Super Resolve Dynamic Scene From Continuous Spike Streams

Jing Zhao, Jiyu Xie, Ruiqin Xiong, Jian Zhang, Zhaofei Yu, Tiejun Huang; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 2533-2542


Recently, a novel retina-inspired camera, namely spike camera, has shown great potential for recording high-speed dynamic scenes. Unlike the conventional digital cameras that compact the visual information within the exposure interval into a single snapshot, the spike camera continuously outputs binary spike streams to record the dynamic scenes, yielding a very high temporal resolution. Most of the existing reconstruction methods for spike camera focus on reconstructing images with the same resolution as spike camera. However, as a trade-off of high temporal resolution, the spatial resolution of spike camera is limited, resulting in inferior details of the reconstruction. To address this issue, we develop a spike camera super-resolution framework, aiming to super resolve high-resolution intensity images from the low-resolution binary spike streams. Due to the relative motion between the camera and the objects to capture, the spikes fired by the same sensor pixel no longer describes the same points in the external scene. In this paper, we properly exploit the relative motion and derive the relationship between light intensity and each spike, so as to recover the external scene with both high temporal and high spatial resolution. Experimental results demonstrate that the proposed method can reconstruct pleasant high-resolution images from low-resolution spike streams.

Related Material

[pdf] [supp]
@InProceedings{Zhao_2021_ICCV, author = {Zhao, Jing and Xie, Jiyu and Xiong, Ruiqin and Zhang, Jian and Yu, Zhaofei and Huang, Tiejun}, title = {Super Resolve Dynamic Scene From Continuous Spike Streams}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {2533-2542} }