Real-Time Animatable 2DGS-Avatars with Detail Enhancement from Monocular Videos

TL;DR

This paper presents a real-time framework for creating detailed, animatable 2D Gaussian Splatting-based human avatars from monocular videos, improving detail preservation and animation stability.

Contribution

It introduces a novel real-time method combining 2D Gaussian Splatting with a Rotation Compensation Network for enhanced detail and stable animation of reconstructed avatars.

Findings

Successfully reconstructs realistic, detailed avatars from monocular videos.

Achieves superior animation stability and detail preservation compared to existing methods.

Outperforms state-of-the-art approaches on public benchmarks.

Abstract

High-quality, animatable 3D human avatar reconstruction from monocular videos offers significant potential for reducing reliance on complex hardware, making it highly practical for applications in game development, augmented reality, and social media. However, existing methods still face substantial challenges in capturing fine geometric details and maintaining animation stability, particularly under dynamic or complex poses. To address these issues, we propose a novel real-time framework for animatable human avatar reconstruction based on 2D Gaussian Splatting (2DGS). By leveraging 2DGS and global SMPL pose parameters, our framework not only aligns positional and rotational discrepancies but also enables robust and natural pose-driven animation of the reconstructed avatars. Furthermore, we introduce a Rotation Compensation Network (RCN) that learns rotation residuals by integrating local geometric features with global pose parameters. This network significantly improves the handling of non-rigid deformations and ensures smooth, artifact-free pose transitions during animation. Experimental results demonstrate that our method successfully reconstructs realistic and highly animatable human avatars from monocular videos, effectively preserving fine-grained details while ensuring stable and natural pose variation. Our approach surpasses current state-of-the-art methods in both reconstruction quality and animation robustness on public benchmarks.