6 papers
Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation
Mutian Xu, Tianbao Zhang, Tianqi Liu +3
Simulating robot-world interactions is a cornerstone of Embodied AI. Recently, a few works have shown promise in leveraging video generations to transcend the rigid visual/physical…
RealDPO: Real or Not Real, that is the Preference
Guo Cheng, Danni Yang, Ziqi Huang +3
Video generative models have recently achieved notable advancements in synthesis quality. However, generating complex motions remains a critical challenge, as existing models often…
Simulating the Visual World with Artificial Intelligence: A Roadmap
Jingtong Yue, Ziqi Huang, Zhaoxi Chen +3
The landscape of video generation is shifting, from a focus on generating visually appealing clips to building virtual environments that support interaction and maintain physical p…
Stencil: Subject-Driven Generation with Context Guidance
Gordon Chen, Ziqi Huang, Cheston Tan +1
Recent text-to-image diffusion models can generate striking visuals from text prompts, but they often fail to maintain subject consistency across generations and contexts. One majo…
CineScale: Free Lunch in High-Resolution Cinematic Visual Generation
Haonan Qiu, Ning Yu, Ziqi Huang +2
Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resou…
Cut2Next: Generating Next Shot via In-Context Tuning
Jingwen He, Hongbo Liu, Jiajun Li +4
Effective multi-shot generation demands purposeful, film-like transitions and strict cinematic continuity. Current methods, however, often prioritize basic visual consistency, negl…