Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Fast Low-light Enhancement and Deblurring for 3D Dark Scenes

Feng Zhang, Jinglong Wang, Ze Li, Yanghong Zhou, Yang Chen, Lei Chen, Xiatian Zhu

TL;DR

Fast low-light enhancement and deblurring framework that reformulates 3D scene restoration as an alternating cycle of enhancement and reconstruction, and outperforms state-of-the-art LuSh-NeRF in training and rendering.

Abstract

Novel view synthesis from low-light, noisy, and motion-blurred imagery remains a valuable and challenging task. Current volumetric rendering methods struggle with compound degradation, and sequential 2D preprocessing introduces artifacts due to interdependencies. In this work, we introduce FLED-GS, a fast low-light enhancement and deblurring framework that reformulates 3D scene restoration as an alternating cycle of enhancement and reconstruction. Specifically, FLED-GS inserts several intermediate brightness anchors to enable progressive recovery, preventing noise blow-up from harming deblurring or geometry. Each iteration sharpens inputs with an off-the-shelf 2D deblurrer and then performs noise-aware 3DGS reconstruction that estimates and suppresses noise while producing clean priors for the next level. Experiments show FLED-GS outperforms state-of-the-art LuSh-NeRF, achieving 21$\times$ faster training and 11$\times$ faster rendering.

Fast Low-light Enhancement and Deblurring for 3D Dark Scenes

TL;DR

Fast low-light enhancement and deblurring framework that reformulates 3D scene restoration as an alternating cycle of enhancement and reconstruction, and outperforms state-of-the-art LuSh-NeRF in training and rendering.

Abstract

Novel view synthesis from low-light, noisy, and motion-blurred imagery remains a valuable and challenging task. Current volumetric rendering methods struggle with compound degradation, and sequential 2D preprocessing introduces artifacts due to interdependencies. In this work, we introduce FLED-GS, a fast low-light enhancement and deblurring framework that reformulates 3D scene restoration as an alternating cycle of enhancement and reconstruction. Specifically, FLED-GS inserts several intermediate brightness anchors to enable progressive recovery, preventing noise blow-up from harming deblurring or geometry. Each iteration sharpens inputs with an off-the-shelf 2D deblurrer and then performs noise-aware 3DGS reconstruction that estimates and suppresses noise while producing clean priors for the next level. Experiments show FLED-GS outperforms state-of-the-art LuSh-NeRF, achieving 21 faster training and 11 faster rendering.
Paper Structure (10 sections, 2 equations, 2 figures, 4 tables, 1 algorithm)

This paper contains 10 sections, 2 equations, 2 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Methods
  3. Progressive Iterative Enhancement Framework
  4. Noise-Aware 3DGS
  5. Experiments
  6. Dataset and Implementation Details
  7. Experimental Results
  8. Ablation Study
  9. Conclusion
  10. ACKNOWLEDGMENT

Figures (2)

  • Figure 1: Overview of the pipeline for FLED-GS. Our framework consists of three main stages: Pre-processing, Progressive Iterative Enhancement, and Rendering. In the pre-processing stage, low-light images are enhanced step-by-step with varying histogram equalization and Gamma parameters to achieve progressive brightness adjustment. In the progressive iterative enhancement stage, the framework progressively performs low-light enhancement, deblurring, and denoising. Finally, the framework finishes training and leverages sharp normal-light 3DGS to render novel-view images.
  • Figure 2: Qualitative results of different methods on the LuSh-NeRF dataset. The upper scenes are synthetic scenes, and the lower scenes are real scenes.