Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation

TL;DR

This paper introduces a novel monocular depth estimation method that integrates structured attention with continuous CRFs in a deep architecture, enabling end-to-end training and improved performance on benchmark datasets.

Contribution

It presents a structured attention model integrated into CRFs for better multi-scale feature fusion in depth estimation, a novel approach compared to prior methods.

Findings

Competitive results on KITTI benchmark

Outperforms state-of-the-art on NYU Depth V2

Effective multi-scale feature regulation

Abstract

Recent works have shown the benefit of integrating Conditional Random Fields (CRFs) models into deep architectures for improving pixel-level prediction tasks. Following this line of research, in this paper we introduce a novel approach for monocular depth estimation. Similarly to previous works, our method employs a continuous CRF to fuse multi-scale information derived from different layers of a front-end Convolutional Neural Network (CNN). Differently from past works, our approach benefits from a structured attention model which automatically regulates the amount of information transferred between corresponding features at different scales. Importantly, the proposed attention model is seamlessly integrated into the CRF, allowing end-to-end training of the entire architecture. Our extensive experimental evaluation demonstrates the effectiveness of the proposed method which is competitive with previous methods on the KITTI benchmark and outperforms the state of the art on the NYU Depth V2 dataset.