High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

MM		80.20 8	80.28 10	79.99 2	82.19 91	60.01 49	86.19 21	83.93 62	73.19 1	77.08 46	91.21 20	57.23 40	90.73 10	83.35 1	88.12 38	89.22 9

MSP-MVS		81.06 3	81.40 4	80.02 1	86.21 33	62.73 9	86.09 22	86.83 8	65.51 13	83.81 10	90.51 30	63.71 13	89.23 26	81.51 2	88.44 31	88.09 47
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
MGCNet		78.45 21	78.28 22	78.98 29	80.73 116	57.91 91	84.68 41	81.64 135	68.35 2	75.77 52	90.38 34	53.98 82	90.26 13	81.30 3	87.68 46	88.77 19

MP-MVS-pluss		78.35 23	78.46 20	78.03 45	84.96 57	59.52 58	82.93 70	85.39 34	62.15 82	76.41 50	91.51 11	52.47 111	86.78 78	80.66 4	89.64 21	87.80 58
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_9		75.16 61	75.22 60	75.01 102	78.34 181	55.37 140	77.30 188	73.95 320	61.40 97	79.46 24	90.14 41	57.07 41	81.15 233	80.00 5	79.31 156	88.51 31

SMA-MVS		80.28 7	80.39 8	79.95 4	86.60 24	61.95 19	86.33 17	85.75 28	62.49 72	82.20 20	92.28 1	56.53 45	89.70 21	79.85 6	91.48 1	88.19 42
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
DVP-MVS++		81.67 1	82.40 1	79.47 10	87.24 14	59.15 69	88.18 1	87.15 3	65.04 17	84.26 5	91.86 6	67.01 1	90.84 3	79.48 7	91.38 2	88.42 32

test_0728_THIRD									65.04 17	83.82 8	92.00 3	64.69 11	90.75 8	79.48 7	90.63 10	88.09 47

ACMMP_NAP		78.77 18	78.78 17	78.74 34	85.44 47	61.04 31	83.84 60	85.16 38	62.88 63	78.10 35	91.26 19	52.51 109	88.39 36	79.34 9	90.52 13	86.78 102

MSC_two_6792asdad				79.95 4	87.24 14	61.04 31		85.62 31					90.96 1	79.31 10	90.65 8	87.85 55

No_MVS				79.95 4	87.24 14	61.04 31		85.62 31					90.96 1	79.31 10	90.65 8	87.85 55

fmvsm_s_conf0.5_n_4		72.04 129	71.85 118	72.58 194	73.74 324	52.49 204	76.69 211	72.42 338	56.42 226	75.32 57	87.04 114	52.13 119	78.01 314	79.29 12	73.65 262	87.26 84

IU-MVS					87.77 4	59.15 69		85.53 33	53.93 290	84.64 3				79.07 13	90.87 5	88.37 34

HPM-MVS++		79.88 11	80.14 11	79.10 21	88.17 1	64.80 1	86.59 16	83.70 81	65.37 14	78.78 30	90.64 24	58.63 32	87.24 62	79.00 14	90.37 14	85.26 182

APDe-MVS		80.16 9	80.59 7	78.86 33	86.64 21	60.02 48	88.12 3	86.42 16	62.94 61	82.40 16	92.12 2	59.64 24	89.76 20	78.70 15	88.32 35	86.79 101
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
fmvsm_s_conf0.5_n_3		73.55 91	74.39 70	71.03 252	74.09 320	51.86 219	77.77 172	75.60 284	61.18 103	78.67 31	88.98 63	55.88 63	77.73 324	78.69 16	78.68 177	83.50 248

CNVR-MVS		79.84 12	79.97 12	79.45 11	87.90 2	62.17 17	84.37 45	85.03 43	66.96 5	77.58 40	90.06 45	59.47 26	89.13 28	78.67 17	89.73 16	87.03 92

DVP-MVS		80.84 4	81.64 3	78.42 38	87.75 7	59.07 74	87.85 5	85.03 43	64.26 32	83.82 8	92.00 3	64.82 8	90.75 8	78.66 18	90.61 11	85.45 170
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_SECOND				79.19 16	87.82 3	59.11 72	87.85 5	87.15 3					90.84 3	78.66 18	90.61 11	87.62 66

SED-MVS		81.56 2	82.30 2	79.32 13	87.77 4	58.90 79	87.82 7	86.78 10	64.18 35	85.97 1	91.84 8	66.87 3	90.83 5	78.63 20	90.87 5	88.23 40

test_241102_TWO								86.73 12	64.18 35	84.26 5	91.84 8	65.19 6	90.83 5	78.63 20	90.70 7	87.65 64

fmvsm_s_conf0.5_n_8		74.30 75	74.39 70	74.01 143	75.33 282	52.89 191	78.24 149	77.32 246	61.65 92	78.13 34	88.90 66	52.82 105	81.54 223	78.46 22	78.67 178	87.60 67

SteuartSystems-ACMMP		79.48 14	79.31 14	79.98 3	83.01 82	62.18 16	87.60 9	85.83 26	66.69 10	78.03 37	90.98 21	54.26 77	90.06 14	78.42 23	89.02 27	87.69 62
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_l_conf0.5_n_9		73.27 98	73.66 87	72.09 209	73.82 321	52.72 197	77.45 182	74.28 313	56.61 221	77.10 45	88.16 78	56.17 51	77.09 339	78.27 24	81.13 121	86.48 116

test_fmvsmconf0.1_n		72.81 108	72.33 112	74.24 129	69.89 401	55.81 127	78.22 155	75.40 291	54.17 286	75.00 65	88.03 86	53.82 87	80.23 262	78.08 25	78.34 187	86.69 106

test_fmvsmconf0.01_n		72.17 125	71.50 124	74.16 133	67.96 432	55.58 135	78.06 162	74.67 306	54.19 285	74.54 78	88.23 76	50.35 150	80.24 261	78.07 26	77.46 201	86.65 110

test_fmvsmconf_n		73.01 104	72.59 107	74.27 127	71.28 375	55.88 126	78.21 156	75.56 286	54.31 284	74.86 70	87.80 90	54.72 73	80.23 262	78.07 26	78.48 183	86.70 105

fmvsm_s_conf0.5_n_10		74.11 77	73.98 80	74.48 121	74.61 302	52.86 193	78.10 161	77.06 251	57.14 203	78.24 33	88.79 71	52.83 104	82.26 209	77.79 28	81.30 119	88.32 35

9.14			78.75 18		83.10 79		84.15 54	88.26 1	59.90 140	78.57 32	90.36 35	57.51 39	86.86 76	77.39 29	89.52 23

test-260524					86.59 25	59.16 67		86.47 15		82.32 18		62.54 14	89.91 16	77.25 30	89.69 18

MTAPA		76.90 38	76.42 43	78.35 39	86.08 39	63.57 2	74.92 256	80.97 161	65.13 16	75.77 52	90.88 22	48.63 176	86.66 81	77.23 31	88.17 37	84.81 198

MP-MVS		78.35 23	78.26 24	78.64 35	86.54 27	63.47 4	86.02 24	83.55 87	63.89 40	73.60 98	90.60 25	54.85 72	86.72 79	77.20 32	88.06 40	85.74 155
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
fmvsm_s_conf0.5_n_6		72.59 115	72.87 103	71.73 220	75.14 289	51.96 217	76.28 220	77.12 249	57.63 197	73.85 94	86.91 117	51.54 130	77.87 320	77.18 33	80.18 138	85.37 176

SF-MVS		78.82 16	79.22 15	77.60 52	82.88 84	57.83 92	84.99 37	88.13 2	61.86 90	79.16 27	90.75 23	57.96 33	87.09 71	77.08 34	90.18 15	87.87 54

aaatest				79.09 23	85.30 51	59.25 64	86.84 11	85.86 24	60.95 107	83.65 12	90.57 27		89.91 16	77.02 35	89.43 24	88.10 45

MED-MVS		80.42 6	80.87 6	79.07 25	85.30 51	59.25 64	86.84 11	85.86 24	63.31 49	83.65 12	91.48 12	64.70 10	89.91 16	77.02 35	89.69 18	88.06 50

aaEdge-Enhanced		80.04 10	80.36 9	79.08 24	86.63 23	59.25 64	85.62 32	86.73 12	63.10 58	82.27 19	90.57 27	61.90 17	89.88 19	77.02 35	89.43 24	88.10 45

TSAR-MVS + MP.		78.44 22	78.28 22	78.90 31	84.96 57	61.41 26	84.03 56	83.82 76	59.34 156	79.37 26	89.76 54	59.84 21	87.62 59	76.69 38	86.74 59	87.68 63
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_s_conf0.5_n_5		72.69 112	72.80 104	72.37 205	74.11 319	53.21 182	78.12 158	73.31 327	53.98 289	76.81 47	88.05 83	53.38 95	77.37 334	76.64 39	80.78 123	86.53 114

ZNCC-MVS		78.82 16	78.67 19	79.30 14	86.43 30	62.05 18	86.62 15	86.01 21	63.32 48	75.08 63	90.47 33	53.96 84	88.68 33	76.48 40	89.63 22	87.16 89

DPE-MVS		80.56 5	80.98 5	79.29 15	87.27 13	60.56 41	85.71 31	86.42 16	63.28 52	83.27 15	91.83 10	64.96 7	90.47 11	76.41 41	89.67 20	86.84 99
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_l_conf0.5_n_3		73.23 99	73.13 99	73.55 168	74.40 309	55.13 143	78.97 132	74.96 303	56.64 215	74.76 74	88.75 72	55.02 69	78.77 303	76.33 42	78.31 188	86.74 104

fmvsm_l_conf0.5_n		70.99 150	70.82 141	71.48 229	71.45 368	54.40 152	77.18 194	70.46 357	48.67 375	75.17 60	86.86 118	53.77 89	76.86 347	76.33 42	77.51 200	83.17 260

TestfortrainingZip a		79.61 13	79.84 13	78.92 30	85.30 51	59.08 73	86.84 11	86.01 21	63.31 49	82.37 17	91.48 12	60.88 19	89.61 22	76.25 44	86.13 66	88.06 50

fmvsm_s_conf0.5_n_11		73.16 100	73.35 94	72.58 194	75.48 277	52.41 208	78.84 134	76.85 256	58.64 170	73.58 99	87.25 109	54.09 81	79.47 274	76.19 45	79.27 157	85.86 145

SD-MVS		77.70 30	77.62 30	77.93 47	84.47 65	61.88 21	84.55 43	83.87 69	60.37 125	79.89 23	89.38 58	54.97 70	85.58 117	76.12 46	84.94 72	86.33 126
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
test_fmvsmvis_n_1920		70.84 152	70.38 151	72.22 208	71.16 376	55.39 139	75.86 233	72.21 341	49.03 370	73.28 107	86.17 149	51.83 125	77.29 336	75.80 47	78.05 191	83.98 225

fmvsm_s_conf0.5_n		69.58 190	68.84 186	71.79 218	72.31 354	52.90 189	77.90 164	62.43 432	49.97 358	72.85 123	85.90 160	52.21 116	76.49 356	75.75 48	70.26 323	85.97 139

fmvsm_s_conf0.5_n_2		69.82 180	69.27 176	71.46 230	72.00 358	51.08 226	73.30 292	67.79 380	55.06 265	75.24 59	87.51 93	44.02 240	77.00 343	75.67 49	72.86 280	86.31 131

lecture		77.75 28	77.84 28	77.50 54	82.75 86	57.62 95	85.92 25	86.20 19	60.53 118	78.99 29	91.45 14	51.51 131	87.78 54	75.65 50	87.55 47	87.10 91

fmvsm_s_conf0.1_n_2		69.64 188	69.01 182	71.52 228	71.66 363	51.04 227	73.39 291	67.14 386	55.02 269	75.11 61	87.64 92	42.94 252	77.01 342	75.55 51	72.63 286	86.52 115

fmvsm_s_conf0.1_n		69.41 198	68.60 192	71.83 215	71.07 377	52.88 192	77.85 168	62.44 431	49.58 363	72.97 118	86.22 146	51.68 128	76.48 357	75.53 52	70.10 326	86.14 134

fmvsm_l_conf0.5_n_a		70.50 162	70.27 154	71.18 245	71.30 374	54.09 157	76.89 205	69.87 361	47.90 390	74.37 81	86.49 138	53.07 103	76.69 353	75.41 53	77.11 210	82.76 267

HPM-MVS		77.28 33	76.85 34	78.54 36	85.00 56	60.81 38	82.91 71	85.08 40	62.57 70	73.09 116	89.97 50	50.90 143	87.48 60	75.30 54	86.85 57	87.33 83
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test9_res														75.28 55	88.31 36	83.81 233

train_agg		76.27 48	76.15 45	76.64 71	85.58 45	61.59 24	81.62 91	81.26 150	55.86 236	74.93 66	88.81 68	53.70 91	84.68 141	75.24 56	88.33 34	83.65 244

fmvsm_s_conf0.5_n_a		69.54 192	68.74 189	71.93 212	72.47 348	53.82 162	78.25 148	62.26 434	49.78 360	73.12 115	86.21 147	52.66 107	76.79 349	75.02 57	68.88 350	85.18 183

test_fmvsm_n_1920		71.73 135	71.14 135	73.50 169	72.52 346	56.53 113	75.60 237	76.16 271	48.11 386	77.22 42	85.56 170	53.10 101	77.43 331	74.86 58	77.14 209	86.55 113

fmvsm_s_conf0.1_n_a		69.32 200	68.44 198	71.96 210	70.91 379	53.78 163	78.12 158	62.30 433	49.35 366	73.20 109	86.55 137	51.99 121	76.79 349	74.83 59	68.68 355	85.32 178

GST-MVS		78.14 25	77.85 27	78.99 28	86.05 40	61.82 22	85.84 26	85.21 37	63.56 44	74.29 83	90.03 47	52.56 108	88.53 35	74.79 60	88.34 33	86.63 111

DeepC-MVS	69.38 2	78.56 20	78.14 25	79.83 7	83.60 72	61.62 23	84.17 53	86.85 6	63.23 54	73.84 95	90.25 40	57.68 36	89.96 15	74.62 61	89.03 26	87.89 52
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PC_three_1452									55.09 260	84.46 4	89.84 52	66.68 5	89.41 24	74.24 62	91.38 2	88.42 32

DeepPCF-MVS	69.58 1	79.03 15	79.00 16	79.13 19	84.92 61	60.32 46	83.03 68	85.33 35	62.86 64	80.17 22	90.03 47	61.76 18	88.95 30	74.21 63	88.67 30	88.12 44

NCCC		78.58 19	78.31 21	79.39 12	87.51 12	62.61 13	85.20 36	84.42 53	66.73 8	74.67 77	89.38 58	55.30 66	89.18 27	74.19 64	87.34 50	86.38 119

ZD-MVS					86.64 21	60.38 45		82.70 120	57.95 187	78.10 35	90.06 45	56.12 54	88.84 32	74.05 65	87.00 55

HFP-MVS		78.01 27	77.65 29	79.10 21	86.71 19	62.81 8	86.29 18	84.32 55	62.82 65	73.96 88	90.50 31	53.20 99	88.35 37	74.02 66	87.05 51	86.13 135

ACMMPR		77.71 29	77.23 32	79.16 17	86.75 18	62.93 7	86.29 18	84.24 56	62.82 65	73.55 100	90.56 29	49.80 157	88.24 39	74.02 66	87.03 52	86.32 128

region2R		77.67 31	77.18 33	79.15 18	86.76 17	62.95 6	86.29 18	84.16 58	62.81 67	73.30 105	90.58 26	49.90 154	88.21 40	73.78 68	87.03 52	86.29 132

MCST-MVS		77.48 32	77.45 31	77.54 53	86.67 20	58.36 86	83.22 66	86.93 5	56.91 211	74.91 68	88.19 77	59.15 29	87.68 58	73.67 69	87.45 49	86.57 112

CP-MVS		77.12 36	76.68 36	78.43 37	86.05 40	63.18 5	87.55 10	83.45 90	62.44 74	72.68 126	90.50 31	48.18 181	87.34 61	73.59 70	85.71 68	84.76 201

APD-MVS		78.02 26	78.04 26	77.98 46	86.44 29	60.81 38	85.52 33	84.36 54	60.61 116	79.05 28	90.30 38	55.54 65	88.32 38	73.48 71	87.03 52	84.83 197
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
OPU-MVS				79.83 7	87.54 11	60.93 35	87.82 7				89.89 51	67.01 1	90.33 12	73.16 72	91.15 4	88.23 40

agg_prior2														73.09 73	87.93 44	84.33 211

BridgeMVS		76.58 43	76.55 41	76.68 68	81.73 97	52.90 189	80.94 99	85.70 30	61.12 105	74.90 69	87.17 112	56.46 46	88.14 42	72.87 74	88.03 42	89.00 12

casdiffmvs_mvg		76.14 51	76.30 44	75.66 89	76.46 260	51.83 220	79.67 122	85.08 40	65.02 20	75.84 51	88.58 75	59.42 27	85.08 129	72.75 75	83.93 84	90.08 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CANet		76.46 45	75.93 49	78.06 43	81.29 106	57.53 97	82.35 80	83.31 98	67.78 3	70.09 165	86.34 143	54.92 71	88.90 31	72.68 76	84.55 75	87.76 60

reproduce-ours		76.90 38	76.58 38	77.87 48	83.99 68	60.46 43	84.75 38	83.34 95	60.22 132	77.85 38	91.42 16	50.67 144	87.69 56	72.46 77	84.53 76	85.46 168

our_new_method		76.90 38	76.58 38	77.87 48	83.99 68	60.46 43	84.75 38	83.34 95	60.22 132	77.85 38	91.42 16	50.67 144	87.69 56	72.46 77	84.53 76	85.46 168

