arXiv 2606.293292026-06-28cs.CV

RAGA：面向3DGS化身-场景交互的实时光线追踪高斯阴影投射

RAGA: Real Time Ray Traced Gaussian Shadow Casting for 3DGS Avatar-Scene Interaction

Tübingen AI Center, University of Tübingen, Germany（图宾根人工智能中心，图宾根大学，德国）；Max Planck Institute for Informatics, Saarland Informatics Campus, Germany（马克斯·普朗克研究所信息学院，萨尔兰信息学院，德国）；Imperial College London, UK（伦敦帝国理工学院，英国）；King Abdullah University of Science and Technology (KAUST), Saudi Arabia（国王阿卜杜勒阿齐兹科技大学（KAUST），沙特阿拉伯）；Snap Inc., USA（Snap公司，美国）

Aymen Mir, Riza Alp Guler, Jian Wang, Peter Wonka, Bing Zhou, Gerard Pons-Moll

备注：: ECCV 2026. Project Page at https://miraymen.github.io/raga/

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出RAGA方法，通过精确的射线-高斯线积分在纯高斯空间中实现阴影计算，无需网格重建，支持单/多化身及物体交互场景，达到约50 FPS的实时性能。

摘要：

我们研究了在现有3DGS场景中动画化3D高斯泼溅（3DGS）化身时，实现物理上合理的阴影投射问题，包括单化身、多化身以及物体交互场景。与先前依赖二元命中测试和基于网格的阴影投射器的方法不同，我们的方法完全在高斯空间中进行阴影计算，无需任何网格重建。我们引入了RAGA，一种基于精确射线-高斯线积分的射线追踪高斯阴影投射公式。对于每个遮挡高斯体，我们沿阴影射线积分不透明度轮廓，并通过理论最大积分进行归一化，产生一个权重，该权重捕捉射线如何穿过遮挡物，而不仅仅是是否发生相交。为了减少动画化身中衣物变形引起的时间方差，我们进一步引入了一种化身代理表示，在保持视觉保真度的同时稳定阴影投射。我们使用与NVIDIA OptiX框架集成的自定义CUDA内核实现RAGA；因此，我们的阴影追踪器以约50 FPS的速率运行。我们在多个数据集上评估了单化身、多化身和化身-物体交互场景，展示了显著改善的阴影真实感、时间稳定性和场景一致性。我们的项目页面位于https://miraymen.github.io/raga/。

英文摘要：

We study the problem of physically plausible shadow casting when animating 3D Gaussian Splatting (3DGS) avatars, either individually or in multi-avatar and object-interaction scenarios, within existing 3DGS scenes. In contrast to prior methods that rely on binary hit tests and mesh-based shadow casters, our method performs shadow computation entirely in Gaussian space, without requiring any mesh reconstruction. We introduce RAGA, a Ray-Traced Gaussian Shadow Casting formulation based on exact ray-Gaussian line integrals. For each occluding Gaussian, we integrate the opacity profile along the shadow ray and normalize by the theoretical maximum integral, producing a weight that captures how the ray traverses the occluder rather than merely whether an intersection occurred. To reduce temporal variance from clothing deformations in animated avatars, we further introduce an avatar proxy representation that stabilizes shadow casting while preserving visual fidelity. We implement RAGA using custom CUDA kernels integrated with the NVIDIA OptiX framework; as such, our shadow tracer runs at rates of about 50 FPS. We evaluate on single-avatar, multi-avatar, and avatar-object interaction scenarios across multiple datasets, demonstrating substantially improved shadow realism, temporal stability, and scene coherence. Our project page is available at https://miraymen.github.io/raga/.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。