Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches

04/01/2021
by   Benoit Guillard, et al.
0

Reconstructing 3D shape from 2D sketches has long been an open problem because the sketches only provide very sparse and ambiguous information. In this paper, we use an encoder/decoder architecture for the sketch to mesh translation. This enables us to leverage its latent parametrization to represent and refine a 3D mesh so that its projections match the external contours outlined in the sketch. We will show that this approach is easy to deploy, robust to style changes, and effective. Furthermore, it can be used for shape refinement given only single pen strokes. We compare our approach to state-of-the-art methods on sketches – both hand-drawn and synthesized – and demonstrate that we outperform them.

READ FULL TEXT

page 3

page 6

page 11

page 13

research
03/01/2023

Sketch2Cloth: Sketch-based 3D Garment Generation with Unsigned Distance Fields

3D model reconstruction from a single image has achieved great progress ...
research
06/09/2023

SENS: Sketch-based Implicit Neural Shape Modeling

We present SENS, a novel method for generating and editing 3D models fro...
research
07/20/2017

3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks

We propose a method for reconstructing 3D shapes from 2D sketches in the...
research
01/09/2020

Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches

Sketch-based image editing aims to synthesize and modify photos based on...
research
06/26/2014

DASS: Detail Aware Sketch-Based Surface Modeling

We present a sketch-based modeling system suitable for detail editing, b...
research
08/23/2021

Black-Box Test-Time Shape REFINEment for Single View 3D Reconstruction

Much recent progress has been made in reconstructing the 3D shape of an ...

Please sign up or login with your details

Forgot password? Click here to reset