FastHuman: Reconstructing High-Quality Clothed Human in Minutes (original) (raw)

Method

We first employ visual hull to obtain the initial mesh. Then we sample the oriented point clouds as optimization target. The oriented point clouds are optimized by multi-view patch-based photometric constraints. Moreover, we fix the mesh topology and employ a shape from shading refinement to refine the coarse mesh and recover the albedo.

BibTeX

@inproceedings{lin2024fasthuman,
      title={FastHuman: Reconstructing High-Quality Clothed Human in Minutes}, 
      author={Lixiang Lin and Songyou Peng and Qijun Gan and Jianke Zhu},
      year={2024},
      booktitle={International Conference on 3D Vision, 3DV},
}