Vision-Language-Action (VLA) models have demonstrated significant potential in complex scene understanding and action reasoning, leading to their increasing adoption in end-to-end autonomous driving systems. However, the long visual tokens of VLA models greatly increase computational costs. Current visual token pruning methods in Vision-Language Models (VLM) rely on either visual token similarity or visual-text attention, but both have shown poor performance in autonomous driving scenarios. Given that human drivers concentrate on relevant foreground areas while driving, we assert that retaining visual tokens containing this foreground information is essential for effective decision-making. Inspired by this, we propose FastDriveVLA, a novel reconstruction-based vision token pruning framework designed specifically for autonomous driving. FastDriveVLA includes a plug-and-play visual token pruner called ReconPruner, which prioritizes foreground information through MAE-style pixel reconstruction. A novel adversarial foreground-background reconstruction strategy is designed to train ReconPruner for the visual encoder of VLA models. Once trained, ReconPruner can be seamlessly applied to different VLA models with the same visual encoder without retraining. To train ReconPruner, we also introduce a large-scale dataset called nuScenes-FG, consisting of 241K image-mask pairs with annotated foreground regions. Our approach achieves state-of-the-art results on the nuScenes open-loop planning benchmark across different pruning ratios.

Despite the recent advances in the application of diffusion models to the realm of image restoration, their inherent stochastic nature can often lead to inaccuracies in reconstructing spatial structures and fine details. This paper introduces an innovative paradigm that harnesses the rich knowledge encapsulated in existing high-level pre-trained models to guide the diffusion process, offering a flexible and potent approach to restoration tasks. However, there are significant challenges in leveraging a pre-trained model for image restoration, including a data gap between natural clean images and degradation images, and paradigm differences that cause insufficient intermediate knowledge. To tackle these issues, we introduce informative Messenger prompts and a Self-adapter for the pre-trained model, whose appropriate information acts as explicit constraints for diffusion, enabling reliable result generation. Specifically, ourMeSa-IRsuccessfully adapts to feature exploration for degraded samples, via disseminating distinctive information from degraded instances. Furthermore, it bolsters knowledge representation through the bidirectional interchange of hierarchical information facilitated by the innovative use of messenger prompts. Experimental results demonstrate the state-of-the-art performance of our framework on five tasks in terms of perceptual and distortion metrics. We will release codes at https://github.com/Ephemeral182/MeSa-IR.

Mirror detection in dynamic scenes plays a crucial role in ensuring safety for various applications, such as drone tracking and robot navigation. However, current mirror detection models often fail in areas with mirrors that have a similar visual and color appearance to their surrounding objects. They also struggle to generalize well in complex cases, primarily due to limited annotated datasets. In this work, we propose a novel temporal prompt learning network with depth memory (TPD-Net) to address these critical challenges. Our approach includes several key components. First, we introduce a Temporal Prompt Generator (TPG) to learn temporal prompt features. Then, we devise Multi-layer Depth-aware Adaptor (MDA) modules to progressively adapt prompt features from the TPG, thereby learning mirror-related features by embedding temporal depth information as guidance. Moreover, we further refine these mirror-related features by constructing a depth memory and a Depth Memory Read module to read the temporal depths stored in the memory, boosting video mirror detection. Experimental results on a benchmark dataset show that our TPD-Net significantly outperforms 22 state-of-the-art methods in video mirror detection tasks. Our code, models, and results are publicly available athttps://github.com/ge-xing/TPDNet.

Real-world image dehazing remains a challenging task due to the diverse nature of haze degradation and the lack of large-scale paired datasets. Existing methods based on hand-crafted priors or generative priors struggle to recover accurate backgrounds and fine details from dense haze regions. In this work, we propose a novel paradigm, PromptHaze, for real-world image dehazing via the depth prompt from the Depth Anything model. By employing a prompt-by-prompt strategy, our method iteratively updates the depth prompt and progressively restores the background through a dehazing network with controllable dehazing strength. Extensive experiments on widely-used real-world dehazing benchmarks demonstrate the superiority of PromptHaze in recovering authentic backgrounds and fine details from various haze scenes, outperforming state-of-the-art methods across multiple quality metrics.

Defocus deblurring is a challenging task due to the spatially varying nature of defocus blur with multiple plausible solutions of a single given image. However, most existing methods falter when faced with extensive and variable defocus blur, either ignoring it or relying on additional loss functions to enhance perceptual quality. This often results in unrealistic reconstructions and compromised generalizability. In this paper, we propose a novel Residual Diffusion Deblurring Model framework for single image defocus deblurring. Our approach integrates a pre-trained defocus map estimator and a lightweight pre-deblur module with a learnable receptive field, providing crucial posterior information to effectively address large-scale and varying shaped defocus blur. In addition, a carefully-design denoising network enables the generation of diverse reconstructions from a single input. This approach not only significantly improves the perceptual quality of defocus deblurring outputs through multi-step residual learning, but also offers a more efficient inference strategy. Experimental results demonstrate that our method achieves competitive performance on real-world defocus deblurring image datasets across both perceptual and distortion evaluation metrics.

Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limitations arise from two inherent challenges in real-world LIE: 1) the collection of distorted/clean image pairs is often impractical and sometimes even unavailable, and 2) accurately modeling complex degradations presents a non-trivial problem. To overcome them, we propose the Attribute Guidance Diffusion framework (AGLLDiff), a training-free method for effective real-world LIE. Instead of specifically defining the degradation process, AGLLDiff shifts the paradigm and models the desired attributes, such as image exposure, structure and color of normal-light images. These attributes are readily available and impose no assumptions about the degradation process, which guides the diffusion sampling process to a reliable high-quality solution space. Extensive experiments demonstrate that our approach outperforms the current leading unsupervised LIE methods across benchmarks in terms of distortion-based and perceptual-based metrics, and it performs well even in sophisticated wild degradation.

Low-light image enhancement (LIE) aims at precisely and efficiently recovering an image degraded in poor illumination environments. Recent advanced LIE techniques are using deep neural networks, which require lots of low-normal light image pairs, network parameters, and computational resources. As a result, their practicality is limited. In this work, we devise a novel unsupervised LIE framework based on diffusion priors and lookup tables (DPLUT) to achieve efficient low-light image recovery. The proposed approach comprises two critical components: a light adjustment lookup table (LLUT) and a noise suppression lookup table (NLUT). LLUT is optimized with a set of unsupervised losses. It aims at predicting pixel-wise curve parameters for the dynamic range adjustment of a specific image. NLUT is designed to remove the amplified noise after the light brightens. As diffusion models are sensitive to noise, diffusion priors are introduced to achieve high-performance noise suppression. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods in terms of visual quality and efficiency.

3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial configurations. Recent research has increasingly focused on the explicit extraction of 3D features, while still facing challenges such as the lack of large-scale robotic 3D data and the potential loss of spatial geometry. To address these limitations, we propose the Lift3D framework, which progressively enhances 2D foundation models with implicit and explicit 3D robotic representations to construct a robust 3D manipulation policy. Specifically, we first design a task-aware masked autoencoder that masks task-relevant affordance patches and reconstructs depth information, enhancing the 2D foundation model’s implicit 3D robotic representation. After self-supervised fine-tuning, we introduce a 2D model-lifting strategy that establishes a positional mapping between the input 3D points and the positional embeddings of the 2D model. Based on the mapping, Lift3D utilizes the 2D foundation model to directly encode point cloud data, leveraging large-scale pretrained knowledge to construct explicit 3D robotic representations while minimizing spatial information loss. In experiments, Lift3D consistently outperforms previous state-of-the-art methods across several simulation benchmarks and real-world scenarios.

