Gradient-Based Uncertainty for Monocular Depth Estimation

Hornauer, Julia; Belagiannis, Vasileios

doi:10.1007/978-3-031-20044-1_35

Cited by 15 publications

(4 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the performance of traditional depth estimation methods [8], [16], [17], [30], [56], [57], [58] on transparent glass walls, we evaluate the models trained on NYU depth V2 [9] and tested on our GW-Depth dataset. The results in Tab.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Monocular Depth Estimation for Glass Walls With Context: A New Dataset and Method

Liang,

Deng,

Liu

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Traditional monocular depth estimation assumes that all objects are reliably visible in the RGB color domain. However, this is not always the case as more and more buildings are decorated with transparent glass walls. This problem has not been explored due to the difficulties in annotating the depth levels of glass walls, as commercial depth sensors cannot provide correct feedbacks on transparent objects. Furthermore, estimating depths from transparent glass walls requires the aids of surrounding context, which has not been considered in prior works. To cope with this problem, we introduce the first Glass Walls Depth Dataset (GW-Depth dataset). We annotate the depth levels of transparent glass walls by propagating the context depth values within neighboring flat areas, and the glass segmentation mask and instance level line segments of glass edges are also provided. On the other hand, a tailored monocular depth estimation method is proposed to fully activate the glass wall contextual understanding. First, we propose to exploit the glass structure context by incorporating the structural prior knowledge embedded in glass boundary line segment detections. Furthermore, to make our method adaptive to scenes without structure context where the glass boundary is either absent in the image or too narrow to be recognized, we propose to derive a reflection context by utilizing the depth reliable points sampled according to the variance between two depth estimations from different resolutions. High-resolution depth is thus estimated by the weighted summation of depths by those reliable points. Extensive experiments are conducted to evaluate the effectiveness of the proposed dual context design. Superior performances of our method is also demonstrated by comparing with state-of-the-art methods. We present the first feasible solution for monocular depth estimation in the presence of glass walls, which can be widely adopted in autonomous navigation.

show abstract

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…3 show that their generalization ability is reduced in scenes with glass walls. Additionally, methods that incorporate structure prior from larger complementary datasets [56] or uncertainty [58] derived from image gradients tend to generalize better in these scenarios.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Monocular Depth Estimation for Glass Walls With Context: A New Dataset and Method

Liang,

Deng,

Liu

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…Since the accuracy of DNNs' predictions typically declines significantly on OOD input [12], [13], the potential consequences could be disastrous. Therefore, various techniques have been developed to train uncertainty-aware DNNs models [5], [14], [9], [15], [16], [17] to explicitly estimate uncertainty in the predictions.…”

Section: Introductionmentioning

confidence: 99%

Normalizing Flow based Uncertainty Estimation for Deep Regression Analysis

Zhang¹,

Sui²,

Huang³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Uncertainty estimation is a critical component of building safe and reliable machine learning models. Accurate estimation of uncertainties is essential for identifying and mitigating potential risks and ensuring that machine learning systems operate reliably in real-world scenarios. Various approaches, such as ensemble and Bayesian neural networks have been developed by sampling probability predictions from submodels, which is computatinally expensive. Currently, these methods are unable to clearly define the boundary between in distribution (ID) and out-of-distribution (OOD) data. To fill up this research gap, this paper presents a normalizing flow based framework to directly predict parameters of prior distributions over the probability with a neural network, which is capable of effectively distinguishing ID and OOD data for regression problems. The posterior distributions learned by the proposed model accurately model uncertainties for OOD data from ID data without requiring OOD data at training time. This approach has shown promising results in a number of applications, including image depth estimation and image adversarial attacks.</p>

show abstract

“…Let's clarify this out way upfront that this is not for the first time an approach with a motivation of continuous modeling for SIDP is proposed [4,22,26,28,31,47]. Yet, existing methods in this direction model depth per pixel independently.…”

Section: Introductionmentioning

confidence: 99%

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

Liu,

Kumar,

et al. 2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Neural-network-based single image depth prediction (SIDP) is a challenging task where the goal is to predict the scene's per-pixel depth at test time. Since the problem, by definition, is ill-posed, the fundamental goal is to come up with an approach that can reliably model the scene depth from a set of training examples. In the pursuit of perfect depth estimation, most existing state-of-the-art learning techniques predict a single scalar depth value per-pixel. Yet, it is well-known that the trained model has accuracy limits and can predict imprecise depth. Therefore, an SIDP approach must be mindful of the expected depth variations in the model's prediction at test time. Accordingly, we introduce an approach that performs continuous modeling of per-pixel depth, where we can predict and reason about the per-pixel depth and its distribution. To this end, we model per-pixel scene depth using a multivariate Gaussian distribution. Moreover, contrary to the existing uncertainty modeling methods-in the same spirit, where per-pixel depth is assumed to be independent, we introduce per-pixel covariance modeling that encodes its depth dependency w.r.t. all the scene points. Unfortunately, per-pixel depth covariance modeling leads to a computationally expensive continuous loss function, which we solve efficiently using the learned low-rank approximation of the overall covariance matrix. Notably, when tested on benchmark datasets such as KITTI, NYU, and SUN-RGB-D, the SIDP model obtained by optimizing our loss function shows state-of-the-art results. Our method's accuracy (named MG) is among the top on the KITTI depth-prediction benchmark leaderboard 1 .

show abstract

Gradient-Based Uncertainty for Monocular Depth Estimation

Cited by 15 publications

References 52 publications

Monocular Depth Estimation for Glass Walls With Context: A New Dataset and Method

Monocular Depth Estimation for Glass Walls With Context: A New Dataset and Method

Normalizing Flow based Uncertainty Estimation for Deep Regression Analysis

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

Contact Info

Product

Resources

About