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 MVSNeRF, a novel neural rendering approach that can efficientlyreconstruct neural radiance fields for view synthesis. Unlike prior works onneural radiance fields that consider per-scene optimization on densely capturedimages, we propose a generic deep neural network that can reconstruct radiancefields from only three nearby input views via fast network inference. Ourapproach leverages plane-swept cost volumes (widely used in multi-view stereo)for geometry-aware scene reasoning, and combines this with physically basedvolume rendering for neural radiance field reconstruction. We train our networkon real objects in the DTU dataset, and test it on three different datasets toevaluate its effectiveness and generalizability. Our approach can generalizeacross scenes (even indoor scenes, completely different from our trainingscenes of objects) and generate realistic view synthesis results using onlythree input images, significantly outperforming concurrent works ongeneralizable radiance field reconstruction. Moreover, if dense images arecaptured, our estimated radiance field representation can be easily fine-tuned;this leads to fast per-scene reconstruction with higher rendering quality andsubstantially less optimization time than NeRF.

MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo