CutDepth:Edge-aware Data Augmentation in Depth Estimation

2021-07-16 · Yasunori Ishii, Takayoshi Yamashita

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.

📄 PDF Abstract BibTeX arXiv:2107.07684

Code (1)

aradhye2002/ecodepth pytorch

Tasks

Data Augmentation Depth Estimation Monocular Depth Estimation

Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth

2022-01-19 · Doyeon Kim, Woonghyun Ka, Pyungwhan Ahn, Donggyu Joo 외

Depth estimation from a single image is an important task that can be applied to various fields in computer vision, and has grown rapidly with the development of convolutional neural networks. In this paper, we propose a…

Decoder Depth Estimation Monocular Depth Estimation

Depth Jitter: Seeing through the Depth

2025-08-08 · Md Sazidur Rahman, David Cabecinhas, Ricard Marxer arxiv

Depth information is essential in computer vision, particularly in underwater imaging, robotics, and autonomous navigation. However, conventional augmentation techniques overlook depth aware transformations, limiting mod…

Depth-Copy-Paste: Multimodal and Depth-Aware Compositing for Robust Face Detection

2025-12-12 · Qiushi Guo arxiv

Data augmentation is crucial for improving the robustness of face detection systems, especially under challenging conditions such as occlusion, illumination variation, and complex environments. Traditional copy paste aug…

Data Augmentation Face Detection

Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation

2023-11-21 · Mu Chen, Zhedong Zheng, Yi Yang

Scene segmentation via unsupervised domain adaptation (UDA) enables the transfer of knowledge acquired from source synthetic data to real-world target data, which largely reduces the need for manual pixel-level annotatio…

Depth Estimation Domain Adaptation Scene Segmentation Synthetic-to-Real Translation+1

Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias

2020-07-08 · CVPR 2021 1 · Yunhan Zhao, Shu Kong, Charless Fowlkes

Monocular depth predictors are typically trained on large-scale training sets which are naturally biased w.r.t the distribution of camera poses. As a result, trained predictors fail to make reliable depth predictions for…

Data Augmentation Depth Estimation Depth Prediction