Publication
C-Flow: Conditional generative flow models for images and 3D point clouds
Conference Article
Conference
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Edition
2020
Pages
7946-7955
Doc link
https://doi.org/10.1109/CVPR42600.2020.00797
File
Authors
-
Pumarola Peris, Albert
-
Popov, Stefan
-
Moreno Noguer, Francesc
-
Ferrari, Vittorio
Projects associated
Abstract
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.
Categories
computer vision.
Scientific reference
A. Pumarola, S. Popov, F. Moreno-Noguer and V. Ferrari. C-Flow: Conditional generative flow models for images and 3D point clouds, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, Seattle, WA, USA (Virtual), pp. 7946-7955.
Follow us!