PGM-MVS		76.77 41	76.06 47	78.88 32	86.14 37	62.73 9	82.55 78	83.74 78	61.71 91	72.45 132	90.34 37	48.48 179	88.13 43	72.32 79	86.85 57	85.78 149

Casviewmamba		76.62 42	76.52 42	76.90 62	77.91 198	53.66 166	80.76 103	84.47 50	66.73 8	75.75 54	88.63 74	59.17 28	86.66 81	72.28 80	83.01 92	90.39 1

test_prior2							81.75 89		60.37 125	75.01 64	89.06 61	56.22 50		72.19 81	88.96 28

MVSMamba_PlusPlus		75.75 57	75.44 55	76.67 69	80.84 114	53.06 186	78.62 140	85.13 39	59.65 146	71.53 145	87.47 95	56.92 42	88.17 41	72.18 82	86.63 62	88.80 16

ACMMP		76.02 53	75.33 57	78.07 42	85.20 54	61.91 20	85.49 35	84.44 52	63.04 59	69.80 175	89.74 55	45.43 221	87.16 68	72.01 83	82.87 100	85.14 184
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
reproduce_model		76.43 46	76.08 46	77.49 55	83.47 76	60.09 47	84.60 42	82.90 115	59.65 146	77.31 41	91.43 15	49.62 160	87.24 62	71.99 84	83.75 88	85.14 184

EC-MVSNet		75.84 55	75.87 51	75.74 87	78.86 160	52.65 198	83.73 61	86.08 20	63.47 46	72.77 125	87.25 109	53.13 100	87.93 48	71.97 85	85.57 70	86.66 109

fmvsm_s_conf0.5_n_7		69.54 192	69.67 166	69.15 293	73.47 329	51.41 224	70.35 353	73.34 326	57.05 206	68.41 197	85.83 163	49.86 155	72.84 377	71.86 86	76.83 214	83.19 256

CS-MVS		76.25 50	75.98 48	77.06 61	80.15 130	55.63 132	84.51 44	83.90 65	63.24 53	73.30 105	87.27 104	55.06 68	86.30 97	71.78 87	84.58 74	89.25 8

mPP-MVS		76.54 44	75.93 49	78.34 40	86.47 28	63.50 3	85.74 30	82.28 125	62.90 62	71.77 139	90.26 39	46.61 207	86.55 88	71.71 88	85.66 69	84.97 193

SR-MVS		76.13 52	75.70 53	77.40 58	85.87 42	61.20 29	85.52 33	82.19 126	59.99 138	75.10 62	90.35 36	47.66 188	86.52 89	71.64 89	82.99 94	84.47 210

XVS		77.17 35	76.56 40	79.00 26	86.32 31	62.62 11	85.83 27	83.92 63	64.55 26	72.17 134	90.01 49	47.95 183	88.01 46	71.55 90	86.74 59	86.37 121

X-MVStestdata		70.21 169	67.28 231	79.00 26	86.32 31	62.62 11	85.83 27	83.92 63	64.55 26	72.17 134	6.49 527	47.95 183	88.01 46	71.55 90	86.74 59	86.37 121

BP-MVS1		73.41 94	72.25 113	76.88 63	76.68 253	53.70 164	79.15 130	81.07 157	60.66 115	71.81 138	87.39 99	40.93 284	87.24 62	71.23 92	81.29 120	89.71 3

dcpmvs_2		74.55 72	75.23 59	72.48 200	82.34 89	53.34 178	77.87 166	81.46 139	57.80 193	75.49 55	86.81 120	62.22 15	77.75 323	71.09 93	82.02 109	86.34 123

diffmvs_AUTHOR		71.02 147	70.87 140	71.45 232	69.89 401	48.97 288	73.16 299	78.33 224	57.79 194	72.11 136	85.26 179	51.84 124	77.89 319	71.00 94	78.47 185	87.49 71

PHI-MVS		75.87 54	75.36 56	77.41 56	80.62 121	55.91 125	84.28 50	85.78 27	56.08 234	73.41 101	86.58 134	50.94 142	88.54 34	70.79 95	89.71 17	87.79 59

diffmvs		70.69 158	70.43 149	71.46 230	69.45 408	48.95 289	72.93 302	78.46 217	57.27 201	71.69 140	83.97 214	51.48 132	77.92 318	70.70 96	77.95 193	87.53 70
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
h-mvs33		72.71 111	71.49 125	76.40 74	81.99 94	59.58 57	76.92 204	76.74 262	60.40 122	74.81 71	85.95 158	45.54 217	85.76 113	70.41 97	70.61 314	83.86 232

hse-mvs2		71.04 146	69.86 162	74.60 115	79.58 139	57.12 108	73.96 277	75.25 294	60.40 122	74.81 71	81.95 268	45.54 217	82.90 188	70.41 97	66.83 370	83.77 237

APD-MVS_3200maxsize		74.96 62	74.39 70	76.67 69	82.20 90	58.24 87	83.67 62	83.29 99	58.41 175	73.71 96	90.14 41	45.62 214	85.99 107	69.64 99	82.85 101	85.78 149

baseline		74.61 70	74.70 66	74.34 124	75.70 270	49.99 263	77.54 178	84.63 49	62.73 69	73.98 87	87.79 91	57.67 37	83.82 158	69.49 100	82.74 103	89.20 10

OPM-MVS		74.73 67	74.25 73	76.19 78	80.81 115	59.01 77	82.60 77	83.64 84	63.74 42	72.52 129	87.49 94	47.18 198	85.88 110	69.47 101	80.78 123	83.66 243
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
casdiffmvs		74.80 65	74.89 65	74.53 119	75.59 275	50.37 252	78.17 157	85.06 42	62.80 68	74.40 80	87.86 88	57.88 34	83.61 162	69.46 102	82.79 102	89.59 5
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CDPH-MVS		76.31 47	75.67 54	78.22 41	85.35 50	59.14 71	81.31 96	84.02 59	56.32 228	74.05 86	88.98 63	53.34 96	87.92 49	69.23 103	88.42 32	87.59 68

CPTT-MVS		72.78 109	72.08 116	74.87 105	84.88 62	61.41 26	84.15 54	77.86 230	55.27 254	67.51 228	88.08 82	41.93 263	81.85 216	69.04 104	80.01 139	81.35 301

balanced_ft_v1		72.98 105	72.55 108	74.27 127	79.52 142	50.64 241	77.78 171	83.29 99	56.76 212	67.88 215	85.95 158	49.42 164	85.29 127	68.64 105	83.76 87	86.87 97

viewmamba		71.13 144	70.66 145	72.56 196	70.23 392	50.07 260	74.25 271	77.85 231	59.92 139	70.94 152	85.55 172	52.30 115	80.25 260	68.42 106	76.47 220	87.35 82

hybridcas		74.86 64	75.07 61	74.24 129	76.30 261	50.58 243	79.30 128	83.88 68	63.15 57	74.69 75	88.13 79	58.91 30	82.98 179	68.30 107	82.93 97	89.15 11

DeepC-MVS_fast	68.24 3	77.25 34	76.63 37	79.12 20	86.15 36	60.86 36	84.71 40	84.85 47	61.98 89	73.06 117	88.88 67	53.72 90	89.06 29	68.27 108	88.04 41	87.42 74
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		74.57 71	73.90 81	76.58 72	83.49 74	59.87 54	84.29 48	81.36 143	58.07 181	73.14 112	90.07 43	44.74 231	85.84 111	68.20 109	81.76 114	84.03 222

RE-MVS-def			73.71 86		83.49 74	59.87 54	84.29 48	81.36 143	58.07 181	73.14 112	90.07 43	43.06 250		68.20 109	81.76 114	84.03 222

E6new		74.10 78	74.09 75	74.15 135	77.14 231	50.74 236	78.24 149	83.85 74	62.34 76	73.95 89	87.27 104	55.98 58	82.95 182	68.17 111	79.85 142	88.77 19

E6		74.10 78	74.09 75	74.15 135	77.14 231	50.74 236	78.24 149	83.85 74	62.34 76	73.95 89	87.27 104	55.98 58	82.95 182	68.17 111	79.85 142	88.77 19

E5new		74.10 78	74.09 75	74.15 135	77.14 231	50.74 236	78.24 149	83.86 72	62.34 76	73.95 89	87.27 104	55.97 60	82.95 182	68.16 113	79.86 140	88.77 19

E5		74.10 78	74.09 75	74.15 135	77.14 231	50.74 236	78.24 149	83.86 72	62.34 76	73.95 89	87.27 104	55.97 60	82.95 182	68.16 113	79.86 140	88.77 19

HQP_MVS		74.31 74	73.73 85	76.06 79	81.41 103	56.31 114	84.22 51	84.01 60	64.52 28	69.27 184	86.10 151	45.26 225	87.21 66	68.16 113	80.58 129	84.65 202

plane_prior5								84.01 60					87.21 66	68.16 113	80.58 129	84.65 202

NormalMVS		76.26 49	75.74 52	77.83 50	82.75 86	59.89 52	84.36 46	83.21 103	64.69 23	74.21 84	87.40 97	49.48 161	86.17 100	68.04 117	87.55 47	87.42 74

SymmetryMVS		75.28 60	74.60 67	77.30 59	83.85 71	59.89 52	84.36 46	75.51 288	64.69 23	74.21 84	87.40 97	49.48 161	86.17 100	68.04 117	83.88 85	85.85 146

E4		73.91 84	73.83 84	74.15 135	77.13 235	50.47 249	77.15 195	83.79 77	62.21 81	73.61 97	87.19 111	56.08 56	83.03 174	67.91 119	79.35 154	88.94 14

CSCG		76.92 37	76.75 35	77.41 56	83.96 70	59.60 56	82.95 69	86.50 14	60.78 112	75.27 58	84.83 185	60.76 20	86.56 85	67.86 120	87.87 45	86.06 137

hybridnocas07		69.86 178	69.44 172	71.14 248	68.10 430	48.28 300	72.52 312	77.08 250	56.94 209	70.50 159	84.91 184	50.48 147	78.37 307	67.84 121	76.55 219	86.76 103

SPE-MVS-test		75.62 58	75.31 58	76.56 73	80.63 120	55.13 143	83.88 59	85.22 36	62.05 86	71.49 146	86.03 154	53.83 86	86.36 95	67.74 122	86.91 56	88.19 42

onestephybrid01		71.00 149	70.34 153	72.99 185	70.38 389	50.88 233	74.14 274	77.41 241	58.80 164	71.36 148	84.93 182	50.96 140	80.87 245	67.73 123	77.35 203	87.23 86

LPG-MVS_test		72.74 110	71.74 121	75.76 85	80.22 125	57.51 98	82.55 78	83.40 92	61.32 98	66.67 246	87.33 102	39.15 304	86.59 83	67.70 124	77.30 207	83.19 256

LGP-MVS_train				75.76 85	80.22 125	57.51 98		83.40 92	61.32 98	66.67 246	87.33 102	39.15 304	86.59 83	67.70 124	77.30 207	83.19 256

HPM-MVS_fast		74.30 75	73.46 91	76.80 65	84.45 66	59.04 76	83.65 63	81.05 158	60.15 134	70.43 160	89.84 52	41.09 283	85.59 116	67.61 126	82.90 99	85.77 152

MVS_111021_HR		74.02 82	73.46 91	75.69 88	83.01 82	60.63 40	77.29 189	78.40 222	61.18 103	70.58 158	85.97 157	54.18 79	84.00 155	67.52 127	82.98 96	82.45 278

E2		73.72 88	73.60 88	74.06 140	77.16 229	50.40 250	76.97 200	83.74 78	61.64 93	73.36 102	86.75 124	56.14 52	82.99 176	67.50 128	79.18 164	88.80 16

E3		73.72 88	73.60 88	74.06 140	77.16 229	50.40 250	76.97 200	83.74 78	61.64 93	73.36 102	86.76 121	56.13 53	82.99 176	67.50 128	79.18 164	88.80 16

ETV-MVS		74.46 73	73.84 83	76.33 76	79.27 148	55.24 142	79.22 129	85.00 45	64.97 22	72.65 127	79.46 320	53.65 94	87.87 51	67.45 130	82.91 98	85.89 143

DELS-MVS		74.76 66	74.46 69	75.65 90	77.84 201	52.25 209	75.59 238	84.17 57	63.76 41	73.15 111	82.79 237	59.58 25	86.80 77	67.24 131	86.04 67	87.89 52
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
viewcassd2359sk11		73.56 90	73.41 93	74.00 144	77.13 235	50.35 253	76.86 207	83.69 82	61.23 102	73.14 112	86.38 142	56.09 55	82.96 180	67.15 132	79.01 169	88.70 25

hybrid		69.38 199	68.93 184	70.75 258	67.86 434	48.20 302	72.49 314	76.90 254	55.23 256	70.42 161	84.34 205	49.76 158	77.62 328	67.11 133	76.20 223	86.42 118

TSAR-MVS + GP.		74.90 63	74.15 74	77.17 60	82.00 93	58.77 82	81.80 88	78.57 211	58.58 172	74.32 82	84.51 201	55.94 62	87.22 65	67.11 133	84.48 79	85.52 163

BP-MVS														67.04 135

HQP-MVS		73.45 92	72.80 104	75.40 94	80.66 117	54.94 145	82.31 82	83.90 65	62.10 83	67.85 216	85.54 174	45.46 219	86.93 74	67.04 135	80.35 134	84.32 212

viewmacassd2359aftdt		73.15 101	73.16 98	73.11 182	75.15 288	49.31 279	77.53 180	83.21 103	60.42 121	73.20 109	87.34 101	53.82 87	81.05 238	67.02 137	80.79 122	88.96 13

GDP-MVS		72.64 113	71.28 132	76.70 66	77.72 205	54.22 156	79.57 125	84.45 51	55.30 253	71.38 147	86.97 116	39.94 290	87.00 73	67.02 137	79.20 161	88.89 15

ACMP	63.53 6	72.30 122	71.20 134	75.59 93	80.28 123	57.54 96	82.74 74	82.84 118	60.58 117	65.24 278	86.18 148	39.25 302	86.03 106	66.95 139	76.79 215	83.22 254
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
E3new		73.41 94	73.22 96	73.95 147	77.06 240	50.31 254	76.78 210	83.66 83	60.90 108	72.93 120	86.02 155	55.99 57	82.95 182	66.89 140	78.77 174	88.61 27

viewmanbaseed2359cas		72.92 107	72.89 102	73.00 184	75.16 286	49.25 282	77.25 192	83.11 111	59.52 153	72.93 120	86.63 130	54.11 80	80.98 239	66.63 141	80.67 126	88.76 24

EI-MVSNet-Vis-set		72.42 120	71.59 122	74.91 103	78.47 174	54.02 158	77.05 198	79.33 189	65.03 19	71.68 141	79.35 323	52.75 106	84.89 136	66.46 142	74.23 252	85.83 148

DPM-MVS		75.47 59	75.00 62	76.88 63	81.38 105	59.16 67	79.94 115	85.71 29	56.59 222	72.46 130	86.76 121	56.89 43	87.86 52	66.36 143	88.91 29	83.64 245

patch_mono-2		69.85 179	71.09 136	66.16 342	79.11 155	54.80 149	71.97 323	74.31 311	53.50 300	70.90 154	84.17 207	57.63 38	63.31 439	66.17 144	82.02 109	80.38 326

MVSFormer		71.50 139	70.38 151	74.88 104	78.76 163	57.15 106	82.79 72	78.48 215	51.26 340	69.49 178	83.22 232	43.99 241	83.24 170	66.06 145	79.37 151	84.23 216

test_djsdf		69.45 197	67.74 214	74.58 116	74.57 305	54.92 147	82.79 72	78.48 215	51.26 340	65.41 271	83.49 228	38.37 315	83.24 170	66.06 145	69.25 345	85.56 162

sasdasda		74.67 68	74.98 63	73.71 158	78.94 158	50.56 246	80.23 108	83.87 69	60.30 129	77.15 43	86.56 135	59.65 22	82.00 213	66.01 147	82.12 106	88.58 29

canonicalmvs		74.67 68	74.98 63	73.71 158	78.94 158	50.56 246	80.23 108	83.87 69	60.30 129	77.15 43	86.56 135	59.65 22	82.00 213	66.01 147	82.12 106	88.58 29

