Abstract An ultralightweight self-supervised stereo matching network, called US $$^3$$ 3 Net, which requires only 12K parameters, is designed for efficient and accurate depth estimation using resource-constrained devices. US $$^3$$ 3 Net incorporates two key innovations: a low-complexity feature extraction module and a soft occlusion detection approach for performance improvement. First, we design a low-complexity feature extraction module to reduce the computational burden while preserving structural details necessary for stereo matching. By refining the encoder backbone and aggregation module, our design ensures a better balance between model complexity and accuracy. Second, to address occlusion-related errors in disparity estimation, we propose a novel occlusion detection method, called Depth-Aware Geometric Soft Occlusion (DAGSO), to adaptively define the occlusion confidence scores based on depth information. DAGSO can effectively mitigate false occlusions in distant regions and can improve the accuracy of disparity estimation. Experimental results using KITTI datasets demonstrate that US $$^3$$ 3 Net achieves state-of-the-art performance in terms of model complexity and depth estimation accuracy. It outperforms previous self-supervised stereo matching methods and monocular depth estimation methods in metrics such as AbsRel, SqRel, RMSE, and RMSElog at a reduction of parameter size by 47% compared with ES $$^3$$ 3 Net (23K). This makes US $$^3$$ 3 Net a practical solution for real-time depth estimation on edge devices such as drones and autonomous systems. Code is available at: https://github.com/g830319ag/US3Net.

Traditional visible light cameras are prone to performance degradation under varying weather and lighting conditions. To address this challenge, we introduce an eventbased camera and propose a novel hierarchical spatiotemporal fusion approach for event-visible object detection. Our method enhances detection performance by integrating data from both event-based and visible light cameras. We have designed three key modules: The Gated Event Accumulation Representation module (GEAR), the Temporal Feature Selection module (TFS), and the Adaptive Fusion module (AF). GEAR and TFS enhance temporal feature fusion at both image and feature levels, while AF effectively integrates multi-modal features with low computational complexity. Our approach has been trained and validated on the publicly available DSEC-Detection dataset, achieving mAP50 and mAP50-95 scores of 67.2% and 45.6%, respectively, demonstrating superior detection performance and validating the effectiveness of the proposed method.

Blind source separation (BSS) has been widely utilized for recovering a set of source signals from their mixtures. When the mixture is convolutive, source separation can be solved in the frequency domain but involves several challenges including the scaling uncertainty and the permutation indeterminacy. This paper presents a sliding k-means algorithm to handle the permutation problem. Experiments were conducted by playing the source files to a pair of loudspeakers and obtaining the mixture by microphones. Objective indices are then defined to evaluate the separation performance based on the actual frequency responses. Results have shown that the standard k-means method alone can consistently achieve > 90.5% permutation accuracy in different parameter settings. After introducing the proposed sliding process, the permutation accuracy further rises. Compared to a previous de-permutation method [1], the present method has a more stable performance against parameter variations in terms of its permutation accuracy and signal-to-interference ratio (SIR).