发表机构
Universitat Politècnica de Catalunya; Institut de Robòtica i Informàtica Industrial, CSIC-UPC（加泰罗尼亚理工大学; 工业机器人信息学研究所，CSIC-UPC）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出ManifoldSplat，首个端到端框架，在FLAME流形内编辑3D高斯头像，通过DeltaRegion CVAE实现语言引导的局部形状编辑，保持身份和动画，速度约90秒重建，800 FPS渲染。
AI 中文摘要
高保真3D头部头像已达到近乎照片级真实的质量。尽管近期方法实现了文本驱动的操作，但它们难以提供细粒度的局部控制，常常纠缠特征或缺乏几何一致性。通过自然语言修改几何目前需要缓慢的逐提示优化或牺牲身份和绑定。我们提出了ManifoldSplat，这是第一个用于从单目视频重建的可动画3D高斯溅射头像的语言引导语义形状编辑的端到端框架。通过在结构化的FLAME流形内执行编辑，而不是直接优化非结构化的高斯云，我们严格保留了身份和动画。我们引入了DeltaRegion，一个逐区域解耦的条件变分自编码器（CVAE），提供前馈形状增量，并配有一个细化阶段以恢复视图一致的细节。ManifoldSplat在消费级GPU上约90秒内重建和编辑头像，渲染速度约为800 FPS。广泛评估表明，我们的方法在局部提示对齐、几何一致性和身份保留方面树立了新的最先进水平。项目页面和代码：此https URL
英文摘要
High-fidelity 3D head avatars have reached near-photorealistic quality. While recent methods enable text-driven manipulation, they struggle to provide fine-grained localized control, often entangling features or lacking geometric consistency. Modifying geometry through natural language currently requires slow per-prompt optimization or compromises identity and rigging. We present ManifoldSplat, the first end-toend framework for language-guided semantic shape editing of animatable 3D Gaussian Splatting avatars reconstructed from monocular videos. By performing edits within the structured FLAME manifold rather than directly optimizing an unstructured Gaussian cloud, we strictly preserve identity and animation. We introduce DeltaRegion, a per-region disentangled Conditional Variational Autoencoder (CVAE) delivering feedforward shape deltas, alongside a refining stage to recover view-consistent details. ManifoldSplat reconstructs and edits an avatar in ~90 seconds on a consumer GPU, rendering at ~800 FPS. Extensive evaluations demonstrate our approach sets a new state-of-the-art in localized prompt alignment, geometric coherence, and identity preservation. Project page and code: https://a-canela.github.io/manifoldsplat/
CommentsGCPR 2026
