Skip to content

A-Jacobson/Depth_in_The_Wild

Repository files navigation

Depth in The Wild

Pytorch implementation of Single-Image Depth Perception in the Wild https://arxiv.org/pdf/1604.03901.pdf

  • Data Loader for NYUDepth
  • Architecture
  • Custom Criterion
  • Train on Small sample
  • Tweak Architecture
  • Fully Train Model (310/~500 epochs)
  • Validate Results

Network Architecture:

Network Architecture

Targets

target1 target2

Outputs (120 epochs)

output1 output2

About

Pytorch implementation of Single-Image Depth Perception in the Wild https://arxiv.org/pdf/1604.03901.pdf

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published