SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.01392 · ICCV · 2023

Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion

Yiming Sun, Qinghua Hu, Bing Cao, Pengfei Zhu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 4 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
sunym2020/moe-fusion canonical 4 of 4
FunctionStatusWhere it lives
cal_line_length Ran sunym2020/moe-fusion/DOTA_devkit/ImgSplit.py
code served (permissive licence) · get_code("334c71c1848e108a")
choose_best_pointorder_fit_another Ran sunym2020/moe-fusion/DOTA_devkit/ImgSplit.py
code served (permissive licence) · get_code("787051d64e55a326")
nmsbynamedict Ran sunym2020/moe-fusion/DOTA_devkit/ResultMerge.py
code served (permissive licence) · get_code("98c4d71247a0078c")
py_cpu_nms Ran sunym2020/moe-fusion/DOTA_devkit/ResultMerge.py
code served (permissive licence) · get_code("5502a789c2da0e5e")

Repositories linked to this paper

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

Abstract

on the global information that complements the fused image with overall texture detail and contrast. Extensive experiments show that our MoE-Fusion outperforms stateof-the-art methods in preserving multi-modal image texture and contrast through the local-to-global dynamic learning paradigm, and also achieves superior performance on detection tasks. Our code is available: https://github. com/SunYM2020/MoE-Fusion.

For agents

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

get_harvested_code_for_paper("2302.01392")
get_code_for_paper("2302.01392")
have("2302.01392")

Connect an agent — have() is free.