Rui Chen

Yun Liu, Xiaomeng Xu, Weihang Chen et al.

When manipulating an object to accomplish complex tasks, humans rely on both vision and touch to keep track of the object's 6D pose. However, most existing object pose tracking systems in robotics rely exclusively on visual signals, which hinder a robot's ability to manipulate objects effectively. To address this limitation, we introduce TEG-Track, a tactile-enhanced 6D pose tracking system that can track previously unseen objects held in hand. From consecutive tactile signals, TEG-Track optimizes object velocities from marker flows when slippage does not occur, or regresses velocities using a slippage estimation network when slippage is detected. The estimated object velocities are integrated into a geometric-kinematic optimization scheme to enhance existing visual pose trackers. To evaluate our method and to facilitate future research, we construct a real-world dataset for visual-tactile in-hand object pose tracking. Experimental results demonstrate that TEG-Track consistently enhances state-of-the-art generalizable 6D pose trackers in synthetic and real-world scenarios. Our code and dataset are available at https://github.com/leolyliu/TEG-Track.

Rui Chen, Xiaofeng Yang, Hui Zhang

In this paper, we consider the numerical approximations for a hydrodynamical model of smectic-A liquid crystals. The model, derived from the variational approach of the modified Oseen-Frank energy, is a highly nonlinear system that couples the incompressible Navier-Stokes equations and a constitutive equation for the layer variable. We develop two linear, second-order time-marching schemes based on the "Invariant Energy Quadratization" method for nonlinear terms in the constitutive equation, the projection method for the Navier-Stokes equations, and some subtle implicit-explicit treatments for the convective and stress terms. Moreover, we prove the well-posedness of the linear system and their unconditionally energy stabilities rigorously. Various numerical experiments are presented to demonstrate the stability and the accuracy of the numerical schemes in simulating the dynamics under shear flow and the magnetic field.

Rui Chen, Yongqiang Tang, Wensheng Zhang et al.

Multi-view clustering has attracted much attention thanks to the capacity of multi-source information integration. Although numerous advanced methods have been proposed in past decades, most of them generally overlook the significance of weakly-supervised information and fail to preserve the feature properties of multiple views, thus resulting in unsatisfactory clustering performance. To address these issues, in this paper, we propose a novel Deep Multi-view Semi-supervised Clustering (DMSC) method, which jointly optimizes three kinds of losses during networks finetuning, including multi-view clustering loss, semi-supervised pairwise constraint loss and multiple autoencoders reconstruction loss. Specifically, a KL divergence based multi-view clustering loss is imposed on the common representation of multi-view data to perform heterogeneous feature optimization, multi-view weighting and clustering prediction simultaneously. Then, we innovatively propose to integrate pairwise constraints into the process of multi-view clustering by enforcing the learned multi-view representation of must-link samples (cannot-link samples) to be similar (dissimilar), such that the formed clustering architecture can be more credible. Moreover, unlike existing rivals that only preserve the encoders for each heterogeneous branch during networks finetuning, we further propose to tune the intact autoencoders frame that contains both encoders and decoders. In this way, the issue of serious corruption of view-specific and view-shared feature space could be alleviated, making the whole training procedure more stable. Through comprehensive experiments on eight popular image datasets, we demonstrate that our proposed approach performs better than the state-of-the-art multi-view and single-view competitors.

Rui Chen, Christos G. Cassandras, Amin Tahmasbi-Sarvestani

We derive optimal control policies for a Connected and Automated Vehicle (CAV) cooperating with neighboring CAVs to implement a highway lane change maneuver. We optimize the maneuver time and subsequently minimize the associated energy consumption of all cooperating vehicles in this maneuver. We prove structural properties of the optimal policies which simplify the solution derivations and lead to analytical optimal control expressions. The solutions, when they exist, are guaranteed to satisfy safety constraints for all vehicles involved in the maneuver. Simulation results show the effectiveness of the proposed solution and significant performance improvements compared to maneuvers performed by human-driven vehicles.

Jianyu Tao, Changping Hu, Edward Yang et al.

