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.

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 71	96.26 46	72.84 32	99.38 1	92.64 33	95.93 9	97.08 11

MM		90.87 2	91.52 2	88.92 15	92.12 105	71.10 27	97.02 3	96.04 6	88.70 2	91.57 19	96.19 48	70.12 49	98.91 21	96.83 2	95.06 17	96.76 15

DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 169	76.68 2	97.29 1	95.35 17	82.87 37	91.58 18	97.22 8	79.93 5	99.10 9	83.12 128	97.64 2	97.94 1

DVP-MVS++		90.53 4	91.09 5	88.87 16	97.31 4	69.91 43	93.96 88	94.37 61	72.48 239	92.07 11	96.85 27	83.82 2	99.15 2	91.53 46	97.42 4	97.55 4

MSP-MVS		90.38 5	91.87 1	85.88 110	92.83 84	64.03 236	93.06 133	94.33 63	82.19 45	93.65 3	96.15 50	85.89 1	97.19 98	91.02 50	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
MGCNet		90.32 6	90.90 7	88.55 23	94.05 49	70.23 37	97.00 5	93.73 82	87.30 4	92.15 8	96.15 50	66.38 75	98.94 20	96.71 3	94.67 33	96.47 28

CNVR-MVS		90.32 6	90.89 8	88.61 22	96.76 8	70.65 30	96.47 14	94.83 36	84.83 17	89.07 43	96.80 30	70.86 45	99.06 15	92.64 33	95.71 11	96.12 40

DELS-MVS		90.05 8	90.09 11	89.94 4	93.14 75	73.88 9	97.01 4	94.40 59	88.32 3	85.71 72	94.91 91	74.11 23	98.91 21	87.26 78	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
SED-MVS		89.94 9	90.36 10	88.70 18	96.45 12	69.38 59	96.89 6	94.44 55	71.65 269	92.11 9	97.21 9	76.79 9	99.11 6	92.34 35	95.36 14	97.62 2

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 168	93.00 80	58.16 378	96.72 9	94.41 57	86.50 9	90.25 34	97.83 1	75.46 16	98.67 29	92.78 32	95.49 13	97.32 6

patch_mono-2		89.71 11	90.99 6	85.85 113	96.04 25	63.70 253	95.04 42	95.19 22	86.74 8	91.53 20	95.15 84	73.86 24	97.58 69	93.38 27	92.00 75	96.28 37

CANet		89.61 12	89.99 12	88.46 24	94.39 43	69.71 52	96.53 13	93.78 75	86.89 7	89.68 40	95.78 57	65.94 80	99.10 9	92.99 30	93.91 46	96.58 21

DVP-MVS		89.41 13	89.73 14	88.45 25	96.40 15	69.99 39	96.64 10	94.52 51	71.92 255	90.55 30	96.93 21	73.77 25	99.08 11	91.91 41	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
HPM-MVS++		89.37 14	89.95 13	87.64 35	95.10 31	68.23 101	95.24 34	94.49 53	82.43 42	88.90 45	96.35 41	71.89 42	98.63 30	88.76 64	96.40 6	96.06 41

balanced_conf03		89.08 15	88.84 23	89.81 6	93.66 58	75.15 5	90.61 275	93.43 97	84.06 24	86.20 66	90.17 226	72.42 37	96.98 115	93.09 29	95.92 10	97.29 7

NCCC		89.07 16	89.46 15	87.91 28	96.60 10	69.05 75	96.38 15	94.64 46	84.42 21	86.74 61	96.20 47	66.56 74	98.76 27	89.03 63	94.56 34	95.92 49

MED-MVS		88.94 17	89.45 16	87.42 45	94.76 34	67.28 126	94.47 61	94.87 32	70.09 301	91.27 23	96.95 17	76.77 11	98.98 16	91.55 43	94.28 37	95.99 45

DPE-MVS		88.77 18	89.21 19	87.45 44	96.26 21	67.56 119	94.17 74	94.15 68	68.77 322	90.74 28	97.27 6	76.09 14	98.49 33	90.58 54	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
TestfortrainingZip a		88.66 19	88.99 21	87.70 33	94.76 34	68.73 84	94.47 61	94.87 32	73.09 226	91.27 23	96.95 17	76.77 11	98.98 16	84.41 111	94.28 37	95.37 69

ME-MVS		88.25 20	88.55 27	87.33 50	96.33 18	67.28 126	93.93 90	94.81 37	70.09 301	88.91 44	96.95 17	70.12 49	98.73 28	91.55 43	94.28 37	95.99 45

fmvsm_l_conf0.5_n_9		88.24 21	89.36 17	84.85 157	88.15 230	61.94 303	95.65 25	89.70 299	85.54 12	92.07 11	97.33 5	67.51 66	97.27 93	96.23 5	92.07 74	95.35 73

fmvsm_s_conf0.5_n_9		88.14 22	89.21 19	84.92 152	89.29 180	61.41 320	92.97 138	88.36 354	86.96 6	91.49 21	97.49 3	69.48 54	97.46 76	97.00 1	89.88 111	95.89 50

SMA-MVS		88.14 22	88.29 31	87.67 34	93.21 72	68.72 86	93.85 96	94.03 71	74.18 200	91.74 15	96.67 33	65.61 85	98.42 37	89.24 60	96.08 7	95.88 51
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
PS-MVSNAJ		88.14 22	87.61 41	89.71 7	92.06 108	76.72 1	95.75 20	93.26 103	83.86 25	89.55 41	96.06 52	53.55 266	97.89 51	91.10 48	93.31 57	94.54 131

TSAR-MVS + MP.		88.11 25	88.64 26	86.54 88	91.73 123	68.04 105	90.36 282	93.55 89	82.89 35	91.29 22	92.89 146	72.27 39	96.03 169	87.99 68	94.77 26	95.54 62
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_11		87.99 26	89.25 18	84.23 194	89.07 188	61.60 313	94.87 49	89.06 327	85.65 11	91.09 26	97.41 4	68.26 58	97.43 80	95.07 13	92.74 64	93.66 183

fmvsm_s_conf0.5_n_8		87.96 27	88.93 22	85.07 147	88.43 217	61.78 306	94.73 56	91.74 178	85.87 10	91.66 17	97.50 2	64.03 106	98.33 38	96.28 4	90.08 107	95.10 90

TSAR-MVS + GP.		87.96 27	88.37 30	86.70 71	93.51 66	65.32 190	95.15 37	93.84 74	78.17 130	85.93 70	94.80 94	75.80 15	98.21 40	89.38 57	88.78 123	96.59 19

DeepC-MVS_fast	79.48 2	87.95 29	88.00 35	87.79 31	95.86 28	68.32 95	95.74 21	94.11 69	83.82 26	83.49 97	96.19 48	64.53 101	98.44 35	83.42 127	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
fmvsm_s_conf0.5_n_10		87.93 30	88.67 25	85.71 120	88.69 199	63.71 251	94.56 59	90.22 275	85.04 15	92.27 6	97.05 12	63.67 114	98.15 42	95.09 12	91.39 87	95.27 81

xiu_mvs_v2_base		87.92 31	87.38 45	89.55 12	91.41 135	76.43 3	95.74 21	93.12 111	83.53 29	89.55 41	95.95 55	53.45 270	97.68 59	91.07 49	92.62 65	94.54 131

EPNet		87.84 32	88.38 29	86.23 100	93.30 69	66.05 169	95.26 33	94.84 35	87.09 5	88.06 48	94.53 100	66.79 71	97.34 86	83.89 118	91.68 81	95.29 78
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
lupinMVS		87.74 33	87.77 38	87.63 39	89.24 185	71.18 24	96.57 12	92.90 122	82.70 39	87.13 56	95.27 77	64.99 91	95.80 185	89.34 58	91.80 79	95.93 48

test_fmvsm_n_1920		87.69 34	88.50 28	85.27 140	87.05 265	63.55 260	93.69 106	91.08 222	84.18 23	90.17 36	97.04 14	67.58 65	97.99 46	95.72 8	90.03 108	94.26 151

fmvsm_l_conf0.5_n_3		87.54 35	88.29 31	85.30 137	86.92 276	62.63 286	95.02 44	90.28 270	84.95 16	90.27 33	96.86 25	65.36 87	97.52 74	94.93 15	90.03 108	95.76 54

APDe-MVS		87.54 35	87.84 37	86.65 74	96.07 24	66.30 164	94.84 51	93.78 75	69.35 311	88.39 47	96.34 42	67.74 64	97.66 64	90.62 53	93.44 55	96.01 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
fmvsm_s_conf0.5_n_6		87.50 37	88.72 24	83.84 206	86.89 278	60.04 354	95.05 40	92.17 157	84.80 18	92.27 6	96.37 39	64.62 98	96.54 141	94.43 19	91.86 77	94.94 99

fmvsm_l_conf0.5_n		87.49 38	88.19 33	85.39 131	86.95 271	64.37 222	94.30 71	88.45 352	80.51 70	92.70 4	96.86 25	69.98 51	97.15 103	95.83 7	88.08 131	94.65 124

SD-MVS		87.49 38	87.49 43	87.50 43	93.60 60	68.82 82	93.90 93	92.63 137	76.86 157	87.90 50	95.76 58	66.17 77	97.63 66	89.06 62	91.48 85	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
fmvsm_l_conf0.5_n_a		87.44 40	88.15 34	85.30 137	87.10 263	64.19 231	94.41 66	88.14 362	80.24 81	92.54 5	96.97 16	69.52 53	97.17 99	95.89 6	88.51 126	94.56 128

dcpmvs_2		87.37 41	87.55 42	86.85 62	95.04 33	68.20 102	90.36 282	90.66 250	79.37 105	81.20 121	93.67 130	74.73 18	96.55 140	90.88 51	92.00 75	95.82 52

alignmvs		87.28 42	86.97 49	88.24 27	91.30 137	71.14 26	95.61 26	93.56 88	79.30 106	87.07 58	95.25 79	68.43 56	96.93 123	87.87 69	84.33 182	96.65 17

train_agg		87.21 43	87.42 44	86.60 77	94.18 45	67.28 126	94.16 75	93.51 91	71.87 260	85.52 75	95.33 71	68.19 59	97.27 93	89.09 61	94.90 22	95.25 85

MG-MVS		87.11 44	86.27 62	89.62 8	97.79 1	76.27 4	94.96 46	94.49 53	78.74 121	83.87 93	92.94 144	64.34 102	96.94 121	75.19 206	94.09 42	95.66 57

SF-MVS		87.03 45	87.09 47	86.84 63	92.70 90	67.45 124	93.64 109	93.76 78	70.78 293	86.25 64	96.44 38	66.98 69	97.79 55	88.68 65	94.56 34	95.28 80

fmvsm_s_conf0.5_n_3		86.88 46	87.99 36	83.58 220	87.26 257	60.74 334	93.21 130	87.94 369	84.22 22	91.70 16	97.27 6	65.91 82	95.02 228	93.95 24	90.42 103	94.99 96

CSCG		86.87 47	86.26 63	88.72 17	95.05 32	70.79 29	93.83 101	95.33 18	68.48 326	77.63 181	94.35 109	73.04 30	98.45 34	84.92 103	93.71 51	96.92 14

sasdasda		86.85 48	86.25 64	88.66 20	91.80 121	71.92 16	93.54 114	91.71 181	80.26 78	87.55 53	95.25 79	63.59 118	96.93 123	88.18 66	84.34 180	97.11 9

canonicalmvs		86.85 48	86.25 64	88.66 20	91.80 121	71.92 16	93.54 114	91.71 181	80.26 78	87.55 53	95.25 79	63.59 118	96.93 123	88.18 66	84.34 180	97.11 9

UBG		86.83 50	86.70 55	87.20 52	93.07 78	69.81 47	93.43 122	95.56 13	81.52 52	81.50 116	92.12 167	73.58 28	96.28 153	84.37 112	85.20 169	95.51 63

PHI-MVS		86.83 50	86.85 54	86.78 67	93.47 67	65.55 185	95.39 31	95.10 25	71.77 265	85.69 73	96.52 35	62.07 143	98.77 26	86.06 91	95.60 12	96.03 43

SteuartSystems-ACMMP		86.82 52	86.90 52	86.58 80	90.42 154	66.38 161	96.09 17	93.87 73	77.73 139	84.01 92	95.66 60	63.39 121	97.94 47	87.40 76	93.55 54	95.42 65
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_s_conf0.5_n_4		86.79 53	87.63 39	84.27 192	86.15 294	61.48 317	94.69 57	91.16 208	83.79 28	90.51 32	96.28 44	64.24 103	98.22 39	95.00 14	86.88 143	93.11 201

PVSNet_Blended		86.73 54	86.86 53	86.31 99	93.76 54	67.53 121	96.33 16	93.61 86	82.34 44	81.00 127	93.08 140	63.19 125	97.29 89	87.08 82	91.38 88	94.13 160

testing11		86.71 55	86.44 60	87.55 41	93.54 64	71.35 21	93.65 108	95.58 11	81.36 59	80.69 132	92.21 165	72.30 38	96.46 146	85.18 99	83.43 197	94.82 109

test_fmvsmconf_n		86.58 56	87.17 46	84.82 159	85.28 312	62.55 287	94.26 73	89.78 290	83.81 27	87.78 52	96.33 43	65.33 88	96.98 115	94.40 20	87.55 137	94.95 98

BP-MVS1		86.54 57	86.68 57	86.13 103	87.80 245	67.18 133	92.97 138	95.62 10	79.92 86	82.84 104	94.14 118	74.95 17	96.46 146	82.91 132	88.96 122	94.74 114

jason		86.40 58	86.17 66	87.11 55	86.16 293	70.54 32	95.71 24	92.19 154	82.00 47	84.58 85	94.34 110	61.86 146	95.53 210	87.76 70	90.89 96	95.27 81
jason: jason.
NormalMVS		86.39 59	86.66 58	85.60 125	92.12 105	65.95 174	94.88 47	90.83 238	84.69 19	83.67 95	94.10 119	63.16 127	96.91 127	85.31 95	91.15 92	93.93 171

fmvsm_s_conf0.5_n		86.39 59	86.91 51	84.82 159	87.36 256	63.54 261	94.74 53	90.02 283	82.52 40	90.14 37	96.92 23	62.93 132	97.84 54	95.28 11	82.26 208	93.07 204

fmvsm_s_conf0.5_n_5		86.38 61	86.94 50	84.71 170	84.67 324	63.29 266	94.04 84	89.99 285	82.88 36	87.85 51	96.03 53	62.89 134	96.36 150	94.15 21	89.95 110	94.48 141

SymmetryMVS		86.32 62	86.39 61	86.12 104	90.52 152	65.95 174	94.88 47	94.58 50	84.69 19	83.67 95	94.10 119	63.16 127	96.91 127	85.31 95	86.59 152	95.51 63

WTY-MVS		86.32 62	85.81 74	87.85 29	92.82 86	69.37 61	95.20 35	95.25 20	82.71 38	81.91 112	94.73 95	67.93 63	97.63 66	79.55 171	82.25 210	96.54 22

myMVS_eth3d28		86.31 64	86.15 67	86.78 67	93.56 62	70.49 33	92.94 141	95.28 19	82.47 41	78.70 171	92.07 169	72.45 36	95.41 212	82.11 141	85.78 162	94.44 143

