paper-with-me

Papers

Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model

2025-02-13 · Fei Shen, Cong Wang, Junyao Gao, Qin Guo, Jisheng Dang, Jinhui Tang, Tat-Seng Chua

Recent advances in conditional diffusion models have shown promise for generating realistic TalkingFace videos, yet challenges persist in achieving consistent head movement, synchronized facial expressions, and accurate lip synchronization over extended generations. To address these, we introduce the \textbf{M}otion-priors \textbf{C}onditional \textbf{D}iffusion \textbf{M}odel (\textbf{MCDM}), which utilizes both archived and current clip motion priors to enhance motion prediction and ensure temporal consistency. The model consists of three key elements: (1) an archived-clip motion-prior that incorporates historical frames and a reference frame to preserve identity and context; (2) a present-clip motion-prior diffusion model that captures multimodal causality for accurate predictions of head movements, lip sync, and expressions; and (3) a memory-efficient temporal attention mechanism that mitigates error accumulation by dynamically storing and updating motion features. We also release the \textbf{TalkingFace-Wild} dataset, a multilingual collection of over 200 hours of footage across 10 languages. Experimental results demonstrate the effectiveness of MCDM in maintaining identity and motion continuity for long-term TalkingFace generation. Code, models, and datasets will be publicly available.

📄 PDF Abstract BibTeX arXiv:2502.09533

Code (0)

등록된 구현이 없습니다.

Tasks

motion prediction

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Talking-head Generation with Rhythmic Head Motion

2020-07-16 · Lele Chen, Guofeng Cui, Celong Liu, Zhong Li 외

When people deliver a speech, they naturally move heads, and this rhythmic head motion conveys prosodic information. However, generating a lip-synced video while moving head naturally is challenging. While remarkably suc…

Talking Head Generation

Hybrid eye center localization using cascaded regression and hand-crafted model fitting

2017-12-07 · Alex Levinshtein, Edmund Phung, Parham Aarabi

We propose a new cascaded regressor for eye center detection. Previous methods start from a face or an eye detector and use either advanced features or powerful regressors for eye center localization, but not both. Inste…

regression

Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation

2025-06-20 · Xiuyu Yang, Shuhan Tan, Philipp Krähenbühl

An ideal traffic simulator replicates the realistic long-term point-to-point trip that a self-driving system experiences during deployment. Prior models and benchmarks focus on closed-loop motion simulation for initial a…

Scene Generation

Cross-Conditioned Recurrent Networks for Long-Term Synthesis of Inter-Person Human Motion Interactions

2020-05-14 · IEEE Winter Conference on Applications of Computer Vision (WACV) 2020 5 · Jogendra Nath Kundu, Himanshu Buckchash, Priyanka Mandikal, Anirudh Jamkhandi 외

Modeling dynamics of human motion is one of the most challenging sequence modeling problem, with diverse applications in animation industry, human-robot interaction, motion-based surveillance, etc. Available attempts to …

DecoderMotion Generationmotion predictionMotion Synthesis+1

T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences

2024-06-02 · Taeryung Lee, Fabien Baradel, Thomas Lucas, Kyoung Mu Lee 외

In this paper, we address the challenging problem of long-term 3D human motion generation. Specifically, we aim to generate a long sequence of smoothly connected actions from a stream of multiple sentences (i.e., paragra…

Action GenerationDecoderMotion Generation