NeRFs have achieved incredible success in novel view synthesis. However, the accuracy of the implicit geometry is unsatisfactory because the passive static environmental illumination has low spatial frequency and cannot provide enough information for accurate geometry reconstruction. In this work, we propose ActiveNeRF, a 3D geometry reconstruction framework, which improves the geometry quality of NeRF by actively projecting patterns of high spatial frequency onto the scene using a projector which has a constant relative pose to the camera. We design a learnable active pattern rendering pipeline which jointly learns the scene geometry and the active pattern. We find that, by adding the active pattern and imposing its consistency across different views, our proposed method outperforms state of the art geometry reconstruction methods qualitatively and quantitatively in both simulation and real experiments. Code is avaliable at https://github.com/hcp16/active_nerf

Rui Chen, Christos G. Cassandras

We extend Stochastic Flow Models (SFMs), used for a large class of discrete event and hybrid systems, by including the delays which typically arise in flow movement. We apply this framework to the multi-intersection traffic light control problem by including transit delays for vehicles moving from one intersection to the next. Using Infinitesimal Perturbation Analysis (IPA) for this SFM with delays, we derive new on-line gradient estimates of several congestion cost metrics with respect to the controllable green and red cycle lengths. The IPA estimators are used to iteratively adjust light cycle lengths to improve performance and, in conjunction with a standard gradient-based algorithm, to obtain optimal values which adapt to changing traffic conditions. We introduce two new cost metrics to better capture congestion and show that the inclusion of delays in our analysis leads to improved performance relative to models that ignore delays.

Weiye Zhao, Feihan Li, Yifan Sun et al.

In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily emphasize improvement in expected performance, lacking the ability to control over the worst-case performance outcomes. To address this limitation, we introduce a novel objective function, optimizing which leads to guaranteed monotonic improvement in the lower probability bound of performance with high confidence. Building upon this groundbreaking theoretical advancement, we further introduce a practical solution called Absolute Policy Optimization (APO). Our experiments demonstrate the effectiveness of our approach across challenging continuous control benchmark tasks and extend its applicability to mastering Atari games. Our findings reveal that APO as well as its efficient variation Proximal Absolute Policy Optimization (PAPO) significantly outperforms state-of-the-art policy gradient algorithms, resulting in substantial improvements in worst-case performance, as well as expected performance.

Songyuan Sui, Hongyi Liu, Serena Liu et al.

Table understanding requires structured, multi-step reasoning. Large Language Models (LLMs) struggle with it due to the structural complexity of tabular data. Recently, multi-agent frameworks for SQL generation have shown promise in tackling the challenges of understanding tabular data, but existing approaches often suffer from limitations such as the inability to comprehend table structure for reliable SQL generation, error propagation that results in invalid queries, and over-reliance on execution correctness. To address these issues, we propose Chain-of-Query (CoQ), a novel multi-agent framework for SQL-aided table understanding. CoQ adopts natural-language-style representations of table schemas to abstract away structural noise and enhance understanding. It employs a clause-by-clause SQL generation strategy to improve query quality and introduces a hybrid reasoning division that separates SQL-based mechanical reasoning from LLM-based logical inference, thereby reducing reliance on execution outcomes. Extensive experiments across four models and five widely used benchmarks demonstrate that CoQ achieves substantial accuracy improvements and significantly lowers invalid SQL rates compared to prior generic LLM-based, SQL-aided, and hybrid baselines, confirming its superior effectiveness in table understanding. The code is available at https://github.com/SongyuanSui/ChainofQuery.

Li Shen, Yao Lu, Hao Chen et al.

Building-change detection underpins many important applications, especially in the military and crisis-management domains. Recent methods used for change detection have shifted towards deep learning, which depends on the quality of its training data. The assembly of large-scale annotated satellite imagery datasets is therefore essential for global building-change surveillance. Existing datasets almost exclusively offer near-nadir viewing angles. This limits the range of changes that can be detected. By offering larger observation ranges, the scroll imaging mode of optical satellites presents an opportunity to overcome this restriction. This paper therefore introduces S2Looking, a building-change-detection dataset that contains large-scale side-looking satellite images captured at various off-nadir angles. The dataset consists of 5000 bitemporal image pairs of rural areas and more than 65,920 annotated instances of changes throughout the world. The dataset can be used to train deep-learning-based change-detection algorithms. It expands upon existing datasets by providing (1) larger viewing angles; (2) large illumination variances; and (3) the added complexity of rural images. To facilitate {the} use of the dataset, a benchmark task has been established, and preliminary tests suggest that deep-learning algorithms find the dataset significantly more challenging than the closest-competing near-nadir dataset, LEVIR-CD+. S2Looking may therefore promote important advances in existing building-change-detection algorithms. The dataset is available at https://github.com/S2Looking/.

