Search

We present a new additive image factorization technique that treats images to be composed of multiple latent specular components which can be simply estimated recursively by modulating the sparsity during decomposition. Our model-driven {\em RSFNet} estimates these factors by unrolling the optimization into network layers requiring only a few scalars to be learned. The resultant factors are interpretable by design and can be fused for different image enhancement tasks via a network or combined directly by the user in a controllable fashion. Based on RSFNet, we detail a zero-reference Low Light Enhancement (LLE) application trained without paired or unpaired supervision. Our system improves the state-of-the-art performance on standard benchmarks and achieves better generalization on multiple other datasets. We also integrate our factors with other task specific fusion networks for applications like deraining, deblurring and dehazing with negligible overhead thereby highlighting the multi-domain and multi-task generalizability of our proposed RSFNet. The code and data is released for reproducibility on the project homepage., Comment: CVPR 2024, Pages: 8(main)+4(references)+17(supp) = 29

The focus of recent research has shifted from merely improving the metrics based performance of Deep Neural Networks (DNNs) to DNNs which are more interpretable to humans. The field of eXplainable Artificial Intelligence (XAI) has observed various techniques, including saliency-based and concept-based approaches. These approaches explain the model's decisions in simple human understandable terms called Concepts. Concepts are known to be the thinking ground of humans}. Explanations in terms of concepts enable detecting spurious correlations, inherent biases, or clever-hans. With the advent of concept-based explanations, a range of concept representation methods and automatic concept discovery algorithms have been introduced. Some recent works also use concepts for model improvement in terms of interpretability and generalization. We provide a systematic review and taxonomy of various concept representations and their discovery algorithms in DNNs, specifically in vision. We also provide details on concept-based model improvement literature marking the first comprehensive survey of these methods.

Traditional Radiance Field (RF) representations capture details of a specific scene and must be trained afresh on each scene. Semantic feature fields have been added to RFs to facilitate several segmentation tasks. Generalised RF representations learn the principles of view interpolation. A generalised RF can render new views of an unknown and untrained scene, given a few views. We present a way to distil feature fields into the generalised GNT representation. Our GSN representation generates new views of unseen scenes on the fly along with consistent, per-pixel semantic features. This enables multi-view segmentation of arbitrary new scenes. We show different semantic features being distilled into generalised RFs. Our multi-view segmentation results are on par with methods that use traditional RFs. GSN closes the gap between standard and generalisable RF methods significantly. Project Page: https://vinayak-vg.github.io/GSN/, Comment: Accepted at the Main Technical Track of AAAI 2024

Stylized view generation of scenes captured casually using a camera has received much attention recently. The geometry and appearance of the scene are typically captured as neural point sets or neural radiance fields in the previous work. An image stylization method is used to stylize the captured appearance by training its network jointly or iteratively with the structure capture network. The state-of-the-art SNeRF method trains the NeRF and stylization network in an alternating manner. These methods have high training time and require joint optimization. In this work, we present StyleTRF, a compact, quick-to-optimize strategy for stylized view generation using TensoRF. The appearance part is fine-tuned using sparse stylized priors of a few views rendered using the TensoRF representation for a few iterations. Our method thus effectively decouples style-adaption from view capture and is much faster than the previous methods. We show state-of-the-art results on several scenes used for this purpose., Comment: Accepted at ICVGIP-2022

Precomputed Radiance Transfer (PRT) is widely used for real-time photorealistic effects. PRT disentangles the rendering equation into transfer and lighting, enabling their precomputation. Transfer accounts for the cosine-weighted visibility of points in the scene while lighting for emitted radiance from the environment. Prior art stored precomputed transfer in a tabulated manner, either in vertex or texture space. These values are fetched with interpolation at each point for shading. Vertex space methods require densely tessellated mesh vertices for high quality images. Texture space methods require non-overlapping and area-preserving UV mapping to be available. They also require a high-resolution texture to avoid rendering artifacts. In this paper, we propose a compact transfer representation that is learnt directly on scene geometry points. Specifically, we train a small multi-layer perceptron (MLP) to predict the transfer at sampled surface points. Our approach is most beneficial where inherent mesh storage structure and natural UV mapping are not available, such as Implicit Surfaces as it learns the transfer values directly on the surface. We demonstrate real-time, photorealistic renderings of diffuse and glossy materials on SDF geometries with PRT using our approach., Comment: Accepted at ICVGIP 2022

