Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries
This addresses the problem of robust depth estimation in low-light conditions for applications like robotics or imaging, though it appears incremental as it builds on existing depth from defocus techniques.
The paper tackles depth estimation from photon-limited, defocused images by introducing a novel Blurry-Edges representation and deep network to predict it, achieving the highest accuracy compared to state-of-the-art methods.
Extracting depth information from photon-limited, defocused images is challenging because depth from defocus (DfD) relies on accurate estimation of defocus blur, which is fundamentally sensitive to image noise. We present a novel approach to robustly measure object depths from photon-limited images along the defocused boundaries. It is based on a new image patch representation, Blurry-Edges, that explicitly stores and visualizes a rich set of low-level patch information, including boundaries, color, and smoothness. We develop a deep neural network architecture that predicts the Blurry-Edges representation from a pair of differently defocused images, from which depth can be calculated using a closed-form DfD relation we derive. The experimental results on synthetic and real data show that our method achieves the highest depth estimation accuracy on photon-limited images compared to a broad range of state-of-the-art DfD methods.