A new pre-training method for two-view pose estimation, which is classifying each pixel as co-visible, occluded, or outside field-of-view in the other view.

We demonstrate the stability of Langevin diffusion and use it to derive the first proof of convergence for Proximal Stochastic Gradient Langevin Algorithm in a non-convex setting.

A near-optimal quantum-accelerated Monte Carlo estimator for nested expectations