REVIEW 3 cited by
Relightable Gaussian Codec Avatars
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The fidelity of relighting is bounded by both geometry and appearance representations. For geometry, both mesh and volumetric approaches have difficulty modeling intricate structures like 3D hair geometry. For appearance, existing relighting models are limited in fidelity and often too slow to render in real-time with high-resolution continuous environments. In this work, we present Relightable Gaussian Codec Avatars, a method to build high-fidelity relightable head avatars that can be animated to generate novel expressions. Our geometry model based on 3D Gaussians can capture 3D-consistent sub-millimeter details such as hair strands and pores on dynamic face sequences. To support diverse materials of human heads such as the eyes, skin, and hair in a unified manner, we present a novel relightable appearance model based on learnable radiance transfer. Together with global illumination-aware spherical harmonics for the diffuse components, we achieve real-time relighting with all-frequency reflections using spherical Gaussians. This appearance model can be efficiently relit under both point light and continuous illumination. We further improve the fidelity of eye reflections and enable explicit gaze control by introducing relightable explicit eye models. Our method outperforms existing approaches without compromising real-time performance. We also demonstrate real-time relighting of avatars on a tethered consumer VR headset, showcasing the efficiency and fidelity of our avatars.
Forward citations
Cited by 3 Pith papers
-
A Hybrid Neural-Microfacet BRDF Model for Real-Time Rendering
A hybrid BRDF model, combining a GGX analytical term with a tiny learned residual and gating network, fits measured materials more accurately than fully neural models at equal memory cost.
-
Text2Relight: Creative Portrait Relighting with Text Guidance
Text2Relight learns to re-light portrait photos from text prompts using a synthetic dataset generated by a three-stage pipeline.
-
GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor
GaussianAvatar-Editor adds a visibility-weighted alpha blending term and a temporal adversarial loss to make text-driven edits of animatable Gaussian head avatars robust to motion occlusion and 4D inconsistency.
Discussion (0). Continue with ORCID to comment.