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 13	97.89 3	96.53 99	98.41 80	91.73 125	98.01 61	99.02 1	96.37 10	99.30 4	98.92 20	92.39 41	99.79 40	99.16 11	99.46 41	98.08 198

PGM-MVS		96.81 52	96.53 63	97.65 43	99.35 22	93.53 61	97.65 122	98.98 2	92.22 157	97.14 69	98.44 57	91.17 68	99.85 18	94.35 141	99.46 41	99.57 31

MVS_111021_HR		96.68 63	96.58 62	96.99 80	98.46 75	92.31 106	96.20 278	98.90 3	94.30 83	95.86 126	97.74 123	92.33 42	99.38 129	96.04 88	99.42 51	99.28 72

test_fmvsmconf_n		97.49 17	97.56 12	97.29 60	97.44 158	92.37 103	97.91 80	98.88 4	95.83 16	98.92 20	99.05 12	91.45 58	99.80 35	99.12 13	99.46 41	99.69 13

lecture		97.58 12	97.63 9	97.43 54	99.37 16	92.93 82	98.86 7	98.85 5	95.27 31	98.65 30	98.90 22	91.97 49	99.80 35	97.63 35	99.21 76	99.57 31

ACMMP		96.27 80	95.93 83	97.28 62	99.24 30	92.62 94	98.25 36	98.81 6	92.99 132	94.56 161	98.39 61	88.96 97	99.85 18	94.57 139	97.63 156	99.36 67
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 81	96.19 79	96.39 117	98.23 98	91.35 146	96.24 276	98.79 7	93.99 90	95.80 128	97.65 131	89.92 87	99.24 142	95.87 92	99.20 81	98.58 149

patch_mono-2		96.83 51	97.44 20	95.01 201	99.05 41	85.39 334	96.98 205	98.77 8	94.70 63	97.99 44	98.66 40	93.61 19	99.91 1	97.67 34	99.50 35	99.72 12

fmvsm_s_conf0.5_n		96.85 48	97.13 25	96.04 141	98.07 113	90.28 191	97.97 72	98.76 9	94.93 45	98.84 25	99.06 11	88.80 101	99.65 72	99.06 15	98.63 116	98.18 184

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 57	98.21 99	92.75 88	97.83 92	98.73 10	95.04 42	99.30 4	98.84 33	93.34 22	99.78 43	99.32 5	99.13 91	99.50 47

fmvsm_s_conf0.5_n_a		96.75 56	96.93 40	96.20 133	97.64 144	90.72 176	98.00 62	98.73 10	94.55 70	98.91 21	99.08 7	88.22 113	99.63 81	98.91 18	98.37 129	98.25 179

FC-MVSNet-test		93.94 160	93.57 151	95.04 199	95.48 286	91.45 143	98.12 51	98.71 12	93.37 115	90.23 266	96.70 192	87.66 123	97.85 319	91.49 201	90.39 308	95.83 292

UniMVSNet (Re)		93.31 181	92.55 194	95.61 171	95.39 292	93.34 67	97.39 164	98.71 12	93.14 128	90.10 275	94.83 294	87.71 122	98.03 292	91.67 199	83.99 380	95.46 311

fmvsm_l_conf0.5_n_a		97.63 9	97.76 5	97.26 64	98.25 93	92.59 96	97.81 97	98.68 14	94.93 45	99.24 7	98.87 28	93.52 20	99.79 40	99.32 5	99.21 76	99.40 61

FIs		94.09 151	93.70 147	95.27 189	95.70 275	92.03 118	98.10 52	98.68 14	93.36 117	90.39 263	96.70 192	87.63 126	97.94 310	92.25 180	90.50 307	95.84 291

WR-MVS_H		92.00 238	91.35 235	93.95 264	95.09 319	89.47 219	98.04 59	98.68 14	91.46 184	88.34 326	94.68 301	85.86 156	97.56 348	85.77 321	84.24 378	94.82 356

fmvsm_s_conf0.5_n_4		96.75 56	97.07 28	95.79 158	97.76 135	89.57 213	97.66 121	98.66 17	95.36 27	99.03 13	98.90 22	88.39 109	99.73 54	99.17 10	98.66 114	98.08 198

VPA-MVSNet		93.24 183	92.48 199	95.51 177	95.70 275	92.39 102	97.86 85	98.66 17	92.30 155	92.09 224	95.37 269	80.49 261	98.40 246	93.95 147	85.86 351	95.75 300

fmvsm_l_conf0.5_n_3		97.64 8	97.60 10	97.79 30	98.14 106	93.94 52	97.93 78	98.65 19	96.70 5	99.38 2	99.07 10	89.92 87	99.81 30	99.16 11	99.43 48	99.61 25

fmvsm_s_conf0.5_n_3		97.15 30	97.36 22	96.52 101	97.98 119	91.19 154	97.84 89	98.65 19	97.08 4	99.25 6	99.10 5	87.88 120	99.79 40	99.32 5	99.18 83	98.59 148

fmvsm_s_conf0.5_n_8		97.32 24	97.48 19	96.85 82	98.28 89	91.07 162	97.76 102	98.62 21	97.53 2	99.20 9	99.12 4	88.24 112	99.81 30	99.41 3	99.17 84	99.67 14

fmvsm_s_conf0.5_n_2		96.62 64	96.82 49	96.02 143	97.98 119	90.43 186	97.50 145	98.59 22	96.59 7	99.31 3	99.08 7	84.47 177	99.75 51	99.37 4	98.45 126	97.88 211

UniMVSNet_NR-MVSNet		93.37 179	92.67 188	95.47 182	95.34 298	92.83 85	97.17 188	98.58 23	92.98 137	90.13 271	95.80 245	88.37 111	97.85 319	91.71 196	83.93 381	95.73 302

CSCG		96.05 84	95.91 84	96.46 111	99.24 30	90.47 183	98.30 29	98.57 24	89.01 273	93.97 178	97.57 140	92.62 37	99.76 47	94.66 133	99.27 69	99.15 82

fmvsm_s_conf0.5_n_9		97.33 23	97.57 11	96.62 95	98.43 78	90.32 190	97.80 98	98.53 25	97.24 3	99.62 1	99.14 1	88.65 104	99.80 35	99.54 1	99.15 88	99.74 8

fmvsm_s_conf0.5_n_6		97.08 33	97.17 24	96.81 83	97.28 163	91.73 125	97.75 104	98.50 26	94.86 49	99.22 8	98.78 37	89.75 90	99.76 47	99.10 14	99.29 67	98.94 110

MSLP-MVS++		96.94 42	97.06 29	96.59 96	98.72 60	91.86 123	97.67 118	98.49 27	94.66 66	97.24 65	98.41 60	92.31 44	98.94 188	96.61 64	99.46 41	98.96 106

HyFIR lowres test		93.66 170	92.92 176	95.87 152	98.24 94	89.88 204	94.58 351	98.49 27	85.06 369	93.78 181	95.78 249	82.86 212	98.67 224	91.77 194	95.71 208	99.07 93

CHOSEN 1792x2688		94.15 146	93.51 157	96.06 139	98.27 90	89.38 224	95.18 337	98.48 29	85.60 359	93.76 182	97.11 169	83.15 202	99.61 83	91.33 204	98.72 112	99.19 78

fmvsm_s_conf0.5_n_7		96.45 71	96.80 51	95.37 185	97.29 162	88.38 256	97.23 182	98.47 30	95.14 36	98.43 35	99.09 6	87.58 127	99.72 58	98.80 22	99.21 76	98.02 202

fmvsm_s_conf0.5_n_5		97.00 39	96.97 37	97.09 75	97.58 154	92.56 97	97.68 117	98.47 30	94.02 88	98.90 22	98.89 25	88.94 98	99.78 43	99.18 9	99.03 100	98.93 114

PHI-MVS		96.77 54	96.46 70	97.71 41	98.40 81	94.07 48	98.21 43	98.45 32	89.86 245	97.11 71	98.01 97	92.52 39	99.69 66	96.03 89	99.53 29	99.36 67

fmvsm_s_conf0.1_n		96.58 67	96.77 54	96.01 146	96.67 210	90.25 192	97.91 80	98.38 33	94.48 74	98.84 25	99.14 1	88.06 115	99.62 82	98.82 20	98.60 118	98.15 188

PVSNet_BlendedMVS		94.06 152	93.92 142	94.47 233	98.27 90	89.46 221	96.73 228	98.36 34	90.17 237	94.36 166	95.24 277	88.02 116	99.58 91	93.44 158	90.72 303	94.36 376

PVSNet_Blended		94.87 126	94.56 124	95.81 157	98.27 90	89.46 221	95.47 320	98.36 34	88.84 281	94.36 166	96.09 234	88.02 116	99.58 91	93.44 158	98.18 138	98.40 169

3Dnovator	91.36 5	95.19 114	94.44 132	97.44 53	96.56 220	93.36 66	98.65 12	98.36 34	94.12 85	89.25 305	98.06 91	82.20 229	99.77 46	93.41 160	99.32 65	99.18 79

FOURS1					99.55 1	93.34 67	99.29 1	98.35 37	94.98 43	98.49 33

DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 34	95.78 7	97.21 185	98.35 37	95.16 35	98.71 29	98.80 35	95.05 10	99.89 3	96.70 62	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 73	96.47 67	96.16 135	95.48 286	90.69 177	97.91 80	98.33 39	94.07 86	98.93 17	99.14 1	87.44 134	99.61 83	98.63 23	98.32 131	98.18 184

HFP-MVS		97.14 31	96.92 41	97.83 26	99.42 7	94.12 46	98.52 16	98.32 40	93.21 120	97.18 66	98.29 77	92.08 46	99.83 26	95.63 105	99.59 19	99.54 40

ACMMPR		97.07 35	96.84 45	97.79 30	99.44 6	93.88 53	98.52 16	98.31 41	93.21 120	97.15 68	98.33 71	91.35 62	99.86 9	95.63 105	99.59 19	99.62 22

test_fmvsmvis_n_1920		96.70 59	96.84 45	96.31 122	96.62 212	91.73 125	97.98 66	98.30 42	96.19 11	96.10 116	98.95 18	89.42 91	99.76 47	98.90 19	99.08 95	97.43 238

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 35	94.82 28	98.81 8	98.30 42	94.76 61	98.30 37	98.90 22	93.77 17	99.68 68	97.93 26	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 44	94.92 47	98.99 15	98.92 20	95.08 8

MSP-MVS		97.59 11	97.54 13	97.73 38	99.40 11	93.77 57	98.53 15	98.29 44	95.55 24	98.56 32	97.81 118	93.90 15	99.65 72	96.62 63	99.21 76	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 46	94.78 58	98.93 17	98.87 28	96.04 2	99.86 9	97.45 43	99.58 23	99.59 27

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 46					99.86 9	97.52 39	99.67 6	99.75 6

CP-MVS		97.02 37	96.81 50	97.64 45	99.33 23	93.54 60	98.80 9	98.28 46	92.99 132	96.45 103	98.30 76	91.90 50	99.85 18	95.61 107	99.68 4	99.54 40

test_fmvsmconf0.1_n		97.09 32	97.06 29	97.19 69	95.67 277	92.21 110	97.95 75	98.27 49	95.78 20	98.40 36	99.00 14	89.99 85	99.78 43	99.06 15	99.41 54	99.59 27

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 49	95.13 37	99.19 10	98.89 25	95.54 5	99.85 18	97.52 39	99.66 10	99.56 35

test_241102_TWO								98.27 49	95.13 37	98.93 17	98.89 25	94.99 11	99.85 18	97.52 39	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 49	95.09 40	99.19 10	98.81 34	95.54 5	99.65 72

SF-MVS		97.39 20	97.13 25	98.17 15	99.02 44	95.28 19	98.23 40	98.27 49	92.37 154	98.27 38	98.65 42	93.33 23	99.72 58	96.49 68	99.52 30	99.51 44

SteuartSystems-ACMMP		97.62 10	97.53 14	97.87 24	98.39 83	94.25 40	98.43 23	98.27 49	95.34 29	98.11 40	98.56 44	94.53 12	99.71 60	96.57 66	99.62 17	99.65 19
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 24	95.20 20		98.25 55	95.13 37	98.48 34	98.87 28	95.16 7

PVSNet_Blended_VisFu		95.27 108	94.91 113	96.38 118	98.20 100	90.86 170	97.27 176	98.25 55	90.21 236	94.18 171	97.27 158	87.48 133	99.73 54	93.53 155	97.77 154	98.55 150

region2R		97.07 35	96.84 45	97.77 34	99.46 2	93.79 55	98.52 16	98.24 57	93.19 123	97.14 69	98.34 68	91.59 57	99.87 7	95.46 111	99.59 19	99.64 20

PS-CasMVS		91.55 258	90.84 259	93.69 280	94.96 323	88.28 259	97.84 89	98.24 57	91.46 184	88.04 337	95.80 245	79.67 277	97.48 356	87.02 301	84.54 375	95.31 325

DU-MVS		92.90 201	92.04 210	95.49 179	94.95 324	92.83 85	97.16 189	98.24 57	93.02 131	90.13 271	95.71 252	83.47 194	97.85 319	91.71 196	83.93 381	95.78 296

9.14			96.75 55		98.93 52		97.73 108	98.23 60	91.28 193	97.88 48	98.44 57	93.00 26	99.65 72	95.76 98	99.47 40

reproduce_model		97.51 16	97.51 16	97.50 50	98.99 48	93.01 78	97.79 100	98.21 61	95.73 21	97.99 44	99.03 13	92.63 36	99.82 28	97.80 28	99.42 51	99.67 14

D2MVS		91.30 275	90.95 253	92.35 328	94.71 339	85.52 330	96.18 280	98.21 61	88.89 279	86.60 366	93.82 350	79.92 273	97.95 308	89.29 250	90.95 300	93.56 391

reproduce-ours		97.53 14	97.51 16	97.60 47	98.97 49	93.31 69	97.71 113	98.20 63	95.80 18	97.88 48	98.98 16	92.91 27	99.81 30	97.68 30	99.43 48	99.67 14

our_new_method		97.53 14	97.51 16	97.60 47	98.97 49	93.31 69	97.71 113	98.20 63	95.80 18	97.88 48	98.98 16	92.91 27	99.81 30	97.68 30	99.43 48	99.67 14

SDMVSNet		94.17 144	93.61 150	95.86 154	98.09 109	91.37 145	97.35 168	98.20 63	93.18 125	91.79 232	97.28 156	79.13 285	98.93 189	94.61 136	92.84 266	97.28 246

XVS		97.18 28	96.96 39	97.81 28	99.38 14	94.03 50	98.59 13	98.20 63	94.85 50	96.59 92	98.29 77	91.70 53	99.80 35	95.66 100	99.40 56	99.62 22

X-MVStestdata		91.71 247	89.67 313	97.81 28	99.38 14	94.03 50	98.59 13	98.20 63	94.85 50	96.59 92	32.69 451	91.70 53	99.80 35	95.66 100	99.40 56	99.62 22

ACMMP_NAP		97.20 27	96.86 43	98.23 11	99.09 36	95.16 22	97.60 131	98.19 68	92.82 144	97.93 47	98.74 39	91.60 56	99.86 9	96.26 72	99.52 30	99.67 14

CP-MVSNet		91.89 243	91.24 242	93.82 272	95.05 320	88.57 249	97.82 94	98.19 68	91.70 175	88.21 332	95.76 250	81.96 234	97.52 354	87.86 276	84.65 369	95.37 321

ZNCC-MVS		96.96 40	96.67 58	97.85 25	99.37 16	94.12 46	98.49 20	98.18 70	92.64 150	96.39 105	98.18 84	91.61 55	99.88 4	95.59 110	99.55 26	99.57 31

SMA-MVS		97.35 21	97.03 34	98.30 8	99.06 40	95.42 10	97.94 76	98.18 70	90.57 228	98.85 24	98.94 19	93.33 23	99.83 26	96.72 60	99.68 4	99.63 21
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		91.20 280	90.44 276	93.48 291	94.49 347	87.91 274	97.76 102	98.18 70	91.29 190	87.78 341	95.74 251	80.35 264	97.33 367	85.46 325	82.96 391	95.19 336

DELS-MVS		96.61 65	96.38 74	97.30 59	97.79 133	93.19 74	95.96 291	98.18 70	95.23 32	95.87 125	97.65 131	91.45 58	99.70 65	95.87 92	99.44 47	99.00 101
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		89.70 332	88.40 338	93.60 284	95.15 315	90.10 194	97.56 136	98.16 74	87.28 332	86.16 372	94.63 305	77.57 313	98.05 288	74.48 411	84.59 373	92.65 404

VNet		95.89 92	95.45 95	97.21 67	98.07 113	92.94 81	97.50 145	98.15 75	93.87 94	97.52 55	97.61 137	85.29 165	99.53 105	95.81 97	95.27 219	99.16 80

DeepPCF-MVS	93.97 1	96.61 65	97.09 27	95.15 193	98.09 109	86.63 305	96.00 289	98.15 75	95.43 25	97.95 46	98.56 44	93.40 21	99.36 130	96.77 57	99.48 39	99.45 54

SD-MVS		97.41 19	97.53 14	97.06 78	98.57 74	94.46 34	97.92 79	98.14 77	94.82 54	99.01 14	98.55 46	94.18 14	97.41 363	96.94 52	99.64 14	99.32 69
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 48	96.52 64	97.82 27	99.36 20	94.14 45	98.29 30	98.13 78	92.72 147	96.70 84	98.06 91	91.35 62	99.86 9	94.83 127	99.28 68	99.47 53

UA-Net		95.95 89	95.53 91	97.20 68	97.67 140	92.98 80	97.65 122	98.13 78	94.81 56	96.61 90	98.35 65	88.87 99	99.51 110	90.36 225	97.35 166	99.11 88

QAPM		93.45 177	92.27 204	96.98 81	96.77 205	92.62 94	98.39 25	98.12 80	84.50 377	88.27 330	97.77 121	82.39 226	99.81 30	85.40 326	98.81 108	98.51 155

Vis-MVSNet		95.23 111	94.81 114	96.51 105	97.18 168	91.58 136	98.26 35	98.12 80	94.38 81	94.90 151	98.15 86	82.28 227	98.92 191	91.45 203	98.58 120	99.01 98
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 204	91.68 225	96.40 115	95.34 298	92.73 90	98.27 33	98.12 80	84.86 372	85.78 374	97.75 122	78.89 295	99.74 52	87.50 291	98.65 115	96.73 263

TranMVSNet+NR-MVSNet		92.50 213	91.63 226	95.14 194	94.76 335	92.07 115	97.53 142	98.11 83	92.90 141	89.56 293	96.12 229	83.16 201	97.60 346	89.30 249	83.20 390	95.75 300

CPTT-MVS		95.57 102	95.19 105	96.70 86	99.27 28	91.48 140	98.33 27	98.11 83	87.79 317	95.17 147	98.03 94	87.09 140	99.61 83	93.51 156	99.42 51	99.02 95

APD-MVS		96.95 41	96.60 60	98.01 20	99.03 43	94.93 27	97.72 111	98.10 85	91.50 182	98.01 43	98.32 73	92.33 42	99.58 91	94.85 125	99.51 33	99.53 43
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 46	96.60 60	97.64 45	99.40 11	93.44 62	98.50 19	98.09 86	93.27 119	95.95 123	98.33 71	91.04 70	99.88 4	95.20 114	99.57 25	99.60 26

ZD-MVS					99.05 41	94.59 32		98.08 87	89.22 266	97.03 74	98.10 87	92.52 39	99.65 72	94.58 138	99.31 66

MTGPA								98.08 87

MTAPA		97.08 33	96.78 53	97.97 23	99.37 16	94.42 36	97.24 178	98.08 87	95.07 41	96.11 115	98.59 43	90.88 75	99.90 2	96.18 84	99.50 35	99.58 30

CNVR-MVS		97.68 6	97.44 20	98.37 7	98.90 55	95.86 6	97.27 176	98.08 87	95.81 17	97.87 51	98.31 74	94.26 13	99.68 68	97.02 51	99.49 38	99.57 31

DP-MVS Recon		95.68 97	95.12 109	97.37 56	99.19 33	94.19 42	97.03 196	98.08 87	88.35 299	95.09 149	97.65 131	89.97 86	99.48 117	92.08 188	98.59 119	98.44 166

SR-MVS		97.01 38	96.86 43	97.47 52	99.09 36	93.27 71	97.98 66	98.07 92	93.75 97	97.45 57	98.48 54	91.43 60	99.59 88	96.22 75	99.27 69	99.54 40

MCST-MVS		97.18 28	96.84 45	98.20 14	99.30 26	95.35 15	97.12 192	98.07 92	93.54 107	96.08 117	97.69 126	93.86 16	99.71 60	96.50 67	99.39 58	99.55 38

NR-MVSNet		92.34 222	91.27 241	95.53 176	94.95 324	93.05 77	97.39 164	98.07 92	92.65 149	84.46 385	95.71 252	85.00 170	97.77 330	89.71 237	83.52 387	95.78 296

MP-MVS-pluss		96.70 59	96.27 77	97.98 22	99.23 32	94.71 29	96.96 207	98.06 95	90.67 218	95.55 139	98.78 37	91.07 69	99.86 9	96.58 65	99.55 26	99.38 65
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 52	96.71 57	97.12 72	99.01 47	92.31 106	97.98 66	98.06 95	93.11 129	97.44 58	98.55 46	90.93 73	99.55 101	96.06 85	99.25 73	99.51 44

MP-MVS		96.77 54	96.45 71	97.72 39	99.39 13	93.80 54	98.41 24	98.06 95	93.37 115	95.54 141	98.34 68	90.59 79	99.88 4	94.83 127	99.54 28	99.49 49
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 68	96.27 77	97.22 66	99.32 24	92.74 89	98.74 10	98.06 95	90.57 228	96.77 81	98.35 65	90.21 82	99.53 105	94.80 130	99.63 16	99.38 65

HPM-MVS		96.69 61	96.45 71	97.40 55	99.36 20	93.11 76	98.87 6	98.06 95	91.17 199	96.40 104	97.99 98	90.99 71	99.58 91	95.61 107	99.61 18	99.49 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 136	93.80 144	96.64 88	97.07 174	91.97 120	96.32 268	98.06 95	88.94 277	94.50 163	96.78 187	84.60 174	99.27 140	91.90 189	96.02 198	98.68 142

DeepC-MVS	93.07 3	96.06 83	95.66 88	97.29 60	97.96 121	93.17 75	97.30 174	98.06 95	93.92 92	93.38 192	98.66 40	86.83 142	99.73 54	95.60 109	99.22 75	98.96 106
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 25	97.03 34	98.11 17	98.77 58	95.06 25	97.34 169	98.04 102	95.96 12	97.09 72	97.88 109	93.18 25	99.71 60	95.84 96	99.17 84	99.56 35

DeepC-MVS_fast	93.89 2	96.93 43	96.64 59	97.78 32	98.64 69	94.30 37	97.41 159	98.04 102	94.81 56	96.59 92	98.37 63	91.24 65	99.64 80	95.16 116	99.52 30	99.42 60
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 45	96.80 51	97.11 74	99.02 44	92.34 104	97.98 66	98.03 104	93.52 110	97.43 60	98.51 49	91.40 61	99.56 99	96.05 86	99.26 71	99.43 58

RE-MVS-def			96.72 56		99.02 44	92.34 104	97.98 66	98.03 104	93.52 110	97.43 60	98.51 49	90.71 77		96.05 86	99.26 71	99.43 58

RPMNet		88.98 338	87.05 352	94.77 219	94.45 349	87.19 290	90.23 426	98.03 104	77.87 424	92.40 210	87.55 431	80.17 268	99.51 110	68.84 431	93.95 252	97.60 231

save fliter					98.91 54	94.28 38	97.02 198	98.02 107	95.35 28

TEST9					98.70 61	94.19 42	96.41 256	98.02 107	88.17 303	96.03 118	97.56 142	92.74 33	99.59 88

train_agg		96.30 79	95.83 87	97.72 39	98.70 61	94.19 42	96.41 256	98.02 107	88.58 290	96.03 118	97.56 142	92.73 34	99.59 88	95.04 118	99.37 62	99.39 63

test_8					98.67 63	94.06 49	96.37 263	98.01 110	88.58 290	95.98 122	97.55 144	92.73 34	99.58 91

agg_prior					98.67 63	93.79 55		98.00 111		95.68 135			99.57 98

test_prior				97.23 65	98.67 63	92.99 79		98.00 111					99.41 125			99.29 70

WR-MVS		92.34 222	91.53 230	94.77 219	95.13 317	90.83 171	96.40 260	97.98 113	91.88 170	89.29 302	95.54 263	82.50 222	97.80 326	89.79 236	85.27 360	95.69 303

HPM-MVS++		97.34 22	96.97 37	98.47 5	99.08 38	96.16 4	97.55 141	97.97 114	95.59 22	96.61 90	97.89 107	92.57 38	99.84 23	95.95 91	99.51 33	99.40 61

CANet		96.39 74	96.02 82	97.50 50	97.62 147	93.38 64	97.02 198	97.96 115	95.42 26	94.86 152	97.81 118	87.38 136	99.82 28	96.88 54	99.20 81	99.29 70

114514_t		93.95 159	93.06 172	96.63 92	99.07 39	91.61 133	97.46 156	97.96 115	77.99 422	93.00 201	97.57 140	86.14 154	99.33 132	89.22 253	99.15 88	98.94 110

IU-MVS					99.42 7	95.39 11		97.94 117	90.40 234	98.94 16				97.41 46	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 63	96.94 1		97.93 118					99.86 9	97.68 30	99.67 6	99.77 2

No_MVS				98.86 1	98.67 63	96.94 1		97.93 118					99.86 9	97.68 30	99.67 6	99.77 2

fmvsm_s_conf0.1_n_2		96.33 78	96.44 73	96.00 147	97.30 161	90.37 189	97.53 142	97.92 120	96.52 8	99.14 12	99.08 7	83.21 199	99.74 52	99.22 8	98.06 143	97.88 211

Anonymous20231211		90.63 304	89.42 320	94.27 247	98.24 94	89.19 236	98.05 58	97.89 121	79.95 414	88.25 331	94.96 286	72.56 354	98.13 271	89.70 238	85.14 362	95.49 307

原ACMM1				96.38 118	98.59 71	91.09 161		97.89 121	87.41 328	95.22 146	97.68 127	90.25 81	99.54 103	87.95 275	99.12 93	98.49 158

CDPH-MVS		95.97 88	95.38 100	97.77 34	98.93 52	94.44 35	96.35 264	97.88 123	86.98 336	96.65 88	97.89 107	91.99 48	99.47 118	92.26 178	99.46 41	99.39 63

test11								97.88 123

EIA-MVS		95.53 103	95.47 94	95.71 166	97.06 177	89.63 209	97.82 94	97.87 125	93.57 103	93.92 179	95.04 283	90.61 78	98.95 186	94.62 135	98.68 113	98.54 151

CS-MVS		96.86 46	97.06 29	96.26 128	98.16 105	91.16 159	99.09 3	97.87 125	95.30 30	97.06 73	98.03 94	91.72 51	98.71 221	97.10 49	99.17 84	98.90 119

无先验							95.79 301	97.87 125	83.87 385				99.65 72	87.68 285		98.89 123

3Dnovator+	91.43 4	95.40 104	94.48 130	98.16 16	96.90 191	95.34 16	98.48 21	97.87 125	94.65 67	88.53 322	98.02 96	83.69 190	99.71 60	93.18 164	98.96 103	99.44 56

VPNet		92.23 230	91.31 238	94.99 202	95.56 282	90.96 165	97.22 184	97.86 129	92.96 138	90.96 254	96.62 204	75.06 334	98.20 265	91.90 189	83.65 386	95.80 294

test_vis1_n_1920		94.17 144	94.58 123	92.91 312	97.42 159	82.02 381	97.83 92	97.85 130	94.68 64	98.10 41	98.49 51	70.15 373	99.32 134	97.91 27	98.82 107	97.40 240

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 130	94.92 47	98.73 27	98.87 28	95.08 8	99.84 23	97.52 39	99.67 6	99.48 51
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 18	97.33 23	97.69 42	99.25 29	94.24 41	98.07 56	97.85 130	93.72 98	98.57 31	98.35 65	93.69 18	99.40 126	97.06 50	99.46 41	99.44 56
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 44	97.04 33	96.45 112	98.29 88	91.66 132	99.03 4	97.85 130	95.84 15	96.90 76	97.97 100	91.24 65	98.75 213	96.92 53	99.33 64	98.94 110

test_fmvsmconf0.01_n		96.15 82	95.85 86	97.03 79	92.66 400	91.83 124	97.97 72	97.84 134	95.57 23	97.53 54	99.00 14	84.20 183	99.76 47	98.82 20	99.08 95	99.48 51

GDP-MVS		95.62 99	95.13 107	97.09 75	96.79 202	93.26 72	97.89 83	97.83 135	93.58 102	96.80 78	97.82 117	83.06 206	99.16 154	94.40 140	97.95 149	98.87 125

balanced_conf03		96.84 50	96.89 42	96.68 87	97.63 146	92.22 109	98.17 49	97.82 136	94.44 76	98.23 39	97.36 153	90.97 72	99.22 144	97.74 29	99.66 10	98.61 145

AdaColmap		94.34 140	93.68 148	96.31 122	98.59 71	91.68 131	96.59 247	97.81 137	89.87 244	92.15 220	97.06 172	83.62 193	99.54 103	89.34 248	98.07 142	97.70 224

MVSMamba_PlusPlus		96.51 68	96.48 66	96.59 96	98.07 113	91.97 120	98.14 50	97.79 138	90.43 232	97.34 63	97.52 145	91.29 64	99.19 147	98.12 25	99.64 14	98.60 146

KinetiMVS		95.26 109	94.75 118	96.79 84	96.99 186	92.05 116	97.82 94	97.78 139	94.77 60	96.46 101	97.70 125	80.62 258	99.34 131	92.37 177	98.28 133	98.97 103

mamv4		94.66 134	96.10 81	90.37 381	98.01 116	73.41 431	96.82 220	97.78 139	89.95 243	94.52 162	97.43 149	92.91 27	99.09 167	98.28 24	99.16 87	98.60 146

ETV-MVS		96.02 85	95.89 85	96.40 115	97.16 169	92.44 101	97.47 154	97.77 141	94.55 70	96.48 99	94.51 311	91.23 67	98.92 191	95.65 103	98.19 137	97.82 219

新几何1				97.32 58	98.60 70	93.59 59		97.75 142	81.58 405	95.75 130	97.85 113	90.04 84	99.67 70	86.50 307	99.13 91	98.69 141

旧先验1					98.38 84	93.38 64		97.75 142			98.09 89	92.30 45			99.01 101	99.16 80

EC-MVSNet		96.42 72	96.47 67	96.26 128	97.01 184	91.52 138	98.89 5	97.75 142	94.42 77	96.64 89	97.68 127	89.32 92	98.60 231	97.45 43	99.11 94	98.67 143

EI-MVSNet-Vis-set		96.51 68	96.47 67	96.63 92	98.24 94	91.20 153	96.89 212	97.73 145	94.74 62	96.49 98	98.49 51	90.88 75	99.58 91	96.44 69	98.32 131	99.13 84

PAPM_NR		95.01 117	94.59 122	96.26 128	98.89 56	90.68 178	97.24 178	97.73 145	91.80 171	92.93 206	96.62 204	89.13 95	99.14 159	89.21 254	97.78 153	98.97 103

Anonymous20240529		91.98 239	90.73 266	95.73 164	98.14 106	89.40 223	97.99 63	97.72 147	79.63 416	93.54 187	97.41 151	69.94 375	99.56 99	91.04 211	91.11 296	98.22 181

CHOSEN 280x420		93.12 189	92.72 187	94.34 241	96.71 209	87.27 286	90.29 425	97.72 147	86.61 343	91.34 243	95.29 271	84.29 182	98.41 245	93.25 162	98.94 104	97.35 243

EI-MVSNet-UG-set		96.34 77	96.30 76	96.47 109	98.20 100	90.93 167	96.86 215	97.72 147	94.67 65	96.16 114	98.46 55	90.43 80	99.58 91	96.23 74	97.96 148	98.90 119

LS3D		93.57 173	92.61 192	96.47 109	97.59 150	91.61 133	97.67 118	97.72 147	85.17 367	90.29 265	98.34 68	84.60 174	99.73 54	83.85 349	98.27 134	98.06 200

PAPR		94.18 143	93.42 163	96.48 108	97.64 144	91.42 144	95.55 315	97.71 151	88.99 274	92.34 216	95.82 244	89.19 93	99.11 162	86.14 313	97.38 164	98.90 119

UGNet		94.04 154	93.28 166	96.31 122	96.85 194	91.19 154	97.88 84	97.68 152	94.40 79	93.00 201	96.18 224	73.39 351	99.61 83	91.72 195	98.46 125	98.13 189
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				95.46 183	98.18 104	88.90 242		97.66 153	82.73 396	97.03 74	98.07 90	90.06 83	98.85 198	89.67 239	98.98 102	98.64 144

test12				97.65 43	98.46 75	94.26 39		97.66 153		95.52 142		90.89 74	99.46 119		99.25 73	99.22 77

DTE-MVSNet		90.56 305	89.75 311	93.01 308	93.95 362	87.25 287	97.64 126	97.65 155	90.74 213	87.12 354	95.68 255	79.97 272	97.00 380	83.33 350	81.66 397	94.78 363

TAPA-MVS	90.10 7	92.30 225	91.22 244	95.56 173	98.33 86	89.60 211	96.79 222	97.65 155	81.83 402	91.52 238	97.23 161	87.94 118	98.91 193	71.31 426	98.37 129	98.17 187
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 190	92.45 200	95.05 198	98.09 109	89.21 233	96.89 212	97.64 157	93.18 125	91.79 232	97.28 156	75.35 333	98.65 226	88.99 259	92.84 266	97.28 246

test_cas_vis1_n_1920		94.48 138	94.55 127	94.28 246	96.78 203	86.45 310	97.63 128	97.64 157	93.32 118	97.68 53	98.36 64	73.75 349	99.08 170	96.73 59	99.05 97	97.31 245

NormalMVS		96.36 76	96.11 80	97.12 72	99.37 16	92.90 83	97.99 63	97.63 159	95.92 13	96.57 95	97.93 102	85.34 163	99.50 113	94.99 121	99.21 76	98.97 103

Elysia		94.00 156	93.12 169	96.64 88	96.08 261	92.72 91	97.50 145	97.63 159	91.15 201	94.82 153	97.12 167	74.98 336	99.06 176	90.78 214	98.02 144	98.12 191

StellarMVS		94.00 156	93.12 169	96.64 88	96.08 261	92.72 91	97.50 145	97.63 159	91.15 201	94.82 153	97.12 167	74.98 336	99.06 176	90.78 214	98.02 144	98.12 191

cdsmvs_eth3d_5k		23.24 421	30.99 423	0.00 439	0.00 462	0.00 464	0.00 450	97.63 159	0.00 457	0.00 458	96.88 183	84.38 179	0.00 458	0.00 457	0.00 456	0.00 454

DPM-MVS		95.69 96	94.92 112	98.01 20	98.08 112	95.71 9	95.27 331	97.62 163	90.43 232	95.55 139	97.07 171	91.72 51	99.50 113	89.62 241	98.94 104	98.82 131

sasdasda		96.02 85	95.45 95	97.75 36	97.59 150	95.15 23	98.28 31	97.60 164	94.52 72	96.27 109	96.12 229	87.65 124	99.18 150	96.20 80	94.82 228	98.91 116

canonicalmvs		96.02 85	95.45 95	97.75 36	97.59 150	95.15 23	98.28 31	97.60 164	94.52 72	96.27 109	96.12 229	87.65 124	99.18 150	96.20 80	94.82 228	98.91 116

test222					98.24 94	92.21 110	95.33 326	97.60 164	79.22 418	95.25 144	97.84 115	88.80 101			99.15 88	98.72 138

cascas		91.20 280	90.08 293	94.58 228	94.97 322	89.16 237	93.65 390	97.59 167	79.90 415	89.40 297	92.92 376	75.36 332	98.36 253	92.14 183	94.75 231	96.23 273

h-mvs33		94.15 146	93.52 156	96.04 141	97.81 132	90.22 193	97.62 130	97.58 168	95.19 33	96.74 82	97.45 146	83.67 191	99.61 83	95.85 94	79.73 404	98.29 177

MGCFI-Net		95.94 90	95.40 99	97.56 49	97.59 150	94.62 31	98.21 43	97.57 169	94.41 78	96.17 113	96.16 227	87.54 129	99.17 152	96.19 82	94.73 233	98.91 116

MVSFormer		95.37 105	95.16 106	95.99 148	96.34 242	91.21 151	98.22 41	97.57 169	91.42 186	96.22 111	97.32 154	86.20 152	97.92 313	94.07 144	99.05 97	98.85 127

test_djsdf		93.07 192	92.76 182	94.00 258	93.49 379	88.70 246	98.22 41	97.57 169	91.42 186	90.08 277	95.55 262	82.85 213	97.92 313	94.07 144	91.58 287	95.40 318

OMC-MVS		95.09 116	94.70 119	96.25 131	98.46 75	91.28 147	96.43 254	97.57 169	92.04 166	94.77 157	97.96 101	87.01 141	99.09 167	91.31 205	96.77 184	98.36 173

PS-MVSNAJss		93.74 168	93.51 157	94.44 235	93.91 364	89.28 231	97.75 104	97.56 173	92.50 151	89.94 279	96.54 207	88.65 104	98.18 268	93.83 153	90.90 301	95.86 288

casdiffmvs_mvg		95.81 95	95.57 89	96.51 105	96.87 192	91.49 139	97.50 145	97.56 173	93.99 90	95.13 148	97.92 105	87.89 119	98.78 207	95.97 90	97.33 167	99.26 74
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		92.42 218	91.89 218	94.03 257	93.33 387	88.50 253	97.73 108	97.53 175	92.00 168	88.85 314	96.50 209	75.62 331	98.11 275	93.88 151	91.56 288	95.48 308

mvs_tets		92.31 224	91.76 221	93.94 266	93.41 384	88.29 258	97.63 128	97.53 175	92.04 166	88.76 317	96.45 211	74.62 341	98.09 280	93.91 149	91.48 289	95.45 313

dcpmvs_2		96.37 75	97.05 32	94.31 244	98.96 51	84.11 355	97.56 136	97.51 177	93.92 92	97.43 60	98.52 48	92.75 32	99.32 134	97.32 48	99.50 35	99.51 44

HQP_MVS		93.78 167	93.43 161	94.82 212	96.21 246	89.99 198	97.74 106	97.51 177	94.85 50	91.34 243	96.64 197	81.32 246	98.60 231	93.02 170	92.23 275	95.86 288

plane_prior5								97.51 177					98.60 231	93.02 170	92.23 275	95.86 288

reproduce_monomvs		91.30 275	91.10 248	91.92 342	96.82 199	82.48 375	97.01 201	97.49 180	94.64 68	88.35 325	95.27 274	70.53 368	98.10 276	95.20 114	84.60 372	95.19 336

PS-MVSNAJ		95.37 105	95.33 102	95.49 179	97.35 160	90.66 179	95.31 328	97.48 181	93.85 95	96.51 97	95.70 254	88.65 104	99.65 72	94.80 130	98.27 134	96.17 277

API-MVS		94.84 127	94.49 129	95.90 151	97.90 127	92.00 119	97.80 98	97.48 181	89.19 267	94.81 155	96.71 190	88.84 100	99.17 152	88.91 261	98.76 111	96.53 266

MG-MVS		95.61 100	95.38 100	96.31 122	98.42 79	90.53 181	96.04 286	97.48 181	93.47 112	95.67 136	98.10 87	89.17 94	99.25 141	91.27 206	98.77 110	99.13 84

MAR-MVS		94.22 142	93.46 159	96.51 105	98.00 118	92.19 113	97.67 118	97.47 184	88.13 307	93.00 201	95.84 242	84.86 172	99.51 110	87.99 274	98.17 139	97.83 218
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		92.98 196	92.53 196	94.32 242	96.12 258	89.20 234	95.28 329	97.47 184	92.66 148	89.90 280	95.62 258	80.58 259	98.40 246	92.73 175	92.40 273	95.38 320
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 273	90.22 289	94.68 222	94.86 331	87.86 275	97.23 182	97.46 186	87.99 308	89.90 280	96.92 181	66.35 403	98.23 262	90.30 226	90.99 299	97.96 205

nrg030		94.05 153	93.31 165	96.27 127	95.22 309	94.59 32	98.34 26	97.46 186	92.93 139	91.21 252	96.64 197	87.23 139	98.22 263	94.99 121	85.80 352	95.98 287

XVG-OURS		93.72 169	93.35 164	94.80 217	97.07 174	88.61 247	94.79 346	97.46 186	91.97 169	93.99 176	97.86 112	81.74 240	98.88 195	92.64 176	92.67 271	96.92 258

LPG-MVS_test		92.94 199	92.56 193	94.10 252	96.16 253	88.26 260	97.65 122	97.46 186	91.29 190	90.12 273	97.16 164	79.05 288	98.73 216	92.25 180	91.89 283	95.31 325

LGP-MVS_train				94.10 252	96.16 253	88.26 260		97.46 186	91.29 190	90.12 273	97.16 164	79.05 288	98.73 216	92.25 180	91.89 283	95.31 325

MVS		91.71 247	90.44 276	95.51 177	95.20 311	91.59 135	96.04 286	97.45 191	73.44 432	87.36 350	95.60 259	85.42 162	99.10 164	85.97 318	97.46 159	95.83 292

XVG-OURS-SEG-HR		93.86 164	93.55 152	94.81 214	97.06 177	88.53 252	95.28 329	97.45 191	91.68 176	94.08 175	97.68 127	82.41 225	98.90 194	93.84 152	92.47 272	96.98 254

baseline		95.58 101	95.42 98	96.08 137	96.78 203	90.41 187	97.16 189	97.45 191	93.69 101	95.65 137	97.85 113	87.29 137	98.68 223	95.66 100	97.25 173	99.13 84

ab-mvs		93.57 173	92.55 194	96.64 88	97.28 163	91.96 122	95.40 322	97.45 191	89.81 249	93.22 198	96.28 220	79.62 279	99.46 119	90.74 217	93.11 263	98.50 156

xiu_mvs_v2_base		95.32 107	95.29 103	95.40 184	97.22 165	90.50 182	95.44 321	97.44 195	93.70 100	96.46 101	96.18 224	88.59 108	99.53 105	94.79 132	97.81 152	96.17 277

1314		92.81 208	92.03 211	95.14 194	95.33 301	89.52 218	96.04 286	97.44 195	87.72 321	86.25 371	95.33 270	83.84 188	98.79 206	89.26 251	97.05 179	97.11 252

casdiffmvs		95.64 98	95.49 92	96.08 137	96.76 208	90.45 184	97.29 175	97.44 195	94.00 89	95.46 143	97.98 99	87.52 132	98.73 216	95.64 104	97.33 167	99.08 91
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		92.16 232	91.23 243	94.95 208	94.75 336	90.94 166	97.47 154	97.43 198	89.14 268	88.90 310	96.43 212	79.71 276	98.24 261	89.56 242	87.68 333	95.67 304

anonymousdsp		92.16 232	91.55 229	93.97 262	92.58 402	89.55 215	97.51 144	97.42 199	89.42 261	88.40 324	94.84 293	80.66 257	97.88 318	91.87 191	91.28 293	94.48 371

Effi-MVS+		94.93 122	94.45 131	96.36 120	96.61 213	91.47 141	96.41 256	97.41 200	91.02 207	94.50 163	95.92 238	87.53 130	98.78 207	93.89 150	96.81 183	98.84 130

RRT-MVS		94.51 136	94.35 134	94.98 204	96.40 237	86.55 308	97.56 136	97.41 200	93.19 123	94.93 150	97.04 173	79.12 286	99.30 138	96.19 82	97.32 169	99.09 90

HQP3-MVS								97.39 202							92.10 280

HQP-MVS		93.19 186	92.74 185	94.54 231	95.86 267	89.33 227	96.65 238	97.39 202	93.55 104	90.14 267	95.87 240	80.95 250	98.50 239	92.13 185	92.10 280	95.78 296

PLC	91.00 6	94.11 150	93.43 161	96.13 136	98.58 73	91.15 160	96.69 234	97.39 202	87.29 331	91.37 242	96.71 190	88.39 109	99.52 109	87.33 294	97.13 177	97.73 222
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 297	89.86 304	93.45 293	93.54 376	87.60 281	97.70 116	97.37 205	88.85 280	87.65 343	94.08 341	81.08 249	98.10 276	84.68 335	83.79 385	94.66 368

UnsupCasMVSNet_eth		85.99 374	84.45 378	90.62 377	89.97 420	82.40 378	93.62 391	97.37 205	89.86 245	78.59 422	92.37 386	65.25 411	95.35 412	82.27 363	70.75 430	94.10 382

ACMM	89.79 8	92.96 197	92.50 198	94.35 239	96.30 244	88.71 245	97.58 132	97.36 207	91.40 188	90.53 260	96.65 196	79.77 275	98.75 213	91.24 207	91.64 285	95.59 306
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 117	94.76 115	95.75 161	96.58 216	91.71 128	96.25 273	97.35 208	92.99 132	96.70 84	96.63 201	82.67 217	99.44 122	96.22 75	97.46 159	96.11 283

xiu_mvs_v1_base		95.01 117	94.76 115	95.75 161	96.58 216	91.71 128	96.25 273	97.35 208	92.99 132	96.70 84	96.63 201	82.67 217	99.44 122	96.22 75	97.46 159	96.11 283

xiu_mvs_v1_base_debi		95.01 117	94.76 115	95.75 161	96.58 216	91.71 128	96.25 273	97.35 208	92.99 132	96.70 84	96.63 201	82.67 217	99.44 122	96.22 75	97.46 159	96.11 283

diffmvs		95.25 110	95.13 107	95.63 169	96.43 236	89.34 226	95.99 290	97.35 208	92.83 143	96.31 107	97.37 152	86.44 147	98.67 224	96.26 72	97.19 175	98.87 125
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		94.71 133	94.02 140	96.79 84	97.71 138	92.05 116	96.59 247	97.35 208	90.61 224	94.64 159	96.93 178	86.41 148	99.39 127	91.20 208	94.71 234	98.94 110

mamba_0404		94.73 132	94.31 136	95.98 149	97.05 179	90.90 169	97.01 201	97.29 213	91.24 194	94.17 172	97.60 138	85.03 169	98.76 211	92.14 183	97.30 170	98.29 177

F-COLMAP		93.58 172	92.98 174	95.37 185	98.40 81	88.98 240	97.18 187	97.29 213	87.75 320	90.49 261	97.10 170	85.21 166	99.50 113	86.70 304	96.72 187	97.63 226

VortexMVS		92.88 203	92.64 189	93.58 286	96.58 216	87.53 282	96.93 209	97.28 215	92.78 146	89.75 285	94.99 284	82.73 216	97.76 331	94.60 137	88.16 328	95.46 311

XVG-ACMP-BASELINE		90.93 293	90.21 290	93.09 306	94.31 355	85.89 323	95.33 326	97.26 216	91.06 206	89.38 298	95.44 268	68.61 386	98.60 231	89.46 244	91.05 297	94.79 361

PCF-MVS	89.48 11	91.56 257	89.95 301	96.36 120	96.60 214	92.52 99	92.51 410	97.26 216	79.41 417	88.90 310	96.56 206	84.04 187	99.55 101	77.01 402	97.30 170	97.01 253
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 212	92.14 207	94.05 255	96.40 237	88.20 263	97.36 167	97.25 218	91.52 181	88.30 328	96.64 197	78.46 300	98.72 220	91.86 192	91.48 289	95.23 332
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ICG_test_0404		92.44 216	91.92 216	94.00 258	96.19 249	86.16 319	93.84 383	97.24 219	91.54 179	88.17 334	97.04 173	76.96 318	97.09 374	90.68 219	95.59 212	98.76 133

icg_test_0403		93.98 158	93.79 145	94.55 230	96.19 249	86.16 319	96.35 264	97.24 219	91.54 179	93.59 184	97.04 173	85.86 156	98.73 216	90.68 219	95.59 212	98.76 133

OPM-MVS		93.28 182	92.76 182	94.82 212	94.63 342	90.77 174	96.65 238	97.18 221	93.72 98	91.68 236	97.26 159	79.33 283	98.63 228	92.13 185	92.28 274	95.07 339
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 201	92.02 212	95.56 173	98.19 102	90.80 172	95.27 331	97.18 221	87.96 309	91.86 231	95.68 255	80.44 262	98.99 184	84.01 344	97.54 158	96.89 259

alignmvs		95.87 94	95.23 104	97.78 32	97.56 156	95.19 21	97.86 85	97.17 223	94.39 80	96.47 100	96.40 214	85.89 155	99.20 146	96.21 79	95.11 224	98.95 109

MVS_Test		94.89 124	94.62 121	95.68 167	96.83 197	89.55 215	96.70 232	97.17 223	91.17 199	95.60 138	96.11 233	87.87 121	98.76 211	93.01 172	97.17 176	98.72 138

Fast-Effi-MVS+		93.46 176	92.75 184	95.59 172	96.77 205	90.03 195	96.81 221	97.13 225	88.19 302	91.30 246	94.27 329	86.21 151	98.63 228	87.66 286	96.46 194	98.12 191

EI-MVSNet		93.03 194	92.88 178	93.48 291	95.77 273	86.98 295	96.44 252	97.12 226	90.66 220	91.30 246	97.64 134	86.56 144	98.05 288	89.91 232	90.55 305	95.41 315

MVSTER		93.20 185	92.81 181	94.37 238	96.56 220	89.59 212	97.06 195	97.12 226	91.24 194	91.30 246	95.96 236	82.02 233	98.05 288	93.48 157	90.55 305	95.47 310

test_yl		94.78 130	94.23 137	96.43 113	97.74 136	91.22 149	96.85 216	97.10 228	91.23 196	95.71 132	96.93 178	84.30 180	99.31 136	93.10 165	95.12 222	98.75 135

DCV-MVSNet		94.78 130	94.23 137	96.43 113	97.74 136	91.22 149	96.85 216	97.10 228	91.23 196	95.71 132	96.93 178	84.30 180	99.31 136	93.10 165	95.12 222	98.75 135

LTVRE_ROB	88.41 13	90.99 289	89.92 303	94.19 248	96.18 251	89.55 215	96.31 269	97.09 230	87.88 312	85.67 375	95.91 239	78.79 296	98.57 235	81.50 366	89.98 310	94.44 374
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		92.73 210	92.88 178	92.29 332	96.08 261	81.05 389	97.98 66	97.08 231	90.72 215	96.79 80	98.18 84	63.07 415	98.45 243	97.62 37	98.42 128	97.36 241

v10		91.04 287	90.23 287	93.49 290	94.12 358	88.16 266	97.32 172	97.08 231	88.26 301	88.29 329	94.22 334	82.17 230	97.97 300	86.45 308	84.12 379	94.33 377

v144192		91.06 286	90.28 283	93.39 294	93.66 373	87.23 289	96.83 219	97.07 233	87.43 327	89.69 288	94.28 328	81.48 243	98.00 295	87.18 298	84.92 368	94.93 347

v1192		91.07 285	90.23 287	93.58 286	93.70 370	87.82 277	96.73 228	97.07 233	87.77 318	89.58 291	94.32 326	80.90 254	97.97 300	86.52 306	85.48 355	94.95 343

v8		91.29 277	90.53 275	93.57 288	94.15 357	88.12 267	97.34 169	97.06 235	88.99 274	88.32 327	94.26 331	83.08 204	98.01 294	87.62 288	83.92 383	94.57 370

mvs_anonymous		93.82 165	93.74 146	94.06 254	96.44 235	85.41 332	95.81 299	97.05 236	89.85 247	90.09 276	96.36 216	87.44 134	97.75 333	93.97 146	96.69 188	99.02 95

IterMVS-LS		92.29 226	91.94 215	93.34 296	96.25 245	86.97 296	96.57 250	97.05 236	90.67 218	89.50 296	94.80 296	86.59 143	97.64 341	89.91 232	86.11 350	95.40 318
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 295	90.03 298	93.29 298	93.55 375	86.96 297	96.74 227	97.04 238	87.36 329	89.52 295	94.34 323	80.23 267	97.97 300	86.27 309	85.21 361	94.94 345

CDS-MVSNet		94.14 149	93.54 153	95.93 150	96.18 251	91.46 142	96.33 267	97.04 238	88.97 276	93.56 185	96.51 208	87.55 128	97.89 317	89.80 235	95.95 200	98.44 166
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 331	89.26 324	91.19 366	95.16 312	80.29 400	94.53 353	97.03 240	91.79 172	88.86 313	94.10 338	69.94 375	97.82 323	85.29 327	86.66 346	95.45 313

v1144		91.37 270	90.60 271	93.68 281	93.89 365	88.23 262	96.84 218	97.03 240	88.37 298	89.69 288	94.39 318	82.04 232	97.98 297	87.80 278	85.37 357	94.84 353

v1240		90.70 301	89.85 305	93.23 300	93.51 378	86.80 298	96.61 244	97.02 242	87.16 334	89.58 291	94.31 327	79.55 280	97.98 297	85.52 324	85.44 356	94.90 350

EPP-MVSNet		95.22 112	95.04 110	95.76 159	97.49 157	89.56 214	98.67 11	97.00 243	90.69 216	94.24 169	97.62 136	89.79 89	98.81 204	93.39 161	96.49 192	98.92 115

