Transformers have recently been shown to generate high quality images from text input. However, the existing method of pose conditioning using skeleton image tokens is computationally inefficient and generate low quality images. Therefore we propose a new method; Keypoint Pose Encoding (KPE); KPE is 10 times more memory efficient and over 73% faster at generating high quality images from text input conditioned on the pose. The pose constraint improves the image quality and reduces errors on body extremities such as arms and legs. The additional benefits include invariance to changes in the target image domain and image resolution, making it easily scalable to higher resolution images. We demonstrate the versatility of KPE by generating photorealistic multiperson images derived from the DeepFashion dataset. We also introduce a evaluation method People Count Error (PCE) that is effective in detecting error in generated human images.
翻译:最近显示变换器通过文本输入生成高质量的图像。 但是, 现有的使用骨架图像符号的配置调节方法在计算上效率低下, 并生成低质量图像。 因此, 我们提议了一个新方法; 关键点 Pose 编码( KPE) ; KPE 的内存效率是高十倍, 且速度超过 73%, 生成由文本输入而成的高质量图像, 以图像为条件。 造成制约, 提高了图像质量, 并减少了像胳膊和腿这样的身体外部的错误。 额外的好处包括无法改变目标图像域和图像分辨率, 使其易于向更高分辨率图像缩放。 我们通过生成来自深时装数据集的光真人图像来展示 KPE 的多功能性。 我们还引入了一种评估方法, 人计错误( PCE), 有效检测生成的人类图像中的错误。