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

In this work, we tackle 6-DoF grasp detection for transparent and specularobjects, which is an important yet challenging problem in vision-based roboticsystems, due to the failure of depth cameras in sensing their geometry. We, forthe first time, propose a multiview RGB-based 6-DoF grasp detection network,GraspNeRF, that leverages the generalizable neural radiance field (NeRF) toachieve material-agnostic object grasping in clutter. Compared to the existingNeRF-based 3-DoF grasp detection methods that rely on densely captured inputimages and time-consuming per-scene optimization, our system can performzero-shot NeRF construction with sparse RGB inputs and reliably detect 6-DoFgrasps, both in real-time. The proposed framework jointly learns generalizableNeRF and grasp detection in an end-to-end manner, optimizing the scenerepresentation construction for the grasping. For training data, we generate alarge-scale photorealistic domain-randomized synthetic dataset of grasping incluttered tabletop scenes that enables direct transfer to the real world. Ourextensive experiments in synthetic and real-world environments demonstrate thatour method significantly outperforms all the baselines in all the experimentswhile remaining in real-time. Project page can be found athttps://pku-epic.github.io/GraspNeRF

GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRF