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

Objects play a crucial role in our everyday activities. Though multisensoryobject-centric learning has shown great potential lately, the modeling ofobjects in prior work is rather unrealistic. ObjectFolder 1.0 is a recentdataset that introduces 100 virtualized objects with visual, acoustic, andtactile sensory data. However, the dataset is small in scale and themultisensory data is of limited quality, hampering generalization to real-worldscenarios. We present ObjectFolder 2.0, a large-scale, multisensory dataset ofcommon household objects in the form of implicit neural representations thatsignificantly enhances ObjectFolder 1.0 in three aspects. First, our dataset is10 times larger in the amount of objects and orders of magnitude faster inrendering time. Second, we significantly improve the multisensory renderingquality for all three modalities. Third, we show that models learned fromvirtual objects in our dataset successfully transfer to their real-worldcounterparts in three challenging tasks: object scale estimation, contactlocalization, and shape reconstruction. ObjectFolder 2.0 offers a new path andtestbed for multisensory learning in computer vision and robotics. The datasetis available at https://github.com/rhgao/ObjectFolder.

ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer