feat(record): plumb DepthEncoderConfig through lerobot-record

src/lerobot/configs/__init__.py

@@ -35,7 +35,9 @@ from .video import (
     VALID_VIDEO_CODECS,
     VIDEO_ENCODER_INFO_KEYS,
     VideoEncoderConfig,
+    DepthEncoderConfig,
     camera_encoder_defaults,
+    depth_encoder_defaults,
 )
 
 __all__ = [
@@ -53,8 +55,10 @@ __all__ = [
     "PreTrainedConfig",
     "WandBConfig",
     "VideoEncoderConfig",
+    "DepthEncoderConfig",
     # Defaults
     "camera_encoder_defaults",
+    "depth_encoder_defaults",
     # Constants
     "VALID_VIDEO_CODECS",
     "VIDEO_ENCODER_INFO_KEYS",

src/lerobot/datasets/lerobot_dataset.py

@@ -761,6 +761,7 @@ class LeRobotDataset(torch.utils.data.Dataset):
         video_backend: str | None = None,
         batch_encoding_size: int = 1,
         camera_encoder: VideoEncoderConfig | None = None,
+        depth_encoder: DepthEncoderConfig | None = None,
         encoder_threads: int | None = None,
         image_writer_processes: int = 0,
         image_writer_threads: int = 0,
@@ -790,6 +791,8 @@ class LeRobotDataset(torch.utils.data.Dataset):
                 batch-encoding videos.
             camera_encoder: Video encoder settings for cameras (codec, quality, etc.).
                 When ``None``, :func:`~lerobot.configs.video.camera_encoder_defaults` is used.
+            depth_encoder: Video encoder settings for depth cameras (codec, quality, etc.).
+                When ``None``, :func:`~lerobot.configs.depth.depth_encoder_defaults` is used.
             encoder_threads: Number of encoder threads (global). ``None``
                 lets the codec decide.
             image_writer_processes: Subprocesses for async image writing.
@@ -836,12 +839,13 @@ class LeRobotDataset(torch.utils.data.Dataset):
         streaming_enc = None
         if streaming_encoding and len(obj.meta.video_keys) > 0:
             streaming_enc = cls._build_streaming_encoder(
-                obj.meta.fps, camera_encoder, encoder_queue_maxsize, encoder_threads
+                obj.meta.fps, camera_encoder, depth_encoder, encoder_queue_maxsize, encoder_threads
             )
         obj.writer = DatasetWriter(
             meta=obj.meta,
             root=obj.root,
             camera_encoder=camera_encoder,
+            depth_encoder=depth_encoder,
             encoder_threads=encoder_threads,
             batch_encoding_size=batch_encoding_size,
             streaming_encoder=streaming_enc,

src/lerobot/scripts/lerobot_record.py

@@ -399,6 +399,7 @@ def record(
                 root=cfg.dataset.root,
                 batch_encoding_size=cfg.dataset.video_encoding_batch_size,
                 camera_encoder=cfg.dataset.camera_encoder,
+                depth_encoder=cfg.dataset.depth_encoder,
                 encoder_threads=cfg.dataset.encoder_threads,
                 streaming_encoding=cfg.dataset.streaming_encoding,
                 encoder_queue_maxsize=cfg.dataset.encoder_queue_maxsize,
@@ -428,6 +429,7 @@ def record(
                 image_writer_threads=cfg.dataset.num_image_writer_threads_per_camera * len(robot.cameras),
                 batch_encoding_size=cfg.dataset.video_encoding_batch_size,
                 camera_encoder=cfg.dataset.camera_encoder,
+                depth_encoder=cfg.dataset.depth_encoder,
                 encoder_threads=cfg.dataset.encoder_threads,
                 streaming_encoding=cfg.dataset.streaming_encoding,
                 encoder_queue_maxsize=cfg.dataset.encoder_queue_maxsize,