Research map / 3D vision / Depth and stereo
Full-Velocity Radar Returns by Radar-Camera Fusion
Yunfei Long, Daniel Morris, Xiaoming Liu, Marcos Castro, Punarjay Chakravarty, Praveen Narayanan
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 |
|---|---|---|---|
| add the R2P network for radar-camera association (vs raw projection) (ablation) | full-velocity estimator · nuScenes point-wise velocity (moving points) | mean full velocity error (m/s): 0.577 -> 0.433 | Improved |
| add the R2P network for radar-camera association (vs raw projection) (ablation) | full-velocity estimator · nuScenes point-wise velocity (moving points) | mean tangential error (m/s): 0.472 -> 0.322 | Improved |
| add camera optical flow to recover tangential velocity (vs raw radial velocity) | radar returns · nuScenes point-wise velocity (moving points) | mean full velocity error (m/s): 1.599 -> 0.433 | Improved |
| use point-wise full velocity from radar-camera fusion (vs CenterFusion) | object velocity estimation · nuScenes object-wise velocity | velocity error (m/s): 0.826 -> 0.451 | Improved |
| compensate accumulated radar points with full velocity (vs radial velocity) | BoxNet pose estimation · nuScenes pose estimation with BoxNet | center error (m): 0.997 -> 0.834 | Improved |
| compensate accumulated radar points with full velocity (vs radial velocity) | BoxNet pose estimation · nuScenes pose estimation with BoxNet | orientation error (degree): 7.517 -> 6.873 | Improved |
| compensate accumulated radar points with full velocity (vs radial velocity) | BoxNet pose estimation · nuScenes pose estimation with BoxNet | IoU: 0.462 -> 0.546 | Improved |
| add full-velocity motion compensation to radar accumulation (vs none or radial) | radar point accumulation · nuScenes accumulation up to 25 frames | accumulation error | Improved |
Closest papers by meaning
- RaVF: Learning Radar Velocity Fields via Spatial-Doppler Guidance (NeurIPS 2026 · similarity 0.86)
- RICCARDO: Radar Hit Prediction and Convolution for Camera-Radar 3D Object Detection (CVPR 2025 · similarity 0.84)
- Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation (NeurIPS 2026 · similarity 0.84)
- HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection (AAAI 2025 · similarity 0.84)
- RadarMOSEVE: A Spatial-Temporal Transformer Network for Radar-Only Moving Object Segmentation and Ego-Velocity Estimation (AAAI 2024 · similarity 0.84)
- CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detection (NeurIPS 2024 · similarity 0.83)
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.
