InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:BDLX2L7Frecord.jsonopen to challenge →
read the original abstract
Recent breakthroughs in video AIGC have ushered in a transformative era for audio-driven human animation. However, conventional video dubbing techniques remain constrained to mouth region editing, resulting in discordant facial expressions and body gestures that compromise viewer immersion. To overcome this limitation, we introduce sparse-frame video dubbing, a novel paradigm that strategically preserves reference keyframes to maintain identity, iconic gestures, and camera trajectories while enabling holistic, audio-synchronized full-body motion editing. Through critical analysis, we identify why naive image-to-video models fail in this task, particularly their inability to achieve adaptive conditioning. Addressing this, we propose InfiniteTalk, a streaming audio-driven generator designed for infinite-length long sequence dubbing. This architecture leverages temporal context frames for seamless inter-chunk transitions and incorporates a simple yet effective sampling strategy that optimizes control strength via fine-grained reference frame positioning. Comprehensive evaluations on HDTF, CelebV-HQ, and EMTD datasets demonstrate state-of-the-art performance. Quantitative metrics confirm superior visual realism, emotional coherence, and full-body motion synchronization.
This paper has not been read by Pith yet.
Forward citations
Cited by 13 Pith papers
-
AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation
AsymTalker maintains identity consistency in long-term diffusion talking-head videos by encoding temporal references from a static image and training a student model under inference-like conditions via asymmetric dist...
-
JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion
JUST-DUB-IT adapts a joint audio-visual diffusion model via LoRA to generate high-quality dubbed videos with translated audio and lip-synced facial motion.
-
AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation
AsymK-Talker introduces kernel-conditioned loop generation, temporal reference encoding, and asymmetric kernel distillation to achieve real-time, drift-resistant talking head synthesis from audio using diffusion models.
-
AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation
AsymTalker uses temporal reference encoding and asymmetric knowledge distillation to produce identity-consistent talking head videos up to 600 seconds long at 66 FPS.
-
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
CoInteract adds a human-aware mixture-of-experts and spatially-structured co-generation to a diffusion transformer to synthesize videos with stable structures and physically plausible human-object contacts.
-
OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation
OmniHuman is a new large-scale multi-scene dataset with video-, frame-, and individual-level annotations for human-centric video generation, accompanied by the OHBench benchmark that adds metrics aligned with human pe...
-
OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation
A large-scale, hierarchically-annotated human-centric video dataset and a three-level benchmark (OHBench) are presented, showing that fine-tuning on a subset of the data improves audio-video generation model performance.
-
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms
Video generation models can function as world simulators if efficiency gaps in spatiotemporal modeling are bridged via organized paradigms, architectures, and algorithms.
-
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Live Avatar enables 45 FPS real-time streaming infinite-length audio-driven avatar generation from a 14B diffusion model via distillation and timestep-forcing pipeline parallelism.
-
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation
DomainShuttle introduces domain-aware modeling and token separation techniques to achieve high subject fidelity with generative flexibility in open-domain subject-driven text-to-video tasks.
-
TurboTalk: Progressive Distillation for One-Step Audio-Driven Talking Avatar Generation
TurboTalk uses progressive distillation from 4 steps to 1 step with distribution matching and adversarial training to achieve 120x faster single-step audio-driven talking avatar video generation.
-
EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation
EchoTorrent combines multi-teacher distillation, adaptive CFG calibration, hybrid long-tail forcing, and VAE decoder refinement to enable few-pass autoregressive streaming video generation with improved temporal consi...
-
LongCat-Video-Avatar 1.5 Technical Report
LongCat-Video-Avatar 1.5 delivers an engineering-focused upgrade to audio-driven video generation with claimed competitive performance against closed-source systems on a 500-case benchmark.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.