Xianghui Xie


I am a PhD student at the Real Virtual Humans group at Max Planck Institute for Informatics and University of Tuebingen under supervision of Prof. Dr. Gerard Pons-Moll. I also work closely with Jan Eric Lessen. I am interested in 3D computer vision, generative models, especially in accurate reconstruction/tracking and realistic synthesis of humans and objects. My research goal is to create digital humans that behave like real humans and empower them with intelligence to finish daily tasks as humans do.

For any inquiries or collaborations, feel free to reach out to me via email!

Mail Twitter Scholar Github LinkedIn

Profile picture

News

  • Aug 2025 Two papers accepted to SIGGRAPH Asia!
  • Jun 2025 MVGBench accepted to ICCV'25, check out at project page.
  • Jun 2025 Started research intern at NVIDIA@Santa Clara, in the learning and perception research team.
  • Jun 2025 One paper accepted to TPAMI, check out Gen-3Diffusion.
  • Nov 2024 One paper accepted to 3DV. See InterTrack.
  • Sep 2024 One paper accepted to NeurIPS, checkout Human3Diffusion.
  • Aug 2024 Started research internship at Amazon.
  • Feb 2024 One paper accepted to CVPR as highlight, checkout ProciGen.
  • Feb 2023 One paper accepted to CVPR'23, checkout VisTracker.
  • Jul 2022 CHORE paper accepted to ECCV'22, checkout CHORE.
  • Feb 2022 BEHAVE accepted to CVPR'22, see BEHAVE.

