FaceFolds: Meshed Radiance Manifolds for Efficient Volumetric Rendering of Dynamic Faces
Proceedings of the ACM on Computer Graphics and Interactive Techniques(2024)
摘要
3D rendering of dynamic face captures is a challenging problem, and it
demands improvements on several frontsx2014photorealism,
efficiency, compatibility, and configurability. We present a novel
representation that enables high-quality volumetric rendering of an actor's
dynamic facial performances with minimal compute and memory footprint. It runs
natively on commodity graphics soft- and hardware, and allows for a graceful
trade-off between quality and efficiency. Our method utilizes recent advances
in neural rendering, particularly learning discrete radiance manifolds to
sparsely sample the scene to model volumetric effects. We achieve efficient
modeling by learning a single set of manifolds for the entire dynamic sequence,
while implicitly modeling appearance changes as temporal canonical texture. We
export a single layered mesh and view-independent RGBA texture video that is
compatible with legacy graphics renderers without additional ML integration. We
demonstrate our method by rendering dynamic face captures of real actors in a
game engine, at comparable photorealism to state-of-the-art neural rendering
techniques at previously unseen frame rates.
更多查看译文
关键词
Face Modeling,Neural Radiance Fields,Novel View Synthesis,Performance Capture,Volumetric Rendering
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