Discontinuous and Smooth Depth Completion with Binary Anisotropic Diffusion Tensor

TL;DR

This paper introduces a novel unsupervised depth completion method using a Binary Anisotropic Diffusion Tensor to produce smooth yet discontinuous depth maps from sparse data, outperforming previous methods in accuracy and visual plausibility.

Contribution

The paper presents the Binary Anisotropic Diffusion Tensor and Image-guided Nearest Neighbor Search as new techniques for unsupervised depth completion that better preserve object boundaries.

Findings

Outperforms previous unsupervised depth completion methods in accuracy.

Produces depth maps that preserve object discontinuities and are visually plausible.

Enables conversion of depth maps into realistic point clouds.

Abstract

We propose an unsupervised real-time dense depth completion from a sparse depth map guided by a single image. Our method generates a smooth depth map while preserving discontinuity between different objects. Our key idea is a Binary Anisotropic Diffusion Tensor (B-ADT) which can completely eliminate smoothness constraint at intended positions and directions by applying it to variational regularization. We also propose an Image-guided Nearest Neighbor Search (IGNNS) to derive a piecewise constant depth map which is used for B-ADT derivation and in the data term of the variational energy. Our experiments show that our method can outperform previous unsupervised and semi-supervised depth completion methods in terms of accuracy. Moreover, since our resulting depth map preserves the discontinuity between objects, the result can be converted to a visually plausible point cloud. This is remarkable since previous methods generate unnatural surface-like artifacts between discontinuous objects.