paper-with-me

Papers

Gaussian Pixel Codec Avatars: A Hybrid Representation for Efficient Rendering

2025-12-17 · Divam Gupta, Anuj Pahuja, Nemanja Bartolovic, Tomas Simon, Forrest Iandola, Giljoo Nam arxiv

We present Gaussian Pixel Codec Avatars (GPiCA), photorealistic head avatars that can be generated from multi-view images and efficiently rendered on mobile devices. GPiCA utilizes a unique hybrid representation that combines a triangle mesh and anisotropic 3D Gaussians. This combination maximizes memory and rendering efficiency while maintaining a photorealistic appearance. The triangle mesh is highly efficient in representing surface areas like facial skin, while the 3D Gaussians effectively handle non-surface areas such as hair and beard. To this end, we develop a unified differentiable rendering pipeline that treats the mesh as a semi-transparent layer within the volumetric rendering paradigm of 3D Gaussian Splatting. We train neural networks to decode a facial expression code into three components: a 3D face mesh, an RGBA texture, and a set of 3D Gaussians. These components are rendered simultaneously in a unified rendering engine. The networks are trained using multi-view image supervision. Our results demonstrate that GPiCA achieves the realism of purely Gaussian-based avatars while matching the rendering performance of mesh-based avatars.

📄 PDF Abstract BibTeX arXiv:2512.15711

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Pixel Codec Avatars

2021-04-09 · CVPR 2021 1 · Shugao Ma, Tomas Simon, Jason Saragih, Dawei Wang 외

Telecommunication with photorealistic avatars in virtual or augmented reality is a promising path for achieving authentic face-to-face communication in 3D over remote physical distances. In this work, we present the Pixe…

Decoder

Relightable Gaussian Codec Avatars

2023-12-06 · CVPR 2024 1 · Shunsuke Saito, Gabriel Schwartz, Tomas Simon, Junxuan Li 외

The fidelity of relighting is bounded by both geometry and appearance representations. For geometry, both mesh and volumetric approaches have difficulty modeling intricate structures like 3D hair geometry. For appearance…

FiCA: Feed-forward instant Gaussian Codec Avatars from a Single Portrait Image

2026-06-23 · Kim Youwang, Zhengyu Yang, Liuhao Ge, Yu Rong 외 arxiv

We introduce FiCA, a Feed-forward, instant Gaussian Codec Avatar generation pipeline that creates lifelike avatars from a single portrait image. Generating a photorealistic and drivable avatar from just a single image is…

TexAvatars : Hybrid Texel-3D Representations for Stable Rigging of Photorealistic Gaussian Head Avatars

2025-12-24 · Jaeseong Lee, Junyeong Ahn, Taewoong Kang, Jaegul Choo arxiv

Constructing drivable and photorealistic 3D head avatars has become a central task in AR/XR, enabling immersive and expressive user experiences. With the emergence of high-fidelity and efficient representations such as 3…

SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting

2024-03-08 · CVPR 2024 1 · Zhijing Shao, Zhaolong Wang, Zhuang Li, Duotun Wang 외

We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting embedded on a triangle mesh, which renders over 300 FPS on a modern GPU and 30 FPS on a mobile device. We dis…

GPU