Add video_human_3d_pose_mapper.

data_juicer/config/config_all.yaml

@@ -639,6 +639,11 @@ process:
       capture_stderr: true                                    # whether to capture stderr.
       overwrite_output: true                                  # whether to overwrite the output file.
       save_dir: null                                          # The directory where generated files will be stored. If not specified, outputs will be saved in the same directory as their corresponding input files. This path can alternatively be defined by setting the `DJ_PRODUCED_DATA_DIR` environment variable.
+  - video_human_3d_pose_mapper:                             # Extract 3D human pose with Human3R (SMPL-X).
+      model_path: "human3r_896L.pth"                          # The path to the Human3R model checkpoint.
+      frame_num: 3                                            # the number of frames to be extracted uniformly from the video. If it's 1, only the middle frame will be extracted. If it's 2, only the first and the last frames will be extracted. If it's larger than 2, in addition to the first and the last frames, other frames will be extracted uniformly within the video duration.
+      duration: 0                                             # the duration of each segment in seconds. If 0, frames are extracted from the entire video. If duration > 0, the video is segmented into multiple segments based on duration, and frames are extracted from each segment.
+      frame_dir: null                                         # Output directory to save extracted frames.
   - video_remove_watermark_mapper:                          # Remove the watermarks in videos given regions
       roi_strings: ['0,0,0.1,0.1']                            # a given list of regions the watermarks locate. The format of each can be "x1, y1, x2, y2", "(x1, y1, x2, y2)", or "[x1, y1, x2, y2]".
       roi_type: ratio                                         # the roi string type. When the type is 'pixel', (x1, y1), (x2, y2) are the locations of pixels in the top left corner and the bottom right corner respectively. If the roi_type is 'ratio', the coordinates are normalized by widths and heights.

data_juicer/ops/mapper/__init__.py

@@ -120,6 +120,7 @@
 from .video_ffmpeg_wrapped_mapper import VideoFFmpegWrappedMapper
 from .video_hand_reconstruction_hawor_mapper import VideoHandReconstructionHaworMapper
 from .video_hand_reconstruction_mapper import VideoHandReconstructionMapper
+from .video_human_3d_pose_mapper import VideoHuman3DPoseMapper
 from .video_object_segmenting_mapper import VideoObjectSegmentingMapper
 from .video_remove_watermark_mapper import VideoRemoveWatermarkMapper
 from .video_resize_aspect_ratio_mapper import VideoResizeAspectRatioMapper
@@ -244,6 +245,7 @@
     "VideoFFmpegWrappedMapper",
     "VideoHandReconstructionHaworMapper",
     "VideoHandReconstructionMapper",
+    "VideoHuman3DPoseMapper",
     "VideoFaceBlurMapper",
     "VideoObjectSegmentingMapper",
     "VideoRemoveWatermarkMapper",