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_vis3_rt		99.89 3	99.90 3	99.87 15	99.98 3	99.75 62	99.70 34	100.00 1	99.73 57	100.00 1	99.89 31	99.79 8	99.88 172	99.98 1	100.00 1	99.98 1

test_fmvs3		99.83 12	99.93 2	99.53 158	99.96 5	98.62 256	99.67 48	100.00 1	99.95 4	100.00 1	99.95 13	99.85 3	99.99 6	99.98 1	99.99 13	99.98 1

test_f		99.75 18	99.88 6	99.37 204	99.96 5	98.21 279	99.51 86	100.00 1	99.94 8	100.00 1	99.93 17	99.58 24	99.94 64	99.97 4	99.99 13	99.97 3

test_fmvs2		99.72 22	99.85 11	99.34 211	99.91 26	98.08 292	99.48 92	100.00 1	99.90 13	99.99 7	99.91 24	99.50 31	99.98 10	99.98 1	99.99 13	99.96 4

test_vis1_n		99.68 31	99.79 17	99.36 208	99.94 16	98.18 282	99.52 83	100.00 1	99.86 28	100.00 1	99.88 36	98.99 87	99.96 41	99.97 4	99.96 56	99.95 5

tmp_tt		95.75 336	95.42 334	96.76 345	89.90 381	94.42 356	98.86 230	97.87 354	78.01 372	99.30 245	99.69 137	97.70 225	95.89 376	99.29 83	98.14 355	99.95 5

mvsany_test3		99.85 8	99.88 6	99.75 60	99.95 13	99.37 163	99.53 82	99.98 8	99.77 55	99.99 7	99.95 13	99.85 3	99.94 64	99.95 7	99.98 30	99.94 7

PS-MVSNAJss		99.84 10	99.82 13	99.89 8	99.96 5	99.77 50	99.68 44	99.85 39	99.95 4	99.98 10	99.92 21	99.28 51	99.98 10	99.75 23	100.00 1	99.94 7

test_fmvs1_n		99.68 31	99.81 14	99.28 226	99.95 13	97.93 301	99.49 91	100.00 1	99.82 41	99.99 7	99.89 31	99.21 60	99.98 10	99.97 4	99.98 30	99.93 9

mvs_tets		99.90 2	99.90 3	99.90 5	99.96 5	99.79 44	99.72 29	99.88 30	99.92 11	99.98 10	99.93 17	99.94 1	99.98 10	99.77 22	100.00 1	99.92 10

UA-Net		99.78 16	99.76 21	99.86 18	99.72 124	99.71 76	99.91 3	99.95 17	99.96 2	99.71 117	99.91 24	99.15 66	99.97 22	99.50 50	100.00 1	99.90 11

RRT_MVS		99.67 37	99.59 50	99.91 2	99.94 16	99.88 12	99.78 11	99.27 286	99.87 25	99.91 31	99.87 40	98.04 203	99.96 41	99.68 27	99.99 13	99.90 11

jajsoiax		99.89 3	99.89 5	99.89 8	99.96 5	99.78 47	99.70 34	99.86 35	99.89 19	99.98 10	99.90 27	99.94 1	99.98 10	99.75 23	100.00 1	99.90 11

EU-MVSNet		99.39 99	99.62 41	98.72 295	99.88 38	96.44 336	99.56 79	99.85 39	99.90 13	99.90 37	99.85 49	98.09 199	99.83 250	99.58 37	99.95 67	99.90 11

test_djsdf		99.84 10	99.81 14	99.91 2	99.94 16	99.84 24	99.77 14	99.80 63	99.73 57	99.97 13	99.92 21	99.77 10	99.98 10	99.43 56	100.00 1	99.90 11

CVMVSNet		98.61 235	98.88 199	97.80 326	99.58 175	93.60 361	99.26 143	99.64 146	99.66 81	99.72 112	99.67 153	93.26 310	99.93 81	99.30 80	99.81 172	99.87 16

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 10	99.99 1	100.00 1	99.98 10	99.78 9	100.00 1	99.92 9	100.00 1	99.87 16

FC-MVSNet-test		99.70 25	99.65 35	99.86 18	99.88 38	99.86 18	99.72 29	99.78 74	99.90 13	99.82 66	99.83 55	98.45 162	99.87 186	99.51 48	99.97 42	99.86 18

PS-CasMVS		99.66 39	99.58 54	99.89 8	99.80 72	99.85 19	99.66 52	99.73 96	99.62 88	99.84 61	99.71 124	98.62 134	99.96 41	99.30 80	99.96 56	99.86 18

anonymousdsp		99.80 14	99.77 19	99.90 5	99.96 5	99.88 12	99.73 26	99.85 39	99.70 68	99.92 28	99.93 17	99.45 32	99.97 22	99.36 68	100.00 1	99.85 20

UniMVSNet_ETH3D		99.85 8	99.83 12	99.90 5	99.89 33	99.91 4	99.89 4	99.71 108	99.93 9	99.95 19	99.89 31	99.71 13	99.96 41	99.51 48	99.97 42	99.84 21

CP-MVSNet		99.54 64	99.43 82	99.87 15	99.76 101	99.82 35	99.57 77	99.61 158	99.54 101	99.80 76	99.64 164	97.79 222	99.95 51	99.21 90	99.94 78	99.84 21

Test_1112_low_res		98.95 203	98.73 213	99.63 121	99.68 147	99.15 205	98.09 304	99.80 63	97.14 323	99.46 204	99.40 260	96.11 282	99.89 158	99.01 118	99.84 146	99.84 21

ANet_high		99.88 5	99.87 8	99.91 2	99.99 1	99.91 4	99.65 58	100.00 1	99.90 13	100.00 1	99.97 11	99.61 21	99.97 22	99.75 23	100.00 1	99.84 21

patch_mono-2		99.51 67	99.46 75	99.64 114	99.70 135	99.11 208	99.04 204	99.87 32	99.71 63	99.47 200	99.79 80	98.24 186	99.98 10	99.38 63	99.96 56	99.83 25

nrg030		99.70 25	99.66 33	99.82 27	99.76 101	99.84 24	99.61 66	99.70 114	99.93 9	99.78 85	99.68 148	99.10 72	99.78 286	99.45 54	99.96 56	99.83 25

FIs		99.65 44	99.58 54	99.84 23	99.84 49	99.85 19	99.66 52	99.75 87	99.86 28	99.74 107	99.79 80	98.27 184	99.85 221	99.37 66	99.93 86	99.83 25

v7n		99.82 13	99.80 16	99.88 12	99.96 5	99.84 24	99.82 8	99.82 52	99.84 36	99.94 21	99.91 24	99.13 71	99.96 41	99.83 17	99.99 13	99.83 25

PEN-MVS		99.66 39	99.59 50	99.89 8	99.83 53	99.87 15	99.66 52	99.73 96	99.70 68	99.84 61	99.73 110	98.56 144	99.96 41	99.29 83	99.94 78	99.83 25

WR-MVS_H		99.61 53	99.53 67	99.87 15	99.80 72	99.83 29	99.67 48	99.75 87	99.58 100	99.85 58	99.69 137	98.18 195	99.94 64	99.28 85	99.95 67	99.83 25

Anonymous20231211		99.62 51	99.57 57	99.76 51	99.61 164	99.60 113	99.81 9	99.73 96	99.82 41	99.90 37	99.90 27	97.97 210	99.86 204	99.42 61	99.96 56	99.80 31

APDe-MVS		99.48 72	99.36 94	99.85 20	99.55 197	99.81 38	99.50 87	99.69 120	98.99 181	99.75 99	99.71 124	98.79 110	99.93 81	98.46 161	99.85 141	99.80 31

DTE-MVSNet		99.68 31	99.61 45	99.88 12	99.80 72	99.87 15	99.67 48	99.71 108	99.72 61	99.84 61	99.78 87	98.67 128	99.97 22	99.30 80	99.95 67	99.80 31

XXY-MVS		99.71 24	99.67 32	99.81 30	99.89 33	99.72 74	99.59 72	99.82 52	99.39 127	99.82 66	99.84 54	99.38 39	99.91 123	99.38 63	99.93 86	99.80 31

1112_ss		99.05 181	98.84 204	99.67 95	99.66 153	99.29 179	98.52 271	99.82 52	97.65 297	99.43 210	99.16 309	96.42 272	99.91 123	99.07 114	99.84 146	99.80 31

LTVRE_ROB	99.19 1	99.88 5	99.87 8	99.88 12	99.91 26	99.90 7	99.96 1	99.92 18	99.90 13	99.97 13	99.87 40	99.81 7	99.95 51	99.54 43	99.99 13	99.80 31
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
test_fmvs1		99.48 72	99.65 35	98.97 266	99.54 198	97.16 322	99.11 190	99.98 8	99.78 51	99.96 15	99.81 66	98.72 122	99.97 22	99.95 7	99.97 42	99.79 37

bld_raw_dy_0_64		99.70 25	99.65 35	99.85 20	99.95 13	99.77 50	99.66 52	99.71 108	99.95 4	99.91 31	99.77 94	98.35 175	100.00 1	99.54 43	99.99 13	99.79 37

PMMVS2		99.48 72	99.45 77	99.57 147	99.76 101	98.99 220	98.09 304	99.90 24	98.95 186	99.78 85	99.58 205	99.57 25	99.93 81	99.48 51	99.95 67	99.79 37

MSC_two_6792asdad				99.74 65	99.03 327	99.53 127		99.23 296					99.92 101	97.77 217	99.69 222	99.78 40

No_MVS				99.74 65	99.03 327	99.53 127		99.23 296					99.92 101	97.77 217	99.69 222	99.78 40

dcpmvs_2		99.61 53	99.64 39	99.53 158	99.79 82	98.82 237	99.58 74	99.97 10	99.95 4	99.96 15	99.76 98	98.44 163	99.99 6	99.34 71	99.96 56	99.78 40

CHOSEN 1792x2688		99.39 99	99.30 107	99.65 107	99.88 38	99.25 188	98.78 247	99.88 30	98.66 219	99.96 15	99.79 80	97.45 239	99.93 81	99.34 71	99.99 13	99.78 40

test_vis1_rt		99.45 82	99.46 75	99.41 191	99.71 127	98.63 255	98.99 217	99.96 14	99.03 179	99.95 19	99.12 315	98.75 117	99.84 235	99.82 19	99.82 163	99.77 44

IU-MVS					99.69 139	99.77 50		99.22 299	97.50 305	99.69 123				97.75 221	99.70 218	99.77 44

test_0728_THIRD									99.18 155	99.62 151	99.61 190	98.58 141	99.91 123	97.72 223	99.80 177	99.77 44

test_0728_SECOND				99.83 25	99.70 135	99.79 44	99.14 178	99.61 158					99.92 101	97.88 206	99.72 213	99.77 44

MSP-MVS		99.04 184	98.79 211	99.81 30	99.78 89	99.73 70	99.35 117	99.57 188	98.54 233	99.54 182	98.99 332	96.81 263	99.93 81	96.97 275	99.53 271	99.77 44
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
mvsmamba		99.74 21	99.70 24	99.85 20	99.93 23	99.83 29	99.76 18	99.81 61	99.96 2	99.91 31	99.81 66	98.60 138	99.94 64	99.58 37	99.98 30	99.77 44

DPE-MVS		99.14 165	98.92 194	99.82 27	99.57 185	99.77 50	98.74 250	99.60 170	98.55 230	99.76 92	99.69 137	98.23 190	99.92 101	96.39 307	99.75 195	99.76 50
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
Baseline_NR-MVSNet		99.49 70	99.37 91	99.82 27	99.91 26	99.84 24	98.83 235	99.86 35	99.68 73	99.65 137	99.88 36	97.67 229	99.87 186	99.03 116	99.86 137	99.76 50

OurMVSNet-221017-0		99.75 18	99.71 23	99.84 23	99.96 5	99.83 29	99.83 6	99.85 39	99.80 46	99.93 24	99.93 17	98.54 147	99.93 81	99.59 34	99.98 30	99.76 50

test_241102_TWO								99.54 205	99.13 168	99.76 92	99.63 174	98.32 181	99.92 101	97.85 212	99.69 222	99.75 53

DP-MVS		99.48 72	99.39 86	99.74 65	99.57 185	99.62 105	99.29 136	99.61 158	99.87 25	99.74 107	99.76 98	98.69 124	99.87 186	98.20 179	99.80 177	99.75 53

tt0805		99.63 45	99.57 57	99.81 30	99.87 42	99.88 12	99.58 74	98.70 328	99.72 61	99.91 31	99.60 198	99.43 33	99.81 274	99.81 20	99.53 271	99.73 55

v10		99.69 28	99.69 28	99.66 102	99.81 67	99.39 158	99.66 52	99.75 87	99.60 97	99.92 28	99.87 40	98.75 117	99.86 204	99.90 10	99.99 13	99.73 55

EI-MVSNet-UG-set		99.48 72	99.50 69	99.42 184	99.57 185	98.65 253	99.24 150	99.46 238	99.68 73	99.80 76	99.66 157	98.99 87	99.89 158	99.19 94	99.90 100	99.72 57

Vis-MVSNet		99.75 18	99.74 22	99.79 38	99.88 38	99.66 93	99.69 41	99.92 18	99.67 77	99.77 90	99.75 103	99.61 21	99.98 10	99.35 70	99.98 30	99.72 57
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
HyFIR lowres test		98.91 206	98.64 220	99.73 74	99.85 48	99.47 133	98.07 307	99.83 47	98.64 221	99.89 41	99.60 198	92.57 317	100.00 1	99.33 74	99.97 42	99.72 57

EI-MVSNet-Vis-set		99.47 79	99.49 70	99.42 184	99.57 185	98.66 250	99.24 150	99.46 238	99.67 77	99.79 81	99.65 162	98.97 91	99.89 158	99.15 103	99.89 109	99.71 60

v8		99.68 31	99.69 28	99.65 107	99.80 72	99.40 156	99.66 52	99.76 82	99.64 85	99.93 24	99.85 49	98.66 130	99.84 235	99.88 14	99.99 13	99.71 60

TransMVSNet (Re)		99.78 16	99.77 19	99.81 30	99.91 26	99.85 19	99.75 21	99.86 35	99.70 68	99.91 31	99.89 31	99.60 23	99.87 186	99.59 34	99.74 202	99.71 60

test1111		97.74 291	98.16 267	96.49 350	99.60 166	89.86 379	99.71 33	91.21 376	99.89 19	99.88 47	99.87 40	93.73 306	99.90 141	99.56 40	99.99 13	99.70 63

VPA-MVSNet		99.66 39	99.62 41	99.79 38	99.68 147	99.75 62	99.62 61	99.69 120	99.85 33	99.80 76	99.81 66	98.81 105	99.91 123	99.47 52	99.88 118	99.70 63

WR-MVS		99.11 172	98.93 190	99.66 102	99.30 282	99.42 151	98.42 280	99.37 264	99.04 178	99.57 168	99.20 307	96.89 261	99.86 204	98.66 153	99.87 129	99.70 63

ACMH	98.42 6	99.59 55	99.54 63	99.72 80	99.86 45	99.62 105	99.56 79	99.79 69	98.77 211	99.80 76	99.85 49	99.64 17	99.85 221	98.70 149	99.89 109	99.70 63
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs6		99.86 7	99.86 10	99.83 25	99.94 16	99.90 7	99.83 6	99.91 21	99.85 33	99.94 21	99.95 13	99.73 12	99.90 141	99.65 29	99.97 42	99.69 67

HPM-MVS_fast		99.43 86	99.30 107	99.80 34	99.83 53	99.81 38	99.52 83	99.70 114	98.35 255	99.51 194	99.50 235	99.31 47	99.88 172	98.18 183	99.84 146	99.69 67

LPG-MVS_test		99.22 142	99.05 163	99.74 65	99.82 60	99.63 103	99.16 174	99.73 96	97.56 299	99.64 138	99.69 137	99.37 41	99.89 158	96.66 293	99.87 129	99.69 67

LGP-MVS_train				99.74 65	99.82 60	99.63 103		99.73 96	97.56 299	99.64 138	99.69 137	99.37 41	99.89 158	96.66 293	99.87 129	99.69 67

SteuartSystems-ACMMP		99.30 121	99.14 133	99.76 51	99.87 42	99.66 93	99.18 165	99.60 170	98.55 230	99.57 168	99.67 153	99.03 84	99.94 64	97.01 273	99.80 177	99.69 67
Skip Steuart: Steuart Systems R&D Blog.
MG-MVS		98.52 247	98.39 245	98.94 269	99.15 308	97.39 317	98.18 293	99.21 302	98.89 197	99.23 253	99.63 174	97.37 244	99.74 302	94.22 352	99.61 250	99.69 67

ACMMP_NAP		99.28 123	99.11 142	99.79 38	99.75 112	99.81 38	98.95 223	99.53 214	98.27 264	99.53 187	99.73 110	98.75 117	99.87 186	97.70 228	99.83 154	99.68 73

HFP-MVS		99.25 130	99.08 153	99.76 51	99.73 121	99.70 83	99.31 127	99.59 176	98.36 250	99.36 227	99.37 268	98.80 109	99.91 123	97.43 249	99.75 195	99.68 73

EI-MVSNet		99.38 101	99.44 80	99.21 238	99.58 175	98.09 289	99.26 143	99.46 238	99.62 88	99.75 99	99.67 153	98.54 147	99.85 221	99.15 103	99.92 90	99.68 73

TranMVSNet+NR-MVSNet		99.54 64	99.47 71	99.76 51	99.58 175	99.64 99	99.30 130	99.63 148	99.61 91	99.71 117	99.56 217	98.76 115	99.96 41	99.14 109	99.92 90	99.68 73

PVSNet_Blended_VisFu		99.40 95	99.38 88	99.44 178	99.90 31	98.66 250	98.94 225	99.91 21	97.97 281	99.79 81	99.73 110	99.05 82	99.97 22	99.15 103	99.99 13	99.68 73

IterMVS-LS		99.41 93	99.47 71	99.25 234	99.81 67	98.09 289	98.85 232	99.76 82	99.62 88	99.83 65	99.64 164	98.54 147	99.97 22	99.15 103	99.99 13	99.68 73
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MP-MVS-pluss		99.14 165	98.92 194	99.80 34	99.83 53	99.83 29	98.61 256	99.63 148	96.84 330	99.44 206	99.58 205	98.81 105	99.91 123	97.70 228	99.82 163	99.67 79
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
region2R		99.23 134	99.05 163	99.77 44	99.76 101	99.70 83	99.31 127	99.59 176	98.41 244	99.32 236	99.36 272	98.73 121	99.93 81	97.29 256	99.74 202	99.67 79

XVS		99.27 127	99.11 142	99.75 60	99.71 127	99.71 76	99.37 113	99.61 158	99.29 136	98.76 309	99.47 246	98.47 158	99.88 172	97.62 236	99.73 207	99.67 79

v1240		99.56 59	99.58 54	99.51 162	99.80 72	99.00 219	99.00 212	99.65 140	99.15 166	99.90 37	99.75 103	99.09 74	99.88 172	99.90 10	99.96 56	99.67 79

X-MVStestdata		96.09 330	94.87 339	99.75 60	99.71 127	99.71 76	99.37 113	99.61 158	99.29 136	98.76 309	61.30 383	98.47 158	99.88 172	97.62 236	99.73 207	99.67 79

VPNet		99.46 80	99.37 91	99.71 85	99.82 60	99.59 115	99.48 92	99.70 114	99.81 43	99.69 123	99.58 205	97.66 233	99.86 204	99.17 99	99.44 284	99.67 79

ACMMPR		99.23 134	99.06 159	99.76 51	99.74 118	99.69 86	99.31 127	99.59 176	98.36 250	99.35 228	99.38 266	98.61 136	99.93 81	97.43 249	99.75 195	99.67 79

SixPastTwentyTwo		99.42 89	99.30 107	99.76 51	99.92 25	99.67 91	99.70 34	99.14 308	99.65 83	99.89 41	99.90 27	96.20 280	99.94 64	99.42 61	99.92 90	99.67 79

HPM-MVS		99.25 130	99.07 157	99.78 41	99.81 67	99.75 62	99.61 66	99.67 127	97.72 294	99.35 228	99.25 296	99.23 58	99.92 101	97.21 267	99.82 163	99.67 79
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
v144192		99.55 62	99.54 63	99.58 141	99.78 89	99.20 200	99.11 190	99.62 151	99.18 155	99.89 41	99.72 117	98.66 130	99.87 186	99.88 14	99.97 42	99.66 88

v1921920		99.56 59	99.57 57	99.55 153	99.75 112	99.11 208	99.05 202	99.61 158	99.15 166	99.88 47	99.71 124	99.08 77	99.87 186	99.90 10	99.97 42	99.66 88

v1192		99.57 56	99.57 57	99.57 147	99.77 97	99.22 195	99.04 204	99.60 170	99.18 155	99.87 55	99.72 117	99.08 77	99.85 221	99.89 13	99.98 30	99.66 88

PGM-MVS		99.20 149	99.01 174	99.77 44	99.75 112	99.71 76	99.16 174	99.72 105	97.99 279	99.42 212	99.60 198	98.81 105	99.93 81	96.91 278	99.74 202	99.66 88

mPP-MVS		99.19 152	99.00 177	99.76 51	99.76 101	99.68 89	99.38 109	99.54 205	98.34 259	99.01 281	99.50 235	98.53 151	99.93 81	97.18 268	99.78 187	99.66 88

CP-MVS		99.23 134	99.05 163	99.75 60	99.66 153	99.66 93	99.38 109	99.62 151	98.38 248	99.06 279	99.27 291	98.79 110	99.94 64	97.51 245	99.82 163	99.66 88

EG-PatchMatch MVS		99.57 56	99.56 62	99.62 130	99.77 97	99.33 173	99.26 143	99.76 82	99.32 135	99.80 76	99.78 87	99.29 49	99.87 186	99.15 103	99.91 99	99.66 88

UGNet		99.38 101	99.34 96	99.49 165	98.90 337	98.90 233	99.70 34	99.35 268	99.86 28	98.57 323	99.81 66	98.50 157	99.93 81	99.38 63	99.98 30	99.66 88
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
test2506		94.73 340	94.59 342	95.15 356	99.59 170	85.90 381	99.75 21	74.01 382	99.89 19	99.71 117	99.86 47	79.00 380	99.90 141	99.52 47	99.99 13	99.65 96

ECVR-MVS		97.73 292	98.04 272	96.78 344	99.59 170	90.81 375	99.72 29	90.43 378	99.89 19	99.86 56	99.86 47	93.60 308	99.89 158	99.46 53	99.99 13	99.65 96

h-mvs33		98.61 235	98.34 251	99.44 178	99.60 166	98.67 247	99.27 141	99.44 243	99.68 73	99.32 236	99.49 239	92.50 320	100.00 1	99.24 87	96.51 369	99.65 96

TSAR-MVS + MP.		99.34 114	99.24 122	99.63 121	99.82 60	99.37 163	99.26 143	99.35 268	98.77 211	99.57 168	99.70 131	99.27 54	99.88 172	97.71 225	99.75 195	99.65 96
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MTAPA		99.35 109	99.20 125	99.80 34	99.81 67	99.81 38	99.33 120	99.53 214	99.27 140	99.42 212	99.63 174	98.21 191	99.95 51	97.83 216	99.79 182	99.65 96

MCST-MVS		99.02 187	98.81 208	99.65 107	99.58 175	99.49 131	98.58 260	99.07 311	98.40 246	99.04 280	99.25 296	98.51 156	99.80 280	97.31 255	99.51 275	99.65 96

UniMVSNet_NR-MVSNet		99.37 104	99.25 120	99.72 80	99.47 233	99.56 122	98.97 221	99.61 158	99.43 122	99.67 131	99.28 289	97.85 218	99.95 51	99.17 99	99.81 172	99.65 96

casdiffmvs_mvg		99.68 31	99.68 31	99.69 90	99.81 67	99.59 115	99.29 136	99.90 24	99.71 63	99.79 81	99.73 110	99.54 28	99.84 235	99.36 68	99.96 56	99.65 96
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ZNCC-MVS		99.22 142	99.04 168	99.77 44	99.76 101	99.73 70	99.28 138	99.56 193	98.19 269	99.14 268	99.29 288	98.84 104	99.92 101	97.53 244	99.80 177	99.64 104

v1144		99.54 64	99.53 67	99.59 138	99.79 82	99.28 181	99.10 192	99.61 158	99.20 153	99.84 61	99.73 110	98.67 128	99.84 235	99.86 16	99.98 30	99.64 104

v2v482		99.50 68	99.47 71	99.58 141	99.78 89	99.25 188	99.14 178	99.58 186	99.25 144	99.81 73	99.62 181	98.24 186	99.84 235	99.83 17	99.97 42	99.64 104

K. test v3		98.87 214	98.60 223	99.69 90	99.93 23	99.46 137	99.74 23	94.97 369	99.78 51	99.88 47	99.88 36	93.66 307	99.97 22	99.61 32	99.95 67	99.64 104

DeepC-MVS	98.90 4	99.62 51	99.61 45	99.67 95	99.72 124	99.44 144	99.24 150	99.71 108	99.27 140	99.93 24	99.90 27	99.70 15	99.93 81	98.99 119	99.99 13	99.64 104
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
mvsany_test1		99.44 84	99.45 77	99.40 193	99.37 257	98.64 254	97.90 326	99.59 176	99.27 140	99.92 28	99.82 62	99.74 11	99.93 81	99.55 42	99.87 129	99.63 109

SMA-MVS		99.19 152	99.00 177	99.73 74	99.46 237	99.73 70	99.13 184	99.52 219	97.40 310	99.57 168	99.64 164	98.93 94	99.83 250	97.61 238	99.79 182	99.63 109
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
IterMVS-SCA-FT		99.00 193	99.16 129	98.51 302	99.75 112	95.90 344	98.07 307	99.84 45	99.84 36	99.89 41	99.73 110	96.01 284	99.99 6	99.33 74	100.00 1	99.63 109

pm-mvs1		99.79 15	99.79 17	99.78 41	99.91 26	99.83 29	99.76 18	99.87 32	99.73 57	99.89 41	99.87 40	99.63 18	99.87 186	99.54 43	99.92 90	99.63 109

MP-MVS		99.06 178	98.83 206	99.76 51	99.76 101	99.71 76	99.32 122	99.50 227	98.35 255	98.97 283	99.48 242	98.37 173	99.92 101	95.95 326	99.75 195	99.63 109
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DU-MVS		99.33 117	99.21 124	99.71 85	99.43 244	99.56 122	98.83 235	99.53 214	99.38 128	99.67 131	99.36 272	97.67 229	99.95 51	99.17 99	99.81 172	99.63 109

NR-MVSNet		99.40 95	99.31 102	99.68 92	99.43 244	99.55 125	99.73 26	99.50 227	99.46 114	99.88 47	99.36 272	97.54 236	99.87 186	98.97 123	99.87 129	99.63 109

IterMVS		98.97 197	99.16 129	98.42 306	99.74 118	95.64 347	98.06 309	99.83 47	99.83 39	99.85 58	99.74 106	96.10 283	99.99 6	99.27 86	100.00 1	99.63 109
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EPP-MVSNet		99.17 160	99.00 177	99.66 102	99.80 72	99.43 148	99.70 34	99.24 295	99.48 107	99.56 175	99.77 94	94.89 292	99.93 81	98.72 148	99.89 109	99.63 109

ACMMP		99.25 130	99.08 153	99.74 65	99.79 82	99.68 89	99.50 87	99.65 140	98.07 275	99.52 189	99.69 137	98.57 142	99.92 101	97.18 268	99.79 182	99.63 109
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
DeepC-MVS_fast	98.47 5	99.23 134	99.12 139	99.56 150	99.28 287	99.22 195	98.99 217	99.40 256	99.08 173	99.58 165	99.64 164	98.90 100	99.83 250	97.44 248	99.75 195	99.63 109
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DVP-MVS++		99.38 101	99.25 120	99.77 44	99.03 327	99.77 50	99.74 23	99.61 158	99.18 155	99.76 92	99.61 190	99.00 85	99.92 101	97.72 223	99.60 253	99.62 120

PC_three_1452									97.56 299	99.68 126	99.41 256	99.09 74	97.09 375	96.66 293	99.60 253	99.62 120

GeoE		99.69 28	99.66 33	99.78 41	99.76 101	99.76 58	99.60 71	99.82 52	99.46 114	99.75 99	99.56 217	99.63 18	99.95 51	99.43 56	99.88 118	99.62 120

test_method		91.72 341	92.32 344	89.91 358	93.49 380	70.18 382	90.28 371	99.56 193	61.71 375	95.39 372	99.52 230	93.90 301	99.94 64	98.76 144	98.27 350	99.62 120

GST-MVS		99.16 161	98.96 188	99.75 60	99.73 121	99.73 70	99.20 160	99.55 199	98.22 266	99.32 236	99.35 277	98.65 132	99.91 123	96.86 281	99.74 202	99.62 120

new-patchmatchnet		99.35 109	99.57 57	98.71 297	99.82 60	96.62 334	98.55 266	99.75 87	99.50 105	99.88 47	99.87 40	99.31 47	99.88 172	99.43 56	100.00 1	99.62 120

CPTT-MVS		98.74 226	98.44 240	99.64 114	99.61 164	99.38 160	99.18 165	99.55 199	96.49 334	99.27 247	99.37 268	97.11 256	99.92 101	95.74 332	99.67 233	99.62 120

MIMVSNet1		99.66 39	99.62 41	99.80 34	99.94 16	99.87 15	99.69 41	99.77 77	99.78 51	99.93 24	99.89 31	97.94 211	99.92 101	99.65 29	99.98 30	99.62 120

DeepPCF-MVS	98.42 6	99.18 156	99.02 171	99.67 95	99.22 296	99.75 62	97.25 354	99.47 235	98.72 216	99.66 135	99.70 131	99.29 49	99.63 347	98.07 191	99.81 172	99.62 120

3Dnovator+	98.92 3	99.35 109	99.24 122	99.67 95	99.35 262	99.47 133	99.62 61	99.50 227	99.44 117	99.12 271	99.78 87	98.77 114	99.94 64	97.87 209	99.72 213	99.62 120

DVP-MVS		99.32 119	99.17 128	99.77 44	99.69 139	99.80 42	99.14 178	99.31 277	99.16 162	99.62 151	99.61 190	98.35 175	99.91 123	97.88 206	99.72 213	99.61 130
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
APD-MVS		98.87 214	98.59 225	99.71 85	99.50 217	99.62 105	99.01 210	99.57 188	96.80 332	99.54 182	99.63 174	98.29 182	99.91 123	95.24 341	99.71 216	99.61 130
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		98.82 218	98.57 229	99.58 141	99.21 298	99.31 176	98.61 256	99.25 292	98.65 220	98.43 329	99.26 294	97.86 216	99.81 274	96.55 298	99.27 307	99.61 130

TAMVS		99.49 70	99.45 77	99.63 121	99.48 227	99.42 151	99.45 98	99.57 188	99.66 81	99.78 85	99.83 55	97.85 218	99.86 204	99.44 55	99.96 56	99.61 130

HPM-MVS++		98.96 200	98.70 218	99.74 65	99.52 209	99.71 76	98.86 230	99.19 303	98.47 240	98.59 321	99.06 322	98.08 201	99.91 123	96.94 276	99.60 253	99.60 134

V42		99.56 59	99.54 63	99.63 121	99.79 82	99.46 137	99.39 107	99.59 176	99.24 146	99.86 56	99.70 131	98.55 145	99.82 259	99.79 21	99.95 67	99.60 134

HQP_MVS		98.90 208	98.68 219	99.55 153	99.58 175	99.24 192	98.80 243	99.54 205	98.94 187	99.14 268	99.25 296	97.24 248	99.82 259	95.84 329	99.78 187	99.60 134

plane_prior5								99.54 205					99.82 259	95.84 329	99.78 187	99.60 134

TDRefinement		99.72 22	99.70 24	99.77 44	99.90 31	99.85 19	99.86 5	99.92 18	99.69 71	99.78 85	99.92 21	99.37 41	99.88 172	98.93 131	99.95 67	99.60 134

ACMH+	98.40 8	99.50 68	99.43 82	99.71 85	99.86 45	99.76 58	99.32 122	99.77 77	99.53 103	99.77 90	99.76 98	99.26 55	99.78 286	97.77 217	99.88 118	99.60 134

ACMM	98.09 11	99.46 80	99.38 88	99.72 80	99.80 72	99.69 86	99.13 184	99.65 140	98.99 181	99.64 138	99.72 117	99.39 35	99.86 204	98.23 176	99.81 172	99.60 134
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VDDNet		98.97 197	98.82 207	99.42 184	99.71 127	98.81 238	99.62 61	98.68 329	99.81 43	99.38 225	99.80 70	94.25 299	99.85 221	98.79 140	99.32 299	99.59 141

casdiffmvs		99.63 45	99.61 45	99.67 95	99.79 82	99.59 115	99.13 184	99.85 39	99.79 49	99.76 92	99.72 117	99.33 46	99.82 259	99.21 90	99.94 78	99.59 141
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UniMVSNet (Re)		99.37 104	99.26 118	99.68 92	99.51 211	99.58 119	98.98 220	99.60 170	99.43 122	99.70 120	99.36 272	97.70 225	99.88 172	99.20 93	99.87 129	99.59 141

DSMNet-mixed		99.48 72	99.65 35	98.95 268	99.71 127	97.27 319	99.50 87	99.82 52	99.59 99	99.41 218	99.85 49	99.62 20	100.00 1	99.53 46	99.89 109	99.59 141

3Dnovator	99.15 2	99.43 86	99.36 94	99.65 107	99.39 252	99.42 151	99.70 34	99.56 193	99.23 148	99.35 228	99.80 70	99.17 64	99.95 51	98.21 178	99.84 146	99.59 141

SED-MVS		99.40 95	99.28 114	99.77 44	99.69 139	99.82 35	99.20 160	99.54 205	99.13 168	99.82 66	99.63 174	98.91 97	99.92 101	97.85 212	99.70 218	99.58 146

