========================== 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 `_ Kubric ------ Paper: **Kubric: A scalable dataset generator** - `https://arxiv.org/abs/2203.03570 `_ Dataset link: `https://github.com/google-research/kubric `_ Kubric-NK --------- Paper: **DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework** - `https://arxiv.org/abs/2503.14880 `_ Dataset link: `https://github.com/hmorimitsu/kubric-nk `_ 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/ `_ Middlebury-ST ------------- Paper: **High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth** - `http://www.cs.middlebury.edu/~schar/papers/datasets-gcpr2014.pdf `_ Dataset link: `https://vision.middlebury.edu/stereo/data/scenes2014/ `_ 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/ `_ TartanAir --------- Paper: **TartanAir: A Dataset to Push the Limits of Visual SLAM** - `https://arxiv.org/abs/2003.14338 `_ Dataset link: `https://theairlab.org/tartanair-dataset/ `_ VIPER ----- Paper: **Playing for Benchmarks** - `http://vladlen.info/papers/playing-for-benchmarks.pdf `_ Dataset link: `https://playing-for-benchmarks.org/download/ `_