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/

Zendy Plus

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

Zendy Tools

Zendy Open

Many Multi-View-Stereo algorithms extract a 3D mesh model of a scene, afterfusing depth maps into a volumetric representation of the space. Due to thelimited scalability of such representations, the estimated model does notcapture fine details of the scene. Therefore a mesh refinement algorithm isusually applied; it improves the mesh resolution and accuracy by minimizing thephotometric error induced by the 3D model into pairs of cameras. The choice ofthese pairs significantly affects the quality of the refinement and usuallyrelies on sparse 3D points belonging to the surface. Instead, in this paper, toincrease the quality of pairs selection, we exploit the 3D model (before therefinement) to compute five metrics: scene coverage, mutual image overlap,image resolution, camera parallax, and a new symmetry term. To improve therefinement robustness, we also propose an explicit method to manage occlusions,which may negatively affect the computation of the photometric error. Theproposed method takes into account the depth of the model while computing thesimilarity measure and its gradient. We quantitatively and qualitativelyvalidated our approach on publicly available datasets against state of the artreconstruction methods.

Mesh-based Camera Pairs Selection and Occlusion-Aware Masking for Mesh Refinement