3D Geometry from Uncalibrated Images

Kamberov, G.; Kamberova, Gerda; Chum, Ondřej; Obdržálek, Štěpán; Martinec, Daniel; Kostková, Jana; Pajdla, Tomáš; Matas, Jiřı́; Šára, Radim

doi:10.1007/11919629_80

Cited by 9 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Commonly, MVS methods assume a relatively uniform viewpoint distribution and simply choose the k nearest images for each reference view [19,4,6]. CPC datasets are more challenging in that they are non-uniformly distributed in a 7D viewpoint space of camera pose and focal length, thus representing an extreme case of unorganized image sets [12]. Furthermore, choosing the nearest views is often undesirable, since many images are nearly identical and thus offer little parallax.…”

Section: Previous Workmentioning

confidence: 99%

“…Our work is closely related to Kamberov et al's automatic geometry reconstruction pipeline for unstructured image sets [12]. The key algorithmic differences are our use of MVS instead of binocular stereo for each reference view and our view selection approach, which accounts for variations in image resolution and avoids matching narrow baselines.…”

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi-View Stereo for Community Photo Collections

Goesele

Snavely

Curless

et al. 2007

2007 IEEE 11th International Conference on Computer Vision

580

415

View full text Add to dashboard Cite

We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clutter, and other effects in large online community photo collections. Our idea is to intelligently choose images to match, both at a per-view and per-pixel level. We show that such adaptive view selection enables robust performance even with dramatic appearance variability. The stereo matching technique takes as input sparse 3D points reconstructed from structure-from-motion methods and iteratively grows surfaces from these points. Optimizing for surface normals within a photoconsistency measure significantly improves the matching results. While the focus of our approach is to estimate high-quality depth maps, we also show examples of merging the resulting depth maps into compelling scene reconstructions. We demonstrate our algorithm on standard multi-view stereo datasets and on casually acquired photo collections of famous scenes gathered from the Internet.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

Multi-View Stereo for Community Photo Collections

Goesele

Snavely

Curless

et al. 2007

2007 IEEE 11th International Conference on Computer Vision

580

415

View full text Add to dashboard Cite

show abstract

“…Existing pipelines either assume known internal parameters [26,27,19,28,29,15,24], or constant internal parameters [30], or rely on EXIF data plus external information (camera CCD dimensions) [31,32]. Methods working in large scale environments usually rely on a lot of additional information, such as camera calibration and GPS/INS navigation systems [2,33] or geotags [17].…”

Section: Structure-and-motion: Related Workmentioning

confidence: 99%

Hierarchical structure-and-motion recovery from uncalibrated images

Toldo

Gherardi

Farenzena

et al. 2015

Computer Vision and Image Understanding

100

View full text Add to dashboard Cite

This paper addresses the structure-and-motion problem, that requires to find camera motion and 3D structure from point matches. A new pipeline, dubbed Samantha, is presented, that departs from the prevailing sequential paradigm and embraces instead a hierarchical approach. This method has several advantages, like a provably lower computational complexity, which is necessary to achieve true scalability, and better error containment, leading to more stability and less drift. Moreover, a practical autocalibration procedure allows to process images without ancillary information. Experiments with real data assess the accuracy and the computational efficiency of the method.

show abstract

“…Relevant literature comprises several Structure and Motion (SaM) pipelines that process images in batch and handle the reconstruction process making no assumptions on the imaged scene and on the acquisition rig (Brown and Lowe, 2005, Kamberov et al, 2006, Snavely et al, 2006, Vergauwen and Gool, 2006, Irschara et al, 2007.…”

Section: Introductionmentioning

confidence: 99%

Automatic Camera Orientation and Structure Recovery With Samantha

Gherardi

Toldo

Garro

et al. 2012

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:SAMANTHA is a software capable of computing camera orientation and structure recovery from a sparse block of casual images without human intervention. It can process both calibrated images or uncalibrated, in which case an autocalibration routine is run. Pictures are organized into a hierarchical tree which has single images as leaves and partial reconstructions as internal nodes. The method proceeds bottom up until it reaches the root node, corresponding to the final result. This framework is one order of magnitude faster than sequential approaches, inherently parallel, less sensitive to the error accumulation causing drift. We have verified the quality of our reconstructions both qualitatively producing compelling point clouds and quantitatively, comparing them with laser scans serving as ground truth.

show abstract

3D Geometry from Uncalibrated Images

Cited by 9 publications

References 25 publications

Multi-View Stereo for Community Photo Collections

Multi-View Stereo for Community Photo Collections

Hierarchical structure-and-motion recovery from uncalibrated images

Automatic Camera Orientation and Structure Recovery With Samantha

Contact Info

Product

Resources

About