Event-based Continuous Color Video Decompression from Single Frames
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917996466798592 |
|---|---|
| author | Wang, Ziyun Hamann, Friedhelm Chaney, Kenneth Jiang, Wen Gallego, Guillermo Daniilidis, Kostas |
| author_facet | Wang, Ziyun Hamann, Friedhelm Chaney, Kenneth Jiang, Wen Gallego, Guillermo Daniilidis, Kostas |
| contents | We present ContinuityCam, a novel approach to generate a continuous video from a single static RGB image and an event camera stream. Conventional cameras struggle with high-speed motion capture due to bandwidth and dynamic range limitations. Event cameras are ideal sensors to solve this problem because they encode compressed change information at high temporal resolution. In this work, we tackle the problem of event-based continuous color video decompression, pairing single static color frames and event data to reconstruct temporally continuous videos. Our approach combines continuous long-range motion modeling with a neural synthesis model, enabling frame prediction at arbitrary times within the events. Our method only requires an initial image, thus increasing the robustness to sudden motions, light changes, minimizing the prediction latency, and decreasing bandwidth usage. We also introduce a novel single-lens beamsplitter setup that acquires aligned images and events, and a novel and challenging Event Extreme Decompression Dataset (E2D2) that tests the method in various lighting and motion profiles. We thoroughly evaluate our method by benchmarking color frame reconstruction, outperforming the baseline methods by 3.61 dB in PSNR and by 33% decrease in LPIPS, as well as showing superior results on two downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_00113 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Event-based Continuous Color Video Decompression from Single Frames Wang, Ziyun Hamann, Friedhelm Chaney, Kenneth Jiang, Wen Gallego, Guillermo Daniilidis, Kostas Computer Vision and Pattern Recognition We present ContinuityCam, a novel approach to generate a continuous video from a single static RGB image and an event camera stream. Conventional cameras struggle with high-speed motion capture due to bandwidth and dynamic range limitations. Event cameras are ideal sensors to solve this problem because they encode compressed change information at high temporal resolution. In this work, we tackle the problem of event-based continuous color video decompression, pairing single static color frames and event data to reconstruct temporally continuous videos. Our approach combines continuous long-range motion modeling with a neural synthesis model, enabling frame prediction at arbitrary times within the events. Our method only requires an initial image, thus increasing the robustness to sudden motions, light changes, minimizing the prediction latency, and decreasing bandwidth usage. We also introduce a novel single-lens beamsplitter setup that acquires aligned images and events, and a novel and challenging Event Extreme Decompression Dataset (E2D2) that tests the method in various lighting and motion profiles. We thoroughly evaluate our method by benchmarking color frame reconstruction, outperforming the baseline methods by 3.61 dB in PSNR and by 33% decrease in LPIPS, as well as showing superior results on two downstream tasks. |
| title | Event-based Continuous Color Video Decompression from Single Frames |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.00113 |