Depth Estimation from Single Image using Sparse Representations

TL;DR

This paper introduces a deep sparse coding approach for monocular depth estimation, leveraging learned representations and deterministic dictionary initialization to improve depth prediction from single images.

Contribution

It presents a novel deep sparse coding method with a deterministic dictionary initialization for monocular depth estimation.

Findings

Demonstrates improved depth estimation accuracy

Introduces a new sparse coding-based framework

Shows effectiveness over existing methods

Abstract

Monocular depth estimation is an interesting and challenging problem as there is no analytic mapping known between an intensity image and its depth map. Recently there has been a lot of data accumulated through depth-sensing cameras, in parallel to that researchers started to tackle this task using various learning algorithms. In this paper, a deep sparse coding method is proposed for monocular depth estimation along with an approach for deterministic dictionary initialization.