Material-Based Segmentation of Objects

Jonathan Dyssel Stets, Rasmus Ahrenkiel Lyngby*, Jeppe Revall Frisvad, Anders Bjorholm Dahl

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

168 Downloads (Pure)


We present a data-driven proof of concept method for image-based semantic segmentation of objects based on their materials. We target materials with complex radiometric appearances, such as reflective and refractive materials, as their detection is particularly challenging in many modern vision systems. Specifically, we select glass, chrome, plastic, and ceramics as these often appear in real-world settings. A large dataset of synthetic images is generated with the Blender 3D creation suite and the Cycles renderer. We use this data to fine-tune the pre-trained DeepLabv3+ semantic segmentation convolutional neural network. The network performs well on rendered test data and, although trained with rendered images only, the network generalizes so that the four selected materials can be segmented from real photos.
Original languageEnglish
Title of host publicationScandinavian Conference on Image Analysis
Publication date2019
ISBN (Print)978-3-030-20204-0
Publication statusPublished - 2019
EventScandinavian Conference on Image Analysis - Norrköpings Visualisering Center, Norrköping, Sweden
Duration: 11 Jun 201913 Jun 2019


ConferenceScandinavian Conference on Image Analysis
LocationNorrköpings Visualisering Center
Internet address
SeriesLecture Notes in Computer Science


  • Semantic segmentation
  • Deep learning
  • Synthetic data

Fingerprint Dive into the research topics of 'Material-Based Segmentation of Objects'. Together they form a unique fingerprint.

Cite this