Research map / 3D vision / 3D generation
Sparse-Aware Vector Quantization for Bandwidth-Efficient Collaborative 3D Semantic Occupancy Prediction
Feng Li, Chaokun Zhang, Gong 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 SAVQ to baseline (ablation) | collaborative occupancy baseline · Semantic-OPV2V | communication volume (MB): 7.32 -> 0.013 | Improved |
| add SAVQ to baseline (ablation) | collaborative occupancy baseline · Semantic-OPV2V | mIoU: 40.72 -> 40.11 | Hurt |
| add ASR to baseline (ablation) | collaborative occupancy baseline · Semantic-OPV2V | mIoU: 40.72 -> 41.26 | Improved |
| add ASR on top of SAVQ (ablation) | VQSOP · Semantic-OPV2V | mIoU: 40.11 -> 41.54 | Improved |
| add ASR on top of SAVQ (ablation) | VQSOP · Semantic-OPV2V | IoU: 72.06 -> 73.79 | Improved |
| raise confidence threshold from 0.6 to 0.8 (ablation) | SAVQ selector · Semantic-OPV2V | mIoU: 41.47 -> 41.54 | Improved |
| raise confidence threshold from 0.8 to 0.9 (ablation) | SAVQ selector · Semantic-OPV2V | mIoU: 41.54 -> 41.03 | Hurt |
| add local branch to ASR (ablation) | ASR · Semantic-OPV2V | mIoU: 40.11 -> 40.23 | Improved |
| add context branch to ASR (ablation) | ASR · Semantic-OPV2V | mIoU: 40.11 -> 40.85 | Improved |
| add adaptive integration instead of fixed equal weights (ablation) | ASR · Semantic-OPV2V | mIoU: 41.03 -> 41.54 | Improved |
| use VQSOP instead of GSFusion | collaborative occupancy · Semantic-OPV2V | communication volume (MB): 1.07 -> 0.013 | Improved |
| use VQSOP instead of GSFusion | collaborative occupancy · Semantic-OPV2V | mIoU: 37.44 -> 41.54 | 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.
- GaussianFormer — GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction (ECCV 2024) · better on 2 of 2 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
- Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles (CVPR 2024 · similarity 0.89)
- LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction (CVPR 2024 · similarity 0.88)
- LOMA: Language-assisted Semantic Occupancy Network via Triplane Mamba (AAAI 2025 · similarity 0.88)
- OctOcc: High-Resolution 3D Occupancy Prediction with Octree (AAAI 2024 · similarity 0.87)
- Achieving Speed-Accuracy Balance in Vision-based 3D Occupancy Prediction via Geometric-Semantic Disentanglement (AAAI 2025 · similarity 0.87)
- SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction (CVPR 2024 · 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.