PRO-TEST		70.71 157	69.90 161	73.16 181	77.69 207	46.08 329	70.69 346	82.79 119	57.81 191	58.42 379	85.08 180	48.68 175	87.92 49	65.99 149	81.92 111	85.48 165

MVS_Test		72.45 118	72.46 110	72.42 204	74.88 291	48.50 297	76.28 220	83.14 109	59.40 154	72.46 130	84.68 190	55.66 64	81.12 234	65.98 150	79.66 147	87.63 65

alignmvs		73.86 85	73.99 79	73.45 172	78.20 185	50.50 248	78.57 142	82.43 123	59.40 154	76.57 48	86.71 127	56.42 48	81.23 232	65.84 151	81.79 113	88.62 26

nrg030		72.96 106	73.01 100	72.84 189	75.41 280	50.24 255	80.02 113	82.89 117	58.36 177	74.44 79	86.73 125	58.90 31	80.83 246	65.84 151	74.46 248	87.44 73

MVS_111021_LR		69.50 195	68.78 188	71.65 225	78.38 177	59.33 61	74.82 258	70.11 359	58.08 180	67.83 221	84.68 190	41.96 261	76.34 360	65.62 153	77.54 198	79.30 350

EI-MVSNet-UG-set		71.92 130	71.06 137	74.52 120	77.98 196	53.56 170	76.62 212	79.16 190	64.40 30	71.18 149	78.95 328	52.19 117	84.66 143	65.47 154	73.57 265	85.32 178

viewdifsd2359ckpt07		71.90 131	71.97 117	71.69 223	74.81 295	48.08 306	75.30 243	80.49 169	60.00 137	71.63 142	86.33 144	56.34 49	79.25 279	65.40 155	77.41 202	87.76 60

PS-MVSNAJss		72.24 123	71.21 133	75.31 96	78.50 172	55.93 124	81.63 90	82.12 127	56.24 231	70.02 169	85.68 169	47.05 200	84.34 147	65.27 156	74.41 251	85.67 158

MSLP-MVS++		73.77 86	73.47 90	74.66 111	83.02 81	59.29 63	82.30 85	81.88 130	59.34 156	71.59 143	86.83 119	45.94 212	83.65 161	65.09 157	85.22 71	81.06 311

v2v482		70.50 162	69.45 171	73.66 161	72.62 343	50.03 262	77.58 175	80.51 168	59.90 140	69.52 177	82.14 264	47.53 191	84.88 138	65.07 158	70.17 324	86.09 136

RRT-MVS		71.46 140	70.70 144	73.74 156	77.76 204	49.30 280	76.60 213	80.45 170	61.25 101	68.17 203	84.78 187	44.64 233	84.90 135	64.79 159	77.88 194	87.03 92

jason		69.65 187	68.39 200	73.43 174	78.27 184	56.88 110	77.12 196	73.71 323	46.53 410	69.34 183	83.22 232	43.37 245	79.18 281	64.77 160	79.20 161	84.23 216
jason: jason.
anonymousdsp		67.00 261	64.82 281	73.57 167	70.09 397	56.13 119	76.35 218	77.35 244	48.43 381	64.99 286	80.84 294	33.01 379	80.34 256	64.66 161	67.64 363	84.23 216

lupinMVS		69.57 191	68.28 205	73.44 173	78.76 163	57.15 106	76.57 214	73.29 329	46.19 413	69.49 178	82.18 260	43.99 241	79.23 280	64.66 161	79.37 151	83.93 227

CLD-MVS		73.33 96	72.68 106	75.29 98	78.82 162	53.33 179	78.23 154	84.79 48	61.30 100	70.41 162	81.04 286	52.41 112	87.12 69	64.61 163	82.49 105	85.41 174
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
V42		68.65 217	67.35 229	72.56 196	68.93 418	50.18 257	72.90 304	79.47 186	56.92 210	69.45 180	80.26 302	46.29 210	82.99 176	64.07 164	67.82 361	84.53 207

3Dnovator+	66.72 4	75.84 55	74.57 68	79.66 9	82.40 88	59.92 51	85.83 27	86.32 18	66.92 7	67.80 222	89.24 60	42.03 260	89.38 25	64.07 164	86.50 63	89.69 4

v1144		70.42 164	69.31 174	73.76 153	73.22 331	50.64 241	77.83 169	81.43 140	58.58 172	69.40 181	81.16 283	47.53 191	85.29 127	64.01 166	70.64 312	85.34 177

Effi-MVS+		73.31 97	72.54 109	75.62 91	77.87 199	53.64 167	79.62 124	79.61 183	61.63 95	72.02 137	82.61 242	56.44 47	85.97 108	63.99 167	79.07 167	87.25 85

MGCFI-Net		72.45 118	73.34 95	69.81 279	77.77 203	43.21 365	75.84 235	81.18 154	59.59 151	75.45 56	86.64 128	57.74 35	77.94 315	63.92 168	81.90 112	88.30 36

SDMVSNet		68.03 235	68.10 210	67.84 309	77.13 235	48.72 293	65.32 406	79.10 191	58.02 183	65.08 281	82.55 248	47.83 185	73.40 374	63.92 168	73.92 256	81.41 296

KinetiMVS		71.26 143	70.16 157	74.57 117	74.59 303	52.77 196	75.91 232	81.20 153	60.72 114	69.10 190	85.71 168	41.67 271	83.53 164	63.91 170	78.62 180	87.42 74

xiu_mvs_v1_base_debu		68.58 219	67.28 231	72.48 200	78.19 186	57.19 103	75.28 244	75.09 299	51.61 329	70.04 166	81.41 280	32.79 382	79.02 294	63.81 171	77.31 204	81.22 304

xiu_mvs_v1_base		68.58 219	67.28 231	72.48 200	78.19 186	57.19 103	75.28 244	75.09 299	51.61 329	70.04 166	81.41 280	32.79 382	79.02 294	63.81 171	77.31 204	81.22 304

xiu_mvs_v1_base_debi		68.58 219	67.28 231	72.48 200	78.19 186	57.19 103	75.28 244	75.09 299	51.61 329	70.04 166	81.41 280	32.79 382	79.02 294	63.81 171	77.31 204	81.22 304

viewdifsd2359ckpt09		73.42 93	72.45 111	76.30 77	77.25 227	53.27 180	80.36 107	82.48 122	57.96 186	72.24 133	85.73 167	53.22 97	86.27 98	63.79 174	79.06 168	89.36 7

Elysia		70.19 171	68.29 203	75.88 82	74.15 316	54.33 154	78.26 146	83.21 103	55.04 266	67.28 231	83.59 223	30.16 409	86.11 102	63.67 175	79.26 158	87.20 87

StellarMVS		70.19 171	68.29 203	75.88 82	74.15 316	54.33 154	78.26 146	83.21 103	55.04 266	67.28 231	83.59 223	30.16 409	86.11 102	63.67 175	79.26 158	87.20 87

v8		70.33 167	69.28 175	73.49 170	73.15 333	50.22 256	78.62 140	80.78 164	60.79 111	66.45 250	82.11 266	49.35 165	84.98 132	63.58 177	68.71 353	85.28 180

jajsoiax		68.25 229	66.45 249	73.66 161	75.62 273	55.49 137	80.82 101	78.51 214	52.33 318	64.33 294	84.11 209	28.28 430	81.81 218	63.48 178	70.62 313	83.67 241

mvs_tets		68.18 232	66.36 255	73.63 164	75.61 274	55.35 141	80.77 102	78.56 212	52.48 317	64.27 296	84.10 210	27.45 439	81.84 217	63.45 179	70.56 315	83.69 240

viewdifsd2359ckpt11		69.13 205	68.38 201	71.38 237	71.57 365	48.61 294	73.22 297	73.18 330	57.65 195	70.67 156	84.73 188	50.03 152	79.80 266	63.25 180	71.10 308	85.74 155

viewmsd2359difaftdt		69.13 205	68.38 201	71.38 237	71.57 365	48.61 294	73.22 297	73.18 330	57.65 195	70.67 156	84.73 188	50.03 152	79.80 266	63.25 180	71.10 308	85.74 155

AstraMVS		67.86 241	66.83 242	70.93 254	73.50 328	49.34 278	73.28 295	74.01 318	55.45 250	68.10 210	83.28 230	38.93 307	79.14 286	63.22 182	71.74 299	84.30 214

LuminaMVS		68.24 230	66.82 243	72.51 199	73.46 330	53.60 169	76.23 222	78.88 198	52.78 309	68.08 211	80.13 304	32.70 387	81.41 225	63.16 183	75.97 229	82.53 274

viewdifsd2359ckpt13		72.40 121	71.79 120	74.22 131	75.63 272	51.77 221	78.67 138	83.13 110	57.08 204	71.59 143	85.36 178	53.10 101	82.64 200	63.07 184	78.51 182	88.24 39

v144192		69.71 183	68.51 193	73.33 177	73.10 334	50.13 258	77.54 178	80.64 165	56.65 214	68.57 195	80.55 296	46.87 205	84.96 134	62.98 185	69.66 338	84.89 196

v1192		69.97 176	68.68 190	73.85 148	73.19 332	50.94 229	77.68 174	81.36 143	57.51 199	68.95 191	80.85 293	45.28 224	85.33 126	62.97 186	70.37 318	85.27 181

v10		70.21 169	69.02 180	73.81 150	73.51 327	50.92 231	78.74 136	81.39 141	60.05 136	66.39 251	81.83 271	47.58 190	85.41 125	62.80 187	68.86 352	85.09 188

OMC-MVS		71.40 142	70.60 146	73.78 151	76.60 256	53.15 183	79.74 121	79.78 179	58.37 176	68.75 192	86.45 140	45.43 221	80.60 250	62.58 188	77.73 195	87.58 69

XVG-OURS-SEG-HR		68.81 213	67.47 224	72.82 191	74.40 309	56.87 111	70.59 348	79.04 194	54.77 274	66.99 238	86.01 156	39.57 296	78.21 311	62.54 189	73.33 272	83.37 250

EPNet		73.09 103	72.16 114	75.90 81	75.95 267	56.28 116	83.05 67	72.39 339	66.53 11	65.27 274	87.00 115	50.40 148	85.47 122	62.48 190	86.32 65	85.94 140
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v1921920		69.47 196	68.17 207	73.36 176	73.06 335	50.10 259	77.39 183	80.56 166	56.58 223	68.59 193	80.37 298	44.72 232	84.98 132	62.47 191	69.82 332	85.00 190

c3_l		68.33 227	67.56 218	70.62 263	70.87 380	46.21 327	74.47 266	78.80 201	56.22 232	66.19 254	78.53 336	51.88 122	81.40 226	62.08 192	69.04 348	84.25 215

AUN-MVS		68.45 226	66.41 253	74.57 117	79.53 141	57.08 109	73.93 280	75.23 295	54.44 282	66.69 244	81.85 270	37.10 333	82.89 189	62.07 193	66.84 369	83.75 238

XVG-OURS		68.76 216	67.37 227	72.90 188	74.32 312	57.22 101	70.09 357	78.81 200	55.24 255	67.79 223	85.81 166	36.54 339	78.28 310	62.04 194	75.74 233	83.19 256

v1240		69.24 203	67.91 212	73.25 180	73.02 337	49.82 264	77.21 193	80.54 167	56.43 225	68.34 200	80.51 297	43.33 246	84.99 130	62.03 195	69.77 335	84.95 194

ET-MVSNet_ETH3D		67.96 238	65.72 267	74.68 110	76.67 254	55.62 134	75.11 249	74.74 304	52.91 307	60.03 355	80.12 305	33.68 371	82.64 200	61.86 196	76.34 221	85.78 149

VDD-MVS		72.50 116	72.09 115	73.75 155	81.58 99	49.69 272	77.76 173	77.63 236	63.21 55	73.21 108	89.02 62	42.14 259	83.32 168	61.72 197	82.50 104	88.25 38

casdiffseed414692147		73.73 87	73.22 96	75.28 99	76.76 251	52.16 211	80.05 112	83.01 112	63.38 47	73.35 104	87.11 113	53.22 97	84.14 149	61.71 198	80.38 133	89.55 6

PS-MVSNAJ		70.51 161	69.70 165	72.93 187	81.52 100	55.79 128	74.92 256	79.00 195	55.04 266	69.88 173	78.66 331	47.05 200	82.19 210	61.61 199	79.58 148	80.83 315

xiu_mvs_v2_base		70.52 160	69.75 163	72.84 189	81.21 109	55.63 132	75.11 249	78.92 197	54.92 271	69.96 172	79.68 315	47.00 204	82.09 212	61.60 200	79.37 151	80.81 316

cl22		67.47 249	66.45 249	70.54 265	69.85 403	46.49 323	73.85 283	77.35 244	55.07 263	65.51 269	77.92 345	47.64 189	81.10 235	61.58 201	69.32 342	84.01 224

viewmambaseed2359dif		68.91 210	68.18 206	71.11 249	70.21 393	48.05 309	72.28 318	75.90 277	51.96 324	70.93 153	84.47 202	51.37 133	78.59 305	61.55 202	74.97 243	86.68 107

miper_ehance_all_eth		68.03 235	67.24 235	70.40 267	70.54 384	46.21 327	73.98 276	78.68 205	55.07 263	66.05 258	77.80 352	52.16 118	81.31 229	61.53 203	69.32 342	83.67 241

MG-MVS		73.96 83	73.89 82	74.16 133	85.65 44	49.69 272	81.59 93	81.29 149	61.45 96	71.05 151	88.11 80	51.77 126	87.73 55	61.05 204	83.09 91	85.05 189

guyue		68.10 234	67.23 237	70.71 261	73.67 326	49.27 281	73.65 287	76.04 276	55.62 246	67.84 220	82.26 258	41.24 281	78.91 301	61.01 205	73.72 260	83.94 226

miper_enhance_ethall		67.11 258	66.09 262	70.17 271	69.21 412	45.98 330	72.85 305	78.41 221	51.38 337	65.65 267	75.98 387	51.17 137	81.25 230	60.82 206	69.32 342	83.29 253

ACMM	61.98 7	70.80 156	69.73 164	74.02 142	80.59 122	58.59 84	82.68 75	82.02 129	55.46 249	67.18 235	84.39 204	38.51 313	83.17 172	60.65 207	76.10 228	80.30 331
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+-dtu		69.64 188	67.53 221	75.95 80	76.10 265	62.29 15	80.20 111	76.06 275	59.83 145	65.26 277	77.09 364	41.56 274	84.02 154	60.60 208	71.09 310	81.53 294

PVSNet_Blended_VisFu		71.45 141	70.39 150	74.65 112	82.01 92	58.82 81	79.93 116	80.35 173	55.09 260	65.82 266	82.16 263	49.17 169	82.64 200	60.34 209	78.62 180	82.50 277

MVSTER		67.16 257	65.58 270	71.88 214	70.37 390	49.70 270	70.25 355	78.45 218	51.52 332	69.16 188	80.37 298	38.45 314	82.50 204	60.19 210	71.46 303	83.44 249

EIA-MVS		71.78 133	70.60 146	75.30 97	79.85 134	53.54 171	77.27 191	83.26 102	57.92 188	66.49 248	79.39 321	52.07 120	86.69 80	60.05 211	79.14 166	85.66 159

v148		68.24 230	67.19 238	71.40 236	70.43 387	47.77 312	75.76 236	77.03 252	58.91 162	67.36 229	80.10 306	48.60 178	81.89 215	60.01 212	66.52 373	84.53 207

test_vis1_n_1920		58.86 370	59.06 359	58.25 418	63.76 459	43.14 367	67.49 386	66.36 393	40.22 459	65.89 263	71.95 424	31.04 401	59.75 453	59.94 213	64.90 383	71.85 443

CANet_DTU		68.18 232	67.71 217	69.59 282	74.83 294	46.24 326	78.66 139	76.85 256	59.60 148	63.45 305	82.09 267	35.25 350	77.41 332	59.88 214	78.76 175	85.14 184

IterMVS-LS		69.22 204	68.48 194	71.43 235	74.44 308	49.40 276	76.23 222	77.55 237	59.60 148	65.85 265	81.59 278	51.28 135	81.58 222	59.87 215	69.90 331	83.30 251
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		69.27 202	68.44 198	71.73 220	74.47 306	49.39 277	75.20 247	78.45 218	59.60 148	69.16 188	76.51 377	51.29 134	82.50 204	59.86 216	71.45 304	83.30 251

3Dnovator	64.47 5	72.49 117	71.39 128	75.79 84	77.70 206	58.99 78	80.66 105	83.15 108	62.24 80	65.46 270	86.59 133	42.38 258	85.52 118	59.59 217	84.72 73	82.85 266

eth_miper_zixun_eth		67.63 246	66.28 259	71.67 224	71.60 364	48.33 299	73.68 286	77.88 229	55.80 240	65.91 261	78.62 334	47.35 197	82.88 190	59.45 218	66.25 374	83.81 233

