Image restoration (IR) models are typically trained to recover high-quality images using L1 or LPIPS loss. To handle diverse unknown degradations, zero-shot IR methods have also been introduced. However, existing pre-trained and zero-shot IR approaches often fail to align with human preferences, resulting in restored images that may not be favored. This highlights the critical need to enhance restoration quality and adapt flexibly to various image restoration tasks or backbones without requiring model retraining and ideally without labor-intensive preference data collection. In this paper, we propose the first Test-Time Preference Optimization (TTPO) paradigm for image restoration, which enhances perceptual quality, generates preference data on-the-fly, and is compatible with any IR model backbone. Specifically, we design a training-free, three-stage pipeline: (i) generate candidate preference images online using diffusion inversion and denoising based on the initially restored image; (ii) select preferred and dispreferred images using automated preference-aligned metrics or human feedback; and (iii) use the selected preference images as reward signals to guide the diffusion denoising process, optimizing the restored image to better align with human preferences. Extensive experiments across various image restoration tasks and models demonstrate the effectiveness and flexibility of the proposed pipeline.

Introducing high-quality references can largely alleviate the uncertainty in blind face image restoration tasks, yet the equivocal utilization of reference priors makes it still a struggle to well preserve the human identity. We attribute the identity inconsistency to two deficiencies of existing reference-based face restoration methods, namely the inability to effectively determine which features need to be transferred, and the failure to preserve the structure and details of the selected features. This work mainly focuses on these two issues, and we present a novel blind face image restoration method that considers reference selection, transfer, and reconstruction (RefSTAR) to introduce proper features from reference images. Specifically, we construct a reference selection (RefSel) module, which can generate accurate masks to select reference features. For training the RefSel module, we construct a RefSel-HQ dataset through a mask generation pipeline, which contains annotated masks for 10,000 ground truth-reference pairs. To guarantee the exact introduction of selected reference features, a feature fusion paradigm is designed for reference feature transferring, and a Mask-Compatible Cycle-Consistency Loss is redesigned based on reference reconstruction to further ensure the presence of selected reference image features in the output image. Experiments on various backbone models demonstrate superior performance, showing better identity preservation ability and reference feature transfer quality.

Video outpainting is a challenging task that generates new video content by extending beyond the boundaries of an original input video, requiring both temporal and spatial consistency. Many existing methods utilize latent diffusion models with U-Net backbones but still struggle to achieve high quality and adaptability in generated content. Diffusion transformers (DiTs) have emerged as a promising alternative because of their superior performance. We introduce OutDreamer, a DiT-based video outpainting framework comprising two main components: a video control branch and a conditional outpainting branch. The video control branch effectively extracts masked video information, while the conditional outpainting branch generates missing content based on these extracted conditions. Additionally, we propose a mask-driven self-attention layer that dynamically integrates the given mask information, further enhancing the model's adaptability to outpainting tasks. Furthermore, we introduce a latent alignment loss to maintain overall consistency both within and between frames. For long video outpainting, we employ a cross-video-clip refiner to iteratively generate missing content, ensuring temporal consistency across video clips. Extensive evaluations demonstrate that our OutDreamer outperforms existing video outpainting methods on widely recognized benchmarks.

Single image super-solution (SR) aims to restore a high-resolution (HR) image from a degraded low-resolution (LR) image. However, existing SR models still face a significant domain gap between synthetic and real-world datasets due to the mismatched degradation distributions, hindering SR models from achieving optimal results. In this paper, we propose an unsupervised diffusion-based degradation modeling framework (UDDM) to effectively capture real-world degradation distributions. Specifically, given unpaired LR and HR images, a diffusion-based degradation module (DDM) first models the degradation distribution by diffusing real-world LR images to downsampled LR images, which does not require HR images. It then applies reverse diffusion to generate real-world LR images from extremely downsampled HR images. This approach allows DDM to model and generate real-world degradation distributions without requiring paired data, by using extreme downsampling to link unpaired LR and HR images. Additionally, we introduce a physics-based dynamic degradation module (P-DDM) that adaptively models content-aware degradation, ensuring both content and structural accuracy. Finally, the LR images generated by DDM and P-DDM are adaptively weighted to produce the final LR images, which are paired with the given HR images for training the SR network. Extensive experiments across multiple real-world datasets demonstrate that our framework achieves state-of-the-art performance in both qualitative and quantitative comparison.

Burst super-resolution (BurstSR) aims to reconstruct high-resolution images by fusing subpixel details from multiple low-resolution burst frames. The primary challenge lies in effectively extracting useful information while mitigating the impact of high-frequency noise. Most existing methods rely on frame-by-frame fusion, which often struggles to distinguish informative subpixels from noise, leading to suboptimal performance. To address these limitations, we introduce a novel Query Mamba Burst Super-Resolution (QMambaBSR) network. Specifically, we observe that sub-pixels have consistent spatial distribution while noise appears randomly. Considering the entire burst sequence during fusion allows for more reliable extraction of consistent subpixels and better suppression of noise outliers. Based on this, a Query State Space Model (QSSM) is proposed for both inter-frame querying and intra-frame scanning, enabling a more efficient fusion of useful subpixels. Additionally, to overcome the limitations of static upsampling methods that often result in over-smoothing, we propose an Adaptive Upsampling (AdaUp) module that dynamically adjusts the upsampling kernel to suit the characteristics of different burst scenes, achieving superior detail reconstruction. Extensive experiments on four benchmark datasets—spanning both synthetic and real-world images—demonstrate that QMambaBSR outperforms existing state-of-the-art methods.

Customized text-to-image generation, which synthesizes images based on user-specified concepts, has made significant progress in handling individual concepts. However, when extended to multiple concepts, existing methods often struggle with properly integrating different models and avoiding the unintended blending of characteristics from distinct concepts. In this paper, we propose MC2, a novel approach for multi-concept customization that enhances flexibility and fidelity through inference-time optimization. MC2enables the integration of multiple single-concept models with heterogeneous architectures. By adaptively refining attention weights between visual and textual tokens, our method ensures that image regions accurately correspond to their associated concepts while minimizing interference between concepts. Extensive experiments demonstrate that MC2outperforms training-based methods in terms of prompt-reference alignment. Furthermore, MC2can be seamlessly applied to text-to-image generation, providing robust compositional capabilities. To facilitate the evaluation of multi-concept customization, we also introduce a new benchmark, MC++. The code is available at https://github.com/jiangJiaxiu/MC-2.

Recent state-of-the-art image restoration methods mostly adopt latent diffusion models with U-Net backbones, yet still facing challenges in achieving high-quality restoration due to their limited capabilities. Diffusion transformers (DiTs), like SD3, are emerging as a promising alternative because of their better quality with scalability. In this paper, we introduce DPIR (Dual Prompting Image Restoration), a novel image restoration method that effectivly extracts conditional information of low-quality images from multiple perspectives. Specifically, DPIR consits of two branches: a low-quality image conditioning branch and a dual prompting control branch. The first branch utilizes a lightweight module to incorporate image priors into the DiT with high efficiency. More importantly, we believe that in image restoration, textual description alone cannot fully capture its rich visual characteristics. Therefore, a dual prompting module is designed to provide DiT with additional visual cues, capturing both global context and local appearance. The extracted global-local visual prompts as extra conditional control, alongside textual prompts to form dual prompts, greatly enhance the quality of the restoration. Extensive experimental results demonstrate that DPIR delivers superior image restoration performance.