Snowfall presents significant challenges for visual data processing, necessitating specialized desnowing algorithms. However, existing models often fail to generalize effectively due to their heavy reliance on synthetic datasets. Furthermore, current real-world snowfall datasets are limited in scale and lack dedicated evaluation metrics designed specifically for snowfall degradation, thus hindering the effective integration of real snowy images into model training to reduce domain gaps. To address these challenges, we first introduce RealSnow10K, a large-scale, high-quality dataset consisting of over 10,000 annotated real-world snowy images. In addition, we curate a preference dataset comprising 36,000 expert-ranked image pairs, enabling the adaptation of multimodal large language models (MLLMs) to better perceive snowy image quality through our innovative Multi-Model Preference Optimization (MMPO). Finally, we propose the SnowMaster, which employs MMPO-enhanced MLLM to perform accurate snowy image evaluation and pseudo-label filtering for semi-supervised training. Experiments demonstrate that SnowMaster delivers superior desnowing performance under real-world conditions.

Vision-centric perception systems struggle with unpredictable and coupled weather degradations in the wild. Current solutions are often limited, as they either depend on specific degradation priors or suffer from significant domain gaps. To enable robust and autonomous operation in real-world conditions, we propose JarvisIR, a VLM-powered agent that leverages the VLM as a controller to manage multiple expert restoration models. To further enhance system robustness, reduce hallucinations, and improve generalizability in real-world adverse weather, JarvisIR employs a novel two-stage framework consisting of supervised fine-tuning and human feedback alignment. Specifically, to address the lack of paired data in real-world scenarios, the human feedback alignment enables the VLM to be fine-tuned effectively on large-scale real-world data in an unsupervised manner. To support the training and evaluation of JarvisIR, we introduce CleanBench, a comprehensive dataset consisting of high-quality and large-scale instruction-responses pairs, including 150K synthetic entries and 80K real entries. Extensive experiments demonstrate that JarvisIR exhibits superior decision-making and restoration capabilities. Compared with existing methods, it achieves a 50% improvement in the average of all perception metrics on CleanBench-Real.

Mirror detection is a challenging task because a mirror’s visual appearance varies depending on the reflected content. Due to limited annotated data, current methods failed to generalize well for detecting diverse mirror scenes. Semi-supervised learning with large-scale unlabeled data can improve generalization capabilities on mirror detection, but these methods often suffer from unreliable pseudo-labels due to distribution differences between labeled and unlabeled data, therefore affecting the learning process. To address this issue, we first collect a large-scale dataset of approximately 0.4 million mirror-related images from the internet, significantly expanding the data scale for mirror detection. To effectively exploit this unlabeled dataset, we propose the first semi-supervised framework (namely an iterative data engine) consisting of four steps: (1) mirror detection model training, (2) pseudo label prediction, (3) dual guidance scoring, and (4) selection of highly reliable pseudo labels. In each iteration of the data engine, we employ a geometric accuracy scoring approach to assess pseudo labels based on multiple segmentation metrics, and design a multi-modal agent-driven semantic scoring approach to enhance the semantic perception of pseudo labels. These two scoring approaches can effectively improve the reliability of pseudo labels by selecting unlabeled samples with higher scores. Our method demonstrates promising performance across three mirror detection tasks and exhibits strong generalization on unseen examples. Our code will be publicly available at https://github.com/ge-xing/DAM.

Real-world image dehazing is crucial for enhancing visual quality in computer vision applications. However, existing physics-based haze generation paradigms struggle to model the complexities of real-world haze and lack controllability, limiting the performance of existing baselines on real-world images. In this paper, we introduce GenHaze, a pioneering haze generation framework that enables the one-step generation of high-quality, reference-controllable hazy images. GenHaze leverages the pre-trained latent diffusion model (LDM) with a carefully designed clean-to-haze generation protocol to produce realistic hazy images. Additionally, by leveraging its fast, controllable generation of paired highquality hazy images, we illustrate that existing dehazing baselines can be unleashed in a simple and efficient manner. Extensive experiments indicate that GenHaze achieves visually convincing and quantitatively superior hazy images. It also significantly improves multiple existing dehazing models across 7 non-reference metrics with minimal fine-tuning epochs. Our work demonstrates that LDM possesses the potential to generate realistic degradations, providing an effective alternative to prior generation pipelines.

