High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

DeepC-MVS_fast	93.32 1	96.48 22	96.42 27	96.56 20	98.70 25	98.31 38	97.97 22	95.76 20	96.31 14	92.01 27	91.43 40	95.42 40	96.46 22	97.65 11	97.69 1	98.49 31	98.12 47
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepPCF-MVS	92.65 2	95.50 33	96.96 19	93.79 51	96.44 57	98.21 42	93.51 96	94.08 36	96.94 4	89.29 44	93.08 32	96.77 28	93.82 54	97.68 9	97.40 4	95.59 178	98.65 16

DeepC-MVS	92.10 3	95.22 34	94.77 41	95.75 30	97.77 38	98.54 25	97.63 28	95.96 17	95.07 31	88.85 48	85.35 74	91.85 54	95.82 30	96.88 28	97.10 12	98.44 38	98.63 17
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PLC	90.69 4	94.32 46	92.99 57	95.87 28	97.91 34	96.49 92	95.95 51	94.12 35	94.94 32	94.09 12	85.90 70	90.77 63	95.58 33	94.52 84	93.32 97	97.55 115	95.00 146
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator+	90.56 5	95.06 36	94.56 45	95.65 31	98.11 32	98.15 45	97.19 33	91.59 51	95.11 30	93.23 22	81.99 101	94.71 43	95.43 36	96.48 39	96.88 18	98.35 46	98.63 17

TAPA-MVS	90.35 6	93.69 53	93.52 51	93.90 47	96.89 52	97.62 63	96.15 45	91.67 50	94.94 32	85.97 73	87.72 58	91.96 53	94.40 44	93.76 99	93.06 107	98.30 54	95.58 134
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
3Dnovator	90.28 7	94.70 42	94.34 48	95.11 35	98.06 33	98.21 42	96.89 38	91.03 57	94.72 37	91.45 29	82.87 92	93.10 50	94.61 41	96.24 48	97.08 13	98.63 21	98.16 43

PCF-MVS	90.19 8	92.98 56	92.07 71	94.04 43	96.39 58	97.87 51	96.03 48	95.47 29	87.16 116	85.09 91	84.81 78	93.21 49	93.46 60	91.98 133	91.98 129	97.78 98	97.51 71
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.13 9	92.03 66	91.70 77	92.41 71	94.92 77	96.44 96	93.95 82	89.96 67	91.81 63	85.48 86	90.97 42	79.12 122	92.42 72	93.28 112	92.55 116	97.76 100	97.74 64
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	88.76 10	91.70 75	90.43 90	93.19 57	95.56 67	95.14 110	93.35 100	91.48 52	92.26 58	87.12 63	84.02 82	79.34 121	93.99 50	94.07 93	92.68 113	97.62 114	95.50 135
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OpenMVS	88.18 11	92.51 61	91.61 78	93.55 53	97.74 39	98.02 49	95.66 53	90.46 61	89.14 101	86.50 69	75.80 135	90.38 69	92.69 69	94.99 67	95.30 57	98.27 58	97.63 65

ACMH+	85.75 12	87.19 126	86.02 142	88.56 115	93.42 103	94.41 119	89.91 148	87.66 107	83.45 152	72.25 146	76.42 132	71.99 153	90.78 89	89.86 166	90.94 143	97.32 121	95.11 145

ACMH	85.51 13	87.31 124	86.59 134	88.14 120	93.96 89	94.51 115	89.00 164	87.99 96	81.58 162	70.15 159	78.41 119	71.78 154	90.60 94	91.30 142	91.99 128	97.17 128	96.58 100
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IB-MVS	85.10 14	87.98 118	87.97 119	87.99 122	94.55 80	96.86 86	84.52 194	88.21 94	86.48 126	88.54 52	74.41 143	77.74 134	74.10 201	89.65 171	92.85 111	98.06 79	97.80 63
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
COLMAP_ROB	84.39 15	87.61 121	86.03 141	89.46 105	95.54 69	94.48 116	91.77 126	90.14 66	87.16 116	75.50 130	73.41 150	76.86 140	87.33 131	90.05 165	89.76 175	96.48 159	90.46 187
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
LTVRE_ROB	81.71 16	82.44 186	81.84 184	83.13 176	89.01 155	92.99 156	88.90 165	82.32 161	66.26 213	54.02 214	74.68 142	59.62 211	88.87 118	90.71 153	92.02 127	95.68 175	96.62 97
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
CMPMVS	61.19 17	79.86 196	77.46 204	82.66 185	91.54 131	91.82 185	83.25 197	81.57 169	70.51 209	68.64 170	59.89 204	66.77 177	79.63 184	84.00 203	84.30 199	91.34 205	84.89 208
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PMVS	56.77 18	61.27 211	58.64 214	64.35 210	75.66 213	54.60 221	53.62 221	74.23 197	53.69 218	58.37 207	44.27 217	49.38 219	44.16 218	69.51 216	65.35 216	80.07 217	73.66 216
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.81 19	39.52 216	41.58 217	37.11 217	33.93 224	49.06 222	26.45 226	54.22 218	29.46 222	24.15 223	20.77 221	10.60 229	34.42 219	51.12 219	65.27 217	49.49 224	64.81 219
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_re		87.31 124	86.10 139	88.74 113	89.84 147	94.28 122	92.66 108	89.41 78	82.61 157	74.69 132	74.69 141	69.47 163	87.78 124	92.38 124	93.23 98	98.03 81	96.02 122

TPM-MVS					98.33 29	97.85 53	97.06 36			89.97 40	93.26 31	97.16 25	93.12 64			97.79 96	95.95 124

FA-MVS(training)		90.79 87	91.33 81	90.17 99	93.76 98	97.22 73	92.74 107	77.79 188	90.60 75	88.03 54	78.80 116	87.41 74	91.00 87	95.40 62	93.43 93	97.70 106	96.46 103

test2506		90.93 84	89.20 103	92.95 63	94.97 75	98.30 39	94.53 66	90.25 64	89.91 90	88.39 53	83.23 88	64.17 192	90.69 91	96.75 32	96.10 44	98.87 8	95.97 123

test1111		90.47 93	89.10 105	92.07 75	94.92 77	98.30 39	94.17 79	90.30 63	89.56 97	83.92 94	73.25 152	73.66 147	90.26 97	96.77 30	96.14 42	98.87 8	96.04 120

ECVR-MVS		90.77 88	89.27 101	92.52 68	94.97 75	98.30 39	94.53 66	90.25 64	89.91 90	85.80 78	73.64 145	74.31 146	90.69 91	96.75 32	96.10 44	98.87 8	95.91 127

DVP-MVS++		98.07 1	98.46 1	97.62 1	99.08 3	99.29 2	98.84 3	96.63 4	97.89 1	95.35 3	97.83 4	99.48 3	96.98 9	97.99 2	97.14 11	98.82 11	99.60 1

GeoE		89.29 110	88.68 109	89.99 102	92.75 117	96.03 103	93.07 105	83.79 143	86.98 118	81.34 104	74.72 140	78.92 123	91.22 83	93.31 110	93.21 101	97.78 98	97.60 69

test_method		58.10 213	64.61 213	50.51 213	28.26 225	41.71 224	61.28 219	32.07 220	75.92 196	52.04 216	47.94 214	61.83 201	51.80 215	79.83 210	63.95 218	77.60 219	81.05 212

pmnet_mix02		80.14 195	80.21 196	80.06 194	86.61 194	89.66 201	80.40 205	82.20 163	82.29 160	61.35 201	71.52 157	66.67 178	76.75 193	82.55 206	80.18 209	93.05 195	88.62 197

RE-MVS-def										60.19 203

SED-MVS		97.98 2	98.36 2	97.54 4	98.94 16	99.29 2	98.81 4	96.64 3	97.14 3	95.16 4	97.96 2	99.61 2	96.92 12	98.00 1	97.24 8	98.75 17	99.25 3

SF-MVS		97.20 12	97.29 14	97.10 9	98.95 15	98.51 29	97.51 29	96.48 7	96.17 16	94.64 6	97.32 6	97.57 19	96.23 26	96.78 29	96.15 41	98.79 14	98.55 27

9.14												97.28 23

uanet_test		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

ET-MVSNet_ETH3D		89.93 99	90.84 88	88.87 111	79.60 212	96.19 99	94.43 68	86.56 114	90.63 72	80.75 111	90.71 44	77.78 133	93.73 56	91.36 141	93.45 92	98.15 69	95.77 129

UniMVSNet_ETH3D		84.57 155	81.40 189	88.28 118	89.34 154	94.38 121	90.33 134	86.50 115	74.74 200	77.52 123	59.90 203	62.04 200	88.78 120	88.82 181	92.65 114	97.22 125	97.24 80

EIA-MVS		92.72 59	92.96 58	92.44 70	93.86 95	97.76 57	93.13 102	88.65 89	89.78 94	86.68 67	86.69 63	87.57 73	93.74 55	96.07 51	95.32 56	98.58 23	97.53 70

ETV-MVS		93.80 51	94.57 44	92.91 65	93.98 88	97.50 65	93.62 93	88.70 87	91.95 60	87.57 60	90.21 47	90.79 62	94.56 42	97.20 19	96.35 31	99.02 1	97.98 51

CS-MVS		94.53 44	94.73 42	94.31 42	96.30 60	98.53 26	94.98 61	89.24 82	93.37 48	90.24 39	88.96 54	89.76 71	96.09 28	97.48 13	96.42 26	98.99 2	98.59 21

DVP-MVS		97.93 3	98.23 3	97.58 3	99.05 6	99.31 1	98.64 6	96.62 5	97.56 2	95.08 5	96.61 13	99.64 1	97.32 1	97.91 4	97.31 6	98.77 15	99.26 2
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
SR-MVS					98.93 18			96.00 16				97.75 15

DPM-MVS		95.07 35	94.84 40	95.34 34	97.44 43	97.49 66	97.76 26	95.52 24	94.88 34	88.92 47	87.25 59	96.44 30	94.41 43	95.78 55	96.11 43	97.99 86	95.95 124

thisisatest0530		91.04 82	91.74 75	90.21 96	92.93 113	97.00 81	92.06 121	87.63 108	90.74 69	81.51 102	86.81 61	82.48 102	89.23 109	94.81 76	93.03 109	97.90 91	97.33 78

Anonymous202405211			88.00 117		93.16 107	96.38 97	93.58 94	89.34 79	87.92 112		65.04 189	83.03 97	92.07 75	92.67 117	93.33 95	96.96 142	97.63 65

DCV-MVSNet		91.24 78	91.26 82	91.22 89	92.84 114	93.44 141	93.82 87	86.75 113	91.33 68	85.61 82	84.00 83	85.46 86	91.27 82	92.91 114	93.62 85	97.02 138	98.05 50

tttt0517		91.01 83	91.71 76	90.19 98	92.98 109	97.07 80	91.96 124	87.63 108	90.61 74	81.42 103	86.76 62	82.26 106	89.23 109	94.86 74	93.03 109	97.90 91	97.36 76

our_test_3					86.93 189	89.77 200	81.61 202

thisisatest0515		85.70 141	87.00 131	84.19 164	88.16 167	93.67 136	84.20 196	84.14 139	83.39 153	72.91 141	76.79 127	74.75 145	78.82 188	92.57 121	91.26 141	96.94 144	96.56 102

SMA-MVS		97.53 7	97.93 7	97.07 10	99.21 1	99.02 8	98.08 19	96.25 11	96.36 12	93.57 15	96.56 14	99.27 5	96.78 16	97.91 4	97.43 3	98.51 26	98.94 12
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
DPE-MVS		97.83 4	98.13 4	97.48 5	98.83 22	99.19 4	98.99 1	96.70 1	96.05 18	94.39 9	98.30 1	99.47 4	97.02 6	97.75 7	97.02 14	98.98 3	99.10 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
thres100view900		89.36 108	87.61 125	91.39 85	93.90 93	96.86 86	94.35 71	89.66 75	85.87 128	81.15 106	76.46 130	70.38 158	91.17 84	94.09 92	93.43 93	98.13 71	96.16 115

tfpnnormal		83.80 169	81.26 191	86.77 136	89.60 151	93.26 149	89.72 153	87.60 110	72.78 202	70.44 157	60.53 202	61.15 204	85.55 148	92.72 116	91.44 138	97.71 104	96.92 91

tfpn200view9		89.55 105	87.86 120	91.53 82	93.90 93	97.26 70	94.31 74	89.74 71	85.87 128	81.15 106	76.46 130	70.38 158	91.76 79	94.92 70	93.51 87	98.28 57	96.61 98

CHOSEN 280x420		90.77 88	92.14 70	89.17 109	93.86 95	92.81 163	93.16 101	80.22 178	90.21 82	84.67 93	89.89 49	91.38 60	90.57 95	94.94 69	92.11 124	92.52 199	93.65 163

CANet		94.85 38	94.92 39	94.78 37	97.25 47	98.52 28	97.20 32	91.81 48	93.25 49	91.06 31	86.29 66	94.46 44	92.99 65	97.02 24	96.68 20	98.34 48	98.20 41

Fast-Effi-MVS+-dtu		86.25 132	87.70 123	84.56 159	90.37 146	93.70 134	90.54 132	78.14 185	83.50 150	65.37 191	81.59 105	75.83 144	86.09 146	91.70 136	91.70 134	96.88 151	95.84 128

Effi-MVS+-dtu		87.51 122	88.13 116	86.77 136	91.10 136	94.90 112	90.91 129	82.67 155	83.47 151	71.55 148	81.11 107	77.04 138	89.41 104	92.65 119	91.68 136	95.00 189	96.09 118

CANet_DTU		90.74 90	92.93 59	88.19 119	94.36 81	96.61 88	94.34 72	84.66 131	90.66 71	68.75 169	90.41 46	86.89 77	89.78 100	95.46 60	94.87 64	97.25 124	95.62 132

MVS_0304		94.30 47	94.68 43	93.86 50	96.33 59	98.48 30	97.41 30	91.20 53	92.75 53	86.96 65	86.03 69	93.81 47	92.64 70	96.89 27	96.54 25	98.61 22	98.24 39

MSP-MVS		97.70 6	98.09 5	97.24 6	99.00 11	99.17 5	98.76 5	96.41 9	96.91 5	93.88 14	97.72 5	99.04 7	96.93 11	97.29 17	97.31 6	98.45 37	99.23 4
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
IterMVS-SCA-FT		85.44 147	86.71 132	83.97 168	90.59 144	90.84 196	89.73 152	78.34 184	84.07 148	66.40 185	77.27 126	78.66 125	83.06 166	91.20 143	90.10 167	95.72 173	94.78 147

