Year: 2025
Type: preprint
Abstract: Event-based cameras offer unique advantages such as high temporal resolution, high dynamic range, and low power consumption. However, the massive storage requirements and I/O burdens of existing synthetic data generation pipelines and the scarcity of real data prevent event-based training datasets from scaling up, limiting the development and generalization capabilities of event vision models. To address this challenge, we introduce Video-to-Voxel (V2V), an approach that directly converts conventional video frames into event-based voxel grid representations, bypassing the storage-intensive event stream generation entirely. V2V enables a 150 times reduction in storage requirements while supporting on-the-fly parameter randomization for enhanced model robustness. Leveraging this efficiency, we train several video reconstruction and optical flow estimation model architectures on 10,000 diverse videos totaling 52 hours--an order of magnitude larger than existing event datasets, yielding substantial improvements.
Source: arXiv (Cornell University)
Language: English
Topic: Advanced Vision and Imaging
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6979329987
Cites:
Cited by:
Related to: