Impact of color and mixing proportion of synthetic point clouds on semantic segmentation

Shaojie Zhou, Jia-Rui Lin, Peng Pan, Yuandong Pan, Ioannis Brilakis
12/26/2024
cs.CV

No official code found. Best implementation: smartaec/Synthetic-Point-Clouds-for-semantic-segmentation (0 stars, last commit 2025-01-20).

Abstract

Deep learning (DL)-based point cloud segmentation is essential for understanding built environment. Despite synthetic point clouds (SPC) having the potential to compensate for data shortage, how synthetic color and mixing proportion impact DL-based segmentation remains a long-standing question. Therefore, this paper addresses this question with extensive experiments by introducing: 1) method to generate SPC with real colors and uniform colors from BIM, and 2) enhanced benchmarks for better performance evaluation. Experiments on DL models including PointNet, PointNet++, and DGCNN show that model performance on SPC with real colors outperforms that on SPC with uniform colors by 8.2 % + on both OA and mIoU. Furthermore, a higher than 70 % mixing proportion of SPC usually leads to better performance. And SPC can replace real ones to train a DL model for detecting large and flat building elements. Overall, this paper unveils the performance-improving mechanism of SPC and brings new insights to boost SPC's value (for building large models for point clouds).

View on arXivView PDF

Code Implementations(1)

smartaec/Synthetic-Point-Clouds-for-semantic-segmentationCommunity100%

The results for the paper "Impact of color and mixing proportion of synthetic point clouds on semantic segmentation"

00Dec 17, 20241 years ago

Similar Papers

Evaluating the Impact of Point Cloud Colorization on Semantic Segmentation Accuracy

85% match2024

InvNeRF-Seg: Fine-Tuning a Pre-Trained NeRF for 3D Object Segmentation

84% match2025

DPGLA: Bridging the Gap between Synthetic and Real Data for Unsupervised Domain Adaptation in 3D LiDAR Semantic Segmentation

84% match2025

Deep Learning-Based 3D Instance and Semantic Segmentation: A Review

84% match2024

3DSES: an indoor Lidar point cloud segmentation dataset with real and pseudo-labels from a 3D model

84% match2025

Adversarially Masking Synthetic to Mimic Real: Adaptive Noise Injection for Point Cloud Segmentation Adaptation

83% match2026

Cite this paper

@article{zhou2024impact,
  title  = {Impact of color and mixing proportion of synthetic point clouds on semantic segmentation},
  author = {Shaojie Zhou and Jia-Rui Lin and Peng Pan and Yuandong Pan and Ioannis Brilakis},
  year   = {2024},
  eprint = {2412.19145},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.19145v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.19145.svg)](https://codeofpaper.com/paper/2412.19145)

Discussion