论文标题
室内和室外场景解析的密集材料分割数据集
A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing
论文作者
论文摘要
理解世界的关键算法是物质分段，该算法将标签（金属，玻璃等）分配给每个像素。我们发现，在某些情况下，对现有数据的训练不佳的模型，并建议通过在44,560个室内和室外图像上使用320万个密度段的大型数据集来解决此问题，该图像比现有数据多23倍。我们的数据涵盖了更多样化的场景，对象，观点和材料，并包含皮肤类型的更公平的分布。我们表明，经过数据训练的模型优于数据集和观点的最先进模型。我们提出了一个大型场景解析基准和基线为0.729的每金精度，0.585平均班级准确度和46个材料的平均值为0.420。
A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel. We find that a model trained on existing data underperforms in some settings and propose to address this with a large-scale dataset of 3.2 million dense segments on 44,560 indoor and outdoor images, which is 23x more segments than existing data. Our data covers a more diverse set of scenes, objects, viewpoints and materials, and contains a more fair distribution of skin types. We show that a model trained on our data outperforms a state-of-the-art model across datasets and viewpoints. We propose a large-scale scene parsing benchmark and baseline of 0.729 per-pixel accuracy, 0.585 mean class accuracy and 0.420 mean IoU across 46 materials.
