PulseAugur
EN
LIVE 07:29:00

New 3D Face Re-Aging Framework Achieves View Consistency

Researchers have developed ReAge3D, a new framework for realistic and controllable 3D face re-aging. This method addresses inconsistencies in existing 3D editing techniques by first using a 2D diffusion-based re-aging model called DiffReaging. It then employs a center-out editing propagation strategy to reconstruct multi-view-consistent re-aged images, ensuring coherence with existing pixels through a Masked-DiffReaging process. The consistent set of re-aged views then guides the optimization of the 3D face model, outperforming current 3D editing methods visually and quantitatively. AI

IMPACT This research advances controllable 3D face manipulation, potentially impacting digital avatars and media synthesis.

RANK_REASON The cluster contains a research paper detailing a new method for 3D face re-aging. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Nima Khademi Kalantari ·

    ReAge3D: Re-Aging 3D Faces with View Consistency

    We present a novel framework for realistic and controllable 3D face re-aging which produces highly detailed, identity-preserving results. Existing 3D editing methods, while effective for coarse semantic changes, are not well suited for re-aging, as even small inconsistencies acro…