Automatic video dubbing in the wild remains fundamentally limited by two competing constraints: hierarchical methods depend on brittle, multi-stage preprocessing pipelines that severely restrict data scalability and practical deployment, while holistic approaches operating on uncropped video suffer from weak temporal a...
Yu-Sheng Dai, Kangdi Wang, Baolong Gao et al.· 1 citation
Continuous-latent audio autoencoders form the backbone of latent music generators, yet decoders at high compression rates commonly exhibit three failure modes: high-frequency loss, phase incoherence, and stereo-image collapse. These share a structural root: waveform autoencoders lack an explicit frequency axis, leaving...
Autoregressive video diffusion enables interactive streaming generation, but suffers from error accumulation over long rollouts. Self-rollout training reduces exposure bias, yet finite rollouts leave long-range drift unresolved. We observe that the noise level of the history key-value (K/V) representations trades visua...
Weiqiang Wang, Zhuo-Kun Chen, Yu-Sheng Dai et al.· 0 citations
This work introduces TD-V2A, which leverages temporal differences (TD) as the key representation that distinguishes V2A from I2A, enriching visual conditioning with minimal architectural modification and significantly improves end-to-end V2A generation quality, even outperforming dedicated V2A representations such as c...
Zehua Chen, Junyou Wang, Yuxuan Jiang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
