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.
By Shikun Zhang, Yong Li, Yiqun Wang, Qiuhong Ke, Cunjian Chen
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...
By Lei Shi, Sen Peng, Zhiyang Deng, Zhonggui Chen, Xiaohu Guo, Baorong Yang, Xiao Dong
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
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.
By Ramazan Fazylov, Sergey Zagoruyko, Aleksandr Parkin, Stamatis Lefkimmiatis, Ivan Laptev
arXiv:2609.38343v1 Announce Type: new
Abstract: We present SInGA, a novel method for learning Semantic Inpainting for animatable Gaussian head Avatars from a single image. Existing avatar approaches...
By Pilseo Park, Fizza Rubab, Yiying Tong
arXiv:2407. 13922v3 Announce Type: replace-cross Abstract: Face recognition (FR) systems are widely deployed in critical applications, making their reliability and robustness across diverse populations and conditions essential.
By Guruprasad Viswanathan Ramesh, Ashish Hooda, Shimaa Ahmed, Harrison J Rosenberg, Ramya Korlakai Vinayak, Kassem Fawaz
Reinforcement learning from human feedback (RLHF) for 3D generation is now established across a number of works, but most existing pipelines optimise explicit surface representations, often by converting radiance fields into meshes and training heavily on surface-supervised data. We instead fine-tune a pretrained 3D-aware generative model directly from a learned reward over radiance-field density ($σ$) values, with no externally supplied mesh or shape prior.
arXiv:2608.23410v1 Announce Type: new
Abstract: Photorealistic novel view synthesis of people remains challenging at high spatial resolutions and across multiple target cameras, where preserving iden...
By Federico Stella, Fei Jiang, Zhongshi Jiang, Zohar Barzelay, Emanuel Garbin, Amin Jourabloo, Liuhao Ge
The paper introduces EC²Face, a multimodal face synthesis framework that enhances semantic alignment by combining Explicit Conditional Consistency Guidance (ECCG) and Long‑Tail Adaptive Flow Matching (LAFM). ECCG enforces pixel‑level consistency between generated faces, textual descriptions, and semantic masks, while a temporal dynamic modulation adjusts supervision strength over diffusion timesteps. LAFM reweights spatial optimization signals according to attribute frequency, improving rare attribute synthesis without adding inference overhead. Experiments demonstrate that EC²Face outperforms baselines, achieving a 29.38% improvement in mask accuracy for rare attributes.
By Yushe Cao, Xuechao Zou, Xing Xi, Dianxi Shi, Chun Yu, Junliang Xing
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
arXiv:2606. 30347v1 Announce Type: cross Abstract: We present FFAvatar, a Transformer-based 3D Gaussian framework for fast construction of high-quality and animatable 4D head avatars from one or more reference portrait images.
By Jianjiang Yao, Ke Xian, Renxiang Dai, Robert Caiming Qiu
arXiv:2609.24158v1 Announce Type: new
Abstract: Reconstructing expressive and relightable 3D head avatars from monocular videos remains challenging in computer vision, as it requires accurate modelin...
By Jiankuo Zhao, Xiangyu Zhu, Jijie Li, Baiqin Wang, Shukai Chen, Zhen Lei