Retinex-guided Channel-grouping based Patch Swap for Arbitrary Style Transfer (under review)

Published in , 2022

The basic principle of the patch-matching based style transfer is to substitute the patches of the content image feature maps by the closest patches from the style image feature maps. Since the finite features harvested from one single aesthetic style image are inadequate to represent the rich textures of the content natural image, existing techniques treat the full-channel style feature patches as simple signal tensors and create new style feature patches via signal-level fusion. In this paper, we propose a Retinex theory guided, channel-grouping based patch swap technique to group the style feature maps into surface and texture channels, and the new features are created by the combination of these two groups, which can be regarded as a semantic-level fusion of the raw style features. In addition, we provide complementary fusion and multi-scale generation strategy to prevent unexpected black area and over-stylised results respectively. Experimental results demonstrate that the proposed method outperforms the existing techniques in providing more style-consistent textures while keeping the content fidelity.

NL-CALIC Soft Decoding Using Strict Constrained Wide-Activated Recurrent Residual Network

Published in IEEE Transactions on Image Processing, 2021

In this work, we propose a normalized Tanh activate strategy and a lightweight wide-activate recurrent structure to solve three key challenges of the soft-decoding of near-lossless codes: 1. How to add an effective strict constrained peak absolute error (PAE) boundary to the network; 2. An end-to-end solution that is suitable for different quantization steps (compression ratios). 3. Simple structure that favors the GPU and FPGA implementation. To this end, we propose a Wide-activated Recurrent structure with a normalized Tanh activate strategy for Soft-Decoding (WRSD). Experiments demonstrate the effectiveness of the proposed WRSD technique that WRSD outperforms better than the state-of-the-art soft decoders with less than 5% number of parameters, and every computation node of WRSD requires less than 64KB storage for the parameters which can be easily cached by most of the current consumer-level GPUs.

Recommended citation: Niu Y, Liu C, Ma M, et al. NL-CALIC Soft Decoding Using Strict Constrained Wide-Activated Recurrent Residual Network[J]. IEEE Transactions on Image Processing, 2021, 31: 1243-1257.