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.

test_fmvsm_n_1920		97.55 15	97.89 3	96.53 103	98.41 82	91.73 128	98.01 63	99.02 1	96.37 12	99.30 6	98.92 22	92.39 43	99.79 43	99.16 13	99.46 44	98.08 217

PGM-MVS		96.81 56	96.53 67	97.65 45	99.35 23	93.53 63	97.65 126	98.98 2	92.22 167	97.14 73	98.44 61	91.17 70	99.85 19	94.35 152	99.46 44	99.57 34

MVS_111021_HR		96.68 67	96.58 66	96.99 82	98.46 77	92.31 108	96.20 293	98.90 3	94.30 85	95.86 131	97.74 133	92.33 44	99.38 133	96.04 93	99.42 54	99.28 75

test_fmvsmconf_n		97.49 20	97.56 14	97.29 62	97.44 162	92.37 105	97.91 82	98.88 4	95.83 18	98.92 22	99.05 13	91.45 60	99.80 38	99.12 15	99.46 44	99.69 14

lecture		97.58 14	97.63 11	97.43 56	99.37 17	92.93 84	98.86 7	98.85 5	95.27 33	98.65 33	98.90 24	91.97 51	99.80 38	97.63 37	99.21 80	99.57 34

ACMMP		96.27 84	95.93 87	97.28 64	99.24 31	92.62 96	98.25 38	98.81 6	92.99 137	94.56 171	98.39 65	88.96 100	99.85 19	94.57 146	97.63 160	99.36 70
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
MVS_111021_LR		96.24 85	96.19 83	96.39 121	98.23 102	91.35 150	96.24 291	98.79 7	93.99 93	95.80 133	97.65 143	89.92 90	99.24 146	95.87 97	99.20 85	98.58 162

patch_mono-2		96.83 55	97.44 22	95.01 214	99.05 43	85.39 353	96.98 210	98.77 8	94.70 65	97.99 48	98.66 42	93.61 20	99.91 1	97.67 36	99.50 38	99.72 13

fmvsm_s_conf0.5_n		96.85 52	97.13 29	96.04 146	98.07 117	90.28 199	97.97 74	98.76 9	94.93 47	98.84 27	99.06 11	88.80 104	99.65 76	99.06 17	98.63 120	98.18 203

fmvsm_l_conf0.5_n		97.65 8	97.75 7	97.34 59	98.21 103	92.75 90	97.83 95	98.73 10	95.04 44	99.30 6	98.84 35	93.34 23	99.78 46	99.32 7	99.13 95	99.50 50

fmvsm_s_conf0.5_n_a		96.75 60	96.93 44	96.20 137	97.64 148	90.72 181	98.00 64	98.73 10	94.55 72	98.91 23	99.08 7	88.22 116	99.63 85	98.91 20	98.37 133	98.25 198

fmvsm_s_conf0.5_n_10		97.29 29	97.40 24	96.97 84	98.24 97	91.96 124	97.89 85	98.72 12	96.77 6	99.46 3	99.06 11	87.78 125	99.84 24	99.40 4	99.27 72	99.12 90

fmvsm_l_conf0.5_n_9		97.59 12	97.79 5	96.97 84	98.28 91	91.49 142	97.61 135	98.71 13	97.10 4	99.70 1	98.93 21	90.95 75	99.77 49	99.35 6	99.53 31	99.65 20

FC-MVSNet-test		93.94 173	93.57 165	95.04 212	95.48 305	91.45 147	98.12 53	98.71 13	93.37 119	90.23 285	96.70 211	87.66 127	97.85 336	91.49 216	90.39 325	95.83 311

UniMVSNet (Re)		93.31 200	92.55 213	95.61 182	95.39 311	93.34 69	97.39 169	98.71 13	93.14 132	90.10 294	94.83 313	87.71 126	98.03 309	91.67 214	83.99 399	95.46 330

TestfortrainingZip a		97.92 3	97.70 9	98.58 3	99.56 1	96.08 5	98.69 11	98.70 16	93.45 116	98.73 29	98.53 50	95.46 7	99.86 9	96.63 66	99.58 23	99.80 1

fmvsm_l_conf0.5_n_a		97.63 10	97.76 6	97.26 66	98.25 96	92.59 98	97.81 100	98.68 17	94.93 47	99.24 9	98.87 30	93.52 21	99.79 43	99.32 7	99.21 80	99.40 64

FIs		94.09 164	93.70 161	95.27 201	95.70 294	92.03 120	98.10 54	98.68 17	93.36 121	90.39 282	96.70 211	87.63 130	97.94 327	92.25 194	90.50 324	95.84 310

WR-MVS_H		92.00 257	91.35 254	93.95 282	95.09 338	89.47 231	98.04 61	98.68 17	91.46 197	88.34 345	94.68 320	85.86 164	97.56 365	85.77 340	84.24 397	94.82 375

fmvsm_s_conf0.5_n_4		96.75 60	97.07 32	95.79 169	97.76 139	89.57 225	97.66 125	98.66 20	95.36 29	99.03 15	98.90 24	88.39 112	99.73 58	99.17 12	98.66 118	98.08 217

VPA-MVSNet		93.24 202	92.48 218	95.51 188	95.70 294	92.39 104	97.86 88	98.66 20	92.30 164	92.09 243	95.37 288	80.49 280	98.40 263	93.95 158	85.86 370	95.75 319

fmvsm_l_conf0.5_n_3		97.64 9	97.60 12	97.79 32	98.14 110	93.94 54	97.93 80	98.65 22	96.70 7	99.38 4	99.07 10	89.92 90	99.81 33	99.16 13	99.43 51	99.61 28

fmvsm_s_conf0.5_n_3		97.15 34	97.36 26	96.52 105	97.98 123	91.19 158	97.84 92	98.65 22	97.08 5	99.25 8	99.10 5	87.88 123	99.79 43	99.32 7	99.18 87	98.59 161

fmvsm_s_conf0.5_n_8		97.32 27	97.48 21	96.85 86	98.28 91	91.07 166	97.76 105	98.62 24	97.53 2	99.20 11	99.12 4	88.24 115	99.81 33	99.41 3	99.17 88	99.67 15

fmvsm_s_conf0.5_n_2		96.62 68	96.82 53	96.02 148	97.98 123	90.43 191	97.50 150	98.59 25	96.59 9	99.31 5	99.08 7	84.47 194	99.75 55	99.37 5	98.45 130	97.88 230

UniMVSNet_NR-MVSNet		93.37 198	92.67 207	95.47 194	95.34 317	92.83 87	97.17 193	98.58 26	92.98 142	90.13 290	95.80 264	88.37 114	97.85 336	91.71 211	83.93 400	95.73 321

CSCG		96.05 88	95.91 88	96.46 115	99.24 31	90.47 188	98.30 31	98.57 27	89.01 291	93.97 192	97.57 153	92.62 39	99.76 51	94.66 140	99.27 72	99.15 85

fmvsm_s_conf0.5_n_9		97.33 26	97.57 13	96.62 99	98.43 80	90.32 198	97.80 101	98.53 28	97.24 3	99.62 2	99.14 1	88.65 107	99.80 38	99.54 1	99.15 92	99.74 9

fmvsm_s_conf0.5_n_6		97.08 37	97.17 28	96.81 87	97.28 167	91.73 128	97.75 107	98.50 29	94.86 51	99.22 10	98.78 39	89.75 93	99.76 51	99.10 16	99.29 70	98.94 116

MSLP-MVS++		96.94 46	97.06 33	96.59 100	98.72 62	91.86 126	97.67 122	98.49 30	94.66 68	97.24 69	98.41 64	92.31 46	98.94 192	96.61 68	99.46 44	98.96 112

HyFIR lowres test		93.66 185	92.92 195	95.87 159	98.24 97	89.88 214	94.58 369	98.49 30	85.06 388	93.78 195	95.78 268	82.86 229	98.67 237	91.77 209	95.71 223	99.07 98

CHOSEN 1792x2688		94.15 159	93.51 171	96.06 144	98.27 93	89.38 236	95.18 355	98.48 32	85.60 378	93.76 196	97.11 186	83.15 219	99.61 87	91.33 219	98.72 116	99.19 81

fmvsm_s_conf0.5_n_7		96.45 75	96.80 55	95.37 197	97.29 166	88.38 269	97.23 187	98.47 33	95.14 38	98.43 38	99.09 6	87.58 131	99.72 62	98.80 24	99.21 80	98.02 221

fmvsm_s_conf0.5_n_5		97.00 43	96.97 41	97.09 77	97.58 158	92.56 99	97.68 121	98.47 33	94.02 91	98.90 24	98.89 27	88.94 101	99.78 46	99.18 11	99.03 104	98.93 120

PHI-MVS		96.77 58	96.46 74	97.71 43	98.40 83	94.07 50	98.21 45	98.45 35	89.86 263	97.11 75	98.01 101	92.52 41	99.69 70	96.03 94	99.53 31	99.36 70

fmvsm_s_conf0.1_n		96.58 71	96.77 58	96.01 151	96.67 222	90.25 200	97.91 82	98.38 36	94.48 76	98.84 27	99.14 1	88.06 118	99.62 86	98.82 22	98.60 122	98.15 207

PVSNet_BlendedMVS		94.06 165	93.92 155	94.47 249	98.27 93	89.46 233	96.73 239	98.36 37	90.17 255	94.36 177	95.24 296	88.02 119	99.58 95	93.44 172	90.72 320	94.36 395

PVSNet_Blended		94.87 134	94.56 133	95.81 166	98.27 93	89.46 233	95.47 337	98.36 37	88.84 300	94.36 177	96.09 253	88.02 119	99.58 95	93.44 172	98.18 142	98.40 183

3Dnovator	91.36 5	95.19 121	94.44 142	97.44 55	96.56 232	93.36 68	98.65 14	98.36 37	94.12 88	89.25 324	98.06 95	82.20 246	99.77 49	93.41 174	99.32 68	99.18 82

FOURS1					99.55 2	93.34 69	99.29 1	98.35 40	94.98 45	98.49 36

DPE-MVS		97.86 5	97.65 10	98.47 6	99.17 36	95.78 8	97.21 190	98.35 40	95.16 37	98.71 32	98.80 37	95.05 11	99.89 3	96.70 65	99.73 1	99.73 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ME-MVS		97.54 16	97.39 25	98.00 23	99.21 34	94.50 35	97.75 107	98.34 42	94.23 86	98.15 43	98.53 50	93.32 26	99.84 24	97.40 49	99.58 23	99.65 20

fmvsm_s_conf0.1_n_a		96.40 77	96.47 71	96.16 139	95.48 305	90.69 182	97.91 82	98.33 43	94.07 89	98.93 19	99.14 1	87.44 138	99.61 87	98.63 25	98.32 135	98.18 203

HFP-MVS		97.14 35	96.92 45	97.83 28	99.42 8	94.12 48	98.52 18	98.32 44	93.21 124	97.18 70	98.29 81	92.08 48	99.83 29	95.63 110	99.59 19	99.54 43

ACMMPR		97.07 39	96.84 49	97.79 32	99.44 7	93.88 55	98.52 18	98.31 45	93.21 124	97.15 72	98.33 75	91.35 64	99.86 9	95.63 110	99.59 19	99.62 25

test_fmvsmvis_n_1920		96.70 63	96.84 49	96.31 126	96.62 224	91.73 128	97.98 68	98.30 46	96.19 13	96.10 121	98.95 19	89.42 94	99.76 51	98.90 21	99.08 99	97.43 257

APDe-MVS		97.82 6	97.73 8	98.08 19	99.15 37	94.82 29	98.81 8	98.30 46	94.76 63	98.30 40	98.90 24	93.77 18	99.68 72	97.93 28	99.69 3	99.75 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test0726					99.45 4	95.36 14	98.31 30	98.29 48	94.92 49	98.99 17	98.92 22	95.08 9

MSP-MVS		97.59 12	97.54 15	97.73 40	99.40 12	93.77 59	98.53 17	98.29 48	95.55 26	98.56 35	97.81 126	93.90 16	99.65 76	96.62 67	99.21 80	99.77 3
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
DVP-MVS++		98.06 1	97.99 1	98.28 10	98.67 65	95.39 12	99.29 1	98.28 50	94.78 60	98.93 19	98.87 30	96.04 2	99.86 9	97.45 45	99.58 23	99.59 30

test_0728_SECOND				98.51 5	99.45 4	95.93 6	98.21 45	98.28 50					99.86 9	97.52 41	99.67 6	99.75 7

CP-MVS		97.02 41	96.81 54	97.64 47	99.33 24	93.54 62	98.80 9	98.28 50	92.99 137	96.45 108	98.30 80	91.90 52	99.85 19	95.61 112	99.68 4	99.54 43

test_fmvsmconf0.1_n		97.09 36	97.06 33	97.19 71	95.67 296	92.21 112	97.95 77	98.27 53	95.78 22	98.40 39	99.00 15	89.99 88	99.78 46	99.06 17	99.41 57	99.59 30

SED-MVS		98.05 2	97.99 1	98.24 11	99.42 8	95.30 18	98.25 38	98.27 53	95.13 39	99.19 12	98.89 27	95.54 5	99.85 19	97.52 41	99.66 10	99.56 38

test_241102_TWO								98.27 53	95.13 39	98.93 19	98.89 27	94.99 12	99.85 19	97.52 41	99.65 13	99.74 9

test_241102_ONE					99.42 8	95.30 18		98.27 53	95.09 42	99.19 12	98.81 36	95.54 5	99.65 76

SF-MVS		97.39 23	97.13 29	98.17 16	99.02 46	95.28 20	98.23 42	98.27 53	92.37 163	98.27 41	98.65 44	93.33 24	99.72 62	96.49 72	99.52 33	99.51 47

SteuartSystems-ACMMP		97.62 11	97.53 16	97.87 26	98.39 85	94.25 42	98.43 25	98.27 53	95.34 31	98.11 44	98.56 46	94.53 13	99.71 64	96.57 70	99.62 17	99.65 20
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 25	95.20 21		98.25 59	95.13 39	98.48 37	98.87 30	95.16 8

PVSNet_Blended_VisFu		95.27 113	94.91 120	96.38 122	98.20 104	90.86 174	97.27 181	98.25 59	90.21 254	94.18 185	97.27 175	87.48 137	99.73 58	93.53 169	97.77 158	98.55 164

region2R		97.07 39	96.84 49	97.77 36	99.46 3	93.79 57	98.52 18	98.24 61	93.19 127	97.14 73	98.34 72	91.59 59	99.87 7	95.46 116	99.59 19	99.64 23

PS-CasMVS		91.55 277	90.84 278	93.69 299	94.96 342	88.28 272	97.84 92	98.24 61	91.46 197	88.04 356	95.80 264	79.67 296	97.48 373	87.02 320	84.54 394	95.31 344

DU-MVS		92.90 220	92.04 229	95.49 191	94.95 343	92.83 87	97.16 194	98.24 61	93.02 136	90.13 290	95.71 271	83.47 211	97.85 336	91.71 211	83.93 400	95.78 315

9.14			96.75 59		98.93 54		97.73 112	98.23 64	91.28 206	97.88 52	98.44 61	93.00 28	99.65 76	95.76 103	99.47 43

reproduce_model		97.51 19	97.51 18	97.50 52	98.99 50	93.01 80	97.79 103	98.21 65	95.73 23	97.99 48	99.03 14	92.63 38	99.82 31	97.80 30	99.42 54	99.67 15

D2MVS		91.30 294	90.95 272	92.35 347	94.71 358	85.52 347	96.18 295	98.21 65	88.89 298	86.60 385	93.82 369	79.92 292	97.95 325	89.29 269	90.95 317	93.56 410

reproduce-ours		97.53 17	97.51 18	97.60 49	98.97 51	93.31 71	97.71 117	98.20 67	95.80 20	97.88 52	98.98 17	92.91 29	99.81 33	97.68 32	99.43 51	99.67 15

our_new_method		97.53 17	97.51 18	97.60 49	98.97 51	93.31 71	97.71 117	98.20 67	95.80 20	97.88 52	98.98 17	92.91 29	99.81 33	97.68 32	99.43 51	99.67 15

SDMVSNet		94.17 157	93.61 164	95.86 162	98.09 113	91.37 149	97.35 173	98.20 67	93.18 129	91.79 251	97.28 173	79.13 304	98.93 193	94.61 143	92.84 283	97.28 265

XVS		97.18 32	96.96 43	97.81 30	99.38 15	94.03 52	98.59 15	98.20 67	94.85 52	96.59 96	98.29 81	91.70 55	99.80 38	95.66 105	99.40 59	99.62 25

X-MVStestdata		91.71 266	89.67 332	97.81 30	99.38 15	94.03 52	98.59 15	98.20 67	94.85 52	96.59 96	32.69 471	91.70 55	99.80 38	95.66 105	99.40 59	99.62 25

ACMMP_NAP		97.20 31	96.86 47	98.23 12	99.09 38	95.16 23	97.60 136	98.19 72	92.82 151	97.93 51	98.74 41	91.60 58	99.86 9	96.26 77	99.52 33	99.67 15

CP-MVSNet		91.89 262	91.24 261	93.82 291	95.05 339	88.57 262	97.82 97	98.19 72	91.70 186	88.21 351	95.76 269	81.96 251	97.52 371	87.86 295	84.65 388	95.37 340

ZNCC-MVS		96.96 44	96.67 62	97.85 27	99.37 17	94.12 48	98.49 22	98.18 74	92.64 158	96.39 110	98.18 88	91.61 57	99.88 4	95.59 115	99.55 28	99.57 34

SMA-MVS		97.35 24	97.03 38	98.30 9	99.06 42	95.42 11	97.94 78	98.18 74	90.57 245	98.85 26	98.94 20	93.33 24	99.83 29	96.72 63	99.68 4	99.63 24
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
PEN-MVS		91.20 299	90.44 295	93.48 310	94.49 366	87.91 287	97.76 105	98.18 74	91.29 203	87.78 360	95.74 270	80.35 283	97.33 384	85.46 344	82.96 410	95.19 355

DELS-MVS		96.61 69	96.38 78	97.30 61	97.79 137	93.19 76	95.96 307	98.18 74	95.23 34	95.87 130	97.65 143	91.45 60	99.70 69	95.87 97	99.44 50	99.00 107
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
tfpnnormal		89.70 351	88.40 357	93.60 303	95.15 334	90.10 203	97.56 141	98.16 78	87.28 351	86.16 391	94.63 324	77.57 332	98.05 305	74.48 430	84.59 392	92.65 423

VNet		95.89 96	95.45 99	97.21 69	98.07 117	92.94 83	97.50 150	98.15 79	93.87 97	97.52 59	97.61 149	85.29 178	99.53 109	95.81 102	95.27 236	99.16 83

DeepPCF-MVS	93.97 1	96.61 69	97.09 31	95.15 205	98.09 113	86.63 320	96.00 305	98.15 79	95.43 27	97.95 50	98.56 46	93.40 22	99.36 134	96.77 60	99.48 42	99.45 57

SD-MVS		97.41 22	97.53 16	97.06 80	98.57 76	94.46 36	97.92 81	98.14 81	94.82 56	99.01 16	98.55 48	94.18 15	97.41 380	96.94 55	99.64 14	99.32 72
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
GST-MVS		96.85 52	96.52 68	97.82 29	99.36 21	94.14 47	98.29 32	98.13 82	92.72 154	96.70 88	98.06 95	91.35 64	99.86 9	94.83 132	99.28 71	99.47 56

UA-Net		95.95 93	95.53 95	97.20 70	97.67 144	92.98 82	97.65 126	98.13 82	94.81 58	96.61 94	98.35 69	88.87 102	99.51 114	90.36 244	97.35 171	99.11 92

QAPM		93.45 196	92.27 223	96.98 83	96.77 216	92.62 96	98.39 27	98.12 84	84.50 396	88.27 349	97.77 130	82.39 243	99.81 33	85.40 345	98.81 112	98.51 169

Vis-MVSNet		95.23 118	94.81 121	96.51 109	97.18 172	91.58 139	98.26 37	98.12 84	94.38 83	94.90 160	98.15 90	82.28 244	98.92 195	91.45 218	98.58 124	99.01 104
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 223	91.68 244	96.40 119	95.34 317	92.73 92	98.27 35	98.12 84	84.86 391	85.78 393	97.75 131	78.89 314	99.74 56	87.50 310	98.65 119	96.73 282

TranMVSNet+NR-MVSNet		92.50 232	91.63 245	95.14 206	94.76 354	92.07 117	97.53 147	98.11 87	92.90 148	89.56 312	96.12 248	83.16 218	97.60 363	89.30 268	83.20 409	95.75 319

CPTT-MVS		95.57 106	95.19 110	96.70 90	99.27 29	91.48 144	98.33 29	98.11 87	87.79 336	95.17 155	98.03 98	87.09 145	99.61 87	93.51 170	99.42 54	99.02 101

APD-MVS		96.95 45	96.60 64	98.01 21	99.03 45	94.93 28	97.72 115	98.10 89	91.50 195	98.01 47	98.32 77	92.33 44	99.58 95	94.85 130	99.51 36	99.53 46
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 50	96.60 64	97.64 47	99.40 12	93.44 64	98.50 21	98.09 90	93.27 123	95.95 128	98.33 75	91.04 72	99.88 4	95.20 119	99.57 27	99.60 29

ZD-MVS					99.05 43	94.59 33		98.08 91	89.22 284	97.03 78	98.10 91	92.52 41	99.65 76	94.58 145	99.31 69

MTGPA								98.08 91

MTAPA		97.08 37	96.78 57	97.97 25	99.37 17	94.42 38	97.24 183	98.08 91	95.07 43	96.11 120	98.59 45	90.88 78	99.90 2	96.18 89	99.50 38	99.58 33

CNVR-MVS		97.68 7	97.44 22	98.37 8	98.90 57	95.86 7	97.27 181	98.08 91	95.81 19	97.87 55	98.31 78	94.26 14	99.68 72	97.02 54	99.49 41	99.57 34

DP-MVS Recon		95.68 101	95.12 114	97.37 58	99.19 35	94.19 44	97.03 201	98.08 91	88.35 318	95.09 157	97.65 143	89.97 89	99.48 121	92.08 203	98.59 123	98.44 180

SR-MVS		97.01 42	96.86 47	97.47 54	99.09 38	93.27 73	97.98 68	98.07 96	93.75 100	97.45 61	98.48 58	91.43 62	99.59 92	96.22 80	99.27 72	99.54 43

MCST-MVS		97.18 32	96.84 49	98.20 15	99.30 27	95.35 16	97.12 197	98.07 96	93.54 110	96.08 122	97.69 138	93.86 17	99.71 64	96.50 71	99.39 61	99.55 41

NR-MVSNet		92.34 241	91.27 260	95.53 187	94.95 343	93.05 79	97.39 169	98.07 96	92.65 156	84.46 404	95.71 271	85.00 185	97.77 347	89.71 256	83.52 406	95.78 315

MP-MVS-pluss		96.70 63	96.27 81	97.98 24	99.23 33	94.71 30	96.96 212	98.06 99	90.67 235	95.55 144	98.78 39	91.07 71	99.86 9	96.58 69	99.55 28	99.38 68
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 56	96.71 61	97.12 74	99.01 49	92.31 108	97.98 68	98.06 99	93.11 133	97.44 62	98.55 48	90.93 76	99.55 105	96.06 90	99.25 77	99.51 47

MP-MVS		96.77 58	96.45 75	97.72 41	99.39 14	93.80 56	98.41 26	98.06 99	93.37 119	95.54 146	98.34 72	90.59 82	99.88 4	94.83 132	99.54 30	99.49 52
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 72	96.27 81	97.22 68	99.32 25	92.74 91	98.74 10	98.06 99	90.57 245	96.77 85	98.35 69	90.21 85	99.53 109	94.80 136	99.63 16	99.38 68

HPM-MVS		96.69 65	96.45 75	97.40 57	99.36 21	93.11 78	98.87 6	98.06 99	91.17 214	96.40 109	97.99 104	90.99 73	99.58 95	95.61 112	99.61 18	99.49 52
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 148	93.80 157	96.64 92	97.07 178	91.97 122	96.32 283	98.06 99	88.94 296	94.50 174	96.78 206	84.60 191	99.27 144	91.90 204	96.02 213	98.68 155

DeepC-MVS	93.07 3	96.06 87	95.66 92	97.29 62	97.96 125	93.17 77	97.30 179	98.06 99	93.92 95	93.38 211	98.66 42	86.83 147	99.73 58	95.60 114	99.22 79	98.96 112
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		97.30 28	97.03 38	98.11 18	98.77 60	95.06 26	97.34 174	98.04 106	95.96 14	97.09 76	97.88 116	93.18 27	99.71 64	95.84 101	99.17 88	99.56 38

DeepC-MVS_fast	93.89 2	96.93 47	96.64 63	97.78 34	98.64 71	94.30 39	97.41 164	98.04 106	94.81 58	96.59 96	98.37 67	91.24 67	99.64 84	95.16 121	99.52 33	99.42 63
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		96.88 49	96.80 55	97.11 76	99.02 46	92.34 106	97.98 68	98.03 108	93.52 113	97.43 64	98.51 53	91.40 63	99.56 103	96.05 91	99.26 75	99.43 61

RE-MVS-def			96.72 60		99.02 46	92.34 106	97.98 68	98.03 108	93.52 113	97.43 64	98.51 53	90.71 80		96.05 91	99.26 75	99.43 61

RPMNet		88.98 357	87.05 371	94.77 233	94.45 368	87.19 304	90.23 445	98.03 108	77.87 444	92.40 229	87.55 451	80.17 287	99.51 114	68.84 451	93.95 269	97.60 250

save fliter					98.91 56	94.28 40	97.02 203	98.02 111	95.35 30

TEST9					98.70 63	94.19 44	96.41 269	98.02 111	88.17 322	96.03 123	97.56 155	92.74 35	99.59 92

train_agg		96.30 83	95.83 91	97.72 41	98.70 63	94.19 44	96.41 269	98.02 111	88.58 309	96.03 123	97.56 155	92.73 36	99.59 92	95.04 123	99.37 65	99.39 66

test_8					98.67 65	94.06 51	96.37 277	98.01 114	88.58 309	95.98 127	97.55 157	92.73 36	99.58 95

agg_prior					98.67 65	93.79 57		98.00 115		95.68 140			99.57 102

test_prior				97.23 67	98.67 65	92.99 81		98.00 115					99.41 129			99.29 73

WR-MVS		92.34 241	91.53 249	94.77 233	95.13 336	90.83 175	96.40 273	97.98 117	91.88 181	89.29 321	95.54 282	82.50 239	97.80 343	89.79 255	85.27 379	95.69 322

HPM-MVS++		97.34 25	96.97 41	98.47 6	99.08 40	96.16 4	97.55 146	97.97 118	95.59 24	96.61 94	97.89 113	92.57 40	99.84 24	95.95 96	99.51 36	99.40 64

CANet		96.39 78	96.02 86	97.50 52	97.62 151	93.38 66	97.02 203	97.96 119	95.42 28	94.86 161	97.81 126	87.38 140	99.82 31	96.88 57	99.20 85	99.29 73

114514_t		93.95 172	93.06 189	96.63 96	99.07 41	91.61 136	97.46 161	97.96 119	77.99 442	93.00 220	97.57 153	86.14 161	99.33 136	89.22 272	99.15 92	98.94 116

IU-MVS					99.42 8	95.39 12		97.94 121	90.40 252	98.94 18				97.41 48	99.66 10	99.74 9

MSC_two_6792asdad				98.86 1	98.67 65	96.94 1		97.93 122					99.86 9	97.68 32	99.67 6	99.77 3

No_MVS				98.86 1	98.67 65	96.94 1		97.93 122					99.86 9	97.68 32	99.67 6	99.77 3

fmvsm_s_conf0.1_n_2		96.33 82	96.44 77	96.00 152	97.30 165	90.37 197	97.53 147	97.92 124	96.52 10	99.14 14	99.08 7	83.21 216	99.74 56	99.22 10	98.06 147	97.88 230

Anonymous20231211		90.63 323	89.42 339	94.27 263	98.24 97	89.19 248	98.05 60	97.89 125	79.95 434	88.25 350	94.96 305	72.56 373	98.13 288	89.70 257	85.14 381	95.49 326

原ACMM1				96.38 122	98.59 73	91.09 165		97.89 125	87.41 347	95.22 154	97.68 139	90.25 84	99.54 107	87.95 294	99.12 97	98.49 172

CDPH-MVS		95.97 92	95.38 104	97.77 36	98.93 54	94.44 37	96.35 278	97.88 127	86.98 355	96.65 92	97.89 113	91.99 50	99.47 122	92.26 192	99.46 44	99.39 66

test11								97.88 127

EIA-MVS		95.53 107	95.47 98	95.71 177	97.06 181	89.63 221	97.82 97	97.87 129	93.57 106	93.92 193	95.04 302	90.61 81	98.95 190	94.62 142	98.68 117	98.54 165

CS-MVS		96.86 50	97.06 33	96.26 132	98.16 109	91.16 163	99.09 3	97.87 129	95.30 32	97.06 77	98.03 98	91.72 53	98.71 230	97.10 52	99.17 88	98.90 125

无先验							95.79 318	97.87 129	83.87 404				99.65 76	87.68 304		98.89 131

3Dnovator+	91.43 4	95.40 108	94.48 140	98.16 17	96.90 197	95.34 17	98.48 23	97.87 129	94.65 69	88.53 341	98.02 100	83.69 207	99.71 64	93.18 178	98.96 107	99.44 59

VPNet		92.23 249	91.31 257	94.99 216	95.56 301	90.96 169	97.22 189	97.86 133	92.96 143	90.96 273	96.62 223	75.06 353	98.20 282	91.90 204	83.65 405	95.80 313

test_vis1_n_1920		94.17 157	94.58 132	92.91 331	97.42 163	82.02 401	97.83 95	97.85 134	94.68 66	98.10 45	98.49 55	70.15 392	99.32 138	97.91 29	98.82 111	97.40 259

DVP-MVS		97.91 4	97.81 4	98.22 14	99.45 4	95.36 14	98.21 45	97.85 134	94.92 49	98.73 29	98.87 30	95.08 9	99.84 24	97.52 41	99.67 6	99.48 54
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
TSAR-MVS + MP.		97.42 21	97.33 27	97.69 44	99.25 30	94.24 43	98.07 58	97.85 134	93.72 101	98.57 34	98.35 69	93.69 19	99.40 130	97.06 53	99.46 44	99.44 59
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SPE-MVS-test		96.89 48	97.04 37	96.45 116	98.29 90	91.66 135	99.03 4	97.85 134	95.84 17	96.90 80	97.97 106	91.24 67	98.75 220	96.92 56	99.33 67	98.94 116

test_fmvsmconf0.01_n		96.15 86	95.85 90	97.03 81	92.66 419	91.83 127	97.97 74	97.84 138	95.57 25	97.53 58	99.00 15	84.20 200	99.76 51	98.82 22	99.08 99	99.48 54

GDP-MVS		95.62 103	95.13 112	97.09 77	96.79 210	93.26 74	97.89 85	97.83 139	93.58 105	96.80 82	97.82 124	83.06 223	99.16 158	94.40 149	97.95 153	98.87 134

balanced_conf03		96.84 54	96.89 46	96.68 91	97.63 150	92.22 111	98.17 51	97.82 140	94.44 78	98.23 42	97.36 168	90.97 74	99.22 148	97.74 31	99.66 10	98.61 158

AdaColmap		94.34 152	93.68 162	96.31 126	98.59 73	91.68 134	96.59 258	97.81 141	89.87 262	92.15 239	97.06 189	83.62 210	99.54 107	89.34 267	98.07 146	97.70 243

MVSMamba_PlusPlus		96.51 72	96.48 70	96.59 100	98.07 117	91.97 122	98.14 52	97.79 142	90.43 250	97.34 67	97.52 158	91.29 66	99.19 151	98.12 27	99.64 14	98.60 159

KinetiMVS		95.26 114	94.75 126	96.79 88	96.99 190	92.05 118	97.82 97	97.78 143	94.77 62	96.46 106	97.70 136	80.62 277	99.34 135	92.37 191	98.28 137	98.97 109

mamv4		94.66 145	96.10 85	90.37 400	98.01 120	73.41 451	96.82 228	97.78 143	89.95 261	94.52 172	97.43 163	92.91 29	99.09 171	98.28 26	99.16 91	98.60 159

ETV-MVS		96.02 89	95.89 89	96.40 119	97.16 173	92.44 103	97.47 159	97.77 145	94.55 72	96.48 104	94.51 330	91.23 69	98.92 195	95.65 108	98.19 141	97.82 238

新几何1				97.32 60	98.60 72	93.59 61		97.75 146	81.58 425	95.75 135	97.85 120	90.04 87	99.67 74	86.50 326	99.13 95	98.69 154

旧先验1					98.38 86	93.38 66		97.75 146			98.09 93	92.30 47			99.01 105	99.16 83

EC-MVSNet		96.42 76	96.47 71	96.26 132	97.01 188	91.52 141	98.89 5	97.75 146	94.42 79	96.64 93	97.68 139	89.32 95	98.60 246	97.45 45	99.11 98	98.67 156

EI-MVSNet-Vis-set		96.51 72	96.47 71	96.63 96	98.24 97	91.20 157	96.89 220	97.73 149	94.74 64	96.49 103	98.49 55	90.88 78	99.58 95	96.44 73	98.32 135	99.13 87

PAPM_NR		95.01 125	94.59 131	96.26 132	98.89 58	90.68 183	97.24 183	97.73 149	91.80 182	92.93 225	96.62 223	89.13 98	99.14 163	89.21 273	97.78 157	98.97 109

Anonymous20240529		91.98 258	90.73 285	95.73 175	98.14 110	89.40 235	97.99 65	97.72 151	79.63 436	93.54 204	97.41 165	69.94 394	99.56 103	91.04 226	91.11 313	98.22 200

CHOSEN 280x420		93.12 208	92.72 206	94.34 257	96.71 221	87.27 300	90.29 444	97.72 151	86.61 362	91.34 262	95.29 290	84.29 199	98.41 262	93.25 176	98.94 108	97.35 262

EI-MVSNet-UG-set		96.34 81	96.30 80	96.47 113	98.20 104	90.93 171	96.86 223	97.72 151	94.67 67	96.16 119	98.46 59	90.43 83	99.58 95	96.23 79	97.96 152	98.90 125

LS3D		93.57 189	92.61 211	96.47 113	97.59 154	91.61 136	97.67 122	97.72 151	85.17 386	90.29 284	98.34 72	84.60 191	99.73 58	83.85 368	98.27 138	98.06 219

PAPR		94.18 156	93.42 178	96.48 112	97.64 148	91.42 148	95.55 332	97.71 155	88.99 293	92.34 235	95.82 263	89.19 96	99.11 166	86.14 332	97.38 169	98.90 125

UGNet		94.04 167	93.28 181	96.31 126	96.85 202	91.19 158	97.88 87	97.68 156	94.40 81	93.00 220	96.18 243	73.39 370	99.61 87	91.72 210	98.46 129	98.13 208
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
testdata				95.46 195	98.18 108	88.90 255		97.66 157	82.73 416	97.03 78	98.07 94	90.06 86	98.85 202	89.67 258	98.98 106	98.64 157

test12				97.65 45	98.46 77	94.26 41		97.66 157		95.52 147		90.89 77	99.46 123		99.25 77	99.22 80

DTE-MVSNet		90.56 324	89.75 330	93.01 327	93.95 381	87.25 301	97.64 130	97.65 159	90.74 230	87.12 373	95.68 274	79.97 291	97.00 397	83.33 369	81.66 416	94.78 382

TAPA-MVS	90.10 7	92.30 244	91.22 263	95.56 184	98.33 88	89.60 223	96.79 232	97.65 159	81.83 422	91.52 257	97.23 178	87.94 121	98.91 197	71.31 445	98.37 133	98.17 206
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 209	92.45 219	95.05 210	98.09 113	89.21 245	96.89 220	97.64 161	93.18 129	91.79 251	97.28 173	75.35 352	98.65 240	88.99 278	92.84 283	97.28 265

test_cas_vis1_n_1920		94.48 150	94.55 136	94.28 262	96.78 214	86.45 325	97.63 132	97.64 161	93.32 122	97.68 57	98.36 68	73.75 368	99.08 174	96.73 62	99.05 101	97.31 264

NormalMVS		96.36 80	96.11 84	97.12 74	99.37 17	92.90 85	97.99 65	97.63 163	95.92 15	96.57 99	97.93 108	85.34 176	99.50 117	94.99 126	99.21 80	98.97 109

Elysia		94.00 169	93.12 186	96.64 92	96.08 280	92.72 93	97.50 150	97.63 163	91.15 216	94.82 162	97.12 184	74.98 355	99.06 180	90.78 231	98.02 148	98.12 210

StellarMVS		94.00 169	93.12 186	96.64 92	96.08 280	92.72 93	97.50 150	97.63 163	91.15 216	94.82 162	97.12 184	74.98 355	99.06 180	90.78 231	98.02 148	98.12 210

cdsmvs_eth3d_5k		23.24 441	30.99 443	0.00 459	0.00 482	0.00 484	0.00 471	97.63 163	0.00 477	0.00 478	96.88 202	84.38 196	0.00 478	0.00 477	0.00 476	0.00 474

DPM-MVS		95.69 100	94.92 119	98.01 21	98.08 116	95.71 10	95.27 348	97.62 167	90.43 250	95.55 144	97.07 188	91.72 53	99.50 117	89.62 260	98.94 108	98.82 140

sasdasda		96.02 89	95.45 99	97.75 38	97.59 154	95.15 24	98.28 33	97.60 168	94.52 74	96.27 114	96.12 248	87.65 128	99.18 154	96.20 85	94.82 245	98.91 122

canonicalmvs		96.02 89	95.45 99	97.75 38	97.59 154	95.15 24	98.28 33	97.60 168	94.52 74	96.27 114	96.12 248	87.65 128	99.18 154	96.20 85	94.82 245	98.91 122

test222					98.24 97	92.21 112	95.33 343	97.60 168	79.22 438	95.25 152	97.84 122	88.80 104			99.15 92	98.72 151

cascas		91.20 299	90.08 312	94.58 243	94.97 341	89.16 249	93.65 409	97.59 171	79.90 435	89.40 316	92.92 395	75.36 351	98.36 270	92.14 197	94.75 248	96.23 292

h-mvs33		94.15 159	93.52 170	96.04 146	97.81 136	90.22 201	97.62 134	97.58 172	95.19 35	96.74 86	97.45 160	83.67 208	99.61 87	95.85 99	79.73 423	98.29 196

MGCFI-Net		95.94 94	95.40 103	97.56 51	97.59 154	94.62 32	98.21 45	97.57 173	94.41 80	96.17 118	96.16 246	87.54 133	99.17 156	96.19 87	94.73 250	98.91 122

MVSFormer		95.37 109	95.16 111	95.99 153	96.34 256	91.21 155	98.22 43	97.57 173	91.42 199	96.22 116	97.32 169	86.20 159	97.92 330	94.07 155	99.05 101	98.85 136

test_djsdf		93.07 211	92.76 201	94.00 276	93.49 398	88.70 259	98.22 43	97.57 173	91.42 199	90.08 296	95.55 281	82.85 230	97.92 330	94.07 155	91.58 304	95.40 337

OMC-MVS		95.09 123	94.70 127	96.25 135	98.46 77	91.28 151	96.43 265	97.57 173	92.04 177	94.77 166	97.96 107	87.01 146	99.09 171	91.31 220	96.77 192	98.36 187

viewcassd2359sk11		95.26 114	95.09 115	95.80 167	96.95 194	89.72 219	96.80 231	97.56 177	92.21 169	95.37 150	97.80 128	87.17 144	98.77 215	94.82 134	97.10 184	98.90 125

PS-MVSNAJss		93.74 182	93.51 171	94.44 251	93.91 383	89.28 243	97.75 107	97.56 177	92.50 159	89.94 298	96.54 226	88.65 107	98.18 285	93.83 164	90.90 318	95.86 307

casdiffmvs_mvg		95.81 99	95.57 93	96.51 109	96.87 199	91.49 142	97.50 150	97.56 177	93.99 93	95.13 156	97.92 111	87.89 122	98.78 212	95.97 95	97.33 172	99.26 77
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jajsoiax		92.42 237	91.89 237	94.03 275	93.33 406	88.50 266	97.73 112	97.53 180	92.00 179	88.85 333	96.50 228	75.62 350	98.11 292	93.88 162	91.56 305	95.48 327

mvs_tets		92.31 243	91.76 240	93.94 284	93.41 403	88.29 271	97.63 132	97.53 180	92.04 177	88.76 336	96.45 230	74.62 360	98.09 297	93.91 160	91.48 306	95.45 332

dcpmvs_2		96.37 79	97.05 36	94.31 260	98.96 53	84.11 374	97.56 141	97.51 182	93.92 95	97.43 64	98.52 52	92.75 34	99.32 138	97.32 51	99.50 38	99.51 47

HQP_MVS		93.78 181	93.43 176	94.82 226	96.21 260	89.99 207	97.74 110	97.51 182	94.85 52	91.34 262	96.64 216	81.32 263	98.60 246	93.02 184	92.23 292	95.86 307

plane_prior5								97.51 182					98.60 246	93.02 184	92.23 292	95.86 307

viewmanbaseed2359cas		95.24 117	95.02 117	95.91 156	96.87 199	89.98 209	96.82 228	97.49 185	92.26 165	95.47 148	97.82 124	86.47 152	98.69 232	94.80 136	97.20 180	99.06 99

reproduce_monomvs		91.30 294	91.10 267	91.92 361	96.82 207	82.48 395	97.01 206	97.49 185	94.64 70	88.35 344	95.27 293	70.53 387	98.10 293	95.20 119	84.60 391	95.19 355

viewmacassd2359aftdt		95.07 124	94.80 122	95.87 159	96.53 237	89.84 215	96.90 219	97.48 187	92.44 160	95.36 151	97.89 113	85.23 179	98.68 234	94.40 149	97.00 187	99.09 94

PS-MVSNAJ		95.37 109	95.33 106	95.49 191	97.35 164	90.66 184	95.31 345	97.48 187	93.85 98	96.51 102	95.70 273	88.65 107	99.65 76	94.80 136	98.27 138	96.17 296

API-MVS		94.84 136	94.49 139	95.90 157	97.90 131	92.00 121	97.80 101	97.48 187	89.19 285	94.81 164	96.71 209	88.84 103	99.17 156	88.91 280	98.76 115	96.53 285

MG-MVS		95.61 104	95.38 104	96.31 126	98.42 81	90.53 186	96.04 302	97.48 187	93.47 115	95.67 141	98.10 91	89.17 97	99.25 145	91.27 221	98.77 114	99.13 87

