A warm welcome from the organisers!

Diego Thomas Vincent Nozick Takuya Funatomi

 

Self introduction and presentation slides.

 

  • Kindly include your self-introduction slides to this Google Slide.
  • Kindly include your presentation slides to this Google Slide.

 

We thank our generous sponsors

 

 

What is a Shonan Meeting?

 

Excerpt from NII:

 

NII Shonan Meetings, following the well-known Dagstuhl Seminars, aim to internationally promote informatics research, by providing another world's premier venue for world-class scientists, promising young researchers, and practitioners to come together in Asia to exchange their knowledge, discuss their research findings, and explore a cutting-edge informatics topics.

 

The meetings are held in Shonan Village Center near Tokyo, which offers facilities for conferences, trainings, and lodging in a resort-like setting. The friendly and open atmosphere is to promote communications among participants. The NII Shonan Meetings are managed by National Institute of Informatics (NII), Japan.

 

Meeting Abstract

 

In the last decade, deep learning has become ubiquitous in Computer Vision to solve various tasks ranging from object recognition to 3D and 4D capture. A vast majority of recent scientific papers published in top level venues such as the international conference on Computer Vision and Pattern Recognition (CVPR), the International Conference on Computer Vision (ICCV) or the IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI) rely on deep neural models formulated in the linear algebra. This is because of the simplicity of the basic operations in the neurons: scalar multiplication and addition, and the availability of many existing tools such as automatic differentiation in pytorch. However, for some tasks such as 3D transformation, other algebras such as Clifford Algebra (also called Geometric Algebra) have proven to be more efficient. Deep neural networks formulated with geometric algebra have been proposed recently, with promising applications in Computer Graphics. However, none has been applied yet to solve Computer Vision tasks.

 

The meeting is envisaged to focus on new settings and applications of AI models defined with Geometric algebra for tasks in Computer Vision such as 3D and 4D capture. The meeting will invite internationally leading and renown researchers in the fields of Geometric Algebra, Computer Vision and Computer Graphics, whose contributions are likely to be essential to the field. We anticipate that the meeting will foster discussions and new ideas to open a new research area at the frontier between Geometric Algebra, Computer Vision and Computer Graphics. The meeting will also be a wonderful opportunity to strengthen existing collaborations and create new collaborations between top-level researchers in Japan and abroad.

 

Technical Themes

 

1. Deep learning with Geometric Algebra

  • Geometric Algebra
  • Geometric Priors in Deep Neural Networks
  • Clifford Neural Layers
  • Generalization Over Dimensions
  • Deep Learning Formulation Using Geometric Algebra
2. 3D and 4D capture with the support of Geometric AI
  • Neural Radiance Fields (NeRF)
  • Combination of NeRF with Signed Distance Fields (SDF)
  • Neural Warp Fields for Dynamic Scene Reconstruction
  • Potential of Geometric Algebra for Interpolation
Following the spirit of Shonan Meetings, we will consider other related topics, based on the interest of the attendees and the trajectory of the discussions.

 

The primary objective of this seminar is to provide a comprehensive overview of existing alternatives for modeling 3D non-rigid deformations. The initial focus will involve exploring novel formulations of 3D neural warp fields capable of learning to deform 3D shapes and volumes based on input images and videos. A secondary aim is to identify exciting new applications of Geometric AI, specifically employing deep learning with Geometric Algebra, for various tasks in Computer Vision. This involves elucidating the advantages of geometric algebra over classical linear algebra and highlighting the available tools for implementing concrete solutions. To achieve these goals, the seminar aims to bring together participants from diverse backgrounds. This includes experts in Geometric Algebra with a keen interest in its applications in Computer Vision, as well as specialists in Computer Vision intrigued by alternative approaches to modeling 3D shape transformations and manipulations.

 

Keynote Speakers

Martin Roelfs

 

Participants

Takuya FunatomiNARA Institute of Science and Technology, Japan
Vincent NozickUniveristy Gustave Eiffel, France
Diego ThomasKyushu University, Japan
Shizuo KajiKyushu University, Japan
Hiroyuki OchiaiKyushu University, Japan
Jacques-Olivier LachaudUniversity of Savoie Mont-Blanc, France
Eckhard HitzerInternational Christian University, Japan
Georges PapagiannakisUniversity of Crete / FORTH-ICS, Greece
Kanta TachibanaKogakuin University, Japan
Zhaoyuan YuNanjing Normal University, China
Tomas PajdlaCIIRC - Czech Technical University in Prague, Czech Republic
Hideo SaitoKeio University, Japan
Geraldine MorinUniversité de Toulouse, France
Stephane BreuilsUniversite Savoie Mont Blanc, France
Shohei HidakaJapan Advanced Institute of Science and Technology (JAIST), Japan
Pascal MonasseLIGM, Ecole nationale des ponts et chaussees, France
Takuma ToriiTokyo Denki University, Japan
Clement ChomickiKyushu University, Japan
Marilyn KellerTechnical University of Munich, Germany
Martin RoelfsUniversity of Antwerp, Belgium
Akihiro SugimotoNational Institute of Informatics, Japan

 

Program

 

Contact the organisers if there are any issues with the program.

 

Sunday 18 May

1500 onwardsCheck-in
1900-2100Welcome banquet - Self Intro (1mn per person)

 

Monday 19 May

0730-0900Breakfast
0900-0915Welcoming address - Diego Thomas, Vincent Nozick, Takuya Funatomi
0915-1000Research introductions (5 mn by each participant)
1000-1030Coffee break
1030-1200Research introductions (5 mn by each participant)
1200-1330Lunch
1330-1400Group photo
1400-1500Tutorial 1 - Martin Roelfs
1500-1530Coffee break
1530-1630Tutorial 2 - Martin Roelfs
1630-1700Coffee break
1700-1800Breakout session 1
1800-1930Dinner
1930-2030EU-style apetizer tasting

 

Tuesday 20 May

0730-0900Breakfast
0900-0915Program briefing
0915-1030Breakout session 2
1030-1100Cofee break
0915-1030Breakout session 3
1200-1330Lunch
1330-1400Keynote 1 - TBA
1400-1430Keynote 2 - TBA
1400-1430Keynote 3 - TBA
1430-1500Keynote 4 - TBA
1500-1530Keynote 5 - TBA
1530-1600Coffee break
1600-1800Breakout session 4
1800-1930Dinner
1930-2030Japan-style apetizer tasting

 

Wednesday 21 May

0730-0900Breakfast
0900-0915Program briefing
0915-1030Breakout session 4
1030-1100Cofee break
0915-1030Breakout session 5
1200-1330Lunch
1330-2045Excursion and dinner

 

Thursday 22 May

0730-0930Breakfast and check-out
0930-1030Final presentations by each group
1030-1100Coffee break
1100-1130Breakout session 6
1130-1200Conclusion and wrap-up
1200-1330Lunch and end of meeting