PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Yong, Yu, Hongshan, Feng, Mingtao, Chen, Tongjia, Li, Zechuan, Ulhaq, Anwaar, Anwar, Saeed, Mian, Ajmal Saeed
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909533531537408
author He, Yong
Yu, Hongshan
Feng, Mingtao
Chen, Tongjia
Li, Zechuan
Ulhaq, Anwaar
Anwar, Saeed
Mian, Ajmal Saeed
author_facet He, Yong
Yu, Hongshan
Feng, Mingtao
Chen, Tongjia
Li, Zechuan
Ulhaq, Anwaar
Anwar, Saeed
Mian, Ajmal Saeed
contents Diffusion probabilistic models are traditionally used to generate colors at fixed pixel positions in 2D images. Building on this, we extend diffusion models to point cloud semantic segmentation, where point positions also remain fixed, and the diffusion model generates point labels instead of colors. To accelerate the denoising process in reverse diffusion, we introduce a noisy label embedding mechanism. This approach integrates semantic information into the noisy label, providing an initial semantic reference that improves the reverse diffusion efficiency. Additionally, we propose a point frequency transformer that enhances the adjustment of high-level context in point clouds. To reduce computational complexity, we introduce the position condition into MLP and propose denoising PointNet to process the high-resolution point cloud without sacrificing geometric details. Finally, we integrate the proposed noisy label embedding, point frequency transformer and denoising PointNet in our proposed dual conditional diffusion model-based network (PointDiffuse) to perform large-scale point cloud semantic segmentation. Extensive experiments on five benchmarks demonstrate the superiority of PointDiffuse, achieving the state-of-the-art mIoU of 74.2\% on S3DIS Area 5, 81.2\% on S3DIS 6-fold and 64.8\% on SWAN dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06094
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentation
He, Yong
Yu, Hongshan
Feng, Mingtao
Chen, Tongjia
Li, Zechuan
Ulhaq, Anwaar
Anwar, Saeed
Mian, Ajmal Saeed
Computer Vision and Pattern Recognition
Diffusion probabilistic models are traditionally used to generate colors at fixed pixel positions in 2D images. Building on this, we extend diffusion models to point cloud semantic segmentation, where point positions also remain fixed, and the diffusion model generates point labels instead of colors. To accelerate the denoising process in reverse diffusion, we introduce a noisy label embedding mechanism. This approach integrates semantic information into the noisy label, providing an initial semantic reference that improves the reverse diffusion efficiency. Additionally, we propose a point frequency transformer that enhances the adjustment of high-level context in point clouds. To reduce computational complexity, we introduce the position condition into MLP and propose denoising PointNet to process the high-resolution point cloud without sacrificing geometric details. Finally, we integrate the proposed noisy label embedding, point frequency transformer and denoising PointNet in our proposed dual conditional diffusion model-based network (PointDiffuse) to perform large-scale point cloud semantic segmentation. Extensive experiments on five benchmarks demonstrate the superiority of PointDiffuse, achieving the state-of-the-art mIoU of 74.2\% on S3DIS Area 5, 81.2\% on S3DIS 6-fold and 64.8\% on SWAN dataset.
title PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.06094