Research map / Point clouds / Segmentation and detection
GOOD: Geometry-guided Out-of-Distribution Modeling for Open-set Test-time Adaptation in Point Cloud Semantic Segmentation
Tianpei Zou, Guo Yu, Ya Wu, Fan Lu, Zhongcong Xu, Zhang Bo, Ziqiao Wang, Sanqing Qu, Guang Chen
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 Superpoint Confidence to temporal pseudo-labels (ablation) | GOOD · Synth4D to SemanticKITTI | AUROC: 66.66 -> 71.47 | Improved |
| add Superpoint Confidence to temporal pseudo-labels (ablation) | GOOD · Synth4D to SemanticKITTI | mIoU gain: +4.61 -> +4.54 | Hurt |
| add Superpoint ID Prototypes (ablation) | GOOD · Synth4D to SemanticKITTI | AUROC / FPR95: AUROC 71.47 -> 73.39; FPR95 76.82 -> 71.91 | Improved |
| add Superpoint ID Prototypes (ablation) | GOOD · Synth4D to SemanticKITTI | mIoU gain: +4.54 -> +4.83 | Improved |
| add temporal pseudo-labels alone (ablation) | GOOD · Synth4D to SemanticKITTI | mIoU gain: +2.90 -> +4.61 | Improved |
| add GOOD to HGL | HGL · Synth4D to SemanticKITTI | mIoU gain / FPR95: mIoU +2.90 -> +5.31; FPR95 79.82 -> 71.31 | Improved |
| replace HGL with GOOD | GOOD · SynLiDAR to SemanticKITTI | mIoU gain / AUROC: +1.90 -> +5.03; 62.91 -> 73.23 | Improved |
| apply 2D UniEnt entropy maximization to 3D TTA | GIPSO · Synth4D to SemanticKITTI | mIoU gain: +2.08 -> +1.17 | Hurt |
| add WCEM to HGL | HGL · Synth4D to SemanticKITTI | FPR95: 79.82 -> 100.0 | No clear effect |
| add multi-frame superpoint clustering (ablation) | GOOD · Synth4D to SemanticKITTI | runtime: 0.70 s -> 1.45 s | Hurt |
| increase lambda for OOD entropy loss (ablation) | GOOD · Synth4D to SemanticKITTI | mIoU / open-set | Mixed |
| use SRB under sparse unknown class (other-vehicle) (ablation) | GOOD · SynLiDAR to SemanticKITTI | AUROC: 65.35 -> 73.23 | Improved |
Closest papers by meaning
- Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation (CVPR 2023 · similarity 0.89)
- PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentation (CVPR 2024 · similarity 0.88)
- Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding (CVPR 2024 · similarity 0.87)
- Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis (CVPR 2025 · similarity 0.87)
- FreePoint: Unsupervised Point Cloud Instance Segmentation (CVPR 2024 · similarity 0.87)
- Point-SAM: Promptable 3D Segmentation Model for Point Clouds (ICLR 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.
