Naka-GS: A Bionics-inspired Dual-Branch Naka Correction and Progressive Point Pruning for Low-Light 3DGS
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908959797936128 |
|---|---|
| author | Zhu, Runyu Dong, SiXun Zhang, Zhiqiang Ye, Qingxia Xu, Zhihua |
| author_facet | Zhu, Runyu Dong, SiXun Zhang, Zhiqiang Ye, Qingxia Xu, Zhihua |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11142 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Naka-GS: A Bionics-inspired Dual-Branch Naka Correction and Progressive Point Pruning for Low-Light 3DGS Zhu, Runyu Dong, SiXun Zhang, Zhiqiang Ye, Qingxia Xu, Zhihua Computer Vision and Pattern Recognition 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 |
| title | Naka-GS: A Bionics-inspired Dual-Branch Naka Correction and Progressive Point Pruning for Low-Light 3DGS |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.11142 |