HandOccNet
HandOccNet copied to clipboard
namepllet
Offical pytorch implementation of "HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network", CVPR 2022.
Thanks for your excellent work. I checked the references in FPHA part of paper and found that there are several ways to split the data. Could you give a more...
I'm working on the two datasets. I found that `mano_param` : `pose` parameters in json file are different from the original dataset's pose parameters. So I wonder what makes them...
Hi， I found that the pose parameters and the 21 hand joints in the JSON annotation file of the HO3D dataset are different from the original dataset. Can you tell...
Hi, Thank you for producing such fantastic work for the community. I followed the training instructions and trained a model of DexYCB for 25 epochs. I got very poor results:...
Hi， The paper has documented experimental results of the Pose2Mesh model on the HO3D dataset, but I found that the Pose2Mesh paper did not experiment on the HO3D dataset. Did...
Hi, Thanks for making your code publicly available, and this work is really impressive! I have tried to load the pre-trained model and found that its performance on the HO-3D...
how to do the feature map visualization like figure 2 and 7?
Hey [@namepllet](https://github.com/namepllet)! 👋 This pull request makes it possible to run your model inside a Docker environment, which makes it easier for other people to run it. We're using an...
with open('/home/hongsuk.c/Projects/HandOccNet/main/novel_object_test_list.json', 'r') as f: target_img_list_sum = json.load(f) print("TARGET LENGTH: ", len(target_img_list_sum)) Can you tell me how to download novel_object_test_list.json?
hii, worderful work, but I have some problem with testing and the given model [snapshot_demo.pth.tar](https://drive.google.com/drive/folders/1OlyV-qbzOmtQYdzV6dbQX4OtAU5ajBOa?usp=sharing). I use the pretrained model you given and test on HO3D website, but I found...
