2DGS-Avatar: Animatable High-fidelity Clothed Avatar via 2D Gaussian Splatting
This addresses the challenge of creating realistic, pose-driven avatars for applications in computer vision and graphics, representing an incremental improvement over existing 3DGS methods.
The paper tackles the problem of real-time rendering of high-fidelity animatable avatars from monocular videos by proposing 2DGS-Avatar, which achieves fast training and rendering while capturing detailed and photo-realistic appearances, outperforming 3DGS-based methods on datasets like AvatarRex and THuman4.0.
Real-time rendering of high-fidelity and animatable avatars from monocular videos remains a challenging problem in computer vision and graphics. Over the past few years, the Neural Radiance Field (NeRF) has made significant progress in rendering quality but behaves poorly in run-time performance due to the low efficiency of volumetric rendering. Recently, methods based on 3D Gaussian Splatting (3DGS) have shown great potential in fast training and real-time rendering. However, they still suffer from artifacts caused by inaccurate geometry. To address these problems, we propose 2DGS-Avatar, a novel approach based on 2D Gaussian Splatting (2DGS) for modeling animatable clothed avatars with high-fidelity and fast training performance. Given monocular RGB videos as input, our method generates an avatar that can be driven by poses and rendered in real-time. Compared to 3DGS-based methods, our 2DGS-Avatar retains the advantages of fast training and rendering while also capturing detailed, dynamic, and photo-realistic appearances. We conduct abundant experiments on popular datasets such as AvatarRex and THuman4.0, demonstrating impressive performance in both qualitative and quantitative metrics.