High-res multi-view results

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

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

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

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

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

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

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

test_fmvsm_n_1920		97.55 14	97.89 3	96.53 101	98.41 80	91.73 126	98.01 61	99.02 1	96.37 12	99.30 6	98.92 22	92.39 41	99.79 41	99.16 13	99.46 42	98.08 214

PGM-MVS		96.81 54	96.53 65	97.65 43	99.35 22	93.53 61	97.65 123	98.98 2	92.22 165	97.14 71	98.44 59	91.17 68	99.85 18	94.35 150	99.46 42	99.57 32

MVS_111021_HR		96.68 65	96.58 64	96.99 80	98.46 75	92.31 106	96.20 289	98.90 3	94.30 85	95.86 129	97.74 131	92.33 42	99.38 131	96.04 91	99.42 52	99.28 73

test_fmvsmconf_n		97.49 18	97.56 13	97.29 60	97.44 160	92.37 103	97.91 80	98.88 4	95.83 18	98.92 22	99.05 13	91.45 58	99.80 36	99.12 15	99.46 42	99.69 13

lecture		97.58 13	97.63 10	97.43 54	99.37 16	92.93 82	98.86 7	98.85 5	95.27 33	98.65 32	98.90 24	91.97 49	99.80 36	97.63 37	99.21 78	99.57 32

ACMMP		96.27 82	95.93 85	97.28 62	99.24 30	92.62 94	98.25 36	98.81 6	92.99 135	94.56 169	98.39 63	88.96 98	99.85 18	94.57 144	97.63 158	99.36 68
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MVS_111021_LR		96.24 83	96.19 81	96.39 119	98.23 100	91.35 148	96.24 287	98.79 7	93.99 92	95.80 131	97.65 141	89.92 88	99.24 144	95.87 95	99.20 83	98.58 159

patch_mono-2		96.83 53	97.44 21	95.01 211	99.05 41	85.39 350	96.98 207	98.77 8	94.70 65	97.99 46	98.66 42	93.61 19	99.91 1	97.67 36	99.50 36	99.72 12

fmvsm_s_conf0.5_n		96.85 50	97.13 27	96.04 143	98.07 115	90.28 196	97.97 72	98.76 9	94.93 47	98.84 27	99.06 11	88.80 102	99.65 74	99.06 17	98.63 118	98.18 200

fmvsm_l_conf0.5_n		97.65 7	97.75 7	97.34 57	98.21 101	92.75 88	97.83 93	98.73 10	95.04 44	99.30 6	98.84 35	93.34 22	99.78 44	99.32 7	99.13 93	99.50 48

fmvsm_s_conf0.5_n_a		96.75 58	96.93 42	96.20 135	97.64 146	90.72 178	98.00 62	98.73 10	94.55 72	98.91 23	99.08 7	88.22 114	99.63 83	98.91 20	98.37 131	98.25 195

fmvsm_s_conf0.5_n_10		97.29 27	97.40 23	96.97 82	98.24 95	91.96 122	97.89 83	98.72 12	96.77 6	99.46 3	99.06 11	87.78 123	99.84 23	99.40 4	99.27 70	99.12 88

fmvsm_l_conf0.5_n_9		97.59 11	97.79 5	96.97 82	98.28 89	91.49 140	97.61 132	98.71 13	97.10 4	99.70 1	98.93 21	90.95 73	99.77 47	99.35 6	99.53 29	99.65 19

FC-MVSNet-test		93.94 170	93.57 162	95.04 209	95.48 302	91.45 145	98.12 51	98.71 13	93.37 117	90.23 282	96.70 208	87.66 125	97.85 333	91.49 213	90.39 322	95.83 308

UniMVSNet (Re)		93.31 197	92.55 210	95.61 179	95.39 308	93.34 67	97.39 166	98.71 13	93.14 130	90.10 291	94.83 310	87.71 124	98.03 306	91.67 211	83.99 396	95.46 327

fmvsm_l_conf0.5_n_a		97.63 9	97.76 6	97.26 64	98.25 94	92.59 96	97.81 98	98.68 16	94.93 47	99.24 9	98.87 30	93.52 20	99.79 41	99.32 7	99.21 78	99.40 62

FIs		94.09 161	93.70 158	95.27 198	95.70 291	92.03 118	98.10 52	98.68 16	93.36 119	90.39 279	96.70 208	87.63 128	97.94 324	92.25 191	90.50 321	95.84 307

WR-MVS_H		92.00 254	91.35 251	93.95 279	95.09 335	89.47 228	98.04 59	98.68 16	91.46 195	88.34 342	94.68 317	85.86 162	97.56 362	85.77 337	84.24 394	94.82 372

fmvsm_s_conf0.5_n_4		96.75 58	97.07 30	95.79 166	97.76 137	89.57 222	97.66 122	98.66 19	95.36 29	99.03 15	98.90 24	88.39 110	99.73 56	99.17 12	98.66 116	98.08 214

VPA-MVSNet		93.24 199	92.48 215	95.51 185	95.70 291	92.39 102	97.86 86	98.66 19	92.30 162	92.09 240	95.37 285	80.49 277	98.40 260	93.95 156	85.86 367	95.75 316

fmvsm_l_conf0.5_n_3		97.64 8	97.60 11	97.79 30	98.14 108	93.94 52	97.93 78	98.65 21	96.70 7	99.38 4	99.07 10	89.92 88	99.81 31	99.16 13	99.43 49	99.61 26

fmvsm_s_conf0.5_n_3		97.15 32	97.36 24	96.52 103	97.98 121	91.19 156	97.84 90	98.65 21	97.08 5	99.25 8	99.10 5	87.88 121	99.79 41	99.32 7	99.18 85	98.59 158

fmvsm_s_conf0.5_n_8		97.32 25	97.48 20	96.85 84	98.28 89	91.07 164	97.76 103	98.62 23	97.53 2	99.20 11	99.12 4	88.24 113	99.81 31	99.41 3	99.17 86	99.67 14

fmvsm_s_conf0.5_n_2		96.62 66	96.82 51	96.02 145	97.98 121	90.43 188	97.50 147	98.59 24	96.59 9	99.31 5	99.08 7	84.47 191	99.75 53	99.37 5	98.45 128	97.88 227

UniMVSNet_NR-MVSNet		93.37 195	92.67 204	95.47 191	95.34 314	92.83 85	97.17 190	98.58 25	92.98 140	90.13 287	95.80 261	88.37 112	97.85 333	91.71 208	83.93 397	95.73 318

CSCG		96.05 86	95.91 86	96.46 113	99.24 30	90.47 185	98.30 29	98.57 26	89.01 288	93.97 189	97.57 151	92.62 37	99.76 49	94.66 138	99.27 70	99.15 83

fmvsm_s_conf0.5_n_9		97.33 24	97.57 12	96.62 97	98.43 78	90.32 195	97.80 99	98.53 27	97.24 3	99.62 2	99.14 1	88.65 105	99.80 36	99.54 1	99.15 90	99.74 8

fmvsm_s_conf0.5_n_6		97.08 35	97.17 26	96.81 85	97.28 165	91.73 126	97.75 105	98.50 28	94.86 51	99.22 10	98.78 39	89.75 91	99.76 49	99.10 16	99.29 68	98.94 114

MSLP-MVS++		96.94 44	97.06 31	96.59 98	98.72 60	91.86 124	97.67 119	98.49 29	94.66 68	97.24 67	98.41 62	92.31 44	98.94 190	96.61 66	99.46 42	98.96 110

HyFIR lowres test		93.66 182	92.92 192	95.87 156	98.24 95	89.88 211	94.58 365	98.49 29	85.06 385	93.78 192	95.78 265	82.86 226	98.67 234	91.77 206	95.71 220	99.07 96

CHOSEN 1792x2688		94.15 156	93.51 168	96.06 141	98.27 91	89.38 233	95.18 351	98.48 31	85.60 375	93.76 193	97.11 183	83.15 216	99.61 85	91.33 216	98.72 114	99.19 79

fmvsm_s_conf0.5_n_7		96.45 73	96.80 53	95.37 194	97.29 164	88.38 266	97.23 184	98.47 32	95.14 38	98.43 37	99.09 6	87.58 129	99.72 60	98.80 24	99.21 78	98.02 218

fmvsm_s_conf0.5_n_5		97.00 41	96.97 39	97.09 75	97.58 156	92.56 97	97.68 118	98.47 32	94.02 90	98.90 24	98.89 27	88.94 99	99.78 44	99.18 11	99.03 102	98.93 118

PHI-MVS		96.77 56	96.46 72	97.71 41	98.40 81	94.07 48	98.21 43	98.45 34	89.86 260	97.11 73	98.01 99	92.52 39	99.69 68	96.03 92	99.53 29	99.36 68

fmvsm_s_conf0.1_n		96.58 69	96.77 56	96.01 148	96.67 219	90.25 197	97.91 80	98.38 35	94.48 76	98.84 27	99.14 1	88.06 116	99.62 84	98.82 22	98.60 120	98.15 204

PVSNet_BlendedMVS		94.06 162	93.92 152	94.47 246	98.27 91	89.46 230	96.73 235	98.36 36	90.17 252	94.36 175	95.24 293	88.02 117	99.58 93	93.44 169	90.72 317	94.36 392

PVSNet_Blended		94.87 132	94.56 131	95.81 163	98.27 91	89.46 230	95.47 333	98.36 36	88.84 297	94.36 175	96.09 250	88.02 117	99.58 93	93.44 169	98.18 140	98.40 180

3Dnovator	91.36 5	95.19 119	94.44 140	97.44 53	96.56 229	93.36 66	98.65 12	98.36 36	94.12 87	89.25 321	98.06 93	82.20 243	99.77 47	93.41 171	99.32 66	99.18 80

FOURS1					99.55 1	93.34 67	99.29 1	98.35 39	94.98 45	98.49 35

DPE-MVS		97.86 4	97.65 9	98.47 5	99.17 34	95.78 7	97.21 187	98.35 39	95.16 37	98.71 31	98.80 37	95.05 10	99.89 3	96.70 64	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 75	96.47 69	96.16 137	95.48 302	90.69 179	97.91 80	98.33 41	94.07 88	98.93 19	99.14 1	87.44 136	99.61 85	98.63 25	98.32 133	98.18 200

HFP-MVS		97.14 33	96.92 43	97.83 26	99.42 7	94.12 46	98.52 16	98.32 42	93.21 122	97.18 68	98.29 79	92.08 46	99.83 27	95.63 108	99.59 19	99.54 41

ACMMPR		97.07 37	96.84 47	97.79 30	99.44 6	93.88 53	98.52 16	98.31 43	93.21 122	97.15 70	98.33 73	91.35 62	99.86 9	95.63 108	99.59 19	99.62 23

test_fmvsmvis_n_1920		96.70 61	96.84 47	96.31 124	96.62 221	91.73 126	97.98 66	98.30 44	96.19 13	96.10 119	98.95 19	89.42 92	99.76 49	98.90 21	99.08 97	97.43 254

APDe-MVS		97.82 5	97.73 8	98.08 18	99.15 35	94.82 28	98.81 8	98.30 44	94.76 63	98.30 39	98.90 24	93.77 17	99.68 70	97.93 28	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 46	94.92 49	98.99 17	98.92 22	95.08 8

MSP-MVS		97.59 11	97.54 14	97.73 38	99.40 11	93.77 57	98.53 15	98.29 46	95.55 26	98.56 34	97.81 124	93.90 15	99.65 74	96.62 65	99.21 78	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 48	94.78 60	98.93 19	98.87 30	96.04 2	99.86 9	97.45 45	99.58 23	99.59 28

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 48					99.86 9	97.52 41	99.67 6	99.75 6

CP-MVS		97.02 39	96.81 52	97.64 45	99.33 23	93.54 60	98.80 9	98.28 48	92.99 135	96.45 106	98.30 78	91.90 50	99.85 18	95.61 110	99.68 4	99.54 41

test_fmvsmconf0.1_n		97.09 34	97.06 31	97.19 69	95.67 293	92.21 110	97.95 75	98.27 51	95.78 22	98.40 38	99.00 15	89.99 86	99.78 44	99.06 17	99.41 55	99.59 28

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 51	95.13 39	99.19 12	98.89 27	95.54 5	99.85 18	97.52 41	99.66 10	99.56 36

test_241102_TWO								98.27 51	95.13 39	98.93 19	98.89 27	94.99 11	99.85 18	97.52 41	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 51	95.09 42	99.19 12	98.81 36	95.54 5	99.65 74

SF-MVS		97.39 21	97.13 27	98.17 15	99.02 44	95.28 19	98.23 40	98.27 51	92.37 161	98.27 40	98.65 44	93.33 23	99.72 60	96.49 70	99.52 31	99.51 45

SteuartSystems-ACMMP		97.62 10	97.53 15	97.87 24	98.39 83	94.25 40	98.43 23	98.27 51	95.34 31	98.11 42	98.56 46	94.53 12	99.71 62	96.57 68	99.62 17	99.65 19
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 24	95.20 20		98.25 57	95.13 39	98.48 36	98.87 30	95.16 7

PVSNet_Blended_VisFu		95.27 111	94.91 118	96.38 120	98.20 102	90.86 172	97.27 178	98.25 57	90.21 251	94.18 182	97.27 172	87.48 135	99.73 56	93.53 166	97.77 156	98.55 161

region2R		97.07 37	96.84 47	97.77 34	99.46 2	93.79 55	98.52 16	98.24 59	93.19 125	97.14 71	98.34 70	91.59 57	99.87 7	95.46 114	99.59 19	99.64 21

PS-CasMVS		91.55 274	90.84 275	93.69 296	94.96 339	88.28 269	97.84 90	98.24 59	91.46 195	88.04 353	95.80 261	79.67 293	97.48 370	87.02 317	84.54 391	95.31 341

DU-MVS		92.90 217	92.04 226	95.49 188	94.95 340	92.83 85	97.16 191	98.24 59	93.02 134	90.13 287	95.71 268	83.47 208	97.85 333	91.71 208	83.93 397	95.78 312

9.14			96.75 57		98.93 52		97.73 109	98.23 62	91.28 204	97.88 50	98.44 59	93.00 26	99.65 74	95.76 101	99.47 41

reproduce_model		97.51 17	97.51 17	97.50 50	98.99 48	93.01 78	97.79 101	98.21 63	95.73 23	97.99 46	99.03 14	92.63 36	99.82 29	97.80 30	99.42 52	99.67 14

D2MVS		91.30 291	90.95 269	92.35 344	94.71 355	85.52 344	96.18 291	98.21 63	88.89 295	86.60 382	93.82 366	79.92 289	97.95 322	89.29 266	90.95 314	93.56 407

reproduce-ours		97.53 15	97.51 17	97.60 47	98.97 49	93.31 69	97.71 114	98.20 65	95.80 20	97.88 50	98.98 17	92.91 27	99.81 31	97.68 32	99.43 49	99.67 14

our_new_method		97.53 15	97.51 17	97.60 47	98.97 49	93.31 69	97.71 114	98.20 65	95.80 20	97.88 50	98.98 17	92.91 27	99.81 31	97.68 32	99.43 49	99.67 14

SDMVSNet		94.17 154	93.61 161	95.86 159	98.09 111	91.37 147	97.35 170	98.20 65	93.18 127	91.79 248	97.28 170	79.13 301	98.93 191	94.61 141	92.84 280	97.28 262

XVS		97.18 30	96.96 41	97.81 28	99.38 14	94.03 50	98.59 13	98.20 65	94.85 52	96.59 94	98.29 79	91.70 53	99.80 36	95.66 103	99.40 57	99.62 23

X-MVStestdata		91.71 263	89.67 329	97.81 28	99.38 14	94.03 50	98.59 13	98.20 65	94.85 52	96.59 94	32.69 468	91.70 53	99.80 36	95.66 103	99.40 57	99.62 23

ACMMP_NAP		97.20 29	96.86 45	98.23 11	99.09 36	95.16 22	97.60 133	98.19 70	92.82 149	97.93 49	98.74 41	91.60 56	99.86 9	96.26 75	99.52 31	99.67 14

CP-MVSNet		91.89 259	91.24 258	93.82 288	95.05 336	88.57 259	97.82 95	98.19 70	91.70 184	88.21 348	95.76 266	81.96 248	97.52 368	87.86 292	84.65 385	95.37 337

ZNCC-MVS		96.96 42	96.67 60	97.85 25	99.37 16	94.12 46	98.49 20	98.18 72	92.64 156	96.39 108	98.18 86	91.61 55	99.88 4	95.59 113	99.55 26	99.57 32

SMA-MVS		97.35 22	97.03 36	98.30 8	99.06 40	95.42 10	97.94 76	98.18 72	90.57 243	98.85 26	98.94 20	93.33 23	99.83 27	96.72 62	99.68 4	99.63 22
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
PEN-MVS		91.20 296	90.44 292	93.48 307	94.49 363	87.91 284	97.76 103	98.18 72	91.29 201	87.78 357	95.74 267	80.35 280	97.33 381	85.46 341	82.96 407	95.19 352

DELS-MVS		96.61 67	96.38 76	97.30 59	97.79 135	93.19 74	95.96 303	98.18 72	95.23 34	95.87 128	97.65 141	91.45 58	99.70 67	95.87 95	99.44 48	99.00 105
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		89.70 348	88.40 354	93.60 300	95.15 331	90.10 200	97.56 138	98.16 76	87.28 348	86.16 388	94.63 321	77.57 329	98.05 302	74.48 427	84.59 389	92.65 420

VNet		95.89 94	95.45 97	97.21 67	98.07 115	92.94 81	97.50 147	98.15 77	93.87 96	97.52 57	97.61 147	85.29 175	99.53 107	95.81 100	95.27 233	99.16 81

DeepPCF-MVS	93.97 1	96.61 67	97.09 29	95.15 202	98.09 111	86.63 317	96.00 301	98.15 77	95.43 27	97.95 48	98.56 46	93.40 21	99.36 132	96.77 59	99.48 40	99.45 55

SD-MVS		97.41 20	97.53 15	97.06 78	98.57 74	94.46 34	97.92 79	98.14 79	94.82 56	99.01 16	98.55 48	94.18 14	97.41 377	96.94 54	99.64 14	99.32 70
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
GST-MVS		96.85 50	96.52 66	97.82 27	99.36 20	94.14 45	98.29 30	98.13 80	92.72 152	96.70 86	98.06 93	91.35 62	99.86 9	94.83 130	99.28 69	99.47 54

UA-Net		95.95 91	95.53 93	97.20 68	97.67 142	92.98 80	97.65 123	98.13 80	94.81 58	96.61 92	98.35 67	88.87 100	99.51 112	90.36 241	97.35 169	99.11 90

QAPM		93.45 193	92.27 220	96.98 81	96.77 213	92.62 94	98.39 25	98.12 82	84.50 393	88.27 346	97.77 128	82.39 240	99.81 31	85.40 342	98.81 110	98.51 166

Vis-MVSNet		95.23 116	94.81 119	96.51 107	97.18 170	91.58 137	98.26 35	98.12 82	94.38 83	94.90 158	98.15 88	82.28 241	98.92 193	91.45 215	98.58 122	99.01 102
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 220	91.68 241	96.40 117	95.34 314	92.73 90	98.27 33	98.12 82	84.86 388	85.78 390	97.75 129	78.89 311	99.74 54	87.50 307	98.65 117	96.73 279

TranMVSNet+NR-MVSNet		92.50 229	91.63 242	95.14 203	94.76 351	92.07 115	97.53 144	98.11 85	92.90 146	89.56 309	96.12 245	83.16 215	97.60 360	89.30 265	83.20 406	95.75 316

CPTT-MVS		95.57 104	95.19 108	96.70 88	99.27 28	91.48 142	98.33 27	98.11 85	87.79 333	95.17 153	98.03 96	87.09 143	99.61 85	93.51 167	99.42 52	99.02 99

APD-MVS		96.95 43	96.60 62	98.01 20	99.03 43	94.93 27	97.72 112	98.10 87	91.50 193	98.01 45	98.32 75	92.33 42	99.58 93	94.85 128	99.51 34	99.53 44
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 48	96.60 62	97.64 45	99.40 11	93.44 62	98.50 19	98.09 88	93.27 121	95.95 126	98.33 73	91.04 70	99.88 4	95.20 117	99.57 25	99.60 27

ZD-MVS					99.05 41	94.59 32		98.08 89	89.22 281	97.03 76	98.10 89	92.52 39	99.65 74	94.58 143	99.31 67

MTGPA								98.08 89

MTAPA		97.08 35	96.78 55	97.97 23	99.37 16	94.42 36	97.24 180	98.08 89	95.07 43	96.11 118	98.59 45	90.88 76	99.90 2	96.18 87	99.50 36	99.58 31

CNVR-MVS		97.68 6	97.44 21	98.37 7	98.90 55	95.86 6	97.27 178	98.08 89	95.81 19	97.87 53	98.31 76	94.26 13	99.68 70	97.02 53	99.49 39	99.57 32

DP-MVS Recon		95.68 99	95.12 112	97.37 56	99.19 33	94.19 42	97.03 198	98.08 89	88.35 315	95.09 155	97.65 141	89.97 87	99.48 119	92.08 200	98.59 121	98.44 177

SR-MVS		97.01 40	96.86 45	97.47 52	99.09 36	93.27 71	97.98 66	98.07 94	93.75 99	97.45 59	98.48 56	91.43 60	99.59 90	96.22 78	99.27 70	99.54 41

MCST-MVS		97.18 30	96.84 47	98.20 14	99.30 26	95.35 15	97.12 194	98.07 94	93.54 109	96.08 120	97.69 136	93.86 16	99.71 62	96.50 69	99.39 59	99.55 39

NR-MVSNet		92.34 238	91.27 257	95.53 184	94.95 340	93.05 77	97.39 166	98.07 94	92.65 154	84.46 401	95.71 268	85.00 182	97.77 344	89.71 253	83.52 403	95.78 312

MP-MVS-pluss		96.70 61	96.27 79	97.98 22	99.23 32	94.71 29	96.96 209	98.06 97	90.67 233	95.55 142	98.78 39	91.07 69	99.86 9	96.58 67	99.55 26	99.38 66
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 54	96.71 59	97.12 72	99.01 47	92.31 106	97.98 66	98.06 97	93.11 131	97.44 60	98.55 48	90.93 74	99.55 103	96.06 88	99.25 75	99.51 45

MP-MVS		96.77 56	96.45 73	97.72 39	99.39 13	93.80 54	98.41 24	98.06 97	93.37 117	95.54 144	98.34 70	90.59 80	99.88 4	94.83 130	99.54 28	99.49 50
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 70	96.27 79	97.22 66	99.32 24	92.74 89	98.74 10	98.06 97	90.57 243	96.77 83	98.35 67	90.21 83	99.53 107	94.80 134	99.63 16	99.38 66

HPM-MVS		96.69 63	96.45 73	97.40 55	99.36 20	93.11 76	98.87 6	98.06 97	91.17 212	96.40 107	97.99 102	90.99 71	99.58 93	95.61 110	99.61 18	99.49 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 145	93.80 154	96.64 90	97.07 176	91.97 120	96.32 279	98.06 97	88.94 293	94.50 172	96.78 203	84.60 188	99.27 142	91.90 201	96.02 210	98.68 152

DeepC-MVS	93.07 3	96.06 85	95.66 90	97.29 60	97.96 123	93.17 75	97.30 176	98.06 97	93.92 94	93.38 208	98.66 42	86.83 145	99.73 56	95.60 112	99.22 77	98.96 110
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		97.30 26	97.03 36	98.11 17	98.77 58	95.06 25	97.34 171	98.04 104	95.96 14	97.09 74	97.88 114	93.18 25	99.71 62	95.84 99	99.17 86	99.56 36

DeepC-MVS_fast	93.89 2	96.93 45	96.64 61	97.78 32	98.64 69	94.30 37	97.41 161	98.04 104	94.81 58	96.59 94	98.37 65	91.24 65	99.64 82	95.16 119	99.52 31	99.42 61
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		96.88 47	96.80 53	97.11 74	99.02 44	92.34 104	97.98 66	98.03 106	93.52 112	97.43 62	98.51 51	91.40 61	99.56 101	96.05 89	99.26 73	99.43 59

RE-MVS-def			96.72 58		99.02 44	92.34 104	97.98 66	98.03 106	93.52 112	97.43 62	98.51 51	90.71 78		96.05 89	99.26 73	99.43 59

RPMNet		88.98 354	87.05 368	94.77 230	94.45 365	87.19 301	90.23 441	98.03 106	77.87 441	92.40 226	87.55 448	80.17 284	99.51 112	68.84 448	93.95 266	97.60 247

save fliter					98.91 54	94.28 38	97.02 200	98.02 109	95.35 30

TEST9					98.70 61	94.19 42	96.41 265	98.02 109	88.17 319	96.03 121	97.56 153	92.74 33	99.59 90

train_agg		96.30 81	95.83 89	97.72 39	98.70 61	94.19 42	96.41 265	98.02 109	88.58 306	96.03 121	97.56 153	92.73 34	99.59 90	95.04 121	99.37 63	99.39 64

test_8					98.67 63	94.06 49	96.37 273	98.01 112	88.58 306	95.98 125	97.55 155	92.73 34	99.58 93

agg_prior					98.67 63	93.79 55		98.00 113		95.68 138			99.57 100

test_prior				97.23 65	98.67 63	92.99 79		98.00 113					99.41 127			99.29 71

WR-MVS		92.34 238	91.53 246	94.77 230	95.13 333	90.83 173	96.40 269	97.98 115	91.88 179	89.29 318	95.54 279	82.50 236	97.80 340	89.79 252	85.27 376	95.69 319

HPM-MVS++		97.34 23	96.97 39	98.47 5	99.08 38	96.16 4	97.55 143	97.97 116	95.59 24	96.61 92	97.89 111	92.57 38	99.84 23	95.95 94	99.51 34	99.40 62

CANet		96.39 76	96.02 84	97.50 50	97.62 149	93.38 64	97.02 200	97.96 117	95.42 28	94.86 159	97.81 124	87.38 138	99.82 29	96.88 56	99.20 83	99.29 71

114514_t		93.95 169	93.06 186	96.63 94	99.07 39	91.61 134	97.46 158	97.96 117	77.99 439	93.00 217	97.57 151	86.14 159	99.33 134	89.22 269	99.15 90	98.94 114

IU-MVS					99.42 7	95.39 11		97.94 119	90.40 249	98.94 18				97.41 48	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 63	96.94 1		97.93 120					99.86 9	97.68 32	99.67 6	99.77 2

No_MVS				98.86 1	98.67 63	96.94 1		97.93 120					99.86 9	97.68 32	99.67 6	99.77 2

fmvsm_s_conf0.1_n_2		96.33 80	96.44 75	96.00 149	97.30 163	90.37 194	97.53 144	97.92 122	96.52 10	99.14 14	99.08 7	83.21 213	99.74 54	99.22 10	98.06 145	97.88 227

Anonymous20231211		90.63 320	89.42 336	94.27 260	98.24 95	89.19 245	98.05 58	97.89 123	79.95 431	88.25 347	94.96 302	72.56 370	98.13 285	89.70 254	85.14 378	95.49 323

原ACMM1				96.38 120	98.59 71	91.09 163		97.89 123	87.41 344	95.22 152	97.68 137	90.25 82	99.54 105	87.95 291	99.12 95	98.49 169

CDPH-MVS		95.97 90	95.38 102	97.77 34	98.93 52	94.44 35	96.35 274	97.88 125	86.98 352	96.65 90	97.89 111	91.99 48	99.47 120	92.26 189	99.46 42	99.39 64

test11								97.88 125

EIA-MVS		95.53 105	95.47 96	95.71 174	97.06 179	89.63 218	97.82 95	97.87 127	93.57 105	93.92 190	95.04 299	90.61 79	98.95 188	94.62 140	98.68 115	98.54 162

CS-MVS		96.86 48	97.06 31	96.26 130	98.16 107	91.16 161	99.09 3	97.87 127	95.30 32	97.06 75	98.03 96	91.72 51	98.71 228	97.10 51	99.17 86	98.90 123

无先验							95.79 314	97.87 127	83.87 401				99.65 74	87.68 301		98.89 128

3Dnovator+	91.43 4	95.40 106	94.48 138	98.16 16	96.90 194	95.34 16	98.48 21	97.87 127	94.65 69	88.53 338	98.02 98	83.69 204	99.71 62	93.18 175	98.96 105	99.44 57

VPNet		92.23 246	91.31 254	94.99 213	95.56 298	90.96 167	97.22 186	97.86 131	92.96 141	90.96 270	96.62 220	75.06 350	98.20 279	91.90 201	83.65 402	95.80 310

test_vis1_n_1920		94.17 154	94.58 130	92.91 328	97.42 161	82.02 398	97.83 93	97.85 132	94.68 66	98.10 43	98.49 53	70.15 389	99.32 136	97.91 29	98.82 109	97.40 256

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 132	94.92 49	98.73 29	98.87 30	95.08 8	99.84 23	97.52 41	99.67 6	99.48 52
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
TSAR-MVS + MP.		97.42 19	97.33 25	97.69 42	99.25 29	94.24 41	98.07 56	97.85 132	93.72 100	98.57 33	98.35 67	93.69 18	99.40 128	97.06 52	99.46 42	99.44 57
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SPE-MVS-test		96.89 46	97.04 35	96.45 114	98.29 88	91.66 133	99.03 4	97.85 132	95.84 17	96.90 78	97.97 104	91.24 65	98.75 218	96.92 55	99.33 65	98.94 114

test_fmvsmconf0.01_n		96.15 84	95.85 88	97.03 79	92.66 416	91.83 125	97.97 72	97.84 136	95.57 25	97.53 56	99.00 15	84.20 197	99.76 49	98.82 22	99.08 97	99.48 52

GDP-MVS		95.62 101	95.13 110	97.09 75	96.79 207	93.26 72	97.89 83	97.83 137	93.58 104	96.80 80	97.82 122	83.06 220	99.16 156	94.40 147	97.95 151	98.87 131

balanced_conf03		96.84 52	96.89 44	96.68 89	97.63 148	92.22 109	98.17 49	97.82 138	94.44 78	98.23 41	97.36 165	90.97 72	99.22 146	97.74 31	99.66 10	98.61 155

AdaColmap		94.34 149	93.68 159	96.31 124	98.59 71	91.68 132	96.59 254	97.81 139	89.87 259	92.15 236	97.06 186	83.62 207	99.54 105	89.34 264	98.07 144	97.70 240

MVSMamba_PlusPlus		96.51 70	96.48 68	96.59 98	98.07 115	91.97 120	98.14 50	97.79 140	90.43 247	97.34 65	97.52 156	91.29 64	99.19 149	98.12 27	99.64 14	98.60 156

KinetiMVS		95.26 112	94.75 124	96.79 86	96.99 188	92.05 116	97.82 95	97.78 141	94.77 62	96.46 104	97.70 134	80.62 274	99.34 133	92.37 188	98.28 135	98.97 107

mamv4		94.66 142	96.10 83	90.37 397	98.01 118	73.41 448	96.82 224	97.78 141	89.95 258	94.52 170	97.43 161	92.91 27	99.09 169	98.28 26	99.16 89	98.60 156

ETV-MVS		96.02 87	95.89 87	96.40 117	97.16 171	92.44 101	97.47 156	97.77 143	94.55 72	96.48 102	94.51 327	91.23 67	98.92 193	95.65 106	98.19 139	97.82 235

新几何1				97.32 58	98.60 70	93.59 59		97.75 144	81.58 422	95.75 133	97.85 118	90.04 85	99.67 72	86.50 323	99.13 93	98.69 151

旧先验1					98.38 84	93.38 64		97.75 144			98.09 91	92.30 45			99.01 103	99.16 81

EC-MVSNet		96.42 74	96.47 69	96.26 130	97.01 186	91.52 139	98.89 5	97.75 144	94.42 79	96.64 91	97.68 137	89.32 93	98.60 243	97.45 45	99.11 96	98.67 153

EI-MVSNet-Vis-set		96.51 70	96.47 69	96.63 94	98.24 95	91.20 155	96.89 216	97.73 147	94.74 64	96.49 101	98.49 53	90.88 76	99.58 93	96.44 71	98.32 133	99.13 85

PAPM_NR		95.01 123	94.59 129	96.26 130	98.89 56	90.68 180	97.24 180	97.73 147	91.80 180	92.93 222	96.62 220	89.13 96	99.14 161	89.21 270	97.78 155	98.97 107

Anonymous20240529		91.98 255	90.73 282	95.73 172	98.14 108	89.40 232	97.99 63	97.72 149	79.63 433	93.54 201	97.41 163	69.94 391	99.56 101	91.04 223	91.11 310	98.22 197

CHOSEN 280x420		93.12 205	92.72 203	94.34 254	96.71 218	87.27 297	90.29 440	97.72 149	86.61 359	91.34 259	95.29 287	84.29 196	98.41 259	93.25 173	98.94 106	97.35 259

EI-MVSNet-UG-set		96.34 79	96.30 78	96.47 111	98.20 102	90.93 169	96.86 219	97.72 149	94.67 67	96.16 117	98.46 57	90.43 81	99.58 93	96.23 77	97.96 150	98.90 123

LS3D		93.57 186	92.61 208	96.47 111	97.59 152	91.61 134	97.67 119	97.72 149	85.17 383	90.29 281	98.34 70	84.60 188	99.73 56	83.85 365	98.27 136	98.06 216

PAPR		94.18 153	93.42 175	96.48 110	97.64 146	91.42 146	95.55 328	97.71 153	88.99 290	92.34 232	95.82 260	89.19 94	99.11 164	86.14 329	97.38 167	98.90 123

UGNet		94.04 164	93.28 178	96.31 124	96.85 199	91.19 156	97.88 85	97.68 154	94.40 81	93.00 217	96.18 240	73.39 367	99.61 85	91.72 207	98.46 127	98.13 205
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				95.46 192	98.18 106	88.90 252		97.66 155	82.73 413	97.03 76	98.07 92	90.06 84	98.85 200	89.67 255	98.98 104	98.64 154

test12				97.65 43	98.46 75	94.26 39		97.66 155		95.52 145		90.89 75	99.46 121		99.25 75	99.22 78

DTE-MVSNet		90.56 321	89.75 327	93.01 324	93.95 378	87.25 298	97.64 127	97.65 157	90.74 228	87.12 370	95.68 271	79.97 288	97.00 394	83.33 366	81.66 413	94.78 379

TAPA-MVS	90.10 7	92.30 241	91.22 260	95.56 181	98.33 86	89.60 220	96.79 228	97.65 157	81.83 419	91.52 254	97.23 175	87.94 119	98.91 195	71.31 442	98.37 131	98.17 203
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 206	92.45 216	95.05 207	98.09 111	89.21 242	96.89 216	97.64 159	93.18 127	91.79 248	97.28 170	75.35 349	98.65 237	88.99 275	92.84 280	97.28 262

test_cas_vis1_n_1920		94.48 147	94.55 134	94.28 259	96.78 211	86.45 322	97.63 129	97.64 159	93.32 120	97.68 55	98.36 66	73.75 365	99.08 172	96.73 61	99.05 99	97.31 261

NormalMVS		96.36 78	96.11 82	97.12 72	99.37 16	92.90 83	97.99 63	97.63 161	95.92 15	96.57 97	97.93 106	85.34 173	99.50 115	94.99 124	99.21 78	98.97 107

Elysia		94.00 166	93.12 183	96.64 90	96.08 277	92.72 91	97.50 147	97.63 161	91.15 214	94.82 160	97.12 181	74.98 352	99.06 178	90.78 228	98.02 146	98.12 207

StellarMVS		94.00 166	93.12 183	96.64 90	96.08 277	92.72 91	97.50 147	97.63 161	91.15 214	94.82 160	97.12 181	74.98 352	99.06 178	90.78 228	98.02 146	98.12 207

cdsmvs_eth3d_5k		23.24 438	30.99 440	0.00 456	0.00 479	0.00 481	0.00 467	97.63 161	0.00 474	0.00 475	96.88 199	84.38 193	0.00 475	0.00 474	0.00 473	0.00 471

DPM-MVS		95.69 98	94.92 117	98.01 20	98.08 114	95.71 9	95.27 344	97.62 165	90.43 247	95.55 142	97.07 185	91.72 51	99.50 115	89.62 257	98.94 106	98.82 137

sasdasda		96.02 87	95.45 97	97.75 36	97.59 152	95.15 23	98.28 31	97.60 166	94.52 74	96.27 112	96.12 245	87.65 126	99.18 152	96.20 83	94.82 242	98.91 120

canonicalmvs		96.02 87	95.45 97	97.75 36	97.59 152	95.15 23	98.28 31	97.60 166	94.52 74	96.27 112	96.12 245	87.65 126	99.18 152	96.20 83	94.82 242	98.91 120

test222					98.24 95	92.21 110	95.33 339	97.60 166	79.22 435	95.25 150	97.84 120	88.80 102			99.15 90	98.72 148

cascas		91.20 296	90.08 309	94.58 240	94.97 338	89.16 246	93.65 405	97.59 169	79.90 432	89.40 313	92.92 392	75.36 348	98.36 267	92.14 194	94.75 245	96.23 289

h-mvs33		94.15 156	93.52 167	96.04 143	97.81 134	90.22 198	97.62 131	97.58 170	95.19 35	96.74 84	97.45 158	83.67 205	99.61 85	95.85 97	79.73 420	98.29 193

MGCFI-Net		95.94 92	95.40 101	97.56 49	97.59 152	94.62 31	98.21 43	97.57 171	94.41 80	96.17 116	96.16 243	87.54 131	99.17 154	96.19 85	94.73 247	98.91 120

MVSFormer		95.37 107	95.16 109	95.99 150	96.34 253	91.21 153	98.22 41	97.57 171	91.42 197	96.22 114	97.32 166	86.20 157	97.92 327	94.07 153	99.05 99	98.85 133

test_djsdf		93.07 208	92.76 198	94.00 273	93.49 395	88.70 256	98.22 41	97.57 171	91.42 197	90.08 293	95.55 278	82.85 227	97.92 327	94.07 153	91.58 301	95.40 334

OMC-MVS		95.09 121	94.70 125	96.25 133	98.46 75	91.28 149	96.43 261	97.57 171	92.04 175	94.77 164	97.96 105	87.01 144	99.09 169	91.31 217	96.77 190	98.36 184

viewcassd2359sk11		95.26 112	95.09 113	95.80 164	96.95 192	89.72 216	96.80 227	97.56 175	92.21 167	95.37 148	97.80 126	87.17 142	98.77 213	94.82 132	97.10 182	98.90 123

PS-MVSNAJss		93.74 179	93.51 168	94.44 248	93.91 380	89.28 240	97.75 105	97.56 175	92.50 157	89.94 295	96.54 223	88.65 105	98.18 282	93.83 162	90.90 315	95.86 304

casdiffmvs_mvg		95.81 97	95.57 91	96.51 107	96.87 196	91.49 140	97.50 147	97.56 175	93.99 92	95.13 154	97.92 109	87.89 120	98.78 210	95.97 93	97.33 170	99.26 75
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jajsoiax		92.42 234	91.89 234	94.03 272	93.33 403	88.50 263	97.73 109	97.53 178	92.00 177	88.85 330	96.50 225	75.62 347	98.11 289	93.88 160	91.56 302	95.48 324

mvs_tets		92.31 240	91.76 237	93.94 281	93.41 400	88.29 268	97.63 129	97.53 178	92.04 175	88.76 333	96.45 227	74.62 357	98.09 294	93.91 158	91.48 303	95.45 329

dcpmvs_2		96.37 77	97.05 34	94.31 257	98.96 51	84.11 371	97.56 138	97.51 180	93.92 94	97.43 62	98.52 50	92.75 32	99.32 136	97.32 50	99.50 36	99.51 45

HQP_MVS		93.78 178	93.43 173	94.82 223	96.21 257	89.99 204	97.74 107	97.51 180	94.85 52	91.34 259	96.64 213	81.32 260	98.60 243	93.02 181	92.23 289	95.86 304

plane_prior5								97.51 180					98.60 243	93.02 181	92.23 289	95.86 304

viewmanbaseed2359cas		95.24 115	95.02 115	95.91 153	96.87 196	89.98 206	96.82 224	97.49 183	92.26 163	95.47 146	97.82 122	86.47 150	98.69 229	94.80 134	97.20 178	99.06 97

reproduce_monomvs		91.30 291	91.10 264	91.92 358	96.82 204	82.48 392	97.01 203	97.49 183	94.64 70	88.35 341	95.27 290	70.53 384	98.10 290	95.20 117	84.60 388	95.19 352

viewmacassd2359aftdt		95.07 122	94.80 120	95.87 156	96.53 234	89.84 212	96.90 215	97.48 185	92.44 158	95.36 149	97.89 111	85.23 176	98.68 231	94.40 147	97.00 185	99.09 92

PS-MVSNAJ		95.37 107	95.33 104	95.49 188	97.35 162	90.66 181	95.31 341	97.48 185	93.85 97	96.51 100	95.70 270	88.65 105	99.65 74	94.80 134	98.27 136	96.17 293

API-MVS		94.84 134	94.49 137	95.90 154	97.90 129	92.00 119	97.80 99	97.48 185	89.19 282	94.81 162	96.71 206	88.84 101	99.17 154	88.91 277	98.76 113	96.53 282

MG-MVS		95.61 102	95.38 102	96.31 124	98.42 79	90.53 183	96.04 298	97.48 185	93.47 114	95.67 139	98.10 89	89.17 95	99.25 143	91.27 218	98.77 112	99.13 85

MAR-MVS		94.22 152	93.46 170	96.51 107	98.00 120	92.19 113	97.67 119	97.47 189	88.13 323	93.00 217	95.84 258	84.86 186	99.51 112	87.99 290	98.17 141	97.83 234
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		92.98 212	92.53 212	94.32 255	96.12 272	89.20 243	95.28 342	97.47 189	92.66 153	89.90 296	95.62 274	80.58 275	98.40 260	92.73 186	92.40 287	95.38 336
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 289	90.22 305	94.68 234	94.86 347	87.86 285	97.23 184	97.46 191	87.99 324	89.90 296	96.92 197	66.35 419	98.23 276	90.30 242	90.99 313	97.96 221

nrg030		94.05 163	93.31 177	96.27 129	95.22 325	94.59 32	98.34 26	97.46 191	92.93 142	91.21 268	96.64 213	87.23 141	98.22 277	94.99 124	85.80 368	95.98 303

XVG-OURS		93.72 180	93.35 176	94.80 228	97.07 176	88.61 257	94.79 360	97.46 191	91.97 178	93.99 187	97.86 117	81.74 254	98.88 197	92.64 187	92.67 285	96.92 274

LPG-MVS_test		92.94 215	92.56 209	94.10 267	96.16 267	88.26 270	97.65 123	97.46 191	91.29 201	90.12 289	97.16 178	79.05 304	98.73 222	92.25 191	91.89 297	95.31 341

LGP-MVS_train				94.10 267	96.16 267	88.26 270		97.46 191	91.29 201	90.12 289	97.16 178	79.05 304	98.73 222	92.25 191	91.89 297	95.31 341

MVS		91.71 263	90.44 292	95.51 185	95.20 327	91.59 136	96.04 298	97.45 196	73.44 449	87.36 366	95.60 275	85.42 172	99.10 166	85.97 334	97.46 162	95.83 308

XVG-OURS-SEG-HR		93.86 175	93.55 163	94.81 225	97.06 179	88.53 262	95.28 342	97.45 196	91.68 185	94.08 186	97.68 137	82.41 239	98.90 196	93.84 161	92.47 286	96.98 270

baseline		95.58 103	95.42 100	96.08 139	96.78 211	90.41 189	97.16 191	97.45 196	93.69 103	95.65 140	97.85 118	87.29 139	98.68 231	95.66 103	97.25 176	99.13 85

ab-mvs		93.57 186	92.55 210	96.64 90	97.28 165	91.96 122	95.40 335	97.45 196	89.81 264	93.22 214	96.28 236	79.62 295	99.46 121	90.74 231	93.11 277	98.50 167

xiu_mvs_v2_base		95.32 110	95.29 105	95.40 193	97.22 167	90.50 184	95.44 334	97.44 200	93.70 102	96.46 104	96.18 240	88.59 109	99.53 107	94.79 137	97.81 154	96.17 293

1314		92.81 224	92.03 227	95.14 203	95.33 317	89.52 227	96.04 298	97.44 200	87.72 337	86.25 387	95.33 286	83.84 202	98.79 209	89.26 267	97.05 184	97.11 268

casdiffmvs		95.64 100	95.49 94	96.08 139	96.76 216	90.45 186	97.29 177	97.44 200	94.00 91	95.46 147	97.98 103	87.52 134	98.73 222	95.64 107	97.33 170	99.08 94
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt07		94.76 139	94.68 126	95.01 211	96.76 216	87.41 293	96.38 271	97.43 203	92.65 154	94.52 170	97.75 129	85.55 170	98.81 206	94.36 149	96.69 195	98.82 137

XXY-MVS		92.16 248	91.23 259	94.95 219	94.75 352	90.94 168	97.47 156	97.43 203	89.14 283	88.90 326	96.43 228	79.71 292	98.24 275	89.56 258	87.68 349	95.67 320

anonymousdsp		92.16 248	91.55 245	93.97 277	92.58 418	89.55 224	97.51 146	97.42 205	89.42 276	88.40 340	94.84 309	80.66 273	97.88 332	91.87 203	91.28 307	94.48 387

Effi-MVS+		94.93 128	94.45 139	96.36 122	96.61 222	91.47 143	96.41 265	97.41 206	91.02 220	94.50 172	95.92 254	87.53 132	98.78 210	93.89 159	96.81 189	98.84 136

RRT-MVS		94.51 145	94.35 142	94.98 215	96.40 247	86.55 320	97.56 138	97.41 206	93.19 125	94.93 157	97.04 187	79.12 302	99.30 140	96.19 85	97.32 172	99.09 92

HQP3-MVS								97.39 208							92.10 294

HQP-MVS		93.19 202	92.74 201	94.54 243	95.86 283	89.33 236	96.65 245	97.39 208	93.55 106	90.14 283	95.87 256	80.95 264	98.50 253	92.13 197	92.10 294	95.78 312

PLC	91.00 6	94.11 160	93.43 173	96.13 138	98.58 73	91.15 162	96.69 241	97.39 208	87.29 347	91.37 258	96.71 206	88.39 110	99.52 111	87.33 310	97.13 181	97.73 238
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
diffmvs_AUTHOR		95.33 109	95.27 106	95.50 187	96.37 251	89.08 248	96.08 296	97.38 211	93.09 133	96.53 99	97.74 131	86.45 151	98.68 231	96.32 73	97.48 161	98.75 144

v7n		90.76 313	89.86 320	93.45 309	93.54 392	87.60 291	97.70 117	97.37 212	88.85 296	87.65 359	94.08 357	81.08 263	98.10 290	84.68 351	83.79 401	94.66 384

UnsupCasMVSNet_eth		85.99 390	84.45 394	90.62 393	89.97 436	82.40 395	93.62 406	97.37 212	89.86 260	78.59 439	92.37 402	65.25 428	95.35 428	82.27 379	70.75 447	94.10 398

viewdifsd2359ckpt13		94.87 132	94.52 135	95.90 154	96.88 195	90.19 199	96.92 212	97.36 214	91.26 205	94.65 166	97.46 157	85.79 165	98.64 238	93.64 165	96.76 191	98.88 130

ACMM	89.79 8	92.96 213	92.50 214	94.35 252	96.30 255	88.71 255	97.58 134	97.36 214	91.40 199	90.53 276	96.65 212	79.77 291	98.75 218	91.24 219	91.64 299	95.59 322
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 123	94.76 121	95.75 169	96.58 225	91.71 129	96.25 284	97.35 216	92.99 135	96.70 86	96.63 217	82.67 231	99.44 124	96.22 78	97.46 162	96.11 299

xiu_mvs_v1_base		95.01 123	94.76 121	95.75 169	96.58 225	91.71 129	96.25 284	97.35 216	92.99 135	96.70 86	96.63 217	82.67 231	99.44 124	96.22 78	97.46 162	96.11 299

xiu_mvs_v1_base_debi		95.01 123	94.76 121	95.75 169	96.58 225	91.71 129	96.25 284	97.35 216	92.99 135	96.70 86	96.63 217	82.67 231	99.44 124	96.22 78	97.46 162	96.11 299

diffmvs		95.25 114	95.13 110	95.63 177	96.43 246	89.34 235	95.99 302	97.35 216	92.83 148	96.31 110	97.37 164	86.44 152	98.67 234	96.26 75	97.19 179	98.87 131
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		94.71 141	94.02 150	96.79 86	97.71 140	92.05 116	96.59 254	97.35 216	90.61 239	94.64 167	96.93 194	86.41 153	99.39 129	91.20 220	94.71 248	98.94 114

SSM_0407		94.54 144	94.12 149	95.80 164	96.79 207	90.38 191	96.79 228	97.29 221	91.24 206	93.68 194	97.60 148	85.03 180	98.67 234	92.14 194	96.51 200	98.35 186

SSM_0404		94.73 140	94.31 144	95.98 151	97.05 181	90.90 171	97.01 203	97.29 221	91.24 206	94.17 183	97.60 148	85.03 180	98.76 215	92.14 194	97.30 173	98.29 193

F-COLMAP		93.58 184	92.98 190	95.37 194	98.40 81	88.98 250	97.18 189	97.29 221	87.75 336	90.49 277	97.10 184	85.21 177	99.50 115	86.70 320	96.72 194	97.63 242

VortexMVS		92.88 219	92.64 205	93.58 302	96.58 225	87.53 292	96.93 211	97.28 224	92.78 151	89.75 301	94.99 300	82.73 230	97.76 345	94.60 142	88.16 344	95.46 327

XVG-ACMP-BASELINE		90.93 309	90.21 306	93.09 322	94.31 371	85.89 337	95.33 339	97.26 225	91.06 219	89.38 314	95.44 284	68.61 402	98.60 243	89.46 260	91.05 311	94.79 377

PCF-MVS	89.48 11	91.56 273	89.95 317	96.36 122	96.60 223	92.52 99	92.51 425	97.26 225	79.41 434	88.90 326	96.56 222	84.04 201	99.55 103	77.01 418	97.30 173	97.01 269
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 228	92.14 223	94.05 270	96.40 247	88.20 273	97.36 169	97.25 227	91.52 192	88.30 344	96.64 213	78.46 316	98.72 227	91.86 204	91.48 303	95.23 348
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 184	93.46 170	93.94 281	96.19 261	86.16 331	93.73 400	97.24 228	91.54 188	93.50 203	97.04 187	85.64 168	96.91 397	90.68 233	95.59 224	98.76 140

IMVS_0407		93.94 170	93.75 156	94.49 245	96.19 261	86.16 331	96.35 274	97.24 228	91.54 188	93.50 203	97.04 187	85.64 168	98.54 250	90.68 233	95.59 224	98.76 140

IMVS_0404		92.44 232	91.92 232	94.00 273	96.19 261	86.16 331	93.84 397	97.24 228	91.54 188	88.17 350	97.04 187	76.96 334	97.09 388	90.68 233	95.59 224	98.76 140

IMVS_0403		93.98 168	93.79 155	94.55 242	96.19 261	86.16 331	96.35 274	97.24 228	91.54 188	93.59 198	97.04 187	85.86 162	98.73 222	90.68 233	95.59 224	98.76 140

OPM-MVS		93.28 198	92.76 198	94.82 223	94.63 358	90.77 176	96.65 245	97.18 232	93.72 100	91.68 252	97.26 173	79.33 299	98.63 240	92.13 197	92.28 288	95.07 355
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 217	92.02 228	95.56 181	98.19 104	90.80 174	95.27 344	97.18 232	87.96 325	91.86 247	95.68 271	80.44 278	98.99 186	84.01 360	97.54 160	96.89 275

alignmvs		95.87 96	95.23 107	97.78 32	97.56 158	95.19 21	97.86 86	97.17 234	94.39 82	96.47 103	96.40 230	85.89 161	99.20 148	96.21 82	95.11 238	98.95 113

MVS_Test		94.89 130	94.62 128	95.68 175	96.83 202	89.55 224	96.70 239	97.17 234	91.17 212	95.60 141	96.11 249	87.87 122	98.76 215	93.01 183	97.17 180	98.72 148

Fast-Effi-MVS+		93.46 190	92.75 200	95.59 180	96.77 213	90.03 201	96.81 226	97.13 236	88.19 318	91.30 262	94.27 345	86.21 156	98.63 240	87.66 302	96.46 206	98.12 207

EI-MVSNet		93.03 210	92.88 194	93.48 307	95.77 289	86.98 306	96.44 259	97.12 237	90.66 235	91.30 262	97.64 144	86.56 147	98.05 302	89.91 248	90.55 319	95.41 331

MVSTER		93.20 201	92.81 197	94.37 251	96.56 229	89.59 221	97.06 197	97.12 237	91.24 206	91.30 262	95.96 252	82.02 247	98.05 302	93.48 168	90.55 319	95.47 326

viewmambaseed2359dif		94.28 150	94.14 147	94.71 233	96.21 257	86.97 307	95.93 305	97.11 239	89.00 289	95.00 156	97.70 134	86.02 160	98.59 247	93.71 164	96.59 199	98.57 160

test_yl		94.78 137	94.23 145	96.43 115	97.74 138	91.22 151	96.85 220	97.10 240	91.23 209	95.71 135	96.93 194	84.30 194	99.31 138	93.10 176	95.12 236	98.75 144

DCV-MVSNet		94.78 137	94.23 145	96.43 115	97.74 138	91.22 151	96.85 220	97.10 240	91.23 209	95.71 135	96.93 194	84.30 194	99.31 138	93.10 176	95.12 236	98.75 144

LTVRE_ROB	88.41 13	90.99 305	89.92 319	94.19 261	96.18 265	89.55 224	96.31 280	97.09 242	87.88 328	85.67 391	95.91 255	78.79 312	98.57 248	81.50 382	89.98 324	94.44 390
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
viewmsd2359difaftdt		93.46 190	93.23 180	94.17 262	96.12 272	85.42 346	96.43 261	97.08 243	92.91 143	94.21 179	98.00 100	80.82 270	98.74 220	94.41 146	89.05 333	98.34 190

test_fmvs1_n		92.73 226	92.88 194	92.29 348	96.08 277	81.05 406	97.98 66	97.08 243	90.72 230	96.79 82	98.18 86	63.07 432	98.45 257	97.62 39	98.42 130	97.36 257

v10		91.04 303	90.23 303	93.49 306	94.12 374	88.16 276	97.32 174	97.08 243	88.26 317	88.29 345	94.22 350	82.17 244	97.97 314	86.45 324	84.12 395	94.33 393

viewdifsd2359ckpt11		93.46 190	93.22 181	94.17 262	96.11 274	85.42 346	96.43 261	97.07 246	92.91 143	94.20 180	98.00 100	80.82 270	98.73 222	94.42 145	89.04 335	98.34 190

mamba_0408		93.70 181	92.99 187	95.83 161	96.79 207	90.38 191	88.69 450	97.07 246	90.96 222	93.68 194	97.31 168	84.97 183	98.76 215	90.95 224	96.51 200	98.35 186

SSM_04072		93.51 189	92.99 187	95.05 207	96.79 207	90.38 191	88.69 450	97.07 246	90.96 222	93.68 194	97.31 168	84.97 183	96.42 408	90.95 224	96.51 200	98.35 186

v144192		91.06 302	90.28 299	93.39 310	93.66 389	87.23 300	96.83 223	97.07 246	87.43 343	89.69 304	94.28 344	81.48 257	98.00 309	87.18 314	84.92 384	94.93 363

v1192		91.07 301	90.23 303	93.58 302	93.70 386	87.82 287	96.73 235	97.07 246	87.77 334	89.58 307	94.32 342	80.90 268	97.97 314	86.52 322	85.48 371	94.95 359

v8		91.29 293	90.53 291	93.57 304	94.15 373	88.12 277	97.34 171	97.06 251	88.99 290	88.32 343	94.26 347	83.08 218	98.01 308	87.62 304	83.92 399	94.57 386

mvs_anonymous		93.82 176	93.74 157	94.06 269	96.44 245	85.41 348	95.81 312	97.05 252	89.85 262	90.09 292	96.36 232	87.44 136	97.75 347	93.97 155	96.69 195	99.02 99

IterMVS-LS		92.29 242	91.94 231	93.34 312	96.25 256	86.97 307	96.57 257	97.05 252	90.67 233	89.50 312	94.80 312	86.59 146	97.64 355	89.91 248	86.11 366	95.40 334
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 311	90.03 314	93.29 314	93.55 391	86.96 309	96.74 234	97.04 254	87.36 345	89.52 311	94.34 339	80.23 283	97.97 314	86.27 325	85.21 377	94.94 361

CDS-MVSNet		94.14 159	93.54 164	95.93 152	96.18 265	91.46 144	96.33 278	97.04 254	88.97 292	93.56 199	96.51 224	87.55 130	97.89 331	89.80 251	95.95 212	98.44 177
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 347	89.26 340	91.19 382	95.16 328	80.29 417	94.53 367	97.03 256	91.79 181	88.86 329	94.10 354	69.94 391	97.82 337	85.29 343	86.66 362	95.45 329

v1144		91.37 286	90.60 287	93.68 297	93.89 381	88.23 272	96.84 222	97.03 256	88.37 314	89.69 304	94.39 334	82.04 246	97.98 311	87.80 294	85.37 373	94.84 369

v1240		90.70 317	89.85 321	93.23 316	93.51 394	86.80 310	96.61 251	97.02 258	87.16 350	89.58 307	94.31 343	79.55 296	97.98 311	85.52 340	85.44 372	94.90 366

EPP-MVSNet		95.22 117	95.04 114	95.76 167	97.49 159	89.56 223	98.67 11	97.00 259	90.69 231	94.24 178	97.62 146	89.79 90	98.81 206	93.39 172	96.49 204	98.92 119

V42		91.58 272	90.87 271	93.73 292	94.05 377	88.50 263	97.32 174	96.97 260	88.80 302	89.71 302	94.33 340	82.54 235	98.05 302	89.01 274	85.07 380	94.64 385

test_fmvs1		93.21 200	93.53 165	92.25 351	96.55 231	81.20 405	97.40 165	96.96 261	90.68 232	96.80 80	98.04 95	69.25 397	98.40 260	97.58 40	98.50 123	97.16 267

FMVSNet2		91.31 290	90.08 309	94.99 213	96.51 238	92.21 110	97.41 161	96.95 262	88.82 299	88.62 335	94.75 314	73.87 361	97.42 376	85.20 346	88.55 341	95.35 338

ACMH	87.59 16	90.53 322	89.42 336	93.87 286	96.21 257	87.92 282	97.24 180	96.94 263	88.45 312	83.91 411	96.27 237	71.92 373	98.62 242	84.43 354	89.43 330	95.05 357
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 287	90.27 300	94.59 236	96.51 238	91.18 158	97.50 147	96.93 264	88.82 299	89.35 315	94.51 327	73.87 361	97.29 383	86.12 330	88.82 336	95.31 341

test1		91.35 287	90.27 300	94.59 236	96.51 238	91.18 158	97.50 147	96.93 264	88.82 299	89.35 315	94.51 327	73.87 361	97.29 383	86.12 330	88.82 336	95.31 341

FMVSNet3		91.78 261	90.69 285	95.03 210	96.53 234	92.27 108	97.02 200	96.93 264	89.79 265	89.35 315	94.65 320	77.01 332	97.47 371	86.12 330	88.82 336	95.35 338

FMVSNet1		89.88 342	88.31 355	94.59 236	95.41 307	91.18 158	97.50 147	96.93 264	86.62 358	87.41 364	94.51 327	65.94 424	97.29 383	83.04 369	87.43 352	95.31 341

GeoE		93.89 173	93.28 178	95.72 173	96.96 191	89.75 215	98.24 39	96.92 268	89.47 273	92.12 238	97.21 176	84.42 192	98.39 265	87.71 297	96.50 203	99.01 102

SymmetryMVS		95.94 92	95.54 92	97.15 70	97.85 131	92.90 83	97.99 63	96.91 269	95.92 15	96.57 97	97.93 106	85.34 173	99.50 115	94.99 124	96.39 207	99.05 98

miper_enhance_ethall		91.54 276	91.01 267	93.15 320	95.35 313	87.07 305	93.97 389	96.90 270	86.79 356	89.17 322	93.43 386	86.55 148	97.64 355	89.97 247	86.93 357	94.74 381

eth_miper_zixun_eth		91.02 304	90.59 288	92.34 346	95.33 317	84.35 367	94.10 386	96.90 270	88.56 308	88.84 331	94.33 340	84.08 199	97.60 360	88.77 280	84.37 393	95.06 356

TAMVS		94.01 165	93.46 170	95.64 176	96.16 267	90.45 186	96.71 238	96.89 272	89.27 280	93.46 206	96.92 197	87.29 139	97.94 324	88.70 282	95.74 218	98.53 163

miper_ehance_all_eth		91.59 270	91.13 263	92.97 326	95.55 299	86.57 318	94.47 370	96.88 273	87.77 334	88.88 328	94.01 359	86.22 155	97.54 364	89.49 259	86.93 357	94.79 377

v2v482		91.59 270	90.85 274	93.80 289	93.87 382	88.17 275	96.94 210	96.88 273	89.54 270	89.53 310	94.90 306	81.70 255	98.02 307	89.25 268	85.04 382	95.20 349

CNLPA		94.28 150	93.53 165	96.52 103	98.38 84	92.55 98	96.59 254	96.88 273	90.13 255	91.91 244	97.24 174	85.21 177	99.09 169	87.64 303	97.83 153	97.92 224

PAPM		91.52 277	90.30 298	95.20 200	95.30 320	89.83 213	93.38 411	96.85 276	86.26 366	88.59 336	95.80 261	84.88 185	98.15 284	75.67 423	95.93 213	97.63 242

c3_l		91.38 284	90.89 270	92.88 330	95.58 297	86.30 325	94.68 362	96.84 277	88.17 319	88.83 332	94.23 348	85.65 167	97.47 371	89.36 263	84.63 386	94.89 367

pm-mvs1		90.72 316	89.65 331	93.96 278	94.29 372	89.63 218	97.79 101	96.82 278	89.07 285	86.12 389	95.48 283	78.61 314	97.78 342	86.97 318	81.67 412	94.46 388

test_vis1_n		92.37 237	92.26 221	92.72 336	94.75 352	82.64 388	98.02 60	96.80 279	91.18 211	97.77 54	97.93 106	58.02 442	98.29 273	97.63 37	98.21 138	97.23 265

CMPMVS	62.92 21	85.62 395	84.92 390	87.74 420	89.14 441	73.12 450	94.17 384	96.80 279	73.98 446	73.65 448	94.93 304	66.36 418	97.61 359	83.95 362	91.28 307	92.48 425
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 329	89.77 325	91.78 367	94.33 369	84.72 364	95.55 328	96.73 281	86.17 368	86.36 386	95.28 289	71.28 378	97.80 340	84.09 359	98.14 142	92.81 417

Effi-MVS+-dtu		93.08 207	93.21 182	92.68 339	96.02 280	83.25 381	97.14 193	96.72 282	93.85 97	91.20 269	93.44 383	83.08 218	98.30 272	91.69 210	95.73 219	96.50 284

TSAR-MVS + GP.		96.69 63	96.49 67	97.27 63	98.31 87	93.39 63	96.79 228	96.72 282	94.17 86	97.44 60	97.66 140	92.76 31	99.33 134	96.86 58	97.76 157	99.08 94

1112_ss		93.37 195	92.42 217	96.21 134	97.05 181	90.99 165	96.31 280	96.72 282	86.87 355	89.83 299	96.69 210	86.51 149	99.14 161	88.12 287	93.67 271	98.50 167

PVSNet	86.66 18	92.24 245	91.74 240	93.73 292	97.77 136	83.69 378	92.88 420	96.72 282	87.91 327	93.00 217	94.86 308	78.51 315	99.05 181	86.53 321	97.45 166	98.47 172

miper_lstm_enhance		90.50 325	90.06 313	91.83 363	95.33 317	83.74 375	93.86 395	96.70 286	87.56 341	87.79 356	93.81 367	83.45 210	96.92 396	87.39 308	84.62 387	94.82 372

v148		90.99 305	90.38 294	92.81 333	93.83 383	85.80 338	96.78 232	96.68 287	89.45 275	88.75 334	93.93 363	82.96 224	97.82 337	87.83 293	83.25 404	94.80 375

ACMH+	87.92 14	90.20 333	89.18 342	93.25 315	96.48 241	86.45 322	96.99 206	96.68 287	88.83 298	84.79 400	96.22 239	70.16 388	98.53 251	84.42 355	88.04 345	94.77 380

CANet_DTU		94.37 148	93.65 160	96.55 100	96.46 244	92.13 114	96.21 288	96.67 289	94.38 83	93.53 202	97.03 192	79.34 298	99.71 62	90.76 230	98.45 128	97.82 235

cl____		90.96 308	90.32 296	92.89 329	95.37 311	86.21 328	94.46 372	96.64 290	87.82 330	88.15 351	94.18 351	82.98 222	97.54 364	87.70 298	85.59 369	94.92 365

HY-MVS	89.66 9	93.87 174	92.95 191	96.63 94	97.10 175	92.49 100	95.64 325	96.64 290	89.05 287	93.00 217	95.79 264	85.77 166	99.45 123	89.16 273	94.35 250	97.96 221

Test_1112_low_res		92.84 222	91.84 235	95.85 160	97.04 183	89.97 208	95.53 330	96.64 290	85.38 378	89.65 306	95.18 294	85.86 162	99.10 166	87.70 298	93.58 276	98.49 169

DIV-MVS_self_test		90.97 307	90.33 295	92.88 330	95.36 312	86.19 330	94.46 372	96.63 293	87.82 330	88.18 349	94.23 348	82.99 221	97.53 366	87.72 295	85.57 370	94.93 363

Fast-Effi-MVS+-dtu		92.29 242	91.99 229	93.21 318	95.27 321	85.52 344	97.03 198	96.63 293	92.09 173	89.11 324	95.14 296	80.33 281	98.08 295	87.54 306	94.74 246	96.03 302

UnsupCasMVSNet_bld		82.13 412	79.46 417	90.14 400	88.00 449	82.47 393	90.89 438	96.62 295	78.94 436	75.61 443	84.40 454	56.63 445	96.31 410	77.30 415	66.77 455	91.63 435

cl22		91.21 295	90.56 290	93.14 321	96.09 276	86.80 310	94.41 374	96.58 296	87.80 332	88.58 337	93.99 361	80.85 269	97.62 358	89.87 250	86.93 357	94.99 358

jason		94.84 134	94.39 141	96.18 136	95.52 300	90.93 169	96.09 295	96.52 297	89.28 279	96.01 124	97.32 166	84.70 187	98.77 213	95.15 120	98.91 108	98.85 133
jason: jason.
tt0805		91.09 300	90.07 312	94.16 265	95.61 295	88.31 267	97.56 138	96.51 298	89.56 269	89.17 322	95.64 273	67.08 416	98.38 266	91.07 222	88.44 342	95.80 310

AUN-MVS		91.76 262	90.75 280	94.81 225	97.00 187	88.57 259	96.65 245	96.49 299	89.63 267	92.15 236	96.12 245	78.66 313	98.50 253	90.83 226	79.18 423	97.36 257

hse-mvs2		93.45 193	92.99 187	94.81 225	97.02 185	88.59 258	96.69 241	96.47 300	95.19 35	96.74 84	96.16 243	83.67 205	98.48 256	95.85 97	79.13 424	97.35 259

SD_0403		90.01 337	90.02 315	89.96 403	95.65 294	76.76 438	95.76 316	96.46 301	90.58 242	86.59 383	96.29 235	82.12 245	94.78 432	73.00 437	93.76 269	98.35 186

EG-PatchMatch MVS		87.02 377	85.44 382	91.76 369	92.67 415	85.00 358	96.08 296	96.45 302	83.41 409	79.52 434	93.49 380	57.10 444	97.72 349	79.34 406	90.87 316	92.56 422

KD-MVS_self_test		85.95 391	84.95 389	88.96 414	89.55 440	79.11 432	95.13 352	96.42 303	85.91 371	84.07 409	90.48 425	70.03 390	94.82 431	80.04 398	72.94 444	92.94 415

pmmvs6		87.81 369	86.19 377	92.69 338	91.32 428	86.30 325	97.34 171	96.41 304	80.59 430	84.05 410	94.37 336	67.37 411	97.67 352	84.75 350	79.51 422	94.09 400

PMMVS		92.86 220	92.34 218	94.42 250	94.92 343	86.73 313	94.53 367	96.38 305	84.78 390	94.27 177	95.12 298	83.13 217	98.40 260	91.47 214	96.49 204	98.12 207

RPSCF		90.75 314	90.86 272	90.42 396	96.84 200	76.29 441	95.61 326	96.34 306	83.89 399	91.38 257	97.87 115	76.45 338	98.78 210	87.16 315	92.23 289	96.20 291

BP-MVS1		95.89 94	95.49 94	97.08 77	96.67 219	93.20 73	98.08 54	96.32 307	94.56 71	96.32 109	97.84 120	84.07 200	99.15 158	96.75 60	98.78 111	98.90 123

MSDG		91.42 282	90.24 302	94.96 218	97.15 173	88.91 251	93.69 403	96.32 307	85.72 374	86.93 379	96.47 226	80.24 282	98.98 187	80.57 395	95.05 239	96.98 270

WBMVS		90.69 319	89.99 316	92.81 333	96.48 241	85.00 358	95.21 349	96.30 309	89.46 274	89.04 325	94.05 358	72.45 371	97.82 337	89.46 260	87.41 354	95.61 321

