Rolling Shutter

Rolling shutter (RS) is a common image sensor mechanism that captures images row-by-row, introducing distortions in dynamic scenes. Current research focuses on correcting these distortions using various techniques, including deep learning models (e.g., neural radiance fields, diffusion models) and bundle adjustment methods that leverage line features or event camera data to improve accuracy and robustness. These advancements are significant because accurate RS correction is crucial for applications such as autonomous driving, 3D reconstruction, and video stabilization, where accurate scene representation is paramount.