2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019
DOI: 10.1109/cvpr.2019.00029
|View full text |Cite
|
Sign up to set email alerts
|

LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
38
0
1

Year Published

2020
2020
2022
2022

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 56 publications
(40 citation statements)
references
References 31 publications
1
38
0
1
Order By: Relevance
“…With the convincing results on the Middlebury dataset, LGC+, like almost all learned confidence estimation procedures, proves to be relatively insensitive to differences between the training and test domains. Overall, these results underline the findings of Kim et al (2019) and Kim et al (2020) regarding the higher accuracy of multi-modal approaches. This is due to complementary information supporting the task of confidence estimation in a broader range of failure cases than a single or bi-modal input.…”
Section: Complete Modelsupporting
confidence: 76%
See 1 more Smart Citation
“…With the convincing results on the Middlebury dataset, LGC+, like almost all learned confidence estimation procedures, proves to be relatively insensitive to differences between the training and test domains. Overall, these results underline the findings of Kim et al (2019) and Kim et al (2020) regarding the higher accuracy of multi-modal approaches. This is due to complementary information supporting the task of confidence estimation in a broader range of failure cases than a single or bi-modal input.…”
Section: Complete Modelsupporting
confidence: 76%
“…Nevertheless, essential issues of CVA arise from the high computational cost of 3D convolutions, the small receptive field, and the exclusive consideration of a single modality, potentially neglecting other valuable information. Kim et al (2019) and Kim et al (2020), on the other hand, consider the cost volume in a multi-modal approach, further extending the quantity of modalities used. For this purpose, features from RGB images, disparity maps and cost volumes are combined, forming a tri-modal input.…”
Section: Related Workmentioning
confidence: 99%
“…With the rise of deep learning, methods based on convolutional neural networks have been developed. Some of these CNN approaches focused on the disparity map learning (Poggi et al, 2017), other methods worked directly with the cost volume in order to take more information into account (Mehltretter and Heipke, 2019;Kim et al, 2019).…”
Section: Related Workmentioning
confidence: 99%
“…[26] proposed a novel method that combines the contextual information with multiviewpoint depth images to construct multiviewpoint context-aware representation for scene classification. Kim et al [27] exploited tri-modal information to produce confidence of the disparity for stereo confidence estimation. However, these methods neglect the spatial relationship among features.…”
Section: B Feature Fusionmentioning
confidence: 99%