基于自增强注意力机制的室内单图像分段平面三维重建被引量：2

3D piece-wise planar reconstruction from a single indoor image based on self-augmented-attention mechanism

下载PDF

导出

摘要基于卷积神经网络(CNN)的分段平面三维重建已然成为室内场景建模研究的焦点之一。针对室内场景中,平面和非平面元素常常交织在一起,导致网络提取的平面特征中掺杂了非平面信息,从而影响了最终分割的精度;且室内场景中的平面存在尺度差异巨大的情况,带来了明显的类别不平衡,小尺度平面实例往往会失真的问题。提出了一种自增强注意力的多尺度特征融合三维分段平面重建网络,该网络能够自动学习场景中的平面特征,并有效地将不同尺度的特征信息融合,从而提升了平面实例分割的精度。同时,通过为平面实例中的每个像素分配不同的权重,特别是增加了对小尺度平面边缘像素的权重值,进一步增强了小尺度平面分割对象的通道表达。最终,采用平衡交叉熵损失和骰子损失构建了一种新的损失函数来训练模型,进一步提升了平面分割的精度。实验证明,该算法在平面召回率和分割准确度方面均取得了显著地提升,能够产生更为准确的室内三维分段平面重建模型。 The piece-wise 3D reconstruction of indoor scenes using convolutional neural networks(CNN)has become one of the hot topics in the research of indoor scene modeling.However,the intertwining of planar and non-planar elements often leads to the network’s extraction of non-planar information mixed with planar features,thereby affecting the final segmentation accuracy.Moreover,there are significant scale differences in the planes present in indoor scenes,leading to pronounced class imbalances,where small-scale plane instances are prone to distortion.To address these challenges,this paper proposed a self-enhanced attention-based multi-scale feature fusion network for 3D plane segmentation reconstruction.This network can automatically learn planar features in the scene and effectively fuse feature information from different scales,thereby enhancing the accuracy of plane instance segmentation.At the same time,by assigning different weights to each pixel in the plane instance,particularly increasing the weight values for small-scale plane edge pixels,the channel representation of small-scale plane segmentation objects was further enhanced.Finally,a new loss function was constructed using balanced cross-entropy loss and dice loss to train the model,further improving the accuracy of plane segmentation.Extensive experiments demonstrated that the algorithm proposed achieves significant improvements in plane recall rate and segmentation accuracy,resulting in more accurate indoor 3D segmented plane reconstruction models.

作者朱光辉缪君胡宏利申基杜荣华 ZHU Guanghui;MIAO Jun;HU Hongli;SHEN Ji;DU Ronghua(School of Aeronautical Manufacturing Engineering,Nanchang Hangkong University,Nanchang Jiangxi 330063,China)

机构地区南昌航空大学航空制造工程学院

出处《图学学报》 CSCD 北大核心 2024年第3期464-471,共8页 Journal of Graphics

基金国家自然科学基金项目(62162045,62366032)。

关键词深度学习分段平面重建多尺度融合增强注意力自注意力 deep learning segmented plane reconstruction multi-scale fusion enhance attention self-attention

分类号 TP183 [自动化与计算机技术—控制理论与控制工程]