---
format: "aidr-story-markdown/v1"
id: "13747e6775fbfd487c23a07a131b8d0aacb631ca6ceb266b7779d6b1ec5c0ca3"
canonical_url: "https://aidr.today/13747e67?lang=en"
title: "GHARP: Real-Time Gaussian Head Animation from Large-Scale Reconstruction Prior"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-26T00:00:00.000Z"
category: "Research"
topics: ["inference"]
source_urls: ["https://machinelearning.apple.com/research/gharp-head-animation"]
summary: "Researchers introduced GHARP, a method for real-time 3D human head animation using a two-stage approach that separates identity reconstruction from runtime expression-driven animation."
---

# GHARP: Real\-Time Gaussian Head Animation from Large\-Scale Reconstruction Prior

> [Open the canonical story](<https://aidr.today/13747e67?lang=en>)

**Published:** 2026-10-26T00:00:00.000Z
**Category:** Research
**Topics:** inference

## Summary

Researchers introduced GHARP, a method for real\-time 3D human head animation using a two\-stage approach that separates identity reconstruction from runtime expression\-driven animation\.

## Sources

- [Story source](<https://machinelearning.apple.com/research/gharp-head-animation>)