iCITRIS - Causal Representation Learning Datasets

<p>This repository contains the datasets from the paper &quot;iCITRIS: Causal Representation Learning for Instantaneous Temporal Effects&quot;&nbsp;(<a href="http://arxiv.org/abs/2206.06169">link</a>) by Phillip Lippe,&nbsp;Sara Magliacane,&nbsp;Sindy L&ouml;we,&nbsp;Yuki M. Asano,&nbsp;Taco Cohen,&nbsp;Efstratios Gavves.&nbsp;</p> <p><strong>Instantaneous Temporal Causal3Ident&nbsp;</strong>-&nbsp;The Temporal Causal3DIdent dataset is a collection of 3D object shapes, which are observed under varying positions, rotations, lightning, and colors. Overall, we this dataset contains&nbsp;7 (multidimensional) causal factors with instantaneous and temporal causal relations between them. The 7 shapes used are&nbsp;<a href="http://graphics.stanford.edu/data/3Dscanrep/">Armadillo</a>,&nbsp;<a href="http://graphics.stanford.edu/data/3Dscanrep/">Bunny</a>,&nbsp;<a href="https://www.cs.cmu.edu/~kmcrane/Projects/ModelRepository/#spot">Cow</a>,&nbsp;<a href="http://graphics.stanford.edu/data/3Dscanrep/">Dragon</a>,&nbsp;<a href="https://gfx.cs.princeton.edu/proj/sugcon/models/">Head</a>,&nbsp;<a href="https://www.cc.gatech.edu/projects/large_models/horse.html">Horse</a>,&nbsp;<a href="https://github.com/brendel-group/cl-ica">Teapot</a>.&nbsp;For more details on the dataset, see&nbsp;<a href="https://github.com/phlippe/CITRIS">our GitHub repository</a>.</p> <p><strong>Causal Pinball </strong>- The Causal Pinball environment implements the simplified, real-world game dynamics of Pinball. This dataset considers 5 causal variables with instantaneous effects: the paddle position left, the paddle position right, the ball (velocity and position), the state of all bumpers, and the score.&nbsp;For more details on the dataset as well as the code to generate this dataset, see&nbsp;<a href="https://github.com/phlippe/CITRIS">our GitHub repository</a>.</p>