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	98.08 228

PGM-MVS		96.81 58	96.53 69	97.65 47	99.35 25	93.53 65	97.65 129	98.98 2	92.22 177	97.14 76	98.44 64	91.17 71	99.85 21	94.35 163	99.46 46	99.57 36

MVS_111021_HR		96.68 69	96.58 68	96.99 84	98.46 79	92.31 110	96.20 305	98.90 3	94.30 86	95.86 134	97.74 144	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	94.56 182	98.39 68	88.96 102	99.85 21	94.57 157	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	96.24 302	98.79 7	93.99 95	95.80 136	97.65 154	89.92 91	99.24 149	95.87 100	99.20 88	98.58 172

patch_mono-2		96.83 57	97.44 24	95.01 225	99.05 45	85.39 372	96.98 217	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	90.28 204	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	98.18 213

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	90.72 186	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	98.25 208

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		93.94 183	93.57 175	95.04 223	95.48 316	91.45 149	98.12 55	98.71 13	93.37 122	90.23 296	96.70 222	87.66 129	97.85 347	91.49 227	90.39 336	95.83 322

UniMVSNet (Re)		93.31 210	92.55 223	95.61 189	95.39 322	93.34 71	97.39 172	98.71 13	93.14 135	90.10 305	94.83 324	87.71 128	98.03 320	91.67 225	83.99 412	95.46 341

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		94.09 174	93.70 171	95.27 212	95.70 305	92.03 122	98.10 56	98.68 19	93.36 124	90.39 293	96.70 222	87.63 132	97.94 338	92.25 205	90.50 335	95.84 321

WR-MVS_H		92.00 267	91.35 264	93.95 295	95.09 349	89.47 240	98.04 63	98.68 19	91.46 208	88.34 358	94.68 331	85.86 170	97.56 379	85.77 358	84.24 410	94.82 392

fmvsm_s_conf0.5_n_4		96.75 62	97.07 34	95.79 173	97.76 142	89.57 233	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	98.08 228

VPA-MVSNet		93.24 212	92.48 228	95.51 199	95.70 305	92.39 106	97.86 91	98.66 22	92.30 174	92.09 254	95.37 299	80.49 292	98.40 274	93.95 169	85.86 383	95.75 330

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	98.59 171

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	90.43 196	97.50 153	98.59 27	96.59 10	99.31 6	99.08 8	84.47 204	99.75 58	99.37 5	98.45 133	97.88 241

UniMVSNet_NR-MVSNet		93.37 208	92.67 217	95.47 205	95.34 328	92.83 89	97.17 200	98.58 28	92.98 145	90.13 301	95.80 275	88.37 116	97.85 347	91.71 222	83.93 413	95.73 332

CSCG		96.05 90	95.91 90	96.46 117	99.24 33	90.47 193	98.30 33	98.57 29	89.01 304	93.97 203	97.57 164	92.62 40	99.76 54	94.66 151	99.27 75	99.15 87

fmvsm_s_conf0.5_n_9		97.33 27	97.57 15	96.62 101	98.43 82	90.32 203	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		93.66 195	92.92 205	95.87 162	98.24 100	89.88 219	94.58 388	98.49 32	85.06 402	93.78 206	95.78 279	82.86 239	98.67 248	91.77 220	95.71 234	99.07 100

CHOSEN 1792x2688		94.15 169	93.51 181	96.06 147	98.27 96	89.38 245	95.18 371	98.48 34	85.60 392	93.76 207	97.11 197	83.15 229	99.61 90	91.33 230	98.72 119	99.19 83

fmvsm_s_conf0.5_n_7		96.45 77	96.80 57	95.37 208	97.29 169	88.38 286	97.23 194	98.47 35	95.14 39	98.43 41	99.09 7	87.58 133	99.72 65	98.80 25	99.21 83	98.02 232

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	89.86 274	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	90.25 205	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	98.15 217

PVSNet_BlendedMVS		94.06 175	93.92 165	94.47 262	98.27 96	89.46 242	96.73 250	98.36 39	90.17 266	94.36 188	95.24 307	88.02 121	99.58 98	93.44 183	90.72 331	94.36 413

PVSNet_Blended		94.87 144	94.56 143	95.81 169	98.27 96	89.46 242	95.47 350	98.36 39	88.84 313	94.36 188	96.09 264	88.02 121	99.58 98	93.44 183	98.18 145	98.40 193

3Dnovator	91.36 5	95.19 126	94.44 152	97.44 57	96.56 243	93.36 70	98.65 16	98.36 39	94.12 90	89.25 335	98.06 98	82.20 256	99.77 52	93.41 185	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	97.21 197	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	95.48 316	90.69 187	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	98.18 213

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	97.43 268

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	97.81 136	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	95.67 307	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	92.37 171	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	90.86 179	97.27 188	98.25 61	90.21 265	94.18 196	97.27 186	87.48 140	99.73 61	93.53 180	97.77 161	98.55 174

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		91.55 289	90.84 288	93.69 312	94.96 353	88.28 289	97.84 95	98.24 63	91.46 208	88.04 369	95.80 275	79.67 308	97.48 391	87.02 338	84.54 407	95.31 355

DU-MVS		92.90 230	92.04 239	95.49 202	94.95 354	92.83 89	97.16 201	98.24 63	93.02 139	90.13 301	95.71 282	83.47 221	97.85 347	91.71 222	83.93 413	95.78 326

9.14			96.75 61		98.93 56		97.73 115	98.23 66	91.28 217	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		91.30 306	90.95 282	92.35 365	94.71 369	85.52 366	96.18 307	98.21 67	88.89 311	86.60 398	93.82 380	79.92 304	97.95 336	89.29 280	90.95 328	93.56 429

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		94.17 167	93.61 174	95.86 165	98.09 116	91.37 151	97.35 176	98.20 69	93.18 132	91.79 262	97.28 184	79.13 316	98.93 196	94.61 154	92.84 294	97.28 276

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		91.71 276	89.67 344	97.81 32	99.38 17	94.03 54	98.59 17	98.20 69	94.85 53	96.59 99	32.69 491	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		91.89 272	91.24 271	93.82 304	95.05 350	88.57 277	97.82 100	98.19 74	91.70 197	88.21 364	95.76 280	81.96 261	97.52 389	87.86 306	84.65 401	95.37 351

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	90.57 256	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		91.20 311	90.44 307	93.48 328	94.49 377	87.91 305	97.76 108	98.18 76	91.29 214	87.78 373	95.74 281	80.35 295	97.33 402	85.46 362	82.96 423	95.19 366

DELS-MVS		96.61 71	96.38 80	97.30 63	97.79 140	93.19 78	95.96 319	98.18 76	95.23 35	95.87 133	97.65 154	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		89.70 363	88.40 369	93.60 320	95.15 345	90.10 208	97.56 144	98.16 80	87.28 365	86.16 405	94.63 335	77.57 344	98.05 316	74.48 449	84.59 405	92.65 442

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	97.61 160	85.29 188	99.53 112	95.81 105	95.27 247	99.16 85

DeepPCF-MVS	93.97 1	96.61 71	97.09 33	95.15 216	98.09 116	86.63 338	96.00 317	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	97.41 398	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	94.83 140	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	90.36 255	97.35 174	99.11 94

QAPM		93.45 206	92.27 233	96.98 85	96.77 221	92.62 98	98.39 29	98.12 86	84.50 410	88.27 362	97.77 140	82.39 253	99.81 35	85.40 363	98.81 115	98.51 179

Vis-MVSNet		95.23 121	94.81 131	96.51 111	97.18 175	91.58 141	98.26 39	98.12 86	94.38 84	94.90 171	98.15 93	82.28 254	98.92 198	91.45 229	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	92.86 233	91.68 254	96.40 122	95.34 328	92.73 94	98.27 37	98.12 86	84.86 405	85.78 411	97.75 141	78.89 326	99.74 59	87.50 328	98.65 122	96.73 293

TranMVSNet+NR-MVSNet		92.50 242	91.63 255	95.14 217	94.76 365	92.07 119	97.53 150	98.11 89	92.90 151	89.56 323	96.12 259	83.16 228	97.60 376	89.30 279	83.20 422	95.75 330

CPTT-MVS		95.57 108	95.19 112	96.70 92	99.27 31	91.48 146	98.33 31	98.11 89	87.79 350	95.17 161	98.03 101	87.09 148	99.61 90	93.51 181	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	91.50 206	98.01 50	98.32 80	92.33 45	99.58 98	94.85 137	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	89.22 297	97.03 81	98.10 94	92.52 42	99.65 79	94.58 156	99.31 72

MTGPA								98.08 93

MTAPA		97.08 39	96.78 59	97.97 27	99.37 19	94.42 40	97.24 190	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	97.27 188	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	97.03 208	98.08 93	88.35 331	95.09 163	97.65 154	89.97 90	99.48 124	92.08 214	98.59 126	98.44 190

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	97.12 204	98.07 98	93.54 112	96.08 125	97.69 149	93.86 18	99.71 67	96.50 74	99.39 63	99.55 43

NR-MVSNet		92.34 251	91.27 270	95.53 194	94.95 354	93.05 81	97.39 172	98.07 98	92.65 159	84.46 422	95.71 282	85.00 195	97.77 358	89.71 267	83.52 419	95.78 326

MP-MVS-pluss		96.70 65	96.27 83	97.98 26	99.23 35	94.71 30	96.96 219	98.06 101	90.67 246	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	94.83 140	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	90.57 256	96.77 88	98.35 72	90.21 86	99.53 112	94.80 144	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	91.17 225	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		94.51 158	93.80 167	96.64 94	97.07 181	91.97 124	96.32 294	98.06 101	88.94 309	94.50 185	96.78 217	84.60 201	99.27 147	91.90 215	96.02 224	98.68 165

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	93.38 222	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	97.88 123	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		88.98 369	87.05 383	94.77 244	94.45 379	87.19 322	90.23 465	98.03 110	77.87 463	92.40 240	87.55 468	80.17 299	99.51 117	68.84 471	93.95 280	97.60 261

save fliter					98.91 58	94.28 42	97.02 210	98.02 113	95.35 31

TEST9					98.70 65	94.19 46	96.41 280	98.02 113	88.17 335	96.03 126	97.56 166	92.74 36	99.59 95

train_agg		96.30 85	95.83 93	97.72 43	98.70 65	94.19 46	96.41 280	98.02 113	88.58 322	96.03 126	97.56 166	92.73 37	99.59 95	95.04 126	99.37 67	99.39 68

test_8					98.67 67	94.06 53	96.37 288	98.01 116	88.58 322	95.98 130	97.55 168	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	98.12 220

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		92.34 251	91.53 259	94.77 244	95.13 347	90.83 180	96.40 284	97.98 120	91.88 192	89.29 332	95.54 293	82.50 249	97.80 354	89.79 266	85.27 392	95.69 333

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

CANet		96.39 80	96.02 88	97.50 54	97.62 154	93.38 68	97.02 210	97.96 122	95.42 29	94.86 172	97.81 136	87.38 143	99.82 33	96.88 60	99.20 88	99.29 75

114514_t		93.95 182	93.06 199	96.63 98	99.07 43	91.61 138	97.46 164	97.96 122	77.99 461	93.00 231	97.57 164	86.14 166	99.33 139	89.22 283	99.15 95	98.94 121

IU-MVS					99.42 10	95.39 12		97.94 124	90.40 263	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	90.37 202	97.53 150	97.92 127	96.52 11	99.14 15	99.08 8	83.21 226	99.74 59	99.22 11	98.06 150	97.88 241

Anonymous20231211		90.63 335	89.42 351	94.27 276	98.24 100	89.19 257	98.05 62	97.89 128	79.95 452	88.25 363	94.96 316	72.56 389	98.13 299	89.70 268	85.14 394	95.49 337

原ACMM1				96.38 125	98.59 75	91.09 168		97.89 128	87.41 361	95.22 160	97.68 150	90.25 85	99.54 110	87.95 305	99.12 100	98.49 182

CDPH-MVS		95.97 94	95.38 106	97.77 38	98.93 56	94.44 39	96.35 289	97.88 130	86.98 369	96.65 95	97.89 118	91.99 51	99.47 125	92.26 203	99.46 46	99.39 68

test11								97.88 130

EIA-MVS		95.53 109	95.47 100	95.71 184	97.06 184	89.63 229	97.82 100	97.87 132	93.57 108	93.92 204	95.04 313	90.61 82	98.95 193	94.62 153	98.68 120	98.54 175

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	98.71 241	97.10 55	99.17 91	98.90 130

无先验							95.79 331	97.87 132	83.87 418				99.65 79	87.68 319		98.89 136

3Dnovator+	91.43 4	95.40 110	94.48 150	98.16 17	96.90 201	95.34 17	98.48 25	97.87 132	94.65 70	88.53 354	98.02 103	83.69 217	99.71 67	93.18 189	98.96 110	99.44 61

VPNet		92.23 259	91.31 267	94.99 227	95.56 312	90.96 172	97.22 196	97.86 136	92.96 146	90.96 284	96.62 234	75.06 365	98.20 293	91.90 215	83.65 418	95.80 324

test_vis1_n_1920		94.17 167	94.58 142	92.91 349	97.42 166	82.02 420	97.83 98	97.85 137	94.68 67	98.10 48	98.49 58	70.15 408	99.32 141	97.91 30	98.82 114	97.40 270

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	98.75 231	96.92 59	99.33 70	98.94 121

test_fmvsmconf0.01_n		96.15 88	95.85 92	97.03 83	92.66 432	91.83 129	97.97 77	97.84 141	95.57 26	97.53 61	99.00 16	84.20 210	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	97.82 134	83.06 233	99.16 161	94.40 160	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	97.36 179	90.97 75	99.22 151	97.74 32	99.66 10	98.61 168

AdaColmap		94.34 162	93.68 172	96.31 129	98.59 75	91.68 136	96.59 269	97.81 144	89.87 273	92.15 250	97.06 200	83.62 220	99.54 110	89.34 278	98.07 149	97.70 254

MVSMamba_PlusPlus		96.51 74	96.48 72	96.59 102	98.07 120	91.97 124	98.14 54	97.79 145	90.43 261	97.34 70	97.52 169	91.29 67	99.19 154	98.12 28	99.64 14	98.60 169

KinetiMVS		95.26 117	94.75 136	96.79 90	96.99 194	92.05 120	97.82 100	97.78 146	94.77 63	96.46 109	97.70 147	80.62 289	99.34 138	92.37 202	98.28 140	98.97 111

mamv4		94.66 155	96.10 87	90.37 419	98.01 123	73.41 471	96.82 236	97.78 146	89.95 272	94.52 183	97.43 174	92.91 30	99.09 174	98.28 27	99.16 94	98.60 169

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	94.51 341	91.23 70	98.92 198	95.65 111	98.19 144	97.82 249

新几何1				97.32 62	98.60 74	93.59 63		97.75 149	81.58 443	95.75 138	97.85 128	90.04 88	99.67 77	86.50 344	99.13 98	98.69 164

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	97.68 150	89.32 96	98.60 257	97.45 46	99.11 101	98.67 166

EI-MVSNet-Vis-set		96.51 74	96.47 73	96.63 98	98.24 100	91.20 160	96.89 227	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		95.01 135	94.59 141	96.26 135	98.89 60	90.68 188	97.24 190	97.73 152	91.80 193	92.93 236	96.62 234	89.13 100	99.14 166	89.21 284	97.78 160	98.97 111

Anonymous20240529		91.98 268	90.73 295	95.73 182	98.14 113	89.40 244	97.99 68	97.72 154	79.63 454	93.54 215	97.41 176	69.94 410	99.56 106	91.04 237	91.11 324	98.22 210

CHOSEN 280x420		93.12 218	92.72 216	94.34 270	96.71 227	87.27 318	90.29 464	97.72 154	86.61 376	91.34 273	95.29 301	84.29 209	98.41 273	93.25 187	98.94 111	97.35 273

EI-MVSNet-UG-set		96.34 83	96.30 82	96.47 115	98.20 107	90.93 176	96.86 230	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		93.57 199	92.61 221	96.47 115	97.59 157	91.61 138	97.67 125	97.72 154	85.17 400	90.29 295	98.34 75	84.60 201	99.73 61	83.85 386	98.27 141	98.06 230

PAPR		94.18 166	93.42 188	96.48 114	97.64 151	91.42 150	95.55 345	97.71 158	88.99 306	92.34 246	95.82 274	89.19 98	99.11 169	86.14 350	97.38 172	98.90 130

UGNet		94.04 177	93.28 191	96.31 129	96.85 206	91.19 161	97.88 90	97.68 159	94.40 82	93.00 231	96.18 254	73.39 384	99.61 90	91.72 221	98.46 132	98.13 218
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				95.46 206	98.18 111	88.90 268		97.66 160	82.73 433	97.03 81	98.07 97	90.06 87	98.85 205	89.67 269	98.98 109	98.64 167

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		90.56 336	89.75 342	93.01 345	93.95 392	87.25 319	97.64 133	97.65 162	90.74 241	87.12 386	95.68 285	79.97 303	97.00 415	83.33 387	81.66 429	94.78 399

TAPA-MVS	90.10 7	92.30 254	91.22 273	95.56 191	98.33 91	89.60 231	96.79 242	97.65 162	81.83 440	91.52 268	97.23 189	87.94 123	98.91 200	71.31 464	98.37 136	98.17 216
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 219	92.45 229	95.05 221	98.09 116	89.21 254	96.89 227	97.64 164	93.18 132	91.79 262	97.28 184	75.35 364	98.65 251	88.99 289	92.84 294	97.28 276

test_cas_vis1_n_1920		94.48 160	94.55 146	94.28 275	96.78 219	86.45 344	97.63 135	97.64 164	93.32 125	97.68 60	98.36 71	73.75 380	99.08 177	96.73 65	99.05 104	97.31 275

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	85.34 186	99.50 120	94.99 129	99.21 83	98.97 111

Elysia		94.00 179	93.12 196	96.64 94	96.08 291	92.72 95	97.50 153	97.63 166	91.15 227	94.82 173	97.12 195	74.98 367	99.06 183	90.78 242	98.02 151	98.12 220

StellarMVS		94.00 179	93.12 196	96.64 94	96.08 291	92.72 95	97.50 153	97.63 166	91.15 227	94.82 173	97.12 195	74.98 367	99.06 183	90.78 242	98.02 151	98.12 220

cdsmvs_eth3d_5k		23.24 460	30.99 462	0.00 479	0.00 502	0.00 504	0.00 491	97.63 166	0.00 497	0.00 498	96.88 213	84.38 206	0.00 498	0.00 497	0.00 496	0.00 494

DPM-MVS		95.69 102	94.92 124	98.01 21	98.08 119	95.71 10	95.27 362	97.62 170	90.43 261	95.55 147	97.07 199	91.72 54	99.50 120	89.62 271	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	96.12 259	87.65 130	99.18 157	96.20 88	94.82 256	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	96.12 259	87.65 130	99.18 157	96.20 88	94.82 256	98.91 127

test222					98.24 100	92.21 114	95.33 357	97.60 171	79.22 456	95.25 158	97.84 130	88.80 106			99.15 95	98.72 161

cascas		91.20 311	90.08 324	94.58 256	94.97 352	89.16 258	93.65 429	97.59 174	79.90 453	89.40 327	92.92 408	75.36 363	98.36 281	92.14 208	94.75 259	96.23 303

E2		95.20 123	95.00 121	95.79 173	96.79 214	89.66 226	96.82 236	97.58 175	92.35 172	95.28 156	97.83 132	86.68 152	98.76 225	94.79 147	96.92 193	98.95 118

E3		95.20 123	95.00 121	95.79 173	96.77 221	89.66 226	96.82 236	97.58 175	92.35 172	95.28 156	97.83 132	86.69 151	98.76 225	94.79 147	96.92 193	98.95 118

h-mvs33		94.15 169	93.52 180	96.04 149	97.81 139	90.22 206	97.62 137	97.58 175	95.19 36	96.74 89	97.45 171	83.67 218	99.61 90	95.85 102	79.73 436	98.29 206

E5new		95.04 131	94.88 126	95.52 195	96.62 230	89.02 262	97.29 183	97.57 178	92.54 162	95.04 164	97.89 118	85.65 178	98.77 219	94.92 132	96.44 217	98.78 149

E6new		95.04 131	94.88 126	95.52 195	96.60 234	89.02 262	97.29 183	97.57 178	92.54 162	95.04 164	97.90 116	85.66 176	98.77 219	94.92 132	96.44 217	98.78 149

E6		95.04 131	94.88 126	95.52 195	96.60 234	89.02 262	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	89.02 262	97.29 183	97.57 178	92.54 162	95.04 164	97.89 118	85.65 178	98.77 219	94.92 132	96.44 217	98.78 149

MGCFI-Net		95.94 96	95.40 105	97.56 53	97.59 157	94.62 32	98.21 47	97.57 178	94.41 81	96.17 121	96.16 257	87.54 135	99.17 159	96.19 90	94.73 261	98.91 127

MVSFormer		95.37 111	95.16 113	95.99 156	96.34 267	91.21 158	98.22 45	97.57 178	91.42 210	96.22 119	97.32 180	86.20 164	97.92 341	94.07 166	99.05 104	98.85 142

test_djsdf		93.07 221	92.76 211	94.00 289	93.49 411	88.70 272	98.22 45	97.57 178	91.42 210	90.08 307	95.55 292	82.85 240	97.92 341	94.07 166	91.58 315	95.40 348

OMC-MVS		95.09 128	94.70 137	96.25 138	98.46 79	91.28 154	96.43 276	97.57 178	92.04 188	94.77 177	97.96 110	87.01 149	99.09 174	91.31 231	96.77 198	98.36 197

E4		95.09 128	94.86 130	95.77 176	96.58 238	89.56 234	96.85 231	97.56 186	92.50 166	95.03 168	97.86 126	86.03 167	98.78 215	94.71 150	96.65 207	98.96 114

viewcassd2359sk11		95.26 117	95.09 118	95.80 170	96.95 198	89.72 225	96.80 241	97.56 186	92.21 179	95.37 154	97.80 138	87.17 147	98.77 219	94.82 142	97.10 187	98.90 130

PS-MVSNAJss		93.74 192	93.51 181	94.44 264	93.91 394	89.28 252	97.75 110	97.56 186	92.50 166	89.94 309	96.54 237	88.65 109	98.18 296	93.83 175	90.90 329	95.86 318

casdiffmvs_mvg		95.81 101	95.57 95	96.51 111	96.87 203	91.49 144	97.50 153	97.56 186	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	89.76 223	96.78 246	97.54 190	92.06 187	95.40 153	97.75 141	87.49 139	98.76 225	94.85 137	97.10 187	98.88 138

jajsoiax		92.42 247	91.89 247	94.03 288	93.33 419	88.50 282	97.73 115	97.53 191	92.00 190	88.85 346	96.50 239	75.62 362	98.11 303	93.88 173	91.56 316	95.48 338

mvs_tets		92.31 253	91.76 250	93.94 297	93.41 416	88.29 288	97.63 135	97.53 191	92.04 188	88.76 349	96.45 241	74.62 372	98.09 308	93.91 171	91.48 317	95.45 343

dcpmvs_2		96.37 81	97.05 38	94.31 273	98.96 55	84.11 393	97.56 144	97.51 193	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		93.78 191	93.43 186	94.82 237	96.21 271	89.99 212	97.74 113	97.51 193	94.85 53	91.34 273	96.64 227	81.32 273	98.60 257	93.02 195	92.23 303	95.86 318

plane_prior5								97.51 193					98.60 257	93.02 195	92.23 303	95.86 318

viewmanbaseed2359cas		95.24 120	95.02 120	95.91 159	96.87 203	89.98 214	96.82 236	97.49 196	92.26 175	95.47 151	97.82 134	86.47 157	98.69 243	94.80 144	97.20 183	99.06 101

reproduce_monomvs		91.30 306	91.10 277	91.92 379	96.82 211	82.48 414	97.01 213	97.49 196	94.64 71	88.35 357	95.27 304	70.53 403	98.10 304	95.20 122	84.60 404	95.19 366

viewmacassd2359aftdt		95.07 130	94.80 132	95.87 162	96.53 248	89.84 220	96.90 226	97.48 198	92.44 168	95.36 155	97.89 118	85.23 189	98.68 245	94.40 160	97.00 191	99.09 96

PS-MVSNAJ		95.37 111	95.33 108	95.49 202	97.35 167	90.66 189	95.31 359	97.48 198	93.85 100	96.51 105	95.70 284	88.65 109	99.65 79	94.80 144	98.27 141	96.17 307

API-MVS		94.84 146	94.49 149	95.90 160	97.90 134	92.00 123	97.80 104	97.48 198	89.19 298	94.81 175	96.71 220	88.84 105	99.17 159	88.91 291	98.76 118	96.53 296

