PHAF-Personalized Hand Avatars in a Flash

Meghana Shankar; Akanxit Upadhyay; Anmol Namdev; Green Rosh KS; Pawan Prasad BH

cs.CVJun 2, 2026

PHAF-Personalized Hand Avatars in a Flash

Authors: Meghana Shankar, Akanxit Upadhyay, Anmol Namdev, Green Rosh KS, Pawan Prasad BH

Abstract

We present PHAF-Personalized Hand Avatars in a Flash, a personalized photo-realistic hand avatar which provides high quality multi-view renders from just two images (dorsal and palmar views).Unlike slow optimization-based techniques, PHAF generates fast personalized textures for real-time deployment on edge devices. Our approach combines semantic guided mesh alignment and densified texture extraction to transfer high-frequency details efficiently. A view-based inpainting network refines textures ensuring smooth, continuous appearance. PHAF generalizes to novel viewpoints and leverages a parametric hand model for accurate articulations, making it compatible with standard graphics engines. Experiments show it is comparable to existing methods in visual fidelity while drastically reducing texture generation time by 30 times, enabling practical AR/VR applications.

Explore similar work

FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction
May 14, 2026Thuan Hoang Nguyen, Jiahao Luo, Yinyu Nie +3Animatable 3D Human Avatars Avatars
Generative Relightable Avatars
Jun 21, 2026Kunwar Maheep Singh, Christian Theobalt, Rishabh DabralAvatars Image Relighting
High-Fidelity Mobile Avatars with Pruned Local Blendshapes
May 3, 2026Youyi Zhan, He Wang, Tianjia Shao +1Animatable 3D Human Avatars Avatars

May 14, 2026 · cs.GRJ/K move · Enter open · S save

FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction

Thuan Hoang Nguyen, Jiahao Luo, Yinyu Nie, Hao Li+2

Snap Inc. · MBZUAI · University of California, Santa Cruz

Avatar reconstruction has traditionally relied on per-subject optimization that requires hours of computation or on expensive preprocessing that limits scalability. We introduce FFAvatar, a generalizable feed-forward framework that reconstructs high-quality, animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds. FFAvatar fuses information from multiple source images into a unified canonical Gaussian representation through Multi-View Query-Former, which is animated via FLAME parameters predicted end-to-end directly from pixels, eliminating the overhead of offline FLAME extraction. We further propose a three-stage training curriculum that achieves both broad generalization and high-fidelity reconstruction: (i) scalable pretraining on extensive monocular video data with over 1M identities to learn strong generalizable priors; (ii) multi-view fine-tuning on a small but high-quality dataset of 360-degree captures to enhance geometric fidelity and extreme-view awareness; and (iii) optional personalization that adapts to specific identities for maximum fidelity within 500 optimization steps. Extensive experiments demonstrate that FFAvatar sets a new standard for identity preservation, geometric consistency, and animation fidelity. On the NeRSemble benchmark, it outperforms the state-of-the-art LAM by a substantial 5.5 PSNR gain. Furthermore, FFAvatar enables real-time deployment, reconstructing avatars in 2 seconds without personalization and 10 seconds with personalization, while supporting 49 FPS animation on a single NVIDIA A100 GPU.

Animatable 3D Human Avatars Avatars Visual Fidelity Feed-Forward

Open paper Ask about it PDF

Abstract

Explore similar work

FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction

Generative Relightable Avatars

High-Fidelity Mobile Avatars with Pruned Local Blendshapes