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.

fmvsm_l_conf0.5_n_3		97.64 8	97.60 9	97.79 30	98.14 102	93.94 52	97.93 75	98.65 18	96.70 3	99.38 1	99.07 7	89.92 86	99.81 30	99.16 9	99.43 48	99.61 23

fmvsm_s_conf0.5_n_2		96.62 61	96.82 46	96.02 134	97.98 115	90.43 177	97.50 137	98.59 20	96.59 5	99.31 2	99.08 4	84.47 169	99.75 48	99.37 2	98.45 121	97.88 195

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 56	98.21 95	92.75 84	97.83 89	98.73 9	95.04 36	99.30 3	98.84 29	93.34 22	99.78 40	99.32 3	99.13 86	99.50 44

test_fmvsm_n_1920		97.55 12	97.89 3	96.53 91	98.41 77	91.73 118	98.01 60	99.02 1	96.37 8	99.30 3	98.92 17	92.39 41	99.79 37	99.16 9	99.46 41	98.08 184

fmvsm_s_conf0.5_n_3		97.15 27	97.36 19	96.52 92	97.98 115	91.19 147	97.84 86	98.65 18	97.08 2	99.25 5	99.10 3	87.88 117	99.79 37	99.32 3	99.18 80	98.59 138

fmvsm_l_conf0.5_n_a		97.63 9	97.76 5	97.26 63	98.25 89	92.59 90	97.81 93	98.68 13	94.93 38	99.24 6	98.87 24	93.52 20	99.79 37	99.32 3	99.21 76	99.40 58

fmvsm_s_conf0.5_n_6		97.08 30	97.17 21	96.81 79	97.28 157	91.73 118	97.75 98	98.50 23	94.86 42	99.22 7	98.78 33	89.75 89	99.76 44	99.10 12	99.29 67	98.94 102

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 35	98.27 45	95.13 31	99.19 8	98.89 21	95.54 5	99.85 18	97.52 35	99.66 10	99.56 32

test_241102_ONE					99.42 7	95.30 17		98.27 45	95.09 34	99.19 8	98.81 30	95.54 5	99.65 68

fmvsm_s_conf0.1_n_2		96.33 73	96.44 69	96.00 138	97.30 156	90.37 180	97.53 134	97.92 116	96.52 6	99.14 10	99.08 4	83.21 191	99.74 49	99.22 6	98.06 137	97.88 195

fmvsm_s_conf0.5_n_4		96.75 53	97.07 25	95.79 147	97.76 130	89.57 202	97.66 115	98.66 16	95.36 23	99.03 11	98.90 19	88.39 107	99.73 51	99.17 8	98.66 109	98.08 184

SD-MVS		97.41 18	97.53 12	97.06 75	98.57 72	94.46 34	97.92 76	98.14 73	94.82 47	99.01 12	98.55 42	94.18 14	97.41 347	96.94 48	99.64 14	99.32 66
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
test0726					99.45 3	95.36 13	98.31 27	98.29 40	94.92 40	98.99 13	98.92 17	95.08 8

IU-MVS					99.42 7	95.39 11		97.94 113	90.40 217	98.94 14				97.41 42	99.66 10	99.74 8

fmvsm_s_conf0.1_n_a		96.40 69	96.47 63	96.16 126	95.48 270	90.69 168	97.91 77	98.33 35	94.07 77	98.93 15	99.14 1	87.44 130	99.61 79	98.63 20	98.32 126	98.18 172

DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 61	95.39 11	99.29 1	98.28 42	94.78 50	98.93 15	98.87 24	96.04 2	99.86 9	97.45 39	99.58 23	99.59 25

test_241102_TWO								98.27 45	95.13 31	98.93 15	98.89 21	94.99 11	99.85 18	97.52 35	99.65 13	99.74 8

test_fmvsmconf_n		97.49 16	97.56 10	97.29 59	97.44 153	92.37 97	97.91 77	98.88 4	95.83 12	98.92 18	99.05 9	91.45 57	99.80 34	99.12 11	99.46 41	99.69 12

fmvsm_s_conf0.5_n_a		96.75 53	96.93 37	96.20 124	97.64 139	90.72 167	98.00 61	98.73 9	94.55 61	98.91 19	99.08 4	88.22 110	99.63 77	98.91 16	98.37 124	98.25 167

fmvsm_s_conf0.5_n_5		97.00 36	96.97 34	97.09 72	97.58 149	92.56 91	97.68 111	98.47 27	94.02 79	98.90 20	98.89 21	88.94 97	99.78 40	99.18 7	99.03 95	98.93 106

PC_three_1452									90.77 196	98.89 21	98.28 75	96.24 1	98.35 240	95.76 91	99.58 23	99.59 25

SMA-MVS		97.35 20	97.03 31	98.30 8	99.06 38	95.42 10	97.94 73	98.18 66	90.57 211	98.85 22	98.94 16	93.33 23	99.83 26	96.72 55	99.68 4	99.63 19
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
fmvsm_s_conf0.1_n		96.58 64	96.77 50	96.01 137	96.67 201	90.25 182	97.91 77	98.38 29	94.48 65	98.84 23	99.14 1	88.06 112	99.62 78	98.82 18	98.60 113	98.15 176

fmvsm_s_conf0.5_n		96.85 45	97.13 22	96.04 132	98.07 109	90.28 181	97.97 69	98.76 8	94.93 38	98.84 23	99.06 8	88.80 100	99.65 68	99.06 13	98.63 111	98.18 172

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 42	97.85 126	94.92 40	98.73 25	98.87 24	95.08 8	99.84 23	97.52 35	99.67 6	99.48 48
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
test_0728_THIRD									94.78 50	98.73 25	98.87 24	95.87 4	99.84 23	97.45 39	99.72 2	99.77 2

DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 32	95.78 7	97.21 174	98.35 33	95.16 30	98.71 27	98.80 31	95.05 10	99.89 3	96.70 56	99.73 1	99.73 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + MP.		97.42 17	97.33 20	97.69 42	99.25 27	94.24 41	98.07 55	97.85 126	93.72 89	98.57 28	98.35 61	93.69 18	99.40 120	97.06 46	99.46 41	99.44 53
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MSP-MVS		97.59 11	97.54 11	97.73 38	99.40 11	93.77 57	98.53 14	98.29 40	95.55 20	98.56 29	97.81 111	93.90 15	99.65 68	96.62 57	99.21 76	99.77 2
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
FOURS1					99.55 1	93.34 67	99.29 1	98.35 33	94.98 37	98.49 30

test_one_0601					99.32 22	95.20 20		98.25 51	95.13 31	98.48 31	98.87 24	95.16 7

test_fmvsmconf0.1_n		97.09 29	97.06 26	97.19 68	95.67 262	92.21 104	97.95 72	98.27 45	95.78 16	98.40 32	99.00 11	89.99 84	99.78 40	99.06 13	99.41 54	99.59 25

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 33	94.82 28	98.81 7	98.30 38	94.76 52	98.30 33	98.90 19	93.77 17	99.68 64	97.93 23	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		97.39 19	97.13 22	98.17 15	99.02 42	95.28 19	98.23 39	98.27 45	92.37 143	98.27 34	98.65 38	93.33 23	99.72 55	96.49 62	99.52 30	99.51 41

balanced_conf03		96.84 47	96.89 39	96.68 82	97.63 141	92.22 103	98.17 48	97.82 132	94.44 67	98.23 35	97.36 143	90.97 71	99.22 137	97.74 26	99.66 10	98.61 135

SteuartSystems-ACMMP		97.62 10	97.53 12	97.87 24	98.39 80	94.25 40	98.43 22	98.27 45	95.34 25	98.11 36	98.56 40	94.53 12	99.71 56	96.57 60	99.62 17	99.65 17
Skip Steuart: Steuart Systems R&D Blog.
test_vis1_n_1920		94.17 133	94.58 114	92.91 295	97.42 154	82.02 362	97.83 89	97.85 126	94.68 55	98.10 37	98.49 47	70.15 356	99.32 127	97.91 24	98.82 102	97.40 224

test_part2					99.28 25	95.74 8				98.10 37

APD-MVS		96.95 38	96.60 56	98.01 20	99.03 41	94.93 27	97.72 105	98.10 81	91.50 169	98.01 39	98.32 69	92.33 42	99.58 87	94.85 116	99.51 33	99.53 40
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
reproduce_model		97.51 15	97.51 14	97.50 50	98.99 46	93.01 78	97.79 95	98.21 57	95.73 17	97.99 40	99.03 10	92.63 36	99.82 28	97.80 25	99.42 51	99.67 13

patch_mono-2		96.83 48	97.44 17	95.01 188	99.05 39	85.39 315	96.98 193	98.77 7	94.70 54	97.99 40	98.66 36	93.61 19	99.91 1	97.67 31	99.50 35	99.72 11

DeepPCF-MVS	93.97 1	96.61 62	97.09 24	95.15 180	98.09 105	86.63 291	96.00 271	98.15 71	95.43 21	97.95 42	98.56 40	93.40 21	99.36 124	96.77 52	99.48 39	99.45 51

ACMMP_NAP		97.20 24	96.86 40	98.23 11	99.09 34	95.16 22	97.60 125	98.19 64	92.82 134	97.93 43	98.74 35	91.60 55	99.86 9	96.26 65	99.52 30	99.67 13

reproduce-ours		97.53 13	97.51 14	97.60 47	98.97 47	93.31 69	97.71 107	98.20 59	95.80 14	97.88 44	98.98 13	92.91 27	99.81 30	97.68 27	99.43 48	99.67 13

our_new_method		97.53 13	97.51 14	97.60 47	98.97 47	93.31 69	97.71 107	98.20 59	95.80 14	97.88 44	98.98 13	92.91 27	99.81 30	97.68 27	99.43 48	99.67 13

9.14			96.75 51		98.93 50		97.73 102	98.23 56	91.28 180	97.88 44	98.44 53	93.00 26	99.65 68	95.76 91	99.47 40

CNVR-MVS		97.68 6	97.44 17	98.37 7	98.90 53	95.86 6	97.27 166	98.08 83	95.81 13	97.87 47	98.31 70	94.26 13	99.68 64	97.02 47	99.49 38	99.57 29

test_vis1_n		92.37 205	92.26 190	92.72 303	94.75 319	82.64 352	98.02 59	96.80 250	91.18 184	97.77 48	97.93 98	58.02 407	98.29 245	97.63 32	98.21 130	97.23 233

test_cas_vis1_n_1920		94.48 127	94.55 118	94.28 232	96.78 194	86.45 296	97.63 122	97.64 152	93.32 109	97.68 49	98.36 60	73.75 332	99.08 163	96.73 54	99.05 92	97.31 229

test_fmvsmconf0.01_n		96.15 77	95.85 81	97.03 76	92.66 380	91.83 117	97.97 69	97.84 130	95.57 19	97.53 50	99.00 11	84.20 175	99.76 44	98.82 18	99.08 90	99.48 48

MM		97.29 23	96.98 33	98.23 11	98.01 112	95.03 26	98.07 55	95.76 302	97.78 1	97.52 51	98.80 31	88.09 111	99.86 9	99.44 1	99.37 62	99.80 1

VNet		95.89 86	95.45 89	97.21 66	98.07 109	92.94 81	97.50 137	98.15 71	93.87 85	97.52 51	97.61 129	85.29 158	99.53 101	95.81 90	95.27 204	99.16 77

SR-MVS		97.01 35	96.86 40	97.47 52	99.09 34	93.27 71	97.98 63	98.07 88	93.75 88	97.45 53	98.48 50	91.43 59	99.59 84	96.22 68	99.27 69	99.54 37

APD-MVS_3200maxsize		96.81 49	96.71 53	97.12 70	99.01 45	92.31 100	97.98 63	98.06 91	93.11 120	97.44 54	98.55 42	90.93 72	99.55 97	96.06 78	99.25 73	99.51 41

TSAR-MVS + GP.		96.69 58	96.49 61	97.27 62	98.31 84	93.39 63	96.79 208	96.72 253	94.17 75	97.44 54	97.66 122	92.76 31	99.33 125	96.86 51	97.76 147	99.08 88

SR-MVS-dyc-post		96.88 42	96.80 48	97.11 71	99.02 42	92.34 98	97.98 63	98.03 100	93.52 101	97.43 56	98.51 45	91.40 60	99.56 95	96.05 79	99.26 71	99.43 55

RE-MVS-def			96.72 52		99.02 42	92.34 98	97.98 63	98.03 100	93.52 101	97.43 56	98.51 45	90.71 76		96.05 79	99.26 71	99.43 55

dcpmvs_2		96.37 71	97.05 29	94.31 230	98.96 49	84.11 336	97.56 129	97.51 169	93.92 83	97.43 56	98.52 44	92.75 32	99.32 127	97.32 44	99.50 35	99.51 41

MVSMamba_PlusPlus		96.51 65	96.48 62	96.59 88	98.07 109	91.97 113	98.14 49	97.79 134	90.43 215	97.34 59	97.52 136	91.29 63	99.19 140	98.12 22	99.64 14	98.60 136

旧先验2							95.94 274		81.66 387	97.34 59			98.82 190	92.26 167

MSLP-MVS++		96.94 39	97.06 26	96.59 88	98.72 58	91.86 116	97.67 112	98.49 24	94.66 57	97.24 61	98.41 56	92.31 44	98.94 179	96.61 58	99.46 41	98.96 99

HFP-MVS		97.14 28	96.92 38	97.83 26	99.42 7	94.12 46	98.52 15	98.32 36	93.21 111	97.18 62	98.29 73	92.08 46	99.83 26	95.63 98	99.59 19	99.54 37

MVS_0304		96.74 55	96.31 71	98.02 19	96.87 183	94.65 30	97.58 126	94.39 364	96.47 7	97.16 63	98.39 57	87.53 126	99.87 7	98.97 15	99.41 54	99.55 35

ACMMPR		97.07 32	96.84 42	97.79 30	99.44 6	93.88 53	98.52 15	98.31 37	93.21 111	97.15 64	98.33 67	91.35 61	99.86 9	95.63 98	99.59 19	99.62 20

region2R		97.07 32	96.84 42	97.77 34	99.46 2	93.79 55	98.52 15	98.24 53	93.19 114	97.14 65	98.34 64	91.59 56	99.87 7	95.46 104	99.59 19	99.64 18

PGM-MVS		96.81 49	96.53 59	97.65 43	99.35 20	93.53 61	97.65 116	98.98 2	92.22 146	97.14 65	98.44 53	91.17 67	99.85 18	94.35 131	99.46 41	99.57 29

PHI-MVS		96.77 51	96.46 66	97.71 41	98.40 78	94.07 48	98.21 42	98.45 28	89.86 228	97.11 67	98.01 93	92.52 39	99.69 62	96.03 82	99.53 29	99.36 64

NCCC		97.30 22	97.03 31	98.11 17	98.77 56	95.06 25	97.34 159	98.04 98	95.96 10	97.09 68	97.88 102	93.18 25	99.71 56	95.84 89	99.17 81	99.56 32

CS-MVS		96.86 43	97.06 26	96.26 119	98.16 101	91.16 152	99.09 3	97.87 121	95.30 26	97.06 69	98.03 90	91.72 50	98.71 207	97.10 45	99.17 81	98.90 111

ZD-MVS					99.05 39	94.59 32		98.08 83	89.22 249	97.03 70	98.10 83	92.52 39	99.65 68	94.58 128	99.31 66

testdata				95.46 172	98.18 100	88.90 231		97.66 148	82.73 379	97.03 70	98.07 86	90.06 82	98.85 188	89.67 223	98.98 97	98.64 134

SPE-MVS-test		96.89 41	97.04 30	96.45 103	98.29 85	91.66 125	99.03 4	97.85 126	95.84 11	96.90 72	97.97 96	91.24 64	98.75 200	96.92 49	99.33 64	98.94 102

mvsany_test1		93.93 147	93.98 130	93.78 260	94.94 309	86.80 284	94.62 330	92.55 395	88.77 270	96.85 73	98.49 47	88.98 95	98.08 267	95.03 112	95.62 198	96.46 254

GDP-MVS		95.62 93	95.13 101	97.09 72	96.79 193	93.26 72	97.89 80	97.83 131	93.58 93	96.80 74	97.82 110	83.06 198	99.16 147	94.40 130	97.95 141	98.87 117

test_fmvs1		93.21 170	93.53 142	92.25 317	96.55 212	81.20 369	97.40 153	96.96 233	90.68 201	96.80 74	98.04 89	69.25 364	98.40 232	97.58 34	98.50 116	97.16 234

test_fmvs1_n		92.73 195	92.88 164	92.29 314	96.08 248	81.05 370	97.98 63	97.08 219	90.72 199	96.79 76	98.18 80	63.07 398	98.45 229	97.62 33	98.42 123	97.36 225

HPM-MVS_fast		96.51 65	96.27 73	97.22 65	99.32 22	92.74 85	98.74 9	98.06 91	90.57 211	96.77 77	98.35 61	90.21 81	99.53 101	94.80 121	99.63 16	99.38 62

h-mvs33		94.15 135	93.52 144	96.04 132	97.81 127	90.22 183	97.62 124	97.58 160	95.19 28	96.74 78	97.45 137	83.67 183	99.61 79	95.85 87	79.73 387	98.29 166

hse-mvs2		93.45 163	92.99 159	94.81 201	97.02 176	88.59 237	96.69 219	96.47 271	95.19 28	96.74 78	96.16 211	83.67 183	98.48 228	95.85 87	79.13 391	97.35 227

GST-MVS		96.85 45	96.52 60	97.82 27	99.36 18	94.14 45	98.29 29	98.13 74	92.72 136	96.70 80	98.06 87	91.35 61	99.86 9	94.83 118	99.28 68	99.47 50

xiu_mvs_v1_base_debu		95.01 109	94.76 108	95.75 150	96.58 207	91.71 121	96.25 257	97.35 200	92.99 123	96.70 80	96.63 186	82.67 207	99.44 116	96.22 68	97.46 151	96.11 266

xiu_mvs_v1_base		95.01 109	94.76 108	95.75 150	96.58 207	91.71 121	96.25 257	97.35 200	92.99 123	96.70 80	96.63 186	82.67 207	99.44 116	96.22 68	97.46 151	96.11 266

xiu_mvs_v1_base_debi		95.01 109	94.76 108	95.75 150	96.58 207	91.71 121	96.25 257	97.35 200	92.99 123	96.70 80	96.63 186	82.67 207	99.44 116	96.22 68	97.46 151	96.11 266

CDPH-MVS		95.97 83	95.38 94	97.77 34	98.93 50	94.44 35	96.35 249	97.88 119	86.98 319	96.65 84	97.89 100	91.99 48	99.47 112	92.26 167	99.46 41	99.39 60

EC-MVSNet		96.42 68	96.47 63	96.26 119	97.01 177	91.52 131	98.89 5	97.75 137	94.42 68	96.64 85	97.68 119	89.32 91	98.60 217	97.45 39	99.11 89	98.67 133

UA-Net		95.95 84	95.53 85	97.20 67	97.67 135	92.98 80	97.65 116	98.13 74	94.81 48	96.61 86	98.35 61	88.87 98	99.51 106	90.36 209	97.35 158	99.11 85

HPM-MVS++		97.34 21	96.97 34	98.47 5	99.08 36	96.16 4	97.55 133	97.97 110	95.59 18	96.61 86	97.89 100	92.57 38	99.84 23	95.95 84	99.51 33	99.40 58

XVS		97.18 25	96.96 36	97.81 28	99.38 14	94.03 50	98.59 12	98.20 59	94.85 43	96.59 88	98.29 73	91.70 52	99.80 34	95.66 93	99.40 56	99.62 20

X-MVStestdata		91.71 231	89.67 296	97.81 28	99.38 14	94.03 50	98.59 12	98.20 59	94.85 43	96.59 88	32.69 431	91.70 52	99.80 34	95.66 93	99.40 56	99.62 20

DeepC-MVS_fast	93.89 2	96.93 40	96.64 55	97.78 32	98.64 67	94.30 37	97.41 149	98.04 98	94.81 48	96.59 88	98.37 59	91.24 64	99.64 76	95.16 109	99.52 30	99.42 57
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PS-MVSNAJ		95.37 99	95.33 96	95.49 168	97.35 155	90.66 170	95.31 309	97.48 173	93.85 86	96.51 91	95.70 238	88.65 103	99.65 68	94.80 121	98.27 128	96.17 260

EI-MVSNet-Vis-set		96.51 65	96.47 63	96.63 85	98.24 90	91.20 146	96.89 199	97.73 140	94.74 53	96.49 92	98.49 47	90.88 74	99.58 87	96.44 63	98.32 126	99.13 81

ETV-MVS		96.02 80	95.89 80	96.40 106	97.16 163	92.44 95	97.47 144	97.77 136	94.55 61	96.48 93	94.51 294	91.23 66	98.92 181	95.65 96	98.19 131	97.82 203

alignmvs		95.87 88	95.23 98	97.78 32	97.56 151	95.19 21	97.86 82	97.17 211	94.39 71	96.47 94	96.40 199	85.89 151	99.20 139	96.21 72	95.11 209	98.95 101

xiu_mvs_v2_base		95.32 101	95.29 97	95.40 173	97.22 159	90.50 173	95.44 302	97.44 187	93.70 91	96.46 95	96.18 208	88.59 106	99.53 101	94.79 123	97.81 144	96.17 260

CP-MVS		97.02 34	96.81 47	97.64 45	99.33 21	93.54 60	98.80 8	98.28 42	92.99 123	96.45 96	98.30 72	91.90 49	99.85 18	95.61 100	99.68 4	99.54 37

HPM-MVS		96.69 58	96.45 67	97.40 54	99.36 18	93.11 76	98.87 6	98.06 91	91.17 185	96.40 97	97.99 94	90.99 70	99.58 87	95.61 100	99.61 18	99.49 46
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ZNCC-MVS		96.96 37	96.67 54	97.85 25	99.37 16	94.12 46	98.49 19	98.18 66	92.64 139	96.39 98	98.18 80	91.61 54	99.88 4	95.59 103	99.55 26	99.57 29

BP-MVS1		95.89 86	95.49 86	97.08 74	96.67 201	93.20 73	98.08 53	96.32 277	94.56 60	96.32 99	97.84 108	84.07 178	99.15 149	96.75 53	98.78 104	98.90 111

diffmvs		95.25 103	95.13 101	95.63 158	96.43 226	89.34 215	95.99 272	97.35 200	92.83 133	96.31 100	97.37 142	86.44 143	98.67 210	96.26 65	97.19 166	98.87 117
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LFMVS		93.60 157	92.63 175	96.52 92	98.13 104	91.27 141	97.94 73	93.39 384	90.57 211	96.29 101	98.31 70	69.00 366	99.16 147	94.18 133	95.87 190	99.12 84

sasdasda		96.02 80	95.45 89	97.75 36	97.59 145	95.15 23	98.28 30	97.60 156	94.52 63	96.27 102	96.12 213	87.65 121	99.18 143	96.20 73	94.82 213	98.91 108

canonicalmvs		96.02 80	95.45 89	97.75 36	97.59 145	95.15 23	98.28 30	97.60 156	94.52 63	96.27 102	96.12 213	87.65 121	99.18 143	96.20 73	94.82 213	98.91 108

MVSFormer		95.37 99	95.16 100	95.99 139	96.34 231	91.21 144	98.22 40	97.57 161	91.42 173	96.22 104	97.32 144	86.20 148	97.92 298	94.07 134	99.05 92	98.85 119

lupinMVS		94.99 113	94.56 115	96.29 117	96.34 231	91.21 144	95.83 280	96.27 281	88.93 261	96.22 104	96.88 169	86.20 148	98.85 188	95.27 106	99.05 92	98.82 123

MGCFI-Net		95.94 85	95.40 93	97.56 49	97.59 145	94.62 31	98.21 42	97.57 161	94.41 69	96.17 106	96.16 211	87.54 125	99.17 145	96.19 75	94.73 218	98.91 108

EI-MVSNet-UG-set		96.34 72	96.30 72	96.47 100	98.20 96	90.93 159	96.86 201	97.72 142	94.67 56	96.16 107	98.46 51	90.43 79	99.58 87	96.23 67	97.96 140	98.90 111

MTAPA		97.08 30	96.78 49	97.97 23	99.37 16	94.42 36	97.24 168	98.08 83	95.07 35	96.11 108	98.59 39	90.88 74	99.90 2	96.18 77	99.50 35	99.58 28

test_fmvsmvis_n_1920		96.70 56	96.84 42	96.31 113	96.62 203	91.73 118	97.98 63	98.30 38	96.19 9	96.10 109	98.95 15	89.42 90	99.76 44	98.90 17	99.08 90	97.43 222

MCST-MVS		97.18 25	96.84 42	98.20 14	99.30 24	95.35 15	97.12 181	98.07 88	93.54 98	96.08 110	97.69 118	93.86 16	99.71 56	96.50 61	99.39 58	99.55 35

TEST9					98.70 59	94.19 42	96.41 241	98.02 103	88.17 286	96.03 111	97.56 133	92.74 33	99.59 84

train_agg		96.30 74	95.83 82	97.72 39	98.70 59	94.19 42	96.41 241	98.02 103	88.58 273	96.03 111	97.56 133	92.73 34	99.59 84	95.04 111	99.37 62	99.39 60

test_prior2							96.35 249		92.80 135	96.03 111	97.59 130	92.01 47		95.01 113	99.38 59

jason		94.84 118	94.39 124	96.18 125	95.52 268	90.93 159	96.09 266	96.52 268	89.28 247	96.01 114	97.32 144	84.70 165	98.77 198	95.15 110	98.91 101	98.85 119
jason: jason.
test_8					98.67 61	94.06 49	96.37 248	98.01 106	88.58 273	95.98 115	97.55 135	92.73 34	99.58 87

mPP-MVS		96.86 43	96.60 56	97.64 45	99.40 11	93.44 62	98.50 18	98.09 82	93.27 110	95.95 116	98.33 67	91.04 69	99.88 4	95.20 107	99.57 25	99.60 24

