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.

mvs5depth		95.28 88	95.82 71	93.66 162	96.42 192	83.08 224	97.35 12	99.28 3	96.44 26	96.20 109	99.65 2	84.10 248	98.01 232	94.06 48	98.93 125	99.87 1

LCM-MVSNet		99.43 1	99.49 1	99.24 2	99.95 1	98.13 2	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 2	97.58 2	99.94 1	99.85 2

mmtdpeth		95.82 62	96.02 58	95.23 95	96.91 157	88.62 113	96.49 39	99.26 4	95.07 44	93.41 224	99.29 4	90.25 170	97.27 290	94.49 38	99.01 113	99.80 3

PS-CasMVS		96.69 24	97.43 6	94.49 130	99.13 6	84.09 209	96.61 32	97.97 85	97.91 6	98.64 14	98.13 43	95.24 40	99.65 5	93.39 76	99.84 3	99.72 4

CP-MVSNet		96.19 49	96.80 20	94.38 135	98.99 16	83.82 212	96.31 52	97.53 124	97.60 8	98.34 20	97.52 86	91.98 127	99.63 8	93.08 89	99.81 8	99.70 5

FC-MVSNet-test		95.32 84	95.88 65	93.62 164	98.49 56	81.77 240	95.90 73	98.32 30	93.93 63	97.53 45	97.56 81	88.48 188	99.40 49	92.91 94	99.83 5	99.68 6

PEN-MVS		96.69 24	97.39 9	94.61 120	99.16 4	84.50 199	96.54 34	98.05 72	98.06 5	98.64 14	98.25 40	95.01 53	99.65 5	92.95 93	99.83 5	99.68 6

WR-MVS_H		96.60 29	97.05 17	95.24 94	99.02 12	86.44 164	96.78 26	98.08 65	97.42 10	98.48 17	97.86 65	91.76 134	99.63 8	94.23 45	99.84 3	99.66 8

test_djsdf		96.62 27	96.49 30	97.01 36	98.55 44	91.77 63	97.15 15	97.37 133	88.98 182	98.26 24	98.86 12	93.35 92	99.60 10	96.41 9	99.45 45	99.66 8

v7n		96.82 13	97.31 11	95.33 88	98.54 46	86.81 152	96.83 22	98.07 68	96.59 23	98.46 18	98.43 35	92.91 107	99.52 20	96.25 12	99.76 10	99.65 10

UA-Net		97.35 5	97.24 12	97.69 6	98.22 75	93.87 34	98.42 6	98.19 47	96.95 16	95.46 147	99.23 6	93.45 87	99.57 15	95.34 29	99.89 2	99.63 11

DTE-MVSNet		96.74 21	97.43 6	94.67 117	99.13 6	84.68 198	96.51 36	97.94 91	98.14 4	98.67 13	98.32 37	95.04 50	99.69 4	93.27 81	99.82 7	99.62 12

FIs		94.90 101	95.35 89	93.55 167	98.28 69	81.76 241	95.33 98	98.14 57	93.05 82	97.07 64	97.18 118	87.65 202	99.29 73	91.72 124	99.69 14	99.61 13

UniMVSNet_ETH3D		97.13 9	97.72 4	95.35 86	99.51 2	87.38 137	97.70 8	97.54 122	98.16 3	98.94 3	99.33 3	97.84 4	99.08 98	90.73 147	99.73 13	99.59 14

PS-MVSNAJss		96.01 54	96.04 56	95.89 69	98.82 25	88.51 119	95.57 89	97.88 92	88.72 188	98.81 7	98.86 12	90.77 157	99.60 10	95.43 25	99.53 37	99.57 15

anonymousdsp		96.74 21	96.42 33	97.68 8	98.00 92	94.03 29	96.97 19	97.61 116	87.68 214	98.45 19	98.77 17	94.20 77	99.50 22	96.70 6	99.40 55	99.53 16

ANet_high		94.83 104	96.28 41	90.47 279	96.65 173	73.16 358	94.33 137	98.74 14	96.39 28	98.09 29	98.93 10	93.37 91	98.70 162	90.38 157	99.68 17	99.53 16

Anonymous20231211		96.60 29	97.13 16	95.00 103	97.46 132	86.35 168	97.11 18	98.24 40	97.58 9	98.72 9	98.97 9	93.15 99	99.15 89	93.18 84	99.74 12	99.50 18

OurMVSNet-221017-0		96.80 16	96.75 21	96.96 39	99.03 11	91.85 61	97.98 7	98.01 80	94.15 58	98.93 4	99.07 7	88.07 195	99.57 15	95.86 15	99.69 14	99.46 19

pmmvs6		96.80 16	97.36 10	95.15 100	99.12 8	87.82 132	96.68 29	97.86 94	96.10 33	98.14 28	99.28 5	97.94 3	98.21 214	91.38 136	99.69 14	99.42 20

v10		94.68 111	95.27 95	92.90 191	96.57 179	80.15 259	94.65 125	97.57 120	90.68 148	97.43 50	98.00 52	88.18 192	99.15 89	94.84 34	99.55 35	99.41 21

mvs_tets		96.83 12	96.71 22	97.17 31	98.83 24	92.51 52	96.58 33	97.61 116	87.57 216	98.80 8	98.90 11	96.50 9	99.59 14	96.15 13	99.47 41	99.40 22

v8		94.65 112	95.29 93	92.74 196	96.65 173	79.77 274	94.59 126	97.17 153	91.86 109	97.47 49	97.93 57	88.16 193	99.08 98	94.32 42	99.47 41	99.38 23

TranMVSNet+NR-MVSNet		96.07 53	96.26 42	95.50 82	98.26 71	87.69 134	93.75 158	97.86 94	95.96 38	97.48 48	97.14 121	95.33 36	99.44 32	90.79 145	99.76 10	99.38 23

nrg030		96.32 44	96.55 29	95.62 78	97.83 103	88.55 118	95.77 78	98.29 36	92.68 84	98.03 30	97.91 62	95.13 45	98.95 118	93.85 54	99.49 40	99.36 25

WR-MVS		93.49 152	93.72 149	92.80 195	97.57 125	80.03 265	90.14 284	95.68 233	93.70 68	96.62 88	95.39 233	87.21 210	99.04 106	87.50 230	99.64 23	99.33 26

jajsoiax		96.59 31	96.42 33	97.12 33	98.76 30	92.49 53	96.44 43	97.42 131	86.96 225	98.71 11	98.72 19	95.36 34	99.56 18	95.92 14	99.45 45	99.32 27

LTVRE_ROB	93.87 1	97.93 3	98.16 2	97.26 30	98.81 27	93.86 35	99.07 2	98.98 9	97.01 15	98.92 5	98.78 16	95.22 42	98.61 174	96.85 4	99.77 9	99.31 28
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
UniMVSNet_NR-MVSNet		95.35 82	95.21 96	95.76 73	97.69 117	88.59 116	92.26 216	97.84 97	94.91 47	96.80 80	95.78 213	90.42 166	99.41 42	91.60 128	99.58 31	99.29 29

DU-MVS		95.28 88	95.12 100	95.75 74	97.75 109	88.59 116	92.58 196	97.81 100	93.99 60	96.80 80	95.90 203	90.10 175	99.41 42	91.60 128	99.58 31	99.26 30

NR-MVSNet		95.28 88	95.28 94	95.26 92	97.75 109	87.21 141	95.08 110	97.37 133	93.92 65	97.65 37	95.90 203	90.10 175	99.33 70	90.11 171	99.66 21	99.26 30

Baseline_NR-MVSNet		94.47 119	95.09 102	92.60 206	98.50 55	80.82 255	92.08 220	96.68 190	93.82 66	96.29 101	98.56 27	90.10 175	97.75 262	90.10 173	99.66 21	99.24 32

v1921920		93.26 160	93.61 155	92.19 217	96.04 229	78.31 302	91.88 232	97.24 149	85.17 257	96.19 112	96.19 190	86.76 221	99.05 103	94.18 46	98.84 135	99.22 33

v1192		93.49 152	93.78 147	92.62 204	96.16 215	79.62 276	91.83 236	97.22 151	86.07 237	96.10 115	96.38 176	87.22 209	99.02 108	94.14 47	98.88 130	99.22 33

v1240		93.29 158	93.71 150	92.06 224	96.01 230	77.89 308	91.81 237	97.37 133	85.12 259	96.69 85	96.40 171	86.67 222	99.07 102	94.51 37	98.76 149	99.22 33

dcpmvs_2		93.96 141	95.01 104	90.82 271	97.60 122	74.04 353	93.68 162	98.85 10	89.80 166	97.82 32	97.01 133	91.14 151	99.21 82	90.56 151	98.59 167	99.19 36

v144192		93.20 165	93.54 159	92.16 221	96.05 225	78.26 303	91.95 225	97.14 155	84.98 263	95.96 118	96.11 195	87.08 213	99.04 106	93.79 55	98.84 135	99.17 37

UniMVSNet (Re)		95.32 84	95.15 98	95.80 72	97.79 107	88.91 107	92.91 184	98.07 68	93.46 74	96.31 99	95.97 202	90.14 172	99.34 65	92.11 110	99.64 23	99.16 38

SixPastTwentyTwo		94.91 100	95.21 96	93.98 146	98.52 48	83.19 221	95.93 71	94.84 263	94.86 48	98.49 16	98.74 18	81.45 275	99.60 10	94.69 35	99.39 56	99.15 39

v2v482		93.29 158	93.63 153	92.29 213	96.35 198	78.82 295	91.77 239	96.28 210	88.45 195	95.70 136	96.26 187	86.02 230	98.90 122	93.02 90	98.81 143	99.14 40

v1144		93.50 151	93.81 144	92.57 207	96.28 205	79.61 277	91.86 235	96.96 168	86.95 226	95.91 122	96.32 180	87.65 202	98.96 116	93.51 65	98.88 130	99.13 41

HPM-MVS		96.81 15	96.62 26	97.36 27	98.89 20	93.53 42	97.51 10	98.44 20	92.35 93	95.95 119	96.41 170	96.71 8	99.42 36	93.99 51	99.36 58	99.13 41
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
patch_mono-2		92.46 188	92.72 180	91.71 234	96.65 173	78.91 292	88.85 321	97.17 153	83.89 276	92.45 263	96.76 148	89.86 179	97.09 302	90.24 166	98.59 167	99.12 43

MP-MVS-pluss		96.08 52	95.92 63	96.57 48	99.06 10	91.21 69	93.25 173	98.32 30	87.89 207	96.86 76	97.38 96	95.55 26	99.39 52	95.47 23	99.47 41	99.11 44
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
LPG-MVS_test		96.38 43	96.23 43	96.84 42	98.36 66	92.13 56	95.33 98	98.25 37	91.78 117	97.07 64	97.22 114	96.38 12	99.28 76	92.07 113	99.59 27	99.11 44

LGP-MVS_train				96.84 42	98.36 66	92.13 56		98.25 37	91.78 117	97.07 64	97.22 114	96.38 12	99.28 76	92.07 113	99.59 27	99.11 44

MIMVSNet1		95.52 73	95.45 84	95.72 75	99.14 5	89.02 105	96.23 59	96.87 177	93.73 67	97.87 31	98.49 31	90.73 161	99.05 103	86.43 251	99.60 25	99.10 47

VPA-MVSNet		95.14 93	95.67 77	93.58 166	97.76 108	83.15 222	94.58 128	97.58 119	93.39 75	97.05 67	98.04 49	93.25 95	98.51 187	89.75 181	99.59 27	99.08 48

TransMVSNet (Re)		95.27 91	96.04 56	92.97 186	98.37 63	81.92 239	95.07 111	96.76 186	93.97 62	97.77 34	98.57 26	95.72 20	97.90 241	88.89 205	99.23 86	99.08 48

SSC-MVS		90.16 243	92.96 170	81.78 388	97.88 100	48.48 420	90.75 262	87.69 358	96.02 37	96.70 84	97.63 77	85.60 236	97.80 254	85.73 259	98.60 166	99.06 50

MP-MVS		96.14 50	95.68 76	97.51 17	98.81 27	94.06 25	96.10 63	97.78 105	92.73 83	93.48 222	96.72 154	94.23 76	99.42 36	91.99 115	99.29 75	99.05 51
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EI-MVSNet-UG-set		94.35 125	94.27 134	94.59 124	92.46 337	85.87 180	92.42 206	94.69 270	93.67 71	96.13 113	95.84 207	91.20 147	98.86 129	93.78 56	98.23 202	99.03 52

ACMMP		96.61 28	96.34 38	97.43 22	98.61 37	93.88 33	96.95 20	98.18 49	92.26 96	96.33 97	96.84 144	95.10 48	99.40 49	93.47 69	99.33 65	99.02 53
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
ACMMPR		96.46 35	96.14 49	97.41 24	98.60 38	93.82 37	96.30 56	97.96 86	92.35 93	95.57 140	96.61 160	94.93 58	99.41 42	93.78 56	99.15 98	99.00 54

