Avatar

Juewen Peng (彭珏文)

Postgraduate

Wuhan, China

im.pengjw@gmail.com

https://github.com/JuewenPeng

Google Scholar

Research Interests

  • Computer vision
  • Computational photography
  • Bokeh rendering
  • Deblurring
  • Super resolution
  • Image generation


News

  • [ 2024-02 ] Won 2023 CAA Outstanding Master's Degree Thesis Award.
  • [ 2023-08 ] One paper accepted by TMM 2023.
  • [ 2023-07 ] One paper accepted by ACM MM 2023.
  • [ 2023-06 ] Won Winner Award in "NTIRE 2023 Bokeh Effect Transformation Challenge".
  • [ 2023-04 ] One paper accepted by CVPR 2023 Workshops.
  • [ 2022-11 ] One paper accepted by TCSVT 2023.
  • [ 2022-08 ] One paper accepted by Information Fusion 2023.
  • [ 2022-07 ] One paper accepted by ECCV 2022.
  • [ 2022-06 ] One paper accepted by ACM MM 2022.
  • [ 2022-03 ] One paper accepted by CVPR 2022 as an oral presentation.

Educations

M.Eng., Huazhong University of Science and Technology
Sep. 2020 - Jun. 2023
  • Major: Pattern Recognition and Intelligent Systems, School of Artificial Intelligence and Automation
  • Supervisor: Prof. Zhiguo Cao
  • GPA: 3.98/4.00; 92.96/100 (Rank 1st)
  • Honors and Awards: Outstanding Graduates (2023), National Scholarship (2022), Outstanding Freshman Scholarship (2020), etc.
B.Eng., Huazhong University of Science and Technology
Sep. 2016 - Jun. 2020
  • Major: Automation, School of Artificial Intelligence and Automation
  • GPA: 3.89/4.00; 91.3/100 (Rank 1st)
  • Honors and Awards: Outstanding Graduates (2020), National Scholarship (2018), etc.


Publications

ViTA: Video Transformer Adaptor for Robust Video Depth Estimation

Ke Xian, Juewen Peng, Zhiguo Cao, Jianming Zhang, Guosheng Lin

IEEE Transactions on Multimedia (TMM), 2023

Paper  |  GitHub  |  Project

Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image

Liao Shen, Xingyi Li, Huiqiang Sun, Juewen Peng, Ke Xian, Zhiguo Cao, Guosheng Lin

Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), 2023

Paper  |  GitHub

Selective Bokeh Effect Transformation

Juewen Peng, Zhiyu Pan, Chengxin Liu, Xianrui Luo, Huiqiang Sun, Liao Shen, Ke Xian, Zhiguo Cao

Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023

Paper  |  GitHub

Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challenge Report

Marcos V. Conde, Manuel Kolmet, Tim Seizinger, Tom E. Bishop, Radu Timofte, Xiangyu Kong, Dafeng Zhang, Jinlong Wu, Fan Wang, Juewen Peng, et al.

Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023

Paper

Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Pair

Xianrui Luo, Juewen Peng, Weiyue Zhao, Ke Xian, Hao Lu, Zhiguo Cao

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023

Paper

Defocus to Focus: Photo-Realistic Bokeh Rendering by Fusing Defocus and Radiance Priors

Xianrui Luo*, Juewen Peng*, Ke Xian, Zijin Wu, Zhiguo Cao (*Co-first authors)

Information Fusion, 2023

Paper  |  GitHub

MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects

Juewen Peng, Jianming Zhang, Xianrui Luo, Hao Lu, Ke Xian, Zhiguo Cao

Proceedings of the European Conference on Computer Vision (ECCV), 2022

Paper  |  GitHub  |  Project

DoF-NeRF: Depth-of-Field Meets Neural Radiance Fields

Zijin Wu, Xingyi Li, Juewen Peng, Hao Lu, Zhiguo Cao, Weicai Zhong

Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), 2022

Paper  |  GitHub

BokehMe: When Neural Rendering Meets Classical Rendering

Juewen Peng, Zhiguo Cao, Xianrui Luo, Hao Lu, Ke Xian, Jianming Zhang

Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (Oral)

Paper  |  GitHub  |  Project

Interactive Portrait Bokeh Rendering System

Juewen Peng, Xianrui Luo, Ke Xian, Zhiguo Cao

IEEE International Conference on Image Processing (ICIP), 2021

Paper

Ranking-Based Salient Object Detection and Depth Prediction for Shallow Depth-of-Field

Ke Xian, Juewen Peng, Chao Zhang, Hao Lu, Zhiguo Cao

Sensors, 2021

Paper

Bokeh Rendering from Defocus Estimation

Xianrui Luo*, Juewen Peng*, Ke Xian, Zijin Wu, Zhiguo Cao (*Co-first authors)

Proceedings of the European Conference on Computer Vision Workshops (ECCVW), 2020

Paper

AIM 2020 Challenge on Rendering Realistic Bokeh

Andrey Ignatov, Radu Timofte, Ming Qian, Congyu Qiao, Jiamin Lin, Zhenyu Guo, Chenghua Li, Cong Leng, Jian Cheng, Juewen Peng, et al.

Proceedings of the European Conference on Computer Vision Workshops (ECCVW), 2020

Paper


Patents

A Two-Branch Bokeh Rendering Method and System Based on Physical Optics Model and Neural Network

Juewen Peng, Zhiguo Cao, Xianrui Luo, Ke Xian, Hao Lu

China Invention Patent, Publication Patent Number: CN113763524A, 2021



Competitions

Won Winner Award in "NTIRE 2023 Bokeh Effect Transformation Challenge".

Juewen Peng, Zhiyu Pan, Chengxin Liu, Xianrui Luo, Huiqiang Sun, Liao Shen, Ke Xian, Zhiguo Cao

Won Runner-Up Award in "AIM 2020 Challenge on Rendering Realistic Bokeh".

Juewen Peng, Xianrui Luo, Ke Xian, Zijin Wu, Zhiguo Cao



Other Experiences

Feb. 2024

Won 2023 CAA Outstanding Master's Degree Thesis Award（2023 中国自动化学会优秀硕士学位论文奖）.

Oct. 2022 - Dec. 2023

Worked on project “Large Aperture Bokeh Effect Simulation of DSLR” with Vivio.

Jul. 2021 - Jan. 2023

Cooperate with Jianming Zhang of Adobe Research.

Aug. 2022

Participated in "2022 Artificial Intelligence Conference and Entrepreneurs Summit Forum of China's Optics Valley (AICCOV 2022)" and won Best Poster Award.


Sep. 2020 - Apr. 2022

Worked on project "Multi-Camera Registration and Intelligent Depth-of-Field Extension" with Huawei.