3D Multi-Person Mesh Recovery
9 papers with code • 2 benchmarks • 2 datasets
Through a body-center-guided sampling process, the body mesh parameters of all people in the image are easily extracted from the Mesh Parameter map.
To understand how people look, interact, or perform tasks, we need to quickly and accurately capture their 3D body, face, and hands together from an RGB image.
Additionally, we fine-tune methods on AGORA and show improved performance on both AGORA and 3DPW, confirming the realism of the dataset.
It is challenging to perform this task with a single network due to resolution issues, i. e., the face and hands are usually located in extremely small regions.
1) For the data scaling, we perform a systematic investigation on 32 EHPS datasets, including a wide range of scenarios that a model trained on any single dataset cannot handle.