From 7c9c31edb9515df6f3f21ea93d34ac8573b4c82c Mon Sep 17 00:00:00 2001 From: Anis Kacem Date: Fri, 5 Feb 2021 14:00:56 +0100 Subject: [PATCH] Update README.md --- README.md | 35 ++++++++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 77e60ef..2a4f215 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,31 @@ -# cvpr2021-sharp-workshop +# SHARP: SHApe Recovery from Partial textured 3D scans -Details about the SHARP challenges: -- data processing scripts -- inout scripts -- etc. \ No newline at end of file +[SHARP 2021 website](https://cvi2.uni.lu/sharp2021/) + +A workshop and challenge in conjunction with +[CVPR 2021](http://cvpr2021.thecvf.com). + +Organised by [CVI²](https://cvi2.uni.lu) & [Artec3D](https://www.artec3d.com). + +## Overview + +We propose three challenges. The task of the challenges is to reconstruct a full 3D textured mesh from a partial 3D scan. The first challenge is for human bodies, while the second and third challenges are for a variety of generic objects. The third challenge launches a new unique dataset. + + +- Challenge 1 - Recovery of Human Body Scans: +The task of this challenge is to reconstruct a full 3D textured mesh from a partial 3D human scan acquisition. 3DBodyTex.v2 is used, which consists of about 2500 clothed scans with a large diversity in clothing and in poses. + + +- Challenge 2 - Recovery of Generic Object Scans: +This challenge is focused on textured 3D scans of generic objects. It uses 3DObjectTex.v1 dataset – a subset from the ViewShape repository – containing 2000 textured 3D scans of very diverse objects. + +- Challenge 3 - Recovery of Feature Edges in 3D Object Scans: +This challenge is focused on recovering feature edges of 3D scans. Here, the very recently introduced CC3D dataset is considered. The CC3D dataset contains 50k+ pairs of CAD models and their corresponding 3D scans. + + +🏆 An overall 9k€ will be awarded as cash prizes to the winners. + + +## Detailed instructions + +To be announced. Stay tuned. -- GitLab