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

Non-line-of-sight reconstruction (NLoS) is a novel indirect imaging modalitythat aims to recover objects or scene parts outside the field of view frommeasurements of light that is indirectly scattered off a directly visible,diffuse wall. Despite recent advances in acquisition and reconstructiontechniques, the well-posedness of the problem at large, and the recoverabilityof objects and their shapes in particular, remains an open question. Thecommonly employed Fermat path criterion is rather conservative with thisregard, as it classifies some surfaces as unrecoverable, although theycontribute to the signal.  In this paper, we use a simpler necessary criterion for an opaque surfacepatch to be recoverable. Such piece of surface must be directly visible fromsome point on the wall, and it must occlude the space behind itself. Inspiredby recent advances in neural implicit representations, we devise a newrepresentation and reconstruction technique for NLoS scenes that unifies thetreatment of recoverability with the reconstruction itself. Our approach, whichwe validate on various synthetic and experimental datasets, exhibitsinteresting properties. Unlike memory-inefficient volumetric representations,ours allows to infer adaptively tessellated surfaces from time-of-flightmeasurements of moderate resolution. It can further recover features beyond theFermat path criterion, and it is robust to significant amounts ofself-occlusion. We believe that this is the first time that these propertieshave been achieved in one system that, as an additional benefit, is trainableand hence suited for data-driven approaches.

Occlusion Fields: An Implicit Representation for Non-Line-of-Sight Surface Reconstruction