DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation

Abstract

This paper aims to address the problem of supervised monocular depth estimation. We start with a meticulous pilot study to demonstrate that the long-range correlation is essential for accurate depth estimation. Therefore, we propose to leverage the Transformer to model this global context with an effective attention mechanism. We also adopt an additional convolution branch to preserve the local information as the Transformer lacks the spatial inductive bias in modeling such contents. However, independent branches lead to a shortage of connections between features. To bridge this gap, we design a hierarchical aggregation and heterogeneous interaction module to enhance the Transformer features via element-wise interaction and model the affinity between the Transformer and the CNN features in a set-to-set translation manner. Due to the unbearable memory cost caused by global attention on high-resolution feature maps, we introduce the deformable scheme to reduce the complexity. Extensive experiments on the KITTI, NYU, and SUN RGB-D datasets demonstrate that our proposed model, termed DepthFormer, surpasses state-of-the-art monocular depth estimation methods with prominent margins. Notably, it achieves the most competitive result on the highly competitive KITTI depth estimation benchmark. Our codes and models are available at https://github.com/zhyever/Monocular-Depth-Estimation-Toolbox.

References in corpus (3)

• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• CoAtNet: Marrying Convolution and Attention for All Data Sizes
• AdaBins: Depth Estimation using Adaptive Bins

Cited by in corpus (5)

• MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer
• METER: a mobile vision transformer architecture for monocular depth estimation
• Monocular Per-Object Distance Estimation with Masked Object Modeling
• Enhancing kelp forest detection in remote sensing images using crowdsourced labels with Mixed Vision Transformers and ConvNeXt segmentation models
• Syn-Mediverse: A Multimodal Synthetic Dataset for Intelligent Scene Understanding of Healthcare Facilities