This software provides a general framework for point cloud/mesh registration based on robust optimal mass transport (robOT) / unbalanced optimal mass transport. It supports both optimization- and learning-based registration approaches. It also provides a general framework for deep prediction tasks, e.
This software allows for interactive image segmentation. We aim to develop SimpleClick as a practical tool for interactive image segmentation, editing, and generation.
The SimpleClick repository can be found here: https://github.
This software uses a learning framework (YETI) building on an auto-encoder structure between 2D and 3D image time-series, which incorporates an advection-diffusion model to capture blood perfusion. To help with identifiability, the deep learning model is trained via simulated data from an advection-diffusion simulator.
Deep learning models struggle with compositional generalization, i.e. the ability to recognize or generate novel combinations of observed elementary concepts. In hopes of enabling compositional generalization, various unsupervised learning algorithms …
Interactive image segmentation has been widely applied to obtain high-quality voxel-level labels for medical images. The recent success of Transformers on various vision tasks has paved the road for developing Transformer-based interactive image …
We study the excess capacity of deep networks in the context of supervised classification. That is, given a capacity measure of the underlying hypothesis class – in our case, empirical Rademacher complexity – to what extent can we (a priori) …
Click-based interactive image segmentation aims at extracting objects with a limited user clicking. A hierarchical backbone is the de-facto architecture for current methods. Recently, the plain, non-hierarchical Vision Transformer (ViT) has emerged …
This work investigates the use of robust optimal transport (OT) for shape matching. Specifically, we show that recent OT solvers improve both optimization-based and deep learning methods for point cloud registration, boosting accuracy at an …
Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks. However, recent works show that one can directly …
Learning maps between data samples is fundamental. Applications range from representation learning, image translation and generative modeling, to the estimation of spatial deformations. Such maps relate feature vectors, or map between feature spaces. …