Haoran Wang

PhD candidate at the Max Planck Institute for Informatics

face.png

I am actively looking for industry positions starting from 2027.

I am currently a final-year PhD candidate at the Max Planck Institute for Informatics, Germany, under the supervision of Prof. Adam Kortylewski, Prof. Christian Theobalt, and Prof. Bernt Schiele. Before that, I obtained my master’s degree in Computer Science from ETH Zürich, where I worked with Prof. Wen Li and Prof. Siyu Tang. I obtained my bachelor’s degree in Computer Science from Sichuan University, China.

My research spans agentic AI, vision-language models, 3D/4D vision, and generative AI. Across these areas, I am interested in developing intelligent systems that can perceive and reason about rich spatial and temporal information, and interact effectively with complex environments.

selected publications

Full publication list can be found on Google Scholar.
* Equal contribution.
  1. ECCV
    emotegpt_eccv2026.png
    EmoteGPT: 3D Human Facial Expressions from Natural Language Descriptions
    Haoran Wang, Mohit Mendiratta, Christian Theobalt, and Adam Kortylewski
    In European Conference on Computer Vision, 2026
  2. ECCV
    soco_eccv2026.jpg
    SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
    Olaf Dünkel*, Basavaraj Sunagad*, Haoran Wang, David T. Hoffmann, Christian Theobalt, and Adam Kortylewski
    In European Conference on Computer Vision, 2026
  3. TPAMI
    acdc_tpami.png
    ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception
    Christos Sakaridis*, Haoran Wang*, Ke Li, René Zurbrügg, Arpit Jadon, Wim Abbeloos, Daniel Olmeda Reino, Luc Van Gool, and Dengxin Dai
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
  4. CVPR
    personahoi_cvpr2025.png
    PersonaHOI: Effortlessly Improving Face Personalization in Human-Object Interaction Generation
    Xinting Hu*, Haoran Wang*, Jan Eric Lenssen, and Bernt Schiele
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2025
  5. ECCV
    fada_eccv2020.png
    Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
    Haoran Wang*, Tong Shen*, Wei Zhang, Ling-Yu Duan, and Tao Mei
    In European Conference on Computer Vision, 2020
    PDF