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	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.43 1	99.49 1	99.24 1	99.95 1	98.13 1	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 1	97.58 1	99.94 1	99.85 2

UA-Net		97.35 4	97.24 15	97.69 5	98.22 83	93.87 39	98.42 6	98.19 61	96.95 18	95.46 194	99.23 9	93.45 107	99.57 14	95.34 45	99.89 2	99.63 12

PS-CasMVS		96.69 27	97.43 9	94.49 153	99.13 6	84.09 264	96.61 37	97.97 107	97.91 8	98.64 16	98.13 45	95.24 45	99.65 4	93.39 97	99.84 3	99.72 4

WR-MVS_H		96.60 32	97.05 20	95.24 106	99.02 13	86.44 210	96.78 28	98.08 83	97.42 12	98.48 19	97.86 73	91.76 162	99.63 7	94.23 63	99.84 3	99.66 9

FC-MVSNet-test		95.32 94	95.88 75	93.62 193	98.49 65	81.77 313	95.90 81	98.32 38	93.93 72	97.53 52	97.56 95	88.48 242	99.40 51	92.91 116	99.83 5	99.68 7

PEN-MVS		96.69 27	97.39 12	94.61 142	99.16 4	84.50 253	96.54 39	98.05 92	98.06 7	98.64 16	98.25 42	95.01 59	99.65 4	92.95 115	99.83 5	99.68 7

DTE-MVSNet		96.74 24	97.43 9	94.67 139	99.13 6	84.68 251	96.51 41	97.94 115	98.14 6	98.67 15	98.32 39	95.04 56	99.69 3	93.27 103	99.82 7	99.62 13

CP-MVSNet		96.19 54	96.80 23	94.38 158	98.99 19	83.82 267	96.31 61	97.53 168	97.60 10	98.34 22	97.52 100	91.98 156	99.63 7	93.08 111	99.81 8	99.70 5

LTVRE_ROB	93.87 1	97.93 2	98.16 2	97.26 29	98.81 32	93.86 40	99.07 2	98.98 8	97.01 17	98.92 5	98.78 19	95.22 47	98.61 197	96.85 11	99.77 9	99.31 33
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
tt0320-xc		97.00 12	97.67 5	94.98 117	98.89 23	86.94 195	96.72 31	98.46 24	98.28 4	98.86 7	99.43 4	96.80 10	98.51 223	91.79 152	99.76 10	99.50 19

v7n		96.82 16	97.31 14	95.33 99	98.54 55	86.81 198	96.83 24	98.07 86	96.59 25	98.46 20	98.43 37	92.91 131	99.52 19	96.25 21	99.76 10	99.65 11

TranMVSNet+NR-MVSNet		96.07 58	96.26 49	95.50 90	98.26 80	87.69 177	93.75 181	97.86 126	95.96 41	97.48 56	97.14 149	95.33 40	99.44 33	90.79 187	99.76 10	99.38 28

Anonymous20231211		96.60 32	97.13 19	95.00 116	97.46 145	86.35 214	97.11 18	98.24 54	97.58 11	98.72 11	98.97 12	93.15 120	99.15 100	93.18 106	99.74 13	99.50 19

UniMVSNet_ETH3D		97.13 10	97.72 3	95.35 97	99.51 2	87.38 181	97.70 8	97.54 165	98.16 5	98.94 3	99.33 6	97.84 4	99.08 112	90.73 189	99.73 14	99.59 15

sc_t1		97.21 9	97.71 4	95.71 78	99.06 10	88.89 142	96.72 31	97.79 139	98.34 2	98.97 2	99.40 5	96.81 9	98.79 161	92.58 129	99.72 15	99.45 23

tt0320		96.97 13	97.64 6	94.96 120	98.89 23	86.86 197	96.85 23	98.45 25	98.29 3	98.88 6	99.45 3	96.48 13	98.54 215	91.73 155	99.72 15	99.47 21

pmmvs6		96.80 19	97.36 13	95.15 112	99.12 8	87.82 175	96.68 33	97.86 126	96.10 36	98.14 30	99.28 8	97.94 3	98.21 263	91.38 168	99.69 17	99.42 24

FIs		94.90 115	95.35 104	93.55 197	98.28 78	81.76 314	95.33 106	98.14 72	93.05 91	97.07 83	97.18 144	87.65 262	99.29 82	91.72 156	99.69 17	99.61 14

OurMVSNet-221017-0		96.80 19	96.75 25	96.96 38	99.03 12	91.85 82	97.98 7	98.01 102	94.15 64	98.93 4	99.07 10	88.07 251	99.57 14	95.86 27	99.69 17	99.46 22

Anonymous20240521		92.86 227	93.57 199	90.74 363	96.57 222	75.50 458	94.15 161	95.60 304	89.38 209	95.90 161	97.90 72	80.39 356	97.96 302	92.60 128	99.68 20	98.75 115

ANet_high		94.83 118	96.28 48	90.47 373	96.65 209	73.16 480	94.33 150	98.74 13	96.39 30	98.09 33	98.93 13	93.37 111	98.70 183	90.38 201	99.68 20	99.53 17

DeepC-MVS	91.39 4	95.43 87	95.33 107	95.71 78	97.67 130	90.17 117	93.86 177	98.02 101	87.35 273	96.22 142	97.99 58	94.48 85	99.05 119	92.73 123	99.68 20	97.93 228
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NR-MVSNet		95.28 98	95.28 110	95.26 104	97.75 120	87.21 185	95.08 120	97.37 180	93.92 74	97.65 43	95.90 260	90.10 217	99.33 77	90.11 220	99.66 23	99.26 37

Baseline_NR-MVSNet		94.47 144	95.09 124	92.60 257	98.50 64	80.82 336	92.08 270	96.68 253	93.82 75	96.29 136	98.56 29	90.10 217	97.75 328	90.10 222	99.66 23	99.24 41

UniMVSNet (Re)		95.32 94	95.15 114	95.80 74	97.79 118	88.91 141	92.91 224	98.07 86	93.46 83	96.31 133	95.97 259	90.14 214	99.34 70	92.11 139	99.64 25	99.16 47

WR-MVS		93.49 192	93.72 189	92.80 242	97.57 137	80.03 351	90.14 358	95.68 302	93.70 77	96.62 113	95.39 298	87.21 271	99.04 122	87.50 306	99.64 25	99.33 31

MIMVSNet1		95.52 82	95.45 95	95.72 77	99.14 5	89.02 139	96.23 68	96.87 233	93.73 76	97.87 35	98.49 33	90.73 200	99.05 119	86.43 329	99.60 27	99.10 57

ACMH+	88.43 11	96.48 38	96.82 22	95.47 92	98.54 55	89.06 138	95.65 91	98.61 15	96.10 36	98.16 29	97.52 100	96.90 7	98.62 196	90.30 209	99.60 27	98.72 121

VPA-MVSNet		95.14 105	95.67 87	93.58 196	97.76 119	83.15 283	94.58 141	97.58 161	93.39 84	97.05 86	98.04 52	93.25 115	98.51 223	89.75 232	99.59 29	99.08 58

LPG-MVS_test		96.38 47	96.23 50	96.84 41	98.36 75	92.13 77	95.33 106	98.25 46	91.78 132	97.07 83	97.22 140	96.38 16	99.28 86	92.07 142	99.59 29	99.11 54

LGP-MVS_train				96.84 41	98.36 75	92.13 77		98.25 46	91.78 132	97.07 83	97.22 140	96.38 16	99.28 86	92.07 142	99.59 29	99.11 54

ACMH	88.36 12	96.59 34	97.43 9	94.07 169	98.56 49	85.33 243	96.33 54	98.30 41	94.66 54	98.72 11	98.30 40	97.51 5	98.00 298	94.87 50	99.59 29	98.86 94
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UniMVSNet_NR-MVSNet		95.35 92	95.21 112	95.76 75	97.69 128	88.59 151	92.26 266	97.84 130	94.91 52	96.80 100	95.78 271	90.42 206	99.41 43	91.60 160	99.58 33	99.29 36

DU-MVS		95.28 98	95.12 120	95.75 76	97.75 120	88.59 151	92.58 243	97.81 135	93.99 68	96.80 100	95.90 260	90.10 217	99.41 43	91.60 160	99.58 33	99.26 37

MM		94.41 147	94.14 173	95.22 109	95.84 300	87.21 185	94.31 152	90.92 437	94.48 58	92.80 331	97.52 100	85.27 303	99.49 29	96.58 17	99.57 35	98.97 73

ACMP	88.15 13	95.71 74	95.43 99	96.54 48	98.17 86	91.73 86	94.24 155	98.08 83	89.46 207	96.61 114	96.47 209	95.85 22	99.12 106	90.45 198	99.56 36	98.77 114
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v10		94.68 127	95.27 111	92.90 234	96.57 222	80.15 345	94.65 138	97.57 162	90.68 173	97.43 58	98.00 55	88.18 248	99.15 100	94.84 51	99.55 37	99.41 26

MGCNet		92.88 223	92.27 251	94.69 136	92.35 432	86.03 224	92.88 226	89.68 445	90.53 180	91.52 378	96.43 212	82.52 334	99.32 78	95.01 48	99.54 38	98.71 124

PS-MVSNAJss		96.01 59	96.04 63	95.89 71	98.82 30	88.51 154	95.57 97	97.88 123	88.72 227	98.81 9	98.86 15	90.77 196	99.60 9	95.43 40	99.53 39	99.57 16

TDRefinement		97.68 3	97.60 8	97.93 2	99.02 13	95.95 8	98.61 3	98.81 10	97.41 13	97.28 71	98.46 35	94.62 77	98.84 150	94.64 53	99.53 39	98.99 66

IS-MVSNet		94.49 143	94.35 163	94.92 121	98.25 82	86.46 209	97.13 17	94.31 356	96.24 34	96.28 138	96.36 224	82.88 326	99.35 67	88.19 288	99.52 41	98.96 77

SSC-MVS3.2		89.88 337	91.06 291	86.31 478	95.90 296	63.76 531	82.68 516	92.43 412	91.42 152	92.37 351	94.58 340	86.34 289	96.60 407	84.35 365	99.50 42	98.57 147

nrg030		96.32 49	96.55 34	95.62 84	97.83 114	88.55 153	95.77 86	98.29 44	92.68 94	98.03 34	97.91 70	95.13 50	98.95 136	93.85 74	99.49 43	99.36 30

MP-MVS-pluss		96.08 57	95.92 72	96.57 47	99.06 10	91.21 94	93.25 203	98.32 38	87.89 258	96.86 95	97.38 115	95.55 30	99.39 54	95.47 38	99.47 44	99.11 54
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mvs_tets		96.83 15	96.71 26	97.17 30	98.83 29	92.51 70	96.58 38	97.61 156	87.57 269	98.80 10	98.90 14	96.50 12	99.59 13	96.15 22	99.47 44	99.40 27

v8		94.65 128	95.29 109	92.74 245	96.65 209	79.77 362	94.59 139	97.17 202	91.86 124	97.47 57	97.93 62	88.16 249	99.08 112	94.32 60	99.47 44	99.38 28

CLD-MVS		91.82 269	91.41 279	93.04 224	96.37 244	83.65 269	86.82 452	97.29 193	84.65 357	92.27 356	89.67 478	92.20 152	97.85 315	83.95 371	99.47 44	97.62 272
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
SPE-MVS-test		95.32 94	95.10 123	95.96 62	96.86 189	90.75 108	96.33 54	99.20 4	93.99 68	91.03 394	93.73 378	93.52 104	99.55 18	91.81 151	99.45 48	97.58 276

jajsoiax		96.59 34	96.42 38	97.12 32	98.76 35	92.49 71	96.44 48	97.42 177	86.96 288	98.71 13	98.72 22	95.36 38	99.56 17	95.92 25	99.45 48	99.32 32

test_djsdf		96.62 30	96.49 35	97.01 35	98.55 53	91.77 85	97.15 15	97.37 180	88.98 219	98.26 26	98.86 15	93.35 112	99.60 9	96.41 18	99.45 48	99.66 9

FE-MVSNET2		94.07 170	94.47 156	92.90 234	97.45 147	81.26 326	93.58 189	97.54 165	88.28 245	96.46 120	97.92 67	91.41 174	98.74 172	88.12 292	99.44 51	98.69 128

CP-MVS		96.44 42	96.08 60	97.54 14	98.29 77	94.62 18	96.80 26	98.08 83	92.67 96	95.08 229	96.39 221	94.77 73	99.42 37	93.17 107	99.44 51	98.58 146

COLMAP_ROB	91.06 5	96.75 23	96.62 31	97.13 31	98.38 70	94.31 21	96.79 27	98.32 38	96.69 21	96.86 95	97.56 95	95.48 31	98.77 168	90.11 220	99.44 51	98.31 178
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
NormalMVS		94.10 167	93.36 207	96.31 55	99.01 15	90.84 104	94.70 134	97.90 118	90.98 162	93.22 310	95.73 274	78.94 369	99.12 106	90.38 201	99.42 54	98.97 73

lecture		97.32 6	97.64 6	96.33 54	99.01 15	90.77 107	96.90 21	98.60 16	96.30 33	97.74 41	98.00 55	96.87 8	99.39 54	95.95 24	99.42 54	98.84 98

test_0728_THIRD									93.26 87	97.40 63	97.35 124	94.69 74	99.34 70	93.88 72	99.42 54	98.89 91

MTAPA		96.65 29	96.38 42	97.47 18	98.95 21	94.05 27	95.88 82	97.62 154	94.46 59	96.29 136	96.94 168	93.56 102	99.37 65	94.29 62	99.42 54	98.99 66

pm-mvs1		95.43 87	95.94 69	93.93 177	98.38 70	85.08 247	95.46 102	97.12 209	91.84 128	97.28 71	98.46 35	95.30 42	97.71 332	90.17 218	99.42 54	98.99 66

XVG-ACMP-BASELINE		95.68 75	95.34 105	96.69 44	98.40 68	93.04 58	94.54 146	98.05 92	90.45 183	96.31 133	96.76 185	92.91 131	98.72 175	91.19 172	99.42 54	98.32 176

wuyk23d		87.83 394	90.79 302	78.96 522	90.46 494	88.63 147	92.72 233	90.67 440	91.65 140	98.68 14	97.64 89	96.06 19	77.53 545	59.84 538	99.41 60	70.73 543

anonymousdsp		96.74 24	96.42 38	97.68 7	98.00 102	94.03 29	96.97 19	97.61 156	87.68 266	98.45 21	98.77 20	94.20 90	99.50 23	96.70 13	99.40 61	99.53 17

SixPastTwentyTwo		94.91 113	95.21 112	93.98 172	98.52 57	83.19 282	95.93 79	94.84 339	94.86 53	98.49 18	98.74 21	81.45 345	99.60 9	94.69 52	99.39 62	99.15 48

Elysia		96.00 60	96.36 43	94.91 122	98.01 100	85.96 227	95.29 110	97.90 118	95.31 45	98.14 30	97.28 132	88.82 234	99.51 20	97.08 7	99.38 63	99.26 37

StellarMVS		96.00 60	96.36 43	94.91 122	98.01 100	85.96 227	95.29 110	97.90 118	95.31 45	98.14 30	97.28 132	88.82 234	99.51 20	97.08 7	99.38 63	99.26 37

HPM-MVS_fast		97.01 11	96.89 21	97.39 24	99.12 8	93.92 36	97.16 14	98.17 67	93.11 89	96.48 118	97.36 121	96.92 6	99.34 70	94.31 61	99.38 63	98.92 87

HPM-MVS		96.81 18	96.62 31	97.36 26	98.89 23	93.53 51	97.51 10	98.44 26	92.35 104	95.95 157	96.41 215	96.71 11	99.42 37	93.99 70	99.36 66	99.13 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
reproduce_model		97.35 4	97.24 15	97.70 4	98.44 67	95.08 12	95.88 82	98.50 21	96.62 24	98.27 23	97.93 62	94.57 79	99.50 23	95.57 35	99.35 67	98.52 151

SDMVSNet		94.43 146	95.02 125	92.69 248	97.93 108	82.88 291	91.92 280	95.99 295	93.65 81	95.51 189	98.63 25	94.60 78	96.48 411	87.57 305	99.35 67	98.70 125

sd_testset		93.94 176	94.39 158	92.61 256	97.93 108	83.24 278	93.17 207	95.04 332	93.65 81	95.51 189	98.63 25	94.49 84	95.89 431	81.72 398	99.35 67	98.70 125

KD-MVS_self_test		94.10 167	94.73 140	92.19 278	97.66 131	79.49 375	94.86 128	97.12 209	89.59 205	96.87 94	97.65 88	90.40 208	98.34 248	89.08 257	99.35 67	98.75 115

ACMMP_NAP		96.21 53	96.12 57	96.49 51	98.90 22	91.42 92	94.57 142	98.03 99	90.42 184	96.37 127	97.35 124	95.68 25	99.25 90	94.44 58	99.34 71	98.80 104

SteuartSystems-ACMMP		96.40 45	96.30 47	96.71 43	98.63 42	91.96 80	95.70 88	98.01 102	93.34 86	96.64 112	96.57 203	94.99 60	99.36 66	93.48 89	99.34 71	98.82 99
Skip Steuart: Steuart Systems R&D Blog.
reproduce-ours		97.28 7	97.19 17	97.57 11	98.37 72	94.84 13	95.57 97	98.40 30	96.36 31	98.18 27	97.78 75	95.47 32	99.50 23	95.26 46	99.33 73	98.36 171

our_new_method		97.28 7	97.19 17	97.57 11	98.37 72	94.84 13	95.57 97	98.40 30	96.36 31	98.18 27	97.78 75	95.47 32	99.50 23	95.26 46	99.33 73	98.36 171

ACMMP		96.61 31	96.34 45	97.43 21	98.61 45	93.88 37	96.95 20	98.18 63	92.26 107	96.33 130	96.84 180	95.10 54	99.40 51	93.47 90	99.33 73	99.02 63
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
ACMM	88.83 9	96.30 51	96.07 61	96.97 37	98.39 69	92.95 61	94.74 131	98.03 99	90.82 168	97.15 78	96.85 177	96.25 18	99.00 126	93.10 109	99.33 73	98.95 80
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test1111		90.39 314	90.61 307	89.74 399	98.04 97	71.50 494	95.59 93	79.72 537	89.41 208	95.94 158	98.14 44	70.79 456	98.81 157	88.52 279	99.32 77	98.90 90

DVP-MVS		95.82 69	96.18 53	94.72 134	98.51 58	86.69 202	95.20 116	97.00 216	91.85 125	97.40 63	97.35 124	95.58 28	99.34 70	93.44 93	99.31 78	98.13 201
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
test_0728_SECOND				94.88 125	98.55 53	86.72 201	95.20 116	98.22 58					99.38 63	93.44 93	99.31 78	98.53 150

MSC_two_6792asdad				95.90 69	96.54 225	89.57 124		96.87 233					99.41 43	94.06 67	99.30 80	98.72 121

No_MVS				95.90 69	96.54 225	89.57 124		96.87 233					99.41 43	94.06 67	99.30 80	98.72 121

APDe-MVS		96.46 39	96.64 29	95.93 66	97.68 129	89.38 131	96.90 21	98.41 29	92.52 98	97.43 58	97.92 67	95.11 52	99.50 23	94.45 57	99.30 80	98.92 87
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SED-MVS		96.00 60	96.41 41	94.76 132	98.51 58	86.97 192	95.21 114	98.10 80	91.95 118	97.63 45	97.25 135	96.48 13	99.35 67	93.29 101	99.29 83	97.95 223

IU-MVS					98.51 58	86.66 204		96.83 238	72.74 496	95.83 165				93.00 113	99.29 83	98.64 138

SMA-MVS		95.77 71	95.54 92	96.47 52	98.27 79	91.19 95	95.09 119	97.79 139	86.48 296	97.42 61	97.51 104	94.47 86	99.29 82	93.55 84	99.29 83	98.93 83
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
MP-MVS		96.14 55	95.68 86	97.51 16	98.81 32	94.06 25	96.10 72	97.78 141	92.73 93	93.48 291	96.72 191	94.23 89	99.42 37	91.99 145	99.29 83	99.05 61
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test_0402		95.73 73	96.22 51	94.26 161	98.19 85	85.77 233	93.24 204	97.24 198	96.88 20	97.69 42	97.77 79	94.12 92	99.13 105	91.54 164	99.29 83	97.88 239

ZNCC-MVS		96.42 43	96.20 52	97.07 33	98.80 34	92.79 64	96.08 73	98.16 70	91.74 136	95.34 201	96.36 224	95.68 25	99.44 33	94.41 59	99.28 88	98.97 73

DPE-MVS		95.89 66	95.88 75	95.92 68	97.93 108	89.83 121	93.46 195	98.30 41	92.37 102	97.75 39	96.95 167	95.14 49	99.51 20	91.74 154	99.28 88	98.41 164
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
mPP-MVS		96.46 39	96.05 62	97.69 5	98.62 43	94.65 17	96.45 46	97.74 143	92.59 97	95.47 192	96.68 194	94.50 83	99.42 37	93.10 109	99.26 90	98.99 66

test_241102_TWO								98.10 80	91.95 118	97.54 50	97.25 135	95.37 36	99.35 67	93.29 101	99.25 91	98.49 155

ACMMP++															99.25 91

DKM		92.97 220	92.35 249	94.81 129	96.53 228	93.72 46	90.94 318	94.88 337	85.21 340	96.42 123	95.18 306	83.11 322	93.06 480	89.66 236	99.24 93	97.64 270

CSCG		94.69 126	94.75 137	94.52 150	97.55 138	87.87 173	95.01 124	97.57 162	92.68 94	96.20 144	93.44 387	91.92 157	98.78 165	89.11 256	99.24 93	96.92 325

testf1		96.77 21	96.49 35	97.60 9	99.01 15	96.70 3	96.31 61	98.33 36	94.96 50	97.30 68	97.93 62	96.05 20	97.90 305	89.32 242	99.23 95	98.19 193

APD_test2		96.77 21	96.49 35	97.60 9	99.01 15	96.70 3	96.31 61	98.33 36	94.96 50	97.30 68	97.93 62	96.05 20	97.90 305	89.32 242	99.23 95	98.19 193

TransMVSNet (Re)		95.27 101	96.04 63	92.97 227	98.37 72	81.92 312	95.07 121	96.76 245	93.97 70	97.77 38	98.57 28	95.72 24	97.90 305	88.89 263	99.23 95	99.08 58

EC-MVSNet		95.44 86	95.62 89	94.89 124	96.93 184	87.69 177	96.48 45	99.14 6	93.93 72	92.77 333	94.52 342	93.95 97	99.49 29	93.62 81	99.22 98	97.51 282

EGC-MVSNET		80.97 485	75.73 505	96.67 45	98.85 28	94.55 19	96.83 24	96.60 258	2.44 551	5.32 553	98.25 42	92.24 149	98.02 295	91.85 150	99.21 99	97.45 287

PGM-MVS		96.32 49	95.94 69	97.43 21	98.59 48	93.84 41	95.33 106	98.30 41	91.40 153	95.76 170	96.87 176	95.26 44	99.45 32	92.77 120	99.21 99	99.00 64

SIFT-PointCN		87.02 423	86.47 423	88.65 430	90.27 498	91.47 90	83.91 507	84.08 502	84.84 354	91.35 382	92.24 431	75.25 426	87.29 525	77.11 453	99.20 101	87.20 525

test-260524					97.94 107	87.97 171		97.94 115		96.37 127		93.24 116	99.34 70	94.10 66	99.19 102

MED-MVS		96.38 47	96.63 30	95.63 83	98.69 37	88.21 161	96.32 56	98.58 18	94.10 65	97.38 65	97.37 116	95.11 52	99.39 54	92.89 117	99.19 102	99.30 34

SD-MVS		95.19 103	95.73 84	93.55 197	96.62 218	88.88 144	94.67 136	98.05 92	91.26 156	97.25 74	96.40 216	95.42 34	94.36 466	92.72 124	99.19 102	97.40 295
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
Vis-MVSNet (Re-imp)		90.42 311	90.16 320	91.20 337	97.66 131	77.32 427	94.33 150	87.66 466	91.20 158	92.99 323	95.13 309	75.40 425	98.28 251	77.86 441	99.19 102	97.99 216

test2506		85.42 441	84.57 444	87.96 446	97.81 116	66.53 517	96.14 70	56.35 552	89.04 217	93.55 288	98.10 47	42.88 543	98.68 187	88.09 294	99.18 106	98.67 130

ECVR-MVS		90.12 326	90.16 320	90.00 391	97.81 116	72.68 486	95.76 87	78.54 541	89.04 217	95.36 200	98.10 47	70.51 458	98.64 193	87.10 313	99.18 106	98.67 130

tfpnnormal		94.27 155	94.87 131	92.48 266	97.71 125	80.88 335	94.55 145	95.41 318	93.70 77	96.67 109	97.72 81	91.40 175	98.18 267	87.45 307	99.18 106	98.36 171

RoMa-HiRes		94.64 129	94.29 165	95.68 81	97.47 144	93.88 37	93.83 179	96.23 281	88.05 253	97.75 39	96.20 239	88.58 240	94.93 457	91.33 169	99.17 109	98.22 188

FMVSNet1		94.84 117	95.13 119	93.97 173	97.60 134	84.29 257	95.99 75	96.56 262	92.38 101	97.03 87	98.53 30	90.12 215	98.98 128	88.78 268	99.16 110	98.65 132

ACMMPR		96.46 39	96.14 56	97.41 23	98.60 46	93.82 42	96.30 65	97.96 109	92.35 104	95.57 187	96.61 200	94.93 64	99.41 43	93.78 76	99.15 111	99.00 64

HFP-MVS		96.39 46	96.17 55	97.04 34	98.51 58	93.37 52	96.30 65	97.98 105	92.35 104	95.63 184	96.47 209	95.37 36	99.27 89	93.78 76	99.14 112	98.48 156

VDD-MVS		94.37 150	94.37 160	94.40 157	97.49 141	86.07 223	93.97 171	93.28 391	94.49 57	96.24 140	97.78 75	87.99 255	98.79 161	88.92 261	99.14 112	98.34 175

region2R		96.41 44	96.09 58	97.38 25	98.62 43	93.81 44	96.32 56	97.96 109	92.26 107	95.28 207	96.57 203	95.02 58	99.41 43	93.63 80	99.11 114	98.94 81

aaatest				95.52 89	98.69 37	88.21 161	96.32 56	98.58 18	88.79 225	97.38 65	96.22 236		99.39 54	92.89 117	99.10 115	98.96 77

aaEdge-Enhanced		95.61 77	95.65 88	95.49 91	97.62 133	88.21 161	94.21 158	97.87 125	92.48 99	96.38 125	96.22 236	94.06 94	99.32 78	92.89 117	99.10 115	98.96 77

fmvsm_s_conf0.5_n_6		94.14 166	94.54 153	92.95 229	96.51 230	82.74 298	92.71 235	98.13 73	86.56 294	96.44 121	96.85 177	88.51 241	98.05 289	96.03 23	99.09 117	98.06 204

Gipuma		95.31 97	95.80 82	93.81 184	97.99 105	90.91 101	96.42 49	97.95 112	96.69 21	91.78 372	98.85 17	91.77 160	95.49 439	91.72 156	99.08 118	95.02 424
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
GST-MVS		96.24 52	95.99 66	97.00 36	98.65 41	92.71 66	95.69 90	98.01 102	92.08 116	95.74 175	96.28 230	95.22 47	99.42 37	93.17 107	99.06 119	98.88 93

OPM-MVS		95.61 77	95.45 95	96.08 58	98.49 65	91.00 98	92.65 239	97.33 188	90.05 194	96.77 103	96.85 177	95.04 56	98.56 212	92.77 120	99.06 119	98.70 125
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPNet		93.08 214	93.76 188	91.03 344	98.60 46	75.83 456	91.51 298	95.62 303	91.84 128	95.74 175	97.10 155	89.31 228	98.32 249	85.07 353	99.06 119	98.93 83

SF-MVS		95.88 67	95.88 75	95.87 72	98.12 88	89.65 123	95.58 96	98.56 20	91.84 128	96.36 129	96.68 194	94.37 87	99.32 78	92.41 134	99.05 122	98.64 138

CS-MVS		95.77 71	95.58 91	96.37 53	96.84 191	91.72 87	96.73 30	99.06 7	94.23 62	92.48 343	94.79 329	93.56 102	99.49 29	93.47 90	99.05 122	97.89 238

XVS		96.49 37	96.18 53	97.44 19	98.56 49	93.99 32	96.50 42	97.95 112	94.58 55	94.38 256	96.49 208	94.56 80	99.39 54	93.57 82	99.05 122	98.93 83

X-MVStestdata		90.70 301	88.45 361	97.44 19	98.56 49	93.99 32	96.50 42	97.95 112	94.58 55	94.38 256	26.89 548	94.56 80	99.39 54	93.57 82	99.05 122	98.93 83

test20.03		90.80 297	90.85 298	90.63 369	95.63 319	79.24 384	89.81 373	92.87 398	89.90 196	94.39 255	96.40 216	85.77 295	95.27 448	73.86 492	99.05 122	97.39 296

TestfortrainingZip a		96.50 36	96.80 23	95.62 84	98.69 37	88.28 158	96.32 56	98.06 90	94.10 65	97.65 43	97.37 116	94.54 82	99.28 86	95.41 42	99.04 127	99.30 34

Anonymous20240529		95.50 83	95.83 79	94.50 151	97.33 153	85.93 229	95.19 118	96.77 244	96.64 23	97.61 48	98.05 50	93.23 117	98.79 161	88.60 275	99.04 127	98.78 111

IterMVS-LS		93.78 181	94.28 167	92.27 271	96.27 261	79.21 386	91.87 285	96.78 241	91.77 134	96.57 117	97.07 157	87.15 273	98.74 172	91.99 145	99.03 129	98.86 94
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Casviewmamba		95.48 85	95.97 67	94.04 170	96.94 181	84.57 252	93.96 172	98.29 44	93.94 71	96.76 104	97.14 149	95.27 43	98.72 175	92.37 136	99.02 130	98.82 99

mmtdpeth		95.82 69	96.02 65	95.23 107	96.91 185	88.62 148	96.49 44	99.26 3	95.07 49	93.41 293	99.29 7	90.25 210	97.27 367	94.49 55	99.01 131	99.80 3

RoMa-SfM		93.45 194	92.92 223	95.03 115	96.77 199	94.01 31	93.01 212	95.19 328	83.99 369	97.28 71	95.33 301	87.17 272	93.66 473	88.55 278	99.00 132	97.42 290

fmvsm_s_conf0.5_n_9		95.58 80	95.91 73	94.59 146	97.25 156	86.26 216	92.96 217	97.86 126	91.88 123	97.52 53	98.13 45	91.45 173	98.54 215	97.17 4	98.99 133	98.98 70

test_fmvsmconf0.01_n		95.90 65	96.09 58	95.31 102	97.30 155	89.21 133	94.24 155	98.76 12	86.25 305	97.56 49	98.66 23	95.73 23	98.44 236	97.35 3	98.99 133	98.27 183

SIFT-NCMNet		87.31 412	87.07 405	88.02 445	90.01 503	91.85 82	82.65 517	89.57 447	86.52 295	93.34 299	92.51 420	78.05 390	86.22 534	71.95 503	98.98 135	86.01 531

test_fmvsmconf0.1_n		95.61 77	95.72 85	95.26 104	96.85 190	89.20 134	93.51 193	98.60 16	85.68 326	97.42 61	98.30 40	95.34 39	98.39 237	96.85 11	98.98 135	98.19 193

cl____		90.65 304	90.56 311	90.91 355	91.85 452	76.98 435	86.75 453	95.36 320	85.53 331	94.06 267	94.89 320	77.36 402	97.98 301	90.27 211	98.98 135	97.76 258

AllTest		94.88 116	94.51 155	96.00 59	98.02 98	92.17 74	95.26 112	98.43 27	90.48 181	95.04 231	96.74 188	92.54 140	97.86 313	85.11 351	98.98 135	97.98 217

TestCases				96.00 59	98.02 98	92.17 74		98.43 27	90.48 181	95.04 231	96.74 188	92.54 140	97.86 313	85.11 351	98.98 135	97.98 217

Patchmtry		90.11 327	89.92 327	90.66 367	90.35 496	77.00 433	92.96 217	92.81 399	90.25 187	94.74 244	96.93 170	67.11 472	97.52 346	85.17 346	98.98 135	97.46 286

DIV-MVS_self_test		90.65 304	90.56 311	90.91 355	91.85 452	76.99 434	86.75 453	95.36 320	85.52 334	94.06 267	94.89 320	77.37 401	97.99 300	90.28 210	98.97 141	97.76 258

9.14			94.81 132		97.49 141		94.11 164	98.37 34	87.56 270	95.38 197	96.03 253	94.66 75	99.08 112	90.70 190	98.97 141

D2MVS		89.93 335	89.60 336	90.92 353	94.03 387	78.40 401	88.69 416	94.85 338	78.96 447	93.08 319	95.09 312	74.57 429	96.94 392	88.19 288	98.96 143	97.41 291

PHI-MVS		94.34 153	93.80 186	95.95 63	95.65 316	91.67 88	94.82 129	97.86 126	87.86 259	93.04 322	94.16 360	91.58 165	98.78 165	90.27 211	98.96 143	97.41 291

casdiffseed414692147		94.56 134	94.90 128	93.54 199	96.60 219	83.33 275	93.57 190	98.06 90	91.57 142	95.26 210	97.31 129	94.06 94	98.39 237	88.67 271	98.95 145	98.91 89

fmvsm_s_conf0.5_n_11		94.91 113	95.44 98	93.33 212	96.45 235	83.11 286	93.56 191	98.64 14	89.76 200	95.70 179	97.97 59	92.32 146	98.08 282	95.62 31	98.95 145	98.79 106

test_fmvsmconf_n		95.43 87	95.50 93	95.22 109	96.48 234	89.19 135	93.23 205	98.36 35	85.61 329	96.92 93	98.02 54	95.23 46	98.38 241	96.69 14	98.95 145	98.09 203

PDCNetPlus		79.66 497	78.21 501	84.01 501	79.49 548	73.91 475	75.29 536	96.44 270	66.51 528	89.20 438	91.98 441	30.56 553	84.51 540	75.48 469	98.93 148	93.62 466

fmvsm_s_conf0.5_n_7		93.61 186	93.94 181	92.63 253	96.11 278	82.76 297	90.81 324	97.55 164	86.57 293	93.14 316	97.69 83	90.17 213	96.83 399	94.46 56	98.93 148	98.31 178

mvs5depth		95.28 98	95.82 81	93.66 191	96.42 239	83.08 287	97.35 12	99.28 2	96.44 28	96.20 144	99.65 2	84.10 313	98.01 296	94.06 67	98.93 148	99.87 1

ambc				92.98 226	96.88 187	83.01 289	95.92 80	96.38 273		96.41 124	97.48 106	88.26 247	97.80 319	89.96 226	98.93 148	98.12 202

DKM-HiRes		92.87 225	91.94 263	95.65 82	97.16 163	93.66 47	90.90 320	94.27 359	87.11 285	95.29 205	95.39 298	77.59 395	95.36 443	90.86 185	98.92 152	97.94 225

BridgeMVS		93.45 194	94.17 172	91.28 331	95.81 304	78.40 401	96.20 69	97.48 174	88.56 237	95.29 205	97.20 143	85.56 302	99.21 93	92.52 131	98.91 153	96.24 369

DenseAffine		91.92 268	90.90 294	94.97 118	96.37 244	93.07 56	90.35 347	93.65 379	84.62 358	95.66 183	94.39 349	78.19 385	94.97 456	86.02 335	98.90 154	96.87 331

hybridcas		94.81 120	95.45 95	92.88 237	96.74 201	81.36 324	93.32 202	98.13 73	92.16 113	96.79 102	96.98 166	94.91 65	98.53 219	91.16 173	98.90 154	98.75 115

fmvsm_s_conf0.5_n_10		94.63 130	95.11 121	93.18 221	96.28 258	83.51 271	93.00 214	98.25 46	88.37 243	97.43 58	97.70 82	88.90 232	98.63 195	97.15 5	98.90 154	97.41 291

EPNet		89.80 340	88.25 370	94.45 155	83.91 540	86.18 220	93.87 176	87.07 472	91.16 160	80.64 532	94.72 331	78.83 371	98.89 142	85.17 346	98.89 157	98.28 181
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPP-MVSNet		93.91 177	93.68 194	94.59 146	98.08 91	85.55 239	97.44 11	94.03 365	94.22 63	94.94 235	96.19 240	82.07 338	99.57 14	87.28 311	98.89 157	98.65 132

v1192		93.49 192	93.78 187	92.62 255	96.16 272	79.62 366	91.83 288	97.22 200	86.07 311	96.10 151	96.38 222	87.22 270	99.02 124	94.14 65	98.88 159	99.22 42

v1144		93.50 191	93.81 184	92.57 258	96.28 258	79.61 367	91.86 287	96.96 219	86.95 289	95.91 160	96.32 226	87.65 262	98.96 134	93.51 86	98.88 159	99.13 50

APD-MVS_3200maxsize		96.82 16	96.65 28	97.32 28	97.95 106	93.82 42	96.31 61	98.25 46	95.51 44	96.99 90	97.05 160	95.63 27	99.39 54	93.31 99	98.88 159	98.75 115

APD-MVS		95.00 110	94.69 141	95.93 66	97.38 149	90.88 102	94.59 139	97.81 135	89.22 214	95.46 194	96.17 244	93.42 110	99.34 70	89.30 244	98.87 162	97.56 279
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
OMC-MVS		94.22 162	93.69 193	95.81 73	97.25 156	91.27 93	92.27 265	97.40 179	87.10 286	94.56 250	95.42 293	93.74 99	98.11 277	86.62 322	98.85 163	98.06 204

SR-MVS-dyc-post		96.84 14	96.60 33	97.56 13	98.07 92	95.27 9	96.37 51	98.12 76	95.66 42	97.00 88	97.03 161	94.85 69	99.42 37	93.49 87	98.84 164	98.00 213

RE-MVS-def			96.66 27		98.07 92	95.27 9	96.37 51	98.12 76	95.66 42	97.00 88	97.03 161	95.40 35		93.49 87	98.84 164	98.00 213

v144192		93.20 211	93.54 201	92.16 282	96.05 284	78.26 408	91.95 276	97.14 204	84.98 351	95.96 156	96.11 249	87.08 276	99.04 122	93.79 75	98.84 164	99.17 46

v1921920		93.26 204	93.61 197	92.19 278	96.04 288	78.31 407	91.88 284	97.24 198	85.17 342	96.19 147	96.19 240	86.76 284	99.05 119	94.18 64	98.84 164	99.22 42

DP-MVS		95.62 76	95.84 78	94.97 118	97.16 163	88.62 148	94.54 146	97.64 152	96.94 19	96.58 116	97.32 128	93.07 125	98.72 175	90.45 198	98.84 164	97.57 277

VDDNet		94.03 171	94.27 169	93.31 213	98.87 26	82.36 305	95.51 101	91.78 427	97.19 15	96.32 132	98.60 27	84.24 311	98.75 169	87.09 314	98.83 169	98.81 102

CPTT-MVS		94.74 122	94.12 174	96.60 46	98.15 87	93.01 59	95.84 84	97.66 151	89.21 215	93.28 303	95.46 289	88.89 233	98.98 128	89.80 228	98.82 170	97.80 252

ACMMP++_ref															98.82 170

usedtu_dtu_shiyan2		93.15 213	92.40 246	95.41 95	98.56 49	90.53 111	94.71 133	94.14 363	92.10 115	93.73 282	96.94 168	89.66 225	97.77 324	72.97 498	98.81 172	97.92 233

KinetiMVS		95.09 107	95.40 101	94.15 164	97.42 148	84.35 256	93.91 175	96.69 250	94.41 60	96.67 109	97.25 135	87.67 260	99.14 102	95.78 29	98.81 172	98.97 73

fmvsm_s_conf0.1_n_2		94.38 148	94.78 136	93.19 220	97.07 171	81.72 316	91.97 275	97.51 171	87.05 287	97.31 67	97.92 67	88.29 246	98.15 273	97.10 6	98.81 172	99.70 5

v2v482		93.29 202	93.63 195	92.29 270	96.35 250	78.82 395	91.77 292	96.28 277	88.45 238	95.70 179	96.26 233	86.02 294	98.90 140	93.02 112	98.81 172	99.14 49

fmvsm_s_conf0.5_n_8		94.70 125	95.34 105	92.78 244	96.77 199	81.50 321	92.64 240	98.50 21	91.51 148	97.22 75	97.93 62	88.07 251	98.45 234	96.62 16	98.80 176	98.39 169

MVSMamba_PlusPlus		94.82 119	95.89 74	91.62 308	97.82 115	78.88 393	96.52 40	97.60 158	97.14 16	94.23 259	98.48 34	87.01 277	99.71 2	95.43 40	98.80 176	96.28 366

USDC		89.02 359	89.08 343	88.84 424	95.07 349	74.50 467	88.97 402	96.39 272	73.21 491	93.27 304	96.28 230	82.16 337	96.39 416	77.55 445	98.80 176	95.62 404

LoFTR		90.05 332	89.57 337	91.50 315	93.73 398	91.47 90	90.72 329	89.37 449	81.71 410	97.13 79	96.40 216	74.09 433	92.38 485	84.18 367	98.79 179	90.63 503

tttt0517		89.81 339	88.90 350	92.55 259	97.00 178	79.73 365	95.03 123	83.65 507	89.88 197	95.30 203	94.79 329	53.64 520	99.39 54	91.99 145	98.79 179	98.54 149

PMVS	87.21 14	94.97 111	95.33 107	93.91 178	98.97 20	97.16 2	95.54 100	95.85 298	96.47 27	93.40 296	97.46 107	95.31 41	95.47 440	86.18 333	98.78 181	89.11 509
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
fmvsm_s_conf0.5_n_2		94.25 160	94.63 148	93.10 223	96.65 209	81.75 315	91.72 293	97.25 196	86.93 291	97.20 76	97.67 86	88.44 244	98.14 276	97.06 9	98.77 182	99.42 24

TinyColmap		92.00 267	92.76 227	89.71 400	95.62 320	77.02 432	90.72 329	96.17 287	87.70 265	95.26 210	96.29 228	92.54 140	96.45 414	81.77 396	98.77 182	95.66 401

LuminaMVS		93.43 196	93.18 213	94.16 163	97.32 154	85.29 244	93.36 200	93.94 371	88.09 252	97.12 81	96.43 212	80.11 357	98.98 128	93.53 85	98.76 184	98.21 189

VortexMVS		92.13 262	92.56 239	90.85 357	94.54 371	76.17 449	92.30 263	96.63 257	86.20 307	96.66 111	96.79 182	79.87 360	98.16 271	91.27 171	98.76 184	98.24 185

v1240		93.29 202	93.71 192	92.06 286	96.01 289	77.89 414	91.81 289	97.37 180	85.12 345	96.69 108	96.40 216	86.67 285	99.07 118	94.51 54	98.76 184	99.22 42

DeepPCF-MVS	90.46 6	94.20 163	93.56 200	96.14 56	95.96 291	92.96 60	89.48 386	97.46 175	85.14 344	96.23 141	95.42 293	93.19 118	98.08 282	90.37 204	98.76 184	97.38 298

FE-MVSNET		92.02 266	92.22 253	91.41 321	96.63 217	79.08 388	91.53 297	96.84 237	85.52 334	95.16 221	96.14 245	83.97 314	97.50 347	85.48 342	98.75 188	97.64 270

Anonymous20231206		88.77 369	88.29 367	90.20 383	96.31 255	78.81 396	89.56 383	93.49 387	74.26 484	92.38 349	95.58 284	82.21 335	95.43 442	72.07 502	98.75 188	96.34 359

fmvsm_l_conf0.5_n_9		94.51 137	95.11 121	92.72 246	96.70 205	83.14 284	91.91 281	97.89 122	88.44 239	97.30 68	97.57 93	91.60 164	97.54 344	95.82 28	98.74 190	97.47 285

BP-MVS1		91.77 271	91.10 290	93.75 186	96.42 239	83.40 273	94.10 165	91.89 424	91.27 155	93.36 297	94.85 324	64.43 490	99.29 82	94.88 49	98.74 190	98.56 148

E5new		94.50 138	95.15 114	92.55 259	97.04 172	80.27 341	92.96 217	98.25 46	90.18 188	95.77 167	97.45 108	94.85 69	98.59 202	91.16 173	98.73 192	98.79 106

E6new		94.50 138	95.15 114	92.55 259	97.04 172	80.28 339	92.96 217	98.25 46	90.18 188	95.76 170	97.45 108	94.86 67	98.59 202	91.16 173	98.73 192	98.79 106

E6		94.50 138	95.15 114	92.55 259	97.04 172	80.28 339	92.96 217	98.25 46	90.18 188	95.76 170	97.45 108	94.86 67	98.59 202	91.16 173	98.73 192	98.79 106

E5		94.50 138	95.15 114	92.55 259	97.04 172	80.27 341	92.96 217	98.25 46	90.18 188	95.77 167	97.45 108	94.85 69	98.59 202	91.16 173	98.73 192	98.79 106

test_fmvsmvis_n_1920		95.08 108	95.40 101	94.13 167	96.66 208	87.75 176	93.44 197	98.49 23	85.57 330	98.27 23	97.11 153	94.11 93	97.75 328	96.26 20	98.72 196	96.89 328

casdiffmvs_mvg		95.10 106	95.62 89	93.53 201	96.25 264	83.23 279	92.66 238	98.19 61	93.06 90	97.49 55	97.15 148	94.78 72	98.71 182	92.27 137	98.72 196	98.65 132
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SIFT-PCN-Cal		87.04 422	86.65 415	88.22 441	90.09 502	90.20 116	83.84 509	85.36 490	85.16 343	91.83 371	91.84 443	78.22 384	87.02 530	74.79 478	98.71 198	87.44 520

SR-MVS		96.70 26	96.42 38	97.54 14	98.05 94	94.69 15	96.13 71	98.07 86	95.17 48	96.82 99	96.73 190	95.09 55	99.43 36	92.99 114	98.71 198	98.50 153

UGNet		93.08 214	92.50 241	94.79 131	93.87 393	87.99 168	95.07 121	94.26 360	90.64 174	87.33 478	97.67 86	86.89 282	98.49 225	88.10 293	98.71 198	97.91 235
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
LFMVS		91.33 285	91.16 288	91.82 297	96.27 261	79.36 380	95.01 124	85.61 488	96.04 39	94.82 240	97.06 159	72.03 451	98.46 233	84.96 355	98.70 201	97.65 269

HPM-MVS++		95.02 109	94.39 158	96.91 40	97.88 111	93.58 50	94.09 166	96.99 218	91.05 161	92.40 348	95.22 305	91.03 190	99.25 90	92.11 139	98.69 202	97.90 236

DVP-MVS++		95.93 63	96.34 45	94.70 135	96.54 225	86.66 204	98.45 4	98.22 58	93.26 87	97.54 50	97.36 121	93.12 121	99.38 63	93.88 72	98.68 203	98.04 208

PC_three_1452									75.31 476	95.87 163	95.75 273	92.93 130	96.34 421	87.18 312	98.68 203	98.04 208

miper_lstm_enhance		89.90 336	89.80 330	90.19 384	91.37 468	77.50 422	83.82 511	95.00 333	84.84 354	93.05 321	94.96 317	76.53 420	95.20 450	89.96 226	98.67 205	97.86 243

FMVSNet2		92.78 230	92.73 230	92.95 229	95.40 332	81.98 311	94.18 159	95.53 313	88.63 229	96.05 152	97.37 116	81.31 347	98.81 157	87.38 310	98.67 205	98.06 204

APD_test1		95.91 64	95.42 100	97.36 26	98.82 30	96.62 6	95.64 92	97.64 152	93.38 85	95.89 162	97.23 138	93.35 112	97.66 335	88.20 287	98.66 207	97.79 253

ArgMatch-SfM		91.28 288	90.08 324	94.88 125	95.22 340	92.66 68	89.81 373	94.51 353	79.15 444	95.27 208	93.71 379	78.33 380	95.52 436	86.11 334	98.63 208	96.46 354

fmvsm_s_conf0.5_n_3		95.20 102	95.95 68	92.94 231	96.60 219	82.18 309	93.13 208	98.39 32	91.44 151	97.16 77	97.68 84	93.03 128	97.82 316	97.54 2	98.63 208	98.81 102

DeepC-MVS_fast	89.96 7	93.73 182	93.44 204	94.60 145	96.14 275	87.90 172	93.36 200	97.14 204	85.53 331	93.90 275	95.45 290	91.30 178	98.59 202	89.51 238	98.62 210	97.31 301
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OPU-MVS				95.15 112	96.84 191	89.43 128	95.21 114				95.66 279	93.12 121	98.06 288	86.28 332	98.61 211	97.95 223

114514_t		90.51 308	89.80 330	92.63 253	98.00 102	82.24 308	93.40 198	97.29 193	65.84 532	89.40 436	94.80 328	86.99 278	98.75 169	83.88 372	98.61 211	96.89 328

SSC-MVS		90.16 324	92.96 219	81.78 514	97.88 111	48.48 551	90.75 327	87.69 465	96.02 40	96.70 107	97.63 90	85.60 301	97.80 319	85.73 339	98.60 213	99.06 60

patch_mono-2		92.46 247	92.72 232	91.71 303	96.65 209	78.91 392	88.85 406	97.17 202	83.89 372	92.45 345	96.76 185	89.86 223	97.09 383	90.24 213	98.59 214	99.12 53

dcpmvs_2		93.96 175	95.01 126	90.82 360	97.60 134	74.04 474	93.68 185	98.85 9	89.80 199	97.82 36	97.01 164	91.14 186	99.21 93	90.56 193	98.59 214	99.19 45

CDPH-MVS		92.67 236	91.83 268	95.18 111	96.94 181	88.46 156	90.70 331	97.07 212	77.38 457	92.34 354	95.08 313	92.67 138	98.88 143	85.74 338	98.57 216	98.20 191

SIFT-CM-Cal		87.51 406	86.76 413	89.76 397	91.48 465	93.30 55	84.73 492	84.04 503	85.53 331	91.66 375	92.58 417	77.01 411	88.75 514	75.29 470	98.56 217	87.24 523

MatchFormer		85.84 438	85.60 435	86.56 471	90.63 487	87.98 170	89.85 370	83.79 506	72.98 494	95.69 182	94.88 323	69.40 463	87.92 518	74.60 479	98.55 218	83.77 535

c3_l		91.32 286	91.42 278	91.00 347	92.29 434	76.79 438	87.52 435	96.42 271	85.76 324	94.72 246	93.89 371	82.73 330	98.16 271	90.93 184	98.55 218	98.04 208

test_prior2							90.21 354		89.33 211	90.77 400	94.81 326	90.41 207		88.21 286	98.55 218

LCM-MVSNet-Re		94.20 163	94.58 150	93.04 224	95.91 295	83.13 285	93.79 180	99.19 5	92.00 117	98.84 8	98.04 52	93.64 101	99.02 124	81.28 405	98.54 221	96.96 324

ALIKED-MNN		88.42 377	87.16 399	92.21 276	93.47 402	93.93 35	92.87 228	95.20 327	71.10 507	87.62 473	93.76 377	77.41 398	91.34 493	74.50 482	98.53 222	91.36 494

SymmetryMVS		93.26 204	92.36 248	95.97 61	97.13 167	90.84 104	94.70 134	91.61 430	90.98 162	93.22 310	95.73 274	78.94 369	99.12 106	90.38 201	98.53 222	97.97 221

Patchmatch-RL test		88.81 367	88.52 359	89.69 401	95.33 337	79.94 355	86.22 470	92.71 403	78.46 451	95.80 166	94.18 359	66.25 480	95.33 446	89.22 250	98.53 222	93.78 460

Anonymous202405211		92.58 241	92.50 241	92.83 240	96.55 224	83.22 281	92.43 252	91.64 429	94.10 65	95.59 186	96.64 196	81.88 344	97.50 347	85.12 350	98.52 225	97.77 257

CNVR-MVS		94.58 133	94.29 165	95.46 93	96.94 181	89.35 132	91.81 289	96.80 240	89.66 203	93.90 275	95.44 291	92.80 135	98.72 175	92.74 122	98.52 225	98.32 176

HQP_MVS		94.26 156	93.93 182	95.23 107	97.71 125	88.12 164	94.56 143	97.81 135	91.74 136	93.31 300	95.59 281	86.93 280	98.95 136	89.26 248	98.51 227	98.60 144

plane_prior5								97.81 135					98.95 136	89.26 248	98.51 227	98.60 144

baseline		94.26 156	94.80 133	92.64 250	96.08 281	80.99 332	93.69 184	98.04 98	90.80 169	94.89 238	96.32 226	93.19 118	98.48 230	91.68 158	98.51 227	98.43 160

test_fmvsm_n_1920		94.72 123	94.74 139	94.67 139	96.30 257	88.62 148	93.19 206	98.07 86	85.63 328	97.08 82	97.35 124	90.86 193	97.66 335	95.70 30	98.48 230	97.74 263

fmvsm_s_conf0.5_n_5		94.50 138	94.80 133	93.60 194	96.80 195	84.93 248	92.81 229	97.59 160	85.27 338	96.85 98	97.29 130	91.48 172	98.05 289	96.67 15	98.47 231	97.83 247

AstraMVS		92.75 232	92.73 230	92.79 243	97.02 176	81.48 322	92.88 226	90.62 441	87.99 255	96.48 118	96.71 192	82.02 340	98.48 230	92.44 133	98.46 232	98.40 168

thisisatest0530		88.69 372	87.52 385	92.20 277	96.33 253	79.36 380	92.81 229	84.01 504	86.44 299	93.67 284	92.68 414	53.62 521	99.25 90	89.65 237	98.45 233	98.00 213

ArgMatch-Sym		90.98 294	89.75 333	94.68 137	95.17 346	92.64 69	89.09 399	93.46 388	78.60 450	95.11 225	92.37 427	80.44 354	95.24 449	85.04 354	98.44 234	96.18 373

viewmacassd2359aftdt		93.83 179	94.36 162	92.24 274	96.45 235	79.58 371	91.60 295	97.96 109	89.14 216	95.05 230	97.09 156	93.69 100	98.48 230	89.79 229	98.43 235	98.65 132

train_agg		92.71 234	91.83 268	95.35 97	96.45 235	89.46 126	90.60 335	96.92 223	79.37 439	90.49 405	94.39 349	91.20 182	98.88 143	88.66 272	98.43 235	97.72 264

E4		94.00 173	94.53 154	92.42 269	96.78 198	79.99 353	91.33 305	98.16 70	89.69 201	95.27 208	97.16 145	93.94 98	98.64 193	89.99 224	98.42 237	98.61 143

fmvsm_l_conf0.5_n_3		95.19 103	95.36 103	94.68 137	96.79 197	87.49 179	93.05 211	98.38 33	87.21 278	96.59 115	97.76 80	94.20 90	98.11 277	95.90 26	98.40 238	98.42 161

GeoE		94.55 135	94.68 145	94.15 164	97.23 158	85.11 246	94.14 163	97.34 187	88.71 228	95.26 210	95.50 287	94.65 76	99.12 106	90.94 183	98.40 238	98.23 186

ZD-MVS					97.23 158	90.32 113		97.54 165	84.40 363	94.78 242	95.79 267	92.76 136	99.39 54	88.72 270	98.40 238

test9_res														88.16 291	98.40 238	97.83 247

TSAR-MVS + GP.		93.07 217	92.41 245	95.06 114	95.82 302	90.87 103	90.97 317	92.61 408	88.04 254	94.61 249	93.79 376	88.08 250	97.81 318	89.41 241	98.39 242	96.50 350

VNet		92.67 236	92.96 219	91.79 298	96.27 261	80.15 345	91.95 276	94.98 334	92.19 111	94.52 252	96.07 251	87.43 266	97.39 359	84.83 356	98.38 243	97.83 247

GBi-Net		93.21 209	92.96 219	93.97 173	95.40 332	84.29 257	95.99 75	96.56 262	88.63 229	95.10 226	98.53 30	81.31 347	98.98 128	86.74 317	98.38 243	98.65 132

test1		93.21 209	92.96 219	93.97 173	95.40 332	84.29 257	95.99 75	96.56 262	88.63 229	95.10 226	98.53 30	81.31 347	98.98 128	86.74 317	98.38 243	98.65 132

FMVSNet3		90.78 298	90.32 318	92.16 282	93.03 416	79.92 356	92.54 244	94.95 335	86.17 310	95.10 226	96.01 255	69.97 461	98.75 169	86.74 317	98.38 243	97.82 250

MVS_111021_HR		93.63 184	93.42 206	94.26 161	96.65 209	86.96 194	89.30 393	96.23 281	88.36 244	93.57 287	94.60 338	93.45 107	97.77 324	90.23 214	98.38 243	98.03 211

guyue		92.60 239	92.62 236	92.52 265	96.73 202	81.00 331	93.00 214	91.83 426	88.28 245	96.38 125	96.23 235	80.71 353	98.37 245	92.06 144	98.37 248	98.20 191

agg_prior2														87.06 315	98.36 249	97.98 217

TSAR-MVS + MP.		94.96 112	94.75 137	95.57 87	98.86 27	88.69 145	96.37 51	96.81 239	85.23 339	94.75 243	97.12 152	91.85 158	99.40 51	93.45 92	98.33 250	98.62 142
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
pmmvs-eth3d		91.54 279	90.73 304	93.99 171	95.76 309	87.86 174	90.83 323	93.98 370	78.23 453	94.02 270	96.22 236	82.62 333	96.83 399	86.57 323	98.33 250	97.29 302

mamba_0408		93.60 187	93.72 189	93.27 216	96.65 209	82.79 294	88.81 409	97.68 148	90.62 177	95.19 218	96.01 255	91.54 170	99.08 112	88.63 273	98.32 252	97.93 228

SSM_04072		93.25 207	93.72 189	91.84 295	96.65 209	82.79 294	88.81 409	97.68 148	90.62 177	95.19 218	96.01 255	91.54 170	94.81 458	88.63 273	98.32 252	97.93 228

SSM_0407		94.23 161	94.56 152	93.24 218	96.65 209	82.79 294	93.66 186	97.84 130	91.46 149	95.19 218	96.56 205	92.50 144	98.99 127	88.83 264	98.32 252	97.93 228

casdiffmvs		94.32 154	94.80 133	92.85 239	96.05 284	81.44 323	92.35 257	98.05 92	91.53 145	95.75 174	96.80 181	93.35 112	98.49 225	91.01 182	98.32 252	98.64 138
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
3Dnovator+	92.74 2	95.86 68	95.77 83	96.13 57	96.81 194	90.79 106	96.30 65	97.82 134	96.13 35	94.74 244	97.23 138	91.33 176	99.16 99	93.25 104	98.30 256	98.46 157

MVS_111021_LR		93.66 183	93.28 210	94.80 130	96.25 264	90.95 100	90.21 354	95.43 317	87.91 256	93.74 281	94.40 348	92.88 133	96.38 417	90.39 200	98.28 257	97.07 314

CANet		92.38 250	91.99 261	93.52 203	93.82 396	83.46 272	91.14 310	97.00 216	89.81 198	86.47 482	94.04 363	87.90 257	99.21 93	89.50 239	98.27 258	97.90 236

EI-MVSNet		92.99 218	93.26 212	92.19 278	92.12 443	79.21 386	92.32 260	94.67 349	91.77 134	95.24 214	95.85 262	87.14 274	98.49 225	91.99 145	98.26 259	98.86 94

MVSTER		89.32 349	88.75 353	91.03 344	90.10 501	76.62 444	90.85 322	94.67 349	82.27 401	95.24 214	95.79 267	61.09 506	98.49 225	90.49 197	98.26 259	97.97 221

SIFT-ConvMatch		87.94 390	87.21 396	90.11 385	91.67 460	93.60 49	85.55 482	83.12 514	86.48 296	92.15 362	92.98 400	78.11 388	88.58 515	76.60 457	98.25 261	88.14 516

MSLP-MVS++		93.25 207	93.88 183	91.37 324	96.34 251	82.81 293	93.11 209	97.74 143	89.37 210	94.08 265	95.29 303	90.40 208	96.35 419	90.35 205	98.25 261	94.96 425

LF4IMVS		92.72 233	92.02 260	94.84 128	95.65 316	91.99 79	92.92 223	96.60 258	85.08 347	92.44 346	93.62 382	86.80 283	96.35 419	86.81 316	98.25 261	96.18 373

viewdifsd2359ckpt07		93.63 184	94.33 164	91.55 311	96.19 270	77.86 415	90.11 361	97.74 143	90.76 170	96.11 150	96.61 200	94.37 87	98.27 255	88.82 266	98.23 264	98.51 152

SSM_0404		94.38 148	94.69 141	93.43 207	97.16 163	83.23 279	93.95 173	97.84 130	91.46 149	95.70 179	96.56 205	92.50 144	99.08 112	88.83 264	98.23 264	97.98 217

EI-MVSNet-UG-set		94.35 152	94.27 169	94.59 146	92.46 429	85.87 231	92.42 253	94.69 347	93.67 80	96.13 148	95.84 264	91.20 182	98.86 147	93.78 76	98.23 264	99.03 62

PM-MVS		93.33 201	92.67 235	95.33 99	96.58 221	94.06 25	92.26 266	92.18 415	85.92 316	96.22 142	96.61 200	85.64 300	95.99 429	90.35 205	98.23 264	95.93 386

EI-MVSNet-Vis-set		94.36 151	94.28 167	94.61 142	92.55 426	85.98 226	92.44 251	94.69 347	93.70 77	96.12 149	95.81 266	91.24 179	98.86 147	93.76 79	98.22 268	98.98 70

V42		93.43 196	93.58 198	92.97 227	95.34 336	81.22 328	92.67 237	96.49 267	87.25 276	96.20 144	96.37 223	87.32 268	98.85 149	92.39 135	98.21 269	98.85 97

TAMVS		90.16 324	89.05 344	93.49 205	96.49 232	86.37 212	90.34 349	92.55 409	80.84 424	92.99 323	94.57 341	81.94 343	98.20 264	73.51 493	98.21 269	95.90 389

K. test v3		93.37 198	93.27 211	93.66 191	98.05 94	82.62 301	94.35 149	86.62 474	96.05 38	97.51 54	98.85 17	76.59 419	99.65 4	93.21 105	98.20 271	98.73 120

DELS-MVS		92.05 265	92.16 254	91.72 302	94.44 374	80.13 347	87.62 429	97.25 196	87.34 274	92.22 358	93.18 395	89.54 227	98.73 174	89.67 235	98.20 271	96.30 364
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
SIFT-UM-Cal		87.93 391	87.42 389	89.44 405	90.95 480	92.71 66	84.33 503	88.32 456	86.32 302	90.41 408	92.73 412	78.78 372	88.31 516	76.83 455	98.16 273	87.31 522

TAPA-MVS	88.58 10	92.49 246	91.75 270	94.73 133	96.50 231	89.69 122	92.91 224	97.68 148	78.02 454	92.79 332	94.10 361	90.85 194	97.96 302	84.76 358	98.16 273	96.54 343
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
LS3D		96.11 56	95.83 79	96.95 39	94.75 360	94.20 23	97.34 13	97.98 105	97.31 14	95.32 202	96.77 183	93.08 123	99.20 96	91.79 152	98.16 273	97.44 289

GDP-MVS		91.56 278	90.83 299	93.77 185	96.34 251	83.65 269	93.66 186	98.12 76	87.32 275	92.98 325	94.71 332	63.58 496	99.30 81	92.61 127	98.14 276	98.35 174

DP-MVS Recon		92.31 254	91.88 266	93.60 194	97.18 162	86.87 196	91.10 312	97.37 180	84.92 352	92.08 366	94.08 362	88.59 238	98.20 264	83.50 374	98.14 276	95.73 396

EG-PatchMatch MVS		94.54 136	94.67 146	94.14 166	97.87 113	86.50 206	92.00 274	96.74 246	88.16 251	96.93 92	97.61 91	93.04 127	97.90 305	91.60 160	98.12 278	98.03 211

PCF-MVS	84.52 17	89.12 354	87.71 382	93.34 211	96.06 283	85.84 232	86.58 461	97.31 190	68.46 523	93.61 286	93.89 371	87.51 265	98.52 222	67.85 522	98.11 279	95.66 401
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
3Dnovator	92.54 3	94.80 121	94.90 128	94.47 154	95.47 330	87.06 189	96.63 36	97.28 195	91.82 131	94.34 258	97.41 112	90.60 203	98.65 192	92.47 132	98.11 279	97.70 265

WBMVS		84.00 457	83.48 456	85.56 483	92.71 422	61.52 535	83.82 511	89.38 448	79.56 437	90.74 401	93.20 394	48.21 526	97.28 364	75.63 468	98.10 281	97.88 239

PMMVS2		81.31 481	83.44 457	74.92 525	90.52 490	46.49 554	69.19 542	85.23 495	84.30 366	87.95 467	94.71 332	76.95 412	84.36 541	64.07 532	98.09 282	93.89 458

ELoFTR		89.04 358	88.72 354	89.99 392	94.38 377	89.08 137	90.15 357	89.10 450	75.60 471	95.85 164	96.52 207	75.00 427	89.26 510	83.82 373	98.08 283	91.61 493

lessismore_v0				93.87 180	98.05 94	83.77 268		80.32 535		97.13 79	97.91 70	77.49 396	99.11 110	92.62 126	98.08 283	98.74 119

viewdifsd2359ckpt11		93.36 199	93.99 177	91.48 316	95.50 328	78.39 403	90.47 339	96.69 250	88.59 232	96.03 154	96.88 174	93.48 105	97.63 339	90.20 216	98.07 285	98.41 164

viewmsd2359difaftdt		93.36 199	93.99 177	91.48 316	95.50 328	78.39 403	90.47 339	96.69 250	88.59 232	96.03 154	96.88 174	93.48 105	97.63 339	90.20 216	98.07 285	98.41 164

new-patchmatchnet		88.97 363	90.79 302	83.50 506	94.28 379	55.83 546	85.34 486	93.56 384	86.18 309	95.47 192	95.73 274	83.10 323	96.51 410	85.40 343	98.06 287	98.16 196

plane_prior						88.12 164	93.01 212		88.98 219						98.06 287

PVSNet_BlendedMVS		90.35 317	89.96 326	91.54 313	94.81 356	78.80 397	90.14 358	96.93 221	79.43 438	88.68 455	95.06 314	86.27 291	98.15 273	80.27 413	98.04 289	97.68 267

fmvsm_l_conf0.5_n_a		93.59 188	93.63 195	93.49 205	96.10 279	85.66 237	92.32 260	96.57 261	81.32 418	95.63 184	97.14 149	90.19 211	97.73 331	95.37 44	98.03 290	97.07 314

CL-MVSNet_self_test		90.04 334	89.90 328	90.47 373	95.24 339	77.81 416	86.60 460	92.62 407	85.64 327	93.25 308	93.92 369	83.84 315	96.06 426	79.93 421	98.03 290	97.53 281

FMVSNet5		87.82 395	86.56 418	91.62 308	92.31 433	79.81 360	93.49 194	94.81 342	83.26 380	91.36 381	96.93 170	52.77 523	97.49 350	76.07 464	98.03 290	97.55 280

fmvsm_s_conf0.5_n_4		94.26 156	94.58 150	93.31 213	96.40 241	82.73 299	92.59 242	97.41 178	86.60 292	96.33 130	97.07 157	89.91 221	98.07 286	96.88 10	98.01 293	99.13 50

testing3-2		83.95 458	84.22 448	83.13 508	96.28 258	54.34 550	88.51 420	83.01 515	92.19 111	89.09 443	90.98 459	45.51 532	97.44 353	74.38 485	98.01 293	97.60 274

原ACMM1				92.87 238	96.91 185	84.22 260		97.01 215	76.84 464	89.64 431	94.46 347	88.00 254	98.70 183	81.53 401	98.01 293	95.70 399

SIFT-UMatch		87.96 389	87.52 385	89.29 410	91.48 465	92.84 63	85.46 484	83.94 505	87.47 271	91.86 370	92.92 402	76.78 417	87.35 523	79.73 424	98.00 296	87.69 518

fmvsm_l_conf0.5_n		93.79 180	93.81 184	93.73 188	96.16 272	86.26 216	92.46 249	96.72 247	81.69 411	95.77 167	97.11 153	90.83 195	97.82 316	95.58 34	97.99 297	97.11 309

v148		92.87 225	93.29 208	91.62 308	96.25 264	77.72 420	91.28 306	95.05 331	89.69 201	95.93 159	96.04 252	87.34 267	98.38 241	90.05 223	97.99 297	98.78 111

E2		93.53 189	93.96 179	92.25 272	96.39 242	79.76 363	91.06 315	98.05 92	88.58 234	94.71 247	96.64 196	93.08 123	98.57 208	89.16 252	97.97 299	98.42 161

E3		93.53 189	93.96 179	92.25 272	96.39 242	79.76 363	91.06 315	98.05 92	88.58 234	94.71 247	96.64 196	93.07 125	98.57 208	89.16 252	97.97 299	98.42 161

WB-MVS		89.44 347	92.15 256	81.32 515	97.73 123	48.22 552	89.73 376	87.98 463	95.24 47	96.05 152	96.99 165	85.18 304	96.95 391	82.45 389	97.97 299	98.78 111

ITE_SJBPF				95.95 63	97.34 152	93.36 54		96.55 265	91.93 120	94.82 240	95.39 298	91.99 155	97.08 384	85.53 341	97.96 302	97.41 291

test12				94.43 156	95.95 292	86.75 200		96.24 280		89.76 429		89.79 224	98.79 161		97.95 303	97.75 262

MCST-MVS		92.91 221	92.51 240	94.10 168	97.52 139	85.72 235	91.36 304	97.13 206	80.33 427	92.91 329	94.24 355	91.23 180	98.72 175	89.99 224	97.93 304	97.86 243

CDS-MVSNet		89.55 343	88.22 373	93.53 201	95.37 335	86.49 207	89.26 394	93.59 382	79.76 433	91.15 391	92.31 429	77.12 404	98.38 241	77.51 446	97.92 305	95.71 397
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
旧先验1					96.20 268	84.17 262		94.82 340			95.57 285	89.57 226			97.89 306	96.32 363

reproduce_monomvs		87.13 419	86.90 407	87.84 452	90.92 481	68.15 509	91.19 308	93.75 376	85.84 321	94.21 261	95.83 265	42.99 540	97.10 382	89.46 240	97.88 307	98.26 184

alignmvs		93.26 204	92.85 224	94.50 151	95.70 311	87.45 180	93.45 196	95.76 299	91.58 141	95.25 213	92.42 426	81.96 342	98.72 175	91.61 159	97.87 308	97.33 300

testgi		90.38 315	91.34 282	87.50 455	97.49 141	71.54 493	89.43 388	95.16 329	88.38 241	94.54 251	94.68 334	92.88 133	93.09 479	71.60 507	97.85 309	97.88 239

fmvsm_s_conf0.1_n		94.19 165	94.41 157	93.52 203	97.22 160	84.37 254	93.73 182	95.26 324	84.45 361	95.76 170	98.00 55	91.85 158	97.21 374	95.62 31	97.82 310	98.98 70

fmvsm_s_conf0.5_n		94.00 173	94.20 171	93.42 208	96.69 206	84.37 254	93.38 199	95.13 330	84.50 360	95.40 196	97.55 99	91.77 160	97.20 375	95.59 33	97.79 311	98.69 128

ALIKED-LG		89.78 341	88.57 358	93.39 209	93.97 388	95.11 11	94.30 153	95.57 311	79.81 430	93.27 304	94.93 319	72.44 443	92.52 484	75.11 475	97.77 312	92.53 485

balanced_ft_v1		92.65 238	93.17 214	91.10 341	94.47 373	77.32 427	96.67 34	96.70 249	88.23 247	93.70 283	97.16 145	83.33 319	99.41 43	90.51 196	97.76 313	96.57 342

PMatch-SfM		91.76 272	90.58 310	95.30 103	95.64 318	91.67 88	89.49 385	94.79 344	84.45 361	96.31 133	96.02 254	71.68 452	97.26 369	89.13 255	97.75 314	96.98 321

新几何1				93.17 222	97.16 163	87.29 182		94.43 354	67.95 524	91.29 383	94.94 318	86.97 279	98.23 261	81.06 409	97.75 314	93.98 456

viewmanbaseed2359cas		93.08 214	93.43 205	92.01 290	95.69 312	79.29 382	91.15 309	97.70 147	87.45 272	94.18 262	96.12 247	92.31 147	98.37 245	88.58 276	97.73 316	98.38 170

ETV-MVS		92.99 218	92.74 228	93.72 189	95.86 299	86.30 215	92.33 259	97.84 130	91.70 139	92.81 330	86.17 508	92.22 150	99.19 97	88.03 298	97.73 316	95.66 401

HQP3-MVS								97.31 190							97.73 316

HQP-MVS		92.09 263	91.49 277	93.88 179	96.36 247	84.89 249	91.37 301	97.31 190	87.16 281	88.81 447	93.40 388	84.76 308	98.60 200	86.55 325	97.73 316	98.14 200

viewdifsd2359ckpt09		92.60 239	92.34 250	93.36 210	95.94 294	83.36 274	92.35 257	97.93 117	83.17 385	92.92 328	94.66 335	89.87 222	98.57 208	86.51 327	97.71 320	98.15 198

CANet_DTU		89.85 338	89.17 342	91.87 294	92.20 438	80.02 352	90.79 325	95.87 297	86.02 312	82.53 520	91.77 445	80.01 358	98.57 208	85.66 340	97.70 321	97.01 319

NCCC		94.08 169	93.54 201	95.70 80	96.49 232	89.90 120	92.39 255	96.91 226	90.64 174	92.33 355	94.60 338	90.58 204	98.96 134	90.21 215	97.70 321	98.23 186

Vis-MVSNet		95.50 83	95.48 94	95.56 88	98.11 89	89.40 130	95.35 104	98.22 58	92.36 103	94.11 263	98.07 49	92.02 154	99.44 33	93.38 98	97.67 323	97.85 245
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MGCFI-Net		94.44 145	94.67 146	93.75 186	95.56 324	85.47 240	95.25 113	98.24 54	91.53 145	95.04 231	92.21 433	94.94 63	98.54 215	91.56 163	97.66 324	97.24 304

PRO-TEST		92.55 245	92.43 244	92.90 234	95.14 347	82.69 300	94.18 159	97.13 206	86.47 298	93.36 297	97.39 114	82.07 338	99.34 70	88.52 279	97.64 325	96.68 339

AdaColmap		91.63 276	91.36 280	92.47 267	95.56 324	86.36 213	92.24 268	96.27 278	88.88 223	89.90 425	92.69 413	91.65 163	98.32 249	77.38 448	97.64 325	92.72 482

EPNet_dtu		85.63 439	84.37 445	89.40 408	86.30 531	74.33 469	91.64 294	88.26 457	84.84 354	72.96 543	89.85 470	71.27 455	97.69 333	76.60 457	97.62 327	96.18 373
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs_AUTHOR		92.34 253	92.70 233	91.26 332	94.20 380	78.42 400	89.12 398	97.60 158	87.16 281	93.17 315	95.50 287	88.66 237	97.57 343	91.30 170	97.61 328	97.79 253

XVG-OURS		94.72 123	94.12 174	96.50 50	98.00 102	94.23 22	91.48 300	98.17 67	90.72 171	95.30 203	96.47 209	87.94 256	96.98 389	91.41 167	97.61 328	98.30 180

SIFT-NCM-Cal		87.99 388	87.39 391	89.77 396	92.16 442	93.98 34	86.51 464	82.96 516	85.99 313	91.10 393	92.99 398	80.00 359	87.11 526	77.21 450	97.60 330	88.22 514

sasdasda		94.59 131	94.69 141	94.30 159	95.60 321	87.03 190	95.59 93	98.24 54	91.56 143	95.21 216	92.04 438	94.95 61	98.66 189	91.45 165	97.57 331	97.20 306

canonicalmvs		94.59 131	94.69 141	94.30 159	95.60 321	87.03 190	95.59 93	98.24 54	91.56 143	95.21 216	92.04 438	94.95 61	98.66 189	91.45 165	97.57 331	97.20 306

PMatch-Up-SfM		92.38 250	91.36 280	95.46 93	96.22 267	92.32 73	89.61 379	95.31 322	85.08 347	96.71 106	96.12 247	75.90 422	97.27 367	89.73 233	97.54 333	96.78 335

viewcassd2359sk11		93.16 212	93.51 203	92.13 284	96.07 282	79.59 368	90.88 321	97.97 107	87.82 260	94.23 259	96.19 240	92.31 147	98.53 219	88.58 276	97.51 334	98.28 181

XXY-MVS		92.58 241	93.16 215	90.84 358	97.75 120	79.84 357	91.87 285	96.22 284	85.94 315	95.53 188	97.68 84	92.69 137	94.48 462	83.21 377	97.51 334	98.21 189

FA-MVS(test-final)		91.81 270	91.85 267	91.68 306	94.95 351	79.99 353	96.00 74	93.44 389	87.80 261	94.02 270	97.29 130	77.60 394	98.45 234	88.04 297	97.49 336	96.61 341

Effi-MVS+-dtu		93.90 178	92.60 238	97.77 3	94.74 363	96.67 5	94.00 169	95.41 318	89.94 195	91.93 369	92.13 436	90.12 215	98.97 133	87.68 304	97.48 337	97.67 268

OpenMVS	89.45 8	92.27 258	92.13 257	92.68 249	94.53 372	84.10 263	95.70 88	97.03 214	82.44 400	91.14 392	96.42 214	88.47 243	98.38 241	85.95 336	97.47 338	95.55 406

fmvsm_s_conf0.1_n_a		94.26 156	94.37 160	93.95 176	97.36 151	85.72 235	94.15 161	95.44 315	83.25 381	95.51 189	98.05 50	92.54 140	97.19 377	95.55 36	97.46 339	98.94 81

SIFT-NN-PointCN		86.59 430	85.79 431	88.99 418	90.15 499	92.46 72	84.96 490	82.76 518	83.11 386	88.70 453	92.34 428	77.62 393	87.10 527	75.03 476	97.44 340	87.42 521

ab-mvs		92.40 249	92.62 236	91.74 301	97.02 176	81.65 317	95.84 84	95.50 314	86.95 289	92.95 327	97.56 95	90.70 201	97.50 347	79.63 425	97.43 341	96.06 379

fmvsm_s_conf0.5_n_a		94.02 172	94.08 176	93.84 182	96.72 204	85.73 234	93.65 188	95.23 326	83.30 379	95.13 223	97.56 95	92.22 150	97.17 378	95.51 37	97.41 342	98.64 138

thisisatest0515		84.72 448	82.99 462	89.90 393	92.96 418	75.33 459	84.36 502	83.42 509	77.37 458	88.27 461	86.65 503	53.94 519	98.72 175	82.56 386	97.40 343	95.67 400

test222					96.95 180	85.27 245	88.83 407	93.61 381	65.09 534	90.74 401	94.85 324	84.62 310			97.36 344	93.91 457

API-MVS		91.52 280	91.61 272	91.26 332	94.16 381	86.26 216	94.66 137	94.82 340	91.17 159	92.13 364	91.08 458	90.03 220	97.06 387	79.09 434	97.35 345	90.45 504

SIFT-MNN		87.81 396	87.11 403	89.90 393	92.19 439	93.62 48	86.73 455	84.68 498	87.19 279	90.95 395	92.80 408	73.54 437	87.09 529	78.62 438	97.32 346	88.98 510

SIFT-NN-CMatch		86.64 429	85.79 431	89.18 416	91.21 473	93.07 56	84.60 498	80.33 534	84.07 368	89.10 440	91.58 451	78.69 374	87.33 524	75.28 472	97.28 347	87.13 526

usedtu_dtu_shiyan1		89.18 350	88.59 356	90.95 351	94.75 360	77.79 417	86.25 467	94.63 351	81.61 412	90.88 396	92.24 431	77.03 407	98.08 282	82.62 383	97.27 348	96.97 322

FE-MVSNET3		89.18 350	88.59 356	90.95 351	94.75 360	77.79 417	86.25 467	94.63 351	81.61 412	90.88 396	92.25 430	77.03 407	98.08 282	82.62 383	97.27 348	96.97 322

EIA-MVS		92.35 252	92.03 259	93.30 215	95.81 304	83.97 265	92.80 231	98.17 67	87.71 264	89.79 428	87.56 497	91.17 185	99.18 98	87.97 299	97.27 348	96.77 336

testdata				91.03 344	96.87 188	82.01 310		94.28 358	71.55 503	92.46 344	95.42 293	85.65 299	97.38 361	82.64 382	97.27 348	93.70 463

PatchmatchNet1														77.38 448	97.25 352	96.00 381
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
N_pmnet		88.90 365	87.25 395	93.83 183	94.40 376	93.81 44	84.73 492	87.09 470	79.36 441	93.26 306	92.43 425	79.29 366	91.68 490	77.50 447	97.22 353	96.00 381

testing3		83.66 460	82.52 465	87.08 460	95.84 300	65.84 522	89.80 375	77.17 545	88.17 250	90.84 399	88.63 488	30.95 552	98.11 277	84.05 368	97.19 354	97.28 303

ppachtmachnet_test		88.61 373	88.64 355	88.50 435	91.76 455	70.99 497	84.59 499	92.98 396	79.30 443	92.38 349	93.53 386	79.57 363	97.45 352	86.50 328	97.17 355	97.07 314

CNLPA		91.72 274	91.20 285	93.26 217	96.17 271	91.02 96	91.14 310	95.55 312	90.16 192	90.87 398	93.56 385	86.31 290	94.40 465	79.92 423	97.12 356	94.37 445

FE-MVS		89.06 357	88.29 367	91.36 325	94.78 358	79.57 372	96.77 29	90.99 434	84.87 353	92.96 326	96.29 228	60.69 508	98.80 160	80.18 416	97.11 357	95.71 397

icg_test_0407_2		91.18 290	91.92 265	88.94 421	95.19 342	76.72 439	84.66 497	96.89 227	85.92 316	93.55 288	94.50 343	91.06 187	92.99 481	88.49 281	97.07 358	97.10 310

IMVS_0407		92.28 255	92.83 225	90.63 369	95.19 342	76.72 439	92.79 232	96.89 227	85.92 316	93.55 288	94.50 343	91.06 187	98.07 286	88.49 281	97.07 358	97.10 310

IMVS_0404		90.67 303	91.06 291	89.50 403	95.19 342	76.72 439	86.58 461	96.89 227	85.92 316	89.17 439	94.50 343	85.77 295	94.67 459	88.49 281	97.07 358	97.10 310

