Colored Point Cloud-based Mesh Registration for Enhancing Inter-frame Coding of Texture Video in V-DMC

The Moving Picture Experts Group (MPEG) is developing a new standard, i.e., Video-based Dynamic Mesh Coding (V-DMC), for dynamic meshes with time-varying topology. The time-varying topology and attributes challenge the V-DMC encoder in exploiting temporal correlations for redundancy minimization. Currently, the inter-frame coding in V-DMC is constrained to tracked sequences having consistent topology, with non-tracked ones predominantly using intra-coding. Texture images, as the dominant bit rate component, are inadequately compressed in Random Access (RA) mode. The precision of the mesh registration algorithm directly influences the intra-frame blocks’ proportion during the inter-frame coding of texture images, thereby affecting its coding efficiency. This paper proposed a colored point cloud-based mesh registration technique to bolster the intra-frame coding efficiency for non-tracked sequences. This method transforms the mesh into a colored point cloud and employs an inter-frame search algorithm for enhanced motion search efficiency. Local deformation near the matching point is then ascertained through directional searches at individual points. Experimental results indicate that the proposed method achieves a geometric gain of 4.1% and a texture gain of 6.47% for non-tracked sequences.

Authors

Institutions

Publication Details

Published
2025-03-12
DOI
https://doi.org/10.1109/icassp49660.2025.10890425
Citations
1
Primary Topic
3D Shape Modeling and Analysis
Type
article
Field-Weighted Citation Impact
1.33

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Colored Point Cloud-based Mesh Registration for Enhancing Inter-frame Coding of Texture Video in V-DMC

Jianxiang Sun, Fuzheng Yang, Wenjie Zou, Jiapan Zhao
1 citations
3D Shape Modeling and Analysis
1.33
article

Colored Point Cloud-based Mesh Registration for Enhancing Inter-frame Coding of Texture Video in V-DMC

Jianxiang Sun, Fuzheng Yang, Wenjie Zou, Jiapan Zhao
article en
1 citations

Abstract

The Moving Picture Experts Group (MPEG) is developing a new standard, i.e., Video-based Dynamic Mesh Coding (V-DMC), for dynamic meshes with time-varying topology. The time-varying topology and attributes challenge the V-DMC encoder in exploiting temporal correlations for redundancy minimization. Currently, the inter-frame coding in V-DMC is constrained to tracked sequences having consistent topology, with non-tracked ones predominantly using intra-coding. Texture images, as the dominant bit rate component, are inadequately compressed in Random Access (RA) mode. The precision of the mesh registration algorithm directly influences the intra-frame blocks’ proportion during the inter-frame coding of texture images, thereby affecting its coding efficiency. This paper proposed a colored point cloud-based mesh registration technique to bolster the intra-frame coding efficiency for non-tracked sequences. This method transforms the mesh into a colored point cloud and employs an inter-frame search algorithm for enhanced motion search efficiency. Local deformation near the matching point is then ascertained through directional searches at individual points. Experimental results indicate that the proposed method achieves a geometric gain of 4.1% and a texture gain of 6.47% for non-tracked sequences.

Xidian University (CN)
National Natural Science Foundation of China
Openalex Percentile: Top 26%
3D Shape Modeling and Analysis
1.33
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.