MSLP-MVS++		86.27 65	85.91 73	87.35 48	92.01 112	68.97 78	95.04 42	92.70 128	79.04 116	81.50 116	96.50 37	58.98 191	96.78 131	83.49 126	93.93 45	96.29 35

VNet		86.20 66	85.65 78	87.84 30	93.92 51	69.99 39	95.73 23	95.94 7	78.43 126	86.00 69	93.07 141	58.22 201	97.00 111	85.22 97	84.33 182	96.52 23

MVS_111021_HR		86.19 67	85.80 75	87.37 47	93.17 74	69.79 48	93.99 87	93.76 78	79.08 113	78.88 167	93.99 124	62.25 141	98.15 42	85.93 92	91.15 92	94.15 159

SPE-MVS-test		86.14 68	87.01 48	83.52 221	92.63 92	59.36 366	95.49 28	91.92 167	80.09 82	85.46 77	95.53 66	61.82 148	95.77 189	86.77 86	93.37 56	95.41 66

ACMMP_NAP		86.05 69	85.80 75	86.80 66	91.58 127	67.53 121	91.79 208	93.49 94	74.93 190	84.61 84	95.30 73	59.42 181	97.92 48	86.13 89	94.92 20	94.94 99

testing99		86.01 70	85.47 80	87.63 39	93.62 59	71.25 23	93.47 120	95.23 21	80.42 73	80.60 134	91.95 176	71.73 43	96.50 144	80.02 168	82.22 211	95.13 88

ETV-MVS		86.01 70	86.11 68	85.70 121	90.21 159	67.02 140	93.43 122	91.92 167	81.21 61	84.13 91	94.07 123	60.93 157	95.63 199	89.28 59	89.81 112	94.46 142

testing91		85.93 72	85.31 84	87.78 32	93.59 61	71.47 19	93.50 117	95.08 28	80.26 78	80.53 137	91.93 177	70.43 47	96.51 143	80.32 166	82.13 213	95.37 69

APD-MVS		85.93 72	85.99 71	85.76 117	95.98 27	65.21 193	93.59 112	92.58 139	66.54 345	86.17 67	95.88 56	63.83 110	97.00 111	86.39 88	92.94 61	95.06 92
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PAPM		85.89 74	85.46 81	87.18 53	88.20 229	72.42 15	92.41 175	92.77 126	82.11 46	80.34 140	93.07 141	68.27 57	95.02 228	78.39 187	93.59 53	94.09 162

CS-MVS		85.80 75	86.65 59	83.27 233	92.00 113	58.92 370	95.31 32	91.86 172	79.97 83	84.82 83	95.40 69	62.26 140	95.51 211	86.11 90	92.08 73	95.37 69

fmvsm_s_conf0.5_n_a		85.75 76	86.09 69	84.72 168	85.73 305	63.58 258	93.79 102	89.32 310	81.42 57	90.21 35	96.91 24	62.41 139	97.67 61	94.48 18	80.56 236	92.90 210

test_fmvsmconf0.1_n		85.71 77	86.08 70	84.62 178	80.83 375	62.33 292	93.84 99	88.81 339	83.50 30	87.00 59	96.01 54	63.36 122	96.93 123	94.04 23	87.29 140	94.61 126

CDPH-MVS		85.71 77	85.46 81	86.46 90	94.75 38	67.19 131	93.89 94	92.83 124	70.90 289	83.09 102	95.28 75	63.62 116	97.36 84	80.63 162	94.18 41	94.84 105

casdiffmvs_mvg		85.66 79	85.18 86	87.09 56	88.22 228	69.35 62	93.74 105	91.89 170	81.47 53	80.10 143	91.45 189	64.80 96	96.35 151	87.23 79	87.69 135	95.58 60
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.1_n		85.61 80	85.93 72	84.68 172	82.95 356	63.48 263	94.03 86	89.46 304	81.69 50	89.86 38	96.74 31	61.85 147	97.75 57	94.74 17	82.01 215	92.81 214

MGCFI-Net		85.59 81	85.73 77	85.17 144	91.41 135	62.44 288	92.87 146	91.31 198	79.65 93	86.99 60	95.14 85	62.90 133	96.12 161	87.13 81	84.13 188	96.96 13

GDP-MVS		85.54 82	85.32 83	86.18 101	87.64 248	67.95 109	92.91 144	92.36 144	77.81 136	83.69 94	94.31 112	72.84 32	96.41 148	80.39 165	85.95 159	94.19 155

DeepC-MVS	77.85 3	85.52 83	85.24 85	86.37 95	88.80 197	66.64 155	92.15 185	93.68 84	81.07 63	76.91 193	93.64 131	62.59 136	98.44 35	85.50 93	92.84 63	94.03 166
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
casdiffmvs		85.37 84	84.87 92	86.84 63	88.25 226	69.07 72	93.04 135	91.76 177	81.27 60	80.84 130	92.07 169	64.23 104	96.06 167	84.98 102	87.43 139	95.39 67
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ZNCC-MVS		85.33 85	85.08 88	86.06 105	93.09 77	65.65 181	93.89 94	93.41 99	73.75 211	79.94 145	94.68 97	60.61 162	98.03 45	82.63 136	93.72 50	94.52 133

fmvsm_s_conf0.5_n_7		85.24 86	86.69 56	80.91 309	84.52 329	60.10 352	93.35 125	90.35 263	83.41 31	86.54 63	96.27 45	60.50 163	90.02 393	94.84 16	90.38 104	92.61 218

MP-MVS-pluss		85.24 86	85.13 87	85.56 126	91.42 132	65.59 183	91.54 227	92.51 141	74.56 193	80.62 133	95.64 61	59.15 186	97.00 111	86.94 84	93.80 47	94.07 164
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
testing222		85.18 88	84.69 96	86.63 76	92.91 82	69.91 43	92.61 161	95.80 9	80.31 77	80.38 139	92.27 161	68.73 55	95.19 225	75.94 200	83.27 199	94.81 111

PAPR		85.15 89	84.47 97	87.18 53	96.02 26	68.29 96	91.85 206	93.00 117	76.59 168	79.03 163	95.00 86	61.59 149	97.61 68	78.16 188	89.00 121	95.63 58

fmvsm_s_conf0.5_n_2		85.06 90	85.60 79	83.44 227	86.92 276	60.53 341	94.41 66	87.31 377	83.30 32	88.72 46	96.72 32	54.28 258	97.75 57	94.07 22	84.68 179	92.04 241

MP-MVS		85.02 91	84.97 90	85.17 144	92.60 93	64.27 227	93.24 127	92.27 147	73.13 222	79.63 155	94.43 103	61.90 144	97.17 99	85.00 101	92.56 66	94.06 165
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
baseline		85.01 92	84.44 98	86.71 70	88.33 223	68.73 84	90.24 287	91.82 176	81.05 64	81.18 122	92.50 153	63.69 113	96.08 166	84.45 110	86.71 150	95.32 76

CHOSEN 1792x2688		84.98 93	83.45 118	89.57 11	89.94 164	75.14 6	92.07 191	92.32 145	81.87 48	75.68 202	88.27 260	60.18 167	98.60 31	80.46 164	90.27 106	94.96 97

MVSMamba_PlusPlus		84.97 94	83.65 111	88.93 14	90.17 160	74.04 8	87.84 345	92.69 131	62.18 388	81.47 118	87.64 274	71.47 44	96.28 153	84.69 105	94.74 31	96.47 28

E3new		84.94 95	84.36 100	86.69 73	89.06 189	69.31 63	92.68 158	91.29 203	80.72 67	81.03 125	92.14 166	61.89 145	95.91 173	84.59 107	85.85 161	94.86 101

viewmanbaseed2359cas		84.89 96	84.26 102	86.78 67	88.50 208	69.77 50	92.69 157	91.13 214	81.11 62	81.54 115	91.98 173	60.35 164	95.73 191	84.47 109	86.56 153	94.84 105

EIA-MVS		84.84 97	84.88 91	84.69 171	91.30 137	62.36 291	93.85 96	92.04 160	79.45 101	79.33 160	94.28 114	62.42 138	96.35 151	80.05 167	91.25 91	95.38 68

lecture		84.77 98	84.81 94	84.65 174	92.12 105	62.27 295	94.74 53	92.64 136	68.35 327	85.53 74	95.30 73	59.77 174	97.91 49	83.73 122	91.15 92	93.77 180

fmvsm_s_conf0.1_n_a		84.76 99	84.84 93	84.53 180	80.23 388	63.50 262	92.79 148	88.73 342	80.46 71	89.84 39	96.65 34	60.96 156	97.57 71	93.80 25	80.14 238	92.53 223

viewcassd2359sk11		84.74 100	84.11 103	86.64 75	88.57 202	69.20 70	92.61 161	91.23 205	80.58 68	80.85 129	91.96 174	61.39 151	95.89 175	84.28 113	85.49 166	94.82 109

HFP-MVS		84.73 101	84.40 99	85.72 119	93.75 56	65.01 199	93.50 117	93.19 107	72.19 249	79.22 161	94.93 89	59.04 189	97.67 61	81.55 151	92.21 69	94.49 140

MVS		84.66 102	82.86 140	90.06 2	90.93 144	74.56 7	87.91 343	95.54 14	68.55 324	72.35 259	94.71 96	59.78 173	98.90 23	81.29 157	94.69 32	96.74 16

GST-MVS		84.63 103	84.29 101	85.66 122	92.82 86	65.27 191	93.04 135	93.13 110	73.20 220	78.89 164	94.18 117	59.41 182	97.85 53	81.45 153	92.48 68	93.86 177

EC-MVSNet		84.53 104	85.04 89	83.01 239	89.34 176	61.37 321	94.42 65	91.09 218	77.91 134	83.24 98	94.20 116	58.37 199	95.40 213	85.35 94	91.41 86	92.27 235

E2		84.45 105	83.74 107	86.56 82	87.90 238	69.06 73	92.53 169	91.13 214	80.35 75	80.58 135	91.69 184	60.70 158	95.84 178	83.80 120	84.99 171	94.79 112

E3		84.45 105	83.74 107	86.56 82	87.90 238	69.06 73	92.53 169	91.13 214	80.35 75	80.58 135	91.69 184	60.70 158	95.84 178	83.80 120	84.99 171	94.79 112

fmvsm_s_conf0.1_n_2		84.40 107	84.78 95	83.27 233	85.25 313	60.41 344	94.13 78	85.69 402	83.05 34	87.99 49	96.37 39	52.75 275	97.68 59	93.75 26	84.05 189	91.71 249

ACMMPR		84.37 108	84.06 104	85.28 139	93.56 62	64.37 222	93.50 117	93.15 109	72.19 249	78.85 169	94.86 92	56.69 225	97.45 77	81.55 151	92.20 70	94.02 167

region2R		84.36 109	84.03 105	85.36 135	93.54 64	64.31 225	93.43 122	92.95 120	72.16 252	78.86 168	94.84 93	56.97 220	97.53 73	81.38 155	92.11 72	94.24 153

LFMVS		84.34 110	82.73 142	89.18 13	94.76 34	73.25 11	94.99 45	91.89 170	71.90 257	82.16 111	93.49 135	47.98 328	97.05 106	82.55 137	84.82 175	97.25 8

test_yl		84.28 111	83.16 131	87.64 35	94.52 41	69.24 68	95.78 18	95.09 26	69.19 314	81.09 123	92.88 147	57.00 218	97.44 78	81.11 159	81.76 219	96.23 38

DCV-MVSNet		84.28 111	83.16 131	87.64 35	94.52 41	69.24 68	95.78 18	95.09 26	69.19 314	81.09 123	92.88 147	57.00 218	97.44 78	81.11 159	81.76 219	96.23 38

diffmvs		84.28 111	83.83 106	85.61 124	87.40 254	68.02 106	90.88 260	89.24 313	80.54 69	81.64 114	92.52 152	59.83 172	94.52 257	87.32 77	85.11 170	94.29 150
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HY-MVS	76.49 5	84.28 111	83.36 124	87.02 59	92.22 100	67.74 114	84.65 374	94.50 52	79.15 110	82.23 110	87.93 269	66.88 70	96.94 121	80.53 163	82.20 212	96.39 33

ETVMVS		84.22 115	83.71 109	85.76 117	92.58 94	68.25 100	92.45 173	95.53 15	79.54 100	79.46 157	91.64 187	70.29 48	94.18 271	69.16 269	82.76 205	94.84 105

MAR-MVS		84.18 116	83.43 119	86.44 92	96.25 22	65.93 176	94.28 72	94.27 65	74.41 195	79.16 162	95.61 62	53.99 261	98.88 25	69.62 263	93.26 58	94.50 139
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
MVS_Test		84.16 117	83.20 128	87.05 58	91.56 128	69.82 46	89.99 296	92.05 159	77.77 138	82.84 104	86.57 291	63.93 109	96.09 163	74.91 211	89.18 118	95.25 85

CANet_DTU		84.09 118	83.52 112	85.81 114	90.30 157	66.82 149	91.87 204	89.01 330	85.27 13	86.09 68	93.74 128	47.71 334	96.98 115	77.90 190	89.78 114	93.65 184

viewdifsd2359ckpt13		84.08 119	83.21 127	86.70 71	88.49 212	69.55 55	92.25 179	91.14 212	79.71 91	79.73 152	91.72 183	58.83 192	95.89 175	82.06 142	84.99 171	94.66 123

viewmacassd2359aftdt		84.03 120	83.18 130	86.59 79	86.76 279	69.44 56	92.44 174	90.85 237	80.38 74	80.78 131	91.33 195	58.54 196	95.62 201	82.15 140	85.41 167	94.72 117

ET-MVSNet_ETH3D		84.01 121	83.15 133	86.58 80	90.78 149	70.89 28	94.74 53	94.62 47	81.44 56	58.19 406	93.64 131	73.64 27	92.35 348	82.66 135	78.66 258	96.50 27

E4		84.00 122	83.19 129	86.46 90	86.99 266	68.85 80	92.39 176	90.99 231	79.94 84	80.17 142	91.36 194	59.73 175	95.79 186	82.87 133	84.22 186	94.74 114

diffmvs_AUTHOR		83.97 123	83.49 115	85.39 131	86.09 295	67.83 111	90.76 265	89.05 328	79.94 84	81.43 119	92.23 164	59.53 178	94.42 260	87.18 80	85.22 168	93.92 173

PVSNet_Blended_VisFu		83.97 123	83.50 114	85.39 131	90.02 162	66.59 158	93.77 103	91.73 179	77.43 148	77.08 192	89.81 236	63.77 112	96.97 118	79.67 170	88.21 129	92.60 219

MTAPA		83.91 125	83.38 123	85.50 127	91.89 119	65.16 195	81.75 406	92.23 148	75.32 185	80.53 137	95.21 82	56.06 234	97.16 102	84.86 104	92.55 67	94.18 156

XVS		83.87 126	83.47 117	85.05 148	93.22 70	63.78 245	92.92 142	92.66 133	73.99 203	78.18 175	94.31 112	55.25 240	97.41 81	79.16 177	91.58 83	93.95 169

Effi-MVS+		83.82 127	82.76 141	86.99 60	89.56 172	69.40 57	91.35 240	86.12 396	72.59 236	83.22 101	92.81 150	59.60 177	96.01 171	81.76 150	87.80 134	95.56 61

test_fmvsmvis_n_1920		83.80 128	83.48 116	84.77 163	82.51 359	63.72 250	91.37 236	83.99 420	81.42 57	77.68 180	95.74 59	58.37 199	97.58 69	93.38 27	86.87 144	93.00 207

EI-MVSNet-Vis-set		83.77 129	83.67 110	84.06 197	92.79 89	63.56 259	91.76 213	94.81 37	79.65 93	77.87 178	94.09 121	63.35 123	97.90 50	79.35 175	79.36 248	90.74 270

MVSFormer		83.75 130	82.88 139	86.37 95	89.24 185	71.18 24	89.07 321	90.69 247	65.80 355	87.13 56	94.34 110	64.99 91	92.67 334	72.83 228	91.80 79	95.27 81

CP-MVS		83.71 131	83.40 122	84.65 174	93.14 75	63.84 243	94.59 58	92.28 146	71.03 287	77.41 185	94.92 90	55.21 243	96.19 158	81.32 156	90.70 98	93.91 174

test_fmvsmconf0.01_n		83.70 132	83.52 112	84.25 193	75.26 438	61.72 310	92.17 184	87.24 379	82.36 43	84.91 82	95.41 68	55.60 238	96.83 130	92.85 31	85.87 160	94.21 154

baseline2		83.68 133	83.42 121	84.48 183	87.37 255	66.00 171	90.06 291	95.93 8	79.71 91	69.08 297	90.39 214	77.92 6	96.28 153	78.91 182	81.38 223	91.16 263

E5new		83.62 134	82.65 144	86.55 84	86.98 267	69.28 66	91.69 217	90.96 232	79.61 95	79.80 147	91.25 197	58.04 204	95.84 178	81.83 148	83.66 194	94.52 133

E6new		83.62 134	82.65 144	86.55 84	86.98 267	69.29 64	91.69 217	90.95 234	79.60 98	79.80 147	91.25 197	58.04 204	95.84 178	81.84 146	83.67 192	94.52 133

E6		83.62 134	82.65 144	86.55 84	86.98 267	69.29 64	91.69 217	90.95 234	79.60 98	79.80 147	91.25 197	58.04 204	95.84 178	81.84 146	83.67 192	94.52 133

E5		83.62 134	82.65 144	86.55 84	86.98 267	69.28 66	91.69 217	90.96 232	79.61 95	79.80 147	91.25 197	58.04 204	95.84 178	81.83 148	83.66 194	94.52 133

viewdifsd2359ckpt09		83.52 138	82.57 149	86.37 95	88.02 235	68.47 91	91.78 210	89.63 300	79.61 95	78.56 173	92.00 172	59.28 184	95.96 172	81.94 144	82.35 206	94.69 118

reproduce-ours		83.51 139	83.33 125	84.06 197	92.18 103	60.49 342	90.74 267	92.04 160	64.35 365	83.24 98	95.59 64	59.05 187	97.27 93	83.61 123	89.17 119	94.41 148

our_new_method		83.51 139	83.33 125	84.06 197	92.18 103	60.49 342	90.74 267	92.04 160	64.35 365	83.24 98	95.59 64	59.05 187	97.27 93	83.61 123	89.17 119	94.41 148

thisisatest0515		83.41 141	82.49 151	86.16 102	89.46 175	68.26 98	93.54 114	94.70 43	74.31 198	75.75 200	90.92 204	72.62 34	96.52 142	69.64 261	81.50 222	93.71 181

PVSNet_BlendedMVS		83.38 142	83.43 119	83.22 235	93.76 54	67.53 121	94.06 80	93.61 86	79.13 111	81.00 127	85.14 309	63.19 125	97.29 89	87.08 82	73.91 296	84.83 378

test2506		83.29 143	82.92 138	84.37 187	88.39 220	63.18 272	92.01 194	91.35 197	77.66 141	78.49 174	91.42 190	64.58 100	95.09 227	73.19 224	89.23 116	94.85 102

PGM-MVS		83.25 144	82.70 143	84.92 152	92.81 88	64.07 235	90.44 277	92.20 152	71.28 281	77.23 189	94.43 103	55.17 244	97.31 88	79.33 176	91.38 88	93.37 191

HPM-MVS		83.25 144	82.95 137	84.17 195	92.25 99	62.88 281	90.91 257	91.86 172	70.30 298	77.12 190	93.96 125	56.75 223	96.28 153	82.04 143	91.34 90	93.34 192
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
reproduce_model		83.15 146	82.96 135	83.73 212	92.02 109	59.74 358	90.37 281	92.08 158	63.70 372	82.86 103	95.48 67	58.62 194	97.17 99	83.06 129	88.42 127	94.26 151

EI-MVSNet-UG-set		83.14 147	82.96 135	83.67 217	92.28 98	63.19 271	91.38 235	94.68 44	79.22 108	76.60 195	93.75 127	62.64 135	97.76 56	78.07 189	78.01 261	90.05 279

testing3-2		83.11 148	83.15 133	82.98 240	91.92 116	64.01 238	94.39 69	95.37 16	78.32 127	75.53 207	90.06 232	73.18 29	93.18 313	74.34 216	75.27 285	91.77 248

VDD-MVS		83.06 149	81.81 162	86.81 65	90.86 147	67.70 115	95.40 30	91.50 192	75.46 180	81.78 113	92.34 160	40.09 383	97.13 104	86.85 85	82.04 214	95.60 59

h-mvs33		83.01 150	82.56 150	84.35 188	89.34 176	62.02 299	92.72 151	93.76 78	81.45 54	82.73 107	92.25 163	60.11 168	97.13 104	87.69 71	62.96 382	93.91 174

PAPM_NR		82.97 151	81.84 161	86.37 95	94.10 48	66.76 152	87.66 349	92.84 123	69.96 304	74.07 232	93.57 133	63.10 130	97.50 75	70.66 256	90.58 100	94.85 102

mPP-MVS		82.96 152	82.44 152	84.52 181	92.83 84	62.92 279	92.76 149	91.85 174	71.52 277	75.61 205	94.24 115	53.48 269	96.99 114	78.97 180	90.73 97	93.64 185

viewdifsd2359ckpt07		82.95 153	82.04 156	85.66 122	87.19 260	66.73 153	91.56 226	90.39 262	77.58 144	77.58 184	91.19 201	58.57 195	95.65 198	82.32 138	82.01 215	94.60 127

SR-MVS		82.81 154	82.58 148	83.50 224	93.35 68	61.16 324	92.23 182	91.28 204	64.48 364	81.27 120	95.28 75	53.71 265	95.86 177	82.87 133	88.77 124	93.49 189

DP-MVS Recon		82.73 155	81.65 163	85.98 107	97.31 4	67.06 136	95.15 37	91.99 164	69.08 319	76.50 197	93.89 126	54.48 254	98.20 41	70.76 254	85.66 164	92.69 215

CLD-MVS		82.73 155	82.35 154	83.86 205	87.90 238	67.65 117	95.45 29	92.18 155	85.06 14	72.58 250	92.27 161	52.46 278	95.78 187	84.18 114	79.06 253	88.16 307
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
sss		82.71 157	82.38 153	83.73 212	89.25 182	59.58 361	92.24 181	94.89 31	77.96 132	79.86 146	92.38 158	56.70 224	97.05 106	77.26 193	80.86 231	94.55 129

3Dnovator	73.91 6	82.69 158	80.82 176	88.31 26	89.57 171	71.26 22	92.60 163	94.39 60	78.84 118	67.89 320	92.48 156	48.42 323	98.52 32	68.80 274	94.40 36	95.15 87

RRT-MVS		82.61 159	81.16 167	86.96 61	91.10 141	68.75 83	87.70 348	92.20 152	76.97 155	72.68 246	87.10 285	51.30 292	96.41 148	83.56 125	87.84 133	95.74 55

viewmambaseed2359dif		82.60 160	81.91 160	84.67 173	85.83 302	66.09 168	90.50 276	89.01 330	75.46 180	79.64 154	92.01 171	59.51 179	94.38 262	82.99 131	82.26 208	93.54 187

MVSTER		82.47 161	82.05 155	83.74 210	92.68 91	69.01 76	91.90 203	93.21 104	79.83 87	72.14 260	85.71 304	74.72 19	94.72 242	75.72 202	72.49 306	87.50 314

TESTMET0.1,1		82.41 162	81.98 159	83.72 214	88.08 231	63.74 247	92.70 153	93.77 77	79.30 106	77.61 182	87.57 276	58.19 202	94.08 276	73.91 218	86.68 151	93.33 194

CostFormer		82.33 163	81.15 168	85.86 112	89.01 192	68.46 92	82.39 403	93.01 115	75.59 178	80.25 141	81.57 356	72.03 41	94.96 232	79.06 179	77.48 269	94.16 158

API-MVS		82.28 164	80.53 185	87.54 42	96.13 23	70.59 31	93.63 110	91.04 228	65.72 357	75.45 208	92.83 149	56.11 233	98.89 24	64.10 330	89.75 115	93.15 199

IB-MVS	77.80 4	82.18 165	80.46 187	87.35 48	89.14 187	70.28 36	95.59 27	95.17 24	78.85 117	70.19 285	85.82 302	70.66 46	97.67 61	72.19 240	66.52 351	94.09 162
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
xiu_mvs_v1_base_debu		82.16 166	81.12 169	85.26 141	86.42 286	68.72 86	92.59 165	90.44 259	73.12 223	84.20 88	94.36 105	38.04 396	95.73 191	84.12 115	86.81 145	91.33 256

xiu_mvs_v1_base		82.16 166	81.12 169	85.26 141	86.42 286	68.72 86	92.59 165	90.44 259	73.12 223	84.20 88	94.36 105	38.04 396	95.73 191	84.12 115	86.81 145	91.33 256

xiu_mvs_v1_base_debi		82.16 166	81.12 169	85.26 141	86.42 286	68.72 86	92.59 165	90.44 259	73.12 223	84.20 88	94.36 105	38.04 396	95.73 191	84.12 115	86.81 145	91.33 256

3Dnovator+	73.60 7	82.10 169	80.60 183	86.60 77	90.89 146	66.80 151	95.20 35	93.44 96	74.05 202	67.42 327	92.49 155	49.46 313	97.65 65	70.80 253	91.68 81	95.33 74

MVS_111021_LR		82.02 170	81.52 164	83.51 223	88.42 218	62.88 281	89.77 299	88.93 335	76.78 160	75.55 206	93.10 138	50.31 302	95.38 215	83.82 119	87.02 142	92.26 236

PMMVS		81.98 171	82.04 156	81.78 277	89.76 168	56.17 399	91.13 253	90.69 247	77.96 132	80.09 144	93.57 133	46.33 352	94.99 231	81.41 154	87.46 138	94.17 157

baseline1		81.84 172	81.03 173	84.28 191	91.60 126	66.62 156	91.08 254	91.66 186	81.87 48	74.86 218	91.67 186	69.98 51	94.92 235	71.76 243	64.75 368	91.29 261

EPP-MVSNet		81.79 173	81.52 164	82.61 250	88.77 198	60.21 350	93.02 137	93.66 85	68.52 325	72.90 244	90.39 214	72.19 40	94.96 232	74.93 210	79.29 251	92.67 216

WBMVS		81.67 174	80.98 175	83.72 214	93.07 78	69.40 57	94.33 70	93.05 113	76.84 158	72.05 262	84.14 322	74.49 21	93.88 290	72.76 231	68.09 337	87.88 309

test_vis1_n_1920		81.66 175	82.01 158	80.64 312	82.24 361	55.09 408	94.76 52	86.87 383	81.67 51	84.40 87	94.63 98	38.17 393	94.67 248	91.98 40	83.34 198	92.16 239

APD-MVS_3200maxsize		81.64 176	81.32 166	82.59 252	92.36 96	58.74 372	91.39 233	91.01 230	63.35 376	79.72 153	94.62 99	51.82 281	96.14 160	79.71 169	87.93 132	92.89 211

mvsmamba		81.55 177	80.72 178	84.03 201	91.42 132	66.93 147	83.08 394	89.13 321	78.55 125	67.50 325	87.02 286	51.79 283	90.07 392	87.48 74	90.49 102	95.10 90

ACMMP		81.49 178	80.67 180	83.93 203	91.71 124	62.90 280	92.13 186	92.22 151	71.79 264	71.68 268	93.49 135	50.32 301	96.96 119	78.47 186	84.22 186	91.93 246
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
KinetiMVS		81.43 179	80.11 189	85.38 134	86.60 282	65.47 189	92.90 145	93.54 90	75.33 184	77.31 187	90.39 214	46.81 343	96.75 132	71.65 246	86.46 156	93.93 171

CDS-MVSNet		81.43 179	80.74 177	83.52 221	86.26 290	64.45 216	92.09 189	90.65 251	75.83 176	73.95 234	89.81 236	63.97 108	92.91 324	71.27 247	82.82 202	93.20 198
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
mvs_anonymous		81.36 181	79.99 193	85.46 128	90.39 156	68.40 93	86.88 360	90.61 252	74.41 195	70.31 284	84.67 314	63.79 111	92.32 350	73.13 225	85.70 163	95.67 56

ECVR-MVS		81.29 182	80.38 188	84.01 202	88.39 220	61.96 301	92.56 168	86.79 385	77.66 141	76.63 194	91.42 190	46.34 351	95.24 224	74.36 215	89.23 116	94.85 102

guyue		81.23 183	80.57 184	83.21 237	86.64 280	61.85 304	92.52 171	92.78 125	78.69 122	74.92 217	89.42 240	50.07 305	95.35 216	80.79 161	79.31 250	92.42 225

IMVS_0403		81.19 184	79.88 195	85.13 146	88.54 203	64.75 204	88.84 326	90.80 241	76.73 163	75.21 211	90.18 220	54.22 259	96.21 157	73.47 220	80.95 226	94.43 144

thisisatest0530		81.15 185	80.07 190	84.39 186	88.26 225	65.63 182	91.40 231	94.62 47	71.27 282	70.93 275	89.18 245	72.47 35	96.04 168	65.62 315	76.89 276	91.49 252

Fast-Effi-MVS+		81.14 186	80.01 192	84.51 182	90.24 158	65.86 177	94.12 79	89.15 319	73.81 210	75.37 210	88.26 261	57.26 213	94.53 256	66.97 298	84.92 174	93.15 199

HQP-MVS		81.14 186	80.64 181	82.64 249	87.54 250	63.66 256	94.06 80	91.70 184	79.80 88	74.18 225	90.30 217	51.63 286	95.61 202	77.63 191	78.90 254	88.63 298

hse-mvs2		81.12 188	81.11 172	81.16 297	86.52 285	57.48 387	89.40 312	91.16 208	81.45 54	82.73 107	90.49 212	60.11 168	94.58 249	87.69 71	60.41 409	91.41 255

