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 48	97.51 122	92.78 87	99.85 8	98.05 46	96.78 8	99.60 1	99.23 26	90.42 46	99.92 40	99.55 12	98.50 104	99.55 74

fmvsm_l_conf0.5_n_a		97.70 12	97.80 11	97.42 47	97.59 117	92.91 85	99.86 5	98.04 48	96.70 10	99.58 2	99.26 21	90.90 37	99.94 34	99.57 11	98.66 99	99.40 89

IU-MVS					99.63 18	95.38 24		97.73 80	95.54 28	99.54 3				99.69 6	99.81 23	99.99 1

PC_three_1452									94.60 38	99.41 4	99.12 48	95.50 7	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 16	97.99 52	97.05 6	99.41 4	99.59 2	92.89 24	100.00 1	98.99 25	99.90 7	99.96 10

patch_mono-2		97.10 26	97.97 8	94.49 177	99.21 61	83.73 292	99.62 38	98.25 32	95.28 32	99.38 6	98.91 77	92.28 27	99.94 34	99.61 9	99.22 71	99.78 38

test0726					99.66 12	95.20 32	99.77 18	97.70 86	93.95 50	99.35 7	99.54 3	93.18 21

iter_conf05_11		94.23 112	93.49 121	96.46 96	97.51 122	91.32 110	99.96 1	94.31 337	95.62 26	99.32 8	99.22 27	57.79 347	98.59 172	98.00 50	99.64 40	99.46 83

SED-MVS		98.18 2	98.10 4	98.41 18	99.63 18	95.24 27	99.77 18	97.72 81	94.17 45	99.30 9	99.54 3	93.32 18	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 47	99.30 9	99.49 9	93.32 18	99.98 9

DVP-MVS++		98.18 2	98.09 5	98.44 16	99.61 24	95.38 24	99.55 45	97.68 90	93.01 72	99.23 11	99.45 14	95.12 8	99.98 9	99.25 18	99.92 3	99.97 7

test_241102_TWO								97.72 81	94.17 45	99.23 11	99.54 3	93.14 23	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 57	99.16 97	97.65 102	89.55 160	99.22 13	99.52 8	90.34 49	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	95.31 147	96.51 167	89.01 174	99.81 12	98.39 27	95.46 30	99.19 14	99.16 38	81.44 199	99.91 45	98.83 28	96.97 137	97.01 218

test_fmvsm_n_1920		97.08 27	97.55 14	95.67 135	97.94 105	89.61 163	99.93 2	98.48 24	97.08 5	99.08 15	99.13 46	88.17 72	99.93 38	99.11 23	99.06 76	97.47 202

DVP-MVS		98.07 7	98.00 6	98.29 19	99.66 12	95.20 32	99.72 24	97.47 141	93.95 50	99.07 16	99.46 10	93.18 21	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 72	99.07 16	99.46 10	94.66 13	99.97 21	99.25 18	99.82 19	99.95 15

TSAR-MVS + MP.		97.44 18	97.46 16	97.39 50	99.12 65	93.49 71	98.52 175	97.50 136	94.46 40	98.99 18	98.64 101	91.58 29	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 82	95.15 77	95.18 152	92.06 302	88.94 178	99.29 82	97.53 127	94.46 40	98.98 19	98.99 62	79.99 207	99.85 67	98.24 47	96.86 139	96.73 223

PS-MVSNAJ		96.87 31	96.40 39	98.29 19	97.35 130	97.29 5	99.03 120	97.11 179	95.83 20	98.97 20	99.14 44	82.48 181	99.60 103	98.60 33	99.08 74	98.00 189

旧先验2							98.67 157		85.75 260	98.96 21			98.97 154	93.84 135

test_one_0601					99.59 28	94.89 36		97.64 103	93.14 71	98.93 22	99.45 14	93.45 17

fmvsm_s_conf0.5_n		96.19 49	96.49 36	95.30 148	97.37 129	89.16 168	99.86 5	98.47 25	95.68 23	98.87 23	99.15 41	82.44 185	99.92 40	99.14 21	97.43 128	96.83 222

xiu_mvs_v2_base		96.66 36	96.17 48	98.11 28	97.11 147	96.96 6	99.01 123	97.04 186	95.51 29	98.86 24	99.11 52	82.19 189	99.36 130	98.59 35	98.14 112	98.00 189

NCCC		98.12 5	98.11 3	98.13 25	99.76 6	94.46 50	99.81 12	97.88 57	96.54 13	98.84 25	99.46 10	92.55 26	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 65	99.33 79	97.38 154	93.73 61	98.83 26	99.02 60	90.87 39	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 63	97.45 144	89.60 156	98.70 27	99.42 17	90.42 46	99.72 89	98.47 38	99.65 38	99.77 43

fmvsm_s_conf0.1_n		95.56 72	95.68 65	95.20 151	94.35 252	89.10 170	99.50 52	97.67 94	94.76 36	98.68 28	99.03 58	81.13 202	99.86 63	98.63 32	97.36 130	96.63 225

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 23	99.29 82	97.72 81	94.50 39	98.64 29	99.54 3	93.32 18	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 94	99.54 36	90.14 144	99.41 69	97.70 86	95.46 30	98.60 30	99.19 32	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 52	97.49 138	89.41 164	98.59 31	99.43 16	89.78 55	99.69 91	98.69 30	99.62 45

APD-MVS		96.95 29	96.72 32	97.63 40	99.51 41	93.58 67	99.16 97	97.44 147	90.08 143	98.59 31	99.07 53	89.06 60	99.42 123	97.92 53	99.66 37	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_vis1_n_1920		93.08 150	93.42 123	92.04 241	96.31 176	79.36 338	99.83 10	96.06 248	96.72 9	98.53 33	98.10 131	58.57 344	99.91 45	97.86 55	98.79 95	96.85 221

testdata				95.26 150	98.20 96	87.28 219		97.60 112	85.21 266	98.48 34	99.15 41	88.15 74	98.72 164	90.29 181	99.45 58	99.78 38

test_fmvsmconf_n		96.78 34	96.84 29	96.61 87	95.99 192	90.25 139	99.90 3	98.13 42	96.68 11	98.42 35	98.92 76	85.34 136	99.88 54	99.12 22	99.08 74	99.70 52

TEST9					99.57 33	93.17 75	99.38 72	97.66 95	89.57 158	98.39 36	99.18 35	90.88 38	99.66 94

train_agg		97.20 23	97.08 23	97.57 44	99.57 33	93.17 75	99.38 72	97.66 95	90.18 138	98.39 36	99.18 35	90.94 35	99.66 94	98.58 36	99.85 13	99.88 26

test_8					99.55 35	93.07 78	99.37 75	97.64 103	90.18 138	98.36 38	99.19 32	90.94 35	99.64 100

CS-MVS-test		95.98 55	96.34 41	94.90 162	98.06 102	87.66 206	99.69 34	96.10 243	93.66 62	98.35 39	99.05 56	86.28 117	97.66 222	96.96 71	98.90 88	99.37 92

MM		97.76 10	97.39 19	98.86 5	98.30 93	96.83 7	99.81 12	99.13 9	97.66 2	98.29 40	98.96 68	85.84 126	99.90 50	99.72 3	98.80 92	99.85 30

HPM-MVS++		97.72 11	97.59 13	98.14 24	99.53 40	94.76 44	99.19 91	97.75 76	95.66 24	98.21 41	99.29 20	91.10 32	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 21	97.78 73	96.61 12	98.15 42	99.53 7	93.62 16	100.00 1	91.79 164	99.80 26	99.94 18

test_part2					99.54 36	95.42 22				98.13 43

SteuartSystems-ACMMP		97.25 19	97.34 20	97.01 62	97.38 128	91.46 108	99.75 22	97.66 95	94.14 49	98.13 43	99.26 21	92.16 28	99.66 94	97.91 54	99.64 40	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
FOURS1					99.50 42	88.94 178	99.55 45	97.47 141	91.32 111	98.12 45

test_prior2							99.57 43		91.43 108	98.12 45	98.97 64	90.43 45		98.33 42	99.81 23

CS-MVS		95.75 68	96.19 43	94.40 181	97.88 107	86.22 243	99.66 35	96.12 242	92.69 80	98.07 47	98.89 80	87.09 95	97.59 228	96.71 74	98.62 100	99.39 91

PHI-MVS		96.65 37	96.46 38	97.21 56	99.34 50	91.77 101	99.70 27	98.05 46	86.48 249	98.05 48	99.20 30	89.33 58	99.96 28	98.38 39	99.62 45	99.90 22

MVSFormer		94.71 100	94.08 101	96.61 87	95.05 233	94.87 38	97.77 244	96.17 239	86.84 238	98.04 49	98.52 108	85.52 128	95.99 308	89.83 184	98.97 82	98.96 127

lupinMVS		96.32 45	95.94 54	97.44 46	95.05 233	94.87 38	99.86 5	96.50 216	93.82 59	98.04 49	98.77 87	85.52 128	98.09 192	96.98 70	98.97 82	99.37 92

APDe-MVS		97.53 14	97.47 15	97.70 38	99.58 30	93.63 66	99.56 44	97.52 131	93.59 65	98.01 51	99.12 48	90.80 40	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 68	98.88 135	97.59 116	90.66 122	97.98 52	99.14 44	86.59 109	100.00 1	96.47 83	99.46 56	99.89 25

agg_prior					99.54 36	92.66 88		97.64 103		97.98 52			99.61 102

CDPH-MVS		96.56 39	96.18 45	97.70 38	99.59 28	93.92 62	99.13 109	97.44 147	89.02 173	97.90 54	99.22 27	88.90 63	99.49 112	94.63 124	99.79 27	99.68 56

EPNet		96.82 32	96.68 34	97.25 55	98.65 86	93.10 77	99.48 54	98.76 15	96.54 13	97.84 55	98.22 126	87.49 84	99.66 94	95.35 105	97.78 119	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 74	99.70 27	98.13 42	94.61 37	97.78 56	99.46 10	89.85 54	99.81 79	97.97 52	99.91 6	99.88 26

test12				97.83 35	99.33 53	94.45 51		97.55 123		97.56 57		88.60 66	99.50 111		99.71 34	99.55 74

xiu_mvs_v1_base_debu		94.73 97	93.98 104	96.99 64	95.19 219	95.24 27	98.62 164	96.50 216	92.99 74	97.52 58	98.83 84	72.37 264	99.15 141	97.03 67	96.74 140	96.58 228

xiu_mvs_v1_base		94.73 97	93.98 104	96.99 64	95.19 219	95.24 27	98.62 164	96.50 216	92.99 74	97.52 58	98.83 84	72.37 264	99.15 141	97.03 67	96.74 140	96.58 228

xiu_mvs_v1_base_debi		94.73 97	93.98 104	96.99 64	95.19 219	95.24 27	98.62 164	96.50 216	92.99 74	97.52 58	98.83 84	72.37 264	99.15 141	97.03 67	96.74 140	96.58 228

ZD-MVS					99.67 10	93.28 73		97.61 110	87.78 216	97.41 61	99.16 38	90.15 52	99.56 105	98.35 41	99.70 35

ETV-MVS		96.00 53	96.00 53	96.00 122	96.56 163	91.05 121	99.63 37	96.61 206	93.26 70	97.39 62	98.30 123	86.62 108	98.13 189	98.07 49	97.57 122	98.82 144

DeepPCF-MVS	93.56 1	96.55 40	97.84 10	92.68 228	98.71 85	78.11 350	99.70 27	97.71 85	98.18 1	97.36 63	99.76 1	90.37 48	99.94 34	99.27 16	99.54 53	99.99 1

test_vis1_n		90.40 201	90.27 191	90.79 269	91.55 312	76.48 355	99.12 110	94.44 331	94.31 43	97.34 64	96.95 183	43.60 385	99.42 123	97.57 59	97.60 121	96.47 232

EC-MVSNet		95.09 84	95.17 76	94.84 165	95.42 210	88.17 194	99.48 54	95.92 261	91.47 106	97.34 64	98.36 120	82.77 173	97.41 239	97.24 64	98.58 101	98.94 132

test_fmvsmconf0.1_n		95.94 59	95.79 62	96.40 102	92.42 296	89.92 155	99.79 17	96.85 197	96.53 15	97.22 66	98.67 99	82.71 177	99.84 69	98.92 27	98.98 81	99.43 88

CANet		97.00 28	96.49 36	98.55 12	98.86 80	96.10 16	99.83 10	97.52 131	95.90 19	97.21 67	98.90 78	82.66 178	99.93 38	98.71 29	98.80 92	99.63 66

CANet_DTU		94.31 111	93.35 125	97.20 57	97.03 151	94.71 46	98.62 164	95.54 290	95.61 27	97.21 67	98.47 116	71.88 269	99.84 69	88.38 203	97.46 127	97.04 216

MVS_0304		97.53 14	97.15 22	98.67 11	97.30 132	96.52 12	99.60 39	98.88 14	97.14 4	97.21 67	98.94 74	86.89 101	99.91 45	99.43 15	98.91 87	99.59 73

test_cas_vis1_n_1920		93.86 124	93.74 116	94.22 190	95.39 213	86.08 249	99.73 23	96.07 247	96.38 17	97.19 70	97.78 138	65.46 319	99.86 63	96.71 74	98.92 86	96.73 223

VNet		95.08 85	94.26 93	97.55 45	98.07 101	93.88 63	98.68 155	98.73 18	90.33 135	97.16 71	97.43 157	79.19 217	99.53 109	96.91 73	91.85 205	99.24 104

region2R		96.30 46	96.17 48	96.70 83	99.70 7	90.31 138	99.46 60	97.66 95	90.55 128	97.07 72	99.07 53	86.85 102	99.97 21	95.43 103	99.74 29	99.81 33

原ACMM1				96.18 112	99.03 71	90.08 147		97.63 107	88.98 174	97.00 73	98.97 64	88.14 75	99.71 90	88.23 205	99.62 45	98.76 151

HFP-MVS		96.42 42	96.26 42	96.90 71	99.69 8	90.96 124	99.47 56	97.81 68	90.54 129	96.88 74	99.05 56	87.57 82	99.96 28	95.65 96	99.72 31	99.78 38

XVS		96.47 41	96.37 40	96.77 76	99.62 22	90.66 132	99.43 66	97.58 118	92.41 87	96.86 75	98.96 68	87.37 87	99.87 58	95.65 96	99.43 60	99.78 38

X-MVStestdata		90.69 198	88.66 221	96.77 76	99.62 22	90.66 132	99.43 66	97.58 118	92.41 87	96.86 75	29.59 409	87.37 87	99.87 58	95.65 96	99.43 60	99.78 38

SR-MVS		96.13 50	96.16 50	96.07 118	99.42 47	89.04 172	98.59 170	97.33 158	90.44 132	96.84 77	99.12 48	86.75 104	99.41 126	97.47 60	99.44 59	99.76 45

TSAR-MVS + GP.		96.95 29	96.91 26	97.07 59	98.88 79	91.62 104	99.58 42	96.54 214	95.09 34	96.84 77	98.63 103	91.16 30	99.77 85	99.04 24	96.42 145	99.81 33

ACMMPR		96.28 47	96.14 52	96.73 80	99.68 9	90.47 136	99.47 56	97.80 70	90.54 129	96.83 79	99.03 58	86.51 113	99.95 31	95.65 96	99.72 31	99.75 46

test_fmvs1		92.35 163	92.94 138	90.57 274	97.19 139	75.43 359	99.55 45	94.97 315	95.20 33	96.82 80	97.57 151	59.59 342	99.84 69	97.30 63	98.29 111	96.46 233

PMMVS		93.62 133	93.90 111	92.79 223	96.79 158	81.40 321	98.85 136	96.81 198	91.25 112	96.82 80	98.15 130	77.02 231	98.13 189	93.15 150	96.30 149	98.83 143

PGM-MVS		95.85 62	95.65 68	96.45 98	99.50 42	89.77 159	98.22 209	98.90 13	89.19 168	96.74 82	98.95 71	85.91 125	99.92 40	93.94 132	99.46 56	99.66 60

jason		95.40 77	94.86 84	97.03 61	92.91 291	94.23 56	99.70 27	96.30 227	93.56 66	96.73 83	98.52 108	81.46 198	97.91 201	96.08 90	98.47 106	98.96 127
jason: jason.
新几何1				97.40 49	98.92 77	92.51 93		97.77 75	85.52 262	96.69 84	99.06 55	88.08 76	99.89 53	84.88 243	99.62 45	99.79 36

SR-MVS-dyc-post		95.75 68	95.86 57	95.41 143	99.22 59	87.26 222	98.40 193	97.21 167	89.63 154	96.67 85	98.97 64	86.73 106	99.36 130	96.62 77	99.31 66	99.60 69

RE-MVS-def			95.70 64		99.22 59	87.26 222	98.40 193	97.21 167	89.63 154	96.67 85	98.97 64	85.24 137		96.62 77	99.31 66	99.60 69

APD-MVS_3200maxsize		95.64 71	95.65 68	95.62 137	99.24 58	87.80 202	98.42 188	97.22 166	88.93 178	96.64 87	98.98 63	85.49 131	99.36 130	96.68 76	99.27 69	99.70 52

mvsany_test1		94.57 105	95.09 80	92.98 219	95.84 196	82.07 314	98.76 148	95.24 308	92.87 79	96.45 88	98.71 96	84.81 143	99.15 141	97.68 57	95.49 163	97.73 194

MG-MVS		97.24 20	96.83 31	98.47 15	99.79 5	95.71 19	99.07 114	99.06 10	94.45 42	96.42 89	98.70 97	88.81 64	99.74 88	95.35 105	99.86 12	99.97 7

test_fmvs1_n		91.07 189	91.41 169	90.06 288	94.10 259	74.31 363	99.18 93	94.84 319	94.81 35	96.37 90	97.46 155	50.86 374	99.82 76	97.14 66	97.90 114	96.04 240

h-mvs33		92.47 162	91.95 158	94.05 198	97.13 145	85.01 275	98.36 199	98.08 44	93.85 57	96.27 91	96.73 196	83.19 165	99.43 122	95.81 94	68.09 363	97.70 195

hse-mvs2		91.67 177	91.51 167	92.15 238	96.22 180	82.61 310	97.74 247	97.53 127	93.85 57	96.27 91	96.15 212	83.19 165	97.44 237	95.81 94	66.86 370	96.40 235

alignmvs		95.77 66	95.00 82	98.06 29	97.35 130	95.68 20	99.71 26	97.50 136	91.50 105	96.16 93	98.61 105	86.28 117	99.00 151	96.19 86	91.74 207	99.51 79

CP-MVS		96.22 48	96.15 51	96.42 100	99.67 10	89.62 162	99.70 27	97.61 110	90.07 144	96.00 94	99.16 38	87.43 85	99.92 40	96.03 91	99.72 31	99.70 52

MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 10	99.70 27	97.98 53	97.18 3	95.96 95	99.33 19	92.62 25	100.00 1	98.99 25	99.93 1	99.98 6

diffmvs		94.59 104	94.19 96	95.81 129	95.54 206	90.69 130	98.70 153	95.68 282	91.61 101	95.96 95	97.81 135	80.11 206	98.06 194	96.52 82	95.76 158	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 71	99.49 45	91.22 111	99.45 62	97.48 139	89.69 152	95.89 97	98.72 93	86.37 116	99.95 31	94.62 125	99.22 71	99.52 77

DeepC-MVS_fast	93.52 2	97.16 24	96.84 29	98.13 25	99.61 24	94.45 51	98.85 136	97.64 103	96.51 16	95.88 98	99.39 18	87.35 91	99.99 5	96.61 79	99.69 36	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	91.21 112	98.08 226	97.58 118	83.74 291	95.87 99	99.02 60	86.74 105			99.64 40	99.81 33

sasdasda		95.02 86	93.96 107	98.20 21	97.53 120	95.92 17	98.71 150	96.19 236	91.78 98	95.86 100	98.49 112	79.53 212	99.03 149	96.12 87	91.42 219	99.66 60

ZNCC-MVS		96.09 51	95.81 60	96.95 70	99.42 47	91.19 113	99.55 45	97.53 127	89.72 151	95.86 100	98.94 74	86.59 109	99.97 21	95.13 110	99.56 51	99.68 56

canonicalmvs		95.02 86	93.96 107	98.20 21	97.53 120	95.92 17	98.71 150	96.19 236	91.78 98	95.86 100	98.49 112	79.53 212	99.03 149	96.12 87	91.42 219	99.66 60

dcpmvs_2		95.67 70	96.18 45	94.12 194	98.82 81	84.22 285	97.37 262	95.45 295	90.70 121	95.77 103	98.63 103	90.47 44	98.68 166	99.20 20	99.22 71	99.45 85

MGCFI-Net		94.89 88	93.84 113	98.06 29	97.49 125	95.55 21	98.64 161	96.10 243	91.60 103	95.75 104	98.46 118	79.31 216	98.98 153	95.95 93	91.24 223	99.65 63

Effi-MVS+		93.87 123	93.15 132	96.02 121	95.79 197	90.76 128	96.70 291	95.78 275	86.98 235	95.71 105	97.17 172	79.58 210	98.01 199	94.57 126	96.09 153	99.31 98

HPM-MVS_fast		94.89 88	94.62 86	95.70 133	99.11 66	88.44 192	99.14 106	97.11 179	85.82 257	95.69 106	98.47 116	83.46 158	99.32 135	93.16 149	99.63 44	99.35 94

HY-MVS	88.56 7	95.29 79	94.23 94	98.48 14	97.72 110	96.41 13	94.03 338	98.74 16	92.42 86	95.65 107	94.76 240	86.52 112	99.49 112	95.29 107	92.97 184	99.53 76

CHOSEN 280x420		96.80 33	96.85 28	96.66 86	97.85 108	94.42 53	94.76 330	98.36 29	92.50 83	95.62 108	97.52 152	97.92 1	97.38 240	98.31 44	98.80 92	98.20 183

test_fmvsmconf0.01_n		94.14 114	93.51 120	96.04 119	86.79 369	89.19 167	99.28 85	95.94 257	95.70 21	95.50 109	98.49 112	73.27 256	99.79 82	98.28 45	98.32 110	99.15 111

MP-MVS		96.00 53	95.82 58	96.54 93	99.47 46	90.13 146	99.36 76	97.41 151	90.64 125	95.49 110	98.95 71	85.51 130	99.98 9	96.00 92	99.59 50	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 76	95.22 75	95.99 123	99.29 55	89.14 169	99.17 96	97.09 183	87.28 229	95.40 111	98.48 115	84.93 140	99.38 128	95.64 100	99.65 38	99.47 82
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UA-Net		93.30 142	92.62 144	95.34 145	96.27 178	88.53 191	95.88 316	96.97 194	90.90 117	95.37 112	97.07 176	82.38 186	99.10 147	83.91 259	94.86 169	98.38 170

sss		94.85 93	93.94 109	97.58 42	96.43 170	94.09 61	98.93 130	99.16 8	89.50 161	95.27 113	97.85 133	81.50 196	99.65 98	92.79 156	94.02 175	98.99 124

WTY-MVS		95.97 56	95.11 79	98.54 13	97.62 114	96.65 9	99.44 63	98.74 16	92.25 91	95.21 114	98.46 118	86.56 111	99.46 118	95.00 115	92.69 188	99.50 80

DELS-MVS		97.12 25	96.60 35	98.68 10	98.03 103	96.57 11	99.84 9	97.84 61	96.36 18	95.20 115	98.24 125	88.17 72	99.83 73	96.11 89	99.60 49	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 82	98.58 88	91.00 123	99.14 106	99.45 1	93.86 56	95.15 116	98.73 91	88.48 67	99.76 86	97.23 65	99.56 51	99.40 89

MVS_Test		93.67 131	92.67 143	96.69 84	96.72 160	92.66 88	97.22 270	96.03 249	87.69 222	95.12 117	94.03 248	81.55 195	98.28 183	89.17 198	96.46 143	99.14 112

