الملخص
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/.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Dong, S., Meng, Z., Sun, H., Fan, B., Zhang, C., Joseph, D., Sha, K., Feng, Y., & Fan, H. (2026). RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation. https://omanscience.com/ar/articles/rgbd20k-a-large-scale-benchmark-for-rgb-d-semantic-segmentation
MLA 9
Dong, Shaohua, et al. "RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation." https://omanscience.com/ar/articles/rgbd20k-a-large-scale-benchmark-for-rgb-d-semantic-segmentation.
شيكاغو (المؤلف–التاريخ)
Dong, Shaohua, Zexuan Meng, Haiyan Sun, Bing Fan, Cuicui Zhang, Dylan Joseph, Kewei Sha, Yunhe Feng, and Heng Fan. 2026. "RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation." https://omanscience.com/ar/articles/rgbd20k-a-large-scale-benchmark-for-rgb-d-semantic-segmentation.
هارفارد
Dong, S., Meng, Z., Sun, H., Fan, B., Zhang, C., Joseph, D., Sha, K., Feng, Y. and Fan, H. (2026) 'RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation', Available at: https://omanscience.com/ar/articles/rgbd20k-a-large-scale-benchmark-for-rgb-d-semantic-segmentation.
فانكوفر
Dong S, Meng Z, Sun H, Fan B, Zhang C, Joseph D, et al. RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation. https://omanscience.com/ar/articles/rgbd20k-a-large-scale-benchmark-for-rgb-d-semantic-segmentation
IEEE
S. Dong, Z. Meng, H. Sun, B. Fan, C. Zhang, D. Joseph, K. Sha, Y. Feng, and H. Fan, "RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation," https://omanscience.com/ar/articles/rgbd20k-a-large-scale-benchmark-for-rgb-d-semantic-segmentation.