A Benchmark for Video Dehazing.
Accepted by IJCV on 13 January 2020. We propose a dual-branch convolutional neural network to extract base features and recovered features separately. The base features contain local and global information of the input image.
Accepted by BMVC 2018 as Oral presentation. SISR is a fundamental task for vision applications to enhance image quality with respect to spatial resolution. If the input image contains degraded pixels, the artifacts caused by the degradation could be amplified by SR methods.
Accepted by ICASSP 2018. In this paper, we propose an end-to-end convolution neural network(CNN) to restore a clear high-resolution image from a severely blurry image.
This is Xinyi Zhang's personal website. I'm a researcher in computer vision, and also have a cute furry puppy, four years old. It's great to have you. We can be in touch in these ways.
Stay up to date! Get all the latest & greatest posts delivered straight to your inbox