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 14	97.72 12	97.41 50	97.51 128	92.78 92	99.85 8	98.05 46	96.78 8	99.60 1	99.23 29	90.42 50	99.92 41	99.55 13	98.50 108	99.55 77

fmvsm_l_conf0.5_n_a		97.70 13	97.80 11	97.42 49	97.59 123	92.91 90	99.86 5	98.04 48	96.70 10	99.58 2	99.26 24	90.90 41	99.94 35	99.57 12	98.66 103	99.40 93

IU-MVS					99.63 18	95.38 24		97.73 82	95.54 26	99.54 3				99.69 7	99.81 23	99.99 1

PC_three_1452									94.60 37	99.41 4	99.12 49	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 10	99.80 4	96.19 15	99.80 16	97.99 52	97.05 6	99.41 4	99.59 2	92.89 26	100.00 1	98.99 25	99.90 7	99.96 10

patch_mono-2		97.10 26	97.97 8	94.49 185	99.21 61	83.73 301	99.62 38	98.25 31	95.28 30	99.38 6	98.91 78	92.28 31	99.94 35	99.61 10	99.22 74	99.78 41

test0726					99.66 12	95.20 32	99.77 18	97.70 88	93.95 49	99.35 7	99.54 3	93.18 23

SED-MVS		98.18 2	98.10 4	98.41 18	99.63 18	95.24 27	99.77 18	97.72 83	94.17 44	99.30 8	99.54 3	93.32 20	99.98 9	99.70 5	99.81 23	99.99 1

test_241102_ONE					99.63 18	95.24 27		97.72 83	94.16 46	99.30 8	99.49 9	93.32 20	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 92	93.01 74	99.23 10	99.45 14	95.12 8	99.98 9	99.25 18	99.92 3	99.97 7

test_241102_TWO								97.72 83	94.17 44	99.23 10	99.54 3	93.14 25	99.98 9	99.70 5	99.82 19	99.99 1

SMA-MVS		97.24 20	96.99 24	98.00 31	99.30 54	94.20 61	99.16 98	97.65 104	89.55 166	99.22 12	99.52 8	90.34 53	99.99 5	98.32 47	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 62	96.19 48	95.31 155	96.51 173	89.01 180	99.81 12	98.39 26	95.46 28	99.19 13	99.16 39	81.44 210	99.91 46	98.83 28	96.97 144	97.01 228

test_fmvsm_n_1920		97.08 27	97.55 14	95.67 141	97.94 110	89.61 167	99.93 1	98.48 23	97.08 5	99.08 14	99.13 47	88.17 82	99.93 39	99.11 23	99.06 80	97.47 212

DVP-MVS		98.07 7	98.00 6	98.29 19	99.66 12	95.20 32	99.72 24	97.47 143	93.95 49	99.07 15	99.46 10	93.18 23	99.97 21	99.64 8	99.82 19	99.69 58
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 74	99.07 15	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 17	97.39 52	99.12 65	93.49 74	98.52 179	97.50 138	94.46 39	98.99 17	98.64 102	91.58 33	99.08 151	98.49 40	99.83 15	99.60 73
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 90	95.15 84	95.18 160	92.06 315	88.94 184	99.29 82	97.53 129	94.46 39	98.98 18	98.99 63	79.99 219	99.85 67	98.24 51	96.86 147	96.73 233

PS-MVSNAJ		96.87 31	96.40 43	98.29 19	97.35 134	97.29 5	99.03 121	97.11 185	95.83 20	98.97 19	99.14 45	82.48 191	99.60 106	98.60 33	99.08 78	98.00 199

旧先验2							98.67 158		85.75 267	98.96 20			98.97 157	93.84 145

test_one_0601					99.59 28	94.89 37		97.64 105	93.14 73	98.93 21	99.45 14	93.45 18

fmvsm_s_conf0.5_n		96.19 54	96.49 40	95.30 156	97.37 133	89.16 172	99.86 5	98.47 24	95.68 23	98.87 22	99.15 42	82.44 195	99.92 41	99.14 21	97.43 135	96.83 232

xiu_mvs_v2_base		96.66 37	96.17 53	98.11 28	97.11 150	96.96 6	99.01 124	97.04 192	95.51 27	98.86 23	99.11 53	82.19 199	99.36 133	98.59 35	98.14 118	98.00 199

NCCC		98.12 5	98.11 3	98.13 25	99.76 6	94.46 53	99.81 12	97.88 58	96.54 13	98.84 24	99.46 10	92.55 28	99.98 9	98.25 50	99.93 1	99.94 18

SD-MVS		97.51 16	97.40 19	97.81 36	99.01 72	93.79 68	99.33 80	97.38 157	93.73 60	98.83 25	99.02 61	90.87 43	99.88 54	98.69 30	99.74 29	99.77 46
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
MVS_0304		97.81 9	97.51 15	98.74 9	98.97 73	96.57 11	99.91 2	98.17 36	97.45 3	98.76 26	98.97 65	86.69 116	99.96 28	99.72 3	98.92 90	99.69 58

SF-MVS		97.22 22	96.92 25	98.12 27	99.11 66	94.88 38	99.44 62	97.45 146	89.60 162	98.70 27	99.42 17	90.42 50	99.72 92	98.47 41	99.65 40	99.77 46

balanced_conf03		96.83 32	96.51 39	97.81 36	97.60 122	95.15 34	98.40 197	96.77 209	93.00 76	98.69 28	96.19 216	89.75 61	98.76 165	98.45 42	99.72 32	99.51 82

fmvsm_s_conf0.1_n		95.56 80	95.68 70	95.20 159	94.35 263	89.10 174	99.50 51	97.67 96	94.76 35	98.68 29	99.03 59	81.13 213	99.86 63	98.63 32	97.36 137	96.63 235

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 23	99.29 82	97.72 83	94.50 38	98.64 30	99.54 3	93.32 20	99.97 21	99.58 11	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 10	98.18 2	96.53 99	99.54 36	90.14 148	99.41 69	97.70 88	95.46 28	98.60 31	99.19 33	95.71 5	99.49 115	98.15 52	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	97.49 140	89.41 171	98.59 32	99.43 16	89.78 60	99.69 94	98.69 30	99.62 46

APD-MVS		96.95 29	96.72 35	97.63 41	99.51 41	93.58 70	99.16 98	97.44 150	90.08 149	98.59 32	99.07 54	89.06 67	99.42 126	97.92 55	99.66 39	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_vis1_n_1920		93.08 158	93.42 132	92.04 251	96.31 183	79.36 347	99.83 10	96.06 260	96.72 9	98.53 34	98.10 134	58.57 358	99.91 46	97.86 57	98.79 99	96.85 231

testdata				95.26 158	98.20 101	87.28 228		97.60 114	85.21 273	98.48 35	99.15 42	88.15 84	98.72 169	90.29 190	99.45 59	99.78 41

test_fmvsmconf_n		96.78 35	96.84 29	96.61 92	95.99 200	90.25 143	99.90 3	98.13 42	96.68 11	98.42 36	98.92 77	85.34 146	99.88 54	99.12 22	99.08 78	99.70 55

TEST9					99.57 33	93.17 80	99.38 72	97.66 97	89.57 164	98.39 37	99.18 36	90.88 42	99.66 97

train_agg		97.20 23	97.08 23	97.57 45	99.57 33	93.17 80	99.38 72	97.66 97	90.18 144	98.39 37	99.18 36	90.94 39	99.66 97	98.58 36	99.85 13	99.88 26

test_8					99.55 35	93.07 83	99.37 75	97.64 105	90.18 144	98.36 39	99.19 33	90.94 39	99.64 103

SPE-MVS-test		95.98 61	96.34 46	94.90 170	98.06 107	87.66 215	99.69 34	96.10 255	93.66 61	98.35 40	99.05 57	86.28 127	97.66 232	96.96 76	98.90 92	99.37 96

MM		97.76 11	97.39 20	98.86 5	98.30 97	96.83 7	99.81 12	99.13 9	97.66 2	98.29 41	98.96 70	85.84 136	99.90 50	99.72 3	98.80 96	99.85 30

HPM-MVS++		97.72 12	97.59 13	98.14 24	99.53 40	94.76 45	99.19 92	97.75 78	95.66 24	98.21 42	99.29 23	91.10 36	99.99 5	97.68 60	99.87 9	99.68 60

DPM-MVS		97.86 8	97.25 22	99.68 1	98.25 98	99.10 1	99.76 21	97.78 75	96.61 12	98.15 43	99.53 7	93.62 17	100.00 1	91.79 173	99.80 26	99.94 18

test_part2					99.54 36	95.42 22				98.13 44

SteuartSystems-ACMMP		97.25 19	97.34 21	97.01 66	97.38 132	91.46 113	99.75 22	97.66 97	94.14 48	98.13 44	99.26 24	92.16 32	99.66 97	97.91 56	99.64 42	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
FOURS1					99.50 42	88.94 184	99.55 44	97.47 143	91.32 115	98.12 46

test_prior2							99.57 42		91.43 112	98.12 46	98.97 65	90.43 49		98.33 46	99.81 23

CS-MVS		95.75 74	96.19 48	94.40 189	97.88 112	86.22 251	99.66 35	96.12 254	92.69 84	98.07 48	98.89 81	87.09 105	97.59 238	96.71 80	98.62 104	99.39 95

PHI-MVS		96.65 40	96.46 42	97.21 60	99.34 50	91.77 106	99.70 27	98.05 46	86.48 256	98.05 49	99.20 32	89.33 65	99.96 28	98.38 43	99.62 46	99.90 22

MVSFormer		94.71 108	94.08 109	96.61 92	95.05 243	94.87 39	97.77 249	96.17 251	86.84 245	98.04 50	98.52 110	85.52 138	95.99 318	89.83 193	98.97 86	98.96 133

lupinMVS		96.32 50	95.94 59	97.44 47	95.05 243	94.87 39	99.86 5	96.50 227	93.82 58	98.04 50	98.77 88	85.52 138	98.09 201	96.98 75	98.97 86	99.37 96

APDe-MVS		97.53 15	97.47 16	97.70 39	99.58 30	93.63 69	99.56 43	97.52 133	93.59 64	98.01 52	99.12 49	90.80 44	99.55 109	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 41	96.18 50	97.81 36	98.82 85	93.55 71	98.88 136	97.59 118	90.66 127	97.98 53	99.14 45	86.59 119	100.00 1	96.47 89	99.46 57	99.89 25

agg_prior					99.54 36	92.66 93		97.64 105		97.98 53			99.61 105

CDPH-MVS		96.56 44	96.18 50	97.70 39	99.59 28	93.92 65	99.13 109	97.44 150	89.02 179	97.90 55	99.22 30	88.90 72	99.49 115	94.63 133	99.79 27	99.68 60

MVSMamba_PlusPlus		95.73 76	95.15 84	97.44 47	97.28 139	94.35 59	98.26 212	96.75 210	83.09 310	97.84 56	95.97 224	89.59 63	98.48 182	97.86 57	99.73 31	99.49 85

EPNet		96.82 33	96.68 37	97.25 59	98.65 90	93.10 82	99.48 53	98.76 14	96.54 13	97.84 56	98.22 129	87.49 94	99.66 97	95.35 114	97.78 126	99.00 129
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		97.50 17	97.45 18	97.63 41	99.65 16	93.21 79	99.70 27	98.13 42	94.61 36	97.78 58	99.46 10	89.85 59	99.81 79	97.97 54	99.91 6	99.88 26

test12				97.83 35	99.33 53	94.45 54		97.55 125		97.56 59		88.60 76	99.50 114		99.71 36	99.55 77

xiu_mvs_v1_base_debu		94.73 105	93.98 112	96.99 68	95.19 229	95.24 27	98.62 165	96.50 227	92.99 77	97.52 60	98.83 85	72.37 277	99.15 144	97.03 72	96.74 148	96.58 238

xiu_mvs_v1_base		94.73 105	93.98 112	96.99 68	95.19 229	95.24 27	98.62 165	96.50 227	92.99 77	97.52 60	98.83 85	72.37 277	99.15 144	97.03 72	96.74 148	96.58 238

xiu_mvs_v1_base_debi		94.73 105	93.98 112	96.99 68	95.19 229	95.24 27	98.62 165	96.50 227	92.99 77	97.52 60	98.83 85	72.37 277	99.15 144	97.03 72	96.74 148	96.58 238

ZD-MVS					99.67 10	93.28 77		97.61 112	87.78 222	97.41 63	99.16 39	90.15 56	99.56 108	98.35 45	99.70 37

ETV-MVS		96.00 59	96.00 58	96.00 128	96.56 169	91.05 125	99.63 37	96.61 217	93.26 71	97.39 64	98.30 126	86.62 118	98.13 198	98.07 53	97.57 129	98.82 150

DeepPCF-MVS	93.56 1	96.55 45	97.84 10	92.68 238	98.71 89	78.11 360	99.70 27	97.71 87	98.18 1	97.36 65	99.76 1	90.37 52	99.94 35	99.27 16	99.54 54	99.99 1

test_vis1_n		90.40 212	90.27 202	90.79 278	91.55 326	76.48 366	99.12 111	94.44 345	94.31 42	97.34 66	96.95 186	43.60 400	99.42 126	97.57 62	97.60 128	96.47 242

EC-MVSNet		95.09 92	95.17 83	94.84 173	95.42 219	88.17 203	99.48 53	95.92 274	91.47 110	97.34 66	98.36 123	82.77 183	97.41 249	97.24 69	98.58 105	98.94 138

test_fmvsmconf0.1_n		95.94 65	95.79 67	96.40 106	92.42 309	89.92 159	99.79 17	96.85 204	96.53 15	97.22 68	98.67 100	82.71 187	99.84 69	98.92 27	98.98 85	99.43 92

CANet		97.00 28	96.49 40	98.55 12	98.86 84	96.10 16	99.83 10	97.52 133	95.90 19	97.21 69	98.90 79	82.66 188	99.93 39	98.71 29	98.80 96	99.63 70

CANet_DTU		94.31 119	93.35 134	97.20 61	97.03 155	94.71 48	98.62 165	95.54 304	95.61 25	97.21 69	98.47 119	71.88 282	99.84 69	88.38 213	97.46 134	97.04 226

test_cas_vis1_n_1920		93.86 132	93.74 125	94.22 197	95.39 222	86.08 257	99.73 23	96.07 259	96.38 17	97.19 71	97.78 141	65.46 333	99.86 63	96.71 80	98.92 90	96.73 233

VNet		95.08 93	94.26 101	97.55 46	98.07 106	93.88 66	98.68 156	98.73 17	90.33 141	97.16 72	97.43 160	79.19 229	99.53 112	96.91 78	91.85 215	99.24 109

GDP-MVS		96.05 58	95.63 75	97.31 54	95.37 223	94.65 50	99.36 76	96.42 232	92.14 98	97.07 73	98.53 108	93.33 19	98.50 177	91.76 174	96.66 151	98.78 155

region2R		96.30 51	96.17 53	96.70 87	99.70 7	90.31 142	99.46 59	97.66 97	90.55 134	97.07 73	99.07 54	86.85 111	99.97 21	95.43 112	99.74 29	99.81 35

原ACMM1				96.18 117	99.03 71	90.08 151		97.63 109	88.98 180	97.00 75	98.97 65	88.14 85	99.71 93	88.23 215	99.62 46	98.76 158

reproduce_model		96.57 43	96.75 34	96.02 126	98.93 80	88.46 200	98.56 176	97.34 163	93.18 72	96.96 76	99.35 21	88.69 75	99.80 81	98.53 37	99.21 77	99.79 38

HFP-MVS		96.42 47	96.26 47	96.90 75	99.69 8	90.96 128	99.47 55	97.81 69	90.54 135	96.88 77	99.05 57	87.57 92	99.96 28	95.65 104	99.72 32	99.78 41

XVS		96.47 46	96.37 44	96.77 80	99.62 22	90.66 136	99.43 66	97.58 120	92.41 91	96.86 78	98.96 70	87.37 97	99.87 58	95.65 104	99.43 61	99.78 41

X-MVStestdata		90.69 208	88.66 231	96.77 80	99.62 22	90.66 136	99.43 66	97.58 120	92.41 91	96.86 78	29.59 424	87.37 97	99.87 58	95.65 104	99.43 61	99.78 41

SR-MVS		96.13 55	96.16 55	96.07 123	99.42 47	89.04 176	98.59 173	97.33 164	90.44 138	96.84 80	99.12 49	86.75 113	99.41 129	97.47 63	99.44 60	99.76 48

TSAR-MVS + GP.		96.95 29	96.91 26	97.07 63	98.88 83	91.62 109	99.58 41	96.54 225	95.09 32	96.84 80	98.63 104	91.16 34	99.77 88	99.04 24	96.42 154	99.81 35

ACMMPR		96.28 52	96.14 57	96.73 84	99.68 9	90.47 140	99.47 55	97.80 71	90.54 135	96.83 82	99.03 59	86.51 123	99.95 32	95.65 104	99.72 32	99.75 49

test_fmvs1		92.35 171	92.94 146	90.57 283	97.19 143	75.43 372	99.55 44	94.97 329	95.20 31	96.82 83	97.57 154	59.59 356	99.84 69	97.30 67	98.29 117	96.46 243

PMMVS		93.62 141	93.90 120	92.79 233	96.79 164	81.40 329	98.85 137	96.81 205	91.25 117	96.82 83	98.15 133	77.02 245	98.13 198	93.15 160	96.30 158	98.83 149

reproduce-ours		96.66 37	96.80 32	96.22 113	98.95 77	89.03 178	98.62 165	97.38 157	93.42 66	96.80 85	99.36 19	88.92 70	99.80 81	98.51 38	99.26 71	99.82 32

our_new_method		96.66 37	96.80 32	96.22 113	98.95 77	89.03 178	98.62 165	97.38 157	93.42 66	96.80 85	99.36 19	88.92 70	99.80 81	98.51 38	99.26 71	99.82 32

PGM-MVS		95.85 68	95.65 73	96.45 102	99.50 42	89.77 163	98.22 215	98.90 13	89.19 174	96.74 87	98.95 73	85.91 135	99.92 41	93.94 142	99.46 57	99.66 64

jason		95.40 85	94.86 92	97.03 65	92.91 303	94.23 60	99.70 27	96.30 239	93.56 65	96.73 88	98.52 110	81.46 209	97.91 211	96.08 98	98.47 111	98.96 133
jason: jason.
新几何1				97.40 51	98.92 81	92.51 98		97.77 77	85.52 269	96.69 89	99.06 56	88.08 86	99.89 53	84.88 253	99.62 46	99.79 38

SR-MVS-dyc-post		95.75 74	95.86 62	95.41 150	99.22 59	87.26 231	98.40 197	97.21 173	89.63 160	96.67 90	98.97 65	86.73 115	99.36 133	96.62 83	99.31 67	99.60 73

RE-MVS-def			95.70 69		99.22 59	87.26 231	98.40 197	97.21 173	89.63 160	96.67 90	98.97 65	85.24 147		96.62 83	99.31 67	99.60 73

APD-MVS_3200maxsize		95.64 79	95.65 73	95.62 144	99.24 58	87.80 211	98.42 192	97.22 172	88.93 184	96.64 92	98.98 64	85.49 141	99.36 133	96.68 82	99.27 70	99.70 55

mvsany_test1		94.57 113	95.09 88	92.98 228	95.84 205	82.07 323	98.76 149	95.24 322	92.87 82	96.45 93	98.71 97	84.81 153	99.15 144	97.68 60	95.49 172	97.73 204

MG-MVS		97.24 20	96.83 31	98.47 15	99.79 5	95.71 19	99.07 115	99.06 10	94.45 41	96.42 94	98.70 98	88.81 73	99.74 91	95.35 114	99.86 12	99.97 7

BP-MVS1		96.59 41	96.36 45	97.29 55	95.05 243	94.72 47	99.44 62	97.45 146	92.71 83	96.41 95	98.50 112	94.11 16	98.50 177	95.61 109	97.97 120	98.66 166

test_fmvs1_n		91.07 199	91.41 179	90.06 297	94.10 271	74.31 376	99.18 94	94.84 333	94.81 33	96.37 96	97.46 158	50.86 389	99.82 76	97.14 71	97.90 121	96.04 250

h-mvs33		92.47 170	91.95 167	94.05 205	97.13 148	85.01 283	98.36 204	98.08 44	93.85 56	96.27 97	96.73 200	83.19 175	99.43 125	95.81 102	68.09 374	97.70 205

hse-mvs2		91.67 186	91.51 177	92.15 248	96.22 187	82.61 319	97.74 253	97.53 129	93.85 56	96.27 97	96.15 217	83.19 175	97.44 247	95.81 102	66.86 381	96.40 245

alignmvs		95.77 72	95.00 90	98.06 29	97.35 134	95.68 20	99.71 26	97.50 138	91.50 109	96.16 99	98.61 106	86.28 127	99.00 154	96.19 93	91.74 217	99.51 82

CP-MVS		96.22 53	96.15 56	96.42 104	99.67 10	89.62 166	99.70 27	97.61 112	90.07 150	96.00 100	99.16 39	87.43 95	99.92 41	96.03 99	99.72 32	99.70 55

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 4	95.96 101	99.33 22	92.62 27	100.00 1	98.99 25	99.93 1	99.98 6

diffmvs		94.59 112	94.19 104	95.81 135	95.54 215	90.69 134	98.70 154	95.68 296	91.61 105	95.96 101	97.81 138	80.11 218	98.06 203	96.52 88	95.76 167	98.67 163
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 62	95.66 71	96.90 75	99.49 45	91.22 115	99.45 61	97.48 141	89.69 158	95.89 103	98.72 94	86.37 126	99.95 32	94.62 134	99.22 74	99.52 80

DeepC-MVS_fast	93.52 2	97.16 24	96.84 29	98.13 25	99.61 24	94.45 54	98.85 137	97.64 105	96.51 16	95.88 104	99.39 18	87.35 101	99.99 5	96.61 85	99.69 38	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 96	91.21 116	98.08 232	97.58 120	83.74 298	95.87 105	99.02 61	86.74 114			99.64 42	99.81 35

sasdasda		95.02 94	93.96 115	98.20 21	97.53 126	95.92 17	98.71 151	96.19 248	91.78 102	95.86 106	98.49 115	79.53 224	99.03 152	96.12 95	91.42 229	99.66 64

ZNCC-MVS		96.09 56	95.81 65	96.95 74	99.42 47	91.19 117	99.55 44	97.53 129	89.72 157	95.86 106	98.94 76	86.59 119	99.97 21	95.13 120	99.56 52	99.68 60

canonicalmvs		95.02 94	93.96 115	98.20 21	97.53 126	95.92 17	98.71 151	96.19 248	91.78 102	95.86 106	98.49 115	79.53 224	99.03 152	96.12 95	91.42 229	99.66 64

dcpmvs_2		95.67 78	96.18 50	94.12 201	98.82 85	84.22 294	97.37 269	95.45 309	90.70 126	95.77 109	98.63 104	90.47 48	98.68 171	99.20 20	99.22 74	99.45 89

MGCFI-Net		94.89 96	93.84 122	98.06 29	97.49 129	95.55 21	98.64 162	96.10 255	91.60 107	95.75 110	98.46 121	79.31 228	98.98 156	95.95 101	91.24 233	99.65 67

Effi-MVS+		93.87 131	93.15 140	96.02 126	95.79 206	90.76 132	96.70 298	95.78 288	86.98 242	95.71 111	97.17 175	79.58 222	98.01 208	94.57 135	96.09 162	99.31 103

HPM-MVS_fast		94.89 96	94.62 94	95.70 139	99.11 66	88.44 201	99.14 106	97.11 185	85.82 264	95.69 112	98.47 119	83.46 168	99.32 138	93.16 159	99.63 45	99.35 99

HY-MVS	88.56 7	95.29 87	94.23 102	98.48 14	97.72 115	96.41 13	94.03 351	98.74 15	92.42 90	95.65 113	94.76 246	86.52 122	99.49 115	95.29 117	92.97 194	99.53 79

CHOSEN 280x420		96.80 34	96.85 28	96.66 91	97.85 113	94.42 56	94.76 342	98.36 28	92.50 87	95.62 114	97.52 155	97.92 1	97.38 250	98.31 48	98.80 96	98.20 193

test_fmvsmconf0.01_n		94.14 122	93.51 130	96.04 124	86.79 381	89.19 171	99.28 85	95.94 269	95.70 21	95.50 115	98.49 115	73.27 269	99.79 85	98.28 49	98.32 116	99.15 116

MP-MVS		96.00 59	95.82 63	96.54 98	99.47 46	90.13 150	99.36 76	97.41 154	90.64 130	95.49 116	98.95 73	85.51 140	99.98 9	96.00 100	99.59 51	99.52 80
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS		95.41 84	95.22 82	95.99 129	99.29 55	89.14 173	99.17 97	97.09 189	87.28 236	95.40 117	98.48 118	84.93 150	99.38 131	95.64 108	99.65 40	99.47 88
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UA-Net		93.30 150	92.62 153	95.34 153	96.27 185	88.53 199	95.88 325	96.97 200	90.90 122	95.37 118	97.07 179	82.38 196	99.10 150	83.91 269	94.86 178	98.38 178

sss		94.85 101	93.94 117	97.58 43	96.43 176	94.09 64	98.93 131	99.16 8	89.50 167	95.27 119	97.85 136	81.50 207	99.65 101	92.79 165	94.02 184	98.99 130

WTY-MVS		95.97 62	95.11 87	98.54 13	97.62 119	96.65 9	99.44 62	98.74 15	92.25 94	95.21 120	98.46 121	86.56 121	99.46 121	95.00 125	92.69 198	99.50 84

DELS-MVS		97.12 25	96.60 38	98.68 11	98.03 108	96.57 11	99.84 9	97.84 62	96.36 18	95.20 121	98.24 128	88.17 82	99.83 73	96.11 97	99.60 50	99.64 68
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 36	96.69 36	96.72 86	98.58 92	91.00 127	99.14 106	99.45 1	93.86 55	95.15 122	98.73 92	88.48 77	99.76 89	97.23 70	99.56 52	99.40 93

MVS_Test		93.67 139	92.67 151	96.69 88	96.72 166	92.66 93	97.22 277	96.03 261	87.69 228	95.12 123	94.03 254	81.55 205	98.28 190	89.17 207	96.46 152	99.14 117

MVS_111021_LR		95.78 71	95.94 59	95.28 157	98.19 103	87.69 212	98.80 143	99.26 7	93.39 68	95.04 124	98.69 99	84.09 160	99.76 89	96.96 76	99.06 80	98.38 178

CostFormer		92.89 160	92.48 156	94.12 201	94.99 246	85.89 264	92.89 361	97.00 198	86.98 242	95.00 125	90.78 323	90.05 58	97.51 243	92.92 163	91.73 218	98.96 133

testing222		94.48 116	94.00 111	95.95 131	97.30 136	92.27 100	98.82 140	97.92 56	89.20 173	94.82 126	97.26 166	87.13 104	97.32 253	91.95 171	91.56 221	98.25 187

mPP-MVS		95.90 67	95.75 68	96.38 107	99.58 30	89.41 170	99.26 87	97.41 154	90.66 127	94.82 126	98.95 73	86.15 131	99.98 9	95.24 119	99.64 42	99.74 50

EI-MVSNet-Vis-set		95.76 73	95.63 75	96.17 119	99.14 64	90.33 141	98.49 185	97.82 66	91.92 100	94.75 128	98.88 83	87.06 107	99.48 119	95.40 113	97.17 142	98.70 161

LFMVS		92.23 176	90.84 191	96.42 104	98.24 100	91.08 124	98.24 214	96.22 245	83.39 305	94.74 129	98.31 125	61.12 351	98.85 159	94.45 136	92.82 195	99.32 102

tpmrst		92.78 161	92.16 161	94.65 180	96.27 185	87.45 222	91.83 371	97.10 188	89.10 178	94.68 130	90.69 327	88.22 81	97.73 230	89.78 196	91.80 216	98.77 157

test_yl		95.27 88	94.60 95	97.28 57	98.53 93	92.98 86	99.05 119	98.70 18	86.76 248	94.65 131	97.74 144	87.78 89	99.44 122	95.57 110	92.61 199	99.44 90

DCV-MVSNet		95.27 88	94.60 95	97.28 57	98.53 93	92.98 86	99.05 119	98.70 18	86.76 248	94.65 131	97.74 144	87.78 89	99.44 122	95.57 110	92.61 199	99.44 90

testing11		95.33 86	94.98 91	96.37 108	97.20 141	92.31 99	99.29 82	97.68 92	90.59 131	94.43 133	97.20 171	90.79 45	98.60 174	95.25 118	92.38 203	98.18 194

DP-MVS Recon		95.85 68	95.15 84	97.95 32	99.87 2	94.38 57	99.60 39	97.48 141	86.58 251	94.42 134	99.13 47	87.36 100	99.98 9	93.64 149	98.33 114	99.48 86

ETVMVS		94.50 115	93.90 120	96.31 111	97.48 130	92.98 86	99.07 115	97.86 60	88.09 212	94.40 135	96.90 189	88.35 79	97.28 254	90.72 187	92.25 209	98.66 166

MTAPA		96.09 56	95.80 66	96.96 73	99.29 55	91.19 117	97.23 276	97.45 146	92.58 85	94.39 136	99.24 28	86.43 125	99.99 5	96.22 92	99.40 64	99.71 54

UBG		95.73 76	95.41 77	96.69 88	96.97 156	93.23 78	99.13 109	97.79 73	91.28 116	94.38 137	96.78 197	92.37 30	98.56 176	96.17 94	93.84 186	98.26 186

CPTT-MVS		94.60 111	94.43 99	95.09 163	99.66 12	86.85 236	99.44 62	97.47 143	83.22 307	94.34 138	98.96 70	82.50 189	99.55 109	94.81 128	99.50 55	98.88 143

PVSNet_BlendedMVS		93.36 148	93.20 139	93.84 213	98.77 87	91.61 110	99.47 55	98.04 48	91.44 111	94.21 139	92.63 288	83.50 166	99.87 58	97.41 64	83.37 285	90.05 350

PVSNet_Blended		95.94 65	95.66 71	96.75 82	98.77 87	91.61 110	99.88 4	98.04 48	93.64 63	94.21 139	97.76 142	83.50 166	99.87 58	97.41 64	97.75 127	98.79 153

EI-MVSNet-UG-set		95.43 82	95.29 80	95.86 134	99.07 70	89.87 160	98.43 191	97.80 71	91.78 102	94.11 141	98.77 88	86.25 129	99.48 119	94.95 127	96.45 153	98.22 191

EIA-MVS		95.11 91	95.27 81	94.64 182	96.34 182	86.51 240	99.59 40	96.62 216	92.51 86	94.08 142	98.64 102	86.05 132	98.24 193	95.07 122	98.50 108	99.18 114

mvsmamba		94.27 120	93.91 119	95.35 152	96.42 177	88.61 195	97.77 249	96.38 234	91.17 119	94.05 143	95.27 238	78.41 237	97.96 210	97.36 66	98.40 112	99.48 86

MAR-MVS		94.43 117	94.09 108	95.45 148	99.10 68	87.47 221	98.39 201	97.79 73	88.37 201	94.02 144	99.17 38	78.64 235	99.91 46	92.48 167	98.85 94	98.96 133
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 48	95.94 59	97.58 43	94.10 271	95.25 26	98.93 131	98.17 36	94.26 43	93.94 145	98.72 94	89.68 62	97.88 214	96.36 90	99.29 69	99.62 72

GG-mvs-BLEND				96.98 71	96.53 171	94.81 44	87.20 392	97.74 79		93.91 146	96.40 209	96.56 2	96.94 267	95.08 121	98.95 89	99.20 113

API-MVS		94.78 103	94.18 106	96.59 94	99.21 61	90.06 155	98.80 143	97.78 75	83.59 302	93.85 147	99.21 31	83.79 163	99.97 21	92.37 168	99.00 84	99.74 50

tpm2		91.77 184	91.09 184	93.82 214	94.83 253	85.56 272	92.51 366	97.16 180	84.00 293	93.83 148	90.66 329	87.54 93	97.17 256	87.73 221	91.55 222	98.72 159

PAPR		96.35 48	95.82 63	97.94 33	99.63 18	94.19 62	99.42 68	97.55 125	92.43 88	93.82 149	99.12 49	87.30 102	99.91 46	94.02 141	99.06 80	99.74 50

testing99		94.88 98	94.45 97	96.17 119	97.20 141	91.91 104	99.20 91	97.66 97	89.95 152	93.68 150	97.06 180	90.28 54	98.50 177	93.52 151	91.54 223	98.12 196

testing91		94.88 98	94.44 98	96.21 115	97.19 143	91.90 105	99.23 89	97.66 97	89.91 153	93.66 151	97.05 182	90.21 55	98.50 177	93.52 151	91.53 226	98.25 187

PVSNet	87.13 12	93.69 136	92.83 148	96.28 112	97.99 109	90.22 146	99.38 72	98.93 12	91.42 113	93.66 151	97.68 147	71.29 289	99.64 103	87.94 219	97.20 139	98.98 131

baseline		93.91 129	93.30 136	95.72 138	95.10 240	90.07 152	97.48 264	95.91 279	91.03 120	93.54 153	97.68 147	79.58 222	98.02 207	94.27 138	95.14 175	99.08 125

test2506		94.80 102	94.21 103	96.58 95	96.41 178	92.18 102	98.01 235	98.96 11	90.82 124	93.46 154	97.28 164	85.92 133	98.45 183	89.82 195	97.19 140	99.12 120

VDD-MVS		91.24 197	90.18 203	94.45 188	97.08 152	85.84 267	98.40 197	96.10 255	86.99 239	93.36 155	98.16 132	54.27 376	99.20 141	96.59 86	90.63 239	98.31 185

VDDNet		90.08 222	88.54 236	94.69 179	94.41 262	87.68 213	98.21 217	96.40 233	76.21 370	93.33 156	97.75 143	54.93 374	98.77 163	94.71 132	90.96 234	97.61 210

thisisatest0515		94.75 104	94.19 104	96.43 103	96.13 197	92.64 96	99.47 55	97.60 114	87.55 231	93.17 157	97.59 152	94.71 12	98.42 184	88.28 214	93.20 191	98.24 190

MP-MVS-pluss		95.80 70	95.30 79	97.29 55	98.95 77	92.66 93	98.59 173	97.14 181	88.95 182	93.12 158	99.25 26	85.62 137	99.94 35	96.56 87	99.48 56	99.28 106
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MDTV_nov1_ep13_2view						91.17 119	91.38 378		87.45 233	93.08 159		86.67 117		87.02 225		98.95 137

EPNet_dtu		92.28 174	92.15 162	92.70 237	97.29 137	84.84 286	98.64 162	97.82 66	92.91 80	93.02 160	97.02 183	85.48 143	95.70 333	72.25 357	94.89 177	97.55 211
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
gg-mvs-nofinetune		90.00 223	87.71 248	96.89 79	96.15 192	94.69 49	85.15 399	97.74 79	68.32 398	92.97 161	60.16 412	96.10 4	96.84 270	93.89 143	98.87 93	99.14 117

test_fmvsmvis_n_1920		95.47 81	95.40 78	95.70 139	94.33 264	90.22 146	99.70 27	96.98 199	96.80 7	92.75 162	98.89 81	82.46 194	99.92 41	98.36 44	98.33 114	96.97 229

casdiffmvs		93.98 127	93.43 131	95.61 145	95.07 242	89.86 161	98.80 143	95.84 287	90.98 121	92.74 163	97.66 149	79.71 221	98.10 200	94.72 131	95.37 173	98.87 145
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
RRT-MVS		93.39 146	92.64 152	95.64 142	96.11 198	88.75 192	97.40 265	95.77 290	89.46 169	92.70 164	95.42 235	72.98 271	98.81 161	96.91 78	96.97 144	99.37 96

114514_t		94.06 123	93.05 142	97.06 64	99.08 69	92.26 101	98.97 129	97.01 197	82.58 322	92.57 165	98.22 129	80.68 216	99.30 139	89.34 203	99.02 83	99.63 70

OMC-MVS		93.90 130	93.62 127	94.73 178	98.63 91	87.00 234	98.04 234	96.56 223	92.19 95	92.46 166	98.73 92	79.49 226	99.14 148	92.16 170	94.34 182	98.03 198

PAPM_NR		95.43 82	95.05 89	96.57 97	99.42 47	90.14 148	98.58 175	97.51 135	90.65 129	92.44 167	98.90 79	87.77 91	99.90 50	90.88 182	99.32 66	99.68 60

mmtdpeth		83.69 323	82.59 322	86.99 343	92.82 305	76.98 365	96.16 317	91.63 387	82.89 319	92.41 168	82.90 388	54.95 373	98.19 195	96.27 91	53.27 406	85.81 388

UGNet		91.91 183	90.85 190	95.10 162	97.06 153	88.69 194	98.01 235	98.24 33	92.41 91	92.39 169	93.61 268	60.52 353	99.68 95	88.14 216	97.25 138	96.92 230
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			90.47 201		96.14 194	88.55 197	91.34 379	97.51 135	89.58 163	92.24 170	90.50 340	86.99 110	97.61 237	77.64 318	92.34 205

FE-MVS		91.38 192	90.16 204	95.05 166	96.46 175	87.53 219	89.69 389	97.84 62	82.97 313	92.18 171	92.00 298	84.07 161	98.93 158	80.71 297	95.52 171	98.68 162

Vis-MVSNet		92.64 164	91.85 168	95.03 167	95.12 236	88.23 202	98.48 187	96.81 205	91.61 105	92.16 172	97.22 170	71.58 287	98.00 209	85.85 244	97.81 123	98.88 143
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
FA-MVS(test-final)		92.22 177	91.08 185	95.64 142	96.05 199	88.98 181	91.60 375	97.25 167	86.99 239	91.84 173	92.12 292	83.03 178	99.00 154	86.91 229	93.91 185	98.93 139

TESTMET0.1,1		93.82 133	93.26 138	95.49 147	95.21 228	90.25 143	99.15 103	97.54 128	89.18 175	91.79 174	94.87 244	89.13 66	97.63 235	86.21 237	96.29 159	98.60 168

thisisatest0530		94.00 125	93.52 129	95.43 149	95.76 208	90.02 157	98.99 126	97.60 114	86.58 251	91.74 175	97.36 163	94.78 11	98.34 186	86.37 235	92.48 202	97.94 201

UWE-MVS		93.18 154	93.40 133	92.50 241	96.56 169	83.55 303	98.09 231	97.84 62	89.50 167	91.72 176	96.23 215	91.08 37	96.70 276	86.28 236	93.33 190	97.26 218

AUN-MVS		90.17 219	89.50 212	92.19 246	96.21 188	82.67 317	97.76 252	97.53 129	88.05 213	91.67 177	96.15 217	83.10 177	97.47 244	88.11 217	66.91 380	96.43 244

EPMVS		92.59 167	91.59 175	95.59 146	97.22 140	90.03 156	91.78 372	98.04 48	90.42 139	91.66 178	90.65 330	86.49 124	97.46 245	81.78 290	96.31 157	99.28 106

test-LLR		93.11 157	92.68 150	94.40 189	94.94 249	87.27 229	99.15 103	97.25 167	90.21 142	91.57 179	94.04 252	84.89 151	97.58 239	85.94 241	96.13 160	98.36 182

test-mter		93.27 152	92.89 147	94.40 189	94.94 249	87.27 229	99.15 103	97.25 167	88.95 182	91.57 179	94.04 252	88.03 87	97.58 239	85.94 241	96.13 160	98.36 182

JIA-IIPM		85.97 291	84.85 291	89.33 318	93.23 299	73.68 379	85.05 400	97.13 183	69.62 394	91.56 181	68.03 410	88.03 87	96.96 265	77.89 317	93.12 192	97.34 215

casdiffmvs_mvg		94.00 125	93.33 135	96.03 125	95.22 227	90.90 130	99.09 113	95.99 262	90.58 132	91.55 182	97.37 162	79.91 220	98.06 203	95.01 124	95.22 174	99.13 119
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		94.67 109	94.11 107	96.34 110	97.14 147	91.10 122	99.32 81	97.43 152	92.10 99	91.53 183	96.38 212	83.29 172	99.68 95	93.42 156	96.37 155	98.25 187

CHOSEN 1792x2688		94.35 118	93.82 123	95.95 131	97.40 131	88.74 193	98.41 194	98.27 30	92.18 96	91.43 184	96.40 209	78.88 230	99.81 79	93.59 150	97.81 123	99.30 104

ACMMP		94.67 109	94.30 100	95.79 136	99.25 57	88.13 205	98.41 194	98.67 21	90.38 140	91.43 184	98.72 94	82.22 198	99.95 32	93.83 146	95.76 167	99.29 105
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		92.29 173	91.33 180	95.15 161	96.41 178	87.84 210	98.10 228	94.84 333	90.82 124	91.42 186	97.28 164	65.61 330	98.49 181	90.33 189	97.19 140	99.12 120

EPP-MVSNet		93.75 135	93.67 126	94.01 207	95.86 204	85.70 269	98.67 158	97.66 97	84.46 287	91.36 187	97.18 174	91.16 34	97.79 220	92.93 162	93.75 187	98.53 170

PLC	91.07 3	94.23 121	94.01 110	94.87 171	99.17 63	87.49 220	99.25 88	96.55 224	88.43 199	91.26 188	98.21 131	85.92 133	99.86 63	89.77 197	97.57 129	97.24 219
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HyFIR lowres test		93.68 138	93.29 137	94.87 171	97.57 125	88.04 207	98.18 219	98.47 24	87.57 230	91.24 189	95.05 242	85.49 141	97.46 245	93.22 158	92.82 195	99.10 123

thres200		93.69 136	92.59 154	96.97 72	97.76 114	94.74 46	99.35 78	99.36 2	89.23 172	91.21 190	96.97 185	83.42 169	98.77 163	85.08 249	90.96 234	97.39 214

test1111		92.12 178	91.19 183	94.94 169	96.15 192	87.36 225	98.12 225	94.84 333	90.85 123	90.97 191	97.26 166	65.60 331	98.37 185	89.74 198	97.14 143	99.07 127

CDS-MVSNet		93.47 142	93.04 143	94.76 175	94.75 255	89.45 169	98.82 140	97.03 194	87.91 219	90.97 191	96.48 207	89.06 67	96.36 295	89.50 199	92.81 197	98.49 172
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tfpn200view9		93.43 144	92.27 159	96.90 75	97.68 117	94.84 41	99.18 94	99.36 2	88.45 196	90.79 193	96.90 189	83.31 170	98.75 166	84.11 265	90.69 236	97.12 221

thres400		93.39 146	92.27 159	96.73 84	97.68 117	94.84 41	99.18 94	99.36 2	88.45 196	90.79 193	96.90 189	83.31 170	98.75 166	84.11 265	90.69 236	96.61 236

CR-MVSNet		88.83 242	87.38 253	93.16 225	93.47 292	86.24 249	84.97 401	94.20 354	88.92 185	90.76 195	86.88 377	84.43 156	94.82 354	70.64 361	92.17 211	98.41 175

RPMNet		85.07 305	81.88 324	94.64 182	93.47 292	86.24 249	84.97 401	97.21 173	64.85 405	90.76 195	78.80 403	80.95 215	99.27 140	53.76 404	92.17 211	98.41 175

PatchmatchNet		92.05 182	91.04 186	95.06 164	96.17 191	89.04 176	91.26 380	97.26 166	89.56 165	90.64 197	90.56 336	88.35 79	97.11 259	79.53 303	96.07 164	99.03 128
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tttt0517		93.30 150	93.01 144	94.17 199	95.57 213	86.47 242	98.51 182	97.60 114	85.99 262	90.55 198	97.19 173	94.80 10	98.31 187	85.06 250	91.86 214	97.74 203

PatchT		85.44 301	83.19 311	92.22 244	93.13 301	83.00 309	83.80 407	96.37 235	70.62 388	90.55 198	79.63 402	84.81 153	94.87 352	58.18 400	91.59 220	98.79 153

tpm		89.67 227	88.95 224	91.82 255	92.54 307	81.43 328	92.95 360	95.92 274	87.81 221	90.50 200	89.44 356	84.99 149	95.65 334	83.67 272	82.71 290	98.38 178

thres100view900		93.34 149	92.15 162	96.90 75	97.62 119	94.84 41	99.06 118	99.36 2	87.96 217	90.47 201	96.78 197	83.29 172	98.75 166	84.11 265	90.69 236	97.12 221

thres600view7		93.18 154	92.00 165	96.75 82	97.62 119	94.92 36	99.07 115	99.36 2	87.96 217	90.47 201	96.78 197	83.29 172	98.71 170	82.93 279	90.47 240	96.61 236

AdaColmap		93.82 133	93.06 141	96.10 122	99.88 1	89.07 175	98.33 206	97.55 125	86.81 247	90.39 203	98.65 101	75.09 251	99.98 9	93.32 157	97.53 132	99.26 108

XVG-OURS-SEG-HR		90.95 202	90.66 197	91.83 254	95.18 232	81.14 336	95.92 322	95.92 274	88.40 200	90.33 204	97.85 136	70.66 292	99.38 131	92.83 164	88.83 246	94.98 257

IS-MVSNet		93.00 159	92.51 155	94.49 185	96.14 194	87.36 225	98.31 209	95.70 294	88.58 192	90.17 205	97.50 156	83.02 179	97.22 255	87.06 224	96.07 164	98.90 142

CSCG		94.87 100	94.71 93	95.36 151	99.54 36	86.49 241	99.34 79	98.15 40	82.71 320	90.15 206	99.25 26	89.48 64	99.86 63	94.97 126	98.82 95	99.72 53

SCA		90.64 210	89.25 218	94.83 174	94.95 248	88.83 188	96.26 311	97.21 173	90.06 151	90.03 207	90.62 332	66.61 322	96.81 272	83.16 275	94.36 181	98.84 146

XVG-OURS		90.83 204	90.49 199	91.86 253	95.23 226	81.25 333	95.79 330	95.92 274	88.96 181	90.02 208	98.03 135	71.60 286	99.35 136	91.06 179	87.78 250	94.98 257

ADS-MVSNet2		87.62 267	86.88 261	89.86 303	96.21 188	79.14 350	87.15 393	92.99 368	83.01 311	89.91 209	87.27 373	78.87 231	92.80 376	74.20 343	92.27 207	97.64 206

ADS-MVSNet		88.99 235	87.30 254	94.07 203	96.21 188	87.56 218	87.15 393	96.78 208	83.01 311	89.91 209	87.27 373	78.87 231	97.01 264	74.20 343	92.27 207	97.64 206

mamv4		91.41 190	93.57 128	84.91 360	97.11 150	58.11 407	95.68 333	95.93 272	82.09 332	89.78 211	95.71 229	90.09 57	98.24 193	97.26 68	98.50 108	98.38 178

ab-mvs		91.05 201	89.17 219	96.69 88	95.96 201	91.72 108	92.62 365	97.23 171	85.61 268	89.74 212	93.89 261	68.55 304	99.42 126	91.09 178	87.84 249	98.92 141

TAMVS		92.62 165	92.09 164	94.20 198	94.10 271	87.68 213	98.41 194	96.97 200	87.53 232	89.74 212	96.04 222	84.77 155	96.49 288	88.97 209	92.31 206	98.42 174

Vis-MVSNet (Re-imp)		93.26 153	93.00 145	94.06 204	96.14 194	86.71 239	98.68 156	96.70 212	88.30 205	89.71 214	97.64 150	85.43 144	96.39 293	88.06 218	96.32 156	99.08 125

CNLPA		93.64 140	92.74 149	96.36 109	98.96 76	90.01 158	99.19 92	95.89 282	86.22 259	89.40 215	98.85 84	80.66 217	99.84 69	88.57 211	96.92 146	99.24 109

Anonymous202405211		88.84 240	87.03 259	94.27 194	98.14 105	84.18 295	98.44 190	95.58 302	76.79 368	89.34 216	96.88 192	53.42 380	99.54 111	87.53 223	87.12 253	99.09 124

Fast-Effi-MVS+		91.72 185	90.79 194	94.49 185	95.89 202	87.40 224	99.54 49	95.70 294	85.01 280	89.28 217	95.68 230	77.75 241	97.57 242	83.22 274	95.06 176	98.51 171

PatchMatch-RL		91.47 188	90.54 198	94.26 195	98.20 101	86.36 247	96.94 286	97.14 181	87.75 224	88.98 218	95.75 228	71.80 284	99.40 130	80.92 295	97.39 136	97.02 227

dp		90.16 220	88.83 227	94.14 200	96.38 181	86.42 243	91.57 376	97.06 191	84.76 284	88.81 219	90.19 348	84.29 158	97.43 248	75.05 335	91.35 232	98.56 169

DeepC-MVS	91.02 4	94.56 114	93.92 118	96.46 101	97.16 146	90.76 132	98.39 201	97.11 185	93.92 51	88.66 220	98.33 124	78.14 239	99.85 67	95.02 123	98.57 106	98.78 155
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline1		92.61 166	91.28 181	96.58 95	97.05 154	94.63 51	97.72 254	96.20 246	89.82 155	88.56 221	96.85 193	86.85 111	97.82 218	88.42 212	80.10 302	97.30 216

Anonymous20240529		87.66 266	85.58 279	93.92 210	97.59 123	85.01 283	98.13 223	97.13 183	66.69 403	88.47 222	96.01 223	55.09 372	99.51 113	87.00 226	84.12 276	97.23 220

CVMVSNet		90.30 215	90.91 189	88.46 330	94.32 265	73.58 380	97.61 261	97.59 118	90.16 147	88.43 223	97.10 177	76.83 246	92.86 373	82.64 281	93.54 189	98.93 139

TR-MVS		90.77 205	89.44 214	94.76 175	96.31 183	88.02 208	97.92 239	95.96 266	85.52 269	88.22 224	97.23 169	66.80 321	98.09 201	84.58 257	92.38 203	98.17 195

F-COLMAP		92.07 181	91.75 173	93.02 227	98.16 104	82.89 313	98.79 147	95.97 264	86.54 253	87.92 225	97.80 139	78.69 234	99.65 101	85.97 239	95.93 166	96.53 241

WB-MVSnew		88.69 248	88.34 238	89.77 307	94.30 269	85.99 262	98.14 222	97.31 165	87.15 238	87.85 226	96.07 221	69.91 293	95.52 337	72.83 354	91.47 227	87.80 374

BH-RMVSNet		91.25 196	89.99 205	95.03 167	96.75 165	88.55 197	98.65 160	94.95 330	87.74 225	87.74 227	97.80 139	68.27 307	98.14 197	80.53 300	97.49 133	98.41 175

Effi-MVS+-dtu		89.97 224	90.68 196	87.81 334	95.15 233	71.98 387	97.87 243	95.40 313	91.92 100	87.57 228	91.44 310	74.27 260	96.84 270	89.45 200	93.10 193	94.60 259

HQP-NCC					93.95 276		99.16 98		93.92 51	87.57 228

ACMP_Plane					93.95 276		99.16 98		93.92 51	87.57 228

HQP4-MVS										87.57 228			97.77 222			92.72 269

HQP-MVS		91.50 187	91.23 182	92.29 243	93.95 276	86.39 245	99.16 98	96.37 235	93.92 51	87.57 228	96.67 203	73.34 266	97.77 222	93.82 147	86.29 257	92.72 269

TAPA-MVS	87.50 9	90.35 213	89.05 222	94.25 196	98.48 95	85.17 280	98.42 192	96.58 222	82.44 327	87.24 233	98.53 108	82.77 183	98.84 160	59.09 398	97.88 122	98.72 159
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		90.60 211	89.56 211	93.72 217	95.10 240	85.43 273	99.41 69	94.94 331	83.96 295	87.21 234	96.83 196	74.37 258	97.05 263	80.50 301	93.73 188	98.67 163

HQP_MVS		91.26 194	90.95 188	92.16 247	93.84 283	86.07 259	99.02 122	96.30 239	93.38 69	86.99 235	96.52 205	72.92 272	97.75 228	93.46 154	86.17 260	92.67 271

plane_prior3						85.91 263			93.65 62	86.99 235

GA-MVS		90.10 221	88.69 230	94.33 192	92.44 308	87.97 209	99.08 114	96.26 243	89.65 159	86.92 237	93.11 280	68.09 309	96.96 265	82.54 283	90.15 241	98.05 197

1112_ss		92.71 162	91.55 176	96.20 116	95.56 214	91.12 120	98.48 187	94.69 340	88.29 206	86.89 238	98.50 112	87.02 108	98.66 172	84.75 254	89.77 244	98.81 151

Test_1112_low_res		92.27 175	90.97 187	96.18 117	95.53 216	91.10 122	98.47 189	94.66 341	88.28 207	86.83 239	93.50 272	87.00 109	98.65 173	84.69 255	89.74 245	98.80 152

cascas		90.93 203	89.33 217	95.76 137	95.69 210	93.03 85	98.99 126	96.59 219	80.49 348	86.79 240	94.45 249	65.23 334	98.60 174	93.52 151	92.18 210	95.66 253

baseline2		94.04 124	93.80 124	94.74 177	93.07 302	90.25 143	98.12 225	98.16 39	89.86 154	86.53 241	96.95 186	95.56 6	98.05 205	91.44 176	94.53 179	95.93 251

OPM-MVS		89.76 226	89.15 220	91.57 262	90.53 339	85.58 271	98.11 227	95.93 272	92.88 81	86.05 242	96.47 208	67.06 320	97.87 215	89.29 206	86.08 262	91.26 317
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPA-MVSNet		89.10 234	87.66 249	93.45 219	92.56 306	91.02 126	97.97 238	98.32 29	86.92 244	86.03 243	92.01 296	68.84 303	97.10 261	90.92 181	75.34 326	92.23 281

MonoMVSNet		90.69 208	89.78 208	93.45 219	91.78 322	84.97 285	96.51 302	94.44 345	90.56 133	85.96 244	90.97 319	78.61 236	96.27 308	95.35 114	83.79 281	99.11 122

SDMVSNet		91.09 198	89.91 206	94.65 180	96.80 162	90.54 139	97.78 247	97.81 69	88.34 203	85.73 245	95.26 239	66.44 325	98.26 191	94.25 139	86.75 254	95.14 254

sd_testset		89.23 232	88.05 245	92.74 236	96.80 162	85.33 276	95.85 328	97.03 194	88.34 203	85.73 245	95.26 239	61.12 351	97.76 227	85.61 245	86.75 254	95.14 254

tpm cat1		88.89 238	87.27 255	93.76 215	95.79 206	85.32 277	90.76 385	97.09 189	76.14 371	85.72 247	88.59 362	82.92 180	98.04 206	76.96 322	91.43 228	97.90 202

IB-MVS	89.43 6	92.12 178	90.83 193	95.98 130	95.40 221	90.78 131	99.81 12	98.06 45	91.23 118	85.63 248	93.66 267	90.63 46	98.78 162	91.22 177	71.85 363	98.36 182
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		89.87 225	89.38 216	91.36 265	94.32 265	85.87 265	97.61 261	96.59 219	85.10 275	85.51 249	97.10 177	81.30 212	96.56 282	83.85 271	83.03 287	91.64 296

MVSTER		92.71 162	92.32 157	93.86 212	97.29 137	92.95 89	99.01 124	96.59 219	90.09 148	85.51 249	94.00 256	94.61 15	96.56 282	90.77 186	83.03 287	92.08 289

test_fmvs2		85.10 304	85.45 282	84.02 366	89.85 347	65.63 400	98.49 185	92.59 373	90.45 137	85.43 251	93.32 273	43.94 398	96.59 280	90.81 184	84.19 275	89.85 354

RPSCF		85.33 302	85.55 280	84.67 363	94.63 259	62.28 402	93.73 353	93.76 359	74.38 379	85.23 252	97.06 180	64.09 337	98.31 187	80.98 293	86.08 262	93.41 265

BH-w/o		92.32 172	91.79 171	93.91 211	96.85 159	86.18 253	99.11 112	95.74 292	88.13 210	84.81 253	97.00 184	77.26 244	97.91 211	89.16 208	98.03 119	97.64 206

CLD-MVS		91.06 200	90.71 195	92.10 249	94.05 275	86.10 256	99.55 44	96.29 242	94.16 46	84.70 254	97.17 175	69.62 298	97.82 218	94.74 130	86.08 262	92.39 274
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tpmvs		89.16 233	87.76 246	93.35 221	97.19 143	84.75 288	90.58 387	97.36 161	81.99 333	84.56 255	89.31 359	83.98 162	98.17 196	74.85 338	90.00 243	97.12 221

nrg030		90.23 216	88.87 225	94.32 193	91.53 327	93.54 72	98.79 147	95.89 282	88.12 211	84.55 256	94.61 248	78.80 233	96.88 269	92.35 169	75.21 327	92.53 273

VPNet		88.30 254	86.57 264	93.49 218	91.95 318	91.35 114	98.18 219	97.20 177	88.61 190	84.52 257	94.89 243	62.21 346	96.76 275	89.34 203	72.26 360	92.36 275

dmvs_re		88.69 248	88.06 244	90.59 282	93.83 285	78.68 354	95.75 331	96.18 250	87.99 216	84.48 258	96.32 213	67.52 315	96.94 267	84.98 252	85.49 266	96.14 248

MVS		93.92 128	92.28 158	98.83 7	95.69 210	96.82 8	96.22 314	98.17 36	84.89 282	84.34 259	98.61 106	79.32 227	99.83 73	93.88 144	99.43 61	99.86 29

mvs_anonymous		92.50 169	91.65 174	95.06 164	96.60 168	89.64 165	97.06 282	96.44 231	86.64 250	84.14 260	93.93 259	82.49 190	96.17 312	91.47 175	96.08 163	99.35 99

Fast-Effi-MVS+-dtu		88.84 240	88.59 234	89.58 312	93.44 295	78.18 358	98.65 160	94.62 342	88.46 195	84.12 261	95.37 237	68.91 301	96.52 285	82.06 287	91.70 219	94.06 260

LS3D		90.19 218	88.72 229	94.59 184	98.97 73	86.33 248	96.90 288	96.60 218	74.96 376	84.06 262	98.74 91	75.78 248	99.83 73	74.93 336	97.57 129	97.62 209

ACMM	86.95 13	88.77 245	88.22 241	90.43 288	93.61 289	81.34 331	98.50 183	95.92 274	87.88 220	83.85 263	95.20 241	67.20 318	97.89 213	86.90 230	84.90 269	92.06 290
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
BH-untuned		91.46 189	90.84 191	93.33 222	96.51 173	84.83 287	98.84 139	95.50 306	86.44 258	83.50 264	96.70 201	75.49 250	97.77 222	86.78 232	97.81 123	97.40 213

FIs		90.70 207	89.87 207	93.18 224	92.29 310	91.12 120	98.17 221	98.25 31	89.11 177	83.44 265	94.82 245	82.26 197	96.17 312	87.76 220	82.76 289	92.25 279

UniMVSNet (Re)		89.50 231	88.32 239	93.03 226	92.21 312	90.96 128	98.90 135	98.39 26	89.13 176	83.22 266	92.03 294	81.69 204	96.34 301	86.79 231	72.53 356	91.81 294

UniMVSNet_NR-MVSNet		89.60 228	88.55 235	92.75 235	92.17 313	90.07 152	98.74 150	98.15 40	88.37 201	83.21 267	93.98 257	82.86 181	95.93 322	86.95 227	72.47 357	92.25 279

DU-MVS		88.83 242	87.51 250	92.79 233	91.46 328	90.07 152	98.71 151	97.62 111	88.87 186	83.21 267	93.68 265	74.63 252	95.93 322	86.95 227	72.47 357	92.36 275

LPG-MVS_test		88.86 239	88.47 237	90.06 297	93.35 297	80.95 338	98.22 215	95.94 269	87.73 226	83.17 269	96.11 219	66.28 326	97.77 222	90.19 191	85.19 267	91.46 307

LGP-MVS_train				90.06 297	93.35 297	80.95 338		95.94 269	87.73 226	83.17 269	96.11 219	66.28 326	97.77 222	90.19 191	85.19 267	91.46 307

miper_enhance_ethall		90.33 214	89.70 209	92.22 244	97.12 149	88.93 186	98.35 205	95.96 266	88.60 191	83.14 271	92.33 291	87.38 96	96.18 311	86.49 234	77.89 311	91.55 304

WBMVS		91.35 193	90.49 199	93.94 209	96.97 156	93.40 76	99.27 86	96.71 211	87.40 234	83.10 272	91.76 304	92.38 29	96.23 309	88.95 210	77.89 311	92.17 285

FC-MVSNet-test		90.22 217	89.40 215	92.67 239	91.78 322	89.86 161	97.89 240	98.22 34	88.81 187	82.96 273	94.66 247	81.90 203	95.96 320	85.89 243	82.52 292	92.20 284

PCF-MVS	89.78 5	91.26 194	89.63 210	96.16 121	95.44 218	91.58 112	95.29 337	96.10 255	85.07 277	82.75 274	97.45 159	78.28 238	99.78 87	80.60 299	95.65 170	97.12 221
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
V42		87.00 273	85.68 278	90.98 272	89.91 344	86.08 257	98.32 208	95.61 300	83.67 301	82.72 275	90.67 328	74.00 263	96.53 284	81.94 289	74.28 339	90.32 343

v1144		86.83 276	85.31 284	91.40 263	89.75 348	87.21 233	98.31 209	95.45 309	83.22 307	82.70 276	90.78 323	73.36 265	96.36 295	79.49 304	74.69 333	90.63 338

Syy-MVS		84.10 321	84.53 299	82.83 372	95.14 234	65.71 399	97.68 257	96.66 214	86.52 254	82.63 277	96.84 194	68.15 308	89.89 395	45.62 410	91.54 223	92.87 267

myMVS_eth3d		88.68 250	89.07 221	87.50 338	95.14 234	79.74 345	97.68 257	96.66 214	86.52 254	82.63 277	96.84 194	85.22 148	89.89 395	69.43 366	91.54 223	92.87 267

v144192		86.40 285	84.89 290	90.91 273	89.48 354	85.59 270	98.21 217	95.43 312	82.45 326	82.62 279	90.58 335	72.79 275	96.36 295	78.45 314	74.04 343	90.79 330

3Dnovator	87.35 11	93.17 156	91.77 172	97.37 53	95.41 220	93.07 83	98.82 140	97.85 61	91.53 108	82.56 280	97.58 153	71.97 281	99.82 76	91.01 180	99.23 73	99.22 112

v2v482		87.27 271	85.76 276	91.78 260	89.59 350	87.58 217	98.56 176	95.54 304	84.53 286	82.51 281	91.78 302	73.11 270	96.47 289	82.07 286	74.14 342	91.30 315

tt0805		86.50 284	84.79 293	91.63 261	91.97 316	81.49 327	96.49 303	97.38 157	82.24 329	82.44 282	95.82 227	51.22 386	98.25 192	84.55 258	80.96 298	95.13 256

Baseline_NR-MVSNet		85.83 294	84.82 292	88.87 327	88.73 362	83.34 306	98.63 164	91.66 386	80.41 351	82.44 282	91.35 312	74.63 252	95.42 341	84.13 264	71.39 366	87.84 372

v1192		86.32 287	84.71 295	91.17 267	89.53 353	86.40 244	98.13 223	95.44 311	82.52 324	82.42 284	90.62 332	71.58 287	96.33 302	77.23 319	74.88 330	90.79 330

test_djsdf		88.26 256	87.73 247	89.84 304	88.05 370	82.21 321	97.77 249	96.17 251	86.84 245	82.41 285	91.95 300	72.07 280	95.99 318	89.83 193	84.50 272	91.32 314

cl22		89.57 229	88.79 228	91.91 252	97.94 110	87.62 216	97.98 237	96.51 226	85.03 278	82.37 286	91.79 301	83.65 164	96.50 286	85.96 240	77.89 311	91.61 301

1314		93.44 143	91.98 166	97.84 34	95.24 225	94.38 57	96.22 314	97.92 56	90.18 144	82.28 287	97.71 146	77.63 242	99.80 81	91.94 172	98.67 102	99.34 101

v1921920		86.02 290	84.44 301	90.77 279	89.32 356	85.20 278	98.10 228	95.35 317	82.19 330	82.25 288	90.71 325	70.73 290	96.30 306	76.85 324	74.49 335	90.80 329

v1240		85.77 297	84.11 304	90.73 280	89.26 357	85.15 281	97.88 242	95.23 326	81.89 336	82.16 289	90.55 337	69.60 299	96.31 303	75.59 333	74.87 331	90.72 335

XVG-ACMP-BASELINE		85.86 293	84.95 289	88.57 328	89.90 345	77.12 364	94.30 346	95.60 301	87.40 234	82.12 290	92.99 283	53.42 380	97.66 232	85.02 251	83.83 278	90.92 326

GBi-Net		86.67 279	84.96 287	91.80 256	95.11 237	88.81 189	96.77 292	95.25 319	82.94 314	82.12 290	90.25 343	62.89 343	94.97 349	79.04 307	80.24 299	91.62 298

test1		86.67 279	84.96 287	91.80 256	95.11 237	88.81 189	96.77 292	95.25 319	82.94 314	82.12 290	90.25 343	62.89 343	94.97 349	79.04 307	80.24 299	91.62 298

FMVSNet3		88.81 244	87.08 258	93.99 208	96.52 172	94.59 52	98.08 232	96.20 246	85.85 263	82.12 290	91.60 307	74.05 262	95.40 342	79.04 307	80.24 299	91.99 292

IterMVS-LS		88.34 253	87.44 251	91.04 270	94.10 271	85.85 266	98.10 228	95.48 307	85.12 274	82.03 294	91.21 315	81.35 211	95.63 335	83.86 270	75.73 324	91.63 297
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		88.94 237	88.12 243	91.40 263	95.32 224	86.93 235	97.85 244	95.55 303	84.19 290	81.97 295	91.50 309	84.16 159	95.91 325	84.69 255	77.89 311	91.36 312

MIMVSNet		84.48 313	81.83 325	92.42 242	91.73 324	87.36 225	85.52 396	94.42 349	81.40 339	81.91 296	87.58 367	51.92 383	92.81 375	73.84 346	88.15 248	97.08 225

PS-MVSNAJss		89.54 230	89.05 222	91.00 271	88.77 361	84.36 292	97.39 266	95.97 264	88.47 193	81.88 297	93.80 263	82.48 191	96.50 286	89.34 203	83.34 286	92.15 286

WR-MVS		88.54 252	87.22 257	92.52 240	91.93 320	89.50 168	98.56 176	97.84 62	86.99 239	81.87 298	93.81 262	74.25 261	95.92 324	85.29 247	74.43 336	92.12 287

TranMVSNet+NR-MVSNet		87.75 262	86.31 268	92.07 250	90.81 336	88.56 196	98.33 206	97.18 178	87.76 223	81.87 298	93.90 260	72.45 276	95.43 340	83.13 277	71.30 367	92.23 281

eth_miper_zixun_eth		87.76 261	87.00 260	90.06 297	94.67 257	82.65 318	97.02 285	95.37 315	84.19 290	81.86 300	91.58 308	81.47 208	95.90 326	83.24 273	73.61 345	91.61 301

UniMVSNet_ETH3D		85.65 300	83.79 308	91.21 266	90.41 341	80.75 341	95.36 335	95.78 288	78.76 357	81.83 301	94.33 250	49.86 391	96.66 277	84.30 260	83.52 284	96.22 247

c3_l		88.19 257	87.23 256	91.06 269	94.97 247	86.17 254	97.72 254	95.38 314	83.43 304	81.68 302	91.37 311	82.81 182	95.72 332	84.04 268	73.70 344	91.29 316

DP-MVS		88.75 246	86.56 265	95.34 153	98.92 81	87.45 222	97.64 260	93.52 365	70.55 389	81.49 303	97.25 168	74.43 257	99.88 54	71.14 360	94.09 183	98.67 163

3Dnovator+	87.72 8	93.43 144	91.84 169	98.17 23	95.73 209	95.08 35	98.92 133	97.04 192	91.42 113	81.48 304	97.60 151	74.60 254	99.79 85	90.84 183	98.97 86	99.64 68

QAPM		91.41 190	89.49 213	97.17 62	95.66 212	93.42 75	98.60 171	97.51 135	80.92 346	81.39 305	97.41 161	72.89 274	99.87 58	82.33 284	98.68 101	98.21 192

testing3		87.75 262	88.22 241	86.36 347	94.66 258	77.41 363	99.52 50	97.95 54	86.05 261	81.12 306	96.69 202	86.18 130	89.31 399	61.65 392	90.12 242	92.35 278

XXY-MVS		87.75 262	86.02 272	92.95 231	90.46 340	89.70 164	97.71 256	95.90 280	84.02 292	80.95 307	94.05 251	67.51 316	97.10 261	85.16 248	78.41 308	92.04 291

v148		86.38 286	85.06 286	90.37 292	89.47 355	84.10 296	98.52 179	95.48 307	83.80 297	80.93 308	90.22 346	74.60 254	96.31 303	80.92 295	71.55 365	90.69 336

DIV-MVS_self_test		87.82 259	86.81 262	90.87 276	94.87 252	85.39 275	97.81 245	95.22 327	82.92 317	80.76 309	91.31 313	81.99 200	95.81 329	81.36 291	75.04 329	91.42 310

cl____		87.82 259	86.79 263	90.89 275	94.88 251	85.43 273	97.81 245	95.24 322	82.91 318	80.71 310	91.22 314	81.97 202	95.84 327	81.34 292	75.06 328	91.40 311

FMVSNet2		86.90 274	84.79 293	93.24 223	95.11 237	92.54 97	97.67 259	95.86 286	82.94 314	80.55 311	91.17 316	62.89 343	95.29 344	77.23 319	79.71 305	91.90 293

pmmvs4		87.58 268	86.17 271	91.80 256	89.58 351	88.92 187	97.25 274	95.28 318	82.54 323	80.49 312	93.17 279	75.62 249	96.05 317	82.75 280	78.90 306	90.42 341

reproduce_monomvs		92.11 180	91.82 170	92.98 228	98.25 98	90.55 138	98.38 203	97.93 55	94.81 33	80.46 313	92.37 290	96.46 3	97.17 256	94.06 140	73.61 345	91.23 318

ACMP	87.39 10	88.71 247	88.24 240	90.12 296	93.91 281	81.06 337	98.50 183	95.67 297	89.43 170	80.37 314	95.55 231	65.67 328	97.83 217	90.55 188	84.51 271	91.47 306
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
pmmvs5		85.87 292	84.40 303	90.30 293	88.53 365	84.23 293	98.60 171	93.71 361	81.53 338	80.29 315	92.02 295	64.51 336	95.52 337	82.04 288	78.34 309	91.15 320

test0.0.03 1		88.96 236	88.61 232	90.03 301	91.09 333	84.43 291	98.97 129	97.02 196	90.21 142	80.29 315	96.31 214	84.89 151	91.93 387	72.98 352	85.70 265	93.73 261

miper_lstm_enhance		86.90 274	86.20 270	89.00 324	94.53 260	81.19 334	96.74 296	95.24 322	82.33 328	80.15 317	90.51 339	81.99 200	94.68 358	80.71 297	73.58 347	91.12 321

jajsoiax		87.35 269	86.51 266	89.87 302	87.75 375	81.74 325	97.03 283	95.98 263	88.47 193	80.15 317	93.80 263	61.47 348	96.36 295	89.44 201	84.47 273	91.50 305

mvs_tets		87.09 272	86.22 269	89.71 308	87.87 371	81.39 330	96.73 297	95.90 280	88.19 209	79.99 319	93.61 268	59.96 355	96.31 303	89.40 202	84.34 274	91.43 309

ITE_SJBPF				87.93 332	92.26 311	76.44 367		93.47 366	87.67 229	79.95 320	95.49 234	56.50 365	97.38 250	75.24 334	82.33 293	89.98 352

v8		86.11 289	84.45 300	91.10 268	89.99 343	86.85 236	97.24 275	95.36 316	81.99 333	79.89 321	89.86 352	74.53 256	96.39 293	78.83 311	72.32 359	90.05 350

v10		85.73 298	84.01 306	90.87 276	90.03 342	86.73 238	97.20 278	95.22 327	81.25 341	79.85 322	89.75 353	73.30 268	96.28 307	76.87 323	72.64 355	89.61 358

WR-MVS_H		86.53 283	85.49 281	89.66 311	91.04 334	83.31 307	97.53 263	98.20 35	84.95 281	79.64 323	90.90 321	78.01 240	95.33 343	76.29 328	72.81 353	90.35 342

anonymousdsp		86.69 278	85.75 277	89.53 313	86.46 383	82.94 310	96.39 305	95.71 293	83.97 294	79.63 324	90.70 326	68.85 302	95.94 321	86.01 238	84.02 277	89.72 356

Patchmtry		83.61 326	81.64 326	89.50 314	93.36 296	82.84 315	84.10 404	94.20 354	69.47 395	79.57 325	86.88 377	84.43 156	94.78 355	68.48 371	74.30 338	90.88 327

CP-MVSNet		86.54 282	85.45 282	89.79 306	91.02 335	82.78 316	97.38 268	97.56 124	85.37 271	79.53 326	93.03 281	71.86 283	95.25 345	79.92 302	73.43 351	91.34 313

Patchmatch-test		86.25 288	84.06 305	92.82 232	94.42 261	82.88 314	82.88 408	94.23 353	71.58 385	79.39 327	90.62 332	89.00 69	96.42 292	63.03 388	91.37 231	99.16 115

DSMNet-mixed		81.60 335	81.43 329	82.10 375	84.36 390	60.79 403	93.63 355	86.74 408	79.00 353	79.32 328	87.15 375	63.87 339	89.78 397	66.89 377	91.92 213	95.73 252

MSDG		88.29 255	86.37 267	94.04 206	96.90 158	86.15 255	96.52 301	94.36 351	77.89 363	79.22 329	96.95 186	69.72 296	99.59 107	73.20 351	92.58 201	96.37 246

Anonymous20231211		84.72 308	82.65 320	90.91 273	97.71 116	84.55 290	97.28 272	96.67 213	66.88 402	79.18 330	90.87 322	58.47 359	96.60 279	82.61 282	74.20 340	91.59 303

PS-CasMVS		85.81 295	84.58 298	89.49 316	90.77 337	82.11 322	97.20 278	97.36 161	84.83 283	79.12 331	92.84 284	67.42 317	95.16 347	78.39 315	73.25 352	91.21 319

IterMVS		85.81 295	84.67 296	89.22 319	93.51 291	83.67 302	96.32 308	94.80 336	85.09 276	78.69 332	90.17 349	66.57 324	93.17 372	79.48 305	77.42 318	90.81 328
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PEN-MVS		85.21 303	83.93 307	89.07 323	89.89 346	81.31 332	97.09 281	97.24 170	84.45 288	78.66 333	92.68 287	68.44 306	94.87 352	75.98 330	70.92 368	91.04 323

IterMVS-SCA-FT		85.73 298	84.64 297	89.00 324	93.46 294	82.90 312	96.27 309	94.70 339	85.02 279	78.62 334	90.35 341	66.61 322	93.33 369	79.38 306	77.36 319	90.76 332

OpenMVS	85.28 14	90.75 206	88.84 226	96.48 100	93.58 290	93.51 73	98.80 143	97.41 154	82.59 321	78.62 334	97.49 157	68.00 311	99.82 76	84.52 259	98.55 107	96.11 249

PVSNet_0	83.28 16	87.31 270	85.16 285	93.74 216	94.78 254	84.59 289	98.91 134	98.69 20	89.81 156	78.59 336	93.23 277	61.95 347	99.34 137	94.75 129	55.72 403	97.30 216

EU-MVSNet		84.19 318	84.42 302	83.52 370	88.64 364	67.37 398	96.04 320	95.76 291	85.29 272	78.44 337	93.18 278	70.67 291	91.48 389	75.79 332	75.98 322	91.70 295

v7n		84.42 315	82.75 318	89.43 317	88.15 368	81.86 324	96.75 295	95.67 297	80.53 347	78.38 338	89.43 357	69.89 294	96.35 300	73.83 347	72.13 361	90.07 348

FMVSNet1		83.94 322	81.32 331	91.80 256	91.94 319	88.81 189	96.77 292	95.25 319	77.98 359	78.25 339	90.25 343	50.37 390	94.97 349	73.27 350	77.81 316	91.62 298

D2MVS		87.96 258	87.39 252	89.70 309	91.84 321	83.40 305	98.31 209	98.49 22	88.04 214	78.23 340	90.26 342	73.57 264	96.79 274	84.21 262	83.53 283	88.90 366

mvs5depth		78.17 354	75.56 358	85.97 351	80.43 403	76.44 367	85.46 397	89.24 403	76.39 369	78.17 341	88.26 363	51.73 384	95.73 331	69.31 367	61.09 393	85.73 389

MS-PatchMatch		86.75 277	85.92 274	89.22 319	91.97 316	82.47 320	96.91 287	96.14 253	83.74 298	77.73 342	93.53 271	58.19 360	97.37 252	76.75 325	98.35 113	87.84 372

DTE-MVSNet		84.14 319	82.80 315	88.14 331	88.95 360	79.87 344	96.81 291	96.24 244	83.50 303	77.60 343	92.52 289	67.89 313	94.24 363	72.64 355	69.05 372	90.32 343

COLMAP_ROB	82.69 18	84.54 312	82.82 314	89.70 309	96.72 166	78.85 351	95.89 323	92.83 371	71.55 386	77.54 344	95.89 226	59.40 357	99.14 148	67.26 375	88.26 247	91.11 322
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		84.13 320	83.59 309	85.77 354	87.81 372	70.24 392	94.89 341	93.65 363	86.08 260	76.53 345	93.28 276	61.41 349	96.14 314	80.95 294	77.69 317	90.93 325

tfpnnormal		83.65 324	81.35 330	90.56 285	91.37 330	88.06 206	97.29 271	97.87 59	78.51 358	76.20 346	90.91 320	64.78 335	96.47 289	61.71 391	73.50 348	87.13 381

ppachtmachnet_test		83.63 325	81.57 328	89.80 305	89.01 358	85.09 282	97.13 280	94.50 344	78.84 355	76.14 347	91.00 318	69.78 295	94.61 359	63.40 386	74.36 337	89.71 357

pm-mvs1		84.68 309	82.78 317	90.40 289	89.58 351	85.18 279	97.31 270	94.73 338	81.93 335	76.05 348	92.01 296	65.48 332	96.11 315	78.75 312	69.14 371	89.91 353

AllTest		84.97 306	83.12 312	90.52 286	96.82 160	78.84 352	95.89 323	92.17 378	77.96 361	75.94 349	95.50 232	55.48 368	99.18 142	71.15 358	87.14 251	93.55 263

TestCases				90.52 286	96.82 160	78.84 352		92.17 378	77.96 361	75.94 349	95.50 232	55.48 368	99.18 142	71.15 358	87.14 251	93.55 263

CL-MVSNet_self_test		79.89 344	78.34 345	84.54 364	81.56 399	75.01 373	96.88 289	95.62 299	81.10 342	75.86 351	85.81 382	68.49 305	90.26 393	63.21 387	56.51 401	88.35 369

testgi		82.29 330	81.00 333	86.17 349	87.24 378	74.84 375	97.39 266	91.62 388	88.63 189	75.85 352	95.42 235	46.07 397	91.55 388	66.87 378	79.94 303	92.12 287

MVP-Stereo		86.61 281	85.83 275	88.93 326	88.70 363	83.85 300	96.07 319	94.41 350	82.15 331	75.64 353	91.96 299	67.65 314	96.45 291	77.20 321	98.72 100	86.51 384
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LF4IMVS		81.94 333	81.17 332	84.25 365	87.23 379	68.87 397	93.35 357	91.93 383	83.35 306	75.40 354	93.00 282	49.25 394	96.65 278	78.88 310	78.11 310	87.22 380

our_test_3		84.47 314	82.80 315	89.50 314	89.01 358	83.90 299	97.03 283	94.56 343	81.33 340	75.36 355	90.52 338	71.69 285	94.54 360	68.81 369	76.84 320	90.07 348

LTVRE_ROB	81.71 19	84.59 311	82.72 319	90.18 294	92.89 304	83.18 308	93.15 358	94.74 337	78.99 354	75.14 356	92.69 286	65.64 329	97.63 235	69.46 365	81.82 295	89.74 355
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
ttmdpeth		79.80 345	77.91 347	85.47 356	83.34 394	75.75 369	95.32 336	91.45 391	76.84 367	74.81 357	91.71 305	53.98 378	94.13 364	72.42 356	61.29 392	86.51 384

Anonymous20231206		80.76 339	79.42 343	84.79 362	84.78 389	72.98 382	96.53 300	92.97 369	79.56 352	74.33 358	88.83 360	61.27 350	92.15 384	60.59 394	75.92 323	89.24 363

FMVSNet5		82.29 330	80.54 335	87.52 337	93.79 287	84.01 297	93.73 353	92.47 375	76.92 366	74.27 359	86.15 381	63.69 341	89.24 400	69.07 368	74.79 332	89.29 362

MVS-HIRNet		79.01 348	75.13 361	90.66 281	93.82 286	81.69 326	85.16 398	93.75 360	54.54 408	74.17 360	59.15 414	57.46 362	96.58 281	63.74 385	94.38 180	93.72 262

ACMH+	83.78 15	84.21 317	82.56 323	89.15 321	93.73 288	79.16 349	96.43 304	94.28 352	81.09 343	74.00 361	94.03 254	54.58 375	97.67 231	76.10 329	78.81 307	90.63 338

kuosan		84.40 316	83.34 310	87.60 336	95.87 203	79.21 348	92.39 367	96.87 203	76.12 372	73.79 362	93.98 257	81.51 206	90.63 391	64.13 384	75.42 325	92.95 266

KD-MVS_2432*1600		82.98 327	80.52 336	90.38 290	94.32 265	88.98 181	92.87 362	95.87 284	80.46 349	73.79 362	87.49 370	82.76 185	93.29 370	70.56 362	46.53 414	88.87 367

miper_refine_blended		82.98 327	80.52 336	90.38 290	94.32 265	88.98 181	92.87 362	95.87 284	80.46 349	73.79 362	87.49 370	82.76 185	93.29 370	70.56 362	46.53 414	88.87 367

NR-MVSNet		87.74 265	86.00 273	92.96 230	91.46 328	90.68 135	96.65 299	97.42 153	88.02 215	73.42 365	93.68 265	77.31 243	95.83 328	84.26 261	71.82 364	92.36 275

test_fmvs3		75.09 364	75.19 360	74.81 385	77.45 408	54.08 411	95.93 321	90.64 395	82.51 325	73.29 366	81.19 396	22.29 414	86.29 407	85.50 246	67.89 376	84.06 398

USDC		84.74 307	82.93 313	90.16 295	91.73 324	83.54 304	95.00 340	93.30 367	88.77 188	73.19 367	93.30 275	53.62 379	97.65 234	75.88 331	81.54 296	89.30 361

KD-MVS_self_test		77.47 358	75.88 357	82.24 373	81.59 398	68.93 396	92.83 364	94.02 357	77.03 365	73.14 368	83.39 387	55.44 370	90.42 392	67.95 372	57.53 400	87.38 376

LCM-MVSNet-Re		88.59 251	88.61 232	88.51 329	95.53 216	72.68 385	96.85 290	88.43 405	88.45 196	73.14 368	90.63 331	75.82 247	94.38 361	92.95 161	95.71 169	98.48 173

TDRefinement		78.01 355	75.31 359	86.10 350	70.06 415	73.84 378	93.59 356	91.58 389	74.51 378	73.08 370	91.04 317	49.63 393	97.12 258	74.88 337	59.47 396	87.33 378

TransMVSNet (Re)		81.97 332	79.61 342	89.08 322	89.70 349	84.01 297	97.26 273	91.85 384	78.84 355	73.07 371	91.62 306	67.17 319	95.21 346	67.50 374	59.46 397	88.02 371

SixPastTwentyTwo		82.63 329	81.58 327	85.79 353	88.12 369	71.01 390	95.17 338	92.54 374	84.33 289	72.93 372	92.08 293	60.41 354	95.61 336	74.47 340	74.15 341	90.75 333

pmmvs6		79.90 343	77.31 350	87.67 335	84.17 391	78.13 359	95.86 327	93.68 362	67.94 399	72.67 373	89.62 355	50.98 388	95.75 330	74.80 339	66.04 382	89.14 364

ACMH	83.09 17	84.60 310	82.61 321	90.57 283	93.18 300	82.94 310	96.27 309	94.92 332	81.01 344	72.61 374	93.61 268	56.54 364	97.79 220	74.31 341	81.07 297	90.99 324
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		78.63 352	76.90 353	83.82 367	82.82 396	72.86 383	95.72 332	93.57 364	73.55 383	72.17 375	84.79 384	49.69 392	92.51 380	65.29 382	74.50 334	86.09 387

Patchmatch-RL test		81.90 334	80.13 338	87.23 341	80.71 401	70.12 394	84.07 405	88.19 406	83.16 309	70.57 376	82.18 393	87.18 103	92.59 378	82.28 285	62.78 388	98.98 131

mvsany_test3		75.85 363	74.52 364	79.83 380	73.53 412	60.64 404	91.73 373	87.87 407	83.91 296	70.55 377	82.52 390	31.12 409	93.66 366	86.66 233	62.83 387	85.19 396

test_0402		78.81 350	76.33 355	86.26 348	91.18 332	78.44 357	95.88 325	91.34 392	68.55 396	70.51 378	89.91 351	52.65 382	94.99 348	47.14 409	79.78 304	85.34 394

dongtai		81.36 336	80.61 334	83.62 369	94.25 270	73.32 381	95.15 339	96.81 205	73.56 382	69.79 379	92.81 285	81.00 214	86.80 406	52.08 407	70.06 370	90.75 333

TinyColmap		80.42 341	77.94 346	87.85 333	92.09 314	78.58 355	93.74 352	89.94 398	74.99 375	69.77 380	91.78 302	46.09 396	97.58 239	65.17 383	77.89 311	87.38 376

dmvs_testset		77.17 359	78.99 344	71.71 388	87.25 377	38.55 425	91.44 377	81.76 416	85.77 265	69.49 381	95.94 225	69.71 297	84.37 408	52.71 406	76.82 321	92.21 283

test20.03		78.51 353	77.48 349	81.62 377	83.07 395	71.03 389	96.11 318	92.83 371	81.66 337	69.31 382	89.68 354	57.53 361	87.29 405	58.65 399	68.47 373	86.53 383

test_vis1_rt		81.31 337	80.05 340	85.11 357	91.29 331	70.66 391	98.98 128	77.39 420	85.76 266	68.80 383	82.40 391	36.56 407	99.44 122	92.67 166	86.55 256	85.24 395

N_pmnet		70.19 370	69.87 372	71.12 390	88.24 367	30.63 429	95.85 328	28.70 428	70.18 391	68.73 384	86.55 379	64.04 338	93.81 365	53.12 405	73.46 349	88.94 365

OpenMVS_ROB	73.86 20	77.99 356	75.06 362	86.77 345	83.81 393	77.94 361	96.38 306	91.53 390	67.54 400	68.38 385	87.13 376	43.94 398	96.08 316	55.03 403	81.83 294	86.29 386

ambc				79.60 381	72.76 414	56.61 408	76.20 412	92.01 382		68.25 386	80.23 400	23.34 413	94.73 356	73.78 348	60.81 394	87.48 375

PM-MVS		74.88 365	72.85 368	80.98 379	78.98 406	64.75 401	90.81 384	85.77 409	80.95 345	68.23 387	82.81 389	29.08 411	92.84 374	76.54 327	62.46 390	85.36 393

pmmvs3		72.86 368	69.76 373	82.17 374	73.86 411	74.19 377	94.20 348	89.01 404	64.23 406	67.72 388	80.91 399	41.48 402	88.65 402	62.40 389	54.02 405	83.68 400

lessismore_v0				85.08 358	85.59 387	69.28 395		90.56 396		67.68 389	90.21 347	54.21 377	95.46 339	73.88 345	62.64 389	90.50 340

K. test v3		81.04 338	79.77 341	84.83 361	87.41 376	70.23 393	95.60 334	93.93 358	83.70 300	67.51 390	89.35 358	55.76 366	93.58 368	76.67 326	68.03 375	90.67 337

MIMVSNet1		75.92 362	73.30 367	83.81 368	81.29 400	75.57 371	92.26 368	92.05 381	73.09 384	67.48 391	86.18 380	40.87 404	87.64 404	55.78 402	70.68 369	88.21 370

ET-MVSNet_ETH3D		92.56 168	91.45 178	95.88 133	96.39 180	94.13 63	99.46 59	96.97 200	92.18 96	66.94 392	98.29 127	94.65 14	94.28 362	94.34 137	83.82 280	99.24 109

pmmvs-eth3d		78.71 351	76.16 356	86.38 346	80.25 404	81.19 334	94.17 349	92.13 380	77.97 360	66.90 393	82.31 392	55.76 366	92.56 379	73.63 349	62.31 391	85.38 392

EG-PatchMatch MVS		79.92 342	77.59 348	86.90 344	87.06 380	77.90 362	96.20 316	94.06 356	74.61 377	66.53 394	88.76 361	40.40 405	96.20 310	67.02 376	83.66 282	86.61 382

test_method		70.10 371	68.66 374	74.41 387	86.30 385	55.84 409	94.47 343	89.82 399	35.18 416	66.15 395	84.75 385	30.54 410	77.96 417	70.40 364	60.33 395	89.44 360

UnsupCasMVSNet_eth		78.90 349	76.67 354	85.58 355	82.81 397	74.94 374	91.98 370	96.31 238	84.64 285	65.84 396	87.71 366	51.33 385	92.23 383	72.89 353	56.50 402	89.56 359

test_f		71.94 369	70.82 370	75.30 384	72.77 413	53.28 412	91.62 374	89.66 401	75.44 374	64.47 397	78.31 404	20.48 415	89.56 398	78.63 313	66.02 383	83.05 403

new-patchmatchnet		74.80 366	72.40 369	81.99 376	78.36 407	72.20 386	94.44 344	92.36 376	77.06 364	63.47 398	79.98 401	51.04 387	88.85 401	60.53 395	54.35 404	84.92 397

new_pmnet		76.02 361	73.71 365	82.95 371	83.88 392	72.85 384	91.26 380	92.26 377	70.44 390	62.60 399	81.37 395	47.64 395	92.32 382	61.85 390	72.10 362	83.68 400

UnsupCasMVSNet_bld		73.85 367	70.14 371	84.99 359	79.44 405	75.73 370	88.53 390	95.24 322	70.12 392	61.94 400	74.81 407	41.41 403	93.62 367	68.65 370	51.13 410	85.62 390

CMPMVS	58.40 21	80.48 340	80.11 339	81.59 378	85.10 388	59.56 405	94.14 350	95.95 268	68.54 397	60.71 401	93.31 274	55.35 371	97.87 215	83.06 278	84.85 270	87.33 378
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
APD_test1		68.93 372	66.98 375	74.77 386	80.62 402	53.15 413	87.97 391	85.01 411	53.76 409	59.26 402	87.52 369	25.19 412	89.95 394	56.20 401	67.33 379	81.19 404

MVStest1		76.56 360	73.43 366	85.96 352	86.30 385	80.88 340	94.26 347	91.74 385	61.98 407	58.53 403	89.96 350	69.30 300	91.47 390	59.26 397	49.56 412	85.52 391

DeepMVS_CX				76.08 383	90.74 338	51.65 416		90.84 394	86.47 257	57.89 404	87.98 364	35.88 408	92.60 377	65.77 381	65.06 385	83.97 399

WB-MVS		66.44 373	66.29 376	66.89 393	74.84 409	44.93 420	93.00 359	84.09 414	71.15 387	55.82 405	81.63 394	63.79 340	80.31 415	21.85 419	50.47 411	75.43 406

SSC-MVS		65.42 374	65.20 377	66.06 394	73.96 410	43.83 421	92.08 369	83.54 415	69.77 393	54.73 406	80.92 398	63.30 342	79.92 416	20.48 420	48.02 413	74.44 407

YYNet1		79.64 347	77.04 352	87.43 340	87.80 373	79.98 343	96.23 313	94.44 345	73.83 381	51.83 407	87.53 368	67.96 312	92.07 386	66.00 380	67.75 378	90.23 345

MDA-MVSNet_test_wron		79.65 346	77.05 351	87.45 339	87.79 374	80.13 342	96.25 312	94.44 345	73.87 380	51.80 408	87.47 372	68.04 310	92.12 385	66.02 379	67.79 377	90.09 346

LCM-MVSNet		60.07 378	56.37 380	71.18 389	54.81 424	48.67 417	82.17 409	89.48 402	37.95 414	49.13 409	69.12 408	13.75 422	81.76 409	59.28 396	51.63 409	83.10 402

MDA-MVSNet-bldmvs		77.82 357	74.75 363	87.03 342	88.33 366	78.52 356	96.34 307	92.85 370	75.57 373	48.87 410	87.89 365	57.32 363	92.49 381	60.79 393	64.80 386	90.08 347

PMMVS2		58.97 379	55.07 382	70.69 391	62.72 419	55.37 410	85.97 395	80.52 417	49.48 410	45.94 411	68.31 409	15.73 420	80.78 413	49.79 408	37.12 416	75.91 405

testf1		56.38 380	53.73 383	64.31 397	64.84 417	45.11 418	80.50 410	75.94 422	38.87 412	42.74 412	75.07 405	11.26 424	81.19 411	41.11 412	53.27 406	66.63 411

APD_test2		56.38 380	53.73 383	64.31 397	64.84 417	45.11 418	80.50 410	75.94 422	38.87 412	42.74 412	75.07 405	11.26 424	81.19 411	41.11 412	53.27 406	66.63 411

FPMVS		61.57 375	60.32 378	65.34 395	60.14 422	42.44 423	91.02 383	89.72 400	44.15 411	42.63 414	80.93 397	19.02 416	80.59 414	42.50 411	72.76 354	73.00 408

test_vis3_rt		61.29 376	58.75 379	68.92 392	67.41 416	52.84 414	91.18 382	59.23 427	66.96 401	41.96 415	58.44 415	11.37 423	94.72 357	74.25 342	57.97 399	59.20 414

Gipuma		54.77 382	52.22 386	62.40 399	86.50 382	59.37 406	50.20 417	90.35 397	36.52 415	41.20 416	49.49 417	18.33 418	81.29 410	32.10 416	65.34 384	46.54 417
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		53.66 383	52.86 385	56.05 400	32.75 428	41.97 424	73.42 414	76.12 421	21.91 421	39.68 417	96.39 211	42.59 401	65.10 420	78.00 316	14.92 421	61.08 413

E-PMN		41.02 387	40.93 389	41.29 403	61.97 420	33.83 426	84.00 406	65.17 425	27.17 418	27.56 418	46.72 419	17.63 419	60.41 422	19.32 421	18.82 418	29.61 418

ANet_high		50.71 384	46.17 387	64.33 396	44.27 426	52.30 415	76.13 413	78.73 418	64.95 404	27.37 419	55.23 416	14.61 421	67.74 419	36.01 415	18.23 419	72.95 409

EMVS		39.96 388	39.88 390	40.18 404	59.57 423	32.12 428	84.79 403	64.57 426	26.27 419	26.14 420	44.18 422	18.73 417	59.29 423	17.03 422	17.67 420	29.12 419

MVE	44.00 22	41.70 386	37.64 391	53.90 402	49.46 425	43.37 422	65.09 416	66.66 424	26.19 420	25.77 421	48.53 418	3.58 428	63.35 421	26.15 418	27.28 417	54.97 416
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	41.42 23	45.67 385	42.50 388	55.17 401	34.28 427	32.37 427	66.24 415	78.71 419	30.72 417	22.04 422	59.59 413	4.59 426	77.85 418	27.49 417	58.84 398	55.29 415
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		18.81 390	23.05 393	6.10 407	4.48 429	2.29 432	97.78 247	3.00 430	3.27 423	18.60 423	62.71 411	1.53 430	2.49 426	14.26 424	1.80 423	13.50 421

test123		16.58 392	19.47 394	7.91 406	3.59 430	5.37 431	94.32 345	1.39 431	2.49 424	13.98 424	44.60 421	2.91 429	2.65 425	11.35 425	0.57 424	15.70 420

wuyk23d		16.71 391	16.73 395	16.65 405	60.15 421	25.22 430	41.24 418	5.17 429	6.56 422	5.48 425	3.61 425	3.64 427	22.72 424	15.20 423	9.52 422	1.99 422

EGC-MVSNET		60.70 377	55.37 381	76.72 382	86.35 384	71.08 388	89.96 388	84.44 413	0.38 425	1.50 426	84.09 386	37.30 406	88.10 403	40.85 414	73.44 350	70.97 410

mmdepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

cdsmvs_eth3d_5k		22.52 389	30.03 392	0.00 408	0.00 431	0.00 433	0.00 419	97.17 179	0.00 426	0.00 427	98.77 88	74.35 259	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		6.87 394	9.16 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	82.48 191	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

ab-mvs-re		8.21 393	10.94 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	98.50 112	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						79.74 345								67.75 373

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 90					99.98 9	99.55 13	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 90					99.98 9	99.55 13	99.83 15	99.96 10

eth-test2					0.00 431

eth-test					0.00 431

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 18				99.19 33	95.12 8	99.97 21	99.90 1	99.92 3	99.99 1

save fliter					99.34 50	93.85 67	99.65 36	97.63 109	95.69 22

test_0728_SECOND				98.77 8	99.66 12	96.37 14	99.72 24	97.68 92					99.98 9	99.64 8	99.82 19	99.96 10

GSMVS																98.84 146

sam_mvs1												88.39 78				98.84 146

sam_mvs												87.08 106

MTGPA								97.45 146

test_post1							90.74 386				41.37 423	85.38 145	96.36 295	83.16 275

test_post											46.00 420	87.37 97	97.11 259

patchmatchnet-post											84.86 383	88.73 74	96.81 272

MTMP							99.21 90	91.09 393

gm-plane-assit					94.69 256	88.14 204			88.22 208		97.20 171		98.29 189	90.79 185

test9_res														98.60 33	99.87 9	99.90 22

agg_prior2														97.84 59	99.87 9	99.91 21

test_prior4						92.00 103	99.41 69

test_prior				97.01 66	99.58 30	91.77 106		97.57 123					99.49 115			99.79 38

新几何2							98.26 212

旧先验1					98.97 73	92.90 91		97.74 79			99.15 42	91.05 38			99.33 65	99.60 73

无先验							98.52 179	97.82 66	87.20 237				99.90 50	87.64 222		99.85 30

原ACMM2							98.69 155

testdata2													99.88 54	84.16 263

segment_acmp												90.56 47

testdata1							97.89 240		92.43 88

plane_prior7					93.84 283	85.73 268

plane_prior6					93.92 280	86.02 261						72.92 272

plane_prior5								96.30 239					97.75 228	93.46 154	86.17 260	92.67 271

plane_prior4											96.52 205

plane_prior2							99.02 122		93.38 69

plane_prior1					93.90 282

plane_prior						86.07 259	99.14 106		93.81 59						86.26 259

n2								0.00 432

nn								0.00 432

door-mid								84.90 412

test11								97.68 92

door								85.30 410

HQP5-MVS						86.39 245

BP-MVS														93.82 147

HQP3-MVS								96.37 235							86.29 257

HQP2-MVS												73.34 266

NP-MVS					93.94 279	86.22 251					96.67 203

ACMMP++_ref															82.64 291

ACMMP++															83.83 278

Test By Simon												83.62 165

High-resolution multi-view benchmark