MVS_111021_LR		95.78 65	95.94 54	95.28 149	98.19 98	87.69 203	98.80 142	99.26 7	93.39 67	95.04 118	98.69 98	84.09 150	99.76 86	96.96 71	99.06 76	98.38 170

CostFormer		92.89 152	92.48 147	94.12 194	94.99 235	85.89 256	92.89 348	97.00 192	86.98 235	95.00 119	90.78 311	90.05 53	97.51 233	92.92 153	91.73 208	98.96 127

testing222		94.48 108	94.00 103	95.95 125	97.30 132	92.27 95	98.82 139	97.92 55	89.20 167	94.82 120	97.26 163	87.13 94	97.32 243	91.95 162	91.56 211	98.25 177

mPP-MVS		95.90 61	95.75 63	96.38 103	99.58 30	89.41 166	99.26 86	97.41 151	90.66 122	94.82 120	98.95 71	86.15 121	99.98 9	95.24 109	99.64 40	99.74 47

EI-MVSNet-Vis-set		95.76 67	95.63 70	96.17 114	99.14 64	90.33 137	98.49 181	97.82 65	91.92 96	94.75 122	98.88 82	87.06 97	99.48 116	95.40 104	97.17 135	98.70 154

LFMVS		92.23 168	90.84 181	96.42 100	98.24 95	91.08 120	98.24 208	96.22 233	83.39 298	94.74 123	98.31 122	61.12 337	98.85 156	94.45 127	92.82 185	99.32 97

tpmrst		92.78 153	92.16 152	94.65 172	96.27 178	87.45 213	91.83 357	97.10 182	89.10 172	94.68 124	90.69 315	88.22 71	97.73 220	89.78 187	91.80 206	98.77 150

test_yl		95.27 80	94.60 87	97.28 53	98.53 89	92.98 81	99.05 118	98.70 19	86.76 241	94.65 125	97.74 141	87.78 79	99.44 119	95.57 101	92.61 189	99.44 86

DCV-MVSNet		95.27 80	94.60 87	97.28 53	98.53 89	92.98 81	99.05 118	98.70 19	86.76 241	94.65 125	97.74 141	87.78 79	99.44 119	95.57 101	92.61 189	99.44 86

testing11		95.33 78	94.98 83	96.37 104	97.20 137	92.31 94	99.29 82	97.68 90	90.59 126	94.43 127	97.20 168	90.79 41	98.60 170	95.25 108	92.38 193	98.18 184

DP-MVS Recon		95.85 62	95.15 77	97.95 32	99.87 2	94.38 54	99.60 39	97.48 139	86.58 244	94.42 128	99.13 46	87.36 90	99.98 9	93.64 139	98.33 108	99.48 81

ETVMVS		94.50 107	93.90 111	96.31 107	97.48 126	92.98 81	99.07 114	97.86 59	88.09 206	94.40 129	96.90 186	88.35 69	97.28 244	90.72 177	92.25 199	98.66 159

MTAPA		96.09 51	95.80 61	96.96 69	99.29 55	91.19 113	97.23 269	97.45 144	92.58 81	94.39 130	99.24 25	86.43 115	99.99 5	96.22 85	99.40 63	99.71 51

CPTT-MVS		94.60 103	94.43 91	95.09 155	99.66 12	86.85 227	99.44 63	97.47 141	83.22 300	94.34 131	98.96 68	82.50 179	99.55 106	94.81 118	99.50 54	98.88 137

PVSNet_BlendedMVS		93.36 140	93.20 130	93.84 205	98.77 83	91.61 105	99.47 56	98.04 48	91.44 107	94.21 132	92.63 280	83.50 156	99.87 58	97.41 61	83.37 277	90.05 339

PVSNet_Blended		95.94 59	95.66 66	96.75 78	98.77 83	91.61 105	99.88 4	98.04 48	93.64 64	94.21 132	97.76 139	83.50 156	99.87 58	97.41 61	97.75 120	98.79 147

EI-MVSNet-UG-set		95.43 74	95.29 73	95.86 128	99.07 70	89.87 156	98.43 187	97.80 70	91.78 98	94.11 134	98.77 87	86.25 119	99.48 116	94.95 117	96.45 144	98.22 181

EIA-MVS		95.11 83	95.27 74	94.64 174	96.34 175	86.51 231	99.59 41	96.62 205	92.51 82	94.08 135	98.64 101	86.05 122	98.24 186	95.07 112	98.50 104	99.18 109

MAR-MVS		94.43 109	94.09 100	95.45 141	99.10 68	87.47 212	98.39 197	97.79 72	88.37 195	94.02 136	99.17 37	78.64 223	99.91 45	92.48 158	98.85 90	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	94.10 259	95.25 26	98.93 130	98.17 37	94.26 44	93.94 137	98.72 93	89.68 56	97.88 204	96.36 84	99.29 68	99.62 68

GG-mvs-BLEND				96.98 67	96.53 165	94.81 43	87.20 378	97.74 77		93.91 138	96.40 205	96.56 2	96.94 256	95.08 111	98.95 85	99.20 108

API-MVS		94.78 95	94.18 98	96.59 89	99.21 61	90.06 151	98.80 142	97.78 73	83.59 295	93.85 139	99.21 29	83.79 153	99.97 21	92.37 159	99.00 80	99.74 47

tpm2		91.77 175	91.09 174	93.82 206	94.83 242	85.56 264	92.51 353	97.16 174	84.00 286	93.83 140	90.66 317	87.54 83	97.17 246	87.73 211	91.55 212	98.72 152

PAPR		96.35 43	95.82 58	97.94 33	99.63 18	94.19 58	99.42 68	97.55 123	92.43 84	93.82 141	99.12 48	87.30 92	99.91 45	94.02 131	99.06 76	99.74 47

testing99		94.88 90	94.45 89	96.17 114	97.20 137	91.91 99	99.20 90	97.66 95	89.95 146	93.68 142	97.06 177	90.28 50	98.50 173	93.52 141	91.54 213	98.12 186

testing91		94.88 90	94.44 90	96.21 110	97.19 139	91.90 100	99.23 88	97.66 95	89.91 147	93.66 143	97.05 179	90.21 51	98.50 173	93.52 141	91.53 216	98.25 177

PVSNet	87.13 12	93.69 128	92.83 140	96.28 108	97.99 104	90.22 142	99.38 72	98.93 12	91.42 109	93.66 143	97.68 144	71.29 276	99.64 100	87.94 209	97.20 132	98.98 125

baseline		93.91 121	93.30 127	95.72 132	95.10 230	90.07 148	97.48 258	95.91 266	91.03 114	93.54 145	97.68 144	79.58 210	98.02 198	94.27 129	95.14 166	99.08 119

test2506		94.80 94	94.21 95	96.58 90	96.41 171	92.18 97	98.01 230	98.96 11	90.82 119	93.46 146	97.28 161	85.92 123	98.45 176	89.82 186	97.19 133	99.12 115

VDD-MVS		91.24 187	90.18 192	94.45 180	97.08 148	85.84 259	98.40 193	96.10 243	86.99 232	93.36 147	98.16 129	54.27 363	99.20 138	96.59 80	90.63 229	98.31 176

VDDNet		90.08 211	88.54 227	94.69 171	94.41 251	87.68 204	98.21 211	96.40 221	76.21 358	93.33 148	97.75 140	54.93 361	98.77 159	94.71 122	90.96 224	97.61 200

thisisatest0515		94.75 96	94.19 96	96.43 99	96.13 190	92.64 91	99.47 56	97.60 112	87.55 225	93.17 149	97.59 149	94.71 12	98.42 177	88.28 204	93.20 181	98.24 180

MP-MVS-pluss		95.80 64	95.30 72	97.29 52	98.95 76	92.66 88	98.59 170	97.14 175	88.95 176	93.12 150	99.25 23	85.62 127	99.94 34	96.56 81	99.48 55	99.28 101
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MDTV_nov1_ep13_2view						91.17 115	91.38 364		87.45 227	93.08 151		86.67 107		87.02 215		98.95 131

EPNet_dtu		92.28 166	92.15 153	92.70 227	97.29 134	84.84 277	98.64 161	97.82 65	92.91 77	93.02 152	97.02 180	85.48 133	95.70 322	72.25 346	94.89 168	97.55 201
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
gg-mvs-nofinetune		90.00 212	87.71 239	96.89 75	96.15 185	94.69 47	85.15 384	97.74 77	68.32 384	92.97 153	60.16 397	96.10 3	96.84 259	93.89 133	98.87 89	99.14 112

test_fmvsmvis_n_1920		95.47 73	95.40 71	95.70 133	94.33 253	90.22 142	99.70 27	96.98 193	96.80 7	92.75 154	98.89 80	82.46 184	99.92 40	98.36 40	98.33 108	96.97 219

casdiffmvs		93.98 119	93.43 122	95.61 138	95.07 232	89.86 157	98.80 142	95.84 274	90.98 116	92.74 155	97.66 146	79.71 209	98.10 191	94.72 121	95.37 164	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		94.06 115	93.05 134	97.06 60	99.08 69	92.26 96	98.97 128	97.01 191	82.58 313	92.57 156	98.22 126	80.68 204	99.30 136	89.34 194	99.02 79	99.63 66

OMC-MVS		93.90 122	93.62 118	94.73 170	98.63 87	87.00 225	98.04 229	96.56 212	92.19 92	92.46 157	98.73 91	79.49 214	99.14 145	92.16 161	94.34 173	98.03 188

PAPM_NR		95.43 74	95.05 81	96.57 92	99.42 47	90.14 144	98.58 172	97.51 133	90.65 124	92.44 158	98.90 78	87.77 81	99.90 50	90.88 172	99.32 65	99.68 56

UGNet		91.91 174	90.85 180	95.10 154	97.06 149	88.69 187	98.01 230	98.24 34	92.41 87	92.39 159	93.61 261	60.52 339	99.68 92	88.14 206	97.25 131	96.92 220
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			90.47 190		96.14 187	88.55 189	91.34 365	97.51 133	89.58 157	92.24 160	90.50 328	86.99 100	97.61 227	77.64 308	92.34 195

FE-MVS		91.38 182	90.16 193	95.05 158	96.46 169	87.53 210	89.69 375	97.84 61	82.97 305	92.18 161	92.00 289	84.07 151	98.93 155	80.71 287	95.52 162	98.68 155

Vis-MVSNet		92.64 156	91.85 159	95.03 159	95.12 226	88.23 193	98.48 183	96.81 198	91.61 101	92.16 162	97.22 167	71.58 274	98.00 200	85.85 234	97.81 116	98.88 137
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
FA-MVS(test-final)		92.22 169	91.08 175	95.64 136	96.05 191	88.98 175	91.60 361	97.25 161	86.99 232	91.84 163	92.12 283	83.03 168	99.00 151	86.91 219	93.91 176	98.93 133

TESTMET0.1,1		93.82 125	93.26 129	95.49 140	95.21 218	90.25 139	99.15 103	97.54 126	89.18 169	91.79 164	94.87 237	89.13 59	97.63 225	86.21 227	96.29 150	98.60 160

thisisatest0530		94.00 117	93.52 119	95.43 142	95.76 199	90.02 153	98.99 125	97.60 112	86.58 244	91.74 165	97.36 160	94.78 11	98.34 179	86.37 225	92.48 192	97.94 191

UWE-MVS		93.18 146	93.40 124	92.50 231	96.56 163	83.55 294	98.09 225	97.84 61	89.50 161	91.72 166	96.23 211	91.08 33	96.70 265	86.28 226	93.33 180	97.26 208

AUN-MVS		90.17 208	89.50 201	92.19 236	96.21 181	82.67 308	97.76 246	97.53 127	88.05 207	91.67 167	96.15 212	83.10 167	97.47 234	88.11 207	66.91 369	96.43 234

EPMVS		92.59 159	91.59 165	95.59 139	97.22 136	90.03 152	91.78 358	98.04 48	90.42 133	91.66 168	90.65 318	86.49 114	97.46 235	81.78 280	96.31 148	99.28 101

test-LLR		93.11 149	92.68 142	94.40 181	94.94 238	87.27 220	99.15 103	97.25 161	90.21 136	91.57 169	94.04 246	84.89 141	97.58 229	85.94 231	96.13 151	98.36 173

test-mter		93.27 144	92.89 139	94.40 181	94.94 238	87.27 220	99.15 103	97.25 161	88.95 176	91.57 169	94.04 246	88.03 77	97.58 229	85.94 231	96.13 151	98.36 173

JIA-IIPM		85.97 282	84.85 282	89.33 310	93.23 287	73.68 366	85.05 385	97.13 177	69.62 380	91.56 171	68.03 395	88.03 77	96.96 254	77.89 307	93.12 182	97.34 205

casdiffmvs_mvg		94.00 117	93.33 126	96.03 120	95.22 217	90.90 126	99.09 112	95.99 250	90.58 127	91.55 172	97.37 159	79.91 208	98.06 194	95.01 114	95.22 165	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		94.67 101	94.11 99	96.34 106	97.14 144	91.10 118	99.32 80	97.43 149	92.10 95	91.53 173	96.38 208	83.29 162	99.68 92	93.42 146	96.37 146	98.25 177

CHOSEN 1792x2688		94.35 110	93.82 114	95.95 125	97.40 127	88.74 186	98.41 190	98.27 31	92.18 93	91.43 174	96.40 205	78.88 218	99.81 79	93.59 140	97.81 116	99.30 99

ACMMP		94.67 101	94.30 92	95.79 130	99.25 57	88.13 196	98.41 190	98.67 22	90.38 134	91.43 174	98.72 93	82.22 188	99.95 31	93.83 136	95.76 158	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		92.29 165	91.33 170	95.15 153	96.41 171	87.84 201	98.10 222	94.84 319	90.82 119	91.42 176	97.28 161	65.61 316	98.49 175	90.33 180	97.19 133	99.12 115

EPP-MVSNet		93.75 127	93.67 117	94.01 200	95.86 195	85.70 261	98.67 157	97.66 95	84.46 280	91.36 177	97.18 171	91.16 30	97.79 210	92.93 152	93.75 177	98.53 162

PLC	91.07 3	94.23 112	94.01 102	94.87 163	99.17 63	87.49 211	99.25 87	96.55 213	88.43 193	91.26 178	98.21 128	85.92 123	99.86 63	89.77 188	97.57 122	97.24 209
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HyFIR lowres test		93.68 130	93.29 128	94.87 163	97.57 119	88.04 198	98.18 213	98.47 25	87.57 224	91.24 179	95.05 234	85.49 131	97.46 235	93.22 148	92.82 185	99.10 117

thres200		93.69 128	92.59 145	96.97 68	97.76 109	94.74 45	99.35 77	99.36 2	89.23 166	91.21 180	96.97 182	83.42 159	98.77 159	85.08 239	90.96 224	97.39 204

test1111		92.12 170	91.19 173	94.94 161	96.15 185	87.36 216	98.12 219	94.84 319	90.85 118	90.97 181	97.26 163	65.60 317	98.37 178	89.74 189	97.14 136	99.07 121

CDS-MVSNet		93.47 135	93.04 135	94.76 167	94.75 244	89.45 165	98.82 139	97.03 188	87.91 213	90.97 181	96.48 203	89.06 60	96.36 286	89.50 190	92.81 187	98.49 164
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tfpn200view9		93.43 137	92.27 150	96.90 71	97.68 112	94.84 40	99.18 93	99.36 2	88.45 190	90.79 183	96.90 186	83.31 160	98.75 161	84.11 255	90.69 226	97.12 211

thres400		93.39 139	92.27 150	96.73 80	97.68 112	94.84 40	99.18 93	99.36 2	88.45 190	90.79 183	96.90 186	83.31 160	98.75 161	84.11 255	90.69 226	96.61 226

CR-MVSNet		88.83 233	87.38 244	93.16 216	93.47 280	86.24 241	84.97 386	94.20 340	88.92 179	90.76 185	86.88 363	84.43 146	94.82 343	70.64 350	92.17 201	98.41 167

RPMNet		85.07 296	81.88 313	94.64 174	93.47 280	86.24 241	84.97 386	97.21 167	64.85 391	90.76 185	78.80 388	80.95 203	99.27 137	53.76 390	92.17 201	98.41 167

PatchmatchNet		92.05 173	91.04 176	95.06 156	96.17 184	89.04 172	91.26 366	97.26 160	89.56 159	90.64 187	90.56 324	88.35 69	97.11 248	79.53 293	96.07 155	99.03 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tttt0517		93.30 142	93.01 136	94.17 192	95.57 204	86.47 233	98.51 178	97.60 112	85.99 255	90.55 188	97.19 170	94.80 10	98.31 180	85.06 240	91.86 204	97.74 193

PatchT		85.44 292	83.19 301	92.22 234	93.13 289	83.00 300	83.80 392	96.37 223	70.62 374	90.55 188	79.63 387	84.81 143	94.87 341	58.18 386	91.59 210	98.79 147

tpm		89.67 217	88.95 214	91.82 245	92.54 294	81.43 320	92.95 347	95.92 261	87.81 215	90.50 190	89.44 343	84.99 139	95.65 323	83.67 262	82.71 282	98.38 170

thres100view900		93.34 141	92.15 153	96.90 71	97.62 114	94.84 40	99.06 117	99.36 2	87.96 211	90.47 191	96.78 194	83.29 162	98.75 161	84.11 255	90.69 226	97.12 211

thres600view7		93.18 146	92.00 156	96.75 78	97.62 114	94.92 35	99.07 114	99.36 2	87.96 211	90.47 191	96.78 194	83.29 162	98.71 165	82.93 269	90.47 230	96.61 226

AdaColmap		93.82 125	93.06 133	96.10 117	99.88 1	89.07 171	98.33 201	97.55 123	86.81 240	90.39 193	98.65 100	75.09 238	99.98 9	93.32 147	97.53 125	99.26 103

XVG-OURS-SEG-HR		90.95 192	90.66 187	91.83 244	95.18 222	81.14 328	95.92 313	95.92 261	88.40 194	90.33 194	97.85 133	70.66 279	99.38 128	92.83 154	88.83 236	94.98 247

IS-MVSNet		93.00 151	92.51 146	94.49 177	96.14 187	87.36 216	98.31 204	95.70 280	88.58 186	90.17 195	97.50 153	83.02 169	97.22 245	87.06 214	96.07 155	98.90 136

CSCG		94.87 92	94.71 85	95.36 144	99.54 36	86.49 232	99.34 78	98.15 40	82.71 311	90.15 196	99.25 23	89.48 57	99.86 63	94.97 116	98.82 91	99.72 50

SCA		90.64 199	89.25 208	94.83 166	94.95 237	88.83 182	96.26 303	97.21 167	90.06 145	90.03 197	90.62 320	66.61 308	96.81 261	83.16 265	94.36 172	98.84 140

XVG-OURS		90.83 194	90.49 189	91.86 243	95.23 216	81.25 325	95.79 321	95.92 261	88.96 175	90.02 198	98.03 132	71.60 273	99.35 133	91.06 169	87.78 240	94.98 247

ADS-MVSNet2		87.62 258	86.88 252	89.86 295	96.21 181	79.14 340	87.15 379	92.99 354	83.01 303	89.91 199	87.27 359	78.87 219	92.80 364	74.20 333	92.27 197	97.64 196

ADS-MVSNet		88.99 225	87.30 245	94.07 196	96.21 181	87.56 209	87.15 379	96.78 200	83.01 303	89.91 199	87.27 359	78.87 219	97.01 253	74.20 333	92.27 197	97.64 196

ab-mvs		91.05 191	89.17 209	96.69 84	95.96 193	91.72 103	92.62 352	97.23 165	85.61 261	89.74 201	93.89 254	68.55 290	99.42 123	91.09 168	87.84 239	98.92 135

TAMVS		92.62 157	92.09 155	94.20 191	94.10 259	87.68 204	98.41 190	96.97 194	87.53 226	89.74 201	96.04 217	84.77 145	96.49 279	88.97 200	92.31 196	98.42 166

Vis-MVSNet (Re-imp)		93.26 145	93.00 137	94.06 197	96.14 187	86.71 230	98.68 155	96.70 201	88.30 199	89.71 203	97.64 147	85.43 134	96.39 284	88.06 208	96.32 147	99.08 119

CNLPA		93.64 132	92.74 141	96.36 105	98.96 75	90.01 154	99.19 91	95.89 269	86.22 252	89.40 204	98.85 83	80.66 205	99.84 69	88.57 201	96.92 138	99.24 104

Anonymous202405211		88.84 231	87.03 250	94.27 187	98.14 100	84.18 286	98.44 186	95.58 288	76.79 357	89.34 205	96.88 189	53.42 366	99.54 108	87.53 213	87.12 243	99.09 118

Fast-Effi-MVS+		91.72 176	90.79 184	94.49 177	95.89 194	87.40 215	99.54 50	95.70 280	85.01 273	89.28 206	95.68 223	77.75 227	97.57 232	83.22 264	95.06 167	98.51 163

PatchMatch-RL		91.47 179	90.54 188	94.26 188	98.20 96	86.36 238	96.94 279	97.14 175	87.75 218	88.98 207	95.75 222	71.80 271	99.40 127	80.92 285	97.39 129	97.02 217

dp		90.16 209	88.83 217	94.14 193	96.38 174	86.42 234	91.57 362	97.06 185	84.76 277	88.81 208	90.19 336	84.29 148	97.43 238	75.05 325	91.35 222	98.56 161

DeepC-MVS	91.02 4	94.56 106	93.92 110	96.46 96	97.16 142	90.76 128	98.39 197	97.11 179	93.92 52	88.66 209	98.33 121	78.14 225	99.85 67	95.02 113	98.57 102	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		92.61 158	91.28 171	96.58 90	97.05 150	94.63 48	97.72 248	96.20 234	89.82 149	88.56 210	96.85 190	86.85 102	97.82 208	88.42 202	80.10 295	97.30 206

Anonymous20240529		87.66 257	85.58 270	93.92 202	97.59 117	85.01 275	98.13 217	97.13 177	66.69 389	88.47 211	96.01 218	55.09 360	99.51 110	87.00 216	84.12 268	97.23 210

CVMVSNet		90.30 204	90.91 179	88.46 322	94.32 254	73.58 367	97.61 255	97.59 116	90.16 141	88.43 212	97.10 174	76.83 232	92.86 361	82.64 271	93.54 179	98.93 133

TR-MVS		90.77 195	89.44 203	94.76 167	96.31 176	88.02 199	97.92 234	95.96 254	85.52 262	88.22 213	97.23 166	66.80 307	98.09 192	84.58 247	92.38 193	98.17 185

F-COLMAP		92.07 172	91.75 163	93.02 218	98.16 99	82.89 304	98.79 146	95.97 252	86.54 246	87.92 214	97.80 136	78.69 222	99.65 98	85.97 229	95.93 157	96.53 231

WB-MVSnew		88.69 239	88.34 229	89.77 299	94.30 258	85.99 254	98.14 216	97.31 159	87.15 231	87.85 215	96.07 216	69.91 280	95.52 326	72.83 344	91.47 217	87.80 363

BH-RMVSNet		91.25 186	89.99 194	95.03 159	96.75 159	88.55 189	98.65 159	94.95 316	87.74 219	87.74 216	97.80 136	68.27 293	98.14 188	80.53 290	97.49 126	98.41 167

Effi-MVS+-dtu		89.97 214	90.68 186	87.81 326	95.15 223	71.98 373	97.87 238	95.40 299	91.92 96	87.57 217	91.44 299	74.27 247	96.84 259	89.45 191	93.10 183	94.60 249

HQP-NCC					93.95 264		99.16 97		93.92 52	87.57 217

ACMP_Plane					93.95 264		99.16 97		93.92 52	87.57 217

HQP4-MVS										87.57 217			97.77 212			92.72 258

HQP-MVS		91.50 178	91.23 172	92.29 233	93.95 264	86.39 236	99.16 97	96.37 223	93.92 52	87.57 217	96.67 199	73.34 253	97.77 212	93.82 137	86.29 247	92.72 258

TAPA-MVS	87.50 9	90.35 202	89.05 212	94.25 189	98.48 91	85.17 272	98.42 188	96.58 211	82.44 318	87.24 222	98.53 107	82.77 173	98.84 157	59.09 384	97.88 115	98.72 152
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		90.60 200	89.56 200	93.72 209	95.10 230	85.43 265	99.41 69	94.94 317	83.96 288	87.21 223	96.83 193	74.37 245	97.05 252	80.50 291	93.73 178	98.67 156

bld_raw_dy_0_64		91.37 183	89.75 197	96.23 109	97.51 122	90.58 134	99.16 97	88.98 389	95.64 25	87.18 224	99.20 30	57.19 351	98.66 167	98.00 50	84.86 260	99.46 83

HQP_MVS		91.26 184	90.95 178	92.16 237	93.84 271	86.07 251	99.02 121	96.30 227	93.38 68	86.99 225	96.52 201	72.92 259	97.75 218	93.46 144	86.17 250	92.67 260

plane_prior3						85.91 255			93.65 63	86.99 225

GA-MVS		90.10 210	88.69 220	94.33 185	92.44 295	87.97 200	99.08 113	96.26 231	89.65 153	86.92 227	93.11 273	68.09 295	96.96 254	82.54 273	90.15 231	98.05 187

1112_ss		92.71 154	91.55 166	96.20 111	95.56 205	91.12 116	98.48 183	94.69 326	88.29 200	86.89 228	98.50 110	87.02 98	98.66 167	84.75 244	89.77 234	98.81 145

Test_1112_low_res		92.27 167	90.97 177	96.18 112	95.53 207	91.10 118	98.47 185	94.66 327	88.28 201	86.83 229	93.50 265	87.00 99	98.65 169	84.69 245	89.74 235	98.80 146

cascas		90.93 193	89.33 207	95.76 131	95.69 201	93.03 80	98.99 125	96.59 208	80.49 338	86.79 230	94.45 243	65.23 320	98.60 170	93.52 141	92.18 200	95.66 243

iter_conf05		93.48 134	93.18 131	94.39 184	97.15 143	94.17 59	99.30 81	92.97 355	92.38 90	86.70 231	95.42 228	95.67 5	96.59 269	94.67 123	84.32 266	92.39 263

baseline2		94.04 116	93.80 115	94.74 169	93.07 290	90.25 139	98.12 219	98.16 39	89.86 148	86.53 232	96.95 183	95.56 6	98.05 196	91.44 166	94.53 170	95.93 241

OPM-MVS		89.76 216	89.15 210	91.57 253	90.53 326	85.58 263	98.11 221	95.93 260	92.88 78	86.05 233	96.47 204	67.06 306	97.87 205	89.29 197	86.08 252	91.26 308
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPA-MVSNet		89.10 224	87.66 240	93.45 211	92.56 293	91.02 122	97.97 233	98.32 30	86.92 237	86.03 234	92.01 287	68.84 289	97.10 250	90.92 171	75.34 317	92.23 271

SDMVSNet		91.09 188	89.91 195	94.65 172	96.80 156	90.54 135	97.78 242	97.81 68	88.34 197	85.73 235	95.26 231	66.44 311	98.26 184	94.25 130	86.75 244	95.14 244

sd_testset		89.23 222	88.05 236	92.74 226	96.80 156	85.33 268	95.85 319	97.03 188	88.34 197	85.73 235	95.26 231	61.12 337	97.76 217	85.61 235	86.75 244	95.14 244

tpm cat1		88.89 229	87.27 246	93.76 207	95.79 197	85.32 269	90.76 371	97.09 183	76.14 359	85.72 237	88.59 349	82.92 170	98.04 197	76.96 312	91.43 218	97.90 192

IB-MVS	89.43 6	92.12 170	90.83 183	95.98 124	95.40 212	90.78 127	99.81 12	98.06 45	91.23 113	85.63 238	93.66 260	90.63 42	98.78 158	91.22 167	71.85 353	98.36 173
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		89.87 215	89.38 206	91.36 256	94.32 254	85.87 257	97.61 255	96.59 208	85.10 268	85.51 239	97.10 174	81.30 201	96.56 272	83.85 261	83.03 279	91.64 287

MVSTER		92.71 154	92.32 148	93.86 204	97.29 134	92.95 84	99.01 123	96.59 208	90.09 142	85.51 239	94.00 250	94.61 15	96.56 272	90.77 176	83.03 279	92.08 280

test_fmvs2		85.10 295	85.45 273	84.02 352	89.85 335	65.63 386	98.49 181	92.59 360	90.45 131	85.43 241	93.32 266	43.94 383	96.59 269	90.81 174	84.19 267	89.85 343

RPSCF		85.33 293	85.55 271	84.67 349	94.63 248	62.28 388	93.73 340	93.76 345	74.38 366	85.23 242	97.06 177	64.09 323	98.31 180	80.98 283	86.08 252	93.41 255

BH-w/o		92.32 164	91.79 161	93.91 203	96.85 153	86.18 245	99.11 111	95.74 278	88.13 204	84.81 243	97.00 181	77.26 230	97.91 201	89.16 199	98.03 113	97.64 196

mvsmamba		89.99 213	89.42 204	91.69 251	90.64 325	86.34 239	98.40 193	92.27 364	91.01 115	84.80 244	94.93 235	76.12 233	96.51 276	92.81 155	83.84 270	92.21 273

CLD-MVS		91.06 190	90.71 185	92.10 239	94.05 263	86.10 248	99.55 45	96.29 230	94.16 47	84.70 245	97.17 172	69.62 285	97.82 208	94.74 120	86.08 252	92.39 263
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tpmvs		89.16 223	87.76 237	93.35 212	97.19 139	84.75 279	90.58 373	97.36 156	81.99 323	84.56 246	89.31 346	83.98 152	98.17 187	74.85 328	90.00 233	97.12 211

nrg030		90.23 205	88.87 215	94.32 186	91.53 313	93.54 69	98.79 146	95.89 269	88.12 205	84.55 247	94.61 242	78.80 221	96.88 258	92.35 160	75.21 318	92.53 262

VPNet		88.30 245	86.57 255	93.49 210	91.95 305	91.35 109	98.18 213	97.20 171	88.61 184	84.52 248	94.89 236	62.21 332	96.76 264	89.34 194	72.26 350	92.36 265

dmvs_re		88.69 239	88.06 235	90.59 273	93.83 273	78.68 344	95.75 322	96.18 238	87.99 210	84.48 249	96.32 209	67.52 301	96.94 256	84.98 242	85.49 256	96.14 238

MVS		93.92 120	92.28 149	98.83 7	95.69 201	96.82 8	96.22 306	98.17 37	84.89 275	84.34 250	98.61 105	79.32 215	99.83 73	93.88 134	99.43 60	99.86 29

mvs_anonymous		92.50 161	91.65 164	95.06 156	96.60 162	89.64 161	97.06 275	96.44 220	86.64 243	84.14 251	93.93 252	82.49 180	96.17 301	91.47 165	96.08 154	99.35 94

Fast-Effi-MVS+-dtu		88.84 231	88.59 224	89.58 304	93.44 283	78.18 348	98.65 159	94.62 328	88.46 189	84.12 252	95.37 230	68.91 287	96.52 275	82.06 277	91.70 209	94.06 250

LS3D		90.19 207	88.72 219	94.59 176	98.97 73	86.33 240	96.90 281	96.60 207	74.96 363	84.06 253	98.74 90	75.78 235	99.83 73	74.93 326	97.57 122	97.62 199

ACMM	86.95 13	88.77 236	88.22 232	90.43 279	93.61 277	81.34 323	98.50 179	95.92 261	87.88 214	83.85 254	95.20 233	67.20 304	97.89 203	86.90 220	84.90 259	92.06 281
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
BH-untuned		91.46 180	90.84 181	93.33 213	96.51 167	84.83 278	98.84 138	95.50 292	86.44 251	83.50 255	96.70 197	75.49 237	97.77 212	86.78 222	97.81 116	97.40 203

FIs		90.70 197	89.87 196	93.18 215	92.29 297	91.12 116	98.17 215	98.25 32	89.11 171	83.44 256	94.82 239	82.26 187	96.17 301	87.76 210	82.76 281	92.25 269

UniMVSNet (Re)		89.50 221	88.32 230	93.03 217	92.21 299	90.96 124	98.90 134	98.39 27	89.13 170	83.22 257	92.03 285	81.69 194	96.34 292	86.79 221	72.53 346	91.81 285

UniMVSNet_NR-MVSNet		89.60 218	88.55 226	92.75 225	92.17 300	90.07 148	98.74 149	98.15 40	88.37 195	83.21 258	93.98 251	82.86 171	95.93 312	86.95 217	72.47 347	92.25 269

DU-MVS		88.83 233	87.51 241	92.79 223	91.46 314	90.07 148	98.71 150	97.62 109	88.87 180	83.21 258	93.68 258	74.63 239	95.93 312	86.95 217	72.47 347	92.36 265

LPG-MVS_test		88.86 230	88.47 228	90.06 288	93.35 285	80.95 330	98.22 209	95.94 257	87.73 220	83.17 260	96.11 214	66.28 312	97.77 212	90.19 182	85.19 257	91.46 298

LGP-MVS_train				90.06 288	93.35 285	80.95 330		95.94 257	87.73 220	83.17 260	96.11 214	66.28 312	97.77 212	90.19 182	85.19 257	91.46 298

miper_enhance_ethall		90.33 203	89.70 198	92.22 234	97.12 146	88.93 180	98.35 200	95.96 254	88.60 185	83.14 262	92.33 282	87.38 86	96.18 300	86.49 224	77.89 304	91.55 295

FC-MVSNet-test		90.22 206	89.40 205	92.67 229	91.78 309	89.86 157	97.89 235	98.22 35	88.81 181	82.96 263	94.66 241	81.90 193	95.96 310	85.89 233	82.52 284	92.20 275

PCF-MVS	89.78 5	91.26 184	89.63 199	96.16 116	95.44 209	91.58 107	95.29 326	96.10 243	85.07 270	82.75 264	97.45 156	78.28 224	99.78 84	80.60 289	95.65 161	97.12 211
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
V42		87.00 264	85.68 269	90.98 263	89.91 332	86.08 249	98.32 203	95.61 286	83.67 294	82.72 265	90.67 316	74.00 250	96.53 274	81.94 279	74.28 330	90.32 332

v1144		86.83 267	85.31 275	91.40 254	89.75 336	87.21 224	98.31 204	95.45 295	83.22 300	82.70 266	90.78 311	73.36 252	96.36 286	79.49 294	74.69 324	90.63 327

Syy-MVS		84.10 311	84.53 290	82.83 357	95.14 224	65.71 385	97.68 251	96.66 203	86.52 247	82.63 267	96.84 191	68.15 294	89.89 381	45.62 395	91.54 213	92.87 256

myMVS_eth3d		88.68 241	89.07 211	87.50 329	95.14 224	79.74 336	97.68 251	96.66 203	86.52 247	82.63 267	96.84 191	85.22 138	89.89 381	69.43 355	91.54 213	92.87 256

v144192		86.40 276	84.89 281	90.91 264	89.48 342	85.59 262	98.21 211	95.43 298	82.45 317	82.62 269	90.58 323	72.79 262	96.36 286	78.45 304	74.04 334	90.79 320

3Dnovator	87.35 11	93.17 148	91.77 162	97.37 51	95.41 211	93.07 78	98.82 139	97.85 60	91.53 104	82.56 270	97.58 150	71.97 268	99.82 76	91.01 170	99.23 70	99.22 107

v2v482		87.27 262	85.76 267	91.78 250	89.59 338	87.58 208	98.56 173	95.54 290	84.53 279	82.51 271	91.78 293	73.11 258	96.47 280	82.07 276	74.14 333	91.30 306

tt0805		86.50 275	84.79 284	91.63 252	91.97 303	81.49 319	96.49 295	97.38 154	82.24 320	82.44 272	95.82 221	51.22 371	98.25 185	84.55 248	80.96 291	95.13 246

Baseline_NR-MVSNet		85.83 285	84.82 283	88.87 319	88.73 350	83.34 297	98.63 163	91.66 373	80.41 341	82.44 272	91.35 301	74.63 239	95.42 330	84.13 254	71.39 356	87.84 361

v1192		86.32 278	84.71 286	91.17 258	89.53 341	86.40 235	98.13 217	95.44 297	82.52 315	82.42 274	90.62 320	71.58 274	96.33 293	77.23 309	74.88 321	90.79 320

RRT_MVS		88.91 228	88.56 225	89.93 293	90.31 329	81.61 318	98.08 226	96.38 222	89.30 165	82.41 275	94.84 238	73.15 257	96.04 307	90.38 179	82.23 286	92.15 276

test_djsdf		88.26 247	87.73 238	89.84 296	88.05 358	82.21 312	97.77 244	96.17 239	86.84 238	82.41 275	91.95 291	72.07 267	95.99 308	89.83 184	84.50 263	91.32 305

cl22		89.57 219	88.79 218	91.91 242	97.94 105	87.62 207	97.98 232	96.51 215	85.03 271	82.37 277	91.79 292	83.65 154	96.50 277	85.96 230	77.89 304	91.61 292

1314		93.44 136	91.98 157	97.84 34	95.24 215	94.38 54	96.22 306	97.92 55	90.18 138	82.28 278	97.71 143	77.63 228	99.80 81	91.94 163	98.67 98	99.34 96

v1921920		86.02 281	84.44 292	90.77 270	89.32 344	85.20 270	98.10 222	95.35 303	82.19 321	82.25 279	90.71 313	70.73 277	96.30 297	76.85 314	74.49 326	90.80 319

v1240		85.77 288	84.11 295	90.73 271	89.26 345	85.15 273	97.88 237	95.23 312	81.89 326	82.16 280	90.55 325	69.60 286	96.31 294	75.59 323	74.87 322	90.72 324

XVG-ACMP-BASELINE		85.86 284	84.95 280	88.57 320	89.90 333	77.12 354	94.30 334	95.60 287	87.40 228	82.12 281	92.99 276	53.42 366	97.66 222	85.02 241	83.83 271	90.92 316

GBi-Net		86.67 270	84.96 278	91.80 246	95.11 227	88.81 183	96.77 285	95.25 305	82.94 306	82.12 281	90.25 331	62.89 329	94.97 338	79.04 297	80.24 292	91.62 289

test1		86.67 270	84.96 278	91.80 246	95.11 227	88.81 183	96.77 285	95.25 305	82.94 306	82.12 281	90.25 331	62.89 329	94.97 338	79.04 297	80.24 292	91.62 289

FMVSNet3		88.81 235	87.08 249	93.99 201	96.52 166	94.59 49	98.08 226	96.20 234	85.85 256	82.12 281	91.60 296	74.05 249	95.40 331	79.04 297	80.24 292	91.99 283

IterMVS-LS		88.34 244	87.44 242	91.04 261	94.10 259	85.85 258	98.10 222	95.48 293	85.12 267	82.03 285	91.21 304	81.35 200	95.63 324	83.86 260	75.73 316	91.63 288
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		88.94 227	88.12 234	91.40 254	95.32 214	86.93 226	97.85 239	95.55 289	84.19 283	81.97 286	91.50 298	84.16 149	95.91 315	84.69 245	77.89 304	91.36 303

MIMVSNet		84.48 304	81.83 314	92.42 232	91.73 310	87.36 216	85.52 382	94.42 334	81.40 329	81.91 287	87.58 353	51.92 369	92.81 363	73.84 336	88.15 238	97.08 215

PS-MVSNAJss		89.54 220	89.05 212	91.00 262	88.77 349	84.36 283	97.39 259	95.97 252	88.47 187	81.88 288	93.80 256	82.48 181	96.50 277	89.34 194	83.34 278	92.15 276

WR-MVS		88.54 243	87.22 248	92.52 230	91.93 307	89.50 164	98.56 173	97.84 61	86.99 232	81.87 289	93.81 255	74.25 248	95.92 314	85.29 237	74.43 327	92.12 278

TranMVSNet+NR-MVSNet		87.75 253	86.31 259	92.07 240	90.81 322	88.56 188	98.33 201	97.18 172	87.76 217	81.87 289	93.90 253	72.45 263	95.43 329	83.13 267	71.30 357	92.23 271

eth_miper_zixun_eth		87.76 252	87.00 251	90.06 288	94.67 246	82.65 309	97.02 278	95.37 301	84.19 283	81.86 291	91.58 297	81.47 197	95.90 316	83.24 263	73.61 336	91.61 292

UniMVSNet_ETH3D		85.65 291	83.79 299	91.21 257	90.41 328	80.75 332	95.36 325	95.78 275	78.76 347	81.83 292	94.33 244	49.86 376	96.66 266	84.30 250	83.52 276	96.22 237

c3_l		88.19 248	87.23 247	91.06 260	94.97 236	86.17 246	97.72 248	95.38 300	83.43 297	81.68 293	91.37 300	82.81 172	95.72 321	84.04 258	73.70 335	91.29 307

DP-MVS		88.75 237	86.56 256	95.34 145	98.92 77	87.45 213	97.64 254	93.52 351	70.55 375	81.49 294	97.25 165	74.43 244	99.88 54	71.14 349	94.09 174	98.67 156

3Dnovator+	87.72 8	93.43 137	91.84 160	98.17 23	95.73 200	95.08 34	98.92 132	97.04 186	91.42 109	81.48 295	97.60 148	74.60 241	99.79 82	90.84 173	98.97 82	99.64 64

QAPM		91.41 181	89.49 202	97.17 58	95.66 203	93.42 72	98.60 168	97.51 133	80.92 336	81.39 296	97.41 158	72.89 261	99.87 58	82.33 274	98.68 97	98.21 182

testing3		87.75 253	88.22 232	86.36 337	94.66 247	77.41 353	99.52 51	97.95 54	86.05 254	81.12 297	96.69 198	86.18 120	89.31 385	61.65 379	90.12 232	92.35 268

XXY-MVS		87.75 253	86.02 263	92.95 221	90.46 327	89.70 160	97.71 250	95.90 267	84.02 285	80.95 298	94.05 245	67.51 302	97.10 250	85.16 238	78.41 301	92.04 282

v148		86.38 277	85.06 277	90.37 283	89.47 343	84.10 287	98.52 175	95.48 293	83.80 290	80.93 299	90.22 334	74.60 241	96.31 294	80.92 285	71.55 355	90.69 325

DIV-MVS_self_test		87.82 250	86.81 253	90.87 267	94.87 241	85.39 267	97.81 240	95.22 313	82.92 309	80.76 300	91.31 302	81.99 190	95.81 319	81.36 281	75.04 320	91.42 301

cl____		87.82 250	86.79 254	90.89 266	94.88 240	85.43 265	97.81 240	95.24 308	82.91 310	80.71 301	91.22 303	81.97 192	95.84 317	81.34 282	75.06 319	91.40 302

FMVSNet2		86.90 265	84.79 284	93.24 214	95.11 227	92.54 92	97.67 253	95.86 273	82.94 306	80.55 302	91.17 305	62.89 329	95.29 333	77.23 309	79.71 298	91.90 284

pmmvs4		87.58 259	86.17 262	91.80 246	89.58 339	88.92 181	97.25 267	95.28 304	82.54 314	80.49 303	93.17 272	75.62 236	96.05 306	82.75 270	78.90 299	90.42 330

ACMP	87.39 10	88.71 238	88.24 231	90.12 287	93.91 269	81.06 329	98.50 179	95.67 283	89.43 163	80.37 304	95.55 224	65.67 314	97.83 207	90.55 178	84.51 262	91.47 297
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
pmmvs5		85.87 283	84.40 294	90.30 284	88.53 353	84.23 284	98.60 168	93.71 347	81.53 328	80.29 305	92.02 286	64.51 322	95.52 326	82.04 278	78.34 302	91.15 310

test0.0.03 1		88.96 226	88.61 222	90.03 292	91.09 319	84.43 282	98.97 128	97.02 190	90.21 136	80.29 305	96.31 210	84.89 141	91.93 375	72.98 342	85.70 255	93.73 251

miper_lstm_enhance		86.90 265	86.20 261	89.00 316	94.53 249	81.19 326	96.74 289	95.24 308	82.33 319	80.15 307	90.51 327	81.99 190	94.68 347	80.71 287	73.58 337	91.12 311

jajsoiax		87.35 260	86.51 257	89.87 294	87.75 363	81.74 316	97.03 276	95.98 251	88.47 187	80.15 307	93.80 256	61.47 334	96.36 286	89.44 192	84.47 264	91.50 296

mvs_tets		87.09 263	86.22 260	89.71 300	87.87 359	81.39 322	96.73 290	95.90 267	88.19 203	79.99 309	93.61 261	59.96 341	96.31 294	89.40 193	84.34 265	91.43 300

ITE_SJBPF				87.93 324	92.26 298	76.44 356		93.47 352	87.67 223	79.95 310	95.49 227	56.50 353	97.38 240	75.24 324	82.33 285	89.98 341

v8		86.11 280	84.45 291	91.10 259	89.99 331	86.85 227	97.24 268	95.36 302	81.99 323	79.89 311	89.86 339	74.53 243	96.39 284	78.83 301	72.32 349	90.05 339

v10		85.73 289	84.01 297	90.87 267	90.03 330	86.73 229	97.20 271	95.22 313	81.25 331	79.85 312	89.75 340	73.30 255	96.28 298	76.87 313	72.64 345	89.61 347

WR-MVS_H		86.53 274	85.49 272	89.66 303	91.04 320	83.31 298	97.53 257	98.20 36	84.95 274	79.64 313	90.90 309	78.01 226	95.33 332	76.29 318	72.81 343	90.35 331

anonymousdsp		86.69 269	85.75 268	89.53 305	86.46 371	82.94 301	96.39 297	95.71 279	83.97 287	79.63 314	90.70 314	68.85 288	95.94 311	86.01 228	84.02 269	89.72 345

Patchmtry		83.61 315	81.64 315	89.50 306	93.36 284	82.84 306	84.10 389	94.20 340	69.47 381	79.57 315	86.88 363	84.43 146	94.78 344	68.48 359	74.30 329	90.88 317

CP-MVSNet		86.54 273	85.45 273	89.79 298	91.02 321	82.78 307	97.38 261	97.56 122	85.37 264	79.53 316	93.03 274	71.86 270	95.25 334	79.92 292	73.43 341	91.34 304

Patchmatch-test		86.25 279	84.06 296	92.82 222	94.42 250	82.88 305	82.88 393	94.23 339	71.58 371	79.39 317	90.62 320	89.00 62	96.42 283	63.03 375	91.37 221	99.16 110

DSMNet-mixed		81.60 324	81.43 318	82.10 360	84.36 377	60.79 389	93.63 342	86.74 393	79.00 343	79.32 318	87.15 361	63.87 325	89.78 383	66.89 365	91.92 203	95.73 242

MSDG		88.29 246	86.37 258	94.04 199	96.90 152	86.15 247	96.52 294	94.36 336	77.89 353	79.22 319	96.95 183	69.72 283	99.59 104	73.20 341	92.58 191	96.37 236

Anonymous20231211		84.72 299	82.65 310	90.91 264	97.71 111	84.55 281	97.28 265	96.67 202	66.88 388	79.18 320	90.87 310	58.47 345	96.60 268	82.61 272	74.20 331	91.59 294

PS-CasMVS		85.81 286	84.58 289	89.49 308	90.77 323	82.11 313	97.20 271	97.36 156	84.83 276	79.12 321	92.84 277	67.42 303	95.16 336	78.39 305	73.25 342	91.21 309

IterMVS		85.81 286	84.67 287	89.22 311	93.51 279	83.67 293	96.32 300	94.80 322	85.09 269	78.69 322	90.17 337	66.57 310	93.17 360	79.48 295	77.42 310	90.81 318
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PEN-MVS		85.21 294	83.93 298	89.07 315	89.89 334	81.31 324	97.09 274	97.24 164	84.45 281	78.66 323	92.68 279	68.44 292	94.87 341	75.98 320	70.92 358	91.04 313

