feat(encoding parameters): adding support for user provided video encoding parameters (#3455)

* chore(video backend): renaming codec into video_backend in get_safe_default_video_backend()

* feat(pyav utils): adding suport for PyAV encoding parameters validation

* feat(VideoEncoderConfig): creating a VideoEncoderConfig to encapsulate encoding parameters

* feat(VideoEncoderConfig): propagating the VideoEncoderConfig in the codebase

* chore(docs): updating the docs

* feat(metadata): adding encoding parameters in dataset metadata

* fix(concatenation compatibility): adding compatibility check when concatenating video files

* feat(VideoEncoderConfig init): making VideoEncoderConfig more robust and adaptable to multiple backends

* feat(pyav checks): making pyav parameters checks more robust

* chore(duplicate): removing duplicate get_codec_options definition

* test(existing): adapting existing tests

* test(new): adding new tests for encoding related features

* chore(format): fixing formatting issues

* chore(PyAV): cleaning up PyAV utils and encoding parameters checks to stick to the minimun required tooling.

* chore(format): formatting code

* chore(doctrings): updating docstrings

* fix(camera_encoder_config): Removing camera_encoder_config from LeRobotDataset, as it's only required in LeRobotDatasetWriter.

* feat(default values): applying a consistent naming convention for default RGB cameras video encoder parameters

* fix(rollout): propagating VideoEncoderConfig to the latest recording modes

* chore(format): formatting code, fixing error messages and variable names

* fix(arguments order): reverting changes in arguments order in StreamingVideoEncoder

* chore(relative imports): switching to relative local imports within lerobot.datasets

* test(artifacts): cleaning up artifacts for the video encoding tests

* chore(docs): updating docs

* chore(fromat): formatting code

* fix(imports): refactoring the file architecture to avoid circular imports. VideoEncoderConfig is now defined in lerobot.configs and lazily imports av at runtime.

* fix(typos): fixing typos and small mistakes

* test(factories): updating factories

* feat(aggregate): updating dataset aggregation procedure. Encoding tuning paramters (crf, g,...) are ignored for validation and changed to None in the aggregated dataset if incompatible.

* docs(typos): fixing typos

* fix(deletion): reverting unwanted deletion

* fix(typos): fixing multiple typos

* feat(codec options): passing codec options to lerobot_edit_dataset episode deletion tool

* typo(typo): typo

* fix(typos): fixing remaining typos

* chore(rename): renaming camera_encoder_config to camera_encoder

* docs(clean): cleaning and formating docs

* docs(dataset): addind details about datasets

* chore(format): formatting code

* docs(warning): adding warning regarding encoding parameters modification

* fix(re-encoding): removing inconsistent re-encoding option in lerobot_edit_dataset

* typos(typos): typos

* chore(format): resolving prettier issues

* fix(h264_nvenc): fixing crf handling for h264_nvenc

* docs(clean): removing too technical parts of the docs

* fix(imports): fixing imports at the __init__ level

* fix(imports): fixing not very pretty imports in video config file

src/lerobot/datasets/dataset_writer.py

@@ -31,6 +31,8 @@ import PIL.Image
 import pyarrow.parquet as pq
 import torch
 
+from lerobot.configs import VideoEncoderConfig, camera_encoder_defaults
+
 from .compute_stats import compute_episode_stats
 from .dataset_metadata import LeRobotDatasetMetadata
 from .feature_utils import (
@@ -65,14 +67,19 @@ def _encode_video_worker(
     episode_index: int,
     root: Path,
     fps: int,
-    vcodec: str = "libsvtav1",
+    camera_encoder: VideoEncoderConfig | None = None,
     encoder_threads: int | None = None,
 ) -> Path:
     temp_path = Path(tempfile.mkdtemp(dir=root)) / f"{video_key}_{episode_index:03d}.mp4"
     fpath = DEFAULT_IMAGE_PATH.format(image_key=video_key, episode_index=episode_index, frame_index=0)
     img_dir = (root / fpath).parent
     encode_video_frames(
-        img_dir, temp_path, fps, vcodec=vcodec, overwrite=True, encoder_threads=encoder_threads
+        img_dir,
+        temp_path,
+        fps,
+        camera_encoder=camera_encoder,
+        encoder_threads=encoder_threads,
+        overwrite=True,
     )
     shutil.rmtree(img_dir)
     return temp_path
@@ -89,20 +96,22 @@ class DatasetWriter:
         self,
         meta: LeRobotDatasetMetadata,
         root: Path,
-        vcodec: str,
+        camera_encoder: VideoEncoderConfig | None,
         encoder_threads: int | None,
         batch_encoding_size: int,
         streaming_encoder: StreamingVideoEncoder | None = None,
         initial_frames: int = 0,
     ):
-        """Initialize the writer with metadata, codec, and encoding config.
+        """Initialize the writer with metadata, codec, and encoder config.
 
         Args:
             meta: Dataset metadata instance (used for feature schema, chunk
                 settings, and episode persistence).
             root: Local dataset root directory.
-            vcodec: Video codec for encoding (e.g. ``'libsvtav1'``, ``'h264'``).
-            encoder_threads: Threads per encoder instance. ``None`` for auto.
+            camera_encoder: Video encoder settings applied to all cameras.
+                ``None`` uses :func:`~lerobot.configs.camera_encoder_defaults`.
+            encoder_threads: Number of encoder threads (global). ``None``
+                lets the codec decide.
             batch_encoding_size: Number of episodes to accumulate before
                 batch-encoding videos.
             streaming_encoder: Optional pre-built :class:`StreamingVideoEncoder`
@@ -111,7 +120,7 @@ class DatasetWriter:
         """
         self._meta = meta
         self._root = root
-        self._vcodec = vcodec
+        self._camera_encoder = camera_encoder or camera_encoder_defaults()
         self._encoder_threads = encoder_threads
         self._batch_encoding_size = batch_encoding_size
         self._streaming_encoder = streaming_encoder
@@ -284,7 +293,7 @@ class DatasetWriter:
                             episode_index,
                             self._root,
                             self._meta.fps,
-                            self._vcodec,
+                            self._camera_encoder,
                             self._encoder_threads,
                         ): video_key
                         for video_key in self._meta.video_keys
@@ -495,7 +504,7 @@ class DatasetWriter:
 
         # Update video info (only needed when first episode is encoded)
         if episode_index == 0:
-            self._meta.update_video_info(video_key)
+            self._meta.update_video_info(video_key, camera_encoder=self._camera_encoder)
             write_info(self._meta.info, self._meta.root)
 
         metadata = {
@@ -564,7 +573,12 @@ class DatasetWriter:
     def _encode_temporary_episode_video(self, video_key: str, episode_index: int) -> Path:
         """Use ffmpeg to convert frames stored as png into mp4 videos."""
         return _encode_video_worker(
-            video_key, episode_index, self._root, self._meta.fps, self._vcodec, self._encoder_threads
+            video_key,
+            episode_index,
+            self._root,
+            self._meta.fps,
+            self._camera_encoder,
+            self._encoder_threads,
         )
 
     def close_writer(self) -> None: