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.

HPM-MVS++		89.02 4	89.15 4	88.63 1	95.01 3	76.03 1	92.38 14	92.85 34	80.26 14	87.78 13	94.27 18	75.89 9	96.81 10	87.45 9	96.44 1	93.05 64

test_part1								94.09 1				81.79 1			96.38 2	93.74 36

ESAPD		89.40 1	89.87 1	87.98 11	95.06 1	72.65 26	92.22 18	94.09 1	75.63 74	91.80 1	95.29 2	81.79 1	97.56 1	86.60 12	96.38 2	93.74 36

ACMMP_Plus		88.05 10	88.08 10	87.94 12	93.70 25	73.05 18	90.86 35	93.59 9	76.27 66	88.14 9	95.09 5	71.06 38	96.67 15	87.67 6	96.37 4	94.09 22

MP-MVS-pluss		87.67 13	87.72 12	87.54 27	93.64 28	72.04 40	89.80 57	93.50 11	75.17 85	86.34 18	95.29 2	70.86 39	96.00 35	88.78 3	96.04 5	94.58 7
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CNVR-MVS		88.93 5	89.13 5	88.33 3	94.77 4	73.82 6	90.51 41	93.00 26	80.90 10	88.06 11	94.06 26	76.43 6	96.84 9	88.48 4	95.99 6	94.34 15

PHI-MVS		86.43 32	86.17 34	87.24 31	90.88 69	70.96 49	92.27 17	94.07 3	72.45 138	85.22 27	91.90 60	69.47 52	96.42 24	83.28 36	95.94 7	94.35 14

test_prior3		86.73 27	86.86 26	86.33 47	92.61 48	69.59 73	88.85 81	92.97 31	75.41 78	84.91 31	93.54 31	74.28 19	95.48 45	83.31 34	95.86 8	93.91 30

test_prior2							88.85 81		75.41 78	84.91 31	93.54 31	74.28 19		83.31 34	95.86 8

SteuartSystems-ACMMP		88.72 6	88.86 6	88.32 4	92.14 54	72.96 19	93.73 3	93.67 8	80.19 15	88.10 10	94.80 6	73.76 22	97.11 5	87.51 8	95.82 10	94.90 4
Skip Steuart: Steuart Systems R&D Blog.
DeepPCF-MVS	80.84 1	88.10 7	88.56 7	86.73 40	92.24 52	69.03 81	89.57 64	93.39 15	77.53 39	89.79 6	94.12 24	78.98 3	96.58 22	85.66 14	95.72 11	94.58 7

train_agg		86.43 32	86.20 32	87.13 34	93.26 35	72.96 19	88.75 86	91.89 69	68.69 198	85.00 29	93.10 41	74.43 15	95.41 50	84.97 17	95.71 12	93.02 65

agg_prior3		86.16 38	85.85 39	87.10 35	93.31 32	72.86 23	88.77 84	91.68 79	68.29 209	84.26 44	92.83 49	72.83 27	95.42 49	84.97 17	95.71 12	93.02 65

test9_res														84.90 19	95.70 14	92.87 70

APDe-MVS		89.15 3	89.63 3	87.73 21	94.49 10	71.69 43	93.83 2	93.96 4	75.70 72	91.06 4	96.03 1	76.84 5	97.03 7	89.09 2	95.65 15	94.47 11

agg_prior2														82.91 41	95.45 16	92.70 71

CDPH-MVS		85.76 42	85.29 47	87.17 33	93.49 31	71.08 47	88.58 92	92.42 48	68.32 208	84.61 38	93.48 33	72.32 31	96.15 32	79.00 62	95.43 17	94.28 18

DeepC-MVS	79.81 2	87.08 25	86.88 25	87.69 25	91.16 64	72.32 37	90.31 47	93.94 5	77.12 44	82.82 61	94.23 20	72.13 33	97.09 6	84.83 22	95.37 18	93.65 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MPTG		87.53 15	87.41 16	87.90 16	94.18 21	74.25 2	90.23 49	92.02 60	79.45 19	85.88 20	94.80 6	68.07 59	96.21 29	86.69 10	95.34 19	93.23 56

MTAPA		87.23 21	87.00 21	87.90 16	94.18 21	74.25 2	86.58 162	92.02 60	79.45 19	85.88 20	94.80 6	68.07 59	96.21 29	86.69 10	95.34 19	93.23 56

agg_prior1		86.22 37	86.09 36	86.62 43	92.85 43	71.94 41	88.59 91	91.78 75	68.96 195	84.41 41	93.18 40	74.94 11	94.93 67	84.75 24	95.33 21	93.01 67

DeepC-MVS_fast	79.65 3	86.91 26	86.62 27	87.76 20	93.52 30	72.37 36	91.26 29	93.04 23	76.62 57	84.22 45	93.36 37	71.44 36	96.76 12	80.82 53	95.33 21	94.16 19
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		87.71 12	87.64 13	87.93 15	94.36 16	73.88 4	92.71 13	92.65 42	77.57 35	83.84 49	94.40 17	72.24 32	96.28 27	85.65 15	95.30 23	93.62 45

MCST-MVS		87.37 19	87.25 17	87.73 21	94.53 9	72.46 33	89.82 55	93.82 6	73.07 126	84.86 36	92.89 47	76.22 7	96.33 25	84.89 21	95.13 24	94.40 12

APD-MVS		87.44 16	87.52 14	87.19 32	94.24 18	72.39 34	91.86 24	92.83 35	73.01 127	88.58 8	94.52 9	73.36 23	96.49 23	84.26 29	95.01 25	92.70 71
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		88.06 8	88.01 11	88.24 5	94.41 14	73.62 7	91.22 32	92.83 35	81.50 7	85.79 23	93.47 35	73.02 26	97.00 8	84.90 19	94.94 26	94.10 21

ACMMPR		87.44 16	87.23 18	88.08 7	94.64 5	73.59 8	93.04 5	93.20 19	76.78 52	84.66 37	94.52 9	68.81 57	96.65 16	84.53 25	94.90 27	94.00 28

HFP-MVS		87.58 14	87.47 15	87.94 12	94.58 7	73.54 11	93.04 5	93.24 17	76.78 52	84.91 31	94.44 14	70.78 40	96.61 18	84.53 25	94.89 28	93.66 38

#test#		87.33 20	87.13 20	87.94 12	94.58 7	73.54 11	92.34 15	93.24 17	75.23 82	84.91 31	94.44 14	70.78 40	96.61 18	83.75 33	94.89 28	93.66 38

region2R		87.42 18	87.20 19	88.09 6	94.63 6	73.55 9	93.03 7	93.12 22	76.73 55	84.45 40	94.52 9	69.09 55	96.70 14	84.37 28	94.83 30	94.03 25

原ACMM1				84.35 86	93.01 41	68.79 87		92.44 45	63.96 251	81.09 80	91.57 68	66.06 77	95.45 47	67.19 169	94.82 31	88.81 202

HPM-MVS		87.11 23	86.98 22	87.50 29	93.88 24	72.16 38	92.19 20	93.33 16	76.07 69	83.81 50	93.95 28	69.77 50	96.01 34	85.15 16	94.66 32	94.32 17

TSAR-MVS + MP.		88.02 11	88.11 9	87.72 23	93.68 27	72.13 39	91.41 28	92.35 50	74.62 91	88.90 7	93.85 29	75.75 10	96.00 35	87.80 5	94.63 33	95.04 2

PGM-MVS		86.68 28	86.27 31	87.90 16	94.22 19	73.38 15	90.22 50	93.04 23	75.53 76	83.86 48	94.42 16	67.87 63	96.64 17	82.70 43	94.57 34	93.66 38

XVS		87.18 22	86.91 24	88.00 9	94.42 12	73.33 16	92.78 9	92.99 28	79.14 21	83.67 52	94.17 21	67.45 66	96.60 20	83.06 38	94.50 35	94.07 23

X-MVStestdata		80.37 118	77.83 152	88.00 9	94.42 12	73.33 16	92.78 9	92.99 28	79.14 21	83.67 52	12.47 349	67.45 66	96.60 20	83.06 38	94.50 35	94.07 23

test12				86.80 39	92.63 47	70.70 57		91.79 74		82.71 63		71.67 34	96.16 31		94.50 35	93.54 48

CP-MVS		87.11 23	86.92 23	87.68 26	94.20 20	73.86 5	93.98 1	92.82 37	76.62 57	83.68 51	94.46 13	67.93 61	95.95 37	84.20 31	94.39 38	93.23 56

CSCG		86.41 34	86.19 33	87.07 36	92.91 42	72.48 32	90.81 36	93.56 10	73.95 99	83.16 57	91.07 78	75.94 8	95.19 57	79.94 60	94.38 39	93.55 47

MSLP-MVS++		85.43 47	85.76 41	84.45 82	91.93 57	70.24 60	90.71 38	92.86 33	77.46 41	84.22 45	92.81 52	67.16 69	92.94 154	80.36 56	94.35 40	90.16 149

mPP-MVS		86.67 29	86.32 30	87.72 23	94.41 14	73.55 9	92.74 11	92.22 53	76.87 50	82.81 62	94.25 19	66.44 73	96.24 28	82.88 42	94.28 41	93.38 51

SD-MVS		88.06 8	88.50 8	86.71 41	92.60 50	72.71 24	91.81 25	93.19 20	77.87 32	90.32 5	94.00 27	74.83 12	93.78 114	87.63 7	94.27 42	93.65 43

MVS_0304		86.37 36	85.81 40	88.02 8	90.13 77	72.39 34	89.66 62	92.75 38	81.64 6	82.66 65	92.04 56	64.44 88	97.35 3	84.76 23	94.25 43	94.33 16

HSP-MVS		89.28 2	89.76 2	87.85 19	94.28 17	73.46 14	92.90 8	92.73 39	80.27 13	91.35 3	94.16 22	78.35 4	96.77 11	89.59 1	94.22 44	93.33 54

DELS-MVS		85.41 48	85.30 46	85.77 56	88.49 132	67.93 109	85.52 198	93.44 13	78.70 28	83.63 54	89.03 119	74.57 13	95.71 40	80.26 58	94.04 45	93.66 38
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
EPNet		83.72 58	82.92 64	86.14 52	84.22 214	69.48 76	91.05 34	85.27 224	81.30 8	76.83 141	91.65 64	66.09 76	95.56 43	76.00 91	93.85 46	93.38 51
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
3Dnovator+	77.84 4	85.48 45	84.47 53	88.51 2	91.08 65	73.49 13	93.18 4	93.78 7	80.79 11	76.66 144	93.37 36	60.40 162	96.75 13	77.20 80	93.73 47	95.29 1

CANet		86.45 31	86.10 35	87.51 28	90.09 79	70.94 51	89.70 61	92.59 43	81.78 4	81.32 75	91.43 73	70.34 43	97.23 4	84.26 29	93.36 48	94.37 13

新几何1				83.42 113	93.13 37	70.71 56		85.48 222	57.43 300	81.80 72	91.98 58	63.28 98	92.27 173	64.60 190	92.99 49	87.27 244

1121		80.84 98	79.77 103	84.05 95	93.11 39	70.78 55	84.66 210	85.42 223	57.37 301	81.76 73	92.02 57	63.41 96	94.12 95	67.28 167	92.93 50	87.26 245

HPM-MVS_fast		85.35 49	84.95 50	86.57 45	93.69 26	70.58 58	92.15 21	91.62 80	73.89 102	82.67 64	94.09 25	62.60 122	95.54 44	80.93 51	92.93 50	93.57 46

旧先验1					91.96 56	65.79 142		86.37 214			93.08 45	69.31 54			92.74 52	88.74 205

3Dnovator	76.31 5	83.38 65	82.31 71	86.59 44	87.94 147	72.94 22	90.64 39	92.14 57	77.21 42	75.47 169	92.83 49	58.56 169	94.72 77	73.24 121	92.71 53	92.13 90

MVS_111021_HR		85.14 52	84.75 52	86.32 49	91.65 60	72.70 25	85.98 177	90.33 118	76.11 68	82.08 68	91.61 67	71.36 37	94.17 94	81.02 50	92.58 54	92.08 91

APD-MVS_3200maxsize		85.97 39	85.88 37	86.22 50	92.69 46	69.53 75	91.93 23	92.99 28	73.54 113	85.94 19	94.51 12	65.80 80	95.61 41	83.04 40	92.51 55	93.53 49

MAR-MVS		81.84 83	80.70 89	85.27 62	91.32 63	71.53 45	89.82 55	90.92 99	69.77 176	78.50 102	86.21 204	62.36 129	94.52 81	65.36 183	92.05 56	89.77 176
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
TSAR-MVS + GP.		85.71 43	85.33 44	86.84 38	91.34 62	72.50 31	89.07 76	87.28 204	76.41 59	85.80 22	90.22 94	74.15 21	95.37 54	81.82 47	91.88 57	92.65 74

IS-MVSNet		83.15 66	82.81 65	84.18 91	89.94 83	63.30 201	91.59 26	88.46 184	79.04 25	79.49 90	92.16 54	65.10 84	94.28 86	67.71 162	91.86 58	94.95 3

Vis-MVSNet (Re-imp)		78.36 158	78.45 138	78.07 243	88.64 128	51.78 309	86.70 159	79.63 287	74.14 97	75.11 183	90.83 85	61.29 145	89.75 233	58.10 241	91.60 59	92.69 73

MG-MVS		83.41 63	83.45 56	83.28 118	92.74 45	62.28 218	88.17 107	89.50 145	75.22 83	81.49 74	92.74 53	66.75 70	95.11 60	72.85 123	91.58 60	92.45 78

CPTT-MVS		83.73 57	83.33 58	84.92 73	93.28 34	70.86 54	92.09 22	90.38 113	68.75 197	79.57 89	92.83 49	60.60 158	93.04 152	80.92 52	91.56 61	90.86 119

test222					91.50 61	68.26 103	84.16 227	83.20 248	54.63 312	79.74 87	91.63 66	58.97 167			91.42 62	86.77 256

testdata				79.97 207	90.90 68	64.21 183		84.71 228	59.27 287	85.40 24	92.91 46	62.02 135	89.08 251	68.95 156	91.37 63	86.63 260

abl_6		85.23 50	84.95 50	86.07 53	92.23 53	70.48 59	90.80 37	92.08 58	73.51 114	85.26 26	94.16 22	62.75 115	95.92 38	82.46 46	91.30 64	91.81 98

API-MVS		81.99 81	81.23 83	84.26 89	90.94 67	70.18 66	91.10 33	89.32 150	71.51 154	78.66 100	88.28 137	65.26 82	95.10 63	64.74 189	91.23 65	87.51 238

Vis-MVSNet		83.46 62	82.80 66	85.43 59	90.25 76	68.74 91	90.30 48	90.13 127	76.33 65	80.87 83	92.89 47	61.00 151	94.20 91	72.45 130	90.97 66	93.35 53
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	72.83 10	79.77 132	78.33 144	84.09 93	85.17 198	69.91 67	90.57 40	90.97 98	66.70 220	72.17 216	91.91 59	54.70 198	93.96 100	61.81 210	90.95 67	88.41 222

UA-Net		85.08 53	84.96 49	85.45 58	92.07 55	68.07 107	89.78 58	90.86 101	82.48 2	84.60 39	93.20 39	69.35 53	95.22 56	71.39 142	90.88 68	93.07 63

ACMMP		85.89 41	85.39 43	87.38 30	93.59 29	72.63 28	92.74 11	93.18 21	76.78 52	80.73 84	93.82 30	64.33 89	96.29 26	82.67 44	90.69 69	93.23 56
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
Regformer-1		86.41 34	86.33 29	86.64 42	89.33 101	70.93 52	88.43 94	91.39 89	82.14 3	86.65 17	90.09 96	74.39 17	95.01 66	83.97 32	90.63 70	93.97 29

Regformer-2		86.63 30	86.53 28	86.95 37	89.33 101	71.24 46	88.43 94	92.05 59	82.50 1	86.88 16	90.09 96	74.45 14	95.61 41	84.38 27	90.63 70	94.01 27

UGNet		80.83 100	79.59 108	84.54 79	88.04 144	68.09 106	89.42 65	88.16 186	76.95 48	76.22 155	89.46 110	49.30 261	93.94 102	68.48 159	90.31 72	91.60 100
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
MVSFormer		82.85 71	82.05 74	85.24 63	87.35 169	70.21 61	90.50 42	90.38 113	68.55 200	81.32 75	89.47 108	61.68 136	93.46 130	78.98 63	90.26 73	92.05 92

lupinMVS		81.39 92	80.27 97	84.76 76	87.35 169	70.21 61	85.55 194	86.41 212	62.85 259	81.32 75	88.61 127	61.68 136	92.24 175	78.41 69	90.26 73	91.83 96

DP-MVS Recon		83.11 68	82.09 73	86.15 51	94.44 11	70.92 53	88.79 83	92.20 54	70.53 166	79.17 93	91.03 81	64.12 91	96.03 33	68.39 161	90.14 75	91.50 104

MVS_111021_LR		82.61 74	82.11 72	84.11 92	88.82 121	71.58 44	85.15 203	86.16 217	74.69 90	80.47 85	91.04 79	62.29 130	90.55 224	80.33 57	90.08 76	90.20 148

jason		81.39 92	80.29 96	84.70 77	86.63 183	69.90 68	85.95 178	86.77 208	63.24 253	81.07 81	89.47 108	61.08 150	92.15 176	78.33 70	90.07 77	92.05 92
jason: jason.
LFMVS		81.82 84	81.23 83	83.57 110	91.89 58	63.43 199	89.84 54	81.85 266	77.04 47	83.21 55	93.10 41	52.26 217	93.43 134	71.98 136	89.95 78	93.85 33

