8 papers
TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows
Shuai Fu, Jing Gu, Jian Zhou +3
Recent text-to-image models have made substantial progress in photorealism, aesthetics, and text-image alignment. Yet visually appealing images can still violate real-world plausib…
Latent Spatial Memory for Video World Models
Weijie Wang, Haoyu Zhao, Yifan Yang +7
Video world models that maintain 3D spatial consistency across generated frames typically rely on explicit point cloud memory constructed in RGB space. This design is both computat…
Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors
Jiatong Xia, Zicheng Duan, Anton van den Hengel +1
Recent progress in 3D generation has been driven largely by models conditioned on images or text, while readily available 3D priors are still underused. In many real-world scenario…
LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models
Zicheng Duan, Jiatong Xia, Zeyu Zhang +7
Recent generative video world models aim to simulate visual environment evolution, allowing an observer to interactively explore the scene via camera control. However, they implici…
Let Your Video Listen to Your Music!
Xinyu Zhang, Dong Gong, Zicheng Duan +2
Aligning the rhythm of visual motion in a video with a given music track is a practical need in multimedia production, yet remains an underexplored task in autonomous video editing…
Frame-wise Conditioning Adaptation for Fine-Tuning Diffusion Models in Text-to-Video Prediction
Zheyuan Liu, Junyan Wang, Zicheng Duan +2
Text-video prediction (TVP) is a downstream video generation task that requires a model to produce subsequent video frames given a series of initial video frames and text describin…
Training-Free Motion-Guided Video Generation with Enhanced Temporal Consistency Using Motion Consistency Loss
Xinyu Zhang, Zicheng Duan, Dong Gong +1
In this paper, we address the challenge of generating temporally consistent videos with motion guidance. While many existing methods depend on additional control modules or inferen…
EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidance
Zicheng Duan, Yuxuan Ding, Chenhui Gou +3
Zero-shot personalized image generation models aim to produce images that align with both a given text prompt and subject image, requiring the model to incorporate both sources of…