High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_fmvsm_n_1920		97.55 16	97.89 3	96.53 105	98.41 85	91.73 130	98.01 66	99.02 1	96.37 13	99.30 7	98.92 23	92.39 44	99.79 46	99.16 14	99.46 46	98.08 226

PGM-MVS		96.81 58	96.53 69	97.65 47	99.35 25	93.53 65	97.65 129	98.98 2	92.22 175	97.14 76	98.44 64	91.17 71	99.85 21	94.35 161	99.46 46	99.57 36

MVS_111021_HR		96.68 69	96.58 68	96.99 84	98.46 79	92.31 110	96.20 303	98.90 3	94.30 86	95.86 134	97.74 142	92.33 45	99.38 136	96.04 96	99.42 56	99.28 77

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

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

ACMMP		96.27 86	95.93 89	97.28 66	99.24 33	92.62 98	98.25 40	98.81 6	92.99 140	94.56 180	98.39 68	88.96 102	99.85 21	94.57 155	97.63 163	99.36 72
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MVS_111021_LR		96.24 87	96.19 85	96.39 124	98.23 105	91.35 153	96.24 300	98.79 7	93.99 95	95.80 136	97.65 152	89.92 91	99.24 149	95.87 100	99.20 88	98.58 170

patch_mono-2		96.83 57	97.44 24	95.01 223	99.05 45	85.39 366	96.98 215	98.77 8	94.70 66	97.99 51	98.66 43	93.61 21	99.91 1	97.67 37	99.50 40	99.72 13

fmvsm_s_conf0.5_n		96.85 54	97.13 31	96.04 149	98.07 120	90.28 203	97.97 77	98.76 9	94.93 48	98.84 28	99.06 12	88.80 106	99.65 79	99.06 18	98.63 123	98.18 211

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

fmvsm_s_conf0.5_n_a		96.75 62	96.93 46	96.20 140	97.64 151	90.72 185	98.00 67	98.73 10	94.55 73	98.91 24	99.08 8	88.22 118	99.63 88	98.91 21	98.37 136	98.25 206

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

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

FC-MVSNet-test		93.94 181	93.57 173	95.04 221	95.48 314	91.45 149	98.12 55	98.71 13	93.37 122	90.23 294	96.70 220	87.66 129	97.85 345	91.49 225	90.39 334	95.83 320

UniMVSNet (Re)		93.31 208	92.55 221	95.61 189	95.39 320	93.34 71	97.39 172	98.71 13	93.14 135	90.10 303	94.83 322	87.71 128	98.03 318	91.67 223	83.99 409	95.46 339

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

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

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

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

FIs		94.09 172	93.70 169	95.27 210	95.70 303	92.03 122	98.10 56	98.68 19	93.36 124	90.39 291	96.70 220	87.63 132	97.94 336	92.25 203	90.50 333	95.84 319

WR-MVS_H		92.00 265	91.35 262	93.95 292	95.09 347	89.47 239	98.04 63	98.68 19	91.46 206	88.34 355	94.68 329	85.86 170	97.56 375	85.77 352	84.24 407	94.82 386

fmvsm_s_conf0.5_n_4		96.75 62	97.07 34	95.79 173	97.76 142	89.57 232	97.66 128	98.66 22	95.36 30	99.03 16	98.90 25	88.39 114	99.73 61	99.17 13	98.66 121	98.08 226

VPA-MVSNet		93.24 210	92.48 226	95.51 197	95.70 303	92.39 106	97.86 91	98.66 22	92.30 172	92.09 252	95.37 297	80.49 289	98.40 272	93.95 167	85.86 380	95.75 328

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

fmvsm_s_conf0.5_n_3		97.15 36	97.36 28	96.52 107	97.98 126	91.19 161	97.84 95	98.65 24	97.08 6	99.25 9	99.10 6	87.88 125	99.79 46	99.32 7	99.18 90	98.59 169

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

fmvsm_s_conf0.5_n_2		96.62 70	96.82 55	96.02 151	97.98 126	90.43 195	97.50 153	98.59 27	96.59 10	99.31 6	99.08 8	84.47 202	99.75 58	99.37 5	98.45 133	97.88 239

UniMVSNet_NR-MVSNet		93.37 206	92.67 215	95.47 203	95.34 326	92.83 89	97.17 198	98.58 28	92.98 145	90.13 299	95.80 273	88.37 116	97.85 345	91.71 220	83.93 410	95.73 330

CSCG		96.05 90	95.91 90	96.46 117	99.24 33	90.47 192	98.30 33	98.57 29	89.01 301	93.97 201	97.57 162	92.62 40	99.76 54	94.66 149	99.27 75	99.15 87

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

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

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

HyFIR lowres test		93.66 193	92.92 203	95.87 162	98.24 100	89.88 218	94.58 382	98.49 32	85.06 399	93.78 204	95.78 277	82.86 237	98.67 246	91.77 218	95.71 232	99.07 100

CHOSEN 1792x2688		94.15 167	93.51 179	96.06 147	98.27 96	89.38 244	95.18 366	98.48 34	85.60 389	93.76 205	97.11 195	83.15 227	99.61 90	91.33 228	98.72 119	99.19 83

fmvsm_s_conf0.5_n_7		96.45 77	96.80 57	95.37 206	97.29 169	88.38 281	97.23 192	98.47 35	95.14 39	98.43 41	99.09 7	87.58 133	99.72 65	98.80 25	99.21 83	98.02 230

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

PHI-MVS		96.77 60	96.46 76	97.71 45	98.40 86	94.07 52	98.21 47	98.45 37	89.86 272	97.11 78	98.01 104	92.52 42	99.69 73	96.03 97	99.53 33	99.36 72

fmvsm_s_conf0.1_n		96.58 73	96.77 60	96.01 154	96.67 228	90.25 204	97.91 85	98.38 38	94.48 77	98.84 28	99.14 2	88.06 120	99.62 89	98.82 23	98.60 125	98.15 215

PVSNet_BlendedMVS		94.06 173	93.92 163	94.47 259	98.27 96	89.46 241	96.73 248	98.36 39	90.17 264	94.36 186	95.24 305	88.02 121	99.58 98	93.44 181	90.72 329	94.36 407

PVSNet_Blended		94.87 142	94.56 141	95.81 169	98.27 96	89.46 241	95.47 348	98.36 39	88.84 310	94.36 186	96.09 262	88.02 121	99.58 98	93.44 181	98.18 145	98.40 191

3Dnovator	91.36 5	95.19 126	94.44 150	97.44 57	96.56 241	93.36 70	98.65 16	98.36 39	94.12 90	89.25 333	98.06 98	82.20 254	99.77 52	93.41 183	99.32 71	99.18 84

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

DPE-MVS		97.86 6	97.65 11	98.47 6	99.17 38	95.78 8	97.21 195	98.35 42	95.16 38	98.71 35	98.80 38	95.05 12	99.89 3	96.70 68	99.73 1	99.73 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ME-MVS		97.54 17	97.39 27	98.00 23	99.21 36	94.50 35	97.75 110	98.34 44	94.23 87	98.15 46	98.53 51	93.32 27	99.84 26	97.40 50	99.58 23	99.65 20

fmvsm_s_conf0.1_n_a		96.40 79	96.47 73	96.16 142	95.48 314	90.69 186	97.91 85	98.33 45	94.07 91	98.93 20	99.14 2	87.44 141	99.61 90	98.63 26	98.32 138	98.18 211

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

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

test_fmvsmvis_n_1920		96.70 65	96.84 51	96.31 129	96.62 230	91.73 130	97.98 71	98.30 48	96.19 14	96.10 124	98.95 20	89.42 95	99.76 54	98.90 22	99.08 102	97.43 266

APDe-MVS		97.82 7	97.73 9	98.08 19	99.15 39	94.82 29	98.81 8	98.30 48	94.76 64	98.30 43	98.90 25	93.77 19	99.68 75	97.93 29	99.69 3	99.75 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test0726					99.45 6	95.36 14	98.31 32	98.29 50	94.92 50	98.99 18	98.92 23	95.08 10

MSP-MVS		97.59 13	97.54 17	97.73 42	99.40 14	93.77 61	98.53 19	98.29 50	95.55 27	98.56 38	97.81 134	93.90 17	99.65 79	96.62 70	99.21 83	99.77 3
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DVP-MVS++		98.06 1	97.99 1	98.28 10	98.67 67	95.39 12	99.29 1	98.28 52	94.78 61	98.93 20	98.87 31	96.04 2	99.86 9	97.45 46	99.58 23	99.59 32

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

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

test_fmvsmconf0.1_n		97.09 38	97.06 35	97.19 73	95.67 305	92.21 114	97.95 80	98.27 55	95.78 23	98.40 42	99.00 16	89.99 89	99.78 49	99.06 18	99.41 59	99.59 32

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

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

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

SF-MVS		97.39 24	97.13 31	98.17 16	99.02 48	95.28 20	98.23 44	98.27 55	92.37 169	98.27 44	98.65 45	93.33 25	99.72 65	96.49 75	99.52 35	99.51 49

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

PVSNet_Blended_VisFu		95.27 116	94.91 125	96.38 125	98.20 107	90.86 178	97.27 186	98.25 61	90.21 263	94.18 194	97.27 184	87.48 140	99.73 61	93.53 178	97.77 161	98.55 172

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

PS-CasMVS		91.55 286	90.84 286	93.69 309	94.96 351	88.28 284	97.84 95	98.24 63	91.46 206	88.04 366	95.80 273	79.67 305	97.48 385	87.02 332	84.54 404	95.31 353

DU-MVS		92.90 228	92.04 237	95.49 200	94.95 352	92.83 89	97.16 199	98.24 63	93.02 139	90.13 299	95.71 280	83.47 219	97.85 345	91.71 220	83.93 410	95.78 324

9.14			96.75 61		98.93 56		97.73 115	98.23 66	91.28 215	97.88 55	98.44 64	93.00 29	99.65 79	95.76 106	99.47 45

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

D2MVS		91.30 303	90.95 280	92.35 359	94.71 367	85.52 360	96.18 305	98.21 67	88.89 308	86.60 395	93.82 378	79.92 301	97.95 334	89.29 278	90.95 326	93.56 422

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

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

SDMVSNet		94.17 165	93.61 172	95.86 165	98.09 116	91.37 151	97.35 176	98.20 69	93.18 132	91.79 260	97.28 182	79.13 313	98.93 196	94.61 152	92.84 292	97.28 274

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

X-MVStestdata		91.71 274	89.67 341	97.81 32	99.38 17	94.03 54	98.59 17	98.20 69	94.85 53	96.59 99	32.69 484	91.70 56	99.80 40	95.66 108	99.40 61	99.62 27

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

CP-MVSNet		91.89 270	91.24 269	93.82 301	95.05 348	88.57 274	97.82 100	98.19 74	91.70 195	88.21 361	95.76 278	81.96 259	97.52 383	87.86 304	84.65 398	95.37 349

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

SMA-MVS		97.35 25	97.03 40	98.30 9	99.06 44	95.42 11	97.94 81	98.18 76	90.57 254	98.85 27	98.94 21	93.33 25	99.83 31	96.72 66	99.68 4	99.63 26
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
PEN-MVS		91.20 308	90.44 304	93.48 322	94.49 375	87.91 299	97.76 108	98.18 76	91.29 212	87.78 370	95.74 279	80.35 292	97.33 396	85.46 356	82.96 420	95.19 364

DELS-MVS		96.61 71	96.38 80	97.30 63	97.79 140	93.19 78	95.96 317	98.18 76	95.23 35	95.87 133	97.65 152	91.45 61	99.70 72	95.87 100	99.44 52	99.00 109
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
tfpnnormal		89.70 360	88.40 366	93.60 315	95.15 343	90.10 207	97.56 144	98.16 80	87.28 362	86.16 401	94.63 333	77.57 341	98.05 314	74.48 443	84.59 402	92.65 435

VNet		95.89 98	95.45 101	97.21 71	98.07 120	92.94 85	97.50 153	98.15 81	93.87 99	97.52 62	97.61 158	85.29 186	99.53 112	95.81 105	95.27 245	99.16 85

DeepPCF-MVS	93.97 1	96.61 71	97.09 33	95.15 214	98.09 116	86.63 332	96.00 315	98.15 81	95.43 28	97.95 53	98.56 47	93.40 23	99.36 137	96.77 63	99.48 44	99.45 59

SD-MVS		97.41 23	97.53 18	97.06 82	98.57 78	94.46 38	97.92 84	98.14 83	94.82 57	99.01 17	98.55 49	94.18 16	97.41 392	96.94 58	99.64 14	99.32 74
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
GST-MVS		96.85 54	96.52 70	97.82 31	99.36 23	94.14 49	98.29 34	98.13 84	92.72 157	96.70 91	98.06 98	91.35 65	99.86 9	94.83 138	99.28 74	99.47 58

UA-Net		95.95 95	95.53 97	97.20 72	97.67 147	92.98 84	97.65 129	98.13 84	94.81 59	96.61 97	98.35 72	88.87 104	99.51 117	90.36 253	97.35 174	99.11 94

QAPM		93.45 204	92.27 231	96.98 85	96.77 221	92.62 98	98.39 29	98.12 86	84.50 407	88.27 359	97.77 138	82.39 251	99.81 35	85.40 357	98.81 115	98.51 177

Vis-MVSNet		95.23 121	94.81 129	96.51 111	97.18 175	91.58 141	98.26 39	98.12 86	94.38 84	94.90 169	98.15 93	82.28 252	98.92 198	91.45 227	98.58 127	99.01 106
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 231	91.68 252	96.40 122	95.34 326	92.73 94	98.27 37	98.12 86	84.86 402	85.78 405	97.75 139	78.89 323	99.74 59	87.50 322	98.65 122	96.73 291

