Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo
This work addresses shape estimation for non-convex surfaces in computer vision, representing an incremental improvement over prior methods.
The paper tackled the challenge of estimating surface shape from reflectance in non-Lambertian photometric stereo by introducing a fully-convolutional architecture that leverages both spatial and photometric context simultaneously, resulting in outperforming existing methods in efficiency and accuracy on a real-world benchmark.
The problem of estimating a surface shape from its observed reflectance properties still remains a challenging task in computer vision. The presence of global illumination effects such as inter-reflections or cast shadows makes the task particularly difficult for non-convex real-world surfaces. State-of-the-art methods for calibrated photometric stereo address these issues using convolutional neural networks (CNNs) that primarily aim to capture either the spatial context among adjacent pixels or the photometric one formed by illuminating a sample from adjacent directions. In this paper, we bridge these two objectives and introduce an efficient fully-convolutional architecture that can leverage both spatial and photometric context simultaneously. In contrast to existing approaches that rely on standard 2D CNNs and regress directly to surface normals, we argue that using separable 4D convolutions and regressing to 2D Gaussian heat-maps severely reduces the size of the network and makes inference more efficient. Our experimental results on a real-world photometric stereo benchmark show that the proposed approach outperforms the existing methods both in efficiency and accuracy.