Search
Results
-
Single Image Depth Prediction Made Better: A Multivariate Gaussian Take
(2023)2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Neural-network-based single image depth prediction (SIDP) is a challenging task where the goal is to predict the scene's per-pixel depth at test time. Since the problem, by definition, is ill-posed, the fundamental goal is to come up with an approach that can reliably model the scene depth from a set of training examples. In the pursuit of perfect depth estimation, most existing state-of-the-art learning techniques predict a single scalar ...Conference Paper -
Enhanced Stable View-Synthesis
(2023)2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)We introduce an approach to enhance the novel view synthesis from images taken from a freely moving camera. The introduced approach focuses on outdoor scenes where recovering accurate geometric scaffold and camera pose is challenging, leading to inferior results using the state-ofthe-art stable view synthesis (SVS) method. SVS and related methods fail for outdoor scenes primarily due to (i) overrelying on the multiview stereo (MVS) for ...Conference Paper -
Organic Priors in Non-rigid Structure from Motion
(2022)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2022This paper advocates the use of organic priors in classical non-rigid structure from motion (NRSfM). By organic priors, we mean invaluable intermediate prior information intrinsic to the NRSfM matrix factorization theory. It is shown that such priors reside in the factorized matrices, and quite surprisingly, existing methods generally disregard them. The paper’s main contribution is to put forward a simple, methodical, and practical method ...Conference Paper -
Generative Flows with Invertible Attentions
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Conference Paper -
Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo
(2022)2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)We present a modern solution to the multi-view photometric stereo problem (MVPS). Our work suitably exploits the image formation model in a MVPS experimental setup to recover the dense 3D reconstruction of an object from images. We procure the surface orientation using a photometric stereo (PS) image formation model and blend it with a multi-view neural radiance field representation to recover the object’s surface geometry. Contrary to ...Conference Paper -
Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo
(2022)2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)We present an automated machine learning approach for uncalibrated photometric stereo (PS). Our work aims at discovering lightweight and computationally efficient PS neural networks with excellent surface normal accuracy. Unlike previous uncalibrated deep PS networks, which are handcrafted and carefully tuned, we leverage differentiable neural architecture search (NAS) strategy to find uncalibrated PS architecture automatically. We begin ...Conference Paper -
Multi-View Photometric Stereo Revisited
(2023)2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)Multi-view photometric stereo (MVPS) is a preferred method for detailed and precise 3D acquisition of an object from images. Although popular methods for MVPS can provide outstanding results, they are often complex to execute and limited to isotropic material objects. To address such limitations, we present a simple, practical ap proach to MVPS, which works well for isotropic as well as other object material types such as anisotropic and ...Conference Paper -
Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces
(2021)2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)This paper presents an uncalibrated deep neural network framework for the photometric stereo problem. For training models to solve the problem, existing neural network-based methods either require exact light directions or ground-truth surface normals of the object or both. However, in practice, it is challenging to procure both of this information precisely, which restricts the broader adoption of photometric stereo algorithms for vision ...Conference Paper -
Quantum Annealing for Single Image Super-Resolution
(2023)2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)This paper proposes a quantum computing-based algorithm to solve the single image super-resolution (SISR) problem. One of the well-known classical approaches for SISR relies on the well-established patch-wise sparse modeling of the problem. Yet, this field’s current state of affairs is that deep neural networks (DNNs) have demonstrated far superior results than traditional approaches. Nevertheless, quantum computing is expected to become ...Conference Paper -
Uncertainty-Aware Deep Multi-View Photometric Stereo
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Conference Paper