Efficient sparse-to-dense optical flow estimation using a learned basis and layers
By Jonas Wulff, Michael J. Black. 2015
198 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Yi Yang
- Chen Change Loy
- Xiaogang Wang
- Andrea Vedaldi
- Jitendra Malik
Citations in the corpus
- FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks (2016, background): “Image Overlay FlowFields [2] DeepFlow [31] LDOF (GPU) [26] PCA-Flow [32] FlowNetS [10] FlowNet2”
- DenseNet for dense flow (2017, unknown): “25 PCA-Flow [19] − 8.”
- An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos (2018, methodology): “Authors [39], propose to trade of accuracy of for fast approximation of optical flow using PCA to interpolate flow fields.”
- Dynamic Video Segmentation Network (2018, background): “Optical flow estimation has been the subject of a number of research works [34, 33, 38, 39, 40, 41, 42].”
- SegFlow: Joint Learning for Video Object Segmentation and Optical Flow (2017, methodology): “On the other hand, learning based methods are more efficient, which can be achieved via Gaussian mixture models [34], principle components [44] or convolutional networks [12, 27].”
- Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “High Speed Flow: With some exceptions (Wulff & Black (2015); Timofte & Gool (2015); Weinzaepfel et al. (2013); Farneback (2003); Zach et al. (2007)) most of the optical flow approaches are very inefficient and can not be applied in real-time which is necessary for applications in autonomous driving.”
- An Unsupervised Learning Model for Deformable Medical Image Registration (2018, unknown): “One study learns a low-dimensional basis for optical flow in natural images using PCA [44].”
- Fast Optical Flow Using Dense Inverse Search (2016, methodology): “For the average EPE of around 6 pixels, DIS is approximately two orders of magnitude faster than the fastest CPU baseline (PCA-Flow [19]) and also more than one order of magnitude faster than the fastest GPU baseline (EPPM [24]).”