torchdrivesim.rendering.base

Base class for renderers producing rasterized birdview images from given background meshes and agent positions.

Attributes

logger

Classes

RendererConfig	Determines behavior of the renderer.
DummyRendererConfig	For DummyRenderer.
Cameras	Lightweight version of pytorch3d.renderer.FoVOrthographicCameras.
BirdviewRenderer	A renderer producing simple 2D birdview images based on static background meshes and rectangular agents.
DummyRenderer	Produces a black image of the required size. Mostly used for debugging and benchmarking.

Functions

get_default_rendering_levels(→ Dict[str, float])	Produces the default rendering levels, mapping object categories
get_default_color_map(→ Dict[str, Tuple[int, int, int]])	Produces the default color map, mapping object categories

Module Contents

torchdrivesim.rendering.base.logger = None

class torchdrivesim.rendering.base.RendererConfig

Determines behavior of the renderer. Subclasses determine renderer class used.

backend: str = 'default'

render_agent_direction: bool = True

left_handed_coordinates: bool = False

highlight_ego_vehicle: bool = False

shift_mesh_by_camera_before_rendering: bool = True

device: str | None = None

class torchdrivesim.rendering.base.DummyRendererConfig

Bases: RendererConfig

For DummyRenderer.

backend: str = 'dummy'

class torchdrivesim.rendering.base.Cameras(xy: torch.Tensor, sc: torch.Tensor, scale: float)

Lightweight version of pytorch3d.renderer.FoVOrthographicCameras. Used to define an interface that works without pytorch3d.

xy

sc

scale

world_to_clip_transform

get_camera_center() → torch.Tensor

get_world_to_view_transform() → torch.Tensor

get_view_to_proj_transform() → torch.Tensor

project_world_to_clip_space(points: torch.Tensor) → torch.Tensor

transform_points_screen(points: torch.Tensor, res: torchdrivesim.utils.Resolution) → torch.Tensor

reverse_transform_points_screen(points: torch.Tensor, res: torchdrivesim.utils.Resolution) → torch.Tensor

class torchdrivesim.rendering.base.BirdviewRenderer(cfg: RendererConfig, color_map: Dict[str, Tuple[int, int, int]] | None = None, rendering_levels: Dict[str, float] | None = None, res: torchdrivesim.utils.Resolution = Resolution(64, 64), fov: float = 35)

Bases: abc.ABC

A renderer producing simple 2D birdview images based on static background meshes and rectangular agents. Currently only square resolutions are supported. The renderer always operates in batch mode, with a single batch dimension on the left.

Parameters:

• cfg – configuration object, usually subclassed

• color_map – a dictionary of RGB tuples in 0-255 range specifying colors of different rendered elements

• res – default resolution

cfg: RendererConfig

res

scale = 0.05714285714285714

color_map = None

rendering_levels = None

copy()

get_color(element_type: str) → Tuple[int, int, int]

render_frame(rgb_mesh: torchdrivesim.mesh.RGBMesh, camera_xy: torch.Tensor, camera_sc: torch.Tensor, res: torchdrivesim.utils.Resolution | None = None, fov: float | None = None)

Renders a given rgb mesh according the camera position and rotation.

Parameters:

• rgb_mesh – the given rgb mesh to render which should be already expanded to match the number of cameras.

• camera_xy – BxNcx2 tensor of camera positions, by default one camera placed on each agent

• camera_sc – BxNcx2 tensor of camera orientations (sine and cosine), by default matching agent orientations

• res – resolution HxW of the resulting image, currently only square resolutions are supported

• fov – Field of view in meters

Returns:

tensor image of float RGB values in [0,255] range with shape shape (B*Nc)xCxHxW

abstract render_rgb_mesh(mesh: torchdrivesim.mesh.RGBMesh, res: torchdrivesim.utils.Resolution, cameras: Cameras) → torch.Tensor

Renders a given mesh, producing BxHxWxC tensor image of float RGB values in [0,255] range.

construct_cameras(xy: torch.Tensor, sc: torch.Tensor, scale: float | None = None) → Cameras

Create PyTorch3D cameras object for given positions and orientations. Input tensor dimensions should be Bx2.

class torchdrivesim.rendering.base.DummyRenderer(cfg: RendererConfig, color_map: Dict[str, Tuple[int, int, int]] | None = None, rendering_levels: Dict[str, float] | None = None, res: torchdrivesim.utils.Resolution = Resolution(64, 64), fov: float = 35)

Bases: BirdviewRenderer

Produces a black image of the required size. Mostly used for debugging and benchmarking.

render_rgb_mesh(mesh: torchdrivesim.mesh.RGBMesh, res: torchdrivesim.utils.Resolution, cameras: Cameras) → torch.Tensor

Renders a given mesh, producing BxHxWxC tensor image of float RGB values in [0,255] range.

torchdrivesim.rendering.base.get_default_rendering_levels() → Dict[str, float]

Produces the default rendering levels, mapping object categories to their rendering level. Lower level renders on top, but levels lower than 0 don’t render at all.

torchdrivesim.rendering.base.get_default_color_map() → Dict[str, Tuple[int, int, int]]

Produces the default color map, mapping object categories to RGB 3-tuples in [0,255] range.