Rui Chen, Songfang Han, Jing Xu et al.

We introduce Point-MVSNet, a novel point-based deep framework for multi-view stereo (MVS). Distinct from existing cost volume approaches, our method directly processes the target scene as point clouds. More specifically, our method predicts the depth in a coarse-to-fine manner. We first generate a coarse depth map, convert it into a point cloud and refine the point cloud iteratively by estimating the residual between the depth of the current iteration and that of the ground truth. Our network leverages 3D geometry priors and 2D texture information jointly and effectively by fusing them into a feature-augmented point cloud, and processes the point cloud to estimate the 3D flow for each point. This point-based architecture allows higher accuracy, more computational efficiency and more flexibility than cost-volume-based counterparts. Experimental results show that our approach achieves a significant improvement in reconstruction quality compared with state-of-the-art methods on the DTU and the Tanks and Temples dataset. Our source code and trained models are available at https://github.com/callmeray/PointMVSNet .

Zhaokun Zhou, Qiulin Wang, Bin Lin et al.

As an alternative to expensive expert evaluation, Image Aesthetic Assessment (IAA) stands out as a crucial task in computer vision. However, traditional IAA methods are typically constrained to a single data source or task, restricting the universality and broader application. In this work, to better align with human aesthetics, we propose a Unified Multi-modal Image Aesthetic Assessment (UNIAA) framework, including a Multi-modal Large Language Model (MLLM) named UNIAA-LLaVA and a comprehensive benchmark named UNIAA-Bench. We choose MLLMs with both visual perception and language ability for IAA and establish a low-cost paradigm for transforming the existing datasets into unified and high-quality visual instruction tuning data, from which the UNIAA-LLaVA is trained. To further evaluate the IAA capability of MLLMs, we construct the UNIAA-Bench, which consists of three aesthetic levels: Perception, Description, and Assessment. Extensive experiments validate the effectiveness and rationality of UNIAA. UNIAA-LLaVA achieves competitive performance on all levels of UNIAA-Bench, compared with existing MLLMs. Specifically, our model performs better than GPT-4V in aesthetic perception and even approaches the junior-level human. We find MLLMs have great potential in IAA, yet there remains plenty of room for further improvement. The UNIAA-LLaVA and UNIAA-Bench will be released.

Zifan Wang, Junyu Chen, Ziqing Chen et al.

This paper presents GenH2R, a framework for learning generalizable vision-based human-to-robot (H2R) handover skills. The goal is to equip robots with the ability to reliably receive objects with unseen geometry handed over by humans in various complex trajectories. We acquire such generalizability by learning H2R handover at scale with a comprehensive solution including procedural simulation assets creation, automated demonstration generation, and effective imitation learning. We leverage large-scale 3D model repositories, dexterous grasp generation methods, and curve-based 3D animation to create an H2R handover simulation environment named \simabbns, surpassing the number of scenes in existing simulators by three orders of magnitude. We further introduce a distillation-friendly demonstration generation method that automatically generates a million high-quality demonstrations suitable for learning. Finally, we present a 4D imitation learning method augmented by a future forecasting objective to distill demonstrations into a visuo-motor handover policy. Experimental evaluations in both simulators and the real world demonstrate significant improvements (at least +10\% success rate) over baselines in all cases. The project page is https://GenH2R.github.io/.

Jingcheng Ni, Yuxin Guo, Yichen Liu et al.

World models that forecast environmental changes from actions are vital for autonomous driving models with strong generalization. The prevailing driving world model mainly build on video prediction model. Although these models can produce high-fidelity video sequences with advanced diffusion-based generator, they are constrained by their predictive duration and overall generalization capabilities. In this paper, we explore to solve this problem by combining generation loss with MAE-style feature-level context learning. In particular, we instantiate this target with three key design: (1) A more scalable Diffusion Transformer (DiT) structure trained with extra mask construction task. (2) we devise diffusion-related mask tokens to deal with the fuzzy relations between mask reconstruction and generative diffusion process. (3) we extend mask construction task to spatial-temporal domain by utilizing row-wise mask for shifted self-attention rather than masked self-attention in MAE. Then, we adopt a row-wise cross-view module to align with this mask design. Based on above improvement, we propose MaskGWM: a Generalizable driving World Model embodied with Video Mask reconstruction. Our model contains two variants: MaskGWM-long, focusing on long-horizon prediction, and MaskGWM-mview, dedicated to multi-view generation. Comprehensive experiments on standard benchmarks validate the effectiveness of the proposed method, which contain normal validation of Nuscene dataset, long-horizon rollout of OpenDV-2K dataset and zero-shot validation of Waymo dataset. Quantitative metrics on these datasets show our method notably improving state-of-the-art driving world model.

