REVIEW 3 cited by
UniAvatar: Taming Lifelike Audio-Driven Talking Head Generation with Comprehensive Motion and Lighting Control
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
Recently, animating portrait images using audio input is a popular task. Creating lifelike talking head videos requires flexible and natural movements, including facial and head dynamics, camera motion, realistic light and shadow effects. Existing methods struggle to offer comprehensive, multifaceted control over these aspects. In this work, we introduce UniAvatar, a designed method that provides extensive control over a wide range of motion and illumination conditions. Specifically, we use the FLAME model to render all motion information onto a single image, maintaining the integrity of 3D motion details while enabling fine-grained, pixel-level control. Beyond motion, this approach also allows for comprehensive global illumination control. We design independent modules to manage both 3D motion and illumination, permitting separate and combined control. Extensive experiments demonstrate that our method outperforms others in both broad-range motion control and lighting control. Additionally, to enhance the diversity of motion and environmental contexts in current datasets, we collect and plan to publicly release two datasets, DH-FaceDrasMvVid-100 and DH-FaceReliVid-200, which capture significant head movements during speech and various lighting scenarios.
Forward citations
Cited by 3 Pith papers
-
Hi-VAE: Efficient Video Autoencoding with Global and Detailed Motion
A hierarchical motion autoencoder with a conditional diffusion decoder reconstructs 16-frame videos from latents as small as 0.07% of the input size while maintaining competitive PSNR and perceptual scores.
-
JOLT3D: Joint Learning of Talking Heads and 3DMM Parameters with Application to Lip-Sync
JOLT3D jointly trains a 3DMM reconstruction network with a talking head generator, then uses FACS mouth blendshapes from a diffusion model to lip-sync videos while preserving the original chin contour.
-
ChronoTailor: Harnessing Attention Guidance for Fine-Grained Video Virtual Try-On
ChronoTailor combines region-aware attention guidance, temporal feature fusion, and multi-scale garment-pose alignment to produce state-of-the-art video virtual try-on results, and contributes the StyleDress dataset.
Discussion (0). Continue with ORCID to comment.