Search

Abstract Timely and effective diagnosis of fungal keratitis (FK) is necessary for suitable treatment and avoiding irreversible vision loss for patients. In vivo confocal microscopy (IVCM) has been widely adopted to guide the FK diagnosis. We present a deep learning framework for diagnosing fungal keratitis using IVCM images to assist ophthalmologists. Inspired by the real diagnostic process, our method employs a two-stage deep architecture for diagnostic predictions based on both image-level and sequence-level information. To the best of our knowledge, we collected the largest dataset with 96,632 IVCM images in total with expert labeling to train and evaluate our method. The specificity and sensitivity of our method in diagnosing FK on the unseen test set achieved 96.65% and 97.57%, comparable or better than experienced ophthalmologists. The network can provide image-level, sequence-level and patient-level diagnostic suggestions to physicians. The results show great promise for assisting ophthalmologists in FK diagnosis.

Abstract 3D morphable models (3DMMs) are generative models for face shape and appearance. Recent works impose face recognition constraints on 3DMM shape parameters so that the face shapes of the same person remain consistent. However, the shape parameters of traditional 3DMMs satisfy the multivariate Gaussian distribution. In contrast, the identity embeddings meet the hypersphere distribution, and this conflict makes it challenging for face reconstruction models to preserve the faithfulness and the shape consistency simultaneously. In other words, recognition loss and reconstruction loss can not decrease jointly due to their conflict distribution. To address this issue, we propose the Sphere Face Model (SFM), a novel 3DMM for monocular face reconstruction, preserving both shape fidelity and identity consistency. The core of our SFM is the basis matrix which can be used to reconstruct 3D face shapes, and the basic matrix is learned by adopting a two-stage training approach where 3D and 2D training data are used in the first and second stages, respectively. We design a novel loss to resolve the distribution mismatch, enforcing that the shape parameters have the hyperspherical distribution. Our model accepts 2D and 3D data for constructing the sphere face models. Extensive experiments show that SFM has high representation ability and clustering performance in its shape parameter space. Moreover, it produces high-fidelity face shapes consistently in challenging conditions in monocular face reconstruction. The code will be released at https://github.com/a686432/SIR

Abstract Photo composition is one of the most important factors in the aesthetics of photographs. As a popular application, composition recommendation for a photo focusing on a specific subject has been ignored by recent deep-learning-based composition recommendation approaches. In this paper, we propose a subject-aware image composition recommendation method, SAC-Net, which takes an RGB image and a binary subject window mask as input, and returns good compositions as crops containing the subject. Our model first determines candidate scores for all possible coarse cropping windows. The crops with high candidate scores are selected and further refined by regressing their corner points to generate the output recommended cropping windows. The final scores of the refined crops are predicted by a final score regression module. Unlike existing methods that need to preset several cropping windows, our network is able to automatically regress cropping windows with arbitrary aspect ratios and sizes. We propose novel stability losses for maximizing smoothness when changing cropping windows along with view changes. Experimental results show that our method outperforms state-of-the-art methods not only on the subject-aware image composition recommendation task, but also for general purpose composition recommendation. We also have designed a multistage labeling scheme so that a large amount of ranked pairs can be produced economically. We use this scheme to propose the first subject-aware composition dataset SACD, which contains 2777 images, and more than 5 million composition ranked pairs. The SACD dataset is publicly available at https://cg.cs.tsinghua.edu.cn/SACD/ .

Due to its intuitive stroke-based user interface, edit propagation has wide applications such as image recoloring and relighting, tone editing, image matting, etc. This paper presents a function interpolation method for efficient edit propagation on 360 degree panoramas. Given a panoramic image as input and user-specified strokes as edit hints, our approach adopts an adaptive sampling strategy based on the diversity of local color distribution. By selecting the most representative samples, this strategy can significantly reduce the number of samples. We assume that the projection of the input panorama is known, so that it can be mapped to a 3D unit sphere where the spherical distance metric can be defined. Then edit propagation is formulated as a radial basis function interpolation problem, which can be efficiently solved by using the non-negative linear least squares. We also utilize a multi-resolution strategy and a function look-up table for further acceleration. Experimental results show that our method can efficiently propagate edits on high-resolution panoramas and produce seam-free and smooth editing results.

Abstract There is a steadily growing range of applications that can benefit from facial reconstruction techniques, leading to an increasing demand for reconstruction of high-quality 3D face models. While it is an important expressive part of the human face, the nose has received less attention than other expressive regions in the face reconstruction literature. When applying existing reconstruction methods to facial images, the reconstructed nose models are often inconsistent with the desired shape and expression. In this paper, we propose a coarse-to-fine 3D nose reconstruction and correction pipeline to build a nose model from a single image, where 3D and 2D nose curve correspondences are adaptively updated and refined. We first correct the reconstruction result coarsely using constraints of 3D-2D sparse landmark correspondences, and then heuristically update a dense 3D-2D curve correspondence based on the coarsely corrected result. A final refinement step is performed to correct the shape based on the updated 3D-2D dense curve constraints. Experimental results show the advantages of our method for 3D nose reconstruction over existing methods.

Abstract For many social events such as public performances, multiple hand-held cameras may capture the same event. This footage is often collected by amateur cinematographers who typically have little control over the scene and may not pay close attention to the camera. For these reasons, each individually captured video may fail to cover the whole time of the event, or may lose track of interesting foreground content such as a performer. We introduce a new algorithm that can synthesize a single smooth video sequence of moving foreground objects captured by multiple hand-held cameras. This allows later viewers to gain a cohesive narrative experience that can transition between different cameras, even though the input footage may be less than ideal. We first introduce a graph-based method for selecting a good transition route. This allows us to automatically select good cut points for the hand-held videos, so that smooth transitions can be created between the resulting video shots. We also propose a method to synthesize a smooth photorealistic transition video between each pair of hand-held cameras, which preserves dynamic foreground content during this transition. Our experiments demonstrate that our method outperforms previous state-of-the-art methods, which struggle to preserve dynamic foreground content.

Abstract Researchers have achieved great success in dealing with 2D images using deep learning. In recent years, 3D computer vision and geometry deep learning have gained ever more attention. Many advanced techniques for 3D shapes have been proposed for different applications. Unlike 2D images, which can be uniformly represented by a regular grid of pixels, 3D shapes have various representations, such as depth images, multi-view images, voxels, point clouds, meshes, implicit surfaces, etc. The performance achieved in different applications largely depends on the representation used, and there is no unique representation that works well for all applications. Therefore, in this survey, we review recent developments in deep learning for 3D geometry from a representation perspective, summarizing the advantages and disadvantages of different representations for different applications. We also present existing datasets in these representations and further discuss future research directions.

Abstract We propose a novel end-to-end deep learning framework, the Joint Matting Network (JMNet), to automatically generate alpha mattes for human images. We utilize the intrinsic structures of the human body as seen in images by introducing a pose estimation module, which can provide both global structural guidance and a local attention focus for the matting task. Our network model includes a pose network, a trimap network, a matting network, and a shared encoder to extract features for the above three networks. We also append a trimap refinement module and utilize gradient loss to provide a sharper alpha matte. Extensive experiments have shown that our method outperforms state-of-theart human matting techniques; the shared encoder leads to better performance and lower memory costs. Our model can process real images downloaded from the Internet for use in composition applications.

Abstract Virtual reality (VR) offers an artificial, computer generated simulation of a real life environment. It originated in the 1960s and has evolved to provide increasing immersion, interactivity, imagination, and intelligence. Because deep learning systems are able to represent and compose information at various levels in a deep hierarchical fashion, they can build very powerful models which leverage large quantities of visual media data. Intelligence of VR methods and applications has been significantly boosted by the recent developments in deep learning techniques. VR content creation and exploration relates to image and video analysis, synthesis and editing, so deep learning methods such as fully convolutional networks and general adversarial networks are widely employed, designed specifically to handle panoramic images and video and virtual 3D scenes. This article surveys recent research that uses such deep learning methods for VR content creation and exploration. It considers the problems involved, and discusses possible future directions in this active and emerging research area.

Abstract It is challenging to track a target continuously in videos with long-term occlusion, or objects which leave then re-enter a scene. Existing tracking algorithms combined with onlinetrained object detectors perform unreliably in complex conditions, and can only provide discontinuous trajectories with jumps in position when the object is occluded. This paper proposes a novel framework of tracking-by-detection using selection and completion to solve the abovementioned problems. It has two components, tracking and trajectory completion. An offline-trained object detector can localize objects in the same category as the object being tracked. The object detector is based on a highly accurate deep learning model. The object selector determines which object should be used to re-initialize a traditional tracker. As the object selector is trained online, it allows the framework to be adaptable. During completion, a predictive non-linear autoregressive neural network completes any discontinuous trajectory. The tracking component is an online real-time algorithm, and the completion part is an after-theevent mechanism. Quantitative experiments show a significant improvement in robustness over prior state-of- the-art methods.

Abstract Current image-editing tools do not match up to the demands of personalized image manipulation, one application of which is changing clothes in usercaptured images. Previous work can change single color clothes using parametric human warping methods. In this paper, we propose an image-based clothes changing system, exploiting body factor extraction and content-aware image warping. Image segmentation and mask generation are first applied to the user input. Afterwards, we determine joint positions via a neural network. Then, body shape matching is performed and the shape of the model is warped to the user’s shape. Finally, head swapping is performed to produce realistic virtual results. We also provide a supervision and labeling tool for refinement and further assistance when creating a dataset.

Abstract This paper surveys the state-of-the-art of research in patch-based synthesis. Patch-based methods synthesize output images by copying small regions from exemplar imagery. This line of research originated from an area called “texture synthesis”, which focused on creating regular or semi-regular textures from small exemplars. However, more recently, much research has focused on synthesis of larger and more diverse imagery, such as photos, photo collections, videos, and light fields. Additionally, recent research has focused on customizing the synthesis process for particular problem domains, such as synthesizing artistic or decorative brushes, synthesis of rich materials, and synthesis for 3D fabrication. This report investigates recent papers that follow these themes, with a particular emphasis on papers published since 2009, when the last survey in this area was published. This survey can serve as a tutorial for readers who are not yet familiar with these topics, as well as provide comparisons between these papers, and highlight some open problems in this area.