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 14	97.89 3	96.53 100	98.41 80	91.73 125	98.01 61	99.02 1	96.37 11	99.30 5	98.92 21	92.39 41	99.79 40	99.16 12	99.46 42	98.08 207

PGM-MVS		96.81 53	96.53 64	97.65 43	99.35 22	93.53 61	97.65 122	98.98 2	92.22 160	97.14 70	98.44 58	91.17 68	99.85 18	94.35 144	99.46 42	99.57 32

MVS_111021_HR		96.68 64	96.58 63	96.99 80	98.46 75	92.31 106	96.20 282	98.90 3	94.30 84	95.86 128	97.74 125	92.33 42	99.38 130	96.04 90	99.42 52	99.28 73

test_fmvsmconf_n		97.49 18	97.56 13	97.29 60	97.44 159	92.37 103	97.91 80	98.88 4	95.83 17	98.92 21	99.05 12	91.45 58	99.80 35	99.12 14	99.46 42	99.69 13

lecture		97.58 13	97.63 10	97.43 54	99.37 16	92.93 82	98.86 7	98.85 5	95.27 32	98.65 31	98.90 23	91.97 49	99.80 35	97.63 36	99.21 77	99.57 32

ACMMP		96.27 81	95.93 84	97.28 62	99.24 30	92.62 94	98.25 36	98.81 6	92.99 134	94.56 165	98.39 62	88.96 98	99.85 18	94.57 142	97.63 157	99.36 68
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 82	96.19 80	96.39 118	98.23 99	91.35 147	96.24 280	98.79 7	93.99 91	95.80 130	97.65 135	89.92 88	99.24 143	95.87 94	99.20 82	98.58 154

patch_mono-2		96.83 52	97.44 21	95.01 207	99.05 41	85.39 343	96.98 206	98.77 8	94.70 64	97.99 45	98.66 41	93.61 19	99.91 1	97.67 35	99.50 36	99.72 12

fmvsm_s_conf0.5_n		96.85 49	97.13 26	96.04 142	98.07 114	90.28 195	97.97 72	98.76 9	94.93 46	98.84 26	99.06 11	88.80 102	99.65 73	99.06 16	98.63 117	98.18 193

fmvsm_l_conf0.5_n		97.65 7	97.75 7	97.34 57	98.21 100	92.75 88	97.83 92	98.73 10	95.04 43	99.30 5	98.84 34	93.34 22	99.78 43	99.32 6	99.13 92	99.50 48

fmvsm_s_conf0.5_n_a		96.75 57	96.93 41	96.20 134	97.64 145	90.72 177	98.00 62	98.73 10	94.55 71	98.91 22	99.08 7	88.22 114	99.63 82	98.91 19	98.37 130	98.25 188

fmvsm_l_conf0.5_n_9		97.59 11	97.79 5	96.97 82	98.28 89	91.49 139	97.61 131	98.71 12	97.10 4	99.70 1	98.93 20	90.95 73	99.77 46	99.35 5	99.53 29	99.65 19

FC-MVSNet-test		93.94 165	93.57 157	95.04 205	95.48 295	91.45 144	98.12 51	98.71 12	93.37 116	90.23 275	96.70 201	87.66 124	97.85 326	91.49 206	90.39 317	95.83 301

UniMVSNet (Re)		93.31 190	92.55 203	95.61 175	95.39 301	93.34 67	97.39 165	98.71 12	93.14 129	90.10 284	94.83 303	87.71 123	98.03 299	91.67 204	83.99 389	95.46 320

fmvsm_l_conf0.5_n_a		97.63 9	97.76 6	97.26 64	98.25 94	92.59 96	97.81 97	98.68 15	94.93 46	99.24 8	98.87 29	93.52 20	99.79 40	99.32 6	99.21 77	99.40 62

FIs		94.09 156	93.70 153	95.27 194	95.70 284	92.03 118	98.10 52	98.68 15	93.36 118	90.39 272	96.70 201	87.63 127	97.94 317	92.25 184	90.50 316	95.84 300

WR-MVS_H		92.00 247	91.35 244	93.95 272	95.09 328	89.47 224	98.04 59	98.68 15	91.46 189	88.34 335	94.68 310	85.86 160	97.56 355	85.77 330	84.24 387	94.82 365

fmvsm_s_conf0.5_n_4		96.75 57	97.07 29	95.79 162	97.76 136	89.57 218	97.66 121	98.66 18	95.36 28	99.03 14	98.90 23	88.39 110	99.73 55	99.17 11	98.66 115	98.08 207

VPA-MVSNet		93.24 192	92.48 208	95.51 181	95.70 284	92.39 102	97.86 85	98.66 18	92.30 157	92.09 233	95.37 278	80.49 270	98.40 253	93.95 150	85.86 360	95.75 309

fmvsm_l_conf0.5_n_3		97.64 8	97.60 11	97.79 30	98.14 107	93.94 52	97.93 78	98.65 20	96.70 6	99.38 3	99.07 10	89.92 88	99.81 30	99.16 12	99.43 49	99.61 26

fmvsm_s_conf0.5_n_3		97.15 31	97.36 23	96.52 102	97.98 120	91.19 155	97.84 89	98.65 20	97.08 5	99.25 7	99.10 5	87.88 121	99.79 40	99.32 6	99.18 84	98.59 153

fmvsm_s_conf0.5_n_8		97.32 25	97.48 20	96.85 83	98.28 89	91.07 163	97.76 102	98.62 22	97.53 2	99.20 10	99.12 4	88.24 113	99.81 30	99.41 3	99.17 85	99.67 14

fmvsm_s_conf0.5_n_2		96.62 65	96.82 50	96.02 144	97.98 120	90.43 187	97.50 146	98.59 23	96.59 8	99.31 4	99.08 7	84.47 186	99.75 52	99.37 4	98.45 127	97.88 220

UniMVSNet_NR-MVSNet		93.37 188	92.67 197	95.47 187	95.34 307	92.83 85	97.17 189	98.58 24	92.98 139	90.13 280	95.80 254	88.37 112	97.85 326	91.71 201	83.93 390	95.73 311

CSCG		96.05 85	95.91 85	96.46 112	99.24 30	90.47 184	98.30 29	98.57 25	89.01 281	93.97 182	97.57 145	92.62 37	99.76 48	94.66 136	99.27 70	99.15 83

fmvsm_s_conf0.5_n_9		97.33 24	97.57 12	96.62 96	98.43 78	90.32 194	97.80 98	98.53 26	97.24 3	99.62 2	99.14 1	88.65 105	99.80 35	99.54 1	99.15 89	99.74 8

fmvsm_s_conf0.5_n_6		97.08 34	97.17 25	96.81 84	97.28 164	91.73 125	97.75 104	98.50 27	94.86 50	99.22 9	98.78 38	89.75 91	99.76 48	99.10 15	99.29 68	98.94 112

MSLP-MVS++		96.94 43	97.06 30	96.59 97	98.72 60	91.86 123	97.67 118	98.49 28	94.66 67	97.24 66	98.41 61	92.31 44	98.94 189	96.61 65	99.46 42	98.96 108

HyFIR lowres test		93.66 177	92.92 185	95.87 154	98.24 95	89.88 209	94.58 357	98.49 28	85.06 378	93.78 185	95.78 258	82.86 221	98.67 228	91.77 199	95.71 215	99.07 94

CHOSEN 1792x2688		94.15 151	93.51 163	96.06 140	98.27 91	89.38 229	95.18 343	98.48 30	85.60 368	93.76 186	97.11 176	83.15 211	99.61 84	91.33 209	98.72 113	99.19 79

fmvsm_s_conf0.5_n_7		96.45 72	96.80 52	95.37 190	97.29 163	88.38 262	97.23 183	98.47 31	95.14 37	98.43 36	99.09 6	87.58 128	99.72 59	98.80 23	99.21 77	98.02 211

fmvsm_s_conf0.5_n_5		97.00 40	96.97 38	97.09 75	97.58 155	92.56 97	97.68 117	98.47 31	94.02 89	98.90 23	98.89 26	88.94 99	99.78 43	99.18 10	99.03 101	98.93 116

PHI-MVS		96.77 55	96.46 71	97.71 41	98.40 81	94.07 48	98.21 43	98.45 33	89.86 253	97.11 72	98.01 98	92.52 39	99.69 67	96.03 91	99.53 29	99.36 68

fmvsm_s_conf0.1_n		96.58 68	96.77 55	96.01 147	96.67 215	90.25 196	97.91 80	98.38 34	94.48 75	98.84 26	99.14 1	88.06 116	99.62 83	98.82 21	98.60 119	98.15 197

PVSNet_BlendedMVS		94.06 157	93.92 147	94.47 241	98.27 91	89.46 226	96.73 231	98.36 35	90.17 245	94.36 170	95.24 286	88.02 117	99.58 92	93.44 162	90.72 312	94.36 385

PVSNet_Blended		94.87 129	94.56 127	95.81 160	98.27 91	89.46 226	95.47 326	98.36 35	88.84 290	94.36 170	96.09 243	88.02 117	99.58 92	93.44 162	98.18 139	98.40 175

3Dnovator	91.36 5	95.19 117	94.44 135	97.44 53	96.56 225	93.36 66	98.65 12	98.36 35	94.12 86	89.25 314	98.06 92	82.20 238	99.77 46	93.41 164	99.32 66	99.18 80

FOURS1					99.55 1	93.34 67	99.29 1	98.35 38	94.98 44	98.49 34

DPE-MVS		97.86 4	97.65 9	98.47 5	99.17 34	95.78 7	97.21 186	98.35 38	95.16 36	98.71 30	98.80 36	95.05 10	99.89 3	96.70 63	99.73 1	99.73 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_s_conf0.1_n_a		96.40 74	96.47 68	96.16 136	95.48 295	90.69 178	97.91 80	98.33 40	94.07 87	98.93 18	99.14 1	87.44 135	99.61 84	98.63 24	98.32 132	98.18 193

HFP-MVS		97.14 32	96.92 42	97.83 26	99.42 7	94.12 46	98.52 16	98.32 41	93.21 121	97.18 67	98.29 78	92.08 46	99.83 26	95.63 107	99.59 19	99.54 41

ACMMPR		97.07 36	96.84 46	97.79 30	99.44 6	93.88 53	98.52 16	98.31 42	93.21 121	97.15 69	98.33 72	91.35 62	99.86 9	95.63 107	99.59 19	99.62 23

test_fmvsmvis_n_1920		96.70 60	96.84 46	96.31 123	96.62 217	91.73 125	97.98 66	98.30 43	96.19 12	96.10 118	98.95 18	89.42 92	99.76 48	98.90 20	99.08 96	97.43 247

APDe-MVS		97.82 5	97.73 8	98.08 18	99.15 35	94.82 28	98.81 8	98.30 43	94.76 62	98.30 38	98.90 23	93.77 17	99.68 69	97.93 27	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test0726					99.45 3	95.36 13	98.31 28	98.29 45	94.92 48	98.99 16	98.92 21	95.08 8

MSP-MVS		97.59 11	97.54 14	97.73 38	99.40 11	93.77 57	98.53 15	98.29 45	95.55 25	98.56 33	97.81 120	93.90 15	99.65 73	96.62 64	99.21 77	99.77 2
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 63	95.39 11	99.29 1	98.28 47	94.78 59	98.93 18	98.87 29	96.04 2	99.86 9	97.45 44	99.58 23	99.59 28

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 47					99.86 9	97.52 40	99.67 6	99.75 6

CP-MVS		97.02 38	96.81 51	97.64 45	99.33 23	93.54 60	98.80 9	98.28 47	92.99 134	96.45 105	98.30 77	91.90 50	99.85 18	95.61 109	99.68 4	99.54 41

test_fmvsmconf0.1_n		97.09 33	97.06 30	97.19 69	95.67 286	92.21 110	97.95 75	98.27 50	95.78 21	98.40 37	99.00 14	89.99 86	99.78 43	99.06 16	99.41 55	99.59 28

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 50	95.13 38	99.19 11	98.89 26	95.54 5	99.85 18	97.52 40	99.66 10	99.56 36

test_241102_TWO								98.27 50	95.13 38	98.93 18	98.89 26	94.99 11	99.85 18	97.52 40	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 50	95.09 41	99.19 11	98.81 35	95.54 5	99.65 73

SF-MVS		97.39 21	97.13 26	98.17 15	99.02 44	95.28 19	98.23 40	98.27 50	92.37 156	98.27 39	98.65 43	93.33 23	99.72 59	96.49 69	99.52 31	99.51 45

SteuartSystems-ACMMP		97.62 10	97.53 15	97.87 24	98.39 83	94.25 40	98.43 23	98.27 50	95.34 30	98.11 41	98.56 45	94.53 12	99.71 61	96.57 67	99.62 17	99.65 19
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 24	95.20 20		98.25 56	95.13 38	98.48 35	98.87 29	95.16 7

PVSNet_Blended_VisFu		95.27 110	94.91 116	96.38 119	98.20 101	90.86 171	97.27 177	98.25 56	90.21 244	94.18 175	97.27 165	87.48 134	99.73 55	93.53 159	97.77 155	98.55 156

region2R		97.07 36	96.84 46	97.77 34	99.46 2	93.79 55	98.52 16	98.24 58	93.19 124	97.14 70	98.34 69	91.59 57	99.87 7	95.46 113	99.59 19	99.64 21

PS-CasMVS		91.55 267	90.84 268	93.69 289	94.96 332	88.28 265	97.84 89	98.24 58	91.46 189	88.04 346	95.80 254	79.67 286	97.48 363	87.02 310	84.54 384	95.31 334

DU-MVS		92.90 210	92.04 219	95.49 184	94.95 333	92.83 85	97.16 190	98.24 58	93.02 133	90.13 280	95.71 261	83.47 203	97.85 326	91.71 201	83.93 390	95.78 305

9.14			96.75 56		98.93 52		97.73 108	98.23 61	91.28 198	97.88 49	98.44 58	93.00 26	99.65 73	95.76 100	99.47 41

reproduce_model		97.51 17	97.51 17	97.50 50	98.99 48	93.01 78	97.79 100	98.21 62	95.73 22	97.99 45	99.03 13	92.63 36	99.82 28	97.80 29	99.42 52	99.67 14

D2MVS		91.30 284	90.95 262	92.35 337	94.71 348	85.52 339	96.18 284	98.21 62	88.89 288	86.60 375	93.82 359	79.92 282	97.95 315	89.29 259	90.95 309	93.56 400

reproduce-ours		97.53 15	97.51 17	97.60 47	98.97 49	93.31 69	97.71 113	98.20 64	95.80 19	97.88 49	98.98 16	92.91 27	99.81 30	97.68 31	99.43 49	99.67 14

our_new_method		97.53 15	97.51 17	97.60 47	98.97 49	93.31 69	97.71 113	98.20 64	95.80 19	97.88 49	98.98 16	92.91 27	99.81 30	97.68 31	99.43 49	99.67 14

SDMVSNet		94.17 149	93.61 156	95.86 156	98.09 110	91.37 146	97.35 169	98.20 64	93.18 126	91.79 241	97.28 163	79.13 294	98.93 190	94.61 139	92.84 275	97.28 255

XVS		97.18 29	96.96 40	97.81 28	99.38 14	94.03 50	98.59 13	98.20 64	94.85 51	96.59 93	98.29 78	91.70 53	99.80 35	95.66 102	99.40 57	99.62 23

X-MVStestdata		91.71 256	89.67 322	97.81 28	99.38 14	94.03 50	98.59 13	98.20 64	94.85 51	96.59 93	32.69 460	91.70 53	99.80 35	95.66 102	99.40 57	99.62 23

ACMMP_NAP		97.20 28	96.86 44	98.23 11	99.09 36	95.16 22	97.60 132	98.19 69	92.82 146	97.93 48	98.74 40	91.60 56	99.86 9	96.26 74	99.52 31	99.67 14

CP-MVSNet		91.89 252	91.24 251	93.82 281	95.05 329	88.57 255	97.82 94	98.19 69	91.70 178	88.21 341	95.76 259	81.96 243	97.52 361	87.86 285	84.65 378	95.37 330

ZNCC-MVS		96.96 41	96.67 59	97.85 25	99.37 16	94.12 46	98.49 20	98.18 71	92.64 152	96.39 107	98.18 85	91.61 55	99.88 4	95.59 112	99.55 26	99.57 32

SMA-MVS		97.35 22	97.03 35	98.30 8	99.06 40	95.42 10	97.94 76	98.18 71	90.57 236	98.85 25	98.94 19	93.33 23	99.83 26	96.72 61	99.68 4	99.63 22
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		91.20 289	90.44 285	93.48 300	94.49 356	87.91 280	97.76 102	98.18 71	91.29 195	87.78 350	95.74 260	80.35 273	97.33 374	85.46 334	82.96 400	95.19 345

DELS-MVS		96.61 66	96.38 75	97.30 59	97.79 134	93.19 74	95.96 296	98.18 71	95.23 33	95.87 127	97.65 135	91.45 58	99.70 66	95.87 94	99.44 48	99.00 103
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		89.70 341	88.40 347	93.60 293	95.15 324	90.10 198	97.56 137	98.16 75	87.28 341	86.16 381	94.63 314	77.57 322	98.05 295	74.48 420	84.59 382	92.65 413

VNet		95.89 93	95.45 96	97.21 67	98.07 114	92.94 81	97.50 146	98.15 76	93.87 95	97.52 56	97.61 141	85.29 171	99.53 106	95.81 99	95.27 228	99.16 81

DeepPCF-MVS	93.97 1	96.61 66	97.09 28	95.15 198	98.09 110	86.63 312	96.00 294	98.15 76	95.43 26	97.95 47	98.56 45	93.40 21	99.36 131	96.77 58	99.48 40	99.45 55

SD-MVS		97.41 20	97.53 15	97.06 78	98.57 74	94.46 34	97.92 79	98.14 78	94.82 55	99.01 15	98.55 47	94.18 14	97.41 370	96.94 53	99.64 14	99.32 70
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 49	96.52 65	97.82 27	99.36 20	94.14 45	98.29 30	98.13 79	92.72 149	96.70 85	98.06 92	91.35 62	99.86 9	94.83 129	99.28 69	99.47 54

UA-Net		95.95 90	95.53 92	97.20 68	97.67 141	92.98 80	97.65 122	98.13 79	94.81 57	96.61 91	98.35 66	88.87 100	99.51 111	90.36 234	97.35 168	99.11 89

QAPM		93.45 186	92.27 213	96.98 81	96.77 210	92.62 94	98.39 25	98.12 81	84.50 386	88.27 339	97.77 123	82.39 235	99.81 30	85.40 335	98.81 109	98.51 161

Vis-MVSNet		95.23 114	94.81 117	96.51 106	97.18 169	91.58 136	98.26 35	98.12 81	94.38 82	94.90 155	98.15 87	82.28 236	98.92 192	91.45 208	98.58 121	99.01 100
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 213	91.68 234	96.40 116	95.34 307	92.73 90	98.27 33	98.12 81	84.86 381	85.78 383	97.75 124	78.89 304	99.74 53	87.50 300	98.65 116	96.73 272

TranMVSNet+NR-MVSNet		92.50 222	91.63 235	95.14 199	94.76 344	92.07 115	97.53 143	98.11 84	92.90 143	89.56 302	96.12 238	83.16 210	97.60 353	89.30 258	83.20 399	95.75 309

CPTT-MVS		95.57 103	95.19 107	96.70 87	99.27 28	91.48 141	98.33 27	98.11 84	87.79 326	95.17 150	98.03 95	87.09 141	99.61 84	93.51 160	99.42 52	99.02 97

APD-MVS		96.95 42	96.60 61	98.01 20	99.03 43	94.93 27	97.72 111	98.10 86	91.50 187	98.01 44	98.32 74	92.33 42	99.58 92	94.85 127	99.51 34	99.53 44
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 47	96.60 61	97.64 45	99.40 11	93.44 62	98.50 19	98.09 87	93.27 120	95.95 125	98.33 72	91.04 70	99.88 4	95.20 116	99.57 25	99.60 27

ZD-MVS					99.05 41	94.59 32		98.08 88	89.22 274	97.03 75	98.10 88	92.52 39	99.65 73	94.58 141	99.31 67

MTGPA								98.08 88

MTAPA		97.08 34	96.78 54	97.97 23	99.37 16	94.42 36	97.24 179	98.08 88	95.07 42	96.11 117	98.59 44	90.88 76	99.90 2	96.18 86	99.50 36	99.58 31

CNVR-MVS		97.68 6	97.44 21	98.37 7	98.90 55	95.86 6	97.27 177	98.08 88	95.81 18	97.87 52	98.31 75	94.26 13	99.68 69	97.02 52	99.49 39	99.57 32

DP-MVS Recon		95.68 98	95.12 111	97.37 56	99.19 33	94.19 42	97.03 197	98.08 88	88.35 308	95.09 152	97.65 135	89.97 87	99.48 118	92.08 193	98.59 120	98.44 172

SR-MVS		97.01 39	96.86 44	97.47 52	99.09 36	93.27 71	97.98 66	98.07 93	93.75 98	97.45 58	98.48 55	91.43 60	99.59 89	96.22 77	99.27 70	99.54 41

MCST-MVS		97.18 29	96.84 46	98.20 14	99.30 26	95.35 15	97.12 193	98.07 93	93.54 108	96.08 119	97.69 130	93.86 16	99.71 61	96.50 68	99.39 59	99.55 39

NR-MVSNet		92.34 231	91.27 250	95.53 180	94.95 333	93.05 77	97.39 165	98.07 93	92.65 151	84.46 394	95.71 261	85.00 177	97.77 337	89.71 246	83.52 396	95.78 305

MP-MVS-pluss		96.70 60	96.27 78	97.98 22	99.23 32	94.71 29	96.96 208	98.06 96	90.67 226	95.55 141	98.78 38	91.07 69	99.86 9	96.58 66	99.55 26	99.38 66
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 53	96.71 58	97.12 72	99.01 47	92.31 106	97.98 66	98.06 96	93.11 130	97.44 59	98.55 47	90.93 74	99.55 102	96.06 87	99.25 74	99.51 45

MP-MVS		96.77 55	96.45 72	97.72 39	99.39 13	93.80 54	98.41 24	98.06 96	93.37 116	95.54 143	98.34 69	90.59 80	99.88 4	94.83 129	99.54 28	99.49 50
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 69	96.27 78	97.22 66	99.32 24	92.74 89	98.74 10	98.06 96	90.57 236	96.77 82	98.35 66	90.21 83	99.53 106	94.80 132	99.63 16	99.38 66

HPM-MVS		96.69 62	96.45 72	97.40 55	99.36 20	93.11 76	98.87 6	98.06 96	91.17 205	96.40 106	97.99 99	90.99 71	99.58 92	95.61 109	99.61 18	99.49 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 140	93.80 149	96.64 89	97.07 175	91.97 120	96.32 272	98.06 96	88.94 286	94.50 167	96.78 196	84.60 183	99.27 141	91.90 194	96.02 205	98.68 147

DeepC-MVS	93.07 3	96.06 84	95.66 89	97.29 60	97.96 122	93.17 75	97.30 175	98.06 96	93.92 93	93.38 201	98.66 41	86.83 143	99.73 55	95.60 111	99.22 76	98.96 108
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 26	97.03 35	98.11 17	98.77 58	95.06 25	97.34 170	98.04 103	95.96 13	97.09 73	97.88 110	93.18 25	99.71 61	95.84 98	99.17 85	99.56 36

DeepC-MVS_fast	93.89 2	96.93 44	96.64 60	97.78 32	98.64 69	94.30 37	97.41 160	98.04 103	94.81 57	96.59 93	98.37 64	91.24 65	99.64 81	95.16 118	99.52 31	99.42 61
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 46	96.80 52	97.11 74	99.02 44	92.34 104	97.98 66	98.03 105	93.52 111	97.43 61	98.51 50	91.40 61	99.56 100	96.05 88	99.26 72	99.43 59

RE-MVS-def			96.72 57		99.02 44	92.34 104	97.98 66	98.03 105	93.52 111	97.43 61	98.51 50	90.71 78		96.05 88	99.26 72	99.43 59

RPMNet		88.98 347	87.05 361	94.77 225	94.45 358	87.19 296	90.23 433	98.03 105	77.87 433	92.40 219	87.55 440	80.17 277	99.51 111	68.84 440	93.95 261	97.60 240

save fliter					98.91 54	94.28 38	97.02 199	98.02 108	95.35 29

TEST9					98.70 61	94.19 42	96.41 259	98.02 108	88.17 312	96.03 120	97.56 147	92.74 33	99.59 89

train_agg		96.30 80	95.83 88	97.72 39	98.70 61	94.19 42	96.41 259	98.02 108	88.58 299	96.03 120	97.56 147	92.73 34	99.59 89	95.04 120	99.37 63	99.39 64

test_8					98.67 63	94.06 49	96.37 266	98.01 111	88.58 299	95.98 124	97.55 149	92.73 34	99.58 92

agg_prior					98.67 63	93.79 55		98.00 112		95.68 137			99.57 99

test_prior				97.23 65	98.67 63	92.99 79		98.00 112					99.41 126			99.29 71

WR-MVS		92.34 231	91.53 239	94.77 225	95.13 326	90.83 172	96.40 263	97.98 114	91.88 173	89.29 311	95.54 272	82.50 231	97.80 333	89.79 245	85.27 369	95.69 312

HPM-MVS++		97.34 23	96.97 38	98.47 5	99.08 38	96.16 4	97.55 142	97.97 115	95.59 23	96.61 91	97.89 108	92.57 38	99.84 23	95.95 93	99.51 34	99.40 62

CANet		96.39 75	96.02 83	97.50 50	97.62 148	93.38 64	97.02 199	97.96 116	95.42 27	94.86 156	97.81 120	87.38 137	99.82 28	96.88 55	99.20 82	99.29 71

114514_t		93.95 164	93.06 179	96.63 93	99.07 39	91.61 133	97.46 157	97.96 116	77.99 431	93.00 210	97.57 145	86.14 157	99.33 133	89.22 262	99.15 89	98.94 112

IU-MVS					99.42 7	95.39 11		97.94 118	90.40 242	98.94 17				97.41 47	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 63	96.94 1		97.93 119					99.86 9	97.68 31	99.67 6	99.77 2

No_MVS				98.86 1	98.67 63	96.94 1		97.93 119					99.86 9	97.68 31	99.67 6	99.77 2

fmvsm_s_conf0.1_n_2		96.33 79	96.44 74	96.00 148	97.30 162	90.37 193	97.53 143	97.92 121	96.52 9	99.14 13	99.08 7	83.21 208	99.74 53	99.22 9	98.06 144	97.88 220

Anonymous20231211		90.63 313	89.42 329	94.27 255	98.24 95	89.19 241	98.05 58	97.89 122	79.95 423	88.25 340	94.96 295	72.56 363	98.13 278	89.70 247	85.14 371	95.49 316

原ACMM1				96.38 119	98.59 71	91.09 162		97.89 122	87.41 337	95.22 149	97.68 131	90.25 82	99.54 104	87.95 284	99.12 94	98.49 164

CDPH-MVS		95.97 89	95.38 101	97.77 34	98.93 52	94.44 35	96.35 267	97.88 124	86.98 345	96.65 89	97.89 108	91.99 48	99.47 119	92.26 182	99.46 42	99.39 64

test11								97.88 124

EIA-MVS		95.53 104	95.47 95	95.71 170	97.06 178	89.63 214	97.82 94	97.87 126	93.57 104	93.92 183	95.04 292	90.61 79	98.95 187	94.62 138	98.68 114	98.54 157

CS-MVS		96.86 47	97.06 30	96.26 129	98.16 106	91.16 160	99.09 3	97.87 126	95.30 31	97.06 74	98.03 95	91.72 51	98.71 223	97.10 50	99.17 85	98.90 121

无先验							95.79 307	97.87 126	83.87 394				99.65 73	87.68 294		98.89 125

3Dnovator+	91.43 4	95.40 105	94.48 133	98.16 16	96.90 192	95.34 16	98.48 21	97.87 126	94.65 68	88.53 331	98.02 97	83.69 199	99.71 61	93.18 168	98.96 104	99.44 57

VPNet		92.23 239	91.31 247	94.99 208	95.56 291	90.96 166	97.22 185	97.86 130	92.96 140	90.96 263	96.62 213	75.06 343	98.20 272	91.90 194	83.65 395	95.80 303

test_vis1_n_1920		94.17 149	94.58 126	92.91 321	97.42 160	82.02 390	97.83 92	97.85 131	94.68 65	98.10 42	98.49 52	70.15 382	99.32 135	97.91 28	98.82 108	97.40 249

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 131	94.92 48	98.73 28	98.87 29	95.08 8	99.84 23	97.52 40	99.67 6	99.48 52
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 19	97.33 24	97.69 42	99.25 29	94.24 41	98.07 56	97.85 131	93.72 99	98.57 32	98.35 66	93.69 18	99.40 127	97.06 51	99.46 42	99.44 57
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 45	97.04 34	96.45 113	98.29 88	91.66 132	99.03 4	97.85 131	95.84 16	96.90 77	97.97 101	91.24 65	98.75 215	96.92 54	99.33 65	98.94 112

test_fmvsmconf0.01_n		96.15 83	95.85 87	97.03 79	92.66 409	91.83 124	97.97 72	97.84 135	95.57 24	97.53 55	99.00 14	84.20 192	99.76 48	98.82 21	99.08 96	99.48 52

GDP-MVS		95.62 100	95.13 109	97.09 75	96.79 204	93.26 72	97.89 83	97.83 136	93.58 103	96.80 79	97.82 118	83.06 215	99.16 155	94.40 143	97.95 150	98.87 127

balanced_conf03		96.84 51	96.89 43	96.68 88	97.63 147	92.22 109	98.17 49	97.82 137	94.44 77	98.23 40	97.36 158	90.97 72	99.22 145	97.74 30	99.66 10	98.61 150

AdaColmap		94.34 144	93.68 154	96.31 123	98.59 71	91.68 131	96.59 250	97.81 138	89.87 252	92.15 229	97.06 179	83.62 202	99.54 104	89.34 257	98.07 143	97.70 233

MVSMamba_PlusPlus		96.51 69	96.48 67	96.59 97	98.07 114	91.97 120	98.14 50	97.79 139	90.43 240	97.34 64	97.52 150	91.29 64	99.19 148	98.12 26	99.64 14	98.60 151

KinetiMVS		95.26 111	94.75 121	96.79 85	96.99 187	92.05 116	97.82 94	97.78 140	94.77 61	96.46 103	97.70 128	80.62 267	99.34 132	92.37 181	98.28 134	98.97 105

mamv4		94.66 137	96.10 82	90.37 390	98.01 117	73.41 440	96.82 221	97.78 140	89.95 251	94.52 166	97.43 154	92.91 27	99.09 168	98.28 25	99.16 88	98.60 151

ETV-MVS		96.02 86	95.89 86	96.40 116	97.16 170	92.44 101	97.47 155	97.77 142	94.55 71	96.48 101	94.51 320	91.23 67	98.92 192	95.65 105	98.19 138	97.82 228

新几何1				97.32 58	98.60 70	93.59 59		97.75 143	81.58 414	95.75 132	97.85 114	90.04 85	99.67 71	86.50 316	99.13 92	98.69 146

旧先验1					98.38 84	93.38 64		97.75 143			98.09 90	92.30 45			99.01 102	99.16 81

EC-MVSNet		96.42 73	96.47 68	96.26 129	97.01 185	91.52 138	98.89 5	97.75 143	94.42 78	96.64 90	97.68 131	89.32 93	98.60 236	97.45 44	99.11 95	98.67 148

EI-MVSNet-Vis-set		96.51 69	96.47 68	96.63 93	98.24 95	91.20 154	96.89 213	97.73 146	94.74 63	96.49 100	98.49 52	90.88 76	99.58 92	96.44 70	98.32 132	99.13 85

PAPM_NR		95.01 120	94.59 125	96.26 129	98.89 56	90.68 179	97.24 179	97.73 146	91.80 174	92.93 215	96.62 213	89.13 96	99.14 160	89.21 263	97.78 154	98.97 105

Anonymous20240529		91.98 248	90.73 275	95.73 168	98.14 107	89.40 228	97.99 63	97.72 148	79.63 425	93.54 194	97.41 156	69.94 384	99.56 100	91.04 216	91.11 305	98.22 190

CHOSEN 280x420		93.12 198	92.72 196	94.34 249	96.71 214	87.27 292	90.29 432	97.72 148	86.61 352	91.34 252	95.29 280	84.29 191	98.41 252	93.25 166	98.94 105	97.35 252

EI-MVSNet-UG-set		96.34 78	96.30 77	96.47 110	98.20 101	90.93 168	96.86 216	97.72 148	94.67 66	96.16 116	98.46 56	90.43 81	99.58 92	96.23 76	97.96 149	98.90 121

LS3D		93.57 181	92.61 201	96.47 110	97.59 151	91.61 133	97.67 118	97.72 148	85.17 376	90.29 274	98.34 69	84.60 183	99.73 55	83.85 358	98.27 135	98.06 209

PAPR		94.18 148	93.42 170	96.48 109	97.64 145	91.42 145	95.55 321	97.71 152	88.99 283	92.34 225	95.82 253	89.19 94	99.11 163	86.14 322	97.38 166	98.90 121

UGNet		94.04 159	93.28 173	96.31 123	96.85 196	91.19 155	97.88 84	97.68 153	94.40 80	93.00 210	96.18 233	73.39 360	99.61 84	91.72 200	98.46 126	98.13 198
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				95.46 188	98.18 105	88.90 248		97.66 154	82.73 405	97.03 75	98.07 91	90.06 84	98.85 199	89.67 248	98.98 103	98.64 149

test12				97.65 43	98.46 75	94.26 39		97.66 154		95.52 144		90.89 75	99.46 120		99.25 74	99.22 78

DTE-MVSNet		90.56 314	89.75 320	93.01 317	93.95 371	87.25 293	97.64 126	97.65 156	90.74 221	87.12 363	95.68 264	79.97 281	97.00 387	83.33 359	81.66 406	94.78 372

TAPA-MVS	90.10 7	92.30 234	91.22 253	95.56 177	98.33 86	89.60 216	96.79 224	97.65 156	81.83 411	91.52 247	97.23 168	87.94 119	98.91 194	71.31 435	98.37 130	98.17 196
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 199	92.45 209	95.05 203	98.09 110	89.21 238	96.89 213	97.64 158	93.18 126	91.79 241	97.28 163	75.35 342	98.65 231	88.99 268	92.84 275	97.28 255

test_cas_vis1_n_1920		94.48 142	94.55 130	94.28 254	96.78 208	86.45 317	97.63 128	97.64 158	93.32 119	97.68 54	98.36 65	73.75 358	99.08 171	96.73 60	99.05 98	97.31 254

NormalMVS		96.36 77	96.11 81	97.12 72	99.37 16	92.90 83	97.99 63	97.63 160	95.92 14	96.57 96	97.93 103	85.34 169	99.50 114	94.99 123	99.21 77	98.97 105

Elysia		94.00 161	93.12 176	96.64 89	96.08 270	92.72 91	97.50 146	97.63 160	91.15 207	94.82 157	97.12 174	74.98 345	99.06 177	90.78 221	98.02 145	98.12 200

StellarMVS		94.00 161	93.12 176	96.64 89	96.08 270	92.72 91	97.50 146	97.63 160	91.15 207	94.82 157	97.12 174	74.98 345	99.06 177	90.78 221	98.02 145	98.12 200

cdsmvs_eth3d_5k		23.24 430	30.99 432	0.00 448	0.00 471	0.00 473	0.00 459	97.63 160	0.00 466	0.00 467	96.88 192	84.38 188	0.00 467	0.00 466	0.00 465	0.00 463

DPM-MVS		95.69 97	94.92 115	98.01 20	98.08 113	95.71 9	95.27 337	97.62 164	90.43 240	95.55 141	97.07 178	91.72 51	99.50 114	89.62 250	98.94 105	98.82 133

sasdasda		96.02 86	95.45 96	97.75 36	97.59 151	95.15 23	98.28 31	97.60 165	94.52 73	96.27 111	96.12 238	87.65 125	99.18 151	96.20 82	94.82 237	98.91 118

canonicalmvs		96.02 86	95.45 96	97.75 36	97.59 151	95.15 23	98.28 31	97.60 165	94.52 73	96.27 111	96.12 238	87.65 125	99.18 151	96.20 82	94.82 237	98.91 118

test222					98.24 95	92.21 110	95.33 332	97.60 165	79.22 427	95.25 147	97.84 116	88.80 102			99.15 89	98.72 143

cascas		91.20 289	90.08 302	94.58 235	94.97 331	89.16 242	93.65 397	97.59 168	79.90 424	89.40 306	92.92 385	75.36 341	98.36 260	92.14 187	94.75 240	96.23 282

h-mvs33		94.15 151	93.52 162	96.04 142	97.81 133	90.22 197	97.62 130	97.58 169	95.19 34	96.74 83	97.45 151	83.67 200	99.61 84	95.85 96	79.73 413	98.29 186

MGCFI-Net		95.94 91	95.40 100	97.56 49	97.59 151	94.62 31	98.21 43	97.57 170	94.41 79	96.17 115	96.16 236	87.54 130	99.17 153	96.19 84	94.73 242	98.91 118

MVSFormer		95.37 106	95.16 108	95.99 149	96.34 248	91.21 152	98.22 41	97.57 170	91.42 191	96.22 113	97.32 159	86.20 155	97.92 320	94.07 147	99.05 98	98.85 129

test_djsdf		93.07 201	92.76 191	94.00 266	93.49 388	88.70 252	98.22 41	97.57 170	91.42 191	90.08 286	95.55 271	82.85 222	97.92 320	94.07 147	91.58 296	95.40 327

OMC-MVS		95.09 119	94.70 122	96.25 132	98.46 75	91.28 148	96.43 257	97.57 170	92.04 169	94.77 161	97.96 102	87.01 142	99.09 168	91.31 210	96.77 187	98.36 179

PS-MVSNAJss		93.74 174	93.51 163	94.44 243	93.91 373	89.28 236	97.75 104	97.56 174	92.50 153	89.94 288	96.54 216	88.65 105	98.18 275	93.83 156	90.90 310	95.86 297

casdiffmvs_mvg		95.81 96	95.57 90	96.51 106	96.87 193	91.49 139	97.50 146	97.56 174	93.99 91	95.13 151	97.92 106	87.89 120	98.78 208	95.97 92	97.33 169	99.26 75
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jajsoiax		92.42 227	91.89 227	94.03 265	93.33 396	88.50 259	97.73 108	97.53 176	92.00 171	88.85 323	96.50 218	75.62 340	98.11 282	93.88 154	91.56 297	95.48 317

mvs_tets		92.31 233	91.76 230	93.94 274	93.41 393	88.29 264	97.63 128	97.53 176	92.04 169	88.76 326	96.45 220	74.62 350	98.09 287	93.91 152	91.48 298	95.45 322

dcpmvs_2		96.37 76	97.05 33	94.31 252	98.96 51	84.11 364	97.56 137	97.51 178	93.92 93	97.43 61	98.52 49	92.75 32	99.32 135	97.32 49	99.50 36	99.51 45

HQP_MVS		93.78 173	93.43 168	94.82 218	96.21 252	89.99 202	97.74 106	97.51 178	94.85 51	91.34 252	96.64 206	81.32 255	98.60 236	93.02 174	92.23 284	95.86 297

plane_prior5								97.51 178					98.60 236	93.02 174	92.23 284	95.86 297

viewmanbaseed2359cas		95.24 113	95.02 113	95.91 152	96.87 193	89.98 204	96.82 221	97.49 181	92.26 158	95.47 145	97.82 118	86.47 148	98.69 224	94.80 132	97.20 177	99.06 95

reproduce_monomvs		91.30 284	91.10 257	91.92 351	96.82 201	82.48 384	97.01 202	97.49 181	94.64 69	88.35 334	95.27 283	70.53 377	98.10 283	95.20 116	84.60 381	95.19 345

PS-MVSNAJ		95.37 106	95.33 103	95.49 184	97.35 161	90.66 180	95.31 334	97.48 183	93.85 96	96.51 99	95.70 263	88.65 105	99.65 73	94.80 132	98.27 135	96.17 286

API-MVS		94.84 130	94.49 132	95.90 153	97.90 128	92.00 119	97.80 98	97.48 183	89.19 275	94.81 159	96.71 199	88.84 101	99.17 153	88.91 270	98.76 112	96.53 275

MG-MVS		95.61 101	95.38 101	96.31 123	98.42 79	90.53 182	96.04 291	97.48 183	93.47 113	95.67 138	98.10 88	89.17 95	99.25 142	91.27 211	98.77 111	99.13 85

MAR-MVS		94.22 147	93.46 165	96.51 106	98.00 119	92.19 113	97.67 118	97.47 186	88.13 316	93.00 210	95.84 251	84.86 181	99.51 111	87.99 283	98.17 140	97.83 227
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		92.98 205	92.53 205	94.32 250	96.12 267	89.20 239	95.28 335	97.47 186	92.66 150	89.90 289	95.62 267	80.58 268	98.40 253	92.73 179	92.40 282	95.38 329
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 282	90.22 298	94.68 229	94.86 340	87.86 281	97.23 183	97.46 188	87.99 317	89.90 289	96.92 190	66.35 412	98.23 269	90.30 235	90.99 308	97.96 214

nrg030		94.05 158	93.31 172	96.27 128	95.22 318	94.59 32	98.34 26	97.46 188	92.93 141	91.21 261	96.64 206	87.23 140	98.22 270	94.99 123	85.80 361	95.98 296

XVG-OURS		93.72 175	93.35 171	94.80 223	97.07 175	88.61 253	94.79 352	97.46 188	91.97 172	93.99 180	97.86 113	81.74 249	98.88 196	92.64 180	92.67 280	96.92 267

LPG-MVS_test		92.94 208	92.56 202	94.10 260	96.16 262	88.26 266	97.65 122	97.46 188	91.29 195	90.12 282	97.16 171	79.05 297	98.73 218	92.25 184	91.89 292	95.31 334

LGP-MVS_train				94.10 260	96.16 262	88.26 266		97.46 188	91.29 195	90.12 282	97.16 171	79.05 297	98.73 218	92.25 184	91.89 292	95.31 334

MVS		91.71 256	90.44 285	95.51 181	95.20 320	91.59 135	96.04 291	97.45 193	73.44 441	87.36 359	95.60 268	85.42 168	99.10 165	85.97 327	97.46 161	95.83 301

XVG-OURS-SEG-HR		93.86 170	93.55 158	94.81 220	97.06 178	88.53 258	95.28 335	97.45 193	91.68 179	94.08 179	97.68 131	82.41 234	98.90 195	93.84 155	92.47 281	96.98 263

baseline		95.58 102	95.42 99	96.08 138	96.78 208	90.41 188	97.16 190	97.45 193	93.69 102	95.65 139	97.85 114	87.29 138	98.68 226	95.66 102	97.25 175	99.13 85

ab-mvs		93.57 181	92.55 203	96.64 89	97.28 164	91.96 122	95.40 328	97.45 193	89.81 257	93.22 207	96.28 229	79.62 288	99.46 120	90.74 224	93.11 272	98.50 162

xiu_mvs_v2_base		95.32 109	95.29 104	95.40 189	97.22 166	90.50 183	95.44 327	97.44 197	93.70 101	96.46 103	96.18 233	88.59 109	99.53 106	94.79 135	97.81 153	96.17 286

1314		92.81 217	92.03 220	95.14 199	95.33 310	89.52 223	96.04 291	97.44 197	87.72 330	86.25 380	95.33 279	83.84 197	98.79 207	89.26 260	97.05 182	97.11 261

casdiffmvs		95.64 99	95.49 93	96.08 138	96.76 213	90.45 185	97.29 176	97.44 197	94.00 90	95.46 146	97.98 100	87.52 133	98.73 218	95.64 106	97.33 169	99.08 92
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
XXY-MVS		92.16 241	91.23 252	94.95 214	94.75 345	90.94 167	97.47 155	97.43 200	89.14 276	88.90 319	96.43 221	79.71 285	98.24 268	89.56 251	87.68 342	95.67 313

anonymousdsp		92.16 241	91.55 238	93.97 270	92.58 411	89.55 220	97.51 145	97.42 201	89.42 269	88.40 333	94.84 302	80.66 266	97.88 325	91.87 196	91.28 302	94.48 380

Effi-MVS+		94.93 125	94.45 134	96.36 121	96.61 218	91.47 142	96.41 259	97.41 202	91.02 213	94.50 167	95.92 247	87.53 131	98.78 208	93.89 153	96.81 186	98.84 132

RRT-MVS		94.51 140	94.35 137	94.98 210	96.40 242	86.55 315	97.56 137	97.41 202	93.19 124	94.93 154	97.04 180	79.12 295	99.30 139	96.19 84	97.32 171	99.09 91

HQP3-MVS								97.39 204							92.10 289

HQP-MVS		93.19 195	92.74 194	94.54 238	95.86 276	89.33 232	96.65 241	97.39 204	93.55 105	90.14 276	95.87 249	80.95 259	98.50 246	92.13 190	92.10 289	95.78 305

PLC	91.00 6	94.11 155	93.43 168	96.13 137	98.58 73	91.15 161	96.69 237	97.39 204	87.29 340	91.37 251	96.71 199	88.39 110	99.52 110	87.33 303	97.13 180	97.73 231
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
diffmvs_AUTHOR		95.33 108	95.27 105	95.50 183	96.37 246	89.08 244	96.08 289	97.38 207	93.09 132	96.53 98	97.74 125	86.45 149	98.68 226	96.32 72	97.48 160	98.75 139

v7n		90.76 306	89.86 313	93.45 302	93.54 385	87.60 287	97.70 116	97.37 208	88.85 289	87.65 352	94.08 350	81.08 258	98.10 283	84.68 344	83.79 394	94.66 377

UnsupCasMVSNet_eth		85.99 383	84.45 387	90.62 386	89.97 429	82.40 387	93.62 398	97.37 208	89.86 253	78.59 431	92.37 395	65.25 420	95.35 421	82.27 372	70.75 439	94.10 391

ACMM	89.79 8	92.96 206	92.50 207	94.35 247	96.30 250	88.71 251	97.58 133	97.36 210	91.40 193	90.53 269	96.65 205	79.77 284	98.75 215	91.24 212	91.64 294	95.59 315
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 120	94.76 118	95.75 165	96.58 221	91.71 128	96.25 277	97.35 211	92.99 134	96.70 85	96.63 210	82.67 226	99.44 123	96.22 77	97.46 161	96.11 292

xiu_mvs_v1_base		95.01 120	94.76 118	95.75 165	96.58 221	91.71 128	96.25 277	97.35 211	92.99 134	96.70 85	96.63 210	82.67 226	99.44 123	96.22 77	97.46 161	96.11 292

xiu_mvs_v1_base_debi		95.01 120	94.76 118	95.75 165	96.58 221	91.71 128	96.25 277	97.35 211	92.99 134	96.70 85	96.63 210	82.67 226	99.44 123	96.22 77	97.46 161	96.11 292

diffmvs		95.25 112	95.13 109	95.63 173	96.43 241	89.34 231	95.99 295	97.35 211	92.83 145	96.31 109	97.37 157	86.44 150	98.67 228	96.26 74	97.19 178	98.87 127
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		94.71 136	94.02 145	96.79 85	97.71 139	92.05 116	96.59 250	97.35 211	90.61 232	94.64 163	96.93 187	86.41 151	99.39 128	91.20 213	94.71 243	98.94 112

SSM_0407		94.54 139	94.12 144	95.80 161	96.79 204	90.38 190	96.79 224	97.29 216	91.24 199	93.68 187	97.60 142	85.03 175	98.67 228	92.14 187	96.51 195	98.35 181

SSM_0404		94.73 135	94.31 139	95.98 150	97.05 180	90.90 170	97.01 202	97.29 216	91.24 199	94.17 176	97.60 142	85.03 175	98.76 212	92.14 187	97.30 172	98.29 186

F-COLMAP		93.58 179	92.98 183	95.37 190	98.40 81	88.98 246	97.18 188	97.29 216	87.75 329	90.49 270	97.10 177	85.21 172	99.50 114	86.70 313	96.72 190	97.63 235

VortexMVS		92.88 212	92.64 198	93.58 295	96.58 221	87.53 288	96.93 210	97.28 219	92.78 148	89.75 294	94.99 293	82.73 225	97.76 338	94.60 140	88.16 337	95.46 320

XVG-ACMP-BASELINE		90.93 302	90.21 299	93.09 315	94.31 364	85.89 332	95.33 332	97.26 220	91.06 212	89.38 307	95.44 277	68.61 395	98.60 236	89.46 253	91.05 306	94.79 370

PCF-MVS	89.48 11	91.56 266	89.95 310	96.36 121	96.60 219	92.52 99	92.51 417	97.26 220	79.41 426	88.90 319	96.56 215	84.04 196	99.55 102	77.01 411	97.30 172	97.01 262
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 221	92.14 216	94.05 263	96.40 242	88.20 269	97.36 168	97.25 222	91.52 186	88.30 337	96.64 206	78.46 309	98.72 222	91.86 197	91.48 298	95.23 341
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 179	93.46 165	93.94 274	96.19 256	86.16 326	93.73 392	97.24 223	91.54 182	93.50 196	97.04 180	85.64 165	96.91 390	90.68 226	95.59 219	98.76 135

IMVS_0407		93.94 165	93.75 151	94.49 240	96.19 256	86.16 326	96.35 267	97.24 223	91.54 182	93.50 196	97.04 180	85.64 165	98.54 243	90.68 226	95.59 219	98.76 135

IMVS_0404		92.44 225	91.92 225	94.00 266	96.19 256	86.16 326	93.84 389	97.24 223	91.54 182	88.17 343	97.04 180	76.96 327	97.09 381	90.68 226	95.59 219	98.76 135

IMVS_0403		93.98 163	93.79 150	94.55 237	96.19 256	86.16 326	96.35 267	97.24 223	91.54 182	93.59 191	97.04 180	85.86 160	98.73 218	90.68 226	95.59 219	98.76 135

OPM-MVS		93.28 191	92.76 191	94.82 218	94.63 351	90.77 175	96.65 241	97.18 227	93.72 99	91.68 245	97.26 166	79.33 292	98.63 233	92.13 190	92.28 283	95.07 348
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 210	92.02 221	95.56 177	98.19 103	90.80 173	95.27 337	97.18 227	87.96 318	91.86 240	95.68 264	80.44 271	98.99 185	84.01 353	97.54 159	96.89 268

alignmvs		95.87 95	95.23 106	97.78 32	97.56 157	95.19 21	97.86 85	97.17 229	94.39 81	96.47 102	96.40 223	85.89 159	99.20 147	96.21 81	95.11 233	98.95 111

MVS_Test		94.89 127	94.62 124	95.68 171	96.83 199	89.55 220	96.70 235	97.17 229	91.17 205	95.60 140	96.11 242	87.87 122	98.76 212	93.01 176	97.17 179	98.72 143

Fast-Effi-MVS+		93.46 185	92.75 193	95.59 176	96.77 210	90.03 199	96.81 223	97.13 231	88.19 311	91.30 255	94.27 338	86.21 154	98.63 233	87.66 295	96.46 201	98.12 200

EI-MVSNet		93.03 203	92.88 187	93.48 300	95.77 282	86.98 301	96.44 255	97.12 232	90.66 228	91.30 255	97.64 138	86.56 145	98.05 295	89.91 241	90.55 314	95.41 324

MVSTER		93.20 194	92.81 190	94.37 246	96.56 225	89.59 217	97.06 196	97.12 232	91.24 199	91.30 255	95.96 245	82.02 242	98.05 295	93.48 161	90.55 314	95.47 319

viewmambaseed2359dif		94.28 145	94.14 142	94.71 228	96.21 252	86.97 302	95.93 298	97.11 234	89.00 282	95.00 153	97.70 128	86.02 158	98.59 240	93.71 158	96.59 194	98.57 155

test_yl		94.78 133	94.23 140	96.43 114	97.74 137	91.22 150	96.85 217	97.10 235	91.23 202	95.71 134	96.93 187	84.30 189	99.31 137	93.10 169	95.12 231	98.75 139

DCV-MVSNet		94.78 133	94.23 140	96.43 114	97.74 137	91.22 150	96.85 217	97.10 235	91.23 202	95.71 134	96.93 187	84.30 189	99.31 137	93.10 169	95.12 231	98.75 139

LTVRE_ROB	88.41 13	90.99 298	89.92 312	94.19 256	96.18 260	89.55 220	96.31 273	97.09 237	87.88 321	85.67 384	95.91 248	78.79 305	98.57 241	81.50 375	89.98 319	94.44 383
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
test_fmvs1_n		92.73 219	92.88 187	92.29 341	96.08 270	81.05 398	97.98 66	97.08 238	90.72 223	96.79 81	98.18 85	63.07 424	98.45 250	97.62 38	98.42 129	97.36 250

v10		91.04 296	90.23 296	93.49 299	94.12 367	88.16 272	97.32 173	97.08 238	88.26 310	88.29 338	94.22 343	82.17 239	97.97 307	86.45 317	84.12 388	94.33 386

mamba_0408		93.70 176	92.99 180	95.83 158	96.79 204	90.38 190	88.69 442	97.07 240	90.96 215	93.68 187	97.31 161	84.97 178	98.76 212	90.95 217	96.51 195	98.35 181

SSM_04072		93.51 184	92.99 180	95.05 203	96.79 204	90.38 190	88.69 442	97.07 240	90.96 215	93.68 187	97.31 161	84.97 178	96.42 401	90.95 217	96.51 195	98.35 181

v144192		91.06 295	90.28 292	93.39 303	93.66 382	87.23 295	96.83 220	97.07 240	87.43 336	89.69 297	94.28 337	81.48 252	98.00 302	87.18 307	84.92 377	94.93 356

v1192		91.07 294	90.23 296	93.58 295	93.70 379	87.82 283	96.73 231	97.07 240	87.77 327	89.58 300	94.32 335	80.90 263	97.97 307	86.52 315	85.48 364	94.95 352

v8		91.29 286	90.53 284	93.57 297	94.15 366	88.12 273	97.34 170	97.06 244	88.99 283	88.32 336	94.26 340	83.08 213	98.01 301	87.62 297	83.92 392	94.57 379

mvs_anonymous		93.82 171	93.74 152	94.06 262	96.44 240	85.41 341	95.81 305	97.05 245	89.85 255	90.09 285	96.36 225	87.44 135	97.75 340	93.97 149	96.69 191	99.02 97

IterMVS-LS		92.29 235	91.94 224	93.34 305	96.25 251	86.97 302	96.57 253	97.05 245	90.67 226	89.50 305	94.80 305	86.59 144	97.64 348	89.91 241	86.11 359	95.40 327
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 304	90.03 307	93.29 307	93.55 384	86.96 304	96.74 230	97.04 247	87.36 338	89.52 304	94.34 332	80.23 276	97.97 307	86.27 318	85.21 370	94.94 354

