Transformers have excelled in image restoration due to their advanced representational abilities. However, their reliance on a fixed local window for attention often undermines translation invariance and local relationship preservation. This limitation can reduce network stability, especially when dealing with positional changes in degradation scenarios. In this research, we present a new Bayesian Window Transformer, which innovates by employing a probability distribution for window shifts, overcoming the limitations of fixed window configurations in traditional transformers. This approach allows for more flexible coverage beyond a predetermined region. During the evaluation procedure, we further develop two approximate inference algorithms: Layer Expectation Propagation and Monte Carlo Average. These two algorithms calculate expectations derived from the introduced distribution to effectively approximate the marginalization results of the probabilistic variables. Hence, our Bayesian Window Transformer not only inherits the powerful representation ability but also maintains essential properties like translation invariance and local relationship preservation for image restoration. We also provide a theoretical guarantee, demonstrating that our method is aligned with the classic sliding window technique in terms of receptive field sizes and sliding behavior. Comprehensive experiments validate the exceptional effectiveness of our Bayesian Window Transformer across multiple image restoration tasks, including image deraining, denoising, and deblurring.

Existing ultra-high-definition (UHD) image restoration methods often struggle with consistency due to downsampling. We aim to address these challenges by leveraging the powerful latent space representation and reconstruction capabilities of Variational Autoencoders (VAE). However, applying VAE to UHD image restoration presents challenges: 1) High-performing VAEs have large parameter sizes, leading to significant carbon footprints; 2) The self-reconstruction property of VAE hinders bridging the domain gap between clean and degraded images; 3) Latent encoding in VAE can lose high-frequency information, compromising image detail. To overcome these challenges, we propose a frequency enhanced VAE UHD image restoration framework by integrating frequency priors. First, we design the Fourier-based lightweight frequency learning within the VAE to improve parameter efficiency. Then, we introduce a wavelet-based adapter that extracts multi-scale image information and employs frequency-aware adaptive modulation to bridge the domain gap by integrating degraded image data into the pre-trained VAE. Additionally, the adapter injects high-frequency information into the VAE decoder, enhancing detail in the restored images. In this way, our method effectively combines the powerful latent space representation with frequency priors to enhance UHD image restoration. Extensive experiments on various UHD image restoration tasks show that our method surpasses state-of-the-art methods both qualitatively and quantitatively.

The rise in sophisticated image forgery techniques, driven by advancements in image editing and generation, has posed new security challenges. Traditional methods, designed for specific tampering artifacts, struggle with out-of-distribution image forgery detection. In this paper, we propose a shift in paradigm, placing greater emphasis on the universal characteristics of authentic images, as opposed to solely focusing on specific forgery signals. We introduce an enhancement to the Masked Autoencoder (MAE), aptly termed the Forgery MAE (FMAE). This modification retains the inherent characteristics of natural images while integrating multi-source forgery information. Our implementation involves applying the lottery ticket hypothesis during pre-training to identify forgery-sensitive parameters, followed by their sparse fine-tuning to target the forgery detection and localization task. Concurrently, we develop a ``mixture of experts'' noise extractor to compile multi-source forgery data. Our FMAE effectively extracts forgery features and shows strong resilience against unseen forgeries. Extensive experiments across multiple datasets confirm our method's superior accuracy and generalization capability over existing techniques.

All-in-one models for adverse weather removal aim to process various degraded images using a single set of parameters, making them ideal for real-world scenarios. However, they encounter two main challenges: catastrophic forgetting and limited degradation awareness. The former causes the model to lose knowledge of previously learned scenarios, reducing its overall effectiveness. While the later hampers the model’s ability to accurately identify and respond to specific types of degradation, limiting its performance across diverse adverse weather conditions. To address these issues, we introduce the Incremental Learning Adverse Weather Removal (ILAWR) framework, which uses a novel degradation-aware distillation strategy for continuous weather removal. Specifically, we first design a degradation-aware module that utilizes Fourier priors to capture a broad range of degradation features, effectively mitigating catastrophic forgetting in low-level visual tasks. Then, we implement multilateral distillation, which combines knowledge from multiple teacher models using an importance-guided aggregation approach. This enables the model to balance adaptation to new degradation types with the preservation of background details. Extensive experiments confirm that ILAWR outperforms existing models across multiple benchmarks, proving its effectiveness in continuous adverse weather removal.

