PAGE: Parts-Aware Guidance for Co-Speech Gesture Portrait Video Generation

cs.CV

Submitted: 2026-10-09

Updated: 2026-10-09

Comments: Accepted to IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) 2026. Project page: https://aigc-explorer.github.io/PAGE/

DOI: 10.1109/TCSVT.2026.3738661

Project page: https://aigc-explorer.github.io/PAGE

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control
• AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
• HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
• Wan: Open and Advanced Large-Scale Video Generative Models
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• Towards Accurate Generative Models of Video: A New Metric & Challenges
• EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation
• OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation
• DINOv3
• MediaPipe: A Framework for Building Perception Pipelines
• PaddleOCR 3.0 Technical Report

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models