将动物毛皮图案变形校正到标准空间，提升识别准确率
Unsupervised Pelage Pattern Unwrapping for Animal Re-identification
- 通过表面法向引导，将毛皮图案映射到标准二维空间
- 在海豹和豹子数据集上实现最高5.4%的识别准确率提升
- 无需人工标注，可自监督训练，适合野外动物识别
现有个体重识别方法常因动物皮毛或皮肤图案受身体运动和姿态变化导致几何扭曲而失效。本文提出一种几何感知的纹理映射方法，将动物皮毛上的独特纹路（称为pelage pattern）映射至标准的UV空间，以实现更鲁棒的特征匹配。该方法利用表面法向估计引导展开过程，保持三维表面与二维纹理空间间的几何一致性。研究聚焦于两种挑战性物种：萨伊马环斑海豹（Pusa hispida saimensis）和豹（Panthera pardus），二者均有显著但高度可变形的毛皮图案。通过将本方法与现有重识别技术结合，显著提升了不同姿态和视角下的识别性能。框架无需真实UV标注，支持自监督训练。在海豹与豹子数据集上的实验表明，识别准确率最高提升5.4%。
原文摘要 · Abstract (English)
Existing individual re-identification methods often struggle with the deformable nature of animal fur or skin patterns which undergo geometric distortions due to body movement and posture changes. In this paper, we propose a geometry-aware texture mapping approach that unwarps pelage patterns, the unique markings found on an animal's skin or fur, into a canonical UV space, enabling more robust feature matching. Our method uses surface normal estimation to guide the unwrapping process while preserving the geometric consistency between the 3D surface and the 2D texture space. We focus on two challenging species: Saimaa ringed seals (Pusa hispida saimensis) and leopards (Panthera pardus). Both species have distinctive yet highly deformable fur patterns. By integrating our pattern-preserving UV mapping with existing re-identification techniques, we demonstrate improved accuracy across diverse poses and viewing angles. Our framework does not require ground truth UV annotations and can be trained in a self-supervised manner. Experiments on seal and leopard datasets show up to a 5.4% improvement in re-identification accuracy.
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。