DELS-MVS		96.61 62	96.38 70	97.30 58	97.79 128	93.19 74	95.96 273	98.18 66	95.23 27	95.87 117	97.65 123	91.45 57	99.70 61	95.87 85	99.44 47	99.00 97
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
VDD-MVS		93.82 151	93.08 157	96.02 134	97.88 124	89.96 192	97.72 105	95.85 298	92.43 141	95.86 118	98.44 53	68.42 373	99.39 121	96.31 64	94.85 211	98.71 130

MVS_111021_HR		96.68 60	96.58 58	96.99 77	98.46 73	92.31 100	96.20 262	98.90 3	94.30 74	95.86 118	97.74 116	92.33 42	99.38 123	96.04 81	99.42 51	99.28 69

MVS_111021_LR		96.24 76	96.19 75	96.39 108	98.23 94	91.35 139	96.24 260	98.79 6	93.99 81	95.80 120	97.65 123	89.92 86	99.24 135	95.87 85	99.20 78	98.58 139

VDDNet		93.05 179	92.07 193	96.02 134	96.84 186	90.39 179	98.08 53	95.85 298	86.22 334	95.79 121	98.46 51	67.59 376	99.19 140	94.92 115	94.85 211	98.47 151

新几何1				97.32 57	98.60 68	93.59 59		97.75 137	81.58 388	95.75 122	97.85 106	90.04 83	99.67 66	86.50 291	99.13 86	98.69 131

test_yl		94.78 120	94.23 126	96.43 104	97.74 131	91.22 142	96.85 202	97.10 216	91.23 182	95.71 123	96.93 164	84.30 172	99.31 129	93.10 155	95.12 207	98.75 125

DCV-MVSNet		94.78 120	94.23 126	96.43 104	97.74 131	91.22 142	96.85 202	97.10 216	91.23 182	95.71 123	96.93 164	84.30 172	99.31 129	93.10 155	95.12 207	98.75 125

agg_prior					98.67 61	93.79 55		98.00 107		95.68 125			99.57 94

MG-MVS		95.61 94	95.38 94	96.31 113	98.42 76	90.53 172	96.04 268	97.48 173	93.47 103	95.67 126	98.10 83	89.17 93	99.25 134	91.27 194	98.77 105	99.13 81

baseline		95.58 95	95.42 92	96.08 128	96.78 194	90.41 178	97.16 178	97.45 183	93.69 92	95.65 127	97.85 106	87.29 133	98.68 209	95.66 93	97.25 164	99.13 81

MVS_Test		94.89 116	94.62 112	95.68 156	96.83 188	89.55 204	96.70 217	97.17 211	91.17 185	95.60 128	96.11 217	87.87 118	98.76 199	93.01 162	97.17 167	98.72 128

DPM-MVS		95.69 90	94.92 105	98.01 20	98.08 108	95.71 9	95.27 312	97.62 155	90.43 215	95.55 129	97.07 159	91.72 50	99.50 109	89.62 225	98.94 99	98.82 123

MP-MVS-pluss		96.70 56	96.27 73	97.98 22	99.23 30	94.71 29	96.96 195	98.06 91	90.67 202	95.55 129	98.78 33	91.07 68	99.86 9	96.58 59	99.55 26	99.38 62
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MP-MVS		96.77 51	96.45 67	97.72 39	99.39 13	93.80 54	98.41 23	98.06 91	93.37 106	95.54 131	98.34 64	90.59 78	99.88 4	94.83 118	99.54 28	99.49 46
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test12				97.65 43	98.46 73	94.26 39		97.66 148		95.52 132		90.89 73	99.46 113		99.25 73	99.22 74

casdiffmvs		95.64 92	95.49 86	96.08 128	96.76 199	90.45 175	97.29 165	97.44 187	94.00 80	95.46 133	97.98 95	87.52 128	98.73 203	95.64 97	97.33 159	99.08 88
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test222					98.24 90	92.21 104	95.33 307	97.60 156	79.22 401	95.25 134	97.84 108	88.80 100			99.15 84	98.72 128

test2506		91.60 237	90.78 245	94.04 242	97.66 137	83.81 339	98.27 32	75.53 432	93.43 104	95.23 135	98.21 77	67.21 379	99.07 167	93.01 162	98.49 117	99.25 72

原ACMM1				96.38 109	98.59 69	91.09 154		97.89 117	87.41 311	95.22 136	97.68 119	90.25 80	99.54 99	87.95 259	99.12 88	98.49 148

CPTT-MVS		95.57 96	95.19 99	96.70 81	99.27 26	91.48 133	98.33 26	98.11 79	87.79 300	95.17 137	98.03 90	87.09 136	99.61 79	93.51 146	99.42 51	99.02 91

casdiffmvs_mvg		95.81 89	95.57 84	96.51 96	96.87 183	91.49 132	97.50 137	97.56 165	93.99 81	95.13 138	97.92 99	87.89 116	98.78 195	95.97 83	97.33 159	99.26 71
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DP-MVS Recon		95.68 91	95.12 103	97.37 55	99.19 31	94.19 42	97.03 185	98.08 83	88.35 282	95.09 139	97.65 123	89.97 85	99.48 111	92.08 176	98.59 114	98.44 156

RRT-MVS		94.51 125	94.35 125	94.98 191	96.40 227	86.55 294	97.56 129	97.41 192	93.19 114	94.93 140	97.04 161	79.12 272	99.30 131	96.19 75	97.32 161	99.09 87

Vis-MVSNet		95.23 104	94.81 107	96.51 96	97.18 162	91.58 129	98.26 34	98.12 76	94.38 72	94.90 141	98.15 82	82.28 217	98.92 181	91.45 191	98.58 115	99.01 94
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CANet		96.39 70	96.02 77	97.50 50	97.62 142	93.38 64	97.02 187	97.96 111	95.42 22	94.86 142	97.81 111	87.38 132	99.82 28	96.88 50	99.20 78	99.29 67

API-MVS		94.84 118	94.49 120	95.90 141	97.90 123	92.00 112	97.80 94	97.48 173	89.19 250	94.81 143	96.71 175	88.84 99	99.17 145	88.91 245	98.76 106	96.53 249

mvsmamba		94.57 124	94.14 128	95.87 142	97.03 175	89.93 193	97.84 86	95.85 298	91.34 176	94.79 144	96.80 171	80.67 243	98.81 192	94.85 116	98.12 135	98.85 119

OMC-MVS		95.09 108	94.70 111	96.25 122	98.46 73	91.28 140	96.43 239	97.57 161	92.04 155	94.77 145	97.96 97	87.01 137	99.09 160	91.31 193	96.77 173	98.36 163

ECVR-MVS		93.19 172	92.73 172	94.57 216	97.66 137	85.41 313	98.21 42	88.23 416	93.43 104	94.70 146	98.21 77	72.57 336	99.07 167	93.05 159	98.49 117	99.25 72

WTY-MVS		94.71 122	94.02 129	96.79 80	97.71 133	92.05 110	96.59 232	97.35 200	90.61 208	94.64 147	96.93 164	86.41 144	99.39 121	91.20 196	94.71 219	98.94 102

test1111		93.19 172	92.82 166	94.30 231	97.58 149	84.56 330	98.21 42	89.02 414	93.53 99	94.58 148	98.21 77	72.69 335	99.05 170	93.06 158	98.48 119	99.28 69

ACMMP		96.27 75	95.93 78	97.28 61	99.24 28	92.62 88	98.25 35	98.81 5	92.99 123	94.56 149	98.39 57	88.96 96	99.85 18	94.57 129	97.63 148	99.36 64
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
mamv4		94.66 123	96.10 76	90.37 362	98.01 112	73.41 411	96.82 206	97.78 135	89.95 226	94.52 150	97.43 140	92.91 27	99.09 160	98.28 21	99.16 83	98.60 136

Effi-MVS+		94.93 114	94.45 122	96.36 111	96.61 204	91.47 134	96.41 241	97.41 192	91.02 191	94.50 151	95.92 222	87.53 126	98.78 195	93.89 140	96.81 172	98.84 122

sss		94.51 125	93.80 133	96.64 83	97.07 168	91.97 113	96.32 252	98.06 91	88.94 260	94.50 151	96.78 172	84.60 166	99.27 133	91.90 177	96.02 186	98.68 132

mmtdpeth		89.70 315	88.96 313	91.90 325	95.84 257	84.42 331	97.46 146	95.53 318	90.27 218	94.46 153	90.50 388	69.74 362	98.95 177	97.39 43	69.48 413	92.34 390

PVSNet_BlendedMVS		94.06 141	93.92 131	94.47 219	98.27 86	89.46 210	96.73 213	98.36 30	90.17 220	94.36 154	95.24 261	88.02 113	99.58 87	93.44 148	90.72 287	94.36 358

PVSNet_Blended		94.87 117	94.56 115	95.81 146	98.27 86	89.46 210	95.47 301	98.36 30	88.84 264	94.36 154	96.09 218	88.02 113	99.58 87	93.44 148	98.18 132	98.40 159

PMMVS		92.86 189	92.34 187	94.42 223	94.92 310	86.73 287	94.53 334	96.38 275	84.78 357	94.27 156	95.12 266	83.13 195	98.40 232	91.47 190	96.49 181	98.12 179

EPP-MVSNet		95.22 105	95.04 104	95.76 148	97.49 152	89.56 203	98.67 10	97.00 231	90.69 200	94.24 157	97.62 128	89.79 88	98.81 192	93.39 151	96.49 181	98.92 107

FA-MVS(test-final)		93.52 161	92.92 162	95.31 175	96.77 196	88.54 240	94.82 326	96.21 286	89.61 236	94.20 158	95.25 260	83.24 190	99.14 152	90.01 213	96.16 185	98.25 167

PVSNet_Blended_VisFu		95.27 102	94.91 106	96.38 109	98.20 96	90.86 161	97.27 166	98.25 51	90.21 219	94.18 159	97.27 148	87.48 129	99.73 51	93.53 145	97.77 146	98.55 140

FE-MVS		92.05 221	91.05 233	95.08 184	96.83 188	87.93 258	93.91 361	95.70 305	86.30 331	94.15 160	94.97 268	76.59 305	99.21 138	84.10 325	96.86 170	98.09 183

thisisatest0530		93.03 180	92.21 191	95.49 168	97.07 168	89.11 227	97.49 143	92.19 397	90.16 221	94.09 161	96.41 198	76.43 309	99.05 170	90.38 208	95.68 196	98.31 165

XVG-OURS-SEG-HR		93.86 150	93.55 140	94.81 201	97.06 171	88.53 241	95.28 310	97.45 183	91.68 165	94.08 162	97.68 119	82.41 215	98.90 184	93.84 142	92.47 256	96.98 237

XVG-OURS		93.72 155	93.35 152	94.80 204	97.07 168	88.61 236	94.79 327	97.46 178	91.97 158	93.99 163	97.86 105	81.74 228	98.88 185	92.64 166	92.67 255	96.92 241

IS-MVSNet		94.90 115	94.52 119	96.05 131	97.67 135	90.56 171	98.44 21	96.22 284	93.21 111	93.99 163	97.74 116	85.55 156	98.45 229	89.98 214	97.86 142	99.14 80

CSCG		96.05 79	95.91 79	96.46 102	99.24 28	90.47 174	98.30 28	98.57 22	89.01 256	93.97 165	97.57 131	92.62 37	99.76 44	94.66 124	99.27 69	99.15 79

EIA-MVS		95.53 97	95.47 88	95.71 155	97.06 171	89.63 198	97.82 91	97.87 121	93.57 94	93.92 166	95.04 267	90.61 77	98.95 177	94.62 126	98.68 108	98.54 141

tttt0517		92.96 183	92.33 188	94.87 198	97.11 166	87.16 278	97.97 69	92.09 398	90.63 206	93.88 167	97.01 163	76.50 306	99.06 169	90.29 211	95.45 201	98.38 161

HyFIR lowres test		93.66 156	92.92 162	95.87 142	98.24 90	89.88 194	94.58 332	98.49 24	85.06 352	93.78 168	95.78 233	82.86 203	98.67 210	91.77 182	95.71 195	99.07 90

CHOSEN 1792x2688		94.15 135	93.51 145	96.06 130	98.27 86	89.38 213	95.18 318	98.48 26	85.60 342	93.76 169	97.11 157	83.15 194	99.61 79	91.33 192	98.72 107	99.19 75

Anonymous202405211		92.07 220	90.83 244	95.76 148	98.19 98	88.75 233	97.58 126	95.00 340	86.00 337	93.64 170	97.45 137	66.24 388	99.53 101	90.68 205	92.71 253	99.01 94

CDS-MVSNet		94.14 138	93.54 141	95.93 140	96.18 238	91.46 135	96.33 251	97.04 226	88.97 259	93.56 171	96.51 193	87.55 124	97.89 302	89.80 219	95.95 188	98.44 156
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MDTV_nov1_ep13_2view						70.35 415	93.10 382		83.88 367	93.55 172		82.47 214		86.25 294		98.38 161

Anonymous20240529		91.98 223	90.73 250	95.73 153	98.14 102	89.40 212	97.99 62	97.72 142	79.63 399	93.54 173	97.41 141	69.94 358	99.56 95	91.04 199	91.11 280	98.22 169

CANet_DTU		94.37 128	93.65 137	96.55 90	96.46 224	92.13 108	96.21 261	96.67 260	94.38 72	93.53 174	97.03 162	79.34 268	99.71 56	90.76 202	98.45 121	97.82 203

tpmrst		91.44 249	91.32 221	91.79 331	95.15 298	79.20 395	93.42 375	95.37 322	88.55 276	93.49 175	93.67 340	82.49 213	98.27 246	90.41 207	89.34 301	97.90 193

TAMVS		94.01 144	93.46 147	95.64 157	96.16 240	90.45 175	96.71 216	96.89 243	89.27 248	93.46 176	96.92 167	87.29 133	97.94 295	88.70 250	95.74 193	98.53 142

thisisatest0515		92.29 210	91.30 223	95.25 177	96.60 205	88.90 231	94.36 343	92.32 396	87.92 293	93.43 177	94.57 290	77.28 301	99.00 174	89.42 230	95.86 191	97.86 199

DeepC-MVS	93.07 3	96.06 78	95.66 83	97.29 59	97.96 117	93.17 75	97.30 164	98.06 91	93.92 83	93.38 178	98.66 36	86.83 138	99.73 51	95.60 102	99.22 75	98.96 99
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
thres600view7		92.49 200	91.60 211	95.18 179	97.91 122	89.47 208	97.65 116	94.66 354	92.18 152	93.33 179	94.91 272	78.06 294	99.10 157	81.61 348	94.06 236	96.98 237

thres100view900		92.43 201	91.58 212	94.98 191	97.92 121	89.37 214	97.71 107	94.66 354	92.20 148	93.31 180	94.90 273	78.06 294	99.08 163	81.40 351	94.08 232	96.48 252

thres200		92.23 214	91.39 218	94.75 208	97.61 143	89.03 228	96.60 231	95.09 337	92.08 154	93.28 181	94.00 326	78.39 288	99.04 173	81.26 357	94.18 228	96.19 259

tfpn200view9		92.38 204	91.52 215	94.95 195	97.85 125	89.29 218	97.41 149	94.88 348	92.19 150	93.27 182	94.46 299	78.17 290	99.08 163	81.40 351	94.08 232	96.48 252

thres400		92.42 202	91.52 215	95.12 183	97.85 125	89.29 218	97.41 149	94.88 348	92.19 150	93.27 182	94.46 299	78.17 290	99.08 163	81.40 351	94.08 232	96.98 237

testing3-2		92.10 219	92.05 194	92.27 315	97.71 133	79.56 389	97.42 148	94.41 363	93.53 99	93.22 184	95.49 249	69.16 365	99.11 155	93.25 152	94.22 226	98.13 177

ab-mvs		93.57 159	92.55 179	96.64 83	97.28 157	91.96 115	95.40 303	97.45 183	89.81 232	93.22 184	96.28 204	79.62 265	99.46 113	90.74 203	93.11 247	98.50 146

Vis-MVSNet (Re-imp)		94.15 135	93.88 132	94.95 195	97.61 143	87.92 259	98.10 51	95.80 301	92.22 146	93.02 186	97.45 137	84.53 168	97.91 301	88.24 254	97.97 139	99.02 91

114514_t		93.95 145	93.06 158	96.63 85	99.07 37	91.61 126	97.46 146	97.96 111	77.99 405	93.00 187	97.57 131	86.14 150	99.33 125	89.22 237	99.15 84	98.94 102

UGNet		94.04 143	93.28 154	96.31 113	96.85 185	91.19 147	97.88 81	97.68 147	94.40 70	93.00 187	96.18 208	73.39 334	99.61 79	91.72 183	98.46 120	98.13 177
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
HY-MVS	89.66 9	93.87 149	92.95 161	96.63 85	97.10 167	92.49 94	95.64 293	96.64 261	89.05 255	93.00 187	95.79 232	85.77 154	99.45 115	89.16 241	94.35 221	97.96 190

PVSNet	86.66 18	92.24 213	91.74 208	93.73 261	97.77 129	83.69 343	92.88 385	96.72 253	87.91 294	93.00 187	94.86 275	78.51 285	99.05 170	86.53 289	97.45 155	98.47 151

MAR-MVS		94.22 131	93.46 147	96.51 96	98.00 114	92.19 107	97.67 112	97.47 176	88.13 290	93.00 187	95.84 226	84.86 164	99.51 106	87.99 258	98.17 133	97.83 202
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
PAPM_NR		95.01 109	94.59 113	96.26 119	98.89 54	90.68 169	97.24 168	97.73 140	91.80 160	92.93 192	96.62 189	89.13 94	99.14 152	89.21 238	97.78 145	98.97 98

MDTV_nov1_ep13			90.76 246		95.22 292	80.33 379	93.03 383	95.28 327	88.14 289	92.84 193	93.83 330	81.34 232	98.08 267	82.86 337	94.34 222

CostFormer		91.18 267	90.70 252	92.62 307	94.84 315	81.76 364	94.09 354	94.43 361	84.15 363	92.72 194	93.77 334	79.43 267	98.20 251	90.70 204	92.18 262	97.90 193

EPNet		95.20 106	94.56 115	97.14 69	92.80 377	92.68 87	97.85 85	94.87 351	96.64 4	92.46 195	97.80 113	86.23 145	99.65 68	93.72 144	98.62 112	99.10 86
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		90.82 280	89.77 292	93.95 249	94.45 332	87.19 276	90.23 406	95.68 309	86.89 321	92.40 196	92.36 371	80.91 239	97.05 359	81.09 358	93.95 237	97.60 215

RPMNet		88.98 321	87.05 335	94.77 206	94.45 332	87.19 276	90.23 406	98.03 100	77.87 407	92.40 196	87.55 411	80.17 254	99.51 106	68.84 411	93.95 237	97.60 215

EPMVS		90.70 285	89.81 290	93.37 278	94.73 321	84.21 334	93.67 369	88.02 417	89.50 240	92.38 198	93.49 346	77.82 298	97.78 313	86.03 301	92.68 254	98.11 182

baseline1		92.82 192	91.90 201	95.55 164	97.20 161	90.77 165	97.19 175	94.58 357	92.20 148	92.36 199	96.34 202	84.16 176	98.21 250	89.20 239	83.90 367	97.68 209

PatchT		88.87 325	87.42 329	93.22 284	94.08 343	85.10 321	89.51 411	94.64 356	81.92 384	92.36 199	88.15 407	80.05 256	97.01 362	72.43 402	93.65 242	97.54 218

UWE-MVS		89.91 306	89.48 302	91.21 344	95.88 251	78.23 400	94.91 325	90.26 410	89.11 252	92.35 201	94.52 293	68.76 368	97.96 290	83.95 329	95.59 199	97.42 223

ETVMVS		90.52 291	89.14 311	94.67 210	96.81 192	87.85 263	95.91 276	93.97 375	89.71 234	92.34 202	92.48 366	65.41 393	97.96 290	81.37 354	94.27 225	98.21 170

PAPR		94.18 132	93.42 151	96.48 99	97.64 139	91.42 137	95.55 296	97.71 146	88.99 257	92.34 202	95.82 228	89.19 92	99.11 155	86.14 297	97.38 156	98.90 111

SCA		91.84 228	91.18 230	93.83 256	95.59 264	84.95 326	94.72 328	95.58 314	90.82 194	92.25 204	93.69 337	75.80 313	98.10 262	86.20 295	95.98 187	98.45 153

CVMVSNet		91.23 262	91.75 206	89.67 370	95.77 258	74.69 406	96.44 237	94.88 348	85.81 339	92.18 205	97.64 126	79.07 273	95.58 389	88.06 257	95.86 191	98.74 127

AUN-MVS		91.76 230	90.75 248	94.81 201	97.00 178	88.57 238	96.65 223	96.49 270	89.63 235	92.15 206	96.12 213	78.66 283	98.50 225	90.83 200	79.18 390	97.36 225

AdaColmap		94.34 129	93.68 136	96.31 113	98.59 69	91.68 124	96.59 232	97.81 133	89.87 227	92.15 206	97.06 160	83.62 185	99.54 99	89.34 232	98.07 136	97.70 208

GeoE		93.89 148	93.28 154	95.72 154	96.96 180	89.75 197	98.24 38	96.92 240	89.47 241	92.12 208	97.21 152	84.42 170	98.39 237	87.71 265	96.50 180	99.01 94

PatchmatchNet		91.91 225	91.35 219	93.59 269	95.38 276	84.11 336	93.15 380	95.39 320	89.54 238	92.10 209	93.68 339	82.82 205	98.13 257	84.81 317	95.32 203	98.52 143
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VPA-MVSNet		93.24 169	92.48 184	95.51 166	95.70 260	92.39 96	97.86 82	98.66 16	92.30 144	92.09 210	95.37 253	80.49 247	98.40 232	93.95 137	85.86 334	95.75 283

tpm		90.25 298	89.74 295	91.76 334	93.92 346	79.73 388	93.98 355	93.54 382	88.28 283	91.99 211	93.25 354	77.51 300	97.44 344	87.30 279	87.94 313	98.12 179

myMVS_eth3d28		91.52 245	90.97 236	93.17 286	96.91 181	83.24 347	95.61 294	94.96 344	92.24 145	91.98 212	93.28 353	69.31 363	98.40 232	88.71 249	95.68 196	97.88 195

UBG		91.55 242	90.76 246	93.94 251	96.52 217	85.06 322	95.22 315	94.54 358	90.47 214	91.98 212	92.71 360	72.02 339	98.74 202	88.10 256	95.26 205	98.01 188

CNLPA		94.28 130	93.53 142	96.52 92	98.38 81	92.55 92	96.59 232	96.88 244	90.13 223	91.91 214	97.24 150	85.21 159	99.09 160	87.64 271	97.83 143	97.92 192

testing91		91.90 226	91.02 234	94.53 218	96.54 213	86.55 294	95.86 278	95.64 311	91.77 162	91.89 215	93.47 348	69.94 358	98.86 186	90.23 212	93.86 239	98.18 172

BH-RMVSNet		92.72 196	91.97 199	94.97 193	97.16 163	87.99 257	96.15 264	95.60 312	90.62 207	91.87 216	97.15 156	78.41 287	98.57 221	83.16 334	97.60 149	98.36 163

PatchMatch-RL		92.90 187	92.02 197	95.56 162	98.19 98	90.80 163	95.27 312	97.18 209	87.96 292	91.86 217	95.68 239	80.44 248	98.99 175	84.01 327	97.54 150	96.89 242

SDMVSNet		94.17 133	93.61 138	95.86 144	98.09 105	91.37 138	97.35 158	98.20 59	93.18 116	91.79 218	97.28 146	79.13 271	98.93 180	94.61 127	92.84 250	97.28 230

sd_testset		93.10 176	92.45 185	95.05 185	98.09 105	89.21 222	96.89 199	97.64 152	93.18 116	91.79 218	97.28 146	75.35 318	98.65 212	88.99 243	92.84 250	97.28 230

testing99		91.62 236	90.72 251	94.32 228	96.48 221	86.11 305	95.81 281	94.76 352	91.55 167	91.75 220	93.44 349	68.55 371	98.82 190	90.43 206	93.69 240	98.04 187

testing222		90.31 295	88.96 313	94.35 225	96.54 213	87.29 270	95.50 299	93.84 379	90.97 192	91.75 220	92.96 357	62.18 403	98.00 281	82.86 337	94.08 232	97.76 205

OPM-MVS		93.28 168	92.76 168	94.82 199	94.63 325	90.77 165	96.65 223	97.18 209	93.72 89	91.68 222	97.26 149	79.33 269	98.63 214	92.13 173	92.28 258	95.07 321
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tpm2		89.96 305	89.21 308	92.23 318	94.91 312	81.25 367	93.78 364	94.42 362	80.62 395	91.56 223	93.44 349	76.44 308	97.94 295	85.60 307	92.08 266	97.49 219

TAPA-MVS	90.10 7	92.30 209	91.22 228	95.56 162	98.33 83	89.60 200	96.79 208	97.65 150	81.83 385	91.52 224	97.23 151	87.94 115	98.91 183	71.31 406	98.37 124	98.17 175
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_fmvs2		89.77 313	89.93 285	89.31 376	93.68 355	76.37 403	97.64 120	95.90 295	89.84 231	91.49 225	96.26 206	58.77 406	97.10 357	94.65 125	91.13 279	94.46 354

TR-MVS		91.48 248	90.59 256	94.16 236	96.40 227	87.33 269	95.67 288	95.34 326	87.68 305	91.46 226	95.52 248	76.77 304	98.35 240	82.85 339	93.61 244	96.79 245

RPSCF		90.75 282	90.86 240	90.42 361	96.84 186	76.29 404	95.61 294	96.34 276	83.89 366	91.38 227	97.87 103	76.45 307	98.78 195	87.16 283	92.23 259	96.20 258

PLC	91.00 6	94.11 139	93.43 149	96.13 127	98.58 71	91.15 153	96.69 219	97.39 194	87.29 314	91.37 228	96.71 175	88.39 107	99.52 105	87.33 278	97.13 168	97.73 206
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		93.12 175	92.72 173	94.34 227	96.71 200	87.27 272	90.29 405	97.72 142	86.61 326	91.34 229	95.29 255	84.29 174	98.41 231	93.25 152	98.94 99	97.35 227

