通过预测物体前后表面坐标，构建超密集2D-3D对应关系提升姿态估计精度。
HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation
- 同时预测物体前表面与后表面坐标，中间稠密采样形成超密集对应
- 在7个BOP核心数据集上超越现有最先进方法，显著提升姿态估计准确率
- 适用于需要高精度姿态估计的工业检测与机器人抓取场景
在已知物体姿态估计中，主流方法利用神经网络预测物体表面在2D图像上的密集3D坐标，进而建立密集的2D-3D对应关系。然而，现有方法主要关注提升前表面3D坐标预测精度的编码效率，忽略了后表面和内部结构的潜在价值。为此，本文提出同时预测物体前表面与后表面的3D坐标，并在两者之间进行稠密采样，构建超密集2D-3D对应关系，从而显著提升基于PnP算法的姿态估计精度。此外，提出分层连续坐标编码（HCCE），实现对前后表面坐标的更精确、高效表示。实验表明，所提方法在BOP官网公布的7个经典核心数据集上均优于现有最先进方法。代码已开源：https://github.com/WangYuLin-SEU/HCCEPose。
原文摘要 · Abstract (English)
In pose estimation for seen objects, a prevalent pipeline involves using neural networks to predict dense 3D coordinates of the object surface on 2D images, which are then used to establish dense 2D-3D correspondences. However, current methods primarily focus on more efficient encoding techniques to improve the precision of predicted 3D coordinates on the object's front surface, overlooking the potential benefits of incorporating the back surface and interior of the object. To better utilize the full surface and interior of the object, this study predicts 3D coordinates of both the object's front and back surfaces and densely samples 3D coordinates between them. This process creates ultra-dense 2D-3D correspondences, effectively enhancing pose estimation accuracy based on the Perspective-n-Point (PnP) algorithm. Additionally, we propose Hierarchical Continuous Coordinate Encoding (HCCE) to provide a more accurate and efficient representation of front and back surface coordinates. Experimental results show that, compared to existing state-of-the-art (SOTA) methods on the BOP website, the proposed approach outperforms across seven classic BOP core datasets. Code is available at https://github.com/WangYuLin-SEU/HCCEPose.
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。