Single-shot dense active stereo with pixel-wise phase estimation based on grid-structure using CNN and correspondence estimation using GCN

Active stereo systems based on static pattern projection, a.k.a. oneshot scan, have been widely used for measuring dynamic scenes. Many patterns used for oneshot active stereo have grid-structures and grid-wise codes. For such systems, the grid structure is first detected, and graph matching methods are applied to estimate correspondences. However, such graph matching is often vulnerable to graph connection errors caused by grid structure analysis based on image features. Also, dense reconstruction for such systems is an open problem, where pixel-wise correspondence estimation from sparse image features is required. We propose a learning-based method to capture grid structure information and pixel-wise positional information simultaneously. We also propose to represent the grid structure by graphs with augmented connections other than 4-neighbor connections and applying them to a graph convolutional network (GCN). The proposed method can analyze large variety of grid patterns, has auto-calibration capability, can reconstruct dense shapes for fast moving objects.