Jing Zhang, Hao Shen, Jie Gui, Xiaofeng Cong, Junming Hou
We lifted 24 functions out of this paper's own repositories and ran 18 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.
| Repository | Role | Ran |
|---|---|---|
| xiaofeng-life/sfsnid | canonical | 7 of 8 |
| Xiaofeng-life/SFSNiD | — | 11 of 16 |
| Function | Status | Where it lives |
|---|---|---|
| BasicConv | Ran | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("cf777657fcd4a612") |
| BidomainNonlinearMapping | Ran | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("45a3ed308b72fa50") |
| BidomainNonlinearMapping_SinglePath | Ran | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("87326e31813a4257") |
| ConvOut_withFFT | Ran | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("875b657d463b5483") |
| FeatureMerge | Ran | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("d07c444c0d226166") |
| Frequency_Spectrum_Dynamic_Aggregation | Ran | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("b2e3910a075de18c") |
| ResBlock_Conv | Ran | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("7b37be285043f2b0") |
| SCM_withFFT | Ran | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("454f7ad32b74b892") |
| SpaBlock | Ran | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("a4c4157fd5060c95") |
| TransformerBlock | Ran | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("5a7a00261e5bfad2") |
| WindowAttention | Ran | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("a6f8738670f038ed") |
| dynamic_gamma_clear | Ran | xiaofeng-life/sfsnid/task_SFSNiD/Generate_Dark_UNREALNH.py pointer only (licence: NONE) · get_code("06db7d462dba3a61") |
| dynamic_gamma_hazy | Ran | xiaofeng-life/sfsnid/task_SFSNiD/Generate_Dark_UNREALNH.py pointer only (licence: NONE) · get_code("7542148c703f6f59") |
| get_ratio | Ran | xiaofeng-life/sfsnid/task_SFSNiD/train_SFSNiD_semi_supervised.py pointer only (licence: NONE) · get_code("98b93da88040b6ab") |
| get_relative_positions | Ran | xiaofeng-life/sfsnid/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("2a53db1b6432ab8c") |
| query | Ran | xiaofeng-life/sfsnid/task_SFSNiD/train_SFSNiD_semi_supervised.py pointer only (licence: NONE) · get_code("71d44f079297c28a") |
| window_partition | Ran | xiaofeng-life/sfsnid/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("751569c78a842e44") |
| window_reverse | Ran | xiaofeng-life/sfsnid/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("7b0d02f75bf6b439") |
| Attention | Not yet run | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("3875f8f476e9b25a") |
| DBlock | Not yet run | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("10f0475cf68882cf") |
| EBlock | Not yet run | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("969613da960105c3") |
| ResBlock | Not yet run | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("365db0298d2a2932") |
| SFSNiD | Not yet run | Xiaofeng-life/SFSNiD/methods/MyNightDehazing/SFSNiD.py pointer only (licence: NONE) · get_code("335ddb620cc7ba2f") |
| get_network | Not yet run | xiaofeng-life/sfsnid/task_SFSNiD/Generate_PseudoLabel.py pointer only (licence: NONE) · get_code("216c12bf1913751d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Existing research based on deep learning has extensively explored the problem of daytime image dehazing. However, few studies have considered the characteristics of nighttime hazy scenes. There are two distinctions between nighttime and daytime haze. First, there may be multiple active colored light sources with lower illumination intensity in nighttime scenes, which may cause haze, glow and noise with localized, coupled and frequency inconsistent characteristics. Second, due to the domain discrepancy between simulated and real-world data, unrealistic brightness may occur when applying a dehazing model trained on simulated data to real-world data. To address the above two issues, we propose a semi-supervised model for real-world nighttime dehazing. First, the spatial attention and frequency spectrum filtering are implemented as a spatial-frequency domain information interaction module to handle the first issue. Second, a pseudo-label-based retraining strategy and a local window-based brightness loss for semi-supervised training process is designed to suppress haze and glow while achieving realistic brightness. Experiments on public benchmarks validate the effectiveness of the proposed method and its superiority over state-of-the-art methods. The source code and Supplementary Materials are placed in the https://github.com/Xiaofeng-life/SFSNiD.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.18548")
get_code_for_paper("2403.18548")
have("2403.18548")
Connect an agent — have() is free.