CDS-MVSNet		94.14 154	93.54 159	95.93 151	96.18 260	91.46 143	96.33 271	97.04 247	88.97 285	93.56 192	96.51 217	87.55 129	97.89 324	89.80 244	95.95 207	98.44 172
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 340	89.26 333	91.19 375	95.16 321	80.29 409	94.53 359	97.03 249	91.79 175	88.86 322	94.10 347	69.94 384	97.82 330	85.29 336	86.66 355	95.45 322

v1144		91.37 279	90.60 280	93.68 290	93.89 374	88.23 268	96.84 219	97.03 249	88.37 307	89.69 297	94.39 327	82.04 241	97.98 304	87.80 287	85.37 366	94.84 362

v1240		90.70 310	89.85 314	93.23 309	93.51 387	86.80 305	96.61 247	97.02 251	87.16 343	89.58 300	94.31 336	79.55 289	97.98 304	85.52 333	85.44 365	94.90 359

EPP-MVSNet		95.22 115	95.04 112	95.76 163	97.49 158	89.56 219	98.67 11	97.00 252	90.69 224	94.24 173	97.62 140	89.79 90	98.81 205	93.39 165	96.49 199	98.92 117

V42		91.58 265	90.87 264	93.73 285	94.05 370	88.50 259	97.32 173	96.97 253	88.80 295	89.71 295	94.33 333	82.54 230	98.05 295	89.01 267	85.07 373	94.64 378

test_fmvs1		93.21 193	93.53 160	92.25 344	96.55 227	81.20 397	97.40 164	96.96 254	90.68 225	96.80 79	98.04 94	69.25 390	98.40 253	97.58 39	98.50 122	97.16 260

FMVSNet2		91.31 283	90.08 302	94.99 208	96.51 233	92.21 110	97.41 160	96.95 255	88.82 292	88.62 328	94.75 307	73.87 354	97.42 369	85.20 339	88.55 334	95.35 331

ACMH	87.59 16	90.53 315	89.42 329	93.87 279	96.21 252	87.92 278	97.24 179	96.94 256	88.45 305	83.91 404	96.27 230	71.92 366	98.62 235	84.43 347	89.43 325	95.05 350
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 280	90.27 293	94.59 231	96.51 233	91.18 157	97.50 146	96.93 257	88.82 292	89.35 308	94.51 320	73.87 354	97.29 376	86.12 323	88.82 329	95.31 334

test1		91.35 280	90.27 293	94.59 231	96.51 233	91.18 157	97.50 146	96.93 257	88.82 292	89.35 308	94.51 320	73.87 354	97.29 376	86.12 323	88.82 329	95.31 334

FMVSNet3		91.78 254	90.69 278	95.03 206	96.53 230	92.27 108	97.02 199	96.93 257	89.79 258	89.35 308	94.65 313	77.01 325	97.47 364	86.12 323	88.82 329	95.35 331

FMVSNet1		89.88 335	88.31 348	94.59 231	95.41 300	91.18 157	97.50 146	96.93 257	86.62 351	87.41 357	94.51 320	65.94 417	97.29 376	83.04 362	87.43 345	95.31 334

GeoE		93.89 168	93.28 173	95.72 169	96.96 190	89.75 212	98.24 39	96.92 261	89.47 266	92.12 231	97.21 169	84.42 187	98.39 258	87.71 290	96.50 198	99.01 100

SymmetryMVS		95.94 91	95.54 91	97.15 70	97.85 130	92.90 83	97.99 63	96.91 262	95.92 14	96.57 96	97.93 103	85.34 169	99.50 114	94.99 123	96.39 202	99.05 96

miper_enhance_ethall		91.54 269	91.01 260	93.15 313	95.35 306	87.07 300	93.97 381	96.90 263	86.79 349	89.17 315	93.43 379	86.55 146	97.64 348	89.97 240	86.93 350	94.74 374

eth_miper_zixun_eth		91.02 297	90.59 281	92.34 339	95.33 310	84.35 360	94.10 378	96.90 263	88.56 301	88.84 324	94.33 333	84.08 194	97.60 353	88.77 273	84.37 386	95.06 349

TAMVS		94.01 160	93.46 165	95.64 172	96.16 262	90.45 185	96.71 234	96.89 265	89.27 273	93.46 199	96.92 190	87.29 138	97.94 317	88.70 275	95.74 213	98.53 158

miper_ehance_all_eth		91.59 263	91.13 256	92.97 319	95.55 292	86.57 313	94.47 362	96.88 266	87.77 327	88.88 321	94.01 352	86.22 153	97.54 357	89.49 252	86.93 350	94.79 370

v2v482		91.59 263	90.85 267	93.80 282	93.87 375	88.17 271	96.94 209	96.88 266	89.54 263	89.53 303	94.90 299	81.70 250	98.02 300	89.25 261	85.04 375	95.20 342

CNLPA		94.28 145	93.53 160	96.52 102	98.38 84	92.55 98	96.59 250	96.88 266	90.13 248	91.91 237	97.24 167	85.21 172	99.09 168	87.64 296	97.83 152	97.92 217

PAPM		91.52 270	90.30 291	95.20 196	95.30 313	89.83 210	93.38 403	96.85 269	86.26 359	88.59 329	95.80 254	84.88 180	98.15 277	75.67 416	95.93 208	97.63 235

c3_l		91.38 277	90.89 263	92.88 323	95.58 290	86.30 320	94.68 354	96.84 270	88.17 312	88.83 325	94.23 341	85.65 164	97.47 364	89.36 256	84.63 379	94.89 360

pm-mvs1		90.72 309	89.65 324	93.96 271	94.29 365	89.63 214	97.79 100	96.82 271	89.07 278	86.12 382	95.48 276	78.61 307	97.78 335	86.97 311	81.67 405	94.46 381

test_vis1_n		92.37 230	92.26 214	92.72 329	94.75 345	82.64 380	98.02 60	96.80 272	91.18 204	97.77 53	97.93 103	58.02 434	98.29 266	97.63 36	98.21 137	97.23 258

CMPMVS	62.92 21	85.62 388	84.92 383	87.74 412	89.14 434	73.12 442	94.17 376	96.80 272	73.98 438	73.65 440	94.93 297	66.36 411	97.61 352	83.95 355	91.28 302	92.48 418
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 322	89.77 318	91.78 360	94.33 362	84.72 357	95.55 321	96.73 274	86.17 361	86.36 379	95.28 282	71.28 371	97.80 333	84.09 352	98.14 141	92.81 410

Effi-MVS+-dtu		93.08 200	93.21 175	92.68 332	96.02 273	83.25 374	97.14 192	96.72 275	93.85 96	91.20 262	93.44 376	83.08 213	98.30 265	91.69 203	95.73 214	96.50 277

TSAR-MVS + GP.		96.69 62	96.49 66	97.27 63	98.31 87	93.39 63	96.79 224	96.72 275	94.17 85	97.44 59	97.66 134	92.76 31	99.33 133	96.86 57	97.76 156	99.08 92

1112_ss		93.37 188	92.42 210	96.21 133	97.05 180	90.99 164	96.31 273	96.72 275	86.87 348	89.83 292	96.69 203	86.51 147	99.14 160	88.12 280	93.67 266	98.50 162

PVSNet	86.66 18	92.24 238	91.74 233	93.73 285	97.77 135	83.69 371	92.88 412	96.72 275	87.91 320	93.00 210	94.86 301	78.51 308	99.05 180	86.53 314	97.45 165	98.47 167

miper_lstm_enhance		90.50 318	90.06 306	91.83 356	95.33 310	83.74 368	93.86 387	96.70 279	87.56 334	87.79 349	93.81 360	83.45 205	96.92 389	87.39 301	84.62 380	94.82 365

v148		90.99 298	90.38 287	92.81 326	93.83 376	85.80 333	96.78 228	96.68 280	89.45 268	88.75 327	93.93 356	82.96 219	97.82 330	87.83 286	83.25 397	94.80 368

ACMH+	87.92 14	90.20 326	89.18 335	93.25 308	96.48 236	86.45 317	96.99 205	96.68 280	88.83 291	84.79 393	96.22 232	70.16 381	98.53 244	84.42 348	88.04 338	94.77 373

CANet_DTU		94.37 143	93.65 155	96.55 99	96.46 239	92.13 114	96.21 281	96.67 282	94.38 82	93.53 195	97.03 185	79.34 291	99.71 61	90.76 223	98.45 127	97.82 228

cl____		90.96 301	90.32 289	92.89 322	95.37 304	86.21 323	94.46 364	96.64 283	87.82 323	88.15 344	94.18 344	82.98 217	97.54 357	87.70 291	85.59 362	94.92 358

HY-MVS	89.66 9	93.87 169	92.95 184	96.63 93	97.10 174	92.49 100	95.64 318	96.64 283	89.05 280	93.00 210	95.79 257	85.77 163	99.45 122	89.16 266	94.35 245	97.96 214

Test_1112_low_res		92.84 215	91.84 228	95.85 157	97.04 182	89.97 206	95.53 323	96.64 283	85.38 371	89.65 299	95.18 287	85.86 160	99.10 165	87.70 291	93.58 271	98.49 164

DIV-MVS_self_test		90.97 300	90.33 288	92.88 323	95.36 305	86.19 325	94.46 364	96.63 286	87.82 323	88.18 342	94.23 341	82.99 216	97.53 359	87.72 288	85.57 363	94.93 356

Fast-Effi-MVS+-dtu		92.29 235	91.99 222	93.21 311	95.27 314	85.52 339	97.03 197	96.63 286	92.09 167	89.11 317	95.14 289	80.33 274	98.08 288	87.54 299	94.74 241	96.03 295

UnsupCasMVSNet_bld		82.13 404	79.46 409	90.14 393	88.00 442	82.47 385	90.89 430	96.62 288	78.94 428	75.61 435	84.40 446	56.63 437	96.31 403	77.30 408	66.77 447	91.63 428

cl22		91.21 288	90.56 283	93.14 314	96.09 269	86.80 305	94.41 366	96.58 289	87.80 325	88.58 330	93.99 354	80.85 264	97.62 351	89.87 243	86.93 350	94.99 351

jason		94.84 130	94.39 136	96.18 135	95.52 293	90.93 168	96.09 288	96.52 290	89.28 272	96.01 123	97.32 159	84.70 182	98.77 211	95.15 119	98.91 107	98.85 129
jason: jason.
tt0805		91.09 293	90.07 305	94.16 258	95.61 288	88.31 263	97.56 137	96.51 291	89.56 262	89.17 315	95.64 266	67.08 409	98.38 259	91.07 215	88.44 335	95.80 303

AUN-MVS		91.76 255	90.75 273	94.81 220	97.00 186	88.57 255	96.65 241	96.49 292	89.63 260	92.15 229	96.12 238	78.66 306	98.50 246	90.83 219	79.18 416	97.36 250

hse-mvs2		93.45 186	92.99 180	94.81 220	97.02 184	88.59 254	96.69 237	96.47 293	95.19 34	96.74 83	96.16 236	83.67 200	98.48 249	95.85 96	79.13 417	97.35 252

SD_0403		90.01 330	90.02 308	89.96 396	95.65 287	76.76 430	95.76 309	96.46 294	90.58 235	86.59 376	96.29 228	82.12 240	94.78 425	73.00 430	93.76 264	98.35 181

EG-PatchMatch MVS		87.02 370	85.44 375	91.76 362	92.67 408	85.00 351	96.08 289	96.45 295	83.41 401	79.52 427	93.49 373	57.10 436	97.72 342	79.34 399	90.87 311	92.56 415

KD-MVS_self_test		85.95 384	84.95 382	88.96 406	89.55 433	79.11 424	95.13 344	96.42 296	85.91 364	84.07 402	90.48 418	70.03 383	94.82 424	80.04 391	72.94 436	92.94 408

pmmvs6		87.81 362	86.19 370	92.69 331	91.32 421	86.30 320	97.34 170	96.41 297	80.59 422	84.05 403	94.37 329	67.37 404	97.67 345	84.75 343	79.51 415	94.09 393

PMMVS		92.86 213	92.34 211	94.42 245	94.92 336	86.73 308	94.53 359	96.38 298	84.78 383	94.27 172	95.12 291	83.13 212	98.40 253	91.47 207	96.49 199	98.12 200

RPSCF		90.75 307	90.86 265	90.42 389	96.84 197	76.29 433	95.61 319	96.34 299	83.89 392	91.38 250	97.87 111	76.45 331	98.78 208	87.16 308	92.23 284	96.20 284

BP-MVS1		95.89 93	95.49 93	97.08 77	96.67 215	93.20 73	98.08 54	96.32 300	94.56 70	96.32 108	97.84 116	84.07 195	99.15 157	96.75 59	98.78 110	98.90 121

MSDG		91.42 275	90.24 295	94.96 213	97.15 172	88.91 247	93.69 395	96.32 300	85.72 367	86.93 372	96.47 219	80.24 275	98.98 186	80.57 388	95.05 234	96.98 263

WBMVS		90.69 312	89.99 309	92.81 326	96.48 236	85.00 351	95.21 342	96.30 302	89.46 267	89.04 318	94.05 351	72.45 364	97.82 330	89.46 253	87.41 347	95.61 314

OurMVSNet-221017-0		90.51 317	90.19 300	91.44 368	93.41 393	81.25 395	96.98 206	96.28 303	91.68 179	86.55 377	96.30 227	74.20 353	97.98 304	88.96 269	87.40 348	95.09 347

MVP-Stereo		90.74 308	90.08 302	92.71 330	93.19 398	88.20 269	95.86 302	96.27 304	86.07 362	84.86 392	94.76 306	77.84 320	97.75 340	83.88 357	98.01 147	92.17 425
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 124	94.56 127	96.29 127	96.34 248	91.21 152	95.83 304	96.27 304	88.93 287	96.22 113	96.88 192	86.20 155	98.85 199	95.27 115	99.05 98	98.82 133

