Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces

TL;DR

This paper introduces Tactile-Informed 3DGS, a novel method combining touch and vision data to improve surface reconstruction, especially for challenging non-Lambertian objects, achieving higher accuracy with fewer images.

Contribution

It presents a new approach that integrates tactile data into 3D Gaussian splatting, enhancing surface reconstruction for reflective surfaces beyond prior vision-only methods.

Findings

Improved reconstruction quality for glossy and reflective objects.

Achieves accurate geometry with fewer images.

Effectively models non-Lambertian surfaces using tactile data.

Abstract

Touch and vision go hand in hand, mutually enhancing our ability to understand the world. From a research perspective, the problem of mixing touch and vision is underexplored and presents interesting challenges. To this end, we propose Tactile-Informed 3DGS, a novel approach that incorporates touch data (local depth maps) with multi-view vision data to achieve surface reconstruction and novel view synthesis. Our method optimises 3D Gaussian primitives to accurately model the object's geometry at points of contact. By creating a framework that decreases the transmittance at touch locations, we achieve a refined surface reconstruction, ensuring a uniformly smooth depth map. Touch is particularly useful when considering non-Lambertian objects (e.g. shiny or reflective surfaces) since contemporary methods tend to fail to reconstruct with fidelity specular highlights. By combining vision and tactile sensing, we achieve more accurate geometry reconstructions with fewer images than prior methods. We conduct evaluation on objects with glossy and reflective surfaces and demonstrate the effectiveness of our approach, offering significant improvements in reconstruction quality.