The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimation

IEEE Conference on Computer Vision and Pattern Recognition(2022)

引用 11|浏览41
暂无评分
摘要
Nonparametric based methods have recently shown promising results in reconstructing human bodies from monocular images while model-based methods can help correct these estimates and improve prediction. However, estimating model parameters from global image features may lead to noticeable misalignment between the estimated meshes and image evidence. To address this issue and leverage the best of both worlds, we propose a framework of three consecutive modules. A dense map prediction module explicitly establishes the dense UV correspondence between the image evidence and each part of the body model. The inverse kinematics module refines the key point prediction and generates a posed template mesh. Finally, a UV inpainting module relies on the corresponding feature, prediction and the posed template, and completes the predictions of occluded body shape. Our framework leverages the best of non-parametric and model-based methods and is also robust to partial occlusion. Experiments demonstrate that our framework outperforms existing 3D human estimation methods on multiple public benchmarks.
更多
查看译文
关键词
key point prediction,posed template mesh,UV inpainting module,corresponding feature,occluded body shape,model-based methods,3D human estimation methods,nonparametric approaches,3D human body estimation,nonparametric based methods,human bodies,monocular images,estimating model parameters,global image features,noticeable misalignment,estimated meshes,image evidence,consecutive modules,dense map prediction module,dense UV correspondence,body model,inverse kinematics module
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要