NLiPsCalib: An Efficient Calibration Framework for High-Fidelity 3D Reconstruction of Curved Visuotactile Sensors

2026-03-10

AI Summary

This work addresses the challenges posed by non-uniform illumination in curved visual tactile sensors and the high cost and complexity of existing calibration methods, which rely on custom indenters and specialized equipment. The authors propose an efficient calibration framework leveraging a controllable near-field light source, uniquely integrating near-light photometric stereo (NLiPs) with physically consistent modeling. This approach enables accurate calibration using only a small number of contacts with everyday objects, eliminating the need for dedicated hardware. The method substantially simplifies the calibration process while achieving high-fidelity 3D reconstruction across diverse curved tactile sensors, thereby lowering development barriers and enhancing the accessibility and practicality of visual tactile sensing.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Recent advances in visuotactile sensors increasingly employ biomimetic curved surfaces to enhance sensorimotor capabilities. Although such curved visuotactile sensors enable more conformal object contact, their perceptual quality is often degraded by non-uniform illumination, which reduces reconstruction accuracy and typically necessitates calibration. Existing calibration methods commonly rely on customized indenters and specialized devices to collect large-scale photometric data, but these processes are expensive and labor-intensive. To overcome these calibration challenges, we present NLiPsCalib, a physics-consistent and efficient calibration framework for curved visuotactile sensors. NLiPsCalib integrates controllable near-field light sources and leverages Near-Light Photometric Stereo (NLiPs) to estimate contact geometry, simplifying calibration to just a few simple contacts with everyday objects. We further introduce NLiPsTac, a controllable-light-source tactile sensor developed to validate our framework. Experimental results demonstrate that our approach enables high-fidelity 3D reconstruction across diverse curved form factors with a simple calibration procedure. We emphasize that our approach lowers the barrier to developing customized visuotactile sensors of diverse geometries, thereby making visuotactile sensing more accessible to the broader community.

Problem

• visuotactile sensors
• calibration
• non-uniform illumination
• 3D reconstruction
• curved surfaces

Innovation

• Near-Light Photometric Stereo
• visuotactile sensor
• curved surface calibration
• 3D reconstruction
• controllable light source