LL-GaussianImage: Efficient Image Representation for Zero-shot Low-Light Enhancement with 2D Gaussian Splatting

• URL: http://arxiv.org/abs/2601.15772v1
• Date: Thu, 22 Jan 2026 09:01:08 GMT
• Title: LL-GaussianImage: Efficient Image Representation for Zero-shot Low-Light Enhancement with 2D Gaussian Splatting
• Authors: Yuhan Chen, Wenxuan Yu, Guofa Li, Yijun Xu, Ying Fang, Yicui Shi, Long Cao, Wenbo Chu, Keqiang Li,
• Abstract summary: 2D Gaussian Splatting (2DGS) is an emerging explicit scene representation method with significant potential for image compression.<n>Existing low-light enhancement algorithms operate predominantly within the pixel domain.<n>We propose LL-GaussianImage, the first zero-shot unsupervised framework designed for low-light enhancement directly within the 2DGS compressed representation domain.
• Score: 26.287424110093113
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 2D Gaussian Splatting (2DGS) is an emerging explicit scene representation method with significant potential for image compression due to high fidelity and high compression ratios. However, existing low-light enhancement algorithms operate predominantly within the pixel domain. Processing 2DGS-compressed images necessitates a cumbersome decompression-enhancement-recompression pipeline, which compromises efficiency and introduces secondary degradation. To address these limitations, we propose LL-GaussianImage, the first zero-shot unsupervised framework designed for low-light enhancement directly within the 2DGS compressed representation domain. Three primary advantages are offered by this framework. First, a semantic-guided Mixture-of-Experts enhancement framework is designed. Dynamic adaptive transformations are applied to the sparse attribute space of 2DGS using rendered images as guidance to enable compression-as-enhancement without full decompression to a pixel grid. Second, a multi-objective collaborative loss function system is established to strictly constrain smoothness and fidelity during enhancement, suppressing artifacts while improving visual quality. Third, a two-stage optimization process is utilized to achieve reconstruction-as-enhancement. The accuracy of the base representation is ensured through single-scale reconstruction and network robustness is enhanced. High-quality enhancement of low-light images is achieved while high compression ratios are maintained. The feasibility and superiority of the paradigm for direct processing within the compressed representation domain are validated through experimental results.

Related papers

• LL-GaussianMap: Zero-shot Low-Light Image Enhancement via 2D Gaussian Splatting Guided Gain Maps [24.549302711851478]
  LL-GaussianMap is proposed as the first unsupervised framework incorporating 2DGS into low-light image enhancement.<n>Results demonstrate that LL-GaussianMap achieves superior enhancement performance with an extremely low storage footprint.
  arXiv  Detail & Related papers  (2026-01-22T08:57:36Z)
• CSGaussian: Progressive Rate-Distortion Compression and Segmentation for 3D Gaussian Splatting [57.73006852239138]
  We present the first unified framework for rate-distortion-optimized compression and segmentation of 3D Gaussian Splatting (3DGS)<n>Inspired by recent advances in rate-distortion-optimized 3DGS compression, this work integrates semantic learning into the compression pipeline to support decoder-side applications.<n>Our scheme features a lightweight implicit neural representation-based hyperprior, enabling efficient entropy coding of both color and semantic attributes.
  arXiv  Detail & Related papers  (2026-01-19T08:21:45Z)
• SANR: Scene-Aware Neural Representation for Light Field Image Compression with Rate-Distortion Optimization [54.184486302645716]
  We propose a Scene-Aware Neural Representation framework for light field image compression with end-to-end rate-distortion optimization.<n>For scene awareness, SANR introduces a hierarchical scene modeling block that leverages multi-scale latent codes to capture intrinsic scene structures.<n>Experiment results demonstrate that SANR significantly outperforms state-of-the-art techniques regarding rate-distortion performance with a 65.62% BD-rate saving against HEVC.
  arXiv  Detail & Related papers  (2025-10-17T16:00:43Z)
• Leveraging Learned Image Prior for 3D Gaussian Compression [47.29061692878941]
  We introduce a novel 3DGS compression framework that leverages the powerful representational capacity of learned image priors to recover compression-induced quality degradation.<n>Our framework is designed to be compatible with existing Gaussian compression methods, making it broadly applicable across different baselines.
  arXiv  Detail & Related papers  (2025-10-16T14:10:02Z)
• High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network [73.19214585791268]
  This paper introduces a pyramid network called LLF-LUT++, which integrates global and local operators through closed-form Laplacian pyramid decomposition and reconstruction.<n>Specifically, we utilize an image-adaptive 3D LUT that capitalizes on the global tonal characteristics of downsampled images.<n>LLF-LUT++ not only achieves a 2.64 dB improvement in PSNR on the HDR+ dataset, but also further reduces, with 4K resolution images processed in just 13 ms on a single GPU.
  arXiv  Detail & Related papers  (2025-10-13T16:52:32Z)
• ExGS: Extreme 3D Gaussian Compression with Diffusion Priors [60.7245825868903]
  We introduce ExGS and GaussPainter for Extreme 3DGS compression.<n>GassPainter fills in missing regions and enhances visible pixels, yielding substantial improvements in degraded renderings.<n>Our framework can even achieve over 100X compression (reducing a typical 354.77 MB model to about 3.31 MB)
  arXiv  Detail & Related papers  (2025-09-29T13:23:06Z)
• GL-PGENet: A Parameterized Generation Framework for Robust Document Image Enhancement [0.42303492200814446]
  Document Image Enhancement (DIE) serves as a critical component in Document AI systems, where its performance determines the effectiveness of downstream tasks.<n>We present Global with Local Parametric Generation Enhancement Network (GL-PGENet), a novel architecture designed for multi-degraded color document images.
  arXiv  Detail & Related papers  (2025-05-28T06:37:06Z)
• Timestep-Aware Diffusion Model for Extreme Image Rescaling [47.89362819768323]
  We propose a novel framework called Timestep-Aware Diffusion Model (TADM) for extreme image rescaling.<n>TADM performs rescaling operations in the latent space of a pre-trained autoencoder.<n>It effectively leverages powerful natural image priors learned by a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-08-17T09:51:42Z)
• Image-GS: Content-Adaptive Image Representation via 2D Gaussians [52.598772767324036]
  We introduce Image-GS, a content-adaptive image representation based on 2D Gaussians radiance.<n>It supports hardware-friendly rapid access for real-time usage, requiring only 0.3K MACs to decode a pixel.<n>We demonstrate its versatility with several applications, including texture compression, semantics-aware compression, and joint image compression and restoration.
  arXiv  Detail & Related papers  (2024-07-02T00:45:21Z)
• Sensitivity Decouple Learning for Image Compression Artifacts Reduction [39.67836965306397]
  We propose to decouple the intrinsic attributes into two complementary features for artifacts reduction. In our proposed DAGN, we develop a cross-feature fusion module to maintain the consistency of compression-insensitive features. Our method achieves an average 2.06 dB PSNR gains on BSD500, outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-15T12:29:35Z)

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.