ELoG-GS: Dual-Branch Gaussian Splatting with Luminance-Guided Enhancement for Extreme Low-light 3D Reconstruction

TL;DR

This paper introduces ELoG-GS, a novel 3D reconstruction method optimized for extreme low-light conditions, combining geometry-aware initialization and luminance-guided enhancement to improve fidelity and realism.

Contribution

The paper proposes a robust low-light 3D reconstruction pipeline that integrates learning-based point cloud initialization with luminance-guided color enhancement for better results.

Findings

Achieved a PSNR of 18.6626 and SSIM of 0.6855 on the NTIRE benchmark.

Significantly outperformed baseline methods in visual fidelity and geometric consistency.

Demonstrated practical effectiveness in real-world degraded low-light scenarios.

Abstract

This paper presents our approach to the NTIRE 2026 3D Restoration and Reconstruction Challenge (Track 1), which focuses on reconstructing high-quality 3D representations from degraded multi-view inputs. The challenge involves recovering geometrically consistent and photorealistic 3D scenes in extreme low-light environments. To address this task, we propose Extreme Low-light Optimized Gaussian Splatting (ELoG-GS), a robust low-light 3D reconstruction pipeline that integrates learning-based point cloud initialization and luminance-guided color enhancement for stable and photorealistic Gaussian Splatting. Our method incorporates both geometry-aware initialization and photometric adaptation strategies to improve reconstruction fidelity under challenging conditions. Extensive experiments on the NTIRE Track 1 benchmark demonstrate that our approach significantly improves reconstruction quality over the baselines, achieving superior visual fidelity and geometric consistency. The proposed method provides a practical solution for robust 3D reconstruction in real-world degraded scenarios. In the final testing phase, our method achieved a PSNR of 18.6626 and an SSIM of 0.6855 on the official platform leaderboard. Code is available at https://github.com/lyh120/FSGS_EAPGS.