Výsledky vyhledávání - "Mao, Xiaolong"

Report

SPAC: Sampling-based Progressive Attribute Compression for Dense Point Clouds

Autor: Mao, Xiaolong, Yuan, Hui, Guo, Tian, Jiang, Shiqi, Hamzaoui, Raouf, Kwong, Sam

We propose an end-to-end attribute compression method for dense point clouds. The proposed method combines a frequency sampling module, an adaptive scale feature extraction module with geometry assistance, and a global hyperprior entropy model. The f

Externí odkaz: http://arxiv.org/abs/2409.10293

Zobrazit plný text záznamu

Report

Enhancing octree-based context models for point cloud geometry compression with attention-based child node number prediction

Autor: Sun, Chang, Yuan, Hui, Mao, Xiaolong, Lu, Xin, Hamzaoui, Raouf

Publikováno v: IEEE Signal Processing Letters, 2024

In point cloud geometry compression, most octreebased context models use the cross-entropy between the onehot encoding of node occupancy and the probability distribution predicted by the context model as the loss. This approach converts the problem o

Externí odkaz: http://arxiv.org/abs/2407.08528

Zobrazit plný text záznamu

Report

PCAC-GAN: A Sparse-Tensor-Based Generative Adversarial Network for 3D Point Cloud Attribute Compression

Autor: Mao, Xiaolong, Yuan, Hui, Lu, Xin, Hamzaoui, Raouf, Gao, Wei

Publikováno v: Computational Visual Media, 2024

Learning-based methods have proven successful in compressing geometric information for point clouds. For attribute compression, however, they still lag behind non-learning-based methods such as the MPEG G-PCC standard. To bridge this gap, we propose

Externí odkaz: http://arxiv.org/abs/2407.05677

Zobrazit plný text záznamu