docs(docstring): updating docstrings

src/lerobot/datasets/compute_stats.py

@@ -506,8 +506,10 @@ def compute_episode_stats(
         Each statistics dictionary contains min, max, mean, std, count, and quantiles.
 
     Note:
-        Image statistics are normalized to [0,1] range and have shape (3,1,1) for
-        per-channel values when dtype is 'image' or 'video'.
+        For 'image'/'video' features, stats are computed per channel and kept with a
+        leading channel axis (e.g. shape (3, 1, 1) for RGB). RGB stats are divided by
+        255 to land in [0, 1]; depth maps (features flagged with ``is_depth_map``) skip
+        this rescaling and remain in their stored units.
     """
     if quantile_list is None:
         quantile_list = DEFAULT_QUANTILES

src/lerobot/datasets/dataset_tools.py

@@ -1679,21 +1679,27 @@ def convert_image_to_video_dataset(
     LeRobot dataset structure with videos stored in chunked MP4 files.
 
     Args:
-        dataset: The source LeRobot dataset with images
-        output_dir: Root directory where the edited dataset will be stored. If not specified, defaults to $HF_LEROBOT_HOME/repo_id. Equivalent to new_root in EditDatasetConfig.
-        repo_id: Edited dataset identifier. Equivalent to new_repo_id in EditDatasetConfig.
-        camera_encoder: Video encoder settings applied to RGB cameras
-            (``None`` uses :func:`~lerobot.configs.camera_encoder_defaults`).
+        dataset: The source LeRobot dataset with images.
+        output_dir: Root directory where the converted dataset will be stored. When
+            ``None``, defaults to ``$HF_LEROBOT_HOME/repo_id``. Equivalent to
+            ``new_root`` in ``EditDatasetConfig``.
+        repo_id: Converted dataset identifier. Equivalent to ``new_repo_id`` in
+            ``EditDatasetConfig``.
+        camera_encoder: Video encoder settings applied to RGB cameras. When ``None``,
+            :func:`~lerobot.configs.video.camera_encoder_defaults` is used.
         depth_encoder: Video encoder settings applied to depth-map cameras, including
-            the quantization parameters persisted to the dataset metadata
-            (``None`` uses :func:`~lerobot.configs.depth_encoder_defaults`).
-        episode_indices: List of episode indices to convert (None = all episodes)
-        num_workers: Number of threads for parallel processing (default: 4)
-        max_episodes_per_batch: Maximum episodes per video batch to avoid memory issues (None = no limit)
-        max_frames_per_batch: Maximum frames per video batch to avoid memory issues (None = no limit)
+            the quantization parameters persisted to the dataset metadata. When
+            ``None``, :func:`~lerobot.configs.video.depth_encoder_defaults` is used.
+        episode_indices: Episode indices to convert. When ``None``, all episodes are
+            converted.
+        num_workers: Number of threads for parallel processing.
+        max_episodes_per_batch: Maximum episodes per video batch, to bound memory use.
+            ``None`` means no limit.
+        max_frames_per_batch: Maximum frames per video batch, to bound memory use.
+            ``None`` means no limit.
 
     Returns:
-        New LeRobotDataset with images encoded as videos
+        A new :class:`LeRobotDataset` with images encoded as videos.
     """
     if camera_encoder is None:
         camera_encoder = camera_encoder_defaults()

src/lerobot/datasets/dataset_writer.py

@@ -120,10 +120,11 @@ class DatasetWriter:
             meta: Dataset metadata instance (used for feature schema, chunk
                 settings, and episode persistence).
             root: Local dataset root directory.
-            camera_encoder: Video encoder settings applied to all cameras.
-                ``None`` uses :func:`~lerobot.configs.camera_encoder_defaults`.
-            depth_encoder: Video encoder settings applied to all **depth** cameras.
-                ``None`` uses :func:`~lerobot.configs.depth_encoder_defaults`.
+            camera_encoder: Video encoder settings applied to RGB cameras. When
+                ``None``, :func:`~lerobot.configs.video.camera_encoder_defaults` is used.
+            depth_encoder: Video encoder settings applied to depth cameras, including
+                the quantization parameters. When ``None``,
+                :func:`~lerobot.configs.video.depth_encoder_defaults` is used.
             encoder_threads: Number of encoder threads (global). ``None``
                 lets the codec decide.
             batch_encoding_size: Number of episodes to accumulate before

src/lerobot/datasets/lerobot_dataset.py

@@ -189,7 +189,7 @@ class LeRobotDataset(torch.utils.data.Dataset):
                 (codec, quality, etc.). When ``None``, :func:`~lerobot.configs.video.camera_encoder_defaults`
                 is used by the writer.
             depth_encoder (DepthEncoderConfig | None, optional): Video encoder settings for depth cameras
-                (codec, quality, etc.). When ``None``, :func:`~lerobot.configs.depth.depth_encoder_defaults`
+                (codec, quality, etc.). When ``None``, :func:`~lerobot.configs.video.depth_encoder_defaults`
                 is used by the writer.
             encoder_threads (int | None, optional): Number of encoder threads (global). ``None`` lets the
                 codec decide.
@@ -692,7 +692,7 @@ class LeRobotDataset(torch.utils.data.Dataset):
             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.
+                When ``None``, :func:`~lerobot.configs.video.depth_encoder_defaults` is used.
             encoder_threads: Number of encoder threads (global). ``None``
                 lets the codec decide.
             metadata_buffer_size: Number of episode metadata records to buffer
@@ -798,7 +798,7 @@ class LeRobotDataset(torch.utils.data.Dataset):
             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.
+                When ``None``, :func:`~lerobot.configs.video.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.

