DWT-FFC and NTIRE-2021-Dehazing-DWGAN

These two tools are competitors, representing different state-of-the-art dehazing solutions that won the same challenge in different years (2021 and 2023), each offering a distinct architecture (DWT-FFC versus DW-GAN) for the task.

DWT-FFC
40
Emerging
Maintenance 6/25
Adoption 8/25
Maturity 16/25
Community 10/25
Maintenance 0/25
Adoption 8/25
Maturity 16/25
Community 14/25
Stars: 50
Forks: 5
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 66
Forks: 9
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
Stale 6m No Package No Dependents

About DWT-FFC

zhouh115/DWT-FFC

Official PyTorch implementation of dehazing method based on FFC and ConvNeXt, 1st place solution of NTIRE 2023 HR NonHomogeneous Dehazing Challenge (CVPR Workshop 2023).

This tool helps improve the clarity of images taken in hazy or foggy conditions, especially when the haze isn't uniform across the scene. You input a hazy image, and it outputs a clearer, dehazed version. This is useful for anyone working with outdoor photography, surveillance, remote sensing, or autonomous vehicle perception where atmospheric conditions obscure important visual details.

image-enhancement computer-vision remote-sensing outdoor-photography visual-inspection

About NTIRE-2021-Dehazing-DWGAN

liuh127/NTIRE-2021-Dehazing-DWGAN

Official PyTorch implementation of DW-GAN, 1st place solution of NTIRE 2021 NonHomogeneous Dehazing Challenge (CVPR Workshop 2021).

This tool helps improve the clarity of images taken in hazy conditions, especially when the haze is unevenly distributed across the scene. It takes hazy images as input and produces clearer, dehazed images, making details more visible. This is useful for anyone working with outdoor photography, surveillance, or remote sensing where atmospheric haze obscures visual information.

image-enhancement outdoor-photography surveillance remote-sensing computer-vision

Scores updated daily from GitHub, PyPI, and npm data. How scores work