发表机构
University of North Texas（北德克萨斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出RGBD20K大规模RGB-D语义分割基准，含160类、2万对图像及高保真标注，并引入SPF融合方法，在多个基准上达到最先进性能。
AI 中文摘要
在本文中，我们提出了RGBD20K，这是一个新颖的数据集，通过涵盖丰富的类别和高精度的标注，促进更鲁棒和通用的RGB-D语义分割的发展。RGBD20K具有几个吸引人的特性：（1）扩展的语义空间。具体而言，它涵盖了160个细粒度类别，大大超过了现有流行RGB-D基准（例如，具有40个类别的NYUv2和具有37个类别的SUN RGB-D）的类别多样性。凭借如此丰富的语义覆盖，我们期望促进更可泛化的分割模型的学习。（2）更大规模。与当前基准相比，RGBD20K提供了20,000对RGB-D图像，提供了更大的训练资源，有利于开发更强大的深度模型。（3）高保真标注。我们对现有标签进行了严格的重新评估和修正，以解决长期存在的标注噪声，从而形成干净可靠的真实基础。此外，我们提出了一种新颖的分数净化融合（SPF）方法，在所有评估基准上均取得了最先进的性能，证明了我们方法在利用高质量多模态信息进行RGB-D语义分割方面的有效性。数据集位于：此https URL。
英文摘要
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/.
