{"id":733501,"date":"2021-04-20T21:08:11","date_gmt":"2021-04-21T04:08:11","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&p=733501"},"modified":"2021-05-30T23:12:35","modified_gmt":"2021-05-31T06:12:35","slug":"image-video-transformation","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/image-video-transformation\/","title":{"rendered":"Image\/Video Transformation"},"content":{"rendered":"

Image and video have become the language people use to communicate on the Internet. Multimedia content connects people and appeals to the young. This project aims at deep image and video transformation to generate high-quality image and video content in an automatic way and create more engaging experiences for modern work and life. Our vision is broad and focuses on developing state-of-the-art AI technology for fast, reliable, and cost-effective content creation, communication, and consumption. Our technology can benefit multiple experiences across M365, including enterprise, education, consumer, and device-specific experiences.<\/p>\n

What are\u00a0we\u00a0trying to do?<\/h5>\n

The objective of this project is to enable a more automated pipeline for image and video generation, review, and publishing.\u00a0Applications include\u00a0image\/video stylization, inpainting, super-resolution, icon generation,\u00a0looping\u00a0videos, and scene composition.\u00a0Powered by deep learning models\u202fbuilt by MSRA,\u00a0 multiple\u202fhigh-quality\u202fvariants can be produced for\u202feach image\/video at no additional cost to human designers.<\/p>\n

How is it done today?<\/h5>\n

Current image\u00a0and\u00a0video transformations\u00a0are\u00a0mainly\u00a0conducted by human designers, which\u00a0is\u00a0labor\u00a0intensive.\u00a0For example, users insert 26M images a day to PowerPoint, and human designers\u00a0generally\u00a0offer limited treatment\u00a0of images.<\/p>\n

What is novel in our approach?<\/h5>\n

We\u00a0seek\u00a0to\u00a0push forward the frontiers of\u00a0research on\u00a0high-quality image\/video transformation and make\u00a0impact\u00a0across both academia and industry.\u00a0 We have developed\u00a0self-attention\u00a0based Generative Networks with lightweight network optimization.\u00a0We\u00a0are\u00a0also designing big models\u00a0to understand and create multimedia content from the perspective of multiple modalities (e.g., vision\u00a0and\u00a0language).\u00a0We have\u00a0already\u00a0published\u00a0top-tier\u00a0papers\u00a0along these\u00a0two dimensions, for example,\u00a0in\u00a0CVPR 2019, CVPR 2020, ECCV 2020, ACM\u00a0Multimedia 2020\u00a0and\u00a0NeurIPS\u00a02020.<\/p>\n

\"SR-Style\"<\/p>\n","protected":false},"excerpt":{"rendered":"

Image and video have become the language people use to communicate on the Internet. Multimedia content connects people and appeals to the young. This project aims at deep image and video transformation to generate high-quality image and video content in an automatic way and create more engaging experiences for modern work and life. Our vision […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556,13551],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-733501","msr-project","type-msr-project","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-graphics-and-multimedia","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"2019-02-01","related-publications":[833962,910146,833968,664185,859608,746284,863247,746293,867717,746305,868332,746350,870258,771334,876189,771340,876195,771346,880014,792887,885171],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Jianlong Fu","user_id":32260,"people_section":"Section name 0","alias":"jianf"},{"type":"user_nicename","display_name":"Bei Liu","user_id":38889,"people_section":"Section name 0","alias":"libei"},{"type":"user_nicename","display_name":"Kai Qiu","user_id":38988,"people_section":"Section name 0","alias":"kaqiu"}],"msr_research_lab":[199560],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/733501"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":7,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/733501\/revisions"}],"predecessor-version":[{"id":745945,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/733501\/revisions\/745945"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=733501"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=733501"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=733501"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=733501"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=733501"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}