IterMVS-SCA-FT		85.73 289	84.64 288	89.00 316	93.46 282	82.90 303	96.27 301	94.70 325	85.02 272	78.62 324	90.35 329	66.61 308	93.33 357	79.38 296	77.36 311	90.76 322

OpenMVS	85.28 14	90.75 196	88.84 216	96.48 95	93.58 278	93.51 70	98.80 142	97.41 151	82.59 312	78.62 324	97.49 154	68.00 297	99.82 76	84.52 249	98.55 103	96.11 239

PVSNet_0	83.28 16	87.31 261	85.16 276	93.74 208	94.78 243	84.59 280	98.91 133	98.69 21	89.81 150	78.59 326	93.23 270	61.95 333	99.34 134	94.75 119	55.72 390	97.30 206

EU-MVSNet		84.19 308	84.42 293	83.52 355	88.64 352	67.37 384	96.04 311	95.76 277	85.29 265	78.44 327	93.18 271	70.67 278	91.48 377	75.79 322	75.98 314	91.70 286

v7n		84.42 306	82.75 308	89.43 309	88.15 356	81.86 315	96.75 288	95.67 283	80.53 337	78.38 328	89.43 344	69.89 281	96.35 291	73.83 337	72.13 351	90.07 337

FMVSNet1		83.94 312	81.32 320	91.80 246	91.94 306	88.81 183	96.77 285	95.25 305	77.98 349	78.25 329	90.25 331	50.37 375	94.97 338	73.27 340	77.81 308	91.62 289

D2MVS		87.96 249	87.39 243	89.70 301	91.84 308	83.40 296	98.31 204	98.49 23	88.04 208	78.23 330	90.26 330	73.57 251	96.79 263	84.21 252	83.53 275	88.90 355

MS-PatchMatch		86.75 268	85.92 265	89.22 311	91.97 303	82.47 311	96.91 280	96.14 241	83.74 291	77.73 331	93.53 264	58.19 346	97.37 242	76.75 315	98.35 107	87.84 361

DTE-MVSNet		84.14 309	82.80 305	88.14 323	88.95 348	79.87 335	96.81 284	96.24 232	83.50 296	77.60 332	92.52 281	67.89 299	94.24 352	72.64 345	69.05 361	90.32 332

COLMAP_ROB	82.69 18	84.54 303	82.82 304	89.70 301	96.72 160	78.85 341	95.89 314	92.83 358	71.55 372	77.54 333	95.89 220	59.40 343	99.14 145	67.26 363	88.26 237	91.11 312
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		84.13 310	83.59 300	85.77 342	87.81 360	70.24 378	94.89 329	93.65 349	86.08 253	76.53 334	93.28 269	61.41 335	96.14 303	80.95 284	77.69 309	90.93 315

tfpnnormal		83.65 313	81.35 319	90.56 276	91.37 316	88.06 197	97.29 264	97.87 58	78.51 348	76.20 335	90.91 308	64.78 321	96.47 280	61.71 378	73.50 338	87.13 370

ppachtmachnet_test		83.63 314	81.57 317	89.80 297	89.01 346	85.09 274	97.13 273	94.50 330	78.84 345	76.14 336	91.00 307	69.78 282	94.61 348	63.40 373	74.36 328	89.71 346

pm-mvs1		84.68 300	82.78 307	90.40 280	89.58 339	85.18 271	97.31 263	94.73 324	81.93 325	76.05 337	92.01 287	65.48 318	96.11 304	78.75 302	69.14 360	89.91 342

AllTest		84.97 297	83.12 302	90.52 277	96.82 154	78.84 342	95.89 314	92.17 366	77.96 351	75.94 338	95.50 225	55.48 356	99.18 139	71.15 347	87.14 241	93.55 253

TestCases				90.52 277	96.82 154	78.84 342		92.17 366	77.96 351	75.94 338	95.50 225	55.48 356	99.18 139	71.15 347	87.14 241	93.55 253

CL-MVSNet_self_test		79.89 332	78.34 333	84.54 350	81.56 385	75.01 360	96.88 282	95.62 285	81.10 332	75.86 340	85.81 368	68.49 291	90.26 379	63.21 374	56.51 388	88.35 358

testgi		82.29 319	81.00 322	86.17 339	87.24 366	74.84 362	97.39 259	91.62 374	88.63 183	75.85 341	95.42 228	46.07 382	91.55 376	66.87 366	79.94 296	92.12 278

MVP-Stereo		86.61 272	85.83 266	88.93 318	88.70 351	83.85 291	96.07 310	94.41 335	82.15 322	75.64 342	91.96 290	67.65 300	96.45 282	77.20 311	98.72 96	86.51 373
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LF4IMVS		81.94 322	81.17 321	84.25 351	87.23 367	68.87 383	93.35 344	91.93 371	83.35 299	75.40 343	93.00 275	49.25 379	96.65 267	78.88 300	78.11 303	87.22 369

our_test_3		84.47 305	82.80 305	89.50 306	89.01 346	83.90 290	97.03 276	94.56 329	81.33 330	75.36 344	90.52 326	71.69 272	94.54 349	68.81 357	76.84 312	90.07 337

LTVRE_ROB	81.71 19	84.59 302	82.72 309	90.18 285	92.89 292	83.18 299	93.15 345	94.74 323	78.99 344	75.14 345	92.69 278	65.64 315	97.63 225	69.46 354	81.82 288	89.74 344
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		80.76 327	79.42 331	84.79 348	84.78 376	72.98 368	96.53 293	92.97 355	79.56 342	74.33 346	88.83 347	61.27 336	92.15 372	60.59 381	75.92 315	89.24 352

FMVSNet5		82.29 319	80.54 323	87.52 328	93.79 275	84.01 288	93.73 340	92.47 362	76.92 356	74.27 347	86.15 367	63.69 327	89.24 386	69.07 356	74.79 323	89.29 351

MVS-HIRNet		79.01 335	75.13 347	90.66 272	93.82 274	81.69 317	85.16 383	93.75 346	54.54 393	74.17 348	59.15 399	57.46 349	96.58 271	63.74 372	94.38 171	93.72 252

ACMH+	83.78 15	84.21 307	82.56 312	89.15 313	93.73 276	79.16 339	96.43 296	94.28 338	81.09 333	74.00 349	94.03 248	54.58 362	97.67 221	76.10 319	78.81 300	90.63 327

KD-MVS_2432*1600		82.98 316	80.52 324	90.38 281	94.32 254	88.98 175	92.87 349	95.87 271	80.46 339	73.79 350	87.49 356	82.76 175	93.29 358	70.56 351	46.53 399	88.87 356

miper_refine_blended		82.98 316	80.52 324	90.38 281	94.32 254	88.98 175	92.87 349	95.87 271	80.46 339	73.79 350	87.49 356	82.76 175	93.29 358	70.56 351	46.53 399	88.87 356

NR-MVSNet		87.74 256	86.00 264	92.96 220	91.46 314	90.68 131	96.65 292	97.42 150	88.02 209	73.42 352	93.68 258	77.31 229	95.83 318	84.26 251	71.82 354	92.36 265

test_fmvs3		75.09 349	75.19 346	74.81 370	77.45 393	54.08 396	95.93 312	90.64 380	82.51 316	73.29 353	81.19 381	22.29 399	86.29 392	85.50 236	67.89 365	84.06 383

USDC		84.74 298	82.93 303	90.16 286	91.73 310	83.54 295	95.00 328	93.30 353	88.77 182	73.19 354	93.30 268	53.62 365	97.65 224	75.88 321	81.54 289	89.30 350

KD-MVS_self_test		77.47 344	75.88 344	82.24 358	81.59 384	68.93 382	92.83 351	94.02 343	77.03 355	73.14 355	83.39 373	55.44 358	90.42 378	67.95 360	57.53 387	87.38 365

LCM-MVSNet-Re		88.59 242	88.61 222	88.51 321	95.53 207	72.68 371	96.85 283	88.43 390	88.45 190	73.14 355	90.63 319	75.82 234	94.38 350	92.95 151	95.71 160	98.48 165

TDRefinement		78.01 341	75.31 345	86.10 340	70.06 400	73.84 365	93.59 343	91.58 375	74.51 365	73.08 357	91.04 306	49.63 378	97.12 247	74.88 327	59.47 383	87.33 367

TransMVSNet (Re)		81.97 321	79.61 330	89.08 314	89.70 337	84.01 288	97.26 266	91.85 372	78.84 345	73.07 358	91.62 295	67.17 305	95.21 335	67.50 362	59.46 384	88.02 360

SixPastTwentyTwo		82.63 318	81.58 316	85.79 341	88.12 357	71.01 376	95.17 327	92.54 361	84.33 282	72.93 359	92.08 284	60.41 340	95.61 325	74.47 330	74.15 332	90.75 323

pmmvs6		79.90 331	77.31 337	87.67 327	84.17 378	78.13 349	95.86 318	93.68 348	67.94 385	72.67 360	89.62 342	50.98 373	95.75 320	74.80 329	66.04 371	89.14 353

ACMH	83.09 17	84.60 301	82.61 311	90.57 274	93.18 288	82.94 301	96.27 301	94.92 318	81.01 334	72.61 361	93.61 261	56.54 352	97.79 210	74.31 331	81.07 290	90.99 314
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		78.63 339	76.90 340	83.82 353	82.82 382	72.86 369	95.72 323	93.57 350	73.55 369	72.17 362	84.79 370	49.69 377	92.51 368	65.29 370	74.50 325	86.09 375

Patchmatch-RL test		81.90 323	80.13 326	87.23 332	80.71 387	70.12 380	84.07 390	88.19 391	83.16 302	70.57 363	82.18 378	87.18 93	92.59 366	82.28 275	62.78 377	98.98 125

mvsany_test3		75.85 348	74.52 350	79.83 365	73.53 397	60.64 390	91.73 359	87.87 392	83.91 289	70.55 364	82.52 375	31.12 394	93.66 354	86.66 223	62.83 376	85.19 381

test_0402		78.81 337	76.33 342	86.26 338	91.18 318	78.44 347	95.88 316	91.34 377	68.55 382	70.51 365	89.91 338	52.65 368	94.99 337	47.14 394	79.78 297	85.34 379

TinyColmap		80.42 329	77.94 334	87.85 325	92.09 301	78.58 345	93.74 339	89.94 383	74.99 362	69.77 366	91.78 293	46.09 381	97.58 229	65.17 371	77.89 304	87.38 365

dmvs_testset		77.17 345	78.99 332	71.71 373	87.25 365	38.55 410	91.44 363	81.76 401	85.77 258	69.49 367	95.94 219	69.71 284	84.37 393	52.71 392	76.82 313	92.21 273

test20.03		78.51 340	77.48 336	81.62 362	83.07 381	71.03 375	96.11 309	92.83 358	81.66 327	69.31 368	89.68 341	57.53 348	87.29 391	58.65 385	68.47 362	86.53 372

test_vis1_rt		81.31 325	80.05 328	85.11 344	91.29 317	70.66 377	98.98 127	77.39 405	85.76 259	68.80 369	82.40 376	36.56 392	99.44 119	92.67 157	86.55 246	85.24 380

N_pmnet		70.19 355	69.87 357	71.12 375	88.24 355	30.63 414	95.85 319	28.70 413	70.18 377	68.73 370	86.55 365	64.04 324	93.81 353	53.12 391	73.46 339	88.94 354

OpenMVS_ROB	73.86 20	77.99 342	75.06 348	86.77 335	83.81 380	77.94 351	96.38 298	91.53 376	67.54 386	68.38 371	87.13 362	43.94 383	96.08 305	55.03 389	81.83 287	86.29 374

ambc				79.60 366	72.76 399	56.61 393	76.20 397	92.01 370		68.25 372	80.23 385	23.34 398	94.73 345	73.78 338	60.81 381	87.48 364

