Next Article in Journal
Ultrasonic Testing of Laser Welds in Medium-Thick Titanium Alloy Plates
Next Article in Special Issue
A Complete Grocery Pick-and-Pack Application Using a Computationally Lightweight Vision-Based Mobile Manipulator
Previous Article in Journal
A Compact SLED Light Source Driver Module for Optical Coherence Tomography Applications
Previous Article in Special Issue
Multimodal Shared Autonomy for Heavy-Load UAV Operations with Physics-Aware Cooperative Control
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sensors
Volume 26
Issue 7
10.3390/s26072083
sensors-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

One Patch Is All You Need: Joint Surface Material Reconstruction and Classification from Minimal Visual Cues

by
Sindhuja Penchala
*,
Gavin Money
,
Gabriel Marques
,
Samuel Wood
,
Jessica Kirschman
,
Travis Atkison
,
Shahram Rahimi
and
Noorbakhsh Amiri Golilarz
Department of Computer Science, The University of Alabama, Tuscaloosa, AL 35487, USA
*
Author to whom correspondence should be addressed.
Sensors 2026, 26(7), 2083; https://doi.org/10.3390/s26072083
Submission received: 26 February 2026 / Revised: 24 March 2026 / Accepted: 24 March 2026 / Published: 27 March 2026
(This article belongs to the Special Issue Advanced Sensors and AI Integration for Human–Robot Teaming)
Browse Figures
Review Reports Versions Notes

Abstract

Understanding material surfaces from sparse visual cues is critical for applications in robotics, simulation and material perception. However, most existing methods rely on dense or full scene observations, limiting their effectiveness in constrained or partial view environments. This gap highlights the need for models capable of inferring surfaces’ properties from extremely limited visual information. To address this challenge, we introduce SMARC, a unified model for Surface MAterial Reconstruction and Classification from minimal visual input. By giving only a single 10% contiguous patch of the image, SMARC recognizes and reconstructs the full RGB surface while simultaneously classifying the material category. Our architecture combines a Partial Convolutional U-Net with a classification head, enabling both spatial inpainting and semantic understanding under extreme observation sparsity. We compared SMARC against five models including convolutional autoencoders, Vision Transformer (ViT), Masked Autoencoder (MAE), Swin Transformer and DETR using the Touch and Go dataset of real-world surface textures. SMARC achieves the highest performance among the evaluated methods with a PSNR of 17.55 dB and a surface classification accuracy of 85.10%. These results validate the effectiveness of SMARC in relation to surface material understanding and highlight its potential for deployment in robotic perception tasks where visual access is inherently limited.
Keywords: material reconstruction; minimal visual input; partial convolution; robotic perception; surface classification material reconstruction; minimal visual input; partial convolution; robotic perception; surface classification

Share and Cite

MDPI and ACS Style

Penchala, S.; Money, G.; Marques, G.; Wood, S.; Kirschman, J.; Atkison, T.; Rahimi, S.; Amiri Golilarz, N. One Patch Is All You Need: Joint Surface Material Reconstruction and Classification from Minimal Visual Cues. Sensors 2026, 26, 2083. https://doi.org/10.3390/s26072083

AMA Style

Penchala S, Money G, Marques G, Wood S, Kirschman J, Atkison T, Rahimi S, Amiri Golilarz N. One Patch Is All You Need: Joint Surface Material Reconstruction and Classification from Minimal Visual Cues. Sensors. 2026; 26(7):2083. https://doi.org/10.3390/s26072083

Chicago/Turabian Style

Penchala, Sindhuja, Gavin Money, Gabriel Marques, Samuel Wood, Jessica Kirschman, Travis Atkison, Shahram Rahimi, and Noorbakhsh Amiri Golilarz. 2026. "One Patch Is All You Need: Joint Surface Material Reconstruction and Classification from Minimal Visual Cues" Sensors 26, no. 7: 2083. https://doi.org/10.3390/s26072083

APA Style

Penchala, S., Money, G., Marques, G., Wood, S., Kirschman, J., Atkison, T., Rahimi, S., & Amiri Golilarz, N. (2026). One Patch Is All You Need: Joint Surface Material Reconstruction and Classification from Minimal Visual Cues. Sensors, 26(7), 2083. https://doi.org/10.3390/s26072083

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop