LapDepth-release
LapDepth-release copied to clipboard
tjqansthd
Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals
I am currently trying the network trained on the NYU dataset on a separate dataset (TUM RGBD desk see: https://vision.in.tum.de/data/datasets/rgbd-dataset/download#freiburg2_desk) I would have expected to get a similar performance but...
Hello,I don't understand how to get the real distance from the "out" in demo.py .What model I used is trained from KITTI.Could you please tell me how to get it...
Hello, I just run the train.py script and I am getting the following error: File "/home/raai/sparse-to-dense/train_main.py", line 356, in main() File "/home/raai/sparse-to-dense/train_main.py", line 269, in main model = LDRN() File...
hello，it's a very good work.And l have a question on it's precision with resnet18
Thanks for your share. Now I have got the depth image, but I do not know how to get the real distance. May I need a scale to make a...
I am currently working on a project that involves deploying deep learning models on edge devices. Due to the computational constraints of these devices, I am in search of lightweight...
Dear authors, I read the code and found out that in the validate() function, you have this part: ``` input_img = rgb_data input_img_flip = torch.flip(input_img,[3]) with torch.no_grad(): _, output_depth =...
Why do you need to integrate horizontal and vertical directions because depth data is sparse?
