arXiv 2606.219382026-09-11cs.CV

Artic-O: 通过潜在几何学习实现端到端的铰接物体重建

Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry Learning

Australian National University（澳大利亚国立大学）；KAUST（阿卜杜拉国王科技大学）

Xuyang Wang, Zhenyu Li, Jian Ding, Habib Slim, Peter Wonka, Hongdong Li, Mohamed Elhoseiny

备注：: Accepted to SIGGRAPH Asia 2026 Conference Papers. Project page/code: https://github.com/Wxyxixixi/Artic-O

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出Artic-O，一种端到端的前馈框架，通过潜在几何学习从稀疏图像重建铰接物体，联合恢复完整几何、活动部件和运动参数，在PartNet-Mobility上达到高质量重建并大幅提升效率。

摘要：

从稀疏图像重建铰接物体需要恢复完整几何、可动部件和运动参数。现有方法通常将几何重建、部件推理和铰接估计分为不同阶段，这种分离会削弱形状、活动部件和运动之间的一致性，同时产生大量推理成本。我们提出Artic-O，一种通过潜在几何学习实现端到端前馈铰接物体重建的框架。Artic-O不直接在图像或视图空间中拟合几何，而是将稀疏多状态观测映射到预训练的潜在几何空间，其中冻结的流匹配解码器提供完整形状先验以恢复可见和遮挡结构。为了连接几何与铰接，Artic-O在基于图像的部分推理模块中融合视觉标记、几何潜在和逐点解码器特征，用于活动部件分割和铰接预测。我们进一步通过几何到铰接课程学习和解耦的两遍策略训练模型，以平衡重建和部件级监督。在PartNet-Mobility上，Artic-O在实现强重建质量的同时，比强基线方法LARM更高效。它降低了倒角距离，提高了F分数，并在大多数关节指标上达到相当或更好的铰接精度，同时将推理时间从每个物体9分钟减少到约0.3秒。

英文摘要：

Reconstructing articulated objects from sparse images requires recovering complete geometry, movable parts, and motion parameters. Recent methods typically separate geometry reconstruction, part reasoning, and articulation estimation into different stages. This separation can weaken consistency between shape, active parts, and motion, while also incurring substantial inference cost. We introduce Artic-O, an end-to-end, feed-forward framework for articulated object reconstruction via latent geometry learning. Instead of fitting geometry in image or view space, Artic-O maps sparse multi-state observations into a pretrained latent geometry space, where a frozen flow-matching decoder provides a complete-shape prior for recovering visible and occluded structures. To connect geometry with articulation, Artic-O fuses visual tokens, geometry latents, and point-wise decoder features in an image-grounded part-reasoning module for active-part segmentation and articulation prediction. We further train the model with a geometry-to-articulation curriculum and a decoupled two-pass strategy to balance reconstruction and part-level supervision. On PartNet-Mobility, Artic-O achieves strong reconstruction quality while being substantially more efficient than LARM, a strong prior method. It reduces Chamfer Distance, improves F-score, and achieves comparable or better articulation accuracy across most joint metrics, while reducing inference time from 9 minutes to about 0.3 seconds per object.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。