Face anti-spoofing, which aims to prevent the attacks of widely-used face recognition systems, is highly related to personal privacy and property security. However, existing benchmarks on face anti-spoofing mainly focus on RGB images, further challenged by consistently developed 3D high-fidelity (HiFi) masks. To facilitate the research on multimodal face anti-spoofing, we construct the HyperSpectral Face Anti-Spoofing (HySpeFAS) dataset. We introduce the newly-developed snapshot spectral imaging (SSI) technology to capture real and spoof faces, as well as identify unknown HiFi masks. Specifically, hyperspectral images (HSIs) acquired by SSI sensor contain rich information about the chemical composition of the targets, which can be used to effectively distinguish live human skin and various spoof materials. The HySpeFAS dataset contains 22,368 multimodal images (i.e., RGB, SSI, HSI) of 17 live subjects and 60 spoof subjects. Moreover, extensive experiments with baseline deep learning models validate the special features of the SSI images and the potential of SSI in FAS. By publishing the dataset as well as the baseline models, we encourage the community to foster the algorithm study associated with hyperspectral images and the development of SSI-equipped intelligent systems.

This paper studies point cloud perception within outdoor environments. Existing methods face limitations in recognizing objects located at a distance or occluded, due to the sparse nature of outdoor point clouds. In this work, we observe a significant mitigation of this problem by accumulating multiple temporally consecutive LiDAR sweeps, resulting in a remarkable improvement in perception accuracy. However, the computation cost also increases, hindering previous approaches from utilizing a large number of LiDAR sweeps. To tackle this challenge, we find that a considerable portion of points in the accumulated point cloud is redundant, and discarding these points has minimal impact on perception accuracy. We introduce a simple yet effective Gumbel Spatial Pruning (GSP) layer that dynamically prunes points based on a learned end-toend sampling. The GSP layer is decoupled from other network components and thus can be seamlessly integrated into existing point cloud network architectures. Extensive experiments show that our pruning strategy improves several perception algorithms in multiple tasks.

Snapshot spectral imaging technology based on the principle of compressed sensing can introduce additional spectral information and solve the problem of inadequate performance of existing optical sensors in dealing with high-fidelity masks. However, using compressed sensing for spectral image reconstruction requires a large amount of computational resources and has limited accuracy, making it the greatest obstacle for the practical application of snapshot spectral imaging technology. In this paper, we propose a new paradigm for Face Anti-Spoofing (FAS) based on snapshot spectral imaging technology. Our method does not require the reconstruction of compressive sensing spectral images, but instead directly treats the snapshot spectral imaging hardware as an optical encoder and designs the end-to-end Snapshot Spectral Imaging Network (SSINet) to decode the optical encoding results to obtain FAS results, which constitutes a software-hardware integrated FAS method. Experimental results show that our method not only surpasses previous state-of-the-art methods based on RGB images, but also performs the better than conventional spectral reconstruction methods in both efficiency and accuracy, with a nearly thousand-fold increase in FAS speed and an Average Classification Error Rate (ACER) decrease of 12.29%.