English
Related papers

Related papers: RelitLRM: Generative Relightable Radiance for Larg…

200 papers

Existing methods for relightable view synthesis -- using a set of images of an object under unknown lighting to recover a 3D representation that can be rendered from novel viewpoints under a target illumination -- are based on inverse…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Xiaoming Zhao , Pratul P. Srinivasan , Dor Verbin , Keunhong Park , Ricardo Martin Brualla , Philipp Henzler

We propose a 3D Gaussian splatting-based framework for outdoor relighting that leverages intrinsic image decomposition to precisely integrate sunlight, sky radiance, and indirect lighting from unconstrained photo collections. Unlike prior…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Haiyang Bai , Jiaqi Zhu , Songru Jiang , Wei Huang , Tao Lu , Yuanqi Li , Jie Guo , Runze Fu , Yanwen Guo , Lijun Chen

We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows impacts feed-forward 3D reconstruction. Although recent object-centric feed-forward methods deliver robust, high-quality reconstruction,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Zhengqin Li , Cheng Zhang , Jakob Engel , Zhao Dong

Recent advances in generalizable Gaussian splatting (GS) have enabled feed-forward reconstruction of scenes from tens of input views. Long-LRM notably scales this paradigm to 32 input images at $950\times540$ resolution, achieving 360{\deg}…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Chen Ziwen , Hao Tan , Peng Wang , Zexiang Xu , Li Fuxin

Recent approaches for 3D relighting have shown promise in integrating 2D image relighting generative priors to alter the appearance of a 3D representation while preserving the underlying structure. Nevertheless, generative priors used for…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Yehonathan Litman , Fernando De la Torre , Shubham Tulsiani

In this paper, we rethink the low-light image enhancement task and propose a physically explainable and generative diffusion model for low-light image enhancement, termed as Diff-Retinex. We aim to integrate the advantages of the physical…

Computer Vision and Pattern Recognition · Computer Science 2023-08-28 Xunpeng Yi , Han Xu , Hao Zhang , Linfeng Tang , Jiayi Ma

We introduce the Deformable Gaussian Splats Large Reconstruction Model (DGS-LRM), the first feed-forward method predicting deformable 3D Gaussian splats from a monocular posed video of any dynamic scene. Feed-forward scene reconstruction…

Object-centric reconstruction seeks to recover the 3D structure of a scene through composition of independent objects. While this independence can simplify modeling, it discards strong signals that could improve reconstruction, notably…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Qirui Wu , Yawar Siddiqui , Duncan Frost , Samir Aroudj , Armen Avetisyan , Richard Newcombe , Angel X. Chang , Jakob Engel , Henry Howard-Jenkins

We present GI-GS, a novel inverse rendering framework that leverages 3D Gaussian Splatting (3DGS) and deferred shading to achieve photo-realistic novel view synthesis and relighting. In inverse rendering, accurately modeling the shading…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Hongze Chen , Zehong Lin , Jun Zhang

Recent 3D-aware head generative models based on 3D Gaussian Splatting achieve real-time, photorealistic and view-consistent head synthesis. However, a fundamental limitation persists: the deep entanglement of illumination and intrinsic…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Yating Wang , Yuan Sun , Xuan Wang , Ran Yi , Boyao Zhou , Yipengjing Sun , Hongyu Liu , Yinuo Wang , Lizhuang Ma

Accurate reconstruction and relighting of glossy objects remains a longstanding challenge, as object shape, material properties, and illumination are inherently difficult to disentangle. Existing neural rendering approaches often rely on…

Graphics · Computer Science 2025-12-15 Georgios Kouros , Minye Wu , Tinne Tuytelaars

Modeling strong gravitational lenses in order to quantify the distortions in the images of background sources and to reconstruct the mass density in the foreground lenses has been a difficult computational challenge. As the quality of…

Instrumentation and Methods for Astrophysics · Physics 2023-07-05 Alexandre Adam , Laurence Perreault-Levasseur , Yashar Hezaveh , Max Welling

Geometry reconstruction of textureless, non-Lambertian objects under unknown natural illumination (i.e., in the wild) remains challenging as correspondences cannot be established and the reflectance cannot be expressed in simple analytical…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Kohei Yamashita , Shohei Nobuhara , Ko Nishino

Image-based lighting (IBL) is a widely used technique that renders objects using a high dynamic range image or environment map. However, aggregating the irradiance at the object's surface is computationally expensive, in particular for…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Shizhan Zhu , Shunsuke Saito , Aljaz Bozic , Carlos Aliaga , Trevor Darrell , Christoph Lassner

We propose Long-LRM, a feed-forward 3D Gaussian reconstruction model for instant, high-resolution, 360{\deg} wide-coverage, scene-level reconstruction. Specifically, it takes in 32 input images at a resolution of 960x540 and produces the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Chen Ziwen , Hao Tan , Kai Zhang , Sai Bi , Fujun Luan , Yicong Hong , Li Fuxin , Zexiang Xu

In this work, we introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Chubin Zhang , Hongliang Song , Yi Wei , Yu Chen , Jiwen Lu , Yansong Tang

Manipulating the illumination of a 3D scene within a single image represents a fundamental challenge in computer vision and graphics. This problem has traditionally been addressed using inverse rendering techniques, which involve explicit…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Shrisha Bharadwaj , Haiwen Feng , Giorgio Becherini , Victoria Fernandez Abrevaya , Michael J. Black

We propose GRGS, a generalizable and relightable 3D Gaussian framework for high-fidelity human novel view synthesis under diverse lighting conditions. Unlike existing methods that rely on per-character optimization or ignore physical…

Computer Vision and Pattern Recognition · Computer Science 2025-11-24 Yipengjing Sun , Shengping Zhang , Chenyang Wang , Shunyuan Zheng , Zonglin Li , Xiangyang Ji

Despite recent advancements in the Large Reconstruction Model (LRM) demonstrating impressive results, when extending its input from single image to multiple images, it exhibits inefficiencies, subpar geometric and texture quality, as well…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Mengfei Li , Xiaoxiao Long , Yixun Liang , Weiyu Li , Yuan Liu , Peng Li , Wenhan Luo , Wenping Wang , Yike Guo

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