FengShaner nielsr HF Staff commited on
Commit
de0329c
·
verified ·
1 Parent(s): cfeaca9

Fix metadata and improve model card (#1)

Browse files

- Fix metadata and improve model card (02d82dc8726803b5fc4c42bad5957e9c8f918929)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +14 -17
README.md CHANGED
@@ -1,5 +1,9 @@
1
  ---
 
 
2
  license: mit
 
 
3
  tags:
4
  - image-dehazing
5
  - spiking-neural-network
@@ -9,15 +13,14 @@ tags:
9
  - pytorch_model_hub_mixin
10
  - model_hub_mixin
11
  - safetensors
12
- - arxiv:<2512.23950>
13
- pipeline_tag: image-to-image
14
- language:
15
- - en
16
  ---
17
 
18
  # DehazeSNN
19
 
20
- > U-Net-Like Spiking Neural Networks for Single Image Dehazing
 
 
21
 
22
  DehazeSNN integrates a U-Net-like encoder-decoder architecture with Spiking Neural Networks (SNNs), using an Orthogonal Leaky-Integrate-and-Fire Block (OLIFBlock) for efficient cross-channel communication. This yields competitive dehazing quality with fewer parameters and MACs compared to Transformer-based methods.
23
 
@@ -40,7 +43,7 @@ DehazeSNN integrates a U-Net-like encoder-decoder architecture with Spiking Neur
40
 
41
  ```bash
42
  # Clone the DehazeSNN repository (for model code + custom CUDA kernels)
43
- git clone https://github.com/FengShaner/DehazeSNN.git
44
  cd DehazeSNN
45
 
46
  # Create environment (requires CUDA 12.x)
@@ -90,10 +93,10 @@ Image.fromarray(output).save("dehazed_image.jpg")
90
 
91
  ## Requirements
92
 
93
- - **CUDA GPU required**: The custom LIF CUDA kernels require an NVIDIA GPU with CUDA support
94
- - **CuPy**: `cupy-cuda12x` (for CUDA 12.x) - CPU-only inference is **not supported**
95
- - PyTorch >= 2.1 with CUDA 12.1
96
- - Python 3.11 recommended
97
 
98
  ## Model Sizes
99
 
@@ -119,10 +122,4 @@ If you find this work useful, please cite our paper:
119
 
120
  ## License
121
 
122
- This project is released under the MIT License.
123
-
124
- ## Links
125
-
126
- - [GitHub Repository](https://github.com/FengShaner/DehazeSNN)
127
- - [Paper (IEEE IJCNN 2025)](https://doi.org/10.1109/IJCNN64981.2025.11228727)
128
- - [Pretrained Models & Results (Zenodo)](https://doi.org/10.5281/zenodo.15486831)
 
1
  ---
2
+ language:
3
+ - en
4
  license: mit
5
+ pipeline_tag: image-to-image
6
+ library_name: pytorch
7
  tags:
8
  - image-dehazing
9
  - spiking-neural-network
 
13
  - pytorch_model_hub_mixin
14
  - model_hub_mixin
15
  - safetensors
16
+ arxiv: 2512.23950
 
 
 
17
  ---
18
 
19
  # DehazeSNN
20
 
21
+ > **U-Net-Like Spiking Neural Networks for Single Image Dehazing**
22
+
23
+ [[📄 Paper](https://huggingface.co/papers/2512.23950)] [[💻 GitHub](https://github.com/HaoranLiu507/DehazeSNN)]
24
 
25
  DehazeSNN integrates a U-Net-like encoder-decoder architecture with Spiking Neural Networks (SNNs), using an Orthogonal Leaky-Integrate-and-Fire Block (OLIFBlock) for efficient cross-channel communication. This yields competitive dehazing quality with fewer parameters and MACs compared to Transformer-based methods.
26
 
 
43
 
44
  ```bash
45
  # Clone the DehazeSNN repository (for model code + custom CUDA kernels)
46
+ git clone https://github.com/HaoranLiu507/DehazeSNN.git
47
  cd DehazeSNN
48
 
49
  # Create environment (requires CUDA 12.x)
 
93
 
94
  ## Requirements
95
 
96
+ - **CUDA GPU required**: The custom LIF CUDA kernels require an NVIDIA GPU with CUDA support.
97
+ - **CuPy**: `cupy-cuda12x` (for CUDA 12.x) - CPU-only inference is **not supported**.
98
+ - PyTorch >= 2.1 with CUDA 12.1.
99
+ - Python 3.11 recommended.
100
 
101
  ## Model Sizes
102
 
 
122
 
123
  ## License
124
 
125
+ This project is released under the MIT License.