BH-untuned		92.94 208	92.62 200	93.92 278	97.22 166	86.16 326	96.40 263	96.25 306	90.06 249	89.79 293	96.17 235	83.19 209	98.35 261	87.19 306	97.27 174	97.24 257

CL-MVSNet_self_test		86.31 379	85.15 379	89.80 398	88.83 437	81.74 393	93.93 384	96.22 307	86.67 350	85.03 390	90.80 416	78.09 316	94.50 426	74.92 419	71.86 438	93.15 406

IS-MVSNet		94.90 126	94.52 131	96.05 141	97.67 141	90.56 181	98.44 22	96.22 307	93.21 121	93.99 180	97.74 125	85.55 167	98.45 250	89.98 239	97.86 151	99.14 84

FA-MVS(test-final)		93.52 183	92.92 185	95.31 193	96.77 210	88.54 257	94.82 351	96.21 309	89.61 261	94.20 174	95.25 285	83.24 207	99.14 160	90.01 238	96.16 204	98.25 188

GA-MVS		91.38 277	90.31 290	94.59 231	94.65 350	87.62 286	94.34 369	96.19 310	90.73 222	90.35 273	93.83 357	71.84 367	97.96 311	87.22 305	93.61 269	98.21 191

LuminaMVS		94.89 127	94.35 137	96.53 100	95.48 295	92.80 87	96.88 215	96.18 311	92.85 144	95.92 126	96.87 194	81.44 253	98.83 202	96.43 71	97.10 181	97.94 216

IterMVS-SCA-FT		90.31 320	89.81 316	91.82 357	95.52 293	84.20 363	94.30 372	96.15 312	90.61 232	87.39 358	94.27 338	75.80 337	96.44 400	87.34 302	86.88 354	94.82 365

IterMVS		90.15 328	89.67 322	91.61 364	95.48 295	83.72 369	94.33 370	96.12 313	89.99 250	87.31 361	94.15 346	75.78 339	96.27 404	86.97 311	86.89 353	94.83 363
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 218	91.51 242	96.52 102	98.77 58	90.99 164	97.38 167	96.08 314	82.38 407	89.29 311	97.87 111	83.77 198	99.69 67	81.37 381	96.69 191	98.89 125

pmmvs4		90.93 302	89.85 314	94.17 257	93.34 395	90.79 174	94.60 356	96.02 315	84.62 384	87.45 355	95.15 288	81.88 247	97.45 366	87.70 291	87.87 340	94.27 390

ppachtmachnet_test		88.35 357	87.29 356	91.53 365	92.45 414	83.57 372	93.75 391	95.97 316	84.28 387	85.32 389	94.18 344	79.00 303	96.93 388	75.71 415	84.99 376	94.10 391

Anonymous20240521		86.42 377	85.44 375	89.34 404	90.33 426	79.79 415	96.73 231	95.92 317	83.71 397	83.25 408	91.36 413	63.92 422	96.01 405	78.39 403	85.36 367	92.22 423

ITE_SJBPF				92.43 335	95.34 307	85.37 344		95.92 317	91.47 188	87.75 351	96.39 224	71.00 373	97.96 311	82.36 371	89.86 321	93.97 396

test_fmvs2		89.77 339	89.93 311	89.31 405	93.68 381	76.37 432	97.64 126	95.90 319	89.84 256	91.49 248	96.26 231	58.77 432	97.10 380	94.65 137	91.13 304	94.46 381

USDC		88.94 348	87.83 353	92.27 342	94.66 349	84.96 353	93.86 387	95.90 319	87.34 339	83.40 406	95.56 270	67.43 403	98.19 274	82.64 370	89.67 323	93.66 399

COLMAP_ROB	87.81 15	90.40 319	89.28 332	93.79 283	97.95 123	87.13 299	96.92 211	95.89 321	82.83 404	86.88 374	97.18 170	73.77 357	99.29 140	78.44 402	93.62 268	94.95 352
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 171	93.08 178	96.02 144	97.88 129	89.96 207	97.72 111	95.85 322	92.43 154	95.86 128	98.44 58	68.42 399	99.39 128	96.31 73	94.85 235	98.71 145

VDDNet		93.05 202	92.07 217	96.02 144	96.84 197	90.39 189	98.08 54	95.85 322	86.22 360	95.79 131	98.46 56	67.59 402	99.19 148	94.92 126	94.85 235	98.47 167

mvsmamba		94.57 138	94.14 142	95.87 154	97.03 183	89.93 208	97.84 89	95.85 322	91.34 194	94.79 160	96.80 195	80.67 265	98.81 205	94.85 127	98.12 142	98.85 129

Vis-MVSNet (Re-imp)		94.15 151	93.88 148	94.95 214	97.61 149	87.92 278	98.10 52	95.80 325	92.22 160	93.02 209	97.45 151	84.53 185	97.91 323	88.24 279	97.97 148	99.02 97

MM		97.29 27	96.98 37	98.23 11	98.01 117	95.03 26	98.07 56	95.76 326	97.78 1	97.52 56	98.80 36	88.09 115	99.86 9	99.44 2	99.37 63	99.80 1

KD-MVS_2432*1600		84.81 394	82.64 397	91.31 370	91.07 423	85.34 345	91.22 425	95.75 327	85.56 369	83.09 409	90.21 421	67.21 405	95.89 407	77.18 409	62.48 451	92.69 411

miper_refine_blended		84.81 394	82.64 397	91.31 370	91.07 423	85.34 345	91.22 425	95.75 327	85.56 369	83.09 409	90.21 421	67.21 405	95.89 407	77.18 409	62.48 451	92.69 411

FE-MVS		92.05 246	91.05 258	95.08 202	96.83 199	87.93 277	93.91 386	95.70 329	86.30 357	94.15 177	94.97 294	76.59 329	99.21 146	84.10 351	96.86 184	98.09 206

tpm cat1		88.36 356	87.21 359	91.81 358	95.13 326	80.55 404	92.58 416	95.70 329	74.97 437	87.45 355	91.96 406	78.01 319	98.17 276	80.39 390	88.74 332	96.72 273

our_test_3		88.78 352	87.98 352	91.20 374	92.45 414	82.53 382	93.61 399	95.69 331	85.77 366	84.88 391	93.71 362	79.99 280	96.78 396	79.47 396	86.24 356	94.28 389

BH-w/o		92.14 243	91.75 231	93.31 306	96.99 187	85.73 336	95.67 313	95.69 331	88.73 297	89.26 313	94.82 304	82.97 218	98.07 292	85.26 338	96.32 203	96.13 291

CR-MVSNet		90.82 305	89.77 318	93.95 272	94.45 358	87.19 296	90.23 433	95.68 333	86.89 347	92.40 219	92.36 398	80.91 261	97.05 383	81.09 385	93.95 261	97.60 240

Patchmtry		88.64 354	87.25 357	92.78 328	94.09 368	86.64 309	89.82 437	95.68 333	80.81 419	87.63 353	92.36 398	80.91 261	97.03 384	78.86 400	85.12 372	94.67 376

testing91		91.90 251	91.02 259	94.53 239	96.54 228	86.55 315	95.86 302	95.64 335	91.77 176	91.89 238	93.47 375	69.94 384	98.86 197	90.23 237	93.86 263	98.18 193

BH-RMVSNet		92.72 220	91.97 223	94.97 212	97.16 170	87.99 276	96.15 286	95.60 336	90.62 231	91.87 239	97.15 173	78.41 310	98.57 241	83.16 360	97.60 158	98.36 179

PVSNet_0	82.17 19	85.46 389	83.64 392	90.92 378	95.27 314	79.49 420	90.55 431	95.60 336	83.76 396	83.00 411	89.95 423	71.09 372	97.97 307	82.75 368	60.79 453	95.31 334

guyue		95.17 118	94.96 114	95.82 159	96.97 189	89.65 213	97.56 137	95.58 338	94.82 55	95.72 133	97.42 155	82.90 220	98.84 201	96.71 62	96.93 183	98.96 108

SCA		91.84 253	91.18 255	93.83 280	95.59 289	84.95 354	94.72 353	95.58 338	90.82 218	92.25 227	93.69 364	75.80 337	98.10 283	86.20 320	95.98 206	98.45 169

MonoMVSNet		91.92 249	91.77 229	92.37 336	92.94 402	83.11 376	97.09 195	95.55 340	92.91 142	90.85 265	94.55 317	81.27 257	96.52 399	93.01 176	87.76 341	97.47 246

AllTest		90.23 324	88.98 338	93.98 268	97.94 124	86.64 309	96.51 254	95.54 341	85.38 371	85.49 386	96.77 197	70.28 379	99.15 157	80.02 392	92.87 273	96.15 289

TestCases				93.98 268	97.94 124	86.64 309		95.54 341	85.38 371	85.49 386	96.77 197	70.28 379	99.15 157	80.02 392	92.87 273	96.15 289

mmtdpeth		89.70 341	88.96 339	91.90 353	95.84 281	84.42 359	97.46 157	95.53 343	90.27 243	94.46 169	90.50 417	69.74 388	98.95 187	97.39 48	69.48 442	92.34 419

tpmvs		89.83 338	89.15 336	91.89 354	94.92 336	80.30 408	93.11 408	95.46 344	86.28 358	88.08 345	92.65 388	80.44 271	98.52 245	81.47 377	89.92 320	96.84 269

pmmvs5		89.86 337	88.87 342	92.82 325	92.86 404	86.23 322	96.26 276	95.39 345	84.24 388	87.12 363	94.51 320	74.27 352	97.36 373	87.61 298	87.57 343	94.86 361

PatchmatchNet		91.91 250	91.35 244	93.59 294	95.38 302	84.11 364	93.15 407	95.39 345	89.54 263	92.10 232	93.68 366	82.82 223	98.13 278	84.81 342	95.32 227	98.52 159
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 274	91.32 246	91.79 359	95.15 324	79.20 423	93.42 402	95.37 347	88.55 302	93.49 198	93.67 367	82.49 232	98.27 267	90.41 232	89.34 326	97.90 218

Anonymous20231206		87.09 369	86.14 371	89.93 397	91.22 422	80.35 406	96.11 287	95.35 348	83.57 399	84.16 398	93.02 383	73.54 359	95.61 415	72.16 432	86.14 358	93.84 398

MIMVSNet1		84.93 392	83.05 394	90.56 387	89.56 432	84.84 356	95.40 328	95.35 348	83.91 391	80.38 423	92.21 403	57.23 435	93.34 438	70.69 438	82.75 403	93.50 401

TDRefinement		86.53 373	84.76 385	91.85 355	82.23 454	84.25 361	96.38 265	95.35 348	84.97 380	84.09 401	94.94 296	65.76 418	98.34 264	84.60 346	74.52 432	92.97 407

TR-MVS		91.48 273	90.59 281	94.16 258	96.40 242	87.33 289	95.67 313	95.34 351	87.68 331	91.46 249	95.52 273	76.77 328	98.35 261	82.85 365	93.61 269	96.79 271

EPNet_dtu		91.71 256	91.28 249	92.99 318	93.76 378	83.71 370	96.69 237	95.28 352	93.15 128	87.02 368	95.95 246	83.37 206	97.38 372	79.46 397	96.84 185	97.88 220
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 366	85.79 373	91.78 360	94.80 343	87.28 291	95.49 325	95.28 352	84.09 390	83.85 405	91.82 407	62.95 425	94.17 430	78.48 401	85.34 368	93.91 397

MDTV_nov1_ep13			90.76 271		95.22 318	80.33 407	93.03 410	95.28 352	88.14 315	92.84 216	93.83 357	81.34 254	98.08 288	82.86 363	94.34 246

LF4IMVS		87.94 360	87.25 357	89.98 395	92.38 416	80.05 414	94.38 367	95.25 355	87.59 333	84.34 395	94.74 308	64.31 421	97.66 347	84.83 341	87.45 344	92.23 422

TransMVSNet (Re)		88.94 348	87.56 354	93.08 316	94.35 361	88.45 261	97.73 108	95.23 356	87.47 335	84.26 397	95.29 280	79.86 283	97.33 374	79.44 398	74.44 433	93.45 403

test20.03		86.14 382	85.40 377	88.35 407	90.12 427	80.06 413	95.90 301	95.20 357	88.59 298	81.29 418	93.62 369	71.43 370	92.65 442	71.26 436	81.17 408	92.34 419

new-patchmatchnet		83.18 400	81.87 403	87.11 415	86.88 445	75.99 434	93.70 393	95.18 358	85.02 379	77.30 434	88.40 433	65.99 416	93.88 435	74.19 424	70.18 440	91.47 432

MDA-MVSNet_test_wron		85.87 386	84.23 389	90.80 384	92.38 416	82.57 381	93.17 405	95.15 359	82.15 408	67.65 446	92.33 401	78.20 312	95.51 418	77.33 406	79.74 412	94.31 388

YYNet1		85.87 386	84.23 389	90.78 385	92.38 416	82.46 386	93.17 405	95.14 360	82.12 409	67.69 444	92.36 398	78.16 315	95.50 419	77.31 407	79.73 413	94.39 384

Baseline_NR-MVSNet		91.20 289	90.62 279	92.95 320	93.83 376	88.03 275	97.01 202	95.12 361	88.42 306	89.70 296	95.13 290	83.47 203	97.44 367	89.66 249	83.24 398	93.37 404

thres200		92.23 239	91.39 243	94.75 227	97.61 149	89.03 245	96.60 249	95.09 362	92.08 168	93.28 204	94.00 353	78.39 311	99.04 183	81.26 384	94.18 252	96.19 285

ADS-MVSNet		89.89 334	88.68 344	93.53 298	95.86 276	84.89 355	90.93 428	95.07 363	83.23 402	91.28 258	91.81 408	79.01 301	97.85 326	79.52 394	91.39 300	97.84 225

pmmvs-eth3d		86.22 380	84.45 387	91.53 365	88.34 441	87.25 293	94.47 362	95.01 364	83.47 400	79.51 428	89.61 426	69.75 387	95.71 412	83.13 361	76.73 426	91.64 427

