-
I trained a model using this code and Kitti dataset, without any parameter modified.
One of the test result is shown as fig 1.
![fig1](https://user-images.githubusercontent.com/26050577/78764188-…
-
Dear Author,
Thank you for your sharing.
When searching in your project, I could not find the GANet-15.py.
Could you provide your GANet-15 model? thanks very much
-
hi thanks for releasing your wonderful work! the depth map come from PSMnet as mentioned in introduction page. I wonder have you ever post-processed the depth of PSMnet such as re-scale or you just d…
-
From the video you provide, I find that It is not smooth . So I want to know if the coordinates of 8 bbox corners in 3d space can be regressed well.
Thanks
-
I have looked at the KITTI Stereo 2012 dataset, which features parts of the KITTI VO dataset. I conclude that they are part of the same set. This means that I can just use the pretrained 2012 model.
…
-
In your paper, Table 2 shows the Param. comparison results among different cost aggregation methods, and we can see that GANet has fewer param. than that of PSMNet.
However, it seems that GANet nee…
-
Thanks for sharing your code on github. I ran into some problems while running your code on my laptop, am i able to run finetune.py or submission.py without CUDA installed? While running submission.p…
-
Firstly, thank you for publishing your code.
I used your pre-trained model on KITTI2012(best.ckpt) to evaluate the validation set of kitti2012(14 pairs of images) and found the following results: fo…
-
file run_submission.sh:
```
python submission.py --datapath ../../2.Data/KITTI/data_scene_flow/testing/ \
--loadmodel ../../2.Data/KITTI/pretrained_model_KITTI2015.tar \
```
…
-
Hello, thank you for this work and well documented code. Our project uses a stereo pair and we are trying to find a network that can perform stereo matching to compute disparity maps (for metric depth…