Unsupervised learning with generative models has the potential of discovering rich
representations of 3D scenes. While geometric deep learning has explored 3D-structure …

Neural Processes (NPs)(Garnelo et al 2018a; b) approach regression by learning to map a
context set of observed input-output pairs to a distribution over regression functions. Each …

Recent work on the representation of functions on sets has considered the use of summation
in a latent space to enforce permutation invariance. In particular, it has been conjectured that …

Stationary stochastic processes (SPs) are a key component of many probabilistic models,
such as those for off-the-grid spatio-temporal data. They enable the statistical symmetry of …

We present a general-purpose framework for image modelling and vision tasks based on
probabilistic frame prediction. Our approach unifies a broad range of tasks, from image …

Neural Processes combine the strengths of neural networks and Gaussian processes to
achieve both flexible learning and fast prediction in stochastic processes. However, a large …

Many real-world situations allow for the acquisition of additional relevant information when
making an assessment with limited or uncertain data. However, traditional ML approaches …

The recent success of implicit neural scene representations has presented a viable new
method for how we capture and store 3D scenes. Unlike conventional 3D representations …

A crucial ability of human intelligence is to build up models of individual 3D objects from
partial scene observations. Recent works either achieve object-centric generation but …

When tasks change over time, meta-transfer learning seeks to improve the efficiency of
learning a new task via both meta-learning and transfer-learning. While the standard …