Search

The 3D CAD shapes in current 3D benchmarks are mostly collected from online model repositories. Thus, they typically have insufficient geometric details and less informative textures, making them less attractive for comprehensive and subtle research in areas such as high-quality 3D mesh and texture recovery. This paper presents 3D Furniture shape with TextURE (3D-FUTURE): a richly-annotated and large-scale repository of 3D furniture shapes in the household scenario. At the time of this technical report, 3D-FUTURE contains 9992 modern 3D furniture shapes with high-resolution textures and detailed attributes. To support the studies of 3D modeling from images, we couple the CAD models with 20,240 scene images. The room scenes are designed by professional designers or generated by an industrial scene creating system. Given the well-organized 3D-FUTURE and its characteristics, we provide a package of baseline experiments, such as joint 2D instance segmentation and 3D object pose estimation, image-based 3D shape retrieval, 3D object reconstruction from a single image, texture recovery for 3D shapes, and furniture composition, to facilitate related future researches on our database. [ABSTRACT FROM AUTHOR]

The task of texture segmentation is to identify image curves that separate different textures. To segment textured images, one must first be able to discriminate textures. A segmentation algorithm performs texture-discrimination tests at densely spaced image positions, then interprets the results to localize edges. This article focuses on the first stage, texture discrimination. We distinguish between perceptual and physical texture differences: the former differences are those perceived by humans, while the latter, on which we concentrate, are those defined by differences in the processes that create the texture in the scene. Physical texture discrimination requires computing image texture measures that allow the inference of physical differences in texture processes, which in turn requires modeling texture in the scene. We use a simple texture model that describes textures by distributions of shape, position, and color of substructures. From this model, a set of image texture measures is derived that allows reliable texture discrimination. These measures are distributions of overall substructure length, width, and orientation; edge length and orientation; and differences in averaged color. Distributions are estimated without explicitly isolating image substructures. Tests of statistical significance are used to compare texture measures. A forced-choice method for evaluating texture measures is described. The proposed measures provide empirical discrimination accuracy of 84 to 100% on a large set of natural textures. By comparison, Laws' texture measures provide less than 50% accuracy when used with the same texture-edge detector. Finally, the measures can distinguish textures differing in second-order statistics, although those statistics are not explicitly measured. [ABSTRACT FROM AUTHOR]

Image texture provides a rich visual description of the surfaces in the scene. Many texture signatures based on various statistical descriptions and various local measurements have been developed. Existing signatures, in general, are not invariant to 3D geometric transformations, which is a serious limitation for many applications. In this paper we introduce a new texture signature, called the multifractal spectrum (MFS). The MFS is invariant under the bi-Lipschitz map, which includes view-point changes and non-rigid deformations of the texture surface, as well as local affine illumination changes. It provides an efficient framework combining global spatial invariance and local robust measurements. Intuitively, the MFS could be viewed as a “better histogram” with greater robustness to various environmental changes and the advantage of capturing some geometrical distribution information encoded in the texture. Experiments demonstrate that the MFS codes the essential structure of textures with very low dimension, and thus represents an useful tool for texture classification. [ABSTRACT FROM AUTHOR]

Textured surfaces are an inherent constituent of the natural surroundings, therefore efficient real-world applications of computer vision algorithms require precise surface descriptors. Often textured surfaces present not only variations of color or reflectance, but also local height variations. This type of surface is referred to as a 3D texture. As the lighting and viewing conditions are varied, effects such as shadowing, foreshortening and occlusions, give rise to significant changes in texture appearance. Accounting for the variation of texture appearance due to changes in imaging parameters is a key issue in developing accurate 3D texture models. The bidirectional texture function (BTF) is observed image texture as a function of viewing and illumination directions. In this work, we construct a BTF-based surface model which captures the variation of the underlying statistical distribution of local structural image features, as the viewing and illumination conditions are changed. This 3D texture representation is called the bidirectional feature histogram (BFH). Based on the BFH, we design a 3D texture recognition method which employs the BFH as the surface model, and classifies surfaces based on a single novel texture image of unknown imaging parameters. Also, we develop a computational method for quantitatively evaluating the relative significance of texture images within the BTF. The performance of our methods is evaluated by employing over 6200 texture images corresponding to 40 real-world surface samples from the CUReT (Columbia-Utrecht reflectance and texture) database. Our experiments produce excellent classification results, which validate the strong descriptive properties of the BFH as a 3D texture representation. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel image coding framework with semantic-aware visual decomposition towards extremely low bitrate compression. In particular, an input image is analyzed into a semantic map as structural representation and semantic-wise texture representation and further compressed into bitstreams at the encoder side. On the decoder side, the received bitstreams of dual-layer representations are decoded and reconstructed for target image synthesis with generative models. Moreover, the attention mechanism is introduced into the model architecture for texture representation modeling and a coherency regularization is proposed to further optimize the texture representation space by aligning the representation space with the source pixel space for higher synthesis quality. Besides, we also propose a cross-channel entropy module and control the quantization scale to facilitate rate-distortion optimization. Upon compressing the decomposed components into the bitstream, the simple yet effective representation philosophy benefits image compression in many aspects. First, in terms of compression performance, compact representations, and high visual synthesis quality can bring remarkable advantages. Second, the proposed framework yields a physically explainable bitstream composed of the structural segment and semantic-wise texture segments. Third and most importantly, subsequent vision tasks (e.g., content manipulation) can receive fundamental support from the semantic-aware visual decomposition and synthesis mechanism. Extensive experimental results demonstrate the superiority of the proposed framework towards efficient visual representation learning, high efficiency image compression ( < 0.1 bpp), and intelligent visual applications (e.g., manipulation and analysis). [ABSTRACT FROM AUTHOR]

Contextual information contained within human environments, such as text on signs, symbols and objects provide important information for robots to use for exploration and navigation. To identify and segment contextual information from images obtained in these environments data-driven methods such as Convolutional Neural Networks (CNNs) can be used. However, these methods require significant amounts of human labeled data which is time-consuming to obtain. In this paper, we present the novel Weakly Supervised Mask Data Distillation (WeSuperMaDD) architecture for autonomously generating pseudo segmentation labels (PSLs) using CNNs not specifically trained for the task of text segmentation, e.g., CNNs alternatively trained for: object classification or image captioning. WeSuperMaDD is uniquely able to generate PSLs using learned image features from datasets that are sparse and with limited diversity, which are common in robot navigation tasks in human-centred environments (i.e., malls, stores). Our proposed architecture uses a new mask refinement system which automatically searches for the PSL with the fewest foreground pixels that satisfies cost constraints. This removes the need for handcrafted heuristic rules. Extensive experiments were conducted to validate the performance of WeSuperMaDD in generating PSLs for datasets containing text of various scales, fonts, orientations, curvatures, and perspectives in several indoor/outdoor environments. A detailed comparison study conducted with existing approaches found a significant improvement in PSL quality. Furthermore, an instance segmentation CNN trained using the WeSuperMaDD architecture achieved measurable improvements in accuracy when compared to an instance segmentation CNN trained with Naïve PSLs. We also found our method to have comparable performance to existing text detection methods. [ABSTRACT FROM AUTHOR]

The creation or manipulation of facial appearance through deep generative approaches, known as DeepFake, have achieved significant progress and promoted a wide range of benign and malicious applications, e.g., visual effect assistance in movie and misinformation generation by faking famous persons. The evil side of this new technique poses another popular study, i.e., DeepFake detection aiming to identify the fake faces from the real ones. With the rapid development of the DeepFake-related studies in the community, both sides (i.e., DeepFake generation and detection) have formed the relationship of battleground, pushing the improvements of each other and inspiring new directions, e.g., the evasion of DeepFake detection. Nevertheless, the overview of such battleground and the new direction is unclear and neglected by recent surveys due to the rapid increase of related publications, limiting the in-depth understanding of the tendency and future works. To fill this gap, in this paper, we provide a comprehensive overview and detailed analysis of the research work on the topic of DeepFake generation, DeepFake detection as well as evasion of DeepFake detection, with more than 318 research papers carefully surveyed. We present the taxonomy of various DeepFake generation methods and the categorization of various DeepFake detection methods, and more importantly, we showcase the battleground between the two parties with detailed interactions between the adversaries (DeepFake generation) and the defenders (DeepFake detection). The battleground allows fresh perspective into the latest landscape of the DeepFake research and can provide valuable analysis towards the research challenges and opportunities as well as research trends and future directions. We also elaborately design interactive diagrams (http://www.xujuefei.com/dfsurvey) to allow researchers to explore their own interests on popular DeepFake generators or detectors. [ABSTRACT FROM AUTHOR]

A 3D scene is more than the geometry and classes of the objects it comprises. An essential aspect beyond object-level perception is the scene context, described as a dense semantic network of interconnected nodes. Scene graphs have become a common representation to encode the semantic richness of images, where nodes in the graph are object entities connected by edges, so-called relationships. Such graphs have been shown to be useful in achieving state-of-the-art performance in image captioning, visual question answering and image generation or editing. While scene graph prediction methods so far focused on images, we propose instead a novel neural network architecture for 3D data, where the aim is to learn to regress semantic graphs from a given 3D scene. With this work, we go beyond object-level perception, by exploring relations between object entities. Our method learns instance embeddings alongside a scene segmentation and is able to predict semantics for object nodes and edges. We leverage 3DSSG, a large scale dataset based on 3RScan that features scene graphs of changing 3D scenes. Finally, we show the effectiveness of graphs as an intermediate representation on a retrieval task. [ABSTRACT FROM AUTHOR]

Three dimensional surface corrugations on globally smooth surfaces give rise to brightness modulations of global shading patterns. We study systematic variations of such 3D image texture as a function of illumination and viewing geometry. The 3D texture is especially noticeable near the shadow terminator (for collimated illumination) or near the dark pole (for hemispherical diffuse illumination). We find that a simple micro-facet model, assuming locally Lambertian scattering, suffices to robustly describe texture contrast gradients of a large variety (measured and rendered textures; laboratory and field conditions) in a semi-quantitative manner. Robust statistical measures of the texture allows one to draw inferences concerning the nature of the light field (collimated to diffuse) and of surface roughness parameters, which can be used as input to the simplest BRDF models. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach for synthesizing facial affect; either in terms of the six basic expressions (i.e., anger, disgust, fear, joy, sadness and surprise), or in terms of valence (i.e., how positive or negative is an emotion) and arousal (i.e., power of the emotion activation). The proposed approach accepts the following inputs:(i) a neutral 2D image of a person; (ii) a basic facial expression or a pair of valence-arousal (VA) emotional state descriptors to be generated, or a path of affect in the 2D VA space to be generated as an image sequence. In order to synthesize affect in terms of VA, for this person, 600,000 frames from the 4DFAB database were annotated. The affect synthesis is implemented by fitting a 3D Morphable Model on the neutral image, then deforming the reconstructed face and adding the inputted affect, and blending the new face with the given affect into the original image. Qualitative experiments illustrate the generation of realistic images, when the neutral image is sampled from fifteen well known lab-controlled or in-the-wild databases, including Aff-Wild, AffectNet, RAF-DB; comparisons with generative adversarial networks (GANs) show the higher quality achieved by the proposed approach. Then, quantitative experiments are conducted, in which the synthesized images are used for data augmentation in training deep neural networks to perform affect recognition over all databases; greatly improved performances are achieved when compared with state-of-the-art methods, as well as with GAN-based data augmentation, in all cases. [ABSTRACT FROM AUTHOR]

Foreground object segmentation is a critical step for many image analysis tasks. While automated methods can produce high-quality results, their failures disappoint users in need of practical solutions. We propose a resource allocation framework for predicting how best to allocate a fixed budget of human annotation effort in order to collect higher quality segmentations for a given batch of images and automated methods. The framework is based on a prediction module that estimates the quality of given algorithm-drawn segmentations. We demonstrate the value of the framework for two novel tasks related to predicting how to distribute annotation efforts between algorithms and humans. Specifically, we develop two systems that automatically decide, for a batch of images, when to recruit humans versus computers to create (1) coarse segmentations required to initialize segmentation tools and (2) final, fine-grained segmentations. Experiments demonstrate the advantage of relying on a mix of human and computer efforts over relying on either resource alone for segmenting objects in images coming from three diverse modalities (visible, phase contrast microscopy, and fluorescence microscopy). [ABSTRACT FROM AUTHOR]

Texture is a fundamental characteristic of many types of images, and texture representation is one of the essential and challenging problems in computer vision and pattern recognition which has attracted extensive research attention over several decades. Since 2000, texture representations based on Bag of Words and on Convolutional Neural Networks have been extensively studied with impressive performance. Given this period of remarkable evolution, this paper aims to present a comprehensive survey of advances in texture representation over the last two decades. More than 250 major publications are cited in this survey covering different aspects of the research, including benchmark datasets and state of the art results. In retrospect of what has been achieved so far, the survey discusses open challenges and directions for future research. [ABSTRACT FROM AUTHOR]

Edge/structure-preserving operations for images aim to smooth images without blurring the edges/structures. Many exemplary edge-preserving filtering methods have recently been proposed to reduce the computational complexity and/or separate structures of different scales. They normally adopt a user-selected scale measurement to control the detail smoothing. However, natural photos contain objects of different sizes, which cannot be described by a single scale measurement. On the other hand, contour analysis is closely related to edge-preserving filtering, and significant progress has recently been achieved. Nevertheless, the majority of state-of-the-art filtering techniques have ignored the successes in this area. Inspired by the fact that learning-based edge detectors significantly outperform traditional manually-designed detectors, this paper proposes a learning-based edge-preserving filtering technique. It synergistically combines the differential operations in edge-preserving filters with the effectiveness of the recent edge detectors for scale-aware filtering. Unlike previous filtering methods, the proposed filters can efficiently extract subjectively meaningful structures from natural scenes containing multiple-scale objects. [ABSTRACT FROM AUTHOR]

Human behavior and affect is inherently a dynamic phenomenon involving temporal evolution of patterns manifested through a multiplicity of non-verbal behavioral cues including facial expressions, body postures and gestures, and vocal outbursts. A natural assumption for human behavior modeling is that a continuous-time characterization of behavior is the output of a linear time-invariant system when behavioral cues act as the input (e.g., continuous rather than discrete annotations of dimensional affect). Here we study the learning of such dynamical system under real-world conditions, namely in the presence of noisy behavioral cues descriptors and possibly unreliable annotations by employing structured rank minimization. To this end, a novel structured rank minimization method and its scalable variant are proposed. The generalizability of the proposed framework is demonstrated by conducting experiments on 3 distinct dynamic behavior analysis tasks, namely (i) conflict intensity prediction, (ii) prediction of valence and arousal, and (iii) tracklet matching. The attained results outperform those achieved by other state-of-the-art methods for these tasks and, hence, evidence the robustness and effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

The unconstrained acquisition of facial data in real-world conditions may result in face images with significant pose variations, illumination changes, and occlusions, affecting the performance of facial landmark localization and recognition methods. In this paper, a novel method, robust to pose, illumination variations, and occlusions is proposed for joint face frontalization and landmark localization. Unlike the state-of-the-art methods for landmark localization and pose correction, where large amount of manually annotated images or 3D facial models are required, the proposed method relies on a small set of frontal images only. By observing that the frontal facial image of both humans and animals, is the one having the minimum rank of all different poses, a model which is able to jointly recover the frontalized version of the face as well as the facial landmarks is devised. To this end, a suitable optimization problem is solved, concerning minimization of the nuclear norm (convex surrogate of the rank function) and the matrix $$\ell _1$$ norm accounting for occlusions. The proposed method is assessed in frontal view reconstruction of human and animal faces, landmark localization, pose-invariant face recognition, face verification in unconstrained conditions, and video inpainting by conducting experiment on 9 databases. The experimental results demonstrate the effectiveness of the proposed method in comparison to the state-of-the-art methods for the target problems. [ABSTRACT FROM AUTHOR]

Detection of surface defects on organic light emitting diode (OLED) panels pose challenges such as irregular shapes and sizes along with varying textures and patterns on the panels. These challenges can be addressed by designing invariant features and training an anomaly detection algorithm such as support vector data description (SVDD). However, these hand designed features may not be capable of handling test datasets that have undergone distributional shift due to changes in lighting configuration or panel specification. This leads to a degradation of the classifier performance. In this paper, we propose a domain adaptation technique for outlier detection called as adaptive support vector data description (A-SVDD) to tackle distributional change in OLED panel datasets. The proposed method aims to learn an incremental classifier based on the existing classifier using an objective function similar to SVDD. We also investigate the application of features called as local inlier-outlier ratios augmented with modified local binary pattern (LBP) for detection of OLED panel defects in the context of SVDD and A-SVDD. In the experiments, the proposed domain adaptation technique is compared with baseline methods and existing approaches to demonstrate its effectiveness. A detailed evaluation of the features was performed in the context of A-SVDD and SVDD on several defects like scratch, spot, stain and pit to demonstrate that the combination of local inlier-outlier ratios and modified LBP significantly increases the detection accuracy. [ABSTRACT FROM AUTHOR]

Various problems in object detection and tracking have attracted researchers to develop methodologies for solving these problems. Occurrence of camouflage is one of such challenges that makes object detection and tracking problems more complex. However, less attention has been given to detect and track camouflaged objects due to complexity of the problem. In this article, we propose a tracking-by-detection algorithm to detect and track camouflaged objects. To increase separability between the camouflaged object and the background, we propose to integrate features (CIELab, histogram of orientation gradients and locally adaptive ternary pattern) from multi-cue (color, shape and texture) to represent a camouflaged object. A probabilistic neural network (PNN) is modified to construct an efficient discriminative appearance model for detecting camouflaged objects in video sequences. A large number of training patterns (many could be redundant) are reduced based on motion of the object in the modified PNN. The modified PNN makes the detection process faster and also increases the detection accuracy. Due to high visual similarity among the camouflaged object and the background, the boundary of camouflaged object is not well defined (i.e., boundary may be smooth and/or discontinuous). In this context, a robust fuzzy energy based active contour model using both global and local information is proposed to extract contour (boundary) of the detected camouflaged object for tracking. We show a realization of the proposed method and demonstrate its performance (both quantitatively and qualitatively) with respect to state-of-the-art techniques on several challenging sequences. Analysis of results concludes that the proposed technique can track camouflaged (fully or partially) objects as well as objects in various complex environments in a better way as compare to the existing ones. [ABSTRACT FROM AUTHOR]

Machine learning has been instrumental in most areas of computer vision, but has not been applied to the problem of stereo matching with similar frequency or success. In this paper, we present a supervised learning approach by defining a set of features that capture various forms of information about each pixel, and then by using them to predict the correctness of stereo matches based on a random forest. We show highly competitive results in predicting the correctness of matches and in confidence estimation, which allows us to rank pixels according to the reliability of their assigned disparities. Moreover, we show how these confidence values can be used to improve the accuracy of disparity maps by integrating them with an MRF-based stereo algorithm. This is an important distinction from current literature that has mainly focused on sparsification by removing potentially erroneous disparities to generate quasi-dense disparity maps. Finally, we demonstrate domain generalization of our method by applying classifiers to datasets different than those they were trained on with minimal loss of accuracy. [ABSTRACT FROM AUTHOR]

This paper presents an approach to estimating the 2.1D sketch from monocular, low-level visual cues. We use a low-level segmenter to partition the image into regions, and, then, estimate their 2.1D sketch, subject to figure-ground and similarity constraints between neighboring regions. The 2.1D sketch assigns a depth ordering to image regions which are expected to correspond to objects and surfaces in the scene. This is cast as a constrained convex optimization problem, and solved within the optimization transfer framework. The optimization objective takes into account the curvature and convexity of parts of region boundaries, appearance, and spatial layout properties of regions. Our new optimization transfer algorithm admits a closed-form expression of the duality gap, and thus allows explicit computation of the achieved accuracy. The algorithm is efficient with quadratic complexity in the number of constraints between image regions. Quantitative and qualitative results on challenging, real-world images of Berkeley segmentation, Geometric Context, and Stanford Make3D datasets demonstrate our high accuracy, efficiency, and robustness. [ABSTRACT FROM AUTHOR]

We refer to the task of recovering the 3D structure of an object or a scene using 2D images as image-based modeling. In this paper, we formulate the task of recovering the 3D structure as a discrete optimization problem solved via energy minimization. In this standard framework of a Markov random field (MRF) defined over the image we present algorithms that allow the user to intuitively interact with the algorithm. We introduce an algorithm where the user guides the process of image-based modeling to find and model the object of interest by manually interacting with the nodes of the graph. We develop end user applications using this algorithm that allow object of interest 3D modeling on a mobile device and 3D printing of the object of interest. We also propose an alternate active learning algorithm that guides the user input. An initial attempt is made at reconstructing the scene without supervision. Given the reconstruction, an active learning algorithm uses intuitive cues to quantify the uncertainty of the algorithm and suggest regions, querying the user to provide support for the uncertain regions via simple scribbles. These constraints are used to update the unary and the pairwise energies that, when solved, lead to better reconstructions. We show through machine experiments and a user study that the proposed approach intelligently queries the users for constraints, and users achieve better reconstructions of the scene faster, especially for scenes with textureless surfaces lacking strong textural or structural cues that algorithms typically require. [ABSTRACT FROM AUTHOR]

Our goal is to detect boundaries of objects or surfaces occurring in an arbitrary image. We present a new approach that discovers boundaries by sequential labeling of a given set of image edges. A visited edge is labeled as on or off a boundary, based on the edge's photometric and geometric properties, and evidence of its perceptual grouping with already identified boundaries. We use both local Gestalt cues (e.g., proximity and good continuation), and the global Helmholtz principle of non-accidental grouping. A new formulation of the Helmholtz principle is specified as the entropy of a layout of image edges. For boundary discovery, we formulate a new, policy iteration algorithm, called SLEDGE. Training of SLEDGE is iterative. In each training image, SLEDGE labels a sequence of edges, which induces loss with respect to the ground truth. These sequences are then used as training examples for learning SLEDGE in the next iteration, such that the total loss is minimized. For extracting image edges that are input to SLEDGE, we use our new, low-level detector. It finds salient pixel sequences that separate distinct textures within the image. On the benchmark Berkeley Segmentation Datasets 300 and 500, our approach proves robust and effective. We outperform the state of the art both in recall and precision for different input sets of image edges. [ABSTRACT FROM AUTHOR]

There have been much interest and a large amount of research on content based image retrieval (CBIR) in recent years due to the ever increasing number of digital images. Texture features play a key role in CBIR. Many texture features exist in literature, however, most of them are neither rotation invariant nor robust to scale and other variations. Texture features based on Gabor filters have been shown with significant advantages over other methods, and they are adopted by MPEG-7 as one of the texture descriptors for image retrieval. In this paper, we propose a rotation invariant curvelet features for texture representation. With systematic analysis and rigorous experiments, we show that the proposed curvelet texture features significantly outperforms the widely used Gabor texture features. A novel region padding method is also proposed to apply curvelet transform to region based image retrieval. Retrieval results from standard image databases show that curvelet features are promising for both texture and region representation. [ABSTRACT FROM AUTHOR]

We consider the Rao geodesic distance (GD) based on the Fisher information as a similarity measure on the manifold of zero-mean multivariate generalized Gaussian distributions (MGGD). The MGGD is shown to be an adequate model for the heavy-tailed wavelet statistics in multicomponent images, such as color or multispectral images. We discuss the estimation of MGGD parameters using various methods. We apply the GD between MGGDs to color texture discrimination in several classification experiments, taking into account the correlation structure between the spectral bands in the wavelet domain. We compare the performance, both in terms of texture discrimination capability and computational load, of the GD and the Kullback-Leibler divergence (KLD). Likewise, both uni- and multivariate generalized Gaussian models are evaluated, characterized by a fixed or a variable shape parameter. The modeling of the interband correlation significantly improves classification efficiency, while the GD is shown to consistently outperform the KLD as a similarity measure. [ABSTRACT FROM AUTHOR]

We present a novel algorithm for segmentation of natural images that harnesses the principle of minimum description length (MDL). Our method is based on observations that a homogeneously textured region of a natural image can be well modeled by a Gaussian distribution and the region boundary can be effectively coded by an adaptive chain code. The optimal segmentation of an image is the one that gives the shortest coding length for encoding all textures and boundaries in the image, and is obtained via an agglomerative clustering process applied to a hierarchy of decreasing window sizes as multi-scale texture features. The optimal segmentation also provides an accurate estimate of the overall coding length and hence the true entropy of the image. We test our algorithm on the publicly available Berkeley Segmentation Dataset. It achieves state-of-the-art segmentation results compared to other existing methods. [ABSTRACT FROM AUTHOR]

The advent of high-resolution digital cameras and sophisticated multi-view stereo algorithms offers the promise of unprecedented geometric fidelity in image-based modeling tasks, but it also puts unprecedented demands on camera calibration to fulfill these promises. This paper presents a novel approach to camera calibration where top-down information from rough camera parameter estimates and the output of a multi-view-stereo system on scaled-down input images is used to effectively guide the search for additional image correspondences and significantly improve camera calibration parameters using a standard bundle adjustment algorithm (Lourakis and Argyros ). The proposed method has been tested on six real datasets including objects without salient features for which image correspondences cannot be found in a purely bottom-up fashion, and objects with high curvature and thin structures that are lost in visual hull construction even with small errors in camera parameters. Three different methods have been used to qualitatively assess the improvements of the camera parameters. The implementation of the proposed algorithm is publicly available at Furukawa and Ponce (). [ABSTRACT FROM AUTHOR]

This paper introduces mesostructure roughness as an effective cue in image segmentation. Mesostructure roughness corresponds to small-scale bumps on the macrostructure (i.e., geometry) of objects. Specifically, the focus is on the texture that is created by the projection of the mesostructure roughness on the camera plane. Three intrinsic images are derived: reflectance, smooth-surface shading and mesostructure roughness shading (meta-texture images). A constructive approach is proposed for computing a meta-texture image by preserving, equalizing and enhancing the underlying surface-roughness across color, brightness and illumination variations. We evaluate the performance on sample images and illustrate quantitatively that different patches of the same material, in an image, are normalized in their statistics despite variations in color, brightness and illumination. We develop an algorithm for segmentation of an image into patches that share salient mesostructure roughness. Finally, segmentation by line-based boundary-detection is proposed and results are provided and compared to known algorithms. [ABSTRACT FROM AUTHOR]

We develop a framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. The approach provides a practical method for learning high-order Markov random field (MRF) models with potential functions that extend over large pixel neighborhoods. These clique potentials are modeled using the Product-of-Experts framework that uses non-linear functions of many linear filter responses. In contrast to previous MRF approaches all parameters, including the linear filters themselves, are learned from training data. We demonstrate the capabilities of this Field-of-Experts model with two example applications, image denoising and image inpainting, which are implemented using a simple, approximate inference scheme. While the model is trained on a generic image database and is not tuned toward a specific application, we obtain results that compete with specialized techniques. [ABSTRACT FROM AUTHOR]

This paper describes a new approach to motion estimation in video. We represent video motion using a set of particles. Each particle is an image point sample with a long-duration trajectory and other properties. To optimize particle trajectories we measure appearance consistency along the particle trajectories and distortion between the particles. The resulting motion representation is useful for a variety of applications and cannot be directly obtained using existing methods such as optical flow or feature tracking. We demonstrate the algorithm on challenging real-world videos that include complex scene geometry, multiple types of occlusion, regions with low texture, and non-rigid deformations. [ABSTRACT FROM AUTHOR]

Recently, “epitomes” were introduced as patch-based probability models that are learned by compiling together a large number of examples of patches from input images. In this paper, we describe how epitomes can be used to model video data and we describe significant computational speedups that can be incorporated into the epitome inference and learning algorithm. In the case of videos, epitomes are estimated so as to model most of the small space-time cubes from the input data. Then, the epitome can be used for various modeling and reconstruction tasks, of which we show results for video super-resolution, video interpolation, and object removal. Besides computational efficiency, an interesting advantage of the epitome as a representation is that it can be reliably estimated even from videos with large amounts of missing data. We illustrate this ability on the task of reconstructing the dropped frames in video broadcast using only the degraded video and also in denoising a severely corrupted video. [ABSTRACT FROM AUTHOR]

The aim in this paper is to use principal geodesic analysis to model the statistical variations for sets of facial needle maps. We commence by showing how to represent the distribution of surface normals using the exponential map. Shape deformations are described using principal geodesic analysis on the exponential map. Using ideas from robust statistics we show how this deformable model may be fitted to facial images in which there is significant self-shadowing. Moreover, we demonstrate that the resulting shape-from-shading algorithm can be used to recover accurate facial shape and albedo from real world images. In particular, the algorithm can effectively fill-in the facial surface when more than 30% of its area is subject to self-shadowing. To investigate the utility of the shape parameters delivered by the method, we conduct experiments with illumination insensitive face recognition. We present a novel recognition strategy in which similarity is measured in the space of the principal geodesic parameters. We also use the recovered shape information to generate illumination normalized prototype images on which recognition can be performed. Finally we show that, from a single input image, we are able to generate the basis images employed by a number of well known illumination-insensitive recognition algorithms. We also demonstrate that the principal geodesics provide an efficient parameterization of the space of harmonic basis images. [ABSTRACT FROM AUTHOR]

Active Appearance Model (AAM) framework is a very useful method that can fit the shape and appearance model to the input image for various image analysis and synthesis problems. However, since the goal of the AAM fitting algorithm is to minimize the residual error between the model appearance and the input image, it often fails to accurately converge to the landmark points of the input image. To alleviate this weakness, we have combined Active Shape Models (ASM) into AAMs, in which ASMs try to find correct landmark points using the local profile model. Since the original objective function of the ASM search is not appropriate for combining these methods, we derive a gradient based iterative method by modifying the objective function of the ASM search. Then, we propose a new fitting method that combines the objective functions of both ASM and AAM into a single objective function in a gradient based optimization framework. Experimental results show that the proposed fitting method reduces the average fitting error when compared with existing fitting methods such as ASM, AAM, and Texture Constrained-ASM (TC-ASM) and improves the performance of facial expression recognition significantly. [ABSTRACT FROM AUTHOR]

In this paper, the automatic annotation task of the 2005 CLEF cross-language image retrieval campaign (ImageCLEF) is described. This paper focuses on the database used, the task setup, and the plans for further medical image annotation tasks in the context of ImageCLEF. Furthermore, a short summary of the results of 2005 is given. The automatic annotation task was added to ImageCLEF in 2005 and provides the first international evaluation of state-of-the-art methods for completely automatic annotation of medical images based on visual properties. The aim of this task is to explore and promote the use of automatic annotation techniques to allow for extracting semantic information from little-annotated medical images. A database of 10.000 images was established and annotated by experienced physicians resulting in 57 classes, each with at least 10 images. Detailed analysis is done regarding the (i) image representation, (ii) classification method, and (iii) learning method. Based on the strong participation of the 2005 campain, future benchmarks are planned. [ABSTRACT FROM AUTHOR]

We present an analysis of the spatial and temporal statistics of “natural” optical flow fields and a novel flow algorithm that exploits their spatial statistics. Training flow fields are constructed using range images of natural scenes and 3D camera motions recovered from hand-held and car-mounted video sequences. A detailed analysis of optical flow statistics in natural scenes is presented and machine learning methods are developed to learn a Markov random field model of optical flow. The prior probability of a flow field is formulated as a Field-of-Experts model that captures the spatial statistics in overlapping patches and is trained using contrastive divergence. This new optical flow prior is compared with previous robust priors and is incorporated into a recent, accurate algorithm for dense optical flow computation. Experiments with natural and synthetic sequences illustrate how the learned optical flow prior quantitatively improves flow accuracy and how it captures the rich spatial structure found in natural scene motion. [ABSTRACT FROM AUTHOR]

A method for recovering a part-based description of human pose from single images of people is described. It is able to perform estimation efficiently in the presence significant background clutter, large foreground variation, self-occlusion and occlusion by other objects. This is achieved through two key developments. Firstly, a new formulation is proposed that allows partial configurations, hypotheses with differing numbers of parts, to be made and compared. This permits efficient global sampling in the presence of self and other object occlusions without prior knowledge of body part visibility. Secondly, a highly discriminatory likelihood model is proposed comprising two complementary components. A boundary component improves upon previous appearance distribution divergence methods by incorporating high-level shape and appearance information and hence better discriminates textured, overlapping body parts. An inter-part component uses appearance similarity of body parts to reduce the number of false-positive, multi-part hypotheses, hence increasing estimation efficiency. Results are presented for challenging images with unknown subject and large variations in subject appearance, scale and pose. [ABSTRACT FROM AUTHOR]

Area-based matching is a fundamental image processing method that obtains displacement between image regions. In addition, the similarity interpolation method to estimate sub-pixel displacement is commonly used to enhance resolution. This paper proposes a novel 2D sub-pixel displacement estimation method based on similarity interpolation. The method estimates the displacement as an intersection point of two lines, which are approximations of zero positions of the partial derivatives with respect to each motion parameter. The proposed method requires a non-iterative computation. Furthermore, the method engenders only slightly higher calculation costs than the conventional similarity interpolation method. Moreover, the method is suitable for hardware implementation. We show that the proposed method can be extended to obtain the N-parameter of image deformation with non-iterative computation. Using similarity measures obtained at discrete positions in the parameter space, our method provides a highly accurate maximum position of the similarity in sub-sampling resolution; that position corresponds to the image deformation parameters. Experimental results using both synthetic and real images demonstrate that our method can estimate parameters more accurately than conventional methods. [ABSTRACT FROM AUTHOR]

We describe a shape from texture method that constructs an estimate of surface geometry using only the deformation of individual texture elements. Our method does not need to use either the boundary of the observed surface or any assumption about the overall distribution of elements.The method assumes that surface texture elements are drawn from a number of different types, each of fixed shape. Neither the shape of the elements nor the number of types need be known in advance. We show that, with this assumption and assuming a generic, scaled orthographic view and texture, each type of texture element can be reconstructed in a frontal coordinate system from image instances. Interest-point methods supply a method of simultaneously obtaining instances of each texture element automatically and defining each type of element. Furthermore, image instances that have been marked in error can be identified and ignored using the Expectation-Maximization algorithm. A further EM procedure yields a surface reconstruction and a relative irradiance map from the data. We provide numerous examples of reconstructions for images of real scenes, show a comparison between our reconstruction and range maps, and demonstrate that the reconstructions display geometric and irradiance phenomena that can be observed in the original image. [ABSTRACT FROM AUTHOR]

