5 papers
ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training
Haian Jin, Rundi Wu, Tianyuan Zhang +4
Feed-forward transformer models have driven rapid progress in 3D vision, but state-of-the-art methods such as VGGT and have a computational cost that scales quadratically wi…
Neural USD: An object-centric framework for iterative editing and control
Alejandro Escontrela, Shrinu Kushagra, Sjoerd van Steenkiste +5
Amazing progress has been made in controllable generative modeling, especially over the last few years. However, some challenges remain. One of them is precise and iterative object…
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
Linyi Jin, Richard Tucker, Zhengqi Li +3
Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale superv…
MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos
Zhengqi Li, Richard Tucker, Forrester Cole +6
We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes. Most conventional stru…
Generative Image Dynamics
Zhengqi Li, Richard Tucker, Noah Snavely +1
We present an approach to modeling an image-space prior on scene motion. Our prior is learned from a collection of motion trajectories extracted from real video sequences depicting…