V42		91.58 256	90.87 255	93.73 276	94.05 361	88.50 253	97.32 172	96.97 244	88.80 286	89.71 286	94.33 324	82.54 221	98.05 288	89.01 258	85.07 364	94.64 369

test_fmvs1		93.21 184	93.53 154	92.25 335	96.55 222	81.20 388	97.40 163	96.96 245	90.68 217	96.80 78	98.04 93	69.25 381	98.40 246	97.58 38	98.50 121	97.16 251

FMVSNet2		91.31 274	90.08 293	94.99 202	96.51 228	92.21 110	97.41 159	96.95 246	88.82 283	88.62 319	94.75 298	73.87 345	97.42 362	85.20 330	88.55 325	95.35 322

ACMH	87.59 16	90.53 306	89.42 320	93.87 270	96.21 246	87.92 272	97.24 178	96.94 247	88.45 296	83.91 395	96.27 221	71.92 357	98.62 230	84.43 338	89.43 316	95.05 341
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 271	90.27 284	94.59 224	96.51 228	91.18 156	97.50 145	96.93 248	88.82 283	89.35 299	94.51 311	73.87 345	97.29 369	86.12 314	88.82 320	95.31 325

test1		91.35 271	90.27 284	94.59 224	96.51 228	91.18 156	97.50 145	96.93 248	88.82 283	89.35 299	94.51 311	73.87 345	97.29 369	86.12 314	88.82 320	95.31 325

FMVSNet3		91.78 245	90.69 269	95.03 200	96.53 225	92.27 108	97.02 198	96.93 248	89.79 250	89.35 299	94.65 304	77.01 316	97.47 357	86.12 314	88.82 320	95.35 322

FMVSNet1		89.88 326	88.31 339	94.59 224	95.41 291	91.18 156	97.50 145	96.93 248	86.62 342	87.41 348	94.51 311	65.94 408	97.29 369	83.04 353	87.43 336	95.31 325

GeoE		93.89 162	93.28 166	95.72 165	96.96 189	89.75 207	98.24 39	96.92 252	89.47 258	92.12 222	97.21 162	84.42 178	98.39 251	87.71 281	96.50 191	99.01 98

SymmetryMVS		95.94 90	95.54 90	97.15 70	97.85 129	92.90 83	97.99 63	96.91 253	95.92 13	96.57 95	97.93 102	85.34 163	99.50 113	94.99 121	96.39 195	99.05 94

miper_enhance_ethall		91.54 260	91.01 251	93.15 304	95.35 297	87.07 294	93.97 375	96.90 254	86.79 340	89.17 306	93.43 370	86.55 145	97.64 341	89.97 231	86.93 341	94.74 365

eth_miper_zixun_eth		91.02 288	90.59 272	92.34 330	95.33 301	84.35 351	94.10 372	96.90 254	88.56 292	88.84 315	94.33 324	84.08 185	97.60 346	88.77 264	84.37 377	95.06 340

TAMVS		94.01 155	93.46 159	95.64 168	96.16 253	90.45 184	96.71 231	96.89 256	89.27 265	93.46 190	96.92 181	87.29 137	97.94 310	88.70 266	95.74 206	98.53 152

miper_ehance_all_eth		91.59 254	91.13 247	92.97 310	95.55 283	86.57 306	94.47 356	96.88 257	87.77 318	88.88 312	94.01 343	86.22 150	97.54 350	89.49 243	86.93 341	94.79 361

v2v482		91.59 254	90.85 258	93.80 273	93.87 366	88.17 265	96.94 208	96.88 257	89.54 255	89.53 294	94.90 290	81.70 241	98.02 293	89.25 252	85.04 366	95.20 333

CNLPA		94.28 141	93.53 154	96.52 101	98.38 84	92.55 98	96.59 247	96.88 257	90.13 240	91.91 228	97.24 160	85.21 166	99.09 167	87.64 287	97.83 151	97.92 208

PAPM		91.52 261	90.30 282	95.20 191	95.30 304	89.83 205	93.38 396	96.85 260	86.26 350	88.59 320	95.80 245	84.88 171	98.15 270	75.67 407	95.93 201	97.63 226

c3_l		91.38 268	90.89 254	92.88 314	95.58 281	86.30 313	94.68 348	96.84 261	88.17 303	88.83 316	94.23 332	85.65 160	97.47 357	89.36 247	84.63 370	94.89 351

pm-mvs1		90.72 300	89.65 315	93.96 263	94.29 356	89.63 209	97.79 100	96.82 262	89.07 270	86.12 373	95.48 267	78.61 298	97.78 328	86.97 302	81.67 396	94.46 372

test_vis1_n		92.37 221	92.26 205	92.72 320	94.75 336	82.64 371	98.02 60	96.80 263	91.18 198	97.77 52	97.93 102	58.02 425	98.29 259	97.63 35	98.21 136	97.23 249

CMPMVS	62.92 21	85.62 379	84.92 374	87.74 403	89.14 425	73.12 433	94.17 370	96.80 263	73.98 429	73.65 431	94.93 288	66.36 402	97.61 345	83.95 346	91.28 293	92.48 409
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 313	89.77 309	91.78 351	94.33 353	84.72 348	95.55 315	96.73 265	86.17 352	86.36 370	95.28 273	71.28 362	97.80 326	84.09 343	98.14 140	92.81 401

Effi-MVS+-dtu		93.08 191	93.21 168	92.68 323	96.02 264	83.25 365	97.14 191	96.72 266	93.85 95	91.20 253	93.44 367	83.08 204	98.30 258	91.69 198	95.73 207	96.50 268

TSAR-MVS + GP.		96.69 61	96.49 65	97.27 63	98.31 87	93.39 63	96.79 222	96.72 266	94.17 84	97.44 58	97.66 130	92.76 31	99.33 132	96.86 56	97.76 155	99.08 91

1112_ss		93.37 179	92.42 201	96.21 132	97.05 179	90.99 163	96.31 269	96.72 266	86.87 339	89.83 283	96.69 194	86.51 146	99.14 159	88.12 271	93.67 257	98.50 156

PVSNet	86.66 18	92.24 229	91.74 224	93.73 276	97.77 134	83.69 362	92.88 405	96.72 266	87.91 311	93.00 201	94.86 292	78.51 299	99.05 179	86.53 305	97.45 163	98.47 161

miper_lstm_enhance		90.50 309	90.06 297	91.83 347	95.33 301	83.74 359	93.86 381	96.70 270	87.56 325	87.79 340	93.81 351	83.45 196	96.92 382	87.39 292	84.62 371	94.82 356

v148		90.99 289	90.38 278	92.81 317	93.83 367	85.80 324	96.78 225	96.68 271	89.45 260	88.75 318	93.93 347	82.96 210	97.82 323	87.83 277	83.25 388	94.80 359

ACMH+	87.92 14	90.20 317	89.18 326	93.25 299	96.48 231	86.45 310	96.99 204	96.68 271	88.83 282	84.79 384	96.22 223	70.16 372	98.53 237	84.42 339	88.04 329	94.77 364

CANet_DTU		94.37 139	93.65 149	96.55 98	96.46 234	92.13 114	96.21 277	96.67 273	94.38 81	93.53 188	97.03 176	79.34 282	99.71 60	90.76 216	98.45 126	97.82 219

cl____		90.96 292	90.32 280	92.89 313	95.37 295	86.21 316	94.46 358	96.64 274	87.82 314	88.15 335	94.18 335	82.98 208	97.54 350	87.70 282	85.59 353	94.92 349

HY-MVS	89.66 9	93.87 163	92.95 175	96.63 92	97.10 173	92.49 100	95.64 312	96.64 274	89.05 272	93.00 201	95.79 248	85.77 159	99.45 121	89.16 257	94.35 236	97.96 205

Test_1112_low_res		92.84 206	91.84 219	95.85 155	97.04 181	89.97 201	95.53 317	96.64 274	85.38 362	89.65 290	95.18 278	85.86 156	99.10 164	87.70 282	93.58 262	98.49 158

DIV-MVS_self_test		90.97 291	90.33 279	92.88 314	95.36 296	86.19 318	94.46 358	96.63 277	87.82 314	88.18 333	94.23 332	82.99 207	97.53 352	87.72 279	85.57 354	94.93 347

Fast-Effi-MVS+-dtu		92.29 226	91.99 213	93.21 302	95.27 305	85.52 330	97.03 196	96.63 277	92.09 164	89.11 308	95.14 280	80.33 265	98.08 281	87.54 290	94.74 232	96.03 286

UnsupCasMVSNet_bld		82.13 395	79.46 400	90.14 384	88.00 433	82.47 376	90.89 423	96.62 279	78.94 419	75.61 426	84.40 437	56.63 428	96.31 394	77.30 399	66.77 438	91.63 419

cl22		91.21 279	90.56 274	93.14 305	96.09 260	86.80 298	94.41 360	96.58 280	87.80 316	88.58 321	93.99 345	80.85 255	97.62 344	89.87 234	86.93 341	94.99 342

jason		94.84 127	94.39 133	96.18 134	95.52 284	90.93 167	96.09 284	96.52 281	89.28 264	96.01 121	97.32 154	84.70 173	98.77 210	95.15 117	98.91 106	98.85 127
jason: jason.
tt0805		91.09 284	90.07 296	94.16 250	95.61 279	88.31 257	97.56 136	96.51 282	89.56 254	89.17 306	95.64 257	67.08 400	98.38 252	91.07 210	88.44 326	95.80 294

AUN-MVS		91.76 246	90.75 264	94.81 214	97.00 185	88.57 249	96.65 238	96.49 283	89.63 252	92.15 220	96.12 229	78.66 297	98.50 239	90.83 212	79.18 407	97.36 241

hse-mvs2		93.45 177	92.99 173	94.81 214	97.02 183	88.59 248	96.69 234	96.47 284	95.19 33	96.74 82	96.16 227	83.67 191	98.48 242	95.85 94	79.13 408	97.35 243

SD_0403		90.01 321	90.02 299	89.96 387	95.65 278	76.76 421	95.76 303	96.46 285	90.58 227	86.59 367	96.29 219	82.12 231	94.78 416	73.00 421	93.76 255	98.35 175

EG-PatchMatch MVS		87.02 361	85.44 366	91.76 353	92.67 399	85.00 342	96.08 285	96.45 286	83.41 392	79.52 418	93.49 364	57.10 427	97.72 335	79.34 390	90.87 302	92.56 406

KD-MVS_self_test		85.95 375	84.95 373	88.96 397	89.55 424	79.11 415	95.13 338	96.42 287	85.91 355	84.07 393	90.48 409	70.03 374	94.82 415	80.04 382	72.94 427	92.94 399

pmmvs6		87.81 353	86.19 361	92.69 322	91.32 412	86.30 313	97.34 169	96.41 288	80.59 413	84.05 394	94.37 320	67.37 395	97.67 338	84.75 334	79.51 406	94.09 384

PMMVS		92.86 204	92.34 202	94.42 237	94.92 327	86.73 301	94.53 353	96.38 289	84.78 374	94.27 168	95.12 282	83.13 203	98.40 246	91.47 202	96.49 192	98.12 191

RPSCF		90.75 298	90.86 256	90.42 380	96.84 195	76.29 424	95.61 313	96.34 290	83.89 383	91.38 241	97.87 110	76.45 322	98.78 207	87.16 299	92.23 275	96.20 275

BP-MVS1		95.89 92	95.49 92	97.08 77	96.67 210	93.20 73	98.08 54	96.32 291	94.56 69	96.32 106	97.84 115	84.07 186	99.15 156	96.75 58	98.78 109	98.90 119

MSDG		91.42 266	90.24 286	94.96 207	97.15 171	88.91 241	93.69 388	96.32 291	85.72 358	86.93 363	96.47 210	80.24 266	98.98 185	80.57 379	95.05 225	96.98 254

WBMVS		90.69 303	89.99 300	92.81 317	96.48 231	85.00 342	95.21 336	96.30 293	89.46 259	89.04 309	94.05 342	72.45 355	97.82 323	89.46 244	87.41 338	95.61 305

OurMVSNet-221017-0		90.51 308	90.19 291	91.44 359	93.41 384	81.25 386	96.98 205	96.28 294	91.68 176	86.55 368	96.30 218	74.20 344	97.98 297	88.96 260	87.40 339	95.09 338

MVP-Stereo		90.74 299	90.08 293	92.71 321	93.19 389	88.20 263	95.86 296	96.27 295	86.07 353	84.86 383	94.76 297	77.84 311	97.75 333	83.88 348	98.01 146	92.17 416
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 121	94.56 124	96.29 126	96.34 242	91.21 151	95.83 298	96.27 295	88.93 278	96.22 111	96.88 183	86.20 152	98.85 198	95.27 113	99.05 97	98.82 131

BH-untuned		92.94 199	92.62 191	93.92 269	97.22 165	86.16 319	96.40 260	96.25 297	90.06 241	89.79 284	96.17 226	83.19 200	98.35 254	87.19 297	97.27 172	97.24 248

CL-MVSNet_self_test		86.31 370	85.15 370	89.80 389	88.83 428	81.74 384	93.93 378	96.22 298	86.67 341	85.03 381	90.80 407	78.09 307	94.50 417	74.92 410	71.86 429	93.15 397

IS-MVSNet		94.90 123	94.52 128	96.05 140	97.67 140	90.56 180	98.44 22	96.22 298	93.21 120	93.99 176	97.74 123	85.55 161	98.45 243	89.98 230	97.86 150	99.14 83

FA-MVS(test-final)		93.52 175	92.92 176	95.31 188	96.77 205	88.54 251	94.82 345	96.21 300	89.61 253	94.20 170	95.25 276	83.24 198	99.14 159	90.01 229	96.16 197	98.25 179

