paper-with-me

Papers

AIGS-Net: Compact Illumination Field Modeling via 2D Gaussian Splatting for Fast Low-Light Image Enhancement

2026-06-16 · Yuhan Chen, Kunyang Huang, Fuchen Li, Zhuohan Qin, Guofa Li, Wenbo Chu, Keqiang Li arxiv

Existing low-light image enhancement methods often face a bottleneck between the representation capacity of illumination-field modeling and computational complexity. To address this issue, this paper proposes an Adaptive Illumination Gaussian Splatting Network (AIGS-Net), an ultra-lightweight architecture for fast low-light enhancement. Unlike conventional static priors, AIGS-Net constructs an input-adaptive 2D Gaussian Splatting illumination field. The opacity of Gaussian basis functions is dynamically modulated by relative luminance statistics of the input image, and spatially varying illumination compensation is rendered through ordered alpha compositing. To guide adaptive illumination compensation efficiently, a zero-parameter nonlinear multiscale contextual encoding module is introduced to extract low-frequency structures and local contrast cues without additional convolutional weights. To suppress noise amplification and sensor-induced color bias, AIGS-Net integrates noise-mask estimation, locked single-channel Gamma mapping, cross-channel consistency regularization, and target color-alignment constraints. Experiments on LOL and LSRW benchmarks show that AIGS-Net improves detail recovery and color fidelity while requiring only approximately 40 learnable parameters, achieving an effective trade-off between enhancement quality and extreme inference efficiency.

📄 PDF Abstract BibTeX arXiv:2606.17998

Code (0)

등록된 구현이 없습니다.

Tasks

Low-Light Image Enhancement

Similar Papers 제목 키워드 기반

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

2026-06-16 · Yuhan Chen, Wenxuan Yu, Guofa Li, Fuchen Li 외 arxiv

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 mecha…

Low-Light Image Enhancement

Modeling Relational Logic Circuits for And-Inverter Graph Convolutional Network

2025-08-16 · Weihao Sun, Shikai Guo, Siwen Wang, Qian Ma 외 arxiv

The automation of logic circuit design enhances chip performance, energy efficiency, and reliability, and is widely applied in the field of Electronic Design Automation (EDA).And-Inverter Graphs (AIGs) efficiently repres…

3iGS: Factorised Tensorial Illumination for 3D Gaussian Splatting

2024-08-07 · Zhe Jun Tang, Tat-Jen Cham

The use of 3D Gaussians as representation of radiance fields has enabled high quality novel view synthesis at real-time rendering speed. However, the choice of optimising the outgoing radiance of each Gaussian independen…

3DGSNovel View Synthesis

Continuous Splatting meets Retinex: Continuous Gaussian Splatting and Implicit Reflectance Modeling for Low-Light Image Enhancement

2026-06-15 · Yuhan Chen, Yicui Shi, Guofa Li, Wenxuan Yu 외 arxiv

Low-light image enhancement aims to recover clear images from low-illumination observations and is crucial for high-level downstream vision tasks. However, existing methods frequently encounter color distortion and struc…

Low-Light Image Enhancement

FuncGNN: Learning Functional Semantics of Logic Circuits with Graph Neural Networks

2025-06-07 · Qiyun Zhao

As integrated circuit scale grows and design complexity rises, effective circuit representation helps support logic synthesis, formal verification, and other automated processes in electronic design automation. And-Inver…

GPU