Related papers: FlashLips: 100-FPS Mask-Free Latent Lip-Sync using…
We propose LayerSync, a domain-agnostic approach for improving the generation quality and the training efficiency of diffusion models. Prior studies have highlighted the connection between the quality of generation and the representations…
Virtual humans have gained considerable attention in numerous industries, e.g., entertainment and e-commerce. As a core technology, synthesizing photorealistic face frames from target speech and facial identity has been actively studied…
Text-guided image editing with diffusion models has achieved remarkable quality but often suffers from prohibitive latency. We introduce \textbf{FlashEdit}, a real-time localized image editing framework for the standard inversion-based…
Speech-driven facial animation is the process which uses speech signals to automatically synthesize a talking character. The majority of work in this domain creates a mapping from audio features to visual features. This often requires…
Lip synchronization and audio-visual editing have emerged as fundamental challenges in multimodal learning, underpinning a wide range of applications, including film production, virtual avatars, and telepresence. Despite recent progress,…
We propose Fast Language-Audio Pre-training (FLAP), a self-supervised approach that efficiently and effectively learns aligned audio and language representations through masking, contrastive learning and reconstruction. For efficiency, FLAP…
We propose a novel method for generating high-resolution videos of talking-heads from speech audio and a single 'identity' image. Our method is based on a convolutional neural network model that incorporates a pre-trained StyleGAN…
Lipreading is an impressive technique and there has been a definite improvement of accuracy in recent years. However, existing methods for lipreading mainly build on autoregressive (AR) model, which generate target tokens one by one and…
Creating a realistic animatable avatar from a single static portrait remains challenging. Existing approaches often struggle to capture subtle facial expressions, the associated global body movements, and the dynamic background. To address…
Real-time speech synthesis requires balancing inference latency and acoustic fidelity for interactive applications. Conventional continuous text-to-speech pipelines require computationally intensive neural vocoders to reconstruct phase…
Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However,…
Realistic, high-fidelity 3D facial animations are crucial for expressive avatar systems in human-computer interaction and accessibility. Although prior methods show promising quality, their reliance on the mesh domain limits their ability…
The challenge of talking face generation from speech lies in aligning two different modal information, audio and video, such that the mouth region corresponds to input audio. Previous methods either exploit audio-visual representation…
We present Free-HeadGAN, a person-generic neural talking head synthesis system. We show that modeling faces with sparse 3D facial landmarks are sufficient for achieving state-of-the-art generative performance, without relying on strong…
In this paper, we propose a talking face generation method that takes an audio signal as input and a short target video clip as reference, and synthesizes a photo-realistic video of the target face with natural lip motions, head poses, and…
We aim to edit the lip movements in talking video according to the given speech while preserving the personal identity and visual details. The task can be decomposed into two sub-problems: (1) speech-driven lip motion generation and (2)…
Recently, there has been numerous breakthroughs in face hallucination tasks. However, the task remains rather challenging in videos in comparison to the images due to inherent consistency issues. The presence of extra temporal dimension in…
Lip motion reflects behavior characteristics of speakers, and thus can be used as a new kind of biometrics in speaker recognition. In the literature, lots of works used two-dimensional (2D) lip images to recognize speaker in a textdependent…
Normalization layers are ubiquitous in large language models (LLMs) yet represent a compute bottleneck: on hardware with distinct vector and matrix execution units, the RMS calculation blocks the subsequent matrix multiplication, preventing…
While the recent advances in research on video reenactment have yielded promising results, the approaches fall short in capturing the fine, detailed, and expressive facial features (e.g., lip-pressing, mouth puckering, mouth gaping, and…