GA-MVS		91.38 268	90.31 281	94.59 224	94.65 341	87.62 280	94.34 363	96.19 301	90.73 214	90.35 264	93.83 348	71.84 358	97.96 304	87.22 296	93.61 260	98.21 182

LuminaMVS		94.89 124	94.35 134	96.53 99	95.48 286	92.80 87	96.88 214	96.18 302	92.85 142	95.92 124	96.87 185	81.44 244	98.83 201	96.43 70	97.10 178	97.94 207

IterMVS-SCA-FT		90.31 311	89.81 307	91.82 348	95.52 284	84.20 354	94.30 366	96.15 303	90.61 224	87.39 349	94.27 329	75.80 328	96.44 392	87.34 293	86.88 345	94.82 356

IterMVS		90.15 319	89.67 313	91.61 355	95.48 286	83.72 360	94.33 364	96.12 304	89.99 242	87.31 352	94.15 337	75.78 330	96.27 395	86.97 302	86.89 344	94.83 354
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 209	91.51 233	96.52 101	98.77 58	90.99 163	97.38 166	96.08 305	82.38 398	89.29 302	97.87 110	83.77 189	99.69 66	81.37 372	96.69 188	98.89 123

pmmvs4		90.93 293	89.85 305	94.17 249	93.34 386	90.79 173	94.60 350	96.02 306	84.62 375	87.45 346	95.15 279	81.88 238	97.45 359	87.70 282	87.87 331	94.27 381

ppachtmachnet_test		88.35 348	87.29 347	91.53 356	92.45 405	83.57 363	93.75 385	95.97 307	84.28 378	85.32 380	94.18 335	79.00 294	96.93 381	75.71 406	84.99 367	94.10 382

Anonymous20240521		86.42 368	85.44 366	89.34 395	90.33 417	79.79 406	96.73 228	95.92 308	83.71 388	83.25 399	91.36 404	63.92 413	96.01 396	78.39 394	85.36 358	92.22 414

ITE_SJBPF				92.43 326	95.34 298	85.37 335		95.92 308	91.47 183	87.75 342	96.39 215	71.00 364	97.96 304	82.36 362	89.86 312	93.97 387

test_fmvs2		89.77 330	89.93 302	89.31 396	93.68 372	76.37 423	97.64 126	95.90 310	89.84 248	91.49 239	96.26 222	58.77 423	97.10 373	94.65 134	91.13 295	94.46 372

USDC		88.94 339	87.83 344	92.27 333	94.66 340	84.96 344	93.86 381	95.90 310	87.34 330	83.40 397	95.56 261	67.43 394	98.19 267	82.64 361	89.67 314	93.66 390

COLMAP_ROB	87.81 15	90.40 310	89.28 323	93.79 274	97.95 122	87.13 293	96.92 210	95.89 312	82.83 395	86.88 365	97.18 163	73.77 348	99.29 139	78.44 393	93.62 259	94.95 343
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 165	93.08 171	96.02 143	97.88 128	89.96 202	97.72 111	95.85 313	92.43 152	95.86 126	98.44 57	68.42 390	99.39 127	96.31 71	94.85 226	98.71 140

VDDNet		93.05 193	92.07 208	96.02 143	96.84 195	90.39 188	98.08 54	95.85 313	86.22 351	95.79 129	98.46 55	67.59 393	99.19 147	94.92 124	94.85 226	98.47 161

mvsmamba		94.57 135	94.14 139	95.87 152	97.03 182	89.93 203	97.84 89	95.85 313	91.34 189	94.79 156	96.80 186	80.67 256	98.81 204	94.85 125	98.12 141	98.85 127

Vis-MVSNet (Re-imp)		94.15 146	93.88 143	94.95 208	97.61 148	87.92 272	98.10 52	95.80 316	92.22 157	93.02 200	97.45 146	84.53 176	97.91 316	88.24 270	97.97 147	99.02 95

MM		97.29 26	96.98 36	98.23 11	98.01 116	95.03 26	98.07 56	95.76 317	97.78 1	97.52 55	98.80 35	88.09 114	99.86 9	99.44 2	99.37 62	99.80 1

KD-MVS_2432*1600		84.81 385	82.64 388	91.31 361	91.07 414	85.34 336	91.22 418	95.75 318	85.56 360	83.09 400	90.21 412	67.21 396	95.89 398	77.18 400	62.48 442	92.69 402

miper_refine_blended		84.81 385	82.64 388	91.31 361	91.07 414	85.34 336	91.22 418	95.75 318	85.56 360	83.09 400	90.21 412	67.21 396	95.89 398	77.18 400	62.48 442	92.69 402

FE-MVS		92.05 237	91.05 249	95.08 197	96.83 197	87.93 271	93.91 380	95.70 320	86.30 348	94.15 173	94.97 285	76.59 320	99.21 145	84.10 342	96.86 181	98.09 197

tpm cat1		88.36 347	87.21 350	91.81 349	95.13 317	80.55 395	92.58 409	95.70 320	74.97 428	87.45 346	91.96 397	78.01 310	98.17 269	80.39 381	88.74 323	96.72 264

our_test_3		88.78 343	87.98 343	91.20 365	92.45 405	82.53 373	93.61 392	95.69 322	85.77 357	84.88 382	93.71 353	79.99 271	96.78 388	79.47 387	86.24 347	94.28 380

BH-w/o		92.14 234	91.75 222	93.31 297	96.99 186	85.73 327	95.67 307	95.69 322	88.73 288	89.26 304	94.82 295	82.97 209	98.07 285	85.26 329	96.32 196	96.13 282

CR-MVSNet		90.82 296	89.77 309	93.95 264	94.45 349	87.19 290	90.23 426	95.68 324	86.89 338	92.40 210	92.36 389	80.91 252	97.05 376	81.09 376	93.95 252	97.60 231

Patchmtry		88.64 345	87.25 348	92.78 319	94.09 359	86.64 302	89.82 430	95.68 324	80.81 410	87.63 344	92.36 389	80.91 252	97.03 377	78.86 391	85.12 363	94.67 367

testing91		91.90 242	91.02 250	94.53 232	96.54 223	86.55 308	95.86 296	95.64 326	91.77 173	91.89 229	93.47 366	69.94 375	98.86 196	90.23 228	93.86 254	98.18 184

BH-RMVSNet		92.72 211	91.97 214	94.97 206	97.16 169	87.99 270	96.15 282	95.60 327	90.62 223	91.87 230	97.15 166	78.41 301	98.57 235	83.16 351	97.60 157	98.36 173

PVSNet_0	82.17 19	85.46 380	83.64 383	90.92 369	95.27 305	79.49 411	90.55 424	95.60 327	83.76 387	83.00 402	89.95 414	71.09 363	97.97 300	82.75 359	60.79 444	95.31 325

guyue		95.17 115	94.96 111	95.82 156	96.97 188	89.65 208	97.56 136	95.58 329	94.82 54	95.72 131	97.42 150	82.90 211	98.84 200	96.71 61	96.93 180	98.96 106

SCA		91.84 244	91.18 246	93.83 271	95.59 280	84.95 345	94.72 347	95.58 329	90.82 210	92.25 218	93.69 355	75.80 328	98.10 276	86.20 311	95.98 199	98.45 163

MonoMVSNet		91.92 240	91.77 220	92.37 327	92.94 393	83.11 367	97.09 194	95.55 331	92.91 140	90.85 256	94.55 308	81.27 248	96.52 391	93.01 172	87.76 332	97.47 237

AllTest		90.23 315	88.98 329	93.98 260	97.94 123	86.64 302	96.51 251	95.54 332	85.38 362	85.49 377	96.77 188	70.28 370	99.15 156	80.02 383	92.87 264	96.15 280

TestCases				93.98 260	97.94 123	86.64 302		95.54 332	85.38 362	85.49 377	96.77 188	70.28 370	99.15 156	80.02 383	92.87 264	96.15 280

mmtdpeth		89.70 332	88.96 330	91.90 344	95.84 272	84.42 350	97.46 156	95.53 334	90.27 235	94.46 165	90.50 408	69.74 379	98.95 186	97.39 47	69.48 433	92.34 410

tpmvs		89.83 329	89.15 327	91.89 345	94.92 327	80.30 399	93.11 401	95.46 335	86.28 349	88.08 336	92.65 379	80.44 262	98.52 238	81.47 368	89.92 311	96.84 260

pmmvs5		89.86 328	88.87 333	92.82 316	92.86 395	86.23 315	96.26 272	95.39 336	84.24 379	87.12 354	94.51 311	74.27 343	97.36 366	87.61 289	87.57 334	94.86 352

PatchmatchNet		91.91 241	91.35 235	93.59 285	95.38 293	84.11 355	93.15 400	95.39 336	89.54 255	92.10 223	93.68 357	82.82 214	98.13 271	84.81 333	95.32 218	98.52 153
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 265	91.32 237	91.79 350	95.15 315	79.20 414	93.42 395	95.37 338	88.55 293	93.49 189	93.67 358	82.49 223	98.27 260	90.41 223	89.34 317	97.90 209

Anonymous20231206		87.09 360	86.14 362	89.93 388	91.22 413	80.35 397	96.11 283	95.35 339	83.57 390	84.16 389	93.02 374	73.54 350	95.61 406	72.16 423	86.14 349	93.84 389

MIMVSNet1		84.93 383	83.05 385	90.56 378	89.56 423	84.84 347	95.40 322	95.35 339	83.91 382	80.38 414	92.21 394	57.23 426	93.34 429	70.69 429	82.75 394	93.50 392

TDRefinement		86.53 364	84.76 376	91.85 346	82.23 445	84.25 352	96.38 262	95.35 339	84.97 371	84.09 392	94.94 287	65.76 409	98.34 257	84.60 337	74.52 423	92.97 398

TR-MVS		91.48 264	90.59 272	94.16 250	96.40 237	87.33 283	95.67 307	95.34 342	87.68 322	91.46 240	95.52 264	76.77 319	98.35 254	82.85 356	93.61 260	96.79 262

EPNet_dtu		91.71 247	91.28 240	92.99 309	93.76 369	83.71 361	96.69 234	95.28 343	93.15 127	87.02 359	95.95 237	83.37 197	97.38 365	79.46 388	96.84 182	97.88 211
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 357	85.79 364	91.78 351	94.80 334	87.28 285	95.49 319	95.28 343	84.09 381	83.85 396	91.82 398	62.95 416	94.17 421	78.48 392	85.34 359	93.91 388

MDTV_nov1_ep13			90.76 262		95.22 309	80.33 398	93.03 403	95.28 343	88.14 306	92.84 207	93.83 348	81.34 245	98.08 281	82.86 354	94.34 237

LF4IMVS		87.94 351	87.25 348	89.98 386	92.38 407	80.05 405	94.38 361	95.25 346	87.59 324	84.34 386	94.74 299	64.31 412	97.66 340	84.83 332	87.45 335	92.23 413

TransMVSNet (Re)		88.94 339	87.56 345	93.08 307	94.35 352	88.45 255	97.73 108	95.23 347	87.47 326	84.26 388	95.29 271	79.86 274	97.33 367	79.44 389	74.44 424	93.45 394

test20.03		86.14 373	85.40 368	88.35 398	90.12 418	80.06 404	95.90 295	95.20 348	88.59 289	81.29 409	93.62 360	71.43 361	92.65 433	71.26 427	81.17 399	92.34 410

new-patchmatchnet		83.18 391	81.87 394	87.11 406	86.88 436	75.99 425	93.70 386	95.18 349	85.02 370	77.30 425	88.40 424	65.99 407	93.88 426	74.19 415	70.18 431	91.47 423

MDA-MVSNet_test_wron		85.87 377	84.23 380	90.80 375	92.38 407	82.57 372	93.17 398	95.15 350	82.15 399	67.65 437	92.33 392	78.20 303	95.51 409	77.33 397	79.74 403	94.31 379

YYNet1		85.87 377	84.23 380	90.78 376	92.38 407	82.46 377	93.17 398	95.14 351	82.12 400	67.69 435	92.36 389	78.16 306	95.50 410	77.31 398	79.73 404	94.39 375

Baseline_NR-MVSNet		91.20 280	90.62 270	92.95 311	93.83 367	88.03 269	97.01 201	95.12 352	88.42 297	89.70 287	95.13 281	83.47 194	97.44 360	89.66 240	83.24 389	93.37 395

thres200		92.23 230	91.39 234	94.75 221	97.61 148	89.03 239	96.60 246	95.09 353	92.08 165	93.28 195	94.00 344	78.39 302	99.04 182	81.26 375	94.18 243	96.19 276

ADS-MVSNet		89.89 325	88.68 335	93.53 289	95.86 267	84.89 346	90.93 421	95.07 354	83.23 393	91.28 249	91.81 399	79.01 292	97.85 319	79.52 385	91.39 291	97.84 216

pmmvs-eth3d		86.22 371	84.45 378	91.53 356	88.34 432	87.25 287	94.47 356	95.01 355	83.47 391	79.51 419	89.61 417	69.75 378	95.71 403	83.13 352	76.73 417	91.64 418

Anonymous202405211		92.07 236	90.83 260	95.76 159	98.19 102	88.75 244	97.58 132	95.00 356	86.00 354	93.64 183	97.45 146	66.24 405	99.53 105	90.68 219	92.71 269	99.01 98

