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.

fmvsm_l_conf0.5_n		97.65 13	97.72 12	97.41 49	97.51 122	92.78 88	99.85 7	98.05 46	96.78 8	99.60 1	99.23 26	90.42 45	99.92 40	99.55 12	98.50 106	99.55 74

fmvsm_l_conf0.5_n_a		97.70 12	97.80 11	97.42 48	97.59 117	92.91 86	99.86 4	98.04 48	96.70 10	99.58 2	99.26 21	90.90 36	99.94 34	99.57 11	98.66 101	99.40 88

IU-MVS					99.63 18	95.38 24		97.73 80	95.54 26	99.54 3				99.69 6	99.81 23	99.99 1

PC_three_1452									94.60 36	99.41 4	99.12 46	95.50 6	99.96 28	99.84 2	99.92 3	99.97 7

CNVR-MVS		98.46 1	98.38 1	98.72 9	99.80 4	96.19 15	99.80 15	97.99 52	97.05 6	99.41 4	99.59 2	92.89 23	100.00 1	98.99 25	99.90 7	99.96 10

patch_mono-2		97.10 26	97.97 8	94.49 179	99.21 61	83.73 293	99.62 37	98.25 32	95.28 30	99.38 6	98.91 75	92.28 26	99.94 34	99.61 9	99.22 73	99.78 38

test0726					99.66 12	95.20 32	99.77 17	97.70 86	93.95 48	99.35 7	99.54 3	93.18 20

SED-MVS		98.18 2	98.10 4	98.41 18	99.63 18	95.24 27	99.77 17	97.72 81	94.17 43	99.30 8	99.54 3	93.32 17	99.98 9	99.70 4	99.81 23	99.99 1

test_241102_ONE					99.63 18	95.24 27		97.72 81	94.16 45	99.30 8	99.49 9	93.32 17	99.98 9

DVP-MVS++		98.18 2	98.09 5	98.44 16	99.61 24	95.38 24	99.55 44	97.68 90	93.01 70	99.23 10	99.45 14	95.12 7	99.98 9	99.25 18	99.92 3	99.97 7

test_241102_TWO								97.72 81	94.17 43	99.23 10	99.54 3	93.14 22	99.98 9	99.70 4	99.82 19	99.99 1

SMA-MVS		97.24 20	96.99 24	98.00 31	99.30 54	94.20 58	99.16 95	97.65 102	89.55 158	99.22 12	99.52 8	90.34 48	99.99 5	98.32 43	99.83 15	99.82 32
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
fmvsm_s_conf0.5_n_a		95.97 56	96.19 43	95.31 148	96.51 168	89.01 175	99.81 11	98.39 27	95.46 28	99.19 13	99.16 36	81.44 204	99.91 45	98.83 28	96.97 141	97.01 220

test_fmvsm_n_1920		97.08 27	97.55 14	95.67 136	97.94 105	89.61 163	99.93 1	98.48 24	97.08 5	99.08 14	99.13 44	88.17 74	99.93 38	99.11 23	99.06 78	97.47 204

DVP-MVS		98.07 7	98.00 6	98.29 19	99.66 12	95.20 32	99.72 23	97.47 141	93.95 48	99.07 15	99.46 10	93.18 20	99.97 21	99.64 7	99.82 19	99.69 55
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_THIRD									93.01 70	99.07 15	99.46 10	94.66 12	99.97 21	99.25 18	99.82 19	99.95 15

TSAR-MVS + MP.		97.44 18	97.46 16	97.39 51	99.12 65	93.49 72	98.52 172	97.50 136	94.46 38	98.99 17	98.64 99	91.58 28	99.08 148	98.49 37	99.83 15	99.60 69
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_s_conf0.1_n_a		95.16 84	95.15 78	95.18 153	92.06 306	88.94 179	99.29 80	97.53 127	94.46 38	98.98 18	98.99 60	79.99 213	99.85 67	98.24 47	96.86 143	96.73 225

PS-MVSNAJ		96.87 31	96.40 39	98.29 19	97.35 128	97.29 5	99.03 117	97.11 179	95.83 20	98.97 19	99.14 42	82.48 185	99.60 103	98.60 33	99.08 76	98.00 190

旧先验2							98.67 154		85.75 257	98.96 20			98.97 154	93.84 137

test_one_0601					99.59 28	94.89 36		97.64 103	93.14 69	98.93 21	99.45 14	93.45 16

fmvsm_s_conf0.5_n		96.19 49	96.49 36	95.30 149	97.37 127	89.16 168	99.86 4	98.47 25	95.68 23	98.87 22	99.15 39	82.44 189	99.92 40	99.14 21	97.43 132	96.83 224

xiu_mvs_v2_base		96.66 36	96.17 48	98.11 28	97.11 147	96.96 6	99.01 120	97.04 186	95.51 27	98.86 23	99.11 50	82.19 193	99.36 130	98.59 35	98.14 115	98.00 190

NCCC		98.12 5	98.11 3	98.13 25	99.76 6	94.46 50	99.81 11	97.88 57	96.54 13	98.84 24	99.46 10	92.55 25	99.98 9	98.25 46	99.93 1	99.94 18

SD-MVS		97.51 16	97.40 18	97.81 36	99.01 72	93.79 66	99.33 78	97.38 154	93.73 59	98.83 25	99.02 58	90.87 38	99.88 54	98.69 30	99.74 29	99.77 43
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
SF-MVS		97.22 22	96.92 25	98.12 27	99.11 66	94.88 37	99.44 62	97.45 144	89.60 154	98.70 26	99.42 17	90.42 45	99.72 89	98.47 38	99.65 40	99.77 43

fmvsm_s_conf0.1_n		95.56 73	95.68 65	95.20 152	94.35 255	89.10 171	99.50 51	97.67 94	94.76 34	98.68 27	99.03 56	81.13 207	99.86 63	98.63 32	97.36 134	96.63 227

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 23	99.29 80	97.72 81	94.50 37	98.64 28	99.54 3	93.32 17	99.97 21	99.58 10	99.90 7	99.95 15
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		97.77 9	98.18 2	96.53 96	99.54 36	90.14 144	99.41 68	97.70 86	95.46 28	98.60 29	99.19 30	95.71 4	99.49 112	98.15 48	99.85 13	99.95 15
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
9.14			96.87 27		99.34 50		99.50 51	97.49 138	89.41 162	98.59 30	99.43 16	89.78 55	99.69 91	98.69 30	99.62 46

APD-MVS		96.95 29	96.72 32	97.63 40	99.51 41	93.58 68	99.16 95	97.44 147	90.08 141	98.59 30	99.07 51	89.06 62	99.42 123	97.92 51	99.66 38	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_vis1_n_1920		93.08 151	93.42 126	92.04 242	96.31 177	79.36 338	99.83 9	96.06 251	96.72 9	98.53 32	98.10 129	58.57 349	99.91 45	97.86 53	98.79 97	96.85 223

testdata				95.26 151	98.20 96	87.28 220		97.60 112	85.21 263	98.48 33	99.15 39	88.15 76	98.72 164	90.29 182	99.45 59	99.78 38

test_fmvsmconf_n		96.78 34	96.84 29	96.61 89	95.99 193	90.25 139	99.90 2	98.13 42	96.68 11	98.42 34	98.92 74	85.34 140	99.88 54	99.12 22	99.08 76	99.70 52

TEST9					99.57 33	93.17 76	99.38 71	97.66 95	89.57 156	98.39 35	99.18 33	90.88 37	99.66 94

train_agg		97.20 23	97.08 23	97.57 44	99.57 33	93.17 76	99.38 71	97.66 95	90.18 136	98.39 35	99.18 33	90.94 34	99.66 94	98.58 36	99.85 13	99.88 26

test_8					99.55 35	93.07 79	99.37 74	97.64 103	90.18 136	98.36 37	99.19 30	90.94 34	99.64 100

CS-MVS-test		95.98 55	96.34 41	94.90 164	98.06 102	87.66 207	99.69 33	96.10 246	93.66 60	98.35 38	99.05 54	86.28 119	97.66 225	96.96 72	98.90 90	99.37 92

MM		97.76 10	97.39 19	98.86 5	98.30 93	96.83 7	99.81 11	99.13 9	97.66 2	98.29 39	98.96 66	85.84 128	99.90 50	99.72 3	98.80 94	99.85 30

HPM-MVS++		97.72 11	97.59 13	98.14 24	99.53 40	94.76 44	99.19 89	97.75 76	95.66 24	98.21 40	99.29 20	91.10 31	99.99 5	97.68 57	99.87 9	99.68 56

DPM-MVS		97.86 8	97.25 21	99.68 1	98.25 94	99.10 1	99.76 20	97.78 73	96.61 12	98.15 41	99.53 7	93.62 15	100.00 1	91.79 166	99.80 26	99.94 18

test_part2					99.54 36	95.42 22				98.13 42

SteuartSystems-ACMMP		97.25 19	97.34 20	97.01 63	97.38 126	91.46 110	99.75 21	97.66 95	94.14 47	98.13 42	99.26 21	92.16 27	99.66 94	97.91 52	99.64 42	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
FOURS1					99.50 42	88.94 179	99.55 44	97.47 141	91.32 109	98.12 44

test_prior2							99.57 42		91.43 105	98.12 44	98.97 62	90.43 44		98.33 42	99.81 23

CS-MVS		95.75 68	96.19 43	94.40 183	97.88 107	86.22 244	99.66 34	96.12 245	92.69 78	98.07 46	98.89 78	87.09 97	97.59 231	96.71 75	98.62 102	99.39 91

PHI-MVS		96.65 37	96.46 38	97.21 57	99.34 50	91.77 103	99.70 26	98.05 46	86.48 246	98.05 47	99.20 29	89.33 60	99.96 28	98.38 39	99.62 46	99.90 22

MVSFormer		94.71 102	94.08 103	96.61 89	95.05 236	94.87 38	97.77 242	96.17 242	86.84 235	98.04 48	98.52 106	85.52 132	95.99 309	89.83 185	98.97 84	98.96 127

lupinMVS		96.32 45	95.94 54	97.44 46	95.05 236	94.87 38	99.86 4	96.50 220	93.82 57	98.04 48	98.77 85	85.52 132	98.09 195	96.98 71	98.97 84	99.37 92

APDe-MVS		97.53 14	97.47 15	97.70 38	99.58 30	93.63 67	99.56 43	97.52 131	93.59 63	98.01 50	99.12 46	90.80 39	99.55 106	99.26 17	99.79 27	99.93 20
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMP_NAP		96.59 38	96.18 45	97.81 36	98.82 81	93.55 69	98.88 132	97.59 116	90.66 120	97.98 51	99.14 42	86.59 111	100.00 1	96.47 84	99.46 57	99.89 25

agg_prior					99.54 36	92.66 89		97.64 103		97.98 51			99.61 102

CDPH-MVS		96.56 39	96.18 45	97.70 38	99.59 28	93.92 63	99.13 106	97.44 147	89.02 170	97.90 53	99.22 27	88.90 65	99.49 112	94.63 125	99.79 27	99.68 56

MVSMamba_PlusPlus		95.73 70	95.15 78	97.44 46	97.28 134	94.35 56	98.26 204	96.75 203	83.09 300	97.84 54	95.97 218	89.59 57	98.48 175	97.86 53	99.73 31	99.49 81

iter_conf05_11		95.50 74	95.43 71	95.70 133	97.26 136	89.15 169	98.26 204	96.60 210	91.37 108	97.84 54	96.18 210	85.57 131	98.56 171	96.12 88	99.66 38	99.40 88

EPNet		96.82 32	96.68 34	97.25 56	98.65 86	93.10 78	99.48 53	98.76 15	96.54 13	97.84 54	98.22 124	87.49 86	99.66 94	95.35 107	97.78 123	99.00 123
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		97.50 17	97.45 17	97.63 40	99.65 16	93.21 75	99.70 26	98.13 42	94.61 35	97.78 57	99.46 10	89.85 54	99.81 79	97.97 50	99.91 6	99.88 26

test12				97.83 35	99.33 53	94.45 51		97.55 123		97.56 58		88.60 68	99.50 111		99.71 35	99.55 74

xiu_mvs_v1_base_debu		94.73 99	93.98 106	96.99 65	95.19 222	95.24 27	98.62 161	96.50 220	92.99 72	97.52 59	98.83 82	72.37 269	99.15 141	97.03 68	96.74 144	96.58 230

xiu_mvs_v1_base		94.73 99	93.98 106	96.99 65	95.19 222	95.24 27	98.62 161	96.50 220	92.99 72	97.52 59	98.83 82	72.37 269	99.15 141	97.03 68	96.74 144	96.58 230

xiu_mvs_v1_base_debi		94.73 99	93.98 106	96.99 65	95.19 222	95.24 27	98.62 161	96.50 220	92.99 72	97.52 59	98.83 82	72.37 269	99.15 141	97.03 68	96.74 144	96.58 230

ZD-MVS					99.67 10	93.28 74		97.61 110	87.78 213	97.41 62	99.16 36	90.15 51	99.56 105	98.35 41	99.70 36

ETV-MVS		96.00 53	96.00 53	96.00 122	96.56 164	91.05 122	99.63 36	96.61 209	93.26 68	97.39 63	98.30 121	86.62 110	98.13 192	98.07 49	97.57 126	98.82 144

DeepPCF-MVS	93.56 1	96.55 40	97.84 10	92.68 229	98.71 85	78.11 351	99.70 26	97.71 85	98.18 1	97.36 64	99.76 1	90.37 47	99.94 34	99.27 16	99.54 54	99.99 1

test_vis1_n		90.40 203	90.27 193	90.79 270	91.55 316	76.48 356	99.12 107	94.44 337	94.31 41	97.34 65	96.95 181	43.60 388	99.42 123	97.57 59	97.60 125	96.47 234

EC-MVSNet		95.09 86	95.17 77	94.84 167	95.42 213	88.17 195	99.48 53	95.92 266	91.47 103	97.34 65	98.36 118	82.77 177	97.41 242	97.24 65	98.58 103	98.94 132

test_fmvsmconf0.1_n		95.94 59	95.79 62	96.40 103	92.42 300	89.92 155	99.79 16	96.85 198	96.53 15	97.22 67	98.67 97	82.71 181	99.84 69	98.92 27	98.98 83	99.43 87

CANet		97.00 28	96.49 36	98.55 12	98.86 80	96.10 16	99.83 9	97.52 131	95.90 19	97.21 68	98.90 76	82.66 182	99.93 38	98.71 29	98.80 94	99.63 66

CANet_DTU		94.31 114	93.35 128	97.20 58	97.03 152	94.71 46	98.62 161	95.54 296	95.61 25	97.21 68	98.47 114	71.88 274	99.84 69	88.38 204	97.46 131	97.04 218

MVS_0304		97.53 14	97.15 22	98.67 11	97.30 130	96.52 12	99.60 38	98.88 14	97.14 4	97.21 68	98.94 72	86.89 103	99.91 45	99.43 15	98.91 89	99.59 73

test_cas_vis1_n_1920		93.86 126	93.74 119	94.22 191	95.39 216	86.08 250	99.73 22	96.07 250	96.38 17	97.19 71	97.78 136	65.46 324	99.86 63	96.71 75	98.92 88	96.73 225

VNet		95.08 87	94.26 95	97.55 45	98.07 101	93.88 64	98.68 152	98.73 18	90.33 133	97.16 72	97.43 155	79.19 223	99.53 109	96.91 74	91.85 209	99.24 104

region2R		96.30 46	96.17 48	96.70 85	99.70 7	90.31 138	99.46 59	97.66 95	90.55 126	97.07 73	99.07 51	86.85 104	99.97 21	95.43 105	99.74 29	99.81 33

原ACMM1				96.18 112	99.03 71	90.08 147		97.63 107	88.98 171	97.00 74	98.97 62	88.14 77	99.71 90	88.23 206	99.62 46	98.76 151

HFP-MVS		96.42 42	96.26 42	96.90 72	99.69 8	90.96 125	99.47 55	97.81 68	90.54 127	96.88 75	99.05 54	87.57 84	99.96 28	95.65 98	99.72 32	99.78 38

XVS		96.47 41	96.37 40	96.77 78	99.62 22	90.66 133	99.43 65	97.58 118	92.41 85	96.86 76	98.96 66	87.37 89	99.87 58	95.65 98	99.43 61	99.78 38

X-MVStestdata		90.69 200	88.66 223	96.77 78	99.62 22	90.66 133	99.43 65	97.58 118	92.41 85	96.86 76	29.59 412	87.37 89	99.87 58	95.65 98	99.43 61	99.78 38

SR-MVS		96.13 50	96.16 50	96.07 118	99.42 47	89.04 173	98.59 167	97.33 158	90.44 130	96.84 78	99.12 46	86.75 106	99.41 126	97.47 60	99.44 60	99.76 45

TSAR-MVS + GP.		96.95 29	96.91 26	97.07 60	98.88 79	91.62 106	99.58 41	96.54 218	95.09 32	96.84 78	98.63 101	91.16 29	99.77 85	99.04 24	96.42 149	99.81 33

ACMMPR		96.28 47	96.14 52	96.73 82	99.68 9	90.47 136	99.47 55	97.80 70	90.54 127	96.83 80	99.03 56	86.51 115	99.95 31	95.65 98	99.72 32	99.75 46

test_fmvs1		92.35 164	92.94 140	90.57 275	97.19 140	75.43 360	99.55 44	94.97 321	95.20 31	96.82 81	97.57 149	59.59 347	99.84 69	97.30 63	98.29 114	96.46 235

PMMVS		93.62 135	93.90 113	92.79 224	96.79 159	81.40 321	98.85 133	96.81 199	91.25 110	96.82 81	98.15 128	77.02 237	98.13 192	93.15 152	96.30 153	98.83 143

PGM-MVS		95.85 62	95.65 68	96.45 99	99.50 42	89.77 159	98.22 208	98.90 13	89.19 165	96.74 83	98.95 69	85.91 127	99.92 40	93.94 134	99.46 57	99.66 60

jason		95.40 79	94.86 86	97.03 62	92.91 295	94.23 57	99.70 26	96.30 230	93.56 64	96.73 84	98.52 106	81.46 203	97.91 204	96.08 92	98.47 109	98.96 127
jason: jason.
新几何1				97.40 50	98.92 77	92.51 94		97.77 75	85.52 259	96.69 85	99.06 53	88.08 78	99.89 53	84.88 244	99.62 46	99.79 36

SR-MVS-dyc-post		95.75 68	95.86 57	95.41 144	99.22 59	87.26 223	98.40 190	97.21 167	89.63 152	96.67 86	98.97 62	86.73 108	99.36 130	96.62 78	99.31 68	99.60 69

RE-MVS-def			95.70 64		99.22 59	87.26 223	98.40 190	97.21 167	89.63 152	96.67 86	98.97 62	85.24 141		96.62 78	99.31 68	99.60 69

APD-MVS_3200maxsize		95.64 72	95.65 68	95.62 138	99.24 58	87.80 203	98.42 185	97.22 166	88.93 175	96.64 88	98.98 61	85.49 135	99.36 130	96.68 77	99.27 71	99.70 52

mvsany_test1		94.57 108	95.09 82	92.98 220	95.84 199	82.07 315	98.76 145	95.24 314	92.87 77	96.45 89	98.71 94	84.81 147	99.15 141	97.68 57	95.49 167	97.73 196

MG-MVS		97.24 20	96.83 31	98.47 15	99.79 5	95.71 19	99.07 111	99.06 10	94.45 40	96.42 90	98.70 95	88.81 66	99.74 88	95.35 107	99.86 12	99.97 7

test_fmvs1_n		91.07 191	91.41 171	90.06 289	94.10 263	74.31 364	99.18 91	94.84 325	94.81 33	96.37 91	97.46 153	50.86 377	99.82 76	97.14 67	97.90 118	96.04 242

h-mvs33		92.47 163	91.95 160	94.05 199	97.13 145	85.01 276	98.36 196	98.08 44	93.85 55	96.27 92	96.73 194	83.19 169	99.43 122	95.81 96	68.09 366	97.70 197

hse-mvs2		91.67 178	91.51 169	92.15 239	96.22 181	82.61 311	97.74 245	97.53 127	93.85 55	96.27 92	96.15 211	83.19 169	97.44 240	95.81 96	66.86 373	96.40 237

alignmvs		95.77 66	95.00 84	98.06 29	97.35 128	95.68 20	99.71 25	97.50 136	91.50 102	96.16 94	98.61 103	86.28 119	99.00 151	96.19 87	91.74 211	99.51 79

CP-MVS		96.22 48	96.15 51	96.42 101	99.67 10	89.62 162	99.70 26	97.61 110	90.07 142	96.00 95	99.16 36	87.43 87	99.92 40	96.03 93	99.72 32	99.70 52

MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 10	99.70 26	97.98 53	97.18 3	95.96 96	99.33 19	92.62 24	100.00 1	98.99 25	99.93 1	99.98 6

diffmvs		94.59 107	94.19 98	95.81 129	95.54 209	90.69 131	98.70 150	95.68 288	91.61 98	95.96 96	97.81 133	80.11 212	98.06 197	96.52 83	95.76 162	98.67 156
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GST-MVS		95.97 56	95.66 66	96.90 72	99.49 45	91.22 112	99.45 61	97.48 139	89.69 150	95.89 98	98.72 91	86.37 118	99.95 31	94.62 126	99.22 73	99.52 77

DeepC-MVS_fast	93.52 2	97.16 24	96.84 29	98.13 25	99.61 24	94.45 51	98.85 133	97.64 103	96.51 16	95.88 99	99.39 18	87.35 93	99.99 5	96.61 80	99.69 37	99.96 10
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test222					98.32 92	91.21 113	98.08 225	97.58 118	83.74 288	95.87 100	99.02 58	86.74 107			99.64 42	99.81 33

sasdasda		95.02 88	93.96 109	98.20 21	97.53 120	95.92 17	98.71 147	96.19 239	91.78 95	95.86 101	98.49 110	79.53 218	99.03 149	96.12 88	91.42 223	99.66 60

ZNCC-MVS		96.09 51	95.81 60	96.95 71	99.42 47	91.19 114	99.55 44	97.53 127	89.72 149	95.86 101	98.94 72	86.59 111	99.97 21	95.13 112	99.56 52	99.68 56

canonicalmvs		95.02 88	93.96 109	98.20 21	97.53 120	95.92 17	98.71 147	96.19 239	91.78 95	95.86 101	98.49 110	79.53 218	99.03 149	96.12 88	91.42 223	99.66 60

dcpmvs_2		95.67 71	96.18 45	94.12 195	98.82 81	84.22 286	97.37 260	95.45 301	90.70 119	95.77 104	98.63 101	90.47 43	98.68 166	99.20 20	99.22 73	99.45 84

MGCFI-Net		94.89 90	93.84 116	98.06 29	97.49 123	95.55 21	98.64 158	96.10 246	91.60 100	95.75 105	98.46 116	79.31 222	98.98 153	95.95 95	91.24 227	99.65 63

Effi-MVS+		93.87 125	93.15 134	96.02 121	95.79 200	90.76 129	96.70 289	95.78 280	86.98 232	95.71 106	97.17 170	79.58 216	98.01 202	94.57 127	96.09 157	99.31 98

HPM-MVS_fast		94.89 90	94.62 88	95.70 133	99.11 66	88.44 193	99.14 103	97.11 179	85.82 254	95.69 107	98.47 114	83.46 162	99.32 135	93.16 151	99.63 45	99.35 94

HY-MVS	88.56 7	95.29 81	94.23 96	98.48 14	97.72 110	96.41 13	94.03 339	98.74 16	92.42 84	95.65 108	94.76 240	86.52 114	99.49 112	95.29 109	92.97 188	99.53 76

CHOSEN 280x420		96.80 33	96.85 28	96.66 88	97.85 108	94.42 53	94.76 331	98.36 29	92.50 81	95.62 109	97.52 150	97.92 1	97.38 243	98.31 44	98.80 94	98.20 184

test_fmvsmconf0.01_n		94.14 116	93.51 124	96.04 119	86.79 372	89.19 167	99.28 83	95.94 260	95.70 21	95.50 110	98.49 110	73.27 262	99.79 82	98.28 45	98.32 113	99.15 111

MP-MVS		96.00 53	95.82 58	96.54 95	99.47 46	90.13 146	99.36 75	97.41 151	90.64 123	95.49 111	98.95 69	85.51 134	99.98 9	96.00 94	99.59 51	99.52 77
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS		95.41 78	95.22 76	95.99 123	99.29 55	89.14 170	99.17 94	97.09 183	87.28 226	95.40 112	98.48 113	84.93 144	99.38 128	95.64 102	99.65 40	99.47 83
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UA-Net		93.30 143	92.62 146	95.34 146	96.27 179	88.53 192	95.88 314	96.97 194	90.90 115	95.37 113	97.07 174	82.38 190	99.10 147	83.91 260	94.86 173	98.38 170

sss		94.85 95	93.94 111	97.58 42	96.43 171	94.09 61	98.93 127	99.16 8	89.50 159	95.27 114	97.85 131	81.50 201	99.65 98	92.79 158	94.02 179	98.99 124

WTY-MVS		95.97 56	95.11 81	98.54 13	97.62 114	96.65 9	99.44 62	98.74 16	92.25 88	95.21 115	98.46 116	86.56 113	99.46 118	95.00 117	92.69 192	99.50 80

DELS-MVS		97.12 25	96.60 35	98.68 10	98.03 103	96.57 11	99.84 8	97.84 61	96.36 18	95.20 116	98.24 123	88.17 74	99.83 73	96.11 91	99.60 50	99.64 64
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
MVS_111021_HR		96.69 35	96.69 33	96.72 84	98.58 88	91.00 124	99.14 103	99.45 1	93.86 54	95.15 117	98.73 89	88.48 69	99.76 86	97.23 66	99.56 52	99.40 88

MVS_Test		93.67 133	92.67 145	96.69 86	96.72 161	92.66 89	97.22 268	96.03 252	87.69 219	95.12 118	94.03 249	81.55 199	98.28 184	89.17 199	96.46 147	99.14 112

MVS_111021_LR		95.78 65	95.94 54	95.28 150	98.19 98	87.69 204	98.80 139	99.26 7	93.39 65	95.04 119	98.69 96	84.09 154	99.76 86	96.96 72	99.06 78	98.38 170

CostFormer		92.89 153	92.48 149	94.12 195	94.99 238	85.89 257	92.89 349	97.00 192	86.98 232	95.00 120	90.78 314	90.05 53	97.51 236	92.92 155	91.73 212	98.96 127

testing222		94.48 111	94.00 105	95.95 125	97.30 130	92.27 97	98.82 136	97.92 55	89.20 164	94.82 121	97.26 161	87.13 96	97.32 246	91.95 164	91.56 215	98.25 178

mPP-MVS		95.90 61	95.75 63	96.38 104	99.58 30	89.41 166	99.26 84	97.41 151	90.66 120	94.82 121	98.95 69	86.15 123	99.98 9	95.24 111	99.64 42	99.74 47

EI-MVSNet-Vis-set		95.76 67	95.63 70	96.17 114	99.14 64	90.33 137	98.49 178	97.82 65	91.92 93	94.75 123	98.88 80	87.06 99	99.48 116	95.40 106	97.17 139	98.70 154

LFMVS		92.23 169	90.84 183	96.42 101	98.24 95	91.08 121	98.24 207	96.22 236	83.39 295	94.74 124	98.31 120	61.12 342	98.85 156	94.45 128	92.82 189	99.32 97

tpmrst		92.78 154	92.16 154	94.65 174	96.27 179	87.45 214	91.83 359	97.10 182	89.10 169	94.68 125	90.69 318	88.22 73	97.73 223	89.78 188	91.80 210	98.77 150

test_yl		95.27 82	94.60 89	97.28 54	98.53 89	92.98 82	99.05 115	98.70 19	86.76 238	94.65 126	97.74 139	87.78 81	99.44 119	95.57 103	92.61 193	99.44 85

DCV-MVSNet		95.27 82	94.60 89	97.28 54	98.53 89	92.98 82	99.05 115	98.70 19	86.76 238	94.65 126	97.74 139	87.78 81	99.44 119	95.57 103	92.61 193	99.44 85

testing11		95.33 80	94.98 85	96.37 105	97.20 138	92.31 96	99.29 80	97.68 90	90.59 124	94.43 128	97.20 166	90.79 40	98.60 169	95.25 110	92.38 197	98.18 185

DP-MVS Recon		95.85 62	95.15 78	97.95 32	99.87 2	94.38 54	99.60 38	97.48 139	86.58 241	94.42 129	99.13 44	87.36 92	99.98 9	93.64 141	98.33 111	99.48 82

ETVMVS		94.50 110	93.90 113	96.31 108	97.48 124	92.98 82	99.07 111	97.86 59	88.09 203	94.40 130	96.90 184	88.35 71	97.28 247	90.72 179	92.25 203	98.66 159

MTAPA		96.09 51	95.80 61	96.96 70	99.29 55	91.19 114	97.23 267	97.45 144	92.58 79	94.39 131	99.24 25	86.43 117	99.99 5	96.22 86	99.40 64	99.71 51

CPTT-MVS		94.60 105	94.43 93	95.09 156	99.66 12	86.85 228	99.44 62	97.47 141	83.22 297	94.34 132	98.96 66	82.50 183	99.55 106	94.81 120	99.50 55	98.88 137

PVSNet_BlendedMVS		93.36 141	93.20 133	93.84 206	98.77 83	91.61 107	99.47 55	98.04 48	91.44 104	94.21 133	92.63 283	83.50 160	99.87 58	97.41 61	83.37 279	90.05 342

PVSNet_Blended		95.94 59	95.66 66	96.75 80	98.77 83	91.61 107	99.88 3	98.04 48	93.64 62	94.21 133	97.76 137	83.50 160	99.87 58	97.41 61	97.75 124	98.79 147

EI-MVSNet-UG-set		95.43 76	95.29 74	95.86 128	99.07 70	89.87 156	98.43 184	97.80 70	91.78 95	94.11 135	98.77 85	86.25 121	99.48 116	94.95 119	96.45 148	98.22 182

EIA-MVS		95.11 85	95.27 75	94.64 176	96.34 176	86.51 232	99.59 40	96.62 208	92.51 80	94.08 136	98.64 99	86.05 124	98.24 187	95.07 114	98.50 106	99.18 109

MAR-MVS		94.43 112	94.09 102	95.45 142	99.10 68	87.47 213	98.39 194	97.79 72	88.37 192	94.02 137	99.17 35	78.64 229	99.91 45	92.48 160	98.85 92	98.96 127
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
PAPM		96.35 43	95.94 54	97.58 42	94.10 263	95.25 26	98.93 127	98.17 37	94.26 42	93.94 138	98.72 91	89.68 56	97.88 207	96.36 85	99.29 70	99.62 68

GG-mvs-BLEND				96.98 68	96.53 166	94.81 43	87.20 381	97.74 77		93.91 139	96.40 203	96.56 2	96.94 259	95.08 113	98.95 87	99.20 108

API-MVS		94.78 97	94.18 100	96.59 91	99.21 61	90.06 151	98.80 139	97.78 73	83.59 292	93.85 140	99.21 28	83.79 157	99.97 21	92.37 161	99.00 82	99.74 47

tpm2		91.77 176	91.09 176	93.82 207	94.83 245	85.56 265	92.51 354	97.16 174	84.00 283	93.83 141	90.66 320	87.54 85	97.17 249	87.73 212	91.55 216	98.72 152

PAPR		96.35 43	95.82 58	97.94 33	99.63 18	94.19 59	99.42 67	97.55 123	92.43 82	93.82 142	99.12 46	87.30 94	99.91 45	94.02 133	99.06 78	99.74 47

testing99		94.88 92	94.45 91	96.17 114	97.20 138	91.91 101	99.20 88	97.66 95	89.95 144	93.68 143	97.06 175	90.28 49	98.50 172	93.52 143	91.54 217	98.12 187

testing91		94.88 92	94.44 92	96.21 110	97.19 140	91.90 102	99.23 86	97.66 95	89.91 145	93.66 144	97.05 177	90.21 50	98.50 172	93.52 143	91.53 220	98.25 178

PVSNet	87.13 12	93.69 130	92.83 142	96.28 109	97.99 104	90.22 142	99.38 71	98.93 12	91.42 106	93.66 144	97.68 142	71.29 281	99.64 100	87.94 210	97.20 136	98.98 125

baseline		93.91 123	93.30 130	95.72 132	95.10 233	90.07 148	97.48 256	95.91 271	91.03 112	93.54 146	97.68 142	79.58 216	98.02 201	94.27 131	95.14 170	99.08 119

test2506		94.80 96	94.21 97	96.58 92	96.41 172	92.18 99	98.01 228	98.96 11	90.82 117	93.46 147	97.28 159	85.92 125	98.45 177	89.82 187	97.19 137	99.12 115

VDD-MVS		91.24 189	90.18 194	94.45 182	97.08 149	85.84 260	98.40 190	96.10 246	86.99 229	93.36 148	98.16 127	54.27 366	99.20 138	96.59 81	90.63 233	98.31 177

VDDNet		90.08 213	88.54 228	94.69 173	94.41 254	87.68 205	98.21 210	96.40 225	76.21 358	93.33 149	97.75 138	54.93 364	98.77 159	94.71 124	90.96 228	97.61 202

thisisatest0515		94.75 98	94.19 98	96.43 100	96.13 191	92.64 92	99.47 55	97.60 112	87.55 222	93.17 150	97.59 147	94.71 11	98.42 178	88.28 205	93.20 185	98.24 181

MP-MVS-pluss		95.80 64	95.30 73	97.29 53	98.95 76	92.66 89	98.59 167	97.14 175	88.95 173	93.12 151	99.25 23	85.62 129	99.94 34	96.56 82	99.48 56	99.28 101
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MDTV_nov1_ep13_2view						91.17 116	91.38 367		87.45 224	93.08 152		86.67 109		87.02 216		98.95 131

EPNet_dtu		92.28 167	92.15 155	92.70 228	97.29 132	84.84 278	98.64 158	97.82 65	92.91 75	93.02 153	97.02 178	85.48 137	95.70 323	72.25 347	94.89 172	97.55 203
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
gg-mvs-nofinetune		90.00 214	87.71 240	96.89 76	96.15 186	94.69 47	85.15 387	97.74 77	68.32 387	92.97 154	60.16 400	96.10 3	96.84 262	93.89 135	98.87 91	99.14 112

test_fmvsmvis_n_1920		95.47 75	95.40 72	95.70 133	94.33 256	90.22 142	99.70 26	96.98 193	96.80 7	92.75 155	98.89 78	82.46 188	99.92 40	98.36 40	98.33 111	96.97 221

casdiffmvs		93.98 121	93.43 125	95.61 139	95.07 235	89.86 157	98.80 139	95.84 279	90.98 114	92.74 156	97.66 144	79.71 215	98.10 194	94.72 123	95.37 168	98.87 139
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
114514_t		94.06 117	93.05 136	97.06 61	99.08 69	92.26 98	98.97 125	97.01 191	82.58 312	92.57 157	98.22 124	80.68 210	99.30 136	89.34 195	99.02 81	99.63 66

OMC-MVS		93.90 124	93.62 121	94.73 172	98.63 87	87.00 226	98.04 227	96.56 216	92.19 89	92.46 158	98.73 89	79.49 220	99.14 145	92.16 163	94.34 177	98.03 189

PAPM_NR		95.43 76	95.05 83	96.57 94	99.42 47	90.14 144	98.58 169	97.51 133	90.65 122	92.44 159	98.90 76	87.77 83	99.90 50	90.88 174	99.32 67	99.68 56

UGNet		91.91 175	90.85 182	95.10 155	97.06 150	88.69 188	98.01 228	98.24 34	92.41 85	92.39 160	93.61 263	60.52 344	99.68 92	88.14 207	97.25 135	96.92 222
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
MDTV_nov1_ep13			90.47 192		96.14 188	88.55 190	91.34 368	97.51 133	89.58 155	92.24 161	90.50 331	86.99 102	97.61 230	77.64 309	92.34 199

FE-MVS		91.38 184	90.16 195	95.05 159	96.46 170	87.53 211	89.69 378	97.84 61	82.97 304	92.18 162	92.00 292	84.07 155	98.93 155	80.71 288	95.52 166	98.68 155

Vis-MVSNet		92.64 157	91.85 161	95.03 160	95.12 229	88.23 194	98.48 180	96.81 199	91.61 98	92.16 163	97.22 165	71.58 279	98.00 203	85.85 235	97.81 120	98.88 137
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
FA-MVS(test-final)		92.22 170	91.08 177	95.64 137	96.05 192	88.98 176	91.60 363	97.25 161	86.99 229	91.84 164	92.12 286	83.03 172	99.00 151	86.91 220	93.91 180	98.93 133

TESTMET0.1,1		93.82 127	93.26 132	95.49 141	95.21 221	90.25 139	99.15 100	97.54 126	89.18 166	91.79 165	94.87 238	89.13 61	97.63 228	86.21 228	96.29 154	98.60 160

thisisatest0530		94.00 119	93.52 123	95.43 143	95.76 202	90.02 153	98.99 122	97.60 112	86.58 241	91.74 166	97.36 158	94.78 10	98.34 180	86.37 226	92.48 196	97.94 192

UWE-MVS		93.18 147	93.40 127	92.50 232	96.56 164	83.55 295	98.09 224	97.84 61	89.50 159	91.72 167	96.23 209	91.08 32	96.70 268	86.28 227	93.33 184	97.26 210

AUN-MVS		90.17 210	89.50 203	92.19 237	96.21 182	82.67 309	97.76 244	97.53 127	88.05 204	91.67 168	96.15 211	83.10 171	97.47 237	88.11 208	66.91 372	96.43 236

EPMVS		92.59 160	91.59 167	95.59 140	97.22 137	90.03 152	91.78 360	98.04 48	90.42 131	91.66 169	90.65 321	86.49 116	97.46 238	81.78 281	96.31 152	99.28 101

test-LLR		93.11 150	92.68 144	94.40 183	94.94 241	87.27 221	99.15 100	97.25 161	90.21 134	91.57 170	94.04 247	84.89 145	97.58 232	85.94 232	96.13 155	98.36 174

test-mter		93.27 145	92.89 141	94.40 183	94.94 241	87.27 221	99.15 100	97.25 161	88.95 173	91.57 170	94.04 247	88.03 79	97.58 232	85.94 232	96.13 155	98.36 174

JIA-IIPM		85.97 283	84.85 283	89.33 310	93.23 291	73.68 367	85.05 388	97.13 177	69.62 383	91.56 172	68.03 398	88.03 79	96.96 257	77.89 308	93.12 186	97.34 207

casdiffmvs_mvg		94.00 119	93.33 129	96.03 120	95.22 220	90.90 127	99.09 109	95.99 253	90.58 125	91.55 173	97.37 157	79.91 214	98.06 197	95.01 116	95.22 169	99.13 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		94.67 103	94.11 101	96.34 107	97.14 144	91.10 119	99.32 79	97.43 149	92.10 92	91.53 174	96.38 206	83.29 166	99.68 92	93.42 148	96.37 150	98.25 178

CHOSEN 1792x2688		94.35 113	93.82 117	95.95 125	97.40 125	88.74 187	98.41 187	98.27 31	92.18 90	91.43 175	96.40 203	78.88 224	99.81 79	93.59 142	97.81 120	99.30 99

ACMMP		94.67 103	94.30 94	95.79 130	99.25 57	88.13 197	98.41 187	98.67 22	90.38 132	91.43 175	98.72 91	82.22 192	99.95 31	93.83 138	95.76 162	99.29 100
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
ECVR-MVS		92.29 166	91.33 172	95.15 154	96.41 172	87.84 202	98.10 221	94.84 325	90.82 117	91.42 177	97.28 159	65.61 321	98.49 174	90.33 181	97.19 137	99.12 115

EPP-MVSNet		93.75 129	93.67 120	94.01 201	95.86 198	85.70 262	98.67 154	97.66 95	84.46 277	91.36 178	97.18 169	91.16 29	97.79 213	92.93 154	93.75 181	98.53 162

PLC	91.07 3	94.23 115	94.01 104	94.87 165	99.17 63	87.49 212	99.25 85	96.55 217	88.43 190	91.26 179	98.21 126	85.92 125	99.86 63	89.77 189	97.57 126	97.24 211
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HyFIR lowres test		93.68 132	93.29 131	94.87 165	97.57 119	88.04 199	98.18 212	98.47 25	87.57 221	91.24 180	95.05 235	85.49 135	97.46 238	93.22 150	92.82 189	99.10 117

thres200		93.69 130	92.59 147	96.97 69	97.76 109	94.74 45	99.35 76	99.36 2	89.23 163	91.21 181	96.97 180	83.42 163	98.77 159	85.08 240	90.96 228	97.39 206

test1111		92.12 171	91.19 175	94.94 162	96.15 186	87.36 217	98.12 218	94.84 325	90.85 116	90.97 182	97.26 161	65.60 322	98.37 179	89.74 190	97.14 140	99.07 121

CDS-MVSNet		93.47 136	93.04 137	94.76 169	94.75 247	89.45 165	98.82 136	97.03 188	87.91 210	90.97 182	96.48 201	89.06 62	96.36 288	89.50 191	92.81 191	98.49 164
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tfpn200view9		93.43 138	92.27 152	96.90 72	97.68 112	94.84 40	99.18 91	99.36 2	88.45 187	90.79 184	96.90 184	83.31 164	98.75 161	84.11 256	90.69 230	97.12 213

thres400		93.39 140	92.27 152	96.73 82	97.68 112	94.84 40	99.18 91	99.36 2	88.45 187	90.79 184	96.90 184	83.31 164	98.75 161	84.11 256	90.69 230	96.61 228

CR-MVSNet		88.83 234	87.38 245	93.16 217	93.47 284	86.24 242	84.97 389	94.20 345	88.92 176	90.76 186	86.88 366	84.43 150	94.82 344	70.64 351	92.17 205	98.41 167

RPMNet		85.07 297	81.88 315	94.64 176	93.47 284	86.24 242	84.97 389	97.21 167	64.85 394	90.76 186	78.80 391	80.95 209	99.27 137	53.76 392	92.17 205	98.41 167

PatchmatchNet		92.05 174	91.04 178	95.06 157	96.17 185	89.04 173	91.26 369	97.26 160	89.56 157	90.64 188	90.56 327	88.35 71	97.11 251	79.53 294	96.07 159	99.03 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tttt0517		93.30 143	93.01 138	94.17 193	95.57 207	86.47 234	98.51 175	97.60 112	85.99 252	90.55 189	97.19 168	94.80 9	98.31 181	85.06 241	91.86 208	97.74 195

PatchT		85.44 293	83.19 303	92.22 235	93.13 293	83.00 301	83.80 395	96.37 226	70.62 376	90.55 189	79.63 390	84.81 147	94.87 342	58.18 388	91.59 214	98.79 147

tpm		89.67 219	88.95 216	91.82 246	92.54 298	81.43 320	92.95 348	95.92 266	87.81 212	90.50 191	89.44 346	84.99 143	95.65 324	83.67 263	82.71 284	98.38 170

thres100view900		93.34 142	92.15 155	96.90 72	97.62 114	94.84 40	99.06 114	99.36 2	87.96 208	90.47 192	96.78 192	83.29 166	98.75 161	84.11 256	90.69 230	97.12 213

thres600view7		93.18 147	92.00 158	96.75 80	97.62 114	94.92 35	99.07 111	99.36 2	87.96 208	90.47 192	96.78 192	83.29 166	98.71 165	82.93 270	90.47 234	96.61 228

AdaColmap		93.82 127	93.06 135	96.10 117	99.88 1	89.07 172	98.33 198	97.55 123	86.81 237	90.39 194	98.65 98	75.09 244	99.98 9	93.32 149	97.53 129	99.26 103

XVG-OURS-SEG-HR		90.95 194	90.66 189	91.83 245	95.18 225	81.14 328	95.92 311	95.92 266	88.40 191	90.33 195	97.85 131	70.66 284	99.38 128	92.83 156	88.83 240	94.98 249

IS-MVSNet		93.00 152	92.51 148	94.49 179	96.14 188	87.36 217	98.31 201	95.70 286	88.58 183	90.17 196	97.50 151	83.02 173	97.22 248	87.06 215	96.07 159	98.90 136

CSCG		94.87 94	94.71 87	95.36 145	99.54 36	86.49 233	99.34 77	98.15 40	82.71 310	90.15 197	99.25 23	89.48 59	99.86 63	94.97 118	98.82 93	99.72 50

iter_conf05		94.60 105	93.87 115	96.79 77	97.28 134	94.04 62	95.67 323	95.94 260	83.09 300	90.06 198	95.97 218	89.59 57	98.48 175	97.86 53	99.34 65	97.86 194

SCA		90.64 201	89.25 210	94.83 168	94.95 240	88.83 183	96.26 301	97.21 167	90.06 143	90.03 199	90.62 323	66.61 313	96.81 264	83.16 266	94.36 176	98.84 140

XVG-OURS		90.83 196	90.49 191	91.86 244	95.23 219	81.25 325	95.79 319	95.92 266	88.96 172	90.02 200	98.03 130	71.60 278	99.35 133	91.06 171	87.78 244	94.98 249

ADS-MVSNet2		87.62 259	86.88 253	89.86 295	96.21 182	79.14 341	87.15 382	92.99 359	83.01 302	89.91 201	87.27 362	78.87 225	92.80 365	74.20 334	92.27 201	97.64 198

ADS-MVSNet		88.99 227	87.30 246	94.07 197	96.21 182	87.56 210	87.15 382	96.78 202	83.01 302	89.91 201	87.27 362	78.87 225	97.01 256	74.20 334	92.27 201	97.64 198

mamv4		91.41 182	93.57 122	84.91 348	97.11 147	58.11 395	95.68 322	95.93 264	82.09 322	89.78 203	95.71 224	90.09 52	98.24 187	97.26 64	98.50 106	98.38 170

ab-mvs		91.05 193	89.17 211	96.69 86	95.96 195	91.72 105	92.62 353	97.23 165	85.61 258	89.74 204	93.89 256	68.55 295	99.42 123	91.09 170	87.84 243	98.92 135

TAMVS		92.62 158	92.09 157	94.20 192	94.10 263	87.68 205	98.41 187	96.97 194	87.53 223	89.74 204	96.04 216	84.77 149	96.49 281	88.97 201	92.31 200	98.42 166

Vis-MVSNet (Re-imp)		93.26 146	93.00 139	94.06 198	96.14 188	86.71 231	98.68 152	96.70 204	88.30 196	89.71 206	97.64 145	85.43 138	96.39 286	88.06 209	96.32 151	99.08 119

CNLPA		93.64 134	92.74 143	96.36 106	98.96 75	90.01 154	99.19 89	95.89 274	86.22 249	89.40 207	98.85 81	80.66 211	99.84 69	88.57 202	96.92 142	99.24 104

Anonymous202405211		88.84 232	87.03 251	94.27 188	98.14 100	84.18 287	98.44 183	95.58 294	76.79 357	89.34 208	96.88 187	53.42 369	99.54 108	87.53 214	87.12 247	99.09 118

Fast-Effi-MVS+		91.72 177	90.79 186	94.49 179	95.89 196	87.40 216	99.54 49	95.70 286	85.01 270	89.28 209	95.68 225	77.75 233	97.57 235	83.22 265	95.06 171	98.51 163

PatchMatch-RL		91.47 180	90.54 190	94.26 189	98.20 96	86.36 239	96.94 277	97.14 175	87.75 215	88.98 210	95.75 223	71.80 276	99.40 127	80.92 286	97.39 133	97.02 219

dp		90.16 211	88.83 219	94.14 194	96.38 175	86.42 235	91.57 364	97.06 185	84.76 274	88.81 211	90.19 339	84.29 152	97.43 241	75.05 326	91.35 226	98.56 161

DeepC-MVS	91.02 4	94.56 109	93.92 112	96.46 98	97.16 143	90.76 129	98.39 194	97.11 179	93.92 50	88.66 212	98.33 119	78.14 231	99.85 67	95.02 115	98.57 104	98.78 149
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline1		92.61 159	91.28 173	96.58 92	97.05 151	94.63 48	97.72 246	96.20 237	89.82 147	88.56 213	96.85 188	86.85 104	97.82 211	88.42 203	80.10 296	97.30 208

Anonymous20240529		87.66 258	85.58 271	93.92 203	97.59 117	85.01 276	98.13 216	97.13 177	66.69 392	88.47 214	96.01 217	55.09 363	99.51 110	87.00 217	84.12 270	97.23 212

CVMVSNet		90.30 206	90.91 181	88.46 322	94.32 257	73.58 368	97.61 253	97.59 116	90.16 139	88.43 215	97.10 172	76.83 238	92.86 362	82.64 272	93.54 183	98.93 133

TR-MVS		90.77 197	89.44 205	94.76 169	96.31 177	88.02 200	97.92 232	95.96 257	85.52 259	88.22 216	97.23 164	66.80 312	98.09 195	84.58 248	92.38 197	98.17 186

F-COLMAP		92.07 173	91.75 165	93.02 219	98.16 99	82.89 305	98.79 143	95.97 255	86.54 243	87.92 217	97.80 134	78.69 228	99.65 98	85.97 230	95.93 161	96.53 233

WB-MVSnew		88.69 240	88.34 230	89.77 299	94.30 261	85.99 255	98.14 215	97.31 159	87.15 228	87.85 218	96.07 215	69.91 285	95.52 327	72.83 345	91.47 221	87.80 366

BH-RMVSNet		91.25 187	89.99 197	95.03 160	96.75 160	88.55 190	98.65 156	94.95 322	87.74 216	87.74 219	97.80 134	68.27 298	98.14 191	80.53 291	97.49 130	98.41 167

Effi-MVS+-dtu		89.97 216	90.68 188	87.81 326	95.15 226	71.98 375	97.87 236	95.40 305	91.92 93	87.57 220	91.44 302	74.27 253	96.84 262	89.45 192	93.10 187	94.60 251

HQP-NCC					93.95 268		99.16 95		93.92 50	87.57 220

ACMP_Plane					93.95 268		99.16 95		93.92 50	87.57 220

HQP4-MVS										87.57 220			97.77 215			92.72 262

HQP-MVS		91.50 179	91.23 174	92.29 234	93.95 268	86.39 237	99.16 95	96.37 226	93.92 50	87.57 220	96.67 197	73.34 259	97.77 215	93.82 139	86.29 251	92.72 262

TAPA-MVS	87.50 9	90.35 204	89.05 214	94.25 190	98.48 91	85.17 273	98.42 185	96.58 215	82.44 317	87.24 225	98.53 105	82.77 177	98.84 157	59.09 386	97.88 119	98.72 152
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		90.60 202	89.56 202	93.72 210	95.10 233	85.43 266	99.41 68	94.94 323	83.96 285	87.21 226	96.83 191	74.37 251	97.05 255	80.50 292	93.73 182	98.67 156

HQP_MVS		91.26 185	90.95 180	92.16 238	93.84 275	86.07 252	99.02 118	96.30 230	93.38 66	86.99 227	96.52 199	72.92 264	97.75 221	93.46 146	86.17 254	92.67 264

plane_prior3						85.91 256			93.65 61	86.99 227

GA-MVS		90.10 212	88.69 222	94.33 186	92.44 299	87.97 201	99.08 110	96.26 234	89.65 151	86.92 229	93.11 275	68.09 300	96.96 257	82.54 274	90.15 235	98.05 188

1112_ss		92.71 155	91.55 168	96.20 111	95.56 208	91.12 117	98.48 180	94.69 332	88.29 197	86.89 230	98.50 108	87.02 100	98.66 167	84.75 245	89.77 238	98.81 145

Test_1112_low_res		92.27 168	90.97 179	96.18 112	95.53 210	91.10 119	98.47 182	94.66 333	88.28 198	86.83 231	93.50 267	87.00 101	98.65 168	84.69 246	89.74 239	98.80 146

cascas		90.93 195	89.33 209	95.76 131	95.69 204	93.03 81	98.99 122	96.59 212	80.49 338	86.79 232	94.45 244	65.23 325	98.60 169	93.52 143	92.18 204	95.66 245

baseline2		94.04 118	93.80 118	94.74 171	93.07 294	90.25 139	98.12 218	98.16 39	89.86 146	86.53 233	96.95 181	95.56 5	98.05 199	91.44 168	94.53 174	95.93 243

OPM-MVS		89.76 218	89.15 212	91.57 254	90.53 330	85.58 264	98.11 220	95.93 264	92.88 76	86.05 234	96.47 202	67.06 311	97.87 208	89.29 198	86.08 256	91.26 310
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPA-MVSNet		89.10 226	87.66 241	93.45 212	92.56 297	91.02 123	97.97 231	98.32 30	86.92 234	86.03 235	92.01 290	68.84 294	97.10 253	90.92 173	75.34 319	92.23 274

SDMVSNet		91.09 190	89.91 198	94.65 174	96.80 157	90.54 135	97.78 240	97.81 68	88.34 194	85.73 236	95.26 232	66.44 316	98.26 185	94.25 132	86.75 248	95.14 246

sd_testset		89.23 224	88.05 237	92.74 227	96.80 157	85.33 269	95.85 317	97.03 188	88.34 194	85.73 236	95.26 232	61.12 342	97.76 220	85.61 236	86.75 248	95.14 246

tpm cat1		88.89 230	87.27 247	93.76 208	95.79 200	85.32 270	90.76 374	97.09 183	76.14 359	85.72 238	88.59 352	82.92 174	98.04 200	76.96 313	91.43 222	97.90 193

IB-MVS	89.43 6	92.12 171	90.83 185	95.98 124	95.40 215	90.78 128	99.81 11	98.06 45	91.23 111	85.63 239	93.66 262	90.63 41	98.78 158	91.22 169	71.85 355	98.36 174
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
EI-MVSNet		89.87 217	89.38 208	91.36 257	94.32 257	85.87 258	97.61 253	96.59 212	85.10 265	85.51 240	97.10 172	81.30 206	96.56 274	83.85 262	83.03 281	91.64 289

MVSTER		92.71 155	92.32 150	93.86 205	97.29 132	92.95 85	99.01 120	96.59 212	90.09 140	85.51 240	94.00 251	94.61 14	96.56 274	90.77 178	83.03 281	92.08 282

test_fmvs2		85.10 296	85.45 274	84.02 354	89.85 338	65.63 388	98.49 178	92.59 364	90.45 129	85.43 242	93.32 268	43.94 386	96.59 272	90.81 176	84.19 269	89.85 346

RPSCF		85.33 294	85.55 272	84.67 351	94.63 251	62.28 390	93.73 341	93.76 350	74.38 367	85.23 243	97.06 175	64.09 328	98.31 181	80.98 284	86.08 256	93.41 258

BH-w/o		92.32 165	91.79 163	93.91 204	96.85 154	86.18 246	99.11 108	95.74 283	88.13 201	84.81 244	97.00 179	77.26 236	97.91 204	89.16 200	98.03 117	97.64 198

mvsmamba		89.99 215	89.42 206	91.69 252	90.64 329	86.34 240	98.40 190	92.27 368	91.01 113	84.80 245	94.93 236	76.12 239	96.51 278	92.81 157	83.84 272	92.21 276

CLD-MVS		91.06 192	90.71 187	92.10 240	94.05 267	86.10 249	99.55 44	96.29 233	94.16 45	84.70 246	97.17 170	69.62 290	97.82 211	94.74 122	86.08 256	92.39 267
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tpmvs		89.16 225	87.76 238	93.35 213	97.19 140	84.75 280	90.58 376	97.36 156	81.99 323	84.56 247	89.31 349	83.98 156	98.17 189	74.85 329	90.00 237	97.12 213

nrg030		90.23 207	88.87 217	94.32 187	91.53 317	93.54 70	98.79 143	95.89 274	88.12 202	84.55 248	94.61 242	78.80 227	96.88 261	92.35 162	75.21 320	92.53 266

VPNet		88.30 246	86.57 256	93.49 211	91.95 309	91.35 111	98.18 212	97.20 171	88.61 181	84.52 249	94.89 237	62.21 337	96.76 267	89.34 195	72.26 352	92.36 268

dmvs_re		88.69 240	88.06 236	90.59 274	93.83 277	78.68 345	95.75 320	96.18 241	87.99 207	84.48 250	96.32 207	67.52 306	96.94 259	84.98 243	85.49 260	96.14 240

MVS		93.92 122	92.28 151	98.83 7	95.69 204	96.82 8	96.22 304	98.17 37	84.89 272	84.34 251	98.61 103	79.32 221	99.83 73	93.88 136	99.43 61	99.86 29

bld_raw_dy_0_64		91.25 187	90.03 196	94.92 163	95.99 193	92.32 95	91.40 366	95.74 283	70.34 379	84.15 252	94.47 243	85.61 130	98.17 189	94.42 129	98.14 115	94.26 252

mvs_anonymous		92.50 162	91.65 166	95.06 157	96.60 163	89.64 161	97.06 273	96.44 224	86.64 240	84.14 253	93.93 254	82.49 184	96.17 303	91.47 167	96.08 158	99.35 94

Fast-Effi-MVS+-dtu		88.84 232	88.59 226	89.58 304	93.44 287	78.18 349	98.65 156	94.62 334	88.46 186	84.12 254	95.37 231	68.91 292	96.52 277	82.06 278	91.70 213	94.06 253

LS3D		90.19 209	88.72 221	94.59 178	98.97 73	86.33 241	96.90 279	96.60 210	74.96 364	84.06 255	98.74 88	75.78 241	99.83 73	74.93 327	97.57 126	97.62 201

ACMM	86.95 13	88.77 237	88.22 233	90.43 280	93.61 281	81.34 323	98.50 176	95.92 266	87.88 211	83.85 256	95.20 234	67.20 309	97.89 206	86.90 221	84.90 263	92.06 283
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
BH-untuned		91.46 181	90.84 183	93.33 214	96.51 168	84.83 279	98.84 135	95.50 298	86.44 248	83.50 257	96.70 195	75.49 243	97.77 215	86.78 223	97.81 120	97.40 205

FIs		90.70 199	89.87 199	93.18 216	92.29 301	91.12 117	98.17 214	98.25 32	89.11 168	83.44 258	94.82 239	82.26 191	96.17 303	87.76 211	82.76 283	92.25 272

UniMVSNet (Re)		89.50 223	88.32 231	93.03 218	92.21 303	90.96 125	98.90 131	98.39 27	89.13 167	83.22 259	92.03 288	81.69 198	96.34 294	86.79 222	72.53 348	91.81 287

UniMVSNet_NR-MVSNet		89.60 220	88.55 227	92.75 226	92.17 304	90.07 148	98.74 146	98.15 40	88.37 192	83.21 260	93.98 252	82.86 175	95.93 313	86.95 218	72.47 349	92.25 272

DU-MVS		88.83 234	87.51 242	92.79 224	91.46 318	90.07 148	98.71 147	97.62 109	88.87 177	83.21 260	93.68 260	74.63 245	95.93 313	86.95 218	72.47 349	92.36 268

LPG-MVS_test		88.86 231	88.47 229	90.06 289	93.35 289	80.95 330	98.22 208	95.94 260	87.73 217	83.17 262	96.11 213	66.28 317	97.77 215	90.19 183	85.19 261	91.46 300

LGP-MVS_train				90.06 289	93.35 289	80.95 330		95.94 260	87.73 217	83.17 262	96.11 213	66.28 317	97.77 215	90.19 183	85.19 261	91.46 300

miper_enhance_ethall		90.33 205	89.70 200	92.22 235	97.12 146	88.93 181	98.35 197	95.96 257	88.60 182	83.14 264	92.33 285	87.38 88	96.18 302	86.49 225	77.89 305	91.55 297

FC-MVSNet-test		90.22 208	89.40 207	92.67 230	91.78 313	89.86 157	97.89 233	98.22 35	88.81 178	82.96 265	94.66 241	81.90 197	95.96 311	85.89 234	82.52 286	92.20 278

PCF-MVS	89.78 5	91.26 185	89.63 201	96.16 116	95.44 212	91.58 109	95.29 326	96.10 246	85.07 267	82.75 266	97.45 154	78.28 230	99.78 84	80.60 290	95.65 165	97.12 213
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
V42		87.00 265	85.68 270	90.98 264	89.91 335	86.08 250	98.32 200	95.61 292	83.67 291	82.72 267	90.67 319	74.00 256	96.53 276	81.94 280	74.28 332	90.32 335

v1144		86.83 268	85.31 276	91.40 255	89.75 339	87.21 225	98.31 201	95.45 301	83.22 297	82.70 268	90.78 314	73.36 258	96.36 288	79.49 295	74.69 326	90.63 330

Syy-MVS		84.10 313	84.53 291	82.83 360	95.14 227	65.71 387	97.68 249	96.66 206	86.52 244	82.63 269	96.84 189	68.15 299	89.89 383	45.62 398	91.54 217	92.87 260

myMVS_eth3d		88.68 242	89.07 213	87.50 330	95.14 227	79.74 336	97.68 249	96.66 206	86.52 244	82.63 269	96.84 189	85.22 142	89.89 383	69.43 356	91.54 217	92.87 260

v144192		86.40 277	84.89 282	90.91 265	89.48 345	85.59 263	98.21 210	95.43 304	82.45 316	82.62 271	90.58 326	72.79 267	96.36 288	78.45 305	74.04 336	90.79 322

