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

Neural Radiance Fields (NeRF) has achieved impressive results in singleobject scene reconstruction and novel view synthesis, which have beendemonstrated on many single modality and single object focused indoor scenedatasets like DTU, BMVS, and NeRF Synthetic.However, the study of NeRF onlarge-scale outdoor scene reconstruction is still limited, as there is nounified outdoor scene dataset for large-scale NeRF evaluation due to expensivedata acquisition and calibration costs. In this paper, we propose a large-scaleoutdoor multi-modal dataset, OMMO dataset, containing complex land objects andscenes with calibrated images, point clouds and prompt annotations. Meanwhile,a new benchmark for several outdoor NeRF-based tasks is established, such asnovel view synthesis, surface reconstruction, and multi-modal NeRF. To createthe dataset, we capture and collect a large number of real fly-view videos andselect high-quality and high-resolution clips from them. Then we design aquality review module to refine images, remove low-quality frames andfail-to-calibrate scenes through a learning-based automatic evaluation plusmanual review. Finally, a number of volunteers are employed to add the textdescriptions for each scene and key-frame to meet the potential multi-modalrequirements in the future. Compared with existing NeRF datasets, our datasetcontains abundant real-world urban and natural scenes with various scales,camera trajectories, and lighting conditions. Experiments show that our datasetcan benchmark most state-of-the-art NeRF methods on different tasks. We willrelease the dataset and model weights very soon.

A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction