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	98.08 194

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	96.20 276	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	96.24 274	98.79 7	93.99 90	95.80 128	97.65 131	89.92 87	99.24 142	95.87 92	99.20 81	98.58 147

patch_mono-2		96.83 51	97.44 20	95.01 200	99.05 41	85.39 331	96.98 204	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	90.28 190	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	98.18 180

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	90.72 175	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	98.25 175

FC-MVSNet-test		93.94 158	93.57 149	95.04 198	95.48 282	91.45 143	98.12 51	98.71 12	93.37 115	90.23 264	96.70 189	87.66 123	97.85 317	91.49 200	90.39 304	95.83 288

UniMVSNet (Re)		93.31 179	92.55 192	95.61 170	95.39 288	93.34 67	97.39 164	98.71 12	93.14 128	90.10 273	94.83 290	87.71 122	98.03 290	91.67 198	83.99 376	95.46 307

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		94.09 150	93.70 145	95.27 188	95.70 272	92.03 118	98.10 52	98.68 14	93.36 117	90.39 261	96.70 189	87.63 126	97.94 308	92.25 180	90.50 303	95.84 287

WR-MVS_H		92.00 235	91.35 232	93.95 261	95.09 315	89.47 218	98.04 59	98.68 14	91.46 182	88.34 324	94.68 297	85.86 156	97.56 346	85.77 318	84.24 374	94.82 352

fmvsm_s_conf0.5_n_4		96.75 56	97.07 28	95.79 157	97.76 135	89.57 212	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	98.08 194

VPA-MVSNet		93.24 181	92.48 197	95.51 176	95.70 272	92.39 102	97.86 85	98.66 17	92.30 155	92.09 222	95.37 265	80.49 258	98.40 244	93.95 147	85.86 347	95.75 296

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	98.59 146

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	90.43 185	97.50 145	98.59 22	96.59 7	99.31 3	99.08 7	84.47 175	99.75 51	99.37 4	98.45 126	97.88 207

UniMVSNet_NR-MVSNet		93.37 177	92.67 186	95.47 181	95.34 294	92.83 85	97.17 188	98.58 23	92.98 137	90.13 269	95.80 241	88.37 111	97.85 317	91.71 195	83.93 377	95.73 298

CSCG		96.05 84	95.91 84	96.46 111	99.24 30	90.47 182	98.30 29	98.57 24	89.01 269	93.97 177	97.57 139	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	90.32 189	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		93.66 168	92.92 174	95.87 151	98.24 94	89.88 203	94.58 348	98.49 27	85.06 365	93.78 180	95.78 245	82.86 210	98.67 222	91.77 193	95.71 207	99.07 93

CHOSEN 1792x2688		94.15 145	93.51 155	96.06 139	98.27 90	89.38 223	95.18 334	98.48 29	85.60 355	93.76 181	97.11 168	83.15 200	99.61 83	91.33 203	98.72 112	99.19 78

fmvsm_s_conf0.5_n_7		96.45 71	96.80 51	95.37 184	97.29 162	88.38 255	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	98.02 198

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	89.86 241	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	96.67 209	90.25 191	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	98.15 184

PVSNet_BlendedMVS		94.06 151	93.92 141	94.47 231	98.27 90	89.46 220	96.73 227	98.36 34	90.17 233	94.36 166	95.24 273	88.02 116	99.58 91	93.44 158	90.72 299	94.36 372

PVSNet_Blended		94.87 126	94.56 124	95.81 156	98.27 90	89.46 220	95.47 317	98.36 34	88.84 277	94.36 166	96.09 230	88.02 116	99.58 91	93.44 158	98.18 138	98.40 167

3Dnovator	91.36 5	95.19 114	94.44 132	97.44 53	96.56 219	93.36 66	98.65 12	98.36 34	94.12 85	89.25 303	98.06 91	82.20 227	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	95.48 282	90.69 176	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	98.18 180

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	96.62 211	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	97.43 234

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	95.67 274	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	90.86 169	97.27 176	98.25 55	90.21 232	94.18 171	97.27 157	87.48 133	99.73 54	93.53 155	97.77 154	98.55 148

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		91.55 255	90.84 256	93.69 277	94.96 319	88.28 258	97.84 89	98.24 57	91.46 182	88.04 334	95.80 241	79.67 274	97.48 354	87.02 298	84.54 371	95.31 321

DU-MVS		92.90 199	92.04 208	95.49 178	94.95 320	92.83 85	97.16 189	98.24 57	93.02 131	90.13 269	95.71 248	83.47 192	97.85 317	91.71 195	83.93 377	95.78 292

9.14			96.75 55		98.93 52		97.73 108	98.23 60	91.28 191	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		91.30 272	90.95 250	92.35 325	94.71 335	85.52 327	96.18 278	98.21 61	88.89 275	86.60 363	93.82 346	79.92 270	97.95 306	89.29 247	90.95 296	93.56 387

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		94.17 143	93.61 148	95.86 153	98.09 109	91.37 145	97.35 168	98.20 63	93.18 125	91.79 230	97.28 155	79.13 282	98.93 189	94.61 136	92.84 262	97.28 242

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		91.71 244	89.67 309	97.81 28	99.38 14	94.03 50	98.59 13	98.20 63	94.85 50	96.59 92	32.69 447	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		91.89 240	91.24 239	93.82 269	95.05 316	88.57 248	97.82 94	98.19 68	91.70 175	88.21 330	95.76 246	81.96 231	97.52 352	87.86 273	84.65 365	95.37 317

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	90.57 224	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		91.20 277	90.44 273	93.48 288	94.49 343	87.91 273	97.76 102	98.18 70	91.29 188	87.78 338	95.74 247	80.35 261	97.33 365	85.46 322	82.96 387	95.19 332

DELS-MVS		96.61 65	96.38 74	97.30 59	97.79 133	93.19 74	95.96 289	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		89.70 328	88.40 334	93.60 281	95.15 311	90.10 193	97.56 136	98.16 74	87.28 328	86.16 368	94.63 301	77.57 310	98.05 286	74.48 408	84.59 369	92.65 400

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	85.29 164	99.53 105	95.81 97	95.27 216	99.16 80

DeepPCF-MVS	93.97 1	96.61 65	97.09 27	95.15 192	98.09 109	86.63 304	96.00 287	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	97.41 361	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	90.36 222	97.35 166	99.11 88

QAPM		93.45 175	92.27 202	96.98 81	96.77 204	92.62 94	98.39 25	98.12 80	84.50 373	88.27 328	97.77 121	82.39 224	99.81 30	85.40 323	98.81 108	98.51 153

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	82.28 225	98.92 191	91.45 202	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	92.86 202	91.68 222	96.40 115	95.34 294	92.73 90	98.27 33	98.12 80	84.86 368	85.78 370	97.75 122	78.89 292	99.74 52	87.50 288	98.65 115	96.73 259

TranMVSNet+NR-MVSNet		92.50 211	91.63 223	95.14 193	94.76 331	92.07 115	97.53 142	98.11 83	92.90 141	89.56 291	96.12 225	83.16 199	97.60 344	89.30 246	83.20 386	95.75 296

CPTT-MVS		95.57 102	95.19 105	96.70 86	99.27 28	91.48 140	98.33 27	98.11 83	87.79 313	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	91.50 180	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	89.22 262	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	88.35 295	95.09 149	97.65 131	89.97 86	99.48 117	92.08 187	98.59 119	98.44 164

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		92.34 219	91.27 238	95.53 175	94.95 320	93.05 77	97.39 164	98.07 92	92.65 149	84.46 381	95.71 248	85.00 168	97.77 328	89.71 234	83.52 383	95.78 292

MP-MVS-pluss		96.70 59	96.27 77	97.98 22	99.23 32	94.71 29	96.96 206	98.06 95	90.67 215	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	90.57 224	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	91.17 196	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		94.51 135	93.80 143	96.64 88	97.07 174	91.97 120	96.32 266	98.06 95	88.94 273	94.50 163	96.78 184	84.60 172	99.27 140	91.90 188	96.02 197	98.68 140

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	93.38 190	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		88.98 334	87.05 348	94.77 218	94.45 345	87.19 289	90.23 422	98.03 104	77.87 420	92.40 208	87.55 427	80.17 265	99.51 110	68.84 427	93.95 249	97.60 227

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

TEST9					98.70 61	94.19 42	96.41 255	98.02 107	88.17 299	96.03 118	97.56 141	92.74 33	99.59 88

train_agg		96.30 79	95.83 87	97.72 39	98.70 61	94.19 42	96.41 255	98.02 107	88.58 286	96.03 118	97.56 141	92.73 34	99.59 88	95.04 118	99.37 62	99.39 63

test_8					98.67 63	94.06 49	96.37 262	98.01 110	88.58 286	95.98 122	97.55 143	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		92.34 219	91.53 227	94.77 218	95.13 313	90.83 170	96.40 259	97.98 113	91.88 170	89.29 300	95.54 259	82.50 220	97.80 324	89.79 233	85.27 356	95.69 299

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		93.95 157	93.06 170	96.63 92	99.07 39	91.61 133	97.46 156	97.96 115	77.99 418	93.00 199	97.57 139	86.14 154	99.33 132	89.22 250	99.15 88	98.94 110

IU-MVS					99.42 7	95.39 11		97.94 117	90.40 230	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	90.37 188	97.53 142	97.92 120	96.52 8	99.14 12	99.08 7	83.21 197	99.74 52	99.22 8	98.06 143	97.88 207

Anonymous20231211		90.63 301	89.42 316	94.27 245	98.24 94	89.19 235	98.05 58	97.89 121	79.95 410	88.25 329	94.96 282	72.56 350	98.13 269	89.70 235	85.14 358	95.49 303

原ACMM1				96.38 118	98.59 71	91.09 161		97.89 121	87.41 324	95.22 146	97.68 127	90.25 81	99.54 103	87.95 272	99.12 93	98.49 156

CDPH-MVS		95.97 88	95.38 100	97.77 34	98.93 52	94.44 35	96.35 263	97.88 123	86.98 332	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	95.71 165	97.06 177	89.63 208	97.82 94	97.87 125	93.57 103	93.92 178	95.04 279	90.61 78	98.95 186	94.62 135	98.68 113	98.54 149

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	98.71 219	97.10 49	99.17 84	98.90 119

无先验							95.79 299	97.87 125	83.87 381				99.65 72	87.68 282		98.89 123

3Dnovator+	91.43 4	95.40 104	94.48 130	98.16 16	96.90 190	95.34 16	98.48 21	97.87 125	94.65 67	88.53 320	98.02 96	83.69 188	99.71 60	93.18 164	98.96 103	99.44 56

VPNet		92.23 227	91.31 235	94.99 201	95.56 278	90.96 165	97.22 184	97.86 129	92.96 138	90.96 252	96.62 201	75.06 330	98.20 263	91.90 188	83.65 382	95.80 290

test_vis1_n_1920		94.17 143	94.58 123	92.91 309	97.42 159	82.02 378	97.83 92	97.85 130	94.68 64	98.10 41	98.49 51	70.15 369	99.32 134	97.91 27	98.82 107	97.40 236

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	98.75 212	96.92 53	99.33 64	98.94 110

test_fmvsmconf0.01_n		96.15 82	95.85 86	97.03 79	92.66 396	91.83 124	97.97 72	97.84 134	95.57 23	97.53 54	99.00 14	84.20 181	99.76 47	98.82 20	99.08 95	99.48 51

GDP-MVS		95.62 99	95.13 107	97.09 75	96.79 201	93.26 72	97.89 83	97.83 135	93.58 102	96.80 78	97.82 117	83.06 204	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	97.36 152	90.97 72	99.22 144	97.74 29	99.66 10	98.61 143

AdaColmap		94.34 139	93.68 146	96.31 122	98.59 71	91.68 131	96.59 246	97.81 137	89.87 240	92.15 218	97.06 171	83.62 191	99.54 103	89.34 245	98.07 142	97.70 220

MVSMamba_PlusPlus		96.51 68	96.48 66	96.59 96	98.07 113	91.97 120	98.14 50	97.79 138	90.43 228	97.34 63	97.52 144	91.29 64	99.19 147	98.12 25	99.64 14	98.60 144

KinetiMVS		95.26 109	94.75 118	96.79 84	96.99 185	92.05 116	97.82 94	97.78 139	94.77 60	96.46 101	97.70 125	80.62 255	99.34 131	92.37 177	98.28 133	98.97 103

mamv4		94.66 133	96.10 81	90.37 378	98.01 116	73.41 427	96.82 219	97.78 139	89.95 239	94.52 162	97.43 148	92.91 27	99.09 167	98.28 24	99.16 87	98.60 144

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	94.51 307	91.23 67	98.92 191	95.65 103	98.19 137	97.82 215

新几何1				97.32 58	98.60 70	93.59 59		97.75 142	81.58 401	95.75 130	97.85 113	90.04 84	99.67 70	86.50 304	99.13 91	98.69 139

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	97.01 183	91.52 138	98.89 5	97.75 142	94.42 77	96.64 89	97.68 127	89.32 92	98.60 229	97.45 43	99.11 94	98.67 141

EI-MVSNet-Vis-set		96.51 68	96.47 67	96.63 92	98.24 94	91.20 153	96.89 211	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	90.68 177	97.24 178	97.73 145	91.80 171	92.93 204	96.62 201	89.13 95	99.14 159	89.21 251	97.78 153	98.97 103

Anonymous20240529		91.98 236	90.73 263	95.73 163	98.14 106	89.40 222	97.99 63	97.72 147	79.63 412	93.54 185	97.41 150	69.94 371	99.56 99	91.04 210	91.11 292	98.22 177

CHOSEN 280x420		93.12 187	92.72 185	94.34 239	96.71 208	87.27 285	90.29 421	97.72 147	86.61 339	91.34 241	95.29 267	84.29 180	98.41 243	93.25 162	98.94 104	97.35 239

EI-MVSNet-UG-set		96.34 77	96.30 76	96.47 109	98.20 100	90.93 167	96.86 214	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		93.57 171	92.61 190	96.47 109	97.59 150	91.61 133	97.67 118	97.72 147	85.17 363	90.29 263	98.34 68	84.60 172	99.73 54	83.85 346	98.27 134	98.06 196

PAPR		94.18 142	93.42 161	96.48 108	97.64 144	91.42 144	95.55 312	97.71 151	88.99 270	92.34 214	95.82 240	89.19 93	99.11 162	86.14 310	97.38 164	98.90 119

UGNet		94.04 153	93.28 164	96.31 122	96.85 193	91.19 154	97.88 84	97.68 152	94.40 79	93.00 199	96.18 220	73.39 347	99.61 83	91.72 194	98.46 125	98.13 185
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				95.46 182	98.18 104	88.90 241		97.66 153	82.73 392	97.03 74	98.07 90	90.06 83	98.85 198	89.67 236	98.98 102	98.64 142

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		90.56 302	89.75 307	93.01 305	93.95 358	87.25 286	97.64 126	97.65 155	90.74 210	87.12 351	95.68 251	79.97 269	97.00 377	83.33 347	81.66 393	94.78 359

TAPA-MVS	90.10 7	92.30 222	91.22 241	95.56 172	98.33 86	89.60 210	96.79 221	97.65 155	81.83 398	91.52 236	97.23 160	87.94 118	98.91 193	71.31 422	98.37 129	98.17 183
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 188	92.45 198	95.05 197	98.09 109	89.21 232	96.89 211	97.64 157	93.18 125	91.79 230	97.28 155	75.35 329	98.65 224	88.99 256	92.84 262	97.28 242

test_cas_vis1_n_1920		94.48 137	94.55 127	94.28 244	96.78 202	86.45 309	97.63 128	97.64 157	93.32 118	97.68 53	98.36 64	73.75 345	99.08 170	96.73 59	99.05 97	97.31 241

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	85.34 162	99.50 113	94.99 121	99.21 76	98.97 103

Elysia		94.00 155	93.12 167	96.64 88	96.08 258	92.72 91	97.50 145	97.63 159	91.15 198	94.82 153	97.12 166	74.98 332	99.06 176	90.78 213	98.02 144	98.12 187

StellarMVS		94.00 155	93.12 167	96.64 88	96.08 258	92.72 91	97.50 145	97.63 159	91.15 198	94.82 153	97.12 166	74.98 332	99.06 176	90.78 213	98.02 144	98.12 187

cdsmvs_eth3d_5k		23.24 417	30.99 419	0.00 435	0.00 458	0.00 460	0.00 446	97.63 159	0.00 453	0.00 454	96.88 180	84.38 177	0.00 454	0.00 453	0.00 452	0.00 450

DPM-MVS		95.69 96	94.92 112	98.01 20	98.08 112	95.71 9	95.27 328	97.62 163	90.43 228	95.55 139	97.07 170	91.72 51	99.50 113	89.62 238	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	96.12 225	87.65 124	99.18 150	96.20 80	94.82 225	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	96.12 225	87.65 124	99.18 150	96.20 80	94.82 225	98.91 116

test222					98.24 94	92.21 110	95.33 323	97.60 164	79.22 414	95.25 144	97.84 115	88.80 101			99.15 88	98.72 136

cascas		91.20 277	90.08 290	94.58 227	94.97 318	89.16 236	93.65 386	97.59 167	79.90 411	89.40 295	92.92 372	75.36 328	98.36 251	92.14 183	94.75 228	96.23 269

h-mvs33		94.15 145	93.52 154	96.04 141	97.81 132	90.22 192	97.62 130	97.58 168	95.19 33	96.74 82	97.45 145	83.67 189	99.61 83	95.85 94	79.73 400	98.29 174

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	96.16 223	87.54 129	99.17 152	96.19 82	94.73 230	98.91 116

MVSFormer		95.37 105	95.16 106	95.99 148	96.34 241	91.21 151	98.22 41	97.57 169	91.42 184	96.22 111	97.32 153	86.20 152	97.92 311	94.07 144	99.05 97	98.85 127

test_djsdf		93.07 190	92.76 180	94.00 256	93.49 375	88.70 245	98.22 41	97.57 169	91.42 184	90.08 275	95.55 258	82.85 211	97.92 311	94.07 144	91.58 283	95.40 314

OMC-MVS		95.09 116	94.70 119	96.25 131	98.46 75	91.28 147	96.43 253	97.57 169	92.04 166	94.77 157	97.96 101	87.01 141	99.09 167	91.31 204	96.77 183	98.36 171

PS-MVSNAJss		93.74 166	93.51 155	94.44 233	93.91 360	89.28 230	97.75 104	97.56 173	92.50 151	89.94 277	96.54 204	88.65 104	98.18 266	93.83 153	90.90 297	95.86 284

casdiffmvs_mvg		95.81 95	95.57 89	96.51 105	96.87 191	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		92.42 215	91.89 215	94.03 255	93.33 383	88.50 252	97.73 108	97.53 175	92.00 168	88.85 312	96.50 206	75.62 327	98.11 273	93.88 151	91.56 284	95.48 304

mvs_tets		92.31 221	91.76 218	93.94 263	93.41 380	88.29 257	97.63 128	97.53 175	92.04 166	88.76 315	96.45 208	74.62 337	98.09 278	93.91 149	91.48 285	95.45 309

dcpmvs_2		96.37 75	97.05 32	94.31 242	98.96 51	84.11 352	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		93.78 165	93.43 159	94.82 211	96.21 245	89.99 197	97.74 106	97.51 177	94.85 50	91.34 241	96.64 194	81.32 243	98.60 229	93.02 170	92.23 271	95.86 284

plane_prior5								97.51 177					98.60 229	93.02 170	92.23 271	95.86 284

reproduce_monomvs		91.30 272	91.10 245	91.92 339	96.82 198	82.48 372	97.01 201	97.49 180	94.64 68	88.35 323	95.27 270	70.53 364	98.10 274	95.20 114	84.60 368	95.19 332

PS-MVSNAJ		95.37 105	95.33 102	95.49 178	97.35 160	90.66 178	95.31 325	97.48 181	93.85 95	96.51 97	95.70 250	88.65 104	99.65 72	94.80 130	98.27 134	96.17 273

API-MVS		94.84 127	94.49 129	95.90 150	97.90 127	92.00 119	97.80 98	97.48 181	89.19 263	94.81 155	96.71 187	88.84 100	99.17 152	88.91 258	98.76 111	96.53 262

MG-MVS		95.61 100	95.38 100	96.31 122	98.42 79	90.53 180	96.04 284	97.48 181	93.47 112	95.67 136	98.10 87	89.17 94	99.25 141	91.27 205	98.77 110	99.13 84

MAR-MVS		94.22 141	93.46 157	96.51 105	98.00 118	92.19 113	97.67 118	97.47 184	88.13 303	93.00 199	95.84 238	84.86 170	99.51 110	87.99 271	98.17 139	97.83 214
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		92.98 194	92.53 194	94.32 240	96.12 255	89.20 233	95.28 326	97.47 184	92.66 148	89.90 278	95.62 254	80.58 256	98.40 244	92.73 175	92.40 269	95.38 316
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 270	90.22 286	94.68 221	94.86 327	87.86 274	97.23 182	97.46 186	87.99 304	89.90 278	96.92 178	66.35 399	98.23 260	90.30 223	90.99 295	97.96 201

nrg030		94.05 152	93.31 163	96.27 127	95.22 305	94.59 32	98.34 26	97.46 186	92.93 139	91.21 250	96.64 194	87.23 139	98.22 261	94.99 121	85.80 348	95.98 283

XVG-OURS		93.72 167	93.35 162	94.80 216	97.07 174	88.61 246	94.79 343	97.46 186	91.97 169	93.99 175	97.86 112	81.74 237	98.88 195	92.64 176	92.67 267	96.92 254