MG-MVS		95.61 106	95.38 106	96.31 129	98.42 83	90.53 191	96.04 314	97.48 198	93.47 117	95.67 144	98.10 94	89.17 99	99.25 148	91.27 232	98.77 117	99.13 89

MAR-MVS		94.22 165	93.46 183	96.51 111	98.00 125	92.19 117	97.67 125	97.47 202	88.13 339	93.00 231	95.84 272	84.86 199	99.51 117	87.99 304	98.17 146	97.83 248
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		92.98 225	92.53 225	94.32 271	96.12 286	89.20 255	95.28 360	97.47 202	92.66 158	89.90 310	95.62 288	80.58 290	98.40 274	92.73 200	92.40 301	95.38 350
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 304	90.22 320	94.68 248	94.86 361	87.86 306	97.23 194	97.46 204	87.99 340	89.90 310	96.92 211	66.35 438	98.23 290	90.30 256	90.99 327	97.96 235

nrg030		94.05 176	93.31 190	96.27 134	95.22 339	94.59 33	98.34 30	97.46 204	92.93 147	91.21 282	96.64 227	87.23 146	98.22 291	94.99 129	85.80 384	95.98 317

XVG-OURS		93.72 193	93.35 189	94.80 242	97.07 181	88.61 275	94.79 383	97.46 204	91.97 191	93.99 201	97.86 126	81.74 267	98.88 202	92.64 201	92.67 299	96.92 288

LPG-MVS_test		92.94 228	92.56 222	94.10 283	96.16 281	88.26 290	97.65 129	97.46 204	91.29 214	90.12 303	97.16 192	79.05 319	98.73 235	92.25 205	91.89 311	95.31 355

LGP-MVS_train				94.10 283	96.16 281	88.26 290		97.46 204	91.29 214	90.12 303	97.16 192	79.05 319	98.73 235	92.25 205	91.89 311	95.31 355

MVS		91.71 276	90.44 307	95.51 199	95.20 341	91.59 140	96.04 314	97.45 209	73.44 471	87.36 382	95.60 289	85.42 185	99.10 171	85.97 355	97.46 167	95.83 322

XVG-OURS-SEG-HR		93.86 188	93.55 176	94.81 239	97.06 184	88.53 281	95.28 360	97.45 209	91.68 198	94.08 200	97.68 150	82.41 252	98.90 201	93.84 174	92.47 300	96.98 284

baseline		95.58 107	95.42 104	96.08 145	96.78 219	90.41 197	97.16 201	97.45 209	93.69 106	95.65 145	97.85 128	87.29 144	98.68 245	95.66 108	97.25 181	99.13 89

ab-mvs		93.57 199	92.55 223	96.64 94	97.28 170	91.96 126	95.40 353	97.45 209	89.81 278	93.22 228	96.28 250	79.62 310	99.46 126	90.74 245	93.11 291	98.50 180

xiu_mvs_v2_base		95.32 114	95.29 109	95.40 207	97.22 172	90.50 192	95.44 352	97.44 213	93.70 105	96.46 109	96.18 254	88.59 113	99.53 112	94.79 147	97.81 159	96.17 307

1314		92.81 237	92.03 240	95.14 217	95.33 331	89.52 239	96.04 314	97.44 213	87.72 354	86.25 403	95.33 300	83.84 215	98.79 214	89.26 281	97.05 190	97.11 282

casdiffmvs		95.64 104	95.49 98	96.08 145	96.76 225	90.45 194	97.29 183	97.44 213	94.00 94	95.46 152	97.98 108	87.52 138	98.73 235	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		94.76 152	94.68 138	95.01 225	96.76 225	87.41 314	96.38 286	97.43 216	92.65 159	94.52 183	97.75 141	85.55 183	98.81 211	94.36 162	96.69 204	98.82 146

XXY-MVS		92.16 261	91.23 272	94.95 233	94.75 366	90.94 175	97.47 162	97.43 216	89.14 299	88.90 342	96.43 242	79.71 307	98.24 289	89.56 272	87.68 365	95.67 334

anonymousdsp		92.16 261	91.55 258	93.97 293	92.58 434	89.55 236	97.51 152	97.42 218	89.42 292	88.40 356	94.84 323	80.66 288	97.88 346	91.87 217	91.28 321	94.48 408

Effi-MVS+		94.93 140	94.45 151	96.36 127	96.61 233	91.47 147	96.41 280	97.41 219	91.02 233	94.50 185	95.92 268	87.53 136	98.78 215	93.89 172	96.81 197	98.84 145

RRT-MVS		94.51 158	94.35 155	94.98 229	96.40 261	86.55 341	97.56 144	97.41 219	93.19 130	94.93 170	97.04 201	79.12 317	99.30 145	96.19 90	97.32 177	99.09 96

HQP3-MVS								97.39 221							92.10 308

HQP-MVS		93.19 215	92.74 214	94.54 259	95.86 297	89.33 248	96.65 260	97.39 221	93.55 109	90.14 297	95.87 270	80.95 279	98.50 267	92.13 211	92.10 308	95.78 326

PLC	91.00 6	94.11 173	93.43 186	96.13 143	98.58 77	91.15 167	96.69 256	97.39 221	87.29 364	91.37 272	96.71 220	88.39 114	99.52 116	87.33 331	97.13 186	97.73 252
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	95.50 201	96.37 265	89.08 260	96.08 312	97.38 224	93.09 138	96.53 104	97.74 144	86.45 158	98.68 245	96.32 78	97.48 166	98.75 157

v7n		90.76 328	89.86 335	93.45 330	93.54 408	87.60 312	97.70 123	97.37 225	88.85 312	87.65 375	94.08 371	81.08 278	98.10 304	84.68 372	83.79 417	94.66 405

UnsupCasMVSNet_eth		85.99 411	84.45 415	90.62 415	89.97 452	82.40 417	93.62 430	97.37 225	89.86 274	78.59 461	92.37 418	65.25 448	95.35 450	82.27 401	70.75 469	94.10 419

viewdifsd2359ckpt13		94.87 144	94.52 147	95.90 160	96.88 202	90.19 207	96.92 223	97.36 227	91.26 218	94.65 179	97.46 170	85.79 173	98.64 252	93.64 178	96.76 199	98.88 138

ACMM	89.79 8	92.96 226	92.50 227	94.35 268	96.30 269	88.71 271	97.58 140	97.36 227	91.40 212	90.53 290	96.65 226	79.77 306	98.75 231	91.24 233	91.64 313	95.59 336
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 135	94.76 133	95.75 179	96.58 238	91.71 133	96.25 299	97.35 229	92.99 140	96.70 91	96.63 231	82.67 244	99.44 129	96.22 83	97.46 167	96.11 313

xiu_mvs_v1_base		95.01 135	94.76 133	95.75 179	96.58 238	91.71 133	96.25 299	97.35 229	92.99 140	96.70 91	96.63 231	82.67 244	99.44 129	96.22 83	97.46 167	96.11 313

xiu_mvs_v1_base_debi		95.01 135	94.76 133	95.75 179	96.58 238	91.71 133	96.25 299	97.35 229	92.99 140	96.70 91	96.63 231	82.67 244	99.44 129	96.22 83	97.46 167	96.11 313

diffmvs		95.25 119	95.13 114	95.63 187	96.43 260	89.34 247	95.99 318	97.35 229	92.83 153	96.31 115	97.37 178	86.44 159	98.67 248	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		94.71 154	94.02 163	96.79 90	97.71 145	92.05 120	96.59 269	97.35 229	90.61 252	94.64 180	96.93 208	86.41 160	99.39 134	91.20 234	94.71 262	98.94 121

viewdifsd2359ckpt09		94.81 149	94.37 154	96.12 144	96.91 199	90.75 185	96.94 220	97.31 234	90.51 259	94.31 190	97.38 177	85.70 175	98.71 241	93.54 179	96.75 200	98.90 130

SSM_0407		94.54 157	94.12 162	95.80 170	96.79 214	90.38 199	96.79 242	97.29 235	91.24 219	93.68 208	97.60 161	85.03 193	98.67 248	92.14 208	96.51 210	98.35 199

SSM_0404		94.73 153	94.31 157	95.98 157	97.05 186	90.90 178	97.01 213	97.29 235	91.24 219	94.17 197	97.60 161	85.03 193	98.76 225	92.14 208	97.30 178	98.29 206

F-COLMAP		93.58 197	92.98 203	95.37 208	98.40 86	88.98 266	97.18 199	97.29 235	87.75 353	90.49 291	97.10 198	85.21 190	99.50 120	86.70 341	96.72 203	97.63 256

VortexMVS		92.88 232	92.64 218	93.58 322	96.58 238	87.53 313	96.93 222	97.28 238	92.78 156	89.75 315	94.99 314	82.73 243	97.76 359	94.60 155	88.16 360	95.46 341

XVG-ACMP-BASELINE		90.93 324	90.21 321	93.09 343	94.31 385	85.89 359	95.33 357	97.26 239	91.06 232	89.38 328	95.44 298	68.61 421	98.60 257	89.46 274	91.05 325	94.79 397

PCF-MVS	89.48 11	91.56 288	89.95 332	96.36 127	96.60 234	92.52 103	92.51 449	97.26 239	79.41 455	88.90 342	96.56 236	84.04 214	99.55 108	77.01 440	97.30 178	97.01 283
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 241	92.14 236	94.05 286	96.40 261	88.20 294	97.36 175	97.25 241	91.52 205	88.30 360	96.64 227	78.46 331	98.72 240	91.86 218	91.48 317	95.23 362
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 197	93.46 183	93.94 297	96.19 275	86.16 353	93.73 424	97.24 242	91.54 201	93.50 217	97.04 201	85.64 181	96.91 418	90.68 247	95.59 238	98.76 153

IMVS_0407		93.94 183	93.75 169	94.49 261	96.19 275	86.16 353	96.35 289	97.24 242	91.54 201	93.50 217	97.04 201	85.64 181	98.54 264	90.68 247	95.59 238	98.76 153

IMVS_0404		92.44 245	91.92 245	94.00 289	96.19 275	86.16 353	93.84 421	97.24 242	91.54 201	88.17 366	97.04 201	76.96 349	97.09 409	90.68 247	95.59 238	98.76 153

IMVS_0403		93.98 181	93.79 168	94.55 258	96.19 275	86.16 353	96.35 289	97.24 242	91.54 201	93.59 212	97.04 201	85.86 170	98.73 235	90.68 247	95.59 238	98.76 153

OPM-MVS		93.28 211	92.76 211	94.82 237	94.63 372	90.77 183	96.65 260	97.18 246	93.72 103	91.68 266	97.26 187	79.33 314	98.63 254	92.13 211	92.28 302	95.07 371
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 230	92.02 241	95.56 191	98.19 109	90.80 181	95.27 362	97.18 246	87.96 341	91.86 261	95.68 285	80.44 293	98.99 191	84.01 381	97.54 165	96.89 289

alignmvs		95.87 100	95.23 111	97.78 36	97.56 163	95.19 22	97.86 91	97.17 248	94.39 83	96.47 108	96.40 244	85.89 169	99.20 153	96.21 87	95.11 252	98.95 118

MVS_Test		94.89 142	94.62 140	95.68 185	96.83 209	89.55 236	96.70 254	97.17 248	91.17 225	95.60 146	96.11 263	87.87 126	98.76 225	93.01 197	97.17 185	98.72 161

Fast-Effi-MVS+		93.46 203	92.75 213	95.59 190	96.77 221	90.03 209	96.81 240	97.13 250	88.19 334	91.30 276	94.27 359	86.21 163	98.63 254	87.66 321	96.46 216	98.12 220

usedtu_dtu_shiyan1		91.65 280	90.67 299	94.60 250	93.65 405	90.95 173	94.86 380	97.12 251	89.69 281	89.21 336	93.62 390	81.17 276	97.67 366	87.54 325	89.14 347	95.17 368

FE-MVSNET3		91.65 280	90.67 299	94.60 250	93.65 405	90.95 173	94.86 380	97.12 251	89.69 281	89.21 336	93.62 390	81.17 276	97.67 366	87.54 325	89.14 347	95.17 368

EI-MVSNet		93.03 223	92.88 207	93.48 328	95.77 303	86.98 327	96.44 274	97.12 251	90.66 248	91.30 276	97.64 157	86.56 154	98.05 316	89.91 262	90.55 333	95.41 345

