用优化方法实现高分辨率深度图重建，比深度学习更快更准。
Depth from Defocus via Direct Optimization
- 交替优化深度图和全聚焦图像，利用线性模型与并行计算提升效率。
- 在合成与真实模糊数据上均达到更高分辨率，优于现有深度学习方法。
- 适合需要高精度深度图的科研与工业场景，代码开源可复现。
尽管基于光学物理的模糊前向模型已较为成熟，但从一系列失焦图像中恢复深度仍是一个计算挑战。本文表明，在现代优化方法和合理算力支持下，全局优化的深度图重建是可行的。方法采用交替最小化：固定深度图时，前向模型对全聚焦图像呈线性；固定全聚焦图像时，每个像素的深度可独立求解，实现高度并行。通过交替使用凸优化与并行网格搜索，可在比当前深度学习方法更高的分辨率下有效求解深度图问题。我们在包含合成与真实失焦模糊的基准数据集上验证了该方法，结果优于以往方法。代码已公开于 github.com/hollyjackson/dfd。
原文摘要 · Abstract (English)
Though there exists a reasonable forward model for blur based on optical physics, recovering depth from a collection of defocused images remains a computationally challenging optimization problem. In this paper, we show that with contemporary optimization methods and reasonable computing resources, a global optimization approach to depth from defocus is feasible. Our approach rests on alternating minimization. When holding the depth map fixed, the forward model is linear with respect to the all-in-focus image. When holding the all-in-focus image fixed, the depth at each pixel can be computed independently, enabling embarrassingly parallel computation. We show that alternating between convex optimization and parallel grid search can effectively solve the depth-from-defocus problem at higher resolutions than current deep learning methods. We demonstrate our approach on benchmark datasets with synthetic and real defocus blur and show promising results compared to prior approaches. Our code is available at github.com/hollyjackson/dfd.
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。