vision3d.viz#

Optional 3D visualization utilities.

Requires the viz dependency group:

pip install vision3d[viz]

Functions

log_boxes_3d(entity, boxes, *[, labels, ...])

Log 3D bounding boxes to Rerun.

log_cameras(entity_prefix, images[, ...])

Log all camera images with optional pinhole projection to Rerun.

log_point_cloud(entity, points, *[, ...])

Log a point cloud to Rerun.

log_sample(inputs[, targets, entity_prefix, ...])

Log a full sample dict to Rerun.
vision3d.viz.log_boxes_3d(entity, boxes, *, labels=None, class_ids=None, log_heading=True)[source]#

Log 3D bounding boxes to Rerun.

Logs boxes as rr.Boxes3D and optionally heading arrows as rr.Arrows3D on a /heading sub-entity.

For consistent class coloring across frames, pass class_ids and log an rr.AnnotationContext on the entity once before logging any boxes.

Parameters:

  • entity (str) – Rerun entity path (e.g. "world/boxes").

  • boxes (BoundingBoxes3D) – Bounding boxes in any supported format.

  • labels (list[str] | None) – Per-box label strings for display.

  • class_ids (list[int] | None) – Per-box class IDs for coloring via AnnotationContext.

  • log_heading (bool) – If True and boxes have rotation, log heading arrows.

Return type:

None

vision3d.viz.log_cameras(entity_prefix, images, intrinsics=None, extrinsics=None)[source]#

Log all camera images with optional pinhole projection to Rerun.

Each camera is logged to {entity_prefix} for a single camera, or {entity_prefix}_{i} for multiple cameras.

Parameters:

  • entity_prefix (str) – Rerun entity path prefix (e.g. "world/cam").

  • images (CameraImages | Tensor) – Camera images [N_cams, C, H, W].

  • intrinsics (CameraIntrinsics | Tensor | None) – Intrinsic matrices [N_cams, 3, 3].

  • extrinsics (CameraExtrinsics | Tensor | None) – Extrinsic matrices [N_cams, 4, 4] (lidar-to-camera).

Return type:

None

vision3d.viz.log_point_cloud(entity, points, *, color_by_distance=True)[source]#

Log a point cloud to Rerun.

Parameters:

  • entity (str) – Rerun entity path (e.g. "world/lidar").

  • points (PointCloud3D | Tensor) – Point cloud [N, 3+C]. First 3 columns are xyz.

  • color_by_distance (bool) – Color points by distance from origin.

Return type:

None

vision3d.viz.log_sample(inputs, targets=None, *, entity_prefix='world', label_to_id=None)[source]#

Log a full sample dict to Rerun.

Convenience function that dispatches to type-specific loggers.

Parameters:

  • inputs (SampleInputs) – Dict with "points", "images", "extrinsics", "intrinsics" keys.

  • targets (SampleTargets | None) – Optional dict with "boxes", "labels" keys.

  • entity_prefix (str) – Rerun entity path prefix.

  • label_to_id (dict[str, int] | None) – Mapping from class name to class ID for consistent coloring. Build this across all frames before logging.

Return type:

None