# ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids

arXiv: https://arxiv.org/abs/1709.00505 · HTML: https://mlsanity.com/paper/1709.00505/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2017.

## Built on by (most cited first, 1 of 1)

- [Glimpse-Attend-and-Explore: Self-Attention for Active Visual Exploration](https://mlsanity.com/paper/2108.11717/) (2021)

## Abstract (arXiv)

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.