用视觉先验增强烟雾中图像，实现更清晰的3D场景重建。
3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models
- 融合多模态大模型视觉先验，提升烟雾退化图像质量
- 提出Smoke-GS框架，生成视角一致且清晰的新视图
- 轻量级设计保持高效渲染，适合复杂烟雾环境
从烟雾遮蔽的多视角图像中重建3D场景极具挑战性，因烟雾导致强烈散射、视角依赖的外观变化及跨视角一致性严重退化。为此，我们提出一种结合视觉先验与高效3D建模的框架。采用Nano-Banana-Pro增强烟雾退化图像，提供更清晰的重建观测；并开发Smoke-GS，一种面向介质感知的3D高斯泼溅框架，用于烟雾场景重建与以修复为导向的新视角合成。Smoke-GS使用显式3D高斯表示场景，并引入轻量级视角依赖介质分支，捕捉由烟雾引起的方向相关外观变化。该方法在保持3D高斯泼溅渲染效率的同时，显著提升了对烟雾退化的鲁棒性。实验表明，本方法能在极端烟雾环境中生成一致且视觉清晰的新视图。
原文摘要 · Abstract (English)
Reconstructing 3D scenes from smoke-degraded multi-view images is particularly difficult because smoke introduces strong scattering effects, view-dependent appearance changes, and severe degradation of cross-view consistency. To address these issues, we propose a framework that integrates visual priors with efficient 3D scene modeling. We employ Nano-Banana-Pro to enhance smoke-degraded images and provide clearer visual observations for reconstruction and develop Smoke-GS, a medium-aware 3D Gaussian Splatting framework for smoke scene reconstruction and restoration-oriented novel view synthesis. Smoke-GS models the scene using explicit 3D Gaussians and introduces a lightweight view-dependent medium branch to capture direction-dependent appearance variations caused by smoke. Our method preserves the rendering efficiency of 3D Gaussian Splatting while improving robustness to smoke-induced degradation. Results demonstrate the effectiveness of our method for generating consistent and visually clear novel views in challenging smoke environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。