arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.02678cs.GR
收藏

实时神经外观模型

Real-Time Neural Appearance Models

Tizian Zeltner, Fabrice Rousselle, Andrea Weidlich, Petrik Clarberg, Jan Novák, Benedikt Bitterli, Alex Evans, Tomáš Davidovič, Simon Kallweit, Aaron Lefohn

AI总结:

该研究提出实时神经外观渲染系统,结合分层纹理、带图形先验的神经解码器与硬件加速优化,实现复杂外观场景的实时路径追踪,性能远超非神经方案,助力实时应用达成电影级画质。

摘要:

我们提出了一套完整的系统,可对以往仅能离线渲染的复杂外观场景进行实时渲染,这一成果通过算法与系统层面的创新相结合实现。我们的外观模型采用经学习的分层纹理,由神经解码器进行解析,输出反射率值和重要性采样方向。为充分发挥解码器的建模能力,我们为解码器引入两种图形先验:第一种先验是将方向变换到经学习的着色框架中,可精准重建中尺度效果;第二种先验是微表面采样分布,能让神经解码器高效执行重要性采样。最终得到的外观模型支持各向异性采样和细节层次(LOD)渲染,还可将深度分层材质图烘焙为紧凑的统一神经表示。通过为光线追踪着色器提供硬件加速的张量运算支持,我们证明了可以在实时路径追踪器中内联并高效运行神经解码器。我们分析了系统随神经材质数量增长的可扩展性,并提出采用针对连贯与发散执行优化的代码来提升性能。我们的神经材质着色器比非神经分层材质的速度快一个数量级以上,为游戏、实时预览等实时应用实现电影级画质打开了大门。

英文摘要:

We present a complete system for real-time rendering of scenes with complex appearance previously reserved for offline use. This is achieved with a combination of algorithmic and system level innovations. Our appearance model utilizes learned hierarchical textures that are interpreted using neural decoders, which produce reflectance values and importance-sampled directions. To best utilize the modeling capacity of the decoders, we equip the decoders with two graphics priors. The first prior -- transformation of directions into learned shading frames -- facilitates accurate reconstruction of mesoscale effects. The second prior -- a microfacet sampling distribution -- allows the neural decoder to perform importance sampling efficiently. The resulting appearance model supports anisotropic sampling and level-of-detail rendering, and allows baking deeply layered material graphs into a compact unified neural representation. By exposing hardware accelerated tensor operations to ray tracing shaders, we show that it is possible to inline and execute the neural decoders efficiently inside a real-time path tracer. We analyze scalability with increasing number of neural materials and propose to improve performance using code optimized for coherent and divergent execution. Our neural material shaders can be over an order of magnitude faster than non-neural layered materials. This opens up the door for using film-quality visuals in real-time applications such as games and live previews.

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。

↑