Reconstructing and understanding 3D structures from a limited number of images is a
classical problem in computer vision. Traditional approaches typically decompose this task …

Most state-of-the-art point trackers are trained on synthetic data due to the difficulty of
annotating real videos for this task. However, this can result in suboptimal performance due …

We introduce MVSplat360, a feed-forward approach for 360 {\deg} novel view synthesis
(NVS) of diverse real-world scenes, using only sparse observations. This setting is …

We present a unified controllable video generation approach AnimateAnything that
facilitates precise and consistent video manipulation across various conditions, including …

Large-scale vision foundation models have demonstrated remarkable success across
various tasks, underscoring their robust generalization capabilities. While their proficiency in …

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 …

Egocentric Hand Object Interaction (HOI) videos provide valuable insights into human
interactions with the physical world, attracting growing interest from the computer vision and …

We present a unified framework capable of solving a broad range of 3D tasks. Our approach
features a stateful recurrent model that continuously updates its state representation with …

Visual 3D reconstruction enables rebuilding 3D scenes from captured images, serving as a
fundamental data source for digital earth modeling and intelligent cities. In the foundational …

We propose scaling up 3D scene reconstruction by training with synthesized data. At the
core of our work is MegaSynth, a procedurally generated 3D dataset comprising 700K …