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 have witnessed significant progress in deep learning-based 3D vision,ranging from neural radiance field (NeRF) based 3D representation learning toapplications in novel view synthesis (NVS). However, existing scene-leveldatasets for deep learning-based 3D vision, limited to either syntheticenvironments or a narrow selection of real-world scenes, are quiteinsufficient. This insufficiency not only hinders a comprehensive benchmark ofexisting methods but also caps what could be explored in deep learning-based 3Danalysis. To address this critical gap, we present DL3DV-10K, a large-scalescene dataset, featuring 51.2 million frames from 10,510 videos captured from65 types of point-of-interest (POI) locations, covering both bounded andunbounded scenes, with different levels of reflection, transparency, andlighting. We conducted a comprehensive benchmark of recent NVS methods onDL3DV-10K, which revealed valuable insights for future research in NVS. Inaddition, we have obtained encouraging results in a pilot study to learngeneralizable NeRF from DL3DV-10K, which manifests the necessity of alarge-scale scene-level dataset to forge a path toward a foundation model forlearning 3D representation. Our DL3DV-10K dataset, benchmark results, andmodels will be publicly accessible at https://dl3dv-10k.github.io/DL3DV-10K/.

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision