The world’s largest dataset for waste, with pioneering research driving innovation in waste sorting technologies

About WasteNet

Our pioneering research has been developed in partnership with academics at leading universities to create WasteNet: the world’s largest dataset for waste. 

It boasts over 3 million training images created by deep learning and computer vision, refined by weight and brand-level detection. 

WasteNet is underpinned by 4 unique pillars: waste image datasets, research papers, our data exploratory tool and waste taxonomy.

Waste Image DatasetsResearch papersVIZ-EDAWaste Taxonomy

Waste Image Datasets

Through Recycleye Vision, we have analysed over 3 million images of waste items in MRFs (and counting!). Collated by our expert team of machine learning engineers and academic research partners, our databases are available for academic and non-commercial purposes.

Request access

Research Papers

Machine Learning


Single Shot 2D Image to 3D Model

This research consists of 2 papers offering differing reconstruction approaches to obtain high accuracy inferences…

Deep Learning: Unsupervised Domain Adaptation

The goal of this WasteNet series is to engineer a Deep Learning model that will…
Logo detection

An Application of Machine Learning for Brand-Level Waste Management

Computer vision for brand-level logo detection of waste in real-time was tested. The brand recognition…
Recycleye Bin: A Human-in-the-Loop Approach to Computer Vision Waste Disposal
Instance Segmentation of Novel Objects in a Conveyer Setting
ai and waste management
A Generative Adversarial Network (GAN) to Generate Transparent Objects
ai and waste management
Synthetic Generation of Augmented 3D Data for Waste Classification

Waste Management Industry


Modelling of a modern MRF

Paloma's paper has a dual focus on two of the challenges faced by MRFs today:…

Decentralised and Digitised Mini Material Recovery Facilities

This research explores the disruption of centralised waste facilities to accommodate a decentralised model, known as the…
recycling regulations

Regulated Bans in Waste Management

Amandine looks at how we can form healthier consumer habits and increased recycling rates by…


We know that datasets are complex and hard to visualise, so we created Viz-EDA: an exploratory data analysis tool that helps to see through the data. It is completely open-source and available for use.

Learn MoreView GitHub

Our Waste Taxonomy

At Recycleye, we’re constructing a global standard for waste classification so that industry players across the world can speak a common language, establishing clarity between markets.

WasteNet Access

Click below if you are a member of an academic institution, and are interested in exploring one of our datasets within your research

Request access