TranMVSNet+NR-MVSNet		92.50 240	91.63 253	95.14 215	94.76 363	92.07 119	97.53 150	98.11 89	92.90 151	89.56 321	96.12 257	83.16 226	97.60 373	89.30 277	83.20 419	95.75 328

CPTT-MVS		95.57 108	95.19 112	96.70 92	99.27 31	91.48 146	98.33 31	98.11 89	87.79 347	95.17 161	98.03 101	87.09 148	99.61 90	93.51 179	99.42 56	99.02 103

APD-MVS		96.95 47	96.60 66	98.01 21	99.03 47	94.93 28	97.72 118	98.10 91	91.50 204	98.01 50	98.32 80	92.33 45	99.58 98	94.85 135	99.51 38	99.53 48
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 52	96.60 66	97.64 49	99.40 14	93.44 66	98.50 23	98.09 92	93.27 126	95.95 131	98.33 78	91.04 73	99.88 4	95.20 122	99.57 29	99.60 31

ZD-MVS					99.05 45	94.59 33		98.08 93	89.22 294	97.03 81	98.10 94	92.52 42	99.65 79	94.58 154	99.31 72

MTGPA								98.08 93

MTAPA		97.08 39	96.78 59	97.97 27	99.37 19	94.42 40	97.24 188	98.08 93	95.07 44	96.11 123	98.59 46	90.88 79	99.90 2	96.18 92	99.50 40	99.58 35

CNVR-MVS		97.68 8	97.44 24	98.37 8	98.90 59	95.86 7	97.27 186	98.08 93	95.81 20	97.87 58	98.31 81	94.26 15	99.68 75	97.02 57	99.49 43	99.57 36

DP-MVS Recon		95.68 103	95.12 116	97.37 60	99.19 37	94.19 46	97.03 206	98.08 93	88.35 328	95.09 163	97.65 152	89.97 90	99.48 124	92.08 212	98.59 126	98.44 188

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

MCST-MVS		97.18 34	96.84 51	98.20 15	99.30 29	95.35 16	97.12 202	98.07 98	93.54 112	96.08 125	97.69 147	93.86 18	99.71 67	96.50 74	99.39 63	99.55 43

NR-MVSNet		92.34 249	91.27 268	95.53 194	94.95 352	93.05 81	97.39 172	98.07 98	92.65 159	84.46 416	95.71 280	85.00 193	97.77 356	89.71 265	83.52 416	95.78 324

MP-MVS-pluss		96.70 65	96.27 83	97.98 26	99.23 35	94.71 30	96.96 217	98.06 101	90.67 244	95.55 147	98.78 40	91.07 72	99.86 9	96.58 72	99.55 30	99.38 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 58	96.71 63	97.12 76	99.01 51	92.31 110	97.98 71	98.06 101	93.11 136	97.44 65	98.55 49	90.93 77	99.55 108	96.06 93	99.25 80	99.51 49

MP-MVS		96.77 60	96.45 77	97.72 43	99.39 16	93.80 58	98.41 28	98.06 101	93.37 122	95.54 149	98.34 75	90.59 83	99.88 4	94.83 138	99.54 32	99.49 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 74	96.27 83	97.22 70	99.32 27	92.74 93	98.74 10	98.06 101	90.57 254	96.77 88	98.35 72	90.21 86	99.53 112	94.80 142	99.63 16	99.38 70

HPM-MVS		96.69 67	96.45 77	97.40 59	99.36 23	93.11 80	98.87 6	98.06 101	91.17 223	96.40 112	97.99 107	90.99 74	99.58 98	95.61 115	99.61 18	99.49 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 156	93.80 165	96.64 94	97.07 181	91.97 124	96.32 292	98.06 101	88.94 306	94.50 183	96.78 215	84.60 199	99.27 147	91.90 213	96.02 222	98.68 163

DeepC-MVS	93.07 3	96.06 89	95.66 94	97.29 64	97.96 128	93.17 79	97.30 182	98.06 101	93.92 97	93.38 220	98.66 43	86.83 150	99.73 61	95.60 117	99.22 82	98.96 114
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		97.30 29	97.03 40	98.11 18	98.77 62	95.06 26	97.34 177	98.04 108	95.96 15	97.09 79	97.88 121	93.18 28	99.71 67	95.84 104	99.17 91	99.56 40

DeepC-MVS_fast	93.89 2	96.93 49	96.64 65	97.78 36	98.64 73	94.30 41	97.41 167	98.04 108	94.81 59	96.59 99	98.37 70	91.24 68	99.64 87	95.16 124	99.52 35	99.42 65
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		96.88 51	96.80 57	97.11 78	99.02 48	92.34 108	97.98 71	98.03 110	93.52 115	97.43 67	98.51 56	91.40 64	99.56 106	96.05 94	99.26 78	99.43 63

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

RPMNet		88.98 366	87.05 380	94.77 242	94.45 377	87.19 316	90.23 458	98.03 110	77.87 457	92.40 238	87.55 462	80.17 296	99.51 117	68.84 464	93.95 278	97.60 259

save fliter					98.91 58	94.28 42	97.02 208	98.02 113	95.35 31

TEST9					98.70 65	94.19 46	96.41 278	98.02 113	88.17 332	96.03 126	97.56 164	92.74 36	99.59 95

train_agg		96.30 85	95.83 93	97.72 43	98.70 65	94.19 46	96.41 278	98.02 113	88.58 319	96.03 126	97.56 164	92.73 37	99.59 95	95.04 126	99.37 67	99.39 68

test_8					98.67 67	94.06 53	96.37 286	98.01 116	88.58 319	95.98 130	97.55 166	92.73 37	99.58 98

fmvsm_s_conf0.5_n_11		97.30 29	97.59 14	96.43 119	98.42 83	91.37 151	98.04 63	98.00 117	97.30 3	99.45 4	99.21 1	89.28 97	99.80 40	99.27 10	99.35 69	98.12 218

agg_prior					98.67 67	93.79 59		98.00 117		95.68 143			99.57 105

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

WR-MVS		92.34 249	91.53 257	94.77 242	95.13 345	90.83 179	96.40 282	97.98 120	91.88 190	89.29 330	95.54 291	82.50 247	97.80 352	89.79 264	85.27 389	95.69 331

HPM-MVS++		97.34 26	96.97 43	98.47 6	99.08 42	96.16 4	97.55 149	97.97 121	95.59 25	96.61 97	97.89 117	92.57 41	99.84 26	95.95 99	99.51 38	99.40 66

CANet		96.39 80	96.02 88	97.50 54	97.62 154	93.38 68	97.02 208	97.96 122	95.42 29	94.86 170	97.81 134	87.38 143	99.82 33	96.88 60	99.20 88	99.29 75

114514_t		93.95 180	93.06 197	96.63 98	99.07 43	91.61 138	97.46 164	97.96 122	77.99 455	93.00 229	97.57 162	86.14 166	99.33 139	89.22 281	99.15 95	98.94 121

IU-MVS					99.42 10	95.39 12		97.94 124	90.40 261	98.94 19				97.41 49	99.66 10	99.74 9

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

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

fmvsm_s_conf0.1_n_2		96.33 84	96.44 79	96.00 155	97.30 168	90.37 201	97.53 150	97.92 127	96.52 11	99.14 15	99.08 8	83.21 224	99.74 59	99.22 11	98.06 150	97.88 239

Anonymous20231211		90.63 332	89.42 348	94.27 273	98.24 100	89.19 256	98.05 62	97.89 128	79.95 446	88.25 360	94.96 314	72.56 383	98.13 297	89.70 266	85.14 391	95.49 335

原ACMM1				96.38 125	98.59 75	91.09 168		97.89 128	87.41 358	95.22 160	97.68 148	90.25 85	99.54 110	87.95 303	99.12 100	98.49 180

CDPH-MVS		95.97 94	95.38 106	97.77 38	98.93 56	94.44 39	96.35 287	97.88 130	86.98 366	96.65 95	97.89 117	91.99 51	99.47 125	92.26 201	99.46 46	99.39 68

test11								97.88 130

EIA-MVS		95.53 109	95.47 100	95.71 184	97.06 184	89.63 228	97.82 100	97.87 132	93.57 108	93.92 202	95.04 311	90.61 82	98.95 193	94.62 151	98.68 120	98.54 173

CS-MVS		96.86 52	97.06 35	96.26 135	98.16 112	91.16 166	99.09 3	97.87 132	95.30 33	97.06 80	98.03 101	91.72 54	98.71 239	97.10 55	99.17 91	98.90 130

无先验							95.79 329	97.87 132	83.87 415				99.65 79	87.68 315		98.89 136

3Dnovator+	91.43 4	95.40 110	94.48 148	98.16 17	96.90 201	95.34 17	98.48 25	97.87 132	94.65 70	88.53 351	98.02 103	83.69 215	99.71 67	93.18 187	98.96 110	99.44 61

VPNet		92.23 257	91.31 265	94.99 225	95.56 310	90.96 172	97.22 194	97.86 136	92.96 146	90.96 282	96.62 232	75.06 362	98.20 291	91.90 213	83.65 415	95.80 322

test_vis1_n_1920		94.17 165	94.58 140	92.91 343	97.42 166	82.02 414	97.83 98	97.85 137	94.68 67	98.10 48	98.49 58	70.15 402	99.32 141	97.91 30	98.82 114	97.40 268

DVP-MVS		97.91 4	97.81 5	98.22 14	99.45 6	95.36 14	98.21 47	97.85 137	94.92 50	98.73 30	98.87 31	95.08 10	99.84 26	97.52 42	99.67 6	99.48 56
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
TSAR-MVS + MP.		97.42 22	97.33 29	97.69 46	99.25 32	94.24 45	98.07 60	97.85 137	93.72 103	98.57 37	98.35 72	93.69 20	99.40 133	97.06 56	99.46 46	99.44 61
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SPE-MVS-test		96.89 50	97.04 39	96.45 118	98.29 93	91.66 137	99.03 4	97.85 137	95.84 18	96.90 83	97.97 109	91.24 68	98.75 229	96.92 59	99.33 70	98.94 121

test_fmvsmconf0.01_n		96.15 88	95.85 92	97.03 83	92.66 429	91.83 129	97.97 77	97.84 141	95.57 26	97.53 61	99.00 16	84.20 208	99.76 54	98.82 23	99.08 102	99.48 56

GDP-MVS		95.62 105	95.13 114	97.09 79	96.79 214	93.26 76	97.89 88	97.83 142	93.58 107	96.80 85	97.82 132	83.06 231	99.16 161	94.40 158	97.95 156	98.87 140

balanced_conf03		96.84 56	96.89 48	96.68 93	97.63 153	92.22 113	98.17 53	97.82 143	94.44 79	98.23 45	97.36 177	90.97 75	99.22 151	97.74 32	99.66 10	98.61 166

AdaColmap		94.34 160	93.68 170	96.31 129	98.59 75	91.68 136	96.59 267	97.81 144	89.87 271	92.15 248	97.06 198	83.62 218	99.54 110	89.34 276	98.07 149	97.70 252

MVSMamba_PlusPlus		96.51 74	96.48 72	96.59 102	98.07 120	91.97 124	98.14 54	97.79 145	90.43 259	97.34 70	97.52 167	91.29 67	99.19 154	98.12 28	99.64 14	98.60 167

KinetiMVS		95.26 117	94.75 134	96.79 90	96.99 194	92.05 120	97.82 100	97.78 146	94.77 63	96.46 109	97.70 145	80.62 286	99.34 138	92.37 200	98.28 140	98.97 111

mamv4		94.66 153	96.10 87	90.37 413	98.01 123	73.41 464	96.82 234	97.78 146	89.95 270	94.52 181	97.43 172	92.91 30	99.09 174	98.28 27	99.16 94	98.60 167

ETV-MVS		96.02 91	95.89 91	96.40 122	97.16 176	92.44 105	97.47 162	97.77 148	94.55 73	96.48 107	94.51 339	91.23 70	98.92 198	95.65 111	98.19 144	97.82 247

新几何1				97.32 62	98.60 74	93.59 63		97.75 149	81.58 437	95.75 138	97.85 126	90.04 88	99.67 77	86.50 338	99.13 98	98.69 162

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

EC-MVSNet		96.42 78	96.47 73	96.26 135	97.01 192	91.52 143	98.89 5	97.75 149	94.42 80	96.64 96	97.68 148	89.32 96	98.60 255	97.45 46	99.11 101	98.67 164

EI-MVSNet-Vis-set		96.51 74	96.47 73	96.63 98	98.24 100	91.20 160	96.89 225	97.73 152	94.74 65	96.49 106	98.49 58	90.88 79	99.58 98	96.44 76	98.32 138	99.13 89

PAPM_NR		95.01 133	94.59 139	96.26 135	98.89 60	90.68 187	97.24 188	97.73 152	91.80 191	92.93 234	96.62 232	89.13 100	99.14 166	89.21 282	97.78 160	98.97 111

Anonymous20240529		91.98 266	90.73 293	95.73 182	98.14 113	89.40 243	97.99 68	97.72 154	79.63 448	93.54 213	97.41 174	69.94 404	99.56 106	91.04 235	91.11 322	98.22 208

CHOSEN 280x420		93.12 216	92.72 214	94.34 267	96.71 227	87.27 312	90.29 457	97.72 154	86.61 373	91.34 271	95.29 299	84.29 207	98.41 271	93.25 185	98.94 111	97.35 271

EI-MVSNet-UG-set		96.34 83	96.30 82	96.47 115	98.20 107	90.93 175	96.86 228	97.72 154	94.67 68	96.16 122	98.46 62	90.43 84	99.58 98	96.23 82	97.96 155	98.90 130

