Unpaired training has been verified as one of the most effective paradigms for real scene dehazing by learning from unpaired real-world hazy and clear images. Although numerous studies have been proposed, current methods demonstrate limited generalization for various real scenes due to limited feature representation and insufficient use of real-world prior. Inspired by the strong generative capabilities of diffusion models in producing both hazy and clear images, we exploit diffusion prior for real-world image dehazing, and propose an unpaired framework named Diff-Dehazer. Specifically, we leverage diffusion prior as bijective mapping learners within the CycleGAN, a classic unpaired learning framework. Considering that physical priors contain pivotal statistics information of real-world data, we further excavate real-world knowledge by integrating physical priors into our framework. Furthermore, we introduce a new perspective for adequately leveraging the representation ability of diffusion models by removing degradation in image and text modalities, so as to improve the dehazing effect. Extensive experiments on multiple real-world datasets demonstrate the superior performance of our method.

Neural networks have achieved significant advances in the field of image restoration and much research has focused on designing new architectures for convolutional neural networks (CNNs) and Transformers. The choice of loss functions, despite being a critical factor when training image restoration networks, has attracted little attention. The existing losses are primarily based on semantic or hand-crafted representations. Recently, discrete representations have demonstrated strong capabilities in representing images. In this work, we explore the loss of discrete representations for image restoration. Specifically, we propose a Local Residual Quantized Variational AutoEncoder (Local RQ-VAE) to learn prototype vectors that represent the local details of high-quality images. Then we propose a Prototypical Distribution Divergence (PDD) loss that measures the Kullback-Leibler divergence between the prototypical distributions of the restored and target images. Experimental results demonstrate that our PDD loss improves the restored images in both PSNR and visual quality for state-of-the-art CNNs and Transformers on several image restoration tasks, including image super-resolution, image denoising, image motion deblurring, and defocus deblurring.

Transformers have been widely used for video processing owing to the multi-head self attention (MHSA) mechanism. However, the MHSA mechanism encounters an intrinsic difficulty for video inpainting, since the features associated with the corrupted regions are degraded and incur inaccurate self attention. This problem, termed query degradation, may be mitigated by first completing optical flows and then using the flows to guide the self attention, which was verified in our previous work - flow-guided transformer (FGT). We further exploit the flow guidance and propose FGT++ to pursue more effective and efficient video inpainting. First, we design a lightweight flow completion network by using local aggregation and edge loss. Second, to address the query degradation, we propose a flow guidance feature integration module, which uses the motion discrepancy to enhance the features, together with a flow-guided feature propagation module that warps the features according to the flows. Third, we decouple the transformer along the temporal and spatial dimensions, where flows are used to select the tokens through a temporally deformable MHSA mechanism, and global tokens are combined with the inner-window local tokens through a dual-perspective MHSA mechanism. FGT++ is experimentally evaluated to be outperforming the existing video inpainting networks qualitatively and quantitatively.

One tough problem of image inpainting is to restore complex structures in the corrupted regions. It motivates interactive image inpainting which leverages additional hints, e.g., sketches, to assist the inpainting process. A sketch is simple and intuitive for end users to provide, but meanwhile has free forms with much randomness. Such randomness may confuse the inpainting models, and incur severe artifacts in completed images. To better facilitate image inpainting with sketch guidance, we propose a two-stage image inpainting system, termed SketchRefiner. The first stage of our approach serves as a data provider that simulates real sketches and derives the capability of sketch calibration from the simulated data. In the second stage, our approach aligns the sketch guidance with the inpainting process so as to elevate image inpainting with sketches. We also propose a real-world test protocol to address the evaluation of inpainting methods upon practical applications with user sketches. Experimental results on three prevailing benchmark datasets, i.e., CelebA-HQ, Places2, and ImageNet, and the proposed test protocol demonstrate the state-of-the-art performance of our approach, and its great potentials upon real-world applications. Further analyses illustrate that our approach effectively utilizes sketch information as guidance and eliminates the artifacts due to the free-form sketches.

