Unsupervised shape completion of 3D data
Unsupervised shape completion of 3D data
Unsupervised 3D Shape Completion through GAN Inversion
arXiv paper abstract https://arxiv.org/abs/2104.13366
arXiv PDf paper https://arxiv.org/pdf/2104.13366.pdf
Project Web site https://junzhezhang.github.io/projects/ShapeInversion
Most 3D shape completion approaches rely heavily on partial-complete shape pairs and learn in a fully supervised manner.
... In contrast to previous fully supervised approaches, in this paper we present ShapeInversion, which introduces Generative Adversarial Network (GAN) inversion to shape completion for the first time.
... In this way, ShapeInversion no longer needs paired training data, and is capable of incorporating the rich prior captured in a well-trained generative model.
... comparable with supervised methods that are learned using paired data.
... robust results for real-world scans and partial inputs of various forms and incompleteness levels.
... additional abilities
... such as producing multiple valid complete shapes for an ambiguous partial input ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments