GeoAvatar: Geometrically-Consistent Multi-Person Avatar Reconstruction from Sparse Multi-View Videos
Multi-person avatar reconstruction from sparse multi-view videos is challenging. The independent avatar reconstruction of each person often fails to reconstruct the geometric relationship among multiple instances, resulting in inter-penetrations among avatars. Some researchers resolve this issue via neural volumetric rendering techniques but they suffer from huge computational costs for rendering and training. In this paper, we propose a multi-person avatar reconstruction method that reconstructs a 3D avatar of each person while keeping the geometric relations among people. Our 2D Gaussian Splatting (2DGS)-based avatar representation allows us to represent geometrically-accurate surfaces of multiple instances that support sharp inside-outside tests. We utilize the monocular prior to alleviate the inter-penetration via surface ordering and to enhance the geometry in less-observed and textureless surfaces. We demonstrate the efficiency and performance of our method quantitatively and qualitatively on a multi-person dataset containing close interactions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
GeoAvatar: Adaptive Geometrical Gaussian Splatting for 3D Head Avatar
Despite recent progress in 3D head avatar generation, balancing identity preservation, i.e., reconstruction, with novel poses and expressions, i.e., animation, remains a challenge. Existing methods struggle to adapt Gaus…
InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video
We present InstantGeoAvatar, a method for efficient and effective learning from monocular video of detailed 3D geometry and appearance of animatable implicit human avatars. Our key observation is that the optimization of…
3D geometryNovel View SynthesisSpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction
High-quality 4D head avatars from one or a few source portraits are central to telepresence, AR/VR, and digital-human interaction. 3D Gaussian Splatting (3DGS) has emerged as the dominant representation, with two complem…
Split and Drive: Dual-Axis Disentanglement for Real-Time Gaussian Head Avatars
Creating photorealistic animatable head avatars from a single image remains a fundamental challenge in digital human synthesis. While recent 3D Gaussian Splatting methods have achieved promising results, they rely on ext…
DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars
DiffusionAvatars synthesizes a high-fidelity 3D head avatar of a person, offering intuitive control over both pose and expression. We propose a diffusion-based neural renderer that leverages generic 2D priors to produce …