Anonymous202405211		92.07 245	90.83 269	95.76 163	98.19 103	88.75 250	97.58 133	95.00 365	86.00 363	93.64 190	97.45 151	66.24 414	99.53 106	90.68 226	92.71 278	99.01 100

MDA-MVSNet-bldmvs		85.00 391	82.95 396	91.17 376	93.13 400	83.33 373	94.56 358	95.00 365	84.57 385	65.13 450	92.65 388	70.45 378	95.85 409	73.57 427	77.49 422	94.33 386

ambc				86.56 418	83.60 451	70.00 445	85.69 449	94.97 367		80.60 422	88.45 432	37.42 453	96.84 393	82.69 369	75.44 430	92.86 409

testgi		87.97 359	87.21 359	90.24 392	92.86 404	80.76 399	96.67 240	94.97 367	91.74 177	85.52 385	95.83 252	62.66 427	94.47 428	76.25 413	88.36 336	95.48 317

myMVS_eth3d28		91.52 270	90.97 261	93.17 312	96.91 191	83.24 375	95.61 319	94.96 369	92.24 159	91.98 235	93.28 380	69.31 389	98.40 253	88.71 274	95.68 216	97.88 220

dp		88.90 350	88.26 350	90.81 382	94.58 354	76.62 431	92.85 413	94.93 370	85.12 377	90.07 287	93.07 382	75.81 336	98.12 281	80.53 389	87.42 346	97.71 232

test_fmvs3		83.21 399	83.02 395	83.78 422	86.77 446	68.34 448	96.76 229	94.91 371	86.49 353	84.14 400	89.48 427	36.04 454	91.73 444	91.86 197	80.77 410	91.26 434

test_0402		86.46 376	84.79 384	91.45 367	95.02 330	85.55 338	96.29 275	94.89 372	80.90 416	82.21 414	93.97 355	68.21 400	97.29 376	62.98 445	88.68 333	91.51 430

tfpn200view9		92.38 229	91.52 240	94.95 214	97.85 130	89.29 234	97.41 160	94.88 373	92.19 164	93.27 205	94.46 325	78.17 313	99.08 171	81.40 378	94.08 256	96.48 278

CVMVSNet		91.23 287	91.75 231	89.67 399	95.77 282	74.69 435	96.44 255	94.88 373	85.81 365	92.18 228	97.64 138	79.07 296	95.58 417	88.06 282	95.86 211	98.74 142

thres400		92.42 227	91.52 240	95.12 201	97.85 130	89.29 234	97.41 160	94.88 373	92.19 164	93.27 205	94.46 325	78.17 313	99.08 171	81.40 378	94.08 256	96.98 263

tt0320		85.39 390	83.12 393	92.19 346	93.44 392	85.79 334	96.19 283	94.87 376	71.19 444	82.92 412	91.76 410	58.43 433	96.81 394	81.03 386	78.26 421	93.98 395

EPNet		95.20 116	94.56 127	97.14 71	92.80 406	92.68 93	97.85 88	94.87 376	96.64 7	92.46 218	97.80 122	86.23 152	99.65 73	93.72 157	98.62 118	99.10 90
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 261	90.72 276	94.32 250	96.48 236	86.11 331	95.81 305	94.76 378	91.55 181	91.75 243	93.44 376	68.55 397	98.82 203	90.43 231	93.69 265	98.04 210

sc_t1		86.48 375	84.10 391	93.63 291	93.45 391	85.76 335	96.79 224	94.71 379	73.06 442	86.45 378	94.35 330	55.13 440	97.95 315	84.38 349	78.55 420	97.18 259

SixPastTwentyTwo		89.15 346	88.54 346	90.98 377	93.49 388	80.28 410	96.70 235	94.70 380	90.78 219	84.15 399	95.57 269	71.78 368	97.71 343	84.63 345	85.07 373	94.94 354

thres100view900		92.43 226	91.58 237	94.98 210	97.92 126	89.37 230	97.71 113	94.66 381	92.20 162	93.31 203	94.90 299	78.06 317	99.08 171	81.40 378	94.08 256	96.48 278

thres600view7		92.49 224	91.60 236	95.18 197	97.91 127	89.47 224	97.65 122	94.66 381	92.18 166	93.33 202	94.91 298	78.06 317	99.10 165	81.61 374	94.06 260	96.98 263

PatchT		88.87 351	87.42 355	93.22 310	94.08 369	85.10 349	89.51 438	94.64 383	81.92 410	92.36 222	88.15 436	80.05 279	97.01 386	72.43 431	93.65 267	97.54 243

baseline1		92.82 216	91.90 226	95.55 179	97.20 168	90.77 175	97.19 187	94.58 384	92.20 162	92.36 222	96.34 226	84.16 193	98.21 271	89.20 264	83.90 393	97.68 234

AstraMVS		94.82 132	94.64 123	95.34 192	96.36 247	88.09 274	97.58 133	94.56 385	94.98 44	95.70 136	97.92 106	81.93 246	98.93 190	96.87 56	95.88 209	98.99 104

UBG		91.55 267	90.76 271	93.94 274	96.52 232	85.06 350	95.22 340	94.54 386	90.47 239	91.98 235	92.71 387	72.02 365	98.74 217	88.10 281	95.26 229	98.01 212

Gipuma		67.86 420	65.41 422	75.18 435	92.66 409	73.45 439	66.50 456	94.52 387	53.33 455	57.80 456	66.07 456	30.81 456	89.20 448	48.15 454	78.88 419	62.90 456
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 259	90.75 273	94.47 241	96.53 230	86.56 314	95.76 309	94.51 388	91.10 211	91.24 260	93.59 370	68.59 396	98.86 197	91.10 214	94.29 248	98.00 213

CostFormer		91.18 292	90.70 277	92.62 333	94.84 341	81.76 392	94.09 379	94.43 389	84.15 389	92.72 217	93.77 361	79.43 290	98.20 272	90.70 225	92.18 287	97.90 218

tpm2		89.96 331	89.21 334	92.23 345	94.91 338	81.25 395	93.78 390	94.42 390	80.62 421	91.56 246	93.44 376	76.44 332	97.94 317	85.60 332	92.08 291	97.49 244

testing3-2		92.10 244	92.05 218	92.27 342	97.71 139	79.56 417	97.42 159	94.41 391	93.53 109	93.22 207	95.49 274	69.16 391	99.11 163	93.25 166	94.22 250	98.13 198

MVS_0304		96.74 59	96.31 76	98.02 19	96.87 193	94.65 30	97.58 133	94.39 392	96.47 10	97.16 68	98.39 62	87.53 131	99.87 7	98.97 18	99.41 55	99.55 39

JIA-IIPM		88.26 358	87.04 362	91.91 352	93.52 386	81.42 394	89.38 439	94.38 393	80.84 418	90.93 264	80.74 448	79.22 293	97.92 320	82.76 367	91.62 295	96.38 281

dmvs_re		90.21 325	89.50 327	92.35 337	95.47 299	85.15 347	95.70 312	94.37 394	90.94 217	88.42 332	93.57 371	74.63 349	95.67 414	82.80 366	89.57 324	96.22 283

Patchmatch-test		89.42 344	87.99 351	93.70 288	95.27 314	85.11 348	88.98 440	94.37 394	81.11 415	87.10 366	93.69 364	82.28 236	97.50 362	74.37 422	94.76 239	98.48 166

LCM-MVSNet		72.55 413	69.39 417	82.03 424	70.81 464	65.42 453	90.12 435	94.36 396	55.02 454	65.88 448	81.72 447	24.16 462	89.96 445	74.32 423	68.10 445	90.71 437

ADS-MVSNet2		89.45 343	88.59 345	92.03 349	95.86 276	82.26 388	90.93 428	94.32 397	83.23 402	91.28 258	91.81 408	79.01 301	95.99 406	79.52 394	91.39 300	97.84 225

mvs5depth		86.53 373	85.08 380	90.87 379	88.74 439	82.52 383	91.91 421	94.23 398	86.35 356	87.11 365	93.70 363	66.52 410	97.76 338	81.37 381	75.80 428	92.31 421

EU-MVSNet		88.72 353	88.90 341	88.20 409	93.15 399	74.21 437	96.63 246	94.22 399	85.18 375	87.32 360	95.97 244	76.16 334	94.98 423	85.27 337	86.17 357	95.41 324

tt0320-xc		84.83 393	82.33 401	92.31 340	93.66 382	86.20 324	96.17 285	94.06 400	71.26 443	82.04 416	92.22 402	55.07 441	96.72 397	81.49 376	75.04 431	94.02 394

MIMVSNet		88.50 355	86.76 365	93.72 287	94.84 341	87.77 284	91.39 423	94.05 401	86.41 355	87.99 347	92.59 391	63.27 423	95.82 411	77.44 405	92.84 275	97.57 242

OpenMVS_ROB	81.14 20	84.42 396	82.28 402	90.83 380	90.06 428	84.05 366	95.73 311	94.04 402	73.89 440	80.17 426	91.53 412	59.15 431	97.64 348	66.92 443	89.05 328	90.80 436

TinyColmap		86.82 371	85.35 378	91.21 372	94.91 338	82.99 378	93.94 383	94.02 403	83.58 398	81.56 417	94.68 310	62.34 428	98.13 278	75.78 414	87.35 349	92.52 417

ETVMVS		90.52 316	89.14 337	94.67 230	96.81 203	87.85 282	95.91 300	93.97 404	89.71 259	92.34 225	92.48 393	65.41 419	97.96 311	81.37 381	94.27 249	98.21 191

IB-MVS	87.33 17	89.91 332	88.28 349	94.79 224	95.26 317	87.70 285	95.12 345	93.95 405	89.35 271	87.03 367	92.49 392	70.74 376	99.19 148	89.18 265	81.37 407	97.49 244
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		87.13 368	87.02 363	87.47 413	95.16 321	73.21 441	95.00 347	93.93 406	88.55 302	86.96 369	91.99 404	75.90 335	94.00 432	61.59 447	94.11 253	95.20 342

myMVS_eth3d		87.18 367	86.38 368	89.58 400	95.16 321	79.53 418	95.00 347	93.93 406	88.55 302	86.96 369	91.99 404	56.23 438	94.00 432	75.47 418	94.11 253	95.20 342

testing222		90.31 320	88.96 339	94.35 247	96.54 228	87.29 290	95.50 324	93.84 408	90.97 214	91.75 243	92.96 384	62.18 429	98.00 302	82.86 363	94.08 256	97.76 230

test_f		80.57 406	79.62 408	83.41 423	83.38 452	67.80 450	93.57 400	93.72 409	80.80 420	77.91 433	87.63 439	33.40 455	92.08 443	87.14 309	79.04 418	90.34 438

LCM-MVSNet-Re		92.50 222	92.52 206	92.44 334	96.82 201	81.89 391	96.92 211	93.71 410	92.41 155	84.30 396	94.60 315	85.08 174	97.03 384	91.51 205	97.36 167	98.40 175

tpm		90.25 323	89.74 321	91.76 362	93.92 372	79.73 416	93.98 380	93.54 411	88.28 309	91.99 234	93.25 381	77.51 323	97.44 367	87.30 304	87.94 339	98.12 200

ET-MVSNet_ETH3D		91.49 272	90.11 301	95.63 173	96.40 242	91.57 137	95.34 331	93.48 412	90.60 234	75.58 436	95.49 274	80.08 278	96.79 395	94.25 145	89.76 322	98.52 159

LFMVS		93.60 178	92.63 199	96.52 102	98.13 109	91.27 149	97.94 76	93.39 413	90.57 236	96.29 110	98.31 75	69.00 392	99.16 155	94.18 146	95.87 210	99.12 88

MVStest1		82.38 403	80.04 407	89.37 402	87.63 444	82.83 379	95.03 346	93.37 414	73.90 439	73.50 441	94.35 330	62.89 426	93.25 440	73.80 425	65.92 448	92.04 426

Patchmatch-RL test		87.38 365	86.24 369	90.81 382	88.74 439	78.40 427	88.12 447	93.17 415	87.11 344	82.17 415	89.29 428	81.95 244	95.60 416	88.64 276	77.02 423	98.41 174

ttmdpeth		85.91 385	84.76 385	89.36 403	89.14 434	80.25 411	95.66 316	93.16 416	83.77 395	83.39 407	95.26 284	66.24 414	95.26 422	80.65 387	75.57 429	92.57 414

test-LLR		91.42 275	91.19 254	92.12 347	94.59 352	80.66 401	94.29 373	92.98 417	91.11 209	90.76 267	92.37 395	79.02 299	98.07 292	88.81 271	96.74 188	97.63 235

test-mter		90.19 327	89.54 326	92.12 347	94.59 352	80.66 401	94.29 373	92.98 417	87.68 331	90.76 267	92.37 395	67.67 401	98.07 292	88.81 271	96.74 188	97.63 235

