no code implementations • CVPR 2021 • Peiqi Duan, Zihao W. Wang, Xinyu Zhou, Yi Ma, Boxin Shi
EventZoom is trained in a noise-to-noise fashion where the two ends of the network are unfiltered noisy events, enforcing noise-free event restoration.
no code implementations • 29 May 2021 • Srutarshi Banerjee, Henry H. Chopp, Jianping Zhang, Zihao W. Wang, Oliver Cossairt, Aggelos Katsaggelos
The detection and tracking of objects in the scene are done on the distorted data at the host.
1 code implementation • 9 Dec 2020 • Alexis Baudron, Zihao W. Wang, Oliver Cossairt, Aggelos K. Katsaggelos
We first introduce an event-to-silhouette (E2S) neural network module to transform a stack of event frames to the corresponding silhouettes, with additional neural branches for camera pose regression.
no code implementations • CVPR 2020 • Zihao W. Wang, Peiqi Duan, Oliver Cossairt, Aggelos Katsaggelos, Tiejun Huang, Boxin Shi
The filtered output represents the temporal gradient of the captured space-time volume, which can be viewed as motion-compensated event frames with high resolution and low noise.
no code implementations • 3 May 2020 • Srutarshi Banerjee, Zihao W. Wang, Henry H. Chopp, Oliver Cossairt, Aggelos Katsaggelos
The histograms are then variably sampled via Poisson Disk Sampling prioritized by the QT based segmentation map.
1 code implementation • 26 Feb 2019 • Zihao W. Wang, Weixin Jiang, Kuan He, Boxin Shi, Aggelos Katsaggelos, Oliver Cossairt
Temporal Video Frame Synthesis (TVFS) aims at synthesizing novel frames at timestamps different from existing frames, which has wide applications in video codec, editing and analysis.
no code implementations • 25 Feb 2019 • Zihao W. Wang, Vibhav Vineet, Francesco Pittaluga, Sudipta Sinha, Oliver Cossairt, Sing Bing Kang
We propose a lens-free coded aperture camera system for human action recognition that is privacy-preserving.