FaceFolds: Meshed Radiance Manifolds for Efficient Volumetric Rendering of Dynamic Faces
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929323812847616 |
|---|---|
| author | Medin, Safa C. Li, Gengyan Du, Ruofei Garbin, Stephan Davidson, Philip Wornell, Gregory W. Beeler, Thabo Meka, Abhimitra |
| author_facet | Medin, Safa C. Li, Gengyan Du, Ruofei Garbin, Stephan Davidson, Philip Wornell, Gregory W. Beeler, Thabo Meka, Abhimitra |
| contents | 3D rendering of dynamic face captures is a challenging problem, and it demands improvements on several fronts$\unicode{x2014}$photorealism, 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13807 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FaceFolds: Meshed Radiance Manifolds for Efficient Volumetric Rendering of Dynamic Faces Medin, Safa C. Li, Gengyan Du, Ruofei Garbin, Stephan Davidson, Philip Wornell, Gregory W. Beeler, Thabo Meka, Abhimitra Computer Vision and Pattern Recognition Graphics 3D rendering of dynamic face captures is a challenging problem, and it demands improvements on several fronts$\unicode{x2014}$photorealism, 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. |
| title | FaceFolds: Meshed Radiance Manifolds for Efficient Volumetric Rendering of Dynamic Faces |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2404.13807 |