Get 3D object shape from unposed images by use semantic template feature to estimate pose with TeFF
Get 3D object shape from unposed images by use semantic template feature to estimate pose with TeFF
Learning 3D-Aware GANs from Unposed Images with Template Feature Field
arXiv paper abstract https://arxiv.org/abs/2404.05705
arXiv PDF paper https://arxiv.org/pdf/2404.05705.pdf
Project page https://xdimlab.github.io/TeFF
Collecting accurate camera poses of training images … serve the learning of 3D-aware generative adversarial networks (GANs) yet can be quite expensive in practice.
This work targets learning 3D-aware GANs from unposed images … propose to perform on-the-fly pose estimation of training images with a learned template feature field (TeFF).
… in addition to a generative radiance field as in previous approaches … generator to also learn a field from 2D semantic features while sharing the density from the radiance field.
… framework … acquire a canonical 3D feature template leveraging the dataset mean discovered by the generative model, and … estimate the pose parameters on real data.
… demonstrate the superiority of … approach over state-of-the-art alternatives from both the qualitative and the quantitative perspectives.
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