TSAR-MVS + MP.		97.31 9	97.64 9	96.92 13	97.28 46	98.56 23	98.61 7	95.48 28	96.72 8	94.03 13	96.73 12	98.29 9	97.15 4	97.61 12	96.42 26	98.96 6	99.13 7
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
OPM-MVS		91.08 80	89.34 100	93.11 61	96.18 61	96.13 101	96.39 43	92.39 43	82.97 155	81.74 101	82.55 98	80.20 118	93.97 52	94.62 80	93.23 98	98.00 85	95.73 130
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMMP_NAP		96.93 16	97.27 15	96.53 23	99.06 5	98.95 9	98.24 13	96.06 15	95.66 21	90.96 32	95.63 24	97.71 16	96.53 20	97.66 10	96.68 20	98.30 54	98.61 20

ambc			67.96 211		73.69 215	79.79 216	73.82 213		71.61 204	59.80 205	46.00 215	20.79 225	66.15 209	86.92 191	80.11 210	89.13 214	90.50 186

CS-MVS-test		94.63 43	95.28 36	93.88 49	96.56 56	98.67 13	93.41 98	89.31 80	94.27 41	89.64 42	90.84 43	91.64 57	95.58 33	97.04 23	96.17 39	98.77 15	98.32 36

Effi-MVS+		89.79 102	89.83 98	89.74 103	92.98 109	96.45 95	93.48 97	84.24 136	87.62 114	76.45 127	81.76 102	77.56 136	93.48 59	94.61 81	93.59 86	97.82 95	97.22 83

new-patchmatchnet		72.32 206	71.09 209	73.74 205	81.17 211	84.86 213	72.21 215	77.48 189	68.32 211	54.89 212	55.10 209	49.31 220	63.68 211	79.30 211	76.46 212	93.03 196	84.32 210

pmmvs6		80.90 192	78.77 198	83.38 175	85.84 198	91.61 188	86.01 189	82.54 157	64.17 214	70.43 158	54.14 212	67.06 175	80.73 182	90.50 157	89.17 181	94.74 190	94.75 148

pmmvs5		83.37 174	82.68 175	84.18 165	87.13 186	93.18 151	86.74 183	82.08 164	76.48 191	67.28 180	71.26 158	62.70 196	84.71 155	90.77 150	90.12 165	97.15 129	94.24 154

Fast-Effi-MVS+		88.56 115	87.99 118	89.22 108	91.56 130	95.21 108	92.29 114	82.69 154	86.82 119	77.73 122	76.24 133	73.39 148	93.36 61	94.22 90	93.64 84	97.65 111	96.43 105

Anonymous20231211		89.82 101	88.18 115	91.74 78	92.52 120	96.09 102	93.38 99	89.30 81	88.95 103	85.90 76	64.55 193	84.39 90	92.41 73	92.24 128	93.06 107	96.93 147	97.95 53

pmmvs-eth3d		79.78 197	77.58 202	82.34 188	81.57 210	87.46 208	82.92 198	81.28 172	75.33 199	71.34 150	61.88 197	52.41 216	81.59 179	87.56 186	86.90 188	95.36 184	91.48 177

GG-mvs-BLEND		62.84 210	90.21 92	30.91 218	0.57 227	94.45 117	86.99 181	0.34 224	88.71 105	0.98 227	81.55 106	91.58 58	0.86 224	92.66 118	91.43 139	95.73 172	91.11 182

Anonymous20231206		78.09 200	78.11 201	78.07 200	85.19 203	89.17 202	80.99 203	81.24 174	75.46 198	58.25 208	54.78 211	59.90 210	66.73 208	88.94 180	88.26 184	96.01 167	90.25 189

MTAPA										95.36 2		97.46 21

MTMP										95.70 1		96.90 27

gm-plane-assit		77.65 201	78.50 199	76.66 201	87.96 169	85.43 212	64.70 218	74.50 196	64.15 215	51.26 217	61.32 200	58.17 213	84.11 162	95.16 65	93.83 81	97.45 119	91.41 178

train_agg		96.15 25	96.64 25	95.58 33	98.44 27	98.03 48	98.14 18	95.40 31	93.90 45	87.72 59	96.26 17	98.10 10	95.75 31	96.25 47	95.45 55	98.01 84	98.47 31

gg-mvs-nofinetune		81.83 189	83.58 162	79.80 196	91.57 129	96.54 91	93.79 88	68.80 212	62.71 216	43.01 222	55.28 208	85.06 88	83.65 164	96.13 49	94.86 65	97.98 89	94.46 151

SCA		86.25 132	87.52 128	84.77 155	91.59 128	93.90 128	89.11 161	73.25 205	90.38 79	72.84 142	83.26 87	83.79 93	88.49 121	86.07 195	85.56 193	93.33 192	89.67 193

MS-PatchMatch		87.63 120	87.61 125	87.65 127	93.95 90	94.09 125	92.60 110	81.52 170	86.64 121	76.41 128	73.46 149	85.94 83	85.01 154	92.23 129	90.00 169	96.43 162	90.93 184

Patchmatch-RL test							18.47 227

tmp_tt				50.24 214	68.55 218	46.86 223	48.90 223	18.28 221	86.51 125	68.32 172	70.19 165	65.33 183	26.69 221	74.37 213	66.80 215	70.72 221

canonicalmvs		93.08 55	93.09 55	93.07 62	94.24 82	97.86 52	95.45 57	87.86 103	94.00 44	87.47 61	88.32 56	82.37 105	95.13 38	93.96 98	96.41 29	98.27 58	98.73 13

anonymousdsp		84.51 157	85.85 147	82.95 181	86.30 197	93.51 140	85.77 191	80.38 177	78.25 182	63.42 197	73.51 148	72.20 151	84.64 156	93.21 113	92.16 123	97.19 127	98.14 45

v144192		83.48 173	82.23 178	84.94 153	86.65 192	92.84 160	89.63 155	82.48 158	77.87 183	67.36 179	65.33 187	63.50 193	86.51 138	89.72 169	89.99 170	97.03 137	96.35 108

v1921920		83.30 175	82.09 181	84.70 156	86.59 195	92.67 166	89.82 151	82.23 162	78.32 180	65.76 188	64.64 192	62.35 197	86.78 137	90.34 158	90.02 168	97.02 138	96.31 111

FC-MVSNet-train		90.55 91	90.19 93	90.97 91	93.78 97	95.16 109	92.11 120	88.85 84	87.64 113	83.38 97	84.36 81	78.41 128	89.53 102	94.69 78	93.15 104	98.15 69	97.92 56

UA-Net		90.81 85	92.58 62	88.74 113	94.87 79	97.44 67	92.61 109	88.22 93	82.35 159	78.93 119	85.20 76	95.61 38	79.56 185	96.52 38	96.57 24	98.23 63	94.37 153

v1192		83.56 172	82.35 177	84.98 152	86.84 191	92.84 160	90.01 145	82.70 153	78.54 179	66.48 183	64.88 190	62.91 194	86.91 135	90.72 152	90.25 160	96.94 144	96.32 110

FC-MVSNet-test		86.15 135	89.10 105	82.71 184	89.83 148	93.18 151	87.88 174	84.69 130	86.54 123	62.18 200	82.39 99	83.31 95	74.18 200	92.52 122	91.86 131	97.50 117	93.88 160

v1144		84.03 166	82.88 174	85.37 147	87.17 184	93.15 154	90.18 139	83.31 150	78.83 178	67.85 175	65.99 182	64.99 187	86.79 136	90.75 151	90.33 158	96.90 149	96.15 116

sosnet-low-res		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

HFP-MVS		97.11 14	97.19 16	97.00 12	98.97 13	98.73 12	98.37 11	95.69 21	96.60 9	93.28 20	96.87 8	96.64 29	97.27 2	96.64 35	96.33 35	98.44 38	98.56 22

v148		83.61 171	82.10 180	85.37 147	87.34 180	92.94 158	87.48 176	85.72 124	78.92 177	73.87 137	65.71 185	64.69 190	81.78 177	87.82 184	89.35 179	96.01 167	95.26 142

sosnet		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

v7n		82.25 187	81.54 187	83.07 179	85.55 201	92.58 168	86.68 185	81.10 175	76.54 190	65.97 187	62.91 196	60.56 206	82.36 171	91.07 147	90.35 157	96.77 156	96.80 93

DI_MVS_plusplus_trai		91.05 81	90.15 94	92.11 74	92.67 119	96.61 88	96.03 48	88.44 91	90.25 80	85.92 75	73.73 144	84.89 89	91.92 76	94.17 91	94.07 78	97.68 109	97.31 79

HPM-MVS++		97.22 11	97.40 12	97.01 11	99.08 3	98.55 24	98.19 14	96.48 7	96.02 19	93.28 20	96.26 17	98.71 8	96.76 17	97.30 16	96.25 37	98.30 54	98.68 15

XVS					95.68 64	98.66 14	94.96 62			88.03 54		96.06 32				98.46 34

v1240		82.88 181	81.66 185	84.29 162	86.46 196	92.52 172	89.06 162	81.82 167	77.16 187	65.09 192	64.17 194	61.50 202	86.36 139	90.12 162	90.13 162	96.95 143	96.04 120

pm-mvs1		84.55 156	83.46 163	85.82 142	88.16 167	93.39 143	89.05 163	85.36 127	74.03 201	72.43 145	65.08 188	71.11 155	82.30 172	93.48 105	91.70 134	97.64 112	95.43 139

X-MVStestdata					95.68 64	98.66 14	94.96 62			88.03 54		96.06 32				98.46 34

X-MVS		96.07 26	96.33 28	95.77 29	98.94 16	98.66 14	97.94 23	95.41 30	95.12 28	88.03 54	93.00 33	96.06 32	95.85 29	96.65 34	96.35 31	98.47 32	98.48 30

v8		84.45 161	83.30 170	85.80 143	87.53 178	92.95 157	90.31 136	82.46 159	80.46 167	71.43 149	66.99 175	67.16 174	86.14 144	89.26 175	90.22 161	96.94 144	96.06 119

v10		84.18 162	83.17 172	85.37 147	87.34 180	92.68 165	90.32 135	81.33 171	79.93 175	69.23 167	66.33 180	65.74 182	87.03 133	90.84 149	90.38 156	96.97 140	96.29 112

v2v482		84.51 157	83.05 173	86.20 141	87.25 182	93.28 147	90.22 138	85.40 126	79.94 174	69.78 162	67.74 172	65.15 186	87.57 127	89.12 177	90.55 154	96.97 140	95.60 133

V42		84.48 159	83.36 169	85.79 144	87.14 185	93.28 147	90.03 143	83.98 141	80.30 169	71.20 152	66.90 177	67.17 173	85.55 148	89.35 172	90.27 159	96.82 154	96.27 113

SD-MVS		97.35 8	97.73 8	96.90 14	97.35 44	98.66 14	97.85 25	96.25 11	96.86 6	94.54 8	96.75 11	99.13 6	96.99 7	96.94 26	96.58 23	98.39 44	99.20 5
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
GA-MVS		85.08 150	85.65 148	84.42 161	89.77 149	94.25 123	89.26 158	84.62 132	81.19 165	62.25 199	75.72 136	68.44 168	84.14 161	93.57 102	91.68 136	96.49 158	94.71 149

MSLP-MVS++		96.05 27	95.63 31	96.55 21	98.33 29	98.17 44	96.94 37	94.61 34	94.70 38	94.37 10	89.20 52	95.96 35	96.81 13	95.57 58	97.33 5	98.24 62	98.47 31

APDe-MVS		97.79 5	97.96 6	97.60 2	99.20 2	99.10 6	98.88 2	96.68 2	96.81 7	94.64 6	97.84 3	98.02 11	97.24 3	97.74 8	97.02 14	98.97 5	99.16 6

TSAR-MVS + COLMAP		92.39 63	92.31 68	92.47 69	95.35 74	96.46 94	96.13 46	92.04 47	95.33 26	80.11 114	94.95 29	77.35 137	94.05 49	94.49 86	93.08 105	97.15 129	94.53 150

CVMVSNet		83.83 168	85.53 149	81.85 191	89.60 151	90.92 194	87.81 175	83.21 151	80.11 171	60.16 204	76.47 129	78.57 126	76.79 192	89.76 167	90.13 162	93.51 191	92.75 173

TSAR-MVS + ACMM		96.19 23	97.39 13	94.78 37	97.70 40	98.41 35	97.72 27	95.49 27	96.47 11	86.66 68	96.35 15	97.85 13	93.99 50	97.19 20	96.37 30	97.12 132	99.13 7

pmmvs4		86.00 139	84.28 158	88.00 121	87.80 171	92.01 182	89.94 147	84.91 129	86.79 120	80.98 109	73.41 150	66.34 180	88.12 122	89.31 174	88.90 183	96.24 165	93.20 169

EU-MVSNet		78.43 198	80.25 195	76.30 202	83.81 206	87.27 210	80.99 203	79.52 180	76.01 194	54.12 213	70.44 163	64.87 188	67.40 207	86.23 194	85.54 194	91.95 204	91.41 178

test-LLR		86.88 127	88.28 112	85.24 150	91.22 133	92.07 179	87.41 177	83.62 145	84.58 137	69.33 165	83.00 89	82.79 98	84.24 158	92.26 126	89.81 172	95.64 176	93.44 164

TESTMET0.1,1		86.11 137	88.28 112	83.59 171	87.80 171	92.07 179	87.41 177	77.12 190	84.58 137	69.33 165	83.00 89	82.79 98	84.24 158	92.26 126	89.81 172	95.64 176	93.44 164

test-mter		86.09 138	88.38 111	83.43 174	87.89 170	92.61 167	86.89 182	77.11 191	84.30 142	68.62 171	82.57 97	82.45 103	84.34 157	92.40 123	90.11 166	95.74 171	94.21 156

ACMMPR		96.92 17	96.96 19	96.87 15	98.99 12	98.78 11	98.38 10	95.52 24	96.57 10	92.81 24	96.06 20	95.90 36	97.07 5	96.60 37	96.34 34	98.46 34	98.42 33

testgi		81.94 188	84.09 159	79.43 197	89.53 153	90.83 197	82.49 200	81.75 168	80.59 166	59.46 206	82.82 93	65.75 181	67.97 205	90.10 163	89.52 177	95.39 182	89.03 194

test20.03		76.41 203	78.49 200	73.98 204	85.64 200	87.50 207	75.89 210	80.71 176	70.84 208	51.07 218	68.06 171	61.40 203	54.99 214	88.28 182	87.20 187	95.58 179	86.15 204

thres600view7		89.28 111	87.47 130	91.39 85	94.12 84	97.25 71	93.94 84	89.74 71	85.62 133	80.63 112	75.24 139	69.33 164	91.66 81	94.92 70	93.23 98	98.27 58	96.72 95

ADS-MVSNet		84.08 164	84.95 152	83.05 180	91.53 132	91.75 186	88.16 171	70.70 209	89.96 89	69.51 164	78.83 115	76.97 139	86.29 141	84.08 202	84.60 198	92.13 203	88.48 200

MP-MVS		96.56 21	96.72 23	96.37 24	98.93 18	98.48 30	98.04 20	95.55 23	94.32 40	90.95 34	95.88 22	97.02 26	96.29 25	96.77 30	96.01 47	98.47 32	98.56 22
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testmvs		4.35 218	6.54 220	1.79 219	0.60 226	1.82 227	3.06 228	0.95 222	7.22 223	0.88 228	12.38 223	1.25 230	3.87 223	6.09 222	5.58 221	1.40 225	11.42 223

thres400		89.40 107	87.58 127	91.53 82	94.06 87	97.21 74	94.19 78	89.83 69	85.69 130	81.08 108	75.50 137	69.76 162	91.80 77	94.79 77	93.51 87	98.20 66	96.60 99

test123		3.48 219	5.31 221	1.34 220	0.20 228	1.52 228	2.17 229	0.58 223	6.13 224	0.31 229	9.85 224	0.31 231	3.90 222	2.65 223	5.28 222	0.87 226	11.46 222

thres200		89.49 106	87.72 122	91.55 81	93.95 90	97.25 71	94.34 72	89.74 71	85.66 131	81.18 105	76.12 134	70.19 161	91.80 77	94.92 70	93.51 87	98.27 58	96.40 106

test0.0.03 1		85.58 143	87.69 124	83.11 177	91.22 133	92.54 170	85.60 193	83.62 145	85.66 131	67.84 176	82.79 94	79.70 120	73.51 203	91.15 146	90.79 145	96.88 151	91.23 181

pmmvs3		71.13 208	71.06 210	71.21 208	73.54 216	80.19 215	71.69 216	64.86 214	62.04 217	52.10 215	54.92 210	48.00 221	75.03 198	83.75 204	83.24 203	90.04 212	85.27 206

EMVS		39.04 217	34.32 219	44.54 216	58.25 222	39.35 225	27.61 225	62.55 216	35.99 220	16.40 226	20.04 222	14.77 227	44.80 216	33.12 221	44.10 220	57.61 223	52.89 221

E-PMN		40.00 215	35.74 218	44.98 215	57.69 223	39.15 226	28.05 224	62.70 215	35.52 221	17.78 225	20.90 220	14.36 228	44.47 217	35.89 220	47.86 219	59.15 222	56.47 220

PGM-MVS		96.16 24	96.33 28	95.95 26	99.04 7	98.63 19	98.32 12	92.76 42	93.42 47	90.49 37	96.30 16	95.31 41	96.71 18	96.46 40	96.02 46	98.38 45	98.19 42

MCST-MVS		96.83 18	97.06 17	96.57 19	98.88 20	98.47 32	98.02 21	96.16 14	95.58 23	90.96 32	95.78 23	97.84 14	96.46 22	97.00 25	96.17 39	98.94 7	98.55 27

MVS_Test		91.81 72	92.19 69	91.37 87	93.24 105	96.95 83	94.43 68	86.25 117	91.45 67	83.45 96	86.31 65	85.15 87	92.93 66	93.99 94	94.71 67	97.92 90	96.77 94

MDA-MVSNet-bldmvs		73.81 204	72.56 208	75.28 203	72.52 217	88.87 203	74.95 212	82.67 155	71.57 205	55.02 211	65.96 183	42.84 223	76.11 195	70.61 215	81.47 206	90.38 211	86.59 203

CDPH-MVS		94.80 41	95.50 33	93.98 46	98.34 28	98.06 47	97.41 30	93.23 39	92.81 52	82.98 98	92.51 34	94.82 42	93.53 58	96.08 50	96.30 36	98.42 40	97.94 54

casdiffmvs		91.72 74	91.16 85	92.38 72	93.16 107	97.15 76	93.95 82	89.49 77	91.58 66	86.03 72	80.75 109	80.95 114	93.16 62	95.25 63	95.22 60	98.50 29	97.23 81
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
diffmvs		91.37 77	91.09 86	91.70 79	92.71 118	96.47 93	94.03 80	88.78 85	92.74 54	85.43 88	83.63 86	80.37 116	91.76 79	93.39 108	93.78 82	97.50 117	97.23 81
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline2		88.97 112	89.50 99	88.36 116	91.14 135	95.30 107	90.13 142	85.17 128	87.24 115	80.80 110	84.46 80	78.44 127	85.60 147	93.54 104	91.87 130	97.31 122	95.66 131

baseline1		90.81 85	90.29 91	91.42 84	93.67 100	95.86 105	93.94 84	89.69 74	89.29 100	82.85 99	82.91 91	80.30 117	89.60 101	95.05 66	94.79 66	98.80 12	93.82 161

PMMVS2		53.68 214	55.72 216	51.30 212	58.84 221	67.02 219	54.23 220	60.97 217	47.50 219	19.42 224	34.81 218	31.97 224	30.88 220	65.84 217	69.99 213	83.47 216	72.92 217

PM-MVS		80.29 194	79.30 197	81.45 193	81.91 209	88.23 205	82.61 199	79.01 182	79.99 173	67.15 181	69.07 168	51.39 217	82.92 168	87.55 187	85.59 192	95.08 186	93.28 167

PS-CasMVS		82.53 184	81.54 187	83.68 170	87.08 188	92.54 170	86.20 188	83.46 149	76.46 192	65.73 189	65.71 185	59.41 212	81.61 178	89.06 178	90.55 154	98.03 81	97.07 87

UniMVSNet_NR-MVSNet		86.80 128	85.86 146	87.89 125	88.17 166	94.07 126	90.15 140	88.51 90	84.20 145	73.45 139	72.38 156	70.30 160	88.95 115	90.25 159	92.21 121	98.12 72	97.62 67

PEN-MVS		82.49 185	81.58 186	83.56 172	86.93 189	92.05 181	86.71 184	83.84 142	76.94 189	64.68 193	67.24 173	60.11 208	81.17 180	87.78 185	90.70 151	98.02 83	96.21 114

TransMVSNet (Re)		82.67 183	80.93 194	84.69 157	88.71 158	91.50 190	87.90 173	87.15 111	71.54 207	68.24 173	63.69 195	64.67 191	78.51 189	91.65 137	90.73 150	97.64 112	92.73 174

DTE-MVSNet		81.76 190	81.04 192	82.60 186	86.63 193	91.48 192	85.97 190	83.70 144	76.45 193	62.44 198	67.16 174	59.98 209	78.98 187	87.15 189	89.93 171	97.88 93	95.12 144

DU-MVS		86.12 136	84.81 154	87.66 126	87.77 173	93.78 131	90.15 140	87.87 101	84.40 139	73.45 139	70.59 161	64.82 189	88.95 115	90.14 160	92.33 118	97.76 100	97.62 67

