无需训练即可精修与跟踪任意物体6自由度位姿，效率高且稳定。
GoTrack: Generic 6DoF Object Pose Refinement and Tracking
- 融合帧间与模型到帧的注册，用光流实现高效匹配。
- 在标准基准上达到当前仅用RGB的顶尖追踪效果。
- 适合需要轻量、通用、无训练的3D位姿追踪场景。
我们提出GoTrack，一种高效准确的基于CAD的6自由度物体位姿精修与跟踪方法，可处理各类物体而无需特定训练。不同于仅依赖模型到图像注册（分析-合成）的现有方法，GoTrack额外引入帧间注册，降低计算量并提升稳定性。两种注册均通过光流估计实现。模型到帧注册更简化，仅使用标准神经网络模块（在DINOv2之上训练Transformer），无需评分网络即可输出可靠置信度。帧间注册因连续帧高度相似，采用轻量级现成光流模型。实验表明，GoTrack可无缝集成现有粗略位姿估计方法，构建最小化流水线，在标准6自由度位姿估计与跟踪基准上取得仅用RGB的顶尖性能。源代码与训练模型已公开于https://github.com/facebookresearch/gotrack。
原文摘要 · Abstract (English)
We introduce GoTrack, an efficient and accurate CAD-based method for 6DoF object pose refinement and tracking, which can handle diverse objects without any object-specific training. Unlike existing tracking methods that rely solely on an analysis-by-synthesis approach for model-to-frame registration, GoTrack additionally integrates frame-to-frame registration, which saves compute and stabilizes tracking. Both types of registration are realized by optical flow estimation. The model-to-frame registration is noticeably simpler than in existing methods, relying only on standard neural network blocks (a transformer is trained on top of DINOv2) and producing reliable pose confidence scores without a scoring network. For the frame-to-frame registration, which is an easier problem as consecutive video frames are typically nearly identical, we employ a light off-the-shelf optical flow model. We demonstrate that GoTrack can be seamlessly combined with existing coarse pose estimation methods to create a minimal pipeline that reaches state-of-the-art RGB-only results on standard benchmarks for 6DoF object pose estimation and tracking. Our source code and trained models are publicly available at https://github.com/facebookresearch/gotrack
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。