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_9		97.33 19	97.32 22	97.37 55	97.64 123	92.45 106	99.93 1	97.85 66	97.39 5	99.84 1	99.09 62	85.42 149	99.92 44	99.52 18	99.20 78	99.73 53

fmvsm_s_conf0.5_n_9		96.76 40	96.92 27	96.29 122	97.95 112	89.21 197	99.81 18	97.55 138	97.04 12	99.68 2	99.22 31	82.84 191	99.94 35	99.56 14	98.61 110	99.71 55

fmvsm_s_conf0.5_n_6		96.78 38	96.64 43	97.20 64	96.03 214	93.20 82	99.82 17	97.68 103	95.20 40	99.61 3	99.11 60	84.52 163	99.90 55	99.04 33	98.77 104	98.50 187

fmvsm_l_conf0.5_n		97.65 14	97.72 12	97.41 52	97.51 133	92.78 96	99.85 10	98.05 50	96.78 15	99.60 4	99.23 29	90.42 52	99.92 44	99.55 15	98.50 117	99.55 82

fmvsm_l_conf0.5_n_a		97.70 13	97.80 11	97.42 51	97.59 128	92.91 93	99.86 7	98.04 52	96.70 17	99.58 5	99.26 24	90.90 41	99.94 35	99.57 13	98.66 108	99.40 98

IU-MVS					99.63 18	95.38 24		97.73 91	95.54 35	99.54 6				99.69 7	99.81 23	99.99 1

fmvsm_s_conf0.5_n_3		96.58 49	96.55 45	96.66 97	97.23 148	92.59 103	99.81 18	97.82 73	97.35 6	99.42 7	99.16 44	80.27 232	99.93 41	99.26 21	98.60 112	97.45 240

PC_three_1452									94.60 49	99.41 8	99.12 56	95.50 7	99.96 28	99.84 2	99.92 3	99.97 7

CNVR-MVS		98.46 1	98.38 1	98.72 10	99.80 4	96.19 15	99.80 24	97.99 56	97.05 11	99.41 8	99.59 2	92.89 26	100.00 1	98.99 36	99.90 7	99.96 10

fmvsm_l_conf0.5_n_3		97.12 26	96.89 30	97.79 39	97.39 138	93.84 68	99.87 6	97.70 97	97.34 7	99.39 10	99.20 35	82.86 189	99.94 35	99.21 26	99.07 81	99.58 81

patch_mono-2		97.10 28	97.97 8	94.49 213	99.21 63	83.73 336	99.62 51	98.25 34	95.28 39	99.38 11	98.91 89	92.28 31	99.94 35	99.61 11	99.22 74	99.78 41

fmvsm_s_conf0.5_n_4		96.17 63	96.49 47	95.21 182	97.06 164	89.26 196	99.76 30	98.07 48	95.99 26	99.35 12	99.22 31	82.19 211	99.89 62	99.06 32	97.68 138	96.49 275

test0726					99.66 12	95.20 32	99.77 27	97.70 97	93.95 62	99.35 12	99.54 3	93.18 23

SED-MVS		98.18 2	98.10 4	98.41 18	99.63 18	95.24 27	99.77 27	97.72 92	94.17 57	99.30 14	99.54 3	93.32 20	99.98 9	99.70 5	99.81 23	99.99 1

test_241102_ONE					99.63 18	95.24 27		97.72 92	94.16 59	99.30 14	99.49 9	93.32 20	99.98 9

fmvsm_s_conf0.5_n_8		97.06 30	96.94 26	97.44 48	97.78 117	92.77 97	99.83 13	97.83 72	97.58 3	99.25 16	99.20 35	82.71 197	99.92 44	99.64 8	98.61 110	99.64 71

DVP-MVS++		98.18 2	98.09 5	98.44 16	99.61 24	95.38 24	99.55 57	97.68 103	93.01 89	99.23 17	99.45 14	95.12 8	99.98 9	99.25 23	99.92 3	99.97 7

test_241102_TWO								97.72 92	94.17 57	99.23 17	99.54 3	93.14 25	99.98 9	99.70 5	99.82 19	99.99 1

fmvsm_s_conf0.5_n_2		95.85 79	95.83 73	95.91 146	97.19 152	91.79 117	99.78 26	97.65 116	97.23 8	99.22 19	99.06 66	75.93 272	99.90 55	99.30 19	97.09 155	96.02 285

SMA-MVS		97.24 21	96.99 25	98.00 31	99.30 54	94.20 61	99.16 112	97.65 116	89.55 191	99.22 19	99.52 8	90.34 55	99.99 5	98.32 58	99.83 15	99.82 32
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_conf0.5_n_a		95.97 71	96.19 58	95.31 177	96.51 185	89.01 208	99.81 18	98.39 29	95.46 37	99.19 21	99.16 44	81.44 223	99.91 51	98.83 39	96.97 156	97.01 257

test_fmvsm_n_1920		97.08 29	97.55 14	95.67 157	97.94 113	89.61 192	99.93 1	98.48 25	97.08 10	99.08 22	99.13 53	88.17 84	99.93 41	99.11 31	99.06 82	97.47 239

DVP-MVS		98.07 7	98.00 6	98.29 19	99.66 12	95.20 32	99.72 34	97.47 157	93.95 62	99.07 23	99.46 10	93.18 23	99.97 21	99.64 8	99.82 19	99.69 60
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									93.01 89	99.07 23	99.46 10	94.66 13	99.97 21	99.25 23	99.82 19	99.95 15

TSAR-MVS + MP.		97.44 18	97.46 17	97.39 54	99.12 67	93.49 76	98.52 200	97.50 152	94.46 52	98.99 25	98.64 114	91.58 33	99.08 165	98.49 51	99.83 15	99.60 77
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_s_conf0.1_n_a		95.16 106	95.15 98	95.18 184	92.06 353	88.94 212	99.29 95	97.53 143	94.46 52	98.98 26	98.99 74	79.99 234	99.85 78	98.24 62	96.86 160	96.73 265

PS-MVSNAJ		96.87 34	96.40 51	98.29 19	97.35 141	97.29 5	99.03 137	97.11 201	95.83 28	98.97 27	99.14 51	82.48 203	99.60 118	98.60 44	99.08 79	98.00 220

旧先验2							98.67 177		85.75 304	98.96 28			98.97 171	93.84 166

test_one_0601					99.59 28	94.89 37		97.64 118	93.14 88	98.93 29	99.45 14	93.45 18

fmvsm_s_conf0.5_n		96.19 62	96.49 47	95.30 179	97.37 140	89.16 200	99.86 7	98.47 26	95.68 32	98.87 30	99.15 48	82.44 207	99.92 44	99.14 29	97.43 146	96.83 261

xiu_mvs_v2_base		96.66 43	96.17 63	98.11 28	97.11 161	96.96 6	99.01 140	97.04 208	95.51 36	98.86 31	99.11 60	82.19 211	99.36 145	98.59 46	98.14 128	98.00 220

NCCC		98.12 5	98.11 3	98.13 25	99.76 6	94.46 53	99.81 18	97.88 63	96.54 20	98.84 32	99.46 10	92.55 28	99.98 9	98.25 61	99.93 1	99.94 18

SD-MVS		97.51 16	97.40 19	97.81 36	99.01 74	93.79 69	99.33 93	97.38 172	93.73 74	98.83 33	99.02 72	90.87 44	99.88 64	98.69 41	99.74 29	99.77 46
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
fmvsm_s_conf0.1_n_2		95.24 104	95.04 104	95.83 149	95.60 228	91.71 122	99.65 47	96.18 272	96.99 13	98.79 34	98.91 89	73.91 295	99.87 68	99.00 35	96.30 171	95.91 287

MVS_0304		97.81 9	97.51 15	98.74 9	98.97 75	96.57 11	99.91 3	98.17 39	97.45 4	98.76 35	98.97 76	86.69 119	99.96 28	99.72 3	98.92 92	99.69 60

fmvsm_s_conf0.5_n_5		96.46 54	96.23 57	97.15 67	96.42 189	92.80 95	99.83 13	97.39 171	94.50 50	98.71 36	99.13 53	82.52 200	99.90 55	99.24 25	98.38 122	98.74 168

SF-MVS		97.22 23	96.92 27	98.12 27	99.11 68	94.88 38	99.44 75	97.45 160	89.60 187	98.70 37	99.42 17	90.42 52	99.72 104	98.47 52	99.65 40	99.77 46

balanced_conf03		96.83 35	96.51 46	97.81 36	97.60 127	95.15 34	98.40 218	96.77 226	93.00 91	98.69 38	96.19 249	89.75 63	98.76 181	98.45 53	99.72 32	99.51 87

fmvsm_s_conf0.1_n		95.56 93	95.68 82	95.20 183	94.35 294	89.10 202	99.50 64	97.67 108	94.76 47	98.68 39	99.03 70	81.13 227	99.86 74	98.63 43	97.36 148	96.63 267

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 23	99.29 95	97.72 92	94.50 50	98.64 40	99.54 3	93.32 20	99.97 21	99.58 12	99.90 7	99.95 15
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
lecture		96.67 42	96.77 38	96.39 114	99.27 57	89.71 188	99.65 47	98.62 22	92.28 109	98.62 41	99.07 63	86.74 116	99.79 96	97.83 71	98.82 97	99.66 66

MSP-MVS		97.77 10	98.18 2	96.53 106	99.54 36	90.14 167	99.41 82	97.70 97	95.46 37	98.60 42	99.19 38	95.71 5	99.49 127	98.15 63	99.85 13	99.95 15
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
9.14			96.87 31		99.34 50		99.50 64	97.49 154	89.41 196	98.59 43	99.43 16	89.78 62	99.69 106	98.69 41	99.62 46

APD-MVS		96.95 32	96.72 40	97.63 42	99.51 41	93.58 71	99.16 112	97.44 164	90.08 172	98.59 43	99.07 63	89.06 69	99.42 138	97.92 66	99.66 39	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_vis1_n_1920		93.08 180	93.42 150	92.04 287	96.31 196	79.36 384	99.83 13	96.06 283	96.72 16	98.53 45	98.10 146	58.57 396	99.91 51	97.86 68	98.79 103	96.85 260

testdata				95.26 181	98.20 103	87.28 257		97.60 127	85.21 310	98.48 46	99.15 48	88.15 86	98.72 186	90.29 215	99.45 59	99.78 41

fmvsm_s_conf0.5_n_7		95.87 77	96.25 56	94.72 205	96.19 204	87.74 240	99.66 45	97.94 59	95.78 29	98.44 47	99.23 29	81.26 226	99.90 55	99.17 28	98.57 114	96.52 274

test_fmvsmconf_n		96.78 38	96.84 33	96.61 99	95.99 215	90.25 161	99.90 4	98.13 45	96.68 18	98.42 48	98.92 88	85.34 151	99.88 64	99.12 30	99.08 79	99.70 57

TEST9					99.57 33	93.17 83	99.38 85	97.66 109	89.57 189	98.39 49	99.18 41	90.88 43	99.66 109

train_agg		97.20 24	97.08 24	97.57 46	99.57 33	93.17 83	99.38 85	97.66 109	90.18 167	98.39 49	99.18 41	90.94 39	99.66 109	98.58 47	99.85 13	99.88 26

test_8					99.55 35	93.07 86	99.37 88	97.64 118	90.18 167	98.36 51	99.19 38	90.94 39	99.64 115

SPE-MVS-test		95.98 70	96.34 54	94.90 196	98.06 109	87.66 244	99.69 44	96.10 278	93.66 76	98.35 52	99.05 68	86.28 131	97.66 264	96.96 88	98.90 94	99.37 101

MM		97.76 11	97.39 20	98.86 5	98.30 99	96.83 7	99.81 18	99.13 9	97.66 2	98.29 53	98.96 81	85.84 140	99.90 55	99.72 3	98.80 100	99.85 30

HPM-MVS++		97.72 12	97.59 13	98.14 24	99.53 40	94.76 45	99.19 106	97.75 87	95.66 33	98.21 54	99.29 23	91.10 36	99.99 5	97.68 72	99.87 9	99.68 62

DPM-MVS		97.86 8	97.25 23	99.68 1	98.25 100	99.10 1	99.76 30	97.78 84	96.61 19	98.15 55	99.53 7	93.62 17	100.00 1	91.79 198	99.80 26	99.94 18

test_part2					99.54 36	95.42 22				98.13 56

SteuartSystems-ACMMP		97.25 20	97.34 21	97.01 71	97.38 139	91.46 127	99.75 32	97.66 109	94.14 61	98.13 56	99.26 24	92.16 32	99.66 109	97.91 67	99.64 42	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
FOURS1					99.50 42	88.94 212	99.55 57	97.47 157	91.32 132	98.12 58

test_prior2							99.57 55		91.43 128	98.12 58	98.97 76	90.43 51		98.33 57	99.81 23

CS-MVS		95.75 86	96.19 58	94.40 217	97.88 115	86.22 282	99.66 45	96.12 277	92.69 99	98.07 60	98.89 93	87.09 107	97.59 270	96.71 93	98.62 109	99.39 100

PHI-MVS		96.65 46	96.46 50	97.21 63	99.34 50	91.77 119	99.70 37	98.05 50	86.48 289	98.05 61	99.20 35	89.33 67	99.96 28	98.38 54	99.62 46	99.90 22

MVSFormer		94.71 124	94.08 125	96.61 99	95.05 267	94.87 39	97.77 274	96.17 274	86.84 277	98.04 62	98.52 122	85.52 142	95.99 353	89.83 218	98.97 88	98.96 138

lupinMVS		96.32 58	95.94 69	97.44 48	95.05 267	94.87 39	99.86 7	96.50 245	93.82 72	98.04 62	98.77 100	85.52 142	98.09 222	96.98 87	98.97 88	99.37 101

APDe-MVS		97.53 15	97.47 16	97.70 40	99.58 30	93.63 70	99.56 56	97.52 147	93.59 79	98.01 64	99.12 56	90.80 45	99.55 121	99.26 21	99.79 27	99.93 20
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMP_NAP		96.59 47	96.18 60	97.81 36	98.82 87	93.55 73	98.88 153	97.59 131	90.66 147	97.98 65	99.14 51	86.59 122	100.00 1	96.47 102	99.46 57	99.89 25

agg_prior					99.54 36	92.66 98		97.64 118		97.98 65			99.61 117

CDPH-MVS		96.56 51	96.18 60	97.70 40	99.59 28	93.92 65	99.13 125	97.44 164	89.02 204	97.90 67	99.22 31	88.90 74	99.49 127	94.63 151	99.79 27	99.68 62

MVSMamba_PlusPlus		95.73 89	95.15 98	97.44 48	97.28 147	94.35 59	98.26 235	96.75 227	83.09 349	97.84 68	95.97 257	89.59 65	98.48 199	97.86 68	99.73 31	99.49 90

EPNet		96.82 36	96.68 42	97.25 62	98.65 92	93.10 85	99.48 66	98.76 14	96.54 20	97.84 68	98.22 141	87.49 96	99.66 109	95.35 131	97.78 136	99.00 134
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		97.50 17	97.45 18	97.63 42	99.65 16	93.21 81	99.70 37	98.13 45	94.61 48	97.78 70	99.46 10	89.85 61	99.81 90	97.97 65	99.91 6	99.88 26

test12				97.83 35	99.33 53	94.45 54		97.55 138		97.56 71		88.60 78	99.50 126		99.71 36	99.55 82

xiu_mvs_v1_base_debu		94.73 121	93.98 128	96.99 73	95.19 249	95.24 27	98.62 184	96.50 245	92.99 92	97.52 72	98.83 97	72.37 310	99.15 158	97.03 84	96.74 161	96.58 270

xiu_mvs_v1_base		94.73 121	93.98 128	96.99 73	95.19 249	95.24 27	98.62 184	96.50 245	92.99 92	97.52 72	98.83 97	72.37 310	99.15 158	97.03 84	96.74 161	96.58 270

xiu_mvs_v1_base_debi		94.73 121	93.98 128	96.99 73	95.19 249	95.24 27	98.62 184	96.50 245	92.99 92	97.52 72	98.83 97	72.37 310	99.15 158	97.03 84	96.74 161	96.58 270

ZD-MVS					99.67 10	93.28 79		97.61 125	87.78 253	97.41 75	99.16 44	90.15 58	99.56 120	98.35 56	99.70 37

ETV-MVS		96.00 68	96.00 68	96.00 140	96.56 181	91.05 139	99.63 50	96.61 235	93.26 86	97.39 76	98.30 138	86.62 121	98.13 219	98.07 64	97.57 140	98.82 157

DeepPCF-MVS	93.56 1	96.55 52	97.84 10	92.68 274	98.71 91	78.11 398	99.70 37	97.71 96	98.18 1	97.36 77	99.76 1	90.37 54	99.94 35	99.27 20	99.54 54	99.99 1

test_vis1_n		90.40 246	90.27 232	90.79 314	91.55 365	76.48 407	99.12 127	94.44 384	94.31 55	97.34 78	96.95 211	43.60 439	99.42 138	97.57 74	97.60 139	96.47 276

EC-MVSNet		95.09 108	95.17 97	94.84 199	95.42 236	88.17 231	99.48 66	95.92 299	91.47 126	97.34 78	98.36 135	82.77 193	97.41 281	97.24 81	98.58 113	98.94 143

test_fmvsmconf0.1_n		95.94 74	95.79 79	96.40 113	92.42 346	89.92 178	99.79 25	96.85 220	96.53 22	97.22 80	98.67 112	82.71 197	99.84 80	98.92 38	98.98 87	99.43 97

CANet		97.00 31	96.49 47	98.55 12	98.86 86	96.10 16	99.83 13	97.52 147	95.90 27	97.21 81	98.90 91	82.66 199	99.93 41	98.71 40	98.80 100	99.63 74

CANet_DTU		94.31 135	93.35 152	97.20 64	97.03 167	94.71 48	98.62 184	95.54 337	95.61 34	97.21 81	98.47 131	71.88 315	99.84 80	88.38 240	97.46 145	97.04 255

test_cas_vis1_n_1920		93.86 151	93.74 142	94.22 228	95.39 239	86.08 292	99.73 33	96.07 282	96.38 24	97.19 83	97.78 155	65.46 368	99.86 74	96.71 93	98.92 92	96.73 265

VNet		95.08 109	94.26 117	97.55 47	98.07 108	93.88 66	98.68 175	98.73 17	90.33 162	97.16 84	97.43 178	79.19 245	99.53 124	96.91 90	91.85 249	99.24 114

GDP-MVS		96.05 67	95.63 87	97.31 57	95.37 241	94.65 50	99.36 89	96.42 250	92.14 114	97.07 85	98.53 120	93.33 19	98.50 194	91.76 199	96.66 164	98.78 162

region2R		96.30 59	96.17 63	96.70 93	99.70 7	90.31 160	99.46 72	97.66 109	90.55 155	97.07 85	99.07 63	86.85 113	99.97 21	95.43 129	99.74 29	99.81 35

原ACMM1				96.18 128	99.03 73	90.08 170		97.63 122	88.98 205	97.00 87	98.97 76	88.14 87	99.71 105	88.23 242	99.62 46	98.76 166

reproduce_model		96.57 50	96.75 39	96.02 138	98.93 82	88.46 228	98.56 196	97.34 178	93.18 87	96.96 88	99.35 21	88.69 77	99.80 92	98.53 48	99.21 77	99.79 38

HFP-MVS		96.42 55	96.26 55	96.90 81	99.69 8	90.96 142	99.47 68	97.81 77	90.54 156	96.88 89	99.05 68	87.57 94	99.96 28	95.65 121	99.72 32	99.78 41

XVS		96.47 53	96.37 52	96.77 86	99.62 22	90.66 151	99.43 79	97.58 133	92.41 106	96.86 90	98.96 81	87.37 99	99.87 68	95.65 121	99.43 61	99.78 41

X-MVStestdata		90.69 238	88.66 267	96.77 86	99.62 22	90.66 151	99.43 79	97.58 133	92.41 106	96.86 90	29.59 466	87.37 99	99.87 68	95.65 121	99.43 61	99.78 41

SR-MVS		96.13 64	96.16 65	96.07 135	99.42 47	89.04 204	98.59 192	97.33 179	90.44 159	96.84 92	99.12 56	86.75 115	99.41 141	97.47 75	99.44 60	99.76 48

TSAR-MVS + GP.		96.95 32	96.91 29	97.07 68	98.88 85	91.62 123	99.58 54	96.54 243	95.09 42	96.84 92	98.63 116	91.16 34	99.77 100	99.04 33	96.42 167	99.81 35

ACMMPR		96.28 60	96.14 67	96.73 90	99.68 9	90.47 156	99.47 68	97.80 79	90.54 156	96.83 94	99.03 70	86.51 127	99.95 32	95.65 121	99.72 32	99.75 49

test_fmvs1		92.35 195	92.94 166	90.57 319	97.19 152	75.43 413	99.55 57	94.97 368	95.20 40	96.82 95	97.57 171	59.59 394	99.84 80	97.30 79	98.29 127	96.46 277

PMMVS		93.62 160	93.90 137	92.79 268	96.79 176	81.40 365	98.85 154	96.81 222	91.25 134	96.82 95	98.15 145	77.02 268	98.13 219	93.15 182	96.30 171	98.83 156

reproduce-ours		96.66 43	96.80 36	96.22 124	98.95 79	89.03 206	98.62 184	97.38 172	93.42 81	96.80 97	99.36 19	88.92 72	99.80 92	98.51 49	99.26 71	99.82 32

our_new_method		96.66 43	96.80 36	96.22 124	98.95 79	89.03 206	98.62 184	97.38 172	93.42 81	96.80 97	99.36 19	88.92 72	99.80 92	98.51 49	99.26 71	99.82 32

PGM-MVS		95.85 79	95.65 85	96.45 109	99.50 42	89.77 186	98.22 238	98.90 13	89.19 199	96.74 99	98.95 84	85.91 139	99.92 44	93.94 163	99.46 57	99.66 66

jason		95.40 99	94.86 107	97.03 70	92.91 340	94.23 60	99.70 37	96.30 260	93.56 80	96.73 100	98.52 122	81.46 222	97.91 238	96.08 113	98.47 120	98.96 138
jason: jason.
新几何1				97.40 53	98.92 83	92.51 105		97.77 86	85.52 306	96.69 101	99.06 66	88.08 88	99.89 62	84.88 287	99.62 46	99.79 38

SR-MVS-dyc-post		95.75 86	95.86 72	95.41 171	99.22 61	87.26 260	98.40 218	97.21 188	89.63 184	96.67 102	98.97 76	86.73 118	99.36 145	96.62 96	99.31 67	99.60 77

RE-MVS-def			95.70 81		99.22 61	87.26 260	98.40 218	97.21 188	89.63 184	96.67 102	98.97 76	85.24 154		96.62 96	99.31 67	99.60 77

APD-MVS_3200maxsize		95.64 92	95.65 85	95.62 163	99.24 60	87.80 239	98.42 213	97.22 187	88.93 209	96.64 104	98.98 75	85.49 145	99.36 145	96.68 95	99.27 70	99.70 57

mvsany_test1		94.57 129	95.09 102	92.98 262	95.84 220	82.07 359	98.76 166	95.24 358	92.87 97	96.45 105	98.71 109	84.81 160	99.15 158	97.68 72	95.49 189	97.73 227

MG-MVS		97.24 21	96.83 35	98.47 15	99.79 5	95.71 19	99.07 131	99.06 10	94.45 54	96.42 106	98.70 110	88.81 75	99.74 103	95.35 131	99.86 12	99.97 7

BP-MVS1		96.59 47	96.36 53	97.29 58	95.05 267	94.72 47	99.44 75	97.45 160	92.71 98	96.41 107	98.50 124	94.11 16	98.50 194	95.61 126	97.97 130	98.66 181

test_fmvs1_n		91.07 228	91.41 204	90.06 333	94.10 303	74.31 417	99.18 108	94.84 372	94.81 45	96.37 108	97.46 176	50.86 428	99.82 87	97.14 83	97.90 131	96.04 284

NormalMVS		95.87 77	95.83 73	95.99 141	99.27 57	90.37 157	99.14 120	96.39 252	94.92 43	96.30 109	97.98 148	85.33 152	99.23 153	94.35 156	98.82 97	98.37 199

SymmetryMVS		95.49 94	95.27 94	96.17 130	97.13 158	90.37 157	99.14 120	98.59 23	94.92 43	96.30 109	97.98 148	85.33 152	99.23 153	94.35 156	93.67 216	98.92 146

h-mvs33		92.47 194	91.95 191	94.05 236	97.13 158	85.01 318	98.36 227	98.08 47	93.85 70	96.27 111	96.73 231	83.19 183	99.43 137	95.81 119	68.09 413	97.70 231

hse-mvs2		91.67 214	91.51 202	92.15 284	96.22 200	82.61 355	97.74 278	97.53 143	93.85 70	96.27 111	96.15 250	83.19 183	97.44 279	95.81 119	66.86 420	96.40 279

alignmvs		95.77 84	95.00 105	98.06 29	97.35 141	95.68 20	99.71 36	97.50 152	91.50 125	96.16 113	98.61 118	86.28 131	99.00 168	96.19 106	91.74 251	99.51 87

CP-MVS		96.22 61	96.15 66	96.42 111	99.67 10	89.62 191	99.70 37	97.61 125	90.07 173	96.00 114	99.16 44	87.43 97	99.92 44	96.03 115	99.72 32	99.70 57

MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 10	99.70 37	97.98 57	97.18 9	95.96 115	99.33 22	92.62 27	100.00 1	98.99 36	99.93 1	99.98 6

diffmvs		94.59 128	94.19 120	95.81 150	95.54 232	90.69 149	98.70 173	95.68 328	91.61 121	95.96 115	97.81 152	80.11 233	98.06 227	96.52 101	95.76 183	98.67 178
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GST-MVS		95.97 71	95.66 83	96.90 81	99.49 45	91.22 129	99.45 74	97.48 155	89.69 182	95.89 117	98.72 106	86.37 130	99.95 32	94.62 152	99.22 74	99.52 85

DeepC-MVS_fast	93.52 2	97.16 25	96.84 33	98.13 25	99.61 24	94.45 54	98.85 154	97.64 118	96.51 23	95.88 118	99.39 18	87.35 103	99.99 5	96.61 98	99.69 38	99.96 10
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test222					98.32 98	91.21 130	98.08 256	97.58 133	83.74 337	95.87 119	99.02 72	86.74 116			99.64 42	99.81 35

sasdasda		95.02 110	93.96 131	98.20 21	97.53 131	95.92 17	98.71 170	96.19 270	91.78 118	95.86 120	98.49 127	79.53 240	99.03 166	96.12 110	91.42 263	99.66 66

ZNCC-MVS		96.09 65	95.81 77	96.95 79	99.42 47	91.19 131	99.55 57	97.53 143	89.72 181	95.86 120	98.94 87	86.59 122	99.97 21	95.13 137	99.56 52	99.68 62

canonicalmvs		95.02 110	93.96 131	98.20 21	97.53 131	95.92 17	98.71 170	96.19 270	91.78 118	95.86 120	98.49 127	79.53 240	99.03 166	96.12 110	91.42 263	99.66 66

diffmvs_AUTHOR		94.30 136	93.92 134	95.45 168	94.77 281	89.92 178	98.55 199	95.68 328	91.33 131	95.83 123	97.64 166	79.58 237	98.05 230	96.19 106	95.66 186	98.37 199

dcpmvs_2		95.67 91	96.18 60	94.12 232	98.82 87	84.22 329	97.37 299	95.45 344	90.70 146	95.77 124	98.63 116	90.47 50	98.68 188	99.20 27	99.22 74	99.45 94

MGCFI-Net		94.89 112	93.84 139	98.06 29	97.49 134	95.55 21	98.64 181	96.10 278	91.60 123	95.75 125	98.46 133	79.31 244	98.98 170	95.95 117	91.24 268	99.65 70