Recently, mobile manipulation has attracted increasing attention for enabling language-conditioned robotic control in household tasks. However, existing methods still face challenges in coordinating mobile base and manipulator, primarily due to two limitations. On the one hand, they fail to explicitly model the influence of the mobile base on manipulator control, which easily leads to error accumulation under high degrees of freedom. On the other hand, they treat the entire mobile manipulation process with the same visual observation modality (e.g., either all 2D or all 3D), overlooking the distinct multimodal perception requirements at different stages during mobile manipulation. To address this, we propose the Adaptive Coordination Diffusion Transformer (AC-DiT), which enhances mobile base and manipulator coordination for end-to-end mobile manipulation. First, since the motion of the mobile base directly influences the manipulator's actions, we introduce a mobility-to-body conditioning mechanism that guides the model to first extract base motion representations, which are then used as context prior for predicting whole-body actions. This enables whole-body control that accounts for the potential impact of the mobile base’s motion. Second, to meet the perception requirements at different stages of mobile manipulation, we design a perception-aware multimodal conditioning strategy that dynamically adjusts the fusion weights between various 2D visual images and 3D point clouds, yielding visual features tailored to the current perceptual needs. This allows the model to, for example, adaptively rely more on 2D inputs when semantic information is crucial for action prediction, while placing greater emphasis on 3D geometric information when precise spatial understanding is required. We empirically validate AC-DiT through extensive experiments on both simulated and real-world mobile manipulation tasks, demonstrating superior performance compared to existing methods.

Night photography often struggles with challenges like low light and blurring, stemming from dark environments and prolonged exposures. Current methods either disregard priors and directly fitting end-to-end networks, leading to inconsistent illumination, or rely on unreliable handcrafted priors to constrain the network, thereby bringing the greater error to the final result. We believe in the strength of data-driven high-quality priors and strive to offer a reliable and consistent prior, circumventing the restrictions of manual priors. In this paper, we propose Clearer Night Image Restoration with Vector-Quantized Codebook (VQCNIR) to achieve remarkable and consistent restoration outcomes on real-world and synthetic benchmarks. To ensure the faithful restoration of details and illumination, we propose the incorporation of two essential modules: the Adaptive Illumination Enhancement Module (AIEM) and the Deformable Bi-directional Cross-Attention (DBCA) module. The AIEM leverages the inter-channel correlation of features to dynamically maintain illumination consistency between degraded features and high-quality codebook features. Meanwhile, the DBCA module effectively integrates texture and structural information through bi-directional cross-attention and deformable convolution, resulting in enhanced fine-grained detail and structural fidelity across parallel decoders. Extensive experiments validate the remarkable benefits of VQCNIR in enhancing image quality under low-light conditions, showcasing its state-of-the-art performance on both synthetic and real-world datasets. The code is available at https://github.com/AlexZou14/VQCNIR.

Diffusion Models have shown remarkable performance in image generation tasks, which are capable of generating diverse and realistic image content. When adopting diffusion models for image restoration, the crucial challenge lies in how to preserve high-level image fidelity in the random-ness diffusion process and generate accurate background structures and realistic texture details. In this paper, we propose a general framework and develop a Diffusion Texture Prior Model (DTPM) for image restoration tasks. DTPM explicitly models high-quality texture details through the diffusion process, rather than global contextual content. In phase one of the training stage, we pretrain DTPM on approximately 55K high-quality image samples, after which we freeze most of its parameters. In phase two, we insert conditional guidance adapters into DTPM and equip it with an initial predictor, thereby facilitating its rapid adaptation to downstream image restoration tasks. Our DTPM could mitigate the randomness of traditional diffusion models by utilizing encapsulated rich and diverse texture knowledge and background structural information provided by the initial predictor during the sampling process.

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.

