6 papers · 1 filter
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…
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…
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…
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,…
iHDR: Iterative HDR Imaging with Arbitrary Number of Exposures
Yu Yuan, Yiheng Chi, Xingguang Zhang +1
High dynamic range (HDR) imaging aims to obtain a high-quality HDR image by fusing information from multiple low dynamic range (LDR) images. Numerous learning-based HDR imaging met…
Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation
Xingguang Zhang, Nicholas Chimitt, Xijun Wang +2
Atmospheric turbulence is a major source of image degradation in long-range imaging systems. Although numerous deep learning-based turbulence mitigation (TM) methods have been prop…