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.

MED-MVS		99.24 8	99.12 5	99.60 24	99.96 9	98.79 43	99.97 42	98.88 55	96.91 62	99.07 112	99.92 16	97.36 18	100.00 1	99.98 9	99.98 32	100.00 1

TestfortrainingZip a		99.01 16	98.78 21	99.69 17	99.96 9	99.09 26	99.97 42	98.74 76	96.91 62	99.86 16	99.92 16	96.29 38	99.99 40	98.32 136	99.09 151	100.00 1

TestfortrainingZip				99.90 5	99.97 3	99.70 5	99.97 42	98.89 52	96.02 99	99.99 1	99.96 3	97.97 5	100.00 1		99.65 97	100.00 1

DVP-MVS++		99.26 6	99.09 10	99.77 9	99.91 45	99.31 12	99.95 75	98.43 156	96.48 80	99.80 28	99.93 12	97.44 15	100.00 1	99.92 17	99.98 32	100.00 1

MSC_two_6792asdad				99.93 2	99.91 45	99.80 2		98.41 174					100.00 1	99.96 13	100.00 1	100.00 1

PC_three_1452									96.96 60	99.80 28	99.79 63	97.49 11	100.00 1	99.99 5	99.98 32	100.00 1

No_MVS				99.93 2	99.91 45	99.80 2		98.41 174					100.00 1	99.96 13	100.00 1	100.00 1

SED-MVS		99.28 5	99.11 8	99.77 9	99.93 29	99.30 14	99.96 56	98.43 156	97.27 47	99.80 28	99.94 5	96.71 29	100.00 1	100.00 1	100.00 1	100.00 1

IU-MVS					99.93 29	99.31 12		98.41 174	97.71 31	99.84 23				100.00 1	100.00 1	100.00 1

OPU-MVS				99.93 2	99.89 51	99.80 2	99.96 56				99.80 59	97.44 15	100.00 1	100.00 1	99.98 32	100.00 1

test_241102_TWO								98.43 156	97.27 47	99.80 28	99.94 5	97.18 23	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 80	99.83 24	99.91 19	97.87 6	100.00 1	99.92 17	100.00 1	100.00 1

test_0728_SECOND				99.82 8	99.94 18	99.47 8	99.95 75	98.43 156					100.00 1	99.99 5	100.00 1	100.00 1

SMA-MVS		98.76 29	98.48 35	99.62 22	99.87 57	98.87 36	99.86 144	98.38 185	93.19 216	99.77 40	99.94 5	95.54 51	100.00 1	99.74 44	99.99 21	100.00 1
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
MSP-MVS		99.09 10	99.12 5	98.98 92	99.93 29	97.24 123	99.95 75	98.42 168	97.50 38	99.52 76	99.88 29	97.43 17	99.71 161	99.50 62	99.98 32	100.00 1
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
test9_res														99.71 49	99.99 21	100.00 1

agg_prior2														99.48 64	100.00 1	100.00 1

testdata				98.42 142	99.47 104	95.33 217		98.56 113	93.78 190	99.79 37	99.85 38	93.64 115	99.94 95	94.97 253	99.94 59	100.00 1

MSLP-MVS++		99.13 9	99.01 12	99.49 37	99.94 18	98.46 68	99.98 24	98.86 59	97.10 53	99.80 28	99.94 5	95.92 45	100.00 1	99.51 60	100.00 1	100.00 1

MCST-MVS		99.32 3	99.14 4	99.86 6	99.97 3	99.59 6	99.97 42	98.64 91	98.47 3	99.13 107	99.92 16	96.38 37	100.00 1	99.74 44	100.00 1	100.00 1

NCCC		99.37 2	99.25 2	99.71 16	99.96 9	99.15 24	99.97 42	98.62 98	98.02 22	99.90 7	99.95 4	97.33 19	100.00 1	99.54 59	100.00 1	100.00 1

API-MVS		97.86 88	97.66 94	98.47 135	99.52 100	95.41 211	99.47 280	98.87 58	91.68 297	98.84 124	99.85 38	92.34 158	99.99 40	98.44 128	99.96 48	100.00 1

DeepPCF-MVS	95.94 2	97.71 107	98.98 13	93.92 379	99.63 91	81.76 474	99.96 56	98.56 113	99.47 1	99.19 104	99.99 1	94.16 100	100.00 1	99.92 17	99.93 65	100.00 1

DeepC-MVS_fast	96.59 1	98.81 26	98.54 32	99.62 22	99.90 48	98.85 38	99.24 320	98.47 140	98.14 16	99.08 110	99.91 19	93.09 131	100.00 1	99.04 87	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MG-MVS		98.91 22	98.65 27	99.68 18	99.94 18	99.07 27	99.64 241	99.44 19	97.33 44	99.00 118	99.72 95	94.03 103	99.98 52	98.73 110	100.00 1	100.00 1

aaatest				99.60 24	99.96 9	98.79 43	99.97 42	98.88 55	96.36 90	99.07 112	99.93 12		100.00 1	99.98 9	99.96 48	99.99 26

fmvsm_l_conf0.5_n_9		98.55 40	98.23 51	99.49 37	99.10 126	98.50 66	99.99 8	98.70 80	98.14 16	99.94 2	99.68 112	89.02 218	99.98 52	99.89 22	99.61 105	99.99 26

aaEdge-Enhanced		99.07 11	98.89 17	99.59 27	99.93 29	98.79 43	99.95 75	98.80 71	95.89 103	99.28 99	99.93 12	96.28 39	99.98 52	99.98 9	99.96 48	99.99 26

reproduce_model		98.75 30	98.66 26	99.03 85	99.71 84	97.10 133	99.73 211	98.23 213	97.02 58	99.18 105	99.90 23	94.54 82	99.99 40	99.77 38	99.90 73	99.99 26

reproduce-ours		98.78 27	98.67 24	99.09 80	99.70 86	97.30 120	99.74 204	98.25 209	97.10 53	99.10 108	99.90 23	94.59 78	99.99 40	99.77 38	99.91 71	99.99 26

our_new_method		98.78 27	98.67 24	99.09 80	99.70 86	97.30 120	99.74 204	98.25 209	97.10 53	99.10 108	99.90 23	94.59 78	99.99 40	99.77 38	99.91 71	99.99 26

DPE-MVS		99.26 6	99.10 9	99.74 12	99.89 51	99.24 21	99.87 133	98.44 148	97.48 39	99.64 58	99.94 5	96.68 31	99.99 40	99.99 5	100.00 1	99.99 26
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ACMMP_NAP		98.49 45	98.14 59	99.54 32	99.66 90	98.62 61	99.85 147	98.37 188	94.68 139	99.53 74	99.83 51	92.87 137	100.00 1	98.66 115	99.84 80	99.99 26

MTAPA		98.29 62	97.96 75	99.30 52	99.85 62	97.93 91	99.39 293	98.28 205	95.76 106	97.18 207	99.88 29	92.74 141	100.00 1	98.67 113	99.88 77	99.99 26

train_agg		98.88 23	98.65 27	99.59 27	99.92 37	98.92 32	99.96 56	98.43 156	94.35 157	99.71 49	99.86 34	95.94 43	99.85 131	99.69 51	99.98 32	99.99 26

XVS		98.70 32	98.55 31	99.15 71	99.94 18	97.50 112	99.94 93	98.42 168	96.22 93	99.41 87	99.78 67	94.34 90	99.96 77	98.92 96	99.95 54	99.99 26

X-MVStestdata		93.83 290	92.06 325	99.15 71	99.94 18	97.50 112	99.94 93	98.42 168	96.22 93	99.41 87	41.37 549	94.34 90	99.96 77	98.92 96	99.95 54	99.99 26

test_prior				99.43 41	99.94 18	98.49 67		98.65 88					99.80 144			99.99 26

新几何1				99.42 43	99.75 77	98.27 72		98.63 97	92.69 247	99.55 71	99.82 54	94.40 85	100.00 1	91.21 329	99.94 59	99.99 26

旧先验1					99.76 74	97.52 110		98.64 91			99.85 38	95.63 50			99.94 59	99.99 26

无先验							99.49 276	98.71 79	93.46 203				100.00 1	94.36 270		99.99 26

test222					99.55 98	97.41 118	99.34 301	98.55 119	91.86 289	99.27 100	99.83 51	93.84 110			99.95 54	99.99 26

MVS		96.60 170	95.56 206	99.72 14	96.85 330	99.22 22	98.31 413	98.94 44	91.57 299	90.90 332	99.61 124	86.66 255	99.96 77	97.36 185	99.88 77	99.99 26

APDe-MVS		99.06 13	98.91 15	99.51 34	99.94 18	98.76 51	99.91 111	98.39 181	97.20 51	99.46 80	99.85 38	95.53 53	99.79 146	99.86 28	100.00 1	99.99 26
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test12				99.43 41	99.74 78	98.56 63		98.40 178		99.65 55		94.76 74	99.75 155		99.98 32	99.99 26

TSAR-MVS + GP.		98.60 37	98.51 34	98.86 99	99.73 81	96.63 154	99.97 42	97.92 255	98.07 19	98.76 133	99.55 132	95.00 68	99.94 95	99.91 20	97.68 199	99.99 26

HPM-MVS_fast		97.80 97	97.50 103	98.68 110	99.79 70	96.42 163	99.88 130	98.16 228	91.75 295	98.94 120	99.54 134	91.82 173	99.65 173	97.62 180	99.99 21	99.99 26

HPM-MVS		97.96 80	97.72 90	98.68 110	99.84 64	96.39 167	99.90 117	98.17 223	92.61 252	98.62 141	99.57 131	91.87 171	99.67 169	98.87 101	99.99 21	99.99 26
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
APD-MVS		98.62 36	98.35 46	99.41 44	99.90 48	98.51 65	99.87 133	98.36 189	94.08 173	99.74 45	99.73 92	94.08 101	99.74 157	99.42 68	99.99 21	99.99 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		99.40 1	99.26 1	99.84 7	99.98 2	99.51 7	99.98 24	98.69 82	98.20 9	99.93 3	99.98 2	96.82 26	100.00 1	99.75 42	100.00 1	99.99 26

CP-MVS		98.45 48	98.32 47	98.87 98	99.96 9	96.62 155	99.97 42	98.39 181	94.43 152	98.90 122	99.87 32	94.30 93	100.00 1	99.04 87	99.99 21	99.99 26

SteuartSystems-ACMMP		99.02 15	98.97 14	99.18 63	98.72 164	97.71 101	99.98 24	98.44 148	96.85 64	99.80 28	99.91 19	97.57 9	99.85 131	99.44 67	99.99 21	99.99 26
Skip Steuart: Steuart Systems R&D Blog.
CPTT-MVS		97.64 110	97.32 114	98.58 122	99.97 3	95.77 192	99.96 56	98.35 191	89.90 356	98.36 157	99.79 63	91.18 181	99.99 40	98.37 133	99.99 21	99.99 26

PAPM_NR		98.12 75	97.93 78	98.70 109	99.94 18	96.13 181	99.82 167	98.43 156	94.56 142	97.52 192	99.70 101	94.40 85	99.98 52	97.00 199	99.98 32	99.99 26

PAPR		98.52 43	98.16 58	99.58 29	99.97 3	98.77 48	99.95 75	98.43 156	95.35 118	98.03 172	99.75 81	94.03 103	99.98 52	98.11 149	99.83 81	99.99 26

PHI-MVS		98.41 53	98.21 53	99.03 85	99.86 59	97.10 133	99.98 24	98.80 71	90.78 333	99.62 62	99.78 67	95.30 58	100.00 1	99.80 33	99.93 65	99.99 26

fmvsm_l_conf0.5_n		98.94 19	98.84 19	99.25 56	99.17 122	97.81 97	99.98 24	98.86 59	98.25 5	99.90 7	99.76 73	94.21 98	99.97 65	99.87 26	99.52 115	99.98 57

MM		98.83 24	98.53 33	99.76 11	99.59 93	99.33 9	99.99 8	99.76 6	98.39 4	99.39 91	99.80 59	90.49 196	99.96 77	99.89 22	99.43 130	99.98 57

test_fmvsmconf_n		98.43 51	98.32 47	98.78 103	98.12 217	96.41 164	99.99 8	98.83 66	98.22 7	99.67 53	99.64 119	91.11 182	99.94 95	99.67 53	99.62 100	99.98 57

DPM-MVS		98.83 24	98.46 36	99.97 1	99.33 111	99.92 1	99.96 56	98.44 148	97.96 23	99.55 71	99.94 5	97.18 23	100.00 1	93.81 286	99.94 59	99.98 57

HFP-MVS		98.56 39	98.37 43	99.14 73	99.96 9	97.43 116	99.95 75	98.61 99	94.77 134	99.31 95	99.85 38	94.22 96	100.00 1	98.70 111	99.98 32	99.98 57

region2R		98.54 41	98.37 43	99.05 83	99.96 9	97.18 126	99.96 56	98.55 119	94.87 131	99.45 81	99.85 38	94.07 102	100.00 1	98.67 113	100.00 1	99.98 57

ACMMPR		98.50 44	98.32 47	99.05 83	99.96 9	97.18 126	99.95 75	98.60 101	94.77 134	99.31 95	99.84 49	93.73 112	100.00 1	98.70 111	99.98 32	99.98 57

PGM-MVS		98.34 58	98.13 60	98.99 90	99.92 37	97.00 136	99.75 200	99.50 17	93.90 186	99.37 92	99.76 73	93.24 127	100.00 1	97.75 176	99.96 48	99.98 57

CDPH-MVS		98.65 35	98.36 45	99.49 37	99.94 18	98.73 52	99.87 133	98.33 196	93.97 180	99.76 41	99.87 32	94.99 69	99.75 155	98.55 120	100.00 1	99.98 57

mPP-MVS		98.39 56	98.20 54	98.97 93	99.97 3	96.92 140	99.95 75	98.38 185	95.04 124	98.61 142	99.80 59	93.39 118	100.00 1	98.64 116	100.00 1	99.98 57

lecture		98.67 33	98.46 36	99.28 53	99.86 59	97.88 93	99.97 42	99.25 30	96.07 97	99.79 37	99.70 101	92.53 151	99.98 52	99.51 60	99.48 122	99.97 67

fmvsm_s_conf0.5_n_8		98.38 57	98.05 66	99.35 50	99.20 119	98.12 78	99.98 24	98.81 67	98.22 7	99.80 28	99.71 98	87.37 242	99.97 65	99.91 20	99.48 122	99.97 67

SR-MVS-dyc-post		98.31 60	98.17 57	98.71 108	99.79 70	96.37 168	99.76 194	98.31 200	94.43 152	99.40 89	99.75 81	93.28 125	99.78 148	98.90 99	99.92 68	99.97 67

RE-MVS-def			98.13 60		99.79 70	96.37 168	99.76 194	98.31 200	94.43 152	99.40 89	99.75 81	92.95 135		98.90 99	99.92 68	99.97 67

TSAR-MVS + MP.		98.93 20	98.77 22	99.41 44	99.74 78	98.67 55	99.77 187	98.38 185	96.73 71	99.88 13	99.74 88	94.89 71	99.59 175	99.80 33	99.98 32	99.97 67
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		98.92 21	98.70 23	99.56 30	99.70 86	98.73 52	99.94 93	98.34 195	96.38 86	99.81 26	99.76 73	94.59 78	99.98 52	99.84 30	99.96 48	99.97 67
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
APD-MVS_3200maxsize		98.25 68	98.08 64	98.78 103	99.81 68	96.60 157	99.82 167	98.30 203	93.95 182	99.37 92	99.77 71	92.84 138	99.76 154	98.95 92	99.92 68	99.97 67

DP-MVS Recon		98.41 53	98.02 68	99.56 30	99.97 3	98.70 54	99.92 103	98.44 148	92.06 283	98.40 156	99.84 49	95.68 49	100.00 1	98.19 144	99.71 92	99.97 67

fmvsm_s_conf0.5_n_10		98.24 69	97.90 80	99.26 55	99.24 117	97.88 93	99.99 8	98.76 73	98.20 9	99.92 5	99.74 88	85.97 267	99.94 95	99.72 47	99.53 114	99.96 75

SF-MVS		98.67 33	98.40 39	99.50 35	99.77 73	98.67 55	99.90 117	98.21 218	93.53 198	99.81 26	99.89 27	94.70 77	99.86 130	99.84 30	99.93 65	99.96 75

SR-MVS		98.46 47	98.30 50	98.93 96	99.88 55	97.04 135	99.84 152	98.35 191	94.92 128	99.32 94	99.80 59	93.35 120	99.78 148	99.30 73	99.95 54	99.96 75

1314		96.84 152	95.96 184	99.48 40	96.74 338	98.52 64	98.31 413	98.86 59	95.82 104	89.91 347	98.98 210	87.49 239	99.96 77	97.80 169	99.73 91	99.96 75

