Talk Title: Learning 3D Representations with Capsules & Beyond Speaker: Tolga Birdal, Stanford University Abstract: 3D data is arguably the most expressive digital storage for the real physical objects around us. However, it has been repeatedly shown that a flat grid, such as the pixels underlying 2D images, may not be the best encoding for many applications. This brings an additional challenge to 3D machine learning, namely deducing useful and faithful representations from the raw…