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.

Casviewmamba		86.09 56	86.04 64	86.24 67	88.17 201	68.05 149	89.44 104	92.79 71	80.30 10	84.71 89	92.78 104	72.83 52	95.05 101	82.81 95	90.57 123	95.62 1

MM		89.16 7	89.23 9	88.97 4	90.79 104	73.65 10	92.66 28	91.17 155	86.57 1	87.39 60	94.97 26	71.70 67	97.68 1	92.19 1	95.63 32	95.57 2

casdiffmvs_mvg		85.99 60	86.09 63	85.70 83	87.65 236	67.22 183	88.69 144	93.04 48	79.64 22	85.33 79	92.54 107	73.30 42	94.50 128	83.49 85	91.14 112	95.37 3
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
dcpmvs_2		85.63 71	86.15 61	84.06 170	91.71 86	64.94 245	86.47 239	91.87 125	73.63 185	86.60 70	93.02 95	76.57 20	91.87 273	83.36 86	92.15 92	95.35 4

casdiffmvs		85.11 85	85.14 85	85.01 109	87.20 260	65.77 215	87.75 184	92.83 67	77.84 45	84.36 103	92.38 110	72.15 60	93.93 154	81.27 113	90.48 125	95.33 5
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.5_n_9		87.39 33	87.95 23	85.70 83	89.48 140	67.88 156	88.59 148	89.05 243	80.19 13	90.70 21	95.40 18	74.56 30	93.92 155	91.54 2	92.07 94	95.31 6

3Dnovator+	77.84 4	85.48 75	84.47 95	88.51 7	91.08 95	73.49 16	93.18 16	93.78 24	80.79 8	76.66 269	93.37 85	60.40 249	96.75 31	77.20 171	93.73 70	95.29 7

BP-MVS1		84.32 94	83.71 111	86.17 70	87.84 220	67.85 157	89.38 110	89.64 210	77.73 47	83.98 111	92.12 122	56.89 279	95.43 79	84.03 82	91.75 101	95.24 8

hybridcas		85.11 85	85.18 84	84.90 117	87.47 248	65.68 216	88.53 152	92.38 89	77.91 43	84.27 104	92.48 108	72.19 59	93.88 160	80.37 123	90.97 115	95.15 9

MGCNet		87.69 24	87.55 29	88.12 13	89.45 141	71.76 54	91.47 57	89.54 213	82.14 3	86.65 69	94.28 47	68.28 125	97.46 6	90.81 6	95.31 38	95.15 9

CS-MVS		86.69 44	86.95 42	85.90 80	90.76 105	67.57 167	92.83 22	93.30 39	79.67 20	84.57 97	92.27 111	71.47 70	95.02 103	84.24 79	93.46 73	95.13 11

TSAR-MVS + MP.		88.02 21	88.11 20	87.72 33	93.68 48	72.13 48	91.41 58	92.35 91	74.62 157	88.90 35	93.85 72	75.75 25	96.00 61	87.80 44	94.63 54	95.04 12
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
baseline		84.93 89	84.98 86	84.80 122	87.30 258	65.39 225	87.30 205	92.88 64	77.62 49	84.04 110	92.26 112	71.81 64	93.96 148	81.31 111	90.30 128	95.03 13

casdiffseed414692147		83.62 120	83.02 126	85.40 93	87.31 257	67.50 170	88.70 143	91.72 134	76.97 75	82.77 142	91.72 134	66.85 141	93.71 170	73.06 224	88.12 176	94.98 14

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 32	71.25 66	95.06 1	94.23 6	78.38 39	92.78 5	95.74 9	82.45 3	97.49 4	89.42 19	96.68 2	94.95 15

PC_three_1452									68.21 326	92.02 15	94.00 64	82.09 5	95.98 63	84.58 73	96.68 2	94.95 15

IS-MVSNet		83.15 134	82.81 131	84.18 159	89.94 125	63.30 295	91.59 51	88.46 272	79.04 31	79.49 202	92.16 119	65.10 168	94.28 134	67.71 283	91.86 100	94.95 15

SteuartSystems-ACMMP		88.72 14	88.86 14	88.32 9	92.14 80	72.96 25	93.73 5	93.67 26	80.19 13	88.10 45	94.80 28	73.76 40	97.11 18	87.51 47	95.82 25	94.90 18
Skip Steuart: Steuart Systems R&D Blog.
SED-MVS		90.08 2	90.85 2	87.77 28	95.30 2	70.98 74	93.57 8	94.06 15	77.24 65	93.10 1	95.72 11	82.99 1	97.44 7	89.07 25	96.63 4	94.88 19

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 62	82.45 3	96.87 25	83.77 84	96.48 8	94.88 19

SMA-MVS		89.08 9	89.23 9	88.61 6	94.25 36	73.73 9	92.40 29	93.63 27	74.77 153	92.29 8	95.97 3	74.28 35	97.24 15	88.58 34	96.91 1	94.87 21
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
test2506		77.30 291	76.49 286	79.74 326	90.08 118	52.02 455	87.86 182	63.10 500	74.88 149	80.16 194	92.79 102	38.29 460	92.35 251	68.74 276	92.50 86	94.86 22

ECVR-MVS		79.61 224	79.26 217	80.67 296	90.08 118	54.69 436	87.89 180	77.44 451	74.88 149	80.27 191	92.79 102	48.96 379	92.45 245	68.55 277	92.50 86	94.86 22

MED-MVS		89.78 3	90.41 3	87.89 24	94.57 18	71.43 61	93.28 12	94.36 3	77.30 62	92.25 10	95.87 4	81.59 7	97.39 11	88.15 40	96.28 16	94.85 24

TestfortrainingZip a		88.83 13	89.21 11	87.68 37	94.57 18	71.25 66	93.28 12	93.91 20	77.30 62	91.13 19	95.87 4	77.62 17	96.95 23	86.12 59	93.07 76	94.85 24

IU-MVS					95.30 2	71.25 66		92.95 62	66.81 339	92.39 7				88.94 28	96.63 4	94.85 24

test1111		79.43 231	79.18 220	80.15 311	89.99 123	53.31 449	87.33 204	77.05 455	75.04 142	80.23 193	92.77 105	48.97 378	92.33 253	68.87 274	92.40 88	94.81 27

SF-MVS		88.46 15	88.74 15	87.64 39	92.78 72	71.95 52	92.40 29	94.74 2	75.71 118	89.16 31	95.10 21	75.65 26	96.19 53	87.07 51	96.01 19	94.79 28

BridgeMVS		86.78 42	86.99 40	86.15 72	91.24 92	67.61 165	90.51 70	92.90 63	77.26 64	87.44 59	91.63 140	71.27 74	96.06 56	85.62 62	95.01 41	94.78 29

E4		84.10 101	83.99 104	84.45 137	87.58 246	64.99 241	86.54 237	92.25 100	76.38 101	83.37 126	92.09 123	69.88 95	93.58 172	79.78 137	88.03 180	94.77 30

viewmacassd2359aftdt		83.76 113	83.66 113	84.07 167	86.59 284	64.56 255	86.88 221	91.82 128	75.72 117	83.34 127	92.15 121	68.24 126	92.88 224	79.05 144	89.15 152	94.77 30

sasdasda		85.91 64	85.87 69	86.04 76	89.84 127	69.44 107	90.45 76	93.00 53	76.70 86	88.01 48	91.23 154	73.28 43	93.91 156	81.50 108	88.80 158	94.77 30

SPE-MVS-test		86.29 54	86.48 51	85.71 82	91.02 97	67.21 184	92.36 34	93.78 24	78.97 34	83.51 125	91.20 158	70.65 83	95.15 93	81.96 105	94.89 46	94.77 30

canonicalmvs		85.91 64	85.87 69	86.04 76	89.84 127	69.44 107	90.45 76	93.00 53	76.70 86	88.01 48	91.23 154	73.28 43	93.91 156	81.50 108	88.80 158	94.77 30

aaatest				87.86 27	94.57 18	71.43 61	93.28 12	94.36 3	75.24 132	92.25 10	95.03 23		97.39 11	88.15 40	95.96 21	94.75 35

aaEdge-Enhanced		88.98 11	89.39 8	87.75 30	94.54 21	71.43 61	91.61 49	94.25 5	76.30 105	90.62 23	95.03 23	78.06 16	97.07 20	88.15 40	95.96 21	94.75 35

E5new		84.22 95	84.12 98	84.51 132	87.60 238	65.36 227	87.45 194	92.31 93	76.51 91	83.53 121	92.26 112	69.25 107	93.50 183	79.88 132	88.26 169	94.69 37

E6new		84.22 95	84.12 98	84.52 130	87.60 238	65.36 227	87.45 194	92.30 95	76.51 91	83.53 121	92.26 112	69.26 105	93.49 185	79.88 132	88.26 169	94.69 37

E6		84.22 95	84.12 98	84.52 130	87.60 238	65.36 227	87.45 194	92.30 95	76.51 91	83.53 121	92.26 112	69.26 105	93.49 185	79.88 132	88.26 169	94.69 37

E5		84.22 95	84.12 98	84.51 132	87.60 238	65.36 227	87.45 194	92.31 93	76.51 91	83.53 121	92.26 112	69.25 107	93.50 183	79.88 132	88.26 169	94.69 37

GDP-MVS		83.52 123	82.64 135	86.16 71	88.14 204	68.45 134	89.13 122	92.69 73	72.82 212	83.71 116	91.86 129	55.69 288	95.35 88	80.03 129	89.74 140	94.69 37

test_0728_THIRD									78.38 39	92.12 12	95.78 7	81.46 8	97.40 9	89.42 19	96.57 7	94.67 42

MSP-MVS		89.51 5	89.91 6	88.30 10	94.28 35	73.46 17	92.90 21	94.11 11	80.27 11	91.35 17	94.16 55	78.35 15	96.77 29	89.59 17	94.22 66	94.67 42
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
RRT-MVS		82.60 148	82.10 149	84.10 161	87.98 214	62.94 309	87.45 194	91.27 151	77.42 58	79.85 197	90.28 192	56.62 282	94.70 121	79.87 136	88.15 175	94.67 42

E2		84.00 104	83.87 105	84.39 140	87.70 233	64.95 242	86.40 244	92.23 101	75.85 114	83.21 128	91.78 131	70.09 90	93.55 177	79.52 141	88.05 178	94.66 45

E3		84.00 104	83.87 105	84.39 140	87.70 233	64.95 242	86.40 244	92.23 101	75.85 114	83.21 128	91.78 131	70.09 90	93.55 177	79.52 141	88.05 178	94.66 45

MGCFI-Net		85.06 88	85.51 76	83.70 189	89.42 142	63.01 302	89.43 105	92.62 81	76.43 96	87.53 56	91.34 152	72.82 53	93.42 193	81.28 112	88.74 161	94.66 45

viewmanbaseed2359cas		83.66 116	83.55 116	84.00 178	86.81 276	64.53 256	86.65 231	91.75 133	74.89 148	83.15 133	91.68 136	68.74 118	92.83 229	79.02 146	89.24 149	94.63 48

alignmvs		85.48 75	85.32 81	85.96 79	89.51 137	69.47 104	89.74 92	92.47 84	76.17 108	87.73 55	91.46 149	70.32 85	93.78 163	81.51 107	88.95 154	94.63 48

viewdifsd2359ckpt09		83.34 129	82.55 138	85.70 83	87.64 237	67.72 162	88.43 154	91.68 137	71.91 227	81.65 160	90.68 177	67.10 139	94.75 117	76.17 186	87.70 187	94.62 50

MP-MVS-pluss		87.67 25	87.72 25	87.54 40	93.64 49	72.04 51	89.80 90	93.50 31	75.17 140	86.34 71	95.29 20	70.86 79	96.00 61	88.78 31	96.04 18	94.58 51
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
DeepPCF-MVS	80.84 1	88.10 16	88.56 17	86.73 60	92.24 79	69.03 112	89.57 99	93.39 36	77.53 55	89.79 27	94.12 57	78.98 13	96.58 41	85.66 60	95.72 28	94.58 51

viewcassd2359sk11		83.89 107	83.74 110	84.34 145	87.76 228	64.91 249	86.30 248	92.22 104	75.47 125	83.04 134	91.52 145	70.15 88	93.53 180	79.26 143	87.96 181	94.57 53

VDD-MVS		83.01 140	82.36 142	84.96 111	91.02 97	66.40 196	88.91 129	88.11 275	77.57 51	84.39 100	93.29 87	52.19 322	93.91 156	77.05 174	88.70 162	94.57 53

NormalMVS		86.29 54	85.88 67	87.52 41	93.26 57	72.47 38	91.65 47	92.19 109	79.31 25	84.39 100	92.18 117	64.64 174	95.53 73	80.70 120	94.65 52	94.56 55

KinetiMVS		83.31 132	82.61 137	85.39 94	87.08 269	67.56 168	88.06 172	91.65 138	77.80 46	82.21 149	91.79 130	57.27 274	94.07 146	77.77 164	89.89 138	94.56 55

VDDNet		81.52 172	80.67 173	84.05 173	90.44 110	64.13 269	89.73 93	85.91 336	71.11 244	83.18 131	93.48 80	50.54 354	93.49 185	73.40 219	88.25 173	94.54 57

E3new		83.78 112	83.60 115	84.31 147	87.76 228	64.89 250	86.24 251	92.20 107	75.15 141	82.87 137	91.23 154	70.11 89	93.52 182	79.05 144	87.79 184	94.51 58

MVSMamba_PlusPlus		85.99 60	85.96 66	86.05 75	91.09 94	67.64 164	89.63 97	92.65 78	72.89 211	84.64 94	91.71 135	71.85 63	96.03 57	84.77 71	94.45 60	94.49 59

APDe-MVS		89.15 8	89.63 7	87.73 31	94.49 23	71.69 55	93.83 4	93.96 18	75.70 120	91.06 20	96.03 2	76.84 19	97.03 21	89.09 21	95.65 31	94.47 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MSC_two_6792asdad				89.16 1	94.34 32	75.53 2		92.99 56					97.53 2	89.67 15	96.44 9	94.41 61

No_MVS				89.16 1	94.34 32	75.53 2		92.99 56					97.53 2	89.67 15	96.44 9	94.41 61

MCST-MVS		87.37 34	87.25 35	87.73 31	94.53 22	72.46 40	89.82 88	93.82 22	73.07 206	84.86 88	92.89 97	76.22 22	96.33 47	84.89 68	95.13 40	94.40 63

fmvsm_s_conf0.5_n_8		86.56 47	87.17 38	84.73 125	87.76 228	65.62 218	89.20 115	92.21 106	79.94 18	89.74 29	94.86 27	68.63 119	94.20 140	90.83 5	91.39 107	94.38 64

CANet		86.45 48	86.10 62	87.51 42	90.09 117	70.94 78	89.70 94	92.59 82	81.78 4	81.32 165	91.43 150	70.34 84	97.23 16	84.26 77	93.36 74	94.37 65

PHI-MVS		86.43 49	86.17 60	87.24 47	90.88 101	70.96 76	92.27 37	94.07 14	72.45 215	85.22 81	91.90 126	69.47 100	96.42 46	83.28 88	95.94 23	94.35 66

viewdifsd2359ckpt07		82.83 143	82.78 134	82.99 223	86.51 286	62.58 313	85.09 285	90.83 168	75.22 134	82.28 146	91.63 140	69.43 101	92.03 262	77.71 165	86.32 213	94.34 67

CNVR-MVS		88.93 12	89.13 13	88.33 8	94.77 12	73.82 8	90.51 70	93.00 53	80.90 7	88.06 46	94.06 60	76.43 21	96.84 26	88.48 37	95.99 20	94.34 67

ZNCC-MVS		87.94 22	87.85 24	88.20 12	94.39 29	73.33 19	93.03 19	93.81 23	76.81 80	85.24 80	94.32 45	71.76 65	96.93 24	85.53 63	95.79 26	94.32 69

balanced_ft_v1		83.98 106	83.64 114	85.03 107	89.76 130	65.86 210	88.31 163	91.71 135	74.41 162	80.41 190	90.82 173	62.90 199	94.90 107	83.04 91	91.37 108	94.32 69

HPM-MVS		87.11 38	86.98 41	87.50 43	93.88 44	72.16 47	92.19 38	93.33 37	76.07 110	83.81 115	93.95 69	69.77 97	96.01 60	85.15 64	94.66 51	94.32 69
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CDPH-MVS		85.76 69	85.29 83	87.17 49	93.49 52	71.08 72	88.58 149	92.42 88	68.32 325	84.61 95	93.48 80	72.32 56	96.15 55	79.00 148	95.43 34	94.28 72

test_241102_TWO								94.06 15	77.24 65	92.78 5	95.72 11	81.26 9	97.44 7	89.07 25	96.58 6	94.26 73

test_0728_SECOND				87.71 35	95.34 1	71.43 61	93.49 10	94.23 6					97.49 4	89.08 22	96.41 12	94.21 74

fmvsm_s_conf0.5_n_10		86.38 52	86.76 46	85.24 98	87.33 254	67.30 178	89.50 101	90.98 160	76.25 107	90.56 24	94.75 30	68.38 122	94.24 139	90.80 7	92.32 91	94.19 75

fmvsm_l_conf0.5_n_3		86.02 58	86.32 54	85.14 101	87.20 260	68.54 132	89.57 99	90.44 179	75.31 131	87.49 57	94.39 43	72.86 50	92.72 232	89.04 27	90.56 124	94.16 76

