The process of fusing the rich spectral information of a low spatial resolution hyperspectral image (LR-HSI) with the spatial information of a high spatial resolution multispectral image (HR-MSI) to obtain an HSI with the spatial resolution of an MSI image is called hyperspectral image fusion (HIF). To reconstruct hyperspectral images at video frame rate, we propose a lightweight multi-level information network (MINet) for multispectral and hyperspectral image fusion. Specifically, we develop a novel lightweight feature fusion model, namely residual constraint block based on global variance fine-tuning (GVF-RCB), to complete the feature extraction and fusion of hyperspectral images. Further, we define a residual activity factor to judge the learning ability of the residual module, thereby verifying the effectiveness of GVF-RCB. In addition, we use cascade cross-level fusion to embed the different spectral bands of the upsampled LR-HSI in a progressive manner to compensate for lost spectral information at different levels and to maintain spatial high frequency information at all times. Experiments on different datasets show that our MINet outperforms the state-of-the-art methods in terms of objective metrics, in particular by requiring only 30% of the running time and 20% of the number of parameters.

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, which ignore the implicit diversities existed in style features and thus fail for generating better stylised results. In this paper, we propose a Retinex theory guided, channel-grouping based patch swap technique to solve the above challenges. Channel-grouping strategy groups the style feature maps into surface and texture channels, which prevents the winner-takes-all problem. Retinex theory based decomposition controls a more stable channel code rate generation. In addition, we provide complementary fusion and multi-scale generation strategy to prevent unexpected black area and overstylised results respectively. Experimental results demonstrate that the proposed method outperforms the existing techniques in providing more style-consistent textures while keeping the content fidelity.

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. Source code is available at https://github.com/dota-109/WRSD.