Recent advance in text-to-image diffusion models have significantly facilitated the generation of high-quality images, but also raising concerns about the illegal creation of harmful content, such as copyrighted images. Existing concept erasure methods achieve superior results in preventing the production of erased concept from prompts, but typically perform poorly in preventing undesired editing. To address this issue, we propose an Anti-Editing Concept Erasure (ACE) method, which not only erases the target concept during generation but also filters out it during editing. Specifically, we propose to inject the erasure guidance into both conditional and the unconditional noise prediction, enabling the model to effectively prevent the creation of erasure concepts during both editing and generation. Furthermore, a stochastic correction guidance is introduced during training to address the erosion of unrelated concepts. We conducted erasure editing experiments with representative editing methods (i.e., LEDITS++ and MasaCtrl) to erase IP characters, and the results indicate that our ACE effectively filters out target concepts in both types of edits. Additional experiments on erasing explicit concepts and artistic styles further demonstrate that our ACE performs favorably against state-of-the-art methods. Our code will be publicly available at https://github.com/120L020904/ACE.

Existing image super-resolution (SR) techniques often fail to generalize effectively in complex real-world settings due to the significant divergence between training data and practical scenarios. To address this challenge, previous efforts have either manually simulated intricate physical-based degradations or utilized learning-based techniques, yet these approaches remain inadequate for producing large-scale, realistic, and diverse data simultaneously. In this paper, we introduce a novel Realistic Decoupled Data Generator (RealDGen), an unsupervised learning data generation framework designed for real-world super-resolution. We meticulously develop content and degradation extraction strategies, which are integrated into a novel content-degradation decoupled diffusion model to create realistic low-resolution images from unpaired real LR and HR images. Extensive experiments demonstrate that RealDGen excels in generating large-scale, high-quality paired data that mirrors real-world degradations, significantly advancing the performance of popular SR models on various real-world benchmarks.

Image restoration aims to recover details and enhance contrast in degraded images. With the growing demand for high-quality imaging (e.g., 4K and 8K), achieving a balance between restoration quality and computational efficiency has become increasingly critical. Existing methods, primarily based on CNNs, Transformers, or their hybrid approaches, apply uniform deep representation extraction across the image. However, these methods often struggle to effectively model long-range dependencies and largely overlook the spatial characteristics of image degradation (regions with richer textures tend to suffer more severe damage), making it hard to achieve the best trade-off between restoration quality and efficiency. To address these issues, we propose a novel texture-aware image restoration method, TAMambaIR, which simultaneously perceives image textures and achieves a trade-off between performance and efficiency. Specifically, we introduce a novel Texture-Aware State Space Model, which enhances texture awareness and improves efficiency by modulating the transition matrix of the state-space equation and focusing on regions with complex textures. Additionally, we design a Multi-Directional Perception Block to improve multi-directional receptive fields while maintaining low computational overhead. Extensive experiments on benchmarks for image super-resolution, deraining, and low-light image enhancement demonstrate that TAMambaIR achieves state-of-the-art performance with significantly improved efficiency, establishing it as a robust and efficient framework for image restoration.

Multi-frame video enhancement tasks aim to improve the spatial and temporal resolution and quality of video sequences by leveraging temporal information from multiple frames, which are widely used in streaming video processing, surveillance, and generation. Although numerous Transformer-based enhancement methods have achieved impressive performance, their computational and memory demands hinder deployment on edge devices. Quantization offers a practical solution by reducing the bit-width of weights and activations to improve efficiency. However, directly applying existing quantization methods to video enhancement tasks often leads to significant performance degradation and loss of fine details. This stems from two limitations: (a) inability to allocate varying representational capacity across frames, which results in suboptimal dynamic range adaptation; (b) over-reliance on full-precision teachers, which limits the learning of low-bit student models. To tackle these challenges, we propose a novel quantization method for video enhancement: Progressive Multi-Frame Quantization for Video Enhancement (PMQ-VE). This framework features a coarse-to-fine two-stage process: Backtracking-based Multi-Frame Quantization (BMFQ) and Progressive Multi-Teacher Distillation (PMTD). BMFQ utilizes a percentile-based initialization and iterative search with pruning and backtracking for robust clipping bounds. PMTD employs a progressive distillation strategy with both full-precision and multiple high-bit (INT) teachers to enhance low-bit models' capacity and quality. Extensive experiments demonstrate that our method outperforms existing approaches, achieving state-of-the-art performance across multiple tasks and benchmarks. The code will be made publicly available.