src/lerobot/datasets/video_utils.py

@@ -436,7 +436,28 @@ def encode_video_frames(
     log_level: int | None = av.logging.WARNING,
     overwrite: bool = False,
 ) -> None:
-    """More info on ffmpeg arguments tuning on `benchmark/video/README.md`"""
+    """Encode a directory of image frames into an MP4 video.
+
+    When ``video_encoder`` is a :class:`~lerobot.configs.video.DepthEncoderConfig`,
+    frames are read from ``.tiff`` files and quantized to 12-bit depth codes using the
+    encoder's ``depth_min`` / ``depth_max`` / ``shift`` / ``use_log``; otherwise ``.png``
+    RGB frames are encoded directly.
+
+    Args:
+        imgs_dir: Directory containing the frames to encode, named ``frame-000000``
+            onwards (``.png`` for RGB, ``.tiff`` for depth).
+        video_path: Output path for the encoded ``.mp4`` file.
+        fps: Frame rate of the output video.
+        video_encoder: Encoder settings (codec, pixel format, quality, ...). When
+            ``None``, :func:`camera_encoder_defaults` is used. Pass a
+            :class:`~lerobot.configs.video.DepthEncoderConfig` to encode depth frames.
+        encoder_threads: Per-encoder thread count forwarded to the codec. ``None``
+            lets the codec decide.
+        log_level: libav log level to set while encoding, or ``None`` to leave the
+            current logging configuration unchanged.
+        overwrite: When ``False`` and ``video_path`` already exists, skip encoding and
+            log a warning. When ``True``, re-encode and replace the existing file.
+    """
     if video_encoder is None:
         video_encoder = camera_encoder_defaults()
     vcodec = video_encoder.vcodec
@@ -873,12 +894,15 @@ class StreamingVideoEncoder:
         """
         Args:
             fps: Frames per second for the output videos.
-            camera_encoder: Video encoder settings applied to all cameras.
+            camera_encoder: Video encoder settings applied to all RGB cameras.
                 When ``None``, :func:`camera_encoder_defaults` is used.
-            encoder_threads: Number of encoder threads (global setting).
-                ``None`` lets the codec decide.
+            depth_encoder: Video encoder settings applied to all depth cameras,
+                including the depth quantization parameters. When ``None``,
+                :func:`depth_encoder_defaults` is used.
             queue_maxsize: Max frames to buffer per camera before
                 back-pressure drops frames.
+            encoder_threads: Number of encoder threads (global setting).
+                ``None`` lets the codec decide.
         """
         self.fps = fps
         self._camera_encoder = camera_encoder or camera_encoder_defaults()
@@ -1145,7 +1169,15 @@ def get_video_info(
         video_path: Path to the encoded video file to probe.
         video_encoder: If provided, record the exact encoder settings used to encode this
             video. Stream-derived values take precedence — encoder fields are only written for keys
-            not already populated from the video file itself.
+            not already populated from the video file itself. When a
+            :class:`~lerobot.configs.video.DepthEncoderConfig` is passed, the depth
+            quantization parameters (``depth_min`` / ``depth_max`` / ``shift`` /
+            ``use_log``) are recorded so frames can be dequantized on read.
+
+    Returns:
+        The ``video.*`` / ``audio.*`` info dict, including ``is_depth_map`` which is
+        ``True`` only when ``video_encoder`` is a
+        :class:`~lerobot.configs.video.DepthEncoderConfig`.
     """
     logging.getLogger("libav").setLevel(av.logging.WARNING)
 

src/lerobot/utils/feature_utils.py

@@ -51,7 +51,9 @@ def hw_to_dataset_features(
 
     This function takes a dictionary describing hardware outputs (like joint states
     or camera image shapes) and formats it into the standard LeRobot feature
-    specification.
+    specification. Single-channel cameras (shape ``(H, W, 1)``) are flagged as depth
+    maps via ``info["is_depth_map"] = True``; three-channel cameras ``(H, W, 3)`` are
+    treated as RGB.
 
     Args:
         hw_features (dict): Dictionary mapping feature names to their type (float for
@@ -61,7 +63,7 @@ def hw_to_dataset_features(
         use_video (bool): If True, image features are marked as "video", otherwise "image".
 
     Returns:
-        dict: A LeRobot features dictionary.
+        dict: A LeRobot features dictionary. Depth cameras carry ``info["is_depth_map"] = True``.
     """
     features = {}
     joint_fts = {