2018
DOI: 10.1609/aaai.v32i1.12276
|View full text |Cite
|
Sign up to set email alerts
|

UnFlow: Unsupervised Learning of Optical Flow With a Bidirectional Census Loss

Abstract: In the era of end-to-end deep learning, many advances in computer vision are driven by large amounts of labeled data. In the optical flow setting, however, obtaining dense per-pixel ground truth for real scenes is difficult and thus such data is rare. Therefore, recent end-to-end convolutional networks for optical flow rely on synthetic datasets for supervision, but the domain mismatch between training and test scenarios continues to be a challenge. Inspired by classical energy-based optical flow methods, we d… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
94
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 408 publications
(94 citation statements)
references
References 32 publications
0
94
0
Order By: Relevance
“…summa-rizes the quantitative results. We include comparisons with several baseline methods for unsupervised optical flow estimation: Unsup (Jason, Harley, and Derpanis 2016) and Un-Flow (Meister, Hur, and Roth 2018) and its variants, which are also trained on V1FlyingObjects. The proposed model achieves better performance compared to baseline methods.…”
Section: Unsupervised Learningmentioning
confidence: 99%
“…summa-rizes the quantitative results. We include comparisons with several baseline methods for unsupervised optical flow estimation: Unsup (Jason, Harley, and Derpanis 2016) and Un-Flow (Meister, Hur, and Roth 2018) and its variants, which are also trained on V1FlyingObjects. The proposed model achieves better performance compared to baseline methods.…”
Section: Unsupervised Learningmentioning
confidence: 99%
“…The unsupervised methods rely on the brightness constancy constraint and establish a loss function on the original image pixels. In addition to the basic brightness constancy loss, there are many other techniques used for unsupervised optical flow learning, such as smooth constraint (Ren et al 2017;Jason, Harley, and Derpanis 2016), census transformation (Meister, Hur, and Roth 2018). One difficulty of the unsupervised methods is that the pixels in the occluded area do not satisfy the brightness constancy assumption.…”
Section: Optical Flowmentioning
confidence: 99%
“…Early networks are trained on the synthetic dataset [13], that is because the ground truth of optical flow in the real world is difficult to obtain, which increases the difficulty for supervision and estimation. As a result, the method of unsupervised learning on real-world data has attracted much attention [20], [41], [21], [22], [23], [24].…”
Section: B Unsupervised Estimation Of Optical Flowmentioning
confidence: 99%
“…Most supervised research on optical flow has been done on synthetic datasets [18], as well as scene flow [16], [17]. That is why unsupervised learning is as important to scene flow as optical flow [19], [20], [21], [22], [23], [24]. The realworld image data can be used in the unsupervised training of scene flow with suitable losses as shown in Fig.…”
Section: Introductionmentioning
confidence: 99%