Research map / 3D vision / Gaussian splatting
SEHDR: Single-Exposure HDR Novel View Synthesis via 3D Gaussian Bracketing
Yiyu Li, Haoyuan Wang, Ke Xu, Gerhard Petrus Hancke, Rynson W.H. Lau
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 |
|---|---|---|---|
| use SEHDR instead of HDR-GS trained on single exposure without HDR ground truth | HDR-NVS from single-exposure LDR · HDR-NeRF synthetic (single exposure) | PSNR: 11.008 -> 25.371 | Improved |
| use SEHDR instead of SingleHDR+GS, the strongest single-image HDR plus 3DGS baseline | HDR-NVS from single-exposure LDR · HDR-NeRF synthetic (single exposure) | PSNR: 14.251 -> 25.371 | Improved |
| combine single-image HDR reconstruction with 3DGS instead of direct HDR-NVS | DrTMO, IntrinHDR · HDR-NeRF synthetic (single exposure) | PSNR: 4.640 and 8.201 PSNR | Hurt |
| add HDR ground-truth supervision to SEHDR | SEHDR · HDR-NeRF synthetic (single exposure) | PSNR: 25.371 -> 37.054 | Improved |
| use SEHDR instead of HDR-GS when both have HDR ground truth | HDR-NVS with GT supervision · HDR-NeRF synthetic (single exposure) | LPIPS: 0.046 -> 0.032 | Improved |
| add linear loss on base Gaussians (ablation) | SEHDR · HDR-NeRF synthetic | visual HDR color quality | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- HDR-NeRF — HDR-NeRF: High Dynamic Range Neural Radiance Fields (CVPR 2022) · better on 3 of 3 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
- HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting (NeurIPS 2024 · similarity 0.92)
- GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping (CVPR 2025 · similarity 0.92)
- High Dynamic Range Novel View Synthesis with Single Exposure (ICML 2025 · similarity 0.91)
- EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting (AAAI 2025 · similarity 0.89)
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.89)
- From Chaos to Clarity: 3DGS in the Dark (NeurIPS 2024 · similarity 0.88)
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.
