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.

CHOSEN 280x420		99.01 13	99.03 10	98.95 72	99.38 95	98.87 30	98.46 284	99.42 21	97.03 30	99.02 79	99.09 132	99.35 1	98.21 218	99.73 28	99.78 79	99.77 95

GG-mvs-BLEND				98.54 97	98.21 158	98.01 66	93.87 350	98.52 90		97.92 122	97.92 204	99.02 2	97.94 234	98.17 93	99.58 93	99.67 107

gg-mvs-nofinetune		93.51 198	91.86 223	98.47 102	97.72 190	97.96 70	92.62 354	98.51 93	74.70 356	97.33 135	69.59 369	98.91 3	97.79 237	97.77 116	99.56 94	99.67 107

iter_conf05		96.07 130	95.95 121	96.44 182	98.43 146	97.52 83	99.91 71	96.85 298	94.16 117	92.49 213	97.98 201	98.20 4	97.34 252	97.26 126	88.29 245	94.45 242

iter_conf_final		96.01 133	95.93 123	96.28 187	98.38 148	97.03 103	99.87 88	97.03 278	94.05 126	92.61 211	97.98 201	98.01 5	97.34 252	97.02 133	88.39 244	94.47 236

test_0728_THIRD									96.48 47	99.83 11	99.91 14	97.87 6	100.00 1	99.92 12	100.00 1	100.00 1

baseline2		96.71 109	96.49 102	97.37 154	95.63 270	95.96 140	99.74 138	98.88 45	92.94 159	91.61 217	98.97 145	97.72 7	98.62 181	94.83 169	98.08 142	97.53 219

SteuartSystems-ACMMP		99.02 12	98.97 13	99.18 46	98.72 132	97.71 75	99.98 9	98.44 105	96.85 34	99.80 15	99.91 14	97.57 8	99.85 95	99.44 37	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
thisisatest0515		97.41 83	97.02 88	98.59 91	97.71 192	97.52 83	99.97 19	98.54 87	91.83 202	97.45 133	99.04 135	97.50 9	99.10 158	94.75 172	96.37 176	99.16 179

PC_three_1452									96.96 32	99.80 15	99.79 54	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_one_0601					99.94 13	99.30 11		98.41 128	96.63 44	99.75 26	99.93 11	97.49 10

thisisatest0530		97.10 92	96.72 95	98.22 115	97.60 196	96.70 113	99.92 67	98.54 87	91.11 224	97.07 140	98.97 145	97.47 12	99.03 159	93.73 197	96.09 179	98.92 189

tttt0517		96.85 100	96.49 102	97.92 127	97.48 202	95.89 142	99.85 103	98.54 87	90.72 233	96.63 150	98.93 156	97.47 12	99.02 160	93.03 209	95.76 188	98.85 193

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 9	99.95 43	98.43 113	96.48 47	99.80 15	99.93 11	97.44 14	100.00 1	99.92 12	99.98 32	100.00 1

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 26				99.80 51	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

MSP-MVS		99.09 9	99.12 5	98.98 69	99.93 24	97.24 94	99.95 43	98.42 124	97.50 16	99.52 51	99.88 21	97.43 16	99.71 124	99.50 34	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
NCCC		99.37 2	99.25 2	99.71 13	99.96 8	99.15 20	99.97 19	98.62 70	98.02 6	99.90 2	99.95 3	97.33 17	100.00 1	99.54 32	100.00 1	100.00 1

MVSTER		95.53 148	95.22 144	96.45 180	98.56 137	97.72 74	99.91 71	97.67 212	92.38 187	91.39 219	97.14 221	97.24 18	97.30 257	94.80 170	87.85 252	94.34 252

DVP-MVS		99.30 4	99.16 3	99.73 11	99.93 24	99.29 14	99.95 43	98.32 150	97.28 21	99.83 11	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 79
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
test0726					99.93 24	99.29 14	99.96 26	98.42 124	97.28 21	99.86 5	99.94 4	97.22 19

test_241102_TWO								98.43 113	97.27 23	99.80 15	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

DPM-MVS		98.83 18	98.46 25	99.97 1	99.33 97	99.92 1	99.96 26	98.44 105	97.96 7	99.55 46	99.94 4	97.18 21	100.00 1	93.81 192	99.94 54	99.98 48

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 9	98.69 58	98.20 3	99.93 1	99.98 2	96.82 23	100.00 1	99.75 24	100.00 1	99.99 23

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 11	99.96 26	98.43 113	97.27 23	99.80 15	99.94 4	96.71 24	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 11		98.43 113	97.26 25	99.80 15	99.88 21	96.71 24	100.00 1

DPE-MVS		99.26 6	99.10 8	99.74 10	99.89 45	99.24 18	99.87 88	98.44 105	97.48 17	99.64 36	99.94 4	96.68 26	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
segment_acmp												96.68 26

patch_mono-2		98.24 50	99.12 5	95.59 201	99.67 77	86.91 317	99.95 43	98.89 43	97.60 12	99.90 2	99.76 62	96.54 28	99.98 42	99.94 11	99.82 76	99.88 80

PAPM		98.60 26	98.42 26	99.14 55	96.05 250	98.96 24	99.90 76	99.35 24	96.68 43	98.35 110	99.66 89	96.45 29	98.51 186	99.45 36	99.89 66	99.96 61

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 19	98.64 66	98.47 2	99.13 75	99.92 13	96.38 30	100.00 1	99.74 26	100.00 1	100.00 1

ET-MVSNet_ETH3D		94.37 177	93.28 194	97.64 140	98.30 151	97.99 67	99.99 3	97.61 219	94.35 108	71.57 358	99.45 106	96.23 31	95.34 332	96.91 139	85.14 274	99.59 124

EPP-MVSNet		96.69 110	96.60 98	96.96 165	97.74 185	93.05 216	99.37 199	98.56 78	88.75 265	95.83 171	99.01 138	96.01 32	98.56 183	96.92 138	97.20 159	99.25 174

test_prior2							99.95 43		95.78 65	99.73 28	99.76 62	96.00 33		99.78 23	100.00 1

train_agg		98.88 17	98.65 18	99.59 21	99.92 31	98.92 26	99.96 26	98.43 113	94.35 108	99.71 30	99.86 26	95.94 34	99.85 95	99.69 31	99.98 32	99.99 23

test_8					99.92 31	98.88 29	99.96 26	98.43 113	94.35 108	99.69 32	99.85 30	95.94 34	99.85 95

MSLP-MVS++		99.13 8	99.01 11	99.49 30	99.94 13	98.46 57	99.98 9	98.86 47	97.10 28	99.80 15	99.94 4	95.92 36	100.00 1	99.51 33	100.00 1	100.00 1

TEST9					99.92 31	98.92 26	99.96 26	98.43 113	93.90 134	99.71 30	99.86 26	95.88 37	99.85 95

test_yl		97.83 64	97.37 74	99.21 43	99.18 100	97.98 68	99.64 160	99.27 26	91.43 215	97.88 124	98.99 141	95.84 38	99.84 102	98.82 64	95.32 196	99.79 91

DCV-MVSNet		97.83 64	97.37 74	99.21 43	99.18 100	97.98 68	99.64 160	99.27 26	91.43 215	97.88 124	98.99 141	95.84 38	99.84 102	98.82 64	95.32 196	99.79 91

DP-MVS Recon		98.41 39	98.02 51	99.56 23	99.97 3	98.70 44	99.92 67	98.44 105	92.06 196	98.40 108	99.84 41	95.68 40	100.00 1	98.19 92	99.71 83	99.97 55

旧先验1					99.76 66	97.52 83		98.64 66			99.85 30	95.63 41			99.94 54	99.99 23

SMA-MVS		98.76 20	98.48 24	99.62 18	99.87 51	98.87 30	99.86 100	98.38 139	93.19 154	99.77 24	99.94 4	95.54 42	100.00 1	99.74 26	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
TESTMET0.1,1		96.74 107	96.26 107	98.16 116	97.36 207	96.48 119	99.96 26	98.29 156	91.93 199	95.77 172	98.07 196	95.54 42	98.29 210	90.55 243	98.89 118	99.70 102

APDe-MVS		99.06 11	98.91 14	99.51 27	99.94 13	98.76 41	99.91 71	98.39 135	97.20 27	99.46 54	99.85 30	95.53 44	99.79 109	99.86 17	100.00 1	99.99 23

PLC	95.54 3	97.93 59	97.89 61	98.05 123	99.82 58	94.77 179	99.92 67	98.46 101	93.93 132	97.20 137	99.27 119	95.44 45	99.97 51	97.41 122	99.51 98	99.41 155
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HPM-MVS++		99.07 10	98.88 15	99.63 15	99.90 42	99.02 23	99.95 43	98.56 78	97.56 15	99.44 56	99.85 30	95.38 46	100.00 1	99.31 41	99.99 21	99.87 82

PHI-MVS		98.41 39	98.21 39	99.03 64	99.86 53	97.10 101	99.98 9	98.80 52	90.78 232	99.62 39	99.78 58	95.30 47	100.00 1	99.80 21	99.93 60	99.99 23

test-mter		96.39 121	95.93 123	97.78 133	97.02 222	95.44 157	99.96 26	98.21 164	91.81 204	95.55 174	96.38 248	95.17 48	98.27 214	90.42 246	98.83 120	99.64 113

patchmatchnet-post											91.70 341	95.12 49	97.95 232

MDTV_nov1_ep13			95.69 131		97.90 174	94.15 188	95.98 340	98.44 105	93.12 156	97.98 120	95.74 265	95.10 50	98.58 182	90.02 252	96.92 167

IB-MVS	92.85 6	94.99 159	93.94 173	98.16 116	97.72 190	95.69 151	99.99 3	98.81 50	94.28 113	92.70 210	96.90 231	95.08 51	99.17 155	96.07 148	73.88 342	99.60 123
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
ZD-MVS					99.92 31	98.57 52		98.52 90	92.34 188	99.31 66	99.83 43	95.06 52	99.80 107	99.70 30	99.97 42

CDS-MVSNet		96.34 122	96.07 110	97.13 161	97.37 206	94.96 172	99.53 176	97.91 196	91.55 210	95.37 178	98.32 191	95.05 53	97.13 268	93.80 193	95.75 189	99.30 169
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Patchmatch-test		92.65 219	91.50 229	96.10 192	96.85 231	90.49 272	91.50 359	97.19 259	82.76 333	90.23 231	95.59 272	95.02 54	98.00 228	77.41 339	96.98 166	99.82 87

CostFormer		96.10 129	95.88 127	96.78 170	97.03 221	92.55 230	97.08 321	97.83 204	90.04 244	98.72 93	94.89 305	95.01 55	98.29 210	96.54 143	95.77 187	99.50 144

TSAR-MVS + GP.		98.60 26	98.51 23	98.86 76	99.73 72	96.63 115	99.97 19	97.92 195	98.07 5	98.76 91	99.55 97	95.00 56	99.94 69	99.91 15	97.68 148	99.99 23

CDPH-MVS		98.65 24	98.36 33	99.49 30	99.94 13	98.73 42	99.87 88	98.33 148	93.97 129	99.76 25	99.87 24	94.99 57	99.75 118	98.55 80	100.00 1	99.98 48

原ACMM1				98.96 71	99.73 72	96.99 105		98.51 93	94.06 124	99.62 39	99.85 30	94.97 58	99.96 54	95.11 159	99.95 49	99.92 76

TSAR-MVS + MP.		98.93 14	98.77 16	99.41 36	99.74 69	98.67 45	99.77 127	98.38 139	96.73 41	99.88 4	99.74 72	94.89 59	99.59 135	99.80 21	99.98 32	99.97 55
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test12				99.43 33	99.74 69	98.56 53		98.40 132		99.65 35		94.76 60	99.75 118		99.98 32	99.99 23

sam_mvs1												94.72 61				99.59 124

SF-MVS		98.67 23	98.40 27	99.50 28	99.77 65	98.67 45	99.90 76	98.21 164	93.53 144	99.81 13	99.89 19	94.70 62	99.86 94	99.84 18	99.93 60	99.96 61

SD-MVS		98.92 15	98.70 17	99.56 23	99.70 76	98.73 42	99.94 58	98.34 147	96.38 52	99.81 13	99.76 62	94.59 63	99.98 42	99.84 18	99.96 46	99.97 55
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
9.14			98.38 29		99.87 51		99.91 71	98.33 148	93.22 153	99.78 23	99.89 19	94.57 64	99.85 95	99.84 18	99.97 42

test_post											63.35 374	94.43 65	98.13 221

EPMVS		96.53 115	96.01 112	98.09 121	98.43 146	96.12 138	96.36 331	99.43 20	93.53 144	97.64 128	95.04 298	94.41 66	98.38 202	91.13 229	98.11 139	99.75 97

新几何1				99.42 35	99.75 68	98.27 59		98.63 69	92.69 171	99.55 46	99.82 46	94.40 67	100.00 1	91.21 227	99.94 54	99.99 23

MDTV_nov1_ep13_2view						96.26 128	96.11 337		91.89 200	98.06 118		94.40 67		94.30 182		99.67 107

PAPM_NR		98.12 54	97.93 58	98.70 82	99.94 13	96.13 136	99.82 115	98.43 113	94.56 99	97.52 130	99.70 80	94.40 67	99.98 42	97.00 134	99.98 32	99.99 23

dcpmvs_2		97.42 82	98.09 48	95.42 206	99.58 84	87.24 313	99.23 216	96.95 287	94.28 113	98.93 83	99.73 74	94.39 70	99.16 156	99.89 16	99.82 76	99.86 84

miper_enhance_ethall		94.36 179	93.98 172	95.49 202	98.68 134	95.24 165	99.73 143	97.29 253	93.28 152	89.86 239	95.97 261	94.37 71	97.05 274	92.20 216	84.45 279	94.19 261

XVS		98.70 22	98.55 21	99.15 53	99.94 13	97.50 86	99.94 58	98.42 124	96.22 57	99.41 59	99.78 58	94.34 72	99.96 54	98.92 57	99.95 49	99.99 23

X-MVStestdata		93.83 187	92.06 217	99.15 53	99.94 13	97.50 86	99.94 58	98.42 124	96.22 57	99.41 59	41.37 378	94.34 72	99.96 54	98.92 57	99.95 49	99.99 23

CP-MVS		98.45 36	98.32 35	98.87 75	99.96 8	96.62 116	99.97 19	98.39 135	94.43 103	98.90 84	99.87 24	94.30 74	100.00 1	99.04 51	99.99 21	99.99 23

sam_mvs												94.25 75

Patchmatch-RL test		86.90 298	85.98 301	89.67 319	84.45 360	75.59 357	89.71 364	92.43 363	86.89 294	77.83 345	90.94 344	94.22 76	93.63 350	87.75 276	69.61 349	99.79 91

HFP-MVS		98.56 28	98.37 31	99.14 55	99.96 8	97.43 90	99.95 43	98.61 71	94.77 91	99.31 66	99.85 30	94.22 76	100.00 1	98.70 71	99.98 32	99.98 48

PatchmatchNet		95.94 135	95.45 136	97.39 153	97.83 179	94.41 185	96.05 338	98.40 132	92.86 160	97.09 139	95.28 293	94.21 78	98.07 225	89.26 259	98.11 139	99.70 102
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DeepPCF-MVS	95.94 2	97.71 73	98.98 12	93.92 265	99.63 79	81.76 344	99.96 26	98.56 78	99.47 1	99.19 73	99.99 1	94.16 79	100.00 1	99.92 12	99.93 60	100.00 1

APD-MVS		98.62 25	98.35 34	99.41 36	99.90 42	98.51 55	99.87 88	98.36 143	94.08 121	99.74 27	99.73 74	94.08 80	99.74 120	99.42 38	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
region2R		98.54 29	98.37 31	99.05 62	99.96 8	97.18 97	99.96 26	98.55 84	94.87 89	99.45 55	99.85 30	94.07 81	100.00 1	98.67 73	100.00 1	99.98 48

PAPR		98.52 31	98.16 43	99.58 22	99.97 3	98.77 38	99.95 43	98.43 113	95.35 77	98.03 119	99.75 67	94.03 82	99.98 42	98.11 97	99.83 72	99.99 23

MG-MVS		98.91 16	98.65 18	99.68 14	99.94 13	99.07 22	99.64 160	99.44 19	97.33 20	99.00 80	99.72 76	94.03 82	99.98 42	98.73 70	100.00 1	100.00 1

MVS_111021_HR		98.72 21	98.62 20	99.01 67	99.36 96	97.18 97	99.93 64	99.90 1	96.81 39	98.67 95	99.77 60	93.92 84	99.89 83	99.27 43	99.94 54	99.96 61

tpmrst		96.27 128	95.98 115	97.13 161	97.96 171	93.15 213	96.34 332	98.17 169	92.07 194	98.71 94	95.12 296	93.91 85	98.73 173	94.91 167	96.62 170	99.50 144

test-LLR		96.47 116	96.04 111	97.78 133	97.02 222	95.44 157	99.96 26	98.21 164	94.07 122	95.55 174	96.38 248	93.90 86	98.27 214	90.42 246	98.83 120	99.64 113

test0.0.03 1		93.86 186	93.61 179	94.64 233	95.02 279	92.18 237	99.93 64	98.58 74	94.07 122	87.96 280	98.50 181	93.90 86	94.96 337	81.33 322	93.17 215	96.78 222

test222					99.55 85	97.41 92	99.34 202	98.55 84	91.86 201	99.27 70	99.83 43	93.84 88			99.95 49	99.99 23

dp		95.05 157	94.43 162	96.91 166	97.99 170	92.73 224	96.29 334	97.98 187	89.70 248	95.93 168	94.67 311	93.83 89	98.45 191	86.91 290	96.53 172	99.54 136

ACMMPR		98.50 32	98.32 35	99.05 62	99.96 8	97.18 97	99.95 43	98.60 72	94.77 91	99.31 66	99.84 41	93.73 90	100.00 1	98.70 71	99.98 32	99.98 48

EPNet		98.49 33	98.40 27	98.77 79	99.62 80	96.80 112	99.90 76	99.51 16	97.60 12	99.20 71	99.36 114	93.71 91	99.91 77	97.99 104	98.71 123	99.61 121
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
alignmvs		97.81 67	97.33 76	99.25 41	98.77 130	98.66 47	99.99 3	98.44 105	94.40 107	98.41 106	99.47 103	93.65 92	99.42 148	98.57 79	94.26 205	99.67 107

testdata				98.42 107	99.47 91	95.33 161		98.56 78	93.78 137	99.79 22	99.85 30	93.64 93	99.94 69	94.97 163	99.94 54	100.00 1

EI-MVSNet-Vis-set		98.27 46	98.11 47	98.75 80	99.83 57	96.59 118	99.40 192	98.51 93	95.29 79	98.51 102	99.76 62	93.60 94	99.71 124	98.53 81	99.52 96	99.95 68

mPP-MVS		98.39 41	98.20 40	98.97 70	99.97 3	96.92 108	99.95 43	98.38 139	95.04 83	98.61 99	99.80 51	93.39 95	100.00 1	98.64 76	100.00 1	99.98 48

SR-MVS		98.46 35	98.30 37	98.93 73	99.88 49	97.04 102	99.84 107	98.35 145	94.92 87	99.32 65	99.80 51	93.35 96	99.78 111	99.30 42	99.95 49	99.96 61

WTY-MVS		98.10 55	97.60 68	99.60 20	98.92 119	99.28 16	99.89 83	99.52 14	95.58 71	98.24 116	99.39 111	93.33 97	99.74 120	97.98 106	95.58 192	99.78 94

tpm2		95.47 149	95.18 146	96.35 186	96.91 226	91.70 252	96.96 324	97.93 192	88.04 278	98.44 105	95.40 282	93.32 98	97.97 229	94.00 186	95.61 191	99.38 157

HY-MVS	92.50 7	97.79 69	97.17 82	99.63 15	98.98 112	99.32 8	97.49 312	99.52 14	95.69 68	98.32 111	97.41 214	93.32 98	99.77 114	98.08 100	95.75 189	99.81 88

EI-MVSNet-UG-set		98.14 53	97.99 52	98.60 89	99.80 61	96.27 127	99.36 201	98.50 97	95.21 81	98.30 112	99.75 67	93.29 100	99.73 123	98.37 86	99.30 107	99.81 88

SR-MVS-dyc-post		98.31 43	98.17 42	98.71 81	99.79 62	96.37 125	99.76 132	98.31 152	94.43 103	99.40 61	99.75 67	93.28 101	99.78 111	98.90 60	99.92 63	99.97 55

baseline1		95.78 139	94.86 155	98.54 97	98.47 145	98.07 63	99.06 233	97.99 185	92.68 172	94.13 193	98.62 175	93.28 101	98.69 178	93.79 194	85.76 267	98.84 194

PGM-MVS		98.34 42	98.13 45	98.99 68	99.92 31	97.00 104	99.75 135	99.50 17	93.90 134	99.37 63	99.76 62	93.24 103	100.00 1	97.75 118	99.96 46	99.98 48

test_post1							95.78 343				59.23 377	93.20 104	97.74 240	91.06 231

CSCG		97.10 92	97.04 86	97.27 159	99.89 45	91.92 243	99.90 76	99.07 32	88.67 267	95.26 180	99.82 46	93.17 105	99.98 42	98.15 95	99.47 99	99.90 78

DeepC-MVS_fast	96.59 1	98.81 19	98.54 22	99.62 18	99.90 42	98.85 32	99.24 215	98.47 99	98.14 4	99.08 76	99.91 14	93.09 106	100.00 1	99.04 51	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
ZNCC-MVS		98.31 43	98.03 50	99.17 49	99.88 49	97.59 80	99.94 58	98.44 105	94.31 111	98.50 103	99.82 46	93.06 107	99.99 36	98.30 90	99.99 21	99.93 71

GST-MVS		98.27 46	97.97 53	99.17 49	99.92 31	97.57 81	99.93 64	98.39 135	94.04 127	98.80 87	99.74 72	92.98 108	100.00 1	98.16 94	99.76 80	99.93 71

RE-MVS-def			98.13 45		99.79 62	96.37 125	99.76 132	98.31 152	94.43 103	99.40 61	99.75 67	92.95 109		98.90 60	99.92 63	99.97 55

CS-MVS		97.79 69	97.91 59	97.43 150	99.10 104	94.42 184	99.99 3	97.10 270	95.07 82	99.68 33	99.75 67	92.95 109	98.34 206	98.38 85	99.14 113	99.54 136