UniMVSNet (Re)		86.22 134	85.46 151	87.11 131	88.34 164	94.42 118	89.65 154	87.10 112	84.39 141	74.61 133	70.41 164	68.10 169	85.10 153	91.17 145	91.79 132	97.84 94	97.94 54

CP-MVSNet		83.11 179	82.15 179	84.23 163	87.20 183	92.70 164	86.42 186	83.53 148	77.83 184	67.67 177	66.89 178	60.53 207	82.47 170	89.23 176	90.65 152	98.08 76	97.20 84

WR-MVS_H		82.86 182	82.66 176	83.10 178	87.44 179	93.33 145	85.71 192	83.20 152	77.36 186	68.20 174	66.37 179	65.23 185	76.05 196	89.35 172	90.13 162	97.99 86	96.89 92

WR-MVS		83.14 177	83.38 168	82.87 182	87.55 177	93.29 146	86.36 187	84.21 137	80.05 172	66.41 184	66.91 176	66.92 176	75.66 197	88.96 179	90.56 153	97.05 136	96.96 89

NR-MVSNet		85.46 146	84.54 156	86.52 139	88.33 165	93.78 131	90.45 133	87.87 101	84.40 139	71.61 147	70.59 161	62.09 199	82.79 169	91.75 135	91.75 133	98.10 75	97.44 73

Baseline_NR-MVSNet		85.28 148	83.42 166	87.46 130	87.77 173	90.80 198	89.90 150	87.69 105	83.93 149	74.16 135	64.72 191	66.43 179	87.48 130	90.14 160	90.83 144	97.73 103	97.11 86

TranMVSNet+NR-MVSNet		85.57 144	84.41 157	86.92 133	87.67 176	93.34 144	90.31 136	88.43 92	83.07 154	70.11 160	69.99 167	65.28 184	86.96 134	89.73 168	92.27 119	98.06 79	97.17 85

TSAR-MVS + GP.		95.86 28	96.95 21	94.60 41	94.07 86	98.11 46	96.30 44	91.76 49	95.67 20	91.07 30	96.82 10	97.69 17	95.71 32	95.96 52	95.75 50	98.68 18	98.63 17

mPP-MVS					98.76 23							95.49 39

SixPastTwentyTwo		83.12 178	83.44 165	82.74 183	87.71 175	93.11 155	82.30 201	82.33 160	79.24 176	64.33 194	78.77 117	62.75 195	84.11 162	88.11 183	87.89 185	95.70 174	94.21 156

casdiffmvs_mvg		91.94 68	91.25 83	92.75 67	93.41 104	97.19 75	95.48 56	89.77 70	89.86 92	86.41 70	81.02 108	82.23 107	92.93 66	95.44 61	95.61 52	98.51 26	97.40 75
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LGP-MVS_train		91.83 71	92.04 72	91.58 80	95.46 70	96.18 100	95.97 50	89.85 68	90.45 77	77.76 121	91.92 38	80.07 119	92.34 74	94.27 88	93.47 91	98.11 74	97.90 59

baseline		91.19 79	91.89 74	90.38 92	92.76 115	95.04 111	93.55 95	84.54 134	92.92 50	85.71 80	86.68 64	86.96 76	89.28 108	92.00 132	92.62 115	96.46 160	96.99 88

EPNet_dtu		88.32 117	90.61 89	85.64 146	96.79 54	92.27 175	92.03 122	90.31 62	89.05 102	65.44 190	89.43 50	85.90 84	74.22 199	92.76 115	92.09 125	95.02 188	92.76 172
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CHOSEN 1792x2688		88.57 114	87.82 121	89.44 106	95.46 70	96.89 85	93.74 90	85.87 120	89.63 95	77.42 124	61.38 199	83.31 95	88.80 119	93.44 107	93.16 103	95.37 183	96.95 90

EPNet		93.92 50	94.40 46	93.36 54	97.89 35	96.55 90	96.08 47	92.14 45	91.65 64	89.16 45	94.07 30	90.17 70	87.78 124	95.24 64	94.97 63	97.09 134	98.15 44
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
APD-MVS		97.12 13	97.05 18	97.19 7	99.04 7	98.63 19	98.45 8	96.54 6	94.81 36	93.50 16	96.10 19	97.40 22	96.81 13	97.05 22	96.82 19	98.80 12	98.56 22
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		97.30 10	97.41 11	97.18 8	99.02 10	98.60 21	98.15 16	96.24 13	96.12 17	94.10 11	95.54 25	97.99 12	96.99 7	97.97 3	97.17 9	98.57 24	98.50 29

NCCC		96.75 19	96.67 24	96.85 16	99.03 9	98.44 34	98.15 16	96.28 10	96.32 13	92.39 25	92.16 35	97.55 20	96.68 19	97.32 14	96.65 22	98.55 25	98.26 38

CP-MVS		96.68 20	96.59 26	96.77 17	98.85 21	98.58 22	98.18 15	95.51 26	95.34 25	92.94 23	95.21 28	96.25 31	96.79 15	96.44 42	95.77 49	98.35 46	98.56 22

NP-MVS									91.63 65

EG-PatchMatch MVS		81.70 191	81.31 190	82.15 189	88.75 157	93.81 130	87.14 180	78.89 183	71.57 205	64.12 196	61.20 201	68.46 167	76.73 194	91.48 138	90.77 147	97.28 123	91.90 175

tpm cat1		84.13 163	81.99 183	86.63 138	91.74 126	91.50 190	90.68 130	75.69 194	86.12 127	85.44 87	72.39 155	70.72 156	85.16 152	80.89 209	81.56 205	91.07 207	90.71 185

SteuartSystems-ACMMP		97.10 15	97.49 10	96.65 18	98.97 13	98.95 9	98.43 9	95.96 17	95.12 28	91.46 28	96.85 9	97.60 18	96.37 24	97.76 6	97.16 10	98.68 18	98.97 11
Skip Steuart: Steuart Systems R&D Blog.
CostFormer		86.78 129	86.05 140	87.62 129	92.15 122	93.20 150	91.55 127	75.83 193	88.11 111	85.29 89	81.76 102	76.22 142	87.80 123	84.45 200	85.21 196	93.12 194	93.42 166

CR-MVSNet		85.48 145	86.29 137	84.53 160	91.08 138	92.10 177	89.18 159	73.30 203	84.75 135	71.08 153	73.12 154	77.91 132	86.27 142	91.48 138	90.75 148	96.27 164	93.94 158

Patchmtry						92.39 174	89.18 159	73.30 203		71.08 153

PatchT		83.86 167	85.51 150	81.94 190	88.41 163	91.56 189	78.79 208	71.57 207	84.08 147	71.08 153	70.62 160	76.13 143	86.27 142	91.48 138	90.75 148	95.52 181	93.94 158

tpmrst		83.72 170	83.45 164	84.03 167	92.21 121	91.66 187	88.74 167	73.58 202	88.14 110	72.67 143	77.37 124	72.11 152	86.34 140	82.94 205	82.05 204	90.63 209	89.86 192

tpm		83.16 176	83.64 161	82.60 186	90.75 140	91.05 193	88.49 169	73.99 198	82.36 158	67.08 182	78.10 120	68.79 165	84.17 160	85.95 196	85.96 191	91.09 206	93.23 168

