Separation of Line Drawings Based on Split Faces for 3D Object Reconstruction

Zhang, Changqing; Yang, Heng; Liu, Jianzhuang

doi:10.1109/cvpr.2014.94

Cited by 11 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Significant progress has been made on sketch understanding and sketch-based modeling in computer vision and graphics recently [9,20,39,29,7,24,11,34,23,14,37]. Several large-scale sketch datasets [9,19,10] have also been constructed and utilized along the way.…”

Section: Introductionmentioning

confidence: 99%

SketchyScene: Richly-Annotated Scene Sketches

Zhang

et al. 2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

It is a sunny day.It is a family picnic. There are four people, a basket, two apples, one cup,two bananas, and on a picnic rug. There is two trees in the distance.Abstract. We contribute the first large-scale dataset of scene sketches, SketchyScene, with the goal of advancing research on sketch understanding at both the object and scene level. The dataset is created through a novel and carefully designed crowdsourcing pipeline, enabling users to efficiently generate large quantities of realistic and diverse scene sketches. SketchyScene contains more than 29,000 scene-level sketches, 7,000+ pairs of scene templates and photos, and 11,000+ object sketches. All objects in the scene sketches have ground-truth semantic and instance masks. The dataset is also highly scalable and extensible, easily allowing augmenting and/or changing scene composition. We demonstrate the potential impact of SketchyScene by training new computational models for semantic segmentation of scene sketches and showing how the new dataset enables several applications including image retrieval, sketch colorization, editing, and captioning, etc. The dataset and code can be found at https://github.com/SketchyScene/SketchyScene.

show abstract

Section: Introductionmentioning

confidence: 99%

SketchyScene: Richly-Annotated Scene Sketches

Zhang

et al. 2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…It took less than 2 min (varying from 91 to 126 s) to reconstruct complete objects from these initial 2-D wireframes. The reconstruction process might be significantly speeded up by first decomposing a complex object into several parts using the algorithm in [26] and then performing incremental reconstructions of individual parts.…”

Section: Experiments and Discussionmentioning

confidence: 99%

Sketch-based 3-D modeling for piecewise planar objects in single images

Zhang

Peng

et al. 2015

Computers & Graphics

Self Cite

View full text Add to dashboard Cite

“…Given a set of 2D lines in an image which captures a 3D model represented by a set of 3D lines one has to find the camera pose from which sufficiently large number of projected 3D lines align with the 2D lines. This problem gains prominence due to the extensive usage of line sketches for 3D modeling [22]. Searching correspondence or pose space exhaustively purely based on geometry is highly complex.…”

Section: A Challenges Main Contributions and Overviewmentioning

confidence: 99%

Geometry based exhaustive line correspondence determination

Srikrishna

Musti

Heikkilä

2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

In this paper we propose a purely geometric approach to establish correspondence between 3D line segments in a given model and 2D line segments detected in an image. Contrary to the existing methods which use strong assumptions on camera pose, we perform exhaustive search in order to compute maximum number of geometrically permitted correspondences between a 3D model and 2D lines. We present a novel theoretical framework in which we sample the space of camera axis direction (which is bounded and hence can be densely sampled unlike the unbounded space of camera position) and show that geometric constraints arising from it reduce rest of the computation to simple operations of finding camera position as the intersection of 3 planes. These geometric constraints can be represented using indexed arrays which accelerate it further. The algorithm returns all sets of correspondences and associated camera poses having high geometric consensus. The obtained experimental results show that our method has better asymptotic behavior than conventional approach. We also show that with the inclusion of additional sensor information our method can be used to initialize pose in just few seconds in many practical situations.

show abstract

Separation of Line Drawings Based on Split Faces for 3D Object Reconstruction

Cited by 11 publications

References 21 publications

SketchyScene: Richly-Annotated Scene Sketches

SketchyScene: Richly-Annotated Scene Sketches

Sketch-based 3-D modeling for piecewise planar objects in single images

Geometry based exhaustive line correspondence determination

Contact Info

Product

Resources

About