Light Up Your Face: A Physically Consistent Dataset and Diffusion Model for Face Fill-Light Enhancement

Face fill-light enhancement (FFE) brightens underexposed faces by adding virtual fill light while keeping the original scene illumination and background unchanged. Most face relighting methods aim to reshape overall lighting, which can suppress the input illumination or modify the entire scene, leading to foreground–background inconsistency and mismatching practical FFE needs. To support scalable learning, we introduce LightYourFace-160K (LYF-160K), a large-scale paired dataset built with a physically consistent renderer that injects a disk-shaped area fill light controlled by six disentangled factors, producing 160K before-and-after pairs. We first pretrain a physics-aware lighting prompt (PALP) that embeds the 6D parameters into conditioning tokens, using an auxiliary planar-light reconstruction objective. Building on a pretrained diffusion backbone, we then train a fill-light diffusion (FiLitDiff), an efficient one-step model conditioned on physically grounded lighting codes, enabling controllable and high-fidelity fill lighting at low computational cost. Experiments on held-out paired sets demonstrate strong perceptual quality and competitive full-reference metrics, while better preserving background illumination. The dataset and model will be at https://github.com/gobunu/Light-Up-Your-Face.

This paper studies how to improve portrait photos in which a face is too dark because of weak, back, or uneven lighting. Instead of changing the whole photo, our goal is to add a controllable virtual fill light to the face while keeping the original background and overall scene lighting consistent. To train and evaluate this task, we build LightYourFace-160K, a large collection of before-and-after portrait pairs created with a lighting simulation based on real-world fill-light behavior. The simulation lets us control properties such as light position, distance, size, and warmth. We then train an AI model, FiLitDiff, that uses these controls to brighten faces naturally and efficiently. Experiments show that the method improves facial illumination while better preserving the background and overall appearance than existing relighting and editing methods.