Cloud2Curve: Generation and Vectorization of Parametric Sketches

03/29/2021
by   Ayan Das, et al.
0

Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations. We further aim to model sketches as a sequence of low-dimensional parametric curves. To this end, we propose an inverse graphics framework capable of approximating a raster or waypoint based stroke encoded as a point-cloud with a variable-degree Bézier curve. Building on this module, we present Cloud2Curve, a generative model for scalable high-resolution vector sketches that can be trained end-to-end using point-cloud data alone. As a consequence, our model is also capable of deterministic vectorization which can map novel raster or waypoint based sketches to their corresponding high-resolution scalable Bézier equivalent. We evaluate the generation and vectorization capabilities of our model on Quick, Draw! and K-MNIST datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/04/2020

BézierSketch: A generative model for scalable vector sketches

The study of neural generative models of human sketches is a fascinating...
research
01/25/2019

Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network

Reconstructing a high-resolution 3D model of an object is a challenging ...
research
08/11/2023

Learned Point Cloud Compression for Classification

Deep learning is increasingly being used to perform machine vision tasks...
research
12/04/2019

Spectral-GANs for High-Resolution 3D Point-cloud Generation

Point-clouds are a popular choice for vision and graphics tasks due to t...
research
12/04/2020

ChartPointFlow for Topology-Aware 3D Point Cloud Generation

A point cloud serves as a representation of the surface of a three-dimen...
research
11/15/2016

OctNet: Learning Deep 3D Representations at High Resolutions

We present OctNet, a representation for deep learning with sparse 3D dat...
research
04/02/2020

Learning Formation of Physically-Based Face Attributes

Based on a combined data set of 4000 high resolution facial scans, we in...

Please sign up or login with your details

Forgot password? Click here to reset