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.

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 142	93.00 76	58.16 337	96.72 9	94.41 53	86.50 9	90.25 28	97.83 1	75.46 14	98.67 25	92.78 29	95.49 13	97.32 6

fmvsm_s_conf0.5_n_8		87.96 22	88.93 18	85.07 126	88.43 200	61.78 266	94.73 54	91.74 172	85.87 10	91.66 15	97.50 2	64.03 101	98.33 34	96.28 4	90.08 100	95.10 84

fmvsm_s_conf0.5_n_9		88.14 18	89.21 16	84.92 130	89.29 176	61.41 279	92.97 130	88.36 319	86.96 6	91.49 19	97.49 3	69.48 51	97.46 71	97.00 1	89.88 104	95.89 47

fmvsm_s_conf0.5_n_3		86.88 40	87.99 30	83.58 188	87.26 235	60.74 293	93.21 122	87.94 334	84.22 19	91.70 14	97.27 4	65.91 77	95.02 202	93.95 21	90.42 96	94.99 90

DPE-MVS		88.77 17	89.21 16	87.45 43	96.26 20	67.56 104	94.17 67	94.15 64	68.77 288	90.74 22	97.27 4	76.09 12	98.49 29	90.58 48	94.91 21	96.30 34
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 165	76.68 2	97.29 1	95.35 17	82.87 34	91.58 16	97.22 6	79.93 5	99.10 9	83.12 115	97.64 2	97.94 1

SED-MVS		89.94 9	90.36 10	88.70 18	96.45 12	69.38 56	96.89 6	94.44 51	71.65 239	92.11 8	97.21 7	76.79 9	99.11 6	92.34 32	95.36 14	97.62 2

test_241102_TWO								94.41 53	71.65 239	92.07 10	97.21 7	74.58 18	99.11 6	92.34 32	95.36 14	96.59 19

test0726					96.40 15	69.99 39	96.76 8	94.33 59	71.92 225	91.89 12	97.11 9	73.77 23

test_241102_ONE					96.45 12	69.38 56		94.44 51	71.65 239	92.11 8	97.05 10	76.79 9	99.11 6

test_fmvsm_n_1920		87.69 28	88.50 22	85.27 120	87.05 242	63.55 221	93.69 98	91.08 208	84.18 20	90.17 30	97.04 11	67.58 61	97.99 41	95.72 7	90.03 101	94.26 127

OPU-MVS				89.97 3	97.52 3	73.15 14	96.89 6				97.00 12	83.82 2	99.15 2	95.72 7	97.63 3	97.62 2

fmvsm_l_conf0.5_n_a		87.44 34	88.15 28	85.30 117	87.10 240	64.19 197	94.41 59	88.14 327	80.24 72	92.54 5	96.97 13	69.52 50	97.17 92	95.89 5	88.51 119	94.56 112

DVP-MVS		89.41 13	89.73 14	88.45 25	96.40 15	69.99 39	96.64 10	94.52 47	71.92 225	90.55 24	96.93 14	73.77 23	99.08 11	91.91 38	94.90 22	96.29 35
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									72.48 209	90.55 24	96.93 14	76.24 11	99.08 11	91.53 40	94.99 18	96.43 31

fmvsm_s_conf0.5_n		86.39 53	86.91 45	84.82 135	87.36 234	63.54 222	94.74 51	90.02 254	82.52 37	90.14 31	96.92 16	62.93 126	97.84 49	95.28 10	82.26 187	93.07 177

fmvsm_s_conf0.5_n_a		85.75 70	86.09 63	84.72 142	85.73 274	63.58 219	93.79 94	89.32 279	81.42 54	90.21 29	96.91 17	62.41 133	97.67 56	94.48 15	80.56 208	92.90 183

fmvsm_l_conf0.5_n_3		87.54 29	88.29 25	85.30 117	86.92 248	62.63 247	95.02 43	90.28 242	84.95 13	90.27 27	96.86 18	65.36 82	97.52 69	94.93 12	90.03 101	95.76 51

fmvsm_l_conf0.5_n		87.49 32	88.19 27	85.39 112	86.95 243	64.37 190	94.30 64	88.45 317	80.51 64	92.70 4	96.86 18	69.98 48	97.15 96	95.83 6	88.08 124	94.65 109

DVP-MVS++		90.53 4	91.09 5	88.87 16	97.31 4	69.91 43	93.96 81	94.37 57	72.48 209	92.07 10	96.85 20	83.82 2	99.15 2	91.53 40	97.42 4	97.55 4

test_one_0601					96.32 18	69.74 50		94.18 62	71.42 250	90.67 23	96.85 20	74.45 20

PC_three_1452									80.91 61	94.07 2	96.83 22	83.57 4	99.12 5	95.70 9	97.42 4	97.55 4

CNVR-MVS		90.32 6	90.89 8	88.61 22	96.76 8	70.65 30	96.47 14	94.83 33	84.83 14	89.07 37	96.80 23	70.86 43	99.06 15	92.64 30	95.71 11	96.12 40

fmvsm_s_conf0.1_n		85.61 74	85.93 66	84.68 146	82.95 322	63.48 224	94.03 79	89.46 273	81.69 47	89.86 32	96.74 24	61.85 139	97.75 52	94.74 14	82.01 193	92.81 185

fmvsm_s_conf0.5_n_2		85.06 84	85.60 73	83.44 195	86.92 248	60.53 300	94.41 59	87.31 340	83.30 29	88.72 39	96.72 25	54.28 233	97.75 52	94.07 19	84.68 164	92.04 211

SMA-MVS		88.14 18	88.29 25	87.67 33	93.21 68	68.72 73	93.85 88	94.03 67	74.18 172	91.74 13	96.67 26	65.61 80	98.42 33	89.24 54	96.08 7	95.88 48
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
fmvsm_s_conf0.1_n_a		84.76 91	84.84 87	84.53 153	80.23 352	63.50 223	92.79 140	88.73 308	80.46 65	89.84 33	96.65 27	60.96 147	97.57 66	93.80 22	80.14 210	92.53 194

PHI-MVS		86.83 44	86.85 48	86.78 63	93.47 63	65.55 159	95.39 30	95.10 25	71.77 235	85.69 66	96.52 28	62.07 136	98.77 23	86.06 84	95.60 12	96.03 43

9.14			87.63 33		93.86 48		94.41 59	94.18 62	72.76 204	86.21 58	96.51 29	66.64 67	97.88 47	90.08 49	94.04 39

MSLP-MVS++		86.27 59	85.91 67	87.35 45	92.01 108	68.97 67	95.04 41	92.70 122	79.04 99	81.50 108	96.50 30	58.98 175	96.78 124	83.49 113	93.93 41	96.29 35

SF-MVS		87.03 39	87.09 41	86.84 59	92.70 86	67.45 109	93.64 101	93.76 74	70.78 263	86.25 57	96.44 31	66.98 64	97.79 50	88.68 59	94.56 34	95.28 75

fmvsm_s_conf0.5_n_6		87.50 31	88.72 20	83.84 177	86.89 250	60.04 313	95.05 39	92.17 151	84.80 15	92.27 6	96.37 32	64.62 93	96.54 134	94.43 16	91.86 71	94.94 93

fmvsm_s_conf0.1_n_2		84.40 96	84.78 89	83.27 201	85.25 281	60.41 303	94.13 71	85.69 360	83.05 31	87.99 42	96.37 32	52.75 249	97.68 54	93.75 23	84.05 173	91.71 216

HPM-MVS++		89.37 14	89.95 13	87.64 34	95.10 30	68.23 87	95.24 33	94.49 49	82.43 39	88.90 38	96.35 34	71.89 40	98.63 26	88.76 58	96.40 6	96.06 41

APDe-MVS		87.54 29	87.84 31	86.65 67	96.07 23	66.30 139	94.84 49	93.78 71	69.35 279	88.39 40	96.34 35	67.74 60	97.66 59	90.62 47	93.44 51	96.01 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsmconf_n		86.58 50	87.17 40	84.82 135	85.28 280	62.55 248	94.26 66	89.78 261	83.81 24	87.78 45	96.33 36	65.33 83	96.98 108	94.40 17	87.55 130	94.95 92

fmvsm_s_conf0.5_n_4		86.79 47	87.63 33	84.27 165	86.15 265	61.48 276	94.69 55	91.16 200	83.79 25	90.51 26	96.28 37	64.24 98	98.22 35	95.00 11	86.88 136	93.11 174

fmvsm_s_conf0.5_n_7		85.24 80	86.69 50	80.91 269	84.52 297	60.10 311	93.35 117	90.35 235	83.41 28	86.54 56	96.27 38	60.50 152	90.02 353	94.84 13	90.38 97	92.61 189

MCST-MVS		91.08 1	91.46 3	89.94 4	97.66 2	73.37 10	97.13 2	95.58 11	89.33 1	85.77 64	96.26 39	72.84 30	99.38 1	92.64 30	95.93 9	97.08 11

NCCC		89.07 16	89.46 15	87.91 28	96.60 10	69.05 64	96.38 15	94.64 42	84.42 18	86.74 54	96.20 40	66.56 69	98.76 24	89.03 57	94.56 34	95.92 46

MM		90.87 2	91.52 2	88.92 15	92.12 101	71.10 27	97.02 3	96.04 6	88.70 2	91.57 17	96.19 41	70.12 47	98.91 18	96.83 2	95.06 17	96.76 15

DeepC-MVS_fast	79.48 2	87.95 24	88.00 29	87.79 31	95.86 27	68.32 81	95.74 21	94.11 65	83.82 23	83.49 90	96.19 41	64.53 96	98.44 31	83.42 114	94.88 25	96.61 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVS_0304		90.32 6	90.90 7	88.55 23	94.05 45	70.23 37	97.00 5	93.73 78	87.30 4	92.15 7	96.15 43	66.38 70	98.94 17	96.71 3	94.67 33	96.47 28

MSP-MVS		90.38 5	91.87 1	85.88 93	92.83 80	64.03 202	93.06 125	94.33 59	82.19 42	93.65 3	96.15 43	85.89 1	97.19 91	91.02 44	97.75 1	96.43 31
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
PS-MVSNAJ		88.14 18	87.61 35	89.71 7	92.06 104	76.72 1	95.75 20	93.26 99	83.86 22	89.55 35	96.06 45	53.55 240	97.89 46	91.10 42	93.31 53	94.54 115

fmvsm_s_conf0.5_n_5		86.38 55	86.94 44	84.71 144	84.67 292	63.29 227	94.04 77	89.99 256	82.88 33	87.85 44	96.03 46	62.89 128	96.36 143	94.15 18	89.95 103	94.48 121

test_fmvsmconf0.1_n		85.71 71	86.08 64	84.62 151	80.83 339	62.33 253	93.84 91	88.81 305	83.50 27	87.00 52	96.01 47	63.36 116	96.93 116	94.04 20	87.29 133	94.61 111

xiu_mvs_v2_base		87.92 25	87.38 39	89.55 12	91.41 131	76.43 3	95.74 21	93.12 107	83.53 26	89.55 35	95.95 48	53.45 244	97.68 54	91.07 43	92.62 60	94.54 115

APD-MVS		85.93 66	85.99 65	85.76 100	95.98 26	65.21 167	93.59 104	92.58 133	66.54 308	86.17 60	95.88 49	63.83 105	97.00 104	86.39 81	92.94 57	95.06 86
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CANet		89.61 12	89.99 12	88.46 24	94.39 39	69.71 51	96.53 13	93.78 71	86.89 7	89.68 34	95.78 50	65.94 75	99.10 9	92.99 27	93.91 42	96.58 21

SD-MVS		87.49 32	87.49 37	87.50 42	93.60 56	68.82 70	93.90 85	92.63 131	76.86 135	87.90 43	95.76 51	66.17 72	97.63 61	89.06 56	91.48 79	96.05 42
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		83.80 113	83.48 104	84.77 139	82.51 325	63.72 212	91.37 209	83.99 377	81.42 54	77.68 158	95.74 52	58.37 180	97.58 64	93.38 24	86.87 137	93.00 180

SteuartSystems-ACMMP		86.82 46	86.90 46	86.58 71	90.42 150	66.38 136	96.09 17	93.87 69	77.73 122	84.01 85	95.66 53	63.39 115	97.94 42	87.40 70	93.55 50	95.42 62
Skip Steuart: Steuart Systems R&D Blog.
MP-MVS-pluss		85.24 80	85.13 81	85.56 107	91.42 128	65.59 157	91.54 200	92.51 135	74.56 165	80.62 121	95.64 54	59.15 170	97.00 104	86.94 77	93.80 43	94.07 140
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_prior2							95.10 38		75.40 155	85.25 74	95.61 55	67.94 58		87.47 69	94.77 26

MAR-MVS		84.18 105	83.43 107	86.44 76	96.25 21	65.93 150	94.28 65	94.27 61	74.41 167	79.16 141	95.61 55	53.99 235	98.88 22	69.62 232	93.26 54	94.50 119
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
reproduce-ours		83.51 119	83.33 113	84.06 169	92.18 99	60.49 301	90.74 237	92.04 154	64.35 323	83.24 91	95.59 57	59.05 171	97.27 87	83.61 110	89.17 112	94.41 124

our_new_method		83.51 119	83.33 113	84.06 169	92.18 99	60.49 301	90.74 237	92.04 154	64.35 323	83.24 91	95.59 57	59.05 171	97.27 87	83.61 110	89.17 112	94.41 124

