EvTexture leverages high-frequency details of events to better recover texture regions in VSR, using a bidirectional recurrent network and an iterative texture enhancement module.
EvTexture utilizes event signals to enhance the texture restoration in VSR, achieving state-of-the-art performance on four datasets.
EvTexture adopts a bidirectional recurrent network, where features are propagated forward and backward to enhance the restoration of texture regions.
EvTexture uses an iterative texture enhancement module to progressively refine the feature across multiple iterations, leveraging high-frequency textural information from events along with context information from the current frame.
EvTexture leverages high-temporal-resolution event information to better recover texture regions in VSR.
EvTexture gradually refines the texture regions across multiple iterations, leading to more accurate and rich high-resolution details.
Video super-resolution
Video denoising
Video deblurring
Image and video processing
Input event-based data
Preprocess data using a bidirectional recurrent network
Apply iterative texture enhancement module
Refine texture regions across multiple iterations