Nested dwt-based cnn architecture for monocular depth estimation

HIGHLIGHTS

• who: Sandip Paul and colleagues from the Indian Institute of Space Science and Technology, Trivandrum, Kerela, India have published the paper: Nested DWT-Based CNN Architecture for Monocular Depth Estimation, in the Journal: Sensors 2023, 23, 3066. of /2023/
• what: The authors propose a moderately dense encoder-decoder network based on discrete wavelet decomposition and trainable coefficients (LL LH HL HH). As the inclusion of wavelets in a network is useful, the authors propose a moderately dense network using DWT for depth estimates. This model provides better feature detailing showing that edges and high-frequency . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.