C-Flow: conditional generative flow models for images and 3D point clouds
Document typeConference report
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Rights accessOpen Access
European Commission's projectTERRINet - The European Robotics Research Infrastructure Network (EC-H2020-730994)
Flow-based generative models have highly desirable properties like exact log-likelihood evaluation and exact latent-variable inference, however they are still in their infancy and have not received as much attention as alternative generative models. In this paper, we introduce C-Flow, a novel conditioning scheme that brings normalizing flows to an entirely new scenario with great possibilities for multi-modal data modeling. C-Flow is based on a parallel sequence of invertible mappings in which a source flow guides the target flow at every step, enabling fine-grained control over the generation process. We also devise a new strategy to model unordered 3D point clouds that, in combination with the conditioning scheme, makes it possible to address 3D reconstruction from a single image and its inverse problem of rendering an image given a point cloud. We demonstrate our conditioning method to be very adaptable, being also applicable to image manipulation, style transfer and multi-modal image-to-image mapping in a diversity of domains, including RGB images, segmentation maps, and edge masks.
© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
CitationPumarola, A. [et al.]. C-Flow: conditional generative flow models for images and 3D point clouds. A: IEEE Conference on Computer Vision and Pattern Recognition. "2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)". Institute of Electrical and Electronics Engineers (IEEE), 2020, p. 7946-7955. DOI 10.1109/CVPR42600.2020.00797.