24 datasets found

A benchmark for optical flow estimation.

Optical flow estimation on edge devices while ensuring high accuracy.

A large-scale labeled RGB-Depth-Optical Flow dataset for action recognition, containing 1,074 long untrimmed videos with paired RGB, depth, and optical flow modalities for 51...

A dataset for optical flow evaluation, including a naturalistic open source movie.

Unsupervised optical flow benchmark datasets

A dataset of synthetic data for action categorization, including simplified videos without background.

A video salient object detection method using optical flow.

The dataset used for training and testing the proposed EDNet model for efficient disparity estimation.

The FlyingThings3D dataset is a benchmark for stereo matching, consisting of a large collection of images and corresponding disparity maps.

KITTI 2015 dataset contains videos in 200 street scenes captured by RGB cameras, with sparse depth ground truths captured by Velodyne laser scanner.

Large dataset for stereo matching, optical flow, and scene flow estimation

The dataset used in the paper for unsupervised single image intrinsic decomposition.

The Middlebury dataset is a benchmark for stereo vision and 3D reconstruction.

The Vimeo90k dataset is a large-scale video frame interpolation dataset.

Video Frame Interpolation (VFI) aims to synthesize intermediate frames in between existing frames to enhance visual smoothness and quality.

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 dataset used in the paper is a Sintel dataset, which consists of low-resolution optical flow maps and their corresponding high-resolution RGB images.

Video inpainting aims to fill spatio-temporal corrupted regions with plausible content. To achieve this goal, it is necessary to find correspondences from neighboring frames to...

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...

Optical flow estimation using a deep lightweight network