Images captured in snowy days suffer from noticeable degradation of scene visibility, which degenerates the performance of current vision-based intelligent systems. Removing snow from images thus is an important topic in computer vision. In this paper, we propose a Deep Dense Multi-Scale Network (DDMSNet) for snow removal by exploiting semantic and depth priors. As images captured in outdoor often share similar scenes and their visibility varies with depth from camera, such semantic and depth information provides a strong prior for snowy image restoration. We incorporate the semantic and depth maps as input and learn the semantic-aware and geometry-aware representation to remove snow. In particular, we first create a coarse network to remove snow from the input images. Then, the coarsely desnowed images are fed into another network to obtain the semantic and depth labels. Finally, we design a DDMSNet to learn semantic-aware and geometry-aware representation via a self-attention mechanism to produce the final clean images. Experiments evaluated on public synthetic and real-world snowy images verify the superiority of the proposed method, offering better results both quantitatively and qualitatively. https://github.com/HDCVLab/Deep-Dense-Multi-scale-Network https://github.com/HDCVLab/Deep-Dense-Multi-scale-Network .

In this paper, we explore the problem of deep multi-view subspace clustering framework from an information-theoretic point of view. We extend the traditional information bottleneck principle to learn common information among different views in a self-supervised manner, and accordingly establish a new framework called Self-supervised Information Bottleneck based Multi-view Subspace Clustering (SIB-MSC). Inheriting the advantages from information bottleneck, SIB-MSC can learn a latent space for each view to capture common information among the latent representations of different views by removing superfluous information from the view itself while retaining sufficient information for the latent representations of other views. Actually, the latent representation of each view provides a kind of self-supervised signal for training the latent representations of other views. Moreover, SIB-MSC attempts to disengage the other latent space for each view to capture the view-specific information by introducing mutual information based regularization terms, so as to further improve the performance of multi-view subspace clustering. Extensive experiments on real-world multi-view data demonstrate that our method achieves superior performance over the related state-of-the-art methods.

To possess sufficient compliance while keeping an acceptable stiffness level for manipulation with precision, transoral robotic surgery (TORS) demands a flexible robotic system with variable stiffness as presented in this paper. In our study, a flexible 3-PU parallel mechanism employs super-elastic Nickel-Titanium (Ni-Ti) rods to achieve compliant movements beyond the conventional rigid-body parallel mechanisms. With a compact structure and flexible-shaft transmission, the adjustable tube-based variable-stiffness (VS) mechanism allows the stiffness of the manipulator to be continuously tuned in real time according to the surgical requirements. A stiffness model is derived to evaluate the stiffness of the manipulator quantitatively. A parallel mechanism with three prismatic-revolute-spherical (3-PRS) chains is adopted as the master device, to improve the maneuverability and decrease the learning curve for less experienced surgeons. The TORS manipulators are characterized and verified in the laboratory and cadaveric trials, showing the variable stiffness and the execution of the master-slave teleoperated configuration. Furthermore, the cadaveric trials attested the effectiveness of the VS mechanism and the preclinical feasibility of the robotic system.

This paper presents an unsupervised learning approach for simultaneous sample and feature selection, which is in contrast to existing works which mainly tackle these two problems separately. In fact the two tasks are often interleaved with each other: noisy and high-dimensional features will bring adverse effect on sample selection, while informative or representative samples will be beneficial to feature selection. Specifically, we propose a framework to jointly conduct active learning and feature selection based on the CUR matrix decomposition. From the data reconstruction perspective, both the selected samples and features can best approximate the original dataset respectively, such that the selected samples characterized by the features are highly representative. In particular, our method runs in one-shot without the procedure of iterative sample selection for progressive labeling. Thus, our model is especially suitable when there are few labeled samples or even in the absence of supervision, which is a particular challenge for existing methods. As the joint learning problem is NP-hard, the proposed formulation involves a convex but non-smooth optimization problem. We solve it efficiently by an iterative algorithm, and prove its global convergence. Experimental results on publicly available datasets corroborate the efficacy of our method compared with the state-of-the-art.

This paper presents a multi-channel SPAS robotic system consisting of two channels of flexible manipulators and an endoscope channel. Each channel of the manipulators is designed based on a parallel mechanism with three sets of super-elastic Ni-Ti rods and universal joints. This design optimizes the structure for flexibility and safety considerations with a simplified structure compared with conventional parallel mechanisms. Flexible shafts are used for torque transmission, allowing the motors to be farther away from the robotic system. The kinematics of the manipulator is derived, and the reachable workspace and dexterity are analyzed. Furthermore, a prototype of the proposed robotic system is presented. The flexibility of the manipulator is verified via stiffness characterization test. The results of the accuracy tests confirmed that the robotic system can implement manipulation arm with acceptable accuracy. The feasibility and effectiveness of applying the robotic system to the practical operation are also demonstrated through experimentations.