Computer Vision, Graphics, and Image Processing
Computation of component image velocity from local phase information
International Journal of Computer Vision
View interpolation for image synthesis
SIGGRAPH '93 Proceedings of the 20th annual conference on Computer graphics and interactive techniques
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)
Black-box testing: techniques for functional testing of software and systems
Black-box testing: techniques for functional testing of software and systems
Performance characteristics of vision algorithms
Machine Vision and Applications - Special issue on performance evaluation
International Journal of Computer Vision
Multiple view geometry in computer visiond
Multiple view geometry in computer visiond
Vision for Mobile Robot Navigation: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance characterisation in computer vision: statistics in testing and design
Imaging and vision systems
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Handbook of Computer Vision and Applications: Volume 2: From Images to Features
Handbook of Computer Vision and Applications: Volume 2: From Images to Features
On Performance Characterization and Optimization for Image Retrieval
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Reliable Estimates of the Sea Surface Heat Flux from Image Sequences
Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
Learning Parameterized Models of Image Motion
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Recognizing Action at a Distance
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Face recognition: A literature survey
ACM Computing Surveys (CSUR)
Automated Analysis of Nursing Home Observations
IEEE Pervasive Computing
High-quality video view interpolation using a layered representation
ACM SIGGRAPH 2004 Papers
On the Spatial Statistics of Optical Flow
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
ACM Computing Surveys (CSUR)
Coarse to over-fine optical flow estimation
Pattern Recognition
Key frame selection by motion analysis
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 02
EURASIP Journal on Applied Signal Processing
Performance characterization in computer vision: A guide to best practices
Computer Vision and Image Understanding
LabelMe: A Database and Web-Based Tool for Image Annotation
International Journal of Computer Vision
Postprocessing of Optical Flows Via Surface Measures and Motion Inpainting
Proceedings of the 30th DAGM symposium on Pattern Recognition
Statistically Optimal Averaging for Image Restoration and Optical Flow Estimation
Proceedings of the 30th DAGM symposium on Pattern Recognition
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
A Statistical Confidence Measure for Optical Flows
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Continuous dimensionality characterization of image structures
Image and Vision Computing
Requirements Analysis & System Design
Requirements Analysis & System Design
Variational Assimilation of Fluid Motion from Image Sequence
SIAM Journal on Imaging Sciences
Optimal filters for extended optical flow
IWCM'04 Proceedings of the 1st international conference on Complex motion
Wiener-optimized discrete filters for differential motion estimation
IWCM'04 Proceedings of the 1st international conference on Complex motion
Nonlinear disparity mapping for stereoscopic 3D
ACM SIGGRAPH 2010 papers
Perception-motivated interpolation of image sequences
ACM Transactions on Applied Perception (TAP)
Building Rome on a cloudless day
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Benchmarking stereo data (not the matching algorithms)
Proceedings of the 32nd DAGM conference on Pattern recognition
A Database and Evaluation Methodology for Optical Flow
International Journal of Computer Vision
Efficient Dense Reconstruction from Video
CVMP '11 Proceedings of the 2011 Conference for Visual Media Production
Two algorithms for motion estimation from alternate exposure images
Proceedings of the 2010 international conference on Video Processing and Computational Video
Learning to find occlusion regions
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Real-time human pose recognition in parts from single depth images
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Variational optical flow computation in real time
IEEE Transactions on Image Processing
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)
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Modeling temporal coherence for optical flow
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Evaluation of image features using a photorealistic virtual world
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
When is a confidence measure good enough?
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
Hi-index | 0.00 |
Literally thousands of articles on optical flow algorithms have been published in the past thirty years. Only a small subset of the suggested algorithms have been analyzed with respect to their performance. These evaluations were based on black-box tests, mainly yielding information on the average accuracy on test-sequences with ground truth. No theoretically sound justification exists on why this approach meaningfully and/or exhaustively describes the properties of optical flow algorithms. In practice, design choices are often made based on unmotivated criteria or by trial and error. This article is a position paper questioning current methods in performance analysis. Without empirical results, we discuss more rigorous and theoretically sound approaches which could enable scientists and engineers alike to make sufficiently motivated design choices for a given motion estimation task.