@InProceedings{AlbertSuso2021,
author="Albert Suso
and Pau Riba
and Oriol Ramos Terrades
and Josep Llados",
title="A Self-supervised Inverse Graphics Approach for Sketch Parametrization",
booktitle="16th International Conference on Document Analysis and Recognition",
year="2021",
volume="12916",
pages="28--42",
abstract="The study of neural generative models of handwritten text and human sketches is a hot topic in the computer vision field. The landmark SketchRNN provided a breakthrough by sequentially generating sketches as a sequence of waypoints, and more recent articles have managed to generate fully vector sketches by coding the strokes as B{\'e}zier curves. However, the previous attempts with this approach need them all a ground truth consisting in the sequence of points that make up each stroke, which seriously limits the datasets the model is able to train in. In this work, we present a self-supervised end-to-end inverse graphics approach that learns to embed each image to its best fit of B{\'e}zier curves. The self-supervised nature of the training process allows us to train the model in a wider range of datasets, but also to perform better after-training predictions by applying an overfitting process on the input binary image. We report qualitative an quantitative evaluations on the MNIST and the Quick, Draw! datasets.",
optnote="DAG; 600.121",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3675), last updated on Fri, 26 Aug 2022 12:56:23 +0200",
opturl="https://link.springer.com/chapter/10.1007/978-3-030-86198-8_3"
}