释放链式预测的潜力用于单目3D目标检测
Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detection
把 3D 属性（深度/尺寸/朝向）的投影相关性显式建模成链式特征传播，并用不确定性门控在链式与并行预测间逐目标切换，可直接迁移到其他多属性回归的几何估计任务（如单目深度+位姿、6D 位姿估计）。
原文依据 an Uncertainty-Guided Selector (GS) dynamically switches between CoP and parallel paradigms for each object based on the predicted uncertainty
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单目3D检测（Mono3D）旨在从单张RGB图像推断3D边界框。在没有LiDAR等辅助传感器的情况下，该任务本质上是病态的，因为3D到2D的投影引入了深度歧义。以往工作通常并行预测3D属性（如深度、尺寸和朝向），忽视了这些属性通过3D到2D投影而内在相关。然而，仅通过顺序预测来强制这种相关性会在属性之间传播误差，尤其是当目标被遮挡或截断时，不准确的尺寸或朝向预测会进一步放大深度误差。因此，并行预测与顺序预测都不是最优的。本文提出MonoCoP，一个自适应框架，通过两个互补设计学习何时以及如何利用属性间相关性。链式预测（CoP）通过特征级的学习、传播与聚合来探索属性间相关性，而不确定性引导选择器（GS）则根据预测的不确定性为每个目标在CoP与并行范式之间动态切换。通过结合二者优势，MonoCoP在KITTI、nuScenes和Waymo上取得最优性能，显著提升深度精度，尤其是对远处目标。
英文原文摘要 1335 字符
Monocular 3D detection (Mono3D) aims to infer 3D bounding boxes from a single RGB image.Without auxiliary sensors such as LiDAR, this task is inherently ill-posed since the 3D-to-2D projection introduces depth ambiguity.Previous works often predict 3D attributes (e.g., depth, size, and orientation) in parallel, overlooking that these attributes are inherently correlated through the 3D-to-2D projection.However, simply enforcing such correlations through sequential prediction can propagate errors across attributes, especially when objects are occluded or truncated, where inaccurate size or orientation predictions can further amplify depth errors.Therefore, neither parallel nor sequential prediction is optimal.In this paper, we propose MonoCoP, an adaptive framework that learns when and how to leverage inter-attribute correlations with two complementary designs.A Chain-of-Prediction (CoP) explores inter-attribute correlations through feature-level learning, propagation, and aggregation, while an Uncertainty-Guided Selector (GS) dynamically switches between CoP and parallel paradigms for each object based on the predicted uncertainty.By combining their strengths, MonoCoP achieves state-of-the-art (SOTA) performance on KITTI, nuScenes, and Waymo, significantly improving depth accuracy, particularly for distant objects.