RGBD20K: new RGB-D segmentation benchmark with 20K image pairs and 160 categories

UNT · hf · 2026-09-26

UNT released RGBD20K, a new benchmark for RGB-D semantic segmentation: 160 fine-grained categories (vs NYUv2's 40, SUN RGB-D's 37), 20,000 RGB-D image pairs, and rigorously re-annotated ground truth fixing long-standing label noise. The accompanying score-purified fusion (SPF) method achieves SOTA across all evaluated benchmarks. Dataset available on GitHub (ShaohuaDong2021/RGBD20K).

Original post →

More from Research

Research channel →