Research map / 3D vision / 3D generation
Structured Bird's-Eye-View Traffic Scene Understanding From Onboard Images
Yigit Baran Can, Alexander Liniger, Danda Pani Paudel, Luc Van Gool
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 the refinement net to the object branch (ablation) | STSU object branch · nuScenes objects | mIOU: 5.7 points | Improved |
| add split positional encoding to the large model (ablation) | STSU (Large) · nuScenes objects | obj-mean mIOU: 8.5 -> 8.7 | Improved |
| add split positional encoding to the large model (ablation) | STSU (Large) · nuScenes lane graph | Detect: 58.8 -> 52.8 | Hurt |
| add log of BEV locations to split positional encoding (large model) (ablation) | STSU (Large + Split) · nuScenes objects | obj-mean mIOU: 8.7 -> 9.2 | Improved |
| add log of BEV locations to split positional encoding (large model) (ablation) | STSU (Large + Split) · nuScenes lane graph | Con-IOU: 40.8 -> 38.9 | Hurt |
| add log of BEV locations to split positional encoding (large model) (ablation) | STSU (Large + Split) · nuScenes lane graph | Detect: 52.8 -> 60.6 | Improved |
| add log of BEV locations to split positional encoding (small model) (ablation) | STSU (Small + Split) · nuScenes objects | obj-mean mIOU: 8.9 -> 9.9 | Improved |
| add log of BEV locations to split positional encoding (small model) (ablation) | STSU (Small + Split) · nuScenes lane graph | Con-IOU: 41.3 -> 37.8 | Hurt |
| use the large transformer (four encoder and four decoder layers) instead of the small one, with split log (ablation) | STSU · nuScenes objects | obj-mean mIOU: 9.9 -> 9.2 | Hurt |
| use the large transformer instead of the small one, plain positional embedding (ablation) | STSU · nuScenes objects | obj-mean mIOU: 9.1 -> 8.5 | No clear effect |
| predict directed graph with association head instead of Polygon-RNN with estimated initial points | STSU vs Poly(Est) · nuScenes lane graph | C-Rec: 16.3 -> 52.2 | Improved |
| use the proposed transformer instead of PON for objects | STSU · nuScenes objects | car mIOU: 24.7 -> 32.5 | Improved |
Closest papers by meaning
- "The Pedestrian Next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping (CVPR 2022 · similarity 0.89)
- BEV-CAR: Enhancing Monocular Bird's Eye View Segmentation with Context-Aware Rasterization (CVPR 2026 · similarity 0.88)
- BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers (ECCV 2022 · similarity 0.88)
- Delving Into the Devils of Bird’s-Eye-View Perception: A Review, Evaluation and Recipe (TPAMI 2023 · similarity 0.88)
- Improving Bird's Eye View Semantic Segmentation by Task Decomposition (CVPR 2024 · similarity 0.88)
- Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets (NeurIPS 2024 · similarity 0.85)
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.
