DeepSDFStruct.deep_sdf.models#

DeepSDF Model Classes#

This module provides the DeepSDFModel class, which wraps a trained decoder network and latent vectors for evaluating learned implicit representations.

The model can be used to: - Decode latent codes to SDF values at query points - Export models for deployment (TorchScript/LibTorch) - Integrate with gradient-based optimization

Classes#

DeepSDFModel: Main interface for trained DeepSDF models, combining a decoder network with learned latent vectors.

Classes

DeepSDFModel(decoder, ...)

Wrapper for trained DeepSDF decoder and latent vectors.

class DeepSDFStruct.deep_sdf.models.DeepSDFModel(decoder, trained_latent_vectors, device)#

Bases: object

Wrapper for trained DeepSDF decoder and latent vectors.

This class provides a convenient interface for using trained DeepSDF models. It combines the decoder network (which maps latent+position to SDF values) with the trained latent vectors (which encode different shapes).

The model supports both constant latent codes (one code for all query points) and spatially-varying codes (different codes per query point), enabling flexible shape representation.

Parameters:

decoder (torch.nn.Module) – The trained decoder network. Should accept input of shape (N, latent_dim + 3) and output SDF values of shape (N, 1).
trained_latent_vectors (torch.Tensor) – Trained latent codes of shape (num_shapes, latent_dim). Each row encodes one learned shape.
device (str or torch.device) – Device for computation (‘cpu’ or ‘cuda’).

_decoder#

The decoder network.

Type:: torch.nn.Module

_trained_latent_vectors#

The latent code library.

Type:: torch.Tensor

device#

Computation device.

Type:: str or torch.device

_decode_sdf(latent_vec, queries)#: Decode SDF values from a latent code and spatial queries.

export_libtorch_executable(filename)#

Export model to TorchScript for C++ deployment.

Parameters:: filename (str)

Examples

>>> import torch
>>> from DeepSDFStruct.deep_sdf.models import DeepSDFModel
>>>
>>> # Assume we have a trained decoder and latent vectors
>>> # decoder = ...
>>> # latents = torch.randn(10, 256)  # 10 shapes, 256-dim codes
>>>
>>> # Create model
>>> model = DeepSDFModel(decoder, latents, device='cuda')
>>>
>>> # Query first shape
>>> points = torch.rand(1000, 3, device='cuda')
>>> distances = model._decode_sdf(latents[0], points)
>>>
>>> # Use with SDFfromDeepSDF
>>> from DeepSDFStruct.SDF import SDFfromDeepSDF
>>> sdf = SDFfromDeepSDF(model, latent_code=latents[0])
>>> mesh = create_3D_mesh(sdf, N_base=64, mesh_type='surface')

Notes

The decoder architecture typically consists of multiple fully-connected layers with skip connections. See networks/ for architecture definitions.

References

export_libtorch_executable(filename)#

Export the trained decoder model to a TorchScript file for use with LibTorch (C++).

Parameters:: filename (str) – Path where the TorchScript model will be saved (e.g. “decoder.pt”).

Example

>>> model.export_libtorch_executable("decoder.pt")
Example input:  tensor([[...]])
Example Output: tensor([[...]])
# The file "decoder.pt" is now ready for loading in LibTorch.

DeepSDFStruct.deep_sdf.models#

DeepSDF Model Classes#

Classes#

This Page