Beyond Shadows: A Large-Scale Benchmark and Multi-Stage Framework for High-Fidelity Facial Shadow Removal

TL;DR

This paper introduces a large-scale real-world dataset and a multi-stage framework to improve high-fidelity facial shadow removal, addressing limitations of existing methods in complex lighting conditions.

Contribution

The paper presents the ASFW dataset and the FSE method, advancing shadow removal by providing realistic training data and a novel multi-stage approach.

Findings

ASFW improves shadow removal accuracy in real-world images.

FSE outperforms existing shadow removal techniques.

Models trained on ASFW generalize well to diverse lighting conditions.

Abstract

Facial shadows often degrade image quality and the performance of vision algorithms. Existing methods struggle to remove shadows while preserving texture, especially under complex lighting conditions, and they lack real-world paired datasets for training. We present the Augmented Shadow Face in the Wild (ASFW) dataset, the first large-scale real-world dataset for facial shadow removal, containing 1,081 paired shadow and shadow-free images created via a professional Photoshop workflow. ASFW offers photorealistic shadow variations and accurate ground truths, bridging the gap between synthetic and real domains. Deep models trained on ASFW demonstrate improved shadow removal in real-world conditions. We also introduce the Face Shadow Eraser (FSE) method to showcase the effectiveness of the dataset. Experiments demonstrate that ASFW enhances the performance of facial shadow removal models, setting new standards for this task.