Mirror Therapy (MT) effectively supports post-stroke upper-limb rehabilitation but requires professional supervision and often leads to low patient motivation. While digital MT systems address these limitations, they typically compromise the embodiment benefits of traditional mirrors. Through informant-driven design with interdisciplinary experts, we developed A-MIrror, an augmented reality mirror system that preserves the view of both mirrored hand and overlays digital guidance. Using dual cameras for eye and hand tracking, the system creates a visual illusion where both real and mirrored hands appear to naturally interact with virtual 3D objects on screen. Our evaluation with 14 post-stroke patients and 8 therapists demonstrates that A-MIrror significantly enhances motivation compared to traditional MT (p <.01) while achieving comparable embodiment experiences and even superior illusion latency (30.47% faster, p <.001) to traditional mirrors. This study presents a promising approach for independent post-stroke rehabilitation that integrates the strengths of both traditional and digital MT, offering insights for enhancing future digital rehabilitation applications.

In this paper, we focus on exploring the robustness of the 3D object detection in point clouds, which has been rarely discussed in existing approaches. We observe two crucial phenomena: 1) the detection accuracy of the hard objects, e.g., Pedestrians, is unsatisfactory, 2) when adding additional noise points, the performance of existing approaches decreases rapidly. To alleviate these problems, a novel TANet is introduced in this paper, which mainly contains a Triple Attention (TA) module, and a Coarse-to-Fine Regression (CFR) module. By considering the channel-wise, point-wise and voxel-wise attention jointly, the TA module enhances the crucial information of the target while suppresses the unstable cloud points. Besides, the novel stacked TA further exploits the multi-level feature attention. In addition, the CFR module boosts the accuracy of localization without excessive computation cost. Experimental results on the validation set of KITTI dataset demonstrate that, in the challenging noisy cases, i.e., adding additional random noisy points around each object, the presented approach goes far beyond state-of-the-art approaches. Furthermore, for the 3D object detection task of the KITTI benchmark, our approach ranks the first place on Pedestrian class, by using the point clouds as the only input. The running speed is around 29 frames per second.

3D object detection plays an important role in a large number of real-world applications. It requires us to estimate the localizations and the orientations of 3D objects in real scenes. In this paper, we present a new network architecture which focuses on utilizing the front view images and frustum point clouds to generate 3D detection results. On the one hand, a PointSIFT module is utilized to improve the performance of 3D segmentation. It can capture the information from different orientations in space and the robustness to different scale shapes. On the other hand, our network obtains the useful features and suppresses the features with less information by a SENet module. This module reweights channel features and estimates the 3D bounding boxes more effectively. Our method is evaluated on both KITTI dataset for outdoor scenes and SUN-RGBD dataset for indoor scenes. The experimental results illustrate that our method achieves better performance than the state-of-the-art methods especially when point clouds are highly sparse.