Snow removal causes challenges due to its characteristic of complex degradations. To this end, targeted treatment of multi-scale snow degradations is critical for the network to learn effective snow removal. In order to handle the diverse scenes, we propose a multi-scale projection transformer (MSP-Former), which understands and covers a variety of snow degradation features in a multi-path manner, and integrates comprehensive scene context information for clean reconstruction via self-attention operation. For the local details of various snow degradations, the local capture module is introduced in parallel to assist in the rebuilding of a clean image. Such design achieves the SOTA performance on three desnowing benchmark datasets while costing the low parameters and computational complexity, providing a guarantee of practicality.

Varicolored haze caused by chromatic casts poses haze removal and depth estimation challenges. Recent learning-based depth estimation methods are mainly targeted at dehazing first and estimating depth subsequently from haze-free scenes. This way, the inner connections between colored haze and scene depth are lost. In this paper, we propose a real-time transformer for simultaneous single image Depth Estimation and Haze Removal (DEHRFormer). DEHRFormer consists of a single encoder and two task-specific decoders. The transformer decoders with learnable queries are designed to decode coupling features from the task-agnostic encoder and project them into clean image and depth map, respectively. In addition, we introduce a novel learning paradigm that utilizes contrastive learning and domain consistency learning to tackle weak-generalization problem for real-world dehazing, while predicting the same depth map from the same scene with varicolored haze. Experiments demonstrate that DEHRFormer achieves significant performance improvement across diverse varicolored haze scenes over previous depth estimation networks and dehazing approaches.

In the real world, image degradations caused by rain often exhibit a combination of rain streaks and raindrops, thereby increasing the challenges of recovering the underlying clean image. Note that the rain streaks and raindrops have diverse shapes, sizes, and locations in the captured image, and thus modeling the correlation relationship between irregular degradations caused by rain artifacts is a necessary prerequisite for image deraining. This paper aims to present an efficient and flexible mechanism to learn and model degradation relationships in a global view, thereby achieving a unified removal of intricate rain scenes. To do so, we propose a Sparse Sampling Transformer based on Uncertainty-Driven Ranking, dubbed UDR-S2Former. Compared to previous methods, our UDR-S2Former has three merits. First, it can adaptively sample relevant image degradation information to model underlying degradation relationships. Second, explicit application of the uncertainty-driven ranking strategy can facilitate the network to attend to degradation features and understand the reconstruction process. Finally, experimental results show that our UDR-S2Former clearly outperforms state-of-the-art methods for all benchmarks.

Despite recent advancements in unified adverse weather removal methods, there remains a significant challenge of achieving realistic fine-grained texture and reliable background reconstruction to mitigate serious distortions.Inspired by recent advancements in codebook and vector quantization (VQ) techniques, we present a novel Adverse Weather Removal network with Codebook Priors (AWRCP) to address the problem of unified adverse weather removal. AWRCP leverages high-quality codebook priors derived from undistorted images to recover vivid texture details and faithful background structures. However, simply utilizing high-quality features from the codebook does not guarantee good results in terms of fine-grained details and structural fidelity. Therefore, we develop a deformable cross-attention with sparse sampling mechanism for flexible perform feature interaction between degraded features and high-quality features from codebook priors. In order to effectively incorporate high-quality texture features while maintaining the realism of the details generated by codebook priors, we propose a hierarchical texture warping head that gradually fuses hierarchical codebook prior features into high-resolution features at final restoring stage.With the utilization of the VQ codebook as a feature dictionary of high quality and the proposed designs, AWRCP can largely improve the restored quality of texture details, achieving the state-of-the-art performance across multiple adverse weather removal benchmark.

Underwater images typically experience mixed degradations of brightness and structure caused by the absorption and scattering of light by suspended particles. To address this issue, we propose a Real-time Spatial and Frequency Domains Modulation Network (RSFDM-Net) for the efficient enhancement of colors and details in underwater images. Specifically, our proposed conditional network is designed with Adaptive Fourier Gating Mechanism (AFGM) and Multiscale Convolutional Attention Module (MCAM) to generate vectors carrying low-frequency background information and high-frequency detail features, which effectively promote the network to model global background information and local texture details. To more precisely correct the color cast and low saturation of the image, we introduce a Three-branch Feature Extraction (TFE) block in the primary net that processes images pixel by pixel to integrate the color information extended by the same channel (R, G, or B). This block consists of three small branches, each of which has its own weights. Extensive experiments demonstrate that our network significantly outperforms over state-of-the-art methods in both visual quality and quantitative metrics.

