DynamicDepth

DynamicDepth copied to clipboard

Pretrained Model for KITTI

2

Hi @fengziyue, thank you for your work! Could you share the pretrained weights for the KITTI dataset, too?

ldkong1205

Dynamic object masks for KITTI dataset

1

Hi, I also want to reproduce your results on KITTI dataset. Would you please share the dynamic object masks for KITTI dataset also? Hope for your reply, thanks!

Beniko95J

Training from scratch getting worse results

2

Hello, thank you for your sharing. I trained from scratch on your provided Cityscapes data for 20 epochs, but I got a worse result than manydepth, I wonder is DynamicDepth...

JunjieLiuSWU

Where is Occlusion-aware Cost Volume implemented?

8

Hi, Occlusion-aware Cost Volume is proposed in your paper, but I didn't find where it is implemented in the code, could you show me about it?

JunjieLiuSWU

How can I use inference code?

2

Hi @fengziyue, thank you for your work! Could you kindly provide some guidance or steps on how to estimate depth from any image using your model?

kj4483

Dynamic Object Motion Disentanglement (DOMD)

3

I'm sorry to bother you,but I have a question that has puzzled me.the three picture in DynamicDepth Ct-1 or Ct-1d,which one is the the true in frame t-1which one is...

757787182

Some questions about warping and test.

2

Your paper is impressive and insightful, and thanks for your excellent work. I got some question while reading your paper. 1. Why do you get the synthetic **I_{t-1}** by inverse...

whyygug

The number of cityscape dataset

3

Thank your excellent job! I found that the number of training sets is not the same as the official division. There are a certain amount of cuts (69731 vs 52619)...

Qianqian3764