arXiv:2610.39344 · v1

PicturePerfect: Diffusion-based Same-identity Facial Replacement

首次提交 2026-10-29 12:33

版本更新 2026-10-29 12:33

雷达观测 2026-10-30 11:25

摘要

With the growing success of diffusion models in computer vision, we explore their potential for same-identity facial replacement in photographs. Specifically, we propose a diffusion-based method, built on top of a pre-trained text-to-image model, that takes as input a portrait image of a person and a second reference image of the same individual, potentially captured under different conditions. The goal is to seamlessly replace the input face with the reference face, while keeping the background intact. Surprisingly, despite the clear real-world utility of this task, no recently published work has directly addressed face replacement in this specific setting. To support this goal, we construct a large dataset of image pairs depicting the same person under varying facial expressions and poses. Experimental results demonstrate that our approach produces more realistic and identity-consistent results than existing face reenactment models.

作者备注：Camera-ready version (ECCV 2026 workshop - Third Workshop on Foundation and Generative Models in Biometrics)