While supervised methods are effective, they require extensive labeled data for training. Recently, self-supervised foundation models have been introduced to these tasks showing comparable results to supervised methods.

This method allows API users to easily generate, discover, and mix and match image concepts without prior knowledge of how to prompt the model.

We present a method that reconstructs and animates a 3D head avatar from a single-view portrait image.

We propose a Level Set Traversal algorithm that iteratively explores regions of high confidence with respect to the input space using orthogonal components of the local gradients.

Neural Information Processing Systems http://nips.cc/