Ru-Ling Liao

SACHA: Semantic-Aware Compression for 3D Gaussian Head Avatars

Zihan Zhang, Shanzhi Yin, Xinju Wu, Bolin Chen et autres

Animatable 3D Gaussian head avatars offer high-fidelity and flexible facial rendering, but typically require substantial storage and transmission costs for numerous Gaussian primitives. Existing Gaussian head avatar methods overlook the visual saliency of different head semantic regions for more appropriate Gaussian primitive …

Compressing Feed-Forward 3D Gaussian Splatting via Feature Sorting

X. Ju, Shanzhi Yin, Xinju Wu, Bolin Chen et autres

hk, us (code pays fourni par la source)

Sparse2Dense: A Keypoint-Driven Generative Framework for Human Video Compression and Vertex Prediction

Bolin Chen, Ru-Ling Liao, Yan Ye, Jie Chen et autres

For bandwidth-constrained multimedia applications, simultaneously achieving ultra-low bitrate human video compression and accurate vertex prediction remains a critical challenge, as it demands the harmonization of dynamic motion modeling, detailed appearance synthesis, and geometric consistency. To address this challenge, we propose Sparse2Dense, a …

cn, ky, hk (code pays fourni par la source)

Towards Efficient 3D Gaussian Human Avatar Compression: A Prior-Guided Framework

Shanzhi Yin, Bolin Chen, Xiaoqing Wu, Ru-Ling Liao et autres

This paper proposes an efficient 3D avatar coding framework that leverages compact human priors and canonical-to-target transformation to enable high-quality 3D human avatar video compression at ultra-low bit rates. The framework begins by training a canonical Gaussian avatar using articulated splatting in …

hk, ky (code pays fourni par la source)

Adaptive Enhanced Affine Inter Mode for the Next Generation of AVS Standard

Yucheng Zhong, Hongbo Li, Zhu J, Wanglin Lai et autres

To meet the growing demand for advanced video coding, the Joint Video Experts Team (JVET) launched the Enhanced Compression Model (ECM) in April 2021 to explore technologies beyond Versatile Video Coding (VVC). Following this trend, the Audio Video Coding Standard (AVS) Working …

cn, ky (code pays fourni par la source)

Affine with Symmetric Motion Vector Difference Mode

Chen Li, Ru-Ling Liao, Jie Chen, Yan Ye et autres

The Versatile Video Coding (VVC) standard incorporates affine motion compensation to represent complex motions including rotation and zoom. However, affine advanced motion vector prediction (AMVP) mode incurs significant signaling overhead, particularly in biprediction where motion vector differences (MVDs) must be signaled for …

cn, ky (code pays fourni par la source)

Improvements on Template Matching Merge Mode for the Next Generation of AVS

Hongbo Li, Yucheng Zhong, Zhu J, Wanglin Lai et autres

In search for more efficient video compression capability than versatile video coding (VVC), joint video experts team (JVET) launched exploration work on new video coding technologies beyond VVC in 2021. In 2023, audio video coding standard (AVS) workgroup started to explore the …

cn, ky (code pays fourni par la source)

A Dual Merge Mode for Video Coding

Chen Li, Ru-Ling Liao, Jie Chen, X.C. Li et autres

In the latest international video coding standard, Versatile Video Coding, merge mode utilizes spatial or temporal adjacent motion information as motion vector predictors to reduce the signaling overhead. However, only one merge candidate's motion information is selected from previously coded blocks for …

cn, ky (code pays fourni par la source)

Angular Weighted Prediction Mode Improvements Beyond AVS3 Standard

Zhu J, Wanglin Lai, Hui Li, Yucheng Zhong et autres

Audio video coding standard (AVS) workgroup started to explore the latest video coding technologies beyond AVS3 standard and released a software platform named exploration video model (EVM) in March 2023. In EVM-0.7, the construction of the motion vector (MV) candidate list for …

cn, ky (code pays fourni par la source)

Standardizing Generative Face Video Compression Using Supplemental Enhancement Information

Bolin Chen, Yan Ye, Jie Chen, Ru-Ling Liao et autres

This paper proposes a Generative Face Video Compression (GFVC) approach using Supplemental Enhancement Information (SEI), where a series of compact spatial and temporal representations of a face video signal (e.g., 2D/3D key-points, facial semantics and compact features) can be coded using SEI …

us, hk, cn, nl (code pays fourni par la source)

Rethinking Generative Human Video Coding with Implicit Motion Transformation

Bolin Chen, Ru-Ling Liao, Jie Chen, Yan Ye

ky (code pays fourni par la source)

Affine Motion Refinement for the Next Generation of AVS Standard

Yucheng Zhong, Hui Li, Jiabao Zhu, Wanglin Lai et autres

cn, ky (code pays fourni par la source)