6 papers
WaterGen: Decoupling Scene and Medium in Underwater Image Generation
Jiayi Wu, Tianfu Wang, Tianyi Xiong +6
Underwater computer vision tasks, such as detection, restoration, and segmentation, are limited by the scarcity of large-scale and diverse training data. We introduce WaterGen, a m…
Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion
Jiayi Wu, Haoming Cai, Cornelia Fermuller +2
While Video Diffusion Models (VDMs) excel at synthesizing high-fidelity videos, enabling precise camera and scene control remains challenging. Existing methods predominantly rely o…
High-speed Imaging through Turbulence with Event-based Light Fields
Yu-Hsiang Huang, Levi Burner, Sachin Shah +3
This work introduces and demonstrates the first system capable of imaging fast-moving extended non-rigid objects through strong atmospheric turbulence at high frame rate. Event cam…
Reconstructing Tornadoes in 3D with Gaussian Splatting
Adam Yang, Nadula Kadawedduwa, Tianfu Wang +9
Accurately reconstructing the 3D structure of tornadoes is critically important for understanding and preparing for this highly destructive weather phenomenon. While modern 3D scen…
Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation
Jingxi Chen, Brandon Y. Feng, Haoming Cai +6
Video Frame Interpolation aims to recover realistic missing frames between observed frames, generating a high-frame-rate video from a low-frame-rate video. However, without additio…
Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion
Tianyi Xiong, Jiayi Wu, Botao He +4
By combining differentiable rendering with explicit point-based scene representations, 3D Gaussian Splatting (3DGS) has demonstrated breakthrough 3D reconstruction capabilities. Ho…