Method Setting Code Out-Noc Out-All Avg-Noc Avg-All Density Runtime Environment 1 GC-NET 1.77 % 2.30 % 0.6 px 0.7 px 100.00 % 0.9 s Nvidia GTX Titan X A. Kendall, H. Martirosyan, S. Dasgupta, P. Henry, R. Kennedy, A. Bachrach and A. Bry: End-to-End Learning of Geometry and Context for Deep Stereo Regression . arXiv preprint arxiv:1703.04309 2017. 2 L-ResMatch code 2.27 % 3.40 % 0.7 px 1.0 px 100.00 % 48 s Titan X (Torch7, CUDA) A. Shaked and L. Wolf: Improved Stereo Matching with Constant Highway Networks and Reflective Loss . arXiv preprint arxiv:1701.00165 2016. 3 CNNF+SGM 2.28 % 3.48 % 0.7 px 0.9 px 100.00 % 71 s TESLA K40C 4 SN 2.29 % 3.50 % 0.7 px 0.9 px 100.00 % 67 s Titan X 5 PBCP 2.36 % 3.45 % 0.7 px 0.9 px 100.00 % 68 s Nvidia GTX Titan X A. Seki and M. Pollefeys: Patch Based Confidence Prediction for Dense Disparity Map . British Machine Vision Conference (BMVC) 2016. 6 Displets v2 code 2.37 % 3.09 % 0.7 px 0.8 px 100.00 % 265 s >8 cores @ 3.0 Ghz (Matlab + C/C++) F. Guney and A. Geiger: Displets: Resolving Stereo Ambiguities using Object Knowledge . Conference on Computer Vision and Pattern Recognition (CVPR) 2015. 7 MC-CNN-acrt code 2.43 % 3.63 % 0.7 px 0.9 px 100.00 % 67 s Nvidia GTX Titan X (CUDA, Lua/Torch7) J. Zbontar and Y. LeCun: Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches . Submitted to JMLR . 8 cfusion
code 2.46 % 2.69 % 0.8 px 0.8 px 99.93 % 70 s GPU (Matlab + CUDA) V. Ntouskos and F. Pirri: Confidence driven TGV fusion . arXiv preprint arXiv:1603.09302 2016. 9 Displets code 2.47 % 3.27 % 0.7 px 0.9 px 100.00 % 265 s >8 cores @ 3.0 Ghz (Matlab + C/C++) F. Guney and A. Geiger: Displets: Resolving Stereo Ambiguities using Object Knowledge . Conference on Computer Vision and Pattern Recognition (CVPR) 2015. 10 MC-CNN 2.61 % 3.84 % 0.8 px 1.0 px 100.00 % 100 s Nvidia GTX Titan (CUDA, Lua/Torch7) J. Zbontar and Y. LeCun: Computing the Stereo Matching Cost with a Convolutional Neural Network . Conference on Computer Vision and Pattern Recognition (CVPR) 2015. 11 PRSM
code 2.78 % 3.00 % 0.7 px 0.7 px 100.00 % 300 s 1 core @ 2.5 Ghz (C/C++) C. Vogel, K. Schindler and S. Roth: 3D Scene Flow Estimation with a Piecewise Rigid Scene Model . ijcv 2015. 12 SPS-StFl
2.83 % 3.64 % 0.8 px 0.9 px 100.00 % 35 s 1 core @ 3.5 Ghz (C/C++) K. Yamaguchi, D. McAllester and R. Urtasun: Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation . ECCV 2014. 13 MC-CNN-SS 3.02 % 4.45 % 0.8 px 1.0 px 100.00 % 1.35 s 1 core 2.5 Ghz + K40 NVIDIA, Lua-Torch 14 VC-SF
3.05 % 3.31 % 0.8 px 0.8 px 100.00 % 300 s 1 core @ 2.5 Ghz (C/C++) C. Vogel, S. Roth and K. Schindler: View-Consistent 3D Scene Flow Estimation over Multiple Frames . Proceedings of European Conference on Computer Vision. Lecture Notes in, Computer Science 2014. 15 Content-CNN 3.07 % 4.29 % 0.8 px 1.0 px 100.00 % 0.7 s Nvidia GTX Titan X (Torch) W. Luo, A. Schwing and R. Urtasun: Efficient Deep Learning for Stereo Matching . CVPR 2016. 16 TBR 3.09 % 4.29 % 0.7 px 0.9 px 100.00 % 1750 s 4 cores @ 3.0 Ghz (Matlab + C/C++) 17 Deep Embed 3.10 % 4.24 % 0.9 px 1.1 px 100.00 % 3 s 1 core @ 2.5 Ghz (C/C++) Z. Chen, X. Sun, Y. Yu, L. Wang and C. Huang: A Deep Visual Correspondence Embedding Model for Stereo Matching Costs . ICCV 2015. 18 JSOSM 3.15 % 3.94 % 0.8 px 0.9 px 100.00 % 105 s 8 cores @ 2.5 Ghz (C/C++) X. Li and J. Liu: EFFICIENT STEREO MATCHING USING SEGMENT OPTIMIZATION . ICIP 2016. 19 LPU 3.22 % 4.27 % 0.8 px 1.0 px 100.00 % 1650 s 1 core @ 2.5 Ghz (C/C++) 20 OSF
code 3.28 % 4.07 % 0.8 px 0.9 px 99.98 % 50 min 1 core @ 3.0 Ghz (Matlab + C/C++) M. Menze and A. Geiger: Object Scene Flow for Autonomous Vehicles . Conference on Computer Vision and Pattern Recognition (CVPR) 2015. 21 CoR code 3.30 % 4.10 % 0.8 px 0.9 px 100.00 % 6 s 6 cores @ 3.3 Ghz (Matlab + C/C++) A. Chakrabarti, Y. Xiong, S. Gortler and T. Zickler: Low-level Vision by Consensus in a Spatial Hierarchy of Regions . CVPR 2015. 22 TCD-CRF 3.32 % 5.24 % 0.9 px 1.9 px 100.00 % 60 s 4 cores @ 3.5 Ghz (C/C++) S. Arjomand Bigdeli, G. Budweiser and M. Zwicker: Temporally Coherent Disparity Maps Using CRFs with Fast 4D Filtering . Proc. ACPR 2015. 23 SPS-St code 3.39 % 4.41 % 0.9 px 1.0 px 100.00 % 2 s 1 core @ 3.5 Ghz (C/C++) K. Yamaguchi, D. McAllester and R. Urtasun: Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation . ECCV 2014. 24 PCBP-SS 3.40 % 4.72 % 0.8 px 1.0 px 100.00 % 5 min 4 cores @ 2.5 Ghz (Matlab + C/C++) K. Yamaguchi, D. McAllester and R. Urtasun: Robust Monocular Epipolar Flow Estimation . CVPR 2013. 25 STD 3.48 % 4.24 % 0.9 px 1.0 px 99.99 % 40 min 2 cores @ 3.0 Ghz (C/C++) 26 MN 3.58 % 4.77 % 0.9 px 1.1 px 100.00 % 3 min >8 cores @ 2.5 Ghz (C/C++) 27 CPM2 code 3.58 % 4.41 % 0.9 px 1.1 px 99.99 % 1.8 s 1 core @ 2.5 Ghz (C/C++) 28 DDS-SS 3.83 % 4.59 % 0.9 px 1.0 px 100.00 % 1 min 1 core @ 2.5 Ghz (Matlab + C/C++) D. Wei, C. Liu and W. Freeman: A Data-driven Regularization Model for Stereo and Flow . 3DTV-Conference, 2014 International Conference on 2014. 29 StereoSLIC 3.92 % 5.11 % 0.9 px 1.0 px 99.89 % 2.3 s 1 core @ 3.0 Ghz (C/C++) K. Yamaguchi, D. McAllester and R. Urtasun: Robust Monocular Epipolar Flow Estimation . CVPR 2013. 30 SMCM 3.94 % 5.24 % 0.9 px 1.1 px 100.00 % 1800 s Nvidia GTX 1080 (Caffe) M. Yang, Y. Liu, Y. Cai and Z. You: Stereo matching based on classification of materials . Neurocomputing 2016. 31 PR-Sf+E
4.02 % 4.87 % 0.9 px 1.0 px 100.00 % 200 s 4 cores @ 3.0 Ghz (Matlab + C/C++) C. Vogel, K. Schindler and S. Roth: Piecewise Rigid Scene Flow . International Conference on Computer Vision (ICCV) 2013. 32 PCBP 4.04 % 5.37 % 0.9 px 1.1 px 100.00 % 5 min 4 cores @ 2.5 Ghz (Matlab + C/C++) K. Yamaguchi, T. Hazan, D. McAllester and R. Urtasun: Continuous Markov Random Fields for Robust Stereo Estimation . ECCV 2012. 33 DispNetC code 4.11 % 4.65 % 0.9 px 1.0 px 100.00 % 0.06 s Nvidia GTX Titan X (Caffe) N. Mayer, E. Ilg, P. Häusser, P. Fischer, D. Cremers, A. Dosovitskiy and T. Brox: A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation . CVPR 2016. 34 CSPMS 4.13 % 5.92 % 1.2 px 1.6 px 100.00 % 6 s 4 cores @ 2.5 Ghz (C/C++) J. Cho and M. Humenberger: Fast PatchMatch Stereo Matching Using Multi-Scale Cost Fusion for Automotive Applications . IV 2015. 35 SGM-post 4.27 % 5.33 % 1.0 px 1.1 px 100.00 % 5 s 4 cores @ 2.5 Ghz (C/C++) Z. Zhong: Efficient Learning based Semi-Global Stereo Matching . 2015 submitted. 36 SD4CNN 4.27 % 5.45 % 1.0 px 1.1 px 100.00 % 2 s 4 cores @ >3.5 Ghz (C/C++) 37 MBM 4.35 % 5.43 % 1.0 px 1.1 px 100.00 % 0.2 s 1 core @ 3.0 Ghz (C/C++) N. Einecke and J. Eggert: A Multi-Block-Matching Approach for Stereo . IV 2015. 38 PR-Sceneflow
4.36 % 5.22 % 0.9 px 1.1 px 100.00 % 150 sec 4 core @ 3.0 Ghz (Matlab - C/C++) C. Vogel, K. Schindler and S. Roth: Piecewise Rigid Scene Flow . International Conference on Computer Vision (ICCV) 2013. 39 CoR-Conf code 4.49 % 5.26 % 1.0 px 1.2 px 96.37 % 6 s 6 cores @ 3.3 Ghz (Matlab + C/C++) A. Chakrabarti, Y. Xiong, S. Gortler and T. Zickler: Low-level Vision by Consensus in a Spatial Hierarchy of Regions . CVPR 2015. 40 sgm 4.50 % 5.74 % 1.1 px 1.3 px 96.89 % 1 s 1 core @ 2.5 Ghz (C/C++) 41 TVTGV 4.60 % 6.09 % 1.3 px 1.5 px 100.00 % 5.6 s GPU @ 2.5 Ghz (C/C++) 42 AEGF 4.81 % 6.12 % 1.2 px 1.8 px 99.99 % 8 s 1 core @ 2.5 Ghz (C/C++) 43 AARBM 4.86 % 5.94 % 1.0 px 1.2 px 100.00 % 0.25 s 1 core @ 3.0 Ghz (C/C++) N. Einecke and J. Eggert: Block-Matching Stereo with Relaxed Fronto-Parallel Assumption . IV 2014. 44 wSGM 4.97 % 6.18 % 1.3 px 1.6 px 97.03 % 6s 1 core @ 3.5 Ghz (C/C++) R. Spangenberg, T. Langner and R. Rojas: Weighted Semi-Global Matching and Center-Symmetric Census Transform for Robust Driver Assistance . CAIP 2013. 45 AABM 4.97 % 6.04 % 1.0 px 1.2 px 100.00 % 0.12 s 1 core @ 3.1 Ghz (C/C++) N. Einecke and J. Eggert: Stereo Image Warping for Improved Depth Estimation of Road Surfaces . IV 2013. 46 ATGV 5.02 % 6.88 % 1.0 px 1.6 px 100.00 % 6 min >8 cores @ 3.0 Ghz (Matlab + C/C++) R. Ranftl, T. Pock and H. Bischof: Minimizing TGV-based Variational Models with Non-Convex Data terms . ICSSVM 2013. 47 rSGM code 5.03 % 6.60 % 1.1 px 1.5 px 97.22 % 0.2 s 4 cores @ 2.6 Ghz (C/C++) R. Spangenberg, T. Langner, S. Adfeldt and R. Rojas: Large Scale Semi-Global Matching on the CPU . IV 2014. 