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

In this paper, we consider the problem of reconstructing a dense 3D modelusing images captured from different views. Recent methods based onconvolutional neural networks (CNN) allow learning the entire task from data.However, they do not incorporate the physics of image formation such asperspective geometry and occlusion. Instead, classical approaches based onMarkov Random Fields (MRF) with ray-potentials explicitly model these physicalprocesses, but they cannot cope with large surface appearance variations acrossdifferent viewpoints. In this paper, we propose RayNet, which combines thestrengths of both frameworks. RayNet integrates a CNN that learnsview-invariant feature representations with an MRF that explicitly encodes thephysics of perspective projection and occlusion. We train RayNet end-to-endusing empirical risk minimization. We thoroughly evaluate our approach onchallenging real-world datasets and demonstrate its benefits over a piece-wisetrained baseline, hand-crafted models as well as other learning-basedapproaches.

RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials