TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/HAC

HAC

Hybrid Adverse Conditions

ImagesIntroduced 2023-05-17

HAC is a dataset for learning and benchmarking arbitrary Hybrid Adverse Conditions restoration. HAC contains 31 scenarios composed of an arbitrary combination of five common weather, with a total of 316K adverse-weather/clean pairs.

Source: Restoring Images Captured in Arbitrary Hybrid Adverse Weather Conditions in One Go

Image Source: Restoring Images Captured in Arbitrary Hybrid Adverse Weather Conditions in One Go

Related Benchmarks

HACS/Action Localization/Average-mAPHACS/Action Localization/mAP@0.5HACS/Action Localization/mAP@0.75HACS/Action Localization/mAP@0.95HACS/Action Recognition/Top 1 AccuracyHACS/Action Recognition/Top 5 AccuracyHACS/Activity Recognition/Top 1 AccuracyHACS/Activity Recognition/Top 5 AccuracyHACS/Temporal Action Localization/Average-mAPHACS/Temporal Action Localization/mAP@0.5HACS/Temporal Action Localization/mAP@0.75HACS/Temporal Action Localization/mAP@0.95HACS/Video/Average-mAPHACS/Video/mAP@0.5HACS/Video/mAP@0.75HACS/Video/mAP@0.95HACS/Zero-Shot Learning/Average-mAPHACS/Zero-Shot Learning/mAP@0.5HACS/Zero-Shot Learning/mAP@0.75HACS/Zero-Shot Learning/mAP@0.95HackerNews/Language Modelling/BPB

Statistics

Papers
1
Benchmarks
0

Links

Homepage

Tasks

Image Restoration