"image reconstruction"

A Generative Compression Framework For Low Bandwidth Video Conference

Video conferences introduce a new scenario for video transmission, which focuses on keeping the fidelity of faces even in the low bandwidth network environment. In this work, we propose VSBNet, one of the frameworks to utilize face landmarks in video …

TSGAN: A Two-Stream Generative Adversarial Network for Bit-Depth Expansion

The rapid development of display devices and the continuous improvement of visual quality requirements put urgent demands on high bit-depth (HBD) image, but most legacy data are stored and transmitted at low bit-depth (LBD). Bit-depth expansion (BDE) …

Learning-Based Quality Enhancement For Scalable Coded Video Over Packet Lossy Networks

The layered feature of scalable video coding (SVC) offers a sufficient adaptation to unreliable transmission. When network condition drops sharply, enhancement layers will be abandoned, and only base layers are delivered. However, this will cause …

Compression Priors Assisted Convolutional Neural Network for Fractional Interpolation

Fractional interpolation has been extensively utilized in a series of video coding standards to generate fractional precision prediction to remove the temporal redundancy in consecutive frames. In the traditional interpolation filter based methods, …

CNN based post-processing to improve HEVC

In this paper, we propose a frame-based dynamic metadata post-processing scheme in HEVC. Video sequence is classified into different categories contains complexity of video content and quality indicator for each frame, an up-to-one byte flag embedded …

Paralleling variable block size motion estimation of HEVC on CPU plus GPU platform

The emerging HEVC standard supports up to 12 variable block sizes ranging from 4×8/8×4 to 64×64 to conduct motion estimation (ME) and motion compensation (MC). This feature contributes considerable coding gain compared with 7 variable block sizes in …