OPU-MVS				99.29 224	99.12 313	99.44 144	99.20 160				99.40 260	99.00 85	98.84 372	96.54 299	99.60 253	99.58 146

EPNet		98.13 277	97.77 292	99.18 243	94.57 379	97.99 294	99.24 150	97.96 351	99.74 56	97.29 361	99.62 181	93.13 312	99.97 22	98.59 155	99.83 154	99.58 146
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IS-MVSNet		99.03 185	98.85 202	99.55 153	99.80 72	99.25 188	99.73 26	99.15 307	99.37 129	99.61 157	99.71 124	94.73 295	99.81 274	97.70 228	99.88 118	99.58 146

ACMP	97.51 14	99.05 181	98.84 204	99.67 95	99.78 89	99.55 125	98.88 228	99.66 131	97.11 325	99.47 200	99.60 198	99.07 79	99.89 158	96.18 316	99.85 141	99.58 146
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SR-MVS		99.19 152	99.00 177	99.74 65	99.51 211	99.72 74	99.18 165	99.60 170	98.85 200	99.47 200	99.58 205	98.38 172	99.92 101	96.92 277	99.54 269	99.57 151

lessismore_v0				99.64 114	99.86 45	99.38 160		90.66 377		99.89 41	99.83 55	94.56 297	99.97 22	99.56 40	99.92 90	99.57 151

pmmvs5		99.19 152	99.11 142	99.42 184	99.76 101	98.88 234	98.55 266	99.73 96	98.82 204	99.72 112	99.62 181	96.56 266	99.82 259	99.32 76	99.95 67	99.56 153

APD-MVS_3200maxsize		99.31 120	99.16 129	99.74 65	99.53 204	99.75 62	99.27 141	99.61 158	99.19 154	99.57 168	99.64 164	98.76 115	99.90 141	97.29 256	99.62 243	99.56 153

CDPH-MVS		98.56 243	98.20 262	99.61 133	99.50 217	99.46 137	98.32 285	99.41 249	95.22 351	99.21 258	99.10 319	98.34 178	99.82 259	95.09 344	99.66 236	99.56 153

Anonymous20240521		99.44 84	99.42 84	99.49 165	99.89 33	98.96 225	99.62 61	99.76 82	99.85 33	99.82 66	99.88 36	96.39 275	99.97 22	99.59 34	99.98 30	99.55 156

our_test_3		98.85 216	99.09 151	98.13 318	99.66 153	94.90 354	97.72 332	99.58 186	99.07 175	99.64 138	99.62 181	98.19 193	99.93 81	98.41 163	99.95 67	99.55 156

YYNet1		98.95 203	98.99 182	98.84 285	99.64 157	97.14 324	98.22 292	99.32 273	98.92 192	99.59 163	99.66 157	97.40 241	99.83 250	98.27 173	99.90 100	99.55 156

MDA-MVSNet_test_wron		98.95 203	98.99 182	98.85 283	99.64 157	97.16 322	98.23 291	99.33 271	98.93 190	99.56 175	99.66 157	97.39 243	99.83 250	98.29 171	99.88 118	99.55 156

MVSFormer		99.41 93	99.44 80	99.31 221	99.57 185	98.40 268	99.77 14	99.80 63	99.73 57	99.63 142	99.30 285	98.02 205	99.98 10	99.43 56	99.69 222	99.55 156

jason		99.16 161	99.11 142	99.32 218	99.75 112	98.44 265	98.26 289	99.39 259	98.70 217	99.74 107	99.30 285	98.54 147	99.97 22	98.48 160	99.82 163	99.55 156
jason: jason.
CDS-MVSNet		99.22 142	99.13 135	99.50 164	99.35 262	99.11 208	98.96 222	99.54 205	99.46 114	99.61 157	99.70 131	96.31 277	99.83 250	99.34 71	99.88 118	99.55 156
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
COLMAP_ROB	98.06 12	99.45 82	99.37 91	99.70 89	99.83 53	99.70 83	99.38 109	99.78 74	99.53 103	99.67 131	99.78 87	99.19 62	99.86 204	97.32 254	99.87 129	99.55 156
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
iter_conf_final		98.75 224	98.54 233	99.40 193	99.33 275	98.75 242	99.26 143	99.59 176	99.80 46	99.76 92	99.58 205	90.17 346	99.92 101	99.37 66	99.97 42	99.54 164

SR-MVS-dyc-post		99.27 127	99.11 142	99.73 74	99.54 198	99.74 68	99.26 143	99.62 151	99.16 162	99.52 189	99.64 164	98.41 167	99.91 123	97.27 259	99.61 250	99.54 164

RE-MVS-def			99.13 135		99.54 198	99.74 68	99.26 143	99.62 151	99.16 162	99.52 189	99.64 164	98.57 142		97.27 259	99.61 250	99.54 164

SD-MVS		99.01 191	99.30 107	98.15 317	99.50 217	99.40 156	98.94 225	99.61 158	99.22 152	99.75 99	99.82 62	99.54 28	95.51 377	97.48 246	99.87 129	99.54 164
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
CNVR-MVS		98.99 196	98.80 210	99.56 150	99.25 292	99.43 148	98.54 269	99.27 286	98.58 227	98.80 305	99.43 254	98.53 151	99.70 313	97.22 266	99.59 257	99.54 164

MVS_111021_HR		99.12 169	99.02 171	99.40 193	99.50 217	99.11 208	97.92 323	99.71 108	98.76 214	99.08 275	99.47 246	99.17 64	99.54 357	97.85 212	99.76 193	99.54 164

v148		99.40 95	99.41 85	99.39 197	99.76 101	98.94 226	99.09 196	99.59 176	99.17 160	99.81 73	99.61 190	98.41 167	99.69 319	99.32 76	99.94 78	99.53 170

iter_conf05		98.46 255	98.23 258	99.15 246	99.04 326	97.99 294	99.10 192	99.61 158	99.79 49	99.76 92	99.58 205	87.88 356	99.92 101	99.31 79	99.97 42	99.53 170

diffmvs		99.34 114	99.32 101	99.39 197	99.67 152	98.77 241	98.57 264	99.81 61	99.61 91	99.48 199	99.41 256	98.47 158	99.86 204	98.97 123	99.90 100	99.53 170
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		99.63 45	99.62 41	99.66 102	99.80 72	99.62 105	99.44 101	99.80 63	99.71 63	99.72 112	99.69 137	99.15 66	99.83 250	99.32 76	99.94 78	99.53 170

HQP4-MVS										98.15 338			99.70 313			99.53 170

GBi-Net		99.42 89	99.31 102	99.73 74	99.49 222	99.77 50	99.68 44	99.70 114	99.44 117	99.62 151	99.83 55	97.21 250	99.90 141	98.96 125	99.90 100	99.53 170

test1		99.42 89	99.31 102	99.73 74	99.49 222	99.77 50	99.68 44	99.70 114	99.44 117	99.62 151	99.83 55	97.21 250	99.90 141	98.96 125	99.90 100	99.53 170

FMVSNet1		99.66 39	99.63 40	99.73 74	99.78 89	99.77 50	99.68 44	99.70 114	99.67 77	99.82 66	99.83 55	98.98 89	99.90 141	99.24 87	99.97 42	99.53 170

HQP-MVS		98.36 264	98.02 274	99.39 197	99.31 278	98.94 226	97.98 316	99.37 264	97.45 307	98.15 338	98.83 348	96.67 264	99.70 313	94.73 346	99.67 233	99.53 170

QAPM		98.40 262	97.99 275	99.65 107	99.39 252	99.47 133	99.67 48	99.52 219	91.70 365	98.78 308	99.80 70	98.55 145	99.95 51	94.71 348	99.75 195	99.53 170

F-COLMAP		98.74 226	98.45 239	99.62 130	99.57 185	99.47 133	98.84 233	99.65 140	96.31 338	98.93 287	99.19 308	97.68 228	99.87 186	96.52 300	99.37 294	99.53 170

MVSTER		98.47 254	98.22 260	99.24 236	99.06 323	98.35 273	99.08 199	99.46 238	99.27 140	99.75 99	99.66 157	88.61 354	99.85 221	99.14 109	99.92 90	99.52 181

PVSNet_BlendedMVS		99.03 185	99.01 174	99.09 255	99.54 198	97.99 294	98.58 260	99.82 52	97.62 298	99.34 231	99.71 124	98.52 154	99.77 294	97.98 197	99.97 42	99.52 181

OPM-MVS		99.26 129	99.13 135	99.63 121	99.70 135	99.61 111	98.58 260	99.48 232	98.50 236	99.52 189	99.63 174	99.14 69	99.76 296	97.89 205	99.77 191	99.51 183
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
AllTest		99.21 147	99.07 157	99.63 121	99.78 89	99.64 99	99.12 188	99.83 47	98.63 222	99.63 142	99.72 117	98.68 125	99.75 300	96.38 308	99.83 154	99.51 183

TestCases				99.63 121	99.78 89	99.64 99		99.83 47	98.63 222	99.63 142	99.72 117	98.68 125	99.75 300	96.38 308	99.83 154	99.51 183

BH-RMVSNet		98.41 260	98.14 268	99.21 238	99.21 298	98.47 262	98.60 258	98.26 347	98.35 255	98.93 287	99.31 283	97.20 253	99.66 338	94.32 350	99.10 316	99.51 183

USDC		98.96 200	98.93 190	99.05 261	99.54 198	97.99 294	97.07 360	99.80 63	98.21 267	99.75 99	99.77 94	98.43 164	99.64 346	97.90 204	99.88 118	99.51 183

test9_res														95.10 343	99.44 284	99.50 188

train_agg		98.35 267	97.95 279	99.57 147	99.35 262	99.35 170	98.11 302	99.41 249	94.90 355	97.92 348	98.99 332	98.02 205	99.85 221	95.38 339	99.44 284	99.50 188

agg_prior2														94.58 349	99.46 283	99.50 188

VDD-MVS		99.20 149	99.11 142	99.44 178	99.43 244	98.98 221	99.50 87	98.32 346	99.80 46	99.56 175	99.69 137	96.99 259	99.85 221	98.99 119	99.73 207	99.50 188

MDA-MVSNet-bldmvs		99.06 178	99.05 163	99.07 259	99.80 72	97.83 303	98.89 227	99.72 105	99.29 136	99.63 142	99.70 131	96.47 270	99.89 158	98.17 185	99.82 163	99.50 188

KD-MVS_self_test		99.63 45	99.59 50	99.76 51	99.84 49	99.90 7	99.37 113	99.79 69	99.83 39	99.88 47	99.85 49	98.42 166	99.90 141	99.60 33	99.73 207	99.49 193

SF-MVS		99.10 175	98.93 190	99.62 130	99.58 175	99.51 129	99.13 184	99.65 140	97.97 281	99.42 212	99.61 190	98.86 102	99.87 186	96.45 305	99.68 227	99.49 193

Anonymous20240529		99.42 89	99.34 96	99.65 107	99.53 204	99.60 113	99.63 60	99.39 259	99.47 111	99.76 92	99.78 87	98.13 197	99.86 204	98.70 149	99.68 227	99.49 193

WTY-MVS		98.59 240	98.37 247	99.26 231	99.43 244	98.40 268	98.74 250	99.13 310	98.10 272	99.21 258	99.24 301	94.82 293	99.90 141	97.86 210	98.77 333	99.49 193

ppachtmachnet_test		98.89 211	99.12 139	98.20 316	99.66 153	95.24 351	97.63 336	99.68 123	99.08 173	99.78 85	99.62 181	98.65 132	99.88 172	98.02 192	99.96 56	99.48 197

