Submission

• • • Authors are encouraged to submit high-quality, original (i.e., not been previously published or accepted for publication in substantially similar form in any peer-reviewed venue including journal, conference or workshop) research.

    • All submissions should follow the same template as for the main WACV2023 conference. The author kit/paper template is provided in Latex format via this overleaf template and this github repository.

    • The main paper has an 8-page limit, references do not count toward this. There is no limit on the number of pages in the supplementary material. Only .pdf files are accepted.

    • Unlike the main conference, the review process for this workshop has only one round, and is single-blind. Authors do not have to be anonymized when submitting their work.

    • Authors of accepted papers are required to present their work live, either in-person or remote. We will not accept pre-recorded presentations.

Important Dates/Links:

• Submission Deadline: 11^th October, 2022, 11:59pm PST 25th October, 2022, 11:59pm PST

• Submission Link: http://cmt3.research.microsoft.com/WVAQ2023

• Acceptance Notification Deadline: 9^th November, 2022

• Camera Ready Papers Submission Deadline: 19^th November, 2022

• Workshop Day: 7^th January, 2023

• If you have any question, please contact us at: wacv2023-workshop-image-quality@amazon.com.

Call for Papers:

Description: Many computer vision algorithms are susceptible to video/audio quality artifacts. Visual intelligent systems are normally trained and tested on high quality video/audio datasets, while in reality we cannot assume high quality due to video encoding, transmission and decoding. Video/audio quality has become increasingly important in real-world systems, yet is often overlooked in the computer vision community. Therefore, it is interesting to investigate computer vision performance on input images/video with quality distortions. How the video/audio distortions come from, how we assess the quality, how they affect our applications, and what we can do to mitigate them to suit for our computer vision user cases.

This workshop welcomes contributions for oral presentations and/or posters in the following topics:

1. Evaluation of video/audio quality in machine learning and computer vision use-cases such as object detection, segmentation, tracking, and recognition;

2. Evaluation of video/audio quality in multi-modal use cases;

3. Analyze, model and learn the quality impact from video/audio acquisition, compression, transcoding, transmission, decoding, rendering, and/or display;

4. Novel video/audio quality assessment methodologies: full reference, reduced-reference, and non-reference;

5. Video/audio quality issues in synthesized and/or computer-generated video/audio data;

6. Techniques used to remove artifacts such as shadows, glare, and reflections, etc.;

7. Techniques used to improve quality such as brightening, color adjustment, sharpening, inpainting, deblurring, denoising, de-hazing, de-raining, demosaicing, etc.;

8. Video/image quality improvement on resolution, frame rate, color gamut, dynamic range (SDR vs. HDR), blurring, noise, lighting, etc.;

9. Datasets, statistics, and theory of video/audio quality;

10. Research, applications and system development of the above.