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

Peng Li; Yisheng He; Yingdong Hu; Yuan Dong; Weihao Yuan; Yuan Liu; Siyu Zhu; Gang Cheng

cs.CVSep 9, 2025

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

Authors: Peng Li, Yisheng He, Yingdong Hu, Yuan Dong, Weihao Yuan, Yuan Liu, Siyu Zhu, Gang Cheng, +3 more

Organizations: HKUST · Tongyi Lab, Alibaba Group · Fudan University

Abstract

We present a feed-forward framework for static Gaussian full-head reconstruction and novel-view rendering 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 compared to existing work. The dataset is available at https://github.com/PanoLAM/PanoLAM_Dataset.

Figures & tables

Fig. 1: PanoLAM creates high-fidelity Gaussian full-heads given an unposed single image in a single forward pass within a second, enabling efficient creation of high-quality 3D avatar assets.

Fig. 2: Overall Framework. Given an unposed head image as input, PanoLAM involves two branches to achieve single-pass 3D Gaussian head reconstruction: a point-based transformer for coarse-to-fine point shape reconstruction and point feature extraction, and a spherical triplane transformer to distill prior knowledge from a 3D GAN. Features from the two branches are concatenated for high-fidelity Gaussian head regression.

Fig. 3: The proposed feature aggregation mechanism samples and aggregates multi-layer features from the spherical triplane for each point.

Dataset	Sub.	Range	Hair	Dataset	Sub.	Range	Hair
BU-3DFE	100	front	✗	HeadSpace	1519	$270^{\circ}$	✗
BU-4DFE	101	front	✓	FaceScape	938	$360^{\circ}$	✗
BJUT-3D	500	front	✗	AVA-256	256	$360^{\circ}$	✓
Bosphorus	105	front	✗	FaceVerse ∗	128	$360^{\circ}$	✓
FaceWarhouse	150	front	✓	RenderMe360 ∗	500	$360^{\circ}$	✓
4DFAB	180	front	✗	SynHead100	100	$360^{\circ}$	✓

TABLE I: Comparisons of existing 3D head datasets. ∗ denotes 3D head with rough captured 3D hair shape.

Fig. 4: Visualization of reconstruction and novel view synthesis of different methods. The left part shows comparisons of different methods on synthesis data, and the right part shows visualization on in-the-wild real-world images, showing the out-of-domain generalizability of PanoLAM trained on our curated datasets.

Fig. 5: Comparison of reconstruction and novel view synthesis of different methods on the test set. Our framework can reconstruct 360-degree heads given a single input view, with fine-grained details and fewer artifacts compared to baselines.

Fig. 6: Qualitative comparisons with FaceLift [ 39 ] .

Method	Real-world			Synthesis
	PSNR $\uparrow$	LPIPS $\downarrow$	SSIM $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$	SSIM $\uparrow$
PanoHead-PTI	16.260	0.165	0.704	24.37	0.141	0.806
SphereHead-PTI	16.983	0.142	0.698	24.65	0.127	0.811
LGM	11.472	0.444	0.572	21.33	0.350	0.765
LGM-Finetuned	19.313	0.182	0.699	25.67	0.135	0.806
LAM	15.627	0.245	0.647	18.72	0.157	0.713

TABLE II: Quantitative evaluation on synthesis and real-world testsets.

Table 9

Panel of Figure 10 — Fig. 7: Out-of-domain qualitative results of PanoLAM under challenging input conditions. Each triplet shows the input and two synthesized novel views.

Fig. 8: Effect of coarse-to-fine generation. Without the coarse-to-fine strategy, the dense Gaussians are distributed on multiple layers, leading to degradation of rendering quality. Zoom in for details.

Fig. 9: Comparison of our network trained on different numbers of subjects. The model trained on a small number of subjects cannot generalize well to unseen identities.

