Performance of optical flow techniques
International Journal of Computer Vision
Optical flow estimation: advances and comparisons
ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Computer Vision and Image Understanding - Special issue on empirical evaluation of computer vision algorithms
On the Spatial Statistics of Optical Flow
International Journal of Computer Vision
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Database and Evaluation Methodology for Optical Flow
International Journal of Computer Vision
Are we ready for autonomous driving? The KITTI vision benchmark suite
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Lessons and insights from creating a synthetic optical flow benchmark
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
Ground truth design principles: an overview
Proceedings of the International Workshop on Video and Image Ground Truth in Computer Vision Applications
Is crowdsourcing for optical flow ground truth generation feasible?
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
When is a confidence measure good enough?
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
International Journal of Computer Vision
Hi-index | 0.00 |
Ground truth optical flow is difficult to measure in real scenes with natural motion. As a result, optical flow data sets are restricted in terms of size, complexity, and diversity, making optical flow algorithms difficult to train and test on realistic data. We introduce a new optical flow data set derived from the open source 3D animated short film Sintel. This data set has important features not present in the popular Middlebury flow evaluation: long sequences, large motions, specular reflections, motion blur, defocus blur, and atmospheric effects. Because the graphics data that generated the movie is open source, we are able to render scenes under conditions of varying complexity to evaluate where existing flow algorithms fail. We evaluate several recent optical flow algorithms and find that current highly-ranked methods on the Middlebury evaluation have difficulty with this more complex data set suggesting further research on optical flow estimation is needed. To validate the use of synthetic data, we compare the image- and flow-statistics of Sintel to those of real films and videos and show that they are similar. The data set, metrics, and evaluation website are publicly available.