研究人员推出了 Every9D-21M，一个旨在应对从单张图像估计日常物体9D姿态挑战的新数据集。该数据集显著超越了之前的基准，包含来自109,000个以物体为中心的视频的2180万张真实世界图像，涵盖700个物体类别。Every9D-21M 的创建涉及利用多视图几何来重建点云，并将实例对齐到共享的规范坐标系中，手动标注通过跨实例对齐传播并从多个视角进行验证。该数据集旨在作为9D姿态基础模型的基准，并已在 ImageNet3D 和 PASCAL3D+ 等现有数据集上展示了性能改进。 AI
影响 为9D物体姿态估计建立了一个新的、大规模的基准，有可能加速计算机视觉基础模型的研究和开发。
排序理由 该集群描述了一个新的计算机视觉数据集和相关研究论文，专门用于9D物体姿态估计。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Estimating the 9D pose of everyday objects from a single real-world image remains challenging. This is largely due to the lack of large-scale supervision. Most existing datasets either rely heavily on synthetic renderings or provide limited coverage of real-world objects: the lar…
arXiv:2605.28270v1 Announce Type: new Abstract: Estimating the 9D pose of everyday objects from a single real-world image remains challenging. This is largely due to the lack of large-scale supervision. Most existing datasets either rely heavily on synthetic renderings or provide…
Estimating the 9D pose of everyday objects from a single real-world image remains challenging. This is largely due to the lack of large-scale supervision. Most existing datasets either rely heavily on synthetic renderings or provide limited coverage of real-world objects: the lar…