构建可保持几何变换一致性的潜在空间，提升手部姿态估计精度
Learning Transformation-Isomorphic Latent Space for Accurate Hand Pose Estimation
- 在潜在空间中用线性变换模拟图像中的几何变化
- 在DexYCB数据集上比最优方法减少10%的误差
- 适合需要高精度低层特征的视觉回归任务
基于视觉的回归任务如手部姿态估计，通过表征学习已实现更高精度和更快收敛。然而现有表征学习方法存在两个问题：从图像提取的特征语义层次过高，难以回归低层信息；且特征包含与任务无关的内容，降低紧凑性并干扰回归。为此，我们提出TI-Net，一种通用性强的视觉网络主干，用于构建变换同构的潜在空间。具体地，我们在潜在空间中使用线性变换建模几何变换，并确保其与图像空间中的变换对齐。这使得潜在特征能捕捉紧凑、有益于姿态估计的低层信息。我们在手部姿态估计任务上评估了TI-Net的性能。在DexYCB数据集上，相较于专用的最先进方法，TI-Net在PA-MPJPE指标上提升了10%。代码将于后续发布。
原文摘要 · Abstract (English)
Vision-based regression tasks, such as hand pose estimation, have achieved higher accuracy and faster convergence through representation learning. However, existing representation learning methods often encounter the following issues: the high semantic level of features extracted from images is inadequate for regressing low-level information, and the extracted features include task-irrelevant information, reducing their compactness and interfering with regression tasks. To address these challenges, we propose TI-Net, a highly versatile visual Network backbone designed to construct a Transformation Isomorphic latent space. Specifically, we employ linear transformations to model geometric transformations in the latent space and ensure that {\rm TI-Net} aligns them with those in the image space. This ensures that the latent features capture compact, low-level information beneficial for pose estimation tasks. We evaluated TI-Net on the hand pose estimation task to demonstrate the network's superiority. On the DexYCB dataset, TI-Net achieved a 10% improvement in the PA-MPJPE metric compared to specialized state-of-the-art (SOTA) hand pose estimation methods. Our code will be released in the future.
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。