Semantic Pixel Distances for Image Editing.
CVPR Workshops(2020)
摘要
Many image editing techniques make processing decisions based on measures of similarity between pairs of pixels. Traditionally, pixel similarity is measured using a simple L2 distance on RGB or luminance values. In this work, we explore a richer notion of similarity based on feature embeddings learned by convolutional neural networks. We propose to measure pixel similarity by combining distance in a semantically-meaningful feature embedding with traditional color difference. Using semantic features from the penultimate layer of an off-the-shelf semantic segmentation model, we evaluate our distance measure in two image editing applications. A user study shows that incorporating semantic distances into content-aware resizing via seam carving [2] produces improved results. Off-the-shelf semantic features are found to have mixed effectiveness in content-based range masking, suggesting that training better general-purpose pixel embeddings presents a promising future direction for creating semantically-meaningful feature spaces that can be used in a variety of applications.
更多查看译文
关键词
semantic pixel distances,image editing techniques,pixel similarity,simple L2 distance,luminance values,feature embeddings,convolutional neural networks,traditional color difference,off-the-shelf semantic segmentation model,off-the-shelf semantic features,content-based range masking,general-purpose pixel embeddings,semantically-meaningful feature spaces,seam carving,content-aware resizing,RGB
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要