SPE-MVS-test		86.14 62	87.01 42	83.52 189	92.63 88	59.36 325	95.49 27	91.92 161	80.09 73	85.46 70	95.53 59	61.82 140	95.77 169	86.77 79	93.37 52	95.41 63

reproduce_model		83.15 126	82.96 120	83.73 181	92.02 105	59.74 317	90.37 250	92.08 152	63.70 330	82.86 96	95.48 60	58.62 177	97.17 92	83.06 116	88.42 120	94.26 127

test_fmvsmconf0.01_n		83.70 117	83.52 101	84.25 166	75.26 398	61.72 270	92.17 168	87.24 342	82.36 40	84.91 75	95.41 61	55.60 215	96.83 123	92.85 28	85.87 152	94.21 130

CS-MVS		85.80 69	86.65 53	83.27 201	92.00 109	58.92 329	95.31 31	91.86 166	79.97 74	84.82 76	95.40 62	62.26 134	95.51 188	86.11 83	92.08 68	95.37 66

test_8					94.19 40	67.19 113	94.15 70	93.42 94	71.87 230	85.38 71	95.35 63	68.19 55	96.95 113

TEST9					94.18 41	67.28 111	94.16 68	93.51 87	71.75 236	85.52 68	95.33 64	68.01 57	97.27 87

train_agg		87.21 37	87.42 38	86.60 69	94.18 41	67.28 111	94.16 68	93.51 87	71.87 230	85.52 68	95.33 64	68.19 55	97.27 87	89.09 55	94.90 22	95.25 79

lecture		84.77 90	84.81 88	84.65 147	92.12 101	62.27 256	94.74 51	92.64 130	68.35 293	85.53 67	95.30 66	59.77 162	97.91 44	83.73 109	91.15 85	93.77 155

ACMMP_NAP		86.05 63	85.80 69	86.80 62	91.58 123	67.53 106	91.79 190	93.49 90	74.93 162	84.61 77	95.30 66	59.42 166	97.92 43	86.13 82	94.92 20	94.94 93

SR-MVS		82.81 133	82.58 129	83.50 192	93.35 64	61.16 283	92.23 166	91.28 197	64.48 322	81.27 111	95.28 68	53.71 239	95.86 165	82.87 119	88.77 117	93.49 162

CDPH-MVS		85.71 71	85.46 75	86.46 75	94.75 34	67.19 113	93.89 86	92.83 118	70.90 259	83.09 95	95.28 68	63.62 110	97.36 78	80.63 139	94.18 37	94.84 98

cdsmvs_eth3d_5k		19.86 416	26.47 415	0.00 435	0.00 458	0.00 460	0.00 446	93.45 91	0.00 453	0.00 454	95.27 70	49.56 281	0.00 454	0.00 453	0.00 451	0.00 450

lupinMVS		87.74 27	87.77 32	87.63 38	89.24 181	71.18 24	96.57 12	92.90 116	82.70 36	87.13 49	95.27 70	64.99 86	95.80 166	89.34 52	91.80 73	95.93 45

sasdasda		86.85 42	86.25 58	88.66 20	91.80 117	71.92 16	93.54 106	91.71 175	80.26 69	87.55 46	95.25 72	63.59 112	96.93 116	88.18 60	84.34 165	97.11 9

canonicalmvs		86.85 42	86.25 58	88.66 20	91.80 117	71.92 16	93.54 106	91.71 175	80.26 69	87.55 46	95.25 72	63.59 112	96.93 116	88.18 60	84.34 165	97.11 9

alignmvs		87.28 36	86.97 43	88.24 27	91.30 133	71.14 26	95.61 25	93.56 84	79.30 89	87.07 51	95.25 72	68.43 53	96.93 116	87.87 63	84.33 167	96.65 17

MTAPA		83.91 110	83.38 111	85.50 108	91.89 115	65.16 169	81.75 362	92.23 142	75.32 157	80.53 123	95.21 75	56.06 211	97.16 95	84.86 97	92.55 62	94.18 132

ZD-MVS					96.63 9	65.50 161		93.50 89	70.74 264	85.26 73	95.19 76	64.92 89	97.29 83	87.51 67	93.01 56

patch_mono-2		89.71 11	90.99 6	85.85 96	96.04 24	63.70 214	95.04 41	95.19 22	86.74 8	91.53 18	95.15 77	73.86 22	97.58 64	93.38 24	92.00 69	96.28 37

MGCFI-Net		85.59 75	85.73 71	85.17 124	91.41 131	62.44 249	92.87 138	91.31 192	79.65 81	86.99 53	95.14 78	62.90 127	96.12 153	87.13 74	84.13 172	96.96 13

PAPR		85.15 83	84.47 91	87.18 49	96.02 25	68.29 82	91.85 188	93.00 113	76.59 142	79.03 142	95.00 79	61.59 141	97.61 63	78.16 163	89.00 114	95.63 55

1112_ss		80.56 175	79.83 174	82.77 212	88.65 193	60.78 289	92.29 163	88.36 319	72.58 207	72.46 224	94.95 80	65.09 85	93.42 272	66.38 269	77.71 231	94.10 137

ab-mvs-re		7.91 418	10.55 421	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	94.95 80	0.00 458	0.00 454	0.00 453	0.00 451	0.00 450

HFP-MVS		84.73 92	84.40 93	85.72 102	93.75 52	65.01 173	93.50 109	93.19 103	72.19 219	79.22 140	94.93 82	59.04 173	97.67 56	81.55 128	92.21 64	94.49 120

CP-MVS		83.71 116	83.40 110	84.65 147	93.14 71	63.84 205	94.59 56	92.28 140	71.03 257	77.41 162	94.92 83	55.21 220	96.19 150	81.32 133	90.70 91	93.91 149

DELS-MVS		90.05 8	90.09 11	89.94 4	93.14 71	73.88 9	97.01 4	94.40 55	88.32 3	85.71 65	94.91 84	74.11 21	98.91 18	87.26 72	95.94 8	97.03 12
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
ACMMPR		84.37 97	84.06 95	85.28 119	93.56 58	64.37 190	93.50 109	93.15 105	72.19 219	78.85 148	94.86 85	56.69 202	97.45 72	81.55 128	92.20 65	94.02 143

region2R		84.36 98	84.03 96	85.36 115	93.54 60	64.31 193	93.43 114	92.95 114	72.16 222	78.86 147	94.84 86	56.97 197	97.53 68	81.38 132	92.11 67	94.24 129

TSAR-MVS + GP.		87.96 22	88.37 24	86.70 66	93.51 62	65.32 164	95.15 36	93.84 70	78.17 113	85.93 63	94.80 87	75.80 13	98.21 36	89.38 51	88.78 116	96.59 19

WTY-MVS		86.32 56	85.81 68	87.85 29	92.82 82	69.37 58	95.20 34	95.25 20	82.71 35	81.91 105	94.73 88	67.93 59	97.63 61	79.55 148	82.25 188	96.54 22

MVS		84.66 93	82.86 125	90.06 2	90.93 140	74.56 7	87.91 306	95.54 14	68.55 290	72.35 227	94.71 89	59.78 161	98.90 20	81.29 134	94.69 32	96.74 16

ZNCC-MVS		85.33 79	85.08 82	86.06 88	93.09 73	65.65 155	93.89 86	93.41 95	73.75 183	79.94 130	94.68 90	60.61 151	98.03 40	82.63 121	93.72 46	94.52 117

test_vis1_n_1920		81.66 153	82.01 137	80.64 272	82.24 327	55.09 366	94.76 50	86.87 344	81.67 48	84.40 80	94.63 91	38.17 352	94.67 220	91.98 37	83.34 178	92.16 209

APD-MVS_3200maxsize		81.64 154	81.32 144	82.59 220	92.36 92	58.74 331	91.39 206	91.01 213	63.35 334	79.72 133	94.62 92	51.82 255	96.14 152	79.71 146	87.93 125	92.89 184

EPNet		87.84 26	88.38 23	86.23 83	93.30 65	66.05 143	95.26 32	94.84 32	87.09 5	88.06 41	94.53 93	66.79 66	97.34 80	83.89 107	91.68 75	95.29 73
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SR-MVS-dyc-post		81.06 166	80.70 157	82.15 234	92.02 105	58.56 334	90.90 229	90.45 228	62.76 341	78.89 143	94.46 94	51.26 265	95.61 179	78.77 159	86.77 141	92.28 202

RE-MVS-def			80.48 164		92.02 105	58.56 334	90.90 229	90.45 228	62.76 341	78.89 143	94.46 94	49.30 284		78.77 159	86.77 141	92.28 202

MP-MVS		85.02 85	84.97 84	85.17 124	92.60 89	64.27 195	93.24 119	92.27 141	73.13 194	79.63 134	94.43 96	61.90 137	97.17 92	85.00 94	92.56 61	94.06 141
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PGM-MVS		83.25 124	82.70 128	84.92 130	92.81 84	64.07 201	90.44 246	92.20 146	71.28 251	77.23 166	94.43 96	55.17 221	97.31 82	79.33 151	91.38 81	93.37 164

xiu_mvs_v1_base_debu		82.16 144	81.12 147	85.26 121	86.42 257	68.72 73	92.59 154	90.44 232	73.12 195	84.20 81	94.36 98	38.04 355	95.73 171	84.12 104	86.81 138	91.33 223

xiu_mvs_v1_base		82.16 144	81.12 147	85.26 121	86.42 257	68.72 73	92.59 154	90.44 232	73.12 195	84.20 81	94.36 98	38.04 355	95.73 171	84.12 104	86.81 138	91.33 223

xiu_mvs_v1_base_debi		82.16 144	81.12 147	85.26 121	86.42 257	68.72 73	92.59 154	90.44 232	73.12 195	84.20 81	94.36 98	38.04 355	95.73 171	84.12 104	86.81 138	91.33 223

旧先验1					91.94 110	60.74 293		91.50 186			94.36 98	65.23 84			91.84 72	94.55 113

CSCG		86.87 41	86.26 57	88.72 17	95.05 31	70.79 29	93.83 93	95.33 18	68.48 292	77.63 159	94.35 102	73.04 28	98.45 30	84.92 96	93.71 47	96.92 14

MVSFormer		83.75 115	82.88 124	86.37 79	89.24 181	71.18 24	89.07 286	90.69 220	65.80 313	87.13 49	94.34 103	64.99 86	92.67 296	72.83 199	91.80 73	95.27 76

jason		86.40 52	86.17 60	87.11 51	86.16 264	70.54 32	95.71 24	92.19 148	82.00 44	84.58 78	94.34 103	61.86 138	95.53 187	87.76 64	90.89 89	95.27 76
jason: jason.
GDP-MVS		85.54 76	85.32 77	86.18 84	87.64 226	67.95 95	92.91 136	92.36 138	77.81 119	83.69 87	94.31 105	72.84 30	96.41 141	80.39 142	85.95 151	94.19 131

XVS		83.87 111	83.47 105	85.05 127	93.22 66	63.78 207	92.92 134	92.66 127	73.99 175	78.18 153	94.31 105	55.25 217	97.41 75	79.16 152	91.58 77	93.95 145

EIA-MVS		84.84 89	84.88 85	84.69 145	91.30 133	62.36 252	93.85 88	92.04 154	79.45 84	79.33 139	94.28 107	62.42 132	96.35 144	80.05 144	91.25 84	95.38 65

mPP-MVS		82.96 132	82.44 132	84.52 154	92.83 80	62.92 240	92.76 141	91.85 168	71.52 247	75.61 182	94.24 108	53.48 243	96.99 107	78.97 155	90.73 90	93.64 159

EC-MVSNet		84.53 95	85.04 83	83.01 207	89.34 172	61.37 280	94.42 58	91.09 206	77.91 117	83.24 91	94.20 109	58.37 180	95.40 190	85.35 87	91.41 80	92.27 205

GST-MVS		84.63 94	84.29 94	85.66 104	92.82 82	65.27 165	93.04 127	93.13 106	73.20 192	78.89 143	94.18 110	59.41 167	97.85 48	81.45 130	92.48 63	93.86 152

BP-MVS1		86.54 51	86.68 51	86.13 86	87.80 223	67.18 115	92.97 130	95.62 10	79.92 75	82.84 97	94.14 111	74.95 15	96.46 139	82.91 118	88.96 115	94.74 103

NormalMVS		86.39 53	86.66 52	85.60 106	92.12 101	65.95 148	94.88 46	90.83 215	84.69 16	83.67 88	94.10 112	63.16 121	96.91 120	85.31 88	91.15 85	93.93 147

SymmetryMVS		86.32 56	86.39 55	86.12 87	90.52 148	65.95 148	94.88 46	94.58 46	84.69 16	83.67 88	94.10 112	63.16 121	96.91 120	85.31 88	86.59 145	95.51 60

EI-MVSNet-Vis-set		83.77 114	83.67 99	84.06 169	92.79 85	63.56 220	91.76 193	94.81 34	79.65 81	77.87 156	94.09 114	63.35 117	97.90 45	79.35 150	79.36 217	90.74 236

testdata				81.34 253	89.02 185	57.72 341		89.84 260	58.65 373	85.32 72	94.09 114	57.03 193	93.28 273	69.34 235	90.56 94	93.03 178

ETV-MVS		86.01 64	86.11 62	85.70 103	90.21 155	67.02 121	93.43 114	91.92 161	81.21 58	84.13 84	94.07 116	60.93 148	95.63 177	89.28 53	89.81 105	94.46 122

MVS_111021_HR		86.19 61	85.80 69	87.37 44	93.17 70	69.79 48	93.99 80	93.76 74	79.08 96	78.88 146	93.99 117	62.25 135	98.15 38	85.93 85	91.15 85	94.15 135

HPM-MVS		83.25 124	82.95 122	84.17 167	92.25 95	62.88 242	90.91 228	91.86 166	70.30 268	77.12 167	93.96 118	56.75 200	96.28 146	82.04 125	91.34 83	93.34 165
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DP-MVS Recon		82.73 134	81.65 141	85.98 90	97.31 4	67.06 118	95.15 36	91.99 158	69.08 285	76.50 174	93.89 119	54.48 229	98.20 37	70.76 223	85.66 155	92.69 186

