We introduce CoTracker, a transformer-based model that tracks a large number of 2D points
in long video sequences. Differently from most existing approaches that track points …

Optical flow estimation is a crucial task in computer vision that provides low-level motion
information. Despite recent advances, real-world applications still present significant …

We present a new test-time optimization method for estimating dense and long-range motion
from a video sequence. Prior optical flow or particle video tracking algorithms typically …

We introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework,
for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to …

We propose a novel multimodal video benchmark-the Perception Test-to evaluate the
perception and reasoning skills of pre-trained multimodal models (eg Flamingo, BEiT-3, or …

We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried
point on any physical surface throughout a video sequence. Our approach employs two …

Generic motion understanding from video involves not only tracking objects, but also
perceiving how their surfaces deform and move. This information is useful to make …

A classical problem in computer vision is to infer a 3D scene representation from few images
that can be used to render novel views at interactive rates. Previous work focuses on …

Existing image editing tools, while powerful, typically disregard the underlying 3D geometry
from which the image is projected. As a result, edits made using these tools may become …

We introduce Infinigen, a procedural generator of photorealistic 3D scenes of the natural
world. Infinigen is entirely procedural: every asset, from shape to texture, is generated from …