Initialize the image conditioning model.

Naive implementation of scaled dot product attention.

Normalizes the given weights to be non-negative. If input weights are None, it creates and returns a set of weights of ones.

Create sinusoidal position embeddings. Args: x: a 1-D Tensor of N indices Returns: an (N, D) Tensor

Connects four neighboring dual vertices to form a quadrilateral. The quadrilaterals are then split into triangles based on the gamma

Bake texture to a mesh from multiple observations. Args: vertices (np.array): Vertices of the mesh. Shape (V, 3). faces (np.

Return the attention configuration of the model.

Calculate serialization and partitioning for a set of coordinates. Args: tensor (SparseTensor): The input tensor. window_siz

Calculate serialization and partitioning for a set of coordinates. Args: tensor (SparseTensor): The input tensor. window_siz

construct a dense grid based on resolution

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Args: cubes [Vx8] verts index for each cube value [Vx8xM] value to be scattered Operation: reduced[cubes[i][j]][k] +=

Decode the structured latent. Args: slat (sp.SparseTensor): The structured latent. formats (List[str]): The

Evaluate spherical harmonics at unit directions using hardcoded SH polynomials. Works with torch/np/jnp. ... Can be 0 or more batch d

Expand the DINOv2 patch embedding to accept additional input channels.

Batched version of get_cond that handles B>1 samples. Args: preprocessed_list: List of preprocessed tensors/dicts from p

OpenCV intrinsics to OpenGL perspective matrix Args: intrinsics (torch.Tensor): [3, 3] OpenCV intrinsics matrix near (float)

OpenCV intrinsics to OpenGL perspective matrix Args: intrinsics (torch.Tensor): [3, 3] OpenCV intrinsics matrix near (float)

Load an RGB image and handle alpha / transparency consistently.

Parametrize a mesh to a texture space, using xatlas. Args: vertices (np.array): Vertices of the mesh. Shape (V, 3). faces (n

3D pixel shuffle.

Postprocess a mesh by simplifying, removing invisible faces, and removing isolated pieces. Args: vertices (np.array): Vertices of th

Preprocess the input image.

Render the scene. Background tensor (bg_color) must be on GPU!

Sample x_{t-1} from the model using Euler method. Args: model: The model to sample from. x_t: The [N x C x .

Sample structured latent with the given conditioning. Args: cond (dict): The conditioning information. coord

Sample sparse structures with the given conditioning. Args: cond (dict): The conditioning information. num_s

Apply serialized scaled dot product self attention to a sparse tensor. Args: qkv (SparseTensor): [N, *, 3, H, C] sparse tensor conta

Unbind a sparse tensor along a dimension. Args: input (SparseTensor): Sparse tensor to unbind. dim (int): Dimension to unbin

Apply windowed scaled dot product self attention to a sparse tensor. Args: qkv (SparseTensor): [N, *, 3, H, C] sparse tensor contain

Create sinusoidal timestep embeddings. Args: t: a 1-D Tensor of N indices, one per batch element. These

Convert a batch of network outputs to 3D representations. Args: x: The [N x * x C] sparse tensor output by the network.

Convert a batch of network outputs to 3D representations. Args: x: The [N x * x C] sparse tensor output by the network.