用光线表示2D关键点，让3D姿态估计无视摄像头参数和视角数。
RUMPL: Ray-Based Transformers for Universal Multi-View 2D to 3D Human Pose Lifting
- 用3D光线替代传统坐标，实现无需标定相机的多视角融合
- 在真实场景数据上比三角法低53%误差，比基线模型低60%以上
- 支持任意数量和位置摄像头，适合实际部署且无需重新训练
从2D图像估计3D人体姿态仍面临遮挡和投影模糊的挑战。基于多视角学习的方法虽可缓解问题，但因缺乏大规模带3D真值的真实场景多视角数据而难以泛化。现有方法依赖合成数据训练2D到3D姿态提升模型。本文在先前MPL框架基础上提出RUMPL，一种基于变换器的3D姿态提升模型，引入2D关键点的3D光线表示，使模型摆脱相机标定与视角数量限制，实现任意多视角配置下的通用部署，无需重训或微调。新增的视图融合变换器利用学习后的融合光线标记沿光线聚合信息，进一步提升多视角一致性。大量实验表明，RUMPL相较三角法降低MPJPE达53%，相较基于图像表示的变换器基线降低超60%。在新基准测试（包括野外多视角与多人数据集）中验证了其鲁棒性与可扩展性。代码已开源：https://github.com/aghasemzadeh/OpenRUMPL
原文摘要 · Abstract (English)
Estimating 3D human poses from 2D images remains challenging due to occlusions and projective ambiguity. Multi-view learning-based approaches mitigate these issues but often fail to generalize to real-world scenarios, as large-scale multi-view datasets with 3D ground truth are scarce and captured under constrained conditions. To overcome this limitation, recent methods rely on 2D pose estimation combined with 2D-to-3D pose lifting trained on synthetic data. Building on our previous MPL framework, we propose RUMPL, a transformer-based 3D pose lifter that introduces a 3D ray-based representation of 2D keypoints. This formulation makes the model independent of camera calibration and the number of views, enabling universal deployment across arbitrary multi-view configurations without retraining or fine-tuning. A new View Fusion Transformer leverages learned fused-ray tokens to aggregate information along rays, further improving multi-view consistency. Extensive experiments demonstrate that RUMPL reduces MPJPE by up to 53% compared to triangulation and over 60% compared to transformer-based image-representation baselines. Results on new benchmarks, including in-the-wild multi-view and multi-person datasets, confirm its robustness and scalability. The framework's source code is available at https://github.com/aghasemzadeh/OpenRUMPL
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。