PGM-MVS		96.32 44	95.94 60	97.43 22	98.59 40	93.84 36	95.33 98	98.30 33	91.40 132	95.76 129	96.87 141	95.26 39	99.45 31	92.77 95	99.21 90	99.00 54

MTAPA		96.65 26	96.38 37	97.47 19	98.95 18	94.05 27	95.88 74	97.62 114	94.46 54	96.29 101	96.94 136	93.56 84	99.37 60	94.29 44	99.42 50	98.99 56

pm-mvs1		95.43 77	95.94 60	93.93 151	98.38 61	85.08 195	95.46 94	97.12 158	91.84 113	97.28 58	98.46 33	95.30 38	97.71 266	90.17 169	99.42 50	98.99 56

mPP-MVS		96.46 35	96.05 55	97.69 6	98.62 35	94.65 17	96.45 41	97.74 107	92.59 87	95.47 145	96.68 156	94.50 71	99.42 36	93.10 87	99.26 82	98.99 56

TDRefinement		97.68 4	97.60 5	97.93 3	99.02 12	95.95 9	98.61 3	98.81 11	97.41 11	97.28 58	98.46 33	94.62 66	98.84 132	94.64 36	99.53 37	98.99 56

fmvsm_s_conf0.1_n		94.19 135	94.41 125	93.52 172	97.22 143	84.37 200	93.73 159	95.26 252	84.45 270	95.76 129	98.00 52	91.85 129	97.21 293	95.62 17	97.82 236	98.98 60

EI-MVSNet-Vis-set		94.36 124	94.28 132	94.61 120	92.55 334	85.98 177	92.44 204	94.69 270	93.70 68	96.12 114	95.81 209	91.24 144	98.86 129	93.76 59	98.22 204	98.98 60

MM		94.41 122	94.14 138	95.22 97	95.84 238	87.21 141	94.31 139	90.92 335	94.48 53	92.80 250	97.52 86	85.27 238	99.49 28	96.58 8	99.57 33	98.97 62

ZNCC-MVS		96.42 39	96.20 45	97.07 34	98.80 29	92.79 50	96.08 65	98.16 56	91.74 121	95.34 154	96.36 178	95.68 21	99.44 32	94.41 41	99.28 80	98.97 62

IS-MVSNet		94.49 118	94.35 130	94.92 105	98.25 73	86.46 163	97.13 17	94.31 276	96.24 31	96.28 103	96.36 178	82.88 258	99.35 62	88.19 215	99.52 39	98.96 64

ACMM	88.83 9	96.30 46	96.07 54	96.97 38	98.39 60	92.95 48	94.74 121	98.03 77	90.82 144	97.15 61	96.85 142	96.25 14	99.00 110	93.10 87	99.33 65	98.95 65
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n_a		94.26 129	94.37 128	93.95 150	97.36 136	85.72 184	94.15 144	95.44 245	83.25 282	95.51 142	98.05 47	92.54 116	97.19 296	95.55 21	97.46 255	98.94 66

region2R		96.41 40	96.09 51	97.38 26	98.62 35	93.81 39	96.32 51	97.96 86	92.26 96	95.28 159	96.57 162	95.02 52	99.41 42	93.63 60	99.11 101	98.94 66

SMA-MVS		95.77 64	95.54 81	96.47 53	98.27 70	91.19 70	95.09 109	97.79 104	86.48 228	97.42 52	97.51 90	94.47 74	99.29 73	93.55 64	99.29 75	98.93 68
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
XVS		96.49 33	96.18 46	97.44 20	98.56 41	93.99 30	96.50 37	97.95 88	94.58 50	94.38 196	96.49 164	94.56 69	99.39 52	93.57 62	99.05 106	98.93 68

X-MVStestdata		90.70 223	88.45 271	97.44 20	98.56 41	93.99 30	96.50 37	97.95 88	94.58 50	94.38 196	26.89 419	94.56 69	99.39 52	93.57 62	99.05 106	98.93 68

VPNet		93.08 166	93.76 148	91.03 261	98.60 38	75.83 337	91.51 242	95.62 234	91.84 113	95.74 132	97.10 126	89.31 183	98.32 205	85.07 270	99.06 103	98.93 68

APDe-MVS		96.46 35	96.64 25	95.93 64	97.68 118	89.38 98	96.90 21	98.41 23	92.52 88	97.43 50	97.92 61	95.11 47	99.50 22	94.45 39	99.30 72	98.92 72
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
HPM-MVS_fast		97.01 10	96.89 18	97.39 25	99.12 8	93.92 32	97.16 14	98.17 53	93.11 80	96.48 92	97.36 100	96.92 6	99.34 65	94.31 43	99.38 57	98.92 72

test1111		90.39 234	90.61 230	89.74 299	98.04 89	71.50 370	95.59 85	79.72 409	89.41 172	95.94 120	98.14 42	70.79 343	98.81 139	88.52 212	99.32 69	98.90 74

test_0728_THIRD									93.26 78	97.40 54	97.35 103	94.69 63	99.34 65	93.88 52	99.42 50	98.89 75

MSP-MVS		95.34 83	94.63 122	97.48 18	98.67 32	94.05 27	96.41 45	98.18 49	91.26 134	95.12 169	95.15 237	86.60 224	99.50 22	93.43 75	96.81 280	98.89 75
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
GST-MVS		96.24 47	95.99 59	97.00 37	98.65 33	92.71 51	95.69 82	98.01 80	92.08 102	95.74 132	96.28 184	95.22 42	99.42 36	93.17 85	99.06 103	98.88 77

EI-MVSNet		92.99 169	93.26 167	92.19 217	92.12 347	79.21 287	92.32 211	94.67 272	91.77 119	95.24 163	95.85 205	87.14 212	98.49 188	91.99 115	98.26 198	98.86 78

IterMVS-LS		93.78 146	94.28 132	92.27 214	96.27 206	79.21 287	91.87 233	96.78 183	91.77 119	96.57 91	97.07 127	87.15 211	98.74 153	91.99 115	99.03 112	98.86 78
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	88.36 12	96.59 31	97.43 6	94.07 144	98.56 41	85.33 192	96.33 49	98.30 33	94.66 49	98.72 9	98.30 38	97.51 5	98.00 234	94.87 33	99.59 27	98.86 78
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
V42		93.43 155	93.58 156	92.97 186	95.34 268	81.22 249	92.67 192	96.49 203	87.25 220	96.20 109	96.37 177	87.32 208	98.85 131	92.39 107	98.21 205	98.85 81

test_fmvs3		92.42 189	92.40 188	92.46 212	93.80 312	87.28 139	93.86 155	97.05 162	76.86 348	96.25 104	98.66 21	82.87 259	91.26 391	95.44 24	96.83 279	98.82 82

SteuartSystems-ACMMP		96.40 41	96.30 40	96.71 44	98.63 34	91.96 59	95.70 80	98.01 80	93.34 77	96.64 87	96.57 162	94.99 54	99.36 61	93.48 68	99.34 63	98.82 82
Skip Steuart: Steuart Systems R&D Blog.
VDDNet		94.03 138	94.27 134	93.31 178	98.87 21	82.36 234	95.51 93	91.78 327	97.19 13	96.32 98	98.60 25	84.24 246	98.75 150	87.09 238	98.83 140	98.81 84

ACMMP_NAP		96.21 48	96.12 50	96.49 52	98.90 19	91.42 67	94.57 129	98.03 77	90.42 156	96.37 95	97.35 103	95.68 21	99.25 79	94.44 40	99.34 63	98.80 85

RPSCF		95.58 72	94.89 107	97.62 9	97.58 124	96.30 8	95.97 70	97.53 124	92.42 89	93.41 224	97.78 67	91.21 146	97.77 259	91.06 139	97.06 268	98.80 85

WB-MVS		89.44 261	92.15 193	81.32 389	97.73 112	48.22 421	89.73 297	87.98 356	95.24 42	96.05 116	96.99 134	85.18 239	96.95 308	82.45 296	97.97 227	98.78 87

Anonymous20240529		95.50 74	95.83 69	94.50 128	97.33 138	85.93 178	95.19 108	96.77 185	96.64 21	97.61 41	98.05 47	93.23 96	98.79 143	88.60 211	99.04 111	98.78 87

v148		92.87 175	93.29 163	91.62 238	96.25 209	77.72 311	91.28 249	95.05 256	89.69 167	95.93 121	96.04 198	87.34 207	98.38 199	90.05 174	97.99 225	98.78 87

ACMP	88.15 13	95.71 67	95.43 86	96.54 49	98.17 78	91.73 64	94.24 140	98.08 65	89.46 171	96.61 89	96.47 165	95.85 18	99.12 94	90.45 154	99.56 34	98.77 90
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20240521		92.86 176	93.57 157	90.74 273	96.57 179	75.50 339	94.15 144	95.60 235	89.38 173	95.90 123	97.90 64	80.39 284	97.96 238	92.60 102	99.68 17	98.75 91

KD-MVS_self_test		94.10 136	94.73 115	92.19 217	97.66 120	79.49 280	94.86 118	97.12 158	89.59 170	96.87 75	97.65 75	90.40 168	98.34 204	89.08 200	99.35 59	98.75 91

APD-MVS_3200maxsize		96.82 13	96.65 24	97.32 29	97.95 96	93.82 37	96.31 52	98.25 37	95.51 41	96.99 71	97.05 129	95.63 23	99.39 52	93.31 78	98.88 130	98.75 91

lessismore_v0				93.87 154	98.05 86	83.77 213		80.32 407		97.13 62	97.91 62	77.49 305	99.11 96	92.62 101	98.08 217	98.74 94

K. test v3		93.37 156	93.27 166	93.66 162	98.05 86	82.62 230	94.35 136	86.62 367	96.05 35	97.51 46	98.85 14	76.59 320	99.65 5	93.21 83	98.20 207	98.73 95

MSC_two_6792asdad				95.90 67	96.54 182	89.57 91		96.87 177					99.41 42	94.06 48	99.30 72	98.72 96

No_MVS				95.90 67	96.54 182	89.57 91		96.87 177					99.41 42	94.06 48	99.30 72	98.72 96

ACMH+	88.43 11	96.48 34	96.82 19	95.47 83	98.54 46	89.06 104	95.65 83	98.61 15	96.10 33	98.16 27	97.52 86	96.90 7	98.62 173	90.30 162	99.60 25	98.72 96

MVS_0304		92.88 173	92.27 189	94.69 116	92.35 338	86.03 176	92.88 186	89.68 342	90.53 152	91.52 285	96.43 168	82.52 266	99.32 71	95.01 32	99.54 36	98.71 99

SDMVSNet		94.43 121	95.02 103	92.69 198	97.93 97	82.88 228	91.92 229	95.99 226	93.65 72	95.51 142	98.63 23	94.60 67	96.48 325	87.57 229	99.35 59	98.70 100

sd_testset		93.94 142	94.39 126	92.61 205	97.93 97	83.24 218	93.17 177	95.04 257	93.65 72	95.51 142	98.63 23	94.49 72	95.89 344	81.72 304	99.35 59	98.70 100

OPM-MVS		95.61 70	95.45 84	96.08 57	98.49 56	91.00 72	92.65 194	97.33 141	90.05 161	96.77 82	96.85 142	95.04 50	98.56 181	92.77 95	99.06 103	98.70 100
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
fmvsm_s_conf0.5_n		94.00 140	94.20 136	93.42 176	96.69 170	84.37 200	93.38 171	95.13 255	84.50 269	95.40 149	97.55 85	91.77 132	97.20 294	95.59 18	97.79 237	98.69 103

test2506		85.42 328	84.57 331	87.96 332	97.81 105	66.53 393	96.14 61	56.35 422	89.04 180	93.55 221	98.10 44	42.88 419	98.68 166	88.09 219	99.18 94	98.67 104

ECVR-MVS		90.12 245	90.16 239	90.00 295	97.81 105	72.68 364	95.76 79	78.54 412	89.04 180	95.36 153	98.10 44	70.51 345	98.64 172	87.10 237	99.18 94	98.67 104

casdiffmvs_mvg		95.10 94	95.62 78	93.53 170	96.25 209	83.23 219	92.66 193	98.19 47	93.06 81	97.49 47	97.15 120	94.78 61	98.71 161	92.27 108	98.72 152	98.65 106
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GBi-Net		93.21 163	92.96 170	93.97 147	95.40 264	84.29 202	95.99 67	96.56 198	88.63 190	95.10 170	98.53 28	81.31 277	98.98 111	86.74 241	98.38 186	98.65 106

test1		93.21 163	92.96 170	93.97 147	95.40 264	84.29 202	95.99 67	96.56 198	88.63 190	95.10 170	98.53 28	81.31 277	98.98 111	86.74 241	98.38 186	98.65 106

