High-res multi-view results

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

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

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

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

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

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

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

test_fmvsm_n_1920		97.55 16	97.89 4	96.53 106	98.41 87	91.73 132	98.01 67	99.02 1	96.37 13	99.30 7	98.92 25	92.39 45	99.79 47	99.16 14	99.46 46	98.08 238

PGM-MVS		96.81 58	96.53 69	97.65 48	99.35 25	93.53 67	97.65 131	98.98 2	92.22 185	97.14 78	98.44 64	91.17 72	99.85 22	94.35 171	99.46 46	99.57 36

MVS_111021_HR		96.68 69	96.58 68	96.99 85	98.46 81	92.31 112	96.20 311	98.90 3	94.30 88	95.86 138	97.74 149	92.33 46	99.38 138	96.04 98	99.42 56	99.28 77

test_fmvsmconf_n		97.49 21	97.56 16	97.29 65	97.44 166	92.37 109	97.91 86	98.88 4	95.83 19	98.92 24	99.05 14	91.45 62	99.80 41	99.12 16	99.46 46	99.69 15

lecture		97.58 15	97.63 11	97.43 59	99.37 19	92.93 88	98.86 7	98.85 5	95.27 36	98.65 36	98.90 27	91.97 53	99.80 41	97.63 38	99.21 83	99.57 36

ACMMP		96.27 86	95.93 88	97.28 67	99.24 34	92.62 100	98.25 40	98.81 6	92.99 145	94.56 192	98.39 68	88.96 103	99.85 22	94.57 165	97.63 165	99.36 72
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MVS_111021_LR		96.24 87	96.19 85	96.39 125	98.23 107	91.35 155	96.24 308	98.79 7	93.99 98	95.80 140	97.65 160	89.92 92	99.24 152	95.87 102	99.20 88	98.58 181

patch_mono-2		96.83 57	97.44 24	95.01 234	99.05 46	85.39 389	96.98 222	98.77 8	94.70 68	97.99 52	98.66 45	93.61 21	99.91 1	97.67 37	99.50 40	99.72 14

fmvsm_s_conf0.5_n		96.85 54	97.13 31	96.04 152	98.07 122	90.28 208	97.97 78	98.76 9	94.93 50	98.84 29	99.06 12	88.80 107	99.65 80	99.06 18	98.63 124	98.18 223

fmvsm_l_conf0.5_n		97.65 9	97.75 8	97.34 62	98.21 108	92.75 94	97.83 99	98.73 10	95.04 47	99.30 7	98.84 38	93.34 26	99.78 50	99.32 7	99.13 97	99.50 52

fmvsm_s_conf0.5_n_a		96.75 62	96.93 46	96.20 141	97.64 152	90.72 189	98.00 68	98.73 10	94.55 75	98.91 25	99.08 8	88.22 119	99.63 89	98.91 21	98.37 138	98.25 218

fmvsm_s_conf0.5_n_10		97.29 31	97.40 26	96.97 87	98.24 102	91.96 128	97.89 89	98.72 12	96.77 7	99.46 3	99.06 12	87.78 128	99.84 27	99.40 4	99.27 75	99.12 94

fmvsm_l_conf0.5_n_9		97.59 13	97.79 6	96.97 87	98.28 96	91.49 146	97.61 141	98.71 13	97.10 5	99.70 1	98.93 24	90.95 77	99.77 53	99.35 6	99.53 33	99.65 21

FC-MVSNet-test		93.94 192	93.57 184	95.04 232	95.48 328	91.45 151	98.12 56	98.71 13	93.37 127	90.23 308	96.70 232	87.66 130	97.85 363	91.49 236	90.39 349	95.83 337

UniMVSNet (Re)		93.31 219	92.55 232	95.61 194	95.39 334	93.34 73	97.39 177	98.71 13	93.14 140	90.10 317	94.83 335	87.71 129	98.03 336	91.67 234	83.99 426	95.46 356

aaatest				98.00 25	99.56 1	94.50 37	98.69 11	98.70 16	93.45 124	98.73 31	98.53 53		99.86 11	97.40 50	99.58 25	99.65 21

MED-MVS		98.08 1	98.08 1	98.06 21	99.56 1	94.50 37	98.69 11	98.70 16	95.63 25	98.73 31	98.95 20	95.46 7	99.86 11	97.40 50	99.63 16	99.82 1

fmvsm_l_conf0.5_n_a		97.63 11	97.76 7	97.26 69	98.25 101	92.59 102	97.81 104	98.68 18	94.93 50	99.24 10	98.87 33	93.52 23	99.79 47	99.32 7	99.21 83	99.40 66

FIs		94.09 183	93.70 180	95.27 219	95.70 317	92.03 124	98.10 57	98.68 18	93.36 129	90.39 305	96.70 232	87.63 133	97.94 354	92.25 214	90.50 348	95.84 336

WR-MVS_H		92.00 276	91.35 273	93.95 309	95.09 361	89.47 246	98.04 64	98.68 18	91.46 217	88.34 371	94.68 342	85.86 175	97.56 395	85.77 375	84.24 424	94.82 409

fmvsm_s_conf0.5_n_4		96.75 62	97.07 34	95.79 178	97.76 143	89.57 239	97.66 130	98.66 21	95.36 32	99.03 16	98.90 27	88.39 115	99.73 62	99.17 13	98.66 122	98.08 238

VPA-MVSNet		93.24 221	92.48 237	95.51 204	95.70 317	92.39 108	97.86 92	98.66 21	92.30 182	92.09 265	95.37 310	80.49 303	98.40 285	93.95 177	85.86 396	95.75 345

fmvsm_l_conf0.5_n_3		97.64 10	97.60 13	97.79 35	98.14 115	93.94 58	97.93 84	98.65 23	96.70 8	99.38 5	99.07 11	89.92 92	99.81 36	99.16 14	99.43 53	99.61 30

fmvsm_s_conf0.5_n_3		97.15 36	97.36 28	96.52 108	97.98 127	91.19 163	97.84 96	98.65 23	97.08 6	99.25 9	99.10 6	87.88 126	99.79 47	99.32 7	99.18 90	98.59 180

fmvsm_s_conf0.5_n_8		97.32 28	97.48 23	96.85 89	98.28 96	91.07 171	97.76 109	98.62 25	97.53 2	99.20 12	99.12 5	88.24 118	99.81 36	99.41 3	99.17 91	99.67 16

fmvsm_s_conf0.5_n_2		96.62 70	96.82 55	96.02 155	97.98 127	90.43 199	97.50 157	98.59 26	96.59 10	99.31 6	99.08 8	84.47 212	99.75 59	99.37 5	98.45 134	97.88 251

UniMVSNet_NR-MVSNet		93.37 217	92.67 226	95.47 210	95.34 340	92.83 91	97.17 205	98.58 27	92.98 150	90.13 313	95.80 286	88.37 117	97.85 363	91.71 231	83.93 427	95.73 347

CSCG		96.05 90	95.91 89	96.46 118	99.24 34	90.47 196	98.30 33	98.57 28	89.01 315	93.97 213	97.57 172	92.62 41	99.76 55	94.66 159	99.27 75	99.15 88

fmvsm_s_conf0.5_n_9		97.33 27	97.57 15	96.62 102	98.43 84	90.32 207	97.80 105	98.53 29	97.24 4	99.62 2	99.14 2	88.65 110	99.80 41	99.54 1	99.15 94	99.74 10

fmvsm_s_conf0.5_n_6		97.08 39	97.17 30	96.81 90	97.28 171	91.73 132	97.75 111	98.50 30	94.86 54	99.22 11	98.78 42	89.75 95	99.76 55	99.10 17	99.29 73	98.94 125

MSLP-MVS++		96.94 48	97.06 35	96.59 103	98.72 65	91.86 130	97.67 127	98.49 31	94.66 71	97.24 74	98.41 67	92.31 48	98.94 198	96.61 73	99.46 46	98.96 118

HyFIR lowres test		93.66 204	92.92 214	95.87 167	98.24 102	89.88 225	94.58 399	98.49 31	85.06 415	93.78 217	95.78 290	82.86 249	98.67 253	91.77 229	95.71 246	99.07 103

CHOSEN 1792x2688		94.15 178	93.51 190	96.06 150	98.27 98	89.38 251	95.18 381	98.48 33	85.60 405	93.76 218	97.11 206	83.15 239	99.61 92	91.33 239	98.72 120	99.19 83

fmvsm_s_conf0.5_n_7		96.45 77	96.80 57	95.37 214	97.29 170	88.38 295	97.23 199	98.47 34	95.14 41	98.43 41	99.09 7	87.58 134	99.72 66	98.80 25	99.21 83	98.02 242

fmvsm_s_conf0.5_n_5		97.00 45	96.97 43	97.09 80	97.58 162	92.56 103	97.68 126	98.47 34	94.02 96	98.90 26	98.89 30	88.94 104	99.78 50	99.18 12	99.03 106	98.93 129

PHI-MVS		96.77 60	96.46 76	97.71 46	98.40 88	94.07 54	98.21 48	98.45 36	89.86 283	97.11 80	98.01 106	92.52 43	99.69 74	96.03 99	99.53 33	99.36 72

fmvsm_s_conf0.1_n		96.58 73	96.77 60	96.01 158	96.67 233	90.25 209	97.91 86	98.38 37	94.48 79	98.84 29	99.14 2	88.06 121	99.62 91	98.82 23	98.60 126	98.15 227

PVSNet_BlendedMVS		94.06 184	93.92 174	94.47 274	98.27 98	89.46 248	96.73 254	98.36 38	90.17 276	94.36 197	95.24 318	88.02 122	99.58 100	93.44 191	90.72 344	94.36 430

PVSNet_Blended		94.87 150	94.56 150	95.81 174	98.27 98	89.46 248	95.47 360	98.36 38	88.84 324	94.36 197	96.09 275	88.02 122	99.58 100	93.44 191	98.18 147	98.40 203

3Dnovator	91.36 5	95.19 129	94.44 159	97.44 58	96.56 249	93.36 72	98.65 16	98.36 38	94.12 92	89.25 348	98.06 99	82.20 266	99.77 53	93.41 193	99.32 71	99.18 85

TestfortrainingZip a		97.79 7	97.62 12	98.28 10	99.56 1	95.15 25	98.69 11	98.35 41	95.63 25	98.95 19	98.95 20	93.45 24	99.88 4	96.63 71	98.41 137	99.82 1

FOURS1					99.55 4	93.34 73	99.29 1	98.35 41	94.98 48	98.49 39

DPE-MVS		97.86 5	97.65 10	98.47 5	99.17 39	95.78 8	97.21 202	98.35 41	95.16 40	98.71 35	98.80 40	95.05 11	99.89 3	96.70 69	99.73 1	99.73 13
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
aaEdge-Enhanced		97.54 17	97.39 27	98.00 25	99.21 37	94.50 37	97.75 111	98.34 44	94.23 89	98.15 47	98.53 53	93.32 29	99.84 27	97.40 50	99.58 25	99.65 21

fmvsm_s_conf0.1_n_a		96.40 79	96.47 73	96.16 143	95.48 328	90.69 190	97.91 86	98.33 45	94.07 94	98.93 21	99.14 2	87.44 142	99.61 92	98.63 26	98.32 140	98.18 223

HFP-MVS		97.14 37	96.92 47	97.83 31	99.42 10	94.12 52	98.52 20	98.32 46	93.21 132	97.18 75	98.29 84	92.08 50	99.83 32	95.63 116	99.59 21	99.54 45

ACMMPR		97.07 41	96.84 51	97.79 35	99.44 9	93.88 59	98.52 20	98.31 47	93.21 132	97.15 77	98.33 78	91.35 66	99.86 11	95.63 116	99.59 21	99.62 27

test_fmvsmvis_n_1920		96.70 65	96.84 51	96.31 130	96.62 235	91.73 132	97.98 72	98.30 48	96.19 14	96.10 127	98.95 20	89.42 96	99.76 55	98.90 22	99.08 101	97.43 279

APDe-MVS		97.82 6	97.73 9	98.08 20	99.15 40	94.82 31	98.81 8	98.30 48	94.76 66	98.30 43	98.90 27	93.77 19	99.68 76	97.93 29	99.69 3	99.75 8
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test0726					99.45 6	95.36 15	98.31 32	98.29 50	94.92 52	98.99 18	98.92 25	95.08 9

MSP-MVS		97.59 13	97.54 17	97.73 43	99.40 14	93.77 63	98.53 19	98.29 50	95.55 29	98.56 38	97.81 140	93.90 17	99.65 80	96.62 72	99.21 83	99.77 4
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DVP-MVS++		98.06 2	97.99 2	98.28 10	98.67 68	95.39 13	99.29 1	98.28 52	94.78 63	98.93 21	98.87 33	96.04 2	99.86 11	97.45 46	99.58 25	99.59 32

test_0728_SECOND				98.51 4	99.45 6	95.93 6	98.21 48	98.28 52					99.86 11	97.52 42	99.67 6	99.75 8

CP-MVS		97.02 43	96.81 56	97.64 50	99.33 26	93.54 66	98.80 9	98.28 52	92.99 145	96.45 113	98.30 83	91.90 54	99.85 22	95.61 118	99.68 4	99.54 45

test_fmvsmconf0.1_n		97.09 38	97.06 35	97.19 74	95.67 319	92.21 116	97.95 81	98.27 55	95.78 23	98.40 42	99.00 16	89.99 90	99.78 50	99.06 18	99.41 59	99.59 32

SED-MVS		98.05 3	97.99 2	98.24 12	99.42 10	95.30 19	98.25 40	98.27 55	95.13 42	99.19 13	98.89 30	95.54 5	99.85 22	97.52 42	99.66 10	99.56 40

test_241102_TWO								98.27 55	95.13 42	98.93 21	98.89 30	94.99 12	99.85 22	97.52 42	99.65 13	99.74 10

test_241102_ONE					99.42 10	95.30 19		98.27 55	95.09 45	99.19 13	98.81 39	95.54 5	99.65 80

SF-MVS		97.39 24	97.13 31	98.17 17	99.02 49	95.28 21	98.23 44	98.27 55	92.37 178	98.27 44	98.65 47	93.33 27	99.72 66	96.49 77	99.52 35	99.51 49

SteuartSystems-ACMMP		97.62 12	97.53 18	97.87 29	98.39 90	94.25 46	98.43 27	98.27 55	95.34 34	98.11 48	98.56 49	94.53 13	99.71 68	96.57 75	99.62 19	99.65 21
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 27	95.20 22		98.25 61	95.13 42	98.48 40	98.87 33	95.16 8

PVSNet_Blended_VisFu		95.27 119	94.91 130	96.38 126	98.20 109	90.86 181	97.27 193	98.25 61	90.21 275	94.18 206	97.27 194	87.48 141	99.73 62	93.53 188	97.77 163	98.55 184

region2R		97.07 41	96.84 51	97.77 39	99.46 5	93.79 61	98.52 20	98.24 63	93.19 135	97.14 78	98.34 75	91.59 61	99.87 8	95.46 124	99.59 21	99.64 25

PS-CasMVS		91.55 299	90.84 298	93.69 326	94.96 365	88.28 299	97.84 96	98.24 63	91.46 217	88.04 382	95.80 286	79.67 319	97.48 408	87.02 355	84.54 420	95.31 370

DU-MVS		92.90 239	92.04 248	95.49 207	94.95 366	92.83 91	97.16 206	98.24 63	93.02 144	90.13 313	95.71 293	83.47 230	97.85 363	91.71 231	83.93 427	95.78 341

9.14			96.75 61		98.93 57		97.73 116	98.23 66	91.28 227	97.88 57	98.44 64	93.00 31	99.65 80	95.76 108	99.47 45

reproduce_model		97.51 20	97.51 20	97.50 55	98.99 53	93.01 84	97.79 107	98.21 67	95.73 24	97.99 52	99.03 15	92.63 40	99.82 34	97.80 31	99.42 56	99.67 16

D2MVS		91.30 316	90.95 292	92.35 382	94.71 381	85.52 383	96.18 313	98.21 67	88.89 322	86.60 411	93.82 391	79.92 315	97.95 352	89.29 291	90.95 341	93.56 446

reproduce-ours		97.53 18	97.51 20	97.60 52	98.97 54	93.31 75	97.71 122	98.20 69	95.80 21	97.88 57	98.98 18	92.91 32	99.81 36	97.68 33	99.43 53	99.67 16

our_new_method		97.53 18	97.51 20	97.60 52	98.97 54	93.31 75	97.71 122	98.20 69	95.80 21	97.88 57	98.98 18	92.91 32	99.81 36	97.68 33	99.43 53	99.67 16

SDMVSNet		94.17 175	93.61 183	95.86 170	98.09 118	91.37 153	97.35 181	98.20 69	93.18 137	91.79 273	97.28 192	79.13 328	98.93 199	94.61 162	92.84 307	97.28 287

XVS		97.18 34	96.96 45	97.81 33	99.38 17	94.03 56	98.59 17	98.20 69	94.85 55	96.59 101	98.29 84	91.70 57	99.80 41	95.66 111	99.40 61	99.62 27

X-MVStestdata		91.71 285	89.67 355	97.81 33	99.38 17	94.03 56	98.59 17	98.20 69	94.85 55	96.59 101	32.69 551	91.70 57	99.80 41	95.66 111	99.40 61	99.62 27

test-260524					99.31 29	95.74 9		98.19 74		97.99 52		93.53 22	99.87 8	98.08 28	99.63 16

ACMMP_NAP		97.20 33	96.86 49	98.23 13	99.09 41	95.16 24	97.60 142	98.19 74	92.82 160	97.93 56	98.74 44	91.60 60	99.86 11	96.26 82	99.52 35	99.67 16

CP-MVSNet		91.89 281	91.24 280	93.82 318	95.05 362	88.57 286	97.82 101	98.19 74	91.70 206	88.21 377	95.76 291	81.96 271	97.52 406	87.86 320	84.65 414	95.37 366

ZNCC-MVS		96.96 46	96.67 64	97.85 30	99.37 19	94.12 52	98.49 24	98.18 77	92.64 168	96.39 115	98.18 91	91.61 59	99.88 4	95.59 121	99.55 30	99.57 36

SMA-MVS		97.35 25	97.03 40	98.30 9	99.06 45	95.42 12	97.94 82	98.18 77	90.57 266	98.85 28	98.94 23	93.33 27	99.83 32	96.72 67	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		91.20 321	90.44 318	93.48 344	94.49 389	87.91 319	97.76 109	98.18 77	91.29 224	87.78 386	95.74 292	80.35 306	97.33 420	85.46 379	82.96 437	95.19 381

DELS-MVS		96.61 71	96.38 80	97.30 64	97.79 141	93.19 80	95.96 328	98.18 77	95.23 37	95.87 137	97.65 160	91.45 62	99.70 73	95.87 102	99.44 52	99.00 112
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
tfpnnormal		89.70 374	88.40 380	93.60 335	95.15 357	90.10 213	97.56 147	98.16 81	87.28 377	86.16 418	94.63 346	77.57 356	98.05 332	74.48 470	84.59 418	92.65 461

VNet		95.89 98	95.45 101	97.21 72	98.07 122	92.94 87	97.50 157	98.15 82	93.87 102	97.52 64	97.61 167	85.29 195	99.53 114	95.81 107	95.27 259	99.16 86

DeepPCF-MVS	93.97 1	96.61 71	97.09 33	95.15 225	98.09 118	86.63 355	96.00 326	98.15 82	95.43 30	97.95 55	98.56 49	93.40 25	99.36 139	96.77 64	99.48 44	99.45 59

SD-MVS		97.41 23	97.53 18	97.06 83	98.57 79	94.46 40	97.92 85	98.14 84	94.82 59	99.01 17	98.55 51	94.18 15	97.41 415	96.94 59	99.64 14	99.32 74
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
GST-MVS		96.85 54	96.52 70	97.82 32	99.36 23	94.14 51	98.29 34	98.13 85	92.72 163	96.70 93	98.06 99	91.35 66	99.86 11	94.83 147	99.28 74	99.47 58

UA-Net		95.95 95	95.53 97	97.20 73	97.67 148	92.98 86	97.65 131	98.13 85	94.81 61	96.61 99	98.35 72	88.87 105	99.51 119	90.36 266	97.35 179	99.11 96

QAPM		93.45 215	92.27 242	96.98 86	96.77 226	92.62 100	98.39 29	98.12 87	84.50 423	88.27 375	97.77 145	82.39 263	99.81 36	85.40 380	98.81 115	98.51 189

Vis-MVSNet		95.23 124	94.81 136	96.51 112	97.18 177	91.58 143	98.26 39	98.12 87	94.38 86	94.90 180	98.15 94	82.28 264	98.92 201	91.45 238	98.58 128	99.01 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 242	91.68 263	96.40 123	95.34 340	92.73 96	98.27 37	98.12 87	84.86 418	85.78 427	97.75 146	78.89 338	99.74 60	87.50 343	98.65 123	96.73 306

TranMVSNet+NR-MVSNet		92.50 251	91.63 264	95.14 226	94.76 377	92.07 121	97.53 153	98.11 90	92.90 156	89.56 336	96.12 270	83.16 238	97.60 392	89.30 290	83.20 436	95.75 345

CPTT-MVS		95.57 109	95.19 114	96.70 93	99.27 32	91.48 148	98.33 31	98.11 90	87.79 361	95.17 169	98.03 103	87.09 150	99.61 92	93.51 189	99.42 56	99.02 106

APD-MVS		96.95 47	96.60 66	98.01 23	99.03 48	94.93 30	97.72 119	98.10 92	91.50 215	98.01 51	98.32 80	92.33 46	99.58 100	94.85 144	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 50	99.40 14	93.44 68	98.50 23	98.09 93	93.27 131	95.95 135	98.33 78	91.04 74	99.88 4	95.20 129	99.57 29	99.60 31

ZD-MVS					99.05 46	94.59 35		98.08 94	89.22 308	97.03 83	98.10 95	92.52 43	99.65 80	94.58 164	99.31 72

MTGPA								98.08 94

MTAPA		97.08 39	96.78 59	97.97 28	99.37 19	94.42 42	97.24 195	98.08 94	95.07 46	96.11 126	98.59 48	90.88 80	99.90 2	96.18 94	99.50 40	99.58 35

CNVR-MVS		97.68 8	97.44 24	98.37 7	98.90 60	95.86 7	97.27 193	98.08 94	95.81 20	97.87 60	98.31 81	94.26 14	99.68 76	97.02 58	99.49 43	99.57 36

DP-MVS Recon		95.68 103	95.12 119	97.37 61	99.19 38	94.19 48	97.03 213	98.08 94	88.35 342	95.09 171	97.65 160	89.97 91	99.48 126	92.08 223	98.59 127	98.44 200

SR-MVS		97.01 44	96.86 49	97.47 57	99.09 41	93.27 77	97.98 72	98.07 99	93.75 106	97.45 66	98.48 61	91.43 64	99.59 97	96.22 85	99.27 75	99.54 45

MCST-MVS		97.18 34	96.84 51	98.20 16	99.30 30	95.35 17	97.12 209	98.07 99	93.54 118	96.08 128	97.69 155	93.86 18	99.71 68	96.50 76	99.39 63	99.55 43

NR-MVSNet		92.34 260	91.27 279	95.53 199	94.95 366	93.05 83	97.39 177	98.07 99	92.65 166	84.46 439	95.71 293	85.00 202	97.77 374	89.71 278	83.52 433	95.78 341

MP-MVS-pluss		96.70 65	96.27 83	97.98 27	99.23 36	94.71 32	96.96 224	98.06 102	90.67 256	95.55 153	98.78 42	91.07 73	99.86 11	96.58 74	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 77	99.01 52	92.31 112	97.98 72	98.06 102	93.11 141	97.44 67	98.55 51	90.93 78	99.55 110	96.06 95	99.25 80	99.51 49

MP-MVS		96.77 60	96.45 77	97.72 44	99.39 16	93.80 60	98.41 28	98.06 102	93.37 127	95.54 155	98.34 75	90.59 84	99.88 4	94.83 147	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 71	99.32 27	92.74 95	98.74 10	98.06 102	90.57 266	96.77 90	98.35 72	90.21 87	99.53 114	94.80 151	99.63 16	99.38 70

HPM-MVS		96.69 67	96.45 77	97.40 60	99.36 23	93.11 82	98.87 6	98.06 102	91.17 235	96.40 114	97.99 109	90.99 75	99.58 100	95.61 118	99.61 20	99.49 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 165	93.80 176	96.64 95	97.07 184	91.97 126	96.32 298	98.06 102	88.94 320	94.50 194	96.78 227	84.60 209	99.27 149	91.90 224	96.02 235	98.68 174

DeepC-MVS	93.07 3	96.06 89	95.66 93	97.29 65	97.96 129	93.17 81	97.30 187	98.06 102	93.92 100	93.38 233	98.66 45	86.83 153	99.73 62	95.60 120	99.22 82	98.96 118
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		97.30 29	97.03 40	98.11 19	98.77 63	95.06 28	97.34 182	98.04 109	95.96 15	97.09 81	97.88 127	93.18 30	99.71 68	95.84 106	99.17 91	99.56 40

DeepC-MVS_fast	93.89 2	96.93 49	96.64 65	97.78 37	98.64 74	94.30 43	97.41 172	98.04 109	94.81 61	96.59 101	98.37 70	91.24 69	99.64 88	95.16 131	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 79	99.02 49	92.34 110	97.98 72	98.03 111	93.52 121	97.43 69	98.51 56	91.40 65	99.56 108	96.05 96	99.26 78	99.43 63

RE-MVS-def			96.72 62		99.02 49	92.34 110	97.98 72	98.03 111	93.52 121	97.43 69	98.51 56	90.71 82		96.05 96	99.26 78	99.43 63

RPMNet		88.98 380	87.05 394	94.77 253	94.45 391	87.19 338	90.23 485	98.03 111	77.87 484	92.40 251	87.55 485	80.17 310	99.51 119	68.84 492	93.95 293	97.60 272

save fliter					98.91 59	94.28 44	97.02 215	98.02 114	95.35 33

TEST9					98.70 66	94.19 48	96.41 284	98.02 114	88.17 346	96.03 129	97.56 174	92.74 37	99.59 97

train_agg		96.30 85	95.83 92	97.72 44	98.70 66	94.19 48	96.41 284	98.02 114	88.58 333	96.03 129	97.56 174	92.73 38	99.59 97	95.04 133	99.37 67	99.39 68

test_8					98.67 68	94.06 55	96.37 292	98.01 117	88.58 333	95.98 134	97.55 176	92.73 38	99.58 100

fmvsm_s_conf0.5_n_11		97.30 29	97.59 14	96.43 120	98.42 85	91.37 153	98.04 64	98.00 118	97.30 3	99.45 4	99.21 1	89.28 98	99.80 41	99.27 10	99.35 69	98.12 230

agg_prior					98.67 68	93.79 61		98.00 118		95.68 147			99.57 107

test_prior				97.23 70	98.67 68	92.99 85		98.00 118					99.41 134			99.29 75

WR-MVS		92.34 260	91.53 268	94.77 253	95.13 359	90.83 182	96.40 288	97.98 121	91.88 201	89.29 345	95.54 304	82.50 259	97.80 370	89.79 277	85.27 405	95.69 348

HPM-MVS++		97.34 26	96.97 43	98.47 5	99.08 43	96.16 5	97.55 152	97.97 122	95.59 27	96.61 99	97.89 122	92.57 42	99.84 27	95.95 101	99.51 38	99.40 66

CANet		96.39 80	96.02 87	97.50 55	97.62 155	93.38 70	97.02 215	97.96 123	95.42 31	94.86 181	97.81 140	87.38 144	99.82 34	96.88 61	99.20 88	99.29 75

114514_t		93.95 191	93.06 208	96.63 99	99.07 44	91.61 140	97.46 168	97.96 123	77.99 482	93.00 242	97.57 172	86.14 171	99.33 141	89.22 294	99.15 94	98.94 125

IU-MVS					99.42 10	95.39 13		97.94 125	90.40 273	98.94 20				97.41 49	99.66 10	99.74 10

MSC_two_6792asdad				98.86 1	98.67 68	96.94 1		97.93 126					99.86 11	97.68 33	99.67 6	99.77 4

No_MVS				98.86 1	98.67 68	96.94 1		97.93 126					99.86 11	97.68 33	99.67 6	99.77 4

fmvsm_s_conf0.1_n_2		96.33 84	96.44 79	96.00 159	97.30 169	90.37 205	97.53 153	97.92 128	96.52 11	99.14 15	99.08 8	83.21 236	99.74 60	99.22 11	98.06 152	97.88 251

Anonymous20231211		90.63 346	89.42 362	94.27 289	98.24 102	89.19 263	98.05 63	97.89 129	79.95 472	88.25 376	94.96 327	72.56 402	98.13 315	89.70 279	85.14 407	95.49 352

原ACMM1				96.38 126	98.59 76	91.09 170		97.89 129	87.41 373	95.22 168	97.68 156	90.25 86	99.54 112	87.95 319	99.12 99	98.49 192

CDPH-MVS		95.97 94	95.38 107	97.77 39	98.93 57	94.44 41	96.35 293	97.88 131	86.98 381	96.65 97	97.89 122	91.99 52	99.47 127	92.26 212	99.46 46	99.39 68

test11								97.88 131

EIA-MVS		95.53 111	95.47 100	95.71 189	97.06 187	89.63 235	97.82 101	97.87 133	93.57 114	93.92 215	95.04 324	90.61 83	98.95 196	94.62 161	98.68 121	98.54 185

CS-MVS		96.86 52	97.06 35	96.26 136	98.16 114	91.16 168	99.09 3	97.87 133	95.30 35	97.06 82	98.03 103	91.72 55	98.71 246	97.10 56	99.17 91	98.90 134

无先验							95.79 340	97.87 133	83.87 433				99.65 80	87.68 333		98.89 140

3Dnovator+	91.43 4	95.40 113	94.48 157	98.16 18	96.90 205	95.34 18	98.48 25	97.87 133	94.65 72	88.53 367	98.02 105	83.69 226	99.71 68	93.18 197	98.96 110	99.44 61

VPNet		92.23 268	91.31 276	94.99 236	95.56 324	90.96 174	97.22 201	97.86 137	92.96 151	90.96 296	96.62 244	75.06 377	98.20 308	91.90 224	83.65 432	95.80 339

TestfortrainingZip				98.34 8	98.54 80	96.25 4	98.69 11	97.85 138	94.15 91	98.17 46	97.94 113	94.00 16	99.63 89		97.45 175	99.15 88

test_vis1_n_1920		94.17 175	94.58 149	92.91 365	97.42 167	82.02 437	97.83 99	97.85 138	94.68 69	98.10 49	98.49 58	70.15 424	99.32 143	97.91 30	98.82 114	97.40 281

DVP-MVS		97.91 4	97.81 5	98.22 15	99.45 6	95.36 15	98.21 48	97.85 138	94.92 52	98.73 31	98.87 33	95.08 9	99.84 27	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 47	99.25 33	94.24 47	98.07 61	97.85 138	93.72 107	98.57 37	98.35 72	93.69 20	99.40 135	97.06 57	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	96.45 119	98.29 95	91.66 139	99.03 4	97.85 138	95.84 18	96.90 85	97.97 111	91.24 69	98.75 235	96.92 60	99.33 70	98.94 125

test_fmvsmconf0.01_n		96.15 88	95.85 91	97.03 84	92.66 445	91.83 131	97.97 78	97.84 143	95.57 28	97.53 63	99.00 16	84.20 219	99.76 55	98.82 23	99.08 101	99.48 56

GDP-MVS		95.62 106	95.13 117	97.09 80	96.79 219	93.26 78	97.89 89	97.83 144	93.58 113	96.80 87	97.82 138	83.06 243	99.16 164	94.40 168	97.95 158	98.87 145

BridgeMVS		96.84 56	96.89 48	96.68 94	97.63 154	92.22 115	98.17 54	97.82 145	94.44 81	98.23 45	97.36 187	90.97 76	99.22 154	97.74 32	99.66 10	98.61 178

AdaColmap		94.34 170	93.68 181	96.31 130	98.59 76	91.68 138	96.59 273	97.81 146	89.87 282	92.15 261	97.06 210	83.62 229	99.54 112	89.34 289	98.07 151	97.70 265

MVSMamba_PlusPlus		96.51 74	96.48 72	96.59 103	98.07 122	91.97 126	98.14 55	97.79 147	90.43 271	97.34 72	97.52 177	91.29 68	99.19 157	98.12 27	99.64 14	98.60 179

KinetiMVS		95.26 120	94.75 142	96.79 91	96.99 197	92.05 122	97.82 101	97.78 148	94.77 65	96.46 111	97.70 153	80.62 300	99.34 140	92.37 211	98.28 142	98.97 115

ETV-MVS		96.02 91	95.89 90	96.40 123	97.16 178	92.44 107	97.47 166	97.77 149	94.55 75	96.48 109	94.51 352	91.23 71	98.92 201	95.65 114	98.19 146	97.82 259

新几何1				97.32 63	98.60 75	93.59 65		97.75 150	81.58 463	95.75 142	97.85 132	90.04 89	99.67 78	86.50 361	99.13 97	98.69 173

旧先验1					98.38 91	93.38 70		97.75 150			98.09 97	92.30 49			99.01 107	99.16 86

EC-MVSNet		96.42 78	96.47 73	96.26 136	97.01 195	91.52 145	98.89 5	97.75 150	94.42 82	96.64 98	97.68 156	89.32 97	98.60 268	97.45 46	99.11 100	98.67 175

