Research Overview

The AIT lab conducts research at the fore-front of human-centric computer vision. Our core research interests are algorithms and methods for the spatio-temporal understanding of how humans move within and interact with the physical world. We develop learning-based algorithms, methods and representations for human- and interaction-centric understanding of our world from videos, images and other sensor data. Application domains of interest include Augmented and Virtual Reality, Human Robot Interaction and more. Please refer to our publications for more information.

The AIT Lab, led by Prof. Dr. Otmar Hilliges, is part of the Institute for Intelligent Interactive Systems (IIS), in the Department of Computer Science at ETH Zurich.

Latest News

27.02.2023
We have 12 papers accepted at CVPR 2023. Stay tuned for more details.
01.09.2022
Dr. Christoph Gebhardt joins the AIT lab as a post-doc. Welcome back!
06.09.2022
Markos Diomataris joins the AIT lab. Welcome!
01.07.2022
Mert Albaba joins the AIT lab. Welcome!
09.08.2022
We have 1 paper accepted at TMLR. Stay tuned for more details.
09.08.2022
We have 2 papers accepted at 3DV 2022. Stay tuned for more details.
01.07.2022
We have 1 paper accepted at ECCV 2022. Stay tuned for more details.
09.05.2022
We have 1 paper accepted at SIGGRAPH 2022. Stay tuned for more details.
01.05.2022
Hsuan-I Ho and Artur Grigorev join the AIT lab. Welcome!
Check here for previous news.

Latest Projects


Teaser-Picture

X-Avatar: Expressive Human Avatars

AuthorsK. Shen*, C. Guo*, M. Kaufmann, J. Zarate, J. Valentin, J. Song, O. Hilliges
In ProceedingsComputer Vision and Pattern Recognition (CVPR), 2023
* These two authors contributed equally to this work.

Teaser-Picture

Learning Locally Editable Virtual Humans


Teaser-Picture

Hi4D: 4D Instance Segmentation of Close Human Interaction


Teaser-Picture

InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds

AuthorsT. Jiang*, X. Chen*, J. Song, O. Hilliges
In ProceedingsComputer Vision and Pattern Recognition (CVPR), 2023
* These two authors contributed equally to this work.

Teaser-Picture

Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition


Teaser-Picture

HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics


Teaser-Picture

DINER: (D)epth-aware (I)mage-based (Ne)ural (R)adiance Fields

AuthorsM. Prinzler, O. Hilliges, J. Thies
In ProceedingsComputer Vision and Pattern Recognition (CVPR), 2023

Teaser-Picture

PointAvatar: Deformable Point-based Head Avatars from Videos

AuthorsY. Zheng, W. Yifan, G. Wetzstein, M. Black, O. Hilliges
In ProceedingsComputer Vision and Pattern Recognition (CVPR), 2023

Teaser-Picture

HARP: Personalized Hand Reconstruction from a Monocular RGB Video


Learning Human-to-Robot Handovers from Point Clouds

AuthorsS. Christen, W. Yang, C. Pérez-D'Arpino, O. Hilliges, D. Fox, Y. Chao
In ProceedingsComputer Vision and Pattern Recognition (CVPR), 2023

Accepted as Highlight

Teaser-Picture

ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation

AuthorsZ. Fan, O. Taheri, D. Tzionas, M. Kocabas, M. Kaufmann, M. Black, O. Hilliges
In ProceedingsComputer Vision and Pattern Recognition (CVPR), 2023

Teaser-Picture

LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space

AuthorsE. Aksan, S. Ma, A. Caliskan, S. Pidhorskyi, A. Richard, S. Wei, J. Saragih, O. Hilliges
In ProceedingsEuropean Conference on Computer Vision (ECCV), 2022

Teaser-Picture

Computational Design of Active Kinesthetic Garments

AuthorsV. Vechev, R. Hinchet, S. Coros, B. Thomaszewski, O. Hilliges
In ProceedingsACM Symposium on User Interface Software and Technologies (UIST), Bend, Oregon, USA, Oct 2022

Teaser-Picture

Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors

AuthorsX. Wang*, G. Li*, Y. Kuo, M. Kocabas, E. Aksan, O. Hilliges
In ProceedingsInternational Conference on 3D Vision (3DV), 2022
* These two authors contributed equally to this work.

