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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Image outpainting technology generates visually plausible content regardlessof authenticity, making it unreliable to be applied in practice. Thus, wepropose a reliable image outpainting task, introducing the sparse depth fromLiDARs to extrapolate authentic RGB scenes. The large field view of LiDARsallows it to serve for data enhancement and further multimodal tasks.Concretely, we propose a Depth-Guided Outpainting Network to model differentfeature representations of two modalities and learn the structure-awarecross-modal fusion. And two components are designed: 1) The Multimodal LearningModule produces unique depth and RGB feature representations from theperspectives of different modal characteristics. 2) The Depth Guidance FusionModule leverages the complete depth modality to guide the establishment of RGBcontents by progressive multimodal feature fusion. Furthermore, we speciallydesign an additional constraint strategy consisting of Cross-modal Loss andEdge Loss to enhance ambiguous contours and expedite reliable contentgeneration. Extensive experiments on KITTI and Waymo datasets demonstrate oursuperiority over the state-of-the-art method, quantitatively and qualitatively.

Towards Reliable Image Outpainting: Learning Structure-Aware Multimodal Fusion with Depth Guidance