Effi-MVS+		93.87 150	93.15 159	96.02 138	95.79 221	90.76 147	96.70 330	95.78 315	86.98 274	95.71 126	97.17 196	79.58 237	98.01 234	94.57 153	96.09 178	99.31 108

HPM-MVS_fast		94.89 112	94.62 110	95.70 155	99.11 68	88.44 229	99.14 120	97.11 201	85.82 301	95.69 127	98.47 131	83.46 176	99.32 150	93.16 181	99.63 45	99.35 104

HY-MVS	88.56 7	95.29 101	94.23 118	98.48 14	97.72 119	96.41 13	94.03 389	98.74 15	92.42 105	95.65 128	94.76 283	86.52 126	99.49 127	95.29 134	92.97 222	99.53 84

CHOSEN 280x420		96.80 37	96.85 32	96.66 97	97.85 116	94.42 56	94.76 378	98.36 31	92.50 102	95.62 129	97.52 172	97.92 1	97.38 282	98.31 59	98.80 100	98.20 213

test_fmvsmconf0.01_n		94.14 140	93.51 148	96.04 136	86.79 423	89.19 198	99.28 98	95.94 293	95.70 30	95.50 130	98.49 127	73.27 301	99.79 96	98.28 60	98.32 126	99.15 121

MP-MVS		96.00 68	95.82 75	96.54 105	99.47 46	90.13 169	99.36 89	97.41 168	90.64 150	95.49 131	98.95 84	85.51 144	99.98 9	96.00 116	99.59 51	99.52 85
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS		95.41 98	95.22 96	95.99 141	99.29 55	89.14 201	99.17 111	97.09 205	87.28 267	95.40 132	98.48 130	84.93 157	99.38 143	95.64 125	99.65 40	99.47 93
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UA-Net		93.30 170	92.62 174	95.34 174	96.27 198	88.53 227	95.88 359	96.97 216	90.90 141	95.37 133	97.07 203	82.38 208	99.10 164	83.91 304	94.86 197	98.38 195

sss		94.85 117	93.94 133	97.58 44	96.43 188	94.09 64	98.93 147	99.16 8	89.50 192	95.27 134	97.85 150	81.50 220	99.65 113	92.79 188	94.02 208	98.99 135

WTY-MVS		95.97 71	95.11 101	98.54 13	97.62 124	96.65 9	99.44 75	98.74 15	92.25 110	95.21 135	98.46 133	86.56 124	99.46 133	95.00 142	92.69 226	99.50 89

DELS-MVS		97.12 26	96.60 44	98.68 11	98.03 110	96.57 11	99.84 12	97.84 68	96.36 25	95.20 136	98.24 140	88.17 84	99.83 84	96.11 112	99.60 50	99.64 71
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
MVS_111021_HR		96.69 41	96.69 41	96.72 92	98.58 94	91.00 141	99.14 120	99.45 1	93.86 69	95.15 137	98.73 104	88.48 79	99.76 101	97.23 82	99.56 52	99.40 98

MVS_Test		93.67 158	92.67 171	96.69 94	96.72 178	92.66 98	97.22 307	96.03 284	87.69 259	95.12 138	94.03 291	81.55 218	98.28 207	89.17 234	96.46 165	99.14 122

MVS_111021_LR		95.78 83	95.94 69	95.28 180	98.19 105	87.69 241	98.80 160	99.26 7	93.39 83	95.04 139	98.69 111	84.09 168	99.76 101	96.96 88	99.06 82	98.38 195

CostFormer		92.89 184	92.48 177	94.12 232	94.99 270	85.89 299	92.89 401	97.00 214	86.98 274	95.00 140	90.78 362	90.05 60	97.51 275	92.92 186	91.73 252	98.96 138

testing222		94.48 132	94.00 127	95.95 144	97.30 144	92.27 109	98.82 157	97.92 61	89.20 198	94.82 141	97.26 186	87.13 106	97.32 285	91.95 196	91.56 255	98.25 207

mPP-MVS		95.90 76	95.75 80	96.38 115	99.58 30	89.41 195	99.26 101	97.41 168	90.66 147	94.82 141	98.95 84	86.15 135	99.98 9	95.24 136	99.64 42	99.74 50

EI-MVSNet-Vis-set		95.76 85	95.63 87	96.17 130	99.14 66	90.33 159	98.49 206	97.82 73	91.92 116	94.75 143	98.88 95	87.06 109	99.48 131	95.40 130	97.17 153	98.70 176

LFMVS		92.23 201	90.84 221	96.42 111	98.24 102	91.08 138	98.24 237	96.22 266	83.39 344	94.74 144	98.31 137	61.12 389	98.85 175	94.45 154	92.82 223	99.32 107

tpmrst		92.78 185	92.16 184	94.65 207	96.27 198	87.45 251	91.83 411	97.10 204	89.10 203	94.68 145	90.69 366	88.22 83	97.73 261	89.78 221	91.80 250	98.77 164

test_yl		95.27 102	94.60 111	97.28 60	98.53 95	92.98 89	99.05 135	98.70 18	86.76 281	94.65 146	97.74 159	87.78 91	99.44 134	95.57 127	92.61 227	99.44 95

DCV-MVSNet		95.27 102	94.60 111	97.28 60	98.53 95	92.98 89	99.05 135	98.70 18	86.76 281	94.65 146	97.74 159	87.78 91	99.44 134	95.57 127	92.61 227	99.44 95

testing11		95.33 100	94.98 106	96.37 116	97.20 150	92.31 108	99.29 95	97.68 103	90.59 152	94.43 148	97.20 192	90.79 46	98.60 191	95.25 135	92.38 236	98.18 214

DP-MVS Recon		95.85 79	95.15 98	97.95 32	99.87 2	94.38 57	99.60 52	97.48 155	86.58 284	94.42 149	99.13 53	87.36 102	99.98 9	93.64 170	98.33 124	99.48 91

ETVMVS		94.50 131	93.90 137	96.31 121	97.48 135	92.98 89	99.07 131	97.86 65	88.09 242	94.40 150	96.90 218	88.35 81	97.28 286	90.72 212	92.25 242	98.66 181

MTAPA		96.09 65	95.80 78	96.96 78	99.29 55	91.19 131	97.23 306	97.45 160	92.58 100	94.39 151	99.24 28	86.43 129	99.99 5	96.22 105	99.40 64	99.71 55

UBG		95.73 89	95.41 89	96.69 94	96.97 168	93.23 80	99.13 125	97.79 81	91.28 133	94.38 152	96.78 228	92.37 30	98.56 193	96.17 108	93.84 210	98.26 206

CPTT-MVS		94.60 127	94.43 115	95.09 188	99.66 12	86.85 265	99.44 75	97.47 157	83.22 346	94.34 153	98.96 81	82.50 201	99.55 121	94.81 146	99.50 55	98.88 149

PVSNet_BlendedMVS		93.36 168	93.20 158	93.84 244	98.77 89	91.61 124	99.47 68	98.04 52	91.44 127	94.21 154	92.63 325	83.50 174	99.87 68	97.41 76	83.37 321	90.05 390

PVSNet_Blended		95.94 74	95.66 83	96.75 88	98.77 89	91.61 124	99.88 5	98.04 52	93.64 78	94.21 154	97.76 157	83.50 174	99.87 68	97.41 76	97.75 137	98.79 160

EI-MVSNet-UG-set		95.43 96	95.29 93	95.86 148	99.07 72	89.87 180	98.43 212	97.80 79	91.78 118	94.11 156	98.77 100	86.25 133	99.48 131	94.95 144	96.45 166	98.22 211

EIA-MVS		95.11 107	95.27 94	94.64 209	96.34 195	86.51 271	99.59 53	96.62 234	92.51 101	94.08 157	98.64 114	86.05 136	98.24 210	95.07 139	98.50 117	99.18 119

mvsmamba		94.27 137	93.91 136	95.35 173	96.42 189	88.61 223	97.77 274	96.38 255	91.17 137	94.05 158	95.27 275	78.41 257	97.96 237	97.36 78	98.40 121	99.48 91

MAR-MVS		94.43 133	94.09 124	95.45 168	99.10 70	87.47 250	98.39 223	97.79 81	88.37 231	94.02 159	99.17 43	78.64 255	99.91 51	92.48 190	98.85 96	98.96 138
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
KinetiMVS		93.07 181	91.98 189	96.34 118	94.84 278	91.78 118	98.73 169	97.18 193	91.25 134	94.01 160	97.09 202	71.02 323	98.86 174	86.77 262	96.89 159	98.37 199

PAPM		96.35 56	95.94 69	97.58 44	94.10 303	95.25 26	98.93 147	98.17 39	94.26 56	93.94 161	98.72 106	89.68 64	97.88 242	96.36 103	99.29 69	99.62 76

myMVS_eth3d28		95.74 88	95.34 91	96.92 80	97.41 136	93.58 71	99.28 98	97.70 97	90.97 140	93.91 162	97.25 188	90.59 48	98.75 182	96.85 92	94.14 206	98.44 190

GG-mvs-BLEND				96.98 76	96.53 183	94.81 44	87.20 432	97.74 88		93.91 162	96.40 242	96.56 2	96.94 299	95.08 138	98.95 91	99.20 118

API-MVS		94.78 119	94.18 122	96.59 101	99.21 63	90.06 174	98.80 160	97.78 84	83.59 341	93.85 164	99.21 34	83.79 171	99.97 21	92.37 192	99.00 86	99.74 50

tpm2		91.77 212	91.09 211	93.82 245	94.83 279	85.56 307	92.51 406	97.16 196	84.00 332	93.83 165	90.66 368	87.54 95	97.17 288	87.73 248	91.55 256	98.72 174

PAPR		96.35 56	95.82 75	97.94 33	99.63 18	94.19 62	99.42 81	97.55 138	92.43 103	93.82 166	99.12 56	87.30 104	99.91 51	94.02 162	99.06 82	99.74 50

testing99		94.88 114	94.45 113	96.17 130	97.20 150	91.91 115	99.20 105	97.66 109	89.95 175	93.68 167	97.06 204	90.28 56	98.50 194	93.52 172	91.54 257	98.12 217

testing91		94.88 114	94.44 114	96.21 126	97.19 152	91.90 116	99.23 103	97.66 109	89.91 176	93.66 168	97.05 206	90.21 57	98.50 194	93.52 172	91.53 260	98.25 207

PVSNet	87.13 12	93.69 155	92.83 168	96.28 123	97.99 111	90.22 164	99.38 85	98.93 12	91.42 129	93.66 168	97.68 163	71.29 322	99.64 115	87.94 246	97.20 150	98.98 136

viewmanbaseed2359cas		93.90 148	93.34 153	95.56 166	95.39 239	89.72 187	98.58 194	96.00 285	90.32 163	93.58 170	97.78 155	78.71 253	98.07 225	94.43 155	95.29 191	98.88 149

baseline		93.91 147	93.30 155	95.72 154	95.10 264	90.07 171	97.48 293	95.91 304	91.03 138	93.54 171	97.68 163	79.58 237	98.02 233	94.27 159	95.14 194	99.08 130

test2506		94.80 118	94.21 119	96.58 102	96.41 191	92.18 111	98.01 259	98.96 11	90.82 144	93.46 172	97.28 184	85.92 137	98.45 200	89.82 220	97.19 151	99.12 125

viewmambaseed2359dif		93.05 182	92.64 172	94.25 225	94.94 273	86.53 270	98.38 225	95.69 327	87.03 270	93.38 173	97.74 159	78.79 251	98.08 224	93.49 175	94.35 204	98.15 216

VDD-MVS		91.24 226	90.18 233	94.45 216	97.08 163	85.84 302	98.40 218	96.10 278	86.99 271	93.36 174	98.16 144	54.27 415	99.20 155	96.59 99	90.63 274	98.31 205

VDDNet		90.08 258	88.54 273	94.69 206	94.41 293	87.68 242	98.21 240	96.40 251	76.21 409	93.33 175	97.75 158	54.93 413	98.77 179	94.71 150	90.96 269	97.61 237

thisisatest0515		94.75 120	94.19 120	96.43 110	96.13 211	92.64 101	99.47 68	97.60 127	87.55 262	93.17 176	97.59 169	94.71 12	98.42 201	88.28 241	93.20 219	98.24 210

MP-MVS-pluss		95.80 82	95.30 92	97.29 58	98.95 79	92.66 98	98.59 192	97.14 197	88.95 207	93.12 177	99.25 26	85.62 141	99.94 35	96.56 100	99.48 56	99.28 111
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MDTV_nov1_ep13_2view						91.17 133	91.38 418		87.45 264	93.08 178		86.67 120		87.02 254		98.95 142

LuminaMVS		93.16 177	92.30 180	95.76 152	92.26 348	92.64 101	97.60 291	96.21 267	90.30 164	93.06 179	95.59 267	76.00 271	97.89 240	94.93 145	94.70 198	96.76 262

EPNet_dtu		92.28 199	92.15 185	92.70 273	97.29 145	84.84 321	98.64 181	97.82 73	92.91 95	93.02 180	97.02 207	85.48 147	95.70 368	72.25 397	94.89 196	97.55 238
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
guyue		94.21 139	93.72 143	95.66 158	95.22 246	90.17 166	98.74 167	96.85 220	93.67 75	93.01 181	96.72 232	78.83 249	98.06 227	96.04 114	94.44 201	98.77 164

gg-mvs-nofinetune		90.00 259	87.71 285	96.89 85	96.15 206	94.69 49	85.15 439	97.74 88	68.32 437	92.97 182	60.16 454	96.10 4	96.84 302	93.89 164	98.87 95	99.14 122