Recent advances in diffusion models have substantially improved text-driven image editing. However, existing frameworks based on discrete textual tokens struggle to support continuous control over camera parameters and smooth transitions in visual effects. These limitations hinder their applications to realistic, camera-aware, and fine-grained editing tasks. In this paper, we present CamEdit, a diffusion-based framework for photorealistic image editing that enables continuous and semantically meaningful manipulation of common camera parameters such as aperture and shutter speed. CamEdit incorporates a continuous parameter prompting mechanism and a parameter-aware modulation module that guides the model in smoothly adjusting focal plane, aperture, and shutter speed, reflecting the effects of varying camera settings within the diffusion process. To support supervised learning in this setting, we introduce CamEdit50K, a dataset specifically designed for photorealistic image editing with continuous camera parameter settings. It contains over 50k image pairs combining real and synthetic data with dense camera parameter variations across diverse scenes. Extensive experiments demonstrate that CamEdit enables flexible, consistent, and high-fidelity image editing, achieving state-of-the-art performance in camera-aware visual manipulation and fine-grained photographic control.

Real-world image super-resolution (RealSR) aims to enhance the visual quality of in-the-wild images, such as those captured by mobile phones. While existing methods leveraging large generative models demonstrate impressive results, the high computational cost and latency make them impractical for edge deployment. In this paper, we introduce PocketSR, an ultra-lightweight, single-step model that brings generative modeling capabilities to RealSR while maintaining high fidelity. To achieve this, we design LiteED, a highly efficient alternative to the original computationally intensive VAE in SD, reducing parameters by 97.5\% while preserving high-quality encoding and decoding. Additionally, we propose online annealing pruning for the U-Net, which progressively shifts generative priors from heavy modules to lightweight counterparts, ensuring effective knowledge transfer and further optimizing efficiency. To mitigate the loss of prior knowledge during pruning, we incorporate a multi-layer feature distillation loss. Through an in-depth analysis of each design component, we provide valuable insights for future research. PocketSR, with a model size of 146M parameters, processes 4K images in just 0.8 seconds, achieving a remarkable speedup over previous methods. Notably, it delivers performance on par with state-of-the-art single-step and even multi-step RealSR models, making it a highly practical solution for edge-device applications.

Dual-camera smartphones suffer from geometric and photometric inconsistencies during zoom transitions, primarily due to disparities in intrinsic/extrinsic parameters and divergent image processing pipelines between the two cameras. Existing interpolation methods struggle to effectively address this issue, constrained by the lack of ground-truth datasets and motion ambiguity in dynamic scenarios. To overcome these challenges, we propose OmniZoom, a universal plug-and-play paradigm for cross-device smooth zoom interpolation. Specifically, we present a novel cross-device virtual data generation method utilizing 3D Gaussian Splatting. This method tackles data scarcity by decoupling geometric features via spatial transition modeling and correcting photometric variations with dynamic color adaptation. It is further enhanced by cross-domain consistency learning for device-agnostic semantic alignment. Additionally, we introduce a plug-and-play 3D-TPR (3D Trajectory Progress Ratio Mapping) framework that surmounts 2D spatial limitations. As components of our framework, a texture-focus strategy is introduced for high-frequency detail preservation, incorporating mask penalty constraints to suppress interpolation artifacts. Our pipeline exhibits broad compatibility with diverse interpolation methods and achieves good performance across multiple public benchmarks. Real-world evaluations on various smartphone platforms also reveal significant quality improvements after fine-tuning on our synthetic data, which underscores the robustness and practical effectiveness of our approach for cross-device zoom applications.

