3 papers
cs.CV2026
Gen Through the Lens: Camera-Controllable Video Generation via Cross-Coordinate Conditioning Fusion
Shuai Li, Jinxu Xiang, Xinyuan Li +5
We present Gen Through the Lens, a camera-controllable image-to-video generation framework that synthesizes videos from a given reference image while enabling realistic and physica…
cs.CV2026
ScenDi: 3D-to-2D Scene Diffusion Cascades for Urban Generation
Hanlei Guo, Jiahao Shao, Xinya Chen +4
Recent advancements in 3D object generation using diffusion models have achieved remarkable success, but generating realistic 3D urban scenes remains challenging. Existing methods…
cs.CV2024
PhysMotion: Physics-Grounded Dynamics From a Single Image
Xiyang Tan, Ying Jiang, Xuan Li +4
We introduce PhysMotion, a novel framework that leverages principled physics-based simulations to guide intermediate 3D representations generated from a single image and input cond…