3Dnovator	87.35 11	93.17 149	91.77 164	97.37 52	95.41 214	93.07 79	98.82 136	97.85 60	91.53 101	82.56 272	97.58 148	71.97 273	99.82 76	91.01 172	99.23 72	99.22 107

v2v482		87.27 263	85.76 268	91.78 251	89.59 341	87.58 209	98.56 170	95.54 296	84.53 276	82.51 273	91.78 296	73.11 263	96.47 282	82.07 277	74.14 335	91.30 308

tt0805		86.50 276	84.79 285	91.63 253	91.97 307	81.49 319	96.49 293	97.38 154	82.24 319	82.44 274	95.82 222	51.22 374	98.25 186	84.55 249	80.96 292	95.13 248

Baseline_NR-MVSNet		85.83 286	84.82 284	88.87 319	88.73 353	83.34 298	98.63 160	91.66 377	80.41 341	82.44 274	91.35 304	74.63 245	95.42 331	84.13 255	71.39 358	87.84 364

v1192		86.32 279	84.71 287	91.17 259	89.53 344	86.40 236	98.13 216	95.44 303	82.52 314	82.42 276	90.62 323	71.58 279	96.33 295	77.23 310	74.88 323	90.79 322

test_djsdf		88.26 248	87.73 239	89.84 296	88.05 361	82.21 313	97.77 242	96.17 242	86.84 235	82.41 277	91.95 294	72.07 272	95.99 309	89.83 185	84.50 266	91.32 307

cl22		89.57 221	88.79 220	91.91 243	97.94 105	87.62 208	97.98 230	96.51 219	85.03 268	82.37 278	91.79 295	83.65 158	96.50 279	85.96 231	77.89 305	91.61 294

1314		93.44 137	91.98 159	97.84 34	95.24 218	94.38 54	96.22 304	97.92 55	90.18 136	82.28 279	97.71 141	77.63 234	99.80 81	91.94 165	98.67 100	99.34 96

v1921920		86.02 282	84.44 293	90.77 271	89.32 347	85.20 271	98.10 221	95.35 309	82.19 320	82.25 280	90.71 316	70.73 282	96.30 299	76.85 315	74.49 328	90.80 321

v1240		85.77 289	84.11 296	90.73 272	89.26 348	85.15 274	97.88 235	95.23 318	81.89 326	82.16 281	90.55 328	69.60 291	96.31 296	75.59 324	74.87 324	90.72 327

XVG-ACMP-BASELINE		85.86 285	84.95 281	88.57 320	89.90 336	77.12 355	94.30 335	95.60 293	87.40 225	82.12 282	92.99 278	53.42 369	97.66 225	85.02 242	83.83 273	90.92 318

GBi-Net		86.67 271	84.96 279	91.80 247	95.11 230	88.81 184	96.77 283	95.25 311	82.94 305	82.12 282	90.25 334	62.89 334	94.97 339	79.04 298	80.24 293	91.62 291

test1		86.67 271	84.96 279	91.80 247	95.11 230	88.81 184	96.77 283	95.25 311	82.94 305	82.12 282	90.25 334	62.89 334	94.97 339	79.04 298	80.24 293	91.62 291

FMVSNet3		88.81 236	87.08 250	93.99 202	96.52 167	94.59 49	98.08 225	96.20 237	85.85 253	82.12 282	91.60 299	74.05 255	95.40 332	79.04 298	80.24 293	91.99 285

IterMVS-LS		88.34 245	87.44 243	91.04 262	94.10 263	85.85 259	98.10 221	95.48 299	85.12 264	82.03 286	91.21 307	81.35 205	95.63 325	83.86 261	75.73 317	91.63 290
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		88.94 229	88.12 235	91.40 255	95.32 217	86.93 227	97.85 237	95.55 295	84.19 280	81.97 287	91.50 301	84.16 153	95.91 316	84.69 246	77.89 305	91.36 305

MIMVSNet		84.48 305	81.83 316	92.42 233	91.73 314	87.36 217	85.52 385	94.42 340	81.40 329	81.91 288	87.58 356	51.92 372	92.81 364	73.84 337	88.15 242	97.08 217

PS-MVSNAJss		89.54 222	89.05 214	91.00 263	88.77 352	84.36 284	97.39 257	95.97 255	88.47 184	81.88 289	93.80 258	82.48 185	96.50 279	89.34 195	83.34 280	92.15 279

WR-MVS		88.54 244	87.22 249	92.52 231	91.93 311	89.50 164	98.56 170	97.84 61	86.99 229	81.87 290	93.81 257	74.25 254	95.92 315	85.29 238	74.43 329	92.12 280

TranMVSNet+NR-MVSNet		87.75 254	86.31 260	92.07 241	90.81 326	88.56 189	98.33 198	97.18 172	87.76 214	81.87 290	93.90 255	72.45 268	95.43 330	83.13 268	71.30 359	92.23 274

eth_miper_zixun_eth		87.76 253	87.00 252	90.06 289	94.67 249	82.65 310	97.02 276	95.37 307	84.19 280	81.86 292	91.58 300	81.47 202	95.90 317	83.24 264	73.61 338	91.61 294

UniMVSNet_ETH3D		85.65 292	83.79 300	91.21 258	90.41 332	80.75 332	95.36 325	95.78 280	78.76 347	81.83 293	94.33 245	49.86 379	96.66 269	84.30 251	83.52 278	96.22 239

c3_l		88.19 249	87.23 248	91.06 261	94.97 239	86.17 247	97.72 246	95.38 306	83.43 294	81.68 294	91.37 303	82.81 176	95.72 322	84.04 259	73.70 337	91.29 309

DP-MVS		88.75 238	86.56 257	95.34 146	98.92 77	87.45 214	97.64 252	93.52 356	70.55 377	81.49 295	97.25 163	74.43 250	99.88 54	71.14 350	94.09 178	98.67 156

3Dnovator+	87.72 8	93.43 138	91.84 162	98.17 23	95.73 203	95.08 34	98.92 129	97.04 186	91.42 106	81.48 296	97.60 146	74.60 247	99.79 82	90.84 175	98.97 84	99.64 64

QAPM		91.41 182	89.49 204	97.17 59	95.66 206	93.42 73	98.60 165	97.51 133	80.92 336	81.39 297	97.41 156	72.89 266	99.87 58	82.33 275	98.68 99	98.21 183

testing3		87.75 254	88.22 233	86.36 338	94.66 250	77.41 354	99.52 50	97.95 54	86.05 251	81.12 298	96.69 196	86.18 122	89.31 387	61.65 381	90.12 236	92.35 271

XXY-MVS		87.75 254	86.02 264	92.95 222	90.46 331	89.70 160	97.71 248	95.90 272	84.02 282	80.95 299	94.05 246	67.51 307	97.10 253	85.16 239	78.41 302	92.04 284

v148		86.38 278	85.06 278	90.37 284	89.47 346	84.10 288	98.52 172	95.48 299	83.80 287	80.93 300	90.22 337	74.60 247	96.31 296	80.92 286	71.55 357	90.69 328

DIV-MVS_self_test		87.82 251	86.81 254	90.87 268	94.87 244	85.39 268	97.81 238	95.22 319	82.92 308	80.76 301	91.31 305	81.99 194	95.81 320	81.36 282	75.04 322	91.42 303

cl____		87.82 251	86.79 255	90.89 267	94.88 243	85.43 266	97.81 238	95.24 314	82.91 309	80.71 302	91.22 306	81.97 196	95.84 318	81.34 283	75.06 321	91.40 304

FMVSNet2		86.90 266	84.79 285	93.24 215	95.11 230	92.54 93	97.67 251	95.86 278	82.94 305	80.55 303	91.17 308	62.89 334	95.29 334	77.23 310	79.71 299	91.90 286

pmmvs4		87.58 260	86.17 263	91.80 247	89.58 342	88.92 182	97.25 265	95.28 310	82.54 313	80.49 304	93.17 274	75.62 242	96.05 308	82.75 271	78.90 300	90.42 333

ACMP	87.39 10	88.71 239	88.24 232	90.12 288	93.91 273	81.06 329	98.50 176	95.67 289	89.43 161	80.37 305	95.55 226	65.67 319	97.83 210	90.55 180	84.51 265	91.47 299
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
pmmvs5		85.87 284	84.40 295	90.30 285	88.53 356	84.23 285	98.60 165	93.71 352	81.53 328	80.29 306	92.02 289	64.51 327	95.52 327	82.04 279	78.34 303	91.15 312

test0.0.03 1		88.96 228	88.61 224	90.03 293	91.09 323	84.43 283	98.97 125	97.02 190	90.21 134	80.29 306	96.31 208	84.89 145	91.93 376	72.98 343	85.70 259	93.73 254

miper_lstm_enhance		86.90 266	86.20 262	89.00 316	94.53 252	81.19 326	96.74 287	95.24 314	82.33 318	80.15 308	90.51 330	81.99 194	94.68 348	80.71 288	73.58 339	91.12 313

jajsoiax		87.35 261	86.51 258	89.87 294	87.75 366	81.74 317	97.03 274	95.98 254	88.47 184	80.15 308	93.80 258	61.47 339	96.36 288	89.44 193	84.47 267	91.50 298

mvs_tets		87.09 264	86.22 261	89.71 300	87.87 362	81.39 322	96.73 288	95.90 272	88.19 200	79.99 310	93.61 263	59.96 346	96.31 296	89.40 194	84.34 268	91.43 302

ITE_SJBPF				87.93 324	92.26 302	76.44 357		93.47 357	87.67 220	79.95 311	95.49 229	56.50 356	97.38 243	75.24 325	82.33 287	89.98 344

v8		86.11 281	84.45 292	91.10 260	89.99 334	86.85 228	97.24 266	95.36 308	81.99 323	79.89 312	89.86 342	74.53 249	96.39 286	78.83 302	72.32 351	90.05 342

v10		85.73 290	84.01 298	90.87 268	90.03 333	86.73 230	97.20 269	95.22 319	81.25 331	79.85 313	89.75 343	73.30 261	96.28 300	76.87 314	72.64 347	89.61 350

WR-MVS_H		86.53 275	85.49 273	89.66 303	91.04 324	83.31 299	97.53 255	98.20 36	84.95 271	79.64 314	90.90 312	78.01 232	95.33 333	76.29 319	72.81 345	90.35 334

anonymousdsp		86.69 270	85.75 269	89.53 305	86.46 374	82.94 302	96.39 295	95.71 285	83.97 284	79.63 315	90.70 317	68.85 293	95.94 312	86.01 229	84.02 271	89.72 348

Patchmtry		83.61 317	81.64 317	89.50 306	93.36 288	82.84 307	84.10 392	94.20 345	69.47 384	79.57 316	86.88 366	84.43 150	94.78 345	68.48 360	74.30 331	90.88 319

CP-MVSNet		86.54 274	85.45 274	89.79 298	91.02 325	82.78 308	97.38 259	97.56 122	85.37 261	79.53 317	93.03 276	71.86 275	95.25 335	79.92 293	73.43 343	91.34 306

Patchmatch-test		86.25 280	84.06 297	92.82 223	94.42 253	82.88 306	82.88 396	94.23 344	71.58 373	79.39 318	90.62 323	89.00 64	96.42 285	63.03 377	91.37 225	99.16 110

DSMNet-mixed		81.60 326	81.43 320	82.10 363	84.36 380	60.79 391	93.63 343	86.74 396	79.00 343	79.32 319	87.15 364	63.87 330	89.78 385	66.89 366	91.92 207	95.73 244

MSDG		88.29 247	86.37 259	94.04 200	96.90 153	86.15 248	96.52 292	94.36 342	77.89 353	79.22 320	96.95 181	69.72 288	99.59 104	73.20 342	92.58 195	96.37 238

Anonymous20231211		84.72 300	82.65 312	90.91 265	97.71 111	84.55 282	97.28 263	96.67 205	66.88 391	79.18 321	90.87 313	58.47 350	96.60 271	82.61 273	74.20 333	91.59 296

PS-CasMVS		85.81 287	84.58 290	89.49 308	90.77 327	82.11 314	97.20 269	97.36 156	84.83 273	79.12 322	92.84 279	67.42 308	95.16 337	78.39 306	73.25 344	91.21 311

IterMVS		85.81 287	84.67 288	89.22 311	93.51 283	83.67 294	96.32 298	94.80 328	85.09 266	78.69 323	90.17 340	66.57 315	93.17 361	79.48 296	77.42 311	90.81 320
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PEN-MVS		85.21 295	83.93 299	89.07 315	89.89 337	81.31 324	97.09 272	97.24 164	84.45 278	78.66 324	92.68 282	68.44 297	94.87 342	75.98 321	70.92 360	91.04 315

IterMVS-SCA-FT		85.73 290	84.64 289	89.00 316	93.46 286	82.90 304	96.27 299	94.70 331	85.02 269	78.62 325	90.35 332	66.61 313	93.33 358	79.38 297	77.36 312	90.76 324

OpenMVS	85.28 14	90.75 198	88.84 218	96.48 97	93.58 282	93.51 71	98.80 139	97.41 151	82.59 311	78.62 325	97.49 152	68.00 302	99.82 76	84.52 250	98.55 105	96.11 241

PVSNet_0	83.28 16	87.31 262	85.16 277	93.74 209	94.78 246	84.59 281	98.91 130	98.69 21	89.81 148	78.59 327	93.23 272	61.95 338	99.34 134	94.75 121	55.72 393	97.30 208

EU-MVSNet		84.19 310	84.42 294	83.52 358	88.64 355	67.37 386	96.04 309	95.76 282	85.29 262	78.44 328	93.18 273	70.67 283	91.48 378	75.79 323	75.98 315	91.70 288

v7n		84.42 307	82.75 310	89.43 309	88.15 359	81.86 316	96.75 286	95.67 289	80.53 337	78.38 329	89.43 347	69.89 286	96.35 293	73.83 338	72.13 353	90.07 340

FMVSNet1		83.94 314	81.32 322	91.80 247	91.94 310	88.81 184	96.77 283	95.25 311	77.98 349	78.25 330	90.25 334	50.37 378	94.97 339	73.27 341	77.81 309	91.62 291

D2MVS		87.96 250	87.39 244	89.70 301	91.84 312	83.40 297	98.31 201	98.49 23	88.04 205	78.23 331	90.26 333	73.57 257	96.79 266	84.21 253	83.53 277	88.90 358

MS-PatchMatch		86.75 269	85.92 266	89.22 311	91.97 307	82.47 312	96.91 278	96.14 244	83.74 288	77.73 332	93.53 266	58.19 351	97.37 245	76.75 316	98.35 110	87.84 364

DTE-MVSNet		84.14 311	82.80 307	88.14 323	88.95 351	79.87 335	96.81 282	96.24 235	83.50 293	77.60 333	92.52 284	67.89 304	94.24 353	72.64 346	69.05 364	90.32 335

COLMAP_ROB	82.69 18	84.54 304	82.82 306	89.70 301	96.72 161	78.85 342	95.89 312	92.83 362	71.55 374	77.54 334	95.89 221	59.40 348	99.14 145	67.26 364	88.26 241	91.11 314
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		84.13 312	83.59 301	85.77 343	87.81 363	70.24 380	94.89 330	93.65 354	86.08 250	76.53 335	93.28 271	61.41 340	96.14 305	80.95 285	77.69 310	90.93 317

tfpnnormal		83.65 315	81.35 321	90.56 277	91.37 320	88.06 198	97.29 262	97.87 58	78.51 348	76.20 336	90.91 311	64.78 326	96.47 282	61.71 380	73.50 340	87.13 373

ppachtmachnet_test		83.63 316	81.57 319	89.80 297	89.01 349	85.09 275	97.13 271	94.50 336	78.84 345	76.14 337	91.00 310	69.78 287	94.61 349	63.40 375	74.36 330	89.71 349

pm-mvs1		84.68 301	82.78 309	90.40 281	89.58 342	85.18 272	97.31 261	94.73 330	81.93 325	76.05 338	92.01 290	65.48 323	96.11 306	78.75 303	69.14 363	89.91 345

AllTest		84.97 298	83.12 304	90.52 278	96.82 155	78.84 343	95.89 312	92.17 370	77.96 351	75.94 339	95.50 227	55.48 359	99.18 139	71.15 348	87.14 245	93.55 256

TestCases				90.52 278	96.82 155	78.84 343		92.17 370	77.96 351	75.94 339	95.50 227	55.48 359	99.18 139	71.15 348	87.14 245	93.55 256

CL-MVSNet_self_test		79.89 335	78.34 336	84.54 352	81.56 388	75.01 361	96.88 280	95.62 291	81.10 332	75.86 341	85.81 371	68.49 296	90.26 381	63.21 376	56.51 391	88.35 361

testgi		82.29 321	81.00 324	86.17 340	87.24 369	74.84 363	97.39 257	91.62 378	88.63 180	75.85 342	95.42 230	46.07 385	91.55 377	66.87 367	79.94 297	92.12 280

MVP-Stereo		86.61 273	85.83 267	88.93 318	88.70 354	83.85 292	96.07 308	94.41 341	82.15 321	75.64 343	91.96 293	67.65 305	96.45 284	77.20 312	98.72 98	86.51 376
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LF4IMVS		81.94 324	81.17 323	84.25 353	87.23 370	68.87 385	93.35 345	91.93 375	83.35 296	75.40 344	93.00 277	49.25 382	96.65 270	78.88 301	78.11 304	87.22 372

our_test_3		84.47 306	82.80 307	89.50 306	89.01 349	83.90 291	97.03 274	94.56 335	81.33 330	75.36 345	90.52 329	71.69 277	94.54 350	68.81 358	76.84 313	90.07 340

LTVRE_ROB	81.71 19	84.59 303	82.72 311	90.18 286	92.89 296	83.18 300	93.15 346	94.74 329	78.99 344	75.14 346	92.69 281	65.64 320	97.63 228	69.46 355	81.82 289	89.74 347
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
Anonymous20231206		80.76 330	79.42 334	84.79 350	84.78 379	72.98 370	96.53 291	92.97 360	79.56 342	74.33 347	88.83 350	61.27 341	92.15 373	60.59 383	75.92 316	89.24 355

FMVSNet5		82.29 321	80.54 326	87.52 329	93.79 279	84.01 289	93.73 341	92.47 366	76.92 356	74.27 348	86.15 370	63.69 332	89.24 388	69.07 357	74.79 325	89.29 354

MVS-HIRNet		79.01 338	75.13 350	90.66 273	93.82 278	81.69 318	85.16 386	93.75 351	54.54 396	74.17 349	59.15 402	57.46 353	96.58 273	63.74 374	94.38 175	93.72 255

ACMH+	83.78 15	84.21 309	82.56 314	89.15 313	93.73 280	79.16 340	96.43 294	94.28 343	81.09 333	74.00 350	94.03 249	54.58 365	97.67 224	76.10 320	78.81 301	90.63 330

kuosan		84.40 308	83.34 302	87.60 328	95.87 197	79.21 339	92.39 355	96.87 197	76.12 360	73.79 351	93.98 252	81.51 200	90.63 379	64.13 373	75.42 318	92.95 259

KD-MVS_2432*1600		82.98 318	80.52 327	90.38 282	94.32 257	88.98 176	92.87 350	95.87 276	80.46 339	73.79 351	87.49 359	82.76 179	93.29 359	70.56 352	46.53 402	88.87 359

miper_refine_blended		82.98 318	80.52 327	90.38 282	94.32 257	88.98 176	92.87 350	95.87 276	80.46 339	73.79 351	87.49 359	82.76 179	93.29 359	70.56 352	46.53 402	88.87 359

NR-MVSNet		87.74 257	86.00 265	92.96 221	91.46 318	90.68 132	96.65 290	97.42 150	88.02 206	73.42 354	93.68 260	77.31 235	95.83 319	84.26 252	71.82 356	92.36 268

test_fmvs3		75.09 352	75.19 349	74.81 373	77.45 396	54.08 399	95.93 310	90.64 384	82.51 315	73.29 355	81.19 384	22.29 402	86.29 395	85.50 237	67.89 368	84.06 386

USDC		84.74 299	82.93 305	90.16 287	91.73 314	83.54 296	95.00 329	93.30 358	88.77 179	73.19 356	93.30 270	53.62 368	97.65 227	75.88 322	81.54 290	89.30 353

KD-MVS_self_test		77.47 347	75.88 347	82.24 361	81.59 387	68.93 384	92.83 352	94.02 348	77.03 355	73.14 357	83.39 376	55.44 361	90.42 380	67.95 361	57.53 390	87.38 368

LCM-MVSNet-Re		88.59 243	88.61 224	88.51 321	95.53 210	72.68 373	96.85 281	88.43 393	88.45 187	73.14 357	90.63 322	75.82 240	94.38 351	92.95 153	95.71 164	98.48 165

TDRefinement		78.01 344	75.31 348	86.10 341	70.06 403	73.84 366	93.59 344	91.58 379	74.51 366	73.08 359	91.04 309	49.63 381	97.12 250	74.88 328	59.47 386	87.33 370

TransMVSNet (Re)		81.97 323	79.61 333	89.08 314	89.70 340	84.01 289	97.26 264	91.85 376	78.84 345	73.07 360	91.62 298	67.17 310	95.21 336	67.50 363	59.46 387	88.02 363

SixPastTwentyTwo		82.63 320	81.58 318	85.79 342	88.12 360	71.01 378	95.17 327	92.54 365	84.33 279	72.93 361	92.08 287	60.41 345	95.61 326	74.47 331	74.15 334	90.75 325

pmmvs6		79.90 334	77.31 340	87.67 327	84.17 381	78.13 350	95.86 316	93.68 353	67.94 388	72.67 362	89.62 345	50.98 376	95.75 321	74.80 330	66.04 374	89.14 356

ACMH	83.09 17	84.60 302	82.61 313	90.57 275	93.18 292	82.94 302	96.27 299	94.92 324	81.01 334	72.61 363	93.61 263	56.54 355	97.79 213	74.31 332	81.07 291	90.99 316
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		78.63 342	76.90 343	83.82 355	82.82 385	72.86 371	95.72 321	93.57 355	73.55 371	72.17 364	84.79 373	49.69 380	92.51 369	65.29 371	74.50 327	86.09 378

Patchmatch-RL test		81.90 325	80.13 329	87.23 333	80.71 390	70.12 382	84.07 393	88.19 394	83.16 299	70.57 365	82.18 381	87.18 95	92.59 367	82.28 276	62.78 380	98.98 125

mvsany_test3		75.85 351	74.52 353	79.83 368	73.53 400	60.64 392	91.73 361	87.87 395	83.91 286	70.55 366	82.52 378	31.12 397	93.66 355	86.66 224	62.83 379	85.19 384

test_0402		78.81 340	76.33 345	86.26 339	91.18 322	78.44 348	95.88 314	91.34 381	68.55 385	70.51 367	89.91 341	52.65 371	94.99 338	47.14 397	79.78 298	85.34 382

dongtai		81.36 327	80.61 325	83.62 357	94.25 262	73.32 369	95.15 328	96.81 199	73.56 370	69.79 368	92.81 280	81.00 208	86.80 394	52.08 395	70.06 362	90.75 325

TinyColmap		80.42 332	77.94 337	87.85 325	92.09 305	78.58 346	93.74 340	89.94 387	74.99 363	69.77 369	91.78 296	46.09 384	97.58 232	65.17 372	77.89 305	87.38 368

dmvs_testset		77.17 348	78.99 335	71.71 376	87.25 368	38.55 413	91.44 365	81.76 404	85.77 255	69.49 370	95.94 220	69.71 289	84.37 396	52.71 394	76.82 314	92.21 276

test20.03		78.51 343	77.48 339	81.62 365	83.07 384	71.03 377	96.11 307	92.83 362	81.66 327	69.31 371	89.68 344	57.53 352	87.29 393	58.65 387	68.47 365	86.53 375

test_vis1_rt		81.31 328	80.05 331	85.11 345	91.29 321	70.66 379	98.98 124	77.39 408	85.76 256	68.80 372	82.40 379	36.56 395	99.44 119	92.67 159	86.55 250	85.24 383

N_pmnet		70.19 358	69.87 360	71.12 378	88.24 358	30.63 417	95.85 317	28.70 416	70.18 380	68.73 373	86.55 368	64.04 329	93.81 354	53.12 393	73.46 341	88.94 357

OpenMVS_ROB	73.86 20	77.99 345	75.06 351	86.77 336	83.81 383	77.94 352	96.38 296	91.53 380	67.54 389	68.38 374	87.13 365	43.94 386	96.08 307	55.03 391	81.83 288	86.29 377

ambc				79.60 369	72.76 402	56.61 396	76.20 400	92.01 374		68.25 375	80.23 388	23.34 401	94.73 346	73.78 339	60.81 384	87.48 367

PM-MVS		74.88 353	72.85 356	80.98 367	78.98 394	64.75 389	90.81 373	85.77 397	80.95 335	68.23 376	82.81 377	29.08 399	92.84 363	76.54 318	62.46 382	85.36 381

pmmvs3		72.86 356	69.76 361	82.17 362	73.86 399	74.19 365	94.20 336	89.01 392	64.23 395	67.72 377	80.91 387	41.48 390	88.65 390	62.40 378	54.02 395	83.68 388

lessismore_v0				85.08 346	85.59 377	69.28 383		90.56 385		67.68 378	90.21 338	54.21 367	95.46 329	73.88 336	62.64 381	90.50 332

K. test v3		81.04 329	79.77 332	84.83 349	87.41 367	70.23 381	95.60 324	93.93 349	83.70 290	67.51 379	89.35 348	55.76 357	93.58 357	76.67 317	68.03 367	90.67 329

MIMVSNet1		75.92 350	73.30 355	83.81 356	81.29 389	75.57 359	92.26 356	92.05 373	73.09 372	67.48 380	86.18 369	40.87 392	87.64 392	55.78 390	70.68 361	88.21 362

ET-MVSNet_ETH3D		92.56 161	91.45 170	95.88 127	96.39 174	94.13 60	99.46 59	96.97 194	92.18 90	66.94 381	98.29 122	94.65 13	94.28 352	94.34 130	83.82 275	99.24 104

pmmvs-eth3d		78.71 341	76.16 346	86.38 337	80.25 392	81.19 326	94.17 337	92.13 372	77.97 350	66.90 382	82.31 380	55.76 357	92.56 368	73.63 340	62.31 383	85.38 380

EG-PatchMatch MVS		79.92 333	77.59 338	86.90 335	87.06 371	77.90 353	96.20 306	94.06 347	74.61 365	66.53 383	88.76 351	40.40 393	96.20 301	67.02 365	83.66 276	86.61 374

test_method		70.10 359	68.66 362	74.41 375	86.30 376	55.84 397	94.47 332	89.82 388	35.18 404	66.15 384	84.75 374	30.54 398	77.96 405	70.40 354	60.33 385	89.44 352

UnsupCasMVSNet_eth		78.90 339	76.67 344	85.58 344	82.81 386	74.94 362	91.98 358	96.31 229	84.64 275	65.84 385	87.71 355	51.33 373	92.23 372	72.89 344	56.50 392	89.56 351

test_f		71.94 357	70.82 358	75.30 372	72.77 401	53.28 400	91.62 362	89.66 390	75.44 362	64.47 386	78.31 392	20.48 403	89.56 386	78.63 304	66.02 375	83.05 391

new-patchmatchnet		74.80 354	72.40 357	81.99 364	78.36 395	72.20 374	94.44 333	92.36 367	77.06 354	63.47 387	79.98 389	51.04 375	88.85 389	60.53 384	54.35 394	84.92 385

new_pmnet		76.02 349	73.71 354	82.95 359	83.88 382	72.85 372	91.26 369	92.26 369	70.44 378	62.60 388	81.37 383	47.64 383	92.32 371	61.85 379	72.10 354	83.68 388

UnsupCasMVSNet_bld		73.85 355	70.14 359	84.99 347	79.44 393	75.73 358	88.53 379	95.24 314	70.12 381	61.94 389	74.81 395	41.41 391	93.62 356	68.65 359	51.13 399	85.62 379

CMPMVS	58.40 21	80.48 331	80.11 330	81.59 366	85.10 378	59.56 393	94.14 338	95.95 259	68.54 386	60.71 390	93.31 269	55.35 362	97.87 208	83.06 269	84.85 264	87.33 370
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
APD_test1		68.93 360	66.98 363	74.77 374	80.62 391	53.15 401	87.97 380	85.01 399	53.76 397	59.26 391	87.52 358	25.19 400	89.95 382	56.20 389	67.33 371	81.19 392

DeepMVS_CX				76.08 371	90.74 328	51.65 404		90.84 383	86.47 247	57.89 392	87.98 353	35.88 396	92.60 366	65.77 370	65.06 377	83.97 387

WB-MVS		66.44 361	66.29 364	66.89 381	74.84 397	44.93 408	93.00 347	84.09 402	71.15 375	55.82 393	81.63 382	63.79 331	80.31 403	21.85 407	50.47 400	75.43 394

SSC-MVS		65.42 362	65.20 365	66.06 382	73.96 398	43.83 409	92.08 357	83.54 403	69.77 382	54.73 394	80.92 386	63.30 333	79.92 404	20.48 408	48.02 401	74.44 395

YYNet1		79.64 337	77.04 342	87.43 332	87.80 364	79.98 334	96.23 303	94.44 337	73.83 369	51.83 395	87.53 357	67.96 303	92.07 375	66.00 369	67.75 370	90.23 337

MDA-MVSNet_test_wron		79.65 336	77.05 341	87.45 331	87.79 365	80.13 333	96.25 302	94.44 337	73.87 368	51.80 396	87.47 361	68.04 301	92.12 374	66.02 368	67.79 369	90.09 338

LCM-MVSNet		60.07 366	56.37 368	71.18 377	54.81 412	48.67 405	82.17 397	89.48 391	37.95 402	49.13 397	69.12 396	13.75 410	81.76 397	59.28 385	51.63 398	83.10 390

MDA-MVSNet-bldmvs		77.82 346	74.75 352	87.03 334	88.33 357	78.52 347	96.34 297	92.85 361	75.57 361	48.87 398	87.89 354	57.32 354	92.49 370	60.79 382	64.80 378	90.08 339

PMMVS2		58.97 367	55.07 370	70.69 379	62.72 407	55.37 398	85.97 384	80.52 405	49.48 398	45.94 399	68.31 397	15.73 408	80.78 401	49.79 396	37.12 404	75.91 393

testf1		56.38 368	53.73 371	64.31 385	64.84 405	45.11 406	80.50 398	75.94 410	38.87 400	42.74 400	75.07 393	11.26 412	81.19 399	41.11 400	53.27 396	66.63 399

APD_test2		56.38 368	53.73 371	64.31 385	64.84 405	45.11 406	80.50 398	75.94 410	38.87 400	42.74 400	75.07 393	11.26 412	81.19 399	41.11 400	53.27 396	66.63 399

FPMVS		61.57 363	60.32 366	65.34 383	60.14 410	42.44 411	91.02 372	89.72 389	44.15 399	42.63 402	80.93 385	19.02 404	80.59 402	42.50 399	72.76 346	73.00 396

test_vis3_rt		61.29 364	58.75 367	68.92 380	67.41 404	52.84 402	91.18 371	59.23 415	66.96 390	41.96 403	58.44 403	11.37 411	94.72 347	74.25 333	57.97 389	59.20 402

Gipuma		54.77 370	52.22 374	62.40 387	86.50 373	59.37 394	50.20 405	90.35 386	36.52 403	41.20 404	49.49 405	18.33 406	81.29 398	32.10 404	65.34 376	46.54 405
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		53.66 371	52.86 373	56.05 388	32.75 416	41.97 412	73.42 402	76.12 409	21.91 409	39.68 405	96.39 205	42.59 389	65.10 408	78.00 307	14.92 409	61.08 401

E-PMN		41.02 375	40.93 377	41.29 391	61.97 408	33.83 414	84.00 394	65.17 413	27.17 406	27.56 406	46.72 407	17.63 407	60.41 410	19.32 409	18.82 406	29.61 406

ANet_high		50.71 372	46.17 375	64.33 384	44.27 414	52.30 403	76.13 401	78.73 406	64.95 393	27.37 407	55.23 404	14.61 409	67.74 407	36.01 403	18.23 407	72.95 397

EMVS		39.96 376	39.88 378	40.18 392	59.57 411	32.12 416	84.79 391	64.57 414	26.27 407	26.14 408	44.18 410	18.73 405	59.29 411	17.03 410	17.67 408	29.12 407

MVE	44.00 22	41.70 374	37.64 379	53.90 390	49.46 413	43.37 410	65.09 404	66.66 412	26.19 408	25.77 409	48.53 406	3.58 416	63.35 409	26.15 406	27.28 405	54.97 404
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	41.42 23	45.67 373	42.50 376	55.17 389	34.28 415	32.37 415	66.24 403	78.71 407	30.72 405	22.04 410	59.59 401	4.59 414	77.85 406	27.49 405	58.84 388	55.29 403
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		18.81 378	23.05 381	6.10 395	4.48 417	2.29 420	97.78 240	3.00 418	3.27 411	18.60 411	62.71 399	1.53 418	2.49 414	14.26 412	1.80 411	13.50 409

test123		16.58 380	19.47 382	7.91 394	3.59 418	5.37 419	94.32 334	1.39 419	2.49 412	13.98 412	44.60 409	2.91 417	2.65 413	11.35 413	0.57 412	15.70 408

wuyk23d		16.71 379	16.73 383	16.65 393	60.15 409	25.22 418	41.24 406	5.17 417	6.56 410	5.48 413	3.61 413	3.64 415	22.72 412	15.20 411	9.52 410	1.99 410

EGC-MVSNET		60.70 365	55.37 369	76.72 370	86.35 375	71.08 376	89.96 377	84.44 401	0.38 413	1.50 414	84.09 375	37.30 394	88.10 391	40.85 402	73.44 342	70.97 398

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

cdsmvs_eth3d_5k		22.52 377	30.03 380	0.00 396	0.00 419	0.00 421	0.00 407	97.17 173	0.00 414	0.00 415	98.77 85	74.35 252	0.00 415	0.00 414	0.00 413	0.00 411

pcd_1.5k_mvsjas		6.87 382	9.16 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	82.48 185	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		8.21 381	10.94 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	98.50 108	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

WAC-MVS						79.74 336								67.75 362

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 88					99.98 9	99.55 12	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 88					99.98 9	99.55 12	99.83 15	99.96 10

eth-test2					0.00 419

eth-test					0.00 419

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 17				99.19 30	95.12 7	99.97 21	99.90 1	99.92 3	99.99 1

save fliter					99.34 50	93.85 65	99.65 35	97.63 107	95.69 22

test_0728_SECOND				98.77 8	99.66 12	96.37 14	99.72 23	97.68 90					99.98 9	99.64 7	99.82 19	99.96 10

GSMVS																98.84 140

sam_mvs1												88.39 70				98.84 140

sam_mvs												87.08 98

MTGPA								97.45 144

test_post1							90.74 375				41.37 411	85.38 139	96.36 288	83.16 266

test_post											46.00 408	87.37 89	97.11 251

patchmatchnet-post											84.86 372	88.73 67	96.81 264

MTMP							99.21 87	91.09 382

gm-plane-assit					94.69 248	88.14 196			88.22 199		97.20 166		98.29 183	90.79 177

test9_res														98.60 33	99.87 9	99.90 22

agg_prior2														97.84 56	99.87 9	99.91 21

test_prior4						92.00 100	99.41 68

test_prior				97.01 63	99.58 30	91.77 103		97.57 121					99.49 112			99.79 36

新几何2							98.26 204

旧先验1					98.97 73	92.90 87		97.74 77			99.15 39	91.05 33			99.33 66	99.60 69

无先验							98.52 172	97.82 65	87.20 227				99.90 50	87.64 213		99.85 30

原ACMM2							98.69 151

testdata2													99.88 54	84.16 254

segment_acmp												90.56 42

testdata1							97.89 233		92.43 82

plane_prior7					93.84 275	85.73 261

plane_prior6					93.92 272	86.02 254						72.92 264

plane_prior5								96.30 230					97.75 221	93.46 146	86.17 254	92.67 264

plane_prior4											96.52 199

plane_prior2							99.02 118		93.38 66

plane_prior1					93.90 274

plane_prior						86.07 252	99.14 103		93.81 58						86.26 253

n2								0.00 420

nn								0.00 420

door-mid								84.90 400

test11								97.68 90

door								85.30 398

HQP5-MVS						86.39 237

BP-MVS														93.82 139

HQP3-MVS								96.37 226							86.29 251

HQP2-MVS												73.34 259

NP-MVS					93.94 271	86.22 244					96.67 197

ACMMP++_ref															82.64 285

ACMMP++															83.83 273

Test By Simon												83.62 159

High-resolution multi-view benchmark