PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Peng, He, Yisheng, Hu, Yingdong, Dong, Yuan, Yuan, Weihao, Liu, Yuan, Zhu, Siyu, Cheng, Gang, Dong, Zilong, Guo, Yike
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908586203938816
author Li, Peng
He, Yisheng
Hu, Yingdong
Dong, Yuan
Yuan, Weihao
Liu, Yuan
Zhu, Siyu
Cheng, Gang
Dong, Zilong
Guo, Yike
author_facet Li, Peng
He, Yisheng
Hu, Yingdong
Dong, Yuan
Yuan, Weihao
Liu, Yuan
Zhu, Siyu
Cheng, Gang
Dong, Zilong
Guo, Yike
contents We present a feed-forward framework for Gaussian full-head synthesis from a single unposed image. Unlike previous work that relies on time-consuming GAN inversion and test-time optimization, our framework can reconstruct the Gaussian full-head model given a single unposed image in a single forward pass. This enables fast reconstruction and rendering during inference. To mitigate the lack of large-scale 3D head assets, we propose a large-scale synthetic dataset from trained 3D GANs and train our framework using only synthetic data. For efficient high-fidelity generation, we introduce a coarse-to-fine Gaussian head generation pipeline, where sparse points from the FLAME model interact with the image features by transformer blocks for feature extraction and coarse shape reconstruction, which are then densified for high-fidelity reconstruction. To fully leverage the prior knowledge residing in pretrained 3D GANs for effective reconstruction, we propose a dual-branch framework that effectively aggregates the structured spherical triplane feature and unstructured point-based features for more effective Gaussian head reconstruction. Experimental results show the effectiveness of our framework towards existing work. Project page at: https://panolam.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07552
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image
Li, Peng
He, Yisheng
Hu, Yingdong
Dong, Yuan
Yuan, Weihao
Liu, Yuan
Zhu, Siyu
Cheng, Gang
Dong, Zilong
Guo, Yike
Computer Vision and Pattern Recognition
We present a feed-forward framework for Gaussian full-head synthesis from a single unposed image. Unlike previous work that relies on time-consuming GAN inversion and test-time optimization, our framework can reconstruct the Gaussian full-head model given a single unposed image in a single forward pass. This enables fast reconstruction and rendering during inference. To mitigate the lack of large-scale 3D head assets, we propose a large-scale synthetic dataset from trained 3D GANs and train our framework using only synthetic data. For efficient high-fidelity generation, we introduce a coarse-to-fine Gaussian head generation pipeline, where sparse points from the FLAME model interact with the image features by transformer blocks for feature extraction and coarse shape reconstruction, which are then densified for high-fidelity reconstruction. To fully leverage the prior knowledge residing in pretrained 3D GANs for effective reconstruction, we propose a dual-branch framework that effectively aggregates the structured spherical triplane feature and unstructured point-based features for more effective Gaussian head reconstruction. Experimental results show the effectiveness of our framework towards existing work. Project page at: https://panolam.github.io/.
title PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.07552