DIV-MVS_self_test		67.18 255	66.26 260	69.94 274	70.20 394	45.74 332	73.29 294	76.83 258	55.10 258	65.27 274	79.58 316	47.38 196	80.53 252	59.43 219	69.22 346	83.54 246

cl____		67.18 255	66.26 260	69.94 274	70.20 394	45.74 332	73.30 292	76.83 258	55.10 258	65.27 274	79.57 317	47.39 195	80.53 252	59.41 220	69.22 346	83.53 247

mvsmamba		68.47 224	66.56 246	74.21 132	79.60 138	52.95 187	74.94 255	75.48 289	52.09 323	60.10 353	83.27 231	36.54 339	84.70 140	59.32 221	77.69 196	84.99 192

icg_test_0407_2		66.41 274	66.75 244	65.37 360	77.06 240	49.73 266	63.79 422	78.60 207	52.70 310	66.19 254	82.58 243	45.17 227	63.65 438	59.20 222	75.46 238	82.74 268

IMVS_0407		68.90 211	67.93 211	71.82 216	77.06 240	49.73 266	74.40 269	78.60 207	52.70 310	66.19 254	82.58 243	45.17 227	83.00 175	59.20 222	75.46 238	82.74 268

IMVS_0404		64.63 297	64.22 285	65.88 350	77.06 240	49.73 266	64.40 415	78.60 207	52.70 310	53.16 442	82.58 243	34.82 355	65.16 432	59.20 222	75.46 238	82.74 268

IMVS_0403		69.09 207	68.14 208	71.95 211	77.06 240	49.73 266	74.51 264	78.60 207	52.70 310	66.69 244	82.58 243	46.43 208	83.38 167	59.20 222	75.46 238	82.74 268

VortexMVS		66.41 274	65.50 271	69.16 292	73.75 322	48.14 303	73.41 290	78.28 225	53.73 296	64.98 287	78.33 337	40.62 286	79.07 289	58.88 226	67.50 364	80.26 332

SSM_0407		70.41 165	68.96 183	74.75 107	78.65 167	53.46 173	77.28 190	80.00 177	53.88 291	68.14 205	84.61 195	43.21 247	86.26 99	58.80 227	76.11 225	84.54 204

SSM_0404		70.84 152	69.41 173	75.12 101	79.20 150	53.86 160	77.89 165	80.00 177	53.88 291	69.40 181	84.61 195	43.21 247	86.56 85	58.80 227	77.68 197	84.95 194

reproduce_monomvs		62.56 324	61.20 333	66.62 333	70.62 383	44.30 350	70.13 356	73.13 333	54.78 273	61.13 345	76.37 380	25.63 455	75.63 364	58.75 229	60.29 433	79.93 338

旧先验2							76.08 226		45.32 421	76.55 49			65.56 430	58.75 229

VDDNet		71.81 132	71.33 130	73.26 179	82.80 85	47.60 315	78.74 136	75.27 293	59.59 151	72.94 119	89.40 57	41.51 276	83.91 156	58.75 229	82.99 94	88.26 37

mmtdpeth		60.40 357	59.12 357	64.27 371	69.59 405	48.99 286	70.67 347	70.06 360	54.96 270	62.78 316	73.26 415	27.00 444	67.66 412	58.44 232	45.29 481	76.16 393

dtuplus		68.48 223	67.76 213	70.63 262	70.33 391	48.09 305	72.62 308	75.88 279	52.33 318	71.09 150	84.66 192	50.09 151	77.93 317	58.02 233	74.82 246	85.87 144

114514_t		70.83 154	69.56 167	74.64 113	86.21 33	54.63 150	82.34 81	81.81 132	48.22 384	63.01 314	85.83 163	40.92 285	87.10 70	57.91 234	79.79 144	82.18 283

Vis-MVSNet		72.18 124	71.37 129	74.61 114	81.29 106	55.41 138	80.90 100	78.28 225	60.73 113	69.23 187	88.09 81	44.36 237	82.65 199	57.68 235	81.75 116	85.77 152
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_cas_vis1_n_1920		56.91 388	56.71 381	57.51 427	59.13 482	45.40 338	63.58 423	61.29 439	36.24 470	67.14 236	71.85 425	29.89 413	56.69 469	57.65 236	63.58 398	70.46 458

PAPM_NR		72.63 114	71.80 119	75.13 100	81.72 98	53.42 177	79.91 117	83.28 101	59.14 158	66.31 253	85.90 160	51.86 123	86.06 104	57.45 237	80.62 127	85.91 142

LFMVS		71.78 133	71.59 122	72.32 206	83.40 77	46.38 324	79.75 120	71.08 348	64.18 35	72.80 124	88.64 73	42.58 255	83.72 159	57.41 238	84.49 78	86.86 98

v7n		69.01 209	67.36 228	73.98 145	72.51 347	52.65 198	78.54 144	81.30 148	60.26 131	62.67 320	81.62 275	43.61 243	84.49 144	57.01 239	68.70 354	84.79 199

GeoE		71.01 148	70.15 158	73.60 166	79.57 140	52.17 210	78.93 133	78.12 227	58.02 183	67.76 225	83.87 215	52.36 113	82.72 197	56.90 240	75.79 232	85.92 141

FA-MVS(test-final)		69.82 180	68.48 194	73.84 149	78.44 175	50.04 261	75.58 240	78.99 196	58.16 179	67.59 226	82.14 264	42.66 253	85.63 114	56.60 241	76.19 224	85.84 147

mamba_0408		67.78 243	65.42 272	74.85 106	78.65 167	53.46 173	50.83 480	79.09 192	53.75 294	68.14 205	83.83 216	41.79 269	86.56 85	56.58 242	76.11 225	84.54 204

SSM_04072		64.98 293	65.42 272	63.68 375	78.65 167	53.46 173	50.83 480	79.09 192	53.75 294	68.14 205	83.83 216	41.79 269	53.03 483	56.58 242	76.11 225	84.54 204

mvs_anonymous		68.03 235	67.51 222	69.59 282	72.08 356	44.57 348	71.99 322	75.23 295	51.67 327	67.06 237	82.57 247	54.68 74	77.94 315	56.56 244	75.71 234	86.26 133

Patchmatch-RL test		58.16 379	55.49 395	66.15 343	67.92 433	48.89 290	60.66 444	51.07 476	47.86 393	59.36 365	62.71 477	34.02 366	72.27 383	56.41 245	59.40 436	77.30 378

miper_lstm_enhance		62.03 337	60.88 338	65.49 357	66.71 443	46.25 325	56.29 464	75.70 282	50.68 348	61.27 343	75.48 394	40.21 289	68.03 410	56.31 246	65.25 381	82.18 283

thisisatest0530		67.92 239	65.78 266	74.33 125	76.29 262	51.03 228	76.89 205	74.25 314	53.67 298	65.59 268	81.76 273	35.15 351	85.50 120	55.94 247	72.47 287	86.47 117

EPP-MVSNet		72.16 127	71.31 131	74.71 108	78.68 166	49.70 270	82.10 86	81.65 134	60.40 122	65.94 260	85.84 162	51.74 127	86.37 94	55.93 248	79.55 150	88.07 49

PVSNet_BlendedMVS		68.56 222	67.72 215	71.07 251	77.03 246	50.57 244	74.50 265	81.52 136	53.66 299	64.22 299	79.72 314	49.13 170	82.87 191	55.82 249	73.92 256	79.77 345

PVSNet_Blended		68.59 218	67.72 215	71.19 244	77.03 246	50.57 244	72.51 313	81.52 136	51.91 325	64.22 299	77.77 355	49.13 170	82.87 191	55.82 249	79.58 148	80.14 335

PAPR		71.72 136	70.82 141	74.41 123	81.20 110	51.17 225	79.55 126	83.33 97	55.81 239	66.93 240	84.61 195	50.95 141	86.06 104	55.79 251	79.20 161	86.00 138

tttt0517		67.83 242	65.66 268	74.33 125	76.69 252	50.82 234	77.86 167	73.99 319	54.54 280	64.64 291	82.53 251	35.06 352	85.50 120	55.71 252	69.91 330	86.67 108

IterMVS-SCA-FT		62.49 325	61.52 325	65.40 359	71.99 359	50.80 235	71.15 337	69.63 364	45.71 419	60.61 349	77.93 344	37.45 325	65.99 428	55.67 253	63.50 399	79.42 348

tt0805		67.77 244	67.24 235	69.34 287	74.87 292	40.08 401	77.36 184	81.37 142	55.31 252	66.33 252	84.65 193	37.35 327	82.55 203	55.65 254	72.28 292	85.39 175

XVG-ACMP-BASELINE		64.36 302	62.23 317	70.74 259	72.35 352	52.45 206	70.80 345	78.45 218	53.84 293	59.87 358	81.10 285	16.24 480	79.32 278	55.64 255	71.76 298	80.47 322

Anonymous20231211		69.28 201	68.47 196	71.73 220	80.28 123	47.18 319	79.98 114	82.37 124	54.61 277	67.24 233	84.01 212	39.43 297	82.41 207	55.45 256	72.83 281	85.62 161

GA-MVS		65.53 284	63.70 293	71.02 253	70.87 380	48.10 304	70.48 350	74.40 309	56.69 213	64.70 290	76.77 369	33.66 372	81.10 235	55.42 257	70.32 321	83.87 231

test_yl		69.69 184	69.13 177	71.36 239	78.37 179	45.74 332	74.71 260	80.20 174	57.91 189	70.01 170	83.83 216	42.44 256	82.87 191	54.97 258	79.72 145	85.48 165

DCV-MVSNet		69.69 184	69.13 177	71.36 239	78.37 179	45.74 332	74.71 260	80.20 174	57.91 189	70.01 170	83.83 216	42.44 256	82.87 191	54.97 258	79.72 145	85.48 165

1314		64.61 298	63.21 305	68.80 296	71.87 361	47.46 316	73.95 278	78.39 223	42.88 444	59.97 356	76.60 376	38.11 320	79.39 277	54.84 260	72.32 290	79.55 346

Fast-Effi-MVS+-dtu		67.37 250	65.33 276	73.48 171	72.94 338	57.78 94	77.47 181	76.88 255	57.60 198	61.97 332	76.85 368	39.31 300	80.49 255	54.72 261	70.28 322	82.17 285

UniMVSNet_NR-MVSNet		71.11 145	71.00 138	71.44 233	79.20 150	44.13 351	76.02 230	82.60 121	66.48 12	68.20 201	84.60 198	56.82 44	82.82 195	54.62 262	70.43 316	87.36 81

DU-MVS		70.01 174	69.53 168	71.44 233	78.05 193	44.13 351	75.01 252	81.51 138	64.37 31	68.20 201	84.52 199	49.12 172	82.82 195	54.62 262	70.43 316	87.37 79

FIs		70.82 155	71.43 126	68.98 294	78.33 182	38.14 422	76.96 202	83.59 86	61.02 106	67.33 230	86.73 125	55.07 67	81.64 219	54.61 264	79.22 160	87.14 90

VPA-MVSNet		69.02 208	69.47 170	67.69 313	77.42 221	41.00 394	74.04 275	79.68 181	60.06 135	69.26 186	84.81 186	51.06 139	77.58 329	54.44 265	74.43 250	84.48 209

MonoMVSNet		64.15 305	63.31 303	66.69 329	70.51 385	44.12 353	74.47 266	74.21 315	57.81 191	63.03 312	76.62 373	38.33 316	77.31 335	54.22 266	60.59 432	78.64 359

Anonymous20240529		69.91 177	69.02 180	72.56 196	80.19 128	47.65 313	77.56 177	80.99 160	55.45 250	69.88 173	86.76 121	39.24 303	82.18 211	54.04 267	77.10 211	87.85 55

UniMVSNet (Re)		70.63 159	70.20 155	71.89 213	78.55 171	45.29 339	75.94 231	82.92 114	63.68 43	68.16 204	83.59 223	53.89 85	83.49 166	53.97 268	71.12 307	86.89 96

D2MVS		62.30 332	60.29 347	68.34 304	66.46 446	48.42 298	65.70 398	73.42 325	47.71 394	58.16 383	75.02 398	30.51 404	77.71 325	53.96 269	71.68 301	78.90 357

原ACMM1				74.69 109	85.39 49	59.40 59		83.42 91	51.47 336	70.27 164	86.61 132	48.61 177	86.51 90	53.85 270	87.96 43	78.16 364

无先验							79.66 123	74.30 312	48.40 382				80.78 248	53.62 271		79.03 355

UA-Net		73.13 102	72.93 101	73.76 153	83.58 73	51.66 222	78.75 135	77.66 235	67.75 4	72.61 128	89.42 56	49.82 156	83.29 169	53.61 272	83.14 90	86.32 128

VNet		69.68 186	70.19 156	68.16 307	79.73 136	41.63 387	70.53 349	77.38 243	60.37 125	70.69 155	86.63 130	51.08 138	77.09 339	53.61 272	81.69 118	85.75 154

Fast-Effi-MVS+		70.28 168	69.12 179	73.73 157	78.50 172	51.50 223	75.01 252	79.46 187	56.16 233	68.59 193	79.55 318	53.97 83	84.05 151	53.34 274	77.53 199	85.65 160

testdata				64.66 366	81.52 100	52.93 188		65.29 402	46.09 414	73.88 93	87.46 96	38.08 321	66.26 425	53.31 275	78.48 183	74.78 412

thisisatest0515		65.83 280	63.50 298	72.82 191	73.75 322	49.50 275	71.32 332	73.12 334	49.39 365	63.82 301	76.50 379	34.95 354	84.84 139	53.20 276	75.49 237	84.13 221

MVS		67.37 250	66.33 256	70.51 266	75.46 278	50.94 229	73.95 278	81.85 131	41.57 451	62.54 324	78.57 335	47.98 182	85.47 122	52.97 277	82.05 108	75.14 404

IterMVS		62.79 322	61.27 330	67.35 320	69.37 409	52.04 215	71.17 335	68.24 378	52.63 316	59.82 359	76.91 367	37.32 328	72.36 380	52.80 278	63.19 403	77.66 373
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		69.80 182	70.58 148	67.46 317	77.61 216	34.73 456	76.05 228	83.19 107	60.84 110	65.88 264	86.46 139	54.52 76	80.76 249	52.52 279	78.12 190	86.91 95

TranMVSNet+NR-MVSNet		70.36 166	70.10 160	71.17 246	78.64 170	42.97 372	76.53 215	81.16 156	66.95 6	68.53 196	85.42 176	51.61 129	83.07 173	52.32 280	69.70 337	87.46 72

Baseline_NR-MVSNet		67.05 259	67.56 218	65.50 356	75.65 271	37.70 428	75.42 241	74.65 307	59.90 140	68.14 205	83.15 235	49.12 172	77.20 337	52.23 281	69.78 333	81.60 291

UniMVSNet_ETH3D		67.60 247	67.07 240	69.18 291	77.39 222	42.29 378	74.18 273	75.59 285	60.37 125	66.77 242	86.06 153	37.64 323	78.93 299	52.16 282	73.49 267	86.32 128

ECVR-MVS		67.72 245	67.51 222	68.35 303	79.46 143	36.29 445	74.79 259	66.93 388	58.72 166	67.19 234	88.05 83	36.10 342	81.38 227	52.07 283	84.25 80	87.39 77

test1111		67.21 252	67.14 239	67.42 318	79.24 149	34.76 455	73.89 282	65.65 398	58.71 168	66.96 239	87.95 87	36.09 343	80.53 252	52.03 284	83.79 86	86.97 94

test2506		65.33 288	64.61 282	67.50 314	79.46 143	34.19 461	74.43 268	51.92 472	58.72 166	66.75 243	88.05 83	25.99 452	80.92 243	51.94 285	84.25 80	87.39 77

API-MVS		72.17 125	71.41 127	74.45 122	81.95 95	57.22 101	84.03 56	80.38 172	59.89 144	68.40 198	82.33 255	49.64 159	87.83 53	51.87 286	84.16 83	78.30 362

PCF-MVS	61.88 8	70.95 151	69.49 169	75.35 95	77.63 211	55.71 129	76.04 229	81.81 132	50.30 353	69.66 176	85.40 177	52.51 109	84.89 136	51.82 287	80.24 136	85.45 170
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DP-MVS Recon		72.15 128	70.73 143	76.40 74	86.57 26	57.99 90	81.15 98	82.96 113	57.03 207	66.78 241	85.56 170	44.50 235	88.11 44	51.77 288	80.23 137	83.10 261

UGNet		68.81 213	67.39 226	73.06 183	78.33 182	54.47 151	79.77 119	75.40 291	60.45 120	63.22 307	84.40 203	32.71 386	80.91 244	51.71 289	80.56 131	83.81 233
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
MAR-MVS		71.51 138	70.15 158	75.60 92	81.84 96	59.39 60	81.38 95	82.90 115	54.90 272	68.08 211	78.70 329	47.73 186	85.51 119	51.68 290	84.17 82	81.88 289
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
VPNet		67.52 248	68.11 209	65.74 352	79.18 152	36.80 437	72.17 320	72.83 335	62.04 87	67.79 223	85.83 163	48.88 174	76.60 355	51.30 291	72.97 279	83.81 233

test_fmvs1_n		51.37 428	50.35 431	54.42 442	52.85 490	37.71 427	61.16 441	51.93 471	28.15 483	63.81 302	69.73 448	13.72 484	53.95 480	51.16 292	60.65 430	71.59 446

test_fmvs1		51.32 430	50.48 430	53.81 445	53.57 488	37.51 429	60.63 445	51.16 474	28.02 485	63.62 303	69.23 452	16.41 479	53.93 481	51.01 293	60.70 429	69.99 462