Local image features or interest points provide compact and abstract representations of patterns in an image. In this paper, we extend the notion of spatial interest points into the spatio-temporal domain and show how the resulting features often reflect interesting events that can be used for a compact representation of video data as well as for interpretation of spatio-temporal events. To detect spatio-temporal events, we build on the idea of the Harris and Förstner interest point operators and detect local structures in space-time where the image values have significant local variations in both space and time. We estimate the spatio-temporal extents of the detected events by maximizing a normalized spatio-temporal Laplacian operator over spatial and temporal scales. To represent the detected events, we then compute local, spatio-temporal, scale-invariant N-jets and classify each event with respect to its jet descriptor. For the problem of human motion analysis, we illustrate how a video representation in terms of local space-time features allows for detection of walking people in scenes with occlusions and dynamic cluttered backgrounds. [ABSTRACT FROM AUTHOR]

In this paper we present a Bayesian framework for parsing images into their constituent visual patterns. The parsing algorithm optimizes the posterior probability and outputs a scene representation as a “parsing graph”, in a spirit similar to parsing sentences in speech and natural language. The algorithmconstructsthe parsing graph andre-configuresit dynamically using a set of moves, which are mostly reversible Markov chain jumps. This computational framework integrates two popular inference approaches-generative(top-down) methods anddiscriminative(bottom-up) methods. The former formulates the posterior probability in terms of generative models for images defined by likelihood functions and priors. The latter computes discriminative probabilities based on a sequence (cascade) of bottom-up tests/filters. In our Markov chain algorithm design, the posterior probability, defined by the generative models, is the invariant (target) probability for the Markov chain, and the discriminative probabilities are used to construct proposal probabilities to drive the Markov chain. Intuitively, the bottom-up discriminative probabilities activate top-down generative models. In this paper, we focus on two types of visual patterns-generic visual patterns, such as texture and shading, and object patterns including human faces and text. These types of patterns compete and cooperate to explain the image and so image parsing unifies image segmentation, object detection, and recognition (if we use generic visual patterns only then image parsing will correspond to image segmentation (Tu and Zhu, 2002.IEEE Trans. PAMI, 24(5):657-673). We illustrate our algorithm on natural images of complex city scenes and show examples where image segmentation can be improved by allowing object specific knowledge to disambiguate low-level segmentation cues, and conversely where object detection can be improved by using generic visual patterns to explain away shadows and occlusions. [ABSTRACT FROM AUTHOR]

We integrate a model for filter response statistics of natural images into a variational framework for image segmentation. Incorporated in a sound probabilistic distance measure, the model drives level sets toward meaningful segmentations of complex textures and natural scenes. Despite its enhanced descriptive power, our approach preserves the efficiency of level set based segmentation since each region comprises two model parameters only. Analyzing thousands of natural images we select suitable filter banks, validate the statistical basis of our model, and demonstrate that it outperforms variational segmentation methods using second-order statistics. [ABSTRACT FROM AUTHOR]

This paper presents a novel variational framework to deal with frame partition problems in Computer Vision. This framework exploits boundary and region-based segmentation modules under a curve-based optimization objective function. The task of supervised texture segmentation is considered to demonstrate the potentials of the proposed framework. The textured feature space is generated by filtering the given textured images using isotropic and anisotropic filters, and analyzing their responses as multi-component conditional probability density functions. The texture segmentation is obtained by unifying region and boundary-based information as an improved Geodesic Active Contour Model. The defined objective function is minimized using a gradient-descent method where a level set approach is used to implement the obtained PDE. According to this PDE, the curve propagation towards the final solution is guided by boundary and region-based segmentation forces, and is constrained by a regularity force. The level set implementation is performed using a fast front propagation algorithm where topological changes are naturally handled. The performance of our method is demonstrated on a variety of synthetic and real textured frames. [ABSTRACT FROM AUTHOR]

We describe a learning-based method for low-level vision problems—estimating scenes from images. We generate a synthetic world of scenes and their corresponding rendered images, modeling their relationships with a Markov network. Bayesian belief propagation allows us to efficiently find a local maximum of the posterior probability for the scene, given an image. We call this approach VISTA—Vision by Image/Scene TrAining. We apply VISTA to the “super-resolution” problem (estimating high frequency details from a low-resolution image), showing good results. To illustrate the potential breadth of the technique, we also apply it in two other problem domains, both simplified. We learn to distinguish shading from reflectance variations in a single image under particular lighting conditions. For the motion estimation problem in a “blobs world”, we show figure/ground discrimination, solution of the aperture problem, and filling-in arising from application of the same probabilistic machinery. [ABSTRACT FROM AUTHOR]

We present a universal statistical model for texture images in the context of an overcomplete complex wavelet transform. The model is parameterized by a set of statistics computed on pairs of coefficients corresponding to basis functions at adjacent spatial locations, orientations, and scales. We develop an efficient algorithm for synthesizing random images subject to these constraints, by iteratively projecting onto the set of images satisfying each constraint, and we use this to test the perceptual validity of the model. In particular, we demonstrate the necessity of subgroups of the parameter set by showing examples of texture synthesis that fail when those parameters are removed from the set. We also demonstrate the power of our model by successfully synthesizing examples drawn from a diverse collection of artificial and natural textures. [ABSTRACT FROM AUTHOR]

An overview is given of a vision system for locating, recognising and tracking multiple vehicles, using an image sequence taken by a single camera mounted on a moving vehicle. The camera motion is estimated by matching features on the ground plane from one image to the next. Vehicle detection and hypothesis generation are performed using template correlation and a 3D wire frame model of the vehicle is fitted to the image. Once detected and identified, vehicles are tracked using dynamic filtering. A separate batch mode filter obtains the 3D trajectories of nearby vehicles over an extended time. Results are shown for a motorway image sequence. [ABSTRACT FROM AUTHOR]