Removing snow from a single image poses a significant challenge within the image restoration domain, as snowfall's effects are in various scales and forms. Existing methods have tried to tackle this issue by using multi-scale approaches, but their reliance on targeted design for handling each single-scale feature has resulted in unsatisfactory performance. This is primarily due to a lack of cross-scale knowledge, making it difficult to effectively handle degradations. To this end, we propose a novel approach, CPLFormer, which uses snow prototypes to own comprehensive clean scene understanding through learning from cross-scale features, outperforming convolutional network and vanilla transformer-based solutions. CPLFormer has several advantages: firstly, learnable snow prototypes learn global context information from multiple scales to uncover hidden clean cues; secondly, prototypes can propagate cross-scale information to each patch through cross-attention to assist with clean patch reconstruction; thirdly, CPLFormer surpasses advanced state-of-the-art desnowing networks and the prevalent universal image restoration transformers on six synthetic and real-world benchmark tests.

Single-image snow removal aims to restore clean images from heterogeneous and irregular snow degradations. Recent methods utilize neural networks to remove various degradations directly. However, these approaches suffer from the limited ability to flexibly perceive complicated snow degradation patterns and insufficient representation of background structure information. To further improve the performance and generalization ability of snow removal, this paper aims to develop a novel and efficient paradigm from the perspective of degradation perceiving and background modeling.

Nighttime image dehazing is a challenging task due to the presence of multiple types of adverse degrading effects including glow, haze, blur, noise, color distortion, and so on. However, most previous studies mainly focus on daytime image dehazing or partial degradations presented in nighttime hazy scenes, which may lead to unsatisfactory restoration results. In this paper, we propose an end-to-end transformer-based framework for nighttime haze removal, called NightHazeFormer. Our proposed approach consists of two stages: supervised pre-training and semi-supervised fine-tuning. During the pre-training stage, we introduce two powerful priors into the transformer decoder to generate the non-learnable prior queries, which guide the model to extract specific degradations. For the fine-tuning, we combine the generated pseudo ground truths with input real-world nighttime hazy images as paired images and feed into the synthetic domain to fine-tune the pre-trained model. This semi-supervised fine-tuning paradigm helps improve the generalization to real domain. In addition, we also propose a large-scale synthetic dataset called UNREAL-NH, to simulate the real-world nighttime haze scenarios comprehensively. Extensive experiments on several synthetic and real-world datasets demonstrate the superiority of our NightHazeFormer over state-of-the-art nighttime haze removal methods in terms of both visually and quantitatively.

Video restoration networks aim to restore high-quality frame sequences from degraded ones. However, traditional video restoration methods heavily rely on temporal modeling operators or optical flow estimation, which limits their versatility. The aim of this work is to present a novel approach for video restoration that eliminates inefficient temporal modeling operators and pixel-level feature alignment in the network architecture. The proposed method, Sequential Affinity Learning Network (SALN), is designed based on an affinity mechanism that establishes direct correspondences between the Query frame, degraded sequence, and restored frames in latent space. This unique perspective allows for more accurate and effective restoration of video content without relying on temporal modeling operators or optical flow estimation techniques. Moreover, we enhanced the design of the channel-wise self-attention block to improve the decoder's performance for video restoration. Our method outperformed previous state-of-the-art methods by a significant margin in several classic video tasks, including video deraining, video dehazing, and video waterdrop removal, demonstrating excellent efficiency. As a novel network that differs significantly from previous video restoration methods, SALN aims to provide innovative ideas and directions for video restoration. Our contributions include proposing a novel affinity-based approach for video restoration, enhancing the design of the channel-wise self-attention block, and achieving state-of-the-art performance on several classic video tasks.