GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

• URL: http://arxiv.org/abs/2604.03039v2
• Date: Mon, 06 Apr 2026 14:41:55 GMT
• Title: GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model
• Abstract summary: This paper describes our method for Track 2 of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge on smoke-degraded images.<n>Smoke reduces image visibility and weakens the cross-view consistency required by scene optimization and rendering.<n>We address this problem with a multi-stage pipeline consisting of image restoration, dehazing, MLLM-based enhancement, 3DGS-MCMC optimization, and averaging over repeated runs.
• Score: 19.832333333869578
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper describes our method for Track 2 of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge on smoke-degraded images. In this task, smoke reduces image visibility and weakens the cross-view consistency required by scene optimization and rendering. We address this problem with a multi-stage pipeline consisting of image restoration, dehazing, MLLM-based enhancement, 3DGS-MCMC optimization, and averaging over repeated runs. The main purpose of the pipeline is to improve visibility before rendering while limiting scene-content changes across input views. Experimental results on the challenge benchmark show improved quantitative performance and better visual quality than the provided baselines. The code is available at https://github.com/plbbl/GenSmoke-GS. Our method achieved a ranking of 1 out of 14 participants in Track 2 of the NTIRE 3DRR Challenge, as reported on the official competition website: https://www.codabench.org/competitions/13993/#/results-tab.

Related papers

• VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors [79.88300861391114]
  VidSplat is a training-free generative reconstruction framework.<n>We tackle two key challenges that enable the effective integration of generation and reconstruction.<n>Experiments on widely used benchmarks demonstrate our superior performance in sparse-view scene reconstruction.
  arXiv  Detail & Related papers  (2026-05-12T02:20:31Z)
• Dehaze-then-Splat: Generative Dehazing with Physics-Informed 3D Gaussian Splatting for Smoke-Free Novel View Synthesis [1.8997372468370612]
  We present Dehaze-then-Splat, a two-stage pipeline for multi-view smoke removal and novel view synthesis developed for Track2 of the NTIRE 2026 3D Restoration and Reconstruction Challenge.<n>In the first stage, we produce pseudo-clean training images via per-frame generative dehazing using Nano Banana Pro, followed by brightness normalization.<n>In the second stage, we train 3D Gaussian Splatting with physics-informed auxiliary losses.
  arXiv  Detail & Related papers  (2026-04-15T07:52:53Z)
• 3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models [20.914336026776]
  Smoke introduces strong scattering effects, view-dependent appearance changes, and severe degradation of cross-view consistency.<n>We employ Nano-Banana-Pro to enhance smoke-degraded images and provide clearer visual observations for reconstruction.<n>We develop Smoke-GS, a medium-aware 3D Gaussian Splatting framework for smoke scene reconstruction.
  arXiv  Detail & Related papers  (2026-04-07T10:37:30Z)
• SmokeGS-R: Physics-Guided Pseudo-Clean 3DGS for Real-World Multi-View Smoke Restoration [2.0130120622614114]
  Real-world smoke simultaneously attenuates scene radiance, adds airlight, and destabilizes multi-view appearance consistency.<n>We present textbfSmokeGS-R, a practical pipeline developed for the NTIRE 2026 3D Restoration and Reconstruction Track 2 challenge.
  arXiv  Detail & Related papers  (2026-04-07T01:15:05Z)
• Breaking the Vicious Cycle: Coherent 3D Gaussian Splatting from Sparse and Motion-Blurred Views [40.70901994944635]
  We introduce CoherentGS, a framework for high-fidelity 3D reconstruction from sparse and blurry images.<n>Our key insight is to address these compound degradations using a dual-prior strategy.<n>CoherentGS significantly outperforms existing methods, setting a new state-of-the-art for this challenging task.
  arXiv  Detail & Related papers  (2025-12-11T07:36:35Z)
• FlowR: Flowing from Sparse to Dense 3D Reconstructions [60.28571003356382]
  We propose a flow matching model that learns a flow to connect novel view renderings from possibly sparse reconstructions to renderings that we expect from dense reconstructions.<n>Our model is trained on a novel dataset of 3.6M image pairs and can process up to 45 views at 540x960 resolution (91K tokens) on one H100 GPU in a single forward pass.
  arXiv  Detail & Related papers  (2025-04-02T11:57:01Z)
• 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors [13.191199172286508]
  Novel-view synthesis aims to generate novel views of a scene from multiple input images or videos. 3DGS-Enhancer is a novel pipeline for enhancing the representation quality of 3DGS representations.
  arXiv  Detail & Related papers  (2024-10-21T17:59:09Z)
• Phys3DGS: Physically-based 3D Gaussian Splatting for Inverse Rendering [5.908471365011943]
  We first report a problem incurred by hidden Gaussians, where Gaussians beneath the surface adversely affect the pixel color in the volume rendering adopted by the existing methods. In an effort to improve the quality of 3DGS-based inverse rendering under deferred rendering, we propose a novel two-step training approach. Our experiments show that, under relighting, the proposed method offers significantly better rendering quality than the existing 3DGS-based inverse rendering methods.
  arXiv  Detail & Related papers  (2024-09-16T14:46:36Z)
• Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction [153.52406455209538]
  Gamba is an end-to-end 3D reconstruction model from a single-view image. It completes reconstruction within 0.05 seconds on a single NVIDIA A100 GPU.
  arXiv  Detail & Related papers  (2024-03-27T17:40:14Z)
• 2L3: Lifting Imperfect Generated 2D Images into Accurate 3D [16.66666619143761]
  Multi-view (MV) 3D reconstruction is a promising solution to fuse generated MV images into consistent 3D objects. However, the generated images usually suffer from inconsistent lighting, misaligned geometry, and sparse views, leading to poor reconstruction quality. We present a novel 3D reconstruction framework that leverages intrinsic decomposition guidance, transient-mono prior guidance, and view augmentation to cope with the three issues.
  arXiv  Detail & Related papers  (2024-01-29T02:30:31Z)
• Splatter Image: Ultra-Fast Single-View 3D Reconstruction [67.96212093828179]
  Splatter Image is based on Gaussian Splatting, which allows fast and high-quality reconstruction of 3D scenes from multiple images. We learn a neural network that, at test time, performs reconstruction in a feed-forward manner, at 38 FPS. On several synthetic, real, multi-category and large-scale benchmark datasets, we achieve better results in terms of PSNR, LPIPS, and other metrics while training and evaluating much faster than prior works.
  arXiv  Detail & Related papers  (2023-12-20T16:14:58Z)
• High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization [51.878078860524795]
  We present a high-fidelity 3D generative adversarial network (GAN) inversion framework that can synthesize photo-realistic novel views. Our approach enables high-fidelity 3D rendering from a single image, which is promising for various applications of AI-generated 3D content.
  arXiv  Detail & Related papers  (2022-11-28T18:59:52Z)
• Solving Inverse Problems with NerfGANs [88.24518907451868]
  We introduce a novel framework for solving inverse problems using NeRF-style generative models. We show that naively optimizing the latent space leads to artifacts and poor novel view rendering. We propose a novel radiance field regularization method to obtain better 3-D surfaces and improved novel views given single view observations.
  arXiv  Detail & Related papers  (2021-12-16T17:56:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.