Publications

Project image
InfiniHuman: Realistic 3D Human Creation with Precise Control
Yuxuan Xue, Xianghui Xie, Margaret Kostyrko, Gerard Pons-Moll
ACM SIGGRAPH Asia, 2025
Project Page /
@InProceedings{xue2025infinihuman, 
	author = {Yuxuan Xue and Xianghui Xie and Margaret Kostyrko and Gerard Pons-Moll}, 
	title = {InfiniHuman: Realistic 3D Human Creation with Precise Control}, 
	booktitle = {ACM SIGGRAPH Asia}, 
	year = {2025}, 
}
Project image
PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image
Pradyumna Yalandur-Muralidhar, Yuxuan Xue, Xianghui Xie, Margaret Kostyrko, Gerard Pons-Moll
ACM SIGGRAPH Asia, 2025
Project Page /
@InProceedings{yalandur2025physic, 
	author = {Pradyumna Yalandur-Muralidhar and Yuxuan Xue and Xianghui Xie and Margaret Kostyrko and Gerard Pons-Moll}, 
	title = {PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image}, 
	booktitle = {ACM SIGGRAPH Asia}, 
	year = {2025}, 
}
Project image
MVGBench: Comprehensive Benchmark for Multi-view Generation Models
Xianghui Xie, Chuhang Zou, Gitika Meher Karumuri, Jan Eric Lenssen, Gerard Pons-Moll
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025
Project Page /
@InProceedings{xie2025MVGBench, 
	author = {Xianghui Xie and Chuhang Zou and Gitika Meher Karumuri and Jan Eric Lenssen and Gerard Pons-Moll}, 
	title = {MVGBench: Comprehensive Benchmark for Multi-view Generation Models}, 
	booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision}, 
	year = {2025}, 
}
Project image
Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergy
Yuxuan Xue, Xianghui Xie, Riccardo Marin, Gerard Pons-Moll
IEEE Transactions on Pattern Analysis \& Machine Intelligence, 2025
Project Page /
@InProceedings{xue2024gen3diffusion, 
	author = {Yuxuan Xue and Xianghui Xie and Riccardo Marin and Gerard Pons-Moll}, 
	title = {Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergy}, 
	booktitle = {IEEE Transactions on Pattern Analysis \& Machine Intelligence}, 
	year = {2025}, 
}
Project image
InterTrack: Tracking Human Object Interaction without Object Templates
Xianghui Xie, Jan Eric Lenssen, Gerard Pons-Moll
International Conference on 3D Vision (3DV), 2025
Project Page /
@InProceedings{xie2024InterTrack, 
	author = {Xianghui Xie and Jan Eric Lenssen and Gerard Pons-Moll}, 
	title = {InterTrack: Tracking Human Object Interaction without Object Templates}, 
	booktitle = {International Conference on 3D Vision (3DV)}, 
	year = {2025}, 
}
Project image
Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models
Yuxuan Xue, Xianghui Xie, Riccardo Marin, Gerard Pons-Moll
Advances in Neural Information Processing Systems ({NeurIPS}), 2024
Project Page /
@InProceedings{xue2024human3diffusion, 
	author = {Yuxuan Xue and Xianghui Xie and Riccardo Marin and Gerard Pons-Moll}, 
	title = {Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models}, 
	booktitle = {Advances in Neural Information Processing Systems ({NeurIPS})}, 
	year = {2024}, 
}
Project image
Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation (Highlight)
Xianghui Xie, Bharat Lal Bhatnagar, Jan Eric Lenssen, Gerard Pons-Moll
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Project Page /
@InProceedings{xie2023template_free, 
	author = {Xianghui Xie and Bharat Lal Bhatnagar and Jan Eric Lenssen and Gerard Pons-Moll}, 
	title = {Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation}, 
	booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, 
	year = {2024}, 
}
Project image
RHOBIN Challenge: Reconstruction of Human Object Interaction
Xianghui Xie, Xi Wang, Nikos Athanasiou, Bharat Lal Bhatnagar, Chun-Hao P. Huang, Kaichun Mo, Hao Chen, Xia Jia, Zerui Zhang, Liangxian Cui, Xiao Lin, Bingqiao Qian, Jie Xiao, Wenfei Yang, Hyeongjin Nam, Daniel Sungho Jung, Kihoon Kim, Kyoung Mu Lee, Otmar Hilliges, Gerard Pons-Moll
ArXiv, 2023
Project Page /
@InProceedings{xie2024rhobin, 
	author = {Xianghui Xie and Xi Wang and Nikos Athanasiou and Bharat Lal Bhatnagar and Chun-Hao P. Huang and Kaichun Mo and 
Hao Chen and Xia Jia and Zerui Zhang and Liangxian Cui and Xiao Lin and 
Bingqiao Qian and Jie Xiao and Wenfei Yang and Hyeongjin Nam and Daniel Sungho Jung and 
Kihoon Kim and Kyoung Mu Lee and Otmar Hilliges and Gerard Pons-Moll}, 
	title = {RHOBIN Challenge: Reconstruction of Human Object Interaction}, 
	booktitle = {ArXiv}, 
	year = {2023}, 
}
Project image
Visibility Aware Human-Object Interaction Tracking from Single RGB Camera
Xianghui Xie, Bharat Lal Bhatnagar, Gerard Pons-Moll
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Project Page /
@InProceedings{xie2023vistracker, 
	author = {Xianghui Xie and Bharat Lal Bhatnagar and Gerard Pons-Moll}, 
	title = {Visibility Aware Human-Object Interaction Tracking from Single RGB Camera}, 
	booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, 
	year = {2023}, 
}
Project image
CHORE: Contact, Human and Object REconstruction from a single RGB image
Xianghui Xie, Bharat Lal Bhatnagar, Gerard Pons-Moll
European Conference on Computer Vision ({ECCV}), 2022
Project Page /
@InProceedings{xie22chore, 
	author = {Xianghui Xie and Bharat Lal Bhatnagar and Gerard Pons-Moll}, 
	title = {CHORE: Contact, Human and Object REconstruction from a single RGB image}, 
	booktitle = {European Conference on Computer Vision ({ECCV})}, 
	year = {2022}, 
}
Project image
BEHAVE: Dataset and Method for Tracking Human Object Interactions
Bharat Lal Bhatnagar*, Xianghui Xie*, Ilya A. Petrov, Cristian Sminchisescu, Christian Theobalt, Gerard Pons-Moll
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
*Joint first author, equal contribution
Project Page /
@InProceedings{bhatnagar22behave, 
	author = {Bharat Lal Bhatnagar and Xianghui Xie and Ilya A. Petrov and Cristian Sminchisescu and Christian Theobalt and Gerard Pons-Moll
}, 
	title = {BEHAVE: Dataset and Method for Tracking Human Object Interactions}, 
	booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, 
	year = {2022}, 
}

Talks

Project image
Capturing Human Object Interactions from Monocular RGB Camera
Amazon-MPI science hub, 2023

Homepage Template

This website is based on the template from Michael Miemeyer.