Evaluation of CNN-Based Single-Image Depth Estimation Methods

Koch, Tobias; Lukas, Lukas; Fraundorfer, Friedrich; Körner, Marco

doi:10.1007/978-3-030-11015-4_25

Cited by 77 publications

(79 citation statements)

References 41 publications

(87 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More precisely, an Euclidean distance transform E = DT (Y bin ) is applied to the "ground truth" binary edges image and distances are truncated to a maximum of 10 pixels. Pixels E i in E exceeding 10 pixels distance are ignored in order to evaluate predicted edges only in the local neighborhood of the ground truth edges (we refer the reader to the authors original paper [15] for further details). Finally, the depth boundary accuracy error is defined as:…”

Section: Evaluation Methodsmentioning

confidence: 99%

SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation

Ramamonjisoa

Lepetit

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

116

View full text Add to dashboard Cite

We introduce SharpNet, a method that predicts an accurate depth map for an input color image, with a particular attention to the reconstruction of occluding contours: Occluding contours are an important cue for object recognition, and for realistic integration of virtual objects in Augmented Reality, but they are also notoriously difficult to reconstruct accurately. For example, they are a challenge for stereo-based reconstruction methods, as points around an occluding contour are visible in only one image. Inspired by recent methods that introduce normal estimation to improve depth prediction, we introduce a novel term that constrains depth and occluding contours predictions. Since ground truth depth is difficult to obtain with pixel-perfect accuracy along occluding contours, we use synthetic images for training, followed by fine-tuning on real data. We demonstrate our approach on the challenging NYUv2-Depth dataset, and show that our method outperforms the state-of-the-art along occluding contours, while performing on par with the best recent methods for the rest of the images. Its accuracy along the occluding contours is actually better than the "ground truth" acquired by a depth camera based on structured light. We show this by introducing a new benchmark based on NYUv2-Depth for evaluating occluding contours in monocular reconstruction, which is our second contribution.

show abstract

Section: Evaluation Methodsmentioning

confidence: 99%

SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation

Ramamonjisoa

Lepetit

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

116

View full text Add to dashboard Cite

show abstract

“…To make quantitative evaluation of roofs planarity, we evaluate the flatness and orientation of 3D planes π p k fitted to predicted roof surface points P p k;m,n in comparison to 3D planes π t k fitted to the ground truth roof surface points P t k;m,n , as proposed by (Koch et al, 2019). Mainly, the flatness error…”

Section: Roofs Planaritymentioning

confidence: 99%

Long-Short Skip Connections in Deep Neural Networks for DSM Refinement

Bittner

Lukas

Reinartz

2020

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

View full text Add to dashboard Cite

Abstract. Detailed digital surface models (DSMs) from space-borne sensors are the key to successful solutions for many remote sensing problems, like environmental disaster simulations, change detection in rural and urban areas, 3D urban modeling for city planning and management, etc. Traditional methodologies, e.g., stereo matching, used to generate photogrammetric DSMs from stereo imagery, usually deliver low-quality results due to the matching errors in homogeneous areas or the lack of information when observing the scene under different viewing angles. This makes the tasks related to building reconstruction very challenging since in most cases it is difficult to recognize the type of roofs, especially if overlaid with trees. This work represents a continuation of research regarding the automatic optimization of building geometries in photogrammetric DSMs with half-meter resolution and introduces an improved generative adversarial network (GAN) architecture which allows to reconstruct complete and detailed building structures without neglecting even low-rise urban constructions. The generative part of the network is constructed in a way that it simultaneously processes height and intensity information, and combines short and long skip connections within one architecture. To improve different aspects of the surface, several loss terms are used, the contributions of which are automatically balanced during training. The obtained results demonstrate that the proposed methodology can achieve two goals without any manual intervention: improve the roof surfaces by making them more planar and also recognize and optimize even small residential buildings which are hard to detect.

show abstract

“…First approaches to SIDE for indoor scenes using deep convolutional neural networks (CNNs) were presented by Eigen et al [11,10]. Ever since then, various methods for the prediction [28,35,30,34,21,53] and evaluation [25] of depth maps for indoor scenes have been proposed. SIDE in unstructured outdoor environments poses an even greater challenge.…”

Section: Introductionmentioning

confidence: 99%

MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification

Lukas

2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

Self Cite

View full text Add to dashboard Cite

We introduce MultiDepth, a novel training strategy and convolutional neural network (CNN) architecture that allows approaching single-image depth estimation (SIDE) as a multi-task problem. SIDE is an important part of road scene understanding. It, thus, plays a vital role in advanced driver assistance systems and autonomous vehicles. Best results for the SIDE task so far have been achieved using deep CNNs. However, optimization of regression problems, such as estimating depth, is still a challenging task. For the related tasks of image classification and semantic segmentation, numerous CNN-based methods with robust training behavior have been proposed. Hence, in order to overcome the notorious instability and slow convergence of depth value regression during training, MultiDepth makes use of depth interval classification as an auxiliary task. The auxiliary task can be disabled at test-time to predict continuous depth values using the main regression branch more efficiently. We applied MultiDepth to road scenes and present results on the KITTI depth prediction dataset. In experiments, we were able to show that end-to-end multi-task learning with both, regression and classification, is able to considerably improve training and yield more accurate results.

show abstract

Evaluation of CNN-Based Single-Image Depth Estimation Methods

Cited by 77 publications

References 41 publications

SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation

SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation

Long-Short Skip Connections in Deep Neural Networks for DSM Refinement

MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification

Contact Info

Product

Resources

About