10 papers
SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation
Yu Yuan, Tharindu Wickremasinghe, Zeeshan Nadir +3
Images and videos are discrete 2D projections of the 4D world (3D space + time). Most visual understanding, prediction, and generation operate directly on 2D observations, leading…
NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics
Yu Yuan, Xijun Wang, Tharindu Wickremasinghe +3
A primary bottleneck in large-scale text-to-video generation today is physical consistency and controllability. Despite recent advances, state-of-the-art models often produce unrea…
PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment
Zhexiao Xiong, Yizhi Song, Liu He +4
Video Diffusion Models (VDMs) offer a promising approach for simulating dynamic scenes and environments, with broad applications in robotics and media generation. However, existing…
Progressive Image Restoration via Text-Conditioned Video Generation
Peng Kang, Xijun Wang, Yu Yuan
Recent text-to-video models have demonstrated strong temporal generation capabilities, yet their potential for image restoration remains underexplored. In this work, we repurpose C…
Personalized Generative Low-light Image Denoising and Enhancement
Xijun Wang, Prateek Chennuri, Dilshan Godaliyadda +5
Modern cameras' performance in low-light conditions remains suboptimal due to fundamental limitations in photon shot noise and sensor read noise. Generative image restoration metho…
Astrophotography turbulence mitigation via generative models
Joonyeoup Kim, Yu Yuan, Xingguang Zhang +2
Photography is the cornerstone of modern astronomical and space research. However, most astronomical images captured by ground-based telescopes suffer from atmospheric turbulence,…