Research map / Detection and segmentation / Open-set and few-shot detection
Waymo Open Dataset: Panoramic Video Panoptic Segmentation
Jieru Mei, Alex Zihao Zhu, Xinchen Yan, Hang Yan, Siyuan Qiao, Yukun Zhu, Liang-Chieh Chen, Henrik Kretzschmar
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 |
|---|---|---|---|
| train one model on all views instead of five camera-specific models (ablation) | ViP-DeepLab (View eval) · WOD PVPS | wSTQ: 16.92 -> 17.78 | Improved |
| evaluate on panoramas instead of views (trained View) (ablation) | ViP-DeepLab · WOD PVPS | wSTQ: 17.78 -> 14.87 | Hurt |
| evaluate on View instead of Pano (trained Pano) (ablation) | ViP-DeepLab · WOD PVPS | wSTQ: 15.72 -> 17.56 | Improved |
| train on all views instead of five camera models (ablation) | Panoptic-DeepLab (View eval) · WOD PVPS | PQ: 35.70 -> 40.00 | Improved |
| evaluate on panoramas instead of views (trained View) (ablation) | Panoptic-DeepLab · WOD PVPS | PQ: 40.00 -> 33.65 | Hurt |
| train on panorama rather than views (Pano eval) (ablation) | ViP-DeepLab · WOD PVPS | wSQ: 38.46 -> 39.78 | Improved |
| train on all cameras instead of Front only (eval Front) (ablation) | ViP-DeepLab · WOD PVPS | wSTQ: 14.54 -> 15.63 | Improved |
| train on all cameras instead of Side Left only (eval All) (ablation) | ViP-DeepLab · WOD PVPS | wSTQ: 16.31 -> 17.78 | Improved |
Closest papers by meaning
- Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation (NeurIPS 2020 · similarity 0.89)
- Panoptic Segmentation (CVPR 2019 · similarity 0.89)
- Unifying Panoptic Segmentation for Autonomous Driving (CVPR 2022 · similarity 0.89)
- PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation (ECCV 2024 · similarity 0.89)
- Revisiting Open-Set Panoptic Segmentation (AAAI 2024 · similarity 0.87)
- Scene-Centric Unsupervised Panoptic Segmentation (CVPR 2025 · 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.