IMVS_0403		92.20 260	92.70 233	90.69 365	95.19 342	76.72 439	92.39 255	96.89 227	85.92 316	93.66 285	94.50 343	90.18 212	98.24 259	88.49 281	97.07 358	97.10 310

jason		89.17 353	88.32 365	91.70 304	95.73 310	80.07 348	88.10 423	93.22 392	71.98 500	90.09 416	92.79 409	78.53 378	98.56 212	87.43 308	97.06 362	96.46 354
jason: jason.
RPSCF		95.58 80	94.89 130	97.62 8	97.58 136	96.30 7	95.97 78	97.53 168	92.42 100	93.41 293	97.78 75	91.21 181	97.77 324	91.06 179	97.06 362	98.80 104

cl22		89.02 359	88.50 360	90.59 371	89.76 505	76.45 446	86.62 459	94.03 365	82.98 390	92.65 337	92.49 421	72.05 450	97.53 345	88.93 260	97.02 364	97.78 256

miper_ehance_all_eth		90.48 309	90.42 314	90.69 365	91.62 462	76.57 445	86.83 451	96.18 286	83.38 378	94.06 267	92.66 415	82.20 336	98.04 291	89.79 229	97.02 364	97.45 287

miper_enhance_ethall		88.42 377	87.87 380	90.07 386	88.67 519	75.52 457	85.10 487	95.59 308	75.68 469	92.49 342	89.45 481	78.96 368	97.88 309	87.86 302	97.02 364	96.81 333

eth_miper_zixun_eth		90.72 300	90.61 307	91.05 342	92.04 446	76.84 437	86.91 448	96.67 254	85.21 340	94.41 254	93.92 369	79.53 364	98.26 256	89.76 231	97.02 364	98.06 204

QAPM		92.88 223	92.77 226	93.22 219	95.82 302	83.31 276	96.45 46	97.35 186	83.91 371	93.75 279	96.77 183	89.25 229	98.88 143	84.56 360	97.02 364	97.49 284

E3new		92.83 228	93.10 216	92.04 287	95.78 306	79.45 376	90.76 326	97.90 118	87.23 277	93.79 278	95.70 277	91.55 166	98.49 225	88.17 290	96.99 369	98.16 196

thres600view7		87.66 399	87.10 404	89.36 409	96.05 284	73.17 479	92.72 233	85.31 492	91.89 122	93.29 302	90.97 460	63.42 497	98.39 237	73.23 495	96.99 369	96.51 347

tt0805		95.42 90	95.93 71	93.86 181	98.75 36	88.47 155	97.68 9	94.29 357	96.48 26	95.38 197	93.63 381	94.89 66	97.94 304	95.38 43	96.92 371	95.17 415

test_yl		90.11 327	89.73 334	91.26 332	94.09 384	79.82 358	90.44 341	92.65 405	90.90 164	93.19 313	93.30 390	73.90 434	98.03 292	82.23 391	96.87 372	95.93 386

DCV-MVSNet		90.11 327	89.73 334	91.26 332	94.09 384	79.82 358	90.44 341	92.65 405	90.90 164	93.19 313	93.30 390	73.90 434	98.03 292	82.23 391	96.87 372	95.93 386

onestephybrid01		92.06 264	92.07 258	92.04 287	93.45 404	80.93 334	89.82 372	96.78 241	87.60 268	91.68 374	95.43 292	88.73 236	97.43 354	88.32 285	96.85 374	97.76 258

test_fmvs3		92.42 248	92.40 246	92.46 268	93.80 397	87.28 183	93.86 177	97.05 213	76.86 463	96.25 139	98.66 23	82.87 327	91.26 494	95.44 39	96.83 375	98.82 99

MSP-MVS		95.34 93	94.63 148	97.48 17	98.67 40	94.05 27	96.41 50	98.18 63	91.26 156	95.12 224	95.15 307	86.60 287	99.50 23	93.43 96	96.81 376	98.89 91
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
pmmvs5		87.87 393	87.14 400	90.07 386	93.26 409	76.97 436	88.89 404	92.18 415	73.71 487	88.36 459	93.89 371	76.86 416	96.73 404	80.32 412	96.81 376	96.51 347

PVSNet_Blended_VisFu		91.63 276	91.20 285	92.94 231	97.73 123	83.95 266	92.14 269	97.46 175	78.85 449	92.35 352	94.98 316	84.16 312	99.08 112	86.36 330	96.77 378	95.79 394

MVSFormer		92.18 261	92.23 252	92.04 287	94.74 363	80.06 349	97.15 15	97.37 180	88.98 219	88.83 445	92.79 409	77.02 409	99.60 9	96.41 18	96.75 379	96.46 354

lupinMVS		88.34 381	87.31 392	91.45 318	94.74 363	80.06 349	87.23 440	92.27 414	71.10 507	88.83 445	91.15 455	77.02 409	98.53 219	86.67 321	96.75 379	95.76 395

SP-MNN		89.68 342	89.55 338	90.06 389	90.43 495	88.06 166	89.60 380	92.13 419	86.42 301	89.57 433	92.55 418	78.14 387	87.91 519	90.35 205	96.74 381	94.22 449

ttmdpeth		86.91 426	86.57 417	87.91 450	89.68 507	74.24 471	91.49 299	87.09 470	79.84 429	89.46 435	97.86 73	65.42 484	91.04 495	81.57 400	96.74 381	98.44 159

diffmvs		91.74 273	91.93 264	91.15 340	93.06 414	78.17 409	88.77 412	97.51 171	86.28 304	92.42 347	93.96 368	88.04 253	97.46 351	90.69 191	96.67 383	97.82 250
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ALIKED-NN		85.96 436	84.14 449	91.44 320	91.73 457	93.37 52	90.32 350	93.65 379	67.84 525	82.08 522	92.92 402	72.88 440	90.01 502	69.17 518	96.64 384	90.93 499

SP-SuperGlue		91.30 287	91.15 289	91.75 300	91.06 475	90.99 99	90.32 350	93.55 385	90.63 176	91.17 389	93.82 375	79.84 361	88.92 513	93.30 100	96.63 385	95.34 413

DPM-MVS		89.35 348	88.40 362	92.18 281	96.13 277	84.20 261	86.96 447	96.15 289	75.40 474	87.36 477	91.55 452	83.30 320	98.01 296	82.17 393	96.62 386	94.32 447

hybridnocas07		91.51 281	91.66 271	91.04 343	93.14 412	78.03 410	88.75 414	96.92 223	85.97 314	91.63 377	95.31 302	87.67 260	97.31 362	88.97 259	96.61 387	97.79 253

test_fmvs2		90.62 307	90.40 315	91.29 330	91.93 450	85.46 241	92.70 236	96.48 268	74.44 480	94.91 237	97.59 92	75.52 424	90.57 497	93.44 93	96.56 388	97.84 246

thres100view900		87.35 411	86.89 408	88.72 427	96.14 275	73.09 481	93.00 214	85.31 492	92.13 114	93.26 306	90.96 461	63.42 497	98.28 251	71.27 509	96.54 389	94.79 434

tfpn200view9		87.05 421	86.52 420	88.67 428	95.77 307	72.94 483	91.89 282	86.00 480	90.84 166	92.61 338	89.80 472	63.93 493	98.28 251	71.27 509	96.54 389	94.79 434

thres400		87.20 416	86.52 420	89.24 415	95.77 307	72.94 483	91.89 282	86.00 480	90.84 166	92.61 338	89.80 472	63.93 493	98.28 251	71.27 509	96.54 389	96.51 347

CMPMVS	68.83 22	87.28 413	85.67 433	92.09 285	88.77 518	85.42 242	90.31 352	94.38 355	70.02 516	88.00 465	93.30 390	73.78 436	94.03 471	75.96 466	96.54 389	96.83 332
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
viewmamba		92.69 235	93.03 217	91.69 305	93.92 391	79.50 374	89.92 366	97.33 188	88.86 224	93.13 318	95.79 267	90.97 191	97.65 337	90.86 185	96.45 393	97.94 225

XFeat-MNN		80.76 488	79.73 492	83.85 503	79.29 549	82.86 292	76.90 534	83.32 512	69.86 517	92.27 356	87.53 499	57.82 512	84.65 538	74.17 488	96.44 394	84.03 534

SIFT-NN-UMatch		86.43 433	85.66 434	88.76 425	90.73 484	92.76 65	84.99 489	81.25 527	84.13 367	88.17 463	92.04 438	76.90 413	86.62 531	76.34 462	96.36 395	86.91 528

UWE-MVS		80.29 493	79.10 494	83.87 502	91.97 449	59.56 540	86.50 465	77.43 544	75.40 474	87.79 471	88.10 494	44.08 537	96.90 396	64.23 531	96.36 395	95.14 418

pmmvs4		88.95 364	87.70 383	92.70 247	94.30 378	85.60 238	87.22 441	92.16 417	74.62 479	89.75 430	94.19 358	77.97 391	96.41 415	82.71 381	96.36 395	96.09 377

MVStest1		84.79 447	84.06 451	86.98 463	77.73 551	74.76 461	91.08 314	85.63 485	77.70 455	96.86 95	97.97 59	41.05 547	88.24 517	92.22 138	96.28 398	97.94 225

SP-LightGlue		90.98 294	90.67 305	91.92 293	91.04 476	91.02 96	90.68 332	94.22 361	89.56 206	90.35 413	92.90 404	77.08 405	89.38 509	93.92 71	96.27 399	95.35 412

gbinet_0.2-2-1-0.02		88.14 386	86.86 409	91.99 291	90.70 485	80.51 337	87.36 439	93.01 395	83.45 377	90.38 410	82.42 532	72.73 441	98.54 215	85.40 343	96.27 399	96.90 326

Fast-Effi-MVS+-dtu		92.77 231	92.16 254	94.58 149	94.66 368	88.25 159	92.05 271	96.65 255	89.62 204	90.08 420	91.23 454	92.56 139	98.60 200	86.30 331	96.27 399	96.90 326

hybrid		91.14 291	91.24 284	90.83 359	93.15 410	77.49 423	88.76 413	96.87 233	84.51 359	91.25 387	95.23 304	87.14 274	97.25 370	88.05 295	96.24 402	97.76 258

viewdifsd2359ckpt13		92.57 243	92.48 243	92.83 240	95.60 321	82.35 307	91.80 291	97.49 173	85.04 349	93.14 316	95.41 296	90.94 192	98.25 257	86.68 320	96.24 402	97.87 242

MAR-MVS		90.32 320	88.87 352	94.66 141	94.82 355	91.85 82	94.22 157	94.75 345	80.91 421	87.52 476	88.07 495	86.63 286	97.87 312	76.67 456	96.21 404	94.25 448
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
viewmambaseed2359dif		90.77 299	90.81 300	90.64 368	93.46 403	77.04 431	88.83 407	96.29 276	80.79 425	92.21 360	95.11 310	88.99 231	97.28 364	85.39 345	96.20 405	97.59 275

AUN-MVS		90.05 332	88.30 366	95.32 101	96.09 280	90.52 112	92.42 253	92.05 422	82.08 404	88.45 458	92.86 405	65.76 482	98.69 185	88.91 262	96.07 406	96.75 338

hse-mvs2		92.24 259	91.20 285	95.38 96	96.16 272	90.65 109	92.52 245	92.01 423	89.23 212	93.95 272	92.99 398	76.88 414	98.69 185	91.02 180	96.03 407	96.81 333

dtuplus		90.63 306	90.59 309	90.74 363	93.85 395	77.43 425	89.01 401	96.16 288	81.42 415	92.77 333	95.54 286	88.59 238	97.28 364	81.99 394	96.00 408	97.50 283

PVSNet_Blended		88.74 370	88.16 376	90.46 375	94.81 356	78.80 397	86.64 457	96.93 221	74.67 478	88.68 455	89.18 485	86.27 291	98.15 273	80.27 413	96.00 408	94.44 444

F-COLMAP		92.28 255	91.06 291	95.95 63	97.52 139	91.90 81	93.53 192	97.18 201	83.98 370	88.70 453	94.04 363	88.41 245	98.55 214	80.17 417	95.99 410	97.39 296

xiu_mvs_v1_base_debu		91.47 282	91.52 274	91.33 327	95.69 312	81.56 318	89.92 366	96.05 292	83.22 382	91.26 384	90.74 463	91.55 166	98.82 152	89.29 245	95.91 411	93.62 466

xiu_mvs_v1_base		91.47 282	91.52 274	91.33 327	95.69 312	81.56 318	89.92 366	96.05 292	83.22 382	91.26 384	90.74 463	91.55 166	98.82 152	89.29 245	95.91 411	93.62 466

xiu_mvs_v1_base_debi		91.47 282	91.52 274	91.33 327	95.69 312	81.56 318	89.92 366	96.05 292	83.22 382	91.26 384	90.74 463	91.55 166	98.82 152	89.29 245	95.91 411	93.62 466

thres200		85.85 437	85.18 439	87.88 451	94.44 374	72.52 489	89.08 400	86.21 476	88.57 236	91.44 380	88.40 491	64.22 491	98.00 298	68.35 520	95.88 414	93.12 473

RRT-MVS		92.28 255	93.01 218	90.07 386	94.06 386	73.01 482	95.36 103	97.88 123	92.24 109	95.16 221	97.52 100	78.51 379	99.29 82	90.55 194	95.83 415	97.92 233

Patchmatch-test		86.10 435	86.01 428	86.38 476	90.63 487	74.22 472	89.57 382	86.69 473	85.73 325	89.81 427	92.83 406	65.24 487	91.04 495	77.82 444	95.78 416	93.88 459

dtuonly		84.38 451	85.24 438	81.80 513	87.13 527	58.46 543	81.58 523	92.71 403	74.41 481	85.68 489	92.62 416	78.17 386	92.13 488	79.15 433	95.73 417	94.82 431

h-mvs33		92.89 222	91.99 261	95.58 86	96.97 179	90.55 110	93.94 174	94.01 369	89.23 212	93.95 272	96.19 240	76.88 414	99.14 102	91.02 180	95.71 418	97.04 318

SIFT-NN-NCMNet		86.55 431	85.56 436	89.51 402	91.84 454	94.02 30	85.72 478	81.31 526	84.33 365	86.13 486	91.77 445	79.22 367	87.46 521	74.06 490	95.70 419	87.07 527

test_fmvs1_n		88.73 371	88.38 363	89.76 397	92.06 445	82.53 302	92.30 263	96.59 260	71.14 506	92.58 340	95.41 296	68.55 466	89.57 506	91.12 178	95.66 420	97.18 308

myMVS_eth3d28		80.97 485	80.42 486	82.62 510	93.35 406	58.25 544	84.70 496	85.62 487	86.31 303	84.04 505	85.20 517	46.00 530	94.07 470	62.93 535	95.65 421	95.53 407

cascas		87.02 423	86.28 427	89.25 414	91.56 464	76.45 446	84.33 503	96.78 241	71.01 509	86.89 481	85.91 509	81.35 346	96.94 392	83.09 378	95.60 422	94.35 446

XVG-OURS-SEG-HR		95.38 91	95.00 127	96.51 49	98.10 90	94.07 24	92.46 249	98.13 73	90.69 172	93.75 279	96.25 234	98.03 2	97.02 388	92.08 141	95.55 423	98.45 158

DSMNet-mixed		82.21 474	81.56 472	84.16 499	89.57 510	70.00 504	90.65 334	77.66 543	54.99 545	83.30 514	97.57 93	77.89 392	90.50 499	66.86 526	95.54 424	91.97 488

MVS_Test		92.57 243	93.29 208	90.40 376	93.53 401	75.85 453	92.52 245	96.96 219	88.73 226	92.35 352	96.70 193	90.77 196	98.37 245	92.53 130	95.49 425	96.99 320

MIMVSNet		87.13 419	86.54 419	88.89 423	96.05 284	76.11 450	94.39 148	88.51 454	81.37 417	88.27 461	96.75 187	72.38 445	95.52 436	65.71 529	95.47 426	95.03 423

Fast-Effi-MVS+		91.28 288	90.86 297	92.53 264	95.45 331	82.53 302	89.25 396	96.52 266	85.00 350	89.91 424	88.55 490	92.94 129	98.84 150	84.72 359	95.44 427	96.22 371

SP-DiffGlue		90.34 318	90.20 319	90.76 362	90.52 490	90.29 114	90.37 346	94.02 367	87.19 279	93.85 277	92.55 418	78.24 383	87.50 520	89.68 234	95.41 428	94.49 442

ET-MVSNet_ETH3D		86.15 434	84.27 447	91.79 298	93.04 415	81.28 325	87.17 443	86.14 477	79.57 436	83.65 509	88.66 487	57.10 513	98.18 267	87.74 303	95.40 429	95.90 389

BH-RMVSNet		90.47 310	90.44 313	90.56 372	95.21 341	78.65 399	89.15 397	93.94 371	88.21 248	92.74 335	94.22 356	86.38 288	97.88 309	78.67 437	95.39 430	95.14 418

CHOSEN 1792x2688		87.19 417	85.92 430	91.00 347	97.13 167	79.41 379	84.51 500	95.60 304	64.14 536	90.07 421	94.81 326	78.26 382	97.14 381	73.34 494	95.38 431	96.46 354

MASt3R-SfM		82.76 471	82.17 470	84.53 494	83.29 543	86.01 225	82.08 520	80.49 533	63.10 539	92.22 358	94.20 357	69.18 464	77.62 544	79.63 425	95.37 432	89.94 507

test_fmvs1		87.59 402	87.27 394	88.54 432	88.32 520	81.26 326	90.43 344	95.72 301	70.55 513	91.70 373	94.63 336	68.13 467	89.42 508	90.59 192	95.34 433	94.94 428

wanda-best-256-512		87.53 404	86.39 424	90.97 349	91.29 470	78.39 403	85.63 480	93.75 376	81.91 406	90.09 416	83.30 526	72.25 446	98.18 267	83.96 369	95.32 434	96.33 360

FE-blended-shiyan7		87.53 404	86.39 424	90.97 349	91.29 470	78.39 403	85.63 480	93.75 376	81.91 406	90.09 416	83.30 526	72.25 446	98.18 267	83.96 369	95.32 434	96.33 360

blended_shiyan6		88.42 377	87.43 388	91.40 322	92.37 430	79.43 378	87.41 437	93.91 374	82.51 397	91.17 389	85.44 513	74.34 431	98.24 259	84.38 364	95.32 434	96.53 345

usedtu_blend_shiyan5		89.08 356	88.33 364	91.34 326	91.29 470	79.59 368	94.02 167	97.13 206	90.07 193	90.09 416	83.30 526	72.25 446	98.10 280	81.45 402	95.32 434	96.33 360

Effi-MVS+		92.79 229	92.74 228	92.94 231	95.10 348	83.30 277	94.00 169	97.53 168	91.36 154	89.35 437	90.65 468	94.01 96	98.66 189	87.40 309	95.30 438	96.88 330

blended_shiyan8		88.43 376	87.44 387	91.40 322	92.37 430	79.45 376	87.43 436	93.92 373	82.51 397	91.24 388	85.42 514	74.35 430	98.23 261	84.43 363	95.28 439	96.52 346

dtuonlycased		90.11 327	90.39 316	89.28 412	97.09 170	72.61 487	85.75 477	95.27 323	81.57 414	94.42 253	94.89 320	90.47 205	96.81 401	78.74 435	95.27 440	98.41 164

MG-MVS		89.54 344	89.80 330	88.76 425	94.88 352	72.47 490	89.60 380	92.44 411	85.82 322	89.48 434	95.98 258	82.85 328	97.74 330	81.87 395	95.27 440	96.08 378

HyFIR lowres test		87.19 417	85.51 437	92.24 274	97.12 169	80.51 337	85.03 488	96.06 290	66.11 531	91.66 375	92.98 400	70.12 459	99.14 102	75.29 470	95.23 442	97.07 314

mvsmamba		90.24 322	89.43 339	92.64 250	95.52 326	82.36 305	96.64 35	92.29 413	81.77 408	92.14 363	96.28 230	70.59 457	99.10 111	84.44 362	95.22 443	96.47 353

BH-untuned		90.68 302	90.90 294	90.05 390	95.98 290	79.57 372	90.04 362	94.94 336	87.91 256	94.07 266	93.00 397	87.76 258	97.78 323	79.19 432	95.17 444	92.80 481

pmmvs3		80.83 487	78.96 496	86.45 473	87.23 526	77.48 424	84.87 491	82.31 520	63.83 537	85.03 495	89.50 480	49.66 524	93.10 478	73.12 497	95.10 445	88.78 513

testing222		80.54 491	78.53 499	86.58 470	92.54 428	68.60 508	86.24 469	82.72 519	83.78 374	82.68 519	84.24 521	39.25 549	95.94 430	60.25 537	95.09 446	95.20 414

TestfortrainingZip				93.68 190	95.25 338	86.20 219	96.32 56	96.38 273	92.81 92	92.13 364	93.87 374	87.28 269	98.61 197		95.07 447	96.23 370

mvs_anonymous		90.37 316	91.30 283	87.58 454	92.17 441	68.00 510	89.84 371	94.73 346	83.82 373	93.22 310	97.40 113	87.54 264	97.40 358	87.94 300	95.05 448	97.34 299

test_vis1_n		89.01 361	89.01 346	89.03 417	92.57 425	82.46 304	92.62 241	96.06 290	73.02 493	90.40 409	95.77 272	74.86 428	89.68 504	90.78 188	94.98 449	94.95 426

SIFT-NN		84.10 455	83.04 460	87.28 459	90.76 483	92.16 76	84.45 501	81.34 525	83.54 376	83.80 508	89.75 476	70.08 460	82.09 542	68.68 519	94.96 450	87.60 519

IterMVS-SCA-FT		91.65 275	91.55 273	91.94 292	93.89 392	79.22 385	87.56 432	93.51 386	91.53 145	95.37 199	96.62 199	78.65 375	98.90 140	91.89 149	94.95 451	97.70 265

test_vis3_rt		90.40 312	90.03 325	91.52 314	92.58 424	88.95 140	90.38 345	97.72 146	73.30 490	97.79 37	97.51 104	77.05 406	87.10 527	89.03 258	94.89 452	98.50 153

test-LLR		83.58 461	83.17 459	84.79 492	89.68 507	66.86 515	83.08 513	84.52 499	83.07 388	82.85 516	84.78 519	62.86 500	93.49 475	82.85 379	94.86 453	94.03 454

test-mter		81.21 483	80.01 491	84.79 492	89.68 507	66.86 515	83.08 513	84.52 499	73.85 486	82.85 516	84.78 519	43.66 538	93.49 475	82.85 379	94.86 453	94.03 454

PatchMatch-RL		89.18 350	88.02 378	92.64 250	95.90 296	92.87 62	88.67 418	91.06 433	80.34 426	90.03 422	91.67 448	83.34 318	94.42 464	76.35 461	94.84 455	90.64 502

OpenMVS_ROB	85.12 16	89.52 345	89.05 344	90.92 353	94.58 370	81.21 329	91.10 312	93.41 390	77.03 462	93.41 293	93.99 367	83.23 321	97.80 319	79.93 421	94.80 456	93.74 462

our_test_3		87.55 403	87.59 384	87.44 456	91.76 455	70.48 498	83.83 510	90.55 442	79.79 432	92.06 367	92.17 435	78.63 377	95.63 434	84.77 357	94.73 457	96.22 371

CHOSEN 280x420		80.04 495	77.97 503	86.23 479	90.13 500	74.53 466	72.87 539	89.59 446	66.38 530	76.29 539	85.32 516	56.96 514	95.36 443	69.49 517	94.72 458	88.79 512

IterMVS		90.18 323	90.16 320	90.21 382	93.15 410	75.98 452	87.56 432	92.97 397	86.43 300	94.09 264	96.40 216	78.32 381	97.43 354	87.87 301	94.69 459	97.23 305
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EMVS		80.35 492	80.28 489	80.54 517	84.73 539	69.07 506	72.54 540	80.73 531	87.80 261	81.66 527	81.73 533	62.89 499	89.84 503	75.79 467	94.65 460	82.71 538

PLC	85.34 15	90.40 312	88.92 348	94.85 127	96.53 228	90.02 118	91.58 296	96.48 268	80.16 428	86.14 485	92.18 434	85.73 297	98.25 257	76.87 454	94.61 461	96.30 364
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSDG		90.82 296	90.67 305	91.26 332	94.16 381	83.08 287	86.63 458	96.19 285	90.60 179	91.94 368	91.89 442	89.16 230	95.75 433	80.96 410	94.51 462	94.95 426

SP-NN		88.21 383	87.96 379	88.97 419	89.33 513	87.99 168	88.06 425	90.93 436	85.48 336	84.50 499	91.11 457	77.25 403	84.79 537	90.55 194	94.42 463	94.14 450

SD_0403		88.79 368	88.88 351	88.51 434	95.89 298	72.58 488	94.27 154	95.24 325	83.77 375	87.92 468	94.38 352	87.70 259	96.47 413	66.36 527	94.40 464	96.49 351

test_f		86.65 428	87.13 401	85.19 488	90.28 497	86.11 222	86.52 463	91.66 428	69.76 518	95.73 177	97.21 142	69.51 462	81.28 543	89.15 254	94.40 464	88.17 515

xiu_mvs_v2_base		89.00 362	89.19 341	88.46 437	94.86 354	74.63 464	86.97 446	95.60 304	80.88 422	87.83 469	88.62 489	91.04 189	98.81 157	82.51 388	94.38 466	91.93 489

PS-MVSNAJ		88.86 366	88.99 347	88.48 436	94.88 352	74.71 462	86.69 456	95.60 304	80.88 422	87.83 469	87.37 501	90.77 196	98.82 152	82.52 387	94.37 467	91.93 489

EU-MVSNet		87.39 410	86.71 414	89.44 405	93.40 405	76.11 450	94.93 127	90.00 444	57.17 543	95.71 178	97.37 116	64.77 489	97.68 334	92.67 125	94.37 467	94.52 441

E-PMN		80.72 489	80.86 480	80.29 518	85.11 537	68.77 507	72.96 538	81.97 521	87.76 263	83.25 515	83.01 530	62.22 503	89.17 511	77.15 452	94.31 469	82.93 537

GA-MVS		87.70 397	86.82 410	90.31 377	93.27 408	77.22 430	84.72 495	92.79 401	85.11 346	89.82 426	90.07 469	66.80 475	97.76 327	84.56 360	94.27 470	95.96 384

ETVMVS		79.85 496	77.94 504	85.59 482	92.97 417	66.20 520	86.13 471	80.99 530	81.41 416	83.52 512	83.89 522	41.81 546	94.98 455	56.47 541	94.25 471	95.61 405

mvsany_test3		89.11 355	88.21 374	91.83 296	91.30 469	90.25 115	88.09 424	78.76 539	76.37 467	96.43 122	98.39 38	83.79 316	90.43 500	86.57 323	94.20 472	94.80 433

sss		87.23 414	86.82 410	88.46 437	93.96 389	77.94 411	86.84 450	92.78 402	77.59 456	87.61 475	91.83 444	78.75 373	91.92 489	77.84 442	94.20 472	95.52 408

MDA-MVSNet-bldmvs		91.04 292	90.88 296	91.55 311	94.68 367	80.16 344	85.49 483	92.14 418	90.41 185	94.93 236	95.79 267	85.10 305	96.93 394	85.15 348	94.19 474	97.57 277

Syy-MVS		84.81 446	84.93 440	84.42 496	91.71 458	63.36 533	85.89 473	81.49 523	81.03 419	85.13 493	81.64 534	77.44 397	95.00 452	85.94 337	94.12 475	94.91 429

myMVS_eth3d		79.62 498	78.26 500	83.72 504	91.71 458	61.25 537	85.89 473	81.49 523	81.03 419	85.13 493	81.64 534	32.12 551	95.00 452	71.17 512	94.12 475	94.91 429

WB-MVSnew		84.20 454	83.89 454	85.16 489	91.62 462	66.15 521	88.44 422	81.00 529	76.23 468	87.98 466	87.77 496	84.98 307	93.35 477	62.85 536	94.10 477	95.98 383

testing91		83.56 462	82.45 466	86.91 466	92.92 419	67.29 511	86.33 466	88.07 462	86.22 306	84.26 503	85.76 510	48.15 527	97.17 378	76.27 463	94.08 478	96.27 367

PAPM_NR		91.03 293	90.81 300	91.68 306	96.73 202	81.10 330	93.72 183	96.35 275	88.19 249	88.77 451	92.12 437	85.09 306	97.25 370	82.40 390	93.90 479	96.68 339

YYNet1		88.17 384	88.24 371	87.93 448	92.21 437	73.62 477	80.75 525	88.77 452	82.51 397	94.99 234	95.11 310	82.70 331	93.70 472	83.33 375	93.83 480	96.48 352

MDA-MVSNet_test_wron		88.16 385	88.23 372	87.93 448	92.22 436	73.71 476	80.71 526	88.84 451	82.52 396	94.88 239	95.14 308	82.70 331	93.61 474	83.28 376	93.80 481	96.46 354

1112_ss		88.42 377	87.41 390	91.45 318	96.69 206	80.99 332	89.72 377	96.72 247	73.37 489	87.00 480	90.69 466	77.38 400	98.20 264	81.38 404	93.72 482	95.15 417

PVSNet	76.22 20	82.89 469	82.37 467	84.48 495	93.96 389	64.38 529	78.60 531	88.61 453	71.50 504	84.43 502	86.36 507	74.27 432	94.60 461	69.87 516	93.69 483	94.46 443

test_vis1_n_1920		89.45 346	89.85 329	88.28 439	93.59 400	76.71 443	90.67 333	97.78 141	79.67 435	90.30 414	96.11 249	76.62 418	92.17 487	90.31 208	93.57 484	95.96 384

testing99		82.94 468	81.72 471	86.59 469	92.55 426	66.53 517	86.08 472	85.70 483	85.47 337	83.95 506	85.70 511	45.87 531	97.07 386	76.58 459	93.56 485	96.17 376

test_cas_vis1_n_1920		88.25 382	88.27 369	88.20 442	92.19 439	78.92 391	89.45 387	95.44 315	75.29 477	93.23 309	95.65 280	71.58 453	90.23 501	88.05 295	93.55 486	95.44 409

UBG		80.28 494	78.94 497	84.31 498	92.86 420	61.77 534	83.87 508	83.31 513	77.33 459	82.78 518	83.72 523	47.60 529	96.06 426	65.47 530	93.48 487	95.11 421

TESTMET0.1,1		79.09 500	78.04 502	82.25 511	87.52 524	64.03 530	83.08 513	80.62 532	70.28 515	80.16 533	83.22 529	44.13 536	90.56 498	79.95 419	93.36 488	92.15 487

PAPR		87.65 400	86.77 412	90.27 379	92.85 421	77.38 426	88.56 419	96.23 281	76.82 465	84.98 496	89.75 476	86.08 293	97.16 380	72.33 501	93.35 489	96.26 368

SCA		87.43 409	87.21 396	88.10 444	92.01 447	71.98 492	89.43 388	88.11 461	82.26 402	88.71 452	92.83 406	78.65 375	97.59 341	79.61 427	93.30 490	94.75 436

testing11		81.98 478	80.52 485	86.38 476	92.69 423	67.13 512	85.79 475	84.80 497	82.16 403	81.19 531	85.41 515	45.24 533	96.88 397	74.14 489	93.24 491	95.14 418

Test_1112_low_res		87.50 408	86.58 416	90.25 380	96.80 195	77.75 419	87.53 434	96.25 279	69.73 519	86.47 482	93.61 383	75.67 423	97.88 309	79.95 419	93.20 492	95.11 421

MDTV_nov1_ep13			83.88 455		89.42 512	61.52 535	88.74 415	87.41 467	73.99 485	84.96 497	94.01 366	65.25 486	95.53 435	78.02 440	93.16 493

WTY-MVS		86.93 425	86.50 422	88.24 440	94.96 350	74.64 463	87.19 442	92.07 421	78.29 452	88.32 460	91.59 450	78.06 389	94.27 467	74.88 477	93.15 494	95.80 393

UWE-MVS-28		74.73 507	73.18 508	79.35 520	85.42 536	55.55 547	87.63 428	65.92 549	74.39 482	77.33 538	88.19 493	47.63 528	89.48 507	39.01 547	93.14 495	93.03 477

PMMVS		83.00 467	81.11 476	88.66 429	83.81 541	86.44 210	82.24 519	85.65 484	61.75 541	82.07 523	85.64 512	79.75 362	91.59 492	75.99 465	93.09 496	87.94 517

UnsupCasMVSNet_bld		88.50 374	88.03 377	89.90 393	95.52 326	78.88 393	87.39 438	94.02 367	79.32 442	93.06 320	94.02 365	80.72 352	94.27 467	75.16 474	93.08 497	96.54 343

MVS		84.98 445	84.30 446	87.01 462	91.03 477	77.69 421	91.94 278	94.16 362	59.36 542	84.23 504	87.50 500	85.66 298	96.80 402	71.79 504	93.05 498	86.54 530

PatchT		87.51 406	88.17 375	85.55 484	90.64 486	66.91 514	92.02 273	86.09 479	92.20 110	89.05 444	97.16 145	64.15 492	96.37 418	89.21 251	92.98 499	93.37 471

MS-PatchMatch		88.05 387	87.75 381	88.95 420	93.28 407	77.93 412	87.88 427	92.49 410	75.42 473	92.57 341	93.59 384	80.44 354	94.24 469	81.28 405	92.75 500	94.69 439

CR-MVSNet		87.89 392	87.12 402	90.22 381	91.01 478	78.93 389	92.52 245	92.81 399	73.08 492	89.10 440	96.93 170	67.11 472	97.64 338	88.80 267	92.70 501	94.08 451

RPMNet		90.31 321	90.14 323	90.81 361	91.01 478	78.93 389	92.52 245	98.12 76	91.91 121	89.10 440	96.89 173	68.84 465	99.41 43	90.17 218	92.70 501	94.08 451

KD-MVS_2432*1600		82.17 475	80.75 481	86.42 474	82.04 545	70.09 501	81.75 521	90.80 438	82.56 394	90.37 411	89.30 482	42.90 541	96.11 424	74.47 483	92.55 503	93.06 474

miper_refine_blended		82.17 475	80.75 481	86.42 474	82.04 545	70.09 501	81.75 521	90.80 438	82.56 394	90.37 411	89.30 482	42.90 541	96.11 424	74.47 483	92.55 503	93.06 474

BH-w/o		87.21 415	87.02 406	87.79 453	94.77 359	77.27 429	87.90 426	93.21 394	81.74 409	89.99 423	88.39 492	83.47 317	96.93 394	71.29 508	92.43 505	89.15 508

IB-MVS	77.21 19	83.11 465	81.05 477	89.29 410	91.15 474	75.85 453	85.66 479	86.00 480	79.70 434	82.02 525	86.61 504	48.26 525	98.39 237	77.84 442	92.22 506	93.63 465
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
gg-mvs-nofinetune		82.10 477	81.02 478	85.34 486	87.46 525	71.04 495	94.74 131	67.56 548	96.44 28	79.43 535	98.99 11	45.24 533	96.15 422	67.18 524	92.17 507	88.85 511

HY-MVS	82.50 18	86.81 427	85.93 429	89.47 404	93.63 399	77.93 412	94.02 167	91.58 431	75.68 469	83.64 510	93.64 380	77.40 399	97.42 356	71.70 506	92.07 508	93.05 476

TR-MVS		87.70 397	87.17 398	89.27 413	94.11 383	79.26 383	88.69 416	91.86 425	81.94 405	90.69 403	89.79 474	82.82 329	97.42 356	72.65 500	91.98 509	91.14 497

new_pmnet		81.22 482	81.01 479	81.86 512	90.92 481	70.15 500	84.03 505	80.25 536	70.83 510	85.97 487	89.78 475	67.93 471	84.65 538	67.44 523	91.90 510	90.78 501

FPMVS		84.50 450	83.28 458	88.16 443	96.32 254	94.49 20	85.76 476	85.47 489	83.09 387	85.20 492	94.26 354	63.79 495	86.58 533	63.72 533	91.88 511	83.40 536

XFeat-NN		75.97 504	74.88 506	79.25 521	77.98 550	79.81 360	70.81 541	79.50 538	64.75 535	86.32 484	82.83 531	53.44 522	76.70 546	66.89 525	91.40 512	81.23 541

UnsupCasMVSNet_eth		90.33 319	90.34 317	90.28 378	94.64 369	80.24 343	89.69 378	95.88 296	85.77 323	93.94 274	95.69 278	81.99 341	92.98 482	84.21 366	91.30 513	97.62 272

MVP-Stereo		90.07 331	88.92 348	93.54 199	96.31 255	86.49 207	90.93 319	95.59 308	79.80 431	91.48 379	95.59 281	80.79 351	97.39 359	78.57 439	91.19 514	96.76 337
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
1314		86.46 432	86.33 426	86.87 467	91.65 461	74.54 465	91.94 278	94.10 364	74.28 483	84.78 498	87.33 502	83.03 325	95.00 452	78.72 436	91.16 515	91.06 498

tpm		84.38 451	84.08 450	85.30 487	90.47 493	63.43 532	89.34 391	85.63 485	77.24 461	87.62 473	95.03 315	61.00 507	97.30 363	79.26 431	91.09 516	95.16 416

dmvs_re		84.69 449	83.94 453	86.95 465	92.24 435	82.93 290	89.51 384	87.37 468	84.38 364	85.37 490	85.08 518	72.44 443	86.59 532	68.05 521	91.03 517	91.33 495

CVMVSNet		85.16 443	84.72 441	86.48 472	92.12 443	70.19 499	92.32 260	88.17 460	56.15 544	90.64 404	95.85 262	67.97 470	96.69 405	88.78 268	90.52 518	92.56 483

test0.0.03 1		82.48 472	81.47 475	85.48 485	89.70 506	73.57 478	84.73 492	81.64 522	83.07 388	88.13 464	86.61 504	62.86 500	89.10 512	66.24 528	90.29 519	93.77 461

baseline2		83.38 463	81.54 474	88.90 422	91.38 467	72.84 485	88.78 411	81.22 528	78.97 446	79.82 534	87.56 497	61.73 504	97.80 319	74.30 487	90.05 520	96.05 380

test_vis1_rt		85.58 440	84.58 443	88.60 431	87.97 521	86.76 199	85.45 485	93.59 382	66.43 529	87.64 472	89.20 484	79.33 365	85.38 536	81.59 399	89.98 521	93.66 464

MonoMVSNet		88.46 375	89.28 340	85.98 480	90.52 490	70.07 503	95.31 109	94.81 342	88.38 241	93.47 292	96.13 246	73.21 438	95.07 451	82.61 385	89.12 522	92.81 480

PAPM		81.91 479	80.11 490	87.31 458	93.87 393	72.32 491	84.02 506	93.22 392	69.47 520	76.13 540	89.84 471	72.15 449	97.23 372	53.27 543	89.02 523	92.37 486

MVS-HIRNet		78.83 501	80.60 484	73.51 526	93.07 413	47.37 553	87.10 444	78.00 542	68.94 521	77.53 537	97.26 134	71.45 454	94.62 460	63.28 534	88.74 524	78.55 542

tpm2		81.46 480	80.35 488	84.80 491	89.90 504	65.14 525	90.44 341	85.36 490	65.82 533	82.05 524	92.44 424	57.94 511	96.69 405	70.71 513	88.49 525	92.56 483

CostFormer		83.09 466	82.21 468	85.73 481	89.27 514	67.01 513	90.35 347	86.47 475	70.42 514	83.52 512	93.23 393	61.18 505	96.85 398	77.21 450	88.26 526	93.34 472

GG-mvs-BLEND				83.24 507	85.06 538	71.03 496	94.99 126	65.55 550		74.09 541	75.51 539	44.57 535	94.46 463	59.57 539	87.54 527	84.24 533

GLUNet-SfM		58.71 510	56.43 513	65.55 527	45.28 554	59.80 539	54.31 545	55.90 553	37.80 547	81.24 530	73.75 541	38.27 550	70.23 550	34.22 549	87.09 528	66.64 544

PatchmatchNet		85.22 442	84.64 442	86.98 463	89.51 511	69.83 505	90.52 337	87.34 469	78.87 448	87.22 479	92.74 411	66.91 474	96.53 408	81.77 396	86.88 529	94.58 440
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
mvsany_test1		83.91 459	82.93 463	86.84 468	86.18 532	85.93 229	81.11 524	75.03 546	70.80 512	88.57 457	94.63 336	83.08 324	87.38 522	80.39 411	86.57 530	87.21 524

baseline1		87.62 401	87.31 392	88.54 432	94.71 366	74.27 470	93.10 210	88.20 459	86.20 307	92.18 361	93.04 396	73.21 438	95.52 436	79.32 430	85.82 531	95.83 392

tpmvs		84.22 453	83.97 452	84.94 490	87.09 528	65.18 524	91.21 307	88.35 455	82.87 391	85.21 491	90.96 461	65.24 487	96.75 403	79.60 429	85.25 532	92.90 479

ADS-MVSNet2		84.01 456	82.20 469	89.41 407	89.04 515	76.37 448	87.57 430	90.98 435	72.71 497	84.46 500	92.45 422	68.08 468	96.48 411	70.58 514	83.97 533	95.38 410

ADS-MVSNet		82.25 473	81.55 473	84.34 497	89.04 515	65.30 523	87.57 430	85.13 496	72.71 497	84.46 500	92.45 422	68.08 468	92.33 486	70.58 514	83.97 533	95.38 410

JIA-IIPM		85.08 444	83.04 460	91.19 338	87.56 523	86.14 221	89.40 390	84.44 501	88.98 219	82.20 521	97.95 61	56.82 515	96.15 422	76.55 460	83.45 535	91.30 496

MVE	59.87 23	73.86 509	72.65 510	77.47 523	87.00 530	74.35 468	61.37 544	60.93 551	67.27 526	69.69 546	86.49 506	81.24 350	72.33 548	56.45 542	83.45 535	85.74 532
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		78.23 502	78.99 495	75.94 524	91.99 448	55.34 548	88.86 405	78.70 540	82.69 392	81.64 528	79.46 536	75.93 421	85.74 535	48.78 545	82.85 537	86.76 529

EPMVS		81.17 484	80.37 487	83.58 505	85.58 534	65.08 526	90.31 352	71.34 547	77.31 460	85.80 488	91.30 453	59.38 509	92.70 483	79.99 418	82.34 538	92.96 478

tpmrst		82.85 470	82.93 463	82.64 509	87.65 522	58.99 542	90.14 358	87.90 464	75.54 472	83.93 507	91.63 449	66.79 477	95.36 443	81.21 407	81.54 539	93.57 470

tpm cat1		80.61 490	79.46 493	84.07 500	88.78 517	65.06 527	89.26 394	88.23 458	62.27 540	81.90 526	89.66 479	62.70 502	95.29 447	71.72 505	80.60 540	91.86 491

0.4-1-1-0.1		77.15 503	73.55 507	87.95 447	85.49 535	75.84 455	80.59 528	82.87 517	73.51 488	73.61 542	68.65 542	42.84 544	97.22 373	75.20 473	79.18 541	90.80 500

0.4-1-1-0.2		75.80 505	72.05 511	87.04 461	82.70 544	74.17 473	77.51 532	83.48 508	71.80 501	71.57 544	65.16 544	43.07 539	96.96 390	74.34 486	78.78 542	90.00 506

0.3-1-1-0.015		75.73 506	71.83 512	87.44 456	83.47 542	74.98 460	78.69 530	83.38 511	72.24 499	70.43 545	65.81 543	39.55 548	97.08 384	74.57 480	78.30 543	90.28 505

dp		79.28 499	78.62 498	81.24 516	85.97 533	56.45 545	86.91 448	85.26 494	72.97 495	81.45 529	89.17 486	56.01 517	95.45 441	73.19 496	76.68 544	91.82 492

blend_shiyan4		83.29 464	80.66 483	91.19 338	91.86 451	79.59 368	87.05 445	93.91 374	82.66 393	89.60 432	83.36 525	42.82 545	98.10 280	81.45 402	73.26 545	95.87 391

DeepMVS_CX				53.83 529	70.38 552	64.56 528		48.52 555	33.01 548	65.50 548	74.21 540	56.19 516	46.64 552	38.45 548	70.07 546	50.30 546

tmp_tt		37.97 514	44.33 516	18.88 532	11.80 556	21.54 558	63.51 543	45.66 556	4.23 550	51.34 549	50.48 547	59.08 510	22.11 553	44.50 546	68.35 547	13.00 548

PVSNet_0	70.34 21	74.58 508	72.96 509	79.47 519	90.63 487	66.24 519	73.26 537	83.40 510	63.67 538	78.02 536	78.35 538	72.53 442	89.59 505	56.68 540	60.05 548	82.57 539

test_method		50.44 512	48.94 515	54.93 528	39.68 555	12.38 559	28.59 546	90.09 443	6.82 549	41.10 551	78.41 537	54.41 518	70.69 549	50.12 544	51.26 549	81.72 540

dongtai		53.72 511	53.79 514	53.51 530	79.69 547	36.70 556	77.18 533	32.53 558	71.69 502	68.63 547	60.79 545	26.65 554	73.11 547	30.67 550	36.29 550	50.73 545

kuosan		43.63 513	44.25 517	41.78 531	66.04 553	34.37 557	75.56 535	32.62 557	53.25 546	50.46 550	51.18 546	25.28 555	49.13 551	13.44 551	30.41 551	41.84 547

VLMVS		7.75 518	8.50 523	5.52 533	7.85 557	5.47 560	5.34 547	3.06 559	0.41 554	11.88 552	15.91 549	11.95 556	3.89 554	3.42 552	16.65 552	7.20 549

test123		9.49 516	12.01 519	1.91 534	2.87 558	1.30 561	82.38 518	1.34 561	1.36 552	2.84 554	6.56 551	2.45 557	0.97 555	2.73 553	5.56 553	3.47 550

testmvs		9.02 517	11.42 520	1.81 535	2.77 559	1.13 562	79.44 529	1.90 560	1.18 553	2.65 555	6.80 550	1.95 558	0.87 556	2.62 554	3.45 554	3.44 551

mmdepth		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

monomultidepth		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

test_blank		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

uanet_test		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

DCPMVS		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

cdsmvs_eth3d_5k		23.35 515	31.13 518	0.00 536	0.00 560	0.00 563	0.00 548	95.58 310	0.00 555	0.00 556	91.15 455	93.43 109	0.00 557	0.00 555	0.00 555	0.00 552

pcd_1.5k_mvsjas		7.56 519	10.09 521	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	90.77 196	0.00 557	0.00 555	0.00 555	0.00 552

sosnet-low-res		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

sosnet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

uncertanet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

Regformer		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

ab-mvs-re		7.56 519	10.08 522	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	90.69 466	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

uanet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

PatchmatchNet2					0.00 560	54.43 549	80.66 527	86.13 478	76.71 466
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													91.63 491
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						61.25 537								74.55 481

FOURS1					99.21 3	94.68 16	98.45 4	98.81 10	97.73 9	98.27 23

test_one_0601					98.26 80	87.14 187		98.18 63	94.25 61	96.99 90	97.36 121	95.13 50

eth-test2					0.00 560

eth-test					0.00 560

test_241102_ONE					98.51 58	86.97 192		98.10 80	91.85 125	97.63 45	97.03 161	96.48 13	98.95 136

save fliter					97.46 145	88.05 167	92.04 272	97.08 211	87.63 267

test0726					98.51 58	86.69 202	95.34 105	98.18 63	91.85 125	97.63 45	97.37 116	95.58 28

GSMVS																94.75 436

test_part2					98.21 84	89.41 129				96.72 105

sam_mvs1												66.64 478				94.75 436

sam_mvs												66.41 479

MTGPA								97.62 154

test_post1							90.21 354				5.85 553	65.36 485	96.00 428	79.61 427

test_post											6.07 552	65.74 483	95.84 432

patchmatchnet-post											91.71 447	66.22 481	97.59 341

MTMP							94.82 129	54.62 554

gm-plane-assit					87.08 529	59.33 541			71.22 505		83.58 524		97.20 375	73.95 491

TEST9					96.45 235	89.46 126	90.60 335	96.92 223	79.09 445	90.49 405	94.39 349	91.31 177	98.88 143

test_8					96.37 244	89.14 136	90.51 338	96.89 227	79.37 439	90.42 407	94.36 353	91.20 182	98.82 152

agg_prior					96.20 268	88.89 142		96.88 232		90.21 415			98.78 165

test_prior4						89.91 119	90.74 328

test_prior				94.61 142	95.95 292	87.23 184		97.36 185					98.68 187			97.93 228

旧先验2							90.00 364		68.65 522	92.71 336			96.52 409	85.15 348

新几何2							90.02 363

无先验							89.94 365	95.75 300	70.81 511				98.59 202	81.17 408		94.81 432

原ACMM2							89.34 391

testdata2													98.03 292	80.24 415

segment_acmp												92.14 153

testdata1							88.96 403		88.44 239

plane_prior7					97.71 125	88.68 146

plane_prior6					97.21 161	88.23 160						86.93 280

plane_prior4											95.59 281

plane_prior3						88.43 157			90.35 186	93.31 300

plane_prior2							94.56 143		91.74 136

plane_prior1					97.38 149

n2								0.00 562

nn								0.00 562

door-mid								92.13 419

test11								96.65 255

door								91.26 432

HQP5-MVS						84.89 249

HQP-NCC					96.36 247		91.37 301		87.16 281	88.81 447

ACMP_Plane					96.36 247		91.37 301		87.16 281	88.81 447

BP-MVS														86.55 325

HQP4-MVS										88.81 447			98.61 197			98.15 198

HQP2-MVS												84.76 308

NP-MVS					96.82 193	87.10 188					93.40 388

MDTV_nov1_ep13_2view						42.48 555	88.45 421		67.22 527	83.56 511		66.80 475		72.86 499		94.06 453

Test By Simon												90.61 202

High-resolution multi-view benchmark