Name
Abstract | ||
|---|---|---|
Dense motion estimations obtained from optical flow techniques play a significant role in many image processing and computer vision tasks. Remarkable progress has been made in both theory and its application in practice. In this paper, we provide a systematic review of recent optical flow techniques with a focus on the variational method and approaches based on Convolutional Neural Networks (CNNs). These two categories have led to state-of-the-art performance. We discuss recent modifications and extensions of the original model, and highlight remaining challenges. For the first time, we provide an overview of recent CNN-based optical flow methods and discuss their potential and current limitations. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1016/j.image.2018.12.002 | Signal Processing: Image Communication |
Keywords | Field | DocType |
Optical flow,Variational method,CNN-based method,Evaluation measures,Challenges | Convolutional neural network,Computer science,Variational method,Image processing,Theoretical computer science,Computer engineering,Optical flow | Journal |
Volume | ISSN | Citations |
72 | 0923-5965 | 5 |
PageRank | References | Authors |
0.46 | 60 | 7 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhigang Tu | 1 | 85 | 11.72 |
| Wei Xie | 2 | 29 | 2.53 |
| Dejun Zhang | 3 | 238 | 19.97 |
| Ronald Poppe | 4 | 1083 | 49.93 |
| Remco C. Veltkamp | 5 | 2127 | 157.19 |
| Baoxin Li | 6 | 1017 | 94.72 |
| Junsong Yuan | 7 | 3703 | 187.68 |