Digging into the multi-scale structure for a more refined depth map and 3D reconstruction

Ding, Yinzhang; Lin, Liwu; Wang, Lianghao; Zhang, Ming; Li, Dongxiao

doi:10.1007/s00521-020-04702-3

Cited by 9 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both involve the complexity of recovering depth information from a 2D image projection of a 3D scene, where depth information is inherently lost, and its retrieval from a single image is challenging. MDE has diverse applications, including 3D reconstruction [42], autonomous navigation [43], augmented reality [24], and virtual reality [24]. Recent years have witnessed significant progress in MDE, primarily driven by advancements in deep learning techniques and the availability of extensive datasets for training depth estimation models.…”

Section: Mdementioning

confidence: 99%

MFTSC: A Semantically Constrained Method for Urban Building Height Estimation Using Multiple Source Images

Chen,

Yan,

Huang

2023

Remote Sensing

View full text Add to dashboard Cite

The use of remote sensing imagery has significantly enhanced the efficiency of building extraction; however, the precise estimation of building height remains a formidable challenge. In light of ongoing advancements in computer vision, numerous techniques leveraging convolutional neural networks and Transformers have been applied to remote sensing imagery, yielding promising outcomes. Nevertheless, most existing approaches directly estimate height without considering the intrinsic relationship between semantic building segmentation and building height estimation. In this study, we present a unified architectural framework that integrates the tasks of building semantic segmentation and building height estimation. We introduce a Transformer model that systematically merges multi-level features with semantic constraints and leverages shallow spatial detail feature cues in the encoder. Our approach excels in both height estimation and semantic segmentation tasks. Specifically, the coefficient of determination (R2) in the height estimation task attains a remarkable 0.9671, with a root mean square error (RMSE) of 1.1733 m. The mean intersection over union (mIoU) for building semantic segmentation reaches 0.7855. These findings underscore the efficacy of multi-task learning by integrating semantic segmentation with height estimation, thereby enhancing the precision of height estimation.

show abstract

Section: Mdementioning

confidence: 99%

MFTSC: A Semantically Constrained Method for Urban Building Height Estimation Using Multiple Source Images

Chen,

Yan,

Huang

2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In the past few decades, numerous feature-based or direct photometric visual simultaneous localization and mapping (vS-LAM) systems [14,15,36,39,17] have been proposed and achieved great success in some real-world environment. Some SLAM systems [10,26] are also fused with depth information to enhance the system performance. However, these traditional methods often fail in featureless or lightchange conditions.…”

Section: Introductionmentioning

confidence: 99%

Transformer Guided Geometry Model for Flow-Based Unsupervised Visual Odometry

Hou

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

Existing unsupervised visual odometry (VO) methods either match pairwise images or integrate the temporal information using recurrent neural networks over a long sequence of images. They are either not accurate, timeconsuming in training or error accumulative. In this paper, we propose a method consisting of two camera pose estimators that deal with the information from pairwise images and a short sequence of images respectively. For image sequences, a Transformer-like structure is adopted to build a geometry model over a local temporal window, referred to as Transformer-based Auxiliary Pose Estimator (TAPE). Meanwhile, a Flow-to-Flow Pose Estimator (F2FPE) is proposed to exploit the relationship between pairwise images. The two estimators are constrained through a simple yet effective consistency loss in training. Empirical evaluation has shown that the proposed method outperforms the state-of-the-art unsupervised learning-based methods by a large margin and performs comparably to supervised and traditional ones on the KITTI and Malaga dataset.

show abstract

Self-supervised monocular depth estimation via joint attention and intelligent mask loss

Guo,

Pan,

Gao

et al. 2024

Machine Vision and Applications

View full text Add to dashboard Cite

Digging into the multi-scale structure for a more refined depth map and 3D reconstruction

Cited by 9 publications

References 37 publications

MFTSC: A Semantically Constrained Method for Urban Building Height Estimation Using Multiple Source Images

MFTSC: A Semantically Constrained Method for Urban Building Height Estimation Using Multiple Source Images

Transformer Guided Geometry Model for Flow-Based Unsupervised Visual Odometry

Self-supervised monocular depth estimation via joint attention and intelligent mask loss

Contact Info

Product

Resources

About