SR-MVS-dyc-post		81.06 189	80.70 179	82.15 268	92.02 109	58.56 375	90.90 258	90.45 255	62.76 383	78.89 164	94.46 101	51.26 293	95.61 202	78.77 184	86.77 148	92.28 232

HyFIR lowres test		81.03 190	79.56 202	85.43 129	87.81 244	68.11 104	90.18 288	90.01 284	70.65 295	72.95 243	86.06 298	63.61 117	94.50 258	75.01 209	79.75 242	93.67 182

nrg030		80.93 191	79.86 196	84.13 196	83.69 345	68.83 81	93.23 128	91.20 206	75.55 179	75.06 213	88.22 264	63.04 131	94.74 241	81.88 145	66.88 348	88.82 296

Vis-MVSNet		80.92 192	79.98 194	83.74 210	88.48 214	61.80 305	93.44 121	88.26 361	73.96 206	77.73 179	91.76 180	49.94 307	94.76 239	65.84 310	90.37 105	94.65 124
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test1111		80.84 193	80.02 191	83.33 228	87.87 241	60.76 332	92.62 160	86.86 384	77.86 135	75.73 201	91.39 192	46.35 350	94.70 247	72.79 230	88.68 125	94.52 133

UWE-MVS		80.81 194	81.01 174	80.20 322	89.33 178	57.05 393	91.91 202	94.71 42	75.67 177	75.01 214	89.37 241	63.13 129	91.44 375	67.19 295	82.80 204	92.12 240

IMVS_0407		80.80 195	79.39 208	85.00 151	88.54 203	64.75 204	88.40 334	90.80 241	76.73 163	73.95 234	90.18 220	51.55 288	95.81 184	73.47 220	80.95 226	94.43 144

1314		80.70 196	78.95 216	85.94 109	87.77 247	67.56 119	87.91 343	92.55 140	72.17 251	67.44 326	93.09 139	50.27 303	97.04 109	71.68 245	87.64 136	93.23 196

AstraMVS		80.66 197	79.79 198	83.28 232	85.07 319	61.64 312	92.19 183	90.58 253	79.40 103	74.77 220	90.18 220	45.93 356	95.61 202	83.04 130	76.96 275	92.60 219

tpmrst		80.57 198	79.14 214	84.84 158	90.10 161	68.28 97	81.70 407	89.72 297	77.63 143	75.96 199	79.54 388	64.94 93	92.71 331	75.43 204	77.28 272	93.55 186

1112_ss		80.56 199	79.83 197	82.77 244	88.65 200	60.78 330	92.29 178	88.36 354	72.58 237	72.46 256	94.95 87	65.09 90	93.42 308	66.38 304	77.71 263	94.10 161

VDDNet		80.50 200	78.26 224	87.21 51	86.19 291	69.79 48	94.48 60	91.31 198	60.42 404	79.34 159	90.91 205	38.48 391	96.56 139	82.16 139	81.05 225	95.27 81

BH-w/o		80.49 201	79.30 210	84.05 200	90.83 148	64.36 224	93.60 111	89.42 307	74.35 197	69.09 296	90.15 228	55.23 242	95.61 202	64.61 325	86.43 157	92.17 238

test_cas_vis1_n_1920		80.45 202	80.61 182	79.97 331	78.25 415	57.01 395	94.04 84	88.33 356	79.06 115	82.81 106	93.70 129	38.65 388	91.63 366	90.82 52	79.81 240	91.27 262

icg_test_0407_2		80.38 203	79.22 212	83.88 204	88.54 203	64.75 204	86.79 361	90.80 241	76.73 163	73.95 234	90.18 220	51.55 288	92.45 343	73.47 220	80.95 226	94.43 144

TAMVS		80.37 204	79.45 205	83.13 238	85.14 316	63.37 264	91.23 247	90.76 246	74.81 192	72.65 248	88.49 254	60.63 161	92.95 319	69.41 265	81.95 217	93.08 203

HQP_MVS		80.34 205	79.75 199	82.12 270	86.94 272	62.42 289	93.13 131	91.31 198	78.81 119	72.53 251	89.14 247	50.66 298	95.55 208	76.74 194	78.53 259	88.39 304

SDMVSNet		80.26 206	78.88 217	84.40 185	89.25 182	67.63 118	85.35 370	93.02 114	76.77 161	70.84 276	87.12 283	47.95 331	96.09 163	85.04 100	74.55 287	89.48 289

HPM-MVS_fast		80.25 207	79.55 204	82.33 260	91.55 129	59.95 355	91.32 242	89.16 318	65.23 361	74.71 222	93.07 141	47.81 333	95.74 190	74.87 213	88.23 128	91.31 260

ab-mvs		80.18 208	78.31 223	85.80 115	88.44 216	65.49 188	83.00 397	92.67 132	71.82 263	77.36 186	85.01 310	54.50 251	96.59 136	76.35 199	75.63 283	95.32 76

IS-MVSNet		80.14 209	79.41 206	82.33 260	87.91 237	60.08 353	91.97 198	88.27 359	72.90 232	71.44 272	91.73 182	61.44 150	93.66 299	62.47 344	86.53 154	93.24 195

test-LLR		80.10 210	79.56 202	81.72 279	86.93 274	61.17 322	92.70 153	91.54 189	71.51 278	75.62 203	86.94 287	53.83 262	92.38 345	72.21 238	84.76 177	91.60 250

PVSNet	73.49 8	80.05 211	78.63 219	84.31 189	90.92 145	64.97 200	92.47 172	91.05 227	79.18 109	72.43 257	90.51 211	37.05 408	94.06 278	68.06 282	86.00 158	93.90 176

UA-Net		80.02 212	79.65 200	81.11 300	89.33 178	57.72 382	86.33 366	89.00 334	77.44 147	81.01 126	89.15 246	59.33 183	95.90 174	61.01 351	84.28 184	89.73 285

test-mter		79.96 213	79.38 209	81.72 279	86.93 274	61.17 322	92.70 153	91.54 189	73.85 208	75.62 203	86.94 287	49.84 309	92.38 345	72.21 238	84.76 177	91.60 250

QAPM		79.95 214	77.39 245	87.64 35	89.63 170	71.41 20	93.30 126	93.70 83	65.34 360	67.39 329	91.75 181	47.83 332	98.96 19	57.71 367	89.81 112	92.54 222

UGNet		79.87 215	78.68 218	83.45 226	89.96 163	61.51 315	92.13 186	90.79 245	76.83 159	78.85 169	86.33 295	38.16 394	96.17 159	67.93 285	87.17 141	92.67 216
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
tpm2		79.80 216	77.95 231	85.34 136	88.28 224	68.26 98	81.56 409	91.42 195	70.11 300	77.59 183	80.50 374	67.40 67	94.26 269	67.34 292	77.35 270	93.51 188

thres200		79.66 217	78.33 222	83.66 218	92.54 95	65.82 179	93.06 133	96.31 3	74.90 191	73.30 240	88.66 252	59.67 176	95.61 202	47.84 411	78.67 257	89.56 288

CPTT-MVS		79.59 218	79.16 213	80.89 310	91.54 130	59.80 357	92.10 188	88.54 351	60.42 404	72.96 242	93.28 137	48.27 324	92.80 328	78.89 183	86.50 155	90.06 278

Test_1112_low_res		79.56 219	78.60 220	82.43 254	88.24 227	60.39 346	92.09 189	87.99 366	72.10 253	71.84 264	87.42 278	64.62 98	93.04 315	65.80 311	77.30 271	93.85 178

tttt0517		79.50 220	78.53 221	82.41 257	87.22 259	61.43 319	89.75 300	94.76 39	69.29 312	67.91 318	88.06 268	72.92 31	95.63 199	62.91 340	73.90 297	90.16 277

reproduce_monomvs		79.49 221	79.11 215	80.64 312	92.91 82	61.47 318	91.17 252	93.28 102	83.09 33	64.04 359	82.38 342	66.19 76	94.57 251	81.19 158	57.71 417	85.88 361

FIs		79.47 222	79.41 206	79.67 339	85.95 298	59.40 363	91.68 221	93.94 72	78.06 131	68.96 302	88.28 259	66.61 73	91.77 362	66.20 307	74.99 286	87.82 310

SSM_0404		79.46 223	77.65 235	84.91 154	88.37 222	67.04 138	89.59 301	87.03 380	67.99 330	75.45 208	89.32 242	47.98 328	95.34 218	71.23 248	81.90 218	92.34 228

BH-RMVSNet		79.46 223	77.65 235	84.89 155	91.68 125	65.66 180	93.55 113	88.09 364	72.93 229	73.37 239	91.12 203	46.20 354	96.12 161	56.28 373	85.61 165	92.91 209

viewdifsd2359ckpt11		79.42 225	77.95 231	83.81 207	83.87 342	63.85 241	89.54 306	87.38 373	77.39 150	74.94 215	89.95 233	51.11 294	94.72 242	79.52 172	67.90 340	92.88 212

viewmsd2359difaftdt		79.42 225	77.96 230	83.81 207	83.88 341	63.85 241	89.54 306	87.38 373	77.39 150	74.94 215	89.95 233	51.11 294	94.72 242	79.52 172	67.90 340	92.88 212

PCF-MVS	73.15 9	79.29 227	77.63 237	84.29 190	86.06 296	65.96 173	87.03 356	91.10 217	69.86 306	69.79 292	90.64 207	57.54 212	96.59 136	64.37 329	82.29 207	90.32 275
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Vis-MVSNet (Re-imp)		79.24 228	79.57 201	78.24 360	88.46 215	52.29 419	90.41 279	89.12 322	74.24 199	69.13 295	91.91 178	65.77 83	90.09 391	59.00 363	88.09 130	92.33 229

114514_t		79.17 229	77.67 234	83.68 216	95.32 30	65.53 186	92.85 147	91.60 188	63.49 374	67.92 317	90.63 209	46.65 347	95.72 196	67.01 297	83.54 196	89.79 283

FA-MVS(test-final)		79.12 230	77.23 247	84.81 162	90.54 151	63.98 240	81.35 412	91.71 181	71.09 286	74.85 219	82.94 335	52.85 273	97.05 106	67.97 283	81.73 221	93.41 190

SSM_0407		79.09 231	77.21 248	84.75 166	88.50 208	66.98 143	89.21 317	87.03 380	67.99 330	74.12 229	89.32 242	47.98 328	95.29 223	71.23 248	79.52 243	91.98 243

VPA-MVSNet		79.03 232	78.00 228	82.11 273	85.95 298	64.48 215	93.22 129	94.66 45	75.05 189	74.04 233	84.95 311	52.17 280	93.52 301	74.90 212	67.04 347	88.32 306

OPM-MVS		79.00 233	78.09 226	81.73 278	83.52 348	63.83 244	91.64 223	90.30 268	76.36 172	71.97 263	89.93 235	46.30 353	95.17 226	75.10 207	77.70 264	86.19 349
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
EI-MVSNet		78.97 234	78.22 225	81.25 294	85.33 309	62.73 284	89.53 309	93.21 104	72.39 244	72.14 260	90.13 229	60.99 154	94.72 242	67.73 287	72.49 306	86.29 346

AdaColmap		78.94 235	77.00 252	84.76 165	96.34 17	65.86 177	92.66 159	87.97 368	62.18 388	70.56 278	92.37 159	43.53 368	97.35 85	64.50 328	82.86 201	91.05 265

GeoE		78.90 236	77.43 241	83.29 231	88.95 193	62.02 299	92.31 177	86.23 392	70.24 299	71.34 273	89.27 244	54.43 255	94.04 281	63.31 336	80.81 233	93.81 179

miper_enhance_ethall		78.86 237	77.97 229	81.54 285	88.00 236	65.17 194	91.41 229	89.15 319	75.19 187	68.79 305	83.98 325	67.17 68	92.82 326	72.73 232	65.30 358	86.62 337

VPNet		78.82 238	77.53 240	82.70 247	84.52 329	66.44 160	93.93 90	92.23 148	80.46 71	72.60 249	88.38 258	49.18 317	93.13 314	72.47 236	63.97 378	88.55 301

EPNet_dtu		78.80 239	79.26 211	77.43 368	88.06 232	49.71 436	91.96 199	91.95 166	77.67 140	76.56 196	91.28 196	58.51 197	90.20 389	56.37 372	80.95 226	92.39 226
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tfpn200view9		78.79 240	77.43 241	82.88 242	92.21 101	64.49 213	92.05 192	96.28 4	73.48 217	71.75 266	88.26 261	60.07 170	95.32 219	45.16 424	77.58 266	88.83 294

TR-MVS		78.77 241	77.37 246	82.95 241	90.49 153	60.88 328	93.67 107	90.07 279	70.08 303	74.51 223	91.37 193	45.69 357	95.70 197	60.12 357	80.32 237	92.29 231

thres400		78.68 242	77.43 241	82.43 254	92.21 101	64.49 213	92.05 192	96.28 4	73.48 217	71.75 266	88.26 261	60.07 170	95.32 219	45.16 424	77.58 266	87.48 315

BH-untuned		78.68 242	77.08 249	83.48 225	89.84 165	63.74 247	92.70 153	88.59 348	71.57 275	66.83 336	88.65 253	51.75 284	95.39 214	59.03 362	84.77 176	91.32 259

OMC-MVS		78.67 244	77.91 233	80.95 307	85.76 304	57.40 389	88.49 332	88.67 345	73.85 208	72.43 257	92.10 168	49.29 316	94.55 255	72.73 232	77.89 262	90.91 269

tpm		78.58 245	77.03 250	83.22 235	85.94 300	64.56 211	83.21 393	91.14 212	78.31 128	73.67 237	79.68 386	64.01 107	92.09 356	66.07 308	71.26 316	93.03 205

OpenMVS	70.45 11	78.54 246	75.92 271	86.41 94	85.93 301	71.68 18	92.74 150	92.51 141	66.49 346	64.56 353	91.96 174	43.88 367	98.10 44	54.61 378	90.65 99	89.44 291

EPMVS		78.49 247	75.98 270	86.02 106	91.21 139	69.68 53	80.23 421	91.20 206	75.25 186	72.48 255	78.11 397	54.65 250	93.69 298	57.66 368	83.04 200	94.69 118

AUN-MVS		78.37 248	77.43 241	81.17 296	86.60 282	57.45 388	89.46 311	91.16 208	74.11 201	74.40 224	90.49 212	55.52 239	94.57 251	74.73 214	60.43 408	91.48 253

thres100view900		78.37 248	77.01 251	82.46 253	91.89 119	63.21 270	91.19 251	96.33 1	72.28 247	70.45 281	87.89 270	60.31 165	95.32 219	45.16 424	77.58 266	88.83 294