AstraMVS		93.38 167	93.01 163	94.50 212	93.94 311	86.55 269	98.91 150	95.86 311	93.88 68	92.88 183	97.49 174	75.61 280	98.21 214	96.15 109	92.39 235	98.73 173

viewmacassd2359aftdt		93.16 177	92.44 178	95.31 177	94.34 295	89.19 198	98.40 218	95.84 313	89.62 186	92.87 184	97.31 183	76.07 270	98.00 235	92.93 184	94.58 199	98.75 167

testing3-2		95.17 105	94.78 108	96.33 120	97.35 141	92.35 107	99.85 10	98.43 28	90.60 151	92.84 185	97.00 208	90.89 42	98.89 173	95.95 117	90.12 277	97.76 225

test_fmvsmvis_n_1920		95.47 95	95.40 90	95.70 155	94.33 296	90.22 164	99.70 37	96.98 215	96.80 14	92.75 186	98.89 93	82.46 206	99.92 44	98.36 55	98.33 124	96.97 258

casdiffmvs		93.98 145	93.43 149	95.61 164	95.07 266	89.86 181	98.80 160	95.84 313	90.98 139	92.74 187	97.66 165	79.71 236	98.10 221	94.72 149	95.37 190	98.87 152
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
RRT-MVS		93.39 165	92.64 172	95.64 159	96.11 212	88.75 220	97.40 295	95.77 317	89.46 194	92.70 188	95.42 272	72.98 304	98.81 177	96.91 90	96.97 156	99.37 101

114514_t		94.06 141	93.05 161	97.06 69	99.08 71	92.26 110	98.97 145	97.01 213	82.58 361	92.57 189	98.22 141	80.68 230	99.30 151	89.34 228	99.02 85	99.63 74

OMC-MVS		93.90 148	93.62 145	94.73 204	98.63 93	87.00 263	98.04 258	96.56 241	92.19 111	92.46 190	98.73 104	79.49 242	99.14 162	92.16 194	94.34 205	98.03 219

PAPM_NR		95.43 96	95.05 103	96.57 104	99.42 47	90.14 167	98.58 194	97.51 149	90.65 149	92.44 191	98.90 91	87.77 93	99.90 55	90.88 207	99.32 66	99.68 62

mmtdpeth		83.69 362	82.59 361	86.99 383	92.82 342	76.98 406	96.16 351	91.63 426	82.89 358	92.41 192	82.90 430	54.95 412	98.19 216	96.27 104	53.27 448	85.81 430

UGNet		91.91 210	90.85 220	95.10 187	97.06 164	88.69 222	98.01 259	98.24 36	92.41 106	92.39 193	93.61 305	60.52 391	99.68 107	88.14 243	97.25 149	96.92 259
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
MDTV_nov1_ep13			90.47 231		96.14 208	88.55 225	91.34 419	97.51 149	89.58 188	92.24 194	90.50 379	86.99 112	97.61 269	77.64 355	92.34 238

FE-MVS		91.38 221	90.16 234	95.05 192	96.46 187	87.53 248	89.69 429	97.84 68	82.97 352	92.18 195	92.00 335	84.07 169	98.93 172	80.71 334	95.52 188	98.68 177

Vis-MVSNet		92.64 188	91.85 193	95.03 193	95.12 256	88.23 230	98.48 208	96.81 222	91.61 121	92.16 196	97.22 191	71.58 320	98.00 235	85.85 278	97.81 133	98.88 149
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
FA-MVS(test-final)		92.22 202	91.08 212	95.64 159	96.05 213	88.98 209	91.60 415	97.25 182	86.99 271	91.84 197	92.12 329	83.03 186	99.00 168	86.91 258	93.91 209	98.93 144

TESTMET0.1,1		93.82 152	93.26 157	95.49 167	95.21 248	90.25 161	99.15 117	97.54 142	89.18 200	91.79 198	94.87 281	89.13 68	97.63 267	86.21 271	96.29 173	98.60 183

thisisatest0530		94.00 143	93.52 147	95.43 170	95.76 223	90.02 176	98.99 142	97.60 127	86.58 284	91.74 199	97.36 182	94.78 11	98.34 203	86.37 269	92.48 234	97.94 223

UWE-MVS		93.18 174	93.40 151	92.50 277	96.56 181	83.55 338	98.09 254	97.84 68	89.50 192	91.72 200	96.23 248	91.08 37	96.70 308	86.28 270	93.33 218	97.26 247

AUN-MVS		90.17 255	89.50 243	92.19 282	96.21 201	82.67 352	97.76 277	97.53 143	88.05 243	91.67 201	96.15 250	83.10 185	97.47 276	88.11 244	66.91 419	96.43 278

EPMVS		92.59 191	91.59 200	95.59 165	97.22 149	90.03 175	91.78 412	98.04 52	90.42 160	91.66 202	90.65 369	86.49 128	97.46 277	81.78 327	96.31 170	99.28 111

test-LLR		93.11 179	92.68 170	94.40 217	94.94 273	87.27 258	99.15 117	97.25 182	90.21 165	91.57 203	94.04 289	84.89 158	97.58 271	85.94 275	96.13 176	98.36 202

test-mter		93.27 172	92.89 167	94.40 217	94.94 273	87.27 258	99.15 117	97.25 182	88.95 207	91.57 203	94.04 289	88.03 89	97.58 271	85.94 275	96.13 176	98.36 202

JIA-IIPM		85.97 329	84.85 329	89.33 355	93.23 334	73.68 420	85.05 440	97.13 199	69.62 433	91.56 205	68.03 452	88.03 89	96.96 297	77.89 354	93.12 220	97.34 243

casdiffmvs_mvg		94.00 143	93.33 154	96.03 137	95.22 246	90.90 145	99.09 129	95.99 286	90.58 153	91.55 206	97.37 181	79.91 235	98.06 227	95.01 141	95.22 193	99.13 124
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		94.67 125	94.11 123	96.34 118	97.14 157	91.10 136	99.32 94	97.43 166	92.10 115	91.53 207	96.38 245	83.29 180	99.68 107	93.42 178	96.37 168	98.25 207

CHOSEN 1792x2688		94.35 134	93.82 140	95.95 144	97.40 137	88.74 221	98.41 215	98.27 33	92.18 112	91.43 208	96.40 242	78.88 246	99.81 90	93.59 171	97.81 133	99.30 109

ACMMP		94.67 125	94.30 116	95.79 151	99.25 59	88.13 233	98.41 215	98.67 21	90.38 161	91.43 208	98.72 106	82.22 210	99.95 32	93.83 167	95.76 183	99.29 110
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
ECVR-MVS		92.29 198	91.33 205	95.15 185	96.41 191	87.84 238	98.10 251	94.84 372	90.82 144	91.42 210	97.28 184	65.61 365	98.49 198	90.33 214	97.19 151	99.12 125

EPP-MVSNet		93.75 154	93.67 144	94.01 238	95.86 219	85.70 304	98.67 177	97.66 109	84.46 326	91.36 211	97.18 195	91.16 34	97.79 250	92.93 184	93.75 214	98.53 185

PLC	91.07 3	94.23 138	94.01 126	94.87 197	99.17 65	87.49 249	99.25 102	96.55 242	88.43 229	91.26 212	98.21 143	85.92 137	99.86 74	89.77 222	97.57 140	97.24 248
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HyFIR lowres test		93.68 157	93.29 156	94.87 197	97.57 130	88.04 235	98.18 242	98.47 26	87.57 261	91.24 213	95.05 279	85.49 145	97.46 277	93.22 180	92.82 223	99.10 128

thres200		93.69 155	92.59 175	96.97 77	97.76 118	94.74 46	99.35 91	99.36 2	89.23 197	91.21 214	96.97 210	83.42 177	98.77 179	85.08 283	90.96 269	97.39 242

test1111		92.12 203	91.19 209	94.94 195	96.15 206	87.36 254	98.12 248	94.84 372	90.85 143	90.97 215	97.26 186	65.60 366	98.37 202	89.74 223	97.14 154	99.07 132

CDS-MVSNet		93.47 161	93.04 162	94.76 201	94.75 282	89.45 194	98.82 157	97.03 210	87.91 249	90.97 215	96.48 240	89.06 69	96.36 327	89.50 224	92.81 225	98.49 188
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tfpn200view9		93.43 163	92.27 182	96.90 81	97.68 121	94.84 41	99.18 108	99.36 2	88.45 226	90.79 217	96.90 218	83.31 178	98.75 182	84.11 300	90.69 271	97.12 250

thres400		93.39 165	92.27 182	96.73 90	97.68 121	94.84 41	99.18 108	99.36 2	88.45 226	90.79 217	96.90 218	83.31 178	98.75 182	84.11 300	90.69 271	96.61 268

CR-MVSNet		88.83 279	87.38 290	93.16 259	93.47 327	86.24 280	84.97 441	94.20 393	88.92 210	90.76 219	86.88 417	84.43 164	94.82 391	70.64 401	92.17 244	98.41 192

RPMNet		85.07 344	81.88 363	94.64 209	93.47 327	86.24 280	84.97 441	97.21 188	64.85 444	90.76 219	78.80 445	80.95 229	99.27 152	53.76 446	92.17 244	98.41 192

PatchmatchNet		92.05 207	91.04 213	95.06 190	96.17 205	89.04 204	91.26 420	97.26 181	89.56 190	90.64 221	90.56 375	88.35 81	97.11 291	79.53 340	96.07 180	99.03 133
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Elysia		90.62 242	88.95 258	95.64 159	93.08 337	91.94 113	97.65 286	96.39 252	84.72 322	90.59 222	95.95 258	62.22 382	98.23 212	83.69 307	96.23 174	96.74 263

StellarMVS		90.62 242	88.95 258	95.64 159	93.08 337	91.94 113	97.65 286	96.39 252	84.72 322	90.59 222	95.95 258	62.22 382	98.23 212	83.69 307	96.23 174	96.74 263

tttt0517		93.30 170	93.01 163	94.17 230	95.57 230	86.47 273	98.51 203	97.60 127	85.99 297	90.55 224	97.19 194	94.80 10	98.31 204	85.06 284	91.86 248	97.74 226

PatchT		85.44 339	83.19 350	92.22 280	93.13 336	83.00 344	83.80 447	96.37 256	70.62 427	90.55 224	79.63 444	84.81 160	94.87 389	58.18 442	91.59 254	98.79 160

tpm		89.67 264	88.95 258	91.82 291	92.54 344	81.43 364	92.95 400	95.92 299	87.81 252	90.50 226	89.44 396	84.99 156	95.65 369	83.67 309	82.71 326	98.38 195

thres100view900		93.34 169	92.15 185	96.90 81	97.62 124	94.84 41	99.06 134	99.36 2	87.96 247	90.47 227	96.78 228	83.29 180	98.75 182	84.11 300	90.69 271	97.12 250

thres600view7		93.18 174	92.00 188	96.75 88	97.62 124	94.92 36	99.07 131	99.36 2	87.96 247	90.47 227	96.78 228	83.29 180	98.71 187	82.93 316	90.47 275	96.61 268

AdaColmap		93.82 152	93.06 160	96.10 134	99.88 1	89.07 203	98.33 229	97.55 138	86.81 279	90.39 229	98.65 113	75.09 282	99.98 9	93.32 179	97.53 143	99.26 113

XVG-OURS-SEG-HR		90.95 232	90.66 227	91.83 290	95.18 252	81.14 372	95.92 356	95.92 299	88.40 230	90.33 230	97.85 150	70.66 326	99.38 143	92.83 187	88.83 282	94.98 294

SSM_0404		92.33 196	91.33 205	95.33 176	95.35 242	90.54 154	97.45 294	95.49 340	86.17 293	90.26 231	97.13 198	75.65 277	97.82 246	89.26 232	95.26 192	97.63 235

IS-MVSNet		93.00 183	92.51 176	94.49 213	96.14 208	87.36 254	98.31 232	95.70 325	88.58 222	90.17 232	97.50 173	83.02 187	97.22 287	87.06 253	96.07 180	98.90 148

CSCG		94.87 116	94.71 109	95.36 172	99.54 36	86.49 272	99.34 92	98.15 43	82.71 359	90.15 233	99.25 26	89.48 66	99.86 74	94.97 143	98.82 97	99.72 54

viewmsd2359difaftdt		90.43 245	89.65 240	92.74 271	93.72 322	82.67 352	98.09 254	95.27 354	89.80 180	90.12 234	97.40 180	69.43 334	98.20 215	92.45 191	80.62 335	97.34 243

SCA		90.64 241	89.25 250	94.83 200	94.95 272	88.83 216	96.26 345	97.21 188	90.06 174	90.03 235	90.62 371	66.61 357	96.81 304	83.16 312	94.36 203	98.84 153

XVG-OURS		90.83 234	90.49 229	91.86 289	95.23 245	81.25 369	95.79 364	95.92 299	88.96 206	90.02 236	98.03 147	71.60 319	99.35 148	91.06 204	87.78 286	94.98 294

IMVS_0403		91.93 209	91.13 210	94.34 220	94.61 287	86.22 282	96.70 330	95.72 320	88.78 213	90.00 237	96.93 214	78.07 260	98.07 225	86.73 263	92.59 229	98.74 168

ADS-MVSNet2		87.62 304	86.88 299	89.86 339	96.21 201	79.14 387	87.15 433	92.99 407	83.01 350	89.91 238	87.27 413	78.87 247	92.80 416	74.20 381	92.27 240	97.64 232

ADS-MVSNet		88.99 272	87.30 291	94.07 234	96.21 201	87.56 247	87.15 433	96.78 225	83.01 350	89.91 238	87.27 413	78.87 247	97.01 296	74.20 381	92.27 240	97.64 232

mamv4		91.41 219	93.57 146	84.91 402	97.11 161	58.11 449	95.68 368	95.93 297	82.09 371	89.78 240	95.71 265	90.09 59	98.24 210	97.26 80	98.50 117	98.38 195

icg_test_0407_2		91.56 215	90.90 219	93.54 250	94.61 287	86.22 282	95.72 366	95.72 320	88.78 213	89.76 241	96.93 214	77.24 266	95.65 369	86.73 263	92.59 229	98.74 168

IMVS_0407		91.79 211	90.98 215	94.24 227	94.61 287	86.22 282	96.45 337	95.72 320	88.78 213	89.76 241	96.93 214	77.24 266	97.77 252	86.73 263	92.59 229	98.74 168

ab-mvs		91.05 230	89.17 251	96.69 94	95.96 216	91.72 121	92.62 405	97.23 186	85.61 305	89.74 243	93.89 298	68.55 339	99.42 138	91.09 203	87.84 285	98.92 146