WB-MVSnew		89.88 335	89.56 325	90.82 381	94.57 355	83.06 377	95.65 317	92.85 419	87.86 322	90.83 266	94.10 347	79.66 287	96.88 391	76.34 412	94.19 251	92.54 416

testing3		87.67 363	86.88 364	90.05 394	96.14 265	80.71 400	97.10 194	92.85 419	90.15 247	87.54 354	94.55 317	55.70 439	94.10 431	73.77 426	94.10 255	95.35 331

test_method		66.11 421	64.89 423	69.79 438	72.62 462	35.23 470	65.19 457	92.83 421	20.35 460	65.20 449	88.08 437	43.14 451	82.70 455	73.12 429	63.46 450	91.45 433

test0.0.03 1		89.37 345	88.70 343	91.41 369	92.47 413	85.63 337	95.22 340	92.70 422	91.11 209	86.91 373	93.65 368	79.02 299	93.19 441	78.00 404	89.18 327	95.41 324

new_pmnet		82.89 401	81.12 406	88.18 410	89.63 431	80.18 412	91.77 422	92.57 423	76.79 435	75.56 437	88.23 435	61.22 430	94.48 427	71.43 434	82.92 401	89.87 439

mvsany_test1		93.93 167	93.98 146	93.78 284	94.94 335	86.80 305	94.62 355	92.55 424	88.77 296	96.85 78	98.49 52	88.98 97	98.08 288	95.03 121	95.62 218	96.46 280

thisisatest0515		92.29 235	91.30 248	95.25 195	96.60 219	88.90 248	94.36 368	92.32 425	87.92 319	93.43 200	94.57 316	77.28 324	99.00 184	89.42 255	95.86 211	97.86 224

thisisatest0530		93.03 203	92.21 215	95.49 184	97.07 175	89.11 243	97.49 154	92.19 426	90.16 246	94.09 178	96.41 222	76.43 333	99.05 180	90.38 233	95.68 216	98.31 185

tttt0517		92.96 206	92.33 212	94.87 217	97.11 173	87.16 298	97.97 72	92.09 427	90.63 230	93.88 184	97.01 186	76.50 330	99.06 177	90.29 236	95.45 225	98.38 177

K. test v3		87.64 364	86.75 366	90.32 391	93.02 401	79.48 421	96.61 247	92.08 428	90.66 228	80.25 425	94.09 349	67.21 405	96.65 398	85.96 328	80.83 409	94.83 363

TESTMET0.1,1		90.06 329	89.42 329	91.97 350	94.41 360	80.62 403	94.29 373	91.97 429	87.28 341	90.44 271	92.47 394	68.79 393	97.67 345	88.50 278	96.60 193	97.61 239

PM-MVS		83.48 398	81.86 404	88.31 408	87.83 443	77.59 429	93.43 401	91.75 430	86.91 346	80.63 421	89.91 424	44.42 450	95.84 410	85.17 340	76.73 426	91.50 431

baseline2		91.63 260	90.86 265	93.94 274	94.33 362	86.32 319	95.92 299	91.64 431	89.37 270	86.94 371	94.69 309	81.62 251	98.69 224	88.64 276	94.57 244	96.81 270

APD_test1		79.31 408	77.70 411	84.14 421	89.11 436	69.07 447	92.36 420	91.50 432	69.07 446	73.87 439	92.63 390	39.93 452	94.32 429	70.54 439	80.25 411	89.02 441

FPMVS		71.27 414	69.85 416	75.50 434	74.64 459	59.03 459	91.30 424	91.50 432	58.80 451	57.92 455	88.28 434	29.98 458	85.53 454	53.43 452	82.84 402	81.95 447

door								91.13 434

door-mid								91.06 435

EGC-MVSNET		68.77 419	63.01 425	86.07 420	92.49 412	82.24 389	93.96 382	90.96 436	0.71 465	2.62 466	90.89 415	53.66 442	93.46 436	57.25 450	84.55 383	82.51 446

mvsany_test3		83.59 397	82.44 400	87.03 416	83.80 449	73.82 438	93.70 393	90.92 437	86.42 354	82.51 413	90.26 420	46.76 449	95.71 412	90.82 220	76.76 425	91.57 429

pmmvs3		79.97 407	77.50 412	87.39 414	82.80 453	79.38 422	92.70 415	90.75 438	70.69 445	78.66 430	87.47 441	51.34 445	93.40 437	73.39 428	69.65 441	89.38 440

UWE-MVS		89.91 332	89.48 328	91.21 372	95.88 275	78.23 428	94.91 350	90.26 439	89.11 277	92.35 224	94.52 319	68.76 394	97.96 311	83.95 355	95.59 219	97.42 248

DSMNet-mixed		86.34 378	86.12 372	87.00 417	89.88 430	70.43 443	94.93 349	90.08 440	77.97 432	85.42 388	92.78 386	74.44 351	93.96 434	74.43 421	95.14 230	96.62 274

MVS-HIRNet		82.47 402	81.21 405	86.26 419	95.38 302	69.21 446	88.96 441	89.49 441	66.28 448	80.79 420	74.08 453	68.48 398	97.39 371	71.93 433	95.47 224	92.18 424

WB-MVS		76.77 410	76.63 413	77.18 429	85.32 447	56.82 461	94.53 359	89.39 442	82.66 406	71.35 442	89.18 429	75.03 344	88.88 449	35.42 458	66.79 446	85.84 443

test1111		93.19 195	92.82 189	94.30 253	97.58 155	84.56 358	98.21 43	89.02 443	93.53 109	94.58 164	98.21 82	72.69 361	99.05 180	93.06 172	98.48 125	99.28 73

SSC-MVS		76.05 411	75.83 414	76.72 433	84.77 448	56.22 462	94.32 371	88.96 444	81.82 412	70.52 443	88.91 430	74.79 348	88.71 450	33.69 459	64.71 449	85.23 444

ECVR-MVS		93.19 195	92.73 195	94.57 236	97.66 143	85.41 341	98.21 43	88.23 445	93.43 114	94.70 162	98.21 82	72.57 362	99.07 175	93.05 173	98.49 123	99.25 76

EPMVS		90.70 310	89.81 316	93.37 304	94.73 347	84.21 362	93.67 396	88.02 446	89.50 265	92.38 221	93.49 373	77.82 321	97.78 335	86.03 326	92.68 279	98.11 205

ANet_high		63.94 423	59.58 426	77.02 430	61.24 466	66.06 451	85.66 450	87.93 447	78.53 430	42.94 458	71.04 455	25.42 461	80.71 457	52.60 453	30.83 459	84.28 445

PMMVS2		70.19 415	66.92 419	80.01 425	76.35 458	65.67 452	86.22 448	87.58 448	64.83 450	62.38 451	80.29 450	26.78 460	88.49 452	63.79 444	54.07 455	85.88 442

lessismore_v0				90.45 388	91.96 419	79.09 425		87.19 449		80.32 424	94.39 327	66.31 413	97.55 356	84.00 354	76.84 424	94.70 375

PMVS	53.92 22	58.58 424	55.40 427	68.12 439	51.00 467	48.64 464	78.86 453	87.10 450	46.77 456	35.84 462	74.28 452	8.76 466	86.34 453	42.07 456	73.91 434	69.38 453
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 372	86.41 367	88.02 411	92.87 403	74.60 436	95.38 330	86.70 451	88.17 312	87.28 362	94.67 312	70.83 375	93.30 439	67.45 441	94.31 247	96.17 286

test_vis1_rt		86.16 381	85.06 381	89.46 401	93.47 390	80.46 405	96.41 259	86.61 452	85.22 374	79.15 429	88.64 431	52.41 444	97.06 382	93.08 171	90.57 313	90.87 435

testf1		69.31 417	66.76 420	76.94 431	78.61 456	61.93 455	88.27 445	86.11 453	55.62 452	59.69 452	85.31 444	20.19 464	89.32 446	57.62 448	69.44 443	79.58 448

APD_test2		69.31 417	66.76 420	76.94 431	78.61 456	61.93 455	88.27 445	86.11 453	55.62 452	59.69 452	85.31 444	20.19 464	89.32 446	57.62 448	69.44 443	79.58 448

gg-mvs-nofinetune		87.82 361	85.61 374	94.44 243	94.46 357	89.27 237	91.21 427	84.61 455	80.88 417	89.89 291	74.98 451	71.50 369	97.53 359	85.75 331	97.21 176	96.51 276

dmvs_testset		81.38 405	82.60 399	77.73 428	91.74 420	51.49 463	93.03 410	84.21 456	89.07 278	78.28 432	91.25 414	76.97 326	88.53 451	56.57 451	82.24 404	93.16 405

GG-mvs-BLEND				93.62 292	93.69 380	89.20 239	92.39 419	83.33 457		87.98 348	89.84 425	71.00 373	96.87 392	82.08 373	95.40 226	94.80 368

MTMP							97.86 85	82.03 458

DeepMVS_CX				74.68 436	90.84 425	64.34 454		81.61 459	65.34 449	67.47 447	88.01 438	48.60 448	80.13 458	62.33 446	73.68 435	79.58 448

E-PMN		53.28 425	52.56 429	55.43 442	74.43 460	47.13 465	83.63 452	76.30 460	42.23 457	42.59 459	62.22 458	28.57 459	74.40 459	31.53 460	31.51 458	44.78 457

test2506		91.60 262	90.78 270	94.04 264	97.66 143	83.81 367	98.27 33	75.53 461	93.43 114	95.23 148	98.21 82	67.21 405	99.07 175	93.01 176	98.49 123	99.25 76

EMVS		52.08 427	51.31 430	54.39 443	72.62 462	45.39 467	83.84 451	75.51 462	41.13 458	40.77 460	59.65 459	30.08 457	73.60 460	28.31 462	29.90 460	44.18 458

test_vis3_rt		72.73 412	70.55 415	79.27 426	80.02 455	68.13 449	93.92 385	74.30 463	76.90 434	58.99 454	73.58 454	20.29 463	95.37 420	84.16 350	72.80 437	74.31 451

MVE	50.73 23	53.25 426	48.81 431	66.58 441	65.34 465	57.50 460	72.49 455	70.94 464	40.15 459	39.28 461	63.51 457	6.89 468	73.48 461	38.29 457	42.38 457	68.76 455
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 428	53.82 428	46.29 444	33.73 468	45.30 468	78.32 454	67.24 465	18.02 461	50.93 457	87.05 442	52.99 443	53.11 463	70.76 437	25.29 461	40.46 459

kuosan		65.27 422	64.66 424	67.11 440	83.80 449	61.32 458	88.53 444	60.77 466	68.22 447	67.67 445	80.52 449	49.12 447	70.76 462	29.67 461	53.64 456	69.26 454

dongtai		69.99 416	69.33 418	71.98 437	88.78 438	61.64 457	89.86 436	59.93 467	75.67 436	74.96 438	85.45 443	50.19 446	81.66 456	43.86 455	55.27 454	72.63 452

N_pmnet		78.73 409	78.71 410	78.79 427	92.80 406	46.50 466	94.14 377	43.71 468	78.61 429	80.83 419	91.66 411	74.94 347	96.36 402	67.24 442	84.45 385	93.50 401

wuyk23d		25.11 429	24.57 433	26.74 445	73.98 461	39.89 469	57.88 458	9.80 469	12.27 462	10.39 463	6.97 465	7.03 467	36.44 464	25.43 463	17.39 462	3.89 462

testmvs		13.36 431	16.33 434	4.48 447	5.04 469	2.26 472	93.18 404	3.28 470	2.70 463	8.24 464	21.66 461	2.29 470	2.19 465	7.58 464	2.96 463	9.00 461

test123		13.04 432	15.66 435	5.18 446	4.51 470	3.45 471	92.50 418	1.81 471	2.50 464	7.58 465	20.15 462	3.67 469	2.18 466	7.13 465	1.07 464	9.90 460

mmdepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

monomultidepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

test_blank		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet_test		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

DCPMVS		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

pcd_1.5k_mvsjas		7.39 434	9.85 437	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	88.65 105	0.00 467	0.00 466	0.00 465	0.00 463

sosnet-low-res		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

sosnet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uncertanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

Regformer		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

n2								0.00 472

nn								0.00 472

ab-mvs-re		8.06 433	10.74 436	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	96.69 203	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

WAC-MVS						79.53 418								75.56 417

PC_three_1452									90.77 220	98.89 24	98.28 80	96.24 1	98.35 261	95.76 100	99.58 23	99.59 28

eth-test2					0.00 471

eth-test					0.00 471

OPU-MVS				98.55 3	98.82 57	96.86 3	98.25 36				98.26 81	96.04 2	99.24 143	95.36 114	99.59 19	99.56 36

test_0728_THIRD									94.78 59	98.73 28	98.87 29	95.87 4	99.84 23	97.45 44	99.72 2	99.77 2

GSMVS																98.45 169

test_part2					99.28 27	95.74 8				98.10 42

sam_mvs1												82.76 224				98.45 169

sam_mvs												81.94 245

test_post1							92.81 414				16.58 464	80.53 269	97.68 344	86.20 320

test_post											17.58 463	81.76 248	98.08 288

patchmatchnet-post											90.45 419	82.65 229	98.10 283

gm-plane-assit					93.22 397	78.89 426			84.82 382		93.52 372		98.64 232	87.72 288

test9_res														94.81 131	99.38 60	99.45 55

agg_prior2														93.94 151	99.38 60	99.50 48

test_prior4						93.66 58	96.42 258

test_prior2							96.35 267		92.80 147	96.03 120	97.59 144	92.01 47		95.01 122	99.38 60

旧先验2							95.94 297		81.66 413	97.34 64			98.82 203	92.26 182

新几何2							95.79 307

原ACMM2							95.67 313

testdata2													99.67 71	85.96 328

segment_acmp												92.89 30

testdata1							95.26 339		93.10 131

plane_prior7					96.21 252	89.98 204

plane_prior6					96.10 268	90.00 200						81.32 255

plane_prior4											96.64 206

plane_prior3						90.00 200			94.46 76	91.34 252

plane_prior2							97.74 106		94.85 51

plane_prior1					96.14 265

plane_prior						89.99 202	97.24 179		94.06 88						92.16 288

HQP5-MVS						89.33 232

HQP-NCC					95.86 276		96.65 241		93.55 105	90.14 276

ACMP_Plane					95.86 276		96.65 241		93.55 105	90.14 276

BP-MVS														92.13 190

HQP4-MVS										90.14 276			98.50 246			95.78 305

HQP2-MVS												80.95 259

NP-MVS					95.99 274	89.81 211					95.87 249

MDTV_nov1_ep13_2view						70.35 444	93.10 409		83.88 393	93.55 193		82.47 233		86.25 319		98.38 177

ACMMP++_ref															90.30 318

ACMMP++															91.02 307

Test By Simon												88.73 104

High-resolution multi-view benchmark