Corpus ID: 232352398

GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning

  title={GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning},
  author={Haipeng Li and Kunming Luo and Shuaicheng Liu},
Existing optical flow methods are erroneous in challenging scenes, such as fog, rain, and night because the basic optical flow assumptions such as brightness and gradient constancy are broken. To address this problem, we present an unsupervised learning approach that fuses gyroscope into optical flow learning. Specifically, we first convert gyroscope readings into motion fields named gyro field. Second, we design a self-guided fusion module to fuse the background motion extracted from the gyro… Expand


DeepOIS: Gyroscope-Guided Deep Optical Image Stabilizer Compensation
A deep network is proposed that compensates the motions caused by the OIS, such that the gyroscopes can be used for image alignment on the Ois cameras, delivering strong robustness and comparable results with a relatively large margin. Expand
UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss
This work designs an unsupervised loss based on occlusion-aware bidirectional flow estimation and the robust census transform to circumvent the need for ground truth flow, enabling generic pre-training of supervised networks for datasets with limited amounts of ground truth. Expand
SelFlow: Self-Supervised Learning of Optical Flow
We present a self-supervised learning approach for optical flow. Our method distills reliable flow estimations from non-occluded pixels, and uses these predictions as ground truth to learn opticalExpand
Gyroscope-Aided Motion Deblurring with Deep Networks
A deblurring method that incorporates gyroscope measurements into a convolutional neural network (CNN) can handle extremely strong and spatially-variant motion blur and is shown to improve the performance of existing feature detectors and descriptors against the motion blur. Expand
Optical Flow in Dense Foggy Scenes Using Semi-Supervised Learning
A semi-supervised deep learning technique that employs real fog images without optical flow ground-truths in the training process, which outperforms the state-of-the-art methods in estimating optical flow in dense foggy scenes and proposes a new training strategy that combines supervised synthetic-data training and unsupervised real- data training. Expand
Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness
An unsupervised approach to train a convnet end-to-end for predicting optical flow between two images using a loss function that combines a data term that measures photometric constancy over time with a spatial term that models the expected variation of flow across the image. Expand
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
This paper presents an alternative network that attains performance on par with FlowNet2 on the challenging Sintel final pass and KITTI benchmarks, while being 30 times smaller in the model size and 1.36 times faster in the running speed. Expand
Unsupervised Deep Learning for Optical Flow Estimation
This work devise a simple yet effective unsupervised method for learning optical flow, by directly minimizing photometric consistency by using image warping by the estimated flow. Expand
Optical Flow in the Dark
This work develops a method to synthesize large-scale low-light optical flow datasets by simulating the noise model on dark raw images and collects a new optical flow dataset in raw format with a large range of exposure to be used as a benchmark. Expand
UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning
This work designs a self-guided upsample module to tackle the interpolation blur problem caused by bilinear upsampling between pyramid levels, and proposes a pyramid distillation loss to add supervision for intermediate levels via distilling the finest flow as pseudo labels. Expand