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 16	97.89 3	96.53 105	98.41 85	91.73 130	98.01 66	99.02 1	96.37 13	99.30 7	98.92 23	92.39 44	99.79 46	99.16 14	99.46 46	98.08 227

PGM-MVS		96.81 58	96.53 69	97.65 47	99.35 25	93.53 65	97.65 129	98.98 2	92.22 176	97.14 76	98.44 64	91.17 71	99.85 21	94.35 162	99.46 46	99.57 36

MVS_111021_HR		96.68 69	96.58 68	96.99 84	98.46 79	92.31 110	96.20 304	98.90 3	94.30 86	95.86 134	97.74 143	92.33 45	99.38 136	96.04 96	99.42 56	99.28 77

test_fmvsmconf_n		97.49 21	97.56 16	97.29 64	97.44 165	92.37 107	97.91 85	98.88 4	95.83 19	98.92 23	99.05 14	91.45 61	99.80 40	99.12 16	99.46 46	99.69 14

lecture		97.58 15	97.63 12	97.43 58	99.37 19	92.93 86	98.86 7	98.85 5	95.27 34	98.65 36	98.90 25	91.97 52	99.80 40	97.63 38	99.21 83	99.57 36

ACMMP		96.27 86	95.93 89	97.28 66	99.24 33	92.62 98	98.25 40	98.81 6	92.99 140	94.56 181	98.39 68	88.96 102	99.85 21	94.57 156	97.63 163	99.36 72
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 87	96.19 85	96.39 124	98.23 105	91.35 153	96.24 301	98.79 7	93.99 95	95.80 136	97.65 153	89.92 91	99.24 149	95.87 100	99.20 88	98.58 171

patch_mono-2		96.83 57	97.44 24	95.01 224	99.05 45	85.39 367	96.98 216	98.77 8	94.70 66	97.99 51	98.66 43	93.61 21	99.91 1	97.67 37	99.50 40	99.72 13

fmvsm_s_conf0.5_n		96.85 54	97.13 31	96.04 149	98.07 120	90.28 203	97.97 77	98.76 9	94.93 48	98.84 28	99.06 12	88.80 106	99.65 79	99.06 18	98.63 123	98.18 212

fmvsm_l_conf0.5_n		97.65 9	97.75 8	97.34 61	98.21 106	92.75 92	97.83 98	98.73 10	95.04 45	99.30 7	98.84 36	93.34 24	99.78 49	99.32 7	99.13 98	99.50 52

fmvsm_s_conf0.5_n_a		96.75 62	96.93 46	96.20 140	97.64 151	90.72 185	98.00 67	98.73 10	94.55 73	98.91 24	99.08 8	88.22 118	99.63 88	98.91 21	98.37 136	98.25 207

fmvsm_s_conf0.5_n_10		97.29 31	97.40 26	96.97 86	98.24 100	91.96 126	97.89 88	98.72 12	96.77 7	99.46 3	99.06 12	87.78 127	99.84 26	99.40 4	99.27 75	99.12 92

fmvsm_l_conf0.5_n_9		97.59 13	97.79 6	96.97 86	98.28 94	91.49 144	97.61 138	98.71 13	97.10 5	99.70 1	98.93 22	90.95 76	99.77 52	99.35 6	99.53 33	99.65 20

FC-MVSNet-test		93.94 182	93.57 174	95.04 222	95.48 315	91.45 149	98.12 55	98.71 13	93.37 122	90.23 295	96.70 221	87.66 129	97.85 346	91.49 226	90.39 335	95.83 321

UniMVSNet (Re)		93.31 209	92.55 222	95.61 189	95.39 321	93.34 71	97.39 172	98.71 13	93.14 135	90.10 304	94.83 323	87.71 128	98.03 319	91.67 224	83.99 410	95.46 340

MED-MVS test				98.00 23	99.56 1	94.50 35	98.69 11	98.70 16	93.45 118	98.73 30	98.53 51		99.86 9	97.40 50	99.58 23	99.65 20

MED-MVS		97.91 4	97.88 4	98.00 23	99.56 1	94.50 35	98.69 11	98.70 16	94.23 87	98.73 30	98.53 51	95.46 7	99.86 9	97.40 50	99.58 23	99.65 20

TestfortrainingZip a		97.92 3	97.70 10	98.58 3	99.56 1	96.08 5	98.69 11	98.70 16	93.45 118	98.73 30	98.53 51	95.46 7	99.86 9	96.63 69	99.58 23	99.80 1

fmvsm_l_conf0.5_n_a		97.63 11	97.76 7	97.26 68	98.25 99	92.59 100	97.81 103	98.68 19	94.93 48	99.24 10	98.87 31	93.52 22	99.79 46	99.32 7	99.21 83	99.40 66

FIs		94.09 173	93.70 170	95.27 211	95.70 304	92.03 122	98.10 56	98.68 19	93.36 124	90.39 292	96.70 221	87.63 132	97.94 337	92.25 204	90.50 334	95.84 320

WR-MVS_H		92.00 266	91.35 263	93.95 293	95.09 348	89.47 239	98.04 63	98.68 19	91.46 207	88.34 356	94.68 330	85.86 170	97.56 376	85.77 353	84.24 408	94.82 387

fmvsm_s_conf0.5_n_4		96.75 62	97.07 34	95.79 173	97.76 142	89.57 232	97.66 128	98.66 22	95.36 30	99.03 16	98.90 25	88.39 114	99.73 61	99.17 13	98.66 121	98.08 227

VPA-MVSNet		93.24 211	92.48 227	95.51 198	95.70 304	92.39 106	97.86 91	98.66 22	92.30 173	92.09 253	95.37 298	80.49 290	98.40 273	93.95 168	85.86 381	95.75 329

fmvsm_l_conf0.5_n_3		97.64 10	97.60 13	97.79 34	98.14 113	93.94 56	97.93 83	98.65 24	96.70 8	99.38 5	99.07 11	89.92 91	99.81 35	99.16 14	99.43 53	99.61 30

fmvsm_s_conf0.5_n_3		97.15 36	97.36 28	96.52 107	97.98 126	91.19 161	97.84 95	98.65 24	97.08 6	99.25 9	99.10 6	87.88 125	99.79 46	99.32 7	99.18 90	98.59 170

fmvsm_s_conf0.5_n_8		97.32 28	97.48 23	96.85 88	98.28 94	91.07 169	97.76 108	98.62 26	97.53 2	99.20 12	99.12 5	88.24 117	99.81 35	99.41 3	99.17 91	99.67 15

fmvsm_s_conf0.5_n_2		96.62 70	96.82 55	96.02 151	97.98 126	90.43 195	97.50 153	98.59 27	96.59 10	99.31 6	99.08 8	84.47 203	99.75 58	99.37 5	98.45 133	97.88 240

UniMVSNet_NR-MVSNet		93.37 207	92.67 216	95.47 204	95.34 327	92.83 89	97.17 199	98.58 28	92.98 145	90.13 300	95.80 274	88.37 116	97.85 346	91.71 221	83.93 411	95.73 331

CSCG		96.05 90	95.91 90	96.46 117	99.24 33	90.47 192	98.30 33	98.57 29	89.01 302	93.97 202	97.57 163	92.62 40	99.76 54	94.66 150	99.27 75	99.15 87

fmvsm_s_conf0.5_n_9		97.33 27	97.57 15	96.62 101	98.43 82	90.32 202	97.80 104	98.53 30	97.24 4	99.62 2	99.14 2	88.65 109	99.80 40	99.54 1	99.15 95	99.74 9

fmvsm_s_conf0.5_n_6		97.08 39	97.17 30	96.81 89	97.28 170	91.73 130	97.75 110	98.50 31	94.86 52	99.22 11	98.78 40	89.75 94	99.76 54	99.10 17	99.29 73	98.94 121

MSLP-MVS++		96.94 48	97.06 35	96.59 102	98.72 64	91.86 128	97.67 125	98.49 32	94.66 69	97.24 72	98.41 67	92.31 47	98.94 195	96.61 71	99.46 46	98.96 114

HyFIR lowres test		93.66 194	92.92 204	95.87 162	98.24 100	89.88 218	94.58 383	98.49 32	85.06 400	93.78 205	95.78 278	82.86 238	98.67 247	91.77 219	95.71 233	99.07 100

CHOSEN 1792x2688		94.15 168	93.51 180	96.06 147	98.27 96	89.38 244	95.18 367	98.48 34	85.60 390	93.76 206	97.11 196	83.15 228	99.61 90	91.33 229	98.72 119	99.19 83

fmvsm_s_conf0.5_n_7		96.45 77	96.80 57	95.37 207	97.29 169	88.38 282	97.23 193	98.47 35	95.14 39	98.43 41	99.09 7	87.58 133	99.72 65	98.80 25	99.21 83	98.02 231

fmvsm_s_conf0.5_n_5		97.00 45	96.97 43	97.09 79	97.58 161	92.56 101	97.68 124	98.47 35	94.02 93	98.90 25	98.89 28	88.94 103	99.78 49	99.18 12	99.03 107	98.93 125

PHI-MVS		96.77 60	96.46 76	97.71 45	98.40 86	94.07 52	98.21 47	98.45 37	89.86 273	97.11 78	98.01 104	92.52 42	99.69 73	96.03 97	99.53 33	99.36 72

fmvsm_s_conf0.1_n		96.58 73	96.77 60	96.01 154	96.67 228	90.25 204	97.91 85	98.38 38	94.48 77	98.84 28	99.14 2	88.06 120	99.62 89	98.82 23	98.60 125	98.15 216

PVSNet_BlendedMVS		94.06 174	93.92 164	94.47 260	98.27 96	89.46 241	96.73 249	98.36 39	90.17 265	94.36 187	95.24 306	88.02 121	99.58 98	93.44 182	90.72 330	94.36 408

PVSNet_Blended		94.87 143	94.56 142	95.81 169	98.27 96	89.46 241	95.47 349	98.36 39	88.84 311	94.36 187	96.09 263	88.02 121	99.58 98	93.44 182	98.18 145	98.40 192

3Dnovator	91.36 5	95.19 126	94.44 151	97.44 57	96.56 242	93.36 70	98.65 16	98.36 39	94.12 90	89.25 334	98.06 98	82.20 255	99.77 52	93.41 184	99.32 71	99.18 84

FOURS1					99.55 4	93.34 71	99.29 1	98.35 42	94.98 46	98.49 39

DPE-MVS		97.86 6	97.65 11	98.47 6	99.17 38	95.78 8	97.21 196	98.35 42	95.16 38	98.71 35	98.80 38	95.05 12	99.89 3	96.70 68	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 17	97.39 27	98.00 23	99.21 36	94.50 35	97.75 110	98.34 44	94.23 87	98.15 46	98.53 51	93.32 27	99.84 26	97.40 50	99.58 23	99.65 20

fmvsm_s_conf0.1_n_a		96.40 79	96.47 73	96.16 142	95.48 315	90.69 186	97.91 85	98.33 45	94.07 91	98.93 20	99.14 2	87.44 141	99.61 90	98.63 26	98.32 138	98.18 212

HFP-MVS		97.14 37	96.92 47	97.83 30	99.42 10	94.12 50	98.52 20	98.32 46	93.21 127	97.18 73	98.29 84	92.08 49	99.83 31	95.63 113	99.59 19	99.54 45

ACMMPR		97.07 41	96.84 51	97.79 34	99.44 9	93.88 57	98.52 20	98.31 47	93.21 127	97.15 75	98.33 78	91.35 65	99.86 9	95.63 113	99.59 19	99.62 27

test_fmvsmvis_n_1920		96.70 65	96.84 51	96.31 129	96.62 230	91.73 130	97.98 71	98.30 48	96.19 14	96.10 124	98.95 20	89.42 95	99.76 54	98.90 22	99.08 102	97.43 267

APDe-MVS		97.82 7	97.73 9	98.08 19	99.15 39	94.82 29	98.81 8	98.30 48	94.76 64	98.30 43	98.90 25	93.77 19	99.68 75	97.93 29	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 6	95.36 14	98.31 32	98.29 50	94.92 50	98.99 18	98.92 23	95.08 10

MSP-MVS		97.59 13	97.54 17	97.73 42	99.40 14	93.77 61	98.53 19	98.29 50	95.55 27	98.56 38	97.81 135	93.90 17	99.65 79	96.62 70	99.21 83	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 67	95.39 12	99.29 1	98.28 52	94.78 61	98.93 20	98.87 31	96.04 2	99.86 9	97.45 46	99.58 23	99.59 32

test_0728_SECOND				98.51 5	99.45 6	95.93 6	98.21 47	98.28 52					99.86 9	97.52 42	99.67 6	99.75 7

CP-MVS		97.02 43	96.81 56	97.64 49	99.33 26	93.54 64	98.80 9	98.28 52	92.99 140	96.45 111	98.30 83	91.90 53	99.85 21	95.61 115	99.68 4	99.54 45

test_fmvsmconf0.1_n		97.09 38	97.06 35	97.19 73	95.67 306	92.21 114	97.95 80	98.27 55	95.78 23	98.40 42	99.00 16	89.99 89	99.78 49	99.06 18	99.41 59	99.59 32

SED-MVS		98.05 2	97.99 1	98.24 11	99.42 10	95.30 18	98.25 40	98.27 55	95.13 40	99.19 13	98.89 28	95.54 5	99.85 21	97.52 42	99.66 10	99.56 40

test_241102_TWO								98.27 55	95.13 40	98.93 20	98.89 28	94.99 13	99.85 21	97.52 42	99.65 13	99.74 9

test_241102_ONE					99.42 10	95.30 18		98.27 55	95.09 43	99.19 13	98.81 37	95.54 5	99.65 79

SF-MVS		97.39 24	97.13 31	98.17 16	99.02 48	95.28 20	98.23 44	98.27 55	92.37 170	98.27 44	98.65 45	93.33 25	99.72 65	96.49 75	99.52 35	99.51 49

SteuartSystems-ACMMP		97.62 12	97.53 18	97.87 28	98.39 88	94.25 44	98.43 27	98.27 55	95.34 32	98.11 47	98.56 47	94.53 14	99.71 67	96.57 73	99.62 17	99.65 20
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 27	95.20 21		98.25 61	95.13 40	98.48 40	98.87 31	95.16 9

PVSNet_Blended_VisFu		95.27 116	94.91 125	96.38 125	98.20 107	90.86 178	97.27 187	98.25 61	90.21 264	94.18 195	97.27 185	87.48 140	99.73 61	93.53 179	97.77 161	98.55 173

region2R		97.07 41	96.84 51	97.77 38	99.46 5	93.79 59	98.52 20	98.24 63	93.19 130	97.14 76	98.34 75	91.59 60	99.87 7	95.46 119	99.59 19	99.64 25

PS-CasMVS		91.55 287	90.84 287	93.69 310	94.96 352	88.28 285	97.84 95	98.24 63	91.46 207	88.04 367	95.80 274	79.67 306	97.48 386	87.02 333	84.54 405	95.31 354

DU-MVS		92.90 229	92.04 238	95.49 201	94.95 353	92.83 89	97.16 200	98.24 63	93.02 139	90.13 300	95.71 281	83.47 220	97.85 346	91.71 221	83.93 411	95.78 325

9.14			96.75 61		98.93 56		97.73 115	98.23 66	91.28 216	97.88 55	98.44 64	93.00 29	99.65 79	95.76 106	99.47 45

reproduce_model		97.51 20	97.51 20	97.50 54	98.99 52	93.01 82	97.79 106	98.21 67	95.73 24	97.99 51	99.03 15	92.63 39	99.82 33	97.80 31	99.42 56	99.67 15

D2MVS		91.30 304	90.95 281	92.35 360	94.71 368	85.52 361	96.18 306	98.21 67	88.89 309	86.60 396	93.82 379	79.92 302	97.95 335	89.29 279	90.95 327	93.56 423

reproduce-ours		97.53 18	97.51 20	97.60 51	98.97 53	93.31 73	97.71 120	98.20 69	95.80 21	97.88 55	98.98 18	92.91 30	99.81 35	97.68 33	99.43 53	99.67 15

our_new_method		97.53 18	97.51 20	97.60 51	98.97 53	93.31 73	97.71 120	98.20 69	95.80 21	97.88 55	98.98 18	92.91 30	99.81 35	97.68 33	99.43 53	99.67 15

SDMVSNet		94.17 166	93.61 173	95.86 165	98.09 116	91.37 151	97.35 176	98.20 69	93.18 132	91.79 261	97.28 183	79.13 314	98.93 196	94.61 153	92.84 293	97.28 275

XVS		97.18 34	96.96 45	97.81 32	99.38 17	94.03 54	98.59 17	98.20 69	94.85 53	96.59 99	98.29 84	91.70 56	99.80 40	95.66 108	99.40 61	99.62 27

X-MVStestdata		91.71 275	89.67 342	97.81 32	99.38 17	94.03 54	98.59 17	98.20 69	94.85 53	96.59 99	32.69 485	91.70 56	99.80 40	95.66 108	99.40 61	99.62 27

ACMMP_NAP		97.20 33	96.86 49	98.23 12	99.09 40	95.16 23	97.60 139	98.19 74	92.82 154	97.93 54	98.74 42	91.60 59	99.86 9	96.26 80	99.52 35	99.67 15

CP-MVSNet		91.89 271	91.24 270	93.82 302	95.05 349	88.57 275	97.82 100	98.19 74	91.70 196	88.21 362	95.76 279	81.96 260	97.52 384	87.86 305	84.65 399	95.37 350

ZNCC-MVS		96.96 46	96.67 64	97.85 29	99.37 19	94.12 50	98.49 24	98.18 76	92.64 161	96.39 113	98.18 91	91.61 58	99.88 4	95.59 118	99.55 30	99.57 36

SMA-MVS		97.35 25	97.03 40	98.30 9	99.06 44	95.42 11	97.94 81	98.18 76	90.57 255	98.85 27	98.94 21	93.33 25	99.83 31	96.72 66	99.68 4	99.63 26
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		91.20 309	90.44 305	93.48 323	94.49 376	87.91 300	97.76 108	98.18 76	91.29 213	87.78 371	95.74 280	80.35 293	97.33 397	85.46 357	82.96 421	95.19 365

DELS-MVS		96.61 71	96.38 80	97.30 63	97.79 140	93.19 78	95.96 318	98.18 76	95.23 35	95.87 133	97.65 153	91.45 61	99.70 72	95.87 100	99.44 52	99.00 109
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		89.70 361	88.40 367	93.60 316	95.15 344	90.10 207	97.56 144	98.16 80	87.28 363	86.16 402	94.63 334	77.57 342	98.05 315	74.48 444	84.59 403	92.65 436

VNet		95.89 98	95.45 101	97.21 71	98.07 120	92.94 85	97.50 153	98.15 81	93.87 99	97.52 62	97.61 159	85.29 187	99.53 112	95.81 105	95.27 246	99.16 85

DeepPCF-MVS	93.97 1	96.61 71	97.09 33	95.15 215	98.09 116	86.63 333	96.00 316	98.15 81	95.43 28	97.95 53	98.56 47	93.40 23	99.36 137	96.77 63	99.48 44	99.45 59

SD-MVS		97.41 23	97.53 18	97.06 82	98.57 78	94.46 38	97.92 84	98.14 83	94.82 57	99.01 17	98.55 49	94.18 16	97.41 393	96.94 58	99.64 14	99.32 74
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 54	96.52 70	97.82 31	99.36 23	94.14 49	98.29 34	98.13 84	92.72 157	96.70 91	98.06 98	91.35 65	99.86 9	94.83 139	99.28 74	99.47 58

UA-Net		95.95 95	95.53 97	97.20 72	97.67 147	92.98 84	97.65 129	98.13 84	94.81 59	96.61 97	98.35 72	88.87 104	99.51 117	90.36 254	97.35 174	99.11 94

QAPM		93.45 205	92.27 232	96.98 85	96.77 221	92.62 98	98.39 29	98.12 86	84.50 408	88.27 360	97.77 139	82.39 252	99.81 35	85.40 358	98.81 115	98.51 178

Vis-MVSNet		95.23 121	94.81 130	96.51 111	97.18 175	91.58 141	98.26 39	98.12 86	94.38 84	94.90 170	98.15 93	82.28 253	98.92 198	91.45 228	98.58 127	99.01 106
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 232	91.68 253	96.40 122	95.34 327	92.73 94	98.27 37	98.12 86	84.86 403	85.78 406	97.75 140	78.89 324	99.74 59	87.50 323	98.65 122	96.73 292

TranMVSNet+NR-MVSNet		92.50 241	91.63 254	95.14 216	94.76 364	92.07 119	97.53 150	98.11 89	92.90 151	89.56 322	96.12 258	83.16 227	97.60 374	89.30 278	83.20 420	95.75 329

CPTT-MVS		95.57 108	95.19 112	96.70 92	99.27 31	91.48 146	98.33 31	98.11 89	87.79 348	95.17 161	98.03 101	87.09 148	99.61 90	93.51 180	99.42 56	99.02 103

APD-MVS		96.95 47	96.60 66	98.01 21	99.03 47	94.93 28	97.72 118	98.10 91	91.50 205	98.01 50	98.32 80	92.33 45	99.58 98	94.85 136	99.51 38	99.53 48
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 52	96.60 66	97.64 49	99.40 14	93.44 66	98.50 23	98.09 92	93.27 126	95.95 131	98.33 78	91.04 73	99.88 4	95.20 122	99.57 29	99.60 31

ZD-MVS					99.05 45	94.59 33		98.08 93	89.22 295	97.03 81	98.10 94	92.52 42	99.65 79	94.58 155	99.31 72

MTGPA								98.08 93

MTAPA		97.08 39	96.78 59	97.97 27	99.37 19	94.42 40	97.24 189	98.08 93	95.07 44	96.11 123	98.59 46	90.88 79	99.90 2	96.18 92	99.50 40	99.58 35

CNVR-MVS		97.68 8	97.44 24	98.37 8	98.90 59	95.86 7	97.27 187	98.08 93	95.81 20	97.87 58	98.31 81	94.26 15	99.68 75	97.02 57	99.49 43	99.57 36

DP-MVS Recon		95.68 103	95.12 116	97.37 60	99.19 37	94.19 46	97.03 207	98.08 93	88.35 329	95.09 163	97.65 153	89.97 90	99.48 124	92.08 213	98.59 126	98.44 189

SR-MVS		97.01 44	96.86 49	97.47 56	99.09 40	93.27 75	97.98 71	98.07 98	93.75 102	97.45 64	98.48 61	91.43 63	99.59 95	96.22 83	99.27 75	99.54 45

MCST-MVS		97.18 34	96.84 51	98.20 15	99.30 29	95.35 16	97.12 203	98.07 98	93.54 112	96.08 125	97.69 148	93.86 18	99.71 67	96.50 74	99.39 63	99.55 43

NR-MVSNet		92.34 250	91.27 269	95.53 194	94.95 353	93.05 81	97.39 172	98.07 98	92.65 159	84.46 417	95.71 281	85.00 194	97.77 357	89.71 266	83.52 417	95.78 325

MP-MVS-pluss		96.70 65	96.27 83	97.98 26	99.23 35	94.71 30	96.96 218	98.06 101	90.67 245	95.55 147	98.78 40	91.07 72	99.86 9	96.58 72	99.55 30	99.38 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 58	96.71 63	97.12 76	99.01 51	92.31 110	97.98 71	98.06 101	93.11 136	97.44 65	98.55 49	90.93 77	99.55 108	96.06 93	99.25 80	99.51 49

MP-MVS		96.77 60	96.45 77	97.72 43	99.39 16	93.80 58	98.41 28	98.06 101	93.37 122	95.54 149	98.34 75	90.59 83	99.88 4	94.83 139	99.54 32	99.49 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 74	96.27 83	97.22 70	99.32 27	92.74 93	98.74 10	98.06 101	90.57 255	96.77 88	98.35 72	90.21 86	99.53 112	94.80 143	99.63 16	99.38 70

HPM-MVS		96.69 67	96.45 77	97.40 59	99.36 23	93.11 80	98.87 6	98.06 101	91.17 224	96.40 112	97.99 107	90.99 74	99.58 98	95.61 115	99.61 18	99.49 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 157	93.80 166	96.64 94	97.07 181	91.97 124	96.32 293	98.06 101	88.94 307	94.50 184	96.78 216	84.60 200	99.27 147	91.90 214	96.02 223	98.68 164

DeepC-MVS	93.07 3	96.06 89	95.66 94	97.29 64	97.96 128	93.17 79	97.30 182	98.06 101	93.92 97	93.38 221	98.66 43	86.83 150	99.73 61	95.60 117	99.22 82	98.96 114
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 29	97.03 40	98.11 18	98.77 62	95.06 26	97.34 177	98.04 108	95.96 15	97.09 79	97.88 122	93.18 28	99.71 67	95.84 104	99.17 91	99.56 40

DeepC-MVS_fast	93.89 2	96.93 49	96.64 65	97.78 36	98.64 73	94.30 41	97.41 167	98.04 108	94.81 59	96.59 99	98.37 70	91.24 68	99.64 87	95.16 124	99.52 35	99.42 65
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 51	96.80 57	97.11 78	99.02 48	92.34 108	97.98 71	98.03 110	93.52 115	97.43 67	98.51 56	91.40 64	99.56 106	96.05 94	99.26 78	99.43 63

RE-MVS-def			96.72 62		99.02 48	92.34 108	97.98 71	98.03 110	93.52 115	97.43 67	98.51 56	90.71 81		96.05 94	99.26 78	99.43 63

RPMNet		88.98 367	87.05 381	94.77 243	94.45 378	87.19 317	90.23 459	98.03 110	77.87 458	92.40 239	87.55 463	80.17 297	99.51 117	68.84 465	93.95 279	97.60 260

save fliter					98.91 58	94.28 42	97.02 209	98.02 113	95.35 31

TEST9					98.70 65	94.19 46	96.41 279	98.02 113	88.17 333	96.03 126	97.56 165	92.74 36	99.59 95

train_agg		96.30 85	95.83 93	97.72 43	98.70 65	94.19 46	96.41 279	98.02 113	88.58 320	96.03 126	97.56 165	92.73 37	99.59 95	95.04 126	99.37 67	99.39 68

test_8					98.67 67	94.06 53	96.37 287	98.01 116	88.58 320	95.98 130	97.55 167	92.73 37	99.58 98

fmvsm_s_conf0.5_n_11		97.30 29	97.59 14	96.43 119	98.42 83	91.37 151	98.04 63	98.00 117	97.30 3	99.45 4	99.21 1	89.28 97	99.80 40	99.27 10	99.35 69	98.12 219

agg_prior					98.67 67	93.79 59		98.00 117		95.68 143			99.57 105

test_prior				97.23 69	98.67 67	92.99 83		98.00 117					99.41 132			99.29 75

WR-MVS		92.34 250	91.53 258	94.77 243	95.13 346	90.83 179	96.40 283	97.98 120	91.88 191	89.29 331	95.54 292	82.50 248	97.80 353	89.79 265	85.27 390	95.69 332

HPM-MVS++		97.34 26	96.97 43	98.47 6	99.08 42	96.16 4	97.55 149	97.97 121	95.59 25	96.61 97	97.89 118	92.57 41	99.84 26	95.95 99	99.51 38	99.40 66

CANet		96.39 80	96.02 88	97.50 54	97.62 154	93.38 68	97.02 209	97.96 122	95.42 29	94.86 171	97.81 135	87.38 143	99.82 33	96.88 60	99.20 88	99.29 75

114514_t		93.95 181	93.06 198	96.63 98	99.07 43	91.61 138	97.46 164	97.96 122	77.99 456	93.00 230	97.57 163	86.14 166	99.33 139	89.22 282	99.15 95	98.94 121

IU-MVS					99.42 10	95.39 12		97.94 124	90.40 262	98.94 19				97.41 49	99.66 10	99.74 9

MSC_two_6792asdad				98.86 1	98.67 67	96.94 1		97.93 125					99.86 9	97.68 33	99.67 6	99.77 3

No_MVS				98.86 1	98.67 67	96.94 1		97.93 125					99.86 9	97.68 33	99.67 6	99.77 3

fmvsm_s_conf0.1_n_2		96.33 84	96.44 79	96.00 155	97.30 168	90.37 201	97.53 150	97.92 127	96.52 11	99.14 15	99.08 8	83.21 225	99.74 59	99.22 11	98.06 150	97.88 240

Anonymous20231211		90.63 333	89.42 349	94.27 274	98.24 100	89.19 256	98.05 62	97.89 128	79.95 447	88.25 361	94.96 315	72.56 384	98.13 298	89.70 267	85.14 392	95.49 336

原ACMM1				96.38 125	98.59 75	91.09 168		97.89 128	87.41 359	95.22 160	97.68 149	90.25 85	99.54 110	87.95 304	99.12 100	98.49 181

CDPH-MVS		95.97 94	95.38 106	97.77 38	98.93 56	94.44 39	96.35 288	97.88 130	86.98 367	96.65 95	97.89 118	91.99 51	99.47 125	92.26 202	99.46 46	99.39 68

test11								97.88 130

EIA-MVS		95.53 109	95.47 100	95.71 184	97.06 184	89.63 228	97.82 100	97.87 132	93.57 108	93.92 203	95.04 312	90.61 82	98.95 193	94.62 152	98.68 120	98.54 174

CS-MVS		96.86 52	97.06 35	96.26 135	98.16 112	91.16 166	99.09 3	97.87 132	95.30 33	97.06 80	98.03 101	91.72 54	98.71 240	97.10 55	99.17 91	98.90 130

无先验							95.79 330	97.87 132	83.87 416				99.65 79	87.68 316		98.89 136

3Dnovator+	91.43 4	95.40 110	94.48 149	98.16 17	96.90 201	95.34 17	98.48 25	97.87 132	94.65 70	88.53 352	98.02 103	83.69 216	99.71 67	93.18 188	98.96 110	99.44 61

VPNet		92.23 258	91.31 266	94.99 226	95.56 311	90.96 172	97.22 195	97.86 136	92.96 146	90.96 283	96.62 233	75.06 363	98.20 292	91.90 214	83.65 416	95.80 323

test_vis1_n_1920		94.17 166	94.58 141	92.91 344	97.42 166	82.02 415	97.83 98	97.85 137	94.68 67	98.10 48	98.49 58	70.15 403	99.32 141	97.91 30	98.82 114	97.40 269

DVP-MVS		97.91 4	97.81 5	98.22 14	99.45 6	95.36 14	98.21 47	97.85 137	94.92 50	98.73 30	98.87 31	95.08 10	99.84 26	97.52 42	99.67 6	99.48 56
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 22	97.33 29	97.69 46	99.25 32	94.24 45	98.07 60	97.85 137	93.72 103	98.57 37	98.35 72	93.69 20	99.40 133	97.06 56	99.46 46	99.44 61
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 50	97.04 39	96.45 118	98.29 93	91.66 137	99.03 4	97.85 137	95.84 18	96.90 83	97.97 109	91.24 68	98.75 230	96.92 59	99.33 70	98.94 121

test_fmvsmconf0.01_n		96.15 88	95.85 92	97.03 83	92.66 430	91.83 129	97.97 77	97.84 141	95.57 26	97.53 61	99.00 16	84.20 209	99.76 54	98.82 23	99.08 102	99.48 56

GDP-MVS		95.62 105	95.13 114	97.09 79	96.79 214	93.26 76	97.89 88	97.83 142	93.58 107	96.80 85	97.82 133	83.06 232	99.16 161	94.40 159	97.95 156	98.87 140

balanced_conf03		96.84 56	96.89 48	96.68 93	97.63 153	92.22 113	98.17 53	97.82 143	94.44 79	98.23 45	97.36 178	90.97 75	99.22 151	97.74 32	99.66 10	98.61 167

AdaColmap		94.34 161	93.68 171	96.31 129	98.59 75	91.68 136	96.59 268	97.81 144	89.87 272	92.15 249	97.06 199	83.62 219	99.54 110	89.34 277	98.07 149	97.70 253

MVSMamba_PlusPlus		96.51 74	96.48 72	96.59 102	98.07 120	91.97 124	98.14 54	97.79 145	90.43 260	97.34 70	97.52 168	91.29 67	99.19 154	98.12 28	99.64 14	98.60 168

KinetiMVS		95.26 117	94.75 135	96.79 90	96.99 194	92.05 120	97.82 100	97.78 146	94.77 63	96.46 109	97.70 146	80.62 287	99.34 138	92.37 201	98.28 140	98.97 111

mamv4		94.66 154	96.10 87	90.37 414	98.01 123	73.41 465	96.82 235	97.78 146	89.95 271	94.52 182	97.43 173	92.91 30	99.09 174	98.28 27	99.16 94	98.60 168

ETV-MVS		96.02 91	95.89 91	96.40 122	97.16 176	92.44 105	97.47 162	97.77 148	94.55 73	96.48 107	94.51 340	91.23 70	98.92 198	95.65 111	98.19 144	97.82 248

新几何1				97.32 62	98.60 74	93.59 63		97.75 149	81.58 438	95.75 138	97.85 127	90.04 88	99.67 77	86.50 339	99.13 98	98.69 163

旧先验1					98.38 89	93.38 68		97.75 149			98.09 96	92.30 48			99.01 108	99.16 85

EC-MVSNet		96.42 78	96.47 73	96.26 135	97.01 192	91.52 143	98.89 5	97.75 149	94.42 80	96.64 96	97.68 149	89.32 96	98.60 256	97.45 46	99.11 101	98.67 165

EI-MVSNet-Vis-set		96.51 74	96.47 73	96.63 98	98.24 100	91.20 160	96.89 226	97.73 152	94.74 65	96.49 106	98.49 58	90.88 79	99.58 98	96.44 76	98.32 138	99.13 89

PAPM_NR		95.01 134	94.59 140	96.26 135	98.89 60	90.68 187	97.24 189	97.73 152	91.80 192	92.93 235	96.62 233	89.13 100	99.14 166	89.21 283	97.78 160	98.97 111

Anonymous20240529		91.98 267	90.73 294	95.73 182	98.14 113	89.40 243	97.99 68	97.72 154	79.63 449	93.54 214	97.41 175	69.94 405	99.56 106	91.04 236	91.11 323	98.22 209

CHOSEN 280x420		93.12 217	92.72 215	94.34 268	96.71 227	87.27 313	90.29 458	97.72 154	86.61 374	91.34 272	95.29 300	84.29 208	98.41 272	93.25 186	98.94 111	97.35 272

EI-MVSNet-UG-set		96.34 83	96.30 82	96.47 115	98.20 107	90.93 175	96.86 229	97.72 154	94.67 68	96.16 122	98.46 62	90.43 84	99.58 98	96.23 82	97.96 155	98.90 130

LS3D		93.57 198	92.61 220	96.47 115	97.59 157	91.61 138	97.67 125	97.72 154	85.17 398	90.29 294	98.34 75	84.60 200	99.73 61	83.85 381	98.27 141	98.06 229

PAPR		94.18 165	93.42 187	96.48 114	97.64 151	91.42 150	95.55 344	97.71 158	88.99 304	92.34 245	95.82 273	89.19 98	99.11 169	86.14 345	97.38 172	98.90 130

UGNet		94.04 176	93.28 190	96.31 129	96.85 206	91.19 161	97.88 90	97.68 159	94.40 82	93.00 230	96.18 253	73.39 380	99.61 90	91.72 220	98.46 132	98.13 217
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				95.46 205	98.18 111	88.90 266		97.66 160	82.73 429	97.03 81	98.07 97	90.06 87	98.85 205	89.67 268	98.98 109	98.64 166

test12				97.65 47	98.46 79	94.26 43		97.66 160		95.52 150		90.89 78	99.46 126		99.25 80	99.22 82

DTE-MVSNet		90.56 334	89.75 340	93.01 340	93.95 391	87.25 314	97.64 133	97.65 162	90.74 240	87.12 384	95.68 284	79.97 301	97.00 410	83.33 382	81.66 427	94.78 394

TAPA-MVS	90.10 7	92.30 253	91.22 272	95.56 191	98.33 91	89.60 230	96.79 241	97.65 162	81.83 435	91.52 267	97.23 188	87.94 123	98.91 200	71.31 459	98.37 136	98.17 215
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 218	92.45 228	95.05 220	98.09 116	89.21 253	96.89 226	97.64 164	93.18 132	91.79 261	97.28 183	75.35 362	98.65 250	88.99 288	92.84 293	97.28 275

test_cas_vis1_n_1920		94.48 159	94.55 145	94.28 273	96.78 219	86.45 339	97.63 135	97.64 164	93.32 125	97.68 60	98.36 71	73.75 378	99.08 177	96.73 65	99.05 104	97.31 274

NormalMVS		96.36 82	96.11 86	97.12 76	99.37 19	92.90 87	97.99 68	97.63 166	95.92 16	96.57 102	97.93 111	85.34 185	99.50 120	94.99 129	99.21 83	98.97 111

Elysia		94.00 178	93.12 195	96.64 94	96.08 290	92.72 95	97.50 153	97.63 166	91.15 226	94.82 172	97.12 194	74.98 365	99.06 183	90.78 241	98.02 151	98.12 219

StellarMVS		94.00 178	93.12 195	96.64 94	96.08 290	92.72 95	97.50 153	97.63 166	91.15 226	94.82 172	97.12 194	74.98 365	99.06 183	90.78 241	98.02 151	98.12 219

cdsmvs_eth3d_5k		23.24 454	30.99 456	0.00 473	0.00 496	0.00 498	0.00 485	97.63 166	0.00 491	0.00 492	96.88 212	84.38 205	0.00 492	0.00 491	0.00 490	0.00 488

DPM-MVS		95.69 102	94.92 124	98.01 21	98.08 119	95.71 10	95.27 360	97.62 170	90.43 260	95.55 147	97.07 198	91.72 54	99.50 120	89.62 270	98.94 111	98.82 146

sasdasda		96.02 91	95.45 101	97.75 40	97.59 157	95.15 24	98.28 35	97.60 171	94.52 75	96.27 117	96.12 258	87.65 130	99.18 157	96.20 88	94.82 255	98.91 127

canonicalmvs		96.02 91	95.45 101	97.75 40	97.59 157	95.15 24	98.28 35	97.60 171	94.52 75	96.27 117	96.12 258	87.65 130	99.18 157	96.20 88	94.82 255	98.91 127

test222					98.24 100	92.21 114	95.33 355	97.60 171	79.22 451	95.25 158	97.84 129	88.80 106			99.15 95	98.72 160

cascas		91.20 309	90.08 322	94.58 254	94.97 351	89.16 257	93.65 423	97.59 174	79.90 448	89.40 326	92.92 406	75.36 361	98.36 280	92.14 207	94.75 258	96.23 302

E2		95.20 123	95.00 121	95.79 173	96.79 214	89.66 225	96.82 235	97.58 175	92.35 171	95.28 156	97.83 131	86.68 152	98.76 224	94.79 146	96.92 193	98.95 118

E3		95.20 123	95.00 121	95.79 173	96.77 221	89.66 225	96.82 235	97.58 175	92.35 171	95.28 156	97.83 131	86.69 151	98.76 224	94.79 146	96.92 193	98.95 118

h-mvs33		94.15 168	93.52 179	96.04 149	97.81 139	90.22 205	97.62 137	97.58 175	95.19 36	96.74 89	97.45 170	83.67 217	99.61 90	95.85 102	79.73 434	98.29 205

E6new		95.04 131	94.88 126	95.52 195	96.60 233	89.02 261	97.29 183	97.57 178	92.54 162	95.04 164	97.90 116	85.66 176	98.77 219	94.92 132	96.44 217	98.78 149

E6		95.04 131	94.88 126	95.52 195	96.60 233	89.02 261	97.29 183	97.57 178	92.54 162	95.04 164	97.90 116	85.66 176	98.77 219	94.92 132	96.44 217	98.78 149

E5		95.04 131	94.88 126	95.52 195	96.62 230	89.02 261	97.29 183	97.57 178	92.54 162	95.04 164	97.89 118	85.65 178	98.77 219	94.92 132	96.44 217	98.78 149

MGCFI-Net		95.94 96	95.40 105	97.56 53	97.59 157	94.62 32	98.21 47	97.57 178	94.41 81	96.17 121	96.16 256	87.54 135	99.17 159	96.19 90	94.73 260	98.91 127

MVSFormer		95.37 111	95.16 113	95.99 156	96.34 266	91.21 158	98.22 45	97.57 178	91.42 209	96.22 119	97.32 179	86.20 164	97.92 340	94.07 165	99.05 104	98.85 142

test_djsdf		93.07 220	92.76 210	94.00 287	93.49 409	88.70 270	98.22 45	97.57 178	91.42 209	90.08 306	95.55 291	82.85 239	97.92 340	94.07 165	91.58 314	95.40 347

OMC-MVS		95.09 128	94.70 136	96.25 138	98.46 79	91.28 154	96.43 275	97.57 178	92.04 187	94.77 176	97.96 110	87.01 149	99.09 174	91.31 230	96.77 198	98.36 196

E4		95.09 128	94.86 129	95.77 176	96.58 237	89.56 233	96.85 230	97.56 185	92.50 165	95.03 167	97.86 125	86.03 167	98.78 215	94.71 149	96.65 207	98.96 114

viewcassd2359sk11		95.26 117	95.09 118	95.80 170	96.95 198	89.72 224	96.80 240	97.56 185	92.21 178	95.37 154	97.80 137	87.17 147	98.77 219	94.82 141	97.10 187	98.90 130

PS-MVSNAJss		93.74 191	93.51 180	94.44 262	93.91 393	89.28 251	97.75 110	97.56 185	92.50 165	89.94 308	96.54 236	88.65 109	98.18 295	93.83 174	90.90 328	95.86 317

casdiffmvs_mvg		95.81 101	95.57 95	96.51 111	96.87 203	91.49 144	97.50 153	97.56 185	93.99 95	95.13 162	97.92 114	87.89 124	98.78 215	95.97 98	97.33 175	99.26 79
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E3new		95.28 115	95.11 117	95.80 170	97.03 189	89.76 222	96.78 245	97.54 189	92.06 186	95.40 153	97.75 140	87.49 139	98.76 224	94.85 136	97.10 187	98.88 138

jajsoiax		92.42 246	91.89 246	94.03 286	93.33 417	88.50 279	97.73 115	97.53 190	92.00 189	88.85 344	96.50 238	75.62 360	98.11 302	93.88 172	91.56 315	95.48 337

mvs_tets		92.31 252	91.76 249	93.94 295	93.41 414	88.29 284	97.63 135	97.53 190	92.04 187	88.76 347	96.45 240	74.62 370	98.09 307	93.91 170	91.48 316	95.45 342

dcpmvs_2		96.37 81	97.05 38	94.31 271	98.96 55	84.11 388	97.56 144	97.51 192	93.92 97	97.43 67	98.52 55	92.75 35	99.32 141	97.32 54	99.50 40	99.51 49

HQP_MVS		93.78 190	93.43 185	94.82 236	96.21 270	89.99 211	97.74 113	97.51 192	94.85 53	91.34 272	96.64 226	81.32 272	98.60 256	93.02 194	92.23 302	95.86 317

plane_prior5								97.51 192					98.60 256	93.02 194	92.23 302	95.86 317

viewmanbaseed2359cas		95.24 120	95.02 120	95.91 159	96.87 203	89.98 213	96.82 235	97.49 195	92.26 174	95.47 151	97.82 133	86.47 157	98.69 242	94.80 143	97.20 183	99.06 101

reproduce_monomvs		91.30 304	91.10 276	91.92 374	96.82 211	82.48 409	97.01 212	97.49 195	94.64 71	88.35 355	95.27 303	70.53 398	98.10 303	95.20 122	84.60 402	95.19 365

viewmacassd2359aftdt		95.07 130	94.80 131	95.87 162	96.53 247	89.84 219	96.90 225	97.48 197	92.44 167	95.36 155	97.89 118	85.23 188	98.68 244	94.40 159	97.00 191	99.09 96

PS-MVSNAJ		95.37 111	95.33 108	95.49 201	97.35 167	90.66 188	95.31 357	97.48 197	93.85 100	96.51 105	95.70 283	88.65 109	99.65 79	94.80 143	98.27 141	96.17 306

API-MVS		94.84 145	94.49 148	95.90 160	97.90 134	92.00 123	97.80 104	97.48 197	89.19 296	94.81 174	96.71 219	88.84 105	99.17 159	88.91 290	98.76 118	96.53 295

MG-MVS		95.61 106	95.38 106	96.31 129	98.42 83	90.53 190	96.04 313	97.48 197	93.47 117	95.67 144	98.10 94	89.17 99	99.25 148	91.27 231	98.77 117	99.13 89

MAR-MVS		94.22 164	93.46 182	96.51 111	98.00 125	92.19 117	97.67 125	97.47 201	88.13 337	93.00 230	95.84 271	84.86 198	99.51 117	87.99 303	98.17 146	97.83 247
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		92.98 224	92.53 224	94.32 269	96.12 285	89.20 254	95.28 358	97.47 201	92.66 158	89.90 309	95.62 287	80.58 288	98.40 273	92.73 199	92.40 300	95.38 349
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 302	90.22 318	94.68 247	94.86 360	87.86 301	97.23 193	97.46 203	87.99 338	89.90 309	96.92 210	66.35 433	98.23 289	90.30 255	90.99 326	97.96 234

nrg030		94.05 175	93.31 189	96.27 134	95.22 338	94.59 33	98.34 30	97.46 203	92.93 147	91.21 281	96.64 226	87.23 146	98.22 290	94.99 129	85.80 382	95.98 316

XVG-OURS		93.72 192	93.35 188	94.80 241	97.07 181	88.61 273	94.79 378	97.46 203	91.97 190	93.99 200	97.86 125	81.74 266	98.88 202	92.64 200	92.67 298	96.92 287

LPG-MVS_test		92.94 227	92.56 221	94.10 281	96.16 280	88.26 286	97.65 129	97.46 203	91.29 213	90.12 302	97.16 191	79.05 317	98.73 234	92.25 204	91.89 310	95.31 354

LGP-MVS_train				94.10 281	96.16 280	88.26 286		97.46 203	91.29 213	90.12 302	97.16 191	79.05 317	98.73 234	92.25 204	91.89 310	95.31 354

MVS		91.71 275	90.44 305	95.51 198	95.20 340	91.59 140	96.04 313	97.45 208	73.44 466	87.36 380	95.60 288	85.42 184	99.10 171	85.97 350	97.46 167	95.83 321

XVG-OURS-SEG-HR		93.86 187	93.55 175	94.81 238	97.06 184	88.53 278	95.28 358	97.45 208	91.68 197	94.08 199	97.68 149	82.41 251	98.90 201	93.84 173	92.47 299	96.98 283

baseline		95.58 107	95.42 104	96.08 145	96.78 219	90.41 196	97.16 200	97.45 208	93.69 106	95.65 145	97.85 127	87.29 144	98.68 244	95.66 108	97.25 181	99.13 89

ab-mvs		93.57 198	92.55 222	96.64 94	97.28 170	91.96 126	95.40 351	97.45 208	89.81 277	93.22 227	96.28 249	79.62 308	99.46 126	90.74 244	93.11 290	98.50 179

xiu_mvs_v2_base		95.32 114	95.29 109	95.40 206	97.22 172	90.50 191	95.44 350	97.44 212	93.70 105	96.46 109	96.18 253	88.59 113	99.53 112	94.79 146	97.81 159	96.17 306

1314		92.81 236	92.03 239	95.14 216	95.33 330	89.52 238	96.04 313	97.44 212	87.72 352	86.25 401	95.33 299	83.84 214	98.79 214	89.26 280	97.05 190	97.11 281

casdiffmvs		95.64 104	95.49 98	96.08 145	96.76 225	90.45 193	97.29 183	97.44 212	94.00 94	95.46 152	97.98 108	87.52 138	98.73 234	95.64 112	97.33 175	99.08 98
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		94.76 151	94.68 137	95.01 224	96.76 225	87.41 309	96.38 285	97.43 215	92.65 159	94.52 182	97.75 140	85.55 182	98.81 211	94.36 161	96.69 204	98.82 146

XXY-MVS		92.16 260	91.23 271	94.95 232	94.75 365	90.94 174	97.47 162	97.43 215	89.14 297	88.90 340	96.43 241	79.71 305	98.24 288	89.56 271	87.68 363	95.67 333

anonymousdsp		92.16 260	91.55 257	93.97 291	92.58 432	89.55 235	97.51 152	97.42 217	89.42 290	88.40 354	94.84 322	80.66 286	97.88 345	91.87 216	91.28 320	94.48 403

Effi-MVS+		94.93 139	94.45 150	96.36 127	96.61 232	91.47 147	96.41 279	97.41 218	91.02 232	94.50 184	95.92 267	87.53 136	98.78 215	93.89 171	96.81 197	98.84 145

RRT-MVS		94.51 157	94.35 154	94.98 228	96.40 260	86.55 336	97.56 144	97.41 218	93.19 130	94.93 169	97.04 200	79.12 315	99.30 145	96.19 90	97.32 177	99.09 96

HQP3-MVS								97.39 220							92.10 307

HQP-MVS		93.19 214	92.74 213	94.54 257	95.86 296	89.33 247	96.65 259	97.39 220	93.55 109	90.14 296	95.87 269	80.95 277	98.50 266	92.13 210	92.10 307	95.78 325

PLC	91.00 6	94.11 172	93.43 185	96.13 143	98.58 77	91.15 167	96.69 255	97.39 220	87.29 362	91.37 271	96.71 219	88.39 114	99.52 116	87.33 326	97.13 186	97.73 251
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
diffmvs_AUTHOR		95.33 113	95.27 110	95.50 200	96.37 264	89.08 259	96.08 311	97.38 223	93.09 138	96.53 104	97.74 143	86.45 158	98.68 244	96.32 78	97.48 166	98.75 156

v7n		90.76 326	89.86 333	93.45 325	93.54 406	87.60 307	97.70 123	97.37 224	88.85 310	87.65 373	94.08 370	81.08 276	98.10 303	84.68 367	83.79 415	94.66 400

UnsupCasMVSNet_eth		85.99 406	84.45 410	90.62 410	89.97 450	82.40 412	93.62 424	97.37 224	89.86 273	78.59 456	92.37 416	65.25 443	95.35 445	82.27 396	70.75 464	94.10 414

viewdifsd2359ckpt13		94.87 143	94.52 146	95.90 160	96.88 202	90.19 206	96.92 222	97.36 226	91.26 217	94.65 178	97.46 169	85.79 173	98.64 251	93.64 177	96.76 199	98.88 138

ACMM	89.79 8	92.96 225	92.50 226	94.35 266	96.30 268	88.71 269	97.58 140	97.36 226	91.40 211	90.53 289	96.65 225	79.77 304	98.75 230	91.24 232	91.64 312	95.59 335
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 134	94.76 132	95.75 179	96.58 237	91.71 133	96.25 298	97.35 228	92.99 140	96.70 91	96.63 230	82.67 243	99.44 129	96.22 83	97.46 167	96.11 312

xiu_mvs_v1_base		95.01 134	94.76 132	95.75 179	96.58 237	91.71 133	96.25 298	97.35 228	92.99 140	96.70 91	96.63 230	82.67 243	99.44 129	96.22 83	97.46 167	96.11 312

xiu_mvs_v1_base_debi		95.01 134	94.76 132	95.75 179	96.58 237	91.71 133	96.25 298	97.35 228	92.99 140	96.70 91	96.63 230	82.67 243	99.44 129	96.22 83	97.46 167	96.11 312

diffmvs		95.25 119	95.13 114	95.63 187	96.43 259	89.34 246	95.99 317	97.35 228	92.83 153	96.31 115	97.37 177	86.44 159	98.67 247	96.26 80	97.19 184	98.87 140
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		94.71 153	94.02 162	96.79 90	97.71 145	92.05 120	96.59 268	97.35 228	90.61 251	94.64 179	96.93 207	86.41 160	99.39 134	91.20 233	94.71 261	98.94 121

viewdifsd2359ckpt09		94.81 148	94.37 153	96.12 144	96.91 199	90.75 184	96.94 219	97.31 233	90.51 258	94.31 189	97.38 176	85.70 175	98.71 240	93.54 178	96.75 200	98.90 130

SSM_0407		94.54 156	94.12 161	95.80 170	96.79 214	90.38 198	96.79 241	97.29 234	91.24 218	93.68 207	97.60 160	85.03 192	98.67 247	92.14 207	96.51 210	98.35 198

SSM_0404		94.73 152	94.31 156	95.98 157	97.05 186	90.90 177	97.01 212	97.29 234	91.24 218	94.17 196	97.60 160	85.03 192	98.76 224	92.14 207	97.30 178	98.29 205

F-COLMAP		93.58 196	92.98 202	95.37 207	98.40 86	88.98 264	97.18 198	97.29 234	87.75 351	90.49 290	97.10 197	85.21 189	99.50 120	86.70 336	96.72 203	97.63 255

VortexMVS		92.88 231	92.64 217	93.58 318	96.58 237	87.53 308	96.93 221	97.28 237	92.78 156	89.75 314	94.99 313	82.73 242	97.76 358	94.60 154	88.16 358	95.46 340

XVG-ACMP-BASELINE		90.93 322	90.21 319	93.09 338	94.31 384	85.89 354	95.33 355	97.26 238	91.06 231	89.38 327	95.44 297	68.61 416	98.60 256	89.46 273	91.05 324	94.79 392

PCF-MVS	89.48 11	91.56 286	89.95 330	96.36 127	96.60 233	92.52 103	92.51 443	97.26 238	79.41 450	88.90 340	96.56 235	84.04 213	99.55 108	77.01 435	97.30 178	97.01 282
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 240	92.14 235	94.05 284	96.40 260	88.20 289	97.36 175	97.25 240	91.52 204	88.30 358	96.64 226	78.46 329	98.72 239	91.86 217	91.48 316	95.23 361
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 196	93.46 182	93.94 295	96.19 274	86.16 348	93.73 418	97.24 241	91.54 200	93.50 216	97.04 200	85.64 180	96.91 413	90.68 246	95.59 237	98.76 152

IMVS_0407		93.94 182	93.75 168	94.49 259	96.19 274	86.16 348	96.35 288	97.24 241	91.54 200	93.50 216	97.04 200	85.64 180	98.54 263	90.68 246	95.59 237	98.76 152

IMVS_0404		92.44 244	91.92 244	94.00 287	96.19 274	86.16 348	93.84 415	97.24 241	91.54 200	88.17 364	97.04 200	76.96 347	97.09 404	90.68 246	95.59 237	98.76 152

IMVS_0403		93.98 180	93.79 167	94.55 256	96.19 274	86.16 348	96.35 288	97.24 241	91.54 200	93.59 211	97.04 200	85.86 170	98.73 234	90.68 246	95.59 237	98.76 152

OPM-MVS		93.28 210	92.76 210	94.82 236	94.63 371	90.77 182	96.65 259	97.18 245	93.72 103	91.68 265	97.26 186	79.33 312	98.63 253	92.13 210	92.28 301	95.07 369
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 229	92.02 240	95.56 191	98.19 109	90.80 180	95.27 360	97.18 245	87.96 339	91.86 260	95.68 284	80.44 291	98.99 191	84.01 376	97.54 165	96.89 288

alignmvs		95.87 100	95.23 111	97.78 36	97.56 163	95.19 22	97.86 91	97.17 247	94.39 83	96.47 108	96.40 243	85.89 169	99.20 153	96.21 87	95.11 251	98.95 118

MVS_Test		94.89 141	94.62 139	95.68 185	96.83 209	89.55 235	96.70 253	97.17 247	91.17 224	95.60 146	96.11 262	87.87 126	98.76 224	93.01 196	97.17 185	98.72 160

Fast-Effi-MVS+		93.46 202	92.75 212	95.59 190	96.77 221	90.03 208	96.81 239	97.13 249	88.19 332	91.30 275	94.27 358	86.21 163	98.63 253	87.66 317	96.46 216	98.12 219

FE-MVSNET3		91.65 279	90.67 298	94.60 249	93.65 404	90.95 173	94.86 376	97.12 250	89.69 280	89.21 335	93.62 389	81.17 275	97.67 365	87.54 321	89.14 346	95.17 367

EI-MVSNet		93.03 222	92.88 206	93.48 323	95.77 302	86.98 322	96.44 273	97.12 250	90.66 247	91.30 275	97.64 156	86.56 154	98.05 315	89.91 261	90.55 332	95.41 344

MVSTER		93.20 213	92.81 209	94.37 265	96.56 242	89.59 231	97.06 206	97.12 250	91.24 218	91.30 275	95.96 265	82.02 259	98.05 315	93.48 181	90.55 332	95.47 339

viewmambaseed2359dif		94.28 162	94.14 159	94.71 246	96.21 270	86.97 323	95.93 320	97.11 253	89.00 303	95.00 168	97.70 146	86.02 168	98.59 260	93.71 176	96.59 209	98.57 172

test_yl		94.78 149	94.23 157	96.43 119	97.74 143	91.22 156	96.85 230	97.10 254	91.23 221	95.71 140	96.93 207	84.30 206	99.31 143	93.10 189	95.12 249	98.75 156

DCV-MVSNet		94.78 149	94.23 157	96.43 119	97.74 143	91.22 156	96.85 230	97.10 254	91.23 221	95.71 140	96.93 207	84.30 206	99.31 143	93.10 189	95.12 249	98.75 156

LTVRE_ROB	88.41 13	90.99 318	89.92 332	94.19 275	96.18 278	89.55 235	96.31 294	97.09 256	87.88 342	85.67 407	95.91 268	78.79 325	98.57 261	81.50 399	89.98 337	94.44 406
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		93.46 202	93.23 192	94.17 276	96.12 285	85.42 363	96.43 275	97.08 257	92.91 148	94.21 192	98.00 105	80.82 283	98.74 232	94.41 158	89.05 347	98.34 202

test_fmvs1_n		92.73 238	92.88 206	92.29 364	96.08 290	81.05 423	97.98 71	97.08 257	90.72 242	96.79 87	98.18 91	63.07 448	98.45 270	97.62 40	98.42 135	97.36 270

v10		91.04 316	90.23 316	93.49 322	94.12 387	88.16 292	97.32 180	97.08 257	88.26 331	88.29 359	94.22 363	82.17 256	97.97 327	86.45 340	84.12 409	94.33 409

viewdifsd2359ckpt11		93.46 202	93.22 193	94.17 276	96.11 287	85.42 363	96.43 275	97.07 260	92.91 148	94.20 193	98.00 105	80.82 283	98.73 234	94.42 157	89.04 349	98.34 202

mamba_0408		93.70 193	92.99 199	95.83 167	96.79 214	90.38 198	88.69 468	97.07 260	90.96 234	93.68 207	97.31 181	84.97 195	98.76 224	90.95 237	96.51 210	98.35 198

SSM_04072		93.51 201	92.99 199	95.05 220	96.79 214	90.38 198	88.69 468	97.07 260	90.96 234	93.68 207	97.31 181	84.97 195	96.42 424	90.95 237	96.51 210	98.35 198

v144192		91.06 315	90.28 312	93.39 326	93.66 402	87.23 316	96.83 234	97.07 260	87.43 358	89.69 317	94.28 357	81.48 269	98.00 322	87.18 330	84.92 398	94.93 377

v1192		91.07 314	90.23 316	93.58 318	93.70 399	87.82 303	96.73 249	97.07 260	87.77 349	89.58 320	94.32 355	80.90 281	97.97 327	86.52 338	85.48 385	94.95 373

v8		91.29 306	90.53 304	93.57 320	94.15 386	88.12 293	97.34 177	97.06 265	88.99 304	88.32 357	94.26 360	83.08 230	98.01 321	87.62 319	83.92 413	94.57 402

mvs_anonymous		93.82 188	93.74 169	94.06 283	96.44 258	85.41 365	95.81 328	97.05 266	89.85 275	90.09 305	96.36 245	87.44 141	97.75 360	93.97 167	96.69 204	99.02 103

IterMVS-LS		92.29 254	91.94 243	93.34 328	96.25 269	86.97 323	96.57 271	97.05 266	90.67 245	89.50 325	94.80 325	86.59 153	97.64 369	89.91 261	86.11 380	95.40 347
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 324	90.03 327	93.29 330	93.55 405	86.96 325	96.74 248	97.04 268	87.36 360	89.52 324	94.34 352	80.23 296	97.97 327	86.27 341	85.21 391	94.94 375

CDS-MVSNet		94.14 171	93.54 176	95.93 158	96.18 278	91.46 148	96.33 292	97.04 268	88.97 306	93.56 212	96.51 237	87.55 134	97.89 344	89.80 264	95.95 225	98.44 189
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 360	89.26 353	91.19 399	95.16 341	80.29 434	94.53 385	97.03 270	91.79 193	88.86 343	94.10 367	69.94 405	97.82 350	85.29 359	86.66 376	95.45 342

v1144		91.37 299	90.60 300	93.68 312	93.89 394	88.23 288	96.84 233	97.03 270	88.37 328	89.69 317	94.39 347	82.04 258	97.98 324	87.80 307	85.37 387	94.84 383

v1240		90.70 330	89.85 334	93.23 332	93.51 408	86.80 326	96.61 265	97.02 272	87.16 365	89.58 320	94.31 356	79.55 309	97.98 324	85.52 356	85.44 386	94.90 380

EPP-MVSNet		95.22 122	95.04 119	95.76 177	97.49 164	89.56 233	98.67 15	97.00 273	90.69 243	94.24 191	97.62 158	89.79 93	98.81 211	93.39 185	96.49 214	98.92 126

V42		91.58 285	90.87 283	93.73 306	94.05 390	88.50 279	97.32 180	96.97 274	88.80 316	89.71 315	94.33 353	82.54 247	98.05 315	89.01 287	85.07 394	94.64 401

test_fmvs1		93.21 212	93.53 177	92.25 367	96.55 244	81.20 422	97.40 171	96.96 275	90.68 244	96.80 85	98.04 100	69.25 411	98.40 273	97.58 41	98.50 128	97.16 280

FMVSNet2		91.31 303	90.08 322	94.99 226	96.51 251	92.21 114	97.41 167	96.95 276	88.82 313	88.62 349	94.75 327	73.87 374	97.42 392	85.20 362	88.55 355	95.35 351

ACMH	87.59 16	90.53 335	89.42 349	93.87 300	96.21 270	87.92 298	97.24 189	96.94 277	88.45 326	83.91 427	96.27 250	71.92 387	98.62 255	84.43 370	89.43 343	95.05 371
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 300	90.27 313	94.59 250	96.51 251	91.18 163	97.50 153	96.93 278	88.82 313	89.35 328	94.51 340	73.87 374	97.29 399	86.12 346	88.82 350	95.31 354

test1		91.35 300	90.27 313	94.59 250	96.51 251	91.18 163	97.50 153	96.93 278	88.82 313	89.35 328	94.51 340	73.87 374	97.29 399	86.12 346	88.82 350	95.31 354

FMVSNet3		91.78 273	90.69 297	95.03 223	96.53 247	92.27 112	97.02 209	96.93 278	89.79 278	89.35 328	94.65 333	77.01 345	97.47 387	86.12 346	88.82 350	95.35 351

FMVSNet1		89.88 355	88.31 368	94.59 250	95.41 320	91.18 163	97.50 153	96.93 278	86.62 373	87.41 378	94.51 340	65.94 438	97.29 399	83.04 385	87.43 366	95.31 354

GeoE		93.89 185	93.28 190	95.72 183	96.96 197	89.75 223	98.24 43	96.92 282	89.47 287	92.12 251	97.21 189	84.42 204	98.39 278	87.71 312	96.50 213	99.01 106

SymmetryMVS		95.94 96	95.54 96	97.15 74	97.85 136	92.90 87	97.99 68	96.91 283	95.92 16	96.57 102	97.93 111	85.34 185	99.50 120	94.99 129	96.39 220	99.05 102

miper_enhance_ethall		91.54 289	91.01 279	93.15 336	95.35 326	87.07 321	93.97 407	96.90 284	86.79 371	89.17 336	93.43 400	86.55 155	97.64 369	89.97 260	86.93 371	94.74 397

eth_miper_zixun_eth		91.02 317	90.59 301	92.34 362	95.33 330	84.35 384	94.10 404	96.90 284	88.56 322	88.84 345	94.33 353	84.08 211	97.60 374	88.77 293	84.37 407	95.06 370

TAMVS		94.01 177	93.46 182	95.64 186	96.16 280	90.45 193	96.71 252	96.89 286	89.27 294	93.46 219	96.92 210	87.29 144	97.94 337	88.70 295	95.74 231	98.53 175

miper_ehance_all_eth		91.59 283	91.13 275	92.97 342	95.55 312	86.57 334	94.47 388	96.88 287	87.77 349	88.88 342	94.01 372	86.22 162	97.54 380	89.49 272	86.93 371	94.79 392

v2v482		91.59 283	90.85 286	93.80 303	93.87 395	88.17 291	96.94 219	96.88 287	89.54 284	89.53 323	94.90 319	81.70 267	98.02 320	89.25 281	85.04 396	95.20 362

CNLPA		94.28 162	93.53 177	96.52 107	98.38 89	92.55 102	96.59 268	96.88 287	90.13 268	91.91 257	97.24 187	85.21 189	99.09 174	87.64 318	97.83 158	97.92 237

PAPM		91.52 290	90.30 311	95.20 213	95.30 333	89.83 220	93.38 429	96.85 290	86.26 381	88.59 350	95.80 274	84.88 197	98.15 297	75.67 440	95.93 226	97.63 255

c3_l		91.38 297	90.89 282	92.88 346	95.58 310	86.30 342	94.68 380	96.84 291	88.17 333	88.83 346	94.23 361	85.65 178	97.47 387	89.36 276	84.63 400	94.89 381

pm-mvs1		90.72 329	89.65 344	93.96 292	94.29 385	89.63 228	97.79 106	96.82 292	89.07 299	86.12 404	95.48 296	78.61 327	97.78 355	86.97 334	81.67 426	94.46 404

test_vis1_n		92.37 249	92.26 233	92.72 352	94.75 365	82.64 405	98.02 65	96.80 293	91.18 223	97.77 59	97.93 111	58.02 458	98.29 286	97.63 38	98.21 143	97.23 278

CMPMVS	62.92 21	85.62 411	84.92 403	87.74 437	89.14 455	73.12 467	94.17 402	96.80 293	73.98 463	73.65 465	94.93 317	66.36 432	97.61 373	83.95 378	91.28 320	92.48 441
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 342	89.77 338	91.78 383	94.33 382	84.72 381	95.55 344	96.73 295	86.17 383	86.36 400	95.28 302	71.28 392	97.80 353	84.09 375	98.14 147	92.81 433

Effi-MVS+-dtu		93.08 219	93.21 194	92.68 355	96.02 293	83.25 398	97.14 202	96.72 296	93.85 100	91.20 282	93.44 397	83.08 230	98.30 285	91.69 223	95.73 232	96.50 297

TSAR-MVS + GP.		96.69 67	96.49 71	97.27 67	98.31 92	93.39 67	96.79 241	96.72 296	94.17 89	97.44 65	97.66 152	92.76 34	99.33 139	96.86 62	97.76 162	99.08 98

1112_ss		93.37 207	92.42 229	96.21 139	97.05 186	90.99 170	96.31 294	96.72 296	86.87 370	89.83 312	96.69 223	86.51 156	99.14 166	88.12 300	93.67 284	98.50 179

PVSNet	86.66 18	92.24 257	91.74 252	93.73 306	97.77 141	83.69 395	92.88 438	96.72 296	87.91 341	93.00 230	94.86 321	78.51 328	99.05 186	86.53 337	97.45 171	98.47 184

miper_lstm_enhance		90.50 338	90.06 326	91.83 379	95.33 330	83.74 392	93.86 413	96.70 300	87.56 356	87.79 370	93.81 380	83.45 222	96.92 412	87.39 324	84.62 401	94.82 387

v148		90.99 318	90.38 307	92.81 349	93.83 396	85.80 355	96.78 245	96.68 301	89.45 289	88.75 348	93.93 376	82.96 236	97.82 350	87.83 306	83.25 418	94.80 390

ACMH+	87.92 14	90.20 346	89.18 355	93.25 331	96.48 254	86.45 339	96.99 215	96.68 301	88.83 312	84.79 416	96.22 252	70.16 402	98.53 264	84.42 371	88.04 359	94.77 395

CANet_DTU		94.37 160	93.65 172	96.55 104	96.46 257	92.13 118	96.21 302	96.67 303	94.38 84	93.53 215	97.03 205	79.34 311	99.71 67	90.76 243	98.45 133	97.82 248

cl____		90.96 321	90.32 309	92.89 345	95.37 324	86.21 345	94.46 390	96.64 304	87.82 345	88.15 365	94.18 364	82.98 234	97.54 380	87.70 313	85.59 383	94.92 379

HY-MVS	89.66 9	93.87 186	92.95 203	96.63 98	97.10 180	92.49 104	95.64 341	96.64 304	89.05 301	93.00 230	95.79 277	85.77 174	99.45 128	89.16 286	94.35 263	97.96 234

Test_1112_low_res		92.84 234	91.84 247	95.85 166	97.04 188	89.97 215	95.53 346	96.64 304	85.38 393	89.65 319	95.18 307	85.86 170	99.10 171	87.70 313	93.58 289	98.49 181

DIV-MVS_self_test		90.97 320	90.33 308	92.88 346	95.36 325	86.19 347	94.46 390	96.63 307	87.82 345	88.18 363	94.23 361	82.99 233	97.53 382	87.72 310	85.57 384	94.93 377

Fast-Effi-MVS+-dtu		92.29 254	91.99 241	93.21 334	95.27 334	85.52 361	97.03 207	96.63 307	92.09 184	89.11 338	95.14 309	80.33 294	98.08 308	87.54 321	94.74 259	96.03 315

UnsupCasMVSNet_bld		82.13 428	79.46 433	90.14 417	88.00 465	82.47 410	90.89 456	96.62 309	78.94 452	75.61 460	84.40 471	56.63 461	96.31 426	77.30 432	66.77 472	91.63 452

cl22		91.21 308	90.56 303	93.14 337	96.09 289	86.80 326	94.41 392	96.58 310	87.80 347	88.58 351	93.99 374	80.85 282	97.62 372	89.87 263	86.93 371	94.99 372

jason		94.84 145	94.39 152	96.18 141	95.52 313	90.93 175	96.09 310	96.52 311	89.28 293	96.01 129	97.32 179	84.70 199	98.77 219	95.15 125	98.91 113	98.85 142
jason: jason.
tt0805		91.09 313	90.07 325	94.16 279	95.61 308	88.31 283	97.56 144	96.51 312	89.56 283	89.17 336	95.64 286	67.08 430	98.38 279	91.07 235	88.44 356	95.80 323

AUN-MVS		91.76 274	90.75 292	94.81 238	97.00 193	88.57 275	96.65 259	96.49 313	89.63 281	92.15 249	96.12 258	78.66 326	98.50 266	90.83 239	79.18 437	97.36 270

hse-mvs2		93.45 205	92.99 199	94.81 238	97.02 191	88.59 274	96.69 255	96.47 314	95.19 36	96.74 89	96.16 256	83.67 217	98.48 269	95.85 102	79.13 438	97.35 272

SD_0403		90.01 350	90.02 328	89.96 420	95.65 307	76.76 455	95.76 332	96.46 315	90.58 254	86.59 397	96.29 248	82.12 257	94.78 449	73.00 454	93.76 282	98.35 198

EG-PatchMatch MVS		87.02 391	85.44 395	91.76 385	92.67 429	85.00 375	96.08 311	96.45 316	83.41 424	79.52 450	93.49 394	57.10 460	97.72 362	79.34 423	90.87 329	92.56 438

KD-MVS_self_test		85.95 407	84.95 402	88.96 431	89.55 454	79.11 449	95.13 369	96.42 317	85.91 386	84.07 425	90.48 439	70.03 404	94.82 448	80.04 415	72.94 459	92.94 431

FE-MVSNET2		86.36 400	84.68 408	91.39 393	87.67 467	86.47 338	96.21 302	96.41 318	87.87 343	79.31 452	89.64 447	65.29 442	95.58 440	82.42 394	77.28 444	92.14 449

pmmvs6		87.81 382	86.19 390	92.69 354	91.32 442	86.30 342	97.34 177	96.41 318	80.59 446	84.05 426	94.37 349	67.37 425	97.67 365	84.75 366	79.51 436	94.09 416

PMMVS		92.86 232	92.34 230	94.42 264	94.92 356	86.73 329	94.53 385	96.38 320	84.78 405	94.27 190	95.12 311	83.13 229	98.40 273	91.47 227	96.49 214	98.12 219

RPSCF		90.75 327	90.86 284	90.42 413	96.84 207	76.29 458	95.61 342	96.34 321	83.89 414	91.38 270	97.87 123	76.45 351	98.78 215	87.16 331	92.23 302	96.20 304

BP-MVS1		95.89 98	95.49 98	97.08 81	96.67 228	93.20 77	98.08 58	96.32 322	94.56 72	96.32 114	97.84 129	84.07 212	99.15 163	96.75 64	98.78 116	98.90 130

MSDG		91.42 295	90.24 315	94.96 231	97.15 178	88.91 265	93.69 421	96.32 322	85.72 389	86.93 393	96.47 239	80.24 295	98.98 192	80.57 412	95.05 252	96.98 283

blend_shiyan4		86.87 392	84.61 409	93.67 313	88.87 458	88.70 270	95.17 368	96.30 324	82.80 428	86.16 402	87.11 465	65.12 444	97.55 377	87.73 308	72.21 461	94.75 396

WBMVS		90.69 332	89.99 329	92.81 349	96.48 254	85.00 375	95.21 365	96.30 324	89.46 288	89.04 339	94.05 371	72.45 385	97.82 350	89.46 273	87.41 368	95.61 334

OurMVSNet-221017-0		90.51 337	90.19 320	91.44 391	93.41 414	81.25 420	96.98 216	96.28 326	91.68 197	86.55 398	96.30 247	74.20 373	97.98 324	88.96 289	87.40 369	95.09 368

MVP-Stereo		90.74 328	90.08 322	92.71 353	93.19 419	88.20 289	95.86 324	96.27 327	86.07 384	84.86 415	94.76 326	77.84 340	97.75 360	83.88 380	98.01 153	92.17 448
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 138	94.56 142	96.29 133	96.34 266	91.21 158	95.83 326	96.27 327	88.93 308	96.22 119	96.88 212	86.20 164	98.85 205	95.27 121	99.05 104	98.82 146

BH-untuned		92.94 227	92.62 219	93.92 299	97.22 172	86.16 348	96.40 283	96.25 329	90.06 269	89.79 313	96.17 255	83.19 226	98.35 281	87.19 329	97.27 180	97.24 277

CL-MVSNet_self_test		86.31 402	85.15 399	89.80 422	88.83 459	81.74 418	93.93 410	96.22 330	86.67 372	85.03 413	90.80 437	78.09 336	94.50 450	74.92 443	71.86 462	93.15 429

IS-MVSNet		94.90 140	94.52 146	96.05 148	97.67 147	90.56 189	98.44 26	96.22 330	93.21 127	93.99 200	97.74 143	85.55 182	98.45 270	89.98 259	97.86 157	99.14 88

FA-MVS(test-final)		93.52 200	92.92 204	95.31 210	96.77 221	88.54 277	94.82 377	96.21 332	89.61 282	94.20 193	95.25 305	83.24 224	99.14 166	90.01 258	96.16 222	98.25 207

GA-MVS		91.38 297	90.31 310	94.59 250	94.65 370	87.62 306	94.34 395	96.19 333	90.73 241	90.35 293	93.83 377	71.84 388	97.96 331	87.22 328	93.61 287	98.21 210

LuminaMVS		94.89 141	94.35 154	96.53 105	95.48 315	92.80 91	96.88 228	96.18 334	92.85 152	95.92 132	96.87 214	81.44 270	98.83 208	96.43 77	97.10 187	97.94 236

IterMVS-SCA-FT		90.31 340	89.81 336	91.82 380	95.52 313	84.20 387	94.30 398	96.15 335	90.61 251	87.39 379	94.27 358	75.80 357	96.44 423	87.34 325	86.88 375	94.82 387

IterMVS		90.15 348	89.67 342	91.61 387	95.48 315	83.72 393	94.33 396	96.12 336	89.99 270	87.31 382	94.15 366	75.78 359	96.27 427	86.97 334	86.89 374	94.83 384
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 237	91.51 261	96.52 107	98.77 62	90.99 170	97.38 174	96.08 337	82.38 431	89.29 331	97.87 123	83.77 215	99.69 73	81.37 405	96.69 204	98.89 136

pmmvs4		90.93 322	89.85 334	94.17 276	93.34 416	90.79 181	94.60 382	96.02 338	84.62 406	87.45 376	95.15 308	81.88 264	97.45 389	87.70 313	87.87 361	94.27 413

ppachtmachnet_test		88.35 377	87.29 376	91.53 388	92.45 435	83.57 396	93.75 417	95.97 339	84.28 409	85.32 412	94.18 364	79.00 323	96.93 411	75.71 439	84.99 397	94.10 414

Anonymous20240521		86.42 399	85.44 395	89.34 429	90.33 447	79.79 440	96.73 249	95.92 340	83.71 419	83.25 431	91.36 434	63.92 446	96.01 428	78.39 427	85.36 388	92.22 446

ITE_SJBPF				92.43 358	95.34 327	85.37 368		95.92 340	91.47 206	87.75 372	96.39 244	71.00 394	97.96 331	82.36 395	89.86 339	93.97 419

test_fmvs2		89.77 359	89.93 331	89.31 430	93.68 401	76.37 457	97.64 133	95.90 342	89.84 276	91.49 268	96.26 251	58.77 456	97.10 403	94.65 151	91.13 322	94.46 404

USDC		88.94 368	87.83 373	92.27 365	94.66 369	84.96 377	93.86 413	95.90 342	87.34 361	83.40 429	95.56 290	67.43 424	98.19 294	82.64 393	89.67 341	93.66 422

COLMAP_ROB	87.81 15	90.40 339	89.28 352	93.79 304	97.95 129	87.13 320	96.92 222	95.89 344	82.83 427	86.88 395	97.18 190	73.77 377	99.29 146	78.44 426	93.62 286	94.95 373
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 188	93.08 197	96.02 151	97.88 135	89.96 216	97.72 118	95.85 345	92.43 168	95.86 134	98.44 64	68.42 420	99.39 134	96.31 79	94.85 253	98.71 162

VDDNet		93.05 221	92.07 236	96.02 151	96.84 207	90.39 197	98.08 58	95.85 345	86.22 382	95.79 137	98.46 62	67.59 423	99.19 154	94.92 132	94.85 253	98.47 184

mvsmamba		94.57 155	94.14 159	95.87 162	97.03 189	89.93 217	97.84 95	95.85 345	91.34 212	94.79 175	96.80 215	80.67 285	98.81 211	94.85 136	98.12 148	98.85 142

Vis-MVSNet (Re-imp)		94.15 168	93.88 165	94.95 232	97.61 155	87.92 298	98.10 56	95.80 348	92.22 176	93.02 229	97.45 170	84.53 202	97.91 343	88.24 299	97.97 154	99.02 103

MM		97.29 31	96.98 42	98.23 12	98.01 123	95.03 27	98.07 60	95.76 349	97.78 1	97.52 62	98.80 38	88.09 119	99.86 9	99.44 2	99.37 67	99.80 1

KD-MVS_2432*1600		84.81 417	82.64 420	91.31 394	91.07 444	85.34 369	91.22 451	95.75 350	85.56 391	83.09 432	90.21 442	67.21 426	95.89 430	77.18 433	62.48 476	92.69 434

miper_refine_blended		84.81 417	82.64 420	91.31 394	91.07 444	85.34 369	91.22 451	95.75 350	85.56 391	83.09 432	90.21 442	67.21 426	95.89 430	77.18 433	62.48 476	92.69 434

FE-MVS		92.05 265	91.05 277	95.08 219	96.83 209	87.93 297	93.91 412	95.70 352	86.30 379	94.15 197	94.97 314	76.59 349	99.21 152	84.10 374	96.86 195	98.09 226

tpm cat1		88.36 376	87.21 379	91.81 381	95.13 346	80.55 429	92.58 442	95.70 352	74.97 462	87.45 376	91.96 427	78.01 339	98.17 296	80.39 414	88.74 353	96.72 293

our_test_3		88.78 372	87.98 372	91.20 398	92.45 435	82.53 407	93.61 425	95.69 354	85.77 388	84.88 414	93.71 382	79.99 300	96.78 419	79.47 420	86.24 377	94.28 412

BH-w/o		92.14 262	91.75 250	93.31 329	96.99 194	85.73 358	95.67 336	95.69 354	88.73 318	89.26 333	94.82 324	82.97 235	98.07 312	85.26 361	96.32 221	96.13 311

CR-MVSNet		90.82 325	89.77 338	93.95 293	94.45 378	87.19 317	90.23 459	95.68 356	86.89 369	92.40 239	92.36 419	80.91 279	97.05 406	81.09 409	93.95 279	97.60 260

Patchmtry		88.64 374	87.25 377	92.78 351	94.09 388	86.64 330	89.82 463	95.68 356	80.81 443	87.63 374	92.36 419	80.91 279	97.03 407	78.86 424	85.12 393	94.67 399

testing91		91.90 270	91.02 278	94.53 258	96.54 245	86.55 336	95.86 324	95.64 358	91.77 194	91.89 258	93.47 396	69.94 405	98.86 203	90.23 257	93.86 281	98.18 212

BH-RMVSNet		92.72 239	91.97 242	94.97 230	97.16 176	87.99 296	96.15 308	95.60 359	90.62 250	91.87 259	97.15 193	78.41 330	98.57 261	83.16 383	97.60 164	98.36 196

PVSNet_0	82.17 19	85.46 412	83.64 415	90.92 402	95.27 334	79.49 445	90.55 457	95.60 359	83.76 418	83.00 434	89.95 444	71.09 393	97.97 327	82.75 391	60.79 478	95.31 354

guyue		95.17 127	94.96 123	95.82 168	96.97 196	89.65 227	97.56 144	95.58 361	94.82 57	95.72 139	97.42 174	82.90 237	98.84 207	96.71 67	96.93 192	98.96 114

SCA		91.84 272	91.18 274	93.83 301	95.59 309	84.95 378	94.72 379	95.58 361	90.82 237	92.25 247	93.69 384	75.80 357	98.10 303	86.20 343	95.98 224	98.45 186

MonoMVSNet		91.92 268	91.77 248	92.37 359	92.94 423	83.11 401	97.09 205	95.55 363	92.91 148	90.85 285	94.55 337	81.27 274	96.52 422	93.01 196	87.76 362	97.47 266

usedtu_blend_shiyan5		87.06 390	84.84 404	93.69 310	88.54 463	88.70 270	95.83 326	95.54 364	78.74 453	85.92 405	86.89 467	73.03 381	97.55 377	87.73 308	71.36 463	94.83 384

AllTest		90.23 344	88.98 358	93.98 289	97.94 130	86.64 330	96.51 272	95.54 364	85.38 393	85.49 409	96.77 217	70.28 400	99.15 163	80.02 416	92.87 291	96.15 309

TestCases				93.98 289	97.94 130	86.64 330		95.54 364	85.38 393	85.49 409	96.77 217	70.28 400	99.15 163	80.02 416	92.87 291	96.15 309

mmtdpeth		89.70 361	88.96 359	91.90 376	95.84 301	84.42 383	97.46 164	95.53 367	90.27 263	94.46 186	90.50 438	69.74 409	98.95 193	97.39 53	69.48 467	92.34 442

tpmvs		89.83 358	89.15 356	91.89 377	94.92 356	80.30 433	93.11 434	95.46 368	86.28 380	88.08 366	92.65 409	80.44 291	98.52 265	81.47 401	89.92 338	96.84 289

pmmvs5		89.86 357	88.87 362	92.82 348	92.86 425	86.23 344	96.26 297	95.39 369	84.24 410	87.12 384	94.51 340	74.27 372	97.36 396	87.61 320	87.57 364	94.86 382

PatchmatchNet		91.91 269	91.35 263	93.59 317	95.38 322	84.11 388	93.15 433	95.39 369	89.54 284	92.10 252	93.68 386	82.82 240	98.13 298	84.81 365	95.32 245	98.52 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 294	91.32 265	91.79 382	95.15 344	79.20 448	93.42 428	95.37 371	88.55 323	93.49 218	93.67 387	82.49 249	98.27 287	90.41 252	89.34 344	97.90 238

Anonymous20231206		87.09 389	86.14 391	89.93 421	91.22 443	80.35 431	96.11 309	95.35 372	83.57 421	84.16 421	93.02 404	73.54 379	95.61 438	72.16 456	86.14 379	93.84 421

MIMVSNet1		84.93 415	83.05 417	90.56 411	89.56 453	84.84 380	95.40 351	95.35 372	83.91 413	80.38 446	92.21 424	57.23 459	93.34 463	70.69 462	82.75 424	93.50 424

TDRefinement		86.53 395	84.76 406	91.85 378	82.23 479	84.25 385	96.38 285	95.35 372	84.97 402	84.09 424	94.94 316	65.76 439	98.34 284	84.60 369	74.52 455	92.97 430

TR-MVS		91.48 293	90.59 301	94.16 279	96.40 260	87.33 310	95.67 336	95.34 375	87.68 353	91.46 269	95.52 293	76.77 348	98.35 281	82.85 388	93.61 287	96.79 291

EPNet_dtu		91.71 275	91.28 268	92.99 341	93.76 398	83.71 394	96.69 255	95.28 376	93.15 134	87.02 389	95.95 266	83.37 223	97.38 395	79.46 421	96.84 196	97.88 240
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 386	85.79 393	91.78 383	94.80 363	87.28 312	95.49 348	95.28 376	84.09 412	83.85 428	91.82 428	62.95 449	94.17 454	78.48 425	85.34 389	93.91 420

MDTV_nov1_ep13			90.76 290		95.22 338	80.33 432	93.03 436	95.28 376	88.14 336	92.84 236	93.83 377	81.34 271	98.08 308	82.86 386	94.34 264

LF4IMVS		87.94 380	87.25 377	89.98 419	92.38 437	80.05 439	94.38 393	95.25 379	87.59 355	84.34 418	94.74 328	64.31 445	97.66 368	84.83 364	87.45 365	92.23 445

TransMVSNet (Re)		88.94 368	87.56 374	93.08 339	94.35 381	88.45 281	97.73 115	95.23 380	87.47 357	84.26 420	95.29 300	79.86 303	97.33 397	79.44 422	74.44 456	93.45 426

test20.03		86.14 405	85.40 397	88.35 432	90.12 448	80.06 438	95.90 323	95.20 381	88.59 319	81.29 441	93.62 389	71.43 391	92.65 467	71.26 460	81.17 429	92.34 442

new-patchmatchnet		83.18 424	81.87 427	87.11 440	86.88 470	75.99 459	93.70 419	95.18 382	85.02 401	77.30 459	88.40 456	65.99 437	93.88 459	74.19 448	70.18 465	91.47 457

