English
Related papers

Related papers: GR3EN: Generative Relighting for 3D Environments

200 papers

3D scene generation seeks to synthesize spatially structured, semantically meaningful, and photorealistic environments for applications such as immersive media, robotics, autonomous driving, and embodied AI. Early methods based on…

Computer Vision and Pattern Recognition · Computer Science 2025-05-09 Beichen Wen , Haozhe Xie , Zhaoxi Chen , Fangzhou Hong , Ziwei Liu

We present a method that takes as input a set of images of a scene illuminated by unconstrained known lighting, and produces as output a 3D representation that can be rendered from novel viewpoints under arbitrary lighting conditions. Our…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Pratul P. Srinivasan , Boyang Deng , Xiuming Zhang , Matthew Tancik , Ben Mildenhall , Jonathan T. Barron

Recent advancements in 3D object generation using diffusion models have achieved remarkable success, but generating realistic 3D urban scenes remains challenging. Existing methods relying solely on 3D diffusion models tend to suffer a…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 Hanlei Guo , Jiahao Shao , Xinya Chen , Xiyang Tan , Sheng Miao , Yujun Shen , Yiyi Liao

We address the problem of 3D inconsistency of image inpainting based on diffusion models. We propose a generative model using image pairs that belong to the same scene. To achieve the 3D-consistent and semantically coherent inpainting, we…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Leonid Antsfeld , Boris Chidlovskii

3D scene reconstruction is essential for applications in virtual reality, robotics, and autonomous driving, enabling machines to understand and interact with complex environments. Traditional 3D Gaussian Splatting techniques rely on images…

Graphics · Computer Science 2025-03-04 Changlin Song , Jiaqi Wang , Liyun Zhu , He Weng

Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion. Recent NeRF based methods achieve impressive fidelity of 3D reconstruction, but bake…

Computer Vision and Pattern Recognition · Computer Science 2023-04-07 Zian Wang , Tianchang Shen , Jun Gao , Shengyu Huang , Jacob Munkberg , Jon Hasselgren , Zan Gojcic , Wenzheng Chen , Sanja Fidler

3D Gaussian Splatting shows great potential in reconstructing photo-realistic 3D scenes. However, these methods typically bake illumination into their representations, limiting their use for physically-based rendering and scene editing.…

Graphics · Computer Science 2025-04-03 Zirui Wu , Jianteng Chen , Laijian Li , Shaoteng Wu , Zhikai Zhu , Kang Xu , Martin R. Oswald , Jie Song

We present a simple, yet effective diffusion-based method for fine-grained, parametric control over light sources in an image. Existing relighting methods either rely on multiple input views to perform inverse rendering at inference time,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-15 Nadav Magar , Amir Hertz , Eric Tabellion , Yael Pritch , Alex Rav-Acha , Ariel Shamir , Yedid Hoshen

We present a deep learning approach to reconstruct scene appearance from unstructured images captured under collocated point lighting. At the heart of Deep Reflectance Volumes is a novel volumetric scene representation consisting of…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Sai Bi , Zexiang Xu , Kalyan Sunkavalli , Miloš Hašan , Yannick Hold-Geoffroy , David Kriegman , Ravi Ramamoorthi

Modern scene reconstruction methods are able to accurately recover 3D surfaces that are visible in one or more images. However, this leads to incomplete reconstructions, missing all occluded surfaces. While much progress has been made on…

Computer Vision and Pattern Recognition · Computer Science 2025-11-07 Sam Bahrami , Dylan Campbell

Virtual production (VP) use LED walls to provide both background imagery and image-based lighting. While this enables on-set compositing, it couples lighting to background and scene appearance, limiting flexibility for downstream editing.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Adrian Azzarelli , Nantheera Anantrasirichai , James Pollock , David R. Bull

Advances in 3D reconstruction have enabled high-quality 3D capture, but require a user to collect hundreds to thousands of images to create a 3D scene. We present CAT3D, a method for creating anything in 3D by simulating this real-world…

Computer Vision and Pattern Recognition · Computer Science 2024-05-17 Ruiqi Gao , Aleksander Holynski , Philipp Henzler , Arthur Brussee , Ricardo Martin-Brualla , Pratul Srinivasan , Jonathan T. Barron , Ben Poole

Single-channel 3D reconstruction is widely used in fields such as robotics and medical imaging. While these methods are good at reconstructing 3D geometry, their outputs are typically uncolored 3D models, making 3D colorization necessary…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yeonjin Chang , Juhwan Cho , Seunghyeon Seo , Wonsik Shin , Nojun Kwak

In this work, we address the problem of jointly estimating albedo, normals, depth and 3D spatially-varying lighting from a single image. Most existing methods formulate the task as image-to-image translation, ignoring the 3D properties of…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Zian Wang , Jonah Philion , Sanja Fidler , Jan Kautz

Controlling illumination during video post-production is a crucial yet elusive goal in computational photography. Existing methods often lack flexibility, restricting users to certain relighting models. This paper introduces ReLumix, a…

Recent 3D large reconstruction models typically employ a two-stage process, including first generate multi-view images by a multi-view diffusion model, and then utilize a feed-forward model to reconstruct images to 3D content.However,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Zhenyu Tang , Junwu Zhang , Xinhua Cheng , Wangbo Yu , Chaoran Feng , Yatian Pang , Bin Lin , Li Yuan

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

In this work, we propose an inverse rendering model that estimates 3D shape, spatially-varying reflectance, homogeneous subsurface scattering parameters, and an environment illumination jointly from only a pair of captured images of a…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Chenhao Li , Trung Thanh Ngo , Hajime Nagahara

3D scene generation has long been dominated by 2D multi-view or video diffusion models. This is due not only to the lack of scene-level 3D latent representation, but also to the fact that most scene-level 3D visual data exists in the form…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Dongxu Wei , Qi Xu , Zhiqi Li , Hangning Zhou , Cong Qiu , Hailong Qin , Mu Yang , Zhaopeng Cui , Peidong Liu

Volumetric scene reconstruction from a single image is crucial for a broad range of applications like autonomous driving and robotics. Recent volumetric reconstruction methods achieve impressive results, but generally require expensive 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Philipp Wulff , Felix Wimbauer , Dominik Muhle , Daniel Cremers