48 DeepCostAggr 5.08 % 6.37 % 1.1 px 1.4 px 100.00 % 0.03 s GPU @ 2.5 Ghz (C/C++) 49 iSGM 5.11 % 7.15 % 1.2 px 2.1 px 94.70 % 8 s 2 cores @ 2.5 Ghz (C/C++) S. Hermann and R. Klette: Iterative Semi-Global Matching for Robust Driver Assistance Systems . ACCV 2012. 50 RBM 5.18 % 6.21 % 1.1 px 1.3 px 100.00 % 0.2 s 1 core @ 3.0 Ghz (C/C++) N. Einecke and J. Eggert: Block-Matching Stereo with Relaxed Fronto-Parallel Assumption . IV 2014. 51 ARW code 5.20 % 6.87 % 1.2 px 1.5 px 99.33 % 4.6s 1 core @ 3.5 Ghz (MATLAB+C/C++) S. Lee, J. Lee, J. Lim and I. Suh: Robust Stereo Matching using Adaptive Random Walk with Restart Algorithm . Image and vision computing (accepted) 2015. 52 DLP 5.28 % 7.21 % 1.2 px 2.0 px 100.00 % 60 s 8 cores @ >3.5 Ghz (C/C++) V. Nguyen, H. Nguyen and J. Jeon: Robust Stereo Data Cost With a Learning Strategy . IEEE Transactions on Intelligent Transportation Systems 2017. 53 Ensemble 5.34 % 6.91 % 1.5 px 2.0 px 100.00 % 135 s 2 cores @ >3.5 Ghz (Matlab) A. Spyropoulos and P. Mordohai: Ensemble Classifier for Combining Stereo Matching Algorithms . International Conference on 3D Vision (3DV) 2015. 54 ALTGV 5.36 % 6.49 % 1.1 px 1.2 px 100.00 % 20 s GPU @ 2.5 Ghz (C/C++) G. Kuschk and D. Cremers: Fast and Accurate Large-scale Stereo Reconstruction using Variational Methods . ICCV Workshop on Big Data in 3D Computer Vision 2013. 55 SNCC 5.40 % 6.44 % 1.2 px 1.3 px 100.00 % 0.11 s 1 core @ 3.1 Ghz (C/C++) N. Einecke and J. Eggert: A Two-Stage Correlation Method for Stereoscopic Depth Estimation . DICTA 2010. 56 CAT 5.45 % 6.54 % 1.1 px 1.2 px 100.00 % 10 s 1 core @ 3.5 Ghz (C/C++) J. Ha, J. Jeon, G. Bae, S. Jo and H. Jeong: Cost Aggregation Table: Cost Aggregation Method Using Summed Area Table Scheme for Dense Stereo Correspondence . Advances in Visual Computing 2014. 57 SGM 5.76 % 7.00 % 1.2 px 1.3 px 85.80 % 3.7 s 1 core @ 3.0 Ghz (C/C++) H. Hirschmueller: Stereo Processing by Semi-Global Matching and Mutual Information . PAMI 2008. 58 mSGM-LDE 6.01 % 8.22 % 1.4 px 2.4 px 100.00 % 55 s 2 cores @ 2.5 Ghz (C/C++) V. Nguyen, D. Nguyen, S. Lee and J. Jeon: Local Density Encoding for Robust Stereo Matching . TCSVT 2014. 59 Toast2
6.16 % 7.42 % 1.2 px 1.4 px 95.39 % 0.03 s 4 cores @ 3.5 Ghz (C/C++) B. Ranft and T. Strau\ss: Modeling Arbitrarily Oriented Slanted Planes for Efficient Stereo Vision based on Block Matching . Intelligent Transportation Systems (ITSC), 2014 IEEE 17th International Conference on 2014. 60 ITGV 6.20 % 7.30 % 1.3 px 1.5 px 100.00 % 7 s 1 core @ 3.0 Ghz (Matlab + C/C++) R. Ranftl, S. Gehrig, T. Pock and H. Bischof: Pushing the Limits of Stereo Using Variational Stereo Estimation . IV 2012. 61 TFS
6.28 % 6.59 % 1.4 px 1.5 px 97.32 % 0.4 s 1 core @ 3.5 Ghz (C/C++) 62 WlinBPM 6.43 % 8.60 % 1.2 px 2.0 px 99.99 % 2.5 min 1 core @ 2.5 Ghz (C/C++) ERROR: Wrong syntax in BIBTEX file. 63 ELSEP 6.84 % 8.02 % 1.3 px 1.5 px 82.28 % 1 s 1 core @ 2.5 Ghz (Python) 64 EGCCS 7.10 % 8.58 % 1.5 px 2.0 px 100.00 % 280 s 1 core @ 3.0 Ghz (C/C++) 65 OCV-SGBM code 7.64 % 9.13 % 1.8 px 2.0 px 86.50 % 1.1 s 1 core @ 2.5 Ghz (C/C++) H. Hirschmueller: Stereo processing by semiglobal matching and mutual information . PAMI 2008. 66 SSMW 7.83 % 8.95 % 1.6 px 1.8 px 99.99 % 2.5 min 8 cores @ 2.5 Ghz (C/C++) X. Li, J. Liu, G. Chen and H. Fu: Efficient Methods Using Slanted Support Windows for Slanted Surfaces . IET Computer Vision, http://ietdl.org/t/5QsTxb 2016. 67 MSMW
code 8.01 % 9.24 % 1.6 px 1.7 px 72.39 % 3 min 4 cores @ 2.5 Ghz (C/C++) A. Buades and G. Facciolo: On the performance of local methods for stereovision . 2013 submitted. 68 ELAS code 8.24 % 9.96 % 1.4 px 1.6 px 94.55 % 0.3 s 1 core @ 2.5 Ghz (C/C++) A. Geiger, M. Roser and R. Urtasun: Efficient Large-Scale Stereo Matching . ACCV 2010. 69 linBP 8.56 % 10.70 % 1.7 px 2.7 px 99.89 % 1.6 min 1 core @ 3.0 Ghz (C/C++) W. Khan, V. Suaste, D. Caudillo and R. Klette: Belief Propagation Stereo Matching Compared to iSGM on Binocular or Trinocular Video Data . IV 2013. 70 ADSM 8.71 % 10.05 % 2.1 px 2.7 px 100.00 % 125 s 1 core @ 2.0 Ghz (C/C++) 71 Deep-Raw 8.93 % 11.07 % 3.9 px 4.9 px 100.00 % 1 s 1 core @ 2.5 Ghz (C/C++) Z. Chen, X. Sun, Y. Yu, L. Wang and C. Huang: A Deep Visual Correspondence Embedding Model for Stereo Matching Costs . ICCV 2015. 72 S+GF (Cen) code 9.03 % 11.21 % 2.1 px 3.4 px 100.00 % 140 s 1 core @ 3.0 Ghz (C/C++) K. Zhang, Y. Fang, D. Min, L. Sun, S. Yang, S. Yan and Q. Tian: Cross-Scale Cost Aggregation for Stereo Matching . CVPR 2014. 73 CrossCensus 9.46 % 10.86 % 2.3 px 2.7 px 100.00 % 30 s 1 core @ 2.5 Ghz (C/C++) K. Zhang, J. Lu and G. Lafruit: Cross-Based Local Stereo Matching Using Orthogonal Integral Images . Circuits and Systems for Video Technology, IEEE Transactions on 2009. 74 SymST-GP 9.79 % 11.66 % 2.5 px 3.3 px 100.00 % 0.254 s Dual - Nvidia GTX Titan (CUDA) R. Ralha, G. Falcao, J. Amaro, V. Mota, M. Antunes, J. Barreto and U. Nunes: Parallel refinement of slanted 3D reconstruction using dense stereo induced from symmetry . Journal of Real-Time Image Processing 2016. 75 SM_GPTM 9.79 % 11.38 % 2.1 px 2.6 px 100.00 % 6.5 s 2 cores @ 2.5 Ghz (C/C++) C. Cigla and A. Alatan: An Improved Stereo Matching Algorithm with Ground Plane and Temporal Smoothness Constraints . ECCV Workshops 2012. 76 LAMC-DSΜ 9.82 % 11.49 % 2.1 px 2.7 px 99.96 % 10.8 min 2 cores @ 2.5 Ghz (Matlab) C. Stentoumis, L. Grammatikopoulos, I. Kalisperakis, E. Petsa and G. Karras: A local adaptive approach for dense stereo matching in architectural scene reconstruction . ISPRS 2013. 77 IIW 10.78 % 12.62 % 3.3 px 4.3 px 70.85 % 5.5 s 1 core @ 2.5 Ghz (C/C++) A. Murarka and N. Einecke: A meta-technique for increasing density of local stereo methods through iterative interpolation and warping . Canadian Conference on Computer and Robot Vision 2014. 78 SDM code 10.95 % 12.14 % 2.0 px 2.3 px 63.58 % 1 min 1 core @ 2.5 Ghz (C/C++) J. Kostkova: Stratified dense matching for stereopsis in complex scenes . BMVC 2003. 79 HLSC_mesh 11.22 % 12.82 % 2.3 px 2.9 px 100.00 % 800 s 1 core @ 2.5 Ghz (Matlab + C/C++) S. Hadfield, K. Lebeda and R. Bowden: Stereo reconstruction using top-down cues . Computer Vision and Image Understanding 2016. 80 GF (Census) code 11.65 % 13.76 % 4.5 px 5.6 px 100.00 % 120 s 1 core @ 3.0 Ghz (C/C++) A. Hosni, C. Rhemann, M. Bleyer, C. Rother and M. Gelautz: Fast Cost-Volume Filtering for Visual Correspondence and Beyond . TPAMI 2013. K. Zhang, Y. Fang, D. Min, L. Sun, S. Yang, S. Yan and Q. Tian: Cross-Scale Cost Aggregation for Stereo Matching . CVPR 2014. 81 BSM code 11.74 % 13.44 % 2.2 px 2.8 px 97.02 % 2.5 min 1 core @ 3.0 Ghz (C/C++) K. Zhang, J. Li, Y. Li, W. Hu, L. Sun and S. Yang: Binary stereo matching . Pattern Recognition (ICPR), 2012 21st International Conference on 2012. 82 GCSF
code 12.05 % 13.24 % 1.9 px 2.1 px 60.77 % 2.4 s 1 core @ 2.5 Ghz (C/C++) J. Cech, J. Sanchez-Riera and R. Horaud: Scene Flow Estimation by Growing Correspondence Seeds . CVPR 2011. 83 OCV-BM-post code 12.28 % 13.76 % 2.1 px 2.3 px 47.11 % 0.1 s 1 core @ 2.5 Ghz (C/C++) G. Bradski: The OpenCV Library . Dr. Dobb's Journal of Software Tools 2000. 84 GCS code 13.38 % 14.54 % 2.1 px 2.3 px 51.06 % 2.2 s 1 core @ 2.5 Ghz (C/C++) J. Cech and R. Sara: Efficient Sampling of Disparity Space for Fast And Accurate Matching . BenCOS 2007. 85 CostFilter code 19.99 % 21.08 % 5.0 px 5.4 px 100.00 % 4 min 1 core @ 2.5 Ghz (Matlab) C. Rhemann, A. Hosni, M. Bleyer, C. Rother and M. Gelautz: Fast Cost-Volume Filtering for Visual Correspondence and Beyond . CVPR 2011. 86 GC+occ code 33.49 % 34.73 % 8.6 px 9.2 px 87.57 % 6 min 1 core @ 2.5 Ghz (C/C++) V. Kolmogorov and R. Zabih: Computing Visual Correspondence with Occlusions using Graph Cuts . ICCV 2001. 87 VariableCros 34.84 % 36.11 % 12.4 px 12.9 px 95.66 % 30 s 1 core @ 2.5 Ghz (Matlab) K. Zhang, J. Lu and G. Lafruit: Cross-Based Local Stereo Matching Using Orthogonal Integral Images . Circuits and Systems for Video Technology, IEEE Transactions on 2009. 88 ALE-Stereo code 50.48 % 51.19 % 13.0 px 13.5 px 100.00 % 50 min 1 core @ 3.0 Ghz (C/C++) L. Ladicky, P. Sturgess, C. Russell, S. Sengupta, Y. Bastanlar, W. Clocksin and P. Torr: Joint Optimisation for Object Class Segmentation and Dense Stereo Reconstruction . BMVC 2010. 89 MEDIAN 52.61 % 53.67 % 7.7 px 8.2 px 99.95 % 0.01 s 1 core @ 2.5 Ghz (C/C++) 90 AVERAGE 61.62 % 62.49 % 8.0 px 8.6 px 99.95 % 0.01 s 1 core @ 2.5 Ghz (C/C++)