SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.14614 · 2024

AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 15 functions out of this paper's own repositories and ran 12 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
c-yn/adair canonical 12 of 15
FunctionStatusWhere it lives
contributions Ran c-yn/adair/utils/imresize.py
code served (permissive licence) · get_code("b921438690ac017f")
crop_a_image Ran c-yn/adair/utils/image_io.py
code served (permissive licence) · get_code("8ade57fc1fb950bb")
crop_img Ran c-yn/adair/utils/image_utils.py
code served (permissive licence) · get_code("11c75b3b8bc61c21")
crop_patch Ran c-yn/adair/utils/image_utils.py
code served (permissive licence) · get_code("86abcfa12b6612f0")
fix_scale_and_size Ran c-yn/adair/utils/imresize.py
code served (permissive licence) · get_code("ee75635bb6c497f1")
get_position_from_periods Ran c-yn/adair/utils/schedulers.py
code served (permissive licence) · get_code("cd569444547de84f")
imresize Ran c-yn/adair/utils/imresize.py
code served (permissive licence) · get_code("c38287d2acea0ce0")
linear_warmup_decay Ran c-yn/adair/utils/schedulers.py
code served (permissive licence) · get_code("442cb54f21dcfe50")
prepare_gt_img Ran c-yn/adair/utils/image_io.py
code served (permissive licence) · get_code("e91553b51010dfd6")
prepare_hazy_image Ran c-yn/adair/utils/image_io.py
code served (permissive licence) · get_code("8564be766b7cda56")
to_3d Ran c-yn/adair/net/model.py
code served (permissive licence) · get_code("82a15cc1e46f7e4d")
to_4d Ran c-yn/adair/net/model.py
code served (permissive licence) · get_code("b20f2a5df739a59e")
accuracy Not yet run c-yn/adair/utils/val_utils.py
code served (permissive licence) · get_code("418284b6911ecae5")
compute_psnr_ssim Not yet run c-yn/adair/utils/val_utils.py
code served (permissive licence) · get_code("41bf6e3c6e9bb89b")
slice_image2patches Not yet run c-yn/adair/utils/image_utils.py
code served (permissive licence) · get_code("779d9bd47765629e")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In the image acquisition process, various forms of degradation, including noise, haze, and rain, are frequently introduced. These degradations typically arise from the inherent limitations of cameras or unfavorable ambient conditions. To recover clean images from degraded versions, numerous specialized restoration methods have been developed, each targeting a specific type of degradation. Recently, all-in-one algorithms have garnered significant attention by addressing different types of degradations within a single model without requiring prior information of the input degradation type. However, these methods purely operate in the spatial domain and do not delve into the distinct frequency variations inherent to different degradation types. To address this gap, we propose an adaptive all-in-one image restoration network based on frequency mining and modulation. Our approach is motivated by the observation that different degradation types impact the image content on different frequency subbands, thereby requiring different treatments for each restoration task. Specifically, we first mine low- and high-frequency information from the input features, guided by the adaptively decoupled spectra of the degraded image. The extracted features are then modulated by a bidirectional operator to facilitate interactions between different frequency components. Finally, the modulated features are merged into the original input for a progressively guided restoration. With this approach, the model achieves adaptive reconstruction by accentuating the informative frequency subbands according to different input degradations. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance on different image restoration tasks, including denoising, dehazing, deraining, motion deblurring, and low-light image enhancement. Our code is available at https://github.com/c-yn/AdaIR.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.14614")
get_code_for_paper("2403.14614")
have("2403.14614")

Connect an agent — have() is free.