Naka-GS: A Bionics-inspired Dual-Branch Naka Correction and Progressive Point Pruning for Low-Light 3DGS

Runyu Zhu; SiXun Dong; Zhiqiang Zhang; Qingxia Ye; Zhihua Xu

cs.CVApr 13, 2026

Naka-GS: A Bionics-inspired Dual-Branch Naka Correction and Progressive Point Pruning for Low-Light 3DGS

Authors: Runyu Zhu, SiXun Dong, Zhiqiang Zhang, Qingxia Ye, Zhihua Xu

Organizations: China University of Mining and Technology-Beijing

Abstract

Low-light conditions severely hinder 3D restoration and reconstruction by degrading image visibility, introducing color distortions, and contaminating geometric priors for downstream optimization. We present NAKA-GS, a bionics-inspired framework for low-light 3D Gaussian Splatting that jointly improves photometric restoration and geometric initialization. Our method starts with a Naka-guided chroma-correction network, which combines physics-prior low-light enhancement, dual-branch input modeling, frequency-decoupled correction, and mask-guided optimization to suppress bright-region chromatic artifacts and edge-structure errors. The enhanced images are then fed into a feed-forward multi-view reconstruction model to produce dense scene priors. To further improve Gaussian initialization, we introduce a lightweight Point Preprocessing Module (PPM) that performs coordinate alignment, voxel pooling, and distance-adaptive progressive pruning to remove noisy and redundant points while preserving representative structures. Without introducing heavy inference overhead, NAKA-GS improves restoration quality, training stability, and optimization efficiency for low-light 3D reconstruction. The proposed method was presented in the NTIRE 3D Restoration and Reconstruction (3DRR) Challenge, and outperformed the baseline methods by a large margin. The code is available at https://github.com/RunyuZhu/Naka-GS

Figures & tables

Figure 1: Overview of the proposed NAKA-GS pipeline. The pipeline consists of three stages: (1) NAKA-based enhancement for low-light image preprocessing, (2) VGGT-based multi-view reconstruction for generating a sparse scene package, and (3) Gaussian Splatting with PPM preprocessing, including voxel pooling and distance-adaptive pruning, followed by Gaussian initialization and scene optimization for novel view synthesis.

Figure 2: Overall architecture of the proposed chroma-guided correction network. The model takes the Naka-enhanced image and its auxiliary representations as input, predicts multiplicative and additive correction maps through a U-Net-style encoder-decoder, and reconstructs the corrected output via frequency-aware modulation.

Figure 3: Overview of the Point Preprocessing Module (PPM). The input point cloud is first voxelized and downsampled through voxel pooling to reduce redundancy. Then, distance-adaptive pruning is applied iteratively to remove sparse and unstable points according to local distance thresholds. The refined point cloud is finally used as the pruned point cloud for subsequent Gaussian initialization.

Methods	Metrics	BlueHawaii	Chocolate	Cupcake	GearWorks	Laboratory	MilkCookie	Popcorn	Sculpture	Ujikintoki	Avg.
3DGS Kerbl et al. ( 2023 )	PSNR $\uparrow$	7.49	7.89	4.42	6.9	7.59	6.15	7.46	5.85	6.23	6.66
	SSIM $\uparrow$	0.055	0.084	0.064	0.081	0.041	0.052	0.062	0.018	0.062	0.058
	LPIPS $\downarrow$	0.671	0.645	0.625	0.658	0.61	0.653	0.65	0.733	0.683	0.659
AlethNeRF Cui et al. ( 2024 )	PSNR $\uparrow$	15.84	11.53	13.49	8.82	14.14	13.49	13.25	12.22	14.12	12.99
	SSIM $\uparrow$	0.572	0.406	0.552	0.217	0.484	0.567	0.452	0.208	0.544	0.445
	LPIPS $\downarrow$	0.717	0.692	0.612	0.671	0.696	0.725	0.688	0.891	0.646	0.704

Table 1: Quantitative comparison across nine scenes. Darker blue denotes the best result and lighter blue denotes the second-best result for each metric.

Panel of Figure 4 — Figure 4: Qualitative comparisons on six representative scenes. Each row shows the visual results of different methods on the same scene. Our method consistently yields more faithful render results, fewer artifacts, and clearer structures.

Panel of Figure 5 — Figure 5: Additional qualitative comparisons on three representative scenes.

Explore similar work

ELoG-GS: Dual-Branch Gaussian Splatting with Luminance-Guided Enhancement for Extreme Low-light 3D Reconstruction
Apr 14, 2026Yuhao Liu, Dingju Wang, Ziyang Zheng3D Reconstruction Multi-View 3D Reconstruction
Shanghai Jiao Tong University
NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-Light Novel View Synthesis
Sep 11, 2026Shaurya Pavan A, Vemunuri Divya Madhuri, Yash Pradeep Gawande +1Multi-View Consistency 3D Gaussian Splatting
Indian Institute of Technology Madras
Fast Low-light Enhancement and Deblurring for 3D Dark Scenes
Mar 9, 2026Feng Zhang, Jinglong Wang, Ze Li +4Novel View Synthesis 3D Reconstruction
Nanjing University of Posts and Telecommunications, Nanjing. · The Hong Kong University of Science and Technology, Hong Kong. · The Hong Kong Polytechnic University, Hong Kong. +1

Apr 14, 2026J/K move · Enter open · S save

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

Yuhao Liu, Dingju Wang, Ziyang Zheng

Shanghai Jiao Tong University

3D Reconstruction Multi-View 3D Reconstruction 3D Gaussian Splatting

Open paper AskPDF arXiv

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.

Abstract

Explore similar work

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

NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-Light Novel View Synthesis

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