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.

MM		80.20 8	80.28 10	79.99 2	82.19 91	60.01 49	86.19 21	83.93 62	73.19 1	77.08 47	91.21 21	57.23 40	90.73 10	83.35 1	88.12 38	89.22 9

MSP-MVS		81.06 3	81.40 4	80.02 1	86.21 33	62.73 9	86.09 22	86.83 8	65.51 13	83.81 10	90.51 31	63.71 13	89.23 26	81.51 2	88.44 31	88.09 47
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
MGCNet		78.45 21	78.28 22	78.98 29	80.73 116	57.91 91	84.68 41	81.64 134	68.35 2	75.77 53	90.38 35	53.98 83	90.26 13	81.30 3	87.68 46	88.77 19

MP-MVS-pluss		78.35 23	78.46 20	78.03 45	84.96 57	59.52 58	82.93 70	85.39 34	62.15 82	76.41 51	91.51 11	52.47 112	86.78 77	80.66 4	89.64 21	87.80 58
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_9		75.16 61	75.22 60	75.01 102	78.34 184	55.37 140	77.30 189	73.95 321	61.40 97	79.46 25	90.14 42	57.07 41	81.15 234	80.00 5	79.31 158	88.51 31

SMA-MVS		80.28 7	80.39 8	79.95 4	86.60 24	61.95 19	86.33 17	85.75 28	62.49 72	82.20 20	92.28 1	56.53 45	89.70 21	79.85 6	91.48 1	88.19 42
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
DVP-MVS++		81.67 1	82.40 1	79.47 10	87.24 14	59.15 69	88.18 1	87.15 3	65.04 17	84.26 5	91.86 6	67.01 1	90.84 3	79.48 7	91.38 2	88.42 32

test_0728_THIRD									65.04 17	83.82 8	92.00 3	64.69 11	90.75 8	79.48 7	90.63 10	88.09 47

ACMMP_NAP		78.77 18	78.78 17	78.74 34	85.44 47	61.04 31	83.84 60	85.16 38	62.88 63	78.10 36	91.26 20	52.51 110	88.39 36	79.34 9	90.52 13	86.78 103

MSC_two_6792asdad				79.95 4	87.24 14	61.04 31		85.62 31					90.96 1	79.31 10	90.65 8	87.85 55

No_MVS				79.95 4	87.24 14	61.04 31		85.62 31					90.96 1	79.31 10	90.65 8	87.85 55

fmvsm_s_conf0.5_n_4		72.04 130	71.85 119	72.58 194	73.74 326	52.49 205	76.69 213	72.42 339	56.42 227	75.32 58	87.04 115	52.13 120	78.01 317	79.29 12	73.65 265	87.26 84

IU-MVS					87.77 4	59.15 69		85.53 33	53.93 293	84.64 3				79.07 13	90.87 5	88.37 34

HPM-MVS++		79.88 11	80.14 11	79.10 21	88.17 1	64.80 1	86.59 16	83.70 81	65.37 14	78.78 31	90.64 25	58.63 32	87.24 61	79.00 14	90.37 14	85.26 182

APDe-MVS		80.16 9	80.59 7	78.86 33	86.64 21	60.02 48	88.12 3	86.42 16	62.94 61	82.40 16	92.12 2	59.64 24	89.76 20	78.70 15	88.32 35	86.79 102
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
fmvsm_s_conf0.5_n_3		73.55 91	74.39 70	71.03 254	74.09 322	51.86 220	77.77 173	75.60 284	61.18 103	78.67 32	88.98 64	55.88 64	77.73 327	78.69 16	78.68 179	83.50 250

CNVR-MVS		79.84 12	79.97 12	79.45 11	87.90 2	62.17 17	84.37 45	85.03 43	66.96 5	77.58 41	90.06 46	59.47 26	89.13 28	78.67 17	89.73 16	87.03 92

DVP-MVS		80.84 4	81.64 3	78.42 38	87.75 7	59.07 74	87.85 5	85.03 43	64.26 32	83.82 8	92.00 3	64.82 8	90.75 8	78.66 18	90.61 11	85.45 170
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				79.19 16	87.82 3	59.11 72	87.85 5	87.15 3					90.84 3	78.66 18	90.61 11	87.62 66

SED-MVS		81.56 2	82.30 2	79.32 13	87.77 4	58.90 79	87.82 7	86.78 10	64.18 35	85.97 1	91.84 8	66.87 3	90.83 5	78.63 20	90.87 5	88.23 40

test_241102_TWO								86.73 12	64.18 35	84.26 5	91.84 8	65.19 6	90.83 5	78.63 20	90.70 7	87.65 64

fmvsm_s_conf0.5_n_8		74.30 75	74.39 70	74.01 143	75.33 284	52.89 191	78.24 149	77.32 246	61.65 92	78.13 35	88.90 67	52.82 106	81.54 224	78.46 22	78.67 180	87.60 67

SteuartSystems-ACMMP		79.48 14	79.31 14	79.98 3	83.01 82	62.18 16	87.60 9	85.83 26	66.69 10	78.03 38	90.98 22	54.26 78	90.06 14	78.42 23	89.02 27	87.69 62
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_l_conf0.5_n_9		73.27 98	73.66 87	72.09 209	73.82 323	52.72 197	77.45 183	74.28 314	56.61 222	77.10 46	88.16 79	56.17 52	77.09 342	78.27 24	81.13 122	86.48 117

test_fmvsmconf0.1_n		72.81 108	72.33 113	74.24 129	69.89 404	55.81 127	78.22 155	75.40 291	54.17 289	75.00 66	88.03 87	53.82 88	80.23 263	78.08 25	78.34 189	86.69 107

test_fmvsmconf0.01_n		72.17 126	71.50 125	74.16 133	67.96 436	55.58 135	78.06 162	74.67 307	54.19 288	74.54 79	88.23 77	50.35 151	80.24 262	78.07 26	77.46 203	86.65 111

test_fmvsmconf_n		73.01 104	72.59 108	74.27 127	71.28 378	55.88 126	78.21 156	75.56 286	54.31 287	74.86 71	87.80 91	54.72 74	80.23 263	78.07 26	78.48 185	86.70 106

fmvsm_s_conf0.5_n_10		74.11 77	73.98 80	74.48 121	74.61 304	52.86 193	78.10 161	77.06 251	57.14 204	78.24 34	88.79 72	52.83 105	82.26 208	77.79 28	81.30 120	88.32 35

9.14			78.75 18		83.10 79		84.15 54	88.26 1	59.90 140	78.57 33	90.36 36	57.51 39	86.86 75	77.39 29	89.52 23

test-260524					86.59 25	59.16 67		86.47 15		82.32 18		62.54 14	89.91 16	77.25 30	89.69 18

MTAPA		76.90 38	76.42 43	78.35 39	86.08 39	63.57 2	74.92 259	80.97 161	65.13 16	75.77 53	90.88 23	48.63 178	86.66 80	77.23 31	88.17 37	84.81 198

MP-MVS		78.35 23	78.26 24	78.64 35	86.54 27	63.47 4	86.02 24	83.55 87	63.89 40	73.60 99	90.60 26	54.85 73	86.72 78	77.20 32	88.06 40	85.74 156
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
fmvsm_s_conf0.5_n_6		72.59 115	72.87 103	71.73 220	75.14 291	51.96 218	76.28 222	77.12 249	57.63 198	73.85 95	86.91 118	51.54 131	77.87 323	77.18 33	80.18 140	85.37 176

SF-MVS		78.82 16	79.22 15	77.60 52	82.88 84	57.83 92	84.99 37	88.13 2	61.86 90	79.16 28	90.75 24	57.96 33	87.09 70	77.08 34	90.18 15	87.87 54

aaatest				79.09 23	85.30 51	59.25 64	86.84 11	85.86 24	60.95 107	83.65 12	90.57 28		89.91 16	77.02 35	89.43 24	88.10 45

MED-MVS		80.42 6	80.87 6	79.07 25	85.30 51	59.25 64	86.84 11	85.86 24	63.31 49	83.65 12	91.48 12	64.70 10	89.91 16	77.02 35	89.69 18	88.06 50

aaEdge-Enhanced		80.04 10	80.36 9	79.08 24	86.63 23	59.25 64	85.62 32	86.73 12	63.10 58	82.27 19	90.57 28	61.90 17	89.88 19	77.02 35	89.43 24	88.10 45

TSAR-MVS + MP.		78.44 22	78.28 22	78.90 31	84.96 57	61.41 26	84.03 56	83.82 76	59.34 156	79.37 27	89.76 55	59.84 21	87.62 58	76.69 38	86.74 59	87.68 63
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_s_conf0.5_n_5		72.69 112	72.80 104	72.37 205	74.11 321	53.21 182	78.12 158	73.31 328	53.98 292	76.81 48	88.05 84	53.38 96	77.37 337	76.64 39	80.78 124	86.53 115

ZNCC-MVS		78.82 16	78.67 19	79.30 14	86.43 30	62.05 18	86.62 15	86.01 21	63.32 48	75.08 64	90.47 34	53.96 85	88.68 33	76.48 40	89.63 22	87.16 89

DPE-MVS		80.56 5	80.98 5	79.29 15	87.27 13	60.56 41	85.71 31	86.42 16	63.28 52	83.27 15	91.83 10	64.96 7	90.47 11	76.41 41	89.67 20	86.84 100
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_l_conf0.5_n_3		73.23 99	73.13 99	73.55 168	74.40 311	55.13 143	78.97 132	74.96 303	56.64 216	74.76 75	88.75 73	55.02 70	78.77 305	76.33 42	78.31 190	86.74 105

fmvsm_l_conf0.5_n		70.99 152	70.82 143	71.48 229	71.45 371	54.40 152	77.18 195	70.46 359	48.67 378	75.17 61	86.86 119	53.77 90	76.86 350	76.33 42	77.51 202	83.17 262

TestfortrainingZip a		79.61 13	79.84 13	78.92 30	85.30 51	59.08 73	86.84 11	86.01 21	63.31 49	82.37 17	91.48 12	60.88 19	89.61 22	76.25 44	86.13 66	88.06 50

fmvsm_s_conf0.5_n_11		73.16 100	73.35 94	72.58 194	75.48 279	52.41 209	78.84 134	76.85 256	58.64 170	73.58 100	87.25 110	54.09 82	79.47 275	76.19 45	79.27 159	85.86 146

SD-MVS		77.70 30	77.62 30	77.93 47	84.47 65	61.88 21	84.55 43	83.87 69	60.37 125	79.89 24	89.38 59	54.97 71	85.58 116	76.12 46	84.94 72	86.33 127
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
test_fmvsmvis_n_1920		70.84 154	70.38 153	72.22 208	71.16 379	55.39 139	75.86 235	72.21 342	49.03 373	73.28 108	86.17 150	51.83 126	77.29 339	75.80 47	78.05 193	83.98 225

fmvsm_s_conf0.5_n		69.58 191	68.84 187	71.79 218	72.31 357	52.90 189	77.90 165	62.43 436	49.97 361	72.85 124	85.90 161	52.21 117	76.49 359	75.75 48	70.26 326	85.97 140

fmvsm_s_conf0.5_n_2		69.82 181	69.27 177	71.46 230	72.00 361	51.08 227	73.30 295	67.79 382	55.06 268	75.24 60	87.51 94	44.02 242	77.00 346	75.67 49	72.86 283	86.31 132

lecture		77.75 28	77.84 28	77.50 54	82.75 86	57.62 95	85.92 25	86.20 19	60.53 118	78.99 30	91.45 14	51.51 132	87.78 53	75.65 50	87.55 47	87.10 91

fmvsm_s_conf0.1_n_2		69.64 189	69.01 183	71.52 228	71.66 366	51.04 228	73.39 294	67.14 388	55.02 272	75.11 62	87.64 93	42.94 254	77.01 345	75.55 51	72.63 289	86.52 116

fmvsm_s_conf0.1_n		69.41 199	68.60 193	71.83 215	71.07 380	52.88 192	77.85 169	62.44 435	49.58 366	72.97 119	86.22 147	51.68 129	76.48 360	75.53 52	70.10 330	86.14 135

fmvsm_l_conf0.5_n_a		70.50 163	70.27 156	71.18 246	71.30 377	54.09 157	76.89 206	69.87 363	47.90 394	74.37 82	86.49 139	53.07 104	76.69 356	75.41 53	77.11 212	82.76 269

HPM-MVS		77.28 33	76.85 34	78.54 36	85.00 56	60.81 38	82.91 71	85.08 40	62.57 70	73.09 117	89.97 51	50.90 144	87.48 59	75.30 54	86.85 57	87.33 83
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test9_res														75.28 55	88.31 36	83.81 234

train_agg		76.27 48	76.15 45	76.64 71	85.58 45	61.59 24	81.62 91	81.26 149	55.86 239	74.93 67	88.81 69	53.70 92	84.68 140	75.24 56	88.33 34	83.65 245

fmvsm_s_conf0.5_n_a		69.54 193	68.74 190	71.93 212	72.47 351	53.82 162	78.25 148	62.26 438	49.78 363	73.12 116	86.21 148	52.66 108	76.79 352	75.02 57	68.88 354	85.18 183

test_fmvsm_n_1920		71.73 136	71.14 136	73.50 169	72.52 349	56.53 113	75.60 239	76.16 271	48.11 390	77.22 43	85.56 171	53.10 102	77.43 334	74.86 58	77.14 211	86.55 114

fmvsm_s_conf0.1_n_a		69.32 201	68.44 199	71.96 210	70.91 382	53.78 163	78.12 158	62.30 437	49.35 369	73.20 110	86.55 138	51.99 122	76.79 352	74.83 59	68.68 359	85.32 178

GST-MVS		78.14 25	77.85 27	78.99 28	86.05 40	61.82 22	85.84 26	85.21 37	63.56 44	74.29 84	90.03 48	52.56 109	88.53 35	74.79 60	88.34 33	86.63 112

DeepC-MVS	69.38 2	78.56 20	78.14 25	79.83 7	83.60 72	61.62 23	84.17 53	86.85 6	63.23 54	73.84 96	90.25 41	57.68 36	89.96 15	74.62 61	89.03 26	87.89 52
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PC_three_1452									55.09 263	84.46 4	89.84 53	66.68 5	89.41 24	74.24 62	91.38 2	88.42 32

DeepPCF-MVS	69.58 1	79.03 15	79.00 16	79.13 19	84.92 61	60.32 46	83.03 68	85.33 35	62.86 64	80.17 23	90.03 48	61.76 18	88.95 30	74.21 63	88.67 30	88.12 44

NCCC		78.58 19	78.31 21	79.39 12	87.51 12	62.61 13	85.20 36	84.42 53	66.73 8	74.67 78	89.38 59	55.30 67	89.18 27	74.19 64	87.34 50	86.38 120

ZD-MVS					86.64 21	60.38 45		82.70 119	57.95 189	78.10 36	90.06 46	56.12 55	88.84 32	74.05 65	87.00 55

HFP-MVS		78.01 27	77.65 29	79.10 21	86.71 19	62.81 8	86.29 18	84.32 55	62.82 65	73.96 89	90.50 32	53.20 100	88.35 37	74.02 66	87.05 51	86.13 136

ACMMPR		77.71 29	77.23 32	79.16 17	86.75 18	62.93 7	86.29 18	84.24 56	62.82 65	73.55 101	90.56 30	49.80 160	88.24 39	74.02 66	87.03 52	86.32 129

region2R		77.67 31	77.18 33	79.15 18	86.76 17	62.95 6	86.29 18	84.16 58	62.81 67	73.30 106	90.58 27	49.90 157	88.21 40	73.78 68	87.03 52	86.29 133

MCST-MVS		77.48 32	77.45 31	77.54 53	86.67 20	58.36 86	83.22 66	86.93 5	56.91 212	74.91 69	88.19 78	59.15 29	87.68 57	73.67 69	87.45 49	86.57 113

CP-MVS		77.12 36	76.68 36	78.43 37	86.05 40	63.18 5	87.55 10	83.45 90	62.44 74	72.68 127	90.50 32	48.18 183	87.34 60	73.59 70	85.71 68	84.76 201

APD-MVS		78.02 26	78.04 26	77.98 46	86.44 29	60.81 38	85.52 33	84.36 54	60.61 116	79.05 29	90.30 39	55.54 66	88.32 38	73.48 71	87.03 52	84.83 197
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
OPU-MVS				79.83 7	87.54 11	60.93 35	87.82 7				89.89 52	67.01 1	90.33 12	73.16 72	91.15 4	88.23 40

agg_prior2														73.09 73	87.93 44	84.33 211

BridgeMVS		76.58 43	76.55 41	76.68 68	81.73 97	52.90 189	80.94 99	85.70 30	61.12 105	74.90 70	87.17 113	56.46 46	88.14 42	72.87 74	88.03 42	89.00 12

casdiffmvs_mvg		76.14 51	76.30 44	75.66 89	76.46 262	51.83 221	79.67 122	85.08 40	65.02 20	75.84 52	88.58 76	59.42 27	85.08 128	72.75 75	83.93 84	90.08 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CANet		76.46 45	75.93 49	78.06 43	81.29 106	57.53 97	82.35 80	83.31 98	67.78 3	70.09 166	86.34 144	54.92 72	88.90 31	72.68 76	84.55 75	87.76 60

reproduce-ours		76.90 38	76.58 38	77.87 48	83.99 68	60.46 43	84.75 38	83.34 95	60.22 132	77.85 39	91.42 16	50.67 145	87.69 55	72.46 77	84.53 76	85.46 168

our_new_method		76.90 38	76.58 38	77.87 48	83.99 68	60.46 43	84.75 38	83.34 95	60.22 132	77.85 39	91.42 16	50.67 145	87.69 55	72.46 77	84.53 76	85.46 168

PGM-MVS		76.77 41	76.06 47	78.88 32	86.14 37	62.73 9	82.55 78	83.74 78	61.71 91	72.45 133	90.34 38	48.48 181	88.13 43	72.32 79	86.85 57	85.78 150

Casviewmamba		76.62 42	76.52 42	76.90 62	77.91 201	53.66 166	80.76 103	84.47 50	66.73 8	75.75 55	88.63 75	59.17 28	86.66 80	72.28 80	83.01 93	90.39 1

fmvsm_l_mol_unc0.5_1		72.30 122	72.61 107	71.37 239	72.96 340	48.16 305	72.91 307	64.68 410	58.47 175	81.24 22	91.38 18	56.26 50	79.00 298	72.19 81	83.35 90	86.95 95

test_prior2							81.75 89		60.37 125	75.01 65	89.06 62	56.22 51		72.19 81	88.96 28

MVSMamba_PlusPlus		75.75 57	75.44 55	76.67 69	80.84 114	53.06 186	78.62 140	85.13 39	59.65 146	71.53 146	87.47 96	56.92 42	88.17 41	72.18 83	86.63 62	88.80 16

ACMMP		76.02 53	75.33 57	78.07 42	85.20 54	61.91 20	85.49 35	84.44 52	63.04 59	69.80 176	89.74 56	45.43 223	87.16 67	72.01 84	82.87 101	85.14 184
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
reproduce_model		76.43 46	76.08 46	77.49 55	83.47 76	60.09 47	84.60 42	82.90 115	59.65 146	77.31 42	91.43 15	49.62 163	87.24 61	71.99 85	83.75 88	85.14 184

EC-MVSNet		75.84 55	75.87 51	75.74 87	78.86 161	52.65 198	83.73 61	86.08 20	63.47 46	72.77 126	87.25 110	53.13 101	87.93 48	71.97 86	85.57 70	86.66 110

fmvsm_s_conf0.5_n_7		69.54 193	69.67 167	69.15 295	73.47 331	51.41 225	70.35 356	73.34 327	57.05 207	68.41 198	85.83 164	49.86 158	72.84 380	71.86 87	76.83 217	83.19 258

CS-MVS		76.25 50	75.98 48	77.06 61	80.15 130	55.63 132	84.51 44	83.90 65	63.24 53	73.30 106	87.27 105	55.06 69	86.30 96	71.78 88	84.58 74	89.25 8

mPP-MVS		76.54 44	75.93 49	78.34 40	86.47 28	63.50 3	85.74 30	82.28 124	62.90 62	71.77 140	90.26 40	46.61 209	86.55 87	71.71 89	85.66 69	84.97 193

SR-MVS		76.13 52	75.70 53	77.40 58	85.87 42	61.20 29	85.52 33	82.19 125	59.99 138	75.10 63	90.35 37	47.66 190	86.52 88	71.64 90	82.99 95	84.47 210

XVS		77.17 35	76.56 40	79.00 26	86.32 31	62.62 11	85.83 27	83.92 63	64.55 26	72.17 135	90.01 50	47.95 185	88.01 46	71.55 91	86.74 59	86.37 122

X-MVStestdata		70.21 170	67.28 233	79.00 26	86.32 31	62.62 11	85.83 27	83.92 63	64.55 26	72.17 135	6.49 531	47.95 185	88.01 46	71.55 91	86.74 59	86.37 122

BP-MVS1		73.41 94	72.25 114	76.88 63	76.68 255	53.70 164	79.15 130	81.07 156	60.66 115	71.81 139	87.39 100	40.93 286	87.24 61	71.23 93	81.29 121	89.71 3

dcpmvs_2		74.55 72	75.23 59	72.48 200	82.34 89	53.34 178	77.87 167	81.46 138	57.80 194	75.49 56	86.81 121	62.22 15	77.75 326	71.09 94	82.02 110	86.34 124

diffmvs_AUTHOR		71.02 149	70.87 142	71.45 232	69.89 404	48.97 290	73.16 302	78.33 224	57.79 195	72.11 137	85.26 180	51.84 125	77.89 322	71.00 95	78.47 187	87.49 71

PHI-MVS		75.87 54	75.36 56	77.41 56	80.62 121	55.91 125	84.28 50	85.78 27	56.08 237	73.41 102	86.58 135	50.94 143	88.54 34	70.79 96	89.71 17	87.79 59

diffmvs		70.69 159	70.43 151	71.46 230	69.45 411	48.95 291	72.93 305	78.46 217	57.27 202	71.69 141	83.97 214	51.48 133	77.92 321	70.70 97	77.95 195	87.53 70
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
h-mvs33		72.71 111	71.49 126	76.40 74	81.99 94	59.58 57	76.92 205	76.74 262	60.40 122	74.81 72	85.95 159	45.54 219	85.76 112	70.41 98	70.61 317	83.86 233

hse-mvs2		71.04 148	69.86 163	74.60 115	79.58 139	57.12 108	73.96 280	75.25 294	60.40 122	74.81 72	81.95 270	45.54 219	82.90 187	70.41 98	66.83 374	83.77 238

APD-MVS_3200maxsize		74.96 62	74.39 70	76.67 69	82.20 90	58.24 87	83.67 62	83.29 99	58.41 176	73.71 97	90.14 42	45.62 216	85.99 106	69.64 100	82.85 102	85.78 150

baseline		74.61 70	74.70 66	74.34 124	75.70 272	49.99 264	77.54 179	84.63 49	62.73 69	73.98 88	87.79 92	57.67 37	83.82 157	69.49 101	82.74 104	89.20 10

OPM-MVS		74.73 67	74.25 73	76.19 78	80.81 115	59.01 77	82.60 77	83.64 84	63.74 42	72.52 130	87.49 95	47.18 200	85.88 109	69.47 102	80.78 124	83.66 244
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
casdiffmvs		74.80 65	74.89 65	74.53 119	75.59 277	50.37 253	78.17 157	85.06 42	62.80 68	74.40 81	87.86 89	57.88 34	83.61 161	69.46 103	82.79 103	89.59 5
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CDPH-MVS		76.31 47	75.67 54	78.22 41	85.35 50	59.14 71	81.31 96	84.02 59	56.32 230	74.05 87	88.98 64	53.34 97	87.92 49	69.23 104	88.42 32	87.59 68

CPTT-MVS		72.78 109	72.08 117	74.87 105	84.88 62	61.41 26	84.15 54	77.86 230	55.27 257	67.51 230	88.08 83	41.93 265	81.85 216	69.04 105	80.01 141	81.35 303

balanced_ft_v1		72.98 105	72.55 109	74.27 127	79.52 142	50.64 242	77.78 172	83.29 99	56.76 213	67.88 217	85.95 159	49.42 167	85.29 126	68.64 106	83.76 87	86.87 98

viewmamba		71.13 146	70.66 147	72.56 196	70.23 395	50.07 261	74.25 274	77.85 231	59.92 139	70.94 153	85.55 173	52.30 116	80.25 261	68.42 107	76.47 223	87.35 82

hybridcas		74.86 64	75.07 61	74.24 129	76.30 263	50.58 244	79.30 128	83.88 68	63.15 57	74.69 76	88.13 80	58.91 30	82.98 178	68.30 108	82.93 98	89.15 11

DeepC-MVS_fast	68.24 3	77.25 34	76.63 37	79.12 20	86.15 36	60.86 36	84.71 40	84.85 47	61.98 89	73.06 118	88.88 68	53.72 91	89.06 29	68.27 109	88.04 41	87.42 74
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		74.57 71	73.90 81	76.58 72	83.49 74	59.87 54	84.29 48	81.36 142	58.07 183	73.14 113	90.07 44	44.74 233	85.84 110	68.20 110	81.76 114	84.03 222

RE-MVS-def			73.71 86		83.49 74	59.87 54	84.29 48	81.36 142	58.07 183	73.14 113	90.07 44	43.06 252		68.20 110	81.76 114	84.03 222

E6new		74.10 78	74.09 75	74.15 135	77.14 233	50.74 237	78.24 149	83.85 74	62.34 76	73.95 90	87.27 105	55.98 59	82.95 181	68.17 112	79.85 144	88.77 19

E6		74.10 78	74.09 75	74.15 135	77.14 233	50.74 237	78.24 149	83.85 74	62.34 76	73.95 90	87.27 105	55.98 59	82.95 181	68.17 112	79.85 144	88.77 19

E5new		74.10 78	74.09 75	74.15 135	77.14 233	50.74 237	78.24 149	83.86 72	62.34 76	73.95 90	87.27 105	55.97 61	82.95 181	68.16 114	79.86 142	88.77 19

E5		74.10 78	74.09 75	74.15 135	77.14 233	50.74 237	78.24 149	83.86 72	62.34 76	73.95 90	87.27 105	55.97 61	82.95 181	68.16 114	79.86 142	88.77 19

HQP_MVS		74.31 74	73.73 85	76.06 79	81.41 103	56.31 114	84.22 51	84.01 60	64.52 28	69.27 185	86.10 152	45.26 227	87.21 65	68.16 114	80.58 130	84.65 202

plane_prior5								84.01 60					87.21 65	68.16 114	80.58 130	84.65 202

NormalMVS		76.26 49	75.74 52	77.83 50	82.75 86	59.89 52	84.36 46	83.21 103	64.69 23	74.21 85	87.40 98	49.48 164	86.17 99	68.04 118	87.55 47	87.42 74

SymmetryMVS		75.28 60	74.60 67	77.30 59	83.85 71	59.89 52	84.36 46	75.51 288	64.69 23	74.21 85	87.40 98	49.48 164	86.17 99	68.04 118	83.88 85	85.85 147

E4		73.91 84	73.83 84	74.15 135	77.13 237	50.47 250	77.15 196	83.79 77	62.21 81	73.61 98	87.19 112	56.08 57	83.03 173	67.91 120	79.35 156	88.94 14

CSCG		76.92 37	76.75 35	77.41 56	83.96 70	59.60 56	82.95 69	86.50 14	60.78 112	75.27 59	84.83 185	60.76 20	86.56 84	67.86 121	87.87 45	86.06 138

hybridnocas07		69.86 179	69.44 173	71.14 250	68.10 434	48.28 302	72.52 316	77.08 250	56.94 210	70.50 160	84.91 184	50.48 148	78.37 309	67.84 122	76.55 222	86.76 104

SPE-MVS-test		75.62 58	75.31 58	76.56 73	80.63 120	55.13 143	83.88 59	85.22 36	62.05 86	71.49 147	86.03 155	53.83 87	86.36 94	67.74 123	86.91 56	88.19 42

onestephybrid01		71.00 151	70.34 155	72.99 184	70.38 392	50.88 234	74.14 277	77.41 241	58.80 164	71.36 149	84.93 182	50.96 141	80.87 246	67.73 124	77.35 205	87.23 86

LPG-MVS_test		72.74 110	71.74 122	75.76 85	80.22 125	57.51 98	82.55 78	83.40 92	61.32 98	66.67 248	87.33 103	39.15 306	86.59 82	67.70 125	77.30 209	83.19 258

LGP-MVS_train				75.76 85	80.22 125	57.51 98		83.40 92	61.32 98	66.67 248	87.33 103	39.15 306	86.59 82	67.70 125	77.30 209	83.19 258

HPM-MVS_fast		74.30 75	73.46 91	76.80 65	84.45 66	59.04 76	83.65 63	81.05 157	60.15 134	70.43 161	89.84 53	41.09 285	85.59 115	67.61 127	82.90 100	85.77 153

MVS_111021_HR		74.02 82	73.46 91	75.69 88	83.01 82	60.63 40	77.29 190	78.40 222	61.18 103	70.58 159	85.97 158	54.18 80	84.00 154	67.52 128	82.98 97	82.45 280

E2		73.72 88	73.60 88	74.06 140	77.16 231	50.40 251	76.97 201	83.74 78	61.64 93	73.36 103	86.75 125	56.14 53	82.99 175	67.50 129	79.18 166	88.80 16

E3		73.72 88	73.60 88	74.06 140	77.16 231	50.40 251	76.97 201	83.74 78	61.64 93	73.36 103	86.76 122	56.13 54	82.99 175	67.50 129	79.18 166	88.80 16

ETV-MVS		74.46 73	73.84 83	76.33 76	79.27 148	55.24 142	79.22 129	85.00 45	64.97 22	72.65 128	79.46 322	53.65 95	87.87 50	67.45 131	82.91 99	85.89 144

DELS-MVS		74.76 66	74.46 69	75.65 90	77.84 204	52.25 210	75.59 240	84.17 57	63.76 41	73.15 112	82.79 238	59.58 25	86.80 76	67.24 132	86.04 67	87.89 52
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
viewcassd2359sk11		73.56 90	73.41 93	74.00 144	77.13 237	50.35 254	76.86 209	83.69 82	61.23 102	73.14 113	86.38 143	56.09 56	82.96 179	67.15 133	79.01 171	88.70 25

hybrid		69.38 200	68.93 185	70.75 260	67.86 438	48.20 304	72.49 318	76.90 254	55.23 259	70.42 162	84.34 205	49.76 161	77.62 331	67.11 134	76.20 226	86.42 119

TSAR-MVS + GP.		74.90 63	74.15 74	77.17 60	82.00 93	58.77 82	81.80 88	78.57 211	58.58 172	74.32 83	84.51 201	55.94 63	87.22 64	67.11 134	84.48 79	85.52 164

BP-MVS														67.04 136

HQP-MVS		73.45 92	72.80 104	75.40 94	80.66 117	54.94 145	82.31 82	83.90 65	62.10 83	67.85 218	85.54 175	45.46 221	86.93 73	67.04 136	80.35 136	84.32 212

viewmacassd2359aftdt		73.15 101	73.16 98	73.11 181	75.15 290	49.31 281	77.53 181	83.21 103	60.42 121	73.20 110	87.34 102	53.82 88	81.05 239	67.02 138	80.79 123	88.96 13

GDP-MVS		72.64 113	71.28 133	76.70 66	77.72 208	54.22 156	79.57 125	84.45 51	55.30 256	71.38 148	86.97 117	39.94 292	87.00 72	67.02 138	79.20 163	88.89 15

ACMP	63.53 6	72.30 122	71.20 135	75.59 93	80.28 123	57.54 96	82.74 74	82.84 118	60.58 117	65.24 282	86.18 149	39.25 304	86.03 105	66.95 140	76.79 218	83.22 256
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
E3new		73.41 94	73.22 96	73.95 147	77.06 242	50.31 255	76.78 212	83.66 83	60.90 108	72.93 121	86.02 156	55.99 58	82.95 181	66.89 141	78.77 176	88.61 27

viewmanbaseed2359cas		72.92 107	72.89 102	73.00 183	75.16 288	49.25 284	77.25 193	83.11 111	59.52 153	72.93 121	86.63 131	54.11 81	80.98 240	66.63 142	80.67 127	88.76 24

EI-MVSNet-Vis-set		72.42 120	71.59 123	74.91 103	78.47 176	54.02 158	77.05 199	79.33 189	65.03 19	71.68 142	79.35 325	52.75 107	84.89 135	66.46 143	74.23 255	85.83 149

DPM-MVS		75.47 59	75.00 62	76.88 63	81.38 105	59.16 67	79.94 115	85.71 29	56.59 223	72.46 131	86.76 122	56.89 43	87.86 51	66.36 144	88.91 29	83.64 246

patch_mono-2		69.85 180	71.09 137	66.16 345	79.11 156	54.80 149	71.97 327	74.31 312	53.50 303	70.90 155	84.17 207	57.63 38	63.31 443	66.17 145	82.02 110	80.38 329

MVSFormer		71.50 140	70.38 153	74.88 104	78.76 164	57.15 106	82.79 72	78.48 215	51.26 343	69.49 179	83.22 233	43.99 243	83.24 169	66.06 146	79.37 153	84.23 216

test_djsdf		69.45 198	67.74 216	74.58 116	74.57 307	54.92 147	82.79 72	78.48 215	51.26 343	65.41 275	83.49 229	38.37 317	83.24 169	66.06 146	69.25 349	85.56 163

sasdasda		74.67 68	74.98 63	73.71 158	78.94 159	50.56 247	80.23 108	83.87 69	60.30 129	77.15 44	86.56 136	59.65 22	82.00 213	66.01 148	82.12 107	88.58 29

canonicalmvs		74.67 68	74.98 63	73.71 158	78.94 159	50.56 247	80.23 108	83.87 69	60.30 129	77.15 44	86.56 136	59.65 22	82.00 213	66.01 148	82.12 107	88.58 29

MVS_Test		72.45 118	72.46 111	72.42 204	74.88 293	48.50 299	76.28 222	83.14 109	59.40 154	72.46 131	84.68 190	55.66 65	81.12 235	65.98 150	79.66 149	87.63 65

alignmvs		73.86 85	73.99 79	73.45 172	78.20 188	50.50 249	78.57 142	82.43 122	59.40 154	76.57 49	86.71 128	56.42 48	81.23 233	65.84 151	81.79 113	88.62 26

nrg030		72.96 106	73.01 100	72.84 188	75.41 282	50.24 256	80.02 113	82.89 117	58.36 179	74.44 80	86.73 126	58.90 31	80.83 247	65.84 151	74.46 251	87.44 73

MVS_111021_LR		69.50 196	68.78 189	71.65 225	78.38 179	59.33 61	74.82 261	70.11 361	58.08 182	67.83 223	84.68 190	41.96 263	76.34 363	65.62 153	77.54 200	79.30 353

EI-MVSNet-UG-set		71.92 131	71.06 138	74.52 120	77.98 199	53.56 170	76.62 214	79.16 190	64.40 30	71.18 150	78.95 330	52.19 118	84.66 142	65.47 154	73.57 268	85.32 178

viewdifsd2359ckpt07		71.90 132	71.97 118	71.69 223	74.81 297	48.08 309	75.30 245	80.49 169	60.00 137	71.63 143	86.33 145	56.34 49	79.25 280	65.40 155	77.41 204	87.76 60

PS-MVSNAJss		72.24 124	71.21 134	75.31 96	78.50 174	55.93 124	81.63 90	82.12 126	56.24 234	70.02 170	85.68 170	47.05 202	84.34 146	65.27 156	74.41 254	85.67 159

MSLP-MVS++		73.77 86	73.47 90	74.66 111	83.02 81	59.29 63	82.30 85	81.88 129	59.34 156	71.59 144	86.83 120	45.94 214	83.65 160	65.09 157	85.22 71	81.06 314

v2v482		70.50 163	69.45 172	73.66 161	72.62 346	50.03 263	77.58 176	80.51 168	59.90 140	69.52 178	82.14 266	47.53 193	84.88 137	65.07 158	70.17 328	86.09 137

RRT-MVS		71.46 141	70.70 146	73.74 156	77.76 207	49.30 282	76.60 215	80.45 170	61.25 101	68.17 205	84.78 187	44.64 235	84.90 134	64.79 159	77.88 196	87.03 92

jason		69.65 188	68.39 201	73.43 174	78.27 187	56.88 110	77.12 197	73.71 324	46.53 414	69.34 184	83.22 233	43.37 247	79.18 282	64.77 160	79.20 163	84.23 216
jason: jason.
anonymousdsp		67.00 263	64.82 284	73.57 167	70.09 400	56.13 119	76.35 220	77.35 244	48.43 384	64.99 290	80.84 296	33.01 382	80.34 257	64.66 161	67.64 367	84.23 216

lupinMVS		69.57 192	68.28 207	73.44 173	78.76 164	57.15 106	76.57 216	73.29 330	46.19 417	69.49 179	82.18 261	43.99 243	79.23 281	64.66 161	79.37 153	83.93 227

CLD-MVS		73.33 96	72.68 106	75.29 98	78.82 163	53.33 179	78.23 154	84.79 48	61.30 100	70.41 163	81.04 288	52.41 113	87.12 68	64.61 163	82.49 106	85.41 174
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PRO-TEST		71.42 143	71.02 139	72.62 193	78.68 167	52.64 200	78.04 163	81.04 158	56.33 229	68.21 202	82.15 265	50.03 154	81.69 219	64.20 164	80.51 133	83.52 249

V42		68.65 218	67.35 231	72.56 196	68.93 421	50.18 258	72.90 308	79.47 186	56.92 211	69.45 181	80.26 304	46.29 212	82.99 175	64.07 165	67.82 365	84.53 207

3Dnovator+	66.72 4	75.84 55	74.57 68	79.66 9	82.40 88	59.92 51	85.83 27	86.32 18	66.92 7	67.80 224	89.24 61	42.03 262	89.38 25	64.07 165	86.50 63	89.69 4

v1144		70.42 165	69.31 175	73.76 153	73.22 333	50.64 242	77.83 170	81.43 139	58.58 172	69.40 182	81.16 285	47.53 193	85.29 126	64.01 167	70.64 315	85.34 177

Effi-MVS+		73.31 97	72.54 110	75.62 91	77.87 202	53.64 167	79.62 124	79.61 183	61.63 95	72.02 138	82.61 243	56.44 47	85.97 107	63.99 168	79.07 169	87.25 85

MGCFI-Net		72.45 118	73.34 95	69.81 281	77.77 206	43.21 368	75.84 237	81.18 153	59.59 151	75.45 57	86.64 129	57.74 35	77.94 318	63.92 169	81.90 112	88.30 36

SDMVSNet		68.03 236	68.10 212	67.84 311	77.13 237	48.72 295	65.32 409	79.10 191	58.02 185	65.08 285	82.55 249	47.83 187	73.40 377	63.92 169	73.92 259	81.41 298

KinetiMVS		71.26 145	70.16 159	74.57 117	74.59 305	52.77 196	75.91 234	81.20 152	60.72 114	69.10 191	85.71 169	41.67 273	83.53 163	63.91 171	78.62 182	87.42 74

xiu_mvs_v1_base_debu		68.58 220	67.28 233	72.48 200	78.19 189	57.19 103	75.28 246	75.09 299	51.61 332	70.04 167	81.41 282	32.79 385	79.02 295	63.81 172	77.31 206	81.22 306

xiu_mvs_v1_base		68.58 220	67.28 233	72.48 200	78.19 189	57.19 103	75.28 246	75.09 299	51.61 332	70.04 167	81.41 282	32.79 385	79.02 295	63.81 172	77.31 206	81.22 306

xiu_mvs_v1_base_debi		68.58 220	67.28 233	72.48 200	78.19 189	57.19 103	75.28 246	75.09 299	51.61 332	70.04 167	81.41 282	32.79 385	79.02 295	63.81 172	77.31 206	81.22 306

viewdifsd2359ckpt09		73.42 93	72.45 112	76.30 77	77.25 229	53.27 180	80.36 107	82.48 121	57.96 188	72.24 134	85.73 168	53.22 98	86.27 97	63.79 175	79.06 170	89.36 7

Elysia		70.19 172	68.29 205	75.88 82	74.15 318	54.33 154	78.26 146	83.21 103	55.04 269	67.28 233	83.59 224	30.16 413	86.11 101	63.67 176	79.26 160	87.20 87

StellarMVS		70.19 172	68.29 205	75.88 82	74.15 318	54.33 154	78.26 146	83.21 103	55.04 269	67.28 233	83.59 224	30.16 413	86.11 101	63.67 176	79.26 160	87.20 87

v8		70.33 168	69.28 176	73.49 170	73.15 335	50.22 257	78.62 140	80.78 164	60.79 111	66.45 252	82.11 268	49.35 168	84.98 131	63.58 178	68.71 357	85.28 180

jajsoiax		68.25 230	66.45 251	73.66 161	75.62 275	55.49 137	80.82 101	78.51 214	52.33 321	64.33 298	84.11 209	28.28 434	81.81 218	63.48 179	70.62 316	83.67 242

mvs_tets		68.18 233	66.36 257	73.63 164	75.61 276	55.35 141	80.77 102	78.56 212	52.48 320	64.27 300	84.10 210	27.45 443	81.84 217	63.45 180	70.56 318	83.69 241

viewdifsd2359ckpt11		69.13 206	68.38 202	71.38 237	71.57 368	48.61 296	73.22 300	73.18 331	57.65 196	70.67 157	84.73 188	50.03 154	79.80 267	63.25 181	71.10 311	85.74 156

viewmsd2359difaftdt		69.13 206	68.38 202	71.38 237	71.57 368	48.61 296	73.22 300	73.18 331	57.65 196	70.67 157	84.73 188	50.03 154	79.80 267	63.25 181	71.10 311	85.74 156

AstraMVS		67.86 242	66.83 244	70.93 256	73.50 330	49.34 280	73.28 298	74.01 319	55.45 253	68.10 212	83.28 231	38.93 309	79.14 287	63.22 183	71.74 302	84.30 214

LuminaMVS		68.24 231	66.82 245	72.51 199	73.46 332	53.60 169	76.23 224	78.88 198	52.78 312	68.08 213	80.13 306	32.70 390	81.41 226	63.16 184	75.97 232	82.53 276

viewdifsd2359ckpt13		72.40 121	71.79 121	74.22 131	75.63 274	51.77 222	78.67 138	83.13 110	57.08 205	71.59 144	85.36 179	53.10 102	82.64 199	63.07 185	78.51 184	88.24 39

v144192		69.71 184	68.51 194	73.33 177	73.10 336	50.13 259	77.54 179	80.64 165	56.65 215	68.57 196	80.55 298	46.87 207	84.96 133	62.98 186	69.66 342	84.89 196

v1192		69.97 177	68.68 191	73.85 148	73.19 334	50.94 230	77.68 175	81.36 142	57.51 200	68.95 192	80.85 295	45.28 226	85.33 125	62.97 187	70.37 321	85.27 181

v10		70.21 170	69.02 181	73.81 150	73.51 329	50.92 232	78.74 136	81.39 140	60.05 136	66.39 254	81.83 273	47.58 192	85.41 124	62.80 188	68.86 356	85.09 188

OMC-MVS		71.40 144	70.60 148	73.78 151	76.60 258	53.15 183	79.74 121	79.78 179	58.37 178	68.75 193	86.45 141	45.43 223	80.60 251	62.58 189	77.73 197	87.58 69

XVG-OURS-SEG-HR		68.81 214	67.47 226	72.82 190	74.40 311	56.87 111	70.59 351	79.04 194	54.77 277	66.99 240	86.01 157	39.57 298	78.21 313	62.54 190	73.33 275	83.37 252

EPNet		73.09 103	72.16 115	75.90 81	75.95 269	56.28 116	83.05 67	72.39 340	66.53 11	65.27 278	87.00 116	50.40 149	85.47 121	62.48 191	86.32 65	85.94 141
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v1921920		69.47 197	68.17 209	73.36 176	73.06 337	50.10 260	77.39 184	80.56 166	56.58 224	68.59 194	80.37 300	44.72 234	84.98 131	62.47 192	69.82 336	85.00 190

c3_l		68.33 228	67.56 220	70.62 265	70.87 383	46.21 331	74.47 269	78.80 201	56.22 235	66.19 257	78.53 338	51.88 123	81.40 227	62.08 193	69.04 352	84.25 215

AUN-MVS		68.45 227	66.41 255	74.57 117	79.53 141	57.08 109	73.93 283	75.23 295	54.44 285	66.69 246	81.85 272	37.10 335	82.89 188	62.07 194	66.84 373	83.75 239

XVG-OURS		68.76 217	67.37 229	72.90 187	74.32 314	57.22 101	70.09 360	78.81 200	55.24 258	67.79 225	85.81 167	36.54 341	78.28 312	62.04 195	75.74 236	83.19 258

v1240		69.24 204	67.91 214	73.25 180	73.02 339	49.82 266	77.21 194	80.54 167	56.43 226	68.34 201	80.51 299	43.33 248	84.99 129	62.03 196	69.77 339	84.95 194

ET-MVSNet_ETH3D		67.96 239	65.72 269	74.68 110	76.67 256	55.62 134	75.11 251	74.74 304	52.91 310	60.03 359	80.12 307	33.68 374	82.64 199	61.86 197	76.34 224	85.78 150

VDD-MVS		72.50 116	72.09 116	73.75 155	81.58 99	49.69 274	77.76 174	77.63 236	63.21 55	73.21 109	89.02 63	42.14 261	83.32 167	61.72 198	82.50 105	88.25 38

casdiffseed414692147		73.73 87	73.22 96	75.28 99	76.76 253	52.16 212	80.05 112	83.01 112	63.38 47	73.35 105	87.11 114	53.22 98	84.14 148	61.71 199	80.38 135	89.55 6

PS-MVSNAJ		70.51 162	69.70 166	72.93 186	81.52 100	55.79 128	74.92 259	79.00 195	55.04 269	69.88 174	78.66 333	47.05 202	82.19 209	61.61 200	79.58 150	80.83 318

xiu_mvs_v2_base		70.52 161	69.75 164	72.84 188	81.21 109	55.63 132	75.11 251	78.92 197	54.92 274	69.96 173	79.68 317	47.00 206	82.09 211	61.60 201	79.37 153	80.81 319

cl22		67.47 251	66.45 251	70.54 267	69.85 406	46.49 327	73.85 286	77.35 244	55.07 266	65.51 273	77.92 347	47.64 191	81.10 236	61.58 202	69.32 346	84.01 224

viewmambaseed2359dif		68.91 211	68.18 208	71.11 251	70.21 396	48.05 312	72.28 322	75.90 277	51.96 327	70.93 154	84.47 202	51.37 134	78.59 307	61.55 203	74.97 246	86.68 108

miper_ehance_all_eth		68.03 236	67.24 237	70.40 269	70.54 387	46.21 331	73.98 279	78.68 205	55.07 266	66.05 261	77.80 354	52.16 119	81.31 230	61.53 204	69.32 346	83.67 242

MG-MVS		73.96 83	73.89 82	74.16 133	85.65 44	49.69 274	81.59 93	81.29 148	61.45 96	71.05 152	88.11 81	51.77 127	87.73 54	61.05 205	83.09 92	85.05 189

guyue		68.10 235	67.23 239	70.71 263	73.67 328	49.27 283	73.65 290	76.04 276	55.62 249	67.84 222	82.26 259	41.24 283	78.91 303	61.01 206	73.72 263	83.94 226

miper_enhance_ethall		67.11 260	66.09 264	70.17 273	69.21 415	45.98 333	72.85 309	78.41 221	51.38 340	65.65 271	75.98 390	51.17 138	81.25 231	60.82 207	69.32 346	83.29 255

ACMM	61.98 7	70.80 158	69.73 165	74.02 142	80.59 122	58.59 84	82.68 75	82.02 128	55.46 252	67.18 237	84.39 204	38.51 315	83.17 171	60.65 208	76.10 231	80.30 334
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+-dtu		69.64 189	67.53 223	75.95 80	76.10 267	62.29 15	80.20 111	76.06 275	59.83 145	65.26 281	77.09 367	41.56 276	84.02 153	60.60 209	71.09 313	81.53 296

PVSNet_Blended_VisFu		71.45 142	70.39 152	74.65 112	82.01 92	58.82 81	79.93 116	80.35 173	55.09 263	65.82 270	82.16 264	49.17 172	82.64 199	60.34 210	78.62 182	82.50 279

MVSTER		67.16 259	65.58 272	71.88 214	70.37 393	49.70 272	70.25 358	78.45 218	51.52 335	69.16 189	80.37 300	38.45 316	82.50 203	60.19 211	71.46 306	83.44 251

EIA-MVS		71.78 134	70.60 148	75.30 97	79.85 134	53.54 171	77.27 192	83.26 102	57.92 190	66.49 250	79.39 323	52.07 121	86.69 79	60.05 212	79.14 168	85.66 160

v148		68.24 231	67.19 240	71.40 236	70.43 390	47.77 315	75.76 238	77.03 252	58.91 162	67.36 231	80.10 308	48.60 180	81.89 215	60.01 213	66.52 377	84.53 207

test_vis1_n_1920		58.86 373	59.06 362	58.25 422	63.76 463	43.14 370	67.49 389	66.36 395	40.22 463	65.89 266	71.95 428	31.04 405	59.75 457	59.94 214	64.90 387	71.85 446

CANet_DTU		68.18 233	67.71 219	69.59 284	74.83 296	46.24 330	78.66 139	76.85 256	59.60 148	63.45 309	82.09 269	35.25 353	77.41 335	59.88 215	78.76 177	85.14 184

IterMVS-LS		69.22 205	68.48 195	71.43 235	74.44 310	49.40 278	76.23 224	77.55 237	59.60 148	65.85 268	81.59 280	51.28 136	81.58 223	59.87 216	69.90 335	83.30 253
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		69.27 203	68.44 199	71.73 220	74.47 308	49.39 279	75.20 249	78.45 218	59.60 148	69.16 189	76.51 380	51.29 135	82.50 203	59.86 217	71.45 307	83.30 253

3Dnovator	64.47 5	72.49 117	71.39 129	75.79 84	77.70 209	58.99 78	80.66 105	83.15 108	62.24 80	65.46 274	86.59 134	42.38 260	85.52 117	59.59 218	84.72 73	82.85 268

eth_miper_zixun_eth		67.63 248	66.28 261	71.67 224	71.60 367	48.33 301	73.68 289	77.88 229	55.80 243	65.91 264	78.62 336	47.35 199	82.88 189	59.45 219	66.25 378	83.81 234

DIV-MVS_self_test		67.18 257	66.26 262	69.94 276	70.20 397	45.74 335	73.29 297	76.83 258	55.10 261	65.27 278	79.58 318	47.38 198	80.53 253	59.43 220	69.22 350	83.54 247

cl____		67.18 257	66.26 262	69.94 276	70.20 397	45.74 335	73.30 295	76.83 258	55.10 261	65.27 278	79.57 319	47.39 197	80.53 253	59.41 221	69.22 350	83.53 248

mvsmamba		68.47 225	66.56 248	74.21 132	79.60 138	52.95 187	74.94 258	75.48 289	52.09 326	60.10 357	83.27 232	36.54 341	84.70 139	59.32 222	77.69 198	84.99 192

icg_test_0407_2		66.41 277	66.75 246	65.37 363	77.06 242	49.73 268	63.79 425	78.60 207	52.70 313	66.19 257	82.58 244	45.17 229	63.65 442	59.20 223	75.46 241	82.74 270

IMVS_0407		68.90 212	67.93 213	71.82 216	77.06 242	49.73 268	74.40 272	78.60 207	52.70 313	66.19 257	82.58 244	45.17 229	83.00 174	59.20 223	75.46 241	82.74 270

IMVS_0404		64.63 300	64.22 288	65.88 353	77.06 242	49.73 268	64.40 418	78.60 207	52.70 313	53.16 446	82.58 244	34.82 358	65.16 436	59.20 223	75.46 241	82.74 270

IMVS_0403		69.09 208	68.14 210	71.95 211	77.06 242	49.73 268	74.51 267	78.60 207	52.70 313	66.69 246	82.58 244	46.43 210	83.38 166	59.20 223	75.46 241	82.74 270

VortexMVS		66.41 277	65.50 273	69.16 294	73.75 324	48.14 306	73.41 293	78.28 225	53.73 299	64.98 291	78.33 339	40.62 288	79.07 290	58.88 227	67.50 368	80.26 335

SSM_0407		70.41 166	68.96 184	74.75 107	78.65 169	53.46 173	77.28 191	80.00 177	53.88 294	68.14 207	84.61 195	43.21 249	86.26 98	58.80 228	76.11 228	84.54 204

SSM_0404		70.84 154	69.41 174	75.12 101	79.20 151	53.86 160	77.89 166	80.00 177	53.88 294	69.40 182	84.61 195	43.21 249	86.56 84	58.80 228	77.68 199	84.95 194

reproduce_monomvs		62.56 327	61.20 336	66.62 335	70.62 386	44.30 353	70.13 359	73.13 334	54.78 276	61.13 349	76.37 383	25.63 459	75.63 367	58.75 230	60.29 437	79.93 341

旧先验2							76.08 228		45.32 425	76.55 50			65.56 433	58.75 230

VDDNet		71.81 133	71.33 131	73.26 179	82.80 85	47.60 319	78.74 136	75.27 293	59.59 151	72.94 120	89.40 58	41.51 278	83.91 155	58.75 230	82.99 95	88.26 37

mmtdpeth		60.40 360	59.12 360	64.27 374	69.59 408	48.99 288	70.67 350	70.06 362	54.96 273	62.78 320	73.26 418	27.00 448	67.66 415	58.44 233	45.29 485	76.16 396

dtuplus		68.48 224	67.76 215	70.63 264	70.33 394	48.09 308	72.62 312	75.88 279	52.33 321	71.09 151	84.66 192	50.09 153	77.93 320	58.02 234	74.82 249	85.87 145

114514_t		70.83 156	69.56 168	74.64 113	86.21 33	54.63 150	82.34 81	81.81 131	48.22 387	63.01 318	85.83 164	40.92 287	87.10 69	57.91 235	79.79 146	82.18 285

Vis-MVSNet		72.18 125	71.37 130	74.61 114	81.29 106	55.41 138	80.90 100	78.28 225	60.73 113	69.23 188	88.09 82	44.36 239	82.65 198	57.68 236	81.75 116	85.77 153
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_cas_vis1_n_1920		56.91 392	56.71 385	57.51 431	59.13 486	45.40 341	63.58 426	61.29 443	36.24 474	67.14 238	71.85 429	29.89 417	56.69 473	57.65 237	63.58 402	70.46 462

PAPM_NR		72.63 114	71.80 120	75.13 100	81.72 98	53.42 177	79.91 117	83.28 101	59.14 158	66.31 256	85.90 161	51.86 124	86.06 103	57.45 238	80.62 128	85.91 143

LFMVS		71.78 134	71.59 123	72.32 206	83.40 77	46.38 328	79.75 120	71.08 350	64.18 35	72.80 125	88.64 74	42.58 257	83.72 158	57.41 239	84.49 78	86.86 99

v7n		69.01 210	67.36 230	73.98 145	72.51 350	52.65 198	78.54 144	81.30 147	60.26 131	62.67 324	81.62 277	43.61 245	84.49 143	57.01 240	68.70 358	84.79 199

GeoE		71.01 150	70.15 160	73.60 166	79.57 140	52.17 211	78.93 133	78.12 227	58.02 185	67.76 227	83.87 215	52.36 114	82.72 196	56.90 241	75.79 235	85.92 142

FA-MVS(test-final)		69.82 181	68.48 195	73.84 149	78.44 177	50.04 262	75.58 242	78.99 196	58.16 181	67.59 228	82.14 266	42.66 255	85.63 113	56.60 242	76.19 227	85.84 148

mamba_0408		67.78 245	65.42 274	74.85 106	78.65 169	53.46 173	50.83 484	79.09 192	53.75 297	68.14 207	83.83 217	41.79 271	86.56 84	56.58 243	76.11 228	84.54 204

SSM_04072		64.98 296	65.42 274	63.68 378	78.65 169	53.46 173	50.83 484	79.09 192	53.75 297	68.14 207	83.83 217	41.79 271	53.03 487	56.58 243	76.11 228	84.54 204

mvs_anonymous		68.03 236	67.51 224	69.59 284	72.08 359	44.57 351	71.99 326	75.23 295	51.67 330	67.06 239	82.57 248	54.68 75	77.94 318	56.56 245	75.71 237	86.26 134

Patchmatch-RL test		58.16 383	55.49 399	66.15 346	67.92 437	48.89 292	60.66 447	51.07 480	47.86 397	59.36 370	62.71 481	34.02 369	72.27 386	56.41 246	59.40 440	77.30 381

miper_lstm_enhance		62.03 340	60.88 341	65.49 360	66.71 447	46.25 329	56.29 467	75.70 282	50.68 351	61.27 347	75.48 397	40.21 291	68.03 413	56.31 247	65.25 385	82.18 285

thisisatest0530		67.92 240	65.78 268	74.33 125	76.29 264	51.03 229	76.89 206	74.25 315	53.67 301	65.59 272	81.76 275	35.15 354	85.50 119	55.94 248	72.47 290	86.47 118

EPP-MVSNet		72.16 128	71.31 132	74.71 108	78.68 167	49.70 272	82.10 86	81.65 133	60.40 122	65.94 263	85.84 163	51.74 128	86.37 93	55.93 249	79.55 152	88.07 49

PVSNet_BlendedMVS		68.56 223	67.72 217	71.07 253	77.03 248	50.57 245	74.50 268	81.52 135	53.66 302	64.22 303	79.72 316	49.13 173	82.87 190	55.82 250	73.92 259	79.77 348

PVSNet_Blended		68.59 219	67.72 217	71.19 245	77.03 248	50.57 245	72.51 317	81.52 135	51.91 328	64.22 303	77.77 357	49.13 173	82.87 190	55.82 250	79.58 150	80.14 338

PAPR		71.72 137	70.82 143	74.41 123	81.20 110	51.17 226	79.55 126	83.33 97	55.81 242	66.93 242	84.61 195	50.95 142	86.06 103	55.79 252	79.20 163	86.00 139

tttt0517		67.83 244	65.66 270	74.33 125	76.69 254	50.82 235	77.86 168	73.99 320	54.54 283	64.64 295	82.53 252	35.06 355	85.50 119	55.71 253	69.91 334	86.67 109

IterMVS-SCA-FT		62.49 328	61.52 328	65.40 362	71.99 362	50.80 236	71.15 341	69.63 366	45.71 423	60.61 353	77.93 346	37.45 327	65.99 431	55.67 254	63.50 403	79.42 351

tt0805		67.77 246	67.24 237	69.34 289	74.87 294	40.08 404	77.36 185	81.37 141	55.31 255	66.33 255	84.65 193	37.35 329	82.55 202	55.65 255	72.28 295	85.39 175

XVG-ACMP-BASELINE		64.36 305	62.23 320	70.74 261	72.35 355	52.45 207	70.80 349	78.45 218	53.84 296	59.87 362	81.10 287	16.24 484	79.32 279	55.64 256	71.76 301	80.47 325

Anonymous20231211		69.28 202	68.47 197	71.73 220	80.28 123	47.18 323	79.98 114	82.37 123	54.61 280	67.24 235	84.01 212	39.43 299	82.41 206	55.45 257	72.83 284	85.62 162

GA-MVS		65.53 287	63.70 296	71.02 255	70.87 383	48.10 307	70.48 353	74.40 310	56.69 214	64.70 294	76.77 372	33.66 375	81.10 236	55.42 258	70.32 324	83.87 231

test_yl		69.69 185	69.13 178	71.36 240	78.37 181	45.74 335	74.71 263	80.20 174	57.91 191	70.01 171	83.83 217	42.44 258	82.87 190	54.97 259	79.72 147	85.48 166

DCV-MVSNet		69.69 185	69.13 178	71.36 240	78.37 181	45.74 335	74.71 263	80.20 174	57.91 191	70.01 171	83.83 217	42.44 258	82.87 190	54.97 259	79.72 147	85.48 166

1314		64.61 301	63.21 308	68.80 298	71.87 364	47.46 320	73.95 281	78.39 223	42.88 448	59.97 360	76.60 379	38.11 322	79.39 278	54.84 261	72.32 293	79.55 349

Fast-Effi-MVS+-dtu		67.37 252	65.33 279	73.48 171	72.94 341	57.78 94	77.47 182	76.88 255	57.60 199	61.97 336	76.85 371	39.31 302	80.49 256	54.72 262	70.28 325	82.17 287

UniMVSNet_NR-MVSNet		71.11 147	71.00 140	71.44 233	79.20 151	44.13 354	76.02 232	82.60 120	66.48 12	68.20 203	84.60 198	56.82 44	82.82 194	54.62 263	70.43 319	87.36 81

DU-MVS		70.01 175	69.53 169	71.44 233	78.05 196	44.13 354	75.01 255	81.51 137	64.37 31	68.20 203	84.52 199	49.12 175	82.82 194	54.62 263	70.43 319	87.37 79

FIs		70.82 157	71.43 127	68.98 296	78.33 185	38.14 426	76.96 203	83.59 86	61.02 106	67.33 232	86.73 126	55.07 68	81.64 220	54.61 265	79.22 162	87.14 90

VPA-MVSNet		69.02 209	69.47 171	67.69 315	77.42 223	41.00 397	74.04 278	79.68 181	60.06 135	69.26 187	84.81 186	51.06 140	77.58 332	54.44 266	74.43 253	84.48 209

MonoMVSNet		64.15 308	63.31 306	66.69 331	70.51 388	44.12 356	74.47 269	74.21 316	57.81 193	63.03 316	76.62 376	38.33 318	77.31 338	54.22 267	60.59 436	78.64 362

Anonymous20240529		69.91 178	69.02 181	72.56 196	80.19 128	47.65 316	77.56 178	80.99 160	55.45 253	69.88 174	86.76 122	39.24 305	82.18 210	54.04 268	77.10 213	87.85 55

UniMVSNet (Re)		70.63 160	70.20 157	71.89 213	78.55 173	45.29 342	75.94 233	82.92 114	63.68 43	68.16 206	83.59 224	53.89 86	83.49 165	53.97 269	71.12 310	86.89 97

D2MVS		62.30 335	60.29 350	68.34 306	66.46 450	48.42 300	65.70 401	73.42 326	47.71 398	58.16 387	75.02 401	30.51 408	77.71 328	53.96 270	71.68 304	78.90 360

原ACMM1				74.69 109	85.39 49	59.40 59		83.42 91	51.47 339	70.27 165	86.61 133	48.61 179	86.51 89	53.85 271	87.96 43	78.16 367

无先验							79.66 123	74.30 313	48.40 385				80.78 249	53.62 272		79.03 358

UA-Net		73.13 102	72.93 101	73.76 153	83.58 73	51.66 223	78.75 135	77.66 235	67.75 4	72.61 129	89.42 57	49.82 159	83.29 168	53.61 273	83.14 91	86.32 129

VNet		69.68 187	70.19 158	68.16 309	79.73 136	41.63 390	70.53 352	77.38 243	60.37 125	70.69 156	86.63 131	51.08 139	77.09 342	53.61 273	81.69 118	85.75 155

Fast-Effi-MVS+		70.28 169	69.12 180	73.73 157	78.50 174	51.50 224	75.01 255	79.46 187	56.16 236	68.59 194	79.55 320	53.97 84	84.05 150	53.34 275	77.53 201	85.65 161

testdata				64.66 369	81.52 100	52.93 188		65.29 404	46.09 418	73.88 94	87.46 97	38.08 323	66.26 428	53.31 276	78.48 185	74.78 415

thisisatest0515		65.83 283	63.50 301	72.82 190	73.75 324	49.50 277	71.32 336	73.12 335	49.39 368	63.82 305	76.50 382	34.95 357	84.84 138	53.20 277	75.49 240	84.13 221

MVS		67.37 252	66.33 258	70.51 268	75.46 280	50.94 230	73.95 281	81.85 130	41.57 455	62.54 328	78.57 337	47.98 184	85.47 121	52.97 278	82.05 109	75.14 407

IterMVS		62.79 325	61.27 333	67.35 322	69.37 412	52.04 216	71.17 339	68.24 380	52.63 319	59.82 363	76.91 370	37.32 330	72.36 383	52.80 279	63.19 407	77.66 376
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		69.80 183	70.58 150	67.46 319	77.61 218	34.73 460	76.05 230	83.19 107	60.84 110	65.88 267	86.46 140	54.52 77	80.76 250	52.52 280	78.12 192	86.91 96

TranMVSNet+NR-MVSNet		70.36 167	70.10 162	71.17 248	78.64 172	42.97 375	76.53 217	81.16 155	66.95 6	68.53 197	85.42 177	51.61 130	83.07 172	52.32 281	69.70 341	87.46 72

Baseline_NR-MVSNet		67.05 261	67.56 220	65.50 359	75.65 273	37.70 432	75.42 243	74.65 308	59.90 140	68.14 207	83.15 236	49.12 175	77.20 340	52.23 282	69.78 337	81.60 293

UniMVSNet_ETH3D		67.60 249	67.07 242	69.18 293	77.39 224	42.29 381	74.18 276	75.59 285	60.37 125	66.77 244	86.06 154	37.64 325	78.93 301	52.16 283	73.49 270	86.32 129

ECVR-MVS		67.72 247	67.51 224	68.35 305	79.46 143	36.29 449	74.79 262	66.93 390	58.72 166	67.19 236	88.05 84	36.10 345	81.38 228	52.07 284	84.25 80	87.39 77

test1111		67.21 254	67.14 241	67.42 320	79.24 149	34.76 459	73.89 285	65.65 400	58.71 168	66.96 241	87.95 88	36.09 346	80.53 253	52.03 285	83.79 86	86.97 94

test2506		65.33 291	64.61 285	67.50 316	79.46 143	34.19 465	74.43 271	51.92 476	58.72 166	66.75 245	88.05 84	25.99 456	80.92 244	51.94 286	84.25 80	87.39 77

API-MVS		72.17 126	71.41 128	74.45 122	81.95 95	57.22 101	84.03 56	80.38 172	59.89 144	68.40 199	82.33 256	49.64 162	87.83 52	51.87 287	84.16 83	78.30 365

PCF-MVS	61.88 8	70.95 153	69.49 170	75.35 95	77.63 213	55.71 129	76.04 231	81.81 131	50.30 356	69.66 177	85.40 178	52.51 110	84.89 135	51.82 288	80.24 138	85.45 170
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DP-MVS Recon		72.15 129	70.73 145	76.40 74	86.57 26	57.99 90	81.15 98	82.96 113	57.03 208	66.78 243	85.56 171	44.50 237	88.11 44	51.77 289	80.23 139	83.10 263

UGNet		68.81 214	67.39 228	73.06 182	78.33 185	54.47 151	79.77 119	75.40 291	60.45 120	63.22 311	84.40 203	32.71 389	80.91 245	51.71 290	80.56 132	83.81 234
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
MAR-MVS		71.51 139	70.15 160	75.60 92	81.84 96	59.39 60	81.38 95	82.90 115	54.90 275	68.08 213	78.70 331	47.73 188	85.51 118	51.68 291	84.17 82	81.88 291
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
VPNet		67.52 250	68.11 211	65.74 355	79.18 153	36.80 441	72.17 324	72.83 336	62.04 87	67.79 225	85.83 164	48.88 177	76.60 358	51.30 292	72.97 282	83.81 234

test_fmvs1_n		51.37 432	50.35 435	54.42 446	52.85 494	37.71 431	61.16 444	51.93 475	28.15 487	63.81 306	69.73 452	13.72 488	53.95 484	51.16 293	60.65 434	71.59 449

test_fmvs1		51.32 434	50.48 434	53.81 449	53.57 492	37.51 433	60.63 448	51.16 478	28.02 489	63.62 307	69.23 456	16.41 483	53.93 485	51.01 294	60.70 433	69.99 466

QAPM		70.05 174	68.81 188	73.78 151	76.54 260	53.43 176	83.23 65	83.48 88	52.89 311	65.90 265	86.29 146	41.55 277	86.49 90	51.01 294	78.40 188	81.42 297

NR-MVSNet		69.54 193	68.85 186	71.59 227	78.05 196	43.81 359	74.20 275	80.86 163	65.18 15	62.76 322	84.52 199	52.35 115	83.59 162	50.96 296	70.78 314	87.37 79

IB-MVS	56.42 12	65.40 290	62.73 314	73.40 175	74.89 292	52.78 195	73.09 304	75.13 298	55.69 245	58.48 383	73.73 413	32.86 384	86.32 95	50.63 297	70.11 329	81.10 312
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
PM-MVS		52.33 427	50.19 436	58.75 419	62.10 472	45.14 343	65.75 400	40.38 503	43.60 439	53.52 442	72.65 419	9.16 502	65.87 432	50.41 298	54.18 462	65.24 479

cascas		65.98 281	63.42 303	73.64 163	77.26 228	52.58 202	72.26 323	77.21 247	48.56 380	61.21 348	74.60 405	32.57 396	85.82 111	50.38 299	76.75 219	82.52 278

IS-MVSNet		71.57 138	71.00 140	73.27 178	78.86 161	45.63 339	80.22 110	78.69 204	64.14 38	66.46 251	87.36 101	49.30 169	85.60 114	50.26 300	83.71 89	88.59 28

WR-MVS		68.47 225	68.47 197	68.44 304	80.20 127	39.84 408	73.75 288	76.07 274	64.68 25	68.11 211	83.63 223	50.39 150	79.14 287	49.78 301	69.66 342	86.34 124

CVMVSNet		59.63 368	59.14 359	61.08 403	74.47 308	38.84 419	75.20 249	68.74 376	31.15 483	58.24 385	76.51 380	32.39 399	68.58 409	49.77 302	65.84 381	75.81 399

CostFormer		64.04 310	62.51 315	68.61 301	71.88 363	45.77 334	71.30 337	70.60 358	47.55 401	64.31 299	76.61 378	41.63 274	79.62 272	49.74 303	69.00 353	80.42 327

新几何1				70.76 259	85.66 43	61.13 30		66.43 394	44.68 429	70.29 164	86.64 129	41.29 280	75.23 369	49.72 304	81.75 116	75.93 398

test-LLR		58.15 384	58.13 373	58.22 423	68.57 425	44.80 345	65.46 406	57.92 455	50.08 359	55.44 415	69.82 450	32.62 393	57.44 469	49.66 305	73.62 266	72.41 439

test-mter		56.42 397	55.82 395	58.22 423	68.57 425	44.80 345	65.46 406	57.92 455	39.94 467	55.44 415	69.82 450	21.92 470	57.44 469	49.66 305	73.62 266	72.41 439

Anonymous202405211		66.84 266	65.99 265	69.40 288	80.19 128	42.21 383	71.11 342	71.31 349	58.80 164	67.90 215	86.39 142	29.83 418	79.65 270	49.60 307	78.78 175	86.33 127

test_fmvs2		48.69 441	47.49 446	52.29 461	48.63 501	33.06 474	57.76 460	48.05 490	25.71 493	59.76 365	69.60 454	11.57 495	52.23 491	49.45 308	56.86 450	71.58 450

testing915		67.86 242	68.34 204	66.42 338	78.35 183	40.04 406	75.04 254	71.84 346	58.41 176	66.43 253	83.87 215	50.32 152	78.04 316	49.26 309	81.49 119	81.19 309

tpmrst		58.24 382	58.70 366	56.84 432	66.97 444	34.32 463	69.57 370	61.14 444	47.17 408	58.58 382	71.60 430	41.28 281	60.41 453	49.20 310	62.84 410	75.78 400

test_vis1_n		49.89 439	48.69 441	53.50 452	53.97 491	37.38 434	61.53 438	47.33 492	28.54 486	59.62 367	67.10 469	13.52 489	52.27 490	49.07 311	57.52 447	70.84 459

pm-mvs1		65.24 292	64.97 283	66.04 349	72.38 354	39.40 415	72.62 312	75.63 283	55.53 250	62.35 335	83.18 235	47.45 195	76.47 361	49.06 312	66.54 376	82.24 284

gm-plane-assit					71.40 375	41.72 389			48.85 377		73.31 416		82.48 205	48.90 313

CMPMVS	42.80 21	57.81 387	55.97 393	63.32 381	60.98 480	47.38 321	64.66 416	69.50 369	32.06 481	46.83 473	77.80 354	29.50 421	71.36 391	48.68 314	73.75 262	71.21 455
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ab-mvs		66.65 271	66.42 254	67.37 321	76.17 266	41.73 387	70.41 355	76.14 273	53.99 291	65.98 262	83.51 228	49.48 164	76.24 364	48.60 315	73.46 272	84.14 220

OurMVSNet-221017-0		61.37 352	58.63 367	69.61 283	72.05 360	48.06 310	73.93 283	72.51 338	47.23 407	54.74 426	80.92 292	21.49 474	81.24 232	48.57 316	56.22 454	79.53 350

OpenMVS	61.03 9	68.85 213	67.56 220	72.70 192	74.26 316	53.99 159	81.21 97	81.34 146	52.70 313	62.75 323	85.55 173	38.86 310	84.14 148	48.41 317	83.01 93	79.97 340

testing91		64.46 303	63.80 294	66.47 337	78.43 178	40.06 405	67.63 386	69.59 367	59.06 159	63.18 313	78.05 343	34.05 367	76.99 347	48.30 318	75.87 234	82.37 282

testing99		64.05 309	63.29 307	66.34 340	78.17 192	39.76 410	67.33 391	68.00 381	58.60 171	63.03 316	78.10 342	32.57 396	76.94 349	48.22 319	75.58 238	82.34 283

baseline2		63.42 315	61.26 334	69.89 280	72.55 348	47.62 317	71.54 333	68.38 378	50.11 358	54.82 425	75.55 395	43.06 252	80.96 241	48.13 320	67.16 372	81.11 311

TESTMET0.1,1		55.28 408	54.90 404	56.42 434	66.56 448	43.67 361	65.46 406	56.27 466	39.18 469	53.83 436	67.44 465	24.21 465	55.46 480	48.04 321	73.11 280	70.13 465

test_fmvs3		44.30 449	42.55 452	49.55 467	42.83 506	27.15 498	53.03 476	44.93 496	22.03 501	53.69 439	64.94 476	4.21 510	49.63 494	47.47 322	49.82 477	71.88 445

usedtu_blend_shiyan5		62.63 326	60.77 344	68.20 307	68.53 427	44.64 348	73.47 292	77.00 253	51.91 328	57.10 398	69.95 446	38.83 311	79.61 273	47.44 323	62.67 411	80.37 330

blend_shiyan4		61.38 351	59.10 361	68.20 307	68.94 420	44.64 348	70.81 348	76.52 264	51.63 331	57.56 394	69.94 449	28.30 433	79.61 273	47.44 323	60.78 432	80.36 333

K. test v3		60.47 359	57.11 378	70.56 266	73.74 326	48.22 303	75.10 253	62.55 433	58.27 180	53.62 440	76.31 384	27.81 439	81.59 222	47.42 325	39.18 493	81.88 291

pmmvs6		63.69 313	62.82 313	66.27 343	70.63 385	39.27 416	73.13 303	75.47 290	52.69 318	59.75 366	82.30 257	39.71 297	77.03 344	47.40 326	64.35 394	82.53 276

blended_shiyan8		62.46 330	60.71 345	67.71 313	69.15 417	43.43 363	70.83 346	76.52 264	51.49 337	57.67 391	71.36 434	39.38 300	79.07 290	47.37 327	62.67 411	80.62 323

blended_shiyan6		62.46 330	60.71 345	67.71 313	69.14 418	43.42 364	70.82 347	76.52 264	51.50 336	57.64 392	71.37 433	39.38 300	79.08 289	47.36 328	62.67 411	80.65 322

sd_testset		64.46 303	64.45 286	64.51 371	77.13 237	42.25 382	62.67 432	72.11 343	58.02 185	65.08 285	82.55 249	41.22 284	69.88 403	47.32 329	73.92 259	81.41 298

baseline1		63.81 312	63.87 293	63.62 379	76.29 264	36.36 444	71.78 331	67.29 386	56.05 238	64.23 302	82.95 237	47.11 201	74.41 373	47.30 330	61.85 424	80.10 339

gbinet_0.2-2-1-0.02		62.43 332	60.41 348	68.49 302	68.91 422	43.71 360	71.73 332	75.89 278	52.10 325	58.33 384	69.67 453	36.86 339	80.59 252	47.18 331	63.05 409	81.16 310

GBi-Net		67.21 254	66.55 249	69.19 290	77.63 213	43.33 365	77.31 186	77.83 232	56.62 219	65.04 287	82.70 239	41.85 268	80.33 258	47.18 331	72.76 285	83.92 228

test1		67.21 254	66.55 249	69.19 290	77.63 213	43.33 365	77.31 186	77.83 232	56.62 219	65.04 287	82.70 239	41.85 268	80.33 258	47.18 331	72.76 285	83.92 228

FMVSNet3		66.32 279	65.61 271	68.46 303	76.48 261	42.34 380	74.98 257	77.15 248	55.83 241	65.04 287	81.16 285	39.91 293	80.14 266	47.18 331	72.76 285	82.90 267

wanda-best-256-512		62.00 342	60.17 351	67.49 317	68.53 427	43.07 372	69.65 364	76.38 268	51.26 343	57.10 398	69.95 446	38.83 311	79.04 293	47.14 335	62.67 411	80.37 330

FE-blended-shiyan7		62.00 342	60.17 351	67.49 317	68.53 427	43.07 372	69.65 364	76.38 268	51.26 343	57.10 398	69.95 446	38.83 311	79.04 293	47.14 335	62.67 411	80.37 330

FMVSNet2		66.93 264	66.31 260	68.79 299	77.63 213	42.98 374	76.11 227	77.47 238	56.62 219	65.22 284	82.17 263	41.85 268	80.18 265	47.05 337	72.72 288	83.20 257

testdata2													72.18 388	46.95 338

BH-RMVSNet		68.81 214	67.42 227	72.97 185	80.11 131	52.53 203	74.26 273	76.29 270	58.48 174	68.38 200	84.20 206	42.59 256	83.83 156	46.53 339	75.91 233	82.56 274

AdaColmap		69.99 176	68.66 192	73.97 146	84.94 59	57.83 92	82.63 76	78.71 203	56.28 233	64.34 297	84.14 208	41.57 275	87.06 71	46.45 340	78.88 172	77.02 386

EG-PatchMatch MVS		64.71 298	62.87 311	70.22 270	77.68 210	53.48 172	77.99 164	78.82 199	53.37 304	56.03 411	77.41 362	24.75 464	84.04 151	46.37 341	73.42 274	73.14 428

usedtu_dtu_shiyan1		64.34 306	63.57 298	66.66 332	72.44 352	40.74 400	69.60 367	76.80 260	53.21 306	61.73 341	77.92 347	41.92 266	77.68 329	46.23 342	72.25 296	81.57 294

FE-MVSNET3		64.34 306	63.57 298	66.66 332	72.44 352	40.74 400	69.60 367	76.80 260	53.21 306	61.73 341	77.92 347	41.92 266	77.68 329	46.23 342	72.25 296	81.57 294

1112_ss		64.00 311	63.36 304	65.93 351	79.28 147	42.58 379	71.35 335	72.36 341	46.41 415	60.55 354	77.89 351	46.27 213	73.28 378	46.18 344	69.97 332	81.92 290

FMVSNet1		66.70 270	65.87 266	69.19 290	77.49 221	43.33 365	77.31 186	77.83 232	56.45 225	64.60 296	82.70 239	38.08 323	80.33 258	46.08 345	72.31 294	83.92 228

HyFIR lowres test		65.67 285	63.01 310	73.67 160	79.97 133	55.65 131	69.07 375	75.52 287	42.68 449	63.53 308	77.95 345	40.43 290	81.64 220	46.01 346	71.91 300	83.73 240

lessismore_v0				69.91 278	71.42 374	47.80 313		50.90 481		50.39 461	75.56 394	27.43 444	81.33 229	45.91 347	34.10 499	80.59 324

CHOSEN 1792x2688		65.08 295	62.84 312	71.82 216	81.49 102	56.26 117	66.32 397	74.20 317	40.53 461	63.16 314	78.65 334	41.30 279	77.80 325	45.80 348	74.09 256	81.40 300

LCM-MVSNet-Re		61.88 345	61.35 331	63.46 380	74.58 306	31.48 481	61.42 440	58.14 454	58.71 168	53.02 448	79.55 320	43.07 251	76.80 351	45.69 349	77.96 194	82.11 288

ambc				65.13 367	63.72 465	37.07 438	47.66 492	78.78 202		54.37 433	71.42 431	11.24 497	80.94 242	45.64 350	53.85 466	77.38 380

MS-PatchMatch		62.42 333	61.46 329	65.31 365	75.21 286	52.10 213	72.05 325	74.05 318	46.41 415	57.42 397	74.36 406	34.35 364	77.57 333	45.62 351	73.67 264	66.26 476

nomal-1		58.46 377	57.31 377	61.90 392	68.64 424	49.90 265	55.10 470	63.49 423	48.22 387	59.51 368	72.40 421	32.56 398	65.29 434	45.60 352	70.25 327	70.51 461

ACMH+	57.40 11	66.12 280	64.06 289	72.30 207	77.79 205	52.83 194	80.39 106	78.03 228	57.30 201	57.47 395	82.55 249	27.68 441	84.17 147	45.54 353	69.78 337	79.90 342

testing11		62.81 324	61.90 324	65.54 357	78.38 179	40.76 399	67.59 388	66.78 392	55.48 251	60.13 356	77.11 366	31.67 404	76.79 352	45.53 354	74.45 252	79.06 356

CR-MVSNet		59.91 363	57.90 374	65.96 350	69.96 402	52.07 214	65.31 410	63.15 428	42.48 450	59.36 370	74.84 402	35.83 348	70.75 396	45.50 355	64.65 390	75.06 408

0.4-1-1-0.1		59.29 371	56.70 386	67.07 324	69.35 413	43.16 369	66.59 393	70.87 355	48.59 379	55.11 421	62.25 482	28.22 435	78.92 302	45.49 356	63.79 398	79.14 354

CDS-MVSNet		66.80 268	65.37 277	71.10 252	78.98 158	53.13 185	73.27 299	71.07 351	52.15 324	64.72 293	80.23 305	43.56 246	77.10 341	45.48 357	78.88 172	83.05 264
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CP-MVSNet		66.49 275	66.41 255	66.72 328	77.67 211	36.33 446	76.83 211	79.52 185	62.45 73	62.54 328	83.47 230	46.32 211	78.37 309	45.47 358	63.43 404	85.45 170

BH-untuned		68.27 229	67.29 232	71.21 244	79.74 135	53.22 181	76.06 229	77.46 240	57.19 203	66.10 260	81.61 278	45.37 225	83.50 164	45.42 359	76.68 220	76.91 390

PS-CasMVS		66.42 276	66.32 259	66.70 330	77.60 219	36.30 448	76.94 204	79.61 183	62.36 75	62.43 333	83.66 222	45.69 215	78.37 309	45.35 360	63.26 406	85.42 173

XXY-MVS		60.68 354	61.67 326	57.70 430	70.43 390	38.45 423	64.19 421	66.47 393	48.05 392	63.22 311	80.86 294	49.28 170	60.47 452	45.25 361	67.28 371	74.19 423

FBQ-MVS		66.84 266	65.39 276	71.18 246	79.22 150	47.61 318	76.89 206	74.70 306	56.31 232	65.84 269	77.22 363	36.21 344	82.07 212	45.20 362	76.94 215	83.87 231

dtuonly		54.95 413	55.26 402	54.01 447	59.03 487	35.99 450	61.92 437	56.33 464	38.48 470	54.61 429	77.85 353	34.27 365	51.60 493	45.10 363	69.74 340	74.43 419

0.3-1-1-0.015		58.40 378	55.56 397	66.91 326	68.08 435	43.09 371	65.25 412	70.96 354	47.89 396	53.10 447	59.82 485	26.48 451	78.79 304	45.07 364	63.43 404	78.84 361

HY-MVS	56.14 13	64.55 302	63.89 291	66.55 336	74.73 300	41.02 394	69.96 361	74.43 309	49.29 370	61.66 343	80.92 292	47.43 196	76.68 357	44.91 365	71.69 303	81.94 289

0.4-1-1-0.2		58.31 381	55.53 398	66.64 334	67.46 441	42.78 378	64.38 419	70.97 353	47.65 399	53.38 445	59.02 486	28.39 432	78.72 306	44.86 366	63.63 400	78.42 364

FE-MVSNET2		62.01 341	60.88 341	65.42 361	68.74 423	38.43 424	72.92 306	77.39 242	54.74 279	55.40 417	76.71 373	35.46 351	76.72 355	44.25 367	62.31 420	81.10 312

PEN-MVS		66.60 272	66.45 251	67.04 325	77.11 241	36.56 443	77.03 200	80.42 171	62.95 60	62.51 330	84.03 211	46.69 208	79.07 290	44.22 368	63.08 408	85.51 165

test_post1							68.67 377				3.64 537	32.39 399	69.49 404	44.17 369

SCA		60.49 358	58.38 369	66.80 327	74.14 320	48.06 310	63.35 428	63.23 427	49.13 372	59.33 373	72.10 425	37.45 327	74.27 374	44.17 369	62.57 417	78.05 369

PMMVS		53.96 416	53.26 422	56.04 435	62.60 470	50.92 232	61.17 443	56.09 467	32.81 480	53.51 443	66.84 470	34.04 368	59.93 456	44.14 371	68.18 362	57.27 489

MVP-Stereo		65.41 289	63.80 294	70.22 270	77.62 217	55.53 136	76.30 221	78.53 213	50.59 354	56.47 407	78.65 334	39.84 295	82.68 197	44.10 372	72.12 299	72.44 438
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
FE-MVS		65.91 282	63.33 305	73.63 164	77.36 225	51.95 219	72.62 312	75.81 280	53.70 300	65.31 276	78.96 329	28.81 428	86.39 92	43.93 373	73.48 271	82.55 275

CNLPA		65.43 288	64.02 290	69.68 282	78.73 166	58.07 89	77.82 171	70.71 357	51.49 337	61.57 345	83.58 227	38.23 321	70.82 395	43.90 374	70.10 330	80.16 337

pmmvs4		61.48 350	59.39 357	67.76 312	71.57 368	53.86 160	71.42 334	65.34 403	44.20 434	59.46 369	77.92 347	35.90 347	74.71 371	43.87 375	64.87 388	74.71 417

mvs5depth		55.64 405	53.81 417	61.11 402	59.39 485	40.98 398	65.89 399	68.28 379	50.21 357	58.11 388	75.42 398	17.03 480	67.63 417	43.79 376	46.21 482	74.73 416

Test_1112_low_res		62.32 334	61.77 325	64.00 376	79.08 157	39.53 414	68.17 382	70.17 360	43.25 443	59.03 375	79.90 310	44.08 240	71.24 393	43.79 376	68.42 360	81.25 305

sc_t1		59.76 365	57.84 375	65.54 357	74.87 294	42.95 376	69.61 366	64.16 417	48.90 375	58.68 378	77.12 365	28.19 436	72.35 384	43.75 378	55.28 457	81.31 304

TransMVSNet (Re)		64.72 297	64.33 287	65.87 354	75.22 285	38.56 421	74.66 265	75.08 302	58.90 163	61.79 339	82.63 242	51.18 137	78.07 315	43.63 379	55.87 455	80.99 316

pmmvs-eth3d		58.81 374	56.31 391	66.30 342	67.61 439	52.42 208	72.30 321	64.76 408	43.55 440	54.94 424	74.19 408	28.95 425	72.60 381	43.31 380	57.21 449	73.88 426

SixPastTwentyTwo		61.65 347	58.80 365	70.20 272	75.80 270	47.22 322	75.59 240	69.68 365	54.61 280	54.11 434	79.26 326	27.07 447	82.96 179	43.27 381	49.79 478	80.41 328

BH-w/o		66.85 265	65.83 267	69.90 279	79.29 145	52.46 206	74.66 265	76.65 263	54.51 284	64.85 292	78.12 341	45.59 218	82.95 181	43.26 382	75.54 239	74.27 422

TR-MVS		66.59 274	65.07 282	71.17 248	79.18 153	49.63 276	73.48 291	75.20 297	52.95 309	67.90 215	80.33 303	39.81 296	83.68 159	43.20 383	73.56 269	80.20 336

EU-MVSNet		55.61 406	54.41 410	59.19 416	65.41 456	33.42 470	72.44 319	71.91 345	28.81 485	51.27 453	73.87 412	24.76 463	69.08 406	43.04 384	58.20 445	75.06 408

PatchmatchNet		59.84 364	58.24 370	64.65 370	73.05 338	46.70 326	69.42 371	62.18 439	47.55 401	58.88 376	71.96 427	34.49 362	69.16 405	42.99 385	63.60 401	78.07 368
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
WR-MVS_H		67.02 262	66.92 243	67.33 323	77.95 200	37.75 430	77.57 177	82.11 127	62.03 88	62.65 325	82.48 253	50.57 147	79.46 276	42.91 386	64.01 395	84.79 199

ACMH	55.70 15	65.20 293	63.57 298	70.07 274	78.07 195	52.01 217	79.48 127	79.69 180	55.75 244	56.59 404	80.98 290	27.12 446	80.94 242	42.90 387	71.58 305	77.25 384
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		55.30 407	54.41 410	57.96 427	60.92 482	41.73 387	71.09 343	71.06 352	41.18 456	48.65 467	73.31 416	16.93 481	59.25 459	42.54 388	64.01 395	72.90 430

WTY-MVS		59.75 366	60.39 349	57.85 428	72.32 356	37.83 429	61.05 445	64.18 415	45.95 422	61.91 337	79.11 328	47.01 205	60.88 451	42.50 389	69.49 345	74.83 413

TAMVS		66.78 269	65.27 280	71.33 243	79.16 155	53.67 165	73.84 287	69.59 367	52.32 323	65.28 277	81.72 276	44.49 238	77.40 336	42.32 390	78.66 181	82.92 265

LTVRE_ROB	55.42 16	63.15 321	61.23 335	68.92 297	76.57 259	47.80 313	59.92 449	76.39 267	54.35 286	58.67 379	82.46 254	29.44 422	81.49 225	42.12 391	71.14 309	77.46 378
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
WBMVS		60.54 357	60.61 347	60.34 406	78.00 198	35.95 452	64.55 417	64.89 406	49.63 364	63.39 310	78.70 331	33.85 372	67.65 416	42.10 392	70.35 323	77.43 379

sss		56.17 400	56.57 387	54.96 441	66.93 445	36.32 447	57.94 458	61.69 441	41.67 453	58.64 380	75.32 400	38.72 314	56.25 476	42.04 393	66.19 379	72.31 442

UnsupCasMVSNet_eth		53.16 426	52.47 423	55.23 440	59.45 484	33.39 471	59.43 452	69.13 373	45.98 419	50.35 462	72.32 422	29.30 423	58.26 466	42.02 394	44.30 486	74.05 424

tpm2		62.07 338	60.10 353	67.99 310	72.79 343	43.86 358	71.05 344	66.85 391	43.14 445	62.77 321	75.39 399	38.32 319	80.80 248	41.69 395	68.88 354	79.32 352

PLC	56.13 14	65.09 294	63.21 308	70.72 262	81.04 112	54.87 148	78.57 142	77.47 238	48.51 382	55.71 412	81.89 271	33.71 373	79.71 269	41.66 396	70.37 321	77.58 377
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EPMVS		53.96 416	53.69 419	54.79 443	66.12 453	31.96 479	62.34 435	49.05 484	44.42 433	55.54 413	71.33 435	30.22 412	56.70 472	41.65 397	62.54 418	75.71 401

DTE-MVSNet		65.58 286	65.34 278	66.31 341	76.06 268	34.79 457	76.43 219	79.38 188	62.55 71	61.66 343	83.83 217	45.60 217	79.15 286	41.64 398	60.88 430	85.00 190

tt0320-xc		58.33 380	56.41 390	64.08 375	75.79 271	41.34 391	68.30 381	62.72 432	47.90 394	56.29 408	74.16 410	28.53 429	71.04 394	41.50 399	52.50 469	79.88 343

PAPM		67.92 240	66.69 247	71.63 226	78.09 194	49.02 287	77.09 198	81.24 151	51.04 348	60.91 351	83.98 213	47.71 189	84.99 129	40.81 400	79.32 157	80.90 317

tpm		57.34 389	58.16 371	54.86 442	71.80 365	34.77 458	67.47 390	56.04 468	48.20 389	60.10 357	76.92 369	37.17 333	53.41 486	40.76 401	65.01 386	76.40 394

dtuonlycased		55.96 402	54.88 405	59.22 414	68.38 432	40.38 402	69.17 374	63.12 430	40.00 466	53.62 440	68.84 458	36.27 343	66.23 429	40.57 402	53.92 464	71.06 458

KD-MVS_self_test		55.22 409	53.89 416	59.21 415	57.80 490	27.47 495	57.75 461	74.32 311	47.38 403	50.90 456	70.00 445	28.45 431	70.30 401	40.44 403	57.92 446	79.87 344

F-COLMAP		63.05 323	60.87 343	69.58 286	76.99 250	53.63 168	78.12 158	76.16 271	47.97 393	52.41 450	81.61 278	27.87 438	78.11 314	40.07 404	66.66 375	77.00 387

Patchmtry		57.16 390	56.47 388	59.23 413	69.17 416	34.58 461	62.98 430	63.15 428	44.53 430	56.83 402	74.84 402	35.83 348	68.71 408	40.03 405	60.91 429	74.39 421

pmmvs5		56.47 396	55.68 396	58.86 418	61.41 476	36.71 442	66.37 396	62.75 431	40.38 462	53.70 437	76.62 376	34.56 360	67.05 421	40.02 406	65.27 384	72.83 431

testing3-2		62.06 339	62.36 318	61.17 401	79.29 145	30.31 485	64.09 424	63.49 423	63.50 45	62.84 319	82.22 260	32.35 401	69.02 407	40.01 407	73.43 273	84.17 219

tt0320		58.59 375	56.81 384	63.92 377	75.46 280	41.32 392	68.63 378	64.06 418	47.05 409	56.19 409	74.19 408	30.34 410	71.36 391	39.92 408	55.45 456	79.09 355

EPNet_dtu		61.90 344	61.97 323	61.68 394	72.89 342	39.78 409	75.85 236	65.62 401	55.09 263	54.56 430	79.36 324	37.59 326	67.02 422	39.80 409	76.95 214	78.25 366
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CL-MVSNet_self_test		61.53 348	60.94 340	63.30 382	68.95 419	36.93 440	67.60 387	72.80 337	55.67 246	59.95 361	76.63 375	45.01 232	72.22 387	39.74 410	62.09 423	80.74 321

SSC-MVS3.2		60.57 356	61.39 330	58.12 426	74.29 315	32.63 475	59.52 450	65.53 402	59.90 140	62.45 331	79.75 315	41.96 263	63.90 441	39.47 411	69.65 344	77.84 374

test_vis1_rt		41.35 457	39.45 458	47.03 470	46.65 505	37.86 428	47.76 490	38.65 504	23.10 497	44.21 483	51.22 498	11.20 498	44.08 501	39.27 412	53.02 467	59.14 484

Vis-MVSNet (Re-imp)		63.69 313	63.88 292	63.14 384	74.75 299	31.04 483	71.16 340	63.64 422	56.32 230	59.80 364	84.99 181	44.51 236	75.46 368	39.12 413	80.62 128	82.92 265

PVSNet	50.76 19	58.40 378	57.39 376	61.42 397	75.53 278	44.04 357	61.43 439	63.45 425	47.04 410	56.91 401	73.61 414	27.00 448	64.76 437	39.12 413	72.40 291	75.47 404

UBG		59.62 369	59.53 356	59.89 407	78.12 193	35.92 453	64.11 423	60.81 446	49.45 367	61.34 346	75.55 395	33.05 380	67.39 420	38.68 415	74.62 250	76.35 395

MDTV_nov1_ep13_2view						25.89 501	61.22 442		40.10 464	51.10 454		32.97 383		38.49 416		78.61 363

our_test_3		56.49 395	54.42 409	62.68 388	69.51 409	45.48 340	66.08 398	61.49 442	44.11 437	50.73 459	69.60 454	33.05 380	68.15 410	38.38 417	56.86 450	74.40 420

tpm cat1		59.25 372	56.95 381	66.15 346	72.19 358	46.96 324	68.09 383	65.76 399	40.03 465	57.81 390	70.56 439	38.32 319	74.51 372	38.26 418	61.50 427	77.00 387

USDC		56.35 398	54.24 413	62.69 387	64.74 459	40.31 403	65.05 413	73.83 322	43.93 438	47.58 469	77.71 358	15.36 487	75.05 370	38.19 419	61.81 425	72.70 432

MSDG		61.81 346	59.23 358	69.55 287	72.64 345	52.63 201	70.45 354	75.81 280	51.38 340	53.70 437	76.11 385	29.52 420	81.08 238	37.70 420	65.79 382	74.93 412

MDTV_nov1_ep13			57.00 380		72.73 344	38.26 425	65.02 414	64.73 409	44.74 428	55.46 414	72.48 420	32.61 395	70.47 397	37.47 421	67.75 366

SD_0403		63.07 322	63.49 302	61.82 393	75.16 288	31.14 482	71.89 330	73.47 325	53.34 305	58.22 386	81.81 274	45.17 229	73.86 376	37.43 422	74.87 248	80.45 326

gg-mvs-nofinetune		57.86 386	56.43 389	62.18 390	72.62 346	35.35 455	66.57 394	56.33 464	50.65 352	57.64 392	57.10 490	30.65 407	76.36 362	37.38 423	78.88 172	74.82 414

dmvs_re		56.77 393	56.83 383	56.61 433	69.23 414	41.02 394	58.37 455	64.18 415	50.59 354	57.45 396	71.42 431	35.54 350	58.94 462	37.23 424	67.45 369	69.87 467

RPSCF		55.80 404	54.22 414	60.53 405	65.13 458	42.91 377	64.30 420	57.62 457	36.84 473	58.05 389	82.28 258	28.01 437	56.24 477	37.14 425	58.61 444	82.44 281

testing222		62.29 336	61.31 332	65.25 366	77.87 202	38.53 422	68.34 380	66.31 396	56.37 228	63.15 315	77.58 360	28.47 430	76.18 366	37.04 426	76.65 221	81.05 315

PatchT		53.17 425	53.44 421	52.33 460	68.29 433	25.34 503	58.21 456	54.41 471	44.46 432	54.56 430	69.05 457	33.32 378	60.94 450	36.93 427	61.76 426	70.73 460

YYNet1		50.73 435	48.96 437	56.03 436	61.10 478	41.78 386	51.94 479	56.44 462	40.94 459	44.84 479	67.80 462	30.08 415	55.08 482	36.77 428	50.71 474	71.22 454

TAPA-MVS	59.36 10	66.60 272	65.20 281	70.81 258	76.63 257	48.75 293	76.52 218	80.04 176	50.64 353	65.24 282	84.93 182	39.15 306	78.54 308	36.77 428	76.88 216	85.14 184
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MDA-MVSNet_test_wron		50.71 436	48.95 438	56.00 437	61.17 477	41.84 385	51.90 480	56.45 461	40.96 458	44.79 480	67.84 461	30.04 416	55.07 483	36.71 430	50.69 475	71.11 457

ppachtmachnet_test		58.06 385	55.38 400	66.10 348	69.51 409	48.99 288	68.01 384	66.13 398	44.50 431	54.05 435	70.74 438	32.09 402	72.34 385	36.68 431	56.71 453	76.99 389

tpmvs		58.47 376	56.95 381	63.03 386	70.20 397	41.21 393	67.90 385	67.23 387	49.62 365	54.73 427	70.84 437	34.14 366	76.24 364	36.64 432	61.29 428	71.64 448

CHOSEN 280x420		47.83 443	46.36 447	52.24 462	67.37 442	49.78 267	38.91 503	43.11 501	35.00 476	43.27 485	63.30 480	28.95 425	49.19 495	36.53 433	60.80 431	57.76 488

PatchMatch-RL		56.25 399	54.55 408	61.32 400	77.06 242	56.07 121	65.57 403	54.10 473	44.13 436	53.49 444	71.27 436	25.20 461	66.78 423	36.52 434	63.66 399	61.12 481

RPMNet		61.53 348	58.42 368	70.86 257	69.96 402	52.07 214	65.31 410	81.36 142	43.20 444	59.36 370	70.15 444	35.37 352	85.47 121	36.42 435	64.65 390	75.06 408

ITE_SJBPF				62.09 391	66.16 452	44.55 352		64.32 413	47.36 404	55.31 418	80.34 302	19.27 476	62.68 446	36.29 436	62.39 419	79.04 357

myMVS_eth3d28		60.66 355	61.04 338	59.51 409	77.32 226	31.58 480	63.11 429	63.87 419	59.00 160	60.90 352	78.26 340	32.69 391	66.15 430	36.10 437	78.13 191	80.81 319

JIA-IIPM		51.56 431	47.68 445	63.21 383	64.61 460	50.73 241	47.71 491	58.77 452	42.90 447	48.46 468	51.72 494	24.97 462	70.24 402	36.06 438	53.89 465	68.64 473

KD-MVS_2432*1600		53.45 420	51.50 429	59.30 411	62.82 467	37.14 436	55.33 468	71.79 347	47.34 405	55.09 422	70.52 440	21.91 471	70.45 398	35.72 439	42.97 488	70.31 463

miper_refine_blended		53.45 420	51.50 429	59.30 411	62.82 467	37.14 436	55.33 468	71.79 347	47.34 405	55.09 422	70.52 440	21.91 471	70.45 398	35.72 439	42.97 488	70.31 463

OpenMVS_ROB	52.78 18	60.03 362	58.14 372	65.69 356	70.47 389	44.82 344	75.33 244	70.86 356	45.04 426	56.06 410	76.00 387	26.89 450	79.65 270	35.36 441	67.29 370	72.60 433

GG-mvs-BLEND				62.34 389	71.36 376	37.04 439	69.20 373	57.33 460		54.73 427	65.48 475	30.37 409	77.82 324	34.82 442	74.93 247	72.17 443

UnsupCasMVSNet_bld		50.07 438	48.87 439	53.66 450	60.97 481	33.67 469	57.62 462	64.56 412	39.47 468	47.38 470	64.02 479	27.47 442	59.32 458	34.69 443	43.68 487	67.98 475

MDA-MVSNet-bldmvs		53.87 418	50.81 431	63.05 385	66.25 451	48.58 298	56.93 465	63.82 420	48.09 391	41.22 487	70.48 442	30.34 410	68.00 414	34.24 444	45.92 484	72.57 434

dp		51.89 430	51.60 428	52.77 457	68.44 431	32.45 477	62.36 434	54.57 470	44.16 435	49.31 466	67.91 460	28.87 427	56.61 474	33.89 445	54.89 459	69.24 472

AllTest		57.08 391	54.65 406	64.39 372	71.44 372	49.03 285	69.92 362	67.30 384	45.97 420	47.16 471	79.77 313	17.47 478	67.56 418	33.65 446	59.16 441	76.57 392

TestCases				64.39 372	71.44 372	49.03 285		67.30 384	45.97 420	47.16 471	79.77 313	17.47 478	67.56 418	33.65 446	59.16 441	76.57 392

test_vis3_rt		32.09 468	30.20 473	37.76 484	35.36 516	27.48 494	40.60 502	28.29 513	16.69 506	32.52 500	40.53 508	1.96 518	37.40 509	33.64 448	42.21 490	48.39 495

UWE-MVS		60.18 361	59.78 354	61.39 399	77.67 211	33.92 468	69.04 376	63.82 420	48.56 380	64.27 300	77.64 359	27.20 445	70.40 400	33.56 449	76.24 225	79.83 345

FMVSNet5		55.86 403	54.93 403	58.66 420	71.05 381	36.35 445	64.18 422	62.48 434	46.76 413	50.66 460	74.73 404	25.80 457	64.04 439	33.11 450	65.57 383	75.59 402

mvsany_test1		39.38 459	38.16 462	43.02 477	49.05 499	34.28 464	44.16 499	25.94 514	22.74 499	46.57 475	62.21 483	23.85 466	41.16 507	33.01 451	35.91 496	53.63 492

DP-MVS		65.68 284	63.66 297	71.75 219	84.93 60	56.87 111	80.74 104	73.16 333	53.06 308	59.09 374	82.35 255	36.79 340	85.94 108	32.82 452	69.96 333	72.45 437

PVSNet_0	43.31 20	47.46 445	45.64 448	52.92 456	67.60 440	44.65 347	54.06 474	54.64 469	41.59 454	46.15 476	58.75 487	30.99 406	58.66 463	32.18 453	24.81 504	55.46 491

ETVMVS		59.51 370	58.81 363	61.58 396	77.46 222	34.87 456	64.94 415	59.35 449	54.06 290	61.08 350	76.67 374	29.54 419	71.87 389	32.16 454	74.07 257	78.01 373

WB-MVSnew		59.66 367	59.69 355	59.56 408	75.19 287	35.78 454	69.34 372	64.28 414	46.88 411	61.76 340	75.79 391	40.61 289	65.20 435	32.16 454	71.21 308	77.70 375

TinyColmap		54.14 415	51.72 427	61.40 398	66.84 446	41.97 384	66.52 395	68.51 377	44.81 427	42.69 486	75.77 392	11.66 494	72.94 379	31.96 456	56.77 452	69.27 471

MIMVSNet		57.35 388	57.07 379	58.22 423	74.21 317	37.18 435	62.46 433	60.88 445	48.88 376	55.29 419	75.99 389	31.68 403	62.04 448	31.87 457	72.35 292	75.43 405

thres100view900		63.28 318	62.41 317	65.89 352	77.31 227	38.66 420	72.65 310	69.11 374	57.07 206	62.45 331	81.03 289	37.01 337	79.17 283	31.84 458	73.25 277	79.83 345

tfpn200view9		63.18 320	62.18 321	66.21 344	76.85 251	39.62 412	71.96 328	69.44 370	56.63 217	62.61 326	79.83 311	37.18 331	79.17 283	31.84 458	73.25 277	79.83 345

thres400		63.31 316	62.18 321	66.72 328	76.85 251	39.62 412	71.96 328	69.44 370	56.63 217	62.61 326	79.83 311	37.18 331	79.17 283	31.84 458	73.25 277	81.36 301

pmmvs3		44.92 448	41.95 455	53.86 448	52.58 496	43.55 362	62.11 436	46.90 494	26.05 492	40.63 488	60.19 484	11.08 499	57.91 467	31.83 461	46.15 483	60.11 482

LF4IMVS		42.95 451	42.26 453	45.04 472	48.30 502	32.50 476	54.80 471	48.49 486	28.03 488	40.51 489	70.16 443	9.24 501	43.89 502	31.63 462	49.18 480	58.72 485

COLMAP_ROB	52.97 17	61.27 353	58.81 363	68.64 300	74.63 303	52.51 204	78.42 145	73.30 329	49.92 362	50.96 455	81.51 281	23.06 467	79.40 277	31.63 462	65.85 380	74.01 425
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
new-patchmatchnet		47.56 444	47.73 444	47.06 469	58.81 488	9.37 521	48.78 488	59.21 450	43.28 442	44.22 482	68.66 459	25.67 458	57.20 471	31.57 464	49.35 479	74.62 418

thres600view7		63.30 317	62.27 319	66.41 339	77.18 230	38.87 418	72.35 320	69.11 374	56.98 209	62.37 334	80.96 291	37.01 337	79.00 298	31.43 465	73.05 281	81.36 301

thres200		62.20 337	61.16 337	65.34 364	75.38 283	39.99 407	69.60 367	69.29 372	55.64 248	61.87 338	76.99 368	37.07 336	78.96 300	31.28 466	73.28 276	77.06 385

LCM-MVSNet		40.30 458	35.88 464	53.57 451	42.24 507	29.15 488	45.21 497	60.53 447	22.23 500	28.02 502	50.98 499	3.72 512	61.78 449	31.22 467	38.76 494	69.78 468

test_f		31.86 469	31.05 470	34.28 486	32.33 518	21.86 508	32.34 506	30.46 511	16.02 507	39.78 493	55.45 491	4.80 508	32.36 513	30.61 468	37.66 495	48.64 494

test0.0.03 1		53.32 424	53.59 420	52.50 459	62.81 469	29.45 487	59.51 451	54.11 472	50.08 359	54.40 432	74.31 407	32.62 393	55.92 478	30.50 469	63.95 397	72.15 444

FE-MVSNET		55.16 411	53.75 418	59.41 410	65.29 457	33.20 472	67.21 392	66.21 397	48.39 386	49.56 465	73.53 415	29.03 424	72.51 382	30.38 470	54.10 463	72.52 435

Anonymous20231206		55.10 412	55.30 401	54.48 444	69.81 407	33.94 467	62.91 431	62.13 440	41.08 457	55.18 420	75.65 393	32.75 388	56.59 475	30.32 471	67.86 364	72.91 429

tfpnnormal		62.47 329	61.63 327	64.99 368	74.81 297	39.01 417	71.22 338	73.72 323	55.22 260	60.21 355	80.09 309	41.26 282	76.98 348	30.02 472	68.09 363	78.97 359

test20.03		53.87 418	54.02 415	53.41 453	61.47 475	28.11 492	61.30 441	59.21 450	51.34 342	52.09 451	77.43 361	33.29 379	58.55 464	29.76 473	60.27 438	73.58 427

LS3D		64.71 298	62.50 316	71.34 242	79.72 137	55.71 129	79.82 118	74.72 305	48.50 383	56.62 403	84.62 194	33.59 376	82.34 207	29.65 474	75.23 245	75.97 397

mvsany_test3		32.62 467	30.57 472	38.77 483	36.16 515	24.20 505	38.10 504	20.63 518	19.14 503	40.36 491	57.43 489	5.06 507	36.63 510	29.59 475	28.66 501	55.49 490

testgi		51.90 429	52.37 424	50.51 466	60.39 483	23.55 506	58.42 454	58.15 453	49.03 373	51.83 452	79.21 327	22.39 468	55.59 479	29.24 476	62.64 416	72.40 441

MIMVSNet1		55.17 410	54.31 412	57.77 429	70.03 401	32.01 478	65.68 402	64.81 407	49.19 371	46.75 474	76.00 387	25.53 460	64.04 439	28.65 477	62.13 422	77.26 383

TDRefinement		53.44 422	50.72 433	61.60 395	64.31 462	46.96 324	70.89 345	65.27 405	41.78 451	44.61 481	77.98 344	11.52 496	66.36 427	28.57 478	51.59 472	71.49 451

usedtu_dtu_shiyan2		53.34 423	50.78 432	61.00 404	61.86 474	39.63 411	68.47 379	64.58 411	42.94 446	45.22 478	67.61 464	19.25 477	66.71 424	28.08 479	59.05 443	76.66 391

WAC-MVS						27.31 496								27.77 480

myMVS_eth3d		54.86 414	54.61 407	55.61 438	74.69 301	27.31 496	65.52 404	57.49 458	50.97 349	56.52 405	72.18 423	21.87 473	68.09 411	27.70 481	64.59 392	71.44 452

ttmdpeth		45.56 446	42.95 451	53.39 454	52.33 497	29.15 488	57.77 459	48.20 489	31.81 482	49.86 464	77.21 364	8.69 503	59.16 460	27.31 482	33.40 500	71.84 447

ADS-MVSNet2		51.33 433	48.76 440	59.07 417	66.02 454	44.60 350	50.90 482	59.76 448	36.90 471	50.74 457	66.18 473	26.38 452	63.11 444	27.17 483	54.76 460	69.50 469

ADS-MVSNet		48.48 442	47.77 443	50.63 465	66.02 454	29.92 486	50.90 482	50.87 482	36.90 471	50.74 457	66.18 473	26.38 452	52.47 489	27.17 483	54.76 460	69.50 469

Patchmatch-test		49.08 440	48.28 442	51.50 464	64.40 461	30.85 484	45.68 495	48.46 487	35.60 475	46.10 477	72.10 425	34.47 363	46.37 499	27.08 485	60.65 434	77.27 382

MVS-HIRNet		45.52 447	44.48 449	48.65 468	68.49 430	34.05 466	59.41 453	44.50 498	27.03 490	37.96 497	50.47 500	26.16 455	64.10 438	26.74 486	59.52 439	47.82 498

test_0402		63.25 319	61.01 339	69.96 275	80.00 132	54.37 153	76.86 209	72.02 344	54.58 282	58.71 377	80.79 297	35.00 356	84.36 145	26.41 487	64.71 389	71.15 456

N_pmnet		39.35 460	40.28 457	36.54 485	63.76 463	1.62 540	49.37 487	0.76 538	34.62 477	43.61 484	66.38 472	26.25 454	42.57 503	26.02 488	51.77 471	65.44 477

PatchmatchNet1														25.92 489	51.90 470	65.44 477
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
testing3		56.54 394	55.92 394	58.41 421	77.52 220	27.93 493	69.72 363	56.36 463	54.75 278	58.63 381	77.80 354	20.88 475	71.75 390	25.31 490	62.25 421	75.53 403

Syy-MVS		56.00 401	56.23 392	55.32 439	74.69 301	26.44 499	65.52 404	57.49 458	50.97 349	56.52 405	72.18 423	39.89 294	68.09 411	24.20 491	64.59 392	71.44 452

MVStest1		42.65 452	39.29 459	52.71 458	47.26 504	34.58 461	54.41 473	50.84 483	23.35 495	39.31 495	74.08 411	12.57 491	55.09 481	23.32 492	28.47 502	68.47 474

DSMNet-mixed		39.30 461	38.72 460	41.03 480	51.22 498	19.66 510	45.53 496	31.35 510	15.83 508	39.80 492	67.42 467	22.19 469	45.13 500	22.43 493	52.69 468	58.31 486

dmvs_testset		50.16 437	51.90 426	44.94 474	66.49 449	11.78 518	61.01 446	51.50 477	51.17 347	50.30 463	67.44 465	39.28 303	60.29 454	22.38 494	57.49 448	62.76 480

ANet_high		41.38 456	37.47 463	53.11 455	39.73 512	24.45 504	56.94 464	69.69 364	47.65 399	26.04 504	52.32 493	12.44 492	62.38 447	21.80 495	10.61 515	72.49 436

ArgMatch-Sym		21.00 477	19.89 480	24.35 496	23.32 519	15.10 515	32.50 505	4.90 524	11.83 511	24.09 505	51.35 497	0.56 523	19.55 517	21.24 496	9.18 518	38.40 507

ArgMatch-SfM		20.82 478	19.10 481	25.97 494	21.54 520	13.77 516	29.84 509	6.08 523	9.69 513	22.36 506	51.71 495	0.53 524	21.69 516	20.98 497	9.18 518	42.43 501

new_pmnet		34.13 466	34.29 467	33.64 487	52.63 495	18.23 512	44.43 498	33.90 509	22.81 498	30.89 501	53.18 492	10.48 500	35.72 511	20.77 498	39.51 492	46.98 499

UWE-MVS-28		52.25 428	52.35 425	51.93 463	66.99 443	22.79 507	63.48 427	48.31 488	46.78 412	52.73 449	76.11 385	27.78 440	57.82 468	20.58 499	68.41 361	75.17 406

APD_test1		37.39 462	34.94 465	44.72 475	48.88 500	33.19 473	52.95 477	44.00 500	19.49 502	27.28 503	58.59 488	3.18 514	52.84 488	18.92 500	41.17 491	48.14 497

EGC-MVSNET		42.47 453	38.48 461	54.46 445	74.33 313	48.73 294	70.33 357	51.10 479	0.03 558	0.18 557	67.78 463	13.28 490	66.49 426	18.91 501	50.36 476	48.15 496

PMMVS2		27.40 473	25.91 476	31.87 490	39.46 513	6.57 525	31.17 507	28.52 512	23.96 494	20.45 510	48.94 503	4.20 511	37.94 508	16.51 502	19.97 507	51.09 493

test_method		19.68 479	18.10 482	24.41 495	13.68 524	3.11 534	12.06 517	42.37 502	2.00 523	11.97 517	36.38 509	5.77 506	29.35 515	15.06 503	23.65 505	40.76 504

Gipuma		34.77 464	31.91 469	43.33 476	62.05 473	37.87 427	20.39 510	67.03 389	23.23 496	18.41 511	25.84 517	4.24 509	62.73 445	14.71 504	51.32 473	29.38 509
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FPMVS		42.18 454	41.11 456	45.39 471	58.03 489	41.01 396	49.50 486	53.81 474	30.07 484	33.71 499	64.03 477	11.69 493	52.08 492	14.01 505	55.11 458	43.09 500

testf1		31.46 470	28.89 474	39.16 481	41.99 509	28.78 490	46.45 493	37.56 505	14.28 509	21.10 507	48.96 501	1.48 520	47.11 497	13.63 506	34.56 497	41.60 502

APD_test2		31.46 470	28.89 474	39.16 481	41.99 509	28.78 490	46.45 493	37.56 505	14.28 509	21.10 507	48.96 501	1.48 520	47.11 497	13.63 506	34.56 497	41.60 502

tmp_tt		9.43 486	11.14 487	4.30 511	2.38 541	4.40 527	13.62 515	16.08 520	0.39 531	15.89 512	13.06 528	15.80 486	5.54 529	12.63 508	10.46 516	2.95 529

dongtai		34.52 465	34.94 465	33.26 488	61.06 479	16.00 514	52.79 478	23.78 516	40.71 460	39.33 494	48.65 504	16.91 482	48.34 496	12.18 509	19.05 508	35.44 508

WB-MVS		43.26 450	43.41 450	42.83 478	63.32 466	10.32 520	58.17 457	45.20 495	45.42 424	40.44 490	67.26 468	34.01 370	58.98 461	11.96 510	24.88 503	59.20 483

DenseAffine		14.16 481	13.16 484	17.15 497	17.01 522	8.89 523	19.68 511	2.17 527	7.89 514	15.00 513	40.64 507	0.19 527	15.28 519	11.16 511	4.69 523	27.27 511

SSC-MVS		41.96 455	41.99 454	41.90 479	62.46 471	9.28 522	57.41 463	44.32 499	43.38 441	38.30 496	66.45 471	32.67 392	58.42 465	10.98 512	21.91 506	57.99 487

RoMa-SfM		11.96 483	11.39 486	13.68 499	10.24 526	6.80 524	15.83 513	1.33 531	6.34 516	13.06 516	41.41 505	0.16 528	12.72 520	10.58 513	3.56 526	21.52 512

MVE	17.77 23	21.41 476	17.77 483	32.34 489	34.34 517	25.44 502	16.11 512	24.11 515	11.19 512	13.22 515	31.92 512	1.58 519	30.95 514	10.47 514	17.03 510	40.62 505
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		23.77 474	22.73 478	26.90 491	42.02 508	20.67 509	42.66 500	35.70 507	17.43 504	10.28 521	25.05 518	6.42 505	42.39 505	10.28 515	14.71 511	17.63 515

PMVS	28.69 22	36.22 463	33.29 468	45.02 473	36.82 514	35.98 451	54.68 472	48.74 485	26.31 491	21.02 509	51.61 496	2.88 515	60.10 455	9.99 516	47.58 481	38.99 506
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DKM		10.33 484	10.10 488	11.02 501	10.54 525	5.43 526	14.18 514	1.03 534	4.97 517	11.74 518	36.09 510	0.11 532	9.09 524	9.38 517	2.85 527	18.53 514

EMVS		22.97 475	21.84 479	26.36 492	40.20 511	19.53 511	41.95 501	34.64 508	17.09 505	9.73 522	22.83 520	7.29 504	42.22 506	9.18 518	13.66 513	17.32 516

DKM-HiRes		7.91 490	7.93 494	7.83 505	7.35 529	3.58 532	10.03 521	0.66 541	3.58 521	9.05 524	30.62 514	0.08 539	5.66 528	8.09 519	1.91 534	14.26 518

DeepMVS_CX				12.03 500	17.97 521	10.91 519		10.60 521	7.46 515	11.07 519	28.36 516	3.28 513	11.29 521	8.01 520	9.74 517	13.89 520

PDCNetPlus		9.23 487	8.89 491	10.23 503	13.70 523	3.70 530	12.27 516	1.51 530	3.98 519	6.73 527	29.50 515	0.24 526	8.07 526	7.83 521	4.30 524	18.93 513

RoMa-HiRes		8.28 489	8.27 493	8.28 504	6.12 531	3.67 531	10.07 520	0.74 539	3.93 520	9.17 523	34.46 511	0.12 531	7.12 527	7.80 522	2.05 533	14.04 519

kuosan		29.62 472	30.82 471	26.02 493	52.99 493	16.22 513	51.09 481	22.71 517	33.91 479	33.99 498	40.85 506	15.89 485	33.11 512	7.59 523	18.37 509	28.72 510

wuyk23d		13.32 482	12.52 485	15.71 498	47.54 503	26.27 500	31.06 508	1.98 528	4.93 518	5.18 529	1.94 544	0.45 525	18.54 518	6.81 524	12.83 514	2.33 531

VLMVS_CLIP		8.61 488	9.36 489	6.34 508	7.07 530	4.23 529	8.66 522	10.16 522	1.75 524	13.91 514	20.41 522	2.33 516	10.32 523	6.21 525	13.74 512	4.49 526

MVS_clip		4.22 497	4.98 499	1.95 514	5.46 533	1.99 535	3.96 524	0.34 545	0.36 532	7.04 526	17.25 523	0.66 522	0.80 539	4.04 526	5.70 522	3.07 528

PMatch-SfM		4.42 495	4.43 500	4.39 510	2.90 537	1.50 541	4.85 523	0.36 544	1.17 526	4.73 531	20.99 521	0.01 559	3.26 532	3.74 527	1.10 541	8.40 524

LoFTR		9.45 485	9.00 490	10.79 502	10.22 527	4.31 528	11.11 518	4.11 525	2.40 522	10.53 520	30.89 513	0.13 529	10.75 522	3.12 528	8.52 520	17.31 517

PMatch-Up-SfM		3.14 501	3.26 504	2.81 512	1.97 546	1.00 545	3.35 529	0.23 551	0.79 528	3.44 534	16.19 526	0.01 559	2.11 533	2.62 529	0.70 554	5.32 525

MASt3R-SfM		3.33 500	3.70 501	2.21 513	2.02 545	1.04 543	3.52 528	1.05 533	0.67 529	4.93 530	16.68 524	0.10 534	1.50 536	2.06 530	2.29 532	4.09 527

ELoFTR		4.04 498	3.55 503	5.50 509	2.33 542	1.25 542	3.58 526	1.18 532	0.90 527	4.23 533	16.28 525	0.03 547	5.46 531	1.95 531	1.42 538	9.81 523

MatchFormer		7.03 491	6.96 495	7.26 506	7.64 528	3.36 533	10.21 519	3.04 526	1.31 525	9.02 525	22.94 519	0.08 539	8.15 525	1.46 532	6.91 521	10.26 522

VLMVS		2.25 503	2.47 506	1.62 517	2.41 540	1.01 544	1.61 536	0.72 540	0.07 557	4.27 532	6.17 532	2.11 517	1.03 538	1.17 533	3.66 525	2.83 530

GLUNet-SfM		4.33 496	3.64 502	6.41 507	3.38 536	1.65 538	3.23 530	1.54 529	0.66 530	6.36 528	15.13 527	0.08 539	5.54 529	0.94 534	1.44 537	12.05 521

SP-DiffGlue		0.98 508	1.05 511	0.75 523	0.81 562	0.40 552	1.24 537	0.37 543	0.19 536	1.26 541	3.80 536	0.11 532	0.34 546	0.51 535	1.18 539	1.52 537

MVS_baseline		1.38 506	1.71 509	0.39 529	1.08 560	0.02 567	0.39 553	0.06 565	0.01 559	2.77 535	7.83 529	0.07 544	0.00 561	0.47 536	2.72 529	1.14 541

XFeat-MNN		1.07 507	1.17 510	0.77 520	0.52 563	0.31 560	1.15 538	0.41 542	0.15 539	1.62 537	4.35 535	0.07 544	0.77 540	0.38 537	1.88 535	1.22 540

XFeat-NN		0.87 512	0.97 514	0.59 525	0.48 564	0.24 563	0.94 539	0.29 550	0.12 542	1.41 540	3.45 539	0.06 546	0.56 541	0.29 538	1.65 536	0.95 542

SP-LightGlue		0.94 509	0.99 512	0.78 519	2.60 538	0.38 553	1.71 532	0.34 545	0.17 537	0.50 543	2.14 540	0.09 537	0.38 543	0.26 539	1.13 540	1.59 534

SP-SuperGlue		0.93 510	0.98 513	0.77 520	2.54 539	0.38 553	1.70 533	0.34 545	0.17 537	0.52 542	2.13 541	0.10 534	0.36 545	0.26 539	1.10 541	1.57 536

SP-NN		0.85 513	0.90 516	0.73 524	2.22 544	0.33 559	1.63 535	0.31 549	0.14 540	0.47 545	1.97 543	0.08 539	0.38 543	0.25 541	1.01 544	1.47 538

SP-MNN		0.89 511	0.93 515	0.77 520	2.32 543	0.34 557	1.68 534	0.33 548	0.13 541	0.49 544	2.07 542	0.08 539	0.39 542	0.25 541	1.07 543	1.58 535

ALIKED-LG		2.35 502	2.54 505	1.78 515	5.54 532	1.79 537	3.81 525	0.96 535	0.33 533	1.86 536	7.18 530	0.13 529	1.60 534	0.20 543	2.81 528	1.94 532

ALIKED-MNN		2.09 504	2.23 507	1.67 516	5.15 534	1.82 536	3.53 527	0.77 536	0.25 534	1.45 538	6.03 533	0.09 537	1.52 535	0.17 544	2.64 530	1.66 533

ALIKED-NN		1.96 505	2.12 508	1.48 518	4.72 535	1.65 538	3.19 531	0.77 536	0.23 535	1.43 539	5.87 534	0.10 534	1.37 537	0.16 545	2.61 531	1.42 539

SIFT-NN-UMatch		0.48 519	0.52 522	0.36 532	1.27 556	0.36 555	0.75 543	0.12 555	0.10 543	0.25 551	1.29 547	0.02 548	0.26 551	0.04 546	0.85 549	0.44 547

SIFT-NN-NCMNet		0.53 516	0.58 519	0.40 528	1.60 550	0.49 548	0.80 542	0.15 554	0.09 546	0.28 549	1.29 547	0.02 548	0.27 549	0.04 546	0.94 546	0.44 547

SIFT-NN-CMatch		0.49 518	0.53 521	0.38 530	1.35 554	0.41 551	0.70 545	0.12 555	0.09 546	0.30 547	1.28 549	0.02 548	0.26 551	0.04 546	0.83 550	0.47 545

SIFT-NN		0.60 514	0.65 517	0.45 526	1.90 547	0.55 546	0.90 540	0.16 552	0.10 543	0.34 546	1.43 545	0.02 548	0.28 547	0.04 546	0.95 545	0.50 543

SIFT-UMatch		0.45 521	0.50 524	0.32 535	1.46 552	0.34 557	0.66 546	0.10 560	0.09 546	0.22 553	1.19 551	0.02 548	0.25 553	0.04 546	0.73 553	0.36 552

SIFT-ConvMatch		0.48 519	0.52 522	0.35 533	1.51 551	0.42 550	0.64 547	0.11 558	0.09 546	0.26 550	1.24 550	0.02 548	0.25 553	0.04 546	0.76 552	0.38 550

SIFT-MNN		0.56 515	0.61 518	0.43 527	1.75 548	0.50 547	0.82 541	0.16 552	0.10 543	0.30 547	1.38 546	0.02 548	0.28 547	0.04 546	0.92 547	0.50 543

testmvs		4.52 494	6.03 497	0.01 542	0.01 565	0.00 569	53.86 475	0.00 567	0.01 559	0.04 561	0.27 559	0.00 565	0.00 561	0.04 546	0.00 560	0.03 558

SIFT-UM-Cal		0.41 524	0.46 526	0.28 537	1.35 554	0.29 561	0.57 549	0.08 562	0.09 546	0.20 555	1.10 554	0.02 548	0.23 556	0.03 554	0.68 555	0.30 555

SIFT-NCM-Cal		0.51 517	0.55 520	0.38 530	1.66 549	0.45 549	0.75 543	0.12 555	0.09 546	0.21 554	1.18 552	0.02 548	0.27 549	0.03 554	0.89 548	0.43 549

SIFT-CM-Cal		0.42 523	0.46 526	0.31 536	1.40 553	0.35 556	0.56 550	0.09 561	0.09 546	0.20 555	1.09 555	0.02 548	0.23 556	0.03 554	0.66 556	0.34 553

SIFT-PCN-Cal		0.36 525	0.39 528	0.26 538	1.16 558	0.21 564	0.46 552	0.07 564	0.08 554	0.17 558	0.92 556	0.01 559	0.20 559	0.03 554	0.59 558	0.37 551

SIFT-NN-PointCN		0.44 522	0.47 525	0.33 534	1.17 557	0.29 561	0.64 547	0.11 558	0.09 546	0.25 551	1.14 553	0.02 548	0.25 553	0.03 554	0.78 551	0.46 546

SIFT-PointCN		0.36 525	0.39 528	0.25 539	1.14 559	0.21 564	0.50 551	0.08 562	0.08 554	0.17 558	0.89 557	0.01 559	0.21 558	0.03 554	0.60 557	0.34 553

test123		4.73 493	6.30 496	0.02 541	0.01 565	0.01 568	56.36 466	0.00 567	0.01 559	0.04 561	0.21 560	0.01 559	0.00 561	0.03 554	0.00 560	0.04 557

SIFT-NCMNet		0.30 527	0.33 530	0.19 540	1.04 561	0.18 566	0.39 553	0.05 566	0.08 554	0.14 560	0.77 558	0.01 559	0.16 560	0.02 561	0.49 559	0.22 556

mmdepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	0.00 561	0.00 565	0.00 561	0.00 562	0.00 560	0.00 559

monomultidepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	0.00 561	0.00 565	0.00 561	0.00 562	0.00 560	0.00 559

test_blank		0.00 528	0.00 531	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	0.00 561	0.00 565	0.00 561	0.00 562	0.00 560	0.00 559

uanet_test		0.00 528	0.00 531	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	0.00 561	0.00 565	0.00 561	0.00 562	0.00 560	0.00 559

DCPMVS		0.00 528	0.00 531	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	0.00 561	0.00 565	0.00 561	0.00 562	0.00 560	0.00 559

cdsmvs_eth3d_5k		17.50 480	23.34 477	0.00 543	0.00 567	0.00 569	0.00 555	78.63 206	0.00 562	0.00 563	82.18 261	49.25 171	0.00 561	0.00 562	0.00 560	0.00 559

pcd_1.5k_mvsjas		3.92 499	5.23 498	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	0.00 561	47.05 202	0.00 561	0.00 562	0.00 560	0.00 559

sosnet-low-res		0.00 528	0.00 531	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	0.00 561	0.00 565	0.00 561	0.00 562	0.00 560	0.00 559

sosnet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	0.00 561	0.00 565	0.00 561	0.00 562	0.00 560	0.00 559

uncertanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	0.00 561	0.00 565	0.00 561	0.00 562	0.00 560	0.00 559

Regformer		0.00 528	0.00 531	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	0.00 561	0.00 565	0.00 561	0.00 562	0.00 560	0.00 559

ab-mvs-re		6.49 492	8.65 492	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	77.89 351	0.00 565	0.00 561	0.00 562	0.00 560	0.00 559

uanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 569	0.00 555	0.00 567	0.00 562	0.00 563	0.00 561	0.00 565	0.00 561	0.00 562	0.00 560	0.00 559

Meshroom													0.00 561
: In preparation.
AliceVision / Meshro													0.00 561
: In preparation.
AliceVision_Meshroom													0.00 561
: In preparation.
PatchmatchNet2					0.00 567	13.27 517	48.02 489	44.92 497	34.52 478
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													42.51 504
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip				78.05 44	84.66 63	58.22 88	86.84 11	85.98 23	63.31 49	79.39 26	88.94 66	62.01 16	89.61 22		86.45 64	86.34 124

FOURS1					86.12 38	60.82 37	88.18 1	83.61 85	60.87 109	81.50 21

test_one_0601					87.58 9	59.30 62		86.84 7	65.01 21	83.80 11	91.86 6	64.03 12

eth-test2					0.00 567

eth-test					0.00 567

test_241102_ONE					87.77 4	58.90 79		86.78 10	64.20 34	85.97 1	91.34 19	66.87 3	90.78 7

save fliter					86.17 35	61.30 28	83.98 58	79.66 182	59.00 160

test0726					87.75 7	59.07 74	87.86 4	86.83 8	64.26 32	84.19 7	91.92 5	64.82 8

GSMVS																78.05 369

test_part2					87.58 9	60.47 42				83.42 14

sam_mvs1												34.74 359				78.05 369

sam_mvs												33.43 377

MTGPA								80.97 161

test_post											3.55 538	33.90 371	66.52 425

patchmatchnet-post											64.03 477	34.50 361	74.27 374

MTMP							86.03 23	17.08 519

TEST9					85.58 45	61.59 24	81.62 91	81.26 149	55.65 247	74.93 67	88.81 69	53.70 92	84.68 140

test_8					85.40 48	60.96 34	81.54 94	81.18 153	55.86 239	74.81 72	88.80 71	53.70 92	84.45 144

agg_prior					85.04 55	59.96 50		81.04 158		74.68 77			84.04 151

test_prior4						62.51 14	82.08 87

test_prior				76.69 67	84.20 67	57.27 100		84.88 46					86.43 91			86.38 120

新几何2							76.12 226

旧先验1					83.04 80	53.15 183		67.52 383			87.85 90	44.08 240			80.76 126	78.03 372

原ACMM2							79.02 131

test222					83.14 78	58.68 83	72.57 315	63.45 425	41.78 451	67.56 229	86.12 151	37.13 334			78.73 178	74.98 411

segment_acmp												54.23 79

testdata1							72.65 310		60.50 119

test12				77.76 51	84.52 64	58.41 85		83.36 94		72.93 121		54.61 76	88.05 45		88.12 38	86.81 101

plane_prior7					81.41 103	55.96 123

plane_prior6					81.20 110	56.24 118						45.26 227

plane_prior4											86.10 152

plane_prior3						56.09 120			63.92 39	69.27 185

plane_prior2							84.22 51		64.52 28

plane_prior1					81.27 108

plane_prior						56.31 114	83.58 64		63.19 56						80.48 134

n2								0.00 567

nn								0.00 567

door-mid								47.19 493

test11								83.47 89

door								47.60 491

HQP5-MVS						54.94 145

HQP-NCC					80.66 117		82.31 82		62.10 83	67.85 218

ACMP_Plane					80.66 117		82.31 82		62.10 83	67.85 218

HQP4-MVS										67.85 218			86.93 73			84.32 212

HQP3-MVS								83.90 65							80.35 136

HQP2-MVS												45.46 221

NP-MVS					80.98 113	56.05 122					85.54 175

ACMMP++_ref															74.07 257

ACMMP++															72.16 298

Test By Simon												48.33 182

High-resolution multi-view benchmark