QAPM		70.05 173	68.81 187	73.78 151	76.54 258	53.43 176	83.23 65	83.48 88	52.89 308	65.90 262	86.29 145	41.55 275	86.49 91	51.01 293	78.40 186	81.42 295

NR-MVSNet		69.54 192	68.85 185	71.59 227	78.05 193	43.81 356	74.20 272	80.86 163	65.18 15	62.76 318	84.52 199	52.35 114	83.59 163	50.96 295	70.78 311	87.37 79

IB-MVS	56.42 12	65.40 287	62.73 311	73.40 175	74.89 290	52.78 195	73.09 301	75.13 298	55.69 242	58.48 378	73.73 410	32.86 381	86.32 96	50.63 296	70.11 325	81.10 309
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
PM-MVS		52.33 423	50.19 432	58.75 415	62.10 468	45.14 340	65.75 397	40.38 499	43.60 435	53.52 438	72.65 416	9.16 498	65.87 429	50.41 297	54.18 458	65.24 475

cascas		65.98 278	63.42 300	73.64 163	77.26 226	52.58 201	72.26 319	77.21 247	48.56 377	61.21 344	74.60 402	32.57 393	85.82 112	50.38 298	76.75 216	82.52 276

IS-MVSNet		71.57 137	71.00 138	73.27 178	78.86 160	45.63 336	80.22 110	78.69 204	64.14 38	66.46 249	87.36 100	49.30 166	85.60 115	50.26 299	83.71 89	88.59 28

WR-MVS		68.47 224	68.47 196	68.44 302	80.20 127	39.84 404	73.75 285	76.07 274	64.68 25	68.11 209	83.63 222	50.39 149	79.14 286	49.78 300	69.66 338	86.34 123

CVMVSNet		59.63 365	59.14 356	61.08 399	74.47 306	38.84 415	75.20 247	68.74 374	31.15 479	58.24 381	76.51 377	32.39 395	68.58 406	49.77 301	65.84 377	75.81 396

CostFormer		64.04 307	62.51 312	68.61 299	71.88 360	45.77 331	71.30 333	70.60 356	47.55 397	64.31 295	76.61 375	41.63 272	79.62 271	49.74 302	69.00 349	80.42 324

新几何1				70.76 257	85.66 43	61.13 30		66.43 392	44.68 425	70.29 163	86.64 128	41.29 278	75.23 366	49.72 303	81.75 116	75.93 395

test-LLR		58.15 380	58.13 370	58.22 419	68.57 421	44.80 342	65.46 403	57.92 451	50.08 356	55.44 411	69.82 446	32.62 390	57.44 465	49.66 304	73.62 263	72.41 436

test-mter		56.42 393	55.82 391	58.22 419	68.57 421	44.80 342	65.46 403	57.92 451	39.94 463	55.44 411	69.82 446	21.92 466	57.44 465	49.66 304	73.62 263	72.41 436

Anonymous202405211		66.84 264	65.99 263	69.40 286	80.19 128	42.21 380	71.11 338	71.31 347	58.80 164	67.90 213	86.39 141	29.83 414	79.65 269	49.60 306	78.78 173	86.33 126

test_fmvs2		48.69 437	47.49 442	52.29 457	48.63 497	33.06 470	57.76 457	48.05 486	25.71 489	59.76 361	69.60 450	11.57 491	52.23 487	49.45 307	56.86 446	71.58 447

tpmrst		58.24 378	58.70 363	56.84 428	66.97 440	34.32 459	69.57 367	61.14 440	47.17 404	58.58 377	71.60 426	41.28 279	60.41 449	49.20 308	62.84 406	75.78 397

test_vis1_n		49.89 435	48.69 437	53.50 448	53.97 487	37.38 430	61.53 435	47.33 488	28.54 482	59.62 363	67.10 465	13.52 485	52.27 486	49.07 309	57.52 443	70.84 456

pm-mvs1		65.24 289	64.97 280	66.04 346	72.38 351	39.40 411	72.62 308	75.63 283	55.53 247	62.35 331	83.18 234	47.45 193	76.47 358	49.06 310	66.54 372	82.24 282

gm-plane-assit					71.40 372	41.72 386			48.85 374		73.31 413		82.48 206	48.90 311

CMPMVS	42.80 21	57.81 383	55.97 389	63.32 378	60.98 476	47.38 317	64.66 413	69.50 367	32.06 477	46.83 469	77.80 352	29.50 417	71.36 388	48.68 312	73.75 259	71.21 452
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ab-mvs		66.65 268	66.42 252	67.37 319	76.17 264	41.73 384	70.41 352	76.14 273	53.99 288	65.98 259	83.51 227	49.48 161	76.24 361	48.60 313	73.46 269	84.14 220

OurMVSNet-221017-0		61.37 349	58.63 364	69.61 281	72.05 357	48.06 307	73.93 280	72.51 337	47.23 403	54.74 422	80.92 290	21.49 470	81.24 231	48.57 314	56.22 450	79.53 347

OpenMVS	61.03 9	68.85 212	67.56 218	72.70 193	74.26 314	53.99 159	81.21 97	81.34 147	52.70 310	62.75 319	85.55 172	38.86 308	84.14 149	48.41 315	83.01 92	79.97 337

testing91		64.46 300	63.80 291	66.47 335	78.43 176	40.06 402	67.63 383	69.59 365	59.06 159	63.18 309	78.05 341	34.05 364	76.99 344	48.30 316	75.87 231	82.37 280

testing99		64.05 306	63.29 304	66.34 337	78.17 189	39.76 406	67.33 388	68.00 379	58.60 171	63.03 312	78.10 340	32.57 393	76.94 346	48.22 317	75.58 235	82.34 281

baseline2		63.42 312	61.26 331	69.89 278	72.55 345	47.62 314	71.54 329	68.38 376	50.11 355	54.82 421	75.55 392	43.06 250	80.96 240	48.13 318	67.16 368	81.11 308

TESTMET0.1,1		55.28 404	54.90 400	56.42 430	66.56 444	43.67 358	65.46 403	56.27 462	39.18 465	53.83 432	67.44 461	24.21 461	55.46 476	48.04 319	73.11 277	70.13 461

test_fmvs3		44.30 445	42.55 448	49.55 463	42.83 502	27.15 494	53.03 472	44.93 492	22.03 497	53.69 435	64.94 472	4.21 506	49.63 490	47.47 320	49.82 473	71.88 442

usedtu_blend_shiyan5		62.63 323	60.77 341	68.20 305	68.53 423	44.64 345	73.47 289	77.00 253	51.91 325	57.10 394	69.95 442	38.83 309	79.61 272	47.44 321	62.67 407	80.37 327

blend_shiyan4		61.38 348	59.10 358	68.20 305	68.94 417	44.64 345	70.81 344	76.52 264	51.63 328	57.56 390	69.94 445	28.30 429	79.61 272	47.44 321	60.78 428	80.36 330

K. test v3		60.47 356	57.11 374	70.56 264	73.74 324	48.22 301	75.10 251	62.55 429	58.27 178	53.62 436	76.31 381	27.81 435	81.59 221	47.42 323	39.18 489	81.88 289

pmmvs6		63.69 310	62.82 310	66.27 340	70.63 382	39.27 412	73.13 300	75.47 290	52.69 315	59.75 362	82.30 256	39.71 295	77.03 341	47.40 324	64.35 390	82.53 274

blended_shiyan8		62.46 327	60.71 342	67.71 311	69.15 414	43.43 360	70.83 342	76.52 264	51.49 334	57.67 387	71.36 430	39.38 298	79.07 289	47.37 325	62.67 407	80.62 320

blended_shiyan6		62.46 327	60.71 342	67.71 311	69.14 415	43.42 361	70.82 343	76.52 264	51.50 333	57.64 388	71.37 429	39.38 298	79.08 288	47.36 326	62.67 407	80.65 319

sd_testset		64.46 300	64.45 283	64.51 368	77.13 235	42.25 379	62.67 429	72.11 342	58.02 183	65.08 281	82.55 248	41.22 282	69.88 400	47.32 327	73.92 256	81.41 296

baseline1		63.81 309	63.87 290	63.62 376	76.29 262	36.36 440	71.78 327	67.29 384	56.05 235	64.23 298	82.95 236	47.11 199	74.41 370	47.30 328	61.85 420	80.10 336

gbinet_0.2-2-1-0.02		62.43 329	60.41 345	68.49 300	68.91 419	43.71 357	71.73 328	75.89 278	52.10 322	58.33 380	69.67 449	36.86 337	80.59 251	47.18 329	63.05 405	81.16 307

GBi-Net		67.21 252	66.55 247	69.19 288	77.63 211	43.33 362	77.31 185	77.83 232	56.62 218	65.04 283	82.70 238	41.85 266	80.33 257	47.18 329	72.76 282	83.92 228

test1		67.21 252	66.55 247	69.19 288	77.63 211	43.33 362	77.31 185	77.83 232	56.62 218	65.04 283	82.70 238	41.85 266	80.33 257	47.18 329	72.76 282	83.92 228

FMVSNet3		66.32 276	65.61 269	68.46 301	76.48 259	42.34 377	74.98 254	77.15 248	55.83 238	65.04 283	81.16 283	39.91 291	80.14 265	47.18 329	72.76 282	82.90 265

wanda-best-256-512		62.00 339	60.17 348	67.49 315	68.53 423	43.07 369	69.65 361	76.38 268	51.26 340	57.10 394	69.95 442	38.83 309	79.04 292	47.14 333	62.67 407	80.37 327

FE-blended-shiyan7		62.00 339	60.17 348	67.49 315	68.53 423	43.07 369	69.65 361	76.38 268	51.26 340	57.10 394	69.95 442	38.83 309	79.04 292	47.14 333	62.67 407	80.37 327

FMVSNet2		66.93 262	66.31 258	68.79 297	77.63 211	42.98 371	76.11 225	77.47 238	56.62 218	65.22 280	82.17 262	41.85 266	80.18 264	47.05 335	72.72 285	83.20 255

testdata2													72.18 385	46.95 336

BH-RMVSNet		68.81 213	67.42 225	72.97 186	80.11 131	52.53 202	74.26 270	76.29 270	58.48 174	68.38 199	84.20 206	42.59 254	83.83 157	46.53 337	75.91 230	82.56 272

AdaColmap		69.99 175	68.66 191	73.97 146	84.94 59	57.83 92	82.63 76	78.71 203	56.28 230	64.34 293	84.14 208	41.57 273	87.06 72	46.45 338	78.88 170	77.02 383

EG-PatchMatch MVS		64.71 295	62.87 308	70.22 268	77.68 208	53.48 172	77.99 163	78.82 199	53.37 301	56.03 407	77.41 360	24.75 460	84.04 152	46.37 339	73.42 271	73.14 425

usedtu_dtu_shiyan1		64.34 303	63.57 295	66.66 330	72.44 349	40.74 397	69.60 364	76.80 260	53.21 303	61.73 337	77.92 345	41.92 264	77.68 326	46.23 340	72.25 293	81.57 292

FE-MVSNET3		64.34 303	63.57 295	66.66 330	72.44 349	40.74 397	69.60 364	76.80 260	53.21 303	61.73 337	77.92 345	41.92 264	77.68 326	46.23 340	72.25 293	81.57 292

1112_ss		64.00 308	63.36 301	65.93 348	79.28 147	42.58 376	71.35 331	72.36 340	46.41 411	60.55 350	77.89 349	46.27 211	73.28 375	46.18 342	69.97 328	81.92 288

FMVSNet1		66.70 267	65.87 264	69.19 288	77.49 219	43.33 362	77.31 185	77.83 232	56.45 224	64.60 292	82.70 238	38.08 321	80.33 257	46.08 343	72.31 291	83.92 228

HyFIR lowres test		65.67 282	63.01 307	73.67 160	79.97 133	55.65 131	69.07 372	75.52 287	42.68 445	63.53 304	77.95 343	40.43 288	81.64 219	46.01 344	71.91 297	83.73 239

lessismore_v0				69.91 276	71.42 371	47.80 310		50.90 477		50.39 457	75.56 391	27.43 440	81.33 228	45.91 345	34.10 495	80.59 321

CHOSEN 1792x2688		65.08 292	62.84 309	71.82 216	81.49 102	56.26 117	66.32 394	74.20 316	40.53 457	63.16 310	78.65 332	41.30 277	77.80 322	45.80 346	74.09 253	81.40 298

LCM-MVSNet-Re		61.88 342	61.35 328	63.46 377	74.58 304	31.48 477	61.42 437	58.14 450	58.71 168	53.02 444	79.55 318	43.07 249	76.80 348	45.69 347	77.96 192	82.11 286

ambc				65.13 364	63.72 461	37.07 434	47.66 488	78.78 202		54.37 429	71.42 427	11.24 493	80.94 241	45.64 348	53.85 462	77.38 377

MS-PatchMatch		62.42 330	61.46 326	65.31 362	75.21 284	52.10 212	72.05 321	74.05 317	46.41 411	57.42 393	74.36 403	34.35 361	77.57 330	45.62 349	73.67 261	66.26 472

ACMH+	57.40 11	66.12 277	64.06 286	72.30 207	77.79 202	52.83 194	80.39 106	78.03 228	57.30 200	57.47 391	82.55 248	27.68 437	84.17 148	45.54 350	69.78 333	79.90 339

testing11		62.81 321	61.90 321	65.54 354	78.38 177	40.76 396	67.59 385	66.78 390	55.48 248	60.13 352	77.11 363	31.67 400	76.79 349	45.53 351	74.45 249	79.06 353

CR-MVSNet		59.91 360	57.90 371	65.96 347	69.96 399	52.07 213	65.31 407	63.15 424	42.48 446	59.36 365	74.84 399	35.83 345	70.75 393	45.50 352	64.65 386	75.06 405

0.4-1-1-0.1		59.29 368	56.70 382	67.07 322	69.35 410	43.16 366	66.59 390	70.87 353	48.59 376	55.11 417	62.25 478	28.22 431	78.92 300	45.49 353	63.79 394	79.14 351

CDS-MVSNet		66.80 265	65.37 274	71.10 250	78.98 157	53.13 185	73.27 296	71.07 349	52.15 321	64.72 289	80.23 303	43.56 244	77.10 338	45.48 354	78.88 170	83.05 262
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CP-MVSNet		66.49 272	66.41 253	66.72 326	77.67 209	36.33 442	76.83 209	79.52 185	62.45 73	62.54 324	83.47 229	46.32 209	78.37 307	45.47 355	63.43 400	85.45 170

BH-untuned		68.27 228	67.29 230	71.21 243	79.74 135	53.22 181	76.06 227	77.46 240	57.19 202	66.10 257	81.61 276	45.37 223	83.50 165	45.42 356	76.68 217	76.91 387

PS-CasMVS		66.42 273	66.32 257	66.70 328	77.60 217	36.30 444	76.94 203	79.61 183	62.36 75	62.43 329	83.66 221	45.69 213	78.37 307	45.35 357	63.26 402	85.42 173

XXY-MVS		60.68 351	61.67 323	57.70 426	70.43 387	38.45 419	64.19 418	66.47 391	48.05 388	63.22 307	80.86 292	49.28 167	60.47 448	45.25 358	67.28 367	74.19 420

dtuonly		54.95 409	55.26 398	54.01 443	59.03 483	35.99 446	61.92 434	56.33 460	38.48 466	54.61 425	77.85 351	34.27 362	51.60 489	45.10 359	69.74 336	74.43 416

0.3-1-1-0.015		58.40 374	55.56 393	66.91 324	68.08 431	43.09 368	65.25 409	70.96 352	47.89 392	53.10 443	59.82 481	26.48 447	78.79 302	45.07 360	63.43 400	78.84 358

HY-MVS	56.14 13	64.55 299	63.89 288	66.55 334	74.73 298	41.02 391	69.96 358	74.43 308	49.29 367	61.66 339	80.92 290	47.43 194	76.68 354	44.91 361	71.69 300	81.94 287

0.4-1-1-0.2		58.31 377	55.53 394	66.64 332	67.46 437	42.78 375	64.38 416	70.97 351	47.65 395	53.38 441	59.02 482	28.39 428	78.72 304	44.86 362	63.63 396	78.42 361

FE-MVSNET2		62.01 338	60.88 338	65.42 358	68.74 420	38.43 420	72.92 303	77.39 242	54.74 276	55.40 413	76.71 370	35.46 348	76.72 352	44.25 363	62.31 416	81.10 309

