视频扩散后面采样,以看到超越动态散射层
IEEE transactions on pattern analysis and machine intelligence
|August 13, 2025
概括
本研究引入了一种新的视频扩散模型,用于通过动态散射层进行成像. 该方法通过利用时间相关性有效地重建高分辨率的细节,优于仅使用空间的方法.
科学领域:
- 光学和光子学 在光学和光子学.
- 计算机视觉 计算机视觉
- 机器学习 机器学习
背景情况:
- 通过散射介质进行成像是由于光扰动而面临的重大挑战.
- 精确建模动态或厚散射层仍然是困难的.
- 现有的方法难以重建分散图像中的细节.
研究的目的:
- 开发一种先进的逆向溶解器,通过动态散射层进行成像.
- 为了改进从分散的视频中重建高分辨率的空间细节.
- 为了提高适应未知和时间变化的散射条件的适应性.
主要方法:
- 使用视频扩散模型与物理接地前进模型.
- 将扩散后面采样 (DPS) 扩展到时空领域.
- 使用轻量级映射网络实现推断时间优化,用于联合参数估计.
主要成果:
- 通过有效捕捉时间相关性,成功恢复了高分辨率的空间细节.
- 与仅使用空间的方法相比,表现出更高的性能.
- 在各种条件下取得了强大而有效的结果,包括对噪声和模型不匹配的真实实验.
结论:
- 拟议的插即用反向溶解器对于盲点反向散射问题是有效的.
- 该方法显示了作为各种退化情况的一般视频恢复框架的多功能性.
- 这种方法通过动态散射介质在成像方面取得了重大进展.
相关概念视频
Protein Dynamics in Living Cells
2.3K
Different fluorescence-based techniques are used to study the protein dynamics in living cells. These techniques include FRAP, FRET, and PET.
Fluorescent recovery after photobleaching (FRAP) is a fluorescent-protein-based detection technique used to quantify protein movement rates within the cell. This method exposes a small portion of the cell to an intense laser beam. The laser beam causes permanent photobleaching of the fluorophore-tagged proteins in the exposed region. As the bleached...
Fluorescent recovery after photobleaching (FRAP) is a fluorescent-protein-based detection technique used to quantify protein movement rates within the cell. This method exposes a small portion of the cell to an intense laser beam. The laser beam causes permanent photobleaching of the fluorophore-tagged proteins in the exposed region. As the bleached...
2.3K
Uniform Depth Channel Flow
154
Uniform depth channel flow keeps fluid depth consistent along channels such as irrigation canals. In natural channels, such as rivers, approximate uniform flow is often assumed. This condition occurs when the channel’s bottom slope matches the energy slope, balancing potential energy lost from gravity with head loss due to shear stress. This balance prevents depth changes along the channel length, resulting in a steady, uniform flow.Uniform flow in open channels with a constant cross-section...
154