Existing super-resolution (SR) models primarily focus on restoring local texture details, often neglecting the global semantic information within the scene. This oversight can lead to the omission of crucial semantic details or the intro-duction of inaccurate textures during the recovery process. In our work, we introduce the Cognitive Super-Resolution (CoSeR) framework, empowering SR models with the ca-pacity to comprehend low-resolution images. We achieve this by marrying image appearance and language under-standing to generate a cognitive embedding, which not only activates prior information from large text-to-image diffusion models but also facilitates the generation of high-quality reference images to optimize the SR process. To fur-ther improve image fidelity, we propose a novel condition injection scheme called “Ali-in-Attention ”, consolidating all conditional information into a single module. Conse-quently, our method successfully restores semantically cor-rect and photorealistic details, demonstrating state-of-the-art performance across multiple benchmarks. Project page: https://coser-main.github.io/

Latent Diffusion Models (LDMs) are renowned for their powerful capabilities in image and video synthesis. Yet, compared to text-to-image (T2I) editing, text-to-video (T2V) editing suffers from a lack of decent temporal consistency and structure, due to insufficient pre-training data, limited model editability, or extensive tuning costs. To address this gap, we propose FLDM (Fused Latent Diffusion Model), a training-free framework that achieves high-quality T2V editing by integrating various T2I and T2V LDMs. Specifically, FLDM utilizes a hyper-parameter with an update schedule to effectively fuse image and video latents during the denoising process. This paper is the first to reveal that T2I and T2V LDMs can complement each other in terms of structure and temporal consistency, ultimately generating high-quality videos. It is worth noting that FLDM can serve as a versatile plugin, applicable to off-the-shelf image and video LDMs, to significantly enhance the quality of video editing. Extensive quantitative and qualitative experiments on popular T2I and T2V LDMs demonstrate FLDM's superior editing quality than state-of-the-art T2V editing methods.

Natural images captured by mobile devices often suffer from multiple types of degradation, such as noise, blur, and low light. Traditional image restoration methods require manual selection of specific tasks, algorithms, and execution sequences, which is time-consuming and may yield suboptimal results. All-in-one models, though capable of handling multiple tasks, typically support only a limited range and often produce overly smooth, low-fidelity outcomes due to their broad data distribution fitting. To address these challenges, we first define a new pipeline for restoring images with multiple degradations, and then introduce RestoreAgent, an intelligent image restoration system leveraging multimodal large language models. RestoreAgent autonomously assesses the type and extent of degradation in input images and performs restoration through (1) determining the appropriate restoration tasks, (2) optimizing the task sequence, (3) selecting the most suitable models, and (4) executing the restoration. Experimental results demonstrate the superior performance of RestoreAgent in handling complex degradation, surpassing human experts. Furthermore, the system’s modular design facilitates the fast integration of new tasks and models.

Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands. We present UltraPixel, a novel architecture utilizing cascade diffusion models to generate high-quality images at multiple resolutions (\textit{e.g.}, 1K, 2K, and 4K) within a single model, while maintaining computational efficiency. UltraPixel leverages semantics-rich representations of lower-resolution images in a later denoising stage to guide the whole generation of highly detailed high-resolution images, significantly reducing complexity. Specifically, we introduce implicit neural representations for continuous upsampling and scale-aware normalization layers adaptable to various resolutions. Notably, both low- and high-resolution processes are performed in the most compact space, sharing the majority of parameters with less than 3$\%$ additional parameters for high-resolution outputs, largely enhancing training and inference efficiency. Our model achieves fast training with reduced data requirements, producing photo-realistic high-resolution images and demonstrating state-of-the-art performance in extensive experiments.

Pre-training a vision-language model and then fine-tuning it on downstream tasks have become a popular paradigm. However, pre-trained vision-language models with the Transformer architecture usually take long inference time. Knowledge distillation has been an efficient technique to transfer the capability of a large model to a small one while maintaining the accuracy, which has achieved remarkable success in natural language processing. However, it faces many problems when applying KD to the multi-modality applications. In this paper, we propose a novel knowledge distillation method, named CLIPPING11In this paper, CLIPPING means cutting something to make it smaller through distilling., where the plentiful knowledge of a large teacher model that has been fine-tuned for video-language tasks with the powerful pre-trained CLIP can be effectively transferred to a small student only at the fine-tuning stage. Especially, a new layer-wise alignment with the student as the base is proposed for knowledge distillation of the intermediate layers in CLIPPING, which enables the student's layers to be the bases of the teacher, and thus allows the student to fully absorb the knowledge of the teacher. CLIPPING with MobileViT-v2 as the vision encoder without any vision-language pre-training achieves 88.1%-95.3% of the performance of its teacher on three video-language retrieval benchmarks, with its vision encoder being 19.5x smaller. CLIPPING also significantly outperforms a state-of-the-art small baseline (ALL-in-one-B) on the MSR-VTT dataset, obtaining relatively 7.4% performance gain, with 29% fewer parameters and 86.9% fewer flops. Moreover, CLIPPING is comparable or even superior to many large pre-training models.

Text-video retrieval is a fundamental task with high practical value in multi-modal research. Inspired by the great success of pre-trained image-text models with large-scale data, such as CLIP, many methods are proposed to transfer the strong representation learning capability of CLIP to text-video retrieval. However, due to the modality difference between videos and images, how to effectively adapt CLIP to the video domain is still underexplored. In this paper, we investigate this problem from two aspects. First, we enhance the transferred image encoder of CLIP for fine-grained video understanding in a seamless fashion. Second, we conduct fine-grained contrast between videos and texts from both model improvement and loss design. Particularly, we propose a fine-grained contrastive model equipped with parallel isomeric attention and dynamic routing, namely PIDRo, for text-video retrieval. The parallel isomeric attention module is used as the video encoder, which consists of two parallel branches modeling the spatial-temporal information of videos from both patch and frame levels. The dynamic routing module is constructed to enhance the text encoder of CLIP, generating informative word representations by distributing the fine-grained information to the related word tokens within a sentence. Such model design provides us with informative patch, frame and word representations. We then conduct token-wise interaction upon them. With the enhanced encoders and the token-wise loss, we are able to achieve finer-grained text-video alignment and more accurate retrieval. PIDRo obtains state-of-the-art performance over various text-video retrieval benchmarks, including MSR-VTT, MSVD, LSMDC, DiDeMo and ActivityNet.

Video-Language Pre-training (VLP) has become one of the most popular research topics in deep learning. However, compared to image-language pre-training, VLP has lagged far behind due to the lack of large amounts of video-text pairs. In this work, we train a VLP model with a hybrid of image-text and video-text pairs, which significantly outperforms pre-training with only the video-text pairs. Besides, existing methods usually model the cross-modal interaction using cross-attention between single-scale visual tokens and textual tokens. These visual features are either of low resolutions lacking fine-grained information, or of high resolutions without high-level semantics. To address the issue, we propose Hierarchical interactive Video-Language Pre-training (HiVLP) that efficiently uses a hierarchical visual feature group for multi-modal cross-attention during pre-training. In the hierarchical framework, low-resolution features are learned with focus on more global high-level semantic information, while high-resolution features carry fine-grained details. As a result, HiVLP has the ability to effectively learn both the global and fine-grained representations to achieve better alignment between video and text inputs. Furthermore, we design a hierarchical multi-scale vision contrastive loss for self-supervised learning to boost the interaction between them. Experimental results show that HiVLP establishes new state-of-the-art results in three downstream tasks, text-video retrieval, video-text retrieval, and video captioning.