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

Humans rely on their visual and tactile senses to develop a comprehensive 3Dunderstanding of their physical environment. Recently, there has been a growinginterest in exploring and manipulating objects using data-driven approachesthat utilise high-resolution vision-based tactile sensors. However, 3D shapereconstruction using tactile sensing has lagged behind visual shapereconstruction because of limitations in existing techniques, including theinability to generalise over unseen shapes, the absence of real-world testing,and limited expressive capacity imposed by discrete representations. To addressthese challenges, we propose TouchSDF, a Deep Learning approach for tactile 3Dshape reconstruction that leverages the rich information provided by avision-based tactile sensor and the expressivity of the implicit neuralrepresentation DeepSDF. Our technique consists of two components: (1) aConvolutional Neural Network that maps tactile images into local meshesrepresenting the surface at the touch location, and (2) an implicit neuralfunction that predicts a signed distance function to extract the desired 3Dshape. This combination allows TouchSDF to reconstruct smooth and continuous 3Dshapes from tactile inputs in simulation and real-world settings, opening upresearch avenues for robust 3D-aware representations and improved multimodalperception in robotics. Code and supplementary material are available at:https://touchsdf.github.io/

TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction using Vision-Based Tactile Sensing