A computer vision and deep learning researcher.
A novel approach which jointly optimizes a canonical time and pose configuration coupled with temporal and cyclic consistency constraints providing high quality outputs as the observed views become sparser.
Emergent communication via mid-level patches in a referential game played on a large-scale image dataset.
Bo He's Personal Website
Hanyu Wang
Gowthami Somepalli's webpage
Chop & Learn
FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Views
Anubhav