PulseAugur
实时 21:11:05
English(EN) SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment

SUFLECA 框架提高了零样本 CAD 到图像对齐的准确性

研究人员推出 SUFLECA,一个旨在改进零样本 CAD 到图像对齐的弱监督框架。该方法利用大规模真实和合成图像数据集上的归一化对象坐标 (NOCs) 监督,增强了基于几何的特征学习。SUFLECA 的几何一致性匹配算法建立了可靠的对应关系,无需迭代优化即可实现准确快速的对齐,并在 ScanNet25k 基准测试中展现出卓越的性能。 AI

影响 这项研究通过实现更准确高效的图像对象姿态估计,有望改进机器人和增强现实应用。

排序理由 该集群包含详细介绍新对象姿态估计方法的学术论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

SUFLECA 框架提高了零样本 CAD 到图像对齐的准确性

报道来源 [3]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    SUFLECA:扩大CAD到图像对齐的特征学习规模

    CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, enabling applications in robotics and augmented reality. Recent zero-shot methods use visual foundation models to match image regions to CAD models,…

  2. arXiv cs.CV TIER_1 English(EN) · Saad Ejaz, Miguel Fernandez-Cortizas, Javier Civera, Holger Voos, Jose Luis Sanchez-Lopez ·

    SUFLECA:扩大CAD到图像对齐的特征学习规模

    arXiv:2607.15058v1 Announce Type: new Abstract: CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, enabling applications in robotics and augmented reality. Recent zero-shot methods use visual foundat…

  3. arXiv cs.CV TIER_1 English(EN) · Jose Luis Sanchez-Lopez ·

    SUFLECA:扩大CAD到图像对齐的特征学习规模

    CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, enabling applications in robotics and augmented reality. Recent zero-shot methods use visual foundation models to match image regions to CAD models,…