Research map / Point clouds / Registration and matching
E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning
Xiuhong Lin, Changjie Qiu, zhipeng cai, Siqi Shen, Yu Zang, Weiquan Liu, Xuesheng Bian, Matthias Müller, Cheng Wang
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 |
|---|---|---|---|
| remove separation of spatial and temporal domains in STA (ablation) | E2PNet · MVSEC-E2P (LCD) | RE (deg): 3.710 -> 3.606 | Improved |
| add the STA module (ablation) | E2PNet · MVSEC-E2P (LCD) | RE (deg): 3.922 -> 3.606 | Improved |
| add LA and FP modules (ablation) | E2PNet · MVSEC-E2P (LCD) | RE (deg): 4.878 -> 3.606 | Improved |
| add LA, STA and FP (full EP2T) (ablation) | E2PNet · MVSEC-E2P (LCD) | TE (m): 1.297 -> 0.821 | Improved |
| replace grayscale images with event tensor from E2PNet | LCD · MVSEC-E2P | RE (deg): 6.335 -> 3.606 | Improved |
| replace grayscale images with event tensor from E2PNet | DeepI2P · VECtor-E2P | TE (m): 3.176 -> 2.454 | Improved |
| replace grayscale images with event tensor from E2PNet | LCD · VECtor-E2P | TE (m): 13.200 -> 7.403 | Improved |
| use tensor output (TR) instead of point-based features (ablation) | E2PNet · MVSEC-E2P (LCD) | RE (deg): 4.422 -> 3.606 | Improved |
| use tensor output (TR) instead of point-based features (ablation) | E2PNet · MVSEC-E2P (LCD) | TE (m): 0.768 -> 0.821 | Mixed |
| add EP2T module to cGAN flow baseline | cGAN · Flow estimation | AEE: 0.34 -> 0.30 | Improved |
| add EP2T module to EV-FlowNet | EV-Flow · Flow estimation | outlier %: 0.03 -> 0.03 | No clear effect |
| add EP2T module to EST | EST · N-caltech101 recognition | accuracy: 0.746 -> 0.771 | Improved |
Closest papers by meaning
- Scalable Event Cloud Network for Event-based Classification (ICML 2026 · similarity 0.87)
- Rethinking Efficient and Effective Point-Based Networks for Event Camera Classification and Regression (TPAMI 2025 · similarity 0.86)
- Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension (CVPR 2024 · similarity 0.85)
- E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning (AAAI 2024 · similarity 0.85)
- EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation (CVPR 2025 · similarity 0.84)
- Partial Point Cloud Registration with Multi-view 2D Image Learning (AAAI 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.
