Research map / 3D vision / 3D generation
Consistent Instance Field for Dynamic Scene Understanding
Junyi Wu, Van Nguyen Nguyen, Benjamin Planche, Jiachen Tao, Changchang Sun, Zhongpai Gao, Zhenghao Zhao, Anwesa Choudhuri, Gengyu Zhang, Meng Zheng, Feiran Wang, Terrence Chen and 2 more
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 identity visibility-bias calibration (ablation) | CIF · HyperNeRF split-cookie | mIoU: 78.16 -> 86.03 | Improved |
| add identity visibility-bias calibration (ablation) | CIF · HyperNeRF split-cookie | PSNR: 26.73 -> 32.42 | Improved |
| add instance-guided resampling (ablation) | CIF · HyperNeRF split-cookie | mIoU: 82.82 -> 86.03 | Improved |
| add learned adaptive occupancy instead of constant occupancy (ablation) | CIF · HyperNeRF split-cookie | mIoU: 80.80 -> 86.03 | Improved |
| add separate occupancy instead of using opacity as occupancy (ablation) | CIF · HyperNeRF split-cookie | mIoU: 82.34 -> 86.03 | Improved |
| add instance-guided resampling (ablation) | CIF · HyperNeRF split-cookie | PSNR: 32.34 -> 32.42 | No clear effect |
| use CIF instead of VLGS | CIF · HyperNeRF (average) | mIoU: +11.42 | Improved |
| use CIF instead of VLGS | CIF · Neu3D (average) | mIoU: +5.82 | Improved |
| use CIF instead of SA4D | CIF · HyperNeRF torchocolate | mIoU: +15.11 | Improved |
| use CIF instead of VLGS | CIF · HyperNeRF torchocolate | mIoU: +20.89 | Improved |
| use CIF instead of VLGS | CIF · Neu3D flame salmon | mIoU: 70.83 -> 87.69 | Improved |
Closest papers by meaning
- InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception (CVPR 2025 · similarity 0.89)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.88)
- Tackling View-Dependent Semantics in 3D Language Gaussian Splatting (ICML 2025 · similarity 0.86)
- Online Segment Any 3D Thing as Instance Tracking (NeurIPS 2025 · similarity 0.86)
- Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception (CVPR 2024 · similarity 0.86)
- Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding (AAAI 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.
