Loading...

Mobile Intelligent Photography & Imaging
Workshop 2022

MIPI Workshop in conjunction with ECCV 2022, Tel-Aviv, Israel (Online)
Sunday October 23, 2022

Challenge Tracks

Overview

Developing and integrating advanced image sensors with novel algorithms in camera systems is prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lack of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI).

The workshop's main focus is on MIPI, emphasizing the integration of novel image sensors and imaging algorithms. Together with the workshop, we organize a few exciting challenges and invite renowned researchers from both industry and academia to share their insights and recent work. Our challenge includes five tracks:

Unlike previous workshops that focus on image or video manipulation, restoration and enhancement, or the efficient designs of AI models for mobile devices, the central theme of our workshop encompasses new sensors and imaging systems, which are the indispensable foundation for mobile intelligent photography and imaging. As the first workshop of this kind, MIPI aims to organize a dedicated workshop so that we can solicit relevant solutions and attract a focused group from both academia and industry for fruitful discussions.

Datasets and Submission

Datasets are available at the Codalab site of each challenge track. Submissions to all phases will be done through the CodaLab site. Please register to the site and refer to the instructions on how to download the datasets and submit your results. The evaluation metrics of each track will be introduced in the respective site.

Link to Codalab: RGB+ToF Depth Completion -- Quad-Bayer Re-mosaic -- RGBW Sensor Re-mosaic -- RGBW Sensor Fusion -- Under-display Camera Image Restoration

Awards and Prizes

The winner teams of each track will receive a certificate and be awarded a cash prize. Challenge participants with the most successful and innovative methods will be invited to present at the MIPI workshop. The cash prize for each track:

  • First place: USD 1000
  • Second place: USD 800
  • Third place: USD 500

Terms and Conditions

Link to Terms and Conditions.

In the event of any inconsistency between the terms and details of this website and Codalab competition sites, the details on the Codalab sites shall prevail.

Contact

For more information, please contact us at mipi.challenge@gmail.com.

Call for Papers

Coupled with the workshop, besides the challenge, we also provide a fertile ground for researchers, scientists, and engineers from around the world to disseminate their research outcomes and push forward the frontiers of knowledge within novel image sensors and imaging systems-related areas. The MIPI workshop topics cover but are not limited to:

  • ToF depth completion
  • Quad-Bayer/RGBW sensor re-mosaic and fusion
  • Under-display camera image restoration
  • Event camera for image/video restoration
  • Learnable ISPs
  • Learning-based computational imaging systems: smart imaging and sensing systems, learned data acquisition, task-driven ISPs, etc
  • Computationally efficient computational imaging systems and algorithms

Papers will be peer-reviewed and comply with the ECCV 2022 proceedings style, format and length. The deadline for camera ready submission is the same as the main conference. Papers accepted must be registered and presented to ensure their inclusion in the IEEE Xplore Library. Selected papers will be invited to present in the workshop. Some papers will also be invited to contribute to a book chapter or a special issue article in our future publication. The format for submission is the same as the ECCV 2022 requirements .

Paper submission and review site: Submission Site


Certificates for Best Paper Award and Best Paper Honorable Mention:

Best Paper Award:
Paper title: Event-based Image Deblurring with Dynamic Motion Awareness
Authors: Patricia Vitoria, Stamatios Georgoulis, Stepan Tulyakov, Alfredo Bochicchio, Julius Erbach, Yuanyou Li
Affiliation: Huawei
Prize: USD 1000

Best Paper Honorable Mention:
Paper title: Continuous Spectral Reconstruction from RGB Images via Implicit Neural Representation
Authors: Ruikang Xu, Mingde Yao, Chang Chen, Lizhi Wang, Zhiwei Xiong
Affiliations: University of Science and Technology of China, Huawei Noah's Ark Lab, Beijing Institute of Technology
Prize: USD 800

Important Dates

Event Date (Always 11:59 PM Pacific Time)
Site online Apr 08, 2022
Release of training data and validation data May 15, 2022
Validation server online May 15, 2022
Release of test data, test server online Jul 13, 2022
Test results submission deadline, test server closed Jul 20, 2022
Fact sheets submission deadline Jul 20, 2022
Final test and rating results release to participants Jul 30, 2022
Event Date (Always 11:59 PM Pacific Time)
Site online Apr 08, 2022
CMT online Apr 25, 2022
Paper submission deadline Aug 08, 2022
Supplementary materials deadline Aug 08, 2022
Notification to authors Aug 18, 2022
Camera ready deadline Aug 22, 2022
Workshop date Oct 23, 2022

Schedule

Time (Israel)

Programme (Video Recording)

9:00 – 9:10
Opening and Welcome
9:10 – 10:00
Keynote Speaker
Keynote: Denoising as a Building Block for Imaging, Inverse Problems, and Machine Learning
  • [Abstract]
  • Denoising is one of the oldest problems in imaging. In the last decade, the quality of denoising algorithms has reached phenomenal levels – almost as good as we can ever hope. There are thousands of papers on this topic, and their scope is vast and approaches so diverse that putting them in some order (as I will do) is both useful and challenging. I will describe what we can say about this general class of operators, and what makes them so special. I will argue that denoising is more important than ever; not simply as a process for removing noise, but especially now as a core engine and building block for much more complex tasks in imaging, inverse problems, and machine learning.
Jerome Bell
Peyman Milanfar

Principal Scientist/Director, Google Research

10:00 – 10:15
Best Paper Award
Best Paper Award

Winner Paper: Event-based Image Deblurring with Dynamic Motion Awareness

Presenter: Patricia Vitoria (Huawei Zurich Research Center)
10:15 – 10:30
Best Paper Mention
Best Paper Honorable Mention

Winner Paper: Continuous Spectral Reconstruction from RGB Images via Implicit Neural Representation

Presenter: Ruikang Xu (University of Science and Technology of China)
10:30 - 10:50
Invited Speaker
Invited Talk: Combining Internal and External Constraints for Unrolling Shutter in Videos
Presenter: Eyal Naor (The Weizmann Institute of Science)
10:50 - 11:10
Invited Speaker
Invited Talk: Synthesizing Light Field Video from Monocular Video
Presenter: Shrisudhan Govindarajan (Indian Institute of Technology Madras)
11:10 - 11:20
☕ Tea Break
11:20 - 11:35
Winning Solution
Challenge Winner: ToF Depth Completion Track
Presenter: Dewang Hou (Peking University)
11:35-11:50
Winning Solution
Challenge Winner: Quad-Bayer Remosaic & RGBW Sensor Remosaic Tracks
Presenter: Lingchen Sun (OPPO Research Institute)
11:50 - 12:10
Invited Speaker
Invited Talk: Animation from Motion Blur or Rolling Shutter Distortion
Presenter: Zhihang Zhong (The University of Tokyo)
12:10 - 12:30
Invited Speaker
Invited Talk: Event-Based Fusion for Motion Deblurring with Cross-Modal Attention
Presenter: Lei Sun (ETH Zurich)
12:30 - 13:50
🍱 Break
13:50 - 14:05
Winning Solution
Challenge Winner: RGBW Sensor Fusion Track
Presenter: DongJae Lee (Korea Advanced Institute of Science and Technology)
14:05 - 14:20
Winning Solution
Challenge Runner-up: RGBW Sensor Remosaic Track
Presenter: Qiaosi Yi (East China Normal University)
14:20 - 14:35
Winning Solution
Challenge Winner: UDC Image Restoration Track
Presenter: Yurui Zhu (University of Science and Technology of China)
14:35 - 15:25
Keynote Speaker
Keynote: Recent Evolution on Image Sensing
  • [Abstract]
  • The current growth of the image sensor market is mainly driven by demands for the mobile imaging market. The driving force is further expected to continue more than several years from now. Thus, it is worthy to consider what kinds of demands come from the mobile imaging market to understand what kinds of imaging technologies are required.
    
    On the other hand, sensing applications, which utilize image sensor date not only for taking pictures but also for person identification, product inspection, obstacle avoidance and so on, are emerging. They seem to growth in industry and automotive markets at first but expected in mobile market soon. In sensing applications, non-RGB image sensors are utilized as well as RGB image sensors.
    
    In this talk, recent evolutions of image sensors for both RGB and other than RGB are introduced. First, RGB imaging technologies which have been implemented in recent image sensor products for mobile market are introduced. Second, some new-generation image sensors which are to acquire information other than RGB are introduced. Also, expectations that such new-generation image sensors are promising for mobile imaging applications in the future are explained by introducing some recent researches in vision-based imaging area.
Jerome Bell
Tomoo Mitsunaga

Manager, Sony Europe B.V.

15:25 - 16:15
Keynote Speaker
Keynote: Robust Imaging Color and the Dual-Purpose ISP
  • [Abstract]
  • In this talk, I will discuss recent work targeting imaging strategies to allow robust color imaging. In particular, I will overview capture-time algorithms that allows processed images to be unprocessed to correct potential errors that affect image color. I will also discuss the idea of a "dual-purpose" image signal processor (ISP) that is suitable for both photographic and scientific tasks.
Jerome Bell
Michael S. Brown

Professor, York University

16:15 - 17:05
Keynote Speaker
Keynote: Computer Vision, One Photon at a Time
  • [Abstract]
  • Single-photon avalanche diodes (SPADs) are an emerging sensor technology that promises single-photon sensitivity and the ability to time-tag photons with picosecond precision. In the last few years, we have witnessed a single-photon revolution, resulting for the first time in multi-megapixel SPAD arrays, which allow capturing sufficient spatial details needed for mainstream computer vision applications, including object detection and tracking, text recognition, pose recognition, and SLAM. This raises the following questions: Are SPADs ready to be used beyond niche scientific applications, as general-purpose computer vision sensors? Can they be deployed outside the lab in-the-wild? If so, what are their benefits over conventional cameras?
Jerome Bell
Mohit Gupta

Associate Professor, University of Wisconsin-Madison

17:05 - 17:20
Closing

Keynote Speakers

Ralph Edwards
Michael S. Brown

Professor/Director
York University/Samsung AI Center

Ralph Edwards
Mohit Gupta

Associate Professor
University of Wisconsin-Madison

Ralph Edwards
Peyman Milanfar

Principal Scientist/Director
Google Research

Ralph Edwards
Tomoo Mitsunaga

Manager
Sony Europe B.V.

