InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds
Authors:
Top Cited Papers
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 16922-16932
Abstract
In this paper, we take one step further towards real-world applicability of monocular neural avatar reconstruction by contributing InstantAvatar, a system that can reconstruct human avatars from a monocular video within seconds, and these avatars can be animated and rendered at an inter-active rate. To achieve this efficiency we propose a carefully designed and engineered system, that leverages emerging acceleration structures for neural fields, in combination with an efficient empty-space skipping strategy for dynamic scenes. We also contribute an efficient implementation that we will make available for research purposes. Compared to existing methods, InstantAvatar converges 130x faster and can be trained in minutes instead of hours. It achieves comparable or even better reconstruction quality and novel pose synthesis results. When given the same time budget, our method significantly outperforms SoTA methods. In-stantAvatar can yield acceptable visual quality in as little as 10 seconds training time. For code and more demo results, please refer to https://ait.ethz.ch/InstantAvatar.Keywords
All Related Versions
This publication has 58 references indexed in Scilit:
- LiveCapACM Transactions on Graphics, 2019
- Detailed Human Avatars from Monocular Video2018
- Video Based Reconstruction of 3D People Models2018
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- MonoPerfCapACM Transactions on Graphics, 2018
- Learning from Synthetic Humans2017
- Fusion4DACM Transactions on Graphics, 2016
- SMPLACM Transactions on Graphics, 2015
- High-quality streamable free-viewpoint videoACM Transactions on Graphics, 2015
- Image-based visual hulls2000