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 4	96.53 106	98.41 86	91.73 131	98.01 67	99.02 1	96.37 13	99.30 7	98.92 25	92.39 44	99.79 46	99.16 14	99.46 45	98.08 235

PGM-MVS		96.81 58	96.53 69	97.65 48	99.35 25	93.53 66	97.65 131	98.98 2	92.22 182	97.14 77	98.44 64	91.17 71	99.85 21	94.35 167	99.46 45	99.57 36

MVS_111021_HR		96.68 69	96.58 68	96.99 85	98.46 80	92.31 111	96.20 308	98.90 3	94.30 88	95.86 136	97.74 148	92.33 45	99.38 137	96.04 96	99.42 55	99.28 77

test_fmvsmconf_n		97.49 21	97.56 16	97.29 65	97.44 165	92.37 108	97.91 86	98.88 4	95.83 19	98.92 24	99.05 14	91.45 61	99.80 40	99.12 16	99.46 45	99.69 15

lecture		97.58 15	97.63 11	97.43 59	99.37 19	92.93 87	98.86 7	98.85 5	95.27 36	98.65 36	98.90 27	91.97 52	99.80 40	97.63 37	99.21 82	99.57 36

ACMMP		96.27 86	95.93 88	97.28 67	99.24 33	92.62 99	98.25 40	98.81 6	92.99 143	94.56 189	98.39 68	88.96 102	99.85 21	94.57 161	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	96.39 125	98.23 106	91.35 154	96.24 305	98.79 7	93.99 98	95.80 138	97.65 158	89.92 91	99.24 151	95.87 100	99.20 87	98.58 178

patch_mono-2		96.83 57	97.44 24	95.01 232	99.05 45	85.39 385	96.98 221	98.77 8	94.70 68	97.99 52	98.66 45	93.61 21	99.91 1	97.67 36	99.50 39	99.72 14

fmvsm_s_conf0.5_n		96.85 54	97.13 31	96.04 152	98.07 121	90.28 207	97.97 78	98.76 9	94.93 50	98.84 29	99.06 12	88.80 106	99.65 79	99.06 18	98.63 122	98.18 220

fmvsm_l_conf0.5_n		97.65 9	97.75 8	97.34 62	98.21 107	92.75 93	97.83 99	98.73 10	95.04 47	99.30 7	98.84 38	93.34 25	99.78 49	99.32 7	99.13 96	99.50 52

fmvsm_s_conf0.5_n_a		96.75 62	96.93 46	96.20 141	97.64 151	90.72 188	98.00 68	98.73 10	94.55 75	98.91 25	99.08 8	88.22 118	99.63 88	98.91 21	98.37 136	98.25 215

fmvsm_s_conf0.5_n_10		97.29 31	97.40 26	96.97 87	98.24 101	91.96 127	97.89 89	98.72 12	96.77 7	99.46 3	99.06 12	87.78 127	99.84 26	99.40 4	99.27 74	99.12 94

fmvsm_l_conf0.5_n_9		97.59 13	97.79 6	96.97 87	98.28 95	91.49 145	97.61 141	98.71 13	97.10 5	99.70 1	98.93 24	90.95 76	99.77 52	99.35 6	99.53 32	99.65 21

FC-MVSNet-test		93.94 189	93.57 181	95.04 230	95.48 323	91.45 150	98.12 56	98.71 13	93.37 125	90.23 304	96.70 229	87.66 129	97.85 358	91.49 232	90.39 344	95.83 333

UniMVSNet (Re)		93.31 216	92.55 229	95.61 194	95.39 329	93.34 72	97.39 176	98.71 13	93.14 138	90.10 313	94.83 332	87.71 128	98.03 331	91.67 230	83.99 420	95.46 352

MED-MVS test				98.00 25	99.56 1	94.50 36	98.69 11	98.70 16	93.45 122	98.73 31	98.53 53		99.86 10	97.40 49	99.58 23	99.65 21

MED-MVS		98.07 1	98.08 1	98.06 21	99.56 1	94.50 36	98.69 11	98.70 16	95.63 25	98.73 31	98.95 20	95.46 7	99.86 10	97.40 49	99.58 23	99.82 1

fmvsm_l_conf0.5_n_a		97.63 11	97.76 7	97.26 69	98.25 100	92.59 101	97.81 104	98.68 18	94.93 50	99.24 10	98.87 33	93.52 22	99.79 46	99.32 7	99.21 82	99.40 66

FIs		94.09 180	93.70 177	95.27 218	95.70 312	92.03 123	98.10 57	98.68 18	93.36 127	90.39 301	96.70 229	87.63 132	97.94 349	92.25 210	90.50 343	95.84 332

WR-MVS_H		92.00 273	91.35 270	93.95 306	95.09 356	89.47 245	98.04 64	98.68 18	91.46 214	88.34 366	94.68 339	85.86 172	97.56 390	85.77 370	84.24 418	94.82 405

fmvsm_s_conf0.5_n_4		96.75 62	97.07 34	95.79 178	97.76 142	89.57 238	97.66 130	98.66 21	95.36 32	99.03 16	98.90 27	88.39 114	99.73 61	99.17 13	98.66 120	98.08 235

VPA-MVSNet		93.24 218	92.48 234	95.51 204	95.70 312	92.39 107	97.86 92	98.66 21	92.30 179	92.09 261	95.37 307	80.49 299	98.40 281	93.95 173	85.86 391	95.75 341

fmvsm_l_conf0.5_n_3		97.64 10	97.60 13	97.79 35	98.14 114	93.94 57	97.93 84	98.65 23	96.70 8	99.38 5	99.07 11	89.92 91	99.81 35	99.16 14	99.43 52	99.61 30

fmvsm_s_conf0.5_n_3		97.15 36	97.36 28	96.52 108	97.98 126	91.19 162	97.84 96	98.65 23	97.08 6	99.25 9	99.10 6	87.88 125	99.79 46	99.32 7	99.18 89	98.59 177

fmvsm_s_conf0.5_n_8		97.32 28	97.48 23	96.85 89	98.28 95	91.07 170	97.76 109	98.62 25	97.53 2	99.20 12	99.12 5	88.24 117	99.81 35	99.41 3	99.17 90	99.67 16

fmvsm_s_conf0.5_n_2		96.62 70	96.82 55	96.02 155	97.98 126	90.43 198	97.50 156	98.59 26	96.59 10	99.31 6	99.08 8	84.47 209	99.75 58	99.37 5	98.45 132	97.88 248

UniMVSNet_NR-MVSNet		93.37 214	92.67 223	95.47 210	95.34 335	92.83 90	97.17 204	98.58 27	92.98 148	90.13 309	95.80 283	88.37 116	97.85 358	91.71 227	83.93 421	95.73 343

CSCG		96.05 90	95.91 89	96.46 118	99.24 33	90.47 195	98.30 33	98.57 28	89.01 311	93.97 209	97.57 170	92.62 40	99.76 54	94.66 155	99.27 74	99.15 88

fmvsm_s_conf0.5_n_9		97.33 27	97.57 15	96.62 102	98.43 83	90.32 206	97.80 105	98.53 29	97.24 4	99.62 2	99.14 2	88.65 109	99.80 40	99.54 1	99.15 93	99.74 10

fmvsm_s_conf0.5_n_6		97.08 39	97.17 30	96.81 90	97.28 170	91.73 131	97.75 111	98.50 30	94.86 54	99.22 11	98.78 42	89.75 94	99.76 54	99.10 17	99.29 72	98.94 125

MSLP-MVS++		96.94 48	97.06 35	96.59 103	98.72 64	91.86 129	97.67 127	98.49 31	94.66 71	97.24 73	98.41 67	92.31 47	98.94 196	96.61 71	99.46 45	98.96 118

HyFIR lowres test		93.66 201	92.92 211	95.87 167	98.24 101	89.88 224	94.58 395	98.49 31	85.06 411	93.78 213	95.78 287	82.86 246	98.67 251	91.77 225	95.71 242	99.07 103

CHOSEN 1792x2688		94.15 175	93.51 187	96.06 150	98.27 97	89.38 250	95.18 377	98.48 33	85.60 401	93.76 214	97.11 203	83.15 236	99.61 91	91.33 235	98.72 118	99.19 83

fmvsm_s_conf0.5_n_7		96.45 77	96.80 57	95.37 213	97.29 169	88.38 293	97.23 198	98.47 34	95.14 41	98.43 41	99.09 7	87.58 133	99.72 65	98.80 25	99.21 82	98.02 239

fmvsm_s_conf0.5_n_5		97.00 45	96.97 43	97.09 80	97.58 161	92.56 102	97.68 126	98.47 34	94.02 96	98.90 26	98.89 30	88.94 103	99.78 49	99.18 12	99.03 105	98.93 129

PHI-MVS		96.77 60	96.46 76	97.71 46	98.40 87	94.07 53	98.21 48	98.45 36	89.86 280	97.11 79	98.01 106	92.52 42	99.69 73	96.03 97	99.53 32	99.36 72

fmvsm_s_conf0.1_n		96.58 73	96.77 60	96.01 158	96.67 231	90.25 208	97.91 86	98.38 37	94.48 79	98.84 29	99.14 2	88.06 120	99.62 90	98.82 23	98.60 124	98.15 224

PVSNet_BlendedMVS		94.06 181	93.92 171	94.47 271	98.27 97	89.46 247	96.73 253	98.36 38	90.17 273	94.36 194	95.24 315	88.02 121	99.58 99	93.44 187	90.72 339	94.36 426

PVSNet_Blended		94.87 148	94.56 147	95.81 174	98.27 97	89.46 247	95.47 356	98.36 38	88.84 320	94.36 194	96.09 272	88.02 121	99.58 99	93.44 187	98.18 145	98.40 200

3Dnovator	91.36 5	95.19 129	94.44 156	97.44 58	96.56 247	93.36 71	98.65 16	98.36 38	94.12 92	89.25 343	98.06 99	82.20 263	99.77 52	93.41 189	99.32 70	99.18 85

TestfortrainingZip a		97.79 7	97.62 12	98.28 10	99.56 1	95.15 24	98.69 11	98.35 41	95.63 25	98.95 19	98.95 20	93.45 23	99.88 4	96.63 69	98.41 135	99.82 1

FOURS1					99.55 4	93.34 72	99.29 1	98.35 41	94.98 48	98.49 39

DPE-MVS		97.86 5	97.65 10	98.47 5	99.17 38	95.78 8	97.21 201	98.35 41	95.16 40	98.71 35	98.80 40	95.05 11	99.89 3	96.70 68	99.73 1	99.73 13
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 25	99.21 36	94.50 36	97.75 111	98.34 44	94.23 89	98.15 47	98.53 53	93.32 28	99.84 26	97.40 49	99.58 23	99.65 21

fmvsm_s_conf0.1_n_a		96.40 79	96.47 73	96.16 143	95.48 323	90.69 189	97.91 86	98.33 45	94.07 94	98.93 21	99.14 2	87.44 141	99.61 91	98.63 26	98.32 138	98.18 220

HFP-MVS		97.14 37	96.92 47	97.83 31	99.42 10	94.12 51	98.52 20	98.32 46	93.21 130	97.18 74	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 35	99.44 9	93.88 58	98.52 20	98.31 47	93.21 130	97.15 76	98.33 78	91.35 65	99.86 10	95.63 113	99.59 19	99.62 27

test_fmvsmvis_n_1920		96.70 65	96.84 51	96.31 130	96.62 233	91.73 131	97.98 72	98.30 48	96.19 14	96.10 126	98.95 20	89.42 95	99.76 54	98.90 22	99.08 100	97.43 275

APDe-MVS		97.82 6	97.73 9	98.08 20	99.15 39	94.82 30	98.81 8	98.30 48	94.76 66	98.30 43	98.90 27	93.77 19	99.68 75	97.93 28	99.69 3	99.75 8
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 52	98.99 18	98.92 25	95.08 9

MSP-MVS		97.59 13	97.54 17	97.73 43	99.40 14	93.77 62	98.53 19	98.29 50	95.55 29	98.56 38	97.81 139	93.90 17	99.65 79	96.62 70	99.21 82	99.77 4
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 2	97.99 2	98.28 10	98.67 67	95.39 12	99.29 1	98.28 52	94.78 63	98.93 21	98.87 33	96.04 2	99.86 10	97.45 45	99.58 23	99.59 32

test_0728_SECOND				98.51 4	99.45 6	95.93 6	98.21 48	98.28 52					99.86 10	97.52 41	99.67 6	99.75 8

CP-MVS		97.02 43	96.81 56	97.64 50	99.33 26	93.54 65	98.80 9	98.28 52	92.99 143	96.45 112	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 74	95.67 314	92.21 115	97.95 81	98.27 55	95.78 23	98.40 42	99.00 16	89.99 89	99.78 49	99.06 18	99.41 58	99.59 32

SED-MVS		98.05 3	97.99 2	98.24 12	99.42 10	95.30 18	98.25 40	98.27 55	95.13 42	99.19 13	98.89 30	95.54 5	99.85 21	97.52 41	99.66 10	99.56 40

test_241102_TWO								98.27 55	95.13 42	98.93 21	98.89 30	94.99 12	99.85 21	97.52 41	99.65 13	99.74 10

test_241102_ONE					99.42 10	95.30 18		98.27 55	95.09 45	99.19 13	98.81 39	95.54 5	99.65 79

SF-MVS		97.39 24	97.13 31	98.17 17	99.02 48	95.28 20	98.23 44	98.27 55	92.37 175	98.27 44	98.65 47	93.33 26	99.72 65	96.49 75	99.52 34	99.51 49

SteuartSystems-ACMMP		97.62 12	97.53 18	97.87 29	98.39 89	94.25 45	98.43 27	98.27 55	95.34 34	98.11 48	98.56 49	94.53 13	99.71 67	96.57 73	99.62 17	99.65 21
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 27	95.20 21		98.25 61	95.13 42	98.48 40	98.87 33	95.16 8

PVSNet_Blended_VisFu		95.27 119	94.91 127	96.38 126	98.20 108	90.86 180	97.27 192	98.25 61	90.21 272	94.18 202	97.27 192	87.48 140	99.73 61	93.53 184	97.77 161	98.55 181

region2R		97.07 41	96.84 51	97.77 39	99.46 5	93.79 60	98.52 20	98.24 63	93.19 133	97.14 77	98.34 75	91.59 60	99.87 8	95.46 120	99.59 19	99.64 25

PS-CasMVS		91.55 295	90.84 295	93.69 323	94.96 360	88.28 297	97.84 96	98.24 63	91.46 214	88.04 377	95.80 283	79.67 315	97.48 403	87.02 350	84.54 415	95.31 366

DU-MVS		92.90 236	92.04 245	95.49 207	94.95 361	92.83 90	97.16 205	98.24 63	93.02 142	90.13 309	95.71 290	83.47 227	97.85 358	91.71 227	83.93 421	95.78 337

9.14			96.75 61		98.93 56		97.73 116	98.23 66	91.28 224	97.88 56	98.44 64	93.00 30	99.65 79	95.76 106	99.47 44

reproduce_model		97.51 20	97.51 20	97.50 55	98.99 52	93.01 83	97.79 107	98.21 67	95.73 24	97.99 52	99.03 15	92.63 39	99.82 33	97.80 30	99.42 55	99.67 16

D2MVS		91.30 312	90.95 289	92.35 378	94.71 376	85.52 379	96.18 310	98.21 67	88.89 318	86.60 406	93.82 388	79.92 311	97.95 347	89.29 286	90.95 336	93.56 442

reproduce-ours		97.53 18	97.51 20	97.60 52	98.97 53	93.31 74	97.71 122	98.20 69	95.80 21	97.88 56	98.98 18	92.91 31	99.81 35	97.68 32	99.43 52	99.67 16

our_new_method		97.53 18	97.51 20	97.60 52	98.97 53	93.31 74	97.71 122	98.20 69	95.80 21	97.88 56	98.98 18	92.91 31	99.81 35	97.68 32	99.43 52	99.67 16

SDMVSNet		94.17 172	93.61 180	95.86 170	98.09 117	91.37 152	97.35 180	98.20 69	93.18 135	91.79 269	97.28 190	79.13 324	98.93 197	94.61 158	92.84 302	97.28 283

XVS		97.18 34	96.96 45	97.81 33	99.38 17	94.03 55	98.59 17	98.20 69	94.85 55	96.59 100	98.29 84	91.70 56	99.80 40	95.66 108	99.40 60	99.62 27

X-MVStestdata		91.71 282	89.67 351	97.81 33	99.38 17	94.03 55	98.59 17	98.20 69	94.85 55	96.59 100	32.69 539	91.70 56	99.80 40	95.66 108	99.40 60	99.62 27

ACMMP_NAP		97.20 33	96.86 49	98.23 13	99.09 40	95.16 23	97.60 142	98.19 74	92.82 158	97.93 55	98.74 44	91.60 59	99.86 10	96.26 80	99.52 34	99.67 16

CP-MVSNet		91.89 278	91.24 277	93.82 315	95.05 357	88.57 284	97.82 101	98.19 74	91.70 203	88.21 372	95.76 288	81.96 268	97.52 401	87.86 315	84.65 409	95.37 362

ZNCC-MVS		96.96 46	96.67 64	97.85 30	99.37 19	94.12 51	98.49 24	98.18 76	92.64 165	96.39 114	98.18 91	91.61 58	99.88 4	95.59 118	99.55 29	99.57 36

SMA-MVS		97.35 25	97.03 40	98.30 9	99.06 44	95.42 11	97.94 82	98.18 76	90.57 263	98.85 28	98.94 23	93.33 26	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		91.20 317	90.44 314	93.48 341	94.49 384	87.91 316	97.76 109	98.18 76	91.29 221	87.78 381	95.74 289	80.35 302	97.33 415	85.46 374	82.96 431	95.19 377

DELS-MVS		96.61 71	96.38 80	97.30 64	97.79 140	93.19 79	95.96 325	98.18 76	95.23 37	95.87 135	97.65 158	91.45 61	99.70 72	95.87 100	99.44 51	99.00 112
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		89.70 370	88.40 376	93.60 332	95.15 352	90.10 212	97.56 147	98.16 80	87.28 373	86.16 413	94.63 343	77.57 352	98.05 327	74.48 464	84.59 413	92.65 456

VNet		95.89 98	95.45 101	97.21 72	98.07 121	92.94 86	97.50 156	98.15 81	93.87 102	97.52 63	97.61 165	85.29 192	99.53 113	95.81 105	95.27 255	99.16 86

DeepPCF-MVS	93.97 1	96.61 71	97.09 33	95.15 223	98.09 117	86.63 351	96.00 323	98.15 81	95.43 30	97.95 54	98.56 49	93.40 24	99.36 138	96.77 63	99.48 43	99.45 59

SD-MVS		97.41 23	97.53 18	97.06 83	98.57 78	94.46 39	97.92 85	98.14 83	94.82 59	99.01 17	98.55 51	94.18 15	97.41 410	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 32	99.36 23	94.14 50	98.29 34	98.13 84	92.72 161	96.70 92	98.06 99	91.35 65	99.86 10	94.83 143	99.28 73	99.47 58

UA-Net		95.95 95	95.53 97	97.20 73	97.67 147	92.98 85	97.65 131	98.13 84	94.81 61	96.61 98	98.35 72	88.87 104	99.51 118	90.36 261	97.35 177	99.11 96

QAPM		93.45 212	92.27 239	96.98 86	96.77 224	92.62 99	98.39 29	98.12 86	84.50 419	88.27 370	97.77 144	82.39 260	99.81 35	85.40 375	98.81 113	98.51 186

Vis-MVSNet		95.23 124	94.81 133	96.51 112	97.18 175	91.58 142	98.26 39	98.12 86	94.38 86	94.90 177	98.15 94	82.28 261	98.92 199	91.45 234	98.58 126	99.01 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 239	91.68 260	96.40 123	95.34 335	92.73 95	98.27 37	98.12 86	84.86 414	85.78 422	97.75 145	78.89 334	99.74 59	87.50 338	98.65 121	96.73 302

TranMVSNet+NR-MVSNet		92.50 248	91.63 261	95.14 224	94.76 372	92.07 120	97.53 153	98.11 89	92.90 154	89.56 331	96.12 267	83.16 235	97.60 387	89.30 285	83.20 430	95.75 341

CPTT-MVS		95.57 109	95.19 114	96.70 93	99.27 31	91.48 147	98.33 31	98.11 89	87.79 357	95.17 166	98.03 103	87.09 149	99.61 91	93.51 185	99.42 55	99.02 106

APD-MVS		96.95 47	96.60 66	98.01 23	99.03 47	94.93 29	97.72 119	98.10 91	91.50 212	98.01 51	98.32 80	92.33 45	99.58 99	94.85 140	99.51 37	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 50	99.40 14	93.44 67	98.50 23	98.09 92	93.27 129	95.95 133	98.33 78	91.04 73	99.88 4	95.20 125	99.57 28	99.60 31

ZD-MVS					99.05 45	94.59 34		98.08 93	89.22 304	97.03 82	98.10 95	92.52 42	99.65 79	94.58 160	99.31 71

MTGPA								98.08 93

MTAPA		97.08 39	96.78 59	97.97 28	99.37 19	94.42 41	97.24 194	98.08 93	95.07 46	96.11 125	98.59 48	90.88 79	99.90 2	96.18 92	99.50 39	99.58 35

CNVR-MVS		97.68 8	97.44 24	98.37 7	98.90 59	95.86 7	97.27 192	98.08 93	95.81 20	97.87 59	98.31 81	94.26 14	99.68 75	97.02 57	99.49 42	99.57 36

DP-MVS Recon		95.68 103	95.12 118	97.37 61	99.19 37	94.19 47	97.03 212	98.08 93	88.35 338	95.09 168	97.65 158	89.97 90	99.48 125	92.08 219	98.59 125	98.44 197

SR-MVS		97.01 44	96.86 49	97.47 57	99.09 40	93.27 76	97.98 72	98.07 98	93.75 106	97.45 65	98.48 61	91.43 63	99.59 96	96.22 83	99.27 74	99.54 45

MCST-MVS		97.18 34	96.84 51	98.20 16	99.30 29	95.35 16	97.12 208	98.07 98	93.54 116	96.08 127	97.69 153	93.86 18	99.71 67	96.50 74	99.39 62	99.55 43

NR-MVSNet		92.34 257	91.27 276	95.53 199	94.95 361	93.05 82	97.39 176	98.07 98	92.65 163	84.46 434	95.71 290	85.00 199	97.77 369	89.71 273	83.52 427	95.78 337

MP-MVS-pluss		96.70 65	96.27 83	97.98 27	99.23 35	94.71 31	96.96 223	98.06 101	90.67 253	95.55 150	98.78 42	91.07 72	99.86 10	96.58 72	99.55 29	99.38 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 58	96.71 63	97.12 77	99.01 51	92.31 111	97.98 72	98.06 101	93.11 139	97.44 66	98.55 51	90.93 77	99.55 109	96.06 93	99.25 79	99.51 49

MP-MVS		96.77 60	96.45 77	97.72 44	99.39 16	93.80 59	98.41 28	98.06 101	93.37 125	95.54 152	98.34 75	90.59 83	99.88 4	94.83 143	99.54 31	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 71	99.32 27	92.74 94	98.74 10	98.06 101	90.57 263	96.77 89	98.35 72	90.21 86	99.53 113	94.80 147	99.63 16	99.38 70

HPM-MVS		96.69 67	96.45 77	97.40 60	99.36 23	93.11 81	98.87 6	98.06 101	91.17 232	96.40 113	97.99 109	90.99 74	99.58 99	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		94.51 163	93.80 173	96.64 95	97.07 182	91.97 125	96.32 297	98.06 101	88.94 316	94.50 191	96.78 224	84.60 206	99.27 148	91.90 220	96.02 231	98.68 171

DeepC-MVS	93.07 3	96.06 89	95.66 93	97.29 65	97.96 128	93.17 80	97.30 186	98.06 101	93.92 100	93.38 229	98.66 45	86.83 152	99.73 61	95.60 117	99.22 81	98.96 118
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 19	98.77 62	95.06 27	97.34 181	98.04 108	95.96 15	97.09 80	97.88 126	93.18 29	99.71 67	95.84 104	99.17 90	99.56 40

DeepC-MVS_fast	93.89 2	96.93 49	96.64 65	97.78 37	98.64 73	94.30 42	97.41 171	98.04 108	94.81 61	96.59 100	98.37 70	91.24 68	99.64 87	95.16 127	99.52 34	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 79	99.02 48	92.34 109	97.98 72	98.03 110	93.52 119	97.43 68	98.51 56	91.40 64	99.56 107	96.05 94	99.26 77	99.43 63

RE-MVS-def			96.72 62		99.02 48	92.34 109	97.98 72	98.03 110	93.52 119	97.43 68	98.51 56	90.71 81		96.05 94	99.26 77	99.43 63

RPMNet		88.98 376	87.05 390	94.77 251	94.45 386	87.19 334	90.23 479	98.03 110	77.87 478	92.40 247	87.55 480	80.17 306	99.51 118	68.84 486	93.95 288	97.60 268

save fliter					98.91 58	94.28 43	97.02 214	98.02 113	95.35 33

TEST9					98.70 65	94.19 47	96.41 283	98.02 113	88.17 342	96.03 128	97.56 172	92.74 36	99.59 96

train_agg		96.30 85	95.83 92	97.72 44	98.70 65	94.19 47	96.41 283	98.02 113	88.58 329	96.03 128	97.56 172	92.73 37	99.59 96	95.04 129	99.37 66	99.39 68

test_8					98.67 67	94.06 54	96.37 291	98.01 116	88.58 329	95.98 132	97.55 174	92.73 37	99.58 99

fmvsm_s_conf0.5_n_11		97.30 29	97.59 14	96.43 120	98.42 84	91.37 152	98.04 64	98.00 117	97.30 3	99.45 4	99.21 1	89.28 97	99.80 40	99.27 10	99.35 68	98.12 227

agg_prior					98.67 67	93.79 60		98.00 117		95.68 145			99.57 106

test_prior				97.23 70	98.67 67	92.99 84		98.00 117					99.41 133			99.29 75

WR-MVS		92.34 257	91.53 265	94.77 251	95.13 354	90.83 181	96.40 287	97.98 120	91.88 198	89.29 340	95.54 301	82.50 256	97.80 365	89.79 272	85.27 400	95.69 344

HPM-MVS++		97.34 26	96.97 43	98.47 5	99.08 42	96.16 5	97.55 152	97.97 121	95.59 27	96.61 98	97.89 121	92.57 41	99.84 26	95.95 99	99.51 37	99.40 66

CANet		96.39 80	96.02 87	97.50 55	97.62 154	93.38 69	97.02 214	97.96 122	95.42 31	94.86 178	97.81 139	87.38 143	99.82 33	96.88 60	99.20 87	99.29 75

114514_t		93.95 188	93.06 205	96.63 99	99.07 43	91.61 139	97.46 167	97.96 122	77.99 476	93.00 238	97.57 170	86.14 168	99.33 140	89.22 289	99.15 93	98.94 125

IU-MVS					99.42 10	95.39 12		97.94 124	90.40 270	98.94 20				97.41 48	99.66 10	99.74 10

MSC_two_6792asdad				98.86 1	98.67 67	96.94 1		97.93 125					99.86 10	97.68 32	99.67 6	99.77 4

No_MVS				98.86 1	98.67 67	96.94 1		97.93 125					99.86 10	97.68 32	99.67 6	99.77 4

fmvsm_s_conf0.1_n_2		96.33 84	96.44 79	96.00 159	97.30 168	90.37 204	97.53 153	97.92 127	96.52 11	99.14 15	99.08 8	83.21 233	99.74 59	99.22 11	98.06 150	97.88 248

Anonymous20231211		90.63 342	89.42 358	94.27 286	98.24 101	89.19 262	98.05 63	97.89 128	79.95 467	88.25 371	94.96 324	72.56 398	98.13 310	89.70 274	85.14 402	95.49 348

原ACMM1				96.38 126	98.59 75	91.09 169		97.89 128	87.41 369	95.22 165	97.68 154	90.25 85	99.54 111	87.95 314	99.12 98	98.49 189

CDPH-MVS		95.97 94	95.38 107	97.77 39	98.93 56	94.44 40	96.35 292	97.88 130	86.98 377	96.65 96	97.89 121	91.99 51	99.47 126	92.26 208	99.46 45	99.39 68

test11								97.88 130

EIA-MVS		95.53 111	95.47 100	95.71 189	97.06 185	89.63 234	97.82 101	97.87 132	93.57 112	93.92 211	95.04 321	90.61 82	98.95 194	94.62 157	98.68 119	98.54 182

CS-MVS		96.86 52	97.06 35	96.26 136	98.16 113	91.16 167	99.09 3	97.87 132	95.30 35	97.06 81	98.03 103	91.72 54	98.71 244	97.10 55	99.17 90	98.90 134

无先验							95.79 337	97.87 132	83.87 429				99.65 79	87.68 328		98.89 140

3Dnovator+	91.43 4	95.40 113	94.48 154	98.16 18	96.90 203	95.34 17	98.48 25	97.87 132	94.65 72	88.53 362	98.02 105	83.69 223	99.71 67	93.18 193	98.96 108	99.44 61

VPNet		92.23 265	91.31 273	94.99 234	95.56 319	90.96 173	97.22 200	97.86 136	92.96 149	90.96 292	96.62 241	75.06 373	98.20 303	91.90 220	83.65 426	95.80 335

TestfortrainingZip				98.34 8	98.54 79	96.25 4	98.69 11	97.85 137	94.15 91	98.17 46	97.94 113	94.00 16	99.63 88		97.45 173	99.15 88

test_vis1_n_1920		94.17 172	94.58 146	92.91 362	97.42 166	82.02 433	97.83 99	97.85 137	94.68 69	98.10 49	98.49 58	70.15 419	99.32 142	97.91 29	98.82 112	97.40 277

DVP-MVS		97.91 4	97.81 5	98.22 15	99.45 6	95.36 14	98.21 48	97.85 137	94.92 52	98.73 31	98.87 33	95.08 9	99.84 26	97.52 41	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 47	99.25 32	94.24 46	98.07 61	97.85 137	93.72 107	98.57 37	98.35 72	93.69 20	99.40 134	97.06 56	99.46 45	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	96.45 119	98.29 94	91.66 138	99.03 4	97.85 137	95.84 18	96.90 84	97.97 111	91.24 68	98.75 233	96.92 59	99.33 69	98.94 125

test_fmvsmconf0.01_n		96.15 88	95.85 91	97.03 84	92.66 440	91.83 130	97.97 78	97.84 142	95.57 28	97.53 62	99.00 16	84.20 216	99.76 54	98.82 23	99.08 100	99.48 56

GDP-MVS		95.62 106	95.13 116	97.09 80	96.79 217	93.26 77	97.89 89	97.83 143	93.58 111	96.80 86	97.82 137	83.06 240	99.16 163	94.40 164	97.95 156	98.87 144

BridgeMVS		96.84 56	96.89 48	96.68 94	97.63 153	92.22 114	98.17 54	97.82 144	94.44 81	98.23 45	97.36 185	90.97 75	99.22 153	97.74 31	99.66 10	98.61 175

AdaColmap		94.34 167	93.68 178	96.31 130	98.59 75	91.68 137	96.59 272	97.81 145	89.87 279	92.15 257	97.06 207	83.62 226	99.54 111	89.34 284	98.07 149	97.70 261

MVSMamba_PlusPlus		96.51 74	96.48 72	96.59 103	98.07 121	91.97 125	98.14 55	97.79 146	90.43 268	97.34 71	97.52 175	91.29 67	99.19 156	98.12 27	99.64 14	98.60 176

KinetiMVS		95.26 120	94.75 139	96.79 91	96.99 195	92.05 121	97.82 101	97.78 147	94.77 65	96.46 110	97.70 151	80.62 296	99.34 139	92.37 207	98.28 140	98.97 115

ETV-MVS		96.02 91	95.89 90	96.40 123	97.16 176	92.44 106	97.47 165	97.77 148	94.55 75	96.48 108	94.51 349	91.23 70	98.92 199	95.65 111	98.19 144	97.82 256

新几何1				97.32 63	98.60 74	93.59 64		97.75 149	81.58 458	95.75 140	97.85 131	90.04 88	99.67 77	86.50 356	99.13 96	98.69 170

旧先验1					98.38 90	93.38 69		97.75 149			98.09 97	92.30 48			99.01 106	99.16 86

EC-MVSNet		96.42 78	96.47 73	96.26 136	97.01 193	91.52 144	98.89 5	97.75 149	94.42 82	96.64 97	97.68 154	89.32 96	98.60 264	97.45 45	99.11 99	98.67 172

EI-MVSNet-Vis-set		96.51 74	96.47 73	96.63 99	98.24 101	91.20 161	96.89 231	97.73 152	94.74 67	96.49 107	98.49 58	90.88 79	99.58 99	96.44 76	98.32 138	99.13 91

PAPM_NR		95.01 138	94.59 145	96.26 136	98.89 60	90.68 190	97.24 194	97.73 152	91.80 199	92.93 243	96.62 241	89.13 100	99.14 168	89.21 290	97.78 160	98.97 115

Anonymous20240529		91.98 274	90.73 302	95.73 187	98.14 114	89.40 249	97.99 69	97.72 154	79.63 469	93.54 222	97.41 182	69.94 421	99.56 107	91.04 242	91.11 332	98.22 217

CHOSEN 280x420		93.12 224	92.72 222	94.34 279	96.71 230	87.27 330	90.29 478	97.72 154	86.61 385	91.34 281	95.29 309	84.29 215	98.41 280	93.25 191	98.94 109	97.35 280

EI-MVSNet-UG-set		96.34 83	96.30 82	96.47 116	98.20 108	90.93 177	96.86 234	97.72 154	94.67 70	96.16 124	98.46 62	90.43 84	99.58 99	96.23 82	97.96 155	98.90 134

LS3D		93.57 205	92.61 227	96.47 116	97.59 157	91.61 139	97.67 127	97.72 154	85.17 409	90.29 303	98.34 75	84.60 206	99.73 61	83.85 398	98.27 141	98.06 237

PAPR		94.18 171	93.42 194	96.48 115	97.64 151	91.42 151	95.55 351	97.71 158	88.99 313	92.34 253	95.82 282	89.19 98	99.11 171	86.14 362	97.38 175	98.90 134

UGNet		94.04 183	93.28 197	96.31 130	96.85 208	91.19 162	97.88 91	97.68 159	94.40 84	93.00 238	96.18 262	73.39 392	99.61 91	91.72 226	98.46 131	98.13 225
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				95.46 211	98.18 112	88.90 273		97.66 160	82.73 447	97.03 82	98.07 98	90.06 87	98.85 206	89.67 275	98.98 107	98.64 173

test12				97.65 48	98.46 80	94.26 44		97.66 160		95.52 153		90.89 78	99.46 127		99.25 79	99.22 82

DTE-MVSNet		90.56 343	89.75 349	93.01 358	93.95 399	87.25 331	97.64 135	97.65 162	90.74 248	87.12 394	95.68 293	79.97 310	97.00 428	83.33 399	81.66 437	94.78 412

TAPA-MVS	90.10 7	92.30 260	91.22 279	95.56 196	98.33 92	89.60 236	96.79 245	97.65 162	81.83 455	91.52 275	97.23 195	87.94 123	98.91 201	71.31 479	98.37 136	98.17 223
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 225	92.45 235	95.05 228	98.09 117	89.21 259	96.89 231	97.64 164	93.18 135	91.79 269	97.28 190	75.35 372	98.65 255	88.99 296	92.84 302	97.28 283

test_cas_vis1_n_1920		94.48 165	94.55 150	94.28 285	96.78 222	86.45 357	97.63 137	97.64 164	93.32 128	97.68 61	98.36 71	73.75 388	99.08 178	96.73 65	99.05 102	97.31 282

NormalMVS		96.36 82	96.11 86	97.12 77	99.37 19	92.90 88	97.99 69	97.63 166	95.92 16	96.57 103	97.93 114	85.34 190	99.50 121	94.99 132	99.21 82	98.97 115

Elysia		94.00 185	93.12 202	96.64 95	96.08 298	92.72 96	97.50 156	97.63 166	91.15 234	94.82 179	97.12 201	74.98 375	99.06 184	90.78 247	98.02 151	98.12 227

StellarMVS		94.00 185	93.12 202	96.64 95	96.08 298	92.72 96	97.50 156	97.63 166	91.15 234	94.82 179	97.12 201	74.98 375	99.06 184	90.78 247	98.02 151	98.12 227

cdsmvs_eth3d_5k		23.24 503	30.99 496	0.00 528	0.00 551	0.00 553	0.00 539	97.63 166	0.00 546	0.00 547	96.88 220	84.38 211	0.00 547	0.00 545	0.00 545	0.00 543

DPM-MVS		95.69 102	94.92 126	98.01 23	98.08 120	95.71 10	95.27 368	97.62 170	90.43 268	95.55 150	97.07 206	91.72 54	99.50 121	89.62 277	98.94 109	98.82 152

sasdasda		96.02 91	95.45 101	97.75 41	97.59 157	95.15 24	98.28 35	97.60 171	94.52 77	96.27 119	96.12 267	87.65 130	99.18 159	96.20 88	94.82 264	98.91 131

canonicalmvs		96.02 91	95.45 101	97.75 41	97.59 157	95.15 24	98.28 35	97.60 171	94.52 77	96.27 119	96.12 267	87.65 130	99.18 159	96.20 88	94.82 264	98.91 131

test222					98.24 101	92.21 115	95.33 363	97.60 171	79.22 471	95.25 162	97.84 133	88.80 106			99.15 93	98.72 167

cascas		91.20 317	90.08 331	94.58 264	94.97 359	89.16 263	93.65 438	97.59 174	79.90 468	89.40 335	92.92 417	75.36 371	98.36 288	92.14 213	94.75 267	96.23 314

E2		95.20 126	95.00 123	95.79 178	96.79 217	89.66 231	96.82 240	97.58 175	92.35 176	95.28 160	97.83 135	86.68 154	98.76 227	94.79 150	96.92 196	98.95 122

E3		95.20 126	95.00 123	95.79 178	96.77 224	89.66 231	96.82 240	97.58 175	92.35 176	95.28 160	97.83 135	86.69 153	98.76 227	94.79 150	96.92 196	98.95 122

h-mvs33		94.15 175	93.52 186	96.04 152	97.81 139	90.22 209	97.62 140	97.58 175	95.19 38	96.74 90	97.45 178	83.67 224	99.61 91	95.85 102	79.73 445	98.29 213

E5new		95.04 134	94.88 128	95.52 200	96.62 233	89.02 267	97.29 187	97.57 178	92.54 166	95.04 169	97.89 121	85.65 180	98.77 221	94.92 135	96.44 222	98.78 155

E6new		95.04 134	94.88 128	95.52 200	96.60 238	89.02 267	97.29 187	97.57 178	92.54 166	95.04 169	97.90 119	85.66 178	98.77 221	94.92 135	96.44 222	98.78 155

E6		95.04 134	94.88 128	95.52 200	96.60 238	89.02 267	97.29 187	97.57 178	92.54 166	95.04 169	97.90 119	85.66 178	98.77 221	94.92 135	96.44 222	98.78 155

E5		95.04 134	94.88 128	95.52 200	96.62 233	89.02 267	97.29 187	97.57 178	92.54 166	95.04 169	97.89 121	85.65 180	98.77 221	94.92 135	96.44 222	98.78 155

MGCFI-Net		95.94 96	95.40 105	97.56 54	97.59 157	94.62 33	98.21 48	97.57 178	94.41 83	96.17 123	96.16 265	87.54 135	99.17 161	96.19 90	94.73 269	98.91 131

MVSFormer		95.37 114	95.16 115	95.99 160	96.34 271	91.21 159	98.22 46	97.57 178	91.42 216	96.22 121	97.32 186	86.20 166	97.92 352	94.07 170	99.05 102	98.85 146

test_djsdf		93.07 227	92.76 217	94.00 300	93.49 418	88.70 278	98.22 46	97.57 178	91.42 216	90.08 315	95.55 300	82.85 247	97.92 352	94.07 170	91.58 323	95.40 359

OMC-MVS		95.09 131	94.70 140	96.25 139	98.46 80	91.28 155	96.43 279	97.57 178	92.04 194	94.77 184	97.96 112	87.01 150	99.09 176	91.31 236	96.77 202	98.36 204

E4		95.09 131	94.86 132	95.77 181	96.58 242	89.56 239	96.85 235	97.56 186	92.50 170	95.03 173	97.86 129	86.03 169	98.78 217	94.71 153	96.65 212	98.96 118

viewcassd2359sk11		95.26 120	95.09 120	95.80 175	96.95 199	89.72 230	96.80 244	97.56 186	92.21 184	95.37 158	97.80 141	87.17 148	98.77 221	94.82 145	97.10 190	98.90 134

PS-MVSNAJss		93.74 198	93.51 187	94.44 273	93.91 401	89.28 257	97.75 111	97.56 186	92.50 170	89.94 317	96.54 245	88.65 109	98.18 306	93.83 179	90.90 337	95.86 329

casdiffmvs_mvg		95.81 101	95.57 94	96.51 112	96.87 205	91.49 145	97.50 156	97.56 186	93.99 98	95.13 167	97.92 117	87.89 124	98.78 217	95.97 98	97.33 178	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
cashybrid2		95.67 104	95.55 95	96.03 154	96.95 199	90.12 211	97.72 119	97.55 190	94.10 93	95.23 163	98.18 91	87.32 144	98.80 215	95.40 121	97.52 167	99.19 83

E3new		95.28 118	95.11 119	95.80 175	97.03 190	89.76 228	96.78 249	97.54 191	92.06 193	95.40 156	97.75 145	87.49 139	98.76 227	94.85 140	97.10 190	98.88 142

jajsoiax		92.42 253	91.89 253	94.03 299	93.33 426	88.50 289	97.73 116	97.53 192	92.00 196	88.85 354	96.50 247	75.62 370	98.11 314	93.88 177	91.56 324	95.48 349

mvs_tets		92.31 259	91.76 256	93.94 308	93.41 423	88.29 296	97.63 137	97.53 192	92.04 194	88.76 357	96.45 249	74.62 380	98.09 319	93.91 175	91.48 325	95.45 354

dcpmvs_2		96.37 81	97.05 38	94.31 283	98.96 55	84.11 406	97.56 147	97.51 194	93.92 100	97.43 68	98.52 55	92.75 35	99.32 142	97.32 54	99.50 39	99.51 49

HQP_MVS		93.78 197	93.43 192	94.82 244	96.21 277	89.99 217	97.74 114	97.51 194	94.85 55	91.34 281	96.64 234	81.32 280	98.60 264	93.02 199	92.23 311	95.86 329

plane_prior5								97.51 194					98.60 264	93.02 199	92.23 311	95.86 329

hybridcas		95.46 112	95.29 110	95.96 162	96.83 211	90.08 213	97.63 137	97.49 197	93.76 105	94.79 182	98.04 101	86.87 151	98.72 242	94.71 153	97.53 166	99.08 100

viewmanbaseed2359cas		95.24 123	95.02 122	95.91 164	96.87 205	89.98 219	96.82 240	97.49 197	92.26 180	95.47 154	97.82 137	86.47 159	98.69 246	94.80 147	97.20 186	99.06 104

reproduce_monomvs		91.30 312	91.10 284	91.92 392	96.82 214	82.48 427	97.01 217	97.49 197	94.64 73	88.35 365	95.27 312	70.53 414	98.10 315	95.20 125	84.60 412	95.19 377

viewmacassd2359aftdt		95.07 133	94.80 134	95.87 167	96.53 252	89.84 225	96.90 230	97.48 200	92.44 172	95.36 159	97.89 121	85.23 193	98.68 248	94.40 164	97.00 194	99.09 98

PS-MVSNAJ		95.37 114	95.33 109	95.49 207	97.35 167	90.66 191	95.31 365	97.48 200	93.85 103	96.51 106	95.70 292	88.65 109	99.65 79	94.80 147	98.27 141	96.17 318

API-MVS		94.84 150	94.49 153	95.90 165	97.90 134	92.00 124	97.80 105	97.48 200	89.19 305	94.81 181	96.71 227	88.84 105	99.17 161	88.91 299	98.76 117	96.53 307

MG-MVS		95.61 107	95.38 107	96.31 130	98.42 84	90.53 193	96.04 319	97.48 200	93.47 121	95.67 146	98.10 95	89.17 99	99.25 150	91.27 237	98.77 116	99.13 91

MAR-MVS		94.22 170	93.46 189	96.51 112	98.00 125	92.19 118	97.67 127	97.47 204	88.13 346	93.00 238	95.84 280	84.86 204	99.51 118	87.99 313	98.17 146	97.83 255
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		92.98 231	92.53 231	94.32 281	96.12 293	89.20 260	95.28 366	97.47 204	92.66 162	89.90 318	95.62 296	80.58 297	98.40 281	92.73 204	92.40 309	95.38 361
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 310	90.22 327	94.68 256	94.86 368	87.86 317	97.23 198	97.46 206	87.99 347	89.90 318	96.92 218	66.35 449	98.23 300	90.30 262	90.99 335	97.96 242

nrg030		94.05 182	93.31 196	96.27 135	95.22 346	94.59 34	98.34 30	97.46 206	92.93 150	91.21 290	96.64 234	87.23 147	98.22 301	94.99 132	85.80 392	95.98 328

XVG-OURS		93.72 199	93.35 195	94.80 249	97.07 182	88.61 282	94.79 390	97.46 206	91.97 197	93.99 207	97.86 129	81.74 274	98.88 203	92.64 205	92.67 307	96.92 297

LPG-MVS_test		92.94 234	92.56 228	94.10 294	96.16 288	88.26 298	97.65 131	97.46 206	91.29 221	90.12 311	97.16 198	79.05 327	98.73 237	92.25 210	91.89 319	95.31 366

LGP-MVS_train				94.10 294	96.16 288	88.26 298		97.46 206	91.29 221	90.12 311	97.16 198	79.05 327	98.73 237	92.25 210	91.89 319	95.31 366

MVS		91.71 282	90.44 314	95.51 204	95.20 348	91.59 141	96.04 319	97.45 211	73.44 486	87.36 390	95.60 297	85.42 189	99.10 173	85.97 367	97.46 169	95.83 333

XVG-OURS-SEG-HR		93.86 194	93.55 182	94.81 246	97.06 185	88.53 288	95.28 366	97.45 211	91.68 204	94.08 206	97.68 154	82.41 259	98.90 202	93.84 178	92.47 308	96.98 292

baseline		95.58 108	95.42 104	96.08 147	96.78 222	90.41 199	97.16 205	97.45 211	93.69 110	95.65 147	97.85 131	87.29 145	98.68 248	95.66 108	97.25 184	99.13 91

ab-mvs		93.57 205	92.55 229	96.64 95	97.28 170	91.96 127	95.40 359	97.45 211	89.81 284	93.22 235	96.28 258	79.62 318	99.46 127	90.74 250	93.11 299	98.50 187

xiu_mvs_v2_base		95.32 117	95.29 110	95.40 212	97.22 172	90.50 194	95.44 358	97.44 215	93.70 109	96.46 110	96.18 262	88.59 113	99.53 113	94.79 150	97.81 159	96.17 318

1314		92.81 243	92.03 246	95.14 224	95.33 338	89.52 244	96.04 319	97.44 215	87.72 361	86.25 411	95.33 308	83.84 221	98.79 216	89.26 287	97.05 193	97.11 290

casdiffmvs		95.64 105	95.49 98	96.08 147	96.76 228	90.45 196	97.29 187	97.44 215	94.00 97	95.46 155	97.98 110	87.52 138	98.73 237	95.64 112	97.33 178	99.08 100
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		94.76 156	94.68 141	95.01 232	96.76 228	87.41 326	96.38 289	97.43 218	92.65 163	94.52 190	97.75 145	85.55 186	98.81 212	94.36 166	96.69 209	98.82 152

XXY-MVS		92.16 267	91.23 278	94.95 240	94.75 373	90.94 176	97.47 165	97.43 218	89.14 306	88.90 350	96.43 250	79.71 314	98.24 299	89.56 278	87.68 373	95.67 345

anonymousdsp		92.16 267	91.55 264	93.97 304	92.58 442	89.55 241	97.51 155	97.42 220	89.42 299	88.40 364	94.84 331	80.66 295	97.88 357	91.87 222	91.28 329	94.48 421

Effi-MVS+		94.93 143	94.45 155	96.36 128	96.61 236	91.47 148	96.41 283	97.41 221	91.02 240	94.50 191	95.92 276	87.53 136	98.78 217	93.89 176	96.81 201	98.84 150

RRT-MVS		94.51 163	94.35 159	94.98 236	96.40 265	86.55 354	97.56 147	97.41 221	93.19 133	94.93 176	97.04 208	79.12 325	99.30 146	96.19 90	97.32 180	99.09 98

casdiffseed414692147		94.55 161	94.02 167	96.15 144	96.61 236	90.79 183	97.42 169	97.39 223	92.18 189	93.95 210	97.64 161	84.37 212	98.66 254	90.68 252	95.91 235	99.00 112

HQP3-MVS								97.39 223							92.10 316

HQP-MVS		93.19 221	92.74 220	94.54 267	95.86 304	89.33 253	96.65 263	97.39 223	93.55 113	90.14 305	95.87 278	80.95 286	98.50 274	92.13 216	92.10 316	95.78 337

PLC	91.00 6	94.11 179	93.43 192	96.13 145	98.58 77	91.15 168	96.69 259	97.39 223	87.29 372	91.37 279	96.71 227	88.39 114	99.52 117	87.33 343	97.13 189	97.73 259
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
diffmvs_AUTHOR		95.33 116	95.27 112	95.50 206	96.37 269	89.08 265	96.08 316	97.38 227	93.09 141	96.53 105	97.74 148	86.45 160	98.68 248	96.32 78	97.48 168	98.75 163

v7n		90.76 335	89.86 342	93.45 343	93.54 415	87.60 324	97.70 125	97.37 228	88.85 319	87.65 383	94.08 379	81.08 285	98.10 315	84.68 384	83.79 425	94.66 418

UnsupCasMVSNet_eth		85.99 423	84.45 425	90.62 428	89.97 465	82.40 430	93.62 439	97.37 228	89.86 280	78.59 476	92.37 427	65.25 461	95.35 464	82.27 413	70.75 484	94.10 432

viewdifsd2359ckpt13		94.87 148	94.52 151	95.90 165	96.88 204	90.19 210	96.92 227	97.36 230	91.26 225	94.65 186	97.46 177	85.79 175	98.64 257	93.64 182	96.76 203	98.88 142

ACMM	89.79 8	92.96 232	92.50 233	94.35 277	96.30 273	88.71 277	97.58 143	97.36 230	91.40 218	90.53 298	96.65 233	79.77 313	98.75 233	91.24 238	91.64 321	95.59 347
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 138	94.76 136	95.75 184	96.58 242	91.71 134	96.25 302	97.35 232	92.99 143	96.70 92	96.63 238	82.67 251	99.44 130	96.22 83	97.46 169	96.11 324

xiu_mvs_v1_base		95.01 138	94.76 136	95.75 184	96.58 242	91.71 134	96.25 302	97.35 232	92.99 143	96.70 92	96.63 238	82.67 251	99.44 130	96.22 83	97.46 169	96.11 324

xiu_mvs_v1_base_debi		95.01 138	94.76 136	95.75 184	96.58 242	91.71 134	96.25 302	97.35 232	92.99 143	96.70 92	96.63 238	82.67 251	99.44 130	96.22 83	97.46 169	96.11 324

diffmvs		95.25 122	95.13 116	95.63 192	96.43 264	89.34 252	95.99 324	97.35 232	92.83 157	96.31 117	97.37 184	86.44 161	98.67 251	96.26 80	97.19 187	98.87 144
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		94.71 159	94.02 167	96.79 91	97.71 145	92.05 121	96.59 272	97.35 232	90.61 259	94.64 187	96.93 215	86.41 162	99.39 135	91.20 239	94.71 270	98.94 125

viewdifsd2359ckpt09		94.81 153	94.37 158	96.12 146	96.91 201	90.75 187	96.94 224	97.31 237	90.51 266	94.31 196	97.38 183	85.70 177	98.71 244	93.54 183	96.75 204	98.90 134

balanced_ft_v1		95.56 110	95.40 105	96.07 149	97.16 176	90.36 205	98.23 44	97.31 237	92.89 155	96.36 115	97.11 203	83.28 231	99.26 149	97.40 49	98.80 114	98.58 178

SSM_0407		94.54 162	94.12 166	95.80 175	96.79 217	90.38 201	96.79 245	97.29 239	91.24 226	93.68 215	97.60 166	85.03 197	98.67 251	92.14 213	96.51 215	98.35 206

SSM_0404		94.73 158	94.31 161	95.98 161	97.05 187	90.90 179	97.01 217	97.29 239	91.24 226	94.17 203	97.60 166	85.03 197	98.76 227	92.14 213	97.30 181	98.29 213

F-COLMAP		93.58 203	92.98 209	95.37 213	98.40 87	88.98 271	97.18 203	97.29 239	87.75 360	90.49 299	97.10 205	85.21 194	99.50 121	86.70 353	96.72 207	97.63 263

VortexMVS		92.88 238	92.64 224	93.58 334	96.58 242	87.53 325	96.93 226	97.28 242	92.78 160	89.75 323	94.99 322	82.73 250	97.76 370	94.60 159	88.16 368	95.46 352

hybridnocas07		94.93 143	94.78 135	95.37 213	96.27 274	88.62 281	96.10 314	97.26 243	92.35 176	95.58 149	97.48 176	85.60 185	98.65 255	95.47 119	96.90 198	98.85 146

XVG-ACMP-BASELINE		90.93 330	90.21 328	93.09 356	94.31 392	85.89 372	95.33 363	97.26 243	91.06 239	89.38 336	95.44 306	68.61 432	98.60 264	89.46 280	91.05 333	94.79 410

PCF-MVS	89.48 11	91.56 294	89.95 339	96.36 128	96.60 238	92.52 104	92.51 461	97.26 243	79.41 470	88.90 350	96.56 244	84.04 220	99.55 109	77.01 454	97.30 181	97.01 291
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
hybrid		94.76 156	94.60 144	95.27 218	96.24 276	88.36 294	96.05 318	97.25 246	91.40 218	95.40 156	97.59 168	85.48 188	98.63 259	95.23 124	96.71 208	98.83 151

ACMP	89.59 10	92.62 247	92.14 242	94.05 297	96.40 265	88.20 304	97.36 179	97.25 246	91.52 211	88.30 368	96.64 234	78.46 339	98.72 242	91.86 223	91.48 325	95.23 373
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 203	93.46 189	93.94 308	96.19 281	86.16 366	93.73 432	97.24 248	91.54 207	93.50 224	97.04 208	85.64 183	96.91 431	90.68 252	95.59 246	98.76 159

IMVS_0407		93.94 189	93.75 175	94.49 270	96.19 281	86.16 366	96.35 292	97.24 248	91.54 207	93.50 224	97.04 208	85.64 183	98.54 271	90.68 252	95.59 246	98.76 159

IMVS_0404		92.44 251	91.92 251	94.00 300	96.19 281	86.16 366	93.84 429	97.24 248	91.54 207	88.17 374	97.04 208	76.96 357	97.09 422	90.68 252	95.59 246	98.76 159

IMVS_0403		93.98 187	93.79 174	94.55 266	96.19 281	86.16 366	96.35 292	97.24 248	91.54 207	93.59 219	97.04 208	85.86 172	98.73 237	90.68 252	95.59 246	98.76 159

OPM-MVS		93.28 217	92.76 217	94.82 244	94.63 379	90.77 185	96.65 263	97.18 252	93.72 107	91.68 273	97.26 193	79.33 322	98.63 259	92.13 216	92.28 310	95.07 382
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 236	92.02 247	95.56 196	98.19 110	90.80 182	95.27 368	97.18 252	87.96 348	91.86 268	95.68 293	80.44 300	98.99 192	84.01 393	97.54 165	96.89 298

alignmvs		95.87 100	95.23 113	97.78 37	97.56 163	95.19 22	97.86 92	97.17 254	94.39 85	96.47 109	96.40 252	85.89 171	99.20 155	96.21 87	95.11 260	98.95 122

MVS_Test		94.89 146	94.62 143	95.68 190	96.83 211	89.55 241	96.70 257	97.17 254	91.17 232	95.60 148	96.11 271	87.87 126	98.76 227	93.01 201	97.17 188	98.72 167

Fast-Effi-MVS+		93.46 209	92.75 219	95.59 195	96.77 224	90.03 214	96.81 243	97.13 256	88.19 341	91.30 284	94.27 367	86.21 165	98.63 259	87.66 331	96.46 221	98.12 227

usedtu_dtu_shiyan1		91.65 286	90.67 306	94.60 258	93.65 412	90.95 174	94.86 387	97.12 257	89.69 288	89.21 344	93.62 398	81.17 283	97.67 377	87.54 335	89.14 355	95.17 379

FE-MVSNET3		91.65 286	90.67 306	94.60 258	93.65 412	90.95 174	94.86 387	97.12 257	89.69 288	89.21 344	93.62 398	81.17 283	97.67 377	87.54 335	89.14 355	95.17 379

EI-MVSNet		93.03 229	92.88 213	93.48 341	95.77 310	86.98 339	96.44 277	97.12 257	90.66 255	91.30 284	97.64 161	86.56 156	98.05 327	89.91 268	90.55 341	95.41 356

MVSTER		93.20 220	92.81 216	94.37 276	96.56 247	89.59 237	97.06 211	97.12 257	91.24 226	91.30 284	95.96 274	82.02 267	98.05 327	93.48 186	90.55 341	95.47 351

viewmambaseed2359dif		94.28 168	94.14 164	94.71 254	96.21 277	86.97 340	95.93 327	97.11 261	89.00 312	95.00 175	97.70 151	86.02 170	98.59 268	93.71 181	96.59 214	98.57 180

test_yl		94.78 154	94.23 162	96.43 120	97.74 143	91.22 157	96.85 235	97.10 262	91.23 229	95.71 142	96.93 215	84.30 213	99.31 144	93.10 194	95.12 258	98.75 163

DCV-MVSNet		94.78 154	94.23 162	96.43 120	97.74 143	91.22 157	96.85 235	97.10 262	91.23 229	95.71 142	96.93 215	84.30 213	99.31 144	93.10 194	95.12 258	98.75 163

LTVRE_ROB	88.41 13	90.99 326	89.92 341	94.19 288	96.18 285	89.55 241	96.31 298	97.09 264	87.88 351	85.67 423	95.91 277	78.79 335	98.57 269	81.50 417	89.98 346	94.44 424
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		93.46 209	93.23 199	94.17 289	96.12 293	85.42 381	96.43 279	97.08 265	92.91 151	94.21 199	98.00 107	80.82 292	98.74 235	94.41 163	89.05 357	98.34 210

test_fmvs1_n		92.73 245	92.88 213	92.29 382	96.08 298	81.05 441	97.98 72	97.08 265	90.72 250	96.79 88	98.18 91	63.07 466	98.45 278	97.62 39	98.42 134	97.36 278

v10		91.04 324	90.23 325	93.49 340	94.12 395	88.16 307	97.32 184	97.08 265	88.26 340	88.29 369	94.22 372	82.17 264	97.97 339	86.45 357	84.12 419	94.33 427

dtuplus		94.16 174	93.98 169	94.70 255	96.18 285	86.85 343	96.04 319	97.07 268	89.75 286	95.02 174	97.79 143	84.94 202	98.62 262	92.62 206	96.43 226	98.62 174

viewdifsd2359ckpt11		93.46 209	93.22 200	94.17 289	96.11 295	85.42 381	96.43 279	97.07 268	92.91 151	94.20 200	98.00 107	80.82 292	98.73 237	94.42 162	89.04 359	98.34 210

mamba_0408		93.70 200	92.99 206	95.83 172	96.79 217	90.38 201	88.69 488	97.07 268	90.96 242	93.68 215	97.31 188	84.97 200	98.76 227	90.95 243	96.51 215	98.35 206

SSM_04072		93.51 208	92.99 206	95.05 228	96.79 217	90.38 201	88.69 488	97.07 268	90.96 242	93.68 215	97.31 188	84.97 200	96.42 442	90.95 243	96.51 215	98.35 206

v144192		91.06 323	90.28 321	93.39 344	93.66 410	87.23 333	96.83 239	97.07 268	87.43 368	89.69 326	94.28 366	81.48 277	98.00 334	87.18 347	84.92 408	94.93 390

v1192		91.07 322	90.23 325	93.58 334	93.70 407	87.82 319	96.73 253	97.07 268	87.77 358	89.58 329	94.32 364	80.90 290	97.97 339	86.52 355	85.48 395	94.95 386

v8		91.29 314	90.53 313	93.57 336	94.15 394	88.12 308	97.34 181	97.06 274	88.99 313	88.32 367	94.26 369	83.08 238	98.01 333	87.62 333	83.92 423	94.57 420

mvs_anonymous		93.82 195	93.74 176	94.06 296	96.44 263	85.41 383	95.81 335	97.05 275	89.85 282	90.09 314	96.36 254	87.44 141	97.75 372	93.97 172	96.69 209	99.02 106

IterMVS-LS		92.29 261	91.94 250	93.34 346	96.25 275	86.97 340	96.57 275	97.05 275	90.67 253	89.50 334	94.80 334	86.59 155	97.64 382	89.91 268	86.11 390	95.40 359
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 333	90.03 336	93.29 348	93.55 414	86.96 342	96.74 252	97.04 277	87.36 370	89.52 333	94.34 361	80.23 305	97.97 339	86.27 358	85.21 401	94.94 388

CDS-MVSNet		94.14 178	93.54 183	95.93 163	96.18 285	91.46 149	96.33 296	97.04 277	88.97 315	93.56 220	96.51 246	87.55 134	97.89 356	89.80 271	95.95 233	98.44 197
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 369	89.26 362	91.19 417	95.16 349	80.29 452	94.53 397	97.03 279	91.79 200	88.86 353	94.10 376	69.94 421	97.82 362	85.29 376	86.66 386	95.45 354

v1144		91.37 307	90.60 309	93.68 326	93.89 402	88.23 300	96.84 238	97.03 279	88.37 337	89.69 326	94.39 356	82.04 266	97.98 336	87.80 318	85.37 397	94.84 399

v1240		90.70 339	89.85 343	93.23 350	93.51 417	86.80 344	96.61 269	97.02 281	87.16 375	89.58 329	94.31 365	79.55 319	97.98 336	85.52 373	85.44 396	94.90 393

EPP-MVSNet		95.22 125	95.04 121	95.76 182	97.49 164	89.56 239	98.67 15	97.00 282	90.69 251	94.24 198	97.62 164	89.79 93	98.81 212	93.39 190	96.49 219	98.92 130

V42		91.58 293	90.87 291	93.73 319	94.05 398	88.50 289	97.32 184	96.97 283	88.80 325	89.71 324	94.33 362	82.54 255	98.05 327	89.01 295	85.07 404	94.64 419

test_fmvs1		93.21 219	93.53 184	92.25 385	96.55 249	81.20 440	97.40 175	96.96 284	90.68 252	96.80 86	98.04 101	69.25 427	98.40 281	97.58 40	98.50 127	97.16 289

FMVSNet2		91.31 311	90.08 331	94.99 234	96.51 256	92.21 115	97.41 171	96.95 285	88.82 322	88.62 359	94.75 336	73.87 384	97.42 409	85.20 379	88.55 365	95.35 363

ACMH	87.59 16	90.53 344	89.42 358	93.87 313	96.21 277	87.92 314	97.24 194	96.94 286	88.45 335	83.91 445	96.27 259	71.92 401	98.62 262	84.43 387	89.43 352	95.05 384
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 308	90.27 322	94.59 260	96.51 256	91.18 164	97.50 156	96.93 287	88.82 322	89.35 337	94.51 349	73.87 384	97.29 417	86.12 363	88.82 360	95.31 366

test1		91.35 308	90.27 322	94.59 260	96.51 256	91.18 164	97.50 156	96.93 287	88.82 322	89.35 337	94.51 349	73.87 384	97.29 417	86.12 363	88.82 360	95.31 366

FMVSNet3		91.78 280	90.69 305	95.03 231	96.53 252	92.27 113	97.02 214	96.93 287	89.79 285	89.35 337	94.65 342	77.01 355	97.47 404	86.12 363	88.82 360	95.35 363

FMVSNet1		89.88 364	88.31 377	94.59 260	95.41 328	91.18 164	97.50 156	96.93 287	86.62 384	87.41 388	94.51 349	65.94 454	97.29 417	83.04 402	87.43 376	95.31 366

GeoE		93.89 192	93.28 197	95.72 188	96.96 198	89.75 229	98.24 43	96.92 291	89.47 296	92.12 259	97.21 196	84.42 210	98.39 286	87.71 323	96.50 218	99.01 109

SymmetryMVS		95.94 96	95.54 96	97.15 75	97.85 136	92.90 88	97.99 69	96.91 292	95.92 16	96.57 103	97.93 114	85.34 190	99.50 121	94.99 132	96.39 227	99.05 105

miper_enhance_ethall		91.54 297	91.01 287	93.15 354	95.35 334	87.07 338	93.97 421	96.90 293	86.79 381	89.17 346	93.43 410	86.55 157	97.64 382	89.97 267	86.93 381	94.74 415

eth_miper_zixun_eth		91.02 325	90.59 310	92.34 380	95.33 338	84.35 402	94.10 418	96.90 293	88.56 331	88.84 355	94.33 362	84.08 218	97.60 387	88.77 303	84.37 417	95.06 383

TAMVS		94.01 184	93.46 189	95.64 191	96.16 288	90.45 196	96.71 256	96.89 295	89.27 303	93.46 227	96.92 218	87.29 145	97.94 349	88.70 305	95.74 240	98.53 183

miper_ehance_all_eth		91.59 291	91.13 282	92.97 360	95.55 320	86.57 352	94.47 402	96.88 296	87.77 358	88.88 352	94.01 381	86.22 164	97.54 397	89.49 279	86.93 381	94.79 410

v2v482		91.59 291	90.85 294	93.80 316	93.87 403	88.17 306	96.94 224	96.88 296	89.54 293	89.53 332	94.90 328	81.70 275	98.02 332	89.25 288	85.04 406	95.20 374

CNLPA		94.28 168	93.53 184	96.52 108	98.38 90	92.55 103	96.59 272	96.88 296	90.13 276	91.91 265	97.24 194	85.21 194	99.09 176	87.64 332	97.83 158	97.92 245

PAPM		91.52 298	90.30 320	95.20 221	95.30 341	89.83 226	93.38 444	96.85 299	86.26 392	88.59 360	95.80 283	84.88 203	98.15 308	75.67 460	95.93 234	97.63 263

c3_l		91.38 305	90.89 290	92.88 364	95.58 318	86.30 360	94.68 392	96.84 300	88.17 342	88.83 356	94.23 370	85.65 180	97.47 404	89.36 283	84.63 410	94.89 394

pm-mvs1		90.72 338	89.65 353	93.96 305	94.29 393	89.63 234	97.79 107	96.82 301	89.07 308	86.12 416	95.48 305	78.61 337	97.78 367	86.97 351	81.67 436	94.46 422

test_vis1_n		92.37 256	92.26 240	92.72 370	94.75 373	82.64 423	98.02 66	96.80 302	91.18 231	97.77 60	97.93 114	58.02 477	98.29 296	97.63 37	98.21 143	97.23 286

CMPMVS	62.92 21	85.62 429	84.92 418	87.74 456	89.14 470	73.12 488	94.17 416	96.80 302	73.98 483	73.65 486	94.93 326	66.36 448	97.61 386	83.95 395	91.28 329	92.48 461
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 351	89.77 347	91.78 401	94.33 390	84.72 399	95.55 351	96.73 304	86.17 394	86.36 410	95.28 311	71.28 407	97.80 365	84.09 392	98.14 147	92.81 452

Effi-MVS+-dtu		93.08 226	93.21 201	92.68 373	96.02 301	83.25 416	97.14 207	96.72 305	93.85 103	91.20 291	93.44 407	83.08 238	98.30 295	91.69 229	95.73 241	96.50 309

TSAR-MVS + GP.		96.69 67	96.49 71	97.27 68	98.31 93	93.39 68	96.79 245	96.72 305	94.17 90	97.44 66	97.66 157	92.76 34	99.33 140	96.86 62	97.76 162	99.08 100

1112_ss		93.37 214	92.42 236	96.21 140	97.05 187	90.99 171	96.31 298	96.72 305	86.87 380	89.83 321	96.69 231	86.51 158	99.14 168	88.12 310	93.67 293	98.50 187

PVSNet	86.66 18	92.24 264	91.74 259	93.73 319	97.77 141	83.69 413	92.88 453	96.72 305	87.91 350	93.00 238	94.86 330	78.51 338	99.05 187	86.53 354	97.45 173	98.47 192

miper_lstm_enhance		90.50 347	90.06 335	91.83 397	95.33 338	83.74 410	93.86 427	96.70 309	87.56 366	87.79 380	93.81 389	83.45 229	96.92 430	87.39 341	84.62 411	94.82 405

v148		90.99 326	90.38 316	92.81 367	93.83 404	85.80 373	96.78 249	96.68 310	89.45 298	88.75 358	93.93 385	82.96 244	97.82 362	87.83 316	83.25 428	94.80 408

ACMH+	87.92 14	90.20 355	89.18 364	93.25 349	96.48 259	86.45 357	96.99 220	96.68 310	88.83 321	84.79 433	96.22 261	70.16 418	98.53 272	84.42 388	88.04 369	94.77 413

CANet_DTU		94.37 166	93.65 179	96.55 105	96.46 262	92.13 119	96.21 306	96.67 312	94.38 86	93.53 223	97.03 213	79.34 321	99.71 67	90.76 249	98.45 132	97.82 256

cl____		90.96 329	90.32 318	92.89 363	95.37 332	86.21 363	94.46 404	96.64 313	87.82 354	88.15 375	94.18 373	82.98 242	97.54 397	87.70 324	85.59 393	94.92 392

HY-MVS	89.66 9	93.87 193	92.95 210	96.63 99	97.10 181	92.49 105	95.64 348	96.64 313	89.05 310	93.00 238	95.79 286	85.77 176	99.45 129	89.16 293	94.35 272	97.96 242

Test_1112_low_res		92.84 241	91.84 254	95.85 171	97.04 189	89.97 221	95.53 353	96.64 313	85.38 404	89.65 328	95.18 316	85.86 172	99.10 173	87.70 324	93.58 298	98.49 189

DIV-MVS_self_test		90.97 328	90.33 317	92.88 364	95.36 333	86.19 365	94.46 404	96.63 316	87.82 354	88.18 373	94.23 370	82.99 241	97.53 399	87.72 321	85.57 394	94.93 390

Fast-Effi-MVS+-dtu		92.29 261	91.99 248	93.21 352	95.27 342	85.52 379	97.03 212	96.63 316	92.09 191	89.11 348	95.14 318	80.33 303	98.08 320	87.54 335	94.74 268	96.03 327

UnsupCasMVSNet_bld		82.13 447	79.46 452	90.14 434	88.00 485	82.47 428	90.89 476	96.62 318	78.94 472	75.61 481	84.40 494	56.63 480	96.31 444	77.30 451	66.77 493	91.63 472

cl22		91.21 316	90.56 312	93.14 355	96.09 297	86.80 344	94.41 406	96.58 319	87.80 356	88.58 361	93.99 383	80.85 291	97.62 385	89.87 270	86.93 381	94.99 385

jason		94.84 150	94.39 157	96.18 142	95.52 321	90.93 177	96.09 315	96.52 320	89.28 302	96.01 131	97.32 186	84.70 205	98.77 221	95.15 128	98.91 111	98.85 146
jason: jason.
tt0805		91.09 321	90.07 334	94.16 292	95.61 316	88.31 295	97.56 147	96.51 321	89.56 292	89.17 346	95.64 295	67.08 446	98.38 287	91.07 241	88.44 366	95.80 335

AUN-MVS		91.76 281	90.75 300	94.81 246	97.00 194	88.57 284	96.65 263	96.49 322	89.63 290	92.15 257	96.12 267	78.66 336	98.50 274	90.83 245	79.18 448	97.36 278

hse-mvs2		93.45 212	92.99 206	94.81 246	97.02 192	88.59 283	96.69 259	96.47 323	95.19 38	96.74 90	96.16 265	83.67 224	98.48 277	95.85 102	79.13 449	97.35 280

SD_0403		90.01 359	90.02 337	89.96 438	95.65 315	76.76 475	95.76 339	96.46 324	90.58 262	86.59 407	96.29 257	82.12 265	94.78 468	73.00 474	93.76 291	98.35 206

EG-PatchMatch MVS		87.02 405	85.44 407	91.76 403	92.67 439	85.00 393	96.08 316	96.45 325	83.41 439	79.52 470	93.49 404	57.10 479	97.72 374	79.34 442	90.87 338	92.56 458

KD-MVS_self_test		85.95 424	84.95 417	88.96 450	89.55 469	79.11 468	95.13 380	96.42 326	85.91 397	84.07 443	90.48 452	70.03 420	94.82 467	80.04 433	72.94 473	92.94 450

FE-MVSNET2		86.36 415	84.68 423	91.39 411	87.67 487	86.47 356	96.21 306	96.41 327	87.87 352	79.31 472	89.64 460	65.29 459	95.58 458	82.42 411	77.28 455	92.14 469

pmmvs6		87.81 391	86.19 399	92.69 372	91.32 455	86.30 360	97.34 181	96.41 327	80.59 466	84.05 444	94.37 358	67.37 441	97.67 377	84.75 383	79.51 447	94.09 434

PMMVS		92.86 239	92.34 237	94.42 275	94.92 364	86.73 347	94.53 397	96.38 329	84.78 416	94.27 197	95.12 320	83.13 237	98.40 281	91.47 233	96.49 219	98.12 227

RPSCF		90.75 336	90.86 292	90.42 431	96.84 209	76.29 478	95.61 349	96.34 330	83.89 427	91.38 278	97.87 127	76.45 361	98.78 217	87.16 348	92.23 311	96.20 316

BP-MVS1		95.89 98	95.49 98	97.08 82	96.67 231	93.20 78	98.08 59	96.32 331	94.56 74	96.32 116	97.84 133	84.07 219	99.15 165	96.75 64	98.78 115	98.90 134

MSDG		91.42 303	90.24 324	94.96 239	97.15 179	88.91 272	93.69 435	96.32 331	85.72 400	86.93 403	96.47 248	80.24 304	98.98 193	80.57 430	95.05 261	96.98 292

blended_shiyan6		87.55 395	85.52 406	93.64 329	88.78 475	88.50 289	95.23 371	96.30 333	82.80 445	86.09 417	87.70 478	73.69 390	97.56 390	87.70 324	71.36 480	94.86 395

blend_shiyan4		86.87 406	84.61 424	93.67 327	88.87 473	88.70 278	95.17 378	96.30 333	82.80 445	86.16 413	87.11 483	65.12 462	97.55 392	87.73 319	72.21 476	94.75 414

WBMVS		90.69 341	89.99 338	92.81 367	96.48 259	85.00 393	95.21 374	96.30 333	89.46 297	89.04 349	94.05 380	72.45 399	97.82 362	89.46 280	87.41 378	95.61 346

blended_shiyan8		87.58 394	85.55 405	93.66 328	88.76 477	88.54 286	95.21 374	96.29 336	82.81 444	86.25 411	87.73 477	73.70 389	97.58 389	87.81 317	71.42 479	94.85 398

OurMVSNet-221017-0		90.51 346	90.19 329	91.44 409	93.41 423	81.25 438	96.98 221	96.28 337	91.68 204	86.55 408	96.30 256	74.20 383	97.98 336	88.96 298	87.40 379	95.09 381

wanda-best-256-512		87.29 398	85.21 411	93.53 337	88.54 481	88.21 302	94.51 400	96.27 338	82.69 448	85.92 419	86.89 486	73.04 393	97.55 392	87.68 328	71.36 480	94.83 400

FE-blended-shiyan7		87.29 398	85.21 411	93.53 337	88.54 481	88.21 302	94.51 400	96.27 338	82.69 448	85.92 419	86.89 486	73.03 394	97.55 392	87.68 328	71.36 480	94.83 400

MVP-Stereo		90.74 337	90.08 331	92.71 371	93.19 428	88.20 304	95.86 331	96.27 338	86.07 395	84.86 432	94.76 335	77.84 350	97.75 372	83.88 397	98.01 153	92.17 468
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 142	94.56 147	96.29 134	96.34 271	91.21 159	95.83 333	96.27 338	88.93 317	96.22 121	96.88 220	86.20 166	98.85 206	95.27 123	99.05 102	98.82 152

BH-untuned		92.94 234	92.62 226	93.92 312	97.22 172	86.16 366	96.40 287	96.25 342	90.06 277	89.79 322	96.17 264	83.19 234	98.35 289	87.19 346	97.27 183	97.24 285

CL-MVSNet_self_test		86.31 417	85.15 414	89.80 440	88.83 474	81.74 436	93.93 424	96.22 343	86.67 383	85.03 430	90.80 450	78.09 346	94.50 469	74.92 463	71.86 477	93.15 448

IS-MVSNet		94.90 145	94.52 151	96.05 151	97.67 147	90.56 192	98.44 26	96.22 343	93.21 130	93.99 207	97.74 148	85.55 186	98.45 278	89.98 266	97.86 157	99.14 90

FA-MVS(test-final)		93.52 207	92.92 211	95.31 217	96.77 224	88.54 286	94.82 389	96.21 345	89.61 291	94.20 200	95.25 314	83.24 232	99.14 168	90.01 265	96.16 230	98.25 215

gbinet_0.2-2-1-0.02		87.30 397	85.16 413	93.69 323	88.70 480	88.81 275	95.14 379	96.20 346	83.03 442	86.14 415	87.06 484	71.26 408	97.40 411	87.46 339	71.49 478	94.86 395

GA-MVS		91.38 305	90.31 319	94.59 260	94.65 378	87.62 323	94.34 409	96.19 347	90.73 249	90.35 302	93.83 386	71.84 402	97.96 343	87.22 345	93.61 296	98.21 218

LuminaMVS		94.89 146	94.35 159	96.53 106	95.48 323	92.80 92	96.88 233	96.18 348	92.85 156	95.92 134	96.87 222	81.44 278	98.83 209	96.43 77	97.10 190	97.94 244

IterMVS-SCA-FT		90.31 349	89.81 345	91.82 398	95.52 321	84.20 405	94.30 412	96.15 349	90.61 259	87.39 389	94.27 367	75.80 367	96.44 441	87.34 342	86.88 385	94.82 405

IterMVS		90.15 357	89.67 351	91.61 405	95.48 323	83.72 411	94.33 410	96.12 350	89.99 278	87.31 392	94.15 375	75.78 369	96.27 445	86.97 351	86.89 384	94.83 400
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 244	91.51 268	96.52 108	98.77 62	90.99 171	97.38 178	96.08 351	82.38 451	89.29 340	97.87 127	83.77 222	99.69 73	81.37 423	96.69 209	98.89 140

pmmvs4		90.93 330	89.85 343	94.17 289	93.34 425	90.79 183	94.60 394	96.02 352	84.62 417	87.45 386	95.15 317	81.88 272	97.45 406	87.70 324	87.87 371	94.27 431

ppachtmachnet_test		88.35 386	87.29 385	91.53 406	92.45 445	83.57 414	93.75 431	95.97 353	84.28 420	85.32 428	94.18 373	79.00 333	96.93 429	75.71 459	84.99 407	94.10 432

Anonymous20240521		86.42 414	85.44 407	89.34 447	90.33 462	79.79 458	96.73 253	95.92 354	83.71 432	83.25 449	91.36 447	63.92 464	96.01 446	78.39 446	85.36 398	92.22 466

ITE_SJBPF				92.43 376	95.34 335	85.37 386		95.92 354	91.47 213	87.75 382	96.39 253	71.00 410	97.96 343	82.36 412	89.86 348	93.97 437

test_fmvs2		89.77 368	89.93 340	89.31 448	93.68 409	76.37 477	97.64 135	95.90 356	89.84 283	91.49 276	96.26 260	58.77 475	97.10 421	94.65 156	91.13 331	94.46 422

USDC		88.94 377	87.83 382	92.27 383	94.66 377	84.96 395	93.86 427	95.90 356	87.34 371	83.40 447	95.56 299	67.43 440	98.19 305	82.64 410	89.67 350	93.66 441

COLMAP_ROB	87.81 15	90.40 348	89.28 361	93.79 317	97.95 129	87.13 337	96.92 227	95.89 358	82.83 443	86.88 405	97.18 197	73.77 387	99.29 147	78.44 445	93.62 295	94.95 386
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 195	93.08 204	96.02 155	97.88 135	89.96 222	97.72 119	95.85 359	92.43 173	95.86 136	98.44 64	68.42 436	99.39 135	96.31 79	94.85 262	98.71 169

VDDNet		93.05 228	92.07 243	96.02 155	96.84 209	90.39 200	98.08 59	95.85 359	86.22 393	95.79 139	98.46 62	67.59 439	99.19 156	94.92 135	94.85 262	98.47 192

mvsmamba		94.57 160	94.14 164	95.87 167	97.03 190	89.93 223	97.84 96	95.85 359	91.34 220	94.79 182	96.80 223	80.67 294	98.81 212	94.85 140	98.12 148	98.85 146

Vis-MVSNet (Re-imp)		94.15 175	93.88 172	94.95 240	97.61 155	87.92 314	98.10 57	95.80 362	92.22 182	93.02 237	97.45 178	84.53 208	97.91 355	88.24 309	97.97 154	99.02 106

MM		97.29 31	96.98 42	98.23 13	98.01 124	95.03 28	98.07 61	95.76 363	97.78 1	97.52 63	98.80 40	88.09 119	99.86 10	99.44 2	99.37 66	99.80 3

KD-MVS_2432*1600		84.81 435	82.64 438	91.31 412	91.07 457	85.34 387	91.22 470	95.75 364	85.56 402	83.09 450	90.21 455	67.21 442	95.89 448	77.18 452	62.48 499	92.69 454

miper_refine_blended		84.81 435	82.64 438	91.31 412	91.07 457	85.34 387	91.22 470	95.75 364	85.56 402	83.09 450	90.21 455	67.21 442	95.89 448	77.18 452	62.48 499	92.69 454

FE-MVS		92.05 272	91.05 285	95.08 227	96.83 211	87.93 313	93.91 426	95.70 366	86.30 390	94.15 204	94.97 323	76.59 359	99.21 154	84.10 391	96.86 199	98.09 234

tpm cat1		88.36 385	87.21 388	91.81 399	95.13 354	80.55 447	92.58 460	95.70 366	74.97 482	87.45 386	91.96 439	78.01 349	98.17 307	80.39 432	88.74 363	96.72 303

our_test_3		88.78 381	87.98 381	91.20 416	92.45 445	82.53 425	93.61 440	95.69 368	85.77 399	84.88 431	93.71 391	79.99 309	96.78 437	79.47 439	86.24 387	94.28 430

BH-w/o		92.14 269	91.75 257	93.31 347	96.99 195	85.73 376	95.67 343	95.69 368	88.73 327	89.26 342	94.82 333	82.97 243	98.07 324	85.26 378	96.32 228	96.13 323

CR-MVSNet		90.82 334	89.77 347	93.95 306	94.45 386	87.19 334	90.23 479	95.68 370	86.89 379	92.40 247	92.36 430	80.91 288	97.05 424	81.09 427	93.95 288	97.60 268

Patchmtry		88.64 383	87.25 386	92.78 369	94.09 396	86.64 348	89.82 483	95.68 370	80.81 463	87.63 384	92.36 430	80.91 288	97.03 425	78.86 443	85.12 403	94.67 417

testing91		91.90 277	91.02 286	94.53 268	96.54 250	86.55 354	95.86 331	95.64 372	91.77 201	91.89 266	93.47 406	69.94 421	98.86 204	90.23 264	93.86 290	98.18 220

BH-RMVSNet		92.72 246	91.97 249	94.97 238	97.16 176	87.99 312	96.15 312	95.60 373	90.62 258	91.87 267	97.15 200	78.41 340	98.57 269	83.16 400	97.60 164	98.36 204

PVSNet_0	82.17 19	85.46 430	83.64 431	90.92 420	95.27 342	79.49 464	90.55 477	95.60 373	83.76 431	83.00 452	89.95 457	71.09 409	97.97 339	82.75 408	60.79 501	95.31 366

guyue		95.17 130	94.96 125	95.82 173	96.97 197	89.65 233	97.56 147	95.58 375	94.82 59	95.72 141	97.42 181	82.90 245	98.84 208	96.71 67	96.93 195	98.96 118

SCA		91.84 279	91.18 281	93.83 314	95.59 317	84.95 396	94.72 391	95.58 375	90.82 245	92.25 255	93.69 393	75.80 367	98.10 315	86.20 360	95.98 232	98.45 194

MonoMVSNet		91.92 275	91.77 255	92.37 377	92.94 433	83.11 419	97.09 210	95.55 377	92.91 151	90.85 294	94.55 346	81.27 282	96.52 440	93.01 201	87.76 372	97.47 274

dtuonly		90.88 332	91.13 282	90.13 435	92.98 432	75.01 481	92.74 457	95.54 378	87.69 362	91.37 279	96.61 243	79.65 317	98.15 308	87.44 340	96.21 229	97.23 286

usedtu_blend_shiyan5		87.06 404	84.84 419	93.69 323	88.54 481	88.70 278	95.83 333	95.54 378	78.74 473	85.92 419	86.89 486	73.03 394	97.55 392	87.73 319	71.36 480	94.83 400

AllTest		90.23 353	88.98 367	93.98 302	97.94 130	86.64 348	96.51 276	95.54 378	85.38 404	85.49 425	96.77 225	70.28 416	99.15 165	80.02 434	92.87 300	96.15 321

TestCases				93.98 302	97.94 130	86.64 348		95.54 378	85.38 404	85.49 425	96.77 225	70.28 416	99.15 165	80.02 434	92.87 300	96.15 321

mmtdpeth		89.70 370	88.96 368	91.90 394	95.84 309	84.42 401	97.46 167	95.53 382	90.27 271	94.46 193	90.50 451	69.74 425	98.95 194	97.39 53	69.48 487	92.34 462

tpmvs		89.83 367	89.15 365	91.89 395	94.92 364	80.30 451	93.11 449	95.46 383	86.28 391	88.08 376	92.65 420	80.44 300	98.52 273	81.47 419	89.92 347	96.84 299

pmmvs5		89.86 366	88.87 371	92.82 366	92.86 435	86.23 362	96.26 301	95.39 384	84.24 422	87.12 394	94.51 349	74.27 382	97.36 414	87.61 334	87.57 374	94.86 395

PatchmatchNet		91.91 276	91.35 270	93.59 333	95.38 330	84.11 406	93.15 448	95.39 384	89.54 293	92.10 260	93.68 395	82.82 248	98.13 310	84.81 382	95.32 254	98.52 184
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 302	91.32 272	91.79 400	95.15 352	79.20 467	93.42 443	95.37 386	88.55 332	93.49 226	93.67 396	82.49 257	98.27 298	90.41 259	89.34 353	97.90 246

Anonymous20231206		87.09 403	86.14 400	89.93 439	91.22 456	80.35 449	96.11 313	95.35 387	83.57 434	84.16 439	93.02 415	73.54 391	95.61 456	72.16 476	86.14 389	93.84 439

MIMVSNet1		84.93 433	83.05 435	90.56 429	89.56 468	84.84 398	95.40 359	95.35 387	83.91 426	80.38 466	92.21 435	57.23 478	93.34 484	70.69 482	82.75 434	93.50 443

TDRefinement		86.53 410	84.76 421	91.85 396	82.23 504	84.25 403	96.38 289	95.35 387	84.97 413	84.09 442	94.94 325	65.76 455	98.34 292	84.60 386	74.52 466	92.97 449

TR-MVS		91.48 301	90.59 310	94.16 292	96.40 265	87.33 327	95.67 343	95.34 390	87.68 363	91.46 277	95.52 302	76.77 358	98.35 289	82.85 405	93.61 296	96.79 301

EPNet_dtu		91.71 282	91.28 275	92.99 359	93.76 406	83.71 412	96.69 259	95.28 391	93.15 137	87.02 399	95.95 275	83.37 230	97.38 413	79.46 440	96.84 200	97.88 248
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 398	85.79 402	91.78 401	94.80 371	87.28 329	95.49 355	95.28 391	84.09 424	83.85 446	91.82 440	62.95 467	94.17 474	78.48 444	85.34 399	93.91 438

MDTV_nov1_ep13			90.76 298		95.22 346	80.33 450	93.03 451	95.28 391	88.14 345	92.84 244	93.83 386	81.34 279	98.08 320	82.86 403	94.34 273

LF4IMVS		87.94 389	87.25 386	89.98 437	92.38 448	80.05 457	94.38 407	95.25 394	87.59 365	84.34 436	94.74 337	64.31 463	97.66 381	84.83 381	87.45 375	92.23 465

TransMVSNet (Re)		88.94 377	87.56 383	93.08 357	94.35 389	88.45 292	97.73 116	95.23 395	87.47 367	84.26 438	95.29 309	79.86 312	97.33 415	79.44 441	74.44 468	93.45 445

test20.03		86.14 421	85.40 409	88.35 451	90.12 463	80.06 456	95.90 330	95.20 396	88.59 328	81.29 460	93.62 398	71.43 406	92.65 490	71.26 480	81.17 439	92.34 462

new-patchmatchnet		83.18 442	81.87 445	87.11 460	86.88 491	75.99 480	93.70 433	95.18 397	85.02 412	77.30 479	88.40 470	65.99 453	93.88 480	74.19 468	70.18 485	91.47 477

MDA-MVSNet_test_wron		85.87 427	84.23 428	90.80 426	92.38 448	82.57 424	93.17 446	95.15 398	82.15 452	67.65 493	92.33 433	78.20 342	95.51 461	77.33 449	79.74 444	94.31 429

YYNet1		85.87 427	84.23 428	90.78 427	92.38 448	82.46 429	93.17 446	95.14 399	82.12 453	67.69 491	92.36 430	78.16 345	95.50 462	77.31 450	79.73 445	94.39 425

Baseline_NR-MVSNet		91.20 317	90.62 308	92.95 361	93.83 404	88.03 310	97.01 217	95.12 400	88.42 336	89.70 325	95.13 319	83.47 227	97.44 407	89.66 276	83.24 429	93.37 446

thres200		92.23 265	91.39 269	94.75 253	97.61 155	89.03 266	96.60 271	95.09 401	92.08 192	93.28 232	94.00 382	78.39 341	99.04 190	81.26 426	94.18 279	96.19 317

ADS-MVSNet		89.89 363	88.68 373	93.53 337	95.86 304	84.89 397	90.93 474	95.07 402	83.23 440	91.28 287	91.81 441	79.01 331	97.85 358	79.52 437	91.39 327	97.84 253

pmmvs-eth3d		86.22 419	84.45 425	91.53 406	88.34 484	87.25 331	94.47 402	95.01 403	83.47 436	79.51 471	89.61 461	69.75 424	95.71 453	83.13 401	76.73 459	91.64 471

Anonymous202405211		92.07 271	90.83 296	95.76 182	98.19 110	88.75 276	97.58 143	95.00 404	86.00 396	93.64 218	97.45 178	66.24 451	99.53 113	90.68 252	92.71 305	99.01 109

MDA-MVSNet-bldmvs		85.00 432	82.95 437	91.17 418	93.13 430	83.33 415	94.56 396	95.00 404	84.57 418	65.13 497	92.65 420	70.45 415	95.85 450	73.57 471	77.49 454	94.33 427

ambc				86.56 464	83.60 499	70.00 492	85.69 500	94.97 406		80.60 465	88.45 469	37.42 498	96.84 434	82.69 409	75.44 464	92.86 451

testgi		87.97 388	87.21 388	90.24 433	92.86 435	80.76 442	96.67 262	94.97 406	91.74 202	85.52 424	95.83 281	62.66 470	94.47 471	76.25 456	88.36 367	95.48 349

myMVS_eth3d28		91.52 298	90.97 288	93.17 353	96.91 201	83.24 417	95.61 349	94.96 408	92.24 181	91.98 263	93.28 412	69.31 426	98.40 281	88.71 304	95.68 243	97.88 248

dp		88.90 379	88.26 379	90.81 424	94.58 382	76.62 476	92.85 454	94.93 409	85.12 410	90.07 316	93.07 414	75.81 366	98.12 313	80.53 431	87.42 377	97.71 260

test_fmvs3		83.21 441	83.02 436	83.78 468	86.77 492	68.34 495	96.76 251	94.91 410	86.49 386	84.14 441	89.48 462	36.04 499	91.73 492	91.86 223	80.77 441	91.26 479

test_0402		86.46 413	84.79 420	91.45 408	95.02 358	85.55 378	96.29 300	94.89 411	80.90 460	82.21 455	93.97 384	68.21 437	97.29 417	62.98 495	88.68 364	91.51 474

tfpn200view9		92.38 255	91.52 266	94.95 240	97.85 136	89.29 255	97.41 171	94.88 412	92.19 187	93.27 233	94.46 354	78.17 343	99.08 178	81.40 420	94.08 283	96.48 310

CVMVSNet		91.23 315	91.75 257	89.67 441	95.77 310	74.69 482	96.44 277	94.88 412	85.81 398	92.18 256	97.64 161	79.07 326	95.58 458	88.06 312	95.86 238	98.74 166

thres400		92.42 253	91.52 266	95.12 226	97.85 136	89.29 255	97.41 171	94.88 412	92.19 187	93.27 233	94.46 354	78.17 343	99.08 178	81.40 420	94.08 283	96.98 292

tt0320		85.39 431	83.12 434	92.19 387	93.44 422	85.79 374	96.19 309	94.87 415	71.19 490	82.92 453	91.76 443	58.43 476	96.81 435	81.03 428	78.26 453	93.98 436

EPNet		95.20 126	94.56 147	97.14 76	92.80 437	92.68 98	97.85 95	94.87 415	96.64 9	92.46 246	97.80 141	86.23 163	99.65 79	93.72 180	98.62 123	99.10 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 289	90.72 303	94.32 281	96.48 259	86.11 371	95.81 335	94.76 417	91.55 206	91.75 271	93.44 407	68.55 434	98.82 210	90.43 258	93.69 292	98.04 238

sc_t1		86.48 412	84.10 430	93.63 330	93.45 421	85.76 375	96.79 245	94.71 418	73.06 487	86.45 409	94.35 359	55.13 483	97.95 347	84.38 389	78.55 452	97.18 288

SixPastTwentyTwo		89.15 375	88.54 375	90.98 419	93.49 418	80.28 453	96.70 257	94.70 419	90.78 246	84.15 440	95.57 298	71.78 403	97.71 375	84.63 385	85.07 404	94.94 388

thres100view900		92.43 252	91.58 263	94.98 236	97.92 132	89.37 251	97.71 122	94.66 420	92.20 185	93.31 231	94.90 328	78.06 347	99.08 178	81.40 420	94.08 283	96.48 310

thres600view7		92.49 250	91.60 262	95.18 222	97.91 133	89.47 245	97.65 131	94.66 420	92.18 189	93.33 230	94.91 327	78.06 347	99.10 173	81.61 416	94.06 287	96.98 292

PatchT		88.87 380	87.42 384	93.22 351	94.08 397	85.10 391	89.51 484	94.64 422	81.92 454	92.36 250	88.15 473	80.05 308	97.01 427	72.43 475	93.65 294	97.54 271

baseline1		92.82 242	91.90 252	95.55 198	97.20 174	90.77 185	97.19 202	94.58 423	92.20 185	92.36 250	96.34 255	84.16 217	98.21 302	89.20 291	83.90 424	97.68 262

AstraMVS		94.82 152	94.64 142	95.34 216	96.36 270	88.09 309	97.58 143	94.56 424	94.98 48	95.70 144	97.92 117	81.93 271	98.93 197	96.87 61	95.88 236	98.99 114

UBG		91.55 295	90.76 298	93.94 308	96.52 255	85.06 392	95.22 372	94.54 425	90.47 267	91.98 263	92.71 419	72.02 400	98.74 235	88.10 311	95.26 256	98.01 240

Gipuma		67.86 469	65.41 470	75.18 486	92.66 440	73.45 486	66.50 518	94.52 426	53.33 509	57.80 506	66.07 513	30.81 501	89.20 496	48.15 508	78.88 451	62.90 517
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 285	90.75 300	94.47 271	96.53 252	86.56 353	95.76 339	94.51 427	91.10 238	91.24 289	93.59 401	68.59 433	98.86 204	91.10 240	94.29 275	98.00 241

dtuonlycased		85.91 425	85.69 403	86.60 463	92.42 447	76.96 474	93.66 437	94.49 428	86.68 382	80.87 461	92.00 436	71.52 404	93.23 487	79.58 436	79.97 443	89.60 486

CostFormer		91.18 320	90.70 304	92.62 374	94.84 369	81.76 435	94.09 419	94.43 429	84.15 423	92.72 245	93.77 390	79.43 320	98.20 303	90.70 251	92.18 314	97.90 246

tpm2		89.96 360	89.21 363	92.23 386	94.91 366	81.25 438	93.78 430	94.42 430	80.62 465	91.56 274	93.44 407	76.44 362	97.94 349	85.60 372	92.08 318	97.49 272

testing3-2		92.10 270	92.05 244	92.27 383	97.71 145	79.56 461	97.42 169	94.41 431	93.53 117	93.22 235	95.49 303	69.16 428	99.11 171	93.25 191	94.22 277	98.13 225

MGCNet		96.74 64	96.31 81	98.02 22	96.87 205	94.65 32	97.58 143	94.39 432	96.47 12	97.16 75	98.39 68	87.53 136	99.87 8	98.97 20	99.41 58	99.55 43

JIA-IIPM		88.26 387	87.04 391	91.91 393	93.52 416	81.42 437	89.38 485	94.38 433	80.84 462	90.93 293	80.74 502	79.22 323	97.92 352	82.76 407	91.62 322	96.38 313

dmvs_re		90.21 354	89.50 356	92.35 378	95.47 327	85.15 389	95.70 342	94.37 434	90.94 244	88.42 363	93.57 402	74.63 379	95.67 455	82.80 406	89.57 351	96.22 315

Patchmatch-test		89.42 373	87.99 380	93.70 322	95.27 342	85.11 390	88.98 486	94.37 434	81.11 459	87.10 397	93.69 393	82.28 261	97.50 402	74.37 466	94.76 266	98.48 191

LCM-MVSNet		72.55 457	69.39 462	82.03 472	70.81 524	65.42 502	90.12 481	94.36 436	55.02 506	65.88 495	81.72 499	24.16 509	89.96 493	74.32 467	68.10 491	90.71 482

ADS-MVSNet2		89.45 372	88.59 374	92.03 390	95.86 304	82.26 431	90.93 474	94.32 437	83.23 440	91.28 287	91.81 441	79.01 331	95.99 447	79.52 437	91.39 327	97.84 253

mvs5depth		86.53 410	85.08 415	90.87 421	88.74 478	82.52 426	91.91 465	94.23 438	86.35 389	87.11 396	93.70 392	66.52 447	97.76 370	81.37 423	75.80 461	92.31 464

EU-MVSNet		88.72 382	88.90 370	88.20 453	93.15 429	74.21 484	96.63 268	94.22 439	85.18 408	87.32 391	95.97 273	76.16 364	94.98 466	85.27 377	86.17 388	95.41 356

usedtu_dtu_shiyan2		80.00 450	76.91 456	89.27 449	82.13 505	79.69 460	95.45 357	94.20 440	72.95 488	75.80 480	87.75 476	44.44 494	94.30 473	70.64 483	68.81 490	93.84 439

tt0320-xc		84.83 434	82.33 442	92.31 381	93.66 410	86.20 364	96.17 311	94.06 441	71.26 489	82.04 457	92.22 434	55.07 484	96.72 438	81.49 418	75.04 465	94.02 435

MIMVSNet		88.50 384	86.76 394	93.72 321	94.84 369	87.77 320	91.39 468	94.05 442	86.41 388	87.99 378	92.59 423	63.27 465	95.82 452	77.44 448	92.84 302	97.57 270

OpenMVS_ROB	81.14 20	84.42 437	82.28 443	90.83 422	90.06 464	84.05 408	95.73 341	94.04 443	73.89 485	80.17 469	91.53 445	59.15 474	97.64 382	66.92 489	89.05 357	90.80 481

TinyColmap		86.82 408	85.35 410	91.21 414	94.91 366	82.99 421	93.94 423	94.02 444	83.58 433	81.56 459	94.68 339	62.34 471	98.13 310	75.78 458	87.35 380	92.52 460

ETVMVS		90.52 345	89.14 366	94.67 257	96.81 216	87.85 318	95.91 329	93.97 445	89.71 287	92.34 253	92.48 425	65.41 457	97.96 343	81.37 423	94.27 276	98.21 218

IB-MVS	87.33 17	89.91 361	88.28 378	94.79 250	95.26 345	87.70 321	95.12 381	93.95 446	89.35 301	87.03 398	92.49 424	70.74 413	99.19 156	89.18 292	81.37 438	97.49 272
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		87.13 402	87.02 392	87.47 457	95.16 349	73.21 487	95.00 383	93.93 447	88.55 332	86.96 400	91.99 437	75.90 365	94.00 477	61.59 497	94.11 280	95.20 374

myMVS_eth3d		87.18 401	86.38 397	89.58 442	95.16 349	79.53 462	95.00 383	93.93 447	88.55 332	86.96 400	91.99 437	56.23 481	94.00 477	75.47 462	94.11 280	95.20 374

testing222		90.31 349	88.96 368	94.35 277	96.54 250	87.29 328	95.50 354	93.84 449	90.97 241	91.75 271	92.96 416	62.18 472	98.00 334	82.86 403	94.08 283	97.76 258

test_f		80.57 449	79.62 451	83.41 470	83.38 501	67.80 497	93.57 441	93.72 450	80.80 464	77.91 478	87.63 479	33.40 500	92.08 491	87.14 349	79.04 450	90.34 483

LCM-MVSNet-Re		92.50 248	92.52 232	92.44 375	96.82 214	81.89 434	96.92 227	93.71 451	92.41 174	84.30 437	94.60 344	85.08 196	97.03 425	91.51 231	97.36 176	98.40 200

tpm		90.25 352	89.74 350	91.76 403	93.92 400	79.73 459	93.98 420	93.54 452	88.28 339	91.99 262	93.25 413	77.51 353	97.44 407	87.30 344	87.94 370	98.12 227

ET-MVSNet_ETH3D		91.49 300	90.11 330	95.63 192	96.40 265	91.57 143	95.34 362	93.48 453	90.60 261	75.58 482	95.49 303	80.08 307	96.79 436	94.25 168	89.76 349	98.52 184

LFMVS		93.60 202	92.63 225	96.52 108	98.13 116	91.27 156	97.94 82	93.39 454	90.57 263	96.29 118	98.31 81	69.00 429	99.16 163	94.18 169	95.87 237	99.12 94

MVStest1		82.38 446	80.04 450	89.37 445	87.63 488	82.83 422	95.03 382	93.37 455	73.90 484	73.50 487	94.35 359	62.89 468	93.25 486	73.80 469	65.92 495	92.04 470

FE-MVSNET		83.85 438	81.97 444	89.51 443	87.19 490	83.19 418	95.21 374	93.17 456	83.45 437	78.90 474	89.05 465	65.46 456	93.84 481	69.71 485	75.56 463	91.51 474

Patchmatch-RL test		87.38 396	86.24 398	90.81 424	88.74 478	78.40 471	88.12 495	93.17 456	87.11 376	82.17 456	89.29 463	81.95 269	95.60 457	88.64 306	77.02 456	98.41 199

ttmdpeth		85.91 425	84.76 421	89.36 446	89.14 470	80.25 454	95.66 346	93.16 458	83.77 430	83.39 448	95.26 313	66.24 451	95.26 465	80.65 429	75.57 462	92.57 457

test-LLR		91.42 303	91.19 280	92.12 388	94.59 380	80.66 444	94.29 413	92.98 459	91.11 236	90.76 296	92.37 427	79.02 329	98.07 324	88.81 301	96.74 205	97.63 263

test-mter		90.19 356	89.54 355	92.12 388	94.59 380	80.66 444	94.29 413	92.98 459	87.68 363	90.76 296	92.37 427	67.67 438	98.07 324	88.81 301	96.74 205	97.63 263

WB-MVSnew		89.88 364	89.56 354	90.82 423	94.57 383	83.06 420	95.65 347	92.85 461	87.86 353	90.83 295	94.10 376	79.66 316	96.88 432	76.34 455	94.19 278	92.54 459

testing3		87.67 392	86.88 393	90.05 436	96.14 291	80.71 443	97.10 209	92.85 461	90.15 275	87.54 385	94.55 346	55.70 482	94.10 475	73.77 470	94.10 282	95.35 363

test_method		66.11 471	64.89 471	69.79 492	72.62 522	35.23 529	65.19 519	92.83 463	20.35 525	65.20 496	88.08 474	43.14 496	82.70 507	73.12 473	63.46 497	91.45 478

test0.0.03 1		89.37 374	88.70 372	91.41 410	92.47 444	85.63 377	95.22 372	92.70 464	91.11 236	86.91 404	93.65 397	79.02 329	93.19 488	78.00 447	89.18 354	95.41 356

new_pmnet		82.89 444	81.12 449	88.18 454	89.63 467	80.18 455	91.77 466	92.57 465	76.79 480	75.56 483	88.23 472	61.22 473	94.48 470	71.43 478	82.92 432	89.87 484

mvsany_test1		93.93 191	93.98 169	93.78 318	94.94 363	86.80 344	94.62 393	92.55 466	88.77 326	96.85 85	98.49 58	88.98 101	98.08 320	95.03 130	95.62 245	96.46 312

0.4-1-1-0.2		86.27 418	83.62 432	94.20 287	90.38 461	87.69 322	91.04 473	92.52 467	83.43 438	85.22 429	81.49 500	65.31 458	98.29 296	88.90 300	74.30 469	96.64 305

0.3-1-1-0.015		86.11 422	83.37 433	94.34 279	90.58 460	88.02 311	91.64 467	92.45 468	83.56 435	84.46 434	81.84 498	62.73 469	98.31 293	88.98 297	74.09 470	96.70 304

thisisatest0515		92.29 261	91.30 274	95.25 220	96.60 238	88.90 273	94.36 408	92.32 469	87.92 349	93.43 228	94.57 345	77.28 354	99.00 191	89.42 282	95.86 238	97.86 252

0.4-1-1-0.1		86.83 407	84.27 427	94.50 269	91.39 454	88.23 300	92.62 459	92.27 470	84.04 425	86.01 418	83.30 495	65.29 459	98.31 293	89.08 294	74.45 467	96.96 296

thisisatest0530		93.03 229	92.21 241	95.49 207	97.07 182	89.11 264	97.49 164	92.19 471	90.16 274	94.09 205	96.41 251	76.43 363	99.05 187	90.38 260	95.68 243	98.31 212

tttt0517		92.96 232	92.33 238	94.87 243	97.11 180	87.16 336	97.97 78	92.09 472	90.63 257	93.88 212	97.01 214	76.50 360	99.06 184	90.29 263	95.45 252	98.38 202

K. test v3		87.64 393	86.75 395	90.32 432	93.02 431	79.48 465	96.61 269	92.08 473	90.66 255	80.25 468	94.09 378	67.21 442	96.65 439	85.96 368	80.83 440	94.83 400

TESTMET0.1,1		90.06 358	89.42 358	91.97 391	94.41 388	80.62 446	94.29 413	91.97 474	87.28 373	90.44 300	92.47 426	68.79 430	97.67 377	88.50 308	96.60 213	97.61 267

PM-MVS		83.48 440	81.86 446	88.31 452	87.83 486	77.59 473	93.43 442	91.75 475	86.91 378	80.63 464	89.91 458	44.42 495	95.84 451	85.17 380	76.73 459	91.50 476

baseline2		91.63 288	90.86 292	93.94 308	94.33 390	86.32 359	95.92 328	91.64 476	89.37 300	86.94 402	94.69 338	81.62 276	98.69 246	88.64 306	94.57 271	96.81 300

APD_test1		79.31 452	77.70 454	84.14 467	89.11 472	69.07 494	92.36 464	91.50 477	69.07 492	73.87 485	92.63 422	39.93 497	94.32 472	70.54 484	80.25 442	89.02 488

FPMVS		71.27 460	69.85 461	75.50 485	74.64 514	59.03 510	91.30 469	91.50 477	58.80 503	57.92 505	88.28 471	29.98 503	85.53 505	53.43 505	82.84 433	81.95 501

ArgMatch-SfM		83.09 443	81.67 447	87.34 459	91.48 453	76.29 478	92.76 456	91.31 479	84.26 421	81.99 458	93.35 411	45.52 493	92.98 489	81.83 415	72.49 475	92.76 453

door								91.13 480

door-mid								91.06 481

EGC-MVSNET		68.77 467	63.01 475	86.07 466	92.49 443	82.24 432	93.96 422	90.96 482	0.71 545	2.62 546	90.89 449	53.66 485	93.46 482	57.25 502	84.55 414	82.51 500

mvsany_test3		83.59 439	82.44 441	87.03 461	83.80 497	73.82 485	93.70 433	90.92 483	86.42 387	82.51 454	90.26 454	46.76 492	95.71 453	90.82 246	76.76 458	91.57 473

pmmvs3		79.97 451	77.50 455	87.39 458	82.80 503	79.38 466	92.70 458	90.75 484	70.69 491	78.66 475	87.47 481	51.34 488	93.40 483	73.39 472	69.65 486	89.38 487

UWE-MVS		89.91 361	89.48 357	91.21 414	95.88 303	78.23 472	94.91 386	90.26 485	89.11 307	92.35 252	94.52 348	68.76 431	97.96 343	83.95 395	95.59 246	97.42 276

DSMNet-mixed		86.34 416	86.12 401	87.00 462	89.88 466	70.43 490	94.93 385	90.08 486	77.97 477	85.42 427	92.78 418	74.44 381	93.96 479	74.43 465	95.14 257	96.62 306

MVS-HIRNet		82.47 445	81.21 448	86.26 465	95.38 330	69.21 493	88.96 487	89.49 487	66.28 495	80.79 463	74.08 508	68.48 435	97.39 412	71.93 477	95.47 251	92.18 467

WB-MVS		76.77 454	76.63 457	77.18 480	85.32 494	56.82 512	94.53 397	89.39 488	82.66 450	71.35 489	89.18 464	75.03 374	88.88 497	35.42 513	66.79 492	85.84 494

test1111		93.19 221	92.82 215	94.30 284	97.58 161	84.56 400	98.21 48	89.02 489	93.53 117	94.58 188	98.21 88	72.69 396	99.05 187	93.06 197	98.48 130	99.28 77

SSC-MVS		76.05 455	75.83 458	76.72 484	84.77 495	56.22 513	94.32 411	88.96 490	81.82 456	70.52 490	88.91 466	74.79 378	88.71 498	33.69 515	64.71 496	85.23 496

ECVR-MVS		93.19 221	92.73 221	94.57 265	97.66 149	85.41 383	98.21 48	88.23 491	93.43 123	94.70 185	98.21 88	72.57 397	99.07 182	93.05 198	98.49 128	99.25 80

EPMVS		90.70 339	89.81 345	93.37 345	94.73 375	84.21 404	93.67 436	88.02 492	89.50 295	92.38 249	93.49 404	77.82 351	97.78 367	86.03 366	92.68 306	98.11 233

ANet_high		63.94 473	59.58 476	77.02 481	61.24 530	66.06 499	85.66 501	87.93 493	78.53 475	42.94 513	71.04 510	25.42 507	80.71 511	52.60 506	30.83 522	84.28 498

PMMVS2		70.19 463	66.92 467	80.01 474	76.35 512	65.67 500	86.22 499	87.58 494	64.83 499	62.38 500	80.29 504	26.78 505	88.49 500	63.79 493	54.07 506	85.88 493