DeepC-MVS_fast	79.65 3	86.91 41	86.62 50	87.76 29	93.52 51	72.37 43	91.26 59	93.04 48	76.62 88	84.22 105	93.36 86	71.44 71	96.76 30	80.82 117	95.33 37	94.16 76
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EPP-MVSNet		83.40 127	83.02 126	84.57 128	90.13 116	64.47 261	92.32 35	90.73 171	74.45 161	79.35 207	91.10 161	69.05 113	95.12 94	72.78 227	87.22 195	94.13 78

viewdifsd2359ckpt13		82.91 141	82.29 144	84.77 123	86.96 272	66.90 191	87.47 191	91.62 140	72.19 220	81.68 159	90.71 176	66.92 140	93.28 196	75.90 191	87.15 197	94.12 79

NCCC		88.06 18	88.01 22	88.24 11	94.41 27	73.62 11	91.22 62	92.83 67	81.50 5	85.79 75	93.47 82	73.02 48	97.00 22	84.90 66	94.94 44	94.10 80

ACMMP_NAP		88.05 20	88.08 21	87.94 19	93.70 46	73.05 22	90.86 65	93.59 29	76.27 106	88.14 44	95.09 22	71.06 77	96.67 34	87.67 45	96.37 14	94.09 81

XVS		87.18 37	86.91 44	88.00 17	94.42 25	73.33 19	92.78 23	92.99 56	79.14 27	83.67 118	94.17 54	67.45 133	96.60 39	83.06 89	94.50 57	94.07 82

X-MVStestdata		80.37 209	77.83 250	88.00 17	94.42 25	73.33 19	92.78 23	92.99 56	79.14 27	83.67 118	12.47 535	67.45 133	96.60 39	83.06 89	94.50 57	94.07 82

region2R		87.42 31	87.20 37	88.09 14	94.63 14	73.55 13	93.03 19	93.12 47	76.73 85	84.45 98	94.52 33	69.09 110	96.70 32	84.37 76	94.83 49	94.03 84

fmvsm_s_conf0.5_n_4		85.39 79	85.75 72	84.30 149	86.70 280	65.83 211	88.77 137	89.78 202	75.46 126	88.35 39	93.73 75	69.19 109	93.06 216	91.30 3	88.44 167	94.02 85

ACMMPR		87.44 29	87.23 36	88.08 15	94.64 13	73.59 12	93.04 17	93.20 41	76.78 82	84.66 93	94.52 33	68.81 116	96.65 36	84.53 74	94.90 45	94.00 86

fmvsm_s_conf0.1_n_2		83.80 110	83.79 109	83.83 185	85.62 306	64.94 245	87.03 213	86.62 325	74.32 164	87.97 50	94.33 44	60.67 241	92.60 235	89.72 14	87.79 184	93.96 87

test_fmvsmconf_n		85.92 63	86.04 64	85.57 89	85.03 325	69.51 102	89.62 98	90.58 174	73.42 194	87.75 53	94.02 62	72.85 51	93.24 200	90.37 8	90.75 120	93.96 87

DPE-MVS		89.48 6	89.98 5	88.01 16	94.80 11	72.69 31	91.59 51	94.10 13	75.90 113	92.29 8	95.66 13	81.67 6	97.38 13	87.44 49	96.34 15	93.95 89
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_fmvsm_n_1920		85.29 82	85.34 79	85.13 104	86.12 296	69.93 94	88.65 146	90.78 170	69.97 282	88.27 41	93.98 67	71.39 72	91.54 290	88.49 36	90.45 126	93.91 90

test_prior				86.33 65	92.61 76	69.59 100		92.97 61					95.48 76			93.91 90

GST-MVS		87.42 31	87.26 34	87.89 24	94.12 41	72.97 24	92.39 31	93.43 34	76.89 78	84.68 90	93.99 66	70.67 82	96.82 27	84.18 81	95.01 41	93.90 92

test_fmvsmconf0.1_n		85.61 72	85.65 73	85.50 90	82.99 382	69.39 109	89.65 95	90.29 188	73.31 198	87.77 52	94.15 56	71.72 66	93.23 201	90.31 9	90.67 122	93.89 93

fmvsm_l_mol_unc0.5_1		85.55 73	86.37 53	83.10 215	86.42 288	62.98 308	85.89 261	84.85 351	76.48 95	92.88 3	96.67 1	74.16 37	92.46 244	87.11 50	92.90 79	93.85 94

Anonymous202405211		78.25 262	77.01 272	81.99 261	91.03 96	60.67 354	84.77 292	83.90 366	70.65 263	80.00 196	91.20 158	41.08 442	91.43 298	65.21 306	85.26 238	93.85 94

LFMVS		81.82 162	81.23 162	83.57 194	91.89 84	63.43 293	89.84 87	81.85 401	77.04 74	83.21 128	93.10 90	52.26 321	93.43 192	71.98 239	89.95 136	93.85 94

fmvsm_s_conf0.5_n_2		84.04 102	84.11 102	83.81 187	86.17 294	65.00 240	86.96 216	87.28 301	74.35 163	88.25 42	94.23 51	61.82 217	92.60 235	89.85 12	88.09 177	93.84 97

Effi-MVS+		83.62 120	83.08 124	85.24 98	88.38 193	67.45 171	88.89 130	89.15 239	75.50 124	82.27 147	88.28 256	69.61 99	94.45 131	77.81 163	87.84 183	93.84 97

Anonymous20240529		80.19 215	78.89 226	84.10 161	90.60 106	64.75 253	88.95 128	90.90 164	65.97 358	80.59 185	91.17 160	49.97 361	93.73 169	69.16 271	82.70 287	93.81 99

MVS_Test		83.15 134	83.06 125	83.41 201	86.86 273	63.21 297	86.11 255	92.00 117	74.31 165	82.87 137	89.44 222	70.03 92	93.21 203	77.39 170	88.50 166	93.81 99

Elysia		81.53 170	80.16 188	85.62 86	85.51 309	68.25 141	88.84 134	92.19 109	71.31 238	80.50 187	89.83 202	46.89 391	94.82 112	76.85 176	89.57 142	93.80 101

StellarMVS		81.53 170	80.16 188	85.62 86	85.51 309	68.25 141	88.84 134	92.19 109	71.31 238	80.50 187	89.83 202	46.89 391	94.82 112	76.85 176	89.57 142	93.80 101

test_fmvsmconf0.01_n		84.73 92	84.52 94	85.34 95	80.25 427	69.03 112	89.47 102	89.65 209	73.24 202	86.98 65	94.27 48	66.62 144	93.23 201	90.26 10	89.95 136	93.78 103

GeoE		81.71 164	81.01 168	83.80 188	89.51 137	64.45 262	88.97 127	88.73 264	71.27 241	78.63 219	89.76 207	66.32 150	93.20 206	69.89 263	86.02 223	93.74 104

diffmvs		82.10 154	81.88 155	82.76 240	83.00 378	63.78 278	83.68 326	89.76 204	72.94 209	82.02 152	89.85 201	65.96 161	90.79 327	82.38 103	87.30 194	93.71 105
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
lecture		88.09 17	88.59 16	86.58 63	93.26 57	69.77 98	93.70 6	94.16 8	77.13 70	89.76 28	95.52 17	72.26 57	96.27 50	86.87 52	94.65 52	93.70 106

viewmamba		82.38 149	82.11 147	83.19 210	83.30 364	64.26 266	84.62 299	89.16 237	75.24 132	80.97 174	91.10 161	67.12 138	91.63 280	81.36 110	86.13 219	93.67 107

HFP-MVS		87.58 26	87.47 31	87.94 19	94.58 16	73.54 15	93.04 17	93.24 40	76.78 82	84.91 85	94.44 40	70.78 80	96.61 38	84.53 74	94.89 46	93.66 108

VNet		82.21 153	82.41 140	81.62 268	90.82 102	60.93 347	84.47 303	89.78 202	76.36 103	84.07 109	91.88 127	64.71 173	90.26 340	70.68 252	88.89 155	93.66 108

PGM-MVS		86.68 45	86.27 56	87.90 22	94.22 38	73.38 18	90.22 81	93.04 48	75.53 123	83.86 113	94.42 41	67.87 130	96.64 37	82.70 101	94.57 56	93.66 108

DELS-MVS		85.41 78	85.30 82	85.77 81	88.49 187	67.93 155	85.52 276	93.44 33	78.70 35	83.63 120	89.03 230	74.57 29	95.71 68	80.26 128	94.04 67	93.66 108
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
SD-MVS		88.06 18	88.50 18	86.71 61	92.60 77	72.71 29	91.81 46	93.19 42	77.87 44	90.32 25	94.00 64	74.83 28	93.78 163	87.63 46	94.27 65	93.65 112
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
DeepC-MVS	79.81 2	87.08 40	86.88 45	87.69 36	91.16 93	72.32 45	90.31 79	93.94 19	77.12 71	82.82 140	94.23 51	72.13 61	97.09 19	84.83 69	95.37 35	93.65 112
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
patch_mono-2		83.65 117	84.54 92	80.99 288	90.06 122	65.83 211	84.21 314	88.74 262	71.60 233	85.01 82	92.44 109	74.51 31	83.50 431	82.15 104	92.15 92	93.64 114

EIA-MVS		83.31 132	82.80 132	84.82 120	89.59 133	65.59 219	88.21 166	92.68 74	74.66 156	78.96 211	86.42 314	69.06 112	95.26 89	75.54 197	90.09 132	93.62 115

MP-MVS		87.71 23	87.64 26	87.93 21	94.36 31	73.88 6	92.71 27	92.65 78	77.57 51	83.84 114	94.40 42	72.24 58	96.28 49	85.65 61	95.30 39	93.62 115
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
diffmvs_AUTHOR		82.38 149	82.27 145	82.73 242	83.26 366	63.80 276	83.89 321	89.76 204	73.35 197	82.37 145	90.84 171	66.25 151	90.79 327	82.77 96	87.93 182	93.59 117

HPM-MVS_fast		85.35 81	84.95 88	86.57 64	93.69 47	70.58 86	92.15 40	91.62 140	73.89 179	82.67 144	94.09 58	62.60 201	95.54 72	80.93 115	92.93 78	93.57 118

fmvsm_s_conf0.1_n		83.56 122	83.38 120	84.10 161	84.86 327	67.28 179	89.40 109	83.01 383	70.67 259	87.08 63	93.96 68	68.38 122	91.45 297	88.56 35	84.50 249	93.56 119

CSCG		86.41 51	86.19 59	87.07 51	92.91 68	72.48 37	90.81 66	93.56 30	73.95 175	83.16 132	91.07 164	75.94 23	95.19 91	79.94 131	94.38 62	93.55 120

test12				86.80 59	92.63 75	70.70 83		91.79 130		82.71 143		71.67 68	96.16 54		94.50 57	93.54 121

onestephybrid01		82.22 152	81.81 157	83.46 196	83.16 372	64.93 248	84.64 298	89.19 236	73.95 175	81.48 163	90.63 179	66.00 160	91.92 270	80.33 126	86.93 201	93.53 122

APD-MVS_3200maxsize		85.97 62	85.88 67	86.22 69	92.69 74	69.53 101	91.93 42	92.99 56	73.54 190	85.94 72	94.51 36	65.80 162	95.61 69	83.04 91	92.51 85	93.53 122

mvs_anonymous		79.42 232	79.11 221	80.34 304	84.45 338	57.97 386	82.59 352	87.62 293	67.40 336	76.17 285	88.56 249	68.47 121	89.59 354	70.65 253	86.05 222	93.47 124

fmvsm_s_conf0.5_n		83.80 110	83.71 111	84.07 167	86.69 281	67.31 177	89.46 103	83.07 382	71.09 245	86.96 66	93.70 76	69.02 115	91.47 296	88.79 30	84.62 248	93.44 125

fmvsm_s_conf0.5_n_5		85.22 83	85.55 75	84.25 156	86.26 290	67.40 174	89.18 116	89.31 226	72.50 214	88.31 40	93.86 71	69.66 98	91.96 266	89.81 13	91.05 113	93.38 126

mPP-MVS		86.67 46	86.32 54	87.72 33	94.41 27	73.55 13	92.74 25	92.22 104	76.87 79	82.81 141	94.25 50	66.44 148	96.24 51	82.88 94	94.28 64	93.38 126

EPNet		83.72 115	82.92 130	86.14 74	84.22 341	69.48 103	91.05 64	85.27 343	81.30 6	76.83 264	91.65 138	66.09 156	95.56 70	76.00 190	93.85 68	93.38 126
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Vis-MVSNet		83.46 125	82.80 132	85.43 92	90.25 114	68.74 123	90.30 80	90.13 193	76.33 104	80.87 178	92.89 97	61.00 236	94.20 140	72.45 236	90.97 115	93.35 129
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DVP-MVS		89.60 4	90.35 4	87.33 45	95.27 5	71.25 66	93.49 10	92.73 72	77.33 60	92.12 12	95.78 7	80.98 10	97.40 9	89.08 22	96.41 12	93.33 130
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
UniMVSNet_ETH3D		79.10 242	78.24 240	81.70 267	86.85 274	60.24 362	87.28 206	88.79 255	74.25 168	76.84 263	90.53 185	49.48 368	91.56 286	67.98 281	82.15 291	93.29 131

EI-MVSNet-Vis-set		84.19 99	83.81 108	85.31 96	88.18 200	67.85 157	87.66 186	89.73 207	80.05 16	82.95 135	89.59 214	70.74 81	94.82 112	80.66 122	84.72 246	93.28 132

hybridnocas07		81.44 175	81.13 164	82.37 251	82.13 400	63.11 301	83.45 335	88.74 262	72.54 213	80.71 183	90.73 174	65.14 167	90.74 332	80.35 125	86.41 212	93.27 133

MTAPA		87.23 36	87.00 39	87.90 22	94.18 40	74.25 5	86.58 235	92.02 115	79.45 23	85.88 73	94.80 28	68.07 127	96.21 52	86.69 54	95.34 36	93.23 134

CP-MVS		87.11 38	86.92 43	87.68 37	94.20 39	73.86 7	93.98 3	92.82 70	76.62 88	83.68 117	94.46 37	67.93 128	95.95 64	84.20 80	94.39 61	93.23 134

ACMMP		85.89 66	85.39 78	87.38 44	93.59 50	72.63 33	92.74 25	93.18 46	76.78 82	80.73 181	93.82 73	64.33 177	96.29 48	82.67 102	90.69 121	93.23 134
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
SymmetryMVS		85.38 80	84.81 89	87.07 51	91.47 89	72.47 38	91.65 47	88.06 279	79.31 25	84.39 100	92.18 117	64.64 174	95.53 73	80.70 120	90.91 118	93.21 137

fmvsm_s_conf0.1_n_a		83.32 131	82.99 128	84.28 151	83.79 351	68.07 147	89.34 112	82.85 388	69.80 286	87.36 61	94.06 60	68.34 124	91.56 286	87.95 43	83.46 275	93.21 137

fmvsm_s_conf0.5_n_6		85.55 73	86.20 57	83.60 191	87.32 256	65.13 235	88.86 131	91.63 139	75.41 127	88.23 43	93.45 83	68.56 120	92.47 243	89.52 18	92.78 81	93.20 139

hybrid		81.05 182	80.66 174	82.22 255	81.97 402	62.99 306	83.42 336	88.68 265	70.76 257	80.56 186	90.40 188	64.49 176	90.48 336	79.57 140	86.06 221	93.19 140

PAPM_NR		83.02 139	82.41 140	84.82 120	92.47 78	66.37 197	87.93 178	91.80 129	73.82 180	77.32 252	90.66 178	67.90 129	94.90 107	70.37 255	89.48 145	93.19 140

fmvsm_l_conf0.5_n_9		85.84 67	86.63 49	83.46 196	87.12 268	66.01 204	88.56 150	89.43 217	75.59 122	89.32 30	94.32 45	72.89 49	91.21 308	90.11 11	92.33 89	93.16 142

reproduce_model		87.28 35	87.39 33	86.95 55	93.10 63	71.24 71	91.60 50	93.19 42	74.69 154	88.80 36	95.61 14	70.29 86	96.44 45	86.20 58	93.08 75	93.16 142

OMC-MVS		82.69 144	81.97 154	84.85 119	88.75 179	67.42 172	87.98 174	90.87 166	74.92 147	79.72 199	91.65 138	62.19 211	93.96 148	75.26 201	86.42 211	93.16 142

fmvsm_s_conf0.5_n_a		83.63 119	83.41 119	84.28 151	86.14 295	68.12 145	89.43 105	82.87 387	70.27 275	87.27 62	93.80 74	69.09 110	91.58 283	88.21 39	83.65 269	93.14 145

fmvsm_s_conf0.5_n_11		86.06 57	86.75 47	84.00 178	87.78 225	66.09 201	89.96 86	90.80 169	77.37 59	86.72 68	94.20 53	72.51 55	92.78 231	89.08 22	92.33 89	93.13 146

TestfortrainingZip				87.28 46	92.85 69	72.05 50	93.28 12	93.32 38	76.52 90	88.91 34	93.52 78	77.30 18	96.67 34		91.98 96	93.13 146

PAPR		81.66 167	80.89 170	83.99 180	90.27 113	64.00 270	86.76 228	91.77 132	68.84 316	77.13 262	89.50 215	67.63 131	94.88 110	67.55 285	88.52 165	93.09 148

UA-Net		85.08 87	84.96 87	85.45 91	92.07 81	68.07 147	89.78 91	90.86 167	82.48 2	84.60 96	93.20 89	69.35 102	95.22 90	71.39 244	90.88 119	93.07 149

reproduce-ours		87.47 27	87.61 27	87.07 51	93.27 55	71.60 56	91.56 54	93.19 42	74.98 144	88.96 32	95.54 15	71.20 75	96.54 42	86.28 56	93.49 71	93.06 150

our_new_method		87.47 27	87.61 27	87.07 51	93.27 55	71.60 56	91.56 54	93.19 42	74.98 144	88.96 32	95.54 15	71.20 75	96.54 42	86.28 56	93.49 71	93.06 150

HPM-MVS++		89.02 10	89.15 12	88.63 5	95.01 9	76.03 1	92.38 32	92.85 66	80.26 12	87.78 51	94.27 48	75.89 24	96.81 28	87.45 48	96.44 9	93.05 152

thisisatest0530		79.40 233	77.76 255	84.31 147	87.69 235	65.10 238	87.36 202	84.26 361	70.04 278	77.42 249	88.26 258	49.94 362	94.79 116	70.20 258	84.70 247	93.03 153

PRO-TEST		83.03 138	82.63 136	84.23 157	88.20 198	66.81 192	87.41 200	90.93 162	73.55 189	80.73 181	88.90 236	66.17 154	92.85 225	78.39 157	89.36 147	93.02 154

train_agg		86.43 49	86.20 57	87.13 50	93.26 57	72.96 25	88.75 139	91.89 123	68.69 318	85.00 83	93.10 90	74.43 32	95.41 82	84.97 65	95.71 29	93.02 154

EC-MVSNet		86.01 59	86.38 52	84.91 116	89.31 150	66.27 199	92.32 35	93.63 27	79.37 24	84.17 107	91.88 127	69.04 114	95.43 79	83.93 83	93.77 69	93.01 156

mvsmamba		80.60 200	79.38 212	84.27 153	89.74 131	67.24 182	87.47 191	86.95 314	70.02 279	75.38 301	88.93 235	51.24 344	92.56 238	75.47 199	89.22 150	93.00 157

EI-MVSNet-UG-set		83.81 109	83.38 120	85.09 106	87.87 218	67.53 169	87.44 199	89.66 208	79.74 19	82.23 148	89.41 223	70.24 87	94.74 118	79.95 130	83.92 261	92.99 158

tttt0517		79.40 233	77.91 246	83.90 184	88.10 207	63.84 275	88.37 160	84.05 364	71.45 236	76.78 266	89.12 227	49.93 364	94.89 109	70.18 259	83.18 280	92.96 159

viewdifsd2359ckpt11		80.37 209	79.73 201	82.30 253	83.70 355	62.39 317	84.20 315	86.67 321	73.22 203	80.90 176	90.62 180	63.00 197	91.56 286	76.81 180	78.44 339	92.95 160

viewmsd2359difaftdt		80.37 209	79.73 201	82.30 253	83.70 355	62.39 317	84.20 315	86.67 321	73.22 203	80.90 176	90.62 180	63.00 197	91.56 286	76.81 180	78.44 339	92.95 160

test9_res														84.90 66	95.70 30	92.87 162

viewmambaseed2359dif		80.41 205	79.84 198	82.12 256	82.95 384	62.50 316	83.39 337	88.06 279	67.11 337	80.98 173	90.31 191	66.20 153	91.01 317	74.62 205	84.90 241	92.86 163

AstraMVS		80.81 188	80.14 190	82.80 234	86.05 298	63.96 271	86.46 240	85.90 337	73.71 183	80.85 179	90.56 183	54.06 305	91.57 285	79.72 138	83.97 260	92.86 163

SR-MVS		86.73 43	86.67 48	86.91 56	94.11 42	72.11 49	92.37 33	92.56 83	74.50 158	86.84 67	94.65 32	67.31 135	95.77 66	84.80 70	92.85 80	92.84 165

ETV-MVS		84.90 91	84.67 91	85.59 88	89.39 145	68.66 129	88.74 141	92.64 80	79.97 17	84.10 108	85.71 328	69.32 103	95.38 84	80.82 117	91.37 108	92.72 166

agg_prior2														82.91 93	95.45 33	92.70 167

APD-MVS		87.44 29	87.52 30	87.19 48	94.24 37	72.39 41	91.86 45	92.83 67	73.01 208	88.58 37	94.52 33	73.36 41	96.49 44	84.26 77	95.01 41	92.70 167
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ET-MVSNet_ETH3D		78.63 254	76.63 285	84.64 127	86.73 279	69.47 104	85.01 287	84.61 354	69.54 293	66.51 435	86.59 307	50.16 358	91.75 276	76.26 185	84.24 257	92.69 169

Vis-MVSNet (Re-imp)		78.36 261	78.45 233	78.07 365	88.64 183	51.78 461	86.70 229	79.63 433	74.14 171	75.11 314	90.83 172	61.29 230	89.75 351	58.10 389	91.60 102	92.69 169

TSAR-MVS + GP.		85.71 70	85.33 80	86.84 57	91.34 90	72.50 36	89.07 125	87.28 301	76.41 97	85.80 74	90.22 196	74.15 38	95.37 87	81.82 106	91.88 97	92.65 171

test_fmvsmvis_n_1920		84.02 103	83.87 105	84.49 136	84.12 343	69.37 110	88.15 170	87.96 283	70.01 280	83.95 112	93.23 88	68.80 117	91.51 293	88.61 32	89.96 135	92.57 172

FA-MVS(test-final)		80.96 184	79.91 195	84.10 161	88.30 196	65.01 239	84.55 302	90.01 196	73.25 201	79.61 200	87.57 276	58.35 263	94.72 119	71.29 245	86.25 216	92.56 173

guyue		81.13 180	80.64 175	82.60 245	86.52 285	63.92 274	86.69 230	87.73 291	73.97 174	80.83 180	89.69 208	56.70 280	91.33 302	78.26 162	85.40 237	92.54 174

dtuplus		80.04 218	79.40 211	81.97 262	83.08 374	62.61 312	83.63 330	87.98 281	67.47 335	81.02 172	90.50 186	64.86 172	90.77 330	71.28 246	84.76 245	92.53 175

test_yl		81.17 178	80.47 180	83.24 207	89.13 159	63.62 280	86.21 252	89.95 198	72.43 218	81.78 157	89.61 212	57.50 271	93.58 172	70.75 250	86.90 202	92.52 176

DCV-MVSNet		81.17 178	80.47 180	83.24 207	89.13 159	63.62 280	86.21 252	89.95 198	72.43 218	81.78 157	89.61 212	57.50 271	93.58 172	70.75 250	86.90 202	92.52 176

SR-MVS-dyc-post		85.77 68	85.61 74	86.23 68	93.06 65	70.63 84	91.88 43	92.27 97	73.53 191	85.69 76	94.45 38	65.00 171	95.56 70	82.75 97	91.87 98	92.50 178

RE-MVS-def			85.48 77		93.06 65	70.63 84	91.88 43	92.27 97	73.53 191	85.69 76	94.45 38	63.87 182		82.75 97	91.87 98	92.50 178

nrg030		83.88 108	83.53 117	84.96 111	86.77 278	69.28 111	90.46 75	92.67 75	74.79 152	82.95 135	91.33 153	72.70 54	93.09 214	80.79 119	79.28 332	92.50 178

SSM_0404		81.91 159	80.84 171	85.13 104	89.24 154	68.26 139	87.84 183	89.25 231	71.06 247	80.62 184	90.39 189	59.57 252	94.65 123	72.45 236	87.19 196	92.47 181

MG-MVS		83.41 126	83.45 118	83.28 204	92.74 73	62.28 322	88.17 168	89.50 215	75.22 134	81.49 162	92.74 106	66.75 142	95.11 96	72.85 226	91.58 104	92.45 182

FIs		82.07 156	82.42 139	81.04 287	88.80 175	58.34 380	88.26 165	93.49 32	76.93 77	78.47 225	91.04 165	69.92 94	92.34 252	69.87 264	84.97 240	92.44 183

testing3-2		75.12 330	75.19 312	74.91 406	90.40 111	45.09 492	80.29 393	78.42 443	78.37 41	76.54 274	87.75 270	44.36 419	87.28 393	57.04 399	83.49 273	92.37 184

fmvsm_s_conf0.5_n_3		86.36 53	87.46 32	83.09 216	87.08 269	65.21 232	89.09 124	90.21 190	79.67 20	89.98 26	95.02 25	73.17 45	91.71 279	91.30 3	91.60 102	92.34 185

FC-MVSNet-test		81.52 172	82.02 152	80.03 313	88.42 192	55.97 420	87.95 176	93.42 35	77.10 72	77.38 250	90.98 170	69.96 93	91.79 274	68.46 279	84.50 249	92.33 186

Fast-Effi-MVS+		80.81 188	79.92 194	83.47 195	88.85 167	64.51 258	85.53 274	89.39 219	70.79 255	78.49 223	85.06 348	67.54 132	93.58 172	67.03 293	86.58 208	92.32 187

TranMVSNet+NR-MVSNet		80.84 186	80.31 183	82.42 249	87.85 219	62.33 320	87.74 185	91.33 150	80.55 9	77.99 237	89.86 200	65.23 166	92.62 233	67.05 292	75.24 393	92.30 188

ab-mvs		79.51 227	78.97 224	81.14 284	88.46 189	60.91 348	83.84 322	89.24 233	70.36 270	79.03 210	88.87 239	63.23 190	90.21 342	65.12 307	82.57 288	92.28 189

CANet_DTU		80.61 198	79.87 197	82.83 231	85.60 307	63.17 300	87.36 202	88.65 268	76.37 102	75.88 288	88.44 252	53.51 310	93.07 215	73.30 220	89.74 140	92.25 190

UniMVSNet_NR-MVSNet		81.88 160	81.54 159	82.92 227	88.46 189	63.46 291	87.13 208	92.37 90	80.19 13	78.38 226	89.14 226	71.66 69	93.05 217	70.05 260	76.46 366	92.25 190

fmvsm_l_conf0.5_n		84.47 93	84.54 92	84.27 153	85.42 312	68.81 118	88.49 153	87.26 306	68.08 327	88.03 47	93.49 79	72.04 62	91.77 275	88.90 29	89.14 153	92.24 192

DU-MVS		81.12 181	80.52 178	82.90 228	87.80 222	63.46 291	87.02 214	91.87 125	79.01 32	78.38 226	89.07 228	65.02 169	93.05 217	70.05 260	76.46 366	92.20 193

NR-MVSNet		80.23 213	79.38 212	82.78 238	87.80 222	63.34 294	86.31 247	91.09 159	79.01 32	72.17 359	89.07 228	67.20 136	92.81 230	66.08 299	75.65 379	92.20 193

mamba_0408		79.37 236	77.52 262	84.93 114	88.81 171	67.96 152	65.03 496	88.66 266	70.96 251	79.48 203	89.80 204	58.69 258	94.65 123	70.35 256	85.93 226	92.18 195

SSM_04072		77.67 283	77.52 262	78.12 363	88.81 171	67.96 152	65.03 496	88.66 266	70.96 251	79.48 203	89.80 204	58.69 258	74.23 489	70.35 256	85.93 226	92.18 195

SSM_0407		81.58 169	80.48 179	84.87 118	88.81 171	67.96 152	87.37 201	89.25 231	71.06 247	79.48 203	90.39 189	59.57 252	94.48 130	72.45 236	85.93 226	92.18 195

TAPA-MVS	73.13 9	79.15 240	77.94 245	82.79 237	89.59 133	62.99 306	88.16 169	91.51 145	65.77 359	77.14 261	91.09 163	60.91 237	93.21 203	50.26 442	87.05 199	92.17 198
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
fmvsm_l_conf0.5_n_a		84.13 100	84.16 97	84.06 170	85.38 313	68.40 135	88.34 161	86.85 318	67.48 334	87.48 58	93.40 84	70.89 78	91.61 281	88.38 38	89.22 150	92.16 199

3Dnovator	76.31 5	83.38 128	82.31 143	86.59 62	87.94 215	72.94 28	90.64 68	92.14 114	77.21 67	75.47 295	92.83 99	58.56 261	94.72 119	73.24 222	92.71 83	92.13 200

MVS_111021_HR		85.14 84	84.75 90	86.32 66	91.65 87	72.70 30	85.98 257	90.33 185	76.11 109	82.08 151	91.61 143	71.36 73	94.17 143	81.02 114	92.58 84	92.08 201

MVSFormer		82.85 142	82.05 151	85.24 98	87.35 249	70.21 88	90.50 72	90.38 181	68.55 320	81.32 165	89.47 217	61.68 219	93.46 190	78.98 149	90.26 129	92.05 202

jason		81.39 176	80.29 185	84.70 126	86.63 283	69.90 96	85.95 258	86.77 319	63.24 396	81.07 171	89.47 217	61.08 235	92.15 258	78.33 158	90.07 134	92.05 202
jason: jason.
HyFIR lowres test		77.53 286	75.40 305	83.94 183	89.59 133	66.62 193	80.36 391	88.64 269	56.29 464	76.45 275	85.17 345	57.64 269	93.28 196	61.34 357	83.10 281	91.91 204

XVG-OURS-SEG-HR		80.81 188	79.76 200	83.96 182	85.60 307	68.78 120	83.54 334	90.50 177	70.66 262	76.71 268	91.66 137	60.69 240	91.26 303	76.94 175	81.58 300	91.83 205

lupinMVS		81.39 176	80.27 186	84.76 124	87.35 249	70.21 88	85.55 272	86.41 327	62.85 403	81.32 165	88.61 246	61.68 219	92.24 256	78.41 156	90.26 129	91.83 205

WR-MVS		79.49 228	79.22 219	80.27 306	88.79 176	58.35 379	85.06 286	88.61 270	78.56 36	77.65 244	88.34 254	63.81 184	90.66 334	64.98 309	77.22 354	91.80 207

icg_test_0407_2		78.92 248	78.93 225	78.90 346	87.13 263	63.59 284	76.58 440	89.33 221	70.51 265	77.82 239	89.03 230	61.84 215	81.38 448	72.56 232	85.56 233	91.74 208

IMVS_0407		80.61 198	79.90 196	82.75 241	87.13 263	63.59 284	85.33 278	89.33 221	70.51 265	77.82 239	89.03 230	61.84 215	92.91 222	72.56 232	85.56 233	91.74 208

IMVS_0404		77.16 293	76.42 289	79.37 337	87.13 263	63.59 284	77.12 437	89.33 221	70.51 265	66.22 438	89.03 230	50.36 356	82.78 436	72.56 232	85.56 233	91.74 208

IMVS_0403		80.80 191	80.12 191	82.87 230	87.13 263	63.59 284	85.19 279	89.33 221	70.51 265	78.49 223	89.03 230	63.26 188	93.27 198	72.56 232	85.56 233	91.74 208

h-mvs33		83.15 134	82.19 146	86.02 78	90.56 107	70.85 81	88.15 170	89.16 237	76.02 111	84.67 91	91.39 151	61.54 222	95.50 75	82.71 99	75.48 383	91.72 212

FBQ-MVS		77.66 284	76.04 294	82.50 247	88.78 178	63.76 279	86.60 234	84.86 350	70.85 253	77.63 245	82.83 399	47.83 384	92.10 260	60.18 366	84.82 244	91.65 213

UniMVSNet (Re)		81.60 168	81.11 165	83.09 216	88.38 193	64.41 263	87.60 187	93.02 52	78.42 38	78.56 221	88.16 260	69.78 96	93.26 199	69.58 267	76.49 365	91.60 214

UGNet		80.83 187	79.59 207	84.54 129	88.04 210	68.09 146	89.42 107	88.16 274	76.95 76	76.22 281	89.46 219	49.30 373	93.94 151	68.48 278	90.31 127	91.60 214
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
testing91		76.54 301	75.66 300	79.18 342	88.43 191	55.89 421	81.08 377	83.00 384	73.76 182	75.34 303	84.29 363	46.20 403	90.07 345	64.33 313	84.50 249	91.58 216

