Research map / 3D vision / NeRF and radiance fields
MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene
Wenjie Mu, Zhan Li, Chuanzhou Su, Xuanyi Shen, Ziniu Liu, Fan Lu, Yujian Mo, Junqiao Zhao, Tiantian Feng, Chen Ye, Guang Chen
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 MU-GeNeRF instead of ReTR without per-scene optimization | generalizable NeRF · On-the-go Corner | PSNR: 16.33 -> 17.96 | Improved |
| use MU-GeNeRF instead of ReTR without per-scene optimization | generalizable NeRF · On-the-go Patio | PSNR: 16.39 -> 18.63 | Improved |
| use MU-GeNeRF instead of MuRF without per-scene optimization | generalizable NeRF · RobustNeRF Statue | PSNR: 12.88 -> 18.28 | Improved |
| use MU-GeNeRF instead of ReTR without per-scene optimization | generalizable NeRF · RobustNeRF Android | PSNR: 18.63 -> 19.87 | Improved |
| add per-scene fine-tuning to MU-GeNeRF | MU-GeNeRF · On-the-go Corner | PSNR: 17.96 -> 21.77 | Improved |
| add per-scene fine-tuning to MU-GeNeRF | MU-GeNeRF · RobustNeRF Android | PSNR: 19.87 -> 22.34 | Improved |
| use MU-GeNeRF ft instead of ReTR ft | fine-tuned generalizable NeRF · On-the-go Patio | PSNR: 17.97 -> 20.72 | Improved |
| use MU-GeNeRF ft instead of UP-NeRF | fine-tuned methods · On-the-go Patio | PSNR: 15.78 -> 20.72 | Improved |
| use scene-specific NeRF on-the-go instead of MU-GeNeRF ft | fine-tuned methods · On-the-go Corner | PSNR: 23.15 vs 21.77 | Hurt |
| use scene-specific NeRF on-the-go instead of MU-GeNeRF ft | fine-tuned methods · RobustNeRF Statue | PSNR: 21.25 vs 19.97 | Hurt |
| use MU-GeNeRF instead of ReTR without per-scene optimization | generalizable NeRF · On-the-go Patio-High | LPIPS: 0.593 -> 0.507 | Improved |
| use released pretrained MuRF weights instead of training from scratch, then fine-tune | MuRF ft · On-the-go Corner | PSNR: 13.57 -> 14.03 | No clear effect |
Closest papers by meaning
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.91)
- NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation (CVPR 2024 · similarity 0.88)
- PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency (ICML 2024 · similarity 0.88)
- ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models (CVPR 2024 · similarity 0.87)
- Optimize the Unseen - Fast NeRF Cleanup with Free Space Prior (NeurIPS 2025 · similarity 0.87)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (AAAI 2024 · 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.
