activity
20172020
most citedLearning a Virtual Codec Based on Deep Convolutional Neural Network to Compress Image

7 citations · 9 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CV2020

Deep Optimized Multiple Description Image Coding via Scalar Quantization Learning

Lijun Zhao, Huihui Bai, Anhong Wang +1

In this paper, we introduce a deep multiple description coding (MDC) framework optimized by minimizing multiple description (MD) compressive loss. First, MD multi-scale-dilated enc…

cs.CV2020

Concurrently Extrapolating and Interpolating Networks for Continuous Model Generation

Lijun Zhao, Jinjing Zhang, Fan Zhang +3

Most deep image smoothing operators are always trained repetitively when different explicit structure-texture pairs are employed as label images for each algorithm configured with…

cs.MM2018

Deep Multiple Description Coding by Learning Scalar Quantization

Lijun Zhao, Huihui Bai, Anhong Wang +1

In this paper, we propose a deep multiple description coding framework, whose quantizers are adaptively learned via the minimization of multiple description compressive loss. First…

eess.IV2018

Virtual Codec Supervised Re-Sampling Network for Image Compression

Lijun Zhao, Huihui Bai, Anhong Wang +1

In this paper, we propose an image re-sampling compression method by learning virtual codec network (VCN) to resolve the non-differentiable problem of quantization function for ima…

cs.CV2018

Mixed-Resolution Image Representation and Compression with Convolutional Neural Networks

Lijun Zhao, Huihui Bai, Feng Li +2

In this paper, we propose an end-to-end mixed-resolution image compression framework with convolutional neural networks. Firstly, given one input image, feature description neural…

cs.CV20187 cited

Learning a Virtual Codec Based on Deep Convolutional Neural Network to Compress Image

Lijun Zhao, Huihui Bai, Anhong Wang +1

Although deep convolutional neural network has been proved to efficiently eliminate coding artifacts caused by the coarse quantization of traditional codec, it's difficult to train…