DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras
This enables high-fidelity 3D capture of interacting characters for applications like VR/AR and film, though it is an incremental improvement combining existing techniques.
The authors tackled multi-person 3D performance capture from sparse camera views, developing DeepMultiCap to reconstruct detailed surfaces without pre-scanned templates and handle occlusions in close interactions. Their method achieved state-of-the-art results, outperforming prior works by a large margin on their new MultiHuman dataset of 150 scenes.
We propose DeepMultiCap, a novel method for multi-person performance capture using sparse multi-view cameras. Our method can capture time varying surface details without the need of using pre-scanned template models. To tackle with the serious occlusion challenge for close interacting scenes, we combine a recently proposed pixel-aligned implicit function with parametric model for robust reconstruction of the invisible surface areas. An effective attention-aware module is designed to obtain the fine-grained geometry details from multi-view images, where high-fidelity results can be generated. In addition to the spatial attention method, for video inputs, we further propose a novel temporal fusion method to alleviate the noise and temporal inconsistencies for moving character reconstruction. For quantitative evaluation, we contribute a high quality multi-person dataset, MultiHuman, which consists of 150 static scenes with different levels of occlusions and ground truth 3D human models. Experimental results demonstrate the state-of-the-art performance of our method and the well generalization to real multiview video data, which outperforms the prior works by a large margin.