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.

MM		89.16 6	89.23 7	88.97 4	90.79 98	73.65 10	92.66 24	91.17 132	86.57 1	87.39 51	94.97 21	71.70 57	97.68 1	92.19 1	95.63 28	95.57 1

casdiffmvs_mvg		85.99 54	86.09 56	85.70 77	87.65 216	67.22 169	88.69 135	93.04 42	79.64 21	85.33 69	92.54 97	73.30 36	94.50 117	83.49 76	91.14 101	95.37 2
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 64	86.15 54	84.06 144	91.71 80	64.94 218	86.47 213	91.87 108	73.63 157	86.60 60	93.02 86	76.57 15	91.87 238	83.36 77	92.15 83	95.35 3

casdiffmvs		85.11 77	85.14 76	85.01 98	87.20 231	65.77 196	87.75 170	92.83 61	77.84 43	84.36 92	92.38 99	72.15 50	93.93 141	81.27 101	90.48 112	95.33 4
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 30	87.95 20	85.70 77	89.48 133	67.88 145	88.59 139	89.05 206	80.19 12	90.70 17	95.40 15	74.56 25	93.92 142	91.54 2	92.07 85	95.31 5

3Dnovator+	77.84 4	85.48 67	84.47 86	88.51 7	91.08 89	73.49 16	93.18 12	93.78 19	80.79 8	76.66 222	93.37 76	60.40 209	96.75 26	77.20 142	93.73 66	95.29 6

BP-MVS1		84.32 85	83.71 94	86.17 64	87.84 205	67.85 146	89.38 102	89.64 182	77.73 45	83.98 99	92.12 106	56.89 235	95.43 73	84.03 73	91.75 91	95.24 7

MVS_0304		87.69 21	87.55 26	88.12 13	89.45 134	71.76 53	91.47 52	89.54 185	82.14 3	86.65 59	94.28 40	68.28 103	97.46 6	90.81 6	95.31 34	95.15 8

CS-MVS		86.69 41	86.95 39	85.90 74	90.76 99	67.57 155	92.83 18	93.30 33	79.67 19	84.57 86	92.27 100	71.47 60	95.02 96	84.24 70	93.46 69	95.13 9

TSAR-MVS + MP.		88.02 18	88.11 17	87.72 30	93.68 43	72.13 48	91.41 53	92.35 83	74.62 132	88.90 26	93.85 64	75.75 20	96.00 55	87.80 37	94.63 50	95.04 10
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 80	84.98 77	84.80 108	87.30 229	65.39 205	87.30 184	92.88 58	77.62 47	84.04 98	92.26 101	71.81 54	93.96 135	81.31 99	90.30 115	95.03 11

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 61	95.06 1	94.23 3	78.38 38	92.78 4	95.74 6	82.45 3	97.49 4	89.42 17	96.68 2	94.95 12

PC_three_1452									68.21 278	92.02 12	94.00 56	82.09 5	95.98 57	84.58 64	96.68 2	94.95 12

IS-MVSNet		83.15 111	82.81 109	84.18 134	89.94 119	63.30 256	91.59 46	88.46 228	79.04 30	79.49 162	92.16 104	65.10 137	94.28 122	67.71 239	91.86 90	94.95 12

SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 74	72.96 25	93.73 5	93.67 21	80.19 12	88.10 36	94.80 23	73.76 34	97.11 15	87.51 40	95.82 21	94.90 15
Skip Steuart: Steuart Systems R&D Blog.
SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 68	93.57 8	94.06 11	77.24 60	93.10 1	95.72 8	82.99 1	97.44 7	89.07 22	96.63 4	94.88 16

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 54	82.45 3	96.87 20	83.77 75	96.48 8	94.88 16

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 25	93.63 22	74.77 128	92.29 7	95.97 2	74.28 30	97.24 13	88.58 30	96.91 1	94.87 18
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		77.30 247	76.49 244	79.74 273	90.08 112	52.02 391	87.86 169	63.10 434	74.88 124	80.16 155	92.79 93	38.29 398	92.35 219	68.74 232	92.50 80	94.86 19

ECVR-MVS		79.61 184	79.26 177	80.67 253	90.08 112	54.69 374	87.89 167	77.44 387	74.88 124	80.27 152	92.79 93	48.96 324	92.45 213	68.55 233	92.50 80	94.86 19

IU-MVS					95.30 2	71.25 61		92.95 56	66.81 289	92.39 6				88.94 25	96.63 4	94.85 21

test1111		79.43 191	79.18 180	80.15 265	89.99 117	53.31 387	87.33 183	77.05 391	75.04 118	80.23 154	92.77 95	48.97 323	92.33 221	68.87 230	92.40 82	94.81 22

SF-MVS		88.46 12	88.74 12	87.64 35	92.78 66	71.95 51	92.40 25	94.74 2	75.71 100	89.16 23	95.10 18	75.65 21	96.19 47	87.07 43	96.01 17	94.79 23

balanced_conf03		86.78 39	86.99 37	86.15 66	91.24 86	67.61 153	90.51 65	92.90 57	77.26 59	87.44 50	91.63 119	71.27 64	96.06 50	85.62 53	95.01 37	94.78 24

sasdasda		85.91 58	85.87 61	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 39	91.23 131	73.28 37	93.91 143	81.50 97	88.80 141	94.77 25

SPE-MVS-test		86.29 50	86.48 45	85.71 76	91.02 91	67.21 170	92.36 30	93.78 19	78.97 33	83.51 109	91.20 134	70.65 73	95.15 87	81.96 94	94.89 42	94.77 25

canonicalmvs		85.91 58	85.87 61	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 39	91.23 131	73.28 37	93.91 143	81.50 97	88.80 141	94.77 25

GDP-MVS		83.52 101	82.64 112	86.16 65	88.14 189	68.45 128	89.13 114	92.69 66	72.82 180	83.71 104	91.86 112	55.69 242	95.35 82	80.03 114	89.74 127	94.69 28

test_0728_THIRD									78.38 38	92.12 9	95.78 4	81.46 7	97.40 9	89.42 17	96.57 7	94.67 29

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 17	94.11 7	80.27 10	91.35 14	94.16 47	78.35 13	96.77 24	89.59 15	94.22 62	94.67 29
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		82.60 122	82.10 121	84.10 136	87.98 199	62.94 267	87.45 179	91.27 128	77.42 56	79.85 157	90.28 155	56.62 238	94.70 112	79.87 117	88.15 154	94.67 29

MGCFI-Net		85.06 79	85.51 68	83.70 161	89.42 135	63.01 262	89.43 97	92.62 74	76.43 84	87.53 47	91.34 129	72.82 45	93.42 169	81.28 100	88.74 144	94.66 32

alignmvs		85.48 67	85.32 73	85.96 73	89.51 130	69.47 98	89.74 86	92.47 77	76.17 93	87.73 46	91.46 126	70.32 75	93.78 149	81.51 96	88.95 138	94.63 33

MP-MVS-pluss		87.67 22	87.72 22	87.54 36	93.64 44	72.04 50	89.80 84	93.50 26	75.17 117	86.34 61	95.29 17	70.86 69	96.00 55	88.78 28	96.04 16	94.58 34
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
DeepPCF-MVS	80.84 1	88.10 13	88.56 14	86.73 55	92.24 73	69.03 106	89.57 93	93.39 31	77.53 53	89.79 20	94.12 49	78.98 12	96.58 35	85.66 51	95.72 24	94.58 34

VDD-MVS		83.01 116	82.36 117	84.96 100	91.02 91	66.40 180	88.91 121	88.11 231	77.57 49	84.39 89	93.29 78	52.19 276	93.91 143	77.05 145	88.70 145	94.57 36

NormalMVS		86.29 50	85.88 59	87.52 37	93.26 52	72.47 38	91.65 43	92.19 92	79.31 24	84.39 89	92.18 102	64.64 142	95.53 67	80.70 108	94.65 48	94.56 37

KinetiMVS		83.31 109	82.61 113	85.39 86	87.08 235	67.56 156	88.06 159	91.65 116	77.80 44	82.21 123	91.79 113	57.27 230	94.07 133	77.77 136	89.89 125	94.56 37

VDDNet		81.52 141	80.67 142	84.05 147	90.44 104	64.13 236	89.73 87	85.91 281	71.11 209	83.18 111	93.48 71	50.54 302	93.49 163	73.40 185	88.25 152	94.54 39

MVSMamba_PlusPlus		85.99 54	85.96 58	86.05 69	91.09 88	67.64 152	89.63 91	92.65 71	72.89 179	84.64 83	91.71 115	71.85 53	96.03 51	84.77 62	94.45 56	94.49 40

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 54	93.83 4	93.96 14	75.70 102	91.06 16	96.03 1	76.84 14	97.03 17	89.09 19	95.65 27	94.47 41
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 27	75.53 2		92.99 50					97.53 2	89.67 13	96.44 9	94.41 42

No_MVS				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 13	96.44 9	94.41 42

MCST-MVS		87.37 31	87.25 32	87.73 28	94.53 17	72.46 40	89.82 82	93.82 17	73.07 174	84.86 78	92.89 88	76.22 17	96.33 41	84.89 59	95.13 36	94.40 44

fmvsm_s_conf0.5_n_8		86.56 44	87.17 35	84.73 110	87.76 212	65.62 199	89.20 107	92.21 90	79.94 17	89.74 22	94.86 22	68.63 98	94.20 127	90.83 5	91.39 97	94.38 45

CANet		86.45 45	86.10 55	87.51 38	90.09 111	70.94 72	89.70 88	92.59 75	81.78 4	81.32 136	91.43 127	70.34 74	97.23 14	84.26 68	93.36 70	94.37 46

PHI-MVS		86.43 46	86.17 53	87.24 42	90.88 95	70.96 70	92.27 33	94.07 10	72.45 182	85.22 71	91.90 109	69.47 85	96.42 40	83.28 79	95.94 19	94.35 47

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 65	93.00 47	80.90 7	88.06 37	94.06 52	76.43 16	96.84 21	88.48 33	95.99 18	94.34 48

ZNCC-MVS		87.94 19	87.85 21	88.20 12	94.39 24	73.33 19	93.03 15	93.81 18	76.81 74	85.24 70	94.32 39	71.76 55	96.93 19	85.53 54	95.79 22	94.32 49

HPM-MVS		87.11 35	86.98 38	87.50 39	93.88 39	72.16 47	92.19 34	93.33 32	76.07 95	83.81 103	93.95 61	69.77 82	96.01 54	85.15 55	94.66 47	94.32 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CDPH-MVS		85.76 62	85.29 75	87.17 44	93.49 47	71.08 66	88.58 140	92.42 81	68.32 277	84.61 84	93.48 71	72.32 47	96.15 49	79.00 121	95.43 30	94.28 51

test_241102_TWO								94.06 11	77.24 60	92.78 4	95.72 8	81.26 8	97.44 7	89.07 22	96.58 6	94.26 52

test_0728_SECOND				87.71 32	95.34 1	71.43 60	93.49 10	94.23 3					97.49 4	89.08 20	96.41 12	94.21 53

fmvsm_l_conf0.5_n_3		86.02 52	86.32 47	85.14 92	87.20 231	68.54 126	89.57 93	90.44 152	75.31 111	87.49 48	94.39 37	72.86 43	92.72 201	89.04 24	90.56 111	94.16 54

DeepC-MVS_fast	79.65 3	86.91 38	86.62 44	87.76 27	93.52 46	72.37 43	91.26 54	93.04 42	76.62 82	84.22 93	93.36 77	71.44 61	96.76 25	80.82 105	95.33 33	94.16 54
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EPP-MVSNet		83.40 105	83.02 105	84.57 113	90.13 110	64.47 229	92.32 31	90.73 144	74.45 136	79.35 164	91.10 137	69.05 93	95.12 88	72.78 192	87.22 166	94.13 56

NCCC		88.06 15	88.01 19	88.24 11	94.41 22	73.62 11	91.22 57	92.83 61	81.50 5	85.79 65	93.47 73	73.02 42	97.00 18	84.90 57	94.94 40	94.10 57

ACMMP_NAP		88.05 17	88.08 18	87.94 19	93.70 41	73.05 22	90.86 60	93.59 24	76.27 92	88.14 35	95.09 19	71.06 67	96.67 29	87.67 38	96.37 14	94.09 58

XVS		87.18 34	86.91 41	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 106	94.17 46	67.45 111	96.60 33	83.06 80	94.50 53	94.07 59

X-MVStestdata		80.37 173	77.83 210	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 106	12.47 448	67.45 111	96.60 33	83.06 80	94.50 53	94.07 59

region2R		87.42 28	87.20 34	88.09 14	94.63 14	73.55 13	93.03 15	93.12 41	76.73 79	84.45 87	94.52 27	69.09 90	96.70 27	84.37 67	94.83 45	94.03 61

fmvsm_s_conf0.5_n_4		85.39 71	85.75 64	84.30 125	86.70 244	65.83 192	88.77 129	89.78 175	75.46 106	88.35 30	93.73 67	69.19 89	93.06 190	91.30 3	88.44 150	94.02 62

ACMMPR		87.44 26	87.23 33	88.08 15	94.64 13	73.59 12	93.04 13	93.20 35	76.78 76	84.66 82	94.52 27	68.81 96	96.65 30	84.53 65	94.90 41	94.00 63

fmvsm_s_conf0.1_n_2		83.80 92	83.79 93	83.83 157	85.62 268	64.94 218	87.03 191	86.62 270	74.32 138	87.97 41	94.33 38	60.67 201	92.60 204	89.72 12	87.79 157	93.96 64

test_fmvsmconf_n		85.92 57	86.04 57	85.57 82	85.03 287	69.51 96	89.62 92	90.58 147	73.42 165	87.75 44	94.02 54	72.85 44	93.24 174	90.37 7	90.75 108	93.96 64