We present PanoHDR-NeRF, a neural representation of the full HDR radiance field of an indoor scene, and a pipeline to capture it casually, without elaborate setups or complex capture protocols. First, a user captures a low dynamic range (LDR) omnidirectional video of the scene by freely waving an off-the-shelf camera around the scene. Then, an LDR2HDR network uplifts the captured LDR frames to HDR, which are used to train a tailored NeRF++ model. The resulting PanoHDR-NeRF can render full HDR images from any location of the scene. Through experiments on a novel test dataset of real scenes with the ground truth HDR radiance captured at locations not seen during training, we show that PanoHDR-NeRF predicts plausible HDR radiance from any scene point. We also show that the predicted radiance can synthesize correct lighting effects, enabling the augmentation of indoor scenes with synthetic objects that are lit correctly. Datasets and code are available at https://lvsn.github.io/PanoHDR-NeRF/., Comment: BMVC 2022

Recent advancements in deep learning have enabled 3D human body reconstruction from a monocular image, which has broad applications in multiple domains. In this paper, we propose SHARP (SHape Aware Reconstruction of People in loose clothing), a novel end-to-end trainable network that accurately recovers the 3D geometry and appearance of humans in loose clothing from a monocular image. SHARP uses a sparse and efficient fusion strategy to combine parametric body prior with a non-parametric 2D representation of clothed humans. The parametric body prior enforces geometrical consistency on the body shape and pose, while the non-parametric representation models loose clothing and handle self-occlusions as well. We also leverage the sparseness of the non-parametric representation for faster training of our network while using losses on 2D maps. Another key contribution is 3DHumans, our new life-like dataset of 3D human body scans with rich geometrical and textural details. We evaluate SHARP on 3DHumans and other publicly available datasets and show superior qualitative and quantitative performance than existing state-of-the-art methods., Comment: 20 pages

Precomputed Radiance Transfer (PRT) can achieve high quality renders of glossy materials at real-time framerates. PRT involves precomputing a k-dimensional transfer vector of Spherical Harmonic (SH) coefficients at specific points for a scene. Most prior art precomputes transfer at vertices of the mesh and interpolates color for interior points. They require finer mesh tessellations for high quality renderings. In this paper, we explore and present the use of textures for storing transfer. Using transfer textures decouples mesh resolution from transfer storage and sampling which is useful especially for glossy renders. We further demonstrate glossy inter-reflections by precomputing additional textures. We thoroughly discuss practical aspects of transfer textures and analyze their performance in real-time rendering applications. We show equivalent or higher render quality and FPS and demonstrate results on several challenging scenes., Comment: Eurographics 2022 - Poster

Linearly Transformed Cosines (LTCs) are a family of distributions that are used for real-time area-light shading thanks to their analytic integration properties. Modern game engines use an LTC approximation of the ubiquitous GGX model, but currently this approximation only exists for isotropic GGX and thus anisotropic GGX is not supported. While the higher dimensionality presents a challenge in itself, we show that several additional problems arise when fitting, post-processing, storing, and interpolating LTCs in the anisotropic case. Each of these operations must be done carefully to avoid rendering artifacts. We find robust solutions for each operation by introducing and exploiting invariance properties of LTCs. As a result, we obtain a small $8^4$ look-up table that provides a plausible and artifact-free LTC approximation to anisotropic GGX and brings it to real-time area-light shading., Comment: ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D), 2022

We present a neural rendering framework for simultaneous view synthesis and appearance editing of a scene from multi-view images captured under known environment illumination. Existing approaches either achieve view synthesis alone or view synthesis along with relighting, without direct control over the scene's appearance. Our approach explicitly disentangles the appearance and learns a lighting representation that is independent of it. Specifically, we independently estimate the BRDF and use it to learn a lighting-only representation of the scene. Such disentanglement allows our approach to generalize to arbitrary changes in appearance while performing view synthesis. We show results of editing the appearance of a real scene, demonstrating that our approach produces plausible appearance editing. The performance of our view synthesis approach is demonstrated to be at par with state-of-the-art approaches on both real and synthetic data.

3D human body reconstruction from monocular images is an interesting and ill-posed problem in computer vision with wider applications in multiple domains. In this paper, we propose SHARP, a novel end-to-end trainable network that accurately recovers the detailed geometry and appearance of 3D people in loose clothing from a monocular image. We propose a sparse and efficient fusion of a parametric body prior with a non-parametric peeled depth map representation of clothed models. The parametric body prior constraints our model in two ways: first, the network retains geometrically consistent body parts that are not occluded by clothing, and second, it provides a body shape context that improves prediction of the peeled depth maps. This enables SHARP to recover fine-grained 3D geometrical details with just L1 losses on the 2D maps, given an input image. We evaluate SHARP on publicly available Cloth3D and THuman datasets and report superior performance to state-of-the-art approaches.

