ReAge3D: Re-Aging 3D Faces with View Consistency

2026-06-16

AI Summary

Existing 3D face re-aging methods struggle to maintain consistency of age-related details across multiple viewpoints, often resulting in over-smoothed outputs. This work proposes a 3D face re-aging framework grounded in 2D diffusion models, leveraging a center-outward view propagation strategy to generate multi-view consistent edits that supervise the optimization of 3D representations. The core innovation lies in the Masked-DiffReaging mechanism, which progressively injects edited content during the diffusion process to ensure both cross-view consistency and preservation of fine-grained details. Experimental results demonstrate that the proposed method outperforms current 3D editing approaches in both visual quality and quantitative metrics, achieving smooth and controllable 3D facial age transformation.

Abstract

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 across re-aged 2D views can lead to over-smoothing of subtle but perceptually important age-related details. To address this challenge, we first introduce a 2D diffusion-based re-aging model, DiffReaging, trained on synthetically generated image pairs. We further propose a center-out editing propagation strategy that leverages this re-aging model to reconstruct multi-view-consistent re-aged images. Specifically, starting from a re-aged frontal pivot view, we reconstruct the remaining views through warping and our proposed Masked-DiffReaging process. By injecting existing content at every step of the diffusion process, Masked-DiffReaging ensures that the reconstructed regions remain coherent with existing pixels. The resulting consistent set of re-aged views supervises the optimization of the re-aged 3D representation. Our method outperforms existing 3D editing techniques both visually and quantitatively, enabling smooth, fine-grained control over age transformations in 3D face models.

Problem

• 3D face re-aging
• view consistency
• age-related details
• identity preservation
• 3D face editing

Innovation

• 3D face re-aging
• view consistency
• diffusion model
• masked editing
• multi-view reconstruction