EAvatar: Expression-Aware Head Avatar Reconstruction with Generative Geometry Priors
cs.CV, cs.AI
Submitted: 2025-08-19
Updated: 2026-11-02
Comments: 23 pages, 13 figures
Project page: https://kkun12345.github.io/EAvatar
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
- Structured 3D Latents for Scalable and Versatile 3D Generation
- The relative Hodge-Tate spectral sequence for rigid analytic spaces
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs