Research map / 3D vision / Gaussian splatting
Expo-GS: Exposure-Aware Signed Distance Function in Gaussian Splatting for High Dynamic Range
Chaoda Song, Yiren Lu, Xinpeng Li, Yunlai Zhou, Yanyan Zhang, Yu Yin, Vipin Chaudhary
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add geometry (Expo-SDF) training stage after irradiance (ablation) | Expo-GS · HDR synthetic | PSNR: 28.86 -> 30.29 | Improved |
| add 1K joint iterations after geometry stage (ablation) | Expo-GS · HDR synthetic | PSNR: 30.29 -> 34.76 | Improved |
| full 10K joint training instead of 1K (ablation) | Expo-GS · HDR synthetic | PSNR: 34.76 -> 39.06 | Improved |
| add joint training to LDR-OE (ablation) | Expo-GS · LDR-OE synthetic | PSNR: 31.92 -> 41.38 | Improved |
| nonlinear logarithmic CRF instead of linear (ablation) | Expo-GS · LDR-OE synthetic | PSNR: 33.49 -> 41.33 | Improved |
| logarithmic CRF instead of Reinhard on HDR (ablation) | Expo-GS · HDR synthetic | PSNR: 38.91 vs 38.77 | No clear effect |
| increase exposure diversity from {t3} to {t1,t5} (ablation) | Expo-GS · HDR synthetic | PSNR: 24.17 -> 32.81 | Improved |
| use all five exposures instead of three (ablation) | Expo-GS · HDR synthetic | PSNR: 38.64 -> 38.98 | Improved |
| Expo-GS vs HDR-GS on LDR-NE synthetic | Expo-GS · LDR-NE synthetic | PSNR: 36.36 -> 37.47 | Improved |
| Expo-GS vs HDR-GS on HDR synthetic | Expo-GS · HDR synthetic | PSNR: 37.98 -> 39.06 | Improved |
| Expo-GS vs HDR-NeRF on LDR-NE real-world | Expo-GS · LDR-NE real-world | PSNR: 32.71 vs 32.17 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- HDR-GS — HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting (NeurIPS 2024) · better on 6 of 6 shared results
- HDR-NeRF — HDR-NeRF: High Dynamic Range Neural Radiance Fields (CVPR 2022) · better on 4 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction (CVPR 2026 · similarity 0.89)
- Physically Inspired Gaussian Splatting for HDR Novel View Synthesis (CVPR 2026 · similarity 0.89)
- MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild (NeurIPS 2025 · similarity 0.88)
- Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections (NeurIPS 2024 · similarity 0.87)
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.87)
- GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
