About me

I am a research scientist working at Ubisoft La Forge (Montreal). Previously, I worked as a Senior Research Scientist at InterDigital R&I (France) and Technicolor Research, and as a Research Engineer at Inria. I obtained my PhD from Inria in 2016.

I develop methods for face capture, facial animation, and avatar reconstruction in video games and interactive entertainment. My research combines capture systems (including lightstage capture) and generative models to create practical tools that solve production challenges and support artists and creators.

I supervise research interns and PhD students, and I am always seeking motivated candidates to contribute to state-of-the-art projects in facial animation and generative models. You can reach me by email: deeb.abdallah AT gmail DOT com

News

• 06/07/2025 We’ve published a new blog post on Ubisoft website, showcasing our work on the paper MoSAR, a technique used by artists to streamline their workflow.
• 25/06/2025: SEREP paper got accepted to ICCV 2025. We introduce a novel learning-based method for monocular facial expression capture and retargeting. More details from Here
• 20/05/2025: One paper accepted to 'AI for Creative Visual Content Generation Editing and Understanding' (CVEU), CVPR 2025. We propose a texture generator model giving artists control over shape, skin tone and fine details. More details from Here
• 09/03/2024: We released FFHQ-UV-Intrinsics dataset that contains intrinsics texture maps for 10K subjects at HD resolution. Download it from here
• 01/03/2024: Mosar paper got accepted to CVPR 2024. MoSAR turns a portrait image into a relightable 3D avatar. More details from Here
• 05/04/2023: We published a technical paper showcasing our FaceLab solution, which was used by artists to capture 3D facial performance for the 2019 film Cats.
• 01/02/2023: S2F2 paper got accepted to FG2023. S2F2 is a robust self-supervised model that esimate 3D shape and reflectance from a monocular image. More details from Here
• 18/05/2022: DeepNextFace is a 3D face reconstruction library from a single monocular RGB image via deep convolutional neural networks and differentiable ray tracing. Check it from https://github.com/abdallahdib/DeepNextFace
• 21/04/2022: NextFace is a lightweight open source library, written in pytorch, for high fidelity face reconstruction. Check it from https://github.com/abdallahdib/NextFace
• 11/10/2021 Our paper on self-supervised monocular 3D face reconstruciton got accepted to ICCV 2021. More details from Here
• 09/03/2021 Our paper on monocular 3D face reconstruction got accepted to EuroGraphics 2021. We achieve realistic 3D face reconstruction from a single image. More details from Here

Publications

Geometry-Aware Texture Generation for 3D Head Modeling with Artist-driven Control
Amin Fadaeinejad, Abdallah Dib, Luiz Gustavo Hafemann, Emeline Got, Trevor Anderson, Amaury Depierre, Nikolaus F. Troje, Marcus A Brubaker, Marc-Andre Carbonneau
AI for Creative Visual Content Generation Editing and Understanding (CVEU), CVPR 2025
pre-print | Project page

SEREP: Semantic Facial Expression Representation for Robust In-the-Wild Capture and Retargeting
Arthur Josi, Luiz Gustavo Hafemann, Abdallah Dib, Emeline Got, Rafael MO Cruz, Marc-Andre Carbonneau
International Conference on Computer Vision (ICCV 2025)
pre-print | Project page

MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shading
Abdallah Dib, Luiz Gustavo Hafemann, Emeline Got, Trevor Anderson, Amin Fadaeinejad, Rafael M. O. Cruz, Marc-Andre Carbonneau
IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR 2024)
pre-print | Project page | Dataset

S2F2: Self-Supervised High Fidelity Face Reconstruction From Monocular Image
Abdallah Dib, Cedric Thebault, Junghyun Ahn, Philippe-Henri Gosselin, Louis Chevallier
International Conference on Automatic Face and Gesture Recognition FG 2023
pre-print | video |

Practical Face Reconstruction via Differentiable Ray Tracing
Abdallah Dib, Gaurav Bharaj, Junghyun Ahn, Cédric Thébault, Philippe-Henri Gosselin, Marco Romeo, Louis Chevallier
Computer Graphics Forum, Eurographics' 2021
paper | video | code

Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing
Abdallah Dib, Cedric Thebault, Junghyun Ahn, Philippe-Henri Gosselin, Christian Theobalt, Louis Chevallier
International Conference on Computer Vision (ICCV 2021)
paper | video | code

PhotoApp: Photorealistic Appearance Editing of Head Portraits
Mallikarjun B R, Ayush Tewari, Abdallah Dib, Tim Weyrich, Bernd Bickel, Hans-Peter Seidel, Hanspeter Pfister, Wojciech Matusik, Louis Chevallier, Mohamed Elgharib, Christian Theobalt
ACM Transactions on Graphics (SIGGRAPH Asia 2021)
paper | video

FaceLab: Scalable Facial Performance Capture for Visual Effects
Andrus, Curtis and Ahn, Junghyun and Alessi, Michele and Dib, Abdallah and Gosselin, Philippe and Thébault, Cédric and Chevallier, Louis and Romeo, Marco
The Digital Production Symposium (DigiPro 2020)
paper

Pose Estimation For A Partially Observable Human Body From RGB-D Cameras
Abdallah Dib, François Charpillet
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015)
paper | video

Robust Dense Visual Odometry For RGB-D Cameras In A Dynamic Environment
Abdallah Dib, François Charpillet
IEEE International Conference on Advanced Robotics (ICAR 2015)
paper | video

Using Hmms for Discriminating Mobile From Static Objects in a 3D Occupancy Grid
Dubois, Amandine and Dib, Abdallah and Charpillet, François
International Conference on Tools with Artificial Intelligence (ICTAI 2011)
paper | video

Personal Devs

Here you find some of my personal projects I did (and continue doing) in spare time. they are related to C++ and Graphics programming (OpenGL/GLSL), and mobile dev (iOS).

OpenGLES 2.0 tutorials (with source code)
In 2013, I wrote educational tutorials on Graphics programming for iOS using OpenGLES shading language. Tutorials were written in C++ with a clean and intuitive API for beginners. It covers: 3D mesh loader, camera movement, normal mappping, gpu skinning, environment mapping, shadow mapping. Code source can be found on my old website from here

Rendering Engine
I Continue developing and maintaining this graphics engine. It is used mainly for visualizing 3D models. it is written in C++/OpenGL and i ported it to many platforms: windows/mac/linux/iOS/Android(via JNI)/Web(via Emiscripten). It implements physically based rendering with various BRDF models (Cook-Torrance, Phong), Deferred shading, Shadow and normal mapping. It has built-in 2D GUI support via 'imgui'.

iOS Graphics Programming
In 2012, I started developing mobile games and apps. In 2017, I removed these apps from App store (Because i didn't have enough time to maintain them). Below are these apps/games. The code source for these apps can be shared upon request.

Jumper Buggy
Developed in 2013. A 3D action and car simulation game for iOS. It uses the old OpenDynamics Engine for physics simulation. Written in C++/OpenGL. Video from here

Mosaic Puzzle
Developed in 2014. The goal of this educational game is to help children develop their eye<->hand coordination skills. Written in C++/OpenGL.

Camera Art Effects
Developed in 2012. It is photography application for iOS ( iPhone, iPod and iPad) that lets you apply filter and effects to your camera and in real time. It uses optimized GLSL shaders to run in realtime on an iPhone 3GS. Supported filters: Cartoon; Old Movie, Pencil, Colored Pencil, Bulge, Dent, Rain, ... Written in C++/OpenGL.