SHARP2021 – CVI²

Important announcements

Announcement of the winners

Julian CHIBANE from Max Planck Institute for Informatics & University of Tübingen was ranked first in the 2 first sub-challenges (Challenge 1 and Challenge 2). The SnT team ( Kseniya CHERENKOVA, Anis Kacem, Gleb GUSEV, and Djamila AOUADA) were ranked second in Challenge 1 and ranked first in Challenge 3. Youseong Lee from MINDs Lab, Inc., Republic of Korea was ranked second in Challenge 3. A summary of the leaderboard can be found below

Challenge 1:

1st place: Julian CHIBANE from Max Planck Institute for Informatics & University of Tübingen, Germany
2^nd place: The SnT team ( Kseniya CHERENKOVA, Anis KACEM, Gleb GUSEV, and Djamila AOUADA), SnT and Artec3D, Luxembourg

Challenge 2:

1st place: Julian CHIBANE from Max Planck Institute for Informatics & University of Tübingen, Germany

Challenge 3:

1st place: The SnT team (Kseniya CHERENKOVA, Anis KACEM, Gleb GUSEV, and Djamila AOUADA), SnT and Artec3D, Luxembourg
2^nd place: Youseong Lee from MINDs Lab, Inc., Republic of Korea

Winners

The basis for decision: The organizers of SHARP challenge have implemented an algorithm for evaluating the submissions of the participants, this algorithm provides a score indicating the accuracy of the method in percentage. The higher the score is the better.

Prizes: The total prize pool for this challenge was 8K euros divided as follows

Julian CHIBANE is awarded 4K euros (2k euros for Challenge 1 + 2k euros for Challenge 2)
The SnT team is awarded 3K euros (1k euros for Challenge 1 + 2k euros for Challenge 3)
Youseong Lee is awarded 1K euros for Challenge 3

Workshop and Challenge were held virtually in conjunction with CVPR on June 25, 2021

The recording of the workshop is available on YouTube here

The 2nd SHApe Recovery from Partial textured 3D scans (SHARP) Workshop and Challenge will be held virtually in conjunction with CVPR on June 25, 2021 (4:00 p.m. – 8:30 p.m. CET). Research on data-driven 3D reconstruction of shapes has been very active in the past years thanks to the availability of large datasets of 3D models. However, the focus has been so far on recovering the geometry only and very little has been proposed for reconstructing full 3D objects with shape and texture at the same time.

The goal of this workshop is to promote concepts that exploit both shape and texture in the processing of 3D scans in general, with a special attention to the specific task of recovery from partial and noisy data.

This workshop will host a paper submission track and a competition:

The paper submission track encourages participants to submit novel contributions on data-driven shape and texture processing. A call for papers specifying the topics of interest can be found below.
The competition focuses on the reconstruction of full high-resolution 3D meshes from partial or noisy 3D scans and includes 3 challenges and 3 datasets:
- The first one involves the recovery of textured 3D human body scans. The dataset used in this scope is the 3DBodyTex.v2 dataset, containing 2500 textured 3D scans. It is an extended version of the original 3DBodyTex data, first published in the 2018 International Conference on 3D Computer Vision, 3DV 2018.
- The second challenge involves the recovery of generic object scans from the 3DObjectTex.v2 dataset, which is a subset from the ViewShape online repository of 3D scans. This dataset contains over 2000 various generic objects with different levels of complexity in texture and geometry.
- The third challenge focuses on the recovery of fine object details in the form of sharp edges from noisy sparse scans with soft edges. The CC3D dataset, introduced at the 2020 IEEE International Conference on Image Processing (ICIP), will be used for this purpose. It contains over 50k pairs of CAD models and their corresponding 3D scans.

This is the second edition of SHARP, after the first one held successfully in conjunction with ECCV 2020.

Sponsor

Call for Participation (Challenges)

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.

🏆 An overall 9k€ will be awarded as cash prizes to the winners.

Challenge 1: Recovery of Human Body Scans

CHALLENGE 1

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.

By entering Challenge 1, participants agree to be bound by these Terms and Conditions.

Challenge 2: Recovery of Generic Object Scans

CHALLENGE 2

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.

By entering Challenge 2, participants agree to be bound by these Terms and Conditions.

Challenge 3: Recovery of Feature Edges in 3D Object Scans

CHALLENGE 3

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.

By entering Challenge 3, participants agree to be bound by these Terms and Conditions.

All challenges will be available with the same deadline for registration. In order to participate to SHARP challenges, participants have to submit a short accompanying paper describing their proposed solutions. Details on the submission of the accompanying papers will be communicated soon. A working implementation of the method is optional, but encouraged.

Call for Papers (Paper Submission Track)

The main focus of SHARP is to encourage paper submissions on high-resolution 3D shape and texture recovery from partial data, especially as accompanying papers to the challenge submissions. In addition, all topics that relate to and serve the goal of data-driven shape and texture processing are of interest. This includes original contributions at different levels of data processing; for different industrial applications, as well as proposals for new evaluation metrics and relevant original datasets. Topics of interest include, but are not limited to:

Textured 3D data representation and evaluation
Textured 3D scan feature extraction
Generative modelling of textured 3D scans
Learning-based 3D reconstruction
Joint texture and shape matching
Joint texture and shape completion

Semantic 3D data reconstruction
Effective 3D and 2D data fusion
Textured 3D data refinement
3D feature edge detection and refinement
High-level representations of 3D data
CAD modeling from unstructured 3D data

Authors are encouraged to submit their contributions to the SHARP 2021 submission site. All accepted papers will be included in the CVPR 2021 conference proceedings. The papers will be peer-reviewed and they must comply with the CVPR 2021 proceedings style and format. More details about the submission formats can be found in the submission page.