PM-MVS		74.88 350	72.85 353	80.98 364	78.98 391	64.75 387	90.81 370	85.77 394	80.95 335	68.23 373	82.81 374	29.08 396	92.84 362	76.54 317	62.46 379	85.36 378

pmmvs3		72.86 353	69.76 358	82.17 359	73.86 396	74.19 364	94.20 335	89.01 388	64.23 392	67.72 374	80.91 384	41.48 387	88.65 388	62.40 376	54.02 392	83.68 385

lessismore_v0				85.08 345	85.59 374	69.28 381		90.56 381		67.68 375	90.21 335	54.21 364	95.46 328	73.88 335	62.64 378	90.50 329

K. test v3		81.04 326	79.77 329	84.83 347	87.41 364	70.23 379	95.60 324	93.93 344	83.70 293	67.51 376	89.35 345	55.76 354	93.58 356	76.67 316	68.03 364	90.67 326

MIMVSNet1		75.92 347	73.30 352	83.81 354	81.29 386	75.57 358	92.26 354	92.05 369	73.09 370	67.48 377	86.18 366	40.87 389	87.64 390	55.78 388	70.68 359	88.21 359

ET-MVSNet_ETH3D		92.56 160	91.45 168	95.88 127	96.39 173	94.13 60	99.46 60	96.97 194	92.18 93	66.94 378	98.29 124	94.65 14	94.28 351	94.34 128	83.82 273	99.24 104

pmmvs-eth3d		78.71 338	76.16 343	86.38 336	80.25 389	81.19 326	94.17 336	92.13 368	77.97 350	66.90 379	82.31 377	55.76 354	92.56 367	73.63 339	62.31 380	85.38 377

EG-PatchMatch MVS		79.92 330	77.59 335	86.90 334	87.06 368	77.90 352	96.20 308	94.06 342	74.61 364	66.53 380	88.76 348	40.40 390	96.20 299	67.02 364	83.66 274	86.61 371

test_method		70.10 356	68.66 359	74.41 372	86.30 373	55.84 394	94.47 331	89.82 384	35.18 401	66.15 381	84.75 371	30.54 395	77.96 402	70.40 353	60.33 382	89.44 349

UnsupCasMVSNet_eth		78.90 336	76.67 341	85.58 343	82.81 383	74.94 361	91.98 356	96.31 226	84.64 278	65.84 382	87.71 352	51.33 370	92.23 371	72.89 343	56.50 389	89.56 348

test_f		71.94 354	70.82 355	75.30 369	72.77 398	53.28 397	91.62 360	89.66 386	75.44 361	64.47 383	78.31 389	20.48 400	89.56 384	78.63 303	66.02 372	83.05 388

new-patchmatchnet		74.80 351	72.40 354	81.99 361	78.36 392	72.20 372	94.44 332	92.36 363	77.06 354	63.47 384	79.98 386	51.04 372	88.85 387	60.53 382	54.35 391	84.92 382

new_pmnet		76.02 346	73.71 351	82.95 356	83.88 379	72.85 370	91.26 366	92.26 365	70.44 376	62.60 385	81.37 380	47.64 380	92.32 370	61.85 377	72.10 352	83.68 385

UnsupCasMVSNet_bld		73.85 352	70.14 356	84.99 346	79.44 390	75.73 357	88.53 376	95.24 308	70.12 378	61.94 386	74.81 392	41.41 388	93.62 355	68.65 358	51.13 396	85.62 376

CMPMVS	58.40 21	80.48 328	80.11 327	81.59 363	85.10 375	59.56 391	94.14 337	95.95 256	68.54 383	60.71 387	93.31 267	55.35 359	97.87 205	83.06 268	84.85 261	87.33 367
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
APD_test1		68.93 357	66.98 360	74.77 371	80.62 388	53.15 398	87.97 377	85.01 396	53.76 394	59.26 388	87.52 355	25.19 397	89.95 380	56.20 387	67.33 368	81.19 389

DeepMVS_CX				76.08 368	90.74 324	51.65 401		90.84 379	86.47 250	57.89 389	87.98 350	35.88 393	92.60 365	65.77 369	65.06 374	83.97 384

WB-MVS		66.44 358	66.29 361	66.89 378	74.84 394	44.93 405	93.00 346	84.09 399	71.15 373	55.82 390	81.63 379	63.79 326	80.31 400	21.85 404	50.47 397	75.43 391

SSC-MVS		65.42 359	65.20 362	66.06 379	73.96 395	43.83 406	92.08 355	83.54 400	69.77 379	54.73 391	80.92 383	63.30 328	79.92 401	20.48 405	48.02 398	74.44 392

YYNet1		79.64 334	77.04 339	87.43 331	87.80 361	79.98 334	96.23 305	94.44 331	73.83 368	51.83 392	87.53 354	67.96 298	92.07 374	66.00 368	67.75 367	90.23 334

MDA-MVSNet_test_wron		79.65 333	77.05 338	87.45 330	87.79 362	80.13 333	96.25 304	94.44 331	73.87 367	51.80 393	87.47 358	68.04 296	92.12 373	66.02 367	67.79 366	90.09 335

LCM-MVSNet		60.07 363	56.37 365	71.18 374	54.81 409	48.67 402	82.17 394	89.48 387	37.95 399	49.13 394	69.12 393	13.75 407	81.76 394	59.28 383	51.63 395	83.10 387

MDA-MVSNet-bldmvs		77.82 343	74.75 349	87.03 333	88.33 354	78.52 346	96.34 299	92.85 357	75.57 360	48.87 395	87.89 351	57.32 350	92.49 369	60.79 380	64.80 375	90.08 336

PMMVS2		58.97 364	55.07 367	70.69 376	62.72 404	55.37 395	85.97 381	80.52 402	49.48 395	45.94 396	68.31 394	15.73 405	80.78 398	49.79 393	37.12 401	75.91 390

testf1		56.38 365	53.73 368	64.31 382	64.84 402	45.11 403	80.50 395	75.94 407	38.87 397	42.74 397	75.07 390	11.26 409	81.19 396	41.11 397	53.27 393	66.63 396

APD_test2		56.38 365	53.73 368	64.31 382	64.84 402	45.11 403	80.50 395	75.94 407	38.87 397	42.74 397	75.07 390	11.26 409	81.19 396	41.11 397	53.27 393	66.63 396

FPMVS		61.57 360	60.32 363	65.34 380	60.14 407	42.44 408	91.02 369	89.72 385	44.15 396	42.63 399	80.93 382	19.02 401	80.59 399	42.50 396	72.76 344	73.00 393

test_vis3_rt		61.29 361	58.75 364	68.92 377	67.41 401	52.84 399	91.18 368	59.23 412	66.96 387	41.96 400	58.44 400	11.37 408	94.72 346	74.25 332	57.97 386	59.20 399

Gipuma		54.77 367	52.22 371	62.40 384	86.50 370	59.37 392	50.20 402	90.35 382	36.52 400	41.20 401	49.49 402	18.33 403	81.29 395	32.10 401	65.34 373	46.54 402
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		53.66 368	52.86 370	56.05 385	32.75 413	41.97 409	73.42 399	76.12 406	21.91 406	39.68 402	96.39 207	42.59 386	65.10 405	78.00 306	14.92 406	61.08 398

E-PMN		41.02 372	40.93 374	41.29 388	61.97 405	33.83 411	84.00 391	65.17 410	27.17 403	27.56 403	46.72 404	17.63 404	60.41 407	19.32 406	18.82 403	29.61 403

ANet_high		50.71 369	46.17 372	64.33 381	44.27 411	52.30 400	76.13 398	78.73 403	64.95 390	27.37 404	55.23 401	14.61 406	67.74 404	36.01 400	18.23 404	72.95 394

EMVS		39.96 373	39.88 375	40.18 389	59.57 408	32.12 413	84.79 388	64.57 411	26.27 404	26.14 405	44.18 407	18.73 402	59.29 408	17.03 407	17.67 405	29.12 404

MVE	44.00 22	41.70 371	37.64 376	53.90 387	49.46 410	43.37 407	65.09 401	66.66 409	26.19 405	25.77 406	48.53 403	3.58 413	63.35 406	26.15 403	27.28 402	54.97 401
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	41.42 23	45.67 370	42.50 373	55.17 386	34.28 412	32.37 412	66.24 400	78.71 404	30.72 402	22.04 407	59.59 398	4.59 411	77.85 403	27.49 402	58.84 385	55.29 400
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		18.81 375	23.05 378	6.10 392	4.48 414	2.29 417	97.78 242	3.00 415	3.27 408	18.60 408	62.71 396	1.53 415	2.49 411	14.26 409	1.80 408	13.50 406

test123		16.58 377	19.47 379	7.91 391	3.59 415	5.37 416	94.32 333	1.39 416	2.49 409	13.98 409	44.60 406	2.91 414	2.65 410	11.35 410	0.57 409	15.70 405

wuyk23d		16.71 376	16.73 380	16.65 390	60.15 406	25.22 415	41.24 403	5.17 414	6.56 407	5.48 410	3.61 410	3.64 412	22.72 409	15.20 408	9.52 407	1.99 407

EGC-MVSNET		60.70 362	55.37 366	76.72 367	86.35 372	71.08 374	89.96 374	84.44 398	0.38 410	1.50 411	84.09 372	37.30 391	88.10 389	40.85 399	73.44 340	70.97 395

test_blank		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet_test		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

DCPMVS		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

cdsmvs_eth3d_5k		22.52 374	30.03 377	0.00 393	0.00 416	0.00 418	0.00 404	97.17 173	0.00 411	0.00 412	98.77 87	74.35 246	0.00 412	0.00 411	0.00 410	0.00 408

pcd_1.5k_mvsjas		6.87 379	9.16 382	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	82.48 181	0.00 412	0.00 411	0.00 410	0.00 408

sosnet-low-res		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uncertanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

Regformer		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

ab-mvs-re		8.21 378	10.94 381	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	98.50 110	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

WAC-MVS						79.74 336								67.75 361

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					0.00 416

eth-test					0.00 416

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 18				99.19 32	95.12 8	99.97 21	99.90 1	99.92 3	99.99 1

save fliter					99.34 50	93.85 64	99.65 36	97.63 107	95.69 22

test_0728_SECOND				98.77 8	99.66 12	96.37 14	99.72 24	97.68 90					99.98 9	99.64 7	99.82 19	99.96 10

GSMVS																98.84 140

sam_mvs1												88.39 68				98.84 140

sam_mvs												87.08 96

MTGPA								97.45 144

test_post1							90.74 372				41.37 408	85.38 135	96.36 286	83.16 265

test_post											46.00 405	87.37 87	97.11 248

patchmatchnet-post											84.86 369	88.73 65	96.81 261

MTMP							99.21 89	91.09 378

gm-plane-assit					94.69 245	88.14 195			88.22 202		97.20 168		98.29 182	90.79 175

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 98	99.41 69

test_prior				97.01 62	99.58 30	91.77 101		97.57 121					99.49 112			99.79 36

新几何2							98.26 207

旧先验1					98.97 73	92.90 86		97.74 77			99.15 41	91.05 34			99.33 64	99.60 69

无先验							98.52 175	97.82 65	87.20 230				99.90 50	87.64 212		99.85 30

原ACMM2							98.69 154

testdata2													99.88 54	84.16 253

segment_acmp												90.56 43

testdata1							97.89 235		92.43 84

plane_prior7					93.84 271	85.73 260

plane_prior6					93.92 268	86.02 253						72.92 259

plane_prior5								96.30 227					97.75 218	93.46 144	86.17 250	92.67 260

plane_prior4											96.52 201

plane_prior2							99.02 121		93.38 68

plane_prior1					93.90 270

plane_prior						86.07 251	99.14 106		93.81 60						86.26 249

n2								0.00 417

nn								0.00 417

door-mid								84.90 397

test11								97.68 90

door								85.30 395

HQP5-MVS						86.39 236

BP-MVS														93.82 137

HQP3-MVS								96.37 223							86.29 247

HQP2-MVS												73.34 253

NP-MVS					93.94 267	86.22 243					96.67 199

ACMMP++_ref															82.64 283

ACMMP++															83.83 271

Test By Simon												83.62 155

High-resolution multi-view benchmark