Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses

cs.CV, cs.CR

Submitted: 2026-10-06

Updated: 2026-10-06

Comments: 24 pages, Accepted at ICML 2026

Code: https://github.com/AnsonShe/LipDA

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

Sources

• OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation
• LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision
• DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models
• A Comprehensive Taxonomy and Analysis of Talking Head Synthesis: Techniques for Portrait Generation, Driving Mechanisms, and Editing
• OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers
• Wan: Open and Advanced Large-Scale Video Generative Models
• V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation
• Latent Image Animator: Learning to Animate Images via Latent Space Navigation
• TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detection
• Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
• Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait
• InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing

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