Research map / Detection and segmentation / 3D detection and driving
Joint 3D Instance Segmentation and Object Detection for Autonomous Driving
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use Spatial Embedding instead of feature embedding and directional losses (ablation) | Joint detection and instance segmentation framework · KITTI instance segmentation | Mean AP: 40.78 -> 47.15 | Helped |
| Use Spatial Embedding instead of feature embedding and directional losses (ablation) | Joint detection and instance segmentation framework · KITTI instance segmentation | AP50: 64.75 -> 74.83 | Helped |
| Use Spatial Embedding instead of feature embedding and directional losses (ablation) | Joint detection and instance segmentation framework · KITTI instance segmentation | AP75: 43.25 -> 49.40 | Helped |
| Use Spatial Embedding instead of feature embedding and directional losses (ablation) | Joint detection and instance segmentation framework · KITTI instance segmentation | AP90: 8.53 -> 12.93 | Helped |
| Use the proposed joint detector | KITTI test Car detection · KITTI test, Car 3D detection, moderate and hard | AP3D70: 79.71 -> 78.96; 75.09 -> 74.30 | Mixed |
| Use the proposed joint detector | KITTI validation Car detection · KITTI validation, Car BEV detection | APBEV70 Hard: 83.81 -> 86.45 | Helped |
Closest papers by meaning
- Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth (CVPR 2019 · similarity 0.88)
- IDA-3D: Instance-Depth-Aware 3D Object Detection From Stereo Vision for Autonomous Driving (CVPR 2020 · similarity 0.87)
- One Million Scenes for Autonomous Driving: ONCE Dataset (NeurIPS 2021 · similarity 0.86)
- DALDet: Depth-Aware Learning Based Object Detection for Autonomous Driving (AAAI 2024 · similarity 0.85)
- Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking (CVPR 2025 · similarity 0.85)
- Segment Anything, Even Occluded (CVPR 2025 · 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.