Sept. 14th 2018   
 Munich, Germany


Workshop and Challenge on
Perceptual Image Restoration
and Manipulation


in conjunction with ECCV 2018

The Challenges:

The Workshop

A key goal in image restoration, manipulation and generation, is to produce images that are visually appealing to human observers. In recent years, there has been great interest as well as significant progress in perceptually-aware computer vision algorithms. However, many works have observed a fundamental disagreement between this recent leap in performance, as evaluated by human observers, and the objective assessment of these methods by common evaluation metrics (e.g. PSNR, SSIM). This workshop will revolve around two main themes: (i) How to design algorithms which satisfy human observers, and (ii) How to evaluate the perceptual quality of such algorithms.

Invited talks

The workshop will host three invited talks by Alexei A. Efros (UC Berkeley), Eli Shechtman (Adobe Research) and Tomer Michaeli (Technion).

Challenges

Three challenges on perceptual super-resolution, mobile photo enhancement, and hyperspectral reconstruction will compare and rank perceptual-quality based methods.

Poster session

Exciting new results of recent and ongoing research projects will be presented in a poster session.

The Challenges

The PIRM challenges will promote perceptual image restoration. State-of-the-art methods in terms of perceptual quality (e.g. SRGAN) are rated poorly by "simple" distortion measures such as PSNR and SSIM. Therefore, in contrast to previous challenges, the evaluation and ranking will be done in a perceptual-quality aware manner based on [Blau and Michaeli, CVPR'18]. This unified approach quantifies the accuracy and perceptual quality of algorithms jointly, and will enable perceptual-driven methods to compete alongside algorithms that target PSNR maximization.

The challenge results will be announced at the workshop. Challenge participants may submit papers for the ECCV workshop proceedings. Papers will be accepted based on: (i) academic quality, and (ii) challenge ranking.

Super-Resolution

Challenge on 4x super-resolution from a single-image.

Mobile photo enhancement

Challenge on enhancing photos taken by mobile phone cameras.

Hyperspectral reconstruction

Challenge on reconstrcuting hyper-spectral images.

Invited Speakers

Alexei A. Efros

UC Berkeley

Alexei A. Efros is a professor at EECS Department at UC Berkeley, where he is part of the Berkeley Artificial Intelligence Research Lab (BAIR). Before that, he spent nine years on the faculty of the Robotics Institute at CMU. He did his post-doc with Andrew Zisserman at Oxford. Starting in 2007, he have also been closely collaborating with Team WILLOW at École Normale Supérieure / INRIA in Paris. The central goal of his research is to use vast amounts of visual data to understand, model, and recreate the visual world around us. His research has been mainly in data-driven computer vision, as well as its projection onto computer graphics and computational photography. Other interests include human vision, unsupervised learning, visual data mining, robotics, and the applications of computer vision to the visual arts and the humanities. For a high-level overview of his research, see a recent Heidelberg Forum talk on "Self-Supervised Visual Learning and Synthesis".

Eli Shechtman

Adobe Research

Eli Shechtman is a Principal Scientist at the Creative Intelligence Lab at Adobe Research. He received the B.Sc. degree in Electrical Engineering (magna cum laude) from Tel-Aviv University in 1996. Between 2001 and 2007 he attended the Weizmann Institute of Science where he received with honors his M.Sc. and Ph.D. degrees in Applied Mathematics and Computer Science. In 2007 he joined Adobe and started sharing his time as a post-doc with the University of Washington in Seattle. He published over 60 academic publications and holds over 20 issued patents. He served as a Technical Paper Committee member at SIGGRAPH 2013 and 2014, as an Area Chair at CVPR’15, ICCV’15 and CVPR’17 and serves an Associate Editor at TPAMI. He received several honors and awards, including the Best Paper prize at ECCV 2002, a Best Poster Award at CVPR 2004, a Best Reviewer Award at ECCV 2014, published two Research Highlights papers in the Communication of the ACM journal and recently he awarded the Hemholtz Prize at ICCV’17.

Tomer Michaeli

Technion

Tomer Michaeli is an Assistant Professor at the EE faculty at the Technion -- Israel Institute of Technology. He completed his B.Sc. (summa cum laude) and Ph.D degrees at the EE faculty at the Technion in 2005 and 2012, respectively. From 2012 to 2015 he was a postdoctoral fellow at the CS and Applied Math Department at the Weizmann Institute Science. In 2015 he joined the Technion as a faculty member. His research lies in the fields of Signal and Image Processing, Computer Vision, Graphics, and Machine Learning. In particular, he studies statistical and machine-learning techniques for signal recovery problems (noise removal, blur removal, resolution enhancement), feature extraction and visualization, and analyzes fundamental tradeoffs and limitations in those domains. He won several awards, including the Alon Fellowship, the Konigsberg Award for Excellence in Teaching, and the Hershel Rich Technion Innovation Award.

Call for Posters

A poster session will be held at the workshop. We invite submissions of posters presenting work on perceptual-quality driven algorithms, methods for evaluating perceptual quality, or any other related topic.

Submission

To submit your poster, please send an extended abstract of 2-3 pages by email to . The email must include the poster title, authors, affiliations, and main contact email. Submission deadline is July 29th.

Review

Submissions will be reviewed by the workshop organizers. Accepted posters will be presented at the workshop. Note that accepted abstracts will not appear in the ECCV workshop proceedings.

Acceptance

Posters will be accepted in a rolling manner, i.e. if you submit your abstract before the deadline, acceptance may be decided earlier. Acceptance notification will be sent at latest by August 1st.

Important dates

Date

Event

May 1st

Validation data released - Done!

July 18th

Test data released

July 25th

Final results submission deadline

July 29th

Poster submission deadline

August 1st

Challenge results released to participants
Poster decisions released

August 22nd

Paper submission deadline
(optional for challenge participants only)

September 5th

Notification of accepted papers

September 14th

PIRM 2018 Workshop

TBD

Camera-ready deadline

* All dates refer to 11:59 PM CET

Sponsors

Organizers

Lihi Zelnik-Manor

Technion, Israel

Tomer Michaeli

Technion, Israel

Radu Timofte

ETH Zurich, Switzerland

Roey Mechrez

Technion, Israel

Yochai Blau

Technion, Israel

Co-organizers

Andrey Ignatov

ETH Zurich, Switzerland

Antonio Robles-Kelly

Australian National University and Date61-CSIRO

Mehrdad Shoeiby

Data61-CSIRO