Yanir Kleiman

Mobile: +44 73053 14271
Website: www.yanirk.com
Email Address: yanirk@gmail.com

I am an experienced computer graphics researcher and developer.
I am currently a research engineer at Meta AI.
I completed my PhD at Tel Aviv University where I was a part of the Computer Graphics lab,
followed by a post-doc at Laboratoire d'Informatique (LIX) at École Polytechnique near Paris.

My research initially focused on shape analysis, shape and image similarity, segmentation and shape matching. In recent years I have worked mainly on 3D reconstruction and generative AI of 3D shapes.

I also have prior experience in VFX production.

Professional Experience

2020 - Now
Research Engineer, Meta
In recent years I was a research engineer at FAIR / GenAI at Meta. Selected projects:
  • Contributed to Llama 3 and Llama 4 multi-modal post-training
  • Meta 3D TextureGen project (joint first author)
  • Meta 3D AssetGen
  • Replay dataset: aligned multi-modal multi-view videos for 3D reconstruction
    (joint first author)
Technical leadership of 3D shapes dataset management and curation:
  • Evaluation of datasets from external vendors
  • Ingestion and conversion of shapes in various 3D formats
  • Shape preprocessing and rendering setups
  • PBR materials manipulation and verification
Previously, I was part of Spark AR, developing 3D studio software that artists use to create 3D effects for mobile phones and headsets.
  • Incorporated real time location tracking simulation in Spark Studio
  • Worked on simulated environments in Spark Studio
2019 - 2020
Research Scientist, Shapes AI
Shapes AI was an early stage startup company that developed solutions in the space of 3D shapes and video-based visual reasoning. I led the research efforts in the 3D domain, which include generative modeling, point clouds processing, and 3D search.
  • Worked on generative modeling research.
  • Developed a deep learning method to clean up noisy point clouds.
  • Developed an end-to-end solution for generating thousands of textured shapes from a small set, which includes procedural modeling and texture generation.
  • Worked on 3D shapes search where the input is an image or a 3D shape.
2018 - 2019
Software Developer, DNEG
DNEG is a visual effects company in London. I developed tools for the "on-set" department which is responsible of taking reference footage on the set of a show.
  • Worked on tools for browsing massive sets of 100K+ images.
  • Developed a deep learning method to detect color charts in images.
  • Developed a deep learning method to remove noise artifacts from images.
  • Developing in C++, Python, and MEL script language.
  • Worked with Maya, Nuke, Alembic, libraw, OpenEXR, and other common tools of the VFX industry.
2016 - 2017
Post-doc Researcher, Laboratoire d'Informatique, École Polytechnique, France.
Part of a computer graphics group led by Maks Ovsjanikov.
2011 - 2016
PhD Student, Computer Science, Tel Aviv University, Israel.
Computer graphics lab, under the supervision of Prof. Daniel Cohen-Or.
2010
Lighting and Rendering TD / Compositor, Crew 972
Worked on "The Looney Tunes Show" for Warner Bros.
  • Lighting and set dressing shots in Maya.
  • Creating visual effects (dust, smoke) using dynamics and MEL scripting.
  • Creating render layers and monitoring the render process on a render farm.
  • Final compositing of shots using Nuke.
2009
3D Artist, Gravity Israel Visual Effects
Worked mostly on shading, lighting, and render passes.
Additional work included modeling and scripting.
2009
Freelance Effects Artist, "Deus".
Created visual effects for several shots on the show from start to finish.
Tracking, modeling, simulation, animation, rendering and compositing.
2008 - 2009
3D Animation and Visual Effects Diploma, Vancouver Film School, Canada.
Visual Effects specialization, graduated with honors.
2008
Algorithms Developer, MutualArt Inc.
Developed and implemented automated text categorization and linking algorithms with C# and SQL Server.
2005 - 2007
Development Team Leader, Amobee Media Systems Ltd.
Led a team that developed a web based back-office system that enables advertisers to manage their campaigns and creative ads.
  • .NET infrastructures (ASP.NET) and SQL Server development.
  • Management, task planning, recruiting and training.
  • Requirements specification, GUI design (flow and graphic design).
  • Java development.

Expertise

ML / AI
Exeprience with both diffusion models and LLMs
3D Geometry
Working with meshes, point clouds, and implicit 3D representations (NeRF / SDF)
3D Software
Deep knowledge of the content production pipeline and Blender and Maya scripting

Academics

2016
PhD in Computer Science, Tel Aviv University, Israel.
Dissertation: Semantic Similarity and Correspondence of 3D Shapes and Images.
2005
M.Sc. in Computer Science, Tel Aviv Academic College, Israel
Graduated with honors.
2000
B.Sc. in Math and Computer Science, Tel Aviv University, Israel

