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 60	96.26 35	72.84 30	99.38 1	92.64 26	95.93 9	97.08 11

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 15	96.19 37	70.12 47	98.91 18	96.83 1	95.06 17	96.76 15

DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 162	76.68 2	97.29 1	95.35 17	82.87 28	91.58 14	97.22 4	79.93 5	99.10 9	83.12 108	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 76	94.37 56	72.48 199	92.07 9	96.85 18	83.82 2	99.15 2	91.53 36	97.42 4	97.55 4

MSP-MVS		90.38 5	91.87 1	85.88 92	92.83 80	64.03 196	93.06 119	94.33 58	82.19 36	93.65 3	96.15 39	85.89 1	97.19 88	91.02 40	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
MVS_0304		90.32 6	90.90 7	88.55 23	94.05 45	70.23 37	97.00 5	93.73 77	87.30 4	92.15 6	96.15 39	66.38 69	98.94 17	96.71 2	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 33	84.83 12	89.07 34	96.80 21	70.86 43	99.06 15	92.64 26	95.71 11	96.12 40

DELS-MVS		90.05 8	90.09 11	89.94 4	93.14 71	73.88 9	97.01 4	94.40 54	88.32 3	85.71 61	94.91 79	74.11 21	98.91 18	87.26 68	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 56	96.89 6	94.44 50	71.65 229	92.11 7	97.21 5	76.79 9	99.11 6	92.34 28	95.36 14	97.62 2

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 137	93.00 76	58.16 322	96.72 9	94.41 52	86.50 8	90.25 25	97.83 1	75.46 14	98.67 25	92.78 25	95.49 13	97.32 6

patch_mono-2		89.71 11	90.99 6	85.85 95	96.04 24	63.70 207	95.04 40	95.19 22	86.74 7	91.53 16	95.15 72	73.86 22	97.58 62	93.38 20	92.00 69	96.28 37

CANet		89.61 12	89.99 12	88.46 24	94.39 39	69.71 51	96.53 13	93.78 70	86.89 6	89.68 31	95.78 46	65.94 74	99.10 9	92.99 23	93.91 42	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 46	71.92 215	90.55 21	96.93 12	73.77 23	99.08 11	91.91 34	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 34	95.10 30	68.23 87	95.24 33	94.49 48	82.43 33	88.90 35	96.35 31	71.89 40	98.63 26	88.76 54	96.40 6	96.06 41

balanced_conf03		89.08 15	88.84 17	89.81 6	93.66 54	75.15 5	90.61 234	93.43 91	84.06 16	86.20 55	90.17 190	72.42 35	96.98 105	93.09 22	95.92 10	97.29 7

NCCC		89.07 16	89.46 15	87.91 28	96.60 10	69.05 64	96.38 15	94.64 42	84.42 13	86.74 51	96.20 36	66.56 68	98.76 24	89.03 53	94.56 34	95.92 46

DPE-MVS		88.77 17	89.21 16	87.45 43	96.26 20	67.56 104	94.17 62	94.15 63	68.77 278	90.74 19	97.27 2	76.09 12	98.49 29	90.58 44	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
SMA-MVS		88.14 18	88.29 22	87.67 33	93.21 68	68.72 73	93.85 83	94.03 66	74.18 162	91.74 12	96.67 24	65.61 79	98.42 33	89.24 50	96.08 7	95.88 47
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 18	87.61 32	89.71 7	92.06 102	76.72 1	95.75 20	93.26 97	83.86 17	89.55 32	96.06 41	53.55 233	97.89 44	91.10 38	93.31 53	94.54 111

TSAR-MVS + MP.		88.11 20	88.64 18	86.54 73	91.73 117	68.04 91	90.36 240	93.55 84	82.89 26	91.29 17	92.89 132	72.27 37	96.03 154	87.99 58	94.77 26	95.54 58
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
TSAR-MVS + GP.		87.96 21	88.37 21	86.70 66	93.51 62	65.32 161	95.15 36	93.84 69	78.17 105	85.93 59	94.80 82	75.80 13	98.21 35	89.38 47	88.78 110	96.59 19

DeepC-MVS_fast	79.48 2	87.95 22	88.00 26	87.79 31	95.86 27	68.32 81	95.74 21	94.11 64	83.82 18	83.49 83	96.19 37	64.53 94	98.44 31	83.42 107	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
xiu_mvs_v2_base		87.92 23	87.38 36	89.55 12	91.41 129	76.43 3	95.74 21	93.12 105	83.53 21	89.55 32	95.95 44	53.45 237	97.68 52	91.07 39	92.62 60	94.54 111

EPNet		87.84 24	88.38 20	86.23 83	93.30 65	66.05 143	95.26 32	94.84 32	87.09 5	88.06 38	94.53 88	66.79 65	97.34 77	83.89 101	91.68 74	95.29 71
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
lupinMVS		87.74 25	87.77 29	87.63 38	89.24 177	71.18 24	96.57 12	92.90 114	82.70 30	87.13 46	95.27 65	64.99 85	95.80 159	89.34 48	91.80 72	95.93 45

test_fmvsm_n_1920		87.69 26	88.50 19	85.27 117	87.05 236	63.55 214	93.69 93	91.08 201	84.18 15	90.17 27	97.04 9	67.58 60	97.99 40	95.72 5	90.03 96	94.26 123

fmvsm_l_conf0.5_n_3		87.54 27	88.29 22	85.30 114	86.92 242	62.63 240	95.02 42	90.28 229	84.95 11	90.27 24	96.86 16	65.36 81	97.52 67	94.93 10	90.03 96	95.76 50

APDe-MVS		87.54 27	87.84 28	86.65 67	96.07 23	66.30 139	94.84 46	93.78 70	69.35 269	88.39 37	96.34 32	67.74 59	97.66 57	90.62 43	93.44 51	96.01 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
fmvsm_l_conf0.5_n		87.49 29	88.19 24	85.39 110	86.95 237	64.37 186	94.30 59	88.45 304	80.51 58	92.70 4	96.86 16	69.98 48	97.15 93	95.83 4	88.08 118	94.65 105

SD-MVS		87.49 29	87.49 34	87.50 42	93.60 56	68.82 70	93.90 80	92.63 127	76.86 126	87.90 40	95.76 47	66.17 71	97.63 59	89.06 52	91.48 78	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 31	88.15 25	85.30 114	87.10 234	64.19 193	94.41 54	88.14 313	80.24 66	92.54 5	96.97 11	69.52 50	97.17 89	95.89 3	88.51 113	94.56 108

dcpmvs_2		87.37 32	87.55 33	86.85 58	95.04 32	68.20 88	90.36 240	90.66 213	79.37 81	81.20 105	93.67 116	74.73 16	96.55 127	90.88 41	92.00 69	95.82 48

alignmvs		87.28 33	86.97 40	88.24 27	91.30 131	71.14 26	95.61 25	93.56 83	79.30 82	87.07 48	95.25 67	68.43 52	96.93 113	87.87 59	84.33 159	96.65 17

train_agg		87.21 34	87.42 35	86.60 69	94.18 41	67.28 111	94.16 63	93.51 85	71.87 220	85.52 63	95.33 60	68.19 54	97.27 84	89.09 51	94.90 22	95.25 77

MG-MVS		87.11 35	86.27 50	89.62 8	97.79 1	76.27 4	94.96 44	94.49 48	78.74 97	83.87 81	92.94 130	64.34 95	96.94 111	75.19 170	94.09 38	95.66 53

SF-MVS		87.03 36	87.09 38	86.84 59	92.70 86	67.45 109	93.64 96	93.76 73	70.78 253	86.25 53	96.44 29	66.98 63	97.79 48	88.68 55	94.56 34	95.28 73

fmvsm_s_conf0.5_n_3		86.88 37	87.99 27	83.58 181	87.26 229	60.74 281	93.21 116	87.94 320	84.22 14	91.70 13	97.27 2	65.91 76	95.02 193	93.95 17	90.42 93	94.99 87

CSCG		86.87 38	86.26 51	88.72 17	95.05 31	70.79 29	93.83 88	95.33 18	68.48 282	77.63 152	94.35 97	73.04 28	98.45 30	84.92 90	93.71 47	96.92 14

sasdasda		86.85 39	86.25 52	88.66 20	91.80 115	71.92 16	93.54 101	91.71 169	80.26 63	87.55 43	95.25 67	63.59 109	96.93 113	88.18 56	84.34 157	97.11 9

canonicalmvs		86.85 39	86.25 52	88.66 20	91.80 115	71.92 16	93.54 101	91.71 169	80.26 63	87.55 43	95.25 67	63.59 109	96.93 113	88.18 56	84.34 157	97.11 9

UBG		86.83 41	86.70 46	87.20 48	93.07 74	69.81 47	93.43 109	95.56 13	81.52 43	81.50 101	92.12 151	73.58 26	96.28 139	84.37 96	85.20 149	95.51 59

PHI-MVS		86.83 41	86.85 45	86.78 63	93.47 63	65.55 157	95.39 30	95.10 25	71.77 225	85.69 62	96.52 26	62.07 131	98.77 23	86.06 80	95.60 12	96.03 43

SteuartSystems-ACMMP		86.82 43	86.90 43	86.58 71	90.42 147	66.38 136	96.09 17	93.87 68	77.73 113	84.01 80	95.66 49	63.39 112	97.94 41	87.40 66	93.55 50	95.42 60
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_s_conf0.5_n_4		86.79 44	87.63 30	84.27 159	86.15 256	61.48 265	94.69 50	91.16 193	83.79 20	90.51 23	96.28 34	64.24 96	98.22 34	95.00 9	86.88 130	93.11 167

PVSNet_Blended		86.73 45	86.86 44	86.31 82	93.76 50	67.53 106	96.33 16	93.61 81	82.34 35	81.00 110	93.08 126	63.19 116	97.29 80	87.08 71	91.38 80	94.13 132

testing11		86.71 46	86.44 49	87.55 40	93.54 60	71.35 21	93.65 95	95.58 11	81.36 50	80.69 113	92.21 150	72.30 36	96.46 132	85.18 86	83.43 167	94.82 97

test_fmvsmconf_n		86.58 47	87.17 37	84.82 130	85.28 271	62.55 241	94.26 61	89.78 248	83.81 19	87.78 42	96.33 33	65.33 82	96.98 105	94.40 13	87.55 124	94.95 89

BP-MVS1		86.54 48	86.68 47	86.13 86	87.80 217	67.18 115	92.97 124	95.62 10	79.92 69	82.84 90	94.14 106	74.95 15	96.46 132	82.91 110	88.96 109	94.74 99

jason		86.40 49	86.17 54	87.11 51	86.16 255	70.54 32	95.71 24	92.19 144	82.00 38	84.58 73	94.34 98	61.86 133	95.53 179	87.76 60	90.89 86	95.27 74
jason: jason.
fmvsm_s_conf0.5_n		86.39 50	86.91 42	84.82 130	87.36 228	63.54 215	94.74 48	90.02 241	82.52 31	90.14 28	96.92 14	62.93 121	97.84 47	95.28 8	82.26 177	93.07 170

fmvsm_s_conf0.5_n_5		86.38 51	86.94 41	84.71 139	84.67 282	63.29 220	94.04 72	89.99 243	82.88 27	87.85 41	96.03 42	62.89 123	96.36 136	94.15 14	89.95 98	94.48 117

WTY-MVS		86.32 52	85.81 62	87.85 29	92.82 82	69.37 58	95.20 34	95.25 20	82.71 29	81.91 98	94.73 83	67.93 58	97.63 59	79.55 139	82.25 178	96.54 22

myMVS_eth3d28		86.31 53	86.15 55	86.78 63	93.56 58	70.49 33	92.94 126	95.28 19	82.47 32	78.70 143	92.07 153	72.45 34	95.41 181	82.11 116	85.78 145	94.44 119

MSLP-MVS++		86.27 54	85.91 61	87.35 45	92.01 106	68.97 67	95.04 40	92.70 119	79.04 92	81.50 101	96.50 28	58.98 168	96.78 119	83.49 106	93.93 41	96.29 35

VNet		86.20 55	85.65 66	87.84 30	93.92 47	69.99 39	95.73 23	95.94 7	78.43 101	86.00 58	93.07 127	58.22 175	97.00 101	85.22 84	84.33 159	96.52 23

MVS_111021_HR		86.19 56	85.80 63	87.37 44	93.17 70	69.79 48	93.99 75	93.76 73	79.08 89	78.88 139	93.99 110	62.25 130	98.15 37	85.93 81	91.15 84	94.15 131

SPE-MVS-test		86.14 57	87.01 39	83.52 182	92.63 88	59.36 311	95.49 27	91.92 156	80.09 67	85.46 65	95.53 55	61.82 135	95.77 162	86.77 75	93.37 52	95.41 61

ACMMP_NAP		86.05 58	85.80 63	86.80 62	91.58 121	67.53 106	91.79 180	93.49 88	74.93 152	84.61 72	95.30 62	59.42 159	97.92 42	86.13 78	94.92 20	94.94 90

testing99		86.01 59	85.47 68	87.63 38	93.62 55	71.25 23	93.47 107	95.23 21	80.42 61	80.60 115	91.95 156	71.73 41	96.50 130	80.02 136	82.22 179	95.13 80

