General virtual sketching framework for vector line art

Mo, Haoran; Simo-Serra, Edgar; Gao, Chengying; Zhang, Changqing; Wang, Ruomei

doi:10.1145/3476576.3476598

Cited by 6 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Association with Other Sketches Some CNN based models designed for other kinds of sketches (e.g., well-drawn line drawings [16], [177], [287], [329], cartoons [16], [177]) can be applied to free-hand sketch. In particular, it has been verified by relevant literature that CNN models oriented at high-quality line drawings can be successful for free-hand sketch tasks, including vectorization [155], [164], [330], [331], shading [332], inking [333], etc. It is interesting to evaluate which methods designed for other sketches can or cannot be applied to free-hand sketches.…”

Section: Sketch-specific Designmentioning

confidence: 88%

Deep Learning for Free-Hand Sketch: A Survey

Xu¹,

Hospedales²,

Yin³

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Free-hand sketches are highly illustrative, and have been widely used by humans to depict objects or stories from ancient times to the present. The recent prevalence of touchscreen devices has made sketch creation a much easier task than ever and consequently made sketch-oriented applications increasingly popular. The progress of deep learning has immensely benefited free-hand sketch research and applications. This paper presents a comprehensive survey of the deep learning techniques oriented at free-hand sketch data, and the applications that they enable. The main contents of this survey include: (i) A discussion of the intrinsic traits and unique challenges of free-hand sketch, to highlight the essential differences between sketch data and other data modalities, e.g., natural photos. (ii) A review of the developments of free-hand sketch research in the deep learning era, by surveying existing datasets, research topics, and the state-of-the-art methods through a detailed taxonomy and experimental evaluation. (iii) Promotion of future work via a discussion of bottlenecks, open problems, and potential research directions for the community.

show abstract

Section: Sketch-specific Designmentioning

confidence: 88%

Deep Learning for Free-Hand Sketch: A Survey

Xu¹,

Hospedales²,

Yin³

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…More recently, researchers have leveraged deep learning machinery towards image vectorization [EVA*20,GZH*19,GTG*19, LWKF17, ZQM19, DYH*21, LHES19, CDAT20, LLMRK20, RGLM21, KWOG18, MSSG*21]. These approaches either formulate vectorization as a segmentation task [KWOG18] or predict a fixed number of curves [CDAT20, LHES19].…”

Section: Related Workmentioning

confidence: 99%

Singularity‐Free Frame Fields for Line Drawing Vectorization

Guţan,

Hegde,

Berumen

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

State‐of‐the‐art methods for line drawing vectorization rely on generated frame fields for robust direction disambiguation, with each of the two axes aligning to different intersecting curve tangents around junctions. However, a common source of topological error for such methods are frame field singularities. To remedy this, we introduce the first frame field optimization framework guaranteed to produce singularity‐free fields aligned to a line drawing. We first perform a convex solve for a roughly‐aligned orthogonal frame field (cross field), and then comb away its internal singularities with an optimal transport–based matching. The resulting topology of the field is strictly maintained with the machinery of discrete trivial connections in a final, non‐convex optimization that allows non‐orthogonality of the field, improving smoothness and tangent alignment. Our frame fields can serve as a drop‐in replacement for frame field optimizations used in previous work, improving the quality of the final vectorizations.

show abstract

“…On the other hand, Gao et al, Egiazarian et al, and Mo et al attempted (Li et al 2020) to generate lines sequentially. Both (Gao et al 2019), (Egiazarian et al 2020), and(Mo et al 2021) rely on the supervision on curve primitives, i.e.primitive-level supervision. However, these methods supervise the primitives of strokes independently without considering the semantics of the strokes, e.g., how each stroke contributes to the overall line drawing.…”

Section: Line-drawing Vectorizationmentioning

confidence: 99%

“…1(b)). Another stream of methods first identifies smooth stroke segments and then connects the stroke segments into strokes based on local properties, such as proximity and continuity (Bessmeltsev and Solomon 2019; Egiazarian et al 2020;Noris et al 2013;Stanko et al 2020;Mo et al 2021). However, the quality of stroke connection generally cannot be guaranteed, leading to obvious broken stroke segments (Fig.…”

Section: Introductionmentioning

confidence: 99%

End-to-End Line Drawing Vectorization

Liu

et al. 2022

AAAI

View full text Add to dashboard Cite

Vector graphics is broadly used in a variety of forms, such as illustrations, logos, posters, billboards, and printed ads. Despite its broad use, many artists still prefer to draw with pen and paper, which leads to a high demand of converting raster designs into the vector form. In particular, line drawing is a primary art and attracts many research efforts in automatically converting raster line drawings to vector form. However, the existing methods generally adopt a two-step approach, stroke segmentation and vectorization. Without vector guidance, the raster-based stroke segmentation frequently obtains unsatisfying segmentation results, such as over-grouped strokes and broken strokes. In this paper, we make an attempt in proposing an end-to-end vectorization method which directly generates vectorized stroke primitives from raster line drawing in one step. We propose a Transformer-based framework to perform stroke tracing like human does in an automatic stroke-by-stroke way with a novel stroke feature representation and multi-modal supervision to achieve vectorization with high quality and fidelity. Qualitative and quantitative evaluations show that our method achieves state of the art performance.

show abstract

General virtual sketching framework for vector line art

Cited by 6 publications

References 17 publications

Deep Learning for Free-Hand Sketch: A Survey

Deep Learning for Free-Hand Sketch: A Survey

Singularity‐Free Frame Fields for Line Drawing Vectorization

End-to-End Line Drawing Vectorization

Contact Info

Product

Resources

About