Research map / Detection and segmentation / Open-set and few-shot detection
Unifying Panoptic Segmentation for Autonomous Driving
Oliver Zendel, Matthias Schörghuber, Bernhard Rainer, Markus Murschitz, Csaba Beleznai
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 |
|---|---|---|---|
| Add WD2 frames through mixed-dataset fine-tuning of the MVD-trained model | mvd100 · WD2 benchmark | PQ: 37.6% -> 42.2% | Improved |
| Add WD2 frames through mixed-dataset fine-tuning of the MVD-trained model | mvd100 · MVD validation | PQ: 35.1% -> 34.1% | Hurt |
| Add WD2 frames through mixed-dataset fine-tuning of the MVD-trained model | mvd100 · WD2 benchmark | PQpickup: 38.1% -> 49.2% | Improved |
| Evaluate frames with visual hazards, including blur, coverage, particles, and screen effects | mvd100 · WD2 benchmark visual-hazard subsets | PQ: blur -22.6%; coverage -46.6%; particles -30.0%; screen -28.7% | Hurt |
| Add WD2 frames through mixed-dataset fine-tuning | mvd100 · WD2 benchmark visual-hazard subsets | PQ | Improved |
Closest papers by meaning
- PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving (CVPR 2026 · similarity 0.89)
- Waymo Open Dataset: Panoramic Video Panoptic Segmentation (ECCV 2022 · similarity 0.89)
- Prior2Former - Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation (ICCV 2025 · similarity 0.88)
- Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving (CVPR 2025 · similarity 0.86)
- PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation (CVPR 2024 · similarity 0.86)
- ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving (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.