LS3D		93.57 197	92.61 219	96.47 115	97.59 157	91.61 138	97.67 125	97.72 154	85.17 397	90.29 293	98.34 75	84.60 199	99.73 61	83.85 380	98.27 141	98.06 228

PAPR		94.18 164	93.42 186	96.48 114	97.64 151	91.42 150	95.55 343	97.71 158	88.99 303	92.34 244	95.82 272	89.19 98	99.11 169	86.14 344	97.38 172	98.90 130

UGNet		94.04 175	93.28 189	96.31 129	96.85 206	91.19 161	97.88 90	97.68 159	94.40 82	93.00 229	96.18 252	73.39 379	99.61 90	91.72 219	98.46 132	98.13 216
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				95.46 204	98.18 111	88.90 265		97.66 160	82.73 428	97.03 81	98.07 97	90.06 87	98.85 205	89.67 267	98.98 109	98.64 165

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

DTE-MVSNet		90.56 333	89.75 339	93.01 339	93.95 390	87.25 313	97.64 133	97.65 162	90.74 239	87.12 383	95.68 283	79.97 300	97.00 409	83.33 381	81.66 426	94.78 393

TAPA-MVS	90.10 7	92.30 252	91.22 271	95.56 191	98.33 91	89.60 230	96.79 240	97.65 162	81.83 434	91.52 266	97.23 187	87.94 123	98.91 200	71.31 458	98.37 136	98.17 214
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 217	92.45 227	95.05 219	98.09 116	89.21 253	96.89 225	97.64 164	93.18 132	91.79 260	97.28 182	75.35 361	98.65 249	88.99 287	92.84 292	97.28 274

test_cas_vis1_n_1920		94.48 158	94.55 144	94.28 272	96.78 219	86.45 338	97.63 135	97.64 164	93.32 125	97.68 60	98.36 71	73.75 377	99.08 177	96.73 65	99.05 104	97.31 273

NormalMVS		96.36 82	96.11 86	97.12 76	99.37 19	92.90 87	97.99 68	97.63 166	95.92 16	96.57 102	97.93 111	85.34 184	99.50 120	94.99 129	99.21 83	98.97 111

Elysia		94.00 177	93.12 194	96.64 94	96.08 289	92.72 95	97.50 153	97.63 166	91.15 225	94.82 171	97.12 193	74.98 364	99.06 183	90.78 240	98.02 151	98.12 218

StellarMVS		94.00 177	93.12 194	96.64 94	96.08 289	92.72 95	97.50 153	97.63 166	91.15 225	94.82 171	97.12 193	74.98 364	99.06 183	90.78 240	98.02 151	98.12 218

cdsmvs_eth3d_5k		23.24 453	30.99 455	0.00 472	0.00 495	0.00 497	0.00 484	97.63 166	0.00 490	0.00 491	96.88 211	84.38 204	0.00 491	0.00 490	0.00 489	0.00 487

DPM-MVS		95.69 102	94.92 124	98.01 21	98.08 119	95.71 10	95.27 359	97.62 170	90.43 259	95.55 147	97.07 197	91.72 54	99.50 120	89.62 269	98.94 111	98.82 146

sasdasda		96.02 91	95.45 101	97.75 40	97.59 157	95.15 24	98.28 35	97.60 171	94.52 75	96.27 117	96.12 257	87.65 130	99.18 157	96.20 88	94.82 254	98.91 127

canonicalmvs		96.02 91	95.45 101	97.75 40	97.59 157	95.15 24	98.28 35	97.60 171	94.52 75	96.27 117	96.12 257	87.65 130	99.18 157	96.20 88	94.82 254	98.91 127

test222					98.24 100	92.21 114	95.33 354	97.60 171	79.22 450	95.25 158	97.84 128	88.80 106			99.15 95	98.72 159

cascas		91.20 308	90.08 321	94.58 253	94.97 350	89.16 257	93.65 422	97.59 174	79.90 447	89.40 325	92.92 405	75.36 360	98.36 279	92.14 206	94.75 257	96.23 301

E2		95.20 123	95.00 121	95.79 173	96.79 214	89.66 225	96.82 234	97.58 175	92.35 170	95.28 156	97.83 130	86.68 152	98.76 223	94.79 145	96.92 193	98.95 118

E3		95.20 123	95.00 121	95.79 173	96.77 221	89.66 225	96.82 234	97.58 175	92.35 170	95.28 156	97.83 130	86.69 151	98.76 223	94.79 145	96.92 193	98.95 118

h-mvs33		94.15 167	93.52 178	96.04 149	97.81 139	90.22 205	97.62 137	97.58 175	95.19 36	96.74 89	97.45 169	83.67 216	99.61 90	95.85 102	79.73 433	98.29 204

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

E5		95.04 131	94.88 126	95.52 195	96.62 230	89.02 261	97.29 183	97.57 178	92.54 162	95.04 164	97.89 117	85.65 177	98.77 219	94.92 132	96.44 217	98.78 149

MGCFI-Net		95.94 96	95.40 105	97.56 53	97.59 157	94.62 32	98.21 47	97.57 178	94.41 81	96.17 121	96.16 255	87.54 135	99.17 159	96.19 90	94.73 259	98.91 127

MVSFormer		95.37 111	95.16 113	95.99 156	96.34 265	91.21 158	98.22 45	97.57 178	91.42 208	96.22 119	97.32 178	86.20 164	97.92 339	94.07 164	99.05 104	98.85 142

test_djsdf		93.07 219	92.76 209	94.00 286	93.49 408	88.70 269	98.22 45	97.57 178	91.42 208	90.08 305	95.55 290	82.85 238	97.92 339	94.07 164	91.58 313	95.40 346

OMC-MVS		95.09 128	94.70 135	96.25 138	98.46 79	91.28 154	96.43 274	97.57 178	92.04 186	94.77 175	97.96 110	87.01 149	99.09 174	91.31 229	96.77 198	98.36 195

E4		95.09 128	94.86 128	95.77 176	96.58 236	89.56 233	96.85 229	97.56 184	92.50 164	95.03 166	97.86 124	86.03 167	98.78 215	94.71 148	96.65 207	98.96 114

viewcassd2359sk11		95.26 117	95.09 118	95.80 170	96.95 198	89.72 224	96.80 239	97.56 184	92.21 177	95.37 154	97.80 136	87.17 147	98.77 219	94.82 140	97.10 187	98.90 130

PS-MVSNAJss		93.74 190	93.51 179	94.44 261	93.91 392	89.28 251	97.75 110	97.56 184	92.50 164	89.94 307	96.54 235	88.65 109	98.18 294	93.83 173	90.90 327	95.86 316

casdiffmvs_mvg		95.81 101	95.57 95	96.51 111	96.87 203	91.49 144	97.50 153	97.56 184	93.99 95	95.13 162	97.92 114	87.89 124	98.78 215	95.97 98	97.33 175	99.26 79
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E3new		95.28 115	95.11 117	95.80 170	97.03 189	89.76 222	96.78 244	97.54 188	92.06 185	95.40 153	97.75 139	87.49 139	98.76 223	94.85 135	97.10 187	98.88 138

jajsoiax		92.42 245	91.89 245	94.03 285	93.33 416	88.50 278	97.73 115	97.53 189	92.00 188	88.85 343	96.50 237	75.62 359	98.11 301	93.88 171	91.56 314	95.48 336

mvs_tets		92.31 251	91.76 248	93.94 294	93.41 413	88.29 283	97.63 135	97.53 189	92.04 186	88.76 346	96.45 239	74.62 369	98.09 306	93.91 169	91.48 315	95.45 341

dcpmvs_2		96.37 81	97.05 38	94.31 270	98.96 55	84.11 387	97.56 144	97.51 191	93.92 97	97.43 67	98.52 55	92.75 35	99.32 141	97.32 54	99.50 40	99.51 49

HQP_MVS		93.78 189	93.43 184	94.82 235	96.21 269	89.99 211	97.74 113	97.51 191	94.85 53	91.34 271	96.64 225	81.32 271	98.60 255	93.02 193	92.23 301	95.86 316

plane_prior5								97.51 191					98.60 255	93.02 193	92.23 301	95.86 316

viewmanbaseed2359cas		95.24 120	95.02 120	95.91 159	96.87 203	89.98 213	96.82 234	97.49 194	92.26 173	95.47 151	97.82 132	86.47 157	98.69 241	94.80 142	97.20 183	99.06 101

reproduce_monomvs		91.30 303	91.10 275	91.92 373	96.82 211	82.48 408	97.01 211	97.49 194	94.64 71	88.35 354	95.27 302	70.53 397	98.10 302	95.20 122	84.60 401	95.19 364

viewmacassd2359aftdt		95.07 130	94.80 130	95.87 162	96.53 246	89.84 219	96.90 224	97.48 196	92.44 166	95.36 155	97.89 117	85.23 187	98.68 243	94.40 158	97.00 191	99.09 96

PS-MVSNAJ		95.37 111	95.33 108	95.49 200	97.35 167	90.66 188	95.31 356	97.48 196	93.85 100	96.51 105	95.70 282	88.65 109	99.65 79	94.80 142	98.27 141	96.17 305

API-MVS		94.84 144	94.49 147	95.90 160	97.90 134	92.00 123	97.80 104	97.48 196	89.19 295	94.81 173	96.71 218	88.84 105	99.17 159	88.91 289	98.76 118	96.53 294

MG-MVS		95.61 106	95.38 106	96.31 129	98.42 83	90.53 190	96.04 312	97.48 196	93.47 117	95.67 144	98.10 94	89.17 99	99.25 148	91.27 230	98.77 117	99.13 89

MAR-MVS		94.22 163	93.46 181	96.51 111	98.00 125	92.19 117	97.67 125	97.47 200	88.13 336	93.00 229	95.84 270	84.86 197	99.51 117	87.99 302	98.17 146	97.83 246
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		92.98 223	92.53 223	94.32 268	96.12 284	89.20 254	95.28 357	97.47 200	92.66 158	89.90 308	95.62 286	80.58 287	98.40 272	92.73 198	92.40 299	95.38 348
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 301	90.22 317	94.68 246	94.86 359	87.86 300	97.23 192	97.46 202	87.99 337	89.90 308	96.92 209	66.35 432	98.23 288	90.30 254	90.99 325	97.96 233

nrg030		94.05 174	93.31 188	96.27 134	95.22 337	94.59 33	98.34 30	97.46 202	92.93 147	91.21 280	96.64 225	87.23 146	98.22 289	94.99 129	85.80 381	95.98 315

XVG-OURS		93.72 191	93.35 187	94.80 240	97.07 181	88.61 272	94.79 377	97.46 202	91.97 189	93.99 199	97.86 124	81.74 265	98.88 202	92.64 199	92.67 297	96.92 286

LPG-MVS_test		92.94 226	92.56 220	94.10 280	96.16 279	88.26 285	97.65 129	97.46 202	91.29 212	90.12 301	97.16 190	79.05 316	98.73 233	92.25 203	91.89 309	95.31 353

LGP-MVS_train				94.10 280	96.16 279	88.26 285		97.46 202	91.29 212	90.12 301	97.16 190	79.05 316	98.73 233	92.25 203	91.89 309	95.31 353

MVS		91.71 274	90.44 304	95.51 197	95.20 339	91.59 140	96.04 312	97.45 207	73.44 465	87.36 379	95.60 287	85.42 183	99.10 171	85.97 349	97.46 167	95.83 320

XVG-OURS-SEG-HR		93.86 186	93.55 174	94.81 237	97.06 184	88.53 277	95.28 357	97.45 207	91.68 196	94.08 198	97.68 148	82.41 250	98.90 201	93.84 172	92.47 298	96.98 282

baseline		95.58 107	95.42 104	96.08 145	96.78 219	90.41 196	97.16 199	97.45 207	93.69 106	95.65 145	97.85 126	87.29 144	98.68 243	95.66 108	97.25 181	99.13 89

ab-mvs		93.57 197	92.55 221	96.64 94	97.28 170	91.96 126	95.40 350	97.45 207	89.81 276	93.22 226	96.28 248	79.62 307	99.46 126	90.74 243	93.11 289	98.50 178

xiu_mvs_v2_base		95.32 114	95.29 109	95.40 205	97.22 172	90.50 191	95.44 349	97.44 211	93.70 105	96.46 109	96.18 252	88.59 113	99.53 112	94.79 145	97.81 159	96.17 305

1314		92.81 235	92.03 238	95.14 215	95.33 329	89.52 238	96.04 312	97.44 211	87.72 351	86.25 400	95.33 298	83.84 213	98.79 214	89.26 279	97.05 190	97.11 280

casdiffmvs		95.64 104	95.49 98	96.08 145	96.76 225	90.45 193	97.29 183	97.44 211	94.00 94	95.46 152	97.98 108	87.52 138	98.73 233	95.64 112	97.33 175	99.08 98
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt07		94.76 150	94.68 136	95.01 223	96.76 225	87.41 308	96.38 284	97.43 214	92.65 159	94.52 181	97.75 139	85.55 181	98.81 211	94.36 160	96.69 204	98.82 146

XXY-MVS		92.16 259	91.23 270	94.95 231	94.75 364	90.94 174	97.47 162	97.43 214	89.14 296	88.90 339	96.43 240	79.71 304	98.24 287	89.56 270	87.68 362	95.67 332

anonymousdsp		92.16 259	91.55 256	93.97 290	92.58 431	89.55 235	97.51 152	97.42 216	89.42 289	88.40 353	94.84 321	80.66 285	97.88 344	91.87 215	91.28 319	94.48 402

