Zhaohuai Liang

Hi,thank you very much for your great work! But there may be a small mistake in your metric code. Refer to Kitti benchmark for the definition of ‘D1’ is percentage...

About the image size testing on Scene Flow datasets.

1

Hi,thank you very much for your great work! The image size to test SceneFlow datasets in your paper is 960x540,  But in your code (sceneflow_dataset.py line 61), it's 960x512...

Whether to submit GraftNet to KITTI BenchMark?

2

Hi,thank you very much for your great work，Whether to submit GraftNet to KITTI BenchMark? I didn't find it on KITTI BechMark(Stereo Evaluation 2012&2015) although I have run it.

About the generalization experiment.

2

Hi, Thanks a lot for your great work. It can be seen from your paper that you are aiming to enhance the generalization ability of the model, but there is...

See the title

# Summary Currently, the pipeline of updating documents in the knowledge base is to delete the old documents first, and then build the index of the new documents. However, this...