example for 3d numpy array registration? about geomloss HOT 4 CLOSED

---Original--- From: "jeanfeydy"<[email protected]> Date: Wed, May 29, 2019 17:55 PM To: "jeanfeydy/geomloss"<[email protected]>; Cc: "coldgemini"<[email protected]>;"Mention"<[email protected]>; Subject: Re: [jeanfeydy/geomloss] example for 3d numpy array registration? (#3) Hi @coldgemini , All the examples in the gallery work fine in 3D: the tutorials are written the way they are because it is easier for me to show what is happening with 2D toy examples, but there really isn't any technical limitation as far as GeomLoss is concerned. See for instance the tutorial on color transfer, which is a simple 3D point cloud registration in the unit RGB cube. Going further, I will implement higher-level loss functions over the summer (such as varifold kernel and OT losses for 3D meshes), and write self-contained rigid or spline registration examples. Before working on it, I just have to release KeOps v1.1 first! Note, however, that unlike KeOps, GeomLoss will not support raw numpy input: the native support of automatic differentiation by PyTorch is a key feature that allowed me to considerably trim down the GeomLoss interface. It really should be favored over numpy for any kind of intensive application, and is on the verge of becoming a new standard for computational anatomy - my main motivation. Best regards, Jean — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.