Official repo for our 3DV 2021 paper "Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements".

Last update: Dec 13, 2022

Related tags

Deep Learning IHMR

Overview

Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements

Yu Rong, Jingbo Wang, Ziwei Liu, Chen Change Loy

Paper.
Project Page

Installation

Please refer to install.md to install the required packages and prepare data and model.

Training

Please refer to train.md for training the models, including IHMR-Baseline and IHMR-MLP.

Testing

Please refer to [test.md][docs/test.md] for testing the models, including IHMR-Baseline, IHMR-MLP, and IHMR-OPT

Citation

Please cite the following papers in your publications if it helps your research:

@InProceedings{rong2021ihmr,
    author = {Rong, Yu and Wang, Jingbo and Liu, Ziwei and Loy, Chen Change},
    title = {Monocular 3D Reconstruction of Interacting Handsvia Collision-Aware Factorized Refinements},
    booktitle = {International Conference on 3D Vision},
    year = {2021}
}

@InProceedings{rong2021frankmocap,
    title={FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration},
    author={Rong, Yu and Shiratori, Takaaki and Joo, Hanbyul},
    booktitle={IEEE International Conference on Computer Vision Workshops},
    year={2021}
}

Official repo for our 3DV 2021 paper "Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements".

Related tags

Overview

Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements

Installation

Training

Testing

Citation

Owner

Yu Rong

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

Coarse implement of the paper "A Simultaneous Denoising and Dereverberation Framework with Target Decoupling", On DNS-2020 dataset, the DNSMOS of first stage is 3.42 and second stage is 3.47.

Configure SRX interfaces with Scrapli

E2e music remastering system - End-to-end Music Remastering System Using Self-supervised and Adversarial Training

Pytorch implementation of the paper "Optimization as a Model for Few-Shot Learning"

Cookiecutter PyTorch Lightning

PyTorch implementation of Histogram Layers from DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation

The official codes for the ICCV2021 presentation "Uniformity in Heterogeneity: Diving Deep into Count Interval Partition for Crowd Counting"

Residual Dense Net De-Interlace Filter (RDNDIF)

This toolkit provides codes to download and pre-process the SLUE datasets, train the baseline models, and evaluate SLUE tasks.

SMD-Nets: Stereo Mixture Density Networks

Improving Factual Completeness and Consistency of Image-to-text Radiology Report Generation

Open-source code for Generic Grouping Network (GGN, CVPR 2022)

Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)

Implementation for ACProp ( Momentum centering and asynchronous update for adaptive gradient methdos, NeurIPS 2021)

Implementation of Squeezenet in pytorch, pretrained models on Cifar 10 data to come

Neural Turing Machine (NTM) & Differentiable Neural Computer (DNC) with pytorch & visdom

CCAFNet: Crossflow and Cross-scale Adaptive Fusion Network for Detecting Salient Objects in RGB-D Images

Code for the Higgs Boson Machine Learning Challenge organised by CERN & EPFL

Train Scene Graph Generation for Visual Genome and GQA in PyTorch >= 1.2 with improved zero and few-shot generalization.