Scholarlink

<p>This paper presents a novel real-time live compression scheme for 3D animated meshes in the context of client-GPU cloud gaming. We specialize in compressing character models animated with linear blend skinning (LBS) with rigid bones, using skinning decomposition to approximate skinning weights and bone transformations as closely as possible to the originals. Our technique leverages the <i>Dem&#xa0;Bones</i> library and proposes adjustments to handle common industrial constraints, such as low bone count decomposition of multicomponent meshes and reconstruction of uniformly scaled mesh poses. We demonstrate the efficiency of our real-time compression technique on meshes with up to 25,000 vertices and 200 bones, achieving compression rates that significantly reduce bandwidth usage while maintaining visually acceptable distortion levels (KGE <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="371_2025_4112_Article_IEq1.gif" Format="GIF" Height="15" Rendition="HTML" Resolution="72" Type="Linedraw" Width="19" /> </InlineMediaObject> <EquationSource Format="TEX">\(\le \)</EquationSource> <EquationSource Format="MATHML"><math> <mo>≤</mo> </math></EquationSource> </InlineEquation> 5%). Here, we show that our approach can effectively address edge cases encountered in video games, thanks to our optimizations and adjustments. Our work contributes to advancing the state of the art in graphics streaming for cloud gaming applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Real-time live compression of dynamic 3D meshes for client-side GPU cloud gaming using skinning decomposition

  • 期刊论文

  • 发表日期：

    2025年8月4日

查看全文
  • Mathieu Pietri,
  • Eric Remy,
  • Vincent Penné,
  • Jean-Luc Mari

摘要

This paper presents a novel real-time live compression scheme for 3D animated meshes in the context of client-GPU cloud gaming. We specialize in compressing character models animated with linear blend skinning (LBS) with rigid bones, using skinning decomposition to approximate skinning weights and bone transformations as closely as possible to the originals. Our technique leverages the Dem Bones library and proposes adjustments to handle common industrial constraints, such as low bone count decomposition of multicomponent meshes and reconstruction of uniformly scaled mesh poses. We demonstrate the efficiency of our real-time compression technique on meshes with up to 25,000 vertices and 200 bones, achieving compression rates that significantly reduce bandwidth usage while maintaining visually acceptable distortion levels (KGE \(\le \) ≤ 5%). Here, we show that our approach can effectively address edge cases encountered in video games, thanks to our optimizations and adjustments. Our work contributes to advancing the state of the art in graphics streaming for cloud gaming applications.