Generative Adversarial Networks for Unsupervised Monocular Depth Prediction

Aleotti, Filippo; Tosi, Fabio; Poggi, Matteo; Mattoccia, Stefano

doi:10.1007/978-3-030-11009-3_20

Cited by 82 publications

(77 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Concerning stereo supervision, Garg et al [14] first followed this approach, while Godard et al [16] introduced a leftright consistency loss. Other methods improved efficiency [35], deploying a pyramidal architecture, and accuracy by simulating a trinocular setup [36], including joint semantic segmentation [49] or adding adversarial term [1,6]. In [33], a strategy was proposed to reduce further the energy efficiency of [35] leveraging fixed-point quantization.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Self-Supervised Monocular Depth Estimation with Traditional Visual Odometry

Andraghetti¹,

Myriokefalitakis²,

Dovesi³

et al. 2019

2019 International Conference on 3D Vision (3DV)

Self Cite

View full text Add to dashboard Cite

Estimating depth from a single image represents an attractive alternative to more traditional approaches leveraging multiple cameras. In this field, deep learning yielded outstanding results at the cost of needing large amounts of data labeled with precise depth measurements for training. An issue softened by self-supervised approaches leveraging monocular sequences or stereo pairs in place of expensive ground truth depth annotations. This paper enables to further improve monocular depth estimation by integrating into existing self-supervised networks a geometrical prior. Specifically, we propose a sparsity-invariant autoencoder able to process the output of conventional visual odometry algorithms working in synergy with depth-from-mono networks. Experimental results on the KITTI dataset show that by exploiting the geometrical prior, our proposal: i) outperforms existing approaches in the literature and ii) couples well with both compact and complex depth-from-mono architectures, allowing for its deployment on high-end GPUs as well as on embedded devices (e.g., NVIDIA Jetson TX2).

show abstract

Section: Related Workmentioning

confidence: 99%

Enhancing Self-Supervised Monocular Depth Estimation with Traditional Visual Odometry

Andraghetti¹,

Myriokefalitakis²,

Dovesi³

et al. 2019

2019 International Conference on 3D Vision (3DV)

Self Cite

View full text Add to dashboard Cite

show abstract

“…3.3) by applying it to [14] and improving their model. Our full model using a generic encoder-decoder outperforms all variants on every metric, including [2] which predicts disparities that generate photo-realistic images. Our full model using our proposed two-branch decoder (*) further improves the state-of-the-art.…”

Section: Kitti Eigen Splitmentioning

confidence: 99%

Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction

Wong

Soatto

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Supervised learning methods to infer (hypothesize) depth of a scene from a single image require costly per-pixel ground-truth. We follow a geometric approach that exploits abundant stereo imagery to learn a model to hypothesize scene structure without direct supervision. Although we train a network with stereo pairs, we only require a single image at test time to hypothesize disparity or depth. We propose a novel objective function that exploits the bilateral cyclic relationship between the left and right disparities and we introduce an adaptive regularization scheme that allows the network to handle both the co-visible and occluded regions in a stereo pair. This process ultimately produces a model to generate hypotheses for the 3-dimensional structure of the scene as viewed in a single image. When used to generate a single (most probable) estimate of depth, our method outperforms state-of-the-art unsupervised monocular depth prediction methods on the KITTI benchmarks. We show that our method generalizes well by applying our models trained on KITTI to the Make3d dataset. Code and pre-trained models available at: https

show abstract

“…Over the last years, convolutional neural networks (CNNs)s have been shown to be well-suited for both SfM, multi-view and monocular approaches, and they can be trained supervised by large RGB-D indoor datasets acquired by consumer ToF cameras. Since the acquisition of ground truth depth in large outdoor environments is challenging, semi-supervised [27] or even self-supervised approaches [2,12,15,41] have been proposed, tackling this challenge by solving proxy tasks such as stereo matching.…”

Section: Related Workmentioning

confidence: 99%

Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios

Gruber

Bijelic

Heide

et al. 2019

2019 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

This work introduces an evaluation benchmark for depth estimation and completion using high-resolution depth measurements with angular resolution of up to 25" (arcsecond), akin to a 50 megapixel camera with per-pixel depth available. Existing datasets, such as the KITTI benchmark [13], provide only sparse reference measurements with an order of magnitude lower angular resolution -these sparse measurements are treated as ground truth by existing depth estimation methods. We propose an evaluation methodology in four characteristic automotive scenarios recorded in varying weather conditions (day, night, fog, rain). As a result, our benchmark allows us to evaluate the robustness of depth sensing methods in adverse weather and different driving conditions. Using the proposed evaluation data, we demonstrate that current stereo approaches provide significantly more stable depth estimates than monocular methods and lidar completion in adverse weather. Data and code are available at https://github.com/ gruberto/PixelAccurateDepthBenchmark.git.

show abstract

Generative Adversarial Networks for Unsupervised Monocular Depth Prediction

Cited by 82 publications

References 43 publications

Enhancing Self-Supervised Monocular Depth Estimation with Traditional Visual Odometry

Enhancing Self-Supervised Monocular Depth Estimation with Traditional Visual Odometry

Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction

Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios

Contact Info

Product

Resources

About