FMVSNet1		94.84 103	95.13 99	93.97 147	97.60 122	84.29 202	95.99 67	96.56 198	92.38 90	97.03 68	98.53 28	90.12 173	98.98 111	88.78 207	99.16 97	98.65 106

EPP-MVSNet		93.91 143	93.68 152	94.59 124	98.08 83	85.55 188	97.44 11	94.03 282	94.22 57	94.94 178	96.19 190	82.07 270	99.57 15	87.28 235	98.89 128	98.65 106

fmvsm_s_conf0.5_n_a		94.02 139	94.08 141	93.84 156	96.72 169	85.73 183	93.65 163	95.23 253	83.30 280	95.13 168	97.56 81	92.22 121	97.17 297	95.51 22	97.41 257	98.64 111

IU-MVS					98.51 49	86.66 158		96.83 180	72.74 375	95.83 126				93.00 91	99.29 75	98.64 111

SF-MVS		95.88 60	95.88 65	95.87 70	98.12 80	89.65 90	95.58 88	98.56 17	91.84 113	96.36 96	96.68 156	94.37 75	99.32 71	92.41 106	99.05 106	98.64 111

casdiffmvs		94.32 127	94.80 110	92.85 193	96.05 225	81.44 246	92.35 209	98.05 72	91.53 129	95.75 131	96.80 145	93.35 92	98.49 188	91.01 142	98.32 194	98.64 111
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TSAR-MVS + MP.		94.96 99	94.75 112	95.57 80	98.86 22	88.69 110	96.37 46	96.81 181	85.23 255	94.75 186	97.12 123	91.85 129	99.40 49	93.45 71	98.33 192	98.62 115
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HQP_MVS		94.26 129	93.93 142	95.23 95	97.71 114	88.12 125	94.56 130	97.81 100	91.74 121	93.31 228	95.59 220	86.93 217	98.95 118	89.26 194	98.51 176	98.60 116

plane_prior5								97.81 100					98.95 118	89.26 194	98.51 176	98.60 116

CP-MVS		96.44 38	96.08 53	97.54 15	98.29 68	94.62 18	96.80 24	98.08 65	92.67 86	95.08 173	96.39 175	94.77 62	99.42 36	93.17 85	99.44 48	98.58 118

tttt0517		89.81 255	88.90 265	92.55 208	97.00 151	79.73 275	95.03 113	83.65 392	89.88 164	95.30 156	94.79 254	53.64 401	99.39 52	91.99 115	98.79 146	98.54 119

mamv4		98.21 2	97.86 3	99.26 1	98.24 74	99.36 1	96.10 63	99.32 2	98.75 2	99.58 2	98.70 20	91.78 131	99.88 1	98.60 1	99.67 20	98.54 119

test_0728_SECOND				94.88 107	98.55 44	86.72 155	95.20 106	98.22 44					99.38 58	93.44 72	99.31 70	98.53 121

reproduce_model		97.35 5	97.24 12	97.70 5	98.44 58	95.08 12	95.88 74	98.50 18	96.62 22	98.27 21	97.93 57	94.57 68	99.50 22	95.57 20	99.35 59	98.52 122

test_vis3_rt		90.40 232	90.03 243	91.52 243	92.58 332	88.95 106	90.38 276	97.72 109	73.30 370	97.79 33	97.51 90	77.05 312	87.10 408	89.03 201	94.89 330	98.50 123

SR-MVS		96.70 23	96.42 33	97.54 15	98.05 86	94.69 15	96.13 62	98.07 68	95.17 43	96.82 79	96.73 153	95.09 49	99.43 35	92.99 92	98.71 154	98.50 123

test_241102_TWO								98.10 62	91.95 104	97.54 43	97.25 110	95.37 32	99.35 62	93.29 79	99.25 83	98.49 125

HFP-MVS		96.39 42	96.17 48	97.04 35	98.51 49	93.37 43	96.30 56	97.98 83	92.35 93	95.63 137	96.47 165	95.37 32	99.27 78	93.78 56	99.14 99	98.48 126

3Dnovator+	92.74 2	95.86 61	95.77 73	96.13 56	96.81 166	90.79 77	96.30 56	97.82 99	96.13 32	94.74 187	97.23 112	91.33 141	99.16 88	93.25 82	98.30 195	98.46 127

XVG-OURS-SEG-HR		95.38 81	95.00 105	96.51 50	98.10 82	94.07 24	92.46 202	98.13 58	90.69 147	93.75 215	96.25 188	98.03 2	97.02 306	92.08 112	95.55 311	98.45 128

ttmdpeth		86.91 319	86.57 313	87.91 335	89.68 388	74.24 351	91.49 243	87.09 363	79.84 317	89.46 325	97.86 65	65.42 368	91.04 392	81.57 306	96.74 285	98.44 129

baseline		94.26 129	94.80 110	92.64 200	96.08 223	80.99 252	93.69 161	98.04 76	90.80 145	94.89 181	96.32 180	93.19 97	98.48 192	91.68 126	98.51 176	98.43 130

DPE-MVS		95.89 59	95.88 65	95.92 66	97.93 97	89.83 88	93.46 167	98.30 33	92.37 91	97.75 35	96.95 135	95.14 44	99.51 21	91.74 123	99.28 80	98.41 131
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
reproduce-ours		97.28 7	97.19 14	97.57 12	98.37 63	94.84 13	95.57 89	98.40 24	96.36 29	98.18 25	97.78 67	95.47 28	99.50 22	95.26 30	99.33 65	98.36 132

our_new_method		97.28 7	97.19 14	97.57 12	98.37 63	94.84 13	95.57 89	98.40 24	96.36 29	98.18 25	97.78 67	95.47 28	99.50 22	95.26 30	99.33 65	98.36 132

tfpnnormal		94.27 128	94.87 108	92.48 210	97.71 114	80.88 254	94.55 132	95.41 248	93.70 68	96.67 86	97.72 72	91.40 140	98.18 218	87.45 231	99.18 94	98.36 132

VDD-MVS		94.37 123	94.37 128	94.40 134	97.49 129	86.07 175	93.97 152	93.28 297	94.49 52	96.24 105	97.78 67	87.99 198	98.79 143	88.92 203	99.14 99	98.34 135

XVG-ACMP-BASELINE		95.68 68	95.34 90	96.69 45	98.40 59	93.04 45	94.54 133	98.05 72	90.45 155	96.31 99	96.76 148	92.91 107	98.72 155	91.19 137	99.42 50	98.32 136

CNVR-MVS		94.58 115	94.29 131	95.46 84	96.94 154	89.35 99	91.81 237	96.80 182	89.66 168	93.90 213	95.44 228	92.80 111	98.72 155	92.74 97	98.52 174	98.32 136

COLMAP_ROB	91.06 5	96.75 20	96.62 26	97.13 32	98.38 61	94.31 21	96.79 25	98.32 30	96.69 19	96.86 76	97.56 81	95.48 27	98.77 149	90.11 171	99.44 48	98.31 138
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
XVG-OURS		94.72 108	94.12 139	96.50 51	98.00 92	94.23 22	91.48 244	98.17 53	90.72 146	95.30 156	96.47 165	87.94 199	96.98 307	91.41 135	97.61 248	98.30 139

EPNet		89.80 256	88.25 279	94.45 132	83.91 417	86.18 172	93.87 154	87.07 365	91.16 138	80.64 406	94.72 256	78.83 292	98.89 124	85.17 263	98.89 128	98.28 140
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmconf0.01_n		95.90 58	96.09 51	95.31 91	97.30 139	89.21 100	94.24 140	98.76 13	86.25 232	97.56 42	98.66 21	95.73 19	98.44 195	97.35 3	98.99 114	98.27 141

reproduce_monomvs		87.13 314	86.90 306	87.84 337	90.92 372	68.15 385	91.19 251	93.75 288	85.84 241	94.21 200	95.83 208	42.99 416	97.10 301	89.46 186	97.88 233	98.26 142

GeoE		94.55 116	94.68 119	94.15 140	97.23 141	85.11 194	94.14 146	97.34 140	88.71 189	95.26 160	95.50 225	94.65 65	99.12 94	90.94 143	98.40 182	98.23 143

NCCC		94.08 137	93.54 159	95.70 77	96.49 187	89.90 87	92.39 208	96.91 174	90.64 149	92.33 272	94.60 261	90.58 165	98.96 116	90.21 168	97.70 242	98.23 143

XXY-MVS		92.58 184	93.16 168	90.84 270	97.75 109	79.84 270	91.87 233	96.22 216	85.94 239	95.53 141	97.68 73	92.69 113	94.48 368	83.21 286	97.51 251	98.21 145

CDPH-MVS		92.67 182	91.83 202	95.18 99	96.94 154	88.46 121	90.70 265	97.07 161	77.38 342	92.34 271	95.08 242	92.67 114	98.88 125	85.74 258	98.57 169	98.20 146

test_fmvsmconf0.1_n		95.61 70	95.72 75	95.26 92	96.85 162	89.20 101	93.51 165	98.60 16	85.68 246	97.42 52	98.30 38	95.34 35	98.39 196	96.85 4	98.98 115	98.19 147

testf1		96.77 18	96.49 30	97.60 10	99.01 14	96.70 4	96.31 52	98.33 28	94.96 45	97.30 56	97.93 57	96.05 16	97.90 241	89.32 188	99.23 86	98.19 147

APD_test2		96.77 18	96.49 30	97.60 10	99.01 14	96.70 4	96.31 52	98.33 28	94.96 45	97.30 56	97.93 57	96.05 16	97.90 241	89.32 188	99.23 86	98.19 147

new-patchmatchnet		88.97 273	90.79 226	83.50 383	94.28 298	55.83 418	85.34 378	93.56 292	86.18 235	95.47 145	95.73 216	83.10 255	96.51 324	85.40 262	98.06 218	98.16 150

HQP4-MVS										88.81 333			98.61 174			98.15 151

HQP-MVS		92.09 199	91.49 210	93.88 153	96.36 195	84.89 196	91.37 245	97.31 142	87.16 221	88.81 333	93.40 299	84.76 243	98.60 176	86.55 248	97.73 239	98.14 152

DVP-MVS		95.82 62	96.18 46	94.72 114	98.51 49	86.69 156	95.20 106	97.00 165	91.85 110	97.40 54	97.35 103	95.58 24	99.34 65	93.44 72	99.31 70	98.13 153
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
ambc				92.98 185	96.88 159	83.01 226	95.92 72	96.38 208		96.41 94	97.48 92	88.26 191	97.80 254	89.96 176	98.93 125	98.12 154

test_fmvsmconf_n		95.43 77	95.50 82	95.22 97	96.48 189	89.19 102	93.23 175	98.36 27	85.61 249	96.92 74	98.02 51	95.23 41	98.38 199	96.69 7	98.95 124	98.09 155

eth_miper_zixun_eth		90.72 222	90.61 230	91.05 260	92.04 350	76.84 324	86.91 351	96.67 191	85.21 256	94.41 194	93.92 284	79.53 288	98.26 211	89.76 180	97.02 270	98.06 156

FMVSNet2		92.78 178	92.73 179	92.95 188	95.40 264	81.98 238	94.18 143	95.53 243	88.63 190	96.05 116	97.37 97	81.31 277	98.81 139	87.38 234	98.67 160	98.06 156

OMC-MVS		94.22 132	93.69 151	95.81 71	97.25 140	91.27 68	92.27 215	97.40 132	87.10 224	94.56 191	95.42 229	93.74 82	98.11 223	86.62 245	98.85 134	98.06 156

DVP-MVS++		95.93 56	96.34 38	94.70 115	96.54 182	86.66 158	98.45 4	98.22 44	93.26 78	97.54 43	97.36 100	93.12 100	99.38 58	93.88 52	98.68 158	98.04 159

PC_three_1452									75.31 359	95.87 125	95.75 215	92.93 106	96.34 334	87.18 236	98.68 158	98.04 159

c3_l		91.32 215	91.42 211	91.00 264	92.29 340	76.79 325	87.52 342	96.42 206	85.76 244	94.72 189	93.89 286	82.73 262	98.16 220	90.93 144	98.55 170	98.04 159

EG-PatchMatch MVS		94.54 117	94.67 120	94.14 141	97.87 102	86.50 160	92.00 224	96.74 187	88.16 203	96.93 73	97.61 78	93.04 104	97.90 241	91.60 128	98.12 212	98.03 162

MVS_111021_HR		93.63 149	93.42 162	94.26 138	96.65 173	86.96 150	89.30 311	96.23 214	88.36 199	93.57 220	94.60 261	93.45 87	97.77 259	90.23 167	98.38 186	98.03 162

SR-MVS-dyc-post		96.84 11	96.60 28	97.56 14	98.07 84	95.27 10	96.37 46	98.12 59	95.66 39	97.00 69	97.03 130	94.85 60	99.42 36	93.49 66	98.84 135	98.00 164

RE-MVS-def			96.66 23		98.07 84	95.27 10	96.37 46	98.12 59	95.66 39	97.00 69	97.03 130	95.40 31		93.49 66	98.84 135	98.00 164

thisisatest0530		88.69 281	87.52 293	92.20 216	96.33 200	79.36 282	92.81 187	84.01 391	86.44 229	93.67 218	92.68 318	53.62 402	99.25 79	89.65 183	98.45 180	98.00 164

Vis-MVSNet (Re-imp)		90.42 231	90.16 239	91.20 257	97.66 120	77.32 316	94.33 137	87.66 359	91.20 136	92.99 244	95.13 239	75.40 325	98.28 207	77.86 340	99.19 92	97.99 167

agg_prior2														87.06 239	98.36 191	97.98 168

AllTest		94.88 102	94.51 124	96.00 58	98.02 90	92.17 54	95.26 102	98.43 21	90.48 153	95.04 174	96.74 151	92.54 116	97.86 249	85.11 268	98.98 115	97.98 168

TestCases				96.00 58	98.02 90	92.17 54		98.43 21	90.48 153	95.04 174	96.74 151	92.54 116	97.86 249	85.11 268	98.98 115	97.98 168

MVSTER		89.32 263	88.75 267	91.03 261	90.10 384	76.62 327	90.85 259	94.67 272	82.27 297	95.24 163	95.79 210	61.09 388	98.49 188	90.49 153	98.26 198	97.97 171

SED-MVS		96.00 55	96.41 36	94.76 112	98.51 49	86.97 148	95.21 104	98.10 62	91.95 104	97.63 38	97.25 110	96.48 10	99.35 62	93.29 79	99.29 75	97.95 172

OPU-MVS				95.15 100	96.84 163	89.43 95	95.21 104				95.66 218	93.12 100	98.06 226	86.28 254	98.61 164	97.95 172

MVStest1		84.79 334	84.06 336	86.98 345	77.73 422	74.76 341	91.08 256	85.63 377	77.70 340	96.86 76	97.97 55	41.05 421	88.24 406	92.22 109	96.28 295	97.94 174

test_prior				94.61 120	95.95 233	87.23 140		97.36 138					98.68 166			97.93 175

DeepC-MVS	91.39 4	95.43 77	95.33 91	95.71 76	97.67 119	90.17 84	93.86 155	98.02 79	87.35 218	96.22 107	97.99 54	94.48 73	99.05 103	92.73 98	99.68 17	97.93 175
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
RRT-MVS		92.28 194	93.01 169	90.07 291	94.06 304	73.01 360	95.36 95	97.88 92	92.24 98	95.16 167	97.52 86	78.51 298	99.29 73	90.55 152	95.83 306	97.92 177

UGNet		93.08 166	92.50 185	94.79 111	93.87 309	87.99 128	95.07 111	94.26 279	90.64 149	87.33 360	97.67 74	86.89 219	98.49 188	88.10 218	98.71 154	97.91 178
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
CANet		92.38 191	91.99 197	93.52 172	93.82 311	83.46 215	91.14 252	97.00 165	89.81 165	86.47 364	94.04 278	87.90 200	99.21 82	89.50 185	98.27 197	97.90 179

HPM-MVS++		95.02 96	94.39 126	96.91 41	97.88 100	93.58 41	94.09 148	96.99 167	91.05 139	92.40 266	95.22 236	91.03 153	99.25 79	92.11 110	98.69 157	97.90 179

CS-MVS		95.77 64	95.58 80	96.37 54	96.84 163	91.72 65	96.73 28	99.06 8	94.23 56	92.48 261	94.79 254	93.56 84	99.49 28	93.47 69	99.05 106	97.89 181

WBMVS		84.00 342	83.48 341	85.56 363	92.71 330	61.52 410	83.82 393	89.38 344	79.56 324	90.74 299	93.20 305	48.21 406	97.28 289	75.63 361	98.10 215	97.88 182

testgi		90.38 235	91.34 214	87.50 340	97.49 129	71.54 369	89.43 306	95.16 254	88.38 197	94.54 192	94.68 258	92.88 109	93.09 383	71.60 384	97.85 235	97.88 182

test_0402		95.73 66	96.22 44	94.26 138	98.19 77	85.77 182	93.24 174	97.24 149	96.88 18	97.69 36	97.77 71	94.12 78	99.13 93	91.54 132	99.29 75	97.88 182

miper_lstm_enhance		89.90 253	89.80 248	90.19 290	91.37 366	77.50 313	83.82 393	95.00 258	84.84 266	93.05 242	94.96 246	76.53 321	95.20 360	89.96 176	98.67 160	97.86 185

MCST-MVS		92.91 171	92.51 184	94.10 143	97.52 127	85.72 184	91.36 248	97.13 157	80.33 315	92.91 248	94.24 271	91.23 145	98.72 155	89.99 175	97.93 230	97.86 185

Vis-MVSNet		95.50 74	95.48 83	95.56 81	98.11 81	89.40 97	95.35 96	98.22 44	92.36 92	94.11 201	98.07 46	92.02 125	99.44 32	93.38 77	97.67 244	97.85 187
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_fmvs2		90.62 227	90.40 236	91.29 251	91.93 354	85.46 190	92.70 191	96.48 204	74.44 363	94.91 180	97.59 79	75.52 324	90.57 394	93.44 72	96.56 288	97.84 188

test9_res														88.16 217	98.40 182	97.83 189

VNet		92.67 182	92.96 170	91.79 230	96.27 206	80.15 259	91.95 225	94.98 259	92.19 100	94.52 193	96.07 197	87.43 206	97.39 285	84.83 272	98.38 186	97.83 189

diffmvs		91.74 204	91.93 199	91.15 259	93.06 322	78.17 304	88.77 324	97.51 127	86.28 231	92.42 265	93.96 283	88.04 196	97.46 279	90.69 149	96.67 286	97.82 191
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
FMVSNet3		90.78 221	90.32 238	92.16 221	93.03 324	79.92 269	92.54 197	94.95 260	86.17 236	95.10 170	96.01 200	69.97 347	98.75 150	86.74 241	98.38 186	97.82 191

CPTT-MVS		94.74 107	94.12 139	96.60 47	98.15 79	93.01 46	95.84 76	97.66 111	89.21 179	93.28 231	95.46 226	88.89 186	98.98 111	89.80 178	98.82 141	97.80 193

APD_test1		95.91 57	95.42 87	97.36 27	98.82 25	96.62 7	95.64 84	97.64 112	93.38 76	95.89 124	97.23 112	93.35 92	97.66 269	88.20 214	98.66 162	97.79 194

cl22		89.02 269	88.50 270	90.59 277	89.76 386	76.45 329	86.62 361	94.03 282	82.98 289	92.65 255	92.49 320	72.05 338	97.53 274	88.93 202	97.02 270	97.78 195

Anonymous202405211		92.58 184	92.50 185	92.83 194	96.55 181	83.22 220	92.43 205	91.64 329	94.10 59	95.59 139	96.64 158	81.88 274	97.50 276	85.12 267	98.52 174	97.77 196

cl____		90.65 225	90.56 232	90.91 268	91.85 355	76.98 322	86.75 356	95.36 250	85.53 251	94.06 205	94.89 248	77.36 310	97.98 237	90.27 164	98.98 115	97.76 197

DIV-MVS_self_test		90.65 225	90.56 232	90.91 268	91.85 355	76.99 321	86.75 356	95.36 250	85.52 253	94.06 205	94.89 248	77.37 309	97.99 236	90.28 163	98.97 120	97.76 197

test12				94.43 133	95.95 233	86.75 154		96.24 213		89.76 321		89.79 180	98.79 143		97.95 229	97.75 199

test_fmvsm_n_1920		94.72 108	94.74 114	94.67 117	96.30 204	88.62 113	93.19 176	98.07 68	85.63 248	97.08 63	97.35 103	90.86 154	97.66 269	95.70 16	98.48 179	97.74 200

train_agg		92.71 181	91.83 202	95.35 86	96.45 190	89.46 93	90.60 268	96.92 172	79.37 326	90.49 303	94.39 267	91.20 147	98.88 125	88.66 210	98.43 181	97.72 201

IterMVS-SCA-FT		91.65 206	91.55 206	91.94 226	93.89 308	79.22 286	87.56 339	93.51 293	91.53 129	95.37 152	96.62 159	78.65 294	98.90 122	91.89 119	94.95 329	97.70 202

3Dnovator	92.54 3	94.80 106	94.90 106	94.47 131	95.47 262	87.06 145	96.63 31	97.28 147	91.82 116	94.34 198	97.41 94	90.60 164	98.65 171	92.47 105	98.11 213	97.70 202

PVSNet_BlendedMVS		90.35 237	89.96 244	91.54 242	94.81 280	78.80 297	90.14 284	96.93 170	79.43 325	88.68 340	95.06 243	86.27 227	98.15 221	80.27 317	98.04 220	97.68 204

Effi-MVS+-dtu		93.90 144	92.60 183	97.77 4	94.74 285	96.67 6	94.00 150	95.41 248	89.94 162	91.93 281	92.13 330	90.12 173	98.97 115	87.68 228	97.48 253	97.67 205

LFMVS		91.33 214	91.16 219	91.82 229	96.27 206	79.36 282	95.01 114	85.61 379	96.04 36	94.82 183	97.06 128	72.03 339	98.46 193	84.96 271	98.70 156	97.65 206

UnsupCasMVSNet_eth		90.33 238	90.34 237	90.28 284	94.64 291	80.24 257	89.69 299	95.88 227	85.77 243	93.94 212	95.69 217	81.99 271	92.98 384	84.21 279	91.30 387	97.62 207

CLD-MVS		91.82 202	91.41 212	93.04 183	96.37 193	83.65 214	86.82 355	97.29 145	84.65 268	92.27 273	89.67 364	92.20 123	97.85 251	83.95 281	99.47 41	97.62 207
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
SPE-MVS-test		95.32 84	95.10 101	95.96 60	96.86 161	90.75 78	96.33 49	99.20 5	93.99 60	91.03 295	93.73 290	93.52 86	99.55 19	91.81 121	99.45 45	97.58 209

MDA-MVSNet-bldmvs		91.04 217	90.88 222	91.55 241	94.68 289	80.16 258	85.49 376	92.14 321	90.41 157	94.93 179	95.79 210	85.10 240	96.93 311	85.15 265	94.19 350	97.57 210

DP-MVS		95.62 69	95.84 68	94.97 104	97.16 146	88.62 113	94.54 133	97.64 112	96.94 17	96.58 90	97.32 107	93.07 103	98.72 155	90.45 154	98.84 135	97.57 210

APD-MVS		95.00 97	94.69 116	95.93 64	97.38 134	90.88 75	94.59 126	97.81 100	89.22 178	95.46 147	96.17 193	93.42 90	99.34 65	89.30 190	98.87 133	97.56 212
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
FMVSNet5		87.82 295	86.56 314	91.62 238	92.31 339	79.81 273	93.49 166	94.81 266	83.26 281	91.36 288	96.93 137	52.77 403	97.49 278	76.07 357	98.03 221	97.55 213

CL-MVSNet_self_test		90.04 251	89.90 246	90.47 279	95.24 270	77.81 309	86.60 362	92.62 311	85.64 247	93.25 235	93.92 284	83.84 249	96.06 339	79.93 325	98.03 221	97.53 214

EC-MVSNet		95.44 76	95.62 78	94.89 106	96.93 156	87.69 134	96.48 40	99.14 7	93.93 63	92.77 252	94.52 264	93.95 81	99.49 28	93.62 61	99.22 89	97.51 215

QAPM		92.88 173	92.77 175	93.22 181	95.82 240	83.31 216	96.45 41	97.35 139	83.91 275	93.75 215	96.77 146	89.25 184	98.88 125	84.56 276	97.02 270	97.49 216

Patchmtry		90.11 246	89.92 245	90.66 275	90.35 381	77.00 320	92.96 182	92.81 304	90.25 159	94.74 187	96.93 137	67.11 356	97.52 275	85.17 263	98.98 115	97.46 217

EGC-MVSNET		80.97 367	75.73 384	96.67 46	98.85 23	94.55 19	96.83 22	96.60 194	2.44 421	5.32 422	98.25 40	92.24 120	98.02 231	91.85 120	99.21 90	97.45 218

miper_ehance_all_eth		90.48 229	90.42 235	90.69 274	91.62 362	76.57 328	86.83 354	96.18 218	83.38 279	94.06 205	92.66 319	82.20 268	98.04 227	89.79 179	97.02 270	97.45 218

LS3D		96.11 51	95.83 69	96.95 40	94.75 284	94.20 23	97.34 13	97.98 83	97.31 12	95.32 155	96.77 146	93.08 102	99.20 85	91.79 122	98.16 209	97.44 220

D2MVS		89.93 252	89.60 253	90.92 266	94.03 305	78.40 300	88.69 326	94.85 262	78.96 333	93.08 240	95.09 241	74.57 327	96.94 309	88.19 215	98.96 122	97.41 221

PHI-MVS		94.34 126	93.80 146	95.95 61	95.65 252	91.67 66	94.82 119	97.86 94	87.86 208	93.04 243	94.16 275	91.58 136	98.78 146	90.27 164	98.96 122	97.41 221

ITE_SJBPF				95.95 61	97.34 137	93.36 44		96.55 201	91.93 106	94.82 183	95.39 233	91.99 126	97.08 303	85.53 261	97.96 228	97.41 221

SD-MVS		95.19 92	95.73 74	93.55 167	96.62 177	88.88 109	94.67 123	98.05 72	91.26 134	97.25 60	96.40 171	95.42 30	94.36 372	92.72 99	99.19 92	97.40 224
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
test20.03		90.80 220	90.85 224	90.63 276	95.63 254	79.24 285	89.81 295	92.87 303	89.90 163	94.39 195	96.40 171	85.77 231	95.27 359	73.86 371	99.05 106	97.39 225

F-COLMAP		92.28 194	91.06 220	95.95 61	97.52 127	91.90 60	93.53 164	97.18 152	83.98 274	88.70 339	94.04 278	88.41 190	98.55 183	80.17 321	95.99 301	97.39 225

DeepPCF-MVS	90.46 6	94.20 133	93.56 158	96.14 55	95.96 232	92.96 47	89.48 304	97.46 129	85.14 258	96.23 106	95.42 229	93.19 97	98.08 225	90.37 158	98.76 149	97.38 227

mvs_anonymous		90.37 236	91.30 215	87.58 339	92.17 346	68.00 386	89.84 294	94.73 269	83.82 277	93.22 237	97.40 95	87.54 204	97.40 284	87.94 224	95.05 327	97.34 228

alignmvs		93.26 160	92.85 174	94.50 128	95.70 248	87.45 136	93.45 168	95.76 230	91.58 126	95.25 162	92.42 325	81.96 272	98.72 155	91.61 127	97.87 234	97.33 229

DeepC-MVS_fast	89.96 7	93.73 147	93.44 161	94.60 123	96.14 218	87.90 129	93.36 172	97.14 155	85.53 251	93.90 213	95.45 227	91.30 143	98.59 178	89.51 184	98.62 163	97.31 230
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
pmmvs-eth3d		91.54 209	90.73 228	93.99 145	95.76 246	87.86 131	90.83 260	93.98 286	78.23 338	94.02 208	96.22 189	82.62 265	96.83 316	86.57 246	98.33 192	97.29 231

testing3		83.66 344	82.52 349	87.08 343	95.84 238	65.84 398	89.80 296	77.17 416	88.17 202	90.84 297	88.63 374	30.95 424	98.11 223	84.05 280	97.19 264	97.28 232

MGCFI-Net		94.44 120	94.67 120	93.75 159	95.56 258	85.47 189	95.25 103	98.24 40	91.53 129	95.04 174	92.21 327	94.94 57	98.54 184	91.56 131	97.66 245	97.24 233

IterMVS		90.18 242	90.16 239	90.21 288	93.15 320	75.98 334	87.56 339	92.97 302	86.43 230	94.09 202	96.40 171	78.32 299	97.43 281	87.87 225	94.69 337	97.23 234
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
sasdasda		94.59 113	94.69 116	94.30 136	95.60 256	87.03 146	95.59 85	98.24 40	91.56 127	95.21 165	92.04 332	94.95 55	98.66 168	91.45 133	97.57 249	97.20 235

canonicalmvs		94.59 113	94.69 116	94.30 136	95.60 256	87.03 146	95.59 85	98.24 40	91.56 127	95.21 165	92.04 332	94.95 55	98.66 168	91.45 133	97.57 249	97.20 235

test_fmvs1_n		88.73 280	88.38 273	89.76 298	92.06 349	82.53 231	92.30 214	96.59 196	71.14 383	92.58 258	95.41 232	68.55 350	89.57 402	91.12 138	95.66 309	97.18 237

fmvsm_l_conf0.5_n		93.79 145	93.81 144	93.73 160	96.16 215	86.26 170	92.46 202	96.72 188	81.69 304	95.77 128	97.11 124	90.83 156	97.82 252	95.58 19	97.99 225	97.11 238

fmvsm_l_conf0.5_n_a		93.59 150	93.63 153	93.49 174	96.10 221	85.66 186	92.32 211	96.57 197	81.32 307	95.63 137	97.14 121	90.19 171	97.73 265	95.37 28	98.03 221	97.07 239

ppachtmachnet_test		88.61 282	88.64 268	88.50 323	91.76 357	70.99 373	84.59 385	92.98 301	79.30 330	92.38 267	93.53 297	79.57 287	97.45 280	86.50 250	97.17 265	97.07 239

MVS_111021_LR		93.66 148	93.28 165	94.80 110	96.25 209	90.95 73	90.21 281	95.43 247	87.91 205	93.74 217	94.40 266	92.88 109	96.38 330	90.39 156	98.28 196	97.07 239

HyFIR lowres test		87.19 312	85.51 325	92.24 215	97.12 149	80.51 256	85.03 380	96.06 221	66.11 404	91.66 284	92.98 310	70.12 346	99.14 91	75.29 362	95.23 322	97.07 239

h-mvs33		92.89 172	91.99 197	95.58 79	96.97 152	90.55 80	93.94 153	94.01 285	89.23 176	93.95 210	96.19 190	76.88 316	99.14 91	91.02 140	95.71 308	97.04 243

CANet_DTU		89.85 254	89.17 257	91.87 227	92.20 344	80.02 266	90.79 261	95.87 228	86.02 238	82.53 396	91.77 336	80.01 285	98.57 180	85.66 260	97.70 242	97.01 244

MVS_Test		92.57 186	93.29 163	90.40 282	93.53 315	75.85 335	92.52 198	96.96 168	88.73 187	92.35 269	96.70 155	90.77 157	98.37 203	92.53 103	95.49 313	96.99 245

LCM-MVSNet-Re		94.20 133	94.58 123	93.04 183	95.91 235	83.13 223	93.79 157	99.19 6	92.00 103	98.84 6	98.04 49	93.64 83	99.02 108	81.28 309	98.54 172	96.96 246

CSCG		94.69 110	94.75 112	94.52 127	97.55 126	87.87 130	95.01 114	97.57 120	92.68 84	96.20 109	93.44 298	91.92 128	98.78 146	89.11 199	99.24 85	96.92 247

Fast-Effi-MVS+-dtu		92.77 179	92.16 191	94.58 126	94.66 290	88.25 123	92.05 221	96.65 192	89.62 169	90.08 312	91.23 343	92.56 115	98.60 176	86.30 253	96.27 296	96.90 248

test_fmvsmvis_n_1920		95.08 95	95.40 88	94.13 142	96.66 172	87.75 133	93.44 169	98.49 19	85.57 250	98.27 21	97.11 124	94.11 79	97.75 262	96.26 11	98.72 152	96.89 249

114514_t		90.51 228	89.80 248	92.63 203	98.00 92	82.24 236	93.40 170	97.29 145	65.84 405	89.40 326	94.80 253	86.99 215	98.75 150	83.88 282	98.61 164	96.89 249

Effi-MVS+		92.79 177	92.74 177	92.94 189	95.10 272	83.30 217	94.00 150	97.53 124	91.36 133	89.35 327	90.65 355	94.01 80	98.66 168	87.40 233	95.30 320	96.88 251

CMPMVS	68.83 22	87.28 308	85.67 324	92.09 223	88.77 398	85.42 191	90.31 279	94.38 275	70.02 392	88.00 349	93.30 301	73.78 331	94.03 376	75.96 359	96.54 289	96.83 252
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
hse-mvs2		92.24 197	91.20 216	95.38 85	96.16 215	90.65 79	92.52 198	92.01 325	89.23 176	93.95 210	92.99 309	76.88 316	98.69 164	91.02 140	96.03 299	96.81 253

miper_enhance_ethall		88.42 285	87.87 288	90.07 291	88.67 399	75.52 338	85.10 379	95.59 239	75.68 353	92.49 260	89.45 367	78.96 291	97.88 245	87.86 226	97.02 270	96.81 253

EIA-MVS		92.35 192	92.03 195	93.30 179	95.81 242	83.97 210	92.80 188	98.17 53	87.71 212	89.79 320	87.56 382	91.17 150	99.18 87	87.97 223	97.27 261	96.77 255

MVP-Stereo		90.07 249	88.92 263	93.54 169	96.31 202	86.49 161	90.93 258	95.59 239	79.80 318	91.48 286	95.59 220	80.79 281	97.39 285	78.57 338	91.19 388	96.76 256
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
AUN-MVS		90.05 250	88.30 275	95.32 90	96.09 222	90.52 81	92.42 206	92.05 324	82.08 300	88.45 343	92.86 311	65.76 366	98.69 164	88.91 204	96.07 298	96.75 257

PAPM_NR		91.03 218	90.81 225	91.68 236	96.73 168	81.10 251	93.72 160	96.35 209	88.19 201	88.77 337	92.12 331	85.09 241	97.25 291	82.40 297	93.90 355	96.68 258

FA-MVS(test-final)		91.81 203	91.85 201	91.68 236	94.95 275	79.99 267	96.00 66	93.44 295	87.80 209	94.02 208	97.29 108	77.60 304	98.45 194	88.04 221	97.49 252	96.61 259

UnsupCasMVSNet_bld		88.50 283	88.03 286	89.90 296	95.52 260	78.88 293	87.39 343	94.02 284	79.32 329	93.06 241	94.02 280	80.72 282	94.27 373	75.16 363	93.08 372	96.54 260

TAPA-MVS	88.58 10	92.49 187	91.75 204	94.73 113	96.50 186	89.69 89	92.91 184	97.68 110	78.02 339	92.79 251	94.10 276	90.85 155	97.96 238	84.76 274	98.16 209	96.54 260
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
pmmvs5		87.87 293	87.14 301	90.07 291	93.26 319	76.97 323	88.89 319	92.18 318	73.71 368	88.36 344	93.89 286	76.86 318	96.73 319	80.32 316	96.81 280	96.51 262

thres600view7		87.66 298	87.10 304	89.36 306	96.05 225	73.17 357	92.72 189	85.31 382	91.89 108	93.29 230	90.97 347	63.42 379	98.39 196	73.23 374	96.99 275	96.51 262

thres400		87.20 311	86.52 316	89.24 310	95.77 244	72.94 361	91.89 230	86.00 372	90.84 142	92.61 256	89.80 359	63.93 376	98.28 207	71.27 386	96.54 289	96.51 262

TSAR-MVS + GP.		93.07 168	92.41 187	95.06 102	95.82 240	90.87 76	90.97 257	92.61 312	88.04 204	94.61 190	93.79 289	88.08 194	97.81 253	89.41 187	98.39 185	96.50 265

YYNet1		88.17 289	88.24 280	87.93 333	92.21 343	73.62 355	80.75 403	88.77 346	82.51 295	94.99 177	95.11 240	82.70 263	93.70 377	83.33 284	93.83 356	96.48 266

mvsmamba		90.24 241	89.43 254	92.64 200	95.52 260	82.36 234	96.64 30	92.29 316	81.77 302	92.14 276	96.28 184	70.59 344	99.10 97	84.44 278	95.22 323	96.47 267

MDA-MVSNet_test_wron		88.16 290	88.23 281	87.93 333	92.22 342	73.71 354	80.71 404	88.84 345	82.52 294	94.88 182	95.14 238	82.70 263	93.61 378	83.28 285	93.80 357	96.46 268

MVSFormer		92.18 198	92.23 190	92.04 225	94.74 285	80.06 263	97.15 15	97.37 133	88.98 182	88.83 331	92.79 314	77.02 313	99.60 10	96.41 9	96.75 283	96.46 268

jason		89.17 265	88.32 274	91.70 235	95.73 247	80.07 262	88.10 332	93.22 298	71.98 378	90.09 311	92.79 314	78.53 297	98.56 181	87.43 232	97.06 268	96.46 268
jason: jason.
CHOSEN 1792x2688		87.19 312	85.92 323	91.00 264	97.13 148	79.41 281	84.51 386	95.60 235	64.14 408	90.07 313	94.81 251	78.26 300	97.14 300	73.34 373	95.38 318	96.46 268

Anonymous20231206		88.77 278	88.29 276	90.20 289	96.31 202	78.81 296	89.56 302	93.49 294	74.26 365	92.38 267	95.58 223	82.21 267	95.43 354	72.07 380	98.75 151	96.34 272

旧先验1					96.20 212	84.17 207		94.82 264			95.57 224	89.57 181			97.89 232	96.32 273

DELS-MVS		92.05 200	92.16 191	91.72 233	94.44 294	80.13 261	87.62 336	97.25 148	87.34 219	92.22 274	93.18 306	89.54 182	98.73 154	89.67 182	98.20 207	96.30 274
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
PLC	85.34 15	90.40 232	88.92 263	94.85 108	96.53 185	90.02 85	91.58 241	96.48 204	80.16 316	86.14 366	92.18 328	85.73 232	98.25 212	76.87 350	94.61 339	96.30 274
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSMamba_PlusPlus		94.82 105	95.89 64	91.62 238	97.82 104	78.88 293	96.52 35	97.60 118	97.14 14	94.23 199	98.48 32	87.01 214	99.71 3	95.43 25	98.80 144	96.28 276

testing91		83.56 346	82.45 350	86.91 348	92.92 327	67.29 387	86.33 366	88.07 355	86.22 233	84.26 381	85.76 394	48.15 407	97.17 297	76.27 356	94.08 354	96.27 277

PAPR		87.65 299	86.77 310	90.27 285	92.85 329	77.38 315	88.56 329	96.23 214	76.82 350	84.98 375	89.75 363	86.08 229	97.16 299	72.33 379	93.35 365	96.26 278

balanced_conf03		93.45 154	94.17 137	91.28 252	95.81 242	78.40 300	96.20 60	97.48 128	88.56 194	95.29 158	97.20 117	85.56 237	99.21 82	92.52 104	98.91 127	96.24 279

our_test_3		87.55 302	87.59 292	87.44 341	91.76 357	70.48 374	83.83 392	90.55 339	79.79 319	92.06 279	92.17 329	78.63 296	95.63 347	84.77 273	94.73 335	96.22 280

Fast-Effi-MVS+		91.28 216	90.86 223	92.53 209	95.45 263	82.53 231	89.25 314	96.52 202	85.00 262	89.91 316	88.55 376	92.94 105	98.84 132	84.72 275	95.44 315	96.22 280

EPNet_dtu		85.63 326	84.37 332	89.40 305	86.30 410	74.33 349	91.64 240	88.26 350	84.84 266	72.96 415	89.85 357	71.27 342	97.69 267	76.60 352	97.62 247	96.18 282
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LF4IMVS		92.72 180	92.02 196	94.84 109	95.65 252	91.99 58	92.92 183	96.60 194	85.08 261	92.44 264	93.62 293	86.80 220	96.35 332	86.81 240	98.25 200	96.18 282

testing99		82.94 351	81.72 354	86.59 351	92.55 334	66.53 393	86.08 370	85.70 375	85.47 254	83.95 383	85.70 395	45.87 409	97.07 304	76.58 353	93.56 361	96.17 284

pmmvs4		88.95 274	87.70 291	92.70 197	94.30 297	85.60 187	87.22 345	92.16 320	74.62 362	89.75 322	94.19 273	77.97 302	96.41 328	82.71 290	96.36 293	96.09 285

MG-MVS		89.54 258	89.80 248	88.76 316	94.88 276	72.47 366	89.60 300	92.44 315	85.82 242	89.48 324	95.98 201	82.85 260	97.74 264	81.87 301	95.27 321	96.08 286

ab-mvs		92.40 190	92.62 182	91.74 232	97.02 150	81.65 242	95.84 76	95.50 244	86.95 226	92.95 247	97.56 81	90.70 162	97.50 276	79.63 328	97.43 256	96.06 287

baseline2		83.38 347	81.54 357	88.90 313	91.38 365	72.84 363	88.78 323	81.22 402	78.97 332	79.82 408	87.56 382	61.73 386	97.80 254	74.30 368	90.05 394	96.05 288

N_pmnet		88.90 275	87.25 298	93.83 157	94.40 296	93.81 39	84.73 382	87.09 363	79.36 328	93.26 233	92.43 324	79.29 290	91.68 389	77.50 346	97.22 263	96.00 289

WB-MVSnew		84.20 340	83.89 339	85.16 369	91.62 362	66.15 397	88.44 331	81.00 403	76.23 352	87.98 350	87.77 381	84.98 242	93.35 381	62.85 408	94.10 353	95.98 290

test_vis1_n_1920		89.45 260	89.85 247	88.28 327	93.59 314	76.71 326	90.67 266	97.78 105	79.67 322	90.30 309	96.11 195	76.62 319	92.17 387	90.31 161	93.57 360	95.96 291

GA-MVS		87.70 296	86.82 308	90.31 283	93.27 318	77.22 318	84.72 384	92.79 306	85.11 260	89.82 318	90.07 356	66.80 359	97.76 261	84.56 276	94.27 346	95.96 291

test_yl		90.11 246	89.73 251	91.26 253	94.09 302	79.82 271	90.44 272	92.65 309	90.90 140	93.19 238	93.30 301	73.90 329	98.03 228	82.23 298	96.87 277	95.93 293

DCV-MVSNet		90.11 246	89.73 251	91.26 253	94.09 302	79.82 271	90.44 272	92.65 309	90.90 140	93.19 238	93.30 301	73.90 329	98.03 228	82.23 298	96.87 277	95.93 293

PM-MVS		93.33 157	92.67 181	95.33 88	96.58 178	94.06 25	92.26 216	92.18 318	85.92 240	96.22 107	96.61 160	85.64 235	95.99 342	90.35 159	98.23 202	95.93 293

ET-MVSNet_ETH3D		86.15 323	84.27 334	91.79 230	93.04 323	81.28 247	87.17 347	86.14 370	79.57 323	83.65 385	88.66 373	57.10 394	98.18 218	87.74 227	95.40 316	95.90 296

TAMVS		90.16 243	89.05 259	93.49 174	96.49 187	86.37 166	90.34 278	92.55 313	80.84 313	92.99 244	94.57 263	81.94 273	98.20 215	73.51 372	98.21 205	95.90 296

baseline1		87.62 300	87.31 295	88.54 321	94.71 288	74.27 350	93.10 179	88.20 352	86.20 234	92.18 275	93.04 307	73.21 332	95.52 349	79.32 332	85.82 404	95.83 298

WTY-MVS		86.93 318	86.50 318	88.24 328	94.96 274	74.64 343	87.19 346	92.07 323	78.29 337	88.32 345	91.59 340	78.06 301	94.27 373	74.88 364	93.15 370	95.80 299

PVSNet_Blended_VisFu		91.63 207	91.20 216	92.94 189	97.73 112	83.95 211	92.14 219	97.46 129	78.85 335	92.35 269	94.98 245	84.16 247	99.08 98	86.36 252	96.77 282	95.79 300

lupinMVS		88.34 287	87.31 295	91.45 244	94.74 285	80.06 263	87.23 344	92.27 317	71.10 384	88.83 331	91.15 344	77.02 313	98.53 185	86.67 244	96.75 283	95.76 301

DP-MVS Recon		92.31 193	91.88 200	93.60 165	97.18 145	86.87 151	91.10 254	97.37 133	84.92 264	92.08 278	94.08 277	88.59 187	98.20 215	83.50 283	98.14 211	95.73 302

FE-MVS		89.06 268	88.29 276	91.36 247	94.78 282	79.57 278	96.77 27	90.99 333	84.87 265	92.96 246	96.29 182	60.69 390	98.80 142	80.18 320	97.11 267	95.71 303

CDS-MVSNet		89.55 257	88.22 282	93.53 170	95.37 267	86.49 161	89.26 312	93.59 290	79.76 320	91.15 293	92.31 326	77.12 311	98.38 199	77.51 345	97.92 231	95.71 303
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
原ACMM1				92.87 192	96.91 157	84.22 205		97.01 164	76.84 349	89.64 323	94.46 265	88.00 197	98.70 162	81.53 307	98.01 224	95.70 305

thisisatest0515		84.72 335	82.99 346	89.90 296	92.96 326	75.33 340	84.36 387	83.42 393	77.37 343	88.27 346	86.65 387	53.94 400	98.72 155	82.56 293	97.40 258	95.67 306

ETV-MVS		92.99 169	92.74 177	93.72 161	95.86 237	86.30 169	92.33 210	97.84 97	91.70 124	92.81 249	86.17 392	92.22 121	99.19 86	88.03 222	97.73 239	95.66 307

TinyColmap		92.00 201	92.76 176	89.71 300	95.62 255	77.02 319	90.72 264	96.17 219	87.70 213	95.26 160	96.29 182	92.54 116	96.45 327	81.77 302	98.77 148	95.66 307

PCF-MVS	84.52 17	89.12 266	87.71 290	93.34 177	96.06 224	85.84 181	86.58 363	97.31 142	68.46 398	93.61 219	93.89 286	87.51 205	98.52 186	67.85 397	98.11 213	95.66 307
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
USDC		89.02 269	89.08 258	88.84 315	95.07 273	74.50 347	88.97 317	96.39 207	73.21 371	93.27 232	96.28 184	82.16 269	96.39 329	77.55 344	98.80 144	95.62 310

ETVMVS		79.85 376	77.94 383	85.59 362	92.97 325	66.20 396	86.13 369	80.99 404	81.41 305	83.52 388	83.89 403	41.81 420	94.98 365	56.47 413	94.25 347	95.61 311

OpenMVS	89.45 8	92.27 196	92.13 194	92.68 199	94.53 293	84.10 208	95.70 80	97.03 163	82.44 296	91.14 294	96.42 169	88.47 189	98.38 199	85.95 256	97.47 254	95.55 312

sss		87.23 309	86.82 308	88.46 325	93.96 306	77.94 305	86.84 353	92.78 307	77.59 341	87.61 357	91.83 335	78.75 293	91.92 388	77.84 341	94.20 348	95.52 313

test_cas_vis1_n_1920		88.25 288	88.27 278	88.20 329	92.19 345	78.92 291	89.45 305	95.44 245	75.29 360	93.23 236	95.65 219	71.58 340	90.23 398	88.05 220	93.55 362	95.44 314

ADS-MVSNet2		84.01 341	82.20 353	89.41 304	89.04 395	76.37 331	87.57 337	90.98 334	72.71 376	84.46 378	92.45 321	68.08 352	96.48 325	70.58 391	83.97 406	95.38 315

ADS-MVSNet		82.25 355	81.55 356	84.34 376	89.04 395	65.30 399	87.57 337	85.13 386	72.71 376	84.46 378	92.45 321	68.08 352	92.33 386	70.58 391	83.97 406	95.38 315

testing222		80.54 371	78.53 379	86.58 352	92.54 336	68.60 384	86.24 367	82.72 396	83.78 278	82.68 395	84.24 402	39.25 422	95.94 343	60.25 409	95.09 326	95.20 317

tt0805		95.42 80	95.93 62	93.86 155	98.75 31	88.47 120	97.68 9	94.29 277	96.48 24	95.38 150	93.63 292	94.89 59	97.94 240	95.38 27	96.92 276	95.17 318

tpm		84.38 338	84.08 335	85.30 367	90.47 379	63.43 407	89.34 309	85.63 377	77.24 346	87.62 356	95.03 244	61.00 389	97.30 288	79.26 333	91.09 390	95.16 319

1112_ss		88.42 285	87.41 294	91.45 244	96.69 170	80.99 252	89.72 298	96.72 188	73.37 369	87.00 362	90.69 353	77.38 308	98.20 215	81.38 308	93.72 358	95.15 320

testing11		81.98 360	80.52 367	86.38 357	92.69 331	67.13 388	85.79 373	84.80 387	82.16 299	81.19 405	85.41 397	45.24 410	96.88 314	74.14 369	93.24 367	95.14 321

UWE-MVS		80.29 373	79.10 374	83.87 380	91.97 353	59.56 414	86.50 365	77.43 415	75.40 357	87.79 354	88.10 379	44.08 414	96.90 313	64.23 404	96.36 293	95.14 321

BH-RMVSNet		90.47 230	90.44 234	90.56 278	95.21 271	78.65 299	89.15 315	93.94 287	88.21 200	92.74 253	94.22 272	86.38 225	97.88 245	78.67 337	95.39 317	95.14 321

UBG		80.28 374	78.94 377	84.31 377	92.86 328	61.77 409	83.87 391	83.31 395	77.33 344	82.78 394	83.72 404	47.60 408	96.06 339	65.47 403	93.48 363	95.11 324

Test_1112_low_res		87.50 304	86.58 312	90.25 286	96.80 167	77.75 310	87.53 341	96.25 212	69.73 394	86.47 364	93.61 294	75.67 323	97.88 245	79.95 323	93.20 368	95.11 324

MIMVSNet		87.13 314	86.54 315	88.89 314	96.05 225	76.11 332	94.39 135	88.51 348	81.37 306	88.27 346	96.75 150	72.38 336	95.52 349	65.71 402	95.47 314	95.03 326

Gipuma		95.31 87	95.80 72	93.81 158	97.99 95	90.91 74	96.42 44	97.95 88	96.69 19	91.78 282	98.85 14	91.77 132	95.49 351	91.72 124	99.08 102	95.02 327
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MSLP-MVS++		93.25 162	93.88 143	91.37 246	96.34 199	82.81 229	93.11 178	97.74 107	89.37 174	94.08 203	95.29 235	90.40 168	96.35 332	90.35 159	98.25 200	94.96 328

test_vis1_n		89.01 271	89.01 261	89.03 311	92.57 333	82.46 233	92.62 195	96.06 221	73.02 373	90.40 306	95.77 214	74.86 326	89.68 400	90.78 146	94.98 328	94.95 329

MSDG		90.82 219	90.67 229	91.26 253	94.16 299	83.08 224	86.63 360	96.19 217	90.60 151	91.94 280	91.89 334	89.16 185	95.75 346	80.96 314	94.51 340	94.95 329

test_fmvs1		87.59 301	87.27 297	88.54 321	88.32 400	81.26 248	90.43 275	95.72 232	70.55 389	91.70 283	94.63 259	68.13 351	89.42 403	90.59 150	95.34 319	94.94 331

Syy-MVS		84.81 333	84.93 327	84.42 375	91.71 359	63.36 408	85.89 371	81.49 400	81.03 308	85.13 372	81.64 409	77.44 306	95.00 362	85.94 257	94.12 351	94.91 332

myMVS_eth3d		79.62 377	78.26 380	83.72 381	91.71 359	61.25 412	85.89 371	81.49 400	81.03 308	85.13 372	81.64 409	32.12 423	95.00 362	71.17 389	94.12 351	94.91 332

无先验							89.94 290	95.75 231	70.81 387				98.59 178	81.17 312		94.81 334

mvsany_test3		89.11 267	88.21 283	91.83 228	91.30 367	90.25 83	88.09 333	78.76 410	76.37 351	96.43 93	98.39 36	83.79 250	90.43 397	86.57 246	94.20 348	94.80 335

thres100view900		87.35 307	86.89 307	88.72 317	96.14 218	73.09 359	93.00 181	85.31 382	92.13 101	93.26 233	90.96 348	63.42 379	98.28 207	71.27 386	96.54 289	94.79 336

tfpn200view9		87.05 316	86.52 316	88.67 318	95.77 244	72.94 361	91.89 230	86.00 372	90.84 142	92.61 256	89.80 359	63.93 376	98.28 207	71.27 386	96.54 289	94.79 336

GSMVS																94.75 338

sam_mvs1												66.64 362				94.75 338

SCA		87.43 305	87.21 299	88.10 331	92.01 351	71.98 368	89.43 306	88.11 354	82.26 298	88.71 338	92.83 312	78.65 294	97.59 272	79.61 329	93.30 366	94.75 338

MS-PatchMatch		88.05 291	87.75 289	88.95 312	93.28 317	77.93 306	87.88 335	92.49 314	75.42 356	92.57 259	93.59 295	80.44 283	94.24 375	81.28 309	92.75 375	94.69 341

PatchmatchNet		85.22 329	84.64 329	86.98 345	89.51 392	69.83 381	90.52 270	87.34 362	78.87 334	87.22 361	92.74 316	66.91 358	96.53 322	81.77 302	86.88 402	94.58 342
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EU-MVSNet		87.39 306	86.71 311	89.44 303	93.40 316	76.11 332	94.93 117	90.00 341	57.17 414	95.71 135	97.37 97	64.77 373	97.68 268	92.67 100	94.37 343	94.52 343

PVSNet	76.22 20	82.89 352	82.37 351	84.48 374	93.96 306	64.38 405	78.60 406	88.61 347	71.50 381	84.43 380	86.36 391	74.27 328	94.60 367	69.87 393	93.69 359	94.46 344

PVSNet_Blended		88.74 279	88.16 285	90.46 281	94.81 280	78.80 297	86.64 359	96.93 170	74.67 361	88.68 340	89.18 371	86.27 227	98.15 221	80.27 317	96.00 300	94.44 345

CNLPA		91.72 205	91.20 216	93.26 180	96.17 214	91.02 71	91.14 252	95.55 242	90.16 160	90.87 296	93.56 296	86.31 226	94.40 371	79.92 327	97.12 266	94.37 346

cascas		87.02 317	86.28 320	89.25 309	91.56 364	76.45 329	84.33 388	96.78 183	71.01 385	86.89 363	85.91 393	81.35 276	96.94 309	83.09 287	95.60 310	94.35 347

DPM-MVS		89.35 262	88.40 272	92.18 220	96.13 220	84.20 206	86.96 350	96.15 220	75.40 357	87.36 359	91.55 341	83.30 253	98.01 232	82.17 300	96.62 287	94.32 348

MAR-MVS		90.32 239	88.87 266	94.66 119	94.82 279	91.85 61	94.22 142	94.75 268	80.91 310	87.52 358	88.07 380	86.63 223	97.87 248	76.67 351	96.21 297	94.25 349
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
CR-MVSNet		87.89 292	87.12 303	90.22 287	91.01 370	78.93 289	92.52 198	92.81 304	73.08 372	89.10 328	96.93 137	67.11 356	97.64 271	88.80 206	92.70 376	94.08 350

RPMNet		90.31 240	90.14 242	90.81 272	91.01 370	78.93 289	92.52 198	98.12 59	91.91 107	89.10 328	96.89 140	68.84 349	99.41 42	90.17 169	92.70 376	94.08 350

MDTV_nov1_ep13_2view						42.48 424	88.45 330		67.22 401	83.56 387		66.80 359		72.86 377		94.06 352

test-LLR		83.58 345	83.17 344	84.79 372	89.68 388	66.86 391	83.08 395	84.52 388	83.07 287	82.85 392	84.78 400	62.86 382	93.49 379	82.85 288	94.86 331	94.03 353

test-mter		81.21 365	80.01 372	84.79 372	89.68 388	66.86 391	83.08 395	84.52 388	73.85 367	82.85 392	84.78 400	43.66 415	93.49 379	82.85 288	94.86 331	94.03 353

新几何1				93.17 182	97.16 146	87.29 138		94.43 274	67.95 399	91.29 289	94.94 247	86.97 216	98.23 213	81.06 313	97.75 238	93.98 355

test222					96.95 153	85.27 193	88.83 322	93.61 289	65.09 407	90.74 299	94.85 250	84.62 245			97.36 259	93.91 356

PMMVS2		81.31 363	83.44 342	74.92 397	90.52 377	46.49 423	69.19 413	85.23 385	84.30 273	87.95 351	94.71 257	76.95 315	84.36 414	64.07 405	98.09 216	93.89 357

Patchmatch-test		86.10 324	86.01 321	86.38 357	90.63 375	74.22 352	89.57 301	86.69 366	85.73 245	89.81 319	92.83 312	65.24 371	91.04 392	77.82 343	95.78 307	93.88 358

Patchmatch-RL test		88.81 277	88.52 269	89.69 301	95.33 269	79.94 268	86.22 368	92.71 308	78.46 336	95.80 127	94.18 274	66.25 364	95.33 357	89.22 196	98.53 173	93.78 359

test0.0.03 1		82.48 354	81.47 358	85.48 365	89.70 387	73.57 356	84.73 382	81.64 399	83.07 287	88.13 348	86.61 388	62.86 382	89.10 405	66.24 401	90.29 393	93.77 360

OpenMVS_ROB	85.12 16	89.52 259	89.05 259	90.92 266	94.58 292	81.21 250	91.10 254	93.41 296	77.03 347	93.41 224	93.99 282	83.23 254	97.80 254	79.93 325	94.80 334	93.74 361

testdata				91.03 261	96.87 160	82.01 237		94.28 278	71.55 380	92.46 262	95.42 229	85.65 234	97.38 287	82.64 291	97.27 261	93.70 362

test_vis1_rt		85.58 327	84.58 330	88.60 320	87.97 401	86.76 153	85.45 377	93.59 290	66.43 402	87.64 355	89.20 370	79.33 289	85.38 412	81.59 305	89.98 395	93.66 363

IB-MVS	77.21 19	83.11 348	81.05 360	89.29 307	91.15 368	75.85 335	85.66 375	86.00 372	79.70 321	82.02 400	86.61 388	48.26 405	98.39 196	77.84 341	92.22 381	93.63 364
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
xiu_mvs_v1_base_debu		91.47 211	91.52 207	91.33 248	95.69 249	81.56 243	89.92 291	96.05 223	83.22 283	91.26 290	90.74 350	91.55 137	98.82 134	89.29 191	95.91 302	93.62 365

xiu_mvs_v1_base		91.47 211	91.52 207	91.33 248	95.69 249	81.56 243	89.92 291	96.05 223	83.22 283	91.26 290	90.74 350	91.55 137	98.82 134	89.29 191	95.91 302	93.62 365

xiu_mvs_v1_base_debi		91.47 211	91.52 207	91.33 248	95.69 249	81.56 243	89.92 291	96.05 223	83.22 283	91.26 290	90.74 350	91.55 137	98.82 134	89.29 191	95.91 302	93.62 365

tpmrst		82.85 353	82.93 347	82.64 385	87.65 402	58.99 416	90.14 284	87.90 357	75.54 355	83.93 384	91.63 339	66.79 361	95.36 355	81.21 311	81.54 412	93.57 368

PatchT		87.51 303	88.17 284	85.55 364	90.64 374	66.91 390	92.02 223	86.09 371	92.20 99	89.05 330	97.16 119	64.15 375	96.37 331	89.21 197	92.98 374	93.37 369

CostFormer		83.09 349	82.21 352	85.73 361	89.27 394	67.01 389	90.35 277	86.47 368	70.42 390	83.52 388	93.23 304	61.18 387	96.85 315	77.21 348	88.26 400	93.34 370

thres200		85.85 325	85.18 326	87.88 336	94.44 294	72.52 365	89.08 316	86.21 369	88.57 193	91.44 287	88.40 377	64.22 374	98.00 234	68.35 395	95.88 305	93.12 371

KD-MVS_2432*1600		82.17 357	80.75 364	86.42 355	82.04 419	70.09 377	81.75 400	90.80 336	82.56 292	90.37 307	89.30 368	42.90 417	96.11 337	74.47 366	92.55 378	93.06 372

miper_refine_blended		82.17 357	80.75 364	86.42 355	82.04 419	70.09 377	81.75 400	90.80 336	82.56 292	90.37 307	89.30 368	42.90 417	96.11 337	74.47 366	92.55 378	93.06 372

HY-MVS	82.50 18	86.81 320	85.93 322	89.47 302	93.63 313	77.93 306	94.02 149	91.58 330	75.68 353	83.64 386	93.64 291	77.40 307	97.42 282	71.70 383	92.07 383	93.05 374

EPMVS		81.17 366	80.37 368	83.58 382	85.58 413	65.08 402	90.31 279	71.34 418	77.31 345	85.80 368	91.30 342	59.38 391	92.70 385	79.99 322	82.34 411	92.96 375

tpmvs		84.22 339	83.97 337	84.94 370	87.09 407	65.18 400	91.21 250	88.35 349	82.87 290	85.21 370	90.96 348	65.24 371	96.75 318	79.60 331	85.25 405	92.90 376

MonoMVSNet		88.46 284	89.28 255	85.98 360	90.52 377	70.07 379	95.31 101	94.81 266	88.38 197	93.47 223	96.13 194	73.21 332	95.07 361	82.61 292	89.12 396	92.81 377

BH-untuned		90.68 224	90.90 221	90.05 294	95.98 231	79.57 278	90.04 287	94.94 261	87.91 205	94.07 204	93.00 308	87.76 201	97.78 258	79.19 334	95.17 324	92.80 378

AdaColmap		91.63 207	91.36 213	92.47 211	95.56 258	86.36 167	92.24 218	96.27 211	88.88 186	89.90 317	92.69 317	91.65 135	98.32 205	77.38 347	97.64 246	92.72 379

CVMVSNet		85.16 330	84.72 328	86.48 353	92.12 347	70.19 375	92.32 211	88.17 353	56.15 415	90.64 302	95.85 205	67.97 354	96.69 320	88.78 207	90.52 392	92.56 380

tpm2		81.46 362	80.35 369	84.80 371	89.90 385	65.14 401	90.44 272	85.36 381	65.82 406	82.05 399	92.44 323	57.94 393	96.69 320	70.71 390	88.49 399	92.56 380

PAPM		81.91 361	80.11 371	87.31 342	93.87 309	72.32 367	84.02 390	93.22 298	69.47 395	76.13 413	89.84 358	72.15 337	97.23 292	53.27 415	89.02 397	92.37 382

TESTMET0.1,1		79.09 379	78.04 381	82.25 386	87.52 404	64.03 406	83.08 395	80.62 406	70.28 391	80.16 407	83.22 406	44.13 413	90.56 395	79.95 323	93.36 364	92.15 383

