Densely Connecting Depth Maps for Monocular Depth Estimation

Zhang, Jinqing; Yue, Haosong; Wu, Xiaofeng; Chen, Weihai; Chen, Wen

doi:10.1007/978-3-030-66823-5_9

Cited by 4 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table 2, we present the comparison of results on the KITTI dataset. Compared to the recent competing methods such as TransDepth, Zhang et al [64] and BTS [32], our approach is superior by a significant margin. Especially notable are results on the metric Sq Rel, and ours improves it by approximately 15% than TransDepth in both the capturing ranges of 0-80m and 0-50m.…”

Section: Comparison To Previous State-of-the-art Approachesmentioning

confidence: 89%

See 1 more Smart Citation

NENet: Monocular Depth Estimation via Neural Ensembles

Shao¹,

Li²,

Pei³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Depth estimation is getting a widespread popularity in the computer vision community, and it is still quite difficult to recover an accurate depth map using only one single RGB image. In this work, we observe a phenomenon that existing methods tend to exhibit asymmetric errors, which might open up a new direction for accurate and robust depth estimation. We carefully investigate into the phenomenon, and construct a two-level ensemble scheme, NENet, to integrate multiple predictions from diverse base predictors. The NENet forms a more reliable depth estimator, which substantially boosts the performance over base predictors. Notably, this is the first attempt to introduce ensemble learning and evaluate its utility for monocular depth estimation to the best of our knowledge. Extensive experiments demonstrate that the proposed NENet achieves better results than previous state-of-the-art approaches on the NYU-Depth-v2 and KITTI datasets. In particular, our method improves previous state-of-the-art methods from 0.365 to 0.349 on the metric RMSE on the NYU dataset. To validate the generalizability across cameras, we directly apply the models trained on the NYU dataset to the SUN RGB-D dataset without any fine-tuning, and achieve the superior results, which indicate its strong generalizability. The source code and trained models will be publicly available upon the acceptance.

show abstract

Section: Comparison To Previous State-of-the-art Approachesmentioning

confidence: 89%

“…Saxena et al [48] introduced one of the first learning-based studies in this area. Thereafter, significant advancements have been made followed by the explosion of deep learning [12,14,30,32,35,37,57,64]. [32] and TransDepth [57], which are highlighted by white and green boxes.…”

Section: Introductionmentioning

confidence: 99%

NENet: Monocular Depth Estimation via Neural Ensembles

Shao¹,

Li²,

Pei³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…And many works use the atrous spatial pyramid pooling (ASPP) (Chen et al 2018) or a similar module to model contextual information. Some works (Fu et al 2018;Fang et al 2020;Zhang et al 2020;Lee et al 2021) Different from modules similar to ASPP, we combine the dilated convolutions as an equivalent large kernel convolution and apply it to replace the regular convolution layers in ResNet blocks. This operator enlarges the receptive field and produces a variety of interest areas in the receptive field.…”

Section: Dilated Convolutionmentioning

confidence: 99%

ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation

Zhuang¹,

Lu²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Depth estimation is a crucial step for 3D reconstruction with panorama images in recent years. Panorama images maintain the complete spatial information but introduce distortion with equirectangular projection. In this paper, we propose an ACDNet based on the adaptively combined dilated convolution to predict the dense depth map for a monocular panoramic image. Specifically, we combine the convolution kernels with different dilations to extend the receptive field in the equirectangular projection. Meanwhile, we introduce an adaptive channel-wise fusion module to summarize the feature maps and get diverse attention areas in the receptive field along the channels. Due to the utilization of channel-wise attention in constructing the adaptive channel-wise fusion module, the network can capture and leverage the cross-channel contextual information efficiently. Finally, we conduct depth estimation experiments on three datasets (both virtual and real-world) and the experimental results demonstrate that our proposed ACDNet substantially outperforms the current state-of-the-art (SOTA) methods. Our codes and model parameters are accessed in https://github.com/zcq15/ACDNet.

show abstract

Self-supervised Depth Estimation from Spectral Consistency and Novel View Synthesis

2022

2022 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Densely Connecting Depth Maps for Monocular Depth Estimation

Cited by 4 publications

References 33 publications

NENet: Monocular Depth Estimation via Neural Ensembles

NENet: Monocular Depth Estimation via Neural Ensembles

ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation

Self-supervised Depth Estimation from Spectral Consistency and Novel View Synthesis

Contact Info

Product

Resources

About