F
Feng Wu
Researcher at University of Science and Technology of China
Publications - 669
Citations - 19574
Feng Wu is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Motion compensation & Data compression. The author has an hindex of 60, co-authored 645 publications receiving 15886 citations. Previous affiliations of Feng Wu include Center for Excellence in Education & Microsoft.
Papers
More filters
Journal ArticleDOI
An Iterative BP-CNN Architecture for Channel Decoding
Fei Liang,Cong Shen,Feng Wu +2 more
TL;DR: A novel iterative belief propagation – convolutional neural network (BP-CNN) architecture for channel decoding under correlated noise that concatenates a trained CNN with a standard BP decoder and the introduction of the normality test to the CNN training shapes the residual noise distribution.
Journal ArticleDOI
Adaptive Directional Lifting-Based Wavelet Transform for Image Coding
TL;DR: Experimental results show that the proposed ADL-based image coding technique outperforms JPEG 2000 in both PSNR and visual quality, with the improvement up to 2.0 dB on images with rich orientation features.
Patent
Systems and methods with error resilience in enhancement layer bitstream of scalable video coding
TL;DR: In this paper, a scalable layered video coding scheme that encodes video data frames into multiple layers, including a base layer of comparatively low quality video and multiple enhancement layers of increasingly higher quality video, adds error resilience to the enhancement layer.
Book ChapterDOI
A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding
Yuanying Dai,Dong Liu,Feng Wu +2 more
TL;DR: A CNN-based post-processing algorithm for High Efficiency Video Coding (HEVC), the state-of-the-art video coding standard, that outperforms previously studied networks in achieving higher bit-rate reduction, lower memory cost, and multiplied computational speedup.
Journal ArticleDOI
Image Compression With Edge-Based Inpainting
TL;DR: This paper proposes an image compression framework towards visual quality rather than pixel-wise fidelity, and constructs a practical system to verify the effectiveness of the compression approach in which edge map serves as assistant information and the edge extraction and region removal approaches are developed accordingly.