Datasets › FlyingThings3D

FlyingThings3D

Introduced by Nikolaus Mayer et al. in A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation7 Dec 2015 archive 2025-07-28

FlyingThings3D is a synthetic dataset for optical flow, disparity and scene flow estimation. It consists of everyday objects flying along randomized 3D trajectories. We generated about 25,000 stereo frames with ground truth data. Instead of focusing on a particular task (like KITTI) or enforcing strict naturalism (like Sintel), we rely on randomness and a large pool of rendering assets to generate orders of magnitude more data than any existing option, without running a risk of repetition or saturation.

Homepage JSON

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

Papers archive 2025-07-28

No paper in the archive has a leaderboard row on this dataset; the archive counts 226 papers for it but never published that list.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

10-shot image generation Optical Flow Estimation Scene Flow Estimation Disparity Estimation

License archive 2025-07-28

Custom (research-only)

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

FlyingThings3D

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections