3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models

TL;DR

This paper introduces a novel framework for 3D smoke scene reconstruction that combines visual priors with efficient 3D modeling, improving robustness and clarity in challenging smoke environments.

Contribution

It integrates Nano-Banana-Pro for enhanced image clarity and develops Smoke-GS, a medium-aware 3D Gaussian Splatting method with a view-dependent branch for better smoke scene reconstruction.

Findings

Effective in generating consistent novel views in smoke environments.

Preserves rendering efficiency of Gaussian Splatting.

Improves robustness to smoke-induced degradation.

Abstract

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.