Research map / 3D vision / NeRF and radiance fields
Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 radiance field propagation with bidirectional photometric loss instead of removing propagation and using vanilla photometric loss (ablation) | RFP · CO3D | N-mIoU: 57.7 -> 94.0 | Helped |
| Use radiance field propagation with bidirectional photometric loss instead of removing propagation and using vanilla photometric loss (ablation) | RFP · RFP Synthetic | Acc.: 84.6 -> 97.7 | Helped |
| Add the initial semantic estimation loss (ablation) | RFP · CO3D | mIoU: 49.4 -> 94.1 | Helped |
| Add the initial semantic estimation loss (ablation) | RFP · RFP Synthetic | mIoU: 60.8 -> 88.0 | Helped |
| Add EM-based mask refinement (ablation) | RFP · RFP Synthetic | N-mIoU: 86.9 -> 87.5 | Helped |
| Use RFP rather than IEM | 3D segmentation · CO3D | mIoU: 83.4 -> 94.1 | Helped |
| Use RFP rather than DFC | 3D segmentation · RFP Synthetic | mIoU: 79.4 -> 88.0 | Helped |
Closest papers by meaning
- Interactive Segmentation of Radiance Fields (CVPR 2023 · similarity 0.90)
- Mask-Based Modeling for Neural Radiance Fields (ICLR 2024 · similarity 0.89)
- NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation (CVPR 2024 · similarity 0.88)
- GSN: Generalisable Segmentation in Neural Radiance Field (AAAI 2024 · similarity 0.88)
- Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields (CVPR 2024 · similarity 0.88)
- Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates (CVPR 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.