Multi-view high-dynamic-range 3D reconstruction and point cloud quality evaluation based on dual-frame difference images

A high dynamic range can easily lead to image saturation, making it a challenge for structured light 3D reconstruction. The article proposes a multi-view 3D topography measurement system, which consists of dual projectors, a single camera, and a high-precision rotary platform. The system utilizes single-frame images to achieve high-dynamic-range surface adaptive exposure. Subsequently, it proposes a method that combines two-frame differential images with multi-view imaging to identify highly reflective regions and complete point cloud holes. This approach addresses the issue of visual blind spots caused by shadows and local high reflectivity due to the occlusion of the measured object’s geometric features. Finally, the system employs deep learning to evaluate the quality of the high-dynamic-range point cloud data. Comparative experiments show that optimal exposure in single-frame images can achieve better imaging quality and shorten capture time. The dual-frame difference image algorithm can identify high-reflection areas and complete the point cloud data. The point cloud quality evaluation model based on IT-PCQA demonstrates the effectiveness of the proposed method for high-dynamic-range 3D reconstruction.