ACMMP_NAP		98.49 33	98.14 44	99.54 25	99.66 78	98.62 51	99.85 103	98.37 142	94.68 96	99.53 49	99.83 43	92.87 111	100.00 1	98.66 75	99.84 71	99.99 23

APD-MVS_3200maxsize		98.25 49	98.08 49	98.78 78	99.81 60	96.60 117	99.82 115	98.30 155	93.95 131	99.37 63	99.77 60	92.84 112	99.76 117	98.95 54	99.92 63	99.97 55

JIA-IIPM		91.76 239	90.70 239	94.94 222	96.11 248	87.51 311	93.16 353	98.13 177	75.79 352	97.58 129	77.68 366	92.84 112	97.97 229	88.47 268	96.54 171	99.33 165

Test By Simon												92.82 114

MTAPA		98.29 45	97.96 56	99.30 40	99.85 54	97.93 71	99.39 196	98.28 157	95.76 66	97.18 138	99.88 21	92.74 115	100.00 1	98.67 73	99.88 68	99.99 23

EPNet_dtu		95.71 142	95.39 138	96.66 175	98.92 119	93.41 209	99.57 169	98.90 42	96.19 59	97.52 130	98.56 180	92.65 116	97.36 250	77.89 337	98.33 130	99.20 177
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MP-MVS-pluss		98.07 56	97.64 66	99.38 39	99.74 69	98.41 58	99.74 138	98.18 168	93.35 148	96.45 155	99.85 30	92.64 117	99.97 51	98.91 59	99.89 66	99.77 95
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
FE-MVS		95.70 144	95.01 152	97.79 132	98.21 158	94.57 180	95.03 345	98.69 58	88.90 262	97.50 132	96.19 254	92.60 118	99.49 144	89.99 253	97.94 145	99.31 167

DELS-MVS		98.54 29	98.22 38	99.50 28	99.15 103	98.65 49	100.00 1	98.58 74	97.70 10	98.21 117	99.24 124	92.58 119	99.94 69	98.63 78	99.94 54	99.92 76
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
ETV-MVS		97.92 60	97.80 63	98.25 114	98.14 164	96.48 119	99.98 9	97.63 214	95.61 70	99.29 69	99.46 105	92.55 120	98.82 166	99.02 53	98.54 125	99.46 148

test2506		97.53 76	97.19 80	98.58 92	98.66 135	96.90 109	98.81 263	99.77 5	94.93 85	97.95 121	98.96 147	92.51 121	99.20 152	94.93 164	98.15 136	99.64 113

KD-MVS_2432*1600		88.00 294	86.10 298	93.70 275	96.91 226	94.04 191	97.17 318	97.12 268	84.93 317	81.96 325	92.41 336	92.48 122	94.51 342	79.23 330	52.68 368	92.56 326

miper_refine_blended		88.00 294	86.10 298	93.70 275	96.91 226	94.04 191	97.17 318	97.12 268	84.93 317	81.96 325	92.41 336	92.48 122	94.51 342	79.23 330	52.68 368	92.56 326

EIA-MVS		97.53 76	97.46 71	97.76 136	98.04 168	94.84 175	99.98 9	97.61 219	94.41 106	97.90 123	99.59 94	92.40 124	98.87 164	98.04 101	99.13 114	99.59 124

F-COLMAP		96.93 98	96.95 89	96.87 168	99.71 75	91.74 248	99.85 103	97.95 190	93.11 157	95.72 173	99.16 130	92.35 125	99.94 69	95.32 157	99.35 106	98.92 189

API-MVS		97.86 62	97.66 65	98.47 102	99.52 87	95.41 159	99.47 186	98.87 46	91.68 207	98.84 85	99.85 30	92.34 126	99.99 36	98.44 83	99.96 46	100.00 1

CNLPA		97.76 71	97.38 73	98.92 74	99.53 86	96.84 110	99.87 88	98.14 176	93.78 137	96.55 153	99.69 82	92.28 127	99.98 42	97.13 129	99.44 102	99.93 71

TAMVS		95.85 137	95.58 134	96.65 176	97.07 218	93.50 205	99.17 221	97.82 205	91.39 219	95.02 182	98.01 197	92.20 128	97.30 257	93.75 196	95.83 186	99.14 182

1112_ss		96.01 133	95.20 145	98.42 107	97.80 181	96.41 122	99.65 156	96.66 310	92.71 169	92.88 208	99.40 109	92.16 129	99.30 149	91.92 220	93.66 210	99.55 133

Test_1112_low_res		95.72 140	94.83 156	98.42 107	97.79 182	96.41 122	99.65 156	96.65 311	92.70 170	92.86 209	96.13 257	92.15 130	99.30 149	91.88 221	93.64 211	99.55 133

HyFIR lowres test		96.66 112	96.43 104	97.36 156	99.05 106	93.91 196	99.70 148	99.80 3	90.54 234	96.26 161	98.08 195	92.15 130	98.23 217	96.84 140	95.46 193	99.93 71

CS-MVS-test		97.88 61	97.94 57	97.70 139	99.28 99	95.20 168	99.98 9	97.15 265	95.53 73	99.62 39	99.79 54	92.08 132	98.38 202	98.75 69	99.28 108	99.52 140

MVS_111021_LR		98.42 38	98.38 29	98.53 99	99.39 94	95.79 144	99.87 88	99.86 2	96.70 42	98.78 88	99.79 54	92.03 133	99.90 79	99.17 45	99.86 70	99.88 80

TAPA-MVS	92.12 8	94.42 175	93.60 181	96.90 167	99.33 97	91.78 247	99.78 124	98.00 184	89.89 246	94.52 186	99.47 103	91.97 134	99.18 154	69.90 354	99.52 96	99.73 99
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PatchT		90.38 264	88.75 279	95.25 213	95.99 252	90.16 278	91.22 361	97.54 227	76.80 348	97.26 136	86.01 360	91.88 135	96.07 321	66.16 361	95.91 184	99.51 142

HPM-MVS		97.96 57	97.72 64	98.68 83	99.84 56	96.39 124	99.90 76	98.17 169	92.61 176	98.62 98	99.57 96	91.87 136	99.67 131	98.87 62	99.99 21	99.99 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MP-MVS		98.23 51	97.97 53	99.03 64	99.94 13	97.17 100	99.95 43	98.39 135	94.70 95	98.26 115	99.81 50	91.84 137	100.00 1	98.85 63	99.97 42	99.93 71
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		97.80 68	97.50 70	98.68 83	99.79 62	96.42 121	99.88 85	98.16 173	91.75 206	98.94 82	99.54 99	91.82 138	99.65 133	97.62 120	99.99 21	99.99 23

tpmvs		94.28 181	93.57 183	96.40 183	98.55 139	91.50 257	95.70 344	98.55 84	87.47 283	92.15 214	94.26 320	91.42 139	98.95 163	88.15 271	95.85 185	98.76 198

ACMMP		97.74 72	97.44 72	98.66 85	99.92 31	96.13 136	99.18 220	99.45 18	94.84 90	96.41 158	99.71 78	91.40 140	99.99 36	97.99 104	98.03 143	99.87 82
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
Vis-MVSNet (Re-imp)		96.32 123	95.98 115	97.35 157	97.93 173	94.82 176	99.47 186	98.15 175	91.83 202	95.09 181	99.11 131	91.37 141	97.47 248	93.47 200	97.43 152	99.74 98

sss		97.57 75	97.03 87	99.18 46	98.37 149	98.04 65	99.73 143	99.38 22	93.46 146	98.76 91	99.06 134	91.21 142	99.89 83	96.33 144	97.01 165	99.62 118

pcd_1.5k_mvsjas		7.60 348	10.13 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 381	91.20 143	0.00 381	0.00 379	0.00 379	0.00 377

PS-MVSNAJss		93.64 196	93.31 193	94.61 234	92.11 329	92.19 236	99.12 223	97.38 244	92.51 184	88.45 271	96.99 230	91.20 143	97.29 260	94.36 180	87.71 255	94.36 248

PS-MVSNAJ		98.44 37	98.20 40	99.16 51	98.80 128	98.92 26	99.54 175	98.17 169	97.34 19	99.85 7	99.85 30	91.20 143	99.89 83	99.41 39	99.67 85	98.69 201

CPTT-MVS		97.64 74	97.32 77	98.58 92	99.97 3	95.77 145	99.96 26	98.35 145	89.90 245	98.36 109	99.79 54	91.18 146	99.99 36	98.37 86	99.99 21	99.99 23

CR-MVSNet		93.45 201	92.62 204	95.94 194	96.29 243	92.66 226	92.01 357	96.23 323	92.62 175	96.94 141	93.31 329	91.04 147	96.03 322	79.23 330	95.96 182	99.13 183

Patchmtry		89.70 279	88.49 282	93.33 281	96.24 246	89.94 286	91.37 360	96.23 323	78.22 346	87.69 282	93.31 329	91.04 147	96.03 322	80.18 329	82.10 293	94.02 279

miper_ehance_all_eth		93.16 204	92.60 205	94.82 228	97.57 197	93.56 203	99.50 181	97.07 274	88.75 265	88.85 266	95.52 276	90.97 149	96.74 293	90.77 239	84.45 279	94.17 262

mvsany_test1		97.82 66	97.90 60	97.55 143	98.77 130	93.04 217	99.80 121	97.93 192	96.95 33	99.61 45	99.68 86	90.92 150	99.83 104	99.18 44	98.29 134	99.80 90

MVSFormer		96.94 97	96.60 98	97.95 125	97.28 214	97.70 77	99.55 173	97.27 255	91.17 221	99.43 57	99.54 99	90.92 150	96.89 286	94.67 175	99.62 88	99.25 174

lupinMVS		97.85 63	97.60 68	98.62 87	97.28 214	97.70 77	99.99 3	97.55 225	95.50 75	99.43 57	99.67 87	90.92 150	98.71 176	98.40 84	99.62 88	99.45 150

h-mvs33		94.92 160	94.36 163	96.59 177	98.85 125	91.29 259	98.93 249	98.94 37	95.90 62	98.77 89	98.42 189	90.89 153	99.77 114	97.80 111	70.76 347	98.72 200

hse-mvs2		94.38 176	94.08 170	95.31 211	98.27 155	90.02 282	99.29 211	98.56 78	95.90 62	98.77 89	98.00 198	90.89 153	98.26 216	97.80 111	69.20 353	97.64 216

xiu_mvs_v2_base		98.23 51	97.97 53	99.02 66	98.69 133	98.66 47	99.52 177	98.08 180	97.05 29	99.86 5	99.86 26	90.65 155	99.71 124	99.39 40	98.63 124	98.69 201

IS-MVSNet		96.29 126	95.90 126	97.45 148	98.13 165	94.80 177	99.08 228	97.61 219	92.02 198	95.54 176	98.96 147	90.64 156	98.08 223	93.73 197	97.41 155	99.47 147

FA-MVS(test-final)		95.86 136	95.09 149	98.15 119	97.74 185	95.62 153	96.31 333	98.17 169	91.42 217	96.26 161	96.13 257	90.56 157	99.47 146	92.18 217	97.07 161	99.35 162

cl22		93.77 191	93.25 195	95.33 210	99.49 90	94.43 183	99.61 164	98.09 178	90.38 236	89.16 261	95.61 270	90.56 157	97.34 252	91.93 219	84.45 279	94.21 260

tpm		93.70 195	93.41 190	94.58 237	95.36 274	87.41 312	97.01 322	96.90 294	90.85 230	96.72 149	94.14 321	90.40 159	96.84 289	90.75 240	88.54 241	99.51 142

114514_t		97.41 83	96.83 91	99.14 55	99.51 89	97.83 72	99.89 83	98.27 159	88.48 271	99.06 77	99.66 89	90.30 160	99.64 134	96.32 145	99.97 42	99.96 61

ADS-MVSNet2		93.80 190	93.88 175	93.55 279	97.87 176	85.94 321	94.24 346	96.84 299	90.07 242	96.43 156	94.48 316	90.29 161	95.37 331	87.44 278	97.23 157	99.36 160

ADS-MVSNet		94.79 162	94.02 171	97.11 163	97.87 176	93.79 197	94.24 346	98.16 173	90.07 242	96.43 156	94.48 316	90.29 161	98.19 219	87.44 278	97.23 157	99.36 160

miper_lstm_enhance		91.81 233	91.39 232	93.06 289	97.34 208	89.18 293	99.38 197	96.79 304	86.70 296	87.47 287	95.22 294	90.00 163	95.86 326	88.26 269	81.37 299	94.15 268

c3_l		92.53 220	91.87 222	94.52 240	97.40 205	92.99 218	99.40 192	96.93 292	87.86 279	88.69 269	95.44 280	89.95 164	96.44 304	90.45 245	80.69 309	94.14 271

thres200		96.96 96	96.21 108	99.22 42	98.97 113	98.84 33	99.85 103	99.71 6	93.17 155	96.26 161	98.88 158	89.87 165	99.51 138	94.26 183	94.91 199	99.31 167

tpm cat1		93.51 198	92.52 210	96.47 178	97.77 183	91.47 258	96.13 336	98.06 181	80.98 339	92.91 207	93.78 324	89.66 166	98.87 164	87.03 286	96.39 175	99.09 185

OMC-MVS		97.28 86	97.23 79	97.41 151	99.76 66	93.36 212	99.65 156	97.95 190	96.03 61	97.41 134	99.70 80	89.61 167	99.51 138	96.73 141	98.25 135	99.38 157

DIV-MVS_self_test		92.32 224	91.60 225	94.47 244	97.31 211	92.74 222	99.58 167	96.75 306	86.99 292	87.64 283	95.54 274	89.55 168	96.50 302	88.58 265	82.44 291	94.17 262

cl____		92.31 225	91.58 226	94.52 240	97.33 210	92.77 220	99.57 169	96.78 305	86.97 293	87.56 285	95.51 277	89.43 169	96.62 298	88.60 264	82.44 291	94.16 267

AUN-MVS		93.28 202	92.60 205	95.34 209	98.29 152	90.09 280	99.31 206	98.56 78	91.80 205	96.35 160	98.00 198	89.38 170	98.28 212	92.46 213	69.22 352	97.64 216

tfpn200view9		96.79 103	95.99 113	99.19 45	98.94 115	98.82 34	99.78 124	99.71 6	92.86 160	96.02 166	98.87 161	89.33 171	99.50 140	93.84 189	94.57 200	99.27 172

thres400		96.78 104	95.99 113	99.16 51	98.94 115	98.82 34	99.78 124	99.71 6	92.86 160	96.02 166	98.87 161	89.33 171	99.50 140	93.84 189	94.57 200	99.16 179

thres100view900		96.74 107	95.92 125	99.18 46	98.90 122	98.77 38	99.74 138	99.71 6	92.59 178	95.84 169	98.86 163	89.25 173	99.50 140	93.84 189	94.57 200	99.27 172

thres600view7		96.69 110	95.87 128	99.14 55	98.90 122	98.78 37	99.74 138	99.71 6	92.59 178	95.84 169	98.86 163	89.25 173	99.50 140	93.44 201	94.50 203	99.16 179

eth_miper_zixun_eth		92.41 223	91.93 220	93.84 269	97.28 214	90.68 267	98.83 261	96.97 286	88.57 270	89.19 260	95.73 267	89.24 175	96.69 296	89.97 254	81.55 297	94.15 268

DROMVSNet		97.38 85	97.24 78	97.80 130	97.41 204	95.64 152	99.99 3	97.06 275	94.59 98	99.63 37	99.32 115	89.20 176	98.14 220	98.76 68	99.23 110	99.62 118

PVSNet_Blended_VisFu		97.27 87	96.81 92	98.66 85	98.81 127	96.67 114	99.92 67	98.64 66	94.51 100	96.38 159	98.49 182	89.05 177	99.88 89	97.10 131	98.34 129	99.43 153

PVSNet_BlendedMVS		96.05 131	95.82 129	96.72 173	99.59 81	96.99 105	99.95 43	99.10 29	94.06 124	98.27 113	95.80 263	89.00 178	99.95 61	99.12 46	87.53 258	93.24 316

PVSNet_Blended		97.94 58	97.64 66	98.83 77	99.59 81	96.99 105	100.00 1	99.10 29	95.38 76	98.27 113	99.08 133	89.00 178	99.95 61	99.12 46	99.25 109	99.57 131

IterMVS-LS		92.69 217	92.11 215	94.43 248	96.80 234	92.74 222	99.45 189	96.89 295	88.98 257	89.65 246	95.38 285	88.77 180	96.34 308	90.98 234	82.04 294	94.22 258
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		93.73 193	93.40 191	94.74 229	96.80 234	92.69 225	99.06 233	97.67 212	88.96 259	91.39 219	99.02 136	88.75 181	97.30 257	91.07 230	87.85 252	94.22 258

UA-Net		96.54 114	95.96 119	98.27 113	98.23 157	95.71 149	98.00 305	98.45 102	93.72 140	98.41 106	99.27 119	88.71 182	99.66 132	91.19 228	97.69 147	99.44 152

MAR-MVS		97.43 78	97.19 80	98.15 119	99.47 91	94.79 178	99.05 237	98.76 53	92.65 174	98.66 96	99.82 46	88.52 183	99.98 42	98.12 96	99.63 87	99.67 107
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
mvs_anonymous		95.65 146	95.03 151	97.53 144	98.19 160	95.74 147	99.33 203	97.49 234	90.87 229	90.47 229	97.10 223	88.23 184	97.16 265	95.92 151	97.66 149	99.68 105

MVS_Test		96.46 117	95.74 130	98.61 88	98.18 161	97.23 95	99.31 206	97.15 265	91.07 225	98.84 85	97.05 227	88.17 185	98.97 161	94.39 179	97.50 151	99.61 121

CANet		98.27 46	97.82 62	99.63 15	99.72 74	99.10 21	99.98 9	98.51 93	97.00 31	98.52 101	99.71 78	87.80 186	99.95 61	99.75 24	99.38 104	99.83 86

jason		97.24 88	96.86 90	98.38 110	95.73 263	97.32 93	99.97 19	97.40 243	95.34 78	98.60 100	99.54 99	87.70 187	98.56 183	97.94 107	99.47 99	99.25 174
jason: jason.
FIs		94.10 183	93.43 187	96.11 191	94.70 283	96.82 111	99.58 167	98.93 41	92.54 181	89.34 253	97.31 217	87.62 188	97.10 271	94.22 185	86.58 263	94.40 244

1314		96.84 101	95.96 119	99.48 32	96.74 238	98.52 54	98.31 292	98.86 47	95.82 64	89.91 237	98.98 143	87.49 189	99.96 54	97.80 111	99.73 82	99.96 61

LS3D		95.84 138	95.11 148	98.02 124	99.85 54	95.10 170	98.74 268	98.50 97	87.22 288	93.66 198	99.86 26	87.45 190	99.95 61	90.94 235	99.81 78	99.02 187

FC-MVSNet-test		93.81 189	93.15 196	95.80 199	94.30 290	96.20 133	99.42 191	98.89 43	92.33 189	89.03 263	97.27 219	87.39 191	96.83 290	93.20 203	86.48 264	94.36 248

RPMNet		89.76 278	87.28 294	97.19 160	96.29 243	92.66 226	92.01 357	98.31 152	70.19 362	96.94 141	85.87 361	87.25 192	99.78 111	62.69 364	95.96 182	99.13 183

UniMVSNet_NR-MVSNet		92.95 210	92.11 215	95.49 202	94.61 285	95.28 163	99.83 113	99.08 31	91.49 211	89.21 258	96.86 234	87.14 193	96.73 294	93.20 203	77.52 328	94.46 237

UniMVSNet (Re)		93.07 208	92.13 214	95.88 195	94.84 280	96.24 132	99.88 85	98.98 35	92.49 185	89.25 255	95.40 282	87.09 194	97.14 267	93.13 207	78.16 323	94.26 255

DP-MVS		94.54 171	93.42 188	97.91 128	99.46 93	94.04 191	98.93 249	97.48 235	81.15 338	90.04 234	99.55 97	87.02 195	99.95 61	88.97 261	98.11 139	99.73 99

PMMVS		96.76 105	96.76 94	96.76 171	98.28 154	92.10 238	99.91 71	97.98 187	94.12 119	99.53 49	99.39 111	86.93 196	98.73 173	96.95 137	97.73 146	99.45 150

canonicalmvs		97.09 94	96.32 106	99.39 38	98.93 117	98.95 25	99.72 146	97.35 246	94.45 101	97.88 124	99.42 107	86.71 197	99.52 137	98.48 82	93.97 209	99.72 101

MVS		96.60 113	95.56 135	99.72 12	96.85 231	99.22 19	98.31 292	98.94 37	91.57 209	90.90 225	99.61 93	86.66 198	99.96 54	97.36 123	99.88 68	99.99 23

Effi-MVS+		96.30 125	95.69 131	98.16 116	97.85 178	96.26 128	97.41 313	97.21 258	90.37 237	98.65 97	98.58 178	86.61 199	98.70 177	97.11 130	97.37 156	99.52 140

diffmvs		97.00 95	96.64 97	98.09 121	97.64 194	96.17 135	99.81 117	97.19 259	94.67 97	98.95 81	99.28 116	86.43 200	98.76 171	98.37 86	97.42 154	99.33 165
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
nrg030		93.51 198	92.53 209	96.45 180	94.36 288	97.20 96	99.81 117	97.16 264	91.60 208	89.86 239	97.46 212	86.37 201	97.68 241	95.88 152	80.31 312	94.46 237

mvsmamba		94.10 183	93.72 178	95.25 213	93.57 301	94.13 189	99.67 153	96.45 319	93.63 143	91.34 221	97.77 206	86.29 202	97.22 263	96.65 142	88.10 249	94.40 244

VNet		97.21 90	96.57 100	99.13 59	98.97 113	97.82 73	99.03 240	99.21 28	94.31 111	99.18 74	98.88 158	86.26 203	99.89 83	98.93 56	94.32 204	99.69 104

AdaColmap		97.23 89	96.80 93	98.51 100	99.99 1	95.60 154	99.09 226	98.84 49	93.32 150	96.74 148	99.72 76	86.04 204	100.00 1	98.01 102	99.43 103	99.94 70

Effi-MVS+-dtu		94.53 173	95.30 142	92.22 297	97.77 183	82.54 337	99.59 166	97.06 275	94.92 87	95.29 179	95.37 286	85.81 205	97.89 235	94.80 170	97.07 161	96.23 227

CVMVSNet		94.68 168	94.94 154	93.89 268	96.80 234	86.92 316	99.06 233	98.98 35	94.45 101	94.23 192	99.02 136	85.60 206	95.31 333	90.91 236	95.39 195	99.43 153

xiu_mvs_v1_base_debu		97.43 78	97.06 83	98.55 94	97.74 185	98.14 60	99.31 206	97.86 201	96.43 49	99.62 39	99.69 82	85.56 207	99.68 128	99.05 48	98.31 131	97.83 211

xiu_mvs_v1_base		97.43 78	97.06 83	98.55 94	97.74 185	98.14 60	99.31 206	97.86 201	96.43 49	99.62 39	99.69 82	85.56 207	99.68 128	99.05 48	98.31 131	97.83 211

xiu_mvs_v1_base_debi		97.43 78	97.06 83	98.55 94	97.74 185	98.14 60	99.31 206	97.86 201	96.43 49	99.62 39	99.69 82	85.56 207	99.68 128	99.05 48	98.31 131	97.83 211

casdiffmvs_mvg		96.43 118	95.94 122	97.89 129	97.44 203	95.47 156	99.86 100	97.29 253	93.35 148	96.03 165	99.19 127	85.39 210	98.72 175	97.89 110	97.04 163	99.49 146
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		96.43 118	95.98 115	97.76 136	97.34 208	95.17 169	99.51 179	97.17 262	93.92 133	96.90 143	99.28 116	85.37 211	98.64 180	97.50 121	96.86 169	99.46 148

PCF-MVS	94.20 5	95.18 154	94.10 169	98.43 106	98.55 139	95.99 139	97.91 307	97.31 251	90.35 238	89.48 250	99.22 125	85.19 212	99.89 83	90.40 248	98.47 127	99.41 155
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		96.42 120	95.97 118	97.77 135	97.30 212	94.98 171	99.84 107	97.09 272	93.75 139	96.58 152	99.26 122	85.07 213	98.78 169	97.77 116	97.04 163	99.54 136
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
D2MVS		92.76 213	92.59 208	93.27 283	95.13 275	89.54 290	99.69 149	99.38 22	92.26 190	87.59 284	94.61 313	85.05 214	97.79 237	91.59 224	88.01 250	92.47 329

BH-w/o		95.71 142	95.38 139	96.68 174	98.49 144	92.28 234	99.84 107	97.50 233	92.12 193	92.06 215	98.79 167	84.69 215	98.67 179	95.29 158	99.66 86	99.09 185

Fast-Effi-MVS+		95.02 158	94.19 167	97.52 145	97.88 175	94.55 181	99.97 19	97.08 273	88.85 264	94.47 188	97.96 203	84.59 216	98.41 194	89.84 255	97.10 160	99.59 124

PVSNet	91.05 13	97.13 91	96.69 96	98.45 104	99.52 87	95.81 143	99.95 43	99.65 11	94.73 93	99.04 78	99.21 126	84.48 217	99.95 61	94.92 165	98.74 122	99.58 130

RRT_MVS		93.14 205	92.92 199	93.78 270	93.31 308	90.04 281	99.66 154	97.69 210	92.53 182	88.91 265	97.76 207	84.36 218	96.93 284	95.10 160	86.99 261	94.37 247

WR-MVS_H		91.30 242	90.35 245	94.15 254	94.17 292	92.62 229	99.17 221	98.94 37	88.87 263	86.48 301	94.46 318	84.36 218	96.61 299	88.19 270	78.51 321	93.21 317

CHOSEN 1792x2688		96.81 102	96.53 101	97.64 140	98.91 121	93.07 214	99.65 156	99.80 3	95.64 69	95.39 177	98.86 163	84.35 220	99.90 79	96.98 135	99.16 112	99.95 68

our_test_3		90.39 263	89.48 267	93.12 286	92.40 326	89.57 289	99.33 203	96.35 322	87.84 280	85.30 311	94.99 302	84.14 221	96.09 320	80.38 326	84.56 278	93.71 306

MSDG		94.37 177	93.36 192	97.40 152	98.88 124	93.95 195	99.37 199	97.38 244	85.75 308	90.80 226	99.17 129	84.11 222	99.88 89	86.35 291	98.43 128	98.36 203

pmmvs4		92.10 229	91.07 236	95.18 215	92.82 321	94.96 172	99.48 185	96.83 300	87.45 284	88.66 270	96.56 246	83.78 223	96.83 290	89.29 258	84.77 277	93.75 301

BH-untuned		95.18 154	94.83 156	96.22 189	98.36 150	91.22 260	99.80 121	97.32 250	90.91 228	91.08 222	98.67 171	83.51 224	98.54 185	94.23 184	99.61 91	98.92 189

LCM-MVSNet-Re		92.31 225	92.60 205	91.43 305	97.53 198	79.27 354	99.02 241	91.83 366	92.07 194	80.31 334	94.38 319	83.50 225	95.48 329	97.22 128	97.58 150	99.54 136

cdsmvs_eth3d_5k		23.43 345	31.24 348	0.00 362	0.00 385	0.00 386	0.00 373	98.09 178	0.00 380	0.00 381	99.67 87	83.37 226	0.00 381	0.00 379	0.00 379	0.00 377

DeepC-MVS	94.51 4	96.92 99	96.40 105	98.45 104	99.16 102	95.90 141	99.66 154	98.06 181	96.37 55	94.37 189	99.49 102	83.29 227	99.90 79	97.63 119	99.61 91	99.55 133
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NR-MVSNet		91.56 241	90.22 249	95.60 200	94.05 293	95.76 146	98.25 294	98.70 57	91.16 223	80.78 333	96.64 242	83.23 228	96.57 300	91.41 225	77.73 327	94.46 237

3Dnovator+	91.53 11	96.31 124	95.24 143	99.52 26	96.88 230	98.64 50	99.72 146	98.24 161	95.27 80	88.42 276	98.98 143	82.76 229	99.94 69	97.10 131	99.83 72	99.96 61

QAPM		95.40 151	94.17 168	99.10 60	96.92 225	97.71 75	99.40 192	98.68 60	89.31 250	88.94 264	98.89 157	82.48 230	99.96 54	93.12 208	99.83 72	99.62 118

PatchMatch-RL		96.04 132	95.40 137	97.95 125	99.59 81	95.22 167	99.52 177	99.07 32	93.96 130	96.49 154	98.35 190	82.28 231	99.82 106	90.15 251	99.22 111	98.81 196

GeoE		94.36 179	93.48 186	96.99 164	97.29 213	93.54 204	99.96 26	96.72 308	88.35 274	93.43 199	98.94 154	82.05 232	98.05 226	88.12 273	96.48 174	99.37 159

3Dnovator	91.47 12	96.28 127	95.34 140	99.08 61	96.82 233	97.47 89	99.45 189	98.81 50	95.52 74	89.39 251	99.00 140	81.97 233	99.95 61	97.27 125	99.83 72	99.84 85

v8		90.54 261	89.17 270	94.66 232	93.43 305	93.40 210	99.20 218	96.94 291	85.76 306	87.56 285	94.51 314	81.96 234	97.19 264	84.94 301	78.25 322	93.38 313

v148		90.70 256	89.63 260	93.92 265	92.97 317	90.97 262	99.75 135	96.89 295	87.51 282	88.27 277	95.01 299	81.67 235	97.04 276	87.40 280	77.17 333	93.75 301

DU-MVS		92.46 222	91.45 231	95.49 202	94.05 293	95.28 163	99.81 117	98.74 54	92.25 191	89.21 258	96.64 242	81.66 236	96.73 294	93.20 203	77.52 328	94.46 237

Baseline_NR-MVSNet		90.33 266	89.51 265	92.81 292	92.84 319	89.95 284	99.77 127	93.94 357	84.69 321	89.04 262	95.66 269	81.66 236	96.52 301	90.99 233	76.98 334	91.97 335

FMVSNet3		92.69 217	91.58 226	95.99 193	98.29 152	97.42 91	99.26 214	97.62 216	89.80 247	89.68 243	95.32 288	81.62 238	96.27 312	87.01 287	85.65 268	94.29 254

Fast-Effi-MVS+-dtu		93.72 194	93.86 176	93.29 282	97.06 219	86.16 319	99.80 121	96.83 300	92.66 173	92.58 212	97.83 205	81.39 239	97.67 242	89.75 256	96.87 168	96.05 229

CANet_DTU		96.76 105	96.15 109	98.60 89	98.78 129	97.53 82	99.84 107	97.63 214	97.25 26	99.20 71	99.64 91	81.36 240	99.98 42	92.77 212	98.89 118	98.28 204

V42		91.28 244	90.12 254	94.74 229	93.42 306	93.46 206	99.68 151	97.02 279	87.36 285	89.85 241	95.05 297	81.31 241	97.34 252	87.34 281	80.07 314	93.40 311

test_djsdf		92.83 212	92.29 213	94.47 244	91.90 332	92.46 231	99.55 173	97.27 255	91.17 221	89.96 235	96.07 260	81.10 242	96.89 286	94.67 175	88.91 231	94.05 278

ppachtmachnet_test		89.58 281	88.35 284	93.25 284	92.40 326	90.44 274	99.33 203	96.73 307	85.49 312	85.90 309	95.77 264	81.09 243	96.00 324	76.00 345	82.49 290	93.30 314

v1144		91.09 248	89.83 256	94.87 224	93.25 309	93.69 201	99.62 163	96.98 284	86.83 295	89.64 247	94.99 302	80.94 244	97.05 274	85.08 300	81.16 301	93.87 294

v10		90.25 269	88.82 277	94.57 238	93.53 303	93.43 208	99.08 228	96.87 297	85.00 316	87.34 291	94.51 314	80.93 245	97.02 281	82.85 314	79.23 317	93.26 315

EU-MVSNet		90.14 273	90.34 246	89.54 320	92.55 324	81.06 348	98.69 273	98.04 183	91.41 218	86.59 298	96.84 237	80.83 246	93.31 353	86.20 292	81.91 295	94.26 255

v2v482		91.30 242	90.07 255	95.01 219	93.13 310	93.79 197	99.77 127	97.02 279	88.05 277	89.25 255	95.37 286	80.73 247	97.15 266	87.28 282	80.04 315	94.09 275

WR-MVS		92.31 225	91.25 233	95.48 205	94.45 287	95.29 162	99.60 165	98.68 60	90.10 241	88.07 279	96.89 232	80.68 248	96.80 292	93.14 206	79.67 316	94.36 248

HQP2-MVS												80.65 249

HQP-MVS		94.61 170	94.50 161	94.92 223	95.78 257	91.85 244	99.87 88	97.89 197	96.82 36	93.37 200	98.65 172	80.65 249	98.39 198	97.92 108	89.60 222	94.53 231

XVG-OURS		94.82 161	94.74 158	95.06 218	98.00 169	89.19 291	99.08 228	97.55 225	94.10 120	94.71 184	99.62 92	80.51 251	99.74 120	96.04 149	93.06 218	96.25 225

v144192		90.79 255	89.52 264	94.59 236	93.11 313	92.77 220	99.56 171	96.99 282	86.38 299	89.82 242	94.95 304	80.50 252	97.10 271	83.98 307	80.41 310	93.90 291

