Saved in:
Bibliographic Details
Main Authors: Kim, Seunghwan, Park, Sunha, Lee, Seungkyu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.04615
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909482404020224
author Kim, Seunghwan
Park, Sunha
Lee, Seungkyu
author_facet Kim, Seunghwan
Park, Sunha
Lee, Seungkyu
contents Prefracture method is a practical implementation for real-time object destruction that is hardly achievable within performance constraints, but can produce unrealistic results due to its heuristic nature. To mitigate it, we approach the clustering of prefractured mesh generation as an unordered segmentation on point cloud data, and propose leveraging the deep neural network trained on a physics-based dataset. Our novel paradigm successfully predicts the structural weakness of object that have been limited, exhibiting ready-to-use results with remarkable quality.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04615
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Clustering for Prefractured Mesh Generation in Real-time Object Destruction
Kim, Seunghwan
Park, Sunha
Lee, Seungkyu
Computer Vision and Pattern Recognition
Graphics
Prefracture method is a practical implementation for real-time object destruction that is hardly achievable within performance constraints, but can produce unrealistic results due to its heuristic nature. To mitigate it, we approach the clustering of prefractured mesh generation as an unordered segmentation on point cloud data, and propose leveraging the deep neural network trained on a physics-based dataset. Our novel paradigm successfully predicts the structural weakness of object that have been limited, exhibiting ready-to-use results with remarkable quality.
title Neural Clustering for Prefractured Mesh Generation in Real-time Object Destruction
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2502.04615