D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field

2023

Conference Paper

ps

Realistic virtual humans play a crucial role in numerous industries, such as metaverse, intelligent healthcare, and self-driving simulation. But creating them on a large scale with high levels of realism remains a challenge. The utilization of deep implicit function sparks a new era of image-based 3D clothed human reconstruction, enabling pixel-aligned shape recovery with fine details. Subsequently, the vast majority of works locate the surface by regressing the deterministic implicit value for each point. However, should all points be treated equally regardless of their proximity to the surface? In this paper, we propose replacing the implicit value with an adaptive uncertainty distribution, to differentiate between points based on their distance to the surface. This simple "value to distribution" transition yields significant improvements on nearly all the baselines. Furthermore, qualitative results demonstrate that the models trained using our uncertainty distribution loss, can capture more intricate wrinkles, and realistic limbs.

@inproceedings{dif2023,
  title = {D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field},
  author = {Yang, Xueting and Luo, Yihao and Xiu, Yuliang and Wang, Wei and Xu, Hao and Fan, Zhaoxin},
  booktitle = {Proc. International Conference on Computer Vision (ICCV)},
  month = oct,
  year = {2023},
  doi = {},
  url = {https://github.com/psyai-net/D-IF_release},
  month_numeric = {10}
}