Extension of the official SMPL implementation to support more joints

Base Dataset Class - Handles data loading and augmentation. Able to handle heterogeneous datasets (different annotations available for differ

Extension of the official FLAME implementation to support more joints

Extension of the official MANO implementation to support more joints

Extension of the official SMPLX implementation to support more functions

"keypoints": { 0: "nose", 1: "left_eye", 2: "right_eye", 3: "left_ear", 4: "right_ear", 5: "left_

Class that handles saving and loading checkpoints during training.

SMPL Iterative Regressor with ResNet50 backbone

Mesh-aligned Feature Extrator As discussed in the paper, we extract mesh-aligned features based on 2D projection of the mesh vertices. The f

Renderer used to render segmentation masks and part segmentations. Internally it uses the Neural 3D Mesh Renderer

PyMAF based Deep Regressor for Human Mesh Recovery PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop, in ICCV

Extension of the official SMPLX implementation to support more joints

Base class for Trainer objects. Takes care of checkpointing/logging/resuming training.

Redefinition of Bottleneck residual block Adapted from the official PyTorch implementation

Dictionary keeping track of the best fit per image in the training set

Feature Extrator with ResNet backbone

Extension of the official SMPLX implementation to support more joints