A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Geometric Capsule Autoencoders group 3D points into parts and objects.
Deep 3D models are vulnerable to isometry transformations under adversarial attacks.
Paper tackles unsupervised learning of 3D shapes from single images.
We introduce a scalable approach for object pose estimation trained on simulated RGB views of multiple 3D models together. We learn an encoding of object views that does not only describe an implicit orientation of all objects seen during training, but can also relate views of untrained objects. Our single-encoder-mult…
Mapper-GIN simplifies 3D point cloud classification with lightweight structure.
InSphereNet uses infilling spheres for 3D object classification, improving accuracy with fewer parameters.
New method escapes local optima in neural architecture optimization.
Generative Adversarial Networks (GAN) can achieve promising performance on learning complex data distributions on different types of data. In this paper, we first show a straightforward extension of existing GAN algorithm is not applicable to point clouds, because the constraint required for discriminators is undefined…