Research map / Point clouds / Point cloud classification
Depth Estimation From Camera Image and mmWave Radar Point Cloud
Akash Deep Singh, Yunhao Ba, Ankur Sarker, Howard Zhang, Achuta Kadambi, Stefano Soatto, Mani Srivastava, Alex Wong
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 |
|---|---|---|---|
| use learned RadarNet correspondence mapping and gated radar-camera fusion instead of DORN | camera-radar depth estimation · nuScenes test, 0-50m | MAE: 10.3% | Improved |
| use learned RadarNet correspondence mapping and gated radar-camera fusion instead of DORN | camera-radar depth estimation · nuScenes test, 0-50m | RMSE: 9.1% | Improved |
| add RadarNet to map raw radar points to probable image surfaces (ablation) | FusionNet · nuScenes test, 0-50m | MAE: 1942.5 -> 1727.7 | Improved |
| add RadarNet to map raw radar points to probable image surfaces (ablation) | FusionNet · nuScenes test, 0-50m | RMSE: 3986.1 -> 3746.8 | Improved |
| add RadarNet to map raw radar points to probable image surfaces (ablation) | FusionNet · nuScenes test, 0-70m | MAE: 2318.2 -> 2073.2 | Improved |
| add RadarNet to map raw radar points to probable image surfaces (ablation) | FusionNet · nuScenes test, 0-70m | RMSE: 4825.0 -> 4590.7 | Improved |
| add RadarNet to map raw radar points to probable image surfaces (ablation) | FusionNet · nuScenes test, 0-80m | MAE: 2441.0 -> 2179.3 | Improved |
| add RadarNet to map raw radar points to probable image surfaces (ablation) | FusionNet · nuScenes test, 0-80m | RMSE: 5141.4 -> 4898.7 | Improved |
Closest papers by meaning
- Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation (NeurIPS 2026 · similarity 0.91)
- TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion (CVPR 2025 · similarity 0.91)
- HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection (AAAI 2025 · similarity 0.87)
- Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views (AAAI 2024 · similarity 0.86)
- RCTrans: Radar-Camera Transformer via Radar Densifier and Sequential Decoder for 3D Object Detection (AAAI 2025 · similarity 0.85)
- D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction (NeurIPS 2025 · 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.
