Deep Optics for Video Snapshot Compressive Imaging

1 code implementation • ICCV 2023 • Ping Wang, Lishun Wang, Xin Yuan

We believe this is a milestone for real-world video SCI.

WaveNet: Wave-Aware Image Enhancement

1 code implementation • The Pacific Conference on Computer Graphics and Applications, Pacific Graphics 2023 • Jiachen Dang, Zehao Li, Yong Zhong, Lishun Wang

In this paper, we formulate the enhancement into a signal modulation problem and propose the WaveNet architecture, which performs well in various parameters and improves the feature expression using wave-like feature representation.

Image Retouching Low-Light Image Enhancement

EfficientSCI: Densely Connected Network with Space-time Factorization for Large-scale Video Snapshot Compressive Imaging

1 code implementation • CVPR 2023 • Lishun Wang, Miao Cao, Xin Yuan

We are the first time to show that an UHD color video with high compression ratio can be reconstructed from a snapshot 2D measurement using a single end-to-end deep learning model with PSNR above 32 dB.

Spatial-Temporal Transformer for Video Snapshot Compressive Imaging

1 code implementation • 4 Sep 2022 • Lishun Wang, Miao Cao, Yong Zhong, Xin Yuan

In this paper, we consider the reconstruction algorithm in video SCI, i. e., recovering a series of video frames from a compressed measurement.

Video Reconstruction

Spectral Compressive Imaging Reconstruction Using Convolution and Contextual Transformer

1 code implementation • 15 Jan 2022 • Lishun Wang, Zongliang Wu, Yong Zhong, Xin Yuan

Spectral compressive imaging (SCI) is able to encode the high-dimensional hyperspectral image to a 2D measurement, and then uses algorithms to reconstruct the spatio-spectral data-cube.

Inductive Bias