# ReAge3D: Re-Aging 3D Faces with View Consistency

Source: [ReAge3D: Re-Aging 3D Faces with View Consistency](<https://www.sota2.com/research/paper/6a322a5ed33dfb23e783edf1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-18T05:00:14.654Z

Authors: Libing Zeng, Li Ma, Mingming He, Ning Yu, Paul Debevec, Nima Khademi Kalantari

Published: 2026-06-16T16:56:00.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Face Re-Aging on NeRSemble](<https://www.sota2.com/research/sota/3d-face-re-aging-on-nersemble.md>): 3D Face Re-Aging; NeRSemble; ID Score: 67.1.

- [Face Re-aging on FFHQ (1,000 unseen images)](<https://www.sota2.com/research/sota/face-re-aging-on-ffhq-1-000-unseen-images.md>): Face Re-aging; FFHQ (1,000 unseen images); Age Error (10): 2.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.18156>)

[PDF](<https://arxiv.org/pdf/2606.18156.pdf>)