SENS: Part-Aware Sketch-based Implicit Neural Shape Modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Binninger, Alexandre, Hertz, Amir, Sorkine-Hornung, Olga, Cohen-Or, Daniel, Giryes, Raja
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910338126970880
author Binninger, Alexandre
Hertz, Amir
Sorkine-Hornung, Olga
Cohen-Or, Daniel
Giryes, Raja
author_facet Binninger, Alexandre
Hertz, Amir
Sorkine-Hornung, Olga
Cohen-Or, Daniel
Giryes, Raja
contents We present SENS, a novel method for generating and editing 3D models from hand-drawn sketches, including those of abstract nature. Our method allows users to quickly and easily sketch a shape, and then maps the sketch into the latent space of a part-aware neural implicit shape architecture. SENS analyzes the sketch and encodes its parts into ViT patch encoding, subsequently feeding them into a transformer decoder that converts them to shape embeddings suitable for editing 3D neural implicit shapes. SENS provides intuitive sketch-based generation and editing, and also succeeds in capturing the intent of the user's sketch to generate a variety of novel and expressive 3D shapes, even from abstract and imprecise sketches. Additionally, SENS supports refinement via part reconstruction, allowing for nuanced adjustments and artifact removal. It also offers part-based modeling capabilities, enabling the combination of features from multiple sketches to create more complex and customized 3D shapes. We demonstrate the effectiveness of our model compared to the state-of-the-art using objective metric evaluation criteria and a user study, both indicating strong performance on sketches with a medium level of abstraction. Furthermore, we showcase our method's intuitive sketch-based shape editing capabilities, and validate it through a usability study.
format Preprint
id arxiv_https___arxiv_org_abs_2306_06088
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SENS: Part-Aware Sketch-based Implicit Neural Shape Modeling
Binninger, Alexandre
Hertz, Amir
Sorkine-Hornung, Olga
Cohen-Or, Daniel
Giryes, Raja
Graphics
Computer Vision and Pattern Recognition
Machine Learning
We present SENS, a novel method for generating and editing 3D models from hand-drawn sketches, including those of abstract nature. Our method allows users to quickly and easily sketch a shape, and then maps the sketch into the latent space of a part-aware neural implicit shape architecture. SENS analyzes the sketch and encodes its parts into ViT patch encoding, subsequently feeding them into a transformer decoder that converts them to shape embeddings suitable for editing 3D neural implicit shapes. SENS provides intuitive sketch-based generation and editing, and also succeeds in capturing the intent of the user's sketch to generate a variety of novel and expressive 3D shapes, even from abstract and imprecise sketches. Additionally, SENS supports refinement via part reconstruction, allowing for nuanced adjustments and artifact removal. It also offers part-based modeling capabilities, enabling the combination of features from multiple sketches to create more complex and customized 3D shapes. We demonstrate the effectiveness of our model compared to the state-of-the-art using objective metric evaluation criteria and a user study, both indicating strong performance on sketches with a medium level of abstraction. Furthermore, we showcase our method's intuitive sketch-based shape editing capabilities, and validate it through a usability study.
title SENS: Part-Aware Sketch-based Implicit Neural Shape Modeling
topic Graphics
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2306.06088