DELS-MVS		93.71 52	93.47 52	94.00 44	96.82 53	98.39 36	96.80 39	91.07 56	89.51 98	89.94 41	83.80 84	89.29 72	90.95 88	97.32 14	97.65 2	98.42 40	98.32 36
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
RPMNet		84.82 154	85.90 145	83.56 172	91.10 136	92.10 177	88.73 168	71.11 208	84.75 135	68.79 168	73.56 146	77.62 135	85.33 151	90.08 164	89.43 178	96.32 163	93.77 162

MVSTER		91.73 73	91.61 78	91.86 77	93.18 106	94.56 113	94.37 70	87.90 99	90.16 85	88.69 51	89.23 51	81.28 113	88.92 117	95.75 56	93.95 80	98.12 72	96.37 107

CPTT-MVS		95.54 31	95.07 37	96.10 25	97.88 36	97.98 50	97.92 24	94.86 32	94.56 39	92.16 26	91.01 41	95.71 37	96.97 10	94.56 83	93.50 90	96.81 155	98.14 45

GBi-Net		90.21 96	90.11 95	90.32 94	88.66 160	93.65 137	94.25 75	85.78 121	90.03 86	85.56 83	77.38 121	86.13 80	89.38 105	93.97 95	94.16 74	98.31 51	95.47 136

PVSNet_Blended_VisFu		91.92 69	92.39 67	91.36 88	95.45 72	97.85 53	92.25 115	89.54 76	88.53 108	87.47 61	79.82 112	90.53 66	85.47 150	96.31 46	95.16 61	97.99 86	98.56 22

PVSNet_BlendedMVS		92.80 57	92.44 65	93.23 55	96.02 62	97.83 55	93.74 90	90.58 59	91.86 61	90.69 35	85.87 72	82.04 108	90.01 98	96.39 43	95.26 58	98.34 48	97.81 61

PVSNet_Blended		92.80 57	92.44 65	93.23 55	96.02 62	97.83 55	93.74 90	90.58 59	91.86 61	90.69 35	85.87 72	82.04 108	90.01 98	96.39 43	95.26 58	98.34 48	97.81 61

FMVSNet5		84.47 160	84.72 155	84.18 165	83.30 207	88.43 204	88.09 172	79.42 181	84.25 143	74.14 136	73.15 153	78.74 124	83.65 164	91.19 144	91.19 142	96.46 160	86.07 205

test1		90.21 96	90.11 95	90.32 94	88.66 160	93.65 137	94.25 75	85.78 121	90.03 86	85.56 83	77.38 121	86.13 80	89.38 105	93.97 95	94.16 74	98.31 51	95.47 136

new_pmnet		72.29 207	73.25 207	71.16 209	75.35 214	81.38 214	73.72 214	69.27 211	75.97 195	49.84 219	56.27 206	56.12 215	69.08 204	81.73 208	80.86 207	89.72 213	80.44 213

FMVSNet3		90.19 98	90.06 97	90.34 93	88.69 159	93.85 129	94.58 65	85.78 121	90.03 86	85.56 83	77.38 121	86.13 80	89.22 111	93.29 111	94.36 71	98.20 66	95.40 140

dps		85.00 151	83.21 171	87.08 132	90.73 141	92.55 169	89.34 156	75.29 195	84.94 134	87.01 64	79.27 114	67.69 172	87.27 132	84.22 201	83.56 201	92.83 197	90.25 189

FMVSNet2		89.61 104	89.14 104	90.16 100	88.66 160	93.65 137	94.25 75	85.44 125	88.57 107	84.96 92	73.53 147	83.82 92	89.38 105	94.23 89	94.68 68	98.31 51	95.47 136

FMVSNet1		87.33 123	86.00 143	88.89 110	87.13 186	92.83 162	93.08 104	84.46 135	81.35 164	82.20 100	66.33 180	77.96 131	88.96 114	93.97 95	94.16 74	97.54 116	95.38 141

N_pmnet		77.55 202	76.68 205	78.56 199	85.43 202	87.30 209	78.84 207	81.88 166	78.30 181	60.61 202	61.46 198	62.15 198	74.03 202	82.04 207	80.69 208	90.59 210	84.81 209

UGNet		91.52 76	93.41 53	89.32 107	94.13 83	97.15 76	91.83 125	89.01 83	90.62 73	85.86 77	86.83 60	91.73 56	77.40 190	94.68 79	94.43 69	97.71 104	98.40 35
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
EC-MVSNet		94.19 48	95.05 38	93.18 58	93.56 102	97.65 62	95.34 58	86.37 116	92.05 59	88.71 50	89.91 48	93.32 48	96.14 27	97.29 17	96.42 26	98.98 3	98.70 14

MDTV_nov1_ep13_2view		80.43 193	80.94 193	79.84 195	84.82 204	90.87 195	84.23 195	73.80 199	80.28 170	64.33 194	70.05 166	68.77 166	79.67 183	84.83 199	83.50 202	92.17 201	88.25 202

MDTV_nov1_ep13		86.64 131	87.50 129	85.65 145	90.73 141	93.69 135	89.96 146	78.03 187	89.48 99	76.85 126	84.92 77	82.42 104	86.14 144	86.85 192	86.15 189	92.17 201	88.97 196

MIMVSNet1		73.19 205	73.70 206	72.60 207	65.42 220	86.69 211	75.56 211	79.65 179	67.87 212	55.30 210	45.24 216	56.41 214	63.79 210	86.98 190	87.66 186	95.85 169	85.04 207

MIMVSNet		82.97 180	84.00 160	81.77 192	82.23 208	92.25 176	87.40 179	72.73 206	81.48 163	69.55 163	68.79 169	72.42 150	81.82 176	92.23 129	92.25 120	96.89 150	88.61 198

IterMVS-LS		88.60 113	88.45 110	88.78 112	92.02 124	92.44 173	92.00 123	83.57 147	86.52 124	78.90 120	78.61 118	81.34 112	89.12 112	90.68 154	93.18 102	97.10 133	96.35 108
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		88.34 116	88.71 108	87.90 124	90.70 143	94.54 114	92.38 111	86.02 118	80.37 168	79.42 117	79.30 113	83.43 94	82.04 173	93.39 108	94.01 79	96.86 153	95.93 126
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS		85.25 149	86.49 135	83.80 169	90.42 145	90.77 199	90.02 144	78.04 186	84.10 146	66.27 186	77.28 125	78.41 128	83.01 167	90.88 148	89.72 176	95.04 187	94.24 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MVS_111021_LR		94.84 39	95.57 32	94.00 44	97.11 49	97.72 61	94.88 64	91.16 55	95.24 27	88.74 49	96.03 21	91.52 59	94.33 47	95.96 52	95.01 62	97.79 96	97.49 72

HQP-MVS		92.39 63	92.49 64	92.29 73	95.65 66	95.94 104	95.64 54	92.12 46	92.46 57	79.65 116	91.97 37	82.68 101	92.92 68	93.47 106	92.77 112	97.74 102	98.12 47

QAPM		94.13 49	94.33 49	93.90 47	97.82 37	98.37 37	96.47 42	90.89 58	92.73 55	85.63 81	85.35 74	93.87 45	94.17 48	95.71 57	95.90 48	98.40 42	98.42 33

