Content Based Image Synthesis
IMAGE AND VIDEO RETRIEVAL, PROCEEDINGS(2004)
摘要
A new method allowing for semantically guided image editing and synthesis is introduced. The editing process is made considerably easier and more powerful with our content-aware tool. We construct a database of image regions annotated with a carefully chosen vocabulary and utilize recent advances in texture synthesis algorithms to generate new and unique image regions from this database of material. These new regions are then seamlessly composited into a user's existing photograph. The goal is to empower the end user with the ability to edit existing photographs and synthesize new ones on a high semantic level. Plausible results are generated using a small prototype database and showcase some of the editing possibilities that such a system affords.
更多查看译文
关键词
Image Region, Source Texture, Texture Synthesis, Clique Partitioning, High Semantic Level
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络