MAR-MVS		94.22 155	93.46 173	96.51 109	98.00 122	92.19 115	97.67 122	97.47 191	88.13 326	93.00 220	95.84 261	84.86 189	99.51 114	87.99 293	98.17 143	97.83 237
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
CLD-MVS		92.98 215	92.53 215	94.32 258	96.12 275	89.20 246	95.28 346	97.47 191	92.66 155	89.90 299	95.62 277	80.58 278	98.40 263	92.73 189	92.40 290	95.38 339
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 292	90.22 308	94.68 237	94.86 350	87.86 288	97.23 187	97.46 193	87.99 327	89.90 299	96.92 200	66.35 422	98.23 279	90.30 245	90.99 316	97.96 224

nrg030		94.05 166	93.31 180	96.27 131	95.22 328	94.59 33	98.34 28	97.46 193	92.93 144	91.21 271	96.64 216	87.23 143	98.22 280	94.99 126	85.80 371	95.98 306

XVG-OURS		93.72 183	93.35 179	94.80 231	97.07 178	88.61 260	94.79 364	97.46 193	91.97 180	93.99 190	97.86 119	81.74 257	98.88 199	92.64 190	92.67 288	96.92 277

LPG-MVS_test		92.94 218	92.56 212	94.10 270	96.16 270	88.26 273	97.65 126	97.46 193	91.29 203	90.12 292	97.16 181	79.05 307	98.73 224	92.25 194	91.89 300	95.31 344

LGP-MVS_train				94.10 270	96.16 270	88.26 273		97.46 193	91.29 203	90.12 292	97.16 181	79.05 307	98.73 224	92.25 194	91.89 300	95.31 344

MVS		91.71 266	90.44 295	95.51 188	95.20 330	91.59 138	96.04 302	97.45 198	73.44 452	87.36 369	95.60 278	85.42 175	99.10 168	85.97 337	97.46 164	95.83 311

XVG-OURS-SEG-HR		93.86 178	93.55 166	94.81 228	97.06 181	88.53 265	95.28 346	97.45 198	91.68 187	94.08 189	97.68 139	82.41 242	98.90 198	93.84 163	92.47 289	96.98 273

baseline		95.58 105	95.42 102	96.08 142	96.78 214	90.41 192	97.16 194	97.45 198	93.69 104	95.65 142	97.85 120	87.29 141	98.68 234	95.66 105	97.25 178	99.13 87

ab-mvs		93.57 189	92.55 213	96.64 92	97.28 167	91.96 124	95.40 339	97.45 198	89.81 267	93.22 217	96.28 239	79.62 298	99.46 123	90.74 234	93.11 280	98.50 170

xiu_mvs_v2_base		95.32 112	95.29 107	95.40 196	97.22 169	90.50 187	95.44 338	97.44 202	93.70 103	96.46 106	96.18 243	88.59 111	99.53 109	94.79 139	97.81 156	96.17 296

1314		92.81 227	92.03 230	95.14 206	95.33 320	89.52 230	96.04 302	97.44 202	87.72 340	86.25 390	95.33 289	83.84 205	98.79 211	89.26 270	97.05 186	97.11 271

casdiffmvs		95.64 102	95.49 96	96.08 142	96.76 219	90.45 189	97.29 180	97.44 202	94.00 92	95.46 149	97.98 105	87.52 136	98.73 224	95.64 109	97.33 172	99.08 96
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt07		94.76 142	94.68 128	95.01 214	96.76 219	87.41 296	96.38 275	97.43 205	92.65 156	94.52 172	97.75 131	85.55 173	98.81 208	94.36 151	96.69 198	98.82 140

XXY-MVS		92.16 251	91.23 262	94.95 222	94.75 355	90.94 170	97.47 159	97.43 205	89.14 286	88.90 329	96.43 231	79.71 295	98.24 278	89.56 261	87.68 352	95.67 323

anonymousdsp		92.16 251	91.55 248	93.97 280	92.58 421	89.55 227	97.51 149	97.42 207	89.42 279	88.40 343	94.84 312	80.66 276	97.88 335	91.87 206	91.28 310	94.48 390

Effi-MVS+		94.93 130	94.45 141	96.36 124	96.61 225	91.47 145	96.41 269	97.41 208	91.02 222	94.50 174	95.92 257	87.53 134	98.78 212	93.89 161	96.81 191	98.84 139

RRT-MVS		94.51 148	94.35 145	94.98 218	96.40 250	86.55 323	97.56 141	97.41 208	93.19 127	94.93 159	97.04 190	79.12 305	99.30 142	96.19 87	97.32 174	99.09 94

HQP3-MVS								97.39 210							92.10 297

HQP-MVS		93.19 205	92.74 204	94.54 246	95.86 286	89.33 239	96.65 249	97.39 210	93.55 107	90.14 286	95.87 259	80.95 267	98.50 256	92.13 200	92.10 297	95.78 315

PLC	91.00 6	94.11 163	93.43 176	96.13 140	98.58 75	91.15 164	96.69 245	97.39 210	87.29 350	91.37 261	96.71 209	88.39 112	99.52 113	87.33 313	97.13 183	97.73 241
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
diffmvs_AUTHOR		95.33 111	95.27 108	95.50 190	96.37 254	89.08 251	96.08 300	97.38 213	93.09 135	96.53 101	97.74 133	86.45 153	98.68 234	96.32 75	97.48 163	98.75 147

v7n		90.76 316	89.86 323	93.45 312	93.54 395	87.60 294	97.70 120	97.37 214	88.85 299	87.65 362	94.08 360	81.08 266	98.10 293	84.68 354	83.79 404	94.66 387

UnsupCasMVSNet_eth		85.99 393	84.45 397	90.62 396	89.97 439	82.40 398	93.62 410	97.37 214	89.86 263	78.59 442	92.37 405	65.25 431	95.35 431	82.27 382	70.75 450	94.10 401

viewdifsd2359ckpt13		94.87 134	94.52 137	95.90 157	96.88 198	90.19 202	96.92 216	97.36 216	91.26 207	94.65 168	97.46 159	85.79 167	98.64 241	93.64 167	96.76 193	98.88 133

ACMM	89.79 8	92.96 216	92.50 217	94.35 255	96.30 258	88.71 258	97.58 137	97.36 216	91.40 201	90.53 279	96.65 215	79.77 294	98.75 220	91.24 222	91.64 302	95.59 325
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 125	94.76 123	95.75 172	96.58 228	91.71 131	96.25 288	97.35 218	92.99 137	96.70 88	96.63 220	82.67 234	99.44 126	96.22 80	97.46 164	96.11 302

xiu_mvs_v1_base		95.01 125	94.76 123	95.75 172	96.58 228	91.71 131	96.25 288	97.35 218	92.99 137	96.70 88	96.63 220	82.67 234	99.44 126	96.22 80	97.46 164	96.11 302

xiu_mvs_v1_base_debi		95.01 125	94.76 123	95.75 172	96.58 228	91.71 131	96.25 288	97.35 218	92.99 137	96.70 88	96.63 220	82.67 234	99.44 126	96.22 80	97.46 164	96.11 302

diffmvs		95.25 116	95.13 112	95.63 180	96.43 249	89.34 238	95.99 306	97.35 218	92.83 150	96.31 112	97.37 167	86.44 154	98.67 237	96.26 77	97.19 181	98.87 134
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WTY-MVS		94.71 144	94.02 153	96.79 88	97.71 142	92.05 118	96.59 258	97.35 218	90.61 241	94.64 169	96.93 197	86.41 155	99.39 131	91.20 223	94.71 251	98.94 116

viewdifsd2359ckpt09		94.81 139	94.37 144	96.12 141	96.91 195	90.75 180	96.94 213	97.31 223	90.51 248	94.31 179	97.38 166	85.70 169	98.71 230	93.54 168	96.75 194	98.90 125

SSM_0407		94.54 147	94.12 152	95.80 167	96.79 210	90.38 194	96.79 232	97.29 224	91.24 208	93.68 197	97.60 150	85.03 183	98.67 237	92.14 197	96.51 203	98.35 189

SSM_0404		94.73 143	94.31 147	95.98 154	97.05 183	90.90 173	97.01 206	97.29 224	91.24 208	94.17 186	97.60 150	85.03 183	98.76 217	92.14 197	97.30 175	98.29 196

F-COLMAP		93.58 187	92.98 193	95.37 197	98.40 83	88.98 253	97.18 192	97.29 224	87.75 339	90.49 280	97.10 187	85.21 180	99.50 117	86.70 323	96.72 197	97.63 245

VortexMVS		92.88 222	92.64 208	93.58 305	96.58 228	87.53 295	96.93 215	97.28 227	92.78 153	89.75 304	94.99 303	82.73 233	97.76 348	94.60 144	88.16 347	95.46 330

XVG-ACMP-BASELINE		90.93 312	90.21 309	93.09 325	94.31 374	85.89 340	95.33 343	97.26 228	91.06 221	89.38 317	95.44 287	68.61 405	98.60 246	89.46 263	91.05 314	94.79 380

PCF-MVS	89.48 11	91.56 276	89.95 320	96.36 124	96.60 226	92.52 101	92.51 429	97.26 228	79.41 437	88.90 329	96.56 225	84.04 204	99.55 105	77.01 421	97.30 175	97.01 272
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 231	92.14 226	94.05 273	96.40 250	88.20 276	97.36 172	97.25 230	91.52 194	88.30 347	96.64 216	78.46 319	98.72 229	91.86 207	91.48 306	95.23 351
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 187	93.46 173	93.94 284	96.19 264	86.16 334	93.73 404	97.24 231	91.54 190	93.50 206	97.04 190	85.64 171	96.91 400	90.68 236	95.59 227	98.76 143

IMVS_0407		93.94 173	93.75 159	94.49 248	96.19 264	86.16 334	96.35 278	97.24 231	91.54 190	93.50 206	97.04 190	85.64 171	98.54 253	90.68 236	95.59 227	98.76 143

IMVS_0404		92.44 235	91.92 235	94.00 276	96.19 264	86.16 334	93.84 401	97.24 231	91.54 190	88.17 353	97.04 190	76.96 337	97.09 391	90.68 236	95.59 227	98.76 143

IMVS_0403		93.98 171	93.79 158	94.55 245	96.19 264	86.16 334	96.35 278	97.24 231	91.54 190	93.59 201	97.04 190	85.86 164	98.73 224	90.68 236	95.59 227	98.76 143

OPM-MVS		93.28 201	92.76 201	94.82 226	94.63 361	90.77 178	96.65 249	97.18 235	93.72 101	91.68 255	97.26 176	79.33 302	98.63 243	92.13 200	92.28 291	95.07 358
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 220	92.02 231	95.56 184	98.19 106	90.80 176	95.27 348	97.18 235	87.96 328	91.86 250	95.68 274	80.44 281	98.99 188	84.01 363	97.54 162	96.89 278

alignmvs		95.87 98	95.23 109	97.78 34	97.56 160	95.19 22	97.86 88	97.17 237	94.39 82	96.47 105	96.40 233	85.89 163	99.20 150	96.21 84	95.11 241	98.95 115

MVS_Test		94.89 132	94.62 130	95.68 178	96.83 205	89.55 227	96.70 243	97.17 237	91.17 214	95.60 143	96.11 252	87.87 124	98.76 217	93.01 186	97.17 182	98.72 151

Fast-Effi-MVS+		93.46 193	92.75 203	95.59 183	96.77 216	90.03 204	96.81 230	97.13 239	88.19 321	91.30 265	94.27 348	86.21 158	98.63 243	87.66 305	96.46 209	98.12 210

EI-MVSNet		93.03 213	92.88 197	93.48 310	95.77 292	86.98 309	96.44 263	97.12 240	90.66 237	91.30 265	97.64 146	86.56 149	98.05 305	89.91 251	90.55 322	95.41 334

MVSTER		93.20 204	92.81 200	94.37 254	96.56 232	89.59 224	97.06 200	97.12 240	91.24 208	91.30 265	95.96 255	82.02 250	98.05 305	93.48 171	90.55 322	95.47 329

viewmambaseed2359dif		94.28 153	94.14 150	94.71 236	96.21 260	86.97 310	95.93 309	97.11 242	89.00 292	95.00 158	97.70 136	86.02 162	98.59 250	93.71 166	96.59 202	98.57 163

test_yl		94.78 140	94.23 148	96.43 117	97.74 140	91.22 153	96.85 224	97.10 243	91.23 211	95.71 137	96.93 197	84.30 197	99.31 140	93.10 179	95.12 239	98.75 147

DCV-MVSNet		94.78 140	94.23 148	96.43 117	97.74 140	91.22 153	96.85 224	97.10 243	91.23 211	95.71 137	96.93 197	84.30 197	99.31 140	93.10 179	95.12 239	98.75 147

LTVRE_ROB	88.41 13	90.99 308	89.92 322	94.19 264	96.18 268	89.55 227	96.31 284	97.09 245	87.88 331	85.67 394	95.91 258	78.79 315	98.57 251	81.50 385	89.98 327	94.44 393
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
viewmsd2359difaftdt		93.46 193	93.23 183	94.17 265	96.12 275	85.42 349	96.43 265	97.08 246	92.91 145	94.21 182	98.00 102	80.82 273	98.74 222	94.41 148	89.05 336	98.34 193

test_fmvs1_n		92.73 229	92.88 197	92.29 351	96.08 280	81.05 409	97.98 68	97.08 246	90.72 232	96.79 84	98.18 88	63.07 435	98.45 260	97.62 39	98.42 132	97.36 260

v10		91.04 306	90.23 306	93.49 309	94.12 377	88.16 279	97.32 177	97.08 246	88.26 320	88.29 348	94.22 353	82.17 247	97.97 317	86.45 327	84.12 398	94.33 396

viewdifsd2359ckpt11		93.46 193	93.22 184	94.17 265	96.11 277	85.42 349	96.43 265	97.07 249	92.91 145	94.20 183	98.00 102	80.82 273	98.73 224	94.42 147	89.04 338	98.34 193

mamba_0408		93.70 184	92.99 190	95.83 164	96.79 210	90.38 194	88.69 454	97.07 249	90.96 224	93.68 197	97.31 171	84.97 186	98.76 217	90.95 227	96.51 203	98.35 189

