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 …

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 …

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 …

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 …

Web-crawled datasets have enabled remarkable generalization capabilities in recent image-
text models such as CLIP (Contrastive Language-Image pre-training) or Flamingo, but little …

Unsupervised object-centric learning aims to represent the modular, compositional, and
causal structure of a scene as a set of object representations and thereby promises to …

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 …

BlenderProc2 is a procedural pipeline that can render realistic images for the training of
neural networks. Our pipeline can be employed in various use cases, including …