GA-MVS		78.33 250	76.23 266	84.65 174	83.65 346	66.30 164	91.44 228	90.14 277	76.01 174	70.32 283	84.02 324	42.50 372	94.72 242	70.98 251	77.00 274	92.94 208

cascas		78.18 251	75.77 273	85.41 130	87.14 262	69.11 71	92.96 140	91.15 211	66.71 344	70.47 279	86.07 297	37.49 402	96.48 145	70.15 259	79.80 241	90.65 271

UniMVSNet_NR-MVSNet		78.15 252	77.55 239	79.98 329	84.46 332	60.26 348	92.25 179	93.20 106	77.50 146	68.88 303	86.61 290	66.10 78	92.13 354	66.38 304	62.55 386	87.54 313

LuminaMVS		78.14 253	76.66 256	82.60 251	80.82 376	64.64 210	89.33 313	90.45 255	68.25 328	74.73 221	85.51 306	41.15 378	94.14 272	78.96 181	80.69 235	89.04 292

IMVS_0404		78.11 254	76.29 265	83.59 219	88.54 203	64.75 204	84.63 375	90.80 241	76.73 163	61.16 382	90.18 220	40.17 382	91.58 368	73.47 220	80.95 226	94.43 144

thres600view7		78.00 255	76.66 256	82.03 275	91.93 115	63.69 254	91.30 243	96.33 1	72.43 242	70.46 280	87.89 270	60.31 165	94.92 235	42.64 436	76.64 277	87.48 315

FC-MVSNet-test		77.99 256	78.08 227	77.70 363	84.89 322	55.51 405	90.27 285	93.75 81	76.87 156	66.80 337	87.59 275	65.71 84	90.23 388	62.89 341	73.94 295	87.37 318

Anonymous202405211		77.96 257	75.33 279	85.87 111	93.73 57	64.52 212	94.85 50	85.36 405	62.52 386	76.11 198	90.18 220	29.43 441	97.29 89	68.51 276	77.24 273	95.81 53

cl22		77.94 258	76.78 254	81.42 287	87.57 249	64.93 202	90.67 270	88.86 338	72.45 241	67.63 324	82.68 339	64.07 105	92.91 324	71.79 241	65.30 358	86.44 339

XXY-MVS		77.94 258	76.44 259	82.43 254	82.60 358	64.44 217	92.01 194	91.83 175	73.59 216	70.00 288	85.82 302	54.43 255	94.76 239	69.63 262	68.02 339	88.10 308

MS-PatchMatch		77.90 260	76.50 258	82.12 270	85.99 297	69.95 42	91.75 215	92.70 128	73.97 205	62.58 376	84.44 318	41.11 379	95.78 187	63.76 333	92.17 71	80.62 427

usedtu_dtu_shiyan1		77.89 261	76.39 262	82.40 258	81.92 366	67.01 141	91.94 200	93.00 117	77.01 153	68.44 312	84.15 320	54.78 248	93.25 310	65.76 312	70.53 319	86.94 327

FE-MVSNET3		77.89 261	76.39 262	82.40 258	81.92 366	67.01 141	91.94 200	93.00 117	77.01 153	68.44 312	84.15 320	54.78 248	93.25 310	65.76 312	70.53 319	86.94 327

FMVSNet3		77.73 263	76.04 269	82.80 243	91.20 140	68.99 77	91.87 204	91.99 164	73.35 219	67.04 332	83.19 334	56.62 226	92.14 353	59.80 359	69.34 325	87.28 321

VortexMVS		77.62 264	76.44 259	81.13 298	88.58 201	63.73 249	91.24 246	91.30 202	77.81 136	65.76 342	81.97 348	49.69 311	93.72 294	76.40 198	65.26 361	85.94 359

miper_ehance_all_eth		77.60 265	76.44 259	81.09 304	85.70 306	64.41 220	90.65 271	88.64 347	72.31 245	67.37 330	82.52 340	64.77 97	92.64 337	70.67 255	65.30 358	86.24 348

UniMVSNet (Re)		77.58 266	76.78 254	79.98 329	84.11 338	60.80 329	91.76 213	93.17 108	76.56 169	69.93 291	84.78 313	63.32 124	92.36 347	64.89 322	62.51 388	86.78 331

PatchmatchNet		77.46 267	74.63 286	85.96 108	89.55 173	70.35 35	79.97 426	89.55 302	72.23 248	70.94 274	76.91 410	57.03 216	92.79 329	54.27 380	81.17 224	94.74 114
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v2v482		77.42 268	75.65 275	82.73 245	80.38 384	67.13 135	91.85 206	90.23 273	75.09 188	69.37 293	83.39 331	53.79 264	94.44 259	71.77 242	65.00 365	86.63 336

CHOSEN 280x420		77.35 269	76.95 253	78.55 355	87.07 264	62.68 285	69.71 458	82.95 428	68.80 321	71.48 271	87.27 282	66.03 79	84.00 441	76.47 197	82.81 203	88.95 293

PS-MVSNAJss		77.26 270	76.31 264	80.13 324	80.64 380	59.16 368	90.63 274	91.06 224	72.80 233	68.58 309	84.57 316	53.55 266	93.96 286	72.97 226	71.96 310	87.27 322

gg-mvs-nofinetune		77.18 271	74.31 293	85.80 115	91.42 132	68.36 94	71.78 452	94.72 41	49.61 449	77.12 190	45.92 479	77.41 8	93.98 285	67.62 288	93.16 59	95.05 93

WB-MVSnew		77.14 272	76.18 268	80.01 328	86.18 292	63.24 268	91.26 244	94.11 69	71.72 267	73.52 238	87.29 281	45.14 362	93.00 317	56.98 370	79.42 246	83.80 387

MVP-Stereo		77.12 273	76.23 266	79.79 336	81.72 368	66.34 163	89.29 314	90.88 236	70.56 296	62.01 379	82.88 336	49.34 314	94.13 273	65.55 317	93.80 47	78.88 443
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
sd_testset		77.08 274	75.37 277	82.20 266	89.25 182	62.11 298	82.06 404	89.09 324	76.77 161	70.84 276	87.12 283	41.43 377	95.01 230	67.23 294	74.55 287	89.48 289

MonoMVSNet		76.99 275	75.08 282	82.73 245	83.32 350	63.24 268	86.47 365	86.37 388	79.08 113	66.31 340	79.30 390	49.80 310	91.72 363	79.37 174	65.70 356	93.23 196

dmvs_re		76.93 276	75.36 278	81.61 283	87.78 246	60.71 336	80.00 425	87.99 366	79.42 102	69.02 299	89.47 239	46.77 345	94.32 263	63.38 335	74.45 290	89.81 282

X-MVStestdata		76.86 277	74.13 299	85.05 148	93.22 70	63.78 245	92.92 142	92.66 133	73.99 203	78.18 175	10.19 494	55.25 240	97.41 81	79.16 177	91.58 83	93.95 169

DU-MVS		76.86 277	75.84 272	79.91 332	82.96 354	60.26 348	91.26 244	91.54 189	76.46 171	68.88 303	86.35 293	56.16 231	92.13 354	66.38 304	62.55 386	87.35 319

Anonymous20240529		76.84 279	74.15 298	84.88 156	91.02 142	64.95 201	93.84 99	91.09 218	53.57 437	73.00 241	87.42 278	35.91 412	97.32 87	69.14 270	72.41 308	92.36 227

UWE-MVS-28		76.83 280	77.60 238	74.51 398	84.58 328	50.34 432	88.22 337	94.60 49	74.46 194	66.66 338	88.98 251	62.53 137	85.50 433	57.55 369	80.80 234	87.69 312

c3_l		76.83 280	75.47 276	80.93 308	85.02 320	64.18 232	90.39 280	88.11 363	71.66 268	66.65 339	81.64 354	63.58 120	92.56 338	69.31 267	62.86 383	86.04 354

WR-MVS		76.76 282	75.74 274	79.82 335	84.60 326	62.27 295	92.60 163	92.51 141	76.06 173	67.87 321	85.34 307	56.76 222	90.24 387	62.20 345	63.69 380	86.94 327

v1144		76.73 283	74.88 283	82.27 262	80.23 388	66.60 157	91.68 221	90.21 276	73.69 213	69.06 298	81.89 349	52.73 276	94.40 261	69.21 268	65.23 362	85.80 362

IterMVS-LS		76.49 284	75.18 281	80.43 316	84.49 331	62.74 283	90.64 272	88.80 340	72.40 243	65.16 348	81.72 352	60.98 155	92.27 351	67.74 286	64.65 370	86.29 346
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
V42		76.46 285	74.55 289	82.19 267	79.14 402	67.82 112	90.26 286	89.42 307	73.75 211	68.63 308	81.89 349	51.31 291	94.09 275	71.69 244	64.84 366	84.66 379

Elysia		76.45 286	74.17 296	83.30 229	80.43 382	64.12 233	89.58 302	90.83 238	61.78 396	72.53 251	85.92 300	34.30 419	94.81 237	68.10 280	84.01 190	90.97 266

StellarMVS		76.45 286	74.17 296	83.30 229	80.43 382	64.12 233	89.58 302	90.83 238	61.78 396	72.53 251	85.92 300	34.30 419	94.81 237	68.10 280	84.01 190	90.97 266

mamba_0408		76.22 288	73.37 310	84.77 163	88.50 208	66.98 143	58.80 479	86.18 394	69.12 317	74.12 229	89.01 249	47.50 335	95.35 216	67.57 289	79.52 243	91.98 243

v148		76.19 289	74.47 291	81.36 290	80.05 390	64.44 217	91.75 215	90.23 273	73.68 214	67.13 331	80.84 369	55.92 236	93.86 293	68.95 272	61.73 397	85.76 365

Effi-MVS+-dtu		76.14 290	75.28 280	78.72 354	83.22 351	55.17 407	89.87 297	87.78 370	75.42 182	67.98 316	81.43 358	45.08 363	92.52 340	75.08 208	71.63 311	88.48 302

cl____		76.07 291	74.67 284	80.28 319	85.15 315	61.76 308	90.12 289	88.73 342	71.16 283	65.43 345	81.57 356	61.15 152	92.95 319	66.54 301	62.17 390	86.13 352

DIV-MVS_self_test		76.07 291	74.67 284	80.28 319	85.14 316	61.75 309	90.12 289	88.73 342	71.16 283	65.42 346	81.60 355	61.15 152	92.94 323	66.54 301	62.16 392	86.14 350

FMVSNet2		76.07 291	74.01 301	82.26 264	88.85 194	67.66 116	91.33 241	91.61 187	70.84 290	65.98 341	82.25 344	48.03 325	92.00 358	58.46 364	68.73 333	87.10 324

v144192		76.05 294	74.03 300	82.12 270	79.50 396	66.55 159	91.39 233	89.71 298	72.30 246	68.17 314	81.33 361	51.75 284	94.03 283	67.94 284	64.19 373	85.77 363

NR-MVSNet		76.05 294	74.59 287	80.44 315	82.96 354	62.18 297	90.83 262	91.73 179	77.12 152	60.96 384	86.35 293	59.28 184	91.80 361	60.74 352	61.34 401	87.35 319

v1192		75.98 296	73.92 302	82.15 268	79.73 392	66.24 166	91.22 248	89.75 292	72.67 235	68.49 310	81.42 359	49.86 308	94.27 267	67.08 296	65.02 364	85.95 357

FE-MVS		75.97 297	73.02 316	84.82 159	89.78 166	65.56 184	77.44 437	91.07 223	64.55 363	72.66 247	79.85 384	46.05 355	96.69 134	54.97 377	80.82 232	92.21 237

eth_miper_zixun_eth		75.96 298	74.40 292	80.66 311	84.66 325	63.02 274	89.28 315	88.27 359	71.88 259	65.73 343	81.65 353	59.45 180	92.81 327	68.13 279	60.53 406	86.14 350

TranMVSNet+NR-MVSNet		75.86 299	74.52 290	79.89 333	82.44 360	60.64 339	91.37 236	91.37 196	76.63 167	67.65 323	86.21 296	52.37 279	91.55 369	61.84 347	60.81 404	87.48 315

SCA		75.82 300	72.76 320	85.01 150	86.63 281	70.08 38	81.06 414	89.19 316	71.60 274	70.01 287	77.09 408	45.53 358	90.25 384	60.43 354	73.27 299	94.68 120

LPG-MVS_test		75.82 300	74.58 288	79.56 343	84.31 335	59.37 364	90.44 277	89.73 295	69.49 309	64.86 349	88.42 256	38.65 388	94.30 265	72.56 234	72.76 303	85.01 376

GBi-Net		75.65 302	73.83 303	81.10 301	88.85 194	65.11 196	90.01 293	90.32 264	70.84 290	67.04 332	80.25 379	48.03 325	91.54 370	59.80 359	69.34 325	86.64 333

test1		75.65 302	73.83 303	81.10 301	88.85 194	65.11 196	90.01 293	90.32 264	70.84 290	67.04 332	80.25 379	48.03 325	91.54 370	59.80 359	69.34 325	86.64 333

v1921920		75.63 304	73.49 308	82.06 274	79.38 397	66.35 162	91.07 256	89.48 303	71.98 254	67.99 315	81.22 364	49.16 319	93.90 289	66.56 300	64.56 371	85.92 360

ACMP	71.68 10	75.58 305	74.23 295	79.62 341	84.97 321	59.64 359	90.80 263	89.07 326	70.39 297	62.95 372	87.30 280	38.28 392	93.87 291	72.89 227	71.45 314	85.36 372
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v8		75.35 306	73.26 314	81.61 283	80.67 379	66.82 149	89.54 306	89.27 312	71.65 269	63.30 367	80.30 378	54.99 246	94.06 278	67.33 293	62.33 389	83.94 385

tpm cat1		75.30 307	72.21 329	84.58 179	88.52 207	67.77 113	78.16 435	88.02 365	61.88 394	68.45 311	76.37 419	60.65 160	94.03 283	53.77 384	74.11 293	91.93 246

PLC	68.80 14	75.23 308	73.68 306	79.86 334	92.93 81	58.68 373	90.64 272	88.30 357	60.90 401	64.43 357	90.53 210	42.38 373	94.57 251	56.52 371	76.54 278	86.33 345
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v1240		75.21 309	72.98 318	81.88 276	79.20 399	66.00 171	90.75 266	89.11 323	71.63 273	67.41 328	81.22 364	47.36 337	93.87 291	65.46 318	64.72 369	85.77 363

blend_shiyan4		75.18 310	73.00 317	81.69 281	75.62 434	64.75 204	91.78 210	91.06 224	65.89 354	61.35 381	77.39 402	62.16 142	93.71 295	68.18 277	63.60 381	86.61 338

Fast-Effi-MVS+-dtu		75.04 311	73.37 310	80.07 325	80.86 374	59.52 362	91.20 250	85.38 404	71.90 257	65.20 347	84.84 312	41.46 376	92.97 318	66.50 303	72.96 302	87.73 311

dp		75.01 312	72.09 330	83.76 209	89.28 181	66.22 167	79.96 427	89.75 292	71.16 283	67.80 322	77.19 407	51.81 282	92.54 339	50.39 394	71.44 315	92.51 224

TAPA-MVS	70.22 12	74.94 313	73.53 307	79.17 349	90.40 155	52.07 420	89.19 319	89.61 301	62.69 385	70.07 286	92.67 151	48.89 322	94.32 263	38.26 451	79.97 239	91.12 264
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SSC-MVS3.2		74.92 314	73.32 313	79.74 338	86.53 284	60.31 347	89.03 324	92.70 128	78.61 124	68.98 301	83.34 332	41.93 375	92.23 352	52.77 388	65.97 354	86.69 332

SSM_04072		74.86 315	73.37 310	79.35 346	88.50 208	66.98 143	58.80 479	86.18 394	69.12 317	74.12 229	89.01 249	47.50 335	79.09 463	67.57 289	79.52 243	91.98 243

v10		74.77 316	72.54 326	81.46 286	80.33 386	66.71 154	89.15 320	89.08 325	70.94 288	63.08 370	79.86 383	52.52 277	94.04 281	65.70 314	62.17 390	83.64 388

XVG-OURS-SEG-HR		74.70 317	73.08 315	79.57 342	78.25 415	57.33 390	80.49 417	87.32 375	63.22 378	68.76 306	90.12 231	44.89 364	91.59 367	70.55 257	74.09 294	89.79 283

ACMM	69.62 13	74.34 318	72.73 322	79.17 349	84.25 337	57.87 380	90.36 282	89.93 286	63.17 380	65.64 344	86.04 299	37.79 400	94.10 274	65.89 309	71.52 313	85.55 368
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CNLPA		74.31 319	72.30 328	80.32 317	91.49 131	61.66 311	90.85 261	80.72 434	56.67 428	63.85 362	90.64 207	46.75 346	90.84 378	53.79 383	75.99 282	88.47 303

XVG-OURS		74.25 320	72.46 327	79.63 340	78.45 413	57.59 386	80.33 419	87.39 372	63.86 370	68.76 306	89.62 238	40.50 381	91.72 363	69.00 271	74.25 292	89.58 286

test_fmvs1		74.07 321	73.69 305	75.22 388	78.91 406	47.34 449	89.06 323	74.69 451	63.68 373	79.41 158	91.59 188	24.36 452	87.77 414	85.22 97	76.26 280	90.55 274

CVMVSNet		74.04 322	74.27 294	73.33 408	85.33 309	43.94 463	89.53 309	88.39 353	54.33 436	70.37 282	90.13 229	49.17 318	84.05 439	61.83 348	79.36 248	91.99 242

Baseline_NR-MVSNet		73.99 323	72.83 319	77.48 367	80.78 377	59.29 367	91.79 208	84.55 413	68.85 320	68.99 300	80.70 370	56.16 231	92.04 357	62.67 342	60.98 403	81.11 421

pmmvs4		73.92 324	71.81 334	80.25 321	79.17 400	65.24 192	87.43 352	87.26 378	67.64 337	63.46 365	83.91 326	48.96 321	91.53 373	62.94 339	65.49 357	83.96 384

D2MVS		73.80 325	72.02 331	79.15 351	79.15 401	62.97 275	88.58 331	90.07 279	72.94 228	59.22 399	78.30 394	42.31 374	92.70 333	65.59 316	72.00 309	81.79 416

SD_0403		73.79 326	73.48 309	74.69 395	85.33 309	45.56 459	83.80 382	85.57 403	76.55 170	62.96 371	88.45 255	50.62 300	87.59 418	48.80 404	79.28 252	90.92 268

CR-MVSNet		73.79 326	70.82 342	82.70 247	83.15 352	67.96 107	70.25 455	84.00 418	73.67 215	69.97 289	72.41 436	57.82 209	89.48 397	52.99 387	73.13 300	90.64 272

test_djsdf		73.76 328	72.56 325	77.39 369	77.00 427	53.93 413	89.07 321	90.69 247	65.80 355	63.92 360	82.03 347	43.14 371	92.67 334	72.83 228	68.53 334	85.57 367

pmmvs5		73.35 329	71.52 336	78.86 353	78.64 410	60.61 340	91.08 254	86.90 382	67.69 334	63.32 366	83.64 327	44.33 366	90.53 381	62.04 346	66.02 353	85.46 370

Anonymous20231211		73.08 330	70.39 346	81.13 298	90.62 150	63.33 265	91.40 231	90.06 281	51.84 442	64.46 356	80.67 372	36.49 410	94.07 277	63.83 332	64.17 374	85.98 356

tt0805		73.07 331	70.73 343	80.07 325	78.37 414	57.05 393	87.78 346	92.18 155	61.23 400	67.04 332	86.49 292	31.35 433	94.58 249	65.06 321	67.12 346	88.57 300

miper_lstm_enhance		73.05 332	71.73 335	77.03 374	83.80 343	58.32 377	81.76 405	88.88 336	69.80 307	61.01 383	78.23 396	57.19 214	87.51 420	65.34 319	59.53 411	85.27 375

jajsoiax		73.05 332	71.51 337	77.67 364	77.46 424	54.83 409	88.81 327	90.04 282	69.13 316	62.85 374	83.51 329	31.16 434	92.75 330	70.83 252	69.80 321	85.43 371

LCM-MVSNet-Re		72.93 334	71.84 333	76.18 383	88.49 212	48.02 444	80.07 424	70.17 466	73.96 206	52.25 433	80.09 382	49.98 306	88.24 408	67.35 291	84.23 185	92.28 232

pm-mvs1		72.89 335	71.09 339	78.26 359	79.10 403	57.62 384	90.80 263	89.30 311	67.66 335	62.91 373	81.78 351	49.11 320	92.95 319	60.29 356	58.89 414	84.22 383

tpmvs		72.88 336	69.76 352	82.22 265	90.98 143	67.05 137	78.22 434	88.30 357	63.10 381	64.35 358	74.98 426	55.09 245	94.27 267	43.25 430	69.57 324	85.34 373

test0.0.03 1		72.76 337	72.71 323	72.88 412	80.25 387	47.99 445	91.22 248	89.45 305	71.51 278	62.51 377	87.66 273	53.83 262	85.06 435	50.16 396	67.84 344	85.58 366

UniMVSNet_ETH3D		72.74 338	70.53 345	79.36 345	78.62 411	56.64 397	85.01 372	89.20 315	63.77 371	64.84 351	84.44 318	34.05 421	91.86 360	63.94 331	70.89 318	89.57 287

mvs_tets		72.71 339	71.11 338	77.52 365	77.41 425	54.52 411	88.45 333	89.76 291	68.76 323	62.70 375	83.26 333	29.49 440	92.71 331	70.51 258	69.62 323	85.34 373

FMVSNet1		72.71 339	69.91 350	81.10 301	83.60 347	65.11 196	90.01 293	90.32 264	63.92 369	63.56 364	80.25 379	36.35 411	91.54 370	54.46 379	66.75 349	86.64 333

test_fmvs1_n		72.69 341	71.92 332	74.99 393	71.15 453	47.08 451	87.34 354	75.67 446	63.48 375	78.08 177	91.17 202	20.16 466	87.87 411	84.65 106	75.57 284	90.01 280

IterMVS		72.65 342	70.83 340	78.09 361	82.17 362	62.96 276	87.64 350	86.28 390	71.56 276	60.44 390	78.85 392	45.42 360	86.66 424	63.30 337	61.83 394	84.65 380
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
myMVS_eth3d		72.58 343	72.74 321	72.10 420	87.87 241	49.45 438	88.07 339	89.01 330	72.91 230	63.11 368	88.10 265	63.63 115	85.54 430	32.73 467	69.23 328	81.32 419

wanda-best-256-512		72.42 344	69.43 354	81.37 288	75.39 435	64.24 229	91.58 224	91.09 218	66.36 347	60.64 386	76.86 411	47.20 339	93.47 303	64.80 323	50.98 438	86.40 340

FE-blended-shiyan7		72.42 344	69.43 354	81.37 288	75.39 435	64.24 229	91.58 224	91.09 218	66.36 347	60.64 386	76.86 411	47.20 339	93.47 303	64.80 323	50.98 438	86.40 340

blended_shiyan8		72.26 346	69.25 358	81.29 292	75.23 440	64.03 236	91.36 239	91.04 228	66.11 352	60.42 391	76.73 415	46.79 344	93.45 306	64.58 327	51.00 437	86.37 343

blended_shiyan6		72.26 346	69.26 357	81.27 293	75.24 439	64.00 239	91.37 236	91.06 224	66.12 351	60.34 392	76.75 414	46.82 342	93.45 306	64.61 325	50.98 438	86.37 343

PatchMatch-RL		72.06 348	69.98 347	78.28 358	89.51 174	55.70 404	83.49 386	83.39 426	61.24 399	63.72 363	82.76 337	34.77 416	93.03 316	53.37 386	77.59 265	86.12 353

PVSNet_0	68.08 15	71.81 349	68.32 365	82.27 262	84.68 323	62.31 294	88.68 329	90.31 267	75.84 175	57.93 411	80.65 373	37.85 399	94.19 270	69.94 260	29.05 482	90.31 276

MIMVSNet		71.64 350	68.44 363	81.23 295	81.97 365	64.44 217	73.05 449	88.80 340	69.67 308	64.59 352	74.79 428	32.79 425	87.82 412	53.99 381	76.35 279	91.42 254

test_vis1_n		71.63 351	70.73 343	74.31 402	69.63 460	47.29 450	86.91 358	72.11 459	63.21 379	75.18 212	90.17 226	20.40 464	85.76 429	84.59 107	74.42 291	89.87 281

IterMVS-SCA-FT		71.55 352	69.97 348	76.32 381	81.48 370	60.67 338	87.64 350	85.99 397	66.17 350	59.50 397	78.88 391	45.53 358	83.65 443	62.58 343	61.93 393	84.63 382

v7n		71.31 353	68.65 360	79.28 347	76.40 429	60.77 331	86.71 362	89.45 305	64.17 368	58.77 404	78.24 395	44.59 365	93.54 300	57.76 366	61.75 396	83.52 391

anonymousdsp		71.14 354	69.37 356	76.45 380	72.95 448	54.71 410	84.19 379	88.88 336	61.92 393	62.15 378	79.77 385	38.14 395	91.44 375	68.90 273	67.45 345	83.21 397

usedtu_blend_shiyan5		71.06 355	67.54 368	81.62 282	75.39 435	64.75 204	85.67 368	86.47 387	56.48 429	60.64 386	76.85 413	47.20 339	93.71 295	68.18 277	50.98 438	86.40 340

F-COLMAP		70.66 356	68.44 363	77.32 370	86.37 289	55.91 402	88.00 341	86.32 389	56.94 426	57.28 415	88.07 267	33.58 423	92.49 341	51.02 391	68.37 335	83.55 389

WR-MVS_H		70.59 357	69.94 349	72.53 414	81.03 373	51.43 424	87.35 353	92.03 163	67.38 338	60.23 394	80.70 370	55.84 237	83.45 446	46.33 419	58.58 416	82.72 404

CP-MVSNet		70.50 358	69.91 350	72.26 417	80.71 378	51.00 428	87.23 355	90.30 268	67.84 333	59.64 396	82.69 338	50.23 304	82.30 454	51.28 390	59.28 412	83.46 393

RPMNet		70.42 359	65.68 380	84.63 177	83.15 352	67.96 107	70.25 455	90.45 255	46.83 458	69.97 289	65.10 461	56.48 230	95.30 222	35.79 456	73.13 300	90.64 272

testing3		70.38 360	70.83 340	69.03 434	85.82 303	43.93 464	90.72 269	90.56 254	68.06 329	60.24 393	86.82 289	64.83 95	84.12 437	26.33 475	64.10 375	79.04 441

tfpnnormal		70.10 361	67.36 370	78.32 357	83.45 349	60.97 327	88.85 325	92.77 126	64.85 362	60.83 385	78.53 393	43.52 369	93.48 302	31.73 470	61.70 398	80.52 428

TransMVSNet (Re)		70.07 362	67.66 367	77.31 371	80.62 381	59.13 369	91.78 210	84.94 409	65.97 353	60.08 395	80.44 375	50.78 297	91.87 359	48.84 403	45.46 455	80.94 423

CL-MVSNet_self_test		69.92 363	68.09 366	75.41 386	73.25 447	55.90 403	90.05 292	89.90 287	69.96 304	61.96 380	76.54 416	51.05 296	87.64 415	49.51 400	50.59 443	82.70 406

DP-MVS		69.90 364	66.48 372	80.14 323	95.36 29	62.93 277	89.56 304	76.11 444	50.27 448	57.69 413	85.23 308	39.68 384	95.73 191	33.35 461	71.05 317	81.78 417

PS-CasMVS		69.86 365	69.13 359	72.07 421	80.35 385	50.57 431	87.02 357	89.75 292	67.27 339	59.19 400	82.28 343	46.58 348	82.24 455	50.69 393	59.02 413	83.39 395

Syy-MVS		69.65 366	69.52 353	70.03 429	87.87 241	43.21 465	88.07 339	89.01 330	72.91 230	63.11 368	88.10 265	45.28 361	85.54 430	22.07 480	69.23 328	81.32 419

MSDG		69.54 367	65.73 379	80.96 306	85.11 318	63.71 251	84.19 379	83.28 427	56.95 425	54.50 422	84.03 323	31.50 431	96.03 169	42.87 434	69.13 330	83.14 399

PEN-MVS		69.46 368	68.56 361	72.17 419	79.27 398	49.71 436	86.90 359	89.24 313	67.24 342	59.08 401	82.51 341	47.23 338	83.54 445	48.42 406	57.12 418	83.25 396

LS3D		69.17 369	66.40 374	77.50 366	91.92 116	56.12 400	85.12 371	80.37 436	46.96 456	56.50 417	87.51 277	37.25 403	93.71 295	32.52 469	79.40 247	82.68 407

PatchT		69.11 370	65.37 384	80.32 317	82.07 364	63.68 255	67.96 465	87.62 371	50.86 446	69.37 293	65.18 460	57.09 215	88.53 404	41.59 440	66.60 350	88.74 297

KD-MVS_2432*1600		69.03 371	66.37 375	77.01 375	85.56 307	61.06 325	81.44 410	90.25 271	67.27 339	58.00 409	76.53 417	54.49 252	87.63 416	48.04 408	35.77 473	82.34 410

miper_refine_blended		69.03 371	66.37 375	77.01 375	85.56 307	61.06 325	81.44 410	90.25 271	67.27 339	58.00 409	76.53 417	54.49 252	87.63 416	48.04 408	35.77 473	82.34 410

mvsany_test1		68.77 373	68.56 361	69.39 432	73.57 446	45.88 458	80.93 415	60.88 480	59.65 410	71.56 269	90.26 219	43.22 370	75.05 467	74.26 217	62.70 385	87.25 323

ACMH	63.93 17	68.62 374	64.81 386	80.03 327	85.22 314	63.25 267	87.72 347	84.66 411	60.83 402	51.57 437	79.43 389	27.29 447	94.96 232	41.76 438	64.84 366	81.88 415
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EG-PatchMatch MVS		68.55 375	65.41 383	77.96 362	78.69 409	62.93 277	89.86 298	89.17 317	60.55 403	50.27 443	77.73 401	22.60 460	94.06 278	47.18 415	72.65 305	76.88 455