Publications

Joint first authors marked with *
2024
The llama 3 herd of models
Abhimanyu Dubey et al. (500+ authors)
arXiv, 2024
2024
Meta 3D Gen (technical report)
*Raphael Bensadoun, *Tom Monnier, *Yanir Kleiman, Filippos Kokkinos, Yawar Siddiqui, Mahendra Kariya, Omri Harosh, Roman Shapovalov, Benjamin Graham, Emilien Garreau, Animesh Karnewar, Ang Cao, Idan Azuri, Iurii Makarov, Eric-Tuan Le, Antoine Toisoul, David Novotny, Oran Gafni, Natalia Neverova, Andrea Vedaldi
Meta Research, 2024
2024
Meta 3D AssetGen: Text-to-mesh generation with high-quality geometry, texture, and pbr materials
Yawar Siddiqui, Tom Monnier, Filippos Kokkinos, Mahendra Kariya, Yanir Kleiman, Emilien Garreau, Oran Gafni, Natalia Neverova, Andrea Vedaldi, Roman Shapovalov, David Novotny
NeurIPS, 2024
2024
Meta 3D TextureGen: fast and consistent texture generation for 3d objects
*Raphael Bensadoun, *Yanir Kleiman, Idan Azuri, Omri Harosh, Andrea Vedaldi, Natalia Neverova, Oran Gafni
arXiv, 2024
2023
Replay: Multi-modal multi-view acted videos for casual holography
*Roman Shapovalov, *Yanir Kleiman, *Ignacio Rocco, David Novotny, Andrea Vedaldi, Changan Chen, Filippos Kokkinos, Ben Graham, Natalia Neverova
ICCV, 2023
2019
Boosting VFX Production with Deep Learning
Yanir Kleiman, Simon Pabst, Patrick Nagle
ACM SIGGRAPH Talks, 2019
2018
PCPNet: Learning Local Shape Properties from Raw Point Clouds
*Paul Guerrero, *Yanir Kleiman, Maks Ovsjanikov, Niloy J. Mitra
Computer Graphics Forum (Proceedings of Eurographics), 2018
2018
Group optimization for multi-attribute visual embedding
Qiong Zeng, Wenzheng Chen, Zhuo Han, Mingyi Shi, Yanir Kleiman, Daniel Cohen-Or, Baoquan Chen, Yangyan Li
Visual Infromatics, 2018
2018
Dance to the beat: Synchronizing motion to audio
Rachele Bellini, Yanir Kleiman, Daniel Cohen-Or
Computational Visual Media, 2018
2018
Robust Structure-Based Shape Correspondence
Yanir Kleiman, Maks Ovsjanikov
Computer Graphics Forum, 2018
2017
Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering
Matteo Denitto, Simone Melzi, Manuele Bicego, Umberto Castellani, Alessandro Farinelli, Mario A. T. Figueiredo, Yanir Kleiman, Maks Ovsjanikov
ICCV 2017
2016
Semantic Similarity and Correspondence of 3D Shapes and Images
Yanir Kleiman
PhD Dissertation
2016
Time-varying Weathering in Texture Space
Rachele Bellini, Yanir Kleiman, Daniel Cohen-Or.
ACM Transactions on Graphics (Proceedings of SIGGRAPH), 2016
2016
Toward Semantic Image Similarity from Crowdsourced Clustering
Yanir Kleiman, George Goldberg, Yael Amsterdamer, Daniel Cohen-Or.
The Visual Computer (Proceedings of CGI), 2016
2015
SHED: Shape Edit Distance for Fine-grained Shape Similarity
Yanir Kleiman, Oliver van Kaick, Olga Sorkine-Hornung, Daniel Cohen-Or.
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 2015
2015
DynamicMaps: Similarity-based Browsing through a Massive Set of Images
Yanir Kleiman, Dov Danon, Jasmin Felberbaum, Joel Lanir, Daniel Cohen-Or.
Proceedings of ACM Conference on Human Factors in Computing Systems, 2015
2014
Shape Segmentation by Approximate Convexity Analysis
Oliver van Kaick, Noa Fish, Yanir Kleiman, Shmuel Asafi, Daniel Cohen-Or.
ACM Transactions on Grpahics (TOG), 2014
2013
Dynamic Maps for Exploring and Browsing Shapes
Yanir Kleiman, Noa Fish, Joel Lanir, Daniel Cohen-Or.
Computer Graphics Forum (Proceedings of SGP), 2013
2011
Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering
Oana Sidi, Oliver van Kaick, Yanir Kleiman, Hao Zhang, Daniel Cohen-Or.
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 2011
2007
Paging with connections: FIFO strikes again
Leah Epstein, Yanir Kleiman, Jiri Sgall, Rob van Stee.
Theoretical computer science, 2007

Public Talks and Academic Visits

2017
Invited Talk, Google Zurich, Switzerland.
2016
Invited Talk, Hebrew University of Jerusalem, Israel.
2016
CGI 2016
Toward Semantic Image Similarity from Crowdsourced Clustering.
2016
PhD Dissertation Public Lecture, Tel Aviv University, Israel.
2015
Visiting Researcher, Shandong University, China.
2015
SIGGRAPH Asia 2015
SHED: Shape Edit Distance for Fine-grained Shape Similarity.
2015
Visiting Researcher, École Polytechnique, France.
2013
Invited Talk, Max Planck Institute for Informatics, Germany.
2013
Visiting Researcher, ETH Zurich, Switzerland.
2013
SGP 2013
Dynamic Maps for Exploring and Browsing Shapes.

Awards and Fellowships

2016-2017
Chateaubriand Fellowship for Postdoctoral Research
2014-2015
Google Focused Research Award
I was partly funded by this grant during my PhD studies.
2010
Animex Visual Effects Award
Runner up for Best Visual Effects in Animex 2010 Festival.
2005
Excellence Scholarship - Tel Aviv Academic College
Awarded for excellence during my M.Sc. studies.
Yanir Kleiman Mobile: +44 73053 14271 Website: www.yanirk.com Email Address: yanirk@gmail.com