Fine-tuning SMPL: A Framework for Highly Detailed Statistical Human Model Buildingстатья

Информация о цитировании статьи получена из Scopus, Web of Science
Дата последнего поиска статьи во внешних источниках: 6 февраля 2020 г.

Работа с статьей


[1] Fine-tuning smpl: A framework for highly detailed statistical human model building / N. Patakin, I. Petrov, V. Guzov, A. Konushin // VSIP 2019: 2019 International Conference on Video, Signal and Image Processing. — New York, N.Y., United States: New York, N.Y., United States, 2019. — P. 21–27. In this paper, we consider the task of statistical modeling of 3D human shape and pose. Current advances in computer graphics and 3D scanning and reconstruction technologies established new application areas for parametrical human body models. These urge the need both in highly detailed human body model that can qualitatively represent details of human appearance, and in a framework for fine-tuning this model using newly collected data. We contribute in both of these aspects in our work by presenting a framework for fully automatic creation of highly detailed human body model based on Skinned Multi-Person Linear (SMPL) human body model. The key features of our framework are mesh subdivision technique that increases the granularity of the model, modified non-rigid deformation algorithm (NRD) for smooth and precise registration of 3D scans and weighted registration process that allows controlling registration in low confidence areas of the 3D scan (holes, artifacts and voluminous haircuts). We propose and evaluate two body models with different detail level and show that even low detailed model outperforms existing body models in terms of registration accuracy and cumulative relative variance. [ DOI ]

Публикация в формате сохранить в файл сохранить в файл сохранить в файл сохранить в файл сохранить в файл сохранить в файл скрыть