9 papers
AV-SyncBench: Decoupled Benchmarking of Temporal and Semantic Audio-Visual Synchronization
Tianhong Zhou, Mingyang Han, Boyu Li +8
Audio-visual feature extraction is a fundamental component of multimodal understanding and generation tasks. However, existing evaluation protocols for feature extraction models ex…
FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing
Yuxuan Jiang, Mingyang Han, Yusheng Dai +12
Text-to-audio (TTA) generation has made significant strides, yet achieving precise and consistent audio editing remains a major challenge. However, existing methods struggle to bal…
Hierarchical Codec Diffusion for Video-to-Speech Generation
Jiaxin Ye, Gaoxiang Cong, Chenhui Wang +4
Video-to-Speech (VTS) generation aims to synthesize speech from a silent video without auditory signals. However, existing VTS methods disregard the hierarchical nature of speech,…
CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing
Gaoxiang Cong, Liang Li, Jiaxin Ye +4
Movie dubbing aims to synthesize speech that preserves the vocal identity of a reference audio while synchronizing with the lip movements in a target video. Existing methods fail t…
Dynamic Differential Linear Attention: Enhancing Linear Diffusion Transformer for High-Quality Image Generation
Boyuan Cao, Xingbo Yao, Chenhui Wang +3
Diffusion transformers (DiTs) have emerged as a powerful architecture for high-fidelity image generation, yet the quadratic cost of self-attention poses a major scalability bottlen…
RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation
Boyuan Cao, Jiaxin Ye, Yujie Wei +1
While latent diffusion models (LDMs), such as Stable Diffusion, are designed for high-resolution (HR) image generation, they often struggle with significant structural distortions…