Coupled Depth Learning

TL;DR

This paper introduces a coupled depth learning method that estimates a global depth map from a single image using a learned basis and refines it locally, achieving higher accuracy efficiently.

Contribution

It presents a novel coupled learning scheme that jointly optimizes a depth basis and regression function for improved depth estimation from single images.

Findings

Outperforms state-of-the-art methods on NYUv2 and KITTI datasets.

Achieves higher accuracy with lower computational cost.

Effectively captures spatial and statistical regularities in depth maps.

Abstract

In this paper we propose a method for estimating depth from a single image using a coarse to fine approach. We argue that modeling the fine depth details is easier after a coarse depth map has been computed. We express a global (coarse) depth map of an image as a linear combination of a depth basis learned from training examples. The depth basis captures spatial and statistical regularities and reduces the problem of global depth estimation to the task of predicting the input-specific coefficients in the linear combination. This is formulated as a regression problem from a holistic representation of the image. Crucially, the depth basis and the regression function are {\bf coupled} and jointly optimized by our learning scheme. We demonstrate that this results in a significant improvement in accuracy compared to direct regression of depth pixel values or approaches learning the depth basis disjointly from the regression function. The global depth estimate is then used as a guidance by a local refinement method that introduces depth details that were not captured at the global level. Experiments on the NYUv2 and KITTI datasets show that our method outperforms the existing state-of-the-art at a considerably lower computational cost for both training and testing.