DARTS: Diffusion Approximated Residual Time Sampling for Low Variance Time-of-flight Rendering in Homogeneous Scattering Medium

Qianyue He,Xin Jin, Haitian Jiang,Dongyu Du

CoRR(2024)

引用 0|浏览7
暂无评分
摘要
Time-of-flight (ToF) devices have greatly propelled the advancement of various multi-modal perception applications. However, due to complexity in both sampling path construction and vertex connection in time domain, it is extremely challenging to accurately render time-resolved information in ToF device simulation, particularly in scenes involving complex geometric structures, diverse materials and volumetric scattering media. Existing works either exhibit significant bias or variance in ToF rendering tasks or prove ineffective in scenes involving participating media and camera-warped settings. To address this challenge, in this paper, we integrate the transient diffusion theory into path construction to generate the unbiased full transport of time-resolved radiance. Additionally, we devise an elliptical sampling method to provide controllable vertex connection satisfying any required photon traversal time. To our knowledge, our work is the first to explore importance sampling according to transient radiance, enabling temporal path construction of higher quality in multiple scattering settings. Extensive experiments show that our sampling method can significantly improve both quality and efficiency of ToF rendering within both path tracing and photon-based frameworks, with at least a 5x MSE reduction versus SOTA methods in equal rendering time. Our method introduces no memory overhead and negligible extra computation compared to the boost in speed, providing a straightforward plug-in for various existing rendering frameworks.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要