SSM_04072		93.51 192	92.99 190	95.05 210	96.79 210	90.38 194	88.69 454	97.07 249	90.96 224	93.68 197	97.31 171	84.97 186	96.42 411	90.95 227	96.51 203	98.35 189

v144192		91.06 305	90.28 302	93.39 313	93.66 392	87.23 303	96.83 227	97.07 249	87.43 346	89.69 307	94.28 347	81.48 260	98.00 312	87.18 317	84.92 387	94.93 366

v1192		91.07 304	90.23 306	93.58 305	93.70 389	87.82 290	96.73 239	97.07 249	87.77 337	89.58 310	94.32 345	80.90 271	97.97 317	86.52 325	85.48 374	94.95 362

v8		91.29 296	90.53 294	93.57 307	94.15 376	88.12 280	97.34 174	97.06 254	88.99 293	88.32 346	94.26 350	83.08 221	98.01 311	87.62 307	83.92 402	94.57 389

mvs_anonymous		93.82 179	93.74 160	94.06 272	96.44 248	85.41 351	95.81 316	97.05 255	89.85 265	90.09 295	96.36 235	87.44 138	97.75 350	93.97 157	96.69 198	99.02 101

IterMVS-LS		92.29 245	91.94 234	93.34 315	96.25 259	86.97 310	96.57 261	97.05 255	90.67 235	89.50 315	94.80 315	86.59 148	97.64 358	89.91 251	86.11 369	95.40 337
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 314	90.03 317	93.29 317	93.55 394	86.96 312	96.74 238	97.04 257	87.36 348	89.52 314	94.34 342	80.23 286	97.97 317	86.27 328	85.21 380	94.94 364

CDS-MVSNet		94.14 162	93.54 167	95.93 155	96.18 268	91.46 146	96.33 282	97.04 257	88.97 295	93.56 202	96.51 227	87.55 132	97.89 334	89.80 254	95.95 215	98.44 180
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 350	89.26 343	91.19 385	95.16 331	80.29 420	94.53 371	97.03 259	91.79 183	88.86 332	94.10 357	69.94 394	97.82 340	85.29 346	86.66 365	95.45 332

v1144		91.37 289	90.60 290	93.68 300	93.89 384	88.23 275	96.84 226	97.03 259	88.37 317	89.69 307	94.39 337	82.04 249	97.98 314	87.80 297	85.37 376	94.84 372

v1240		90.70 320	89.85 324	93.23 319	93.51 397	86.80 313	96.61 255	97.02 261	87.16 353	89.58 310	94.31 346	79.55 299	97.98 314	85.52 343	85.44 375	94.90 369

EPP-MVSNet		95.22 119	95.04 116	95.76 170	97.49 161	89.56 226	98.67 13	97.00 262	90.69 233	94.24 181	97.62 148	89.79 92	98.81 208	93.39 175	96.49 207	98.92 121

V42		91.58 275	90.87 274	93.73 295	94.05 380	88.50 266	97.32 177	96.97 263	88.80 305	89.71 305	94.33 343	82.54 238	98.05 305	89.01 277	85.07 383	94.64 388

test_fmvs1		93.21 203	93.53 168	92.25 354	96.55 234	81.20 408	97.40 168	96.96 264	90.68 234	96.80 82	98.04 97	69.25 400	98.40 263	97.58 40	98.50 125	97.16 270

FMVSNet2		91.31 293	90.08 312	94.99 216	96.51 241	92.21 112	97.41 164	96.95 265	88.82 302	88.62 338	94.75 317	73.87 364	97.42 379	85.20 349	88.55 344	95.35 341

ACMH	87.59 16	90.53 325	89.42 339	93.87 289	96.21 260	87.92 285	97.24 183	96.94 266	88.45 315	83.91 414	96.27 240	71.92 376	98.62 245	84.43 357	89.43 333	95.05 360
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 290	90.27 303	94.59 239	96.51 241	91.18 160	97.50 150	96.93 267	88.82 302	89.35 318	94.51 330	73.87 364	97.29 386	86.12 333	88.82 339	95.31 344

test1		91.35 290	90.27 303	94.59 239	96.51 241	91.18 160	97.50 150	96.93 267	88.82 302	89.35 318	94.51 330	73.87 364	97.29 386	86.12 333	88.82 339	95.31 344

FMVSNet3		91.78 264	90.69 288	95.03 213	96.53 237	92.27 110	97.02 203	96.93 267	89.79 268	89.35 318	94.65 323	77.01 335	97.47 374	86.12 333	88.82 339	95.35 341

FMVSNet1		89.88 345	88.31 358	94.59 239	95.41 310	91.18 160	97.50 150	96.93 267	86.62 361	87.41 367	94.51 330	65.94 427	97.29 386	83.04 372	87.43 355	95.31 344

GeoE		93.89 176	93.28 181	95.72 176	96.96 193	89.75 218	98.24 41	96.92 271	89.47 276	92.12 241	97.21 179	84.42 195	98.39 268	87.71 300	96.50 206	99.01 104

SymmetryMVS		95.94 94	95.54 94	97.15 72	97.85 133	92.90 85	97.99 65	96.91 272	95.92 15	96.57 99	97.93 108	85.34 176	99.50 117	94.99 126	96.39 210	99.05 100

miper_enhance_ethall		91.54 279	91.01 270	93.15 323	95.35 316	87.07 308	93.97 393	96.90 273	86.79 359	89.17 325	93.43 389	86.55 150	97.64 358	89.97 250	86.93 360	94.74 384

eth_miper_zixun_eth		91.02 307	90.59 291	92.34 349	95.33 320	84.35 370	94.10 390	96.90 273	88.56 311	88.84 334	94.33 343	84.08 202	97.60 363	88.77 283	84.37 396	95.06 359

TAMVS		94.01 168	93.46 173	95.64 179	96.16 270	90.45 189	96.71 242	96.89 275	89.27 283	93.46 209	96.92 200	87.29 141	97.94 327	88.70 285	95.74 221	98.53 166

miper_ehance_all_eth		91.59 273	91.13 266	92.97 329	95.55 302	86.57 321	94.47 374	96.88 276	87.77 337	88.88 331	94.01 362	86.22 157	97.54 367	89.49 262	86.93 360	94.79 380

v2v482		91.59 273	90.85 277	93.80 292	93.87 385	88.17 278	96.94 213	96.88 276	89.54 273	89.53 313	94.90 309	81.70 258	98.02 310	89.25 271	85.04 385	95.20 352

CNLPA		94.28 153	93.53 168	96.52 105	98.38 86	92.55 100	96.59 258	96.88 276	90.13 258	91.91 247	97.24 177	85.21 180	99.09 171	87.64 306	97.83 155	97.92 227

PAPM		91.52 280	90.30 301	95.20 203	95.30 323	89.83 216	93.38 415	96.85 279	86.26 369	88.59 339	95.80 264	84.88 188	98.15 287	75.67 426	95.93 216	97.63 245

c3_l		91.38 287	90.89 273	92.88 333	95.58 300	86.30 328	94.68 366	96.84 280	88.17 322	88.83 335	94.23 351	85.65 170	97.47 374	89.36 266	84.63 389	94.89 370

pm-mvs1		90.72 319	89.65 334	93.96 281	94.29 375	89.63 221	97.79 103	96.82 281	89.07 288	86.12 392	95.48 286	78.61 317	97.78 345	86.97 321	81.67 415	94.46 391

test_vis1_n		92.37 240	92.26 224	92.72 339	94.75 355	82.64 391	98.02 62	96.80 282	91.18 213	97.77 56	97.93 108	58.02 445	98.29 276	97.63 37	98.21 140	97.23 268

CMPMVS	62.92 21	85.62 398	84.92 393	87.74 423	89.14 444	73.12 453	94.17 388	96.80 282	73.98 449	73.65 451	94.93 307	66.36 421	97.61 362	83.95 365	91.28 310	92.48 428
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 332	89.77 328	91.78 370	94.33 372	84.72 367	95.55 332	96.73 284	86.17 371	86.36 389	95.28 292	71.28 381	97.80 343	84.09 362	98.14 144	92.81 420

Effi-MVS+-dtu		93.08 210	93.21 185	92.68 342	96.02 283	83.25 384	97.14 196	96.72 285	93.85 98	91.20 272	93.44 386	83.08 221	98.30 275	91.69 213	95.73 222	96.50 287

TSAR-MVS + GP.		96.69 65	96.49 69	97.27 65	98.31 89	93.39 65	96.79 232	96.72 285	94.17 87	97.44 62	97.66 142	92.76 33	99.33 136	96.86 59	97.76 159	99.08 96

1112_ss		93.37 198	92.42 220	96.21 136	97.05 183	90.99 167	96.31 284	96.72 285	86.87 358	89.83 302	96.69 213	86.51 151	99.14 163	88.12 290	93.67 274	98.50 170

PVSNet	86.66 18	92.24 248	91.74 243	93.73 295	97.77 138	83.69 381	92.88 424	96.72 285	87.91 330	93.00 220	94.86 311	78.51 318	99.05 183	86.53 324	97.45 168	98.47 175

miper_lstm_enhance		90.50 328	90.06 316	91.83 366	95.33 320	83.74 378	93.86 399	96.70 289	87.56 344	87.79 359	93.81 370	83.45 213	96.92 399	87.39 311	84.62 390	94.82 375

v148		90.99 308	90.38 297	92.81 336	93.83 386	85.80 341	96.78 236	96.68 290	89.45 278	88.75 337	93.93 366	82.96 227	97.82 340	87.83 296	83.25 407	94.80 378

ACMH+	87.92 14	90.20 336	89.18 345	93.25 318	96.48 244	86.45 325	96.99 209	96.68 290	88.83 301	84.79 403	96.22 242	70.16 391	98.53 254	84.42 358	88.04 348	94.77 383

CANet_DTU		94.37 151	93.65 163	96.55 102	96.46 247	92.13 116	96.21 292	96.67 292	94.38 83	93.53 205	97.03 195	79.34 301	99.71 64	90.76 233	98.45 130	97.82 238

cl____		90.96 311	90.32 299	92.89 332	95.37 314	86.21 331	94.46 376	96.64 293	87.82 333	88.15 354	94.18 354	82.98 225	97.54 367	87.70 301	85.59 372	94.92 368

HY-MVS	89.66 9	93.87 177	92.95 194	96.63 96	97.10 177	92.49 102	95.64 329	96.64 293	89.05 290	93.00 220	95.79 267	85.77 168	99.45 125	89.16 276	94.35 253	97.96 224

Test_1112_low_res		92.84 225	91.84 238	95.85 163	97.04 185	89.97 211	95.53 334	96.64 293	85.38 381	89.65 309	95.18 297	85.86 164	99.10 168	87.70 301	93.58 279	98.49 172

DIV-MVS_self_test		90.97 310	90.33 298	92.88 333	95.36 315	86.19 333	94.46 376	96.63 296	87.82 333	88.18 352	94.23 351	82.99 224	97.53 369	87.72 298	85.57 373	94.93 366

Fast-Effi-MVS+-dtu		92.29 245	91.99 232	93.21 321	95.27 324	85.52 347	97.03 201	96.63 296	92.09 175	89.11 327	95.14 299	80.33 284	98.08 298	87.54 309	94.74 249	96.03 305

UnsupCasMVSNet_bld		82.13 415	79.46 420	90.14 403	88.00 452	82.47 396	90.89 442	96.62 298	78.94 439	75.61 446	84.40 457	56.63 448	96.31 413	77.30 418	66.77 458	91.63 438

cl22		91.21 298	90.56 293	93.14 324	96.09 279	86.80 313	94.41 378	96.58 299	87.80 335	88.58 340	93.99 364	80.85 272	97.62 361	89.87 253	86.93 360	94.99 361

jason		94.84 136	94.39 143	96.18 138	95.52 303	90.93 171	96.09 299	96.52 300	89.28 282	96.01 126	97.32 169	84.70 190	98.77 215	95.15 122	98.91 110	98.85 136
jason: jason.
tt0805		91.09 303	90.07 315	94.16 268	95.61 298	88.31 270	97.56 141	96.51 301	89.56 272	89.17 325	95.64 276	67.08 419	98.38 269	91.07 225	88.44 345	95.80 313

AUN-MVS		91.76 265	90.75 283	94.81 228	97.00 189	88.57 262	96.65 249	96.49 302	89.63 270	92.15 239	96.12 248	78.66 316	98.50 256	90.83 229	79.18 426	97.36 260

hse-mvs2		93.45 196	92.99 190	94.81 228	97.02 187	88.59 261	96.69 245	96.47 303	95.19 35	96.74 86	96.16 246	83.67 208	98.48 259	95.85 99	79.13 427	97.35 262

SD_0403		90.01 340	90.02 318	89.96 406	95.65 297	76.76 441	95.76 320	96.46 304	90.58 244	86.59 386	96.29 238	82.12 248	94.78 435	73.00 440	93.76 272	98.35 189

EG-PatchMatch MVS		87.02 380	85.44 385	91.76 372	92.67 418	85.00 361	96.08 300	96.45 305	83.41 412	79.52 437	93.49 383	57.10 447	97.72 352	79.34 409	90.87 319	92.56 425

KD-MVS_self_test		85.95 394	84.95 392	88.96 417	89.55 443	79.11 435	95.13 356	96.42 306	85.91 374	84.07 412	90.48 428	70.03 393	94.82 434	80.04 401	72.94 447	92.94 418

pmmvs6		87.81 372	86.19 380	92.69 341	91.32 431	86.30 328	97.34 174	96.41 307	80.59 433	84.05 413	94.37 339	67.37 414	97.67 355	84.75 353	79.51 425	94.09 403

PMMVS		92.86 223	92.34 221	94.42 253	94.92 346	86.73 316	94.53 371	96.38 308	84.78 393	94.27 180	95.12 301	83.13 220	98.40 263	91.47 217	96.49 207	98.12 210

RPSCF		90.75 317	90.86 275	90.42 399	96.84 203	76.29 444	95.61 330	96.34 309	83.89 402	91.38 260	97.87 117	76.45 341	98.78 212	87.16 318	92.23 292	96.20 294

BP-MVS1		95.89 96	95.49 96	97.08 79	96.67 222	93.20 75	98.08 56	96.32 310	94.56 71	96.32 111	97.84 122	84.07 203	99.15 160	96.75 61	98.78 113	98.90 125

MSDG		91.42 285	90.24 305	94.96 221	97.15 175	88.91 254	93.69 407	96.32 310	85.72 377	86.93 382	96.47 229	80.24 285	98.98 189	80.57 398	95.05 242	96.98 273

WBMVS		90.69 322	89.99 319	92.81 336	96.48 244	85.00 361	95.21 353	96.30 312	89.46 277	89.04 328	94.05 361	72.45 374	97.82 340	89.46 263	87.41 357	95.61 324

OurMVSNet-221017-0		90.51 327	90.19 310	91.44 378	93.41 403	81.25 406	96.98 210	96.28 313	91.68 187	86.55 387	96.30 237	74.20 363	97.98 314	88.96 279	87.40 358	95.09 357

MVP-Stereo		90.74 318	90.08 312	92.71 340	93.19 408	88.20 276	95.86 313	96.27 314	86.07 372	84.86 402	94.76 316	77.84 330	97.75 350	83.88 367	98.01 150	92.17 435
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 129	94.56 133	96.29 130	96.34 256	91.21 155	95.83 315	96.27 314	88.93 297	96.22 116	96.88 202	86.20 159	98.85 202	95.27 118	99.05 101	98.82 140

BH-untuned		92.94 218	92.62 210	93.92 288	97.22 169	86.16 334	96.40 273	96.25 316	90.06 259	89.79 303	96.17 245	83.19 217	98.35 271	87.19 316	97.27 177	97.24 267

CL-MVSNet_self_test		86.31 389	85.15 389	89.80 408	88.83 447	81.74 404	93.93 396	96.22 317	86.67 360	85.03 400	90.80 426	78.09 326	94.50 436	74.92 429	71.86 449	93.15 416

IS-MVSNet		94.90 131	94.52 137	96.05 145	97.67 144	90.56 185	98.44 24	96.22 317	93.21 124	93.99 190	97.74 133	85.55 173	98.45 260	89.98 249	97.86 154	99.14 86

FA-MVS(test-final)		93.52 191	92.92 195	95.31 200	96.77 216	88.54 264	94.82 363	96.21 319	89.61 271	94.20 183	95.25 295	83.24 215	99.14 163	90.01 248	96.16 212	98.25 198

GA-MVS		91.38 287	90.31 300	94.59 239	94.65 360	87.62 293	94.34 381	96.19 320	90.73 231	90.35 283	93.83 367	71.84 377	97.96 321	87.22 315	93.61 277	98.21 201

LuminaMVS		94.89 132	94.35 145	96.53 103	95.48 305	92.80 89	96.88 222	96.18 321	92.85 149	95.92 129	96.87 204	81.44 261	98.83 205	96.43 74	97.10 184	97.94 226

IterMVS-SCA-FT		90.31 330	89.81 326	91.82 367	95.52 303	84.20 373	94.30 384	96.15 322	90.61 241	87.39 368	94.27 348	75.80 347	96.44 410	87.34 312	86.88 364	94.82 375

IterMVS		90.15 338	89.67 332	91.61 374	95.48 305	83.72 379	94.33 382	96.12 323	89.99 260	87.31 371	94.15 356	75.78 349	96.27 414	86.97 321	86.89 363	94.83 373
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 228	91.51 252	96.52 105	98.77 60	90.99 167	97.38 171	96.08 324	82.38 418	89.29 321	97.87 117	83.77 206	99.69 70	81.37 391	96.69 198	98.89 131

pmmvs4		90.93 312	89.85 324	94.17 265	93.34 405	90.79 177	94.60 368	96.02 325	84.62 394	87.45 365	95.15 298	81.88 255	97.45 376	87.70 301	87.87 350	94.27 400

ppachtmachnet_test		88.35 367	87.29 366	91.53 375	92.45 424	83.57 382	93.75 403	95.97 326	84.28 397	85.32 399	94.18 354	79.00 313	96.93 398	75.71 425	84.99 386	94.10 401

Anonymous20240521		86.42 387	85.44 385	89.34 415	90.33 436	79.79 426	96.73 239	95.92 327	83.71 407	83.25 418	91.36 423	63.92 433	96.01 415	78.39 413	85.36 377	92.22 433

ITE_SJBPF				92.43 345	95.34 317	85.37 354		95.92 327	91.47 196	87.75 361	96.39 234	71.00 383	97.96 321	82.36 381	89.86 329	93.97 406

test_fmvs2		89.77 349	89.93 321	89.31 416	93.68 391	76.37 443	97.64 130	95.90 329	89.84 266	91.49 258	96.26 241	58.77 443	97.10 390	94.65 141	91.13 312	94.46 391

USDC		88.94 358	87.83 363	92.27 352	94.66 359	84.96 363	93.86 399	95.90 329	87.34 349	83.40 416	95.56 280	67.43 413	98.19 284	82.64 380	89.67 331	93.66 409

COLMAP_ROB	87.81 15	90.40 329	89.28 342	93.79 293	97.95 126	87.13 307	96.92 216	95.89 331	82.83 415	86.88 384	97.18 180	73.77 367	99.29 143	78.44 412	93.62 276	94.95 362
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 179	93.08 188	96.02 148	97.88 132	89.96 212	97.72 115	95.85 332	92.43 161	95.86 131	98.44 61	68.42 409	99.39 131	96.31 76	94.85 243	98.71 153

VDDNet		93.05 212	92.07 227	96.02 148	96.84 203	90.39 193	98.08 56	95.85 332	86.22 370	95.79 134	98.46 59	67.59 412	99.19 151	94.92 129	94.85 243	98.47 175

mvsmamba		94.57 146	94.14 150	95.87 159	97.03 186	89.93 213	97.84 92	95.85 332	91.34 202	94.79 165	96.80 205	80.67 275	98.81 208	94.85 130	98.12 145	98.85 136

Vis-MVSNet (Re-imp)		94.15 159	93.88 156	94.95 222	97.61 152	87.92 285	98.10 54	95.80 335	92.22 167	93.02 219	97.45 160	84.53 193	97.91 333	88.24 289	97.97 151	99.02 101

MM		97.29 29	96.98 40	98.23 12	98.01 120	95.03 27	98.07 58	95.76 336	97.78 1	97.52 59	98.80 37	88.09 117	99.86 9	99.44 2	99.37 65	99.80 1

KD-MVS_2432*1600		84.81 404	82.64 407	91.31 380	91.07 433	85.34 355	91.22 437	95.75 337	85.56 379	83.09 419	90.21 431	67.21 415	95.89 417	77.18 419	62.48 462	92.69 421

miper_refine_blended		84.81 404	82.64 407	91.31 380	91.07 433	85.34 355	91.22 437	95.75 337	85.56 379	83.09 419	90.21 431	67.21 415	95.89 417	77.18 419	62.48 462	92.69 421

FE-MVS		92.05 256	91.05 268	95.08 209	96.83 205	87.93 284	93.91 398	95.70 339	86.30 367	94.15 187	94.97 304	76.59 339	99.21 149	84.10 361	96.86 189	98.09 216

tpm cat1		88.36 366	87.21 369	91.81 368	95.13 336	80.55 415	92.58 428	95.70 339	74.97 448	87.45 365	91.96 416	78.01 329	98.17 286	80.39 400	88.74 342	96.72 283

our_test_3		88.78 362	87.98 362	91.20 384	92.45 424	82.53 393	93.61 411	95.69 341	85.77 376	84.88 401	93.71 372	79.99 290	96.78 406	79.47 406	86.24 366	94.28 399

BH-w/o		92.14 253	91.75 241	93.31 316	96.99 190	85.73 344	95.67 324	95.69 341	88.73 307	89.26 323	94.82 314	82.97 226	98.07 302	85.26 348	96.32 211	96.13 301

CR-MVSNet		90.82 315	89.77 328	93.95 282	94.45 368	87.19 304	90.23 445	95.68 343	86.89 357	92.40 229	92.36 408	80.91 269	97.05 393	81.09 395	93.95 269	97.60 250

Patchmtry		88.64 364	87.25 367	92.78 338	94.09 378	86.64 317	89.82 449	95.68 343	80.81 430	87.63 363	92.36 408	80.91 269	97.03 394	78.86 410	85.12 382	94.67 386

testing91		91.90 261	91.02 269	94.53 247	96.54 235	86.55 323	95.86 313	95.64 345	91.77 184	91.89 248	93.47 385	69.94 394	98.86 200	90.23 247	93.86 271	98.18 203

BH-RMVSNet		92.72 230	91.97 233	94.97 220	97.16 173	87.99 283	96.15 297	95.60 346	90.62 240	91.87 249	97.15 183	78.41 320	98.57 251	83.16 370	97.60 161	98.36 187

PVSNet_0	82.17 19	85.46 399	83.64 402	90.92 388	95.27 324	79.49 431	90.55 443	95.60 346	83.76 406	83.00 421	89.95 433	71.09 382	97.97 317	82.75 378	60.79 464	95.31 344

guyue		95.17 122	94.96 118	95.82 165	96.97 192	89.65 220	97.56 141	95.58 348	94.82 56	95.72 136	97.42 164	82.90 228	98.84 204	96.71 64	96.93 188	98.96 112

SCA		91.84 263	91.18 265	93.83 290	95.59 299	84.95 364	94.72 365	95.58 348	90.82 227	92.25 237	93.69 374	75.80 347	98.10 293	86.20 330	95.98 214	98.45 177

MonoMVSNet		91.92 259	91.77 239	92.37 346	92.94 412	83.11 387	97.09 199	95.55 350	92.91 145	90.85 275	94.55 327	81.27 265	96.52 409	93.01 186	87.76 351	97.47 256

AllTest		90.23 334	88.98 348	93.98 278	97.94 127	86.64 317	96.51 262	95.54 351	85.38 381	85.49 396	96.77 207	70.28 389	99.15 160	80.02 402	92.87 281	96.15 299

TestCases				93.98 278	97.94 127	86.64 317		95.54 351	85.38 381	85.49 396	96.77 207	70.28 389	99.15 160	80.02 402	92.87 281	96.15 299

mmtdpeth		89.70 351	88.96 349	91.90 363	95.84 291	84.42 369	97.46 161	95.53 353	90.27 253	94.46 176	90.50 427	69.74 398	98.95 190	97.39 50	69.48 453	92.34 429

tpmvs		89.83 348	89.15 346	91.89 364	94.92 346	80.30 419	93.11 420	95.46 354	86.28 368	88.08 355	92.65 398	80.44 281	98.52 255	81.47 387	89.92 328	96.84 279

pmmvs5		89.86 347	88.87 352	92.82 335	92.86 414	86.23 330	96.26 287	95.39 355	84.24 398	87.12 373	94.51 330	74.27 362	97.36 383	87.61 308	87.57 353	94.86 371

PatchmatchNet		91.91 260	91.35 254	93.59 304	95.38 312	84.11 374	93.15 419	95.39 355	89.54 273	92.10 242	93.68 376	82.82 231	98.13 288	84.81 352	95.32 235	98.52 167
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 284	91.32 256	91.79 369	95.15 334	79.20 434	93.42 414	95.37 357	88.55 312	93.49 208	93.67 377	82.49 240	98.27 277	90.41 242	89.34 334	97.90 228

Anonymous20231206		87.09 379	86.14 381	89.93 407	91.22 432	80.35 417	96.11 298	95.35 358	83.57 409	84.16 408	93.02 393	73.54 369	95.61 425	72.16 442	86.14 368	93.84 408

MIMVSNet1		84.93 402	83.05 404	90.56 397	89.56 442	84.84 366	95.40 339	95.35 358	83.91 401	80.38 433	92.21 413	57.23 446	93.34 449	70.69 448	82.75 413	93.50 411

TDRefinement		86.53 383	84.76 395	91.85 365	82.23 465	84.25 371	96.38 275	95.35 358	84.97 390	84.09 411	94.94 306	65.76 428	98.34 274	84.60 356	74.52 443	92.97 417

TR-MVS		91.48 283	90.59 291	94.16 268	96.40 250	87.33 297	95.67 324	95.34 361	87.68 341	91.46 259	95.52 283	76.77 338	98.35 271	82.85 375	93.61 277	96.79 281

EPNet_dtu		91.71 266	91.28 259	92.99 328	93.76 388	83.71 380	96.69 245	95.28 362	93.15 131	87.02 378	95.95 256	83.37 214	97.38 382	79.46 407	96.84 190	97.88 230
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 376	85.79 383	91.78 370	94.80 353	87.28 299	95.49 336	95.28 362	84.09 400	83.85 415	91.82 417	62.95 436	94.17 440	78.48 411	85.34 378	93.91 407

MDTV_nov1_ep13			90.76 281		95.22 328	80.33 418	93.03 422	95.28 362	88.14 325	92.84 226	93.83 367	81.34 262	98.08 298	82.86 373	94.34 254

LF4IMVS		87.94 370	87.25 367	89.98 405	92.38 426	80.05 425	94.38 379	95.25 365	87.59 343	84.34 405	94.74 318	64.31 432	97.66 357	84.83 351	87.45 354	92.23 432

TransMVSNet (Re)		88.94 358	87.56 364	93.08 326	94.35 371	88.45 268	97.73 112	95.23 366	87.47 345	84.26 407	95.29 290	79.86 293	97.33 384	79.44 408	74.44 444	93.45 413

test20.03		86.14 392	85.40 387	88.35 418	90.12 437	80.06 424	95.90 312	95.20 367	88.59 308	81.29 428	93.62 379	71.43 380	92.65 453	71.26 446	81.17 418	92.34 429

new-patchmatchnet		83.18 411	81.87 414	87.11 426	86.88 456	75.99 445	93.70 405	95.18 368	85.02 389	77.30 445	88.40 444	65.99 426	93.88 445	74.19 434	70.18 451	91.47 443

MDA-MVSNet_test_wron		85.87 396	84.23 399	90.80 394	92.38 426	82.57 392	93.17 417	95.15 369	82.15 419	67.65 457	92.33 411	78.20 322	95.51 428	77.33 416	79.74 422	94.31 398

YYNet1		85.87 396	84.23 399	90.78 395	92.38 426	82.46 397	93.17 417	95.14 370	82.12 420	67.69 455	92.36 408	78.16 325	95.50 429	77.31 417	79.73 423	94.39 394

Baseline_NR-MVSNet		91.20 299	90.62 289	92.95 330	93.83 386	88.03 282	97.01 206	95.12 371	88.42 316	89.70 306	95.13 300	83.47 211	97.44 377	89.66 259	83.24 408	93.37 414

thres200		92.23 249	91.39 253	94.75 235	97.61 152	89.03 252	96.60 257	95.09 372	92.08 176	93.28 214	94.00 363	78.39 321	99.04 186	81.26 394	94.18 260	96.19 295

ADS-MVSNet		89.89 344	88.68 354	93.53 308	95.86 286	84.89 365	90.93 440	95.07 373	83.23 413	91.28 268	91.81 418	79.01 311	97.85 336	79.52 404	91.39 308	97.84 235

pmmvs-eth3d		86.22 390	84.45 397	91.53 375	88.34 451	87.25 301	94.47 374	95.01 374	83.47 410	79.51 438	89.61 436	69.75 397	95.71 422	83.13 371	76.73 436	91.64 437

Anonymous202405211		92.07 255	90.83 279	95.76 170	98.19 106	88.75 257	97.58 137	95.00 375	86.00 373	93.64 200	97.45 160	66.24 424	99.53 109	90.68 236	92.71 286	99.01 104

MDA-MVSNet-bldmvs		85.00 401	82.95 406	91.17 386	93.13 410	83.33 383	94.56 370	95.00 375	84.57 395	65.13 461	92.65 398	70.45 388	95.85 419	73.57 437	77.49 432	94.33 396

ambc				86.56 429	83.60 462	70.00 456	85.69 461	94.97 377		80.60 432	88.45 443	37.42 464	96.84 403	82.69 379	75.44 441	92.86 419

testgi		87.97 369	87.21 369	90.24 402	92.86 414	80.76 410	96.67 248	94.97 377	91.74 185	85.52 395	95.83 262	62.66 438	94.47 438	76.25 423	88.36 346	95.48 327

myMVS_eth3d28		91.52 280	90.97 271	93.17 322	96.91 195	83.24 385	95.61 330	94.96 379	92.24 166	91.98 245	93.28 390	69.31 399	98.40 263	88.71 284	95.68 224	97.88 230

dp		88.90 360	88.26 360	90.81 392	94.58 364	76.62 442	92.85 425	94.93 380	85.12 387	90.07 297	93.07 392	75.81 346	98.12 291	80.53 399	87.42 356	97.71 242

test_fmvs3		83.21 410	83.02 405	83.78 433	86.77 457	68.34 459	96.76 237	94.91 381	86.49 363	84.14 410	89.48 437	36.04 465	91.73 455	91.86 207	80.77 420	91.26 445

test_0402		86.46 386	84.79 394	91.45 377	95.02 340	85.55 346	96.29 286	94.89 382	80.90 427	82.21 424	93.97 365	68.21 410	97.29 386	62.98 456	88.68 343	91.51 440

tfpn200view9		92.38 239	91.52 250	94.95 222	97.85 133	89.29 241	97.41 164	94.88 383	92.19 172	93.27 215	94.46 335	78.17 323	99.08 174	81.40 388	94.08 264	96.48 288

CVMVSNet		91.23 297	91.75 241	89.67 409	95.77 292	74.69 446	96.44 263	94.88 383	85.81 375	92.18 238	97.64 146	79.07 306	95.58 427	88.06 292	95.86 219	98.74 150

thres400		92.42 237	91.52 250	95.12 208	97.85 133	89.29 241	97.41 164	94.88 383	92.19 172	93.27 215	94.46 335	78.17 323	99.08 174	81.40 388	94.08 264	96.98 273

tt0320		85.39 400	83.12 403	92.19 356	93.44 402	85.79 342	96.19 294	94.87 386	71.19 455	82.92 422	91.76 420	58.43 444	96.81 404	81.03 396	78.26 431	93.98 405

EPNet		95.20 120	94.56 133	97.14 73	92.80 416	92.68 95	97.85 91	94.87 386	96.64 8	92.46 228	97.80 128	86.23 156	99.65 76	93.72 165	98.62 121	99.10 93
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 271	90.72 286	94.32 258	96.48 244	86.11 339	95.81 316	94.76 388	91.55 189	91.75 253	93.44 386	68.55 407	98.82 206	90.43 241	93.69 273	98.04 220

sc_t1		86.48 385	84.10 401	93.63 301	93.45 401	85.76 343	96.79 232	94.71 389	73.06 453	86.45 388	94.35 340	55.13 451	97.95 325	84.38 359	78.55 430	97.18 269

SixPastTwentyTwo		89.15 356	88.54 356	90.98 387	93.49 398	80.28 421	96.70 243	94.70 390	90.78 228	84.15 409	95.57 279	71.78 378	97.71 353	84.63 355	85.07 383	94.94 364

thres100view900		92.43 236	91.58 247	94.98 218	97.92 129	89.37 237	97.71 117	94.66 391	92.20 170	93.31 213	94.90 309	78.06 327	99.08 174	81.40 388	94.08 264	96.48 288

thres600view7		92.49 234	91.60 246	95.18 204	97.91 130	89.47 231	97.65 126	94.66 391	92.18 174	93.33 212	94.91 308	78.06 327	99.10 168	81.61 384	94.06 268	96.98 273

PatchT		88.87 361	87.42 365	93.22 320	94.08 379	85.10 359	89.51 450	94.64 393	81.92 421	92.36 232	88.15 447	80.05 289	97.01 396	72.43 441	93.65 275	97.54 253

baseline1		92.82 226	91.90 236	95.55 186	97.20 171	90.77 178	97.19 191	94.58 394	92.20 170	92.36 232	96.34 236	84.16 201	98.21 281	89.20 274	83.90 403	97.68 244

AstraMVS		94.82 138	94.64 129	95.34 199	96.36 255	88.09 281	97.58 137	94.56 395	94.98 45	95.70 139	97.92 111	81.93 254	98.93 193	96.87 58	95.88 217	98.99 108

UBG		91.55 277	90.76 281	93.94 284	96.52 240	85.06 360	95.22 351	94.54 396	90.47 249	91.98 245	92.71 397	72.02 375	98.74 222	88.10 291	95.26 237	98.01 222

Gipuma		67.86 431	65.41 433	75.18 446	92.66 419	73.45 450	66.50 468	94.52 397	53.33 466	57.80 467	66.07 467	30.81 467	89.20 459	48.15 465	78.88 429	62.90 467
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 269	90.75 283	94.47 249	96.53 237	86.56 322	95.76 320	94.51 398	91.10 220	91.24 270	93.59 380	68.59 406	98.86 200	91.10 224	94.29 256	98.00 223

CostFormer		91.18 302	90.70 287	92.62 343	94.84 351	81.76 403	94.09 391	94.43 399	84.15 399	92.72 227	93.77 371	79.43 300	98.20 282	90.70 235	92.18 295	97.90 228

tpm2		89.96 341	89.21 344	92.23 355	94.91 348	81.25 406	93.78 402	94.42 400	80.62 432	91.56 256	93.44 386	76.44 342	97.94 327	85.60 342	92.08 299	97.49 254

testing3-2		92.10 254	92.05 228	92.27 352	97.71 142	79.56 428	97.42 163	94.41 401	93.53 111	93.22 217	95.49 284	69.16 401	99.11 166	93.25 176	94.22 258	98.13 208

MGCNet		96.74 62	96.31 79	98.02 20	96.87 199	94.65 31	97.58 137	94.39 402	96.47 11	97.16 71	98.39 65	87.53 134	99.87 7	98.97 19	99.41 57	99.55 41

JIA-IIPM		88.26 368	87.04 372	91.91 362	93.52 396	81.42 405	89.38 451	94.38 403	80.84 429	90.93 274	80.74 459	79.22 303	97.92 330	82.76 377	91.62 303	96.38 291

dmvs_re		90.21 335	89.50 337	92.35 347	95.47 309	85.15 357	95.70 323	94.37 404	90.94 226	88.42 342	93.57 381	74.63 359	95.67 424	82.80 376	89.57 332	96.22 293

Patchmatch-test		89.42 354	87.99 361	93.70 298	95.27 324	85.11 358	88.98 452	94.37 404	81.11 426	87.10 376	93.69 374	82.28 244	97.50 372	74.37 432	94.76 247	98.48 174

LCM-MVSNet		72.55 424	69.39 428	82.03 435	70.81 475	65.42 464	90.12 447	94.36 406	55.02 465	65.88 459	81.72 458	24.16 473	89.96 456	74.32 433	68.10 456	90.71 448

ADS-MVSNet2		89.45 353	88.59 355	92.03 359	95.86 286	82.26 399	90.93 440	94.32 407	83.23 413	91.28 268	91.81 418	79.01 311	95.99 416	79.52 404	91.39 308	97.84 235

mvs5depth		86.53 383	85.08 390	90.87 389	88.74 449	82.52 394	91.91 433	94.23 408	86.35 366	87.11 375	93.70 373	66.52 420	97.76 348	81.37 391	75.80 438	92.31 431

EU-MVSNet		88.72 363	88.90 351	88.20 420	93.15 409	74.21 448	96.63 254	94.22 409	85.18 385	87.32 370	95.97 254	76.16 344	94.98 433	85.27 347	86.17 367	95.41 334

tt0320-xc		84.83 403	82.33 411	92.31 350	93.66 392	86.20 332	96.17 296	94.06 410	71.26 454	82.04 426	92.22 412	55.07 452	96.72 407	81.49 386	75.04 442	94.02 404

MIMVSNet		88.50 365	86.76 375	93.72 297	94.84 351	87.77 291	91.39 435	94.05 411	86.41 365	87.99 357	92.59 401	63.27 434	95.82 421	77.44 415	92.84 283	97.57 252

OpenMVS_ROB	81.14 20	84.42 406	82.28 412	90.83 390	90.06 438	84.05 376	95.73 322	94.04 412	73.89 451	80.17 436	91.53 422	59.15 442	97.64 358	66.92 454	89.05 336	90.80 447

TinyColmap		86.82 381	85.35 388	91.21 382	94.91 348	82.99 389	93.94 395	94.02 413	83.58 408	81.56 427	94.68 320	62.34 439	98.13 288	75.78 424	87.35 359	92.52 427

ETVMVS		90.52 326	89.14 347	94.67 238	96.81 209	87.85 289	95.91 311	93.97 414	89.71 269	92.34 235	92.48 403	65.41 430	97.96 321	81.37 391	94.27 257	98.21 201

IB-MVS	87.33 17	89.91 342	88.28 359	94.79 232	95.26 327	87.70 292	95.12 357	93.95 415	89.35 281	87.03 377	92.49 402	70.74 386	99.19 151	89.18 275	81.37 417	97.49 254
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
Syy-MVS		87.13 378	87.02 373	87.47 424	95.16 331	73.21 452	95.00 359	93.93 416	88.55 312	86.96 379	91.99 414	75.90 345	94.00 442	61.59 458	94.11 261	95.20 352

myMVS_eth3d		87.18 377	86.38 378	89.58 410	95.16 331	79.53 429	95.00 359	93.93 416	88.55 312	86.96 379	91.99 414	56.23 449	94.00 442	75.47 428	94.11 261	95.20 352

testing222		90.31 330	88.96 349	94.35 255	96.54 235	87.29 298	95.50 335	93.84 418	90.97 223	91.75 253	92.96 394	62.18 440	98.00 312	82.86 373	94.08 264	97.76 240

test_f		80.57 417	79.62 419	83.41 434	83.38 463	67.80 461	93.57 412	93.72 419	80.80 431	77.91 444	87.63 450	33.40 466	92.08 454	87.14 319	79.04 428	90.34 449

LCM-MVSNet-Re		92.50 232	92.52 216	92.44 344	96.82 207	81.89 402	96.92 216	93.71 420	92.41 162	84.30 406	94.60 325	85.08 182	97.03 394	91.51 215	97.36 170	98.40 183

tpm		90.25 333	89.74 331	91.76 372	93.92 382	79.73 427	93.98 392	93.54 421	88.28 319	91.99 244	93.25 391	77.51 333	97.44 377	87.30 314	87.94 349	98.12 210

ET-MVSNet_ETH3D		91.49 282	90.11 311	95.63 180	96.40 250	91.57 140	95.34 342	93.48 422	90.60 243	75.58 447	95.49 284	80.08 288	96.79 405	94.25 153	89.76 330	98.52 167

LFMVS		93.60 186	92.63 209	96.52 105	98.13 112	91.27 152	97.94 78	93.39 423	90.57 245	96.29 113	98.31 78	69.00 402	99.16 158	94.18 154	95.87 218	99.12 90

MVStest1		82.38 414	80.04 418	89.37 413	87.63 454	82.83 390	95.03 358	93.37 424	73.90 450	73.50 452	94.35 340	62.89 437	93.25 451	73.80 435	65.92 459	92.04 436

FE-MVSNET		83.85 407	81.97 413	89.51 411	87.19 455	83.19 386	95.21 353	93.17 425	83.45 411	78.90 440	89.05 440	65.46 429	93.84 446	69.71 450	75.56 440	91.51 440

Patchmatch-RL test		87.38 375	86.24 379	90.81 392	88.74 449	78.40 438	88.12 459	93.17 425	87.11 354	82.17 425	89.29 438	81.95 252	95.60 426	88.64 286	77.02 433	98.41 182

ttmdpeth		85.91 395	84.76 395	89.36 414	89.14 444	80.25 422	95.66 327	93.16 427	83.77 405	83.39 417	95.26 294	66.24 424	95.26 432	80.65 397	75.57 439	92.57 424

test-LLR		91.42 285	91.19 264	92.12 357	94.59 362	80.66 412	94.29 385	92.98 428	91.11 218	90.76 277	92.37 405	79.02 309	98.07 302	88.81 281	96.74 195	97.63 245

test-mter		90.19 337	89.54 336	92.12 357	94.59 362	80.66 412	94.29 385	92.98 428	87.68 341	90.76 277	92.37 405	67.67 411	98.07 302	88.81 281	96.74 195	97.63 245

WB-MVSnew		89.88 345	89.56 335	90.82 391	94.57 365	83.06 388	95.65 328	92.85 430	87.86 332	90.83 276	94.10 357	79.66 297	96.88 401	76.34 422	94.19 259	92.54 426

testing3		87.67 373	86.88 374	90.05 404	96.14 273	80.71 411	97.10 198	92.85 430	90.15 257	87.54 364	94.55 327	55.70 450	94.10 441	73.77 436	94.10 263	95.35 341

test_method		66.11 432	64.89 434	69.79 449	72.62 473	35.23 481	65.19 469	92.83 432	20.35 471	65.20 460	88.08 448	43.14 462	82.70 466	73.12 439	63.46 461	91.45 444

test0.0.03 1		89.37 355	88.70 353	91.41 379	92.47 423	85.63 345	95.22 351	92.70 433	91.11 218	86.91 383	93.65 378	79.02 309	93.19 452	78.00 414	89.18 335	95.41 334

new_pmnet		82.89 412	81.12 417	88.18 421	89.63 441	80.18 423	91.77 434	92.57 434	76.79 446	75.56 448	88.23 446	61.22 441	94.48 437	71.43 444	82.92 411	89.87 450

mvsany_test1		93.93 175	93.98 154	93.78 294	94.94 345	86.80 313	94.62 367	92.55 435	88.77 306	96.85 81	98.49 55	88.98 99	98.08 298	95.03 124	95.62 226	96.46 290

thisisatest0515		92.29 245	91.30 258	95.25 202	96.60 226	88.90 255	94.36 380	92.32 436	87.92 329	93.43 210	94.57 326	77.28 334	99.00 187	89.42 265	95.86 219	97.86 234

thisisatest0530		93.03 213	92.21 225	95.49 191	97.07 178	89.11 250	97.49 158	92.19 437	90.16 256	94.09 188	96.41 232	76.43 343	99.05 183	90.38 243	95.68 224	98.31 195

tttt0517		92.96 216	92.33 222	94.87 225	97.11 176	87.16 306	97.97 74	92.09 438	90.63 239	93.88 194	97.01 196	76.50 340	99.06 180	90.29 246	95.45 233	98.38 185

K. test v3		87.64 374	86.75 376	90.32 401	93.02 411	79.48 432	96.61 255	92.08 439	90.66 237	80.25 435	94.09 359	67.21 415	96.65 408	85.96 338	80.83 419	94.83 373

TESTMET0.1,1		90.06 339	89.42 339	91.97 360	94.41 370	80.62 414	94.29 385	91.97 440	87.28 351	90.44 281	92.47 404	68.79 403	97.67 355	88.50 288	96.60 201	97.61 249

PM-MVS		83.48 409	81.86 415	88.31 419	87.83 453	77.59 440	93.43 413	91.75 441	86.91 356	80.63 431	89.91 434	44.42 461	95.84 420	85.17 350	76.73 436	91.50 442

baseline2		91.63 270	90.86 275	93.94 284	94.33 372	86.32 327	95.92 310	91.64 442	89.37 280	86.94 381	94.69 319	81.62 259	98.69 232	88.64 286	94.57 252	96.81 280

APD_test1		79.31 419	77.70 422	84.14 432	89.11 446	69.07 458	92.36 432	91.50 443	69.07 457	73.87 450	92.63 400	39.93 463	94.32 439	70.54 449	80.25 421	89.02 452

FPMVS		71.27 425	69.85 427	75.50 445	74.64 470	59.03 470	91.30 436	91.50 443	58.80 462	57.92 466	88.28 445	29.98 469	85.53 465	53.43 463	82.84 412	81.95 458

door								91.13 445

door-mid								91.06 446

EGC-MVSNET		68.77 430	63.01 436	86.07 431	92.49 422	82.24 400	93.96 394	90.96 447	0.71 476	2.62 477	90.89 425	53.66 453	93.46 447	57.25 461	84.55 393	82.51 457

mvsany_test3		83.59 408	82.44 410	87.03 427	83.80 460	73.82 449	93.70 405	90.92 448	86.42 364	82.51 423	90.26 430	46.76 460	95.71 422	90.82 230	76.76 435	91.57 439

pmmvs3		79.97 418	77.50 423	87.39 425	82.80 464	79.38 433	92.70 427	90.75 449	70.69 456	78.66 441	87.47 452	51.34 456	93.40 448	73.39 438	69.65 452	89.38 451

UWE-MVS		89.91 342	89.48 338	91.21 382	95.88 285	78.23 439	94.91 362	90.26 450	89.11 287	92.35 234	94.52 329	68.76 404	97.96 321	83.95 365	95.59 227	97.42 258

DSMNet-mixed		86.34 388	86.12 382	87.00 428	89.88 440	70.43 454	94.93 361	90.08 451	77.97 443	85.42 398	92.78 396	74.44 361	93.96 444	74.43 431	95.14 238	96.62 284

MVS-HIRNet		82.47 413	81.21 416	86.26 430	95.38 312	69.21 457	88.96 453	89.49 452	66.28 459	80.79 430	74.08 464	68.48 408	97.39 381	71.93 443	95.47 232	92.18 434

WB-MVS		76.77 421	76.63 424	77.18 440	85.32 458	56.82 472	94.53 371	89.39 453	82.66 417	71.35 453	89.18 439	75.03 354	88.88 460	35.42 469	66.79 457	85.84 454

test1111		93.19 205	92.82 199	94.30 261	97.58 158	84.56 368	98.21 45	89.02 454	93.53 111	94.58 170	98.21 85	72.69 371	99.05 183	93.06 182	98.48 128	99.28 75

SSC-MVS		76.05 422	75.83 425	76.72 444	84.77 459	56.22 473	94.32 383	88.96 455	81.82 423	70.52 454	88.91 441	74.79 358	88.71 461	33.69 470	64.71 460	85.23 455

ECVR-MVS		93.19 205	92.73 205	94.57 244	97.66 146	85.41 351	98.21 45	88.23 456	93.43 117	94.70 167	98.21 85	72.57 372	99.07 178	93.05 183	98.49 126	99.25 78

EPMVS		90.70 320	89.81 326	93.37 314	94.73 357	84.21 372	93.67 408	88.02 457	89.50 275	92.38 231	93.49 383	77.82 331	97.78 345	86.03 336	92.68 287	98.11 215

ANet_high		63.94 434	59.58 437	77.02 441	61.24 477	66.06 462	85.66 462	87.93 458	78.53 441	42.94 469	71.04 466	25.42 472	80.71 468	52.60 464	30.83 470	84.28 456

PMMVS2		70.19 426	66.92 430	80.01 436	76.35 469	65.67 463	86.22 460	87.58 459	64.83 461	62.38 462	80.29 461	26.78 471	88.49 463	63.79 455	54.07 466	85.88 453

lessismore_v0				90.45 398	91.96 429	79.09 436		87.19 460		80.32 434	94.39 337	66.31 423	97.55 366	84.00 364	76.84 434	94.70 385

PMVS	53.92 22	58.58 435	55.40 438	68.12 450	51.00 478	48.64 475	78.86 465	87.10 461	46.77 467	35.84 473	74.28 463	8.76 477	86.34 464	42.07 467	73.91 445	69.38 464
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 382	86.41 377	88.02 422	92.87 413	74.60 447	95.38 341	86.70 462	88.17 322	87.28 372	94.67 322	70.83 385	93.30 450	67.45 452	94.31 255	96.17 296

test_vis1_rt		86.16 391	85.06 391	89.46 412	93.47 400	80.46 416	96.41 269	86.61 463	85.22 384	79.15 439	88.64 442	52.41 455	97.06 392	93.08 181	90.57 321	90.87 446

testf1		69.31 428	66.76 431	76.94 442	78.61 467	61.93 466	88.27 457	86.11 464	55.62 463	59.69 463	85.31 455	20.19 475	89.32 457	57.62 459	69.44 454	79.58 459

APD_test2		69.31 428	66.76 431	76.94 442	78.61 467	61.93 466	88.27 457	86.11 464	55.62 463	59.69 463	85.31 455	20.19 475	89.32 457	57.62 459	69.44 454	79.58 459

gg-mvs-nofinetune		87.82 371	85.61 384	94.44 251	94.46 367	89.27 244	91.21 439	84.61 466	80.88 428	89.89 301	74.98 462	71.50 379	97.53 369	85.75 341	97.21 179	96.51 286

dmvs_testset		81.38 416	82.60 409	77.73 439	91.74 430	51.49 474	93.03 422	84.21 467	89.07 288	78.28 443	91.25 424	76.97 336	88.53 462	56.57 462	82.24 414	93.16 415

GG-mvs-BLEND				93.62 302	93.69 390	89.20 246	92.39 431	83.33 468		87.98 358	89.84 435	71.00 383	96.87 402	82.08 383	95.40 234	94.80 378

MTMP							97.86 88	82.03 469

DeepMVS_CX				74.68 447	90.84 435	64.34 465		81.61 470	65.34 460	67.47 458	88.01 449	48.60 459	80.13 469	62.33 457	73.68 446	79.58 459

E-PMN		53.28 436	52.56 440	55.43 453	74.43 471	47.13 476	83.63 464	76.30 471	42.23 468	42.59 470	62.22 469	28.57 470	74.40 470	31.53 471	31.51 469	44.78 468

test2506		91.60 272	90.78 280	94.04 274	97.66 146	83.81 377	98.27 35	75.53 472	93.43 117	95.23 153	98.21 85	67.21 415	99.07 178	93.01 186	98.49 126	99.25 78

EMVS		52.08 438	51.31 441	54.39 454	72.62 473	45.39 478	83.84 463	75.51 473	41.13 469	40.77 471	59.65 470	30.08 468	73.60 471	28.31 473	29.90 471	44.18 469

test_vis3_rt		72.73 423	70.55 426	79.27 437	80.02 466	68.13 460	93.92 397	74.30 474	76.90 445	58.99 465	73.58 465	20.29 474	95.37 430	84.16 360	72.80 448	74.31 462

MVE	50.73 23	53.25 437	48.81 442	66.58 452	65.34 476	57.50 471	72.49 467	70.94 475	40.15 470	39.28 472	63.51 468	6.89 479	73.48 472	38.29 468	42.38 468	68.76 466
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 439	53.82 439	46.29 455	33.73 479	45.30 479	78.32 466	67.24 476	18.02 472	50.93 468	87.05 453	52.99 454	53.11 474	70.76 447	25.29 472	40.46 470

kuosan		65.27 433	64.66 435	67.11 451	83.80 460	61.32 469	88.53 456	60.77 477	68.22 458	67.67 456	80.52 460	49.12 458	70.76 473	29.67 472	53.64 467	69.26 465

dongtai		69.99 427	69.33 429	71.98 448	88.78 448	61.64 468	89.86 448	59.93 478	75.67 447	74.96 449	85.45 454	50.19 457	81.66 467	43.86 466	55.27 465	72.63 463

N_pmnet		78.73 420	78.71 421	78.79 438	92.80 416	46.50 477	94.14 389	43.71 479	78.61 440	80.83 429	91.66 421	74.94 357	96.36 412	67.24 453	84.45 395	93.50 411

wuyk23d		25.11 440	24.57 444	26.74 456	73.98 472	39.89 480	57.88 470	9.80 480	12.27 473	10.39 474	6.97 476	7.03 478	36.44 475	25.43 474	17.39 473	3.89 473

testmvs		13.36 442	16.33 445	4.48 458	5.04 480	2.26 483	93.18 416	3.28 481	2.70 474	8.24 475	21.66 472	2.29 481	2.19 476	7.58 475	2.96 474	9.00 472

test123		13.04 443	15.66 446	5.18 457	4.51 481	3.45 482	92.50 430	1.81 482	2.50 475	7.58 476	20.15 473	3.67 480	2.18 477	7.13 476	1.07 475	9.90 471

mmdepth		0.00 446	0.00 449	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.00 477	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

monomultidepth		0.00 446	0.00 449	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.00 477	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

test_blank		0.00 446	0.00 449	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.00 477	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

uanet_test		0.00 446	0.00 449	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.00 477	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

DCPMVS		0.00 446	0.00 449	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.00 477	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

pcd_1.5k_mvsjas		7.39 445	9.85 448	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.00 477	88.65 107	0.00 478	0.00 477	0.00 476	0.00 474

sosnet-low-res		0.00 446	0.00 449	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.00 477	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

sosnet		0.00 446	0.00 449	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.00 477	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

uncertanet		0.00 446	0.00 449	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.00 477	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

Regformer		0.00 446	0.00 449	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.00 477	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

n2								0.00 483

nn								0.00 483

ab-mvs-re		8.06 444	10.74 447	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	96.69 213	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

uanet		0.00 446	0.00 449	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.00 477	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

TestfortrainingZip							98.69 11

WAC-MVS						79.53 429								75.56 427

PC_three_1452									90.77 229	98.89 25	98.28 83	96.24 1	98.35 271	95.76 103	99.58 23	99.59 30

eth-test2					0.00 482

eth-test					0.00 482

OPU-MVS				98.55 4	98.82 59	96.86 3	98.25 38				98.26 84	96.04 2	99.24 146	95.36 117	99.59 19	99.56 38

test_0728_THIRD									94.78 60	98.73 29	98.87 30	95.87 4	99.84 24	97.45 45	99.72 2	99.77 3

GSMVS																98.45 177

test_part2					99.28 28	95.74 9				98.10 45

sam_mvs1												82.76 232				98.45 177

sam_mvs												81.94 253

test_post1							92.81 426				16.58 475	80.53 279	97.68 354	86.20 330

test_post											17.58 474	81.76 256	98.08 298

patchmatchnet-post											90.45 429	82.65 237	98.10 293

gm-plane-assit					93.22 407	78.89 437			84.82 392		93.52 382		98.64 241	87.72 298

test9_res														94.81 135	99.38 62	99.45 57

agg_prior2														93.94 159	99.38 62	99.50 50

test_prior4						93.66 60	96.42 268

test_prior2							96.35 278		92.80 152	96.03 123	97.59 152	92.01 49		95.01 125	99.38 62

旧先验2							95.94 308		81.66 424	97.34 67			98.82 206	92.26 192

新几何2							95.79 318

原ACMM2							95.67 324

testdata2													99.67 74	85.96 338

segment_acmp												92.89 32

testdata1							95.26 350		93.10 134

plane_prior7					96.21 260	89.98 209

plane_prior6					96.10 278	90.00 205						81.32 263

plane_prior4											96.64 216

plane_prior3						90.00 205			94.46 77	91.34 262

plane_prior2							97.74 110		94.85 52

plane_prior1					96.14 273

plane_prior						89.99 207	97.24 183		94.06 90						92.16 296

HQP5-MVS						89.33 239

HQP-NCC					95.86 286		96.65 249		93.55 107	90.14 286

ACMP_Plane					95.86 286		96.65 249		93.55 107	90.14 286

BP-MVS														92.13 200

HQP4-MVS										90.14 286			98.50 256			95.78 315

HQP2-MVS												80.95 267

NP-MVS					95.99 284	89.81 217					95.87 259

MDTV_nov1_ep13_2view						70.35 455	93.10 421		83.88 403	93.55 203		82.47 241		86.25 329		98.38 185

ACMMP++_ref															90.30 326

ACMMP++															91.02 315

Test By Simon												88.73 106

High-resolution multi-view benchmark