Research map / Detection and segmentation / Open-set and few-shot detection
Interactive Segmentation of Radiance Fields
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 |
|---|---|---|---|
| Replace N3F feature matching with ISRF's clustered matching and region-growing workflow | Radiance-field object segmentation · Chess Table | Mean IoU: 0.344 -> 0.912 | Helped |
| Replace N3F feature matching with ISRF's clustered matching and region-growing workflow | Radiance-field object segmentation · Color Fountain | Mean IoU: 0.871 -> 0.927 | Helped |
| Replace N3F feature matching with ISRF's clustered matching and region-growing workflow | Radiance-field object segmentation · Stove | Mean IoU: 0.416 -> 0.819 | Helped |
| Replace N3F feature matching with ISRF's clustered matching and region-growing workflow | Radiance-field object segmentation · Shoe Rack | Mean IoU: 0.589 -> 0.861 | Helped |
| Use stroke queries instead of patch queries | ISRF · LLFF scenes | Mean IoU: Chess Table: 0.864 -> 0.912; Color Fountain: 0.927 -> 0.927; Stove: 0.827 -> 0.819; Shoe Rack: 0.763 -> 0.861 | Mixed |
| Add K-Means clustering before nearest-neighbor feature matching (ablation) | ISRF seed-region matching · Radiance-field segmentation | segmentation quality | Helped |
| Replace K-Means plus NNFM with average feature matching (ablation) | ISRF seed-region matching · Radiance-field segmentation | segmentation quality | Hurt |
| Replace K-Means plus NNFM with unclustered NNFM (ablation) | ISRF seed-region matching · Radiance-field segmentation | segmentation quality | Hurt |
| Add bilateral search to grow the high-confidence seed using spatial and semantic proximity (ablation) | ISRF · Radiance-field segmentation | object-region completeness | Helped |
| Add interactive strokes beyond the NVOS-provided strokes (ablation) | ISRF on NVOS dataset · NVOS dataset | mIoU: 83.75 -> 90.8 | Helped |
| Use ISRF with NVOS-provided strokes instead of NVOS | Radiance-field segmentation · NVOS dataset | mIOU: 70.1 -> 83.75 | Helped |
Closest papers by meaning
- GSN: Generalisable Segmentation in Neural Radiance Field (AAAI 2024 · similarity 0.88)
- Rethinking Open-Vocabulary Segmentation of Radiance Fields in 3D Space (AAAI 2025 · similarity 0.87)
- RelationField: Relate Anything in Radiance Fields (CVPR 2025 · similarity 0.86)
- GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding (CVPR 2024 · similarity 0.86)
- GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding (CVPR 2024 · similarity 0.85)
- NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation (CVPR 2024 · similarity 0.85)
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.