LPG-MVS_test		92.94 197	92.56 191	94.10 250	96.16 250	88.26 259	97.65 122	97.46 186	91.29 188	90.12 271	97.16 163	79.05 285	98.73 215	92.25 180	91.89 279	95.31 321

LGP-MVS_train				94.10 250	96.16 250	88.26 259		97.46 186	91.29 188	90.12 271	97.16 163	79.05 285	98.73 215	92.25 180	91.89 279	95.31 321

MVS		91.71 244	90.44 273	95.51 176	95.20 307	91.59 135	96.04 284	97.45 191	73.44 428	87.36 347	95.60 255	85.42 161	99.10 164	85.97 315	97.46 159	95.83 288

XVG-OURS-SEG-HR		93.86 162	93.55 150	94.81 213	97.06 177	88.53 251	95.28 326	97.45 191	91.68 176	94.08 174	97.68 127	82.41 223	98.90 194	93.84 152	92.47 268	96.98 250

baseline		95.58 101	95.42 98	96.08 137	96.78 202	90.41 186	97.16 189	97.45 191	93.69 101	95.65 137	97.85 113	87.29 137	98.68 221	95.66 100	97.25 172	99.13 84

ab-mvs		93.57 171	92.55 192	96.64 88	97.28 163	91.96 122	95.40 319	97.45 191	89.81 245	93.22 196	96.28 216	79.62 276	99.46 119	90.74 216	93.11 259	98.50 154

xiu_mvs_v2_base		95.32 107	95.29 103	95.40 183	97.22 165	90.50 181	95.44 318	97.44 195	93.70 100	96.46 101	96.18 220	88.59 108	99.53 105	94.79 132	97.81 152	96.17 273

1314		92.81 206	92.03 209	95.14 193	95.33 297	89.52 217	96.04 284	97.44 195	87.72 317	86.25 367	95.33 266	83.84 186	98.79 206	89.26 248	97.05 178	97.11 248

casdiffmvs		95.64 98	95.49 92	96.08 137	96.76 207	90.45 183	97.29 175	97.44 195	94.00 89	95.46 143	97.98 99	87.52 132	98.73 215	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		92.16 229	91.23 240	94.95 207	94.75 332	90.94 166	97.47 154	97.43 198	89.14 264	88.90 308	96.43 209	79.71 273	98.24 259	89.56 239	87.68 329	95.67 300

anonymousdsp		92.16 229	91.55 226	93.97 259	92.58 398	89.55 214	97.51 144	97.42 199	89.42 257	88.40 322	94.84 289	80.66 254	97.88 316	91.87 190	91.28 289	94.48 367

Effi-MVS+		94.93 122	94.45 131	96.36 120	96.61 212	91.47 141	96.41 255	97.41 200	91.02 204	94.50 163	95.92 234	87.53 130	98.78 207	93.89 150	96.81 182	98.84 130

RRT-MVS		94.51 135	94.35 134	94.98 203	96.40 236	86.55 307	97.56 136	97.41 200	93.19 123	94.93 150	97.04 172	79.12 283	99.30 138	96.19 82	97.32 169	99.09 90

HQP3-MVS								97.39 202							92.10 276

HQP-MVS		93.19 184	92.74 183	94.54 229	95.86 264	89.33 226	96.65 237	97.39 202	93.55 104	90.14 265	95.87 236	80.95 247	98.50 237	92.13 184	92.10 276	95.78 292

PLC	91.00 6	94.11 149	93.43 159	96.13 136	98.58 73	91.15 160	96.69 233	97.39 202	87.29 327	91.37 240	96.71 187	88.39 109	99.52 109	87.33 291	97.13 176	97.73 218
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 294	89.86 300	93.45 290	93.54 372	87.60 280	97.70 116	97.37 205	88.85 276	87.65 340	94.08 337	81.08 246	98.10 274	84.68 332	83.79 381	94.66 364

UnsupCasMVSNet_eth		85.99 370	84.45 374	90.62 374	89.97 416	82.40 375	93.62 387	97.37 205	89.86 241	78.59 418	92.37 382	65.25 407	95.35 409	82.27 360	70.75 426	94.10 378

ACMM	89.79 8	92.96 195	92.50 196	94.35 237	96.30 243	88.71 244	97.58 132	97.36 207	91.40 186	90.53 258	96.65 193	79.77 272	98.75 212	91.24 206	91.64 281	95.59 302
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	95.75 160	96.58 215	91.71 128	96.25 271	97.35 208	92.99 132	96.70 84	96.63 198	82.67 215	99.44 122	96.22 75	97.46 159	96.11 279

xiu_mvs_v1_base		95.01 117	94.76 115	95.75 160	96.58 215	91.71 128	96.25 271	97.35 208	92.99 132	96.70 84	96.63 198	82.67 215	99.44 122	96.22 75	97.46 159	96.11 279

xiu_mvs_v1_base_debi		95.01 117	94.76 115	95.75 160	96.58 215	91.71 128	96.25 271	97.35 208	92.99 132	96.70 84	96.63 198	82.67 215	99.44 122	96.22 75	97.46 159	96.11 279

diffmvs		95.25 110	95.13 107	95.63 168	96.43 235	89.34 225	95.99 288	97.35 208	92.83 143	96.31 107	97.37 151	86.44 147	98.67 222	96.26 72	97.19 174	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		94.71 132	94.02 139	96.79 84	97.71 138	92.05 116	96.59 246	97.35 208	90.61 221	94.64 159	96.93 175	86.41 148	99.39 127	91.20 207	94.71 231	98.94 110

F-COLMAP		93.58 170	92.98 172	95.37 184	98.40 81	88.98 239	97.18 187	97.29 213	87.75 316	90.49 259	97.10 169	85.21 165	99.50 113	86.70 301	96.72 186	97.63 222

VortexMVS		92.88 201	92.64 187	93.58 283	96.58 215	87.53 281	96.93 208	97.28 214	92.78 146	89.75 283	94.99 280	82.73 214	97.76 329	94.60 137	88.16 324	95.46 307

XVG-ACMP-BASELINE		90.93 290	90.21 287	93.09 303	94.31 351	85.89 320	95.33 323	97.26 215	91.06 203	89.38 296	95.44 264	68.61 382	98.60 229	89.46 241	91.05 293	94.79 357

PCF-MVS	89.48 11	91.56 254	89.95 297	96.36 120	96.60 213	92.52 99	92.51 406	97.26 215	79.41 413	88.90 308	96.56 203	84.04 185	99.55 101	77.01 399	97.30 170	97.01 249
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 210	92.14 205	94.05 253	96.40 236	88.20 262	97.36 167	97.25 217	91.52 179	88.30 326	96.64 194	78.46 297	98.72 218	91.86 191	91.48 285	95.23 328
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		93.28 180	92.76 180	94.82 211	94.63 338	90.77 173	96.65 237	97.18 218	93.72 98	91.68 234	97.26 158	79.33 280	98.63 226	92.13 184	92.28 270	95.07 335
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 199	92.02 210	95.56 172	98.19 102	90.80 171	95.27 328	97.18 218	87.96 305	91.86 229	95.68 251	80.44 259	98.99 184	84.01 341	97.54 158	96.89 255

alignmvs		95.87 94	95.23 104	97.78 32	97.56 156	95.19 21	97.86 85	97.17 220	94.39 80	96.47 100	96.40 211	85.89 155	99.20 146	96.21 79	95.11 221	98.95 109

MVS_Test		94.89 124	94.62 121	95.68 166	96.83 196	89.55 214	96.70 231	97.17 220	91.17 196	95.60 138	96.11 229	87.87 121	98.76 211	93.01 172	97.17 175	98.72 136

Fast-Effi-MVS+		93.46 174	92.75 182	95.59 171	96.77 204	90.03 194	96.81 220	97.13 222	88.19 298	91.30 244	94.27 325	86.21 151	98.63 226	87.66 283	96.46 193	98.12 187

EI-MVSNet		93.03 192	92.88 176	93.48 288	95.77 270	86.98 294	96.44 251	97.12 223	90.66 217	91.30 244	97.64 134	86.56 144	98.05 286	89.91 229	90.55 301	95.41 311

MVSTER		93.20 183	92.81 179	94.37 236	96.56 219	89.59 211	97.06 195	97.12 223	91.24 192	91.30 244	95.96 232	82.02 230	98.05 286	93.48 157	90.55 301	95.47 306

test_yl		94.78 130	94.23 136	96.43 113	97.74 136	91.22 149	96.85 215	97.10 225	91.23 193	95.71 132	96.93 175	84.30 178	99.31 136	93.10 165	95.12 219	98.75 133

DCV-MVSNet		94.78 130	94.23 136	96.43 113	97.74 136	91.22 149	96.85 215	97.10 225	91.23 193	95.71 132	96.93 175	84.30 178	99.31 136	93.10 165	95.12 219	98.75 133

LTVRE_ROB	88.41 13	90.99 286	89.92 299	94.19 246	96.18 248	89.55 214	96.31 267	97.09 227	87.88 308	85.67 371	95.91 235	78.79 293	98.57 233	81.50 363	89.98 306	94.44 370
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		92.73 208	92.88 176	92.29 329	96.08 258	81.05 386	97.98 66	97.08 228	90.72 212	96.79 80	98.18 84	63.07 411	98.45 241	97.62 37	98.42 128	97.36 237

v10		91.04 284	90.23 284	93.49 287	94.12 354	88.16 265	97.32 172	97.08 228	88.26 297	88.29 327	94.22 330	82.17 228	97.97 298	86.45 305	84.12 375	94.33 373

v144192		91.06 283	90.28 280	93.39 291	93.66 369	87.23 288	96.83 218	97.07 230	87.43 323	89.69 286	94.28 324	81.48 240	98.00 293	87.18 295	84.92 364	94.93 343

v1192		91.07 282	90.23 284	93.58 283	93.70 366	87.82 276	96.73 227	97.07 230	87.77 314	89.58 289	94.32 322	80.90 251	97.97 298	86.52 303	85.48 351	94.95 339

v8		91.29 274	90.53 272	93.57 285	94.15 353	88.12 266	97.34 169	97.06 232	88.99 270	88.32 325	94.26 327	83.08 202	98.01 292	87.62 285	83.92 379	94.57 366

mvs_anonymous		93.82 163	93.74 144	94.06 252	96.44 234	85.41 329	95.81 297	97.05 233	89.85 243	90.09 274	96.36 213	87.44 134	97.75 331	93.97 146	96.69 187	99.02 95

IterMVS-LS		92.29 223	91.94 213	93.34 293	96.25 244	86.97 295	96.57 249	97.05 233	90.67 215	89.50 294	94.80 292	86.59 143	97.64 339	89.91 229	86.11 346	95.40 314
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 292	90.03 295	93.29 295	93.55 371	86.96 296	96.74 226	97.04 235	87.36 325	89.52 293	94.34 319	80.23 264	97.97 298	86.27 306	85.21 357	94.94 341

CDS-MVSNet		94.14 148	93.54 151	95.93 149	96.18 248	91.46 142	96.33 265	97.04 235	88.97 272	93.56 183	96.51 205	87.55 128	97.89 315	89.80 232	95.95 199	98.44 164
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 327	89.26 320	91.19 363	95.16 308	80.29 397	94.53 350	97.03 237	91.79 172	88.86 311	94.10 334	69.94 371	97.82 321	85.29 324	86.66 342	95.45 309

v1144		91.37 267	90.60 268	93.68 278	93.89 361	88.23 261	96.84 217	97.03 237	88.37 294	89.69 286	94.39 314	82.04 229	97.98 295	87.80 275	85.37 353	94.84 349

v1240		90.70 298	89.85 301	93.23 297	93.51 374	86.80 297	96.61 243	97.02 239	87.16 330	89.58 289	94.31 323	79.55 277	97.98 295	85.52 321	85.44 352	94.90 346

EPP-MVSNet		95.22 112	95.04 110	95.76 158	97.49 157	89.56 213	98.67 11	97.00 240	90.69 213	94.24 169	97.62 136	89.79 89	98.81 204	93.39 161	96.49 191	98.92 115

V42		91.58 253	90.87 252	93.73 273	94.05 357	88.50 252	97.32 172	96.97 241	88.80 282	89.71 284	94.33 320	82.54 219	98.05 286	89.01 255	85.07 360	94.64 365

test_fmvs1		93.21 182	93.53 152	92.25 332	96.55 221	81.20 385	97.40 163	96.96 242	90.68 214	96.80 78	98.04 93	69.25 377	98.40 244	97.58 38	98.50 121	97.16 247

FMVSNet2		91.31 271	90.08 290	94.99 201	96.51 227	92.21 110	97.41 159	96.95 243	88.82 279	88.62 317	94.75 294	73.87 341	97.42 360	85.20 327	88.55 321	95.35 318

ACMH	87.59 16	90.53 303	89.42 316	93.87 267	96.21 245	87.92 271	97.24 178	96.94 244	88.45 292	83.91 391	96.27 217	71.92 353	98.62 228	84.43 335	89.43 312	95.05 337
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 268	90.27 281	94.59 223	96.51 227	91.18 156	97.50 145	96.93 245	88.82 279	89.35 297	94.51 307	73.87 341	97.29 367	86.12 311	88.82 316	95.31 321

test1		91.35 268	90.27 281	94.59 223	96.51 227	91.18 156	97.50 145	96.93 245	88.82 279	89.35 297	94.51 307	73.87 341	97.29 367	86.12 311	88.82 316	95.31 321

FMVSNet3		91.78 242	90.69 266	95.03 199	96.53 224	92.27 108	97.02 198	96.93 245	89.79 246	89.35 297	94.65 300	77.01 313	97.47 355	86.12 311	88.82 316	95.35 318

FMVSNet1		89.88 322	88.31 335	94.59 223	95.41 287	91.18 156	97.50 145	96.93 245	86.62 338	87.41 345	94.51 307	65.94 404	97.29 367	83.04 350	87.43 332	95.31 321

GeoE		93.89 160	93.28 164	95.72 164	96.96 188	89.75 206	98.24 39	96.92 249	89.47 254	92.12 220	97.21 161	84.42 176	98.39 249	87.71 278	96.50 190	99.01 98

SymmetryMVS		95.94 90	95.54 90	97.15 70	97.85 129	92.90 83	97.99 63	96.91 250	95.92 13	96.57 95	97.93 102	85.34 162	99.50 113	94.99 121	96.39 194	99.05 94

miper_enhance_ethall		91.54 257	91.01 248	93.15 301	95.35 293	87.07 293	93.97 372	96.90 251	86.79 336	89.17 304	93.43 366	86.55 145	97.64 339	89.97 228	86.93 337	94.74 361

eth_miper_zixun_eth		91.02 285	90.59 269	92.34 327	95.33 297	84.35 348	94.10 369	96.90 251	88.56 288	88.84 313	94.33 320	84.08 183	97.60 344	88.77 261	84.37 373	95.06 336

TAMVS		94.01 154	93.46 157	95.64 167	96.16 250	90.45 183	96.71 230	96.89 253	89.27 261	93.46 188	96.92 178	87.29 137	97.94 308	88.70 263	95.74 205	98.53 150

miper_ehance_all_eth		91.59 251	91.13 244	92.97 307	95.55 279	86.57 305	94.47 353	96.88 254	87.77 314	88.88 310	94.01 339	86.22 150	97.54 348	89.49 240	86.93 337	94.79 357

v2v482		91.59 251	90.85 255	93.80 270	93.87 362	88.17 264	96.94 207	96.88 254	89.54 251	89.53 292	94.90 286	81.70 238	98.02 291	89.25 249	85.04 362	95.20 329

CNLPA		94.28 140	93.53 152	96.52 101	98.38 84	92.55 98	96.59 246	96.88 254	90.13 236	91.91 226	97.24 159	85.21 165	99.09 167	87.64 284	97.83 151	97.92 204

PAPM		91.52 258	90.30 279	95.20 190	95.30 300	89.83 204	93.38 392	96.85 257	86.26 346	88.59 318	95.80 241	84.88 169	98.15 268	75.67 404	95.93 200	97.63 222

c3_l		91.38 265	90.89 251	92.88 311	95.58 277	86.30 312	94.68 345	96.84 258	88.17 299	88.83 314	94.23 328	85.65 159	97.47 355	89.36 244	84.63 366	94.89 347

pm-mvs1		90.72 297	89.65 311	93.96 260	94.29 352	89.63 208	97.79 100	96.82 259	89.07 266	86.12 369	95.48 263	78.61 295	97.78 326	86.97 299	81.67 392	94.46 368

test_vis1_n		92.37 218	92.26 203	92.72 317	94.75 332	82.64 368	98.02 60	96.80 260	91.18 195	97.77 52	97.93 102	58.02 421	98.29 257	97.63 35	98.21 136	97.23 245

CMPMVS	62.92 21	85.62 375	84.92 370	87.74 399	89.14 421	73.12 429	94.17 367	96.80 260	73.98 425	73.65 427	94.93 284	66.36 398	97.61 343	83.95 343	91.28 289	92.48 405
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 310	89.77 305	91.78 348	94.33 349	84.72 345	95.55 312	96.73 262	86.17 348	86.36 366	95.28 269	71.28 358	97.80 324	84.09 340	98.14 140	92.81 397

Effi-MVS+-dtu		93.08 189	93.21 166	92.68 320	96.02 261	83.25 362	97.14 191	96.72 263	93.85 95	91.20 251	93.44 363	83.08 202	98.30 256	91.69 197	95.73 206	96.50 264

TSAR-MVS + GP.		96.69 61	96.49 65	97.27 63	98.31 87	93.39 63	96.79 221	96.72 263	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		93.37 177	92.42 199	96.21 132	97.05 179	90.99 163	96.31 267	96.72 263	86.87 335	89.83 281	96.69 191	86.51 146	99.14 159	88.12 268	93.67 253	98.50 154

PVSNet	86.66 18	92.24 226	91.74 221	93.73 273	97.77 134	83.69 359	92.88 401	96.72 263	87.91 307	93.00 199	94.86 288	78.51 296	99.05 179	86.53 302	97.45 163	98.47 159

miper_lstm_enhance		90.50 306	90.06 294	91.83 344	95.33 297	83.74 356	93.86 378	96.70 267	87.56 321	87.79 337	93.81 347	83.45 194	96.92 379	87.39 289	84.62 367	94.82 352

v148		90.99 286	90.38 275	92.81 314	93.83 363	85.80 321	96.78 224	96.68 268	89.45 256	88.75 316	93.93 343	82.96 208	97.82 321	87.83 274	83.25 384	94.80 355

ACMH+	87.92 14	90.20 314	89.18 322	93.25 296	96.48 230	86.45 309	96.99 203	96.68 268	88.83 278	84.79 380	96.22 219	70.16 368	98.53 235	84.42 336	88.04 325	94.77 360

CANet_DTU		94.37 138	93.65 147	96.55 98	96.46 233	92.13 114	96.21 275	96.67 270	94.38 81	93.53 186	97.03 173	79.34 279	99.71 60	90.76 215	98.45 126	97.82 215

cl____		90.96 289	90.32 277	92.89 310	95.37 291	86.21 315	94.46 355	96.64 271	87.82 310	88.15 332	94.18 331	82.98 206	97.54 348	87.70 279	85.59 349	94.92 345

HY-MVS	89.66 9	93.87 161	92.95 173	96.63 92	97.10 173	92.49 100	95.64 309	96.64 271	89.05 268	93.00 199	95.79 244	85.77 158	99.45 121	89.16 254	94.35 233	97.96 201

Test_1112_low_res		92.84 204	91.84 216	95.85 154	97.04 180	89.97 200	95.53 314	96.64 271	85.38 358	89.65 288	95.18 274	85.86 156	99.10 164	87.70 279	93.58 258	98.49 156

DIV-MVS_self_test		90.97 288	90.33 276	92.88 311	95.36 292	86.19 317	94.46 355	96.63 274	87.82 310	88.18 331	94.23 328	82.99 205	97.53 350	87.72 276	85.57 350	94.93 343

Fast-Effi-MVS+-dtu		92.29 223	91.99 211	93.21 299	95.27 301	85.52 327	97.03 196	96.63 274	92.09 164	89.11 306	95.14 276	80.33 262	98.08 279	87.54 287	94.74 229	96.03 282

UnsupCasMVSNet_bld		82.13 391	79.46 396	90.14 381	88.00 429	82.47 373	90.89 419	96.62 276	78.94 415	75.61 422	84.40 433	56.63 424	96.31 391	77.30 396	66.77 434	91.63 415

cl22		91.21 276	90.56 271	93.14 302	96.09 257	86.80 297	94.41 357	96.58 277	87.80 312	88.58 319	93.99 341	80.85 252	97.62 342	89.87 231	86.93 337	94.99 338

jason		94.84 127	94.39 133	96.18 134	95.52 280	90.93 167	96.09 282	96.52 278	89.28 260	96.01 121	97.32 153	84.70 171	98.77 210	95.15 117	98.91 106	98.85 127
jason: jason.
tt0805		91.09 281	90.07 293	94.16 248	95.61 275	88.31 256	97.56 136	96.51 279	89.56 250	89.17 304	95.64 253	67.08 396	98.38 250	91.07 209	88.44 322	95.80 290

AUN-MVS		91.76 243	90.75 261	94.81 213	97.00 184	88.57 248	96.65 237	96.49 280	89.63 248	92.15 218	96.12 225	78.66 294	98.50 237	90.83 211	79.18 403	97.36 237

hse-mvs2		93.45 175	92.99 171	94.81 213	97.02 182	88.59 247	96.69 233	96.47 281	95.19 33	96.74 82	96.16 223	83.67 189	98.48 240	95.85 94	79.13 404	97.35 239

EG-PatchMatch MVS		87.02 357	85.44 362	91.76 350	92.67 395	85.00 339	96.08 283	96.45 282	83.41 388	79.52 414	93.49 360	57.10 423	97.72 333	79.34 387	90.87 298	92.56 402

KD-MVS_self_test		85.95 371	84.95 369	88.96 393	89.55 420	79.11 412	95.13 335	96.42 283	85.91 351	84.07 389	90.48 405	70.03 370	94.82 412	80.04 379	72.94 423	92.94 395

pmmvs6		87.81 349	86.19 357	92.69 319	91.32 408	86.30 312	97.34 169	96.41 284	80.59 409	84.05 390	94.37 316	67.37 391	97.67 336	84.75 331	79.51 402	94.09 380

PMMVS		92.86 202	92.34 200	94.42 235	94.92 323	86.73 300	94.53 350	96.38 285	84.78 370	94.27 168	95.12 278	83.13 201	98.40 244	91.47 201	96.49 191	98.12 187

RPSCF		90.75 295	90.86 253	90.42 377	96.84 194	76.29 420	95.61 310	96.34 286	83.89 379	91.38 239	97.87 110	76.45 318	98.78 207	87.16 296	92.23 271	96.20 271

BP-MVS1		95.89 92	95.49 92	97.08 77	96.67 209	93.20 73	98.08 54	96.32 287	94.56 69	96.32 106	97.84 115	84.07 184	99.15 156	96.75 58	98.78 109	98.90 119

MSDG		91.42 263	90.24 283	94.96 206	97.15 171	88.91 240	93.69 384	96.32 287	85.72 354	86.93 360	96.47 207	80.24 263	98.98 185	80.57 376	95.05 222	96.98 250

WBMVS		90.69 300	89.99 296	92.81 314	96.48 230	85.00 339	95.21 333	96.30 289	89.46 255	89.04 307	94.05 338	72.45 351	97.82 321	89.46 241	87.41 334	95.61 301

OurMVSNet-221017-0		90.51 305	90.19 288	91.44 356	93.41 380	81.25 383	96.98 204	96.28 290	91.68 176	86.55 364	96.30 215	74.20 340	97.98 295	88.96 257	87.40 335	95.09 334

MVP-Stereo		90.74 296	90.08 290	92.71 318	93.19 385	88.20 262	95.86 294	96.27 291	86.07 349	84.86 379	94.76 293	77.84 308	97.75 331	83.88 345	98.01 146	92.17 412
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	96.34 241	91.21 151	95.83 296	96.27 291	88.93 274	96.22 111	96.88 180	86.20 152	98.85 198	95.27 113	99.05 97	98.82 131

BH-untuned		92.94 197	92.62 189	93.92 266	97.22 165	86.16 318	96.40 259	96.25 293	90.06 237	89.79 282	96.17 222	83.19 198	98.35 252	87.19 294	97.27 171	97.24 244

CL-MVSNet_self_test		86.31 366	85.15 366	89.80 385	88.83 424	81.74 381	93.93 375	96.22 294	86.67 337	85.03 377	90.80 403	78.09 304	94.50 413	74.92 407	71.86 425	93.15 393

IS-MVSNet		94.90 123	94.52 128	96.05 140	97.67 140	90.56 179	98.44 22	96.22 294	93.21 120	93.99 175	97.74 123	85.55 160	98.45 241	89.98 227	97.86 150	99.14 83

FA-MVS(test-final)		93.52 173	92.92 174	95.31 187	96.77 204	88.54 250	94.82 342	96.21 296	89.61 249	94.20 170	95.25 272	83.24 196	99.14 159	90.01 226	96.16 196	98.25 175

GA-MVS		91.38 265	90.31 278	94.59 223	94.65 337	87.62 279	94.34 360	96.19 297	90.73 211	90.35 262	93.83 344	71.84 354	97.96 302	87.22 293	93.61 256	98.21 178

LuminaMVS		94.89 124	94.35 134	96.53 99	95.48 282	92.80 87	96.88 213	96.18 298	92.85 142	95.92 124	96.87 182	81.44 241	98.83 201	96.43 70	97.10 177	97.94 203

IterMVS-SCA-FT		90.31 308	89.81 303	91.82 345	95.52 280	84.20 351	94.30 363	96.15 299	90.61 221	87.39 346	94.27 325	75.80 324	96.44 389	87.34 290	86.88 341	94.82 352

IterMVS		90.15 316	89.67 309	91.61 352	95.48 282	83.72 357	94.33 361	96.12 300	89.99 238	87.31 349	94.15 333	75.78 326	96.27 392	86.97 299	86.89 340	94.83 350
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 207	91.51 230	96.52 101	98.77 58	90.99 163	97.38 166	96.08 301	82.38 394	89.29 300	97.87 110	83.77 187	99.69 66	81.37 369	96.69 187	98.89 123

pmmvs4		90.93 290	89.85 301	94.17 247	93.34 382	90.79 172	94.60 347	96.02 302	84.62 371	87.45 343	95.15 275	81.88 235	97.45 357	87.70 279	87.87 327	94.27 377

ppachtmachnet_test		88.35 344	87.29 343	91.53 353	92.45 401	83.57 360	93.75 381	95.97 303	84.28 374	85.32 376	94.18 331	79.00 291	96.93 378	75.71 403	84.99 363	94.10 378

Anonymous20240521		86.42 364	85.44 362	89.34 391	90.33 413	79.79 403	96.73 227	95.92 304	83.71 384	83.25 395	91.36 400	63.92 409	96.01 393	78.39 391	85.36 354	92.22 410

ITE_SJBPF				92.43 323	95.34 294	85.37 332		95.92 304	91.47 181	87.75 339	96.39 212	71.00 360	97.96 302	82.36 359	89.86 308	93.97 383

test_fmvs2		89.77 326	89.93 298	89.31 392	93.68 368	76.37 419	97.64 126	95.90 306	89.84 244	91.49 237	96.26 218	58.77 419	97.10 371	94.65 134	91.13 291	94.46 368

USDC		88.94 335	87.83 340	92.27 330	94.66 336	84.96 341	93.86 378	95.90 306	87.34 326	83.40 393	95.56 257	67.43 390	98.19 265	82.64 358	89.67 310	93.66 386

COLMAP_ROB	87.81 15	90.40 307	89.28 319	93.79 271	97.95 122	87.13 292	96.92 209	95.89 308	82.83 391	86.88 362	97.18 162	73.77 344	99.29 139	78.44 390	93.62 255	94.95 339
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 163	93.08 169	96.02 143	97.88 128	89.96 201	97.72 111	95.85 309	92.43 152	95.86 126	98.44 57	68.42 386	99.39 127	96.31 71	94.85 223	98.71 138

VDDNet		93.05 191	92.07 206	96.02 143	96.84 194	90.39 187	98.08 54	95.85 309	86.22 347	95.79 129	98.46 55	67.59 389	99.19 147	94.92 124	94.85 223	98.47 159

mvsmamba		94.57 134	94.14 138	95.87 151	97.03 181	89.93 202	97.84 89	95.85 309	91.34 187	94.79 156	96.80 183	80.67 253	98.81 204	94.85 125	98.12 141	98.85 127

Vis-MVSNet (Re-imp)		94.15 145	93.88 142	94.95 207	97.61 148	87.92 271	98.10 52	95.80 312	92.22 157	93.02 198	97.45 145	84.53 174	97.91 314	88.24 267	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	95.76 313	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		84.81 381	82.64 384	91.31 358	91.07 410	85.34 333	91.22 414	95.75 314	85.56 356	83.09 396	90.21 408	67.21 392	95.89 395	77.18 397	62.48 438	92.69 398

miper_refine_blended		84.81 381	82.64 384	91.31 358	91.07 410	85.34 333	91.22 414	95.75 314	85.56 356	83.09 396	90.21 408	67.21 392	95.89 395	77.18 397	62.48 438	92.69 398

FE-MVS		92.05 234	91.05 246	95.08 196	96.83 196	87.93 270	93.91 377	95.70 316	86.30 344	94.15 172	94.97 281	76.59 316	99.21 145	84.10 339	96.86 180	98.09 193

tpm cat1		88.36 343	87.21 346	91.81 346	95.13 313	80.55 392	92.58 405	95.70 316	74.97 424	87.45 343	91.96 393	78.01 307	98.17 267	80.39 378	88.74 319	96.72 260

our_test_3		88.78 339	87.98 339	91.20 362	92.45 401	82.53 370	93.61 388	95.69 318	85.77 353	84.88 378	93.71 349	79.99 268	96.78 385	79.47 384	86.24 343	94.28 376

BH-w/o		92.14 231	91.75 219	93.31 294	96.99 185	85.73 324	95.67 304	95.69 318	88.73 284	89.26 302	94.82 291	82.97 207	98.07 283	85.26 326	96.32 195	96.13 278

CR-MVSNet		90.82 293	89.77 305	93.95 261	94.45 345	87.19 289	90.23 422	95.68 320	86.89 334	92.40 208	92.36 385	80.91 249	97.05 373	81.09 373	93.95 249	97.60 227

Patchmtry		88.64 341	87.25 344	92.78 316	94.09 355	86.64 301	89.82 426	95.68 320	80.81 406	87.63 341	92.36 385	80.91 249	97.03 374	78.86 388	85.12 359	94.67 363

testing91		91.90 239	91.02 247	94.53 230	96.54 222	86.55 307	95.86 294	95.64 322	91.77 173	91.89 227	93.47 362	69.94 371	98.86 196	90.23 225	93.86 251	98.18 180

BH-RMVSNet		92.72 209	91.97 212	94.97 205	97.16 169	87.99 269	96.15 280	95.60 323	90.62 220	91.87 228	97.15 165	78.41 298	98.57 233	83.16 348	97.60 157	98.36 171

PVSNet_0	82.17 19	85.46 376	83.64 379	90.92 366	95.27 301	79.49 408	90.55 420	95.60 323	83.76 383	83.00 398	89.95 410	71.09 359	97.97 298	82.75 356	60.79 440	95.31 321

guyue		95.17 115	94.96 111	95.82 155	96.97 187	89.65 207	97.56 136	95.58 325	94.82 54	95.72 131	97.42 149	82.90 209	98.84 200	96.71 61	96.93 179	98.96 106

SCA		91.84 241	91.18 243	93.83 268	95.59 276	84.95 342	94.72 344	95.58 325	90.82 207	92.25 216	93.69 351	75.80 324	98.10 274	86.20 308	95.98 198	98.45 161

MonoMVSNet		91.92 237	91.77 217	92.37 324	92.94 389	83.11 364	97.09 194	95.55 327	92.91 140	90.85 254	94.55 304	81.27 245	96.52 388	93.01 172	87.76 328	97.47 233

AllTest		90.23 312	88.98 325	93.98 257	97.94 123	86.64 301	96.51 250	95.54 328	85.38 358	85.49 373	96.77 185	70.28 366	99.15 156	80.02 380	92.87 260	96.15 276

TestCases				93.98 257	97.94 123	86.64 301		95.54 328	85.38 358	85.49 373	96.77 185	70.28 366	99.15 156	80.02 380	92.87 260	96.15 276

mmtdpeth		89.70 328	88.96 326	91.90 341	95.84 269	84.42 347	97.46 156	95.53 330	90.27 231	94.46 165	90.50 404	69.74 375	98.95 186	97.39 47	69.48 429	92.34 406

tpmvs		89.83 325	89.15 323	91.89 342	94.92 323	80.30 396	93.11 397	95.46 331	86.28 345	88.08 333	92.65 375	80.44 259	98.52 236	81.47 365	89.92 307	96.84 256

pmmvs5		89.86 324	88.87 329	92.82 313	92.86 391	86.23 314	96.26 270	95.39 332	84.24 375	87.12 351	94.51 307	74.27 339	97.36 364	87.61 286	87.57 330	94.86 348

PatchmatchNet		91.91 238	91.35 232	93.59 282	95.38 289	84.11 352	93.15 396	95.39 332	89.54 251	92.10 221	93.68 353	82.82 212	98.13 269	84.81 330	95.32 215	98.52 151
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 262	91.32 234	91.79 347	95.15 311	79.20 411	93.42 391	95.37 334	88.55 289	93.49 187	93.67 354	82.49 221	98.27 258	90.41 220	89.34 313	97.90 205

Anonymous20231206		87.09 356	86.14 358	89.93 384	91.22 409	80.35 394	96.11 281	95.35 335	83.57 386	84.16 385	93.02 370	73.54 346	95.61 403	72.16 419	86.14 345	93.84 385

MIMVSNet1		84.93 379	83.05 381	90.56 375	89.56 419	84.84 344	95.40 319	95.35 335	83.91 378	80.38 410	92.21 390	57.23 422	93.34 425	70.69 425	82.75 390	93.50 388

TDRefinement		86.53 360	84.76 372	91.85 343	82.23 441	84.25 349	96.38 261	95.35 335	84.97 367	84.09 388	94.94 283	65.76 405	98.34 255	84.60 334	74.52 419	92.97 394

TR-MVS		91.48 261	90.59 269	94.16 248	96.40 236	87.33 282	95.67 304	95.34 338	87.68 318	91.46 238	95.52 260	76.77 315	98.35 252	82.85 353	93.61 256	96.79 258

EPNet_dtu		91.71 244	91.28 237	92.99 306	93.76 365	83.71 358	96.69 233	95.28 339	93.15 127	87.02 356	95.95 233	83.37 195	97.38 363	79.46 385	96.84 181	97.88 207
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 353	85.79 360	91.78 348	94.80 330	87.28 284	95.49 316	95.28 339	84.09 377	83.85 392	91.82 394	62.95 412	94.17 417	78.48 389	85.34 355	93.91 384

MDTV_nov1_ep13			90.76 259		95.22 305	80.33 395	93.03 399	95.28 339	88.14 302	92.84 205	93.83 344	81.34 242	98.08 279	82.86 351	94.34 234

LF4IMVS		87.94 347	87.25 344	89.98 383	92.38 403	80.05 402	94.38 358	95.25 342	87.59 320	84.34 382	94.74 295	64.31 408	97.66 338	84.83 329	87.45 331	92.23 409

TransMVSNet (Re)		88.94 335	87.56 341	93.08 304	94.35 348	88.45 254	97.73 108	95.23 343	87.47 322	84.26 384	95.29 267	79.86 271	97.33 365	79.44 386	74.44 420	93.45 390

test20.03		86.14 369	85.40 364	88.35 394	90.12 414	80.06 401	95.90 293	95.20 344	88.59 285	81.29 405	93.62 356	71.43 357	92.65 429	71.26 423	81.17 395	92.34 406

new-patchmatchnet		83.18 387	81.87 390	87.11 402	86.88 432	75.99 421	93.70 382	95.18 345	85.02 366	77.30 421	88.40 420	65.99 403	93.88 422	74.19 412	70.18 427	91.47 419

MDA-MVSNet_test_wron		85.87 373	84.23 376	90.80 372	92.38 403	82.57 369	93.17 394	95.15 346	82.15 395	67.65 433	92.33 388	78.20 300	95.51 406	77.33 394	79.74 399	94.31 375

YYNet1		85.87 373	84.23 376	90.78 373	92.38 403	82.46 374	93.17 394	95.14 347	82.12 396	67.69 431	92.36 385	78.16 303	95.50 407	77.31 395	79.73 400	94.39 371

Baseline_NR-MVSNet		91.20 277	90.62 267	92.95 308	93.83 363	88.03 268	97.01 201	95.12 348	88.42 293	89.70 285	95.13 277	83.47 192	97.44 358	89.66 237	83.24 385	93.37 391

thres200		92.23 227	91.39 231	94.75 220	97.61 148	89.03 238	96.60 245	95.09 349	92.08 165	93.28 193	94.00 340	78.39 299	99.04 182	81.26 372	94.18 240	96.19 272

ADS-MVSNet		89.89 321	88.68 331	93.53 286	95.86 264	84.89 343	90.93 417	95.07 350	83.23 389	91.28 247	91.81 395	79.01 289	97.85 317	79.52 382	91.39 287	97.84 212

pmmvs-eth3d		86.22 367	84.45 374	91.53 353	88.34 428	87.25 286	94.47 353	95.01 351	83.47 387	79.51 415	89.61 413	69.75 374	95.71 400	83.13 349	76.73 413	91.64 414

Anonymous202405211		92.07 233	90.83 257	95.76 158	98.19 102	88.75 243	97.58 132	95.00 352	86.00 350	93.64 182	97.45 145	66.24 401	99.53 105	90.68 218	92.71 265	99.01 98

MDA-MVSNet-bldmvs		85.00 378	82.95 383	91.17 364	93.13 387	83.33 361	94.56 349	95.00 352	84.57 372	65.13 437	92.65 375	70.45 365	95.85 397	73.57 415	77.49 409	94.33 373

ambc				86.56 405	83.60 438	70.00 432	85.69 436	94.97 354		80.60 409	88.45 419	37.42 440	96.84 382	82.69 357	75.44 417	92.86 396

testgi		87.97 346	87.21 346	90.24 380	92.86 391	80.76 387	96.67 236	94.97 354	91.74 174	85.52 372	95.83 239	62.66 414	94.47 415	76.25 401	88.36 323	95.48 304

myMVS_eth3d28		91.52 258	90.97 249	93.17 300	96.91 189	83.24 363	95.61 310	94.96 356	92.24 156	91.98 224	93.28 367	69.31 376	98.40 244	88.71 262	95.68 208	97.88 207

dp		88.90 337	88.26 337	90.81 370	94.58 341	76.62 418	92.85 402	94.93 357	85.12 364	90.07 276	93.07 369	75.81 323	98.12 272	80.53 377	87.42 333	97.71 219

test_fmvs3		83.21 386	83.02 382	83.78 409	86.77 433	68.34 435	96.76 225	94.91 358	86.49 340	84.14 387	89.48 414	36.04 441	91.73 431	91.86 191	80.77 397	91.26 421

test_0402		86.46 363	84.79 371	91.45 355	95.02 317	85.55 326	96.29 269	94.89 359	80.90 403	82.21 401	93.97 342	68.21 387	97.29 367	62.98 432	88.68 320	91.51 417

tfpn200view9		92.38 217	91.52 228	94.95 207	97.85 129	89.29 228	97.41 159	94.88 360	92.19 161	93.27 194	94.46 312	78.17 301	99.08 170	81.40 366	94.08 244	96.48 265

CVMVSNet		91.23 275	91.75 219	89.67 386	95.77 270	74.69 422	96.44 251	94.88 360	85.81 352	92.18 217	97.64 134	79.07 284	95.58 405	88.06 270	95.86 203	98.74 135

thres400		92.42 215	91.52 228	95.12 195	97.85 129	89.29 228	97.41 159	94.88 360	92.19 161	93.27 194	94.46 312	78.17 301	99.08 170	81.40 366	94.08 244	96.98 250

tt0320		85.39 377	83.12 380	92.19 334	93.44 379	85.79 322	96.19 277	94.87 363	71.19 431	82.92 399	91.76 397	58.43 420	96.81 383	81.03 374	78.26 408	93.98 382

EPNet		95.20 113	94.56 124	97.14 71	92.80 393	92.68 93	97.85 88	94.87 363	96.64 6	92.46 207	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		91.62 249	90.72 264	94.32 240	96.48 230	86.11 319	95.81 297	94.76 365	91.55 178	91.75 232	93.44 363	68.55 384	98.82 202	90.43 219	93.69 252	98.04 197

sc_t1		86.48 362	84.10 378	93.63 279	93.45 378	85.76 323	96.79 221	94.71 366	73.06 429	86.45 365	94.35 317	55.13 427	97.95 306	84.38 337	78.55 407	97.18 246

SixPastTwentyTwo		89.15 333	88.54 333	90.98 365	93.49 375	80.28 398	96.70 231	94.70 367	90.78 208	84.15 386	95.57 256	71.78 355	97.71 334	84.63 333	85.07 360	94.94 341

thres100view900		92.43 214	91.58 225	94.98 203	97.92 125	89.37 224	97.71 113	94.66 368	92.20 159	93.31 192	94.90 286	78.06 305	99.08 170	81.40 366	94.08 244	96.48 265

thres600view7		92.49 213	91.60 224	95.18 191	97.91 126	89.47 218	97.65 122	94.66 368	92.18 163	93.33 191	94.91 285	78.06 305	99.10 164	81.61 362	94.06 248	96.98 250

PatchT		88.87 338	87.42 342	93.22 298	94.08 356	85.10 337	89.51 427	94.64 370	81.92 397	92.36 211	88.15 423	80.05 267	97.01 376	72.43 418	93.65 254	97.54 230

baseline1		92.82 205	91.90 214	95.55 174	97.20 167	90.77 173	97.19 186	94.58 371	92.20 159	92.36 211	96.34 214	84.16 182	98.21 262	89.20 252	83.90 380	97.68 221

AstraMVS		94.82 129	94.64 120	95.34 186	96.36 240	88.09 267	97.58 132	94.56 372	94.98 43	95.70 134	97.92 105	81.93 234	98.93 189	96.87 55	95.88 201	98.99 102

UBG		91.55 255	90.76 259	93.94 263	96.52 226	85.06 338	95.22 331	94.54 373	90.47 227	91.98 224	92.71 374	72.02 352	98.74 214	88.10 269	95.26 217	98.01 199

