Novel view synthesis via depth-guided skip connections

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

Abstract

We introduce a principled approach for synthesizing new views of a scene given a single source image. Previous methods for novel view synthesis can be divided into image-based rendering methods (e.g., flow prediction) or pixel generation methods. Flow predictions enable the target view to re-use pixels directly, but can easily lead to distorted results. Directly regressing pixels can produce structurally consistent results but generally suffer from the lack of low-level details. In this paper, we utilize an encoder-decoder architecture to regress pixels of a target view. In order to maintain details, we couple the decoder aligned feature maps with skip connections, where the alignment is guided by predicted depth map of the target view. Our experimental results show that our method does not suffer from distortions and successfully preserves texture details with aligned skip connections.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021
PublisherIEEE
Pages3118-3127
Number of pages10
ISBN (Electronic)9780738142661
DOIs
Publication statusPublished - Jan 2021
MoE publication typeA4 Article in a conference publication
EventIEEE Winter Conference on Applications of Computer Vision - Virtual, Online, United States
Duration: 5 Jan 20219 Jan 2021

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision
Abbreviated titleWACV
Country/TerritoryUnited States
CityVirtual, Online
Period05/01/202109/01/2021

Fingerprint

Dive into the research topics of 'Novel view synthesis via depth-guided skip connections'. Together they form a unique fingerprint.

Cite this