HeatFormer: A Neural Optimizer for Multiview Human Mesh Recovery

https://vision.ist.i.kyoto-u.ac.jp/ Figure 1. HeatFormer is a novel neural optimizer for human mesh recovery from static multiview images. It recovers the SMPL shape and pose parameters by fully leveraging the views to resolve occlusions (e.g., note how well the body parts occluded by objects and other body parts are recovered). It is also agnostic to the configuration and number of views which is essential for generalization in real-world scenes. (From left to right, the datasets are Human3.6M [17], BEHAVE [3], MPI-INF-3DHP [36], and RICH [15].