Teaser-Picture

TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learning

AuthorsA. Ziani*, Z. Fan*, M. Kocabas, S. Christen, O. Hilliges
In ProceedingsInternational Conference on 3D Vision (3DV), 2022
* These two authors contributed equally to this work.

Teaser-Picture

SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning

AuthorsM. Bagatella, S. Christen, O. Hilliges
In ProceedingsTransactions on Machine Learning Research, 2022

Teaser-Picture

EyeNeRF: A Hybrid Representation for Photorealistic Synthesis, Animation and Relighting of Human Eyes

AuthorsG. Li, A. Meka, F. Mueller, M. Buehler, O. Hilliges, T. Beeler
In ProceedingsACM Trans. Graph. (Volume: 41, Issue: 4), Jul 2022

Teaser-Picture

D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions


Teaser-Picture

gDNA: Towards Generative Detailed Neural Avatars


Teaser-Picture

I M Avatar: Implicit Morphable Head Avatars from Videos

AuthorsY. Zheng, V. Abrevaya, M. Bühler, X. Chen, M. Black, O. Hilliges
In ProceedingsComputer Vision and Pattern Recognition (CVPR), 2022

Accepted as Oral Presentation

Teaser-Picture

PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence

AuthorsZ. Dong*, C. Guo*, J. Song, X. Chen, A. Geiger, O. Hilliges
In ProceedingsComputer Vision and Pattern Recognition (CVPR), 2022
* These two authors contributed equally to this work.

Teaser-Picture

Computational Design of Kinesthetic Garments

AuthorsV. Vechev, J. Zarate, B. Thomaszewski, O. Hilliges
In ProceedingsComputer Graphics Forum, 2022

Teaser-Picture

Human Performance Capture from Monocular Video in the Wild


Teaser-Picture

A Skeleton-Driven Neural Occupancy Representation for Articulated Hands

AuthorsK. Karunratanakul, A. Spurr, Z. Fan, O. Hilliges, S. Tang
In ProceedingsInternational Conference on 3D Vision (3DV), 2021

Accepted as Oral Presentation

Teaser-Picture

Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation

AuthorsZ. Fan, A. Spurr, M. Kocabas, S. Tang, M. Black, O. Hilliges
In ProceedingsInternational Conference on 3D Vision (3DV), 2021

Accepted as Oral Presentation

Teaser-Picture

A Spatio-temporal Transformer for 3D Human Motion Prediction


No .bib file exists at /people/buehler/public/varitex/varitex2021.bib!!!

Teaser-Picture

EM-POSE: 3D Human Pose Estimation from Sparse Electromagnetic Trackers

AuthorsM. Kaufmann, Y. Zhao, C. Tang, L. Tao, C. Twigg, J. Song, R. Wang, O. Hilliges
In ProceedingsInternational Conference on Computer Vision (ICCV), 2021

Teaser-Picture

SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes


Teaser-Picture

Shape-aware Multi-Person Pose Estimation from Multi-view Images


Teaser-Picture

PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning

AuthorsA. Spurr*, A. Dahiya*, X. Wang, X. Zhang, O. Hilliges
In ProceedingsInternational Conference on Computer Vision (ICCV), 2021
* These two authors contributed equally to this work.

Accepted as Oral Presentation

Teaser-Picture

SPEC: Seeing People in the wild with an Estimated Camera

AuthorsM. Kocabas, C. Huang, J. Tesch, L. Müller, O. Hilliges, M. Black
In ProceedingsProceedings of the International Conference on Computer Vision 2021, Oct 2021

Teaser-Picture

PARE: Part Attention Regressor for 3D Human Body Estimation