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 EvDNeRF, a pipeline for generating event data and training anevent-based dynamic NeRF, for the purpose of faithfully reconstructingeventstreams on scenes with rigid and non-rigid deformations that may be toofast to capture with a standard camera. Event cameras register asynchronousper-pixel brightness changes at MHz rates with high dynamic range, making themideal for observing fast motion with almost no motion blur. Neural radiancefields (NeRFs) offer visual-quality geometric-based learnable rendering, butprior work with events has only considered reconstruction of static scenes. OurEvDNeRF can predict eventstreams of dynamic scenes from a static or movingviewpoint between any desired timestamps, thereby allowing it to be used as anevent-based simulator for a given scene. We show that by training on variedbatch sizes of events, we can improve test-time predictions of events at finetime resolutions, outperforming baselines that pair standard dynamic NeRFs withevent generators. We release our simulated and real datasets, as well as codefor multi-view event-based data generation and the training and evaluation ofEvDNeRF models (https://github.com/anish-bhattacharya/EvDNeRF).

EvDNeRF: Reconstructing Event Data with Dynamic Neural Radiance Fields