← Back to all news
arXiv Computer Vision By Shikun Zhang, Yong Li, Yiqun Wang, Qiuhong Ke, Cunjian Chen

Fresco++: Frequency-Guided and Canonical-Consistent Optimization for Fine-Grained Head Avatar Modeling

Read the original on arXiv Computer Vision →

Fresco++ is a unified optimization framework for fine‑grained, view‑consistent head avatar reconstruction. It uses a frequency‑guided curriculum that first stabilizes low‑frequency structures before adding high‑frequency constraints, and a Canonical Group Consensus that links local observations across viewpoints to enforce cross‑view consistency. The method incorporates geometric and visibility screening and aggregates multi‑view evidence in feature space, achieving stable optimization from coarse to fine details without extra rendering of auxiliary views.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Oct 19

OMEGA-Avatar: One-shot Modeling of 360{\deg} Gaussian Avatars

OMEGA-Avatar is a feed‑forward framework that creates a 360° complete, animatable 3D Gaussian head from a single image. It introduces a semantic‑aware mesh deformation module to improve hair modeling while preserving topology, and a multi‑view feature splatting module that builds a shared canonical UV representation for consistent, high‑frequency detail across all viewpoints. Experiments show it outperforms existing baselines in full‑head completeness and identity preservation.

By Zehao Xia, Yiqun Wang, Zhengda Lu, Kai Liu, Jun Xiao, Peter Wonka
benchmarks
More like this →
arXiv Machine Learning
Oct 9

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

GHARP is a two‑stage method that animates 3D human heads in real time using a large‑scale reconstruction prior. The first offline identity stage builds a compact Gaussian representation of a subject’s geometry and appearance, while the lightweight runtime animation stage predicts expression‑dependent residuals in a semantically structured latent space. A body alignment network further refines the animation by aligning body pose and clothing, enabling state‑of‑the‑art quality on the Ava‑256 benchmark with significantly faster performance and fewer Gaussians.

By Ali Benlalah, Sepehr Johari, Patricia Vitoria, Armin Kappeler, Artem Sevastopolsky, Alexander Jung, Gabriele Fanelli, Kevin Mader, Manuel Breitenstein, Claudia Pl\"uss, Jan R\"uegg, Simon Biland, Thomas Etterlin, Dmitry Kostiaev, Mathias Deschler, Brian Amberg, Sebastian Martin
diffusionbenchmarkssafety
More like this →