3D Scene Relighting

Follow this topic Ask about this topic

Latest papers

23 papers3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Integrating Learned Priors through Prior-Space Reparameterization for Physically Based Inverse Rendering
Nov 5, 2026Hun Hwangbo, Minjun Park, Yongsung Kim +4Inverse Rendering Physically Based Rendering
IPAI, Seoul National University · ECE, Seoul National University · FAM, Seoul National University
GSHeadRelight: Fast Relightability for 3D Gaussian Head Synthesis
Oct 22, 2026Henglei Lv, Bailin Deng, Jianzhu Guo +4Image Relighting 3D Scene Relighting
Institute of Computing Technology, CAS and University of Chinese Academy of Sciences, China · Cardiff University, United Kingdom · Kuaishou Technology, China
Directionally Factorized Illumination with Spherical Harmonic Rotation
Oct 17, 2026Yimeng Dou, Adam M. Saunders, Andre T. S. Hucke +5Neural Rendering Multi-View Image Synthesis
Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA · Department of Computer Science, Vanderbilt University, Nashville, TN, USA · Department of Biomedical Engineering, Vanderbilt University, Nashville, TN, USA +4
PAM-ToD: Plug-and-Play Appearance Modeling for Cross-Time-of-Day 3D Gaussian Splatting
Oct 8, 2026Kota Shimomura, Sungho Moon, Tsubasa Hirakawa +33D Scene Relighting 3D Gaussian Splatting
Chubu University, Japan · Elith Inc., Japan · DGIST, Daegu, Republic of Korea +1
LightFuse: Relightable Interactive Gaussian Scene Reconstruction via Multi-Scan Fusion and 2D Gaussian Ray Tracing
Aug 29, 2026Haonan Zhou, Gaoxiang Linghu, Youlin Jia +5Differentiable Ray Tracing 3D Scene Relighting
ZJU-UIUC Institute, Zhejiang University · College of Mathematics, Sichuan University · College of Computer Science and Technology, Zhejiang University +1
LumiTokens: 3D Relighting via Token-Space Lighting Transformation
Aug 18, 2026Yiwen Chen, Matheus Gadelha, Huaizu Jiang3D Scene Relighting Image Relighting
Northeastern University · Adobe Research
LiveLight: Real-time Streaming Video Relighting with Interactive Control
Aug 3, 2026Yue Ma, Jiangming Wang, Yucheng Wang +8Video Editing Controllable Video Generation
1HKUST · University of Macau · 3THU +2
Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting
Jul 9, 2026Chenjian Gao, Linning Xu, Tianfan XueMulti-View Consistency Image Relighting
Multimedia Laboratory, The Chinese University of Hong Kong · Shanghai AI Laboratory · CPII under InnoHK
TRON: Tracing Rays to Orchestrate a Neural Renderer for 3D Gaussian Reconstructions
Jun 9, 2026Or Perel, Hassan Abu Alhaija, Zian Wang +43D Gaussian Splatting 3D Scene Editing
1NVIDIA · University of Toronto · 3Vector Institute
F-RNG: Feed-Forward Relightable Neural Gaussians
May 25, 2026Guangming Fu, Jiahui Fan, Jian Yang +23D Gaussian Splatting 3D Reconstruction
Nankai University, China · Nanjing University, China · NVIDIA, USA
SRUG: Shadow-Guided Relightable Urban Scene with Generation Model
May 23, 2026Yonghao Zhao, Zexin Yin, Jian Yang +2Inverse Rendering 3D Reconstruction
College of Computer Science, Nankai University, China · Nankai University and Nanjing University, China · School of Intelligence Science and Technology, Nanjing University, China
SeasonScapes: Learning Large-scale Re-lightable 3D Landscapes with Seasonal Variation from Sparse Webcams
May 9, 2026Timo Kleger, Qi Ma, Deheng Zhang +2Dynamic Scene Reconstruction Sparse-View 3D Reconstruction
2ETH Zurich · 1INSAIT, Sofia University “St. Kliment Ohridski”
Relightable Gaussian Splatting for Virtual Production Using Image-Based Illumination
May 9, 2026Adrian Azzarelli, Nantheera Anantrasirichai, James Pollock +1Inverse Rendering 3D Gaussian Splatting
University of Bristol, UK · Lux Aeterna, Bristol, UK
3DSS: 3D Surface Splatting for Inverse Rendering
May 7, 2026Mae Younes, Adnane BoukhaymaInverse Rendering Differentiable Rendering
INRIA, University of Rennes, France
WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images
Apr 23, 2026Yuki Fujimura, Takahiro Kushida, Kazuya Kitano +23D Gaussian Splatting 3D Reconstruction
NAIST · Ritsumeikan University · Kyoto University
LumiMotion: Improving Gaussian Relighting with Scene Dynamics
Apr 13, 2026Joanna Kaleta, Piotr Wójcik, Kacper Marzol +3Inverse Rendering 3D Scene Relighting
Warsaw University of Technology · Sano Centre for Computational Medicine · Inst. for Biomedical Informatics, Univ. Hospital of Cologne +5
SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes
Apr 3, 2026Quentin Herau, Tianshuo Xu, Depu Meng +53D Scene Relighting 3D Gaussian Splatting
Applied Intuition · The Hong Kong University of Science and Technology · University of California, Berkeley
AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing
Mar 27, 2026Tianyu Liu, Weitao Xiong, Kunming Luo +43D Scene Relighting Video Editing
The Hong Kong University of Science and Technology · Xiamen University · Meituan-M17, Hong Kong
ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination
Mar 20, 2026Jan-Niklas Dihlmann, Mark Boss, Simon Donne +33D Reconstruction Inverse Rendering
University of Tübingen · Stability AI
CamLit: Unified Video Diffusion with Explicit Camera and Lighting Control
Mar 15, 2026Zhiyi Kuang, Chengan He, Egor Zakharov +6Video Relighting Camera-Controlled Video Generation
Codec Avatars Lab, Reality Labs, Meta · State Key Lab of CAD&CG, Zhejiang University · University of Tübingen
PhyGaP: Physically-Grounded Gaussians with Polarization Cues
Mar 14, 2026Jiale Wu, Xiaoyang Bai, Zongqi He +23D Scene Relighting 3D Gaussian Splatting
The University of Hong Kong · Zhejiang University
R3GW: Relightable 3D Gaussians for Outdoor Scenes in the Wild
Mar 3, 2026Margherita Lea Corona, Wieland Morgenstern, Peter Eisert +13D Scene Relighting 3D Gaussian Splatting
Fraunhofer Heinrich Hertz Institute, Berlin, Germany · Humboldt Universität zu Berlin, Berlin, Germany
RRNet: Configurable Real-Time Video Enhancement with Arbitrary Local Lighting Variations
Jan 5, 2026Wenlong Yang, Canran Jin, Weihang Yuan +2Video Relighting Low-Light Image Enhancement
Tsinghua University, Beijing, China

