Dino v1 wrapper using huggingface transformer implementation.

Synthesizer that renders a triplane volume with planes and a camera. Reference: EG3D: https://github.com/NVlabs/eg3d/blob/main/eg3d/

Transformer with condition that generates a triplane representation. Reference: Timm: https://github.com/huggingface/pytorch-image-m

Class to help manage printing simple timing of code execution.

Transformer block that takes in a cross-attention condition and another modulation vector applied to sub-blocks.

This class implements the FlexiCubes method for extracting meshes from scalar fields. It maintains a series of lookup tables and indices to

Modified original version to filter out-of-box samples as TensoRF does. Reference: TensoRF: https://github.com/apchenstu/TensoRF/blo

Joint encoding of visual appearance and location using MLPs

Image Matching Frontend (SuperPoint + SuperGlue)

Multi-head attention to increase model expressivitiy

Triplane decoder that gives RGB and sigma values from sampled features. Using ReLU here instead of Softplus in the original implementation.

Triplane decoder that gives RGB and sigma values from sampled features. Using ReLU here instead of Softplus in the original implementation.

SuperGlue feature matching middle-end Given two sets of keypoints and locations, we determine the correspondences by: 1. Keypoint Encod

SuperPoint Convolutional Detector and Descriptor SuperPoint: Self-Supervised Interest Point Detection and Description. Daniel DeTone, Tomasz

Construct the CLS token, position and patch embeddings. Optionally, also the mask token.

This corresponds to the Block class in the timm implementation.

This class turns `pixel_values` of shape `(batch_size, num_channels, height, width)` into the initial `hidden_states` (patch embeddings) of s

The residual connection is defined in ViTLayer instead of here (as is the case with other models), due to the layernorm applied before each b

Full model of the large reconstruction model.

Full model of the large reconstruction model.

Synthesizer that renders a triplane volume with planes and a camera. Reference: EG3D: https://github.com/NVlabs/eg3d/blob/main/eg3d/

An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.

Class to help process image streams. Four types of possible inputs:" 1.) USB Webcam. 2.) An IP camera 3.) A directory of imag