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

Last update: Dec 13, 2022

Overview

(ACMMM 2021 Oral) SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment

This repository shows two tasks: Face landmark detection and Face 3D reconstruction, which is described in this paper: Deep Unsupervised 3D SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment.

Installation

Clone the repository.
install dependencies.

pip install -r requirement.txt

Face landmark detection

Running a pre-trained model

Download landmark pre-trained model at GoogleDrive, and put it into FaceLandmark/model/
Run the test file

python Facial_landmark.py

Face 3D reconstruction

Running a pre-trained model

Download face 3D reconstruction pre-trained model at GoogleDrive, and put it into FaceReconstruction/checkpoints/
Run the inference.py file to generate disparity map

python inference.py --dataset-dir './FaceReconstruction/test_image/' --output-dir './FaceReconstruction/output/' --pretrained './FaceReconstruction/checkpoints/dispnet_model_best.pth.tar' --resnet-layers 18 --output-disp

Run the generate_ply.py file to generate point cloud .ply file

python generate_ply.py

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

Related tags

Overview

(ACMMM 2021 Oral) SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment

Installation

Face landmark detection

Running a pre-trained model

Face 3D reconstruction

Running a pre-trained model

Owner

BoomStar

reimpliment of DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

PyTorch reimplementation of REALM and ORQA

A small demonstration of using WebDataset with ImageNet and PyTorch Lightning

Implementation of GGB color space

Official implementation for the paper "Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection"

Cancer metastasis detection with neural conditional random field (NCRF)

Code corresponding to The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents

Code for our CVPR2021 paper coordinate attention

OSLO: Open Source framework for Large-scale transformer Optimization

Anomaly Detection Based on Hierarchical Clustering of Mobile Robot Data

The PASS dataset: pretrained models and how to get the data - PASS: Pictures without humAns for Self-Supervised Pretraining

Pytorch implementation of the unsupervised object discovery method LOST.

Tutorial in Python targeted at Epidemiologists. Will discuss the basics of analysis in Python 3

Data-Uncertainty Guided Multi-Phase Learning for Semi-supervised Object Detection

Shape-Adaptive Selection and Measurement for Oriented Object Detection

Simple ONNX operation generator. Simple Operation Generator for ONNX.

The implementation of the algorithm in the paper "Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data" published in ICML 2020.

[peer review] An Arbitrary Scale Super-Resolution Approach for 3D MR Images using Implicit Neural Representation

An implementation of chunked, compressed, N-dimensional arrays for Python.

In this project we combine techniques from neural voice cloning and musical instrument synthesis to achieve good results from as little as 16 seconds of target data.