Image Outpainting Based On Attention Model

淡江大學機構典藏 > 工學院 > 資訊工程學系暨研究所 > 會議論文 > Item 987654321/126990

請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/126990

題名:	Image Outpainting Based On Attention Model
其他題名:	基於注意模型的圖像擴展
作者:	Tai, Wei-Chien;Yen, Shwu-Huey;Tsai, Yihjia
關鍵詞:	image outpainting;image inpainting;attention module;Squeeze Excitation Network (SEnet);discriminator
日期:	2022-10-24
上傳時間:	2025-03-20 12:05:46 (UTC+8)
摘要:	Along the advanced progresses on deep neural networks, there are many impressive results on image inpainting. Consequently, several research are trying to transfer successful experiences into image outpainting. Contextual attention net is one of the popular architectural units being applied to outpainting. We argue that it may not as suitable when embedded in an outpainting network. Instead, we adopt SEnet for it has global receptive field and channel-wise feature recalibration. This is very helpful for image outpainting. We also propose a local discriminator mechanism to decide whether a randomly select partial image is a real one. By ‘randomness’, the generator can produce a realistic result.
DOI:	10.6846/TKU.2022.00658
顯示於類別:	[資訊工程學系暨研究所] 會議論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	10	檢視/開啟

在機構典藏中所有的資料項目都受到原著作權保護.

TAIR相關文章