Research map / Point clouds / Segmentation and detection
CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Omit final-level FPS | CasFusionNet · SSC-PC | CD: 0.70 -> 0.67 | Helped |
| Omit final-level FPS | CasFusionNet · NYUCAD-PC | CD: 10.28 -> 9.99 | Helped |
| Omit final-level FPS | CasFusionNet · SSC-PC | mIoU: 91.3 -> 91.2 | No clear effect |
| Omit final-level FPS | CasFusionNet · NYUCAD-PC | mAcc: 59.7 -> 59.8 | No clear effect |
| Add LRM and SSM to all levels (ablation) | CasFusionNet · NYUCAD-PC | CD: 10.73 -> 10.28 | Helped |
| Add LRM to all levels (ablation) | CasFusionNet · NYUCAD-PC | CD: 10.50 -> 10.28 | Helped |
| Add LRM to all levels (ablation) | CasFusionNet · NYUCAD-PC | mIoU: 49.0 -> 49.5 | Helped |
| Add feature fusion between GCM and SSM (ablation) | CasFusionNet · NYUCAD-PC | CD: 10.61 -> 10.28 | Helped |
| Add feature fusion between GCM and SSM (ablation) | CasFusionNet · NYUCAD-PC | mIoU: 40.3 -> 49.5 | Helped |
| Add feature fusion between GCM and SSM (ablation) | CasFusionNet · NYUCAD-PC | mAcc: 51.9 -> 59.8 | Helped |
| Use levels #2 and #3 (ablation) | CasFusionNet · NYUCAD-PC | CD: 11.60 -> 10.28 | Helped |
| Use levels #2 and #3 (ablation) | CasFusionNet · NYUCAD-PC | mIoU: 41.5 -> 49.5 | Helped |
Closest papers by meaning
- Point Cloud Semantic Scene Completion from RGB-D Images (AAAI 2021 · similarity 0.92)
- SCPNet: Semantic Scene Completion on Point Cloud (CVPR 2023 · similarity 0.91)
- H2GFormer: Horizontal-to-Global Voxel Transformer for 3D Semantic Scene Completion (AAAI 2024 · similarity 0.90)
- Context and Geometry Aware Voxel Transformer for Semantic Scene Completion (NeurIPS 2024 · similarity 0.89)
- Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion (NeurIPS 2024 · similarity 0.89)
- Semi-supervised 3D Semantic Scene Completion with 2D Vision Foundation Model Guidance (AAAI 2025 · 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.