TAMVS		92.62 189	92.09 187	94.20 229	94.10 303	87.68 242	98.41 215	96.97 216	87.53 263	89.74 243	96.04 255	84.77 162	96.49 320	88.97 236	92.31 239	98.42 191

Vis-MVSNet (Re-imp)		93.26 173	93.00 165	94.06 235	96.14 208	86.71 268	98.68 175	96.70 229	88.30 235	89.71 245	97.64 166	85.43 148	96.39 325	88.06 245	96.32 169	99.08 130

mamba_0408		90.65 240	89.16 252	95.12 186	95.12 256	89.81 183	83.02 448	95.17 365	85.95 298	89.50 246	96.85 222	75.85 273	97.82 246	87.19 251	93.79 211	97.73 227

SSM_04072		90.31 249	89.16 252	93.74 247	95.12 256	89.81 183	83.02 448	95.17 365	85.95 298	89.50 246	96.85 222	75.85 273	93.69 405	87.19 251	93.79 211	97.73 227

SSM_0407		92.04 208	91.03 214	95.07 189	95.12 256	89.81 183	97.18 310	95.49 340	86.17 293	89.50 246	97.13 198	75.65 277	97.68 262	89.26 232	93.79 211	97.73 227

CNLPA		93.64 159	92.74 169	96.36 117	98.96 78	90.01 177	99.19 106	95.89 307	86.22 292	89.40 249	98.85 96	80.66 231	99.84 80	88.57 238	96.92 158	99.24 114

Anonymous202405211		88.84 277	87.03 297	94.27 223	98.14 107	84.18 330	98.44 211	95.58 335	76.79 407	89.34 250	96.88 221	53.42 419	99.54 123	87.53 250	87.12 289	99.09 129

Fast-Effi-MVS+		91.72 213	90.79 224	94.49 213	95.89 217	87.40 253	99.54 62	95.70 325	85.01 317	89.28 251	95.68 266	77.75 262	97.57 274	83.22 311	95.06 195	98.51 186

PatchMatch-RL		91.47 217	90.54 228	94.26 224	98.20 103	86.36 278	96.94 318	97.14 197	87.75 255	88.98 252	95.75 264	71.80 317	99.40 142	80.92 332	97.39 147	97.02 256

dp		90.16 256	88.83 263	94.14 231	96.38 194	86.42 274	91.57 416	97.06 207	84.76 321	88.81 253	90.19 387	84.29 166	97.43 280	75.05 373	91.35 266	98.56 184

UWE-MVS-28		90.99 231	91.93 192	88.15 369	95.12 256	77.87 401	97.18 310	97.79 81	88.72 218	88.69 254	96.52 237	86.54 125	90.75 432	84.64 291	92.16 246	95.83 288

DeepC-MVS	91.02 4	94.56 130	93.92 134	96.46 108	97.16 156	90.76 147	98.39 223	97.11 201	93.92 64	88.66 255	98.33 136	78.14 259	99.85 78	95.02 140	98.57 114	98.78 162
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline1		92.61 190	91.28 207	96.58 102	97.05 166	94.63 51	97.72 279	96.20 268	89.82 178	88.56 256	96.85 222	86.85 113	97.82 246	88.42 239	80.10 339	97.30 245

Anonymous20240529		87.66 303	85.58 317	93.92 241	97.59 128	85.01 318	98.13 246	97.13 199	66.69 442	88.47 257	96.01 256	55.09 411	99.51 125	87.00 255	84.12 312	97.23 249

CVMVSNet		90.30 250	90.91 218	88.46 368	94.32 297	73.58 421	97.61 289	97.59 131	90.16 170	88.43 258	97.10 200	76.83 269	92.86 413	82.64 318	93.54 217	98.93 144

TR-MVS		90.77 235	89.44 245	94.76 201	96.31 196	88.02 236	97.92 263	95.96 290	85.52 306	88.22 259	97.23 190	66.80 356	98.09 222	84.58 292	92.38 236	98.17 215

F-COLMAP		92.07 206	91.75 198	93.02 261	98.16 106	82.89 348	98.79 164	95.97 288	86.54 286	87.92 260	97.80 153	78.69 254	99.65 113	85.97 273	95.93 182	96.53 273

WB-MVSnew		88.69 285	88.34 275	89.77 343	94.30 301	85.99 297	98.14 245	97.31 180	87.15 269	87.85 261	96.07 254	69.91 327	95.52 373	72.83 393	91.47 261	87.80 416

BH-RMVSNet		91.25 225	89.99 235	95.03 193	96.75 177	88.55 225	98.65 179	94.95 369	87.74 256	87.74 262	97.80 153	68.27 342	98.14 218	80.53 337	97.49 144	98.41 192

Effi-MVS+-dtu		89.97 260	90.68 226	87.81 373	95.15 253	71.98 428	97.87 267	95.40 348	91.92 116	87.57 263	91.44 348	74.27 291	96.84 302	89.45 225	93.10 221	94.60 297

HQP-NCC					93.95 308		99.16 112		93.92 64	87.57 263

ACMP_Plane					93.95 308		99.16 112		93.92 64	87.57 263

HQP4-MVS										87.57 263			97.77 252			92.72 307

HQP-MVS		91.50 216	91.23 208	92.29 279	93.95 308	86.39 276	99.16 112	96.37 256	93.92 64	87.57 263	96.67 235	73.34 298	97.77 252	93.82 168	86.29 293	92.72 307

TAPA-MVS	87.50 9	90.35 247	89.05 256	94.25 225	98.48 97	85.17 315	98.42 213	96.58 240	82.44 366	87.24 268	98.53 120	82.77 193	98.84 176	59.09 440	97.88 132	98.72 174
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		90.60 244	89.56 242	93.72 249	95.10 264	85.43 308	99.41 82	94.94 370	83.96 334	87.21 269	96.83 227	74.37 289	97.05 295	80.50 338	93.73 215	98.67 178

HQP_MVS		91.26 223	90.95 217	92.16 283	93.84 316	86.07 294	99.02 138	96.30 260	93.38 84	86.99 270	96.52 237	72.92 305	97.75 259	93.46 176	86.17 296	92.67 309

plane_prior3						85.91 298			93.65 77	86.99 270

GA-MVS		90.10 257	88.69 266	94.33 221	92.44 345	87.97 237	99.08 130	96.26 264	89.65 183	86.92 272	93.11 317	68.09 344	96.96 297	82.54 320	90.15 276	98.05 218

1112_ss		92.71 186	91.55 201	96.20 127	95.56 231	91.12 134	98.48 208	94.69 379	88.29 236	86.89 273	98.50 124	87.02 110	98.66 189	84.75 288	89.77 280	98.81 158

Test_1112_low_res		92.27 200	90.97 216	96.18 128	95.53 233	91.10 136	98.47 210	94.66 380	88.28 237	86.83 274	93.50 309	87.00 111	98.65 190	84.69 289	89.74 281	98.80 159

cascas		90.93 233	89.33 248	95.76 152	95.69 225	93.03 88	98.99 142	96.59 237	80.49 387	86.79 275	94.45 286	65.23 370	98.60 191	93.52 172	92.18 243	95.66 290

baseline2		94.04 142	93.80 141	94.74 203	93.07 339	90.25 161	98.12 248	98.16 42	89.86 177	86.53 276	96.95 211	95.56 6	98.05 230	91.44 201	94.53 200	95.93 286

OPM-MVS		89.76 263	89.15 254	91.57 298	90.53 378	85.58 306	98.11 250	95.93 297	92.88 96	86.05 277	96.47 241	67.06 355	97.87 243	89.29 231	86.08 298	91.26 357
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPA-MVSNet		89.10 271	87.66 286	93.45 253	92.56 343	91.02 140	97.97 262	98.32 32	86.92 276	86.03 278	92.01 333	68.84 338	97.10 293	90.92 206	75.34 365	92.23 319

MonoMVSNet		90.69 238	89.78 238	93.45 253	91.78 361	84.97 320	96.51 335	94.44 384	90.56 154	85.96 279	90.97 358	78.61 256	96.27 340	95.35 131	83.79 317	99.11 127

SDMVSNet		91.09 227	89.91 236	94.65 207	96.80 174	90.54 154	97.78 272	97.81 77	88.34 233	85.73 280	95.26 276	66.44 360	98.26 208	94.25 160	86.75 290	95.14 291

sd_testset		89.23 269	88.05 282	92.74 271	96.80 174	85.33 311	95.85 362	97.03 210	88.34 233	85.73 280	95.26 276	61.12 389	97.76 258	85.61 279	86.75 290	95.14 291

tpm cat1		88.89 275	87.27 292	93.76 246	95.79 221	85.32 312	90.76 425	97.09 205	76.14 410	85.72 282	88.59 402	82.92 188	98.04 232	76.96 359	91.43 262	97.90 224

IB-MVS	89.43 6	92.12 203	90.83 223	95.98 143	95.40 238	90.78 146	99.81 18	98.06 49	91.23 136	85.63 283	93.66 304	90.63 47	98.78 178	91.22 202	71.85 402	98.36 202
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
EI-MVSNet		89.87 261	89.38 247	91.36 301	94.32 297	85.87 300	97.61 289	96.59 237	85.10 312	85.51 284	97.10 200	81.30 225	96.56 314	83.85 306	83.03 323	91.64 336

MVSTER		92.71 186	92.32 179	93.86 243	97.29 145	92.95 92	99.01 140	96.59 237	90.09 171	85.51 284	94.00 293	94.61 15	96.56 314	90.77 211	83.03 323	92.08 327

test_fmvs2		85.10 343	85.45 320	84.02 408	89.85 386	65.63 442	98.49 206	92.59 412	90.45 158	85.43 286	93.32 310	43.94 437	96.59 312	90.81 209	84.19 311	89.85 394

RPSCF		85.33 340	85.55 318	84.67 405	94.63 286	62.28 444	93.73 391	93.76 398	74.38 418	85.23 287	97.06 204	64.09 373	98.31 204	80.98 330	86.08 298	93.41 303

BH-w/o		92.32 197	91.79 196	93.91 242	96.85 171	86.18 288	99.11 128	95.74 319	88.13 240	84.81 288	97.00 208	77.26 265	97.91 238	89.16 235	98.03 129	97.64 232

CLD-MVS		91.06 229	90.71 225	92.10 285	94.05 307	86.10 291	99.55 57	96.29 263	94.16 59	84.70 289	97.17 196	69.62 332	97.82 246	94.74 148	86.08 298	92.39 312
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tpmvs		89.16 270	87.76 283	93.35 255	97.19 152	84.75 323	90.58 427	97.36 176	81.99 372	84.56 290	89.31 399	83.98 170	98.17 217	74.85 376	90.00 279	97.12 250

nrg030		90.23 251	88.87 261	94.32 222	91.53 366	93.54 74	98.79 164	95.89 307	88.12 241	84.55 291	94.61 285	78.80 250	96.88 301	92.35 193	75.21 366	92.53 311

VPNet		88.30 291	86.57 302	93.49 251	91.95 356	91.35 128	98.18 242	97.20 192	88.61 220	84.52 292	94.89 280	62.21 384	96.76 307	89.34 228	72.26 399	92.36 313

dmvs_re		88.69 285	88.06 281	90.59 318	93.83 318	78.68 391	95.75 365	96.18 272	87.99 246	84.48 293	96.32 246	67.52 350	96.94 299	84.98 286	85.49 302	96.14 282

MVS		93.92 146	92.28 181	98.83 7	95.69 225	96.82 8	96.22 348	98.17 39	84.89 319	84.34 294	98.61 118	79.32 243	99.83 84	93.88 165	99.43 61	99.86 29

mvs_anonymous		92.50 193	91.65 199	95.06 190	96.60 180	89.64 190	97.06 314	96.44 249	86.64 283	84.14 295	93.93 296	82.49 202	96.17 345	91.47 200	96.08 179	99.35 104

Fast-Effi-MVS+-dtu		88.84 277	88.59 270	89.58 348	93.44 330	78.18 395	98.65 179	94.62 381	88.46 225	84.12 296	95.37 274	68.91 336	96.52 317	82.06 324	91.70 253	94.06 298

LS3D		90.19 253	88.72 265	94.59 211	98.97 75	86.33 279	96.90 320	96.60 236	74.96 415	84.06 297	98.74 103	75.78 276	99.83 84	74.93 374	97.57 140	97.62 236

ACMM	86.95 13	88.77 282	88.22 278	90.43 324	93.61 323	81.34 367	98.50 204	95.92 299	87.88 250	83.85 298	95.20 278	67.20 353	97.89 240	86.90 259	84.90 305	92.06 328
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
BH-untuned		91.46 218	90.84 221	93.33 256	96.51 185	84.83 322	98.84 156	95.50 339	86.44 291	83.50 299	96.70 233	75.49 281	97.77 252	86.78 261	97.81 133	97.40 241

FIs		90.70 237	89.87 237	93.18 258	92.29 347	91.12 134	98.17 244	98.25 34	89.11 202	83.44 300	94.82 282	82.26 209	96.17 345	87.76 247	82.76 325	92.25 317

UniMVSNet (Re)		89.50 268	88.32 276	93.03 260	92.21 350	90.96 142	98.90 152	98.39 29	89.13 201	83.22 301	92.03 331	81.69 217	96.34 333	86.79 260	72.53 395	91.81 332

UniMVSNet_NR-MVSNet		89.60 265	88.55 272	92.75 270	92.17 351	90.07 171	98.74 167	98.15 43	88.37 231	83.21 302	93.98 294	82.86 189	95.93 357	86.95 256	72.47 396	92.25 317

DU-MVS		88.83 279	87.51 287	92.79 268	91.46 367	90.07 171	98.71 170	97.62 124	88.87 211	83.21 302	93.68 302	74.63 283	95.93 357	86.95 256	72.47 396	92.36 313

LPG-MVS_test		88.86 276	88.47 274	90.06 333	93.35 332	80.95 374	98.22 238	95.94 293	87.73 257	83.17 304	96.11 252	66.28 361	97.77 252	90.19 216	85.19 303	91.46 347

