ClevrTex
Introduced by Karazija et al. in ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation
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.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
ClevrTex
|
AST-Seg-B3-CT
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
