Learning Super-Resolution of Environment Matting of Transparent Objects from a Single Image

• Author / Creator

  Hang, Zicun

• This thesis addresses the problem of super-resolution of environment matting of transparent objects. In contrast to traditional methods of environment matting of transparent objects, which often require a large number of input images or complex camera setups, recent approaches using convolutional neural networks are more practical. In particular, after training, they can generate the environment mattes using a single image. However, they still do not have super-resolution capabilities. This thesis first proposes an encoder-decoder network with restoration units for super-resolution environment matting, called Enhanced Transparent Object Matting Network (ETOM-Net). Then, we introduce a refinement phase to improve the details of the output further. Meanwhile, to facilitate future research, we create a high-resolution synthetic dataset called ETOM-Synthetic with 60,000 samples. The ETOM-Net effectively recovers lost features in the low-resolution input images and produces visually plausible high-resolution environment mattes and the corresponding reconstructed images, demonstrating our method's effectiveness.

• Subjects / Keywords

  • Super-Resolution
  • Environment Matting

• Graduation date

  Fall 2021

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/r3-v5qy-7n85

• License

  This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.