Skip to content

snuvclab/durian

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 

Repository files navigation

Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer

arXiv Paper PDF Project Page OpenReview

ICLR 2026

Hyunsoo Cha    Byungjun Kim    Hanbyul Joo

Seoul National University


teaser.mp4

News

TODO

  • Release project page
  • Release arXiv paper
  • Release inference code & pretrained weights
  • Release training code

Abstract

We present Durian, the first method for generating portrait animation videos with cross-identity attribute transfer from one or more reference images to a target portrait. Training such models typically requires attribute pairs of the same individual, which are rarely available at scale. To address this challenge, we propose a self-reconstruction formulation that leverages ordinary portrait videos to learn attribute transfer without explicit paired data. Two frames from the same video act as a pseudo pair: one serves as an attribute reference and the other as an identity reference. To enable this self-reconstruction training, we introduce a Dual ReferenceNet that processes the two references separately and then fuses their features via spatial attention within a diffusion model. To make sure each reference functions as a specialized stream for either identity or attribute information, we apply complementary masking to the reference images. Together, these two components guide the model to reconstruct the original video, naturally learning cross-identity attribute transfer. To bridge the gap between self-reconstruction training and cross-identity inference, we introduce a mask expansion strategy and augmentation schemes, enabling robust transfer of attributes with varying spatial extent and misalignment. Durian achieves state-of-the-art performance on portrait animation with attribute transfer. Moreover, its dual reference design uniquely supports multi-attribute composition and smooth attribute interpolation within a single generation pass, enabling highly flexible and controllable synthesis.

Citation

If you find our work useful, please consider citing:

@inproceedings{cha2026durian,
  title     = {Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer},
  author    = {Cha, Hyunsoo and Kim, Byungjun and Joo, Hanbyul},
  booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)},
  year      = {2026}
}

Acknowledgements

This work was conducted at SNU VCLab.

License

This project is licensed under CC BY 4.0.

About

[ICLR 2026] Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors