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