用Transformer实现高效通用的图像旋转估计，一次推理完成。
Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers
- 基于变压器的隐空间对比机制，联合处理查询与多参考图像特征。
- 无需特定物体训练，单次前向传播即可预测旋转角度。
- 适合对延迟敏感的应用，兼具精度与计算效率。
我们提出Eff-GRot，一种从RGB图像中高效且通用地估计旋转的方法。给定一张查询图像和一组已知朝向的参考图像，该方法通过单次前向传播直接预测物体的旋转，无需针对特定物体或类别进行训练。其核心是一个在隐空间中执行比较的Transformer，联合处理来自多个参考图像及查询图像的旋转感知表征。该设计在准确率与计算效率之间取得良好平衡，同时保持结构简单、可扩展且完全端到端。实验表明，Eff-GRot为更高效的旋转估计提供了有前景的方向，尤其适用于对延迟敏感的应用场景。
原文摘要 · Abstract (English)
We introduce Eff-GRot, an approach for efficient and generalizable rotation estimation from RGB images. Given a query image and a set of reference images with known orientations, our method directly predicts the object's rotation in a single forward pass, without requiring object- or category-specific training. At the core of our framework is a transformer that performs a comparison in the latent space, jointly processing rotation-aware representations from multiple references alongside a query. This design enables a favorable balance between accuracy and computational efficiency while remaining simple, scalable, and fully end-to-end. Experimental results show that Eff-GRot offers a promising direction toward more efficient rotation estimation, particularly in latency-sensitive applications.
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。