Self-supervised monocular depth estimation from oblique UAV videos

Madhuanand, Logambal; Nex, Francesco; Yang, Michael Ying

doi:10.1016/j.isprsjprs.2021.03.024

Cited by 31 publications

(21 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remote sensing. Autoencoders have been widely used to learn representation from various remote sensing data like multispectral images [92,93,94,95,96,97,98,99], hyperspectral images [100,101,102,103,104,105,106,107] and SAR images [108,109,110,111]. Lu et al [92] proposed a combination of a shallowly weighted de-convolution network with a spatial pyramid model in order to learn multi-layer feature maps and filters for input images.…”

Section: A Generative Methodsmentioning

confidence: 99%

“…In hyperspectral image analysis, most of the tasks are based on pixel level, including hyperspectral image classification 4 [106,100,101], image denoising [233], spectral unmixing [99], target detection [232], image restoration [102] and super-resolution [105,104]. Other pixel-level tasks include depth estimation [158,95] and SAR despeckling [110,109].…”

Section: B Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Self-Supervised Learning in Remote Sensing: A review

Wang

Albrecht

Braham

et al. 2022

IEEE Geosci. Remote Sens. Mag.

108

View full text Add to dashboard Cite

In deep learning research, self-supervised learning (SSL) has received great attention triggering interest within both the computer vision and remote sensing communities. While there has been a big success in computer vision, most of the potential of SSL in the domain of earth observation remains locked. In this paper, we provide an introduction to, and a review of the concepts and latest developments in SSL for computer vision in the context of remote sensing. Further, we provide a preliminary benchmark of modern SSL algorithms on popular remote sensing datasets, verifying the potential of SSL in remote sensing and providing an extended study on data augmentations. Finally, we identify a list of promising directions of future research in SSL for earth observation (SSL4EO) to pave the way for fruitful interaction of both domains.

show abstract

Section: A Generative Methodsmentioning

confidence: 99%

Section: B Applicationsmentioning

confidence: 99%

Self-Supervised Learning in Remote Sensing: A review

Wang

Albrecht

Braham

et al. 2022

IEEE Geosci. Remote Sens. Mag.

108

View full text Add to dashboard Cite

show abstract

“…Mahmud et al [42] proposed a boundary-aware multi-task deep-learning-based architecture for fast 3D building modeling from single overhead images, by jointly learning a modified signed distance function, a dense height map, and scene semantics from building boundaries in order to model the buildings within the scenes. Madhuanand et al [43] aimed to estimate depth from a single Unmanned Aerial Vehicle (UAV) aerial image, by designing a self-supervised learning approach named Self-supervised Monocular Depth Estimation that does not need any information other than images.…”

Section: Related Workmentioning

confidence: 99%

THE Benchmark: Transferable Representation Learning for Monocular Height Estimation

Xiong,

Huang,

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Generating 3D city models rapidly is crucial for many applications. Monocular height estimation is one of the most efficient and timely ways to obtain large-scale geometric information. However, existing works focus primarily on training and testing models using unbiased datasets, which does not align well with real-world applications. Therefore, we propose a new benchmark dataset to study the transferability of height estimation models in a cross-dataset setting. To this end, we first design and construct a large-scale benchmark dataset for cross-dataset transfer learning on the height estimation task. This benchmark dataset includes a newly proposed large-scale synthetic dataset, a newly collected real-world dataset, and four existing datasets from different cities. Next, a new experimental protocol, few-shot cross-dataset transfer, is designed. Furthermore, in this paper, we propose a scale-deformable convolution module to enhance the window-based Transformer for handling the scale-variation problem in the height estimation task. Experimental results have demonstrated the effectiveness of the proposed methods in traditional and cross-dataset transfer settings. The datasets and codes are publicly available at https://mediatum.ub.tum.de/1662763 and https://thebenchmarkh.github.io/.

show abstract

“…Few recent works discuss this issue, integrating geometric supervision (Yin et al, 2019) or relying on extra modules for training in point cloud level separately from depth estimation (Yin et al, 2021). The transferability of deep learning depth estimation for realworld photogrammetric scenarios is a challenging problem that has only recently been acknowledged in the community (Madhuanand et al, 2021;Steenbeek and Nex, 2022).…”

Section: Introductionmentioning

confidence: 99%

Monocular Depth Prediction in Photogrammetric Applications

Welponer

Stathopoulou

Remondino

2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Despite the recent success of learning-based monocular depth estimation algorithms and the release of large-scale datasets for training, the methods are limited to depth map prediction and still struggle to yield reliable results in the 3D space without additional scene cues. Indeed, although state-of-the-art approaches produce quality depth maps, they generally fail to recover the 3D structure of the scene robustly. This work explores supervised CNN architectures for monocular depth estimation and evaluates their potential in 3D reconstruction. Since most available datasets for training are not designed toward this goal and are limited to specific indoor scenarios, a new metric, large-scale synthetic benchmark (ArchDepth) is introduced that renders near real-world scenarios of outdoor scenes. A encoder-decoder architecture is used for training, and the generalization of the approach is evaluated via depth inference in unseen views in synthetic and real-world scenarios. The depth map predictions are also projected in the 3D space using a separate module. Results are qualitatively and quantitatively evaluated and compared with state-of-the-art algorithms for single image 3D scene recovery.

show abstract

Self-supervised monocular depth estimation from oblique UAV videos

Cited by 31 publications

References 44 publications

Self-Supervised Learning in Remote Sensing: A review

Self-Supervised Learning in Remote Sensing: A review

THE Benchmark: Transferable Representation Learning for Monocular Height Estimation

Monocular Depth Prediction in Photogrammetric Applications

Contact Info

Product

Resources

About