用3D原型统一解决RGB图像中的物体检测与姿态估计问题
Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes
- 基于神经网格和多模型RANSAC的统一框架
- 在REAL275上平均提升22.9%的性能
- 适合需要高精度3D姿态的应用场景
物体识别是计算机视觉的基础问题。尽管二维图像中的物体检测已很普遍，但许多应用需确定物体在三维空间中的姿态。传统类别级方法依赖RGB-D输入，可能无法获取，或采用两阶段方法，使用独立模型和表示分别进行检测与姿态估计。本文首次提出一种统一模型，通过学习的神经网格模型和多模型RANSAC，将检测与姿态估计整合到单一框架中，仅使用RGB图像。该方法在REAL275数据集上实现了当前最优的类别级姿态估计性能，所有无尺度感知指标平均提升22.9%。最后，我们证明该统一方法相比单阶段基线更具鲁棒性。代码与模型已开源。
原文摘要 · Abstract (English)
Recognizing objects in images is a fundamental problem in computer vision. Although detecting objects in 2D images is common, many applications require determining their pose in 3D space. Traditional category-level methods rely on RGB-D inputs, which may not always be available, or employ two-stage approaches that use separate models and representations for detection and pose estimation. For the first time, we introduce a unified model that integrates detection and pose estimation into a single framework for RGB images by leveraging neural mesh models with learned features and multi-model RANSAC. Our approach achieves state-of-the-art results for RGB category-level pose estimation on REAL275, improving on the current state-of-the-art by 22.9% averaged across all scale-agnostic metrics. Finally, we demonstrate that our unified method exhibits greater robustness compared to single-stage baselines. Our code and models are available at https://github.com/Fischer-Tom/unified-detection-and-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。