EI-MVSNet-UG-set		83.14 127	82.96 120	83.67 186	92.28 94	63.19 232	91.38 208	94.68 40	79.22 91	76.60 172	93.75 120	62.64 129	97.76 51	78.07 164	78.01 229	90.05 245

CANet_DTU		84.09 107	83.52 101	85.81 97	90.30 153	66.82 125	91.87 186	89.01 297	85.27 11	86.09 61	93.74 121	47.71 301	96.98 108	77.90 165	89.78 107	93.65 158

test_cas_vis1_n_1920		80.45 178	80.61 160	79.97 291	78.25 379	57.01 353	94.04 77	88.33 321	79.06 98	82.81 99	93.70 122	38.65 347	91.63 327	90.82 46	79.81 212	91.27 229

dcpmvs_2		87.37 35	87.55 36	86.85 58	95.04 32	68.20 88	90.36 251	90.66 223	79.37 88	81.20 112	93.67 123	74.73 16	96.55 133	90.88 45	92.00 69	95.82 49

ET-MVSNet_ETH3D		84.01 108	83.15 118	86.58 71	90.78 145	70.89 28	94.74 51	94.62 43	81.44 53	58.19 364	93.64 124	73.64 25	92.35 309	82.66 120	78.66 226	96.50 27

DeepC-MVS	77.85 3	85.52 77	85.24 79	86.37 79	88.80 191	66.64 130	92.15 169	93.68 80	81.07 59	76.91 170	93.64 124	62.59 130	98.44 31	85.50 86	92.84 59	94.03 142
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PAPM_NR		82.97 131	81.84 139	86.37 79	94.10 44	66.76 128	87.66 312	92.84 117	69.96 272	74.07 202	93.57 126	63.10 124	97.50 70	70.66 225	90.58 93	94.85 95

PMMVS		81.98 149	82.04 136	81.78 243	89.76 164	56.17 357	91.13 224	90.69 220	77.96 115	80.09 129	93.57 126	46.33 312	94.99 205	81.41 131	87.46 131	94.17 133

LFMVS		84.34 99	82.73 127	89.18 13	94.76 33	73.25 11	94.99 44	91.89 164	71.90 227	82.16 104	93.49 128	47.98 297	97.05 99	82.55 122	84.82 160	97.25 8

ACMMP		81.49 156	80.67 158	83.93 175	91.71 120	62.90 241	92.13 170	92.22 145	71.79 234	71.68 236	93.49 128	50.32 270	96.96 112	78.47 161	84.22 171	91.93 213
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
CPTT-MVS		79.59 193	79.16 188	80.89 270	91.54 126	59.80 316	92.10 172	88.54 316	60.42 362	72.96 210	93.28 130	48.27 293	92.80 290	78.89 158	86.50 147	90.06 244

MVS_111021_LR		82.02 148	81.52 142	83.51 191	88.42 201	62.88 242	89.77 268	88.93 301	76.78 138	75.55 183	93.10 131	50.31 271	95.38 192	83.82 108	87.02 135	92.26 206

1314		80.70 172	78.95 191	85.94 92	87.77 225	67.56 104	87.91 306	92.55 134	72.17 221	67.44 292	93.09 132	50.27 272	97.04 102	71.68 216	87.64 129	93.23 169

PVSNet_Blended		86.73 48	86.86 47	86.31 82	93.76 50	67.53 106	96.33 16	93.61 82	82.34 41	81.00 117	93.08 133	63.19 119	97.29 83	87.08 75	91.38 81	94.13 136

VNet		86.20 60	85.65 72	87.84 30	93.92 47	69.99 39	95.73 23	95.94 7	78.43 109	86.00 62	93.07 134	58.22 182	97.00 104	85.22 90	84.33 167	96.52 23

HPM-MVS_fast		80.25 182	79.55 181	82.33 226	91.55 125	59.95 314	91.32 213	89.16 287	65.23 319	74.71 195	93.07 134	47.81 300	95.74 170	74.87 188	88.23 121	91.31 227

PAPM		85.89 68	85.46 75	87.18 49	88.20 211	72.42 15	92.41 161	92.77 120	82.11 43	80.34 126	93.07 134	68.27 54	95.02 202	78.39 162	93.59 49	94.09 138

MG-MVS		87.11 38	86.27 56	89.62 8	97.79 1	76.27 4	94.96 45	94.49 49	78.74 104	83.87 86	92.94 137	64.34 97	96.94 114	75.19 181	94.09 38	95.66 54

新几何1				84.73 141	92.32 93	64.28 194		91.46 188	59.56 369	79.77 132	92.90 138	56.95 198	96.57 131	63.40 293	92.91 58	93.34 165

TSAR-MVS + MP.		88.11 21	88.64 21	86.54 73	91.73 119	68.04 91	90.36 251	93.55 85	82.89 32	91.29 20	92.89 139	72.27 37	96.03 161	87.99 62	94.77 26	95.54 59
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_yl		84.28 100	83.16 116	87.64 34	94.52 37	69.24 60	95.78 18	95.09 26	69.19 282	81.09 114	92.88 140	57.00 195	97.44 73	81.11 136	81.76 195	96.23 38

DCV-MVSNet		84.28 100	83.16 116	87.64 34	94.52 37	69.24 60	95.78 18	95.09 26	69.19 282	81.09 114	92.88 140	57.00 195	97.44 73	81.11 136	81.76 195	96.23 38

API-MVS		82.28 142	80.53 163	87.54 41	96.13 22	70.59 31	93.63 102	91.04 212	65.72 315	75.45 185	92.83 142	56.11 210	98.89 21	64.10 289	89.75 108	93.15 172

Effi-MVS+		83.82 112	82.76 126	86.99 56	89.56 168	69.40 54	91.35 211	86.12 354	72.59 206	83.22 94	92.81 143	59.60 164	96.01 163	81.76 127	87.80 127	95.56 58

TAPA-MVS	70.22 12	74.94 279	73.53 275	79.17 308	90.40 151	52.07 378	89.19 284	89.61 270	62.69 343	70.07 254	92.67 144	48.89 291	94.32 233	38.26 407	79.97 211	91.12 231
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
diffmvs		84.28 100	83.83 97	85.61 105	87.40 232	68.02 92	90.88 231	89.24 282	80.54 63	81.64 107	92.52 145	59.83 160	94.52 229	87.32 71	85.11 158	94.29 126
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
原ACMM1				84.42 157	93.21 68	64.27 195		93.40 96	65.39 316	79.51 135	92.50 146	58.11 184	96.69 127	65.27 283	93.96 40	92.32 200

baseline		85.01 86	84.44 92	86.71 65	88.33 205	68.73 72	90.24 256	91.82 170	81.05 60	81.18 113	92.50 146	63.69 108	96.08 158	84.45 101	86.71 143	95.32 71

3Dnovator+	73.60 7	82.10 147	80.60 161	86.60 69	90.89 142	66.80 127	95.20 34	93.44 92	74.05 174	67.42 293	92.49 148	49.46 282	97.65 60	70.80 222	91.68 75	95.33 69

3Dnovator	73.91 6	82.69 137	80.82 154	88.31 26	89.57 167	71.26 22	92.60 152	94.39 56	78.84 101	67.89 286	92.48 149	48.42 292	98.52 28	68.80 243	94.40 36	95.15 81

test222					89.77 163	61.60 273	89.55 273	89.42 276	56.83 384	77.28 165	92.43 150	52.76 248			91.14 88	93.09 175

sss		82.71 136	82.38 133	83.73 181	89.25 178	59.58 320	92.24 165	94.89 31	77.96 115	79.86 131	92.38 151	56.70 201	97.05 99	77.26 168	80.86 203	94.55 113

AdaColmap		78.94 206	77.00 223	84.76 140	96.34 17	65.86 151	92.66 149	87.97 333	62.18 346	70.56 246	92.37 152	43.53 328	97.35 79	64.50 287	82.86 181	91.05 232

VDD-MVS		83.06 129	81.81 140	86.81 61	90.86 143	67.70 100	95.40 29	91.50 186	75.46 153	81.78 106	92.34 153	40.09 342	97.13 97	86.85 78	82.04 192	95.60 56

testing222		85.18 82	84.69 90	86.63 68	92.91 78	69.91 43	92.61 151	95.80 9	80.31 68	80.38 125	92.27 154	68.73 52	95.19 199	75.94 175	83.27 179	94.81 102

CLD-MVS		82.73 134	82.35 134	83.86 176	87.90 218	67.65 102	95.45 28	92.18 149	85.06 12	72.58 218	92.27 154	52.46 252	95.78 167	84.18 103	79.06 221	88.16 273
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
h-mvs33		83.01 130	82.56 130	84.35 161	89.34 172	62.02 260	92.72 143	93.76 74	81.45 51	82.73 100	92.25 156	60.11 156	97.13 97	87.69 65	62.96 345	93.91 149

testing11		86.71 49	86.44 54	87.55 40	93.54 60	71.35 21	93.65 100	95.58 11	81.36 56	80.69 120	92.21 157	72.30 36	96.46 139	85.18 92	83.43 177	94.82 101

UBG		86.83 44	86.70 49	87.20 48	93.07 74	69.81 47	93.43 114	95.56 13	81.52 49	81.50 108	92.12 158	73.58 26	96.28 146	84.37 102	85.20 157	95.51 60

OMC-MVS		78.67 215	77.91 206	80.95 267	85.76 273	57.40 348	88.49 296	88.67 311	73.85 180	72.43 225	92.10 159	49.29 285	94.55 227	72.73 203	77.89 230	90.91 235

myMVS_eth3d28		86.31 58	86.15 61	86.78 63	93.56 58	70.49 33	92.94 133	95.28 19	82.47 38	78.70 150	92.07 160	72.45 34	95.41 189	82.11 124	85.78 153	94.44 123

casdiffmvs		85.37 78	84.87 86	86.84 59	88.25 208	69.07 63	93.04 127	91.76 171	81.27 57	80.84 119	92.07 160	64.23 99	96.06 159	84.98 95	87.43 132	95.39 64
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
OpenMVS	70.45 11	78.54 217	75.92 239	86.41 78	85.93 271	71.68 18	92.74 142	92.51 135	66.49 309	64.56 319	91.96 162	43.88 327	98.10 39	54.61 337	90.65 92	89.44 257

testing99		86.01 64	85.47 74	87.63 38	93.62 55	71.25 23	93.47 112	95.23 21	80.42 67	80.60 122	91.95 163	71.73 41	96.50 137	80.02 145	82.22 189	95.13 82

testing91		85.93 66	85.31 78	87.78 32	93.59 57	71.47 19	93.50 109	95.08 28	80.26 69	80.53 123	91.93 164	70.43 45	96.51 136	80.32 143	82.13 191	95.37 66

Vis-MVSNet (Re-imp)		79.24 200	79.57 178	78.24 319	88.46 198	52.29 377	90.41 248	89.12 291	74.24 171	69.13 263	91.91 165	65.77 78	90.09 351	59.00 322	88.09 123	92.33 199

gm-plane-assit					88.42 201	67.04 120			78.62 106		91.83 166		97.37 77	76.57 171

Vis-MVSNet		80.92 169	79.98 172	83.74 179	88.48 197	61.80 265	93.44 113	88.26 326	73.96 178	77.73 157	91.76 167	49.94 276	94.76 213	65.84 275	90.37 98	94.65 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
QAPM		79.95 189	77.39 217	87.64 34	89.63 166	71.41 20	93.30 118	93.70 79	65.34 318	67.39 295	91.75 168	47.83 299	98.96 16	57.71 326	89.81 105	92.54 193

IS-MVSNet		80.14 184	79.41 183	82.33 226	87.91 217	60.08 312	91.97 182	88.27 324	72.90 202	71.44 240	91.73 169	61.44 142	93.66 267	62.47 303	86.53 146	93.24 168

baseline1		81.84 150	81.03 151	84.28 164	91.60 122	66.62 131	91.08 225	91.66 180	81.87 45	74.86 191	91.67 170	69.98 48	94.92 209	71.76 214	64.75 332	91.29 228

ETVMVS		84.22 104	83.71 98	85.76 100	92.58 90	68.25 86	92.45 160	95.53 15	79.54 83	79.46 136	91.64 171	70.29 46	94.18 241	69.16 238	82.76 185	94.84 98

test_fmvs1		74.07 286	73.69 273	75.22 347	78.91 370	47.34 406	89.06 288	74.69 406	63.68 331	79.41 137	91.59 172	24.36 409	87.77 374	85.22 90	76.26 248	90.55 240

casdiffmvs_mvg		85.66 73	85.18 80	87.09 52	88.22 210	69.35 59	93.74 97	91.89 164	81.47 50	80.10 128	91.45 173	64.80 91	96.35 144	87.23 73	87.69 128	95.58 57
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test2506		83.29 123	82.92 123	84.37 160	88.39 203	63.18 233	92.01 178	91.35 191	77.66 124	78.49 152	91.42 174	64.58 95	95.09 201	73.19 195	89.23 109	94.85 95

ECVR-MVS		81.29 160	80.38 166	84.01 174	88.39 203	61.96 262	92.56 157	86.79 346	77.66 124	76.63 171	91.42 174	46.34 311	95.24 198	74.36 190	89.23 109	94.85 95

test1111		80.84 170	80.02 169	83.33 196	87.87 219	60.76 291	92.62 150	86.86 345	77.86 118	75.73 178	91.39 176	46.35 310	94.70 219	72.79 201	88.68 118	94.52 117

TR-MVS		78.77 212	77.37 218	82.95 209	90.49 149	60.88 287	93.67 99	90.07 250	70.08 271	74.51 196	91.37 177	45.69 317	95.70 176	60.12 316	80.32 209	92.29 201

EPNet_dtu		78.80 210	79.26 187	77.43 327	88.06 213	49.71 393	91.96 183	91.95 160	77.67 123	76.56 173	91.28 178	58.51 178	90.20 349	56.37 331	80.95 202	92.39 197
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvs1_n		72.69 305	71.92 296	74.99 351	71.15 411	47.08 408	87.34 317	75.67 401	63.48 333	78.08 155	91.17 179	20.16 423	87.87 371	84.65 99	75.57 252	90.01 246

BH-RMVSNet		79.46 198	77.65 208	84.89 132	91.68 121	65.66 154	93.55 105	88.09 329	72.93 199	73.37 207	91.12 180	46.20 314	96.12 153	56.28 332	85.61 156	92.91 182

thisisatest0515		83.41 121	82.49 131	86.16 85	89.46 171	68.26 84	93.54 106	94.70 39	74.31 170	75.75 177	90.92 181	72.62 32	96.52 135	69.64 230	81.50 198	93.71 156

VDDNet		80.50 176	78.26 199	87.21 47	86.19 262	69.79 48	94.48 57	91.31 192	60.42 362	79.34 138	90.91 182	38.48 350	96.56 132	82.16 123	81.05 201	95.27 76

GG-mvs-BLEND				86.53 74	91.91 114	69.67 53	75.02 403	94.75 36		78.67 151	90.85 183	77.91 7	94.56 226	72.25 208	93.74 45	95.36 68

CNLPA		74.31 284	72.30 292	80.32 277	91.49 127	61.66 271	90.85 232	80.72 390	56.67 385	63.85 328	90.64 184	46.75 306	90.84 338	53.79 341	75.99 250	88.47 269

PCF-MVS	73.15 9	79.29 199	77.63 209	84.29 163	86.06 266	65.96 147	87.03 319	91.10 205	69.86 274	69.79 260	90.64 184	57.54 189	96.59 129	64.37 288	82.29 186	90.32 241
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
114514_t		79.17 201	77.67 207	83.68 185	95.32 29	65.53 160	92.85 139	91.60 182	63.49 332	67.92 283	90.63 186	46.65 307	95.72 175	67.01 262	83.54 176	89.79 249

PLC	68.80 14	75.23 275	73.68 274	79.86 294	92.93 77	58.68 332	90.64 242	88.30 322	60.90 359	64.43 323	90.53 187	42.38 333	94.57 223	56.52 330	76.54 246	86.33 303
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PVSNet	73.49 8	80.05 186	78.63 194	84.31 162	90.92 141	64.97 174	92.47 159	91.05 211	79.18 92	72.43 225	90.51 188	37.05 367	94.06 248	68.06 249	86.00 150	93.90 151

hse-mvs2		81.12 165	81.11 150	81.16 257	86.52 256	57.48 346	89.40 278	91.16 200	81.45 51	82.73 100	90.49 189	60.11 156	94.58 221	87.69 65	60.41 372	91.41 222

AUN-MVS		78.37 219	77.43 213	81.17 256	86.60 253	57.45 347	89.46 277	91.16 200	74.11 173	74.40 197	90.49 189	55.52 216	94.57 223	74.73 189	60.43 371	91.48 220

KinetiMVS		81.43 157	80.11 167	85.38 114	86.60 253	65.47 163	92.90 137	93.54 86	75.33 156	77.31 164	90.39 191	46.81 304	96.75 125	71.65 217	86.46 148	93.93 147

baseline2		83.68 118	83.42 109	84.48 156	87.37 233	66.00 145	90.06 260	95.93 8	79.71 80	69.08 265	90.39 191	77.92 6	96.28 146	78.91 157	81.38 199	91.16 230

EPP-MVSNet		81.79 151	81.52 142	82.61 218	88.77 192	60.21 309	93.02 129	93.66 81	68.52 291	72.90 212	90.39 191	72.19 38	94.96 206	74.93 185	79.29 220	92.67 187

NP-MVS					87.41 231	63.04 234					90.30 194

HQP-MVS		81.14 163	80.64 159	82.64 217	87.54 228	63.66 217	94.06 73	91.70 178	79.80 77	74.18 198	90.30 194	51.63 260	95.61 179	77.63 166	78.90 222	88.63 264

mvsany_test1		68.77 332	68.56 321	69.39 387	73.57 404	45.88 415	80.93 371	60.88 435	59.65 368	71.56 237	90.26 196	43.22 330	75.05 422	74.26 192	62.70 348	87.25 289

AstraMVS		80.66 173	79.79 175	83.28 200	85.07 287	61.64 272	92.19 167	90.58 226	79.40 86	74.77 193	90.18 197	45.93 316	95.61 179	83.04 117	76.96 243	92.60 190

Anonymous202405211		77.96 227	75.33 247	85.87 94	93.73 53	64.52 180	94.85 48	85.36 362	62.52 344	76.11 175	90.18 197	29.43 398	97.29 83	68.51 245	77.24 241	95.81 50

test_vis1_n		71.63 311	70.73 307	74.31 359	69.63 417	47.29 407	86.91 321	72.11 414	63.21 337	75.18 187	90.17 199	20.40 421	85.76 386	84.59 100	74.42 259	89.87 247

balanced_conf03		89.08 15	88.84 19	89.81 6	93.66 54	75.15 5	90.61 245	93.43 93	84.06 21	86.20 59	90.17 199	72.42 35	96.98 108	93.09 26	95.92 10	97.29 7

BH-w/o		80.49 177	79.30 186	84.05 172	90.83 144	64.36 192	93.60 103	89.42 276	74.35 169	69.09 264	90.15 201	55.23 219	95.61 179	64.61 286	86.43 149	92.17 208

EI-MVSNet		78.97 205	78.22 200	81.25 254	85.33 278	62.73 245	89.53 275	93.21 100	72.39 214	72.14 228	90.13 202	60.99 145	94.72 216	67.73 254	72.49 274	86.29 304

CVMVSNet		74.04 287	74.27 262	73.33 365	85.33 278	43.94 419	89.53 275	88.39 318	54.33 392	70.37 250	90.13 202	49.17 287	84.05 396	61.83 307	79.36 217	91.99 212

XVG-OURS-SEG-HR		74.70 282	73.08 280	79.57 302	78.25 379	57.33 349	80.49 373	87.32 338	63.22 336	68.76 274	90.12 204	44.89 324	91.59 328	70.55 226	74.09 262	89.79 249

testing3-2		83.11 128	83.15 118	82.98 208	91.92 112	64.01 203	94.39 62	95.37 16	78.32 110	75.53 184	90.06 205	73.18 27	93.18 275	74.34 191	75.27 253	91.77 215

OPM-MVS		79.00 204	78.09 201	81.73 244	83.52 314	63.83 206	91.64 199	90.30 240	76.36 145	71.97 231	89.93 206	46.30 313	95.17 200	75.10 182	77.70 232	86.19 307
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PVSNet_Blended_VisFu		83.97 109	83.50 103	85.39 112	90.02 158	66.59 133	93.77 95	91.73 173	77.43 130	77.08 169	89.81 207	63.77 107	96.97 111	79.67 147	88.21 122	92.60 190

CDS-MVSNet		81.43 157	80.74 155	83.52 189	86.26 261	64.45 184	92.09 173	90.65 224	75.83 149	73.95 204	89.81 207	63.97 103	92.91 286	71.27 218	82.82 182	93.20 171
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
XVG-OURS		74.25 285	72.46 291	79.63 300	78.45 377	57.59 345	80.33 375	87.39 337	63.86 328	68.76 274	89.62 209	40.50 341	91.72 324	69.00 240	74.25 260	89.58 252

dmvs_re		76.93 244	75.36 246	81.61 247	87.78 224	60.71 295	80.00 381	87.99 331	79.42 85	69.02 267	89.47 210	46.77 305	94.32 233	63.38 294	74.45 258	89.81 248

guyue		81.23 161	80.57 162	83.21 205	86.64 251	61.85 264	92.52 158	92.78 119	78.69 105	74.92 190	89.42 211	50.07 274	95.35 193	80.79 138	79.31 219	92.42 196

UWE-MVS		80.81 171	81.01 152	80.20 282	89.33 174	57.05 351	91.91 184	94.71 38	75.67 150	75.01 189	89.37 212	63.13 123	91.44 335	67.19 260	82.80 184	92.12 210

GeoE		78.90 207	77.43 213	83.29 199	88.95 187	62.02 260	92.31 162	86.23 352	70.24 269	71.34 241	89.27 213	54.43 230	94.04 251	63.31 295	80.81 205	93.81 154

thisisatest0530		81.15 162	80.07 168	84.39 159	88.26 207	65.63 156	91.40 204	94.62 43	71.27 252	70.93 243	89.18 214	72.47 33	96.04 160	65.62 278	76.89 244	91.49 219

UA-Net		80.02 187	79.65 177	81.11 260	89.33 174	57.72 341	86.33 327	89.00 300	77.44 129	81.01 116	89.15 215	59.33 168	95.90 164	61.01 310	84.28 169	89.73 251

HQP_MVS		80.34 180	79.75 176	82.12 236	86.94 244	62.42 250	93.13 123	91.31 192	78.81 102	72.53 219	89.14 216	50.66 268	95.55 185	76.74 169	78.53 227	88.39 270

plane_prior4											89.14 216

UWE-MVS-28		76.83 248	77.60 210	74.51 355	84.58 296	50.34 389	88.22 300	94.60 45	74.46 166	66.66 304	88.98 218	62.53 131	85.50 390	57.55 328	80.80 206	87.69 278

thres200		79.66 192	78.33 197	83.66 187	92.54 91	65.82 153	93.06 125	96.31 3	74.90 163	73.30 208	88.66 219	59.67 163	95.61 179	47.84 368	78.67 225	89.56 254

BH-untuned		78.68 213	77.08 220	83.48 193	89.84 161	63.74 209	92.70 145	88.59 314	71.57 245	66.83 302	88.65 220	51.75 258	95.39 191	59.03 321	84.77 161	91.32 226

TAMVS		80.37 179	79.45 182	83.13 206	85.14 284	63.37 225	91.23 218	90.76 219	74.81 164	72.65 216	88.49 221	60.63 150	92.95 281	69.41 234	81.95 194	93.08 176

LPG-MVS_test		75.82 267	74.58 256	79.56 303	84.31 303	59.37 323	90.44 246	89.73 266	69.49 277	64.86 315	88.42 222	38.65 347	94.30 235	72.56 205	72.76 271	85.01 334

LGP-MVS_train				79.56 303	84.31 303	59.37 323		89.73 266	69.49 277	64.86 315	88.42 222	38.65 347	94.30 235	72.56 205	72.76 271	85.01 334

VPNet		78.82 209	77.53 212	82.70 215	84.52 297	66.44 135	93.93 83	92.23 142	80.46 65	72.60 217	88.38 224	49.18 286	93.13 276	72.47 207	63.97 342	88.55 267

FIs		79.47 197	79.41 183	79.67 299	85.95 268	59.40 322	91.68 197	93.94 68	78.06 114	68.96 270	88.28 225	66.61 68	91.77 323	66.20 272	74.99 254	87.82 276

CHOSEN 1792x2688		84.98 87	83.45 106	89.57 11	89.94 160	75.14 6	92.07 175	92.32 139	81.87 45	75.68 179	88.27 226	60.18 155	98.60 27	80.46 141	90.27 99	94.96 91

tfpn200view9		78.79 211	77.43 213	82.88 210	92.21 97	64.49 181	92.05 176	96.28 4	73.48 189	71.75 234	88.26 227	60.07 158	95.32 194	45.16 381	77.58 234	88.83 260

Fast-Effi-MVS+		81.14 163	80.01 170	84.51 155	90.24 154	65.86 151	94.12 72	89.15 288	73.81 182	75.37 186	88.26 227	57.26 190	94.53 228	66.97 263	84.92 159	93.15 172

thres400		78.68 213	77.43 213	82.43 222	92.21 97	64.49 181	92.05 176	96.28 4	73.48 189	71.75 234	88.26 227	60.07 158	95.32 194	45.16 381	77.58 234	87.48 281

nrg030		80.93 168	79.86 173	84.13 168	83.69 311	68.83 69	93.23 120	91.20 198	75.55 152	75.06 188	88.22 230	63.04 125	94.74 215	81.88 126	66.88 312	88.82 262

Syy-MVS		69.65 325	69.52 317	70.03 385	87.87 219	43.21 421	88.07 302	89.01 297	72.91 200	63.11 334	88.10 231	45.28 321	85.54 387	22.07 435	69.23 294	81.32 376

myMVS_eth3d		72.58 307	72.74 285	72.10 377	87.87 219	49.45 395	88.07 302	89.01 297	72.91 200	63.11 334	88.10 231	63.63 109	85.54 387	32.73 422	69.23 294	81.32 376

F-COLMAP		70.66 315	68.44 323	77.32 329	86.37 260	55.91 360	88.00 304	86.32 349	56.94 383	57.28 373	88.07 233	33.58 381	92.49 303	51.02 349	68.37 301	83.55 347

tttt0517		79.50 195	78.53 196	82.41 225	87.22 237	61.43 278	89.75 269	94.76 35	69.29 280	67.91 284	88.06 234	72.92 29	95.63 177	62.91 299	73.90 265	90.16 243

HY-MVS	76.49 5	84.28 100	83.36 112	87.02 55	92.22 96	67.74 99	84.65 334	94.50 48	79.15 93	82.23 103	87.93 235	66.88 65	96.94 114	80.53 140	82.20 190	96.39 33

thres100view900		78.37 219	77.01 222	82.46 221	91.89 115	63.21 231	91.19 222	96.33 1	72.28 217	70.45 249	87.89 236	60.31 153	95.32 194	45.16 381	77.58 234	88.83 260

thres600view7		78.00 225	76.66 227	82.03 241	91.93 111	63.69 215	91.30 214	96.33 1	72.43 212	70.46 248	87.89 236	60.31 153	94.92 209	42.64 393	76.64 245	87.48 281

dmvs_testset		65.55 356	66.45 332	62.86 403	79.87 355	22.35 449	76.55 395	71.74 416	77.42 131	55.85 376	87.77 238	51.39 262	80.69 416	31.51 428	65.92 319	85.55 326

test0.0.03 1		72.76 301	72.71 287	72.88 369	80.25 351	47.99 402	91.22 219	89.45 274	71.51 248	62.51 342	87.66 239	53.83 236	85.06 392	50.16 354	67.84 308	85.58 324

MVSMamba_PlusPlus		84.97 88	83.65 100	88.93 14	90.17 156	74.04 8	87.84 308	92.69 125	62.18 346	81.47 110	87.64 240	71.47 42	96.28 146	84.69 98	94.74 31	96.47 28

FC-MVSNet-test		77.99 226	78.08 202	77.70 322	84.89 290	55.51 363	90.27 254	93.75 77	76.87 134	66.80 303	87.59 241	65.71 79	90.23 348	62.89 300	73.94 263	87.37 284

TESTMET0.1,1		82.41 140	81.98 138	83.72 183	88.08 212	63.74 209	92.70 145	93.77 73	79.30 89	77.61 160	87.57 242	58.19 183	94.08 246	73.91 193	86.68 144	93.33 167

LS3D		69.17 328	66.40 333	77.50 325	91.92 112	56.12 358	85.12 331	80.37 392	46.96 412	56.50 375	87.51 243	37.25 362	93.71 265	32.52 424	79.40 216	82.68 365

Anonymous20240529		76.84 247	74.15 266	84.88 133	91.02 138	64.95 175	93.84 91	91.09 206	53.57 393	73.00 209	87.42 244	35.91 371	97.32 81	69.14 239	72.41 276	92.36 198

Test_1112_low_res		79.56 194	78.60 195	82.43 222	88.24 209	60.39 305	92.09 173	87.99 331	72.10 223	71.84 232	87.42 244	64.62 93	93.04 277	65.80 276	77.30 239	93.85 153

ACMP	71.68 10	75.58 272	74.23 263	79.62 301	84.97 289	59.64 318	90.80 234	89.07 295	70.39 267	62.95 337	87.30 246	38.28 351	93.87 261	72.89 198	71.45 282	85.36 330
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
WB-MVSnew		77.14 240	76.18 236	80.01 288	86.18 263	63.24 229	91.26 215	94.11 65	71.72 237	73.52 206	87.29 247	45.14 322	93.00 279	56.98 329	79.42 215	83.80 345

CHOSEN 280x420		77.35 237	76.95 224	78.55 314	87.07 241	62.68 246	69.71 414	82.95 384	68.80 287	71.48 239	87.27 248	66.03 74	84.00 398	76.47 172	82.81 183	88.95 259

SDMVSNet		80.26 181	78.88 192	84.40 158	89.25 178	67.63 103	85.35 330	93.02 110	76.77 139	70.84 244	87.12 249	47.95 298	96.09 155	85.04 93	74.55 255	89.48 255

sd_testset		77.08 242	75.37 245	82.20 232	89.25 178	62.11 259	82.06 360	89.09 293	76.77 139	70.84 244	87.12 249	41.43 337	95.01 204	67.23 259	74.55 255	89.48 255

RRT-MVS		82.61 138	81.16 145	86.96 57	91.10 137	68.75 71	87.70 311	92.20 146	76.97 133	72.68 214	87.10 251	51.30 264	96.41 141	83.56 112	87.84 126	95.74 52

mvsmamba		81.55 155	80.72 156	84.03 173	91.42 128	66.93 123	83.08 351	89.13 290	78.55 108	67.50 291	87.02 252	51.79 257	90.07 352	87.48 68	90.49 95	95.10 84

test-LLR		80.10 185	79.56 179	81.72 245	86.93 246	61.17 281	92.70 145	91.54 183	71.51 248	75.62 180	86.94 253	53.83 236	92.38 306	72.21 209	84.76 162	91.60 217

test-mter		79.96 188	79.38 185	81.72 245	86.93 246	61.17 281	92.70 145	91.54 183	73.85 180	75.62 180	86.94 253	49.84 278	92.38 306	72.21 209	84.76 162	91.60 217

testing3		70.38 319	70.83 304	69.03 389	85.82 272	43.93 420	90.72 239	90.56 227	68.06 295	60.24 351	86.82 255	64.83 90	84.12 394	26.33 430	64.10 339	79.04 397

UniMVSNet_NR-MVSNet		78.15 223	77.55 211	79.98 289	84.46 300	60.26 307	92.25 164	93.20 102	77.50 128	68.88 271	86.61 256	66.10 73	92.13 315	66.38 269	62.55 349	87.54 279

MVS_Test		84.16 106	83.20 115	87.05 54	91.56 124	69.82 46	89.99 265	92.05 153	77.77 121	82.84 97	86.57 257	63.93 104	96.09 155	74.91 186	89.18 111	95.25 79

tt0805		73.07 295	70.73 307	80.07 285	78.37 378	57.05 351	87.78 309	92.18 149	61.23 358	67.04 298	86.49 258	31.35 391	94.58 221	65.06 284	67.12 310	88.57 266

DU-MVS		76.86 245	75.84 240	79.91 292	82.96 320	60.26 307	91.26 215	91.54 183	76.46 144	68.88 271	86.35 259	56.16 208	92.13 315	66.38 269	62.55 349	87.35 285

NR-MVSNet		76.05 261	74.59 255	80.44 275	82.96 320	62.18 258	90.83 233	91.73 173	77.12 132	60.96 347	86.35 259	59.28 169	91.80 322	60.74 311	61.34 364	87.35 285

UGNet		79.87 190	78.68 193	83.45 194	89.96 159	61.51 274	92.13 170	90.79 218	76.83 137	78.85 148	86.33 261	38.16 353	96.17 151	67.93 252	87.17 134	92.67 187
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
TranMVSNet+NR-MVSNet		75.86 266	74.52 258	79.89 293	82.44 326	60.64 298	91.37 209	91.37 190	76.63 141	67.65 289	86.21 262	52.37 253	91.55 329	61.84 306	60.81 367	87.48 281

cascas		78.18 222	75.77 241	85.41 111	87.14 239	69.11 62	92.96 132	91.15 203	66.71 307	70.47 247	86.07 263	37.49 361	96.48 138	70.15 228	79.80 213	90.65 237

HyFIR lowres test		81.03 167	79.56 179	85.43 110	87.81 222	68.11 90	90.18 257	90.01 255	70.65 265	72.95 211	86.06 264	63.61 111	94.50 230	75.01 184	79.75 214	93.67 157

ACMM	69.62 13	74.34 283	72.73 286	79.17 308	84.25 305	57.87 339	90.36 251	89.93 257	63.17 338	65.64 310	86.04 265	37.79 359	94.10 244	65.89 274	71.52 281	85.55 326
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Elysia		76.45 254	74.17 264	83.30 197	80.43 346	64.12 199	89.58 270	90.83 215	61.78 354	72.53 219	85.92 266	34.30 378	94.81 211	68.10 247	84.01 174	90.97 233

StellarMVS		76.45 254	74.17 264	83.30 197	80.43 346	64.12 199	89.58 270	90.83 215	61.78 354	72.53 219	85.92 266	34.30 378	94.81 211	68.10 247	84.01 174	90.97 233

XXY-MVS		77.94 228	76.44 230	82.43 222	82.60 324	64.44 185	92.01 178	91.83 169	73.59 188	70.00 256	85.82 268	54.43 230	94.76 213	69.63 231	68.02 305	88.10 274

IB-MVS	77.80 4	82.18 143	80.46 165	87.35 45	89.14 183	70.28 36	95.59 26	95.17 24	78.85 100	70.19 253	85.82 268	70.66 44	97.67 56	72.19 211	66.52 315	94.09 138
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
MVSTER		82.47 139	82.05 135	83.74 179	92.68 87	69.01 65	91.90 185	93.21 100	79.83 76	72.14 228	85.71 270	74.72 17	94.72 216	75.72 177	72.49 274	87.50 280

mamv4		65.18 358	67.43 328	58.44 407	77.88 385	49.36 398	69.40 415	70.99 420	48.31 410	57.78 370	85.53 271	59.01 174	51.88 445	73.67 194	64.32 336	74.07 415

LuminaMVS		78.14 224	76.66 227	82.60 219	80.82 340	64.64 178	89.33 279	90.45 228	68.25 294	74.73 194	85.51 272	41.15 338	94.14 242	78.96 156	80.69 207	89.04 258

WR-MVS		76.76 250	75.74 242	79.82 295	84.60 294	62.27 256	92.60 152	92.51 135	76.06 146	67.87 287	85.34 273	56.76 199	90.24 347	62.20 304	63.69 344	86.94 293

DP-MVS		69.90 323	66.48 331	80.14 283	95.36 28	62.93 238	89.56 272	76.11 399	50.27 404	57.69 371	85.23 274	39.68 343	95.73 171	33.35 417	71.05 285	81.78 374

PVSNet_BlendedMVS		83.38 122	83.43 107	83.22 203	93.76 50	67.53 106	94.06 73	93.61 82	79.13 94	81.00 117	85.14 275	63.19 119	97.29 83	87.08 75	73.91 264	84.83 336

ab-mvs		80.18 183	78.31 198	85.80 98	88.44 199	65.49 162	83.00 354	92.67 126	71.82 233	77.36 163	85.01 276	54.50 226	96.59 129	76.35 174	75.63 251	95.32 71

VPA-MVSNet		79.03 203	78.00 203	82.11 239	85.95 268	64.48 183	93.22 121	94.66 41	75.05 161	74.04 203	84.95 277	52.17 254	93.52 269	74.90 187	67.04 311	88.32 272

Fast-Effi-MVS+-dtu		75.04 277	73.37 277	80.07 285	80.86 338	59.52 321	91.20 221	85.38 361	71.90 227	65.20 313	84.84 278	41.46 336	92.97 280	66.50 268	72.96 270	87.73 277

UniMVSNet (Re)		77.58 234	76.78 225	79.98 289	84.11 306	60.80 288	91.76 193	93.17 104	76.56 143	69.93 259	84.78 279	63.32 118	92.36 308	64.89 285	62.51 351	86.78 295

mvs_anonymous		81.36 159	79.99 171	85.46 109	90.39 152	68.40 79	86.88 323	90.61 225	74.41 167	70.31 252	84.67 280	63.79 106	92.32 311	73.13 196	85.70 154	95.67 53

RPSCF		64.24 363	61.98 365	71.01 383	76.10 395	45.00 416	75.83 400	75.94 400	46.94 413	58.96 360	84.59 281	31.40 390	82.00 412	47.76 370	60.33 373	86.04 312

PS-MVSNAJss		77.26 238	76.31 233	80.13 284	80.64 344	59.16 327	90.63 244	91.06 210	72.80 203	68.58 277	84.57 282	53.55 240	93.96 256	72.97 197	71.96 278	87.27 288

test_fmvs2		65.78 355	64.84 344	68.60 391	66.54 423	41.71 423	83.27 347	69.81 422	54.38 391	67.91 284	84.54 283	15.35 428	81.22 415	75.65 178	66.16 316	82.88 358

UniMVSNet_ETH3D		72.74 302	70.53 309	79.36 305	78.62 375	56.64 355	85.01 332	89.20 284	63.77 329	64.84 317	84.44 284	34.05 380	91.86 321	63.94 290	70.89 286	89.57 253

MS-PatchMatch		77.90 230	76.50 229	82.12 236	85.99 267	69.95 42	91.75 195	92.70 122	73.97 177	62.58 341	84.44 284	41.11 339	95.78 167	63.76 292	92.17 66	80.62 384

WBMVS		81.67 152	80.98 153	83.72 183	93.07 74	69.40 54	94.33 63	93.05 109	76.84 136	72.05 230	84.14 286	74.49 19	93.88 260	72.76 202	68.09 303	87.88 275

MSDG		69.54 326	65.73 338	80.96 266	85.11 286	63.71 213	84.19 338	83.28 383	56.95 382	54.50 380	84.03 287	31.50 389	96.03 161	42.87 391	69.13 296	83.14 357

GA-MVS		78.33 221	76.23 234	84.65 147	83.65 312	66.30 139	91.44 201	90.14 248	76.01 147	70.32 251	84.02 288	42.50 332	94.72 216	70.98 220	77.00 242	92.94 181

miper_enhance_ethall		78.86 208	77.97 204	81.54 249	88.00 216	65.17 168	91.41 202	89.15 288	75.19 159	68.79 273	83.98 289	67.17 63	92.82 288	72.73 203	65.30 322	86.62 301

pmmvs4		73.92 289	71.81 298	80.25 281	79.17 364	65.24 166	87.43 315	87.26 341	67.64 300	63.46 331	83.91 290	48.96 290	91.53 333	62.94 298	65.49 321	83.96 342

pmmvs5		73.35 293	71.52 300	78.86 312	78.64 374	60.61 299	91.08 225	86.90 343	67.69 297	63.32 332	83.64 291	44.33 326	90.53 341	62.04 305	66.02 317	85.46 328

ITE_SJBPF				70.43 384	74.44 401	47.06 409		77.32 397	60.16 365	54.04 383	83.53 292	23.30 414	84.01 397	43.07 388	61.58 363	80.21 390

jajsoiax		73.05 296	71.51 301	77.67 323	77.46 388	54.83 367	88.81 291	90.04 253	69.13 284	62.85 339	83.51 293	31.16 392	92.75 292	70.83 221	69.80 287	85.43 329

testgi		64.48 362	62.87 360	69.31 388	71.24 409	40.62 426	85.49 329	79.92 393	65.36 317	54.18 382	83.49 294	23.74 412	84.55 393	41.60 395	60.79 368	82.77 360

v2v482		77.42 236	75.65 243	82.73 213	80.38 348	67.13 117	91.85 188	90.23 245	75.09 160	69.37 261	83.39 295	53.79 238	94.44 231	71.77 213	65.00 329	86.63 300

SSC-MVS3.2		74.92 280	73.32 278	79.74 298	86.53 255	60.31 306	89.03 289	92.70 122	78.61 107	68.98 269	83.34 296	41.93 335	92.23 313	52.77 346	65.97 318	86.69 296

mvs_tets		72.71 303	71.11 302	77.52 324	77.41 389	54.52 369	88.45 297	89.76 262	68.76 289	62.70 340	83.26 297	29.49 397	92.71 293	70.51 227	69.62 289	85.34 331

FMVSNet3		77.73 231	76.04 237	82.80 211	91.20 136	68.99 66	91.87 186	91.99 158	73.35 191	67.04 298	83.19 298	56.62 203	92.14 314	59.80 318	69.34 291	87.28 287

FA-MVS(test-final)		79.12 202	77.23 219	84.81 138	90.54 147	63.98 204	81.35 368	91.71 175	71.09 256	74.85 192	82.94 299	52.85 247	97.05 99	67.97 250	81.73 197	93.41 163

MVP-Stereo		77.12 241	76.23 234	79.79 296	81.72 332	66.34 138	89.29 280	90.88 214	70.56 266	62.01 344	82.88 300	49.34 283	94.13 243	65.55 280	93.80 43	78.88 399
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchMatch-RL		72.06 308	69.98 311	78.28 317	89.51 170	55.70 362	83.49 343	83.39 382	61.24 357	63.72 329	82.76 301	34.77 375	93.03 278	53.37 344	77.59 233	86.12 311

CP-MVSNet		70.50 317	69.91 314	72.26 374	80.71 342	51.00 386	87.23 318	90.30 240	67.84 296	59.64 354	82.69 302	50.23 273	82.30 410	51.28 348	59.28 375	83.46 351

cl22		77.94 228	76.78 225	81.42 251	87.57 227	64.93 176	90.67 240	88.86 304	72.45 211	67.63 290	82.68 303	64.07 100	92.91 286	71.79 212	65.30 322	86.44 302

miper_ehance_all_eth		77.60 233	76.44 230	81.09 264	85.70 275	64.41 188	90.65 241	88.64 313	72.31 215	67.37 296	82.52 304	64.77 92	92.64 299	70.67 224	65.30 322	86.24 306

PEN-MVS		69.46 327	68.56 321	72.17 376	79.27 362	49.71 393	86.90 322	89.24 282	67.24 305	59.08 359	82.51 305	47.23 303	83.54 401	48.42 363	57.12 381	83.25 354

reproduce_monomvs		79.49 196	79.11 190	80.64 272	92.91 78	61.47 277	91.17 223	93.28 98	83.09 30	64.04 325	82.38 306	66.19 71	94.57 223	81.19 135	57.71 380	85.88 319

PS-CasMVS		69.86 324	69.13 319	72.07 378	80.35 349	50.57 388	87.02 320	89.75 263	67.27 302	59.19 358	82.28 307	46.58 308	82.24 411	50.69 351	59.02 376	83.39 353

FMVSNet2		76.07 258	74.01 269	82.26 230	88.85 188	67.66 101	91.33 212	91.61 181	70.84 260	65.98 307	82.25 308	48.03 294	92.00 319	58.46 323	68.73 299	87.10 290

DTE-MVSNet		68.46 336	67.33 330	71.87 380	77.94 383	49.00 399	86.16 328	88.58 315	66.36 310	58.19 364	82.21 309	46.36 309	83.87 399	44.97 384	55.17 388	82.73 361

CMPMVS	48.56 21	66.77 349	64.41 351	73.84 362	70.65 414	50.31 390	77.79 392	85.73 359	45.54 417	44.76 418	82.14 310	35.40 373	90.14 350	63.18 297	74.54 257	81.07 379
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_djsdf		73.76 292	72.56 289	77.39 328	77.00 391	53.93 371	89.07 286	90.69 220	65.80 313	63.92 326	82.03 311	43.14 331	92.67 296	72.83 199	68.53 300	85.57 325

VortexMVS		77.62 232	76.44 230	81.13 258	88.58 194	63.73 211	91.24 217	91.30 196	77.81 119	65.76 308	81.97 312	49.69 280	93.72 264	76.40 173	65.26 325	85.94 317

v1144		76.73 251	74.88 251	82.27 228	80.23 352	66.60 132	91.68 197	90.21 247	73.69 185	69.06 266	81.89 313	52.73 250	94.40 232	69.21 237	65.23 326	85.80 320

V42		76.46 253	74.55 257	82.19 233	79.14 366	67.82 97	90.26 255	89.42 276	73.75 183	68.63 276	81.89 313	51.31 263	94.09 245	71.69 215	64.84 330	84.66 337

pm-mvs1		72.89 299	71.09 303	78.26 318	79.10 367	57.62 343	90.80 234	89.30 280	67.66 298	62.91 338	81.78 315	49.11 289	92.95 281	60.29 315	58.89 377	84.22 341

IterMVS-LS		76.49 252	75.18 249	80.43 276	84.49 299	62.74 244	90.64 242	88.80 306	72.40 213	65.16 314	81.72 316	60.98 146	92.27 312	67.74 253	64.65 334	86.29 304
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
eth_miper_zixun_eth		75.96 265	74.40 260	80.66 271	84.66 293	63.02 235	89.28 281	88.27 324	71.88 229	65.73 309	81.65 317	59.45 165	92.81 289	68.13 246	60.53 369	86.14 308

c3_l		76.83 248	75.47 244	80.93 268	85.02 288	64.18 198	90.39 249	88.11 328	71.66 238	66.65 305	81.64 318	63.58 114	92.56 300	69.31 236	62.86 346	86.04 312

DIV-MVS_self_test		76.07 258	74.67 252	80.28 279	85.14 284	61.75 269	90.12 258	88.73 308	71.16 253	65.42 312	81.60 319	61.15 143	92.94 285	66.54 266	62.16 355	86.14 308

cl____		76.07 258	74.67 252	80.28 279	85.15 283	61.76 268	90.12 258	88.73 308	71.16 253	65.43 311	81.57 320	61.15 143	92.95 281	66.54 266	62.17 353	86.13 310

CostFormer		82.33 141	81.15 146	85.86 95	89.01 186	68.46 78	82.39 359	93.01 111	75.59 151	80.25 127	81.57 320	72.03 39	94.96 206	79.06 154	77.48 237	94.16 134

Effi-MVS+-dtu		76.14 257	75.28 248	78.72 313	83.22 317	55.17 365	89.87 266	87.78 335	75.42 154	67.98 282	81.43 322	45.08 323	92.52 302	75.08 183	71.63 279	88.48 268

v1192		75.98 263	73.92 270	82.15 234	79.73 356	66.24 141	91.22 219	89.75 263	72.67 205	68.49 278	81.42 323	49.86 277	94.27 237	67.08 261	65.02 328	85.95 315

COLMAP_ROB	57.96 20	62.98 370	59.65 372	72.98 368	81.44 335	53.00 375	83.75 341	75.53 404	48.34 409	48.81 407	81.40 324	24.14 410	90.30 343	32.95 419	60.52 370	75.65 413
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v144192		76.05 261	74.03 268	82.12 236	79.50 360	66.55 134	91.39 206	89.71 269	72.30 216	68.17 280	81.33 325	51.75 258	94.03 253	67.94 251	64.19 337	85.77 321

AllTest		61.66 373	58.06 377	72.46 372	79.57 357	51.42 383	80.17 378	68.61 424	51.25 400	45.88 412	81.23 326	19.86 424	86.58 383	38.98 404	57.01 383	79.39 393

TestCases				72.46 372	79.57 357	51.42 383		68.61 424	51.25 400	45.88 412	81.23 326	19.86 424	86.58 383	38.98 404	57.01 383	79.39 393

v1921920		75.63 271	73.49 276	82.06 240	79.38 361	66.35 137	91.07 227	89.48 272	71.98 224	67.99 281	81.22 328	49.16 288	93.90 259	66.56 265	64.56 335	85.92 318

v1240		75.21 276	72.98 282	81.88 242	79.20 363	66.00 145	90.75 236	89.11 292	71.63 243	67.41 294	81.22 328	47.36 302	93.87 261	65.46 281	64.72 333	85.77 321

XVG-ACMP-BASELINE		68.04 340	65.53 341	75.56 344	74.06 403	52.37 376	78.43 387	85.88 356	62.03 349	58.91 361	81.21 330	20.38 422	91.15 337	60.69 312	68.18 302	83.16 356

EU-MVSNet		64.01 364	63.01 358	67.02 397	74.40 402	38.86 432	83.27 347	86.19 353	45.11 418	54.27 381	81.15 331	36.91 368	80.01 418	48.79 362	57.02 382	82.19 371

ACMH+	65.35 16	67.65 343	64.55 348	76.96 336	84.59 295	57.10 350	88.08 301	80.79 389	58.59 374	53.00 388	81.09 332	26.63 406	92.95 281	46.51 374	61.69 362	80.82 381

v148		76.19 256	74.47 259	81.36 252	80.05 354	64.44 185	91.75 195	90.23 245	73.68 186	67.13 297	80.84 333	55.92 213	93.86 263	68.95 241	61.73 360	85.76 323

WR-MVS_H		70.59 316	69.94 313	72.53 371	81.03 337	51.43 382	87.35 316	92.03 157	67.38 301	60.23 352	80.70 334	55.84 214	83.45 402	46.33 376	58.58 379	82.72 362

Baseline_NR-MVSNet		73.99 288	72.83 283	77.48 326	80.78 341	59.29 326	91.79 190	84.55 370	68.85 286	68.99 268	80.70 334	56.16 208	92.04 318	62.67 301	60.98 366	81.11 378

Anonymous20231211		73.08 294	70.39 310	81.13 258	90.62 146	63.33 226	91.40 204	90.06 252	51.84 398	64.46 322	80.67 336	36.49 369	94.07 247	63.83 291	64.17 338	85.98 314

PVSNet_0	68.08 15	71.81 309	68.32 325	82.27 228	84.68 291	62.31 255	88.68 293	90.31 239	75.84 148	57.93 369	80.65 337	37.85 358	94.19 240	69.94 229	29.05 437	90.31 242

tpm2		79.80 191	77.95 205	85.34 116	88.28 206	68.26 84	81.56 365	91.42 189	70.11 270	77.59 161	80.50 338	67.40 62	94.26 239	67.34 257	77.35 238	93.51 161

TransMVSNet (Re)		70.07 321	67.66 327	77.31 330	80.62 345	59.13 328	91.78 192	84.94 366	65.97 312	60.08 353	80.44 339	50.78 267	91.87 320	48.84 361	45.46 410	80.94 380

USDC		67.43 347	64.51 349	76.19 341	77.94 383	55.29 364	78.38 388	85.00 365	73.17 193	48.36 408	80.37 340	21.23 419	92.48 304	52.15 347	64.02 341	80.81 382

LTVRE_ROB	59.60 19	66.27 351	63.54 355	74.45 356	84.00 308	51.55 381	67.08 423	83.53 379	58.78 372	54.94 379	80.31 341	34.54 376	93.23 274	40.64 400	68.03 304	78.58 403
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
v8		75.35 273	73.26 279	81.61 247	80.67 343	66.82 125	89.54 274	89.27 281	71.65 239	63.30 333	80.30 342	54.99 223	94.06 248	67.33 258	62.33 352	83.94 343

GBi-Net		75.65 269	73.83 271	81.10 261	88.85 188	65.11 170	90.01 262	90.32 236	70.84 260	67.04 298	80.25 343	48.03 294	91.54 330	59.80 318	69.34 291	86.64 297

test1		75.65 269	73.83 271	81.10 261	88.85 188	65.11 170	90.01 262	90.32 236	70.84 260	67.04 298	80.25 343	48.03 294	91.54 330	59.80 318	69.34 291	86.64 297

FMVSNet1		72.71 303	69.91 314	81.10 261	83.60 313	65.11 170	90.01 262	90.32 236	63.92 327	63.56 330	80.25 343	36.35 370	91.54 330	54.46 338	66.75 313	86.64 297

LCM-MVSNet-Re		72.93 298	71.84 297	76.18 342	88.49 196	48.02 401	80.07 380	70.17 421	73.96 178	52.25 391	80.09 346	49.98 275	88.24 368	67.35 256	84.23 170	92.28 202

v10		74.77 281	72.54 290	81.46 250	80.33 350	66.71 129	89.15 285	89.08 294	70.94 258	63.08 336	79.86 347	52.52 251	94.04 251	65.70 277	62.17 353	83.64 346

FE-MVS		75.97 264	73.02 281	84.82 135	89.78 162	65.56 158	77.44 393	91.07 209	64.55 321	72.66 215	79.85 348	46.05 315	96.69 127	54.97 336	80.82 204	92.21 207

anonymousdsp		71.14 314	69.37 318	76.45 339	72.95 406	54.71 368	84.19 338	88.88 302	61.92 351	62.15 343	79.77 349	38.14 354	91.44 335	68.90 242	67.45 309	83.21 355

tpm		78.58 216	77.03 221	83.22 203	85.94 270	64.56 179	83.21 350	91.14 204	78.31 111	73.67 205	79.68 350	64.01 102	92.09 317	66.07 273	71.26 284	93.03 178

OurMVSNet-221017-0		64.68 360	62.17 364	72.21 375	76.08 396	47.35 405	80.67 372	81.02 388	56.19 386	51.60 394	79.66 351	27.05 405	88.56 363	53.60 343	53.63 393	80.71 383

tpmrst		80.57 174	79.14 189	84.84 134	90.10 157	68.28 83	81.70 363	89.72 268	77.63 126	75.96 176	79.54 352	64.94 88	92.71 293	75.43 179	77.28 240	93.55 160

ACMH	63.93 17	68.62 333	64.81 345	80.03 287	85.22 282	63.25 228	87.72 310	84.66 368	60.83 360	51.57 395	79.43 353	27.29 404	94.96 206	41.76 394	64.84 330	81.88 372
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MonoMVSNet		76.99 243	75.08 250	82.73 213	83.32 316	63.24 229	86.47 326	86.37 348	79.08 96	66.31 306	79.30 354	49.80 279	91.72 324	79.37 149	65.70 320	93.23 169

IterMVS-SCA-FT		71.55 312	69.97 312	76.32 340	81.48 334	60.67 297	87.64 313	85.99 355	66.17 311	59.50 355	78.88 355	45.53 318	83.65 400	62.58 302	61.93 356	84.63 340

IterMVS		72.65 306	70.83 304	78.09 320	82.17 328	62.96 237	87.64 313	86.28 350	71.56 246	60.44 350	78.85 356	45.42 320	86.66 382	63.30 296	61.83 357	84.65 338
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tfpnnormal		70.10 320	67.36 329	78.32 316	83.45 315	60.97 286	88.85 290	92.77 120	64.85 320	60.83 348	78.53 357	43.52 329	93.48 270	31.73 425	61.70 361	80.52 385

D2MVS		73.80 290	72.02 295	79.15 310	79.15 365	62.97 236	88.58 295	90.07 250	72.94 198	59.22 357	78.30 358	42.31 334	92.70 295	65.59 279	72.00 277	81.79 373

v7n		71.31 313	68.65 320	79.28 306	76.40 393	60.77 290	86.71 324	89.45 274	64.17 326	58.77 362	78.24 359	44.59 325	93.54 268	57.76 325	61.75 359	83.52 349

miper_lstm_enhance		73.05 296	71.73 299	77.03 333	83.80 309	58.32 336	81.76 361	88.88 302	69.80 275	61.01 346	78.23 360	57.19 191	87.51 378	65.34 282	59.53 374	85.27 333

EPMVS		78.49 218	75.98 238	86.02 89	91.21 135	69.68 52	80.23 377	91.20 198	75.25 158	72.48 223	78.11 361	54.65 225	93.69 266	57.66 327	83.04 180	94.69 105

pmmvs6		67.57 344	64.76 346	76.00 343	72.82 408	53.37 373	88.71 292	86.78 347	53.19 394	57.58 372	78.03 362	35.33 374	92.41 305	55.56 334	54.88 390	82.21 370

OpenMVS_ROB	61.12 18	66.39 350	62.92 359	76.80 338	76.51 392	57.77 340	89.22 282	83.41 381	55.48 389	53.86 384	77.84 363	26.28 407	93.95 257	34.90 414	68.76 298	78.68 402

ttmdpeth		53.34 392	49.96 395	63.45 402	62.07 432	40.04 427	72.06 407	65.64 429	42.54 427	51.88 392	77.79 364	13.94 434	76.48 421	32.93 420	30.82 436	73.84 416

EG-PatchMatch MVS		68.55 334	65.41 342	77.96 321	78.69 373	62.93 238	89.86 267	89.17 286	60.55 361	50.27 400	77.73 365	22.60 417	94.06 248	47.18 372	72.65 273	76.88 410

SixPastTwentyTwo		64.92 359	61.78 366	74.34 358	78.74 372	49.76 392	83.42 346	79.51 395	62.86 340	50.27 400	77.35 366	30.92 394	90.49 342	45.89 378	47.06 405	82.78 359

test20.03		63.83 365	62.65 361	67.38 396	70.58 415	39.94 428	86.57 325	84.17 372	63.29 335	51.86 393	77.30 367	37.09 366	82.47 408	38.87 406	54.13 392	79.73 391

Anonymous20231206		67.53 345	65.78 337	72.79 370	74.95 399	47.59 404	88.23 299	87.32 338	61.75 356	58.07 366	77.29 368	37.79 359	87.29 380	42.91 389	63.71 343	83.48 350

test_0402		64.54 361	61.09 367	74.92 352	84.10 307	60.75 292	87.95 305	79.71 394	52.03 396	52.41 390	77.20 369	32.21 387	91.64 326	23.14 433	61.03 365	72.36 421

dp		75.01 278	72.09 294	83.76 178	89.28 177	66.22 142	79.96 383	89.75 263	71.16 253	67.80 288	77.19 370	51.81 256	92.54 301	50.39 352	71.44 283	92.51 195

SCA		75.82 267	72.76 284	85.01 129	86.63 252	70.08 38	81.06 370	89.19 285	71.60 244	70.01 255	77.09 371	45.53 318	90.25 344	60.43 313	73.27 267	94.68 106

Patchmatch-test		65.86 353	60.94 368	80.62 274	83.75 310	58.83 330	58.91 434	75.26 405	44.50 420	50.95 399	77.09 371	58.81 176	87.90 370	35.13 413	64.03 340	95.12 83

PatchmatchNet		77.46 235	74.63 254	85.96 91	89.55 169	70.35 35	79.97 382	89.55 271	72.23 218	70.94 242	76.91 373	57.03 193	92.79 291	54.27 339	81.17 200	94.74 103
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CL-MVSNet_self_test		69.92 322	68.09 326	75.41 345	73.25 405	55.90 361	90.05 261	89.90 258	69.96 272	61.96 345	76.54 374	51.05 266	87.64 375	49.51 358	50.59 400	82.70 364

KD-MVS_2432*1600		69.03 330	66.37 334	77.01 334	85.56 276	61.06 284	81.44 366	90.25 243	67.27 302	58.00 367	76.53 375	54.49 227	87.63 376	48.04 365	35.77 428	82.34 368

miper_refine_blended		69.03 330	66.37 334	77.01 334	85.56 276	61.06 284	81.44 366	90.25 243	67.27 302	58.00 367	76.53 375	54.49 227	87.63 376	48.04 365	35.77 428	82.34 368

tpm cat1		75.30 274	72.21 293	84.58 152	88.52 195	67.77 98	78.16 391	88.02 330	61.88 352	68.45 279	76.37 377	60.65 149	94.03 253	53.77 342	74.11 261	91.93 213

TDRefinement		55.28 389	51.58 393	66.39 398	59.53 435	46.15 413	76.23 397	72.80 411	44.60 419	42.49 424	76.28 378	15.29 429	82.39 409	33.20 418	43.75 412	70.62 423

our_test_3		68.29 338	64.69 347	79.11 311	78.92 368	64.85 177	88.40 298	85.06 364	60.32 364	52.68 389	76.12 379	40.81 340	89.80 356	44.25 386	55.65 386	82.67 366

ppachtmachnet_test		67.72 342	63.70 354	79.77 297	78.92 368	66.04 144	88.68 293	82.90 385	60.11 366	55.45 377	75.96 380	39.19 344	90.55 340	39.53 402	52.55 396	82.71 363

MDTV_nov1_ep13			72.61 288		89.06 184	68.48 77	80.33 375	90.11 249	71.84 232	71.81 233	75.92 381	53.01 246	93.92 258	48.04 365	73.38 266

TinyColmap		60.32 380	56.42 387	72.00 379	78.78 371	53.18 374	78.36 389	75.64 402	52.30 395	41.59 426	75.82 382	14.76 431	88.35 367	35.84 410	54.71 391	74.46 414

LF4IMVS		54.01 391	52.12 392	59.69 406	62.41 430	39.91 430	68.59 417	68.28 426	42.96 426	44.55 420	75.18 383	14.09 433	68.39 432	41.36 397	51.68 397	70.78 422

tpmvs		72.88 300	69.76 316	82.22 231	90.98 139	67.05 119	78.22 390	88.30 322	63.10 339	64.35 324	74.98 384	55.09 222	94.27 237	43.25 387	69.57 290	85.34 331

MVStest1		51.35 393	46.89 397	64.74 399	65.06 426	51.10 385	67.33 422	72.58 412	30.20 435	35.30 430	74.82 385	27.70 402	69.89 430	24.44 432	24.57 439	73.22 417

MIMVSNet		71.64 310	68.44 323	81.23 255	81.97 331	64.44 185	73.05 405	88.80 306	69.67 276	64.59 318	74.79 386	32.79 383	87.82 372	53.99 340	76.35 247	91.42 221

UnsupCasMVSNet_eth		65.79 354	63.10 357	73.88 361	70.71 413	50.29 391	81.09 369	89.88 259	72.58 207	49.25 405	74.77 387	32.57 385	87.43 379	55.96 333	41.04 418	83.90 344

lessismore_v0				73.72 363	72.93 407	47.83 403		61.72 434		45.86 414	73.76 388	28.63 401	89.81 354	47.75 371	31.37 433	83.53 348

FMVSNet5		68.04 340	65.66 340	75.18 349	84.43 301	57.89 338	83.54 342	86.26 351	61.83 353	53.64 386	73.30 389	37.15 365	85.08 391	48.99 360	61.77 358	82.56 367

sc_t1		63.81 366	59.39 374	77.10 332	77.62 386	56.03 359	84.32 337	73.56 410	46.66 415	58.22 363	73.06 390	23.28 415	90.62 339	50.93 350	46.84 406	84.64 339

mvs5depth		61.03 377	57.65 380	71.18 381	67.16 422	47.04 410	72.74 406	77.49 396	57.47 379	60.52 349	72.53 391	22.84 416	88.38 366	49.15 359	38.94 422	78.11 407

pmmvs-eth3d		65.53 357	62.32 363	75.19 348	69.39 418	59.59 319	82.80 355	83.43 380	62.52 344	51.30 397	72.49 392	32.86 382	87.16 381	55.32 335	50.73 399	78.83 400

MDA-MVSNet-bldmvs		61.54 375	57.70 379	73.05 367	79.53 359	57.00 354	83.08 351	81.23 387	57.57 376	34.91 432	72.45 393	32.79 383	86.26 385	35.81 411	41.95 416	75.89 412

CR-MVSNet		73.79 291	70.82 306	82.70 215	83.15 318	67.96 93	70.25 411	84.00 375	73.67 187	69.97 257	72.41 394	57.82 186	89.48 357	52.99 345	73.13 268	90.64 238

Patchmtry		67.53 345	63.93 353	78.34 315	82.12 329	64.38 189	68.72 416	84.00 375	48.23 411	59.24 356	72.41 394	57.82 186	89.27 358	46.10 377	56.68 385	81.36 375

K. test v3		63.09 369	59.61 373	73.53 364	76.26 394	49.38 397	83.27 347	77.15 398	64.35 323	47.77 410	72.32 396	28.73 399	87.79 373	49.93 356	36.69 425	83.41 352

PM-MVS		59.40 383	56.59 385	67.84 392	63.63 427	41.86 422	76.76 394	63.22 432	59.01 371	51.07 398	72.27 397	11.72 435	83.25 404	61.34 308	50.28 401	78.39 405

MIMVSNet1		60.16 382	57.33 382	68.67 390	69.71 416	44.13 418	78.92 385	84.21 371	55.05 390	44.63 419	71.85 398	23.91 411	81.54 414	32.63 423	55.03 389	80.35 386

DSMNet-mixed		56.78 387	54.44 391	63.79 401	63.21 428	29.44 444	64.43 426	64.10 431	42.12 428	51.32 396	71.60 399	31.76 388	75.04 423	36.23 409	65.20 327	86.87 294

MDA-MVSNet_test_wron		63.78 367	60.16 370	74.64 353	78.15 381	60.41 303	83.49 343	84.03 373	56.17 388	39.17 428	71.59 400	37.22 363	83.24 405	42.87 391	48.73 402	80.26 388

YYNet1		63.76 368	60.14 371	74.62 354	78.06 382	60.19 310	83.46 345	83.99 377	56.18 387	39.25 427	71.56 401	37.18 364	83.34 403	42.90 390	48.70 403	80.32 387

test_fmvs3		56.82 386	54.86 390	62.69 405	53.59 438	35.47 435	75.87 399	65.64 429	43.91 422	55.10 378	71.43 402	6.91 443	74.40 425	68.64 244	52.63 394	78.20 406

Anonymous20240521		62.09 371	59.08 375	71.10 382	67.19 421	48.72 400	83.91 340	85.23 363	50.38 403	47.84 409	71.22 403	20.74 420	85.51 389	46.47 375	58.75 378	79.06 396

ADS-MVSNet2		66.90 348	63.44 356	77.26 331	88.06 213	60.70 296	68.01 419	75.56 403	57.57 376	64.48 320	69.87 404	38.68 345	84.10 395	40.87 398	67.89 306	86.97 291

ADS-MVSNet		68.54 335	64.38 352	81.03 265	88.06 213	66.90 124	68.01 419	84.02 374	57.57 376	64.48 320	69.87 404	38.68 345	89.21 359	40.87 398	67.89 306	86.97 291

kuosan		60.86 379	60.24 369	62.71 404	81.57 333	46.43 412	75.70 401	85.88 356	57.98 375	48.95 406	69.53 406	58.42 179	76.53 420	28.25 429	35.87 427	65.15 428

N_pmnet		50.55 394	49.11 396	54.88 413	77.17 390	4.02 457	84.36 335	2.00 455	48.59 407	45.86 414	68.82 407	32.22 386	82.80 407	31.58 426	51.38 398	77.81 408

mmtdpeth		68.33 337	66.37 334	74.21 360	82.81 323	51.73 379	84.34 336	80.42 391	67.01 306	71.56 237	68.58 408	30.52 395	92.35 309	75.89 176	36.21 426	78.56 404

