Oran Gafni
RESEARCH ENGINEERING MANAGER | TEL AVIV, ISRAEL
Oran is a research engineering manager at GenAI and previously a researcher at Facebook AI Research (FAIR). Oran's research focuses on deep learning, and topics such as computer vision, generative models, and image/video/3D generation from text. He holds a B.Sc. and an M.Sc. in Electrical Engineering from Tel-Aviv University, under the supervision of Prof. Lior Wolf.
Research Areas
Oran's Publications
July 02, 2024
GRAPHICS
COMPUTER VISION
Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials
Roman Shapovalov, Andrea Vedaldi, David Novotny, Emilien Garreau, Filippos Kokkinos, Mahendra Kariya, Natalia Neverova, Oran Gafni, Tom Monnier, Yanir Kleiman, Yawar Siddiqui
July 02, 2024
July 02, 2024
GRAPHICS
COMPUTER VISION
Meta 3D Gen
Yawar Siddiqui, Animesh Karnewar, Natalia Neverova, Andrea Vedaldi, Ang Cao, Antoine Toisoul, David Novotny, Emilien Garreau, Eric-Tuan Le, Filippos Kokkinos, Idan Azuri, Iurii Makarov, Mahendra Kariya, Omri Harosh, Oran Gafni, Raphael Bensadoun, Roman Shapovalov, Tom Monnier, Yanir Kleiman
July 02, 2024
July 02, 2024
GRAPHICS
COMPUTER VISION
Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objects
Oran Gafni, Andrea Vedaldi, Idan Azuri, Natalia Neverova, Omri Harosh, Raphael Bensadoun, Yanir Kleiman
July 02, 2024
February 13, 2024
GRAPHICS
COMPUTER VISION
IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation
Iro Laina, Christian Rupprecht, Filippos Kokkinos, Andrea Vedaldi, Luke Melas-Kyriazi, Natalia Neverova, Oran Gafni
February 13, 2024
December 26, 2023
GRAPHICS
COMPUTER VISION
Mosaic-SDF for 3D Generative Models
Omri Puny, Oran Gafni, Lior Yariv, Natalia Neverova, Yaron Lipman
December 26, 2023
July 26, 2022
Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors
Oran Gafni, Adam Polyak, Devi Parikh, Oron Ashual, Shelly Sheynin, Yaniv Taigman
July 26, 2022
June 13, 2020
June 13, 2020
Our approach
Latest news
Foundational models
Meta © 2026