XVG-OURS		80.41 205	79.23 218	83.97 181	85.64 305	69.02 114	83.03 350	90.39 180	71.09 245	77.63 245	91.49 148	54.62 300	91.35 300	75.71 193	83.47 274	91.54 217

LCM-MVSNet-Re		77.05 294	76.94 275	77.36 379	87.20 260	51.60 462	80.06 396	80.46 419	75.20 137	67.69 414	86.72 299	62.48 204	88.98 367	63.44 319	89.25 148	91.51 218

DP-MVS Recon		83.11 137	82.09 150	86.15 72	94.44 24	70.92 79	88.79 136	92.20 107	70.53 264	79.17 209	91.03 167	64.12 179	96.03 57	68.39 280	90.14 131	91.50 219

PS-MVSNAJss		82.07 156	81.31 160	84.34 145	86.51 286	67.27 180	89.27 113	91.51 145	71.75 228	79.37 206	90.22 196	63.15 192	94.27 135	77.69 166	82.36 290	91.49 220

testing99		76.09 315	75.12 314	79.00 343	88.16 202	55.50 427	80.79 381	81.40 406	73.30 199	75.17 311	84.27 366	44.48 418	90.02 346	64.28 314	84.22 258	91.48 221

thisisatest0515		77.33 290	75.38 306	83.18 211	85.27 317	63.80 276	82.11 360	83.27 376	65.06 373	75.91 287	83.84 375	49.54 367	94.27 135	67.24 289	86.19 217	91.48 221

DPM-MVS		84.93 89	84.29 96	86.84 57	90.20 115	73.04 23	87.12 209	93.04 48	69.80 286	82.85 139	91.22 157	73.06 47	96.02 59	76.72 183	94.63 54	91.46 223

HQP_MVS		83.64 118	83.14 123	85.14 101	90.08 118	68.71 125	91.25 60	92.44 85	79.12 29	78.92 213	91.00 168	60.42 247	95.38 84	78.71 152	86.32 213	91.33 224

plane_prior5								92.44 85					95.38 84	78.71 152	86.32 213	91.33 224

GA-MVS		76.87 298	75.17 313	81.97 262	82.75 387	62.58 313	81.44 372	86.35 330	72.16 223	74.74 322	82.89 397	46.20 403	92.02 264	68.85 275	81.09 305	91.30 226

VPA-MVSNet		80.60 200	80.55 177	80.76 294	88.07 209	60.80 350	86.86 222	91.58 143	75.67 121	80.24 192	89.45 221	63.34 185	90.25 341	70.51 254	79.22 333	91.23 227

Effi-MVS+-dtu		80.03 219	78.57 231	84.42 139	85.13 322	68.74 123	88.77 137	88.10 276	74.99 143	74.97 319	83.49 386	57.27 274	93.36 194	73.53 216	80.88 308	91.18 228

v2v482		80.23 213	79.29 216	83.05 220	83.62 357	64.14 268	87.04 212	89.97 197	73.61 186	78.18 232	87.22 287	61.10 234	93.82 161	76.11 187	76.78 362	91.18 228

FE-MVS		77.78 277	75.68 298	84.08 166	88.09 208	66.00 205	83.13 344	87.79 289	68.42 324	78.01 236	85.23 343	45.50 412	95.12 94	59.11 377	85.83 230	91.11 230

Anonymous20231211		78.97 246	77.69 258	82.81 233	90.54 108	64.29 265	90.11 83	91.51 145	65.01 375	76.16 286	88.13 265	50.56 353	93.03 220	69.68 266	77.56 352	91.11 230

hse-mvs2		81.72 163	80.94 169	84.07 167	88.72 180	67.68 163	85.87 262	87.26 306	76.02 111	84.67 91	88.22 259	61.54 222	93.48 188	82.71 99	73.44 411	91.06 232

AUN-MVS		79.21 239	77.60 260	84.05 173	88.71 181	67.61 165	85.84 264	87.26 306	69.08 307	77.23 255	88.14 264	53.20 314	93.47 189	75.50 198	73.45 410	91.06 232

HQP4-MVS										77.24 254			95.11 96			91.03 234

HQP-MVS		82.61 146	82.02 152	84.37 142	89.33 147	66.98 187	89.17 117	92.19 109	76.41 97	77.23 255	90.23 195	60.17 250	95.11 96	77.47 168	85.99 224	91.03 234

RPSCF		73.23 358	71.46 359	78.54 354	82.50 394	59.85 365	82.18 359	82.84 389	58.96 442	71.15 372	89.41 223	45.48 413	84.77 420	58.82 381	71.83 423	91.02 236

LuminaMVS		80.68 196	79.62 206	83.83 185	85.07 324	68.01 151	86.99 215	88.83 253	70.36 270	81.38 164	87.99 267	50.11 359	92.51 242	79.02 146	86.89 204	90.97 237

test_djsdf		80.30 212	79.32 215	83.27 205	83.98 347	65.37 226	90.50 72	90.38 181	68.55 320	76.19 282	88.70 242	56.44 283	93.46 190	78.98 149	80.14 320	90.97 237

PCF-MVS	73.52 7	80.38 207	78.84 227	85.01 109	87.71 231	68.99 115	83.65 327	91.46 149	63.00 400	77.77 243	90.28 192	66.10 155	95.09 100	61.40 355	88.22 174	90.94 239
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VPNet		78.69 253	78.66 229	78.76 348	88.31 195	55.72 424	84.45 306	86.63 324	76.79 81	78.26 229	90.55 184	59.30 255	89.70 353	66.63 294	77.05 356	90.88 240

CPTT-MVS		83.73 114	83.33 122	84.92 115	93.28 54	70.86 80	92.09 41	90.38 181	68.75 317	79.57 201	92.83 99	60.60 245	93.04 219	80.92 116	91.56 105	90.86 241

fmvsm_s_conf0.5_n_7		83.34 129	84.03 103	81.28 279	85.73 303	65.13 235	85.40 277	89.90 200	74.96 146	82.13 150	93.89 70	66.65 143	87.92 384	86.56 55	91.05 113	90.80 242

tt0805		78.73 251	77.83 250	81.43 273	85.17 318	60.30 361	89.41 108	90.90 164	71.21 242	77.17 260	88.73 241	46.38 398	93.21 203	72.57 230	78.96 334	90.79 243

CLD-MVS		82.31 151	81.65 158	84.29 150	88.47 188	67.73 161	85.81 266	92.35 91	75.78 116	78.33 228	86.58 309	64.01 181	94.35 132	76.05 189	87.48 191	90.79 243
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
v1192		79.59 226	78.43 235	83.07 219	83.55 359	64.52 257	86.93 219	90.58 174	70.83 254	77.78 242	85.90 324	59.15 256	93.94 151	73.96 213	77.19 355	90.76 245

IterMVS-LS		80.06 217	79.38 212	82.11 258	85.89 299	63.20 298	86.79 225	89.34 220	74.19 169	75.45 298	86.72 299	66.62 144	92.39 248	72.58 229	76.86 359	90.75 246
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
myMVS_eth3d28		73.62 345	73.53 335	73.90 420	88.20 198	47.41 482	78.06 427	79.37 435	74.29 167	73.98 333	84.29 363	44.67 415	83.54 430	51.47 432	87.39 192	90.74 247

EI-MVSNet		80.52 204	79.98 193	82.12 256	84.28 339	63.19 299	86.41 241	88.95 250	74.18 170	78.69 216	87.54 279	66.62 144	92.43 246	72.57 230	80.57 314	90.74 247

v1921920		79.22 238	78.03 243	82.80 234	83.30 364	63.94 273	86.80 224	90.33 185	69.91 284	77.48 248	85.53 335	58.44 262	93.75 167	73.60 215	76.85 360	90.71 249

QAPM		80.88 185	79.50 209	85.03 107	88.01 213	68.97 116	91.59 51	92.00 117	66.63 348	75.15 313	92.16 119	57.70 268	95.45 77	63.52 317	88.76 160	90.66 250

v144192		79.47 229	78.37 236	82.78 238	83.35 362	63.96 271	86.96 216	90.36 184	69.99 281	77.50 247	85.67 331	60.66 242	93.77 165	74.27 210	76.58 363	90.62 251

v1240		78.99 245	77.78 253	82.64 243	83.21 368	63.54 288	86.62 233	90.30 187	69.74 291	77.33 251	85.68 330	57.04 277	93.76 166	73.13 223	76.92 357	90.62 251

v1144		80.03 219	79.03 222	83.01 222	83.78 352	64.51 258	87.11 210	90.57 176	71.96 226	78.08 235	86.20 320	61.41 226	93.94 151	74.93 203	77.23 353	90.60 253

1112_ss		77.40 289	76.43 288	80.32 305	89.11 163	60.41 360	83.65 327	87.72 292	62.13 415	73.05 345	86.72 299	62.58 203	89.97 347	62.11 345	80.80 310	90.59 254

CP-MVSNet		78.22 263	78.34 237	77.84 369	87.83 221	54.54 438	87.94 177	91.17 155	77.65 48	73.48 340	88.49 250	62.24 210	88.43 378	62.19 342	74.07 402	90.55 255

testing222		74.04 340	72.66 346	78.19 361	87.89 217	55.36 428	81.06 378	79.20 438	71.30 240	74.65 325	83.57 385	39.11 455	88.67 374	51.43 434	85.75 231	90.53 256

PS-CasMVS		78.01 272	78.09 242	77.77 371	87.71 231	54.39 440	88.02 173	91.22 152	77.50 56	73.26 342	88.64 245	60.73 238	88.41 379	61.88 348	73.88 406	90.53 256

CDS-MVSNet		79.07 243	77.70 257	83.17 212	87.60 238	68.23 143	84.40 311	86.20 332	67.49 333	76.36 278	86.54 311	61.54 222	90.79 327	61.86 349	87.33 193	90.49 258
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		78.89 249	77.51 264	83.03 221	87.80 222	67.79 160	84.72 293	85.05 348	67.63 330	76.75 267	87.70 272	62.25 209	90.82 326	58.53 384	87.13 198	90.49 258

testing915		80.13 216	80.30 184	79.64 331	89.00 166	58.38 378	87.08 211	84.16 363	74.04 173	80.14 195	89.37 225	64.04 180	90.08 344	66.04 300	88.82 157	90.45 260

PEN-MVS		77.73 278	77.69 258	77.84 369	87.07 271	53.91 443	87.91 179	91.18 154	77.56 53	73.14 344	88.82 240	61.23 231	89.17 363	59.95 367	72.37 417	90.43 261

Test_1112_low_res		76.40 310	75.44 303	79.27 339	89.28 152	58.09 382	81.69 367	87.07 312	59.53 437	72.48 354	86.67 304	61.30 229	89.33 358	60.81 361	80.15 319	90.41 262

HY-MVS	69.67 12	77.95 273	77.15 270	80.36 303	87.57 247	60.21 363	83.37 339	87.78 290	66.11 353	75.37 302	87.06 294	63.27 187	90.48 336	61.38 356	82.43 289	90.40 263

sc_t1		72.19 375	69.51 387	80.23 308	84.81 328	61.09 342	84.68 294	80.22 426	60.70 425	71.27 369	83.58 384	36.59 467	89.24 361	60.41 362	63.31 467	90.37 264

CHOSEN 1792x2688		77.63 285	75.69 297	83.44 198	89.98 124	68.58 131	78.70 417	87.50 296	56.38 463	75.80 290	86.84 295	58.67 260	91.40 299	61.58 353	85.75 231	90.34 265

SDMVSNet		80.38 207	80.18 187	80.99 288	89.03 164	64.94 245	80.45 390	89.40 218	75.19 138	76.61 272	89.98 198	60.61 244	87.69 388	76.83 179	83.55 271	90.33 266

sd_testset		77.70 281	77.40 265	78.60 351	89.03 164	60.02 364	79.00 412	85.83 338	75.19 138	76.61 272	89.98 198	54.81 293	85.46 413	62.63 335	83.55 271	90.33 266

114514_t		80.68 196	79.51 208	84.20 158	94.09 43	67.27 180	89.64 96	91.11 158	58.75 446	74.08 332	90.72 175	58.10 264	95.04 102	69.70 265	89.42 146	90.30 268

eth_miper_zixun_eth		77.92 274	76.69 283	81.61 270	83.00 378	61.98 327	83.15 343	89.20 235	69.52 294	74.86 321	84.35 362	61.76 218	92.56 238	71.50 243	72.89 415	90.28 269

PVSNet_Blended_VisFu		82.62 145	81.83 156	84.96 111	90.80 103	69.76 99	88.74 141	91.70 136	69.39 295	78.96 211	88.46 251	65.47 164	94.87 111	74.42 208	88.57 163	90.24 270

MVS_111021_LR		82.61 146	82.11 147	84.11 160	88.82 170	71.58 58	85.15 282	86.16 333	74.69 154	80.47 189	91.04 165	62.29 208	90.55 335	80.33 126	90.08 133	90.20 271

MSLP-MVS++		85.43 77	85.76 71	84.45 137	91.93 83	70.24 87	90.71 67	92.86 65	77.46 57	84.22 105	92.81 101	67.16 137	92.94 221	80.36 124	94.35 63	90.16 272

mvs_tets		79.13 241	77.77 254	83.22 209	84.70 331	66.37 197	89.17 117	90.19 191	69.38 296	75.40 300	89.46 219	44.17 421	93.15 210	76.78 182	80.70 312	90.14 273

BH-RMVSNet		79.61 224	78.44 234	83.14 213	89.38 146	65.93 207	84.95 289	87.15 309	73.56 188	78.19 231	89.79 206	56.67 281	93.36 194	59.53 372	86.74 206	90.13 274

c3_l		78.75 250	77.91 246	81.26 280	82.89 385	61.56 334	84.09 319	89.13 241	69.97 282	75.56 293	84.29 363	66.36 149	92.09 261	73.47 218	75.48 383	90.12 275

v7n		78.97 246	77.58 261	83.14 213	83.45 361	65.51 220	88.32 162	91.21 153	73.69 184	72.41 355	86.32 317	57.93 265	93.81 162	69.18 270	75.65 379	90.11 276

jajsoiax		79.29 237	77.96 244	83.27 205	84.68 332	66.57 195	89.25 114	90.16 192	69.20 304	75.46 297	89.49 216	45.75 409	93.13 212	76.84 178	80.80 310	90.11 276

v148		78.72 252	77.80 252	81.47 272	82.73 388	61.96 328	86.30 248	88.08 277	73.26 200	76.18 283	85.47 337	62.46 205	92.36 250	71.92 240	73.82 407	90.09 278

GBi-Net		78.40 259	77.40 265	81.40 275	87.60 238	63.01 302	88.39 157	89.28 227	71.63 230	75.34 303	87.28 283	54.80 294	91.11 309	62.72 331	79.57 324	90.09 278

test1		78.40 259	77.40 265	81.40 275	87.60 238	63.01 302	88.39 157	89.28 227	71.63 230	75.34 303	87.28 283	54.80 294	91.11 309	62.72 331	79.57 324	90.09 278

FMVSNet1		77.44 287	76.12 293	81.40 275	86.81 276	63.01 302	88.39 157	89.28 227	70.49 269	74.39 329	87.28 283	49.06 377	91.11 309	60.91 359	78.52 337	90.09 278

WR-MVS_H		78.51 258	78.49 232	78.56 353	88.02 211	56.38 414	88.43 154	92.67 75	77.14 69	73.89 334	87.55 278	66.25 151	89.24 361	58.92 379	73.55 409	90.06 282

DTE-MVSNet		76.99 295	76.80 278	77.54 378	86.24 291	53.06 453	87.52 189	90.66 172	77.08 73	72.50 353	88.67 244	60.48 246	89.52 355	57.33 396	70.74 429	90.05 283

v8		79.97 221	79.02 223	82.80 234	84.09 344	64.50 260	87.96 175	90.29 188	74.13 172	75.24 310	86.81 296	62.88 200	93.89 159	74.39 209	75.40 388	90.00 284

thres600view7		76.50 303	75.44 303	79.68 329	89.40 144	57.16 400	85.53 274	83.23 377	73.79 181	76.26 280	87.09 292	51.89 333	91.89 271	48.05 457	83.72 268	90.00 284

thres400		76.50 303	75.37 307	79.86 319	89.13 159	57.65 394	85.17 280	83.60 369	73.41 195	76.45 275	86.39 315	52.12 323	91.95 267	48.33 452	83.75 265	90.00 284

cl22		78.07 269	77.01 272	81.23 281	82.37 398	61.83 330	83.55 332	87.98 281	68.96 314	75.06 316	83.87 373	61.40 227	91.88 272	73.53 216	76.39 368	89.98 287

OPM-MVS		83.50 124	82.95 129	85.14 101	88.79 176	70.95 77	89.13 122	91.52 144	77.55 54	80.96 175	91.75 133	60.71 239	94.50 128	79.67 139	86.51 210	89.97 288
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline2		75.70 319	73.83 332	81.30 278	83.26 366	61.79 331	82.57 353	80.65 414	66.81 339	66.88 426	83.42 387	57.86 267	92.19 257	63.47 318	79.57 324	89.91 289

v10		79.74 223	78.67 228	82.97 226	84.06 345	64.95 242	87.88 181	90.62 173	73.11 205	75.11 314	86.56 310	61.46 225	94.05 147	73.68 214	75.55 381	89.90 290

MVSTER		79.01 244	77.88 249	82.38 250	83.07 375	64.80 252	84.08 320	88.95 250	69.01 311	78.69 216	87.17 290	54.70 298	92.43 246	74.69 204	80.57 314	89.89 291

ACMP	74.13 6	81.51 174	80.57 176	84.36 143	89.42 142	68.69 128	89.97 85	91.50 148	74.46 160	75.04 317	90.41 187	53.82 307	94.54 125	77.56 167	82.91 282	89.86 292
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LPG-MVS_test		82.08 155	81.27 161	84.50 134	89.23 155	68.76 121	90.22 81	91.94 121	75.37 129	76.64 270	91.51 146	54.29 301	94.91 105	78.44 154	83.78 262	89.83 293

LGP-MVS_train				84.50 134	89.23 155	68.76 121		91.94 121	75.37 129	76.64 270	91.51 146	54.29 301	94.91 105	78.44 154	83.78 262	89.83 293

V42		79.38 235	78.24 240	82.83 231	81.10 419	65.50 221	85.55 272	89.82 201	71.57 234	78.21 230	86.12 322	60.66 242	93.18 209	75.64 194	75.46 385	89.81 295

MAR-MVS		81.84 161	80.70 172	85.27 97	91.32 91	71.53 59	89.82 88	90.92 163	69.77 288	78.50 222	86.21 319	62.36 207	94.52 127	65.36 305	92.05 95	89.77 296
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
DIV-MVS_self_test		77.72 279	76.76 280	80.58 298	82.48 396	60.48 358	83.09 346	87.86 287	69.22 302	74.38 330	85.24 342	62.10 212	91.53 291	71.09 247	75.40 388	89.74 297

cl____		77.72 279	76.76 280	80.58 298	82.49 395	60.48 358	83.09 346	87.87 286	69.22 302	74.38 330	85.22 344	62.10 212	91.53 291	71.09 247	75.41 387	89.73 298

miper_ehance_all_eth		78.59 256	77.76 255	81.08 286	82.66 390	61.56 334	83.65 327	89.15 239	68.87 315	75.55 294	83.79 377	66.49 147	92.03 262	73.25 221	76.39 368	89.64 299

anonymousdsp		78.60 255	77.15 270	82.98 225	80.51 425	67.08 185	87.24 207	89.53 214	65.66 361	75.16 312	87.19 289	52.52 316	92.25 255	77.17 172	79.34 331	89.61 300

FMVSNet2		78.20 265	77.21 269	81.20 282	87.60 238	62.89 310	87.47 191	89.02 245	71.63 230	75.29 309	87.28 283	54.80 294	91.10 312	62.38 339	79.38 330	89.61 300

baseline1		76.98 296	76.75 282	77.66 373	88.13 205	55.66 425	85.12 283	81.89 399	73.04 207	76.79 265	88.90 236	62.43 206	87.78 387	63.30 321	71.18 427	89.55 302

ETVMVS		72.25 374	71.05 368	75.84 392	87.77 227	51.91 458	79.39 405	74.98 465	69.26 300	73.71 336	82.95 395	40.82 444	86.14 403	46.17 465	84.43 254	89.47 303

FMVSNet3		77.88 275	76.85 277	80.97 290	86.84 275	62.36 319	86.52 238	88.77 256	71.13 243	75.34 303	86.66 305	54.07 304	91.10 312	62.72 331	79.57 324	89.45 304

SD_0403		74.65 333	74.77 317	74.29 414	86.20 293	47.42 481	83.71 325	85.12 345	69.30 298	68.50 404	87.95 268	59.40 254	86.05 404	49.38 446	83.35 276	89.40 305

miper_enhance_ethall		77.87 276	76.86 276	80.92 291	81.65 407	61.38 338	82.68 351	88.98 247	65.52 363	75.47 295	82.30 407	65.76 163	92.00 265	72.95 225	76.39 368	89.39 306

testing11		75.14 329	74.01 327	78.53 355	88.16 202	56.38 414	80.74 384	80.42 421	70.67 259	72.69 352	83.72 380	43.61 425	89.86 348	62.29 341	83.76 264	89.36 307

cascas		76.72 300	74.64 318	82.99 223	85.78 302	65.88 209	82.33 356	89.21 234	60.85 424	72.74 349	81.02 420	47.28 387	93.75 167	67.48 286	85.02 239	89.34 308

Fast-Effi-MVS+-dtu		78.02 271	76.49 286	82.62 244	83.16 372	66.96 189	86.94 218	87.45 298	72.45 215	71.49 368	84.17 370	54.79 297	91.58 283	67.61 284	80.31 317	89.30 309

IB-MVS	68.01 15	75.85 318	73.36 338	83.31 203	84.76 330	66.03 202	83.38 338	85.06 347	70.21 277	69.40 391	81.05 419	45.76 408	94.66 122	65.10 308	75.49 382	89.25 310
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
thres100view900		76.50 303	75.55 302	79.33 338	89.52 136	56.99 403	85.83 265	83.23 377	73.94 177	76.32 279	87.12 291	51.89 333	91.95 267	48.33 452	83.75 265	89.07 311

tfpn200view9		76.42 309	75.37 307	79.55 335	89.13 159	57.65 394	85.17 280	83.60 369	73.41 195	76.45 275	86.39 315	52.12 323	91.95 267	48.33 452	83.75 265	89.07 311

xiu_mvs_v1_base_debu		80.80 191	79.72 203	84.03 175	87.35 249	70.19 90	85.56 269	88.77 256	69.06 308	81.83 153	88.16 260	50.91 347	92.85 225	78.29 159	87.56 188	89.06 313

xiu_mvs_v1_base		80.80 191	79.72 203	84.03 175	87.35 249	70.19 90	85.56 269	88.77 256	69.06 308	81.83 153	88.16 260	50.91 347	92.85 225	78.29 159	87.56 188	89.06 313

xiu_mvs_v1_base_debi		80.80 191	79.72 203	84.03 175	87.35 249	70.19 90	85.56 269	88.77 256	69.06 308	81.83 153	88.16 260	50.91 347	92.85 225	78.29 159	87.56 188	89.06 313

EPNet_dtu		75.46 323	74.86 315	77.23 382	82.57 393	54.60 437	86.89 220	83.09 381	71.64 229	66.25 437	85.86 326	55.99 286	88.04 383	54.92 414	86.55 209	89.05 316
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pm-mvs1		77.25 292	76.68 284	78.93 345	84.22 341	58.62 376	86.41 241	88.36 273	71.37 237	73.31 341	88.01 266	61.22 232	89.15 364	64.24 315	73.01 414	89.03 317

PVSNet_Blended		80.98 183	80.34 182	82.90 228	88.85 167	65.40 223	84.43 308	92.00 117	67.62 331	78.11 233	85.05 349	66.02 158	94.27 135	71.52 241	89.50 144	89.01 318

PAPM		77.68 282	76.40 290	81.51 271	87.29 259	61.85 329	83.78 323	89.59 212	64.74 377	71.23 370	88.70 242	62.59 202	93.66 171	52.66 426	87.03 200	89.01 318

WTY-MVS		75.65 320	75.68 298	75.57 396	86.40 289	56.82 405	77.92 430	82.40 392	65.10 372	76.18 283	87.72 271	63.13 195	80.90 451	60.31 364	81.96 294	89.00 320

无先验							87.48 190	88.98 247	60.00 432				94.12 144	67.28 288		88.97 321

GSMVS																88.96 322

sam_mvs1												51.32 340				88.96 322

SCA		74.22 337	72.33 350	79.91 317	84.05 346	62.17 323	79.96 399	79.29 437	66.30 351	72.38 356	80.13 432	51.95 329	88.60 375	59.25 375	77.67 351	88.96 322

miper_lstm_enhance		74.11 339	73.11 341	77.13 383	80.11 430	59.62 368	72.23 466	86.92 317	66.76 341	70.40 376	82.92 396	56.93 278	82.92 435	69.06 272	72.63 416	88.87 325

ACMM	73.20 8	80.78 195	79.84 198	83.58 193	89.31 150	68.37 136	89.99 84	91.60 142	70.28 274	77.25 253	89.66 210	53.37 312	93.53 180	74.24 211	82.85 283	88.85 326
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs6		74.69 332	73.39 336	78.61 350	81.38 414	57.48 397	86.64 232	87.95 284	64.99 376	70.18 379	86.61 306	50.43 355	89.52 355	62.12 344	70.18 432	88.83 327

原ACMM1				84.35 144	93.01 67	68.79 119		92.44 85	63.96 391	81.09 170	91.57 144	66.06 157	95.45 77	67.19 290	94.82 50	88.81 328

CNLPA		78.08 268	76.79 279	81.97 262	90.40 111	71.07 73	87.59 188	84.55 355	66.03 356	72.38 356	89.64 211	57.56 270	86.04 405	59.61 371	83.35 276	88.79 329

UWE-MVS		72.13 376	71.49 358	74.03 418	86.66 282	47.70 479	81.40 373	76.89 457	63.60 394	75.59 292	84.22 367	39.94 448	85.62 410	48.98 449	86.13 219	88.77 330

UBG		73.08 361	72.27 351	75.51 398	88.02 211	51.29 466	78.35 424	77.38 452	65.52 363	73.87 335	82.36 405	45.55 410	86.48 400	55.02 413	84.39 255	88.75 331

K. test v3		71.19 381	68.51 394	79.21 341	83.04 377	57.78 392	84.35 312	76.91 456	72.90 210	62.99 461	82.86 398	39.27 452	91.09 314	61.65 352	52.66 491	88.75 331

旧先验1					91.96 82	65.79 214		86.37 329			93.08 94	69.31 104			92.74 82	88.74 333

PatchmatchNet		73.12 359	71.33 362	78.49 357	83.18 370	60.85 349	79.63 402	78.57 442	64.13 385	71.73 364	79.81 437	51.20 345	85.97 406	57.40 395	76.36 373	88.66 334
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SixPastTwentyTwo		73.37 351	71.26 365	79.70 328	85.08 323	57.89 388	85.57 268	83.56 371	71.03 249	65.66 441	85.88 325	42.10 435	92.57 237	59.11 377	63.34 466	88.65 335

SSC-MVS3.2		73.35 354	73.39 336	73.23 424	85.30 316	49.01 477	74.58 457	81.57 403	75.21 136	73.68 337	85.58 334	52.53 315	82.05 442	54.33 418	77.69 350	88.63 336

PS-MVSNAJ		81.69 165	81.02 167	83.70 189	89.51 137	68.21 144	84.28 313	90.09 194	70.79 255	81.26 169	85.62 333	63.15 192	94.29 133	75.62 195	88.87 156	88.59 337

xiu_mvs_v2_base		81.69 165	81.05 166	83.60 191	89.15 158	68.03 150	84.46 305	90.02 195	70.67 259	81.30 168	86.53 312	63.17 191	94.19 142	75.60 196	88.54 164	88.57 338

MonoMVSNet		76.49 306	75.80 295	78.58 352	81.55 410	58.45 377	86.36 246	86.22 331	74.87 151	74.73 323	83.73 379	51.79 336	88.73 372	70.78 249	72.15 420	88.55 339

CostFormer		75.24 328	73.90 330	79.27 339	82.65 391	58.27 381	80.80 380	82.73 390	61.57 419	75.33 307	83.13 392	55.52 289	91.07 315	64.98 309	78.34 344	88.45 340

lessismore_v0				78.97 344	81.01 420	57.15 401		65.99 493		61.16 468	82.82 400	39.12 454	91.34 301	59.67 370	46.92 498	88.43 341

OpenMVS	72.83 10	79.77 222	78.33 238	84.09 165	85.17 318	69.91 95	90.57 69	90.97 161	66.70 342	72.17 359	91.91 125	54.70 298	93.96 148	61.81 350	90.95 117	88.41 342

usedtu_dtu_shiyan1		76.43 307	75.32 309	79.76 324	83.00 378	60.72 351	81.74 364	88.76 260	68.99 312	72.98 346	84.19 368	56.41 284	90.27 338	62.39 337	79.40 328	88.31 343

FE-MVSNET3		76.43 307	75.32 309	79.76 324	83.00 378	60.72 351	81.74 364	88.76 260	68.99 312	72.98 346	84.19 368	56.41 284	90.27 338	62.39 337	79.40 328	88.31 343

reproduce_monomvs		75.40 326	74.38 324	78.46 358	83.92 349	57.80 391	83.78 323	86.94 315	73.47 193	72.25 358	84.47 357	38.74 456	89.27 360	75.32 200	70.53 430	88.31 343

VortexMVS		78.57 257	77.89 248	80.59 297	85.89 299	62.76 311	85.61 267	89.62 211	72.06 224	74.99 318	85.38 339	55.94 287	90.77 330	74.99 202	76.58 363	88.23 346

OurMVSNet-221017-0		74.26 336	72.42 349	79.80 321	83.76 353	59.59 369	85.92 260	86.64 323	66.39 350	66.96 425	87.58 275	39.46 451	91.60 282	65.76 303	69.27 435	88.22 347

LS3D		76.95 297	74.82 316	83.37 202	90.45 109	67.36 176	89.15 121	86.94 315	61.87 418	69.52 390	90.61 182	51.71 337	94.53 126	46.38 464	86.71 207	88.21 348

WBMVS		73.43 348	72.81 344	75.28 402	87.91 216	50.99 468	78.59 420	81.31 408	65.51 365	74.47 328	84.83 352	46.39 397	86.68 397	58.41 385	77.86 346	88.17 349

XVG-ACMP-BASELINE		76.11 314	74.27 326	81.62 268	83.20 369	64.67 254	83.60 331	89.75 206	69.75 289	71.85 363	87.09 292	32.78 476	92.11 259	69.99 262	80.43 316	88.09 350

gbinet_0.2-2-1-0.02		73.24 357	70.86 373	80.39 301	78.03 455	61.62 333	83.10 345	86.69 320	65.98 357	69.29 394	76.15 469	49.77 365	91.51 293	62.75 330	66.00 452	88.03 351

tpm2		73.26 356	71.46 359	78.63 349	83.34 363	56.71 408	80.65 386	80.40 422	56.63 462	73.55 339	82.02 412	51.80 335	91.24 304	56.35 407	78.42 342	87.95 352

MDTV_nov1_ep13_2view						37.79 506	75.16 451		55.10 468	66.53 432		49.34 371		53.98 419		87.94 353

Patchmatch-test		64.82 439	63.24 440	69.57 452	79.42 442	49.82 474	63.49 500	69.05 485	51.98 478	59.95 474	80.13 432	50.91 347	70.98 495	40.66 485	73.57 408	87.90 354

PLC	70.83 11	78.05 270	76.37 291	83.08 218	91.88 85	67.80 159	88.19 167	89.46 216	64.33 384	69.87 387	88.38 253	53.66 308	93.58 172	58.86 380	82.73 285	87.86 355
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		72.37 371	71.71 356	74.35 413	82.19 399	52.00 456	79.22 408	77.29 453	64.56 379	72.95 348	83.68 382	51.35 339	83.26 434	58.33 387	75.80 377	87.81 356

Patchmatch-RL test		70.24 395	67.78 409	77.61 375	77.43 462	59.57 370	71.16 470	70.33 479	62.94 402	68.65 399	72.77 481	50.62 352	85.49 412	69.58 267	66.58 449	87.77 357

F-COLMAP		76.38 311	74.33 325	82.50 247	89.28 152	66.95 190	88.41 156	89.03 244	64.05 388	66.83 427	88.61 246	46.78 393	92.89 223	57.48 393	78.55 336	87.67 358

Baseline_NR-MVSNet		78.15 267	78.33 238	77.61 375	85.79 301	56.21 418	86.78 226	85.76 339	73.60 187	77.93 238	87.57 276	65.02 169	88.99 366	67.14 291	75.33 390	87.63 359

CL-MVSNet_self_test		72.37 371	71.46 359	75.09 404	79.49 441	53.53 445	80.76 383	85.01 349	69.12 306	70.51 374	82.05 411	57.92 266	84.13 424	52.27 428	66.00 452	87.60 360

ACMH+	68.96 14	76.01 316	74.01 327	82.03 260	88.60 184	65.31 231	88.86 131	87.55 294	70.25 276	67.75 413	87.47 281	41.27 440	93.19 208	58.37 386	75.94 376	87.60 360

1314		76.53 302	75.30 311	80.21 309	83.93 348	62.32 321	84.66 295	88.81 254	60.23 429	70.16 381	84.07 372	55.30 291	90.73 333	67.37 287	83.21 279	87.59 362

blended_shiyan6		73.38 349	71.17 366	80.01 315	78.36 450	61.48 337	82.43 354	87.27 304	65.40 367	68.56 402	77.55 456	51.94 331	91.01 317	63.27 323	65.76 454	87.55 363

blended_shiyan8		73.38 349	71.17 366	80.02 314	78.36 450	61.51 336	82.43 354	87.28 301	65.40 367	68.61 400	77.53 457	51.91 332	91.00 320	63.28 322	65.76 454	87.53 364

API-MVS		81.99 158	81.23 162	84.26 155	90.94 99	70.18 93	91.10 63	89.32 225	71.51 235	78.66 218	88.28 256	65.26 165	95.10 99	64.74 311	91.23 111	87.51 365

AdaColmap		80.58 203	79.42 210	84.06 170	93.09 64	68.91 117	89.36 111	88.97 249	69.27 299	75.70 291	89.69 208	57.20 276	95.77 66	63.06 326	88.41 168	87.50 366

0.4-1-1-0.1		70.93 385	67.94 404	79.91 317	79.35 443	61.27 339	78.95 414	82.19 396	63.36 395	67.50 416	69.40 490	39.83 450	91.04 316	62.44 336	68.40 441	87.40 367

PVSNet_BlendedMVS		80.60 200	80.02 192	82.36 252	88.85 167	65.40 223	86.16 254	92.00 117	69.34 297	78.11 233	86.09 323	66.02 158	94.27 135	71.52 241	82.06 293	87.39 368

sss		73.60 346	73.64 334	73.51 423	82.80 386	55.01 433	76.12 442	81.69 402	62.47 410	74.68 324	85.85 327	57.32 273	78.11 462	60.86 360	80.93 306	87.39 368

wanda-best-256-512		72.94 364	70.66 374	79.79 322	77.80 457	61.03 345	81.31 374	87.15 309	65.18 370	68.09 407	76.28 466	51.32 340	90.97 321	63.06 326	65.76 454	87.35 370

FE-blended-shiyan7		72.94 364	70.66 374	79.79 322	77.80 457	61.03 345	81.31 374	87.15 309	65.18 370	68.09 407	76.28 466	51.32 340	90.97 321	63.06 326	65.76 454	87.35 370

usedtu_blend_shiyan5		73.29 355	70.96 370	80.25 307	77.80 457	62.16 324	84.44 307	87.38 299	64.41 381	68.09 407	76.28 466	51.32 340	91.23 305	63.21 324	65.76 454	87.35 370

IterMVS-SCA-FT		75.43 324	73.87 331	80.11 312	82.69 389	64.85 251	81.57 369	83.47 373	69.16 305	70.49 375	84.15 371	51.95 329	88.15 381	69.23 269	72.14 421	87.34 373

PVSNet	64.34 18	72.08 377	70.87 372	75.69 394	86.21 292	56.44 412	74.37 459	80.73 413	62.06 416	70.17 380	82.23 409	42.86 429	83.31 433	54.77 415	84.45 253	87.32 374

tt0320-xc		70.11 397	67.45 415	78.07 365	85.33 315	59.51 371	83.28 340	78.96 440	58.77 444	67.10 424	80.28 430	36.73 466	87.42 391	56.83 403	59.77 480	87.29 375

新几何1				83.42 199	93.13 61	70.71 82		85.48 342	57.43 458	81.80 156	91.98 124	63.28 186	92.27 254	64.60 312	92.99 77	87.27 376

blend_shiyan4		72.29 373	69.65 386	80.21 309	78.24 453	62.16 324	82.29 357	87.27 304	65.41 366	68.43 406	76.42 465	39.91 449	91.23 305	63.21 324	65.66 459	87.22 377

TR-MVS		77.44 287	76.18 292	81.20 282	88.24 197	63.24 296	84.61 300	86.40 328	67.55 332	77.81 241	86.48 313	54.10 303	93.15 210	57.75 392	82.72 286	87.20 378

0.3-1-1-0.015		70.03 399	66.80 423	79.72 327	78.18 454	61.07 343	77.63 432	82.32 395	62.65 408	65.50 442	67.29 491	37.62 464	90.91 323	61.99 347	68.04 443	87.19 379

TransMVSNet (Re)		75.39 327	74.56 320	77.86 368	85.50 311	57.10 402	86.78 226	86.09 335	72.17 222	71.53 367	87.34 282	63.01 196	89.31 359	56.84 402	61.83 472	87.17 380

ACMH	67.68 16	75.89 317	73.93 329	81.77 266	88.71 181	66.61 194	88.62 147	89.01 246	69.81 285	66.78 428	86.70 303	41.95 437	91.51 293	55.64 409	78.14 345	87.17 380
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
KD-MVS_self_test		68.81 410	67.59 413	72.46 434	74.29 476	45.45 487	77.93 429	87.00 313	63.12 397	63.99 456	78.99 446	42.32 432	84.77 420	56.55 406	64.09 465	87.16 382

EPMVS		69.02 409	68.16 398	71.59 439	79.61 439	49.80 475	77.40 434	66.93 491	62.82 405	70.01 382	79.05 442	45.79 407	77.86 464	56.58 405	75.26 392	87.13 383

CR-MVSNet		73.37 351	71.27 364	79.67 330	81.32 417	65.19 233	75.92 444	80.30 424	59.92 433	72.73 350	81.19 417	52.50 317	86.69 396	59.84 368	77.71 348	87.11 384

RPMNet		73.51 347	70.49 378	82.58 246	81.32 417	65.19 233	75.92 444	92.27 97	57.60 455	72.73 350	76.45 462	52.30 320	95.43 79	48.14 456	77.71 348	87.11 384

test_vis1_n_1920		75.52 322	75.78 296	74.75 410	79.84 434	57.44 398	83.26 341	85.52 341	62.83 404	79.34 208	86.17 321	45.10 414	79.71 455	78.75 151	81.21 304	87.10 386

tt0320		70.49 393	68.03 401	77.89 367	84.78 329	59.12 373	83.55 332	80.44 420	58.13 450	67.43 420	80.41 428	39.26 453	87.54 390	55.12 411	63.18 468	86.99 387

XXY-MVS		75.41 325	75.56 301	74.96 405	83.59 358	57.82 390	80.59 387	83.87 367	66.54 349	74.93 320	88.31 255	63.24 189	80.09 454	62.16 343	76.85 360	86.97 388

tpmrst		72.39 369	72.13 352	73.18 428	80.54 424	49.91 473	79.91 400	79.08 439	63.11 398	71.69 365	79.95 434	55.32 290	82.77 437	65.66 304	73.89 405	86.87 389

0.4-1-1-0.2		70.01 400	66.86 422	79.44 336	77.61 460	60.64 355	76.77 439	82.34 394	62.40 411	65.91 440	66.65 492	40.05 447	90.83 325	61.77 351	68.24 442	86.86 390

thres200		75.55 321	74.47 322	78.82 347	87.78 225	57.85 389	83.07 348	83.51 372	72.44 217	75.84 289	84.42 358	52.08 326	91.75 276	47.41 459	83.64 270	86.86 390

ITE_SJBPF				78.22 360	81.77 406	60.57 356		83.30 375	69.25 301	67.54 415	87.20 288	36.33 469	87.28 393	54.34 417	74.62 399	86.80 392

test222					91.50 88	68.26 139	84.16 317	83.20 380	54.63 470	79.74 198	91.63 140	58.97 257			91.42 106	86.77 393

MIMVSNet		70.69 389	69.30 388	74.88 407	84.52 336	56.35 416	75.87 446	79.42 434	64.59 378	67.76 412	82.41 404	41.10 441	81.54 445	46.64 463	81.34 301	86.75 394

BH-untuned		79.47 229	78.60 230	82.05 259	89.19 157	65.91 208	86.07 256	88.52 271	72.18 221	75.42 299	87.69 273	61.15 233	93.54 179	60.38 363	86.83 205	86.70 395

FE-MVSNET2		72.88 367	71.28 363	77.67 372	78.30 452	57.78 392	84.43 308	88.92 252	69.56 292	64.61 450	81.67 414	46.73 395	88.54 377	59.33 373	67.99 444	86.69 396

LTVRE_ROB	69.57 13	76.25 312	74.54 321	81.41 274	88.60 184	64.38 264	79.24 407	89.12 242	70.76 257	69.79 389	87.86 269	49.09 376	93.20 206	56.21 408	80.16 318	86.65 397
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
testdata				79.97 316	90.90 100	64.21 267		84.71 352	59.27 439	85.40 78	92.91 96	62.02 214	89.08 365	68.95 273	91.37 108	86.63 398

MIMVSNet1		68.58 413	66.78 424	73.98 419	80.07 431	51.82 460	80.77 382	84.37 356	64.40 382	59.75 475	82.16 410	36.47 468	83.63 428	42.73 479	70.33 431	86.48 399

tfpnnormal		74.39 334	73.16 340	78.08 364	86.10 297	58.05 383	84.65 297	87.53 295	70.32 273	71.22 371	85.63 332	54.97 292	89.86 348	43.03 478	75.02 395	86.32 400

D2MVS		74.82 331	73.21 339	79.64 331	79.81 435	62.56 315	80.34 392	87.35 300	64.37 383	68.86 397	82.66 402	46.37 399	90.10 343	67.91 282	81.24 303	86.25 401

tpm cat1		70.57 390	68.31 396	77.35 380	82.41 397	57.95 387	78.08 426	80.22 426	52.04 476	68.54 403	77.66 455	52.00 328	87.84 386	51.77 429	72.07 422	86.25 401

CVMVSNet		72.99 363	72.58 347	74.25 415	84.28 339	50.85 469	86.41 241	83.45 374	44.56 490	73.23 343	87.54 279	49.38 370	85.70 408	65.90 301	78.44 339	86.19 403

AllTest		70.96 384	68.09 400	79.58 333	85.15 320	63.62 280	84.58 301	79.83 429	62.31 412	60.32 472	86.73 297	32.02 477	88.96 369	50.28 440	71.57 425	86.15 404

TestCases				79.58 333	85.15 320	63.62 280		79.83 429	62.31 412	60.32 472	86.73 297	32.02 477	88.96 369	50.28 440	71.57 425	86.15 404

test-LLR		72.94 364	72.43 348	74.48 411	81.35 415	58.04 384	78.38 421	77.46 449	66.66 343	69.95 385	79.00 444	48.06 382	79.24 456	66.13 296	84.83 242	86.15 404

test-mter		71.41 380	70.39 381	74.48 411	81.35 415	58.04 384	78.38 421	77.46 449	60.32 428	69.95 385	79.00 444	36.08 470	79.24 456	66.13 296	84.83 242	86.15 404

IterMVS		74.29 335	72.94 343	78.35 359	81.53 411	63.49 290	81.58 368	82.49 391	68.06 328	69.99 384	83.69 381	51.66 338	85.54 411	65.85 302	71.64 424	86.01 408
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		76.78 299	74.57 319	83.42 199	93.29 53	69.46 106	88.55 151	83.70 368	63.98 390	70.20 378	88.89 238	54.01 306	94.80 115	46.66 461	81.88 297	86.01 408

ppachtmachnet_test		70.04 398	67.34 417	78.14 362	79.80 436	61.13 340	79.19 409	80.59 415	59.16 440	65.27 445	79.29 441	46.75 394	87.29 392	49.33 447	66.72 447	86.00 410

mmtdpeth		74.16 338	73.01 342	77.60 377	83.72 354	61.13 340	85.10 284	85.10 346	72.06 224	77.21 259	80.33 429	43.84 423	85.75 407	77.14 173	52.61 492	85.91 411

test_fmvs1_n		70.86 387	70.24 382	72.73 432	72.51 491	55.28 430	81.27 376	79.71 431	51.49 480	78.73 215	84.87 351	27.54 487	77.02 467	76.06 188	79.97 322	85.88 412

Patchmtry		70.74 388	69.16 391	75.49 399	80.72 421	54.07 442	74.94 455	80.30 424	58.34 447	70.01 382	81.19 417	52.50 317	86.54 398	53.37 423	71.09 428	85.87 413

dtuonly		69.95 401	69.98 384	69.85 451	73.09 487	49.46 476	74.55 458	76.40 459	57.56 457	67.82 411	86.31 318	50.89 351	74.23 489	61.46 354	81.71 299	85.86 414

WB-MVSnew		71.96 378	71.65 357	72.89 430	84.67 335	51.88 459	82.29 357	77.57 448	62.31 412	73.67 338	83.00 394	53.49 311	81.10 450	45.75 469	82.13 292	85.70 415

test_fmvs2		68.35 418	67.48 414	70.98 447	69.50 495	51.95 457	80.05 397	76.38 460	49.33 484	74.65 325	84.38 360	23.30 496	75.40 484	74.51 207	75.17 394	85.60 416

usedtu_dtu_shiyan2		64.75 440	61.63 448	74.10 417	70.64 493	53.18 452	82.10 361	81.27 409	56.22 465	56.39 486	74.67 476	27.94 486	83.56 429	42.71 480	62.73 469	85.57 417

ambc				75.24 403	73.16 485	50.51 471	63.05 501	87.47 297		64.28 452	77.81 454	17.80 502	89.73 352	57.88 391	60.64 477	85.49 418

mvs5depth		69.45 406	67.45 415	75.46 400	73.93 477	55.83 422	79.19 409	83.23 377	66.89 338	71.63 366	83.32 388	33.69 475	85.09 416	59.81 369	55.34 488	85.46 419

UnsupCasMVSNet_eth		67.33 423	65.99 427	71.37 441	73.48 482	51.47 464	75.16 451	85.19 344	65.20 369	60.78 469	80.93 424	42.35 431	77.20 466	57.12 397	53.69 490	85.44 420

PatchT		68.46 416	67.85 405	70.29 449	80.70 422	43.93 495	72.47 465	74.88 466	60.15 430	70.55 373	76.57 461	49.94 362	81.59 444	50.58 436	74.83 397	85.34 421

Anonymous20240521		68.80 411	67.22 419	73.55 422	74.33 475	54.11 441	83.18 342	85.61 340	58.15 449	61.68 466	80.94 422	30.71 482	81.27 449	57.00 400	73.34 413	85.28 422

test_cas_vis1_n_1920		73.76 344	73.74 333	73.81 421	75.90 467	59.77 366	80.51 388	82.40 392	58.30 448	81.62 161	85.69 329	44.35 420	76.41 473	76.29 184	78.61 335	85.23 423

ADS-MVSNet2		66.20 435	63.33 439	74.82 408	79.92 432	58.75 375	67.55 485	75.19 464	53.37 473	65.25 446	75.86 471	42.32 432	80.53 453	41.57 483	68.91 437	85.18 424

ADS-MVSNet		64.36 441	62.88 443	68.78 458	79.92 432	47.17 483	67.55 485	71.18 478	53.37 473	65.25 446	75.86 471	42.32 432	73.99 491	41.57 483	68.91 437	85.18 424

FMVSNet5		69.50 405	67.96 402	74.15 416	82.97 383	55.35 429	80.01 398	82.12 398	62.56 409	63.02 459	81.53 415	36.92 465	81.92 443	48.42 451	74.06 403	85.17 426

pmmvs5		71.55 379	70.20 383	75.61 395	77.83 456	56.39 413	81.74 364	80.89 410	57.76 453	67.46 418	84.49 356	49.26 374	85.32 415	57.08 398	75.29 391	85.11 427

testing3		68.56 414	67.67 411	71.22 445	87.33 254	42.87 497	83.06 349	71.54 477	70.36 270	69.08 396	84.38 360	30.33 483	85.69 409	37.50 492	75.45 386	85.09 428

UWE-MVS-28		65.32 436	64.93 430	66.49 467	78.70 447	38.55 505	77.86 431	64.39 498	62.00 417	64.13 454	83.60 383	41.44 438	76.00 477	31.39 499	80.89 307	84.92 429

CMPMVS	51.72 21	70.19 396	68.16 398	76.28 389	73.15 486	57.55 396	79.47 404	83.92 365	48.02 486	56.48 485	84.81 353	43.13 427	86.42 401	62.67 334	81.81 298	84.89 430
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testgi		66.67 429	66.53 425	67.08 466	75.62 471	41.69 502	75.93 443	76.50 458	66.11 353	65.20 448	86.59 307	35.72 471	74.71 486	43.71 475	73.38 412	84.84 431

MSDG		73.36 353	70.99 369	80.49 300	84.51 337	65.80 213	80.71 385	86.13 334	65.70 360	65.46 443	83.74 378	44.60 416	90.91 323	51.13 435	76.89 358	84.74 432

pmmvs4		74.03 342	71.91 353	80.39 301	81.96 403	68.32 137	81.45 371	82.14 397	59.32 438	69.87 387	85.13 346	52.40 319	88.13 382	60.21 365	74.74 398	84.73 433

gg-mvs-nofinetune		69.95 401	67.96 402	75.94 391	83.07 375	54.51 439	77.23 436	70.29 480	63.11 398	70.32 377	62.33 495	43.62 424	88.69 373	53.88 420	87.76 186	84.62 434

test_fmvs1		70.93 385	70.52 377	72.16 435	73.71 479	55.05 432	80.82 379	78.77 441	51.21 481	78.58 220	84.41 359	31.20 481	76.94 468	75.88 192	80.12 321	84.47 435

nomal-1		73.10 360	71.76 355	77.13 383	82.58 392	65.50 221	73.53 463	79.64 432	66.14 352	72.17 359	81.27 416	46.45 396	81.47 447	62.08 346	81.93 296	84.42 436

BH-w/o		78.21 264	77.33 268	80.84 292	88.81 171	65.13 235	84.87 290	87.85 288	69.75 289	74.52 327	84.74 355	61.34 228	93.11 213	58.24 388	85.84 229	84.27 437

MVS		78.19 266	76.99 274	81.78 265	85.66 304	66.99 186	84.66 295	90.47 178	55.08 469	72.02 362	85.27 341	63.83 183	94.11 145	66.10 298	89.80 139	84.24 438

COLMAP_ROB	66.92 17	73.01 362	70.41 380	80.81 293	87.13 263	65.63 217	88.30 164	84.19 362	62.96 401	63.80 458	87.69 273	38.04 461	92.56 238	46.66 461	74.91 396	84.24 438
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
new-patchmatchnet		61.73 447	61.73 447	61.70 473	72.74 489	24.50 521	69.16 480	78.03 445	61.40 420	56.72 484	75.53 474	38.42 458	76.48 472	45.95 467	57.67 481	84.13 440

TESTMET0.1,1		69.89 403	69.00 392	72.55 433	79.27 445	56.85 404	78.38 421	74.71 469	57.64 454	68.09 407	77.19 459	37.75 462	76.70 469	63.92 316	84.09 259	84.10 441

test_fmvs3		63.36 444	61.82 446	67.98 463	62.51 504	46.96 485	77.37 435	74.03 471	45.24 489	67.50 416	78.79 447	12.16 508	72.98 494	72.77 228	66.02 451	83.99 442

our_test_3		69.14 408	67.00 420	75.57 396	79.80 436	58.80 374	77.96 428	77.81 446	59.55 436	62.90 462	78.25 451	47.43 385	83.97 425	51.71 430	67.58 446	83.93 443

test_vis1_n		69.85 404	69.21 390	71.77 438	72.66 490	55.27 431	81.48 370	76.21 461	52.03 477	75.30 308	83.20 391	28.97 484	76.22 475	74.60 206	78.41 343	83.81 444

tpmvs		71.09 383	69.29 389	76.49 388	82.04 401	56.04 419	78.92 415	81.37 407	64.05 388	67.18 423	78.28 450	49.74 366	89.77 350	49.67 445	72.37 417	83.67 445

test20.03		67.45 422	66.95 421	68.94 455	75.48 472	44.84 493	77.50 433	77.67 447	66.66 343	63.01 460	83.80 376	47.02 389	78.40 460	42.53 482	68.86 439	83.58 446

test0.0.03 1		68.00 420	67.69 410	68.90 456	77.55 461	47.43 480	75.70 447	72.95 476	66.66 343	66.56 431	82.29 408	48.06 382	75.87 479	44.97 474	74.51 400	83.41 447

Anonymous20231206		68.60 412	67.80 408	71.02 446	80.23 428	50.75 470	78.30 425	80.47 418	56.79 461	66.11 439	82.63 403	46.35 400	78.95 458	43.62 476	75.70 378	83.36 448

EU-MVSNet		68.53 415	67.61 412	71.31 444	78.51 449	47.01 484	84.47 303	84.27 360	42.27 493	66.44 436	84.79 354	40.44 445	83.76 426	58.76 382	68.54 440	83.17 449

dp		66.80 427	65.43 428	70.90 448	79.74 438	48.82 478	75.12 453	74.77 467	59.61 435	64.08 455	77.23 458	42.89 428	80.72 452	48.86 450	66.58 449	83.16 450

pmmvs-eth3d		70.50 392	67.83 407	78.52 356	77.37 463	66.18 200	81.82 362	81.51 404	58.90 443	63.90 457	80.42 427	42.69 430	86.28 402	58.56 383	65.30 461	83.11 451

YYNet1		65.03 437	62.91 442	71.38 440	75.85 469	56.60 410	69.12 481	74.66 470	57.28 459	54.12 489	77.87 453	45.85 406	74.48 487	49.95 443	61.52 475	83.05 452

MDA-MVSNet-bldmvs		66.68 428	63.66 438	75.75 393	79.28 444	60.56 357	73.92 461	78.35 444	64.43 380	50.13 495	79.87 436	44.02 422	83.67 427	46.10 466	56.86 482	83.03 453

MDA-MVSNet_test_wron		65.03 437	62.92 441	71.37 441	75.93 466	56.73 406	69.09 482	74.73 468	57.28 459	54.03 490	77.89 452	45.88 405	74.39 488	49.89 444	61.55 474	82.99 454

USDC		70.33 394	68.37 395	76.21 390	80.60 423	56.23 417	79.19 409	86.49 326	60.89 423	61.29 467	85.47 337	31.78 479	89.47 357	53.37 423	76.21 374	82.94 455

Syy-MVS		68.05 419	67.85 405	68.67 459	84.68 332	40.97 503	78.62 418	73.08 474	66.65 346	66.74 429	79.46 439	52.11 325	82.30 440	32.89 497	76.38 371	82.75 456

myMVS_eth3d		67.02 426	66.29 426	69.21 454	84.68 332	42.58 498	78.62 418	73.08 474	66.65 346	66.74 429	79.46 439	31.53 480	82.30 440	39.43 488	76.38 371	82.75 456

ttmdpeth		59.91 450	57.10 454	68.34 461	67.13 499	46.65 486	74.64 456	67.41 490	48.30 485	62.52 465	85.04 350	20.40 498	75.93 478	42.55 481	45.90 501	82.44 458

OpenMVS_ROB	64.09 19	70.56 391	68.19 397	77.65 374	80.26 426	59.41 372	85.01 287	82.96 386	58.76 445	65.43 444	82.33 406	37.63 463	91.23 305	45.34 473	76.03 375	82.32 459

JIA-IIPM		66.32 432	62.82 444	76.82 386	77.09 464	61.72 332	65.34 494	75.38 463	58.04 452	64.51 451	62.32 496	42.05 436	86.51 399	51.45 433	69.22 436	82.21 460

dmvs_re		71.14 382	70.58 376	72.80 431	81.96 403	59.68 367	75.60 448	79.34 436	68.55 320	69.27 395	80.72 425	49.42 369	76.54 470	52.56 427	77.79 347	82.19 461

EG-PatchMatch MVS		74.04 340	71.82 354	80.71 295	84.92 326	67.42 172	85.86 263	88.08 277	66.04 355	64.22 453	83.85 374	35.10 472	92.56 238	57.44 394	80.83 309	82.16 462

FE-MVSNET		67.25 425	65.33 429	73.02 429	75.86 468	52.54 454	80.26 395	80.56 416	63.80 393	60.39 470	79.70 438	41.41 439	84.66 422	43.34 477	62.62 470	81.86 463

MVP-Stereo		76.12 313	74.46 323	81.13 285	85.37 314	69.79 97	84.42 310	87.95 284	65.03 374	67.46 418	85.33 340	53.28 313	91.73 278	58.01 390	83.27 278	81.85 464
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
TDRefinement		67.49 421	64.34 433	76.92 385	73.47 483	61.07 343	84.86 291	82.98 385	59.77 434	58.30 479	85.13 346	26.06 488	87.89 385	47.92 458	60.59 478	81.81 465

GG-mvs-BLEND				75.38 401	81.59 409	55.80 423	79.32 406	69.63 482		67.19 422	73.67 479	43.24 426	88.90 371	50.41 437	84.50 249	81.45 466

KD-MVS_2432*1600		66.22 433	63.89 436	73.21 425	75.47 473	53.42 447	70.76 473	84.35 357	64.10 386	66.52 433	78.52 448	34.55 473	84.98 417	50.40 438	50.33 495	81.23 467

miper_refine_blended		66.22 433	63.89 436	73.21 425	75.47 473	53.42 447	70.76 473	84.35 357	64.10 386	66.52 433	78.52 448	34.55 473	84.98 417	50.40 438	50.33 495	81.23 467

test_0402		72.79 368	70.44 379	79.84 320	88.13 205	65.99 206	85.93 259	84.29 359	65.57 362	67.40 421	85.49 336	46.92 390	92.61 234	35.88 494	74.38 401	80.94 469

MVStest1		56.63 454	52.76 460	68.25 462	61.67 505	53.25 451	71.67 468	68.90 487	38.59 498	50.59 494	83.05 393	25.08 490	70.66 496	36.76 493	38.56 502	80.83 470

UnsupCasMVSNet_bld		63.70 443	61.53 449	70.21 450	73.69 480	51.39 465	72.82 464	81.89 399	55.63 467	57.81 481	71.80 483	38.67 457	78.61 459	49.26 448	52.21 493	80.63 471

PatchmatchNet1														37.67 491	64.79 462	80.58 472
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
LCM-MVSNet		54.25 456	49.68 466	67.97 464	53.73 513	45.28 490	66.85 489	80.78 412	35.96 502	39.45 505	62.23 497	8.70 512	78.06 463	48.24 455	51.20 494	80.57 473

N_pmnet		52.79 461	53.26 459	51.40 489	78.99 446	7.68 537	69.52 477	3.89 537	51.63 479	57.01 483	74.98 475	40.83 443	65.96 503	37.78 490	64.67 463	80.56 474

TinyColmap		67.30 424	64.81 431	74.76 409	81.92 405	56.68 409	80.29 393	81.49 405	60.33 427	56.27 487	83.22 389	24.77 492	87.66 389	45.52 470	69.47 434	79.95 475

PM-MVS		66.41 431	64.14 434	73.20 427	73.92 478	56.45 411	78.97 413	64.96 497	63.88 392	64.72 449	80.24 431	19.84 500	83.44 432	66.24 295	64.52 464	79.71 476

ANet_high		50.57 465	46.10 469	63.99 470	48.67 518	39.13 504	70.99 472	80.85 411	61.39 421	31.18 507	57.70 504	17.02 503	73.65 493	31.22 500	15.89 519	79.18 477

LF4IMVS		64.02 442	62.19 445	69.50 453	70.90 492	53.29 450	76.13 441	77.18 454	52.65 475	58.59 477	80.98 421	23.55 495	76.52 471	53.06 425	66.66 448	78.68 478

dtuonlycased		68.45 417	67.29 418	71.92 436	80.18 429	54.90 434	79.76 401	80.38 423	60.11 431	62.57 464	76.44 464	49.34 371	82.31 439	55.05 412	61.77 473	78.53 479

PatchMatch-RL		72.38 370	70.90 371	76.80 387	88.60 184	67.38 175	79.53 403	76.17 462	62.75 406	69.36 392	82.00 413	45.51 411	84.89 419	53.62 421	80.58 313	78.12 480

MS-PatchMatch		73.83 343	72.67 345	77.30 381	83.87 350	66.02 203	81.82 362	84.66 353	61.37 422	68.61 400	82.82 400	47.29 386	88.21 380	59.27 374	84.32 256	77.68 481

DSMNet-mixed		57.77 453	56.90 455	60.38 475	67.70 497	35.61 509	69.18 479	53.97 509	32.30 508	57.49 482	79.88 435	40.39 446	68.57 501	38.78 489	72.37 417	76.97 482

CHOSEN 280x420		66.51 430	64.71 432	71.90 437	81.45 412	63.52 289	57.98 505	68.95 486	53.57 472	62.59 463	76.70 460	46.22 402	75.29 485	55.25 410	79.68 323	76.88 483

mvsany_test3		53.99 457	51.45 462	61.61 474	55.51 509	44.74 494	63.52 499	45.41 515	43.69 492	58.11 480	76.45 462	17.99 501	63.76 506	54.77 415	47.59 497	76.34 484

dmvs_testset		62.63 445	64.11 435	58.19 477	78.55 448	24.76 520	75.28 449	65.94 494	67.91 329	60.34 471	76.01 470	53.56 309	73.94 492	31.79 498	67.65 445	75.88 485

mvsany_test1		62.30 446	61.26 450	65.41 469	69.52 494	54.86 435	66.86 488	49.78 511	46.65 487	68.50 404	83.21 390	49.15 375	66.28 502	56.93 401	60.77 476	75.11 486

ArgMatch-SfM		44.04 472	39.87 477	56.58 480	50.92 517	36.22 508	59.86 503	27.68 521	33.67 506	42.15 502	71.07 485	3.10 523	59.10 508	45.79 468	24.54 510	74.41 487

PMMVS		69.34 407	68.67 393	71.35 443	75.67 470	62.03 326	75.17 450	73.46 472	50.00 483	68.68 398	79.05 442	52.07 327	78.13 461	61.16 358	82.77 284	73.90 488

test_vis1_rt		60.28 449	58.42 452	65.84 468	67.25 498	55.60 426	70.44 475	60.94 503	44.33 491	59.00 476	66.64 493	24.91 491	68.67 500	62.80 329	69.48 433	73.25 489

pmmvs3		57.79 452	54.26 457	68.37 460	64.02 503	56.72 407	75.12 453	65.17 495	40.20 495	52.93 491	69.86 489	20.36 499	75.48 482	45.45 471	55.25 489	72.90 490

ArgMatch-Sym		43.72 473	39.92 476	55.10 486	52.36 515	37.56 507	61.93 502	23.00 523	35.80 503	43.62 500	70.22 488	3.22 521	55.93 512	45.35 472	23.80 512	71.81 491

PVSNet_0	57.27 20	61.67 448	59.27 451	68.85 457	79.61 439	57.44 398	68.01 483	73.44 473	55.93 466	58.54 478	70.41 487	44.58 417	77.55 465	47.01 460	35.91 503	71.55 492

WB-MVS		54.94 455	54.72 456	55.60 484	73.50 481	20.90 523	74.27 460	61.19 502	59.16 440	50.61 493	74.15 477	47.19 388	75.78 480	17.31 517	35.07 504	70.12 493

SSC-MVS		53.88 458	53.59 458	54.75 487	72.87 488	19.59 524	73.84 462	60.53 504	57.58 456	49.18 497	73.45 480	46.34 401	75.47 483	16.20 520	32.28 506	69.20 494

test_f		52.09 462	50.82 463	55.90 482	53.82 512	42.31 501	59.42 504	58.31 507	36.45 501	56.12 488	70.96 486	12.18 507	57.79 510	53.51 422	56.57 484	67.60 495

PMMVS2		40.82 474	38.86 478	46.69 490	53.84 511	16.45 528	48.61 508	49.92 510	37.49 499	31.67 506	60.97 498	8.14 514	56.42 511	28.42 502	30.72 507	67.19 496

new_pmnet		50.91 464	50.29 464	52.78 488	68.58 496	34.94 511	63.71 498	56.63 508	39.73 496	44.95 498	65.47 494	21.93 497	58.48 509	34.98 495	56.62 483	64.92 497

MVS-HIRNet		59.14 451	57.67 453	63.57 471	81.65 407	43.50 496	71.73 467	65.06 496	39.59 497	51.43 492	57.73 503	38.34 459	82.58 438	39.53 486	73.95 404	64.62 498

APD_test1		53.31 460	49.93 465	63.42 472	65.68 500	50.13 472	71.59 469	66.90 492	34.43 504	40.58 504	71.56 484	8.65 513	76.27 474	34.64 496	55.36 487	63.86 499

test_method		31.52 478	29.28 481	38.23 495	27.03 528	6.50 542	20.94 521	62.21 501	4.05 529	22.35 517	52.50 511	13.33 505	47.58 515	27.04 504	34.04 505	60.62 500

EGC-MVSNET		52.07 463	47.05 467	67.14 465	83.51 360	60.71 353	80.50 389	67.75 488	0.07 558	0.43 560	75.85 473	24.26 493	81.54 445	28.82 501	62.25 471	59.16 501

test_vis3_rt		49.26 466	47.02 468	56.00 481	54.30 510	45.27 491	66.76 490	48.08 512	36.83 500	44.38 499	53.20 510	7.17 515	64.07 505	56.77 404	55.66 485	58.65 502

FPMVS		53.68 459	51.64 461	59.81 476	65.08 501	51.03 467	69.48 478	69.58 483	41.46 494	40.67 503	72.32 482	16.46 504	70.00 499	24.24 510	65.42 460	58.40 503

DenseAffine		31.97 476	28.22 482	43.21 493	43.10 520	27.10 515	46.21 509	11.36 527	24.92 511	27.70 510	58.81 502	1.09 527	46.50 518	26.95 505	13.85 523	56.02 504

testf1		45.72 467	41.96 471	57.00 478	56.90 507	45.32 488	66.14 491	59.26 505	26.19 509	30.89 508	60.96 499	4.14 518	70.64 497	26.39 508	46.73 499	55.04 505

APD_test2		45.72 467	41.96 471	57.00 478	56.90 507	45.32 488	66.14 491	59.26 505	26.19 509	30.89 508	60.96 499	4.14 518	70.64 497	26.39 508	46.73 499	55.04 505

LoFTR		27.52 482	24.27 486	37.29 497	34.75 524	19.27 525	33.78 514	21.60 524	12.42 521	21.61 519	56.59 506	0.91 529	40.37 520	13.94 522	22.80 514	52.22 507

RoMa-SfM		28.67 481	25.38 485	38.54 494	32.61 525	22.48 522	40.24 510	7.23 531	21.81 514	26.66 512	60.46 501	0.96 528	41.72 519	26.47 507	11.95 524	51.40 508

PMVS	37.38 22	44.16 471	40.28 475	55.82 483	40.82 521	42.54 500	65.12 495	63.99 499	34.43 504	24.48 513	57.12 505	3.92 520	76.17 476	17.10 518	55.52 486	48.75 509
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 480	25.89 484	43.81 492	44.55 519	35.46 510	28.87 520	39.07 516	18.20 517	18.58 524	40.18 519	2.68 524	47.37 516	17.07 519	23.78 513	48.60 510
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DKM		25.67 483	23.01 487	33.64 500	32.08 526	19.25 526	37.50 512	5.52 533	18.67 515	23.58 516	55.44 508	0.64 534	34.02 521	23.95 511	9.73 526	47.66 511

dongtai		45.42 469	45.38 470	45.55 491	73.36 484	26.85 518	67.72 484	34.19 517	54.15 471	49.65 496	56.41 507	25.43 489	62.94 507	19.45 515	28.09 508	46.86 512

PDCNetPlus		24.75 484	22.46 488	31.64 501	35.53 523	17.00 527	32.00 516	9.46 528	18.43 516	18.56 525	51.31 512	1.65 525	33.00 523	26.51 506	8.70 528	44.91 513

DKM-HiRes		20.87 487	19.15 492	26.02 505	25.34 529	14.13 531	29.63 519	3.62 540	14.53 520	20.13 521	50.55 513	0.47 542	24.22 528	20.96 514	7.15 533	39.70 514

RoMa-HiRes		21.63 486	19.64 491	27.59 503	22.40 530	14.25 530	29.71 518	4.10 535	15.42 519	21.09 520	54.77 509	0.72 532	28.87 524	21.01 513	7.52 532	39.65 515

kuosan		39.70 475	40.40 474	37.58 496	64.52 502	26.98 516	65.62 493	33.02 518	46.12 488	42.79 501	48.99 514	24.10 494	46.56 517	12.16 525	26.30 509	39.20 516

Gipuma		45.18 470	41.86 473	55.16 485	77.03 465	51.52 463	32.50 515	80.52 417	32.46 507	27.12 511	35.02 523	9.52 511	75.50 481	22.31 512	60.21 479	38.45 517
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MatchFormer		22.13 485	19.86 490	28.93 502	28.66 527	15.74 529	31.91 517	17.10 526	7.75 522	18.87 523	47.50 517	0.62 536	33.92 522	7.49 532	18.87 516	37.14 518

ELoFTR		14.23 492	11.56 498	22.24 506	11.02 538	6.56 541	13.59 527	7.57 530	5.55 525	11.96 531	39.09 520	0.21 547	24.93 526	9.43 531	5.66 537	35.22 519

GLUNet-SfM		12.90 495	10.00 499	21.62 507	13.58 535	8.30 535	10.19 531	9.30 529	4.31 528	12.18 530	30.90 526	0.50 540	22.76 529	4.89 533	4.14 544	33.79 520

PMatch-SfM		14.15 493	12.67 497	18.59 509	12.84 536	7.03 539	17.41 522	2.28 542	6.63 524	12.96 529	43.56 518	0.09 559	16.11 531	13.90 523	4.38 543	32.63 521

DeepMVS_CX				27.40 504	40.17 522	26.90 517		24.59 522	17.44 518	23.95 514	48.61 516	9.77 510	26.48 525	18.06 516	24.47 511	28.83 522

PMatch-Up-SfM		10.76 497	9.99 500	13.09 510	9.50 544	4.83 544	12.94 529	1.40 551	4.65 526	10.16 532	37.54 521	0.07 562	10.94 533	10.71 529	2.92 554	23.50 523

E-PMN		31.77 477	30.64 479	35.15 498	52.87 514	27.67 514	57.09 506	47.86 513	24.64 512	16.40 527	33.05 524	11.23 509	54.90 513	14.46 521	18.15 517	22.87 524

EMVS		30.81 479	29.65 480	34.27 499	50.96 516	25.95 519	56.58 507	46.80 514	24.01 513	15.53 528	30.68 527	12.47 506	54.43 514	12.81 524	17.05 518	22.43 525

MASt3R-SfM		13.55 494	13.93 495	12.41 511	10.54 541	5.97 543	16.61 523	6.07 532	4.50 527	16.53 526	48.67 515	0.73 531	9.44 534	11.56 528	10.18 525	21.81 526

MVS_clip		11.37 496	13.03 496	6.40 517	15.78 534	6.79 540	11.98 530	1.47 550	1.89 532	19.38 522	35.95 522	3.13 522	3.09 540	12.10 526	15.54 520	9.34 527

VLMVS_CLIP		15.14 491	16.11 493	12.23 512	12.32 537	7.35 538	15.53 524	20.73 525	4.02 530	22.32 518	31.59 525	4.37 517	21.02 530	11.59 527	22.52 515	8.32 528

ALIKED-LG		8.61 498	8.70 502	8.33 514	20.63 531	8.70 534	15.50 525	4.61 534	2.19 531	5.84 536	18.70 529	0.80 530	8.06 535	1.03 543	8.97 527	8.25 529

SP-MNN		4.14 510	4.24 513	3.82 520	10.32 542	1.83 559	8.11 534	1.99 546	0.82 541	2.23 544	8.27 540	0.47 542	2.14 542	1.20 541	4.77 541	7.49 530

SP-LightGlue		4.27 508	4.41 511	3.86 519	10.99 539	1.99 555	8.19 532	2.06 545	0.98 539	2.37 543	8.29 538	0.56 538	2.10 543	1.27 539	4.99 539	7.48 531

SP-SuperGlue		4.24 509	4.38 512	3.81 521	10.75 540	2.00 554	8.18 533	2.09 544	1.00 538	2.41 542	8.29 538	0.56 538	2.05 545	1.27 539	4.91 540	7.39 532

ALIKED-MNN		7.86 499	7.83 505	7.97 515	19.40 532	8.86 533	14.48 526	3.90 536	1.59 533	4.74 541	16.49 530	0.59 537	7.65 536	0.91 544	8.34 530	7.39 532

SP-DiffGlue		4.29 507	4.46 510	3.77 522	3.68 561	2.12 552	5.97 536	2.22 543	1.10 536	4.89 538	13.93 534	0.66 533	1.95 546	2.47 534	5.24 538	7.22 534

tmp_tt		18.61 489	21.40 489	10.23 513	4.82 560	10.11 532	34.70 513	30.74 520	1.48 535	23.91 515	26.07 528	28.42 485	13.41 532	27.12 503	15.35 521	7.17 535

SP-NN		4.00 511	4.12 514	3.63 523	9.92 543	1.81 560	7.94 535	1.90 548	0.86 540	2.15 545	8.00 541	0.50 540	2.09 544	1.20 541	4.63 542	6.98 536

ALIKED-NN		7.51 500	7.61 506	7.21 516	18.26 533	8.10 536	13.45 528	3.88 538	1.50 534	4.87 539	16.47 531	0.64 534	7.00 537	0.88 545	8.50 529	6.52 537

XFeat-MNN		4.39 506	4.49 509	4.10 518	2.88 563	1.91 558	5.86 537	2.57 541	1.06 537	5.04 537	13.99 533	0.43 544	4.47 538	2.00 536	6.55 535	5.92 538

VLMVS		4.54 505	4.93 508	3.37 524	4.86 559	2.23 551	3.38 545	1.77 549	0.23 557	7.94 533	11.34 537	4.62 516	2.44 541	2.43 535	7.76 531	5.44 539

XFeat-NN		3.78 512	3.96 516	3.23 525	2.65 564	1.53 563	4.99 538	1.92 547	0.81 542	4.77 540	12.37 536	0.38 545	3.39 539	1.64 537	6.13 536	4.77 540

MVS_baseline		3.29 513	4.00 515	1.16 539	3.08 562	0.09 567	1.26 554	0.24 566	0.04 560	6.52 534	16.19 532	0.30 546	0.00 563	1.53 538	6.83 534	3.39 541

wuyk23d		16.82 490	15.94 494	19.46 508	58.74 506	31.45 512	39.22 511	3.74 539	6.84 523	6.04 535	2.70 558	1.27 526	24.29 527	10.54 530	14.40 522	2.63 542

SIFT-NN		2.77 514	2.92 517	2.34 526	8.70 545	3.08 545	4.46 539	1.01 553	0.68 543	1.46 546	5.49 542	0.16 548	1.65 547	0.26 546	4.04 545	2.27 543

SIFT-MNN		2.63 515	2.75 518	2.25 527	8.10 546	2.84 546	4.08 540	1.02 552	0.68 543	1.28 547	5.34 545	0.15 549	1.64 548	0.26 546	3.88 547	2.27 543

SIFT-NN-CMatch		2.31 518	2.41 521	2.00 530	6.59 552	2.34 550	3.48 544	0.83 556	0.65 546	1.28 547	5.09 546	0.14 550	1.52 551	0.23 549	3.41 550	2.14 545

SIFT-NN-PointCN		2.07 522	2.18 525	1.74 533	5.75 555	1.65 562	3.27 547	0.73 559	0.60 553	1.07 550	4.62 552	0.13 553	1.43 555	0.21 554	3.22 551	2.12 546

SIFT-NN-UMatch		2.26 519	2.39 522	1.89 532	6.21 554	2.08 553	3.76 542	0.83 556	0.66 545	1.04 551	5.09 546	0.14 550	1.52 551	0.23 549	3.51 549	2.07 547

SIFT-NN-NCMNet		2.52 516	2.64 519	2.14 528	7.53 548	2.74 547	4.00 541	0.98 554	0.65 546	1.24 549	5.08 548	0.14 550	1.60 549	0.23 549	3.94 546	2.07 547

SIFT-NCM-Cal		2.40 517	2.52 520	2.05 529	7.74 547	2.54 548	3.75 543	0.84 555	0.65 546	0.89 554	4.78 551	0.13 553	1.60 549	0.19 557	3.71 548	2.01 549

SIFT-ConvMatch		2.25 520	2.37 523	1.90 531	7.29 549	2.37 549	3.21 548	0.75 558	0.65 546	1.03 552	4.91 549	0.12 556	1.51 553	0.22 552	3.13 552	1.81 550

SIFT-PCN-Cal		1.72 525	1.82 529	1.39 537	5.64 556	1.19 565	2.39 552	0.53 564	0.55 555	0.72 557	3.90 555	0.09 559	1.22 559	0.17 559	2.42 558	1.76 551

SIFT-UMatch		2.16 521	2.30 524	1.72 534	6.99 550	1.97 557	3.32 546	0.70 560	0.64 550	0.91 553	4.86 550	0.12 556	1.49 554	0.22 552	2.97 553	1.72 552

SIFT-PointCN		1.72 525	1.83 528	1.36 538	5.55 557	1.22 564	2.59 551	0.59 562	0.55 555	0.71 558	3.77 556	0.08 561	1.24 558	0.17 559	2.48 557	1.63 553

SIFT-CM-Cal		2.02 523	2.13 526	1.67 535	6.79 551	1.99 555	2.79 550	0.64 561	0.63 551	0.87 555	4.48 554	0.13 553	1.41 556	0.19 557	2.70 555	1.61 554

SIFT-UM-Cal		1.97 524	2.12 527	1.52 536	6.57 553	1.67 561	2.93 549	0.57 563	0.62 552	0.83 556	4.55 553	0.11 558	1.37 557	0.20 556	2.69 556	1.53 555

SIFT-NCMNet		1.44 527	1.56 530	1.08 540	5.14 558	1.07 566	1.97 553	0.32 565	0.56 554	0.64 559	3.23 557	0.07 562	1.01 560	0.14 561	1.95 559	1.15 556

test123		6.12 502	8.11 503	0.14 541	0.06 566	0.09 567	71.05 471	0.03 568	0.04 560	0.25 562	1.30 560	0.05 564	0.03 562	0.21 554	0.01 561	0.29 557

testmvs		6.04 503	8.02 504	0.10 542	0.08 565	0.03 569	69.74 476	0.04 567	0.05 559	0.31 561	1.68 559	0.02 565	0.04 561	0.24 548	0.02 560	0.25 558

mmdepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

monomultidepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

test_blank		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uanet_test		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

DCPMVS		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

cdsmvs_eth3d_5k		19.96 488	26.61 483	0.00 543	0.00 567	0.00 570	0.00 555	89.26 230	0.00 562	0.00 563	88.61 246	61.62 221	0.00 563	0.00 562	0.00 562	0.00 559

pcd_1.5k_mvsjas		5.26 504	7.02 507	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	63.15 192	0.00 563	0.00 562	0.00 562	0.00 559

sosnet-low-res		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

sosnet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uncertanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

Regformer		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

ab-mvs-re		7.23 501	9.64 501	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	86.72 299	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

Meshroom													0.00 563
: In preparation.
AliceVision / Meshro													0.00 563
: In preparation.
AliceVision_Meshroom													0.00 563
: In preparation.
PatchmatchNet2					0.00 567	30.51 513	67.30 487	67.46 489	50.92 482
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													65.90 504
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					94.58 16	71.43 61		94.16 8		90.64 22		78.62 14	97.13 17	88.60 33	96.28 16

WAC-MVS						42.58 498								39.46 487

FOURS1					95.00 10	72.39 41	95.06 1	93.84 21	74.49 159	91.30 18

test_one_0601					95.07 7	71.46 60		94.14 10	78.27 42	92.05 14	95.74 9	80.83 12

eth-test2					0.00 567

eth-test					0.00 567

ZD-MVS					94.38 30	72.22 46		92.67 75	70.98 250	87.75 53	94.07 59	74.01 39	96.70 32	84.66 72	94.84 48

test_241102_ONE					95.30 2	70.98 74		94.06 15	77.17 68	93.10 1	95.39 19	82.99 1	97.27 14

9.14			88.26 19		92.84 71		91.52 56	94.75 1	73.93 178	88.57 38	94.67 31	75.57 27	95.79 65	86.77 53	95.76 27

save fliter					93.80 45	72.35 44	90.47 74	91.17 155	74.31 165

test0726					95.27 5	71.25 66	93.60 7	94.11 11	77.33 60	92.81 4	95.79 6	80.98 10

test_part2					95.06 8	72.65 32				91.80 16

sam_mvs												50.01 360

MTGPA								92.02 115

test_post1							78.90 416				5.43 544	48.81 381	85.44 414	59.25 375

test_post											5.46 543	50.36 356	84.24 423

patchmatchnet-post											74.00 478	51.12 346	88.60 375

MTMP							92.18 39	32.83 519

gm-plane-assit					81.40 413	53.83 444			62.72 407		80.94 422		92.39 248	63.40 320

TEST9					93.26 57	72.96 25	88.75 139	91.89 123	68.44 323	85.00 83	93.10 90	74.36 34	95.41 82

test_8					93.13 61	72.57 35	88.68 145	91.84 127	68.69 318	84.87 87	93.10 90	74.43 32	95.16 92

agg_prior					92.85 69	71.94 53		91.78 131		84.41 99			94.93 104

test_prior4						72.60 34	89.01 126

test_prior2							88.85 133		75.41 127	84.91 85	93.54 77	74.28 35		83.31 87	95.86 24

旧先验2							86.56 236		58.10 451	87.04 64			88.98 367	74.07 212

新几何2							86.29 250

原ACMM2							86.86 222

testdata2													91.01 317	62.37 340

segment_acmp												73.08 46

testdata1							84.14 318		75.71 118

plane_prior7					90.08 118	68.51 133

plane_prior6					89.84 127	68.70 127						60.42 247

plane_prior4											91.00 168

plane_prior3						68.60 130			78.44 37	78.92 213

plane_prior2							91.25 60		79.12 29

plane_prior1					89.90 126

plane_prior						68.71 125	90.38 78		77.62 49						86.16 218

n2								0.00 569

nn								0.00 569

door-mid								69.98 481

test11								92.23 101

door								69.44 484

HQP5-MVS						66.98 187

HQP-NCC					89.33 147		89.17 117		76.41 97	77.23 255

ACMP_Plane					89.33 147		89.17 117		76.41 97	77.23 255

BP-MVS														77.47 168

HQP3-MVS								92.19 109							85.99 224

HQP2-MVS												60.17 250

NP-MVS					89.62 132	68.32 137					90.24 194

MDTV_nov1_ep13			69.97 385		83.18 370	53.48 446	77.10 438	80.18 428	60.45 426	69.33 393	80.44 426	48.89 380	86.90 395	51.60 431	78.51 338

ACMMP++_ref															81.95 295

ACMMP++															81.25 302

Test By Simon												64.33 177

High-resolution multi-view benchmark