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

We present a novel method, called NeTO, for capturing 3D geometry of solidtransparent objects from 2D images via volume rendering. Reconstructingtransparent objects is a very challenging task, which is ill-suited forgeneral-purpose reconstruction techniques due to the specular light transportphenomena. Although existing refraction-tracing based methods, designedspecially for this task, achieve impressive results, they still suffer fromunstable optimization and loss of fine details, since the explicit surfacerepresentation they adopted is difficult to be optimized, and theself-occlusion problem is ignored for refraction-tracing. In this paper, wepropose to leverage implicit Signed Distance Function (SDF) as surfacerepresentation, and optimize the SDF field via volume rendering with aself-occlusion aware refractive ray tracing. The implicit representationenables our method to be capable of reconstructing high-quality reconstructioneven with a limited set of images, and the self-occlusion aware strategy makesit possible for our method to accurately reconstruct the self-occluded regions.Experiments show that our method achieves faithful reconstruction results andoutperforms prior works by a large margin. Visit our project page athttps://www.xxlong.site/NeTO/

NeTO:Neural Reconstruction of Transparent Objects with Self-Occlusion Aware Refraction-Tracing