Supervised Semantic Gradient Extraction Using Linear-Time Optimization

Yang, Shulin; Wang, Jue; Shapiro, Linda G.

doi:10.1109/cvpr.2013.364

Cited by 2 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our results are visually comparable to those of EZ-Sketching [8], and superior to those of Ref. [16] and both naive approaches in terms of smoothness and conciseness. We further used the precision P , ( recall R, and F -measure (the weighted harmonic mean of P and R) to evaluate edge detection accuracy.…”

Section: Discussionsupporting

confidence: 75%

“…Our system can contribute to this line of work by serving as an efficient tool for generating line abstractions with various styles. Our work is closely related to the work by Yang et al [16] who also tried to extract semantic gradient edges based on input user strokes. Their system first clusters edge points into edgelets and constructs a graph that encodes the spatial relations between the edges near the user strokes.…”

Section: Related Workmentioning

confidence: 92%

“…In particular, our system is compared with two stateof-the-art methods by Yang et al [16] and Su et al [8] (EZ-Sketching), which share the same goal as our system of generating long coherent lines from user strokes. We also implemented two naive approaches for a baseline comparison, including: (i) extracting lines that are near to the user strokes, within a distance threshold of 15 pixels (NN); and (ii) using all the lines that intersect user strokes (NI).…”

Section: Discussionmentioning

confidence: 99%

“…For a fair comparison, we imitated 10 results shown in Ref. [16] by carefully tracing their user strokes using our coherence strokes. These coherence strokes were also used as input to EZ-Sketching [8] to generate the outputs for comparison.…”

Section: Discussionmentioning

confidence: 99%

“…We evaluate the performance of our coherence line matching algorithm against above four alternatives in terms of visual quality and edge detection accuracy with respect to the ground truth. To do so, we used the same benchmark as Yang et al [16] and took gPb [6] edge maps as input reference line images to our system. For a fair comparison, we imitated 10 results shown in Ref.…”

Section: Discussionmentioning

confidence: 99%

See 4 more Smart Citations

User-guided line abstraction using coherence and structure analysis

Tsai

Lee

et al. 2017

Comp. Visual Media

View full text Add to dashboard Cite

Line drawing is a style of image abstraction where the perceptual content of the image is conveyed using distinct straight or curved lines. However, extracting semantically salient lines is not trivial and mastered only by skilled artists. While many parametric filters have successfully extracted accurate and coherent lines, their results are sensitive to parameter choice and easily lead to either an excessive or insufficient number of lines. In this work, we present an interactive system to generate concise line abstractions of arbitrary images via a few user specified strokes. Specifically, the user simply has to provide a few intuitive strokes on the input images, including tracing roughly along edges and scribbling on the region of interest, through a sketching interface. The system then automatically extracts lines that are long, coherent and share similar textural structures to form a corresponding highly detailed line drawing. We have tested our system with a wide variety of images. Our experimental results show that our system outperforms state-of-the-art techniques in terms of quality and efficiency.

show abstract

Section: Discussionsupporting

confidence: 75%

Section: Related Workmentioning

confidence: 92%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

User-guided line abstraction using coherence and structure analysis

Tsai

Lee

et al. 2017

Comp. Visual Media

View full text Add to dashboard Cite

show abstract

EZ-sketching

Wang

et al. 2014

ACM Trans. Graph.

Self Cite

View full text Add to dashboard Cite

a b c e f d Figure 1: The proposed system automatically refines sketch lines (a, c, e) (created by different users) roughly traced over a single image in a three-level optimization framework. The refined sketches (b, d, f) show closer resemblance to the traced images and are often aesthetically more pleasing, as confirmed by the user study. Image credits: AbstractWe present a new image-guided drawing interface called EZSketching, which uses a tracing paradigm and automatically corrects sketch lines roughly traced over an image by analyzing and utilizing the image features being traced. While previous edge snapping methods aim at optimizing individual strokes, we show that a co-analysis of multiple roughly placed nearby strokes better captures the user's intent. We formulate automatic sketch improvement as a three-level optimization problem and present an efficient solution to it. EZ-Sketching can tolerate errors from various sources such as indirect control and inherently inaccurate input, and works well for sketching on touch devices with small screens using fingers. Our user study confirms that the drawings our approach helped generate show closer resemblance to the traced images, and are often aesthetically more pleasing.

show abstract

Supervised Semantic Gradient Extraction Using Linear-Time Optimization

Cited by 2 publications

References 14 publications

User-guided line abstraction using coherence and structure analysis

User-guided line abstraction using coherence and structure analysis

EZ-sketching

Contact Info

Product

Resources

About