paper-with-me

Papers

Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM

2019-07-26 · Shuosen Guan, Haoxin Li, Wei-Shi Zheng

Most of current Convolution Neural Network (CNN) based methods for optical flow estimation focus on learning optical flow on synthetic datasets with groundtruth, which is not practical. In this paper, we propose an unsupervised optical flow estimation framework named PCLNet. It uses pyramid Convolution LSTM (ConvLSTM) with the constraint of adjacent frame reconstruction, which allows flexibly estimating multi-frame optical flows from any video clip. Besides, by decoupling motion feature learning and optical flow representation, our method avoids complex short-cut connections used in existing frameworks while improving accuracy of optical flow estimation. Moreover, different from those methods using specialized CNN architectures for capturing motion, our framework directly learns optical flow from the features of generic CNNs and thus can be easily embedded in any CNN based frameworks for other tasks. Extensive experiments have verified that our method not only estimates optical flow effectively and accurately, but also obtains comparable performance on action recognition.

📄 PDF Abstract BibTeX arXiv:1907.11628

Code (1)

Kwanss/PCLNet 공식 구현 pytorch

Tasks

Action RecognitionOptical Flow Estimation

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling

2021-04-08 · Kunming Luo, Ao Luo, Chuan Wang, Haoqiang Fan 외

We present an unsupervised optical flow estimation method by proposing an adaptive pyramid sampling in the deep pyramid network. Specifically, in the pyramid downsampling, we propose an Content Aware Pooling (CAP) module…

Optical Flow Estimation

UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning

2020-12-01 · CVPR 2021 1 · Kunming Luo, Chuan Wang, Shuaicheng Liu, Haoqiang Fan 외

We present an unsupervised learning approach for optical flow estimation by improving the upsampling and learning of pyramid network. We design a self-guided upsample module to tackle the interpolation blur problem cause…

Optical Flow Estimation

FPCR-Net: Feature Pyramidal Correlation and Residual Reconstruction for Optical Flow Estimation

2020-01-17 · Xiaolin Song, Yuyang Zhao, Jingyu Yang, Cuiling Lan 외

Optical flow estimation is an important yet challenging problem in the field of video analytics. The features of different semantics levels/layers of a convolutional neural network can provide information of different gr…

Optical Flow Estimation

RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation

2024-05-01 · IEEE International Conference on Robotics and Automation (ICRA) 2024 5 · Henrique Morimitsu, Xiaobin Zhu, Roberto M. Cesar-Jr., Xiangyang Ji 외

Extracting motion information from videos with optical flow estimation is vital in multiple practical robot applications. Current optical flow approaches show remarkable accuracy, but top-performing methods have high com…

Optical Flow Estimation

Optical Flow Estimation using a Spatial Pyramid Network

2016-11-03 · CVPR 2017 7 · Anurag Ranjan, Michael J. Black

We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning. This estimates large motions in a coarse-to-fine approach by warping one image of a pair at each pyramid level by …

Dense Pixel Correspondence EstimationOptical Flow Estimation