DSMNet-mixed		82.21 356	81.56 355	84.16 378	89.57 391	70.00 380	90.65 267	77.66 414	54.99 416	83.30 390	97.57 80	77.89 303	90.50 396	66.86 400	95.54 312	91.97 384

xiu_mvs_v2_base		89.00 272	89.19 256	88.46 325	94.86 278	74.63 344	86.97 349	95.60 235	80.88 311	87.83 352	88.62 375	91.04 152	98.81 139	82.51 295	94.38 342	91.93 385

PS-MVSNAJ		88.86 276	88.99 262	88.48 324	94.88 276	74.71 342	86.69 358	95.60 235	80.88 311	87.83 352	87.37 385	90.77 157	98.82 134	82.52 294	94.37 343	91.93 385

tpm cat1		80.61 370	79.46 373	84.07 379	88.78 397	65.06 403	89.26 312	88.23 351	62.27 411	81.90 401	89.66 365	62.70 384	95.29 358	71.72 382	80.60 413	91.86 387

dp		79.28 378	78.62 378	81.24 390	85.97 412	56.45 417	86.91 351	85.26 384	72.97 374	81.45 404	89.17 372	56.01 398	95.45 353	73.19 375	76.68 414	91.82 388

dmvs_re		84.69 336	83.94 338	86.95 347	92.24 341	82.93 227	89.51 303	87.37 361	84.38 272	85.37 369	85.08 399	72.44 335	86.59 409	68.05 396	91.03 391	91.33 389

JIA-IIPM		85.08 331	83.04 345	91.19 258	87.56 403	86.14 173	89.40 308	84.44 390	88.98 182	82.20 397	97.95 56	56.82 396	96.15 335	76.55 354	83.45 408	91.30 390

TR-MVS		87.70 296	87.17 300	89.27 308	94.11 301	79.26 284	88.69 326	91.86 326	81.94 301	90.69 301	89.79 361	82.82 261	97.42 282	72.65 378	91.98 384	91.14 391

1314		86.46 322	86.33 319	86.87 349	91.65 361	74.54 345	91.94 227	94.10 281	74.28 364	84.78 377	87.33 386	83.03 257	95.00 362	78.72 336	91.16 389	91.06 392

new_pmnet		81.22 364	81.01 362	81.86 387	90.92 372	70.15 376	84.03 389	80.25 408	70.83 386	85.97 367	89.78 362	67.93 355	84.65 413	67.44 398	91.90 385	90.78 393

PatchMatch-RL		89.18 264	88.02 287	92.64 200	95.90 236	92.87 49	88.67 328	91.06 332	80.34 314	90.03 314	91.67 338	83.34 252	94.42 370	76.35 355	94.84 333	90.64 394

API-MVS		91.52 210	91.61 205	91.26 253	94.16 299	86.26 170	94.66 124	94.82 264	91.17 137	92.13 277	91.08 346	90.03 178	97.06 305	79.09 335	97.35 260	90.45 395

BH-w/o		87.21 310	87.02 305	87.79 338	94.77 283	77.27 317	87.90 334	93.21 300	81.74 303	89.99 315	88.39 378	83.47 251	96.93 311	71.29 385	92.43 380	89.15 396

PMVS	87.21 14	94.97 98	95.33 91	93.91 152	98.97 17	97.16 3	95.54 92	95.85 229	96.47 25	93.40 227	97.46 93	95.31 37	95.47 352	86.18 255	98.78 147	89.11 397
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
gg-mvs-nofinetune		82.10 359	81.02 361	85.34 366	87.46 405	71.04 371	94.74 121	67.56 419	96.44 26	79.43 409	98.99 8	45.24 410	96.15 335	67.18 399	92.17 382	88.85 398

CHOSEN 280x420		80.04 375	77.97 382	86.23 359	90.13 383	74.53 346	72.87 411	89.59 343	66.38 403	76.29 412	85.32 398	56.96 395	95.36 355	69.49 394	94.72 336	88.79 399

pmmvs3		80.83 368	78.96 376	86.45 354	87.23 406	77.48 314	84.87 381	82.31 397	63.83 409	85.03 374	89.50 366	49.66 404	93.10 382	73.12 376	95.10 325	88.78 400

test_f		86.65 321	87.13 302	85.19 368	90.28 382	86.11 174	86.52 364	91.66 328	69.76 393	95.73 134	97.21 116	69.51 348	81.28 415	89.15 198	94.40 341	88.17 401

PMMVS		83.00 350	81.11 359	88.66 319	83.81 418	86.44 164	82.24 399	85.65 376	61.75 412	82.07 398	85.64 396	79.75 286	91.59 390	75.99 358	93.09 371	87.94 402

mvsany_test1		83.91 343	82.93 347	86.84 350	86.18 411	85.93 178	81.11 402	75.03 417	70.80 388	88.57 342	94.63 259	83.08 256	87.38 407	80.39 315	86.57 403	87.21 403

dmvs_testset		78.23 381	78.99 375	75.94 396	91.99 352	55.34 419	88.86 320	78.70 411	82.69 291	81.64 403	79.46 411	75.93 322	85.74 411	48.78 417	82.85 410	86.76 404

MVS		84.98 332	84.30 333	87.01 344	91.03 369	77.69 312	91.94 227	94.16 280	59.36 413	84.23 382	87.50 384	85.66 233	96.80 317	71.79 381	93.05 373	86.54 405

MVE	59.87 23	73.86 383	72.65 386	77.47 395	87.00 409	74.35 348	61.37 415	60.93 421	67.27 400	69.69 416	86.49 390	81.24 280	72.33 418	56.45 414	83.45 408	85.74 406
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GG-mvs-BLEND				83.24 384	85.06 415	71.03 372	94.99 116	65.55 420		74.09 414	75.51 414	44.57 412	94.46 369	59.57 411	87.54 401	84.24 407

FPMVS		84.50 337	83.28 343	88.16 330	96.32 201	94.49 20	85.76 374	85.47 380	83.09 286	85.20 371	94.26 270	63.79 378	86.58 410	63.72 406	91.88 386	83.40 408

E-PMN		80.72 369	80.86 363	80.29 392	85.11 414	68.77 383	72.96 410	81.97 398	87.76 211	83.25 391	83.01 407	62.22 385	89.17 404	77.15 349	94.31 345	82.93 409

EMVS		80.35 372	80.28 370	80.54 391	84.73 416	69.07 382	72.54 412	80.73 405	87.80 209	81.66 402	81.73 408	62.89 381	89.84 399	75.79 360	94.65 338	82.71 410

PVSNet_0	70.34 21	74.58 382	72.96 385	79.47 393	90.63 375	66.24 395	73.26 409	83.40 394	63.67 410	78.02 410	78.35 413	72.53 334	89.59 401	56.68 412	60.05 417	82.57 411

test_method		50.44 385	48.94 388	54.93 399	39.68 425	12.38 428	28.59 416	90.09 340	6.82 419	41.10 421	78.41 412	54.41 399	70.69 419	50.12 416	51.26 418	81.72 412

MVS-HIRNet		78.83 380	80.60 366	73.51 398	93.07 321	47.37 422	87.10 348	78.00 413	68.94 396	77.53 411	97.26 109	71.45 341	94.62 366	63.28 407	88.74 398	78.55 413

wuyk23d		87.83 294	90.79 226	78.96 394	90.46 380	88.63 112	92.72 189	90.67 338	91.65 125	98.68 12	97.64 76	96.06 15	77.53 416	59.84 410	99.41 54	70.73 414

dongtai		53.72 384	53.79 387	53.51 401	79.69 421	36.70 425	77.18 407	32.53 427	71.69 379	68.63 417	60.79 416	26.65 425	73.11 417	30.67 420	36.29 419	50.73 415

DeepMVS_CX				53.83 400	70.38 423	64.56 404		48.52 424	33.01 418	65.50 418	74.21 415	56.19 397	46.64 421	38.45 419	70.07 415	50.30 416

kuosan		43.63 386	44.25 390	41.78 402	66.04 424	34.37 426	75.56 408	32.62 426	53.25 417	50.46 420	51.18 417	25.28 426	49.13 420	13.44 421	30.41 420	41.84 417

tmp_tt		37.97 387	44.33 389	18.88 403	11.80 426	21.54 427	63.51 414	45.66 425	4.23 420	51.34 419	50.48 418	59.08 392	22.11 422	44.50 418	68.35 416	13.00 418

test123		9.49 389	12.01 392	1.91 404	2.87 427	1.30 429	82.38 398	1.34 429	1.36 422	2.84 423	6.56 421	2.45 427	0.97 423	2.73 422	5.56 421	3.47 419

testmvs		9.02 390	11.42 393	1.81 405	2.77 428	1.13 430	79.44 405	1.90 428	1.18 423	2.65 424	6.80 420	1.95 428	0.87 424	2.62 423	3.45 422	3.44 420

mmdepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

monomultidepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

test_blank		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet_test		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

DCPMVS		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

cdsmvs_eth3d_5k		23.35 388	31.13 391	0.00 406	0.00 429	0.00 431	0.00 417	95.58 241	0.00 424	0.00 425	91.15 344	93.43 89	0.00 425	0.00 424	0.00 423	0.00 421

pcd_1.5k_mvsjas		7.56 391	10.09 394	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	90.77 157	0.00 425	0.00 424	0.00 423	0.00 421

sosnet-low-res		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

sosnet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uncertanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

Regformer		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

ab-mvs-re		7.56 391	10.08 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	90.69 353	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

WAC-MVS						61.25 412								74.55 365

FOURS1					99.21 3	94.68 16	98.45 4	98.81 11	97.73 7	98.27 21

test_one_0601					98.26 71	87.14 143		98.18 49	94.25 55	96.99 71	97.36 100	95.13 45

eth-test2					0.00 429

eth-test					0.00 429

ZD-MVS					97.23 141	90.32 82		97.54 122	84.40 271	94.78 185	95.79 210	92.76 112	99.39 52	88.72 209	98.40 182

test_241102_ONE					98.51 49	86.97 148		98.10 62	91.85 110	97.63 38	97.03 130	96.48 10	98.95 118

9.14			94.81 109		97.49 129		94.11 147	98.37 26	87.56 217	95.38 150	96.03 199	94.66 64	99.08 98	90.70 148	98.97 120

save fliter					97.46 132	88.05 127	92.04 222	97.08 160	87.63 215

test0726					98.51 49	86.69 156	95.34 97	98.18 49	91.85 110	97.63 38	97.37 97	95.58 24

test_part2					98.21 76	89.41 96				96.72 83

sam_mvs												66.41 363

MTGPA								97.62 114

test_post1							90.21 281				5.85 423	65.36 369	96.00 341	79.61 329

test_post											6.07 422	65.74 367	95.84 345

patchmatchnet-post											91.71 337	66.22 365	97.59 272

MTMP							94.82 119	54.62 423

gm-plane-assit					87.08 408	59.33 415			71.22 382		83.58 405		97.20 294	73.95 370

TEST9					96.45 190	89.46 93	90.60 268	96.92 172	79.09 331	90.49 303	94.39 267	91.31 142	98.88 125

test_8					96.37 193	89.14 103	90.51 271	96.89 175	79.37 326	90.42 305	94.36 269	91.20 147	98.82 134

agg_prior					96.20 212	88.89 108		96.88 176		90.21 310			98.78 146

test_prior4						89.91 86	90.74 263

test_prior2							90.21 281		89.33 175	90.77 298	94.81 251	90.41 167		88.21 213	98.55 170

旧先验2							90.00 289		68.65 397	92.71 254			96.52 323	85.15 265

新几何2							90.02 288

原ACMM2							89.34 309

testdata2													98.03 228	80.24 319

segment_acmp												92.14 124

testdata1							88.96 318		88.44 196

plane_prior7					97.71 114	88.68 111

plane_prior6					97.21 144	88.23 124						86.93 217

plane_prior4											95.59 220

plane_prior3						88.43 122			90.35 158	93.31 228

plane_prior2							94.56 130		91.74 121

plane_prior1					97.38 134

plane_prior						88.12 125	93.01 180		88.98 182						98.06 218

n2								0.00 430

nn								0.00 430

door-mid								92.13 322

test11								96.65 192

door								91.26 331

HQP5-MVS						84.89 196

HQP-NCC					96.36 195		91.37 245		87.16 221	88.81 333

ACMP_Plane					96.36 195		91.37 245		87.16 221	88.81 333

BP-MVS														86.55 248

HQP3-MVS								97.31 142							97.73 239

HQP2-MVS												84.76 243

NP-MVS					96.82 165	87.10 144					93.40 299

MDTV_nov1_ep13			83.88 340		89.42 393	61.52 410	88.74 325	87.41 360	73.99 366	84.96 376	94.01 281	65.25 370	95.53 348	78.02 339	93.16 369

ACMMP++_ref															98.82 141

ACMMP++															99.25 83

Test By Simon												90.61 163

High-resolution multi-view benchmark