arXiv Machine Learning
GHARP: Real-time Gaussian Head Animation from Large-scale Reconstruction Prior
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 2
One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars
The paper introduces GALA, a distillation technique that replaces costly neural decoding in 3D Gaussian avatars with a shallow MLP predicting blendshape coefficients, enabling real‑time animation. By constructing a basis via block‑local PCA under a rendering‑aware metric, GALA achieves high fidelity while reducing memory usage. Experiments on three avatar models show up to three orders of magnitude lower CPU cost and frame rates up to 60fps on mobile devices.
arXiv Computer Vision
Sep 18
AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars
AGORA is a new framework that extends 3D Gaussian Splatting with a generative adversarial network to produce high‑fidelity, animatable 3D head avatars. It introduces a lightweight FLAME‑conditioned deformation branch that predicts per‑Gaussian residuals for identity‑preserving, fine‑grained expression control, and a dual‑discriminator training scheme that enforces expression fidelity. The system achieves real‑time inference at 250 FPS on a single GPU and, for the first time, CPU‑only animatable 3DGS avatar synthesis at ~9 FPS.
arXiv Computer Vision
Sep 14
MGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modeling
arXiv:2609.12850v1 Announce Type: new Abstract: Accurate head modeling requires a stable yet expressive geometric representation. Existing Gaussian-based head avatars commonly rely on parametric temp...
arXiv Computer Vision
Aug 21
AvatarDynamizer: From Static to Dynamic Human Avatars via Generative Dynamic Textures
arXiv:2608. 19900v1 Announce Type: new Abstract: For full-body avatars, modeling surface dynamics is crucial for overcoming the uncanny valley and achieving perceptual realism.
arXiv Computer Vision
Sep 11
DirectSwap: Paired, Mask-Free Video Head Swapping with Full-Reference Evaluation
The paper introduces DirectSwap, a mask‑free video head‑swapping method that leverages a newly created cross‑identity paired dataset, HeadSwapBench. By synthesizing expression‑synchronized video pairs from real footage, the authors provide frame‑aligned ground truth for full‑reference evaluation of identity, expression, pose, reconstruction fidelity, and temporal stability. DirectSwap outperforms traditional same‑identity masked reconstruction, especially when head silhouettes change, and can restore non‑head content without external segmentation.
Hugging Face Trending Papers
Aug 20
AvatarDynamizer: From Static to Dynamic Human Avatars via Generative Dynamic Textures
For full-body avatars, modeling surface dynamics is crucial for overcoming the uncanny valley and achieving perceptual realism. Person-agnostic methods recover static 3D avatars from monocular images, videos, or text prompts, but their skeleton-driven animations lack realistic surface dynamics such as clothing wrinkles.