GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes
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_ | 1866910248062681088 |
|---|---|
| author | Lin, Beibei Cao, Xiao Guo, Jingyuan Tan, Robby T. |
| author_facet | Lin, Beibei Cao, Xiao Guo, Jingyuan Tan, Robby T. |
| contents | Existing 3DGS methods effectively render high-quality novel views in clear-day scenes. However, they struggle with night scenes, particularly in glow regions, due to the lack of structural features such as textures and edges, which are key cues for splatting-based reconstruction. To address this problem, we leverage a diffusion model and a Vision Foundation Model (VFM) to compensate for missing structural cues. Our method consists of two key novel ideas: semantic feature generation and novel-view semantic learning. First, semantic feature generation produces high-quality semantic features as implicit structural cues for novel views. Specifically, a diffusion model synthesizes novel views with unknown camera poses from training views, while a VFM evaluates their quality. Once high-quality novel views are identified, the VFM extracts robust features to construct the semantic feature bank. Second, novel-view semantic learning enables 3DGS to optimize rendered novel views without requiring ground truth. It achieves this by extracting semantic features from a rendered novel view, searching the feature bank for the most similar features, and minimizing their distance. This process enforces implicit structural constraints, ensuring semantically coherent, artifact-free rendered views. Extensive experiments demonstrate the effectiveness of our GlowGS in generating semantically accurate 3D views, showing significant improvements over existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_23602 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes Lin, Beibei Cao, Xiao Guo, Jingyuan Tan, Robby T. Computer Vision and Pattern Recognition Existing 3DGS methods effectively render high-quality novel views in clear-day scenes. However, they struggle with night scenes, particularly in glow regions, due to the lack of structural features such as textures and edges, which are key cues for splatting-based reconstruction. To address this problem, we leverage a diffusion model and a Vision Foundation Model (VFM) to compensate for missing structural cues. Our method consists of two key novel ideas: semantic feature generation and novel-view semantic learning. First, semantic feature generation produces high-quality semantic features as implicit structural cues for novel views. Specifically, a diffusion model synthesizes novel views with unknown camera poses from training views, while a VFM evaluates their quality. Once high-quality novel views are identified, the VFM extracts robust features to construct the semantic feature bank. Second, novel-view semantic learning enables 3DGS to optimize rendered novel views without requiring ground truth. It achieves this by extracting semantic features from a rendered novel view, searching the feature bank for the most similar features, and minimizing their distance. This process enforces implicit structural constraints, ensuring semantically coherent, artifact-free rendered views. Extensive experiments demonstrate the effectiveness of our GlowGS in generating semantically accurate 3D views, showing significant improvements over existing methods. |
| title | GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.23602 |