├── .gitignore ├── README.md ├── assets ├── FAzSK8PLmGI_pose.gif ├── FAzSK8PLmGI_raw.gif ├── VoxCeleb2_id03765_mCkWsZ4uVDM_00169_000172.png ├── WRA_BillCassidy0_000.gif ├── facial_orientation.png ├── full_video.png ├── hand_landmarker.task └── landmarks.png ├── blur_detection.py ├── data_processing ├── cropped_faces │ └── FAzSK8PLmGI.mp4 ├── raw_data │ └── FAzSK8PLmGI.mp4 └── specified_formats │ ├── audios │ ├── audios_16k │ │ └── FAzSK8PLmGI.wav │ └── hubert_features │ │ └── FAzSK8PLmGI.npy │ └── videos │ ├── facial_action_units │ └── FAzSK8PLmGI │ │ ├── FAzSK8PLmGI.csv │ │ └── FAzSK8PLmGI_of_details.txt │ ├── landmarks │ └── FAzSK8PLmGI.txt │ ├── pose_orientations │ ├── pose_data │ │ └── FAzSK8PLmGI.npy │ └── visualization │ │ └── FAzSK8PLmGI.mp4 │ └── videos_25fps │ └── FAzSK8PLmGI.mp4 ├── dependencies.txt ├── extract_action_units.py ├── extract_audio_features.py ├── extract_audio_features_whisper.py ├── extract_cropped_faces.py ├── extract_face_orientation.py ├── extract_frame_landmarks.py ├── extract_raw_video_data.py ├── extract_scenes.py ├── filter_videos_rough.py ├── hand_detection.py ├── libs └── mfcc_feature_example.py └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/README.md -------------------------------------------------------------------------------- /assets/FAzSK8PLmGI_pose.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/assets/FAzSK8PLmGI_pose.gif -------------------------------------------------------------------------------- /assets/FAzSK8PLmGI_raw.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/assets/FAzSK8PLmGI_raw.gif -------------------------------------------------------------------------------- /assets/VoxCeleb2_id03765_mCkWsZ4uVDM_00169_000172.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/assets/VoxCeleb2_id03765_mCkWsZ4uVDM_00169_000172.png -------------------------------------------------------------------------------- /assets/WRA_BillCassidy0_000.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/assets/WRA_BillCassidy0_000.gif -------------------------------------------------------------------------------- /assets/facial_orientation.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/assets/facial_orientation.png -------------------------------------------------------------------------------- /assets/full_video.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/assets/full_video.png -------------------------------------------------------------------------------- /assets/hand_landmarker.task: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/assets/hand_landmarker.task -------------------------------------------------------------------------------- /assets/landmarks.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/assets/landmarks.png -------------------------------------------------------------------------------- /blur_detection.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/blur_detection.py -------------------------------------------------------------------------------- /data_processing/cropped_faces/FAzSK8PLmGI.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/data_processing/cropped_faces/FAzSK8PLmGI.mp4 -------------------------------------------------------------------------------- /data_processing/raw_data/FAzSK8PLmGI.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/data_processing/raw_data/FAzSK8PLmGI.mp4 -------------------------------------------------------------------------------- /data_processing/specified_formats/audios/audios_16k/FAzSK8PLmGI.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/data_processing/specified_formats/audios/audios_16k/FAzSK8PLmGI.wav -------------------------------------------------------------------------------- /data_processing/specified_formats/audios/hubert_features/FAzSK8PLmGI.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/data_processing/specified_formats/audios/hubert_features/FAzSK8PLmGI.npy -------------------------------------------------------------------------------- /data_processing/specified_formats/videos/facial_action_units/FAzSK8PLmGI/FAzSK8PLmGI.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/data_processing/specified_formats/videos/facial_action_units/FAzSK8PLmGI/FAzSK8PLmGI.csv -------------------------------------------------------------------------------- /data_processing/specified_formats/videos/facial_action_units/FAzSK8PLmGI/FAzSK8PLmGI_of_details.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/data_processing/specified_formats/videos/facial_action_units/FAzSK8PLmGI/FAzSK8PLmGI_of_details.txt -------------------------------------------------------------------------------- /data_processing/specified_formats/videos/landmarks/FAzSK8PLmGI.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/data_processing/specified_formats/videos/landmarks/FAzSK8PLmGI.txt -------------------------------------------------------------------------------- /data_processing/specified_formats/videos/pose_orientations/pose_data/FAzSK8PLmGI.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/data_processing/specified_formats/videos/pose_orientations/pose_data/FAzSK8PLmGI.npy -------------------------------------------------------------------------------- /data_processing/specified_formats/videos/pose_orientations/visualization/FAzSK8PLmGI.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/data_processing/specified_formats/videos/pose_orientations/visualization/FAzSK8PLmGI.mp4 -------------------------------------------------------------------------------- /data_processing/specified_formats/videos/videos_25fps/FAzSK8PLmGI.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/data_processing/specified_formats/videos/videos_25fps/FAzSK8PLmGI.mp4 -------------------------------------------------------------------------------- /dependencies.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/dependencies.txt -------------------------------------------------------------------------------- /extract_action_units.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/extract_action_units.py -------------------------------------------------------------------------------- /extract_audio_features.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/extract_audio_features.py -------------------------------------------------------------------------------- /extract_audio_features_whisper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/extract_audio_features_whisper.py -------------------------------------------------------------------------------- /extract_cropped_faces.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/extract_cropped_faces.py -------------------------------------------------------------------------------- /extract_face_orientation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/extract_face_orientation.py -------------------------------------------------------------------------------- /extract_frame_landmarks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/extract_frame_landmarks.py -------------------------------------------------------------------------------- /extract_raw_video_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/extract_raw_video_data.py -------------------------------------------------------------------------------- /extract_scenes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/extract_scenes.py -------------------------------------------------------------------------------- /filter_videos_rough.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/filter_videos_rough.py -------------------------------------------------------------------------------- /hand_detection.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/hand_detection.py -------------------------------------------------------------------------------- /libs/mfcc_feature_example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/libs/mfcc_feature_example.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liutaocode/talking_face_preprocessing/HEAD/requirements.txt --------------------------------------------------------------------------------