OurMVSNet-221017-0		90.51 324	90.19 307	91.44 375	93.41 400	81.25 403	96.98 207	96.28 310	91.68 185	86.55 384	96.30 234	74.20 360	97.98 311	88.96 276	87.40 355	95.09 354

MVP-Stereo		90.74 315	90.08 309	92.71 337	93.19 405	88.20 273	95.86 309	96.27 311	86.07 369	84.86 399	94.76 313	77.84 327	97.75 347	83.88 364	98.01 148	92.17 432
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 127	94.56 131	96.29 128	96.34 253	91.21 153	95.83 311	96.27 311	88.93 294	96.22 114	96.88 199	86.20 157	98.85 200	95.27 116	99.05 99	98.82 137

BH-untuned		92.94 215	92.62 207	93.92 285	97.22 167	86.16 331	96.40 269	96.25 313	90.06 256	89.79 300	96.17 242	83.19 214	98.35 268	87.19 313	97.27 175	97.24 264

CL-MVSNet_self_test		86.31 386	85.15 386	89.80 405	88.83 444	81.74 401	93.93 392	96.22 314	86.67 357	85.03 397	90.80 423	78.09 323	94.50 433	74.92 426	71.86 446	93.15 413

IS-MVSNet		94.90 129	94.52 135	96.05 142	97.67 142	90.56 182	98.44 22	96.22 314	93.21 122	93.99 187	97.74 131	85.55 170	98.45 257	89.98 246	97.86 152	99.14 84

FA-MVS(test-final)		93.52 188	92.92 192	95.31 197	96.77 213	88.54 261	94.82 359	96.21 316	89.61 268	94.20 180	95.25 292	83.24 212	99.14 161	90.01 245	96.16 209	98.25 195

GA-MVS		91.38 284	90.31 297	94.59 236	94.65 357	87.62 290	94.34 377	96.19 317	90.73 229	90.35 280	93.83 364	71.84 374	97.96 318	87.22 312	93.61 274	98.21 198

LuminaMVS		94.89 130	94.35 142	96.53 101	95.48 302	92.80 87	96.88 218	96.18 318	92.85 147	95.92 127	96.87 201	81.44 258	98.83 203	96.43 72	97.10 182	97.94 223

IterMVS-SCA-FT		90.31 327	89.81 323	91.82 364	95.52 300	84.20 370	94.30 380	96.15 319	90.61 239	87.39 365	94.27 345	75.80 344	96.44 407	87.34 309	86.88 361	94.82 372

IterMVS		90.15 335	89.67 329	91.61 371	95.48 302	83.72 376	94.33 378	96.12 320	89.99 257	87.31 368	94.15 353	75.78 346	96.27 411	86.97 318	86.89 360	94.83 370
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 225	91.51 249	96.52 103	98.77 58	90.99 165	97.38 168	96.08 321	82.38 415	89.29 318	97.87 115	83.77 203	99.69 68	81.37 388	96.69 195	98.89 128

pmmvs4		90.93 309	89.85 321	94.17 262	93.34 402	90.79 175	94.60 364	96.02 322	84.62 391	87.45 362	95.15 295	81.88 252	97.45 373	87.70 298	87.87 347	94.27 397

ppachtmachnet_test		88.35 364	87.29 363	91.53 372	92.45 421	83.57 379	93.75 399	95.97 323	84.28 394	85.32 396	94.18 351	79.00 310	96.93 395	75.71 422	84.99 383	94.10 398

Anonymous20240521		86.42 384	85.44 382	89.34 412	90.33 433	79.79 423	96.73 235	95.92 324	83.71 404	83.25 415	91.36 420	63.92 430	96.01 412	78.39 410	85.36 374	92.22 430

ITE_SJBPF				92.43 342	95.34 314	85.37 351		95.92 324	91.47 194	87.75 358	96.39 231	71.00 380	97.96 318	82.36 378	89.86 326	93.97 403

test_fmvs2		89.77 346	89.93 318	89.31 413	93.68 388	76.37 440	97.64 127	95.90 326	89.84 263	91.49 255	96.26 238	58.77 440	97.10 387	94.65 139	91.13 309	94.46 388

USDC		88.94 355	87.83 360	92.27 349	94.66 356	84.96 360	93.86 395	95.90 326	87.34 346	83.40 413	95.56 277	67.43 410	98.19 281	82.64 377	89.67 328	93.66 406

COLMAP_ROB	87.81 15	90.40 326	89.28 339	93.79 290	97.95 124	87.13 304	96.92 212	95.89 328	82.83 412	86.88 381	97.18 177	73.77 364	99.29 141	78.44 409	93.62 273	94.95 359
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 176	93.08 185	96.02 145	97.88 130	89.96 209	97.72 112	95.85 329	92.43 159	95.86 129	98.44 59	68.42 406	99.39 129	96.31 74	94.85 240	98.71 150

VDDNet		93.05 209	92.07 224	96.02 145	96.84 200	90.39 190	98.08 54	95.85 329	86.22 367	95.79 132	98.46 57	67.59 409	99.19 149	94.92 127	94.85 240	98.47 172

mvsmamba		94.57 143	94.14 147	95.87 156	97.03 184	89.93 210	97.84 90	95.85 329	91.34 200	94.79 163	96.80 202	80.67 272	98.81 206	94.85 128	98.12 143	98.85 133

Vis-MVSNet (Re-imp)		94.15 156	93.88 153	94.95 219	97.61 150	87.92 282	98.10 52	95.80 332	92.22 165	93.02 216	97.45 158	84.53 190	97.91 330	88.24 286	97.97 149	99.02 99

MM		97.29 27	96.98 38	98.23 11	98.01 118	95.03 26	98.07 56	95.76 333	97.78 1	97.52 57	98.80 37	88.09 115	99.86 9	99.44 2	99.37 63	99.80 1

KD-MVS_2432*1600		84.81 401	82.64 404	91.31 377	91.07 430	85.34 352	91.22 433	95.75 334	85.56 376	83.09 416	90.21 428	67.21 412	95.89 414	77.18 416	62.48 459	92.69 418

miper_refine_blended		84.81 401	82.64 404	91.31 377	91.07 430	85.34 352	91.22 433	95.75 334	85.56 376	83.09 416	90.21 428	67.21 412	95.89 414	77.18 416	62.48 459	92.69 418

FE-MVS		92.05 253	91.05 265	95.08 206	96.83 202	87.93 281	93.91 394	95.70 336	86.30 364	94.15 184	94.97 301	76.59 336	99.21 147	84.10 358	96.86 187	98.09 213

tpm cat1		88.36 363	87.21 366	91.81 365	95.13 333	80.55 412	92.58 424	95.70 336	74.97 445	87.45 362	91.96 413	78.01 326	98.17 283	80.39 397	88.74 339	96.72 280

our_test_3		88.78 359	87.98 359	91.20 381	92.45 421	82.53 390	93.61 407	95.69 338	85.77 373	84.88 398	93.71 369	79.99 287	96.78 403	79.47 403	86.24 363	94.28 396

BH-w/o		92.14 250	91.75 238	93.31 313	96.99 188	85.73 341	95.67 320	95.69 338	88.73 304	89.26 320	94.82 311	82.97 223	98.07 299	85.26 345	96.32 208	96.13 298

CR-MVSNet		90.82 312	89.77 325	93.95 279	94.45 365	87.19 301	90.23 441	95.68 340	86.89 354	92.40 226	92.36 405	80.91 266	97.05 390	81.09 392	93.95 266	97.60 247

Patchmtry		88.64 361	87.25 364	92.78 335	94.09 375	86.64 314	89.82 445	95.68 340	80.81 427	87.63 360	92.36 405	80.91 266	97.03 391	78.86 407	85.12 379	94.67 383

testing91		91.90 258	91.02 266	94.53 244	96.54 232	86.55 320	95.86 309	95.64 342	91.77 182	91.89 245	93.47 382	69.94 391	98.86 198	90.23 244	93.86 268	98.18 200

BH-RMVSNet		92.72 227	91.97 230	94.97 217	97.16 171	87.99 280	96.15 293	95.60 343	90.62 238	91.87 246	97.15 180	78.41 317	98.57 248	83.16 367	97.60 159	98.36 184

PVSNet_0	82.17 19	85.46 396	83.64 399	90.92 385	95.27 321	79.49 428	90.55 439	95.60 343	83.76 403	83.00 418	89.95 430	71.09 379	97.97 314	82.75 375	60.79 461	95.31 341

guyue		95.17 120	94.96 116	95.82 162	96.97 190	89.65 217	97.56 138	95.58 345	94.82 56	95.72 134	97.42 162	82.90 225	98.84 202	96.71 63	96.93 186	98.96 110

SCA		91.84 260	91.18 262	93.83 287	95.59 296	84.95 361	94.72 361	95.58 345	90.82 225	92.25 234	93.69 371	75.80 344	98.10 290	86.20 327	95.98 211	98.45 174

MonoMVSNet		91.92 256	91.77 236	92.37 343	92.94 409	83.11 384	97.09 196	95.55 347	92.91 143	90.85 272	94.55 324	81.27 262	96.52 406	93.01 183	87.76 348	97.47 253

AllTest		90.23 331	88.98 345	93.98 275	97.94 125	86.64 314	96.51 258	95.54 348	85.38 378	85.49 393	96.77 204	70.28 386	99.15 158	80.02 399	92.87 278	96.15 296

TestCases				93.98 275	97.94 125	86.64 314		95.54 348	85.38 378	85.49 393	96.77 204	70.28 386	99.15 158	80.02 399	92.87 278	96.15 296

mmtdpeth		89.70 348	88.96 346	91.90 360	95.84 288	84.42 366	97.46 158	95.53 350	90.27 250	94.46 174	90.50 424	69.74 395	98.95 188	97.39 49	69.48 450	92.34 426

tpmvs		89.83 345	89.15 343	91.89 361	94.92 343	80.30 416	93.11 416	95.46 351	86.28 365	88.08 352	92.65 395	80.44 278	98.52 252	81.47 384	89.92 325	96.84 276

pmmvs5		89.86 344	88.87 349	92.82 332	92.86 411	86.23 327	96.26 283	95.39 352	84.24 395	87.12 370	94.51 327	74.27 359	97.36 380	87.61 305	87.57 350	94.86 368

PatchmatchNet		91.91 257	91.35 251	93.59 301	95.38 309	84.11 371	93.15 415	95.39 352	89.54 270	92.10 239	93.68 373	82.82 228	98.13 285	84.81 349	95.32 232	98.52 164
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 281	91.32 253	91.79 366	95.15 331	79.20 431	93.42 410	95.37 354	88.55 309	93.49 205	93.67 374	82.49 237	98.27 274	90.41 239	89.34 331	97.90 225

Anonymous20231206		87.09 376	86.14 378	89.93 404	91.22 429	80.35 414	96.11 294	95.35 355	83.57 406	84.16 405	93.02 390	73.54 366	95.61 422	72.16 439	86.14 365	93.84 405

MIMVSNet1		84.93 399	83.05 401	90.56 394	89.56 439	84.84 363	95.40 335	95.35 355	83.91 398	80.38 430	92.21 410	57.23 443	93.34 446	70.69 445	82.75 410	93.50 408

TDRefinement		86.53 380	84.76 392	91.85 362	82.23 462	84.25 368	96.38 271	95.35 355	84.97 387	84.09 408	94.94 303	65.76 425	98.34 271	84.60 353	74.52 440	92.97 414

TR-MVS		91.48 280	90.59 288	94.16 265	96.40 247	87.33 294	95.67 320	95.34 358	87.68 338	91.46 256	95.52 280	76.77 335	98.35 268	82.85 372	93.61 274	96.79 278

EPNet_dtu		91.71 263	91.28 256	92.99 325	93.76 385	83.71 377	96.69 241	95.28 359	93.15 129	87.02 375	95.95 253	83.37 211	97.38 379	79.46 404	96.84 188	97.88 227
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 373	85.79 380	91.78 367	94.80 350	87.28 296	95.49 332	95.28 359	84.09 397	83.85 412	91.82 414	62.95 433	94.17 437	78.48 408	85.34 375	93.91 404

MDTV_nov1_ep13			90.76 278		95.22 325	80.33 415	93.03 418	95.28 359	88.14 322	92.84 223	93.83 364	81.34 259	98.08 295	82.86 370	94.34 251

LF4IMVS		87.94 367	87.25 364	89.98 402	92.38 423	80.05 422	94.38 375	95.25 362	87.59 340	84.34 402	94.74 315	64.31 429	97.66 354	84.83 348	87.45 351	92.23 429

TransMVSNet (Re)		88.94 355	87.56 361	93.08 323	94.35 368	88.45 265	97.73 109	95.23 363	87.47 342	84.26 404	95.29 287	79.86 290	97.33 381	79.44 405	74.44 441	93.45 410

test20.03		86.14 389	85.40 384	88.35 415	90.12 434	80.06 421	95.90 308	95.20 364	88.59 305	81.29 425	93.62 376	71.43 377	92.65 450	71.26 443	81.17 415	92.34 426

new-patchmatchnet		83.18 408	81.87 411	87.11 423	86.88 453	75.99 442	93.70 401	95.18 365	85.02 386	77.30 442	88.40 441	65.99 423	93.88 442	74.19 431	70.18 448	91.47 440

MDA-MVSNet_test_wron		85.87 393	84.23 396	90.80 391	92.38 423	82.57 389	93.17 413	95.15 366	82.15 416	67.65 454	92.33 408	78.20 319	95.51 425	77.33 413	79.74 419	94.31 395

YYNet1		85.87 393	84.23 396	90.78 392	92.38 423	82.46 394	93.17 413	95.14 367	82.12 417	67.69 452	92.36 405	78.16 322	95.50 426	77.31 414	79.73 420	94.39 391

Baseline_NR-MVSNet		91.20 296	90.62 286	92.95 327	93.83 383	88.03 279	97.01 203	95.12 368	88.42 313	89.70 303	95.13 297	83.47 208	97.44 374	89.66 256	83.24 405	93.37 411

thres200		92.23 246	91.39 250	94.75 232	97.61 150	89.03 249	96.60 253	95.09 369	92.08 174	93.28 211	94.00 360	78.39 318	99.04 184	81.26 391	94.18 257	96.19 292