Tianhao Wei, Liqian Ma, Rui Chen et al.

The requirements for real-world manipulation tasks are diverse and often conflicting; some tasks require precise motion while others require force compliance; some tasks require avoidance of certain regions, while others require convergence to certain states. Satisfying these varied requirements with a fixed state-action representation and control strategy is challenging, impeding the development of a universal robotic foundation model. In this work, we propose Meta-Control, the first LLM-enabled automatic control synthesis approach that creates customized state representations and control strategies tailored to specific tasks. Our core insight is that a meta-control system can be built to automate the thought process that human experts use to design control systems. Specifically, human experts heavily use a model-based, hierarchical (from abstract to concrete) thought model, then compose various dynamic models and controllers together to form a control system. Meta-Control mimics the thought model and harnesses LLM's extensive control knowledge with Socrates' "art of midwifery" to automate the thought process. Meta-Control stands out for its fully model-based nature, allowing rigorous analysis, generalizability, robustness, efficient parameter tuning, and reliable real-time execution.

Zhenlong Yuan, Xiangyan Qu, Chengxuan Qian et al.

Multimodal large language models (MLLMs) have demonstrated remarkable potential in bridging visual and textual reasoning, yet their reliance on text-centric priors often limits their ability to disentangle semantically similar actions in open-vocabulary scenarios. To address this, we propose Video-STAR, a framework that harmonizes contextual sub-motion decomposition with tool-augmented reinforcement learning for open-vocabulary action recognition (OVAR). Unlike prior methods that treat actions as monolithic entities, our approach innovatively decomposes actions into discriminative sub-motions for fine-grained matching while dynamically invoking domain-specific tools for cross-modal interleaving, thereby enabling category-specific reasoning capacity and reducing cross-modal hallucination. Moreover, by designing a hierarchical reward that balances tool-usage efficiency, sub-motion relevance, and structural coherence in reasoning, our method autonomously leverages external tools to prioritize sub-motion patterns without explicit supervision, transmitting from text-centric reasoning to visually grounded inference. Extensive evaluations on HMDB-51, UCF-101, SSv2, Kinetics-400, and Kinetics-600 datasets demonstrate our state-of-the-art performance, outperforming existing methods in distinguishing fine-grained actions and handling cross-modal hallucination, validating our excellent robustness and generalization.

Haowang Cui, Rui Chen, Tao Luo et al.

The task of synthesizing novel views from a single image is highly ill-posed due to multiple explanations for unobserved areas. Most current methods tend to generate unseen regions from ambiguity priors and interpolation near input views, which often lead to severe distortions. To address this limitation, we propose a novel model dubbed as UniView, which can leverage reference images from a similar object to provide strong prior information during view synthesis. More specifically, we construct a retrieval and augmentation system and employ a multimodal large language model (MLLM) to assist in selecting reference images that meet our requirements. Additionally, a plug-and-play adapter module with multi-level isolation layers is introduced to dynamically generate reference features for the target views. Moreover, in order to preserve the details of an original input image, we design a decoupled triple attention mechanism, which can effectively align and integrate multi-branch features into the synthesis process. Extensive experiments have demonstrated that our UniView significantly improves novel view synthesis performance and outperforms state-of-the-art methods on the challenging datasets.

Giorgio Giannone, Ruoteng Li, Qianli Feng et al.

Vision-language models (VLMs) have demonstrated remarkable potential in integrating visual and linguistic information, but their performance is often constrained by the need for extensive, high-quality image-text training data. Curation of these image-text pairs is both time-consuming and computationally expensive. To address this challenge, we introduce SVP (Sampling-based Visual Projection), a novel framework that enhances vision-language alignment without relying on manually curated text-image pairs or preference annotation. SVP leverages a small set of manually selected images, self-captioning and a pre-trained grounding model as a feedback mechanism to elicit latent information in VLMs. We evaluate our approach across six key areas: captioning, referring, visual question answering, multitasking, hallucination control, and object recall. Results demonstrate significant improvements, including a 14 % average improvement in captioning tasks, up to 12 % increase in object recall, and significantly reduced hallucinations, while maintaining question-answering capabilities. Using SVP, a small VLM achieves hallucination reductions similar to a model five times larger, while a VLM with initially poor referring capabilities more than doubles its performance, approaching parity with a model twice its size.

