Pinned
Check out our latest work, where we propose a simple and computationally efficient approach for integrating priors into dynamic reconstruction models.
Grateful for the incredible collaboration, and special thanks to @sara_oblak for leading this project!
Reconstructing dynamic scenes from video inputs is challenging due to the sparse nature of inputs, both in time and space. In our new preprint, we address this issue by introducing the ReMatching framework - a novel approach for designing and integrating deformation priors into
GIF
