SGDepth
SGDepth copied to clipboard
[ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
Hi, i wonder how can i get the segmentation groundtruth of kitti stereo 2015 dataset? There's something wrong when I evaluate the segmentation performance on Kitti stereo 2015 dataset. Thanks...

i think train the model successful,i dont change anything in the code the result looks good  it is about 10 epoch result but the a1 a2 a3 rmse and...
Hi, Thanks for sharing the awesome work. I use the kitti_zhou_split training split provided by you [here](https://drive.google.com/drive/folders/1sLJQM3VZWFG44lHbPaTnr6EVu3d3ksMX?usp=sharing). It contains *21880* training images from each left and right camera. But the...
Hi there! I hope you are doing well. I was trying to understand the data acquisition pipeline of the project here. I am a student and for me it is...
i think may be use -2 -1 0 1 2 would be better so i change the code  but the resultresult is not so good 
Hello, I have encountered this problem, but I don’t know how to solve it. I hope you can give me some help. Thank you very much. python3 train.py --model-name zhou_full...
Could I know whether you use the KITTI semantic labels for the training? I guess you only use the semantic labels on Cityscapes. Thank you for your work.