Deep Line Drawing Vectorization via Line Subdivision and Topology Reconstruction

Guo, Yuanyuan; Zhang, Zhuming; Han, Chu; Hu, Wenbo; Li, Chengze; Wong, Tien‐Tsin

doi:10.1111/cgf.13818

Cited by 26 publications

(39 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent works have explored using deep learning for vectorization [Carlier et al 2020;Das et al 2021;Egiazarian et al 2020;Gao et al 2019;Guo et al 2019;Kim et al 2018;Li et al 2020;Liu et al 2017;Lopes et al 2019;Reddy et al 2021;Zhou et al 2019a]. These approaches either cast vectorization as a segmentation task [Kim et al 2018], or predict a fixed number of curves either via direct vector supervision [Carlier et al 2020;Lopes et al 2019] or via a differentiable rasterizer [Li et al 2020].…”

Section: Input Bitmapmentioning

confidence: 99%

“…We are inspired by the approaches that separate junction detection and topology reconstruction [Guo et al 2019;Liu et al 2017;Zhou et al 2019a]. Guo et al [2019] use a fully convolutional architecture to infer junctions and centerlines, and disambiguate connectivity around junctions. Zhou et al [2019a] detect straight-line wireframes in photographs.…”

Section: Input Bitmapmentioning

confidence: 99%

“…Zhou et al [2019a] detect straight-line wireframes in photographs. Overall, end-to-end approaches [Das et al 2021;Guo et al 2019], being trained on limited or fully synthetic datasets, struggle to generalize on noisy real pen-and-paper sketches or even on clean digital drawings with variable stroke width. In contrast, we only use learning to detect and classify keypoints, a task that, as we demonstrate, generalizes well (Sec.…”

Section: Input Bitmapmentioning

confidence: 99%

See 2 more Smart Citations

Keypoint-driven line drawing vectorization via PolyVector flow

et al. 2021

View full text Add to dashboard Cite

Line drawing vectorization is a daily task in graphic design, computer animation, and engineering, necessary to convert raster images to a set of curves for editing and geometry processing. Despite recent progress in the area, automatic vectorization tools often produce spurious branches or incorrect connectivity around curve junctions; or smooth out sharp corners. These issues detract from the use of such vectorization tools, both from an aesthetic viewpoint and for feasibility of downstream applications (e.g., automatic coloring or inbetweening). We address these problems by introducing a novel line drawing vectorization algorithm that splits the task into three components: (1) finding keypoints, i.e., curve endpoints, junctions, and sharp corners; (2) extracting drawing topology, i.e., finding connections between keypoints; and (3) computing the geometry of those connections. We compute the optimal geometry of the connecting curves via a novel geometric flow --- PolyVector Flow --- that aligns the curves to the drawing, disambiguating directions around Y-, X-, and T-junctions. We show that our system robustly infers both the geometry and topology of detailed complex drawings. We validate our system both quantitatively and qualitatively, demonstrating that our method visually outperforms previous work.

show abstract

Section: Input Bitmapmentioning

confidence: 99%

Section: Input Bitmapmentioning

confidence: 99%

Section: Input Bitmapmentioning

confidence: 99%

See 1 more Smart Citation

Keypoint-driven line drawing vectorization via PolyVector flow

et al. 2021

View full text Add to dashboard Cite

show abstract

“…VectorNet [Kim et al 2018] combines neural networks and optimization algorithms to segment the raster image into a set of paths, and then uses the existing vectorization techniques, e.g., Potrace, to vectorize each path. Guo et al [2019] use neural networks to subdivide the lines and reconstruct the topology for each junction. Strokes are then traced by curve least-square fitting method.…”

Section: Vectorizationmentioning

confidence: 99%

General virtual sketching framework for vector line art

Simo-Serra

Gao

et al. 2021

ACM Trans. Graph.

View full text Add to dashboard Cite

Vector line art plays an important role in graphic design, however, it is tedious to manually create. We introduce a general framework to produce line drawings from a wide variety of images, by learning a mapping from raster image space to vector image space. Our approach is based on a recurrent neural network that draws the lines one by one. A differentiable rasterization module allows for training with only supervised raster data. We use a dynamic window around a virtual pen while drawing lines, implemented with a proposed aligned cropping and differentiable pasting modules. Furthermore, we develop a stroke regularization loss that encourages the model to use fewer and longer strokes to simplify the resulting vector image. Ablation studies and comparisons with existing methods corroborate the efficiency of our approach which is able to generate visually better results in less computation time, while generalizing better to a diversity of images and applications.

show abstract

“…In recent years, however, there is a growing research interest in vector graphics. Image vectorization i.e., converting raster images to vectors, has been addressed in [34], [20] using deep learning techniques. Vectorization of technical line drawings is studied in [17].…”

Section: Previous Workmentioning

confidence: 99%

SVG-Net: An SVG-based Trajectory Prediction Model

Bahari,

Zehtab,

Khorasani

et al. 2021

Preprint

View full text Add to dashboard Cite

Anticipating motions of vehicles in a scene is an essential problem for safe autonomous driving systems. To this end, the comprehension of the scene's infrastructure is often the main clue for predicting future trajectories. Most of the proposed approaches represent the scene with a rasterized format and some of the more recent approaches leverage custom vectorized formats. In contrast, we propose representing the scene's information by employing Scalable Vector Graphics (SVG). SVG is a well-established format that matches the problem of trajectory prediction better than rasterized formats while being more general than arbitrary vectorized formats. SVG has the potential to provide the convenience and generality of raster-based solutions if coupled with a powerful tool such as CNNs, for which we introduce SVG-Net. SVG-Net is a Transformer-based Neural Network that can effectively capture the scene's information from SVG inputs. Thanks to the selfattention mechanism in its Transformers, SVG-Net can also adequately apprehend relations amongst the scene and the agents. We demonstrate SVG-Net's effectiveness by evaluating its performance on the publicly-available Argoverse forecasting dataset. Finally, we illustrate how, by using SVG, one can benefit from datasets and advancements in other research fronts that also utilize the same input format. Our code is available at https://vita-epfl.github.io/SVGNet/.

show abstract

Deep Line Drawing Vectorization via Line Subdivision and Topology Reconstruction

Cited by 26 publications

References 17 publications

Keypoint-driven line drawing vectorization via PolyVector flow

Keypoint-driven line drawing vectorization via PolyVector flow

General virtual sketching framework for vector line art

SVG-Net: An SVG-based Trajectory Prediction Model

Contact Info

Product

Resources

About