Relightify: Relightable 3D Faces from a Single Image via Diffusion Models

TL;DR

This paper introduces Relightify, a novel method using diffusion models to accurately reconstruct 3D facial reflectance from a single image, enabling realistic relighting and detailed face modeling.

Contribution

It is the first to utilize diffusion models as a prior for precise 3D facial BRDF reconstruction from a single image, improving reflectance estimation and texture completion.

Findings

Superior texture completion compared to existing methods

More faithful and consistent reflectance estimation

Enhanced 3D face relighting capabilities

Abstract

Following the remarkable success of diffusion models on image generation, recent works have also demonstrated their impressive ability to address a number of inverse problems in an unsupervised way, by properly constraining the sampling process based on a conditioning input. Motivated by this, in this paper, we present the first approach to use diffusion models as a prior for highly accurate 3D facial BRDF reconstruction from a single image. We start by leveraging a high-quality UV dataset of facial reflectance (diffuse and specular albedo and normals), which we render under varying illumination settings to simulate natural RGB textures and, then, train an unconditional diffusion model on concatenated pairs of rendered textures and reflectance components. At test time, we fit a 3D morphable model to the given image and unwrap the face in a partial UV texture. By sampling from the diffusion model, while retaining the observed texture part intact, the model inpaints not only the self-occluded areas but also the unknown reflectance components, in a single sequence of denoising steps. In contrast to existing methods, we directly acquire the observed texture from the input image, thus, resulting in more faithful and consistent reflectance estimation. Through a series of qualitative and quantitative comparisons, we demonstrate superior performance in both texture completion as well as reflectance reconstruction tasks.