Tai Qin

2 accepted papers

2026

DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression

Chunyang Fu, Tai Qin, Shiqi Wang, Zhu Li

AAAI 2026technical

Regional Adaptive Hierarchical Transform (RAHT) is an effective point cloud attribute compression (PCAC) method. However, its application in deep learning lacks research. In this paper, we propose an end-to-end RAHT framework for lossy PCAC based on the sparse tensor, called DeepRAHT. The RAHT trans

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Multi-Descriptor Mesh Animation Compression

Tai Qin, Chunyang Fu, Ge Li, Shan Liu

ICASSP 2025accepted

For mesh animation sequences with consistent topology, traditional compression methods are well established, but deep learning approaches are emerging. This paper presents a novel deep learning framework for vertex position reconstruction by encoding displacements. We propose LoD-Uniform Partitionin…

Cited by 0 Source ↗Scholar ↗