FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head
Quick Answer
FA-LAM introduces a Focus-Aware Large Avatar Model for one-shot animatable Gaussian head creation, enhancing 3D and 4D full-head recovery.
Quick Take
It employs a dual-phase training pipeline and semantic attention regularization to improve reconstruction quality, especially in facial details and large viewing angles.
Key Points
- FA-LAM addresses noisy attention activations affecting 3D full-head generation.
- Introduces a dual-phase training pipeline to separate reconstruction and animation tasks.
- Enhances efficiency with autoregressive modifications for multi-view and streaming 4D reconstruction.
- Achieves superior quality in fine facial regions and large viewing angles.
Paper Resources
Source Excerpt
We propose FA-LAM, a Focus-Aware Large Avatar Model for one-shot animatable Gaussian head creation, while simultaneously enabling static 3D and dynamic 4D full-head recovery. The core of our method lies in a thorough analysis of the attention mechanisms and the entangled reconstruction and animation training pipeline adopted by prior state-of-the-art approaches. Our analysis identifies two main factors that compromise the quality of 3D full-head generation: (1) incorrect and noisy attention acti
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.