114514_t		97.41 122	96.83 135	99.14 73	99.51 102	97.83 95	99.89 127	98.27 207	88.48 385	99.06 114	99.66 116	90.30 199	99.64 174	96.32 229	99.97 44	99.96 75

MVS_111021_HR		98.72 31	98.62 29	99.01 89	99.36 109	97.18 126	99.93 100	99.90 1	96.81 69	98.67 137	99.77 71	93.92 105	99.89 119	99.27 75	99.94 59	99.96 75

PAPM		98.60 37	98.42 38	99.14 73	96.05 355	98.96 29	99.90 117	99.35 24	96.68 73	98.35 158	99.66 116	96.45 35	98.51 284	99.45 66	99.89 74	99.96 75

3Dnovator+	91.53 11	96.31 190	95.24 224	99.52 33	96.88 329	98.64 60	99.72 215	98.24 211	95.27 121	88.42 392	98.98 210	82.76 324	99.94 95	97.10 196	99.83 81	99.96 75

fmvsm_l_conf0.5_n_a		99.00 18	98.91 15	99.28 53	99.21 118	97.91 92	99.98 24	98.85 62	98.25 5	99.92 5	99.75 81	94.72 75	99.97 65	99.87 26	99.64 98	99.95 83

MGCNet		99.06 13	98.84 19	99.72 14	99.76 74	99.21 23	99.99 8	99.34 25	98.70 2	99.44 82	99.75 81	93.24 127	99.99 40	99.94 15	99.41 132	99.95 83

EI-MVSNet-Vis-set		98.27 63	98.11 62	98.75 106	99.83 65	96.59 159	99.40 289	98.51 131	95.29 120	98.51 148	99.76 73	93.60 116	99.71 161	98.53 123	99.52 115	99.95 83

CHOSEN 1792x2688		96.81 153	96.53 150	97.64 201	98.91 151	93.07 309	99.65 237	99.80 3	95.64 110	95.39 274	98.86 236	84.35 304	99.90 114	96.98 201	99.16 146	99.95 83

AdaColmap		97.23 130	96.80 138	98.51 133	99.99 1	95.60 203	99.09 333	98.84 65	93.32 211	96.74 226	99.72 95	86.04 265	100.00 1	98.01 155	99.43 130	99.94 87

ZNCC-MVS		98.31 60	98.03 67	99.17 66	99.88 55	97.59 107	99.94 93	98.44 148	94.31 161	98.50 149	99.82 54	93.06 132	99.99 40	98.30 138	99.99 21	99.93 88

GST-MVS		98.27 63	97.97 72	99.17 66	99.92 37	97.57 108	99.93 100	98.39 181	94.04 178	98.80 127	99.74 88	92.98 134	100.00 1	98.16 146	99.76 89	99.93 88

MP-MVS		98.23 71	97.97 72	99.03 85	99.94 18	97.17 129	99.95 75	98.39 181	94.70 138	98.26 163	99.81 58	91.84 172	100.00 1	98.85 102	99.97 44	99.93 88
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HyFIR lowres test		96.66 167	96.43 157	97.36 237	99.05 130	93.91 283	99.70 227	99.80 3	90.54 339	96.26 248	98.08 298	92.15 165	98.23 318	96.84 209	95.46 286	99.93 88

CNLPA		97.76 101	97.38 110	98.92 97	99.53 99	96.84 142	99.87 133	98.14 232	93.78 190	96.55 234	99.69 105	92.28 159	99.98 52	97.13 194	99.44 129	99.93 88

原ACMM1				98.96 94	99.73 81	96.99 137		98.51 131	94.06 176	99.62 62	99.85 38	94.97 70	99.96 77	95.11 249	99.95 54	99.92 93

DELS-MVS		98.54 41	98.22 52	99.50 35	99.15 124	98.65 59	100.00 1	98.58 105	97.70 32	98.21 167	99.24 174	92.58 149	99.94 95	98.63 118	99.94 59	99.92 93
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
fmvsm_l_conf0.5_n_3		98.41 53	98.08 64	99.39 46	99.12 125	98.29 71	99.98 24	98.64 91	98.14 16	99.86 16	99.76 73	87.99 230	99.97 65	99.72 47	99.54 112	99.91 95

CSCG		97.10 136	97.04 126	97.27 243	99.89 51	91.92 340	99.90 117	99.07 37	88.67 380	95.26 278	99.82 54	93.17 130	99.98 52	98.15 147	99.47 125	99.90 96

DVP-MVS		99.30 4	99.16 3	99.73 13	99.93 29	99.29 17	99.95 75	98.32 198	97.28 45	99.83 24	99.91 19	97.22 21	100.00 1	99.99 5	100.00 1	99.89 97
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
patch_mono-2		98.24 69	99.12 5	95.59 305	99.67 89	86.91 437	99.95 75	98.89 52	97.60 34	99.90 7	99.76 73	96.54 34	99.98 52	99.94 15	99.82 85	99.88 98

MVS_111021_LR		98.42 52	98.38 41	98.53 130	99.39 107	95.79 191	99.87 133	99.86 2	96.70 72	98.78 128	99.79 63	92.03 168	99.90 114	99.17 80	99.86 79	99.88 98

HPM-MVS++		99.07 11	98.88 18	99.63 19	99.90 48	99.02 28	99.95 75	98.56 113	97.56 37	99.44 82	99.85 38	95.38 57	100.00 1	99.31 72	99.99 21	99.87 100

ACMMP		97.74 103	97.44 107	98.66 113	99.92 37	96.13 181	99.18 325	99.45 18	94.84 132	96.41 245	99.71 98	91.40 175	99.99 40	97.99 157	98.03 192	99.87 100
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
dcpmvs_2		97.42 121	98.09 63	95.42 312	99.58 97	87.24 433	99.23 321	96.95 407	94.28 164	98.93 121	99.73 92	94.39 88	99.16 208	99.89 22	99.82 85	99.86 102

fmvsm_s_conf0.5_n_5		98.08 77	97.71 92	99.17 66	98.67 167	97.69 105	99.99 8	98.57 107	97.40 40	99.89 11	99.69 105	85.99 266	99.96 77	99.80 33	99.40 133	99.85 103

3Dnovator	91.47 12	96.28 193	95.34 220	99.08 82	96.82 332	97.47 115	99.45 285	98.81 67	95.52 115	89.39 363	99.00 205	81.97 330	99.95 86	97.27 187	99.83 81	99.84 104

fmvsm_s_conf0.5_n_9		98.15 73	98.02 68	98.55 124	99.28 114	95.84 189	99.99 8	98.57 107	98.17 13	99.93 3	99.74 88	87.04 247	99.97 65	99.86 28	99.59 109	99.83 105

CANet		98.27 63	97.82 87	99.63 19	99.72 83	99.10 25	99.98 24	98.51 131	97.00 59	98.52 146	99.71 98	87.80 231	99.95 86	99.75 42	99.38 134	99.83 105

test_fmvsmconf0.1_n		97.74 103	97.44 107	98.64 115	95.76 366	96.20 177	99.94 93	98.05 240	98.17 13	98.89 123	99.42 142	87.65 234	99.90 114	99.50 62	99.60 108	99.82 107

Patchmatch-test		92.65 327	91.50 338	96.10 287	96.85 330	90.49 385	91.50 501	97.19 357	82.76 455	90.23 339	95.59 386	95.02 66	98.00 331	77.41 469	96.98 238	99.82 107

EI-MVSNet-UG-set		98.14 74	97.99 70	98.60 118	99.80 69	96.27 170	99.36 299	98.50 137	95.21 122	98.30 160	99.75 81	93.29 124	99.73 160	98.37 133	99.30 140	99.81 109

HY-MVS	92.50 7	97.79 99	97.17 122	99.63 19	98.98 139	99.32 11	97.49 439	99.52 14	95.69 109	98.32 159	97.41 319	93.32 122	99.77 151	98.08 152	95.75 276	99.81 109

mvsany_test1		97.82 95	97.90 80	97.55 212	98.77 161	93.04 312	99.80 175	97.93 252	96.95 61	99.61 69	99.68 112	90.92 186	99.83 141	99.18 79	98.29 181	99.80 111

test_yl		97.83 92	97.37 111	99.21 60	99.18 120	97.98 87	99.64 241	99.27 27	91.43 306	97.88 182	98.99 208	95.84 47	99.84 139	98.82 103	95.32 291	99.79 112

DCV-MVSNet		97.83 92	97.37 111	99.21 60	99.18 120	97.98 87	99.64 241	99.27 27	91.43 306	97.88 182	98.99 208	95.84 47	99.84 139	98.82 103	95.32 291	99.79 112

Patchmatch-RL test		86.90 417	85.98 416	89.67 446	84.45 504	75.59 491	89.71 509	92.43 499	86.89 411	77.83 477	90.94 476	94.22 96	93.63 480	87.75 390	69.61 476	99.79 112

WTY-MVS		98.10 76	97.60 98	99.60 24	98.92 147	99.28 19	99.89 127	99.52 14	95.58 112	98.24 165	99.39 149	93.33 121	99.74 157	97.98 159	95.58 285	99.78 115

CHOSEN 280x420		99.01 16	99.03 11	98.95 95	99.38 108	98.87 36	98.46 403	99.42 21	97.03 57	99.02 117	99.09 190	99.35 2	98.21 319	99.73 46	99.78 88	99.77 116

MP-MVS-pluss		98.07 78	97.64 96	99.38 49	99.74 78	98.41 70	99.74 204	98.18 222	93.35 209	96.45 238	99.85 38	92.64 146	99.97 65	98.91 98	99.89 74	99.77 116
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
EPMVS		96.53 176	96.01 177	98.09 162	98.43 191	96.12 183	96.36 465	99.43 20	93.53 198	97.64 190	95.04 416	94.41 84	98.38 301	91.13 331	98.11 188	99.75 118

Vis-MVSNet (Re-imp)		96.32 189	95.98 180	97.35 239	97.93 227	94.82 243	99.47 280	98.15 231	91.83 290	95.09 279	99.11 189	91.37 176	97.47 353	93.47 295	97.43 203	99.74 119

DP-MVS		94.54 263	93.42 285	97.91 176	99.46 106	94.04 277	98.93 363	97.48 308	81.15 462	90.04 344	99.55 132	87.02 248	99.95 86	88.97 368	98.11 188	99.73 120

TAPA-MVS	92.12 8	94.42 271	93.60 277	96.90 260	99.33 111	91.78 349	99.78 181	98.00 244	89.89 357	94.52 286	99.47 138	91.97 169	99.18 205	69.90 486	99.52 115	99.73 120
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MGCFI-Net		97.00 143	96.22 167	99.34 51	98.86 155	98.80 42	99.67 235	97.30 334	94.31 161	97.77 188	99.41 146	86.36 260	99.50 181	98.38 131	93.90 312	99.72 122

sasdasda		97.09 138	96.32 162	99.39 46	98.93 144	98.95 30	99.72 215	97.35 322	94.45 148	97.88 182	99.42 142	86.71 252	99.52 177	98.48 125	93.97 310	99.72 122

canonicalmvs		97.09 138	96.32 162	99.39 46	98.93 144	98.95 30	99.72 215	97.35 322	94.45 148	97.88 182	99.42 142	86.71 252	99.52 177	98.48 125	93.97 310	99.72 122

0.3-1-1-0.015		94.22 279	93.13 300	97.49 222	95.50 381	94.17 273	100.00 1	98.22 214	88.44 387	97.14 208	97.04 334	92.73 142	98.59 275	96.45 226	72.65 466	99.70 125

0.4-1-1-0.1		94.07 285	92.95 303	97.42 229	95.24 386	94.00 280	100.00 1	98.22 214	88.27 391	96.81 224	96.93 338	92.27 160	98.56 279	96.21 232	72.63 468	99.70 125

0.4-1-1-0.2		94.14 280	93.02 302	97.51 217	95.45 382	94.25 269	100.00 1	98.22 214	88.53 384	96.83 222	96.95 337	92.25 161	98.57 278	96.34 227	72.65 466	99.70 125

TESTMET0.1,1		96.74 162	96.26 164	98.16 155	97.36 285	96.48 161	99.96 56	98.29 204	91.93 286	95.77 264	98.07 299	95.54 51	98.29 311	90.55 345	98.89 158	99.70 125

PatchmatchNet		95.94 207	95.45 209	97.39 234	97.83 233	94.41 260	96.05 472	98.40 178	92.86 234	97.09 209	95.28 408	94.21 98	98.07 328	89.26 366	98.11 188	99.70 125
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VNet		97.21 131	96.57 149	99.13 77	98.97 140	97.82 96	99.03 347	99.21 32	94.31 161	99.18 105	98.88 227	86.26 262	99.89 119	98.93 94	94.32 304	99.69 130

Anonymous202405211		93.10 313	91.99 326	96.40 278	99.10 126	89.65 402	98.88 369	97.93 252	83.71 445	94.00 298	98.75 246	68.79 442	99.88 125	95.08 250	91.71 324	99.68 131

mvs_anonymous		95.65 228	95.03 234	97.53 214	98.19 210	95.74 194	99.33 302	97.49 307	90.87 324	90.47 338	97.10 328	88.23 227	97.16 369	95.92 236	97.66 200	99.68 131

GG-mvs-BLEND				98.54 128	98.21 208	98.01 85	93.87 484	98.52 128		97.92 177	97.92 306	99.02 3	97.94 337	98.17 145	99.58 110	99.67 133

gg-mvs-nofinetune		93.51 303	91.86 330	98.47 135	97.72 245	97.96 90	92.62 495	98.51 131	74.70 488	97.33 201	69.59 522	98.91 4	97.79 341	97.77 174	99.56 111	99.67 133

alignmvs		97.81 96	97.33 113	99.25 56	98.77 161	98.66 57	99.99 8	98.44 148	94.40 156	98.41 154	99.47 138	93.65 114	99.42 191	98.57 119	94.26 306	99.67 133

LFMVS		94.75 257	93.56 280	98.30 148	99.03 131	95.70 197	98.74 384	97.98 247	87.81 398	98.47 150	99.39 149	67.43 451	99.53 176	98.01 155	95.20 294	99.67 133

MDTV_nov1_ep13_2view						96.26 171	96.11 471		91.89 287	98.06 171		94.40 85		94.30 273		99.67 133

MAR-MVS		97.43 117	97.19 120	98.15 158	99.47 104	94.79 245	99.05 344	98.76 73	92.65 250	98.66 138	99.82 54	88.52 225	99.98 52	98.12 148	99.63 99	99.67 133
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
BridgeMVS		98.27 63	97.99 70	99.11 78	98.64 171	98.43 69	99.47 280	97.79 267	94.56 142	99.74 45	98.35 285	94.33 92	99.25 197	99.12 81	99.96 48	99.64 139

test2506		97.53 114	97.19 120	98.58 122	98.66 169	96.90 141	98.81 378	99.77 5	94.93 126	97.95 176	98.96 214	92.51 152	99.20 203	94.93 254	98.15 185	99.64 139

test1111		95.57 230	94.98 236	97.37 235	98.56 176	93.37 305	98.86 373	98.45 143	94.95 125	96.63 228	98.95 219	75.21 413	99.11 210	95.02 251	98.14 187	99.64 139

ECVR-MVS		95.66 227	95.05 233	97.51 217	98.66 169	93.71 287	98.85 375	98.45 143	94.93 126	96.86 219	98.96 214	75.22 412	99.20 203	95.34 244	98.15 185	99.64 139

balanced_ft_v1		96.88 150	96.52 151	97.96 169	98.60 173	94.94 238	99.41 288	97.56 297	93.53 198	99.42 86	97.89 309	83.33 319	99.31 194	99.29 74	99.62 100	99.64 139

test-LLR		96.47 178	96.04 176	97.78 187	97.02 312	95.44 208	99.96 56	98.21 218	94.07 174	95.55 270	96.38 357	93.90 107	98.27 315	90.42 348	98.83 162	99.64 139

test-mter		96.39 184	95.93 189	97.78 187	97.02 312	95.44 208	99.96 56	98.21 218	91.81 292	95.55 270	96.38 357	95.17 60	98.27 315	90.42 348	98.83 162	99.64 139

fmvsm_s_conf0.5_n_6		98.27 63	97.96 75	99.23 58	97.66 253	98.11 79	99.98 24	98.64 91	97.85 27	99.87 14	99.72 95	88.86 221	99.93 105	99.64 55	99.36 136	99.63 146

MonoMVSNet		94.82 250	94.43 250	95.98 290	94.54 398	90.73 378	99.03 347	97.06 393	93.16 219	93.15 307	95.47 394	88.29 226	97.57 349	97.85 166	91.33 327	99.62 147

EC-MVSNet		97.38 124	97.24 117	97.80 183	97.41 275	95.64 201	99.99 8	97.06 393	94.59 141	99.63 59	99.32 154	89.20 216	98.14 322	98.76 108	99.23 144	99.62 147

sss		97.57 113	97.03 127	99.18 63	98.37 195	98.04 84	99.73 211	99.38 22	93.46 203	98.76 133	99.06 195	91.21 177	99.89 119	96.33 228	97.01 237	99.62 147

QAPM		95.40 234	94.17 259	99.10 79	96.92 324	97.71 101	99.40 289	98.68 84	89.31 362	88.94 376	98.89 226	82.48 326	99.96 77	93.12 304	99.83 81	99.62 147

MVS_Test		96.46 179	95.74 198	98.61 117	98.18 211	97.23 124	99.31 307	97.15 366	91.07 320	98.84 124	97.05 332	88.17 228	98.97 219	94.39 269	97.50 202	99.61 151

EPNet		98.49 45	98.40 39	98.77 105	99.62 92	96.80 148	99.90 117	99.51 16	97.60 34	99.20 102	99.36 152	93.71 113	99.91 112	97.99 157	98.71 167	99.61 151
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IB-MVS	92.85 6	94.99 247	93.94 268	98.16 155	97.72 245	95.69 199	99.99 8	98.81 67	94.28 164	92.70 314	96.90 339	95.08 63	99.17 206	96.07 233	73.88 460	99.60 153
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
ET-MVSNet_ETH3D		94.37 273	93.28 294	97.64 201	98.30 200	97.99 86	99.99 8	97.61 291	94.35 157	71.57 493	99.45 141	96.23 40	95.34 458	96.91 207	85.14 381	99.59 154

EIA-MVS		97.53 114	97.46 104	97.76 191	98.04 221	94.84 241	99.98 24	97.61 291	94.41 155	97.90 178	99.59 125	92.40 156	98.87 227	98.04 154	99.13 148	99.59 154

GSMVS																99.59 154

sam_mvs1												94.72 75				99.59 154

Fast-Effi-MVS+		95.02 246	94.19 258	97.52 216	97.88 229	94.55 252	99.97 42	97.08 384	88.85 376	94.47 288	97.96 305	84.59 299	98.41 293	89.84 357	97.10 227	99.59 154

SCA		94.69 258	93.81 272	97.33 240	97.10 303	94.44 256	98.86 373	98.32 198	93.30 212	96.17 254	95.59 386	76.48 399	97.95 335	91.06 333	97.43 203	99.59 154

MVSMamba_PlusPlus		97.83 92	97.45 106	98.99 90	98.60 173	98.15 73	99.58 255	97.74 276	90.34 347	99.26 101	98.32 288	94.29 94	99.23 198	99.03 90	99.89 74	99.58 160

PVSNet	91.05 13	97.13 135	96.69 144	98.45 138	99.52 100	95.81 190	99.95 75	99.65 12	94.73 136	99.04 115	99.21 178	84.48 302	99.95 86	94.92 255	98.74 166	99.58 160

PVSNet_Blended		97.94 82	97.64 96	98.83 100	99.59 93	96.99 137	100.00 1	99.10 34	95.38 117	98.27 161	99.08 191	89.00 219	99.95 86	99.12 81	99.25 142	99.57 162

ab-mvs		94.69 258	93.42 285	98.51 133	98.07 219	96.26 171	96.49 463	98.68 84	90.31 348	94.54 285	97.00 335	76.30 401	99.71 161	95.98 235	93.38 318	99.56 163

test_fmvsmconf0.01_n		96.39 184	95.74 198	98.32 147	91.47 460	95.56 204	99.84 152	97.30 334	97.74 30	97.89 180	99.35 153	79.62 363	99.85 131	99.25 76	99.24 143	99.55 164

Test_1112_low_res		95.72 221	94.83 240	98.42 142	97.79 236	96.41 164	99.65 237	96.65 432	92.70 246	92.86 313	96.13 368	92.15 165	99.30 195	91.88 322	93.64 314	99.55 164

1112_ss		96.01 204	95.20 226	98.42 142	97.80 235	96.41 164	99.65 237	96.66 431	92.71 245	92.88 312	99.40 147	92.16 164	99.30 195	91.92 321	93.66 313	99.55 164

DeepC-MVS	94.51 4	96.92 149	96.40 160	98.45 138	99.16 123	95.90 187	99.66 236	98.06 238	96.37 89	94.37 292	99.49 137	83.29 320	99.90 114	97.63 179	99.61 105	99.55 164
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CS-MVS		97.79 99	97.91 79	97.43 228	99.10 126	94.42 259	99.99 8	97.10 380	95.07 123	99.68 52	99.75 81	92.95 135	98.34 305	98.38 131	99.14 147	99.54 168

LCM-MVSNet-Re		92.31 334	92.60 312	91.43 426	97.53 265	79.27 485	99.02 349	91.83 503	92.07 281	80.31 463	94.38 440	83.50 313	95.48 454	97.22 192	97.58 201	99.54 168

casdiffmvs		96.42 183	95.97 183	97.77 189	97.30 292	94.98 235	99.84 152	97.09 383	93.75 193	96.58 231	99.26 169	85.07 285	98.78 247	97.77 174	97.04 232	99.54 168
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
dp		95.05 244	94.43 250	96.91 258	97.99 223	92.73 320	96.29 468	97.98 247	89.70 359	95.93 260	94.67 431	93.83 111	98.45 289	86.91 406	96.53 250	99.54 168

PRO-TEST		95.68 226	96.10 173	94.41 354	98.58 175	84.60 453	99.77 187	96.84 419	94.33 160	97.96 175	98.12 296	80.76 350	99.12 209	99.21 78	99.36 136	99.53 172

RRT-MVS		96.24 196	95.68 202	97.94 173	97.65 254	94.92 239	99.27 317	97.10 380	92.79 240	97.43 197	97.99 303	81.85 332	99.37 193	98.46 127	98.57 169	99.53 172

SD_0403		92.63 328	93.38 289	90.40 440	97.32 290	77.91 487	97.75 437	98.03 243	91.89 287	90.83 334	98.29 292	82.00 329	93.79 478	88.51 376	95.75 276	99.52 174

SPE-MVS-test		97.88 86	97.94 77	97.70 196	99.28 114	95.20 228	99.98 24	97.15 366	95.53 114	99.62 62	99.79 63	92.08 167	98.38 301	98.75 109	99.28 141	99.52 174

Effi-MVS+		96.30 191	95.69 200	98.16 155	97.85 232	96.26 171	97.41 442	97.21 356	90.37 345	98.65 140	98.58 268	86.61 256	98.70 261	97.11 195	97.37 208	99.52 174

mvsmamba		96.94 146	96.73 141	97.55 212	97.99 223	94.37 264	99.62 244	97.70 278	93.13 222	98.42 153	97.92 306	88.02 229	98.75 252	98.78 106	99.01 155	99.52 174

PatchT		90.38 374	88.75 391	95.25 319	95.99 357	90.16 392	91.22 503	97.54 300	76.80 480	97.26 204	86.01 504	91.88 170	96.07 442	66.16 497	95.91 270	99.51 178

tpm		93.70 299	93.41 287	94.58 342	95.36 385	87.41 431	97.01 452	96.90 415	90.85 325	96.72 227	94.14 444	90.40 197	96.84 396	90.75 342	88.54 349	99.51 178

CostFormer		96.10 199	95.88 193	96.78 264	97.03 309	92.55 326	97.08 451	97.83 265	90.04 354	98.72 135	94.89 425	95.01 67	98.29 311	96.54 222	95.77 274	99.50 180

tpmrst		96.27 194	95.98 180	97.13 249	97.96 225	93.15 308	96.34 466	98.17 223	92.07 281	98.71 136	95.12 413	93.91 106	98.73 254	94.91 257	96.62 248	99.50 180

casdiffmvs_mvg		96.43 181	95.94 188	97.89 178	97.44 273	95.47 206	99.86 144	97.29 342	93.35 209	96.03 256	99.19 181	85.39 280	98.72 257	97.89 165	97.04 232	99.49 182
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E3new		96.75 159	96.43 157	97.71 194	97.79 236	94.83 242	99.80 175	97.33 326	93.52 201	97.49 195	99.31 157	87.73 232	98.83 231	97.52 181	97.40 207	99.48 183

viewmanbaseed2359cas		96.45 180	96.07 174	97.59 210	97.55 263	94.59 250	99.70 227	97.33 326	93.62 197	97.00 215	99.32 154	85.57 275	98.71 258	97.26 190	97.33 210	99.47 184

IS-MVSNet		96.29 192	95.90 191	97.45 224	98.13 216	94.80 244	99.08 335	97.61 291	92.02 285	95.54 272	98.96 214	90.64 192	98.08 326	93.73 291	97.41 206	99.47 184

E2		96.36 186	95.95 186	97.60 207	97.41 275	94.52 253	99.71 220	97.33 326	93.20 215	97.02 212	99.07 193	85.37 281	98.82 234	97.27 187	97.14 224	99.46 186

E3		96.36 186	95.95 186	97.60 207	97.37 282	94.52 253	99.71 220	97.33 326	93.18 217	97.02 212	99.07 193	85.45 279	98.82 234	97.27 187	97.14 224	99.46 186

viewcassd2359sk11		96.59 171	96.23 165	97.66 199	97.63 256	94.70 247	99.77 187	97.33 326	93.41 206	97.34 200	99.17 183	86.72 251	98.83 231	97.40 184	97.32 211	99.46 186

ETV-MVS		97.92 84	97.80 88	98.25 151	98.14 215	96.48 161	99.98 24	97.63 285	95.61 111	99.29 98	99.46 140	92.55 150	98.82 234	99.02 91	98.54 172	99.46 186

baseline		96.43 181	95.98 180	97.76 191	97.34 287	95.17 230	99.51 272	97.17 361	93.92 184	96.90 218	99.28 161	85.37 281	98.64 272	97.50 182	96.86 242	99.46 186

SymmetryMVS		97.64 110	97.46 104	98.17 154	98.74 163	95.39 213	99.61 248	99.26 29	96.52 78	98.61 142	99.31 157	92.73 142	99.67 169	96.77 215	95.63 283	99.45 191

lupinMVS		97.85 90	97.60 98	98.62 116	97.28 294	97.70 103	99.99 8	97.55 298	95.50 116	99.43 84	99.67 114	90.92 186	98.71 258	98.40 130	99.62 100	99.45 191

PMMVS		96.76 157	96.76 139	96.76 265	98.28 203	92.10 335	99.91 111	97.98 247	94.12 171	99.53 74	99.39 149	86.93 250	98.73 254	96.95 204	97.73 196	99.45 191

UA-Net		96.54 175	95.96 184	98.27 150	98.23 206	95.71 196	98.00 429	98.45 143	93.72 194	98.41 154	99.27 165	88.71 224	99.66 172	91.19 330	97.69 197	99.44 194

viewdifsd2359ckpt09		96.21 197	95.77 196	97.53 214	97.69 249	94.50 255	99.78 181	97.23 353	92.88 233	96.58 231	99.26 169	84.85 290	98.66 269	96.61 219	97.02 235	99.43 195

CVMVSNet		94.68 260	94.94 238	93.89 382	96.80 333	86.92 436	99.06 340	98.98 41	94.45 148	94.23 296	99.02 199	85.60 274	95.31 459	90.91 338	95.39 289	99.43 195

PVSNet_Blended_VisFu		97.27 127	96.81 137	98.66 113	98.81 158	96.67 153	99.92 103	98.64 91	94.51 144	96.38 246	98.49 276	89.05 217	99.88 125	97.10 196	98.34 176	99.43 195

hybridcas		96.09 201	95.62 204	97.50 219	97.37 282	94.44 256	99.84 152	97.16 363	93.16 219	96.03 256	99.21 178	84.19 305	98.65 271	96.53 223	97.07 228	99.42 198

Casviewmamba		96.25 195	95.89 192	97.32 242	97.45 272	93.68 290	99.80 175	97.22 355	93.38 207	96.86 219	99.28 161	84.64 298	98.87 227	97.18 193	97.19 217	99.41 199

PLC	95.54 3	97.93 83	97.89 82	98.05 165	99.82 66	94.77 246	99.92 103	98.46 142	93.93 183	97.20 205	99.27 165	95.44 56	99.97 65	97.41 183	99.51 118	99.41 199
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	94.20 5	95.18 240	94.10 260	98.43 140	98.55 179	95.99 185	97.91 432	97.31 333	90.35 346	89.48 362	99.22 175	85.19 284	99.89 119	90.40 350	98.47 174	99.41 199
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
tpm2		95.47 232	95.18 227	96.35 281	96.91 325	91.70 355	96.96 454	97.93 252	88.04 394	98.44 151	95.40 397	93.32 122	97.97 332	94.00 277	95.61 284	99.38 202

OMC-MVS		97.28 126	97.23 118	97.41 232	99.76 74	93.36 306	99.65 237	97.95 250	96.03 98	97.41 198	99.70 101	89.61 207	99.51 179	96.73 217	98.25 182	99.38 202

GDP-MVS		97.88 86	97.59 100	98.75 106	97.59 260	97.81 97	99.95 75	97.37 320	94.44 151	99.08 110	99.58 128	97.13 25	99.08 212	94.99 252	98.17 183	99.37 204

GeoE		94.36 275	93.48 283	96.99 255	97.29 293	93.54 298	99.96 56	96.72 429	88.35 389	93.43 302	98.94 221	82.05 328	98.05 329	88.12 387	96.48 253	99.37 204

guyue		97.15 134	96.82 136	98.15 158	97.56 262	96.25 175	99.71 220	97.84 264	95.75 107	98.13 170	98.65 257	87.58 236	98.82 234	98.29 139	97.91 195	99.36 206

BP-MVS1		98.33 59	98.18 56	98.81 101	97.44 273	97.98 87	99.96 56	98.17 223	94.88 130	98.77 130	99.59 125	97.59 8	99.08 212	98.24 142	98.93 157	99.36 206

ADS-MVSNet2		93.80 294	93.88 270	93.55 392	97.87 230	85.94 443	94.24 480	96.84 419	90.07 352	96.43 243	94.48 436	90.29 200	95.37 457	87.44 392	97.23 214	99.36 206

ADS-MVSNet		94.79 253	94.02 265	97.11 251	97.87 230	93.79 284	94.24 480	98.16 228	90.07 352	96.43 243	94.48 436	90.29 200	98.19 320	87.44 392	97.23 214	99.36 206

FA-MVS(test-final)		95.86 210	95.09 231	98.15 158	97.74 240	95.62 202	96.31 467	98.17 223	91.42 308	96.26 248	96.13 368	90.56 194	99.47 189	92.18 313	97.07 228	99.35 210

BH-RMVSNet		95.18 240	94.31 255	97.80 183	98.17 212	95.23 226	99.76 194	97.53 302	92.52 263	94.27 295	99.25 172	76.84 393	98.80 243	90.89 339	99.54 112	99.35 210

TR-MVS		94.54 263	93.56 280	97.49 222	97.96 225	94.34 266	98.71 387	97.51 305	90.30 349	94.51 287	98.69 253	75.56 407	98.77 248	92.82 307	95.99 264	99.35 210

diffmvs		97.00 143	96.64 145	98.09 162	97.64 255	96.17 180	99.81 169	97.19 357	94.67 140	98.95 119	99.28 161	86.43 257	98.76 250	98.37 133	97.42 205	99.33 213
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
JIA-IIPM		91.76 348	90.70 349	94.94 327	96.11 353	87.51 430	93.16 493	98.13 233	75.79 484	97.58 191	77.68 515	92.84 138	97.97 332	88.47 377	96.54 249	99.33 213

hybridnocas07		96.57 173	96.16 170	97.81 182	97.36 285	95.32 218	99.81 169	97.12 372	94.17 168	98.02 173	98.90 225	85.05 286	98.80 243	97.85 166	97.18 218	99.32 215

icg_test_0407_2		95.04 245	94.78 244	95.84 299	96.97 318	91.64 358	98.63 395	97.12 372	92.33 272	95.60 268	98.88 227	85.65 271	96.56 412	92.12 314	95.70 279	99.32 215

IMVS_0407		95.21 239	94.80 243	96.46 275	96.97 318	91.64 358	98.81 378	97.12 372	92.33 272	95.60 268	98.88 227	85.65 271	98.42 291	92.12 314	95.70 279	99.32 215

IMVS_0404		93.83 290	93.17 296	95.80 301	96.97 318	91.64 358	97.78 436	97.12 372	92.33 272	90.87 333	98.88 227	76.78 394	96.43 421	92.12 314	95.70 279	99.32 215

IMVS_0403		95.25 238	94.81 242	96.58 272	96.97 318	91.64 358	98.97 357	97.12 372	92.33 272	95.43 273	98.88 227	85.78 269	98.79 245	92.12 314	95.70 279	99.32 215

viewdifsd2359ckpt13		96.19 198	95.77 196	97.45 224	97.62 257	94.40 262	99.70 227	97.23 353	92.76 242	96.63 228	99.05 196	84.96 289	98.64 272	96.65 218	97.35 209	99.31 220

FE-MVS		95.70 225	95.01 235	97.79 185	98.21 208	94.57 251	95.03 479	98.69 82	88.90 374	97.50 194	96.19 364	92.60 148	99.49 186	89.99 355	97.94 194	99.31 220

thres200		96.96 145	96.21 168	99.22 59	98.97 140	98.84 39	99.85 147	99.71 7	93.17 218	96.26 248	98.88 227	89.87 204	99.51 179	94.26 274	94.91 296	99.31 220

CDS-MVSNet		96.34 188	96.07 174	97.13 249	97.37 282	94.96 236	99.53 269	97.91 256	91.55 300	95.37 275	98.32 288	95.05 65	97.13 372	93.80 287	95.75 276	99.30 223
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Vis-MVSNet		95.72 221	95.15 229	97.45 224	97.62 257	94.28 267	99.28 315	98.24 211	94.27 166	96.84 221	98.94 221	79.39 365	98.76 250	93.25 298	98.49 173	99.30 223
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
myMVS_eth3d28		97.86 88	97.59 100	98.68 110	98.50 186	97.26 122	99.92 103	98.55 119	93.79 189	98.26 163	98.75 246	95.20 59	99.48 187	98.93 94	96.40 254	99.29 225

test_vis1_n		93.61 301	93.03 301	95.35 314	95.86 361	86.94 435	99.87 133	96.36 442	96.85 64	99.54 73	98.79 244	52.41 489	99.83 141	98.64 116	98.97 156	99.29 225

onestephybrid01		96.75 159	96.44 156	97.71 194	97.47 271	95.03 234	99.83 160	97.27 344	94.15 169	98.66 138	99.25 172	85.72 270	98.81 238	98.42 129	97.17 222	99.28 227

viewmacassd2359aftdt		95.93 208	95.45 209	97.36 237	97.09 304	94.12 276	99.57 259	97.26 347	93.05 227	96.50 235	99.17 183	82.76 324	98.68 264	96.61 219	97.04 232	99.28 227

ETVMVS		97.03 142	96.64 145	98.20 153	98.67 167	97.12 130	99.89 127	98.57 107	91.10 319	98.17 168	98.59 265	93.86 109	98.19 320	95.64 242	95.24 293	99.28 227

casdiffseed414692147		95.07 243	94.26 256	97.50 219	97.01 315	94.70 247	99.58 255	97.02 397	91.27 312	94.66 284	98.82 243	80.79 349	98.55 282	93.39 297	95.79 273	99.27 230

E4		96.01 204	95.53 208	97.44 227	97.05 308	94.23 270	99.57 259	97.30 334	92.72 243	96.47 237	99.03 198	83.98 309	98.83 231	96.92 205	96.77 243	99.27 230

thres100view900		96.74 162	95.92 190	99.18 63	98.90 152	98.77 48	99.74 204	99.71 7	92.59 254	95.84 261	98.86 236	89.25 213	99.50 181	93.84 283	94.57 300	99.27 230

tfpn200view9		96.79 154	95.99 178	99.19 62	98.94 142	98.82 40	99.78 181	99.71 7	92.86 234	96.02 258	98.87 234	89.33 211	99.50 181	93.84 283	94.57 300	99.27 230

MVSFormer		96.94 146	96.60 147	97.95 170	97.28 294	97.70 103	99.55 266	97.27 344	91.17 314	99.43 84	99.54 134	90.92 186	96.89 392	94.67 265	99.62 100	99.25 234

jason		97.24 129	96.86 133	98.38 145	95.73 369	97.32 119	99.97 42	97.40 316	95.34 119	98.60 145	99.54 134	87.70 233	98.56 279	97.94 160	99.47 125	99.25 234
jason: jason.
EPP-MVSNet		96.69 165	96.60 147	96.96 256	97.74 240	93.05 311	99.37 297	98.56 113	88.75 378	95.83 263	99.01 201	96.01 41	98.56 279	96.92 205	97.20 216	99.25 234

viewmamba		96.61 169	96.34 161	97.42 229	97.26 297	94.37 264	99.83 160	97.16 363	94.51 144	97.89 180	99.26 169	86.38 258	98.66 269	97.70 177	97.06 231	99.23 237

viewdifsd2359ckpt07		95.83 213	95.42 211	97.07 252	97.40 277	93.04 312	99.60 251	97.24 351	92.39 269	96.09 255	99.14 188	83.07 323	98.93 223	97.02 198	96.87 240	99.23 237

AstraMVS		96.57 173	96.46 155	96.91 258	96.79 336	92.50 327	99.90 117	97.38 317	96.02 99	97.79 187	99.32 154	86.36 260	98.99 216	98.26 141	96.33 257	99.23 237

hybrid		96.53 176	96.15 171	97.67 197	97.39 279	95.12 232	99.80 175	97.15 366	93.38 207	98.23 166	99.16 186	85.20 283	98.70 261	97.92 161	97.15 223	99.20 240

EPNet_dtu		95.71 223	95.39 214	96.66 269	98.92 147	93.41 302	99.57 259	98.90 50	96.19 95	97.52 192	98.56 270	92.65 145	97.36 355	77.89 467	98.33 177	99.20 240
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GA-MVS		93.83 290	92.84 305	96.80 263	95.73 369	93.57 296	99.88 130	97.24 351	92.57 258	92.92 310	96.66 349	78.73 373	97.67 346	87.75 390	94.06 309	99.17 242

thisisatest0515		97.41 122	97.02 128	98.59 121	97.71 247	97.52 110	99.97 42	98.54 123	91.83 290	97.45 196	99.04 197	97.50 10	99.10 211	94.75 262	96.37 256	99.16 243

thres600view7		96.69 165	95.87 194	99.14 73	98.90 152	98.78 47	99.74 204	99.71 7	92.59 254	95.84 261	98.86 236	89.25 213	99.50 181	93.44 296	94.50 303	99.16 243

thres400		96.78 156	95.99 178	99.16 69	98.94 142	98.82 40	99.78 181	99.71 7	92.86 234	96.02 258	98.87 234	89.33 211	99.50 181	93.84 283	94.57 300	99.16 243

TAMVS		95.85 211	95.58 205	96.65 270	97.07 306	93.50 299	99.17 326	97.82 266	91.39 310	95.02 280	98.01 300	92.20 163	97.30 362	93.75 290	95.83 272	99.14 246

diffmvs_AUTHOR		96.75 159	96.41 159	97.79 185	97.20 299	95.46 207	99.69 230	97.15 366	94.46 147	98.78 128	99.21 178	85.64 273	98.77 248	98.27 140	97.31 212	99.13 247

CR-MVSNet		93.45 306	92.62 311	95.94 292	96.29 348	92.66 322	92.01 498	96.23 444	92.62 251	96.94 216	93.31 453	91.04 183	96.03 443	79.23 458	95.96 266	99.13 247

RPMNet		89.76 390	87.28 407	97.19 244	96.29 348	92.66 322	92.01 498	98.31 200	70.19 496	96.94 216	85.87 505	87.25 244	99.78 148	62.69 506	95.96 266	99.13 247

UBG		97.84 91	97.69 93	98.29 149	98.38 193	96.59 159	99.90 117	98.53 126	93.91 185	98.52 146	98.42 283	96.77 27	99.17 206	98.54 121	96.20 259	99.11 250

tpm cat1		93.51 303	92.52 318	96.47 273	97.77 238	91.47 367	96.13 470	98.06 238	80.98 463	92.91 311	93.78 447	89.66 205	98.87 227	87.03 402	96.39 255	99.09 251

BH-w/o		95.71 223	95.38 219	96.68 268	98.49 188	92.28 331	99.84 152	97.50 306	92.12 280	92.06 322	98.79 244	84.69 297	98.67 266	95.29 246	99.66 96	99.09 251

fmvsm_s_conf0.5_n_a		97.73 105	97.72 90	97.77 189	98.63 172	94.26 268	99.96 56	98.92 49	97.18 52	99.75 42	99.69 105	87.00 249	99.97 65	99.46 65	98.89 158	99.08 253

testing11		97.48 116	97.27 116	98.10 161	98.36 196	96.02 184	99.92 103	98.45 143	93.45 205	98.15 169	98.70 252	95.48 55	99.22 199	97.85 166	95.05 295	99.07 254

NormalMVS		97.90 85	97.85 85	98.04 166	99.86 59	95.39 213	99.61 248	97.78 271	96.52 78	98.61 142	99.31 157	92.73 142	99.67 169	96.77 215	99.48 122	99.06 255

KinetiMVS		96.10 199	95.29 223	98.53 130	97.08 305	97.12 130	99.56 263	98.12 234	94.78 133	98.44 151	98.94 221	80.30 359	99.39 192	91.56 326	98.79 164	99.06 255

testing222		97.08 141	96.75 140	98.06 164	98.56 176	96.82 143	99.85 147	98.61 99	92.53 262	98.84 124	98.84 240	93.36 119	98.30 310	95.84 238	94.30 305	99.05 257

E5new		95.83 213	95.39 214	97.15 245	97.03 309	93.59 292	99.32 305	97.30 334	92.58 256	96.45 238	99.00 205	83.37 316	98.81 238	96.81 211	96.65 246	99.04 258

E6new		95.83 213	95.39 214	97.14 247	97.00 316	93.58 294	99.31 307	97.30 334	92.57 258	96.45 238	99.01 201	83.44 314	98.81 238	96.80 213	96.66 244	99.04 258

E6		95.83 213	95.39 214	97.14 247	97.00 316	93.58 294	99.31 307	97.30 334	92.57 258	96.45 238	99.01 201	83.44 314	98.81 238	96.80 213	96.66 244	99.04 258

E5		95.83 213	95.39 214	97.15 245	97.03 309	93.59 292	99.32 305	97.30 334	92.58 256	96.45 238	99.00 205	83.37 316	98.81 238	96.81 211	96.65 246	99.04 258

testing91		97.16 133	96.90 131	97.97 168	98.35 198	95.67 200	99.91 111	98.42 168	92.91 232	97.33 201	98.72 249	94.81 73	99.21 200	96.98 201	94.63 298	99.03 262

LS3D		95.84 212	95.11 230	98.02 167	99.85 62	95.10 233	98.74 384	98.50 137	87.22 405	93.66 301	99.86 34	87.45 240	99.95 86	90.94 337	99.81 87	99.02 263

MIMVSNet		90.30 377	88.67 392	95.17 321	96.45 347	91.64 358	92.39 496	97.15 366	85.99 421	90.50 337	93.19 456	66.95 452	94.86 467	82.01 441	93.43 316	99.01 264

testing3-2		97.72 106	97.43 109	98.60 118	98.55 179	97.11 132	100.00 1	99.23 31	93.78 190	97.90 178	98.73 248	95.50 54	99.69 165	98.53 123	94.63 298	98.99 265

viewmambaseed2359dif		95.92 209	95.55 207	97.04 253	97.38 280	93.41 302	99.78 181	96.97 405	91.14 317	96.58 231	99.27 165	84.85 290	98.75 252	96.87 208	97.12 226	98.97 266

testing99		97.17 132	96.91 130	97.95 170	98.35 198	95.70 197	99.91 111	98.43 156	92.94 230	97.36 199	98.72 249	94.83 72	99.21 200	97.00 199	94.64 297	98.95 267

mamba_0408		94.98 248	94.09 261	97.64 201	97.14 300	95.31 219	93.48 490	97.08 384	90.48 341	94.40 289	98.62 262	84.49 300	98.67 266	93.99 278	97.18 218	98.93 268

SSM_04072		94.77 255	94.09 261	96.82 262	97.14 300	95.31 219	93.48 490	97.08 384	90.48 341	94.40 289	98.62 262	84.49 300	96.21 435	93.99 278	97.18 218	98.93 268

SSM_0407		95.62 229	94.95 237	97.61 206	97.14 300	95.31 219	99.00 350	97.25 348	90.81 327	94.40 289	98.83 241	84.74 294	98.58 276	95.24 247	97.18 218	98.93 268

thisisatest0530		97.10 136	96.72 142	98.22 152	97.60 259	96.70 149	99.92 103	98.54 123	91.11 318	97.07 211	98.97 212	97.47 13	99.03 214	93.73 291	96.09 262	98.92 271

BH-untuned		95.18 240	94.83 240	96.22 284	98.36 196	91.22 369	99.80 175	97.32 332	90.91 323	91.08 329	98.67 254	83.51 312	98.54 283	94.23 275	99.61 105	98.92 271

F-COLMAP		96.93 148	96.95 129	96.87 261	99.71 84	91.74 350	99.85 147	97.95 250	93.11 224	95.72 267	99.16 186	92.35 157	99.94 95	95.32 245	99.35 138	98.92 271

Anonymous20240529		92.10 338	90.65 350	96.47 273	98.82 157	90.61 382	98.72 386	98.67 87	75.54 485	93.90 300	98.58 268	66.23 456	99.90 114	94.70 264	90.67 328	98.90 274

dtuplus		95.79 218	95.42 211	96.93 257	97.24 298	93.16 307	99.78 181	96.93 412	91.69 296	96.18 253	99.29 160	83.80 310	98.73 254	96.83 210	97.02 235	98.89 275

tttt0517		96.85 151	96.49 152	97.92 174	97.48 270	95.89 188	99.85 147	98.54 123	90.72 335	96.63 228	98.93 224	97.47 13	99.02 215	93.03 305	95.76 275	98.85 276

baseline1		95.78 219	94.86 239	98.54 128	98.47 189	98.07 81	99.06 340	97.99 245	92.68 248	94.13 297	98.62 262	93.28 125	98.69 263	93.79 288	85.76 374	98.84 277

VDD-MVS		93.77 295	92.94 304	96.27 283	98.55 179	90.22 391	98.77 383	97.79 267	90.85 325	96.82 223	99.42 142	61.18 476	99.77 151	98.95 92	94.13 307	98.82 278

PatchMatch-RL		96.04 203	95.40 213	97.95 170	99.59 93	95.22 227	99.52 270	99.07 37	93.96 181	96.49 236	98.35 285	82.28 327	99.82 143	90.15 353	99.22 145	98.81 279

PVSNet_0	88.03 19	91.80 345	90.27 359	96.38 280	98.27 204	90.46 386	99.94 93	99.61 13	93.99 179	86.26 426	97.39 321	71.13 436	99.89 119	98.77 107	67.05 486	98.79 280

test_vis1_n_1920		95.44 233	95.31 221	95.82 300	98.50 186	88.74 414	99.98 24	97.30 334	97.84 28	99.85 20	99.19 181	66.82 454	99.97 65	98.82 103	99.46 127	98.76 281

tpmvs		94.28 277	93.57 279	96.40 278	98.55 179	91.50 366	95.70 478	98.55 119	87.47 400	92.15 319	94.26 442	91.42 174	98.95 222	88.15 385	95.85 271	98.76 281

fmvsm_s_conf0.1_n_a		97.09 138	96.90 131	97.63 204	95.65 376	94.21 272	99.83 160	98.50 137	96.27 92	99.65 55	99.64 119	84.72 296	99.93 105	99.04 87	98.84 161	98.74 283

test_cas_vis1_n_1920		96.59 171	96.23 165	97.65 200	98.22 207	94.23 270	99.99 8	97.25 348	97.77 29	99.58 70	99.08 191	77.10 386	99.97 65	97.64 178	99.45 128	98.74 283

h-mvs33		94.92 249	94.36 252	96.59 271	98.85 156	91.29 368	98.93 363	98.94 44	95.90 101	98.77 130	98.42 283	90.89 189	99.77 151	97.80 169	70.76 472	98.72 285

xiu_mvs_v2_base		98.23 71	97.97 72	99.02 88	98.69 165	98.66 57	99.52 270	98.08 237	97.05 56	99.86 16	99.86 34	90.65 191	99.71 161	99.39 71	98.63 168	98.69 286

