AI 中文总结
本文提出AtlasLC，一种无源码无训练的以对象为中心的3DGS压缩管线，可减少压缩时间并优化部署相关指标，助力构建可扩展的XR资产库。
AI 中文摘要
3D高斯溅射（3DGS）支持实时渲染的照片级真实感新视图合成，但在XR中部署压缩后的以对象为中心的3DGS，仅靠图像空间率失真是不够的。在实际XR资产管线中，可重用对象会被反复打包、传输、解码和实例化，因此资产准备成本、编解码器兼容性、解码延迟以及深度和轮廓线索的保留成为首要关注点。现有的3DGS压缩方法大多针对场景级采集开发，常依赖繁重的布局生成或激进的全局剪枝，这些假设难以适配语义集中的前景对象。本文提出AtlasLC，这是一种无需原始图像、相机位姿或每个资产优化，直接在已发布的高斯资产上运行的无源码、无训练的以对象为中心的3DGS压缩管线。AtlasLC将局部竞争剪枝与确定性图集打包相结合，消除了映射/重映射瓶颈，同时保留了对象范围的前景支持；轻量级单遍排序的条件传输被用作这些阶段的共享坐标主干。在评估的资产中，AtlasLC将图集准备时间最多减少25倍，端到端压缩时间最多减少5倍，同时相对于评估的压缩基线，在有效载荷、解码延迟、运行时FPS和3D几何之间提供了有利的部署感知平衡。与类似紧凑的结构化基线相比，它使用的比特数减少了约6%至8%，同时保持了相当的感知和几何质量。这些结果表明，以对象为中心的3DGS压缩应针对部署感知的操作点进行优化，以实现可扩展的XR资产库。
英文摘要
3D Gaussian Splatting (3DGS) enables photorealistic novel-view synthesis with real-time rendering, but deploying compressed object-centric 3DGS in XR requires more than image-space rate-distortion. In practical XR asset pipelines, reusable objects are repeatedly packaged, transmitted, decoded, and instantiated, making asset-preparation cost, codec compatibility, decoding latency, and preservation of depth and silhouette cues first-class concerns. Existing 3DGS compression methods are largely developed for scene-scale captures and often rely on heavy layout generation or aggressive global pruning, assumptions that transfer poorly to semantically concentrated foreground objects. We present AtlasLC, a source-free, training-free compression pipeline for object-centric 3DGS that operates directly on released Gaussian assets, without original images, camera poses, or per-asset optimization. AtlasLC couples local-competition pruning with deterministic atlas packing to remove the mapping/remapping bottleneck while preserving object-wide foreground support; a lightweight single-pass sort-based conditional transport is used as a shared coordinate backbone for these stages. Across the evaluated assets, AtlasLC reduces atlas-preparation time by up to a factor of 25 and end-to-end compression time by up to a factor of 5, while offering a favorable deployment-aware balance of payload, decode latency, runtime FPS, and 3D geometry relative to the evaluated compressed baselines. Relative to similarly compact structured baselines, it uses about 6 to 8 percent fewer bits while maintaining comparable perceptual and geometric quality. These results show that object-centric 3DGS compression should be optimized for a deployment-aware operating point enabling scalable XR asset libraries.
CommentsAccepted to IEEE ISMAR 2026 (TVCG)
