Yang Zhang

Constructive solid geometry (CSG) is a technique to create a complex 3D object by using boolean operators to combine simple primitives. However, it is very challenging to obtain programs from 3D models, the inverse of the constructing process. In this Letter, the authors propose a generative recursive network for the inverse problem, which is composed of several kinds of specially designed sub‐networks to get CSG programs directly from the input 3D model. Compared with previous methods, the authors' method can deal with various lengths and structures of programs, does not limit to specific primitives and can generate programs of very similar structures with the input.

The generation of 3D models from a single image has recently received much attention, based on which point cloud generation methods have been developed. However, most current 3D reconstruction methods only work for relatively pure backgrounds, which limits their applications on real images. Meanwhile, more fine-grained details are required to provide finer models. This paper proposes an end-toend efficient generation network, which is composed of an encoder, a 2D-3D fusion module and a decoder. First, a single-object image and a nearest-shape retrieval from ShapeNet are fed into the network; then, the two encoders are integrated adaptively according to their information integrity, followed by the decoder to obtain fine-grained point clouds. The point cloud from the nearest shape effectively instructs the generation of finer point clouds. To have a consistent spatial distribution from multi-view observations, our algorithm adopts projection loss as an additional supervisor. Experiments on complex and pure background images show that our method attains state-of-the-art accuracy compared to volumetric and point set generation methods, particularly toward fine-grained details, and it works well for both complex backgrounds and multiple view angles.

With the rapid development of intelligent transportation, there comes huge demands for high-precision road network maps. However, due to the complex road spectral performance, it is very challenging to extract road networks with complete topologies. Based on the topological networks produced by previous road extraction methods, in this paper, we propose a Multi-conditional Generative Adversarial Network (McGAN) to obtain complete road networks by refining the imperfect road topology. The proposed McGAN, which is composed of two discriminators and a generator, takes both original remote sensing image and the initial road network produced by existing road extraction methods as input. The first discriminator employs the original spectral information to instruct the reconstruction, and the other discriminator aims to refine the road network topology. Such a structure makes the generator capable of receiving both spectral and topological information of the road region, thus producing more complete road networks compared with the initial road network. Three different datasets were used to compare McGan with several recent approaches, which showed that the proposed method significantly improved the precision and recall of the road networks, and also worked well for those road regions where previous methods could hardly obtain complete structures.