Adversarial learning for unguided single depth map completion of indoor scenes

Code

• github.com/Moushumi9medhi/Depth-Completion
  pytorch★ 0

Abstract

Depth map completion without guidance from color images is a challenging, ill-posed problem. Conventional methods rely on computationally intensive optimization processes. This work proposes a deep adversarial learning approach to estimate missing depth information directly from a single degraded observation, without requiring RGB guidance or postprocessing.

Reproductions