用高斯点云与光流结合，提升远距离成像在湍流下的清晰度。
GSTurb: Gaussian Splatting for Atmospheric Turbulence Mitigation
- 用高斯参数建模湍流引起的偏移和模糊，跨帧优化恢复
- 合成数据上达27.67dB PSNR，比顶尖方法高1.3dB
- 适用于真实湍流场景，对视频复原有实用价值
大气湍流导致图像显著退化，表现为像素位移（倾斜）和模糊，尤其在远距离成像中更为严重。本文提出一种新型湍流抑制框架GSTurb，结合光流引导的倾斜校正与高斯点云建模非同相模糊。该框架利用高斯参数表示倾斜与模糊，并在多帧间优化以增强图像恢复效果。在ATSyn-static数据集上的实验表明，本方法达到27.67 dB的峰值PSNR和0.8735的SSIM，相比当前最优方法，PSNR提升1.3 dB（4.5%），SSIM提升0.048（5.8%）。此外，在真实数据集TSRWGAN Real-World和CLEAR上，GSTurb亦表现优异，定量与定性结果均优于现有方法。结果表明，光流引导的倾斜校正与高斯点云建模的结合，能有效提升合成与真实湍流条件下的图像恢复质量。代码将发布于https://github.com/DuhlLiamz/3DGS_turbulence/tree/main。
原文摘要 · Abstract (English)
Atmospheric turbulence causes significant image degradation due to pixel displacement (tilt) and blur, particularly in long-range imaging applications. In this paper, we propose a novel framework for atmospheric turbulence mitigation, GSTurb, which integrates optical flow-guided tilt correction and Gaussian splatting for modeling non-isoplanatic blur. The framework employs Gaussian parameters to represent tilt and blur, and optimizes them across multiple frames to enhance restoration. Experimental results on the ATSyn-static dataset demonstrate the effectiveness of our method, achieving a peak PSNR of 27.67 dB and SSIM of 0.8735. Compared to the state-of-the-art method, GSTurb improves PSNR by 1.3 dB (a 4.5% increase) and SSIM by 0.048 (a 5.8% increase). Additionally, on real datasets, including the TSRWGAN Real-World and CLEAR datasets, GSTurb outperforms existing methods, showing significant improvements in both qualitative and quantitative performance. These results highlight that combining optical flow-guided tilt correction with Gaussian splatting effectively enhances image restoration under both synthetic and real-world turbulence conditions. The code for this method will be available at https://github.com/DuhlLiamz/3DGS_turbulence/tree/main.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。