The creation of 3D human avatars from multi-view videos is a significant yet challenging task in computer vision. However, existing techniques rely on high-quality, sharp images as input, which are often impractical to obtain in real-world scenarios due to variations in human motion speed and intensity. This paper introduces a novel method for directly reconstructing sharp 3D human Gaussian avatars from blurry videos. The proposed approach incorporates a 3D-aware, physics-based model of blur formation caused by human motion, together with a 3D human motion model designed to resolve ambiguities in motion-induced blur. This framework enables the joint optimization of the avatar representation and motion parameters from a coarse initialization. Comprehensive benchmarks are established using both a synthetic dataset and a real-world dataset captured with a 360-degree synchronous hybrid-exposure camera system. Extensive evaluations demonstrate the effectiveness of the model across diverse conditions. Codes Available: https://github.com/MyNiuuu/MAD-Avatar
@article{arxiv.2411.16758,
title = {Motion-Aware Animatable Gaussian Avatars Deblurring},
author = {Muyao Niu and Yifan Zhan and Qingtian Zhu and Zhuoxiao Li and Wei Wang and Zhihang Zhong and Xiao Sun and Yinqiang Zheng},
journal= {arXiv preprint arXiv:2411.16758},
year = {2026}
}
Comments
Accepted at CVPR 2026, Codes: https://github.com/MyNiuuu/MAD-Avatar