Deep convolutional neural networks (CNNs) have become dominant in the task of single image rain removal. Most of current CNN methods, however, suffer from the problem of overfitting on one single synthetic dataset as they neglect the intrinsic prior of the physical properties of rain streaks. To address this issue, we propose a simple but effective prior - Fourier prior to improve the generalization ability of an image rain removal model. The Fourier prior is a kind of property of rainy images. It is based on a key observation of us - replacing the Fourier amplitude of rainy images with that of clean images greatly suppresses the synthetic and real-world rain streaks. This means the amplitude contains most of the rain streak information and the phase keeps the similar structures of the background. So it is natural for single image rain removal to process the amplitude and phase information of the rainy images separately. In this paper, we develop a two-stage model where the first stage restores the amplitude of rainy images to clean rain streaks, and the second stage restores the phase information to refine fine-grained background structures. Extensive experiments on synthetic rainy data demonstrate the power of Fourier prior. Moreover, when trained on synthetic data, a robust generalization ability to real-world images can also be obtained. The code will be publicly available at https://github.com/willinglucky/ExploringFourier-Prior-for-Single-Image-Rain-Removal.

Given an incomplete image without additional constraint, image inpainting natively allows for multiple solutions as long as they appear plausible. Recently, multiple-solution inpainting methods have been proposed and shown the potential of generating diverse results. However, these methods have difficulty in ensuring the quality of each solution, e.g. they produce distorted structure and/or blurry texture. We propose a two-stage model for diverse inpainting, where the first stage generates multiple coarse results each of which has a different structure, and the second stage refines each coarse result separately by augmenting texture. The proposed model is inspired by the hierarchical vector quantized variational auto-encoder (VQ-VAE), whose hierarchical architecture disentangles structural and textural information. In addition, the vector quantization in VQVAE enables autoregressive modeling of the discrete distribution over the structural information. Sampling from the distribution can easily generate diverse and high-quality structures, making up the first stage of our model. In the second stage, we propose a structural attention module inside the texture generation network, where the module utilizes the structural information to capture distant correlations. We further reuse the VQ-VAE to calculate two feature losses, which help improve structure coherence and texture realism, respectively. Experimental results on CelebA-HQ, Places2, and ImageNet datasets show that our method not only enhances the diversity of the inpainting solutions but also improves the visual quality of the generated multiple images. Code and models are available at: https://github.com/USTC-JialunPeng/Diverse-Structure-Inpainting.

Generative adversarial networks (GANs) have been extensively used for training networks that perform image generation. After training, the discriminator in GAN was not used anymore. We propose to recycle the trained discriminator for another use: no-reference image quality assessment (NR-IQA). We are motivated by twofold facts. First, in Wasserstein GAN (WGAN), the discriminator is designed to calculate the distance between the distribution of generated images and that of real images; thus, the trained discriminator may encode the distribution of real-world images. Second, NR-IQA often needs to leverage the distribution of real-world images for assessing image quality. We then conjecture that using the trained discriminator for NR-IQA may help get rid of any human-labeled quality opinion scores and lead to a new opinion-unaware (OU) method. To validate our conjecture, we start from a restricted NR-IQA problem, that is IQA for artificially super-resolved images. We train super-resolution (SR) WGAN with two kinds of discriminators: one is to directly evaluate the entire image, and the other is to work on small patches. For the latter kind, we obtain patch-wise quality scores, and then have the flexibility to fuse the scores, e.g., by weighted average. Moreover, we directly extend the trained discriminators for authentically distorted images that have different kinds of distortions. Our experimental results demonstrate that the proposed method is comparable to the state-of-the-art OU NR-IQA methods on SR images and is even better than them on authentically distorted images. Our method provides a better interpretable approach to NR-IQA. Our code and models are available at https://github.com/YunanZhu/RecycleD.