Translator Disclaimer
1 June 2020 Build receptive pyramid for efficient color image compression artifact reduction
Author Affiliations +

A traditional image pyramid is an effective way to extract multiscale features. However, for image restoration, downsampling and upsampling lose details in the original resolution and result in an over smooth result. To overcome this defect, we propose a receptive pyramid (RP) that replaces downsampling by dilated convolution to extract multiscale features on the original resolution and make a full resolution correction. We present an RP-based convolution neural network named receptive pyramid convolutional network (RPCN) for efficient color image compression artifact reduction (CAR). Specifically, we propose residual connected convolution blocks as the baseline of RPCN. RPs work in convolution blocks to extract the hierarchical multiscale features for local feature correction. Moreover, the global feature fusion and vector correction are also introduced to further exploit the hierarchical features from the baseline. Benefiting from the RP, our RPCN achieves state-of-the-art performance with a much smaller model and much faster running speed for the CAR task.

© 2020 SPIE and IS&T 1017-9909/2020/$28.00 © 2020 SPIE and IS&T
Bolun Zheng, Xiang Tian, Yaowu Chen, Rongxin Jiang, and Xuesong Liu "Build receptive pyramid for efficient color image compression artifact reduction," Journal of Electronic Imaging 29(3), 033009 (1 June 2020).
Received: 15 May 2019; Accepted: 22 May 2020; Published: 1 June 2020

Back to Top