无需训练即可零样本识别物体，提升6D姿态估计精度。
CLON: Cue-Calibrated Linguistic Object Onboarding for Zero-Shot 6D Pose Front-Ends
- 用语言记忆和物体提示权重生成高质量候选框。
- 在7个BOP数据集上检测与分割准确率分别提升8.1和6.2个百分点。
- 适合新物体快速接入，无需重新训练模型。
零样本6D姿态估计依赖强大的下游求解器，但前端性能常受限于物体提案：需保留部分可见的正例，同时排除语义上合理的干扰项。本文提出线索校准语言物体接入（CLON）方法，无需针对新物体进行任务特化训练。给定目标物体的渲染模板，CLON构建语言语义记忆用于自上而下的提案生成，并计算物体集合的提示权重用于校准提案评分。语言记忆引导SAM-3生成高召回率提案，提示权重在场景推理前一次性计算并固定不变。在七个BOP-Classic-Core数据集上，相比CNOS和SAM-6D前端，CLON使检测平均精度（AP）提升8.1个百分点，分割AP提升6.2个百分点，下游6D姿态平均召回率（AR）最高提升4.1个百分点。
原文摘要 · Abstract (English)
Zero-shot 6D pose estimation pipelines increasingly rely on strong downstream pose solvers, but their performance is often limited by the front-end: object proposals must preserve partially visible true positives while rejecting semantically plausible distractors. We introduce Cue-Calibrated Linguistic Object Onboarding (CLON), a front-end requiring no task-specific training for new objects. Given rendered templates of the onboarded object set, CLON constructs a linguistic semantic memory for top-down proposal generation and object-set cue weights for calibrated proposal scoring. The linguistic memory guides SAM 3 toward high-recall proposals for onboarded objects, while cue weights are computed once from the onboarded object set before scene inference and kept fixed during online scoring. On seven BOP-Classic-Core datasets, CLON improves detection AP by 8.1 percentage points (pp), segmentation AP by 6.2 pp, and downstream 6D pose AR by up to 4.1 pp over CNOS and SAM-6D front-ends.
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。