PS-MVSNAJ		98.44 49	98.20 54	99.16 69	98.80 159	98.92 32	99.54 268	98.17 223	97.34 42	99.85 20	99.85 38	91.20 178	99.89 119	99.41 69	99.67 95	98.69 286

fmvsm_s_conf0.5_n		97.80 97	97.85 85	97.67 197	99.06 129	94.41 260	99.98 24	98.97 43	97.34 42	99.63 59	99.69 105	87.27 243	99.97 65	99.62 56	99.06 153	98.62 288

test_fmvsm_n_1920		98.44 49	98.61 30	97.92 174	99.27 116	95.18 229	100.00 1	98.90 50	98.05 20	99.80 28	99.73 92	92.64 146	99.99 40	99.58 58	99.51 118	98.59 289

viewdifsd2359ckpt11		94.09 283	93.63 274	95.46 310	96.68 341	88.92 411	99.62 244	97.12 372	93.07 225	95.73 265	99.22 175	77.05 387	98.88 226	96.52 224	87.69 362	98.58 290

viewmsd2359difaftdt		94.09 283	93.64 273	95.46 310	96.68 341	88.92 411	99.62 244	97.13 371	93.07 225	95.73 265	99.22 175	77.05 387	98.89 225	96.52 224	87.70 361	98.58 290

fmvsm_s_conf0.1_n		97.30 125	97.21 119	97.60 207	97.38 280	94.40 262	99.90 117	98.64 91	96.47 82	99.51 78	99.65 118	84.99 288	99.93 105	99.22 77	99.09 151	98.46 292

SSM_0404		95.75 220	95.16 228	97.50 219	97.53 265	95.39 213	99.11 331	97.25 348	90.81 327	95.27 277	98.83 241	84.74 294	98.67 266	95.24 247	97.69 197	98.45 293

UWE-MVS		96.79 154	96.72 142	97.00 254	98.51 184	93.70 288	99.71 220	98.60 101	92.96 229	97.09 209	98.34 287	96.67 33	98.85 230	92.11 318	96.50 251	98.44 294

test_fmvsmvis_n_1920		97.67 109	97.59 100	97.91 176	97.02 312	95.34 216	99.95 75	98.45 143	97.87 26	97.02 212	99.59 125	89.64 206	99.98 52	99.41 69	99.34 139	98.42 295

fmvsm_s_conf0.5_n_3		97.95 81	97.66 94	98.81 101	98.99 137	98.07 81	99.98 24	98.81 67	98.18 12	99.89 11	99.70 101	84.15 306	99.97 65	99.76 41	99.50 120	98.39 296

dmvs_re		93.20 309	93.15 298	93.34 395	96.54 344	83.81 456	98.71 387	98.51 131	91.39 310	92.37 318	98.56 270	78.66 374	97.83 340	93.89 281	89.74 329	98.38 297

MSDG		94.37 273	93.36 292	97.40 233	98.88 154	93.95 282	99.37 297	97.38 317	85.75 426	90.80 335	99.17 183	84.11 308	99.88 125	86.35 407	98.43 175	98.36 298

UWE-MVS-28		95.95 206	96.49 152	94.34 357	98.51 184	89.99 396	99.39 293	98.57 107	93.14 221	97.33 201	98.31 290	93.44 117	94.68 469	93.69 293	95.98 265	98.34 299

CANet_DTU		96.76 157	96.15 171	98.60 118	98.78 160	97.53 109	99.84 152	97.63 285	97.25 50	99.20 102	99.64 119	81.36 339	99.98 52	92.77 308	98.89 158	98.28 300

dtuonly		93.89 288	93.16 297	96.08 288	94.37 401	91.67 357	99.15 328	95.04 474	91.79 294	94.74 282	98.72 249	81.01 344	98.31 308	87.29 396	96.33 257	98.27 301

test_fmvs1		95.35 236	95.68 202	94.36 356	98.99 137	84.98 449	99.96 56	96.65 432	97.60 34	99.73 47	98.96 214	71.58 432	99.93 105	98.31 137	99.37 135	98.17 302

VDDNet		93.12 312	91.91 328	96.76 265	96.67 343	92.65 324	98.69 390	98.21 218	82.81 454	97.75 189	99.28 161	61.57 474	99.48 187	98.09 151	94.09 308	98.15 303

MVS-HIRNet		86.22 421	83.19 437	95.31 317	96.71 340	90.29 389	92.12 497	97.33 326	62.85 505	86.82 415	70.37 520	69.37 441	97.49 352	75.12 477	97.99 193	98.15 303

test_fmvs1_n		94.25 278	94.36 252	93.92 379	97.68 250	83.70 457	99.90 117	96.57 435	97.40 40	99.67 53	98.88 227	61.82 473	99.92 111	98.23 143	99.13 148	98.14 305

LuminaMVS		96.63 168	96.21 168	97.87 179	95.58 380	96.82 143	99.12 329	97.67 281	94.47 146	97.88 182	98.31 290	87.50 238	98.71 258	98.07 153	97.29 213	98.10 306

UGNet		95.33 237	94.57 248	97.62 205	98.55 179	94.85 240	98.67 392	99.32 26	95.75 107	96.80 225	96.27 362	72.18 429	99.96 77	94.58 267	99.05 154	98.04 307
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
kuosan		93.17 310	92.60 312	94.86 332	98.40 192	89.54 404	98.44 405	98.53 126	84.46 440	88.49 385	97.92 306	90.57 193	97.05 378	83.10 432	93.49 315	97.99 308

DSMNet-mixed		88.28 405	88.24 399	88.42 458	89.64 476	75.38 493	98.06 427	89.86 508	85.59 428	88.20 398	92.14 472	76.15 404	91.95 493	78.46 465	96.05 263	97.92 309

Elysia		94.50 267	93.38 289	97.85 180	96.49 345	96.70 149	98.98 352	97.78 271	90.81 327	96.19 251	98.55 272	73.63 424	98.98 217	89.41 359	98.56 170	97.88 310

StellarMVS		94.50 267	93.38 289	97.85 180	96.49 345	96.70 149	98.98 352	97.78 271	90.81 327	96.19 251	98.55 272	73.63 424	98.98 217	89.41 359	98.56 170	97.88 310

xiu_mvs_v1_base_debu		97.43 117	97.06 123	98.55 124	97.74 240	98.14 75	99.31 307	97.86 261	96.43 83	99.62 62	99.69 105	85.56 276	99.68 166	99.05 84	98.31 178	97.83 312

xiu_mvs_v1_base		97.43 117	97.06 123	98.55 124	97.74 240	98.14 75	99.31 307	97.86 261	96.43 83	99.62 62	99.69 105	85.56 276	99.68 166	99.05 84	98.31 178	97.83 312

xiu_mvs_v1_base_debi		97.43 117	97.06 123	98.55 124	97.74 240	98.14 75	99.31 307	97.86 261	96.43 83	99.62 62	99.69 105	85.56 276	99.68 166	99.05 84	98.31 178	97.83 312

UniMVSNet_ETH3D		90.06 385	88.58 394	94.49 348	94.67 396	88.09 425	97.81 435	97.57 296	83.91 444	88.44 387	97.41 319	57.44 482	97.62 348	91.41 327	88.59 348	97.77 315

cascas		94.64 261	93.61 275	97.74 193	97.82 234	96.26 171	99.96 56	97.78 271	85.76 424	94.00 298	97.54 316	76.95 392	99.21 200	97.23 191	95.43 288	97.76 316

fmvsm_s_conf0.5_n_7		97.70 108	97.74 89	97.59 210	98.44 190	95.16 231	99.97 42	98.65 88	97.95 24	99.62 62	99.78 67	86.09 264	99.94 95	99.69 51	99.50 120	97.66 317

fmvsm_s_conf0.5_n_11		98.03 79	97.89 82	98.46 137	99.35 110	97.76 99	99.99 8	98.04 241	98.20 9	99.90 7	99.78 67	86.21 263	99.95 86	99.89 22	99.68 94	97.65 318

fmvsm_s_conf0.5_n_4		97.75 102	97.86 84	97.42 229	99.01 132	94.69 249	99.97 42	98.76 73	97.91 25	99.87 14	99.76 73	86.70 254	99.93 105	99.67 53	99.12 150	97.64 319

SDMVSNet		94.80 252	93.96 267	97.33 240	98.92 147	95.42 210	99.59 253	98.99 40	92.41 267	92.55 316	97.85 310	75.81 406	98.93 223	97.90 164	91.62 325	97.64 319

sd_testset		93.55 302	92.83 306	95.74 303	98.92 147	90.89 376	98.24 417	98.85 62	92.41 267	92.55 316	97.85 310	71.07 437	98.68 264	93.93 280	91.62 325	97.64 319

hse-mvs2		94.38 272	94.08 263	95.31 317	98.27 204	90.02 395	99.29 314	98.56 113	95.90 101	98.77 130	98.00 301	90.89 189	98.26 317	97.80 169	69.20 480	97.64 319

AUN-MVS		93.28 307	92.60 312	95.34 315	98.29 201	90.09 394	99.31 307	98.56 113	91.80 293	96.35 247	98.00 301	89.38 210	98.28 313	92.46 309	69.22 479	97.64 319

sc_t1		85.01 433	82.46 443	92.67 412	92.44 445	83.09 463	97.39 443	95.72 456	65.06 501	85.64 432	96.16 365	49.50 494	97.34 357	84.86 421	75.39 456	97.57 324

OpenMVS	90.15 15	94.77 255	93.59 278	98.33 146	96.07 354	97.48 114	99.56 263	98.57 107	90.46 343	86.51 420	98.95 219	78.57 375	99.94 95	93.86 282	99.74 90	97.57 324

baseline2		96.71 164	96.49 152	97.37 235	95.63 378	95.96 186	99.74 204	98.88 55	92.94 230	91.61 324	98.97 212	97.72 7	98.62 274	94.83 259	98.08 191	97.53 326

fmvsm_s_conf0.5_n_2		97.59 112	97.28 115	98.53 130	99.01 132	98.15 73	99.98 24	98.59 103	98.17 13	99.75 42	99.63 122	81.83 333	99.94 95	99.78 36	98.79 164	97.51 327

fmvsm_s_conf0.1_n_2		97.25 128	96.85 134	98.43 140	98.08 218	98.08 80	99.92 103	97.76 275	98.05 20	99.65 55	99.58 128	80.88 347	99.93 105	99.59 57	98.17 183	97.29 328

tt0805		91.28 354	90.18 362	94.60 340	96.26 350	87.55 429	98.39 411	98.72 78	89.00 368	89.22 369	98.47 280	62.98 469	98.96 221	90.57 344	88.00 356	97.28 329

dongtai		91.55 351	91.13 344	92.82 409	98.16 213	86.35 438	99.47 280	98.51 131	83.24 448	85.07 437	97.56 315	90.33 198	94.94 464	76.09 475	91.73 323	97.18 330

RPSCF		91.80 345	92.79 308	88.83 452	98.15 214	69.87 498	98.11 425	96.60 434	83.93 443	94.33 293	99.27 165	79.60 364	99.46 190	91.99 319	93.16 320	97.18 330

test0.0.03 1		93.86 289	93.61 275	94.64 338	95.02 391	92.18 334	99.93 100	98.58 105	94.07 174	87.96 400	98.50 275	93.90 107	94.96 463	81.33 444	93.17 319	96.78 332

AllTest		92.48 330	91.64 333	95.00 325	99.01 132	88.43 420	98.94 360	96.82 423	86.50 415	88.71 378	98.47 280	74.73 416	99.88 125	85.39 415	96.18 260	96.71 333

TestCases				95.00 325	99.01 132	88.43 420		96.82 423	86.50 415	88.71 378	98.47 280	74.73 416	99.88 125	85.39 415	96.18 260	96.71 333

Syy-MVS		90.00 386	90.63 351	88.11 461	97.68 250	74.66 494	99.71 220	98.35 191	90.79 331	92.10 320	98.67 254	79.10 370	93.09 485	63.35 503	95.95 268	96.59 335

myMVS_eth3d		94.46 270	94.76 245	93.55 392	97.68 250	90.97 371	99.71 220	98.35 191	90.79 331	92.10 320	98.67 254	92.46 155	93.09 485	87.13 399	95.95 268	96.59 335

XVG-OURS-SEG-HR		94.79 253	94.70 247	95.08 322	98.05 220	89.19 406	99.08 335	97.54 300	93.66 195	94.87 281	99.58 128	78.78 372	99.79 146	97.31 186	93.40 317	96.25 337

XVG-OURS		94.82 250	94.74 246	95.06 323	98.00 222	89.19 406	99.08 335	97.55 298	94.10 172	94.71 283	99.62 123	80.51 355	99.74 157	96.04 234	93.06 322	96.25 337

Effi-MVS+-dtu		94.53 265	95.30 222	92.22 417	97.77 238	82.54 467	99.59 253	97.06 393	94.92 128	95.29 276	95.37 401	85.81 268	97.89 338	94.80 260	97.07 228	96.23 339

testing3		93.92 287	94.23 257	92.99 406	97.54 264	90.23 390	99.99 8	99.16 33	90.57 338	91.33 328	98.63 261	92.99 133	92.52 489	82.46 437	95.39 289	96.22 340

testgi		89.01 400	88.04 401	91.90 421	93.49 418	84.89 450	99.73 211	95.66 459	93.89 188	85.14 434	98.17 294	59.68 478	94.66 470	77.73 468	88.88 340	96.16 341

Fast-Effi-MVS+-dtu		93.72 298	93.86 271	93.29 397	97.06 307	86.16 440	99.80 175	96.83 421	92.66 249	92.58 315	97.83 312	81.39 338	97.67 346	89.75 358	96.87 240	96.05 342

dmvs_testset		83.79 442	86.07 414	76.94 485	92.14 449	48.60 527	96.75 459	90.27 507	89.48 360	78.65 472	98.55 272	79.25 366	86.65 510	66.85 495	82.69 399	95.57 343

COLMAP_ROB	90.47 14	92.18 337	91.49 339	94.25 360	99.00 136	88.04 426	98.42 409	96.70 430	82.30 457	88.43 390	99.01 201	76.97 391	99.85 131	86.11 411	96.50 251	94.86 344
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
HQP4-MVS										93.37 303			98.39 297			94.53 345

HQP-MVS		94.61 262	94.50 249	94.92 328	95.78 362	91.85 343	99.87 133	97.89 257	96.82 66	93.37 303	98.65 257	80.65 353	98.39 297	97.92 161	89.60 330	94.53 345

HQP_MVS		94.49 269	94.36 252	94.87 329	95.71 372	91.74 350	99.84 152	97.87 259	96.38 86	93.01 308	98.59 265	80.47 357	98.37 303	97.79 172	89.55 333	94.52 347

plane_prior5								97.87 259					98.37 303	97.79 172	89.55 333	94.52 347

CLD-MVS		94.06 286	93.90 269	94.55 344	96.02 356	90.69 379	99.98 24	97.72 277	96.62 77	91.05 331	98.85 239	77.21 385	98.47 285	98.11 149	89.51 335	94.48 349
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
nrg030		93.51 303	92.53 317	96.45 276	94.36 402	97.20 125	99.81 169	97.16 363	91.60 298	89.86 349	97.46 317	86.37 259	97.68 345	95.88 237	80.31 425	94.46 350

VPNet		91.81 342	90.46 353	95.85 298	94.74 394	95.54 205	98.98 352	98.59 103	92.14 279	90.77 336	97.44 318	68.73 444	97.54 351	94.89 258	77.89 439	94.46 350

UniMVSNet_NR-MVSNet		92.95 316	92.11 323	95.49 306	94.61 397	95.28 223	99.83 160	99.08 36	91.49 301	89.21 370	96.86 342	87.14 245	96.73 403	93.20 299	77.52 442	94.46 350

DU-MVS		92.46 331	91.45 340	95.49 306	94.05 408	95.28 223	99.81 169	98.74 76	92.25 278	89.21 370	96.64 351	81.66 335	96.73 403	93.20 299	77.52 442	94.46 350

NR-MVSNet		91.56 350	90.22 360	95.60 304	94.05 408	95.76 193	98.25 416	98.70 80	91.16 316	80.78 462	96.64 351	83.23 321	96.57 411	91.41 327	77.73 441	94.46 350

TranMVSNet+NR-MVSNet		91.68 349	90.61 352	94.87 329	93.69 415	93.98 281	99.69 230	98.65 88	91.03 321	88.44 387	96.83 346	80.05 361	96.18 436	90.26 352	76.89 450	94.45 355

FIs		94.10 282	93.43 284	96.11 286	94.70 395	96.82 143	99.58 255	98.93 48	92.54 261	89.34 365	97.31 322	87.62 235	97.10 375	94.22 276	86.58 368	94.40 356

ACMM	91.95 10	92.88 318	92.52 318	93.98 378	95.75 368	89.08 410	99.77 187	97.52 304	93.00 228	89.95 346	97.99 303	76.17 403	98.46 288	93.63 294	88.87 341	94.39 357
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FC-MVSNet-test		93.81 293	93.15 298	95.80 301	94.30 404	96.20 177	99.42 287	98.89 52	92.33 272	89.03 375	97.27 324	87.39 241	96.83 398	93.20 299	86.48 369	94.36 358

PS-MVSNAJss		93.64 300	93.31 293	94.61 339	92.11 450	92.19 333	99.12 329	97.38 317	92.51 264	88.45 386	96.99 336	91.20 178	97.29 365	94.36 270	87.71 359	94.36 358

WR-MVS		92.31 334	91.25 342	95.48 309	94.45 400	95.29 222	99.60 251	98.68 84	90.10 351	88.07 399	96.89 340	80.68 352	96.80 400	93.14 302	79.67 429	94.36 358

WBMVS		94.52 266	94.03 264	95.98 290	98.38 193	96.68 152	99.92 103	97.63 285	90.75 334	89.64 357	95.25 409	96.77 27	96.90 391	94.35 272	83.57 394	94.35 361

XXY-MVS		91.82 341	90.46 353	95.88 296	93.91 411	95.40 212	98.87 372	97.69 280	88.63 382	87.87 401	97.08 329	74.38 419	97.89 338	91.66 324	84.07 391	94.35 361

MVSTER		95.53 231	95.22 225	96.45 276	98.56 176	97.72 100	99.91 111	97.67 281	92.38 270	91.39 326	97.14 326	97.24 20	97.30 362	94.80 260	87.85 357	94.34 363

VPA-MVSNet		92.70 324	91.55 337	96.16 285	95.09 388	96.20 177	98.88 369	99.00 39	91.02 322	91.82 323	95.29 407	76.05 405	97.96 334	95.62 243	81.19 412	94.30 364

FMVSNet3		92.69 325	91.58 335	95.99 289	98.29 201	97.42 117	99.26 319	97.62 288	89.80 358	89.68 353	95.32 403	81.62 337	96.27 432	87.01 403	85.65 375	94.29 365

EU-MVSNet		90.14 383	90.34 357	89.54 447	92.55 443	81.06 478	98.69 390	98.04 241	91.41 309	86.59 419	96.84 345	80.83 348	93.31 483	86.20 409	81.91 407	94.26 366

UniMVSNet (Re)		93.07 314	92.13 322	95.88 296	94.84 392	96.24 176	99.88 130	98.98 41	92.49 265	89.25 367	95.40 397	87.09 246	97.14 371	93.13 303	78.16 437	94.26 366

reproduce_monomvs		95.38 235	95.07 232	96.32 282	99.32 113	96.60 157	99.76 194	98.85 62	96.65 74	87.83 402	96.05 372	99.52 1	98.11 324	96.58 221	81.07 417	94.25 368

FMVSNet2		91.02 359	89.56 373	95.41 313	97.53 265	95.74 194	98.98 352	97.41 315	87.05 406	88.43 390	95.00 421	71.34 433	96.24 434	85.12 418	85.21 380	94.25 368

usedtu_dtu_shiyan1		92.78 320	91.73 331	95.92 294	93.03 429	96.82 143	99.83 160	97.79 267	90.58 336	90.09 340	95.04 416	84.75 292	96.72 405	88.19 383	86.23 371	94.23 370

FE-MVSNET3		92.78 320	91.73 331	95.92 294	93.03 429	96.82 143	99.83 160	97.79 267	90.58 336	90.09 340	95.04 416	84.75 292	96.72 405	88.20 382	86.23 371	94.23 370

VortexMVS		94.11 281	93.50 282	95.94 292	97.70 248	96.61 156	99.35 300	97.18 359	93.52 201	89.57 360	95.74 377	87.55 237	96.97 386	95.76 241	85.13 382	94.23 370

EI-MVSNet		93.73 297	93.40 288	94.74 334	96.80 333	92.69 321	99.06 340	97.67 281	88.96 371	91.39 326	99.02 199	88.75 223	97.30 362	91.07 332	87.85 357	94.22 373

IterMVS-LS		92.69 325	92.11 323	94.43 353	96.80 333	92.74 318	99.45 285	96.89 416	88.98 369	89.65 356	95.38 400	88.77 222	96.34 428	90.98 336	82.04 406	94.22 373
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		93.77 295	93.25 295	95.33 316	99.49 103	94.43 258	99.61 248	98.09 235	90.38 344	89.16 373	95.61 384	90.56 194	97.34 357	91.93 320	84.45 387	94.21 375

miper_enhance_ethall		94.36 275	93.98 266	95.49 306	98.68 166	95.24 225	99.73 211	97.29 342	93.28 213	89.86 349	95.97 373	94.37 89	97.05 378	92.20 312	84.45 387	94.19 376

blend_shiyan4		90.13 384	88.79 389	94.17 361	87.12 486	91.83 345	99.75 200	97.08 384	79.27 475	88.69 380	92.53 461	92.25 161	96.50 415	89.35 362	73.04 464	94.18 377

miper_ehance_all_eth		93.16 311	92.60 312	94.82 333	97.57 261	93.56 297	99.50 274	97.07 392	88.75 378	88.85 377	95.52 390	90.97 185	96.74 402	90.77 341	84.45 387	94.17 378

DIV-MVS_self_test		92.32 333	91.60 334	94.47 349	97.31 291	92.74 318	99.58 255	96.75 427	86.99 409	87.64 404	95.54 388	89.55 208	96.50 415	88.58 372	82.44 403	94.17 378

GBi-Net		90.88 362	89.82 368	94.08 370	97.53 265	91.97 336	98.43 406	96.95 407	87.05 406	89.68 353	94.72 427	71.34 433	96.11 438	87.01 403	85.65 375	94.17 378

test1		90.88 362	89.82 368	94.08 370	97.53 265	91.97 336	98.43 406	96.95 407	87.05 406	89.68 353	94.72 427	71.34 433	96.11 438	87.01 403	85.65 375	94.17 378

FMVSNet1		88.50 403	86.64 410	94.08 370	95.62 379	91.97 336	98.43 406	96.95 407	83.00 452	86.08 428	94.72 427	59.09 480	96.11 438	81.82 443	84.07 391	94.17 378

cl____		92.31 334	91.58 335	94.52 345	97.33 289	92.77 316	99.57 259	96.78 426	86.97 410	87.56 406	95.51 391	89.43 209	96.62 409	88.60 371	82.44 403	94.16 383

blended_shiyan8		87.82 411	85.71 418	94.16 362	86.54 495	91.79 347	99.72 215	97.08 384	79.32 473	88.44 387	92.35 469	77.88 383	96.56 412	88.53 374	61.51 499	94.15 384

eth_miper_zixun_eth		92.41 332	91.93 327	93.84 383	97.28 294	90.68 380	98.83 376	96.97 405	88.57 383	89.19 372	95.73 380	89.24 215	96.69 407	89.97 356	81.55 409	94.15 384

miper_lstm_enhance		91.81 342	91.39 341	93.06 405	97.34 287	89.18 408	99.38 295	96.79 425	86.70 414	87.47 408	95.22 410	90.00 202	95.86 447	88.26 381	81.37 411	94.15 384

Anonymous20231211		89.86 388	88.44 396	94.13 368	98.93 144	90.68 380	98.54 400	98.26 208	76.28 481	86.73 416	95.54 388	70.60 438	97.56 350	90.82 340	80.27 426	94.15 384

wanda-best-256-512		87.82 411	85.71 418	94.15 364	86.66 490	91.88 341	99.76 194	97.08 384	79.46 471	88.37 393	92.36 466	78.01 379	96.43 421	88.39 378	61.26 500	94.14 388

FE-blended-shiyan7		87.82 411	85.71 418	94.15 364	86.66 490	91.88 341	99.76 194	97.08 384	79.46 471	88.37 393	92.36 466	78.01 379	96.43 421	88.39 378	61.26 500	94.14 388

usedtu_blend_shiyan5		86.75 419	84.29 427	94.16 362	86.66 490	91.83 345	97.42 440	95.23 469	69.94 497	88.37 393	92.36 466	78.01 379	96.50 415	89.35 362	61.26 500	94.14 388

SSC-MVS3.2		89.59 393	88.66 393	92.38 414	94.29 405	86.12 441	99.49 276	97.66 284	90.28 350	88.63 383	95.18 411	64.46 463	96.88 394	85.30 417	82.66 400	94.14 388

c3_l		92.53 329	91.87 329	94.52 345	97.40 277	92.99 314	99.40 289	96.93 412	87.86 396	88.69 380	95.44 395	89.95 203	96.44 420	90.45 347	80.69 422	94.14 388

blended_shiyan6		87.74 414	85.62 421	94.09 369	86.53 496	91.73 353	99.72 215	97.08 384	79.32 473	88.22 397	92.31 471	77.82 384	96.43 421	88.31 380	61.26 500	94.13 393

jajsoiax		91.92 340	91.18 343	94.15 364	91.35 461	90.95 374	99.00 350	97.42 313	92.61 252	87.38 410	97.08 329	72.46 428	97.36 355	94.53 268	88.77 343	94.13 393

mvs_tets		91.81 342	91.08 345	94.00 375	91.63 458	90.58 383	98.67 392	97.43 311	92.43 266	87.37 411	97.05 332	71.76 430	97.32 360	94.75 262	88.68 345	94.11 395

v2v482		91.30 352	90.07 366	95.01 324	93.13 423	93.79 284	99.77 187	97.02 397	88.05 393	89.25 367	95.37 401	80.73 351	97.15 370	87.28 397	80.04 428	94.09 396

LPG-MVS_test		92.96 315	92.71 310	93.71 386	95.43 383	88.67 416	99.75 200	97.62 288	92.81 237	90.05 342	98.49 276	75.24 410	98.40 295	95.84 238	89.12 337	94.07 397

LGP-MVS_train				93.71 386	95.43 383	88.67 416		97.62 288	92.81 237	90.05 342	98.49 276	75.24 410	98.40 295	95.84 238	89.12 337	94.07 397

gbinet_0.2-2-1-0.02		87.63 415	85.51 422	93.99 376	87.22 485	91.56 365	99.81 169	97.36 321	79.54 470	88.60 384	93.29 455	73.76 422	96.34 428	89.27 365	60.78 505	94.06 399

test_djsdf		92.83 319	92.29 321	94.47 349	91.90 453	92.46 328	99.55 266	97.27 344	91.17 314	89.96 345	96.07 371	81.10 342	96.89 392	94.67 265	88.91 339	94.05 400

CP-MVSNet		91.23 356	90.22 360	94.26 359	93.96 410	92.39 330	99.09 333	98.57 107	88.95 372	86.42 423	96.57 354	79.19 368	96.37 426	90.29 351	78.95 431	94.02 401

Patchmtry		89.70 391	88.49 395	93.33 396	96.24 351	89.94 400	91.37 502	96.23 444	78.22 478	87.69 403	93.31 453	91.04 183	96.03 443	80.18 455	82.10 405	94.02 401

v1921920		90.46 372	89.12 382	94.50 347	92.96 433	92.46 328	99.49 276	96.98 403	86.10 420	89.61 359	95.30 404	78.55 376	97.03 383	82.17 440	80.89 421	94.01 403

v1192		90.62 370	89.25 380	94.72 336	93.13 423	93.07 309	99.50 274	97.02 397	86.33 418	89.56 361	95.01 419	79.22 367	97.09 377	82.34 439	81.16 413	94.01 403

v1240		90.20 380	88.79 389	94.44 351	93.05 428	92.27 332	99.38 295	96.92 414	85.89 422	89.36 364	94.87 426	77.89 382	97.03 383	80.66 449	81.08 416	94.01 403

OPM-MVS		93.21 308	92.80 307	94.44 351	93.12 425	90.85 377	99.77 187	97.61 291	96.19 95	91.56 325	98.65 257	75.16 414	98.47 285	93.78 289	89.39 336	93.99 406
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMP	92.05 9	92.74 323	92.42 320	93.73 384	95.91 360	88.72 415	99.81 169	97.53 302	94.13 170	87.00 414	98.23 293	74.07 420	98.47 285	96.22 231	88.86 342	93.99 406
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OurMVSNet-221017-0		89.81 389	89.48 378	90.83 432	91.64 457	81.21 476	98.17 423	95.38 466	91.48 303	85.65 431	97.31 322	72.66 427	97.29 365	88.15 385	84.83 384	93.97 408

pmmvs5		90.17 382	89.09 383	93.40 394	92.10 451	89.77 401	99.74 204	95.58 461	85.88 423	87.24 413	95.74 377	73.41 426	96.48 418	88.54 373	83.56 395	93.95 409

PS-CasMVS		90.63 369	89.51 376	93.99 376	93.83 412	91.70 355	98.98 352	98.52 128	88.48 385	86.15 427	96.53 356	75.46 408	96.31 431	88.83 369	78.86 433	93.95 409

IterMVS		90.91 361	90.17 363	93.12 402	96.78 337	90.42 388	98.89 367	97.05 396	89.03 366	86.49 421	95.42 396	76.59 397	95.02 461	87.22 398	84.09 390	93.93 411
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	89.72 17	90.64 368	89.63 371	93.66 390	95.64 377	88.64 418	98.55 398	97.45 309	89.03 366	81.62 455	97.61 314	69.75 440	98.41 293	89.37 361	87.62 363	93.92 412
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v144192		90.79 365	89.52 375	94.59 341	93.11 426	92.77 316	99.56 263	96.99 401	86.38 417	89.82 352	94.95 424	80.50 356	97.10 375	83.98 426	80.41 423	93.90 413

PEN-MVS		90.19 381	89.06 384	93.57 391	93.06 427	90.90 375	99.06 340	98.47 140	88.11 392	85.91 429	96.30 361	76.67 395	95.94 446	87.07 400	76.91 449	93.89 414

XVG-ACMP-BASELINE		91.22 357	90.75 348	92.63 413	93.73 414	85.61 444	98.52 402	97.44 310	92.77 241	89.90 348	96.85 343	66.64 455	98.39 297	92.29 311	88.61 346	93.89 414

v1144		91.09 358	89.83 367	94.87 329	93.25 422	93.69 289	99.62 244	96.98 403	86.83 412	89.64 357	94.99 422	80.94 345	97.05 378	85.08 419	81.16 413	93.87 416

MDA-MVSNet_test_wron		85.51 427	83.32 436	92.10 418	90.96 464	88.58 419	99.20 323	96.52 437	79.70 468	57.12 512	92.69 459	79.11 369	93.86 477	77.10 471	77.46 444	93.86 417

IterMVS-SCA-FT		90.85 364	90.16 364	92.93 407	96.72 339	89.96 397	98.89 367	96.99 401	88.95 372	86.63 418	95.67 381	76.48 399	95.00 462	87.04 401	84.04 393	93.84 418

YYNet1		85.50 428	83.33 435	92.00 419	90.89 465	88.38 423	99.22 322	96.55 436	79.60 469	57.26 511	92.72 458	79.09 371	93.78 479	77.25 470	77.37 445	93.84 418

MDA-MVSNet-bldmvs		84.09 440	81.52 447	91.81 423	91.32 462	88.00 427	98.67 392	95.92 452	80.22 466	55.60 513	93.32 452	68.29 447	93.60 481	73.76 479	76.61 451	93.82 420

ACMH+	89.98 16	90.35 375	89.54 374	92.78 411	95.99 357	86.12 441	98.81 378	97.18 359	89.38 361	83.14 448	97.76 313	68.42 446	98.43 290	89.11 367	86.05 373	93.78 421

v148		90.70 366	89.63 371	93.92 379	92.97 432	90.97 371	99.75 200	96.89 416	87.51 399	88.27 396	95.01 419	81.67 334	97.04 381	87.40 394	77.17 447	93.75 422

pmmvs4		92.10 338	91.07 346	95.18 320	92.82 439	94.96 236	99.48 279	96.83 421	87.45 401	88.66 382	96.56 355	83.78 311	96.83 398	89.29 364	84.77 385	93.75 422

K. test v3		88.05 407	87.24 408	90.47 438	91.82 456	82.23 470	98.96 358	97.42 313	89.05 365	76.93 480	95.60 385	68.49 445	95.42 456	85.87 414	81.01 419	93.75 422

lessismore_v0				90.53 436	90.58 468	80.90 479		95.80 453		77.01 479	95.84 374	66.15 457	96.95 387	83.03 433	75.05 457	93.74 425

SixPastTwentyTwo		88.73 401	88.01 402	90.88 429	91.85 454	82.24 469	98.22 421	95.18 472	88.97 370	82.26 451	96.89 340	71.75 431	96.67 408	84.00 425	82.98 396	93.72 426

our_test_3		90.39 373	89.48 378	93.12 402	92.40 446	89.57 403	99.33 302	96.35 443	87.84 397	85.30 433	94.99 422	84.14 307	96.09 441	80.38 452	84.56 386	93.71 427

LTVRE_ROB	88.28 18	90.29 378	89.05 385	94.02 373	95.08 389	90.15 393	97.19 447	97.43 311	84.91 437	83.99 444	97.06 331	74.00 421	98.28 313	84.08 424	87.71 359	93.62 428
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
ITE_SJBPF				92.38 414	95.69 375	85.14 447		95.71 457	92.81 237	89.33 366	98.11 297	70.23 439	98.42 291	85.91 413	88.16 354	93.59 429

v7n		89.65 392	88.29 398	93.72 385	92.22 448	90.56 384	99.07 339	97.10 380	85.42 431	86.73 416	94.72 427	80.06 360	97.13 372	81.14 445	78.12 438	93.49 430

