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

The task of generating novel views of real scenes is increasingly importantnowadays when AI models become able to create realistic new worlds. In manypractical applications, it is important for novel view synthesis methods tostay grounded in the physical world as much as possible, while also being ableto imagine it from previously unseen views. While most current methods aredeveloped and tested in virtual environments with small scenes and no errors inpose and depth information, we push the boundaries to the real-world domain oflarge scales in the new context of UAVs. Our algorithmic contributions are twofolds. First, we manage to stay anchored in the real 3D world, by introducingan efficient multi-scale voxel carving method, which is able to accommodatesignificant noises in pose, depth, and illumination variations, while beingable to reconstruct the view of the world from drastically different poses attest time. Second, our final high-resolution output is efficiently self-trainedon data automatically generated by the voxel carving module, which gives it theflexibility to adapt efficiently to any scene. We demonstrated theeffectiveness of our method on highly complex and large-scale scenes in realenvironments while outperforming the current state-of-the-art. Our code ispublicly available: https://github.com/onorabil/MSVC.

Self-supervised novel 2D view synthesis of large-scale scenes with efficient multi-scale voxel carving