Derived from diffusion models, MangaNinja specializes in the task of reference-guided line art colorization. We incorporate two thoughtful designs to ensure precise character detail transcription, including a patch shuffling module to facilitate correspondence learning between the reference color image and the target line art, and a point-driven control scheme to enable fine-grained color matching. Experiments on a self-collected benchmark demonstrate the superiority of our model over current solutions in terms of precise colorization. We further showcase the potential of the proposed interactive point control in handling challenging cases (e.g., extreme poses and shadows), cross-character colorization, multi-reference harmonization, etc., beyond the reach of existing algorithms. Our code and model could be found here.

Long video generation involves generating extended videos using models trained on short videos, suffering from distribution shifts due to varying frame counts. It necessitates the use of local information from the original short frames to enhance visual and motion quality, and global information from the entire long frames to ensure appearance consistency. Existing training-free methods struggle to effectively integrate the benefits of both, as appearance and motion in videos are closely coupled, leading to motion inconsistency and visual quality. In this paper, we reveal that global and local information can be precisely decoupled into consistent appearance and motion intensity information by applying Principal Component Analysis (PCA), allowing for refined complementary integration of global consistency and local quality. With this insight, we propose FreePCA, a training-free long video generation paradigm based on PCA that simultaneously achieves high consistency and quality. Concretely, we decouple consistent appearance and motion intensity features by measuring cosine similarity in the principal component space. Critically, we progressively integrate these features to preserve original quality and ensure smooth transitions, while further enhancing consistency by reusing the mean statistics of the initial noise. Experiments demonstrate that FreePCA can be applied to various video diffusion models without requiring training, leading to substantial improvements. Code is available at https://github.com/JosephTiTan/FreePCA.

Advancements in large Vision-Language Models have brought precise, accurate image captioning, vital for advancing multi-modal image understanding and processing. Yet these captions often carry lengthy, intertwined contexts that are difficult to parse and frequently overlook essential cues, posing a great barrier for models like GroundingDINO and SDXL, which lack the strong text encoding and syntax analysis needed to fully leverage dense captions. To address this, we propose BACON, a prompting method that breaks down VLM-generated captions into disentangled, structured elements such as objects, relationships, styles, and themes. This approach not only minimizes confusion from handling complex contexts but also allows for efficient transfer into a JSON dictionary, enabling models without linguistic processing capabilities to easily access key information. We annotated 100,000 image-caption pairs using BACON with GPT-4V and trained an LLaVA captioner on this dataset, enabling it to produce BACON-style captions without relying on costly GPT-4V. Evaluations of overall quality, precision, and recall—as well as user studies—demonstrate that the resulting caption model consistently outperforms other SOTA VLM models in generating high-quality captions. Besides, we show that BACON-style captions exhibit better clarity when applied to various models, enabling them to accomplish previously unattainable tasks or surpass existing SOTA solutions without training. For example, BACON-style captions help GroundingDINO achieve 1.51× higher recall scores on open-vocabulary object detection tasks compared to leading methods.

We present The Matrix, a foundational realistic world simulator capable of generating infinitely long 720p high-fidelity real-scene video streams with real-time, responsive control in both first- and third-person perspectives. Trained on limited supervised data from video games like Forza Horizon 5 and Cyberpunk 2077, complemented by large-scale unsupervised footage from real-world settings like Tokyo streets, The Matrix allows users to traverse diverse terrains—deserts, grasslands, water bodies, and urban landscapes—in continuous, uncut hour-long sequences. With speeds of up to 16 FPS, the system supports real-time interactivity and demonstrates zero-shot generalization, translating virtual game environments to real-world contexts where collecting continuous movement data is often infeasible. For example, The Matrix can simulate a BMW X3 driving through an office setting—an environment present in neither gaming data nor real-world sources. This approach showcases the potential of game data to advance robust world models, bridging the gap between simulations and real-world applications in scenarios with limited data.

Ultra-High Definition (UHD) image restoration struggles to balance computational efficiency and detail retention. While Variational Autoencoders (VAEs) offer improved efficiency by operating in the latent space, with the Gaussian variational constraint, this compression preserves semantics but sacrifices critical high-frequency attributes specific to degradation and thus compromises reconstruction fidelity. % This compromises reconstruction fidelity, even when global semantics are preserved. Consequently, a VAE redesign is imperative to foster a robust semantic representation conducive to generalization and perceptual quality, while simultaneously enabling effective high-frequency information processing crucial for reconstruction fidelity. To address this, we propose \textit{Latent Harmony}, a two-stage framework that reinvigorates VAEs for UHD restoration by concurrently regularizing the latent space and enforcing high-frequency-aware reconstruction constraints. Specifically, Stage One introduces the LH-VAE, which fortifies its latent representation through visual semantic constraints and progressive degradation perturbation for enhanced semantics robustness; meanwhile, it incorporates latent equivariance to bolster its high-frequency reconstruction capabilities. Then, Stage Two facilitates joint training of this refined VAE with a dedicated restoration model. This stage integrates High-Frequency Low-Rank Adaptation (HF-LoRA), featuring two distinct modules: an encoder LoRA, guided by a fidelity-oriented high-frequency alignment loss, tailored for the precise extraction of authentic details from degradation-sensitive high-frequency components; and a decoder LoRA, driven by a perception-oriented loss, designed to synthesize perceptually superior textures. These LoRA modules are meticulously trained via alternating optimization with selective gradient propagation to preserve the integrity of the pre-trained latent structure. This methodology culminates in a flexible fidelity-perception trade-off at inference, managed by an adjustable parameter $\alpha$. Extensive experiments demonstrate that \textit{Latent Harmony} effectively balances perceptual and reconstructive objectives with efficiency, achieving superior restoration performance across diverse UHD and standard-resolution scenarios.

The spatial non-uniformity and diverse patterns of shadow degradation conflict with the weight sharing manner of dominant models, which may lead to an unsatisfactory compromise. To tackle with this issue, we present a novel strategy from the view of shadow transformation in this paper: directly homogenizing the spatial distribution of shadow degradation. Our key design is the random shuffle operation and its corresponding inverse operation. Specifically, random shuffle operation stochastically rearranges the pixels across spatial space and the inverse operation recovers the original order. After randomly shuffling, the shadow diffuses in the whole image and the degradation appears in a homogenized way, which can be effectively processed by the local self-attention layer. Moreover, we further devise a new feed forward network with position modeling to exploit image structural information. Based on these elements, we construct the final local window based transformer named HomoFormer for image shadow removal. Our HomoFormer can enjoy the linear complexity of local transformers while bypassing challenges of non-uniformity and diversity of shadow. Extensive experiments are conducted to verify the superiority of our HomoFormer across public datasets. Code is available at https://github.com/jiexiaou/HomoFormer.

Image restoration poses a garners substantial interest due to the exponential surge in demands for recovering high-quality images from diverse mobile camera devices, adverse lighting conditions, suboptimal shooting environments, and frequent image compression for efficient transmission purposes. Yet this problem gathers significant challenges as people are blind to the type of restoration the images suffer, which, is usually the case in real-day scenarios and is most urgent to solve for this field. Current research, however, heavily relies on prior knowledge of the restoration type, either explicitly through rules or implicitly through the availability of degraded-clean image pairs to define the restoration process, and consumes considerable effort to collect image pairs of vast degradation types. This paper introduces DreamClean, a training-free method that needs no degradation prior knowledge but yields high-fidelity and generality towards various types of image degradation. DreamClean embeds the degraded image back to the latent of pre-trained diffusion models and re-sample it through a carefully designed diffusion process that mimics those generating clean images. Thanks to the rich image prior in diffusion models and our novel Variance Preservation Sampling (VPS) technique, DreamClean manages to handle various different degradation types at one time and reaches far more satisfied final quality than previous competitors. DreamClean relies on elegant theoretical supports to assure its convergence to clean image when VPS has appropriate parameters, and also enjoys superior experimental performance over various challenging tasks that could be overwhelming for previous methods when degradation prior is unavailable.

Consistency Models (CMs) have showed a promise in creating high-quality images with few steps. However, the way to add new conditional controls to the pre-trained CMs has not been explored. In this paper, we explore the pivotal subject of leveraging the generative capacity and efficiency of consistency models to facilitate controllable visual content creation via ControlNet. First, it is observed that ControlNet trained for diffusion models (DMs) can be directly applied to CMs for high-level semantic controls but sacrifice image low-level details and realism. To tackle with this issue, we develop a CMs-tailored training strategy for ControlNet using the consistency training. It is substantiated that ControlNet can be successfully established through the consistency training technique. Besides, a unified adapter can be trained utilizing the consistency training, which enhances the adaptation of DM’s ControlNet. We quantitatively and qualitatively evaluate all strategies across various conditional controls, including sketch, hed, canny, depth, human pose, low-resolution image and masked image, with the pre-trained text-to-image latent consistency models.

