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

Geometry reconstruction of textureless, non-Lambertian objects under unknownnatural illumination (i.e., in the wild) remains challenging as correspondencescannot be established and the reflectance cannot be expressed in simpleanalytical forms. We derive a novel multi-view method, DeepShaRM, that achievesstate-of-the-art accuracy on this challenging task. Unlike past methods thatformulate this as inverse-rendering, i.e., estimation of reflectance,illumination, and geometry from images, our key idea is to realize thatreflectance and illumination need not be disentangled and instead estimated asa compound reflectance map. We introduce a novel deep reflectance mapestimation network that recovers the camera-view reflectance maps from thesurface normals of the current geometry estimate and the input multi-viewimages. The network also explicitly estimates per-pixel confidence scores tohandle global light transport effects. A deep shape-from-shading network thenupdates the geometry estimate expressed with a signed distance function usingthe recovered reflectance maps. By alternating between these two, and, mostimportant, by bypassing the ill-posed problem of reflectance and illuminationdecomposition, the method accurately recovers object geometry in thesechallenging settings. Extensive experiments on both synthetic and real-worlddata clearly demonstrate its state-of-the-art accuracy.

DeepShaRM: Multi-View Shape and Reflectance Map Recovery Under Unknown Lighting