Flow-based GAN for 3D Point Cloud Generation from a Single Image
This work addresses the limited quality in 3D point cloud generation from single images for applications like 3D scene understanding, representing an incremental improvement over existing methods.
The paper tackles the problem of generating 3D point clouds from single 2D images, which is important for 3D scene understanding, by proposing a hybrid explicit-implicit generative modeling scheme that improves detailed 3D structures and achieves superior performance on ShapeNet, with generalization shown on cross-category synthetic and real images from PASCAL3D+.
Generating a 3D point cloud from a single 2D image is of great importance for 3D scene understanding applications. To reconstruct the whole 3D shape of the object shown in the image, the existing deep learning based approaches use either explicit or implicit generative modeling of point clouds, which, however, suffer from limited quality. In this work, we aim to alleviate this issue by introducing a hybrid explicit-implicit generative modeling scheme, which inherits the flow-based explicit generative models for sampling point clouds with arbitrary resolutions while improving the detailed 3D structures of point clouds by leveraging the implicit generative adversarial networks (GANs). We evaluate on the large-scale synthetic dataset ShapeNet, with the experimental results demonstrating the superior performance of the proposed method. In addition, the generalization ability of our method is demonstrated by performing on cross-category synthetic images as well as by testing on real images from PASCAL3D+ dataset.