FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs

arXiv:2512.20033v2 Announce Type: replace Abstract: We present FlashLips, a two-stage, mask-free lip-sync system that decouples lips control from rendering and achieves real-time performance, with our U-Net variant running at over 100 FPS on a single GPU, while matching the visual quality of larger state-of-the-art models. Stage 1 is a compact, one-step latent-space editor that reconstructs an image using a reference identity, a masked target frame, and a low-dimensional lips-pose vector, trained purely with reconstruction losses - no GANs or diffusion. To remove explicit masks at inference, we use self-supervision via mouth-altered target variants as pseudo ground truth, teaching the network to localize lip edits while preserving the rest. Stage 2 is an audio-to-pose transformer trained with a flow-matching objective to predict lips-pose vectors from speech. Together, these stages form a simple and stable pipeline that combines deterministic reconstruction with robust audio control, delivering high perceptual quality and faster-than-real-time speed.

Related

• Streaming Video Instruction Tuning
• Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
• Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration
• CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference
• Splats under Pressure: Exploring Performance-Energy Trade-offs in Real-Time 3D Gaussian Splatting under Constrained GPU Budgets

Source: arXiv cs.CV | 2026-04-13