Research map / Point clouds / Segmentation and detection
Towards Efficient and Effective Interactive 3D Segmentation
Wei Cong, Yang Cong, Jiahua Dong, Gan Sun
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 hierarchical click-aware attention (ablation) | E2I3D · interactive single-object segmentation | IoU@5: 46.8 -> 48.7 | Improved |
| add hierarchical click-aware attention (ablation) | E2I3D · interactive single-object segmentation | NoC@85: 15.1 -> 14.5 | Improved |
| prune E2I3D from 40.5M to 13.0M parameters (ablation) | E2I3D · S3DIS-A5 single-object | IoU@5: 84.2 -> 83.4 | Mixed |
| prune E2I3D from 40.5M to 5.7M parameters (ablation) | E2I3D · ScanNetV2 single-object | IoU@5: 79.9 -> 72.9 | Hurt |
| prune E2I3D from 40.5M to 5.7M parameters (ablation) | E2I3D · KITTI-360 single-object | IoU@5: 49.6 -> 49.0 | Improved |
| E2I3D without pruning vs AGILE3D (ablation) | E2I3D 40.5M · ScanNetV2 multi-object | IoU@5: 86.3 -> 88.7 | Improved |
| use E2I3D with 5.7M params instead of AGILE3D 39.3M | E2I3D · Inference time after 5 clicks | t@5: 0.5 -> 0.1 | Improved |
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.
- AGILE3D — AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation (ICLR 2024) · better on 5 of 6 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
- AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation (ICLR 2024 · similarity 0.92)
- Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes (ICML 2025 · similarity 0.90)
- TETRIS: Towards Exploring the Robustness of Interactive Segmentation (AAAI 2024 · similarity 0.88)
- Order-aware Interactive Segmentation (ICLR 2025 · similarity 0.88)
- RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation (NeurIPS 2024 · similarity 0.87)
- COS3D: Collaborative Open-Vocabulary 3D Segmentation (NeurIPS 2025 · 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.
