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

• URL: http://arxiv.org/abs/2603.12579v1
• Date: Fri, 13 Mar 2026 02:25:24 GMT
• Title: DINOLight: Robust Ambient Light Normalization with Self-supervised Visual Prior Integration
• Abstract summary: Ambient light normalization aims to restore images degraded by non-uniform shadows and lighting caused by multiple light sources and complex scene geometries.<n>We observe that DINOv2 can reliably extract both semantic and geometric information from a degraded image.<n>We propose an adaptive feature fusion module that combines features from different DINOv2 layers using a point-wise softmax mask.
• Score: 19.13863263345781
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• OmniLight: One Model to Rule All Lighting Conditions [20.84793675424915]
  Adverse lighting conditions pose significant challenges to computer vision systems by degrading visibility and color fidelity.<n>We present a comprehensive study on lighting-related image restoration by exploring two contrasting strategies.<n>We discuss the impact of data distribution on the performance of specialized and unified architectures in lighting-related image restoration.
  arXiv  Detail & Related papers  (2026-04-16T15:47:49Z)
• PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors [13.290464696196366]
  We propose PhaSR (Physically Aligned Shadow Removal), addressing this through dual-level prior alignment.<n>Experiments show competitive performance in shadow removal with lower complexity and generalization to ambient lighting.
  arXiv  Detail & Related papers  (2026-01-24T14:15:41Z)
• DIME-Net: A Dual-Illumination Adaptive Enhancement Network Based on Retinex and Mixture-of-Experts [7.6894262288762665]
  We propose a dual-illumination enhancement framework called DIME-Net.<n>By integrating Retinex theory, this module effectively performs enhancement tailored to both low-light and backlit images.<n>We show that DIME-Net achieves competitive performance on both synthetic and real-world low-light and backlit datasets without any retraining.
  arXiv  Detail & Related papers  (2025-08-19T15:17:47Z)
• LightSwitch: Multi-view Relighting with Material-guided Diffusion [73.5965603000002]
  LightSwitch is a novel finetuned material-relighting diffusion framework.<n>We show that our 2D relighting prediction quality exceeds previous state-of-the-art relighting priors that directly relight from images.
  arXiv  Detail & Related papers  (2025-08-08T17:59:52Z)
• SAIGFormer: A Spatially-Adaptive Illumination-Guided Network for Low-Light Image Enhancement [58.79901582809091]
  Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination.<n>Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination.<n>We present a Spatially-Adaptive Illumination-Guided Transformer framework that enables accurate illumination restoration.
  arXiv  Detail & Related papers  (2025-07-21T11:38:56Z)
• Light of Normals: Unified Feature Representation for Universal Photometric Stereo [69.95514862547174]
  Current encoders cannot guarantee that illumination and normal information are decoupled.<n>We introduce LINO UniPS with two key components: (i) Light Register Tokens with light alignment supervision to aggregate point, direction, and environment lights.<n>We also introduce PS-Verse, a large-scale synthetic dataset graded by geometric complexity and lighting diversity.
  arXiv  Detail & Related papers  (2025-06-23T17:53:11Z)
• DLEN: Dual Branch of Transformer for Low-Light Image Enhancement in Dual Domains [0.0]
  Low-light image enhancement (LLE) aims to improve the visual quality of images captured in poorly lit conditions.<n>These issues hinder the performance of computer vision tasks such as object detection, facial recognition, and autonomous driving.<n>We propose the Dual Light Enhance Network (DLEN), a novel architecture that incorporates two distinct attention mechanisms.
  arXiv  Detail & Related papers  (2025-01-21T15:58:16Z)
• CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement [97.95330185793358]
  Low-light image enhancement (LLIE) aims to improve low-illumination images.<n>Existing methods face two challenges: uncertainty in restoration from diverse brightness degradations and loss of texture and color information.<n>We propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement.
  arXiv  Detail & Related papers  (2024-04-08T07:34:39Z)
• Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network [52.77569396659629]
  This paper presents the deep compensation network unfolding (DCUNet) for restoring light field (LF) images captured under low-light conditions. The framework uses the intermediate enhanced result to estimate the illumination map, which is then employed in the unfolding process to produce a new enhanced result. To properly leverage the unique characteristics of LF images, this paper proposes a pseudo-explicit feature interaction module.
  arXiv  Detail & Related papers  (2023-08-10T07:53:06Z)
• Physically Inspired Dense Fusion Networks for Relighting [45.66699760138863]
  We propose a model which enriches neural networks with physical insight. Our method generates the relighted image with new illumination settings via two different strategies. We show that our proposal can outperform many state-of-the-art methods in terms of well-known fidelity metrics and perceptual loss.
  arXiv  Detail & Related papers  (2021-05-05T17:33:45Z)
• Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement [52.49231695707198]
  We investigate the intrinsic degradation and relight the low-light image while refining the details and color in two steps. Inspired by the color image formulation, we first estimate the degradation from low-light inputs to simulate the distortion of environment illumination color, and then refine the content to recover the loss of diffuse illumination color. Our proposed method has surpassed the SOTA by 0.95dB in PSNR on LOL1000 dataset and 3.18% in mAP on ExDark dataset.
  arXiv  Detail & Related papers  (2021-03-19T04:00:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.