Exposure correction task aims to correct the underexposure and its adverse overexposure images to the normal exposure in a single network. As well recognized, the optimization flow is the opposite. Despite great advancement, existing exposure correction methods are usually trained with a mini-batch of both underexposure and overexposure mixed samples and have not explored the relationship between them to solve the optimization inconsistency. In this paper, we introduce a new perspective to conjunct their optimization processes by correlating and constraining the relationship of correction procedure in a mini-batch. The core designs of our framework consist of two steps: 1) formulating the exposure relationship of samples across the batch dimension via a context-irrelevant pretext task. 2) delivering the above sample relationship design as the regularization term within the loss function to promote optimization consistency. The proposed sample relationship design as a general term can be easily integrated into existing exposure correction methods without any computational burden in inference time. Extensive experiments over multiple representative exposure correction benchmarks demonstrate consistent performance gains by introducing our sample relationship design.

Non-local interactions play a vital role in boosting performance for image restoration. However, local window Transformer has been preferred due to its efficiency for processing high-resolution images. The superiority in efficiency comes at the cost of sacrificing the ability to model non-local interactions. In this paper, we present that local window Transformer can also function as modeling non-local interactions. The counterintuitive function is based on the permutation-equivariance of self-attention. The basic principle is quite simple: by *randomly shuffling* the input, local self-attention also has the potential to model non-local interactions without introducing extra parameters. Our random shuffle strategy enjoys elegant theoretical guarantees in extending the local scope. The resulting Transformer dubbed *ShuffleFormer* is capable of processing high-resolution images efficiently while modeling non-local interactions. Extensive experiments demonstrate the effectiveness of ShuffleFormer across a variety of image restoration tasks, including image denoising, deraining, and deblurring. Code is available at https://github.com/jiexiaou/ShuffleFormer.

Image deraining is a challenging task since rain streaks have the characteristics of a spatially long structure and have a complex diversity. Existing deep learning-based methods mainly construct the deraining networks by stacking vanilla convolutional layers with local relations, and can only handle a single dataset due to catastrophic forgetting, resulting in a limited performance and insufficient adaptability. To address these issues, we propose a new image deraining framework to effectively explore nonlocal similarity, and to continuously learn on multiple datasets. Specifically, we first design a patchwise hypergraph convolutional module, which aims to better extract the nonlocal properties with higher-order constraints on the data, to construct a new backbone and to improve the deraining performance. Then, to achieve better generalizability and adaptability in real-world scenarios, we propose a biological brain-inspired continual learning algorithm. By imitating the plasticity mechanism of brain synapses during the learning and memory process, our continual learning process allows the network to achieve a subtle stability-plasticity tradeoff. This it can effectively alleviate catastrophic forgetting and enables a single network to handle multiple datasets. Compared with the competitors, our new deraining network with unified parameters attains a state-of-the-art performance on seen synthetic datasets and has a significantly improved generalizability on unseen real rainy images.

Existing deep learning based de-raining approaches have resorted to the convolutional architectures. However, the intrinsic limitations of convolution, including local receptive fields and independence of input content, hinder the model's ability to capture long-range and complicated rainy artifacts. To overcome these limitations, we propose an effective and efficient transformer-based architecture for the image de-raining. First, we introduce general priors of vision tasks, i.e., locality and hierarchy, into the network architecture so that our model can achieve excellent de-raining performance without costly pre-training. Second, since the geometric appearance of rainy artifacts is complicated and of significant variance in space, it is essential for de-raining models to extract both local and non-local features. Therefore, we design the complementary window-based transformer and spatial transformer to enhance locality while capturing long-range dependencies. Besides, to compensate for the positional blindness of self-attention, we establish a separate representative space for modeling positional relationship, and design a new relative position enhanced multi-head self-attention. In this way, our model enjoys powerful abilities to capture dependencies from both content and position, so as to achieve better image content recovery while removing rainy artifacts. Experiments substantiate that our approach attains more appealing results than state-of-the-art methods quantitatively and qualitatively.

