用少量参考图快速精准估计新物体姿态，无需微调。
MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation
- 基于多视角匹配点，轻量网络直接融合参考图像特征。
- 仅需少量参考图，精度仍达主流方法水平。
- 适合实时部署的工业场景，内存和推理时间极低。
我们提出 MixRI，一种轻量级网络，用于在RGB图像中基于CAD模型解决新物体姿态估计问题。该方法可在测试时即时应用，无需微调。为满足真实应用场景需求，强调降低内存占用和加快推理速度。与现有使用大量参考图像且参数庞大的方法不同，我们通过轻量网络直接基于查询图像与参考图像间的多视角信息匹配关键点。得益于参考图像融合策略，显著减少所需参考图像数量，从而降低处理时间和存储开销。此外，轻量网络使推理时间更短。尽管参考图像更少，但在BOP挑战赛的七个核心数据集上的实验表明，我们的方法性能可媲美依赖更多参考图像和更大模型参数的现有方法。
原文摘要 · Abstract (English)
We present MixRI, a lightweight network that solves the CAD-based novel object pose estimation problem in RGB images. It can be instantly applied to a novel object at test time without finetuning. We design our network to meet the demands of real-world applications, emphasizing reduced memory requirements and fast inference time. Unlike existing works that utilize many reference images and have large network parameters, we directly match points based on the multi-view information between the query and reference images with a lightweight network. Thanks to our reference image fusion strategy, we significantly decrease the number of reference images, thus decreasing the time needed to process these images and the memory required to store them. Furthermore, with our lightweight network, our method requires less inference time. Though with fewer reference images, experiments on seven core datasets in the BOP challenge show that our method achieves comparable results with other methods that require more reference images and larger network parameters.
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。