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

Uncalibrated photometric stereo (UPS) is challenging due to the inherentambiguity brought by unknown light. Existing solutions alleviate the ambiguityby either explicitly associating reflectance to light conditions or resolvinglight conditions in a supervised manner. This paper establishes an implicitrelation between light clues and light estimation and solves UPS in anunsupervised manner. The key idea is to represent the reflectance as fourneural intrinsics fields, i.e., position, light, specular, and shadow, based onwhich the neural light field is implicitly associated with light clues ofspecular reflectance and cast shadow. The unsupervised, joint optimization ofneural intrinsics fields can be free from training data bias as well asaccumulating error, and fully exploits all observed pixel values for UPS. Ourmethod achieves a superior performance advantage over state-of-the-art UPSmethods on public and self-collected datasets, under regular and challengingsetups. The code will be released soon.

NeIF: Representing General Reflectance as Neural Intrinsics Fields for Uncalibrated Photometric Stereo