Effi-MVS+		94.93 138	94.45 149	96.36 127	96.61 232	91.47 147	96.41 278	97.41 217	91.02 231	94.50 183	95.92 266	87.53 136	98.78 215	93.89 170	96.81 197	98.84 145

RRT-MVS		94.51 156	94.35 153	94.98 227	96.40 259	86.55 335	97.56 144	97.41 217	93.19 130	94.93 168	97.04 199	79.12 314	99.30 145	96.19 90	97.32 177	99.09 96

HQP3-MVS								97.39 219							92.10 306

HQP-MVS		93.19 213	92.74 212	94.54 256	95.86 295	89.33 247	96.65 258	97.39 219	93.55 109	90.14 295	95.87 268	80.95 276	98.50 265	92.13 209	92.10 306	95.78 324

PLC	91.00 6	94.11 171	93.43 184	96.13 143	98.58 77	91.15 167	96.69 254	97.39 219	87.29 361	91.37 270	96.71 218	88.39 114	99.52 116	87.33 325	97.13 186	97.73 250
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
diffmvs_AUTHOR		95.33 113	95.27 110	95.50 199	96.37 263	89.08 259	96.08 310	97.38 222	93.09 138	96.53 104	97.74 142	86.45 158	98.68 243	96.32 78	97.48 166	98.75 155

v7n		90.76 325	89.86 332	93.45 324	93.54 405	87.60 306	97.70 123	97.37 223	88.85 309	87.65 372	94.08 369	81.08 275	98.10 302	84.68 366	83.79 414	94.66 399

UnsupCasMVSNet_eth		85.99 405	84.45 409	90.62 409	89.97 449	82.40 411	93.62 423	97.37 223	89.86 272	78.59 455	92.37 415	65.25 442	95.35 444	82.27 395	70.75 463	94.10 413

viewdifsd2359ckpt13		94.87 142	94.52 145	95.90 160	96.88 202	90.19 206	96.92 221	97.36 225	91.26 216	94.65 177	97.46 168	85.79 173	98.64 250	93.64 176	96.76 199	98.88 138

ACMM	89.79 8	92.96 224	92.50 225	94.35 265	96.30 267	88.71 268	97.58 140	97.36 225	91.40 210	90.53 288	96.65 224	79.77 303	98.75 229	91.24 231	91.64 311	95.59 334
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 133	94.76 131	95.75 179	96.58 236	91.71 133	96.25 297	97.35 227	92.99 140	96.70 91	96.63 229	82.67 242	99.44 129	96.22 83	97.46 167	96.11 311

xiu_mvs_v1_base		95.01 133	94.76 131	95.75 179	96.58 236	91.71 133	96.25 297	97.35 227	92.99 140	96.70 91	96.63 229	82.67 242	99.44 129	96.22 83	97.46 167	96.11 311

xiu_mvs_v1_base_debi		95.01 133	94.76 131	95.75 179	96.58 236	91.71 133	96.25 297	97.35 227	92.99 140	96.70 91	96.63 229	82.67 242	99.44 129	96.22 83	97.46 167	96.11 311

diffmvs		95.25 119	95.13 114	95.63 187	96.43 258	89.34 246	95.99 316	97.35 227	92.83 153	96.31 115	97.37 176	86.44 159	98.67 246	96.26 80	97.19 184	98.87 140
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WTY-MVS		94.71 152	94.02 161	96.79 90	97.71 145	92.05 120	96.59 267	97.35 227	90.61 250	94.64 178	96.93 206	86.41 160	99.39 134	91.20 232	94.71 260	98.94 121

viewdifsd2359ckpt09		94.81 147	94.37 152	96.12 144	96.91 199	90.75 184	96.94 218	97.31 232	90.51 257	94.31 188	97.38 175	85.70 175	98.71 239	93.54 177	96.75 200	98.90 130

SSM_0407		94.54 155	94.12 160	95.80 170	96.79 214	90.38 198	96.79 240	97.29 233	91.24 217	93.68 206	97.60 159	85.03 191	98.67 246	92.14 206	96.51 210	98.35 197

SSM_0404		94.73 151	94.31 155	95.98 157	97.05 186	90.90 177	97.01 211	97.29 233	91.24 217	94.17 195	97.60 159	85.03 191	98.76 223	92.14 206	97.30 178	98.29 204

F-COLMAP		93.58 195	92.98 201	95.37 206	98.40 86	88.98 263	97.18 197	97.29 233	87.75 350	90.49 289	97.10 196	85.21 188	99.50 120	86.70 335	96.72 203	97.63 254

VortexMVS		92.88 230	92.64 216	93.58 317	96.58 236	87.53 307	96.93 220	97.28 236	92.78 156	89.75 313	94.99 312	82.73 241	97.76 357	94.60 153	88.16 357	95.46 339

XVG-ACMP-BASELINE		90.93 321	90.21 318	93.09 337	94.31 383	85.89 353	95.33 354	97.26 237	91.06 230	89.38 326	95.44 296	68.61 415	98.60 255	89.46 272	91.05 323	94.79 391

PCF-MVS	89.48 11	91.56 285	89.95 329	96.36 127	96.60 233	92.52 103	92.51 442	97.26 237	79.41 449	88.90 339	96.56 234	84.04 212	99.55 108	77.01 434	97.30 178	97.01 281
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 239	92.14 234	94.05 283	96.40 259	88.20 288	97.36 175	97.25 239	91.52 203	88.30 357	96.64 225	78.46 328	98.72 238	91.86 216	91.48 315	95.23 360
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 195	93.46 181	93.94 294	96.19 273	86.16 347	93.73 417	97.24 240	91.54 199	93.50 215	97.04 199	85.64 179	96.91 412	90.68 245	95.59 236	98.76 151

IMVS_0407		93.94 181	93.75 167	94.49 258	96.19 273	86.16 347	96.35 287	97.24 240	91.54 199	93.50 215	97.04 199	85.64 179	98.54 262	90.68 245	95.59 236	98.76 151

IMVS_0404		92.44 243	91.92 243	94.00 286	96.19 273	86.16 347	93.84 414	97.24 240	91.54 199	88.17 363	97.04 199	76.96 346	97.09 403	90.68 245	95.59 236	98.76 151

IMVS_0403		93.98 179	93.79 166	94.55 255	96.19 273	86.16 347	96.35 287	97.24 240	91.54 199	93.59 210	97.04 199	85.86 170	98.73 233	90.68 245	95.59 236	98.76 151

OPM-MVS		93.28 209	92.76 209	94.82 235	94.63 370	90.77 182	96.65 258	97.18 244	93.72 103	91.68 264	97.26 185	79.33 311	98.63 252	92.13 209	92.28 300	95.07 368
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 228	92.02 239	95.56 191	98.19 109	90.80 180	95.27 359	97.18 244	87.96 338	91.86 259	95.68 283	80.44 290	98.99 191	84.01 375	97.54 165	96.89 287

alignmvs		95.87 100	95.23 111	97.78 36	97.56 163	95.19 22	97.86 91	97.17 246	94.39 83	96.47 108	96.40 242	85.89 169	99.20 153	96.21 87	95.11 250	98.95 118

MVS_Test		94.89 140	94.62 138	95.68 185	96.83 209	89.55 235	96.70 252	97.17 246	91.17 223	95.60 146	96.11 261	87.87 126	98.76 223	93.01 195	97.17 185	98.72 159

Fast-Effi-MVS+		93.46 201	92.75 211	95.59 190	96.77 221	90.03 208	96.81 238	97.13 248	88.19 331	91.30 274	94.27 357	86.21 163	98.63 252	87.66 316	96.46 216	98.12 218

FE-MVSNET3		91.65 278	90.67 297	94.60 248	93.65 403	90.95 173	94.86 375	97.12 249	89.69 279	89.21 334	93.62 388	81.17 274	97.67 364	87.54 320	89.14 345	95.17 366

EI-MVSNet		93.03 221	92.88 205	93.48 322	95.77 301	86.98 321	96.44 272	97.12 249	90.66 246	91.30 274	97.64 155	86.56 154	98.05 314	89.91 260	90.55 331	95.41 343

MVSTER		93.20 212	92.81 208	94.37 264	96.56 241	89.59 231	97.06 205	97.12 249	91.24 217	91.30 274	95.96 264	82.02 258	98.05 314	93.48 180	90.55 331	95.47 338

viewmambaseed2359dif		94.28 161	94.14 158	94.71 245	96.21 269	86.97 322	95.93 319	97.11 252	89.00 302	95.00 167	97.70 145	86.02 168	98.59 259	93.71 175	96.59 209	98.57 171

test_yl		94.78 148	94.23 156	96.43 119	97.74 143	91.22 156	96.85 229	97.10 253	91.23 220	95.71 140	96.93 206	84.30 205	99.31 143	93.10 188	95.12 248	98.75 155

DCV-MVSNet		94.78 148	94.23 156	96.43 119	97.74 143	91.22 156	96.85 229	97.10 253	91.23 220	95.71 140	96.93 206	84.30 205	99.31 143	93.10 188	95.12 248	98.75 155

LTVRE_ROB	88.41 13	90.99 317	89.92 331	94.19 274	96.18 277	89.55 235	96.31 293	97.09 255	87.88 341	85.67 406	95.91 267	78.79 324	98.57 260	81.50 398	89.98 336	94.44 405
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		93.46 201	93.23 191	94.17 275	96.12 284	85.42 362	96.43 274	97.08 256	92.91 148	94.21 191	98.00 105	80.82 282	98.74 231	94.41 157	89.05 346	98.34 201

test_fmvs1_n		92.73 237	92.88 205	92.29 363	96.08 289	81.05 422	97.98 71	97.08 256	90.72 241	96.79 87	98.18 91	63.07 447	98.45 269	97.62 40	98.42 135	97.36 269

v10		91.04 315	90.23 315	93.49 321	94.12 386	88.16 291	97.32 180	97.08 256	88.26 330	88.29 358	94.22 362	82.17 255	97.97 326	86.45 339	84.12 408	94.33 408

viewdifsd2359ckpt11		93.46 201	93.22 192	94.17 275	96.11 286	85.42 362	96.43 274	97.07 259	92.91 148	94.20 192	98.00 105	80.82 282	98.73 233	94.42 156	89.04 348	98.34 201

mamba_0408		93.70 192	92.99 198	95.83 167	96.79 214	90.38 198	88.69 467	97.07 259	90.96 233	93.68 206	97.31 180	84.97 194	98.76 223	90.95 236	96.51 210	98.35 197

SSM_04072		93.51 200	92.99 198	95.05 219	96.79 214	90.38 198	88.69 467	97.07 259	90.96 233	93.68 206	97.31 180	84.97 194	96.42 423	90.95 236	96.51 210	98.35 197

v144192		91.06 314	90.28 311	93.39 325	93.66 401	87.23 315	96.83 233	97.07 259	87.43 357	89.69 316	94.28 356	81.48 268	98.00 321	87.18 329	84.92 397	94.93 376

v1192		91.07 313	90.23 315	93.58 317	93.70 398	87.82 302	96.73 248	97.07 259	87.77 348	89.58 319	94.32 354	80.90 280	97.97 326	86.52 337	85.48 384	94.95 372

v8		91.29 305	90.53 303	93.57 319	94.15 385	88.12 292	97.34 177	97.06 264	88.99 303	88.32 356	94.26 359	83.08 229	98.01 320	87.62 318	83.92 412	94.57 401

mvs_anonymous		93.82 187	93.74 168	94.06 282	96.44 257	85.41 364	95.81 327	97.05 265	89.85 274	90.09 304	96.36 244	87.44 141	97.75 359	93.97 166	96.69 204	99.02 103

IterMVS-LS		92.29 253	91.94 242	93.34 327	96.25 268	86.97 322	96.57 270	97.05 265	90.67 244	89.50 324	94.80 324	86.59 153	97.64 368	89.91 260	86.11 379	95.40 346
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 323	90.03 326	93.29 329	93.55 404	86.96 324	96.74 247	97.04 267	87.36 359	89.52 323	94.34 351	80.23 295	97.97 326	86.27 340	85.21 390	94.94 374

CDS-MVSNet		94.14 170	93.54 175	95.93 158	96.18 277	91.46 148	96.33 291	97.04 267	88.97 305	93.56 211	96.51 236	87.55 134	97.89 343	89.80 263	95.95 224	98.44 188
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 359	89.26 352	91.19 398	95.16 340	80.29 433	94.53 384	97.03 269	91.79 192	88.86 342	94.10 366	69.94 404	97.82 349	85.29 358	86.66 375	95.45 341

v1144		91.37 298	90.60 299	93.68 311	93.89 393	88.23 287	96.84 232	97.03 269	88.37 327	89.69 316	94.39 346	82.04 257	97.98 323	87.80 306	85.37 386	94.84 382

v1240		90.70 329	89.85 333	93.23 331	93.51 407	86.80 325	96.61 264	97.02 271	87.16 364	89.58 319	94.31 355	79.55 308	97.98 323	85.52 355	85.44 385	94.90 379

EPP-MVSNet		95.22 122	95.04 119	95.76 177	97.49 164	89.56 233	98.67 15	97.00 272	90.69 242	94.24 190	97.62 157	89.79 93	98.81 211	93.39 184	96.49 214	98.92 126

V42		91.58 284	90.87 282	93.73 305	94.05 389	88.50 278	97.32 180	96.97 273	88.80 315	89.71 314	94.33 352	82.54 246	98.05 314	89.01 286	85.07 393	94.64 400

test_fmvs1		93.21 211	93.53 176	92.25 366	96.55 243	81.20 421	97.40 171	96.96 274	90.68 243	96.80 85	98.04 100	69.25 410	98.40 272	97.58 41	98.50 128	97.16 279

FMVSNet2		91.31 302	90.08 321	94.99 225	96.51 250	92.21 114	97.41 167	96.95 275	88.82 312	88.62 348	94.75 326	73.87 373	97.42 391	85.20 361	88.55 354	95.35 350

ACMH	87.59 16	90.53 334	89.42 348	93.87 299	96.21 269	87.92 297	97.24 188	96.94 276	88.45 325	83.91 426	96.27 249	71.92 386	98.62 254	84.43 369	89.43 342	95.05 370
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 299	90.27 312	94.59 249	96.51 250	91.18 163	97.50 153	96.93 277	88.82 312	89.35 327	94.51 339	73.87 373	97.29 398	86.12 345	88.82 349	95.31 353

test1		91.35 299	90.27 312	94.59 249	96.51 250	91.18 163	97.50 153	96.93 277	88.82 312	89.35 327	94.51 339	73.87 373	97.29 398	86.12 345	88.82 349	95.31 353

FMVSNet3		91.78 272	90.69 296	95.03 222	96.53 246	92.27 112	97.02 208	96.93 277	89.79 277	89.35 327	94.65 332	77.01 344	97.47 386	86.12 345	88.82 349	95.35 350

FMVSNet1		89.88 354	88.31 367	94.59 249	95.41 319	91.18 163	97.50 153	96.93 277	86.62 372	87.41 377	94.51 339	65.94 437	97.29 398	83.04 384	87.43 365	95.31 353

GeoE		93.89 184	93.28 189	95.72 183	96.96 197	89.75 223	98.24 43	96.92 281	89.47 286	92.12 250	97.21 188	84.42 203	98.39 277	87.71 311	96.50 213	99.01 106

SymmetryMVS		95.94 96	95.54 96	97.15 74	97.85 136	92.90 87	97.99 68	96.91 282	95.92 16	96.57 102	97.93 111	85.34 184	99.50 120	94.99 129	96.39 219	99.05 102

miper_enhance_ethall		91.54 288	91.01 278	93.15 335	95.35 325	87.07 320	93.97 406	96.90 283	86.79 370	89.17 335	93.43 399	86.55 155	97.64 368	89.97 259	86.93 370	94.74 396

eth_miper_zixun_eth		91.02 316	90.59 300	92.34 361	95.33 329	84.35 383	94.10 403	96.90 283	88.56 321	88.84 344	94.33 352	84.08 210	97.60 373	88.77 292	84.37 406	95.06 369

TAMVS		94.01 176	93.46 181	95.64 186	96.16 279	90.45 193	96.71 251	96.89 285	89.27 293	93.46 218	96.92 209	87.29 144	97.94 336	88.70 294	95.74 230	98.53 174

miper_ehance_all_eth		91.59 282	91.13 274	92.97 341	95.55 311	86.57 333	94.47 387	96.88 286	87.77 348	88.88 341	94.01 371	86.22 162	97.54 379	89.49 271	86.93 370	94.79 391

v2v482		91.59 282	90.85 285	93.80 302	93.87 394	88.17 290	96.94 218	96.88 286	89.54 283	89.53 322	94.90 318	81.70 266	98.02 319	89.25 280	85.04 395	95.20 361

CNLPA		94.28 161	93.53 176	96.52 107	98.38 89	92.55 102	96.59 267	96.88 286	90.13 267	91.91 256	97.24 186	85.21 188	99.09 174	87.64 317	97.83 158	97.92 236

PAPM		91.52 289	90.30 310	95.20 212	95.30 332	89.83 220	93.38 428	96.85 289	86.26 380	88.59 349	95.80 273	84.88 196	98.15 296	75.67 439	95.93 225	97.63 254

c3_l		91.38 296	90.89 281	92.88 345	95.58 309	86.30 341	94.68 379	96.84 290	88.17 332	88.83 345	94.23 360	85.65 177	97.47 386	89.36 275	84.63 399	94.89 380

pm-mvs1		90.72 328	89.65 343	93.96 291	94.29 384	89.63 228	97.79 106	96.82 291	89.07 298	86.12 403	95.48 295	78.61 326	97.78 354	86.97 333	81.67 425	94.46 403

test_vis1_n		92.37 248	92.26 232	92.72 351	94.75 364	82.64 404	98.02 65	96.80 292	91.18 222	97.77 59	97.93 111	58.02 457	98.29 285	97.63 38	98.21 143	97.23 277

CMPMVS	62.92 21	85.62 410	84.92 402	87.74 436	89.14 454	73.12 466	94.17 401	96.80 292	73.98 462	73.65 464	94.93 316	66.36 431	97.61 372	83.95 377	91.28 319	92.48 440
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 341	89.77 337	91.78 382	94.33 381	84.72 380	95.55 343	96.73 294	86.17 382	86.36 399	95.28 301	71.28 391	97.80 352	84.09 374	98.14 147	92.81 432

Effi-MVS+-dtu		93.08 218	93.21 193	92.68 354	96.02 292	83.25 397	97.14 201	96.72 295	93.85 100	91.20 281	93.44 396	83.08 229	98.30 284	91.69 222	95.73 231	96.50 296

TSAR-MVS + GP.		96.69 67	96.49 71	97.27 67	98.31 92	93.39 67	96.79 240	96.72 295	94.17 89	97.44 65	97.66 151	92.76 34	99.33 139	96.86 62	97.76 162	99.08 98

1112_ss		93.37 206	92.42 228	96.21 139	97.05 186	90.99 170	96.31 293	96.72 295	86.87 369	89.83 311	96.69 222	86.51 156	99.14 166	88.12 299	93.67 283	98.50 178

PVSNet	86.66 18	92.24 256	91.74 251	93.73 305	97.77 141	83.69 394	92.88 437	96.72 295	87.91 340	93.00 229	94.86 320	78.51 327	99.05 186	86.53 336	97.45 171	98.47 183

miper_lstm_enhance		90.50 337	90.06 325	91.83 378	95.33 329	83.74 391	93.86 412	96.70 299	87.56 355	87.79 369	93.81 379	83.45 221	96.92 411	87.39 323	84.62 400	94.82 386

v148		90.99 317	90.38 306	92.81 348	93.83 395	85.80 354	96.78 244	96.68 300	89.45 288	88.75 347	93.93 375	82.96 235	97.82 349	87.83 305	83.25 417	94.80 389

ACMH+	87.92 14	90.20 345	89.18 354	93.25 330	96.48 253	86.45 338	96.99 214	96.68 300	88.83 311	84.79 415	96.22 251	70.16 401	98.53 263	84.42 370	88.04 358	94.77 394

CANet_DTU		94.37 159	93.65 171	96.55 104	96.46 256	92.13 118	96.21 301	96.67 302	94.38 84	93.53 214	97.03 204	79.34 310	99.71 67	90.76 242	98.45 133	97.82 247

cl____		90.96 320	90.32 308	92.89 344	95.37 323	86.21 344	94.46 389	96.64 303	87.82 344	88.15 364	94.18 363	82.98 233	97.54 379	87.70 312	85.59 382	94.92 378

HY-MVS	89.66 9	93.87 185	92.95 202	96.63 98	97.10 180	92.49 104	95.64 340	96.64 303	89.05 300	93.00 229	95.79 276	85.77 174	99.45 128	89.16 285	94.35 262	97.96 233

Test_1112_low_res		92.84 233	91.84 246	95.85 166	97.04 188	89.97 215	95.53 345	96.64 303	85.38 392	89.65 318	95.18 306	85.86 170	99.10 171	87.70 312	93.58 288	98.49 180

DIV-MVS_self_test		90.97 319	90.33 307	92.88 345	95.36 324	86.19 346	94.46 389	96.63 306	87.82 344	88.18 362	94.23 360	82.99 232	97.53 381	87.72 309	85.57 383	94.93 376

Fast-Effi-MVS+-dtu		92.29 253	91.99 240	93.21 333	95.27 333	85.52 360	97.03 206	96.63 306	92.09 183	89.11 337	95.14 308	80.33 293	98.08 307	87.54 320	94.74 258	96.03 314

UnsupCasMVSNet_bld		82.13 427	79.46 432	90.14 416	88.00 464	82.47 409	90.89 455	96.62 308	78.94 451	75.61 459	84.40 470	56.63 460	96.31 425	77.30 431	66.77 471	91.63 451

cl22		91.21 307	90.56 302	93.14 336	96.09 288	86.80 325	94.41 391	96.58 309	87.80 346	88.58 350	93.99 373	80.85 281	97.62 371	89.87 262	86.93 370	94.99 371

jason		94.84 144	94.39 151	96.18 141	95.52 312	90.93 175	96.09 309	96.52 310	89.28 292	96.01 129	97.32 178	84.70 198	98.77 219	95.15 125	98.91 113	98.85 142
jason: jason.
tt0805		91.09 312	90.07 324	94.16 278	95.61 307	88.31 282	97.56 144	96.51 311	89.56 282	89.17 335	95.64 285	67.08 429	98.38 278	91.07 234	88.44 355	95.80 322

AUN-MVS		91.76 273	90.75 291	94.81 237	97.00 193	88.57 274	96.65 258	96.49 312	89.63 280	92.15 248	96.12 257	78.66 325	98.50 265	90.83 238	79.18 436	97.36 269

hse-mvs2		93.45 204	92.99 198	94.81 237	97.02 191	88.59 273	96.69 254	96.47 313	95.19 36	96.74 89	96.16 255	83.67 216	98.48 268	95.85 102	79.13 437	97.35 271

SD_0403		90.01 349	90.02 327	89.96 419	95.65 306	76.76 454	95.76 331	96.46 314	90.58 253	86.59 396	96.29 247	82.12 256	94.78 448	73.00 453	93.76 281	98.35 197

EG-PatchMatch MVS		87.02 390	85.44 394	91.76 384	92.67 428	85.00 374	96.08 310	96.45 315	83.41 423	79.52 449	93.49 393	57.10 459	97.72 361	79.34 422	90.87 328	92.56 437

KD-MVS_self_test		85.95 406	84.95 401	88.96 430	89.55 453	79.11 448	95.13 368	96.42 316	85.91 385	84.07 424	90.48 438	70.03 403	94.82 447	80.04 414	72.94 458	92.94 430

FE-MVSNET2		86.36 399	84.68 407	91.39 392	87.67 466	86.47 337	96.21 301	96.41 317	87.87 342	79.31 451	89.64 446	65.29 441	95.58 439	82.42 393	77.28 443	92.14 448

pmmvs6		87.81 381	86.19 389	92.69 353	91.32 441	86.30 341	97.34 177	96.41 317	80.59 445	84.05 425	94.37 348	67.37 424	97.67 364	84.75 365	79.51 435	94.09 415

PMMVS		92.86 231	92.34 229	94.42 263	94.92 355	86.73 328	94.53 384	96.38 319	84.78 404	94.27 189	95.12 310	83.13 228	98.40 272	91.47 226	96.49 214	98.12 218

RPSCF		90.75 326	90.86 283	90.42 412	96.84 207	76.29 457	95.61 341	96.34 320	83.89 413	91.38 269	97.87 122	76.45 350	98.78 215	87.16 330	92.23 301	96.20 303

BP-MVS1		95.89 98	95.49 98	97.08 81	96.67 228	93.20 77	98.08 58	96.32 321	94.56 72	96.32 114	97.84 128	84.07 211	99.15 163	96.75 64	98.78 116	98.90 130

MSDG		91.42 294	90.24 314	94.96 230	97.15 178	88.91 264	93.69 420	96.32 321	85.72 388	86.93 392	96.47 238	80.24 294	98.98 192	80.57 411	95.05 251	96.98 282

blend_shiyan4		86.87 391	84.61 408	93.67 312	88.87 457	88.70 269	95.17 367	96.30 323	82.80 427	86.16 401	87.11 464	65.12 443	97.55 376	87.73 307	72.21 460	94.75 395

WBMVS		90.69 331	89.99 328	92.81 348	96.48 253	85.00 374	95.21 364	96.30 323	89.46 287	89.04 338	94.05 370	72.45 384	97.82 349	89.46 272	87.41 367	95.61 333

OurMVSNet-221017-0		90.51 336	90.19 319	91.44 390	93.41 413	81.25 419	96.98 215	96.28 325	91.68 196	86.55 397	96.30 246	74.20 372	97.98 323	88.96 288	87.40 368	95.09 367

MVP-Stereo		90.74 327	90.08 321	92.71 352	93.19 418	88.20 288	95.86 323	96.27 326	86.07 383	84.86 414	94.76 325	77.84 339	97.75 359	83.88 379	98.01 153	92.17 447
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 137	94.56 141	96.29 133	96.34 265	91.21 158	95.83 325	96.27 326	88.93 307	96.22 119	96.88 211	86.20 164	98.85 205	95.27 121	99.05 104	98.82 146

BH-untuned		92.94 226	92.62 218	93.92 298	97.22 172	86.16 347	96.40 282	96.25 328	90.06 268	89.79 312	96.17 254	83.19 225	98.35 280	87.19 328	97.27 180	97.24 276

CL-MVSNet_self_test		86.31 401	85.15 398	89.80 421	88.83 458	81.74 417	93.93 409	96.22 329	86.67 371	85.03 412	90.80 436	78.09 335	94.50 449	74.92 442	71.86 461	93.15 428

IS-MVSNet		94.90 139	94.52 145	96.05 148	97.67 147	90.56 189	98.44 26	96.22 329	93.21 127	93.99 199	97.74 142	85.55 181	98.45 269	89.98 258	97.86 157	99.14 88

FA-MVS(test-final)		93.52 199	92.92 203	95.31 209	96.77 221	88.54 276	94.82 376	96.21 331	89.61 281	94.20 192	95.25 304	83.24 223	99.14 166	90.01 257	96.16 221	98.25 206

