ClevrTex

Dataset Information
Modalities
Images
Introduced
2021
License
CC-BY
Homepage
Official Website
Contents

Overview

ClevrTex is a new benchmark designed as the next challenge to compare, evaluate and analyze algorithms for unsupervised multi-object segmentation. ClevrTex features synthetic scenes with diverse shapes, textures and photo-mapped materials, created using physically based rendering techniques.

Image source: Karazija et al.

Variants: ClevrTex

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Unsupervised Object Segmentation AST-Seg-B3-CT Unsupervised Multi-object Segmentation Using Attention … 2022-05-26
Unsupervised Object Segmentation AST Unsupervised Multi-object Segmentation Using Attention … 2022-05-26
Unsupervised Object Segmentation GNM ClevrTex: A Texture-Rich Benchmark for … 2021-11-19
Unsupervised Object Segmentation DTI ClevrTex: A Texture-Rich Benchmark for … 2021-11-19
Unsupervised Object Segmentation eMORL ClevrTex: A Texture-Rich Benchmark for … 2021-11-19
Unsupervised Object Segmentation IODINE ClevrTex: A Texture-Rich Benchmark for … 2021-11-19
Unsupervised Object Segmentation SA ClevrTex: A Texture-Rich Benchmark for … 2021-11-19
Unsupervised Object Segmentation MONet ClevrTex: A Texture-Rich Benchmark for … 2021-11-19
Unsupervised Object Segmentation MN ClevrTex: A Texture-Rich Benchmark for … 2021-11-19
Unsupervised Object Segmentation SPACE ClevrTex: A Texture-Rich Benchmark for … 2021-11-19
Unsupervised Object Segmentation GenV2 ClevrTex: A Texture-Rich Benchmark for … 2021-11-19
Unsupervised Object Segmentation SPAIR ClevrTex: A Texture-Rich Benchmark for … 2021-11-19

Research Papers

Recent papers with results on this dataset:

External Links: