diffrp.materials.gltf_material

class diffrp.materials.gltf_material.GLTFMaterial(base_color_factor: Tensor, base_color_texture: GLTFSampler, metallic_factor: float, roughness_factor: float, metallic_roughness_texture: GLTFSampler, normal_texture: GLTFSampler | None, occlusion_texture: GLTFSampler | None, emissive_factor: Tensor | None, emissive_texture: GLTFSampler, alpha_cutoff: float, alpha_mode: Literal['OPAQUE', 'MASK', 'BLEND'])

Bases: SurfaceMaterial

A standard PBR material coherent with GLTF 2.0 Specifications.

__init__(base_color_factor: Tensor, base_color_texture: GLTFSampler, metallic_factor: float, roughness_factor: float, metallic_roughness_texture: GLTFSampler, normal_texture: GLTFSampler | None, occlusion_texture: GLTFSampler | None, emissive_factor: Tensor | None, emissive_texture: GLTFSampler, alpha_cutoff: float, alpha_mode: Literal['OPAQUE', 'MASK', 'BLEND']) → None

alpha_cutoff: float

alpha_mode: Literal['OPAQUE', 'MASK', 'BLEND']

base_color_factor: Tensor

base_color_texture: GLTFSampler

emissive_factor: Tensor | None

emissive_texture: GLTFSampler

metallic_factor: float

metallic_roughness_texture: GLTFSampler

normal_texture: GLTFSampler | None

occlusion_texture: GLTFSampler | None

roughness_factor: float

shade(su: SurfaceUniform, si: SurfaceInput) → SurfaceOutputStandard

The interface for implementing materials. It takes a fragment batch specified as SurfaceUniform and SurfaceInput.

You shall not assume any order or shape of the fragment batch. In other words, the method should be trivial on the batch dimension, that is, the method should return batched outputs equivalent to concatenated outputs from the same batch of input but split into multiple sub-batches.

Most functions implemented with attribute accesses, element/vector-wise operations and DiffRP utility functions naturally have this property.

class diffrp.materials.gltf_material.GLTFSampler(image: torch.Tensor, wrap_mode: Literal['repeat', 'clamp', 'mirror'] = 'repeat', interpolation: Literal['point', 'linear'] = 'linear')

Bases: object

__init__(image: Tensor, wrap_mode: Literal['repeat', 'clamp', 'mirror'] = 'repeat', interpolation: Literal['point', 'linear'] = 'linear') → None

image: Tensor

interpolation: Literal['point', 'linear'] = 'linear'

sample(uv: Tensor)

wrap_mode: Literal['repeat', 'clamp', 'mirror'] = 'repeat'