| title | RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation |
|---|---|
| authors | Shaohua Dong, Zexuan Meng, Haiyan Sun, Bing Fan, Cuicui Zhang, Dylan Joseph, Kewei Sha, Yunhe Feng, Heng Fan |
| date | 2026-09-24 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.29028 |
| affiliation | University of North Texas |
| upvotes | 12 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | In this paper, we propose RGBD20K, a novel dataset for facilitating the development of more robust and general RGB-D semantic segmentation by encompassing abundant categories and high-quality annotations. RGBD20K possesses several attractive properties: (1) Expanded Semantic Space. In particular, it covers 160 fine-grained categories, largely surpassing the category diversity of existing popular RGB-D benchmarks (e.g., NYUv2 with 40 classes and SUN RGB-D with 37 classes). With such enriched semantic coverage, we expect to promote the learning of more generalizable segmentation models. (2) Larger Scale. Compared with current benchmarks, RGBD20K offers 20,000 RGB-D image pairs, providing a substantially larger training resource that benefits the development of more powerful deep models. (3) High-Fidelity Annotation. We perform rigorous re-evaluation and correction of existing labels to resolve long-standing annotation noise, resulting in a clean and reliable ground-truth foundation. Furthermore, we propose a novel score-purified fusion (SPF) method, which achieves state-of-the-art performance across all evaluated benchmarks, demonstrating the effectiveness of our approach in leveraging high-quality multimodal information for RGB-D semantic segmentation. The dataset is here: https://github.com/ShaohuaDong2021/RGBD20K/. |
cite
@misc{dong2026rgbd,
title={RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation},
author={Shaohua Dong and Zexuan Meng and Haiyan Sun and Bing Fan and Cuicui Zhang and Dylan Joseph and Kewei Sha and Yunhe Feng and Heng Fan},
year={2026},
eprint={2609.29028},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.29028}
}