Research map / Point clouds / Segmentation and detection
Text-Guided Graph Neural Networks for Referring 3D Instance Segmentation
Pin-Hao Huang, Han-Hung Lee, Hwann-Tzong Chen, Tyng-Luh Liu
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 relation coordinate encoding to the GRU TGNN (ablation) | TGNN · ScanRefer validation | mIOU: 24.8 ± 0.4 -> 26.1 ± 0.2 | Improved |
| add instance-dependent language attention to the GRU TGNN (ablation) | TGNN · ScanRefer validation | mIOU: 25.6 ± 0.2 -> 26.1 ± 0.2 | Improved |
| add instance-dependent language attention to the BERT TGNN (ablation) | TGNN · ScanRefer validation | mIOU: 26.8 ± 0.3 -> 27.8 ± 0.2 | Improved |
| use relation encoding and language attention instead of simple feature concatenation | TGNN with GRU · ScanRefer validation | mIOU: 22.6 ± 0.3 -> 26.1 ± 0.2 | Improved |
| use BERT rather than GRU for language features in TGNN | TGNN · ScanRefer validation | mIOU: 26.1 ± 0.2 -> 27.8 ± 0.2 | Improved |
| use TGNN rather than ReferIt3D's model | referring object identification · Nr3D | accuracy: 35.6% ± 0.7% -> 37.3% ± 0.3% | Improved |
| use TGNN rather than ReferIt3D's model | referring object identification · Sr3D | accuracy: 40.8% ± 0.2% -> 45.0% ± 0.2% | Improved |
| use OursBERT rather than ScanRefer | 3D object localization · ScanRefer test | Acc@0.25: 42.44 -> 41.00 | Hurt |
| use OursBERT rather than ScanRefer | 3D object localization · ScanRefer test | Acc@0.5: 26.03 -> 32.80 | Improved |
Closest papers by meaning
- X-RefSeg3D: Enhancing Referring 3D Instance Segmentation via Structured Cross-Modal Graph Neural Networks (AAAI 2024 · similarity 0.90)
- Learning 3D Semantic Scene Graphs with Instance Embeddings (IJCV 2022 · similarity 0.89)
- SAM-guided Graph Cut for 3D Instance Segmentation (ECCV 2024 · similarity 0.88)
- LESS: Label-Efficient and Single-Stage Referring 3D Segmentation (NeurIPS 2024 · similarity 0.88)
- Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior (CVPR 2024 · similarity 0.87)
- Relation3D : Enhancing Relation Modeling for Point Cloud Instance 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.
