Research map / Detection and segmentation / Open-set and few-shot detection
SceneDiff: A Benchmark and Method for Multiview Object Change Detection
Yuqun Wu, Chih-Hao Lin, Henry Che, Aditi Tiwari, Chuhang Zou, Shenlong Wang, Derek Hoiem
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 pi3 instead of VGGT for geometry (ablation) | SceneDiff · SD-V | obj/im AP: -8.1 for VGGT | Improved |
| use pi3 instead of FASt3R (ablation) | SceneDiff · SD-V | obj/im AP: -39.8 for FASt3R | Improved |
| use DINOv3 instead of DINOv2 features (ablation) | SceneDiff · SD-V | obj/sc AP: -1.5 for DINOv2 | Improved |
| use DINOv3 instead of DINOv2 features (ablation) | SceneDiff · SD-V | obj/im AP: +1.3 for DINOv2 | No clear effect |
| combine geometry, feature and region cues instead of geometry alone (ablation) | SceneDiff · SD-V | obj/sc AP: -10.3 for geometry only | Improved |
| add reprojected feature cue (ablation) | SceneDiff · SD-V | obj/sc AP: region-only -0.8, feature-only 0.0 vs full | Improved |
| add region-matching cue on top of feature and geometry (ablation) | SceneDiff · SD-V | obj/sc AP: E_f+E_r +2.6 vs full; E_g+E_f +0.1 | No clear effect |
| use SceneDiff instead of best baseline | SceneDiff · SceneDiff Benchmark SD-V | obj/sc AP: 5.3 -> 22.8 | Improved |
| use SceneDiff instead of CYWS-3D | SceneDiff · RC-3D | AP50: 41.0 -> 65.3 | Improved |
| use SceneDiff instead of MV3DCD | SceneDiff · PASLCD | mIoU: 46.1 -> 47.3 | Improved |
| require change-type correctness in evaluation | SceneDiff · SD-V | obj/sc AP: 22.8 -> 18.5 | Hurt |
| finetune CYWS-2D on validation set | CYWS-2D · SD-V | obj/im AP: 19.4 -> 24.5 | Improved |
Closest papers by meaning
- Zero-Shot Scene Change Detection (AAAI 2025 · similarity 0.89)
- Towards Generalizable Scene Change Detection (CVPR 2025 · similarity 0.89)
- Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective (CVPR 2025 · similarity 0.87)
- Multi-View Pose-Agnostic Change Localization with Zero Labels (CVPR 2025 · similarity 0.87)
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 2024 · similarity 0.86)
- M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (CVPR 2025 · similarity 0.86)
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.
