Tampere University of Technology

TUTCRIS Research Portal

End-to-end learning for video frame compression with self-attention

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
PublisherIEEE
Pages580-584
Number of pages5
ISBN (Electronic)9781728193601
ISBN (Print)978-1-7281-9361-8
DOIs
Publication statusPublished - 2020
Publication typeA4 Article in a conference publication
EventIEEE Computer Society Conference on Computer Vision and Pattern Recognition workshops - Virtual, Online, United States
Duration: 14 Jun 202019 Jun 2020

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

ConferenceIEEE Computer Society Conference on Computer Vision and Pattern Recognition workshops
CountryUnited States
CityVirtual, Online
Period14/06/2019/06/20

Abstract

One of the core components of conventional (i.e., non-learned) video codecs consists of predicting a frame from a previously-decoded frame, by leveraging temporal correlations. In this paper, we propose an end-to-end learned system for compressing video frames. Instead of relying on pixel-space motion (as with optical flow), our system learns deep embeddings of frames and encodes their difference in latent space. At decoder-side, an attention mechanism is designed to attend to the latent space of frames to decide how different parts of the previous and current frame are combined to form the final predicted current frame. Spatially-varying channel allocation is achieved by using importance masks acting on the feature-channels. The model is trained to reduce the bitrate by minimizing a loss on importance maps and a loss on the probability output by a context model for arithmetic coding. In our experiments, we show that the proposed system achieves high compression rates and high objective visual quality as measured by MS-SSIM and PSNR. Furthermore, we provide ablation studies where we highlight the contribution of different components.

Publication forum classification

Field of science, Statistics Finland