Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

  • 类型:arxiv
  • 标识:1510.05970
  • 链接:https://arxiv.org/abs/1510.05970
  • 主题:rag
  • 主分类:engineering
  • 形态:method
  • 被引:1476
  • 被引来源:Semantic Scholar
  • S2被引:1476
  • OpenAlex被引:941
  • 影响力被引:199
  • TLDR:This work presents a method for extracting depth information from a rectified image pair by learning a similarity measure on small image patches using a convolutional neural network and examines two network architectures for this task: one tuned for speed, the other for accuracy.
  • OpenAlex ID:W1772650917
  • OpenAlex DOI:10.48550/arxiv.1510.05970
  • DOI:10.48550/arxiv.1510.05970
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/1510.05970.pdf
  • OpenAlex更新:2026-08-22
  • 待LLM分类:否
  • 标题中文:通过训练卷积神经网络比较图像块进行立体匹配
  • TLDR中文:提出一种从校正后的图像对中提取深度信息的方法,使用卷积神经网络在小图像块上学习相似性度量,并针对该任务考察了两种网络架构:一种面向速度优化,另一种面向精度优化
  • 来源文件
  • [OpenAlex discover]
  • [S2 enrich]