SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.09679 · 2022

FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing Flow

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 8 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
dsshim0125/FS-NCSR canonical 8 of 10
FunctionStatusWhere it lives
deriveScaleFromSize Ran dsshim0125/FS-NCSR/imresize.py
code served (permissive licence) · get_code("b97b2d33b67260a8")
deriveSizeFromScale Ran dsshim0125/FS-NCSR/imresize.py
code served (permissive licence) · get_code("ffe34bf756a6eaa8")
fiFindByWildcard Ran dsshim0125/FS-NCSR/measure.py
code served (permissive licence) · get_code("2a857e38ee87f92c")
imread Ran dsshim0125/FS-NCSR/prepare_data.py
code served (permissive licence) · get_code("d4a4924746094263")
imread Ran dsshim0125/FS-NCSR/measure.py
code served (permissive licence) · get_code("ff6d805555b31561")
random_crop Ran dsshim0125/FS-NCSR/prepare_data.py
code served (permissive licence) · get_code("9c54ab0c75133028")
t Ran dsshim0125/FS-NCSR/measure.py
code served (permissive licence) · get_code("6a8e1704755f6a34")
triangle Ran dsshim0125/FS-NCSR/imresize.py
code served (permissive licence) · get_code("2722f476a816c1b9")
define_Flow Not yet run dsshim0125/FS-NCSR/models/networks.py
code served (permissive licence) · get_code("6d050c5262a0b80b")
find_model_using_name Not yet run dsshim0125/FS-NCSR/models/networks.py
code served (permissive licence) · get_code("7d04d276ed855e64")

Repositories linked to this paper

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

Abstract

Super-resolution suffers from an innate ill-posed problem that a single low-resolution (LR) image can be from multiple high-resolution (HR) images. Recent studies on the flow-based algorithm solve this ill-posedness by learning the super-resolution space and predicting diverse HR outputs. Unfortunately, the diversity of the super-resolution outputs is still unsatisfactory, and the outputs from the flow-based model usually suffer from undesired artifacts which causes low-quality outputs. In this paper, we propose FS-NCSR which produces diverse and high-quality super-resolution outputs using frequency separation and noise conditioning compared to the existing flow-based approaches. As the sharpness and high-quality detail of the image rely on its high-frequency information, FS-NCSR only estimates the high-frequency information of the high-resolution outputs without redundant low-frequency components. Through this, FS-NCSR significantly improves the diversity score without significant image quality degradation compared to the NCSR, the winner of the previous NTIRE 2021 challenge.

For agents

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

get_harvested_code_for_paper("2204.09679")
get_code_for_paper("2204.09679")
have("2204.09679")

Connect an agent — have() is free.