# 3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models arXiv: https://arxiv.org/abs/2604.05687 ยท HTML: https://mlsanity.com/paper/2604.05687/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. - Builds on 38 of its 63 references that are in the map. - First posted on arXiv 7 Apr 2026. ## Placed in - Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/) ## Builds on (most cited first, 30 of 38) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023) - [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022) - [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022) - [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023) - [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022) - [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022) - [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016) - [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022) - [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020) - [Optimizing Prompts for Text-to-Image Generation](https://mlsanity.com/paper/2212.09611/) (2022) - [One-Step Image Translation with Text-to-Image Models](https://mlsanity.com/paper/2403.12036/) (2024) - [MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing](https://mlsanity.com/paper/2308.14036/) (2023) - [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022) - [Benchmarking Micro-action Recognition: Dataset, Methods, and Applications](https://mlsanity.com/paper/2403.05234/) (2024) - [Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks](https://mlsanity.com/paper/2308.14153/) (2023) - [WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting](https://mlsanity.com/paper/2408.08206/) (2024) - [SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Model](https://mlsanity.com/paper/2409.17345/) (2024) - [ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering](https://mlsanity.com/paper/2305.02103/) (2023) - [Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture](https://mlsanity.com/paper/2403.07347/) (2024) - [EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer](https://mlsanity.com/paper/2312.04152/) (2023) - [Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint](https://mlsanity.com/paper/2409.15739/) (2024) - [RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction](https://mlsanity.com/paper/2512.23437/) (2025) - [I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions](https://mlsanity.com/paper/2510.22161/) (2025) - [SnowFormer: Context Interaction Transformer with Scale-awareness for Single Image Desnowing](https://mlsanity.com/paper/2208.09703/) (2022) - [GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration](https://mlsanity.com/paper/2411.17687/) (2024) - [GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model](https://mlsanity.com/paper/2604.03039/) (2026) - [NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results](https://mlsanity.com/paper/2604.04135/) (2026) - [XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being](https://mlsanity.com/paper/2603.06583/) (2026) - [AquaNeRF: Neural Radiance Fields in Underwater Media with Distractor Removal](https://mlsanity.com/paper/2502.16351/) (2025) ## Built on by (most cited first, 7 of 7) - [Dual-Branch Remote Sensing Infrared Image Super-Resolution](https://mlsanity.com/paper/2604.10112/) (2026) - [Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation](https://mlsanity.com/paper/2604.11564/) (2026) - [Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising](https://mlsanity.com/paper/2604.11468/) (2026) - [ELoG-GS: Dual-Branch Gaussian Splatting with Luminance-Guided Enhancement for Extreme Low-light 3D Reconstruction](https://mlsanity.com/paper/2604.12592/) (2026) - [Dehaze-then-Splat: Generative Dehazing with Physics-Informed 3D Gaussian Splatting for Smoke-Free Novel View Synthesis](https://mlsanity.com/paper/2604.13589/) (2026) - [Robust Incomplete Multimodal Sentiment Analysis via Iterative Proxy Correction](https://mlsanity.com/paper/2608.19971/) (2026) - [FujinSplat: Seeing Through Smoke with RAW-Domain Gaussian Splatting](https://mlsanity.com/paper/2609.06017/) (2026) ## Abstract (arXiv) 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.