ADS-MVSNet		68.54 376	64.38 393	81.03 305	88.06 232	66.90 148	68.01 463	84.02 417	57.57 419	64.48 354	69.87 448	38.68 386	89.21 399	40.87 442	67.89 342	86.97 325

DTE-MVSNet		68.46 377	67.33 371	71.87 423	77.94 419	49.00 442	86.16 367	88.58 349	66.36 347	58.19 406	82.21 345	46.36 349	83.87 442	44.97 427	55.17 425	82.73 403

mmtdpeth		68.33 378	66.37 375	74.21 403	82.81 357	51.73 421	84.34 377	80.42 435	67.01 343	71.56 269	68.58 452	30.52 438	92.35 348	75.89 201	36.21 471	78.56 448

our_test_3		68.29 379	64.69 388	79.11 352	78.92 404	64.85 203	88.40 334	85.06 407	60.32 406	52.68 431	76.12 421	40.81 380	89.80 396	44.25 429	55.65 423	82.67 408

Patchmatch-RL test		68.17 380	64.49 391	79.19 348	71.22 452	53.93 413	70.07 457	71.54 463	69.22 313	56.79 416	62.89 465	56.58 227	88.61 401	69.53 264	52.61 433	95.03 95

XVG-ACMP-BASELINE		68.04 381	65.53 382	75.56 385	74.06 445	52.37 418	78.43 431	85.88 398	62.03 391	58.91 403	81.21 366	20.38 465	91.15 377	60.69 353	68.18 336	83.16 398

FMVSNet5		68.04 381	65.66 381	75.18 390	84.43 333	57.89 379	83.54 384	86.26 391	61.83 395	53.64 428	73.30 431	37.15 406	85.08 434	48.99 402	61.77 395	82.56 409

ppachtmachnet_test		67.72 383	63.70 396	79.77 337	78.92 404	66.04 170	88.68 329	82.90 429	60.11 408	55.45 419	75.96 422	39.19 385	90.55 380	39.53 446	52.55 434	82.71 405

ACMH+	65.35 16	67.65 384	64.55 389	76.96 377	84.59 327	57.10 392	88.08 338	80.79 433	58.59 417	53.00 430	81.09 368	26.63 449	92.95 319	46.51 417	61.69 399	80.82 424

pmmvs6		67.57 385	64.76 387	76.00 384	72.82 450	53.37 415	88.71 328	86.78 386	53.19 438	57.58 414	78.03 398	35.33 415	92.41 344	55.56 375	54.88 427	82.21 412

Anonymous20231206		67.53 386	65.78 378	72.79 413	74.95 441	47.59 447	88.23 336	87.32 375	61.75 398	58.07 408	77.29 405	37.79 400	87.29 422	42.91 432	63.71 379	83.48 392

Patchmtry		67.53 386	63.93 395	78.34 356	82.12 363	64.38 221	68.72 460	84.00 418	48.23 455	59.24 398	72.41 436	57.82 209	89.27 398	46.10 420	56.68 422	81.36 418

USDC		67.43 388	64.51 390	76.19 382	77.94 419	55.29 406	78.38 432	85.00 408	73.17 221	48.36 451	80.37 376	21.23 462	92.48 342	52.15 389	64.02 377	80.81 425

ADS-MVSNet2		66.90 389	63.44 398	77.26 372	88.06 232	60.70 337	68.01 463	75.56 448	57.57 419	64.48 354	69.87 448	38.68 386	84.10 438	40.87 442	67.89 342	86.97 325

FE-MVSNET2		66.80 390	64.06 394	75.03 391	69.84 458	57.11 391	86.57 363	88.57 350	67.94 332	50.97 441	72.16 440	33.79 422	87.55 419	53.94 382	52.74 431	80.45 429

CMPMVS	48.56 21	66.77 391	64.41 392	73.84 405	70.65 456	50.31 433	77.79 436	85.73 401	45.54 461	44.76 462	82.14 346	35.40 414	90.14 390	63.18 338	74.54 289	81.07 422
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
OpenMVS_ROB	61.12 18	66.39 392	62.92 401	76.80 379	76.51 428	57.77 381	89.22 316	83.41 425	55.48 433	53.86 426	77.84 399	26.28 450	93.95 287	34.90 458	68.76 332	78.68 446

LTVRE_ROB	59.60 19	66.27 393	63.54 397	74.45 399	84.00 340	51.55 423	67.08 467	83.53 423	58.78 415	54.94 421	80.31 377	34.54 417	93.23 312	40.64 444	68.03 338	78.58 447
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
JIA-IIPM		66.06 394	62.45 404	76.88 378	81.42 372	54.45 412	57.49 481	88.67 345	49.36 450	63.86 361	46.86 478	56.06 234	90.25 384	49.53 399	68.83 331	85.95 357

Patchmatch-test		65.86 395	60.94 410	80.62 314	83.75 344	58.83 371	58.91 478	75.26 450	44.50 465	50.95 442	77.09 408	58.81 193	87.90 410	35.13 457	64.03 376	95.12 89

UnsupCasMVSNet_eth		65.79 396	63.10 399	73.88 404	70.71 455	50.29 434	81.09 413	89.88 288	72.58 237	49.25 448	74.77 429	32.57 427	87.43 421	55.96 374	41.04 463	83.90 386

test_fmvs2		65.78 397	64.84 385	68.60 436	66.54 467	41.71 468	83.27 390	69.81 467	54.38 435	67.91 318	84.54 317	15.35 472	81.22 459	75.65 203	66.16 352	82.88 400

dmvs_testset		65.55 398	66.45 373	62.86 448	79.87 391	22.35 494	76.55 439	71.74 461	77.42 149	55.85 418	87.77 272	51.39 290	80.69 460	31.51 473	65.92 355	85.55 368

pmmvs-eth3d		65.53 399	62.32 405	75.19 389	69.39 461	59.59 360	82.80 398	83.43 424	62.52 386	51.30 439	72.49 434	32.86 424	87.16 423	55.32 376	50.73 442	78.83 444

mamv4		65.18 400	67.43 369	58.44 452	77.88 421	49.36 441	69.40 459	70.99 465	48.31 454	57.78 412	85.53 305	59.01 190	51.88 490	73.67 219	64.32 372	74.07 460

SixPastTwentyTwo		64.92 401	61.78 408	74.34 401	78.74 408	49.76 435	83.42 389	79.51 439	62.86 382	50.27 443	77.35 403	30.92 436	90.49 382	45.89 421	47.06 449	82.78 401

OurMVSNet-221017-0		64.68 402	62.17 406	72.21 418	76.08 432	47.35 448	80.67 416	81.02 432	56.19 430	51.60 436	79.66 387	27.05 448	88.56 403	53.60 385	53.63 430	80.71 426

test_0402		64.54 403	61.09 409	74.92 394	84.10 339	60.75 333	87.95 342	79.71 438	52.03 440	52.41 432	77.20 406	32.21 429	91.64 365	23.14 478	61.03 402	72.36 466

testgi		64.48 404	62.87 402	69.31 433	71.24 451	40.62 471	85.49 369	79.92 437	65.36 359	54.18 424	83.49 330	23.74 455	84.55 436	41.60 439	60.79 405	82.77 402

RPSCF		64.24 405	61.98 407	71.01 426	76.10 431	45.00 460	75.83 444	75.94 445	46.94 457	58.96 402	84.59 315	31.40 432	82.00 456	47.76 413	60.33 410	86.04 354

EU-MVSNet		64.01 406	63.01 400	67.02 442	74.40 444	38.86 477	83.27 390	86.19 393	45.11 463	54.27 423	81.15 367	36.91 409	80.01 462	48.79 405	57.02 419	82.19 413

test20.03		63.83 407	62.65 403	67.38 441	70.58 457	39.94 473	86.57 363	84.17 415	63.29 377	51.86 435	77.30 404	37.09 407	82.47 452	38.87 450	54.13 429	79.73 435

sc_t1		63.81 408	59.39 416	77.10 373	77.62 422	56.03 401	84.32 378	73.56 455	46.66 459	58.22 405	73.06 432	23.28 458	90.62 379	50.93 392	46.84 450	84.64 381

MDA-MVSNet_test_wron		63.78 409	60.16 412	74.64 396	78.15 417	60.41 344	83.49 386	84.03 416	56.17 432	39.17 473	71.59 443	37.22 404	83.24 449	42.87 434	48.73 445	80.26 432

YYNet1		63.76 410	60.14 413	74.62 397	78.06 418	60.19 351	83.46 388	83.99 420	56.18 431	39.25 472	71.56 444	37.18 405	83.34 447	42.90 433	48.70 446	80.32 431

K. test v3		63.09 411	59.61 415	73.53 407	76.26 430	49.38 440	83.27 390	77.15 442	64.35 365	47.77 453	72.32 438	28.73 442	87.79 413	49.93 398	36.69 470	83.41 394

COLMAP_ROB	57.96 20	62.98 412	59.65 414	72.98 411	81.44 371	53.00 417	83.75 383	75.53 449	48.34 453	48.81 450	81.40 360	24.14 453	90.30 383	32.95 464	60.52 407	75.65 458
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20240521		62.09 413	59.08 417	71.10 425	67.19 465	48.72 443	83.91 381	85.23 406	50.38 447	47.84 452	71.22 446	20.74 463	85.51 432	46.47 418	58.75 415	79.06 440

tt0320		61.85 414	57.45 423	75.03 391	77.49 423	57.60 385	82.74 399	73.65 454	43.65 469	53.65 427	68.18 454	25.47 451	88.66 400	45.56 423	46.68 451	78.81 445

AllTest		61.66 415	58.06 419	72.46 415	79.57 393	51.42 425	80.17 422	68.61 469	51.25 444	45.88 456	81.23 362	19.86 467	86.58 425	38.98 448	57.01 420	79.39 437

UnsupCasMVSNet_bld		61.60 416	57.71 420	73.29 409	68.73 462	51.64 422	78.61 430	89.05 328	57.20 424	46.11 455	61.96 469	28.70 443	88.60 402	50.08 397	38.90 468	79.63 436

MDA-MVSNet-bldmvs		61.54 417	57.70 421	73.05 410	79.53 395	57.00 396	83.08 394	81.23 431	57.57 419	34.91 477	72.45 435	32.79 425	86.26 427	35.81 455	41.95 461	75.89 457

tt0320-xc		61.51 418	56.89 427	75.37 387	78.50 412	58.61 374	82.61 401	71.27 464	44.31 466	53.17 429	68.03 456	23.38 456	88.46 405	47.77 412	43.00 460	79.03 442

mvs5depth		61.03 419	57.65 422	71.18 424	67.16 466	47.04 453	72.74 450	77.49 440	57.47 422	60.52 389	72.53 433	22.84 459	88.38 406	49.15 401	38.94 467	78.11 451

KD-MVS_self_test		60.87 420	58.60 418	67.68 439	66.13 468	39.93 474	75.63 446	84.70 410	57.32 423	49.57 446	68.45 453	29.55 439	82.87 450	48.09 407	47.94 447	80.25 433

kuosan		60.86 421	60.24 411	62.71 449	81.57 369	46.43 455	75.70 445	85.88 398	57.98 418	48.95 449	69.53 450	58.42 198	76.53 465	28.25 474	35.87 472	65.15 473

FE-MVSNET		60.52 422	57.18 426	70.53 427	67.53 464	50.68 430	82.62 400	76.28 443	59.33 413	46.71 454	71.10 447	30.54 437	83.61 444	33.15 463	47.37 448	77.29 454

TinyColmap		60.32 423	56.42 430	72.00 422	78.78 407	53.18 416	78.36 433	75.64 447	52.30 439	41.59 471	75.82 424	14.76 475	88.35 407	35.84 454	54.71 428	74.46 459

MVS-HIRNet		60.25 424	55.55 431	74.35 400	84.37 334	56.57 398	71.64 453	74.11 452	34.44 476	45.54 460	42.24 484	31.11 435	89.81 394	40.36 445	76.10 281	76.67 456

MIMVSNet1		60.16 425	57.33 424	68.67 435	69.71 459	44.13 462	78.92 429	84.21 414	55.05 434	44.63 463	71.85 441	23.91 454	81.54 458	32.63 468	55.03 426	80.35 430

PM-MVS		59.40 426	56.59 428	67.84 437	63.63 471	41.86 466	76.76 438	63.22 477	59.01 414	51.07 440	72.27 439	11.72 479	83.25 448	61.34 349	50.28 444	78.39 449

new-patchmatchnet		59.30 427	56.48 429	67.79 438	65.86 469	44.19 461	82.47 402	81.77 430	59.94 409	43.65 467	66.20 459	27.67 446	81.68 457	39.34 447	41.40 462	77.50 453

test_vis1_rt		59.09 428	57.31 425	64.43 445	68.44 463	46.02 457	83.05 396	48.63 489	51.96 441	49.57 446	63.86 464	16.30 470	80.20 461	71.21 250	62.79 384	67.07 472

usedtu_dtu_shiyan2		57.76 429	53.69 435	69.95 430	57.60 481	41.80 467	83.50 385	83.67 422	45.26 462	43.79 466	62.82 466	17.63 469	85.93 428	42.56 437	46.40 453	82.12 414

test_fmvs3		56.82 430	54.86 433	62.69 450	53.59 483	35.47 480	75.87 443	65.64 474	43.91 467	55.10 420	71.43 445	6.91 487	74.40 470	68.64 275	52.63 432	78.20 450

DSMNet-mixed		56.78 431	54.44 434	63.79 446	63.21 472	29.44 489	64.43 470	64.10 476	42.12 473	51.32 438	71.60 442	31.76 430	75.04 468	36.23 453	65.20 363	86.87 330

pmmvs3		55.51 432	51.50 438	67.53 440	57.90 480	50.93 429	80.37 418	73.66 453	40.63 474	44.15 465	64.75 462	16.30 470	78.97 464	44.77 428	40.98 465	72.69 464

TDRefinement		55.28 433	51.58 437	66.39 443	59.53 479	46.15 456	76.23 441	72.80 456	44.60 464	42.49 469	76.28 420	15.29 473	82.39 453	33.20 462	43.75 457	70.62 468

dongtai		55.18 434	55.46 432	54.34 460	76.03 433	36.88 478	76.07 442	84.61 412	51.28 443	43.41 468	64.61 463	56.56 228	67.81 478	18.09 483	28.50 483	58.32 476

LF4IMVS		54.01 435	52.12 436	59.69 451	62.41 474	39.91 475	68.59 461	68.28 471	42.96 471	44.55 464	75.18 425	14.09 477	68.39 477	41.36 441	51.68 435	70.78 467

ttmdpeth		53.34 436	49.96 439	63.45 447	62.07 476	40.04 472	72.06 451	65.64 474	42.54 472	51.88 434	77.79 400	13.94 478	76.48 466	32.93 465	30.82 481	73.84 461

MVStest1		51.35 437	46.89 441	64.74 444	65.06 470	51.10 427	67.33 466	72.58 457	30.20 480	35.30 475	74.82 427	27.70 445	69.89 475	24.44 477	24.57 484	73.22 462

