no code implementations • 4 Dec 2023 • Xiaojuan Wang, Janne Kontkanen, Brian Curless, Steve Seitz, Ira Kemelmacher, Ben Mildenhall, Pratul Srinivasan, Dor Verbin, Aleksander Holynski
We present a method that uses a text-to-image model to generate consistent content across multiple image scales, enabling extreme semantic zooms into a scene, e. g., ranging from a wide-angle landscape view of a forest to a macro shot of an insect sitting on one of the tree branches.
no code implementations • CVPR 2022 • Qianqian Wang, Zhengqi Li, David Salesin, Noah Snavely, Brian Curless, Janne Kontkanen
As output, we produce a video that smoothly interpolates the scene motion from the first photo to the second, while also producing camera motion with parallax that gives a heightened sense of 3D.
2 code implementations • 10 Feb 2022 • Fitsum Reda, Janne Kontkanen, Eric Tabellion, Deqing Sun, Caroline Pantofaru, Brian Curless
Recent methods use multiple networks to estimate optical flow or depth and a separate network dedicated to frame synthesis.
Ranked #2 on Video Frame Interpolation on Xiph-4k
no code implementations • CVPR 2021 • Edward Zhang, Ricardo Martin-Brualla, Janne Kontkanen, Brian Curless
Removing objects from images is a challenging problem that is important for many applications, including mixed reality.