Deep Image Compositing
원문 초록
Image compositing is a task of combining regions from different images to compose a new image. A common use case is background replacement of portrait images. To obtain high quality composites, professionals typically manually perform multiple editing steps such as segmentation, matting and foreground color decontamination, which is very time consuming even with sophisticated photo editing tools. In this paper, we propose a new method which can automatically generate high-quality image compositing without any user input. Our method can be trained end-to-end to optimize exploitation of contextual and color information of both foreground and background images, where the compositing quality is considered in the optimization. Specifically, inspired by Laplacian pyramid blending, a dense-connected multi-stream fusion network is proposed to effectively fuse the information from the foreground and background images at different scales. In addition, we introduce a self-taught strategy to progressively train from easy to complex cases to mitigate the lack of training data. Experiments show that the proposed method can automatically generate high-quality composites and outperforms existing methods both qualitatively and quantitatively.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MaSS13K: A Matting-level Semantic Segmentation Benchmark
VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion
BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation
ReFlow6D: Refraction-Guided Transparent Object 6D Pose Estimation via Intermediate Representation Learning
Memory Efficient Matting with Adaptive Token Routing
ZIM: Zero-Shot Image Matting for Anything
토론
이 논문과 연결된 포럼 글이 아직 없습니다.