Jue Gong

School of Computer Science, Shanghai Jiao Tong University

I am with the School of Computer Science at Shanghai Jiao Tong University. My research focuses on computer vision, especially image restoration, efficient diffusion models, and human-centric restoration tasks such as face and body restoration.

My recent work centers on one-step diffusion for faithful and efficient restoration, including face restoration, human body restoration, motion-aware degradation modeling, and semantic-oriented JPEG artifact removal. A complete publication list is available on the publications page, including recent arXiv preprints.

Education:

2022-2026: B.Eng. in Biomedical Engineering, Shanghai Jiao Tong University
2026-2031: Direct Ph.D. track, advised by Prof. Yulun Zhang, School of Computer Science, Shanghai Jiao Tong University

Research interests:

One-step diffusion models for efficient restoration
Human body and face restoration
JPEG artifact removal and degradation modeling
Faithful restoration with stronger generative priors

news

Mar 10, 2026	Serving as a reviewer for ICML 2026.
Feb 24, 2026	Completed reviews for Visual Intelligence.
Feb 04, 2026	Released LCUDiff on arXiv for faithful human body restoration with upgraded 16-channel latent diffusion.
Sep 26, 2025	Paper accepted at NeurIPS 2025: HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance.
Aug 10, 2025	Released SODiff, a semantic-oriented one-step diffusion model for JPEG compression artifacts removal.
May 26, 2025	Released HAODiff for human-aware restoration under mixed degradation and motion blur.
Feb 28, 2025	Paper accepted at CVPR 2025: OSDFace: One-Step Diffusion Model for Face Restoration.

selected publications

arXiv
LCUDiff: Latent Capacity Upgrade Diffusion for Faithful Human Body Restoration

Jue Gong, Zihan Zhou, Jingkai Wang, Shu Li, Libo Liu, Jianliang Lan, and Yulun Zhang

arXiv preprint arXiv:2602.04406, Feb 2026

arXiv PDF Code

We propose LCUDiff, a stable one-step framework for human body restoration that upgrades latent diffusion from the 4-channel latent space to a 16-channel latent space. The method uses channel splitting distillation and prior-preserving adaptation to improve fidelity while keeping one-step efficiency, and further introduces a decoder router for per-sample decoder routing under diverse restoration conditions.
@article{gong2026lcudiff, title = {{LCUDiff}: Latent Capacity Upgrade Diffusion for Faithful Human Body Restoration}, status = {preprint}, author = {Gong, Jue and Zhou, Zihan and Wang, Jingkai and Li, Shu and Liu, Libo and Lan, Jianliang and Zhang, Yulun}, journal = {arXiv preprint arXiv:2602.04406}, year = {2026}, month = feb, }
arXiv
Light Up Your Face: Towards End-to-End Universal and Prompt Controllable Relighting

Jue Gong, Zheng Chen, Jingkai Wang, Yulun Zhang, and Xiaokang Yang

arXiv preprint arXiv:2602.04300, Feb 2026

arXiv PDF Code

We propose Light Up Your Face, an end-to-end universal and prompt-controllable face relighting framework built on one-step diffusion and identity-preserving guidance. The method supports diverse illumination edits while retaining identity consistency and fine facial details, and generalizes across in-the-wild portrait conditions.
@article{gong2026lightup, title = {{Light Up Your Face}: Towards End-to-End Universal and Prompt Controllable Relighting}, status = {preprint}, author = {Gong, Jue and Chen, Zheng and Wang, Jingkai and Zhang, Yulun and Yang, Xiaokang}, journal = {arXiv preprint arXiv:2602.04300}, year = {2026}, month = feb, }
AAAI
SODiff: Semantic-Oriented Diffusion Model for JPEG Compression Artifacts Removal

Tingyu Yang^†, Jue Gong^†, Jinpei Guo, Wenbo Li, Yong Guo, and Yulun Zhang^*

In The AAAI Conference on Artificial Intelligence (AAAI), Feb 2026

arXiv PDF Code

SODiff improves JPEG artifact removal with semantic-oriented guidance for a pre-trained one-step diffusion model. It introduces a semantic-aligned image prompt extractor and a quality factor-aware time predictor to better handle varying compression levels.
@inproceedings{yang2026sodiff, title = {{SODiff}: Semantic-Oriented Diffusion Model for {JPEG} Compression Artifacts Removal}, status = {accepted}, author = {Yang, Tingyu and Gong, Jue and Guo, Jinpei and Li, Wenbo and Guo, Yong and Zhang, Yulun}, booktitle = {The AAAI Conference on Artificial Intelligence}, year = {2026}, month = feb, }
NeurIPS
HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance

Jue Gong^*, Tingyu Yang^*, Jingkai Wang, Zheng Chen, Xing Liu, Hong Gu, Yulun Zhang^†, and Xiaokang Yang

Advances in Neural Information Processing Systems (NeurIPS), Dec 2025

arXiv PDF Code

HAODiff targets practical human-centric restoration under mixed degradation and human motion blur. It introduces triple-branch dual-prompt guidance and a dedicated MPII-Test benchmark, enabling stronger robustness and better visual quality in a single diffusion step.
@article{gong2025haodiff, title = {{HAODiff}: Human-Aware One-Step Diffusion via Dual-Prompt Guidance}, status = {accepted}, author = {Gong, Jue and Yang, Tingyu and Wang, Jingkai and Chen, Zheng and Liu, Xing and Gu, Hong and Zhang, Yulun and Yang, Xiaokang}, journal = {Advances in Neural Information Processing Systems}, year = {2025}, month = dec, }
ICML
Human Body Restoration with One-Step Diffusion Model and a New Benchmark

Jue Gong^*, Jingkai Wang^*, Zheng Chen, Xing Liu, Hong Gu, Yulun Zhang^†, and Xiaokang Yang

In Proceedings of the International Conference on Machine Learning (ICML), Jul 2025

arXiv PDF Code

This work introduces the PERSONA benchmark for human body restoration and proposes OSDHuman, a one-step diffusion model guided by a high-fidelity image embedder. The method improves restoration quality while addressing the lack of large-scale, task-specific datasets for human-centric restoration.
@inproceedings{gong2025osdhuman, title = {Human Body Restoration with One-Step Diffusion Model and a New Benchmark}, status = {accepted}, author = {Gong, Jue and Wang, Jingkai and Chen, Zheng and Liu, Xing and Gu, Hong and Zhang, Yulun and Yang, Xiaokang}, booktitle = {Proceedings of the International Conference on Machine Learning}, year = {2025}, month = jul, }
CVPR
OSDFace: One-Step Diffusion Model for Face Restoration

Jingkai Wang^*, Jue Gong^*, Lin Zhang, Zheng Chen, Xing Liu, Hong Gu, Yutong Liu^†, Yulun Zhang^†, and Xiaokang Yang

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2025

arXiv PDF Code

OSDFace is a one-step diffusion model for face restoration that combines a visual representation embedder, identity-aware supervision, and GAN-based guidance. It improves realism and identity consistency while keeping inference efficient.
@article{wang2025osdface, title = {{OSDFace}: One-Step Diffusion Model for Face Restoration}, status = {accepted}, author = {Wang, Jingkai and Gong, Jue and Zhang, Lin and Chen, Zheng and Liu, Xing and Gu, Hong and Liu, Yutong and Zhang, Yulun and Yang, Xiaokang}, journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, year = {2025}, month = jun, }