List of supported datasets

The datasets below are currently natively supported by PTLFlow. You should be able to use datasets for training or testing just by calling them.

AutoFlow

Paper: AutoFlow: Learning a Better Training Set for Optical Flow - https://arxiv.org/pdf/2104.14544.pdf

Dataset link: https://autoflow-google.github.io/

Flying Chairs

Paper: FlowNet: Learning Optical Flow with Convolutional Networks - https://arxiv.org/abs/1504.06852

Dataset link: https://lmb.informatik.uni-freiburg.de/resources/datasets/FlyingChairs.en.html

Flying Chairs 2

Paper: Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation - https://arxiv.org/abs/1808.01838

Dataset link: https://lmb.informatik.uni-freiburg.de/resources/datasets/FlyingChairs.en.html

Flying Things 3D

Paper: A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation - https://arxiv.org/abs/1512.02134

Dataset link: https://lmb.informatik.uni-freiburg.de/resources/datasets/SceneFlowDatasets.en.html

HD1K

Paper: The HCI Benchmark Suite: Stereo And Flow Ground Truth With Uncertainties for Urban Autonomous Driving - http://www.cvlibs.net/projects/autonomous_vision_survey/literature/Kondermann2016CVPRWORK.pdf

Dataset link: http://hci-benchmark.org/

KITTI 2012

Paper: Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite - http://www.cvlibs.net/publications/Geiger2012CVPR.pdf

Dataset link: http://www.cvlibs.net/datasets/kitti/eval_stereo_flow.php?benchmark=flow

KITTI 2015

Papers:

Object Scene Flow - https://www.sciencedirect.com/science/article/abs/pii/S0924271617301727
Joint 3D Estimation of Vehicles and Scene Flow - https://ps.is.mpg.de/publications/menze2015isa

Dataset link: http://www.cvlibs.net/datasets/kitti/eval_scene_flow.php?benchmark=flow

Middlebury

Paper: A Database and Evaluation Methodology for Optical Flow, - https://vision.middlebury.edu/flow/floweval-ijcv2011.pdf

Dataset link: https://vision.middlebury.edu/flow/

Monkaa

Paper: A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation - https://arxiv.org/abs/1512.02134

Dataset link: https://lmb.informatik.uni-freiburg.de/resources/datasets/SceneFlowDatasets.en.html

MPI Sintel

Paper: A naturalistic open source movie for optical flow evaluation - https://files.is.tue.mpg.de/black/papers/ButlerECCV2012.pdf

Dataset link: http://sintel.is.tue.mpg.de/

Spring

Paper: Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo - https://arxiv.org/abs/2303.01943

Dataset link: https://spring-benchmark.org/