Research

The Art Is In the Science

Flawless was born from breakthrough research in neural rendering and visual performance modeling. Our scientists are pushing the boundaries of what AI can do in service of storytelling.

Prestigious Collaborations

Imperial College London MIT Professional Education Max Planck Gesellschaft Stanford University

Where "What If" Becomes Industry Standard

Our research team includes some of the world's leading minds in AI, computer vision, and generative modeling. Their work drives our mission to turn bold ideas into real tools for filmmakers, studios, and storytellers everywhere.

Pablo Garrido

Pablo Garrido

Chief Researcher
Akin Caliskan

Akin Caliskan

Head of Applied Science
Christian Theobalt

Christian Theobalt

Advisor

Discover Our Research

2026
SIGGRAPH

Emotion Manipulation for Talking-head Videos

Kwanggyoon Seo, Rene Jotham Culaway, Byeong-Uk Lee, Junyong Noh — Flawless AI, KRAFTON Inc., KAIST

CVPR

EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images

Jongmin Park, Minh-Quan Viet Bui, Juan Luis Gonzalez Bello, Jaeho Moon, Jihyong Oh, Munchurl Kim — KAIST, Flawless AI, Chung-Ang University

FG

Polyglot: Multilingual Style Preserving Speech-Driven Facial Animation

Frederico Nocentini, Kwanggyoon Seo, Qingju Liu, Claudio Ferrari, Stefano Berretti, David Ferman, Hyeongwoo Kim, Pablo Garrido, Akin Caliskan — University of Florence, Flawless AI, Imperial College London

WACV

Zero-Shot Video Deraining with Video Diffusion Models

Tuomas Varanka, Juan Luis Gonzalez, Hyeongwoo Kim, Pablo Garrido, Xu Yao

JASA Express Letters

Improving Zero-Shot Style Transfer Text-to-Speech by Disentangled Fine-Grained Style Modeling

Eray Eren, Qingju Liu, Abeer Alwan, Gaurav Bharaj

2025
Eurographics

Neural Face Skinning for Mesh-agnostic Facial Expression Cloning

Sihun Cha, Serin Yoon, Kwanggyoon Seo, Junyong Noh — KAIST, Flawless AI

SIGGRAPH Asia

UniGAHA: Audio-Driven Universal Gaussian Head Avatars

Kartik Teotia, Helge Rhodin, Mohit Mendiratta, Hyeongwoo Kim, Marc Habermann, Christian Theobalt

ICCV

KinMo: Kinematic-Aware Human Motion Understanding and Generation

Pengfei Zhang, Pinxin Liu, Pablo Garrido, Hyeongwoo Kim, Bindita Chaudhuri

ACM MM

Contextual Gesture: Co-Speech Gesture Video Generation Through Context-Aware Gesture Representation

Pinxin Liu, Pengfei Zhang, Hyeongwoo Kim, Pablo Garrido, Ari Shapiro, Kyle Olszewski

Interspeech

ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs

Eray Eren, Qingju Liu, Hyeongwoo Kim, Pablo Garrido, Abeer Alwan

CVPR

VideoSPatS: Video SPatiotemporal Splines for Disentangled Occlusion, Appearance and Motion Modeling and Editing

Juan Luis Gonzalez, Xu Yao, Alex Whelan, Kyle Olszewski, Hyeongwoo Kim, Pablo Garrido

2024
SIGGRAPH Asia

GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations

Kartik Teotia, Hyeongwoo Kim, Pablo Garrido, Marc Habermann, Mohamed Elgharib, Christian Theobalt

ECCV

VideoClusterNet: Self-Supervised and Adaptive Face Clustering for Videos

Devesh Walawalkar, Pablo Garrido

BMVC

Content and Style Aware Audio-Driven Facial Animation

Qingju Liu, Hyeongwoo Kim, Gaurav Bharaj

ECCV

PAV: Personalized Head Avatar from Unstructured Video Collection

Akin Caliskan, Berkay Kicanaoglu, Hyeongwoo Kim

SIGGRAPH

HQ3DAvatar: High-Quality Implicit 3D Head Avatar

Kartik Teotia, Mallikarjun B R, Xingang Pan, Hyeongwoo Kim, Pablo Garrido, Mohamed Elgharib, Christian Theobalt

CVPR

FaceLift: Semi-Supervised 3D Facial Landmark Localization

David Ferman, Pablo Garrido, Gaurav Bharaj

2023
ICCV

RANA: Relightable Articulated Neural Avatars

Umar Iqbal, Akin Caliskan, Koki Nagano, Sameh Khamis, Pavlo Molchanov, Jan Kautz

CVPR

Few-Shot Geometry-Aware Keypoint Localization

Xingzhe He, Gaurav Bharaj, David Ferman, Helge Rhodin, Pablo Garrido

ICCV

Unsupervised Facial Performance Editing via Vector-Quantized StyleGAN Representations

Berkay Kicanaoglu, Pablo Garrido, Gaurav Bharaj

CVPR

Implicit Neural Head Synthesis Via Controllable Local Deformation Fields

Chuhan Chen, Matthew O'Toole, Gaurav Bharaj, Pablo Garrido

Help Write the Next Chapter

We're building the science behind the future of filmmaking. If that sounds like your kind of problem, we'd love to meet you.