scispace - formally typeset
F

Fan Hongfei

Researcher at Hong Kong Polytechnic University

Publications -  17
Citations -  168

Fan Hongfei is an academic researcher from Hong Kong Polytechnic University. The author has contributed to research in topics: Image processing & Image restoration. The author has an hindex of 2, co-authored 17 publications receiving 122 citations. Previous affiliations of Fan Hongfei include Seoul National University.

Papers
More filters
Proceedings ArticleDOI

NTIRE 2019 Challenge on Real Image Super-Resolution: Methods and Results

TL;DR: The 3rd NTIRE challenge on single-image super-resolution (restoration of rich details in a low-resolution image) is reviewed with a focus on proposed solutions and results and the state-of-the-art in real-world single image super- resolution.
Patent

Image processing method and device, electronic equipment and storage medium

TL;DR: In this article, the authors proposed a method for denoising a to-be-processed image by adopting a plurality of quality parameters and inputting the image into a preset image denoing model corresponding to the target quality parameter to obtain a denoised image.
Patent

Processing method and device for super-resolution reconstruction of image

TL;DR: In this article, the authors proposed a method for super-resolution reconstruction of an image. But the method is limited to a single image and requires the reconstruction of a target area and a background area.
Patent

Video encoding method and device and electronic equipment

TL;DR: In this article, the authors proposed a video coding method and device and electronic equipment, which relates to the technical field of computer vision, and the method comprises the steps: obtaining a plurality of to-be-coded segmented video streams; wherein the plurality of segmented videos streams are obtained by segmenting an original video stream to be encoded; writing the plurality thereof into a preset first thread and a preset second thread respectively, wherein the first thread is used for determining a video scene corresponding to the segmentedvideo stream, and then the second thread isused for encoding the segment