AI 中文总结
提出ControlGS，一种面向XR的神经高斯渲染流程，将渲染输出与人眼间的下游处理（如后处理和显示光学）建模并整合进优化目标，并根据下游参数动态生成高斯图元，以提升端到端视觉质量，实验验证其在不同骨干和数据集上持续改善且开销极小。
AI 中文摘要
扩展现实（XR）用户并不直接感知渲染引擎的输出。相反，渲染图像在到达人眼之前，会经过后处理流程和物理显示光学路径。关键的是，确切的下游处理在运行时可能会有显著变化，例如受相机姿态和显示功率预算的影响。传统的3DGS方法要么隐式假设该下游流程能保持图像质量，要么无法适应下游处理的变化。为弥合这一差距，我们提出了ControlGS，一个优化端到端视觉质量的XR高斯渲染流程。ControlGS将渲染输出与人眼之间的整个下游处理建模并整合到优化目标中。为了在运行时适应下游处理，ControlGS根据下游处理参数动态生成高斯图元。实验表明，ControlGS在不同神经高斯骨干和数据集上持续改善端到端的光学后XR质量，且开销极小。代码可在以下网址获取：此https URL。
英文摘要
Extended Reality (XR) users do not directly perceive the output of a rendering engine. Instead, rendered images pass through a post-processing pipeline and the physical display-optics path before reaching the eye. Critically, the exact downstream processing can vary significantly at run time, influenced by, for instance, camera pose and display power budget. Traditional 3DGS methods either implicitly assume that this downstream pipeline preserves image quality or cannot adapt to downstream processing changes. To bridge this gap, we present ControlGS, an XR Gaussian rendering pipeline that optimizes end-to-end visual quality. ControlGS models and integrates the entire downstream processing, between the rendering output and the human eye, into the optimization objective. To adapt to downstream processing at run time, ControlGS dynamically generates Gaussian primitives conditioned upon the downstream processing parameters. Experiments show that ControlGS consistently improves end-to-end post-optics XR quality across different neural Gaussian backbones and datasets, with minimal overhead. Code is available at https://horizon-lab.org/controlgs/.
CommentsAccepted to Siggraph Asia'26, 36 pages, poject page: https://horizon-lab.org/controlgs/