MDA-MVSNet-bldmvs		85.00 382	82.95 387	91.17 367	93.13 391	83.33 364	94.56 352	95.00 356	84.57 376	65.13 441	92.65 379	70.45 369	95.85 400	73.57 418	77.49 413	94.33 377

ambc				86.56 409	83.60 442	70.00 436	85.69 440	94.97 358		80.60 413	88.45 423	37.42 444	96.84 385	82.69 360	75.44 421	92.86 400

testgi		87.97 350	87.21 350	90.24 383	92.86 395	80.76 390	96.67 237	94.97 358	91.74 174	85.52 376	95.83 243	62.66 418	94.47 419	76.25 404	88.36 327	95.48 308

myMVS_eth3d28		91.52 261	90.97 252	93.17 303	96.91 190	83.24 366	95.61 313	94.96 360	92.24 156	91.98 226	93.28 371	69.31 380	98.40 246	88.71 265	95.68 209	97.88 211

dp		88.90 341	88.26 341	90.81 373	94.58 345	76.62 422	92.85 406	94.93 361	85.12 368	90.07 278	93.07 373	75.81 327	98.12 274	80.53 380	87.42 337	97.71 223

test_fmvs3		83.21 390	83.02 386	83.78 413	86.77 437	68.34 439	96.76 226	94.91 362	86.49 344	84.14 391	89.48 418	36.04 445	91.73 435	91.86 192	80.77 401	91.26 425

test_0402		86.46 367	84.79 375	91.45 358	95.02 321	85.55 329	96.29 271	94.89 363	80.90 407	82.21 405	93.97 346	68.21 391	97.29 369	62.98 436	88.68 324	91.51 421

tfpn200view9		92.38 220	91.52 231	94.95 208	97.85 129	89.29 229	97.41 159	94.88 364	92.19 161	93.27 196	94.46 316	78.17 304	99.08 170	81.40 369	94.08 247	96.48 269

CVMVSNet		91.23 278	91.75 222	89.67 390	95.77 273	74.69 426	96.44 252	94.88 364	85.81 356	92.18 219	97.64 134	79.07 287	95.58 408	88.06 273	95.86 204	98.74 137

thres400		92.42 218	91.52 231	95.12 196	97.85 129	89.29 229	97.41 159	94.88 364	92.19 161	93.27 196	94.46 316	78.17 304	99.08 170	81.40 369	94.08 247	96.98 254

tt0320		85.39 381	83.12 384	92.19 337	93.44 383	85.79 325	96.19 279	94.87 367	71.19 435	82.92 403	91.76 401	58.43 424	96.81 386	81.03 377	78.26 412	93.98 386

EPNet		95.20 113	94.56 124	97.14 71	92.80 397	92.68 93	97.85 88	94.87 367	96.64 6	92.46 209	97.80 120	86.23 149	99.65 72	93.72 154	98.62 117	99.10 89
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 252	90.72 267	94.32 242	96.48 231	86.11 322	95.81 299	94.76 369	91.55 178	91.75 234	93.44 367	68.55 388	98.82 202	90.43 222	93.69 256	98.04 201

sc_t1		86.48 366	84.10 382	93.63 282	93.45 382	85.76 326	96.79 222	94.71 370	73.06 433	86.45 369	94.35 321	55.13 431	97.95 308	84.38 340	78.55 411	97.18 250

SixPastTwentyTwo		89.15 337	88.54 337	90.98 368	93.49 379	80.28 401	96.70 232	94.70 371	90.78 211	84.15 390	95.57 260	71.78 359	97.71 336	84.63 336	85.07 364	94.94 345

thres100view900		92.43 217	91.58 228	94.98 204	97.92 125	89.37 225	97.71 113	94.66 372	92.20 159	93.31 194	94.90 290	78.06 308	99.08 170	81.40 369	94.08 247	96.48 269

thres600view7		92.49 215	91.60 227	95.18 192	97.91 126	89.47 219	97.65 122	94.66 372	92.18 163	93.33 193	94.91 289	78.06 308	99.10 164	81.61 365	94.06 251	96.98 254

PatchT		88.87 342	87.42 346	93.22 301	94.08 360	85.10 340	89.51 431	94.64 374	81.92 401	92.36 213	88.15 427	80.05 270	97.01 379	72.43 422	93.65 258	97.54 234

baseline1		92.82 207	91.90 217	95.55 175	97.20 167	90.77 174	97.19 186	94.58 375	92.20 159	92.36 213	96.34 217	84.16 184	98.21 264	89.20 255	83.90 384	97.68 225

AstraMVS		94.82 129	94.64 120	95.34 187	96.36 241	88.09 268	97.58 132	94.56 376	94.98 43	95.70 134	97.92 105	81.93 237	98.93 189	96.87 55	95.88 202	98.99 102

UBG		91.55 258	90.76 262	93.94 266	96.52 227	85.06 341	95.22 334	94.54 377	90.47 231	91.98 226	92.71 378	72.02 356	98.74 215	88.10 272	95.26 220	98.01 203

Gipuma		67.86 411	65.41 413	75.18 426	92.66 400	73.45 430	66.50 447	94.52 378	53.33 446	57.80 447	66.07 447	30.81 447	89.20 439	48.15 445	78.88 410	62.90 447
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 250	90.75 264	94.47 233	96.53 225	86.56 307	95.76 303	94.51 379	91.10 205	91.24 251	93.59 361	68.59 387	98.86 196	91.10 209	94.29 239	98.00 204

CostFormer		91.18 283	90.70 268	92.62 324	94.84 332	81.76 383	94.09 373	94.43 380	84.15 380	92.72 208	93.77 352	79.43 281	98.20 265	90.70 218	92.18 278	97.90 209

tpm2		89.96 322	89.21 325	92.23 336	94.91 329	81.25 386	93.78 384	94.42 381	80.62 412	91.56 237	93.44 367	76.44 323	97.94 310	85.60 323	92.08 282	97.49 235

testing3-2		92.10 235	92.05 209	92.27 333	97.71 138	79.56 408	97.42 158	94.41 382	93.53 108	93.22 198	95.49 265	69.16 382	99.11 162	93.25 162	94.22 241	98.13 189

MVS_0304		96.74 58	96.31 75	98.02 19	96.87 192	94.65 30	97.58 132	94.39 383	96.47 9	97.16 67	98.39 61	87.53 130	99.87 7	98.97 17	99.41 54	99.55 38

JIA-IIPM		88.26 349	87.04 353	91.91 343	93.52 377	81.42 385	89.38 432	94.38 384	80.84 409	90.93 255	80.74 439	79.22 284	97.92 313	82.76 358	91.62 286	96.38 272

dmvs_re		90.21 316	89.50 318	92.35 328	95.47 290	85.15 338	95.70 306	94.37 385	90.94 209	88.42 323	93.57 362	74.63 340	95.67 405	82.80 357	89.57 315	96.22 274

Patchmatch-test		89.42 335	87.99 342	93.70 279	95.27 305	85.11 339	88.98 433	94.37 385	81.11 406	87.10 357	93.69 355	82.28 227	97.50 355	74.37 413	94.76 230	98.48 160

LCM-MVSNet		72.55 404	69.39 408	82.03 415	70.81 455	65.42 444	90.12 428	94.36 387	55.02 445	65.88 439	81.72 438	24.16 453	89.96 436	74.32 414	68.10 436	90.71 428

ADS-MVSNet2		89.45 334	88.59 336	92.03 340	95.86 267	82.26 379	90.93 421	94.32 388	83.23 393	91.28 249	91.81 399	79.01 292	95.99 397	79.52 385	91.39 291	97.84 216

mvs5depth		86.53 364	85.08 371	90.87 370	88.74 430	82.52 374	91.91 414	94.23 389	86.35 347	87.11 356	93.70 354	66.52 401	97.76 331	81.37 372	75.80 419	92.31 412

EU-MVSNet		88.72 344	88.90 332	88.20 400	93.15 390	74.21 428	96.63 243	94.22 390	85.18 366	87.32 351	95.97 235	76.16 325	94.98 414	85.27 328	86.17 348	95.41 315

tt0320-xc		84.83 384	82.33 392	92.31 331	93.66 373	86.20 317	96.17 281	94.06 391	71.26 434	82.04 407	92.22 393	55.07 432	96.72 389	81.49 367	75.04 422	94.02 385

MIMVSNet		88.50 346	86.76 356	93.72 278	94.84 332	87.77 278	91.39 416	94.05 392	86.41 346	87.99 338	92.59 382	63.27 414	95.82 402	77.44 396	92.84 266	97.57 233

OpenMVS_ROB	81.14 20	84.42 387	82.28 393	90.83 371	90.06 419	84.05 357	95.73 305	94.04 393	73.89 431	80.17 417	91.53 403	59.15 422	97.64 341	66.92 434	89.05 319	90.80 427

TinyColmap		86.82 362	85.35 369	91.21 363	94.91 329	82.99 369	93.94 377	94.02 394	83.58 389	81.56 408	94.68 301	62.34 419	98.13 271	75.78 405	87.35 340	92.52 408

ETVMVS		90.52 307	89.14 328	94.67 223	96.81 201	87.85 276	95.91 294	93.97 395	89.71 251	92.34 216	92.48 384	65.41 410	97.96 304	81.37 372	94.27 240	98.21 182

IB-MVS	87.33 17	89.91 323	88.28 340	94.79 218	95.26 308	87.70 279	95.12 339	93.95 396	89.35 263	87.03 358	92.49 383	70.74 367	99.19 147	89.18 256	81.37 398	97.49 235
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		87.13 359	87.02 354	87.47 404	95.16 312	73.21 432	95.00 341	93.93 397	88.55 293	86.96 360	91.99 395	75.90 326	94.00 423	61.59 438	94.11 244	95.20 333

myMVS_eth3d		87.18 358	86.38 359	89.58 391	95.16 312	79.53 409	95.00 341	93.93 397	88.55 293	86.96 360	91.99 395	56.23 429	94.00 423	75.47 409	94.11 244	95.20 333

testing222		90.31 311	88.96 330	94.35 239	96.54 223	87.29 284	95.50 318	93.84 399	90.97 208	91.75 234	92.96 375	62.18 420	98.00 295	82.86 354	94.08 247	97.76 221

test_f		80.57 397	79.62 399	83.41 414	83.38 443	67.80 441	93.57 393	93.72 400	80.80 411	77.91 424	87.63 430	33.40 446	92.08 434	87.14 300	79.04 409	90.34 429

LCM-MVSNet-Re		92.50 213	92.52 197	92.44 325	96.82 199	81.89 382	96.92 210	93.71 401	92.41 153	84.30 387	94.60 306	85.08 168	97.03 377	91.51 200	97.36 165	98.40 169

tpm		90.25 314	89.74 312	91.76 353	93.92 363	79.73 407	93.98 374	93.54 402	88.28 300	91.99 225	93.25 372	77.51 314	97.44 360	87.30 295	87.94 330	98.12 191

ET-MVSNet_ETH3D		91.49 263	90.11 292	95.63 169	96.40 237	91.57 137	95.34 325	93.48 403	90.60 226	75.58 427	95.49 265	80.08 269	96.79 387	94.25 142	89.76 313	98.52 153

LFMVS		93.60 171	92.63 190	96.52 101	98.13 108	91.27 148	97.94 76	93.39 404	90.57 228	96.29 108	98.31 74	69.00 383	99.16 154	94.18 143	95.87 203	99.12 87

MVStest1		82.38 394	80.04 398	89.37 393	87.63 435	82.83 370	95.03 340	93.37 405	73.90 430	73.50 432	94.35 321	62.89 417	93.25 431	73.80 416	65.92 439	92.04 417

Patchmatch-RL test		87.38 356	86.24 360	90.81 373	88.74 430	78.40 418	88.12 438	93.17 406	87.11 335	82.17 406	89.29 419	81.95 235	95.60 407	88.64 267	77.02 414	98.41 168

ttmdpeth		85.91 376	84.76 376	89.36 394	89.14 425	80.25 402	95.66 310	93.16 407	83.77 386	83.39 398	95.26 275	66.24 405	95.26 413	80.65 378	75.57 420	92.57 405

test-LLR		91.42 266	91.19 245	92.12 338	94.59 343	80.66 392	94.29 367	92.98 408	91.11 203	90.76 258	92.37 386	79.02 290	98.07 285	88.81 262	96.74 185	97.63 226

test-mter		90.19 318	89.54 317	92.12 338	94.59 343	80.66 392	94.29 367	92.98 408	87.68 322	90.76 258	92.37 386	67.67 392	98.07 285	88.81 262	96.74 185	97.63 226

WB-MVSnew		89.88 326	89.56 316	90.82 372	94.57 346	83.06 368	95.65 311	92.85 410	87.86 313	90.83 257	94.10 338	79.66 278	96.88 383	76.34 403	94.19 242	92.54 407

testing3		87.67 354	86.88 355	90.05 385	96.14 256	80.71 391	97.10 193	92.85 410	90.15 239	87.54 345	94.55 308	55.70 430	94.10 422	73.77 417	94.10 246	95.35 322

test_method		66.11 412	64.89 414	69.79 429	72.62 453	35.23 461	65.19 448	92.83 412	20.35 451	65.20 440	88.08 428	43.14 442	82.70 446	73.12 420	63.46 441	91.45 424

test0.0.03 1		89.37 336	88.70 334	91.41 360	92.47 404	85.63 328	95.22 334	92.70 413	91.11 203	86.91 364	93.65 359	79.02 290	93.19 432	78.00 395	89.18 318	95.41 315

new_pmnet		82.89 392	81.12 397	88.18 401	89.63 422	80.18 403	91.77 415	92.57 414	76.79 426	75.56 428	88.23 426	61.22 421	94.48 418	71.43 425	82.92 392	89.87 430

mvsany_test1		93.93 161	93.98 141	93.78 275	94.94 326	86.80 298	94.62 349	92.55 415	88.77 287	96.85 77	98.49 51	88.98 96	98.08 281	95.03 119	95.62 211	96.46 271

thisisatest0515		92.29 226	91.30 239	95.25 190	96.60 214	88.90 242	94.36 362	92.32 416	87.92 310	93.43 191	94.57 307	77.28 315	99.00 183	89.42 246	95.86 204	97.86 215

thisisatest0530		93.03 194	92.21 206	95.49 179	97.07 174	89.11 238	97.49 153	92.19 417	90.16 238	94.09 174	96.41 213	76.43 324	99.05 179	90.38 224	95.68 209	98.31 176

tttt0517		92.96 197	92.33 203	94.87 211	97.11 172	87.16 292	97.97 72	92.09 418	90.63 222	93.88 180	97.01 177	76.50 321	99.06 176	90.29 227	95.45 216	98.38 171

