Accurate 3D Shape Reconstruction from Single Structured-Light Image via Fringe-to-Fringe Network

Accurate three-dimensional (3D) shape reconstruction of objects from a single image is a challenging task, yet it is highly demanded by numerous applications. This paper presents a novel 3D shape reconstruction technique integrating a high-accuracy structured-light method with a deep neural network learning scheme. The proposed approach employs a convolutional neural network (CNN) to transform a color structured-light fringe image into multiple triple-frequency phase-shifted grayscale fringe images, from which the 3D shape can be accurately reconstructed. The robustness of the proposed technique is verified, and it can be a promising 3D imaging tool in future scientific and industrial applications.

Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields

Multilayer perceptrons (MLPs) have been successfully used to represent 3D shapes implicitly and compactly, by mapping 3D coordinates to the corresponding signed distance values or occupancy values. In this paper, we propose a novel positional encoding scheme, called Spline Positional Encoding, to map the input coordinates to a high dimensional space before passing them to MLPs, which help recover 3D signed distance fields with fine-scale geometric details from unorganized 3D point clouds. We verified the superiority of our approach over other positional encoding schemes on tasks of 3D shape reconstruction and 3D shape space learning from input point clouds. The efficacy of our approach extended to image reconstruction is also demonstrated and evaluated.

Three-Dimensional Measurement and Three-Dimensional Printing of Giant Coastal Rocks

In recent years, the use of three-dimensional (3D) measurement and printing technologies has become an effective means of analyzing and reproducing both physical and natural objects, regardless of size. However, in some complex environments, such as coastal environments, it is difficult to obtain the required data by conventional measurement methods. In this paper, we describe our efforts to archive and digitally reproduce a giant coastal rock formation known as Sanouiwa, a famous site off the coast of Miyako City, Iwate Prefecture, Japan. We used two different 3D measurement techniques. The first involved taking pictures using a drone-mounted camera, and the second involved the use of global navigation satellite system data. The point cloud data generated from the high-resolution camera images were integrated using 3D shape reconstruction software, and 3D digital models were created for use in tourism promotion and environmental protection awareness initiatives. Finally, we fabricated the 3D digital models of the rocks with 3D printers for use as museum exhibitions, school curriculum materials, and related applications.