Gaussian Light Field Splatting: A Physical Prior-Driven Vision Transformer for Unsupervised Low-Light Image Enhancement

• URL: http://arxiv.org/abs/2606.17985v1
• Date: Tue, 16 Jun 2026 14:37:08 GMT
• Title: Gaussian Light Field Splatting: A Physical Prior-Driven Vision Transformer for Unsupervised Low-Light Image Enhancement
• Abstract summary: Existing unsupervised low-light image enhancement methods often encounter local exposure imbalance and color distortion under complex non-uniform illumination.<n>We propose GLFS, a Gaussian light field splatting-based Vision Transformer that integrates continuous physical illumination modeling from Gaussian splatting into the Transformer architecture.<n>It achieves state-of-the-art performance and offers a new representation paradigm for low-light image enhancement.
• Score: 24.549302711851478
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing unsupervised low-light image enhancement methods often encounter local exposure imbalance and color distortion under complex non-uniform illumination. In addition, most Vision Transformers lack an explicit mechanism for modeling the physical priors of illumination degradation. To address these limitations, we propose GLFS, a Gaussian light field splatting-based Vision Transformer that integrates continuous physical illumination modeling from Gaussian splatting into the Transformer architecture. In GLFS, scene illumination is represented by a superposition of anisotropic Gaussian basis functions. Physics-guided biases are introduced into self-attention to adaptively infer a spatial gain field, enabling accurate and uniform restoration under complex illumination. To reduce color bias and structural degradation during enhancement, a color-vector angular loss and a luminance-edge loss are further developed. These losses enforce hue consistency and improve the structural fidelity of local details. Extensive ablation studies and quantitative evaluations show that GLFS provides clear advantages in illumination correction and detail preservation. It achieves state-of-the-art performance and offers a new representation paradigm for low-light image enhancement.

Related papers

• AIGS-Net: Compact Illumination Field Modeling via 2D Gaussian Splatting for Fast Low-Light Image Enhancement [19.712825613823778]
  This paper proposes an Adaptive Illumination Gaussian Splatting Network (AIGS-Net) for fast low-light enhancement.<n>Unlike conventional static priors, AIGS-Net constructs an input-adaptive 2D Gaussian Splatting illumination field.<n>Experiments show that AIGS-Net improves detail recovery and color fidelity while requiring only approximately 40 learnable parameters.
  arXiv  Detail & Related papers  (2026-06-16T14:45:55Z)
• Continuous Splatting meets Retinex: Continuous Gaussian Splatting and Implicit Reflectance Modeling for Low-Light Image Enhancement [25.472500911155347]
  Low-light image enhancement aims to recover clear images from low-illumination observations.<n>Existing methods frequently encounter color distortion and structural artifacts when balancing global smooth illumination adjustment and local high-frequency detail recovery.<n>We propose CGS-Retinex as the first low-light image enhancement framework based on explicit-implicit joint modeling.
  arXiv  Detail & Related papers  (2026-06-15T03:19:28Z)
• GraspALL: Adaptive Structural Compensation from Illumination Variation for Robotic Garment Grasping in Any Low-Light Conditions [55.86392310651848]
  The reduced illumination in low-light scenes severely degrades garment structural features, leading to a significant drop in grasping robustness.<n>Existing methods typically enhance RGB features by exploiting the illumination-invariant properties of non-RGB modalities.<n>We propose GraspALL, an illumination-structure interactive compensation model.<n>Experiments on the self-built garment grasping dataset demonstrate that GraspALL improves grasping accuracy by 32-44% over baselines under diverse illumination conditions.
  arXiv  Detail & Related papers  (2026-03-16T03:38:38Z)
• Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesis [73.27997579020233]
  We propose Luminance-GS++, a 3DGS-based framework for robust NVS under diverse illumination conditions.<n>Our method combines a globally view-adaptive lightness adjustment with a local pixel-wise residual refinement for precise color correction.
  arXiv  Detail & Related papers  (2026-02-20T16:20:50Z)
• GLOW: Global Illumination-Aware Inverse Rendering of Indoor Scenes Captured with Dynamic Co-Located Light & Camera [18.90141473604964]
  Inverse rendering of indoor scenes remains challenging due to the ambiguity between reflectance and lighting.<n>We present GLOW, a Global Illumination-aware Inverse Rendering framework designed to address these challenges.
  arXiv  Detail & Related papers  (2025-11-28T03:24:12Z)
• LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement [65.06462316546806]
  Low-light image enhancement aims to improve illumination while preserving high-quality color and texture.<n>Existing methods often fail to extract reliable feature representations due to severely degraded pixel-level information under low-light conditions.<n>We propose LightQANet, a novel framework that introduces quantized and adaptive feature learning for low-light enhancement.
  arXiv  Detail & Related papers  (2025-10-16T14:54:42Z)
• 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)
• Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network [69.96295927854042]
  Low-light environments usually lead to less informative large-scale dark areas. We propose to integrate the effectiveness of gamma correction with the strong modelling capacities of deep networks. Because exponential operation introduces high computational complexity, we propose to use Taylor Series to approximate gamma correction.
  arXiv  Detail & Related papers  (2023-08-16T08:46:51Z)
• Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement [109.335317310485]
  Cycle-Interactive Generative Adversarial Network (CIGAN) is capable of not only better transferring illumination distributions between low/normal-light images but also manipulating detailed signals. In particular, the proposed low-light guided transformation feed-forwards the features of low-light images from the generator of enhancement GAN into the generator of degradation GAN.
  arXiv  Detail & Related papers  (2022-07-03T06:37:46Z)

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.