Datasets

Datasets

การแนะนำรายละเอียด

Pattern Recognition and Image Processing

Freiburg-Berkeley Motion Segmentation Dataset

Optical Flow Datasets: Flying Chairs, ChairsSDHom

--

--

Optical Flow Datasets: FlyingChairs, ChairsSDHom

--

The Flying Chairs are a synthetic dataset with optical flow ground truth. It consists of 22872 image pairs and corresponding flow fields. Images show renderings of 3D chair models moving in front of random backgrounds from Flickr. Motions of both the chairs and the background are purely planar.

This dataset has been used for training convolutional networks in the ICCV 2015 paperFlowNet: Learning Optical Flow with Convolutional Networks.

The dataset is provided for research purposes only and without any warranty. Any commercial use is prohibited. If you use the dataset in your research, you should cite theaforementioned paper.

@InProceedingsDFIB15, author = A. Dosovitskiy and P. Fischer and E. Ilg and P. H\ausser and C. Haz\irba\cs and V. Golkov and P. v.d. Smagt and D. Cremers and T. Brox, title = FlowNet: Learning Optical Flow with Convolutional Networks, booktitle = IEEE International Conference on Computer Vision (ICCV), month = , year = 2015, url =

Flying chairs train-validation split(1 - train, 2 - validation)

Sintel train-validation split(1 - train, 2 - validation)

The Flying Chairs 2 dataset is generated using the same settings as the Flying Chairs dataset, but contains additional modalities that were used to train the networks in the paperOcclusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation.

First and second image (suffixes _img_0 and _img_1)

First and second image object IDs (suffixes _oids_0 and _oids_1)

Forward and backward optical flow (suffixes _flow_01 and _flow_10)

Forward and backward occlusions (suffixes _occ_01 and _occ_10)

Forward and backward occlusion weights (computed according to the paper; suffixes _occ_weights_01 and _occ_weights_10)

Forward and backward motion boundaries (suffixes _mb_01 and _mb_10)

Forward and backward motion boundary weights (computed according to the paper; suffixes _mb_weights_01 and _mb_weights_10)

The dataset is provided for research purposes only and without any warranty. Any commercial use is prohibited. If you use the dataset in your research, you should cite the following two papers:

@InProceedingsDFIB15, author = A. Dosovitskiy and P. Fischer and E. Ilg and P. H\ausser and C. Haz\irba\cs and V. Golkov and P. v.d. Smagt and D. Cremers and T. Brox, title = FlowNet: Learning Optical Flow with Convolutional Networks, booktitle = IEEE International Conference on Computer Vision (ICCV), month = , year = 2015, url =

@InProceedingsISKB18, author = E. Ilg and T. Saikia and M. Keuper and T. Brox, title = Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation, booktitle = European Conference on Computer Vision (ECCV), month = , year = 2018, url =

Download the Flying Chairs 2 dataset

ChairsSDHom is a synthetic dataset with optical flow ground truth. Designed to be robust to untextured regions and to produce flow magnitude histograms close to those of the UCF101 dataset, ChairsSDHom is a good candidate for training if you want your optical flow method to work well on real-world data and generally rather small displacements. The dataset is abstract enough to not overfit to any realistic scenario, so even if you have specialized data, ChairsSDHom may still serve as good additional or pretraining data.

This dataset has been used for training convolutional networks in the CVPR 2017 paperFlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks.

The dataset is provided for research purposes only and without any warranty. Any commercial use is prohibited. If you use the dataset in your research, you should cite theaforementioned paper.

@InProceedingsIMKDB17, author = E. Ilg and N. Mayer and T. Saikia and M. Keuper and A. Dosovitskiy and T. Brox, title = FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks, booktitle = IEEE Conference on Computer Vision and Pattern Recognition (CVPR), month = Jul, year = 2017, url =

The extended version contains the same flows and images, but also additional modalities that were used to train the networks in the paperOcclusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation.

First and second image (suffixes _img_0 and _img_1)

First and second image object IDs (suffixes _oids_0 and _oids_1)

Forward optical flow (suffix _flow_01)

Forward occlusions (suffix _occ_01)

Forward occlusion weights (computed according to the paper; suffix _occ_weights_01)

Forward motion boundaries (suffix _mb_01)

Forward motion boundary weights (computed according to the paper; suffix _mb_weights_01)

The dataset is provided for research purposes only and without any warranty. Any commercial use is prohibited. If you use the dataset in your research, you should cite the following two papers:

@InProceedingsIMKDB17, author = E. Ilg and N. Mayer and T. Saikia and M. Keuper and A. Dosovitskiy and T. Brox, title = FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks, booktitle = IEEE Conference on Computer Vision and Pattern Recognition (CVPR), month = Jul, year = 2017, url =

@InProceedingsISKB18, author = E. Ilg and T. Saikia and M. Keuper and T. Brox, title = Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation, booktitle = European Conference on Computer Vision (ECCV), month = , year = 2018, url =

Download the ChairsSDHom extended dataset

For questions, please contactNikolaus Mayer().

Copyright © 2002-2022 Thb999 All Rights Reserved

无法在这个位置找到: right.htm