DLTPose通过像素级距离预测提升6自由度姿态估计精度，尤其擅长处理对称和遮挡物体。
DLTPose: 6DoF Pose Estimation From Accurate Dense Surface Point Estimates
- 基于像素级径向距离预测与新式直接线性变换，融合稀疏与密集方法优势
- 在BOP-Classic-Core数据集上超越多数现有方法，对称与遮挡物体表现更优
- 引入对称感知关键点排序，解决对称物体导致的关键点分配不一致问题
我们提出DLTPose，一种从RGBD图像进行6自由度（6DoF）物体姿态估计的新方法，结合了稀疏关键点方法的精度与密集像素级预测的鲁棒性。DLTPose为每个像素预测到一组至少四个关键点的径向距离，这些距离输入我们提出的新型直接线性变换（DLT）公式，生成精确的3D物体表面估计，从而实现更优的6DoF姿态估计。此外，我们设计了一种新颖的对称感知关键点排序方法，以应对物体对称性带来的关键点分配不一致问题。先前基于关键点的方法依赖固定的关键点顺序，无法处理对称物体的多种有效配置，而我们的方法利用这一特性增强了模型学习稳定关键点表示的能力。在基准BOP-Classic-Core数据集上的大量实验表明，DLTPose优于许多近期方法，尤其在对称和遮挡物体上表现突出。代码已公开于anonymous.4open.science/r/DLTPose。
原文摘要 · Abstract (English)
We propose DLTPose, a novel method for 6DoF object pose estimation from RGBD images that combines the accuracy of sparse keypoint methods with the robustness of dense pixel-wise predictions. DLTPose predicts per-pixel radial distances to a set of minimally four keypoints, which are then fed into our novel Direct Linear Transform (DLT) formulation to produce accurate 3D object frame surface estimates, leading to better 6DoF pose estimation. Additionally, we introduce a novel symmetry-aware keypoint ordering approach, designed to handle object symmetries that otherwise cause inconsistencies in keypoint assignments.Previous keypoint-based methods relied on fixed keypoint orderings, which failed to account for the multiple valid configurations exhibited by symmetric objects, which our ordering approach exploits to enhance the model's ability to learn stable keypoint representations. Extensive experiments on the benchmark BOP-Classic-Core datasets show that DLTPose outperforms many recent methods, performing especially well for symmetric and occluded objects. The code is available at anonymous.4open.science/r/DLTPose.
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。