Deep Portrait Lighting Enhancement with 3D Guidance

TL;DR

This paper introduces a two-stage deep learning framework for portrait lighting enhancement that leverages 3D facial guidance, improving results over existing methods by integrating 3D models and transformer-based image translation.

Contribution

The novel framework combines 3D facial guidance with a transformer-based image translation network for improved portrait lighting enhancement.

Findings

Outperforms state-of-the-art methods in quantitative metrics.

Produces superior visual quality on FFHQ and in-the-wild images.

Demonstrates effective use of 3D guidance in lighting correction.

Abstract

Despite recent breakthroughs in deep learning methods for image lighting enhancement, they are inferior when applied to portraits because 3D facial information is ignored in their models. To address this, we present a novel deep learning framework for portrait lighting enhancement based on 3D facial guidance. Our framework consists of two stages. In the first stage, corrected lighting parameters are predicted by a network from the input bad lighting image, with the assistance of a 3D morphable model and a differentiable renderer. Given the predicted lighting parameter, the differentiable renderer renders a face image with corrected shading and texture, which serves as the 3D guidance for learning image lighting enhancement in the second stage. To better exploit the long-range correlations between the input and the guidance, in the second stage, we design an image-to-image translation network with a novel transformer architecture, which automatically produces a lighting-enhanced result. Experimental results on the FFHQ dataset and in-the-wild images show that the proposed method outperforms state-of-the-art methods in terms of both quantitative metrics and visual quality. We will publish our dataset along with more results on https://cassiepython.github.io/egsr/index.html.