# GHARP: Real-time Gaussian Head Animation from Large-scale Reconstruction Prior

arXiv: https://arxiv.org/abs/2610.10945 · HTML: https://mlsanity.com/paper/2610.10945/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 12 of its 84 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 12 of 12)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Towards Fast, Accurate and Stable 3D Dense Face Alignment](https://mlsanity.com/paper/2009.09960/) (2020)
- [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://mlsanity.com/paper/2407.03168/) (2024)
- [Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis](https://mlsanity.com/paper/2401.08503/) (2024)
- [GPAvatar: Generalizable and Precise Head Avatar from Image(s)](https://mlsanity.com/paper/2401.10215/) (2024)
- [FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads](https://mlsanity.com/paper/2412.17812/) (2024)
- [VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence](https://mlsanity.com/paper/2405.16204/) (2024)
- [ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions](https://mlsanity.com/paper/2507.10542/) (2025)
- [FastAvatar: Instant 3D Gaussian Splatting for Faces from Single Unconstrained Poses](https://mlsanity.com/paper/2508.18389/) (2025)
- [PrismAvatar: Real-time animated 3D neural head avatars on edge devices](https://mlsanity.com/paper/2502.07030/) (2025)
- [LegacyAvatars: Volumetric Face Avatars For Traditional Graphics Pipelines](https://mlsanity.com/paper/2601.12285/) (2026)

## Abstract (arXiv)

We present GHARP (Real-time Gaussian Head Animation from Large-scale Reconstruction Prior), a method that animates 3D human heads in real time from a few input images of a subject and a driving expression signal. We decouple the problem into an identity stage that builds a representation of the subject's geometry and appearance offline, and an animation stage that predicts expression-dependent residuals on top of it at runtime. This separation offers a favorable trade-off with respect to fidelity, quality and runtime: the identity stage can be expensive while the animation stage runs a lightweight network, optimized for mobile devices. Our method performs animation in a semantically structured latent space of a pretrained reconstruction model, where expression changes remain spatially contained, making residual prediction efficient. This reconstruction prior provides a consistent spatial layout, allowing fusion of multiple input views into a compact, fixed-size canonical Gaussian representation. While this two-stage design improves the runtime-quality trade-off, it still inherits a problem common to all expression-driven avatar methods: expression codes describe only the face and thus omit body pose and clothing position, making these regions underspecified in the input. The animation network faces an ill-posed mapping and resorts to averaging over conflicting body appearances, producing blur and temporal flicker. We address this with a body alignment network that learns to align the person's body in the target image with the input reference images, removing the ambiguity from the training signal. Our method achieves state-of-the-art quality on the Ava-256 benchmark while running up to 13x faster on an A100 GPU with 8x fewer Gaussians.