Deformable Mesh Transformer for 3D Human Mesh Recovery
Deformable Mesh Transformer for 3D Human Mesh Recovery
复制标题
DOI：
10.1109/cvpr52729.2023.01631
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Y. Yoshiyasu
中科院分区：
文献类型：
--
作者：
Y. Yoshiyasu
提出了一种基于顶点的单目三维人体网格恢复方法--可变形网格转换器(DeFormer)。DeFormer通过在变压器解码器内形成的网格对齐反馈环迭代地将身体网格模型匹配到输入图像，该变压器解码器配备了高效的身体网格驱动注意模块：1)身体稀疏自我注意和2)可变形网格交叉注意。因此，DeFormer可以有效地利用高分辨率的图像特征映射和密集的网格模型，而在以前的方法中，使用标准的变换注意力来处理这些模型的计算代价很高。实验结果表明，DeFormer在Human3.6M和3DPW基准上都达到了最好的性能。还进行了烧蚀研究，以显示DeFormer模型设计在利用多尺度特征地图方面的有效性。代码可在https://github.com/yusukey03012/DeFormer.上找到
We present Deformable mesh transFormer (DeFormer), a novel vertex-based approach to monocular 3D human mesh recovery. DeFormer iteratively fits a body mesh model to an input image via a mesh alignment feedback loop formed within a transformer decoder that is equipped with efficient body mesh driven attention modules: 1) body sparse self-attention and 2) deformable mesh cross attention. As a result, DeFormer can effectively exploit high-resolution image feature maps and a dense mesh model which were computationally expensive to deal with in previous approaches using the standard transformer attention. Experimental results show that DeFormer achieves state-of-the-art performances on the Human3.6M and 3DPW benchmarks. Ablation study is also conducted to show the effectiveness of the DeFormer model designs for leveraging multi-scale feature maps. Code is available at https://github.com/yusukey03012/DeFormer.