3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models
This addresses the challenge of 3D reconstruction in smoke-degraded conditions for applications like robotics or surveillance, but it appears incremental as it builds on existing 3D Gaussian Splatting methods.
The paper tackles the problem of reconstructing 3D scenes from smoke-degraded multi-view images by proposing a framework that integrates visual priors with efficient 3D modeling, resulting in improved robustness and generation of consistent, clear novel views in smoke environments.
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.