input point
Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions
Learning distance functions between complex objects, such as the Wasserstein distance to compare point sets, is a common goal in machine learning applications. However, functions on such complex objects (e.g., point sets and graphs) are often required to be invariant to a wide variety of group actions e.g.
Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State Segmentation
Minerals in rocks, sediment in soil, dust on surfaces, infection on leaves, stains on fabrics, and foam in liquids are some of these almost infinite numbers of states and patterns.
PointCNN: Convolution On X-Transformed Points
Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, Baoquan Chen
Neural Information Processing Systems http://nips.cc/
Differentially Private k-Means with Constant Multiplicative Error
Neural Information Processing Systems http://nips.cc/
Point-Cloud Completion with Pretrained Text-to-image Diffusion Models Y oni Kasten
Here, we leverage recent advances in text-guided 3D shape generation, showing how to use image priors for generating 3D objects.
Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions
However, functions on such complex objects (e.g., point sets and graphs) are often
