Research map / 3D vision / 3D generation
Towards 3D Object-Centric Feature Learning for Semantic Scene Completion
Weihua Wang, Yubo Cui, Xiangru Lin, Zhiheng Li, Zheng Fang
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 MobileSAM-guided SGA3D object-level attention (ablation) | baseline SSC model · SemanticKITTI val | mIoU: 15.80 -> 16.49 | Improved |
| add Global Similarity-Guided Attention to SGA3D (ablation) | Ocean · SemanticKITTI val | mIoU: 16.49 -> 16.80 | Improved |
| add local attention refinement of BEV features (ablation) | Ocean · SemanticKITTI val | mIoU: mIoU 16.80 -> 17.10, IoU 46.01 -> 45.39 | Mixed |
| add Dynamic Instance Decoder (ablation) | Ocean · SemanticKITTI val | mIoU: 17.10 -> 17.39 | Improved |
| add multi-scale image features to SGA3D (ablation) | SGA3D · SemanticKITTI val | mIoU: 16.64 -> 17.39 | Improved |
| add 3D depth-similarity extension to SGA (ablation) | SGA3D · SemanticKITTI val | IoU: 45.84 -> 46.40 | Improved |
| use SGA3D instead of DFA2D or DFA3D (ablation) | Ocean · SemanticKITTI val | mIoU: 16.39 (DFA2D), 16.97 (DFA3D) -> 17.39 | Improved |
| add GSGA module (ablation) | Ocean · SemanticKITTI val | mIoU: 16.98 -> 17.39 | Improved |
| use similarity-guided global features in GSGA instead of naive global operation (ablation) | GSGA · SemanticKITTI val | mIoU: 16.36 -> 17.39 | Improved |
| use dynamic instance selection (Gumbel-Softmax) instead of direct sum fusion (ablation) | Dynamic Instance Decoder · SemanticKITTI val | mIoU: 16.45 -> 17.39 | Improved |
| use dynamic selection instead of sigmoid weighting (ablation) | Dynamic Instance Decoder · SemanticKITTI val | IoU: 46.30 -> 46.40 | Improved |
| use Ocean instead of CGFormer on SSCBench-KITTI360 | Ocean · SSCBench-KITTI360 test | mIoU: 20.05 -> 20.28 | 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.
- LOMA — LOMA: Language-assisted Semantic Occupancy Network via Triplane Mamba (AAAI 2025) · better on 1 of 1 shared result
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
- Semi-supervised 3D Semantic Scene Completion with 2D Vision Foundation Model Guidance (AAAI 2025 · similarity 0.89)
- VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion (AAAI 2025 · similarity 0.89)
- Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance (NeurIPS 2025 · similarity 0.89)
- CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism (ICML 2025 · similarity 0.88)
- Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction (NeurIPS 2025 · similarity 0.88)
- SOAP: Vision-Centric 3D Semantic Scene Completion with Scene-Adaptive Decoder and Occluded Region-Aware View Projection (CVPR 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.