Human can extrapolate well, generalize daily knowledge into unseen scenarios, raise and answer counterfactual questions. To imitate this ability via generative models, previous works have extensively studied explicitly encoding Structural Causal Models (SCMs) into architectures of generator networks. This methodology, however, limits the flexibility of the generator as they must be carefully crafted to follow the causal graph, and demands a ground truth SCM with strong ignorability assumption as prior, which is a nontrivial assumption in many real scenarios. Thus, many current causal GAN methods fail to generate high fidelity counterfactual results as they cannot easily leverage state-of-the-art generative models. In this paper, we propose to study counterfactual synthesis from a new perspective of knowledge extrapolation, where a given knowledge dimension of the data distribution is extrapolated, but the remaining knowledge is kept indistinguishable from the original distribution. We show that an adversarial game with a closed-form discriminator can be used to address the knowledge extrapolation problem, and a novel principal knowledge descent method can efficiently estimate the extrapolated distribution through the adversarial game. Our method enjoys both elegant theoretical guarantees and superior performance in many scenarios.

Thanks to the powerful representation capabilities, transformers have made impressive progress in image restoration. However, existing transformers-based methods do not carefully consider the particularities of image restoration. In general, image restoration requires that an ideal approach should be translation-invariant to the degradation, i.e., the undesirable degradation should be removed irrespective of its position within the image. Furthermore, the local relationships also play a vital role, which should be faithfully exploited for recovering clean images. Nevertheless, most transformers either adopt local attention with the fixed local window strategy or global attention, which unfortunately breaks the translation invariance and causes huge loss of local relationships. To address these issues, we propose an elegant stochastic window strategy for transformers. Specifically, we first introduce the window partition with stochastic shift to replace the original fixed window partition for training. Then, we design a new layer expectation propagation algorithm to efficiently approximate the expectation of the induced stochastic transformer for testing. Our stochastic window transformer not only enjoys powerful representation but also maintains the desired property of translation invariance and locality. Experiments validate the stochastic window strategy consistently improves performance on various image restoration tasks (deraining, denoising and deblurring) by significant margins. The code is available at https://github.com/jiexiaou/Stoformer.

While deep convolutional neural networks (CNNs) have achieved great success on image de-raining task, most existing methods can only learn fixed mapping rules between paired rainy/clean images on a single dataset. This limits their applications in practical situations with multiple and incremental datasets where the mapping rules may change for different types of rain streaks. However, the catastrophic forgetting of traditional deep CNN model challenges the design of generalized framework for multiple and incremental datasets. A strategy of sharing the network structure but in-dependently updating and storing the network parameters on each dataset has been developed as a potential solution. Nevertheless, this strategy is not applicable to compact systems as it dramatically increases the overall training time and parameter space. To alleviate such limitation, in this study, we propose a parameter importance guided weights modification approach, named PIGWM. Specifically, with new dataset (e.g. new rain dataset), the well-trained network weights are updated according to their importance evaluated on previous training dataset. With extensive experimental validation, we demonstrate that a single network with a single parameter set of our proposed method can process multiple rain datasets almost without performance degradation. The proposed model is capable of achieving superior performance on both inhomogeneous and incremental datasets, and is promising for highly compact systems to gradually learn myriad regularities of the different types of rain streaks. The results indicate that our proposed method has great potential for other computer vision tasks with dynamic learning environments.

Most existing image de-raining networks could only learn fixed mapping rules between paired rainy/clean images on single synthetic dataset and then stay static for lifetime. However, since single synthetic dataset merely provides a partial view for the distribution of rain streaks, deep models well trained on an individual synthetic dataset tend to overfit on this biased distribution. This leads to the inability of these methods to well generalize to complex and changeable real-world rainy scenes, thus limiting their practical applications. In this paper, we try for the first time to accumulate the de-raining knowledge from multiple synthetic datasets on a single network parameter set to improve the de-raining generalization of deep networks. To achieve this goal, we explore Neural Reorganization (NR) to allow the de-raining network to keep a subtle stability-plasticity trade-off rather than naive stabilization after training phase. Specifically, we design our NR algorithm by borrowing the synaptic consolidation mechanism in the biological brain and knowledge distillation. Equipped with our NR algorithm, the deep model can be trained on a list of synthetic rainy datasets by overcoming catastrophic forgetting, making it a general-version de-raining network. Extensive experimental validation shows that due to the successful accumulation of de-raining knowledge, our proposed method can not only process multiple synthetic datasets consistently, but also achieve state-of-the-art results when dealing with real-world rainy images.