K. test v3		87.64 355	86.75 357	90.32 382	93.02 392	79.48 412	96.61 244	92.08 419	90.66 220	80.25 416	94.09 340	67.21 396	96.65 390	85.96 319	80.83 400	94.83 354

TESTMET0.1,1		90.06 320	89.42 320	91.97 341	94.41 351	80.62 394	94.29 367	91.97 420	87.28 332	90.44 262	92.47 385	68.79 384	97.67 338	88.50 269	96.60 190	97.61 230

PM-MVS		83.48 389	81.86 395	88.31 399	87.83 434	77.59 420	93.43 394	91.75 421	86.91 337	80.63 412	89.91 415	44.42 441	95.84 401	85.17 331	76.73 417	91.50 422

baseline2		91.63 251	90.86 256	93.94 266	94.33 353	86.32 312	95.92 293	91.64 422	89.37 262	86.94 362	94.69 300	81.62 242	98.69 222	88.64 267	94.57 235	96.81 261

APD_test1		79.31 399	77.70 402	84.14 412	89.11 427	69.07 438	92.36 413	91.50 423	69.07 437	73.87 430	92.63 381	39.93 443	94.32 420	70.54 430	80.25 402	89.02 432

FPMVS		71.27 405	69.85 407	75.50 425	74.64 450	59.03 450	91.30 417	91.50 423	58.80 442	57.92 446	88.28 425	29.98 449	85.53 445	53.43 443	82.84 393	81.95 438

door								91.13 425

door-mid								91.06 426

EGC-MVSNET		68.77 410	63.01 416	86.07 411	92.49 403	82.24 380	93.96 376	90.96 427	0.71 456	2.62 457	90.89 406	53.66 433	93.46 427	57.25 441	84.55 374	82.51 437

mvsany_test3		83.59 388	82.44 391	87.03 407	83.80 440	73.82 429	93.70 386	90.92 428	86.42 345	82.51 404	90.26 411	46.76 440	95.71 403	90.82 213	76.76 416	91.57 420

pmmvs3		79.97 398	77.50 403	87.39 405	82.80 444	79.38 413	92.70 408	90.75 429	70.69 436	78.66 421	87.47 432	51.34 436	93.40 428	73.39 419	69.65 432	89.38 431

UWE-MVS		89.91 323	89.48 319	91.21 363	95.88 266	78.23 419	94.91 344	90.26 430	89.11 269	92.35 215	94.52 310	68.76 385	97.96 304	83.95 346	95.59 212	97.42 239

DSMNet-mixed		86.34 369	86.12 363	87.00 408	89.88 421	70.43 434	94.93 343	90.08 431	77.97 423	85.42 379	92.78 377	74.44 342	93.96 425	74.43 412	95.14 221	96.62 265

MVS-HIRNet		82.47 393	81.21 396	86.26 410	95.38 293	69.21 437	88.96 434	89.49 432	66.28 439	80.79 411	74.08 444	68.48 389	97.39 364	71.93 424	95.47 215	92.18 415

WB-MVS		76.77 401	76.63 404	77.18 420	85.32 438	56.82 452	94.53 353	89.39 433	82.66 397	71.35 433	89.18 420	75.03 335	88.88 440	35.42 449	66.79 437	85.84 434

test1111		93.19 186	92.82 180	94.30 245	97.58 154	84.56 349	98.21 43	89.02 434	93.53 108	94.58 160	98.21 81	72.69 352	99.05 179	93.06 168	98.48 124	99.28 72

SSC-MVS		76.05 402	75.83 405	76.72 424	84.77 439	56.22 453	94.32 365	88.96 435	81.82 403	70.52 434	88.91 421	74.79 339	88.71 441	33.69 450	64.71 440	85.23 435

ECVR-MVS		93.19 186	92.73 186	94.57 229	97.66 142	85.41 332	98.21 43	88.23 436	93.43 113	94.70 158	98.21 81	72.57 353	99.07 174	93.05 169	98.49 122	99.25 75

EPMVS		90.70 301	89.81 307	93.37 295	94.73 338	84.21 353	93.67 389	88.02 437	89.50 257	92.38 212	93.49 364	77.82 312	97.78 328	86.03 317	92.68 270	98.11 196

ANet_high		63.94 414	59.58 417	77.02 421	61.24 457	66.06 442	85.66 441	87.93 438	78.53 421	42.94 449	71.04 446	25.42 452	80.71 448	52.60 444	30.83 450	84.28 436

PMMVS2		70.19 406	66.92 410	80.01 416	76.35 449	65.67 443	86.22 439	87.58 439	64.83 441	62.38 442	80.29 441	26.78 451	88.49 443	63.79 435	54.07 446	85.88 433

lessismore_v0				90.45 379	91.96 410	79.09 416		87.19 440		80.32 415	94.39 318	66.31 404	97.55 349	84.00 345	76.84 415	94.70 366

PMVS	53.92 22	58.58 415	55.40 418	68.12 430	51.00 458	48.64 455	78.86 444	87.10 441	46.77 447	35.84 453	74.28 443	8.76 457	86.34 444	42.07 447	73.91 425	69.38 444
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 363	86.41 358	88.02 402	92.87 394	74.60 427	95.38 324	86.70 442	88.17 303	87.28 353	94.67 303	70.83 366	93.30 430	67.45 432	94.31 238	96.17 277

test_vis1_rt		86.16 372	85.06 372	89.46 392	93.47 381	80.46 396	96.41 256	86.61 443	85.22 365	79.15 420	88.64 422	52.41 435	97.06 375	93.08 167	90.57 304	90.87 426

testf1		69.31 408	66.76 411	76.94 422	78.61 447	61.93 446	88.27 436	86.11 444	55.62 443	59.69 443	85.31 435	20.19 455	89.32 437	57.62 439	69.44 434	79.58 439

APD_test2		69.31 408	66.76 411	76.94 422	78.61 447	61.93 446	88.27 436	86.11 444	55.62 443	59.69 443	85.31 435	20.19 455	89.32 437	57.62 439	69.44 434	79.58 439

gg-mvs-nofinetune		87.82 352	85.61 365	94.44 235	94.46 348	89.27 232	91.21 420	84.61 446	80.88 408	89.89 282	74.98 442	71.50 360	97.53 352	85.75 322	97.21 174	96.51 267

dmvs_testset		81.38 396	82.60 390	77.73 419	91.74 411	51.49 454	93.03 403	84.21 447	89.07 270	78.28 423	91.25 405	76.97 317	88.53 442	56.57 442	82.24 395	93.16 396

GG-mvs-BLEND				93.62 283	93.69 371	89.20 234	92.39 412	83.33 448		87.98 339	89.84 416	71.00 364	96.87 384	82.08 364	95.40 217	94.80 359

MTMP							97.86 85	82.03 449

DeepMVS_CX				74.68 427	90.84 416	64.34 445		81.61 450	65.34 440	67.47 438	88.01 429	48.60 439	80.13 449	62.33 437	73.68 426	79.58 439

E-PMN		53.28 416	52.56 420	55.43 433	74.43 451	47.13 456	83.63 443	76.30 451	42.23 448	42.59 450	62.22 449	28.57 450	74.40 450	31.53 451	31.51 449	44.78 448

test2506		91.60 253	90.78 261	94.04 256	97.66 142	83.81 358	98.27 33	75.53 452	93.43 113	95.23 145	98.21 81	67.21 396	99.07 174	93.01 172	98.49 122	99.25 75

EMVS		52.08 418	51.31 421	54.39 434	72.62 453	45.39 458	83.84 442	75.51 453	41.13 449	40.77 451	59.65 450	30.08 448	73.60 451	28.31 453	29.90 451	44.18 449

test_vis3_rt		72.73 403	70.55 406	79.27 417	80.02 446	68.13 440	93.92 379	74.30 454	76.90 425	58.99 445	73.58 445	20.29 454	95.37 411	84.16 341	72.80 428	74.31 442

MVE	50.73 23	53.25 417	48.81 422	66.58 432	65.34 456	57.50 451	72.49 446	70.94 455	40.15 450	39.28 452	63.51 448	6.89 459	73.48 452	38.29 448	42.38 448	68.76 446
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 419	53.82 419	46.29 435	33.73 459	45.30 459	78.32 445	67.24 456	18.02 452	50.93 448	87.05 433	52.99 434	53.11 454	70.76 428	25.29 452	40.46 450

kuosan		65.27 413	64.66 415	67.11 431	83.80 440	61.32 449	88.53 435	60.77 457	68.22 438	67.67 436	80.52 440	49.12 438	70.76 453	29.67 452	53.64 447	69.26 445

dongtai		69.99 407	69.33 409	71.98 428	88.78 429	61.64 448	89.86 429	59.93 458	75.67 427	74.96 429	85.45 434	50.19 437	81.66 447	43.86 446	55.27 445	72.63 443

N_pmnet		78.73 400	78.71 401	78.79 418	92.80 397	46.50 457	94.14 371	43.71 459	78.61 420	80.83 410	91.66 402	74.94 338	96.36 393	67.24 433	84.45 376	93.50 392

wuyk23d		25.11 420	24.57 424	26.74 436	73.98 452	39.89 460	57.88 449	9.80 460	12.27 453	10.39 454	6.97 456	7.03 458	36.44 455	25.43 454	17.39 453	3.89 453

testmvs		13.36 422	16.33 425	4.48 438	5.04 460	2.26 463	93.18 397	3.28 461	2.70 454	8.24 455	21.66 452	2.29 461	2.19 456	7.58 455	2.96 454	9.00 452

test123		13.04 423	15.66 426	5.18 437	4.51 461	3.45 462	92.50 411	1.81 462	2.50 455	7.58 456	20.15 453	3.67 460	2.18 457	7.13 456	1.07 455	9.90 451

mmdepth		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

monomultidepth		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

test_blank		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

uanet_test		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

DCPMVS		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

pcd_1.5k_mvsjas		7.39 425	9.85 428	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	88.65 104	0.00 458	0.00 457	0.00 456	0.00 454

sosnet-low-res		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

sosnet		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

uncertanet		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

Regformer		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

n2								0.00 463

nn								0.00 463

ab-mvs-re		8.06 424	10.74 427	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	96.69 194	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

uanet		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

WAC-MVS						79.53 409								75.56 408

PC_three_1452									90.77 212	98.89 23	98.28 79	96.24 1	98.35 254	95.76 98	99.58 23	99.59 27

eth-test2					0.00 462

eth-test					0.00 462

OPU-MVS				98.55 3	98.82 57	96.86 3	98.25 36				98.26 80	96.04 2	99.24 142	95.36 112	99.59 19	99.56 35

test_0728_THIRD									94.78 58	98.73 27	98.87 28	95.87 4	99.84 23	97.45 43	99.72 2	99.77 2

GSMVS																98.45 163

test_part2					99.28 27	95.74 8				98.10 41

sam_mvs1												82.76 215				98.45 163

sam_mvs												81.94 236

test_post1							92.81 407				16.58 455	80.53 260	97.68 337	86.20 311

test_post											17.58 454	81.76 239	98.08 281

patchmatchnet-post											90.45 410	82.65 220	98.10 276

gm-plane-assit					93.22 388	78.89 417			84.82 373		93.52 363		98.64 227	87.72 279

test9_res														94.81 129	99.38 59	99.45 54

agg_prior2														93.94 148	99.38 59	99.50 47

test_prior4						93.66 58	96.42 255

test_prior2							96.35 264		92.80 145	96.03 118	97.59 139	92.01 47		95.01 120	99.38 59

旧先验2							95.94 292		81.66 404	97.34 63			98.82 202	92.26 178

新几何2							95.79 301

原ACMM2							95.67 307

testdata2													99.67 70	85.96 319

segment_acmp												92.89 30

testdata1							95.26 333		93.10 130

plane_prior7					96.21 246	89.98 200

plane_prior6					96.10 259	90.00 196						81.32 246

plane_prior4											96.64 197

plane_prior3						90.00 196			94.46 75	91.34 243

plane_prior2							97.74 106		94.85 50

plane_prior1					96.14 256

plane_prior						89.99 198	97.24 178		94.06 87						92.16 279

HQP5-MVS						89.33 227

HQP-NCC					95.86 267		96.65 238		93.55 104	90.14 267

ACMP_Plane					95.86 267		96.65 238		93.55 104	90.14 267

BP-MVS														92.13 185

HQP4-MVS										90.14 267			98.50 239			95.78 296

HQP2-MVS												80.95 250

NP-MVS					95.99 265	89.81 206					95.87 240

MDTV_nov1_ep13_2view						70.35 435	93.10 402		83.88 384	93.55 186		82.47 224		86.25 310		98.38 171

ACMMP++_ref															90.30 309

ACMMP++															91.02 298

Test By Simon												88.73 103

High-resolution multi-view benchmark