FlashLips：基于重建而非扩散或 GAN 的 100 FPS 免掩码潜空间唇形同步
FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs
用纯重建损失的单步潜空间编辑器替代 GAN/扩散做唇形编辑，并以嘴部篡改变体自监督生成伪真值来免除推理期 mask，这套「重建式编辑 + 伪标签定位」思路可迁移到其他局部可控编辑任务。
原文依据 trained purely with reconstruction losses - no GANs or diffusion
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 FlashLips，一个两阶段、免掩码的唇形同步系统，它将嘴唇控制与渲染解耦并实现实时性能，其 U-Net 变体在单块 GPU 上运行速度超过 100 FPS，同时达到更大规模最优模型的视觉质量。第一阶段是一个紧凑的单步潜空间编辑器，它利用参考身份、掩码目标帧和低维嘴唇姿态向量重建图像，仅用重建损失训练——不使用 GAN 或扩散。为在推理时去除显式掩码，我们通过嘴部篡改的目标变体作为伪真值进行自监督，教会网络在保留其余部分的同时定位嘴唇编辑区域。第二阶段是一个音频到姿态的 Transformer，以流匹配目标训练，从语音预测嘴唇姿态向量。这两个阶段共同构成一个简单而稳定的流水线，将确定性重建与稳健的音频控制相结合，提供高感知质量和快于实时的速度。
英文原文摘要 1014 字符
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.