search

haofeixu / aanet

[CVPR'20] AANet: Adaptive Aggregation Network for Efficient Stereo Matching
Apache License 2.0
521 stars 100 forks source link

Directory issue #72

Closed bhaskar-glitch closed 2 years ago

bhaskar-glitch commented 2 years ago

If you would like to use the pseudo ground truth supervision introduced in our paper, you can download the pre-computed disparity on KITTI 2012 and KITTI 2015 training set here: KITTI 2012, KITTI 2015.

For KITTI 2015, you should place disp_occ_0_pseudo_gt under kitti_2015/data_scene_flow/training.

Where to put this "disp_occ_0_pseudo_gt"? and where is this "kitti_2015/data_scene_flow/training"? Please help asap!

haofeixu commented 2 years ago

Hi @bhaskar-glitch , kitti_2015/data_scene_flow/training is from kitti 2015 stereo data. You can download from here: http://www.cvlibs.net/datasets/kitti/eval_scene_flow.php?benchmark=stereo and unzip it.