引導式測驗 · 中等 等級
LaMa 解析度 - 強大的修復測驗
了解 LaMa 如何結合傅立葉卷積、高感受野損失和大掩模進行影像修復及其報告的限制。
問題 1 的 8
賦予 LaMa 圖像全球視野的標誌性建築組件是什麼?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 賦予 LaMa 圖像全球視野的標誌性建築組件是什麼?
- 快速傅立葉卷積
- Transformer 自註意力塊
- 循環 LSTM 層
- 膠囊網絡
- 為什麼 LaMa 比許多早期的修復模型更能處理大型面具?
- 它只適用於小圖像
- 它的全球感受野讓它能夠跨越大洞繼續結構
- 它從邊緣隨機複製像素
- 它拒絕填滿超過固定尺寸的掩模
- LaMa 論文報告了哪些解析行為?
- It only works at one exact training resolution
- It works only below the training resolution
- It generalized to some resolutions higher than those used during training in the evaluated settings
- It accepts no image input
- 由於其頻域處理,LaMa 能夠特別出色地處理哪種紋理?
- 純隨機噪音
- 只有純色
- 只限文字字符
- 重複、週期性的紋理,如磚塊或瓷磚
- 與大型擴散修復系統相比,LaMa通常如何定位?
- As a comparatively efficient convolutional inpainting method
- As a much slower model that requires a data center
- As a video-only model
- As a tool that never needs an image
- 哪種損失有助於 LaMa 產生逼真的填充而不是模糊的平均值?
- 一個簡單的像素均方誤差損失
- 對抗性損失與知覺損失結合
- 根本沒有損失函數
- 僅測量文件大小的損失
- What additional loss component does the LaMa paper emphasize for large-mask inpainting?
- 語音辨識損失
- A bitrate-only loss
- A perceptual loss with a high receptive field
- A loss that ignores image structure
- Who introduced LaMa in the 2021 paper?
- Jonathan Frankle and Michael Carbin
- Cees Taal and colleagues
- Timothy Dozat and Christopher Manning
- Roman Suvorov and colleagues