MatSim Dataset and benchmark for one-shot visual materials and textures recognition

Manuel S. Drehwald, Sagi Eppel, Jolina Li, Han Hao, Alan Aspuru-GuzikZenodo 2022 · DOI · OpenAlex

Abstract

The MatSim Dataset and benchmark Synthetic dataset and real images benchmark for visual similarity recognition of materials and textures. MatSim: a synthetic dataset, a benchmark, and a method for computer vision-based recognition of similarities and transitions between materials and textures focusing on identifying any material under any conditions using one or a few examples (one-shot learning). Based on the paper: One-shot recognition of any material anywhere using contrastive learning with physics-based rendering Benchmark_MATSIM.zip: contain the benchmark made of real-world images as described in the paper Dataset Generation Scripts.zip: Contain the Blender (4.1) Python scripts used for generating the datasetMatSim_object_train_split_1,2,3....zip: Contain a subset of the synthetics dataset for images of CGI images materials on random objects as described in the paper. MatSimTrainObjectsNearField_.zip Contain train sets with near fieldlight sources MatSim_Vessels_Train_1,2,3....zip : Contain a subset of the synthetics dataset for images of CGI images materials inside transparent containers as described in the paper.*Note: these are subsets of the dataset; the full dataset can be found at:https://e1.pcloud.link/publink/show?code=kZIiSQZCYU5M4HOvnQykql9jxF4h0KiC5MX orhttps://icedrive.net/s/A13FWzZ8V2aP9T4ufGQ1N3fBZxDF
BibTeX
@inproceedings{drehwald2022matsim,
  author = {Manuel S. Drehwald and Sagi Eppel and Jolina Li and Han Hao and Alan Aspuru-Guzik},
  title = {{MatSim Dataset and benchmark for one-shot visual materials and textures recognition}},
  booktitle = {Zenodo},
  year = {2022},
  doi = {10.5281/zenodo.7390165},
}

Loading related content...

Figure