Papers
arxiv:2205.13490

SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation

Published on May 26, 2022
Authors:
,
,

Abstract

SemAffiNet enhances point cloud semantic segmentation by integrating class-specific affine transformations and Transformer-based attention mechanisms to improve global structural understanding.

AI-generated summary

Conventional point cloud semantic segmentation methods usually employ an encoder-decoder architecture, where mid-level features are locally aggregated to extract geometric information. However, the over-reliance on these class-agnostic local geometric representations may raise confusion between local parts from different categories that are similar in appearance or spatially adjacent. To address this issue, we argue that mid-level features can be further enhanced with semantic information, and propose semantic-affine transformation that transforms features of mid-level points belonging to different categories with class-specific affine parameters. Based on this technique, we propose SemAffiNet for point cloud semantic segmentation, which utilizes the attention mechanism in the Transformer module to implicitly and explicitly capture global structural knowledge within local parts for overall comprehension of each category. We conduct extensive experiments on the ScanNetV2 and NYUv2 datasets, and evaluate semantic-affine transformation on various 3D point cloud and 2D image segmentation baselines, where both qualitative and quantitative results demonstrate the superiority and generalization ability of our proposed approach. Code is available at https://github.com/wangzy22/SemAffiNet.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2205.13490 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2205.13490 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2205.13490 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.