Research map / Video / Video segmentation and tracking
Events-To-Video: Bringing Modern Computer Vision to Event Cameras
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 |
|---|---|---|---|
| Reconstruct event streams as natural-image videos with a recurrent network | Event Camera Dataset · Event Camera Dataset (mean) | SSIM: 0.462 -> 0.555 | Helped |
| Reconstruct event streams as natural-image videos with a recurrent network | Event Camera Dataset · Event Camera Dataset (mean) | LPIPS: 0.530 -> 0.422 | Helped |
| Classify reconstructed event images with a fine-tuned CNN | N-MNIST · N-MNIST | classification accuracy: 0.991 -> 0.983 | Hurt |
| Classify reconstructed event images with a fine-tuned ResNet-18 | N-CARS · N-CARS | classification accuracy: 0.904 -> 0.910 | Helped |
| Classify reconstructed event images with a fine-tuned ResNet-18 | N-Caltech101 · N-Caltech101 | classification accuracy: 0.700 -> 0.866 | Helped |
| Use reconstructed images with a classifier trained on conventional images, without event-data fine-tuning | N-Caltech101 · N-Caltech101 | classification accuracy: 0.700 -> 0.821 | Helped |
| Run VINS-Mono on videos reconstructed from events | Event Camera Dataset VIO · Event Camera Dataset VIO (median) | mean translation error (m): 0.27 -> 0.15 | Helped |
| Run VINS-Mono on videos reconstructed from events instead of UltimateSLAM with events and frames | Event Camera Dataset VIO · Event Camera Dataset VIO (median) | mean translation error (m): 0.17 -> 0.15 | No clear effect |
Closest papers by meaning
- Video to Events: Recycling Video Datasets for Event Cameras (CVPR 2020 · similarity 0.94)
- Learning to Detect Objects with a 1 Megapixel Event Camera (NeurIPS 2020 · similarity 0.91)
- Learning To Reconstruct High Speed and High Dynamic Range Videos From Events (CVPR 2021 · similarity 0.91)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.89)
- E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning (AAAI 2024 · similarity 0.89)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 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.