研究人员开发了 GlowGS，这是一种用于改进夜景中3D高斯泼溅（3DGS）的新方法，尤其是在有发光效果的区域。现有的 3DGS 方法在低光照条件下由于缺乏纹理和边缘等结构特征而面临挑战。GlowGS 通过使用扩散模型和视觉基础模型（VFM）来生成和学习语义特征，从而弥补了视觉线索的缺失，实现了更准确的 3D 场景重建。 AI
影响 增强了在低光照和发光密集环境下的 3D 场景重建能力，可能改进自动驾驶和增强现实等应用。
排序理由 该集群包含一篇详细介绍特定计算机视觉任务新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.23602v1 Announce Type: new Abstract: 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 …
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.…