HQP_MVS		93.78 153	93.43 149	94.82 199	96.21 235	89.99 188	97.74 100	97.51 169	94.85 43	91.34 229	96.64 182	81.32 233	98.60 217	93.02 160	92.23 259	95.86 271

plane_prior3						90.00 186			94.46 66	91.34 229

Fast-Effi-MVS+		93.46 162	92.75 170	95.59 161	96.77 196	90.03 185	96.81 207	97.13 213	88.19 285	91.30 232	94.27 311	86.21 147	98.63 214	87.66 270	96.46 183	98.12 179

EI-MVSNet		93.03 180	92.88 164	93.48 274	95.77 258	86.98 281	96.44 237	97.12 214	90.66 204	91.30 232	97.64 126	86.56 140	98.05 274	89.91 216	90.55 289	95.41 297

MVSTER		93.20 171	92.81 167	94.37 224	96.56 210	89.59 201	97.06 184	97.12 214	91.24 181	91.30 232	95.96 220	82.02 222	98.05 274	93.48 147	90.55 289	95.47 293

ADS-MVSNet2		89.45 317	88.59 319	92.03 321	95.86 252	82.26 360	90.93 401	94.32 369	83.23 376	91.28 235	91.81 380	79.01 278	95.99 378	79.52 366	91.39 275	97.84 200

ADS-MVSNet		89.89 308	88.68 318	93.53 272	95.86 252	84.89 327	90.93 401	95.07 338	83.23 376	91.28 235	91.81 380	79.01 278	97.85 304	79.52 366	91.39 275	97.84 200

testing11		91.68 234	90.75 248	94.47 219	96.53 215	86.56 293	95.76 285	94.51 360	91.10 189	91.24 237	93.59 343	68.59 370	98.86 186	91.10 197	94.29 224	98.00 189

nrg030		94.05 142	93.31 153	96.27 118	95.22 292	94.59 32	98.34 25	97.46 178	92.93 130	91.21 238	96.64 182	87.23 135	98.22 249	94.99 114	85.80 335	95.98 270

Effi-MVS+-dtu		93.08 177	93.21 156	92.68 306	96.02 249	83.25 346	97.14 180	96.72 253	93.85 86	91.20 239	93.44 349	83.08 196	98.30 244	91.69 186	95.73 194	96.50 251

VPNet		92.23 214	91.31 222	94.99 189	95.56 266	90.96 157	97.22 173	97.86 125	92.96 129	90.96 240	96.62 189	75.06 319	98.20 251	91.90 177	83.65 369	95.80 277

JIA-IIPM		88.26 332	87.04 336	91.91 324	93.52 359	81.42 366	89.38 412	94.38 365	80.84 392	90.93 241	80.74 419	79.22 270	97.92 298	82.76 341	91.62 270	96.38 255

MonoMVSNet		91.92 224	91.77 204	92.37 310	92.94 373	83.11 348	97.09 183	95.55 315	92.91 131	90.85 242	94.55 291	81.27 235	96.52 372	93.01 162	87.76 315	97.47 221

WB-MVSnew		89.88 309	89.56 299	90.82 353	94.57 329	83.06 349	95.65 292	92.85 390	87.86 296	90.83 243	94.10 320	79.66 264	96.88 366	76.34 384	94.19 227	92.54 387

test-LLR		91.42 250	91.19 229	92.12 319	94.59 326	80.66 373	94.29 348	92.98 388	91.11 187	90.76 244	92.37 368	79.02 276	98.07 271	88.81 246	96.74 174	97.63 210

test-mter		90.19 302	89.54 300	92.12 319	94.59 326	80.66 373	94.29 348	92.98 388	87.68 305	90.76 244	92.37 368	67.67 375	98.07 271	88.81 246	96.74 174	97.63 210

ACMM	89.79 8	92.96 183	92.50 183	94.35 225	96.30 233	88.71 234	97.58 126	97.36 199	91.40 175	90.53 246	96.65 181	79.77 261	98.75 200	91.24 195	91.64 269	95.59 289
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
F-COLMAP		93.58 158	92.98 160	95.37 174	98.40 78	88.98 229	97.18 176	97.29 205	87.75 303	90.49 247	97.10 158	85.21 159	99.50 109	86.70 288	96.72 176	97.63 210

TESTMET0.1,1		90.06 304	89.42 303	91.97 322	94.41 334	80.62 375	94.29 348	91.97 400	87.28 315	90.44 248	92.47 367	68.79 367	97.67 322	88.50 253	96.60 179	97.61 214

FIs		94.09 140	93.70 135	95.27 176	95.70 260	92.03 111	98.10 51	98.68 13	93.36 108	90.39 249	96.70 177	87.63 123	97.94 295	92.25 169	90.50 291	95.84 274

GA-MVS		91.38 252	90.31 265	94.59 211	94.65 324	87.62 267	94.34 344	96.19 287	90.73 198	90.35 250	93.83 330	71.84 341	97.96 290	87.22 280	93.61 244	98.21 170

LS3D		93.57 159	92.61 177	96.47 100	97.59 145	91.61 126	97.67 112	97.72 142	85.17 350	90.29 251	98.34 64	84.60 166	99.73 51	83.85 332	98.27 128	98.06 186

FC-MVSNet-test		93.94 146	93.57 139	95.04 186	95.48 270	91.45 136	98.12 50	98.71 11	93.37 106	90.23 252	96.70 177	87.66 120	97.85 304	91.49 189	90.39 292	95.83 275

HQP-NCC					95.86 252		96.65 223		93.55 95	90.14 253

ACMP_Plane					95.86 252		96.65 223		93.55 95	90.14 253

HQP4-MVS										90.14 253			98.50 225			95.78 279

HQP-MVS		93.19 172	92.74 171	94.54 217	95.86 252	89.33 216	96.65 223	97.39 194	93.55 95	90.14 253	95.87 224	80.95 237	98.50 225	92.13 173	92.10 264	95.78 279

UniMVSNet_NR-MVSNet		93.37 165	92.67 174	95.47 171	95.34 281	92.83 82	97.17 177	98.58 21	92.98 128	90.13 257	95.80 229	88.37 109	97.85 304	91.71 184	83.93 364	95.73 285

DU-MVS		92.90 187	92.04 195	95.49 168	94.95 307	92.83 82	97.16 178	98.24 53	93.02 122	90.13 257	95.71 236	83.47 186	97.85 304	91.71 184	83.93 364	95.78 279

LPG-MVS_test		92.94 185	92.56 178	94.10 238	96.16 240	88.26 248	97.65 116	97.46 178	91.29 177	90.12 259	97.16 154	79.05 274	98.73 203	92.25 169	91.89 267	95.31 307

LGP-MVS_train				94.10 238	96.16 240	88.26 248		97.46 178	91.29 177	90.12 259	97.16 154	79.05 274	98.73 203	92.25 169	91.89 267	95.31 307

UniMVSNet (Re)		93.31 167	92.55 179	95.61 160	95.39 275	93.34 67	97.39 154	98.71 11	93.14 119	90.10 261	94.83 277	87.71 119	98.03 278	91.67 187	83.99 363	95.46 294

mvs_anonymous		93.82 151	93.74 134	94.06 240	96.44 225	85.41 313	95.81 281	97.05 224	89.85 230	90.09 262	96.36 201	87.44 130	97.75 317	93.97 136	96.69 177	99.02 91

test_djsdf		93.07 178	92.76 168	94.00 244	93.49 361	88.70 235	98.22 40	97.57 161	91.42 173	90.08 263	95.55 246	82.85 204	97.92 298	94.07 134	91.58 271	95.40 300

dp		88.90 324	88.26 324	90.81 354	94.58 328	76.62 402	92.85 386	94.93 345	85.12 351	90.07 264	93.07 355	75.81 312	98.12 260	80.53 361	87.42 320	97.71 207

PS-MVSNAJss		93.74 154	93.51 145	94.44 221	93.91 347	89.28 220	97.75 98	97.56 165	92.50 140	89.94 265	96.54 192	88.65 103	98.18 254	93.83 143	90.90 285	95.86 271

UniMVSNet_ETH3D		91.34 257	90.22 273	94.68 209	94.86 314	87.86 262	97.23 172	97.46 178	87.99 291	89.90 266	96.92 167	66.35 386	98.23 248	90.30 210	90.99 283	97.96 190

CLD-MVS		92.98 182	92.53 181	94.32 228	96.12 245	89.20 223	95.28 310	97.47 176	92.66 137	89.90 266	95.62 242	80.58 245	98.40 232	92.73 165	92.40 257	95.38 302
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
gg-mvs-nofinetune		87.82 335	85.61 348	94.44 221	94.46 331	89.27 221	91.21 400	84.61 426	80.88 391	89.89 268	74.98 422	71.50 343	97.53 336	85.75 306	97.21 165	96.51 250

1112_ss		93.37 165	92.42 186	96.21 123	97.05 173	90.99 155	96.31 253	96.72 253	86.87 322	89.83 269	96.69 179	86.51 142	99.14 152	88.12 255	93.67 241	98.50 146

BH-untuned		92.94 185	92.62 176	93.92 254	97.22 159	86.16 304	96.40 245	96.25 283	90.06 224	89.79 270	96.17 210	83.19 192	98.35 240	87.19 281	97.27 163	97.24 232

V42		91.58 240	90.87 239	93.73 261	94.05 344	88.50 242	97.32 162	96.97 232	88.80 269	89.71 271	94.33 306	82.54 211	98.05 274	89.01 242	85.07 347	94.64 351

Baseline_NR-MVSNet		91.20 264	90.62 254	92.95 294	93.83 350	88.03 256	97.01 190	95.12 336	88.42 280	89.70 272	95.13 265	83.47 186	97.44 344	89.66 224	83.24 372	93.37 375

v144192		91.06 270	90.28 267	93.39 277	93.66 356	87.23 275	96.83 205	97.07 221	87.43 310	89.69 273	94.28 310	81.48 231	98.00 281	87.18 282	84.92 351	94.93 329

v1144		91.37 254	90.60 255	93.68 266	93.89 348	88.23 250	96.84 204	97.03 228	88.37 281	89.69 273	94.39 301	82.04 221	97.98 283	87.80 262	85.37 340	94.84 335

Test_1112_low_res		92.84 191	91.84 203	95.85 145	97.04 174	89.97 191	95.53 298	96.64 261	85.38 345	89.65 275	95.18 262	85.86 152	99.10 157	87.70 266	93.58 246	98.49 148

v1192		91.07 269	90.23 271	93.58 270	93.70 353	87.82 264	96.73 213	97.07 221	87.77 301	89.58 276	94.32 308	80.90 241	97.97 286	86.52 290	85.48 338	94.95 325

v1240		90.70 285	89.85 288	93.23 283	93.51 360	86.80 284	96.61 229	97.02 230	87.16 317	89.58 276	94.31 309	79.55 266	97.98 283	85.52 308	85.44 339	94.90 332

TranMVSNet+NR-MVSNet		92.50 198	91.63 210	95.14 181	94.76 318	92.07 109	97.53 134	98.11 79	92.90 132	89.56 278	96.12 213	83.16 193	97.60 330	89.30 233	83.20 373	95.75 283

v2v482		91.59 238	90.85 242	93.80 258	93.87 349	88.17 253	96.94 196	96.88 244	89.54 238	89.53 279	94.90 273	81.70 229	98.02 279	89.25 236	85.04 349	95.20 315

v1921920		90.85 279	90.03 282	93.29 281	93.55 357	86.96 283	96.74 212	97.04 226	87.36 312	89.52 280	94.34 305	80.23 253	97.97 286	86.27 293	85.21 344	94.94 327

IterMVS-LS		92.29 210	91.94 200	93.34 279	96.25 234	86.97 282	96.57 235	97.05 224	90.67 202	89.50 281	94.80 279	86.59 139	97.64 325	89.91 216	86.11 333	95.40 300
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cascas		91.20 264	90.08 277	94.58 215	94.97 305	89.16 226	93.65 370	97.59 159	79.90 398	89.40 282	92.92 358	75.36 317	98.36 239	92.14 172	94.75 216	96.23 256

XVG-ACMP-BASELINE		90.93 277	90.21 274	93.09 289	94.31 338	85.89 306	95.33 307	97.26 206	91.06 190	89.38 283	95.44 252	68.61 369	98.60 217	89.46 228	91.05 281	94.79 343

GBi-Net		91.35 255	90.27 268	94.59 211	96.51 218	91.18 149	97.50 137	96.93 236	88.82 266	89.35 284	94.51 294	73.87 328	97.29 353	86.12 298	88.82 304	95.31 307

test1		91.35 255	90.27 268	94.59 211	96.51 218	91.18 149	97.50 137	96.93 236	88.82 266	89.35 284	94.51 294	73.87 328	97.29 353	86.12 298	88.82 304	95.31 307

FMVSNet3		91.78 229	90.69 253	95.03 187	96.53 215	92.27 102	97.02 187	96.93 236	89.79 233	89.35 284	94.65 287	77.01 302	97.47 341	86.12 298	88.82 304	95.35 304

WR-MVS		92.34 206	91.53 214	94.77 206	95.13 300	90.83 162	96.40 245	97.98 109	91.88 159	89.29 287	95.54 247	82.50 212	97.80 311	89.79 220	85.27 343	95.69 286

DP-MVS		92.76 194	91.51 217	96.52 92	98.77 56	90.99 155	97.38 156	96.08 290	82.38 381	89.29 287	97.87 103	83.77 181	99.69 62	81.37 354	96.69 177	98.89 115

BH-w/o		92.14 218	91.75 206	93.31 280	96.99 179	85.73 308	95.67 288	95.69 307	88.73 271	89.26 289	94.82 278	82.97 201	98.07 271	85.26 313	96.32 184	96.13 265

3Dnovator	91.36 5	95.19 107	94.44 123	97.44 53	96.56 210	93.36 66	98.65 11	98.36 30	94.12 76	89.25 290	98.06 87	82.20 219	99.77 43	93.41 150	99.32 65	99.18 76

tt0805		91.09 268	90.07 280	94.16 236	95.61 263	88.31 245	97.56 129	96.51 269	89.56 237	89.17 291	95.64 241	67.08 383	98.38 238	91.07 198	88.44 310	95.80 277

miper_enhance_ethall		91.54 244	91.01 235	93.15 287	95.35 280	87.07 280	93.97 356	96.90 241	86.79 323	89.17 291	93.43 352	86.55 141	97.64 325	89.97 215	86.93 324	94.74 347

Fast-Effi-MVS+-dtu		92.29 210	91.99 198	93.21 285	95.27 288	85.52 311	97.03 185	96.63 264	92.09 153	89.11 293	95.14 264	80.33 251	98.08 267	87.54 274	94.74 217	96.03 269

WBMVS		90.69 287	89.99 283	92.81 300	96.48 221	85.00 323	95.21 317	96.30 279	89.46 242	89.04 294	94.05 324	72.45 338	97.82 308	89.46 228	87.41 321	95.61 288

XXY-MVS		92.16 216	91.23 227	94.95 195	94.75 319	90.94 158	97.47 144	97.43 190	89.14 251	88.90 295	96.43 197	79.71 262	98.24 247	89.56 226	87.68 316	95.67 287

PCF-MVS	89.48 11	91.56 241	89.95 284	96.36 111	96.60 205	92.52 93	92.51 390	97.26 206	79.41 400	88.90 295	96.56 191	84.04 179	99.55 97	77.01 383	97.30 162	97.01 236
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
miper_ehance_all_eth		91.59 238	91.13 231	92.97 293	95.55 267	86.57 292	94.47 337	96.88 244	87.77 301	88.88 297	94.01 325	86.22 146	97.54 334	89.49 227	86.93 324	94.79 343

SSC-MVS3.2		89.74 314	89.26 307	91.19 347	95.16 295	80.29 381	94.53 334	97.03 228	91.79 161	88.86 298	94.10 320	69.94 358	97.82 308	85.29 311	86.66 329	95.45 295

jajsoiax		92.42 202	91.89 202	94.03 243	93.33 367	88.50 242	97.73 102	97.53 167	92.00 157	88.85 299	96.50 194	75.62 316	98.11 261	93.88 141	91.56 272	95.48 291

eth_miper_zixun_eth		91.02 272	90.59 256	92.34 313	95.33 284	84.35 332	94.10 353	96.90 241	88.56 275	88.84 300	94.33 306	84.08 177	97.60 330	88.77 248	84.37 360	95.06 322

c3_l		91.38 252	90.89 238	92.88 297	95.58 265	86.30 299	94.68 329	96.84 248	88.17 286	88.83 301	94.23 314	85.65 155	97.47 341	89.36 231	84.63 353	94.89 333

mvs_tets		92.31 208	91.76 205	93.94 251	93.41 364	88.29 246	97.63 122	97.53 167	92.04 155	88.76 302	96.45 196	74.62 324	98.09 266	93.91 139	91.48 273	95.45 295

v148		90.99 273	90.38 262	92.81 300	93.83 350	85.80 307	96.78 210	96.68 258	89.45 243	88.75 303	93.93 329	82.96 202	97.82 308	87.83 261	83.25 371	94.80 341

FMVSNet2		91.31 258	90.08 277	94.99 189	96.51 218	92.21 104	97.41 149	96.95 234	88.82 266	88.62 304	94.75 281	73.87 328	97.42 346	85.20 314	88.55 309	95.35 304

PAPM		91.52 245	90.30 266	95.20 178	95.30 287	89.83 195	93.38 376	96.85 247	86.26 333	88.59 305	95.80 229	84.88 163	98.15 256	75.67 388	95.93 189	97.63 210

cl22		91.21 263	90.56 258	93.14 288	96.09 247	86.80 284	94.41 341	96.58 267	87.80 299	88.58 306	93.99 327	80.85 242	97.62 328	89.87 218	86.93 324	94.99 324

3Dnovator+	91.43 4	95.40 98	94.48 121	98.16 16	96.90 182	95.34 16	98.48 20	97.87 121	94.65 58	88.53 307	98.02 92	83.69 182	99.71 56	93.18 154	98.96 98	99.44 53

dmvs_re		90.21 300	89.50 301	92.35 311	95.47 273	85.15 319	95.70 287	94.37 366	90.94 193	88.42 308	93.57 344	74.63 323	95.67 386	82.80 340	89.57 299	96.22 257

anonymousdsp		92.16 216	91.55 213	93.97 247	92.58 382	89.55 204	97.51 136	97.42 191	89.42 244	88.40 309	94.84 276	80.66 244	97.88 303	91.87 179	91.28 277	94.48 353

reproduce_monomvs		91.30 259	91.10 232	91.92 323	96.82 190	82.48 356	97.01 190	97.49 172	94.64 59	88.35 310	95.27 258	70.53 351	98.10 262	95.20 107	84.60 355	95.19 318

WR-MVS_H		92.00 222	91.35 219	93.95 249	95.09 302	89.47 208	98.04 58	98.68 13	91.46 171	88.34 311	94.68 284	85.86 152	97.56 332	85.77 305	84.24 361	94.82 338

v8		91.29 261	90.53 259	93.57 271	94.15 340	88.12 255	97.34 159	97.06 223	88.99 257	88.32 312	94.26 313	83.08 196	98.01 280	87.62 272	83.92 366	94.57 352

ACMP	89.59 10	92.62 197	92.14 192	94.05 241	96.40 227	88.20 251	97.36 157	97.25 208	91.52 168	88.30 313	96.64 182	78.46 286	98.72 206	91.86 180	91.48 273	95.23 314
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v10		91.04 271	90.23 271	93.49 273	94.12 341	88.16 254	97.32 162	97.08 219	88.26 284	88.29 314	94.22 316	82.17 220	97.97 286	86.45 292	84.12 362	94.33 359

QAPM		93.45 163	92.27 189	96.98 78	96.77 196	92.62 88	98.39 24	98.12 76	84.50 360	88.27 315	97.77 114	82.39 216	99.81 30	85.40 310	98.81 103	98.51 145

Anonymous20231211		90.63 288	89.42 303	94.27 233	98.24 90	89.19 225	98.05 57	97.89 117	79.95 397	88.25 316	94.96 269	72.56 337	98.13 257	89.70 222	85.14 345	95.49 290

CP-MVSNet		91.89 227	91.24 226	93.82 257	95.05 303	88.57 238	97.82 91	98.19 64	91.70 164	88.21 317	95.76 234	81.96 223	97.52 338	87.86 260	84.65 352	95.37 303

DIV-MVS_self_test		90.97 275	90.33 263	92.88 297	95.36 279	86.19 303	94.46 339	96.63 264	87.82 297	88.18 318	94.23 314	82.99 199	97.53 336	87.72 263	85.57 337	94.93 329

cl____		90.96 276	90.32 264	92.89 296	95.37 278	86.21 302	94.46 339	96.64 261	87.82 297	88.15 319	94.18 317	82.98 200	97.54 334	87.70 266	85.59 336	94.92 331

tpmvs		89.83 312	89.15 310	91.89 326	94.92 310	80.30 380	93.11 381	95.46 319	86.28 332	88.08 320	92.65 361	80.44 248	98.52 224	81.47 350	89.92 295	96.84 243

PS-CasMVS		91.55 242	90.84 243	93.69 265	94.96 306	88.28 247	97.84 86	98.24 53	91.46 171	88.04 321	95.80 229	79.67 263	97.48 340	87.02 285	84.54 358	95.31 307

MIMVSNet		88.50 329	86.76 339	93.72 263	94.84 315	87.77 265	91.39 396	94.05 372	86.41 329	87.99 322	92.59 364	63.27 397	95.82 383	77.44 377	92.84 250	97.57 217

GG-mvs-BLEND				93.62 267	93.69 354	89.20 223	92.39 392	83.33 428		87.98 323	89.84 396	71.00 347	96.87 367	82.08 347	95.40 202	94.80 341

miper_lstm_enhance		90.50 293	90.06 281	91.83 328	95.33 284	83.74 340	93.86 362	96.70 257	87.56 308	87.79 324	93.81 333	83.45 188	96.92 365	87.39 276	84.62 354	94.82 338

PEN-MVS		91.20 264	90.44 260	93.48 274	94.49 330	87.91 261	97.76 97	98.18 66	91.29 177	87.78 325	95.74 235	80.35 250	97.33 351	85.46 309	82.96 374	95.19 318

ITE_SJBPF				92.43 309	95.34 281	85.37 316		95.92 293	91.47 170	87.75 326	96.39 200	71.00 347	97.96 290	82.36 345	89.86 296	93.97 367

v7n		90.76 281	89.86 287	93.45 276	93.54 358	87.60 268	97.70 110	97.37 197	88.85 263	87.65 327	94.08 323	81.08 236	98.10 262	84.68 319	83.79 368	94.66 350

Patchmtry		88.64 328	87.25 331	92.78 302	94.09 342	86.64 288	89.82 410	95.68 309	80.81 393	87.63 328	92.36 371	80.91 239	97.03 360	78.86 372	85.12 346	94.67 349

testing3		87.67 337	86.88 338	90.05 366	96.14 243	80.71 372	97.10 182	92.85 390	90.15 222	87.54 329	94.55 291	55.70 412	94.10 402	73.77 398	94.10 231	95.35 304

pmmvs4		90.93 277	89.85 288	94.17 235	93.34 366	90.79 164	94.60 331	96.02 291	84.62 358	87.45 330	95.15 263	81.88 226	97.45 343	87.70 266	87.87 314	94.27 363

tpm cat1		88.36 330	87.21 333	91.81 330	95.13 300	80.55 376	92.58 389	95.70 305	74.97 411	87.45 330	91.96 378	78.01 296	98.17 255	80.39 362	88.74 307	96.72 247

FMVSNet1		89.88 309	88.31 322	94.59 211	95.41 274	91.18 149	97.50 137	96.93 236	86.62 325	87.41 332	94.51 294	65.94 391	97.29 353	83.04 336	87.43 319	95.31 307

IterMVS-SCA-FT		90.31 295	89.81 290	91.82 329	95.52 268	84.20 335	94.30 347	96.15 288	90.61 208	87.39 333	94.27 311	75.80 313	96.44 373	87.34 277	86.88 328	94.82 338

MVS		91.71 231	90.44 260	95.51 166	95.20 294	91.59 128	96.04 268	97.45 183	73.44 415	87.36 334	95.60 243	85.42 157	99.10 157	85.97 302	97.46 151	95.83 275

EU-MVSNet		88.72 327	88.90 315	88.20 380	93.15 370	74.21 408	96.63 228	94.22 371	85.18 349	87.32 335	95.97 219	76.16 310	94.98 395	85.27 312	86.17 331	95.41 297

IterMVS		90.15 303	89.67 296	91.61 336	95.48 270	83.72 341	94.33 345	96.12 289	89.99 225	87.31 336	94.15 319	75.78 315	96.27 376	86.97 286	86.89 327	94.83 336
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UWE-MVS-28		86.81 346	86.41 341	88.02 382	92.87 374	74.60 407	95.38 305	86.70 422	88.17 286	87.28 337	94.67 286	70.83 349	93.30 410	67.45 412	94.31 223	96.17 260

pmmvs5		89.86 311	88.87 316	92.82 299	92.86 375	86.23 301	96.26 256	95.39 320	84.24 362	87.12 338	94.51 294	74.27 326	97.36 350	87.61 273	87.57 317	94.86 334

DTE-MVSNet		90.56 289	89.75 294	93.01 291	93.95 345	87.25 273	97.64 120	97.65 150	90.74 197	87.12 338	95.68 239	79.97 258	97.00 363	83.33 333	81.66 380	94.78 345

mvs5depth		86.53 347	85.08 354	90.87 351	88.74 410	82.52 355	91.91 394	94.23 370	86.35 330	87.11 340	93.70 336	66.52 384	97.76 316	81.37 354	75.80 400	92.31 392

Patchmatch-test		89.42 318	87.99 325	93.70 264	95.27 288	85.11 320	88.98 413	94.37 366	81.11 389	87.10 341	93.69 337	82.28 217	97.50 339	74.37 394	94.76 215	98.48 150

IB-MVS	87.33 17	89.91 306	88.28 323	94.79 205	95.26 291	87.70 266	95.12 320	93.95 376	89.35 246	87.03 342	92.49 365	70.74 350	99.19 140	89.18 240	81.37 381	97.49 219
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
EPNet_dtu		91.71 231	91.28 224	92.99 292	93.76 352	83.71 342	96.69 219	95.28 327	93.15 118	87.02 343	95.95 221	83.37 189	97.38 349	79.46 369	96.84 171	97.88 195
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Syy-MVS		87.13 342	87.02 337	87.47 384	95.16 295	73.21 412	95.00 322	93.93 377	88.55 276	86.96 344	91.99 376	75.90 311	94.00 403	61.59 418	94.11 229	95.20 315

myMVS_eth3d		87.18 341	86.38 342	89.58 371	95.16 295	79.53 390	95.00 322	93.93 377	88.55 276	86.96 344	91.99 376	56.23 411	94.00 403	75.47 390	94.11 229	95.20 315

baseline2		91.63 235	90.86 240	93.94 251	94.33 336	86.32 298	95.92 275	91.64 402	89.37 245	86.94 346	94.69 283	81.62 230	98.69 208	88.64 251	94.57 220	96.81 244

MSDG		91.42 250	90.24 270	94.96 194	97.15 165	88.91 230	93.69 368	96.32 277	85.72 341	86.93 347	96.47 195	80.24 252	98.98 176	80.57 360	95.05 210	96.98 237

test0.0.03 1		89.37 319	88.70 317	91.41 341	92.47 384	85.63 309	95.22 315	92.70 393	91.11 187	86.91 348	93.65 341	79.02 276	93.19 412	78.00 376	89.18 302	95.41 297

COLMAP_ROB	87.81 15	90.40 294	89.28 306	93.79 259	97.95 118	87.13 279	96.92 197	95.89 297	82.83 378	86.88 349	97.18 153	73.77 331	99.29 132	78.44 374	93.62 243	94.95 325
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
D2MVS		91.30 259	90.95 237	92.35 311	94.71 322	85.52 311	96.18 263	98.21 57	88.89 262	86.60 350	93.82 332	79.92 259	97.95 294	89.29 234	90.95 284	93.56 371

OurMVSNet-221017-0		90.51 292	90.19 275	91.44 340	93.41 364	81.25 367	96.98 193	96.28 280	91.68 165	86.55 351	96.30 203	74.20 327	97.98 283	88.96 244	87.40 322	95.09 320

MS-PatchMatch		90.27 297	89.77 292	91.78 332	94.33 336	84.72 329	95.55 296	96.73 252	86.17 335	86.36 352	95.28 257	71.28 345	97.80 311	84.09 326	98.14 134	92.81 381

1314		92.81 193	92.03 196	95.14 181	95.33 284	89.52 207	96.04 268	97.44 187	87.72 304	86.25 353	95.33 254	83.84 180	98.79 194	89.26 235	97.05 169	97.11 235

tfpnnormal		89.70 315	88.40 321	93.60 268	95.15 298	90.10 184	97.56 129	98.16 70	87.28 315	86.16 354	94.63 288	77.57 299	98.05 274	74.48 392	84.59 356	92.65 384

pm-mvs1		90.72 284	89.65 298	93.96 248	94.29 339	89.63 198	97.79 95	96.82 249	89.07 253	86.12 355	95.48 251	78.61 284	97.78 313	86.97 286	81.67 379	94.46 354

OpenMVS	89.19 12	92.86 189	91.68 209	96.40 106	95.34 281	92.73 86	98.27 32	98.12 76	84.86 355	85.78 356	97.75 115	78.89 281	99.74 49	87.50 275	98.65 110	96.73 246

LTVRE_ROB	88.41 13	90.99 273	89.92 286	94.19 234	96.18 238	89.55 204	96.31 253	97.09 218	87.88 295	85.67 357	95.91 223	78.79 282	98.57 221	81.50 349	89.98 294	94.44 356
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
testgi		87.97 333	87.21 333	90.24 364	92.86 375	80.76 371	96.67 222	94.97 342	91.74 163	85.52 358	95.83 227	62.66 401	94.47 399	76.25 385	88.36 311	95.48 291

AllTest		90.23 299	88.98 312	93.98 245	97.94 119	86.64 288	96.51 236	95.54 316	85.38 345	85.49 359	96.77 173	70.28 353	99.15 149	80.02 364	92.87 248	96.15 263

TestCases				93.98 245	97.94 119	86.64 288		95.54 316	85.38 345	85.49 359	96.77 173	70.28 353	99.15 149	80.02 364	92.87 248	96.15 263

DSMNet-mixed		86.34 351	86.12 346	87.00 388	89.88 401	70.43 414	94.93 324	90.08 411	77.97 406	85.42 361	92.78 359	74.44 325	93.96 405	74.43 393	95.14 206	96.62 248

ppachtmachnet_test		88.35 331	87.29 330	91.53 337	92.45 385	83.57 344	93.75 365	95.97 292	84.28 361	85.32 362	94.18 317	79.00 280	96.93 364	75.71 387	84.99 350	94.10 364

CL-MVSNet_self_test		86.31 352	85.15 353	89.80 369	88.83 408	81.74 365	93.93 359	96.22 284	86.67 324	85.03 363	90.80 387	78.09 293	94.50 397	74.92 391	71.86 409	93.15 377

our_test_3		88.78 326	87.98 326	91.20 346	92.45 385	82.53 354	93.61 372	95.69 307	85.77 340	84.88 364	93.71 335	79.99 257	96.78 370	79.47 368	86.24 330	94.28 362

MVP-Stereo		90.74 283	90.08 277	92.71 304	93.19 369	88.20 251	95.86 278	96.27 281	86.07 336	84.86 365	94.76 280	77.84 297	97.75 317	83.88 331	98.01 138	92.17 396
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMH+	87.92 14	90.20 301	89.18 309	93.25 282	96.48 221	86.45 296	96.99 192	96.68 258	88.83 265	84.79 366	96.22 207	70.16 355	98.53 223	84.42 323	88.04 312	94.77 346

NR-MVSNet		92.34 206	91.27 225	95.53 165	94.95 307	93.05 77	97.39 154	98.07 88	92.65 138	84.46 367	95.71 236	85.00 162	97.77 315	89.71 221	83.52 370	95.78 279

LF4IMVS		87.94 334	87.25 331	89.98 367	92.38 387	80.05 386	94.38 342	95.25 330	87.59 307	84.34 368	94.74 282	64.31 395	97.66 324	84.83 316	87.45 318	92.23 393

LCM-MVSNet-Re		92.50 198	92.52 182	92.44 308	96.82 190	81.89 363	96.92 197	93.71 381	92.41 142	84.30 369	94.60 289	85.08 161	97.03 360	91.51 188	97.36 157	98.40 159

TransMVSNet (Re)		88.94 322	87.56 328	93.08 290	94.35 335	88.45 244	97.73 102	95.23 331	87.47 309	84.26 370	95.29 255	79.86 260	97.33 351	79.44 370	74.44 404	93.45 374

Anonymous20231206		87.09 343	86.14 345	89.93 368	91.22 393	80.35 378	96.11 265	95.35 323	83.57 373	84.16 371	93.02 356	73.54 333	95.61 387	72.16 403	86.14 332	93.84 369

SixPastTwentyTwo		89.15 320	88.54 320	90.98 349	93.49 361	80.28 382	96.70 217	94.70 353	90.78 195	84.15 372	95.57 244	71.78 342	97.71 320	84.63 320	85.07 347	94.94 327

test_fmvs3		83.21 370	83.02 367	83.78 393	86.77 417	68.34 419	96.76 211	94.91 346	86.49 327	84.14 373	89.48 398	36.04 425	91.73 415	91.86 180	80.77 384	91.26 405

TDRefinement		86.53 347	84.76 359	91.85 327	82.23 425	84.25 333	96.38 247	95.35 323	84.97 354	84.09 374	94.94 270	65.76 392	98.34 243	84.60 321	74.52 403	92.97 378

KD-MVS_self_test		85.95 357	84.95 356	88.96 377	89.55 404	79.11 396	95.13 319	96.42 273	85.91 338	84.07 375	90.48 389	70.03 357	94.82 396	80.04 363	72.94 407	92.94 379

pmmvs6		87.81 336	86.19 344	92.69 305	91.32 392	86.30 299	97.34 159	96.41 274	80.59 396	84.05 376	94.37 303	67.37 378	97.67 322	84.75 318	79.51 389	94.09 366

ACMH	87.59 16	90.53 290	89.42 303	93.87 255	96.21 235	87.92 259	97.24 168	96.94 235	88.45 279	83.91 377	96.27 205	71.92 340	98.62 216	84.43 322	89.43 300	95.05 323
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet5		87.29 340	85.79 347	91.78 332	94.80 317	87.28 271	95.49 300	95.28 327	84.09 364	83.85 378	91.82 379	62.95 399	94.17 401	78.48 373	85.34 342	93.91 368

USDC		88.94 322	87.83 327	92.27 315	94.66 323	84.96 325	93.86 362	95.90 295	87.34 313	83.40 379	95.56 245	67.43 377	98.19 253	82.64 344	89.67 298	93.66 370

ttmdpeth		85.91 358	84.76 359	89.36 374	89.14 405	80.25 383	95.66 291	93.16 387	83.77 369	83.39 380	95.26 259	66.24 388	95.26 394	80.65 359	75.57 401	92.57 385

Anonymous20240521		86.42 350	85.44 349	89.34 375	90.33 397	79.79 387	96.73 213	95.92 293	83.71 371	83.25 381	91.36 384	63.92 396	96.01 377	78.39 375	85.36 341	92.22 394

KD-MVS_2432*1600		84.81 365	82.64 369	91.31 342	91.07 394	85.34 317	91.22 398	95.75 303	85.56 343	83.09 382	90.21 392	67.21 379	95.89 379	77.18 381	62.48 422	92.69 382

miper_refine_blended		84.81 365	82.64 369	91.31 342	91.07 394	85.34 317	91.22 398	95.75 303	85.56 343	83.09 382	90.21 392	67.21 379	95.89 379	77.18 381	62.48 422	92.69 382

PVSNet_0	82.17 19	85.46 362	83.64 365	90.92 350	95.27 288	79.49 392	90.55 404	95.60 312	83.76 370	83.00 384	89.95 394	71.09 346	97.97 286	82.75 342	60.79 424	95.31 307

mvsany_test3		83.59 368	82.44 372	87.03 387	83.80 420	73.82 409	93.70 366	90.92 408	86.42 328	82.51 385	90.26 391	46.76 420	95.71 384	90.82 201	76.76 397	91.57 400

test_0402		86.46 349	84.79 358	91.45 339	95.02 304	85.55 310	96.29 255	94.89 347	80.90 390	82.21 386	93.97 328	68.21 374	97.29 353	62.98 416	88.68 308	91.51 401

Patchmatch-RL test		87.38 339	86.24 343	90.81 354	88.74 410	78.40 399	88.12 418	93.17 386	87.11 318	82.17 387	89.29 399	81.95 224	95.60 388	88.64 251	77.02 395	98.41 158

TinyColmap		86.82 345	85.35 352	91.21 344	94.91 312	82.99 350	93.94 358	94.02 374	83.58 372	81.56 388	94.68 284	62.34 402	98.13 257	75.78 386	87.35 323	92.52 388

test20.03		86.14 355	85.40 351	88.35 378	90.12 398	80.06 385	95.90 277	95.20 332	88.59 272	81.29 389	93.62 342	71.43 344	92.65 413	71.26 407	81.17 382	92.34 390

N_pmnet		78.73 380	78.71 381	78.79 398	92.80 377	46.50 437	94.14 352	43.71 439	78.61 403	80.83 390	91.66 382	74.94 321	96.36 374	67.24 413	84.45 359	93.50 372

MVS-HIRNet		82.47 373	81.21 376	86.26 390	95.38 276	69.21 417	88.96 414	89.49 412	66.28 419	80.79 391	74.08 424	68.48 372	97.39 348	71.93 404	95.47 200	92.18 395

PM-MVS		83.48 369	81.86 375	88.31 379	87.83 414	77.59 401	93.43 374	91.75 401	86.91 320	80.63 392	89.91 395	44.42 421	95.84 382	85.17 315	76.73 398	91.50 402

ambc				86.56 389	83.60 422	70.00 416	85.69 420	94.97 342		80.60 393	88.45 403	37.42 424	96.84 368	82.69 343	75.44 402	92.86 380

MIMVSNet1		84.93 364	83.05 366	90.56 359	89.56 403	84.84 328	95.40 303	95.35 323	83.91 365	80.38 394	92.21 375	57.23 408	93.34 409	70.69 409	82.75 377	93.50 372

lessismore_v0				90.45 360	91.96 390	79.09 397		87.19 420		80.32 395	94.39 301	66.31 387	97.55 333	84.00 328	76.84 396	94.70 348

K. test v3		87.64 338	86.75 340	90.32 363	93.02 372	79.48 393	96.61 229	92.08 399	90.66 204	80.25 396	94.09 322	67.21 379	96.65 371	85.96 303	80.83 383	94.83 336

OpenMVS_ROB	81.14 20	84.42 367	82.28 373	90.83 352	90.06 399	84.05 338	95.73 286	94.04 373	73.89 414	80.17 397	91.53 383	59.15 405	97.64 325	66.92 414	89.05 303	90.80 407

EG-PatchMatch MVS		87.02 344	85.44 349	91.76 334	92.67 379	85.00 323	96.08 267	96.45 272	83.41 375	79.52 398	93.49 346	57.10 409	97.72 319	79.34 371	90.87 286	92.56 386

pmmvs-eth3d		86.22 353	84.45 361	91.53 337	88.34 412	87.25 273	94.47 337	95.01 339	83.47 374	79.51 399	89.61 397	69.75 361	95.71 384	83.13 335	76.73 398	91.64 398

test_vis1_rt		86.16 354	85.06 355	89.46 372	93.47 363	80.46 377	96.41 241	86.61 423	85.22 348	79.15 400	88.64 402	52.41 415	97.06 358	93.08 157	90.57 288	90.87 406

pmmvs3		79.97 378	77.50 383	87.39 385	82.80 424	79.38 394	92.70 388	90.75 409	70.69 416	78.66 401	87.47 412	51.34 416	93.40 408	73.39 400	69.65 412	89.38 411

UnsupCasMVSNet_eth		85.99 356	84.45 361	90.62 358	89.97 400	82.40 359	93.62 371	97.37 197	89.86 228	78.59 402	92.37 368	65.25 394	95.35 393	82.27 346	70.75 410	94.10 364

dmvs_testset		81.38 376	82.60 371	77.73 399	91.74 391	51.49 434	93.03 383	84.21 427	89.07 253	78.28 403	91.25 385	76.97 303	88.53 422	56.57 422	82.24 378	93.16 376

test_f		80.57 377	79.62 379	83.41 394	83.38 423	67.80 421	93.57 373	93.72 380	80.80 394	77.91 404	87.63 410	33.40 426	92.08 414	87.14 284	79.04 392	90.34 409

new-patchmatchnet		83.18 371	81.87 374	87.11 386	86.88 416	75.99 405	93.70 366	95.18 333	85.02 353	77.30 405	88.40 404	65.99 390	93.88 406	74.19 396	70.18 411	91.47 403

UnsupCasMVSNet_bld		82.13 375	79.46 380	90.14 365	88.00 413	82.47 357	90.89 403	96.62 266	78.94 402	75.61 406	84.40 417	56.63 410	96.31 375	77.30 380	66.77 418	91.63 399

ET-MVSNet_ETH3D		91.49 247	90.11 276	95.63 158	96.40 227	91.57 130	95.34 306	93.48 383	90.60 210	75.58 407	95.49 249	80.08 255	96.79 369	94.25 132	89.76 297	98.52 143

new_pmnet		82.89 372	81.12 377	88.18 381	89.63 402	80.18 384	91.77 395	92.57 394	76.79 409	75.56 408	88.23 406	61.22 404	94.48 398	71.43 405	82.92 375	89.87 410

dongtai		69.99 387	69.33 389	71.98 408	88.78 409	61.64 428	89.86 409	59.93 438	75.67 410	74.96 409	85.45 414	50.19 417	81.66 427	43.86 426	55.27 425	72.63 423

APD_test1		79.31 379	77.70 382	84.14 392	89.11 407	69.07 418	92.36 393	91.50 403	69.07 417	73.87 410	92.63 363	39.93 423	94.32 400	70.54 410	80.25 385	89.02 412

CMPMVS	62.92 21	85.62 361	84.92 357	87.74 383	89.14 405	73.12 413	94.17 351	96.80 250	73.98 412	73.65 411	94.93 271	66.36 385	97.61 329	83.95 329	91.28 277	92.48 389
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVStest1		82.38 374	80.04 378	89.37 373	87.63 415	82.83 351	95.03 321	93.37 385	73.90 413	73.50 412	94.35 304	62.89 400	93.25 411	73.80 397	65.92 419	92.04 397

WB-MVS		76.77 381	76.63 384	77.18 400	85.32 418	56.82 432	94.53 334	89.39 413	82.66 380	71.35 413	89.18 400	75.03 320	88.88 420	35.42 429	66.79 417	85.84 414

SSC-MVS		76.05 382	75.83 385	76.72 404	84.77 419	56.22 433	94.32 346	88.96 415	81.82 386	70.52 414	88.91 401	74.79 322	88.71 421	33.69 430	64.71 420	85.23 415

YYNet1		85.87 359	84.23 363	90.78 357	92.38 387	82.46 358	93.17 378	95.14 335	82.12 383	67.69 415	92.36 371	78.16 292	95.50 391	77.31 379	79.73 387	94.39 357

kuosan		65.27 393	64.66 395	67.11 411	83.80 420	61.32 429	88.53 415	60.77 437	68.22 418	67.67 416	80.52 420	49.12 418	70.76 433	29.67 432	53.64 427	69.26 425

MDA-MVSNet_test_wron		85.87 359	84.23 363	90.80 356	92.38 387	82.57 353	93.17 378	95.15 334	82.15 382	67.65 417	92.33 374	78.20 289	95.51 390	77.33 378	79.74 386	94.31 361

DeepMVS_CX				74.68 407	90.84 396	64.34 425		81.61 430	65.34 420	67.47 418	88.01 409	48.60 419	80.13 429	62.33 417	73.68 406	79.58 419

LCM-MVSNet		72.55 384	69.39 388	82.03 395	70.81 435	65.42 424	90.12 408	94.36 368	55.02 425	65.88 419	81.72 418	24.16 433	89.96 416	74.32 395	68.10 416	90.71 408

test_method		66.11 392	64.89 394	69.79 409	72.62 433	35.23 441	65.19 428	92.83 392	20.35 431	65.20 420	88.08 408	43.14 422	82.70 426	73.12 401	63.46 421	91.45 404

MDA-MVSNet-bldmvs		85.00 363	82.95 368	91.17 348	93.13 371	83.33 345	94.56 333	95.00 340	84.57 359	65.13 421	92.65 361	70.45 352	95.85 381	73.57 399	77.49 394	94.33 359

PMMVS2		70.19 386	66.92 390	80.01 396	76.35 429	65.67 423	86.22 419	87.58 419	64.83 421	62.38 422	80.29 421	26.78 431	88.49 423	63.79 415	54.07 426	85.88 413

testf1		69.31 388	66.76 391	76.94 402	78.61 427	61.93 426	88.27 416	86.11 424	55.62 423	59.69 423	85.31 415	20.19 435	89.32 417	57.62 419	69.44 414	79.58 419

APD_test2		69.31 388	66.76 391	76.94 402	78.61 427	61.93 426	88.27 416	86.11 424	55.62 423	59.69 423	85.31 415	20.19 435	89.32 417	57.62 419	69.44 414	79.58 419

test_vis3_rt		72.73 383	70.55 386	79.27 397	80.02 426	68.13 420	93.92 360	74.30 434	76.90 408	58.99 425	73.58 425	20.29 434	95.37 392	84.16 324	72.80 408	74.31 422

FPMVS		71.27 385	69.85 387	75.50 405	74.64 430	59.03 430	91.30 397	91.50 403	58.80 422	57.92 426	88.28 405	29.98 429	85.53 425	53.43 423	82.84 376	81.95 418

Gipuma		67.86 391	65.41 393	75.18 406	92.66 380	73.45 410	66.50 427	94.52 359	53.33 426	57.80 427	66.07 427	30.81 427	89.20 419	48.15 425	78.88 393	62.90 427
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		51.94 399	53.82 399	46.29 415	33.73 439	45.30 439	78.32 425	67.24 436	18.02 432	50.93 428	87.05 413	52.99 414	53.11 434	70.76 408	25.29 432	40.46 430

ANet_high		63.94 394	59.58 397	77.02 401	61.24 437	66.06 422	85.66 421	87.93 418	78.53 404	42.94 429	71.04 426	25.42 432	80.71 428	52.60 424	30.83 430	84.28 416

E-PMN		53.28 396	52.56 400	55.43 413	74.43 431	47.13 436	83.63 423	76.30 431	42.23 428	42.59 430	62.22 429	28.57 430	74.40 430	31.53 431	31.51 429	44.78 428

EMVS		52.08 398	51.31 401	54.39 414	72.62 433	45.39 438	83.84 422	75.51 433	41.13 429	40.77 431	59.65 430	30.08 428	73.60 431	28.31 433	29.90 431	44.18 429

MVE	50.73 23	53.25 397	48.81 402	66.58 412	65.34 436	57.50 431	72.49 426	70.94 435	40.15 430	39.28 432	63.51 428	6.89 439	73.48 432	38.29 428	42.38 428	68.76 426
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	53.92 22	58.58 395	55.40 398	68.12 410	51.00 438	48.64 435	78.86 424	87.10 421	46.77 427	35.84 433	74.28 423	8.76 437	86.34 424	42.07 427	73.91 405	69.38 424
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		25.11 400	24.57 404	26.74 416	73.98 432	39.89 440	57.88 429	9.80 440	12.27 433	10.39 434	6.97 436	7.03 438	36.44 435	25.43 434	17.39 433	3.89 433

testmvs		13.36 402	16.33 405	4.48 418	5.04 440	2.26 443	93.18 377	3.28 441	2.70 434	8.24 435	21.66 432	2.29 441	2.19 436	7.58 435	2.96 434	9.00 432

test123		13.04 403	15.66 406	5.18 417	4.51 441	3.45 442	92.50 391	1.81 442	2.50 435	7.58 436	20.15 433	3.67 440	2.18 437	7.13 436	1.07 435	9.90 431

EGC-MVSNET		68.77 390	63.01 396	86.07 391	92.49 383	82.24 361	93.96 357	90.96 407	0.71 436	2.62 437	90.89 386	53.66 413	93.46 407	57.25 421	84.55 357	82.51 417

mmdepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

monomultidepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

test_blank		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet_test		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

DCPMVS		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

cdsmvs_eth3d_5k		23.24 401	30.99 403	0.00 419	0.00 442	0.00 444	0.00 430	97.63 154	0.00 437	0.00 438	96.88 169	84.38 171	0.00 438	0.00 437	0.00 436	0.00 434

pcd_1.5k_mvsjas		7.39 405	9.85 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	88.65 103	0.00 438	0.00 437	0.00 436	0.00 434

sosnet-low-res		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

sosnet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uncertanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

Regformer		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

ab-mvs-re		8.06 404	10.74 407	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	96.69 179	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

WAC-MVS						79.53 390								75.56 389

MSC_two_6792asdad				98.86 1	98.67 61	96.94 1		97.93 114					99.86 9	97.68 27	99.67 6	99.77 2

No_MVS				98.86 1	98.67 61	96.94 1		97.93 114					99.86 9	97.68 27	99.67 6	99.77 2

eth-test2					0.00 442

eth-test					0.00 442

OPU-MVS				98.55 3	98.82 55	96.86 3	98.25 35				98.26 76	96.04 2	99.24 135	95.36 105	99.59 19	99.56 32

save fliter					98.91 52	94.28 38	97.02 187	98.02 103	95.35 24

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 42	98.28 42					99.86 9	97.52 35	99.67 6	99.75 6

GSMVS																98.45 153

sam_mvs1												82.76 206				98.45 153

sam_mvs												81.94 225

MTGPA								98.08 83

test_post1							92.81 387				16.58 435	80.53 246	97.68 321	86.20 295

test_post											17.58 434	81.76 227	98.08 267

patchmatchnet-post											90.45 390	82.65 210	98.10 262

MTMP							97.86 82	82.03 429

gm-plane-assit					93.22 368	78.89 398			84.82 356		93.52 345		98.64 213	87.72 263

test9_res														94.81 120	99.38 59	99.45 51

agg_prior2														93.94 138	99.38 59	99.50 44

test_prior4						93.66 58	96.42 240

test_prior				97.23 64	98.67 61	92.99 79		98.00 107					99.41 119			99.29 67

新几何2							95.79 283

旧先验1					98.38 81	93.38 64		97.75 137			98.09 85	92.30 45			99.01 96	99.16 77

无先验							95.79 283	97.87 121	83.87 368				99.65 68	87.68 269		98.89 115

原ACMM2							95.67 288

testdata2													99.67 66	85.96 303

segment_acmp												92.89 30

testdata1							95.26 314		93.10 121

plane_prior7					96.21 235	89.98 190

plane_prior6					96.10 246	90.00 186						81.32 233

plane_prior5								97.51 169					98.60 217	93.02 160	92.23 259	95.86 271

plane_prior4											96.64 182

plane_prior2							97.74 100		94.85 43

plane_prior1					96.14 243

plane_prior						89.99 188	97.24 168		94.06 78						92.16 263

n2								0.00 443

nn								0.00 443

door-mid								91.06 406

test11								97.88 119

door								91.13 405

HQP5-MVS						89.33 216

BP-MVS														92.13 173

HQP3-MVS								97.39 194							92.10 264

HQP2-MVS												80.95 237

NP-MVS					95.99 250	89.81 196					95.87 224

ACMMP++_ref															90.30 293

ACMMP++															91.02 282

Test By Simon												88.73 102

High-resolution multi-view benchmark