针对6自由度姿态估计，设计高效神经架构搜索框架
FPG-NAS: FLOPs-Aware Gated Differentiable Neural Architecture Search for Efficient 6DoF Pose Estimation
- 基于可微分架构搜索，引入门控机制实现多候选操作选择
- 在10^92种架构中搜索，满足严格算力约束下精度领先
- 专为资源受限场景优化，适合嵌入式视觉应用
我们提出FPG-NAS，一种面向高效6自由度物体姿态估计的感知计算量的可微分神经架构搜索框架。从单张图像估计3D旋转与平移虽被广泛研究，但计算开销大，限制了在资源受限场景的应用。FPG-NAS通过设计任务专用搜索空间和可微门控机制，实现离散多候选操作选择，提升架构多样性；同时引入算力（FLOPs）正则化项，在精度与效率间取得平衡。该框架探索约10^92种可能架构。在LINEMOD与SPEED+数据集上的实验表明，所生成模型在严格算力约束下优于以往方法。据我们所知，FPG-NAS是首个专为6DoF姿态估计设计的可微分神经架构搜索框架。
原文摘要 · Abstract (English)
We introduce FPG-NAS, a FLOPs-aware Gated Differentiable Neural Architecture Search framework for efficient 6DoF object pose estimation. Estimating 3D rotation and translation from a single image has been widely investigated yet remains computationally demanding, limiting applicability in resource-constrained scenarios. FPG-NAS addresses this by proposing a specialized differentiable NAS approach for 6DoF pose estimation, featuring a task-specific search space and a differentiable gating mechanism that enables discrete multi-candidate operator selection, thus improving architectural diversity. Additionally, a FLOPs regularization term ensures a balanced trade-off between accuracy and efficiency. The framework explores a vast search space of approximately 10\textsuperscript{92} possible architectures. Experiments on the LINEMOD and SPEED+ datasets demonstrate that FPG-NAS-derived models outperform previous methods under strict FLOPs constraints. To the best of our knowledge, FPG-NAS is the first differentiable NAS framework specifically designed for 6DoF object pose estimation.
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。