Feature-Based Texture Synthesis

Lee, Tong‐Yee; Yan, Chung-Ren

doi:10.1007/11424857_112

Cited by 4 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In d overlapping computation, we enforce L-shape neighbors as a constraint and use the feature-weighted function [28] to assign weights to each pixel in L-shape neighbors to calculate the similarity. In addition, their prioritized pixel resynthesis method [28] is also applied to the overlapping regions of the patches to reduce the artifacts.…”

Section: Key Map Synthesis At the Coarsest Levelmentioning

confidence: 99%

Stylized Rendering Using Samples of a Painted Image

Yan

Chi

Lee

et al. 2008

IEEE Trans. Visual. Comput. Graphics

Self Cite

View full text Add to dashboard Cite

Abstract-We introduce a novel technique to generate painterly art maps (PAMs) for 3D nonphotorealistic rendering. Our technique can automatically transfer brushstroke textures and color changes to 3D models from samples of a painted image. Therefore, the generation of stylized images or animation in the style of a given artwork can be achieved. This new approach works particularly well for a rich variety of brushstrokes ranging from simple 1D and 2D line-art strokes to very complicated ones with significant variations in stroke characteristics. During the rendering or animation process, the coherence of brushstroke textures and color changes over 3D surfaces can be well maintained. With PAM, we can also easily generate the illusion of flow animation over a 3D surface to convey the shape of a model.

show abstract

Section: Key Map Synthesis At the Coarsest Levelmentioning

confidence: 99%

Stylized Rendering Using Samples of a Painted Image

Yan

Chi

Lee

et al. 2008

IEEE Trans. Visual. Comput. Graphics

Self Cite

View full text Add to dashboard Cite

show abstract

Scene-Aware Style Transferring Using GIST

Toyoura

Abe

Mao

2017

Transactions on Computational Science XXX

View full text Add to dashboard Cite

Patch-Based Synthesis for Non-frontal-parallel Textures (NFPT)

Yan

Lee

Lin

First International Conference on Innovative Computing, Information and Control - Volume I (ICICIC'06)

View full text Add to dashboard Cite

In this paper, we propose a new patch-based texture synthesis method. The proposed method consists of two main components: a feature-weighted similarity and a pixel-based re-synthesis step. Most existing patchbased methods can only handle for frontal-parallel textures (FPT) and generate poorly synthesized results for non-frontal-parallel textures (NFPT). To better synthesize NFPT, we enhance the proposed method with a view warping technique. As a result, the proposed method can handle well for FPT and NFPT.

show abstract

Feature-Based Texture Synthesis

Cited by 4 publications

References 9 publications

Stylized Rendering Using Samples of a Painted Image

Stylized Rendering Using Samples of a Painted Image

Scene-Aware Style Transferring Using GIST

Patch-Based Synthesis for Non-frontal-parallel Textures (NFPT)

Contact Info

Product

Resources

About