Awards (Certificates)

Rank Prize Team Name Affiliation Team Members
1st USD 1000 ZoomNeXt Peking University
Tsinghua University
Dewang Hou
Kai Zhao
2nd USD 800 GAMEON The Chinese University of Hong Kong
International Digital Economy Academy
The Chinese University of Hong Kong
SmartMore
SmartMore
The Chinese University of Hong Kong
Liying Lu
Yu Li
Huaijia Lin
Ruizheng Wu
Jiangbo Lu
Jiaya Jia
3rd USD 500 Singer BeiHang University
BeiHang University
BeiHang University
BeiHang University
BeiHang University
BeiHang University
Qiang Liu
Haosong Yue
Danyang Cao
Lehang Yu
Jiaxuan Quan
Jixiang Liang
Rank Prize Team Name Affiliation Team Members
1st USD 1000 op-summer-po OPPO Research Institute
OPPO Research Institute
East China Normal University
Rongyuan Wu
Lingchen Sun
Qiaosi Yi
2nd USD 800 JHC-SJTU Shanghai Jiao Tong University
Shanghai Jiao Tong University
Shanghai Jiao Tong University
Shanghai Jiao Tong University
Transsion
Transsion
Xiaohong Liu
Jun Jia
Hanchi Sun
Guangtao Zhai
Anlong Xiao
Qihang Xu
3rd USD 500 IMEC-IPI&NPU-MPI IMEC research group in Ghent University
Northwestern PolytechnicalUniversity
Northwestern PolytechnicalUniversity
IMEC & Ghent University
IMEC & Ghent University
IMEC & Ghent University
IMEC & Ghent University
Haijin Zeng
Kai Feng
Yongqiang Zhao
Hiep Quang Luong
Jan Aelterman
Anh Minh Truong
Wilfried Philips
Rank Prize Team Name Affiliation Team Members
1st USD 1000 op-summer-po OPPO Research Institute
OPPO Research Institute
East China Normal University
Lingchen Sun
Rongyuan Wu
Qiaosi Yi
2nd USD 800 Eating, Drinking,
and Playing
East China Normal University
OPPO Research Institute
OPPO Research Institute
East China Normal University
Qiaosi Yi
Rongyuan Wu
Lingchen Sun
Faming Fang
3rd USD 500 HIT-IIL Harbin Institute of Technology
Harbin Institute of Technology
Harbin Institute of Technology
Harbin Institute of Technology
Harbin Institute of Technology
Harbin Institute of Technology
Harbin Institute of Technology
Rongjian Xu
Xiaohui Liu
Zhilu Zhang
Xiaohe Wu
Ruohao Wang
Junyi Li
Wangmeng Zuo
Rank Prize Team Name Affiliation Team Members
1st USD 1000 LLCKP Korea Advanced Institute of Science & Technology DongJae Lee
2nd USD 800 MegNR Megvii Technology
Megvii Technology
Megvii Technology
Megvii Technology
Megvii Technology
Megvii Technology
Megvii Technology
Megvii Technology
Ting Jiang
Qi Wu
Chengzhi Jiang
Mingyan Han
Xinpeng Li
Wenjie Lin
Youwei Li
Haoqiang Fan
Shuaicheng Liu
3rd USD 500 jzsherlock Xiaomi Zhuang Jia
Rank Prize Team Name Affiliation Team Members
1st USD 1000 USTC_WXYZ University of Science and Technology of China
University of Science and Technology of China
University of Science and Technology of China
Shanghai AI Laboratory
Yurui Zhu
Xi Wang
Xueyang Fu
Xiaowei Hu
2nd USD 800 XPixel Group Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
University of Macau & Shenzhen Institutes of Advanced Technology,
Chinese Academy of Sciences & Shanghai AI Laboratory
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences &
Shanghai AI Laboratory
Jinfan Hu
Xina Liu
Xiangyu Chen

Chao Dong
3rd USD 500 SRC-B Samsung Research China
Samsung Research China
Samsung Research China
Samsung Research China
Samsung Research China
Dafeng Zhang
Feiyu Huang
Shizhuo Liu
Xiaobing Wang
Zhezhu Jin

Organizers

Ralph Edwards
Chongyi Li

Nanyang Technological University

Ralph Edwards
Shangchen Zhou

Nanyang Technological University

Ralph Edwards
Ruicheng Feng

Nanyang Technological University

Ralph Edwards
Jun Jiang

SenseBrain

Ralph Edwards
Wenxiu Sun

SenseTime/Tetras.AI

Ralph Edwards
Qingyu Yang

SenseBrain

Qingpeng Zhu

SenseTime/Tetras.AI

Ralph Edwards
Chen Change Loy

Nanyang Technological University

Ralph Edwards
Jinwei Gu

SenseBrain

Sponsors

                   
Top