TCB-spline-based Image Vectorization

Abstract

Vector image representation methods that can faithfully reconstruct objects and color variations in a raster image are desired in many practical applications. This paper presents triangular configuration B-spline (referred to as TCB-spline)-based vector graphics for raster image vectorization. Based on this new representation, an automatic raster image vectorization paradigm is proposed. The proposed framework first detects sharp curvilinear features in the image and constructs knot meshes based on the detected feature lines. It iteratively optimizes color and position of control points and updates the knot meshes. By using collinear knots at feature lines, both smooth and discontinuous color variations can be efficiently modeled by the same set of quadratic TCB-splines. A variational knot mesh generation method is designed to adaptively introduce knots and update their connectivity in order to satisfy the local reconstruction quality. Experiments and comparisons show that our framework outperforms the existing state-of-the-art methods in providing more faithful reconstruction results. In particular, our method is able to model undetected features and subtle or complicated color variations in-between features, which the previous methods cannot handle efficiently. Our vectorization representation also facilitates a variety of editing operations performed directly over vector images.

A Survey of Smooth Vector Graphics: Recent Advances in Repr esentation, Creation, Rasterization, and Image Vectorization

“…In addition, a sharpness factor is stored at the edges to control edge smoothness. Generally, the subdivision-based approaches may generate an excess amount of primitives, and can be strongly dependent on the feature extraction output [146]. Recently, Zhu et al [146] proposed to use quadratic triangle configuration B-splines (TCBs) [19], [112] to faithfully depict complex color variations while remaining C 1 continuous.…”

“…Generally, the subdivision-based approaches may generate an excess amount of primitives, and can be strongly dependent on the feature extraction output [146]. Recently, Zhu et al [146] proposed to use quadratic triangle configuration B-splines (TCBs) [19], [112] to faithfully depict complex color variations while remaining C 1 continuous. An image can be treated as a surface in 5D (geometry and color) and can therefore be approximated and refined as a TCB-spline surface.…”

“…Liao et al [84] accelerated the rendering by a GPU-based patch subdivision. Zhu et al [146] used TCB-spline interpolation for image reconstruction.…”

Error‐bounded Image Triangulation

“…For example, Zhu et al . [ZCX*22] utilize a 2D knot mesh to capture image features and approximate the 2D geometry information of the mesh and 3D color information of the image using a 5D TCB‐spline surface. However, they emphasize similarity and smoothness through refinement, whereas we focus more on simplicity and abstraction through simplification (Fig.…”

“…Compared with [ZCX*22] (a), our method generates a curved image triangulation with the same color error (b). There are 19263 knots in their knot mesh and 4036 knots in our mesh.…”