Yu Rong, Ziwei Liu, Cheng Li, Kaidi Cao, Chen Change Loy

• paper.
• Project Page
  
  
  

Part of the code is inspired by Pytorch-CycleGAN and HMR. Thanks the contributions of their authors.

Please refer to install.md to install the required packages and code.

• Clone this repo

git clone [email protected]:penincillin/DCT_ICCV-2019.git
cd DCT_ICCV-2019

Download processed datasets, demo images and pretrained weights and models from Google Drive, uznip it and place it in the root directory of DCT_ICCV-2019.

Before training starts, to visualize the training results and the loss curve, please run python -m visdom.server 8097 and click the URL http://localhost:8097

sh script/train_all_img.sh

sh script/train_all_img_iuv.sh

sh script/train_up3d_img_3d_dp.sh

sh script/train_up3d_img_dp.sh

sh script/train_up3d_img_iuv_3d_dp.sh

sh script/train_up3d_img_iuv_dp.sh

sh script/test_up3d_img.sh

sh script/test_up3d_img_iuv.sh

After run evaluation code, the results are stored in DCT_ICCV-2019/evaluate_results. To visualize the results, run

sh script/visualize.sh

The generated images are stored in DCT_ICCV-2019/evaluate_results/images.

To run the model on your own images, just center crop the images according to each person.
Then update the content of image list file stored in DCT_ICCV-2019/dct_data/demo/img_list.txt.

To run inference for the pre-processed images, please checkout to the inference branch first.
Remember to commit the current changes you made in master branch first.

Run inference code:

sh script/infer.sh

The results are stored in DCT_ICCV-2019/inference_results. To further visualize the results, run visualization code:

sh script/visualize.sh

The generated images are stored in DCT_ICCV-2019/inference_results/images.

Please cite the paper in your publications if it helps your research:

@inproceedings{Rong_2019_ICCV,
  author = {Rong, Yu and Liu, Ziwei and Li, Cheng and Cao, Kaidi and Loy, Chen Change},
  title = {Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild},
  booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
  month = {October},
  year = {2019}
  }