DPVO
DPVO copied to clipboard
princeton-vl
Deep Patch Visual Odometry
Hello, I have a custom dataset. I want to fine-tune DPVO on this. What are the layers those I can un-freeze for fine-tuning? And also should I change any training...
 I think I run the setup stuff well. But when I run demo, it dosent work.I realy dont know why.Call for help.
Hi, @zachteed @lahavlipson, sorry to bother you again. After almost one-week-long, I made some breakthroughs. After I created the virtual environment on my Ubunutu20.04 and succeeded in installing CUDA 11.8...
Hello, I reimplement the model exactly following the training method introduced in the paper.The results of my implementation are almost equal to those on the tartan dataset (within 10%).But my...
Thank you for open sourcing your excellent work. I encountered some problems during training. For one of the sequences, my path is as follows： ～/datasets/TartanAir/abandonedfactory/Easy/depth_left/abandonedfactory/EasyP000/depth_left/xxxx.npy ~/datasets/TartanAir/abandonedfactory/Easy/image_left/abandonedfactory/Easy/P000/image_left/xxxx.png How can I rearrange...
Hi, I believe there is an issue with the trajectory saving that comes from the way the trajectory is created. Here (https://github.com/princeton-vl/DPVO/blob/main/dpvo/plot_utils.py#L14) when the trajectory is created from the poses...
Hi, thanks for your amazing work. Could you please tell me the coordinate system in the predicted pose file? Colmap ( x right, y down, z forward), Blender(x right, y...
Hi! I am trying to train the model using the python `train.py --steps=240000 --lr=0.00008 --name=` command, but for the steps parameter I use 10000 instead of 240000. Toward the end...
Hi @lahavlipson , have you tried training DPVO on other datasets beside TartanAir? I tried to train it on TUM (using _build_dataset from raw RGB and depth maps), but all...
Hi everyone, seems like the root server of TartanAir is down...So does anyone saved the TartanAir before and can share with google drive or other methods? Thank you so much!!!!!!