# CutDepth:Edge-aware Data Augmentation in Depth Estimation

arXiv: https://arxiv.org/abs/2107.07684 · HTML: https://mlsanity.com/paper/2107.07684/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 16 Jul 2021.

## Builds on (most cited first, 11 of 11)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)
- [Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy](https://mlsanity.com/paper/2004.00448/) (2020)
- [KeepAugment: A Simple Information-Preserving Data Augmentation Approach](https://mlsanity.com/paper/2011.11778/) (2020)
- [Affinity and Diversity: Quantifying Mechanisms of Data Augmentation](https://mlsanity.com/paper/2002.08973/) (2020)

## Built on by (most cited first, 14 of 14)

- [Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention](https://mlsanity.com/paper/2210.09071/) (2022)
- [Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth](https://mlsanity.com/paper/2201.07436/) (2022)
- [All in Tokens: Unifying Output Space of Visual Tasks via Soft Token](https://mlsanity.com/paper/2301.02229/) (2023)
- [ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation](https://mlsanity.com/paper/2403.18807/) (2024)
- [Self-supervised Monocular Depth Estimation: Let's Talk About The Weather](https://mlsanity.com/paper/2307.08357/) (2023)
- [URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation](https://mlsanity.com/paper/2302.08149/) (2023)
- [The Second Monocular Depth Estimation Challenge](https://mlsanity.com/paper/2304.07051/) (2023)
- [ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition](https://mlsanity.com/paper/2204.00239/) (2022)
- [Few-shot Adaptive Object Detection with Cross-Domain CutMix](https://mlsanity.com/paper/2208.14586/) (2022)
- [METER: a mobile vision transformer architecture for monocular depth estimation](https://mlsanity.com/paper/2403.08368/) (2024)
- [Semi-Supervised Semantic Depth Estimation using Symbiotic Transformer and NearFarMix Augmentation](https://mlsanity.com/paper/2308.14400/) (2023)
- [MaskingDepth: Masked Consistency Regularization for Semi-supervised Monocular Depth Estimation](https://mlsanity.com/paper/2212.10806/) (2022)
- [Self-Supervised Learning based Depth Estimation from Monocular Images](https://mlsanity.com/paper/2304.06966/) (2023)
- [Beyond Visual Ambiguity: Guiding Robust Monocular Depth Estimation in Challenging Scenarios via Detailed Long Captions](https://mlsanity.com/paper/2607.28285/) (2026)

## Abstract (arXiv)

It is difficult to collect data on a large scale in a monocular depth estimation because the task requires the simultaneous acquisition of RGB images and depths. Data augmentation is thus important to this task. However, there has been little research on data augmentation for tasks such as monocular depth estimation, where the transformation is performed pixel by pixel. In this paper, we propose a data augmentation method, called CutDepth. In CutDepth, part of the depth is pasted onto an input image during training. The method extends variations data without destroying edge features. Experiments objectively and subjectively show that the proposed method outperforms conventional methods of data augmentation. The estimation accuracy is improved with CutDepth even though there are few training data at long distances.