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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zheng, Xinye, Wang, Fei, Nie, Yiqi, Li, Kun, Chen, Junjie, Zhao, Jiaqi, Wei, Yanyan, Wu, Zhiliang
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910155867684864
author Zheng, Xinye
Wang, Fei
Nie, Yiqi
Li, Kun
Chen, Junjie
Zhao, Jiaqi
Wei, Yanyan
Wu, Zhiliang
author_facet Zheng, Xinye
Wang, Fei
Nie, Yiqi
Li, Kun
Chen, Junjie
Zhao, Jiaqi
Wei, Yanyan
Wu, Zhiliang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05687
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle 3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models
Zheng, Xinye
Wang, Fei
Nie, Yiqi
Li, Kun
Chen, Junjie
Zhao, Jiaqi
Wei, Yanyan
Wu, Zhiliang
Computer Vision and Pattern Recognition
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.
title 3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.05687