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

TL;DR

This paper introduces GenSmoke-GS, a multi-stage generative approach for synthesizing novel views from smoke-degraded images, improving visibility and scene consistency in challenging conditions.

Contribution

The paper presents a novel multi-stage pipeline combining restoration, dehazing, enhancement, and optimization specifically designed for smoke-degraded image reconstruction.

Findings

Outperformed baseline methods in quantitative metrics

Achieved first place in NTIRE 3DRR Challenge Track 2

Produced visually superior reconstructed images

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.