fangchangma / self-supervised-depth-completion

ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera"
MIT License
626 stars 134 forks source link

More Information #1

Closed Cindy-xdZhang closed 5 years ago

Cindy-xdZhang commented 6 years ago

Hi, i m curious about your work. i have already read your paper . Is there anything new? When will you update the repository?

fangchangma commented 6 years ago

Hi. We are cleaning up the code and plan to release all the code/data around mid-Sept.

Cindy-xdZhang commented 6 years ago

Thanks. Looking forward to it.

fangchangma commented 6 years ago

Quick update: I might have to push back the code release, hopefully by mid-October..

SebasRatz commented 6 years ago

Hi, I am also interested in your work! Looking forward to the code being released

zhby99 commented 6 years ago

Hi, I am also interested in your work! Looking forward to the code being released

same here, looking forward to the code!

zouhongwei commented 6 years ago

Hi, I am also interested in your work! Looking forward to the code being released

LingerWang commented 6 years ago

Another looking forward to your updating

MichaleGo commented 6 years ago

Looking forward to releasing you code soon

Usernamezhx commented 6 years ago

Looking forward to releasing you code soon

OscarMind commented 5 years ago

Hi, I am also interested in your work! Looking forward to the code being released

ialhashim commented 5 years ago

Any update on the code?

Hansry commented 5 years ago

Hello, any update on the code?

tartavull commented 5 years ago

+1

fangchangma commented 5 years ago

The network definition and a trained model have been released. I'll put out the complete code and the other trained models later.

wuheng199112068 commented 5 years ago

An error occurred when entering such a parameter on the command line,what can we input about [checkpoint -path]?Can you give us an example? Thank you

Namespace(batch_size=1, criterion='l2', epochs=11, evaluate='[checkpoint-path]', i nput='gd', jitter=0.1, layers=34, lr=1e-05, pretrained=False, print_freq=10, rank_metric='rmse', result='..\results', resume='', start_epoch=0, train_mode='dense', use_d=True, use_g=True, use_pose=False, use_rgb=False, val='select', w1=0, w2=0, weight_decay=0, workers=4) => no model found at '[checkpoint-path]'