paper-with-me

Papers

MoDiT: Learning Highly Consistent 3D Motion Coefficients with Diffusion Transformer for Talking Head Generation

2025-07-07 · Yucheng Wang, Dan Xu arxiv

Audio-driven talking head generation is critical for applications such as virtual assistants, video games, and films, where natural lip movements are essential. Despite progress in this field, challenges remain in producing both consistent and realistic facial animations. Existing methods, often based on GANs or UNet-based diffusion models, face three major limitations: (i) temporal jittering caused by weak temporal constraints, resulting in frame inconsistencies; (ii) identity drift due to insufficient 3D information extraction, leading to poor preservation of facial identity; and (iii) unnatural blinking behavior due to inadequate modeling of realistic blink dynamics. To address these issues, we propose MoDiT, a novel framework that combines the 3D Morphable Model (3DMM) with a Diffusion-based Transformer. Our contributions include: (i) A hierarchical denoising strategy with revised temporal attention and biased self/cross-attention mechanisms, enabling the model to refine lip synchronization and progressively enhance full-face coherence, effectively mitigating temporal jittering. (ii) The integration of 3DMM coefficients to provide explicit spatial constraints, ensuring accurate 3D-informed optical flow prediction and improved lip synchronization using Wav2Lip results, thereby preserving identity consistency. (iii) A refined blinking strategy to model natural eye movements, with smoother and more realistic blinking behaviors.

📄 PDF Abstract BibTeX arXiv:2507.05092

Code (0)

등록된 구현이 없습니다.

Tasks

Talking Head GenerationInformation Extraction

Similar Papers 제목 키워드 기반

MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation

2024-03-28 · Seyeon Kim, Siyoon Jin, JiHye Park, Kihong Kim 외

Conventional GAN-based models for talking head generation often suffer from limited quality and unstable training. Recent approaches based on diffusion models aimed to address these limitations and improve fidelity. Howe…

Talking Head Generation

Local Analysis of Heterogeneous Intracellular Transport: Slow and Fast moving Endosomes

2021-07-24 · Nickolay Korabel, Daniel Han, Alessandro Taloni, Gianni Pagnini 외

Trajectories of endosomes inside living eukaryotic cells are highly heterogeneous in space and time and diffuse anomalously due to a combination of viscoelasticity, caging, aggregation and active transport. Some of the t…

FD2Talk: Towards Generalized Talking Head Generation with Facial Decoupled Diffusion Model

2024-08-18 · Ziyu Yao, Xuxin Cheng, Zhiqi Huang

Talking head generation is a significant research topic that still faces numerous challenges. Previous works often adopt generative adversarial networks or regression models, which are plagued by generation quality and a…

Talking Head Generation

Consistent and Controllable Image Animation with Motion Diffusion Models

2025-01-01 · CVPR 2025 1 · Xin Ma, Yaohui Wang, Gengyun Jia, Xinyuan Chen 외

Diffusion models have achieved significant progress in the task of image animation due to their powerful generative capabilities. However, preserving appearance consistency to the static input image, and avoiding abr…

Image AnimationVideo Editing

Unravelling Heterogeneous Transport of Endosomes

2021-07-16 · Nickolay Korabel, Daniel Han, Alessandro Taloni, Gianni Pagnini 외

A major open problem in biophysics is to understand the highly heterogeneous transport of many structures inside living cells, such as endosomes. We find that mathematically it is described by spatio-temporal heterogeneo…