akumar14

Occlusion-Robust-MoFA

3D-face-reconstruction

3D Face Reconstruction from a Single Image using Direct Volumetric CNN Regression.

3DDFA_V2

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

3DSfMFaceReconstruction

Deep Unsupervised 3D SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment.

3FabRec

3FabRec: Fast Few-shot Face alignment by Reconstruction - PyTorch implementation

AdaptiveWingLoss

[ICCV 2019] Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression - Official Implementation

akumar.github.io

Personal webpage

AlphaPose

Real-Time and Accurate Multi-Person Pose Estimation&Tracking System

Beyond3DMM

Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction, ECCV, 2020

Deep3DFaceRecon_pytorch

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.

detr

End-to-End Object Detection with Transformers

Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks

code for ICCV 2019 Paper Exploiting Spatial-temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks

extreme_3d_faces

Extreme 3D Face Reconstruction: Looking Past Occlusions

face.evoLVe.PyTorch

🔥🔥High-Performance Face Recognition Library on PyTorch🔥🔥

flownet2-pytorch

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

landmark-detection

Several landmark detection algorithms, implemented in PyTorch.

mobilenetv3.pytorch

74.3% MobileNetV3-Large and 67.2% MobileNetV3-Small model on ImageNet

MUNIT

Multimodal Unsupervised Image-to-Image Translation

next_word_prediction

Pytorch implementation of next word prediction. Includes my own implementation of Google AI's Transformer architecture

OpenSeeFace

Robust realtime face and facial landmark tracking with Unity integration

PFLD-pytorch

PFLD pytorch Implementation

PIPNet

Efficient facial landmark detector

portfolio

my personal portfolio site

PRNet

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018)

pytorch_face_landmark

Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Support both coordinate-based and heatmap-based inference; Up to 100 FPS landmark inference speed with SOTA face detector on CPU.

pytorch_geometric

Geometric Deep Learning Extension Library for PyTorch

Res2Net-PretrainedModels

(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

SADRNet

[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

TDAN-VSR-CVPR-2020

TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution, CVPR 2020

VideoPose3D

Efficient 3D human pose estimation in video using 2D keypoint trajectories