High Quality Monocular Depth Estimation via Transfer Learning

Code

• github.com/ialhashim/DenseDepth
  OfficialIn papertf★ 0
• github.com/dsshim0125/grmc
  pytorch★ 27
• github.com/KarthikGangadhar/depth-estimation
  tf★ 0
• github.com/alinstein/Depth_estimation
  pytorch★ 0
• github.com/lemon-liley/isabella
  pytorch★ 0
• github.com/raajeshlr/DenseDepth
  tf★ 0
• github.com/gudaykiran/DepthModel
  tf★ 0
• github.com/NiallEHunt/MonocularDepth-Using-LightFields
  pytorch★ 0
• github.com/brandon-wu76/monocular-depth-estimation
  none★ 0
• github.com/rramjee/DenseDepth
  tf★ 0

Abstract

Accurate depth estimation from images is a fundamental task in many applications including scene understanding and reconstruction. Existing solutions for depth estimation often produce blurry approximations of low resolution. This paper presents a convolutional neural network for computing a high-resolution depth map given a single RGB image with the help of transfer learning. Following a standard encoder-decoder architecture, we leverage features extracted using high performing pre-trained networks when initializing our encoder along with augmentation and training strategies that lead to more accurate results. We show how, even for a very simple decoder, our method is able to achieve detailed high-resolution depth maps. Our network, with fewer parameters and training iterations, outperforms state-of-the-art on two datasets and also produces qualitatively better results that capture object boundaries more faithfully. Code and corresponding pre-trained weights are made publicly available.

Tasks

Reproductions