DINOLight: Robust Ambient Light Normalization with Self-supervised Visual Prior Integration

2026-03-12

AI Summary

This work addresses the challenge of non-uniform shadows and illumination degradation caused by multiple light sources and complex scene geometry. The authors propose a self-supervised image restoration method that leverages visual priors derived from DINOv2 features, introducing semantic and geometric cues into illumination normalization for the first time. An adaptive feature fusion module and a spatial-frequency cross-attention mechanism enable end-to-end restoration. The key innovation lies in a pixel-wise softmax masking strategy that effectively fuses multi-layer DINOv2 features to guide the recovery process without requiring ground-truth shadow masks. Evaluated on Ambient6K, the method achieves state-of-the-art performance and demonstrates competitive results across multiple shadow removal benchmarks.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Adversarial Learning & Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Data transparency and provenance
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

This paper presents a new ambient light normalization framework, DINOLight, that integrates the self-supervised model DINOv2's image understanding capability into the restoration process as a visual prior. Ambient light normalization aims to restore images degraded by non-uniform shadows and lighting caused by multiple light sources and complex scene geometries. We observe that DINOv2 can reliably extract both semantic and geometric information from a degraded image. Based on this observation, we develop a novel framework to utilize DINOv2 features for lighting normalization. First, we propose an adaptive feature fusion module that combines features from different DINOv2 layers using a point-wise softmax mask. Next, the fused features are integrated into our proposed restoration network in both spatial and frequency domains through an auxiliary cross-attention mechanism. Experiments show that DINOLight achieves superior performance on the Ambient6K dataset, and that DINOv2 features are effective for enhancing ambient light normalization. We also apply our method to shadow-removal benchmark datasets, achieving competitive results compared to methods that use mask priors. Codes will be released upon acceptance.

Problem

• ambient light normalization
• non-uniform illumination
• shadow removal
• image restoration
• lighting degradation

Innovation

• ambient light normalization
• self-supervised visual prior
• DINOv2
• adaptive feature fusion
• cross-attention mechanism