MDA-MVSNet_test_wron		85.87 409	84.23 412	90.80 408	92.38 437	82.57 406	93.17 431	95.15 383	82.15 432	67.65 471	92.33 422	78.20 332	95.51 442	77.33 430	79.74 433	94.31 411

YYNet1		85.87 409	84.23 412	90.78 409	92.38 437	82.46 411	93.17 431	95.14 384	82.12 433	67.69 469	92.36 419	78.16 335	95.50 443	77.31 431	79.73 434	94.39 407

Baseline_NR-MVSNet		91.20 309	90.62 299	92.95 343	93.83 396	88.03 295	97.01 212	95.12 385	88.42 327	89.70 316	95.13 310	83.47 220	97.44 390	89.66 269	83.24 419	93.37 427

thres200		92.23 258	91.39 262	94.75 245	97.61 155	89.03 260	96.60 267	95.09 386	92.08 185	93.28 224	94.00 373	78.39 331	99.04 189	81.26 408	94.18 270	96.19 305

ADS-MVSNet		89.89 354	88.68 364	93.53 321	95.86 296	84.89 379	90.93 454	95.07 387	83.23 425	91.28 278	91.81 429	79.01 321	97.85 346	79.52 418	91.39 318	97.84 245

pmmvs-eth3d		86.22 403	84.45 410	91.53 388	88.34 464	87.25 314	94.47 388	95.01 388	83.47 422	79.51 451	89.61 448	69.75 408	95.71 435	83.13 384	76.73 448	91.64 451

Anonymous202405211		92.07 264	90.83 288	95.76 177	98.19 109	88.75 268	97.58 140	95.00 389	86.00 385	93.64 210	97.45 170	66.24 435	99.53 112	90.68 246	92.71 296	99.01 106

MDA-MVSNet-bldmvs		85.00 414	82.95 419	91.17 400	93.13 421	83.33 397	94.56 384	95.00 389	84.57 407	65.13 475	92.65 409	70.45 399	95.85 432	73.57 451	77.49 443	94.33 409

ambc				86.56 443	83.60 476	70.00 470	85.69 475	94.97 391		80.60 445	88.45 455	37.42 477	96.84 416	82.69 392	75.44 453	92.86 432

testgi		87.97 379	87.21 379	90.24 416	92.86 425	80.76 424	96.67 258	94.97 391	91.74 195	85.52 408	95.83 272	62.66 451	94.47 452	76.25 437	88.36 357	95.48 337

myMVS_eth3d28		91.52 290	90.97 280	93.17 335	96.91 199	83.24 399	95.61 342	94.96 393	92.24 175	91.98 255	93.28 401	69.31 410	98.40 273	88.71 294	95.68 234	97.88 240

dp		88.90 370	88.26 370	90.81 406	94.58 374	76.62 456	92.85 439	94.93 394	85.12 399	90.07 307	93.07 403	75.81 356	98.12 301	80.53 413	87.42 367	97.71 252

test_fmvs3		83.21 423	83.02 418	83.78 447	86.77 471	68.34 473	96.76 247	94.91 395	86.49 375	84.14 423	89.48 449	36.04 478	91.73 469	91.86 217	80.77 431	91.26 459

test_0402		86.46 398	84.79 405	91.45 390	95.02 350	85.55 360	96.29 296	94.89 396	80.90 440	82.21 437	93.97 375	68.21 421	97.29 399	62.98 470	88.68 354	91.51 454

tfpn200view9		92.38 248	91.52 259	94.95 232	97.85 136	89.29 249	97.41 167	94.88 397	92.19 181	93.27 225	94.46 345	78.17 333	99.08 177	81.40 402	94.08 274	96.48 298

CVMVSNet		91.23 307	91.75 250	89.67 423	95.77 302	74.69 460	96.44 273	94.88 397	85.81 387	92.18 248	97.64 156	79.07 316	95.58 440	88.06 302	95.86 229	98.74 159

thres400		92.42 246	91.52 259	95.12 218	97.85 136	89.29 249	97.41 167	94.88 397	92.19 181	93.27 225	94.46 345	78.17 333	99.08 177	81.40 402	94.08 274	96.98 283

tt0320		85.39 413	83.12 416	92.19 369	93.44 413	85.79 356	96.19 305	94.87 400	71.19 469	82.92 435	91.76 431	58.43 457	96.81 417	81.03 410	78.26 442	93.98 418

EPNet		95.20 123	94.56 142	97.14 75	92.80 427	92.68 97	97.85 94	94.87 400	96.64 9	92.46 238	97.80 137	86.23 161	99.65 79	93.72 175	98.62 124	99.10 95
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 281	90.72 295	94.32 269	96.48 254	86.11 353	95.81 328	94.76 402	91.55 199	91.75 263	93.44 397	68.55 418	98.82 209	90.43 251	93.69 283	98.04 230

sc_t1		86.48 397	84.10 414	93.63 314	93.45 412	85.76 357	96.79 241	94.71 403	73.06 467	86.45 399	94.35 350	55.13 464	97.95 335	84.38 372	78.55 441	97.18 279

SixPastTwentyTwo		89.15 366	88.54 366	90.98 401	93.49 409	80.28 435	96.70 253	94.70 404	90.78 238	84.15 422	95.57 289	71.78 389	97.71 363	84.63 368	85.07 394	94.94 375

thres100view900		92.43 245	91.58 256	94.98 228	97.92 132	89.37 245	97.71 120	94.66 405	92.20 179	93.31 223	94.90 319	78.06 337	99.08 177	81.40 402	94.08 274	96.48 298

thres600view7		92.49 243	91.60 255	95.18 214	97.91 133	89.47 239	97.65 129	94.66 405	92.18 183	93.33 222	94.91 318	78.06 337	99.10 171	81.61 398	94.06 278	96.98 283

PatchT		88.87 371	87.42 375	93.22 333	94.08 389	85.10 373	89.51 464	94.64 407	81.92 434	92.36 242	88.15 459	80.05 299	97.01 409	72.43 455	93.65 285	97.54 263

baseline1		92.82 235	91.90 245	95.55 193	97.20 174	90.77 182	97.19 197	94.58 408	92.20 179	92.36 242	96.34 246	84.16 210	98.21 291	89.20 284	83.90 414	97.68 254

AstraMVS		94.82 147	94.64 138	95.34 209	96.36 265	88.09 294	97.58 140	94.56 409	94.98 46	95.70 142	97.92 114	81.93 263	98.93 196	96.87 61	95.88 227	98.99 110

UBG		91.55 287	90.76 290	93.94 295	96.52 250	85.06 374	95.22 363	94.54 410	90.47 259	91.98 255	92.71 408	72.02 386	98.74 232	88.10 301	95.26 247	98.01 232

Gipuma		67.86 444	65.41 446	75.18 460	92.66 430	73.45 464	66.50 482	94.52 411	53.33 480	57.80 481	66.07 481	30.81 480	89.20 473	48.15 479	78.88 440	62.90 481
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 278	90.75 292	94.47 260	96.53 247	86.56 335	95.76 332	94.51 412	91.10 230	91.24 280	93.59 391	68.59 417	98.86 203	91.10 234	94.29 266	98.00 233

CostFormer		91.18 312	90.70 296	92.62 356	94.84 361	81.76 417	94.09 405	94.43 413	84.15 411	92.72 237	93.77 381	79.43 310	98.20 292	90.70 245	92.18 305	97.90 238

tpm2		89.96 351	89.21 354	92.23 368	94.91 358	81.25 420	93.78 416	94.42 414	80.62 445	91.56 266	93.44 397	76.44 352	97.94 337	85.60 355	92.08 309	97.49 264

testing3-2		92.10 263	92.05 237	92.27 365	97.71 145	79.56 442	97.42 166	94.41 415	93.53 113	93.22 227	95.49 294	69.16 412	99.11 169	93.25 186	94.22 268	98.13 217

MGCNet		96.74 64	96.31 81	98.02 20	96.87 203	94.65 31	97.58 140	94.39 416	96.47 12	97.16 74	98.39 68	87.53 136	99.87 7	98.97 20	99.41 59	99.55 43

JIA-IIPM		88.26 378	87.04 382	91.91 375	93.52 407	81.42 419	89.38 465	94.38 417	80.84 442	90.93 284	80.74 473	79.22 313	97.92 340	82.76 390	91.62 313	96.38 301

dmvs_re		90.21 345	89.50 347	92.35 360	95.47 319	85.15 371	95.70 335	94.37 418	90.94 236	88.42 353	93.57 392	74.63 369	95.67 437	82.80 389	89.57 342	96.22 303

Patchmatch-test		89.42 364	87.99 371	93.70 309	95.27 334	85.11 372	88.98 466	94.37 418	81.11 439	87.10 387	93.69 384	82.28 253	97.50 385	74.37 446	94.76 257	98.48 183

LCM-MVSNet		72.55 437	69.39 441	82.03 449	70.81 489	65.42 478	90.12 461	94.36 420	55.02 479	65.88 473	81.72 472	24.16 486	89.96 470	74.32 447	68.10 470	90.71 462

ADS-MVSNet2		89.45 363	88.59 365	92.03 372	95.86 296	82.26 413	90.93 454	94.32 421	83.23 425	91.28 278	91.81 429	79.01 321	95.99 429	79.52 418	91.39 318	97.84 245

mvs5depth		86.53 395	85.08 400	90.87 403	88.74 461	82.52 408	91.91 447	94.23 422	86.35 378	87.11 386	93.70 383	66.52 431	97.76 358	81.37 405	75.80 450	92.31 444

EU-MVSNet		88.72 373	88.90 361	88.20 434	93.15 420	74.21 462	96.63 264	94.22 423	85.18 397	87.32 381	95.97 264	76.16 354	94.98 447	85.27 360	86.17 378	95.41 344

tt0320-xc		84.83 416	82.33 424	92.31 363	93.66 402	86.20 346	96.17 307	94.06 424	71.26 468	82.04 439	92.22 423	55.07 465	96.72 420	81.49 400	75.04 454	94.02 417

MIMVSNet		88.50 375	86.76 385	93.72 308	94.84 361	87.77 304	91.39 449	94.05 425	86.41 377	87.99 368	92.59 412	63.27 447	95.82 434	77.44 429	92.84 293	97.57 262

OpenMVS_ROB	81.14 20	84.42 419	82.28 425	90.83 404	90.06 449	84.05 390	95.73 334	94.04 426	73.89 465	80.17 449	91.53 433	59.15 455	97.64 369	66.92 468	89.05 347	90.80 461

TinyColmap		86.82 393	85.35 398	91.21 396	94.91 358	82.99 403	93.94 409	94.02 427	83.58 420	81.56 440	94.68 330	62.34 452	98.13 298	75.78 438	87.35 370	92.52 440

ETVMVS		90.52 336	89.14 357	94.67 248	96.81 213	87.85 302	95.91 322	93.97 428	89.71 279	92.34 245	92.48 414	65.41 441	97.96 331	81.37 405	94.27 267	98.21 210

IB-MVS	87.33 17	89.91 352	88.28 369	94.79 242	95.26 337	87.70 305	95.12 370	93.95 429	89.35 292	87.03 388	92.49 413	70.74 397	99.19 154	89.18 285	81.37 428	97.49 264
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		87.13 388	87.02 383	87.47 438	95.16 341	73.21 466	95.00 372	93.93 430	88.55 323	86.96 390	91.99 425	75.90 355	94.00 456	61.59 472	94.11 271	95.20 362

myMVS_eth3d		87.18 387	86.38 388	89.58 424	95.16 341	79.53 443	95.00 372	93.93 430	88.55 323	86.96 390	91.99 425	56.23 462	94.00 456	75.47 442	94.11 271	95.20 362

testing222		90.31 340	88.96 359	94.35 266	96.54 245	87.29 311	95.50 347	93.84 432	90.97 233	91.75 263	92.96 405	62.18 453	98.00 322	82.86 386	94.08 274	97.76 250

test_f		80.57 430	79.62 432	83.41 448	83.38 477	67.80 475	93.57 426	93.72 433	80.80 444	77.91 458	87.63 462	33.40 479	92.08 468	87.14 332	79.04 439	90.34 463

LCM-MVSNet-Re		92.50 241	92.52 225	92.44 357	96.82 211	81.89 416	96.92 222	93.71 434	92.41 169	84.30 419	94.60 335	85.08 191	97.03 407	91.51 225	97.36 173	98.40 192

tpm		90.25 343	89.74 341	91.76 385	93.92 392	79.73 441	93.98 406	93.54 435	88.28 330	91.99 254	93.25 402	77.51 343	97.44 390	87.30 327	87.94 360	98.12 219

ET-MVSNet_ETH3D		91.49 292	90.11 321	95.63 187	96.40 260	91.57 142	95.34 354	93.48 436	90.60 253	75.58 461	95.49 294	80.08 298	96.79 418	94.25 163	89.76 340	98.52 176

LFMVS		93.60 195	92.63 218	96.52 107	98.13 115	91.27 155	97.94 81	93.39 437	90.57 255	96.29 116	98.31 81	69.00 413	99.16 161	94.18 164	95.87 228	99.12 92

MVStest1		82.38 427	80.04 431	89.37 427	87.63 468	82.83 404	95.03 371	93.37 438	73.90 464	73.50 466	94.35 350	62.89 450	93.25 465	73.80 449	65.92 473	92.04 450

FE-MVSNET		83.85 420	81.97 426	89.51 425	87.19 469	83.19 400	95.21 365	93.17 439	83.45 423	78.90 454	89.05 452	65.46 440	93.84 460	69.71 464	75.56 452	91.51 454

Patchmatch-RL test		87.38 385	86.24 389	90.81 406	88.74 461	78.40 452	88.12 473	93.17 439	87.11 366	82.17 438	89.29 450	81.95 261	95.60 439	88.64 296	77.02 445	98.41 191

ttmdpeth		85.91 408	84.76 406	89.36 428	89.14 455	80.25 436	95.66 339	93.16 441	83.77 417	83.39 430	95.26 304	66.24 435	95.26 446	80.65 411	75.57 451	92.57 437

test-LLR		91.42 295	91.19 273	92.12 370	94.59 372	80.66 426	94.29 399	92.98 442	91.11 228	90.76 287	92.37 416	79.02 319	98.07 312	88.81 291	96.74 201	97.63 255

test-mter		90.19 347	89.54 346	92.12 370	94.59 372	80.66 426	94.29 399	92.98 442	87.68 353	90.76 287	92.37 416	67.67 422	98.07 312	88.81 291	96.74 201	97.63 255

WB-MVSnew		89.88 355	89.56 345	90.82 405	94.57 375	83.06 402	95.65 340	92.85 444	87.86 344	90.83 286	94.10 367	79.66 307	96.88 414	76.34 436	94.19 269	92.54 439

testing3		87.67 383	86.88 384	90.05 418	96.14 283	80.71 425	97.10 204	92.85 444	90.15 267	87.54 375	94.55 337	55.70 463	94.10 455	73.77 450	94.10 273	95.35 351

test_method		66.11 445	64.89 447	69.79 463	72.62 487	35.23 495	65.19 483	92.83 446	20.35 485	65.20 474	88.08 460	43.14 475	82.70 480	73.12 453	63.46 475	91.45 458

test0.0.03 1		89.37 365	88.70 363	91.41 392	92.47 434	85.63 359	95.22 363	92.70 447	91.11 228	86.91 394	93.65 388	79.02 319	93.19 466	78.00 428	89.18 345	95.41 344

new_pmnet		82.89 425	81.12 430	88.18 435	89.63 452	80.18 437	91.77 448	92.57 448	76.79 460	75.56 462	88.23 458	61.22 454	94.48 451	71.43 458	82.92 422	89.87 464

mvsany_test1		93.93 184	93.98 163	93.78 305	94.94 355	86.80 326	94.62 381	92.55 449	88.77 317	96.85 84	98.49 58	88.98 101	98.08 308	95.03 127	95.62 236	96.46 300

thisisatest0515		92.29 254	91.30 267	95.25 212	96.60 233	88.90 266	94.36 394	92.32 450	87.92 340	93.43 220	94.57 336	77.28 344	99.00 190	89.42 275	95.86 229	97.86 244

thisisatest0530		93.03 222	92.21 234	95.49 201	97.07 181	89.11 258	97.49 161	92.19 451	90.16 266	94.09 198	96.41 242	76.43 353	99.05 186	90.38 253	95.68 234	98.31 204

tttt0517		92.96 225	92.33 231	94.87 235	97.11 179	87.16 319	97.97 77	92.09 452	90.63 249	93.88 204	97.01 206	76.50 350	99.06 183	90.29 256	95.45 243	98.38 194

K. test v3		87.64 384	86.75 386	90.32 415	93.02 422	79.48 446	96.61 265	92.08 453	90.66 247	80.25 448	94.09 369	67.21 426	96.65 421	85.96 351	80.83 430	94.83 384

TESTMET0.1,1		90.06 349	89.42 349	91.97 373	94.41 380	80.62 428	94.29 399	91.97 454	87.28 363	90.44 291	92.47 415	68.79 414	97.67 365	88.50 298	96.60 208	97.61 259

PM-MVS		83.48 422	81.86 428	88.31 433	87.83 466	77.59 454	93.43 427	91.75 455	86.91 368	80.63 444	89.91 445	44.42 474	95.84 433	85.17 363	76.73 448	91.50 456

baseline2		91.63 280	90.86 284	93.94 295	94.33 382	86.32 341	95.92 321	91.64 456	89.37 291	86.94 392	94.69 329	81.62 268	98.69 242	88.64 296	94.57 262	96.81 290

APD_test1		79.31 432	77.70 435	84.14 446	89.11 457	69.07 472	92.36 446	91.50 457	69.07 471	73.87 464	92.63 411	39.93 476	94.32 453	70.54 463	80.25 432	89.02 466

FPMVS		71.27 438	69.85 440	75.50 459	74.64 484	59.03 484	91.30 450	91.50 457	58.80 476	57.92 480	88.28 457	29.98 482	85.53 479	53.43 477	82.84 423	81.95 472

door								91.13 459

door-mid								91.06 460

EGC-MVSNET		68.77 443	63.01 449	86.07 445	92.49 433	82.24 414	93.96 408	90.96 461	0.71 490	2.62 491	90.89 436	53.66 466	93.46 461	57.25 475	84.55 404	82.51 471

mvsany_test3		83.59 421	82.44 423	87.03 441	83.80 474	73.82 463	93.70 419	90.92 462	86.42 376	82.51 436	90.26 441	46.76 473	95.71 435	90.82 240	76.76 447	91.57 453

pmmvs3		79.97 431	77.50 436	87.39 439	82.80 478	79.38 447	92.70 441	90.75 463	70.69 470	78.66 455	87.47 464	51.34 469	93.40 462	73.39 452	69.65 466	89.38 465

UWE-MVS		89.91 352	89.48 348	91.21 396	95.88 295	78.23 453	94.91 375	90.26 464	89.11 298	92.35 244	94.52 339	68.76 415	97.96 331	83.95 378	95.59 237	97.42 268

DSMNet-mixed		86.34 401	86.12 392	87.00 442	89.88 451	70.43 468	94.93 374	90.08 465	77.97 457	85.42 411	92.78 407	74.44 371	93.96 458	74.43 445	95.14 248	96.62 294

MVS-HIRNet		82.47 426	81.21 429	86.26 444	95.38 322	69.21 471	88.96 467	89.49 466	66.28 473	80.79 443	74.08 478	68.48 419	97.39 394	71.93 457	95.47 242	92.18 447

WB-MVS		76.77 434	76.63 437	77.18 454	85.32 472	56.82 486	94.53 385	89.39 467	82.66 430	71.35 467	89.18 451	75.03 364	88.88 474	35.42 483	66.79 471	85.84 468

test1111		93.19 214	92.82 208	94.30 272	97.58 161	84.56 382	98.21 47	89.02 468	93.53 113	94.58 180	98.21 88	72.69 382	99.05 186	93.06 192	98.48 131	99.28 77

SSC-MVS		76.05 435	75.83 438	76.72 458	84.77 473	56.22 487	94.32 397	88.96 469	81.82 436	70.52 468	88.91 453	74.79 368	88.71 475	33.69 484	64.71 474	85.23 469

ECVR-MVS		93.19 214	92.73 214	94.57 255	97.66 149	85.41 365	98.21 47	88.23 470	93.43 120	94.70 177	98.21 88	72.57 383	99.07 181	93.05 193	98.49 129	99.25 80

EPMVS		90.70 330	89.81 336	93.37 327	94.73 367	84.21 386	93.67 422	88.02 471	89.50 286	92.38 241	93.49 394	77.82 341	97.78 355	86.03 349	92.68 297	98.11 225

ANet_high		63.94 447	59.58 450	77.02 455	61.24 491	66.06 476	85.66 476	87.93 472	78.53 455	42.94 483	71.04 480	25.42 485	80.71 482	52.60 478	30.83 484	84.28 470

PMMVS2		70.19 439	66.92 443	80.01 450	76.35 483	65.67 477	86.22 474	87.58 473	64.83 475	62.38 476	80.29 475	26.78 484	88.49 477	63.79 469	54.07 480	85.88 467

lessismore_v0				90.45 412	91.96 440	79.09 450		87.19 474		80.32 447	94.39 347	66.31 434	97.55 377	84.00 377	76.84 446	94.70 398

PMVS	53.92 22	58.58 448	55.40 451	68.12 464	51.00 492	48.64 489	78.86 479	87.10 475	46.77 481	35.84 487	74.28 477	8.76 490	86.34 478	42.07 481	73.91 457	69.38 478
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 394	86.41 387	88.02 436	92.87 424	74.60 461	95.38 353	86.70 476	88.17 333	87.28 383	94.67 332	70.83 396	93.30 464	67.45 466	94.31 265	96.17 306

test_vis1_rt		86.16 404	85.06 401	89.46 426	93.47 411	80.46 430	96.41 279	86.61 477	85.22 396	79.15 453	88.64 454	52.41 468	97.06 405	93.08 191	90.57 331	90.87 460

testf1		69.31 441	66.76 444	76.94 456	78.61 481	61.93 480	88.27 471	86.11 478	55.62 477	59.69 477	85.31 469	20.19 488	89.32 471	57.62 473	69.44 468	79.58 473

APD_test2		69.31 441	66.76 444	76.94 456	78.61 481	61.93 480	88.27 471	86.11 478	55.62 477	59.69 477	85.31 469	20.19 488	89.32 471	57.62 473	69.44 468	79.58 473

gg-mvs-nofinetune		87.82 381	85.61 394	94.44 262	94.46 377	89.27 252	91.21 453	84.61 480	80.88 441	89.89 311	74.98 476	71.50 390	97.53 382	85.75 354	97.21 182	96.51 296

dmvs_testset		81.38 429	82.60 422	77.73 453	91.74 441	51.49 488	93.03 436	84.21 481	89.07 299	78.28 457	91.25 435	76.97 346	88.53 476	56.57 476	82.24 425	93.16 428

GG-mvs-BLEND				93.62 315	93.69 400	89.20 254	92.39 445	83.33 482		87.98 369	89.84 446	71.00 394	96.87 415	82.08 397	95.40 244	94.80 390

MTMP							97.86 91	82.03 483

DeepMVS_CX				74.68 461	90.84 446	64.34 479		81.61 484	65.34 474	67.47 472	88.01 461	48.60 472	80.13 483	62.33 471	73.68 458	79.58 473

E-PMN		53.28 449	52.56 453	55.43 467	74.43 485	47.13 490	83.63 478	76.30 485	42.23 482	42.59 484	62.22 483	28.57 483	74.40 484	31.53 485	31.51 483	44.78 482

test2506		91.60 282	90.78 289	94.04 285	97.66 149	83.81 391	98.27 37	75.53 486	93.43 120	95.23 159	98.21 88	67.21 426	99.07 181	93.01 196	98.49 129	99.25 80

EMVS		52.08 451	51.31 454	54.39 468	72.62 487	45.39 492	83.84 477	75.51 487	41.13 483	40.77 485	59.65 484	30.08 481	73.60 485	28.31 487	29.90 485	44.18 483

test_vis3_rt		72.73 436	70.55 439	79.27 451	80.02 480	68.13 474	93.92 411	74.30 488	76.90 459	58.99 479	73.58 479	20.29 487	95.37 444	84.16 373	72.80 460	74.31 476

MVE	50.73 23	53.25 450	48.81 455	66.58 466	65.34 490	57.50 485	72.49 481	70.94 489	40.15 484	39.28 486	63.51 482	6.89 492	73.48 486	38.29 482	42.38 482	68.76 480
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 452	53.82 452	46.29 469	33.73 493	45.30 493	78.32 480	67.24 490	18.02 486	50.93 482	87.05 466	52.99 467	53.11 488	70.76 461	25.29 486	40.46 484

kuosan		65.27 446	64.66 448	67.11 465	83.80 474	61.32 483	88.53 470	60.77 491	68.22 472	67.67 470	80.52 474	49.12 471	70.76 487	29.67 486	53.64 481	69.26 479

dongtai		69.99 440	69.33 442	71.98 462	88.78 460	61.64 482	89.86 462	59.93 492	75.67 461	74.96 463	85.45 468	50.19 470	81.66 481	43.86 480	55.27 479	72.63 477

N_pmnet		78.73 433	78.71 434	78.79 452	92.80 427	46.50 491	94.14 403	43.71 493	78.61 454	80.83 442	91.66 432	74.94 367	96.36 425	67.24 467	84.45 406	93.50 424

wuyk23d		25.11 453	24.57 457	26.74 470	73.98 486	39.89 494	57.88 484	9.80 494	12.27 487	10.39 488	6.97 490	7.03 491	36.44 489	25.43 488	17.39 487	3.89 487

testmvs		13.36 455	16.33 458	4.48 472	5.04 494	2.26 497	93.18 430	3.28 495	2.70 488	8.24 489	21.66 486	2.29 494	2.19 490	7.58 489	2.96 488	9.00 486

test123		13.04 456	15.66 459	5.18 471	4.51 495	3.45 496	92.50 444	1.81 496	2.50 489	7.58 490	20.15 487	3.67 493	2.18 491	7.13 490	1.07 489	9.90 485

mmdepth		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

monomultidepth		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

test_blank		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

uanet_test		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

DCPMVS		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

pcd_1.5k_mvsjas		7.39 458	9.85 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	88.65 109	0.00 492	0.00 491	0.00 490	0.00 488

sosnet-low-res		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

sosnet		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

uncertanet		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

Regformer		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

n2								0.00 497

nn								0.00 497

ab-mvs-re		8.06 457	10.74 460	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	96.69 223	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

uanet		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

TestfortrainingZip							98.69 11

WAC-MVS						79.53 443								75.56 441

PC_three_1452									90.77 239	98.89 26	98.28 86	96.24 1	98.35 281	95.76 106	99.58 23	99.59 32

eth-test2					0.00 496

eth-test					0.00 496

OPU-MVS				98.55 4	98.82 61	96.86 3	98.25 40				98.26 87	96.04 2	99.24 149	95.36 120	99.59 19	99.56 40

test_0728_THIRD									94.78 61	98.73 30	98.87 31	95.87 4	99.84 26	97.45 46	99.72 2	99.77 3

GSMVS																98.45 186

test_part2					99.28 30	95.74 9				98.10 48

sam_mvs1												82.76 241				98.45 186

sam_mvs												81.94 262

test_post1							92.81 440				16.58 489	80.53 289	97.68 364	86.20 343

test_post											17.58 488	81.76 265	98.08 308

patchmatchnet-post											90.45 440	82.65 246	98.10 303

gm-plane-assit					93.22 418	78.89 451			84.82 404		93.52 393		98.64 251	87.72 310

test9_res														94.81 142	99.38 64	99.45 59

agg_prior2														93.94 169	99.38 64	99.50 52

test_prior4						93.66 62	96.42 278

test_prior2							96.35 288		92.80 155	96.03 126	97.59 162	92.01 50		95.01 128	99.38 64

旧先验2							95.94 319		81.66 437	97.34 70			98.82 209	92.26 202

新几何2							95.79 330

原ACMM2							95.67 336

testdata2													99.67 77	85.96 351

segment_acmp												92.89 33

testdata1							95.26 362		93.10 137

plane_prior7					96.21 270	89.98 213

plane_prior6					96.10 288	90.00 209						81.32 272

plane_prior4											96.64 226

plane_prior3						90.00 209			94.46 78	91.34 272

plane_prior2							97.74 113		94.85 53

plane_prior1					96.14 283

plane_prior						89.99 211	97.24 189		94.06 92						92.16 306

HQP5-MVS						89.33 247

HQP-NCC					95.86 296		96.65 259		93.55 109	90.14 296

ACMP_Plane					95.86 296		96.65 259		93.55 109	90.14 296

BP-MVS														92.13 210

HQP4-MVS										90.14 296			98.50 266			95.78 325

HQP2-MVS												80.95 277

NP-MVS					95.99 294	89.81 221					95.87 269

MDTV_nov1_ep13_2view						70.35 469	93.10 435		83.88 415	93.55 213		82.47 250		86.25 342		98.38 194

ACMMP++_ref															90.30 336

ACMMP++															91.02 325

Test By Simon												88.73 108

High-resolution multi-view benchmark