MVSTER		93.20 214	92.81 210	94.37 267	96.56 243	89.59 232	97.06 207	97.12 251	91.24 219	91.30 276	95.96 266	82.02 260	98.05 316	93.48 182	90.55 333	95.47 340

viewmambaseed2359dif		94.28 163	94.14 160	94.71 247	96.21 271	86.97 328	95.93 321	97.11 255	89.00 305	95.00 169	97.70 147	86.02 168	98.59 261	93.71 177	96.59 209	98.57 173

test_yl		94.78 150	94.23 158	96.43 119	97.74 143	91.22 156	96.85 231	97.10 256	91.23 222	95.71 140	96.93 208	84.30 207	99.31 143	93.10 190	95.12 250	98.75 157

DCV-MVSNet		94.78 150	94.23 158	96.43 119	97.74 143	91.22 156	96.85 231	97.10 256	91.23 222	95.71 140	96.93 208	84.30 207	99.31 143	93.10 190	95.12 250	98.75 157

LTVRE_ROB	88.41 13	90.99 320	89.92 334	94.19 277	96.18 279	89.55 236	96.31 295	97.09 258	87.88 344	85.67 412	95.91 269	78.79 327	98.57 262	81.50 404	89.98 338	94.44 411
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		93.46 203	93.23 193	94.17 278	96.12 286	85.42 368	96.43 276	97.08 259	92.91 148	94.21 193	98.00 105	80.82 285	98.74 233	94.41 159	89.05 349	98.34 203

test_fmvs1_n		92.73 239	92.88 207	92.29 369	96.08 291	81.05 428	97.98 71	97.08 259	90.72 243	96.79 87	98.18 91	63.07 453	98.45 271	97.62 40	98.42 135	97.36 271

v10		91.04 318	90.23 318	93.49 327	94.12 388	88.16 297	97.32 180	97.08 259	88.26 333	88.29 361	94.22 364	82.17 257	97.97 328	86.45 345	84.12 411	94.33 414

viewdifsd2359ckpt11		93.46 203	93.22 194	94.17 278	96.11 288	85.42 368	96.43 276	97.07 262	92.91 148	94.20 194	98.00 105	80.82 285	98.73 235	94.42 158	89.04 351	98.34 203

mamba_0408		93.70 194	92.99 200	95.83 167	96.79 214	90.38 199	88.69 474	97.07 262	90.96 235	93.68 208	97.31 182	84.97 196	98.76 225	90.95 238	96.51 210	98.35 199

SSM_04072		93.51 202	92.99 200	95.05 221	96.79 214	90.38 199	88.69 474	97.07 262	90.96 235	93.68 208	97.31 182	84.97 196	96.42 429	90.95 238	96.51 210	98.35 199

v144192		91.06 317	90.28 314	93.39 331	93.66 403	87.23 321	96.83 235	97.07 262	87.43 360	89.69 318	94.28 358	81.48 270	98.00 323	87.18 335	84.92 400	94.93 379

v1192		91.07 316	90.23 318	93.58 322	93.70 400	87.82 308	96.73 250	97.07 262	87.77 351	89.58 321	94.32 356	80.90 283	97.97 328	86.52 343	85.48 387	94.95 375

v8		91.29 308	90.53 306	93.57 324	94.15 387	88.12 298	97.34 177	97.06 267	88.99 306	88.32 359	94.26 361	83.08 231	98.01 322	87.62 323	83.92 415	94.57 407

mvs_anonymous		93.82 189	93.74 170	94.06 285	96.44 259	85.41 370	95.81 329	97.05 268	89.85 276	90.09 306	96.36 246	87.44 141	97.75 361	93.97 168	96.69 204	99.02 103

IterMVS-LS		92.29 255	91.94 244	93.34 333	96.25 270	86.97 328	96.57 272	97.05 268	90.67 246	89.50 326	94.80 326	86.59 153	97.64 371	89.91 262	86.11 382	95.40 348
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 326	90.03 329	93.29 335	93.55 407	86.96 330	96.74 249	97.04 270	87.36 362	89.52 325	94.34 353	80.23 298	97.97 328	86.27 346	85.21 393	94.94 377

CDS-MVSNet		94.14 172	93.54 177	95.93 158	96.18 279	91.46 148	96.33 293	97.04 270	88.97 308	93.56 213	96.51 238	87.55 134	97.89 345	89.80 265	95.95 226	98.44 190
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 362	89.26 355	91.19 404	95.16 342	80.29 439	94.53 390	97.03 272	91.79 194	88.86 345	94.10 368	69.94 410	97.82 351	85.29 364	86.66 378	95.45 343

v1144		91.37 301	90.60 302	93.68 314	93.89 395	88.23 292	96.84 234	97.03 272	88.37 330	89.69 318	94.39 348	82.04 259	97.98 325	87.80 309	85.37 389	94.84 387

v1240		90.70 332	89.85 336	93.23 337	93.51 410	86.80 331	96.61 266	97.02 274	87.16 367	89.58 321	94.31 357	79.55 311	97.98 325	85.52 361	85.44 388	94.90 382

EPP-MVSNet		95.22 122	95.04 119	95.76 177	97.49 164	89.56 234	98.67 15	97.00 275	90.69 244	94.24 192	97.62 159	89.79 93	98.81 211	93.39 186	96.49 214	98.92 126

V42		91.58 287	90.87 284	93.73 308	94.05 391	88.50 282	97.32 180	96.97 276	88.80 318	89.71 316	94.33 354	82.54 248	98.05 316	89.01 288	85.07 396	94.64 406

test_fmvs1		93.21 213	93.53 178	92.25 372	96.55 245	81.20 427	97.40 171	96.96 277	90.68 245	96.80 85	98.04 100	69.25 416	98.40 274	97.58 41	98.50 128	97.16 281

FMVSNet2		91.31 305	90.08 324	94.99 227	96.51 252	92.21 114	97.41 167	96.95 278	88.82 315	88.62 351	94.75 328	73.87 376	97.42 397	85.20 367	88.55 357	95.35 352

ACMH	87.59 16	90.53 337	89.42 351	93.87 302	96.21 271	87.92 303	97.24 190	96.94 279	88.45 328	83.91 432	96.27 251	71.92 392	98.62 256	84.43 375	89.43 344	95.05 373
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 302	90.27 315	94.59 252	96.51 252	91.18 163	97.50 153	96.93 280	88.82 315	89.35 329	94.51 341	73.87 376	97.29 404	86.12 351	88.82 352	95.31 355

test1		91.35 302	90.27 315	94.59 252	96.51 252	91.18 163	97.50 153	96.93 280	88.82 315	89.35 329	94.51 341	73.87 376	97.29 404	86.12 351	88.82 352	95.31 355

FMVSNet3		91.78 274	90.69 298	95.03 224	96.53 248	92.27 112	97.02 210	96.93 280	89.79 279	89.35 329	94.65 334	77.01 347	97.47 392	86.12 351	88.82 352	95.35 352

FMVSNet1		89.88 357	88.31 370	94.59 252	95.41 321	91.18 163	97.50 153	96.93 280	86.62 375	87.41 380	94.51 341	65.94 443	97.29 404	83.04 390	87.43 368	95.31 355

GeoE		93.89 186	93.28 191	95.72 183	96.96 197	89.75 224	98.24 43	96.92 284	89.47 289	92.12 252	97.21 190	84.42 205	98.39 279	87.71 314	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	96.91 285	95.92 16	96.57 102	97.93 111	85.34 186	99.50 120	94.99 129	96.39 221	99.05 102

miper_enhance_ethall		91.54 291	91.01 280	93.15 341	95.35 327	87.07 326	93.97 413	96.90 286	86.79 373	89.17 338	93.43 402	86.55 155	97.64 371	89.97 261	86.93 373	94.74 402

eth_miper_zixun_eth		91.02 319	90.59 303	92.34 367	95.33 331	84.35 389	94.10 410	96.90 286	88.56 324	88.84 347	94.33 354	84.08 212	97.60 376	88.77 294	84.37 409	95.06 372

TAMVS		94.01 178	93.46 183	95.64 186	96.16 281	90.45 194	96.71 253	96.89 288	89.27 296	93.46 220	96.92 211	87.29 144	97.94 338	88.70 296	95.74 232	98.53 176

miper_ehance_all_eth		91.59 285	91.13 276	92.97 347	95.55 313	86.57 339	94.47 394	96.88 289	87.77 351	88.88 344	94.01 373	86.22 162	97.54 385	89.49 273	86.93 373	94.79 397

v2v482		91.59 285	90.85 287	93.80 305	93.87 396	88.17 296	96.94 220	96.88 289	89.54 286	89.53 324	94.90 320	81.70 268	98.02 321	89.25 282	85.04 398	95.20 363

CNLPA		94.28 163	93.53 178	96.52 107	98.38 89	92.55 102	96.59 269	96.88 289	90.13 269	91.91 258	97.24 188	85.21 190	99.09 174	87.64 322	97.83 158	97.92 238

PAPM		91.52 292	90.30 313	95.20 214	95.30 334	89.83 221	93.38 435	96.85 292	86.26 383	88.59 352	95.80 275	84.88 198	98.15 298	75.67 445	95.93 227	97.63 256

c3_l		91.38 299	90.89 283	92.88 351	95.58 311	86.30 347	94.68 385	96.84 293	88.17 335	88.83 348	94.23 362	85.65 178	97.47 392	89.36 277	84.63 402	94.89 383

pm-mvs1		90.72 331	89.65 346	93.96 294	94.29 386	89.63 229	97.79 106	96.82 294	89.07 301	86.12 407	95.48 297	78.61 329	97.78 356	86.97 339	81.67 428	94.46 409

test_vis1_n		92.37 250	92.26 234	92.72 357	94.75 366	82.64 410	98.02 65	96.80 295	91.18 224	97.77 59	97.93 111	58.02 463	98.29 287	97.63 38	98.21 143	97.23 279

CMPMVS	62.92 21	85.62 416	84.92 408	87.74 443	89.14 457	73.12 473	94.17 408	96.80 295	73.98 468	73.65 471	94.93 318	66.36 437	97.61 375	83.95 383	91.28 321	92.48 447
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 344	89.77 340	91.78 388	94.33 383	84.72 386	95.55 345	96.73 297	86.17 385	86.36 402	95.28 303	71.28 397	97.80 354	84.09 380	98.14 147	92.81 439

Effi-MVS+-dtu		93.08 220	93.21 195	92.68 360	96.02 294	83.25 403	97.14 203	96.72 298	93.85 100	91.20 283	93.44 399	83.08 231	98.30 286	91.69 224	95.73 233	96.50 298

TSAR-MVS + GP.		96.69 67	96.49 71	97.27 67	98.31 92	93.39 67	96.79 242	96.72 298	94.17 89	97.44 65	97.66 153	92.76 34	99.33 139	96.86 62	97.76 162	99.08 98

1112_ss		93.37 208	92.42 230	96.21 139	97.05 186	90.99 170	96.31 295	96.72 298	86.87 372	89.83 313	96.69 224	86.51 156	99.14 166	88.12 301	93.67 285	98.50 180

PVSNet	86.66 18	92.24 258	91.74 253	93.73 308	97.77 141	83.69 400	92.88 444	96.72 298	87.91 343	93.00 231	94.86 322	78.51 330	99.05 186	86.53 342	97.45 171	98.47 185

miper_lstm_enhance		90.50 340	90.06 328	91.83 384	95.33 331	83.74 397	93.86 419	96.70 302	87.56 358	87.79 372	93.81 381	83.45 223	96.92 417	87.39 329	84.62 403	94.82 392

v148		90.99 320	90.38 309	92.81 354	93.83 397	85.80 360	96.78 246	96.68 303	89.45 291	88.75 350	93.93 377	82.96 237	97.82 351	87.83 307	83.25 420	94.80 395

ACMH+	87.92 14	90.20 348	89.18 357	93.25 336	96.48 255	86.45 344	96.99 216	96.68 303	88.83 314	84.79 421	96.22 253	70.16 407	98.53 265	84.42 376	88.04 361	94.77 400

CANet_DTU		94.37 161	93.65 173	96.55 104	96.46 258	92.13 118	96.21 303	96.67 305	94.38 84	93.53 216	97.03 206	79.34 313	99.71 67	90.76 244	98.45 133	97.82 249

cl____		90.96 323	90.32 311	92.89 350	95.37 325	86.21 350	94.46 396	96.64 306	87.82 347	88.15 367	94.18 365	82.98 235	97.54 385	87.70 315	85.59 385	94.92 381

HY-MVS	89.66 9	93.87 187	92.95 204	96.63 98	97.10 180	92.49 104	95.64 342	96.64 306	89.05 303	93.00 231	95.79 278	85.77 174	99.45 128	89.16 287	94.35 264	97.96 235

Test_1112_low_res		92.84 235	91.84 248	95.85 166	97.04 188	89.97 216	95.53 347	96.64 306	85.38 395	89.65 320	95.18 308	85.86 170	99.10 171	87.70 315	93.58 290	98.49 182

DIV-MVS_self_test		90.97 322	90.33 310	92.88 351	95.36 326	86.19 352	94.46 396	96.63 309	87.82 347	88.18 365	94.23 362	82.99 234	97.53 387	87.72 312	85.57 386	94.93 379

Fast-Effi-MVS+-dtu		92.29 255	91.99 242	93.21 339	95.27 335	85.52 366	97.03 208	96.63 309	92.09 185	89.11 340	95.14 310	80.33 296	98.08 309	87.54 325	94.74 260	96.03 316

UnsupCasMVSNet_bld		82.13 433	79.46 438	90.14 422	88.00 470	82.47 415	90.89 462	96.62 311	78.94 457	75.61 466	84.40 477	56.63 466	96.31 431	77.30 437	66.77 478	91.63 458

cl22		91.21 310	90.56 305	93.14 342	96.09 290	86.80 331	94.41 398	96.58 312	87.80 349	88.58 353	93.99 375	80.85 284	97.62 374	89.87 264	86.93 373	94.99 374

jason		94.84 146	94.39 153	96.18 141	95.52 314	90.93 176	96.09 311	96.52 313	89.28 295	96.01 129	97.32 180	84.70 200	98.77 219	95.15 125	98.91 113	98.85 142
jason: jason.
tt0805		91.09 315	90.07 327	94.16 281	95.61 309	88.31 287	97.56 144	96.51 314	89.56 285	89.17 338	95.64 287	67.08 435	98.38 280	91.07 236	88.44 358	95.80 324

AUN-MVS		91.76 275	90.75 293	94.81 239	97.00 193	88.57 277	96.65 260	96.49 315	89.63 283	92.15 250	96.12 259	78.66 328	98.50 267	90.83 240	79.18 439	97.36 271

hse-mvs2		93.45 206	92.99 200	94.81 239	97.02 191	88.59 276	96.69 256	96.47 316	95.19 36	96.74 89	96.16 257	83.67 218	98.48 270	95.85 102	79.13 440	97.35 273

SD_0403		90.01 352	90.02 330	89.96 425	95.65 308	76.76 461	95.76 333	96.46 317	90.58 255	86.59 399	96.29 249	82.12 258	94.78 454	73.00 459	93.76 283	98.35 199

EG-PatchMatch MVS		87.02 396	85.44 399	91.76 390	92.67 431	85.00 380	96.08 312	96.45 318	83.41 426	79.52 455	93.49 396	57.10 465	97.72 363	79.34 428	90.87 330	92.56 444

KD-MVS_self_test		85.95 412	84.95 407	88.96 437	89.55 456	79.11 455	95.13 373	96.42 319	85.91 388	84.07 430	90.48 441	70.03 409	94.82 453	80.04 420	72.94 461	92.94 437

FE-MVSNET2		86.36 405	84.68 413	91.39 398	87.67 472	86.47 343	96.21 303	96.41 320	87.87 345	79.31 457	89.64 449	65.29 447	95.58 445	82.42 399	77.28 446	92.14 455

pmmvs6		87.81 384	86.19 392	92.69 359	91.32 444	86.30 347	97.34 177	96.41 320	80.59 451	84.05 431	94.37 350	67.37 430	97.67 366	84.75 371	79.51 438	94.09 421

PMMVS		92.86 233	92.34 231	94.42 266	94.92 357	86.73 334	94.53 390	96.38 322	84.78 407	94.27 191	95.12 312	83.13 230	98.40 274	91.47 228	96.49 214	98.12 220

RPSCF		90.75 329	90.86 285	90.42 418	96.84 207	76.29 464	95.61 343	96.34 323	83.89 416	91.38 271	97.87 124	76.45 353	98.78 215	87.16 336	92.23 303	96.20 305

BP-MVS1		95.89 98	95.49 98	97.08 81	96.67 228	93.20 77	98.08 58	96.32 324	94.56 72	96.32 114	97.84 130	84.07 213	99.15 163	96.75 64	98.78 116	98.90 130

MSDG		91.42 297	90.24 317	94.96 232	97.15 178	88.91 267	93.69 427	96.32 324	85.72 391	86.93 395	96.47 240	80.24 297	98.98 192	80.57 417	95.05 253	96.98 284

blended_shiyan6		87.55 388	85.52 398	93.64 317	88.78 462	88.50 282	95.23 365	96.30 326	82.80 431	86.09 408	87.70 466	73.69 382	97.56 379	87.70 315	71.36 466	94.86 384

blend_shiyan4		86.87 397	84.61 414	93.67 315	88.87 460	88.70 272	95.17 372	96.30 326	82.80 431	86.16 405	87.11 470	65.12 449	97.55 381	87.73 310	72.21 463	94.75 401

WBMVS		90.69 334	89.99 331	92.81 354	96.48 255	85.00 380	95.21 368	96.30 326	89.46 290	89.04 341	94.05 372	72.45 390	97.82 351	89.46 274	87.41 370	95.61 335

blended_shiyan8		87.58 387	85.55 397	93.66 316	88.76 464	88.54 279	95.21 368	96.29 329	82.81 430	86.25 403	87.73 465	73.70 381	97.58 378	87.81 308	71.42 465	94.85 386

OurMVSNet-221017-0		90.51 339	90.19 322	91.44 396	93.41 416	81.25 425	96.98 217	96.28 330	91.68 198	86.55 400	96.30 248	74.20 375	97.98 325	88.96 290	87.40 371	95.09 370

FE-blended-shiyan7		87.29 390	85.21 403	93.53 325	88.54 467	88.21 293	94.51 393	96.27 331	82.69 434	85.92 409	86.89 472	73.03 385	97.55 381	87.68 319	71.36 466	94.83 388

MVP-Stereo		90.74 330	90.08 324	92.71 358	93.19 421	88.20 294	95.86 325	96.27 331	86.07 386	84.86 420	94.76 327	77.84 342	97.75 361	83.88 385	98.01 153	92.17 454
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 139	94.56 143	96.29 133	96.34 267	91.21 158	95.83 327	96.27 331	88.93 310	96.22 119	96.88 213	86.20 164	98.85 205	95.27 121	99.05 104	98.82 146

BH-untuned		92.94 228	92.62 220	93.92 301	97.22 172	86.16 353	96.40 284	96.25 334	90.06 270	89.79 314	96.17 256	83.19 227	98.35 282	87.19 334	97.27 180	97.24 278

CL-MVSNet_self_test		86.31 407	85.15 404	89.80 427	88.83 461	81.74 423	93.93 416	96.22 335	86.67 374	85.03 418	90.80 439	78.09 338	94.50 455	74.92 448	71.86 464	93.15 435

IS-MVSNet		94.90 141	94.52 147	96.05 148	97.67 147	90.56 190	98.44 26	96.22 335	93.21 127	93.99 201	97.74 144	85.55 183	98.45 271	89.98 260	97.86 157	99.14 88

FA-MVS(test-final)		93.52 201	92.92 205	95.31 211	96.77 221	88.54 279	94.82 382	96.21 337	89.61 284	94.20 194	95.25 306	83.24 225	99.14 166	90.01 259	96.16 223	98.25 208

GA-MVS		91.38 299	90.31 312	94.59 252	94.65 371	87.62 311	94.34 401	96.19 338	90.73 242	90.35 294	93.83 378	71.84 393	97.96 332	87.22 333	93.61 288	98.21 211

LuminaMVS		94.89 142	94.35 155	96.53 105	95.48 316	92.80 91	96.88 229	96.18 339	92.85 152	95.92 132	96.87 215	81.44 271	98.83 208	96.43 77	97.10 187	97.94 237

IterMVS-SCA-FT		90.31 342	89.81 338	91.82 385	95.52 314	84.20 392	94.30 404	96.15 340	90.61 252	87.39 381	94.27 359	75.80 359	96.44 428	87.34 330	86.88 377	94.82 392

IterMVS		90.15 350	89.67 344	91.61 392	95.48 316	83.72 398	94.33 402	96.12 341	89.99 271	87.31 384	94.15 367	75.78 361	96.27 432	86.97 339	86.89 376	94.83 388
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 238	91.51 262	96.52 107	98.77 62	90.99 170	97.38 174	96.08 342	82.38 436	89.29 332	97.87 124	83.77 216	99.69 73	81.37 410	96.69 204	98.89 136

pmmvs4		90.93 324	89.85 336	94.17 278	93.34 418	90.79 182	94.60 387	96.02 343	84.62 408	87.45 378	95.15 309	81.88 265	97.45 394	87.70 315	87.87 363	94.27 418

ppachtmachnet_test		88.35 379	87.29 378	91.53 393	92.45 437	83.57 401	93.75 423	95.97 344	84.28 411	85.32 417	94.18 365	79.00 325	96.93 416	75.71 444	84.99 399	94.10 419

Anonymous20240521		86.42 404	85.44 399	89.34 434	90.33 449	79.79 445	96.73 250	95.92 345	83.71 421	83.25 436	91.36 436	63.92 451	96.01 433	78.39 432	85.36 390	92.22 452

ITE_SJBPF				92.43 363	95.34 328	85.37 373		95.92 345	91.47 207	87.75 374	96.39 245	71.00 399	97.96 332	82.36 400	89.86 340	93.97 424

test_fmvs2		89.77 361	89.93 333	89.31 435	93.68 402	76.37 463	97.64 133	95.90 347	89.84 277	91.49 269	96.26 252	58.77 461	97.10 408	94.65 152	91.13 323	94.46 409

USDC		88.94 370	87.83 375	92.27 370	94.66 370	84.96 382	93.86 419	95.90 347	87.34 363	83.40 434	95.56 291	67.43 429	98.19 295	82.64 398	89.67 342	93.66 428

COLMAP_ROB	87.81 15	90.40 341	89.28 354	93.79 306	97.95 129	87.13 325	96.92 223	95.89 349	82.83 429	86.88 397	97.18 191	73.77 379	99.29 146	78.44 431	93.62 287	94.95 375
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 189	93.08 198	96.02 151	97.88 135	89.96 217	97.72 118	95.85 350	92.43 169	95.86 134	98.44 64	68.42 425	99.39 134	96.31 79	94.85 254	98.71 163

VDDNet		93.05 222	92.07 237	96.02 151	96.84 207	90.39 198	98.08 58	95.85 350	86.22 384	95.79 137	98.46 62	67.59 428	99.19 154	94.92 132	94.85 254	98.47 185

mvsmamba		94.57 156	94.14 160	95.87 162	97.03 189	89.93 218	97.84 95	95.85 350	91.34 213	94.79 176	96.80 216	80.67 287	98.81 211	94.85 137	98.12 148	98.85 142

Vis-MVSNet (Re-imp)		94.15 169	93.88 166	94.95 233	97.61 155	87.92 303	98.10 56	95.80 353	92.22 177	93.02 230	97.45 171	84.53 203	97.91 344	88.24 300	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	95.76 354	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		84.81 422	82.64 425	91.31 399	91.07 446	85.34 374	91.22 457	95.75 355	85.56 393	83.09 437	90.21 444	67.21 431	95.89 435	77.18 438	62.48 482	92.69 440

miper_refine_blended		84.81 422	82.64 425	91.31 399	91.07 446	85.34 374	91.22 457	95.75 355	85.56 393	83.09 437	90.21 444	67.21 431	95.89 435	77.18 438	62.48 482	92.69 440

FE-MVS		92.05 266	91.05 278	95.08 220	96.83 209	87.93 302	93.91 418	95.70 357	86.30 381	94.15 198	94.97 315	76.59 351	99.21 152	84.10 379	96.86 195	98.09 227

tpm cat1		88.36 378	87.21 381	91.81 386	95.13 347	80.55 434	92.58 448	95.70 357	74.97 467	87.45 378	91.96 429	78.01 341	98.17 297	80.39 419	88.74 355	96.72 294

our_test_3		88.78 374	87.98 374	91.20 403	92.45 437	82.53 412	93.61 431	95.69 359	85.77 390	84.88 419	93.71 383	79.99 302	96.78 424	79.47 425	86.24 379	94.28 417

BH-w/o		92.14 263	91.75 251	93.31 334	96.99 194	85.73 363	95.67 337	95.69 359	88.73 320	89.26 334	94.82 325	82.97 236	98.07 313	85.26 366	96.32 222	96.13 312

CR-MVSNet		90.82 327	89.77 340	93.95 295	94.45 379	87.19 322	90.23 465	95.68 361	86.89 371	92.40 240	92.36 421	80.91 281	97.05 411	81.09 414	93.95 280	97.60 261

Patchmtry		88.64 376	87.25 379	92.78 356	94.09 389	86.64 335	89.82 469	95.68 361	80.81 448	87.63 376	92.36 421	80.91 281	97.03 412	78.86 429	85.12 395	94.67 404

testing91		91.90 271	91.02 279	94.53 260	96.54 246	86.55 341	95.86 325	95.64 363	91.77 195	91.89 259	93.47 398	69.94 410	98.86 203	90.23 258	93.86 282	98.18 213

BH-RMVSNet		92.72 240	91.97 243	94.97 231	97.16 176	87.99 301	96.15 309	95.60 364	90.62 251	91.87 260	97.15 194	78.41 332	98.57 262	83.16 388	97.60 164	98.36 197

PVSNet_0	82.17 19	85.46 417	83.64 420	90.92 407	95.27 335	79.49 451	90.55 463	95.60 364	83.76 420	83.00 439	89.95 446	71.09 398	97.97 328	82.75 396	60.79 484	95.31 355

guyue		95.17 127	94.96 123	95.82 168	96.97 196	89.65 228	97.56 144	95.58 366	94.82 57	95.72 139	97.42 175	82.90 238	98.84 207	96.71 67	96.93 192	98.96 114

SCA		91.84 273	91.18 275	93.83 303	95.59 310	84.95 383	94.72 384	95.58 366	90.82 238	92.25 248	93.69 385	75.80 359	98.10 304	86.20 348	95.98 225	98.45 187

MonoMVSNet		91.92 269	91.77 249	92.37 364	92.94 425	83.11 406	97.09 206	95.55 368	92.91 148	90.85 286	94.55 338	81.27 275	96.52 427	93.01 197	87.76 364	97.47 267

usedtu_blend_shiyan5		87.06 395	84.84 409	93.69 312	88.54 467	88.70 272	95.83 327	95.54 369	78.74 458	85.92 409	86.89 472	73.03 385	97.55 381	87.73 310	71.36 466	94.83 388

AllTest		90.23 346	88.98 360	93.98 291	97.94 130	86.64 335	96.51 273	95.54 369	85.38 395	85.49 414	96.77 218	70.28 405	99.15 163	80.02 421	92.87 292	96.15 310

TestCases				93.98 291	97.94 130	86.64 335		95.54 369	85.38 395	85.49 414	96.77 218	70.28 405	99.15 163	80.02 421	92.87 292	96.15 310

mmtdpeth		89.70 363	88.96 361	91.90 381	95.84 302	84.42 388	97.46 164	95.53 372	90.27 264	94.46 187	90.50 440	69.74 414	98.95 193	97.39 53	69.48 472	92.34 448

tpmvs		89.83 360	89.15 358	91.89 382	94.92 357	80.30 438	93.11 440	95.46 373	86.28 382	88.08 368	92.65 411	80.44 293	98.52 266	81.47 406	89.92 339	96.84 290

pmmvs5		89.86 359	88.87 364	92.82 353	92.86 427	86.23 349	96.26 298	95.39 374	84.24 412	87.12 386	94.51 341	74.27 374	97.36 401	87.61 324	87.57 366	94.86 384

PatchmatchNet		91.91 270	91.35 264	93.59 321	95.38 323	84.11 393	93.15 439	95.39 374	89.54 286	92.10 253	93.68 387	82.82 241	98.13 299	84.81 370	95.32 246	98.52 177
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 296	91.32 266	91.79 387	95.15 345	79.20 454	93.42 434	95.37 376	88.55 325	93.49 219	93.67 388	82.49 250	98.27 288	90.41 253	89.34 345	97.90 239

Anonymous20231206		87.09 394	86.14 393	89.93 426	91.22 445	80.35 436	96.11 310	95.35 377	83.57 423	84.16 426	93.02 406	73.54 383	95.61 443	72.16 461	86.14 381	93.84 426

MIMVSNet1		84.93 420	83.05 422	90.56 416	89.56 455	84.84 385	95.40 353	95.35 377	83.91 415	80.38 451	92.21 426	57.23 464	93.34 469	70.69 467	82.75 426	93.50 430

TDRefinement		86.53 400	84.76 411	91.85 383	82.23 484	84.25 390	96.38 286	95.35 377	84.97 404	84.09 429	94.94 317	65.76 444	98.34 285	84.60 374	74.52 457	92.97 436

TR-MVS		91.48 295	90.59 303	94.16 281	96.40 261	87.33 315	95.67 337	95.34 380	87.68 355	91.46 270	95.52 294	76.77 350	98.35 282	82.85 393	93.61 288	96.79 292

EPNet_dtu		91.71 276	91.28 269	92.99 346	93.76 399	83.71 399	96.69 256	95.28 381	93.15 134	87.02 391	95.95 267	83.37 224	97.38 400	79.46 426	96.84 196	97.88 241
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 390	85.79 395	91.78 388	94.80 364	87.28 317	95.49 349	95.28 381	84.09 414	83.85 433	91.82 430	62.95 454	94.17 460	78.48 430	85.34 391	93.91 425

MDTV_nov1_ep13			90.76 291		95.22 339	80.33 437	93.03 442	95.28 381	88.14 338	92.84 237	93.83 378	81.34 272	98.08 309	82.86 391	94.34 265

LF4IMVS		87.94 382	87.25 379	89.98 424	92.38 439	80.05 444	94.38 399	95.25 384	87.59 357	84.34 423	94.74 329	64.31 450	97.66 370	84.83 369	87.45 367	92.23 451

TransMVSNet (Re)		88.94 370	87.56 376	93.08 344	94.35 382	88.45 285	97.73 115	95.23 385	87.47 359	84.26 425	95.29 301	79.86 305	97.33 402	79.44 427	74.44 458	93.45 432

test20.03		86.14 410	85.40 401	88.35 438	90.12 450	80.06 443	95.90 324	95.20 386	88.59 321	81.29 446	93.62 390	71.43 396	92.65 473	71.26 465	81.17 431	92.34 448

new-patchmatchnet		83.18 429	81.87 432	87.11 446	86.88 475	75.99 465	93.70 425	95.18 387	85.02 403	77.30 464	88.40 458	65.99 442	93.88 465	74.19 453	70.18 470	91.47 463

MDA-MVSNet_test_wron		85.87 414	84.23 417	90.80 413	92.38 439	82.57 411	93.17 437	95.15 388	82.15 437	67.65 477	92.33 424	78.20 334	95.51 447	77.33 435	79.74 435	94.31 416

YYNet1		85.87 414	84.23 417	90.78 414	92.38 439	82.46 416	93.17 437	95.14 389	82.12 438	67.69 475	92.36 421	78.16 337	95.50 448	77.31 436	79.73 436	94.39 412

Baseline_NR-MVSNet		91.20 311	90.62 301	92.95 348	93.83 397	88.03 300	97.01 213	95.12 390	88.42 329	89.70 317	95.13 311	83.47 221	97.44 395	89.66 270	83.24 421	93.37 433

thres200		92.23 259	91.39 263	94.75 246	97.61 155	89.03 261	96.60 268	95.09 391	92.08 186	93.28 225	94.00 374	78.39 333	99.04 189	81.26 413	94.18 271	96.19 306

ADS-MVSNet		89.89 356	88.68 366	93.53 325	95.86 297	84.89 384	90.93 460	95.07 392	83.23 427	91.28 279	91.81 431	79.01 323	97.85 347	79.52 423	91.39 319	97.84 246

pmmvs-eth3d		86.22 408	84.45 415	91.53 393	88.34 469	87.25 319	94.47 394	95.01 393	83.47 424	79.51 456	89.61 450	69.75 413	95.71 440	83.13 389	76.73 450	91.64 457

Anonymous202405211		92.07 265	90.83 289	95.76 177	98.19 109	88.75 270	97.58 140	95.00 394	86.00 387	93.64 211	97.45 171	66.24 440	99.53 112	90.68 247	92.71 297	99.01 106

MDA-MVSNet-bldmvs		85.00 419	82.95 424	91.17 405	93.13 423	83.33 402	94.56 389	95.00 394	84.57 409	65.13 481	92.65 411	70.45 404	95.85 437	73.57 456	77.49 445	94.33 414

ambc				86.56 449	83.60 481	70.00 476	85.69 481	94.97 396		80.60 450	88.45 457	37.42 483	96.84 421	82.69 397	75.44 455	92.86 438

testgi		87.97 381	87.21 381	90.24 421	92.86 427	80.76 429	96.67 259	94.97 396	91.74 196	85.52 413	95.83 273	62.66 456	94.47 457	76.25 442	88.36 359	95.48 338

myMVS_eth3d28		91.52 292	90.97 281	93.17 340	96.91 199	83.24 404	95.61 343	94.96 398	92.24 176	91.98 256	93.28 403	69.31 415	98.40 274	88.71 295	95.68 235	97.88 241

dp		88.90 372	88.26 372	90.81 411	94.58 375	76.62 462	92.85 445	94.93 399	85.12 401	90.07 308	93.07 405	75.81 358	98.12 302	80.53 418	87.42 369	97.71 253

test_fmvs3		83.21 428	83.02 423	83.78 453	86.77 476	68.34 479	96.76 248	94.91 400	86.49 377	84.14 428	89.48 451	36.04 484	91.73 475	91.86 218	80.77 433	91.26 465

test_0402		86.46 403	84.79 410	91.45 395	95.02 351	85.55 365	96.29 297	94.89 401	80.90 445	82.21 442	93.97 376	68.21 426	97.29 404	62.98 476	88.68 356	91.51 460

tfpn200view9		92.38 249	91.52 260	94.95 233	97.85 136	89.29 250	97.41 167	94.88 402	92.19 182	93.27 226	94.46 346	78.17 335	99.08 177	81.40 407	94.08 275	96.48 299

CVMVSNet		91.23 309	91.75 251	89.67 428	95.77 303	74.69 466	96.44 274	94.88 402	85.81 389	92.18 249	97.64 157	79.07 318	95.58 445	88.06 303	95.86 230	98.74 160

thres400		92.42 247	91.52 260	95.12 219	97.85 136	89.29 250	97.41 167	94.88 402	92.19 182	93.27 226	94.46 346	78.17 335	99.08 177	81.40 407	94.08 275	96.98 284

tt0320		85.39 418	83.12 421	92.19 374	93.44 415	85.79 361	96.19 306	94.87 405	71.19 475	82.92 440	91.76 433	58.43 462	96.81 422	81.03 415	78.26 444	93.98 423

EPNet		95.20 123	94.56 143	97.14 75	92.80 429	92.68 97	97.85 94	94.87 405	96.64 9	92.46 239	97.80 138	86.23 161	99.65 79	93.72 176	98.62 124	99.10 95
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 283	90.72 296	94.32 271	96.48 255	86.11 358	95.81 329	94.76 407	91.55 200	91.75 264	93.44 399	68.55 423	98.82 209	90.43 252	93.69 284	98.04 231

sc_t1		86.48 402	84.10 419	93.63 318	93.45 414	85.76 362	96.79 242	94.71 408	73.06 472	86.45 401	94.35 351	55.13 469	97.95 336	84.38 377	78.55 443	97.18 280

SixPastTwentyTwo		89.15 368	88.54 368	90.98 406	93.49 411	80.28 440	96.70 254	94.70 409	90.78 239	84.15 427	95.57 290	71.78 394	97.71 364	84.63 373	85.07 396	94.94 377

thres100view900		92.43 246	91.58 257	94.98 229	97.92 132	89.37 246	97.71 120	94.66 410	92.20 180	93.31 224	94.90 320	78.06 339	99.08 177	81.40 407	94.08 275	96.48 299

thres600view7		92.49 244	91.60 256	95.18 215	97.91 133	89.47 240	97.65 129	94.66 410	92.18 184	93.33 223	94.91 319	78.06 339	99.10 171	81.61 403	94.06 279	96.98 284

PatchT		88.87 373	87.42 377	93.22 338	94.08 390	85.10 378	89.51 470	94.64 412	81.92 439	92.36 243	88.15 461	80.05 301	97.01 414	72.43 460	93.65 286	97.54 264

baseline1		92.82 236	91.90 246	95.55 193	97.20 174	90.77 183	97.19 198	94.58 413	92.20 180	92.36 243	96.34 247	84.16 211	98.21 292	89.20 285	83.90 416	97.68 255

AstraMVS		94.82 148	94.64 139	95.34 210	96.36 266	88.09 299	97.58 140	94.56 414	94.98 46	95.70 142	97.92 114	81.93 264	98.93 196	96.87 61	95.88 228	98.99 110

UBG		91.55 289	90.76 291	93.94 297	96.52 251	85.06 379	95.22 366	94.54 415	90.47 260	91.98 256	92.71 410	72.02 391	98.74 233	88.10 302	95.26 248	98.01 233

Gipuma		67.86 450	65.41 452	75.18 466	92.66 432	73.45 470	66.50 488	94.52 416	53.33 486	57.80 487	66.07 487	30.81 486	89.20 479	48.15 485	78.88 442	62.90 487
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 279	90.75 293	94.47 262	96.53 248	86.56 340	95.76 333	94.51 417	91.10 231	91.24 281	93.59 393	68.59 422	98.86 203	91.10 235	94.29 267	98.00 234

CostFormer		91.18 314	90.70 297	92.62 361	94.84 362	81.76 422	94.09 411	94.43 418	84.15 413	92.72 238	93.77 382	79.43 312	98.20 293	90.70 246	92.18 306	97.90 239

tpm2		89.96 353	89.21 356	92.23 373	94.91 359	81.25 425	93.78 422	94.42 419	80.62 450	91.56 267	93.44 399	76.44 354	97.94 338	85.60 360	92.08 310	97.49 265

testing3-2		92.10 264	92.05 238	92.27 370	97.71 145	79.56 448	97.42 166	94.41 420	93.53 113	93.22 228	95.49 295	69.16 417	99.11 169	93.25 187	94.22 269	98.13 218

MGCNet		96.74 64	96.31 81	98.02 20	96.87 203	94.65 31	97.58 140	94.39 421	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		88.26 380	87.04 384	91.91 380	93.52 409	81.42 424	89.38 471	94.38 422	80.84 447	90.93 285	80.74 479	79.22 315	97.92 341	82.76 395	91.62 314	96.38 302

dmvs_re		90.21 347	89.50 349	92.35 365	95.47 320	85.15 376	95.70 336	94.37 423	90.94 237	88.42 355	93.57 394	74.63 371	95.67 442	82.80 394	89.57 343	96.22 304

Patchmatch-test		89.42 366	87.99 373	93.70 311	95.27 335	85.11 377	88.98 472	94.37 423	81.11 444	87.10 389	93.69 385	82.28 254	97.50 390	74.37 451	94.76 258	98.48 184

LCM-MVSNet		72.55 443	69.39 447	82.03 455	70.81 495	65.42 484	90.12 467	94.36 425	55.02 485	65.88 479	81.72 478	24.16 492	89.96 476	74.32 452	68.10 476	90.71 468

ADS-MVSNet2		89.45 365	88.59 367	92.03 377	95.86 297	82.26 418	90.93 460	94.32 426	83.23 427	91.28 279	91.81 431	79.01 323	95.99 434	79.52 423	91.39 319	97.84 246

mvs5depth		86.53 400	85.08 405	90.87 408	88.74 465	82.52 413	91.91 453	94.23 427	86.35 380	87.11 388	93.70 384	66.52 436	97.76 359	81.37 410	75.80 452	92.31 450

EU-MVSNet		88.72 375	88.90 363	88.20 440	93.15 422	74.21 468	96.63 265	94.22 428	85.18 399	87.32 383	95.97 265	76.16 356	94.98 452	85.27 365	86.17 380	95.41 345

usedtu_dtu_shiyan2		80.00 436	76.91 442	89.27 436	82.13 485	79.69 447	95.45 351	94.20 429	72.95 473	75.80 465	87.75 464	44.44 479	94.30 459	70.64 468	68.81 475	93.84 426

tt0320-xc		84.83 421	82.33 429	92.31 368	93.66 403	86.20 351	96.17 308	94.06 430	71.26 474	82.04 444	92.22 425	55.07 470	96.72 425	81.49 405	75.04 456	94.02 422

MIMVSNet		88.50 377	86.76 387	93.72 310	94.84 362	87.77 309	91.39 455	94.05 431	86.41 379	87.99 370	92.59 414	63.27 452	95.82 439	77.44 434	92.84 294	97.57 263

OpenMVS_ROB	81.14 20	84.42 424	82.28 430	90.83 409	90.06 451	84.05 395	95.73 335	94.04 432	73.89 470	80.17 454	91.53 435	59.15 460	97.64 371	66.92 474	89.05 349	90.80 467

TinyColmap		86.82 398	85.35 402	91.21 401	94.91 359	82.99 408	93.94 415	94.02 433	83.58 422	81.56 445	94.68 331	62.34 457	98.13 299	75.78 443	87.35 372	92.52 446

ETVMVS		90.52 338	89.14 359	94.67 249	96.81 213	87.85 307	95.91 323	93.97 434	89.71 280	92.34 246	92.48 416	65.41 446	97.96 332	81.37 410	94.27 268	98.21 211

IB-MVS	87.33 17	89.91 354	88.28 371	94.79 243	95.26 338	87.70 310	95.12 374	93.95 435	89.35 294	87.03 390	92.49 415	70.74 402	99.19 154	89.18 286	81.37 430	97.49 265
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		87.13 393	87.02 385	87.47 444	95.16 342	73.21 472	95.00 376	93.93 436	88.55 325	86.96 392	91.99 427	75.90 357	94.00 462	61.59 478	94.11 272	95.20 363

myMVS_eth3d		87.18 392	86.38 390	89.58 429	95.16 342	79.53 449	95.00 376	93.93 436	88.55 325	86.96 392	91.99 427	56.23 467	94.00 462	75.47 447	94.11 272	95.20 363

testing222		90.31 342	88.96 361	94.35 268	96.54 246	87.29 316	95.50 348	93.84 438	90.97 234	91.75 264	92.96 407	62.18 458	98.00 323	82.86 391	94.08 275	97.76 251

test_f		80.57 435	79.62 437	83.41 454	83.38 482	67.80 481	93.57 432	93.72 439	80.80 449	77.91 463	87.63 467	33.40 485	92.08 474	87.14 337	79.04 441	90.34 469

LCM-MVSNet-Re		92.50 242	92.52 226	92.44 362	96.82 211	81.89 421	96.92 223	93.71 440	92.41 170	84.30 424	94.60 336	85.08 192	97.03 412	91.51 226	97.36 173	98.40 193

tpm		90.25 345	89.74 343	91.76 390	93.92 393	79.73 446	93.98 412	93.54 441	88.28 332	91.99 255	93.25 404	77.51 345	97.44 395	87.30 332	87.94 362	98.12 220

ET-MVSNet_ETH3D		91.49 294	90.11 323	95.63 187	96.40 261	91.57 142	95.34 356	93.48 442	90.60 254	75.58 467	95.49 295	80.08 300	96.79 423	94.25 164	89.76 341	98.52 177

LFMVS		93.60 196	92.63 219	96.52 107	98.13 115	91.27 155	97.94 81	93.39 443	90.57 256	96.29 116	98.31 81	69.00 418	99.16 161	94.18 165	95.87 229	99.12 92

MVStest1		82.38 432	80.04 436	89.37 432	87.63 473	82.83 409	95.03 375	93.37 444	73.90 469	73.50 472	94.35 351	62.89 455	93.25 471	73.80 454	65.92 479	92.04 456

FE-MVSNET		83.85 425	81.97 431	89.51 430	87.19 474	83.19 405	95.21 368	93.17 445	83.45 425	78.90 459	89.05 454	65.46 445	93.84 466	69.71 470	75.56 454	91.51 460

Patchmatch-RL test		87.38 389	86.24 391	90.81 411	88.74 465	78.40 458	88.12 479	93.17 445	87.11 368	82.17 443	89.29 452	81.95 262	95.60 444	88.64 297	77.02 447	98.41 192

ttmdpeth		85.91 413	84.76 411	89.36 433	89.14 457	80.25 441	95.66 340	93.16 447	83.77 419	83.39 435	95.26 305	66.24 440	95.26 451	80.65 416	75.57 453	92.57 443

test-LLR		91.42 297	91.19 274	92.12 375	94.59 373	80.66 431	94.29 405	92.98 448	91.11 229	90.76 288	92.37 418	79.02 321	98.07 313	88.81 292	96.74 201	97.63 256

test-mter		90.19 349	89.54 348	92.12 375	94.59 373	80.66 431	94.29 405	92.98 448	87.68 355	90.76 288	92.37 418	67.67 427	98.07 313	88.81 292	96.74 201	97.63 256

WB-MVSnew		89.88 357	89.56 347	90.82 410	94.57 376	83.06 407	95.65 341	92.85 450	87.86 346	90.83 287	94.10 368	79.66 309	96.88 419	76.34 441	94.19 270	92.54 445

testing3		87.67 385	86.88 386	90.05 423	96.14 284	80.71 430	97.10 205	92.85 450	90.15 268	87.54 377	94.55 338	55.70 468	94.10 461	73.77 455	94.10 274	95.35 352

test_method		66.11 451	64.89 453	69.79 469	72.62 493	35.23 501	65.19 489	92.83 452	20.35 491	65.20 480	88.08 462	43.14 481	82.70 486	73.12 458	63.46 481	91.45 464

test0.0.03 1		89.37 367	88.70 365	91.41 397	92.47 436	85.63 364	95.22 366	92.70 453	91.11 229	86.91 396	93.65 389	79.02 321	93.19 472	78.00 433	89.18 346	95.41 345

new_pmnet		82.89 430	81.12 435	88.18 441	89.63 454	80.18 442	91.77 454	92.57 454	76.79 465	75.56 468	88.23 460	61.22 459	94.48 456	71.43 463	82.92 424	89.87 470

mvsany_test1		93.93 185	93.98 164	93.78 307	94.94 356	86.80 331	94.62 386	92.55 455	88.77 319	96.85 84	98.49 58	88.98 101	98.08 309	95.03 127	95.62 237	96.46 301

thisisatest0515		92.29 255	91.30 268	95.25 213	96.60 234	88.90 268	94.36 400	92.32 456	87.92 342	93.43 221	94.57 337	77.28 346	99.00 190	89.42 276	95.86 230	97.86 245

thisisatest0530		93.03 223	92.21 235	95.49 202	97.07 181	89.11 259	97.49 161	92.19 457	90.16 267	94.09 199	96.41 243	76.43 355	99.05 186	90.38 254	95.68 235	98.31 205

tttt0517		92.96 226	92.33 232	94.87 236	97.11 179	87.16 324	97.97 77	92.09 458	90.63 250	93.88 205	97.01 207	76.50 352	99.06 183	90.29 257	95.45 244	98.38 195

K. test v3		87.64 386	86.75 388	90.32 420	93.02 424	79.48 452	96.61 266	92.08 459	90.66 248	80.25 453	94.09 370	67.21 431	96.65 426	85.96 356	80.83 432	94.83 388

TESTMET0.1,1		90.06 351	89.42 351	91.97 378	94.41 381	80.62 433	94.29 405	91.97 460	87.28 365	90.44 292	92.47 417	68.79 419	97.67 366	88.50 299	96.60 208	97.61 260

PM-MVS		83.48 427	81.86 433	88.31 439	87.83 471	77.59 460	93.43 433	91.75 461	86.91 370	80.63 449	89.91 447	44.42 480	95.84 438	85.17 368	76.73 450	91.50 462

baseline2		91.63 282	90.86 285	93.94 297	94.33 383	86.32 346	95.92 322	91.64 462	89.37 293	86.94 394	94.69 330	81.62 269	98.69 243	88.64 297	94.57 263	96.81 291

APD_test1		79.31 438	77.70 440	84.14 452	89.11 459	69.07 478	92.36 452	91.50 463	69.07 477	73.87 470	92.63 413	39.93 482	94.32 458	70.54 469	80.25 434	89.02 472

