Dense 3D correspondence can enhance robotic manipulation by enabling the generalization of spatial, functional, and dynamic information from one object to an unseen counterpart. Compared to shape correspondence, semantic correspondence is more effective in generalizing across different object categories. To this end, we present DenseMatcher, a method capable of computing 3D correspondences between in-the-wild objects that share similar structures. DenseMatcher first computes vertex features by projecting multiview 2D features onto meshes and refining them with a 3D network, and subsequently finds dense correspondences with the obtained features using functional map. In addition, we craft the first 3D matching dataset that contains colored object meshes across diverse categories. We demonstrate the downstream effectiveness of DenseMatcher in (i) robotic manipulation, where it achieves cross-instance and cross-category generalization on long-horizon complex manipulation tasks from observing only one demo; (ii) zero-shot color mapping between digital assets, where appearance can be transferred between different objects with relatable geometry. More details and demonstrations can be found at https://tea-lab.github.io/DenseMatcher/.

Synthetic Aperture Radar (SAR) 3D point cloud reconstruction improves target identification by mitigating issues like overlay masking and shadows found in 2D SAR image projections. Nevertheless, challenges arise from limited SAR data availability and complexities in deciphering and labeling, hindering research in SAR 3D reconstruction point cloud semantic segmentation. To address these hurdles, we propose an alternative training approach—shifting from LiDAR to SAR point clouds. Leveraging benchmark datasets in the LiDAR domain, we advocate using LiDAR point clouds for training to counter the scarcity of SAR training sets. However, applying a segmentation model across different domains leads to a performance decline, particularly in cross-modal SAR-reconstructed point clouds, attributed to distinct roughness introduced by outliers. This paper introduces a 3D semantic segmentation framework based on unsupervised domain adaptation (UDA) for cross-modal learning from LiDAR to SAR. Additionally, we present a simple yet effective geometric transformation data augmentation technique to handle highly imbalanced data distribution. Experimental results confirm the feasibility and effectiveness of our proposed method for SAR 3D reconstructed point cloud semantic segmentation.

Synthetic aperture radar (SAR) tomography (TomoSAR) retrieves three-dimensional (3-D) information from multiple SAR images, effectively addresses the layover problem, and has become pivotal in urban mapping. Unmanned aerial vehicle (UAV) has gained popularity as a TomoSAR platform, offering distinct advantages such as the ability to achieve 3-D imaging in a single flight, cost-effectiveness, rapid deployment, and flexible trajectory planning. The evolution of compressed sensing (CS) has led to the widespread adoption of sparse reconstruction techniques in TomoSAR signal processing, with a focus on ℓ1norm regularization and other grid-based CS methods. However, the discretization of illuminated scene along elevation introduces modeling errors, resulting in reduced reconstruction accuracy, known as the “off-grid" effect. Recent advancements have introduced gridless CS algorithms to mitigate this issue. This paper presents an innovative gridless 3-D imaging framework tailored for UAV-borne TomoSAR. Capitalizing on the pulse repetition frequency (PRF) redundancy inherent in slow UAV platforms, a multiple measurement vectors (MMV) model is constructed to enhance noise immunity without compromising azimuth-range resolution. Given the sparsely placed array elements due to mounting platform constraints, an atomic norm soft thresholding algorithm is proposed for partially observed MMV, offering gridless reconstruction capability and super-resolution. An efficient alternative optimization algorithm is also employed to enhance computational efficiency. Validation of the proposed framework is achieved through computer simulations and flight experiments, affirming its efficacy in UAV-borne TomoSAR applications.

Tomographic SAR (TomoSAR) technology has gained significant attention in recent years due to its three-dimensional imaging capability. However, in practical applications, phase errors between different channels can degrade the quality of three-dimensional imaging. Current state-of-the-art methods for phase error compensation based on autofocus techniques suffer from high computational complexity, making them unsuitable for large-scale three-dimensional imaging. In this paper, we propose a multi-channel phase error estimation method based on error back-propagation training optimization. By utilizing the TomoSAR model that incorporates phase errors from multiple channels, we construct a matrix containing the parameters to be estimated for inter-channel phase errors. Through stochastic gradient descent algorithm, we iteratively optimize the parameters of the phase error matrix, ultimately obtaining an estimation of the inter-channel phase errors. Experimental results validate the accuracy of the proposed method.

Tomographic SAR technique has attracted remarkable interest for its ability of three-dimensional resolving along the elevation direction via a stack of SAR images collected from different cross-track angles. The emerged compressed sensing (CS)-based algorithms have been introduced into TomoSAR considering its super-resolution ability with limited samples. However, the conventional CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity, and complex parameter fine-tuning. Aiming at efficient TomoSAR imaging, this paper proposes a novel and efficient sparse unfolding network based on the analytic learned iterative shrinkage thresholding algorithm (ALISTA) architecture with adaptive threshold, named Adaptive Threshold ALISTA-based Sparse Imaging Network (ATASI-Net). The weight matrix in each layer of ATASI-Net is pre-calculated as the solution of an off-line optimization problem, leaving only two scalar parameters to be learned from data, which significantly simplifies the training stage. Furthermore, the introduction of an adaptive threshold for each azimuth-range pixel permits the threshold shrinkage to be not only layer-varied but also element-wise. Additionally, the final learned thresholds can be visualized and combined with the SAR image semantics for mutual feedback. Finally, extensive experiments on simulated and real data are carried out to demonstrate the effectiveness and efficiency of the proposed method.

Traditional web services transaction processing mechanism handle exception by forward recovery and backward recovery. These compensation mechanisms often lead to waste of resources and time. In this paper, we propose a framework for predicting outcomes of service executions as part of service compositions which allows to choose service instances that are likely to lead to a successful result in the first instance and thus reduces the need for invoking costly recovery mechanisms. The framework makes use of watchdogs to maintain an awareness of service availability and a pre-coordinator which has oversight of the whole composite Web service and acts as a control center. An analysis of a scenario shows that we cannot only provide users with a more satisfactory result, but also can reduce the overhead costs of resources and waste.