GA-MVS		91.38 296	90.31 309	94.59 249	94.65 369	87.62 305	94.34 394	96.19 332	90.73 240	90.35 292	93.83 376	71.84 387	97.96 330	87.22 327	93.61 286	98.21 209

LuminaMVS		94.89 140	94.35 153	96.53 105	95.48 314	92.80 91	96.88 227	96.18 333	92.85 152	95.92 132	96.87 213	81.44 269	98.83 208	96.43 77	97.10 187	97.94 235

IterMVS-SCA-FT		90.31 339	89.81 335	91.82 379	95.52 312	84.20 386	94.30 397	96.15 334	90.61 250	87.39 378	94.27 357	75.80 356	96.44 422	87.34 324	86.88 374	94.82 386

IterMVS		90.15 347	89.67 341	91.61 386	95.48 314	83.72 392	94.33 395	96.12 335	89.99 269	87.31 381	94.15 365	75.78 358	96.27 426	86.97 333	86.89 373	94.83 383
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 236	91.51 260	96.52 107	98.77 62	90.99 170	97.38 174	96.08 336	82.38 430	89.29 330	97.87 122	83.77 214	99.69 73	81.37 404	96.69 204	98.89 136

pmmvs4		90.93 321	89.85 333	94.17 275	93.34 415	90.79 181	94.60 381	96.02 337	84.62 405	87.45 375	95.15 307	81.88 263	97.45 388	87.70 312	87.87 360	94.27 412

ppachtmachnet_test		88.35 376	87.29 375	91.53 387	92.45 434	83.57 395	93.75 416	95.97 338	84.28 408	85.32 411	94.18 363	79.00 322	96.93 410	75.71 438	84.99 396	94.10 413

Anonymous20240521		86.42 398	85.44 394	89.34 428	90.33 446	79.79 439	96.73 248	95.92 339	83.71 418	83.25 430	91.36 433	63.92 445	96.01 427	78.39 426	85.36 387	92.22 445

ITE_SJBPF				92.43 357	95.34 326	85.37 367		95.92 339	91.47 205	87.75 371	96.39 243	71.00 393	97.96 330	82.36 394	89.86 338	93.97 418

test_fmvs2		89.77 358	89.93 330	89.31 429	93.68 400	76.37 456	97.64 133	95.90 341	89.84 275	91.49 267	96.26 250	58.77 455	97.10 402	94.65 150	91.13 321	94.46 403

USDC		88.94 367	87.83 372	92.27 364	94.66 368	84.96 376	93.86 412	95.90 341	87.34 360	83.40 428	95.56 289	67.43 423	98.19 293	82.64 392	89.67 340	93.66 421

COLMAP_ROB	87.81 15	90.40 338	89.28 351	93.79 303	97.95 129	87.13 319	96.92 221	95.89 343	82.83 426	86.88 394	97.18 189	73.77 376	99.29 146	78.44 425	93.62 285	94.95 372
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 187	93.08 196	96.02 151	97.88 135	89.96 216	97.72 118	95.85 344	92.43 167	95.86 134	98.44 64	68.42 419	99.39 134	96.31 79	94.85 252	98.71 161

VDDNet		93.05 220	92.07 235	96.02 151	96.84 207	90.39 197	98.08 58	95.85 344	86.22 381	95.79 137	98.46 62	67.59 422	99.19 154	94.92 132	94.85 252	98.47 183

mvsmamba		94.57 154	94.14 158	95.87 162	97.03 189	89.93 217	97.84 95	95.85 344	91.34 211	94.79 174	96.80 214	80.67 284	98.81 211	94.85 135	98.12 148	98.85 142

Vis-MVSNet (Re-imp)		94.15 167	93.88 164	94.95 231	97.61 155	87.92 297	98.10 56	95.80 347	92.22 175	93.02 228	97.45 169	84.53 201	97.91 342	88.24 298	97.97 154	99.02 103

MM		97.29 31	96.98 42	98.23 12	98.01 123	95.03 27	98.07 60	95.76 348	97.78 1	97.52 62	98.80 38	88.09 119	99.86 9	99.44 2	99.37 67	99.80 1

KD-MVS_2432*1600		84.81 416	82.64 419	91.31 393	91.07 443	85.34 368	91.22 450	95.75 349	85.56 390	83.09 431	90.21 441	67.21 425	95.89 429	77.18 432	62.48 475	92.69 433

miper_refine_blended		84.81 416	82.64 419	91.31 393	91.07 443	85.34 368	91.22 450	95.75 349	85.56 390	83.09 431	90.21 441	67.21 425	95.89 429	77.18 432	62.48 475	92.69 433

FE-MVS		92.05 264	91.05 276	95.08 218	96.83 209	87.93 296	93.91 411	95.70 351	86.30 378	94.15 196	94.97 313	76.59 348	99.21 152	84.10 373	96.86 195	98.09 225

tpm cat1		88.36 375	87.21 378	91.81 380	95.13 345	80.55 428	92.58 441	95.70 351	74.97 461	87.45 375	91.96 426	78.01 338	98.17 295	80.39 413	88.74 352	96.72 292

our_test_3		88.78 371	87.98 371	91.20 397	92.45 434	82.53 406	93.61 424	95.69 353	85.77 387	84.88 413	93.71 381	79.99 299	96.78 418	79.47 419	86.24 376	94.28 411

BH-w/o		92.14 261	91.75 249	93.31 328	96.99 194	85.73 357	95.67 335	95.69 353	88.73 317	89.26 332	94.82 323	82.97 234	98.07 311	85.26 360	96.32 220	96.13 310

CR-MVSNet		90.82 324	89.77 337	93.95 292	94.45 377	87.19 316	90.23 458	95.68 355	86.89 368	92.40 238	92.36 418	80.91 278	97.05 405	81.09 408	93.95 278	97.60 259

Patchmtry		88.64 373	87.25 376	92.78 350	94.09 387	86.64 329	89.82 462	95.68 355	80.81 442	87.63 373	92.36 418	80.91 278	97.03 406	78.86 423	85.12 392	94.67 398

testing91		91.90 269	91.02 277	94.53 257	96.54 244	86.55 335	95.86 323	95.64 357	91.77 193	91.89 257	93.47 395	69.94 404	98.86 203	90.23 256	93.86 280	98.18 211

BH-RMVSNet		92.72 238	91.97 241	94.97 229	97.16 176	87.99 295	96.15 307	95.60 358	90.62 249	91.87 258	97.15 192	78.41 329	98.57 260	83.16 382	97.60 164	98.36 195

PVSNet_0	82.17 19	85.46 411	83.64 414	90.92 401	95.27 333	79.49 444	90.55 456	95.60 358	83.76 417	83.00 433	89.95 443	71.09 392	97.97 326	82.75 390	60.79 477	95.31 353

guyue		95.17 127	94.96 123	95.82 168	96.97 196	89.65 227	97.56 144	95.58 360	94.82 57	95.72 139	97.42 173	82.90 236	98.84 207	96.71 67	96.93 192	98.96 114

SCA		91.84 271	91.18 273	93.83 300	95.59 308	84.95 377	94.72 378	95.58 360	90.82 236	92.25 246	93.69 383	75.80 356	98.10 302	86.20 342	95.98 223	98.45 185

MonoMVSNet		91.92 267	91.77 247	92.37 358	92.94 422	83.11 400	97.09 204	95.55 362	92.91 148	90.85 284	94.55 336	81.27 273	96.52 421	93.01 195	87.76 361	97.47 265

usedtu_blend_shiyan5		87.06 389	84.84 403	93.69 309	88.54 462	88.70 269	95.83 325	95.54 363	78.74 452	85.92 404	86.89 466	73.03 380	97.55 376	87.73 307	71.36 462	94.83 383

AllTest		90.23 343	88.98 357	93.98 288	97.94 130	86.64 329	96.51 271	95.54 363	85.38 392	85.49 408	96.77 216	70.28 399	99.15 163	80.02 415	92.87 290	96.15 308

TestCases				93.98 288	97.94 130	86.64 329		95.54 363	85.38 392	85.49 408	96.77 216	70.28 399	99.15 163	80.02 415	92.87 290	96.15 308

mmtdpeth		89.70 360	88.96 358	91.90 375	95.84 300	84.42 382	97.46 164	95.53 366	90.27 262	94.46 185	90.50 437	69.74 408	98.95 193	97.39 53	69.48 466	92.34 441

tpmvs		89.83 357	89.15 355	91.89 376	94.92 355	80.30 432	93.11 433	95.46 367	86.28 379	88.08 365	92.65 408	80.44 290	98.52 264	81.47 400	89.92 337	96.84 288

pmmvs5		89.86 356	88.87 361	92.82 347	92.86 424	86.23 343	96.26 296	95.39 368	84.24 409	87.12 383	94.51 339	74.27 371	97.36 395	87.61 319	87.57 363	94.86 381

PatchmatchNet		91.91 268	91.35 262	93.59 316	95.38 321	84.11 387	93.15 432	95.39 368	89.54 283	92.10 251	93.68 385	82.82 239	98.13 297	84.81 364	95.32 244	98.52 175
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 293	91.32 264	91.79 381	95.15 343	79.20 447	93.42 427	95.37 370	88.55 322	93.49 217	93.67 386	82.49 248	98.27 286	90.41 251	89.34 343	97.90 237

Anonymous20231206		87.09 388	86.14 390	89.93 420	91.22 442	80.35 430	96.11 308	95.35 371	83.57 420	84.16 420	93.02 403	73.54 378	95.61 437	72.16 455	86.14 378	93.84 420

MIMVSNet1		84.93 414	83.05 416	90.56 410	89.56 452	84.84 379	95.40 350	95.35 371	83.91 412	80.38 445	92.21 423	57.23 458	93.34 462	70.69 461	82.75 423	93.50 423

TDRefinement		86.53 394	84.76 405	91.85 377	82.23 478	84.25 384	96.38 284	95.35 371	84.97 401	84.09 423	94.94 315	65.76 438	98.34 283	84.60 368	74.52 454	92.97 429

TR-MVS		91.48 292	90.59 300	94.16 278	96.40 259	87.33 309	95.67 335	95.34 374	87.68 352	91.46 268	95.52 292	76.77 347	98.35 280	82.85 387	93.61 286	96.79 290

EPNet_dtu		91.71 274	91.28 267	92.99 340	93.76 397	83.71 393	96.69 254	95.28 375	93.15 134	87.02 388	95.95 265	83.37 222	97.38 394	79.46 420	96.84 196	97.88 239
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 385	85.79 392	91.78 382	94.80 362	87.28 311	95.49 347	95.28 375	84.09 411	83.85 427	91.82 427	62.95 448	94.17 453	78.48 424	85.34 388	93.91 419

MDTV_nov1_ep13			90.76 289		95.22 337	80.33 431	93.03 435	95.28 375	88.14 335	92.84 235	93.83 376	81.34 270	98.08 307	82.86 385	94.34 263

LF4IMVS		87.94 379	87.25 376	89.98 418	92.38 436	80.05 438	94.38 392	95.25 378	87.59 354	84.34 417	94.74 327	64.31 444	97.66 367	84.83 363	87.45 364	92.23 444

TransMVSNet (Re)		88.94 367	87.56 373	93.08 338	94.35 380	88.45 280	97.73 115	95.23 379	87.47 356	84.26 419	95.29 299	79.86 302	97.33 396	79.44 421	74.44 455	93.45 425

test20.03		86.14 404	85.40 396	88.35 431	90.12 447	80.06 437	95.90 322	95.20 380	88.59 318	81.29 440	93.62 388	71.43 390	92.65 466	71.26 459	81.17 428	92.34 441

new-patchmatchnet		83.18 423	81.87 426	87.11 439	86.88 469	75.99 458	93.70 418	95.18 381	85.02 400	77.30 458	88.40 455	65.99 436	93.88 458	74.19 447	70.18 464	91.47 456

MDA-MVSNet_test_wron		85.87 408	84.23 411	90.80 407	92.38 436	82.57 405	93.17 430	95.15 382	82.15 431	67.65 470	92.33 421	78.20 331	95.51 441	77.33 429	79.74 432	94.31 410

YYNet1		85.87 408	84.23 411	90.78 408	92.38 436	82.46 410	93.17 430	95.14 383	82.12 432	67.69 468	92.36 418	78.16 334	95.50 442	77.31 430	79.73 433	94.39 406

Baseline_NR-MVSNet		91.20 308	90.62 298	92.95 342	93.83 395	88.03 294	97.01 211	95.12 384	88.42 326	89.70 315	95.13 309	83.47 219	97.44 389	89.66 268	83.24 418	93.37 426

thres200		92.23 257	91.39 261	94.75 244	97.61 155	89.03 260	96.60 266	95.09 385	92.08 184	93.28 223	94.00 372	78.39 330	99.04 189	81.26 407	94.18 269	96.19 304

ADS-MVSNet		89.89 353	88.68 363	93.53 320	95.86 295	84.89 378	90.93 453	95.07 386	83.23 424	91.28 277	91.81 428	79.01 320	97.85 345	79.52 417	91.39 317	97.84 244

pmmvs-eth3d		86.22 402	84.45 409	91.53 387	88.34 463	87.25 313	94.47 387	95.01 387	83.47 421	79.51 450	89.61 447	69.75 407	95.71 434	83.13 383	76.73 447	91.64 450

Anonymous202405211		92.07 263	90.83 287	95.76 177	98.19 109	88.75 267	97.58 140	95.00 388	86.00 384	93.64 209	97.45 169	66.24 434	99.53 112	90.68 245	92.71 295	99.01 106

MDA-MVSNet-bldmvs		85.00 413	82.95 418	91.17 399	93.13 420	83.33 396	94.56 383	95.00 388	84.57 406	65.13 474	92.65 408	70.45 398	95.85 431	73.57 450	77.49 442	94.33 408

ambc				86.56 442	83.60 475	70.00 469	85.69 474	94.97 390		80.60 444	88.45 454	37.42 476	96.84 415	82.69 391	75.44 452	92.86 431

testgi		87.97 378	87.21 378	90.24 415	92.86 424	80.76 423	96.67 257	94.97 390	91.74 194	85.52 407	95.83 271	62.66 450	94.47 451	76.25 436	88.36 356	95.48 336

myMVS_eth3d28		91.52 289	90.97 279	93.17 334	96.91 199	83.24 398	95.61 341	94.96 392	92.24 174	91.98 254	93.28 400	69.31 409	98.40 272	88.71 293	95.68 233	97.88 239

dp		88.90 369	88.26 369	90.81 405	94.58 373	76.62 455	92.85 438	94.93 393	85.12 398	90.07 306	93.07 402	75.81 355	98.12 300	80.53 412	87.42 366	97.71 251

test_fmvs3		83.21 422	83.02 417	83.78 446	86.77 470	68.34 472	96.76 246	94.91 394	86.49 374	84.14 422	89.48 448	36.04 477	91.73 468	91.86 216	80.77 430	91.26 458

test_0402		86.46 397	84.79 404	91.45 389	95.02 349	85.55 359	96.29 295	94.89 395	80.90 439	82.21 436	93.97 374	68.21 420	97.29 398	62.98 469	88.68 353	91.51 453

tfpn200view9		92.38 247	91.52 258	94.95 231	97.85 136	89.29 249	97.41 167	94.88 396	92.19 180	93.27 224	94.46 344	78.17 332	99.08 177	81.40 401	94.08 273	96.48 297

CVMVSNet		91.23 306	91.75 249	89.67 422	95.77 301	74.69 459	96.44 272	94.88 396	85.81 386	92.18 247	97.64 155	79.07 315	95.58 439	88.06 301	95.86 228	98.74 158

thres400		92.42 245	91.52 258	95.12 217	97.85 136	89.29 249	97.41 167	94.88 396	92.19 180	93.27 224	94.46 344	78.17 332	99.08 177	81.40 401	94.08 273	96.98 282

tt0320		85.39 412	83.12 415	92.19 368	93.44 412	85.79 355	96.19 304	94.87 399	71.19 468	82.92 434	91.76 430	58.43 456	96.81 416	81.03 409	78.26 441	93.98 417

EPNet		95.20 123	94.56 141	97.14 75	92.80 426	92.68 97	97.85 94	94.87 399	96.64 9	92.46 237	97.80 136	86.23 161	99.65 79	93.72 174	98.62 124	99.10 95
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 280	90.72 294	94.32 268	96.48 253	86.11 352	95.81 327	94.76 401	91.55 198	91.75 262	93.44 396	68.55 417	98.82 209	90.43 250	93.69 282	98.04 229

sc_t1		86.48 396	84.10 413	93.63 313	93.45 411	85.76 356	96.79 240	94.71 402	73.06 466	86.45 398	94.35 349	55.13 463	97.95 334	84.38 371	78.55 440	97.18 278

SixPastTwentyTwo		89.15 365	88.54 365	90.98 400	93.49 408	80.28 434	96.70 252	94.70 403	90.78 237	84.15 421	95.57 288	71.78 388	97.71 362	84.63 367	85.07 393	94.94 374

thres100view900		92.43 244	91.58 255	94.98 227	97.92 132	89.37 245	97.71 120	94.66 404	92.20 178	93.31 222	94.90 318	78.06 336	99.08 177	81.40 401	94.08 273	96.48 297

thres600view7		92.49 242	91.60 254	95.18 213	97.91 133	89.47 239	97.65 129	94.66 404	92.18 182	93.33 221	94.91 317	78.06 336	99.10 171	81.61 397	94.06 277	96.98 282

PatchT		88.87 370	87.42 374	93.22 332	94.08 388	85.10 372	89.51 463	94.64 406	81.92 433	92.36 241	88.15 458	80.05 298	97.01 408	72.43 454	93.65 284	97.54 262

baseline1		92.82 234	91.90 244	95.55 193	97.20 174	90.77 182	97.19 196	94.58 407	92.20 178	92.36 241	96.34 245	84.16 209	98.21 290	89.20 283	83.90 413	97.68 253

AstraMVS		94.82 146	94.64 137	95.34 208	96.36 264	88.09 293	97.58 140	94.56 408	94.98 46	95.70 142	97.92 114	81.93 262	98.93 196	96.87 61	95.88 226	98.99 110

UBG		91.55 286	90.76 289	93.94 294	96.52 249	85.06 373	95.22 362	94.54 409	90.47 258	91.98 254	92.71 407	72.02 385	98.74 231	88.10 300	95.26 246	98.01 231

Gipuma		67.86 443	65.41 445	75.18 459	92.66 429	73.45 463	66.50 481	94.52 410	53.33 479	57.80 480	66.07 480	30.81 479	89.20 472	48.15 478	78.88 439	62.90 480
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 277	90.75 291	94.47 259	96.53 246	86.56 334	95.76 331	94.51 411	91.10 229	91.24 279	93.59 390	68.59 416	98.86 203	91.10 233	94.29 265	98.00 232

CostFormer		91.18 311	90.70 295	92.62 355	94.84 360	81.76 416	94.09 404	94.43 412	84.15 410	92.72 236	93.77 380	79.43 309	98.20 291	90.70 244	92.18 304	97.90 237

tpm2		89.96 350	89.21 353	92.23 367	94.91 357	81.25 419	93.78 415	94.42 413	80.62 444	91.56 265	93.44 396	76.44 351	97.94 336	85.60 354	92.08 308	97.49 263

testing3-2		92.10 262	92.05 236	92.27 364	97.71 145	79.56 441	97.42 166	94.41 414	93.53 113	93.22 226	95.49 293	69.16 411	99.11 169	93.25 185	94.22 267	98.13 216

MGCNet		96.74 64	96.31 81	98.02 20	96.87 203	94.65 31	97.58 140	94.39 415	96.47 12	97.16 74	98.39 68	87.53 136	99.87 7	98.97 20	99.41 59	99.55 43

JIA-IIPM		88.26 377	87.04 381	91.91 374	93.52 406	81.42 418	89.38 464	94.38 416	80.84 441	90.93 283	80.74 472	79.22 312	97.92 339	82.76 389	91.62 312	96.38 300

dmvs_re		90.21 344	89.50 346	92.35 359	95.47 318	85.15 370	95.70 334	94.37 417	90.94 235	88.42 352	93.57 391	74.63 368	95.67 436	82.80 388	89.57 341	96.22 302

Patchmatch-test		89.42 363	87.99 370	93.70 308	95.27 333	85.11 371	88.98 465	94.37 417	81.11 438	87.10 386	93.69 383	82.28 252	97.50 384	74.37 445	94.76 256	98.48 182

LCM-MVSNet		72.55 436	69.39 440	82.03 448	70.81 488	65.42 477	90.12 460	94.36 419	55.02 478	65.88 472	81.72 471	24.16 485	89.96 469	74.32 446	68.10 469	90.71 461

ADS-MVSNet2		89.45 362	88.59 364	92.03 371	95.86 295	82.26 412	90.93 453	94.32 420	83.23 424	91.28 277	91.81 428	79.01 320	95.99 428	79.52 417	91.39 317	97.84 244

mvs5depth		86.53 394	85.08 399	90.87 402	88.74 460	82.52 407	91.91 446	94.23 421	86.35 377	87.11 385	93.70 382	66.52 430	97.76 357	81.37 404	75.80 449	92.31 443

EU-MVSNet		88.72 372	88.90 360	88.20 433	93.15 419	74.21 461	96.63 263	94.22 422	85.18 396	87.32 380	95.97 263	76.16 353	94.98 446	85.27 359	86.17 377	95.41 343

tt0320-xc		84.83 415	82.33 423	92.31 362	93.66 401	86.20 345	96.17 306	94.06 423	71.26 467	82.04 438	92.22 422	55.07 464	96.72 419	81.49 399	75.04 453	94.02 416

MIMVSNet		88.50 374	86.76 384	93.72 307	94.84 360	87.77 303	91.39 448	94.05 424	86.41 376	87.99 367	92.59 411	63.27 446	95.82 433	77.44 428	92.84 292	97.57 261

OpenMVS_ROB	81.14 20	84.42 418	82.28 424	90.83 403	90.06 448	84.05 389	95.73 333	94.04 425	73.89 464	80.17 448	91.53 432	59.15 454	97.64 368	66.92 467	89.05 346	90.80 460

TinyColmap		86.82 392	85.35 397	91.21 395	94.91 357	82.99 402	93.94 408	94.02 426	83.58 419	81.56 439	94.68 329	62.34 451	98.13 297	75.78 437	87.35 369	92.52 439

ETVMVS		90.52 335	89.14 356	94.67 247	96.81 213	87.85 301	95.91 321	93.97 427	89.71 278	92.34 244	92.48 413	65.41 440	97.96 330	81.37 404	94.27 266	98.21 209

IB-MVS	87.33 17	89.91 351	88.28 368	94.79 241	95.26 336	87.70 304	95.12 369	93.95 428	89.35 291	87.03 387	92.49 412	70.74 396	99.19 154	89.18 284	81.37 427	97.49 263
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		87.13 387	87.02 382	87.47 437	95.16 340	73.21 465	95.00 371	93.93 429	88.55 322	86.96 389	91.99 424	75.90 354	94.00 455	61.59 471	94.11 270	95.20 361

myMVS_eth3d		87.18 386	86.38 387	89.58 423	95.16 340	79.53 442	95.00 371	93.93 429	88.55 322	86.96 389	91.99 424	56.23 461	94.00 455	75.47 441	94.11 270	95.20 361

testing222		90.31 339	88.96 358	94.35 265	96.54 244	87.29 310	95.50 346	93.84 431	90.97 232	91.75 262	92.96 404	62.18 452	98.00 321	82.86 385	94.08 273	97.76 249

test_f		80.57 429	79.62 431	83.41 447	83.38 476	67.80 474	93.57 425	93.72 432	80.80 443	77.91 457	87.63 461	33.40 478	92.08 467	87.14 331	79.04 438	90.34 462

LCM-MVSNet-Re		92.50 240	92.52 224	92.44 356	96.82 211	81.89 415	96.92 221	93.71 433	92.41 168	84.30 418	94.60 334	85.08 190	97.03 406	91.51 224	97.36 173	98.40 191

tpm		90.25 342	89.74 340	91.76 384	93.92 391	79.73 440	93.98 405	93.54 434	88.28 329	91.99 253	93.25 401	77.51 342	97.44 389	87.30 326	87.94 359	98.12 218

ET-MVSNet_ETH3D		91.49 291	90.11 320	95.63 187	96.40 259	91.57 142	95.34 353	93.48 435	90.60 252	75.58 460	95.49 293	80.08 297	96.79 417	94.25 162	89.76 339	98.52 175

LFMVS		93.60 194	92.63 217	96.52 107	98.13 115	91.27 155	97.94 81	93.39 436	90.57 254	96.29 116	98.31 81	69.00 412	99.16 161	94.18 163	95.87 227	99.12 92

MVStest1		82.38 426	80.04 430	89.37 426	87.63 467	82.83 403	95.03 370	93.37 437	73.90 463	73.50 465	94.35 349	62.89 449	93.25 464	73.80 448	65.92 472	92.04 449

FE-MVSNET		83.85 419	81.97 425	89.51 424	87.19 468	83.19 399	95.21 364	93.17 438	83.45 422	78.90 453	89.05 451	65.46 439	93.84 459	69.71 463	75.56 451	91.51 453

Patchmatch-RL test		87.38 384	86.24 388	90.81 405	88.74 460	78.40 451	88.12 472	93.17 438	87.11 365	82.17 437	89.29 449	81.95 260	95.60 438	88.64 295	77.02 444	98.41 190

ttmdpeth		85.91 407	84.76 405	89.36 427	89.14 454	80.25 435	95.66 338	93.16 440	83.77 416	83.39 429	95.26 303	66.24 434	95.26 445	80.65 410	75.57 450	92.57 436

test-LLR		91.42 294	91.19 272	92.12 369	94.59 371	80.66 425	94.29 398	92.98 441	91.11 227	90.76 286	92.37 415	79.02 318	98.07 311	88.81 290	96.74 201	97.63 254

test-mter		90.19 346	89.54 345	92.12 369	94.59 371	80.66 425	94.29 398	92.98 441	87.68 352	90.76 286	92.37 415	67.67 421	98.07 311	88.81 290	96.74 201	97.63 254

