Research map / 3D vision / NeRF and radiance fields
UniCal: Unified Neural Sensor Calibration
Ze Yang, George G Chen, Haowei Zhang, Kevin Ta, Ioan Andrei Bârsan, Daniel Murphy, Sivabalan Manivasagam, Raquel Urtasun
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 surface alignment loss (ablation) | UniCal · PandaSet | Camera rotation error (deg): 0.856 -> 0.267 | Improved |
| train multiple sensors jointly (ablation) | UniCal · PandaSet | Camera rotation error (deg): 0.469 -> 0.267 | Improved |
| add regularizer L_reg (ablation) | UniCal · PandaSet | Camera rotation error (deg): 0.288 -> 0.267 | Improved |
| add interest region sampling (ablation) | UniCal · PandaSet | Camera rotation error (deg): 0.278 -> 0.267 | Improved |
| add LiDAR intensity rendering loss (ablation) | UniCal · PandaSet | Camera rotation error (deg): 0.277 -> 0.267 | No clear effect |
| UniCal vs pose graph optimization on LiDAR-LiDAR alignment | multi-LiDAR calibration · MS-Cal | LiDAR-LiDAR registration error (cm): 2.811 (ICP) vs 2.847 (UniCal) | No clear effect |
| apply pose graph optimization after ICP over multiple LiDARs | ICP · MS-Cal | LiDAR-LiDAR registration error (cm): 2.811 -> 2.962 | Hurt |
| UniCal vs NeRF-based INF and SC-NeRF | neural calibration · MS-Cal | LiDAR-Camera reprojection error (pixel): 47.27 -> 9.27 | Improved |
Closest papers by meaning
- SOAC: Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fields (CVPR 2024 · similarity 0.87)
- The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset (NeurIPS 2026 · similarity 0.85)
- UniPAD: A Universal Pre-training Paradigm for Autonomous Driving (CVPR 2024 · similarity 0.85)
- UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving (ICLR 2024 · similarity 0.85)
- UniScene: Unified Occupancy-centric Driving Scene Generation (CVPR 2025 · similarity 0.85)
- MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception (CVPR 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.
