9 datasets found

A convolutional neural network for optical flow estimation using pyramid, warping, and cost volume.

A novel motion estimation method that combines object-level representations and matching with a state of the art multi-scale DNN-based method.

The dataset used in the paper is a synthetic dataset of blurred videos, generated by capturing sharp videos at high frame rate and averaging adjacent frames.

The dataset used in the paper is a synthetic dataset of blurred videos, generated by capturing sharp videos at high frame rate and averaging adjacent frames.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors applied their approach to the challenging problem of optical flow estimation and...

MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement.

Dense pixel matching is required for many computer vision algorithms such as disparity, optical flow or scene flow estimation. Feature Pyramid Networks (FPN) have proven to be a...

Dense pixel matching is required for many computer vision algorithms such as disparity, optical flow or scene flow estimation. Feature Pyramid Networks (FPN) have proven to be a...

The KITTI 2015 dataset is a real-world dataset of street views, containing 200 training stereo image pairs with sparsely labeled disparity from LiDAR data.