LoFTR		72.43 459	68.71 465	83.60 469	85.67 493	65.61 501	88.04 496	87.40 495	66.11 496	55.94 507	85.54 490	25.43 506	95.55 460	60.87 498	63.38 498	89.63 485

lessismore_v0				90.45 430	91.96 451	79.09 469		87.19 496		80.32 467	94.39 356	66.31 450	97.55 392	84.00 394	76.84 457	94.70 416

PMVS	53.92 22	58.58 476	55.40 479	68.12 494	51.00 543	48.64 518	78.86 506	87.10 497	46.77 511	35.84 520	74.28 507	8.76 530	86.34 503	42.07 510	73.91 471	69.38 509
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 409	86.41 396	88.02 455	92.87 434	74.60 483	95.38 361	86.70 498	88.17 342	87.28 393	94.67 341	70.83 412	93.30 485	67.45 487	94.31 274	96.17 318

test_vis1_rt		86.16 420	85.06 416	89.46 444	93.47 420	80.46 448	96.41 283	86.61 499	85.22 407	79.15 473	88.64 468	52.41 487	97.06 423	93.08 196	90.57 340	90.87 480

testf1		69.31 465	66.76 468	76.94 482	78.61 510	61.93 505	88.27 493	86.11 500	55.62 504	59.69 501	85.31 492	20.19 515	89.32 494	57.62 500	69.44 488	79.58 502

APD_test2		69.31 465	66.76 468	76.94 482	78.61 510	61.93 505	88.27 493	86.11 500	55.62 504	59.69 501	85.31 492	20.19 515	89.32 494	57.62 500	69.44 488	79.58 502

gg-mvs-nofinetune		87.82 390	85.61 404	94.44 273	94.46 385	89.27 258	91.21 472	84.61 502	80.88 461	89.89 320	74.98 506	71.50 405	97.53 399	85.75 371	97.21 185	96.51 308

MatchFormer		67.84 470	63.81 474	79.93 475	83.26 502	60.99 509	87.61 497	84.49 503	54.89 507	51.76 508	81.06 501	22.08 513	94.10 475	50.36 507	58.82 502	84.72 497

dmvs_testset		81.38 448	82.60 440	77.73 479	91.74 452	51.49 515	93.03 451	84.21 504	89.07 308	78.28 477	91.25 448	76.97 356	88.53 499	56.57 503	82.24 435	93.16 447

GG-mvs-BLEND				93.62 331	93.69 408	89.20 260	92.39 463	83.33 505		87.98 379	89.84 459	71.00 410	96.87 433	82.08 414	95.40 253	94.80 408

MTMP							97.86 92	82.03 506

DeepMVS_CX				74.68 487	90.84 459	64.34 504		81.61 507	65.34 497	67.47 494	88.01 475	48.60 491	80.13 512	62.33 496	73.68 472	79.58 502

DenseAffine		72.53 458	69.17 464	82.59 471	87.49 489	70.91 489	88.38 492	81.13 508	67.58 494	64.27 499	87.44 482	23.61 511	88.47 501	66.10 490	56.56 503	88.38 489

MASt3R-SfM		71.17 461	70.37 460	73.55 488	74.50 515	51.20 516	82.17 504	80.88 509	64.49 500	72.54 488	91.37 446	25.17 508	81.85 508	75.86 457	66.37 494	87.59 490

E-PMN		53.28 478	52.56 481	55.43 498	74.43 516	47.13 523	83.63 503	76.30 510	42.23 512	42.59 514	62.22 517	28.57 504	74.40 515	31.53 516	31.51 520	44.78 521

test2506		91.60 290	90.78 297	94.04 298	97.66 149	83.81 409	98.27 37	75.53 511	93.43 123	95.23 163	98.21 88	67.21 442	99.07 182	93.01 201	98.49 128	99.25 80

EMVS		52.08 480	51.31 483	54.39 500	72.62 522	45.39 525	83.84 502	75.51 512	41.13 513	40.77 516	59.65 519	30.08 502	73.60 516	28.31 518	29.90 525	44.18 522

ELoFTR		60.03 475	55.86 478	72.52 489	67.65 526	48.49 519	76.21 509	75.14 513	53.94 508	45.93 512	79.98 505	9.14 529	85.06 506	55.39 504	39.36 517	84.02 499

test_vis3_rt		72.73 456	70.55 459	79.27 476	80.02 509	68.13 496	93.92 425	74.30 514	76.90 479	58.99 504	73.58 509	20.29 514	95.37 463	84.16 390	72.80 474	74.31 505

RoMa-SfM		70.64 462	67.48 466	80.09 473	84.70 496	66.61 498	88.62 490	73.09 515	65.10 498	64.98 498	88.91 466	22.38 512	87.00 502	63.51 494	56.06 504	86.67 492

MVE	50.73 23	53.25 479	48.81 484	66.58 496	65.34 527	57.50 511	72.49 510	70.94 516	40.15 514	39.28 517	63.51 514	6.89 533	73.48 517	38.29 511	42.38 514	68.76 511
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DKM		67.96 468	64.19 473	79.27 476	83.41 500	64.35 503	86.88 498	68.11 517	63.15 501	59.36 503	86.08 489	16.45 522	86.15 504	64.54 492	49.73 508	87.32 491

tmp_tt		51.94 481	53.82 480	46.29 503	33.73 548	45.30 526	78.32 507	67.24 518	18.02 527	50.93 510	87.05 485	52.99 486	53.11 522	70.76 481	25.29 530	40.46 524

kuosan		65.27 472	64.66 472	67.11 495	83.80 497	61.32 508	88.53 491	60.77 519	68.22 493	67.67 492	80.52 503	49.12 490	70.76 518	29.67 517	53.64 507	69.26 510

dongtai		69.99 464	69.33 463	71.98 490	88.78 475	61.64 507	89.86 482	59.93 520	75.67 481	74.96 484	85.45 491	50.19 489	81.66 509	43.86 509	55.27 505	72.63 508

GLUNet-SfM		46.44 483	41.21 492	62.14 497	51.92 540	38.44 528	58.72 521	57.51 521	34.08 515	34.61 521	67.84 512	11.40 528	74.90 514	35.48 512	19.30 535	73.08 507

PDCNetPlus		61.05 474	58.26 477	69.44 493	75.52 513	55.68 514	81.49 505	51.76 522	62.45 502	51.54 509	82.02 497	23.69 510	78.90 513	65.91 491	29.91 524	73.74 506

PMatch-SfM		57.38 477	52.53 482	71.95 491	68.62 525	49.38 517	77.61 508	45.82 523	52.41 510	46.59 511	82.04 496	4.86 544	81.03 510	58.34 499	36.49 519	85.43 495

ALIKED-LG		47.63 482	45.22 485	54.88 499	81.48 506	48.47 520	71.83 511	45.44 524	32.66 516	37.07 518	63.26 516	19.21 517	63.71 519	15.49 527	40.53 515	52.46 518

N_pmnet		78.73 453	78.71 453	78.79 478	92.80 437	46.50 524	94.14 417	43.71 525	78.61 474	80.83 462	91.66 444	74.94 377	96.36 443	67.24 488	84.45 416	93.50 443

ALIKED-NN		46.19 484	43.87 486	53.16 502	80.39 508	47.77 521	69.82 517	43.65 526	27.89 517	36.60 519	63.35 515	17.30 519	61.29 521	15.84 526	39.98 516	50.41 520

ALIKED-MNN		45.42 485	42.62 488	53.80 501	80.52 507	47.58 522	70.83 514	43.05 527	27.21 518	34.32 522	61.10 518	14.85 525	62.94 520	14.90 528	36.82 518	50.89 519

SP-DiffGlue		43.94 486	43.32 487	45.79 506	47.79 545	33.03 530	63.37 520	42.65 528	25.71 519	41.26 515	69.27 511	18.83 518	38.88 529	34.96 514	46.05 509	65.47 516

SP-SuperGlue		43.33 488	42.50 489	45.81 505	73.95 519	31.24 533	71.34 512	41.17 529	23.96 520	33.42 523	56.47 521	16.72 521	39.64 527	21.11 522	44.32 511	66.57 513

SP-LightGlue		43.37 487	42.49 490	46.03 504	74.26 517	31.37 532	71.24 513	40.98 530	23.86 521	33.18 524	56.34 523	16.78 520	39.73 526	21.09 523	44.68 510	66.97 512

SP-MNN		42.11 490	40.98 493	45.49 507	72.87 520	30.19 537	70.72 515	39.96 531	20.98 523	30.21 527	55.72 525	15.26 524	40.07 525	19.70 525	43.42 513	66.21 514

XFeat-MNN		35.01 491	34.34 494	37.02 509	42.54 546	25.71 544	54.01 523	39.41 532	20.70 524	30.13 528	55.85 524	14.08 526	44.62 523	22.90 520	29.45 528	40.75 523

SP-NN		42.37 489	41.40 491	45.29 508	72.86 521	30.45 535	70.32 516	39.16 533	22.21 522	31.32 525	56.73 520	15.45 523	39.53 528	20.27 524	44.25 512	65.88 515

XFeat-NN		33.93 492	33.70 495	34.60 510	41.69 547	24.48 545	51.85 524	36.02 534	19.55 526	31.20 526	56.38 522	13.46 527	40.91 524	22.51 521	30.65 523	38.42 525

SIFT-NN		28.47 493	28.54 497	28.27 511	64.38 528	31.62 531	48.50 525	24.78 535	14.32 528	19.55 529	40.46 526	7.22 531	31.96 531	6.20 531	31.47 521	21.24 526

SIFT-MNN		27.50 494	27.40 498	27.80 512	61.71 529	30.57 534	46.59 526	24.66 536	14.04 529	17.35 530	39.90 527	6.52 534	31.80 532	6.13 532	29.65 526	21.04 527

SIFT-NN-NCMNet		27.16 495	27.05 499	27.51 513	59.97 532	30.42 536	46.49 527	24.52 537	13.94 531	17.23 531	39.47 528	6.39 535	31.40 533	5.94 533	29.49 527	20.72 529

SIFT-NN-UMatch		25.24 498	25.01 502	25.92 518	54.55 538	27.33 541	44.97 528	22.85 538	13.97 530	13.40 535	39.41 529	6.28 536	30.23 536	5.83 534	23.82 531	20.21 530

SIFT-NCM-Cal		25.87 496	25.57 500	26.75 514	60.60 531	29.37 538	44.96 529	22.64 539	13.57 534	11.67 538	37.90 533	5.81 539	31.26 534	5.32 539	27.70 529	19.63 532

SIFT-NN-CMatch		25.59 497	25.23 501	26.67 516	56.47 536	28.89 540	42.75 530	22.52 540	13.89 532	16.98 532	39.39 530	6.26 537	30.38 535	5.77 535	22.99 532	20.75 528

SIFT-ConvMatch		24.62 500	24.14 504	26.03 517	58.66 533	29.15 539	40.80 533	21.31 541	13.69 533	13.51 534	38.52 531	5.65 540	30.22 537	5.51 538	19.65 534	18.73 534

SIFT-NN-PointCN		23.81 502	23.84 505	23.73 521	52.41 539	22.80 547	42.30 532	20.98 542	13.02 538	15.14 533	37.74 535	6.20 538	28.40 540	5.52 537	21.24 533	19.98 531

SIFT-UMatch		24.03 501	23.67 506	25.10 519	57.10 535	26.49 543	42.43 531	20.05 543	13.49 535	12.40 537	38.51 532	5.45 542	30.07 538	5.56 536	18.08 536	18.74 533

SIFT-CM-Cal		23.18 504	22.70 507	24.60 520	57.42 534	26.79 542	37.63 535	18.36 544	13.35 536	12.57 536	37.37 536	5.54 541	28.79 539	5.17 541	16.92 539	18.23 535

SIFT-PointCN		20.70 506	20.89 509	20.14 523	51.62 542	18.11 548	37.52 536	17.71 545	12.03 540	10.05 542	33.23 538	4.33 546	25.40 543	4.55 543	16.94 538	16.90 537

SIFT-UM-Cal		22.52 505	22.27 508	23.27 522	56.41 537	23.87 546	39.94 534	16.81 546	13.33 537	10.54 539	37.90 533	5.16 543	28.36 541	5.23 540	15.12 540	17.57 536

SIFT-PCN-Cal		20.26 507	20.34 510	20.01 524	51.70 541	17.74 549	35.64 537	16.15 547	11.90 541	10.28 541	33.69 537	4.55 545	25.68 542	4.57 542	14.59 541	16.60 538

SIFT-NCMNet		17.70 508	17.74 511	17.60 525	49.47 544	16.50 550	30.22 538	10.39 548	11.77 542	8.79 543	29.74 540	3.61 548	22.42 544	3.97 544	11.69 542	13.89 539

wuyk23d		25.11 499	24.57 503	26.74 515	73.98 518	39.89 527	57.88 522	9.80 549	12.27 539	10.39 540	6.97 545	7.03 532	36.44 530	25.43 519	17.39 537	3.89 542

testmvs		13.36 509	16.33 512	4.48 527	5.04 549	2.26 552	93.18 445	3.28 550	2.70 543	8.24 544	21.66 541	2.29 549	2.19 545	7.58 529	2.96 543	9.00 541

test123		13.04 510	15.66 513	5.18 526	4.51 550	3.45 551	92.50 462	1.81 551	2.50 544	7.58 545	20.15 542	3.67 547	2.18 546	7.13 530	1.07 544	9.90 540

mmdepth		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

monomultidepth		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

test_blank		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uanet_test		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

DCPMVS		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

pcd_1.5k_mvsjas		7.39 512	9.85 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	88.65 109	0.00 547	0.00 545	0.00 545	0.00 543

sosnet-low-res		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

sosnet		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uncertanet		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

Regformer		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

n2								0.00 552

nn								0.00 552

ab-mvs-re		8.06 511	10.74 514	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	96.69 231	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uanet		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

WAC-MVS						79.53 462								75.56 461

PC_three_1452									90.77 247	98.89 27	98.28 86	96.24 1	98.35 289	95.76 106	99.58 23	99.59 32

eth-test2					0.00 551

eth-test					0.00 551

OPU-MVS				98.55 3	98.82 61	96.86 3	98.25 40				98.26 87	96.04 2	99.24 151	95.36 122	99.59 19	99.56 40

test_0728_THIRD									94.78 63	98.73 31	98.87 33	95.87 4	99.84 26	97.45 45	99.72 2	99.77 4

GSMVS																98.45 194

test_part2					99.28 30	95.74 9				98.10 49

sam_mvs1												82.76 249				98.45 194

sam_mvs												81.94 270

test_post1							92.81 455				16.58 544	80.53 298	97.68 376	86.20 360

test_post											17.58 543	81.76 273	98.08 320

patchmatchnet-post											90.45 453	82.65 254	98.10 315

gm-plane-assit					93.22 427	78.89 470			84.82 415		93.52 403		98.64 257	87.72 321

test9_res														94.81 146	99.38 63	99.45 59

agg_prior2														93.94 174	99.38 63	99.50 52

test_prior4						93.66 63	96.42 282

test_prior2							96.35 292		92.80 159	96.03 128	97.59 168	92.01 50		95.01 131	99.38 63

旧先验2							95.94 326		81.66 457	97.34 71			98.82 210	92.26 208

新几何2							95.79 337

原ACMM2							95.67 343

testdata2													99.67 77	85.96 368

segment_acmp												92.89 33

testdata1							95.26 370		93.10 140

plane_prior7					96.21 277	89.98 219

plane_prior6					96.10 296	90.00 215						81.32 280

plane_prior4											96.64 234

plane_prior3						90.00 215			94.46 80	91.34 281

plane_prior2							97.74 114		94.85 55

plane_prior1					96.14 291

plane_prior						89.99 217	97.24 194		94.06 95						92.16 315

HQP5-MVS						89.33 253

HQP-NCC					95.86 304		96.65 263		93.55 113	90.14 305

ACMP_Plane					95.86 304		96.65 263		93.55 113	90.14 305

BP-MVS														92.13 216

HQP4-MVS										90.14 305			98.50 274			95.78 337

HQP2-MVS												80.95 286

NP-MVS					95.99 302	89.81 227					95.87 278

MDTV_nov1_ep13_2view						70.35 491	93.10 450		83.88 428	93.55 221		82.47 258		86.25 359		98.38 202

ACMMP++_ref															90.30 345

ACMMP++															91.02 334

Test By Simon												88.73 108

High-resolution multi-view benchmark