Deep Depth from Focus with Differential Focus Volume
This work improves depth-from-focus for computer vision applications, but it is incremental as it builds on existing CNN-based methods with novel components.
The paper tackles depth estimation from focal stacks by introducing a deep differential focus volume (DFV) and a probability regression mechanism, achieving state-of-the-art performance on multiple datasets with good generalizability and fast speed.
Depth-from-focus (DFF) is a technique that infers depth using the focus change of a camera. In this work, we propose a convolutional neural network (CNN) to find the best-focused pixels in a focal stack and infer depth from the focus estimation. The key innovation of the network is the novel deep differential focus volume (DFV). By computing the first-order derivative with the stacked features over different focal distances, DFV is able to capture both the focus and context information for focus analysis. Besides, we also introduce a probability regression mechanism for focus estimation to handle sparsely sampled focal stacks and provide uncertainty estimation to the final prediction. Comprehensive experiments demonstrate that the proposed model achieves state-of-the-art performance on multiple datasets with good generalizability and fast speed.