Semantic-Aware Image Smoothing
نویسندگان
چکیده
Structure-preserving image smoothing aims to extract semantically meaningful image structure from texture, which is one of the fundamental problems in computer vision and graphics. However, it is still not clear how to define this concept. On the other hand, semantic image labeling has achieved significant progress recently and has been widely used in many computer vision tasks. In this paper, we present an interesting observation, i.e. high-level semantic image labeling information can provide a meaningful structure prior naturally. Based on this observation, we propose a simple and yet effective method, which we term semantic smoothing, by exploiting the semantic information to accomplish semantically structure-preserving image smoothing. We show that our approach outperforms the state-of-the-art approaches in texture removal by considering the semantic information for structure preservation. Also, we apply our approach to three applications: detail enhancement, edge detection, and image segmentation, and we demonstrate the effectiveness of our semantic smoothing method on these problems.
منابع مشابه
Context-aware mesh smoothing for biomedical applications
Smoothing algorithms allow to reduce artifacts from mesh generation, but often degrade accuracy. Thus, we present a method that identifies staircase artifacts which result from image inhomogeneities and binary segmentation in medical image data for subsequent removal by adaptive mesh smoothing. This paper makes the following specific contributions: caps, which are flat regions, resulting from s...
متن کاملPAIRED ANISOTROPIC DISTRIBUTION FOR IMAGE SELECTIVE SMOOTHING
In this paper, we present a novel approach for image selective smoothing by the evolution of two paired nonlinear partial differential equations. The distribution coefficient in de-noising equation controls the speed of distribution, and is determined by the edge-strength function. In the previous works, the edge-strength function depends on isotropic smoothing of the image...
متن کاملSemantic Segmentation for Real-World Data by Jointly Exploiting Supervised and Transferrable Knowledge
This paper addresses two major challenges in semantic segmentation for real-world data. First, with ever-increasing semantic labels, we need a more pragmatic approach other than existing fully-supervised methods. Second, semantic segmentation for rarely-appeared objects are still challenging for existing methods. We assume that there exist one supervised model and one annotated real-world datas...
متن کاملSemantic-Based Image Retrial in the VQ Compressed Domain using Image Annotation Statistical Models
متن کامل
Semiautomatic Image Retrieval Using the High Level Semantic Labels
Content-based image retrieval and text-based image retrieval are two fundamental approaches in the field of image retrieval. The challenges related to each of these approaches, guide the researchers to use combining approaches and semi-automatic retrieval using the user interaction in the retrieval cycle. Hence, in this paper, an image retrieval system is introduced that provided two kind of qu...
متن کامل