FPMVS		71.27 444	69.85 446	75.50 465	74.64 490	59.03 490	91.30 456	91.50 463	58.80 482	57.92 486	88.28 459	29.98 488	85.53 485	53.43 483	82.84 425	81.95 478

door								91.13 465

door-mid								91.06 466

EGC-MVSNET		68.77 449	63.01 455	86.07 451	92.49 435	82.24 419	93.96 414	90.96 467	0.71 496	2.62 497	90.89 438	53.66 471	93.46 467	57.25 481	84.55 406	82.51 477

mvsany_test3		83.59 426	82.44 428	87.03 447	83.80 479	73.82 469	93.70 425	90.92 468	86.42 378	82.51 441	90.26 443	46.76 478	95.71 440	90.82 241	76.76 449	91.57 459

pmmvs3		79.97 437	77.50 441	87.39 445	82.80 483	79.38 453	92.70 447	90.75 469	70.69 476	78.66 460	87.47 469	51.34 474	93.40 468	73.39 457	69.65 471	89.38 471

UWE-MVS		89.91 354	89.48 350	91.21 401	95.88 296	78.23 459	94.91 379	90.26 470	89.11 300	92.35 245	94.52 340	68.76 420	97.96 332	83.95 383	95.59 238	97.42 269

DSMNet-mixed		86.34 406	86.12 394	87.00 448	89.88 453	70.43 474	94.93 378	90.08 471	77.97 462	85.42 416	92.78 409	74.44 373	93.96 464	74.43 450	95.14 249	96.62 295

MVS-HIRNet		82.47 431	81.21 434	86.26 450	95.38 323	69.21 477	88.96 473	89.49 472	66.28 479	80.79 448	74.08 484	68.48 424	97.39 399	71.93 462	95.47 243	92.18 453

WB-MVS		76.77 440	76.63 443	77.18 460	85.32 477	56.82 492	94.53 390	89.39 473	82.66 435	71.35 473	89.18 453	75.03 366	88.88 480	35.42 489	66.79 477	85.84 474

test1111		93.19 215	92.82 209	94.30 274	97.58 161	84.56 387	98.21 47	89.02 474	93.53 113	94.58 181	98.21 88	72.69 387	99.05 186	93.06 193	98.48 131	99.28 77

SSC-MVS		76.05 441	75.83 444	76.72 464	84.77 478	56.22 493	94.32 403	88.96 475	81.82 441	70.52 474	88.91 455	74.79 370	88.71 481	33.69 490	64.71 480	85.23 475

ECVR-MVS		93.19 215	92.73 215	94.57 257	97.66 149	85.41 370	98.21 47	88.23 476	93.43 120	94.70 178	98.21 88	72.57 388	99.07 181	93.05 194	98.49 129	99.25 80

EPMVS		90.70 332	89.81 338	93.37 332	94.73 368	84.21 391	93.67 428	88.02 477	89.50 288	92.38 242	93.49 396	77.82 343	97.78 356	86.03 354	92.68 298	98.11 226

ANet_high		63.94 453	59.58 456	77.02 461	61.24 497	66.06 482	85.66 482	87.93 478	78.53 460	42.94 489	71.04 486	25.42 491	80.71 488	52.60 484	30.83 490	84.28 476

PMMVS2		70.19 445	66.92 449	80.01 456	76.35 489	65.67 483	86.22 480	87.58 479	64.83 481	62.38 482	80.29 481	26.78 490	88.49 483	63.79 475	54.07 486	85.88 473

lessismore_v0				90.45 417	91.96 442	79.09 456		87.19 480		80.32 452	94.39 348	66.31 439	97.55 381	84.00 382	76.84 448	94.70 403

PMVS	53.92 22	58.58 454	55.40 457	68.12 470	51.00 498	48.64 495	78.86 485	87.10 481	46.77 487	35.84 493	74.28 483	8.76 496	86.34 484	42.07 487	73.91 459	69.38 484
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 399	86.41 389	88.02 442	92.87 426	74.60 467	95.38 355	86.70 482	88.17 335	87.28 385	94.67 333	70.83 401	93.30 470	67.45 472	94.31 266	96.17 307

test_vis1_rt		86.16 409	85.06 406	89.46 431	93.47 413	80.46 435	96.41 280	86.61 483	85.22 398	79.15 458	88.64 456	52.41 473	97.06 410	93.08 192	90.57 332	90.87 466

testf1		69.31 447	66.76 450	76.94 462	78.61 487	61.93 486	88.27 477	86.11 484	55.62 483	59.69 483	85.31 475	20.19 494	89.32 477	57.62 479	69.44 473	79.58 479

APD_test2		69.31 447	66.76 450	76.94 462	78.61 487	61.93 486	88.27 477	86.11 484	55.62 483	59.69 483	85.31 475	20.19 494	89.32 477	57.62 479	69.44 473	79.58 479

gg-mvs-nofinetune		87.82 383	85.61 396	94.44 264	94.46 378	89.27 253	91.21 459	84.61 486	80.88 446	89.89 312	74.98 482	71.50 395	97.53 387	85.75 359	97.21 182	96.51 297

dmvs_testset		81.38 434	82.60 427	77.73 459	91.74 443	51.49 494	93.03 442	84.21 487	89.07 301	78.28 462	91.25 437	76.97 348	88.53 482	56.57 482	82.24 427	93.16 434

GG-mvs-BLEND				93.62 319	93.69 401	89.20 255	92.39 451	83.33 488		87.98 371	89.84 448	71.00 399	96.87 420	82.08 402	95.40 245	94.80 395

MTMP							97.86 91	82.03 489

DeepMVS_CX				74.68 467	90.84 448	64.34 485		81.61 490	65.34 480	67.47 478	88.01 463	48.60 477	80.13 489	62.33 477	73.68 460	79.58 479

E-PMN		53.28 455	52.56 459	55.43 473	74.43 491	47.13 496	83.63 484	76.30 491	42.23 488	42.59 490	62.22 489	28.57 489	74.40 490	31.53 491	31.51 489	44.78 488

test2506		91.60 284	90.78 290	94.04 287	97.66 149	83.81 396	98.27 37	75.53 492	93.43 120	95.23 159	98.21 88	67.21 431	99.07 181	93.01 197	98.49 129	99.25 80

EMVS		52.08 457	51.31 460	54.39 474	72.62 493	45.39 498	83.84 483	75.51 493	41.13 489	40.77 491	59.65 490	30.08 487	73.60 491	28.31 493	29.90 491	44.18 489

test_vis3_rt		72.73 442	70.55 445	79.27 457	80.02 486	68.13 480	93.92 417	74.30 494	76.90 464	58.99 485	73.58 485	20.29 493	95.37 449	84.16 378	72.80 462	74.31 482

MVE	50.73 23	53.25 456	48.81 461	66.58 472	65.34 496	57.50 491	72.49 487	70.94 495	40.15 490	39.28 492	63.51 488	6.89 498	73.48 492	38.29 488	42.38 488	68.76 486
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 458	53.82 458	46.29 475	33.73 499	45.30 499	78.32 486	67.24 496	18.02 492	50.93 488	87.05 471	52.99 472	53.11 494	70.76 466	25.29 492	40.46 490

kuosan		65.27 452	64.66 454	67.11 471	83.80 479	61.32 489	88.53 476	60.77 497	68.22 478	67.67 476	80.52 480	49.12 476	70.76 493	29.67 492	53.64 487	69.26 485

dongtai		69.99 446	69.33 448	71.98 468	88.78 462	61.64 488	89.86 468	59.93 498	75.67 466	74.96 469	85.45 474	50.19 475	81.66 487	43.86 486	55.27 485	72.63 483

N_pmnet		78.73 439	78.71 439	78.79 458	92.80 429	46.50 497	94.14 409	43.71 499	78.61 459	80.83 447	91.66 434	74.94 369	96.36 430	67.24 473	84.45 408	93.50 430

wuyk23d		25.11 459	24.57 463	26.74 476	73.98 492	39.89 500	57.88 490	9.80 500	12.27 493	10.39 494	6.97 496	7.03 497	36.44 495	25.43 494	17.39 493	3.89 493

testmvs		13.36 461	16.33 464	4.48 478	5.04 500	2.26 503	93.18 436	3.28 501	2.70 494	8.24 495	21.66 492	2.29 500	2.19 496	7.58 495	2.96 494	9.00 492

test123		13.04 462	15.66 465	5.18 477	4.51 501	3.45 502	92.50 450	1.81 502	2.50 495	7.58 496	20.15 493	3.67 499	2.18 497	7.13 496	1.07 495	9.90 491

mmdepth		0.00 465	0.00 468	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	0.00 497	0.00 501	0.00 498	0.00 497	0.00 496	0.00 494

monomultidepth		0.00 465	0.00 468	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	0.00 497	0.00 501	0.00 498	0.00 497	0.00 496	0.00 494

test_blank		0.00 465	0.00 468	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	0.00 497	0.00 501	0.00 498	0.00 497	0.00 496	0.00 494

uanet_test		0.00 465	0.00 468	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	0.00 497	0.00 501	0.00 498	0.00 497	0.00 496	0.00 494

DCPMVS		0.00 465	0.00 468	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	0.00 497	0.00 501	0.00 498	0.00 497	0.00 496	0.00 494

pcd_1.5k_mvsjas		7.39 464	9.85 467	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	0.00 497	88.65 109	0.00 498	0.00 497	0.00 496	0.00 494

sosnet-low-res		0.00 465	0.00 468	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	0.00 497	0.00 501	0.00 498	0.00 497	0.00 496	0.00 494

sosnet		0.00 465	0.00 468	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	0.00 497	0.00 501	0.00 498	0.00 497	0.00 496	0.00 494

uncertanet		0.00 465	0.00 468	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	0.00 497	0.00 501	0.00 498	0.00 497	0.00 496	0.00 494

Regformer		0.00 465	0.00 468	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	0.00 497	0.00 501	0.00 498	0.00 497	0.00 496	0.00 494

n2								0.00 503

nn								0.00 503

ab-mvs-re		8.06 463	10.74 466	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	96.69 224	0.00 501	0.00 498	0.00 497	0.00 496	0.00 494

uanet		0.00 465	0.00 468	0.00 479	0.00 502	0.00 504	0.00 491	0.00 503	0.00 497	0.00 498	0.00 497	0.00 501	0.00 498	0.00 497	0.00 496	0.00 494

TestfortrainingZip							98.69 11

WAC-MVS						79.53 449								75.56 446

PC_three_1452									90.77 240	98.89 26	98.28 86	96.24 1	98.35 282	95.76 106	99.58 23	99.59 32

eth-test2					0.00 502

eth-test					0.00 502

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																98.45 187

test_part2					99.28 30	95.74 9				98.10 48

sam_mvs1												82.76 242				98.45 187

sam_mvs												81.94 263

test_post1							92.81 446				16.58 495	80.53 291	97.68 365	86.20 348

test_post											17.58 494	81.76 266	98.08 309

patchmatchnet-post											90.45 442	82.65 247	98.10 304

gm-plane-assit					93.22 420	78.89 457			84.82 406		93.52 395		98.64 252	87.72 312

test9_res														94.81 143	99.38 64	99.45 59

agg_prior2														93.94 170	99.38 64	99.50 52

test_prior4						93.66 62	96.42 279

test_prior2							96.35 289		92.80 155	96.03 126	97.59 163	92.01 50		95.01 128	99.38 64

旧先验2							95.94 320		81.66 442	97.34 70			98.82 209	92.26 203

新几何2							95.79 331

原ACMM2							95.67 337

testdata2													99.67 77	85.96 356

segment_acmp												92.89 33

testdata1							95.26 364		93.10 137

plane_prior7					96.21 271	89.98 214

plane_prior6					96.10 289	90.00 210						81.32 273

plane_prior4											96.64 227

plane_prior3						90.00 210			94.46 78	91.34 273

plane_prior2							97.74 113		94.85 53

plane_prior1					96.14 284

plane_prior						89.99 212	97.24 190		94.06 92						92.16 307

HQP5-MVS						89.33 248

HQP-NCC					95.86 297		96.65 260		93.55 109	90.14 297

ACMP_Plane					95.86 297		96.65 260		93.55 109	90.14 297

BP-MVS														92.13 211

HQP4-MVS										90.14 297			98.50 267			95.78 326

HQP2-MVS												80.95 279

NP-MVS					95.99 295	89.81 222					95.87 270

MDTV_nov1_ep13_2view						70.35 475	93.10 441		83.88 417	93.55 214		82.47 251		86.25 347		98.38 195

ACMMP++_ref															90.30 337

ACMMP++															91.02 326

Test By Simon												88.73 108

High-resolution multi-view benchmark