LGP-MVS_train				90.06 333	93.35 332	80.95 374		95.94 293	87.73 257	83.17 304	96.11 252	66.28 361	97.77 252	90.19 216	85.19 303	91.46 347

miper_enhance_ethall		90.33 248	89.70 239	92.22 280	97.12 160	88.93 214	98.35 228	95.96 290	88.60 221	83.14 306	92.33 328	87.38 98	96.18 343	86.49 268	77.89 349	91.55 344

WBMVS		91.35 222	90.49 229	93.94 240	96.97 168	93.40 78	99.27 100	96.71 228	87.40 265	83.10 307	91.76 341	92.38 29	96.23 341	88.95 237	77.89 349	92.17 323

FC-MVSNet-test		90.22 252	89.40 246	92.67 275	91.78 361	89.86 181	97.89 264	98.22 37	88.81 212	82.96 308	94.66 284	81.90 216	95.96 355	85.89 277	82.52 328	92.20 322

PCF-MVS	89.78 5	91.26 223	89.63 241	96.16 133	95.44 235	91.58 126	95.29 372	96.10 278	85.07 314	82.75 309	97.45 177	78.28 258	99.78 99	80.60 336	95.65 187	97.12 250
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
V42		87.00 310	85.68 316	90.98 308	89.91 383	86.08 292	98.32 231	95.61 333	83.67 340	82.72 310	90.67 367	74.00 294	96.53 316	81.94 326	74.28 378	90.32 383

v1144		86.83 313	85.31 322	91.40 299	89.75 387	87.21 262	98.31 232	95.45 344	83.22 346	82.70 311	90.78 362	73.36 297	96.36 327	79.49 341	74.69 372	90.63 378

Syy-MVS		84.10 360	84.53 337	82.83 414	95.14 254	65.71 441	97.68 282	96.66 231	86.52 287	82.63 312	96.84 225	68.15 343	89.89 437	45.62 452	91.54 257	92.87 305

myMVS_eth3d		88.68 287	89.07 255	87.50 377	95.14 254	79.74 382	97.68 282	96.66 231	86.52 287	82.63 312	96.84 225	85.22 155	89.89 437	69.43 407	91.54 257	92.87 305

v144192		86.40 323	84.89 328	90.91 309	89.48 393	85.59 305	98.21 240	95.43 347	82.45 365	82.62 314	90.58 374	72.79 308	96.36 327	78.45 351	74.04 382	90.79 370

3Dnovator	87.35 11	93.17 176	91.77 197	97.37 55	95.41 237	93.07 86	98.82 157	97.85 66	91.53 124	82.56 315	97.58 170	71.97 314	99.82 87	91.01 205	99.23 73	99.22 117

v2v482		87.27 308	85.76 314	91.78 296	89.59 389	87.58 246	98.56 196	95.54 337	84.53 325	82.51 316	91.78 339	73.11 302	96.47 321	82.07 323	74.14 381	91.30 355

tt0805		86.50 322	84.79 331	91.63 297	91.97 354	81.49 363	96.49 336	97.38 172	82.24 368	82.44 317	95.82 263	51.22 425	98.25 209	84.55 293	80.96 334	95.13 293

Baseline_NR-MVSNet		85.83 332	84.82 330	88.87 365	88.73 401	83.34 341	98.63 183	91.66 425	80.41 390	82.44 317	91.35 350	74.63 283	95.42 378	84.13 299	71.39 405	87.84 414

v1192		86.32 325	84.71 333	91.17 303	89.53 392	86.40 275	98.13 246	95.44 346	82.52 363	82.42 319	90.62 371	71.58 320	96.33 334	77.23 356	74.88 369	90.79 370

test_djsdf		88.26 293	87.73 284	89.84 340	88.05 410	82.21 357	97.77 274	96.17 274	86.84 277	82.41 320	91.95 337	72.07 313	95.99 353	89.83 218	84.50 308	91.32 354

cl22		89.57 266	88.79 264	91.91 288	97.94 113	87.62 245	97.98 261	96.51 244	85.03 315	82.37 321	91.79 338	83.65 172	96.50 318	85.96 274	77.89 349	91.61 341

1314		93.44 162	91.98 189	97.84 34	95.24 244	94.38 57	96.22 348	97.92 61	90.18 167	82.28 322	97.71 162	77.63 263	99.80 92	91.94 197	98.67 107	99.34 106

v1921920		86.02 328	84.44 339	90.77 315	89.32 395	85.20 313	98.10 251	95.35 352	82.19 369	82.25 323	90.71 364	70.73 324	96.30 338	76.85 361	74.49 374	90.80 369

v1240		85.77 335	84.11 342	90.73 316	89.26 396	85.15 316	97.88 266	95.23 362	81.89 375	82.16 324	90.55 376	69.60 333	96.31 335	75.59 371	74.87 370	90.72 375

XVG-ACMP-BASELINE		85.86 331	84.95 327	88.57 366	89.90 384	77.12 405	94.30 383	95.60 334	87.40 265	82.12 325	92.99 320	53.42 419	97.66 264	85.02 285	83.83 314	90.92 366

GBi-Net		86.67 317	84.96 325	91.80 292	95.11 261	88.81 217	96.77 324	95.25 355	82.94 353	82.12 325	90.25 382	62.89 379	94.97 386	79.04 344	80.24 336	91.62 338

test1		86.67 317	84.96 325	91.80 292	95.11 261	88.81 217	96.77 324	95.25 355	82.94 353	82.12 325	90.25 382	62.89 379	94.97 386	79.04 344	80.24 336	91.62 338

FMVSNet3		88.81 281	87.08 295	93.99 239	96.52 184	94.59 52	98.08 256	96.20 268	85.85 300	82.12 325	91.60 344	74.05 293	95.40 379	79.04 344	80.24 336	91.99 330

VortexMVS		90.18 254	89.28 249	92.89 266	95.58 229	90.94 144	97.82 269	95.94 293	90.90 141	82.11 329	91.48 347	78.75 252	96.08 349	91.99 195	78.97 343	91.65 335

IterMVS-LS		88.34 290	87.44 288	91.04 306	94.10 303	85.85 301	98.10 251	95.48 342	85.12 311	82.03 330	91.21 354	81.35 224	95.63 371	83.86 305	75.73 363	91.63 337
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSC-MVS3.2		85.22 341	83.90 346	89.17 358	91.87 359	79.84 381	97.66 285	96.63 233	86.81 279	81.99 331	91.35 350	55.80 404	96.00 352	76.52 365	76.53 360	91.67 334

miper_ehance_all_eth		88.94 274	88.12 280	91.40 299	95.32 243	86.93 264	97.85 268	95.55 336	84.19 329	81.97 332	91.50 346	84.16 167	95.91 360	84.69 289	77.89 349	91.36 352

MIMVSNet		84.48 352	81.83 364	92.42 278	91.73 363	87.36 254	85.52 436	94.42 388	81.40 378	81.91 333	87.58 407	51.92 422	92.81 415	73.84 385	88.15 284	97.08 254

IMVS_0404		89.79 262	88.57 271	93.47 252	94.61 287	86.22 282	94.45 380	95.72 320	88.78 213	81.88 334	96.93 214	65.39 369	95.47 375	86.73 263	92.59 229	98.74 168

PS-MVSNAJss		89.54 267	89.05 256	91.00 307	88.77 400	84.36 327	97.39 296	95.97 288	88.47 223	81.88 334	93.80 300	82.48 203	96.50 318	89.34 228	83.34 322	92.15 324

WR-MVS		88.54 289	87.22 294	92.52 276	91.93 358	89.50 193	98.56 196	97.84 68	86.99 271	81.87 336	93.81 299	74.25 292	95.92 359	85.29 281	74.43 375	92.12 325

TranMVSNet+NR-MVSNet		87.75 299	86.31 306	92.07 286	90.81 375	88.56 224	98.33 229	97.18 193	87.76 254	81.87 336	93.90 297	72.45 309	95.43 377	83.13 314	71.30 406	92.23 319

eth_miper_zixun_eth		87.76 298	87.00 298	90.06 333	94.67 284	82.65 354	97.02 317	95.37 350	84.19 329	81.86 338	91.58 345	81.47 221	95.90 361	83.24 310	73.61 384	91.61 341

UniMVSNet_ETH3D		85.65 338	83.79 347	91.21 302	90.41 380	80.75 377	95.36 370	95.78 315	78.76 396	81.83 339	94.33 287	49.86 430	96.66 309	84.30 295	83.52 320	96.22 281

c3_l		88.19 294	87.23 293	91.06 305	94.97 271	86.17 289	97.72 279	95.38 349	83.43 343	81.68 340	91.37 349	82.81 192	95.72 367	84.04 303	73.70 383	91.29 356

DP-MVS		88.75 283	86.56 303	95.34 174	98.92 83	87.45 251	97.64 288	93.52 404	70.55 428	81.49 341	97.25 188	74.43 288	99.88 64	71.14 400	94.09 207	98.67 178

3Dnovator+	87.72 8	93.43 163	91.84 194	98.17 23	95.73 224	95.08 35	98.92 149	97.04 208	91.42 129	81.48 342	97.60 168	74.60 285	99.79 96	90.84 208	98.97 88	99.64 71

QAPM		91.41 219	89.49 244	97.17 66	95.66 227	93.42 77	98.60 190	97.51 149	80.92 385	81.39 343	97.41 179	72.89 307	99.87 68	82.33 321	98.68 106	98.21 212

testing3		87.75 299	88.22 278	86.36 388	94.66 285	77.41 403	99.52 63	97.95 58	86.05 296	81.12 344	96.69 234	86.18 134	89.31 441	61.65 434	90.12 277	92.35 316

XXY-MVS		87.75 299	86.02 310	92.95 265	90.46 379	89.70 189	97.71 281	95.90 305	84.02 331	80.95 345	94.05 288	67.51 351	97.10 293	85.16 282	78.41 346	92.04 329

v148		86.38 324	85.06 324	90.37 328	89.47 394	84.10 331	98.52 200	95.48 342	83.80 336	80.93 346	90.22 385	74.60 285	96.31 335	80.92 332	71.55 404	90.69 376

DIV-MVS_self_test		87.82 296	86.81 300	90.87 312	94.87 277	85.39 310	97.81 270	95.22 363	82.92 356	80.76 347	91.31 352	81.99 213	95.81 364	81.36 328	75.04 368	91.42 350

cl____		87.82 296	86.79 301	90.89 311	94.88 276	85.43 308	97.81 270	95.24 358	82.91 357	80.71 348	91.22 353	81.97 215	95.84 362	81.34 329	75.06 367	91.40 351

FMVSNet2		86.90 311	84.79 331	93.24 257	95.11 261	92.54 104	97.67 284	95.86 311	82.94 353	80.55 349	91.17 355	62.89 379	95.29 381	77.23 356	79.71 342	91.90 331

pmmvs4		87.58 305	86.17 309	91.80 292	89.58 390	88.92 215	97.25 304	95.28 353	82.54 362	80.49 350	93.17 316	75.62 279	96.05 351	82.75 317	78.90 344	90.42 381

SD_0403		86.82 314	87.08 295	86.04 392	93.55 325	69.09 437	94.11 388	95.02 367	87.84 251	80.48 351	95.86 262	73.05 303	91.04 431	72.53 395	91.26 267	97.99 222

reproduce_monomvs		92.11 205	91.82 195	92.98 262	98.25 100	90.55 153	98.38 225	97.93 60	94.81 45	80.46 352	92.37 327	96.46 3	97.17 288	94.06 161	73.61 384	91.23 358

ACMP	87.39 10	88.71 284	88.24 277	90.12 332	93.91 314	81.06 373	98.50 204	95.67 330	89.43 195	80.37 353	95.55 268	65.67 363	97.83 245	90.55 213	84.51 307	91.47 346
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
pmmvs5		85.87 330	84.40 341	90.30 329	88.53 404	84.23 328	98.60 190	93.71 400	81.53 377	80.29 354	92.02 332	64.51 372	95.52 373	82.04 325	78.34 347	91.15 360

test0.0.03 1		88.96 273	88.61 268	90.03 337	91.09 372	84.43 326	98.97 145	97.02 212	90.21 165	80.29 354	96.31 247	84.89 158	91.93 427	72.98 391	85.70 301	93.73 299

miper_lstm_enhance		86.90 311	86.20 308	89.00 362	94.53 291	81.19 370	96.74 328	95.24 358	82.33 367	80.15 356	90.51 378	81.99 213	94.68 395	80.71 334	73.58 386	91.12 361

jajsoiax		87.35 306	86.51 304	89.87 338	87.75 417	81.74 361	97.03 315	95.98 287	88.47 223	80.15 356	93.80 300	61.47 386	96.36 327	89.44 226	84.47 309	91.50 345

mvs_tets		87.09 309	86.22 307	89.71 344	87.87 413	81.39 366	96.73 329	95.90 305	88.19 239	79.99 358	93.61 305	59.96 393	96.31 335	89.40 227	84.34 310	91.43 349

ITE_SJBPF				87.93 371	92.26 348	76.44 408		93.47 405	87.67 260	79.95 359	95.49 271	56.50 403	97.38 282	75.24 372	82.33 329	89.98 392

v8		86.11 327	84.45 338	91.10 304	89.99 382	86.85 265	97.24 305	95.36 351	81.99 372	79.89 360	89.86 391	74.53 287	96.39 325	78.83 348	72.32 398	90.05 390

v10		85.73 336	84.01 344	90.87 312	90.03 381	86.73 267	97.20 308	95.22 363	81.25 380	79.85 361	89.75 392	73.30 300	96.28 339	76.87 360	72.64 394	89.61 398

WR-MVS_H		86.53 321	85.49 319	89.66 347	91.04 373	83.31 342	97.53 292	98.20 38	84.95 318	79.64 362	90.90 360	78.01 261	95.33 380	76.29 366	72.81 392	90.35 382

anonymousdsp		86.69 316	85.75 315	89.53 349	86.46 425	82.94 345	96.39 339	95.71 324	83.97 333	79.63 363	90.70 365	68.85 337	95.94 356	86.01 272	84.02 313	89.72 396

Patchmtry		83.61 365	81.64 365	89.50 350	93.36 331	82.84 350	84.10 444	94.20 393	69.47 434	79.57 364	86.88 417	84.43 164	94.78 392	68.48 413	74.30 377	90.88 367

CP-MVSNet		86.54 320	85.45 320	89.79 342	91.02 374	82.78 351	97.38 298	97.56 137	85.37 308	79.53 365	93.03 318	71.86 316	95.25 382	79.92 339	73.43 390	91.34 353

Patchmatch-test		86.25 326	84.06 343	92.82 267	94.42 292	82.88 349	82.88 450	94.23 392	71.58 424	79.39 366	90.62 371	89.00 71	96.42 324	63.03 430	91.37 265	99.16 120

DSMNet-mixed		81.60 374	81.43 368	82.10 417	84.36 432	60.79 445	93.63 393	86.74 450	79.00 392	79.32 367	87.15 415	63.87 375	89.78 439	66.89 419	91.92 247	95.73 289

MSDG		88.29 292	86.37 305	94.04 237	96.90 170	86.15 290	96.52 334	94.36 390	77.89 402	79.22 368	96.95 211	69.72 330	99.59 119	73.20 390	92.58 233	96.37 280

Anonymous20231211		84.72 347	82.65 359	90.91 309	97.71 120	84.55 325	97.28 302	96.67 230	66.88 441	79.18 369	90.87 361	58.47 397	96.60 311	82.61 319	74.20 379	91.59 343

PS-CasMVS		85.81 333	84.58 336	89.49 352	90.77 376	82.11 358	97.20 308	97.36 176	84.83 320	79.12 370	92.84 321	67.42 352	95.16 384	78.39 352	73.25 391	91.21 359

IterMVS		85.81 333	84.67 334	89.22 356	93.51 326	83.67 337	96.32 342	94.80 375	85.09 313	78.69 371	90.17 388	66.57 359	93.17 412	79.48 342	77.42 356	90.81 368
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PEN-MVS		85.21 342	83.93 345	89.07 361	89.89 385	81.31 368	97.09 313	97.24 185	84.45 327	78.66 372	92.68 324	68.44 341	94.87 389	75.98 368	70.92 407	91.04 363

IterMVS-SCA-FT		85.73 336	84.64 335	89.00 362	93.46 329	82.90 347	96.27 343	94.70 378	85.02 316	78.62 373	90.35 380	66.61 357	93.33 409	79.38 343	77.36 357	90.76 372

OpenMVS	85.28 14	90.75 236	88.84 262	96.48 107	93.58 324	93.51 75	98.80 160	97.41 168	82.59 360	78.62 373	97.49 174	68.00 346	99.82 87	84.52 294	98.55 116	96.11 283

PVSNet_0	83.28 16	87.31 307	85.16 323	93.74 247	94.78 280	84.59 324	98.91 150	98.69 20	89.81 179	78.59 375	93.23 314	61.95 385	99.34 149	94.75 147	55.72 445	97.30 245

EU-MVSNet		84.19 357	84.42 340	83.52 412	88.64 403	67.37 440	96.04 354	95.76 318	85.29 309	78.44 376	93.18 315	70.67 325	91.48 429	75.79 370	75.98 361	91.70 333

v7n		84.42 354	82.75 357	89.43 354	88.15 408	81.86 360	96.75 327	95.67 330	80.53 386	78.38 377	89.43 397	69.89 328	96.35 332	73.83 386	72.13 400	90.07 388

FMVSNet1		83.94 361	81.32 370	91.80 292	91.94 357	88.81 217	96.77 324	95.25 355	77.98 398	78.25 378	90.25 382	50.37 429	94.97 386	73.27 389	77.81 354	91.62 338

D2MVS		87.96 295	87.39 289	89.70 345	91.84 360	83.40 340	98.31 232	98.49 24	88.04 244	78.23 379	90.26 381	73.57 296	96.79 306	84.21 297	83.53 319	88.90 408

mvs5depth		78.17 394	75.56 397	85.97 393	80.43 445	76.44 408	85.46 437	89.24 444	76.39 408	78.17 380	88.26 403	51.73 423	95.73 366	69.31 408	61.09 434	85.73 431

MS-PatchMatch		86.75 315	85.92 312	89.22 356	91.97 354	82.47 356	96.91 319	96.14 276	83.74 337	77.73 381	93.53 308	58.19 398	97.37 284	76.75 362	98.35 123	87.84 414

DTE-MVSNet		84.14 358	82.80 354	88.14 370	88.95 399	79.87 380	96.81 323	96.24 265	83.50 342	77.60 382	92.52 326	67.89 348	94.24 400	72.64 394	69.05 411	90.32 383

COLMAP_ROB	82.69 18	84.54 351	82.82 353	89.70 345	96.72 178	78.85 388	95.89 357	92.83 410	71.55 425	77.54 383	95.89 261	59.40 395	99.14 162	67.26 417	88.26 283	91.11 362
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		84.13 359	83.59 348	85.77 396	87.81 414	70.24 433	94.89 376	93.65 402	86.08 295	76.53 384	93.28 313	61.41 387	96.14 347	80.95 331	77.69 355	90.93 365

sc_t1		78.53 392	74.87 402	89.48 353	87.92 412	77.36 404	94.80 377	90.61 436	57.65 447	76.28 385	89.59 395	38.25 446	96.18 343	74.04 383	64.72 426	94.91 296

tfpnnormal		83.65 363	81.35 369	90.56 321	91.37 369	88.06 234	97.29 301	97.87 64	78.51 397	76.20 386	90.91 359	64.78 371	96.47 321	61.71 433	73.50 387	87.13 423

ppachtmachnet_test		83.63 364	81.57 367	89.80 341	89.01 397	85.09 317	97.13 312	94.50 383	78.84 394	76.14 387	91.00 357	69.78 329	94.61 396	63.40 428	74.36 376	89.71 397

pm-mvs1		84.68 348	82.78 356	90.40 325	89.58 390	85.18 314	97.31 300	94.73 377	81.93 374	76.05 388	92.01 333	65.48 367	96.11 348	78.75 349	69.14 410	89.91 393

AllTest		84.97 345	83.12 351	90.52 322	96.82 172	78.84 389	95.89 357	92.17 417	77.96 400	75.94 389	95.50 269	55.48 407	99.18 156	71.15 398	87.14 287	93.55 301

TestCases				90.52 322	96.82 172	78.84 389		92.17 417	77.96 400	75.94 389	95.50 269	55.48 407	99.18 156	71.15 398	87.14 287	93.55 301

CL-MVSNet_self_test		79.89 383	78.34 384	84.54 406	81.56 441	75.01 414	96.88 321	95.62 332	81.10 381	75.86 391	85.81 422	68.49 340	90.26 435	63.21 429	56.51 443	88.35 411

testgi		82.29 369	81.00 372	86.17 390	87.24 420	74.84 416	97.39 296	91.62 427	88.63 219	75.85 392	95.42 272	46.07 436	91.55 428	66.87 420	79.94 340	92.12 325

MVP-Stereo		86.61 319	85.83 313	88.93 364	88.70 402	83.85 335	96.07 353	94.41 389	82.15 370	75.64 393	91.96 336	67.65 349	96.45 323	77.20 358	98.72 105	86.51 426
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LF4IMVS		81.94 372	81.17 371	84.25 407	87.23 421	68.87 439	93.35 397	91.93 422	83.35 345	75.40 394	93.00 319	49.25 433	96.65 310	78.88 347	78.11 348	87.22 422

our_test_3		84.47 353	82.80 354	89.50 350	89.01 397	83.90 334	97.03 315	94.56 382	81.33 379	75.36 395	90.52 377	71.69 318	94.54 397	68.81 411	76.84 358	90.07 388

LTVRE_ROB	81.71 19	84.59 350	82.72 358	90.18 330	92.89 341	83.18 343	93.15 398	94.74 376	78.99 393	75.14 396	92.69 323	65.64 364	97.63 267	69.46 406	81.82 331	89.74 395
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
ttmdpeth		79.80 384	77.91 386	85.47 398	83.34 436	75.75 410	95.32 371	91.45 430	76.84 406	74.81 397	91.71 342	53.98 417	94.13 401	72.42 396	61.29 433	86.51 426

Anonymous20231206		80.76 378	79.42 382	84.79 404	84.78 431	72.98 423	96.53 333	92.97 408	79.56 391	74.33 398	88.83 400	61.27 388	92.15 424	60.59 436	75.92 362	89.24 403

FMVSNet5		82.29 369	80.54 374	87.52 376	93.79 320	84.01 332	93.73 391	92.47 414	76.92 405	74.27 399	86.15 421	63.69 377	89.24 442	69.07 409	74.79 371	89.29 402

MVS-HIRNet		79.01 387	75.13 400	90.66 317	93.82 319	81.69 362	85.16 438	93.75 399	54.54 450	74.17 400	59.15 456	57.46 400	96.58 313	63.74 427	94.38 202	93.72 300

ACMH+	83.78 15	84.21 356	82.56 362	89.15 359	93.73 321	79.16 386	96.43 338	94.28 391	81.09 382	74.00 401	94.03 291	54.58 414	97.67 263	76.10 367	78.81 345	90.63 378

kuosan		84.40 355	83.34 349	87.60 375	95.87 218	79.21 385	92.39 407	96.87 219	76.12 411	73.79 402	93.98 294	81.51 219	90.63 433	64.13 426	75.42 364	92.95 304

KD-MVS_2432*1600		82.98 366	80.52 375	90.38 326	94.32 297	88.98 209	92.87 402	95.87 309	80.46 388	73.79 402	87.49 410	82.76 195	93.29 410	70.56 402	46.53 456	88.87 409

miper_refine_blended		82.98 366	80.52 375	90.38 326	94.32 297	88.98 209	92.87 402	95.87 309	80.46 388	73.79 402	87.49 410	82.76 195	93.29 410	70.56 402	46.53 456	88.87 409

NR-MVSNet		87.74 302	86.00 311	92.96 264	91.46 367	90.68 150	96.65 332	97.42 167	88.02 245	73.42 405	93.68 302	77.31 264	95.83 363	84.26 296	71.82 403	92.36 313

test_fmvs3		75.09 406	75.19 399	74.81 427	77.45 450	54.08 453	95.93 355	90.64 434	82.51 364	73.29 406	81.19 438	22.29 456	86.29 449	85.50 280	67.89 415	84.06 440

USDC		84.74 346	82.93 352	90.16 331	91.73 363	83.54 339	95.00 375	93.30 406	88.77 217	73.19 407	93.30 312	53.62 418	97.65 266	75.88 369	81.54 332	89.30 401

KD-MVS_self_test		77.47 398	75.88 396	82.24 415	81.59 440	68.93 438	92.83 404	94.02 396	77.03 404	73.14 408	83.39 429	55.44 409	90.42 434	67.95 414	57.53 442	87.38 418

LCM-MVSNet-Re		88.59 288	88.61 268	88.51 367	95.53 233	72.68 426	96.85 322	88.43 447	88.45 226	73.14 408	90.63 370	75.82 275	94.38 398	92.95 183	95.71 185	98.48 189

TDRefinement		78.01 395	75.31 398	86.10 391	70.06 457	73.84 419	93.59 394	91.58 428	74.51 417	73.08 410	91.04 356	49.63 432	97.12 290	74.88 375	59.47 438	87.33 420

TransMVSNet (Re)		81.97 371	79.61 381	89.08 360	89.70 388	84.01 332	97.26 303	91.85 423	78.84 394	73.07 411	91.62 343	67.17 354	95.21 383	67.50 416	59.46 439	88.02 413

SixPastTwentyTwo		82.63 368	81.58 366	85.79 395	88.12 409	71.01 431	95.17 373	92.54 413	84.33 328	72.93 412	92.08 330	60.41 392	95.61 372	74.47 378	74.15 380	90.75 373

pmmvs6		79.90 382	77.31 389	87.67 374	84.17 433	78.13 397	95.86 361	93.68 401	67.94 438	72.67 413	89.62 394	50.98 427	95.75 365	74.80 377	66.04 421	89.14 404

ACMH	83.09 17	84.60 349	82.61 360	90.57 319	93.18 335	82.94 345	96.27 343	94.92 371	81.01 383	72.61 414	93.61 305	56.54 402	97.79 250	74.31 379	81.07 333	90.99 364
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		78.63 391	76.90 392	83.82 409	82.82 438	72.86 424	95.72 366	93.57 403	73.55 422	72.17 415	84.79 426	49.69 431	92.51 420	65.29 424	74.50 373	86.09 429

tt0320		76.58 400	73.16 408	86.86 385	88.03 411	77.60 402	93.55 396	90.63 435	55.37 449	70.93 416	84.98 424	41.57 441	94.01 402	69.02 410	64.32 427	88.97 406

Patchmatch-RL test		81.90 373	80.13 377	87.23 380	80.71 443	70.12 435	84.07 445	88.19 448	83.16 348	70.57 417	82.18 435	87.18 105	92.59 418	82.28 322	62.78 429	98.98 136

mvsany_test3		75.85 405	74.52 404	79.83 422	73.53 454	60.64 446	91.73 413	87.87 449	83.91 335	70.55 418	82.52 432	31.12 451	93.66 406	86.66 267	62.83 428	85.19 438

test_0402		78.81 389	76.33 394	86.26 389	91.18 371	78.44 394	95.88 359	91.34 431	68.55 435	70.51 419	89.91 390	52.65 421	94.99 385	47.14 451	79.78 341	85.34 436

dongtai		81.36 375	80.61 373	83.62 411	94.25 302	73.32 422	95.15 374	96.81 222	73.56 421	69.79 420	92.81 322	81.00 228	86.80 448	52.08 449	70.06 409	90.75 373

TinyColmap		80.42 380	77.94 385	87.85 372	92.09 352	78.58 392	93.74 390	89.94 439	74.99 414	69.77 421	91.78 339	46.09 435	97.58 271	65.17 425	77.89 349	87.38 418

tt0320-xc		75.92 403	72.23 411	87.01 382	88.40 405	78.15 396	93.57 395	89.15 445	55.46 448	69.66 422	85.79 423	38.20 447	93.85 403	69.72 405	60.08 437	89.03 405

dmvs_testset		77.17 399	78.99 383	71.71 430	87.25 419	38.55 467	91.44 417	81.76 458	85.77 302	69.49 423	95.94 260	69.71 331	84.37 450	52.71 448	76.82 359	92.21 321

test20.03		78.51 393	77.48 388	81.62 419	83.07 437	71.03 430	96.11 352	92.83 410	81.66 376	69.31 424	89.68 393	57.53 399	87.29 447	58.65 441	68.47 412	86.53 425

test_vis1_rt		81.31 376	80.05 379	85.11 399	91.29 370	70.66 432	98.98 144	77.39 462	85.76 303	68.80 425	82.40 433	36.56 449	99.44 134	92.67 189	86.55 292	85.24 437

N_pmnet		70.19 412	69.87 414	71.12 432	88.24 407	30.63 471	95.85 362	28.70 470	70.18 430	68.73 426	86.55 419	64.04 374	93.81 404	53.12 447	73.46 388	88.94 407

OpenMVS_ROB	73.86 20	77.99 396	75.06 401	86.77 386	83.81 435	77.94 399	96.38 340	91.53 429	67.54 439	68.38 427	87.13 416	43.94 437	96.08 349	55.03 445	81.83 330	86.29 428

ambc				79.60 423	72.76 456	56.61 450	76.20 454	92.01 421		68.25 428	80.23 442	23.34 455	94.73 393	73.78 387	60.81 435	87.48 417

PM-MVS		74.88 407	72.85 409	80.98 421	78.98 448	64.75 443	90.81 424	85.77 451	80.95 384	68.23 429	82.81 431	29.08 453	92.84 414	76.54 364	62.46 431	85.36 435

pmmvs3		72.86 410	69.76 415	82.17 416	73.86 453	74.19 418	94.20 385	89.01 446	64.23 445	67.72 430	80.91 441	41.48 442	88.65 444	62.40 431	54.02 447	83.68 442

lessismore_v0				85.08 400	85.59 429	69.28 436		90.56 437		67.68 431	90.21 386	54.21 416	95.46 376	73.88 384	62.64 430	90.50 380

K. test v3		81.04 377	79.77 380	84.83 403	87.41 418	70.23 434	95.60 369	93.93 397	83.70 339	67.51 432	89.35 398	55.76 405	93.58 408	76.67 363	68.03 414	90.67 377

MIMVSNet1		75.92 403	73.30 407	83.81 410	81.29 442	75.57 412	92.26 408	92.05 420	73.09 423	67.48 433	86.18 420	40.87 444	87.64 446	55.78 444	70.68 408	88.21 412

ET-MVSNet_ETH3D		92.56 192	91.45 203	95.88 147	96.39 193	94.13 63	99.46 72	96.97 216	92.18 112	66.94 434	98.29 139	94.65 14	94.28 399	94.34 158	83.82 316	99.24 114

pmmvs-eth3d		78.71 390	76.16 395	86.38 387	80.25 446	81.19 370	94.17 386	92.13 419	77.97 399	66.90 435	82.31 434	55.76 405	92.56 419	73.63 388	62.31 432	85.38 434

EG-PatchMatch MVS		79.92 381	77.59 387	86.90 384	87.06 422	77.90 400	96.20 350	94.06 395	74.61 416	66.53 436	88.76 401	40.40 445	96.20 342	67.02 418	83.66 318	86.61 424

test_method		70.10 413	68.66 416	74.41 429	86.30 427	55.84 451	94.47 379	89.82 440	35.18 458	66.15 437	84.75 427	30.54 452	77.96 459	70.40 404	60.33 436	89.44 400

UnsupCasMVSNet_eth		78.90 388	76.67 393	85.58 397	82.81 439	74.94 415	91.98 410	96.31 259	84.64 324	65.84 438	87.71 406	51.33 424	92.23 423	72.89 392	56.50 444	89.56 399

test_f		71.94 411	70.82 412	75.30 426	72.77 455	53.28 454	91.62 414	89.66 442	75.44 413	64.47 439	78.31 446	20.48 457	89.56 440	78.63 350	66.02 422	83.05 445

new-patchmatchnet		74.80 408	72.40 410	81.99 418	78.36 449	72.20 427	94.44 381	92.36 415	77.06 403	63.47 440	79.98 443	51.04 426	88.85 443	60.53 437	54.35 446	84.92 439

new_pmnet		76.02 402	73.71 405	82.95 413	83.88 434	72.85 425	91.26 420	92.26 416	70.44 429	62.60 441	81.37 437	47.64 434	92.32 422	61.85 432	72.10 401	83.68 442

UnsupCasMVSNet_bld		73.85 409	70.14 413	84.99 401	79.44 447	75.73 411	88.53 430	95.24 358	70.12 431	61.94 442	74.81 449	41.41 443	93.62 407	68.65 412	51.13 452	85.62 432

CMPMVS	58.40 21	80.48 379	80.11 378	81.59 420	85.10 430	59.56 447	94.14 387	95.95 292	68.54 436	60.71 443	93.31 311	55.35 410	97.87 243	83.06 315	84.85 306	87.33 420
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
APD_test1		68.93 414	66.98 417	74.77 428	80.62 444	53.15 455	87.97 431	85.01 453	53.76 451	59.26 444	87.52 409	25.19 454	89.95 436	56.20 443	67.33 418	81.19 446

MVStest1		76.56 401	73.43 406	85.96 394	86.30 427	80.88 376	94.26 384	91.74 424	61.98 446	58.53 445	89.96 389	69.30 335	91.47 430	59.26 439	49.56 454	85.52 433

DeepMVS_CX				76.08 425	90.74 377	51.65 458		90.84 433	86.47 290	57.89 446	87.98 404	35.88 450	92.60 417	65.77 423	65.06 424	83.97 441

WB-MVS		66.44 415	66.29 418	66.89 435	74.84 451	44.93 462	93.00 399	84.09 456	71.15 426	55.82 447	81.63 436	63.79 376	80.31 457	21.85 461	50.47 453	75.43 448

SSC-MVS		65.42 416	65.20 419	66.06 436	73.96 452	43.83 463	92.08 409	83.54 457	69.77 432	54.73 448	80.92 440	63.30 378	79.92 458	20.48 462	48.02 455	74.44 449

YYNet1		79.64 386	77.04 391	87.43 379	87.80 415	79.98 379	96.23 347	94.44 384	73.83 420	51.83 449	87.53 408	67.96 347	92.07 426	66.00 422	67.75 417	90.23 385

MDA-MVSNet_test_wron		79.65 385	77.05 390	87.45 378	87.79 416	80.13 378	96.25 346	94.44 384	73.87 419	51.80 450	87.47 412	68.04 345	92.12 425	66.02 421	67.79 416	90.09 386

LCM-MVSNet		60.07 420	56.37 422	71.18 431	54.81 466	48.67 459	82.17 451	89.48 443	37.95 456	49.13 451	69.12 450	13.75 464	81.76 451	59.28 438	51.63 451	83.10 444

MDA-MVSNet-bldmvs		77.82 397	74.75 403	87.03 381	88.33 406	78.52 393	96.34 341	92.85 409	75.57 412	48.87 452	87.89 405	57.32 401	92.49 421	60.79 435	64.80 425	90.08 387

PMMVS2		58.97 421	55.07 424	70.69 433	62.72 461	55.37 452	85.97 435	80.52 459	49.48 452	45.94 453	68.31 451	15.73 462	80.78 455	49.79 450	37.12 458	75.91 447

testf1		56.38 422	53.73 425	64.31 439	64.84 459	45.11 460	80.50 452	75.94 464	38.87 454	42.74 454	75.07 447	11.26 466	81.19 453	41.11 454	53.27 448	66.63 453

APD_test2		56.38 422	53.73 425	64.31 439	64.84 459	45.11 460	80.50 452	75.94 464	38.87 454	42.74 454	75.07 447	11.26 466	81.19 453	41.11 454	53.27 448	66.63 453

FPMVS		61.57 417	60.32 420	65.34 437	60.14 464	42.44 465	91.02 423	89.72 441	44.15 453	42.63 456	80.93 439	19.02 458	80.59 456	42.50 453	72.76 393	73.00 450

test_vis3_rt		61.29 418	58.75 421	68.92 434	67.41 458	52.84 456	91.18 422	59.23 469	66.96 440	41.96 457	58.44 457	11.37 465	94.72 394	74.25 380	57.97 441	59.20 456

Gipuma		54.77 424	52.22 428	62.40 441	86.50 424	59.37 448	50.20 459	90.35 438	36.52 457	41.20 458	49.49 459	18.33 460	81.29 452	32.10 458	65.34 423	46.54 459
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		53.66 425	52.86 427	56.05 442	32.75 470	41.97 466	73.42 456	76.12 463	21.91 463	39.68 459	96.39 244	42.59 440	65.10 462	78.00 353	14.92 463	61.08 455

E-PMN		41.02 429	40.93 431	41.29 445	61.97 462	33.83 468	84.00 446	65.17 467	27.17 460	27.56 460	46.72 461	17.63 461	60.41 464	19.32 463	18.82 460	29.61 460

ANet_high		50.71 426	46.17 429	64.33 438	44.27 468	52.30 457	76.13 455	78.73 460	64.95 443	27.37 461	55.23 458	14.61 463	67.74 461	36.01 457	18.23 461	72.95 451

EMVS		39.96 430	39.88 432	40.18 446	59.57 465	32.12 470	84.79 443	64.57 468	26.27 461	26.14 462	44.18 464	18.73 459	59.29 465	17.03 464	17.67 462	29.12 461

MVE	44.00 22	41.70 428	37.64 433	53.90 444	49.46 467	43.37 464	65.09 458	66.66 466	26.19 462	25.77 463	48.53 460	3.58 470	63.35 463	26.15 460	27.28 459	54.97 458
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	41.42 23	45.67 427	42.50 430	55.17 443	34.28 469	32.37 469	66.24 457	78.71 461	30.72 459	22.04 464	59.59 455	4.59 468	77.85 460	27.49 459	58.84 440	55.29 457
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		18.81 432	23.05 435	6.10 449	4.48 471	2.29 474	97.78 272	3.00 472	3.27 465	18.60 465	62.71 453	1.53 472	2.49 468	14.26 466	1.80 465	13.50 463

test123		16.58 434	19.47 436	7.91 448	3.59 472	5.37 473	94.32 382	1.39 473	2.49 466	13.98 466	44.60 463	2.91 471	2.65 467	11.35 467	0.57 466	15.70 462

wuyk23d		16.71 433	16.73 437	16.65 447	60.15 463	25.22 472	41.24 460	5.17 471	6.56 464	5.48 467	3.61 467	3.64 469	22.72 466	15.20 465	9.52 464	1.99 464

EGC-MVSNET		60.70 419	55.37 423	76.72 424	86.35 426	71.08 429	89.96 428	84.44 455	0.38 467	1.50 468	84.09 428	37.30 448	88.10 445	40.85 456	73.44 389	70.97 452

mmdepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

monomultidepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

test_blank		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet_test		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

DCPMVS		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

cdsmvs_eth3d_5k		22.52 431	30.03 434	0.00 450	0.00 473	0.00 475	0.00 461	97.17 195	0.00 468	0.00 469	98.77 100	74.35 290	0.00 469	0.00 468	0.00 467	0.00 465

pcd_1.5k_mvsjas		6.87 436	9.16 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	82.48 203	0.00 469	0.00 468	0.00 467	0.00 465

sosnet-low-res		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

sosnet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uncertanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

Regformer		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

ab-mvs-re		8.21 435	10.94 438	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	98.50 124	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

WAC-MVS						79.74 382								67.75 415

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 101					99.98 9	99.55 15	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 101					99.98 9	99.55 15	99.83 15	99.96 10

eth-test2					0.00 473

eth-test					0.00 473

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 27				99.19 38	95.12 8	99.97 21	99.90 1	99.92 3	99.99 1

save fliter					99.34 50	93.85 67	99.65 47	97.63 122	95.69 31

test_0728_SECOND				98.77 8	99.66 12	96.37 14	99.72 34	97.68 103					99.98 9	99.64 8	99.82 19	99.96 10

GSMVS																98.84 153

sam_mvs1												88.39 80				98.84 153

sam_mvs												87.08 108

MTGPA								97.45 160

test_post1							90.74 426				41.37 465	85.38 150	96.36 327	83.16 312

test_post											46.00 462	87.37 99	97.11 291

patchmatchnet-post											84.86 425	88.73 76	96.81 304

MTMP							99.21 104	91.09 432

gm-plane-assit					94.69 283	88.14 232			88.22 238		97.20 192		98.29 206	90.79 210

test9_res														98.60 44	99.87 9	99.90 22

agg_prior2														97.84 70	99.87 9	99.91 21

test_prior4						92.00 112	99.41 82

test_prior				97.01 71	99.58 30	91.77 119		97.57 136					99.49 127			99.79 38

新几何2							98.26 235

旧先验1					98.97 75	92.90 94		97.74 88			99.15 48	91.05 38			99.33 65	99.60 77

无先验							98.52 200	97.82 73	87.20 268				99.90 55	87.64 249		99.85 30

原ACMM2							98.69 174

testdata2													99.88 64	84.16 298

segment_acmp												90.56 49

testdata1							97.89 264		92.43 103

plane_prior7					93.84 316	85.73 303

plane_prior6					93.92 313	86.02 296						72.92 305

plane_prior5								96.30 260					97.75 259	93.46 176	86.17 296	92.67 309

plane_prior4											96.52 237

plane_prior2							99.02 138		93.38 84

plane_prior1					93.90 315

plane_prior						86.07 294	99.14 120		93.81 73						86.26 295

n2								0.00 474

nn								0.00 474

door-mid								84.90 454

test11								97.68 103

door								85.30 452

HQP5-MVS						86.39 276

BP-MVS														93.82 168

HQP3-MVS								96.37 256							86.29 293

HQP2-MVS												73.34 298

NP-MVS					93.94 311	86.22 282					96.67 235

ACMMP++_ref															82.64 327

ACMMP++															83.83 314

Test By Simon												83.62 173

High-resolution multi-view benchmark