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

Recent neural view synthesis methods have achieved impressive quality andrealism, surpassing classical pipelines which rely on multi-viewreconstruction. State-of-the-Art methods, such as NeRF, are designed to learn asingle scene with a neural network and require dense multi-view inputs. Testingon a new scene requires re-training from scratch, which takes 2-3 days. In thiswork, we introduce Stereo Radiance Fields (SRF), a neural view synthesisapproach that is trained end-to-end, generalizes to new scenes, and requiresonly sparse views at test time. The core idea is a neural architecture inspiredby classical multi-view stereo methods, which estimates surface points byfinding similar image regions in stereo images. In SRF, we predict color anddensity for each 3D point given an encoding of its stereo correspondence in theinput images. The encoding is implicitly learned by an ensemble of pair-wisesimilarities -- emulating classical stereo. Experiments show that SRF learnsstructure instead of overfitting on a scene. We train on multiple scenes of theDTU dataset and generalize to new ones without re-training, requiring only 10sparse and spread-out views as input. We show that 10-15 minutes of fine-tuningfurther improve the results, achieving significantly sharper, more detailedresults than scene-specific models. The code, model, and videos are availableat https://virtualhumans.mpi-inf.mpg.de/srf/.

Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes