IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty

by   Gwangbin Bae, et al.

Single image surface normal estimation and depth estimation are closely related problems as the former can be calculated from the latter. However, the surface normals computed from the output of depth estimation methods are significantly less accurate than the surface normals directly estimated by networks. To reduce such discrepancy, we introduce a novel framework that uses surface normal and its uncertainty to recurrently refine the predicted depth-map. The depth of each pixel can be propagated to a query pixel, using the predicted surface normal as guidance. We thus formulate depth refinement as a classification of choosing the neighboring pixel to propagate from. Then, by propagating to sub-pixel points, we upsample the refined, low-resolution output. The proposed method shows state-of-the-art performance on NYUv2 and iBims-1 - both in terms of depth and normal. Our refinement module can also be attached to the existing depth estimation methods to improve their accuracy. We also show that our framework, only trained for depth estimation, can also be used for depth completion. The code is available at


page 1

page 2

page 3

page 4

page 7

page 9


Surface Normals in the Wild

We study the problem of single-image depth estimation for images in the ...

GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation

In this paper, we propose a geometric neural network with edge-aware ref...

Adaptive Surface Normal Constraint for Depth Estimation

We present a novel method for single image depth estimation using surfac...

Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

Surface normal estimation from a single image is an important task in 3D...

Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency

Learning to reconstruct depths in a single image by watching unlabeled v...

PlaneRecTR: Unified Query learning for 3D Plane Recovery from a Single View

3D plane recovery from a single image can usually be divided into severa...

A New Distributional Ranking Loss With Uncertainty: Illustrated in Relative Depth Estimation

We propose a new approach for the problem of relative depth estimation f...

Please sign up or login with your details

Forgot password? Click here to reset