Gipuma		67.86 407	65.41 409	75.18 422	92.66 396	73.45 426	66.50 443	94.52 374	53.33 442	57.80 443	66.07 443	30.81 443	89.20 435	48.15 441	78.88 406	62.90 443
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 247	90.75 261	94.47 231	96.53 224	86.56 306	95.76 301	94.51 375	91.10 202	91.24 249	93.59 357	68.59 383	98.86 196	91.10 208	94.29 236	98.00 200

CostFormer		91.18 280	90.70 265	92.62 321	94.84 328	81.76 380	94.09 370	94.43 376	84.15 376	92.72 206	93.77 348	79.43 278	98.20 263	90.70 217	92.18 274	97.90 205

tpm2		89.96 318	89.21 321	92.23 333	94.91 325	81.25 383	93.78 380	94.42 377	80.62 408	91.56 235	93.44 363	76.44 319	97.94 308	85.60 320	92.08 278	97.49 231

testing3-2		92.10 232	92.05 207	92.27 330	97.71 138	79.56 405	97.42 158	94.41 378	93.53 108	93.22 196	95.49 261	69.16 378	99.11 162	93.25 162	94.22 238	98.13 185

MVS_0304		96.74 58	96.31 75	98.02 19	96.87 191	94.65 30	97.58 132	94.39 379	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		88.26 345	87.04 349	91.91 340	93.52 373	81.42 382	89.38 428	94.38 380	80.84 405	90.93 253	80.74 435	79.22 281	97.92 311	82.76 355	91.62 282	96.38 268

dmvs_re		90.21 313	89.50 314	92.35 325	95.47 286	85.15 335	95.70 303	94.37 381	90.94 206	88.42 321	93.57 358	74.63 336	95.67 402	82.80 354	89.57 311	96.22 270

Patchmatch-test		89.42 331	87.99 338	93.70 276	95.27 301	85.11 336	88.98 429	94.37 381	81.11 402	87.10 354	93.69 351	82.28 225	97.50 353	74.37 410	94.76 227	98.48 158

LCM-MVSNet		72.55 400	69.39 404	82.03 411	70.81 451	65.42 440	90.12 424	94.36 383	55.02 441	65.88 435	81.72 434	24.16 449	89.96 432	74.32 411	68.10 432	90.71 424

ADS-MVSNet2		89.45 330	88.59 332	92.03 337	95.86 264	82.26 376	90.93 417	94.32 384	83.23 389	91.28 247	91.81 395	79.01 289	95.99 394	79.52 382	91.39 287	97.84 212

mvs5depth		86.53 360	85.08 367	90.87 367	88.74 426	82.52 371	91.91 410	94.23 385	86.35 343	87.11 353	93.70 350	66.52 397	97.76 329	81.37 369	75.80 415	92.31 408

EU-MVSNet		88.72 340	88.90 328	88.20 396	93.15 386	74.21 424	96.63 242	94.22 386	85.18 362	87.32 348	95.97 231	76.16 321	94.98 411	85.27 325	86.17 344	95.41 311

tt0320-xc		84.83 380	82.33 388	92.31 328	93.66 369	86.20 316	96.17 279	94.06 387	71.26 430	82.04 403	92.22 389	55.07 428	96.72 386	81.49 364	75.04 418	94.02 381

MIMVSNet		88.50 342	86.76 352	93.72 275	94.84 328	87.77 277	91.39 412	94.05 388	86.41 342	87.99 335	92.59 378	63.27 410	95.82 399	77.44 393	92.84 262	97.57 229

OpenMVS_ROB	81.14 20	84.42 383	82.28 389	90.83 368	90.06 415	84.05 354	95.73 302	94.04 389	73.89 427	80.17 413	91.53 399	59.15 418	97.64 339	66.92 430	89.05 315	90.80 423

TinyColmap		86.82 358	85.35 365	91.21 360	94.91 325	82.99 366	93.94 374	94.02 390	83.58 385	81.56 404	94.68 297	62.34 415	98.13 269	75.78 402	87.35 336	92.52 404

ETVMVS		90.52 304	89.14 324	94.67 222	96.81 200	87.85 275	95.91 292	93.97 391	89.71 247	92.34 214	92.48 380	65.41 406	97.96 302	81.37 369	94.27 237	98.21 178

IB-MVS	87.33 17	89.91 319	88.28 336	94.79 217	95.26 304	87.70 278	95.12 336	93.95 392	89.35 259	87.03 355	92.49 379	70.74 363	99.19 147	89.18 253	81.37 394	97.49 231
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		87.13 355	87.02 350	87.47 400	95.16 308	73.21 428	95.00 338	93.93 393	88.55 289	86.96 357	91.99 391	75.90 322	94.00 419	61.59 434	94.11 241	95.20 329

myMVS_eth3d		87.18 354	86.38 355	89.58 387	95.16 308	79.53 406	95.00 338	93.93 393	88.55 289	86.96 357	91.99 391	56.23 425	94.00 419	75.47 406	94.11 241	95.20 329

testing222		90.31 308	88.96 326	94.35 237	96.54 222	87.29 283	95.50 315	93.84 395	90.97 205	91.75 232	92.96 371	62.18 416	98.00 293	82.86 351	94.08 244	97.76 217

test_f		80.57 393	79.62 395	83.41 410	83.38 439	67.80 437	93.57 389	93.72 396	80.80 407	77.91 420	87.63 426	33.40 442	92.08 430	87.14 297	79.04 405	90.34 425

LCM-MVSNet-Re		92.50 211	92.52 195	92.44 322	96.82 198	81.89 379	96.92 209	93.71 397	92.41 153	84.30 383	94.60 302	85.08 167	97.03 374	91.51 199	97.36 165	98.40 167

tpm		90.25 311	89.74 308	91.76 350	93.92 359	79.73 404	93.98 371	93.54 398	88.28 296	91.99 223	93.25 368	77.51 311	97.44 358	87.30 292	87.94 326	98.12 187

ET-MVSNet_ETH3D		91.49 260	90.11 289	95.63 168	96.40 236	91.57 137	95.34 322	93.48 399	90.60 223	75.58 423	95.49 261	80.08 266	96.79 384	94.25 142	89.76 309	98.52 151

LFMVS		93.60 169	92.63 188	96.52 101	98.13 108	91.27 148	97.94 76	93.39 400	90.57 224	96.29 108	98.31 74	69.00 379	99.16 154	94.18 143	95.87 202	99.12 87

MVStest1		82.38 390	80.04 394	89.37 389	87.63 431	82.83 367	95.03 337	93.37 401	73.90 426	73.50 428	94.35 317	62.89 413	93.25 427	73.80 413	65.92 435	92.04 413

Patchmatch-RL test		87.38 352	86.24 356	90.81 370	88.74 426	78.40 415	88.12 434	93.17 402	87.11 331	82.17 402	89.29 415	81.95 232	95.60 404	88.64 264	77.02 410	98.41 166

ttmdpeth		85.91 372	84.76 372	89.36 390	89.14 421	80.25 399	95.66 307	93.16 403	83.77 382	83.39 394	95.26 271	66.24 401	95.26 410	80.65 375	75.57 416	92.57 401

test-LLR		91.42 263	91.19 242	92.12 335	94.59 339	80.66 389	94.29 364	92.98 404	91.11 200	90.76 256	92.37 382	79.02 287	98.07 283	88.81 259	96.74 184	97.63 222

test-mter		90.19 315	89.54 313	92.12 335	94.59 339	80.66 389	94.29 364	92.98 404	87.68 318	90.76 256	92.37 382	67.67 388	98.07 283	88.81 259	96.74 184	97.63 222

WB-MVSnew		89.88 322	89.56 312	90.82 369	94.57 342	83.06 365	95.65 308	92.85 406	87.86 309	90.83 255	94.10 334	79.66 275	96.88 380	76.34 400	94.19 239	92.54 403

testing3		87.67 350	86.88 351	90.05 382	96.14 253	80.71 388	97.10 193	92.85 406	90.15 235	87.54 342	94.55 304	55.70 426	94.10 418	73.77 414	94.10 243	95.35 318

test_method		66.11 408	64.89 410	69.79 425	72.62 449	35.23 457	65.19 444	92.83 408	20.35 447	65.20 436	88.08 424	43.14 438	82.70 442	73.12 417	63.46 437	91.45 420

test0.0.03 1		89.37 332	88.70 330	91.41 357	92.47 400	85.63 325	95.22 331	92.70 409	91.11 200	86.91 361	93.65 355	79.02 287	93.19 428	78.00 392	89.18 314	95.41 311

new_pmnet		82.89 388	81.12 393	88.18 397	89.63 418	80.18 400	91.77 411	92.57 410	76.79 422	75.56 424	88.23 422	61.22 417	94.48 414	71.43 421	82.92 388	89.87 426

mvsany_test1		93.93 159	93.98 140	93.78 272	94.94 322	86.80 297	94.62 346	92.55 411	88.77 283	96.85 77	98.49 51	88.98 96	98.08 279	95.03 119	95.62 210	96.46 267

thisisatest0515		92.29 223	91.30 236	95.25 189	96.60 213	88.90 241	94.36 359	92.32 412	87.92 306	93.43 189	94.57 303	77.28 312	99.00 183	89.42 243	95.86 203	97.86 211

thisisatest0530		93.03 192	92.21 204	95.49 178	97.07 174	89.11 237	97.49 153	92.19 413	90.16 234	94.09 173	96.41 210	76.43 320	99.05 179	90.38 221	95.68 208	98.31 173

tttt0517		92.96 195	92.33 201	94.87 210	97.11 172	87.16 291	97.97 72	92.09 414	90.63 219	93.88 179	97.01 174	76.50 317	99.06 176	90.29 224	95.45 213	98.38 169

K. test v3		87.64 351	86.75 353	90.32 379	93.02 388	79.48 409	96.61 243	92.08 415	90.66 217	80.25 412	94.09 336	67.21 392	96.65 387	85.96 316	80.83 396	94.83 350

TESTMET0.1,1		90.06 317	89.42 316	91.97 338	94.41 347	80.62 391	94.29 364	91.97 416	87.28 328	90.44 260	92.47 381	68.79 380	97.67 336	88.50 266	96.60 189	97.61 226

PM-MVS		83.48 385	81.86 391	88.31 395	87.83 430	77.59 417	93.43 390	91.75 417	86.91 333	80.63 408	89.91 411	44.42 437	95.84 398	85.17 328	76.73 413	91.50 418

baseline2		91.63 248	90.86 253	93.94 263	94.33 349	86.32 311	95.92 291	91.64 418	89.37 258	86.94 359	94.69 296	81.62 239	98.69 220	88.64 264	94.57 232	96.81 257

APD_test1		79.31 395	77.70 398	84.14 408	89.11 423	69.07 434	92.36 409	91.50 419	69.07 433	73.87 426	92.63 377	39.93 439	94.32 416	70.54 426	80.25 398	89.02 428

FPMVS		71.27 401	69.85 403	75.50 421	74.64 446	59.03 446	91.30 413	91.50 419	58.80 438	57.92 442	88.28 421	29.98 445	85.53 441	53.43 439	82.84 389	81.95 434

door								91.13 421

door-mid								91.06 422

EGC-MVSNET		68.77 406	63.01 412	86.07 407	92.49 399	82.24 377	93.96 373	90.96 423	0.71 452	2.62 453	90.89 402	53.66 429	93.46 423	57.25 437	84.55 370	82.51 433

mvsany_test3		83.59 384	82.44 387	87.03 403	83.80 436	73.82 425	93.70 382	90.92 424	86.42 341	82.51 400	90.26 407	46.76 436	95.71 400	90.82 212	76.76 412	91.57 416

pmmvs3		79.97 394	77.50 399	87.39 401	82.80 440	79.38 410	92.70 404	90.75 425	70.69 432	78.66 417	87.47 428	51.34 432	93.40 424	73.39 416	69.65 428	89.38 427

UWE-MVS		89.91 319	89.48 315	91.21 360	95.88 263	78.23 416	94.91 341	90.26 426	89.11 265	92.35 213	94.52 306	68.76 381	97.96 302	83.95 343	95.59 211	97.42 235

DSMNet-mixed		86.34 365	86.12 359	87.00 404	89.88 417	70.43 430	94.93 340	90.08 427	77.97 419	85.42 375	92.78 373	74.44 338	93.96 421	74.43 409	95.14 218	96.62 261

MVS-HIRNet		82.47 389	81.21 392	86.26 406	95.38 289	69.21 433	88.96 430	89.49 428	66.28 435	80.79 407	74.08 440	68.48 385	97.39 362	71.93 420	95.47 212	92.18 411

WB-MVS		76.77 397	76.63 400	77.18 416	85.32 434	56.82 448	94.53 350	89.39 429	82.66 393	71.35 429	89.18 416	75.03 331	88.88 436	35.42 445	66.79 433	85.84 430

test1111		93.19 184	92.82 178	94.30 243	97.58 154	84.56 346	98.21 43	89.02 430	93.53 108	94.58 160	98.21 81	72.69 348	99.05 179	93.06 168	98.48 124	99.28 72

SSC-MVS		76.05 398	75.83 401	76.72 420	84.77 435	56.22 449	94.32 362	88.96 431	81.82 399	70.52 430	88.91 417	74.79 335	88.71 437	33.69 446	64.71 436	85.23 431

ECVR-MVS		93.19 184	92.73 184	94.57 228	97.66 142	85.41 329	98.21 43	88.23 432	93.43 113	94.70 158	98.21 81	72.57 349	99.07 174	93.05 169	98.49 122	99.25 75

EPMVS		90.70 298	89.81 303	93.37 292	94.73 334	84.21 350	93.67 385	88.02 433	89.50 253	92.38 210	93.49 360	77.82 309	97.78 326	86.03 314	92.68 266	98.11 192

ANet_high		63.94 410	59.58 413	77.02 417	61.24 453	66.06 438	85.66 437	87.93 434	78.53 417	42.94 445	71.04 442	25.42 448	80.71 444	52.60 440	30.83 446	84.28 432

PMMVS2		70.19 402	66.92 406	80.01 412	76.35 445	65.67 439	86.22 435	87.58 435	64.83 437	62.38 438	80.29 437	26.78 447	88.49 439	63.79 431	54.07 442	85.88 429

lessismore_v0				90.45 376	91.96 406	79.09 413		87.19 436		80.32 411	94.39 314	66.31 400	97.55 347	84.00 342	76.84 411	94.70 362

PMVS	53.92 22	58.58 411	55.40 414	68.12 426	51.00 454	48.64 451	78.86 440	87.10 437	46.77 443	35.84 449	74.28 439	8.76 453	86.34 440	42.07 443	73.91 421	69.38 440
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 359	86.41 354	88.02 398	92.87 390	74.60 423	95.38 321	86.70 438	88.17 299	87.28 350	94.67 299	70.83 362	93.30 426	67.45 428	94.31 235	96.17 273

test_vis1_rt		86.16 368	85.06 368	89.46 388	93.47 377	80.46 393	96.41 255	86.61 439	85.22 361	79.15 416	88.64 418	52.41 431	97.06 372	93.08 167	90.57 300	90.87 422

testf1		69.31 404	66.76 407	76.94 418	78.61 443	61.93 442	88.27 432	86.11 440	55.62 439	59.69 439	85.31 431	20.19 451	89.32 433	57.62 435	69.44 430	79.58 435

APD_test2		69.31 404	66.76 407	76.94 418	78.61 443	61.93 442	88.27 432	86.11 440	55.62 439	59.69 439	85.31 431	20.19 451	89.32 433	57.62 435	69.44 430	79.58 435

gg-mvs-nofinetune		87.82 348	85.61 361	94.44 233	94.46 344	89.27 231	91.21 416	84.61 442	80.88 404	89.89 280	74.98 438	71.50 356	97.53 350	85.75 319	97.21 173	96.51 263

dmvs_testset		81.38 392	82.60 386	77.73 415	91.74 407	51.49 450	93.03 399	84.21 443	89.07 266	78.28 419	91.25 401	76.97 314	88.53 438	56.57 438	82.24 391	93.16 392

GG-mvs-BLEND				93.62 280	93.69 367	89.20 233	92.39 408	83.33 444		87.98 336	89.84 412	71.00 360	96.87 381	82.08 361	95.40 214	94.80 355

MTMP							97.86 85	82.03 445

DeepMVS_CX				74.68 423	90.84 412	64.34 441		81.61 446	65.34 436	67.47 434	88.01 425	48.60 435	80.13 445	62.33 433	73.68 422	79.58 435

E-PMN		53.28 412	52.56 416	55.43 429	74.43 447	47.13 452	83.63 439	76.30 447	42.23 444	42.59 446	62.22 445	28.57 446	74.40 446	31.53 447	31.51 445	44.78 444

test2506		91.60 250	90.78 258	94.04 254	97.66 142	83.81 355	98.27 33	75.53 448	93.43 113	95.23 145	98.21 81	67.21 392	99.07 174	93.01 172	98.49 122	99.25 75

EMVS		52.08 414	51.31 417	54.39 430	72.62 449	45.39 454	83.84 438	75.51 449	41.13 445	40.77 447	59.65 446	30.08 444	73.60 447	28.31 449	29.90 447	44.18 445

test_vis3_rt		72.73 399	70.55 402	79.27 413	80.02 442	68.13 436	93.92 376	74.30 450	76.90 421	58.99 441	73.58 441	20.29 450	95.37 408	84.16 338	72.80 424	74.31 438

MVE	50.73 23	53.25 413	48.81 418	66.58 428	65.34 452	57.50 447	72.49 442	70.94 451	40.15 446	39.28 448	63.51 444	6.89 455	73.48 448	38.29 444	42.38 444	68.76 442
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 415	53.82 415	46.29 431	33.73 455	45.30 455	78.32 441	67.24 452	18.02 448	50.93 444	87.05 429	52.99 430	53.11 450	70.76 424	25.29 448	40.46 446

kuosan		65.27 409	64.66 411	67.11 427	83.80 436	61.32 445	88.53 431	60.77 453	68.22 434	67.67 432	80.52 436	49.12 434	70.76 449	29.67 448	53.64 443	69.26 441

dongtai		69.99 403	69.33 405	71.98 424	88.78 425	61.64 444	89.86 425	59.93 454	75.67 423	74.96 425	85.45 430	50.19 433	81.66 443	43.86 442	55.27 441	72.63 439

N_pmnet		78.73 396	78.71 397	78.79 414	92.80 393	46.50 453	94.14 368	43.71 455	78.61 416	80.83 406	91.66 398	74.94 334	96.36 390	67.24 429	84.45 372	93.50 388

wuyk23d		25.11 416	24.57 420	26.74 432	73.98 448	39.89 456	57.88 445	9.80 456	12.27 449	10.39 450	6.97 452	7.03 454	36.44 451	25.43 450	17.39 449	3.89 449

testmvs		13.36 418	16.33 421	4.48 434	5.04 456	2.26 459	93.18 393	3.28 457	2.70 450	8.24 451	21.66 448	2.29 457	2.19 452	7.58 451	2.96 450	9.00 448

test123		13.04 419	15.66 422	5.18 433	4.51 457	3.45 458	92.50 407	1.81 458	2.50 451	7.58 452	20.15 449	3.67 456	2.18 453	7.13 452	1.07 451	9.90 447

mmdepth		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

monomultidepth		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

test_blank		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

uanet_test		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

DCPMVS		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

pcd_1.5k_mvsjas		7.39 421	9.85 424	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	88.65 104	0.00 454	0.00 453	0.00 452	0.00 450

sosnet-low-res		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

sosnet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

uncertanet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

Regformer		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

n2								0.00 459

nn								0.00 459

ab-mvs-re		8.06 420	10.74 423	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	96.69 191	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

uanet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

WAC-MVS						79.53 406								75.56 405

PC_three_1452									90.77 209	98.89 23	98.28 79	96.24 1	98.35 252	95.76 98	99.58 23	99.59 27

eth-test2					0.00 458

eth-test					0.00 458

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																98.45 161

test_part2					99.28 27	95.74 8				98.10 41

sam_mvs1												82.76 213				98.45 161

sam_mvs												81.94 233

test_post1							92.81 403				16.58 451	80.53 257	97.68 335	86.20 308

test_post											17.58 450	81.76 236	98.08 279

patchmatchnet-post											90.45 406	82.65 218	98.10 274

gm-plane-assit					93.22 384	78.89 414			84.82 369		93.52 359		98.64 225	87.72 276

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	96.42 254

test_prior2							96.35 263		92.80 145	96.03 118	97.59 138	92.01 47		95.01 120	99.38 59

旧先验2							95.94 290		81.66 400	97.34 63			98.82 202	92.26 178

新几何2							95.79 299

原ACMM2							95.67 304

testdata2													99.67 70	85.96 316

segment_acmp												92.89 30

testdata1							95.26 330		93.10 130

plane_prior7					96.21 245	89.98 199

plane_prior6					96.10 256	90.00 195						81.32 243

plane_prior4											96.64 194

plane_prior3						90.00 195			94.46 75	91.34 241

plane_prior2							97.74 106		94.85 50

plane_prior1					96.14 253

plane_prior						89.99 197	97.24 178		94.06 87						92.16 275

HQP5-MVS						89.33 226

HQP-NCC					95.86 264		96.65 237		93.55 104	90.14 265

ACMP_Plane					95.86 264		96.65 237		93.55 104	90.14 265

BP-MVS														92.13 184

HQP4-MVS										90.14 265			98.50 237			95.78 292

HQP2-MVS												80.95 247

NP-MVS					95.99 262	89.81 205					95.87 236

MDTV_nov1_ep13_2view						70.35 431	93.10 398		83.88 380	93.55 184		82.47 222		86.25 307		98.38 169

ACMMP++_ref															90.30 305

ACMMP++															91.02 294

Test By Simon												88.73 103

High-resolution multi-view benchmark