Dataset Groups Activity Stream MegaDepth dataset The dataset used for training the D2-Net model, consisting of 327,036 image pairs with at least 50% overlap in the sparse SfM point cloud. BibTex: @dataset{Y_Ding_and_Z_Xiong_and_J_Xiong_and_Y_Cui_and_Z_Cao_2024, abstract = {The dataset used for training the D2-Net model, consisting of 327,036 image pairs with at least 50% overlap in the sparse SfM point cloud.}, author = {Y. Ding and Z. Xiong and J. Xiong and Y. Cui and Z. Cao}, doi = {10.57702/1q00ktdo}, institution = {No Organization}, keyword = {'3D reconstruction', 'computer vision', 'depth estimation', 'image formation', 'image matching', 'pose estimation', 'sparse SfM point cloud'}, month = {dec}, publisher = {TIB}, title = {MegaDepth dataset}, url = {https://service.tib.eu/ldmservice/dataset/megadepth-dataset}, year = {2024} }