ADS-MVSNet		89.89 341	88.68 351	93.53 305	95.86 283	84.89 362	90.93 436	95.07 370	83.23 410	91.28 265	91.81 415	79.01 308	97.85 333	79.52 401	91.39 305	97.84 232

pmmvs-eth3d		86.22 387	84.45 394	91.53 372	88.34 448	87.25 298	94.47 370	95.01 371	83.47 407	79.51 435	89.61 433	69.75 394	95.71 419	83.13 368	76.73 433	91.64 434

Anonymous202405211		92.07 252	90.83 276	95.76 167	98.19 104	88.75 254	97.58 134	95.00 372	86.00 370	93.64 197	97.45 158	66.24 421	99.53 107	90.68 233	92.71 283	99.01 102

MDA-MVSNet-bldmvs		85.00 398	82.95 403	91.17 383	93.13 407	83.33 380	94.56 366	95.00 372	84.57 392	65.13 458	92.65 395	70.45 385	95.85 416	73.57 434	77.49 429	94.33 393

ambc				86.56 426	83.60 459	70.00 453	85.69 457	94.97 374		80.60 429	88.45 440	37.42 461	96.84 400	82.69 376	75.44 438	92.86 416

testgi		87.97 366	87.21 366	90.24 399	92.86 411	80.76 407	96.67 244	94.97 374	91.74 183	85.52 392	95.83 259	62.66 435	94.47 435	76.25 420	88.36 343	95.48 324

myMVS_eth3d28		91.52 277	90.97 268	93.17 319	96.91 193	83.24 382	95.61 326	94.96 376	92.24 164	91.98 242	93.28 387	69.31 396	98.40 260	88.71 281	95.68 221	97.88 227

dp		88.90 357	88.26 357	90.81 389	94.58 361	76.62 439	92.85 421	94.93 377	85.12 384	90.07 294	93.07 389	75.81 343	98.12 288	80.53 396	87.42 353	97.71 239

test_fmvs3		83.21 407	83.02 402	83.78 430	86.77 454	68.34 456	96.76 233	94.91 378	86.49 360	84.14 407	89.48 434	36.04 462	91.73 452	91.86 204	80.77 417	91.26 442

test_0402		86.46 383	84.79 391	91.45 374	95.02 337	85.55 343	96.29 282	94.89 379	80.90 424	82.21 421	93.97 362	68.21 407	97.29 383	62.98 453	88.68 340	91.51 437

tfpn200view9		92.38 236	91.52 247	94.95 219	97.85 131	89.29 238	97.41 161	94.88 380	92.19 170	93.27 212	94.46 332	78.17 320	99.08 172	81.40 385	94.08 261	96.48 285

CVMVSNet		91.23 294	91.75 238	89.67 406	95.77 289	74.69 443	96.44 259	94.88 380	85.81 372	92.18 235	97.64 144	79.07 303	95.58 424	88.06 289	95.86 216	98.74 147

thres400		92.42 234	91.52 247	95.12 205	97.85 131	89.29 238	97.41 161	94.88 380	92.19 170	93.27 212	94.46 332	78.17 320	99.08 172	81.40 385	94.08 261	96.98 270

tt0320		85.39 397	83.12 400	92.19 353	93.44 399	85.79 339	96.19 290	94.87 383	71.19 452	82.92 419	91.76 417	58.43 441	96.81 401	81.03 393	78.26 428	93.98 402

EPNet		95.20 118	94.56 131	97.14 71	92.80 413	92.68 93	97.85 89	94.87 383	96.64 8	92.46 225	97.80 126	86.23 154	99.65 74	93.72 163	98.62 119	99.10 91
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 268	90.72 283	94.32 255	96.48 241	86.11 336	95.81 312	94.76 385	91.55 187	91.75 250	93.44 383	68.55 404	98.82 204	90.43 238	93.69 270	98.04 217

sc_t1		86.48 382	84.10 398	93.63 298	93.45 398	85.76 340	96.79 228	94.71 386	73.06 450	86.45 385	94.35 337	55.13 448	97.95 322	84.38 356	78.55 427	97.18 266

SixPastTwentyTwo		89.15 353	88.54 353	90.98 384	93.49 395	80.28 418	96.70 239	94.70 387	90.78 226	84.15 406	95.57 276	71.78 375	97.71 350	84.63 352	85.07 380	94.94 361

thres100view900		92.43 233	91.58 244	94.98 215	97.92 127	89.37 234	97.71 114	94.66 388	92.20 168	93.31 210	94.90 306	78.06 324	99.08 172	81.40 385	94.08 261	96.48 285

thres600view7		92.49 231	91.60 243	95.18 201	97.91 128	89.47 228	97.65 123	94.66 388	92.18 172	93.33 209	94.91 305	78.06 324	99.10 166	81.61 381	94.06 265	96.98 270

PatchT		88.87 358	87.42 362	93.22 317	94.08 376	85.10 356	89.51 446	94.64 390	81.92 418	92.36 229	88.15 444	80.05 286	97.01 393	72.43 438	93.65 272	97.54 250

baseline1		92.82 223	91.90 233	95.55 183	97.20 169	90.77 176	97.19 188	94.58 391	92.20 168	92.36 229	96.34 233	84.16 198	98.21 278	89.20 271	83.90 400	97.68 241

AstraMVS		94.82 136	94.64 127	95.34 196	96.36 252	88.09 278	97.58 134	94.56 392	94.98 45	95.70 137	97.92 109	81.93 251	98.93 191	96.87 57	95.88 214	98.99 106

UBG		91.55 274	90.76 278	93.94 281	96.52 237	85.06 357	95.22 347	94.54 393	90.47 246	91.98 242	92.71 394	72.02 372	98.74 220	88.10 288	95.26 234	98.01 219

Gipuma		67.86 428	65.41 430	75.18 443	92.66 416	73.45 447	66.50 464	94.52 394	53.33 463	57.80 464	66.07 464	30.81 464	89.20 456	48.15 462	78.88 426	62.90 464
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 266	90.75 280	94.47 246	96.53 234	86.56 319	95.76 316	94.51 395	91.10 218	91.24 267	93.59 377	68.59 403	98.86 198	91.10 221	94.29 253	98.00 220

CostFormer		91.18 299	90.70 284	92.62 340	94.84 348	81.76 400	94.09 387	94.43 396	84.15 396	92.72 224	93.77 368	79.43 297	98.20 279	90.70 232	92.18 292	97.90 225

tpm2		89.96 338	89.21 341	92.23 352	94.91 345	81.25 403	93.78 398	94.42 397	80.62 429	91.56 253	93.44 383	76.44 339	97.94 324	85.60 339	92.08 296	97.49 251

testing3-2		92.10 251	92.05 225	92.27 349	97.71 140	79.56 425	97.42 160	94.41 398	93.53 110	93.22 214	95.49 281	69.16 398	99.11 164	93.25 173	94.22 255	98.13 205

MGCNet		96.74 60	96.31 77	98.02 19	96.87 196	94.65 30	97.58 134	94.39 399	96.47 11	97.16 69	98.39 63	87.53 132	99.87 7	98.97 19	99.41 55	99.55 39

JIA-IIPM		88.26 365	87.04 369	91.91 359	93.52 393	81.42 402	89.38 447	94.38 400	80.84 426	90.93 271	80.74 456	79.22 300	97.92 327	82.76 374	91.62 300	96.38 288

dmvs_re		90.21 332	89.50 334	92.35 344	95.47 306	85.15 354	95.70 319	94.37 401	90.94 224	88.42 339	93.57 378	74.63 356	95.67 421	82.80 373	89.57 329	96.22 290

Patchmatch-test		89.42 351	87.99 358	93.70 295	95.27 321	85.11 355	88.98 448	94.37 401	81.11 423	87.10 373	93.69 371	82.28 241	97.50 369	74.37 429	94.76 244	98.48 171

LCM-MVSNet		72.55 421	69.39 425	82.03 432	70.81 472	65.42 461	90.12 443	94.36 403	55.02 462	65.88 456	81.72 455	24.16 470	89.96 453	74.32 430	68.10 453	90.71 445

ADS-MVSNet2		89.45 350	88.59 352	92.03 356	95.86 283	82.26 396	90.93 436	94.32 404	83.23 410	91.28 265	91.81 415	79.01 308	95.99 413	79.52 401	91.39 305	97.84 232

mvs5depth		86.53 380	85.08 387	90.87 386	88.74 446	82.52 391	91.91 429	94.23 405	86.35 363	87.11 372	93.70 370	66.52 417	97.76 345	81.37 388	75.80 435	92.31 428

EU-MVSNet		88.72 360	88.90 348	88.20 417	93.15 406	74.21 445	96.63 250	94.22 406	85.18 382	87.32 367	95.97 251	76.16 341	94.98 430	85.27 344	86.17 364	95.41 331

tt0320-xc		84.83 400	82.33 408	92.31 347	93.66 389	86.20 329	96.17 292	94.06 407	71.26 451	82.04 423	92.22 409	55.07 449	96.72 404	81.49 383	75.04 439	94.02 401

MIMVSNet		88.50 362	86.76 372	93.72 294	94.84 348	87.77 288	91.39 431	94.05 408	86.41 362	87.99 354	92.59 398	63.27 431	95.82 418	77.44 412	92.84 280	97.57 249

OpenMVS_ROB	81.14 20	84.42 403	82.28 409	90.83 387	90.06 435	84.05 373	95.73 318	94.04 409	73.89 448	80.17 433	91.53 419	59.15 439	97.64 355	66.92 451	89.05 333	90.80 444

TinyColmap		86.82 378	85.35 385	91.21 379	94.91 345	82.99 386	93.94 391	94.02 410	83.58 405	81.56 424	94.68 317	62.34 436	98.13 285	75.78 421	87.35 356	92.52 424

ETVMVS		90.52 323	89.14 344	94.67 235	96.81 206	87.85 286	95.91 307	93.97 411	89.71 266	92.34 232	92.48 400	65.41 427	97.96 318	81.37 388	94.27 254	98.21 198

IB-MVS	87.33 17	89.91 339	88.28 356	94.79 229	95.26 324	87.70 289	95.12 353	93.95 412	89.35 278	87.03 374	92.49 399	70.74 383	99.19 149	89.18 272	81.37 414	97.49 251
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		87.13 375	87.02 370	87.47 421	95.16 328	73.21 449	95.00 355	93.93 413	88.55 309	86.96 376	91.99 411	75.90 342	94.00 439	61.59 455	94.11 258	95.20 349

myMVS_eth3d		87.18 374	86.38 375	89.58 407	95.16 328	79.53 426	95.00 355	93.93 413	88.55 309	86.96 376	91.99 411	56.23 446	94.00 439	75.47 425	94.11 258	95.20 349

testing222		90.31 327	88.96 346	94.35 252	96.54 232	87.29 295	95.50 331	93.84 415	90.97 221	91.75 250	92.96 391	62.18 437	98.00 309	82.86 370	94.08 261	97.76 237

test_f		80.57 414	79.62 416	83.41 431	83.38 460	67.80 458	93.57 408	93.72 416	80.80 428	77.91 441	87.63 447	33.40 463	92.08 451	87.14 316	79.04 425	90.34 446

LCM-MVSNet-Re		92.50 229	92.52 213	92.44 341	96.82 204	81.89 399	96.92 212	93.71 417	92.41 160	84.30 403	94.60 322	85.08 179	97.03 391	91.51 212	97.36 168	98.40 180

tpm		90.25 330	89.74 328	91.76 369	93.92 379	79.73 424	93.98 388	93.54 418	88.28 316	91.99 241	93.25 388	77.51 330	97.44 374	87.30 311	87.94 346	98.12 207

ET-MVSNet_ETH3D		91.49 279	90.11 308	95.63 177	96.40 247	91.57 138	95.34 338	93.48 419	90.60 241	75.58 444	95.49 281	80.08 285	96.79 402	94.25 151	89.76 327	98.52 164

LFMVS		93.60 183	92.63 206	96.52 103	98.13 110	91.27 150	97.94 76	93.39 420	90.57 243	96.29 111	98.31 76	69.00 399	99.16 156	94.18 152	95.87 215	99.12 88

MVStest1		82.38 411	80.04 415	89.37 410	87.63 451	82.83 387	95.03 354	93.37 421	73.90 447	73.50 449	94.35 337	62.89 434	93.25 448	73.80 432	65.92 456	92.04 433

FE-MVSNET		83.85 404	81.97 410	89.51 408	87.19 452	83.19 383	95.21 349	93.17 422	83.45 408	78.90 437	89.05 437	65.46 426	93.84 443	69.71 447	75.56 437	91.51 437

Patchmatch-RL test		87.38 372	86.24 376	90.81 389	88.74 446	78.40 435	88.12 455	93.17 422	87.11 351	82.17 422	89.29 435	81.95 249	95.60 423	88.64 283	77.02 430	98.41 179

ttmdpeth		85.91 392	84.76 392	89.36 411	89.14 441	80.25 419	95.66 323	93.16 424	83.77 402	83.39 414	95.26 291	66.24 421	95.26 429	80.65 394	75.57 436	92.57 421

test-LLR		91.42 282	91.19 261	92.12 354	94.59 359	80.66 409	94.29 381	92.98 425	91.11 216	90.76 274	92.37 402	79.02 306	98.07 299	88.81 278	96.74 192	97.63 242

test-mter		90.19 334	89.54 333	92.12 354	94.59 359	80.66 409	94.29 381	92.98 425	87.68 338	90.76 274	92.37 402	67.67 408	98.07 299	88.81 278	96.74 192	97.63 242

WB-MVSnew		89.88 342	89.56 332	90.82 388	94.57 362	83.06 385	95.65 324	92.85 427	87.86 329	90.83 273	94.10 354	79.66 294	96.88 398	76.34 419	94.19 256	92.54 423

testing3		87.67 370	86.88 371	90.05 401	96.14 270	80.71 408	97.10 195	92.85 427	90.15 254	87.54 361	94.55 324	55.70 447	94.10 438	73.77 433	94.10 260	95.35 338

test_method		66.11 429	64.89 431	69.79 446	72.62 470	35.23 478	65.19 465	92.83 429	20.35 468	65.20 457	88.08 445	43.14 459	82.70 463	73.12 436	63.46 458	91.45 441

test0.0.03 1		89.37 352	88.70 350	91.41 376	92.47 420	85.63 342	95.22 347	92.70 430	91.11 216	86.91 380	93.65 375	79.02 306	93.19 449	78.00 411	89.18 332	95.41 331

new_pmnet		82.89 409	81.12 414	88.18 418	89.63 438	80.18 420	91.77 430	92.57 431	76.79 443	75.56 445	88.23 443	61.22 438	94.48 434	71.43 441	82.92 408	89.87 447

mvsany_test1		93.93 172	93.98 151	93.78 291	94.94 342	86.80 310	94.62 363	92.55 432	88.77 303	96.85 79	98.49 53	88.98 97	98.08 295	95.03 122	95.62 223	96.46 287

thisisatest0515		92.29 242	91.30 255	95.25 199	96.60 223	88.90 252	94.36 376	92.32 433	87.92 326	93.43 207	94.57 323	77.28 331	99.00 185	89.42 262	95.86 216	97.86 231

thisisatest0530		93.03 210	92.21 222	95.49 188	97.07 176	89.11 247	97.49 155	92.19 434	90.16 253	94.09 185	96.41 229	76.43 340	99.05 181	90.38 240	95.68 221	98.31 192

tttt0517		92.96 213	92.33 219	94.87 222	97.11 174	87.16 303	97.97 72	92.09 435	90.63 237	93.88 191	97.01 193	76.50 337	99.06 178	90.29 243	95.45 230	98.38 182

K. test v3		87.64 371	86.75 373	90.32 398	93.02 408	79.48 429	96.61 251	92.08 436	90.66 235	80.25 432	94.09 356	67.21 412	96.65 405	85.96 335	80.83 416	94.83 370

TESTMET0.1,1		90.06 336	89.42 336	91.97 357	94.41 367	80.62 411	94.29 381	91.97 437	87.28 348	90.44 278	92.47 401	68.79 400	97.67 352	88.50 285	96.60 198	97.61 246

PM-MVS		83.48 406	81.86 412	88.31 416	87.83 450	77.59 437	93.43 409	91.75 438	86.91 353	80.63 428	89.91 431	44.42 458	95.84 417	85.17 347	76.73 433	91.50 439

baseline2		91.63 267	90.86 272	93.94 281	94.33 369	86.32 324	95.92 306	91.64 439	89.37 277	86.94 378	94.69 316	81.62 256	98.69 229	88.64 283	94.57 249	96.81 277

APD_test1		79.31 416	77.70 419	84.14 429	89.11 443	69.07 455	92.36 428	91.50 440	69.07 454	73.87 447	92.63 397	39.93 460	94.32 436	70.54 446	80.25 418	89.02 449

FPMVS		71.27 422	69.85 424	75.50 442	74.64 467	59.03 467	91.30 432	91.50 440	58.80 459	57.92 463	88.28 442	29.98 466	85.53 462	53.43 460	82.84 409	81.95 455

door								91.13 442

door-mid								91.06 443

EGC-MVSNET		68.77 427	63.01 433	86.07 428	92.49 419	82.24 397	93.96 390	90.96 444	0.71 473	2.62 474	90.89 422	53.66 450	93.46 444	57.25 458	84.55 390	82.51 454

mvsany_test3		83.59 405	82.44 407	87.03 424	83.80 457	73.82 446	93.70 401	90.92 445	86.42 361	82.51 420	90.26 427	46.76 457	95.71 419	90.82 227	76.76 432	91.57 436

pmmvs3		79.97 415	77.50 420	87.39 422	82.80 461	79.38 430	92.70 423	90.75 446	70.69 453	78.66 438	87.47 449	51.34 453	93.40 445	73.39 435	69.65 449	89.38 448

UWE-MVS		89.91 339	89.48 335	91.21 379	95.88 282	78.23 436	94.91 358	90.26 447	89.11 284	92.35 231	94.52 326	68.76 401	97.96 318	83.95 362	95.59 224	97.42 255

DSMNet-mixed		86.34 385	86.12 379	87.00 425	89.88 437	70.43 451	94.93 357	90.08 448	77.97 440	85.42 395	92.78 393	74.44 358	93.96 441	74.43 428	95.14 235	96.62 281

MVS-HIRNet		82.47 410	81.21 413	86.26 427	95.38 309	69.21 454	88.96 449	89.49 449	66.28 456	80.79 427	74.08 461	68.48 405	97.39 378	71.93 440	95.47 229	92.18 431

WB-MVS		76.77 418	76.63 421	77.18 437	85.32 455	56.82 469	94.53 367	89.39 450	82.66 414	71.35 450	89.18 436	75.03 351	88.88 457	35.42 466	66.79 454	85.84 451

test1111		93.19 202	92.82 196	94.30 258	97.58 156	84.56 365	98.21 43	89.02 451	93.53 110	94.58 168	98.21 83	72.69 368	99.05 181	93.06 179	98.48 126	99.28 73

SSC-MVS		76.05 419	75.83 422	76.72 441	84.77 456	56.22 470	94.32 379	88.96 452	81.82 420	70.52 451	88.91 438	74.79 355	88.71 458	33.69 467	64.71 457	85.23 452

ECVR-MVS		93.19 202	92.73 202	94.57 241	97.66 144	85.41 348	98.21 43	88.23 453	93.43 115	94.70 165	98.21 83	72.57 369	99.07 176	93.05 180	98.49 124	99.25 76

EPMVS		90.70 317	89.81 323	93.37 311	94.73 354	84.21 369	93.67 404	88.02 454	89.50 272	92.38 228	93.49 380	77.82 328	97.78 342	86.03 333	92.68 284	98.11 212

ANet_high		63.94 431	59.58 434	77.02 438	61.24 474	66.06 459	85.66 458	87.93 455	78.53 438	42.94 466	71.04 463	25.42 469	80.71 465	52.60 461	30.83 467	84.28 453

PMMVS2		70.19 423	66.92 427	80.01 433	76.35 466	65.67 460	86.22 456	87.58 456	64.83 458	62.38 459	80.29 458	26.78 468	88.49 460	63.79 452	54.07 463	85.88 450

lessismore_v0				90.45 395	91.96 426	79.09 433		87.19 457		80.32 431	94.39 334	66.31 420	97.55 363	84.00 361	76.84 431	94.70 382

PMVS	53.92 22	58.58 432	55.40 435	68.12 447	51.00 475	48.64 472	78.86 461	87.10 458	46.77 464	35.84 470	74.28 460	8.76 474	86.34 461	42.07 464	73.91 442	69.38 461
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 379	86.41 374	88.02 419	92.87 410	74.60 444	95.38 337	86.70 459	88.17 319	87.28 369	94.67 319	70.83 382	93.30 447	67.45 449	94.31 252	96.17 293

test_vis1_rt		86.16 388	85.06 388	89.46 409	93.47 397	80.46 413	96.41 265	86.61 460	85.22 381	79.15 436	88.64 439	52.41 452	97.06 389	93.08 178	90.57 318	90.87 443

testf1		69.31 425	66.76 428	76.94 439	78.61 464	61.93 463	88.27 453	86.11 461	55.62 460	59.69 460	85.31 452	20.19 472	89.32 454	57.62 456	69.44 451	79.58 456

APD_test2		69.31 425	66.76 428	76.94 439	78.61 464	61.93 463	88.27 453	86.11 461	55.62 460	59.69 460	85.31 452	20.19 472	89.32 454	57.62 456	69.44 451	79.58 456

gg-mvs-nofinetune		87.82 368	85.61 381	94.44 248	94.46 364	89.27 241	91.21 435	84.61 463	80.88 425	89.89 298	74.98 459	71.50 376	97.53 366	85.75 338	97.21 177	96.51 283

dmvs_testset		81.38 413	82.60 406	77.73 436	91.74 427	51.49 471	93.03 418	84.21 464	89.07 285	78.28 440	91.25 421	76.97 333	88.53 459	56.57 459	82.24 411	93.16 412

GG-mvs-BLEND				93.62 299	93.69 387	89.20 243	92.39 427	83.33 465		87.98 355	89.84 432	71.00 380	96.87 399	82.08 380	95.40 231	94.80 375

MTMP							97.86 86	82.03 466

DeepMVS_CX				74.68 444	90.84 432	64.34 462		81.61 467	65.34 457	67.47 455	88.01 446	48.60 456	80.13 466	62.33 454	73.68 443	79.58 456

E-PMN		53.28 433	52.56 437	55.43 450	74.43 468	47.13 473	83.63 460	76.30 468	42.23 465	42.59 467	62.22 466	28.57 467	74.40 467	31.53 468	31.51 466	44.78 465

test2506		91.60 269	90.78 277	94.04 271	97.66 144	83.81 374	98.27 33	75.53 469	93.43 115	95.23 151	98.21 83	67.21 412	99.07 176	93.01 183	98.49 124	99.25 76

EMVS		52.08 435	51.31 438	54.39 451	72.62 470	45.39 475	83.84 459	75.51 470	41.13 466	40.77 468	59.65 467	30.08 465	73.60 468	28.31 470	29.90 468	44.18 466

test_vis3_rt		72.73 420	70.55 423	79.27 434	80.02 463	68.13 457	93.92 393	74.30 471	76.90 442	58.99 462	73.58 462	20.29 471	95.37 427	84.16 357	72.80 445	74.31 459

MVE	50.73 23	53.25 434	48.81 439	66.58 449	65.34 473	57.50 468	72.49 463	70.94 472	40.15 467	39.28 469	63.51 465	6.89 476	73.48 469	38.29 465	42.38 465	68.76 463
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 436	53.82 436	46.29 452	33.73 476	45.30 476	78.32 462	67.24 473	18.02 469	50.93 465	87.05 450	52.99 451	53.11 471	70.76 444	25.29 469	40.46 467

kuosan		65.27 430	64.66 432	67.11 448	83.80 457	61.32 466	88.53 452	60.77 474	68.22 455	67.67 453	80.52 457	49.12 455	70.76 470	29.67 469	53.64 464	69.26 462

dongtai		69.99 424	69.33 426	71.98 445	88.78 445	61.64 465	89.86 444	59.93 475	75.67 444	74.96 446	85.45 451	50.19 454	81.66 464	43.86 463	55.27 462	72.63 460

N_pmnet		78.73 417	78.71 418	78.79 435	92.80 413	46.50 474	94.14 385	43.71 476	78.61 437	80.83 426	91.66 418	74.94 354	96.36 409	67.24 450	84.45 392	93.50 408

wuyk23d		25.11 437	24.57 441	26.74 453	73.98 469	39.89 477	57.88 466	9.80 477	12.27 470	10.39 471	6.97 473	7.03 475	36.44 472	25.43 471	17.39 470	3.89 470

testmvs		13.36 439	16.33 442	4.48 455	5.04 477	2.26 480	93.18 412	3.28 478	2.70 471	8.24 472	21.66 469	2.29 478	2.19 473	7.58 472	2.96 471	9.00 469

test123		13.04 440	15.66 443	5.18 454	4.51 478	3.45 479	92.50 426	1.81 479	2.50 472	7.58 473	20.15 470	3.67 477	2.18 474	7.13 473	1.07 472	9.90 468

mmdepth		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

monomultidepth		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

test_blank		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

uanet_test		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

DCPMVS		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

pcd_1.5k_mvsjas		7.39 442	9.85 445	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	88.65 105	0.00 475	0.00 474	0.00 473	0.00 471

sosnet-low-res		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

sosnet		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

uncertanet		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

Regformer		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

n2								0.00 480

nn								0.00 480

ab-mvs-re		8.06 441	10.74 444	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	96.69 210	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

uanet		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

WAC-MVS						79.53 426								75.56 424

PC_three_1452									90.77 227	98.89 25	98.28 81	96.24 1	98.35 268	95.76 101	99.58 23	99.59 28

eth-test2					0.00 479

eth-test					0.00 479

OPU-MVS				98.55 3	98.82 57	96.86 3	98.25 36				98.26 82	96.04 2	99.24 144	95.36 115	99.59 19	99.56 36

test_0728_THIRD									94.78 60	98.73 29	98.87 30	95.87 4	99.84 23	97.45 45	99.72 2	99.77 2

GSMVS																98.45 174

test_part2					99.28 27	95.74 8				98.10 43

sam_mvs1												82.76 229				98.45 174

sam_mvs												81.94 250

test_post1							92.81 422				16.58 472	80.53 276	97.68 351	86.20 327

test_post											17.58 471	81.76 253	98.08 295

patchmatchnet-post											90.45 426	82.65 234	98.10 290

gm-plane-assit					93.22 404	78.89 434			84.82 389		93.52 379		98.64 238	87.72 295

test9_res														94.81 133	99.38 60	99.45 55

agg_prior2														93.94 157	99.38 60	99.50 48

test_prior4						93.66 58	96.42 264

test_prior2							96.35 274		92.80 150	96.03 121	97.59 150	92.01 47		95.01 123	99.38 60

旧先验2							95.94 304		81.66 421	97.34 65			98.82 204	92.26 189

新几何2							95.79 314

原ACMM2							95.67 320

testdata2													99.67 72	85.96 335

segment_acmp												92.89 30

testdata1							95.26 346		93.10 132

plane_prior7					96.21 257	89.98 206

plane_prior6					96.10 275	90.00 202						81.32 260

plane_prior4											96.64 213

plane_prior3						90.00 202			94.46 77	91.34 259

plane_prior2							97.74 107		94.85 52

plane_prior1					96.14 270

plane_prior						89.99 204	97.24 180		94.06 89						92.16 293

HQP5-MVS						89.33 236

HQP-NCC					95.86 283		96.65 245		93.55 106	90.14 283

ACMP_Plane					95.86 283		96.65 245		93.55 106	90.14 283

BP-MVS														92.13 197

HQP4-MVS										90.14 283			98.50 253			95.78 312

HQP2-MVS												80.95 264

NP-MVS					95.99 281	89.81 214					95.87 256

MDTV_nov1_ep13_2view						70.35 452	93.10 417		83.88 400	93.55 200		82.47 238		86.25 326		98.38 182

ACMMP++_ref															90.30 323

ACMMP++															91.02 312

Test By Simon												88.73 104

High-resolution multi-view benchmark