-
thanks for your great work
我跑按照您的指导, 把nyuv2训练集和测试集分开放, 然后分别存rgb文件和depth, rgb里面存的是.png格式的原图, depth文件夹里面存的是.png格式的深度图, 然后会报错, 错误提示如下, 麻烦作者帮忙看看
/home/xsh/anaconda3/envs/arc/bin/python /home/xsh/ARC/tra…
-
## Location
* Remote
## Salary Expectation
* $5000/month
## Requirements
* Experience with OpenPose or related 3D pose estimation algorithms
* Solid grasp of 3D geometry and linear al…
-
Hi @hurjunhwa those configs seem not be used in main.py
```
--training_dataset_root=$KITTI_RAW_HOME \
--training_dataset_flip_augmentations=True \
--training_dataset_preprocessing_crop=True \
--t…
-
-
In your paper you mentioned:
> We also train a monocular depth estimation network that is semi-supervised using a combination of the Holopix50k and Megadepth datasets
Can you open source this trai…
-
Hello! Nice work! But i have a question, when i read your paper, i notice that you said your work can improve 3D pose estimation from monocular images. **So i want to know how to combine your work wit…
-
Over the last week I have been porting my code on monocular depth estimation to Pytorch-Lightning, and everything is working perfectly. However, my models seem to require more GPU memory than before, …
-
Hello, chenyilun95!
Thanks for your great work of monocular 3D object detection. After watch your demo, I am confused about the right_bottom BEV point cloud, is it original velodyne point cloud …
-
I re-implemented MonoDepth2 according to your paper, but my training loss never decreases. It's too easy to miss important implementation details, since they are scattered across various sections of t…
-
Like the following picture.The network seems to learn the structure well,but the distance is not learned well.The depth in the distance seems to be similar to that in the near place.What's the reason …