用深度图作中间表示，单张图像就能精准估计人体姿态与形状。
D-PoSE: Depth as an Intermediate Representation for 3D Human Pose and Shape Estimation
- 以深度图作为中间表征，通过合成数据和真实深度监督训练。
- 在真实数据集上达到当前最佳性能，超越参数量大10倍的ViT模型。
- 轻量级设计适合部署，尤其适合资源受限场景使用。
我们提出D-PoSE（Depth as an Intermediate Representation for 3D Human Pose and Shape Estimation），一种从单张RGB图像中估计人体姿态与SMPL-X形状参数的一阶段方法。现有方法多采用大型Transformer骨干网络以提升精度，而D-PoSE采用基于视觉的方法，将估计的人体深度图作为中间表示，并利用合成数据及其提供的真值深度图进行深度监督训练。尽管仅在合成数据上训练，D-PoSE在真实世界基准数据集EMDB和3DPW上均取得当前最优结果。其轻量级设计搭配CNN骨干网络，在参数量远低于同类模型（相差近一个数量级）的情况下，仍优于基于ViT的模型。
原文摘要 · Abstract (English)
We present D-PoSE (Depth as an Intermediate Representation for 3D Human Pose and Shape Estimation), a one-stage method that estimates human pose and SMPL-X shape parameters from a single RGB image. Recent works use larger models with transformer backbones and decoders to improve the accuracy in human pose and shape (HPS) benchmarks. D-PoSE proposes a vision based approach that uses the estimated human depth-maps as an intermediate representation for HPS and leverages training with synthetic data and the ground-truth depth-maps provided with them for depth supervision during training. Although trained on synthetic datasets, D-PoSE achieves state-of-the-art performance on the real-world benchmark datasets, EMDB and 3DPW. Despite its simple lightweight design and the CNN backbone, it outperforms ViT-based models that have a number of parameters that is larger by almost an order of magnitude. D-PoSE code is available at: https://github.com/nvasilik/D-PoSE
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。