GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping
Jinfeng Liu, Lingtong Kong, Bo Li, Dan Xu
2025Year
7Top-tier citations
Abstract
Inaccurate HDR Rendering 𝑧 (depth) 𝑧 (depth) Training with 3D Tone Mapping HDR Rendering Training with 2D Tone Mapping HDR ray Tone mapping Render LDR ray LDR pixel Loss HDR ray Tone mapping Render HDR pixel LDR pixel Loss LDR RMSE: 0.032 LDR RMSE: 0.054 Figure 1. 3D tone mapping vs. 2D tone mapping. Training with 3D tone mapping often results in inaccurate HDR rendering, while training with 2D tone mapping degrades LDR rendering quality, leading to a higher LDR RMSE metric compared to 3D tone mapping.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers7
- Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular VideosJinfeng Liu, Lingtong Kong, Mi Zhou, Jinwei Chen et al.ICLR 2026 · 3 citations
- HDR-NSFF: High Dynamic Range Neural Scene Flow FieldsShin Dong-Yeon, Kim Jun-Seong, Kwon Byung-Ki, Tae-Hyun OhICLR 2026 · 2 citations
- P2GS: Physical Prior-guided Gaussian Splatting for Photometrically Consistent Urban ReconstructionKota Shimomura, Hidehisa Arai, Tsubasa Takahashi, Takayoshi Yamashita et al.CVPR 2026 · 1 citation
- Physically Inspired Gaussian Splatting for HDR Novel View SynthesisHuimin Zeng, Yue Bai, hailing wang, Yun FuCVPR 2026 · 1 citation
- Dynamic Novel View Synthesis in High Dynamic RangeKaixuan Zhang, Zhipeng Xiong, Minxian Li, Mingwu Ren et al.ICLR 2026
Builds on27
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman et al.ICCV 2021 · 2,700 citations
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen et al.CVPR 2022 · 1,237 citations
Related papers
- Unpaired Learning for High Dynamic Range Image Tone MappingYael Vinker, Inbar Huberman-Spiegelglas, Raanan FattalICCV 2021 · 35 citations
- FastGaMer: Efficient GainMap Learning for Practical Inverse Tone MappingYuanshen Guan, Ruikang Xu, Chang Chen, Yinuo Liao et al.CVPR 2026
- HDR-NeRF: High Dynamic Range Neural Radiance FieldsXin Huang, Qi Zhang, Ying Feng, Hongdong Li et al.CVPR 2022 · 105 citations
- Comparison of single image HDR reconstruction methods - the caveats of quality assessmentParam Hanji, Rafal Mantiuk, Gabriel Eilertsen, Saghi Hajisharif et al.SIGGRAPH 2022 · 48 citations
- Learning Differential Pyramid Representation for Tone MappingQirui Yang, Yinbo Li, Yihao Liu, Peng-Tao Jiang et al.NeurIPS 2025 · 4 citations
