EGGHead: Efficient Generalizable Gaussian Heads from a Single Image
Overview & Synopsis
Creating photorealistic human heads typically involves trade-offs between representation power, efficiency, and generalizability. Traditional mesh-based solutions relying on 3DMMs generally sacrifice representation power but are efficient to render. On the other hand, NeRF-based methods improve representation power and fidelity while sacrificing efficiency. Gaussian splatting methods attempt to resolve these trade-offs by offering both high representation power and efficiency with real-time rendering. However, their efficiency nonetheless depends on the number of rasterized Gaussians, and the time needed to optimize and prepare the head (the enrollment time) is often high. In light of this, we propose EGGHead, which introduces a novel Gaussian allocation algorithm that efficiently assigns Gaussians to the head's semantic regions given a fixed Gaussian budget. Our algorithm reduces the number of Gaussians needed while minimizing the impact on representation power. EGGHead operates in a single forward pass and outperforms previous single-image face modeling methods in reconstruction quality, novel view synthesis, and rendering speeds.
arxiv.org)
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | EGGHead: Efficient Generalizable Gaussian Heads from a Single Image |
|---|---|
| Author / Organization | Pilseo Park, Andrew Hou, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu |
| Subject & Discipline | cs.CV |
| Publication Year | 2026 |
| License / Rights | arXiv Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
arXiv
(arxiv.org)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-278582 |
| Original Source Link | Visit Source Page on arxiv.org » |