Feature out! Let Raw Image as Your Condition for Blind Face Restoration

Xinmin Qiu, Chen Gege, Bonan Li, Congying Han, Tiande Guo, Zicheng Zhang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50502-50525, 2025.

Abstract

Blind face restoration (BFR), which involves converting low-quality (LQ) images into high-quality (HQ) images, remains challenging due to complex and unknown degradations. While previous diffusion-based methods utilize feature extractors from LQ images as guidance, using raw LQ images directly as the starting point for the reverse diffusion process offers a theoretically optimal solution. In this work, we propose Pseudo-Hashing Image-to-image Schrödinger Bridge (P-I2SB), a novel framework inspired by optimal mass transport problems, which enhances the restoration potential of Schrödinger Bridge (SB) by correcting data distributions and effectively learning the optimal transport path between any two data distributions. Notably, we theoretically explore and identify that existing methods are limited by the optimality and reversibility of solutions in SB, leading to suboptimal performance. Our approach involves preprocessing HQ images during training by hashing them into pseudo-samples according to a rule related to LQ images, ensuring structural similarity in distribution. This guarantees optimal and reversible solutions in SB, enabling the inference process to learn effectively and allowing P-I2SB to achieve state-of-the-art results in BFR, with more natural textures and retained inference speed compared to previous methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-qiu25c, title = {Feature out! {L}et Raw Image as Your Condition for Blind Face Restoration}, author = {Qiu, Xinmin and Gege, Chen and Li, Bonan and Han, Congying and Guo, Tiande and Zhang, Zicheng}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {50502--50525}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/qiu25c/qiu25c.pdf}, url = {https://proceedings.mlr.press/v267/qiu25c.html}, abstract = {Blind face restoration (BFR), which involves converting low-quality (LQ) images into high-quality (HQ) images, remains challenging due to complex and unknown degradations. While previous diffusion-based methods utilize feature extractors from LQ images as guidance, using raw LQ images directly as the starting point for the reverse diffusion process offers a theoretically optimal solution. In this work, we propose Pseudo-Hashing Image-to-image Schrödinger Bridge (P-I2SB), a novel framework inspired by optimal mass transport problems, which enhances the restoration potential of Schrödinger Bridge (SB) by correcting data distributions and effectively learning the optimal transport path between any two data distributions. Notably, we theoretically explore and identify that existing methods are limited by the optimality and reversibility of solutions in SB, leading to suboptimal performance. Our approach involves preprocessing HQ images during training by hashing them into pseudo-samples according to a rule related to LQ images, ensuring structural similarity in distribution. This guarantees optimal and reversible solutions in SB, enabling the inference process to learn effectively and allowing P-I2SB to achieve state-of-the-art results in BFR, with more natural textures and retained inference speed compared to previous methods.} }
Endnote
%0 Conference Paper %T Feature out! Let Raw Image as Your Condition for Blind Face Restoration %A Xinmin Qiu %A Chen Gege %A Bonan Li %A Congying Han %A Tiande Guo %A Zicheng Zhang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-qiu25c %I PMLR %P 50502--50525 %U https://proceedings.mlr.press/v267/qiu25c.html %V 267 %X Blind face restoration (BFR), which involves converting low-quality (LQ) images into high-quality (HQ) images, remains challenging due to complex and unknown degradations. While previous diffusion-based methods utilize feature extractors from LQ images as guidance, using raw LQ images directly as the starting point for the reverse diffusion process offers a theoretically optimal solution. In this work, we propose Pseudo-Hashing Image-to-image Schrödinger Bridge (P-I2SB), a novel framework inspired by optimal mass transport problems, which enhances the restoration potential of Schrödinger Bridge (SB) by correcting data distributions and effectively learning the optimal transport path between any two data distributions. Notably, we theoretically explore and identify that existing methods are limited by the optimality and reversibility of solutions in SB, leading to suboptimal performance. Our approach involves preprocessing HQ images during training by hashing them into pseudo-samples according to a rule related to LQ images, ensuring structural similarity in distribution. This guarantees optimal and reversible solutions in SB, enabling the inference process to learn effectively and allowing P-I2SB to achieve state-of-the-art results in BFR, with more natural textures and retained inference speed compared to previous methods.
APA
Qiu, X., Gege, C., Li, B., Han, C., Guo, T. & Zhang, Z.. (2025). Feature out! Let Raw Image as Your Condition for Blind Face Restoration. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:50502-50525 Available from https://proceedings.mlr.press/v267/qiu25c.html.

Related Material