计算机视觉2007年CVPR

需积分: 50 99 浏览量更新于2023-03-03 评论收藏 6.53MB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

资源详情

资源评论

资源推荐

Accurate, Dense, and Robust Multi-View Stereopsis

Yasutaka Furukawa

Department of Computer Science

and Beckman Institute

University of Illinois at Urbana-Champaign, USA

Jean Ponce

1,2

Willow Team–ENS/INRIA/ENPC

D´epartement d’Informatique

Ecole Normale Sup´erieure, Paris, France

Abstract: This paper proposes a novel algorithm for calibrated

multi-view stereopsis that outputs a (quasi) dense set of rectan-

gular patches covering the surfaces visible in the input images.

This algorithm does not require any initialization in the form of a

bounding volume, and it detects and discards automatically out-

liers and obstacles. It does not perform any smoothing across

nearby features, yet is currently the top performer in terms of both

coverage and accuracy for four of the six benchmark datasets pre-

sented in [20]. The keys to its performance are effective tech-

niques for enforcing local photometric consistency and global

visibility constraints. Stereopsis is implemented as a match, ex-

pand, and ﬁlter procedure, starting from a sparse set of matched

keypoints, and repeatedly expanding these to nearby pixel corre-

spondences before using visibility constraints to ﬁlter away false

matches. A simple but effective method for turning the resulting

patch model into a mesh appropriate for image-based modeling is

also presented. The proposed approach is demonstrated on vari-

ous datasets including objects with ﬁne surface details, deep con-

cavities, and thin structures, outdoor scenes observed from a re-

stricted set of viewpoints, and “crowded” scenes where moving

obstacles appear in different places in multiple images of a static

structure of interest.

1. Introduction

As in the binocular case, although most early work in

multi-view stereopsis (e.g., [12, 15, 19]) tended to match

and reconstruct all scene points independently, recent ap-

proaches typically cast this problem as a variational one,

where the objective is to ﬁnd the surface minimizing a

global photometric discrepancy functional, regularized by

explicit smoothness constraints [1, 8, 17, 18, 22, 23](age-

ometric consistency terms is sometimes added as well [3,

4, 7, 9]). Competing approaches mostly differ in the type

of optimization techniques that they use, ranging from

local methods such as gradient descent [3, 4, 7], level

sets [1, 9, 18], or expectation maximization [21], to global

ones such as graph cuts [3, 8, 17, 22, 23]. The variational

approach has led to impressive progress, and several of the

methods recently surveyed by Seitz et al. [20] achieve a rel-

ative accuracy better than 1/200 (1mm for a 20cm wide ob-

ject) from a set of low-resolution (640×480) images. How-

ever, it typically requires determining a bounding volume

(valid depth range, bounding box, or visual hull) prior to

initiating the optimization process, which may not be feasi-

ble for outdoor scenes and/or cluttered images.

We pr o-

pose instead a simple and efﬁcient algorithm for calibrated

multi-view stereopsis that does not require any initializa-

tion, is capable of detecting and discarding outliers and ob-

stacles, and outputs a (quasi) dense collection of small ori-

ented rectangular patches [6, 13], obtained from pixel-level

correspondences and tightly covering the observed surfaces

except in small textureless or occluded regions. It does not

perform any smoothing across nearby features, yet is cur-

rently the top performer in terms of both coverage and accu-

racy for four of the six benchmark datasets provided in [20].

The keys to its performance are effective techniques for en-

forcing local photometric consistency and global visibility

constraints. Stereopsis is implemented as a match, expand,

and ﬁlter procedure, starting from a sparse set of matched

keypoints, and repeatedly expanding these to nearby pixel

correspondences before using visibility constraints to ﬁl-

ter away false matches. A simple but effective method for

turning the resulting patch model into a mesh suitable for

image-based modeling is also presented. The proposed ap-

proach is applied to three classes of datasets:

• objects, where a single, compact object is usually fully

visible in a set of uncluttered images taken from all around

it, and it is relatively straightforward to extract the apparent

contours of the object and compute its visual hull;

• scenes, where the target object(s) may be partially oc-

cluded and/or embedded in clutter, and the range of view-

points may be severely limited, preventing the computation

of effective bounding volumes (typical examples are out-

door scenes with buildings or walls); and

In addition, variational approaches typically involve massive opti-

mization tasks with tens of thousands of coupled variables, potentially

limiting the resolution of the corresponding reconstructions (see, however,

[18] for a fast GPU implementation). We will revisit tradeoffs between

computational efﬁciency and reconstruction accuracy in Sect. 5.

本内容试读结束，登录后可阅读更多

下载后可阅读完整内容，剩余7页未读，立即下载

Slayers_Nada

粉丝: 10
资源: 1

会员权益专享

计算机视觉2007年CVPR

评论0

会员权益专享

最新资源

计算机视觉2007年CVPR

评论0

CVPR2007_tutorial_bag_of_words

CVPR2007_Learning_to_detect_a_salient_object

计算机视觉CVPR论文

计算机视觉领域有哪些顶级会议

cvpr2022汇总 分类

计算机视觉技在哪学习？

手势识别cvpr2023

2022年的CVPR的内容主要有哪些

cvpr2023 图像配准

cvpr中的传统算法

cvpr2000上的代码

cvpr2022注意力机制

inpaint算法 cvpr

cvpr2023 注意力机制

cvpr和cvprw区别

TPAMI和CVPR谁的等级高

cvpr的latex模板

indoor cvpr

CVPR 的Image matching challenge你知道吗，介绍一下

cvpr2022语义分割

会员权益专享

最新资源

cvpr2022汇总分类