Rui Chen, Alvin Shek, Changliu Liu

We study real-time collaborative robot (cobot) handling, where the cobot maneuvers a workpiece under human commands. This is useful when it is risky for humans to directly handle the workpiece. However, it is hard to make the cobot both easy to command and flexible in possible operations. In this work, we propose a Real-Time Collaborative Robot Handling (RTCoHand) framework that allows the control of cobot via user-customized dynamic gestures. This is hard due to variations among users, human motion uncertainties, and noisy human input. We model the task as a probabilistic generative process, referred to as Conditional Collaborative Handling Process (CCHP), and learn from human-human collaboration. We thoroughly evaluate the adaptability and robustness of CCHP and apply our approach to a real-time cobot handling task with Kinova Gen3 robot arm. We achieve seamless human-robot collaboration with both experienced and new users. Compared to classical controllers, RTCoHand allows significantly more complex maneuvers and lower user cognitive burden. It also eliminates the need for trial-and-error, rendering it advantageous in safety-critical tasks.

Isabella Liu, Edward Yang, Jianyu Tao et al.

Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but quite difficult to obtain in the real domain, we propose a method that leverages the best of both worlds. In this paper we present a new framework, ActiveZero, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. First, we demonstrate the transferability of our method to out-of-distribution real data by using a mixed domain learning strategy. In the simulation domain, we use a combination of supervised disparity loss and self-supervised losses on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised losses on a dataset that is out-of-distribution from either training simulation data or test real data. Second, our method introduces a novel self-supervised loss called temporal IR reprojection to increase the robustness and accuracy of our reprojections in hard-to-perceive regions. Finally, we show how the method can be trained end-to-end and that each module is important for attaining the end result. Extensive qualitative and quantitative evaluations on real data demonstrate state of the art results that can even beat a commercial depth sensor.

Gabriel Appleby, Mateus Espadoto, Rui Chen et al.

Projection algorithms such as t-SNE or UMAP are useful for the visualization of high dimensional data, but depend on hyperparameters which must be tuned carefully. Unfortunately, iteratively recomputing projections to find the optimal hyperparameter value is computationally intensive and unintuitive due to the stochastic nature of these methods. In this paper we propose HyperNP, a scalable method that allows for real-time interactive hyperparameter exploration of projection methods by training neural network approximations. HyperNP can be trained on a fraction of the total data instances and hyperparameter configurations and can compute projections for new data and hyperparameters at interactive speeds. HyperNP is compact in size and fast to compute, thus allowing it to be embedded in lightweight visualization systems such as web browsers. We evaluate the performance of the HyperNP across three datasets in terms of performance and speed. The results suggest that HyperNP is accurate, scalable, interactive, and appropriate for use in real-world settings.

Rui Chen, Jinxin Zhao, Liangjun Zhang

Natural language-based robotic navigation remains a challenging problem due to the human knowledge of navigation constraints, and destination is not directly compatible with the robot knowledge base. In this paper, we aim to translate natural destination commands into high-level robot navigation plans given a map of interest. We identify grammatically associated segments of destination description and recursively apply each of them to update a belief distribution of an area over the given map.We train a destination grounding model using a dataset of single-step belief update for precise, proximity, and directional modifier types. We demonstrate our method on real-world navigation task in an office consisting of 80 areas. Offline experimental results show that our method can directly extract goal destination from unheard, long, and composite text commands asked by humans. This enables users to specify their destination goals for the robot in general and natural form. Hardware experiment results also show that the designed model brings much convenience for specifying a navigation goal to a service robot.

Rui Chen, Haizhou Ai, Chong Shang et al.

It remains very challenging to build a pedestrian detection system for real world applications, which demand for both accuracy and speed. This work presents a novel hierarchical knowledge distillation framework to learn a lightweight pedestrian detector, which significantly reduces the computational cost and still holds the high accuracy at the same time. Following the `teacher--student' diagram that a stronger, deeper neural network can teach a lightweight network to learn better representations, we explore multiple knowledge distillation architectures and reframe this approach as a unified, hierarchical distillation framework. In particular, the proposed distillation is performed at multiple hierarchies, multiple stages in a modern detector, which empowers the student detector to learn both low-level details and high-level abstractions simultaneously. Experiment result shows that a student model trained by our framework, with 6 times compression in number of parameters, still achieves competitive performance as the teacher model on the widely used pedestrian detection benchmark.

