Structure-Preserving Retargeting of Irregular 3D Architecture

晃晃

Structure-Preserving Retargeting of Irregular 3D Architecture

Jinjie Lin1 Daniel Cohen-Or  Hao Zhang  Cheng Liang   Andrei Sharf Oliver Deussen

Baoquan Chen

SIAT Tel-Aviv University Simon Fraser University Ben-Gurion University University of Konstanz





Abstract

We present an algorithm for interactive structure-preserving retar-

geting of irregular 3D architecture models, offering the modeler an

easy-to-use tool to quickly generate a variety of 3D models that re-

semble an input piece in its structural style. Working on a more

global and structural level of the input, our technique allows and

even encourages replication of its structural elements, while taking

into account their semantics and expected geometric interrelations

such as alignments and adjacency. The algorithm performs auto-

matic replication and scaling of these elements while preserving

their structures. Instead of formulating and solving a complex con-

strained optimization, we decompose the input model into a set of

sequences, each of which is a 1D structure that is relatively straight-

forward to retarget. As the sequences are retargeted in turn, they

progressively constrain the retargeting of the remaining sequences.

We demonstrate interactivity and variability of results from our re-

targeting algorithm using many examples modeled after real-world

architectures exhibiting various forms of irregularity.

CR Categories: I.3.5 [Computer Graphics]: Computational Ge-

ometry and Object Modeling—Geometric algorithms, languages,

and systems;

Keywords: Model retargeting, irregular 3D architecture

1 Introduction

Generating a scene with a variety of models that share a common

characteristic or style is a challenging task. In the absence of a

concrete description of the target style, a common approach is to

synthesize by examples, where some notion of style in the example

is preserved in the generated models. A straightforward means of

style-preserving synthesis generates models consisting of contents

taken from the example while preserving their general relation. A

primary example is example-based texture synthesis [Wei et al.

2009] where the imitated styles are mainly of a local nature. Re-

cently, such techniques have been extended to preserve more global

structures in images [Risser et al. 2010; Wu et al. 2010].

Works on inverse procedural modeling can be regarded as abstract-

ing the structure present in the examples into a set of rules and then

synthesizing novel models based on the rules [Aliaga et al. 2007;

Stava et al. 2010; Bokeloh et al. 2010]. For effective rule extraction,

dominant presence of regularities in the examples is essential. In a

rather loose sense, works on image or model retargeting [Shamir

and Sorkine 2009] also represent a form of style-preserving synthe-

sis, where the style is signified by the salient features of the source

model. This direction has led to recent work on example-bases syn-

thesis of facade images [Lefebvre et al. 2010].









全文请下载附件：

C.R.CAN

“再次路过……”我造一个-----特别路过

晃晃

很有心,部分已收录自用,谢谢

tc

佩服，好多阿 ，哈哈

tc

加精、加亮滴铁子，尤其要多丁页丁页

菜刀吻电线

水……生命之源……灌……

菜刀吻电线

不错 非常经典  实用

奇

呵呵，很好，方便罗。

菜刀吻电线

好可爱的字,学习了