Learning Task Agnostic Temporal Consistency Correction

Muhammad Kashif Ali, Dongjin Kim, Tae Hyun Kim

Keywords: Video Processing, Temporal Consistency Correction, Video Restoration

TL;DR: This work provides a general framework for task agnostic video temporal consistency correction capable of producing visually pleasing and temporally consistent videos without the requiring their unprocessed counterparts.

Abstract: In many video restoration/translation tasks, image processing operations are naively extended to the video domain by processing each frame independently. This disregard for the temporal connection in video processing often leads to severe temporal inconsistencies. State-of-the-art techniques that address these inconsistencies rely on the availability of unprocessed videos to siphon consistent video dynamics to restore the temporal consistency of frame-wise processed videos. We propose a novel general framework for this task that learns to infer consistent motion dynamics from inconsistent videos to mitigate the temporal flicker while preserving the perceptual quality for both the temporally neighboring and relatively distant frames. The proposed framework produces state-of-the-art results on two benchmark datasets, DAVIS and videvo.net, processed by numerous image processing applications in a frame-wise processing manner. The code and the trained models will be released upon acceptance.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)