Research map / 3D vision / Gaussian splatting
eRetinexGS: Retinex Modeling for Low-Light Scene Enhancement via Event Streams and 3D Gaussian Splatting
Haojie Yan, Zehao Chen, Yan Liu, Shi Gu, Peng Lin, De Ma, Huajin Tang, Qian Zheng, Gang Pan
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 events and frames with Retinex-3DGS (full method vs best prior, EvLowLight) | eRetinexGS · LLFF synthetic, novel view | PSNR: 18.02 -> 22.67 | Improved |
| add event data and event-guided smoothness (full vs w/o E, L_tv) (ablation) | eRetinexGS · LLFF synthetic | PSNR: 17.21 -> 23.45 | Improved |
| add low-light frame supervision (ablation) | eRetinexGS · LLFF synthetic | PSNR: 17.88 -> 23.45 | Improved |
| add event-guided reflectance smoothness L_tv (ablation) | eRetinexGS · LLFF synthetic | LPIPS: 0.2047 -> 0.0888 | Improved |
| add brightness loss (ablation) | eRetinexGS · LLFF synthetic | PSNR: 19.52 -> 23.45 | Improved |
| add gray-world loss (ablation) | eRetinexGS · LLFF synthetic | PSNR: 22.73 -> 23.45 | Improved |
| use confidence-guided complementarity and Retinex decomposition vs frame-only LLNeRF | eRetinexGS · LLFF synthetic, input view | SSIM: 0.5263 -> 0.8312 | 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.
- IncEventGS — IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera (CVPR 2025) · better on 2 of 2 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
- Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach (CVPR 2024 · similarity 0.89)
- EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting (ICML 2024 · similarity 0.89)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.88)
- GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation (NeurIPS 2025 · similarity 0.88)
- EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering (CVPR 2025 · similarity 0.88)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 2025 · 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.
