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

Neural rendering of implicit surfaces performs well in 3D visionapplications. However, it requires dense input views as supervision. When onlysparse input images are available, output quality drops significantly due tothe shape-radiance ambiguity problem. We note that this ambiguity can beconstrained when a 3D point is visible in multiple views, as is the case inmulti-view stereo (MVS). We thus propose to regularize neural renderingoptimization with an MVS solution. The use of an MVS probability volume and ageneralized cross entropy loss leads to a noise-tolerant optimization process.In addition, neural rendering provides global consistency constraints thatguide the MVS depth hypothesis sampling and thus improves MVS performance.Given only three sparse input views, experiments show that our method not onlyoutperforms generic neural rendering models by a large margin but alsosignificantly increases the reconstruction quality of MVS models. Project page:https://hao-yu-wu.github.io/s-volsdf/.

S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfaces