基于注意力机制与对比损失的单视图草图三维重建  

3D Reconstruction of Single-view Sketches Based on Attention Mechanism and Contrastive Loss

作　　者：钟悦 谷杰铭 ZHONG Yue;GU Jieming(Institute of Evidence Law and Forensic Science,China University of Political Science and Law,Beijing 100088,China;School of Cyberspace Science,Harbin Institute of Technology,Harbin 150001,China)

机构地区：[1]中国政法大学证据科学研究院,北京100088 [2]哈尔滨工业大学网络空间安全学院,哈尔滨150001

出　　处：《计算机科学》2025年第3期77-85,共9页Computer Science

摘　　要：元宇宙是三维的沉浸式互联空间。随着虚拟现实、人工智能等技术的发展,元宇宙正在重塑人类的生活方式。三维重建是元宇宙的核心技术之一,其中,基于深度学习的三维重建是计算机视觉领域的研究热点。针对手绘草图难以避免的前景和背景模糊性、绘制风格差异性和视角偏差问题,提出了基于注意力机制与对比损失的单视图草图三维重建方法,重建过程中无需额外的标注信息和交互操作。该模型首先通过空间变换模块矫正输入草图的空间位置,随后使用基于归一化的注意力模块在草图上建立长距离和多层次的依赖关系,利用草图的全局结构信息缓解前景和背景的模糊性所带来的重建困难,并设计对比损失函数使模型学习到对草图风格和视角不变的潜空间特征,提升模型对输入草图的鲁棒性。在多个数据集上的实验结果证明了所提模型的有效性和先进性。The metaverse is a three-dimensional(3D)virtual space that is immersive and interconnected.With the development of technologies such as virtual reality and artificial intelligence,the metaverse is reshaping human lifestyles.3D reconstruction is a core technique for the metaverse,and deep learning-based 3D reconstruction has become a popular research direction in computer vision.To address the problems of inevitable foreground and background ambiguity,drawing style variations,and viewpoint differences in hand-drawn sketches,a single-view sketch 3D reconstruction model based on attention mechanisms and contrastive losses without requiring additional annotations or user interactions is proposed.The model first rectifies the spatial layout of the input sketch using spatial transformers,and then uses the normalized attention module to establish long-distance and multi-level dependencies on the sketch.The global structure information of the sketch is used to alleviate the reconstruction difficulty caused by the ambiguity of the foreground and background.Furthermore,the contrastive loss function is designed to encourage the model to learn view-invariant and style-invariant latent space features of the sketches,so as to improve robustness.Experimental results on multiple datasets demonstrate the effectiveness and advancement of the proposed model.

关 键 词：深度学习 手绘草图 三维重建 单视图 注意力机制 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]