Research map / Detection and segmentation / 3D detection and driving
DriveFlow: Rectified Flow Adaptation for Robust 3D Object Detection in Autonomous Driving
Hongbin Lin, Yiming Yang, Chaoda Zheng, Yifan Zhang, Shuaicheng Niu, Zilu Guo, Yafeng Li, Gui Gui, Shuguang Cui, Zhen Li
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 |
|---|---|---|---|
| replace inversion-based DriveGEN editing with DriveFlow (Snow only) | MonoGround · KITTI-C Car | mean AP3D|R40: 33.38 -> 39.75 | Improved |
| use DriveFlow with one Snow augmentation instead of DriveGEN with 6 augmentations | MonoGround · KITTI-C Car | mean AP3D|R40: 37.21 -> 39.75 | Improved |
| use DriveFlow instead of DriveGEN (6 x Aug.) | MonoCD · KITTI-C Car | mean AP3D|R40: 39.44 -> 42.00 | Improved |
| use DriveFlow instead of DriveGEN (6 x Aug.) | MonoFlex · KITTI-C Pedestrian | mean AP3D|R40: 15.47 -> 21.70 | Improved |
| use DriveFlow instead of DriveGEN (6 x Aug.) | MonoFlex · KITTI-C Cyclist | mean AP3D|R40: 7.26 -> 14.17 | Improved |
| add DriveFlow Snow augmentation to detector training | MonoFlex · KITTI-C Car | mean AP3D|R40: 26.45 -> 40.99 | Improved |
| add Brightness traditional augmentation | MonoFlex · KITTI-C Car | mean AP3D|R40: 26.45 -> 20.05 | Hurt |
| add Color Jitter traditional augmentation | MonoGround · KITTI-C Car | mean AP3D|R40: 26.36 -> 26.36 | No clear effect |
| add ControlNet augmentation, 6 scenes instead of Snow only | MonoGround · KITTI-C Car | mean AP3D|R40: 10.28 -> 1.06 | Hurt |
| add FreeControl augmentation, 6 scenes instead of Snow only | MonoGround · KITTI-C Car | mean AP3D|R40: 22.43 -> 19.44 | Hurt |
| add FlowEdit Snow augmentation | MonoGround · KITTI-C Car | mean AP3D|R40: 26.36 -> 23.87 | Hurt |
| use DriveFlow instead of DriveGEN (3k Snow) | BEVFormer-tiny · nuScenes-C | mAP: 20.52 -> 21.00 | Improved |
Closest papers by meaning
- DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation (CVPR 2025 · similarity 0.87)
- UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Driving (ECCV 2026 · similarity 0.87)
- SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving (ECCV 2024 · similarity 0.87)
- CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving (NeurIPS 2025 · similarity 0.85)
- DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes (AAAI 2025 · similarity 0.85)
- CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching (NeurIPS 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.