KD-MVS_self_test		60.87 378	58.60 376	67.68 394	66.13 424	39.93 429	75.63 402	84.70 367	57.32 380	49.57 403	68.45 409	29.55 396	82.87 406	48.09 364	47.94 404	80.25 389

tt0320		61.85 372	57.45 381	75.03 350	77.49 387	57.60 344	82.74 356	73.65 409	43.65 424	53.65 385	68.18 410	25.47 408	88.66 360	45.56 380	46.68 407	78.81 401

mvsany_test3		48.86 396	46.35 399	56.41 409	46.00 444	31.67 440	62.26 428	47.25 445	43.71 423	45.54 416	68.15 411	10.84 436	64.44 441	57.95 324	35.44 430	73.13 418

tt0320-xc		61.51 376	56.89 384	75.37 346	78.50 376	58.61 333	82.61 357	71.27 419	44.31 421	53.17 387	68.03 412	23.38 413	88.46 365	47.77 369	43.00 415	79.03 398

patchmatchnet-post											67.62 413	57.62 188	90.25 344

ambc				69.61 386	61.38 433	41.35 424	49.07 440	85.86 358		50.18 402	66.40 414	10.16 437	88.14 369	45.73 379	44.20 411	79.32 395

new-patchmatchnet		59.30 384	56.48 386	67.79 393	65.86 425	44.19 417	82.47 358	81.77 386	59.94 367	43.65 422	66.20 415	27.67 403	81.68 413	39.34 403	41.40 417	77.50 409

PatchT		69.11 329	65.37 343	80.32 277	82.07 330	63.68 216	67.96 421	87.62 336	50.86 402	69.37 261	65.18 416	57.09 192	88.53 364	41.59 396	66.60 314	88.74 263

RPMNet		70.42 318	65.68 339	84.63 150	83.15 318	67.96 93	70.25 411	90.45 228	46.83 414	69.97 257	65.10 417	56.48 207	95.30 197	35.79 412	73.13 268	90.64 238

pmmvs3		55.51 388	51.50 394	67.53 395	57.90 436	50.93 387	80.37 374	73.66 408	40.63 429	44.15 421	64.75 418	16.30 426	78.97 419	44.77 385	40.98 420	72.69 419

dongtai		55.18 390	55.46 389	54.34 415	76.03 397	36.88 433	76.07 398	84.61 369	51.28 399	43.41 423	64.61 419	56.56 205	67.81 433	18.09 438	28.50 438	58.32 431

test_vis1_rt		59.09 385	57.31 383	64.43 400	68.44 420	46.02 414	83.05 353	48.63 444	51.96 397	49.57 403	63.86 420	16.30 426	80.20 417	71.21 219	62.79 347	67.07 427

Patchmatch-RL test		68.17 339	64.49 350	79.19 307	71.22 410	53.93 371	70.07 413	71.54 418	69.22 281	56.79 374	62.89 421	56.58 204	88.61 361	69.53 233	52.61 395	95.03 89

EGC-MVSNET		42.35 401	38.09 404	55.11 412	74.57 400	46.62 411	71.63 410	55.77 436	0.04 450	0.24 451	62.70 422	14.24 432	74.91 424	17.59 439	46.06 409	43.80 436

test_f		46.58 397	43.45 401	55.96 410	45.18 445	32.05 439	61.18 429	49.49 443	33.39 432	42.05 425	62.48 423	7.00 442	65.56 437	47.08 373	43.21 414	70.27 424

UnsupCasMVSNet_bld		61.60 374	57.71 378	73.29 366	68.73 419	51.64 380	78.61 386	89.05 296	57.20 381	46.11 411	61.96 424	28.70 400	88.60 362	50.08 355	38.90 423	79.63 392

FPMVS		45.64 399	43.10 403	53.23 416	51.42 441	36.46 434	64.97 425	71.91 415	29.13 436	27.53 436	61.55 425	9.83 438	65.01 439	16.00 442	55.58 387	58.22 432

WB-MVS		46.23 398	44.94 400	50.11 418	62.13 431	21.23 451	76.48 396	55.49 437	45.89 416	35.78 429	61.44 426	35.54 372	72.83 426	9.96 445	21.75 440	56.27 433

SSC-MVS		44.51 400	43.35 402	47.99 422	61.01 434	18.90 453	74.12 404	54.36 438	43.42 425	34.10 433	60.02 427	34.42 377	70.39 429	9.14 447	19.57 441	54.68 434

new_pmnet		49.31 395	46.44 398	57.93 408	62.84 429	40.74 425	68.47 418	62.96 433	36.48 430	35.09 431	57.81 428	14.97 430	72.18 427	32.86 421	46.44 408	60.88 430

APD_test1		40.50 403	37.31 406	50.09 419	51.88 439	35.27 436	59.45 433	52.59 440	21.64 439	26.12 437	57.80 429	4.56 447	66.56 435	22.64 434	39.09 421	48.43 435

DeepMVS_CX				34.71 428	51.45 440	24.73 448		28.48 454	31.46 434	17.49 444	52.75 430	5.80 445	42.60 449	18.18 437	19.42 442	36.81 441

test_method		38.59 406	35.16 409	48.89 420	54.33 437	21.35 450	45.32 441	53.71 439	7.41 447	28.74 435	51.62 431	8.70 440	52.87 444	33.73 415	32.89 432	72.47 420

PMMVS2		37.93 407	33.61 410	50.92 417	46.31 443	24.76 447	60.55 432	50.05 441	28.94 437	20.93 439	47.59 432	4.41 449	65.13 438	25.14 431	18.55 443	62.87 429

JIA-IIPM		66.06 352	62.45 362	76.88 337	81.42 336	54.45 370	57.49 435	88.67 311	49.36 406	63.86 327	46.86 433	56.06 211	90.25 344	49.53 357	68.83 297	85.95 315

gg-mvs-nofinetune		77.18 239	74.31 261	85.80 98	91.42 128	68.36 80	71.78 408	94.72 37	49.61 405	77.12 167	45.92 434	77.41 8	93.98 255	67.62 255	93.16 55	95.05 87

LCM-MVSNet		40.54 402	35.79 407	54.76 414	36.92 451	30.81 441	51.41 438	69.02 423	22.07 438	24.63 438	45.37 435	4.56 447	65.81 436	33.67 416	34.50 431	67.67 425

testf1		32.77 409	29.47 412	42.67 425	41.89 448	30.81 441	52.07 436	43.45 446	15.45 442	18.52 442	44.82 436	2.12 451	58.38 442	16.05 440	30.87 434	38.83 438

APD_test2		32.77 409	29.47 412	42.67 425	41.89 448	30.81 441	52.07 436	43.45 446	15.45 442	18.52 442	44.82 436	2.12 451	58.38 442	16.05 440	30.87 434	38.83 438

tmp_tt		22.26 415	23.75 417	17.80 431	5.23 455	12.06 456	35.26 442	39.48 449	2.82 449	18.94 440	44.20 438	22.23 418	24.64 450	36.30 408	9.31 447	16.69 444

MVS-HIRNet		60.25 381	55.55 388	74.35 357	84.37 302	56.57 356	71.64 409	74.11 407	34.44 431	45.54 416	42.24 439	31.11 393	89.81 354	40.36 401	76.10 249	76.67 411

ANet_high		40.27 405	35.20 408	55.47 411	34.74 452	34.47 437	63.84 427	71.56 417	48.42 408	18.80 441	41.08 440	9.52 439	64.45 440	20.18 436	8.66 448	67.49 426

PMVS	26.43 22	31.84 411	28.16 414	42.89 424	25.87 454	27.58 445	50.92 439	49.78 442	21.37 440	14.17 446	40.81 441	2.01 453	66.62 434	9.61 446	38.88 424	34.49 442
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		40.46 404	37.79 405	48.47 421	44.49 446	33.35 438	66.56 424	32.84 452	32.39 433	29.65 434	39.13 442	3.91 450	68.65 431	50.17 353	40.99 419	43.40 437

MVE	24.84 23	24.35 413	19.77 419	38.09 427	34.56 453	26.92 446	26.57 443	38.87 450	11.73 446	11.37 447	27.44 443	1.37 454	50.42 446	11.41 444	14.60 444	36.93 440
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_post											23.01 444	56.49 206	92.67 296

E-PMN		24.61 412	24.00 416	26.45 429	43.74 447	18.44 454	60.86 430	39.66 448	15.11 444	9.53 448	22.10 445	6.52 444	46.94 447	8.31 448	10.14 445	13.98 445

Gipuma		34.91 408	31.44 411	45.30 423	70.99 412	39.64 431	19.85 445	72.56 413	20.10 441	16.16 445	21.47 446	5.08 446	71.16 428	13.07 443	43.70 413	25.08 443
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_post1							78.95 384				20.70 447	53.05 245	91.50 334	60.43 313

EMVS		23.76 414	23.20 418	25.46 430	41.52 450	16.90 455	60.56 431	38.79 451	14.62 445	8.99 449	20.24 448	7.35 441	45.82 448	7.25 449	9.46 446	13.64 446

X-MVStestdata		76.86 245	74.13 267	85.05 127	93.22 66	63.78 207	92.92 134	92.66 127	73.99 175	78.18 153	10.19 449	55.25 217	97.41 75	79.16 152	91.58 77	93.95 145

wuyk23d		11.30 417	10.95 420	12.33 432	48.05 442	19.89 452	25.89 444	1.92 456	3.58 448	3.12 450	1.37 450	0.64 455	15.77 451	6.23 450	7.77 449	1.35 447

testmvs		7.23 419	9.62 422	0.06 434	0.04 456	0.02 459	84.98 333	0.02 457	0.03 451	0.18 452	1.21 451	0.01 457	0.02 452	0.14 451	0.01 450	0.13 449

test123		6.92 420	9.21 423	0.08 433	0.03 457	0.05 458	81.65 364	0.01 458	0.02 452	0.14 453	0.85 452	0.03 456	0.02 452	0.12 452	0.00 451	0.16 448

mmdepth		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 451	0.00 450

monomultidepth		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 451	0.00 450

test_blank		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 451	0.00 450

uanet_test		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 451	0.00 450

DCPMVS		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 451	0.00 450

pcd_1.5k_mvsjas		4.46 421	5.95 424	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	53.55 240	0.00 454	0.00 453	0.00 451	0.00 450

sosnet-low-res		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 451	0.00 450

sosnet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 451	0.00 450

uncertanet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 451	0.00 450

Regformer		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 451	0.00 450

uanet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 451	0.00 450

WAC-MVS						49.45 395								31.56 427

FOURS1					93.95 46	61.77 267	93.96 81	91.92 161	62.14 348	86.57 55

MSC_two_6792asdad				89.60 9	97.31 4	73.22 12		95.05 29					99.07 13	92.01 35	94.77 26	96.51 24

No_MVS				89.60 9	97.31 4	73.22 12		95.05 29					99.07 13	92.01 35	94.77 26	96.51 24

eth-test2					0.00 458

eth-test					0.00 458

IU-MVS					96.46 11	69.91 43		95.18 23	80.75 62	95.28 1				92.34 32	95.36 14	96.47 28

save fliter					93.84 49	67.89 96	95.05 39	92.66 127	78.19 112

test_0728_SECOND				88.70 18	96.45 12	70.43 34	96.64 10	94.37 57					99.15 2	91.91 38	94.90 22	96.51 24

GSMVS																94.68 106

test_part2					96.29 19	68.16 89				90.78 21

sam_mvs1												57.85 185				94.68 106

sam_mvs												54.91 224

MTGPA								92.23 142

MTMP							93.77 95	32.52 453

test9_res														89.41 50	94.96 19	95.29 73

agg_prior2														86.41 80	94.75 30	95.33 69

agg_prior					94.16 43	66.97 122		93.31 97		84.49 79			96.75 125

test_prior4						67.18 115	93.92 84

test_prior				86.42 77	94.71 35	67.35 110		93.10 108					96.84 122			95.05 87

旧先验2							92.00 181		59.37 370	87.54 48			93.47 271	75.39 180

新几何2							91.41 202

无先验							92.71 144	92.61 132	62.03 349				97.01 103	66.63 264		93.97 144

原ACMM2							92.01 178

testdata2													96.09 155	61.26 309

segment_acmp												65.94 75

testdata1							89.21 283		77.55 127

test12				87.09 52	94.60 36	68.86 68		92.91 115		82.67 102		65.44 81	97.55 67		93.69 48	94.84 98

plane_prior7					86.94 244	61.51 274

plane_prior6					87.23 236	62.32 254						50.66 268

plane_prior5								91.31 192					95.55 185	76.74 169	78.53 227	88.39 270

plane_prior3						61.95 263			79.09 95	72.53 219

plane_prior2							93.13 123		78.81 102

plane_prior1					87.15 238

plane_prior						62.42 250	93.85 88		79.38 87						78.80 224

n2								0.00 459

nn								0.00 459

door-mid								66.01 428

test11								93.01 111

door								66.57 427

HQP5-MVS						63.66 217

HQP-NCC					87.54 228		94.06 73		79.80 77	74.18 198

ACMP_Plane					87.54 228		94.06 73		79.80 77	74.18 198

BP-MVS														77.63 166

HQP4-MVS										74.18 198			95.61 179			88.63 264

HQP3-MVS								91.70 178							78.90 222

HQP2-MVS												51.63 260

MDTV_nov1_ep13_2view						59.90 315	80.13 379		67.65 299	72.79 213		54.33 232		59.83 317		92.58 192

ACMMP++_ref															71.63 279

ACMMP++															69.72 288

Test By Simon												54.21 234

High-resolution multi-view benchmark