Tracking everything everywhere all at once
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 …
from a video sequence. Prior optical flow or particle video tracking algorithms typically …
Pointodyssey: A large-scale synthetic dataset for long-term point tracking
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 …
for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to …
Tap-vid: A benchmark for tracking any point in a video
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 …
perceiving how their surfaces deform and move. This information is useful to make …
Scene representation transformer: Geometry-free novel view synthesis through set-latent scene representations
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 …
that can be used to render novel views at interactive rates. Previous work focuses on …
Tapir: Tracking any point with per-frame initialization and temporal refinement
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 …
point on any physical surface throughout a video sequence. Our approach employs two …
Object 3dit: Language-guided 3d-aware image editing
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 …
from which the image is projected. As a result, edits made using these tools may become …
Quality not quantity: On the interaction between dataset design and robustness of clip
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 …
text models such as CLIP (Contrastive Language-Image pre-training) or Flamingo, but little …
Simple unsupervised object-centric learning for complex and naturalistic videos
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 …
causal structure of a scene as a set of object representations and thereby promises to …
Infinite photorealistic worlds using procedural generation
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 …
world. Infinigen is entirely procedural: every asset, from shape to texture, is generated from …
Blenderproc2: A procedural pipeline for photorealistic rendering
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 …
neural networks. Our pipeline can be employed in various use cases, including …