Herein we propose a complete procedure to analyze and classify the texture of an image. We apply this scheme to solve a specific image processing problem: urban areas detection in satellite images. First we propose to analyze the texture through the modelling of the luminance field with eight different chain-based models. We then derived a texture parameter from these models. The effect of the lattice anisotropy is corrected by a renormalization group technique coming from statistical physics. This parameter, which takes into account local conditional variances of the image, is compared to classical methods of texture analysis. Afterwards we develop a modified fuzzy Cmeans algorithm that includes an entropy term. The advantage of such an algorithm is that the number of classes does not need to be known a priori. Besides this algorithm provides us with further information, i.e. the probability that a given pixel belongs to a given cluster. Finally we introduce this information in a Markovian model of segmentation. Some results on SPOT5 simulated images, SPOT3 images and ERS1 radar images are presented. These images are provided by the French National Space Agency (CNES) and the European Space Agency (ESA). [ABSTRACT FROM AUTHOR]

We call “natural” image any photograph of an outdoor or indoor scene taken by a standard camera. We discuss the physical generation process of natural images as a combination of occlusions, transparencies and contrast changes. This description fits to the phenomenological description of Gaetano Kanizsa according to which visual perception tends to remain stable with respect to these basic operations. We define a contrast invariant presentation of the digital image, the topographic map, where the subjacent occlusion-transparency structure is put into evidence by the interplay of level lines. We prove that each topographic map represents a class of images invariant with respect to local contrast changes. Several visualization strategies of the topographic map are proposed and implemented and mathematical arguments are developed to establish stability properties of the topographic map under digitization. [ABSTRACT FROM AUTHOR]

The fact that objects in the world appear in different ways depending on the scale of observation has important implications if one aims at describing them. It shows that the notion of scale is of utmost importance when processing unknown measurement data by automatic methods. In their seminal works, Witkin (1983) and Koenderink (1984) proposed to approach this problem by representing image structures at different scales in a so-called scale-space representation. Traditional scale-space theory building on this work, however, does not address the problem of how to select local appropriate scales for further analysis. This article proposes a systematic methodology for dealing with this problem. A framework is presented for generating hypotheses about interesting scale levels in image data, based on a general principle stating that local extrema over scales of different combinations of γ-normalized derivatives are likely candidates to correspond to interesting structures. Specifically, it is shown how this idea can be used as a major mechanism in algorithms for automatic scale selection, which adapt the local scales of processing to the local image structure. Support for the proposed approach is given in terms of a general theoretical investigation of the behaviour of the scale selection method under rescalings of the input pattern and by integration with different types of early visual modules, including experiments on real-world and synthetic data. Support is also given by a detailed analysis of how different types of feature detectors perform when integrated with a scale selection mechanism and then applied to characteristic model patterns. Specifically, it is described in detail how the proposed methodology applies to the problems of blob detection, junction detection, edge detection, ridge detection and local frequency estimation. In many computer vision applications, the poor performance of the low-level vision modules constitutes a major bottleneck. It is argued that the inclusion of mechanisms for automatic scale selection is essential if we are to construct vision systems to automatically analyse complex unknown environments. [ABSTRACT FROM AUTHOR]

A fundamental problem in depth from defocus is the measurement of relative defocus between images. The performance of previously proposed focus operators are inevitably sensitive to the frequency spectra of local scene textures. As a result, focus operators such as the Laplacian of Gaussian result in poor depth estimates. An alternative is to use large filter banks that densely sample the frequency space. Though this approach can result in better depth accuracy, it sacrifices the computational efficiency that depth from defocus offers over stereo and structure from motion. We propose a class of broadband operators that, when used together, provide invariance to scene texture and produce accurate and dense depth maps. Since the operators are broadband, a small number of them are sufficient for depth estimation of scenes with complex textural properties. In addition, a depth confidence measure is derived that can be computed from the outputs of the operators. This confidence measure permits further refinement of computed depth maps. Experiments are conducted on both synthetic and real scenes to evaluate the performance of the proposed operators. The depth detection gain error is less than 1%, irrespective of texture frequency. Depth accuracy is found to be 0.5∼1.2% of the distance of the object from the imaging optics. [ABSTRACT FROM AUTHOR]

A structure from motion algorithm is described which recovers structure and camera position, modulo a projective ambiguity. Camera calibration is not required, and camera parameters such as focal length can be altered freely during motion. The structure is updated sequentially over an image sequence, in contrast to schemes which employ a batch process. A specialisation of the algorithm to recover structure and camera position modulo an affine transformation is described, together with a method to periodically update the affine coordinate frame to prevent drift over time. We describe the constraint used to obtain this specialisation. Structure is recovered from image corners detected and matched automatically and reliably in real image sequences. Results are shown for reference objects and indoor environments, and accuracy of recovered structure is fully evaluated and compared for a number of reconstruction schemes. A specific application of the work is demonstrated—affine structure is used to compute free space maps enabling navigation through unstructured environments and avoidance of obstacles. The path planning involves only affine constructions. [ABSTRACT FROM AUTHOR]

Traditional optical flow algorithms assume local image translational motion and apply simple image filtering techniques. Recent studies have taken two separate approaches toward improving the accuracy of computed flow: the application of spatio-temporal filtering schemes and the use of advanced motion models such as the affine model. Each has achieved some improvement over traditional algorithms in specialized situations but the computation of accurate optical flow for general motion has been elusive. In this paper, we exploit the interdependency between these two approaches and propose a unified approach. The general motion model we adopt characterizes arbitrary 3-D steady motion. Under perspective projection, we derive an image motion equation that describes the spatio-temporal relation of gray-scale intensity in an image sequence, thus making the utilization of 3-D filtering possible. However, to accommodate this motion model, we need to extend the filter design to derive additional motion constraint equations. Using Hermite polynomials, we design differentiation filters, whose orthogonality and Gaussian derivative properties insure numerical stability; a recursive relation facilitates application of the general nonlinear motion model while separability promotes efficiency. The resulting algorithm produces accurate optical flow and other useful motion parameters. It is evaluated quantitatively using the scheme established by Barron et al. (1994) and qualitatively with real images. [ABSTRACT FROM AUTHOR]