EI-MVSNet-Vis-set		96.51 74	96.47 73	96.63 99	98.24 102	91.20 162	96.89 232	97.73 153	94.74 67	96.49 108	98.49 58	90.88 80	99.58 100	96.44 78	98.32 140	99.13 91

PAPM_NR		95.01 140	94.59 148	96.26 136	98.89 61	90.68 191	97.24 195	97.73 153	91.80 202	92.93 247	96.62 244	89.13 101	99.14 170	89.21 295	97.78 162	98.97 115

Anonymous20240529		91.98 277	90.73 305	95.73 187	98.14 115	89.40 250	97.99 69	97.72 155	79.63 474	93.54 226	97.41 184	69.94 426	99.56 108	91.04 246	91.11 337	98.22 220

CHOSEN 280x420		93.12 227	92.72 225	94.34 282	96.71 232	87.27 334	90.29 484	97.72 155	86.61 389	91.34 285	95.29 312	84.29 218	98.41 284	93.25 195	98.94 111	97.35 284

EI-MVSNet-UG-set		96.34 83	96.30 82	96.47 116	98.20 109	90.93 178	96.86 235	97.72 155	94.67 70	96.16 125	98.46 62	90.43 85	99.58 100	96.23 84	97.96 157	98.90 134

LS3D		93.57 208	92.61 230	96.47 116	97.59 158	91.61 140	97.67 127	97.72 155	85.17 413	90.29 307	98.34 75	84.60 209	99.73 62	83.85 403	98.27 143	98.06 240

PAPR		94.18 174	93.42 197	96.48 115	97.64 152	91.42 152	95.55 355	97.71 159	88.99 317	92.34 257	95.82 285	89.19 99	99.11 173	86.14 367	97.38 177	98.90 134

UGNet		94.04 186	93.28 200	96.31 130	96.85 210	91.19 163	97.88 91	97.68 160	94.40 84	93.00 242	96.18 265	73.39 396	99.61 92	91.72 230	98.46 133	98.13 228
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
testdata				95.46 211	98.18 113	88.90 275		97.66 161	82.73 452	97.03 83	98.07 98	90.06 88	98.85 208	89.67 280	98.98 109	98.64 176

test12				97.65 48	98.46 81	94.26 45		97.66 161		95.52 156		90.89 79	99.46 128		99.25 80	99.22 82

DTE-MVSNet		90.56 347	89.75 353	93.01 361	93.95 404	87.25 335	97.64 135	97.65 163	90.74 251	87.12 399	95.68 296	79.97 314	97.00 433	83.33 404	81.66 443	94.78 416

TAPA-MVS	90.10 7	92.30 263	91.22 282	95.56 196	98.33 93	89.60 237	96.79 246	97.65 163	81.83 460	91.52 279	97.23 197	87.94 124	98.91 203	71.31 485	98.37 138	98.17 226
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 228	92.45 238	95.05 230	98.09 118	89.21 260	96.89 232	97.64 165	93.18 137	91.79 273	97.28 192	75.35 376	98.65 258	88.99 301	92.84 307	97.28 287

test_cas_vis1_n_1920		94.48 167	94.55 153	94.28 288	96.78 224	86.45 361	97.63 137	97.64 165	93.32 130	97.68 62	98.36 71	73.75 392	99.08 180	96.73 66	99.05 103	97.31 286

NormalMVS		96.36 82	96.11 86	97.12 77	99.37 19	92.90 89	97.99 69	97.63 167	95.92 16	96.57 104	97.93 114	85.34 193	99.50 122	94.99 136	99.21 83	98.97 115

Elysia		94.00 188	93.12 205	96.64 95	96.08 302	92.72 97	97.50 157	97.63 167	91.15 237	94.82 182	97.12 204	74.98 379	99.06 186	90.78 251	98.02 153	98.12 230

StellarMVS		94.00 188	93.12 205	96.64 95	96.08 302	92.72 97	97.50 157	97.63 167	91.15 237	94.82 182	97.12 204	74.98 379	99.06 186	90.78 251	98.02 153	98.12 230

cdsmvs_eth3d_5k		23.24 513	30.99 506	0.00 540	0.00 564	0.00 567	0.00 552	97.63 167	0.00 559	0.00 560	96.88 223	84.38 214	0.00 560	0.00 559	0.00 559	0.00 556

DPM-MVS		95.69 102	94.92 129	98.01 23	98.08 121	95.71 11	95.27 372	97.62 171	90.43 271	95.55 153	97.07 209	91.72 55	99.50 122	89.62 282	98.94 111	98.82 153

sasdasda		96.02 91	95.45 101	97.75 41	97.59 158	95.15 25	98.28 35	97.60 172	94.52 77	96.27 120	96.12 270	87.65 131	99.18 160	96.20 90	94.82 268	98.91 131

canonicalmvs		96.02 91	95.45 101	97.75 41	97.59 158	95.15 25	98.28 35	97.60 172	94.52 77	96.27 120	96.12 270	87.65 131	99.18 160	96.20 90	94.82 268	98.91 131

test222					98.24 102	92.21 116	95.33 367	97.60 172	79.22 476	95.25 165	97.84 134	88.80 107			99.15 94	98.72 169

cascas		91.20 321	90.08 335	94.58 267	94.97 364	89.16 264	93.65 442	97.59 175	79.90 473	89.40 340	92.92 421	75.36 375	98.36 292	92.14 217	94.75 271	96.23 318

E2		95.20 126	95.00 125	95.79 178	96.79 219	89.66 232	96.82 241	97.58 176	92.35 179	95.28 163	97.83 136	86.68 156	98.76 229	94.79 154	96.92 198	98.95 122

E3		95.20 126	95.00 125	95.79 178	96.77 226	89.66 232	96.82 241	97.58 176	92.35 179	95.28 163	97.83 136	86.69 155	98.76 229	94.79 154	96.92 198	98.95 122

h-mvs33		94.15 178	93.52 189	96.04 152	97.81 140	90.22 210	97.62 140	97.58 176	95.19 38	96.74 91	97.45 180	83.67 227	99.61 92	95.85 104	79.73 451	98.29 216

E5new		95.04 136	94.88 131	95.52 200	96.62 235	89.02 268	97.29 188	97.57 179	92.54 169	95.04 172	97.89 122	85.65 183	98.77 223	94.92 139	96.44 226	98.78 157

E6new		95.04 136	94.88 131	95.52 200	96.60 240	89.02 268	97.29 188	97.57 179	92.54 169	95.04 172	97.90 120	85.66 181	98.77 223	94.92 139	96.44 226	98.78 157

E6		95.04 136	94.88 131	95.52 200	96.60 240	89.02 268	97.29 188	97.57 179	92.54 169	95.04 172	97.90 120	85.66 181	98.77 223	94.92 139	96.44 226	98.78 157

E5		95.04 136	94.88 131	95.52 200	96.62 235	89.02 268	97.29 188	97.57 179	92.54 169	95.04 172	97.89 122	85.65 183	98.77 223	94.92 139	96.44 226	98.78 157

MGCFI-Net		95.94 96	95.40 105	97.56 54	97.59 158	94.62 34	98.21 48	97.57 179	94.41 83	96.17 124	96.16 268	87.54 136	99.17 162	96.19 92	94.73 273	98.91 131

MVSFormer		95.37 114	95.16 115	95.99 160	96.34 274	91.21 160	98.22 46	97.57 179	91.42 219	96.22 122	97.32 188	86.20 169	97.92 357	94.07 174	99.05 103	98.85 147

test_djsdf		93.07 230	92.76 220	94.00 303	93.49 423	88.70 280	98.22 46	97.57 179	91.42 219	90.08 319	95.55 303	82.85 250	97.92 357	94.07 174	91.58 328	95.40 363

OMC-MVS		95.09 133	94.70 143	96.25 139	98.46 81	91.28 156	96.43 280	97.57 179	92.04 197	94.77 187	97.96 112	87.01 151	99.09 178	91.31 240	96.77 206	98.36 207

E4		95.09 133	94.86 135	95.77 181	96.58 244	89.56 240	96.85 236	97.56 187	92.50 173	95.03 176	97.86 130	86.03 172	98.78 219	94.71 157	96.65 216	98.96 118

viewcassd2359sk11		95.26 120	95.09 121	95.80 175	96.95 201	89.72 231	96.80 245	97.56 187	92.21 187	95.37 161	97.80 142	87.17 149	98.77 223	94.82 149	97.10 192	98.90 134

PS-MVSNAJss		93.74 201	93.51 190	94.44 276	93.91 406	89.28 258	97.75 111	97.56 187	92.50 173	89.94 321	96.54 248	88.65 110	98.18 311	93.83 183	90.90 342	95.86 333

casdiffmvs_mvg		95.81 101	95.57 94	96.51 112	96.87 207	91.49 146	97.50 157	97.56 187	93.99 98	95.13 170	97.92 117	87.89 125	98.78 219	95.97 100	97.33 180	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
Casviewmamba		95.67 104	95.55 95	96.03 154	96.95 201	90.12 212	97.72 119	97.55 191	94.10 93	95.23 166	98.18 91	87.32 145	98.80 217	95.40 125	97.52 169	99.19 83

E3new		95.28 118	95.11 120	95.80 175	97.03 192	89.76 229	96.78 250	97.54 192	92.06 196	95.40 159	97.75 146	87.49 140	98.76 229	94.85 144	97.10 192	98.88 142

jajsoiax		92.42 256	91.89 256	94.03 302	93.33 431	88.50 291	97.73 116	97.53 193	92.00 199	88.85 359	96.50 250	75.62 374	98.11 319	93.88 181	91.56 329	95.48 353

mvs_tets		92.31 262	91.76 259	93.94 311	93.41 428	88.29 298	97.63 137	97.53 193	92.04 197	88.76 362	96.45 252	74.62 384	98.09 324	93.91 179	91.48 330	95.45 358

dcpmvs_2		96.37 81	97.05 38	94.31 286	98.96 56	84.11 410	97.56 147	97.51 195	93.92 100	97.43 69	98.52 55	92.75 36	99.32 143	97.32 55	99.50 40	99.51 49

HQP_MVS		93.78 200	93.43 195	94.82 246	96.21 281	89.99 218	97.74 114	97.51 195	94.85 55	91.34 285	96.64 237	81.32 284	98.60 268	93.02 203	92.23 316	95.86 333

plane_prior5								97.51 195					98.60 268	93.02 203	92.23 316	95.86 333

hybridcas		95.46 112	95.29 110	95.96 162	96.83 213	90.08 214	97.63 137	97.49 198	93.76 105	94.79 185	98.04 101	86.87 152	98.72 244	94.71 157	97.53 168	99.08 100

viewmanbaseed2359cas		95.24 123	95.02 123	95.91 164	96.87 207	89.98 220	96.82 241	97.49 198	92.26 183	95.47 157	97.82 138	86.47 161	98.69 248	94.80 151	97.20 188	99.06 104

reproduce_monomvs		91.30 316	91.10 287	91.92 396	96.82 216	82.48 431	97.01 218	97.49 198	94.64 73	88.35 370	95.27 315	70.53 419	98.10 320	95.20 129	84.60 417	95.19 381

viewmacassd2359aftdt		95.07 135	94.80 137	95.87 167	96.53 254	89.84 226	96.90 231	97.48 201	92.44 175	95.36 162	97.89 122	85.23 196	98.68 250	94.40 168	97.00 196	99.09 98

PS-MVSNAJ		95.37 114	95.33 109	95.49 207	97.35 168	90.66 192	95.31 369	97.48 201	93.85 103	96.51 107	95.70 295	88.65 110	99.65 80	94.80 151	98.27 143	96.17 322

API-MVS		94.84 152	94.49 156	95.90 165	97.90 135	92.00 125	97.80 105	97.48 201	89.19 309	94.81 184	96.71 230	88.84 106	99.17 162	88.91 304	98.76 119	96.53 311

MG-MVS		95.61 107	95.38 107	96.31 130	98.42 85	90.53 194	96.04 322	97.48 201	93.47 123	95.67 148	98.10 95	89.17 100	99.25 151	91.27 241	98.77 118	99.13 91

MAR-MVS		94.22 173	93.46 192	96.51 112	98.00 126	92.19 119	97.67 127	97.47 205	88.13 350	93.00 242	95.84 283	84.86 207	99.51 119	87.99 318	98.17 148	97.83 258
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		92.98 234	92.53 234	94.32 284	96.12 297	89.20 261	95.28 370	97.47 205	92.66 165	89.90 322	95.62 299	80.58 301	98.40 285	92.73 208	92.40 314	95.38 365
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 314	90.22 331	94.68 258	94.86 373	87.86 320	97.23 199	97.46 207	87.99 351	89.90 322	96.92 221	66.35 454	98.23 305	90.30 267	90.99 340	97.96 245

nrg030		94.05 185	93.31 199	96.27 135	95.22 351	94.59 35	98.34 30	97.46 207	92.93 152	91.21 294	96.64 237	87.23 148	98.22 306	94.99 136	85.80 397	95.98 332

XVG-OURS		93.72 202	93.35 198	94.80 251	97.07 184	88.61 284	94.79 394	97.46 207	91.97 200	93.99 211	97.86 130	81.74 278	98.88 205	92.64 209	92.67 312	96.92 301

LPG-MVS_test		92.94 237	92.56 231	94.10 297	96.16 292	88.26 300	97.65 131	97.46 207	91.29 224	90.12 315	97.16 201	79.05 331	98.73 239	92.25 214	91.89 324	95.31 370

LGP-MVS_train				94.10 297	96.16 292	88.26 300		97.46 207	91.29 224	90.12 315	97.16 201	79.05 331	98.73 239	92.25 214	91.89 324	95.31 370

MVS		91.71 285	90.44 318	95.51 204	95.20 353	91.59 142	96.04 322	97.45 212	73.44 492	87.36 395	95.60 300	85.42 192	99.10 175	85.97 372	97.46 171	95.83 337

XVG-OURS-SEG-HR		93.86 197	93.55 185	94.81 248	97.06 187	88.53 290	95.28 370	97.45 212	91.68 207	94.08 210	97.68 156	82.41 262	98.90 204	93.84 182	92.47 313	96.98 296

baseline		95.58 108	95.42 104	96.08 147	96.78 224	90.41 200	97.16 206	97.45 212	93.69 110	95.65 149	97.85 132	87.29 146	98.68 250	95.66 111	97.25 186	99.13 91

ab-mvs		93.57 208	92.55 232	96.64 95	97.28 171	91.96 128	95.40 363	97.45 212	89.81 287	93.22 239	96.28 261	79.62 322	99.46 128	90.74 254	93.11 304	98.50 190

xiu_mvs_v2_base		95.32 117	95.29 110	95.40 213	97.22 173	90.50 195	95.44 362	97.44 216	93.70 109	96.46 111	96.18 265	88.59 114	99.53 114	94.79 154	97.81 161	96.17 322

1314		92.81 246	92.03 249	95.14 226	95.33 343	89.52 245	96.04 322	97.44 216	87.72 365	86.25 416	95.33 311	83.84 224	98.79 218	89.26 292	97.05 195	97.11 294

casdiffmvs		95.64 105	95.49 98	96.08 147	96.76 230	90.45 197	97.29 188	97.44 216	94.00 97	95.46 158	97.98 110	87.52 139	98.73 239	95.64 115	97.33 180	99.08 100
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt07		94.76 158	94.68 144	95.01 234	96.76 230	87.41 330	96.38 290	97.43 219	92.65 166	94.52 193	97.75 146	85.55 189	98.81 214	94.36 170	96.69 213	98.82 153

XXY-MVS		92.16 270	91.23 281	94.95 242	94.75 378	90.94 177	97.47 166	97.43 219	89.14 310	88.90 355	96.43 253	79.71 318	98.24 304	89.56 283	87.68 378	95.67 349

anonymousdsp		92.16 270	91.55 267	93.97 307	92.58 447	89.55 242	97.51 156	97.42 221	89.42 303	88.40 369	94.84 334	80.66 299	97.88 362	91.87 226	91.28 334	94.48 425

Effi-MVS+		94.93 145	94.45 158	96.36 128	96.61 238	91.47 149	96.41 284	97.41 222	91.02 243	94.50 194	95.92 279	87.53 137	98.78 219	93.89 180	96.81 205	98.84 151

RRT-MVS		94.51 165	94.35 162	94.98 238	96.40 267	86.55 358	97.56 147	97.41 222	93.19 135	94.93 179	97.04 211	79.12 329	99.30 147	96.19 92	97.32 182	99.09 98

casdiffseed414692147		94.55 163	94.02 170	96.15 144	96.61 238	90.79 184	97.42 170	97.39 224	92.18 192	93.95 214	97.64 163	84.37 215	98.66 256	90.68 256	95.91 239	99.00 112

HQP3-MVS								97.39 224							92.10 321

HQP-MVS		93.19 224	92.74 223	94.54 270	95.86 309	89.33 254	96.65 264	97.39 224	93.55 115	90.14 309	95.87 281	80.95 290	98.50 278	92.13 220	92.10 321	95.78 341

PLC	91.00 6	94.11 182	93.43 195	96.13 145	98.58 78	91.15 169	96.69 260	97.39 224	87.29 376	91.37 283	96.71 230	88.39 115	99.52 118	87.33 348	97.13 191	97.73 263
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
diffmvs_AUTHOR		95.33 116	95.27 112	95.50 206	96.37 272	89.08 266	96.08 319	97.38 228	93.09 143	96.53 106	97.74 149	86.45 162	98.68 250	96.32 80	97.48 170	98.75 165

v7n		90.76 339	89.86 346	93.45 346	93.54 420	87.60 328	97.70 125	97.37 229	88.85 323	87.65 388	94.08 382	81.08 289	98.10 320	84.68 389	83.79 431	94.66 422

UnsupCasMVSNet_eth		85.99 427	84.45 429	90.62 432	89.97 471	82.40 434	93.62 443	97.37 229	89.86 283	78.59 482	92.37 432	65.25 466	95.35 470	82.27 418	70.75 491	94.10 436

viewdifsd2359ckpt13		94.87 150	94.52 154	95.90 165	96.88 206	90.19 211	96.92 228	97.36 231	91.26 228	94.65 189	97.46 179	85.79 178	98.64 260	93.64 186	96.76 207	98.88 142

ACMM	89.79 8	92.96 235	92.50 236	94.35 280	96.30 277	88.71 279	97.58 143	97.36 231	91.40 221	90.53 302	96.65 236	79.77 317	98.75 235	91.24 242	91.64 326	95.59 351
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 140	94.76 139	95.75 184	96.58 244	91.71 135	96.25 305	97.35 233	92.99 145	96.70 93	96.63 241	82.67 254	99.44 131	96.22 85	97.46 171	96.11 328

xiu_mvs_v1_base		95.01 140	94.76 139	95.75 184	96.58 244	91.71 135	96.25 305	97.35 233	92.99 145	96.70 93	96.63 241	82.67 254	99.44 131	96.22 85	97.46 171	96.11 328

xiu_mvs_v1_base_debi		95.01 140	94.76 139	95.75 184	96.58 244	91.71 135	96.25 305	97.35 233	92.99 145	96.70 93	96.63 241	82.67 254	99.44 131	96.22 85	97.46 171	96.11 328

diffmvs		95.25 122	95.13 117	95.63 192	96.43 266	89.34 253	95.99 327	97.35 233	92.83 159	96.31 118	97.37 186	86.44 163	98.67 253	96.26 82	97.19 189	98.87 145
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		94.71 161	94.02 170	96.79 91	97.71 146	92.05 122	96.59 273	97.35 233	90.61 262	94.64 190	96.93 218	86.41 164	99.39 136	91.20 243	94.71 274	98.94 125

viewdifsd2359ckpt09		94.81 155	94.37 161	96.12 146	96.91 203	90.75 188	96.94 225	97.31 238	90.51 269	94.31 200	97.38 185	85.70 180	98.71 246	93.54 187	96.75 208	98.90 134

balanced_ft_v1		95.56 110	95.40 105	96.07 149	97.16 178	90.36 206	98.23 44	97.31 238	92.89 157	96.36 116	97.11 206	83.28 234	99.26 150	97.40 50	98.80 116	98.58 181

SSM_0407		94.54 164	94.12 169	95.80 175	96.79 219	90.38 202	96.79 246	97.29 240	91.24 229	93.68 219	97.60 168	85.03 200	98.67 253	92.14 217	96.51 219	98.35 209

SSM_0404		94.73 160	94.31 164	95.98 161	97.05 189	90.90 180	97.01 218	97.29 240	91.24 229	94.17 207	97.60 168	85.03 200	98.76 229	92.14 217	97.30 183	98.29 216

F-COLMAP		93.58 206	92.98 212	95.37 214	98.40 88	88.98 272	97.18 204	97.29 240	87.75 364	90.49 303	97.10 208	85.21 197	99.50 122	86.70 358	96.72 211	97.63 267

VortexMVS		92.88 241	92.64 227	93.58 337	96.58 244	87.53 329	96.93 227	97.28 243	92.78 162	89.75 327	94.99 325	82.73 253	97.76 375	94.60 163	88.16 373	95.46 356

onestephybrid01		95.12 132	95.01 124	95.46 211	96.39 271	88.92 273	96.28 303	97.27 244	92.67 164	96.00 133	97.73 152	86.28 165	98.66 256	95.58 122	96.85 202	98.79 156

viewmamba		95.18 130	95.15 116	95.26 221	96.31 276	88.25 302	96.29 301	97.27 244	93.61 112	95.65 149	97.91 119	86.79 154	98.64 260	95.69 110	96.82 204	98.88 142

hybridnocas07		94.93 145	94.78 138	95.37 214	96.27 278	88.62 283	96.10 317	97.26 246	92.35 179	95.58 152	97.48 178	85.60 188	98.65 258	95.47 123	96.90 200	98.85 147

XVG-ACMP-BASELINE		90.93 334	90.21 332	93.09 359	94.31 397	85.89 376	95.33 367	97.26 246	91.06 242	89.38 341	95.44 309	68.61 437	98.60 268	89.46 285	91.05 338	94.79 414

PCF-MVS	89.48 11	91.56 298	89.95 343	96.36 128	96.60 240	92.52 105	92.51 467	97.26 246	79.41 475	88.90 355	96.56 247	84.04 223	99.55 110	77.01 460	97.30 183	97.01 295
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
hybrid		94.76 158	94.60 147	95.27 219	96.24 280	88.36 296	96.05 321	97.25 249	91.40 221	95.40 159	97.59 170	85.48 191	98.63 263	95.23 128	96.71 212	98.83 152

ACMP	89.59 10	92.62 250	92.14 245	94.05 300	96.40 267	88.20 307	97.36 180	97.25 249	91.52 214	88.30 373	96.64 237	78.46 343	98.72 244	91.86 227	91.48 330	95.23 377
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 206	93.46 192	93.94 311	96.19 285	86.16 370	93.73 436	97.24 251	91.54 210	93.50 228	97.04 211	85.64 186	96.91 436	90.68 256	95.59 250	98.76 161

IMVS_0407		93.94 192	93.75 178	94.49 273	96.19 285	86.16 370	96.35 293	97.24 251	91.54 210	93.50 228	97.04 211	85.64 186	98.54 275	90.68 256	95.59 250	98.76 161

IMVS_0404		92.44 254	91.92 254	94.00 303	96.19 285	86.16 370	93.84 433	97.24 251	91.54 210	88.17 379	97.04 211	76.96 361	97.09 427	90.68 256	95.59 250	98.76 161

IMVS_0403		93.98 190	93.79 177	94.55 269	96.19 285	86.16 370	96.35 293	97.24 251	91.54 210	93.59 223	97.04 211	85.86 175	98.73 239	90.68 256	95.59 250	98.76 161

OPM-MVS		93.28 220	92.76 220	94.82 246	94.63 384	90.77 186	96.65 264	97.18 255	93.72 107	91.68 277	97.26 195	79.33 326	98.63 263	92.13 220	92.28 315	95.07 386
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 239	92.02 250	95.56 196	98.19 111	90.80 183	95.27 372	97.18 255	87.96 352	91.86 272	95.68 296	80.44 304	98.99 194	84.01 398	97.54 167	96.89 302

alignmvs		95.87 100	95.23 113	97.78 37	97.56 164	95.19 23	97.86 92	97.17 257	94.39 85	96.47 110	96.40 255	85.89 174	99.20 156	96.21 89	95.11 264	98.95 122

MVS_Test		94.89 148	94.62 146	95.68 190	96.83 213	89.55 242	96.70 258	97.17 257	91.17 235	95.60 151	96.11 274	87.87 127	98.76 229	93.01 205	97.17 190	98.72 169

Fast-Effi-MVS+		93.46 212	92.75 222	95.59 195	96.77 226	90.03 215	96.81 244	97.13 259	88.19 345	91.30 288	94.27 370	86.21 168	98.63 263	87.66 336	96.46 225	98.12 230

usedtu_dtu_shiyan1		91.65 289	90.67 309	94.60 261	93.65 417	90.95 175	94.86 391	97.12 260	89.69 292	89.21 349	93.62 401	81.17 287	97.67 382	87.54 340	89.14 360	95.17 383

FE-MVSNET3		91.65 289	90.67 309	94.60 261	93.65 417	90.95 175	94.86 391	97.12 260	89.69 292	89.21 349	93.62 401	81.17 287	97.67 382	87.54 340	89.14 360	95.17 383

EI-MVSNet		93.03 232	92.88 216	93.48 344	95.77 315	86.98 343	96.44 278	97.12 260	90.66 258	91.30 288	97.64 163	86.56 158	98.05 332	89.91 273	90.55 346	95.41 360

MVSTER		93.20 223	92.81 219	94.37 279	96.56 249	89.59 238	97.06 212	97.12 260	91.24 229	91.30 288	95.96 277	82.02 270	98.05 332	93.48 190	90.55 346	95.47 355

viewmambaseed2359dif		94.28 171	94.14 167	94.71 256	96.21 281	86.97 344	95.93 330	97.11 264	89.00 316	95.00 178	97.70 153	86.02 173	98.59 272	93.71 185	96.59 218	98.57 183

test_yl		94.78 156	94.23 165	96.43 120	97.74 144	91.22 158	96.85 236	97.10 265	91.23 232	95.71 144	96.93 218	84.30 216	99.31 145	93.10 198	95.12 262	98.75 165

DCV-MVSNet		94.78 156	94.23 165	96.43 120	97.74 144	91.22 158	96.85 236	97.10 265	91.23 232	95.71 144	96.93 218	84.30 216	99.31 145	93.10 198	95.12 262	98.75 165

LTVRE_ROB	88.41 13	90.99 330	89.92 345	94.19 291	96.18 289	89.55 242	96.31 299	97.09 267	87.88 355	85.67 428	95.91 280	78.79 339	98.57 273	81.50 423	89.98 351	94.44 428
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		93.46 212	93.23 202	94.17 292	96.12 297	85.42 385	96.43 280	97.08 268	92.91 153	94.21 203	98.00 107	80.82 296	98.74 237	94.41 167	89.05 362	98.34 213

test_fmvs1_n		92.73 248	92.88 216	92.29 386	96.08 302	81.05 445	97.98 72	97.08 268	90.72 253	96.79 89	98.18 91	63.07 471	98.45 282	97.62 40	98.42 136	97.36 282

v10		91.04 328	90.23 329	93.49 343	94.12 400	88.16 310	97.32 185	97.08 268	88.26 344	88.29 374	94.22 375	82.17 267	97.97 344	86.45 362	84.12 425	94.33 431

dtuplus		94.16 177	93.98 172	94.70 257	96.18 289	86.85 347	96.04 322	97.07 271	89.75 290	95.02 177	97.79 144	84.94 205	98.62 266	92.62 210	96.43 230	98.62 177

viewdifsd2359ckpt11		93.46 212	93.22 203	94.17 292	96.11 299	85.42 385	96.43 280	97.07 271	92.91 153	94.20 204	98.00 107	80.82 296	98.73 239	94.42 166	89.04 364	98.34 213

mamba_0408		93.70 203	92.99 209	95.83 172	96.79 219	90.38 202	88.69 494	97.07 271	90.96 245	93.68 219	97.31 190	84.97 203	98.76 229	90.95 247	96.51 219	98.35 209

SSM_04072		93.51 211	92.99 209	95.05 230	96.79 219	90.38 202	88.69 494	97.07 271	90.96 245	93.68 219	97.31 190	84.97 203	96.42 447	90.95 247	96.51 219	98.35 209

v144192		91.06 327	90.28 325	93.39 347	93.66 415	87.23 337	96.83 240	97.07 271	87.43 372	89.69 330	94.28 369	81.48 281	98.00 339	87.18 352	84.92 413	94.93 394

v1192		91.07 326	90.23 329	93.58 337	93.70 412	87.82 323	96.73 254	97.07 271	87.77 362	89.58 334	94.32 367	80.90 294	97.97 344	86.52 360	85.48 400	94.95 390

v8		91.29 318	90.53 317	93.57 339	94.15 399	88.12 311	97.34 182	97.06 277	88.99 317	88.32 372	94.26 372	83.08 241	98.01 338	87.62 338	83.92 429	94.57 424

mvs_anonymous		93.82 198	93.74 179	94.06 299	96.44 265	85.41 387	95.81 338	97.05 278	89.85 285	90.09 318	96.36 257	87.44 142	97.75 377	93.97 176	96.69 213	99.02 106

IterMVS-LS		92.29 264	91.94 253	93.34 349	96.25 279	86.97 344	96.57 276	97.05 278	90.67 256	89.50 339	94.80 337	86.59 157	97.64 387	89.91 273	86.11 395	95.40 363
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 337	90.03 340	93.29 351	93.55 419	86.96 346	96.74 253	97.04 280	87.36 374	89.52 338	94.34 364	80.23 309	97.97 344	86.27 363	85.21 406	94.94 392

CDS-MVSNet		94.14 181	93.54 186	95.93 163	96.18 289	91.46 150	96.33 297	97.04 280	88.97 319	93.56 224	96.51 249	87.55 135	97.89 361	89.80 276	95.95 237	98.44 200
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 373	89.26 366	91.19 421	95.16 354	80.29 456	94.53 401	97.03 282	91.79 203	88.86 358	94.10 379	69.94 426	97.82 367	85.29 381	86.66 391	95.45 358

v1144		91.37 311	90.60 313	93.68 329	93.89 407	88.23 303	96.84 239	97.03 282	88.37 341	89.69 330	94.39 359	82.04 269	97.98 341	87.80 323	85.37 402	94.84 403

PRO-TEST		94.38 168	94.94 128	92.69 375	97.21 175	80.23 459	97.52 155	97.02 284	93.62 111	94.32 199	97.21 198	81.92 275	99.15 166	96.65 70	99.00 108	98.70 172

v1240		90.70 343	89.85 347	93.23 353	93.51 422	86.80 348	96.61 270	97.02 284	87.16 379	89.58 334	94.31 368	79.55 323	97.98 341	85.52 378	85.44 401	94.90 397

EPP-MVSNet		95.22 125	95.04 122	95.76 182	97.49 165	89.56 240	98.67 15	97.00 286	90.69 254	94.24 202	97.62 166	89.79 94	98.81 214	93.39 194	96.49 223	98.92 130

V42		91.58 297	90.87 294	93.73 322	94.05 403	88.50 291	97.32 185	96.97 287	88.80 329	89.71 328	94.33 365	82.54 258	98.05 332	89.01 300	85.07 409	94.64 423

test_fmvs1		93.21 222	93.53 187	92.25 389	96.55 251	81.20 444	97.40 176	96.96 288	90.68 255	96.80 87	98.04 101	69.25 432	98.40 285	97.58 41	98.50 129	97.16 293

FMVSNet2		91.31 315	90.08 335	94.99 236	96.51 258	92.21 116	97.41 172	96.95 289	88.82 326	88.62 364	94.75 339	73.87 388	97.42 414	85.20 384	88.55 370	95.35 367

ACMH	87.59 16	90.53 348	89.42 362	93.87 316	96.21 281	87.92 317	97.24 195	96.94 290	88.45 339	83.91 450	96.27 262	71.92 406	98.62 266	84.43 392	89.43 357	95.05 388
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 312	90.27 326	94.59 263	96.51 258	91.18 165	97.50 157	96.93 291	88.82 326	89.35 342	94.51 352	73.87 388	97.29 422	86.12 368	88.82 365	95.31 370

test1		91.35 312	90.27 326	94.59 263	96.51 258	91.18 165	97.50 157	96.93 291	88.82 326	89.35 342	94.51 352	73.87 388	97.29 422	86.12 368	88.82 365	95.31 370

FMVSNet3		91.78 283	90.69 308	95.03 233	96.53 254	92.27 114	97.02 215	96.93 291	89.79 289	89.35 342	94.65 345	77.01 359	97.47 409	86.12 368	88.82 365	95.35 367

FMVSNet1		89.88 368	88.31 381	94.59 263	95.41 333	91.18 165	97.50 157	96.93 291	86.62 388	87.41 393	94.51 352	65.94 459	97.29 422	83.04 407	87.43 381	95.31 370

GeoE		93.89 195	93.28 200	95.72 188	96.96 200	89.75 230	98.24 43	96.92 295	89.47 300	92.12 263	97.21 198	84.42 213	98.39 290	87.71 328	96.50 222	99.01 109

SymmetryMVS		95.94 96	95.54 96	97.15 75	97.85 137	92.90 89	97.99 69	96.91 296	95.92 16	96.57 104	97.93 114	85.34 193	99.50 122	94.99 136	96.39 231	99.05 105

miper_enhance_ethall		91.54 301	91.01 290	93.15 357	95.35 339	87.07 342	93.97 425	96.90 297	86.79 385	89.17 351	93.43 414	86.55 159	97.64 387	89.97 272	86.93 386	94.74 419

eth_miper_zixun_eth		91.02 329	90.59 314	92.34 384	95.33 343	84.35 406	94.10 422	96.90 297	88.56 335	88.84 360	94.33 365	84.08 221	97.60 392	88.77 308	84.37 423	95.06 387

TAMVS		94.01 187	93.46 192	95.64 191	96.16 292	90.45 197	96.71 257	96.89 299	89.27 307	93.46 231	96.92 221	87.29 146	97.94 354	88.70 310	95.74 244	98.53 186

miper_ehance_all_eth		91.59 295	91.13 285	92.97 363	95.55 325	86.57 356	94.47 406	96.88 300	87.77 362	88.88 357	94.01 384	86.22 167	97.54 402	89.49 284	86.93 386	94.79 414

v2v482		91.59 295	90.85 297	93.80 319	93.87 408	88.17 309	96.94 225	96.88 300	89.54 297	89.53 337	94.90 331	81.70 279	98.02 337	89.25 293	85.04 411	95.20 378

CNLPA		94.28 171	93.53 187	96.52 108	98.38 91	92.55 104	96.59 273	96.88 300	90.13 279	91.91 269	97.24 196	85.21 197	99.09 178	87.64 337	97.83 160	97.92 248

PAPM		91.52 302	90.30 324	95.20 223	95.30 346	89.83 227	93.38 448	96.85 303	86.26 396	88.59 365	95.80 286	84.88 206	98.15 313	75.67 466	95.93 238	97.63 267

c3_l		91.38 309	90.89 293	92.88 367	95.58 323	86.30 364	94.68 396	96.84 304	88.17 346	88.83 361	94.23 373	85.65 183	97.47 409	89.36 288	84.63 415	94.89 398

pm-mvs1		90.72 342	89.65 357	93.96 308	94.29 398	89.63 235	97.79 107	96.82 305	89.07 312	86.12 421	95.48 308	78.61 341	97.78 372	86.97 356	81.67 442	94.46 426

test_vis1_n		92.37 259	92.26 243	92.72 373	94.75 378	82.64 427	98.02 66	96.80 306	91.18 234	97.77 61	97.93 114	58.02 482	98.29 300	97.63 38	98.21 145	97.23 290

CMPMVS	62.92 21	85.62 433	84.92 422	87.74 460	89.14 476	73.12 495	94.17 420	96.80 306	73.98 489	73.65 492	94.93 329	66.36 453	97.61 391	83.95 400	91.28 334	92.48 466
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 355	89.77 351	91.78 405	94.33 395	84.72 403	95.55 355	96.73 308	86.17 398	86.36 415	95.28 314	71.28 412	97.80 370	84.09 397	98.14 149	92.81 457

Effi-MVS+-dtu		93.08 229	93.21 204	92.68 377	96.02 306	83.25 420	97.14 208	96.72 309	93.85 103	91.20 295	93.44 411	83.08 241	98.30 299	91.69 233	95.73 245	96.50 313

TSAR-MVS + GP.		96.69 67	96.49 71	97.27 68	98.31 94	93.39 69	96.79 246	96.72 309	94.17 90	97.44 67	97.66 159	92.76 35	99.33 141	96.86 63	97.76 164	99.08 100

1112_ss		93.37 217	92.42 239	96.21 140	97.05 189	90.99 172	96.31 299	96.72 309	86.87 384	89.83 325	96.69 234	86.51 160	99.14 170	88.12 315	93.67 298	98.50 190

PVSNet	86.66 18	92.24 267	91.74 262	93.73 322	97.77 142	83.69 417	92.88 457	96.72 309	87.91 354	93.00 242	94.86 333	78.51 342	99.05 189	86.53 359	97.45 175	98.47 195

miper_lstm_enhance		90.50 351	90.06 339	91.83 401	95.33 343	83.74 414	93.86 431	96.70 313	87.56 370	87.79 385	93.81 392	83.45 232	96.92 435	87.39 346	84.62 416	94.82 409

v148		90.99 330	90.38 320	92.81 370	93.83 409	85.80 377	96.78 250	96.68 314	89.45 302	88.75 363	93.93 388	82.96 247	97.82 367	87.83 321	83.25 434	94.80 412

ACMH+	87.92 14	90.20 359	89.18 368	93.25 352	96.48 261	86.45 361	96.99 221	96.68 314	88.83 325	84.79 438	96.22 264	70.16 423	98.53 276	84.42 393	88.04 374	94.77 417

CANet_DTU		94.37 169	93.65 182	96.55 105	96.46 264	92.13 120	96.21 309	96.67 316	94.38 86	93.53 227	97.03 216	79.34 325	99.71 68	90.76 253	98.45 134	97.82 259

cl____		90.96 333	90.32 322	92.89 366	95.37 337	86.21 367	94.46 408	96.64 317	87.82 358	88.15 380	94.18 376	82.98 245	97.54 402	87.70 329	85.59 398	94.92 396

HY-MVS	89.66 9	93.87 196	92.95 213	96.63 99	97.10 183	92.49 106	95.64 351	96.64 317	89.05 314	93.00 242	95.79 289	85.77 179	99.45 130	89.16 298	94.35 277	97.96 245

Test_1112_low_res		92.84 244	91.84 257	95.85 171	97.04 191	89.97 222	95.53 357	96.64 317	85.38 408	89.65 332	95.18 319	85.86 175	99.10 175	87.70 329	93.58 303	98.49 192

DIV-MVS_self_test		90.97 332	90.33 321	92.88 367	95.36 338	86.19 369	94.46 408	96.63 320	87.82 358	88.18 378	94.23 373	82.99 244	97.53 404	87.72 326	85.57 399	94.93 394

Fast-Effi-MVS+-dtu		92.29 264	91.99 251	93.21 355	95.27 347	85.52 383	97.03 213	96.63 320	92.09 194	89.11 353	95.14 321	80.33 307	98.08 325	87.54 340	94.74 272	96.03 331

UnsupCasMVSNet_bld		82.13 452	79.46 457	90.14 438	88.00 491	82.47 432	90.89 482	96.62 322	78.94 477	75.61 487	84.40 500	56.63 485	96.31 450	77.30 457	66.77 500	91.63 478

cl22		91.21 320	90.56 316	93.14 358	96.09 301	86.80 348	94.41 410	96.58 323	87.80 360	88.58 366	93.99 386	80.85 295	97.62 390	89.87 275	86.93 386	94.99 389

jason		94.84 152	94.39 160	96.18 142	95.52 326	90.93 178	96.09 318	96.52 324	89.28 306	96.01 132	97.32 188	84.70 208	98.77 223	95.15 132	98.91 113	98.85 147
jason: jason.
tt0805		91.09 325	90.07 338	94.16 295	95.61 321	88.31 297	97.56 147	96.51 325	89.56 296	89.17 351	95.64 298	67.08 451	98.38 291	91.07 245	88.44 371	95.80 339

AUN-MVS		91.76 284	90.75 303	94.81 248	97.00 196	88.57 286	96.65 264	96.49 326	89.63 294	92.15 261	96.12 270	78.66 340	98.50 278	90.83 249	79.18 454	97.36 282

hse-mvs2		93.45 215	92.99 209	94.81 248	97.02 194	88.59 285	96.69 260	96.47 327	95.19 38	96.74 91	96.16 268	83.67 227	98.48 281	95.85 104	79.13 455	97.35 284

SD_0403		90.01 363	90.02 341	89.96 442	95.65 320	76.76 481	95.76 342	96.46 328	90.58 265	86.59 412	96.29 260	82.12 268	94.78 474	73.00 480	93.76 296	98.35 209

EG-PatchMatch MVS		87.02 409	85.44 411	91.76 407	92.67 444	85.00 397	96.08 319	96.45 329	83.41 444	79.52 476	93.49 407	57.10 484	97.72 379	79.34 448	90.87 343	92.56 463

KD-MVS_self_test		85.95 428	84.95 421	88.96 454	89.55 475	79.11 473	95.13 384	96.42 330	85.91 401	84.07 448	90.48 457	70.03 425	94.82 473	80.04 439	72.94 480	92.94 455

FE-MVSNET2		86.36 419	84.68 427	91.39 415	87.67 493	86.47 360	96.21 309	96.41 331	87.87 356	79.31 478	89.64 465	65.29 464	95.58 464	82.42 416	77.28 461	92.14 475

pmmvs6		87.81 395	86.19 403	92.69 375	91.32 461	86.30 364	97.34 182	96.41 331	80.59 471	84.05 449	94.37 361	67.37 446	97.67 382	84.75 388	79.51 453	94.09 438

PMMVS		92.86 242	92.34 240	94.42 278	94.92 369	86.73 351	94.53 401	96.38 333	84.78 420	94.27 201	95.12 323	83.13 240	98.40 285	91.47 237	96.49 223	98.12 230

RPSCF		90.75 340	90.86 295	90.42 435	96.84 211	76.29 485	95.61 352	96.34 334	83.89 431	91.38 282	97.87 128	76.45 365	98.78 219	87.16 353	92.23 316	96.20 320

BP-MVS1		95.89 98	95.49 98	97.08 82	96.67 233	93.20 79	98.08 59	96.32 335	94.56 74	96.32 117	97.84 134	84.07 222	99.15 166	96.75 65	98.78 117	98.90 134

MSDG		91.42 307	90.24 328	94.96 241	97.15 181	88.91 274	93.69 439	96.32 335	85.72 404	86.93 408	96.47 251	80.24 308	98.98 195	80.57 436	95.05 265	96.98 296

blended_shiyan6		87.55 399	85.52 410	93.64 332	88.78 481	88.50 291	95.23 375	96.30 337	82.80 450	86.09 422	87.70 483	73.69 394	97.56 395	87.70 329	71.36 487	94.86 399

blend_shiyan4		86.87 410	84.61 428	93.67 330	88.87 479	88.70 280	95.17 382	96.30 337	82.80 450	86.16 418	87.11 488	65.12 467	97.55 397	87.73 324	72.21 483	94.75 418

WBMVS		90.69 345	89.99 342	92.81 370	96.48 261	85.00 397	95.21 378	96.30 337	89.46 301	89.04 354	94.05 383	72.45 403	97.82 367	89.46 285	87.41 383	95.61 350

blended_shiyan8		87.58 398	85.55 409	93.66 331	88.76 483	88.54 288	95.21 378	96.29 340	82.81 449	86.25 416	87.73 482	73.70 393	97.58 394	87.81 322	71.42 486	94.85 402

OurMVSNet-221017-0		90.51 350	90.19 333	91.44 413	93.41 428	81.25 442	96.98 222	96.28 341	91.68 207	86.55 413	96.30 259	74.20 387	97.98 341	88.96 303	87.40 384	95.09 385

wanda-best-256-512		87.29 402	85.21 415	93.53 340	88.54 487	88.21 305	94.51 404	96.27 342	82.69 453	85.92 424	86.89 491	73.04 397	97.55 397	87.68 333	71.36 487	94.83 404

FE-blended-shiyan7		87.29 402	85.21 415	93.53 340	88.54 487	88.21 305	94.51 404	96.27 342	82.69 453	85.92 424	86.89 491	73.03 398	97.55 397	87.68 333	71.36 487	94.83 404

MVP-Stereo		90.74 341	90.08 335	92.71 374	93.19 433	88.20 307	95.86 334	96.27 342	86.07 399	84.86 437	94.76 338	77.84 354	97.75 377	83.88 402	98.01 155	92.17 474
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 144	94.56 150	96.29 134	96.34 274	91.21 160	95.83 336	96.27 342	88.93 321	96.22 122	96.88 223	86.20 169	98.85 208	95.27 127	99.05 103	98.82 153

BH-untuned		92.94 237	92.62 229	93.92 315	97.22 173	86.16 370	96.40 288	96.25 346	90.06 280	89.79 326	96.17 267	83.19 237	98.35 293	87.19 351	97.27 185	97.24 289

CL-MVSNet_self_test		86.31 421	85.15 418	89.80 444	88.83 480	81.74 440	93.93 428	96.22 347	86.67 387	85.03 435	90.80 455	78.09 350	94.50 475	74.92 469	71.86 484	93.15 453

IS-MVSNet		94.90 147	94.52 154	96.05 151	97.67 148	90.56 193	98.44 26	96.22 347	93.21 132	93.99 211	97.74 149	85.55 189	98.45 282	89.98 271	97.86 159	99.14 90

FA-MVS(test-final)		93.52 210	92.92 214	95.31 218	96.77 226	88.54 288	94.82 393	96.21 349	89.61 295	94.20 204	95.25 317	83.24 235	99.14 170	90.01 270	96.16 234	98.25 218

gbinet_0.2-2-1-0.02		87.30 401	85.16 417	93.69 326	88.70 486	88.81 277	95.14 383	96.20 350	83.03 447	86.14 420	87.06 489	71.26 413	97.40 416	87.46 344	71.49 485	94.86 399

GA-MVS		91.38 309	90.31 323	94.59 263	94.65 383	87.62 327	94.34 413	96.19 351	90.73 252	90.35 306	93.83 389	71.84 407	97.96 348	87.22 350	93.61 301	98.21 221

LuminaMVS		94.89 148	94.35 162	96.53 106	95.48 328	92.80 93	96.88 234	96.18 352	92.85 158	95.92 136	96.87 225	81.44 282	98.83 211	96.43 79	97.10 192	97.94 247

IterMVS-SCA-FT		90.31 353	89.81 349	91.82 402	95.52 326	84.20 409	94.30 416	96.15 353	90.61 262	87.39 394	94.27 370	75.80 371	96.44 446	87.34 347	86.88 390	94.82 409

IterMVS		90.15 361	89.67 355	91.61 409	95.48 328	83.72 415	94.33 414	96.12 354	89.99 281	87.31 397	94.15 378	75.78 373	96.27 451	86.97 356	86.89 389	94.83 404
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 247	91.51 271	96.52 108	98.77 63	90.99 172	97.38 179	96.08 355	82.38 456	89.29 345	97.87 128	83.77 225	99.69 74	81.37 429	96.69 213	98.89 140

pmmvs4		90.93 334	89.85 347	94.17 292	93.34 430	90.79 184	94.60 398	96.02 356	84.62 421	87.45 391	95.15 320	81.88 276	97.45 411	87.70 329	87.87 376	94.27 435

ppachtmachnet_test		88.35 390	87.29 389	91.53 410	92.45 450	83.57 418	93.75 435	95.97 357	84.28 424	85.32 433	94.18 376	79.00 337	96.93 434	75.71 465	84.99 412	94.10 436

Anonymous20240521		86.42 418	85.44 411	89.34 451	90.33 468	79.79 463	96.73 254	95.92 358	83.71 436	83.25 454	91.36 452	63.92 469	96.01 452	78.39 452	85.36 403	92.22 472

ITE_SJBPF				92.43 380	95.34 340	85.37 390		95.92 358	91.47 216	87.75 387	96.39 256	71.00 415	97.96 348	82.36 417	89.86 353	93.97 441

test_fmvs2		89.77 372	89.93 344	89.31 452	93.68 414	76.37 484	97.64 135	95.90 360	89.84 286	91.49 280	96.26 263	58.77 480	97.10 426	94.65 160	91.13 336	94.46 426

USDC		88.94 381	87.83 386	92.27 387	94.66 382	84.96 399	93.86 431	95.90 360	87.34 375	83.40 452	95.56 302	67.43 445	98.19 310	82.64 415	89.67 355	93.66 445

COLMAP_ROB	87.81 15	90.40 352	89.28 365	93.79 320	97.95 130	87.13 341	96.92 228	95.89 362	82.83 448	86.88 410	97.18 200	73.77 391	99.29 148	78.44 451	93.62 300	94.95 390
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 198	93.08 207	96.02 155	97.88 136	89.96 223	97.72 119	95.85 363	92.43 176	95.86 138	98.44 64	68.42 441	99.39 136	96.31 81	94.85 266	98.71 171

VDDNet		93.05 231	92.07 246	96.02 155	96.84 211	90.39 201	98.08 59	95.85 363	86.22 397	95.79 141	98.46 62	67.59 444	99.19 157	94.92 139	94.85 266	98.47 195

mvsmamba		94.57 162	94.14 167	95.87 167	97.03 192	89.93 224	97.84 96	95.85 363	91.34 223	94.79 185	96.80 226	80.67 298	98.81 214	94.85 144	98.12 150	98.85 147

Vis-MVSNet (Re-imp)		94.15 178	93.88 175	94.95 242	97.61 156	87.92 317	98.10 57	95.80 366	92.22 185	93.02 241	97.45 180	84.53 211	97.91 360	88.24 314	97.97 156	99.02 106

MM		97.29 31	96.98 42	98.23 13	98.01 125	95.03 29	98.07 61	95.76 367	97.78 1	97.52 64	98.80 40	88.09 120	99.86 11	99.44 2	99.37 67	99.80 3

KD-MVS_2432*1600		84.81 439	82.64 442	91.31 416	91.07 463	85.34 391	91.22 476	95.75 368	85.56 406	83.09 455	90.21 460	67.21 447	95.89 454	77.18 458	62.48 506	92.69 459

miper_refine_blended		84.81 439	82.64 442	91.31 416	91.07 463	85.34 391	91.22 476	95.75 368	85.56 406	83.09 455	90.21 460	67.21 447	95.89 454	77.18 458	62.48 506	92.69 459

FE-MVS		92.05 275	91.05 288	95.08 229	96.83 213	87.93 316	93.91 430	95.70 370	86.30 394	94.15 208	94.97 326	76.59 363	99.21 155	84.10 396	96.86 201	98.09 237

tpm cat1		88.36 389	87.21 392	91.81 403	95.13 359	80.55 451	92.58 466	95.70 370	74.97 488	87.45 391	91.96 444	78.01 353	98.17 312	80.39 438	88.74 368	96.72 307

our_test_3		88.78 385	87.98 385	91.20 420	92.45 450	82.53 429	93.61 444	95.69 372	85.77 403	84.88 436	93.71 394	79.99 313	96.78 442	79.47 445	86.24 392	94.28 434

BH-w/o		92.14 272	91.75 260	93.31 350	96.99 197	85.73 380	95.67 346	95.69 372	88.73 331	89.26 347	94.82 336	82.97 246	98.07 329	85.26 383	96.32 232	96.13 327

CR-MVSNet		90.82 338	89.77 351	93.95 309	94.45 391	87.19 338	90.23 485	95.68 374	86.89 383	92.40 251	92.36 435	80.91 292	97.05 429	81.09 433	93.95 293	97.60 272

Patchmtry		88.64 387	87.25 390	92.78 372	94.09 401	86.64 352	89.82 489	95.68 374	80.81 468	87.63 389	92.36 435	80.91 292	97.03 430	78.86 449	85.12 408	94.67 421

testing91		91.90 280	91.02 289	94.53 271	96.54 252	86.55 358	95.86 334	95.64 376	91.77 204	91.89 270	93.47 409	69.94 426	98.86 206	90.23 269	93.86 295	98.18 223

BH-RMVSNet		92.72 249	91.97 252	94.97 240	97.16 178	87.99 315	96.15 315	95.60 377	90.62 261	91.87 271	97.15 203	78.41 344	98.57 273	83.16 405	97.60 166	98.36 207

PVSNet_0	82.17 19	85.46 434	83.64 435	90.92 424	95.27 347	79.49 469	90.55 483	95.60 377	83.76 435	83.00 457	89.95 462	71.09 414	97.97 344	82.75 413	60.79 508	95.31 370

guyue		95.17 131	94.96 127	95.82 173	96.97 199	89.65 234	97.56 147	95.58 379	94.82 59	95.72 143	97.42 183	82.90 248	98.84 210	96.71 68	96.93 197	98.96 118

SCA		91.84 282	91.18 284	93.83 317	95.59 322	84.95 400	94.72 395	95.58 379	90.82 248	92.25 259	93.69 396	75.80 371	98.10 320	86.20 365	95.98 236	98.45 197

MonoMVSNet		91.92 278	91.77 258	92.37 381	92.94 438	83.11 423	97.09 211	95.55 381	92.91 153	90.85 298	94.55 349	81.27 286	96.52 445	93.01 205	87.76 377	97.47 278

dtuonly		90.88 336	91.13 285	90.13 439	92.98 437	75.01 488	92.74 463	95.54 382	87.69 366	91.37 283	96.61 246	79.65 321	98.15 313	87.44 345	96.21 233	97.23 290

usedtu_blend_shiyan5		87.06 408	84.84 423	93.69 326	88.54 487	88.70 280	95.83 336	95.54 382	78.74 478	85.92 424	86.89 491	73.03 398	97.55 397	87.73 324	71.36 487	94.83 404

AllTest		90.23 357	88.98 371	93.98 305	97.94 131	86.64 352	96.51 277	95.54 382	85.38 408	85.49 430	96.77 228	70.28 421	99.15 166	80.02 440	92.87 305	96.15 325

TestCases				93.98 305	97.94 131	86.64 352		95.54 382	85.38 408	85.49 430	96.77 228	70.28 421	99.15 166	80.02 440	92.87 305	96.15 325

mmtdpeth		89.70 374	88.96 372	91.90 398	95.84 314	84.42 405	97.46 168	95.53 386	90.27 274	94.46 196	90.50 456	69.74 430	98.95 196	97.39 54	69.48 494	92.34 468

tpmvs		89.83 371	89.15 369	91.89 399	94.92 369	80.30 455	93.11 453	95.46 387	86.28 395	88.08 381	92.65 425	80.44 304	98.52 277	81.47 425	89.92 352	96.84 303

pmmvs5		89.86 370	88.87 375	92.82 369	92.86 440	86.23 366	96.26 304	95.39 388	84.24 426	87.12 399	94.51 352	74.27 386	97.36 419	87.61 339	87.57 379	94.86 399

PatchmatchNet		91.91 279	91.35 273	93.59 336	95.38 335	84.11 410	93.15 452	95.39 388	89.54 297	92.10 264	93.68 398	82.82 251	98.13 315	84.81 387	95.32 258	98.52 187
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 306	91.32 275	91.79 404	95.15 357	79.20 472	93.42 447	95.37 390	88.55 336	93.49 230	93.67 399	82.49 260	98.27 303	90.41 264	89.34 358	97.90 249

Anonymous20231206		87.09 407	86.14 404	89.93 443	91.22 462	80.35 453	96.11 316	95.35 391	83.57 439	84.16 444	93.02 419	73.54 395	95.61 462	72.16 482	86.14 394	93.84 443

MIMVSNet1		84.93 437	83.05 439	90.56 433	89.56 474	84.84 402	95.40 363	95.35 391	83.91 430	80.38 472	92.21 440	57.23 483	93.34 490	70.69 488	82.75 440	93.50 448

TDRefinement		86.53 414	84.76 425	91.85 400	82.23 510	84.25 407	96.38 290	95.35 391	84.97 417	84.09 447	94.94 328	65.76 460	98.34 296	84.60 391	74.52 472	92.97 454

TR-MVS		91.48 305	90.59 314	94.16 295	96.40 267	87.33 331	95.67 346	95.34 394	87.68 367	91.46 281	95.52 305	76.77 362	98.35 293	82.85 410	93.61 301	96.79 305

EPNet_dtu		91.71 285	91.28 278	92.99 362	93.76 411	83.71 416	96.69 260	95.28 395	93.15 139	87.02 404	95.95 278	83.37 233	97.38 418	79.46 446	96.84 203	97.88 251
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 402	85.79 406	91.78 405	94.80 376	87.28 333	95.49 359	95.28 395	84.09 428	83.85 451	91.82 445	62.95 472	94.17 480	78.48 450	85.34 404	93.91 442

MDTV_nov1_ep13			90.76 301		95.22 351	80.33 454	93.03 455	95.28 395	88.14 349	92.84 248	93.83 389	81.34 283	98.08 325	82.86 408	94.34 278

LF4IMVS		87.94 393	87.25 390	89.98 441	92.38 453	80.05 462	94.38 411	95.25 398	87.59 369	84.34 441	94.74 340	64.31 468	97.66 386	84.83 386	87.45 380	92.23 471

TransMVSNet (Re)		88.94 381	87.56 387	93.08 360	94.35 394	88.45 294	97.73 116	95.23 399	87.47 371	84.26 443	95.29 312	79.86 316	97.33 420	79.44 447	74.44 474	93.45 450

test20.03		86.14 425	85.40 413	88.35 455	90.12 469	80.06 461	95.90 333	95.20 400	88.59 332	81.29 466	93.62 401	71.43 411	92.65 496	71.26 486	81.17 445	92.34 468

new-patchmatchnet		83.18 446	81.87 449	87.11 464	86.88 497	75.99 487	93.70 437	95.18 401	85.02 416	77.30 485	88.40 475	65.99 458	93.88 486	74.19 474	70.18 492	91.47 483

MDA-MVSNet_test_wron		85.87 431	84.23 432	90.80 430	92.38 453	82.57 428	93.17 450	95.15 402	82.15 457	67.65 499	92.33 438	78.20 346	95.51 467	77.33 455	79.74 450	94.31 433

YYNet1		85.87 431	84.23 432	90.78 431	92.38 453	82.46 433	93.17 450	95.14 403	82.12 458	67.69 497	92.36 435	78.16 349	95.50 468	77.31 456	79.73 451	94.39 429

Baseline_NR-MVSNet		91.20 321	90.62 311	92.95 364	93.83 409	88.03 313	97.01 218	95.12 404	88.42 340	89.70 329	95.13 322	83.47 230	97.44 412	89.66 281	83.24 435	93.37 451

thres200		92.23 268	91.39 272	94.75 255	97.61 156	89.03 267	96.60 272	95.09 405	92.08 195	93.28 236	94.00 385	78.39 345	99.04 192	81.26 432	94.18 284	96.19 321

ADS-MVSNet		89.89 367	88.68 377	93.53 340	95.86 309	84.89 401	90.93 480	95.07 406	83.23 445	91.28 291	91.81 446	79.01 335	97.85 363	79.52 443	91.39 332	97.84 256

pmmvs-eth3d		86.22 423	84.45 429	91.53 410	88.34 490	87.25 335	94.47 406	95.01 407	83.47 441	79.51 477	89.61 466	69.75 429	95.71 459	83.13 406	76.73 465	91.64 477

Anonymous202405211		92.07 274	90.83 299	95.76 182	98.19 111	88.75 278	97.58 143	95.00 408	86.00 400	93.64 222	97.45 180	66.24 456	99.53 114	90.68 256	92.71 310	99.01 109

MDA-MVSNet-bldmvs		85.00 436	82.95 441	91.17 422	93.13 435	83.33 419	94.56 400	95.00 408	84.57 422	65.13 503	92.65 425	70.45 420	95.85 456	73.57 477	77.49 460	94.33 431

ambc				86.56 469	83.60 505	70.00 499	85.69 506	94.97 410		80.60 471	88.45 474	37.42 504	96.84 439	82.69 414	75.44 470	92.86 456

testgi		87.97 392	87.21 392	90.24 437	92.86 440	80.76 446	96.67 263	94.97 410	91.74 205	85.52 429	95.83 284	62.66 475	94.47 477	76.25 462	88.36 372	95.48 353

myMVS_eth3d28		91.52 302	90.97 291	93.17 356	96.91 203	83.24 421	95.61 352	94.96 412	92.24 184	91.98 267	93.28 416	69.31 431	98.40 285	88.71 309	95.68 247	97.88 251

dp		88.90 383	88.26 383	90.81 428	94.58 387	76.62 483	92.85 459	94.93 413	85.12 414	90.07 320	93.07 418	75.81 370	98.12 318	80.53 437	87.42 382	97.71 264

test_fmvs3		83.21 445	83.02 440	83.78 473	86.77 498	68.34 502	96.76 252	94.91 414	86.49 390	84.14 446	89.48 467	36.04 505	91.73 499	91.86 227	80.77 447	91.26 485

test_0402		86.46 417	84.79 424	91.45 412	95.02 363	85.55 382	96.29 301	94.89 415	80.90 465	82.21 461	93.97 387	68.21 442	97.29 422	62.98 502	88.68 369	91.51 480

tfpn200view9		92.38 258	91.52 269	94.95 242	97.85 137	89.29 256	97.41 172	94.88 416	92.19 190	93.27 237	94.46 357	78.17 347	99.08 180	81.40 426	94.08 288	96.48 314

CVMVSNet		91.23 319	91.75 260	89.67 445	95.77 315	74.69 489	96.44 278	94.88 416	85.81 402	92.18 260	97.64 163	79.07 330	95.58 464	88.06 317	95.86 242	98.74 168

thres400		92.42 256	91.52 269	95.12 228	97.85 137	89.29 256	97.41 172	94.88 416	92.19 190	93.27 237	94.46 357	78.17 347	99.08 180	81.40 426	94.08 288	96.98 296

tt0320		85.39 435	83.12 438	92.19 391	93.44 427	85.79 378	96.19 312	94.87 419	71.19 496	82.92 458	91.76 448	58.43 481	96.81 440	81.03 434	78.26 459	93.98 440

EPNet		95.20 126	94.56 150	97.14 76	92.80 442	92.68 99	97.85 95	94.87 419	96.64 9	92.46 250	97.80 142	86.23 166	99.65 80	93.72 184	98.62 125	99.10 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 293	90.72 306	94.32 284	96.48 261	86.11 375	95.81 338	94.76 421	91.55 209	91.75 275	93.44 411	68.55 439	98.82 212	90.43 263	93.69 297	98.04 241

sc_t1		86.48 416	84.10 434	93.63 333	93.45 426	85.76 379	96.79 246	94.71 422	73.06 493	86.45 414	94.35 362	55.13 488	97.95 352	84.38 394	78.55 458	97.18 292

SixPastTwentyTwo		89.15 379	88.54 379	90.98 423	93.49 423	80.28 457	96.70 258	94.70 423	90.78 249	84.15 445	95.57 301	71.78 408	97.71 380	84.63 390	85.07 409	94.94 392

thres100view900		92.43 255	91.58 266	94.98 238	97.92 133	89.37 252	97.71 122	94.66 424	92.20 188	93.31 235	94.90 331	78.06 351	99.08 180	81.40 426	94.08 288	96.48 314

thres600view7		92.49 253	91.60 265	95.18 224	97.91 134	89.47 246	97.65 131	94.66 424	92.18 192	93.33 234	94.91 330	78.06 351	99.10 175	81.61 422	94.06 292	96.98 296

PatchT		88.87 384	87.42 388	93.22 354	94.08 402	85.10 395	89.51 490	94.64 426	81.92 459	92.36 254	88.15 478	80.05 312	97.01 432	72.43 481	93.65 299	97.54 275

nomal-1		91.63 291	90.62 311	94.66 260	96.07 305	87.86 320	95.58 354	94.63 427	89.80 288	89.61 333	92.66 424	72.05 404	98.29 300	90.61 262	94.55 276	97.82 259

baseline1		92.82 245	91.90 255	95.55 198	97.20 176	90.77 186	97.19 203	94.58 428	92.20 188	92.36 254	96.34 258	84.16 220	98.21 307	89.20 296	83.90 430	97.68 266

AstraMVS		94.82 154	94.64 145	95.34 217	96.36 273	88.09 312	97.58 143	94.56 429	94.98 48	95.70 146	97.92 117	81.93 274	98.93 199	96.87 62	95.88 240	98.99 114

UBG		91.55 299	90.76 301	93.94 311	96.52 257	85.06 396	95.22 376	94.54 430	90.47 270	91.98 267	92.71 423	72.02 405	98.74 237	88.10 316	95.26 260	98.01 243

Gipuma		67.86 474	65.41 475	75.18 492	92.66 445	73.45 493	66.50 527	94.52 431	53.33 517	57.80 513	66.07 523	30.81 507	89.20 503	48.15 518	78.88 457	62.90 526
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 288	90.75 303	94.47 274	96.53 254	86.56 357	95.76 342	94.51 432	91.10 241	91.24 293	93.59 404	68.59 438	98.86 206	91.10 244	94.29 280	98.00 244

dtuonlycased		85.91 429	85.69 407	86.60 468	92.42 452	76.96 480	93.66 441	94.49 433	86.68 386	80.87 467	92.00 441	71.52 409	93.23 493	79.58 442	79.97 449	89.60 492

CostFormer		91.18 324	90.70 307	92.62 378	94.84 374	81.76 439	94.09 423	94.43 434	84.15 427	92.72 249	93.77 393	79.43 324	98.20 308	90.70 255	92.18 319	97.90 249

tpm2		89.96 364	89.21 367	92.23 390	94.91 371	81.25 442	93.78 434	94.42 435	80.62 470	91.56 278	93.44 411	76.44 366	97.94 354	85.60 377	92.08 323	97.49 276

testing3-2		92.10 273	92.05 247	92.27 387	97.71 146	79.56 466	97.42 170	94.41 436	93.53 119	93.22 239	95.49 306	69.16 433	99.11 173	93.25 195	94.22 282	98.13 228

MGCNet		96.74 64	96.31 81	98.02 22	96.87 207	94.65 33	97.58 143	94.39 437	96.47 12	97.16 76	98.39 68	87.53 137	99.87 8	98.97 20	99.41 59	99.55 43

JIA-IIPM		88.26 391	87.04 395	91.91 397	93.52 421	81.42 441	89.38 491	94.38 438	80.84 467	90.93 297	80.74 509	79.22 327	97.92 357	82.76 412	91.62 327	96.38 317

dmvs_re		90.21 358	89.50 360	92.35 382	95.47 332	85.15 393	95.70 345	94.37 439	90.94 247	88.42 368	93.57 405	74.63 383	95.67 461	82.80 411	89.57 356	96.22 319

Patchmatch-test		89.42 377	87.99 384	93.70 325	95.27 347	85.11 394	88.98 492	94.37 439	81.11 464	87.10 402	93.69 396	82.28 264	97.50 407	74.37 472	94.76 270	98.48 194

LCM-MVSNet		72.55 462	69.39 467	82.03 477	70.81 532	65.42 509	90.12 487	94.36 441	55.02 514	65.88 501	81.72 506	24.16 515	89.96 500	74.32 473	68.10 498	90.71 488

ADS-MVSNet2		89.45 376	88.59 378	92.03 394	95.86 309	82.26 435	90.93 480	94.32 442	83.23 445	91.28 291	91.81 446	79.01 335	95.99 453	79.52 443	91.39 332	97.84 256

mvs5depth		86.53 414	85.08 419	90.87 425	88.74 484	82.52 430	91.91 471	94.23 443	86.35 393	87.11 401	93.70 395	66.52 452	97.76 375	81.37 429	75.80 467	92.31 470

EU-MVSNet		88.72 386	88.90 374	88.20 457	93.15 434	74.21 491	96.63 269	94.22 444	85.18 412	87.32 396	95.97 276	76.16 368	94.98 472	85.27 382	86.17 393	95.41 360

usedtu_dtu_shiyan2		80.00 455	76.91 461	89.27 453	82.13 511	79.69 465	95.45 361	94.20 445	72.95 494	75.80 486	87.75 481	44.44 500	94.30 479	70.64 489	68.81 497	93.84 443

PatchmatchNet2					0.00 564	79.04 475	92.75 462	94.19 446	78.18 481
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
tt0320-xc		84.83 438	82.33 446	92.31 385	93.66 415	86.20 368	96.17 314	94.06 447	71.26 495	82.04 463	92.22 439	55.07 489	96.72 443	81.49 424	75.04 471	94.02 439

MIMVSNet		88.50 388	86.76 398	93.72 324	94.84 374	87.77 324	91.39 474	94.05 448	86.41 392	87.99 383	92.59 428	63.27 470	95.82 458	77.44 454	92.84 307	97.57 274

OpenMVS_ROB	81.14 20	84.42 441	82.28 447	90.83 426	90.06 470	84.05 412	95.73 344	94.04 449	73.89 491	80.17 475	91.53 450	59.15 479	97.64 387	66.92 496	89.05 362	90.80 487

TinyColmap		86.82 412	85.35 414	91.21 418	94.91 371	82.99 425	93.94 427	94.02 450	83.58 438	81.56 465	94.68 342	62.34 476	98.13 315	75.78 464	87.35 385	92.52 465

ETVMVS		90.52 349	89.14 370	94.67 259	96.81 218	87.85 322	95.91 332	93.97 451	89.71 291	92.34 257	92.48 430	65.41 462	97.96 348	81.37 429	94.27 281	98.21 221

IB-MVS	87.33 17	89.91 365	88.28 382	94.79 252	95.26 350	87.70 325	95.12 385	93.95 452	89.35 305	87.03 403	92.49 429	70.74 418	99.19 157	89.18 297	81.37 444	97.49 276
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		87.13 406	87.02 396	87.47 461	95.16 354	73.21 494	95.00 387	93.93 453	88.55 336	86.96 405	91.99 442	75.90 369	94.00 483	61.59 504	94.11 285	95.20 378

myMVS_eth3d		87.18 405	86.38 401	89.58 446	95.16 354	79.53 467	95.00 387	93.93 453	88.55 336	86.96 405	91.99 442	56.23 486	94.00 483	75.47 468	94.11 285	95.20 378

testing222		90.31 353	88.96 372	94.35 280	96.54 252	87.29 332	95.50 358	93.84 455	90.97 244	91.75 275	92.96 420	62.18 477	98.00 339	82.86 408	94.08 288	97.76 262

test_f		80.57 454	79.62 456	83.41 475	83.38 507	67.80 504	93.57 445	93.72 456	80.80 469	77.91 484	87.63 484	33.40 506	92.08 498	87.14 354	79.04 456	90.34 489

LCM-MVSNet-Re		92.50 251	92.52 235	92.44 379	96.82 216	81.89 438	96.92 228	93.71 457	92.41 177	84.30 442	94.60 347	85.08 199	97.03 430	91.51 235	97.36 178	98.40 203

tpm		90.25 356	89.74 354	91.76 407	93.92 405	79.73 464	93.98 424	93.54 458	88.28 343	91.99 266	93.25 417	77.51 357	97.44 412	87.30 349	87.94 375	98.12 230

ET-MVSNet_ETH3D		91.49 304	90.11 334	95.63 192	96.40 267	91.57 144	95.34 366	93.48 459	90.60 264	75.58 488	95.49 306	80.08 311	96.79 441	94.25 172	89.76 354	98.52 187

LFMVS		93.60 205	92.63 228	96.52 108	98.13 117	91.27 157	97.94 82	93.39 460	90.57 266	96.29 119	98.31 81	69.00 434	99.16 164	94.18 173	95.87 241	99.12 94

MVStest1		82.38 451	80.04 455	89.37 449	87.63 494	82.83 426	95.03 386	93.37 461	73.90 490	73.50 493	94.35 362	62.89 473	93.25 492	73.80 475	65.92 502	92.04 476

FE-MVSNET		83.85 442	81.97 448	89.51 447	87.19 496	83.19 422	95.21 378	93.17 462	83.45 442	78.90 480	89.05 470	65.46 461	93.84 487	69.71 491	75.56 469	91.51 480

Patchmatch-RL test		87.38 400	86.24 402	90.81 428	88.74 484	78.40 477	88.12 501	93.17 462	87.11 380	82.17 462	89.29 468	81.95 272	95.60 463	88.64 311	77.02 462	98.41 202

ttmdpeth		85.91 429	84.76 425	89.36 450	89.14 476	80.25 458	95.66 349	93.16 464	83.77 434	83.39 453	95.26 316	66.24 456	95.26 471	80.65 435	75.57 468	92.57 462

test-LLR		91.42 307	91.19 283	92.12 392	94.59 385	80.66 448	94.29 417	92.98 465	91.11 239	90.76 300	92.37 432	79.02 333	98.07 329	88.81 306	96.74 209	97.63 267

test-mter		90.19 360	89.54 359	92.12 392	94.59 385	80.66 448	94.29 417	92.98 465	87.68 367	90.76 300	92.37 432	67.67 443	98.07 329	88.81 306	96.74 209	97.63 267

WB-MVSnew		89.88 368	89.56 358	90.82 427	94.57 388	83.06 424	95.65 350	92.85 467	87.86 357	90.83 299	94.10 379	79.66 320	96.88 437	76.34 461	94.19 283	92.54 464

testing3		87.67 396	86.88 397	90.05 440	96.14 295	80.71 447	97.10 210	92.85 467	90.15 278	87.54 390	94.55 349	55.70 487	94.10 481	73.77 476	94.10 287	95.35 367

test_method		66.11 476	64.89 476	69.79 499	72.62 530	35.23 539	65.19 528	92.83 469	20.35 534	65.20 502	88.08 479	43.14 502	82.70 516	73.12 479	63.46 504	91.45 484

test0.0.03 1		89.37 378	88.70 376	91.41 414	92.47 449	85.63 381	95.22 376	92.70 470	91.11 239	86.91 409	93.65 400	79.02 333	93.19 494	78.00 453	89.18 359	95.41 360

new_pmnet		82.89 449	81.12 454	88.18 458	89.63 473	80.18 460	91.77 472	92.57 471	76.79 486	75.56 489	88.23 477	61.22 478	94.48 476	71.43 484	82.92 438	89.87 490

mvsany_test1		93.93 194	93.98 172	93.78 321	94.94 368	86.80 348	94.62 397	92.55 472	88.77 330	96.85 86	98.49 58	88.98 102	98.08 325	95.03 134	95.62 249	96.46 316

0.4-1-1-0.2		86.27 422	83.62 436	94.20 290	90.38 467	87.69 326	91.04 479	92.52 473	83.43 443	85.22 434	81.49 507	65.31 463	98.29 300	88.90 305	74.30 475	96.64 309

0.3-1-1-0.015		86.11 426	83.37 437	94.34 282	90.58 466	88.02 314	91.64 473	92.45 474	83.56 440	84.46 439	81.84 505	62.73 474	98.31 297	88.98 302	74.09 476	96.70 308

thisisatest0515		92.29 264	91.30 277	95.25 222	96.60 240	88.90 275	94.36 412	92.32 475	87.92 353	93.43 232	94.57 348	77.28 358	99.00 193	89.42 287	95.86 242	97.86 255

0.4-1-1-0.1		86.83 411	84.27 431	94.50 272	91.39 460	88.23 303	92.62 465	92.27 476	84.04 429	86.01 423	83.30 502	65.29 464	98.31 297	89.08 299	74.45 473	96.96 300

thisisatest0530		93.03 232	92.21 244	95.49 207	97.07 184	89.11 265	97.49 165	92.19 477	90.16 277	94.09 209	96.41 254	76.43 367	99.05 189	90.38 265	95.68 247	98.31 215

tttt0517		92.96 235	92.33 241	94.87 245	97.11 182	87.16 340	97.97 78	92.09 478	90.63 260	93.88 216	97.01 217	76.50 364	99.06 186	90.29 268	95.45 256	98.38 205

K. test v3		87.64 397	86.75 399	90.32 436	93.02 436	79.48 470	96.61 270	92.08 479	90.66 258	80.25 474	94.09 381	67.21 447	96.65 444	85.96 373	80.83 446	94.83 404

TESTMET0.1,1		90.06 362	89.42 362	91.97 395	94.41 393	80.62 450	94.29 417	91.97 480	87.28 377	90.44 304	92.47 431	68.79 435	97.67 382	88.50 313	96.60 217	97.61 271

PM-MVS		83.48 444	81.86 450	88.31 456	87.83 492	77.59 479	93.43 446	91.75 481	86.91 382	80.63 470	89.91 463	44.42 501	95.84 457	85.17 385	76.73 465	91.50 482

baseline2		91.63 291	90.86 295	93.94 311	94.33 395	86.32 363	95.92 331	91.64 482	89.37 304	86.94 407	94.69 341	81.62 280	98.69 248	88.64 311	94.57 275	96.81 304

ArgMatch-Sym		83.08 448	81.73 451	87.11 464	91.53 458	76.72 482	92.86 458	91.54 483	83.66 437	82.34 460	93.45 410	44.99 499	92.15 497	81.78 421	73.46 479	92.47 467

APD_test1		79.31 457	77.70 459	84.14 472	89.11 478	69.07 501	92.36 470	91.50 484	69.07 498	73.87 491	92.63 427	39.93 503	94.32 478	70.54 490	80.25 448	89.02 494

FPMVS		71.27 465	69.85 466	75.50 491	74.64 522	59.03 518	91.30 475	91.50 484	58.80 509	57.92 512	88.28 476	29.98 509	85.53 512	53.43 515	82.84 439	81.95 509

ArgMatch-SfM		83.09 447	81.67 452	87.34 463	91.48 459	76.29 485	92.76 461	91.31 486	84.26 425	81.99 464	93.35 415	45.52 498	92.98 495	81.83 420	72.49 482	92.76 458

door								91.13 487

door-mid								91.06 488

EGC-MVSNET		68.77 472	63.01 480	86.07 471	92.49 448	82.24 436	93.96 426	90.96 489	0.71 557	2.62 559	90.89 454	53.66 490	93.46 488	57.25 511	84.55 419	82.51 508

mvsany_test3		83.59 443	82.44 445	87.03 466	83.80 503	73.82 492	93.70 437	90.92 490	86.42 391	82.51 459	90.26 459	46.76 497	95.71 459	90.82 250	76.76 464	91.57 479

pmmvs3		79.97 456	77.50 460	87.39 462	82.80 509	79.38 471	92.70 464	90.75 491	70.69 497	78.66 481	87.47 486	51.34 493	93.40 489	73.39 478	69.65 493	89.38 493

UWE-MVS		89.91 365	89.48 361	91.21 418	95.88 308	78.23 478	94.91 390	90.26 492	89.11 311	92.35 256	94.52 351	68.76 436	97.96 348	83.95 400	95.59 250	97.42 280

DSMNet-mixed		86.34 420	86.12 405	87.00 467	89.88 472	70.43 497	94.93 389	90.08 493	77.97 483	85.42 432	92.78 422	74.44 385	93.96 485	74.43 471	95.14 261	96.62 310

MVS-HIRNet		82.47 450	81.21 453	86.26 470	95.38 335	69.21 500	88.96 493	89.49 494	66.28 501	80.79 469	74.08 517	68.48 440	97.39 417	71.93 483	95.47 255	92.18 473

WB-MVS		76.77 459	76.63 462	77.18 485	85.32 500	56.82 521	94.53 401	89.39 495	82.66 455	71.35 495	89.18 469	75.03 378	88.88 504	35.42 525	66.79 499	85.84 500

test1111		93.19 224	92.82 218	94.30 287	97.58 162	84.56 404	98.21 48	89.02 496	93.53 119	94.58 191	98.21 88	72.69 400	99.05 189	93.06 201	98.48 132	99.28 77

SSC-MVS		76.05 460	75.83 463	76.72 489	84.77 501	56.22 522	94.32 415	88.96 497	81.82 461	70.52 496	88.91 471	74.79 382	88.71 505	33.69 527	64.71 503	85.23 503

ECVR-MVS		93.19 224	92.73 224	94.57 268	97.66 150	85.41 387	98.21 48	88.23 498	93.43 125	94.70 188	98.21 88	72.57 401	99.07 184	93.05 202	98.49 130	99.25 80

EPMVS		90.70 343	89.81 349	93.37 348	94.73 380	84.21 408	93.67 440	88.02 499	89.50 299	92.38 253	93.49 407	77.82 355	97.78 372	86.03 371	92.68 311	98.11 236

ANet_high		63.94 480	59.58 483	77.02 486	61.24 539	66.06 506	85.66 507	87.93 500	78.53 480	42.94 524	71.04 519	25.42 513	80.71 520	52.60 516	30.83 534	84.28 505

PMMVS2		70.19 468	66.92 472	80.01 479	76.35 520	65.67 507	86.22 505	87.58 501	64.83 505	62.38 506	80.29 511	26.78 511	88.49 507	63.79 500	54.07 513	85.88 499

LoFTR		72.43 464	68.71 470	83.60 474	85.67 499	65.61 508	88.04 502	87.40 502	66.11 502	55.94 516	85.54 496	25.43 512	95.55 466	60.87 505	63.38 505	89.63 491

lessismore_v0				90.45 434	91.96 456	79.09 474		87.19 503		80.32 473	94.39 359	66.31 455	97.55 397	84.00 399	76.84 463	94.70 420

PMVS	53.92 22	58.58 483	55.40 486	68.12 501	51.00 553	48.64 527	78.86 514	87.10 504	46.77 520	35.84 531	74.28 516	8.76 541	86.34 510	42.07 522	73.91 477	69.38 518
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 413	86.41 400	88.02 459	92.87 439	74.60 490	95.38 365	86.70 505	88.17 346	87.28 398	94.67 344	70.83 417	93.30 491	67.45 493	94.31 279	96.17 322

test_vis1_rt		86.16 424	85.06 420	89.46 448	93.47 425	80.46 452	96.41 284	86.61 506	85.22 411	79.15 479	88.64 473	52.41 492	97.06 428	93.08 200	90.57 345	90.87 486

testf1		69.31 470	66.76 473	76.94 487	78.61 518	61.93 512	88.27 499	86.11 507	55.62 512	59.69 507	85.31 498	20.19 521	89.32 501	57.62 509	69.44 495	79.58 511

APD_test2		69.31 470	66.76 473	76.94 487	78.61 518	61.93 512	88.27 499	86.11 507	55.62 512	59.69 507	85.31 498	20.19 521	89.32 501	57.62 509	69.44 495	79.58 511

gg-mvs-nofinetune		87.82 394	85.61 408	94.44 276	94.46 390	89.27 259	91.21 478	84.61 509	80.88 466	89.89 324	74.98 515	71.50 410	97.53 404	85.75 376	97.21 187	96.51 312

MatchFormer		67.84 475	63.81 479	79.93 480	83.26 508	60.99 516	87.61 503	84.49 510	54.89 515	51.76 517	81.06 508	22.08 519	94.10 481	50.36 517	58.82 509	84.72 504

dmvs_testset		81.38 453	82.60 444	77.73 484	91.74 457	51.49 524	93.03 455	84.21 511	89.07 312	78.28 483	91.25 453	76.97 360	88.53 506	56.57 512	82.24 441	93.16 452

GG-mvs-BLEND				93.62 334	93.69 413	89.20 261	92.39 469	83.33 512		87.98 384	89.84 464	71.00 415	96.87 438	82.08 419	95.40 257	94.80 412