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 46	94.10 9	75.90 98	92.29 7	95.66 10	81.67 6	97.38 11	87.44 42	96.34 15	93.95 66
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 74	85.34 71	85.13 95	86.12 257	69.93 88	88.65 137	90.78 143	69.97 237	88.27 32	93.98 59	71.39 62	91.54 252	88.49 32	90.45 113	93.91 67

test_prior				86.33 60	92.61 70	69.59 94		92.97 55					95.48 70			93.91 67

GST-MVS		87.42 28	87.26 31	87.89 24	94.12 36	72.97 24	92.39 27	93.43 29	76.89 72	84.68 79	93.99 58	70.67 72	96.82 22	84.18 72	95.01 37	93.90 69

test_fmvsmconf0.1_n		85.61 65	85.65 65	85.50 83	82.99 336	69.39 103	89.65 89	90.29 161	73.31 168	87.77 43	94.15 48	71.72 56	93.23 175	90.31 8	90.67 110	93.89 70

Anonymous202405211		78.25 220	77.01 230	81.99 219	91.03 90	60.67 296	84.77 258	83.90 308	70.65 222	80.00 156	91.20 134	41.08 383	91.43 259	65.21 261	85.26 195	93.85 71

LFMVS		81.82 132	81.23 133	83.57 166	91.89 78	63.43 254	89.84 81	81.85 341	77.04 69	83.21 110	93.10 81	52.26 275	93.43 168	71.98 198	89.95 123	93.85 71

fmvsm_s_conf0.5_n_2		84.04 88	84.11 89	83.81 159	86.17 255	65.00 216	86.96 194	87.28 254	74.35 137	88.25 33	94.23 44	61.82 177	92.60 204	89.85 10	88.09 155	93.84 73

Effi-MVS+		83.62 99	83.08 103	85.24 90	88.38 180	67.45 158	88.89 122	89.15 202	75.50 105	82.27 121	88.28 211	69.61 84	94.45 119	77.81 135	87.84 156	93.84 73

Anonymous20240529		80.19 177	78.89 185	84.10 136	90.60 100	64.75 223	88.95 120	90.90 139	65.97 306	80.59 148	91.17 136	49.97 308	93.73 155	69.16 227	82.70 241	93.81 75

MVS_Test		83.15 111	83.06 104	83.41 171	86.86 238	63.21 258	86.11 225	92.00 100	74.31 139	82.87 115	89.44 183	70.03 78	93.21 177	77.39 141	88.50 149	93.81 75

Elysia		81.53 139	80.16 154	85.62 79	85.51 271	68.25 134	88.84 126	92.19 92	71.31 203	80.50 149	89.83 165	46.89 335	94.82 104	76.85 147	89.57 129	93.80 77

StellarMVS		81.53 139	80.16 154	85.62 79	85.51 271	68.25 134	88.84 126	92.19 92	71.31 203	80.50 149	89.83 165	46.89 335	94.82 104	76.85 147	89.57 129	93.80 77

test_fmvsmconf0.01_n		84.73 83	84.52 85	85.34 87	80.25 377	69.03 106	89.47 95	89.65 181	73.24 172	86.98 56	94.27 41	66.62 118	93.23 175	90.26 9	89.95 123	93.78 79

GeoE		81.71 134	81.01 138	83.80 160	89.51 130	64.45 230	88.97 119	88.73 223	71.27 206	78.63 176	89.76 168	66.32 124	93.20 180	69.89 219	86.02 187	93.74 80

diffmvs		82.10 125	81.88 127	82.76 206	83.00 334	63.78 244	83.68 285	89.76 177	72.94 177	82.02 126	89.85 164	65.96 131	90.79 277	82.38 92	87.30 165	93.71 81
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 14	88.59 13	86.58 58	93.26 52	69.77 92	93.70 6	94.16 5	77.13 65	89.76 21	95.52 14	72.26 48	96.27 44	86.87 44	94.65 48	93.70 82

HFP-MVS		87.58 23	87.47 28	87.94 19	94.58 16	73.54 15	93.04 13	93.24 34	76.78 76	84.91 75	94.44 34	70.78 70	96.61 32	84.53 65	94.89 42	93.66 83

VNet		82.21 124	82.41 115	81.62 225	90.82 96	60.93 291	84.47 267	89.78 175	76.36 90	84.07 97	91.88 110	64.71 141	90.26 284	70.68 210	88.89 139	93.66 83

PGM-MVS		86.68 42	86.27 49	87.90 22	94.22 33	73.38 18	90.22 76	93.04 42	75.53 104	83.86 101	94.42 35	67.87 108	96.64 31	82.70 90	94.57 52	93.66 83

DELS-MVS		85.41 70	85.30 74	85.77 75	88.49 174	67.93 144	85.52 245	93.44 28	78.70 34	83.63 108	89.03 190	74.57 24	95.71 62	80.26 113	94.04 63	93.66 83
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 15	88.50 15	86.71 56	92.60 71	72.71 29	91.81 42	93.19 36	77.87 42	90.32 18	94.00 56	74.83 23	93.78 149	87.63 39	94.27 61	93.65 87
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 37	86.88 42	87.69 33	91.16 87	72.32 45	90.31 74	93.94 15	77.12 66	82.82 117	94.23 44	72.13 51	97.09 16	84.83 60	95.37 31	93.65 87
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 96	84.54 83	80.99 245	90.06 116	65.83 192	84.21 276	88.74 222	71.60 198	85.01 72	92.44 98	74.51 26	83.50 371	82.15 93	92.15 83	93.64 89

EIA-MVS		83.31 109	82.80 110	84.82 106	89.59 126	65.59 200	88.21 153	92.68 67	74.66 131	78.96 168	86.42 269	69.06 92	95.26 83	75.54 164	90.09 119	93.62 90

MP-MVS		87.71 20	87.64 23	87.93 21	94.36 26	73.88 6	92.71 23	92.65 71	77.57 49	83.84 102	94.40 36	72.24 49	96.28 43	85.65 52	95.30 35	93.62 90
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		85.35 73	84.95 79	86.57 59	93.69 42	70.58 80	92.15 36	91.62 118	73.89 151	82.67 120	94.09 50	62.60 163	95.54 66	80.93 103	92.93 73	93.57 92

fmvsm_s_conf0.1_n		83.56 100	83.38 99	84.10 136	84.86 289	67.28 165	89.40 101	83.01 325	70.67 218	87.08 54	93.96 60	68.38 101	91.45 258	88.56 31	84.50 203	93.56 93

CSCG		86.41 48	86.19 52	87.07 46	92.91 63	72.48 37	90.81 61	93.56 25	73.95 148	83.16 112	91.07 139	75.94 18	95.19 85	79.94 116	94.38 58	93.55 94

test12				86.80 54	92.63 69	70.70 77		91.79 112		82.71 119		71.67 58	96.16 48		94.50 53	93.54 95

APD-MVS_3200maxsize		85.97 56	85.88 59	86.22 63	92.69 68	69.53 95	91.93 38	92.99 50	73.54 161	85.94 62	94.51 30	65.80 132	95.61 63	83.04 82	92.51 79	93.53 96

mvs_anonymous		79.42 192	79.11 181	80.34 260	84.45 300	57.97 326	82.59 306	87.62 247	67.40 287	76.17 238	88.56 204	68.47 100	89.59 297	70.65 211	86.05 186	93.47 97

fmvsm_s_conf0.5_n		83.80 92	83.71 94	84.07 142	86.69 245	67.31 164	89.46 96	83.07 324	71.09 210	86.96 57	93.70 68	69.02 95	91.47 257	88.79 27	84.62 202	93.44 98

fmvsm_s_conf0.5_n_5		85.22 75	85.55 67	84.25 132	86.26 251	67.40 161	89.18 108	89.31 193	72.50 181	88.31 31	93.86 63	69.66 83	91.96 232	89.81 11	91.05 102	93.38 99

mPP-MVS		86.67 43	86.32 47	87.72 30	94.41 22	73.55 13	92.74 21	92.22 89	76.87 73	82.81 118	94.25 43	66.44 122	96.24 45	82.88 85	94.28 60	93.38 99

EPNet		83.72 95	82.92 108	86.14 68	84.22 303	69.48 97	91.05 59	85.27 288	81.30 6	76.83 217	91.65 117	66.09 127	95.56 64	76.00 158	93.85 64	93.38 99
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Vis-MVSNet		83.46 103	82.80 110	85.43 85	90.25 108	68.74 117	90.30 75	90.13 166	76.33 91	80.87 144	92.89 88	61.00 196	94.20 127	72.45 197	90.97 104	93.35 102
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DVP-MVS		89.60 3	90.35 3	87.33 41	95.27 5	71.25 61	93.49 10	92.73 65	77.33 57	92.12 9	95.78 4	80.98 9	97.40 9	89.08 20	96.41 12	93.33 103
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		79.10 201	78.24 199	81.70 224	86.85 239	60.24 303	87.28 185	88.79 217	74.25 142	76.84 216	90.53 153	49.48 314	91.56 250	67.98 237	82.15 245	93.29 104

EI-MVSNet-Vis-set		84.19 86	83.81 92	85.31 88	88.18 186	67.85 146	87.66 172	89.73 179	80.05 15	82.95 113	89.59 175	70.74 71	94.82 104	80.66 110	84.72 200	93.28 105

MTAPA		87.23 33	87.00 36	87.90 22	94.18 35	74.25 5	86.58 210	92.02 98	79.45 22	85.88 63	94.80 23	68.07 104	96.21 46	86.69 46	95.34 32	93.23 106

CP-MVS		87.11 35	86.92 40	87.68 34	94.20 34	73.86 7	93.98 3	92.82 64	76.62 82	83.68 105	94.46 31	67.93 106	95.95 58	84.20 71	94.39 57	93.23 106

ACMMP		85.89 60	85.39 70	87.38 40	93.59 45	72.63 33	92.74 21	93.18 40	76.78 76	80.73 147	93.82 65	64.33 144	96.29 42	82.67 91	90.69 109	93.23 106
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 72	84.81 80	87.07 46	91.47 83	72.47 38	91.65 43	88.06 235	79.31 24	84.39 89	92.18 102	64.64 142	95.53 67	80.70 108	90.91 106	93.21 109

fmvsm_s_conf0.1_n_a		83.32 108	82.99 106	84.28 127	83.79 313	68.07 140	89.34 104	82.85 330	69.80 241	87.36 52	94.06 52	68.34 102	91.56 250	87.95 36	83.46 229	93.21 109

fmvsm_s_conf0.5_n_6		85.55 66	86.20 50	83.60 163	87.32 228	65.13 211	88.86 123	91.63 117	75.41 107	88.23 34	93.45 74	68.56 99	92.47 212	89.52 16	92.78 75	93.20 111

PAPM_NR		83.02 115	82.41 115	84.82 106	92.47 72	66.37 181	87.93 165	91.80 111	73.82 152	77.32 205	90.66 149	67.90 107	94.90 100	70.37 213	89.48 132	93.19 112

reproduce_model		87.28 32	87.39 30	86.95 50	93.10 58	71.24 65	91.60 45	93.19 36	74.69 129	88.80 27	95.61 11	70.29 76	96.44 39	86.20 50	93.08 71	93.16 113

OMC-MVS		82.69 118	81.97 126	84.85 105	88.75 166	67.42 159	87.98 161	90.87 141	74.92 123	79.72 159	91.65 117	62.19 173	93.96 135	75.26 168	86.42 179	93.16 113

fmvsm_s_conf0.5_n_a		83.63 98	83.41 98	84.28 127	86.14 256	68.12 138	89.43 97	82.87 329	70.27 230	87.27 53	93.80 66	69.09 90	91.58 247	88.21 35	83.65 223	93.14 115

PAPR		81.66 137	80.89 140	83.99 152	90.27 107	64.00 237	86.76 205	91.77 114	68.84 268	77.13 215	89.50 176	67.63 109	94.88 102	67.55 241	88.52 148	93.09 116

UA-Net		85.08 78	84.96 78	85.45 84	92.07 75	68.07 140	89.78 85	90.86 142	82.48 2	84.60 85	93.20 80	69.35 86	95.22 84	71.39 203	90.88 107	93.07 117

reproduce-ours		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 120	88.96 24	95.54 12	71.20 65	96.54 36	86.28 48	93.49 67	93.06 118

our_new_method		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 120	88.96 24	95.54 12	71.20 65	96.54 36	86.28 48	93.49 67	93.06 118

HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 28	92.85 60	80.26 11	87.78 42	94.27 41	75.89 19	96.81 23	87.45 41	96.44 9	93.05 120

thisisatest0530		79.40 193	77.76 215	84.31 124	87.69 215	65.10 214	87.36 181	84.26 304	70.04 233	77.42 202	88.26 213	49.94 309	94.79 108	70.20 214	84.70 201	93.03 121

train_agg		86.43 46	86.20 50	87.13 45	93.26 52	72.96 25	88.75 131	91.89 106	68.69 270	85.00 73	93.10 81	74.43 27	95.41 76	84.97 56	95.71 25	93.02 122

EC-MVSNet		86.01 53	86.38 46	84.91 104	89.31 143	66.27 183	92.32 31	93.63 22	79.37 23	84.17 95	91.88 110	69.04 94	95.43 73	83.93 74	93.77 65	93.01 123

mvsmamba		80.60 165	79.38 172	84.27 129	89.74 124	67.24 168	87.47 177	86.95 262	70.02 234	75.38 254	88.93 191	51.24 293	92.56 207	75.47 166	89.22 135	93.00 124

EI-MVSNet-UG-set		83.81 91	83.38 99	85.09 96	87.87 203	67.53 157	87.44 180	89.66 180	79.74 18	82.23 122	89.41 184	70.24 77	94.74 109	79.95 115	83.92 215	92.99 125

tttt0517		79.40 193	77.91 206	83.90 156	88.10 192	63.84 242	88.37 148	84.05 306	71.45 201	76.78 219	89.12 187	49.93 311	94.89 101	70.18 215	83.18 234	92.96 126

test9_res														84.90 57	95.70 26	92.87 127

AstraMVS		80.81 155	80.14 156	82.80 200	86.05 260	63.96 238	86.46 214	85.90 282	73.71 155	80.85 145	90.56 151	54.06 259	91.57 249	79.72 118	83.97 214	92.86 128

SR-MVS		86.73 40	86.67 43	86.91 51	94.11 37	72.11 49	92.37 29	92.56 76	74.50 133	86.84 58	94.65 26	67.31 113	95.77 60	84.80 61	92.85 74	92.84 129

ETV-MVS		84.90 82	84.67 82	85.59 81	89.39 138	68.66 123	88.74 133	92.64 73	79.97 16	84.10 96	85.71 282	69.32 87	95.38 78	80.82 105	91.37 98	92.72 130

agg_prior2														82.91 84	95.45 29	92.70 131

APD-MVS		87.44 26	87.52 27	87.19 43	94.24 32	72.39 41	91.86 41	92.83 61	73.01 176	88.58 28	94.52 27	73.36 35	96.49 38	84.26 68	95.01 37	92.70 131
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ET-MVSNet_ETH3D		78.63 212	76.63 243	84.64 112	86.73 243	69.47 98	85.01 253	84.61 297	69.54 247	66.51 377	86.59 262	50.16 305	91.75 241	76.26 154	84.24 211	92.69 133

Vis-MVSNet (Re-imp)		78.36 219	78.45 192	78.07 306	88.64 170	51.78 397	86.70 206	79.63 369	74.14 145	75.11 267	90.83 147	61.29 190	89.75 294	58.10 328	91.60 92	92.69 133

TSAR-MVS + GP.		85.71 63	85.33 72	86.84 52	91.34 84	72.50 36	89.07 117	87.28 254	76.41 85	85.80 64	90.22 159	74.15 32	95.37 81	81.82 95	91.88 87	92.65 135

test_fmvsmvis_n_1920		84.02 89	83.87 91	84.49 117	84.12 305	69.37 104	88.15 157	87.96 237	70.01 235	83.95 100	93.23 79	68.80 97	91.51 255	88.61 29	89.96 122	92.57 136

FA-MVS(test-final)		80.96 151	79.91 160	84.10 136	88.30 183	65.01 215	84.55 266	90.01 169	73.25 171	79.61 160	87.57 231	58.35 219	94.72 110	71.29 204	86.25 182	92.56 137

guyue		81.13 148	80.64 143	82.60 209	86.52 248	63.92 241	86.69 207	87.73 245	73.97 147	80.83 146	89.69 169	56.70 236	91.33 263	78.26 134	85.40 194	92.54 138

test_yl		81.17 146	80.47 147	83.24 177	89.13 151	63.62 245	86.21 222	89.95 171	72.43 185	81.78 131	89.61 173	57.50 227	93.58 157	70.75 208	86.90 170	92.52 139

DCV-MVSNet		81.17 146	80.47 147	83.24 177	89.13 151	63.62 245	86.21 222	89.95 171	72.43 185	81.78 131	89.61 173	57.50 227	93.58 157	70.75 208	86.90 170	92.52 139

SR-MVS-dyc-post		85.77 61	85.61 66	86.23 62	93.06 60	70.63 78	91.88 39	92.27 85	73.53 162	85.69 66	94.45 32	65.00 140	95.56 64	82.75 86	91.87 88	92.50 141

RE-MVS-def			85.48 69		93.06 60	70.63 78	91.88 39	92.27 85	73.53 162	85.69 66	94.45 32	63.87 148		82.75 86	91.87 88	92.50 141

nrg030		83.88 90	83.53 96	84.96 100	86.77 242	69.28 105	90.46 70	92.67 68	74.79 127	82.95 113	91.33 130	72.70 46	93.09 188	80.79 107	79.28 282	92.50 141

MG-MVS		83.41 104	83.45 97	83.28 174	92.74 67	62.28 275	88.17 155	89.50 187	75.22 112	81.49 134	92.74 96	66.75 116	95.11 90	72.85 191	91.58 94	92.45 144

FIs		82.07 127	82.42 114	81.04 244	88.80 163	58.34 320	88.26 152	93.49 27	76.93 71	78.47 181	91.04 140	69.92 80	92.34 220	69.87 220	84.97 197	92.44 145

testing3-2		75.12 284	75.19 266	74.91 345	90.40 105	45.09 427	80.29 339	78.42 379	78.37 40	76.54 227	87.75 225	44.36 361	87.28 335	57.04 338	83.49 227	92.37 146

fmvsm_s_conf0.5_n_3		86.36 49	87.46 29	83.09 184	87.08 235	65.21 208	89.09 116	90.21 163	79.67 19	89.98 19	95.02 20	73.17 39	91.71 244	91.30 3	91.60 92	92.34 147

FC-MVSNet-test		81.52 141	82.02 124	80.03 267	88.42 179	55.97 359	87.95 163	93.42 30	77.10 67	77.38 203	90.98 146	69.96 79	91.79 239	68.46 235	84.50 203	92.33 148

Fast-Effi-MVS+		80.81 155	79.92 159	83.47 167	88.85 158	64.51 226	85.53 243	89.39 190	70.79 215	78.49 180	85.06 302	67.54 110	93.58 157	67.03 249	86.58 176	92.32 149

TranMVSNet+NR-MVSNet		80.84 153	80.31 150	82.42 212	87.85 204	62.33 273	87.74 171	91.33 127	80.55 9	77.99 193	89.86 163	65.23 136	92.62 202	67.05 248	75.24 342	92.30 150

ab-mvs		79.51 187	78.97 184	81.14 241	88.46 176	60.91 292	83.84 281	89.24 198	70.36 225	79.03 167	88.87 194	63.23 155	90.21 286	65.12 262	82.57 242	92.28 151

CANet_DTU		80.61 164	79.87 161	82.83 197	85.60 269	63.17 261	87.36 181	88.65 224	76.37 89	75.88 241	88.44 207	53.51 264	93.07 189	73.30 186	89.74 127	92.25 152

UniMVSNet_NR-MVSNet		81.88 130	81.54 130	82.92 194	88.46 176	63.46 252	87.13 187	92.37 82	80.19 12	78.38 182	89.14 186	71.66 59	93.05 191	70.05 216	76.46 315	92.25 152

fmvsm_l_conf0.5_n		84.47 84	84.54 83	84.27 129	85.42 274	68.81 112	88.49 142	87.26 256	68.08 279	88.03 38	93.49 70	72.04 52	91.77 240	88.90 26	89.14 137	92.24 154

DU-MVS		81.12 149	80.52 146	82.90 195	87.80 207	63.46 252	87.02 192	91.87 108	79.01 31	78.38 182	89.07 188	65.02 138	93.05 191	70.05 216	76.46 315	92.20 155

NR-MVSNet		80.23 175	79.38 172	82.78 204	87.80 207	63.34 255	86.31 219	91.09 136	79.01 31	72.17 311	89.07 188	67.20 114	92.81 200	66.08 255	75.65 328	92.20 155

TAPA-MVS	73.13 9	79.15 199	77.94 205	82.79 203	89.59 126	62.99 266	88.16 156	91.51 122	65.77 307	77.14 214	91.09 138	60.91 197	93.21 177	50.26 380	87.05 168	92.17 157
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
fmvsm_l_conf0.5_n_a		84.13 87	84.16 88	84.06 144	85.38 275	68.40 129	88.34 149	86.85 266	67.48 286	87.48 49	93.40 75	70.89 68	91.61 245	88.38 34	89.22 135	92.16 158

3Dnovator	76.31 5	83.38 106	82.31 118	86.59 57	87.94 200	72.94 28	90.64 63	92.14 97	77.21 62	75.47 248	92.83 90	58.56 217	94.72 110	73.24 188	92.71 77	92.13 159

MVS_111021_HR		85.14 76	84.75 81	86.32 61	91.65 81	72.70 30	85.98 227	90.33 158	76.11 94	82.08 125	91.61 121	71.36 63	94.17 130	81.02 102	92.58 78	92.08 160

MVSFormer		82.85 117	82.05 123	85.24 90	87.35 222	70.21 82	90.50 67	90.38 154	68.55 272	81.32 136	89.47 178	61.68 179	93.46 166	78.98 122	90.26 116	92.05 161

jason		81.39 144	80.29 151	84.70 111	86.63 247	69.90 90	85.95 228	86.77 267	63.24 337	81.07 142	89.47 178	61.08 195	92.15 226	78.33 130	90.07 121	92.05 161
jason: jason.
HyFIR lowres test		77.53 242	75.40 261	83.94 155	89.59 126	66.62 177	80.36 337	88.64 225	56.29 401	76.45 228	85.17 299	57.64 225	93.28 172	61.34 298	83.10 235	91.91 163

XVG-OURS-SEG-HR		80.81 155	79.76 163	83.96 154	85.60 269	68.78 114	83.54 292	90.50 150	70.66 221	76.71 221	91.66 116	60.69 200	91.26 264	76.94 146	81.58 252	91.83 164

lupinMVS		81.39 144	80.27 152	84.76 109	87.35 222	70.21 82	85.55 241	86.41 272	62.85 344	81.32 136	88.61 201	61.68 179	92.24 224	78.41 129	90.26 116	91.83 164

WR-MVS		79.49 188	79.22 179	80.27 262	88.79 164	58.35 319	85.06 252	88.61 226	78.56 35	77.65 198	88.34 209	63.81 150	90.66 281	64.98 264	77.22 303	91.80 166

h-mvs33		83.15 111	82.19 119	86.02 72	90.56 101	70.85 75	88.15 157	89.16 201	76.02 96	84.67 80	91.39 128	61.54 182	95.50 69	82.71 88	75.48 332	91.72 167

UniMVSNet (Re)		81.60 138	81.11 135	83.09 184	88.38 180	64.41 231	87.60 173	93.02 46	78.42 37	78.56 178	88.16 215	69.78 81	93.26 173	69.58 223	76.49 314	91.60 168

UGNet		80.83 154	79.59 168	84.54 114	88.04 195	68.09 139	89.42 99	88.16 230	76.95 70	76.22 234	89.46 180	49.30 318	93.94 138	68.48 234	90.31 114	91.60 168
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		76.54 257	75.66 256	79.18 285	88.43 178	55.89 360	81.08 323	83.00 326	73.76 154	75.34 256	84.29 317	46.20 345	90.07 288	64.33 268	84.50 203	91.58 170

XVG-OURS		80.41 170	79.23 178	83.97 153	85.64 267	69.02 108	83.03 304	90.39 153	71.09 210	77.63 199	91.49 125	54.62 254	91.35 261	75.71 160	83.47 228	91.54 171

LCM-MVSNet-Re		77.05 249	76.94 233	77.36 319	87.20 231	51.60 398	80.06 341	80.46 357	75.20 114	67.69 357	86.72 254	62.48 166	88.98 310	63.44 274	89.25 134	91.51 172

DP-MVS Recon		83.11 114	82.09 122	86.15 66	94.44 19	70.92 73	88.79 128	92.20 91	70.53 223	79.17 166	91.03 142	64.12 146	96.03 51	68.39 236	90.14 118	91.50 173

PS-MVSNAJss		82.07 127	81.31 131	84.34 123	86.51 249	67.27 166	89.27 105	91.51 122	71.75 193	79.37 163	90.22 159	63.15 157	94.27 123	77.69 137	82.36 244	91.49 174

testing99		76.09 269	75.12 268	79.00 286	88.16 187	55.50 366	80.79 327	81.40 346	73.30 169	75.17 264	84.27 320	44.48 360	90.02 289	64.28 269	84.22 212	91.48 175

thisisatest0515		77.33 246	75.38 262	83.18 180	85.27 279	63.80 243	82.11 311	83.27 318	65.06 316	75.91 240	83.84 327	49.54 313	94.27 123	67.24 245	86.19 183	91.48 175

DPM-MVS		84.93 80	84.29 87	86.84 52	90.20 109	73.04 23	87.12 188	93.04 42	69.80 241	82.85 116	91.22 133	73.06 41	96.02 53	76.72 152	94.63 50	91.46 177

HQP_MVS		83.64 97	83.14 102	85.14 92	90.08 112	68.71 119	91.25 55	92.44 78	79.12 28	78.92 170	91.00 144	60.42 207	95.38 78	78.71 125	86.32 180	91.33 178

plane_prior5								92.44 78					95.38 78	78.71 125	86.32 180	91.33 178

GA-MVS		76.87 253	75.17 267	81.97 220	82.75 340	62.58 270	81.44 320	86.35 275	72.16 189	74.74 275	82.89 349	46.20 345	92.02 230	68.85 231	81.09 257	91.30 180

VPA-MVSNet		80.60 165	80.55 145	80.76 251	88.07 194	60.80 294	86.86 199	91.58 120	75.67 103	80.24 153	89.45 182	63.34 151	90.25 285	70.51 212	79.22 283	91.23 181