Xiaotong Chen, Rui Chen, Zhiqiang Sui et al.

Recent advancements have led to a proliferation of machine learning systems used to assist humans in a wide range of tasks. However, we are still far from accurate, reliable, and resource-efficient operations of these systems. For robot perception, convolutional neural networks (CNNs) for object detection and pose estimation are recently coming into widespread use. However, neural networks are known to suffer overfitting during training process and are less robust within unseen conditions, which are especially vulnerable to adversarial scenarios. In this work, we propose Generative Robust Inference and Perception (GRIP) as a two-stage object detection and pose estimation system that aims to combine relative strengths of discriminative CNNs and generative inference methods to achieve robust estimation. Our results show that a second stage of sample-based generative inference is able to recover from false object detection by CNNs, and produce robust estimations in adversarial conditions. We demonstrate the efficacy of GRIP robustness through comparison with state-of-the-art learning-based pose estimators and pick-and-place manipulation in dark and cluttered environments.

Rui Chen, Changshui Yang, Huizhu Jia et al.

In this letter, we address the problem of estimating Gaussian noise level from the trained dictionaries in update stage. We first provide rigorous statistical analysis on the eigenvalue distributions of a sample covariance matrix. Then we propose an interval-bounded estimator for noise variance in high dimensional setting. To this end, an effective estimation method for noise level is devised based on the boundness and asymptotic behavior of noise eigenvalue spectrum. The estimation performance of our method has been guaranteed both theoretically and empirically. The analysis and experiment results have demonstrated that the proposed algorithm can reliably infer true noise levels, and outperforms the relevant existing methods.

Rui Chen, Huizhu Jia, Xiange Wen et al.

Color artifacts of demosaicked images are often found at contours due to interpolation across edges and cross-channel aliasing. To tackle this problem, we propose a novel demosaicking method to reliably reconstruct color channels of a Bayer image based on two different optimized mean-curvature (MC) models. The missing pixel values in green (G) channel are first estimated by minimizing a variational MC model. The curvatures of restored G-image surface are approximated as a linear MC model which guides the initial reconstruction of red (R) and blue (B) channels. Then a refinement process is performed to interpolate accurate full-resolution R and B images. Experiments on benchmark images have testified to the superiority of the proposed method in terms of both the objective and subjective quality.

Rui Chen, Huizhu Jia, Xiaodong Xie et al.

In this letter, we propose a novel image denoising method based on correlation preserving sparse coding. Because the instable and unreliable correlations among basis set can limit the performance of the dictionary-driven denoising methods, two effective regularized strategies are employed in the coding process. Specifically, a graph-based regularizer is built for preserving the global similarity correlations, which can adaptively capture both the geometrical structures and discriminative features of textured patches. In particular, edge weights in the graph are obtained by seeking a nonnegative low-rank construction. Besides, a robust locality-constrained coding can automatically preserve not only spatial neighborhood information but also internal consistency present in noisy patches while learning overcomplete dictionary. Experimental results demonstrate that our proposed method achieves state-of-the-art denoising performance in terms of both PSNR and subjective visual quality.

Rui Chen, Huizhu Jia, Xiaodong Xie et al.

Aerial images are often degraded by space-varying motion blur and simultaneous uneven illumination. To recover high-quality aerial image from its non-uniform version, we propose a novel patch-wise restoration approach based on a key observation that the degree of blurring is inevitably affected by the illuminated conditions. A non-local Retinex model is developed to accurately estimate the reflectance component from the degraded aerial image. Thereafter the uneven illumination is corrected well. And then non-uniform coupled blurring in the enhanced reflectance image is alleviated and transformed towards uniform distribution, which will facilitate the subsequent deblurring. For constructing the multi-scale sparsified regularizer, the discrete shearlet transform is improved to better represent anisotropic image features in term of directional sensitivity and selectivity. In addition, a new adaptive variant of total generalized variation is proposed for the structure-preserving regularizer. These complementary regularizers are elegantly integrated into an objective function. The final deblurred image with uniform illumination can be extracted by applying the fast alternating direction scheme to solve the derived function. The experimental results demonstrate that our algorithm can not only remove both the space-varying illumination and motion blur in the aerial image effectively but also recover the abundant details of aerial scenes with top-level objective and subjective quality, and outperforms other state-of-the-art restoration methods.