Nov 5, 2026J/K move · Enter open · S save

Integrating Learned Priors through Prior-Space Reparameterization for Physically Based Inverse Rendering

Hun Hwangbo, Minjun Park, Yongsung Kim, Wooseok Song+3

IPAI, Seoul National University · ECE, Seoul National University · FAM, Seoul National University

Inverse Rendering Physically Based Rendering 3D Scene Relighting

Open paper AskPDF arXiv

Physically based inverse rendering decomposes appearance into materials and illumination, an ambiguous problem for which learned material predictions provide useful prior information. Most existing methods incorporate these cues through auxiliary regularization losses, which alter the optimization objective and require balancing their influence against photometric fitting. We propose a prior-guided material reparameterization that uses the predicted feature relationships to restrict the optimization space while leaving the objective unchanged. We fuse multi-view material predictions onto a mesh and construct a permutohedral lattice in the resulting prior feature space. Surface points with similar predictions share material variables, which are optimized jointly with geometry and illumination using a purely photometric objective. Experiments with two learned predictors on three synthetic benchmarks and Stanford-ORB demonstrate improved material decomposition and relighting. Our method improves relighting PSNR by 1.5-2.5 dB over the strongest evaluated mesh-based baseline on Synthetic4Relight and TensoIR-Synthetic, and outperforms a regularization loss using the same prior in controlled comparisons. We further show that our reparameterization pools noisy photometric gradients, producing updates that are more consistent across sampled views. This consistency enables a shortened joint optimization schedule that takes less than a minute while retaining relighting quality above all evaluated baselines on TensoIR-Synthetic.