DTE-MVSNet		89.40 396	88.24 399	92.88 408	92.66 442	89.95 398	99.10 332	98.22 214	87.29 403	85.12 435	96.22 363	76.27 402	95.30 460	83.56 430	75.74 454	93.41 431

V42		91.28 354	90.12 365	94.74 334	93.42 420	93.46 300	99.68 233	97.02 397	87.36 402	89.85 351	95.05 415	81.31 341	97.34 357	87.34 395	80.07 427	93.40 432

anonymousdsp		91.79 347	90.92 347	94.41 354	90.76 467	92.93 315	98.93 363	97.17 361	89.08 364	87.46 409	95.30 404	78.43 378	96.92 389	92.38 310	88.73 344	93.39 433

v8		90.54 371	89.17 381	94.66 337	93.43 419	93.40 304	99.20 323	96.94 411	85.76 424	87.56 406	94.51 434	81.96 331	97.19 368	84.94 420	78.25 436	93.38 434

ppachtmachnet_test		89.58 394	88.35 397	93.25 400	92.40 446	90.44 387	99.33 302	96.73 428	85.49 429	85.90 430	95.77 376	81.09 343	96.00 445	76.00 476	82.49 402	93.30 435

v10		90.25 379	88.82 388	94.57 343	93.53 417	93.43 301	99.08 335	96.87 418	85.00 434	87.34 412	94.51 434	80.93 346	97.02 385	82.85 434	79.23 430	93.26 436

PVSNet_BlendedMVS		96.05 202	95.82 195	96.72 267	99.59 93	96.99 137	99.95 75	99.10 34	94.06 176	98.27 161	95.80 375	89.00 219	99.95 86	99.12 81	87.53 364	93.24 437

WR-MVS_H		91.30 352	90.35 356	94.15 364	94.17 407	92.62 325	99.17 326	98.94 44	88.87 375	86.48 422	94.46 438	84.36 303	96.61 410	88.19 383	78.51 434	93.21 438

tt0320-xc		82.94 447	80.35 454	90.72 435	92.90 435	83.54 460	96.85 457	94.73 480	63.12 504	79.85 467	93.77 448	49.43 495	95.46 455	80.98 448	71.54 470	93.16 439

FMVSNet5		88.32 404	87.47 406	90.88 429	96.90 328	88.39 422	97.28 445	95.68 458	82.60 456	84.67 439	92.40 465	79.83 362	91.16 495	76.39 474	81.51 410	93.09 440

Anonymous20231206		86.32 420	85.42 423	89.02 451	89.11 479	80.53 482	99.05 344	95.28 467	85.43 430	82.82 449	93.92 445	74.40 418	93.44 482	66.99 494	81.83 408	93.08 441

pm-mvs1		89.36 397	87.81 403	94.01 374	93.40 421	91.93 339	98.62 396	96.48 440	86.25 419	83.86 445	96.14 367	73.68 423	97.04 381	86.16 410	75.73 455	93.04 442

tt0320		83.56 446	81.15 449	90.77 433	92.77 441	83.58 459	96.83 458	95.52 463	63.26 503	81.36 457	92.54 460	53.26 487	95.77 450	80.45 450	74.38 459	92.96 443

test_method		80.79 453	79.70 456	84.08 472	92.83 438	67.06 502	99.51 272	95.42 464	54.34 515	81.07 460	93.53 450	44.48 498	92.22 492	78.90 463	77.23 446	92.94 444

UnsupCasMVSNet_eth		85.52 426	83.99 429	90.10 443	89.36 478	83.51 461	96.65 460	97.99 245	89.14 363	75.89 484	93.83 446	63.25 468	93.92 475	81.92 442	67.90 485	92.88 445

USDC		90.00 386	88.96 386	93.10 404	94.81 393	88.16 424	98.71 387	95.54 462	93.66 195	83.75 446	97.20 325	65.58 458	98.31 308	83.96 427	87.49 365	92.85 446

test_fmvs2		89.47 395	89.70 370	88.77 455	94.54 398	75.74 490	99.83 160	94.70 482	94.71 137	91.08 329	96.82 347	54.46 485	97.78 343	92.87 306	88.27 352	92.80 447

PatchmatchNet1														68.29 490	82.87 397	92.70 448
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
N_pmnet		80.06 456	80.78 452	77.89 483	91.94 452	45.28 532	98.80 381	56.82 534	78.10 479	80.08 465	93.33 451	77.03 389	95.76 451	68.14 492	82.81 398	92.64 449

usedtu_dtu_shiyan2		75.87 463	72.37 468	86.39 467	76.18 523	75.49 492	96.53 462	93.82 493	64.74 502	72.53 491	88.48 489	37.67 501	91.12 496	64.13 502	57.22 510	92.56 450

KD-MVS_2432*1600		88.00 408	86.10 412	93.70 388	96.91 325	94.04 277	97.17 448	97.12 372	84.93 435	81.96 452	92.41 463	92.48 153	94.51 471	79.23 458	52.68 517	92.56 450

miper_refine_blended		88.00 408	86.10 412	93.70 388	96.91 325	94.04 277	97.17 448	97.12 372	84.93 435	81.96 452	92.41 463	92.48 153	94.51 471	79.23 458	52.68 517	92.56 450

pmmvs6		85.69 424	83.84 432	91.26 428	90.00 474	84.41 454	97.82 434	96.15 447	75.86 483	81.29 458	95.39 399	61.21 475	96.87 395	83.52 431	73.29 462	92.50 453

D2MVS		92.76 322	92.59 316	93.27 398	95.13 387	89.54 404	99.69 230	99.38 22	92.26 277	87.59 405	94.61 433	85.05 286	97.79 341	91.59 325	88.01 355	92.47 454

CL-MVSNet_self_test		84.50 438	83.15 438	88.53 456	86.00 497	81.79 473	98.82 377	97.35 322	85.12 433	83.62 447	90.91 477	76.66 396	91.40 494	69.53 487	60.36 506	92.40 455

ArgMatch-SfM		85.25 430	84.17 428	88.48 457	92.99 431	77.23 489	97.92 430	94.24 486	90.50 340	85.08 436	95.65 383	49.84 493	95.83 448	81.06 447	70.22 473	92.39 456

MIMVSNet1		82.58 448	80.51 453	88.78 453	86.68 489	84.20 455	96.65 460	95.41 465	78.75 476	78.59 473	92.44 462	51.88 490	89.76 501	65.26 500	78.95 431	92.38 457

ArgMatch-Sym		85.85 423	85.07 426	88.21 459	92.84 436	77.63 488	98.42 409	94.70 482	89.91 355	84.33 441	96.72 348	51.42 492	94.89 466	82.48 436	74.80 458	92.10 458

LF4IMVS		89.25 399	88.85 387	90.45 439	92.81 440	81.19 477	98.12 424	94.79 478	91.44 305	86.29 425	97.11 327	65.30 461	98.11 324	88.53 374	85.25 379	92.07 459

TransMVSNet (Re)		87.25 416	85.28 424	93.16 401	93.56 416	91.03 370	98.54 400	94.05 490	83.69 446	81.09 459	96.16 365	75.32 409	96.40 425	76.69 473	68.41 482	92.06 460

DeepMVS_CX				82.92 477	95.98 359	58.66 514		96.01 450	92.72 243	78.34 474	95.51 391	58.29 481	98.08 326	82.57 435	85.29 378	92.03 461

Baseline_NR-MVSNet		90.33 376	89.51 376	92.81 410	92.84 436	89.95 398	99.77 187	93.94 491	84.69 439	89.04 374	95.66 382	81.66 335	96.52 414	90.99 335	76.98 448	91.97 462

TinyColmap		87.87 410	86.51 411	91.94 420	95.05 390	85.57 445	97.65 438	94.08 488	84.40 441	81.82 454	96.85 343	62.14 472	98.33 306	80.25 454	86.37 370	91.91 463

MS-PatchMatch		90.65 367	90.30 358	91.71 425	94.22 406	85.50 446	98.24 417	97.70 278	88.67 380	86.42 423	96.37 359	67.82 449	98.03 330	83.62 429	99.62 100	91.60 464

KD-MVS_self_test		83.59 444	82.06 444	88.20 460	86.93 487	80.70 480	97.21 446	96.38 441	82.87 453	82.49 450	88.97 487	67.63 450	92.32 490	73.75 480	62.30 498	91.58 465

tfpnnormal		89.29 398	87.61 405	94.34 357	94.35 403	94.13 275	98.95 359	98.94 44	83.94 442	84.47 440	95.51 391	74.84 415	97.39 354	77.05 472	80.41 423	91.48 466

MVP-Stereo		90.93 360	90.45 355	92.37 416	91.25 463	88.76 413	98.05 428	96.17 446	87.27 404	84.04 442	95.30 404	78.46 377	97.27 367	83.78 428	99.70 93	91.09 467
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ttmdpeth		88.23 406	87.06 409	91.75 424	89.91 475	87.35 432	98.92 366	95.73 455	87.92 395	84.02 443	96.31 360	68.23 448	96.84 396	86.33 408	76.12 452	91.06 468

test20.03		84.72 437	83.99 429	86.91 465	88.19 483	80.62 481	98.88 369	95.94 451	88.36 388	78.87 470	94.62 432	68.75 443	89.11 504	66.52 496	75.82 453	91.00 469

EG-PatchMatch MVS		85.35 429	83.81 433	89.99 445	90.39 469	81.89 472	98.21 422	96.09 448	81.78 459	74.73 486	93.72 449	51.56 491	97.12 374	79.16 461	88.61 346	90.96 470

TDRefinement		84.76 435	82.56 442	91.38 427	74.58 525	84.80 452	97.36 444	94.56 484	84.73 438	80.21 464	96.12 370	63.56 466	98.39 297	87.92 388	63.97 493	90.95 471

ambc				83.23 475	77.17 521	62.61 506	87.38 511	94.55 485		76.72 481	86.65 502	30.16 507	96.36 427	84.85 422	69.86 475	90.73 472

MVStest1		85.03 432	82.76 441	91.83 422	92.95 434	89.16 409	98.57 397	94.82 477	71.68 493	68.54 498	95.11 414	83.17 322	95.66 452	74.69 478	65.32 489	90.65 473

Anonymous20240521		85.15 431	83.81 433	89.16 450	88.32 481	82.69 465	98.80 381	95.74 454	79.72 467	81.53 456	90.99 475	65.38 460	94.16 473	72.69 481	81.11 415	90.63 474

dtuonlycased		86.10 422	85.82 417	86.95 464	91.84 455	79.57 484	99.27 317	94.89 475	86.79 413	79.46 469	94.46 438	66.85 453	90.93 498	80.41 451	78.44 435	90.34 475

OpenMVS_ROB	79.82 20	83.77 443	81.68 446	90.03 444	88.30 482	82.82 464	98.46 403	95.22 470	73.92 490	76.00 483	91.29 474	55.00 484	96.94 388	68.40 489	88.51 350	90.34 475

new_pmnet		84.49 439	82.92 439	89.21 449	90.03 473	82.60 466	96.89 456	95.62 460	80.59 464	75.77 485	89.17 486	65.04 462	94.79 468	72.12 483	81.02 418	90.23 477

test_0402		85.58 425	83.94 431	90.50 437	93.81 413	85.04 448	98.55 398	95.20 471	76.01 482	79.72 468	95.13 412	64.15 465	96.26 433	66.04 499	86.88 367	90.21 478

LoFTR		74.41 466	70.88 469	84.99 471	86.56 494	67.85 500	93.74 485	89.63 510	69.46 498	54.95 514	87.39 498	30.76 504	96.92 389	61.37 508	64.06 492	90.19 479

mvs5depth		84.87 434	82.90 440	90.77 433	85.59 500	84.84 451	91.10 504	93.29 497	83.14 450	85.07 437	94.33 441	62.17 471	97.32 360	78.83 464	72.59 469	90.14 480

mmtdpeth		88.52 402	87.75 404	90.85 431	95.71 372	83.47 462	98.94 360	94.85 476	88.78 377	97.19 206	89.58 484	63.29 467	98.97 219	98.54 121	62.86 495	90.10 481

test_vis1_rt		86.87 418	86.05 415	89.34 448	96.12 352	78.07 486	99.87 133	83.54 520	92.03 284	78.21 475	89.51 485	45.80 497	99.91 112	96.25 230	93.11 321	90.03 482

pmmvs3		80.27 455	77.77 461	87.76 463	80.32 518	82.43 468	98.23 419	91.97 502	72.74 492	78.75 471	87.97 493	57.30 483	90.99 497	70.31 485	62.37 497	89.87 483

CMPMVS	61.59 21	84.75 436	85.14 425	83.57 473	90.32 470	62.54 507	96.98 453	97.59 295	74.33 489	69.95 495	96.66 349	64.17 464	98.32 307	87.88 389	88.41 351	89.84 484
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FE-MVSNET2		83.57 445	81.36 448	90.20 441	82.83 512	87.59 428	98.28 415	96.04 449	85.33 432	74.13 489	87.45 496	59.16 479	93.26 484	79.12 462	69.91 474	89.77 485

WB-MVSnew		92.90 317	92.77 309	93.26 399	96.95 323	93.63 291	99.71 220	98.16 228	91.49 301	94.28 294	98.14 295	81.33 340	96.48 418	79.47 456	95.46 286	89.68 486

APD_test1		81.15 451	80.92 451	81.86 478	92.45 444	59.76 513	96.04 473	93.61 495	73.29 491	77.06 478	96.64 351	44.28 499	96.16 437	72.35 482	82.52 401	89.67 487

PM-MVS		80.47 454	78.88 459	85.26 469	83.79 509	72.22 495	95.89 476	91.08 505	85.71 427	76.56 482	88.30 490	36.64 503	93.90 476	82.39 438	69.57 477	89.66 488

pmmvs-eth3d		84.03 441	81.97 445	90.20 441	84.15 506	87.09 434	98.10 426	94.73 480	83.05 451	74.10 490	87.77 494	65.56 459	94.01 474	81.08 446	69.24 478	89.49 489

UnsupCasMVSNet_bld		79.97 458	77.03 464	88.78 453	85.62 499	81.98 471	93.66 486	97.35 322	75.51 486	70.79 494	83.05 508	48.70 496	94.91 465	78.31 466	60.29 507	89.46 490

mvsany_test3		82.12 449	81.14 450	85.06 470	81.87 514	70.41 497	97.09 450	92.14 501	91.27 312	77.84 476	88.73 488	39.31 500	95.49 453	90.75 342	71.24 471	89.29 491

new-patchmatchnet		81.19 450	79.34 458	86.76 466	82.86 511	80.36 483	97.92 430	95.27 468	82.09 458	72.02 492	86.87 501	62.81 470	90.74 499	71.10 484	63.08 494	89.19 492

RoMa-SfM		74.91 465	72.77 467	81.35 479	88.00 484	67.35 501	93.55 489	86.23 518	68.27 499	66.79 500	92.92 457	30.40 506	87.68 506	66.14 498	62.62 496	89.02 493

FE-MVSNET		81.05 452	78.81 460	87.79 462	81.98 513	83.70 457	98.23 419	91.78 504	81.27 461	74.29 488	87.44 497	60.92 477	90.67 500	64.92 501	68.43 481	89.01 494

DenseAffine		75.91 462	73.39 466	83.47 474	89.52 477	71.86 496	93.39 492	89.29 513	71.44 494	66.83 499	90.32 481	30.65 505	89.67 502	68.20 491	60.88 504	88.88 495

MatchFormer		70.84 468	66.72 475	83.19 476	85.99 498	64.61 504	93.58 488	88.62 514	59.32 510	50.64 517	82.31 512	28.00 511	96.79 401	52.52 519	59.50 508	88.18 496

MASt3R-SfM		78.94 459	79.57 457	77.07 484	84.15 506	50.74 523	91.56 500	92.34 500	83.22 449	80.84 461	94.16 443	36.67 502	92.30 491	79.45 457	73.71 461	88.16 497

LCM-MVSNet		67.77 476	64.73 479	76.87 486	62.95 541	56.25 517	89.37 510	93.74 494	44.53 519	61.99 504	80.74 513	20.42 531	86.53 511	69.37 488	59.50 508	87.84 498

