HPRN: Holistic Prior-embedded Relation Network for Spectral Super-Resolution

Spectral super-resolution (SSR) refers to the hyperspectral image (HSI) recovery from an RGB counterpart. Due to the one-to-many nature of the SSR problem, a single RGB image can be reprojected to many HSIs. The key to tackle this illposed problem is to plug into multi-source prior information such as the natural RGB spatial context-prior, deep feature-prior or inherent HSI statistical-prior, etc., so as to improve the confidence and fidelity of reconstructed spectra. However, most current approaches only consider the general and limited priors in their designing the customized convolutional neural networks (CNNs), which leads to the inability to effectively alleviate the degree of ill-posedness. To address the problematic issues, we propose a novel holistic prior-embedded relation network (HPRN) for SSR. Basically, the core framework is delicately assembled by several multi-residual relation blocks (MRBs) that fully facilitate the transmission and utilization of the low-frequency content prior of RGB signals. Innovatively, the semantic prior of RGB input is introduced to identify category attributes and a semantic-driven spatial relation module (SSRM) is put forward to perform the feature aggregation among the clustered similar characteristics using a semantic-embedded relation matrix. Additionally, we develop a transformer-based channel relation module (TCRM), which breaks the habit of employing scalars as the descriptors of channel-wise relations in the previous deep feature-prior and replaces them with certain vectors, together with Transformerstyle feature interactions, supporting the representations to be more discriminative. In order to maintain the mathematical correlation and spectral consistency between hyperspectral bands, the second-order prior constraints (SOPC) are incorporated into the loss function to guide the HSI reconstruction process.

AdaptiveWeighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Images

Recent promising effort for spectral reconstruction (SR) focuses on learning a complicated mapping through using a deeper and wider convolutional neural networks (CNNs). Nevertheless, most CNN-based SR algorithms neglect to explore the camera spectral sensitivity (CSS) prior and interdependencies among intermediate features, thus limiting the representation ability of the network and performance of SR. To conquer these issues, we propose a novel adaptive weighted attention network (AWAN) for SR, whose backbone is stacked with multiple dual residual attention blocks (DRAB) decorating with long and short skip connections to form the dual residual learning. Concretely, we investigate an adaptive weighted channel attention (AWCA) module to reallocate channel-wise feature responses via integrating correlations between channels. Furthermore, a patch-level second-order non-local (PSNL) module is developed to capture long-range spatial contextual information by second-order non-local operations for more powerful feature representations. Based on the fact that the recovered RGB images can be projected by the reconstructed hyperspectral image (HSI) and the given CSS function, we incorporate the discrepancies of the RGB images and HSIs as a finer constraint for more accurate reconstruction. Experimental results demonstrate the effectiveness of our proposed AWAN network in terms of quantitative comparison and perceptual quality over other state-of-the-art SR methods. In the NTIRE 2020 Spectral Reconstruction Challenge, our entries obtain the 1st ranking on the Clean track and the 3rd place on the Real World track. Codes are available at https://github.com/Deep-imagelab/AWAN.