MTMP							97.86 92	82.03 513

DeepMVS_CX				74.68 494	90.84 465	64.34 511		81.61 514	65.34 503	67.47 500	88.01 480	48.60 496	80.13 521	62.33 503	73.68 478	79.58 511

DenseAffine		72.53 463	69.17 469	82.59 476	87.49 495	70.91 496	88.38 498	81.13 515	67.58 500	64.27 505	87.44 487	23.61 517	88.47 508	66.10 497	56.56 510	88.38 495

MASt3R-SfM		71.17 466	70.37 465	73.55 495	74.50 523	51.20 525	82.17 512	80.88 516	64.49 506	72.54 494	91.37 451	25.17 514	81.85 517	75.86 463	66.37 501	87.59 496

E-PMN		53.28 485	52.56 488	55.43 506	74.43 524	47.13 532	83.63 511	76.30 517	42.23 521	42.59 525	62.22 527	28.57 510	74.40 525	31.53 528	31.51 532	44.78 530

test2506		91.60 294	90.78 300	94.04 301	97.66 150	83.81 413	98.27 37	75.53 518	93.43 125	95.23 166	98.21 88	67.21 447	99.07 184	93.01 205	98.49 130	99.25 80

EMVS		52.08 488	51.31 490	54.39 508	72.62 530	45.39 534	83.84 510	75.51 519	41.13 522	40.77 527	59.65 529	30.08 508	73.60 526	28.31 530	29.90 538	44.18 531

ELoFTR		60.03 482	55.86 485	72.52 496	67.65 534	48.49 528	76.21 517	75.14 520	53.94 516	45.93 522	79.98 513	9.14 540	85.06 513	55.39 513	39.36 528	84.02 506

test_vis3_rt		72.73 461	70.55 464	79.27 481	80.02 515	68.13 503	93.92 429	74.30 521	76.90 485	58.99 511	73.58 518	20.29 520	95.37 469	84.16 395	72.80 481	74.31 514

RoMa-SfM		70.64 467	67.48 471	80.09 478	84.70 502	66.61 505	88.62 496	73.09 522	65.10 504	64.98 504	88.91 471	22.38 518	87.00 509	63.51 501	56.06 511	86.67 498

MVE	50.73 23	53.25 486	48.81 491	66.58 504	65.34 535	57.50 520	72.49 518	70.94 523	40.15 523	39.28 528	63.51 524	6.89 544	73.48 527	38.29 523	42.38 525	68.76 520
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DKM		67.96 473	64.19 478	79.27 481	83.41 506	64.35 510	86.88 504	68.11 524	63.15 507	59.36 509	86.08 495	16.45 530	86.15 511	64.54 499	49.73 515	87.32 497

tmp_tt		51.94 489	53.82 487	46.29 511	33.73 559	45.30 535	78.32 515	67.24 525	18.02 536	50.93 519	87.05 490	52.99 491	53.11 532	70.76 487	25.29 543	40.46 533

kuosan		65.27 477	64.66 477	67.11 503	83.80 503	61.32 515	88.53 497	60.77 526	68.22 499	67.67 498	80.52 510	49.12 495	70.76 528	29.67 529	53.64 514	69.26 519

dongtai		69.99 469	69.33 468	71.98 497	88.78 481	61.64 514	89.86 488	59.93 527	75.67 487	74.96 490	85.45 497	50.19 494	81.66 518	43.86 520	55.27 512	72.63 517

VLMVS_CLIP		39.93 499	41.64 499	34.80 518	33.81 558	19.16 559	46.81 535	59.30 528	16.50 537	47.57 520	67.74 522	14.11 535	49.88 533	42.98 521	45.94 518	35.36 536

RoMa-HiRes		64.40 478	60.91 481	74.89 493	78.66 517	58.85 519	85.22 508	58.46 529	58.65 510	59.29 510	86.60 494	16.97 527	83.91 514	59.14 507	45.20 520	81.91 510

DKM-HiRes		64.02 479	59.97 482	76.17 490	79.46 516	59.20 517	84.48 509	58.37 530	58.52 511	56.03 515	83.71 501	13.19 538	83.72 515	60.49 506	45.50 519	85.59 501

GLUNet-SfM		46.44 491	41.21 501	62.14 505	51.92 550	38.44 538	58.72 530	57.51 531	34.08 524	34.61 532	67.84 521	11.40 539	74.90 524	35.48 524	19.30 549	73.08 516

PDCNetPlus		61.05 481	58.26 484	69.44 500	75.52 521	55.68 523	81.49 513	51.76 532	62.45 508	51.54 518	82.02 504	23.69 516	78.90 522	65.91 498	29.91 537	73.74 515

PMatch-SfM		57.38 484	52.53 489	71.95 498	68.62 533	49.38 526	77.61 516	45.82 533	52.41 518	46.59 521	82.04 503	4.86 555	81.03 519	58.34 508	36.49 530	85.43 502

ALIKED-LG		47.63 490	45.22 493	54.88 507	81.48 512	48.47 529	71.83 520	45.44 534	32.66 525	37.07 529	63.26 526	19.21 524	63.71 529	15.49 539	40.53 526	52.46 527

N_pmnet		78.73 458	78.71 458	78.79 483	92.80 442	46.50 533	94.14 421	43.71 535	78.61 479	80.83 468	91.66 449	74.94 381	96.36 448	67.24 494	84.45 421	93.50 448

ALIKED-NN		46.19 492	43.87 494	53.16 510	80.39 514	47.77 530	69.82 526	43.65 536	27.89 526	36.60 530	63.35 525	17.30 526	61.29 531	15.84 538	39.98 527	50.41 529

ALIKED-MNN		45.42 493	42.62 496	53.80 509	80.52 513	47.58 531	70.83 523	43.05 537	27.21 527	34.32 533	61.10 528	14.85 534	62.94 530	14.90 540	36.82 529	50.89 528

SP-DiffGlue		43.94 494	43.32 495	45.79 514	47.79 555	33.03 540	63.37 529	42.65 538	25.71 528	41.26 526	69.27 520	18.83 525	38.88 540	34.96 526	46.05 517	65.47 525

SP-SuperGlue		43.33 496	42.50 497	45.81 513	73.95 527	31.24 543	71.34 521	41.17 539	23.96 529	33.42 534	56.47 531	16.72 529	39.64 538	21.11 534	44.32 522	66.57 522

SP-LightGlue		43.37 495	42.49 498	46.03 512	74.26 525	31.37 542	71.24 522	40.98 540	23.86 530	33.18 535	56.34 533	16.78 528	39.73 537	21.09 535	44.68 521	66.97 521

SP-MNN		42.11 498	40.98 502	45.49 515	72.87 528	30.19 547	70.72 524	39.96 541	20.98 532	30.21 539	55.72 535	15.26 533	40.07 536	19.70 537	43.42 524	66.21 523

XFeat-MNN		35.01 501	34.34 504	37.02 517	42.54 556	25.71 554	54.01 532	39.41 542	20.70 533	30.13 540	55.85 534	14.08 536	44.62 534	22.90 532	29.45 541	40.75 532

SP-NN		42.37 497	41.40 500	45.29 516	72.86 529	30.45 545	70.32 525	39.16 543	22.21 531	31.32 536	56.73 530	15.45 532	39.53 539	20.27 536	44.25 523	65.88 524

XFeat-NN		33.93 502	33.70 505	34.60 519	41.69 557	24.48 555	51.85 533	36.02 544	19.55 535	31.20 537	56.38 532	13.46 537	40.91 535	22.51 533	30.65 535	38.42 535

PMatch-Up-SfM		52.53 487	47.58 492	67.36 502	63.24 537	43.29 536	72.10 519	34.71 545	47.03 519	43.51 523	79.07 514	3.90 558	75.83 523	54.68 514	30.02 536	82.95 507

SIFT-NN		28.47 503	28.54 507	28.27 520	64.38 536	31.62 541	48.50 534	24.78 546	14.32 538	19.55 542	40.46 538	7.22 542	31.96 542	6.20 545	31.47 533	21.24 538

SIFT-MNN		27.50 504	27.40 508	27.80 521	61.71 538	30.57 544	46.59 536	24.66 547	14.04 539	17.35 543	39.90 539	6.52 545	31.80 543	6.13 546	29.65 539	21.04 539

SIFT-NN-NCMNet		27.16 505	27.05 509	27.51 522	59.97 541	30.42 546	46.49 537	24.52 548	13.94 541	17.23 544	39.47 540	6.39 546	31.40 544	5.94 547	29.49 540	20.72 541

SIFT-NN-UMatch		25.24 508	25.01 512	25.92 528	54.55 547	27.33 551	44.97 538	22.85 549	13.97 540	13.40 548	39.41 541	6.28 547	30.23 547	5.83 548	23.82 544	20.21 542

SIFT-NCM-Cal		25.87 506	25.57 510	26.75 523	60.60 540	29.37 548	44.96 539	22.64 550	13.57 544	11.67 551	37.90 545	5.81 550	31.26 545	5.32 553	27.70 542	19.63 544

SIFT-NN-CMatch		25.59 507	25.23 511	26.67 526	56.47 545	28.89 550	42.75 541	22.52 551	13.89 542	16.98 545	39.39 542	6.26 548	30.38 546	5.77 549	22.99 545	20.75 540

SIFT-ConvMatch		24.62 510	24.14 514	26.03 527	58.66 542	29.15 549	40.80 544	21.31 552	13.69 543	13.51 547	38.52 543	5.65 551	30.22 548	5.51 552	19.65 548	18.73 546

SIFT-NN-PointCN		23.81 512	23.84 515	23.73 531	52.41 548	22.80 558	42.30 543	20.98 553	13.02 548	15.14 546	37.74 547	6.20 549	28.40 551	5.52 551	21.24 546	19.98 543

SIFT-UMatch		24.03 511	23.67 516	25.10 529	57.10 544	26.49 553	42.43 542	20.05 554	13.49 545	12.40 550	38.51 544	5.45 553	30.07 549	5.56 550	18.08 550	18.74 545

SIFT-CM-Cal		23.18 514	22.70 517	24.60 530	57.42 543	26.79 552	37.63 546	18.36 555	13.35 546	12.57 549	37.37 548	5.54 552	28.79 550	5.17 555	16.92 553	18.23 547

SIFT-PointCN		20.70 517	20.89 520	20.14 533	51.62 552	18.11 560	37.52 547	17.71 556	12.03 551	10.05 555	33.23 550	4.33 557	25.40 554	4.55 557	16.94 552	16.90 549

SIFT-UM-Cal		22.52 515	22.27 518	23.27 532	56.41 546	23.87 556	39.94 545	16.81 557	13.33 547	10.54 552	37.90 545	5.16 554	28.36 552	5.23 554	15.12 554	17.57 548

SIFT-PCN-Cal		20.26 518	20.34 521	20.01 534	51.70 551	17.74 561	35.64 548	16.15 558	11.90 552	10.28 554	33.69 549	4.55 556	25.68 553	4.57 556	14.59 555	16.60 551

VLMVS		20.83 516	22.16 519	16.83 536	23.35 560	13.77 563	21.05 550	12.13 559	1.76 556	31.04 538	45.78 537	15.59 531	13.56 557	13.60 541	35.16 531	23.18 537

MVS_clip		37.19 500	40.69 503	26.70 525	52.35 549	23.34 557	43.13 540	10.51 560	12.50 549	56.71 514	80.13 512	19.51 523	16.50 556	43.87 519	47.47 516	40.26 534

SIFT-NCMNet		17.70 519	17.74 522	17.60 535	49.47 554	16.50 562	30.22 549	10.39 561	11.77 553	8.79 556	29.74 552	3.61 560	22.42 555	3.97 558	11.69 556	13.89 552

wuyk23d		25.11 509	24.57 513	26.74 524	73.98 526	39.89 537	57.88 531	9.80 562	12.27 550	10.39 553	6.97 557	7.03 543	36.44 541	25.43 531	17.39 551	3.89 555

testmvs		13.36 520	16.33 523	4.48 539	5.04 562	2.26 565	93.18 449	3.28 563	2.70 554	8.24 557	21.66 553	2.29 562	2.19 558	7.58 543	2.96 557	9.00 554

MVS_baseline		12.31 522	14.46 525	5.86 537	16.09 561	0.78 566	6.53 551	1.85 564	0.36 558	23.99 541	49.92 536	2.55 561	0.00 560	8.94 542	19.86 547	16.82 550

test123		13.04 521	15.66 524	5.18 538	4.51 563	3.45 564	92.50 468	1.81 565	2.50 555	7.58 558	20.15 554	3.67 559	2.18 559	7.13 544	1.07 558	9.90 553

mmdepth		0.00 525	0.00 528	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	0.00 558	0.00 563	0.00 560	0.00 559	0.00 559	0.00 556

monomultidepth		0.00 525	0.00 528	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	0.00 558	0.00 563	0.00 560	0.00 559	0.00 559	0.00 556

test_blank		0.00 525	0.00 528	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	0.00 558	0.00 563	0.00 560	0.00 559	0.00 559	0.00 556

uanet_test		0.00 525	0.00 528	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	0.00 558	0.00 563	0.00 560	0.00 559	0.00 559	0.00 556

DCPMVS		0.00 525	0.00 528	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	0.00 558	0.00 563	0.00 560	0.00 559	0.00 559	0.00 556

pcd_1.5k_mvsjas		7.39 524	9.85 527	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	0.00 558	88.65 110	0.00 560	0.00 559	0.00 559	0.00 556

sosnet-low-res		0.00 525	0.00 528	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	0.00 558	0.00 563	0.00 560	0.00 559	0.00 559	0.00 556

sosnet		0.00 525	0.00 528	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	0.00 558	0.00 563	0.00 560	0.00 559	0.00 559	0.00 556

uncertanet		0.00 525	0.00 528	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	0.00 558	0.00 563	0.00 560	0.00 559	0.00 559	0.00 556

Regformer		0.00 525	0.00 528	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	0.00 558	0.00 563	0.00 560	0.00 559	0.00 559	0.00 556

n2								0.00 566

nn								0.00 566

ab-mvs-re		8.06 523	10.74 526	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	96.69 234	0.00 563	0.00 560	0.00 559	0.00 559	0.00 556

uanet		0.00 525	0.00 528	0.00 540	0.00 564	0.00 567	0.00 552	0.00 566	0.00 559	0.00 560	0.00 558	0.00 563	0.00 560	0.00 559	0.00 559	0.00 556

PatchmatchNet1														67.11 495	84.43 422	93.53 447
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													96.32 449
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						79.53 467								75.56 467

PC_three_1452									90.77 250	98.89 27	98.28 86	96.24 1	98.35 293	95.76 108	99.58 25	99.59 32

eth-test2					0.00 564

eth-test					0.00 564

OPU-MVS				98.55 3	98.82 62	96.86 3	98.25 40				98.26 87	96.04 2	99.24 152	95.36 126	99.59 21	99.56 40

test_0728_THIRD									94.78 63	98.73 31	98.87 33	95.87 4	99.84 27	97.45 46	99.72 2	99.77 4

GSMVS																98.45 197

test_part2					99.28 31	95.74 9				98.10 49

sam_mvs1												82.76 252				98.45 197

sam_mvs												81.94 273

test_post1							92.81 460				16.58 556	80.53 302	97.68 381	86.20 365

test_post											17.58 555	81.76 277	98.08 325

patchmatchnet-post											90.45 458	82.65 257	98.10 320

gm-plane-assit					93.22 432	78.89 476			84.82 419		93.52 406		98.64 260	87.72 326

test9_res														94.81 150	99.38 64	99.45 59

agg_prior2														93.94 178	99.38 64	99.50 52

test_prior4						93.66 64	96.42 283

test_prior2							96.35 293		92.80 161	96.03 129	97.59 170	92.01 51		95.01 135	99.38 64

旧先验2							95.94 329		81.66 462	97.34 72			98.82 212	92.26 212

新几何2							95.79 340

原ACMM2							95.67 346

testdata2													99.67 78	85.96 373

segment_acmp												92.89 34

testdata1							95.26 374		93.10 142

plane_prior7					96.21 281	89.98 220

plane_prior6					96.10 300	90.00 216						81.32 284

plane_prior4											96.64 237

plane_prior3						90.00 216			94.46 80	91.34 285

plane_prior2							97.74 114		94.85 55

plane_prior1					96.14 295

plane_prior						89.99 218	97.24 195		94.06 95						92.16 320

HQP5-MVS						89.33 254

HQP-NCC					95.86 309		96.65 264		93.55 115	90.14 309

ACMP_Plane					95.86 309		96.65 264		93.55 115	90.14 309

BP-MVS														92.13 220

HQP4-MVS										90.14 309			98.50 278			95.78 341

HQP2-MVS												80.95 290

NP-MVS					95.99 307	89.81 228					95.87 281

MDTV_nov1_ep13_2view						70.35 498	93.10 454		83.88 432	93.55 225		82.47 261		86.25 364		98.38 205

ACMMP++_ref															90.30 350

ACMMP++															91.02 339

Test By Simon												88.73 109

High-resolution multi-view benchmark