Bridging the Gap between Computational Photography and Visual Recognition. Call for Papers

The 6th UG2+ Workshop and Prize Challenge: 
Bridging the Gap between Computational Photography and Visual Recognition. 

In conjunction with CVPR 2023, June 19

Website: http://www.ug2challenge.org/

Contact: cvpr2023.ug2challenge@gmail.com

Track 1: Object Detection in Haze

While most current vision systems are designed to perform in
environments where the subjects are well observable without
(significant) attenuation or alteration, a dependable vision system
must reckon with the entire spectrum of complex unconstrained and
dynamic degraded outdoor environments. It is highly desirable to study
to what extent, and in what sense, such challenging visual conditions
can be coped with, for the goal of achieving robust visual
sensing.This challenge is based on the A2I2-Haze, the first real haze
dataset with in-situ smoke measurement aligned to aerial and ground
imagery.

Track 2: Atmospheric Turbulence Mitigation

The theories of turbulence and propagation of light through random
media have been studied for the better part of a century. Yet progress
for associated image reconstruction algorithms has been slow, as the
turbulence mitigation problem has not thoroughly been given the modern
treatments of advanced image processing approaches (e.g., deep
learning methods) that have positively impacted a wide variety of
other imaging domains (e.g., classification). This challenge aims to
promote the development of new image reconstruction algorithms for
incoherent imaging through anisoplanatic turbulence.

Track 3: Single Image Deraining

Images captured in adverse weather conditions significantly impact the
performance of many vision tasks. Rain is a common weather phenomenon
that introduces visual degradations to captured images and videos
through partial occlusions of objects – in heavy rain, severe
occlusion to the background. As most vision algorithms assume clear
weather, with no interference of rain, their performance
suffers. Deraining is the task of removing such visual degradations so
that the images are better suited to the assumptions of downstream
vision algorithms, as well as for aesthetic fruition. This challenge
aims to spark innovative ideas that will push the envelope of single
image deraining on real images.

Paper Track:

    Novel algorithms for robust object detection, segmentation or
    recognition on outdoor mobility platforms, such as UAVs, gliders,
    autonomous cars, outdoor robots, etc.

    Novel algorithms for robust object detection and/or recognition in
    the presence of one or more real-world adverse conditions, such as
    haze, rain, snow, hail, dust, underwater, low-illumination, low
    resolution, etc.

    The potential models and theories for explaining, quantifying, and
    optimizing the mutual influence between the low-level
    computational photography (image reconstruction, restoration, or
    enhancement) tasks and various high-level computer vision tasks.

    Novel physically grounded and/or explanatory models, for the
    underlying degradation and recovery processes, of real-world
    images going through complicated adverse visual conditions.

    Novel evaluation methods and metrics for image restoration and
    enhancement algorithms, with a particular emphasis on no-reference
    metrics, since for most real outdoor images with adverse visual
    conditions it is hard to obtain any clean "ground truth" to
    compare with.

Submission: https://cmt3.research.microsoft.com/UG2CHALLENGE2023

Special This Year!

The 2023 UG2+ workshop will partner with IEEE Transactions on
Computational Imaging to bridge the computer vision and computational
imaging community. Our objective is to strengthen synergy across the
communities by providing UG2+ authors with an opportunity to publish
in a journal with an expedited review process.

Authors of the workshop proceedings (8-pages) can indicate in the CMT
submission page whether they would like the paper to be considered for
IEEE Transactions on Computational Imaging. A paper cannot be
simultaneously published as a workshop proceeding and a journal.

    Authors of the workshop proceedings will have a choice in the CMT
    submission page to indicate if they would like the paper to be
    considered for publishing at IEEE Transactions on Computational
    Imaging. UG2+ paper reviewers and workshop chairs will identify
    high-quality papers. In consultation with the TCI editorial board,
    we will make recommendations to the shortlisted paper.

    For papers recommended to TCI, authors will be notified of
    additional instructions including reformatting into the TCI format
    (10 pages) and submitting the files to ScholarOne
    website. Suggestions from the TCI editorial board will be given to
    assist authors so that the journal review will be expedited.

    For papers that indicate workshop proceedings OR not shortlisted
    by TCI, the publication decision will be solely based on UG2+
    workshop criteria.

    Our shortlisting criteria follows the IEEE Signal Processing
    Society publication requirement. While we cannot guarantee
    acceptance to the journal ultimately, shortlisted papers are meant
    to pass the screening of the TCI editorial board with positive
    recommendations. The final journal decision will be made by the
    editor-in-chief, Professor Mujdat Cetin.

Important Dates:

    Paper submission: March 22, 2023 (11:59PM PST)
    Camera ready deadline: April 2, 2023 (11:59PM PST)
    Challenge result submission: May 1, 2023 (11:59PM PST)
    Winner Announcement: May 25, 2023 (11:59PM PST)
    CVPR 2023 Workshop: June 19, 2023 (Full day)

Speakers:

    Jong Chul Ye (Korea Advanced Institute of Science & Technology)
    Sabine Süsstrunk (EPFL)
    Jinwei Gu (SenseBrain)
    Vishal M. Patel (John Hopkins University)
    Nianyi Li  (Clemson University)
    Tianfan Xue (The Chinese University of Hong Kong)
    Emma Alexander (North Western University)
    Kevin J. Miller (US Army)

Organizers:

    Zhiyuan Mao (Purdue University)
    Stanley H. Chan (Purdue University)
    Wuyang Chen (UT Austin)
    Zhangyang Wang (UT Austin)
    Howard Zhang (University of California, Los Angeles)
    Yunhao Ba (University of California, Los Angeles)
    Achuta Kadambi (University of California, Los Angeles)
    Alex Wong (Yale University)
    Ajay Jaiswal (UT Austin)
    Abdullah Al-Shabili (Purdue University)
    Xingguang Zhang (Purdue University)
    Zhenyu Wu (Wormpex AI Research)
    Kevin J. Miller (US Army)
    Jiaying Liu (Peking University)
    Walter J. Scheirer (University of Notre Dame)
    Wenqi Ren (Chinese Academy of Sciences)