18 papers
AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation
Yexin Liu, Wen-Jie Shu, Zile Huang +6
Text-guided image-to-video generation has made substantial progress, yet it still struggles to execute text-specified edits that require substantial changes to a reference image (\…
AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
Pengjun Fang, Yingqing He, Yazhou Xing +3
Existing video-to-audio (V2A) generation methods predominantly rely on text prompts alongside visual information to synthesize audio. However, two critical bottlenecks persist: sem…
Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising
Yifan Wang, Liya Ji, Zhanghan Ke +3
We propose an approach to enhancing synthetic video realism, which can re-render synthetic videos from a simulator in photorealistic fashion. Our realism enhancement approach is a…
Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward
Xiaogang Xu, Ruihang Chu, Jian Wang +6
Reinforcement Learning (RL) has recently been incorporated into diffusion models, e.g., tasks such as text-to-image. However, directly applying existing RL methods to diffusion-bas…
When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding
Yan Shu, Hangui Lin, Yexin Liu +7
Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, th…
VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention
Mingzhe Zheng, Yongqi Xu, Haojian Huang +8
Current video generation models excel at short clips but fail to produce cohesive multi-shot narratives due to disjointed visual dynamics and fractured storylines. Existing solutio…