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

2026-01-27

AI Summary

This work addresses the challenge of facial shadow removal under complex lighting conditions, where severe shadows degrade image quality and impair the performance of vision algorithms. Existing methods are hindered by the scarcity of real-world paired training data. To bridge this gap, we introduce ASFW—the first large-scale, real-world paired dataset for facial shadow removal, constructed through a professional photo retouching pipeline—effectively narrowing the domain gap between synthetic and real imagery. We further propose Face Shadow Eraser (FSE), a multi-stage shadow removal framework trained on ASFW. Extensive experiments demonstrate that FSE significantly outperforms current state-of-the-art methods, achieving high-fidelity shadow removal in real-world scenarios while preserving fine facial texture details, thereby establishing a new benchmark for this task.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• facial shadow removal
• image quality degradation
• real-world paired dataset
• complex lighting conditions
• texture preservation

Innovation

• facial shadow removal
• large-scale dataset
• real-world paired data
• photorealistic shadows
• Face Shadow Eraser