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

arXiv:2509.07552 · cs.CV · Submitted 2025-09-09 · Read on arXiv

cs.CV

Submitted: 2025-09-09

Updated: 2026-10-10

Comments: Accepted to IEEE Transactions on Visualization and Computer Graphics (TVCG)

Code: https://github.com/PanoLAM/PanoLAM_Dataset

Project page: https://panolam.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fidelity — 2× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Feed-forward framework — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• HeadNeRF: A Real-time NeRF-based Parametric Head Model
• Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars
• Unsupervised Generative 3D Shape Learning from Natural Images

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models