HQP_MVS		94.49 174	94.36 163	94.87 224	95.71 266	91.74 248	99.84 107	97.87 199	96.38 52	93.01 204	98.59 176	80.47 253	98.37 204	97.79 114	89.55 225	94.52 233

plane_prior6					95.76 261	91.72 251						80.47 253

v7n		89.65 280	88.29 286	93.72 272	92.22 328	90.56 271	99.07 232	97.10 270	85.42 314	86.73 295	94.72 307	80.06 255	97.13 268	81.14 323	78.12 324	93.49 309

TranMVSNet+NR-MVSNet		91.68 240	90.61 241	94.87 224	93.69 300	93.98 194	99.69 149	98.65 64	91.03 226	88.44 272	96.83 238	80.05 256	96.18 315	90.26 250	76.89 336	94.45 242

FMVSNet5		88.32 291	87.47 293	90.88 308	96.90 229	88.39 304	97.28 315	95.68 334	82.60 334	84.67 314	92.40 338	79.83 257	91.16 360	76.39 344	81.51 298	93.09 318

RPSCF		91.80 236	92.79 202	88.83 325	98.15 163	69.87 361	98.11 301	96.60 313	83.93 324	94.33 190	99.27 119	79.60 258	99.46 147	91.99 218	93.16 216	97.18 221

Vis-MVSNet		95.72 140	95.15 147	97.45 148	97.62 195	94.28 187	99.28 212	98.24 161	94.27 115	96.84 145	98.94 154	79.39 259	98.76 171	93.25 202	98.49 126	99.30 169
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v1192		90.62 260	89.25 269	94.72 231	93.13 310	93.07 214	99.50 181	97.02 279	86.33 300	89.56 249	95.01 299	79.22 260	97.09 273	82.34 317	81.16 301	94.01 281

CP-MVSNet		91.23 246	90.22 249	94.26 252	93.96 295	92.39 233	99.09 226	98.57 76	88.95 260	86.42 302	96.57 245	79.19 261	96.37 306	90.29 249	78.95 318	94.02 279

MDA-MVSNet_test_wron		85.51 305	83.32 312	92.10 299	90.96 341	88.58 301	99.20 218	96.52 316	79.70 343	57.12 368	92.69 334	79.11 262	93.86 348	77.10 341	77.46 330	93.86 295

YYNet1		85.50 306	83.33 311	92.00 300	90.89 342	88.38 305	99.22 217	96.55 315	79.60 344	57.26 367	92.72 332	79.09 263	93.78 349	77.25 340	77.37 331	93.84 296

XVG-OURS-SEG-HR		94.79 162	94.70 159	95.08 217	98.05 167	89.19 291	99.08 228	97.54 227	93.66 141	94.87 183	99.58 95	78.78 264	99.79 109	97.31 124	93.40 213	96.25 225

GA-MVS		93.83 187	92.84 200	96.80 169	95.73 263	93.57 202	99.88 85	97.24 257	92.57 180	92.92 206	96.66 240	78.73 265	97.67 242	87.75 276	94.06 208	99.17 178

OpenMVS	90.15 15	94.77 164	93.59 182	98.33 111	96.07 249	97.48 88	99.56 171	98.57 76	90.46 235	86.51 299	98.95 152	78.57 266	99.94 69	93.86 188	99.74 81	97.57 218

v1921920		90.46 262	89.12 271	94.50 242	92.96 318	92.46 231	99.49 183	96.98 284	86.10 302	89.61 248	95.30 289	78.55 267	97.03 279	82.17 318	80.89 308	94.01 281

MVP-Stereo		90.93 250	90.45 244	92.37 296	91.25 340	88.76 295	98.05 304	96.17 325	87.27 287	84.04 316	95.30 289	78.46 268	97.27 262	83.78 309	99.70 84	91.09 340
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
anonymousdsp		91.79 238	90.92 237	94.41 249	90.76 343	92.93 219	98.93 249	97.17 262	89.08 252	87.46 288	95.30 289	78.43 269	96.92 285	92.38 214	88.73 236	93.39 312

bld_raw_dy_0_64		92.74 214	92.03 218	94.87 224	93.09 314	93.46 206	99.12 223	95.41 340	92.84 163	90.44 230	97.54 210	78.08 270	97.04 276	93.94 187	87.77 254	94.11 273

v1240		90.20 270	88.79 278	94.44 246	93.05 316	92.27 235	99.38 197	96.92 293	85.89 304	89.36 252	94.87 306	77.89 271	97.03 279	80.66 325	81.08 304	94.01 281

CLD-MVS		94.06 185	93.90 174	94.55 239	96.02 251	90.69 266	99.98 9	97.72 208	96.62 46	91.05 224	98.85 166	77.21 272	98.47 187	98.11 97	89.51 227	94.48 235
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
N_pmnet		80.06 325	80.78 323	77.89 345	91.94 331	45.28 379	98.80 265	56.82 382	78.10 347	80.08 336	93.33 327	77.03 273	95.76 327	68.14 358	82.81 288	92.64 325

COLMAP_ROB	90.47 14	92.18 228	91.49 230	94.25 253	99.00 110	88.04 308	98.42 289	96.70 309	82.30 335	88.43 274	99.01 138	76.97 274	99.85 95	86.11 294	96.50 173	94.86 230
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
cascas		94.64 169	93.61 179	97.74 138	97.82 180	96.26 128	99.96 26	97.78 207	85.76 306	94.00 194	97.54 210	76.95 275	99.21 151	97.23 127	95.43 194	97.76 215

BH-RMVSNet		95.18 154	94.31 166	97.80 130	98.17 162	95.23 166	99.76 132	97.53 229	92.52 183	94.27 191	99.25 123	76.84 276	98.80 167	90.89 237	99.54 95	99.35 162

PEN-MVS		90.19 271	89.06 273	93.57 278	93.06 315	90.90 264	99.06 233	98.47 99	88.11 276	85.91 308	96.30 251	76.67 277	95.94 325	87.07 284	76.91 335	93.89 292

CL-MVSNet_self_test		84.50 312	83.15 314	88.53 329	86.00 358	81.79 343	98.82 262	97.35 246	85.12 315	83.62 320	90.91 345	76.66 278	91.40 359	69.53 355	60.36 365	92.40 330

IterMVS		90.91 251	90.17 252	93.12 286	96.78 237	90.42 275	98.89 252	97.05 277	89.03 254	86.49 300	95.42 281	76.59 279	95.02 335	87.22 283	84.09 282	93.93 289
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		90.85 254	90.16 253	92.93 290	96.72 239	89.96 283	98.89 252	96.99 282	88.95 260	86.63 297	95.67 268	76.48 280	95.00 336	87.04 285	84.04 285	93.84 296

SCA		94.69 166	93.81 177	97.33 158	97.10 217	94.44 182	98.86 258	98.32 150	93.30 151	96.17 164	95.59 272	76.48 280	97.95 232	91.06 231	97.43 152	99.59 124

ab-mvs		94.69 166	93.42 188	98.51 100	98.07 166	96.26 128	96.49 329	98.68 60	90.31 239	94.54 185	97.00 229	76.30 282	99.71 124	95.98 150	93.38 214	99.56 132

DTE-MVSNet		89.40 283	88.24 287	92.88 291	92.66 323	89.95 284	99.10 225	98.22 163	87.29 286	85.12 313	96.22 253	76.27 283	95.30 334	83.56 311	75.74 339	93.41 310

ACMM	91.95 10	92.88 211	92.52 210	93.98 264	95.75 262	89.08 294	99.77 127	97.52 231	93.00 158	89.95 236	97.99 200	76.17 284	98.46 190	93.63 199	88.87 233	94.39 246
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DSMNet-mixed		88.28 292	88.24 287	88.42 330	89.64 350	75.38 358	98.06 303	89.86 369	85.59 310	88.20 278	92.14 340	76.15 285	91.95 358	78.46 335	96.05 180	97.92 210

VPA-MVSNet		92.70 216	91.55 228	96.16 190	95.09 276	96.20 133	98.88 254	99.00 34	91.02 227	91.82 216	95.29 292	76.05 286	97.96 231	95.62 155	81.19 300	94.30 253

TR-MVS		94.54 171	93.56 184	97.49 147	97.96 171	94.34 186	98.71 271	97.51 232	90.30 240	94.51 187	98.69 170	75.56 287	98.77 170	92.82 211	95.99 181	99.35 162

PS-CasMVS		90.63 259	89.51 265	93.99 263	93.83 297	91.70 252	98.98 243	98.52 90	88.48 271	86.15 306	96.53 247	75.46 288	96.31 310	88.83 262	78.86 320	93.95 287

TransMVSNet (Re)		87.25 297	85.28 303	93.16 285	93.56 302	91.03 261	98.54 281	94.05 356	83.69 327	81.09 331	96.16 255	75.32 289	96.40 305	76.69 343	68.41 354	92.06 333

LPG-MVS_test		92.96 209	92.71 203	93.71 273	95.43 272	88.67 298	99.75 135	97.62 216	92.81 164	90.05 232	98.49 182	75.24 290	98.40 196	95.84 153	89.12 229	94.07 276

LGP-MVS_train				93.71 273	95.43 272	88.67 298		97.62 216	92.81 164	90.05 232	98.49 182	75.24 290	98.40 196	95.84 153	89.12 229	94.07 276

ECVR-MVS		95.66 145	95.05 150	97.51 146	98.66 135	93.71 200	98.85 260	98.45 102	94.93 85	96.86 144	98.96 147	75.22 292	99.20 152	95.34 156	98.15 136	99.64 113

test1111		95.57 147	94.98 153	97.37 154	98.56 137	93.37 211	98.86 258	98.45 102	94.95 84	96.63 150	98.95 152	75.21 293	99.11 157	95.02 162	98.14 138	99.64 113

OPM-MVS		93.21 203	92.80 201	94.44 246	93.12 312	90.85 265	99.77 127	97.61 219	96.19 59	91.56 218	98.65 172	75.16 294	98.47 187	93.78 195	89.39 228	93.99 284
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tfpnnormal		89.29 285	87.61 292	94.34 251	94.35 289	94.13 189	98.95 247	98.94 37	83.94 323	84.47 315	95.51 277	74.84 295	97.39 249	77.05 342	80.41 310	91.48 339

AllTest		92.48 221	91.64 224	95.00 220	99.01 108	88.43 302	98.94 248	96.82 302	86.50 297	88.71 267	98.47 186	74.73 296	99.88 89	85.39 297	96.18 177	96.71 223

TestCases				95.00 220	99.01 108	88.43 302		96.82 302	86.50 297	88.71 267	98.47 186	74.73 296	99.88 89	85.39 297	96.18 177	96.71 223

Anonymous20231206		86.32 300	85.42 302	89.02 324	89.11 352	80.53 352	99.05 237	95.28 343	85.43 313	82.82 322	93.92 322	74.40 298	93.44 352	66.99 359	81.83 296	93.08 319

XXY-MVS		91.82 232	90.46 242	95.88 195	93.91 296	95.40 160	98.87 257	97.69 210	88.63 269	87.87 281	97.08 224	74.38 299	97.89 235	91.66 223	84.07 283	94.35 251

ACMP	92.05 9	92.74 214	92.42 212	93.73 271	95.91 255	88.72 297	99.81 117	97.53 229	94.13 118	87.00 293	98.23 192	74.07 300	98.47 187	96.22 147	88.86 234	93.99 284
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	88.28 18	90.29 268	89.05 274	94.02 260	95.08 277	90.15 279	97.19 317	97.43 238	84.91 319	83.99 317	97.06 226	74.00 301	98.28 212	84.08 305	87.71 255	93.62 307
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
pm-mvs1		89.36 284	87.81 291	94.01 261	93.40 307	91.93 242	98.62 278	96.48 318	86.25 301	83.86 318	96.14 256	73.68 302	97.04 276	86.16 293	75.73 340	93.04 320

pmmvs5		90.17 272	89.09 272	93.40 280	92.10 330	89.77 287	99.74 138	95.58 337	85.88 305	87.24 292	95.74 265	73.41 303	96.48 303	88.54 266	83.56 286	93.95 287

OurMVSNet-221017-0		89.81 277	89.48 267	90.83 310	91.64 335	81.21 346	98.17 299	95.38 342	91.48 212	85.65 310	97.31 217	72.66 304	97.29 260	88.15 271	84.83 276	93.97 286

jajsoiax		91.92 231	91.18 234	94.15 254	91.35 338	90.95 263	99.00 242	97.42 240	92.61 176	87.38 289	97.08 224	72.46 305	97.36 250	94.53 178	88.77 235	94.13 272

UGNet		95.33 153	94.57 160	97.62 142	98.55 139	94.85 174	98.67 275	99.32 25	95.75 67	96.80 147	96.27 252	72.18 306	99.96 54	94.58 177	99.05 116	98.04 209
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
mvs_tets		91.81 233	91.08 235	94.00 262	91.63 336	90.58 270	98.67 275	97.43 238	92.43 186	87.37 290	97.05 227	71.76 307	97.32 256	94.75 172	88.68 237	94.11 273

SixPastTwentyTwo		88.73 289	88.01 290	90.88 308	91.85 333	82.24 339	98.22 297	95.18 347	88.97 258	82.26 324	96.89 232	71.75 308	96.67 297	84.00 306	82.98 287	93.72 305

test_fmvs1		95.35 152	95.68 133	94.36 250	98.99 111	84.98 327	99.96 26	96.65 311	97.60 12	99.73 28	98.96 147	71.58 309	99.93 75	98.31 89	99.37 105	98.17 205

GBi-Net		90.88 252	89.82 257	94.08 257	97.53 198	91.97 239	98.43 286	96.95 287	87.05 289	89.68 243	94.72 307	71.34 310	96.11 317	87.01 287	85.65 268	94.17 262

test1		90.88 252	89.82 257	94.08 257	97.53 198	91.97 239	98.43 286	96.95 287	87.05 289	89.68 243	94.72 307	71.34 310	96.11 317	87.01 287	85.65 268	94.17 262

FMVSNet2		91.02 249	89.56 262	95.41 207	97.53 198	95.74 147	98.98 243	97.41 242	87.05 289	88.43 274	95.00 301	71.34 310	96.24 314	85.12 299	85.21 273	94.25 257

PVSNet_0	88.03 19	91.80 236	90.27 248	96.38 185	98.27 155	90.46 273	99.94 58	99.61 12	93.99 128	86.26 305	97.39 216	71.13 313	99.89 83	98.77 67	67.05 357	98.79 197

Anonymous20231211		89.86 276	88.44 283	94.13 256	98.93 117	90.68 267	98.54 281	98.26 160	76.28 349	86.73 295	95.54 274	70.60 314	97.56 245	90.82 238	80.27 313	94.15 268

ITE_SJBPF				92.38 295	95.69 268	85.14 325		95.71 333	92.81 164	89.33 254	98.11 194	70.23 315	98.42 193	85.91 295	88.16 248	93.59 308

ACMH	89.72 17	90.64 258	89.63 260	93.66 277	95.64 269	88.64 300	98.55 279	97.45 236	89.03 254	81.62 328	97.61 209	69.75 316	98.41 194	89.37 257	87.62 257	93.92 290
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS-HIRNet		86.22 301	83.19 313	95.31 211	96.71 240	90.29 276	92.12 356	97.33 249	62.85 363	86.82 294	70.37 368	69.37 317	97.49 247	75.12 346	97.99 144	98.15 206

Anonymous202405211		93.10 207	91.99 219	96.40 183	99.10 104	89.65 288	98.88 254	97.93 192	83.71 326	94.00 194	98.75 169	68.79 318	99.88 89	95.08 161	91.71 220	99.68 105

test20.03		84.72 311	83.99 305	86.91 333	88.19 355	80.62 351	98.88 254	95.94 329	88.36 273	78.87 339	94.62 312	68.75 319	89.11 364	66.52 360	75.82 338	91.00 341

VPNet		91.81 233	90.46 242	95.85 197	94.74 282	95.54 155	98.98 243	98.59 73	92.14 192	90.77 227	97.44 213	68.73 320	97.54 246	94.89 168	77.89 325	94.46 237

K. test v3		88.05 293	87.24 295	90.47 313	91.82 334	82.23 340	98.96 246	97.42 240	89.05 253	76.93 348	95.60 271	68.49 321	95.42 330	85.87 296	81.01 306	93.75 301

ACMH+	89.98 16	90.35 265	89.54 263	92.78 293	95.99 252	86.12 320	98.81 263	97.18 261	89.38 249	83.14 321	97.76 207	68.42 322	98.43 192	89.11 260	86.05 266	93.78 300

MDA-MVSNet-bldmvs		84.09 314	81.52 320	91.81 303	91.32 339	88.00 309	98.67 275	95.92 330	80.22 341	55.60 369	93.32 328	68.29 323	93.60 351	73.76 347	76.61 337	93.82 298

MS-PatchMatch		90.65 257	90.30 247	91.71 304	94.22 291	85.50 324	98.24 295	97.70 209	88.67 267	86.42 302	96.37 250	67.82 324	98.03 227	83.62 310	99.62 88	91.60 337

KD-MVS_self_test		83.59 317	82.06 317	88.20 331	86.93 356	80.70 350	97.21 316	96.38 320	82.87 331	82.49 323	88.97 349	67.63 325	92.32 356	73.75 348	62.30 364	91.58 338

LFMVS		94.75 165	93.56 184	98.30 112	99.03 107	95.70 150	98.74 268	97.98 187	87.81 281	98.47 104	99.39 111	67.43 326	99.53 136	98.01 102	95.20 198	99.67 107

MIMVSNet		90.30 267	88.67 280	95.17 216	96.45 242	91.64 254	92.39 355	97.15 265	85.99 303	90.50 228	93.19 331	66.95 327	94.86 339	82.01 319	93.43 212	99.01 188

test_vis1_n_1920		95.44 150	95.31 141	95.82 198	98.50 143	88.74 296	99.98 9	97.30 252	97.84 8	99.85 7	99.19 127	66.82 328	99.97 51	98.82 64	99.46 101	98.76 198

XVG-ACMP-BASELINE		91.22 247	90.75 238	92.63 294	93.73 299	85.61 322	98.52 283	97.44 237	92.77 167	89.90 238	96.85 235	66.64 329	98.39 198	92.29 215	88.61 238	93.89 292

Anonymous20240529		92.10 229	90.65 240	96.47 178	98.82 126	90.61 269	98.72 270	98.67 63	75.54 353	93.90 196	98.58 178	66.23 330	99.90 79	94.70 174	90.67 221	98.90 192

lessismore_v0				90.53 311	90.58 344	80.90 349		95.80 331		77.01 347	95.84 262	66.15 331	96.95 282	83.03 313	75.05 341	93.74 304

USDC		90.00 275	88.96 275	93.10 288	94.81 281	88.16 306	98.71 271	95.54 338	93.66 141	83.75 319	97.20 220	65.58 332	98.31 209	83.96 308	87.49 259	92.85 323

pmmvs-eth3d		84.03 315	81.97 318	90.20 315	84.15 361	87.09 314	98.10 302	94.73 351	83.05 329	74.10 356	87.77 355	65.56 333	94.01 345	81.08 324	69.24 351	89.49 354

Anonymous20240521		85.15 308	83.81 309	89.16 323	88.32 353	82.69 335	98.80 265	95.74 332	79.72 342	81.53 329	90.99 343	65.38 334	94.16 344	72.69 349	81.11 303	90.63 345

LF4IMVS		89.25 287	88.85 276	90.45 314	92.81 322	81.19 347	98.12 300	94.79 349	91.44 214	86.29 304	97.11 222	65.30 335	98.11 222	88.53 267	85.25 272	92.07 332

new_pmnet		84.49 313	82.92 315	89.21 322	90.03 348	82.60 336	96.89 326	95.62 336	80.59 340	75.77 353	89.17 348	65.04 336	94.79 340	72.12 351	81.02 305	90.23 347

CMPMVS	61.59 21	84.75 310	85.14 304	83.57 339	90.32 346	62.54 366	96.98 323	97.59 223	74.33 357	69.95 360	96.66 240	64.17 337	98.32 208	87.88 275	88.41 243	89.84 351
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_0402		85.58 303	83.94 307	90.50 312	93.81 298	85.04 326	98.55 279	95.20 346	76.01 350	79.72 338	95.13 295	64.15 338	96.26 313	66.04 362	86.88 262	90.21 348

TDRefinement		84.76 309	82.56 316	91.38 306	74.58 372	84.80 329	97.36 314	94.56 353	84.73 320	80.21 335	96.12 259	63.56 339	98.39 198	87.92 274	63.97 361	90.95 343

UnsupCasMVSNet_eth		85.52 304	83.99 305	90.10 316	89.36 351	83.51 333	96.65 327	97.99 185	89.14 251	75.89 352	93.83 323	63.25 340	93.92 346	81.92 320	67.90 356	92.88 322

tt0805		91.28 244	90.18 251	94.60 235	96.26 245	87.55 310	98.39 290	98.72 55	89.00 256	89.22 257	98.47 186	62.98 341	98.96 162	90.57 242	88.00 251	97.28 220

new-patchmatchnet		81.19 320	79.34 327	86.76 334	82.86 364	80.36 353	97.92 306	95.27 344	82.09 336	72.02 357	86.87 357	62.81 342	90.74 362	71.10 352	63.08 362	89.19 357

TinyColmap		87.87 296	86.51 297	91.94 301	95.05 278	85.57 323	97.65 311	94.08 355	84.40 322	81.82 327	96.85 235	62.14 343	98.33 207	80.25 328	86.37 265	91.91 336

test_fmvs1_n		94.25 182	94.36 163	93.92 265	97.68 193	83.70 332	99.90 76	96.57 314	97.40 18	99.67 34	98.88 158	61.82 344	99.92 76	98.23 91	99.13 114	98.14 208

VDDNet		93.12 206	91.91 221	96.76 171	96.67 241	92.65 228	98.69 273	98.21 164	82.81 332	97.75 127	99.28 116	61.57 345	99.48 145	98.09 99	94.09 207	98.15 206

pmmvs6		85.69 302	83.84 308	91.26 307	90.00 349	84.41 330	97.82 308	96.15 326	75.86 351	81.29 330	95.39 284	61.21 346	96.87 288	83.52 312	73.29 343	92.50 328

VDD-MVS		93.77 191	92.94 198	96.27 188	98.55 139	90.22 277	98.77 267	97.79 206	90.85 230	96.82 146	99.42 107	61.18 347	99.77 114	98.95 54	94.13 206	98.82 195

testgi		89.01 288	88.04 289	91.90 302	93.49 304	84.89 328	99.73 143	95.66 335	93.89 136	85.14 312	98.17 193	59.68 348	94.66 341	77.73 338	88.88 232	96.16 228

