RealPoint3D: Point Cloud Generation from a Single Image with Complex Background

By Yukang Chen, Qian Zhang, Chang Huang, Lisen Mu, Gaofeng Meng, Xinggang Wang. 2018

11 citations recorded by the source corpus.

3D point cloud generation by the deep neural network from a single image has been attracting more and more researchers' attention. However, recently-proposed methods require the objects be captured with relatively clean backgrounds, fixed viewpoint, while this highly limits its application in the real environment. To overcome these drawbacks, we proposed to integrate the prior 3D shape knowledge into the network to guide the 3D generation. By taking additional 3D information, the proposed network can handle the 3D object generation from a single real image captured from any viewpoint and complex background. Specifically, giving a query image, we retrieve the nearest shape model from a pre-prepared 3D model database. Then, the image together with the retrieved shape model is fed into the proposed network to generate the fine-grained 3D point cloud. The effectiveness of our proposed framework has been verified on different kinds of datasets. Experimental results show that the proposed framework achieves state-of-the-art accuracy compared to other volumetric-based and point set generation methods. Furthermore, the proposed framework works well for real images in complex backgrounds with various view angles.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Geology, Generative Models, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Vishnu Naresh Boddeti
2. Jianping Shi
3. Xi Li
4. Xia Hu
5. Qingquan Song
6. Andrea Gesmundo
7. Xiao Huang

In Computer Graphics and Computer-Aided Design

1. Kalyanmoy Deb
2. Xi Li

In Geology

1. Jianping Shi

In Generative Models

1. Vishnu Naresh Boddeti
2. Jianping Shi
3. Xi Li
4. Xia Hu
5. Qingquan Song
6. Sirui Xie

In 3D Vision & Pose

1. Jianping Shi
2. Wolfgang Banzhaf

Citations in the corpus

• Auto-GNN: Neural architecture search of graph neural networks (2019, methodology): “A new framework combines these two search algorithms to improve the search efficiency [44].”
• Evolutionary-Neural Hybrid Agents for Architecture Search (2018, methodology): “RENAS [6] is an alternative RL-evolutionary hybrid that has been developed in parallel to Evo-NAS.”
• NSGA-NET: A Multi-Objective Genetic Algorithm for Neural Architecture Search (2018, methodology): “Chen et al. show in Chen et al. (2018a) that an augmented random search approach to optimize networks for a semantic segmentation application.”
• Graph-Guided Architecture Search for Real-Time Semantic Segmentation (2019, methodology): “Most existing architecture search works are based on either reinforcement learning [52, 17] or evolutionary algorithm [37, 11].”