Blind image deblurring is a long standing challenging problem in image processing and low-level vision. Recently, sophisticated priors such as dark channel prior, extreme channel prior, and local maximum gradient prior, have shown promising effectiveness. However, these methods are computationally expensive. Meanwhile, since these priors involved subproblems cannot be solved explicitly, approximate solution is commonly used, which limits the best exploitation of their capability. To address these problems, this work firstly proposes a simplified sparsity prior of local minimal pixels, namely patch-wise minimal pixels (PMP). The PMP of clear images is much more sparse than that of blurred ones, and hence is very effective in discriminating between clear and blurred images. Then, a novel algorithm is designed to efficiently exploit the sparsity of PMP in deblurring. The new algorithm flexibly imposes sparsity inducing on the PMP under the maximum a posterior (MAP) framework rather than directly uses the half quadratic splitting algorithm. By this, it avoids non-rigorous approximation solution in existing algorithms, while being much more computationally efficient. Extensive experiments demonstrate that the proposed algorithm can achieve better practical stability compared with state-of-the-arts. In terms of deblurring quality, robustness and computational efficiency, the new algorithm is superior to state-of-the-arts. Code for reproducing the results of the new method is available at https://github.com/FWen/deblur-pmp.git.

Consistent and accurate global positioning is a crucial problem for autonomous vehicles and robots. It is especially challenging in situations with global navigation satellite system (GNSS) being intermittently degraded. We propose an adaptive fusion system, namely GVINS (GNSS/visual-inertial navigation system), which adaptively fuses GNSS and visual-inertial odometry (VIO) to achieve consistent and accurate global positioning, even in GNSS intermittently degraded scenarios. Compared with existing methods, GVINS can provide positioning under an Earth-fixed geographic coordinate rather than a local tangent plane (LTP) coordinate, as long as any GNSS measurement presents in the trajectory. To adaptively fuse VIO and GNSS, we first use an inertial measurement unit (IMU) pre-integration based depth uncertainty estimation method to evaluate the accuracy of VIO. Then, in the optimization backend, we perform an innovative over-parameterized, 15 degree-of-freedom (DoF) pose-graph fusion. An alternating minimization (AM) algorithm is used to efficiently solve this problem. Evaluation results on both public and custom-built datasets demonstrate that, GVINS outperforms state-of-the-art fusion methods in both accuracy and stability in GNSS intermittently degraded environments.

Recently, the robustification of principal component analysis (PCA) has attracted much research attention in numerous areas of science and engineering. The most popular and successful approach is to model the robust PCA problem as a low-rank matrix recovery problem in the presence of sparse corruption. With this model, the nuclear norm and l1-norm penalties are usually used for low-rank and sparsity promotion. Although the nuclear norm and l1-norm are favorable due to their convexity, they have a bias problem. In comparison, nonconvex penalties can be expected to yield better recovery performance. In this work, we consider a formulation for robust PCA using generalized nonconvex penalties for low-rank and sparsity inducing. This nonconvex formulation is efficiently solved by a multi-block alternative direction method of multipliers (ADMM) algorithm. A sufficient condition for the convergence of this new ADMM algorithm has been derived. Furthermore, to address the important issue of nonconvex penalty selection, we have evaluated the new algorithm via numerical experiments in various low-rank and sparsity conditions. The results indicate that“, exact” recovery of the low-rank principle component can be achieved only by nonconvex regularization. Matlab code is available at https://github.com/FWen/RPCA.git.

Vision navigation technique, especially the visionbased simultaneous localization and mapping (V-SLAM), plays a critical role in robotic navigation. As a relative positioning technique, V-SLAM often suffers from drift and scale uncertainty problems which incur bias increasing over time. To overcome these drawbacks and to improve the robustness and accuracy of localization, an effective way is to fuse global navigation satellite system (GNSS) with V-SLAM. In this paper, we propose a novel GNSS and SLAM fusion algorithm, which provides egomotion estimation through tightly coupling GNSS pseudo-range measurements and camera feature points. It first decomposes the pose state into basic motion vectors, based on which an asynchronous tracking is performed. Then, a 10-DoF jointoptimization formulation on manifold is proposed to achieve tight fusion of the raw measurement from camera and GNSS. Finally, this formulation is solved to calculate the ego-motion state. The proposed algorithm is verified on an autonomous ground vehicle in two typical environments. The results demonstrated that, the new algorithm can amend the bias in vision SLAM and constrain the GNSS solution, which achieves a better localization result than the traditional methods.

Local features contain crucial clues for face anti-spoofing. Convolutional neural networks (CNNs) are powerful in extracting local features, but the intrinsic inductive bias of CNNs limits the ability to capture long-range dependencies. This paper aims to develop a simple yet effective framework that is versatile in extracting both local information and long-range dependencies for face anti-spoofing. To this end, we propose a novel architecture, namely Conv-MLP, which incorporates local patch convolution with global multi-layer perceptrons (MLP). Conv-MLP breaks the inductive bias limitation of traditional full CNNs and can be expected to better exploit long-range dependencies. Furthermore, we design a new loss specifically for the face anti-spoofing task, namely moat loss. The moat loss benefits discriminative representations learning and can improve the generalization capability on unseen presentation attacks. In this work, multi-modal data are directly fused at the signal level to extract complementary features. Extensive experiments on single and multi-modal datasets demonstrate that Conv-MLP outperforms existing state-of-the-art methods while being more computationally efficient. The code is available at https://github.com/WeihangWANG/Conv-MLP .

Providing an accurate trajectory in an underwater scene is challenging for visual odometry due to weak texture and varying illumination. In this article, we propose a novel underwater visual-inertial odometry (VIO) with the unifying direct method and feature-based method. Our approach starts with a new rectification method for underwater images. The new underwater image rectification method separately eliminates water-air refraction distortion and lens distortion with an approximate single viewpoint (SVP) camera model. Meanwhile, a unified optimization method is used in our approach to obtain robust and highly accurate odometry results. This method jointly optimizes projection errors and photometric errors. Moreover, the robust data association processing, which combines keyframe / keypoint selection, keypoint position prediction, and robust local optical flow, was designed in our approach. The robust data association processing greatly improves the success rate of keypoints tracking. To evaluate the precision of underwater visual odometry, an underwater dataset with complete and highly accurate ground truth trajectories is provided in this work. The performance of our system is compared with other state-of-the-art algorithms on multiple datasets, including visual odometry datasets and our proposed underwater dataset. The evaluation results show that the proposed system can achieve better results than the state-of-the-art algorithms. Furthermore, the proposed system is validated on public natural underwater datasets to show the performance of the system in a real underwater environment. The qualitative results demonstrate that the proposed system can work well in the natural underwater environment.