Dense Scene Information Estimation Network for Dehazing_CVPR2019
Abstract 通常情況下，除霧算法都會求大氣光A和透射圖 t ,而後根據去霧模型公式反推得到去霧圖像J，在本文中，針對這種去霧方法提出了兩個網絡，第一個是At-DH，基於DenseNet編碼器與兩個不同的基於DenseNet的解碼器，共同估計去霧圖像；第二個網絡爲AtJ-DH網絡，在At-DH的基礎上，增加了一個基於DenseNet的解碼器，用以與A、t一起重新創建無霧圖像，通過自定
相關文章
- 1. OCNet_Object Context Network for Scene parsing
- 2. 《Dense Residual Network for Retinal Vessel Segmentation》
- 3. Dual attention network for scene segmentation
- 4. Residual Dense Network for Image Super-Resolution
- 5. Dual Attention Network for Scene Segmentation
- 6. ACNet_ Adaptive Context Network for Scene Parsing
- 7. DANet: Dual Attention Network for Scene Segmentation
- 8. Spatial Attention Network for Scene Parsing
- 9. Stacked Hourglass Network for Human Pose Estimation
- 10. Paper | Residual Dense Network for Image Super-Resolution
- 更多相關文章...
- • Swift for 循環 - Swift 教程
- • Scala for循環 - Scala教程
- • Flink 數據傳輸及反壓詳解
- • Composer 安裝與使用
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. OCNet_Object Context Network for Scene parsing
- 2. 《Dense Residual Network for Retinal Vessel Segmentation》
- 3. Dual attention network for scene segmentation
- 4. Residual Dense Network for Image Super-Resolution
- 5. Dual Attention Network for Scene Segmentation
- 6. ACNet_ Adaptive Context Network for Scene Parsing
- 7. DANet: Dual Attention Network for Scene Segmentation
- 8. Spatial Attention Network for Scene Parsing
- 9. Stacked Hourglass Network for Human Pose Estimation
- 10. Paper | Residual Dense Network for Image Super-Resolution