Research map / Vision-language and multimodal / Cross-modal learning
LiREC-Net: A Target-Free and Learning-Based Network for LiDAR, RGB, and Event Calibration
Aditya Ranjan Dash, Ramy Battrawy, René Schuster, Didier Stricker
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 depth-map features to point features in shared LiDAR branch (ablation) | LiREC-Net · DSEC LiDAR-RGB | translation error (cm): 14.43 -> 2.51 | Improved |
| add point features to depth features (ablation) | LiREC-Net · DSEC LiDAR-RGB | rotation error (deg): 0.70 -> 0.14 | Improved |
| add point and depth fusion (ablation) | LiREC-Net · DSEC LiDAR-Event | translation error (cm): 2.16 -> 1.18 | Improved |
| add scaled depth projection (SDP) (ablation) | LiREC-Net · DSEC LiDAR-Event | translation error (cm): 3.72 -> 1.18 | Improved |
| add scaled feature projection (SFP) (ablation) | LiREC-Net · DSEC LiDAR-Event | translation error (cm): 1.45 -> 1.18 | Improved |
| add scaled feature projection (SFP) (ablation) | LiREC-Net · DSEC LiDAR-Event | rotation error (deg): 0.07 -> 0.07 | No clear effect |
| use MViTV2 instead of ResNet encoders (ablation) | LiREC-Net · DSEC LiDAR-RGB | translation error (cm): 3.04 -> 2.51 | Improved |
| use MViTV2 instead of ResNet encoders (ablation) | LiREC-Net · DSEC LiDAR-Event | translation error (cm): 2.45 -> 1.18 | Improved |
| train jointly tri-modal with shared LiDAR branch vs separate bi-modal networks (ablation) | LiREC-Net · KITTI | inference time (s): 0.51 -> 0.33 | Improved |
| train jointly tri-modal vs separate bi-modal networks (ablation) | LiREC-Net · KITTI LiDAR-RGB | translation error (cm): 2.08 -> 1.80 | Improved |
| train jointly tri-modal vs separate bi-modal networks (ablation) | LiREC-Net · DSEC LiDAR-RGB (5 stages) | translation error (cm): 1.40 -> 2.51 | Hurt |
| train jointly tri-modal vs separate bi-modal networks (ablation) | LiREC-Net · DSEC LiDAR-Event (5 stages) | translation error (cm): 1.31 -> 1.18 | Improved |
Closest papers by meaning
- SOAC: Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fields (CVPR 2024 · similarity 0.85)
- AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking (NeurIPS 2024 · similarity 0.85)
- LiT: Unifying LiDAR "Languages" with LiDAR Translator (NeurIPS 2024 · similarity 0.85)
- LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance (NeurIPS 2026 · similarity 0.84)
- Multi-Space Alignments Towards Universal LiDAR Segmentation (CVPR 2024 · similarity 0.84)
- LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation (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.
