Multi-view reconstruction for projector camera systems based on bundle adjustment

Range scanners using projector-camera systems have been studied actively in recent years as methods for measuring 3D shapes accurately and cost-effectively. To acquire an entire 3D shape of an object with such systems, the shape of the object should be captured from multiple directions and the set of captured shapes should be aligned using algorithms such as ICPs. Then, the aligned shapes are integrated into a single 3D shape model. However, the captured shapes are often distorted due to errors of intrinsic or extrinsic parameters of the camera and the projector. Because of these distortions, gaps between overlapped surfaces remain even after aligning the 3D shapes. In this paper, we propose a new method to capture an entire shape with high precision using an active stereo range scanner which consists of a projector and a camera with fixed relative positions. In the proposed method, minimization of calibration errors of the projector-camera pair and registration errors between 3D shapes from different viewpoints are simultaneously achieved. The proposed method can be considered as a variation of bundle adjustment techniques adapted to projector-camera systems. Since acquisition of correspondences between different views is not easy for projector-camera systems, a solution for the problem is also presented.