Deep learning for free-hand sketch: A survey
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 …
objects or stories from ancient times to the present. The recent prevalence of touchscreen …
[PDF][PDF] OpenSketch: a richly-annotated dataset of product design sketches.
Y Gryaditskaya, M Sypesteyn, JW Hoftijzer… - ACM Trans …, 2019 - academia.edu
Product designers extensively use sketching to reason and communicate about 3D shapes,
as documented in popular design sketching textbooks [Eissen and Steur 2008, 2011; Pipes …
as documented in popular design sketching textbooks [Eissen and Steur 2008, 2011; Pipes …
[HTML][HTML] Information extraction and knowledge linkage of geological profiles and related contextual texts from mineral exploration reports for geological knowledge …
Geological profiles serve as invaluable repositories of data for knowledge extraction and the
identification of geological entities, constituting a fundamental resource in scientific …
identification of geological entities, constituting a fundamental resource in scientific …
Deep vectorization of technical drawings
We present a new method for vectorization of technical line drawings, such as floor plans,
architectural drawings, and 2D CAD images. Our method includes (1) a deep learning …
architectural drawings, and 2D CAD images. Our method includes (1) a deep learning …
Image vectorization and editing via linear gradient layer decomposition
A key advantage of vector graphics over raster graphics is their editability. For example,
linear gradients define a spatially varying color fill with a few intuitive parameters, which are …
linear gradients define a spatially varying color fill with a few intuitive parameters, which are …
A benchmark for rough sketch cleanup
Sketching is a foundational step in the design process. Decades of sketch processing
research have produced algorithms for 3D shape interpretation, beautification, animation …
research have produced algorithms for 3D shape interpretation, beautification, animation …
Scene sketch semantic segmentation with hierarchical Transformer
J Yang, A Ke, Y Yu, B Cai - Knowledge-Based Systems, 2023 - Elsevier
Abstract Convolutional Neural Networks (CNNs) have always been the dominant method for
scene sketch semantic segmentation, but their performance seems to have plateaued due to …
scene sketch semantic segmentation, but their performance seems to have plateaued due to …
Stripmaker: Perception-driven learned vector sketch consolidation
Artist sketches often use multiple overdrawn strokes to depict a single intended curve.
Humans effortlessly mentally consolidate such sketches by detecting groups of overdrawn …
Humans effortlessly mentally consolidate such sketches by detecting groups of overdrawn …
General virtual sketching framework for vector line art
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 …
create. We introduce a general framework to produce line drawings from a wide variety of …
De-rendering stylized texts
Editing raster text is a promising but challenging task. We propose to apply text vectorization
for the task of raster text editing in display media, such as posters, web pages, or …
for the task of raster text editing in display media, such as posters, web pages, or …