引导式测验 · 中等 等级
CodeFormer 稳健面部恢复测验
查看 CodeFormer 的离散面码预测、Transformer 上下文、可控保真度权衡以及严格恢复的证据限制。
问题 1 的 8
CodeFormer 如何从根本上解决人脸恢复问题?
预览每个问题8 问题
当您参加测验时,就会出现答案和解释。
- CodeFormer 如何从根本上解决人脸恢复问题?
- 作为从学习的码本中进行离散码预测
- 作为连续像素回归
- 作为音频转录
- 作为文本摘要
- 什么组件可以预测要使用哪些码本条目?
- 随机数生成器
- 变压器
- 决策树
- 傅立叶变换
- Why can CodeFormer’s discrete codebook help with severely degraded faces?
- It converts images to grayscale
- 它删除所有颜色信息
- It constrains predictions to a learned vocabulary of facial visual atoms
- It requires the input to be pristine
- What does CodeFormer’s controllable feature transformation setting adjust?
- Image resolution only
- File format
- 检测到的人脸数量
- The trade-off between fidelity to the input and restored visual quality
- CodeFormer 在哪个地点发布?
- 神经IPS 2022
- 1999 年 SIGGRAPH
- 一本烹饪杂志
- 它从未被出版过
- 码本训练源自什么技术?
- 线性回归
- VQGAN 风格的矢量量化模型
- 关系数据库
- 电子表格宏
- What two needs does the CodeFormer paper identify for blind face restoration guidance?
- Changing image format and compressing files
- Detecting camera brand and lens type
- Improving the degraded-input mapping and complementing details lost from the input
- Removing color and resizing the image
- What kinds of test data did the CodeFormer paper use in its reported experiments?
- Only hand-drawn illustrations
- Only pristine studio portraits
- Audio and text datasets
- Synthetic and real-world degraded faces