ETV-MVS		86.01 59	86.11 56	85.70 102	90.21 152	67.02 121	93.43 109	91.92 156	81.21 52	84.13 79	94.07 109	60.93 143	95.63 170	89.28 49	89.81 99	94.46 118

testing91		85.93 61	85.31 72	87.78 32	93.59 57	71.47 19	93.50 104	95.08 28	80.26 63	80.53 116	91.93 157	70.43 45	96.51 129	80.32 134	82.13 181	95.37 64

APD-MVS		85.93 61	85.99 59	85.76 99	95.98 26	65.21 164	93.59 99	92.58 129	66.54 296	86.17 56	95.88 45	63.83 102	97.00 101	86.39 77	92.94 57	95.06 83
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PAPM		85.89 63	85.46 69	87.18 49	88.20 205	72.42 15	92.41 152	92.77 117	82.11 37	80.34 119	93.07 127	68.27 53	95.02 193	78.39 152	93.59 49	94.09 134

CS-MVS		85.80 64	86.65 48	83.27 191	92.00 107	58.92 315	95.31 31	91.86 161	79.97 68	84.82 71	95.40 58	62.26 129	95.51 180	86.11 79	92.08 68	95.37 64

fmvsm_s_conf0.5_n_a		85.75 65	86.09 57	84.72 137	85.73 265	63.58 212	93.79 89	89.32 266	81.42 48	90.21 26	96.91 15	62.41 128	97.67 54	94.48 12	80.56 197	92.90 176

test_fmvsmconf0.1_n		85.71 66	86.08 58	84.62 145	80.83 328	62.33 246	93.84 86	88.81 292	83.50 22	87.00 49	96.01 43	63.36 113	96.93 113	94.04 16	87.29 127	94.61 107

CDPH-MVS		85.71 66	85.46 69	86.46 75	94.75 34	67.19 113	93.89 81	92.83 116	70.90 249	83.09 88	95.28 63	63.62 107	97.36 75	80.63 130	94.18 37	94.84 94

casdiffmvs_mvg		85.66 68	85.18 74	87.09 52	88.22 204	69.35 59	93.74 92	91.89 159	81.47 44	80.10 121	91.45 166	64.80 90	96.35 137	87.23 69	87.69 122	95.58 56
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 69	85.93 60	84.68 141	82.95 311	63.48 217	94.03 74	89.46 260	81.69 41	89.86 29	96.74 22	61.85 134	97.75 50	94.74 11	82.01 183	92.81 178

MGCFI-Net		85.59 70	85.73 65	85.17 121	91.41 129	62.44 242	92.87 130	91.31 186	79.65 75	86.99 50	95.14 73	62.90 122	96.12 146	87.13 70	84.13 164	96.96 13

GDP-MVS		85.54 71	85.32 71	86.18 84	87.64 220	67.95 95	92.91 129	92.36 134	77.81 111	83.69 82	94.31 100	72.84 30	96.41 134	80.39 133	85.95 143	94.19 127

DeepC-MVS	77.85 3	85.52 72	85.24 73	86.37 79	88.80 187	66.64 130	92.15 159	93.68 79	81.07 53	76.91 162	93.64 117	62.59 125	98.44 31	85.50 82	92.84 59	94.03 138
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 73	84.87 80	86.84 59	88.25 202	69.07 63	93.04 121	91.76 166	81.27 51	80.84 112	92.07 153	64.23 97	96.06 152	84.98 89	87.43 126	95.39 62
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 74	85.08 76	86.06 87	93.09 73	65.65 153	93.89 81	93.41 93	73.75 173	79.94 123	94.68 85	60.61 146	98.03 39	82.63 113	93.72 46	94.52 113

MP-MVS-pluss		85.24 75	85.13 75	85.56 105	91.42 126	65.59 155	91.54 190	92.51 131	74.56 155	80.62 114	95.64 50	59.15 163	97.00 101	86.94 73	93.80 43	94.07 136
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
testing222		85.18 76	84.69 83	86.63 68	92.91 78	69.91 43	92.61 143	95.80 9	80.31 62	80.38 118	92.27 147	68.73 51	95.19 190	75.94 164	83.27 169	94.81 98

PAPR		85.15 77	84.47 84	87.18 49	96.02 25	68.29 82	91.85 178	93.00 111	76.59 133	79.03 135	95.00 74	61.59 136	97.61 61	78.16 153	89.00 108	95.63 54

fmvsm_s_conf0.5_n_2		85.06 78	85.60 67	83.44 188	86.92 242	60.53 288	94.41 54	87.31 326	83.30 23	88.72 36	96.72 23	54.28 226	97.75 50	94.07 15	84.68 156	92.04 201

MP-MVS		85.02 79	84.97 78	85.17 121	92.60 89	64.27 191	93.24 113	92.27 137	73.13 184	79.63 127	94.43 91	61.90 132	97.17 89	85.00 88	92.56 61	94.06 137
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
baseline		85.01 80	84.44 85	86.71 65	88.33 199	68.73 72	90.24 245	91.82 165	81.05 54	81.18 106	92.50 139	63.69 105	96.08 151	84.45 95	86.71 137	95.32 69

CHOSEN 1792x2688		84.98 81	83.45 99	89.57 11	89.94 157	75.14 6	92.07 165	92.32 135	81.87 39	75.68 171	88.27 216	60.18 149	98.60 27	80.46 132	90.27 95	94.96 88

MVSMamba_PlusPlus		84.97 82	83.65 93	88.93 14	90.17 153	74.04 8	87.84 294	92.69 122	62.18 334	81.47 103	87.64 230	71.47 42	96.28 139	84.69 92	94.74 31	96.47 28

EIA-MVS		84.84 83	84.88 79	84.69 140	91.30 131	62.36 245	93.85 83	92.04 149	79.45 78	79.33 132	94.28 102	62.42 127	96.35 137	80.05 135	91.25 83	95.38 63

fmvsm_s_conf0.1_n_a		84.76 84	84.84 81	84.53 147	80.23 338	63.50 216	92.79 132	88.73 295	80.46 59	89.84 30	96.65 25	60.96 142	97.57 64	93.80 18	80.14 199	92.53 185

HFP-MVS		84.73 85	84.40 86	85.72 101	93.75 52	65.01 170	93.50 104	93.19 101	72.19 209	79.22 133	94.93 77	59.04 166	97.67 54	81.55 120	92.21 64	94.49 116

MVS		84.66 86	82.86 118	90.06 2	90.93 138	74.56 7	87.91 292	95.54 14	68.55 280	72.35 214	94.71 84	59.78 155	98.90 20	81.29 126	94.69 32	96.74 16

GST-MVS		84.63 87	84.29 87	85.66 103	92.82 82	65.27 162	93.04 121	93.13 104	73.20 182	78.89 136	94.18 105	59.41 160	97.85 46	81.45 122	92.48 63	93.86 146

EC-MVSNet		84.53 88	85.04 77	83.01 196	89.34 169	61.37 268	94.42 53	91.09 199	77.91 109	83.24 84	94.20 104	58.37 173	95.40 182	85.35 83	91.41 79	92.27 195

fmvsm_s_conf0.1_n_2		84.40 89	84.78 82	83.27 191	85.25 272	60.41 291	94.13 66	85.69 346	83.05 25	87.99 39	96.37 30	52.75 242	97.68 52	93.75 19	84.05 165	91.71 206

ACMMPR		84.37 90	84.06 88	85.28 116	93.56 58	64.37 186	93.50 104	93.15 103	72.19 209	78.85 141	94.86 80	56.69 195	97.45 69	81.55 120	92.20 65	94.02 139

region2R		84.36 91	84.03 89	85.36 112	93.54 60	64.31 189	93.43 109	92.95 112	72.16 212	78.86 140	94.84 81	56.97 190	97.53 66	81.38 124	92.11 67	94.24 125

LFMVS		84.34 92	82.73 120	89.18 13	94.76 33	73.25 11	94.99 43	91.89 159	71.90 217	82.16 97	93.49 121	47.98 288	97.05 96	82.55 114	84.82 152	97.25 8

test_yl		84.28 93	83.16 109	87.64 34	94.52 37	69.24 60	95.78 18	95.09 26	69.19 272	81.09 107	92.88 133	57.00 188	97.44 70	81.11 128	81.76 185	96.23 38

DCV-MVSNet		84.28 93	83.16 109	87.64 34	94.52 37	69.24 60	95.78 18	95.09 26	69.19 272	81.09 107	92.88 133	57.00 188	97.44 70	81.11 128	81.76 185	96.23 38

diffmvs		84.28 93	83.83 90	85.61 104	87.40 226	68.02 92	90.88 220	89.24 269	80.54 57	81.64 100	92.52 138	59.83 154	94.52 218	87.32 67	85.11 150	94.29 122
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 93	83.36 105	87.02 55	92.22 96	67.74 99	84.65 320	94.50 47	79.15 86	82.23 96	87.93 225	66.88 64	96.94 111	80.53 131	82.20 180	96.39 33

ETVMVS		84.22 97	83.71 91	85.76 99	92.58 90	68.25 86	92.45 151	95.53 15	79.54 77	79.46 129	91.64 164	70.29 46	94.18 230	69.16 226	82.76 175	94.84 94

MAR-MVS		84.18 98	83.43 100	86.44 76	96.25 21	65.93 148	94.28 60	94.27 60	74.41 157	79.16 134	95.61 51	53.99 228	98.88 22	69.62 220	93.26 54	94.50 115
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 99	83.20 108	87.05 54	91.56 122	69.82 46	89.99 254	92.05 148	77.77 112	82.84 90	86.57 247	63.93 101	96.09 148	74.91 175	89.18 105	95.25 77

CANet_DTU		84.09 100	83.52 94	85.81 96	90.30 150	66.82 125	91.87 176	89.01 284	85.27 9	86.09 57	93.74 114	47.71 292	96.98 105	77.90 155	89.78 101	93.65 151

ET-MVSNet_ETH3D		84.01 101	83.15 111	86.58 71	90.78 143	70.89 28	94.74 48	94.62 43	81.44 47	58.19 349	93.64 117	73.64 25	92.35 296	82.66 112	78.66 214	96.50 27

PVSNet_Blended_VisFu		83.97 102	83.50 96	85.39 110	90.02 155	66.59 133	93.77 90	91.73 167	77.43 121	77.08 161	89.81 198	63.77 104	96.97 108	79.67 138	88.21 116	92.60 182

MTAPA		83.91 103	83.38 104	85.50 106	91.89 113	65.16 166	81.75 345	92.23 138	75.32 147	80.53 116	95.21 70	56.06 204	97.16 92	84.86 91	92.55 62	94.18 128

XVS		83.87 104	83.47 98	85.05 123	93.22 66	63.78 201	92.92 127	92.66 124	73.99 165	78.18 146	94.31 100	55.25 210	97.41 72	79.16 143	91.58 76	93.95 141

Effi-MVS+		83.82 105	82.76 119	86.99 56	89.56 165	69.40 54	91.35 201	86.12 340	72.59 196	83.22 87	92.81 136	59.60 157	96.01 156	81.76 119	87.80 121	95.56 57

test_fmvsmvis_n_1920		83.80 106	83.48 97	84.77 134	82.51 314	63.72 205	91.37 199	83.99 363	81.42 48	77.68 151	95.74 48	58.37 173	97.58 62	93.38 20	86.87 131	93.00 173

EI-MVSNet-Vis-set		83.77 107	83.67 92	84.06 163	92.79 85	63.56 213	91.76 183	94.81 34	79.65 75	77.87 149	94.09 107	63.35 114	97.90 43	79.35 141	79.36 206	90.74 224

MVSFormer		83.75 108	82.88 117	86.37 79	89.24 177	71.18 24	89.07 272	90.69 210	65.80 301	87.13 46	94.34 98	64.99 85	92.67 283	72.83 188	91.80 72	95.27 74

CP-MVS		83.71 109	83.40 103	84.65 142	93.14 71	63.84 199	94.59 51	92.28 136	71.03 247	77.41 155	94.92 78	55.21 213	96.19 143	81.32 125	90.70 88	93.91 143

test_fmvsmconf0.01_n		83.70 110	83.52 94	84.25 160	75.26 381	61.72 260	92.17 158	87.24 328	82.36 34	84.91 70	95.41 57	55.60 208	96.83 118	92.85 24	85.87 144	94.21 126

baseline2		83.68 111	83.42 102	84.48 150	87.37 227	66.00 145	90.06 249	95.93 8	79.71 74	69.08 252	90.39 184	77.92 6	96.28 139	78.91 147	81.38 189	91.16 220

reproduce-ours		83.51 112	83.33 106	84.06 163	92.18 99	60.49 289	90.74 226	92.04 149	64.35 311	83.24 84	95.59 53	59.05 164	97.27 84	83.61 103	89.17 106	94.41 120

our_new_method		83.51 112	83.33 106	84.06 163	92.18 99	60.49 289	90.74 226	92.04 149	64.35 311	83.24 84	95.59 53	59.05 164	97.27 84	83.61 103	89.17 106	94.41 120

thisisatest0515		83.41 114	82.49 124	86.16 85	89.46 168	68.26 84	93.54 101	94.70 39	74.31 160	75.75 169	90.92 174	72.62 32	96.52 128	69.64 218	81.50 188	93.71 149

PVSNet_BlendedMVS		83.38 115	83.43 100	83.22 193	93.76 50	67.53 106	94.06 68	93.61 81	79.13 87	81.00 110	85.14 262	63.19 116	97.29 80	87.08 71	73.91 251	84.83 322

test2506		83.29 116	82.92 116	84.37 154	88.39 197	63.18 226	92.01 168	91.35 185	77.66 115	78.49 145	91.42 167	64.58 93	95.09 192	73.19 184	89.23 103	94.85 91

PGM-MVS		83.25 117	82.70 121	84.92 126	92.81 84	64.07 195	90.44 235	92.20 142	71.28 241	77.23 158	94.43 91	55.17 214	97.31 79	79.33 142	91.38 80	93.37 157

HPM-MVS		83.25 117	82.95 115	84.17 161	92.25 95	62.88 235	90.91 217	91.86 161	70.30 258	77.12 159	93.96 111	56.75 193	96.28 139	82.04 117	91.34 82	93.34 158
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
reproduce_model		83.15 119	82.96 113	83.73 174	92.02 103	59.74 303	90.37 239	92.08 147	63.70 318	82.86 89	95.48 56	58.62 170	97.17 89	83.06 109	88.42 114	94.26 123

EI-MVSNet-UG-set		83.14 120	82.96 113	83.67 179	92.28 94	63.19 225	91.38 198	94.68 40	79.22 84	76.60 164	93.75 113	62.64 124	97.76 49	78.07 154	78.01 217	90.05 233

testing3-2		83.11 121	83.15 111	82.98 197	91.92 110	64.01 197	94.39 57	95.37 16	78.32 102	75.53 176	90.06 196	73.18 27	93.18 262	74.34 180	75.27 240	91.77 205

VDD-MVS		83.06 122	81.81 133	86.81 61	90.86 141	67.70 100	95.40 29	91.50 180	75.46 144	81.78 99	92.34 146	40.09 330	97.13 94	86.85 74	82.04 182	95.60 55

h-mvs33		83.01 123	82.56 123	84.35 155	89.34 169	62.02 252	92.72 135	93.76 73	81.45 45	82.73 93	92.25 149	60.11 150	97.13 94	87.69 61	62.96 331	93.91 143

PAPM_NR		82.97 124	81.84 132	86.37 79	94.10 44	66.76 128	87.66 298	92.84 115	69.96 262	74.07 191	93.57 119	63.10 119	97.50 68	70.66 213	90.58 90	94.85 91

mPP-MVS		82.96 125	82.44 125	84.52 148	92.83 80	62.92 233	92.76 133	91.85 163	71.52 237	75.61 174	94.24 103	53.48 236	96.99 104	78.97 146	90.73 87	93.64 152

SR-MVS		82.81 126	82.58 122	83.50 185	93.35 64	61.16 271	92.23 157	91.28 190	64.48 310	81.27 104	95.28 63	53.71 232	95.86 158	82.87 111	88.77 111	93.49 155

DP-MVS Recon		82.73 127	81.65 134	85.98 89	97.31 4	67.06 118	95.15 36	91.99 153	69.08 275	76.50 166	93.89 112	54.48 222	98.20 36	70.76 211	85.66 147	92.69 179

CLD-MVS		82.73 127	82.35 127	83.86 170	87.90 212	67.65 102	95.45 28	92.18 145	85.06 10	72.58 207	92.27 147	52.46 245	95.78 160	84.18 97	79.06 209	88.16 260
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
sss		82.71 129	82.38 126	83.73 174	89.25 174	59.58 306	92.24 156	94.89 31	77.96 107	79.86 124	92.38 144	56.70 194	97.05 96	77.26 158	80.86 193	94.55 109

3Dnovator	73.91 6	82.69 130	80.82 147	88.31 26	89.57 164	71.26 22	92.60 144	94.39 55	78.84 94	67.89 273	92.48 142	48.42 283	98.52 28	68.80 231	94.40 36	95.15 79

RRT-MVS		82.61 131	81.16 138	86.96 57	91.10 135	68.75 71	87.70 297	92.20 142	76.97 124	72.68 203	87.10 241	51.30 257	96.41 134	83.56 105	87.84 120	95.74 51

MVSTER		82.47 132	82.05 128	83.74 172	92.68 87	69.01 65	91.90 175	93.21 98	79.83 70	72.14 215	85.71 258	74.72 17	94.72 205	75.72 166	72.49 261	87.50 267

TESTMET0.1,1		82.41 133	81.98 131	83.72 176	88.08 206	63.74 203	92.70 137	93.77 72	79.30 82	77.61 153	87.57 232	58.19 176	94.08 234	73.91 182	86.68 138	93.33 160

CostFormer		82.33 134	81.15 139	85.86 94	89.01 182	68.46 78	82.39 342	93.01 109	75.59 142	80.25 120	81.57 306	72.03 39	94.96 197	79.06 145	77.48 225	94.16 130

API-MVS		82.28 135	80.53 155	87.54 41	96.13 22	70.59 31	93.63 97	91.04 205	65.72 303	75.45 177	92.83 135	56.11 203	98.89 21	64.10 275	89.75 102	93.15 165

IB-MVS	77.80 4	82.18 136	80.46 157	87.35 45	89.14 179	70.28 36	95.59 26	95.17 24	78.85 93	70.19 240	85.82 256	70.66 44	97.67 54	72.19 200	66.52 302	94.09 134
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		82.16 137	81.12 140	85.26 118	86.42 248	68.72 73	92.59 146	90.44 220	73.12 185	84.20 76	94.36 93	38.04 343	95.73 164	84.12 98	86.81 132	91.33 213

xiu_mvs_v1_base		82.16 137	81.12 140	85.26 118	86.42 248	68.72 73	92.59 146	90.44 220	73.12 185	84.20 76	94.36 93	38.04 343	95.73 164	84.12 98	86.81 132	91.33 213

xiu_mvs_v1_base_debi		82.16 137	81.12 140	85.26 118	86.42 248	68.72 73	92.59 146	90.44 220	73.12 185	84.20 76	94.36 93	38.04 343	95.73 164	84.12 98	86.81 132	91.33 213

3Dnovator+	73.60 7	82.10 140	80.60 154	86.60 69	90.89 140	66.80 127	95.20 34	93.44 90	74.05 164	67.42 280	92.49 141	49.46 273	97.65 58	70.80 210	91.68 74	95.33 67

MVS_111021_LR		82.02 141	81.52 135	83.51 184	88.42 195	62.88 235	89.77 257	88.93 288	76.78 129	75.55 175	93.10 124	50.31 264	95.38 184	83.82 102	87.02 129	92.26 196

PMMVS		81.98 142	82.04 129	81.78 231	89.76 161	56.17 341	91.13 213	90.69 210	77.96 107	80.09 122	93.57 119	46.33 302	94.99 196	81.41 123	87.46 125	94.17 129

baseline1		81.84 143	81.03 144	84.28 158	91.60 120	66.62 131	91.08 214	91.66 174	81.87 39	74.86 182	91.67 163	69.98 48	94.92 200	71.76 203	64.75 318	91.29 218

EPP-MVSNet		81.79 144	81.52 135	82.61 207	88.77 188	60.21 297	93.02 123	93.66 80	68.52 281	72.90 201	90.39 184	72.19 38	94.96 197	74.93 174	79.29 208	92.67 180

WBMVS		81.67 145	80.98 146	83.72 176	93.07 74	69.40 54	94.33 58	93.05 107	76.84 127	72.05 217	84.14 273	74.49 19	93.88 248	72.76 191	68.09 290	87.88 262

test_vis1_n_1920		81.66 146	82.01 130	80.64 258	82.24 316	55.09 349	94.76 47	86.87 330	81.67 42	84.40 75	94.63 86	38.17 340	94.67 209	91.98 33	83.34 168	92.16 199

APD-MVS_3200maxsize		81.64 147	81.32 137	82.59 208	92.36 92	58.74 317	91.39 196	91.01 206	63.35 322	79.72 126	94.62 87	51.82 248	96.14 145	79.71 137	87.93 119	92.89 177

mvsmamba		81.55 148	80.72 149	84.03 167	91.42 126	66.93 123	83.08 336	89.13 277	78.55 100	67.50 278	87.02 242	51.79 250	90.07 338	87.48 64	90.49 92	95.10 82

ACMMP		81.49 149	80.67 151	83.93 169	91.71 118	62.90 234	92.13 160	92.22 141	71.79 224	71.68 223	93.49 121	50.32 263	96.96 109	78.47 151	84.22 163	91.93 203
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
CDS-MVSNet		81.43 150	80.74 148	83.52 182	86.26 252	64.45 180	92.09 163	90.65 214	75.83 140	73.95 193	89.81 198	63.97 100	92.91 273	71.27 206	82.82 172	93.20 164
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
mvs_anonymous		81.36 151	79.99 162	85.46 107	90.39 149	68.40 79	86.88 309	90.61 215	74.41 157	70.31 239	84.67 267	63.79 103	92.32 298	73.13 185	85.70 146	95.67 52

ECVR-MVS		81.29 152	80.38 158	84.01 168	88.39 197	61.96 254	92.56 149	86.79 332	77.66 115	76.63 163	91.42 167	46.34 301	95.24 189	74.36 179	89.23 103	94.85 91

thisisatest0530		81.15 153	80.07 159	84.39 153	88.26 201	65.63 154	91.40 194	94.62 43	71.27 242	70.93 230	89.18 204	72.47 33	96.04 153	65.62 264	76.89 231	91.49 209

Fast-Effi-MVS+		81.14 154	80.01 161	84.51 149	90.24 151	65.86 149	94.12 67	89.15 275	73.81 172	75.37 178	88.26 217	57.26 183	94.53 217	66.97 249	84.92 151	93.15 165

HQP-MVS		81.14 154	80.64 152	82.64 206	87.54 222	63.66 210	94.06 68	91.70 172	79.80 71	74.18 187	90.30 186	51.63 253	95.61 172	77.63 156	78.90 210	88.63 251

hse-mvs2		81.12 156	81.11 143	81.16 245	86.52 247	57.48 330	89.40 265	91.16 193	81.45 45	82.73 93	90.49 182	60.11 150	94.58 210	87.69 61	60.41 358	91.41 212

SR-MVS-dyc-post		81.06 157	80.70 150	82.15 222	92.02 103	58.56 319	90.90 218	90.45 217	62.76 329	78.89 136	94.46 89	51.26 258	95.61 172	78.77 149	86.77 135	92.28 192

HyFIR lowres test		81.03 158	79.56 169	85.43 108	87.81 216	68.11 90	90.18 246	90.01 242	70.65 255	72.95 200	86.06 254	63.61 108	94.50 219	75.01 173	79.75 203	93.67 150

nrg030		80.93 159	79.86 164	84.13 162	83.69 300	68.83 69	93.23 114	91.20 191	75.55 143	75.06 180	88.22 220	63.04 120	94.74 204	81.88 118	66.88 299	88.82 249

Vis-MVSNet		80.92 160	79.98 163	83.74 172	88.48 192	61.80 256	93.44 108	88.26 312	73.96 168	77.73 150	91.76 160	49.94 268	94.76 202	65.84 261	90.37 94	94.65 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test1111		80.84 161	80.02 160	83.33 189	87.87 213	60.76 279	92.62 142	86.86 331	77.86 110	75.73 170	91.39 169	46.35 300	94.70 208	72.79 190	88.68 112	94.52 113

UWE-MVS		80.81 162	81.01 145	80.20 268	89.33 171	57.05 335	91.91 174	94.71 38	75.67 141	75.01 181	89.37 202	63.13 118	91.44 322	67.19 246	82.80 174	92.12 200

1314		80.70 163	78.95 181	85.94 91	87.77 219	67.56 104	87.91 292	92.55 130	72.17 211	67.44 279	93.09 125	50.27 265	97.04 99	71.68 205	87.64 123	93.23 162

tpmrst		80.57 164	79.14 179	84.84 129	90.10 154	68.28 83	81.70 346	89.72 255	77.63 117	75.96 168	79.54 338	64.94 87	92.71 280	75.43 168	77.28 228	93.55 153

1112_ss		80.56 165	79.83 165	82.77 201	88.65 189	60.78 277	92.29 154	88.36 306	72.58 197	72.46 211	94.95 75	65.09 84	93.42 259	66.38 255	77.71 219	94.10 133

VDDNet		80.50 166	78.26 189	87.21 47	86.19 253	69.79 48	94.48 52	91.31 186	60.42 348	79.34 131	90.91 175	38.48 338	96.56 126	82.16 115	81.05 191	95.27 74

BH-w/o		80.49 167	79.30 176	84.05 166	90.83 142	64.36 188	93.60 98	89.42 263	74.35 159	69.09 251	90.15 192	55.23 212	95.61 172	64.61 272	86.43 141	92.17 198

test_cas_vis1_n_1920		80.45 168	80.61 153	79.97 277	78.25 364	57.01 337	94.04 72	88.33 307	79.06 91	82.81 92	93.70 115	38.65 335	91.63 314	90.82 42	79.81 201	91.27 219

TAMVS		80.37 169	79.45 172	83.13 195	85.14 275	63.37 218	91.23 207	90.76 209	74.81 154	72.65 205	88.49 211	60.63 145	92.95 268	69.41 222	81.95 184	93.08 169

HQP_MVS		80.34 170	79.75 166	82.12 224	86.94 238	62.42 243	93.13 117	91.31 186	78.81 95	72.53 208	89.14 206	50.66 261	95.55 177	76.74 159	78.53 215	88.39 257

SDMVSNet		80.26 171	78.88 182	84.40 152	89.25 174	67.63 103	85.35 316	93.02 108	76.77 130	70.84 231	87.12 239	47.95 289	96.09 148	85.04 87	74.55 242	89.48 243

HPM-MVS_fast		80.25 172	79.55 171	82.33 214	91.55 123	59.95 300	91.32 203	89.16 274	65.23 307	74.71 184	93.07 127	47.81 291	95.74 163	74.87 177	88.23 115	91.31 217

ab-mvs		80.18 173	78.31 188	85.80 97	88.44 194	65.49 160	83.00 339	92.67 123	71.82 223	77.36 156	85.01 263	54.50 219	96.59 123	76.35 163	75.63 238	95.32 69

IS-MVSNet		80.14 174	79.41 173	82.33 214	87.91 211	60.08 299	91.97 172	88.27 310	72.90 192	71.44 227	91.73 162	61.44 137	93.66 254	62.47 289	86.53 139	93.24 161

test-LLR		80.10 175	79.56 169	81.72 233	86.93 240	61.17 269	92.70 137	91.54 177	71.51 238	75.62 172	86.94 243	53.83 229	92.38 293	72.21 198	84.76 154	91.60 207

PVSNet	73.49 8	80.05 176	78.63 184	84.31 156	90.92 139	64.97 171	92.47 150	91.05 204	79.18 85	72.43 212	90.51 181	37.05 355	94.06 236	68.06 235	86.00 142	93.90 145

UA-Net		80.02 177	79.65 167	81.11 247	89.33 171	57.72 326	86.33 313	89.00 287	77.44 120	81.01 109	89.15 205	59.33 161	95.90 157	61.01 296	84.28 161	89.73 239

test-mter		79.96 178	79.38 175	81.72 233	86.93 240	61.17 269	92.70 137	91.54 177	73.85 170	75.62 172	86.94 243	49.84 270	92.38 293	72.21 198	84.76 154	91.60 207

QAPM		79.95 179	77.39 207	87.64 34	89.63 163	71.41 20	93.30 112	93.70 78	65.34 306	67.39 282	91.75 161	47.83 290	98.96 16	57.71 312	89.81 99	92.54 184

UGNet		79.87 180	78.68 183	83.45 187	89.96 156	61.51 263	92.13 160	90.79 208	76.83 128	78.85 141	86.33 251	38.16 341	96.17 144	67.93 238	87.17 128	92.67 180
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		79.80 181	77.95 195	85.34 113	88.28 200	68.26 84	81.56 348	91.42 183	70.11 260	77.59 154	80.50 324	67.40 61	94.26 228	67.34 243	77.35 226	93.51 154

thres200		79.66 182	78.33 187	83.66 180	92.54 91	65.82 151	93.06 119	96.31 3	74.90 153	73.30 197	88.66 209	59.67 156	95.61 172	47.84 353	78.67 213	89.56 242

CPTT-MVS		79.59 183	79.16 178	80.89 256	91.54 124	59.80 302	92.10 162	88.54 303	60.42 348	72.96 199	93.28 123	48.27 284	92.80 277	78.89 148	86.50 140	90.06 232

Test_1112_low_res		79.56 184	78.60 185	82.43 210	88.24 203	60.39 293	92.09 163	87.99 317	72.10 213	71.84 219	87.42 234	64.62 92	93.04 264	65.80 262	77.30 227	93.85 147

tttt0517		79.50 185	78.53 186	82.41 213	87.22 231	61.43 267	89.75 258	94.76 35	69.29 270	67.91 271	88.06 224	72.92 29	95.63 170	62.91 285	73.90 252	90.16 231

reproduce_monomvs		79.49 186	79.11 180	80.64 258	92.91 78	61.47 266	91.17 212	93.28 96	83.09 24	64.04 311	82.38 293	66.19 70	94.57 212	81.19 127	57.71 366	85.88 305

FIs		79.47 187	79.41 173	79.67 285	85.95 259	59.40 308	91.68 187	93.94 67	78.06 106	68.96 257	88.28 215	66.61 67	91.77 310	66.20 258	74.99 241	87.82 263

BH-RMVSNet		79.46 188	77.65 198	84.89 127	91.68 119	65.66 152	93.55 100	88.09 315	72.93 189	73.37 196	91.12 173	46.20 304	96.12 146	56.28 318	85.61 148	92.91 175

PCF-MVS	73.15 9	79.29 189	77.63 199	84.29 157	86.06 257	65.96 147	87.03 305	91.10 198	69.86 264	69.79 247	90.64 177	57.54 182	96.59 123	64.37 274	82.29 176	90.32 229
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Vis-MVSNet (Re-imp)		79.24 190	79.57 168	78.24 305	88.46 193	52.29 360	90.41 237	89.12 278	74.24 161	69.13 250	91.91 158	65.77 77	90.09 337	59.00 308	88.09 117	92.33 189

114514_t		79.17 191	77.67 197	83.68 178	95.32 29	65.53 158	92.85 131	91.60 176	63.49 320	67.92 270	90.63 179	46.65 297	95.72 168	67.01 248	83.54 166	89.79 237

FA-MVS(test-final)		79.12 192	77.23 209	84.81 133	90.54 145	63.98 198	81.35 351	91.71 169	71.09 246	74.85 183	82.94 286	52.85 240	97.05 96	67.97 236	81.73 187	93.41 156

VPA-MVSNet		79.03 193	78.00 193	82.11 227	85.95 259	64.48 179	93.22 115	94.66 41	75.05 151	74.04 192	84.95 264	52.17 247	93.52 256	74.90 176	67.04 298	88.32 259

OPM-MVS		79.00 194	78.09 191	81.73 232	83.52 303	63.83 200	91.64 189	90.30 227	76.36 136	71.97 218	89.93 197	46.30 303	95.17 191	75.10 171	77.70 220	86.19 294
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
EI-MVSNet		78.97 195	78.22 190	81.25 242	85.33 269	62.73 238	89.53 262	93.21 98	72.39 204	72.14 215	90.13 193	60.99 140	94.72 205	67.73 240	72.49 261	86.29 291

AdaColmap		78.94 196	77.00 213	84.76 135	96.34 17	65.86 149	92.66 141	87.97 319	62.18 334	70.56 233	92.37 145	43.53 317	97.35 76	64.50 273	82.86 171	91.05 222

GeoE		78.90 197	77.43 203	83.29 190	88.95 183	62.02 252	92.31 153	86.23 338	70.24 259	71.34 228	89.27 203	54.43 223	94.04 239	63.31 281	80.81 195	93.81 148

miper_enhance_ethall		78.86 198	77.97 194	81.54 237	88.00 210	65.17 165	91.41 192	89.15 275	75.19 149	68.79 260	83.98 276	67.17 62	92.82 275	72.73 192	65.30 309	86.62 288

VPNet		78.82 199	77.53 202	82.70 204	84.52 287	66.44 135	93.93 78	92.23 138	80.46 59	72.60 206	88.38 214	49.18 277	93.13 263	72.47 196	63.97 328	88.55 254

EPNet_dtu		78.80 200	79.26 177	77.43 313	88.06 207	49.71 376	91.96 173	91.95 155	77.67 114	76.56 165	91.28 171	58.51 171	90.20 335	56.37 317	80.95 192	92.39 187
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tfpn200view9		78.79 201	77.43 203	82.88 199	92.21 97	64.49 177	92.05 166	96.28 4	73.48 179	71.75 221	88.26 217	60.07 152	95.32 185	45.16 364	77.58 222	88.83 247

TR-MVS		78.77 202	77.37 208	82.95 198	90.49 146	60.88 275	93.67 94	90.07 237	70.08 261	74.51 185	91.37 170	45.69 306	95.70 169	60.12 302	80.32 198	92.29 191

thres400		78.68 203	77.43 203	82.43 210	92.21 97	64.49 177	92.05 166	96.28 4	73.48 179	71.75 221	88.26 217	60.07 152	95.32 185	45.16 364	77.58 222	87.48 268

BH-untuned		78.68 203	77.08 210	83.48 186	89.84 158	63.74 203	92.70 137	88.59 301	71.57 235	66.83 289	88.65 210	51.75 251	95.39 183	59.03 307	84.77 153	91.32 216

OMC-MVS		78.67 205	77.91 196	80.95 254	85.76 264	57.40 332	88.49 282	88.67 298	73.85 170	72.43 212	92.10 152	49.29 276	94.55 216	72.73 192	77.89 218	90.91 223

tpm		78.58 206	77.03 211	83.22 193	85.94 261	64.56 175	83.21 335	91.14 197	78.31 103	73.67 194	79.68 336	64.01 99	92.09 304	66.07 259	71.26 271	93.03 171

OpenMVS	70.45 11	78.54 207	75.92 227	86.41 78	85.93 262	71.68 18	92.74 134	92.51 131	66.49 297	64.56 305	91.96 155	43.88 316	98.10 38	54.61 323	90.65 89	89.44 245

EPMVS		78.49 208	75.98 226	86.02 88	91.21 133	69.68 52	80.23 360	91.20 191	75.25 148	72.48 210	78.11 347	54.65 218	93.69 253	57.66 313	83.04 170	94.69 101

AUN-MVS		78.37 209	77.43 203	81.17 244	86.60 245	57.45 331	89.46 264	91.16 193	74.11 163	74.40 186	90.49 182	55.52 209	94.57 212	74.73 178	60.43 357	91.48 210

thres100view900		78.37 209	77.01 212	82.46 209	91.89 113	63.21 224	91.19 211	96.33 1	72.28 207	70.45 236	87.89 226	60.31 147	95.32 185	45.16 364	77.58 222	88.83 247

GA-MVS		78.33 211	76.23 222	84.65 142	83.65 301	66.30 139	91.44 191	90.14 235	76.01 138	70.32 238	84.02 275	42.50 321	94.72 205	70.98 208	77.00 230	92.94 174

cascas		78.18 212	75.77 229	85.41 109	87.14 233	69.11 62	92.96 125	91.15 196	66.71 295	70.47 234	86.07 253	37.49 349	96.48 131	70.15 216	79.80 202	90.65 225

UniMVSNet_NR-MVSNet		78.15 213	77.55 201	79.98 275	84.46 289	60.26 295	92.25 155	93.20 100	77.50 119	68.88 258	86.61 246	66.10 72	92.13 302	66.38 255	62.55 335	87.54 266

thres600view7		78.00 214	76.66 217	82.03 229	91.93 109	63.69 208	91.30 204	96.33 1	72.43 202	70.46 235	87.89 226	60.31 147	94.92 200	42.64 376	76.64 232	87.48 268

FC-MVSNet-test		77.99 215	78.08 192	77.70 308	84.89 280	55.51 346	90.27 243	93.75 76	76.87 125	66.80 290	87.59 231	65.71 78	90.23 334	62.89 286	73.94 250	87.37 271

Anonymous202405211		77.96 216	75.33 235	85.87 93	93.73 53	64.52 176	94.85 45	85.36 348	62.52 332	76.11 167	90.18 189	29.43 384	97.29 80	68.51 233	77.24 229	95.81 49

cl22		77.94 217	76.78 215	81.42 239	87.57 221	64.93 173	90.67 229	88.86 291	72.45 201	67.63 277	82.68 290	64.07 98	92.91 273	71.79 201	65.30 309	86.44 289

XXY-MVS		77.94 217	76.44 219	82.43 210	82.60 313	64.44 181	92.01 168	91.83 164	73.59 178	70.00 243	85.82 256	54.43 223	94.76 202	69.63 219	68.02 292	88.10 261

MS-PatchMatch		77.90 219	76.50 218	82.12 224	85.99 258	69.95 42	91.75 185	92.70 119	73.97 167	62.58 327	84.44 271	41.11 327	95.78 160	63.76 278	92.17 66	80.62 369

FMVSNet3		77.73 220	76.04 225	82.80 200	91.20 134	68.99 66	91.87 176	91.99 153	73.35 181	67.04 285	83.19 285	56.62 196	92.14 301	59.80 304	69.34 278	87.28 274

miper_ehance_all_eth		77.60 221	76.44 219	81.09 251	85.70 266	64.41 184	90.65 230	88.64 300	72.31 205	67.37 283	82.52 291	64.77 91	92.64 286	70.67 212	65.30 309	86.24 293

UniMVSNet (Re)		77.58 222	76.78 215	79.98 275	84.11 295	60.80 276	91.76 183	93.17 102	76.56 134	69.93 246	84.78 266	63.32 115	92.36 295	64.89 271	62.51 337	86.78 282

PatchmatchNet		77.46 223	74.63 242	85.96 90	89.55 166	70.35 35	79.97 365	89.55 258	72.23 208	70.94 229	76.91 359	57.03 186	92.79 278	54.27 325	81.17 190	94.74 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v2v482		77.42 224	75.65 231	82.73 202	80.38 334	67.13 117	91.85 178	90.23 232	75.09 150	69.37 248	83.39 282	53.79 231	94.44 220	71.77 202	65.00 315	86.63 287

CHOSEN 280x420		77.35 225	76.95 214	78.55 300	87.07 235	62.68 239	69.71 397	82.95 370	68.80 277	71.48 226	87.27 238	66.03 73	84.00 381	76.47 162	82.81 173	88.95 246

PS-MVSNAJss		77.26 226	76.31 221	80.13 270	80.64 332	59.16 313	90.63 233	91.06 203	72.80 193	68.58 264	84.57 269	53.55 233	93.96 244	72.97 186	71.96 265	87.27 275

gg-mvs-nofinetune		77.18 227	74.31 249	85.80 97	91.42 126	68.36 80	71.78 391	94.72 37	49.61 391	77.12 159	45.92 417	77.41 8	93.98 243	67.62 241	93.16 55	95.05 84

WB-MVSnew		77.14 228	76.18 224	80.01 274	86.18 254	63.24 222	91.26 205	94.11 64	71.72 227	73.52 195	87.29 237	45.14 311	93.00 266	56.98 315	79.42 204	83.80 330

MVP-Stereo		77.12 229	76.23 222	79.79 282	81.72 321	66.34 138	89.29 266	90.88 207	70.56 256	62.01 330	82.88 287	49.34 274	94.13 231	65.55 266	93.80 43	78.88 383
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
sd_testset		77.08 230	75.37 233	82.20 220	89.25 174	62.11 251	82.06 343	89.09 280	76.77 130	70.84 231	87.12 239	41.43 326	95.01 195	67.23 245	74.55 242	89.48 243

MonoMVSNet		76.99 231	75.08 238	82.73 202	83.32 305	63.24 222	86.47 312	86.37 334	79.08 89	66.31 293	79.30 340	49.80 271	91.72 311	79.37 140	65.70 307	93.23 162

dmvs_re		76.93 232	75.36 234	81.61 235	87.78 218	60.71 283	80.00 364	87.99 317	79.42 79	69.02 254	89.47 201	46.77 295	94.32 222	63.38 280	74.45 245	89.81 236

X-MVStestdata		76.86 233	74.13 253	85.05 123	93.22 66	63.78 201	92.92 127	92.66 124	73.99 165	78.18 146	10.19 432	55.25 210	97.41 72	79.16 143	91.58 76	93.95 141

DU-MVS		76.86 233	75.84 228	79.91 278	82.96 309	60.26 295	91.26 205	91.54 177	76.46 135	68.88 258	86.35 249	56.16 201	92.13 302	66.38 255	62.55 335	87.35 272

Anonymous20240529		76.84 235	74.15 252	84.88 128	91.02 136	64.95 172	93.84 86	91.09 199	53.57 379	73.00 198	87.42 234	35.91 359	97.32 78	69.14 227	72.41 263	92.36 188

UWE-MVS-28		76.83 236	77.60 200	74.51 338	84.58 286	50.34 372	88.22 286	94.60 45	74.46 156	66.66 291	88.98 208	62.53 126	85.50 373	57.55 314	80.80 196	87.69 265

c3_l		76.83 236	75.47 232	80.93 255	85.02 278	64.18 194	90.39 238	88.11 314	71.66 228	66.65 292	81.64 304	63.58 111	92.56 287	69.31 224	62.86 332	86.04 299

WR-MVS		76.76 238	75.74 230	79.82 281	84.60 284	62.27 249	92.60 144	92.51 131	76.06 137	67.87 274	85.34 260	56.76 192	90.24 333	62.20 290	63.69 330	86.94 280

v1144		76.73 239	74.88 239	82.27 216	80.23 338	66.60 132	91.68 187	90.21 234	73.69 175	69.06 253	81.89 299	52.73 243	94.40 221	69.21 225	65.23 312	85.80 306

IterMVS-LS		76.49 240	75.18 237	80.43 262	84.49 288	62.74 237	90.64 231	88.80 293	72.40 203	65.16 300	81.72 302	60.98 141	92.27 299	67.74 239	64.65 320	86.29 291
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
V42		76.46 241	74.55 245	82.19 221	79.14 352	67.82 97	90.26 244	89.42 263	73.75 173	68.63 263	81.89 299	51.31 256	94.09 233	71.69 204	64.84 316	84.66 323

v148		76.19 242	74.47 247	81.36 240	80.05 340	64.44 181	91.75 185	90.23 232	73.68 176	67.13 284	80.84 319	55.92 206	93.86 251	68.95 229	61.73 346	85.76 309

Effi-MVS+-dtu		76.14 243	75.28 236	78.72 299	83.22 306	55.17 348	89.87 255	87.78 321	75.42 145	67.98 269	81.43 308	45.08 312	92.52 289	75.08 172	71.63 266	88.48 255

cl____		76.07 244	74.67 240	80.28 265	85.15 274	61.76 258	90.12 247	88.73 295	71.16 243	65.43 297	81.57 306	61.15 138	92.95 268	66.54 252	62.17 339	86.13 297

DIV-MVS_self_test		76.07 244	74.67 240	80.28 265	85.14 275	61.75 259	90.12 247	88.73 295	71.16 243	65.42 298	81.60 305	61.15 138	92.94 272	66.54 252	62.16 341	86.14 295

FMVSNet2		76.07 244	74.01 255	82.26 218	88.85 184	67.66 101	91.33 202	91.61 175	70.84 250	65.98 294	82.25 295	48.03 285	92.00 306	58.46 309	68.73 286	87.10 277

v144192		76.05 247	74.03 254	82.12 224	79.50 346	66.55 134	91.39 196	89.71 256	72.30 206	68.17 267	81.33 311	51.75 251	94.03 241	67.94 237	64.19 323	85.77 307

NR-MVSNet		76.05 247	74.59 243	80.44 261	82.96 309	62.18 250	90.83 222	91.73 167	77.12 123	60.96 333	86.35 249	59.28 162	91.80 309	60.74 297	61.34 350	87.35 272

v1192		75.98 249	73.92 256	82.15 222	79.73 342	66.24 141	91.22 208	89.75 250	72.67 195	68.49 265	81.42 309	49.86 269	94.27 226	67.08 247	65.02 314	85.95 302

FE-MVS		75.97 250	73.02 267	84.82 130	89.78 159	65.56 156	77.44 376	91.07 202	64.55 309	72.66 204	79.85 334	46.05 305	96.69 121	54.97 322	80.82 194	92.21 197

eth_miper_zixun_eth		75.96 251	74.40 248	80.66 257	84.66 283	63.02 228	89.28 267	88.27 310	71.88 219	65.73 295	81.65 303	59.45 158	92.81 276	68.13 234	60.53 355	86.14 295

TranMVSNet+NR-MVSNet		75.86 252	74.52 246	79.89 279	82.44 315	60.64 286	91.37 199	91.37 184	76.63 132	67.65 276	86.21 252	52.37 246	91.55 316	61.84 292	60.81 353	87.48 268

SCA		75.82 253	72.76 270	85.01 125	86.63 244	70.08 38	81.06 353	89.19 272	71.60 234	70.01 242	77.09 357	45.53 307	90.25 330	60.43 299	73.27 254	94.68 102

LPG-MVS_test		75.82 253	74.58 244	79.56 289	84.31 292	59.37 309	90.44 235	89.73 253	69.49 267	64.86 301	88.42 212	38.65 335	94.30 224	72.56 194	72.76 258	85.01 320

GBi-Net		75.65 255	73.83 257	81.10 248	88.85 184	65.11 167	90.01 251	90.32 223	70.84 250	67.04 285	80.25 329	48.03 285	91.54 317	59.80 304	69.34 278	86.64 284

test1		75.65 255	73.83 257	81.10 248	88.85 184	65.11 167	90.01 251	90.32 223	70.84 250	67.04 285	80.25 329	48.03 285	91.54 317	59.80 304	69.34 278	86.64 284

v1921920		75.63 257	73.49 262	82.06 228	79.38 347	66.35 137	91.07 216	89.48 259	71.98 214	67.99 268	81.22 314	49.16 279	93.90 247	66.56 251	64.56 321	85.92 304

ACMP	71.68 10	75.58 258	74.23 251	79.62 287	84.97 279	59.64 304	90.80 223	89.07 282	70.39 257	62.95 323	87.30 236	38.28 339	93.87 249	72.89 187	71.45 269	85.36 316
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v8		75.35 259	73.26 265	81.61 235	80.67 331	66.82 125	89.54 261	89.27 268	71.65 229	63.30 319	80.30 328	54.99 216	94.06 236	67.33 244	62.33 338	83.94 328

tpm cat1		75.30 260	72.21 279	84.58 146	88.52 190	67.77 98	78.16 374	88.02 316	61.88 340	68.45 266	76.37 363	60.65 144	94.03 241	53.77 328	74.11 248	91.93 203

PLC	68.80 14	75.23 261	73.68 260	79.86 280	92.93 77	58.68 318	90.64 231	88.30 308	60.90 345	64.43 309	90.53 180	42.38 322	94.57 212	56.52 316	76.54 233	86.33 290
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v1240		75.21 262	72.98 268	81.88 230	79.20 349	66.00 145	90.75 225	89.11 279	71.63 233	67.41 281	81.22 314	47.36 293	93.87 249	65.46 267	64.72 319	85.77 307

Fast-Effi-MVS+-dtu		75.04 263	73.37 263	80.07 271	80.86 327	59.52 307	91.20 210	85.38 347	71.90 217	65.20 299	84.84 265	41.46 325	92.97 267	66.50 254	72.96 257	87.73 264

dp		75.01 264	72.09 280	83.76 171	89.28 173	66.22 142	79.96 366	89.75 250	71.16 243	67.80 275	77.19 356	51.81 249	92.54 288	50.39 337	71.44 270	92.51 186

TAPA-MVS	70.22 12	74.94 265	73.53 261	79.17 294	90.40 148	52.07 361	89.19 270	89.61 257	62.69 331	70.07 241	92.67 137	48.89 282	94.32 222	38.26 390	79.97 200	91.12 221
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SSC-MVS3.2		74.92 266	73.32 264	79.74 284	86.53 246	60.31 294	89.03 275	92.70 119	78.61 99	68.98 256	83.34 283	41.93 324	92.23 300	52.77 332	65.97 305	86.69 283

v10		74.77 267	72.54 276	81.46 238	80.33 336	66.71 129	89.15 271	89.08 281	70.94 248	63.08 322	79.86 333	52.52 244	94.04 239	65.70 263	62.17 339	83.64 331

XVG-OURS-SEG-HR		74.70 268	73.08 266	79.57 288	78.25 364	57.33 333	80.49 356	87.32 324	63.22 324	68.76 261	90.12 195	44.89 313	91.59 315	70.55 214	74.09 249	89.79 237

ACMM	69.62 13	74.34 269	72.73 272	79.17 294	84.25 294	57.87 324	90.36 240	89.93 244	63.17 326	65.64 296	86.04 255	37.79 347	94.10 232	65.89 260	71.52 268	85.55 312
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CNLPA		74.31 270	72.30 278	80.32 263	91.49 125	61.66 261	90.85 221	80.72 376	56.67 371	63.85 314	90.64 177	46.75 296	90.84 325	53.79 327	75.99 237	88.47 256

XVG-OURS		74.25 271	72.46 277	79.63 286	78.45 362	57.59 329	80.33 358	87.39 323	63.86 316	68.76 261	89.62 200	40.50 329	91.72 311	69.00 228	74.25 247	89.58 240

test_fmvs1		74.07 272	73.69 259	75.22 331	78.91 356	47.34 389	89.06 274	74.69 392	63.68 319	79.41 130	91.59 165	24.36 394	87.77 357	85.22 84	76.26 235	90.55 228

CVMVSNet		74.04 273	74.27 250	73.33 348	85.33 269	43.94 402	89.53 262	88.39 305	54.33 378	70.37 237	90.13 193	49.17 278	84.05 379	61.83 293	79.36 206	91.99 202

Baseline_NR-MVSNet		73.99 274	72.83 269	77.48 312	80.78 329	59.29 312	91.79 180	84.55 356	68.85 276	68.99 255	80.70 320	56.16 201	92.04 305	62.67 287	60.98 352	81.11 363

pmmvs4		73.92 275	71.81 284	80.25 267	79.17 350	65.24 163	87.43 301	87.26 327	67.64 288	63.46 317	83.91 277	48.96 281	91.53 320	62.94 284	65.49 308	83.96 327

D2MVS		73.80 276	72.02 281	79.15 296	79.15 351	62.97 229	88.58 281	90.07 237	72.94 188	59.22 343	78.30 344	42.31 323	92.70 282	65.59 265	72.00 264	81.79 358

CR-MVSNet		73.79 277	70.82 292	82.70 204	83.15 307	67.96 93	70.25 394	84.00 361	73.67 177	69.97 244	72.41 379	57.82 179	89.48 342	52.99 331	73.13 255	90.64 226

test_djsdf		73.76 278	72.56 275	77.39 314	77.00 374	53.93 354	89.07 272	90.69 210	65.80 301	63.92 312	82.03 298	43.14 320	92.67 283	72.83 188	68.53 287	85.57 311

pmmvs5		73.35 279	71.52 286	78.86 298	78.64 360	60.61 287	91.08 214	86.90 329	67.69 285	63.32 318	83.64 278	44.33 315	90.53 327	62.04 291	66.02 304	85.46 314

Anonymous20231211		73.08 280	70.39 296	81.13 246	90.62 144	63.33 219	91.40 194	90.06 239	51.84 384	64.46 308	80.67 322	36.49 357	94.07 235	63.83 277	64.17 324	85.98 301

tt0805		73.07 281	70.73 293	80.07 271	78.37 363	57.05 335	87.78 295	92.18 145	61.23 344	67.04 285	86.49 248	31.35 377	94.58 210	65.06 270	67.12 297	88.57 253

miper_lstm_enhance		73.05 282	71.73 285	77.03 318	83.80 298	58.32 321	81.76 344	88.88 289	69.80 265	61.01 332	78.23 346	57.19 184	87.51 361	65.34 268	59.53 360	85.27 319

jajsoiax		73.05 282	71.51 287	77.67 309	77.46 371	54.83 350	88.81 277	90.04 240	69.13 274	62.85 325	83.51 280	31.16 378	92.75 279	70.83 209	69.80 274	85.43 315

LCM-MVSNet-Re		72.93 284	71.84 283	76.18 327	88.49 191	48.02 384	80.07 363	70.17 404	73.96 168	52.25 374	80.09 332	49.98 267	88.24 351	67.35 242	84.23 162	92.28 192

pm-mvs1		72.89 285	71.09 289	78.26 304	79.10 353	57.62 328	90.80 223	89.30 267	67.66 286	62.91 324	81.78 301	49.11 280	92.95 268	60.29 301	58.89 363	84.22 326

tpmvs		72.88 286	69.76 302	82.22 219	90.98 137	67.05 119	78.22 373	88.30 308	63.10 327	64.35 310	74.98 370	55.09 215	94.27 226	43.25 370	69.57 277	85.34 317

test0.0.03 1		72.76 287	72.71 273	72.88 352	80.25 337	47.99 385	91.22 208	89.45 261	71.51 238	62.51 328	87.66 229	53.83 229	85.06 375	50.16 339	67.84 295	85.58 310

UniMVSNet_ETH3D		72.74 288	70.53 295	79.36 291	78.62 361	56.64 339	85.01 318	89.20 271	63.77 317	64.84 303	84.44 271	34.05 366	91.86 308	63.94 276	70.89 273	89.57 241

mvs_tets		72.71 289	71.11 288	77.52 310	77.41 372	54.52 352	88.45 283	89.76 249	68.76 279	62.70 326	83.26 284	29.49 383	92.71 280	70.51 215	69.62 276	85.34 317

FMVSNet1		72.71 289	69.91 300	81.10 248	83.60 302	65.11 167	90.01 251	90.32 223	63.92 315	63.56 316	80.25 329	36.35 358	91.54 317	54.46 324	66.75 300	86.64 284

test_fmvs1_n		72.69 291	71.92 282	74.99 334	71.15 394	47.08 391	87.34 303	75.67 387	63.48 321	78.08 148	91.17 172	20.16 406	87.87 354	84.65 93	75.57 239	90.01 234

IterMVS		72.65 292	70.83 290	78.09 306	82.17 317	62.96 230	87.64 299	86.28 336	71.56 236	60.44 336	78.85 342	45.42 309	86.66 365	63.30 282	61.83 343	84.65 324
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
myMVS_eth3d		72.58 293	72.74 271	72.10 360	87.87 213	49.45 378	88.07 288	89.01 284	72.91 190	63.11 320	88.10 221	63.63 106	85.54 370	32.73 405	69.23 281	81.32 361

PatchMatch-RL		72.06 294	69.98 297	78.28 303	89.51 167	55.70 345	83.49 328	83.39 368	61.24 343	63.72 315	82.76 288	34.77 363	93.03 265	53.37 330	77.59 221	86.12 298

PVSNet_0	68.08 15	71.81 295	68.32 311	82.27 216	84.68 281	62.31 248	88.68 279	90.31 226	75.84 139	57.93 354	80.65 323	37.85 346	94.19 229	69.94 217	29.05 420	90.31 230

MIMVSNet		71.64 296	68.44 309	81.23 243	81.97 320	64.44 181	73.05 388	88.80 293	69.67 266	64.59 304	74.79 372	32.79 369	87.82 355	53.99 326	76.35 234	91.42 211

test_vis1_n		71.63 297	70.73 293	74.31 342	69.63 400	47.29 390	86.91 307	72.11 398	63.21 325	75.18 179	90.17 190	20.40 404	85.76 369	84.59 94	74.42 246	89.87 235

IterMVS-SCA-FT		71.55 298	69.97 298	76.32 325	81.48 323	60.67 285	87.64 299	85.99 341	66.17 299	59.50 341	78.88 341	45.53 307	83.65 383	62.58 288	61.93 342	84.63 325

v7n		71.31 299	68.65 306	79.28 292	76.40 376	60.77 278	86.71 310	89.45 261	64.17 314	58.77 348	78.24 345	44.59 314	93.54 255	57.76 311	61.75 345	83.52 334

anonymousdsp		71.14 300	69.37 304	76.45 324	72.95 389	54.71 351	84.19 323	88.88 289	61.92 339	62.15 329	79.77 335	38.14 342	91.44 322	68.90 230	67.45 296	83.21 340

F-COLMAP		70.66 301	68.44 309	77.32 315	86.37 251	55.91 343	88.00 290	86.32 335	56.94 369	57.28 358	88.07 223	33.58 367	92.49 290	51.02 335	68.37 288	83.55 332

WR-MVS_H		70.59 302	69.94 299	72.53 354	81.03 326	51.43 365	87.35 302	92.03 152	67.38 289	60.23 338	80.70 320	55.84 207	83.45 385	46.33 360	58.58 365	82.72 347

CP-MVSNet		70.50 303	69.91 300	72.26 357	80.71 330	51.00 369	87.23 304	90.30 227	67.84 284	59.64 340	82.69 289	50.23 266	82.30 393	51.28 334	59.28 361	83.46 336

RPMNet		70.42 304	65.68 325	84.63 144	83.15 307	67.96 93	70.25 394	90.45 217	46.83 400	69.97 244	65.10 400	56.48 200	95.30 188	35.79 395	73.13 255	90.64 226

testing3		70.38 305	70.83 290	69.03 372	85.82 263	43.93 403	90.72 228	90.56 216	68.06 283	60.24 337	86.82 245	64.83 89	84.12 377	26.33 413	64.10 325	79.04 382

tfpnnormal		70.10 306	67.36 315	78.32 302	83.45 304	60.97 274	88.85 276	92.77 117	64.85 308	60.83 334	78.53 343	43.52 318	93.48 257	31.73 408	61.70 347	80.52 370

TransMVSNet (Re)		70.07 307	67.66 313	77.31 316	80.62 333	59.13 314	91.78 182	84.94 352	65.97 300	60.08 339	80.44 325	50.78 260	91.87 307	48.84 346	45.46 394	80.94 365

CL-MVSNet_self_test		69.92 308	68.09 312	75.41 330	73.25 388	55.90 344	90.05 250	89.90 245	69.96 262	61.96 331	76.54 360	51.05 259	87.64 358	49.51 343	50.59 386	82.70 349

DP-MVS		69.90 309	66.48 317	80.14 269	95.36 28	62.93 231	89.56 259	76.11 385	50.27 390	57.69 356	85.23 261	39.68 331	95.73 164	33.35 400	71.05 272	81.78 359

PS-CasMVS		69.86 310	69.13 305	72.07 361	80.35 335	50.57 371	87.02 306	89.75 250	67.27 290	59.19 344	82.28 294	46.58 298	82.24 394	50.69 336	59.02 362	83.39 338

Syy-MVS		69.65 311	69.52 303	70.03 368	87.87 213	43.21 404	88.07 288	89.01 284	72.91 190	63.11 320	88.10 221	45.28 310	85.54 370	22.07 418	69.23 281	81.32 361

MSDG		69.54 312	65.73 324	80.96 253	85.11 277	63.71 206	84.19 323	83.28 369	56.95 368	54.50 365	84.03 274	31.50 375	96.03 154	42.87 374	69.13 283	83.14 342

PEN-MVS		69.46 313	68.56 307	72.17 359	79.27 348	49.71 376	86.90 308	89.24 269	67.24 293	59.08 345	82.51 292	47.23 294	83.54 384	48.42 348	57.12 367	83.25 339

LS3D		69.17 314	66.40 319	77.50 311	91.92 110	56.12 342	85.12 317	80.37 378	46.96 398	56.50 360	87.51 233	37.25 350	93.71 252	32.52 407	79.40 205	82.68 350

PatchT		69.11 315	65.37 329	80.32 263	82.07 319	63.68 209	67.96 404	87.62 322	50.86 388	69.37 248	65.18 399	57.09 185	88.53 348	41.59 379	66.60 301	88.74 250

KD-MVS_2432*1600		69.03 316	66.37 320	77.01 319	85.56 267	61.06 272	81.44 349	90.25 230	67.27 290	58.00 352	76.53 361	54.49 220	87.63 359	48.04 350	35.77 411	82.34 353

miper_refine_blended		69.03 316	66.37 320	77.01 319	85.56 267	61.06 272	81.44 349	90.25 230	67.27 290	58.00 352	76.53 361	54.49 220	87.63 359	48.04 350	35.77 411	82.34 353

mvsany_test1		68.77 318	68.56 307	69.39 370	73.57 387	45.88 398	80.93 354	60.88 418	59.65 354	71.56 224	90.26 188	43.22 319	75.05 405	74.26 181	62.70 334	87.25 276

ACMH	63.93 17	68.62 319	64.81 331	80.03 273	85.22 273	63.25 221	87.72 296	84.66 354	60.83 346	51.57 378	79.43 339	27.29 390	94.96 197	41.76 377	64.84 316	81.88 357
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EG-PatchMatch MVS		68.55 320	65.41 328	77.96 307	78.69 359	62.93 231	89.86 256	89.17 273	60.55 347	50.27 383	77.73 351	22.60 400	94.06 236	47.18 356	72.65 260	76.88 393

ADS-MVSNet		68.54 321	64.38 338	81.03 252	88.06 207	66.90 124	68.01 402	84.02 360	57.57 362	64.48 306	69.87 389	38.68 333	89.21 344	40.87 381	67.89 293	86.97 278

DTE-MVSNet		68.46 322	67.33 316	71.87 363	77.94 368	49.00 382	86.16 314	88.58 302	66.36 298	58.19 349	82.21 296	46.36 299	83.87 382	44.97 367	55.17 374	82.73 346

mmtdpeth		68.33 323	66.37 320	74.21 343	82.81 312	51.73 362	84.34 322	80.42 377	67.01 294	71.56 224	68.58 393	30.52 381	92.35 296	75.89 165	36.21 409	78.56 387

our_test_3		68.29 324	64.69 333	79.11 297	78.92 354	64.85 174	88.40 284	85.06 350	60.32 350	52.68 372	76.12 365	40.81 328	89.80 341	44.25 369	55.65 372	82.67 351

Patchmatch-RL test		68.17 325	64.49 336	79.19 293	71.22 393	53.93 354	70.07 396	71.54 402	69.22 271	56.79 359	62.89 404	56.58 197	88.61 345	69.53 221	52.61 381	95.03 86

XVG-ACMP-BASELINE		68.04 326	65.53 327	75.56 329	74.06 386	52.37 359	78.43 370	85.88 342	62.03 337	58.91 347	81.21 316	20.38 405	91.15 324	60.69 298	68.18 289	83.16 341

FMVSNet5		68.04 326	65.66 326	75.18 333	84.43 290	57.89 323	83.54 327	86.26 337	61.83 341	53.64 370	73.30 375	37.15 353	85.08 374	48.99 345	61.77 344	82.56 352

ppachtmachnet_test		67.72 328	63.70 340	79.77 283	78.92 354	66.04 144	88.68 279	82.90 371	60.11 352	55.45 362	75.96 366	39.19 332	90.55 326	39.53 385	52.55 382	82.71 348

ACMH+	65.35 16	67.65 329	64.55 334	76.96 321	84.59 285	57.10 334	88.08 287	80.79 375	58.59 360	53.00 371	81.09 318	26.63 392	92.95 268	46.51 358	61.69 348	80.82 366

pmmvs6		67.57 330	64.76 332	76.00 328	72.82 391	53.37 356	88.71 278	86.78 333	53.19 380	57.58 357	78.03 348	35.33 362	92.41 292	55.56 320	54.88 376	82.21 355

Anonymous20231206		67.53 331	65.78 323	72.79 353	74.95 382	47.59 387	88.23 285	87.32 324	61.75 342	58.07 351	77.29 354	37.79 347	87.29 363	42.91 372	63.71 329	83.48 335

Patchmtry		67.53 331	63.93 339	78.34 301	82.12 318	64.38 185	68.72 399	84.00 361	48.23 397	59.24 342	72.41 379	57.82 179	89.27 343	46.10 361	56.68 371	81.36 360

USDC		67.43 333	64.51 335	76.19 326	77.94 368	55.29 347	78.38 371	85.00 351	73.17 183	48.36 391	80.37 326	21.23 402	92.48 291	52.15 333	64.02 327	80.81 367

ADS-MVSNet2		66.90 334	63.44 342	77.26 317	88.06 207	60.70 284	68.01 402	75.56 389	57.57 362	64.48 306	69.87 389	38.68 333	84.10 378	40.87 381	67.89 293	86.97 278

CMPMVS	48.56 21	66.77 335	64.41 337	73.84 345	70.65 397	50.31 373	77.79 375	85.73 345	45.54 402	44.76 401	82.14 297	35.40 361	90.14 336	63.18 283	74.54 244	81.07 364
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
OpenMVS_ROB	61.12 18	66.39 336	62.92 345	76.80 323	76.51 375	57.77 325	89.22 268	83.41 367	55.48 375	53.86 369	77.84 349	26.28 393	93.95 245	34.90 397	68.76 285	78.68 385

LTVRE_ROB	59.60 19	66.27 337	63.54 341	74.45 339	84.00 297	51.55 364	67.08 406	83.53 365	58.78 358	54.94 364	80.31 327	34.54 364	93.23 261	40.64 383	68.03 291	78.58 386
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		66.06 338	62.45 348	76.88 322	81.42 325	54.45 353	57.49 418	88.67 298	49.36 392	63.86 313	46.86 416	56.06 204	90.25 330	49.53 342	68.83 284	85.95 302

Patchmatch-test		65.86 339	60.94 354	80.62 260	83.75 299	58.83 316	58.91 417	75.26 391	44.50 405	50.95 382	77.09 357	58.81 169	87.90 353	35.13 396	64.03 326	95.12 81

UnsupCasMVSNet_eth		65.79 340	63.10 343	73.88 344	70.71 396	50.29 374	81.09 352	89.88 246	72.58 197	49.25 388	74.77 373	32.57 371	87.43 362	55.96 319	41.04 401	83.90 329

test_fmvs2		65.78 341	64.84 330	68.60 374	66.54 406	41.71 406	83.27 332	69.81 405	54.38 377	67.91 271	84.54 270	15.35 411	81.22 398	75.65 167	66.16 303	82.88 343

dmvs_testset		65.55 342	66.45 318	62.86 386	79.87 341	22.35 432	76.55 378	71.74 400	77.42 122	55.85 361	87.77 228	51.39 255	80.69 399	31.51 411	65.92 306	85.55 312

pmmvs-eth3d		65.53 343	62.32 349	75.19 332	69.39 401	59.59 305	82.80 340	83.43 366	62.52 332	51.30 380	72.49 377	32.86 368	87.16 364	55.32 321	50.73 385	78.83 384

mamv4		65.18 344	67.43 314	58.44 390	77.88 370	49.36 381	69.40 398	70.99 403	48.31 396	57.78 355	85.53 259	59.01 167	51.88 428	73.67 183	64.32 322	74.07 398

SixPastTwentyTwo		64.92 345	61.78 352	74.34 341	78.74 358	49.76 375	83.42 331	79.51 381	62.86 328	50.27 383	77.35 352	30.92 380	90.49 328	45.89 362	47.06 391	82.78 344

OurMVSNet-221017-0		64.68 346	62.17 350	72.21 358	76.08 379	47.35 388	80.67 355	81.02 374	56.19 372	51.60 377	79.66 337	27.05 391	88.56 347	53.60 329	53.63 379	80.71 368

test_0402		64.54 347	61.09 353	74.92 335	84.10 296	60.75 280	87.95 291	79.71 380	52.03 382	52.41 373	77.20 355	32.21 373	91.64 313	23.14 416	61.03 351	72.36 404

testgi		64.48 348	62.87 346	69.31 371	71.24 392	40.62 409	85.49 315	79.92 379	65.36 305	54.18 367	83.49 281	23.74 397	84.55 376	41.60 378	60.79 354	82.77 345

RPSCF		64.24 349	61.98 351	71.01 366	76.10 378	45.00 399	75.83 383	75.94 386	46.94 399	58.96 346	84.59 268	31.40 376	82.00 395	47.76 354	60.33 359	86.04 299

EU-MVSNet		64.01 350	63.01 344	67.02 380	74.40 385	38.86 415	83.27 332	86.19 339	45.11 403	54.27 366	81.15 317	36.91 356	80.01 401	48.79 347	57.02 368	82.19 356

test20.03		63.83 351	62.65 347	67.38 379	70.58 398	39.94 411	86.57 311	84.17 358	63.29 323	51.86 376	77.30 353	37.09 354	82.47 391	38.87 389	54.13 378	79.73 376

MDA-MVSNet_test_wron		63.78 352	60.16 356	74.64 336	78.15 366	60.41 291	83.49 328	84.03 359	56.17 374	39.17 411	71.59 385	37.22 351	83.24 388	42.87 374	48.73 388	80.26 373

YYNet1		63.76 353	60.14 357	74.62 337	78.06 367	60.19 298	83.46 330	83.99 363	56.18 373	39.25 410	71.56 386	37.18 352	83.34 386	42.90 373	48.70 389	80.32 372

K. test v3		63.09 354	59.61 359	73.53 347	76.26 377	49.38 380	83.27 332	77.15 384	64.35 311	47.77 393	72.32 381	28.73 385	87.79 356	49.93 341	36.69 408	83.41 337

COLMAP_ROB	57.96 20	62.98 355	59.65 358	72.98 351	81.44 324	53.00 358	83.75 326	75.53 390	48.34 395	48.81 390	81.40 310	24.14 395	90.30 329	32.95 402	60.52 356	75.65 396
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20240521		62.09 356	59.08 360	71.10 365	67.19 404	48.72 383	83.91 325	85.23 349	50.38 389	47.84 392	71.22 388	20.74 403	85.51 372	46.47 359	58.75 364	79.06 381

AllTest		61.66 357	58.06 362	72.46 355	79.57 343	51.42 366	80.17 361	68.61 407	51.25 386	45.88 395	81.23 312	19.86 407	86.58 366	38.98 387	57.01 369	79.39 378

UnsupCasMVSNet_bld		61.60 358	57.71 363	73.29 349	68.73 402	51.64 363	78.61 369	89.05 283	57.20 367	46.11 394	61.96 407	28.70 386	88.60 346	50.08 340	38.90 406	79.63 377

MDA-MVSNet-bldmvs		61.54 359	57.70 364	73.05 350	79.53 345	57.00 338	83.08 336	81.23 373	57.57 362	34.91 415	72.45 378	32.79 369	86.26 368	35.81 394	41.95 399	75.89 395

mvs5depth		61.03 360	57.65 365	71.18 364	67.16 405	47.04 393	72.74 389	77.49 382	57.47 365	60.52 335	72.53 376	22.84 399	88.38 349	49.15 344	38.94 405	78.11 390

KD-MVS_self_test		60.87 361	58.60 361	67.68 377	66.13 407	39.93 412	75.63 385	84.70 353	57.32 366	49.57 386	68.45 394	29.55 382	82.87 389	48.09 349	47.94 390	80.25 374

kuosan		60.86 362	60.24 355	62.71 387	81.57 322	46.43 395	75.70 384	85.88 342	57.98 361	48.95 389	69.53 391	58.42 172	76.53 403	28.25 412	35.87 410	65.15 411

TinyColmap		60.32 363	56.42 370	72.00 362	78.78 357	53.18 357	78.36 372	75.64 388	52.30 381	41.59 409	75.82 368	14.76 414	88.35 350	35.84 393	54.71 377	74.46 397

MVS-HIRNet		60.25 364	55.55 371	74.35 340	84.37 291	56.57 340	71.64 392	74.11 393	34.44 414	45.54 399	42.24 422	31.11 379	89.81 339	40.36 384	76.10 236	76.67 394

MIMVSNet1		60.16 365	57.33 366	68.67 373	69.71 399	44.13 401	78.92 368	84.21 357	55.05 376	44.63 402	71.85 383	23.91 396	81.54 397	32.63 406	55.03 375	80.35 371

PM-MVS		59.40 366	56.59 368	67.84 375	63.63 410	41.86 405	76.76 377	63.22 415	59.01 357	51.07 381	72.27 382	11.72 418	83.25 387	61.34 294	50.28 387	78.39 388

new-patchmatchnet		59.30 367	56.48 369	67.79 376	65.86 408	44.19 400	82.47 341	81.77 372	59.94 353	43.65 405	66.20 398	27.67 389	81.68 396	39.34 386	41.40 400	77.50 392

test_vis1_rt		59.09 368	57.31 367	64.43 383	68.44 403	46.02 397	83.05 338	48.63 427	51.96 383	49.57 386	63.86 403	16.30 409	80.20 400	71.21 207	62.79 333	67.07 410

test_fmvs3		56.82 369	54.86 373	62.69 388	53.59 421	35.47 418	75.87 382	65.64 412	43.91 406	55.10 363	71.43 387	6.91 426	74.40 408	68.64 232	52.63 380	78.20 389

DSMNet-mixed		56.78 370	54.44 374	63.79 384	63.21 411	29.44 427	64.43 409	64.10 414	42.12 411	51.32 379	71.60 384	31.76 374	75.04 406	36.23 392	65.20 313	86.87 281

pmmvs3		55.51 371	51.50 377	67.53 378	57.90 419	50.93 370	80.37 357	73.66 394	40.63 412	44.15 404	64.75 401	16.30 409	78.97 402	44.77 368	40.98 403	72.69 402

TDRefinement		55.28 372	51.58 376	66.39 381	59.53 418	46.15 396	76.23 380	72.80 395	44.60 404	42.49 407	76.28 364	15.29 412	82.39 392	33.20 401	43.75 396	70.62 406

dongtai		55.18 373	55.46 372	54.34 398	76.03 380	36.88 416	76.07 381	84.61 355	51.28 385	43.41 406	64.61 402	56.56 198	67.81 416	18.09 421	28.50 421	58.32 414

LF4IMVS		54.01 374	52.12 375	59.69 389	62.41 413	39.91 413	68.59 400	68.28 409	42.96 409	44.55 403	75.18 369	14.09 416	68.39 415	41.36 380	51.68 383	70.78 405

ttmdpeth		53.34 375	49.96 378	63.45 385	62.07 415	40.04 410	72.06 390	65.64 412	42.54 410	51.88 375	77.79 350	13.94 417	76.48 404	32.93 403	30.82 419	73.84 399

MVStest1		51.35 376	46.89 380	64.74 382	65.06 409	51.10 368	67.33 405	72.58 396	30.20 418	35.30 413	74.82 371	27.70 388	69.89 413	24.44 415	24.57 422	73.22 400

N_pmnet		50.55 377	49.11 379	54.88 396	77.17 373	4.02 440	84.36 321	2.00 438	48.59 393	45.86 397	68.82 392	32.22 372	82.80 390	31.58 409	51.38 384	77.81 391

new_pmnet		49.31 378	46.44 381	57.93 391	62.84 412	40.74 408	68.47 401	62.96 416	36.48 413	35.09 414	57.81 411	14.97 413	72.18 410	32.86 404	46.44 392	60.88 413

mvsany_test3		48.86 379	46.35 382	56.41 392	46.00 427	31.67 423	62.26 411	47.25 428	43.71 407	45.54 399	68.15 395	10.84 419	64.44 424	57.95 310	35.44 413	73.13 401

test_f		46.58 380	43.45 384	55.96 393	45.18 428	32.05 422	61.18 412	49.49 426	33.39 415	42.05 408	62.48 406	7.00 425	65.56 420	47.08 357	43.21 398	70.27 407

WB-MVS		46.23 381	44.94 383	50.11 401	62.13 414	21.23 434	76.48 379	55.49 420	45.89 401	35.78 412	61.44 409	35.54 360	72.83 409	9.96 428	21.75 423	56.27 416

FPMVS		45.64 382	43.10 386	53.23 399	51.42 424	36.46 417	64.97 408	71.91 399	29.13 419	27.53 419	61.55 408	9.83 421	65.01 422	16.00 425	55.58 373	58.22 415

SSC-MVS		44.51 383	43.35 385	47.99 405	61.01 417	18.90 436	74.12 387	54.36 421	43.42 408	34.10 416	60.02 410	34.42 365	70.39 412	9.14 430	19.57 424	54.68 417

