Research map / 3D vision / Depth and stereo
Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 reconstruction networks using event-based photometric constancy without ground-truth or synthetic training data | E2VID_E and FireNet_E · ECD and HQF | reconstruction quality | Mixed |
| use FireFlowNet instead of EV-FlowNet | event-based optical flow estimation · ECD and HQF | FWL: 1.31 -> 1.39; 1.51 -> 1.58 | Mixed |
| use FireFlowNet instead of EV-FlowNet | event-based optical flow estimation · MVSEC | AEE: 0.92 -> 1.06; 0.79 -> 0.97; 1.40 -> 1.67; 1.18 -> 1.43 | Hurt |
| replace EV-FlowNet with FireFlowNet | event-based optical flow estimation · 240×180 inference | GPU inference time (ms): 4.33 -> 1.97 | Helped |
| add event deblurring before event integration (ablation) | E2VID_E reconstruction · ECD | MSE: 0.14 -> 0.06 | Helped |
| add event deblurring before event integration (ablation) | E2VID_E reconstruction · ECD | SSIM: 0.30 -> 0.55 | Helped |
| add event deblurring before event integration (ablation) | E2VID_E reconstruction · ECD | LPIPS: 0.58 -> 0.37 | Helped |
| add event deblurring before event integration (ablation) | E2VID_E reconstruction · HQF | MSE: 0.11 -> 0.06 | Helped |
| add event deblurring before event integration (ablation) | E2VID_E reconstruction · HQF | SSIM: 0.28 -> 0.48 | Helped |
| add event deblurring before event integration (ablation) | E2VID_E reconstruction · HQF | LPIPS: 0.64 -> 0.47 | Helped |
Closest papers by meaning
- Events-To-Video: Bringing Modern Computer Vision to Event Cameras (CVPR 2019 · similarity 0.90)
- Simultaneous Optical Flow and Intensity Estimation From an Event Camera (CVPR 2016 · similarity 0.89)
- Single Image Optical Flow Estimation With an Event Camera (CVPR 2020 · similarity 0.88)
- Video to Events: Recycling Video Datasets for Event Cameras (CVPR 2020 · similarity 0.88)
- Graph Neural Network Combining Event Stream and Periodic Aggregation for Low-Latency Event-based Vision (CVPR 2025 · similarity 0.88)
- EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation (CVPR 2025 · similarity 0.86)
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.