Andrei Zanfir

Google (United States) — United States

Computer Science · Physical Sciences

11h-index1.3kcitations26works3.42yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Human Pose and Action Recognition(14), Advanced Vision and Imaging(12), 3D Shape Modeling and Analysis(11), Human Motion and Animation(7), Video Surveillance and Tracking Methods(4)

Publications26 total

VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis
2025· 8 cited
DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans
2024· 8 cited
DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans
arXiv (Cornell University)·2024Open Access
SPHEAR: Spherical Head Registration for Complete Statistical 3D Modeling
2024
VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis
arXiv (Cornell University)·2024· 1 citedOpen Access
SPHEAR: Spherical Head Registration for Complete Statistical 3D Modeling
arXiv (Cornell University)·2023Open Access
Blendshapes GHUM: Real-time Monocular Facial Blendshape Prediction
arXiv (Cornell University)·2023· 1 citedOpen Access
DreamHuman: Animatable 3D Avatars from Text
arXiv (Cornell University)·2023· 22 citedOpen Access
Structured 3D Features for Reconstructing Controllable Avatars
2023· 24 cited
HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving
arXiv (Cornell University)·2022· 8 citedOpen Access
Structured 3D Features for Reconstructing Controllable Avatars
arXiv (Cornell University)·2022Open Access
BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation
arXiv (Cornell University)·2022· 22 citedOpen Access
HSPACE: Synthetic Parametric Humans Animated in Complex Environments
arXiv (Cornell University)·2021· 9 citedOpen Access
THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers
2021 IEEE/CVF International Conference on Computer Vision (ICCV)·2021· 2 citedOpen Access
Neural Descent for Visual 3D Human Pose and Shape
2021· 6 citedOpen Access
GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models
2020· 318 cited
Human Synthesis and Scene Compositing
Proceedings of the AAAI Conference on Artificial Intelligence·2020· 1 citedOpen Access
Weakly Supervised 3D Human Pose and Shape Reconstruction with\n Normalizing Flows
arXiv (Cornell University)·2020Open Access
Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows
Lecture notes in computer science·2020· 11 citedOpen Access
Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes: The Importance of Multiple Scene Constraints
2018· 311 cited
page 1 of 2Next →

Frequent Co-authors

Cristian Sminchisescu(26), Eduard Gabriel Băzăvan(15), Mihai Zanfir(12), Thiemo Alldieck(8), Rahul Sukthankar(6), Enric Corona(6), Nikos Kolotouros(5), William T. Freeman(4), Hongyi Xu(2), Elisabeta Marinoiu(2), Alin-Ionut Popa(2), Marius Leordeanu(2), Ivan Grishchenko(2), Karthik Raveendran(2), Matthias Grundmann(2), Bill Freeman(2), Akash Sengupta(2), Teodor Alexandru Szente(2), Alin Ionut Popa(1), Mihai Fieraru(1)