Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. To address these issues, we propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL. Specifically, we present a wavelet-based conditional diffusion model (WCDM) that leverages the generative power of diffusion models to produce results with satisfactory perceptual fidelity. Additionally, it also takes advantage of the strengths of wavelet transformation to greatly accelerate inference and reduce computational resource usage without sacrificing information. To avoid chaotic content and diversity, we perform both forward diffusion and denoising in the training phase of WCDM, enabling the model to achieve stable denoising and reduce randomness during inference. Moreover, we further design a high-frequency restoration module (HFRM) that utilizes the vertical and horizontal details of the image to complement the diagonal information for better fine-grained restoration. Extensive experiments on publicly available real-world benchmarks demonstrate that our method outperforms the existing state-of-the-art methods both quantitatively and visually, and it achieves remarkable improvements in efficiency compared to previous diffusion-based methods. In addition, we empirically show that the application for low-light face detection also reveals the latent practical values of our method. Code is available at https://github.com/JianghaiSCU/Diffusion-Low-Light.

In this work, we simulate the early visual information processing mechanisms in biological visual system (BVS) to solve the visible-infrared image fusion (VIIF) task. Concretely, both infrared and visible images are first processed with a dynamic receptive field (DRF), which is imitated by a Difference of Gaussian (DoG) function whose parameters are adjusted according to local image statistics (e.g., local edge responses). The DRF processing produces two components for each source image (e.g., the visible image or the infrared image) that respectively represent the results of On-center based DRF and Off-center based DRF. Then, the results of On-center based DRF for visible image are fused with the results of Off-center based DRF for infrared image and the results of On-center based DRF for infrared image are fused with the results of Off-center based DRF for visible image, according to the mechanisms of cortex-based center-surround fusion. Algorithmically, this step fuses the visible and infrared images processed by DRF with On-center and Off-center according to the different levels of local homogeneity. Moreover, a feedward signal acting as the sub-cortical flow is also introduced to adjust the results during the fusion. The final output image is simply obtained by the summation of two components after the cortex and sub-cortex based fusion. Qualitative and quantitative tests on four datasets demonstrate that our approach can fuse the infrared and visible images effectively with the good background details and discernible salient areas. We emphasize the importance of corticothalamic feedback, cortex and sub-cortex-based fusion, and the interactions between On-center pathway and Off-center pathway that are ubiquitous in BVS for producing the high-quality visual signals.

This letter aims to combine spatial and frequency information for single image deblurring. Although some methods have tried to use frequency information to perform deblurring, they only simply process the different frequencies information separately or concatenate the real part and imaginary part of frequency features but ignore the strong correlation between them. To address this problem, we propose a simple but effective frequency interaction pipeline to realize the mutual conversion of the real part and the imaginary part. Then, we construct a spatial-frequency conversion module (SFCM) to promote the mutual conversion between the frequency information and the spatial information. Based on the proposed components, we build a multi-scale deblurring network, dubbed SFDNet, which can fully exploit coarse and middle-level information in spatial and frequency domains for finer scale image deblurring. Extensive experiments on the GoPro and HIDE datasets demonstrate that the proposed network outperforms the state-of-the-art methods both quantitatively and visually.

The high-precision navigation and positioning ability of UAV (Unmanned Aerial Vehicles) is the key factor to reflect its degree of automation. Visual navigation based on image matching has become one of the important research fields for UAV to realize autonomous navigation, because of its low cost, strong anti-jamming ability, and good location result. However, the visual quality of images captured by UAV will be seriously affected by some factors, such as weak illumination conditions or insufficient performance of its sensors. Resolving a series of degradation of low-light images can improve the visual quality and enhance the performance of UAV visual navigation. In this paper, we propose a novel fully convolutional network based on the Retinex theory to solve the degradations of low-light images captured by UAV, which can improve the visual quality of the images and visual matching performance effectively. At the same time, a visual navigation system is designed based on the proposed network. Extensive experiments demonstrate that our method outperforms the existing methods by a large margin both quantitatively and qualitatively, and effectively improves the performance of the image matching algorithms. The visual navigation system can successfully realize the self-localization of UAV under different illumination conditions. Moreover, we also prove that our method is also effective in other practical tasks (e.g. autonomous driving).