WB-MVSnew		89.88 354	89.56 344	90.82 404	94.57 374	83.06 401	95.65 339	92.85 443	87.86 343	90.83 285	94.10 366	79.66 306	96.88 413	76.34 435	94.19 268	92.54 438

testing3		87.67 382	86.88 383	90.05 417	96.14 282	80.71 424	97.10 203	92.85 443	90.15 266	87.54 374	94.55 336	55.70 462	94.10 454	73.77 449	94.10 272	95.35 350

test_method		66.11 444	64.89 446	69.79 462	72.62 486	35.23 494	65.19 482	92.83 445	20.35 484	65.20 473	88.08 459	43.14 474	82.70 479	73.12 452	63.46 474	91.45 457

test0.0.03 1		89.37 364	88.70 362	91.41 391	92.47 433	85.63 358	95.22 362	92.70 446	91.11 227	86.91 393	93.65 387	79.02 318	93.19 465	78.00 427	89.18 344	95.41 343

new_pmnet		82.89 424	81.12 429	88.18 434	89.63 451	80.18 436	91.77 447	92.57 447	76.79 459	75.56 461	88.23 457	61.22 453	94.48 450	71.43 457	82.92 421	89.87 463

mvsany_test1		93.93 183	93.98 162	93.78 304	94.94 354	86.80 325	94.62 380	92.55 448	88.77 316	96.85 84	98.49 58	88.98 101	98.08 307	95.03 127	95.62 235	96.46 299

thisisatest0515		92.29 253	91.30 266	95.25 211	96.60 233	88.90 265	94.36 393	92.32 449	87.92 339	93.43 219	94.57 335	77.28 343	99.00 190	89.42 274	95.86 228	97.86 243

thisisatest0530		93.03 221	92.21 233	95.49 200	97.07 181	89.11 258	97.49 161	92.19 450	90.16 265	94.09 197	96.41 241	76.43 352	99.05 186	90.38 252	95.68 233	98.31 203

tttt0517		92.96 224	92.33 230	94.87 234	97.11 179	87.16 318	97.97 77	92.09 451	90.63 248	93.88 203	97.01 205	76.50 349	99.06 183	90.29 255	95.45 242	98.38 193

K. test v3		87.64 383	86.75 385	90.32 414	93.02 421	79.48 445	96.61 264	92.08 452	90.66 246	80.25 447	94.09 368	67.21 425	96.65 420	85.96 350	80.83 429	94.83 383

TESTMET0.1,1		90.06 348	89.42 348	91.97 372	94.41 379	80.62 427	94.29 398	91.97 453	87.28 362	90.44 290	92.47 414	68.79 413	97.67 364	88.50 297	96.60 208	97.61 258

PM-MVS		83.48 421	81.86 427	88.31 432	87.83 465	77.59 453	93.43 426	91.75 454	86.91 367	80.63 443	89.91 444	44.42 473	95.84 432	85.17 362	76.73 447	91.50 455

baseline2		91.63 279	90.86 283	93.94 294	94.33 381	86.32 340	95.92 320	91.64 455	89.37 290	86.94 391	94.69 328	81.62 267	98.69 241	88.64 295	94.57 261	96.81 289

APD_test1		79.31 431	77.70 434	84.14 445	89.11 456	69.07 471	92.36 445	91.50 456	69.07 470	73.87 463	92.63 410	39.93 475	94.32 452	70.54 462	80.25 431	89.02 465

FPMVS		71.27 437	69.85 439	75.50 458	74.64 483	59.03 483	91.30 449	91.50 456	58.80 475	57.92 479	88.28 456	29.98 481	85.53 478	53.43 476	82.84 422	81.95 471

door								91.13 458

door-mid								91.06 459

EGC-MVSNET		68.77 442	63.01 448	86.07 444	92.49 432	82.24 413	93.96 407	90.96 460	0.71 489	2.62 490	90.89 435	53.66 465	93.46 460	57.25 474	84.55 403	82.51 470

mvsany_test3		83.59 420	82.44 422	87.03 440	83.80 473	73.82 462	93.70 418	90.92 461	86.42 375	82.51 435	90.26 440	46.76 472	95.71 434	90.82 239	76.76 446	91.57 452

pmmvs3		79.97 430	77.50 435	87.39 438	82.80 477	79.38 446	92.70 440	90.75 462	70.69 469	78.66 454	87.47 463	51.34 468	93.40 461	73.39 451	69.65 465	89.38 464

UWE-MVS		89.91 351	89.48 347	91.21 395	95.88 294	78.23 452	94.91 374	90.26 463	89.11 297	92.35 243	94.52 338	68.76 414	97.96 330	83.95 377	95.59 236	97.42 267

DSMNet-mixed		86.34 400	86.12 391	87.00 441	89.88 450	70.43 467	94.93 373	90.08 464	77.97 456	85.42 410	92.78 406	74.44 370	93.96 457	74.43 444	95.14 247	96.62 293

MVS-HIRNet		82.47 425	81.21 428	86.26 443	95.38 321	69.21 470	88.96 466	89.49 465	66.28 472	80.79 442	74.08 477	68.48 418	97.39 393	71.93 456	95.47 241	92.18 446

WB-MVS		76.77 433	76.63 436	77.18 453	85.32 471	56.82 485	94.53 384	89.39 466	82.66 429	71.35 466	89.18 450	75.03 363	88.88 473	35.42 482	66.79 470	85.84 467

test1111		93.19 213	92.82 207	94.30 271	97.58 161	84.56 381	98.21 47	89.02 467	93.53 113	94.58 179	98.21 88	72.69 381	99.05 186	93.06 191	98.48 131	99.28 77

SSC-MVS		76.05 434	75.83 437	76.72 457	84.77 472	56.22 486	94.32 396	88.96 468	81.82 435	70.52 467	88.91 452	74.79 367	88.71 474	33.69 483	64.71 473	85.23 468

ECVR-MVS		93.19 213	92.73 213	94.57 254	97.66 149	85.41 364	98.21 47	88.23 469	93.43 120	94.70 176	98.21 88	72.57 382	99.07 181	93.05 192	98.49 129	99.25 80

EPMVS		90.70 329	89.81 335	93.37 326	94.73 366	84.21 385	93.67 421	88.02 470	89.50 285	92.38 240	93.49 393	77.82 340	97.78 354	86.03 348	92.68 296	98.11 224

ANet_high		63.94 446	59.58 449	77.02 454	61.24 490	66.06 475	85.66 475	87.93 471	78.53 454	42.94 482	71.04 479	25.42 484	80.71 481	52.60 477	30.83 483	84.28 469

PMMVS2		70.19 438	66.92 442	80.01 449	76.35 482	65.67 476	86.22 473	87.58 472	64.83 474	62.38 475	80.29 474	26.78 483	88.49 476	63.79 468	54.07 479	85.88 466

lessismore_v0				90.45 411	91.96 439	79.09 449		87.19 473		80.32 446	94.39 346	66.31 433	97.55 376	84.00 376	76.84 445	94.70 397

PMVS	53.92 22	58.58 447	55.40 450	68.12 463	51.00 491	48.64 488	78.86 478	87.10 474	46.77 480	35.84 486	74.28 476	8.76 489	86.34 477	42.07 480	73.91 456	69.38 477
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 393	86.41 386	88.02 435	92.87 423	74.60 460	95.38 352	86.70 475	88.17 332	87.28 382	94.67 331	70.83 395	93.30 463	67.45 465	94.31 264	96.17 305

test_vis1_rt		86.16 403	85.06 400	89.46 425	93.47 410	80.46 429	96.41 278	86.61 476	85.22 395	79.15 452	88.64 453	52.41 467	97.06 404	93.08 190	90.57 330	90.87 459

testf1		69.31 440	66.76 443	76.94 455	78.61 480	61.93 479	88.27 470	86.11 477	55.62 476	59.69 476	85.31 468	20.19 487	89.32 470	57.62 472	69.44 467	79.58 472

APD_test2		69.31 440	66.76 443	76.94 455	78.61 480	61.93 479	88.27 470	86.11 477	55.62 476	59.69 476	85.31 468	20.19 487	89.32 470	57.62 472	69.44 467	79.58 472

gg-mvs-nofinetune		87.82 380	85.61 393	94.44 261	94.46 376	89.27 252	91.21 452	84.61 479	80.88 440	89.89 310	74.98 475	71.50 389	97.53 381	85.75 353	97.21 182	96.51 295

dmvs_testset		81.38 428	82.60 421	77.73 452	91.74 440	51.49 487	93.03 435	84.21 480	89.07 298	78.28 456	91.25 434	76.97 345	88.53 475	56.57 475	82.24 424	93.16 427

GG-mvs-BLEND				93.62 314	93.69 399	89.20 254	92.39 444	83.33 481		87.98 368	89.84 445	71.00 393	96.87 414	82.08 396	95.40 243	94.80 389

MTMP							97.86 91	82.03 482

DeepMVS_CX				74.68 460	90.84 445	64.34 478		81.61 483	65.34 473	67.47 471	88.01 460	48.60 471	80.13 482	62.33 470	73.68 457	79.58 472

E-PMN		53.28 448	52.56 452	55.43 466	74.43 484	47.13 489	83.63 477	76.30 484	42.23 481	42.59 483	62.22 482	28.57 482	74.40 483	31.53 484	31.51 482	44.78 481

test2506		91.60 281	90.78 288	94.04 284	97.66 149	83.81 390	98.27 37	75.53 485	93.43 120	95.23 159	98.21 88	67.21 425	99.07 181	93.01 195	98.49 129	99.25 80

EMVS		52.08 450	51.31 453	54.39 467	72.62 486	45.39 491	83.84 476	75.51 486	41.13 482	40.77 484	59.65 483	30.08 480	73.60 484	28.31 486	29.90 484	44.18 482

test_vis3_rt		72.73 435	70.55 438	79.27 450	80.02 479	68.13 473	93.92 410	74.30 487	76.90 458	58.99 478	73.58 478	20.29 486	95.37 443	84.16 372	72.80 459	74.31 475

MVE	50.73 23	53.25 449	48.81 454	66.58 465	65.34 489	57.50 484	72.49 480	70.94 488	40.15 483	39.28 485	63.51 481	6.89 491	73.48 485	38.29 481	42.38 481	68.76 479
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 451	53.82 451	46.29 468	33.73 492	45.30 492	78.32 479	67.24 489	18.02 485	50.93 481	87.05 465	52.99 466	53.11 487	70.76 460	25.29 485	40.46 483

kuosan		65.27 445	64.66 447	67.11 464	83.80 473	61.32 482	88.53 469	60.77 490	68.22 471	67.67 469	80.52 473	49.12 470	70.76 486	29.67 485	53.64 480	69.26 478

dongtai		69.99 439	69.33 441	71.98 461	88.78 459	61.64 481	89.86 461	59.93 491	75.67 460	74.96 462	85.45 467	50.19 469	81.66 480	43.86 479	55.27 478	72.63 476

N_pmnet		78.73 432	78.71 433	78.79 451	92.80 426	46.50 490	94.14 402	43.71 492	78.61 453	80.83 441	91.66 431	74.94 366	96.36 424	67.24 466	84.45 405	93.50 423

wuyk23d		25.11 452	24.57 456	26.74 469	73.98 485	39.89 493	57.88 483	9.80 493	12.27 486	10.39 487	6.97 489	7.03 490	36.44 488	25.43 487	17.39 486	3.89 486

testmvs		13.36 454	16.33 457	4.48 471	5.04 493	2.26 496	93.18 429	3.28 494	2.70 487	8.24 488	21.66 485	2.29 493	2.19 489	7.58 488	2.96 487	9.00 485

test123		13.04 455	15.66 458	5.18 470	4.51 494	3.45 495	92.50 443	1.81 495	2.50 488	7.58 489	20.15 486	3.67 492	2.18 490	7.13 489	1.07 488	9.90 484

mmdepth		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

monomultidepth		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

test_blank		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uanet_test		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

DCPMVS		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

pcd_1.5k_mvsjas		7.39 457	9.85 460	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	88.65 109	0.00 491	0.00 490	0.00 489	0.00 487

sosnet-low-res		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

sosnet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uncertanet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

Regformer		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

n2								0.00 496

nn								0.00 496

ab-mvs-re		8.06 456	10.74 459	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	96.69 222	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uanet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

TestfortrainingZip							98.69 11

WAC-MVS						79.53 442								75.56 440

PC_three_1452									90.77 238	98.89 26	98.28 86	96.24 1	98.35 280	95.76 106	99.58 23	99.59 32

eth-test2					0.00 495

eth-test					0.00 495

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

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

GSMVS																98.45 185

test_part2					99.28 30	95.74 9				98.10 48

sam_mvs1												82.76 240				98.45 185

sam_mvs												81.94 261

test_post1							92.81 439				16.58 488	80.53 288	97.68 363	86.20 342

test_post											17.58 487	81.76 264	98.08 307

patchmatchnet-post											90.45 439	82.65 245	98.10 302

gm-plane-assit					93.22 417	78.89 450			84.82 403		93.52 392		98.64 250	87.72 309

test9_res														94.81 141	99.38 64	99.45 59

agg_prior2														93.94 168	99.38 64	99.50 52

test_prior4						93.66 62	96.42 277

test_prior2							96.35 287		92.80 155	96.03 126	97.59 161	92.01 50		95.01 128	99.38 64

旧先验2							95.94 318		81.66 436	97.34 70			98.82 209	92.26 201

新几何2							95.79 329

原ACMM2							95.67 335

testdata2													99.67 77	85.96 350

segment_acmp												92.89 33

testdata1							95.26 361		93.10 137

plane_prior7					96.21 269	89.98 213

plane_prior6					96.10 287	90.00 209						81.32 271

plane_prior4											96.64 225

plane_prior3						90.00 209			94.46 78	91.34 271

plane_prior2							97.74 113		94.85 53

plane_prior1					96.14 282

plane_prior						89.99 211	97.24 188		94.06 92						92.16 305

HQP5-MVS						89.33 247

HQP-NCC					95.86 295		96.65 258		93.55 109	90.14 295

ACMP_Plane					95.86 295		96.65 258		93.55 109	90.14 295

BP-MVS														92.13 209

HQP4-MVS										90.14 295			98.50 265			95.78 324

HQP2-MVS												80.95 276

NP-MVS					95.99 293	89.81 221					95.87 268

MDTV_nov1_ep13_2view						70.35 468	93.10 434		83.88 414	93.55 212		82.47 249		86.25 341		98.38 193

ACMMP++_ref															90.30 335

ACMMP++															91.02 324

Test By Simon												88.73 108

High-resolution multi-view benchmark