RARE：学习排序与检索用于单目 3D 目标检测
RARE: Learn to RAnk and REtrieve for Monocular 3D Object Detection
把置信度估计从回归绝对分数改成学习相对排序，并用查询集显式建模单目 3D 定位的多峰分布再检索 top-1，这套「排序+检索」思路可直接迁移到其他存在病态逆问题的 3D 任务（如单目深度、6D 位姿）的置信度与多假设输出设计。
原文依据 RARE formulates confidence estimation as a ranking problem, learning to order detections by their relative quality rather than regressing absolute values.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从单张 RGB 图像进行单目 3D 目标检测仍然具有挑战性，原因在于两个根本性问题：3D 定位的病态性，即同一 2D 观测可能对应多种合理的 3D 配置；以及不可靠的置信度估计，其无法反映真实的定位精度。现有方法预测确定性的 3D 框，往往坍缩为不合理的均值估计，并依赖对定位误差高度敏感的绝对置信度分数。本文提出 RARE，一个通过排序与检索学习来同时解决这两个挑战的统一框架。RARE 将置信度估计建模为排序问题，学习按相对质量对检测结果排序，而非回归绝对值。它提供了更鲁棒、更稳定的置信度估计，对定位不确定性不那么敏感。在改进的置信度估计器基础上，RARE 学习为每个目标构建一个查询集，预测多个多样且合理的 3D 配置，并检索排名最高的预测。它显式地建模了单目 3D 感知的多峰特性，并产生更合理的定位结果。大量实验证明了 RARE 的有效性。代码可在 https://github.com/HyeonjeongPark37/RARE 获取。
英文原文摘要 1335 字符
Monocular 3D object detection from a single RGB image remains challenging due to two fundamental challenges: the ill-posed nature of 3D localization, where multiple plausible configurations can correspond to the same 2D observation, and unreliable confidence estimation that fails to reflect true localization accuracy. Existing methods predict deterministic 3D boxes that often collapse to implausible mean estimates and rely on absolute confidence scores that are highly sensitive to localization errors. This paper introduces RARE, a unified framework that addresses both challenges through learning to rank and retrieve. RARE formulates confidence estimation as a ranking problem, learning to order detections by their relative quality rather than regressing absolute values. It provides more robust and stable confidence estimates that are less sensitive to localization uncertainty. Building on this improved confidence estimator, RARE learns to construct a query set for each object that predicts multiple diverse and plausible 3D configurations, and retrieves the top-ranked prediction. It explicitly models the multimodal nature of monocular 3D perception and produces more plausible localizations. Extensive experiments demonstrate the effectiveness of RARE. The code is available at https://github.com/HyeonjeongPark37/RARE.