Constrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawings

Shaheen, Sara; Affara, Lama; Ghanem, Bernard

doi:10.1109/iccv.2017.474

Cited by 6 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The curves that only contain very few pixels are eliminated to ensure the fitting performance. The cubic Bezier curve can model a great diversity of curves by only four control pivots [39]. As shown in Figure 2, if we change the coordinates of the control pivots, we can get a series of points, which form a new curve.…”

Section: Bezier Pivot Based Sketch Deformationmentioning

confidence: 99%

Sketch-Specific Data Augmentation for Freehand Sketch Recognition

Zheng

Yao

Sun

et al. 2019

Preprint

View full text Add to dashboard Cite

Sketch recognition remains a significant challenge due to the limited training data and the substantial intra-class variance of freehand sketches for the same object. Conventional methods for this task often rely on the availability of the temporal order of sketch strokes, additional cues acquired from different modalities and supervised augmentation of sketch datasets with real images, which also limit the applicability and feasibility of these methods in real scenarios.In this paper, we propose a novel sketch-specific data augmentation (SSDA) method that leverages the quantity and quality of the sketches automatically.From the aspect of quantity, we introduce a Bezier pivot based deformation (BPD) strategy to enrich the training data. Towards quality improvement, we present a mean stroke reconstruction (MSR) approach to generate a set of novel types of sketches with smaller intra-class variances. Both of these solutions are unrestricted from any multi-source data and temporal cues of sketches. Furthermore, we show that some recent deep convolutional neural network models that are trained on generic classes of real images can be better choices than most of the elaborate architectures that are designed explicitly for sketch recognition.

show abstract

Section: Bezier Pivot Based Sketch Deformationmentioning

confidence: 99%

Sketch-Specific Data Augmentation for Freehand Sketch Recognition

Zheng

Yao

Sun

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Convolutional Sparse Coding (CSC) is a rich image representation model that is inspired by the response of neurons to stimuli within their receptive fields for human vision. It is applied to various computer vision tasks such as image and video processing [1,2,3,4,5], computational imaging [6], line drawings [7], tracking [8] as well as the design of deep learning architectures [9]. CSC is a special type of sparse dictionary learning (DL) algorithm, in which it uses the convolution operator, unlike traditional DL that uses regular linear combinations.…”

Section: Discriminability Tradeoff Training Example Images Groundtruthmentioning

confidence: 99%

Supervised Convolutional Sparse Coding

Affara,

Ghanem,

Wonka

2018

Preprint

Self Cite

View full text Add to dashboard Cite

Convolutional Sparse Coding (CSC) is a well established image representation model especially suited for image restoration tasks.In this work, we extend the applicability of this model by proposing a supervised approach to convolutional sparse coding, which aims at learning discriminative dictionaries instead of purely reconstructive ones. We incorporate a supervised regularization term into the traditional unsupervised CSC objective to encourage the final dictionary elements to be discriminative. Experimental results show that using supervised convolutional learning results in two key advantages. First, we learn more semantically relevant filters in the dictionary and second, we achieve improved image reconstruction on unseen data.

show abstract

Remote Sensing Image Sharpening by Integrating Multispectral Image Super-Resolution and Convolutional Sparse Representation Fusion

Zhao

Zhang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Constrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawings

Cited by 6 publications

References 20 publications

Sketch-Specific Data Augmentation for Freehand Sketch Recognition

Sketch-Specific Data Augmentation for Freehand Sketch Recognition

Supervised Convolutional Sparse Coding

Remote Sensing Image Sharpening by Integrating Multispectral Image Super-Resolution and Convolutional Sparse Representation Fusion

Contact Info

Product

Resources

About