Timezone: »

Continuous Surface Embeddings
Natalia Neverova · David Novotny · Marc Szafraniec · Vasil Khalidov · Patrick Labatut · Andrea Vedaldi

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #478

In this work, we focus on the task of learning and representing dense correspondences in deformable object categories. While this problem has been considered before, solutions so far have been rather ad-hoc for specific object types (i.e., humans), often with significant manual work involved. However, scaling the geometry understanding to all objects in nature requires more automated approaches that can also express correspondences between related, but geometrically different objects. To this end, we propose a new, learnable image-based representation of dense correspondences. Our model predicts, for each pixel in a 2D image, an embedding vector of the corresponding vertex in the object mesh, therefore establishing dense correspondences between image pixels and 3D object geometry. We demonstrate that the proposed approach performs on par or better than the state-of-the-art methods for dense pose estimation for humans, while being conceptually simpler. We also collect a new in-the-wild dataset of dense correspondences for animal classes and demonstrate that our framework scales naturally to the new deformable object categories.

Author Information

Natalia Neverova (Facebook AI Research)
David Novotny (Facebook AI Research)
Marc Szafraniec (Facebook AI Research)
Vasil Khalidov (Facebook AI Research)
Patrick Labatut (Facebook AI Research)
Andrea Vedaldi (University of Oxford / Facebook AI Research)

More from the Same Authors