Research map / 3D vision / 3D generation
EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation
Runsong Zhu, Jiaxin Guo, Xiaoyang Guo, Zhengzhe Liu, Ka-Hei Hui, Wei Yin, Kai Chen, Wei Chen, Weiqiang Ren, Yunhui Liu, Pheng-Ann Heng, Chi-Wing Fu
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 feature splatting supervision (ablation) | EPS3D · Replica (8-view) | novel instance F-score: 0.1510 -> 0.3106 | Improved |
| add feature splatting supervision (ablation) | EPS3D · Replica (8-view) | novel semantic mIoU: 0.4533 -> 0.4833 | Improved |
| add Ins2Sem module (ablation) | EPS3D · Replica (8-view) | novel semantic mIoU: 0.4531 -> 0.4833 | Improved |
| add Ins2Sem module (ablation) | EPS3D · Replica (8-view) | novel instance F-score: 0.3103 -> 0.3106 | No clear effect |
| add Sem2Ins module (ablation) | EPS3D · Replica (8-view) | novel instance mIoU: 0.3210 -> 0.3468 | Improved |
| add Sem2Ins module (ablation) | EPS3D · Replica (8-view) | novel semantic mIoU: 0.4821 -> 0.4833 | No clear effect |
| use mutual enhancement module instead of standard cross-attention (ablation) | EPS3D · Replica (8-view) | novel instance mIoU: 0.3230 -> 0.3468 | Improved |
| use mutual enhancement module instead of standard cross-attention (ablation) | EPS3D · Replica (8-view) | novel semantic mIoU: 0.4677 -> 0.4833 | Improved |
| apply feature splatting during training (ablation) | EPS3D · Replica context view | context instance F-score: 0.1598 -> 0.3232 | Improved |
| apply feature splatting at inference (ablation) | EPS3D · Replica context view | context semantic mIoU: 0.4965 -> 0.4999 | No clear effect |
| replace SAM with Semantic-SAM as instance teacher (ablation) | EPS3D · Replica (8-view) | novel instance F-score: 0.3106 -> 0.3198 | No clear effect |
| replace LSeg with MaskCLIP as semantic teacher (ablation) | EPS3D · Replica (8-view) | novel semantic mIoU: 0.4833 -> 0.4788 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Uni3R — Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images (CVPR 2026) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A Unified Framework for 3D Scene Understanding (NeurIPS 2024 · similarity 0.89)
- Multi-view Consistent 3D Panoptic Scene Understanding (AAAI 2025 · similarity 0.89)
- Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation (CVPR 2025 · similarity 0.88)
- IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals (NeurIPS 2025 · similarity 0.88)
- Segment Any 3D Object with Language (ICLR 2025 · similarity 0.88)
- SAI3D: Segment Any Instance in 3D Scenes (CVPR 2024 · similarity 0.88)
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.
