Invertible Residual Neural Networks with Conditional Injector and Interpolator for Point Cloud Upsampling

Invertible Residual Neural Networks with Conditional Injector and Interpolator for Point Cloud Upsampling

Aihua Mao, Yaqi Duan, Yu-Hui Wen, Zihui Du, Hongmin Cai, Yong-Jin Liu

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence
Main Track. Pages 1267-1275. https://doi.org/10.24963/ijcai.2023/141

Point clouds obtained by LiDAR and other sensors are usually sparse and irregular. Low-quality point clouds have serious influence on the final performance of downstream tasks. Recently, a point cloud upsampling network with normalizing flows has been proposed to address this problem. However, the network heavily relies on designing specialized architectures to achieve invertibility. In this paper, we propose a novel invertible residual neural network for point cloud upsampling, called PU-INN, which allows unconstrained architectures to learn more expressive feature transformations. Then, we propose a conditional injector to improve nonlinear transformation ability of the neural network while guaranteeing invertibility. Furthermore, a lightweight interpolator is proposed based on semantic similarity distance in the latent space, which can intuitively reflect the interpolation changes in Euclidean space. Qualitative and quantitative results show that our method outperforms the state-of-the-art works in terms of distribution uniformity, proximity-to-surface accuracy, 3D reconstruction quality, and computation efficiency.
Keywords:
Computer Vision: CV: 3D computer vision
Computer Vision: CV: Neural generative models, auto encoders, GANs  
Machine Learning: ML: Probabilistic machine learning