An image captured with a wide-aperture camera exhibits a finite depth-of-field, with focused and defocused pixels. A compact and robust representation of focus and defocus helps analyze and manipulate such images. In this work, we study the fine characteristics of images with a shallow depth-of-field in the context of focal stacks. We present a composite measure for focus that is a combination of existing measures. We identify in-focus pixels, dual-focus pixels, pixels that exhibit bokeh and spatially-varying blur kernels between focal slices. We use these to build a novel representation that facilitates easy manipulation of focal stacks. We present a comprehensive algorithm for post-capture refocusing in a geometrically correct manner. Our approach can refocus the scene at high fidelity while preserving fine aspects of focus and defocus blur.

We introduce PeeledHuman - a novel shape representation of the human body that is robust to self-occlusions. PeeledHuman encodes the human body as a set of Peeled Depth and RGB maps in 2D, obtained by performing ray-tracing on the 3D body model and extending each ray beyond its first intersection. This formulation allows us to handle self-occlusions efficiently compared to other representations. Given a monocular RGB image, we learn these Peeled maps in an end-to-end generative adversarial fashion using our novel framework - PeelGAN. We train PeelGAN using a 3D Chamfer loss and other 2D losses to generate multiple depth values per-pixel and a corresponding RGB field per-vertex in a dual-branch setup. In our simple non-parametric solution, the generated Peeled Depth maps are back-projected to 3D space to obtain a complete textured 3D shape. The corresponding RGB maps provide vertex-level texture details. We compare our method with current parametric and non-parametric methods in 3D reconstruction and find that we achieve state-of-the-art-results. We demonstrate the effectiveness of our representation on publicly available BUFF and MonoPerfCap datasets as well as loose clothing data collected by our calibrated multi-Kinect setup.

Photo realism in computer generated imagery is crucially dependent on how well an artist is able to recreate real-world materials in the scene. The workflow for material modeling and editing typically involves manual tweaking of material parameters and uses a standard path tracing engine for visual feedback. A lot of time may be spent in iterative selection and rendering of materials at an appropriate quality. In this work, we propose a convolutional neural network based workflow which quickly generates high-quality ray traced material visualizations on a shaderball. Our novel architecture allows for control over environment lighting and assists material selection along with the ability to render spatially-varying materials. Additionally, our network enables control over environment lighting which gives an artist more freedom and provides better visualization of the rendered material. Comparison with state-of-the-art denoising and neural rendering techniques suggests that our neural renderer performs faster and better. We provide a interactive visualization tool and release our training dataset to foster further research in this area., Comment: 10 pages

Intrinsic Image Decomposition (IID) is a challenging and interesting computer vision problem with various applications in several fields. We present novel semantic priors and an integrated approach for single image IID that involves analyzing image at three hierarchical context levels. Local context priors capture scene properties at each pixel within a small neighbourhood. Mid-level context priors encode object level semantics. Global context priors establish correspondences at the scene level. Our semantic priors are designed on both fixed and flexible regions, using selective search method and Convolutional Neural Network features. Our IID method is an iterative multistage optimization scheme and consists of two complementary formulations: $L_2$ smoothing for shading and $L_1$ sparsity for reflectance. Experiments and analysis of our method indicate the utility of our semantic priors and structured hierarchical analysis in an IID framework. We compare our method with other contemporary IID solutions and show results with lesser artifacts. Finally, we highlight that proper choice and encoding of prior knowledge can produce competitive results even when compared to end-to-end deep learning IID methods, signifying the importance of such priors. We believe that the insights and techniques presented in this paper would be useful in the future IID research.

Monocular head pose estimation requires learning a model that computes the intrinsic Euler angles for pose (yaw, pitch, roll) from an input image of human face. Annotating ground truth head pose angles for images in the wild is difficult and requires ad-hoc fitting procedures (which provides only coarse and approximate annotations). This highlights the need for approaches which can train on data captured in controlled environment and generalize on the images in the wild (with varying appearance and illumination of the face). Most present day deep learning approaches which learn a regression function directly on the input images fail to do so. To this end, we propose to use a higher level representation to regress the head pose while using deep learning architectures. More specifically, we use the uncertainty maps in the form of 2D soft localization heatmap images over five facial keypoints, namely left ear, right ear, left eye, right eye and nose, and pass them through an convolutional neural network to regress the head-pose. We show head pose estimation results on two challenging benchmarks BIWI and AFLW and our approach surpasses the state of the art on both the datasets., Comment: 4 pages, ICASSP 2019

