3D human avatar reconstruction with neural fields: A recent survey

M Gu, J Li, Y Wu, H Luo, J Zheng, X Bai - Image and Vision Computing, 2025 - Elsevier
Abstract 3D human avatar reconstruction aims to reconstruct the 3D geometric shape and
appearance of the human body from various data inputs, such as images, videos, and depth …

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

L Qiu, S Zhu, Q Zuo, X Gu, Y Dong, J Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
Generating animatable human avatars from a single image is essential for various digital
human modeling applications. Existing 3D reconstruction methods often struggle to capture …

Interactive Rendering of Relightable and Animatable Gaussian Avatars

Y Zhan, T Shao, H Wang, Y Yang, K Zhou - arxiv preprint arxiv …, 2024 - arxiv.org
Creating relightable and animatable avatars from multi-view or monocular videos is a
challenging task for digital human creation and virtual reality applications. Previous methods …

RMAvatar: Photorealistic Human Avatar Reconstruction from Monocular Video Based on Rectified Mesh-embedded Gaussians

S Peng, W **e, Z Wang, X Guo, Z Chen, B Yang… - arxiv preprint arxiv …, 2025 - arxiv.org
We introduce RMAvatar, a novel human avatar representation with Gaussian splatting
embedded on mesh to learn clothed avatar from a monocular video. We utilize the explicit …