RINO：旋转不变的非刚性对应
RINO: Rotation-Invariant Non-Rigid Correspondences
RINONet 把基于向量的 SO(3) 不变特征学习与方向感知的复函数映射结合，直接从原始几何端到端回归稠密对应，可复用于任意姿态、部分数据、非流形网格的匹配与配准任务，省去预对齐和手工描述子。
原文依据 integrates vector-based SO(3)-invariant learning with orientation-aware complex functional maps to extract robust features directly from raw geometry
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论稠密三维形状对应仍是计算机视觉与图形学中的核心难题，因为许多深度学习方法仍依赖中间几何特征或手工设计的描述子，在非等距形变、部分数据和非流形输入下效果受限。为解决这些问题，我们提出 RINO，一个无监督、旋转不变的稠密对应框架，有效统一了刚性形状匹配与非刚性形状匹配。方法的核心是新颖的 RINONet，一种特征提取器，它将基于向量的 SO(3) 不变学习与方向感知的复函数映射相结合，直接从原始几何中提取鲁棒特征。这使得完全端到端、数据驱动的方法成为可能，无需形状预对齐或手工特征。大量实验表明，RINO 在具有挑战性的非刚性匹配任务上取得了前所未有的性能，包括任意姿态、非等距形变、部分性、非流形性和噪声。
英文原文摘要 1009 字符
Dense 3D shape correspondence remains a central challenge in computer vision and graphics as many deep learning approaches still rely on intermediate geometric features or handcrafted descriptors, limiting their effectiveness under non-isometric deformations, partial data, and non-manifold inputs. To overcome these issues, we introduce RINO, an unsupervised, rotation-invariant dense correspondence framework that effectively unifies rigid and non-rigid shape matching. The core of our method is the novel RINONet, a feature extractor that integrates vector-based SO(3)-invariant learning with orientation-aware complex functional maps to extract robust features directly from raw geometry. This allows for a fully end-to-end, data-driven approach that bypasses the need for shape pre-alignment or handcrafted features. Extensive experiments show unprecedented performance of RINO across challenging non-rigid matching tasks, including arbitrary poses, non-isometry, partiality, non-manifoldness, and noise.