REVIEW 3 cited by
S2F2: Self-Supervised High Fidelity Face Reconstruction from Monocular Image
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
Signed reviews
read the original abstract
We present a novel face reconstruction method capable of reconstructing detailed face geometry, spatially varying face reflectance from a single monocular image. We build our work upon the recent advances of DNN-based auto-encoders with differentiable ray tracing image formation, trained in self-supervised manner. While providing the advantage of learning-based approaches and real-time reconstruction, the latter methods lacked fidelity. In this work, we achieve, for the first time, high fidelity face reconstruction using self-supervised learning only. Our novel coarse-to-fine deep architecture allows us to solve the challenging problem of decoupling face reflectance from geometry using a single image, at high computational speed. Compared to state-of-the-art methods, our method achieves more visually appealing reconstruction.
Forward citations
Cited by 3 Pith papers
-
RelightAnyone: A Generalized Relightable 3D Gaussian Head Model
A two-stage model turns flat-lit photos of a new head into a relightable 3D Gaussian avatar, predicting reflectance parameters without needing one-light-at-a-time captures of that person.
-
Monocular Facial Appearance Capture in the Wild
A monocular head-rotation video in arbitrary lighting is enough to reconstruct relightable facial geometry, diffuse albedo, specular intensity, and roughness using a visibility-aware shading model.
-
Learning to Decouple the Lights for 3D Face Texture Modeling
A 3D face texture modeling method that decouples external-occlusion shadows into multiple learned lighting conditions, improving texture recovery over single-illumination baselines.
Discussion (0). Continue with ORCID to comment.