SUFLECA: 面向CAD到图像对齐的扩展特征学习

摘要

CAD到图像对齐的目标是从单张RGB图像中估计物体的9D姿态（旋转、平移及各向异性缩放），从而支持机器人技术和增强现实等应用。最近的零样本方法利用视觉基础模型将图像区域与CAD模型进行匹配，但这些对应关系通常依赖于外观驱动，在存在遮挡或模拟到现实领域偏移时会退化。为解决这些局限性，我们提出了SUFLECA（缩放特征学习以实现CAD对齐），这是一个用于零样本CAD对齐的弱监督框架，包含两项关键贡献。首先，SUFLECA通过归一化物体坐标（NOCs）监督在涵盖12个真实和合成数据集的674K图像上进行训练，从预训练的视觉表示中扩展了几何基础特征学习，学习出跨领域泛化的紧凑几何感知特征。其次，我们提出了一种几何一致的匹配算法，能够建立可靠的一对一CAD到图像对应关系。这些贡献共同实现了每物体实例亚秒级的精确对齐，无需迭代姿态优化。在ScanNet25k数据集上，SUFLECA在类别/实例准确率上分别达到33.4%/42.3%，以更小的计算开销超越了最强零样本基线10.3/12.2个百分点，并且在该基准测试中首次甚至超过了全监督方法。代码已开源：https://github.com/snt-arg/SUFLECA

English

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, yet typically their correspondences are appearance-driven and degrade under occlusion or sim-to-real domain shift. To address these limitations, we introduce SUFLECA (Scaling Up Feature LEarning for CAD Alignment), a weakly-supervised framework for zero-shot CAD alignment with two key contributions. First, SUFLECA scales up geometry-grounded feature learning from pretrained visual representations through Normalized Object Coordinates (NOCs) supervision on 674K images spanning 12 real and synthetic datasets, learning compact geometry-aware features that generalize across domains. Second, we propose a geometrically consistent matching algorithm that establishes reliable one-to-one CAD-to-image correspondences. Together, these contributions enable accurate, sub-second alignment per object instance without iterative pose refinement. On ScanNet25k, SUFLECA achieves 33.4%/42.3% category/instance accuracy, outperforming, with a smaller computational footprint, the strongest zero-shot baseline by 10.3/12.2 percentage points and, for the first time on this benchmark, even surpassing fully supervised methods. Code is available at: https://github.com/snt-arg/SUFLECA