https://github.com/naver/showme
SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction (Dataset, Contains proposed top baseline reconstructions with estimated camera poses)
https://github.com/naver/showme
hand-object-dataset hand-object-interaction hand-object-reconstruction hand-object-tracking hand-pose-estimation hand-tracking nerf-for-hand-object-reconstruction object-pose-estimation
Last synced: about 1 month ago
JSON representation
SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction (Dataset, Contains proposed top baseline reconstructions with estimated camera poses)
- Host: GitHub
- URL: https://github.com/naver/showme
- Owner: naver
- License: other
- Created: 2023-09-19T00:10:54.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-12-18T16:54:27.000Z (over 1 year ago)
- Last Synced: 2025-03-28T11:21:22.722Z (about 2 months ago)
- Topics: hand-object-dataset, hand-object-interaction, hand-object-reconstruction, hand-object-tracking, hand-pose-estimation, hand-tracking, nerf-for-hand-object-reconstruction, object-pose-estimation
- Language: Python
- Homepage:
- Size: 5.41 MB
- Stars: 16
- Watchers: 3
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction (ICCVW 2023) (ACVR Oral)
[[Paper](https://europe.naverlabs.com/research/showme/)] [[Project Page](https://europe.naverlabs.com/research/showme)]
> [Anilkumar Swamy](https://europe.naverlabs.com/people_user/anilkumar-swamy/),
> [Vincent Lerory](https://europe.naverlabs.com/people_user/vincent-leroy/),
> [Philippe Weinzaepfel](https://europe.naverlabs.com/people_user/philippe-weinzaepfel/),
> [Fabien Baradel](https://fabienbaradel.github.io/),
> [Salma Galaaoui](https://europe.naverlabs.com/people_user/salma-galaaoui/),
> [Romain Brégier](https://europe.naverlabs.com/people_user/romain-bregier/),
> [Matthieu Armando](https://europe.naverlabs.com/people_user/matthieu-armando/),
> [Jean-Sebastien Franco](https://morpheo.inrialpes.fr/~franco/),
> [Grégory Rogez](https://europe.naverlabs.com/people_user/gregory-rogez/)
> *ICCVW 2023*
This repository contains the link for downloading and code for visualizing SHOWMe Hand-Object dataset.
## RGBs Mosaic
## Dataset Information
## Citation
```bibtex
@inproceedings{showme,
title={{SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction}},
author={{Swamy, Anilkumar and Leroy, Vincent and Weinzaepfel, Philippe and Baradel, Fabien and Galaaoui, Salma and Brégier, Romain and Armando, Matthieu and Franco, Jean-Sebastien and Rogez, Grégory}},
booktitle={{ICCVW}},
year={2023}
}
```
# News
- [x] Top baseline 3D Recnostructions and Camera Poses for **quantitative** and **qualitative** comparison
- [x] Dataset Release
- [x] Visualization Scripts Release
# Dataset Download
### [Link](https://download.europe.naverlabs.com/showme)
# 3D recnostruction models and Camera Poses
```To make qualitative and quantitative comparison easier, we release best baseline 3D reconstruction models(mesh files) and the corresponding camera poses, researchers can download these and use for comparision instead of running the whole pipeline again```
### [showme_baseline_recons_camposes](https://download.europe.naverlabs.com/showme/showme_baseline_recons_camposes.tar)
# Scripts
- [x] To print all sequence ids
- [x] To visualize RGB frame
- [x] To visualize RGBD frame
- [x] To visualize GT meshes (hand-object and object)
- [x] To visualize projected meshes
- [x] To visualize mano mesh
- [x] To visualize pixel-aligned depth point clouds
- [x] To render semantic maps (render mano hand and object mesh)
# Running Scripts
## Install
Our code is running using python3.7 and requires the following packages:
- pytorch-1.7.1+cu110
- pytorch3d-0.3.0
- PIL
- numpy
- trimesh
- matplotlib
## Display all sequence ids
```bash
python scripts/dataset_info.py --datadir
```
## Visualize
```bash
python scripts/vis_showme.py --vis_type --datadir --depth_datadir --seq_id --frm_no
```
Arguments help:
- ``````: visualization type argument ( ```rgb``` or ```rgbd``` or ```depth``` or ```ho_mesh``` or ```obj_mesh``` or ```mano_mesh``` or ```proj_verts``` or ```pix_algnd_depth``` )
## Render (renders mano hand and object)
```bash
python scripts/render.py --datadir --outdir --seq_id
```
## License
The code is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 license.
A summary of the CC BY-NC-SA 4.0 license is located here:
https://creativecommons.org/licenses/by-nc-sa/4.0/
The CC BY-NC-SA 4.0 license is located here:
https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode