paper-with-me

Talking Head Generation

7개 벤치마크 · 논문 159편 · 이 태스크의 논문 보기 →

Benchmarks

Most implemented

Papers

Decoupled Self-Forcing Distillation for Streaming Talking Head Generation

2026-09-09 · Yanru An, Ruiyan Wang, Wenwu Wei, Rui Bu 외 arxiv

Streaming talking-head generation produces each frame as its driving audio arrives, yet fidelity and efficiency have so far pulled in opposite directions: end-to-end methods condition a video diffusion model on audio dir…

Talking Head Generation

LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation

2026-07-29 · Rongxiang Zhang, Songhua Liu hf

Long-form and real-time talking-head generation remains challenging due to a latency-quality trade-off: inefficient multi-step diffusion prohibits streaming generation, whereas real-time autoregressive approaches suffer …

Talking Head GenerationVideo Generation

Temporally-Aligned Evaluation for Audio-Driven Talking Head Generation

2026-05-31 · Zhicheng Zhang, Lei Wang, Yu Zhang, Yongsheng Gao arxiv

Audio-driven talking-head generation has advanced rapidly, yet existing evaluation protocols mainly rely on frame-wise metrics that assume strict temporal correspondence between generated and reference videos. This assum…

Talking Head Generation

CapTalk: Text-Guided Stylization and Speech-Driven 3D Head Animation

2026-05-28 · Xuangeng Chu, Yuan Gan, Ziteng Cui, Shuhong Liu 외 arxiv

Audio-driven 3D facial animation aims to generate synchronized lip movements and vivid facial expressions from arbitrary audio clips. While existing methods can produce synchronized lip motions, they often rely on predef…

Talking Head Generation

MoCoTalk: Multi-Conditional Diffusion with Adaptive Router for Controllable Talking Head Generation

2026-05-08 · Xinyan Ye, Jiankang Deng, Abbas Edalat arxiv

Talking-head generation requires joint modeling of identity, head pose, facial expression, and mouth dynamics. Existing methods typically address only a subset of these factors, and rely on fixed-weight or heuristic fusi…

Talking Head Generation

AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation

2026-05-01 · Yuxin Lu, Jiayang Sun, Guibo Zhu, Min Cao arxiv

Diffusion-based talking head generation has achieved remarkable visual quality, yet scaling it to long-term videos remains challenging. The widely adopted chunk-wise paradigm introduces two fundamental failures: (1) temp…

Talking Head GenerationKnowledge Distillation

전체 159편 보기 →