Human actions comprise of joint motion of articulated body parts or `gestures'. Human skeleton is intuitively represented as a sparse graph with joints as nodes and natural connections between them as edges. Graph convolutional networks have been used to recognize actions from skeletal videos. We introduce a part-based graph convolutional network (PB-GCN) for this task, inspired by Deformable Part-based Models (DPMs). We divide the skeleton graph into four subgraphs with joints shared across them and learn a recognition model using a part-based graph convolutional network. We show that such a model improves performance of recognition, compared to a model using entire skeleton graph. Instead of using 3D joint coordinates as node features, we show that using relative coordinates and temporal displacements boosts performance. Our model achieves state-of-the-art performance on two challenging benchmark datasets NTURGB+D and HDM05, for skeletal action recognition., Comment: Main: 13 pages, 3 figures, 2 tables. Supplementary: 5 pages, 3 figures, 1 table. Accepted at BMVC 2018

View-graph is an essential input to large-scale structure from motion (SfM) pipelines. Accuracy and efficiency of large-scale SfM is crucially dependent on the input view-graph. Inconsistent or inaccurate edges can lead to inferior or wrong reconstruction. Most SfM methods remove `undesirable' images and pairs using several, fixed heuristic criteria, and propose tailor-made solutions to achieve specific reconstruction objectives such as efficiency, accuracy, or disambiguation. In contrast to these disparate solutions, we propose a single optimization framework that can be used to achieve these different reconstruction objectives with task-specific cost modeling. We also construct a very efficient network-flow based formulation for its approximate solution. The abstraction brought on by this selection mechanism separates the challenges specific to datasets and reconstruction objectives from the standard SfM pipeline and improves its generalization. This paper demonstrates the application of the proposed view-graph framework with standard SfM pipeline for two particular use-cases, (i) accurate and ghost-free reconstructions of highly ambiguous datasets using costs based on disambiguation priors, and (ii) accurate and efficient reconstruction of large-scale Internet datasets using costs based on commonly used priors., Comment: Submitted to CVPR 2018

Short internet video clips like vines present a significantly wild distribution compared to traditional video datasets. In this paper, we focus on the problem of unsupervised action classification in wild vines using traditional labeled datasets. To this end, we use a data augmentation based simple domain adaptation strategy. We utilise semantic word2vec space as a common subspace to embed video features from both, labeled source domain and unlablled target domain. Our method incrementally augments the labeled source with target samples and iteratively modifies the embedding function to bring the source and target distributions together. Additionally, we utilise a multi-modal representation that incorporates noisy semantic information available in form of hash-tags. We show the effectiveness of this simple adaptation technique on a test set of vines and achieve notable improvements in performance., Comment: 9 pages, GCPR, 2016

Several methods have been proposed for large-scale 3D reconstruction from large, unorganized image collections. A large reconstruction problem is typically divided into multiple components which are reconstructed independently using structure from motion (SFM) and later merged together. Incremental SFM methods are most popular for the basic structure recovery of a single component. They are robust and effective but are strictly sequential in nature. We present a multistage approach for SFM reconstruction of a single component that breaks the sequential nature of the incremental SFM methods. Our approach begins with quickly building a coarse 3D model using only a fraction of features from given images. The coarse model is then enriched by localizing remaining images and matching and triangulating remaining features in subsequent stages. These stages are made efficient and highly parallel by leveraging the geometry of the coarse model. Our method produces similar quality models as compared to incremental SFM methods while being notably fast and parallel.

Parallel computing using accelerators has gained widespread research attention in the past few years. In particular, using GPUs for general purpose computing has brought forth several success stories with respect to time taken, cost, power, and other metrics. However, accelerator based computing has signifi- cantly relegated the role of CPUs in computation. As CPUs evolve and also offer matching computational resources, it is important to also include CPUs in the computation. We call this the hybrid computing model. Indeed, most computer systems of the present age offer a degree of heterogeneity and therefore such a model is quite natural. We reevaluate the claim of a recent paper by Lee et al.(ISCA 2010). We argue that the right question arising out of Lee et al. (ISCA 2010) should be how to use a CPU+GPU platform efficiently, instead of whether one should use a CPU or a GPU exclusively. To this end, we experiment with a set of 13 diverse workloads ranging from databases, image processing, sparse matrix kernels, and graphs. We experiment with two different hybrid platforms: one consisting of a 6-core Intel i7-980X CPU and an NVidia Tesla T10 GPU, and another consisting of an Intel E7400 dual core CPU with an NVidia GT520 GPU. On both these platforms, we show that hybrid solutions offer good advantage over CPU or GPU alone solutions. On both these platforms, we also show that our solutions are 90% resource efficient on average. Our work therefore suggests that hybrid computing can offer tremendous advantages at not only research-scale platforms but also the more realistic scale systems with significant performance gains and resource efficiency to the large scale user community., Comment: 20 pages