Research map / Video / Video segmentation and tracking
Understanding Road Layout From Videos as a Whole
Buyu Liu, Bingbing Zhuang, Samuel Schulter, Pan Ji, Manmohan Chandraker
Check 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 |
|---|---|---|---|
| Combine local BEV with global BEV-COLMAP input | Road layout prediction · KITTI | IOU: .345 -> .416 | Improved |
| Add object context to joint local and global input | BEV-J · KITTI | F1.-Bi: .458 -> .494 | Improved |
| Use LSTM with BEV-J-O input | Road layout prediction · KITTI | F1.-Bi: .494 -> .537 | Improved |
| Add FTM to the LSTM model | +LSTM · KITTI | temp.: 2.78 -> 1.96 | Improved |
| Use denser COLMAP reconstruction (ablation) | BEV-C · KITTI | F1.-Bi.: .456 -> .496 | Improved |
| Add object information to BEV-C input (ablation) | BEV-C · KITTI | F1.-Bi.: .456 -> .507 | Improved |
Closest papers by meaning
- TUMTraf VideoQA: Dataset and Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes (ICML 2025 · similarity 0.85)
- 3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline (ICLR 2025 · similarity 0.85)
- RoadSceneBench: A Lightweight Benchmark for Mid-Level Road Scene Understanding (CVPR 2026 · similarity 0.85)
- MoST: Multi-Modality Scene Tokenization for Motion Prediction (CVPR 2024 · similarity 0.84)
- Motion Graph Unleashed: A Novel Approach to Video Prediction (NeurIPS 2024 · similarity 0.84)
- GigaTraj: Predicting Long-term Trajectories of Hundreds of Pedestrians in Gigapixel Complex Scenes (CVPR 2024 · similarity 0.84)
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.
