mlsanityData to 7 Oct 2026

Cyclegan Network for Sheet Metal Welding Drawing Translation

arXiv 2209.14106 ↗First posted 28 Sep 2022cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In intelligent manufacturing, the quality of machine translation engineering drawings will directly affect its manufacturing accuracy. Currently, most of the work is manually translated, greatly reducing production efficiency. This paper proposes an automatic translation method for welded structural engineering drawings based on Cyclic Generative Adversarial Networks (CycleGAN). The CycleGAN network model of unpaired transfer learning is used to learn the feature mapping of real welding engineering drawings to realize automatic translation of engineering drawings. U-Net and PatchGAN are the main network for the generator and discriminator, respectively. Based on removing the identity mapping function, a high-dimensional sparse network is proposed to replace the traditional dense network for the Cyclegan generator to improve noise robustness. Increase the residual block hidden layer to increase the resolution of the generated graph. The improved and fine-tuned network models are experimentally validated, computing the gap between real and generated data. It meets the welding engineering precision standard and solves the main problem of low drawing recognition efficiency in the welding manufacturing process. The results show. After training with our model, the PSNR, SSIM and MSE of welding engineering drawings reach about 44.89%, 99.58% and 2.11, respectively, which are superior to traditional networks in both training speed and accuracy.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 28 Sep 2022.

Builds on

21 of 30 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  9. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  10. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  11. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  12. 2021Rebooting ACGAN: Auxiliary Classifier GANs with Stable Trainingcited by 57
9 more
  1. 2019How Can We Be So Dense? The Benefits of Using Highly Sparse Representationscited by 45
  2. 2021Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Imagescited by 20
  3. 2021A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines -- From Medical to Remote Sensingcited by 13
  4. 2021csBoundary: City-scale Road-boundary Detection in Aerial Images for High-definition Mapscited by 12
  5. 2020Conditional Image Generation with One-Vs-All Classifiercited by 4
  6. 2018Unpaired Multi-Domain Image Generation via Regularized Conditional GANscited by 3
  7. 2021Training Wasserstein GANs without gradient penaltiescited by 3
  8. 2017Generative Adversarial Mapping Networkscited by 1
  9. 2021Training Generative Adversarial Networks with Adaptive Composite Gradientcited by 1

Built on by

Not cited yet.