Effi-MVS+-dtu		80.03 179	78.57 190	84.42 119	85.13 284	68.74 117	88.77 129	88.10 232	74.99 119	74.97 272	83.49 338	57.27 230	93.36 170	73.53 182	80.88 260	91.18 182

v2v482		80.23 175	79.29 176	83.05 188	83.62 317	64.14 235	87.04 190	89.97 170	73.61 158	78.18 188	87.22 242	61.10 194	93.82 147	76.11 155	76.78 311	91.18 182

FE-MVS		77.78 235	75.68 254	84.08 141	88.09 193	66.00 187	83.13 299	87.79 243	68.42 276	78.01 192	85.23 297	45.50 354	95.12 88	59.11 316	85.83 191	91.11 184

Anonymous20231211		78.97 205	77.69 218	82.81 199	90.54 102	64.29 233	90.11 78	91.51 122	65.01 318	76.16 239	88.13 220	50.56 301	93.03 194	69.68 222	77.56 301	91.11 184

hse-mvs2		81.72 133	80.94 139	84.07 142	88.72 167	67.68 151	85.87 231	87.26 256	76.02 96	84.67 80	88.22 214	61.54 182	93.48 164	82.71 88	73.44 360	91.06 186

AUN-MVS		79.21 198	77.60 220	84.05 147	88.71 168	67.61 153	85.84 233	87.26 256	69.08 261	77.23 208	88.14 219	53.20 268	93.47 165	75.50 165	73.45 359	91.06 186

HQP4-MVS										77.24 207			95.11 90			91.03 188

HQP-MVS		82.61 120	82.02 124	84.37 120	89.33 140	66.98 173	89.17 109	92.19 92	76.41 85	77.23 208	90.23 158	60.17 210	95.11 90	77.47 139	85.99 188	91.03 188

RPSCF		73.23 308	71.46 312	78.54 296	82.50 346	59.85 306	82.18 310	82.84 331	58.96 380	71.15 323	89.41 184	45.48 355	84.77 362	58.82 320	71.83 372	91.02 190

LuminaMVS		80.68 162	79.62 167	83.83 157	85.07 286	68.01 143	86.99 193	88.83 215	70.36 225	81.38 135	87.99 222	50.11 306	92.51 211	79.02 120	86.89 172	90.97 191

test_djsdf		80.30 174	79.32 175	83.27 175	83.98 309	65.37 206	90.50 67	90.38 154	68.55 272	76.19 235	88.70 197	56.44 239	93.46 166	78.98 122	80.14 272	90.97 191

PCF-MVS	73.52 7	80.38 171	78.84 186	85.01 98	87.71 213	68.99 109	83.65 286	91.46 126	63.00 341	77.77 197	90.28 155	66.10 126	95.09 94	61.40 296	88.22 153	90.94 193
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VPNet		78.69 211	78.66 188	78.76 290	88.31 182	55.72 363	84.45 270	86.63 269	76.79 75	78.26 185	90.55 152	59.30 213	89.70 296	66.63 250	77.05 305	90.88 194

CPTT-MVS		83.73 94	83.33 101	84.92 103	93.28 49	70.86 74	92.09 37	90.38 154	68.75 269	79.57 161	92.83 90	60.60 205	93.04 193	80.92 104	91.56 95	90.86 195

fmvsm_s_conf0.5_n_7		83.34 107	84.03 90	81.28 236	85.73 265	65.13 211	85.40 246	89.90 173	74.96 122	82.13 124	93.89 62	66.65 117	87.92 326	86.56 47	91.05 102	90.80 196

tt0805		78.73 209	77.83 210	81.43 230	85.17 280	60.30 302	89.41 100	90.90 139	71.21 207	77.17 213	88.73 196	46.38 340	93.21 177	72.57 195	78.96 284	90.79 197

CLD-MVS		82.31 123	81.65 129	84.29 126	88.47 175	67.73 150	85.81 235	92.35 83	75.78 99	78.33 184	86.58 264	64.01 147	94.35 120	76.05 157	87.48 162	90.79 197
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
v1192		79.59 186	78.43 194	83.07 187	83.55 319	64.52 225	86.93 197	90.58 147	70.83 214	77.78 196	85.90 278	59.15 214	93.94 138	73.96 179	77.19 304	90.76 199

IterMVS-LS		80.06 178	79.38 172	82.11 216	85.89 261	63.20 259	86.79 202	89.34 191	74.19 143	75.45 251	86.72 254	66.62 118	92.39 216	72.58 194	76.86 308	90.75 200
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
myMVS_eth3d28		73.62 299	73.53 289	73.90 358	88.20 185	47.41 417	78.06 371	79.37 371	74.29 141	73.98 286	84.29 317	44.67 357	83.54 370	51.47 370	87.39 163	90.74 201

EI-MVSNet		80.52 169	79.98 158	82.12 215	84.28 301	63.19 260	86.41 215	88.95 213	74.18 144	78.69 173	87.54 234	66.62 118	92.43 214	72.57 195	80.57 266	90.74 201

v1921920		79.22 197	78.03 203	82.80 200	83.30 324	63.94 240	86.80 201	90.33 158	69.91 239	77.48 201	85.53 289	58.44 218	93.75 153	73.60 181	76.85 309	90.71 203

QAPM		80.88 152	79.50 170	85.03 97	88.01 198	68.97 110	91.59 46	92.00 100	66.63 298	75.15 266	92.16 104	57.70 224	95.45 71	63.52 272	88.76 143	90.66 204

v144192		79.47 189	78.37 195	82.78 204	83.35 322	63.96 238	86.96 194	90.36 157	69.99 236	77.50 200	85.67 285	60.66 202	93.77 151	74.27 176	76.58 312	90.62 205

v1240		78.99 204	77.78 213	82.64 207	83.21 326	63.54 249	86.62 209	90.30 160	69.74 246	77.33 204	85.68 284	57.04 233	93.76 152	73.13 189	76.92 306	90.62 205

v1144		80.03 179	79.03 182	83.01 190	83.78 314	64.51 226	87.11 189	90.57 149	71.96 192	78.08 191	86.20 274	61.41 186	93.94 138	74.93 170	77.23 302	90.60 207

1112_ss		77.40 245	76.43 246	80.32 261	89.11 155	60.41 301	83.65 286	87.72 246	62.13 354	73.05 298	86.72 254	62.58 165	89.97 290	62.11 290	80.80 262	90.59 208

CP-MVSNet		78.22 221	78.34 196	77.84 310	87.83 206	54.54 376	87.94 164	91.17 132	77.65 46	73.48 293	88.49 205	62.24 172	88.43 320	62.19 287	74.07 351	90.55 209

testing222		74.04 294	72.66 300	78.19 303	87.89 202	55.36 367	81.06 324	79.20 374	71.30 205	74.65 278	83.57 337	39.11 393	88.67 317	51.43 372	85.75 192	90.53 210

PS-CasMVS		78.01 230	78.09 202	77.77 312	87.71 213	54.39 378	88.02 160	91.22 129	77.50 54	73.26 295	88.64 200	60.73 198	88.41 321	61.88 291	73.88 355	90.53 210

CDS-MVSNet		79.07 202	77.70 217	83.17 181	87.60 217	68.23 136	84.40 273	86.20 277	67.49 285	76.36 231	86.54 266	61.54 182	90.79 277	61.86 292	87.33 164	90.49 212
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		78.89 207	77.51 222	83.03 189	87.80 207	67.79 149	84.72 259	85.05 293	67.63 282	76.75 220	87.70 227	62.25 171	90.82 276	58.53 323	87.13 167	90.49 212

PEN-MVS		77.73 236	77.69 218	77.84 310	87.07 237	53.91 381	87.91 166	91.18 131	77.56 51	73.14 297	88.82 195	61.23 191	89.17 306	59.95 307	72.37 366	90.43 214

Test_1112_low_res		76.40 264	75.44 259	79.27 282	89.28 145	58.09 322	81.69 315	87.07 260	59.53 375	72.48 306	86.67 259	61.30 189	89.33 301	60.81 302	80.15 271	90.41 215

HY-MVS	69.67 12	77.95 231	77.15 228	80.36 259	87.57 221	60.21 304	83.37 294	87.78 244	66.11 302	75.37 255	87.06 249	63.27 153	90.48 283	61.38 297	82.43 243	90.40 216

sc_t1		72.19 320	69.51 331	80.23 263	84.81 290	61.09 289	84.68 260	80.22 363	60.70 364	71.27 320	83.58 336	36.59 404	89.24 304	60.41 303	63.31 404	90.37 217

CHOSEN 1792x2688		77.63 241	75.69 253	83.44 168	89.98 118	68.58 125	78.70 361	87.50 250	56.38 400	75.80 243	86.84 250	58.67 216	91.40 260	61.58 295	85.75 192	90.34 218

SDMVSNet		80.38 171	80.18 153	80.99 245	89.03 156	64.94 218	80.45 336	89.40 189	75.19 115	76.61 225	89.98 161	60.61 204	87.69 330	76.83 150	83.55 225	90.33 219

sd_testset		77.70 239	77.40 223	78.60 293	89.03 156	60.02 305	79.00 356	85.83 283	75.19 115	76.61 225	89.98 161	54.81 247	85.46 355	62.63 283	83.55 225	90.33 219

114514_t		80.68 162	79.51 169	84.20 133	94.09 38	67.27 166	89.64 90	91.11 135	58.75 384	74.08 285	90.72 148	58.10 220	95.04 95	69.70 221	89.42 133	90.30 221

eth_miper_zixun_eth		77.92 232	76.69 241	81.61 227	83.00 334	61.98 278	83.15 298	89.20 200	69.52 248	74.86 274	84.35 316	61.76 178	92.56 207	71.50 202	72.89 364	90.28 222

PVSNet_Blended_VisFu		82.62 119	81.83 128	84.96 100	90.80 97	69.76 93	88.74 133	91.70 115	69.39 249	78.96 168	88.46 206	65.47 134	94.87 103	74.42 174	88.57 146	90.24 223

MVS_111021_LR		82.61 120	82.11 120	84.11 135	88.82 161	71.58 57	85.15 249	86.16 278	74.69 129	80.47 151	91.04 140	62.29 170	90.55 282	80.33 112	90.08 120	90.20 224

MSLP-MVS++		85.43 69	85.76 63	84.45 118	91.93 77	70.24 81	90.71 62	92.86 59	77.46 55	84.22 93	92.81 92	67.16 115	92.94 195	80.36 111	94.35 59	90.16 225

mvs_tets		79.13 200	77.77 214	83.22 179	84.70 293	66.37 181	89.17 109	90.19 164	69.38 250	75.40 253	89.46 180	44.17 363	93.15 184	76.78 151	80.70 264	90.14 226

BH-RMVSNet		79.61 184	78.44 193	83.14 182	89.38 139	65.93 189	84.95 255	87.15 259	73.56 160	78.19 187	89.79 167	56.67 237	93.36 170	59.53 312	86.74 174	90.13 227

c3_l		78.75 208	77.91 206	81.26 237	82.89 338	61.56 284	84.09 279	89.13 204	69.97 237	75.56 246	84.29 317	66.36 123	92.09 228	73.47 184	75.48 332	90.12 228

v7n		78.97 205	77.58 221	83.14 182	83.45 321	65.51 201	88.32 150	91.21 130	73.69 156	72.41 307	86.32 272	57.93 221	93.81 148	69.18 226	75.65 328	90.11 229

jajsoiax		79.29 196	77.96 204	83.27 175	84.68 294	66.57 179	89.25 106	90.16 165	69.20 258	75.46 250	89.49 177	45.75 351	93.13 186	76.84 149	80.80 262	90.11 229

v148		78.72 210	77.80 212	81.47 229	82.73 341	61.96 279	86.30 220	88.08 233	73.26 170	76.18 236	85.47 291	62.46 167	92.36 218	71.92 199	73.82 356	90.09 231

GBi-Net		78.40 217	77.40 223	81.40 232	87.60 217	63.01 262	88.39 145	89.28 194	71.63 195	75.34 256	87.28 238	54.80 248	91.11 267	62.72 279	79.57 276	90.09 231

test1		78.40 217	77.40 223	81.40 232	87.60 217	63.01 262	88.39 145	89.28 194	71.63 195	75.34 256	87.28 238	54.80 248	91.11 267	62.72 279	79.57 276	90.09 231

FMVSNet1		77.44 243	76.12 250	81.40 232	86.81 241	63.01 262	88.39 145	89.28 194	70.49 224	74.39 282	87.28 238	49.06 322	91.11 267	60.91 300	78.52 287	90.09 231

WR-MVS_H		78.51 216	78.49 191	78.56 295	88.02 196	56.38 353	88.43 143	92.67 68	77.14 64	73.89 287	87.55 233	66.25 125	89.24 304	58.92 318	73.55 358	90.06 235

DTE-MVSNet		76.99 250	76.80 236	77.54 318	86.24 252	53.06 390	87.52 175	90.66 145	77.08 68	72.50 305	88.67 199	60.48 206	89.52 298	57.33 335	70.74 378	90.05 236

v8		79.97 181	79.02 183	82.80 200	84.09 306	64.50 228	87.96 162	90.29 161	74.13 146	75.24 263	86.81 251	62.88 162	93.89 146	74.39 175	75.40 337	90.00 237

thres600view7		76.50 259	75.44 259	79.68 275	89.40 137	57.16 339	85.53 243	83.23 319	73.79 153	76.26 233	87.09 247	51.89 285	91.89 236	48.05 395	83.72 222	90.00 237

thres400		76.50 259	75.37 263	79.86 270	89.13 151	57.65 333	85.17 247	83.60 311	73.41 166	76.45 228	86.39 270	52.12 277	91.95 233	48.33 390	83.75 219	90.00 237

cl22		78.07 227	77.01 230	81.23 238	82.37 350	61.83 281	83.55 290	87.98 236	68.96 266	75.06 269	83.87 325	61.40 187	91.88 237	73.53 182	76.39 317	89.98 240

OPM-MVS		83.50 102	82.95 107	85.14 92	88.79 164	70.95 71	89.13 114	91.52 121	77.55 52	80.96 143	91.75 114	60.71 199	94.50 117	79.67 119	86.51 178	89.97 241
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline2		75.70 273	73.83 286	81.30 235	83.26 325	61.79 282	82.57 307	80.65 353	66.81 289	66.88 368	83.42 339	57.86 223	92.19 225	63.47 273	79.57 276	89.91 242

v10		79.74 183	78.67 187	82.97 193	84.06 307	64.95 217	87.88 168	90.62 146	73.11 173	75.11 267	86.56 265	61.46 185	94.05 134	73.68 180	75.55 330	89.90 243

MVSTER		79.01 203	77.88 209	82.38 213	83.07 331	64.80 222	84.08 280	88.95 213	69.01 265	78.69 173	87.17 245	54.70 252	92.43 214	74.69 171	80.57 266	89.89 244

ACMP	74.13 6	81.51 143	80.57 144	84.36 121	89.42 135	68.69 122	89.97 80	91.50 125	74.46 135	75.04 270	90.41 154	53.82 261	94.54 114	77.56 138	82.91 236	89.86 245
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LPG-MVS_test		82.08 126	81.27 132	84.50 115	89.23 147	68.76 115	90.22 76	91.94 104	75.37 109	76.64 223	91.51 123	54.29 255	94.91 98	78.44 127	83.78 216	89.83 246

LGP-MVS_train				84.50 115	89.23 147	68.76 115		91.94 104	75.37 109	76.64 223	91.51 123	54.29 255	94.91 98	78.44 127	83.78 216	89.83 246

V42		79.38 195	78.24 199	82.83 197	81.10 369	65.50 202	85.55 241	89.82 174	71.57 199	78.21 186	86.12 276	60.66 202	93.18 183	75.64 161	75.46 334	89.81 248

MAR-MVS		81.84 131	80.70 141	85.27 89	91.32 85	71.53 58	89.82 82	90.92 138	69.77 243	78.50 179	86.21 273	62.36 169	94.52 116	65.36 260	92.05 86	89.77 249
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		77.72 237	76.76 238	80.58 255	82.48 348	60.48 299	83.09 300	87.86 241	69.22 256	74.38 283	85.24 296	62.10 174	91.53 253	71.09 205	75.40 337	89.74 250

cl____		77.72 237	76.76 238	80.58 255	82.49 347	60.48 299	83.09 300	87.87 240	69.22 256	74.38 283	85.22 298	62.10 174	91.53 253	71.09 205	75.41 336	89.73 251

miper_ehance_all_eth		78.59 214	77.76 215	81.08 243	82.66 343	61.56 284	83.65 286	89.15 202	68.87 267	75.55 247	83.79 329	66.49 121	92.03 229	73.25 187	76.39 317	89.64 252

anonymousdsp		78.60 213	77.15 228	82.98 192	80.51 375	67.08 171	87.24 186	89.53 186	65.66 309	75.16 265	87.19 244	52.52 270	92.25 223	77.17 143	79.34 281	89.61 253

FMVSNet2		78.20 223	77.21 227	81.20 239	87.60 217	62.89 268	87.47 177	89.02 208	71.63 195	75.29 262	87.28 238	54.80 248	91.10 270	62.38 284	79.38 280	89.61 253

baseline1		76.98 251	76.75 240	77.66 313	88.13 190	55.66 364	85.12 250	81.89 339	73.04 175	76.79 218	88.90 192	62.43 168	87.78 329	63.30 276	71.18 376	89.55 255

ETVMVS		72.25 319	71.05 318	75.84 331	87.77 211	51.91 394	79.39 349	74.98 400	69.26 254	73.71 289	82.95 347	40.82 385	86.14 345	46.17 403	84.43 208	89.47 256

FMVSNet3		77.88 233	76.85 235	80.97 247	86.84 240	62.36 272	86.52 212	88.77 218	71.13 208	75.34 256	86.66 260	54.07 258	91.10 270	62.72 279	79.57 276	89.45 257

SD_0403		74.65 287	74.77 271	74.29 353	86.20 254	47.42 416	83.71 284	85.12 290	69.30 252	68.50 352	87.95 223	59.40 212	86.05 346	49.38 384	83.35 230	89.40 258

miper_enhance_ethall		77.87 234	76.86 234	80.92 248	81.65 357	61.38 286	82.68 305	88.98 210	65.52 311	75.47 248	82.30 358	65.76 133	92.00 231	72.95 190	76.39 317	89.39 259

testing11		75.14 283	74.01 281	78.53 297	88.16 187	56.38 353	80.74 330	80.42 359	70.67 218	72.69 304	83.72 332	43.61 367	89.86 291	62.29 286	83.76 218	89.36 260

cascas		76.72 256	74.64 272	82.99 191	85.78 264	65.88 191	82.33 308	89.21 199	60.85 363	72.74 301	81.02 369	47.28 331	93.75 153	67.48 242	85.02 196	89.34 261

Fast-Effi-MVS+-dtu		78.02 229	76.49 244	82.62 208	83.16 330	66.96 175	86.94 196	87.45 252	72.45 182	71.49 319	84.17 322	54.79 251	91.58 247	67.61 240	80.31 269	89.30 262

IB-MVS	68.01 15	75.85 272	73.36 292	83.31 173	84.76 292	66.03 185	83.38 293	85.06 292	70.21 232	69.40 342	81.05 368	45.76 350	94.66 113	65.10 263	75.49 331	89.25 263
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		76.50 259	75.55 258	79.33 281	89.52 129	56.99 342	85.83 234	83.23 319	73.94 149	76.32 232	87.12 246	51.89 285	91.95 233	48.33 390	83.75 219	89.07 264

tfpn200view9		76.42 263	75.37 263	79.55 280	89.13 151	57.65 333	85.17 247	83.60 311	73.41 166	76.45 228	86.39 270	52.12 277	91.95 233	48.33 390	83.75 219	89.07 264

xiu_mvs_v1_base_debu		80.80 158	79.72 164	84.03 149	87.35 222	70.19 84	85.56 238	88.77 218	69.06 262	81.83 127	88.16 215	50.91 296	92.85 197	78.29 131	87.56 159	89.06 266

xiu_mvs_v1_base		80.80 158	79.72 164	84.03 149	87.35 222	70.19 84	85.56 238	88.77 218	69.06 262	81.83 127	88.16 215	50.91 296	92.85 197	78.29 131	87.56 159	89.06 266

xiu_mvs_v1_base_debi		80.80 158	79.72 164	84.03 149	87.35 222	70.19 84	85.56 238	88.77 218	69.06 262	81.83 127	88.16 215	50.91 296	92.85 197	78.29 131	87.56 159	89.06 266

EPNet_dtu		75.46 277	74.86 269	77.23 322	82.57 345	54.60 375	86.89 198	83.09 323	71.64 194	66.25 379	85.86 280	55.99 240	88.04 325	54.92 352	86.55 177	89.05 269
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pm-mvs1		77.25 248	76.68 242	78.93 288	84.22 303	58.62 317	86.41 215	88.36 229	71.37 202	73.31 294	88.01 221	61.22 192	89.15 307	64.24 270	73.01 363	89.03 270

PVSNet_Blended		80.98 150	80.34 149	82.90 195	88.85 158	65.40 203	84.43 271	92.00 100	67.62 283	78.11 189	85.05 303	66.02 129	94.27 123	71.52 200	89.50 131	89.01 271

PAPM		77.68 240	76.40 247	81.51 228	87.29 230	61.85 280	83.78 282	89.59 184	64.74 320	71.23 321	88.70 197	62.59 164	93.66 156	52.66 364	87.03 169	89.01 271

WTY-MVS		75.65 274	75.68 254	75.57 335	86.40 250	56.82 344	77.92 374	82.40 334	65.10 315	76.18 236	87.72 226	63.13 160	80.90 387	60.31 305	81.96 248	89.00 273

无先验							87.48 176	88.98 210	60.00 370				94.12 131	67.28 244		88.97 274

GSMVS																88.96 275

sam_mvs1												51.32 292				88.96 275

SCA		74.22 291	72.33 304	79.91 269	84.05 308	62.17 276	79.96 344	79.29 373	66.30 301	72.38 308	80.13 381	51.95 283	88.60 318	59.25 314	77.67 300	88.96 275

miper_lstm_enhance		74.11 293	73.11 295	77.13 323	80.11 379	59.62 309	72.23 404	86.92 265	66.76 291	70.40 327	82.92 348	56.93 234	82.92 375	69.06 228	72.63 365	88.87 278

ACMM	73.20 8	80.78 161	79.84 162	83.58 165	89.31 143	68.37 130	89.99 79	91.60 119	70.28 229	77.25 206	89.66 171	53.37 266	93.53 162	74.24 177	82.85 237	88.85 279
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs6		74.69 286	73.39 290	78.61 292	81.38 364	57.48 336	86.64 208	87.95 238	64.99 319	70.18 330	86.61 261	50.43 303	89.52 298	62.12 289	70.18 381	88.83 280

原ACMM1				84.35 122	93.01 62	68.79 113		92.44 78	63.96 334	81.09 141	91.57 122	66.06 128	95.45 71	67.19 246	94.82 46	88.81 281

CNLPA		78.08 226	76.79 237	81.97 220	90.40 105	71.07 67	87.59 174	84.55 298	66.03 305	72.38 308	89.64 172	57.56 226	86.04 347	59.61 311	83.35 230	88.79 282

UWE-MVS		72.13 321	71.49 311	74.03 356	86.66 246	47.70 414	81.40 321	76.89 393	63.60 336	75.59 245	84.22 321	39.94 388	85.62 352	48.98 387	86.13 185	88.77 283

UBG		73.08 310	72.27 305	75.51 337	88.02 196	51.29 402	78.35 368	77.38 388	65.52 311	73.87 288	82.36 356	45.55 352	86.48 342	55.02 351	84.39 209	88.75 284

K. test v3		71.19 326	68.51 338	79.21 284	83.04 333	57.78 332	84.35 274	76.91 392	72.90 178	62.99 399	82.86 350	39.27 390	91.09 272	61.65 294	52.66 425	88.75 284

旧先验1					91.96 76	65.79 195		86.37 274			93.08 85	69.31 88			92.74 76	88.74 286

PatchmatchNet		73.12 309	71.33 315	78.49 299	83.18 328	60.85 293	79.63 346	78.57 378	64.13 327	71.73 315	79.81 386	51.20 294	85.97 348	57.40 334	76.36 322	88.66 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SixPastTwentyTwo		73.37 303	71.26 317	79.70 274	85.08 285	57.89 328	85.57 237	83.56 313	71.03 212	65.66 381	85.88 279	42.10 377	92.57 206	59.11 316	63.34 403	88.65 288

SSC-MVS3.2		73.35 306	73.39 290	73.23 362	85.30 278	49.01 412	74.58 397	81.57 343	75.21 113	73.68 290	85.58 288	52.53 269	82.05 380	54.33 356	77.69 299	88.63 289

PS-MVSNAJ		81.69 135	81.02 137	83.70 161	89.51 130	68.21 137	84.28 275	90.09 167	70.79 215	81.26 140	85.62 287	63.15 157	94.29 121	75.62 162	88.87 140	88.59 290

xiu_mvs_v2_base		81.69 135	81.05 136	83.60 163	89.15 150	68.03 142	84.46 269	90.02 168	70.67 218	81.30 139	86.53 267	63.17 156	94.19 129	75.60 163	88.54 147	88.57 291

MonoMVSNet		76.49 262	75.80 251	78.58 294	81.55 360	58.45 318	86.36 218	86.22 276	74.87 126	74.73 276	83.73 331	51.79 288	88.73 315	70.78 207	72.15 369	88.55 292

CostFormer		75.24 282	73.90 284	79.27 282	82.65 344	58.27 321	80.80 326	82.73 332	61.57 358	75.33 260	83.13 344	55.52 243	91.07 273	64.98 264	78.34 292	88.45 293

lessismore_v0				78.97 287	81.01 370	57.15 340		65.99 427		61.16 405	82.82 351	39.12 392	91.34 262	59.67 310	46.92 432	88.43 294

OpenMVS	72.83 10	79.77 182	78.33 197	84.09 140	85.17 280	69.91 89	90.57 64	90.97 137	66.70 292	72.17 311	91.91 108	54.70 252	93.96 135	61.81 293	90.95 105	88.41 295

reproduce_monomvs		75.40 280	74.38 278	78.46 300	83.92 311	57.80 331	83.78 282	86.94 263	73.47 164	72.25 310	84.47 311	38.74 394	89.27 303	75.32 167	70.53 379	88.31 296

VortexMVS		78.57 215	77.89 208	80.59 254	85.89 261	62.76 269	85.61 236	89.62 183	72.06 190	74.99 271	85.38 293	55.94 241	90.77 279	74.99 169	76.58 312	88.23 297

OurMVSNet-221017-0		74.26 290	72.42 303	79.80 272	83.76 315	59.59 310	85.92 230	86.64 268	66.39 300	66.96 367	87.58 230	39.46 389	91.60 246	65.76 258	69.27 384	88.22 298

LS3D		76.95 252	74.82 270	83.37 172	90.45 103	67.36 163	89.15 113	86.94 263	61.87 357	69.52 341	90.61 150	51.71 289	94.53 115	46.38 402	86.71 175	88.21 299

WBMVS		73.43 302	72.81 298	75.28 341	87.91 201	50.99 404	78.59 364	81.31 348	65.51 313	74.47 281	84.83 306	46.39 339	86.68 339	58.41 324	77.86 295	88.17 300

XVG-ACMP-BASELINE		76.11 268	74.27 280	81.62 225	83.20 327	64.67 224	83.60 289	89.75 178	69.75 244	71.85 314	87.09 247	32.78 413	92.11 227	69.99 218	80.43 268	88.09 301

tpm2		73.26 307	71.46 312	78.63 291	83.34 323	56.71 347	80.65 332	80.40 360	56.63 399	73.55 292	82.02 363	51.80 287	91.24 265	56.35 346	78.42 290	87.95 302

MDTV_nov1_ep13_2view						37.79 441	75.16 391		55.10 404	66.53 374		49.34 317		53.98 357		87.94 303

Patchmatch-test		64.82 378	63.24 379	69.57 388	79.42 391	49.82 410	63.49 435	69.05 420	51.98 414	59.95 410	80.13 381	50.91 296	70.98 429	40.66 419	73.57 357	87.90 304

PLC	70.83 11	78.05 228	76.37 248	83.08 186	91.88 79	67.80 148	88.19 154	89.46 188	64.33 326	69.87 338	88.38 208	53.66 262	93.58 157	58.86 319	82.73 239	87.86 305
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		72.37 317	71.71 309	74.35 352	82.19 351	52.00 392	79.22 352	77.29 389	64.56 322	72.95 300	83.68 334	51.35 291	83.26 374	58.33 326	75.80 326	87.81 306

Patchmatch-RL test		70.24 339	67.78 352	77.61 315	77.43 400	59.57 311	71.16 408	70.33 414	62.94 343	68.65 349	72.77 420	50.62 300	85.49 354	69.58 223	66.58 394	87.77 307

F-COLMAP		76.38 265	74.33 279	82.50 211	89.28 145	66.95 176	88.41 144	89.03 207	64.05 331	66.83 369	88.61 201	46.78 337	92.89 196	57.48 332	78.55 286	87.67 308

Baseline_NR-MVSNet		78.15 225	78.33 197	77.61 315	85.79 263	56.21 357	86.78 203	85.76 284	73.60 159	77.93 194	87.57 231	65.02 138	88.99 309	67.14 247	75.33 339	87.63 309

CL-MVSNet_self_test		72.37 317	71.46 312	75.09 343	79.49 390	53.53 383	80.76 329	85.01 294	69.12 260	70.51 325	82.05 362	57.92 222	84.13 365	52.27 366	66.00 397	87.60 310

ACMH+	68.96 14	76.01 270	74.01 281	82.03 218	88.60 171	65.31 207	88.86 123	87.55 248	70.25 231	67.75 356	87.47 236	41.27 381	93.19 182	58.37 325	75.94 325	87.60 310

1314		76.53 258	75.30 265	80.21 264	83.93 310	62.32 274	84.66 261	88.81 216	60.23 368	70.16 332	84.07 324	55.30 245	90.73 280	67.37 243	83.21 233	87.59 312

API-MVS		81.99 129	81.23 133	84.26 131	90.94 93	70.18 87	91.10 58	89.32 192	71.51 200	78.66 175	88.28 211	65.26 135	95.10 93	64.74 266	91.23 100	87.51 313

AdaColmap		80.58 168	79.42 171	84.06 144	93.09 59	68.91 111	89.36 103	88.97 212	69.27 253	75.70 244	89.69 169	57.20 232	95.77 60	63.06 277	88.41 151	87.50 314

PVSNet_BlendedMVS		80.60 165	80.02 157	82.36 214	88.85 158	65.40 203	86.16 224	92.00 100	69.34 251	78.11 189	86.09 277	66.02 129	94.27 123	71.52 200	82.06 247	87.39 315

sss		73.60 300	73.64 288	73.51 361	82.80 339	55.01 372	76.12 382	81.69 342	62.47 350	74.68 277	85.85 281	57.32 229	78.11 398	60.86 301	80.93 258	87.39 315

IterMVS-SCA-FT		75.43 278	73.87 285	80.11 266	82.69 342	64.85 221	81.57 317	83.47 315	69.16 259	70.49 326	84.15 323	51.95 283	88.15 323	69.23 225	72.14 370	87.34 317

PVSNet	64.34 18	72.08 322	70.87 321	75.69 333	86.21 253	56.44 351	74.37 398	80.73 352	62.06 355	70.17 331	82.23 360	42.86 371	83.31 373	54.77 353	84.45 207	87.32 318

tt0320-xc		70.11 341	67.45 358	78.07 306	85.33 277	59.51 312	83.28 295	78.96 376	58.77 382	67.10 366	80.28 379	36.73 403	87.42 333	56.83 342	59.77 414	87.29 319

新几何1				83.42 169	93.13 56	70.71 76		85.48 287	57.43 395	81.80 130	91.98 107	63.28 152	92.27 222	64.60 267	92.99 72	87.27 320

TR-MVS		77.44 243	76.18 249	81.20 239	88.24 184	63.24 257	84.61 264	86.40 273	67.55 284	77.81 195	86.48 268	54.10 257	93.15 184	57.75 331	82.72 240	87.20 321

TransMVSNet (Re)		75.39 281	74.56 274	77.86 309	85.50 273	57.10 341	86.78 203	86.09 280	72.17 188	71.53 318	87.34 237	63.01 161	89.31 302	56.84 341	61.83 407	87.17 322

ACMH	67.68 16	75.89 271	73.93 283	81.77 223	88.71 168	66.61 178	88.62 138	89.01 209	69.81 240	66.78 370	86.70 258	41.95 379	91.51 255	55.64 348	78.14 293	87.17 322
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
KD-MVS_self_test		68.81 351	67.59 356	72.46 372	74.29 413	45.45 422	77.93 373	87.00 261	63.12 338	63.99 394	78.99 394	42.32 374	84.77 362	56.55 345	64.09 402	87.16 324

EPMVS		69.02 350	68.16 342	71.59 376	79.61 388	49.80 411	77.40 377	66.93 425	62.82 346	70.01 333	79.05 390	45.79 349	77.86 400	56.58 344	75.26 341	87.13 325

CR-MVSNet		73.37 303	71.27 316	79.67 276	81.32 367	65.19 209	75.92 384	80.30 361	59.92 371	72.73 302	81.19 366	52.50 271	86.69 338	59.84 308	77.71 297	87.11 326

RPMNet		73.51 301	70.49 324	82.58 210	81.32 367	65.19 209	75.92 384	92.27 85	57.60 393	72.73 302	76.45 408	52.30 274	95.43 73	48.14 394	77.71 297	87.11 326

test_vis1_n_1920		75.52 276	75.78 252	74.75 349	79.84 383	57.44 337	83.26 296	85.52 286	62.83 345	79.34 165	86.17 275	45.10 356	79.71 391	78.75 124	81.21 256	87.10 328

tt0320		70.49 337	68.03 345	77.89 308	84.78 291	59.12 314	83.55 290	80.44 358	58.13 388	67.43 362	80.41 377	39.26 391	87.54 332	55.12 350	63.18 405	86.99 329

XXY-MVS		75.41 279	75.56 257	74.96 344	83.59 318	57.82 330	80.59 333	83.87 309	66.54 299	74.93 273	88.31 210	63.24 154	80.09 390	62.16 288	76.85 309	86.97 330

tpmrst		72.39 315	72.13 306	73.18 366	80.54 374	49.91 409	79.91 345	79.08 375	63.11 339	71.69 316	79.95 383	55.32 244	82.77 376	65.66 259	73.89 354	86.87 331

thres200		75.55 275	74.47 276	78.82 289	87.78 210	57.85 329	83.07 302	83.51 314	72.44 184	75.84 242	84.42 312	52.08 280	91.75 241	47.41 397	83.64 224	86.86 332

ITE_SJBPF				78.22 302	81.77 356	60.57 297		83.30 317	69.25 255	67.54 358	87.20 243	36.33 406	87.28 335	54.34 355	74.62 348	86.80 333

test222					91.50 82	68.26 133	84.16 277	83.20 322	54.63 406	79.74 158	91.63 119	58.97 215			91.42 96	86.77 334

MIMVSNet		70.69 333	69.30 332	74.88 346	84.52 298	56.35 355	75.87 386	79.42 370	64.59 321	67.76 355	82.41 355	41.10 382	81.54 383	46.64 401	81.34 253	86.75 335

BH-untuned		79.47 189	78.60 189	82.05 217	89.19 149	65.91 190	86.07 226	88.52 227	72.18 187	75.42 252	87.69 228	61.15 193	93.54 161	60.38 304	86.83 173	86.70 336

LTVRE_ROB	69.57 13	76.25 266	74.54 275	81.41 231	88.60 171	64.38 232	79.24 351	89.12 205	70.76 217	69.79 340	87.86 224	49.09 321	93.20 180	56.21 347	80.16 270	86.65 337
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				79.97 268	90.90 94	64.21 234		84.71 295	59.27 377	85.40 68	92.91 87	62.02 176	89.08 308	68.95 229	91.37 98	86.63 338

MIMVSNet1		68.58 354	66.78 364	73.98 357	80.07 380	51.82 396	80.77 328	84.37 299	64.40 324	59.75 411	82.16 361	36.47 405	83.63 369	42.73 414	70.33 380	86.48 339

tfpnnormal		74.39 288	73.16 294	78.08 305	86.10 259	58.05 323	84.65 263	87.53 249	70.32 228	71.22 322	85.63 286	54.97 246	89.86 291	43.03 413	75.02 344	86.32 340

D2MVS		74.82 285	73.21 293	79.64 277	79.81 384	62.56 271	80.34 338	87.35 253	64.37 325	68.86 347	82.66 353	46.37 341	90.10 287	67.91 238	81.24 255	86.25 341

tpm cat1		70.57 334	68.31 340	77.35 320	82.41 349	57.95 327	78.08 370	80.22 363	52.04 412	68.54 351	77.66 403	52.00 282	87.84 328	51.77 367	72.07 371	86.25 341

CVMVSNet		72.99 312	72.58 301	74.25 354	84.28 301	50.85 405	86.41 215	83.45 316	44.56 425	73.23 296	87.54 234	49.38 316	85.70 350	65.90 256	78.44 289	86.19 343

AllTest		70.96 329	68.09 344	79.58 278	85.15 282	63.62 245	84.58 265	79.83 366	62.31 351	60.32 408	86.73 252	32.02 414	88.96 312	50.28 378	71.57 374	86.15 344

TestCases				79.58 278	85.15 282	63.62 245		79.83 366	62.31 351	60.32 408	86.73 252	32.02 414	88.96 312	50.28 378	71.57 374	86.15 344

test-LLR		72.94 313	72.43 302	74.48 350	81.35 365	58.04 324	78.38 365	77.46 385	66.66 293	69.95 336	79.00 392	48.06 327	79.24 392	66.13 252	84.83 198	86.15 344

test-mter		71.41 325	70.39 327	74.48 350	81.35 365	58.04 324	78.38 365	77.46 385	60.32 367	69.95 336	79.00 392	36.08 407	79.24 392	66.13 252	84.83 198	86.15 344

IterMVS		74.29 289	72.94 297	78.35 301	81.53 361	63.49 251	81.58 316	82.49 333	68.06 280	69.99 335	83.69 333	51.66 290	85.54 353	65.85 257	71.64 373	86.01 348
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		76.78 255	74.57 273	83.42 169	93.29 48	69.46 100	88.55 141	83.70 310	63.98 333	70.20 329	88.89 193	54.01 260	94.80 107	46.66 399	81.88 250	86.01 348

ppachtmachnet_test		70.04 342	67.34 360	78.14 304	79.80 385	61.13 287	79.19 353	80.59 354	59.16 378	65.27 384	79.29 389	46.75 338	87.29 334	49.33 385	66.72 392	86.00 350

mmtdpeth		74.16 292	73.01 296	77.60 317	83.72 316	61.13 287	85.10 251	85.10 291	72.06 190	77.21 212	80.33 378	43.84 365	85.75 349	77.14 144	52.61 426	85.91 351

test_fmvs1_n		70.86 331	70.24 328	72.73 369	72.51 427	55.28 369	81.27 322	79.71 368	51.49 416	78.73 172	84.87 305	27.54 423	77.02 403	76.06 156	79.97 274	85.88 352

Patchmtry		70.74 332	69.16 335	75.49 338	80.72 371	54.07 380	74.94 395	80.30 361	58.34 385	70.01 333	81.19 366	52.50 271	86.54 340	53.37 361	71.09 377	85.87 353

WB-MVSnew		71.96 323	71.65 310	72.89 367	84.67 297	51.88 395	82.29 309	77.57 384	62.31 351	73.67 291	83.00 346	53.49 265	81.10 386	45.75 406	82.13 246	85.70 354

test_fmvs2		68.35 358	67.48 357	70.98 384	69.50 430	51.95 393	80.05 342	76.38 395	49.33 419	74.65 278	84.38 314	23.30 432	75.40 420	74.51 173	75.17 343	85.60 355

ambc				75.24 342	73.16 422	50.51 407	63.05 436	87.47 251		64.28 390	77.81 402	17.80 438	89.73 295	57.88 330	60.64 411	85.49 356

mvs5depth		69.45 347	67.45 358	75.46 339	73.93 414	55.83 361	79.19 353	83.23 319	66.89 288	71.63 317	83.32 340	33.69 412	85.09 358	59.81 309	55.34 422	85.46 357

UnsupCasMVSNet_eth		67.33 363	65.99 367	71.37 378	73.48 419	51.47 400	75.16 391	85.19 289	65.20 314	60.78 406	80.93 373	42.35 373	77.20 402	57.12 336	53.69 424	85.44 358

PatchT		68.46 357	67.85 348	70.29 386	80.70 372	43.93 430	72.47 403	74.88 401	60.15 369	70.55 324	76.57 407	49.94 309	81.59 382	50.58 374	74.83 346	85.34 359

Anonymous20240521		68.80 352	67.22 361	73.55 360	74.33 412	54.11 379	83.18 297	85.61 285	58.15 387	61.68 403	80.94 371	30.71 419	81.27 385	57.00 339	73.34 362	85.28 360

test_cas_vis1_n_1920		73.76 298	73.74 287	73.81 359	75.90 405	59.77 307	80.51 334	82.40 334	58.30 386	81.62 133	85.69 283	44.35 362	76.41 409	76.29 153	78.61 285	85.23 361

ADS-MVSNet2		66.20 374	63.33 378	74.82 347	79.92 381	58.75 316	67.55 423	75.19 399	53.37 409	65.25 385	75.86 411	42.32 374	80.53 389	41.57 417	68.91 386	85.18 362

ADS-MVSNet		64.36 379	62.88 382	68.78 394	79.92 381	47.17 418	67.55 423	71.18 413	53.37 409	65.25 385	75.86 411	42.32 374	73.99 425	41.57 417	68.91 386	85.18 362

FMVSNet5		69.50 346	67.96 346	74.15 355	82.97 337	55.35 368	80.01 343	82.12 337	62.56 349	63.02 397	81.53 365	36.92 402	81.92 381	48.42 389	74.06 352	85.17 364

pmmvs5		71.55 324	70.20 329	75.61 334	77.83 398	56.39 352	81.74 314	80.89 349	57.76 391	67.46 360	84.49 310	49.26 319	85.32 357	57.08 337	75.29 340	85.11 365

testing3		68.56 355	67.67 354	71.22 382	87.33 227	42.87 432	83.06 303	71.54 412	70.36 225	69.08 346	84.38 314	30.33 420	85.69 351	37.50 425	75.45 335	85.09 366

UWE-MVS-28		65.32 375	64.93 369	66.49 403	78.70 395	38.55 440	77.86 375	64.39 432	62.00 356	64.13 392	83.60 335	41.44 380	76.00 413	31.39 432	80.89 259	84.92 367

CMPMVS	51.72 21	70.19 340	68.16 342	76.28 328	73.15 423	57.55 335	79.47 348	83.92 307	48.02 421	56.48 421	84.81 307	43.13 369	86.42 343	62.67 282	81.81 251	84.89 368
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testgi		66.67 368	66.53 365	67.08 402	75.62 408	41.69 437	75.93 383	76.50 394	66.11 302	65.20 387	86.59 262	35.72 408	74.71 422	43.71 411	73.38 361	84.84 369

MSDG		73.36 305	70.99 319	80.49 257	84.51 299	65.80 194	80.71 331	86.13 279	65.70 308	65.46 382	83.74 330	44.60 358	90.91 275	51.13 373	76.89 307	84.74 370

pmmvs4		74.03 296	71.91 307	80.39 258	81.96 353	68.32 131	81.45 319	82.14 336	59.32 376	69.87 338	85.13 300	52.40 273	88.13 324	60.21 306	74.74 347	84.73 371

gg-mvs-nofinetune		69.95 343	67.96 346	75.94 330	83.07 331	54.51 377	77.23 379	70.29 415	63.11 339	70.32 328	62.33 429	43.62 366	88.69 316	53.88 358	87.76 158	84.62 372

test_fmvs1		70.93 330	70.52 323	72.16 373	73.71 416	55.05 371	80.82 325	78.77 377	51.21 417	78.58 177	84.41 313	31.20 418	76.94 404	75.88 159	80.12 273	84.47 373

BH-w/o		78.21 222	77.33 226	80.84 249	88.81 162	65.13 211	84.87 256	87.85 242	69.75 244	74.52 280	84.74 309	61.34 188	93.11 187	58.24 327	85.84 190	84.27 374

MVS		78.19 224	76.99 232	81.78 222	85.66 266	66.99 172	84.66 261	90.47 151	55.08 405	72.02 313	85.27 295	63.83 149	94.11 132	66.10 254	89.80 126	84.24 375

COLMAP_ROB	66.92 17	73.01 311	70.41 326	80.81 250	87.13 234	65.63 198	88.30 151	84.19 305	62.96 342	63.80 396	87.69 228	38.04 399	92.56 207	46.66 399	74.91 345	84.24 375
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
new-patchmatchnet		61.73 385	61.73 386	61.70 409	72.74 425	24.50 452	69.16 418	78.03 381	61.40 359	56.72 420	75.53 414	38.42 396	76.48 408	45.95 405	57.67 415	84.13 377

TESTMET0.1,1		69.89 344	69.00 336	72.55 370	79.27 393	56.85 343	78.38 365	74.71 404	57.64 392	68.09 354	77.19 405	37.75 400	76.70 405	63.92 271	84.09 213	84.10 378

test_fmvs3		63.36 382	61.82 385	67.98 399	62.51 439	46.96 420	77.37 378	74.03 406	45.24 424	67.50 359	78.79 395	12.16 444	72.98 428	72.77 193	66.02 396	83.99 379

our_test_3		69.14 349	67.00 362	75.57 335	79.80 385	58.80 315	77.96 372	77.81 382	59.55 374	62.90 400	78.25 399	47.43 329	83.97 366	51.71 368	67.58 391	83.93 380

test_vis1_n		69.85 345	69.21 334	71.77 375	72.66 426	55.27 370	81.48 318	76.21 396	52.03 413	75.30 261	83.20 343	28.97 421	76.22 411	74.60 172	78.41 291	83.81 381

mamv4		76.81 254	78.23 201	72.54 371	86.12 257	65.75 197	78.76 360	82.07 338	64.12 328	72.97 299	91.02 143	67.97 105	68.08 436	83.04 82	78.02 294	83.80 382

tpmvs		71.09 328	69.29 333	76.49 327	82.04 352	56.04 358	78.92 358	81.37 347	64.05 331	67.18 365	78.28 398	49.74 312	89.77 293	49.67 383	72.37 366	83.67 383

test20.03		67.45 362	66.95 363	68.94 391	75.48 409	44.84 428	77.50 376	77.67 383	66.66 293	63.01 398	83.80 328	47.02 333	78.40 396	42.53 416	68.86 388	83.58 384

test0.0.03 1		68.00 360	67.69 353	68.90 392	77.55 399	47.43 415	75.70 387	72.95 411	66.66 293	66.56 373	82.29 359	48.06 327	75.87 415	44.97 410	74.51 349	83.41 385

Anonymous20231206		68.60 353	67.80 351	71.02 383	80.23 378	50.75 406	78.30 369	80.47 356	56.79 398	66.11 380	82.63 354	46.35 342	78.95 394	43.62 412	75.70 327	83.36 386

EU-MVSNet		68.53 356	67.61 355	71.31 381	78.51 397	47.01 419	84.47 267	84.27 303	42.27 428	66.44 378	84.79 308	40.44 386	83.76 367	58.76 321	68.54 389	83.17 387

dp		66.80 366	65.43 368	70.90 385	79.74 387	48.82 413	75.12 393	74.77 402	59.61 373	64.08 393	77.23 404	42.89 370	80.72 388	48.86 388	66.58 394	83.16 388

pmmvs-eth3d		70.50 336	67.83 350	78.52 298	77.37 401	66.18 184	81.82 312	81.51 344	58.90 381	63.90 395	80.42 376	42.69 372	86.28 344	58.56 322	65.30 399	83.11 389

YYNet1		65.03 376	62.91 381	71.38 377	75.85 406	56.60 349	69.12 419	74.66 405	57.28 396	54.12 424	77.87 401	45.85 348	74.48 423	49.95 381	61.52 409	83.05 390

MDA-MVSNet-bldmvs		66.68 367	63.66 377	75.75 332	79.28 392	60.56 298	73.92 400	78.35 380	64.43 323	50.13 430	79.87 385	44.02 364	83.67 368	46.10 404	56.86 416	83.03 391

MDA-MVSNet_test_wron		65.03 376	62.92 380	71.37 378	75.93 404	56.73 345	69.09 420	74.73 403	57.28 396	54.03 425	77.89 400	45.88 347	74.39 424	49.89 382	61.55 408	82.99 392

USDC		70.33 338	68.37 339	76.21 329	80.60 373	56.23 356	79.19 353	86.49 271	60.89 362	61.29 404	85.47 291	31.78 416	89.47 300	53.37 361	76.21 323	82.94 393

Syy-MVS		68.05 359	67.85 348	68.67 395	84.68 294	40.97 438	78.62 362	73.08 409	66.65 296	66.74 371	79.46 387	52.11 279	82.30 378	32.89 430	76.38 320	82.75 394

myMVS_eth3d		67.02 365	66.29 366	69.21 390	84.68 294	42.58 433	78.62 362	73.08 409	66.65 296	66.74 371	79.46 387	31.53 417	82.30 378	39.43 422	76.38 320	82.75 394

ttmdpeth		59.91 388	57.10 392	68.34 397	67.13 434	46.65 421	74.64 396	67.41 424	48.30 420	62.52 402	85.04 304	20.40 434	75.93 414	42.55 415	45.90 435	82.44 396

OpenMVS_ROB	64.09 19	70.56 335	68.19 341	77.65 314	80.26 376	59.41 313	85.01 253	82.96 328	58.76 383	65.43 383	82.33 357	37.63 401	91.23 266	45.34 409	76.03 324	82.32 397

JIA-IIPM		66.32 371	62.82 383	76.82 325	77.09 402	61.72 283	65.34 431	75.38 398	58.04 390	64.51 389	62.32 430	42.05 378	86.51 341	51.45 371	69.22 385	82.21 398

dmvs_re		71.14 327	70.58 322	72.80 368	81.96 353	59.68 308	75.60 388	79.34 372	68.55 272	69.27 345	80.72 374	49.42 315	76.54 406	52.56 365	77.79 296	82.19 399

EG-PatchMatch MVS		74.04 294	71.82 308	80.71 252	84.92 288	67.42 159	85.86 232	88.08 233	66.04 304	64.22 391	83.85 326	35.10 409	92.56 207	57.44 333	80.83 261	82.16 400

MVP-Stereo		76.12 267	74.46 277	81.13 242	85.37 276	69.79 91	84.42 272	87.95 238	65.03 317	67.46 360	85.33 294	53.28 267	91.73 243	58.01 329	83.27 232	81.85 401
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
TDRefinement		67.49 361	64.34 372	76.92 324	73.47 420	61.07 290	84.86 257	82.98 327	59.77 372	58.30 415	85.13 300	26.06 424	87.89 327	47.92 396	60.59 412	81.81 402

GG-mvs-BLEND				75.38 340	81.59 359	55.80 362	79.32 350	69.63 417		67.19 364	73.67 418	43.24 368	88.90 314	50.41 375	84.50 203	81.45 403

KD-MVS_2432*1600		66.22 372	63.89 375	73.21 363	75.47 410	53.42 385	70.76 411	84.35 300	64.10 329	66.52 375	78.52 396	34.55 410	84.98 359	50.40 376	50.33 429	81.23 404

miper_refine_blended		66.22 372	63.89 375	73.21 363	75.47 410	53.42 385	70.76 411	84.35 300	64.10 329	66.52 375	78.52 396	34.55 410	84.98 359	50.40 376	50.33 429	81.23 404

test_0402		72.79 314	70.44 325	79.84 271	88.13 190	65.99 188	85.93 229	84.29 302	65.57 310	67.40 363	85.49 290	46.92 334	92.61 203	35.88 427	74.38 350	80.94 406

MVStest1		56.63 392	52.76 398	68.25 398	61.67 440	53.25 389	71.67 406	68.90 422	38.59 433	50.59 429	83.05 345	25.08 426	70.66 430	36.76 426	38.56 436	80.83 407

UnsupCasMVSNet_bld		63.70 381	61.53 387	70.21 387	73.69 417	51.39 401	72.82 402	81.89 339	55.63 403	57.81 417	71.80 422	38.67 395	78.61 395	49.26 386	52.21 427	80.63 408

LCM-MVSNet		54.25 394	49.68 404	67.97 400	53.73 448	45.28 425	66.85 426	80.78 351	35.96 437	39.45 438	62.23 431	8.70 448	78.06 399	48.24 393	51.20 428	80.57 409

N_pmnet		52.79 399	53.26 397	51.40 423	78.99 394	7.68 457	69.52 415	3.89 456	51.63 415	57.01 419	74.98 415	40.83 384	65.96 438	37.78 424	64.67 400	80.56 410

TinyColmap		67.30 364	64.81 370	74.76 348	81.92 355	56.68 348	80.29 339	81.49 345	60.33 366	56.27 422	83.22 341	24.77 428	87.66 331	45.52 407	69.47 383	79.95 411

PM-MVS		66.41 370	64.14 373	73.20 365	73.92 415	56.45 350	78.97 357	64.96 431	63.88 335	64.72 388	80.24 380	19.84 436	83.44 372	66.24 251	64.52 401	79.71 412

ANet_high		50.57 403	46.10 407	63.99 406	48.67 451	39.13 439	70.99 410	80.85 350	61.39 360	31.18 440	57.70 436	17.02 439	73.65 427	31.22 433	15.89 448	79.18 413

LF4IMVS		64.02 380	62.19 384	69.50 389	70.90 428	53.29 388	76.13 381	77.18 390	52.65 411	58.59 413	80.98 370	23.55 431	76.52 407	53.06 363	66.66 393	78.68 414

PatchMatch-RL		72.38 316	70.90 320	76.80 326	88.60 171	67.38 162	79.53 347	76.17 397	62.75 347	69.36 343	82.00 364	45.51 353	84.89 361	53.62 359	80.58 265	78.12 415

MS-PatchMatch		73.83 297	72.67 299	77.30 321	83.87 312	66.02 186	81.82 312	84.66 296	61.37 361	68.61 350	82.82 351	47.29 330	88.21 322	59.27 313	84.32 210	77.68 416

DSMNet-mixed		57.77 391	56.90 393	60.38 411	67.70 432	35.61 442	69.18 417	53.97 443	32.30 441	57.49 418	79.88 384	40.39 387	68.57 435	38.78 423	72.37 366	76.97 417

CHOSEN 280x420		66.51 369	64.71 371	71.90 374	81.45 362	63.52 250	57.98 438	68.95 421	53.57 408	62.59 401	76.70 406	46.22 344	75.29 421	55.25 349	79.68 275	76.88 418

mvsany_test3		53.99 395	51.45 400	61.61 410	55.51 444	44.74 429	63.52 434	45.41 449	43.69 427	58.11 416	76.45 408	17.99 437	63.76 440	54.77 353	47.59 431	76.34 419

dmvs_testset		62.63 383	64.11 374	58.19 413	78.55 396	24.76 451	75.28 389	65.94 428	67.91 281	60.34 407	76.01 410	53.56 263	73.94 426	31.79 431	67.65 390	75.88 420

mvsany_test1		62.30 384	61.26 388	65.41 405	69.52 429	54.86 373	66.86 425	49.78 445	46.65 422	68.50 352	83.21 342	49.15 320	66.28 437	56.93 340	60.77 410	75.11 421

PMMVS		69.34 348	68.67 337	71.35 380	75.67 407	62.03 277	75.17 390	73.46 407	50.00 418	68.68 348	79.05 390	52.07 281	78.13 397	61.16 299	82.77 238	73.90 422

test_vis1_rt		60.28 387	58.42 390	65.84 404	67.25 433	55.60 365	70.44 413	60.94 437	44.33 426	59.00 412	66.64 427	24.91 427	68.67 434	62.80 278	69.48 382	73.25 423

pmmvs3		57.79 390	54.26 395	68.37 396	64.02 438	56.72 346	75.12 393	65.17 429	40.20 430	52.93 426	69.86 426	20.36 435	75.48 418	45.45 408	55.25 423	72.90 424

PVSNet_0	57.27 20	61.67 386	59.27 389	68.85 393	79.61 388	57.44 337	68.01 421	73.44 408	55.93 402	58.54 414	70.41 425	44.58 359	77.55 401	47.01 398	35.91 437	71.55 425

WB-MVS		54.94 393	54.72 394	55.60 419	73.50 418	20.90 453	74.27 399	61.19 436	59.16 378	50.61 428	74.15 416	47.19 332	75.78 416	17.31 444	35.07 438	70.12 426

SSC-MVS		53.88 396	53.59 396	54.75 421	72.87 424	19.59 454	73.84 401	60.53 438	57.58 394	49.18 432	73.45 419	46.34 343	75.47 419	16.20 447	32.28 440	69.20 427

test_f		52.09 400	50.82 401	55.90 417	53.82 447	42.31 436	59.42 437	58.31 441	36.45 436	56.12 423	70.96 424	12.18 443	57.79 443	53.51 360	56.57 418	67.60 428

PMMVS2		40.82 410	38.86 414	46.69 424	53.84 446	16.45 455	48.61 441	49.92 444	37.49 434	31.67 439	60.97 432	8.14 450	56.42 444	28.42 435	30.72 441	67.19 429

new_pmnet		50.91 402	50.29 402	52.78 422	68.58 431	34.94 444	63.71 433	56.63 442	39.73 431	44.95 433	65.47 428	21.93 433	58.48 442	34.98 428	56.62 417	64.92 430

MVS-HIRNet		59.14 389	57.67 391	63.57 407	81.65 357	43.50 431	71.73 405	65.06 430	39.59 432	51.43 427	57.73 435	38.34 397	82.58 377	39.53 420	73.95 353	64.62 431

APD_test1		53.31 398	49.93 403	63.42 408	65.68 435	50.13 408	71.59 407	66.90 426	34.43 438	40.58 437	71.56 423	8.65 449	76.27 410	34.64 429	55.36 421	63.86 432

test_method		31.52 413	29.28 417	38.23 427	27.03 455	6.50 458	20.94 446	62.21 435	4.05 449	22.35 447	52.50 440	13.33 441	47.58 447	27.04 437	34.04 439	60.62 433

EGC-MVSNET		52.07 401	47.05 405	67.14 401	83.51 320	60.71 295	80.50 335	67.75 423	0.07 451	0.43 452	75.85 413	24.26 429	81.54 383	28.82 434	62.25 406	59.16 434

test_vis3_rt		49.26 404	47.02 406	56.00 416	54.30 445	45.27 426	66.76 427	48.08 446	36.83 435	44.38 434	53.20 439	7.17 451	64.07 439	56.77 343	55.66 419	58.65 435

FPMVS		53.68 397	51.64 399	59.81 412	65.08 436	51.03 403	69.48 416	69.58 418	41.46 429	40.67 436	72.32 421	16.46 440	70.00 433	24.24 440	65.42 398	58.40 436

testf1		45.72 405	41.96 409	57.00 414	56.90 442	45.32 423	66.14 428	59.26 439	26.19 442	30.89 441	60.96 433	4.14 452	70.64 431	26.39 438	46.73 433	55.04 437

APD_test2		45.72 405	41.96 409	57.00 414	56.90 442	45.32 423	66.14 428	59.26 439	26.19 442	30.89 441	60.96 433	4.14 452	70.64 431	26.39 438	46.73 433	55.04 437

PMVS	37.38 22	44.16 409	40.28 413	55.82 418	40.82 453	42.54 435	65.12 432	63.99 433	34.43 438	24.48 444	57.12 437	3.92 454	76.17 412	17.10 445	55.52 420	48.75 439
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 415	25.89 419	43.81 426	44.55 452	35.46 443	28.87 445	39.07 450	18.20 446	18.58 448	40.18 443	2.68 455	47.37 448	17.07 446	23.78 445	48.60 440
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dongtai		45.42 407	45.38 408	45.55 425	73.36 421	26.85 449	67.72 422	34.19 451	54.15 407	49.65 431	56.41 438	25.43 425	62.94 441	19.45 442	28.09 442	46.86 441

kuosan		39.70 411	40.40 412	37.58 428	64.52 437	26.98 447	65.62 430	33.02 452	46.12 423	42.79 435	48.99 441	24.10 430	46.56 449	12.16 450	26.30 443	39.20 442

Gipuma		45.18 408	41.86 411	55.16 420	77.03 403	51.52 399	32.50 444	80.52 355	32.46 440	27.12 443	35.02 444	9.52 447	75.50 417	22.31 441	60.21 413	38.45 443
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DeepMVS_CX				27.40 431	40.17 454	26.90 448		24.59 455	17.44 447	23.95 445	48.61 442	9.77 446	26.48 450	18.06 443	24.47 444	28.83 444

E-PMN		31.77 412	30.64 415	35.15 429	52.87 449	27.67 446	57.09 439	47.86 447	24.64 444	16.40 449	33.05 445	11.23 445	54.90 445	14.46 448	18.15 446	22.87 445

EMVS		30.81 414	29.65 416	34.27 430	50.96 450	25.95 450	56.58 440	46.80 448	24.01 445	15.53 450	30.68 446	12.47 442	54.43 446	12.81 449	17.05 447	22.43 446

tmp_tt		18.61 417	21.40 420	10.23 433	4.82 456	10.11 456	34.70 443	30.74 454	1.48 450	23.91 446	26.07 447	28.42 422	13.41 452	27.12 436	15.35 449	7.17 447

wuyk23d		16.82 418	15.94 421	19.46 432	58.74 441	31.45 445	39.22 442	3.74 457	6.84 448	6.04 451	2.70 451	1.27 456	24.29 451	10.54 451	14.40 450	2.63 448

test123		6.12 420	8.11 423	0.14 434	0.06 458	0.09 459	71.05 409	0.03 459	0.04 453	0.25 454	1.30 453	0.05 457	0.03 454	0.21 453	0.01 452	0.29 449

testmvs		6.04 421	8.02 424	0.10 435	0.08 457	0.03 460	69.74 414	0.04 458	0.05 452	0.31 453	1.68 452	0.02 458	0.04 453	0.24 452	0.02 451	0.25 450

mmdepth		0.00 423	0.00 426	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.00 454	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

monomultidepth		0.00 423	0.00 426	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.00 454	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

test_blank		0.00 423	0.00 426	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.00 454	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

uanet_test		0.00 423	0.00 426	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.00 454	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

DCPMVS		0.00 423	0.00 426	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.00 454	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

cdsmvs_eth3d_5k		19.96 416	26.61 418	0.00 436	0.00 459	0.00 461	0.00 447	89.26 197	0.00 454	0.00 455	88.61 201	61.62 181	0.00 455	0.00 454	0.00 453	0.00 451

pcd_1.5k_mvsjas		5.26 422	7.02 425	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.00 454	63.15 157	0.00 455	0.00 454	0.00 453	0.00 451

sosnet-low-res		0.00 423	0.00 426	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.00 454	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

sosnet		0.00 423	0.00 426	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.00 454	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

uncertanet		0.00 423	0.00 426	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.00 454	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

Regformer		0.00 423	0.00 426	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.00 454	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

ab-mvs-re		7.23 419	9.64 422	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	86.72 254	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

uanet		0.00 423	0.00 426	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.00 454	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

WAC-MVS						42.58 433								39.46 421

FOURS1					95.00 10	72.39 41	95.06 1	93.84 16	74.49 134	91.30 15

test_one_0601					95.07 7	71.46 59		94.14 6	78.27 41	92.05 11	95.74 6	80.83 11

eth-test2					0.00 459

eth-test					0.00 459

ZD-MVS					94.38 25	72.22 46		92.67 68	70.98 213	87.75 44	94.07 51	74.01 33	96.70 27	84.66 63	94.84 44

test_241102_ONE					95.30 2	70.98 68		94.06 11	77.17 63	93.10 1	95.39 16	82.99 1	97.27 12

9.14			88.26 16		92.84 65		91.52 51	94.75 1	73.93 150	88.57 29	94.67 25	75.57 22	95.79 59	86.77 45	95.76 23

save fliter					93.80 40	72.35 44	90.47 69	91.17 132	74.31 139

test0726					95.27 5	71.25 61	93.60 7	94.11 7	77.33 57	92.81 3	95.79 3	80.98 9

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs												50.01 307

MTGPA								92.02 98

test_post1							78.90 359				5.43 450	48.81 326	85.44 356	59.25 314

test_post											5.46 449	50.36 304	84.24 364

patchmatchnet-post											74.00 417	51.12 295	88.60 318

MTMP							92.18 35	32.83 453

gm-plane-assit					81.40 363	53.83 382			62.72 348		80.94 371		92.39 216	63.40 275

TEST9					93.26 52	72.96 25	88.75 131	91.89 106	68.44 275	85.00 73	93.10 81	74.36 29	95.41 76

test_8					93.13 56	72.57 35	88.68 136	91.84 110	68.69 270	84.87 77	93.10 81	74.43 27	95.16 86

agg_prior					92.85 64	71.94 52		91.78 113		84.41 88			94.93 97

test_prior4						72.60 34	89.01 118

test_prior2							88.85 125		75.41 107	84.91 75	93.54 69	74.28 30		83.31 78	95.86 20

旧先验2							86.56 211		58.10 389	87.04 55			88.98 310	74.07 178

新几何2							86.29 221

原ACMM2							86.86 199

testdata2													91.01 274	62.37 285

segment_acmp												73.08 40

testdata1							84.14 278		75.71 100

plane_prior7					90.08 112	68.51 127

plane_prior6					89.84 121	68.70 121						60.42 207

plane_prior4											91.00 144

plane_prior3						68.60 124			78.44 36	78.92 170

plane_prior2							91.25 55		79.12 28

plane_prior1					89.90 120

plane_prior						68.71 119	90.38 73		77.62 47						86.16 184

n2								0.00 460

nn								0.00 460

door-mid								69.98 416

test11								92.23 88

door								69.44 419

HQP5-MVS						66.98 173

HQP-NCC					89.33 140		89.17 109		76.41 85	77.23 208

ACMP_Plane					89.33 140		89.17 109		76.41 85	77.23 208

BP-MVS														77.47 139

HQP3-MVS								92.19 92							85.99 188

HQP2-MVS												60.17 210

NP-MVS					89.62 125	68.32 131					90.24 157

MDTV_nov1_ep13			69.97 330		83.18 328	53.48 384	77.10 380	80.18 365	60.45 365	69.33 344	80.44 375	48.89 325	86.90 337	51.60 369	78.51 288

ACMMP++_ref															81.95 249

ACMMP++															81.25 254

Test By Simon												64.33 144

High-resolution multi-view benchmark