VA-DepthNet: A Variational Approach to Single Image Depth Prediction

by   Ce Liu, et al.

We introduce VA-DepthNet, a simple, effective, and accurate deep neural network approach for the single-image depth prediction (SIDP) problem. The proposed approach advocates using classical first-order variational constraints for this problem. While state-of-the-art deep neural network methods for SIDP learn the scene depth from images in a supervised setting, they often overlook the invaluable invariances and priors in the rigid scene space, such as the regularity of the scene. The paper's main contribution is to reveal the benefit of classical and well-founded variational constraints in the neural network design for the SIDP task. It is shown that imposing first-order variational constraints in the scene space together with popular encoder-decoder-based network architecture design provides excellent results for the supervised SIDP task. The imposed first-order variational constraint makes the network aware of the depth gradient in the scene space, i.e., regularity. The paper demonstrates the usefulness of the proposed approach via extensive evaluation and ablation analysis over several benchmark datasets, such as KITTI, NYU Depth V2, and SUN RGB-D. The VA-DepthNet at test time shows considerable improvements in depth prediction accuracy compared to the prior art and is accurate also at high-frequency regions in the scene space. At the time of writing this paper, our method – labeled as VA-DepthNet, when tested on the KITTI depth-prediction evaluation set benchmarks, shows state-of-the-art results, and is the top-performing published approach.


page 3

page 18

page 19

page 20

page 21


Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

Neural-network-based single image depth prediction (SIDP) is a challengi...

Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction

Supervised learning methods to infer (hypothesize) depth of a scene from...

Deep Robust Single Image Depth Estimation Neural Network Using Scene Understanding

Single image depth estimation (SIDE) plays a crucial role in 3D computer...

Enforcing geometric constraints of virtual normal for depth prediction

Monocular depth prediction plays a crucial role in understanding 3D scen...

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

Predicting depth is an essential component in understanding the 3D geome...

Learning Depth from Single Images with Deep Neural Network Embedding Focal Length

Learning depth from a single image, as an important issue in scene under...

Geo-Supervised Visual Depth Prediction

We propose using global orientation from inertial measurements, and the ...

Please sign up or login with your details

Forgot password? Click here to reset