English
Related papers

Related papers: MRD: Using Physically Based Differentiable Renderi…

200 papers

Constructing 3D representations of object geometry is critical for many robotics tasks, particularly manipulation problems. These representations must be built from potentially noisy partial observations. In this work, we focus on the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Herbert Wright , Weiming Zhi , Martin Matak , Matthew Johnson-Roberson , Tucker Hermans

To endow machines with the ability to perceive the real-world in a three dimensional representation as we do as humans is a fundamental and long-standing topic in Artificial Intelligence. Given different types of visual inputs such as…

Computer Vision and Pattern Recognition · Computer Science 2020-10-20 Bo Yang

Synthesizing photo-realistic images and videos is at the heart of computer graphics and has been the focus of decades of research. Traditionally, synthetic images of a scene are generated using rendering algorithms such as rasterization or…

Synthesizing accurate geometry and photo-realistic appearance of small scenes is an active area of research with compelling use cases in gaming, virtual reality, robotic-manipulation, autonomous driving, convenient product capture, and…

Computer Vision and Pattern Recognition · Computer Science 2024-09-06 Arkadeep Narayan Chaudhury , Igor Vasiljevic , Sergey Zakharov , Vitor Guizilini , Rares Ambrus , Srinivasa Narasimhan , Christopher G. Atkeson

Faithfully reconstructing 3D geometry and generating novel views of scenes are critical tasks in 3D computer vision. Despite the widespread use of image augmentations across computer vision applications, their potential remains…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Juan C. Pérez , Sara Rojas , Jesus Zarzar , Bernard Ghanem

Modeling and rendering of dynamic scenes is challenging, as natural scenes often contain complex phenomena such as thin structures, evolving topology, translucency, scattering, occlusion, and biological motion. Mesh-based reconstruction and…

Graphics · Computer Science 2019-08-14 Stephen Lombardi , Tomas Simon , Jason Saragih , Gabriel Schwartz , Andreas Lehrmann , Yaser Sheikh

Dense 3D reconstruction has many applications in automated driving including automated annotation validation, multimodal data augmentation, providing ground truth annotations for systems lacking LiDAR, as well as enhancing auto-labeling…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Shihao Shen , Louis Kerofsky , Varun Ravi Kumar , Senthil Yogamani

Latent diffusion models (LDMs) exhibit an impressive ability to produce realistic images, yet the inner workings of these models remain mysterious. Even when trained purely on images without explicit depth information, they typically output…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Yida Chen , Fernanda Viégas , Martin Wattenberg

Neural rendering is a new image and video generation method based on deep learning. It combines the deep learning model with the physical knowledge of computer graphics, to obtain a controllable and realistic scene model, and realize the…

Graphics · Computer Science 2024-02-02 Xinkai Yan , Jieting Xu , Yuchi Huo , Hujun Bao

Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their…

Computer Vision and Pattern Recognition · Computer Science 2017-07-04 Yinda Zhang , Shuran Song , Ersin Yumer , Manolis Savva , Joon-Young Lee , Hailin Jin , Thomas Funkhouser

Recently neural scene representations have provided very impressive results for representing 3D scenes visually, however, their study and progress have mainly been limited to visualization of virtual models in computer graphics or scene…

Computer Vision and Pattern Recognition · Computer Science 2022-09-26 Yassine Ahmine , Arnab Dey , Andrew I. Comport

Rendering realistic images from 3D reconstruction is an essential task of many Computer Vision and Robotics pipelines, notably for mixed-reality applications as well as training autonomous agents in simulated environments. However, the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Lukas Bösiger , Mihai Dusmanu , Marc Pollefeys , Zuria Bauer

Many machine learning models operate on images, but ignore the fact that images are 2D projections formed by 3D geometry interacting with light, in a process called rendering. Enabling ML models to understand image formation might be key…

Computer Vision and Pattern Recognition · Computer Science 2019-11-22 Wenzheng Chen , Jun Gao , Huan Ling , Edward J. Smith , Jaakko Lehtinen , Alec Jacobson , Sanja Fidler

We introduce a method that can learn to predict scene-level implicit functions for 3D reconstruction from posed RGBD data. At test time, our system maps a previously unseen RGB image to a 3D reconstruction of a scene via implicit functions.…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Nilesh Kulkarni , Linyi Jin , Justin Johnson , David F. Fouhey

We present a method to edit complex indoor lighting from a single image with its predicted depth and light source segmentation masks. This is an extremely challenging problem that requires modeling complex light transport, and disentangling…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Zhengqin Li , Jia Shi , Sai Bi , Rui Zhu , Kalyan Sunkavalli , Miloš Hašan , Zexiang Xu , Ravi Ramamoorthi , Manmohan Chandraker

Recent advances in 3D deep learning have shown that it is possible to train highly effective deep models for 3D shape generation, directly from 2D images. This is particularly interesting since the availability of 3D models is still limited…

Computer Vision and Pattern Recognition · Computer Science 2019-11-05 Shichen Liu , Shunsuke Saito , Weikai Chen , Hao Li

The lack of labeled datasets in 3D vision for surgical scenes inhibits the development of robust 3D reconstruction algorithms in the medical domain. Despite the popularity of Neural Radiance Fields and 3D Gaussian Splatting in the general…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 John J. Han , Jie Ying Wu

A long-standing goal in scene understanding is to obtain interpretable and editable representations that can be directly constructed from a raw monocular RGB-D video, without requiring specialized hardware setup or priors. The problem is…

Computer Vision and Pattern Recognition · Computer Science 2023-06-22 Yu-Shiang Wong , Niloy J. Mitra

Reconstructing photo-realistic large-scale scenes from images, for example at city scale, is a long-standing problem in computer graphics. Neural rendering is an emerging technique that enables photo-realistic image synthesis from…

Graphics · Computer Science 2025-07-22 Yaru Liu , Derek Nowrouzezahri , Morgan Mcguire

Understanding high-resolution (HR) images remains a critical challenge for multimodal large language models (MLLMs). Recent approaches leverage vision-based retrieval-augmented generation (RAG) to retrieve query-relevant crops from HR…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Fan Yang , Xingping Dong , Xin Yu , Wenhan Luo , Wei Liu , Kaihao Zhang