Visual Results by Method

Results for methods appear here after users upload them and approve them for public display.


Return to numerical results table



Metrics


EPE Endpoint error over the complete frames
EPE matched Endpoint error over regions that remain visible in adjacent frames
EPE unmatched Endpoint error over regions that are visible only in one of two adjacent frames
d0-10 Endpoint error over regions closer than 10 pixels to the nearest occlusion boundary
d10-60 Endpoint error over regions between 10 and 60 pixels apart from the nearest occlusion boundary
d60-140 Endpoint error over regions between 60 and 140 pixels apart from the nearest occlusion boundary
s0-10 Endpoint error over regions with velocities lower than 10 pixels per frame
s10-40 Endpoint error over regions with velocities between 10 and 40 pixels per frame
s40+ Endpoint error over regions with velocities larger than 40 pixels per frame
All error images are normalized to be in the range between 0 and 1.

References
[1]
2bit-BM-tele
Rui Xu & David Taubman, Robust Dense Block-Based Motion Estimation Using a Two-Bit Transform on a Laplacian Pyramid, ICIP 2013 +telescopic search
[2]
AGIF+OF
Anonymous. Signal Processing 2015
[3]
AggregFlow
D. Fortun, P. Bouthemy and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. CVIU 2016
[4]
AnisoHuber.L1
M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009.
[5]
AnyFlow
Anonymous. PAMI pending review
[6]
AtrousFlow
Anonymous. Real-time dense optical flow using CUDA
[7]
AutoScaler+
Anonymous. AutoScaler+
[8]
BASELINE-Mean
[9]
BASELINE-zero
[10]
COF
H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[11]
CPM-AUG
Anonymous. ICCV 2017 submission #1170
[12]
CPM-Flow
Yinlin Hu, Rui Song, Yunsong Li. Efficient Coarse-to-Fine PatchMatch for Large Displacement Optical Flow. CVPR 2016.
[13]
CPM2
Coarse-to-fine PatchMatch for dense correspondence, Yunsong Li, Yinlin Hu, Rui Song, Peng Rao, Yangli Wang, submitted to T-CSVT
[14]
Channel-Flow
L. Sevilla-Lara, D. Sun, E. Learned-Miller, and M. Black. Optical Flow Estimation with Channel Constancy. ECCV, pages 423-438, 2014.
[15]
Classic++
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[16]
Classic+NL
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[17]
Classic+NL-fast
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[18]
Classic+NLP
D. Sun, S. Roth, and M. Black. A Quantitative Analysis of Current Practices in Optical Flow Estimation and The Principles behind Them. International Journal of Computer Vision (IJCV), 106(2):115-137, 2014.
[19]
ComponentFusion
Anonymous. Fast Optical Flow by Component Fusion. Submitted to ECCV 2014. Paper ID 941.
[20]
DCFlow
Jia Xu, René Ranftl, Vladlen Koltun. Accurate Optical Flow via Direct Cost Volume Processing. CVPR 2017.
[21]
DF
Nelson Monzón, Agustín Salgado and Javier Sánchez. Regularization Strategies for Discontinuity-Preserving Optical Flow Methods. IEEE Transactions on Image Processing, Vol 25(4), pp. 1580 - 1591, 2016
[22]
DF-Auto
Nelson Monzón, Agustín Salgado and Javier Sánchez. Regularization Strategies for Discontinuity-Preserving Optical Flow Methods. IEEE Transactions on Image Processing, Vol 25(4), pp. 1580 - 1591, 2016
[23]
DF-Beta
Nelson Monzón, Agustín Salgado and Javier Sánchez. Regularization Strategies for Discontinuity-Preserving Optical Flow Methods. IEEE Transactions on Image Processing, Vol 25(4), pp. 1580 - 1591, 2016
[24]
DIS-Fast
T. Kroeger, R. Timofte, D. Dai, L. Van Gool, Fast Optical Flow using Dense Inverse Search. ECCV 2016. Run-time: 0.023 s (20ms preprocessing, 3ms flow computation). Using operating point 2 of the paper.
[25]
Data-Flow
Anonymous. CSAD data cost + second order smoothness
[26]
Deep+R
B. Drayer and T. Brox. Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation. BMVC 2015
[27]
DeepDiscreteFlow
F. Güney and A. Geiger. Deep Discrete Flow. Asian Conference on Computer Vision (ACCV) 2016.
[28]
DeepFlow
P. Weinzaepfel, J. Revaud, Z. Harchaoui and C. Schmid. DeepFlow: Large displacement optical flow with deep matching. ICCV 2013.
[29]
DeepFlow2
J. Revaud, P. Weinzaepfel, Z. Harchaoui and C. Schmid. DeepMatching: Hierarchical Deformable Dense Matching. Submitted to IJCV.
[30]
DiscreteFlow
M. Menze, C. Heipke and A. Geiger. Discrete Optimization for Optical Flow. GCPR 2015
[31]
DiscreteFlow+OIR
Anonymous. Anonymous BMVC 2017 submission #662
[32]
EPPM
L. Bao, Q. Yang, and H. Jin. Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow. CVPR 2014.
[33]
EpicFlow
J. Revaud, P. Weinzaepfel, Z. Harchaoui and C. Schmid. EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow. CVPR 2015.
[34]
F3-MPLF
Anonymous. CVPR Submission #1311
[35]
FALDOI
Roberto P.Palomares, Enric Meinhardt-Llopis, Coloma Ballester and Gloria Haro. FALDOI: A new minimization strategy for large displacement variational optical flow. To appear in JMIV
[36]
FC-2Layers-FF
D. Sun, J. Wulff, E. Sudderth, H. Pfister, M.J. Black. A fully connected layered model of foreground and background flow. CVPR 2013
[37]
FFlow
Anonymous. FFlow
[38]
FGI
Y. Li, D. Min, M. N. Do, and J. Lu. Fast Guided Global Interpolation for Depth and Motion. ECCV 2016
[39]
FlowFields
C. Bailer, B. Taetz and D. Stricker. Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation. ICCV 2015.
[40]
FlowFields+
C. Bailer, B. Taetz and D. Stricker. Optical Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation. Submitted to IEEE T-PAMI.
[41]
FlowFieldsCNN
C. Bailer, K Varanasi and D. Stricker. CNN-based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss. CVPR 2017.
[42]
FlowNet2
Anonymous. CVPR Submission #900
[43]
FlowNet2-ft-sintel
Anonymous. CVPR Submission #900
[44]
FlowNetC+ft+v
Anonymous. ICCV sumbmission 235
[45]
FlowNetS+ft+v
Anonymous. ICCV submission 235
[46]
FullFlow
Q. Chen, V. Koltun. Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids. CVPR 2016.
[47]
GlobalPatchCollider
Shenlong Wang, Sean Fanello, Christoph Rhemann, Shahram Izadi and Pushmeet Kohli, The Global Patch Collider, CVPR, 2016
[48]
GroundTruth
[49]
Grts-Flow-V2
En Zhu, Yuanwei Li, Yanling Shi. Fast Optical Flow Estimation without Parallel Architectures. TCSVT
[50]
HAST
Yinlin Hu, Rui Song, Yunsong Li, Peng Rao, Yangli Wang. Highly Accurate Optical Flow Estimation on Superpixel Tree. Image and Vision Computing (IVC), 2016
[51]
HCOF+multi
R. Kennedy and C. J. Taylor. Hierarchically-Constrained Optical Flow. CVPR 2015.
[52]
Horn+Schunck
A modern Matlab implementation of the Horn & Schunck method by Deqing Sun.
[53]
ICALD
Anonymous. BMVC 2017 Submission #390.
[54]
IPOL_Brox
J. Sánchez, N. Monzón, and A. Salgado, Robust Optical Flow Estimation, Image Processing On Line (IPOL), 3 (2013), pp. 252–270.
[55]
InterpoNet_cpm
Anonymous. CVPR 2017 submission, #1887
[56]
InterpoNet_df
Anonymous. CVPR 2017 submission, #1887
[57]
InterpoNet_dm
Anonymous. CVPR 2017 submission, #1887
[58]
InterpoNet_ff
Anonymous. CVPR 2017 submission, #1887
[59]
LDOF
T. Brox, J. Malik. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(3): 500-513, 2011.
[60]
LocalLayering
D. Sun, C. Liu, and H. Pfister. Local Layering for Joint Motion Estimation and Occlusion Detection. CVPR 2014.
[61]
MDP-Flow2
L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012.
[62]
MLDP-OF
M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. Accepted in IEEE TCSVT 2014.
[63]
MR-Flow
Anonymous. N/A
[64]
MirrorFlow
Anonymous. ICCV 2017 submission #230
[65]
NLTGV-SC
R. Ranftl, K. Bredies, T. Pock. Non-Local Total Generalized Variation for Optical Flow Estimation, ECCV 2014
[66]
NNF-Local
Anonymous. Large Displacement Optical Flow from Nearest Neighbor Fields
[67]
OAR-Flow
D. Maurer, M. Stoll, A. Bruhn: Order-Adaptive Regularisation for Variational Optical Flow: Global, Local and in Between. SSVM 2017.
[68]
PCA-Flow
J. Wulff and M. J. Black: Efficient sparse-to-dense optical flow estimation using a learned basis and layers. CVPR 2015.
[69]
PCA-Layers
J. Wulff and M. J. Black: Efficient sparse-to-dense optical flow estimation using a learned basis and layers. CVPR 2015.
[70]
PGM-C
Anonymous
[71]
PH-Flow
Jiaolong Yang and Hongdong Li. Dense, Accurate Optical Flow Estimation with Piecewise Parametric Model. CVPR 2015
[72]
PMF
J. Lu, Y. Li, H. Yang, D. Min, W. Eng, M. N. Do. PatchMatch Filter: Edge-Aware Filtering Meets Randomized Search for Visual Correspondence. TPAMI 2016
[73]
PWC-DC-ft
Anonymous. ICCV 2017 submission #645
[74]
PatchBatch+Inter
T. Schuster, L. Wolf and D. Gadot: Optical Flow Requires Multiple Strategies (but only one network). CVPR 2017.
[75]
PatchBatch-CENT+SD
Anonymous.
[76]
PatchWMF-OF
Zhigang Tu, Coert Van Gemeren and Remco C. Veltkamp. Improved Color Patch Similarity Measure Based Weighted Median Filter. ACCV2014
[77]
PosetOptimization
Anonymous.
[78]
ProbFlowFields
Anonymous. ICCV 2017 submission, # 619
[79]
RC-LSTM-1dir
Learning Contextual Dependencies for Optical Flow with Recurrent Neural Networks (ACCV 2016)
[80]
RC-LSTM-4dir
Learning Contextual Dependencies for Optical Flow with Recurrent Neural Networks (ACCV 2016)
[81]
RLOF_DENSE
Jonas Geistert, Tobias Senst and Thomas Sikora, Robust Local Optical Flow: Dense Motion Vector Field Interpolation, PCS 2016
[82]
ROF-NND
Sharib Ali, Christian Daul, Ernest Galbrun, Walter Blondel, Illumination invariant optical flow using neighborhood descriptors, Computer Vision and Image Understanding, Available online 17 December 2015, ISSN 1077-3142.
[83]
RegionalFF
Anonymous. ICCV 2017 submission, #1533
[84]
RicFlow
Yinlin Hu, Yunsong Li, Rui Song. Robust Interpolation of Correspondences for Large Displacement Optical Flow. CVPR 2017.
[85]
S2D-Matching
M. Leordeanu, A. Zanfir, C. Sminchisescu. Locally Affine Sparse-to-Dense Matching for Motion and Occlusion estimation. ICCV 2013
[86]
S2F-IF
Yanchao Yang, Stefano Soatto. S2F: Slow-To-Fast Interpolator Flow. CVPR 2017.
[87]
SBFlow
Anonymous. SBFlow
[88]
SPM-BP
Y. Li, D. Min, M. S. Brown, M. N. Do, and J. Lu. SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs. ICCV 2015
[89]
SPM-BPv2
Y. Li, D. Min, M. S. Brown, M. N. Do, and J. Lu. SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs. ICCV 2015. Improved version. Details coming soon.
[90]
SPyNet
Anonymous.
[91]
SPyNet+ft
Anonymous.
[92]
STEAFlow-XY
Anonymous. Submitted to TIP.
[93]
STEAFlow-XYT
Anonymous. Submitted to TIP.
[94]
SVFilterOh
Anonymous. ACCV 2016 Submission 363
[95]
SimpleFlow
M. W. Tao, J. Bai, P. Kohli, and S. Paris. "SimpleFlow: A Non-iterative, Sublinear Optical Flow Algorithm". Computer Graphics Forum (Eurographics 2012), 2012. (OpenCV 2.4.5 Implementation, parameters provided by OpenCV sample)
[96]
SparseFlow
Radu Timofte and Luc Van Gool. SparseFlow: Sparse Matching for Small to Large Displacement Optical Flow. WACV 2015
[97]
SparseFlowFused
Radu Timofte and Luc Van Gool. SparseFlow: Sparse Matching for Small to Large Displacement Optical Flow. WACV 2015
[98]
Steered-L1
Anonymous.
[99]
TF+OFM
R. Kennedy and C.J. Taylor. Optical Flow with Geometric Occlusion Estimation and Fusion of Multiple Frames. EMMCVPR 2015.
[100]
TV-L1
Anonymous. It is a well-known model that uses TV-L1 (coupled) as the regularization term and an L1 data term.
[101]
WKSparse
[102]
WLIF-Flow
Z. Tu, R. Poppe, and R. C. Veltkamp. Weighted local intensity fusion method for variational optical flow estimation.Pattern Recognition,2015