提出新方法实现旋转不变的3D形状补全，无需预知姿态。
ESCAPE: Equivariant Shape Completion via Anchor Point Encoding
- 用锚点到各点的距离编码形状，实现旋转等变性。
- 在任意旋转下重建精度显著优于现有方法。
- 适合需要鲁棒3D补全的工业扫描场景。
3D形状补全是计算机视觉中的关键任务，旨在预测并填补扫描或部分观测物体的缺失区域。现有方法通常依赖已知姿态或规范坐标系，在不同旋转下表现不佳，限制了实际应用。本文提出ESCAPE（Equivariant Shape Completion via Anchor Point Encoding），一种实现旋转等变形状补全的新框架。该方法通过从形状中选取锚点，并将所有点表示为到各个锚点的距离，从而建立对物体几何的一致性、旋转等变理解。ESCAPE采用Transformer架构编码和解码这些距离变换，确保生成的补全结果在旋转变换下保持准确。随后通过优化计算预测形状。实验表明，ESCAPE在任意旋转和位移条件下均能实现鲁棒且高质量的重建，无需额外的姿态估计模块，展现出在真实场景中的有效性。
原文摘要 · Abstract (English)
Shape completion, a crucial task in 3D computer vision, involves predicting and filling the missing regions of scanned or partially observed objects. Current methods expect known pose or canonical coordinates and do not perform well under varying rotations, limiting their real-world applicability. We introduce ESCAPE (Equivariant Shape Completion via Anchor Point Encoding), a novel framework designed to achieve rotation-equivariant shape completion. Our approach employs a distinctive encoding strategy by selecting anchor points from a shape and representing all points as a distance to all anchor points. This enables the model to capture a consistent, rotation-equivariant understanding of the object's geometry. ESCAPE leverages a transformer architecture to encode and decode the distance transformations, ensuring that generated shape completions remain accurate and equivariant under rotational transformations. Subsequently, we perform optimization to calculate the predicted shapes from the encodings. Experimental evaluations demonstrate that ESCAPE achieves robust, high-quality reconstructions across arbitrary rotations and translations, showcasing its effectiveness in real-world applications without additional pose estimation modules.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。