SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.04005 · NeurIPS · 2022

RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts

Jinyoung Park, Minseok Son, Seungju Cho, Inyoung Lee, Changick Kim

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 6 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
jinyxp/weather4cast-2022 alias 6 of 8
FunctionStatusWhere it lives
DownConv Ran jinyxp/weather4cast-2022/models/RainUNET.py
code served (permissive licence) · get_code("5c04b46d301f8ac2")
GridAttention Ran jinyxp/weather4cast-2022/models/RainUNET.py
code served (permissive licence) · get_code("a6730c7058b85eca")
ResizeConv Ran jinyxp/weather4cast-2022/models/RainUNET.py
code served (permissive licence) · get_code("514c7c0584d7ee25")
autocrop Ran jinyxp/weather4cast-2022/models/RainUNET.py
code served (permissive licence) · get_code("9288d9869f40857f")
get_activation Ran jinyxp/weather4cast-2022/models/RainUNET.py
code served (permissive licence) · get_code("689e68cf031b9f81")
upconv2 Ran jinyxp/weather4cast-2022/models/RainUNET.py
code served (permissive licence) · get_code("03d8a887bb4900ac")
UNet Not yet run jinyxp/weather4cast-2022/models/RainUNET.py
code served (permissive licence) · get_code("dbdf5a7a803888ee")
UpConv Not yet run jinyxp/weather4cast-2022/models/RainUNET.py
code served (permissive licence) · get_code("0e0c16f47f48ed39")

Repositories linked to this paper

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

Abstract

This paper presents a solution to the Weather4cast 2022 Challenge Stage 2. The goal of the challenge is to forecast future high-resolution rainfall events obtained from ground radar using low-resolution multiband satellite images. We suggest a solution that performs data preprocessing appropriate to the challenge and then predicts rainfall movies using a novel RainUNet. RainUNet is a hierarchical U-shaped network with temporal-wise separable block (TS block) using a decoupled large kernel 3D convolution to improve the prediction performance. Various evaluation metrics show that our solution is effective compared to the baseline method. The source codes are available at https://github.com/jinyxp/Weather4cast-2022.

For agents

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

get_harvested_code_for_paper("2212.04005")
get_code_for_paper("2212.04005")
have("2212.04005")

Connect an agent — have() is free.