With the prevalence of depth sensors and 3D scanning de- vices, point clouds have attracted increasing attention as a format for 3D object representation, with applications in var- ious fields such as tele-presence, navigation for autonomous driving and heritage reconstruction. However, point clouds usually exhibit holes of missing data, mainly due to the lim- itation of acquisition techniques and complicated structure. Hence, we propose an efficient inpainting method for the at- tribute (e.g., color) of point clouds, exploiting non-local self- similarity in graph spectral domain. Specifically, we represent irregular point clouds naturally on graphs, and split a point cloud into fixed-sized cubes as the processing unit. We then globally search for the most similar cubes to the target cube with holes inside, and compute the graph Fourier transform (GFT) basis from the similar cubes, which will be leveraged for the GFT representation of the target patch. We then for- mulate attribute inpainting as a sparse coding problem, im- posing sparsity on the GFT representation of the attribute for hole filling. Experimental results demonstrate the superiority of our method.

Face anti-spoofing plays a crucial role in protecting face recognition systems from various attacks. Previous modelbased and deep learning approaches achieve satisfactory performance for 2D face spoofs, but remain limited for more advanced 3D attacks such as vivid masks. In this paper, we address 3D face anti-spoofing via the proposed Hypergraph Convolutional Neural Networks (HGCNN). Firstly, we construct a computation-efficient and posture-invariant face representation with only a few key points on hypergraphs. The hypergraph representation is then fed into the designed HGCNN with hypergraph convolution for feature extraction, while the depth auxiliary is also exploited for 3D mask anti-spoofing. Further, we build a 3D face attack database with color, depth and infrared light information to overcome the deficiency of 3D face anti-spoofing data. Experiments show that our method achieves the state-of-theart performance over widely used 3D and 2D databases as well as the proposed one under various tests.