Xintao Wang (original) (raw)

News

[3/2025] We release several interesting papers: ReCamMaster, DiffMoE and IGV-as-GGE.
[2/2025] Three papers (StyleMaster, PatchVSR and SketchVideo) are accepted to CVPR 2025.
[1/2025] Two papers (SynCamMaster and3DTrajMaster) are accepted to ICLR 2025.
[12/2024] Three papers (ImageConductor,CustomCrafter and Anti-Diffusion[oral]) are accepted to AAAI 2025.
[9/2024] Ranked asTop 2% Scientists Worldwide 2024 (Single Year) by Stanford University.
[9/2024] Three papers (MiraData, ReVideo andVideoTetris) are accepted to NeurIPS 2024.
[9/2024] One paper (StyleAdapter) is accepted to IJCV.
[8/2024] Two papers (ToonCrafter and StyleCrafter) are accepted to SIGGRAPH Asia 2024.
[7/2024] One paper (CustomNet) is accepted to ACM MM 2024.
[7/2024] Five papers (DynamiCrafter[oral],BrushNet, DreamDiffusion, MOFA-Video, CheapScaling) are accepted to ECCV 2024.
[5/2024] One paper (PromptGIP) is accepted to ICML 2024.
[3/2024] One paper (MotionCtrl) is accepted to SIGGRAPH 2024.
[3/2024] Nine papers (PhotoMaker, SUPIR, VideoCrafter2, SmartEdit[highlight], Rethink VQ Tokenizer, EvalCrafter, X-Adapter, DiffEditor and Seeing&Hearing) are accepted to CVPR 2024.
[1/2024] Four papers (DragonDiffusion[spotlight], ScaleCrafter[spotlight], FreeNoise and SEED-LlaMa) are accepted to ICLR 2024.
[12/2023] Three papers are accepted to AAAI 2024.
[10/2023] Ranked asTop 2% Scientists Worldwide 2023 (Single Year) by Stanford University. Click for More
[10/2023] Two papers are accepted to NeurIPS 2023.
[09/2023] ReleaseT2I-Adapter for SDXL: the most efficient control models, collaborating withHuggingFace.
[07/2023] Three papers are accepted to ICCV 2023.
[04/2023] One paper is accepted to ICML 2023.
[03/2023] We are holding the360° Super-Resolution Challenge as a part of theNTIRE workshop in conjunction with CVPR 2023.
[02/2023] Three papers to appear in CVPR 2023.
[11/2022] Two papers to appear in AAAI 2023.
[09/2022] Ranked asTop 2% Scientists Worldwide 2022 (Single Year) by Stanford University.
[09/2022] Two papers to appear in NeurIPS 2022.
[07/2022] Two papers to appear in ECCV 2022. VQFR is accepted as oral (2.7%).
[06/2022] Two papers to appear in ACM MM 2022.
[05/2022] BasicSR joins theXPixel Group!
[04/2022] We release a high-quality face video dataset (VFHQ). Please refer to theproject page andour paper.
[12/2021] One paper to appear in NeurIPS 2021 asspotlight (2.85%):FAIG: Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution. Codes are released inTencentARC/FAIG.
[10/2021] Real-ESRGAN is accepted by ICCV 2021 AIM workshop with Honorary Nomination Paper Award.
[07/2021] One paper to appear in ICCV 2021:Towards Vivid and Diverse Image Colorization with Generative Color Prior
[07/2021] The codes for practical image restorationReal-ESRGAN are released onGithub.
[06/2021] The training and testing codes of GFPGAN are released onTencentARC.
[03/2021] 5 papers to appear in CVPR 2021.
[03/2021] A brand-newHandyView online!.
[08/2020] A brand-newBasicSR v1.0.0 online!
[06/2019] We have released theEDVR training and testing codes and also updatedBasicSR codes!
[06/2019] Got my first outstanding reviewer recognition from CVPR 2019!
[05/2019] Our video restoration method, EDVR, won all four tracks in theNTIRE 2019 video restoration and enhancement challenges. Checkour paper for more details.
[03/2019] Our paperDeep Network Interpolation for Continuous Imagery Effect Transition to appear in CVPR 2019.
[08/2018] Our SuperSR team won the third track of the2018 PIRM Challenge on Perceptual Super-Resolution. Check the reportESRGAN for more details.
[06/2018] We won theNTIRE 2018 Challenge on Single Image Super-Resolution as first runner-up and ranked the first in the_Realistic Wild ×4 conditions_ track.
[02/2018] Our paperRecovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform to appear in CVPR 2018.
[07/2017] Our HelloSR team won theNTIRE 2017 Challenge on Single Image Super-Resolution as first runner-up.

GFPGAN

Practical face restoration

Real-ESRGAN

Practical algorithms for image restoration

BasicSR

Open source image and video restoration toolbox

T2I-Adapter

Dig out controllable ability for text-to-image diffusion models

VideoCrafter

Open sourced large models for video generation

HandyView

Handy image viewer

Publications[Full List]

(* equal contribution, # corresponding author)

Selected Preprint

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Jianhong Bai, Menghan Xia, Xiao Fu, Xintao Wang, Lianrui Mu, Jinwen Cao, Zuozhu Liu, Haoji Hu, Xiang Bai, Pengfei Wan, Di Zhang

arXiv preprint: 2503.11647.
Project Page Paper (arXiv) Codes

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers

Minglei Shi, Ziyang Yuan, Haotian Yang, Xintao Wang#, Mingwu Zheng, Xin Tao, Wenliang Zhao, Wenzhao Zheng, Jie Zhou, Jiwen Lu#, Pengfei Wan, Di Zhang, Kun Gai

arXiv preprint: 2503.14487.
Project Page Paper (arXiv) Codes

Improving Video Generation with Human Feedback

Jie Liu, Gongye Liu, Jiajun Liang, Ziyang Yuan, Xiaokun Liu, Mingwu Zheng, Xiele Wu, Qiulin Wang, Wenyu Qin, Menghan Xia, Xintao Wang, Xiaohong Liu, Fei Yang, Pengfei Wan, Di Zhang, Kun Gai, Yujiu Yang, Wanli Ouyang

arXiv preprint: 2501.13918.
Project Page Paper (arXiv) Codes