paper-with-me

Papers

GUAVA: Generalizable Upper Body 3D Gaussian Avatar

2025-05-06 · Dongbin Zhang, Yunfei Liu, Lijian Lin, Ye Zhu, Yang Li, Minghan Qin, Yu Li, Haoqian Wang

Reconstructing a high-quality, animatable 3D human avatar with expressive facial and hand motions from a single image has gained significant attention due to its broad application potential. 3D human avatar reconstruction typically requires multi-view or monocular videos and training on individual IDs, which is both complex and time-consuming. Furthermore, limited by SMPLX's expressiveness, these methods often focus on body motion but struggle with facial expressions. To address these challenges, we first introduce an expressive human model (EHM) to enhance facial expression capabilities and develop an accurate tracking method. Based on this template model, we propose GUAVA, the first framework for fast animatable upper-body 3D Gaussian avatar reconstruction. We leverage inverse texture mapping and projection sampling techniques to infer Ubody (upper-body) Gaussians from a single image. The rendered images are refined through a neural refiner. Experimental results demonstrate that GUAVA significantly outperforms previous methods in rendering quality and offers significant speed improvements, with reconstruction times in the sub-second range (0.1s), and supports real-time animation and rendering.

📄 PDF Abstract BibTeX arXiv:2505.03351

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Focus 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Video

2026-03-30 · Jeonghaeng Lee, Seok Keun Choi, Zhixuan Li, Weisi Lin 외 arxiv

While recent 3D head avatar creation methods attempt to animate facial dynamics, they often fail to capture personalized details, limiting realism and expressiveness. To fill this gap, we present DipGuava (Disentangled a…

GIGA: Generalizable Sparse Image-driven Gaussian Avatars

2025-04-08 · Anton Zubekhin, Heming Zhu, Paulo Gotardo, Thabo Beeler 외

Driving a high-quality and photorealistic full-body human avatar, from only a few RGB cameras, is a challenging problem that has become increasingly relevant with emerging virtual reality technologies. To democratize suc…

Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping

2024-05-20 · Tianhao Wu, Jing Yang, Zhilin Guo, Jingyi Wan 외

By equipping the most recent 3D Gaussian Splatting representation with head 3D morphable models (3DMM), existing methods manage to create head avatars with high fidelity. However, most existing methods only reconstruct a…

Modeling Clothing as a Separate Layer for an Animatable Human Avatar

2021-06-28 · Donglai Xiang, Fabian Prada, Timur Bagautdinov, Weipeng Xu 외

We have recently seen great progress in building photorealistic animatable full-body codec avatars, but generating high-fidelity animation of clothing is still difficult. To address these difficulties, we propose a metho…

Inverse Rendering

F3G-Avatar : Face Focused Full-body Gaussian Avatar

2026-04-10 · Willem Menu, Erkut Akdag, Pedro Quesado, Yasaman Kashefbahrami 외 arxiv

Existing full-body Gaussian avatar methods primarily optimize global reconstruction quality and often fail to preserve fine-grained facial geometry and expression details. This challenge arises from limited facial repres…