主讲题目：Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression

主讲人：Zhan Ma

时间：2024年3月6日上午9:30

地点：勤园11-525

摘要：Due to their outstanding flexibility for representing 3D objects realistically and naturally, point clouds have become a popular media format used in a large number of applications, such as the Augmented/Virtual Reality (AR/VR), autonomous driving, and cultural e-heritage. This then

raises an urgent need for high-efficiency lossless and lossy compression of point clouds. This study develops a unified Point Cloud Geometry (PCG) compression method through the processing of multiscale sparse tensor-based voxelized PCG. We call this compression method SparsePCGC. The proposed SparsePCGC is a low complexity solution because it only performs the convolutions on sparsely-distributed Most-Probable Positively-Occupied Voxels (MP-POV). The multiscale representation also allows us to compress scale-wise MP-POVs by exploiting cross-scale and same-scale correlations extensively and flexibly. The overall compression efficiency highly depends on the accuracy of estimated occupancy probability for each MP-POV. Thus, we first design the Sparse Convolution-based Neural Network (SparseCNN) which stacks sparse convolutions and voxel sampling to best characterize and embed spatial correlations. We then develop the SparseCNN-based Occupancy Probability Approximation (SOPA) model to estimate the occupancy probability either in a single-stage manner only using the cross-scale correlation, or in a multi-stage manner by exploiting stage-wise correlation among same-scale neighbors. Besides, we also suggest the SparseCNN based Local Neighborhood Embedding (SLNE) to aggregate local variations as spatial priors in feature attribute to improve the SOPA. Our unified approach not only shows state-of-the-art performance in both lossless and lossy compression modes across a variety of datasets but also has low complexity which is attractive to practical applications.

个人简介：Zhan~Ma is a Full Professor in the School of Electronic Science and Engineering, Nanjing University, Jiangsu, 210093, China. He received his Ph.D. from New York University, New York, in 2011, and his B.S. and M.S. from the Huazhong University of Science and Technology, Wuhan, China, in 2004 and 2006 respectively. From 2011 to 2014, he has been with Samsung Research America, Dallas, TX, and Futurewei Technologies, Inc., Santa Clara, CA, respectively. His research focuses include learned image/video coding and computational imaging. He is a co-recipient of multiple awards including the 2019 IEEE Broadcast Technology Society Best Paper Award, the 2020 IEEE MMSP Grand Challenge Best Image Coding Solution, and the 2023 IEEE WACV Best Algorithms Paper Award.