Xi Wang
xi.wang (at) inf.ethz.ch
I am an established researcher in the Computer Vision and Geometry Lab with
Prof. Marc Pollefeys at ETH Zurich while continue
working with Prof. Luc Van Gool at INSAIT.
I was an ETH Postdoc Fellow in the Advanced Interactive Technologies
lab led by Prof. Otmar Hilliges at ETH and a member of the virtual group of Ruth
Rosenholtz at MIT.
I completed my PhD in the Computer Graphics group at TU
Berlin, advised by Prof. Marc
Alexa.
In 2020, I visited MIT working in the Computational Perception &
Cognition Group led by Aude Oliva.
Later that year I interned at Adobe Research working with
Zoya Bylinskii and Aaron Hertzmann.
My research interests fall at the intersection of computer vision & graphics, and vision science.
My goal is to bring human common sense and behavior patterns into machine learning.
During my Ph.D., I have studied how humans perceive 3D shapes and what we can tell about people's
mental imagery through observations of their eye movements.
My current research interests are vision-language multimodal learning, with a focus on
understanding how humans' intent drives their actions and their interactions with the
surroundings.
I am excited to learn about human behavior patterns and to leverage the gained knowledge in
computational models and applications.
News
October 2024
September 2024
June 2024
December 2023
Publication
PALM: Predicting Actions through Language Models. ECCV 2024
Sanghwan Kim, Daoji Huang, Yongqin Xian, Luc Van Gool, Otmar Hilliges, and Xi WangPDF Code
ROMEO: Revisiting Optimization Methods for Reconstructing 3D Human-Object Interaction Models From Images. ECCVW 2024, Best paper award
Alexey Gavryushin, Yifei Liu, Daoji Huang, Yen-Ling Kuo, Julien Valentin, Luc Van Gool, Otmar Hilliges, and Xi WangProject page PDF Code
I-Design: Personalized LLM Interior Designer. ECCVW 2024
Ata Celen, Guo Han, Konrad Schindler, Luc Van Gool, Iro Armeni, Anton Obukhov and Xi WangProject page PDF Code
Women in Computer Vision. ECCV Workshop 2024
Workshop page
Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation. CVPR 2024
Razvan-George Pasca*, Alexey Gavryushin*, Muhammad Hamza, Yen-Ling Kuo, Kaichun Mo, Luc Van Gool, Otmar Hilliges, and Xi WangProject page PDF Code
WANDR: Intention-guided Human Motion Generation. CVPR 2024
Markos Diomataris, Nikos Athanasiou, Omid Taheri, Xi Wang, Otmar Hilliges, and Michael J BlackProject page PDF Code
2nd Rhobin: Reconstruction of Human-Object Interactions. CVPR Workshop 2024
Workshop page
Gaze-Guided Graph Neural Network for Action Anticipation Conditioned on Intention. ETRA 2024
Suleyman Ozdel, Yao Rong, Berat Mert Albaba, Yen-Ling Kuo, Xi Wang, and Enkelejda Kasneci
A Transformer-Based Model for the Prediction of Human Gaze Behavior on Videos. ETRA 2024
Suleyman Ozdel, Yao Rong, Berat Mert Albaba, Yen-Ling Kuo, Xi Wang, and Enkelejda Kasneci
Reconstruction of 3D Interaction Models from Images using Shape Prior. ICCV Workshop 2023
Mehrshad Mirmohammadi, Parham Saremi, Yen-Ling Kuo, and Xi WangProject page PDF Code
Model-aware 3D Eye Gaze from Weak and Few-shot Supervisions. ISMAR, 2023
Nikola Popovic*, Dimitrios Christodoulou*, Danda Pani Paudel, Xi Wang, and Luc Van GoolPDF Code
OpenSUN 3D: 1st Workshop on Open-Vocabulary 3D Scene Understanding. ICCV Workshop 2023
Workshop page
Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023. CVPR Workshop 2023, Winner of the Ego4D challenge
Daoji Huang, Otmar Hilliges, Luc Van Gool, and Xi WangProject page Challenge report PDF Code
Rhobin: Reconstruction of Human-Object Interactions. CVPR Workshop 2023
Xi Wang, Gerard Pons-Moll, Kaichun Mo, Nikos Athanasiou, Paul Huang, Otmar Hilliges, Xianghui Xie, and Bharat Lal BhatnagarWorkshop page
EFE: End-to-end Frame-to-Gaze Estimation. CVPR Workshops 2023, Best poster award
Haldun Balim, Seonwook Park, Xi Wang, Xucong Zhang, and Otmar HilligesProject page PDF
A Computational Approach to Studying Aesthetic Judgments of Ambiguous Artworks. Psychology of Aesthetics, Creativity and the Arts, 2023
Xi Wang, Zoya Bylinskii, Aaron Hertzmann, and Robert PepperellProject page PDF
GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields. CVPR 2023
Alessandro Ruzzi*, Xiangwei Shi*, Xi Wang, Gengyan Li, Shalini De Mello, Hyung Jin Chang, Xucong Zhang, and Otmar HilligesProject page PDF
Deepfake Caricatures: Amplifying attention to artifacts increases deepfake detection by humans and machines. arXiv 2022
Camilo Fosco*, Emilie Josephs*, Alex Andonian, Allen Lee, Xi Wang, and Aude OlivaProject page PDF
Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors. 3DV 2022
Xi Wang*, Gen Li*, Yen-Ling Kuo, Muhammed Kocabas, Emre Aksan, and Otmar HilligesProject page PDF
Self-Supervised 3D Hand Pose Estimation from monocular RGB via Contrastive Learning. ICCV 2021, oral
Adrian Spurr*, Aneesh Dahiya*, Xi Wang, Xucong Zhang, and Otmar HilligesProject page PDF Code and Models
Toward Quantifying Ambiguities in Artistic Images. VSS 2021
Xi Wang, Zoya Bylinskii, Aaron Hertzmann, and Robert PepperellProject page Poster
EMICS'21: Eye Movements as an Interface to Cognitive State CHI'21 Workshop
Xi Wang, Zoya Bylinskii, Monica Castelhano, James Hillis, and Andrew T. DuchowskiEvent page
A consensus-based elastic matching algorithm for mapping recall fixations onto encoding fixations in the looking-at-nothing paradigm. Behavior Research Methods, 2021
Xi Wang, Kenneth Holmqvist, and Marc AlexaProject page PDF BibTeX
Toward Quantifying Ambiguities in Artistic Images. TAP, 2020
Xi Wang, Zoya Bylinskii, Aaron Hertzmann, and Robert PepperellProject page arXiv BibTeX
Computational discrimination between natural images based on gaze during mental imagery Scientific Reports, 2020
Xi Wang, Andreas Ley, Sebastian Koch, James Hays, Kenneth Holmqvist, and Marc AlexaProject page PDF BibTeX
EMICS'20: Eye Movements as an Interface to Cognitive State CHI SIG, 2020
Xi Wang, Zoya Bylinskii, Monica Castelhano, James Hillis, and Andrew T. DuchowskiEvent page PDF BibTeX
Keep It Simple: Depth-based Dynamic Adjustment of Rendering for Head-mounted Displays Decreases Visual Comfort TAP, 2019
Jochen Jacobs, Xi Wang, and Marc AlexaPDF BibTeX
Center of circle after perspective transformation arXiv, 2019
Xi Wang, Albert Chern, and Marc AlexaPDF BibTeX
The mean point of vergence is biased under projection JEMR, 2019
Xi Wang, Kenneth Holmqvist, and Marc AlexaPDF BibTeX
The Mental Image Revealed by Gaze Tracking CHI, 2019
Xi Wang, Andreas Ley, Sebastian Koch, David Lindlbauer, James Hays, Kenneth Holmqvist, and Marc AlexaProject page PDF BibTeX
Tracking the Gaze on Objects in 3D: How do People Really Look at the Bunny? SIGGRAPH Asia, 2018
Xi Wang, Sebastian Koch, Kenneth Holmqvist, and Marc AlexaProject page PDF BibTeX
Maps of Visual Importance: What is recalled from visual episodic memory? arXiv and talk at European Conference on Visual Perception (ECVP), 2018
Xi Wang, Kenneth Holmqvist, and Marc AlexaPDF Abstract Slides BibTeX
3D Eye Tracking in Monocular and Binocular Conditions 19th European Conference on Eye Movements (ECEM), 2017
Xi Wang, Marianne Maertens and Marc AlexaAbstract Slides BibTeX
Measuring Visual Salience of 3D Printed Objects IEEE Computer Graphics and Applications, 2016
Xi Wang, David Lindlbauer, Christian Lessig, Marianne Maertens and Marc AlexaProject page PDF BibTeX
Accuracy of Monocular Gaze Tracking on 3D Geometry Workshop on Eye Tracking and Visualization (ETVIS), 2015 and Book Chapter in Eye Tracking and Visualization
Xi Wang, David Lindlbauer, Christian Lessig and Marc AlexaProject page PDF Chapter Book BibTeX
Graph-cut Segmentation of Polarimetric SAR Images. IEEE Geoscience and Remote Sensing Symposium, 2014
Ronny Haensch, Olaf Hellwich, and Xi WangPDF BibTeX
Comparison of Different Color Spaces for Image Segmentation Using Graph-cuts. Computer Vision Theory and Application (VISAPP), 2014
Xi Wang, Ronny Haensch, Lizhuang Ma, and Olaf HellwichPDF BibTeX
Depth Image-based Rendering with Spatio-temporally Consistent Texture Synthesis for 3D Video with Global Motion. IEEE International Conference on Image Processing (ICIP), 2012
Martin Koeppel, Xi Wang, Dimitar Doshkov, Thomas Wiegand, and Patrick Ndjiki-NyaPDF BibTeX
Consistent Spatio-temporal Filling of Disocclusions in the Multiview-Video-Plus-Depth Format. IEEE International Workshop on Multimedia Signal Processing (MMSP), 2012
Martin Koeppel, Xi Wang, Dimitar Doshkov, Thomas Wiegand, and Patrick Ndjiki-NyaPDF BibTeX
Personal
I was born and grew up in a small city (with only a bit more than 1 million people) in China. Five years of my life was spent in Shanghai for study and I had a wonderful time living in Berlin while pursuing my PhD. I enjoy travelling and taking pictures on the way. I also enjoy playing guitar and have been in a rock band during my studies in Shanghai. Since 2014 I started playing jazz, and discovered the powerful secret of playing jazz -- no matter how it sounds, you can always entitle it as improvisation. My favorite jazz guitarists are Pat Metheny and Bill Frisell (their music can easily give me goosebumps). The rest of time is spent cooking, learning to play drum-sets and tap dancing, a perfect combination of jazz and rhythm ;).