EGC-MVSNET		42.35 384	38.09 387	55.11 395	74.57 383	46.62 394	71.63 393	55.77 419	0.04 433	0.24 434	62.70 405	14.24 415	74.91 407	17.59 422	46.06 393	43.80 419

LCM-MVSNet		40.54 385	35.79 390	54.76 397	36.92 434	30.81 424	51.41 421	69.02 406	22.07 421	24.63 421	45.37 418	4.56 430	65.81 419	33.67 399	34.50 414	67.67 408

APD_test1		40.50 386	37.31 389	50.09 402	51.88 422	35.27 419	59.45 416	52.59 423	21.64 422	26.12 420	57.80 412	4.56 430	66.56 418	22.64 417	39.09 404	48.43 418

test_vis3_rt		40.46 387	37.79 388	48.47 404	44.49 429	33.35 421	66.56 407	32.84 435	32.39 416	29.65 417	39.13 425	3.91 433	68.65 414	50.17 338	40.99 402	43.40 420

ANet_high		40.27 388	35.20 391	55.47 394	34.74 435	34.47 420	63.84 410	71.56 401	48.42 394	18.80 424	41.08 423	9.52 422	64.45 423	20.18 419	8.66 431	67.49 409

test_method		38.59 389	35.16 392	48.89 403	54.33 420	21.35 433	45.32 424	53.71 422	7.41 430	28.74 418	51.62 414	8.70 423	52.87 427	33.73 398	32.89 415	72.47 403

PMMVS2		37.93 390	33.61 393	50.92 400	46.31 426	24.76 430	60.55 415	50.05 424	28.94 420	20.93 422	47.59 415	4.41 432	65.13 421	25.14 414	18.55 426	62.87 412

Gipuma		34.91 391	31.44 394	45.30 406	70.99 395	39.64 414	19.85 428	72.56 397	20.10 424	16.16 428	21.47 429	5.08 429	71.16 411	13.07 426	43.70 397	25.08 426
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testf1		32.77 392	29.47 395	42.67 408	41.89 431	30.81 424	52.07 419	43.45 429	15.45 425	18.52 425	44.82 419	2.12 434	58.38 425	16.05 423	30.87 417	38.83 421

APD_test2		32.77 392	29.47 395	42.67 408	41.89 431	30.81 424	52.07 419	43.45 429	15.45 425	18.52 425	44.82 419	2.12 434	58.38 425	16.05 423	30.87 417	38.83 421

PMVS	26.43 22	31.84 394	28.16 397	42.89 407	25.87 437	27.58 428	50.92 422	49.78 425	21.37 423	14.17 429	40.81 424	2.01 436	66.62 417	9.61 429	38.88 407	34.49 425
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		24.61 395	24.00 399	26.45 412	43.74 430	18.44 437	60.86 413	39.66 431	15.11 427	9.53 431	22.10 428	6.52 427	46.94 430	8.31 431	10.14 428	13.98 428

MVE	24.84 23	24.35 396	19.77 402	38.09 410	34.56 436	26.92 429	26.57 426	38.87 433	11.73 429	11.37 430	27.44 426	1.37 437	50.42 429	11.41 427	14.60 427	36.93 423
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		23.76 397	23.20 401	25.46 413	41.52 433	16.90 438	60.56 414	38.79 434	14.62 428	8.99 432	20.24 431	7.35 424	45.82 431	7.25 432	9.46 429	13.64 429

tmp_tt		22.26 398	23.75 400	17.80 414	5.23 438	12.06 439	35.26 425	39.48 432	2.82 432	18.94 423	44.20 421	22.23 401	24.64 433	36.30 391	9.31 430	16.69 427

cdsmvs_eth3d_5k		19.86 399	26.47 398	0.00 418	0.00 441	0.00 443	0.00 429	93.45 89	0.00 436	0.00 437	95.27 65	49.56 272	0.00 437	0.00 436	0.00 434	0.00 433

wuyk23d		11.30 400	10.95 403	12.33 415	48.05 425	19.89 435	25.89 427	1.92 439	3.58 431	3.12 433	1.37 433	0.64 438	15.77 434	6.23 433	7.77 432	1.35 430

ab-mvs-re		7.91 401	10.55 404	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	94.95 75	0.00 441	0.00 437	0.00 436	0.00 434	0.00 433

testmvs		7.23 402	9.62 405	0.06 417	0.04 439	0.02 442	84.98 319	0.02 440	0.03 434	0.18 435	1.21 434	0.01 440	0.02 435	0.14 434	0.01 433	0.13 432

test123		6.92 403	9.21 406	0.08 416	0.03 440	0.05 441	81.65 347	0.01 441	0.02 435	0.14 436	0.85 435	0.03 439	0.02 435	0.12 435	0.00 434	0.16 431

pcd_1.5k_mvsjas		4.46 404	5.95 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	53.55 233	0.00 437	0.00 436	0.00 434	0.00 433

mmdepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 434	0.00 433

monomultidepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 434	0.00 433

test_blank		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 434	0.00 433

uanet_test		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 434	0.00 433

DCPMVS		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 434	0.00 433

sosnet-low-res		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 434	0.00 433

sosnet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 434	0.00 433

uncertanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 434	0.00 433

Regformer		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 434	0.00 433

uanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 434	0.00 433

WAC-MVS						49.45 378								31.56 410

FOURS1					93.95 46	61.77 257	93.96 76	91.92 156	62.14 336	86.57 52

MSC_two_6792asdad				89.60 9	97.31 4	73.22 12		95.05 29					99.07 13	92.01 31	94.77 26	96.51 24

PC_three_1452									80.91 55	94.07 2	96.83 20	83.57 4	99.12 5	95.70 7	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 31	94.77 26	96.51 24

test_one_0601					96.32 18	69.74 50		94.18 61	71.42 240	90.67 20	96.85 18	74.45 20

eth-test2					0.00 441

eth-test					0.00 441

ZD-MVS					96.63 9	65.50 159		93.50 87	70.74 254	85.26 68	95.19 71	64.92 88	97.29 80	87.51 63	93.01 56

RE-MVS-def			80.48 156		92.02 103	58.56 319	90.90 218	90.45 217	62.76 329	78.89 136	94.46 89	49.30 275		78.77 149	86.77 135	92.28 192

IU-MVS					96.46 11	69.91 43		95.18 23	80.75 56	95.28 1				92.34 28	95.36 14	96.47 28

OPU-MVS				89.97 3	97.52 3	73.15 14	96.89 6				97.00 10	83.82 2	99.15 2	95.72 5	97.63 3	97.62 2

test_241102_TWO								94.41 52	71.65 229	92.07 9	97.21 5	74.58 18	99.11 6	92.34 28	95.36 14	96.59 19

test_241102_ONE					96.45 12	69.38 56		94.44 50	71.65 229	92.11 7	97.05 8	76.79 9	99.11 6

9.14			87.63 30		93.86 48		94.41 54	94.18 61	72.76 194	86.21 54	96.51 27	66.64 66	97.88 45	90.08 45	94.04 39

save fliter					93.84 49	67.89 96	95.05 39	92.66 124	78.19 104

test_0728_THIRD									72.48 199	90.55 21	96.93 12	76.24 11	99.08 11	91.53 36	94.99 18	96.43 31

test_0728_SECOND				88.70 18	96.45 12	70.43 34	96.64 10	94.37 56					99.15 2	91.91 34	94.90 22	96.51 24

test0726					96.40 15	69.99 39	96.76 8	94.33 58	71.92 215	91.89 11	97.11 7	73.77 23

GSMVS																94.68 102

test_part2					96.29 19	68.16 89				90.78 18

sam_mvs1												57.85 178				94.68 102

sam_mvs												54.91 217

ambc				69.61 369	61.38 416	41.35 407	49.07 423	85.86 344		50.18 385	66.40 397	10.16 420	88.14 352	45.73 363	44.20 395	79.32 380

MTGPA								92.23 138

test_post1							78.95 367				20.70 430	53.05 238	91.50 321	60.43 299

test_post											23.01 427	56.49 199	92.67 283

patchmatchnet-post											67.62 396	57.62 181	90.25 330

GG-mvs-BLEND				86.53 74	91.91 112	69.67 53	75.02 386	94.75 36		78.67 144	90.85 176	77.91 7	94.56 215	72.25 197	93.74 45	95.36 66

MTMP							93.77 90	32.52 436

gm-plane-assit					88.42 195	67.04 120			78.62 98		91.83 159		97.37 74	76.57 161

test9_res														89.41 46	94.96 19	95.29 71

TEST9					94.18 41	67.28 111	94.16 63	93.51 85	71.75 226	85.52 63	95.33 60	68.01 56	97.27 84

test_8					94.19 40	67.19 113	94.15 65	93.42 92	71.87 220	85.38 66	95.35 59	68.19 54	96.95 110

agg_prior2														86.41 76	94.75 30	95.33 67

agg_prior					94.16 43	66.97 122		93.31 95		84.49 74			96.75 120

TestCases				72.46 355	79.57 343	51.42 366		68.61 407	51.25 386	45.88 395	81.23 312	19.86 407	86.58 366	38.98 387	57.01 369	79.39 378

test_prior4						67.18 115	93.92 79

test_prior2							95.10 38		75.40 146	85.25 69	95.61 51	67.94 57		87.47 65	94.77 26

test_prior				86.42 77	94.71 35	67.35 110		93.10 106					96.84 117			95.05 84

旧先验2							92.00 171		59.37 356	87.54 45			93.47 258	75.39 169

新几何2							91.41 192

新几何1				84.73 136	92.32 93	64.28 190		91.46 182	59.56 355	79.77 125	92.90 131	56.95 191	96.57 125	63.40 279	92.91 58	93.34 158

旧先验1					91.94 108	60.74 281		91.50 180			94.36 93	65.23 83			91.84 71	94.55 109

无先验							92.71 136	92.61 128	62.03 337				97.01 100	66.63 250		93.97 140

原ACMM2							92.01 168

原ACMM1				84.42 151	93.21 68	64.27 191		93.40 94	65.39 304	79.51 128	92.50 139	58.11 177	96.69 121	65.27 269	93.96 40	92.32 190

test222					89.77 160	61.60 262	89.55 260	89.42 263	56.83 370	77.28 157	92.43 143	52.76 241			91.14 85	93.09 168

testdata2													96.09 148	61.26 295

segment_acmp												65.94 74

testdata				81.34 241	89.02 181	57.72 326		89.84 247	58.65 359	85.32 67	94.09 107	57.03 186	93.28 260	69.34 223	90.56 91	93.03 171

testdata1							89.21 269		77.55 118

test12				87.09 52	94.60 36	68.86 68		92.91 113		82.67 95		65.44 80	97.55 65		93.69 48	94.84 94

plane_prior7					86.94 238	61.51 263

plane_prior6					87.23 230	62.32 247						50.66 261

plane_prior5								91.31 186					95.55 177	76.74 159	78.53 215	88.39 257

plane_prior4											89.14 206

plane_prior3						61.95 255			79.09 88	72.53 208

plane_prior2							93.13 117		78.81 95

plane_prior1					87.15 232

plane_prior						62.42 243	93.85 83		79.38 80						78.80 212

n2								0.00 442

nn								0.00 442

door-mid								66.01 411

lessismore_v0				73.72 346	72.93 390	47.83 386		61.72 417		45.86 397	73.76 374	28.63 387	89.81 339	47.75 355	31.37 416	83.53 333

LGP-MVS_train				79.56 289	84.31 292	59.37 309		89.73 253	69.49 267	64.86 301	88.42 212	38.65 335	94.30 224	72.56 194	72.76 258	85.01 320

test11								93.01 109

door								66.57 410

HQP5-MVS						63.66 210

HQP-NCC					87.54 222		94.06 68		79.80 71	74.18 187

ACMP_Plane					87.54 222		94.06 68		79.80 71	74.18 187

BP-MVS														77.63 156

HQP4-MVS										74.18 187			95.61 172			88.63 251

HQP3-MVS								91.70 172							78.90 210

HQP2-MVS												51.63 253

NP-MVS					87.41 225	63.04 227					90.30 186

MDTV_nov1_ep13_2view						59.90 301	80.13 362		67.65 287	72.79 202		54.33 225		59.83 303		92.58 183

MDTV_nov1_ep13			72.61 274		89.06 180	68.48 77	80.33 358	90.11 236	71.84 222	71.81 220	75.92 367	53.01 239	93.92 246	48.04 350	73.38 253

ACMMP++_ref															71.63 266

ACMMP++															69.72 275

Test By Simon												54.21 227

ITE_SJBPF				70.43 367	74.44 384	47.06 392		77.32 383	60.16 351	54.04 368	83.53 279	23.30 398	84.01 380	43.07 371	61.58 349	80.21 375

DeepMVS_CX				34.71 411	51.45 423	24.73 431		28.48 437	31.46 417	17.49 427	52.75 413	5.80 428	42.60 432	18.18 420	19.42 425	36.81 424

High-resolution multi-view benchmark