@article{jayaraman2018shapecodes,
  title = {Shapecodes: self-supervised feature learning by lifting views to viewgrids},
  author = {{Jayaraman}, {Dinesh} and Gao, Ruohan and Grauman, Kristen},
  journal = {ECCV},
  year = {2018},
  month = {Sep},
  pub_type = {conference},
  abstract = {We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation. The main idea is a self-supervised training objective that, given only a single 2D image, requires all unseen views of the object to be predictable from learned features. We implement this idea as an encoder-decoder convolutional neural network. The network maps an input image of an unknown category and unknown viewpoint to a latent space, from which a deconvolutional decoder can best "lift" the image to its complete viewgrid showing the object from all viewing angles. Our class-agnostic training procedure encourages the representation to capture fundamental shape primitives and semantic regularities in a data-driven manner---without manual semantic labels. Our results on two widely-used shape datasets show 1) our approach successfully learns to perform "mental rotation" even for objects unseen during training, and 2) the learned latent space is a powerful representation for object recognition, outperforming several existing unsupervised feature learning methods.},
  url_pdf = {/publication/jayaraman-2018-shapecodes/jayaraman-2018-shapecodes.pdf},
  url = {https://arxiv.org/abs/1709.00505},
  url_arxiv = {https://arxiv.org/abs/1709.00505},
}