Saved in:
Bibliographic Details
Main Authors: Chen, Mingxiang, Zhang, Jian, Zhou, Boli, Song, Yang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.09050
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916247145283584
author Chen, Mingxiang
Zhang, Jian
Zhou, Boli
Song, Yang
author_facet Chen, Mingxiang
Zhang, Jian
Zhou, Boli
Song, Yang
contents Recent advancements in deep learning for 3D models have propelled breakthroughs in generation, detection, and scene understanding. However, the effectiveness of these algorithms hinges on large training datasets. We address the challenge by introducing Efficient 3D Seam Carving (E3SC), a novel 3D model augmentation method based on seam carving, which progressively deforms only part of the input model while ensuring the overall semantics are unchanged. Experiments show that our approach is capable of producing diverse and high-quality augmented 3D shapes across various types and styles of input models, achieving considerable improvements over previous methods. Quantitative evaluations demonstrate that our method effectively enhances the novelty and quality of shapes generated by other subsequent 3D generation algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2405_09050
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle 3D Shape Augmentation with Content-Aware Shape Resizing
Chen, Mingxiang
Zhang, Jian
Zhou, Boli
Song, Yang
Computer Vision and Pattern Recognition
Recent advancements in deep learning for 3D models have propelled breakthroughs in generation, detection, and scene understanding. However, the effectiveness of these algorithms hinges on large training datasets. We address the challenge by introducing Efficient 3D Seam Carving (E3SC), a novel 3D model augmentation method based on seam carving, which progressively deforms only part of the input model while ensuring the overall semantics are unchanged. Experiments show that our approach is capable of producing diverse and high-quality augmented 3D shapes across various types and styles of input models, achieving considerable improvements over previous methods. Quantitative evaluations demonstrate that our method effectively enhances the novelty and quality of shapes generated by other subsequent 3D generation algorithms.
title 3D Shape Augmentation with Content-Aware Shape Resizing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.09050