Pix2Shape: towards unsupervised learning of 3D scenes from images using a view-based representation

DOI10.1007/s11263-020-01322-1zbMath1483.68445arXiv2003.14166OpenAlexW3098589080MaRDI QIDQ2056096

David Vazquez, Aaron Courville, Fahim Mannan, Sai Rajeswar, Jérôme Parent-Lévesque, Florian Golemo, Derek Nowrouzezahrai

Publication date: 1 December 2021

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2003.14166

zbMATH Keywords

computer vision3D understandingadversarial trainingdifferentiable rendering

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Machine vision and scene understanding (68T45)

Related Items (1)

Pix2Shape

Uses Software

• OpenDR
• ShapeNet
• FiLM
• nuScenes
• FrameNet
• HoloGAN
• SoftRas
• "3"D-R2N2
• Wasserstein GAN
• Make3D

Cites Work

• Unnamed Item

This page was built for publication: Pix2Shape: towards unsupervised learning of 3D scenes from images using a view-based representation