├── .gitignore ├── LICENSE ├── README.md ├── configs ├── default.py ├── pose2pose.yaml ├── voice2pose_s2g.yaml ├── voice2pose_sdt_bp.yaml └── voice2pose_sdt_vae.yaml ├── core ├── datasets │ ├── __init__.py │ ├── gesture_dataset.py │ └── speakers_stat.py ├── networks │ ├── __init__.py │ ├── building_blocks.py │ ├── keypoints_generation │ │ ├── discriminator.py │ │ └── generator.py │ └── poses_reconstruction │ │ └── autoencoder.py ├── pipelines │ ├── __init__.py │ ├── pose2pose.py │ ├── trainer.py │ └── voice2pose.py └── utils │ ├── audio_processing.py │ ├── fgd.py │ ├── keypoint_visualization.py │ └── video_processing.py ├── data_preprocess ├── 1_1_change_fps.py ├── 1_2_video2frames.py ├── 2_1_gen_kpts.py ├── 2_2_remove_outlier.py ├── 2_3_rescale_shoulder_width.py ├── 3_1_generate_clips.py ├── 3_2_split_train_val_test.py ├── 4_1_calculate_mean_std.py ├── 4_2_parse_mean_std_npz.py └── generate_dataset_utils.py ├── demo_audio.wav ├── iccv2021_sdt.jpg ├── main.py ├── pose_definition.md ├── pose_definition.png └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/README.md -------------------------------------------------------------------------------- /configs/default.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/configs/default.py -------------------------------------------------------------------------------- /configs/pose2pose.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/configs/pose2pose.yaml -------------------------------------------------------------------------------- /configs/voice2pose_s2g.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/configs/voice2pose_s2g.yaml -------------------------------------------------------------------------------- /configs/voice2pose_sdt_bp.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/configs/voice2pose_sdt_bp.yaml -------------------------------------------------------------------------------- /configs/voice2pose_sdt_vae.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/configs/voice2pose_sdt_vae.yaml -------------------------------------------------------------------------------- /core/datasets/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/datasets/__init__.py -------------------------------------------------------------------------------- /core/datasets/gesture_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/datasets/gesture_dataset.py -------------------------------------------------------------------------------- /core/datasets/speakers_stat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/datasets/speakers_stat.py -------------------------------------------------------------------------------- /core/networks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/networks/__init__.py -------------------------------------------------------------------------------- /core/networks/building_blocks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/networks/building_blocks.py -------------------------------------------------------------------------------- /core/networks/keypoints_generation/discriminator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/networks/keypoints_generation/discriminator.py -------------------------------------------------------------------------------- /core/networks/keypoints_generation/generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/networks/keypoints_generation/generator.py -------------------------------------------------------------------------------- /core/networks/poses_reconstruction/autoencoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/networks/poses_reconstruction/autoencoder.py -------------------------------------------------------------------------------- /core/pipelines/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/pipelines/__init__.py -------------------------------------------------------------------------------- /core/pipelines/pose2pose.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/pipelines/pose2pose.py -------------------------------------------------------------------------------- /core/pipelines/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/pipelines/trainer.py -------------------------------------------------------------------------------- /core/pipelines/voice2pose.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/pipelines/voice2pose.py -------------------------------------------------------------------------------- /core/utils/audio_processing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/utils/audio_processing.py -------------------------------------------------------------------------------- /core/utils/fgd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/utils/fgd.py -------------------------------------------------------------------------------- /core/utils/keypoint_visualization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/utils/keypoint_visualization.py -------------------------------------------------------------------------------- /core/utils/video_processing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/core/utils/video_processing.py -------------------------------------------------------------------------------- /data_preprocess/1_1_change_fps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/data_preprocess/1_1_change_fps.py -------------------------------------------------------------------------------- /data_preprocess/1_2_video2frames.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/data_preprocess/1_2_video2frames.py -------------------------------------------------------------------------------- /data_preprocess/2_1_gen_kpts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/data_preprocess/2_1_gen_kpts.py -------------------------------------------------------------------------------- /data_preprocess/2_2_remove_outlier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/data_preprocess/2_2_remove_outlier.py -------------------------------------------------------------------------------- /data_preprocess/2_3_rescale_shoulder_width.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/data_preprocess/2_3_rescale_shoulder_width.py -------------------------------------------------------------------------------- /data_preprocess/3_1_generate_clips.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/data_preprocess/3_1_generate_clips.py -------------------------------------------------------------------------------- /data_preprocess/3_2_split_train_val_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/data_preprocess/3_2_split_train_val_test.py -------------------------------------------------------------------------------- /data_preprocess/4_1_calculate_mean_std.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/data_preprocess/4_1_calculate_mean_std.py -------------------------------------------------------------------------------- /data_preprocess/4_2_parse_mean_std_npz.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/data_preprocess/4_2_parse_mean_std_npz.py -------------------------------------------------------------------------------- /data_preprocess/generate_dataset_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/data_preprocess/generate_dataset_utils.py -------------------------------------------------------------------------------- /demo_audio.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/demo_audio.wav -------------------------------------------------------------------------------- /iccv2021_sdt.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/iccv2021_sdt.jpg -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/main.py -------------------------------------------------------------------------------- /pose_definition.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/pose_definition.md -------------------------------------------------------------------------------- /pose_definition.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/pose_definition.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenhanQian/SpeechDrivesTemplates/HEAD/requirements.txt --------------------------------------------------------------------------------