N_pmnet		50.55 438	49.11 440	54.88 458	77.17 426	4.02 502	84.36 376	2.00 500	48.59 451	45.86 458	68.82 451	32.22 428	82.80 451	31.58 471	51.38 436	77.81 452

new_pmnet		49.31 439	46.44 442	57.93 453	62.84 473	40.74 470	68.47 462	62.96 478	36.48 475	35.09 476	57.81 473	14.97 474	72.18 472	32.86 466	46.44 452	60.88 475

mvsany_test3		48.86 440	46.35 443	56.41 454	46.00 489	31.67 485	62.26 472	47.25 490	43.71 468	45.54 460	68.15 455	10.84 480	64.44 486	57.95 365	35.44 475	73.13 463

test_f		46.58 441	43.45 445	55.96 455	45.18 490	32.05 484	61.18 473	49.49 488	33.39 477	42.05 470	62.48 468	7.00 486	65.56 482	47.08 416	43.21 459	70.27 469

WB-MVS		46.23 442	44.94 444	50.11 463	62.13 475	21.23 496	76.48 440	55.49 482	45.89 460	35.78 474	61.44 471	35.54 413	72.83 471	9.96 490	21.75 485	56.27 478

FPMVS		45.64 443	43.10 447	53.23 461	51.42 486	36.46 479	64.97 469	71.91 460	29.13 481	27.53 481	61.55 470	9.83 482	65.01 484	16.00 487	55.58 424	58.22 477

SSC-MVS		44.51 444	43.35 446	47.99 467	61.01 478	18.90 498	74.12 448	54.36 483	43.42 470	34.10 478	60.02 472	34.42 418	70.39 474	9.14 492	19.57 486	54.68 479

EGC-MVSNET		42.35 445	38.09 448	55.11 457	74.57 442	46.62 454	71.63 454	55.77 481	0.04 495	0.24 496	62.70 467	14.24 476	74.91 469	17.59 484	46.06 454	43.80 481

LCM-MVSNet		40.54 446	35.79 451	54.76 459	36.92 496	30.81 486	51.41 484	69.02 468	22.07 483	24.63 483	45.37 480	4.56 491	65.81 481	33.67 460	34.50 476	67.67 470

APD_test1		40.50 447	37.31 450	50.09 464	51.88 484	35.27 481	59.45 477	52.59 485	21.64 484	26.12 482	57.80 474	4.56 491	66.56 480	22.64 479	39.09 466	48.43 480

test_vis3_rt		40.46 448	37.79 449	48.47 466	44.49 491	33.35 483	66.56 468	32.84 497	32.39 478	29.65 479	39.13 487	3.91 494	68.65 476	50.17 395	40.99 464	43.40 482

ANet_high		40.27 449	35.20 452	55.47 456	34.74 497	34.47 482	63.84 471	71.56 462	48.42 452	18.80 486	41.08 485	9.52 483	64.45 485	20.18 481	8.66 493	67.49 471

test_method		38.59 450	35.16 453	48.89 465	54.33 482	21.35 495	45.32 487	53.71 484	7.41 492	28.74 480	51.62 476	8.70 484	52.87 489	33.73 459	32.89 477	72.47 465

PMMVS2		37.93 451	33.61 454	50.92 462	46.31 488	24.76 492	60.55 476	50.05 486	28.94 482	20.93 484	47.59 477	4.41 493	65.13 483	25.14 476	18.55 488	62.87 474

Gipuma		34.91 452	31.44 455	45.30 468	70.99 454	39.64 476	19.85 491	72.56 458	20.10 486	16.16 490	21.47 491	5.08 490	71.16 473	13.07 488	43.70 458	25.08 488
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testf1		32.77 453	29.47 456	42.67 470	41.89 493	30.81 486	52.07 482	43.45 491	15.45 487	18.52 487	44.82 481	2.12 495	58.38 487	16.05 485	30.87 479	38.83 483

APD_test2		32.77 453	29.47 456	42.67 470	41.89 493	30.81 486	52.07 482	43.45 491	15.45 487	18.52 487	44.82 481	2.12 495	58.38 487	16.05 485	30.87 479	38.83 483

PMVS	26.43 22	31.84 455	28.16 458	42.89 469	25.87 499	27.58 490	50.92 485	49.78 487	21.37 485	14.17 491	40.81 486	2.01 497	66.62 479	9.61 491	38.88 469	34.49 487
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		24.61 456	24.00 460	26.45 474	43.74 492	18.44 499	60.86 474	39.66 493	15.11 489	9.53 493	22.10 490	6.52 488	46.94 492	8.31 493	10.14 490	13.98 490

MVE	24.84 23	24.35 457	19.77 463	38.09 472	34.56 498	26.92 491	26.57 489	38.87 495	11.73 491	11.37 492	27.44 488	1.37 498	50.42 491	11.41 489	14.60 489	36.93 485
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		23.76 458	23.20 462	25.46 475	41.52 495	16.90 500	60.56 475	38.79 496	14.62 490	8.99 494	20.24 493	7.35 485	45.82 493	7.25 494	9.46 491	13.64 491

tmp_tt		22.26 459	23.75 461	17.80 476	5.23 500	12.06 501	35.26 488	39.48 494	2.82 494	18.94 485	44.20 483	22.23 461	24.64 495	36.30 452	9.31 492	16.69 489

cdsmvs_eth3d_5k		19.86 460	26.47 459	0.00 480	0.00 503	0.00 505	0.00 492	93.45 95	0.00 498	0.00 499	95.27 77	49.56 312	0.00 499	0.00 498	0.00 496	0.00 495

wuyk23d		11.30 461	10.95 464	12.33 477	48.05 487	19.89 497	25.89 490	1.92 501	3.58 493	3.12 495	1.37 495	0.64 499	15.77 496	6.23 495	7.77 494	1.35 492

ab-mvs-re		7.91 462	10.55 465	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	94.95 87	0.00 502	0.00 499	0.00 498	0.00 496	0.00 495

testmvs		7.23 463	9.62 466	0.06 479	0.04 501	0.02 504	84.98 373	0.02 502	0.03 496	0.18 497	1.21 496	0.01 501	0.02 497	0.14 496	0.01 495	0.13 494

test123		6.92 464	9.21 467	0.08 478	0.03 502	0.05 503	81.65 408	0.01 503	0.02 497	0.14 498	0.85 497	0.03 500	0.02 497	0.12 497	0.00 496	0.16 493

pcd_1.5k_mvsjas		4.46 465	5.95 468	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	53.55 266	0.00 499	0.00 498	0.00 496	0.00 495

mmdepth		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 496	0.00 495

monomultidepth		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 496	0.00 495

test_blank		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 496	0.00 495

uanet_test		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 496	0.00 495

DCPMVS		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 496	0.00 495

sosnet-low-res		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 496	0.00 495

sosnet		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 496	0.00 495

uncertanet		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 496	0.00 495

Regformer		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 496	0.00 495

uanet		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 496	0.00 495

MED-MVS test				87.42 45	94.76 34	67.28 126	94.47 61	94.87 32	73.09 226	91.27 23	96.95 17		98.98 16	91.55 43	94.28 37	95.99 45

TestfortrainingZip							94.47 61

WAC-MVS						49.45 438								31.56 472

FOURS1					93.95 50	61.77 307	93.96 88	91.92 167	62.14 390	86.57 62

MSC_two_6792asdad				89.60 9	97.31 4	73.22 12		95.05 29					99.07 13	92.01 38	94.77 26	96.51 24

PC_three_1452									80.91 65	94.07 2	96.83 29	83.57 4	99.12 5	95.70 10	97.42 4	97.55 4

No_MVS				89.60 9	97.31 4	73.22 12		95.05 29					99.07 13	92.01 38	94.77 26	96.51 24

test_one_0601					96.32 19	69.74 51		94.18 66	71.42 280	90.67 29	96.85 27	74.45 22

eth-test2					0.00 503

eth-test					0.00 503

ZD-MVS					96.63 9	65.50 187		93.50 93	70.74 294	85.26 80	95.19 83	64.92 94	97.29 89	87.51 73	93.01 60

RE-MVS-def			80.48 186		92.02 109	58.56 375	90.90 258	90.45 255	62.76 383	78.89 164	94.46 101	49.30 315		78.77 184	86.77 148	92.28 232

IU-MVS					96.46 11	69.91 43		95.18 23	80.75 66	95.28 1				92.34 35	95.36 14	96.47 28

OPU-MVS				89.97 3	97.52 3	73.15 14	96.89 6				97.00 15	83.82 2	99.15 2	95.72 8	97.63 3	97.62 2

test_241102_TWO								94.41 57	71.65 269	92.07 11	97.21 9	74.58 20	99.11 6	92.34 35	95.36 14	96.59 19

test_241102_ONE					96.45 12	69.38 59		94.44 55	71.65 269	92.11 9	97.05 12	76.79 9	99.11 6

9.14			87.63 39		93.86 52		94.41 66	94.18 66	72.76 234	86.21 65	96.51 36	66.64 72	97.88 52	90.08 55	94.04 43

save fliter					93.84 53	67.89 110	95.05 40	92.66 133	78.19 129

test_0728_THIRD									72.48 239	90.55 30	96.93 21	76.24 13	99.08 11	91.53 46	94.99 18	96.43 31

test_0728_SECOND				88.70 18	96.45 12	70.43 34	96.64 10	94.37 61					99.15 2	91.91 41	94.90 22	96.51 24

test0726					96.40 15	69.99 39	96.76 8	94.33 63	71.92 255	91.89 14	97.11 11	73.77 25

GSMVS																94.68 120

test_part2					96.29 20	68.16 103				90.78 27

sam_mvs1												57.85 208				94.68 120

sam_mvs												54.91 247

ambc				69.61 431	61.38 477	41.35 469	49.07 486	85.86 400		50.18 445	66.40 458	10.16 481	88.14 409	45.73 422	44.20 456	79.32 439

MTGPA								92.23 148

test_post1							78.95 428				20.70 492	53.05 271	91.50 374	60.43 354

test_post											23.01 489	56.49 229	92.67 334

patchmatchnet-post											67.62 457	57.62 211	90.25 384

GG-mvs-BLEND				86.53 89	91.91 118	69.67 54	75.02 447	94.75 40		78.67 172	90.85 206	77.91 7	94.56 254	72.25 237	93.74 49	95.36 72

MTMP							93.77 103	32.52 498

gm-plane-assit					88.42 218	67.04 138			78.62 123		91.83 179		97.37 83	76.57 196

test9_res														89.41 56	94.96 19	95.29 78

TEST9					94.18 45	67.28 126	94.16 75	93.51 91	71.75 266	85.52 75	95.33 71	68.01 61	97.27 93

test_8					94.19 44	67.19 131	94.15 77	93.42 98	71.87 260	85.38 78	95.35 70	68.19 59	96.95 120

agg_prior2														86.41 87	94.75 30	95.33 74

agg_prior					94.16 47	66.97 146		93.31 101		84.49 86			96.75 132

TestCases				72.46 415	79.57 393	51.42 425		68.61 469	51.25 444	45.88 456	81.23 362	19.86 467	86.58 425	38.98 448	57.01 420	79.39 437

test_prior4						67.18 133	93.92 92

test_prior2							95.10 39		75.40 183	85.25 81	95.61 62	67.94 62		87.47 75	94.77 26

test_prior				86.42 93	94.71 39	67.35 125		93.10 112					96.84 129			95.05 93

旧先验2							92.00 197		59.37 412	87.54 55			93.47 303	75.39 205

新几何2							91.41 229

新几何1				84.73 167	92.32 97	64.28 226		91.46 194	59.56 411	79.77 151	92.90 145	56.95 221	96.57 138	63.40 334	92.91 62	93.34 192

旧先验1					91.94 114	60.74 334		91.50 192			94.36 105	65.23 89			91.84 78	94.55 129

无先验							92.71 152	92.61 138	62.03 391				97.01 110	66.63 299		93.97 168

原ACMM2							92.01 194

原ACMM1				84.42 184	93.21 72	64.27 227		93.40 100	65.39 358	79.51 156	92.50 153	58.11 203	96.69 134	65.27 320	93.96 44	92.32 230

test222					89.77 167	61.60 313	89.55 305	89.42 307	56.83 427	77.28 188	92.43 157	52.76 274			91.14 95	93.09 202

testdata2													96.09 163	61.26 350

segment_acmp												65.94 80

testdata				81.34 291	89.02 191	57.72 382		89.84 289	58.65 416	85.32 79	94.09 121	57.03 216	93.28 309	69.34 266	90.56 101	93.03 205

testdata1							89.21 317		77.55 145

test12				87.09 56	94.60 40	68.86 79		92.91 121		82.67 109		65.44 86	97.55 72		93.69 52	94.84 105

plane_prior7					86.94 272	61.51 315

plane_prior6					87.23 258	62.32 293						50.66 298

plane_prior5								91.31 198					95.55 208	76.74 194	78.53 259	88.39 304

plane_prior4											89.14 247

plane_prior3						61.95 302			79.09 112	72.53 251

plane_prior2							93.13 131		78.81 119

plane_prior1					87.15 261

plane_prior						62.42 289	93.85 96		79.38 104						78.80 256

n2								0.00 504

nn								0.00 504

door-mid								66.01 473

lessismore_v0				73.72 406	72.93 449	47.83 446		61.72 479		45.86 458	73.76 430	28.63 444	89.81 394	47.75 414	31.37 478	83.53 390

LGP-MVS_train				79.56 343	84.31 335	59.37 364		89.73 295	69.49 309	64.86 349	88.42 256	38.65 388	94.30 265	72.56 234	72.76 303	85.01 376

test11								93.01 115

door								66.57 472

HQP5-MVS						63.66 256

HQP-NCC					87.54 250		94.06 80		79.80 88	74.18 225

ACMP_Plane					87.54 250		94.06 80		79.80 88	74.18 225

BP-MVS														77.63 191

HQP4-MVS										74.18 225			95.61 202			88.63 298

HQP3-MVS								91.70 184							78.90 254

HQP2-MVS												51.63 286

NP-MVS					87.41 253	63.04 273					90.30 217

MDTV_nov1_ep13_2view						59.90 356	80.13 423		67.65 336	72.79 245		54.33 257		59.83 358		92.58 221

MDTV_nov1_ep13			72.61 324		89.06 189	68.48 90	80.33 419	90.11 278	71.84 262	71.81 265	75.92 423	53.01 272	93.92 288	48.04 408	73.38 298

ACMMP++_ref															71.63 311

ACMMP++															69.72 322

Test By Simon												54.21 260

ITE_SJBPF				70.43 428	74.44 443	47.06 452		77.32 441	60.16 407	54.04 425	83.53 328	23.30 457	84.01 440	43.07 431	61.58 400	80.21 434

DeepMVS_CX				34.71 473	51.45 485	24.73 493		28.48 499	31.46 479	17.49 489	52.75 475	5.80 489	42.60 494	18.18 482	19.42 487	36.81 486

High-resolution multi-view benchmark