Vis-MVSNet		89.36 108	91.49 80	86.88 134	92.10 123	97.60 64	92.16 119	85.89 119	84.21 144	75.20 131	82.58 96	87.13 75	77.40 190	95.90 54	95.63 51	98.51 26	97.36 76
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MVS-HIRNet		78.16 199	77.57 203	78.83 198	85.83 199	87.76 206	76.67 209	70.22 210	75.82 197	67.39 178	55.61 207	70.52 157	81.96 175	86.67 193	85.06 197	90.93 208	81.58 211

HyFIR lowres test		87.87 119	86.42 136	89.57 104	95.56 67	96.99 82	92.37 112	84.15 138	86.64 121	77.17 125	57.65 205	83.97 91	91.08 86	92.09 131	92.44 117	97.09 134	95.16 143

EPMVS		85.77 140	86.24 138	85.23 151	92.76 115	93.78 131	89.91 148	73.60 201	90.19 83	74.22 134	82.18 100	78.06 130	87.55 128	85.61 197	85.38 195	93.32 193	88.48 200

TAMVS		84.94 153	84.95 152	84.93 154	88.82 156	93.18 151	88.44 170	81.28 172	77.16 187	73.76 138	75.43 138	76.57 141	82.04 173	90.59 155	90.79 145	95.22 185	90.94 183

IS_MVSNet		91.87 70	93.35 54	90.14 101	94.09 85	97.73 59	93.09 103	88.12 95	88.71 105	79.98 115	84.49 79	90.63 65	87.49 129	97.07 21	96.96 16	98.07 77	97.88 60

RPSCF		89.68 103	89.24 102	90.20 97	92.97 111	92.93 159	92.30 113	87.69 105	90.44 78	85.12 90	91.68 39	85.84 85	90.69 91	87.34 188	86.07 190	92.46 200	90.37 188

Vis-MVSNet (Re-imp)		90.54 92	92.76 60	87.94 123	93.73 99	96.94 84	92.17 118	87.91 98	88.77 104	76.12 129	83.68 85	90.80 61	79.49 186	96.34 45	96.35 31	98.21 65	96.46 103

MVS_111021_HR		94.84 39	95.91 30	93.60 52	97.35 44	98.46 33	95.08 60	91.19 54	94.18 42	85.97 73	95.38 26	92.56 52	93.61 57	96.61 36	96.25 37	98.40 42	97.92 56

CSCG		95.68 30	95.46 35	95.93 27	98.71 24	99.07 7	97.13 35	93.55 37	95.48 24	93.35 19	90.61 45	93.82 46	95.16 37	94.60 82	95.57 53	97.70 106	99.08 10

PatchMatch-RL		90.30 95	88.93 107	91.89 76	95.41 73	95.68 106	90.94 128	88.67 88	89.80 93	86.95 66	85.90 70	72.51 149	92.46 71	93.56 103	92.18 122	96.93 147	92.89 171

TDRefinement		84.97 152	83.39 167	86.81 135	92.97 111	94.12 124	92.18 116	87.77 104	82.78 156	71.31 151	68.43 170	68.07 170	81.10 181	89.70 170	89.03 182	95.55 180	91.62 176

USDC		86.73 130	85.96 144	87.63 128	91.64 127	93.97 127	92.76 106	84.58 133	88.19 109	70.67 156	80.10 111	67.86 171	89.43 103	91.81 134	89.77 174	96.69 157	90.05 191

EPP-MVSNet		92.13 65	93.06 56	91.05 90	93.66 101	97.30 69	92.18 116	87.90 99	90.24 81	83.63 95	86.14 68	90.52 68	90.76 90	94.82 75	94.38 70	98.18 68	97.98 51

PMMVS		89.88 100	91.19 84	88.35 117	89.73 150	91.97 183	90.62 131	81.92 165	90.57 76	80.58 113	92.16 35	86.85 78	91.17 84	92.31 125	91.35 140	96.11 166	93.11 170

ACMMP		95.54 31	95.49 34	95.61 32	98.27 31	98.53 26	97.16 34	94.86 32	94.88 34	89.34 43	95.36 27	91.74 55	95.50 35	95.51 59	94.16 74	98.50 29	98.22 40
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
CNLPA		93.69 53	92.50 63	95.06 36	97.11 49	97.36 68	93.88 86	93.30 38	95.64 22	93.44 18	80.32 110	90.73 64	94.99 39	93.58 101	93.33 95	97.67 110	96.57 101

PatchmatchNet		85.70 141	86.65 133	84.60 158	91.79 125	93.40 142	89.27 157	73.62 200	90.19 83	72.63 144	82.74 95	81.93 110	87.64 126	84.99 198	84.29 200	92.64 198	89.00 195
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PHI-MVS		95.86 28	96.93 22	94.61 40	97.60 42	98.65 18	96.49 41	93.13 40	94.07 43	87.91 58	97.12 7	97.17 24	93.90 53	96.46 40	96.93 17	98.64 20	98.10 49

OMC-MVS		94.49 45	94.36 47	94.64 39	97.17 48	97.73 59	95.49 55	92.25 44	96.18 15	90.34 38	88.51 55	92.88 51	94.90 40	94.92 70	94.17 73	97.69 108	96.15 116

AdaColmap		95.02 37	93.71 50	96.54 22	98.51 26	97.76 57	96.69 40	95.94 19	93.72 46	93.50 16	89.01 53	90.53 66	96.49 21	94.51 85	93.76 83	98.07 77	96.69 96

DeepMVS_CX						71.82 218	68.37 217	48.05 219	77.38 185	46.88 220	65.77 184	47.03 222	67.48 206	64.27 218		76.89 220	76.72 214

TinyColmap		84.04 165	82.01 182	86.42 140	90.87 139	91.84 184	88.89 166	84.07 140	82.11 161	69.89 161	71.08 159	60.81 205	89.04 113	90.52 156	89.19 180	95.76 170	88.50 199

MAR-MVS		92.71 60	92.63 61	92.79 66	97.70 40	97.15 76	93.75 89	87.98 97	90.71 70	85.76 79	86.28 67	86.38 79	94.35 46	94.95 68	95.49 54	97.22 125	97.44 73
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
MSDG		90.42 94	88.25 114	92.94 64	96.67 55	94.41 119	93.96 81	92.91 41	89.59 96	86.26 71	76.74 128	80.92 115	90.43 96	92.60 120	92.08 126	97.44 120	91.41 178

LS3D		91.97 67	90.98 87	93.12 60	97.03 51	97.09 79	95.33 59	95.59 22	92.47 56	79.26 118	81.60 104	82.77 100	94.39 45	94.28 87	94.23 72	97.14 131	94.45 152

CLD-MVS		92.50 62	91.96 73	93.13 59	93.93 92	96.24 98	95.69 52	88.77 86	92.92 50	89.01 46	88.19 57	81.74 111	93.13 63	93.63 100	93.08 105	98.23 63	97.91 58
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
FPMVS		69.87 209	67.10 212	73.10 206	84.09 205	78.35 217	79.40 206	76.41 192	71.92 203	57.71 209	54.06 213	50.04 218	56.72 212	71.19 214	68.70 214	84.25 215	75.43 215

Gipuma		58.52 212	56.17 215	61.27 211	67.14 219	58.06 220	52.16 222	68.40 213	69.00 210	45.02 221	22.79 219	20.57 226	55.11 213	76.27 212	79.33 211	79.80 218	67.16 218
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015

High-resolution multi-view benchmark