3-D Reconstruction from Sparse Views using Monocular Vision

Saxena, Ashutosh; Sun, Min; Ng, Andrew Y.

doi:10.1109/iccv.2007.4409219

Cited by 22 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Russell et al (2006). They have also been successfully used by Hoiem et al (2007) for surface layout estimation in single images or they have been utilized by Saxena et al (2007) in connection to the single view 3D reconstruction enforcing multiple-view constraints and employing pre-learned priors from a laser scanner.…”

Section: Related Workmentioning

confidence: 98%

See 1 more Smart Citation

Multi-view Superpixel Stereo in Urban Environments

Micusik

Košecká

2010

Int J Comput Vis

View full text Add to dashboard Cite

Urban environments possess many regularities which can be efficiently exploited for 3D dense reconstruction from multiple widely separated views. We present an approach utilizing properties of piecewise planarity and restricted number of plane orientations to suppress reconstruction and matching ambiguities causing failures of standard dense stereo methods. We formulate the problem of the 3D reconstruction in MRF framework built on an image pre-segmented into superpixels. Using this representation, we propose novel photometric and superpixel boundary consistency terms explicitly derived from superpixels and show that they overcome many difficulties of standard pixelbased formulations and handle favorably problematic scenarios containing many repetitive structures and no or low textured regions. We demonstrate our approach on several wide-baseline scenes demonstrating superior performance compared to previously proposed methods.

show abstract

Section: Related Workmentioning

confidence: 98%

“…This notion is widely utilized in single-view reconstruction techniques, e.g. Hoiem et al (2007), Saxena et al (2007).…”

Section: Energy Termsmentioning

confidence: 99%

Multi-view Superpixel Stereo in Urban Environments

Micusik

Košecká

2010

Int J Comput Vis

View full text Add to dashboard Cite

show abstract

“…Saxena et al [59] even incorporates sparse SfM as a cue. These methods rely on strong assumptions about the scene (e.g.…”

Section: Accepted Manuscriptmentioning

confidence: 98%

Efficient edge-aware surface mesh reconstruction for urban scenes

Bdis-Szomor¹,

Riemenschneider²,

Gool

2017

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…For example, [20] [8] build piecewise-planar or highly regularized reconstructions, [1] densely reconstructs individual objects from a particular category (also based on an anchoring idea), and [13] solves jointly for a semantic segmentation and a dense 3D model.…”

Section: Related Workmentioning

confidence: 99%

Shape Anchors for Data-Driven Multi-view Reconstruction

Owens¹,

Xiao

Torralba³

et al. 2013

2013 IEEE International Conference on Computer Vision

View full text Add to dashboard Cite

We present a data-driven method for building dense 3D reconstructions using a combination of recognition and multi-view cues. Our approach is based on the idea that there are image patches that are so distinctive that we can accurately estimate their latent 3D shapes solely using recognition. We call these patches shape anchors, and we use them as the basis of a multi-view reconstruction system that transfers dense, complex geometry between scenes. We "anchor" our 3D interpretation from these patches, using them to predict geometry for parts of the scene that are relatively ambiguous. The resulting algorithm produces dense reconstructions from stereo point clouds that are sparse and noisy, and we demonstrate it on a challenging dataset of real-world, indoor scenes.

show abstract

3-D Reconstruction from Sparse Views using Monocular Vision

Abstract: We

Cited by 22 publications

References 27 publications

Multi-view Superpixel Stereo in Urban Environments

Multi-view Superpixel Stereo in Urban Environments

Efficient edge-aware surface mesh reconstruction for urban scenes

Shape Anchors for Data-Driven Multi-view Reconstruction

Contact Info

Product

Resources

About