Fig. 10: Comparisons on different spherical triplane feature query and aggregation strategies. For each point, sampling only one sample of features from the spherical triplane cannot fully fetch all valuable features, resulting in a collapsed rendered image. Aggregating 32 points with Gaussian distribution weights gets better results, but still blurry. Our MLPs learn to aggregate features as the original NeRF and get quite better results.

Fig. 11: Comparison of different numbers of Gaussian points. A small number of Gaussian points cannot model texture details like hair strands and teeth. More high-fidelity Gaussian avatars are reconstructed with an increasing number of Gaussian points. Zoom in to see more details.

Method	PSNR $\uparrow$	LPIPS $\downarrow$	SSIM $\uparrow$	Infer.(s) $\downarrow$	Memory(G) $\downarrow$
10K	22.22	0.203	0.738	0.074	5.65
30K	26.42	0.134	0.835	0.082	7.22
100K	27.45	0.093	0.882	0.110	12.70

TABLE VI: Quantitative comparison of different numbers of Gaussian points on the test set.

Explore similar work

One-Shot Feed-Forward 360 $^{\circ}$ Animatable Avatar via Inpainted UV-Space Gaussian Modeling
Jan 19, 2026Shuling Zhao, Dan Xu3D Gaussian Splatting 3D Reconstruction
The Hong Kong University of Science and Technology · Zeekr Automobile R&D Co., Ltd.
Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures
May 5, 2026Evangelos Ntavelis, Sean Wu, Mohamad Shahbazi +213D Gaussian Splatting Multi-View 3D Reconstruction
Apple
FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head
Jul 23, 2026Yingdong Hu, Yisheng He, Yiming Jiang +33D Gaussian Splatting 4D Reconstruction
HKUST Hong Kong SAR, China · Tongyi Lab, Alibaba Group Hangzhou, China · Lingnan University Hong Kong SAR, China

Jan 19, 2026J/K move · Enter open · S save

One-Shot Feed-Forward 360 $^{\circ}$ Animatable Avatar via Inpainted UV-Space Gaussian Modeling

Shuling Zhao, Dan Xu

The Hong Kong University of Science and Technology · Zeekr Automobile R&D Co., Ltd.

3D Gaussian Splatting 3D Reconstruction 3D Avatar Generation Human Avatar Animation 3D Face Reconstruction Single-View 3D Reconstruction+1

Open paper AskPDF arXiv

Building one-shot 3D animatable head avatars is an important yet challenging problem. Existing methods generally collapse under large camera pose variations, compromising the realism of 3D avatars. In this work, we propose a new framework to tackle the novel setting of one-shot 3D full-head animatable avatar reconstruction in a single forward pass via inpainted UV-space Gaussian modeling, enabling 360

^\circ

rendering views and real-time animation. To facilitate efficient animation control, we model 3D head avatars with Gaussian primitives embedded on the surface of a parametric face model within the UV space, and project the input image features to the UV space, resulting in incomplete local UV feature maps. To inpaint the missing regions, we obtain knowledge of full-head geometry and textures from rich 3D full-head priors within a pretrained 3D generative adversarial network (GAN) for global full-head feature extraction and multi-view supervision. Specifically, to enhance the fidelity of 3D reconstruction during inpainting, we take advantage of the symmetric nature of the UV space and human faces to fuse incomplete yet detailed local UV feature maps with the extracted global full-head textures, resulting in inpainted UV Gaussian attribute maps for avatar modeling. Extensive experiments demonstrate that our method is the first to achieve high-quality 3D full-head animatable avatar modeling, significantly improving side and back views while outperforming state-of-the-art animation approaches, thereby improving the realism of 3D animatable avatars.

Abstract

Explore similar work

One-Shot Feed-Forward 360∘^{\circ}∘ Animatable Avatar via Inpainted UV-Space Gaussian Modeling

Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures

FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head

One-Shot Feed-Forward 360 $^{\circ}$ Animatable Avatar via Inpainted UV-Space Gaussian Modeling