visu3d is an abstraction layer between Torch/TF/Jax/Numpy and your program.
It provides:
- Standard primitives for 3d geometry (
Ray,Camera,Transform,...). You can combine those standard primitives with your custom ones. - Everything is trivially visualizable with zero boilerplate. Inspect & debug camera poses, trajectories,...
- All primitives are
dataclass_array, dataclasses which can be reshaped, sliced,... as if they were numpy arrays. - Everything is extensible, you can gradually opt-in only for the features you need, and replace any standard primitive by your custom ones.
Everything is a v3d.DataclassArray: dataclass behave like np.array (with
indexing, slicing, shape manipulation, vectorization,...).
# Single ray
ray = v3d.Ray(pos=[0, 0, 0], dir=[1, 1, 1])
assert rays.shape == ()
# Multiple rays batched together
rays = v3d.Ray(pos=np.zeros((B, H, W, 3)), dir=np.ones((B, H, W, 3)))
assert rays.shape == (B, H, W)
rays = rays.reshape('b h w -> b (h w)') # Native `einops` support
top_left_ray = rays[..., 0, 0] # (b, h, w) -> (b,)
rays = rays.flatten()
rays = rays[rays.norm() > 0] # Filter invalid raysEverything is visualizable interactively
Every object has a .fig property for interactive visualization:
rays.fig # Plot the raysDisplay multiple objects together:
v3d.make_fig([cam, rays, point_cloud])Auto-plot figures with Colab magic:
v3d.auto_plot_figs() # Once at the start of the Colab
cam, rays, point_cloud # Tuple auto-displayed without `v3d.make_fig` callSame code seamlessly works across Torch, Jax, TensorFlow, Numpy.
rays = rays.as_jax() # .as_tf(), as_np(), .as_jax()
assert isinstance(rays.pos, jnp.ndarray)
assert rays.xnp is jnp
rays = rays.as_torch()
assert isinstance(rays.pos, torch.Tensor)
assert rays.xnp is torchWith native support for auto-diff, jax.vmap, jax.tree_utils,...
Common primitives (Ray, Camera, Transform,...), so user can express
intent, instead of math.
H, W = (256, 1024)
cam_spec = v3d.PinholeCamera.from_focal(
resolution=(H, W),
focal_in_px=35.,
)
cam = v3d.Camera.from_look_at(
spec=cam_spec,
pos=[5, 5, 5],
target=[0, 0, 0], # Camera looks at the scene center
)
rays = cam.rays() # Rays in world coordinates
# Project `(*shape, 3)` world coordinates into `(*shape, 2)` pixel coordinates.
px_coords = cam.px_from_world @ point_cloudSee the API for a full list of primitive.
Creating your own primitives is trivial.
Converting any dataclass to dataclass array is trivial:
- Inherit from
v3d.DataclassArray - Use
etils.array_typesto annotate the array fields (or exlicitly usemy_field: Any = dca.field(shape=, dtype=)instead ofdataclasses.field)
from etils.array_types import FloatArray
class MyRay(v3d.DataclassArray):
pos: FloatArray[..., 3]
dir: FloatArray[..., 3]
rays = MyRay(pos=jnp.zeros((H, W, 3)), dir=jnp.ones((H, W, 3)))
assert rays.shape == (H, W)v3d makes it easy to opt-in to the feature you need by implementing the
corresponding protocol.
The best way to get started is to try the Colab tutorials (in the docs/):
Installation:
pip install visu3dUsage:
import visu3d as v3dpip install visu3dThis is not an official Google product.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent