computer-vision-7

Material Recognition

3260 papers • 126 benchmarks • 313 datasets

Material recognition focuses on identifying classes, types, states, and properties of materials.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in material-recognition-14

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find material-recognition-14 models and implementations

Datasets

Subtasks

No subtasks available.

Most implemented papers

Describing Textures in the Wild

A. Vedaldi, Iasonas Kokkinos, Subhransu Maji, Mircea Cimpoi, S. Mohamed•Wed Nov 13 2013

This work identifies a vocabulary of forty-seven texture terms and uses them to describe a large dataset of patterns collected "in the wild", and shows that they both outperform specialized texture descriptors not only on this problem, but also in established material recognition datasets.

3253

Content

MatSeg

DMS

OpenSurfaces

0

Paper Graph

Deep TEN: Texture Encoding Network

Hang Zhang, Kristin J. Dana, Jia Xue•Wed Dec 07 2016

A Deep Texture Encoding Network with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model, providing an end-to-end learning framework.

253 0

Paper Graph

Classification of Household Materials via Spectroscopy

C. Kemp, Zackory Erickson, S. Chernova, Nathan Luskey•Wed May 09 2018

It is found that spectroscopy poses a promising approach for material classification during robotic manipulation, and how a PR2 robot can leverage spectrometers to estimate the materials of everyday objects found in the home is demonstrated.

46 0

Paper Graph

Fast classification of small X-ray diffraction datasets using data augmentation and deep neural networks

Felipe Oviedo, T. Buonassisi, Brian L. DeCost, A. Kusne, Zekun Ren, S. Tian, Shijing Sun, C. Settens, Zhe Liu, N. T. P. Hartono, R. Savitha, Giuseppe Romano•Mon Nov 19 2018

The sparse-data problem intrinsic to novel materials development is overcome by coupling a supervised machine-learning approach with a physics-based data augmentation strategy and, using this approach, XRD spectrum acquisition and analysis occurs under 5 minutes, with accuracy comparable to human expert labeling.

6 0

Paper Graph

A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing

Paul Upchurch, Ransen Niu•Wed Jul 20 2022

It is shown that a model trained on the data outperforms a state-of-the-art model across datasets and viewpoints, and is proposed to address this with a large-scale dataset of 3.2 million dense segments on 44,560 indoor and outdoor images.

31 0

Paper Graph

Semi-Supervised Haptic Material Recognition for Robots using Generative Adversarial Networks

C. Kemp, Zackory Erickson, S. Chernova•Sun Jul 09 2017

This work presents a semi-supervised learning approach for material recognition that uses generative adversarial networks (GANs) with haptic features such as force, temperature, and vibration and explores how well this approach can recognize the material of new objects.

43 0

Paper Graph

Deep Thermal Imaging: Proximate Material Type Recognition in the Wild through Deep Learning of Spatial Surface Temperature Patterns

N. Bianchi-Berthouze, Youngjun Cho, Nicolai Marquardt, S. Julier•Mon Mar 05 2018

Deep Thermal Imaging is introduced, a new approach for close-range automatic recognition of materials to enhance the understanding of people and ubiquitous technologies of their proximal environment using a low-cost mobile thermal camera integrated into a smartphone to capture thermal textures and a deep neural network classifies these textures into material types.

58 0

Paper Graph

Multimodal Material Classification for Robots using Spectroscopy and High Resolution Texture Imaging

C. Kemp, Zackory Erickson, S. Chernova, Eliot Xing, Bharat Srirangam•Wed Apr 01 2020

A multimodal sensing technique, leveraging near-infrared spectroscopy and close-range high resolution texture imaging, that enables robots to estimate the materials of household objects and a neural network architecture that learns a compact multi-modal representation of spectral measurements and texture images is presented.

46 0

Paper Graph

Computer Vision for Recognition of Materials and Vessels in Chemistry Lab Settings and the Vector-LabPics Data Set

Alán Aspuru-Guzik, S. Eppel, HaoPing Xu, Mor Bismuth•Tue Mar 03 2020

This work presents the Vector-LabPics data set, which consists of 2187 images of materials within mostly transparent vessels in a chemistry lab and other general settings, and trained neural networks achieved good accuracy in detecting and segmenting vessels and material phases, and in classifying liquids and solids.

70 0

Paper Graph

Adding a benchmark result helps the community track progress.