PEN-MVS		66.60 269	66.45 249	67.04 323	77.11 239	36.56 439	77.03 199	80.42 171	62.95 60	62.51 326	84.03 211	46.69 206	79.07 289	44.22 364	63.08 404	85.51 164

test_post1							68.67 374				3.64 533	32.39 395	69.49 401	44.17 365

SCA		60.49 355	58.38 366	66.80 325	74.14 318	48.06 307	63.35 425	63.23 423	49.13 369	59.33 368	72.10 421	37.45 325	74.27 371	44.17 365	62.57 413	78.05 366

PMMVS		53.96 412	53.26 418	56.04 431	62.60 466	50.92 231	61.17 440	56.09 463	32.81 476	53.51 439	66.84 466	34.04 365	59.93 452	44.14 367	68.18 358	57.27 485

MVP-Stereo		65.41 286	63.80 291	70.22 268	77.62 215	55.53 136	76.30 219	78.53 213	50.59 351	56.47 403	78.65 332	39.84 293	82.68 198	44.10 368	72.12 296	72.44 435
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
FE-MVS		65.91 279	63.33 302	73.63 164	77.36 223	51.95 218	72.62 308	75.81 280	53.70 297	65.31 272	78.96 327	28.81 424	86.39 93	43.93 369	73.48 268	82.55 273

CNLPA		65.43 285	64.02 287	69.68 280	78.73 165	58.07 89	77.82 170	70.71 355	51.49 334	61.57 341	83.58 226	38.23 319	70.82 392	43.90 370	70.10 326	80.16 334

pmmvs4		61.48 347	59.39 354	67.76 310	71.57 365	53.86 160	71.42 330	65.34 401	44.20 430	59.46 364	77.92 345	35.90 344	74.71 368	43.87 371	64.87 384	74.71 414

mvs5depth		55.64 401	53.81 413	61.11 398	59.39 481	40.98 395	65.89 396	68.28 377	50.21 354	58.11 384	75.42 395	17.03 476	67.63 414	43.79 372	46.21 478	74.73 413

Test_1112_low_res		62.32 331	61.77 322	64.00 373	79.08 156	39.53 410	68.17 379	70.17 358	43.25 439	59.03 370	79.90 308	44.08 238	71.24 390	43.79 372	68.42 356	81.25 303

sc_t1		59.76 362	57.84 372	65.54 354	74.87 292	42.95 373	69.61 363	64.16 414	48.90 372	58.68 373	77.12 362	28.19 432	72.35 381	43.75 374	55.28 453	81.31 302

TransMVSNet (Re)		64.72 294	64.33 284	65.87 351	75.22 283	38.56 417	74.66 262	75.08 302	58.90 163	61.79 335	82.63 241	51.18 136	78.07 313	43.63 375	55.87 451	80.99 313

pmmvs-eth3d		58.81 371	56.31 387	66.30 339	67.61 435	52.42 207	72.30 317	64.76 406	43.55 436	54.94 420	74.19 405	28.95 421	72.60 378	43.31 376	57.21 445	73.88 423

SixPastTwentyTwo		61.65 344	58.80 362	70.20 270	75.80 268	47.22 318	75.59 238	69.68 363	54.61 277	54.11 430	79.26 324	27.07 443	82.96 180	43.27 377	49.79 474	80.41 325

BH-w/o		66.85 263	65.83 265	69.90 277	79.29 145	52.46 205	74.66 262	76.65 263	54.51 281	64.85 288	78.12 339	45.59 216	82.95 182	43.26 378	75.54 236	74.27 419

TR-MVS		66.59 271	65.07 279	71.17 246	79.18 152	49.63 274	73.48 288	75.20 297	52.95 306	67.90 213	80.33 301	39.81 294	83.68 160	43.20 379	73.56 266	80.20 333

EU-MVSNet		55.61 402	54.41 406	59.19 412	65.41 452	33.42 466	72.44 315	71.91 344	28.81 481	51.27 449	73.87 409	24.76 459	69.08 403	43.04 380	58.20 441	75.06 405

PatchmatchNet		59.84 361	58.24 367	64.65 367	73.05 336	46.70 322	69.42 368	62.18 435	47.55 397	58.88 371	71.96 423	34.49 359	69.16 402	42.99 381	63.60 397	78.07 365
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
WR-MVS_H		67.02 260	66.92 241	67.33 321	77.95 197	37.75 426	77.57 176	82.11 128	62.03 88	62.65 321	82.48 252	50.57 146	79.46 275	42.91 382	64.01 391	84.79 199

ACMH	55.70 15	65.20 290	63.57 295	70.07 272	78.07 192	52.01 216	79.48 127	79.69 180	55.75 241	56.59 400	80.98 288	27.12 442	80.94 241	42.90 383	71.58 302	77.25 381
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		55.30 403	54.41 406	57.96 423	60.92 478	41.73 384	71.09 339	71.06 350	41.18 452	48.65 463	73.31 413	16.93 477	59.25 455	42.54 384	64.01 391	72.90 427

WTY-MVS		59.75 363	60.39 346	57.85 424	72.32 353	37.83 425	61.05 442	64.18 412	45.95 418	61.91 333	79.11 326	47.01 203	60.88 447	42.50 385	69.49 341	74.83 410

TAMVS		66.78 266	65.27 277	71.33 242	79.16 154	53.67 165	73.84 284	69.59 365	52.32 320	65.28 273	81.72 274	44.49 236	77.40 333	42.32 386	78.66 179	82.92 263

LTVRE_ROB	55.42 16	63.15 318	61.23 332	68.92 295	76.57 257	47.80 310	59.92 446	76.39 267	54.35 283	58.67 374	82.46 253	29.44 418	81.49 224	42.12 387	71.14 306	77.46 375
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
WBMVS		60.54 354	60.61 344	60.34 402	78.00 195	35.95 448	64.55 414	64.89 404	49.63 361	63.39 306	78.70 329	33.85 369	67.65 413	42.10 388	70.35 320	77.43 376

sss		56.17 396	56.57 383	54.96 437	66.93 441	36.32 443	57.94 455	61.69 437	41.67 449	58.64 375	75.32 397	38.72 312	56.25 472	42.04 389	66.19 375	72.31 439

UnsupCasMVSNet_eth		53.16 422	52.47 419	55.23 436	59.45 480	33.39 467	59.43 449	69.13 371	45.98 415	50.35 458	72.32 418	29.30 419	58.26 462	42.02 390	44.30 482	74.05 421

tpm2		62.07 335	60.10 350	67.99 308	72.79 340	43.86 355	71.05 340	66.85 389	43.14 441	62.77 317	75.39 396	38.32 317	80.80 247	41.69 391	68.88 350	79.32 349

PLC	56.13 14	65.09 291	63.21 305	70.72 260	81.04 112	54.87 148	78.57 142	77.47 238	48.51 379	55.71 408	81.89 269	33.71 370	79.71 268	41.66 392	70.37 318	77.58 374
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EPMVS		53.96 412	53.69 415	54.79 439	66.12 449	31.96 475	62.34 432	49.05 480	44.42 429	55.54 409	71.33 431	30.22 408	56.70 468	41.65 393	62.54 414	75.71 398

DTE-MVSNet		65.58 283	65.34 275	66.31 338	76.06 266	34.79 453	76.43 217	79.38 188	62.55 71	61.66 339	83.83 216	45.60 215	79.15 285	41.64 394	60.88 426	85.00 190

tt0320-xc		58.33 376	56.41 386	64.08 372	75.79 269	41.34 388	68.30 378	62.72 428	47.90 390	56.29 404	74.16 407	28.53 425	71.04 391	41.50 395	52.50 465	79.88 340

PAPM		67.92 239	66.69 245	71.63 226	78.09 191	49.02 285	77.09 197	81.24 152	51.04 345	60.91 347	83.98 213	47.71 187	84.99 130	40.81 396	79.32 155	80.90 314

tpm		57.34 385	58.16 368	54.86 438	71.80 362	34.77 454	67.47 387	56.04 464	48.20 385	60.10 353	76.92 366	37.17 331	53.41 482	40.76 397	65.01 382	76.40 391

dtuonlycased		55.96 398	54.88 401	59.22 410	68.38 428	40.38 399	69.17 371	63.12 426	40.00 462	53.62 436	68.84 454	36.27 341	66.23 426	40.57 398	53.92 460	71.06 455

KD-MVS_self_test		55.22 405	53.89 412	59.21 411	57.80 486	27.47 491	57.75 458	74.32 310	47.38 399	50.90 452	70.00 441	28.45 427	70.30 398	40.44 399	57.92 442	79.87 341

F-COLMAP		63.05 320	60.87 340	69.58 284	76.99 248	53.63 168	78.12 158	76.16 271	47.97 389	52.41 446	81.61 276	27.87 434	78.11 312	40.07 400	66.66 371	77.00 384

Patchmtry		57.16 386	56.47 384	59.23 409	69.17 413	34.58 457	62.98 427	63.15 424	44.53 426	56.83 398	74.84 399	35.83 345	68.71 405	40.03 401	60.91 425	74.39 418

pmmvs5		56.47 392	55.68 392	58.86 414	61.41 472	36.71 438	66.37 393	62.75 427	40.38 458	53.70 433	76.62 373	34.56 357	67.05 418	40.02 402	65.27 380	72.83 428

testing3-2		62.06 336	62.36 315	61.17 397	79.29 145	30.31 481	64.09 421	63.49 420	63.50 45	62.84 315	82.22 259	32.35 397	69.02 404	40.01 403	73.43 270	84.17 219

tt0320		58.59 372	56.81 380	63.92 374	75.46 278	41.32 389	68.63 375	64.06 415	47.05 405	56.19 405	74.19 405	30.34 406	71.36 388	39.92 404	55.45 452	79.09 352

EPNet_dtu		61.90 341	61.97 320	61.68 390	72.89 339	39.78 405	75.85 234	65.62 399	55.09 260	54.56 426	79.36 322	37.59 324	67.02 419	39.80 405	76.95 212	78.25 363
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CL-MVSNet_self_test		61.53 345	60.94 337	63.30 379	68.95 416	36.93 436	67.60 384	72.80 336	55.67 243	59.95 357	76.63 372	45.01 230	72.22 384	39.74 406	62.09 419	80.74 318

SSC-MVS3.2		60.57 353	61.39 327	58.12 422	74.29 313	32.63 471	59.52 447	65.53 400	59.90 140	62.45 327	79.75 313	41.96 261	63.90 437	39.47 407	69.65 340	77.84 371

test_vis1_rt		41.35 453	39.45 454	47.03 466	46.65 501	37.86 424	47.76 486	38.65 500	23.10 493	44.21 479	51.22 494	11.20 494	44.08 497	39.27 408	53.02 463	59.14 480

Vis-MVSNet (Re-imp)		63.69 310	63.88 289	63.14 381	74.75 297	31.04 479	71.16 336	63.64 419	56.32 228	59.80 360	84.99 181	44.51 234	75.46 365	39.12 409	80.62 127	82.92 263

PVSNet	50.76 19	58.40 374	57.39 373	61.42 393	75.53 276	44.04 354	61.43 436	63.45 421	47.04 406	56.91 397	73.61 411	27.00 444	64.76 433	39.12 409	72.40 288	75.47 401

UBG		59.62 366	59.53 353	59.89 403	78.12 190	35.92 449	64.11 420	60.81 442	49.45 364	61.34 342	75.55 392	33.05 377	67.39 417	38.68 411	74.62 247	76.35 392

MDTV_nov1_ep13_2view						25.89 497	61.22 439		40.10 460	51.10 450		32.97 380		38.49 412		78.61 360

our_test_3		56.49 391	54.42 405	62.68 385	69.51 406	45.48 337	66.08 395	61.49 438	44.11 433	50.73 455	69.60 450	33.05 377	68.15 407	38.38 413	56.86 446	74.40 417

tpm cat1		59.25 369	56.95 377	66.15 343	72.19 355	46.96 320	68.09 380	65.76 397	40.03 461	57.81 386	70.56 435	38.32 317	74.51 369	38.26 414	61.50 423	77.00 384

USDC		56.35 394	54.24 409	62.69 384	64.74 455	40.31 400	65.05 410	73.83 321	43.93 434	47.58 465	77.71 356	15.36 483	75.05 367	38.19 415	61.81 421	72.70 429

MSDG		61.81 343	59.23 355	69.55 285	72.64 342	52.63 200	70.45 351	75.81 280	51.38 337	53.70 433	76.11 382	29.52 416	81.08 237	37.70 416	65.79 378	74.93 409

MDTV_nov1_ep13			57.00 376		72.73 341	38.26 421	65.02 411	64.73 407	44.74 424	55.46 410	72.48 417	32.61 392	70.47 394	37.47 417	67.75 362

SD_0403		63.07 319	63.49 299	61.82 389	75.16 286	31.14 478	71.89 326	73.47 324	53.34 302	58.22 382	81.81 272	45.17 227	73.86 373	37.43 418	74.87 245	80.45 323

gg-mvs-nofinetune		57.86 382	56.43 385	62.18 387	72.62 343	35.35 451	66.57 391	56.33 460	50.65 349	57.64 388	57.10 486	30.65 403	76.36 359	37.38 419	78.88 170	74.82 411

dmvs_re		56.77 389	56.83 379	56.61 429	69.23 411	41.02 391	58.37 452	64.18 412	50.59 351	57.45 392	71.42 427	35.54 347	58.94 458	37.23 420	67.45 365	69.87 463

RPSCF		55.80 400	54.22 410	60.53 401	65.13 454	42.91 374	64.30 417	57.62 453	36.84 469	58.05 385	82.28 257	28.01 433	56.24 473	37.14 421	58.61 440	82.44 279

testing222		62.29 333	61.31 329	65.25 363	77.87 199	38.53 418	68.34 377	66.31 394	56.37 227	63.15 311	77.58 358	28.47 426	76.18 363	37.04 422	76.65 218	81.05 312

PatchT		53.17 421	53.44 417	52.33 456	68.29 429	25.34 499	58.21 453	54.41 467	44.46 428	54.56 426	69.05 453	33.32 375	60.94 446	36.93 423	61.76 422	70.73 457

YYNet1		50.73 431	48.96 433	56.03 432	61.10 474	41.78 383	51.94 475	56.44 458	40.94 455	44.84 475	67.80 458	30.08 411	55.08 478	36.77 424	50.71 470	71.22 451

TAPA-MVS	59.36 10	66.60 269	65.20 278	70.81 256	76.63 255	48.75 291	76.52 216	80.04 176	50.64 350	65.24 278	84.93 182	39.15 304	78.54 306	36.77 424	76.88 213	85.14 184
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MDA-MVSNet_test_wron		50.71 432	48.95 434	56.00 433	61.17 473	41.84 382	51.90 476	56.45 457	40.96 454	44.79 476	67.84 457	30.04 412	55.07 479	36.71 426	50.69 471	71.11 454

ppachtmachnet_test		58.06 381	55.38 396	66.10 345	69.51 406	48.99 286	68.01 381	66.13 396	44.50 427	54.05 431	70.74 434	32.09 398	72.34 382	36.68 427	56.71 449	76.99 386

tpmvs		58.47 373	56.95 377	63.03 383	70.20 394	41.21 390	67.90 382	67.23 385	49.62 362	54.73 423	70.84 433	34.14 363	76.24 361	36.64 428	61.29 424	71.64 445

CHOSEN 280x420		47.83 439	46.36 443	52.24 458	67.37 438	49.78 265	38.91 499	43.11 497	35.00 472	43.27 481	63.30 476	28.95 421	49.19 491	36.53 429	60.80 427	57.76 484

PatchMatch-RL		56.25 395	54.55 404	61.32 396	77.06 240	56.07 121	65.57 400	54.10 469	44.13 432	53.49 440	71.27 432	25.20 457	66.78 420	36.52 430	63.66 395	61.12 477

RPMNet		61.53 345	58.42 365	70.86 255	69.96 399	52.07 213	65.31 407	81.36 143	43.20 440	59.36 365	70.15 440	35.37 349	85.47 122	36.42 431	64.65 386	75.06 405

ITE_SJBPF				62.09 388	66.16 448	44.55 349		64.32 410	47.36 400	55.31 414	80.34 300	19.27 472	62.68 442	36.29 432	62.39 415	79.04 354

myMVS_eth3d28		60.66 352	61.04 335	59.51 405	77.32 224	31.58 476	63.11 426	63.87 416	59.00 160	60.90 348	78.26 338	32.69 388	66.15 427	36.10 433	78.13 189	80.81 316

JIA-IIPM		51.56 427	47.68 441	63.21 380	64.61 456	50.73 240	47.71 487	58.77 448	42.90 443	48.46 464	51.72 490	24.97 458	70.24 399	36.06 434	53.89 461	68.64 469

KD-MVS_2432*1600		53.45 416	51.50 425	59.30 407	62.82 463	37.14 432	55.33 465	71.79 345	47.34 401	55.09 418	70.52 436	21.91 467	70.45 395	35.72 435	42.97 484	70.31 459

miper_refine_blended		53.45 416	51.50 425	59.30 407	62.82 463	37.14 432	55.33 465	71.79 345	47.34 401	55.09 418	70.52 436	21.91 467	70.45 395	35.72 435	42.97 484	70.31 459

OpenMVS_ROB	52.78 18	60.03 359	58.14 369	65.69 353	70.47 386	44.82 341	75.33 242	70.86 354	45.04 422	56.06 406	76.00 384	26.89 446	79.65 269	35.36 437	67.29 366	72.60 430

GG-mvs-BLEND				62.34 386	71.36 373	37.04 435	69.20 370	57.33 456		54.73 423	65.48 471	30.37 405	77.82 321	34.82 438	74.93 244	72.17 440

UnsupCasMVSNet_bld		50.07 434	48.87 435	53.66 446	60.97 477	33.67 465	57.62 459	64.56 409	39.47 464	47.38 466	64.02 475	27.47 438	59.32 454	34.69 439	43.68 483	67.98 471

MDA-MVSNet-bldmvs		53.87 414	50.81 427	63.05 382	66.25 447	48.58 296	56.93 462	63.82 417	48.09 387	41.22 483	70.48 438	30.34 406	68.00 411	34.24 440	45.92 480	72.57 431

dp		51.89 426	51.60 424	52.77 453	68.44 427	32.45 473	62.36 431	54.57 466	44.16 431	49.31 462	67.91 456	28.87 423	56.61 470	33.89 441	54.89 455	69.24 468

AllTest		57.08 387	54.65 402	64.39 369	71.44 369	49.03 283	69.92 359	67.30 382	45.97 416	47.16 467	79.77 311	17.47 474	67.56 415	33.65 442	59.16 437	76.57 389

TestCases				64.39 369	71.44 369	49.03 283		67.30 382	45.97 416	47.16 467	79.77 311	17.47 474	67.56 415	33.65 442	59.16 437	76.57 389

test_vis3_rt		32.09 464	30.20 469	37.76 480	35.36 512	27.48 490	40.60 498	28.29 509	16.69 502	32.52 496	40.53 504	1.96 514	37.40 505	33.64 444	42.21 486	48.39 491

UWE-MVS		60.18 358	59.78 351	61.39 395	77.67 209	33.92 464	69.04 373	63.82 417	48.56 377	64.27 296	77.64 357	27.20 441	70.40 397	33.56 445	76.24 222	79.83 342

FMVSNet5		55.86 399	54.93 399	58.66 416	71.05 378	36.35 441	64.18 419	62.48 430	46.76 409	50.66 456	74.73 401	25.80 453	64.04 435	33.11 446	65.57 379	75.59 399

mvsany_test1		39.38 455	38.16 458	43.02 473	49.05 495	34.28 460	44.16 495	25.94 510	22.74 495	46.57 471	62.21 479	23.85 462	41.16 503	33.01 447	35.91 492	53.63 488

DP-MVS		65.68 281	63.66 294	71.75 219	84.93 60	56.87 111	80.74 104	73.16 332	53.06 305	59.09 369	82.35 254	36.79 338	85.94 109	32.82 448	69.96 329	72.45 434

PVSNet_0	43.31 20	47.46 441	45.64 444	52.92 452	67.60 436	44.65 344	54.06 470	54.64 465	41.59 450	46.15 472	58.75 483	30.99 402	58.66 459	32.18 449	24.81 500	55.46 487

ETVMVS		59.51 367	58.81 360	61.58 392	77.46 220	34.87 452	64.94 412	59.35 445	54.06 287	61.08 346	76.67 371	29.54 415	71.87 386	32.16 450	74.07 254	78.01 370

WB-MVSnew		59.66 364	59.69 352	59.56 404	75.19 285	35.78 450	69.34 369	64.28 411	46.88 407	61.76 336	75.79 388	40.61 287	65.20 431	32.16 450	71.21 305	77.70 372

TinyColmap		54.14 411	51.72 423	61.40 394	66.84 442	41.97 381	66.52 392	68.51 375	44.81 423	42.69 482	75.77 389	11.66 490	72.94 376	31.96 452	56.77 448	69.27 467

MIMVSNet		57.35 384	57.07 375	58.22 419	74.21 315	37.18 431	62.46 430	60.88 441	48.88 373	55.29 415	75.99 386	31.68 399	62.04 444	31.87 453	72.35 289	75.43 402

thres100view900		63.28 315	62.41 314	65.89 349	77.31 225	38.66 416	72.65 306	69.11 372	57.07 205	62.45 327	81.03 287	37.01 335	79.17 282	31.84 454	73.25 274	79.83 342

tfpn200view9		63.18 317	62.18 318	66.21 341	76.85 249	39.62 408	71.96 324	69.44 368	56.63 216	62.61 322	79.83 309	37.18 329	79.17 282	31.84 454	73.25 274	79.83 342

thres400		63.31 313	62.18 318	66.72 326	76.85 249	39.62 408	71.96 324	69.44 368	56.63 216	62.61 322	79.83 309	37.18 329	79.17 282	31.84 454	73.25 274	81.36 299

pmmvs3		44.92 444	41.95 451	53.86 444	52.58 492	43.55 359	62.11 433	46.90 490	26.05 488	40.63 484	60.19 480	11.08 495	57.91 463	31.83 457	46.15 479	60.11 478

LF4IMVS		42.95 447	42.26 449	45.04 468	48.30 498	32.50 472	54.80 467	48.49 482	28.03 484	40.51 485	70.16 439	9.24 497	43.89 498	31.63 458	49.18 476	58.72 481

COLMAP_ROB	52.97 17	61.27 350	58.81 360	68.64 298	74.63 301	52.51 203	78.42 145	73.30 328	49.92 359	50.96 451	81.51 279	23.06 463	79.40 276	31.63 458	65.85 376	74.01 422
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
new-patchmatchnet		47.56 440	47.73 440	47.06 465	58.81 484	9.37 517	48.78 484	59.21 446	43.28 438	44.22 478	68.66 455	25.67 454	57.20 467	31.57 460	49.35 475	74.62 415

thres600view7		63.30 314	62.27 316	66.41 336	77.18 228	38.87 414	72.35 316	69.11 372	56.98 208	62.37 330	80.96 289	37.01 335	79.00 297	31.43 461	73.05 278	81.36 299

thres200		62.20 334	61.16 334	65.34 361	75.38 281	39.99 403	69.60 364	69.29 370	55.64 245	61.87 334	76.99 365	37.07 334	78.96 298	31.28 462	73.28 273	77.06 382

LCM-MVSNet		40.30 454	35.88 460	53.57 447	42.24 503	29.15 484	45.21 493	60.53 443	22.23 496	28.02 498	50.98 495	3.72 508	61.78 445	31.22 463	38.76 490	69.78 464

test_f		31.86 465	31.05 466	34.28 482	32.33 514	21.86 504	32.34 502	30.46 507	16.02 503	39.78 489	55.45 487	4.80 504	32.36 509	30.61 464	37.66 491	48.64 490

test0.0.03 1		53.32 420	53.59 416	52.50 455	62.81 465	29.45 483	59.51 448	54.11 468	50.08 356	54.40 428	74.31 404	32.62 390	55.92 474	30.50 465	63.95 393	72.15 441

FE-MVSNET		55.16 407	53.75 414	59.41 406	65.29 453	33.20 468	67.21 389	66.21 395	48.39 383	49.56 461	73.53 412	29.03 420	72.51 379	30.38 466	54.10 459	72.52 432

Anonymous20231206		55.10 408	55.30 397	54.48 440	69.81 404	33.94 463	62.91 428	62.13 436	41.08 453	55.18 416	75.65 390	32.75 385	56.59 471	30.32 467	67.86 360	72.91 426

tfpnnormal		62.47 326	61.63 324	64.99 365	74.81 295	39.01 413	71.22 334	73.72 322	55.22 257	60.21 351	80.09 307	41.26 280	76.98 345	30.02 468	68.09 359	78.97 356

test20.03		53.87 414	54.02 411	53.41 449	61.47 471	28.11 488	61.30 438	59.21 446	51.34 339	52.09 447	77.43 359	33.29 376	58.55 460	29.76 469	60.27 434	73.58 424

LS3D		64.71 295	62.50 313	71.34 241	79.72 137	55.71 129	79.82 118	74.72 305	48.50 380	56.62 399	84.62 194	33.59 373	82.34 208	29.65 470	75.23 242	75.97 394

mvsany_test3		32.62 463	30.57 468	38.77 479	36.16 511	24.20 501	38.10 500	20.63 514	19.14 499	40.36 487	57.43 485	5.06 503	36.63 506	29.59 471	28.66 497	55.49 486

testgi		51.90 425	52.37 420	50.51 462	60.39 479	23.55 502	58.42 451	58.15 449	49.03 370	51.83 448	79.21 325	22.39 464	55.59 475	29.24 472	62.64 412	72.40 438

MIMVSNet1		55.17 406	54.31 408	57.77 425	70.03 398	32.01 474	65.68 399	64.81 405	49.19 368	46.75 470	76.00 384	25.53 456	64.04 435	28.65 473	62.13 418	77.26 380

TDRefinement		53.44 418	50.72 429	61.60 391	64.31 458	46.96 320	70.89 341	65.27 403	41.78 447	44.61 477	77.98 342	11.52 492	66.36 424	28.57 474	51.59 468	71.49 448

usedtu_dtu_shiyan2		53.34 419	50.78 428	61.00 400	61.86 470	39.63 407	68.47 376	64.58 408	42.94 442	45.22 474	67.61 460	19.25 473	66.71 421	28.08 475	59.05 439	76.66 388

WAC-MVS						27.31 492								27.77 476

myMVS_eth3d		54.86 410	54.61 403	55.61 434	74.69 299	27.31 492	65.52 401	57.49 454	50.97 346	56.52 401	72.18 419	21.87 469	68.09 408	27.70 477	64.59 388	71.44 449

ttmdpeth		45.56 442	42.95 447	53.39 450	52.33 493	29.15 484	57.77 456	48.20 485	31.81 478	49.86 460	77.21 361	8.69 499	59.16 456	27.31 478	33.40 496	71.84 444

ADS-MVSNet2		51.33 429	48.76 436	59.07 413	66.02 450	44.60 347	50.90 478	59.76 444	36.90 467	50.74 453	66.18 469	26.38 448	63.11 440	27.17 479	54.76 456	69.50 465

ADS-MVSNet		48.48 438	47.77 439	50.63 461	66.02 450	29.92 482	50.90 478	50.87 478	36.90 467	50.74 453	66.18 469	26.38 448	52.47 485	27.17 479	54.76 456	69.50 465

Patchmatch-test		49.08 436	48.28 438	51.50 460	64.40 457	30.85 480	45.68 491	48.46 483	35.60 471	46.10 473	72.10 421	34.47 360	46.37 495	27.08 481	60.65 430	77.27 379

MVS-HIRNet		45.52 443	44.48 445	48.65 464	68.49 426	34.05 462	59.41 450	44.50 494	27.03 486	37.96 493	50.47 496	26.16 451	64.10 434	26.74 482	59.52 435	47.82 494

test_0402		63.25 316	61.01 336	69.96 273	80.00 132	54.37 153	76.86 207	72.02 343	54.58 279	58.71 372	80.79 295	35.00 353	84.36 146	26.41 483	64.71 385	71.15 453

N_pmnet		39.35 456	40.28 453	36.54 481	63.76 459	1.62 536	49.37 483	0.76 534	34.62 473	43.61 480	66.38 468	26.25 450	42.57 499	26.02 484	51.77 467	65.44 473

PatchmatchNet1														25.92 485	51.90 466	65.44 473
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
testing3		56.54 390	55.92 390	58.41 417	77.52 218	27.93 489	69.72 360	56.36 459	54.75 275	58.63 376	77.80 352	20.88 471	71.75 387	25.31 486	62.25 417	75.53 400

Syy-MVS		56.00 397	56.23 388	55.32 435	74.69 299	26.44 495	65.52 401	57.49 454	50.97 346	56.52 401	72.18 419	39.89 292	68.09 408	24.20 487	64.59 388	71.44 449

MVStest1		42.65 448	39.29 455	52.71 454	47.26 500	34.58 457	54.41 469	50.84 479	23.35 491	39.31 491	74.08 408	12.57 487	55.09 477	23.32 488	28.47 498	68.47 470

DSMNet-mixed		39.30 457	38.72 456	41.03 476	51.22 494	19.66 506	45.53 492	31.35 506	15.83 504	39.80 488	67.42 463	22.19 465	45.13 496	22.43 489	52.69 464	58.31 482

dmvs_testset		50.16 433	51.90 422	44.94 470	66.49 445	11.78 514	61.01 443	51.50 473	51.17 344	50.30 459	67.44 461	39.28 301	60.29 450	22.38 490	57.49 444	62.76 476

ANet_high		41.38 452	37.47 459	53.11 451	39.73 508	24.45 500	56.94 461	69.69 362	47.65 395	26.04 500	52.32 489	12.44 488	62.38 443	21.80 491	10.61 511	72.49 433

ArgMatch-Sym		21.00 473	19.89 476	24.35 492	23.32 515	15.10 511	32.50 501	4.90 520	11.83 507	24.09 501	51.35 493	0.56 519	19.55 513	21.24 492	9.18 514	38.40 503

ArgMatch-SfM		20.82 474	19.10 477	25.97 490	21.54 516	13.77 512	29.84 505	6.08 519	9.69 509	22.36 502	51.71 491	0.53 520	21.69 512	20.98 493	9.18 514	42.43 497

new_pmnet		34.13 462	34.29 463	33.64 483	52.63 491	18.23 508	44.43 494	33.90 505	22.81 494	30.89 497	53.18 488	10.48 496	35.72 507	20.77 494	39.51 488	46.98 495

UWE-MVS-28		52.25 424	52.35 421	51.93 459	66.99 439	22.79 503	63.48 424	48.31 484	46.78 408	52.73 445	76.11 382	27.78 436	57.82 464	20.58 495	68.41 357	75.17 403

APD_test1		37.39 458	34.94 461	44.72 471	48.88 496	33.19 469	52.95 473	44.00 496	19.49 498	27.28 499	58.59 484	3.18 510	52.84 484	18.92 496	41.17 487	48.14 493

EGC-MVSNET		42.47 449	38.48 457	54.46 441	74.33 311	48.73 292	70.33 354	51.10 475	0.03 554	0.18 553	67.78 459	13.28 486	66.49 423	18.91 497	50.36 472	48.15 492

PMMVS2		27.40 469	25.91 472	31.87 486	39.46 509	6.57 521	31.17 503	28.52 508	23.96 490	20.45 506	48.94 499	4.20 507	37.94 504	16.51 498	19.97 503	51.09 489

test_method		19.68 475	18.10 478	24.41 491	13.68 520	3.11 530	12.06 513	42.37 498	2.00 519	11.97 513	36.38 505	5.77 502	29.35 511	15.06 499	23.65 501	40.76 500

Gipuma		34.77 460	31.91 465	43.33 472	62.05 469	37.87 423	20.39 506	67.03 387	23.23 492	18.41 507	25.84 513	4.24 505	62.73 441	14.71 500	51.32 469	29.38 505
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FPMVS		42.18 450	41.11 452	45.39 467	58.03 485	41.01 393	49.50 482	53.81 470	30.07 480	33.71 495	64.03 473	11.69 489	52.08 488	14.01 501	55.11 454	43.09 496

testf1		31.46 466	28.89 470	39.16 477	41.99 505	28.78 486	46.45 489	37.56 501	14.28 505	21.10 503	48.96 497	1.48 516	47.11 493	13.63 502	34.56 493	41.60 498

APD_test2		31.46 466	28.89 470	39.16 477	41.99 505	28.78 486	46.45 489	37.56 501	14.28 505	21.10 503	48.96 497	1.48 516	47.11 493	13.63 502	34.56 493	41.60 498

tmp_tt		9.43 482	11.14 483	4.30 507	2.38 537	4.40 523	13.62 511	16.08 516	0.39 527	15.89 508	13.06 524	15.80 482	5.54 525	12.63 504	10.46 512	2.95 525

dongtai		34.52 461	34.94 461	33.26 484	61.06 475	16.00 510	52.79 474	23.78 512	40.71 456	39.33 490	48.65 500	16.91 478	48.34 492	12.18 505	19.05 504	35.44 504

WB-MVS		43.26 446	43.41 446	42.83 474	63.32 462	10.32 516	58.17 454	45.20 491	45.42 420	40.44 486	67.26 464	34.01 367	58.98 457	11.96 506	24.88 499	59.20 479

DenseAffine		14.16 477	13.16 480	17.15 493	17.01 518	8.89 519	19.68 507	2.17 523	7.89 510	15.00 509	40.64 503	0.19 523	15.28 515	11.16 507	4.69 519	27.27 507

SSC-MVS		41.96 451	41.99 450	41.90 475	62.46 467	9.28 518	57.41 460	44.32 495	43.38 437	38.30 492	66.45 467	32.67 389	58.42 461	10.98 508	21.91 502	57.99 483

RoMa-SfM		11.96 479	11.39 482	13.68 495	10.24 522	6.80 520	15.83 509	1.33 527	6.34 512	13.06 512	41.41 501	0.16 524	12.72 516	10.58 509	3.56 522	21.52 508

MVE	17.77 23	21.41 472	17.77 479	32.34 485	34.34 513	25.44 498	16.11 508	24.11 511	11.19 508	13.22 511	31.92 508	1.58 515	30.95 510	10.47 510	17.03 506	40.62 501
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		23.77 470	22.73 474	26.90 487	42.02 504	20.67 505	42.66 496	35.70 503	17.43 500	10.28 517	25.05 514	6.42 501	42.39 501	10.28 511	14.71 507	17.63 511

PMVS	28.69 22	36.22 459	33.29 464	45.02 469	36.82 510	35.98 447	54.68 468	48.74 481	26.31 487	21.02 505	51.61 492	2.88 511	60.10 451	9.99 512	47.58 477	38.99 502
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DKM		10.33 480	10.10 484	11.02 497	10.54 521	5.43 522	14.18 510	1.03 530	4.97 513	11.74 514	36.09 506	0.11 528	9.09 520	9.38 513	2.85 523	18.53 510

EMVS		22.97 471	21.84 475	26.36 488	40.20 507	19.53 507	41.95 497	34.64 504	17.09 501	9.73 518	22.83 516	7.29 500	42.22 502	9.18 514	13.66 509	17.32 512

DKM-HiRes		7.91 486	7.93 490	7.83 501	7.35 525	3.58 528	10.03 517	0.66 537	3.58 517	9.05 520	30.62 510	0.08 535	5.66 524	8.09 515	1.91 530	14.26 514

DeepMVS_CX				12.03 496	17.97 517	10.91 515		10.60 517	7.46 511	11.07 515	28.36 512	3.28 509	11.29 517	8.01 516	9.74 513	13.89 516

PDCNetPlus		9.23 483	8.89 487	10.23 499	13.70 519	3.70 526	12.27 512	1.51 526	3.98 515	6.73 523	29.50 511	0.24 522	8.07 522	7.83 517	4.30 520	18.93 509

RoMa-HiRes		8.28 485	8.27 489	8.28 500	6.12 527	3.67 527	10.07 516	0.74 535	3.93 516	9.17 519	34.46 507	0.12 527	7.12 523	7.80 518	2.05 529	14.04 515

kuosan		29.62 468	30.82 467	26.02 489	52.99 489	16.22 509	51.09 477	22.71 513	33.91 475	33.99 494	40.85 502	15.89 481	33.11 508	7.59 519	18.37 505	28.72 506

wuyk23d		13.32 478	12.52 481	15.71 494	47.54 499	26.27 496	31.06 504	1.98 524	4.93 514	5.18 525	1.94 540	0.45 521	18.54 514	6.81 520	12.83 510	2.33 527

VLMVS_CLIP		8.61 484	9.36 485	6.34 504	7.07 526	4.23 525	8.66 518	10.16 518	1.75 520	13.91 510	20.41 518	2.33 512	10.32 519	6.21 521	13.74 508	4.49 522

MVS_clip		4.22 493	4.98 495	1.95 510	5.46 529	1.99 531	3.96 520	0.34 541	0.36 528	7.04 522	17.25 519	0.66 518	0.80 535	4.04 522	5.70 518	3.07 524

PMatch-SfM		4.42 491	4.43 496	4.39 506	2.90 533	1.50 537	4.85 519	0.36 540	1.17 522	4.73 527	20.99 517	0.01 555	3.26 528	3.74 523	1.10 537	8.40 520

LoFTR		9.45 481	9.00 486	10.79 498	10.22 523	4.31 524	11.11 514	4.11 521	2.40 518	10.53 516	30.89 509	0.13 525	10.75 518	3.12 524	8.52 516	17.31 513

PMatch-Up-SfM		3.14 497	3.26 500	2.81 508	1.97 542	1.00 541	3.35 525	0.23 547	0.79 524	3.44 530	16.19 522	0.01 555	2.11 529	2.62 525	0.70 550	5.32 521

MASt3R-SfM		3.33 496	3.70 497	2.21 509	2.02 541	1.04 539	3.52 524	1.05 529	0.67 525	4.93 526	16.68 520	0.10 530	1.50 532	2.06 526	2.29 528	4.09 523

ELoFTR		4.04 494	3.55 499	5.50 505	2.33 538	1.25 538	3.58 522	1.18 528	0.90 523	4.23 529	16.28 521	0.03 543	5.46 527	1.95 527	1.42 534	9.81 519

MatchFormer		7.03 487	6.96 491	7.26 502	7.64 524	3.36 529	10.21 515	3.04 522	1.31 521	9.02 521	22.94 515	0.08 535	8.15 521	1.46 528	6.91 517	10.26 518

VLMVS		2.25 499	2.47 502	1.62 513	2.41 536	1.01 540	1.61 532	0.72 536	0.07 553	4.27 528	6.17 528	2.11 513	1.03 534	1.17 529	3.66 521	2.83 526

GLUNet-SfM		4.33 492	3.64 498	6.41 503	3.38 532	1.65 534	3.23 526	1.54 525	0.66 526	6.36 524	15.13 523	0.08 535	5.54 525	0.94 530	1.44 533	12.05 517

SP-DiffGlue		0.98 504	1.05 507	0.75 519	0.81 558	0.40 548	1.24 533	0.37 539	0.19 532	1.26 537	3.80 532	0.11 528	0.34 542	0.51 531	1.18 535	1.52 533

MVS_baseline		1.38 502	1.71 505	0.39 525	1.08 556	0.02 563	0.39 549	0.06 561	0.01 555	2.77 531	7.83 525	0.07 540	0.00 557	0.47 532	2.72 525	1.14 537

XFeat-MNN		1.07 503	1.17 506	0.77 516	0.52 559	0.31 556	1.15 534	0.41 538	0.15 535	1.62 533	4.35 531	0.07 540	0.77 536	0.38 533	1.88 531	1.22 536

XFeat-NN		0.87 508	0.97 510	0.59 521	0.48 560	0.24 559	0.94 535	0.29 546	0.12 538	1.41 536	3.45 535	0.06 542	0.56 537	0.29 534	1.65 532	0.95 538

SP-LightGlue		0.94 505	0.99 508	0.78 515	2.60 534	0.38 549	1.71 528	0.34 541	0.17 533	0.50 539	2.14 536	0.09 533	0.38 539	0.26 535	1.13 536	1.59 530

SP-SuperGlue		0.93 506	0.98 509	0.77 516	2.54 535	0.38 549	1.70 529	0.34 541	0.17 533	0.52 538	2.13 537	0.10 530	0.36 541	0.26 535	1.10 537	1.57 532

SP-NN		0.85 509	0.90 512	0.73 520	2.22 540	0.33 555	1.63 531	0.31 545	0.14 536	0.47 541	1.97 539	0.08 535	0.38 539	0.25 537	1.01 540	1.47 534

SP-MNN		0.89 507	0.93 511	0.77 516	2.32 539	0.34 553	1.68 530	0.33 544	0.13 537	0.49 540	2.07 538	0.08 535	0.39 538	0.25 537	1.07 539	1.58 531

ALIKED-LG		2.35 498	2.54 501	1.78 511	5.54 528	1.79 533	3.81 521	0.96 531	0.33 529	1.86 532	7.18 526	0.13 525	1.60 530	0.20 539	2.81 524	1.94 528

ALIKED-MNN		2.09 500	2.23 503	1.67 512	5.15 530	1.82 532	3.53 523	0.77 532	0.25 530	1.45 534	6.03 529	0.09 533	1.52 531	0.17 540	2.64 526	1.66 529

ALIKED-NN		1.96 501	2.12 504	1.48 514	4.72 531	1.65 534	3.19 527	0.77 532	0.23 531	1.43 535	5.87 530	0.10 530	1.37 533	0.16 541	2.61 527	1.42 535

SIFT-NN-UMatch		0.48 515	0.52 518	0.36 528	1.27 552	0.36 551	0.75 539	0.12 551	0.10 539	0.25 547	1.29 543	0.02 544	0.26 547	0.04 542	0.85 545	0.44 543

SIFT-NN-NCMNet		0.53 512	0.58 515	0.40 524	1.60 546	0.49 544	0.80 538	0.15 550	0.09 542	0.28 545	1.29 543	0.02 544	0.27 545	0.04 542	0.94 542	0.44 543

SIFT-NN-CMatch		0.49 514	0.53 517	0.38 526	1.35 550	0.41 547	0.70 541	0.12 551	0.09 542	0.30 543	1.28 545	0.02 544	0.26 547	0.04 542	0.83 546	0.47 541

SIFT-NN		0.60 510	0.65 513	0.45 522	1.90 543	0.55 542	0.90 536	0.16 548	0.10 539	0.34 542	1.43 541	0.02 544	0.28 543	0.04 542	0.95 541	0.50 539

SIFT-UMatch		0.45 517	0.50 520	0.32 531	1.46 548	0.34 553	0.66 542	0.10 556	0.09 542	0.22 549	1.19 547	0.02 544	0.25 549	0.04 542	0.73 549	0.36 548

SIFT-ConvMatch		0.48 515	0.52 518	0.35 529	1.51 547	0.42 546	0.64 543	0.11 554	0.09 542	0.26 546	1.24 546	0.02 544	0.25 549	0.04 542	0.76 548	0.38 546

SIFT-MNN		0.56 511	0.61 514	0.43 523	1.75 544	0.50 543	0.82 537	0.16 548	0.10 539	0.30 543	1.38 542	0.02 544	0.28 543	0.04 542	0.92 543	0.50 539

testmvs		4.52 490	6.03 493	0.01 538	0.01 561	0.00 565	53.86 471	0.00 563	0.01 555	0.04 557	0.27 555	0.00 561	0.00 557	0.04 542	0.00 556	0.03 554

SIFT-UM-Cal		0.41 520	0.46 522	0.28 533	1.35 550	0.29 557	0.57 545	0.08 558	0.09 542	0.20 551	1.10 550	0.02 544	0.23 552	0.03 550	0.68 551	0.30 551

SIFT-NCM-Cal		0.51 513	0.55 516	0.38 526	1.66 545	0.45 545	0.75 539	0.12 551	0.09 542	0.21 550	1.18 548	0.02 544	0.27 545	0.03 550	0.89 544	0.43 545

SIFT-CM-Cal		0.42 519	0.46 522	0.31 532	1.40 549	0.35 552	0.56 546	0.09 557	0.09 542	0.20 551	1.09 551	0.02 544	0.23 552	0.03 550	0.66 552	0.34 549

SIFT-PCN-Cal		0.36 521	0.39 524	0.26 534	1.16 554	0.21 560	0.46 548	0.07 560	0.08 550	0.17 554	0.92 552	0.01 555	0.20 555	0.03 550	0.59 554	0.37 547

SIFT-NN-PointCN		0.44 518	0.47 521	0.33 530	1.17 553	0.29 557	0.64 543	0.11 554	0.09 542	0.25 547	1.14 549	0.02 544	0.25 549	0.03 550	0.78 547	0.46 542

SIFT-PointCN		0.36 521	0.39 524	0.25 535	1.14 555	0.21 560	0.50 547	0.08 558	0.08 550	0.17 554	0.89 553	0.01 555	0.21 554	0.03 550	0.60 553	0.34 549

test123		4.73 489	6.30 492	0.02 537	0.01 561	0.01 564	56.36 463	0.00 563	0.01 555	0.04 557	0.21 556	0.01 555	0.00 557	0.03 550	0.00 556	0.04 553

SIFT-NCMNet		0.30 523	0.33 526	0.19 536	1.04 557	0.18 562	0.39 549	0.05 562	0.08 550	0.14 556	0.77 554	0.01 555	0.16 556	0.02 557	0.49 555	0.22 552

mmdepth		0.00 524	0.00 527	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	0.00 557	0.00 561	0.00 557	0.00 558	0.00 556	0.00 555

monomultidepth		0.00 524	0.00 527	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	0.00 557	0.00 561	0.00 557	0.00 558	0.00 556	0.00 555

test_blank		0.00 524	0.00 527	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	0.00 557	0.00 561	0.00 557	0.00 558	0.00 556	0.00 555

uanet_test		0.00 524	0.00 527	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	0.00 557	0.00 561	0.00 557	0.00 558	0.00 556	0.00 555

DCPMVS		0.00 524	0.00 527	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	0.00 557	0.00 561	0.00 557	0.00 558	0.00 556	0.00 555

cdsmvs_eth3d_5k		17.50 476	23.34 473	0.00 539	0.00 563	0.00 565	0.00 551	78.63 206	0.00 558	0.00 559	82.18 260	49.25 168	0.00 557	0.00 558	0.00 556	0.00 555

pcd_1.5k_mvsjas		3.92 495	5.23 494	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	0.00 557	47.05 200	0.00 557	0.00 558	0.00 556	0.00 555

sosnet-low-res		0.00 524	0.00 527	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	0.00 557	0.00 561	0.00 557	0.00 558	0.00 556	0.00 555

sosnet		0.00 524	0.00 527	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	0.00 557	0.00 561	0.00 557	0.00 558	0.00 556	0.00 555

uncertanet		0.00 524	0.00 527	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	0.00 557	0.00 561	0.00 557	0.00 558	0.00 556	0.00 555

Regformer		0.00 524	0.00 527	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	0.00 557	0.00 561	0.00 557	0.00 558	0.00 556	0.00 555

ab-mvs-re		6.49 488	8.65 488	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	77.89 349	0.00 561	0.00 557	0.00 558	0.00 556	0.00 555

uanet		0.00 524	0.00 527	0.00 539	0.00 563	0.00 565	0.00 551	0.00 563	0.00 558	0.00 559	0.00 557	0.00 561	0.00 557	0.00 558	0.00 556	0.00 555

PatchmatchNet2					0.00 563	13.27 513	48.02 485	44.92 493	34.52 474
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													42.51 500
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip				78.05 44	84.66 63	58.22 88	86.84 11	85.98 23	63.31 49	79.39 25	88.94 65	62.01 16	89.61 22		86.45 64	86.34 123

FOURS1					86.12 38	60.82 37	88.18 1	83.61 85	60.87 109	81.50 21

test_one_0601					87.58 9	59.30 62		86.84 7	65.01 21	83.80 11	91.86 6	64.03 12

eth-test2					0.00 563

eth-test					0.00 563

test_241102_ONE					87.77 4	58.90 79		86.78 10	64.20 34	85.97 1	91.34 18	66.87 3	90.78 7

save fliter					86.17 35	61.30 28	83.98 58	79.66 182	59.00 160

test0726					87.75 7	59.07 74	87.86 4	86.83 8	64.26 32	84.19 7	91.92 5	64.82 8

GSMVS																78.05 366

test_part2					87.58 9	60.47 42				83.42 14

sam_mvs1												34.74 356				78.05 366

sam_mvs												33.43 374

MTGPA								80.97 161

test_post											3.55 534	33.90 368	66.52 422

patchmatchnet-post											64.03 473	34.50 358	74.27 371

MTMP							86.03 23	17.08 515

TEST9					85.58 45	61.59 24	81.62 91	81.26 150	55.65 244	74.93 66	88.81 68	53.70 91	84.68 141

test_8					85.40 48	60.96 34	81.54 94	81.18 154	55.86 236	74.81 71	88.80 70	53.70 91	84.45 145

agg_prior					85.04 55	59.96 50		81.04 159		74.68 76			84.04 152

test_prior4						62.51 14	82.08 87

test_prior				76.69 67	84.20 67	57.27 100		84.88 46					86.43 92			86.38 119

新几何2							76.12 224

旧先验1					83.04 80	53.15 183		67.52 381			87.85 89	44.08 238			80.76 125	78.03 369

原ACMM2							79.02 131

test222					83.14 78	58.68 83	72.57 311	63.45 421	41.78 447	67.56 227	86.12 150	37.13 332			78.73 176	74.98 408

segment_acmp												54.23 78

testdata1							72.65 306		60.50 119

test12				77.76 51	84.52 64	58.41 85		83.36 94		72.93 120		54.61 75	88.05 45		88.12 38	86.81 100

plane_prior7					81.41 103	55.96 123

plane_prior6					81.20 110	56.24 118						45.26 225

plane_prior4											86.10 151

plane_prior3						56.09 120			63.92 39	69.27 184

plane_prior2							84.22 51		64.52 28

plane_prior1					81.27 108

plane_prior						56.31 114	83.58 64		63.19 56						80.48 132

n2								0.00 563

nn								0.00 563

door-mid								47.19 489

test11								83.47 89

door								47.60 487

HQP5-MVS						54.94 145

HQP-NCC					80.66 117		82.31 82		62.10 83	67.85 216

ACMP_Plane					80.66 117		82.31 82		62.10 83	67.85 216

HQP4-MVS										67.85 216			86.93 74			84.32 212

HQP3-MVS								83.90 65							80.35 134

HQP2-MVS												45.46 219

NP-MVS					80.98 113	56.05 122					85.54 174

ACMMP++_ref															74.07 254

ACMMP++															72.16 295

Test By Simon												48.33 180

High-resolution multi-view benchmark