English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Novel view synthesis is a challenging problem in computer vision androbotics. Different from the existing works, which need the reference images or3D models of the scene to generate images under novel views, we propose a novelparadigm to this problem. That is, we synthesize the novel view from only a6-DoF camera pose directly. Although this setting is the most straightforwardway, there are few works addressing it. While, our experiments demonstratethat, with a concise CNN, we could get a meaningful parametric model that couldreconstruct the correct scenery images only from the 6-DoF pose. To this end,we propose a two-stage learning strategy, which consists of two consecutiveCNNs: GenNet and RefineNet. GenNet generates a coarse image from a camera pose.RefineNet is a generative adversarial network that refines the coarse image. Inthis way, we decouple the geometric relationship between mapping and texturedetail rendering. Extensive experiments conducted on the public datasets provethe effectiveness of our method. We believe this paradigm is of high researchand application value and could be an important direction in novel viewsynthesis.

Novel View Synthesis from only a 6-DoF Camera Pose by Two-stage Networks