Motion-Aware Animatable Gaussian Avatars Deblurring

TL;DR

This paper presents a novel method for reconstructing sharp 3D human Gaussian avatars directly from blurry videos by modeling motion-induced blur and optimizing avatar and motion parameters jointly.

Contribution

It introduces a physics-based, 3D-aware model of motion blur and a joint optimization framework for avatar reconstruction from blurry inputs.

Findings

Effective reconstruction of sharp 3D avatars from blurry videos.

Robust performance demonstrated on synthetic and real-world datasets.

Outperforms existing methods in handling motion blur in avatar creation.

Abstract

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