{"total":89,"rows":[{"id":"2402.17485","title":"EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions","created":"2024-02-27","cited_by_count":235,"area":"diffusion"},{"id":"2403.17694","title":"AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation","created":"2024-03-26","cited_by_count":194,"area":null},{"id":"2311.17590","title":"SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis","created":"2023-11-29","cited_by_count":86,"area":null},{"id":"2504.04842","title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","created":"2025-04-07","cited_by_count":77,"area":null},{"id":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66,"area":null},{"id":"2412.09262","title":"LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision","created":"2024-12-12","cited_by_count":56,"area":"diffusion"},{"id":"2311.18729","title":"Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data","created":"2023-11-30","cited_by_count":55,"area":null},{"id":"2403.08764","title":"VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis","created":"2024-03-13","cited_by_count":50,"area":"diffusion"},{"id":"2408.06019","title":"HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priors","created":"2024-08-12","cited_by_count":44,"area":null},{"id":"2508.08248","title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation","created":"2025-08-11","cited_by_count":44,"area":"diffusion"},{"id":"2412.01064","title":"FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait","created":"2024-12-02","cited_by_count":40,"area":"diffusion"},{"id":"2412.04037","title":"INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations","created":"2024-12-05","cited_by_count":40,"area":null},{"id":"2401.15668","title":"Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes","created":"2024-01-28","cited_by_count":32,"area":null},{"id":"2405.20851","title":"MegActor: Harness the Power of Raw Video for Vivid Portrait Animation","created":"2024-05-31","cited_by_count":28,"area":null},{"id":"2410.10122","title":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","created":"2024-10-14","cited_by_count":28,"area":null},{"id":"2505.21448","title":"OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers","created":"2025-05-27","cited_by_count":27,"area":"diffusion"},{"id":"2509.03883","title":"Human Motion Video Generation: A Survey","created":"2025-09-04","cited_by_count":25,"area":null},{"id":"2410.10696","title":"TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model","created":"2024-10-14","cited_by_count":19,"area":"diffusion"},{"id":"2601.00664","title":"Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation","created":"2026-01-02","cited_by_count":19,"area":null},{"id":"2504.02542","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","created":"2025-04-03","cited_by_count":17,"area":"diffusion"},{"id":"2312.09767","title":"DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models","created":"2023-12-15","cited_by_count":16,"area":"diffusion"},{"id":"2408.03284","title":"ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer","created":"2024-08-06","cited_by_count":16,"area":null},{"id":"2503.05978","title":"MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice","created":"2025-03-07","cited_by_count":16,"area":"diffusion"},{"id":"2311.18168","title":"Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications","created":"2023-11-30","cited_by_count":15,"area":null},{"id":"2409.05379","title":"PersonaTalk: Bring Attention to Your Persona in Visual Dubbing","created":"2024-09-09","cited_by_count":15,"area":null},{"id":"2403.17217","title":"DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment","created":"2024-03-25","cited_by_count":14,"area":"diffusion"},{"id":"2406.18284","title":"RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment Network","created":"2024-06-26","cited_by_count":14,"area":null},{"id":"2506.00830","title":"SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers","created":"2025-06-01","cited_by_count":14,"area":"diffusion"},{"id":"2507.01390","title":"FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases","created":"2025-07-02","cited_by_count":14,"area":null},{"id":"2307.09368","title":"Audio-driven Talking Face Generation with Stabilized Synchronization Loss","created":"2023-07-18","cited_by_count":13,"area":null},{"id":"2408.14975","title":"MegActor-$\\Sigma$: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer","created":"2024-08-27","cited_by_count":13,"area":"diffusion"},{"id":"2502.11515","title":"SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusion","created":"2025-02-17","cited_by_count":12,"area":"diffusion"},{"id":"2505.00497","title":"KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution","created":"2025-05-01","cited_by_count":11,"area":null},{"id":"2601.10103","title":"FlowAct-R1: Towards Interactive Humanoid Video Generation","created":"2026-01-15","cited_by_count":11,"area":null},{"id":"2309.07509","title":"DiffTalker: Co-driven audio-image diffusion for talking faces via intermediate landmarks","created":"2023-09-14","cited_by_count":10,"area":"diffusion"},{"id":"2503.19824","title":"AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers","created":"2025-03-25","cited_by_count":10,"area":"diffusion"},{"id":"2504.04010","title":"DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion","created":"2025-04-05","cited_by_count":10,"area":"diffusion"},{"id":"2504.02433","title":"OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking","created":"2025-04-03","cited_by_count":9,"area":null},{"id":"2506.14742","title":"SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting","created":"2025-06-17","cited_by_count":9,"area":null},{"id":"2406.08096","title":"Make Your Actor Talk: Generalizable and High-Fidelity Lip Sync with Motion and Appearance Disentanglement","created":"2024-06-12","cited_by_count":7,"area":null},{"id":"2509.18924","title":"Audio-Driven Universal Gaussian Head Avatars","created":"2025-09-23","cited_by_count":7,"area":null},{"id":"2601.22143","title":"JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2409.07255","title":"EMOdiffhead: Continuously Emotional Control in Talking Head Generation via Diffusion","created":"2024-09-11","cited_by_count":6,"area":null},{"id":"2503.14295","title":"PC-Talk: Precise Facial Animation Control for Audio-Driven Talking Face Generation","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2502.17198","title":"Dimitra: Audio-driven Diffusion model for Expressive Talking Head Generation","created":"2025-02-24","cited_by_count":4,"area":"diffusion"},{"id":"2504.21497","title":"MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance","created":"2025-04-30","cited_by_count":4,"area":"diffusion"},{"id":"2311.06772","title":"ChatAnything: Facetime Chat with LLM-Enhanced Personas","created":"2023-11-12","cited_by_count":3,"area":null},{"id":"2312.05572","title":"R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning","created":"2023-12-09","cited_by_count":3,"area":null},{"id":"2401.06126","title":"Dubbing for Everyone: Data-Efficient Visual Dubbing using Neural Rendering Priors","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2406.14176","title":"A Multi-Stream Fusion Approach with One-Class Learning for Audio-Visual Deepfake Detection","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2408.01627","title":"JambaTalk: Speech-Driven 3D Talking Head Generation Based on Hybrid Transformer-Mamba Model","created":"2024-08-03","cited_by_count":3,"area":"ssm"},{"id":"2503.09942","title":"Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers","created":"2025-03-13","cited_by_count":3,"area":"diffusion"},{"id":"2512.25066","title":"From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2309.01950","title":"RADIO: Reference-Agnostic Dubbing Video Synthesis","created":"2023-09-05","cited_by_count":2,"area":null},{"id":"2312.07669","title":"GMTalker: Gaussian Mixture-based Audio-Driven Emotional Talking Video Portraits","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2409.00971","title":"Interpretable Convolutional SyncNet","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2506.16852","title":"Controllable and Expressive One-Shot Video Head Swapping","created":"2025-06-20","cited_by_count":2,"area":null},{"id":"2512.21736","title":"SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild","created":"2025-12-25","cited_by_count":2,"area":null},{"id":"2601.22127","title":"EditYourself: Audio-Driven Generation and Manipulation of Talking Head Videos with Diffusion Transformers","created":"2026-01-29","cited_by_count":2,"area":"diffusion"},{"id":"2307.10636","title":"Learning and Evaluating Human Preferences for Conversational Head Generation","created":"2023-07-20","cited_by_count":1,"area":null},{"id":"2503.13371","title":"SyncDiff: Diffusion-based Talking Head Synthesis with Bottlenecked Temporal Visual Prior for Improved Synchronization","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2505.22141","title":"FaceEditTalker: Controllable Talking Head Generation with Facial Attribute Editing","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2505.23406","title":"Video Editing for Audio-Visual Dubbing","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.20953","title":"Mask-Free Audio-driven Talking Face Generation for Enhanced Visual Quality and Identity Preservation","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2508.20615","title":"EmoCAST: Emotional Talking Portrait via Emotive Text Description","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2602.09534","title":"AUHead: Realistic Emotional Talking Head Generation via Action Units Control","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2602.09736","title":"Toward Fine-Grained Facial Control in 3D Talking Head Generation","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.23132","title":"InterDyad: Interactive Dyadic Speech-to-Video Generation by Querying Intermediate Visual Guidance","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.19129","title":"PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2608.18832","title":"EfficientSync: Real-Time Lip Synchronization via Deformation-Based Reference Texture Mixing","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2404.14667","title":"3DFlowRenderer: One-shot Face Re-enactment via Dense 3D Facial Flow Estimation","created":"2024-04-23","cited_by_count":0,"area":null},{"id":"2405.05636","title":"SwapTalk: Audio-Driven Talking Face Generation with One-Shot Customization in Latent Space","created":"2024-05-09","cited_by_count":0,"area":null},{"id":"2507.03256","title":"MoDA: Multi-modal Diffusion Architecture for Talking Head Generation","created":"2025-07-04","cited_by_count":0,"area":"diffusion"},{"id":"2507.08307","title":"M2DAO-Talker: Harmonizing Multi-granular Motion Decoupling and Alternating Optimization for Talking-head Generation","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2507.20987","title":"JWB-DH-V1: Benchmark for Joint Whole-Body Talking Avatar and Speech Generation Version 1","created":"2025-07-28","cited_by_count":0,"area":"diffusion"},{"id":"2508.08891","title":"Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2508.18337","title":"Warm Chat: Diffuse Emotion-aware Interactive Talking Head Avatar with Tree-Structured Guidance","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2509.21887","title":"StableDub: Taming Diffusion Prior for Generalized and Efficient Visual Dubbing","created":"2025-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2511.22488","title":"AI killed the video star. Audio-driven diffusion model for expressive talking head generation","created":"2025-11-27","cited_by_count":0,"area":"diffusion"},{"id":"2512.20033","title":"FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2601.22501","title":"MIRRORTALK: Forging Personalized Avatars Via Disentangled Style and Hierarchical Motion Control","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.00189","title":"LPIPS-AttnWav2Lip: Generic Audio-Driven lip synchronization for Talking Head Generation in the Wild","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.09883","title":"DISPLAY: Directable Human-Object Interaction Video Generation via Sparse Motion Guidance and Multi-Task Auxiliary","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.23325","title":"EAD-Net: Emotion-Aware Talking Head Generation with Spatial Refinement and Temporal Coherence","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.16918","title":"HighSync: High-Quality Lip Synchronization via Latent Diffusion Models","created":"2026-05-16","cited_by_count":0,"area":"diffusion"},{"id":"2605.25488","title":"Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.02474","title":"EchoCache: Energy-Guided Cross-Modal Caching for Efficient Audio-Driven Video Generation","created":"2026-08-03","cited_by_count":0,"area":"diffusion"},{"id":"2609.18632","title":"VibeAvatar: Aligning Phonetic Kinematics and Human Aesthetics for High-Fidelity Talking Avatar Synthesis","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.29225","title":"ComplexSync: High-Fidelity and Real-Time Lip Sync in Complex Scenarios","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}