EcoDepth
EcoDepth copied to clipboard
[CVPR'2024] Official implementation of the paper "ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation"
Hi, I receive an error if I load the code manually this way: ```python args = argparse.Namespace() # Manually set the arguments args.min_depth = 1e-3 args.max_depth = 128 args.flip_test =...
Hello, Thank you so much for sharing this amazing work! I try to train the model with the NYU dataset. The paper says about 21 mins per epoch for 8...
added udpated infer codes and conda env instalation
please create a demo notebook on colab for demo inference
How does this method perform compared with Depth Anything? I dont see the comparison in the paper.
depth/dataloaders/base_dataset.py:37 lines image = cv2.imread(img_path) image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR) “cv2.COLOR_RGB2BGR”
Great Work! If my research involves training on other data sets. (e.g., endoscopes scenario). How can I train the model. Thanks.
Sorry for the late reply. Thanks for the help. It fixed the inference part. I was able to run inference in the size of 1000*360 as well. Can you tell...
I'm very sorry to disturb you again. I encountered a problem when reproducing your code. I commented on the following code in train.py: # if args.ckpt_path == "": # model_str...