Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence
원문 초록
This paper tackles the automatic colorization task of a sketch image given an already-colored reference image. Colorizing a sketch image is in high demand in comics, animation, and other content creation applications, but it suffers from information scarcity of a sketch image. To address this, a reference image can render the colorization process in a reliable and user-driven manner. However, it is difficult to prepare for a training data set that has a sufficient amount of semantically meaningful pairs of images as well as the ground truth for a colored image reflecting a given reference (e.g., coloring a sketch of an originally blue car given a reference green car). To tackle this challenge, we propose to utilize the identical image with geometric distortion as a virtual reference, which makes it possible to secure the ground truth for a colored output image. Furthermore, it naturally provides the ground truth for dense semantic correspondence, which we utilize in our internal attention mechanism for color transfer from reference to sketch input. We demonstrate the effectiveness of our approach in various types of sketch image colorization via quantitative as well as qualitative evaluation against existing methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Temporal Consistent Automatic Video Colorization via Semantic Correspondence
SPColor: Semantic Prior Guided Exemplar-based Image Colorization
Color2Embed: Fast Exemplar-Based Image Colorization using Color Embeddings
Leveraging the Powerful Attention of a Pre-trained Diffusion Model for Exemplar-based Image Colorization
A GAN-Enhanced Deep Learning Framework for Rooftop Detection from Historical Aerial Imagery
Language-based Image Colorization: A Benchmark and Beyond
토론
이 논문과 연결된 포럼 글이 아직 없습니다.