提升单目3D检测在复杂场景下的泛化能力，解决遮挡、数据分布差异等问题。
Generalizing Monocular 3D Object Detection
- 提出可微分的去重算法，增强遮挡情况下的检测鲁棒性。
- 设计深度等变骨干网络，提升跨数据集的适应能力。
- 针对大物体检测噪声敏感问题，引入基于分割的鸟瞰图方法。
单目3D目标检测（Mono3D）是从单张图像中估计目标类别、3D位置、尺寸和方向的基础计算机视觉任务，广泛应用于自动驾驶、增强现实和机器人等领域，其性能依赖于对三维环境的准确理解。本文聚焦于提升Mono3D模型在多样化场景下的泛化能力，涵盖遮挡、不同数据集、物体尺寸以及相机参数的变化。为增强遮挡鲁棒性，提出一种数学可微分的非极大值抑制（GrooMeD-NMS）；为提升跨数据集泛化能力，探索深度等变（DEVIANT）骨干网络；针对大物体检测问题，揭示其不仅是数据不平衡或感受野不足所致，更与噪声敏感相关，提出基于鸟瞰图分割与Dice损失的SeaBird方法加以缓解；最后从理论上分析模型在未见相机高度下的外推能力，并改进此类分布外场景下的泛化表现。
原文摘要 · Abstract (English)
Monocular 3D object detection (Mono3D) is a fundamental computer vision task that estimates an object's class, 3D position, dimensions, and orientation from a single image. Its applications, including autonomous driving, augmented reality, and robotics, critically rely on accurate 3D environmental understanding. This thesis addresses the challenge of generalizing Mono3D models to diverse scenarios, including occlusions, datasets, object sizes, and camera parameters. To enhance occlusion robustness, we propose a mathematically differentiable NMS (GrooMeD-NMS). To improve generalization to new datasets, we explore depth equivariant (DEVIANT) backbones. We address the issue of large object detection, demonstrating that it's not solely a data imbalance or receptive field problem but also a noise sensitivity issue. To mitigate this, we introduce a segmentation-based approach in bird's-eye view with dice loss (SeaBird). Finally, we mathematically analyze the extrapolation of Mono3D models to unseen camera heights and improve Mono3D generalization in such out-of-distribution settings.
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。