SGDepth icon indicating copy to clipboard operation
SGDepth copied to clipboard

[ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance

Results 19 SGDepth issues
Sort by recently updated
recently updated
newest added

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...

![微信截图_20220305230046](https://user-images.githubusercontent.com/51035342/156888831-b64c739f-8657-41f9-bbf6-e24a3f47c43c.png)

i think train the model successful,i dont change anything in the code the result looks good ![image](https://user-images.githubusercontent.com/79962968/135188722-5c78446e-e96f-4a11-ad7d-d3b10132d27b.png) 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 ![image](https://user-images.githubusercontent.com/79962968/134917461-a22a3d4d-ee8e-4168-a9d1-7b4f5063c315.png) but the resultresult is not so good ![image](https://user-images.githubusercontent.com/79962968/134917532-fa260223-f013-4200-8cd5-ce3d1c0ba92d.png)

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.