FMVSNet1		88.50 290	86.64 296	94.08 257	95.62 271	91.97 239	98.43 286	96.95 287	83.00 330	86.08 307	94.72 307	59.09 349	96.11 317	81.82 321	84.07 283	94.17 262

DeepMVS_CX				82.92 341	95.98 254	58.66 371		96.01 328	92.72 168	78.34 342	95.51 277	58.29 350	98.08 223	82.57 315	85.29 271	92.03 334

UniMVSNet_ETH3D		90.06 274	88.58 281	94.49 243	94.67 284	88.09 307	97.81 309	97.57 224	83.91 325	88.44 272	97.41 214	57.44 351	97.62 244	91.41 225	88.59 240	97.77 214

pmmvs3		80.27 324	77.77 329	87.76 332	80.32 367	82.43 338	98.23 296	91.97 365	72.74 360	78.75 340	87.97 354	57.30 352	90.99 361	70.31 353	62.37 363	89.87 350

OpenMVS_ROB	79.82 20	83.77 316	81.68 319	90.03 317	88.30 354	82.82 334	98.46 284	95.22 345	73.92 358	76.00 351	91.29 342	55.00 353	96.94 283	68.40 357	88.51 242	90.34 346

test_fmvs2		89.47 282	89.70 259	88.77 328	94.54 286	75.74 356	99.83 113	94.70 352	94.71 94	91.08 222	96.82 239	54.46 354	97.78 239	92.87 210	88.27 246	92.80 324

tmp_tt		65.23 337	62.94 340	72.13 352	44.90 381	50.03 377	81.05 368	89.42 372	38.45 371	48.51 373	99.90 18	54.09 355	78.70 373	91.84 222	18.26 375	87.64 359

EGC-MVSNET		69.38 329	63.76 339	86.26 335	90.32 346	81.66 345	96.24 335	93.85 358	0.99 379	3.22 380	92.33 339	52.44 356	92.92 354	59.53 367	84.90 275	84.21 362

test_vis1_n		93.61 197	93.03 197	95.35 208	95.86 256	86.94 315	99.87 88	96.36 321	96.85 34	99.54 48	98.79 167	52.41 357	99.83 104	98.64 76	98.97 117	99.29 171

MIMVSNet1		82.58 318	80.51 324	88.78 326	86.68 357	84.20 331	96.65 327	95.41 340	78.75 345	78.59 341	92.44 335	51.88 358	89.76 363	65.26 363	78.95 318	92.38 331

EG-PatchMatch MVS		85.35 307	83.81 309	89.99 318	90.39 345	81.89 342	98.21 298	96.09 327	81.78 337	74.73 354	93.72 325	51.56 359	97.12 270	79.16 333	88.61 238	90.96 342

MVS_0304		89.28 286	88.31 285	92.21 298	97.05 220	86.53 318	97.76 310	99.57 13	85.58 311	93.86 197	92.71 333	51.04 360	96.30 311	84.49 303	92.72 219	93.79 299

UnsupCasMVSNet_bld		79.97 327	77.03 331	88.78 326	85.62 359	81.98 341	93.66 351	97.35 246	75.51 354	70.79 359	83.05 363	48.70 361	94.91 338	78.31 336	60.29 366	89.46 355

test_vis1_rt		86.87 299	86.05 300	89.34 321	96.12 247	78.07 355	99.87 88	83.54 376	92.03 197	78.21 343	89.51 347	45.80 362	99.91 77	96.25 146	93.11 217	90.03 349

test_method		80.79 322	79.70 326	84.08 338	92.83 320	67.06 363	99.51 179	95.42 339	54.34 367	81.07 332	93.53 326	44.48 363	92.22 357	78.90 334	77.23 332	92.94 321

APD_test1		81.15 321	80.92 322	81.86 342	92.45 325	59.76 370	96.04 339	93.61 360	73.29 359	77.06 346	96.64 242	44.28 364	96.16 316	72.35 350	82.52 289	89.67 352

mvsany_test3		82.12 319	81.14 321	85.06 337	81.87 365	70.41 360	97.09 320	92.14 364	91.27 220	77.84 344	88.73 350	39.31 365	95.49 328	90.75 240	71.24 346	89.29 356

PM-MVS		80.47 323	78.88 328	85.26 336	83.79 363	72.22 359	95.89 342	91.08 367	85.71 309	76.56 350	88.30 351	36.64 366	93.90 347	82.39 316	69.57 350	89.66 353

ambc				83.23 340	77.17 370	62.61 365	87.38 366	94.55 354		76.72 349	86.65 358	30.16 367	96.36 307	84.85 302	69.86 348	90.73 344

Gipuma		66.95 336	65.00 336	72.79 349	91.52 337	67.96 362	66.16 371	95.15 348	47.89 369	58.54 366	67.99 371	29.74 368	87.54 368	50.20 371	77.83 326	62.87 371
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EMVS		51.44 342	51.22 344	52.11 358	70.71 374	44.97 380	94.04 348	75.66 380	35.34 375	42.40 375	61.56 376	28.93 369	65.87 377	27.64 377	24.73 373	45.49 374

test_fmvs3		79.99 326	80.17 325	79.45 344	84.02 362	62.83 364	99.05 237	93.49 361	88.29 275	80.06 337	86.65 358	28.09 370	88.00 365	88.63 263	73.27 344	87.54 360

test_f		78.40 328	77.59 330	80.81 343	80.82 366	62.48 367	96.96 324	93.08 362	83.44 328	74.57 355	84.57 362	27.95 371	92.63 355	84.15 304	72.79 345	87.32 361

E-PMN		52.30 340	52.18 342	52.67 357	71.51 373	45.40 378	93.62 352	76.60 379	36.01 373	43.50 374	64.13 373	27.11 372	67.31 376	31.06 376	26.06 372	45.30 375

FPMVS		68.72 331	68.72 332	68.71 353	65.95 376	44.27 381	95.97 341	94.74 350	51.13 368	53.26 370	90.50 346	25.11 373	83.00 371	60.80 365	80.97 307	78.87 366

PMMVS2		67.15 335	64.15 338	76.14 347	70.56 375	62.07 368	93.89 349	87.52 373	58.09 364	60.02 363	78.32 365	22.38 374	84.54 370	59.56 366	47.03 370	81.80 363

testf1		68.38 332	66.92 333	72.78 350	78.80 368	50.36 375	90.95 362	87.35 374	55.47 365	58.95 364	88.14 352	20.64 375	87.60 366	57.28 368	64.69 359	80.39 364

APD_test2		68.38 332	66.92 333	72.78 350	78.80 368	50.36 375	90.95 362	87.35 374	55.47 365	58.95 364	88.14 352	20.64 375	87.60 366	57.28 368	64.69 359	80.39 364

LCM-MVSNet		67.77 334	64.73 337	76.87 346	62.95 378	56.25 373	89.37 365	93.74 359	44.53 370	61.99 362	80.74 364	20.42 377	86.53 369	69.37 356	59.50 367	87.84 358

test123		37.68 344	39.14 347	33.31 359	19.94 383	24.83 384	98.36 291	9.75 384	15.53 377	51.31 371	87.14 356	19.62 378	17.74 379	47.10 372	3.47 378	57.36 372

ANet_high		56.10 338	52.24 341	67.66 354	49.27 380	56.82 372	83.94 367	82.02 377	70.47 361	33.28 377	64.54 372	17.23 379	69.16 375	45.59 373	23.85 374	77.02 367

test_vis3_rt		68.82 330	66.69 335	75.21 348	76.24 371	60.41 369	96.44 330	68.71 381	75.13 355	50.54 372	69.52 370	16.42 380	96.32 309	80.27 327	66.92 358	68.89 368

testmvs		40.60 343	44.45 346	29.05 360	19.49 384	14.11 385	99.68 151	18.47 383	20.74 376	64.59 361	98.48 185	10.95 381	17.09 380	56.66 370	11.01 376	55.94 373

PMVS	49.05 23	53.75 339	51.34 343	60.97 356	40.80 382	34.68 382	74.82 370	89.62 371	37.55 372	28.67 378	72.12 367	7.09 382	81.63 372	43.17 374	68.21 355	66.59 370
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		20.37 346	20.84 349	18.99 361	65.34 377	27.73 383	50.43 372	7.67 385	9.50 378	8.01 379	6.34 379	6.13 383	26.24 378	23.40 378	10.69 377	2.99 376

MVE	53.74 22	51.54 341	47.86 345	62.60 355	59.56 379	50.93 374	79.41 369	77.69 378	35.69 374	36.27 376	61.76 375	5.79 384	69.63 374	37.97 375	36.61 371	67.24 369
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_blank		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.02 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet_test		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

DCPMVS		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet-low-res		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uncertanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

Regformer		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

ab-mvs-re		8.28 347	11.04 350	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	99.40 109	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

FOURS1					99.92 31	97.66 79	99.95 43	98.36 143	95.58 71	99.52 51

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 128					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 128					100.00 1	99.96 9	100.00 1	100.00 1

eth-test2					0.00 385

eth-test					0.00 385

IU-MVS					99.93 24	99.31 9		98.41 128	97.71 9	99.84 10				100.00 1	100.00 1	100.00 1

save fliter					99.82 58	98.79 36	99.96 26	98.40 132	97.66 11

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 43	98.43 113					100.00 1	99.99 5	100.00 1	100.00 1

GSMVS																99.59 124

test_part2					99.89 45	99.25 17				99.49 53

MTGPA								98.28 157

MTMP							99.87 88	96.49 317

gm-plane-assit					96.97 224	93.76 199			91.47 213		98.96 147		98.79 168	94.92 165

test9_res														99.71 29	99.99 21	100.00 1

agg_prior2														99.48 35	100.00 1	100.00 1

agg_prior					99.93 24	98.77 38		98.43 113		99.63 37			99.85 95

test_prior4						98.05 64	99.94 58

test_prior				99.43 33	99.94 13	98.49 56		98.65 64					99.80 107			99.99 23

旧先验2							99.46 188		94.21 116	99.85 7			99.95 61	96.96 136

新几何2							99.40 192

无先验							99.49 183	98.71 56	93.46 146				100.00 1	94.36 180		99.99 23

原ACMM2							99.90 76

testdata2													99.99 36	90.54 244

testdata1							99.28 212		96.35 56

plane_prior7					95.71 266	91.59 256

plane_prior5								97.87 199					98.37 204	97.79 114	89.55 225	94.52 233

plane_prior4											98.59 176

plane_prior3						91.64 254			96.63 44	93.01 204

plane_prior2							99.84 107		96.38 52

plane_prior1					95.73 263

plane_prior						91.74 248	99.86 100		96.76 40						89.59 224

n2								0.00 386

nn								0.00 386

door-mid								89.69 370

test11								98.44 105

door								90.31 368

HQP5-MVS						91.85 244

HQP-NCC					95.78 257		99.87 88		96.82 36	93.37 200

ACMP_Plane					95.78 257		99.87 88		96.82 36	93.37 200

BP-MVS														97.92 108

HQP4-MVS										93.37 200			98.39 198			94.53 231

HQP3-MVS								97.89 197							89.60 222

NP-MVS					95.77 260	91.79 246					98.65 172

ACMMP++_ref															87.04 260

ACMMP++															88.23 247

High-resolution multi-view benchmark