Research map / 3D vision / Depth and stereo
Learning Optical Flow from Event Camera with Rendered Dataset
Xinglong Luo, Kunming Luo, Ao Luo, Zhengning Wang, Ping Tan, Shuaicheng Liu
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 |
|---|---|---|---|
| train on rendered MDR dataset instead of MVSEC (ablation) | E-RAFT · MVSEC dense dt=1 | EPE: 1.19 -> 0.59 | Improved |
| train on MDR instead of MVSEC (ablation) | PWCNet · MVSEC dense dt=4 | EPE: 4.03 -> 2.92 | Improved |
| plug in ADM module (ablation) | KPAFlow trained on MDR · MVSEC dense dt=4 | EPE: 2.33 -> 1.61 | Improved |
| plug in ADM module (ablation) | E-RAFT trained on MVSEC · MVSEC dense dt=1 | EPE: 1.19 -> 0.82 | Improved |
| add MDC plugin only (ablation) | KPAFlow · MVSEC dense dt=1 | EPE: 0.58 -> 0.57 | No clear effect |
| add MDS density selection module (ablation) | KPAFlow + MDC · MVSEC dense dt=4 | EPE: 2.20 -> 1.92 | Improved |
| add L_MDC loss (ablation) | KPAFlow + MDC + MDS · MVSEC dense dt=4 | EPE: 1.92 -> 1.66 | Improved |
| add L_MDS loss (ablation) | KPAFlow + MDC + MDS + L_MDC · MVSEC dense dt=4 | EPE: 1.66 -> 1.61 | Improved |
| increase average event density of training set | SKFlow, GMA, FlowFormer, KPA-Flow · MVSEC | EPE | Mixed |
Closest papers by meaning
- Learning Efficient Meshflow and Optical Flow From Event Cameras (TPAMI 2025 · similarity 0.92)
- Secrets of Event-Based Optical Flow (ECCV 2022 · similarity 0.91)
- Efficient Meshflow and Optical Flow Estimation from Event Cameras (CVPR 2024 · similarity 0.90)
- Dense Continuous-Time Optical Flow From Event Cameras (TPAMI 2024 · similarity 0.89)
- EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation (CVPR 2025 · similarity 0.88)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.87)
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.