DKM		72.18 467	69.80 470	79.34 482	86.79 488	65.15 503	92.70 494	84.00 519	67.67 500	61.97 505	89.63 483	23.69 522	85.17 512	67.39 493	54.35 515	87.70 499

tmp_tt		65.23 479	62.94 482	72.13 498	44.90 556	50.03 526	81.05 525	89.42 512	38.45 521	48.51 521	99.90 23	54.09 486	78.70 522	91.84 323	18.26 544	87.64 500

test_fmvs3		79.99 457	80.17 455	79.45 481	84.02 508	62.83 505	99.05 344	93.49 496	88.29 390	80.06 466	86.65 502	28.09 510	88.00 505	88.63 370	73.27 463	87.54 501

test_f		78.40 460	77.59 462	80.81 480	80.82 516	62.48 508	96.96 454	93.08 498	83.44 447	74.57 487	84.57 507	27.95 512	92.63 488	84.15 423	72.79 465	87.32 502

DKM-HiRes		68.91 471	66.34 477	76.62 487	84.17 505	60.69 510	90.78 508	78.55 523	62.17 507	58.82 509	87.54 495	20.94 526	82.56 516	63.05 504	51.00 519	86.61 503

PMatch-SfM		62.12 481	58.57 484	72.76 496	74.34 526	52.97 521	84.95 518	65.57 529	56.89 512	46.61 522	85.70 506	9.51 546	80.54 520	60.53 511	43.03 526	84.77 504

PMatch-Up-SfM		57.92 483	53.93 487	69.90 499	69.97 532	46.69 528	81.36 523	55.29 540	51.90 516	43.17 529	82.54 510	7.86 551	78.44 523	57.13 516	36.17 530	84.58 505

ELoFTR		64.32 480	60.56 483	75.60 490	73.46 528	53.20 520	86.50 516	80.09 522	60.74 508	45.95 523	82.48 511	16.05 537	89.20 503	56.48 518	43.34 525	84.38 506

EGC-MVSNET		69.38 469	63.76 481	86.26 468	90.32 470	81.66 475	96.24 469	93.85 492	0.99 554	3.22 555	92.33 470	52.44 488	92.92 487	59.53 513	84.90 383	84.21 507

RoMa-HiRes		69.18 470	67.02 472	75.65 489	83.52 510	60.31 512	90.80 507	76.82 525	62.46 506	62.85 503	90.44 480	24.75 519	83.07 514	60.58 510	50.97 520	83.58 508

WB-MVS		76.28 461	77.28 463	73.29 492	81.18 515	54.68 518	97.87 433	94.19 487	81.30 460	69.43 496	90.70 478	77.02 390	82.06 517	35.71 527	68.11 484	83.13 509

SSC-MVS		75.42 464	76.40 465	72.49 497	80.68 517	53.62 519	97.42 440	94.06 489	80.42 465	68.75 497	90.14 482	76.54 398	81.66 518	33.25 528	66.34 488	82.19 510

SP-LightGlue		55.29 486	53.65 489	60.20 508	85.58 501	39.12 538	86.36 517	57.52 533	32.34 531	44.34 526	67.75 528	24.36 520	59.32 535	29.62 531	54.98 513	82.17 511

PMMVS2		67.15 477	64.15 480	76.14 488	70.56 531	62.07 509	93.89 483	87.52 515	58.09 511	60.02 506	78.32 514	22.38 524	84.54 513	59.56 512	47.03 523	81.80 512

SP-NN		55.28 488	53.59 490	60.34 506	86.63 493	39.01 539	86.70 514	56.31 536	31.08 532	43.77 527	68.45 525	23.39 523	60.24 532	29.19 533	56.76 512	81.77 513

SP-SuperGlue		55.29 486	53.71 488	60.00 510	85.11 502	38.86 540	86.96 513	57.95 532	32.77 529	44.54 525	68.00 526	23.90 521	59.51 534	29.61 532	54.59 514	81.63 514

SP-MNN		53.97 491	52.04 496	59.73 512	84.72 503	38.63 541	86.51 515	55.94 537	29.25 533	40.20 533	67.48 529	22.18 525	59.59 533	27.79 534	54.33 516	80.98 515

SP-DiffGlue		56.84 484	55.72 486	60.19 509	65.70 537	40.86 536	81.89 520	60.28 531	34.62 528	50.39 519	76.88 516	26.61 515	58.81 536	48.21 521	56.94 511	80.90 516

testf1		68.38 474	66.92 473	72.78 494	78.80 519	50.36 524	90.95 505	87.35 516	55.47 513	58.95 507	88.14 491	20.64 529	87.60 507	57.28 514	64.69 490	80.39 517

APD_test2		68.38 474	66.92 473	72.78 494	78.80 519	50.36 524	90.95 505	87.35 516	55.47 513	58.95 507	88.14 491	20.64 529	87.60 507	57.28 514	64.69 490	80.39 517

FPMVS		68.72 473	68.72 471	68.71 500	65.95 536	44.27 535	95.97 475	94.74 479	51.13 517	53.26 515	90.50 479	25.11 517	83.00 515	60.80 509	80.97 420	78.87 519

VLMVS		51.63 495	52.90 491	47.80 516	47.64 555	20.83 558	69.98 529	55.61 539	20.15 537	63.34 502	87.24 499	19.48 534	43.90 542	62.94 505	49.76 521	78.65 520

ANet_high		56.10 485	52.24 494	67.66 501	49.27 554	56.82 515	83.94 519	82.02 521	70.47 495	33.28 538	64.54 531	17.23 535	69.16 529	45.59 523	23.85 540	77.02 521

GLUNet-SfM		51.10 498	46.61 501	64.56 503	61.54 545	39.88 537	79.38 527	65.13 530	36.09 523	33.36 537	69.94 521	14.50 538	78.76 521	42.46 525	17.10 545	75.02 522

PDCNetPlus		59.83 482	57.26 485	67.55 502	76.18 523	56.71 516	87.01 512	45.27 544	59.54 509	48.80 520	83.01 509	26.63 514	76.54 524	62.12 507	26.78 536	69.40 523

test_vis3_rt		68.82 472	66.69 476	75.21 491	76.24 522	60.41 511	96.44 464	68.71 528	75.13 487	50.54 518	69.52 523	16.42 536	96.32 430	80.27 453	66.92 487	68.89 524

MVE	53.74 22	51.54 496	47.86 500	62.60 504	59.56 548	50.93 522	79.41 526	77.69 524	35.69 525	36.27 535	61.76 535	5.79 557	69.63 528	37.97 526	36.61 529	67.24 525
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	49.05 23	53.75 492	51.34 497	60.97 505	40.80 557	34.68 542	74.82 528	89.62 511	37.55 522	28.67 539	72.12 517	7.09 553	81.63 519	43.17 524	68.21 483	66.59 526
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		66.95 478	65.00 478	72.79 493	91.52 459	67.96 499	66.16 532	95.15 473	47.89 518	58.54 510	67.99 527	29.74 508	87.54 509	50.20 520	77.83 440	62.87 527
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ALIKED-LG		54.29 490	52.28 493	60.32 507	88.90 480	45.51 529	81.66 521	56.33 535	38.60 520	42.62 530	70.81 519	25.00 518	75.20 526	19.87 540	46.76 524	60.24 528

ALIKED-NN		54.48 489	52.67 492	59.89 511	90.79 466	45.45 530	81.25 524	55.75 538	34.99 527	44.87 524	71.98 518	25.50 516	74.36 527	21.88 538	47.04 522	59.85 529

ALIKED-MNN		52.51 493	50.15 499	59.60 513	90.05 472	44.33 534	81.60 522	54.93 541	32.36 530	40.96 532	68.77 524	20.90 527	75.30 525	20.00 539	41.78 527	59.18 530

test123		37.68 502	39.14 505	33.31 520	19.94 558	24.83 555	98.36 412	9.75 560	15.53 552	51.31 516	87.14 500	19.62 533	17.74 555	47.10 522	3.47 554	57.36 531

testmvs		40.60 501	44.45 502	29.05 530	19.49 559	14.11 562	99.68 233	18.47 558	20.74 536	64.59 501	98.48 279	10.95 540	17.09 556	56.66 517	11.01 551	55.94 532

XFeat-MNN		41.51 500	41.24 504	42.32 517	55.40 552	28.19 546	69.39 531	46.53 542	23.57 535	34.47 536	63.21 534	20.04 532	52.41 537	27.43 536	31.08 535	46.37 533

EMVS		51.44 497	51.22 498	52.11 515	70.71 530	44.97 533	94.04 482	75.66 527	35.34 526	42.40 531	61.56 536	28.93 509	65.87 531	27.64 535	24.73 538	45.49 534

XFeat-NN		42.54 499	42.87 503	41.54 518	59.73 547	27.86 547	69.53 530	45.34 543	24.36 534	37.16 534	64.79 530	20.84 528	51.40 538	30.01 530	34.12 532	45.36 535

E-PMN		52.30 494	52.18 495	52.67 514	71.51 529	45.40 531	93.62 487	76.60 526	36.01 524	43.50 528	64.13 532	27.11 513	67.31 530	31.06 529	26.06 537	45.30 536

SIFT-NN		35.94 503	36.54 506	34.16 519	73.93 527	29.52 543	62.74 533	37.28 545	19.65 538	27.91 540	49.19 538	11.66 539	46.35 539	9.19 541	37.30 528	26.61 537

SIFT-NN-CMatch		31.71 507	31.56 510	32.16 523	62.58 542	27.53 551	56.45 538	33.28 549	19.00 542	23.65 543	47.34 539	10.05 544	42.72 545	8.71 544	22.96 541	26.24 538

SIFT-NN-NCMNet		33.88 505	34.14 508	33.10 522	66.88 535	28.42 545	60.42 534	36.72 547	19.15 539	24.06 541	47.14 542	10.24 541	44.77 541	8.72 542	33.94 533	26.10 539

SIFT-MNN		34.10 504	34.41 507	33.17 521	68.99 533	28.51 544	60.22 535	36.81 546	19.08 541	24.04 542	47.28 541	10.06 543	45.04 540	8.72 542	34.47 531	25.97 540

SIFT-NN-UMatch		31.23 508	31.05 512	31.79 525	60.08 546	27.23 552	58.49 536	33.65 548	19.14 540	17.30 546	47.31 540	10.12 542	42.88 544	8.67 545	24.67 539	25.27 541

SIFT-NN-PointCN		29.63 510	29.72 514	29.36 529	57.55 549	23.55 557	56.07 540	30.57 552	17.99 548	20.99 544	45.21 546	9.94 545	39.33 550	8.40 546	20.81 542	25.20 542

SIFT-NCM-Cal		31.73 506	31.67 509	31.91 524	67.18 534	27.55 550	58.36 537	33.09 550	18.38 544	14.93 549	45.16 547	8.60 547	43.82 543	7.62 551	31.68 534	24.36 543

SIFT-UMatch		29.40 511	28.87 515	30.98 527	62.08 544	26.57 553	56.09 539	29.45 553	18.31 545	15.86 548	46.00 543	8.23 549	42.54 546	7.99 548	15.81 546	23.85 544

SIFT-ConvMatch		30.09 509	29.76 513	31.09 526	65.16 539	27.56 549	54.13 541	31.17 551	18.55 543	17.88 545	45.89 544	8.40 548	42.26 547	8.11 547	18.51 543	23.46 545

SIFT-CM-Cal		28.34 512	27.90 516	29.63 528	63.75 540	25.98 554	50.66 544	26.18 555	18.12 547	16.88 547	44.64 548	8.08 550	39.70 548	7.65 550	15.19 548	23.22 546

SIFT-UM-Cal		27.47 513	27.02 517	28.83 531	62.12 543	24.58 556	53.60 542	23.46 556	18.14 546	12.85 551	45.56 545	7.49 552	39.45 549	7.68 549	12.30 549	22.45 547

SIFT-PointCN		25.49 514	25.71 518	24.84 532	56.17 550	18.65 559	51.37 543	26.53 554	16.31 549	12.78 552	39.87 551	6.41 555	34.09 552	6.51 553	15.42 547	21.77 548

SIFT-PCN-Cal		24.67 515	24.81 519	24.24 533	56.13 551	18.04 560	49.05 546	23.39 557	16.07 550	12.99 550	40.17 550	6.97 554	34.68 551	6.71 552	11.81 550	19.99 549

SIFT-NCMNet		21.21 517	21.22 520	21.17 534	52.99 553	16.41 561	42.12 547	14.05 559	15.89 551	10.70 553	35.85 552	5.14 558	29.82 553	5.80 554	8.44 553	17.28 550

wuyk23d		20.37 518	20.84 521	18.99 535	65.34 538	27.73 548	50.43 545	7.67 561	9.50 553	8.01 554	6.34 553	6.13 556	26.24 554	23.40 537	10.69 552	2.99 551

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

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

test_blank		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.02 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

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

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

cdsmvs_eth3d_5k		23.43 516	31.24 511	0.00 536	0.00 560	0.00 563	0.00 548	98.09 235	0.00 555	0.00 556	99.67 114	83.37 316	0.00 557	0.00 555	0.00 555	0.00 552

pcd_1.5k_mvsjas		7.60 520	10.13 523	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 555	91.20 178	0.00 557	0.00 555	0.00 555	0.00 552

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

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

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

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

ab-mvs-re		8.28 519	11.04 522	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	99.40 147	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

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

PatchmatchNet2					0.00 560	86.19 439	98.94 360	96.51 438	78.40 477
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													95.80 449
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					99.95 17	99.33 9		98.42 168		99.04 115		96.44 36	100.00 1	99.98 9	99.98 32

WAC-MVS						90.97 371								86.10 412

FOURS1					99.92 37	97.66 106	99.95 75	98.36 189	95.58 112	99.52 76

test_one_0601					99.94 18	99.30 14		98.41 174	96.63 75	99.75 42	99.93 12	97.49 11

eth-test2					0.00 560

eth-test					0.00 560

ZD-MVS					99.92 37	98.57 62		98.52 128	92.34 271	99.31 95	99.83 51	95.06 64	99.80 144	99.70 50	99.97 44

test_241102_ONE					99.93 29	99.30 14		98.43 156	97.26 49	99.80 28	99.88 29	96.71 29	100.00 1

9.14			98.38 41		99.87 57		99.91 111	98.33 196	93.22 214	99.78 39	99.89 27	94.57 81	99.85 131	99.84 30	99.97 44

save fliter					99.82 66	98.79 43	99.96 56	98.40 178	97.66 33

test0726					99.93 29	99.29 17	99.96 56	98.42 168	97.28 45	99.86 16	99.94 5	97.22 21

test_part2					99.89 51	99.25 20				99.49 79

sam_mvs												94.25 95

MTGPA								98.28 205

test_post1							95.78 477				59.23 537	93.20 129	97.74 344	91.06 333

test_post											63.35 533	94.43 83	98.13 323

patchmatchnet-post											91.70 473	95.12 61	97.95 335

MTMP							99.87 133	96.49 439

gm-plane-assit					96.97 318	93.76 286			91.47 304		98.96 214		98.79 245	94.92 255

TEST9					99.92 37	98.92 32	99.96 56	98.43 156	93.90 186	99.71 49	99.86 34	95.88 46	99.85 131

test_8					99.92 37	98.88 35	99.96 56	98.43 156	94.35 157	99.69 51	99.85 38	95.94 43	99.85 131

agg_prior					99.93 29	98.77 48		98.43 156		99.63 59			99.85 131

test_prior4						98.05 83	99.94 93

test_prior2							99.95 75		95.78 105	99.73 47	99.76 73	96.00 42		99.78 36	100.00 1

旧先验2							99.46 284		94.21 167	99.85 20			99.95 86	96.96 203

新几何2							99.40 289

原ACMM2							99.90 117

testdata2													99.99 40	90.54 346

segment_acmp												96.68 31

testdata1							99.28 315		96.35 91

plane_prior7					95.71 372	91.59 364

plane_prior6					95.76 366	91.72 354						80.47 357

plane_prior4											98.59 265

plane_prior3						91.64 358			96.63 75	93.01 308

plane_prior2							99.84 152		96.38 86

plane_prior1					95.73 369

plane_prior						91.74 350	99.86 144		96.76 70						89.59 332

n2								0.00 562

nn								0.00 562

door-mid								89.69 509

test11								98.44 148

door								90.31 506

HQP5-MVS						91.85 343

HQP-NCC					95.78 362		99.87 133		96.82 66	93.37 303

ACMP_Plane					95.78 362		99.87 133		96.82 66	93.37 303

BP-MVS														97.92 161

HQP3-MVS								97.89 257							89.60 330

HQP2-MVS												80.65 353

NP-MVS					95.77 365	91.79 347					98.65 257

MDTV_nov1_ep13			95.69 200		97.90 228	94.15 274	95.98 474	98.44 148	93.12 223	97.98 174	95.74 377	95.10 62	98.58 276	90.02 354	96.92 239

ACMMP++_ref															87.04 366

ACMMP++															88.23 353

Test By Simon												92.82 140

High-resolution multi-view benchmark