Anonymous20231206		99.35 109	99.31 102	99.47 171	99.74 118	99.06 218	99.28 138	99.74 92	99.23 148	99.72 112	99.53 228	97.63 235	99.88 172	99.11 111	99.84 146	99.48 197

test_prior				99.46 173	99.35 262	99.22 195		99.39 259					99.69 319			99.48 197

test12				99.54 157	99.29 284	99.33 173		99.16 306		98.43 329		97.54 236	99.82 259		99.47 281	99.48 197

VNet		99.18 156	99.06 159	99.56 150	99.24 294	99.36 167	99.33 120	99.31 277	99.67 77	99.47 200	99.57 214	96.48 269	99.84 235	99.15 103	99.30 301	99.47 201

test20.03		99.55 62	99.54 63	99.58 141	99.79 82	99.37 163	99.02 208	99.89 26	99.60 97	99.82 66	99.62 181	98.81 105	99.89 158	99.43 56	99.86 137	99.47 201

114514_t		98.49 252	98.11 269	99.64 114	99.73 121	99.58 119	99.24 150	99.76 82	89.94 368	99.42 212	99.56 217	97.76 224	99.86 204	97.74 222	99.82 163	99.47 201

sss		98.90 208	98.77 212	99.27 229	99.48 227	98.44 265	98.72 252	99.32 273	97.94 285	99.37 226	99.35 277	96.31 277	99.91 123	98.85 133	99.63 242	99.47 201

旧先验1					99.49 222	99.29 179		99.26 289			99.39 264	97.67 229			99.36 295	99.46 205

MVP-Stereo		99.16 161	99.08 153	99.43 182	99.48 227	99.07 216	99.08 199	99.55 199	98.63 222	99.31 240	99.68 148	98.19 193	99.78 286	98.18 183	99.58 258	99.45 206
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
新几何1				99.52 160	99.50 217	99.22 195		99.26 289	95.66 347	98.60 320	99.28 289	97.67 229	99.89 158	95.95 326	99.32 299	99.45 206

LFMVS		98.46 255	98.19 265	99.26 231	99.24 294	98.52 261	99.62 61	96.94 362	99.87 25	99.31 240	99.58 205	91.04 333	99.81 274	98.68 152	99.42 288	99.45 206

testgi		99.29 122	99.26 118	99.37 204	99.75 112	98.81 238	98.84 233	99.89 26	98.38 248	99.75 99	99.04 325	99.36 44	99.86 204	99.08 113	99.25 308	99.45 206

UnsupCasMVSNet_eth		98.83 217	98.57 229	99.59 138	99.68 147	99.45 142	98.99 217	99.67 127	99.48 107	99.55 180	99.36 272	94.92 291	99.86 204	98.95 129	96.57 368	99.45 206

无先验							98.01 312	99.23 296	95.83 344				99.85 221	95.79 331		99.44 211

testdata				99.42 184	99.51 211	98.93 229		99.30 280	96.20 339	98.87 297	99.40 260	98.33 180	99.89 158	96.29 311	99.28 304	99.44 211

XVG-OURS-SEG-HR		99.16 161	98.99 182	99.66 102	99.84 49	99.64 99	98.25 290	99.73 96	98.39 247	99.63 142	99.43 254	99.70 15	99.90 141	97.34 253	98.64 341	99.44 211

FMVSNet2		99.35 109	99.28 114	99.55 153	99.49 222	99.35 170	99.45 98	99.57 188	99.44 117	99.70 120	99.74 106	97.21 250	99.87 186	99.03 116	99.94 78	99.44 211

N_pmnet		98.73 228	98.53 235	99.35 210	99.72 124	98.67 247	98.34 283	94.65 370	98.35 255	99.79 81	99.68 148	98.03 204	99.93 81	98.28 172	99.92 90	99.44 211

RPSCF		99.18 156	99.02 171	99.64 114	99.83 53	99.85 19	99.44 101	99.82 52	98.33 260	99.50 196	99.78 87	97.90 213	99.65 344	96.78 286	99.83 154	99.44 211

原ACMM1				99.37 204	99.47 233	98.87 236		99.27 286	96.74 333	98.26 333	99.32 281	97.93 212	99.82 259	95.96 325	99.38 292	99.43 217

test222					99.51 211	99.08 215	97.83 329	99.29 282	95.21 352	98.68 315	99.31 283	97.28 247			99.38 292	99.43 217

XVG-OURS		99.21 147	99.06 159	99.65 107	99.82 60	99.62 105	97.87 327	99.74 92	98.36 250	99.66 135	99.68 148	99.71 13	99.90 141	96.84 284	99.88 118	99.43 217

CSCG		99.37 104	99.29 112	99.60 136	99.71 127	99.46 137	99.43 103	99.85 39	98.79 208	99.41 218	99.60 198	98.92 95	99.92 101	98.02 192	99.92 90	99.43 217

TinyColmap		98.97 197	98.93 190	99.07 259	99.46 237	98.19 280	97.75 331	99.75 87	98.79 208	99.54 182	99.70 131	98.97 91	99.62 348	96.63 296	99.83 154	99.41 221

Anonymous202405211		98.75 224	98.46 238	99.63 121	99.34 270	99.66 93	99.47 95	97.65 355	99.28 139	99.56 175	99.50 235	93.15 311	99.84 235	98.62 154	99.58 258	99.40 222

XVG-ACMP-BASELINE		99.23 134	99.10 150	99.63 121	99.82 60	99.58 119	98.83 235	99.72 105	98.36 250	99.60 160	99.71 124	98.92 95	99.91 123	97.08 271	99.84 146	99.40 222

MS-PatchMatch		99.00 193	98.97 186	99.09 255	99.11 318	98.19 280	98.76 249	99.33 271	98.49 238	99.44 206	99.58 205	98.21 191	99.69 319	98.20 179	99.62 243	99.39 224

FMVSNet3		98.80 220	98.63 222	99.32 218	99.13 311	98.72 245	99.10 192	99.48 232	99.23 148	99.62 151	99.64 164	92.57 317	99.86 204	98.96 125	99.90 100	99.39 224

ambc				99.20 240	99.35 262	98.53 259	99.17 170	99.46 238		99.67 131	99.80 70	98.46 161	99.70 313	97.92 202	99.70 218	99.38 226

FMVSNet5		97.80 289	97.25 305	99.42 184	98.83 345	98.97 223	99.38 109	99.80 63	98.87 198	99.25 249	99.69 137	80.60 375	99.91 123	98.96 125	99.90 100	99.38 226

PAPM_NR		98.36 264	98.04 272	99.33 214	99.48 227	98.93 229	98.79 246	99.28 285	97.54 302	98.56 324	98.57 358	97.12 255	99.69 319	94.09 354	98.90 328	99.38 226

EPNet_dtu		97.62 297	97.79 291	97.11 343	96.67 376	92.31 366	98.51 272	98.04 349	99.24 146	95.77 370	99.47 246	93.78 305	99.66 338	98.98 121	99.62 243	99.37 229
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PHI-MVS		99.11 172	98.95 189	99.59 138	99.13 311	99.59 115	99.17 170	99.65 140	97.88 287	99.25 249	99.46 249	98.97 91	99.80 280	97.26 261	99.82 163	99.37 229

PLC	97.35 16	98.36 264	97.99 275	99.48 169	99.32 277	99.24 192	98.50 273	99.51 223	95.19 353	98.58 322	98.96 339	96.95 260	99.83 250	95.63 333	99.25 308	99.37 229
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tttt0517		97.62 297	97.20 306	98.90 281	99.76 101	97.40 316	99.48 92	94.36 371	99.06 177	99.70 120	99.49 239	84.55 370	99.94 64	98.73 147	99.65 238	99.36 232

pmmvs-eth3d		99.48 72	99.47 71	99.51 162	99.77 97	99.41 155	98.81 240	99.66 131	99.42 126	99.75 99	99.66 157	99.20 61	99.76 296	98.98 121	99.99 13	99.36 232

PVSNet_0	95.53 19	95.85 335	95.31 337	97.47 333	98.78 352	93.48 362	95.72 368	99.40 256	96.18 340	97.37 359	97.73 373	95.73 286	99.58 355	95.49 336	81.40 375	99.36 232

lupinMVS		98.96 200	98.87 200	99.24 236	99.57 185	98.40 268	98.12 300	99.18 304	98.28 263	99.63 142	99.13 311	98.02 205	99.97 22	98.22 177	99.69 222	99.35 235

Vis-MVSNet (Re-imp)		98.77 222	98.58 228	99.34 211	99.78 89	98.88 234	99.61 66	99.56 193	99.11 172	99.24 252	99.56 217	93.00 315	99.78 286	97.43 249	99.89 109	99.35 235

GA-MVS		97.99 285	97.68 295	98.93 272	99.52 209	98.04 293	97.19 356	99.05 314	98.32 261	98.81 303	98.97 337	89.89 350	99.41 367	98.33 169	99.05 318	99.34 237

CANet		99.11 172	99.05 163	99.28 226	98.83 345	98.56 258	98.71 254	99.41 249	99.25 144	99.23 253	99.22 303	97.66 233	99.94 64	99.19 94	99.97 42	99.33 238

Patchmtry		98.78 221	98.54 233	99.49 165	98.89 340	99.19 201	99.32 122	99.67 127	99.65 83	99.72 112	99.79 80	91.87 325	99.95 51	98.00 196	99.97 42	99.33 238

PAPR		97.56 300	97.07 308	99.04 262	98.80 349	98.11 287	97.63 336	99.25 292	94.56 360	98.02 346	98.25 368	97.43 240	99.68 329	90.90 365	98.74 337	99.33 238

testf1		99.63 45	99.60 48	99.72 80	99.94 16	99.95 2	99.47 95	99.89 26	99.43 122	99.88 47	99.80 70	99.26 55	99.90 141	98.81 138	99.88 118	99.32 241

APD_test2		99.63 45	99.60 48	99.72 80	99.94 16	99.95 2	99.47 95	99.89 26	99.43 122	99.88 47	99.80 70	99.26 55	99.90 141	98.81 138	99.88 118	99.32 241

CHOSEN 280x420		98.41 260	98.41 243	98.40 307	99.34 270	95.89 345	96.94 362	99.44 243	98.80 207	99.25 249	99.52 230	93.51 309	99.98 10	98.94 130	99.98 30	99.32 241

baseline1		97.73 292	97.33 302	98.96 267	99.30 282	97.73 307	99.40 105	98.42 342	99.33 134	99.46 204	99.21 305	91.18 331	99.82 259	98.35 167	91.26 374	99.32 241

TAPA-MVS	97.92 13	98.03 282	97.55 298	99.46 173	99.47 233	99.44 144	98.50 273	99.62 151	86.79 369	99.07 278	99.26 294	98.26 185	99.62 348	97.28 258	99.73 207	99.31 245
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
LCM-MVSNet-Re		99.28 123	99.15 132	99.67 95	99.33 275	99.76 58	99.34 118	99.97 10	98.93 190	99.91 31	99.79 80	98.68 125	99.93 81	96.80 285	99.56 260	99.30 246

TSAR-MVS + GP.		99.12 169	99.04 168	99.38 201	99.34 270	99.16 203	98.15 296	99.29 282	98.18 270	99.63 142	99.62 181	99.18 63	99.68 329	98.20 179	99.74 202	99.30 246

PVSNet_Blended		98.70 231	98.59 225	99.02 263	99.54 198	97.99 294	97.58 339	99.82 52	95.70 346	99.34 231	98.98 335	98.52 154	99.77 294	97.98 197	99.83 154	99.30 246

MVS_0304		98.88 212	98.71 215	99.39 197	98.85 343	98.91 232	99.45 98	99.30 280	98.56 228	97.26 362	99.68 148	96.18 281	99.96 41	99.17 99	99.94 78	99.29 249

MVS_111021_LR		99.13 167	99.03 170	99.42 184	99.58 175	99.32 175	97.91 325	99.73 96	98.68 218	99.31 240	99.48 242	99.09 74	99.66 338	97.70 228	99.77 191	99.29 249

miper_lstm_enhance		98.65 234	98.60 223	98.82 290	99.20 301	97.33 318	97.78 330	99.66 131	99.01 180	99.59 163	99.50 235	94.62 296	99.85 221	98.12 188	99.90 100	99.26 251

MVS		95.72 337	94.63 341	98.99 264	98.56 360	97.98 300	99.30 130	98.86 320	72.71 374	97.30 360	99.08 320	98.34 178	99.74 302	89.21 366	98.33 348	99.26 251

MSLP-MVS++		99.05 181	99.09 151	98.91 275	99.21 298	98.36 272	98.82 239	99.47 235	98.85 200	98.90 293	99.56 217	98.78 112	99.09 370	98.57 156	99.68 227	99.26 251

D2MVS		99.22 142	99.19 126	99.29 224	99.69 139	98.74 244	98.81 240	99.41 249	98.55 230	99.68 126	99.69 137	98.13 197	99.87 186	98.82 136	99.98 30	99.24 254

test_yl		98.25 271	97.95 279	99.13 250	99.17 306	98.47 262	99.00 212	98.67 331	98.97 183	99.22 256	99.02 330	91.31 329	99.69 319	97.26 261	98.93 324	99.24 254

DCV-MVSNet		98.25 271	97.95 279	99.13 250	99.17 306	98.47 262	99.00 212	98.67 331	98.97 183	99.22 256	99.02 330	91.31 329	99.69 319	97.26 261	98.93 324	99.24 254

DPM-MVS		98.28 269	97.94 283	99.32 218	99.36 260	99.11 208	97.31 352	98.78 325	96.88 328	98.84 300	99.11 318	97.77 223	99.61 352	94.03 356	99.36 295	99.23 257

CLD-MVS		98.76 223	98.57 229	99.33 214	99.57 185	98.97 223	97.53 342	99.55 199	96.41 335	99.27 247	99.13 311	99.07 79	99.78 286	96.73 289	99.89 109	99.23 257
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
pmmvs4		99.13 167	99.06 159	99.36 208	99.57 185	99.10 213	98.01 312	99.25 292	98.78 210	99.58 165	99.44 253	98.24 186	99.76 296	98.74 146	99.93 86	99.22 259

OMC-MVS		98.90 208	98.72 214	99.44 178	99.39 252	99.42 151	98.58 260	99.64 146	97.31 315	99.44 206	99.62 181	98.59 139	99.69 319	96.17 317	99.79 182	99.22 259

EGC-MVSNET		89.05 342	85.52 345	99.64 114	99.89 33	99.78 47	99.56 79	99.52 219	24.19 376	49.96 377	99.83 55	99.15 66	99.92 101	97.71 225	99.85 141	99.21 261

eth_miper_zixun_eth		98.68 232	98.71 215	98.60 299	99.10 319	96.84 331	97.52 344	99.54 205	98.94 187	99.58 165	99.48 242	96.25 279	99.76 296	98.01 195	99.93 86	99.21 261

c3_l		98.72 229	98.71 215	98.72 295	99.12 313	97.22 321	97.68 335	99.56 193	98.90 194	99.54 182	99.48 242	96.37 276	99.73 305	97.88 206	99.88 118	99.21 261

CMPMVS	77.52 23	98.50 250	98.19 265	99.41 191	98.33 365	99.56 122	99.01 210	99.59 176	95.44 348	99.57 168	99.80 70	95.64 287	99.46 366	96.47 304	99.92 90	99.21 261
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Effi-MVS+		99.06 178	98.97 186	99.34 211	99.31 278	98.98 221	98.31 286	99.91 21	98.81 205	98.79 306	98.94 341	99.14 69	99.84 235	98.79 140	98.74 337	99.20 265

DELS-MVS		99.34 114	99.30 107	99.48 169	99.51 211	99.36 167	98.12 300	99.53 214	99.36 131	99.41 218	99.61 190	99.22 59	99.87 186	99.21 90	99.68 227	99.20 265
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
DROMVSNet		99.69 28	99.69 28	99.68 92	99.71 127	99.91 4	99.76 18	99.96 14	99.86 28	99.51 194	99.39 264	99.57 25	99.93 81	99.64 31	99.86 137	99.20 265

CANet_DTU		98.91 206	98.85 202	99.09 255	98.79 350	98.13 284	98.18 293	99.31 277	99.48 107	98.86 298	99.51 232	96.56 266	99.95 51	99.05 115	99.95 67	99.19 268

alignmvs		98.28 269	97.96 278	99.25 234	99.12 313	98.93 229	99.03 207	98.42 342	99.64 85	98.72 312	97.85 372	90.86 338	99.62 348	98.88 132	99.13 313	99.19 268

DIV-MVS_self_test		98.54 245	98.42 242	98.92 273	99.03 327	97.80 305	97.46 346	99.59 176	98.90 194	99.60 160	99.46 249	93.87 302	99.78 286	97.97 199	99.89 109	99.18 270

MSDG		99.08 176	98.98 185	99.37 204	99.60 166	99.13 206	97.54 340	99.74 92	98.84 203	99.53 187	99.55 224	99.10 72	99.79 283	97.07 272	99.86 137	99.18 270

cl____		98.54 245	98.41 243	98.92 273	99.03 327	97.80 305	97.46 346	99.59 176	98.90 194	99.60 160	99.46 249	93.85 303	99.78 286	97.97 199	99.89 109	99.17 272

PM-MVS		99.36 107	99.29 112	99.58 141	99.83 53	99.66 93	98.95 223	99.86 35	98.85 200	99.81 73	99.73 110	98.40 171	99.92 101	98.36 166	99.83 154	99.17 272

thisisatest0530		97.45 302	96.95 312	98.94 269	99.68 147	97.73 307	99.09 196	94.19 373	98.61 225	99.56 175	99.30 285	84.30 371	99.93 81	98.27 173	99.54 269	99.16 274

PatchmatchNet		97.65 296	97.80 289	97.18 341	98.82 348	92.49 365	99.17 170	98.39 344	98.12 271	98.79 306	99.58 205	90.71 340	99.89 158	97.23 265	99.41 289	99.16 274
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tfpnnormal		99.43 86	99.38 88	99.60 136	99.87 42	99.75 62	99.59 72	99.78 74	99.71 63	99.90 37	99.69 137	98.85 103	99.90 141	97.25 264	99.78 187	99.15 276

CS-MVS-test		99.68 31	99.70 24	99.64 114	99.57 185	99.83 29	99.78 11	99.97 10	99.92 11	99.50 196	99.38 266	99.57 25	99.95 51	99.69 26	99.90 100	99.15 276

mvs_anonymous		99.28 123	99.39 86	98.94 269	99.19 303	97.81 304	99.02 208	99.55 199	99.78 51	99.85 58	99.80 70	98.24 186	99.86 204	99.57 39	99.50 277	99.15 276

ab-mvs		99.33 117	99.28 114	99.47 171	99.57 185	99.39 158	99.78 11	99.43 246	98.87 198	99.57 168	99.82 62	98.06 202	99.87 186	98.69 151	99.73 207	99.15 276

MIMVSNet		98.43 258	98.20 262	99.11 252	99.53 204	98.38 271	99.58 74	98.61 333	98.96 185	99.33 233	99.76 98	90.92 335	99.81 274	97.38 252	99.76 193	99.15 276

GSMVS																99.14 281

sam_mvs1												90.81 339				99.14 281

SCA		98.11 278	98.36 248	97.36 336	99.20 301	92.99 363	98.17 295	98.49 340	98.24 265	99.10 274	99.57 214	96.01 284	99.94 64	96.86 281	99.62 243	99.14 281

LS3D		99.24 133	99.11 142	99.61 133	98.38 363	99.79 44	99.57 77	99.68 123	99.61 91	99.15 266	99.71 124	98.70 123	99.91 123	97.54 242	99.68 227	99.13 284

Patchmatch-RL test		98.60 237	98.36 248	99.33 214	99.77 97	99.07 216	98.27 288	99.87 32	98.91 193	99.74 107	99.72 117	90.57 342	99.79 283	98.55 157	99.85 141	99.11 285

test_0402		99.22 142	99.14 133	99.45 176	99.79 82	99.43 148	99.28 138	99.68 123	99.54 101	99.40 223	99.56 217	99.07 79	99.82 259	96.01 321	99.96 56	99.11 285

APD_test1		99.36 107	99.28 114	99.61 133	99.89 33	99.89 10	99.32 122	99.74 92	99.18 155	99.69 123	99.75 103	98.41 167	99.84 235	97.85 212	99.70 218	99.10 287

MVS_Test		99.28 123	99.31 102	99.19 241	99.35 262	98.79 240	99.36 116	99.49 231	99.17 160	99.21 258	99.67 153	98.78 112	99.66 338	99.09 112	99.66 236	99.10 287

AdaColmap		98.60 237	98.35 250	99.38 201	99.12 313	99.22 195	98.67 255	99.42 248	97.84 291	98.81 303	99.27 291	97.32 246	99.81 274	95.14 342	99.53 271	99.10 287

FPMVS		96.32 326	95.50 333	98.79 291	99.60 166	98.17 283	98.46 279	98.80 324	97.16 322	96.28 366	99.63 174	82.19 372	99.09 370	88.45 368	98.89 329	99.10 287

Patchmatch-test		98.10 279	97.98 277	98.48 304	99.27 289	96.48 335	99.40 105	99.07 311	98.81 205	99.23 253	99.57 214	90.11 347	99.87 186	96.69 290	99.64 240	99.09 291

tpm		97.15 308	96.95 312	97.75 328	98.91 336	94.24 357	99.32 122	97.96 351	97.71 295	98.29 332	99.32 281	86.72 365	99.92 101	98.10 190	96.24 371	99.09 291

PMMVS		98.49 252	98.29 256	99.11 252	98.96 334	98.42 267	97.54 340	99.32 273	97.53 303	98.47 328	98.15 369	97.88 215	99.82 259	97.46 247	99.24 310	99.09 291

cl22		97.56 300	97.28 303	98.40 307	98.37 364	96.75 332	97.24 355	99.37 264	97.31 315	99.41 218	99.22 303	87.30 357	99.37 368	97.70 228	99.62 243	99.08 294

ADS-MVSNet2		97.78 290	97.66 297	98.12 319	99.14 309	95.36 349	99.22 157	98.75 326	96.97 326	98.25 334	99.64 164	90.90 336	99.94 64	96.51 301	99.56 260	99.08 294

ADS-MVSNet		97.72 295	97.67 296	97.86 324	99.14 309	94.65 355	99.22 157	98.86 320	96.97 326	98.25 334	99.64 164	90.90 336	99.84 235	96.51 301	99.56 260	99.08 294

pmmvs3		98.08 280	97.80 289	98.91 275	99.41 250	97.69 309	97.87 327	99.66 131	95.87 342	99.50 196	99.51 232	90.35 344	99.97 22	98.55 157	99.47 281	99.08 294

PVSNet	97.47 15	98.42 259	98.44 240	98.35 309	99.46 237	96.26 338	96.70 365	99.34 270	97.68 296	99.00 282	99.13 311	97.40 241	99.72 307	97.59 240	99.68 227	99.08 294

MVS-HIRNet		97.86 286	98.22 260	96.76 345	99.28 287	91.53 371	98.38 282	92.60 375	99.13 168	99.31 240	99.96 12	97.18 254	99.68 329	98.34 168	99.83 154	99.07 299

PMVS	92.94 21	98.82 218	98.81 208	98.85 283	99.84 49	97.99 294	99.20 160	99.47 235	99.71 63	99.42 212	99.82 62	98.09 199	99.47 364	93.88 358	99.85 141	99.07 299
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		99.57 56	99.59 50	99.49 165	99.98 3	99.71 76	99.72 29	99.84 45	99.81 43	99.94 21	99.78 87	98.91 97	99.71 311	98.41 163	99.95 67	99.05 301
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
canonicalmvs		99.02 187	99.00 177	99.09 255	99.10 319	98.70 246	99.61 66	99.66 131	99.63 87	98.64 317	97.65 374	99.04 83	99.54 357	98.79 140	98.92 326	99.04 302

hse-mvs2		98.52 247	98.30 255	99.16 244	99.29 284	98.60 257	98.77 248	99.02 315	99.68 73	99.32 236	99.04 325	92.50 320	99.85 221	99.24 87	97.87 360	99.03 303

CL-MVSNet_self_test		98.71 230	98.56 232	99.15 246	99.22 296	98.66 250	97.14 357	99.51 223	98.09 274	99.54 182	99.27 291	96.87 262	99.74 302	98.43 162	98.96 323	99.03 303

AUN-MVS		97.82 288	97.38 301	99.14 249	99.27 289	98.53 259	98.72 252	99.02 315	98.10 272	97.18 364	99.03 329	89.26 352	99.85 221	97.94 201	97.91 358	99.03 303

MDTV_nov1_ep13_2view						91.44 372	99.14 178		97.37 312	99.21 258		91.78 327		96.75 287		99.03 303

ITE_SJBPF				99.38 201	99.63 159	99.44 144		99.73 96	98.56 228	99.33 233	99.53 228	98.88 101	99.68 329	96.01 321	99.65 238	99.02 307

UnsupCasMVSNet_bld		98.55 244	98.27 257	99.40 193	99.56 196	99.37 163	97.97 319	99.68 123	97.49 306	99.08 275	99.35 277	95.41 290	99.82 259	97.70 228	98.19 353	99.01 308

miper_ehance_all_eth		98.59 240	98.59 225	98.59 300	98.98 333	97.07 325	97.49 345	99.52 219	98.50 236	99.52 189	99.37 268	96.41 274	99.71 311	97.86 210	99.62 243	99.00 309

CS-MVS		99.67 37	99.70 24	99.58 141	99.53 204	99.84 24	99.79 10	99.96 14	99.90 13	99.61 157	99.41 256	99.51 30	99.95 51	99.66 28	99.89 109	98.96 310

CNLPA		98.57 242	98.34 251	99.28 226	99.18 305	99.10 213	98.34 283	99.41 249	98.48 239	98.52 325	98.98 335	97.05 257	99.78 286	95.59 334	99.50 277	98.96 310

new_pmnet		98.88 212	98.89 198	98.84 285	99.70 135	97.62 310	98.15 296	99.50 227	97.98 280	99.62 151	99.54 226	98.15 196	99.94 64	97.55 241	99.84 146	98.95 312

PCF-MVS	96.03 18	96.73 318	95.86 329	99.33 214	99.44 241	99.16 203	96.87 363	99.44 243	86.58 370	98.95 285	99.40 260	94.38 298	99.88 172	87.93 369	99.80 177	98.95 312
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PatchMatch-RL		98.68 232	98.47 237	99.30 223	99.44 241	99.28 181	98.14 298	99.54 205	97.12 324	99.11 272	99.25 296	97.80 221	99.70 313	96.51 301	99.30 301	98.93 314

Fast-Effi-MVS+		99.02 187	98.87 200	99.46 173	99.38 255	99.50 130	99.04 204	99.79 69	97.17 321	98.62 318	98.74 353	99.34 45	99.95 51	98.32 170	99.41 289	98.92 315

ET-MVSNet_ETH3D		96.78 316	96.07 325	98.91 275	99.26 291	97.92 302	97.70 334	96.05 366	97.96 284	92.37 375	98.43 364	87.06 359	99.90 141	98.27 173	97.56 363	98.91 316

EIA-MVS		99.12 169	99.01 174	99.45 176	99.36 260	99.62 105	99.34 118	99.79 69	98.41 244	98.84 300	98.89 345	98.75 117	99.84 235	98.15 187	99.51 275	98.89 317

CostFormer		96.71 319	96.79 318	96.46 351	98.90 337	90.71 376	99.41 104	98.68 329	94.69 359	98.14 342	99.34 280	86.32 367	99.80 280	97.60 239	98.07 357	98.88 318

DP-MVS Recon		98.50 250	98.23 258	99.31 221	99.49 222	99.46 137	98.56 265	99.63 148	94.86 357	98.85 299	99.37 268	97.81 220	99.59 354	96.08 318	99.44 284	98.88 318

test0.0.03 1		97.37 305	96.91 315	98.74 294	97.72 372	97.57 311	97.60 338	97.36 361	98.00 277	99.21 258	98.02 370	90.04 348	99.79 283	98.37 165	95.89 372	98.86 320

BH-untuned		98.22 275	98.09 270	98.58 301	99.38 255	97.24 320	98.55 266	98.98 318	97.81 292	99.20 263	98.76 352	97.01 258	99.65 344	94.83 345	98.33 348	98.86 320

HY-MVS	98.23 9	98.21 276	97.95 279	98.99 264	99.03 327	98.24 275	99.61 66	98.72 327	96.81 331	98.73 311	99.51 232	94.06 300	99.86 204	96.91 278	98.20 351	98.86 320

miper_enhance_ethall		98.03 282	97.94 283	98.32 311	98.27 366	96.43 337	96.95 361	99.41 249	96.37 337	99.43 210	98.96 339	94.74 294	99.69 319	97.71 225	99.62 243	98.83 323

FE-MVS		97.85 287	97.42 300	99.15 246	99.44 241	98.75 242	99.77 14	98.20 348	95.85 343	99.33 233	99.80 70	88.86 353	99.88 172	96.40 306	99.12 314	98.81 324

Effi-MVS+-dtu		99.07 177	98.92 194	99.52 160	98.89 340	99.78 47	99.15 176	99.66 131	99.34 132	98.92 290	99.24 301	97.69 227	99.98 10	98.11 189	99.28 304	98.81 324

EPMVS		96.53 322	96.32 320	97.17 342	98.18 369	92.97 364	99.39 107	89.95 379	98.21 267	98.61 319	99.59 203	86.69 366	99.72 307	96.99 274	99.23 312	98.81 324

FA-MVS(test-final)		98.52 247	98.32 253	99.10 254	99.48 227	98.67 247	99.77 14	98.60 335	97.35 313	99.63 142	99.80 70	93.07 313	99.84 235	97.92 202	99.30 301	98.78 327

MVE	92.54 22	96.66 320	96.11 324	98.31 313	99.68 147	97.55 312	97.94 321	95.60 368	99.37 129	90.68 376	98.70 354	96.56 266	98.61 374	86.94 374	99.55 264	98.77 328
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tpm2		96.35 325	96.22 322	96.73 347	98.88 342	91.75 369	99.21 159	98.51 338	93.27 362	97.89 350	99.21 305	84.83 369	99.70 313	96.04 320	98.18 354	98.75 329

LF4IMVS		99.01 191	98.92 194	99.27 229	99.71 127	99.28 181	98.59 259	99.77 77	98.32 261	99.39 224	99.41 256	98.62 134	99.84 235	96.62 297	99.84 146	98.69 330

thisisatest0515		96.98 312	96.42 319	98.66 298	99.42 249	97.47 313	97.27 353	94.30 372	97.24 317	99.15 266	98.86 347	85.01 368	99.87 186	97.10 270	99.39 291	98.63 331

Fast-Effi-MVS+-dtu		99.20 149	99.12 139	99.43 182	99.25 292	99.69 86	99.05 202	99.82 52	99.50 105	98.97 283	99.05 323	98.98 89	99.98 10	98.20 179	99.24 310	98.62 332

PAPM		95.61 338	94.71 340	98.31 313	99.12 313	96.63 333	96.66 366	98.46 341	90.77 367	96.25 367	98.68 355	93.01 314	99.69 319	81.60 375	97.86 361	98.62 332

JIA-IIPM		98.06 281	97.92 285	98.50 303	98.59 359	97.02 326	98.80 243	98.51 338	99.88 24	97.89 350	99.87 40	91.89 324	99.90 141	98.16 186	97.68 362	98.59 334

dp		96.86 314	97.07 308	96.24 353	98.68 358	90.30 378	99.19 164	98.38 345	97.35 313	98.23 336	99.59 203	87.23 358	99.82 259	96.27 312	98.73 339	98.59 334

OpenMVS	98.12 10	98.23 274	97.89 288	99.26 231	99.19 303	99.26 185	99.65 58	99.69 120	91.33 366	98.14 342	99.77 94	98.28 183	99.96 41	95.41 338	99.55 264	98.58 336

baseline2		96.83 315	96.28 321	98.46 305	99.09 321	96.91 329	98.83 235	93.87 374	97.23 318	96.23 369	98.36 365	88.12 355	99.90 141	96.68 291	98.14 355	98.57 337

TESTMET0.1,1		96.24 328	95.84 330	97.41 335	98.24 367	93.84 360	97.38 348	95.84 367	98.43 241	97.81 354	98.56 359	79.77 376	99.89 158	97.77 217	98.77 333	98.52 338

xiu_mvs_v1_base_debu		99.23 134	99.34 96	98.91 275	99.59 170	98.23 276	98.47 275	99.66 131	99.61 91	99.68 126	98.94 341	99.39 35	99.97 22	99.18 96	99.55 264	98.51 339

xiu_mvs_v1_base		99.23 134	99.34 96	98.91 275	99.59 170	98.23 276	98.47 275	99.66 131	99.61 91	99.68 126	98.94 341	99.39 35	99.97 22	99.18 96	99.55 264	98.51 339

xiu_mvs_v1_base_debi		99.23 134	99.34 96	98.91 275	99.59 170	98.23 276	98.47 275	99.66 131	99.61 91	99.68 126	98.94 341	99.39 35	99.97 22	99.18 96	99.55 264	98.51 339

KD-MVS_2432*1600		95.89 332	95.41 335	97.31 339	94.96 377	93.89 358	97.09 358	99.22 299	97.23 318	98.88 294	99.04 325	79.23 377	99.54 357	96.24 314	96.81 366	98.50 342

miper_refine_blended		95.89 332	95.41 335	97.31 339	94.96 377	93.89 358	97.09 358	99.22 299	97.23 318	98.88 294	99.04 325	79.23 377	99.54 357	96.24 314	96.81 366	98.50 342

CR-MVSNet		98.35 267	98.20 262	98.83 287	99.05 324	98.12 285	99.30 130	99.67 127	97.39 311	99.16 264	99.79 80	91.87 325	99.91 123	98.78 143	98.77 333	98.44 344

RPMNet		98.60 237	98.53 235	98.83 287	99.05 324	98.12 285	99.30 130	99.62 151	99.86 28	99.16 264	99.74 106	92.53 319	99.92 101	98.75 145	98.77 333	98.44 344

tpmrst		97.73 292	98.07 271	96.73 347	98.71 356	92.00 367	99.10 192	98.86 320	98.52 234	98.92 290	99.54 226	91.90 323	99.82 259	98.02 192	99.03 320	98.37 346

test-LLR		97.15 308	96.95 312	97.74 329	98.18 369	95.02 352	97.38 348	96.10 363	98.00 277	97.81 354	98.58 356	90.04 348	99.91 123	97.69 234	98.78 331	98.31 347

test-mter		96.23 329	95.73 331	97.74 329	98.18 369	95.02 352	97.38 348	96.10 363	97.90 286	97.81 354	98.58 356	79.12 379	99.91 123	97.69 234	98.78 331	98.31 347

ETV-MVS		99.18 156	99.18 127	99.16 244	99.34 270	99.28 181	99.12 188	99.79 69	99.48 107	98.93 287	98.55 360	99.40 34	99.93 81	98.51 159	99.52 274	98.28 349

PatchT		98.45 257	98.32 253	98.83 287	98.94 335	98.29 274	99.24 150	98.82 323	99.84 36	99.08 275	99.76 98	91.37 328	99.94 64	98.82 136	99.00 322	98.26 350

xiu_mvs_v2_base		99.02 187	99.11 142	98.77 292	99.37 257	98.09 289	98.13 299	99.51 223	99.47 111	99.42 212	98.54 361	99.38 39	99.97 22	98.83 134	99.33 298	98.24 351

IB-MVS	95.41 20	95.30 339	94.46 343	97.84 325	98.76 354	95.33 350	97.33 351	96.07 365	96.02 341	95.37 373	97.41 376	76.17 381	99.96 41	97.54 242	95.44 373	98.22 352
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
tpm cat1		96.78 316	96.98 311	96.16 354	98.85 343	90.59 377	99.08 199	99.32 273	92.37 363	97.73 358	99.46 249	91.15 332	99.69 319	96.07 319	98.80 330	98.21 353

MAR-MVS		98.24 273	97.92 285	99.19 241	98.78 352	99.65 98	99.17 170	99.14 308	95.36 349	98.04 345	98.81 350	97.47 238	99.72 307	95.47 337	99.06 317	98.21 353
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
PS-MVSNAJ		99.00 193	99.08 153	98.76 293	99.37 257	98.10 288	98.00 314	99.51 223	99.47 111	99.41 218	98.50 363	99.28 51	99.97 22	98.83 134	99.34 297	98.20 355

cascas		96.99 311	96.82 317	97.48 332	97.57 375	95.64 347	96.43 367	99.56 193	91.75 364	97.13 365	97.61 375	95.58 289	98.63 373	96.68 291	99.11 315	98.18 356

BH-w/o		97.20 307	97.01 310	97.76 327	99.08 322	95.69 346	98.03 311	98.52 337	95.76 345	97.96 347	98.02 370	95.62 288	99.47 364	92.82 360	97.25 365	98.12 357

tpmvs		97.39 304	97.69 294	96.52 349	98.41 362	91.76 368	99.30 130	98.94 319	97.74 293	97.85 353	99.55 224	92.40 322	99.73 305	96.25 313	98.73 339	98.06 358

thres600view7		96.60 321	96.16 323	97.93 322	99.63 159	96.09 342	99.18 165	97.57 356	98.77 211	98.72 312	97.32 377	87.04 360	99.72 307	88.57 367	98.62 342	97.98 359

thres400		96.40 323	95.89 327	97.92 323	99.58 175	96.11 340	99.00 212	97.54 359	98.43 241	98.52 325	96.98 380	86.85 362	99.67 334	87.62 370	98.51 345	97.98 359

TR-MVS		97.44 303	97.15 307	98.32 311	98.53 361	97.46 314	98.47 275	97.91 353	96.85 329	98.21 337	98.51 362	96.42 272	99.51 362	92.16 361	97.29 364	97.98 359

1314		98.00 284	97.90 287	98.27 315	98.90 337	97.45 315	99.30 130	99.06 313	94.98 354	97.21 363	99.12 315	98.43 164	99.67 334	95.58 335	98.56 344	97.71 362

E-PMN		97.14 310	97.43 299	96.27 352	98.79 350	91.62 370	95.54 369	99.01 317	99.44 117	98.88 294	99.12 315	92.78 316	99.68 329	94.30 351	99.03 320	97.50 363

gg-mvs-nofinetune		95.87 334	95.17 338	97.97 321	98.19 368	96.95 327	99.69 41	89.23 380	99.89 19	96.24 368	99.94 16	81.19 373	99.51 362	93.99 357	98.20 351	97.44 364

DeepMVS_CX				97.98 320	99.69 139	96.95 327		99.26 289	75.51 373	95.74 371	98.28 367	96.47 270	99.62 348	91.23 364	97.89 359	97.38 365

OpenMVS_ROB	97.31 17	97.36 306	96.84 316	98.89 282	99.29 284	99.45 142	98.87 229	99.48 232	86.54 371	99.44 206	99.74 106	97.34 245	99.86 204	91.61 362	99.28 304	97.37 366

EMVS		96.96 313	97.28 303	95.99 355	98.76 354	91.03 373	95.26 370	98.61 333	99.34 132	98.92 290	98.88 346	93.79 304	99.66 338	92.87 359	99.05 318	97.30 367

thres100view900		96.39 324	96.03 326	97.47 333	99.63 159	95.93 343	99.18 165	97.57 356	98.75 215	98.70 314	97.31 378	87.04 360	99.67 334	87.62 370	98.51 345	96.81 368

tfpn200view9		96.30 327	95.89 327	97.53 331	99.58 175	96.11 340	99.00 212	97.54 359	98.43 241	98.52 325	96.98 380	86.85 362	99.67 334	87.62 370	98.51 345	96.81 368

API-MVS		98.38 263	98.39 245	98.35 309	98.83 345	99.26 185	99.14 178	99.18 304	98.59 226	98.66 316	98.78 351	98.61 136	99.57 356	94.14 353	99.56 260	96.21 370

thres200		96.09 330	95.68 332	97.33 338	99.48 227	96.22 339	98.53 270	97.57 356	98.06 276	98.37 331	96.73 382	86.84 364	99.61 352	86.99 373	98.57 343	96.16 371

GG-mvs-BLEND				97.36 336	97.59 373	96.87 330	99.70 34	88.49 381		94.64 374	97.26 379	80.66 374	99.12 369	91.50 363	96.50 370	96.08 372

wuyk23d		97.58 299	99.13 135	92.93 357	99.69 139	99.49 131	99.52 83	99.77 77	97.97 281	99.96 15	99.79 80	99.84 5	99.94 64	95.85 328	99.82 163	79.36 373

test123		29.31 343	33.05 348	18.08 359	25.93 383	12.24 383	97.53 342	10.93 384	11.78 377	24.21 378	50.08 387	21.04 382	8.60 378	23.51 376	32.43 377	33.39 374

testmvs		28.94 344	33.33 346	15.79 360	26.03 382	9.81 384	96.77 364	15.67 383	11.55 378	23.87 379	50.74 386	19.03 383	8.53 379	23.21 377	33.07 376	29.03 375

test_blank		8.33 347	11.11 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	100.00 1	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uanet_test		8.33 347	11.11 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	100.00 1	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

DCPMVS		8.33 347	11.11 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	100.00 1	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

cdsmvs_eth3d_5k		24.88 345	33.17 347	0.00 361	0.00 384	0.00 385	0.00 372	99.62 151	0.00 379	0.00 380	99.13 311	99.82 6	0.00 380	0.00 378	0.00 378	0.00 376

pcd_1.5k_mvsjas		16.61 346	22.14 349	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	100.00 1	99.28 51	0.00 380	0.00 378	0.00 378	0.00 376

sosnet-low-res		8.33 347	11.11 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	100.00 1	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

sosnet		8.33 347	11.11 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	100.00 1	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uncertanet		8.33 347	11.11 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	100.00 1	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

Regformer		8.33 347	11.11 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	100.00 1	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

ab-mvs-re		8.26 355	11.02 358	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	99.16 309	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uanet		8.33 347	11.11 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	100.00 1	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

FOURS1					99.83 53	99.89 10	99.74 23	99.71 108	99.69 71	99.63 142

test_one_0601					99.63 159	99.76 58		99.55 199	99.23 148	99.31 240	99.61 190	98.59 139

eth-test2					0.00 384

eth-test					0.00 384

ZD-MVS					99.43 244	99.61 111		99.43 246	96.38 336	99.11 272	99.07 321	97.86 216	99.92 101	94.04 355	99.49 279

test_241102_ONE					99.69 139	99.82 35		99.54 205	99.12 171	99.82 66	99.49 239	98.91 97	99.52 361

9.14			98.64 220		99.45 240		98.81 240	99.60 170	97.52 304	99.28 246	99.56 217	98.53 151	99.83 250	95.36 340	99.64 240

save fliter					99.53 204	99.25 188	98.29 287	99.38 263	99.07 175

test0726					99.69 139	99.80 42	99.24 150	99.57 188	99.16 162	99.73 111	99.65 162	98.35 175

test_part2					99.62 163	99.67 91				99.55 180

sam_mvs												90.52 343

MTGPA								99.53 214

test_post1							99.14 178				51.63 385	89.54 351	99.82 259	96.86 281

test_post											52.41 384	90.25 345	99.86 204

patchmatchnet-post											99.62 181	90.58 341	99.94 64

MTMP							99.09 196	98.59 336

gm-plane-assit					97.59 373	89.02 380			93.47 361		98.30 366		99.84 235	96.38 308

TEST9					99.35 262	99.35 170	98.11 302	99.41 249	94.83 358	97.92 348	98.99 332	98.02 205	99.85 221

test_8					99.34 270	99.31 176	98.08 306	99.40 256	94.90 355	97.87 352	98.97 337	98.02 205	99.84 235

agg_prior					99.35 262	99.36 167		99.39 259		97.76 357			99.85 221

test_prior4						99.19 201	98.00 314

test_prior2							97.95 320		97.87 288	98.05 344	99.05 323	97.90 213		95.99 323	99.49 279

旧先验2							97.94 321		95.33 350	98.94 286			99.88 172	96.75 287

新几何2							98.04 310

原ACMM2							97.92 323

testdata2													99.89 158	95.99 323

segment_acmp												98.37 173

testdata1							97.72 332		97.86 290

plane_prior7					99.58 175	99.38 160

plane_prior6					99.47 233	99.26 185						97.24 248

plane_prior4											99.25 296

plane_prior3						99.31 176			98.36 250	99.14 268

plane_prior2							98.80 243		98.94 187

plane_prior1					99.51 211

plane_prior						99.24 192	98.42 280		97.87 288						99.71 216

n2								0.00 385

nn								0.00 385

door-mid								99.83 47

test11								99.29 282

door								99.77 77

HQP5-MVS						98.94 226

HQP-NCC					99.31 278		97.98 316		97.45 307	98.15 338

ACMP_Plane					99.31 278		97.98 316		97.45 307	98.15 338

BP-MVS														94.73 346

HQP3-MVS								99.37 264							99.67 233

HQP2-MVS												96.67 264

NP-MVS					99.40 251	99.13 206					98.83 348

MDTV_nov1_ep13			97.73 293		98.70 357	90.83 374	99.15 176	98.02 350	98.51 235	98.82 302	99.61 190	90.98 334	99.66 338	96.89 280	98.92 326

ACMMP++_ref															99.94 78

ACMMP++															99.79 182

Test By Simon												98.41 167

High-resolution multi-view benchmark