A Naturalistic Open Source Movie for Optical Flow Evaluation

By Daniel J. Butler, Jonas Wulff, Garrett B. Stanley, Michael J. Black. 2012

2,372 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Evaluation & Benchmarks

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

In Media Technology

In Evaluation & Benchmarks

Citations in the corpus

Perceiver IO: A General Architecture for Structured Inputs & Outputs (2021, methodology): “Private & Confidential We found that concatenating frames led to a non-trivial performance improvement across the more difficult Sintel.final and KITTI Flow 2015 [52] datasets.”
SafetyNet: Detecting and Rejecting Adversarial Examples Robustly (2017, methodology): ““Regression” methods used only in test are: all zero depth values; nearest neighbor down-sample and up-sampled images and depths; low quality JPEG compressed images and depths; Middlebury stereo RGBD dataset [28] and Sintel RGBD dataset [1](which should be classified “fake” because they are renderin”
IRS: A Large Synthetic Indoor Robotics Stereo Dataset for Disparity and Surface Normal Estimation (2019, background): “Recent work in [14], [15], [16] leveraged synthetic technology to generate sufficiently large data volume for DNN training.”
Understanding and Robustifying Differentiable Architecture Search (2019, methodology): “We use the Sintel dataset ( Butler et al. (2012)) for testing our networks.”
Synthetic Data for Text Localisation in Natural Images (2016, methodology): “We prefer to estimate an imperfect depth map instead because: (1) it allows essentially any scene type background image to be used, instead of only the ones for which RGBD data are available, and (2) because publicly available RGBD datasets such as NYUDv2 [40], B3DO [22], Sintel [4], and Make3D [38]”
Lightweight Probabilistic Deep Networks (2018, background): “2 shows how the probabilistic networks perform on select images from the Sintel [8] dataset.”
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation (2015, methodology): “In this regard, it resembles the MPI Sintel dataset.”
FlowNet: Learning Optical Flow with Convolutional Networks (2015, methodology): “Getting optical flow ground truth for realistic video material is known to be extremely difficult [7].”
Playing for Data: Ground Truth from Computer Games (2016, background): “Most recently, the MPI-Sintel dataset has become a standard benchmark for optical flow algorithms [9] and has additionally yielded ground-truth data for depth estimation and bottom-up segmentation.”
Unsupervised Learning of Edges (2015, methodology): “We benchmark optical flow results on the Middlebury [4] and MPI Sintel [7] datasets.”
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer (2019, methodology): “Sintel [1] features perfect ground truth for synthetic scenes.”
Playing for Benchmarks (2017, neutral): “Simulated worlds are commonly used to benchmark optical ﬂow algorithms [5, 4, 8] and visual odometry systems [22, 24, 64].”
Spatio-temporal video autoencoder with differentiable memory (2015, methodology): “…sanity check to conﬁrm the ability of the grid generator GG and image sampler S to generate the next frame given the current frame and the correct optical ﬂow map, we ran simple warping tests using Sintel dataset Butler et al. (2012), by isolating the two modules from the rest of the architecture.”
VirtualWorlds as Proxy for Multi-object Tracking Analysis (2016, neutral): “[26] propose a synthetic benchmark for optical flow estimation: the popular MPI Sintel Flow Dataset.”
A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM (2014, methodology): “Ground truth dataset generation for the assessment of camera pose tracking and object segmentation has been previously presented in many recent works including Tsukuba [6], TUM RGB-D [7], [8], Sintel [9], KITTI [10] and the NYU Dataset [11].”