luyangzhu/nba-players

ECCV2020 - Official code repository for the paper : Reconstructing NBA Players

Reconstructing NBA Players

[Project Page] [Paper] [Dataset]

Overview

This repository maintains the official implementation of our ECCV 2020 paper:

Reconstructing NBA Players

By Luyang Zhu, Konstantinos Rematas, Brian Curless, Steve Seitz, Ira Kemelmacher-Shlizerman

License

This work is licensed under Creative Commons BY-NC-SA 4.0.

Installation

Please see docs/INSTALL.md

Full Pipeline Demo

Please see docs/DEMO.md

Testing Mesh Generation Networks

Please see docs/TEST.md

Training Mesh Generation Networks

Please see docs/TRAIN.md

Citation

If you use this code for your research, please citing our work.

@InProceedings{zhu_2020_eccv_nba,
    author={Zhu, Luyang and Rematas, Konstantinos and Curless, Brian and Seitz, Steve and Kemelmacher-Shlizerman, Ira},
    title={Reconstructing NBA players},
    booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
    month = {August},
    year={2020}
}

nba-players's Issues

求助关于您的另一篇论文

您好，我看了您的论文
Learning to Estimate 3D Human Pose and Shape from a Single Color Image
以后，受益匪浅，想问下您，这个代码目前可以开源吗，我十分想对此代码进行复现，但目前遇到了一些问题

ask about your other paper

您好，我看了您的论文
Learning to Estimate 3D Human Pose and Shape from a Single Color Image

预训练模型

感谢您的作品，有打算放出预训练模型吗？想体验一下您的demo

pkl and npy files

Hi @luyangzhu, thanks for your great work!

I have interest on the skinning model and the spiral convolution used in it.
Especially, I want to implement and test those codes but I can't find necessary files such as 'train_verts.npy'.

Where can I find files loaded in the 33-40 lines of mesh_utils.py ?

Thanks in advance.

About the laplace constraint

Hi, thanks for your great work. It seems that you did not consider the transformation, for example rotation, in you laplacian constraint if I understand the code correctly?