English
Related papers

Related papers: Differentiable Stereopsis: Meshes from multiple vi…

200 papers

Three-dimensional (3D) object reconstruction based on differentiable rendering (DR) is an active research topic in computer vision. DR-based methods minimize the difference between the rendered and target images by optimizing both the shape…

Computer Vision and Pattern Recognition · Computer Science 2022-11-23 Chunyu Li , Taisuke Hashimoto , Eiichi Matsumoto , Hiroharu Kato

This paper introduces a novel deep framework for dense 3D reconstruction from multiple image frames, leveraging a sparse set of depth measurements gathered jointly with image acquisition. Given a deep multi-view stereo network, our…

Computer Vision and Pattern Recognition · Computer Science 2022-10-21 Matteo Poggi , Andrea Conti , Stefano Mattoccia

Rendering bridges the gap between 2D vision and 3D scenes by simulating the physical process of image formation. By inverting such renderer, one can think of a learning approach to infer 3D information from 2D images. However, standard…

Computer Vision and Pattern Recognition · Computer Science 2019-04-04 Shichen Liu , Tianye Li , Weikai Chen , Hao Li

Photometric stereo leverages variations in illumination conditions to reconstruct surface normals. Display photometric stereo, which employs a conventional monitor as an illumination source, has the potential to overcome limitations often…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Seokjun Choi , Seungwoo Yoon , Giljoo Nam , Seungyong Lee , Seung-Hwan Baek

Primitive-based splatting methods like 3D Gaussian Splatting have revolutionized novel view synthesis with real-time rendering. However, their point-based representations remain incompatible with mesh-based pipelines that power AR/VR and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Jan Held , Sanghyun Son , Renaud Vandeghen , Daniel Rebain , Matheus Gadelha , Yi Zhou , Anthony Cioppa , Ming C. Lin , Marc Van Droogenbroeck , Andrea Tagliasacchi

Rendering is the process of generating 2D images from 3D assets, simulated in a virtual environment, typically with a graphics pipeline. By inverting such renderer, one can think of a learning approach to predict a 3D shape from an input…

Computer Vision and Pattern Recognition · Computer Science 2019-01-24 Shichen Liu , Weikai Chen , Tianye Li , Hao Li

We present a differentiable representation, DMesh, for general 3D triangular meshes. DMesh considers both the geometry and connectivity information of a mesh. In our design, we first get a set of convex tetrahedra that compactly tessellates…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Sanghyun Son , Matheus Gadelha , Yang Zhou , Zexiang Xu , Ming C. Lin , Yi Zhou

Generalizable 3D Gaussian Splatting reconstruction showcases advanced Image-to-3D content creation but requires substantial computational resources and large datasets, posing challenges to training models from scratch. Current methods…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Xiufeng Huang , Ka Chun Cheung , Runmin Cong , Simon See , Renjie Wan

Learning accurate depth is essential to multi-view 3D object detection. Recent approaches mainly learn depth from monocular images, which confront inherent difficulties due to the ill-posed nature of monocular depth learning. Instead of…

Computer Vision and Pattern Recognition · Computer Science 2022-08-23 Zengran Wang , Chen Min , Zheng Ge , Yinhao Li , Zeming Li , Hongyu Yang , Di Huang

Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 Linyi Jin , Richard Tucker , Zhengqi Li , David Fouhey , Noah Snavely , Aleksander Holynski

We present a differentiable volume rendering solution that provides differentiability of all continuous parameters of the volume rendering process. This differentiable renderer is used to steer the parameters towards a setting with an…

Graphics · Computer Science 2022-07-26 Sebastian Weiss , Rüdiger Westermann

Highly accurate 3D volumetric reconstruction is still an open research topic where the main difficulty is usually related to merging some rough estimations with high frequency details. One of the most promising methods is the fusion between…

Computer Vision and Pattern Recognition · Computer Science 2019-08-05 Fotios Logothetis , Roberto Mecca , Roberto Cipolla

3D scene reconstruction from multiple views is an important classical problem in computer vision. Deep learning based approaches have recently demonstrated impressive reconstruction results. When training such models, self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2020-09-29 Arijit Mallick , Jörg Stückler , Hendrik Lensch

Accurate recovery of 3D geometrical surfaces from calibrated 2D multi-view images is a fundamental yet active research area in computer vision. Despite the steady progress in multi-view stereo reconstruction, most existing methods are still…

Computer Vision and Pattern Recognition · Computer Science 2016-01-20 Zhaoxin Li , Kuanquan Wang , Wangmeng Zuo , Deyu Meng , Lei Zhang

Reconstructing 3D objects from images is inherently an ill-posed problem due to ambiguities in geometry, appearance, and topology. This paper introduces collaborative inverse rendering with persistent homology priors, a novel strategy that…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Xiang Gao , Xinmu Wang , Yuanpeng Liu , Yue Wang , Junqi Huang , Wei Chen , Xianfeng Gu

In this paper, we present a new perspective towards image-based shape generation. Most existing deep learning based shape reconstruction methods employ a single-view deterministic model which is sometimes insufficient to determine a single…

Computer Vision and Pattern Recognition · Computer Science 2019-04-23 Yi Wei , Shaohui Liu , Wang Zhao , Jiwen Lu , Jie Zhou

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…

Computer Vision and Pattern Recognition · Computer Science 2021-10-13 Berk Kaya , Suryansh Kumar , Francesco Sarno , Vittorio Ferrari , Luc Van Gool

Reconstructing object geometry and material from multiple views typically requires optimization. Differentiable path tracing is an appealing framework as it can reproduce complex appearance effects. However, it is difficult to use due to…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Purvi Goel , Loudon Cohen , James Guesman , Vikas Thamizharasan , James Tompkin , Daniel Ritchie

This paper develops a simple and fast method to reconstruct reality from stereoscopic images. We bring together ideas from robust optical flow techniques, morphing deformations and lightfield 3D rendering in order to create unsupervised…

Image and Video Processing · Electrical Eng. & Systems 2020-01-03 Enrique Canessa , Livio Tenze

Active-stereo-based 3D shape measurement is crucial for various purposes, such as industrial inspection, reverse engineering, and medical systems, due to its strong ability to accurately acquire the shape of textureless objects. Active…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Ryo Furukawa , Kota Nishihara , Hiroshi Kawasaki