MVS		78.19 162	76.99 166	81.78 168	85.66 192	66.99 123	84.66 210	90.47 111	55.08 311	72.02 221	85.27 229	63.83 94	94.11 97	66.10 177	89.80 79	84.24 291

CANet_DTU		80.61 108	79.87 101	82.83 145	85.60 194	63.17 207	87.36 130	88.65 180	76.37 63	75.88 161	88.44 133	53.51 208	93.07 149	73.30 120	89.74 80	92.25 85

PVSNet_Blended		80.98 95	80.34 94	82.90 139	88.85 118	65.40 148	84.43 220	92.00 63	67.62 214	78.11 119	85.05 234	66.02 78	94.27 87	71.52 140	89.50 81	89.01 194

PAPM_NR		83.02 69	82.41 68	84.82 75	92.47 51	66.37 132	87.93 114	91.80 73	73.82 107	77.32 133	90.66 87	67.90 62	94.90 71	70.37 146	89.48 82	93.19 60

114514_t		80.68 107	79.51 112	84.20 90	94.09 23	67.27 120	89.64 63	91.11 96	58.75 291	74.08 192	90.72 86	58.10 172	95.04 65	69.70 151	89.42 83	90.30 146

LCM-MVSNet-Re		77.05 191	76.94 167	77.36 253	87.20 175	51.60 310	80.06 267	80.46 278	75.20 84	67.69 271	86.72 178	62.48 127	88.98 254	63.44 194	89.25 84	91.51 103

alignmvs		85.48 45	85.32 45	85.96 55	89.51 96	69.47 77	89.74 59	92.47 44	76.17 67	87.73 14	91.46 72	70.32 44	93.78 114	81.51 48	88.95 85	94.63 6

VNet		82.21 77	82.41 68	81.62 178	90.82 70	60.93 225	84.47 216	89.78 138	76.36 64	84.07 47	91.88 61	64.71 87	90.26 226	70.68 143	88.89 86	93.66 38

PS-MVSNAJ		81.69 85	81.02 87	83.70 106	89.51 96	68.21 105	84.28 225	90.09 128	70.79 161	81.26 79	85.62 222	63.15 103	94.29 85	75.62 98	88.87 87	88.59 214

canonicalmvs		85.91 40	85.87 38	86.04 54	89.84 85	69.44 79	90.45 45	93.00 26	76.70 56	88.01 12	91.23 75	73.28 24	93.91 105	81.50 49	88.80 88	94.77 5

QAPM		80.88 96	79.50 113	85.03 68	88.01 146	68.97 85	91.59 26	92.00 63	66.63 224	75.15 182	92.16 54	57.70 174	95.45 47	63.52 193	88.76 89	90.66 128

VDD-MVS		83.01 70	82.36 70	84.96 70	91.02 66	66.40 131	88.91 78	88.11 187	77.57 35	84.39 43	93.29 38	52.19 218	93.91 105	77.05 83	88.70 90	94.57 9

Test4		77.83 173	75.90 190	83.62 107	80.24 293	65.25 154	85.27 200	90.67 103	69.03 193	66.48 283	83.75 248	43.07 292	93.00 153	75.93 92	88.66 91	92.62 75

test_normal		79.81 131	78.45 138	83.89 104	82.70 263	65.40 148	85.82 184	89.48 146	69.39 181	70.12 242	85.66 220	57.15 182	93.71 123	77.08 82	88.62 92	92.56 76

PVSNet_Blended_VisFu		82.62 73	81.83 78	84.96 70	90.80 71	69.76 70	88.74 88	91.70 78	69.39 181	78.96 95	88.46 132	65.47 81	94.87 73	74.42 107	88.57 93	90.24 147

DI_MVS_plusplus_test		79.89 130	78.58 135	83.85 105	82.89 259	65.32 152	86.12 174	89.55 143	69.64 180	70.55 233	85.82 217	57.24 180	93.81 112	76.85 85	88.55 94	92.41 80

xiu_mvs_v2_base		81.69 85	81.05 86	83.60 108	89.15 112	68.03 108	84.46 218	90.02 132	70.67 164	81.30 78	86.53 194	63.17 102	94.19 92	75.60 99	88.54 95	88.57 216

PAPR		81.66 87	80.89 88	83.99 100	90.27 75	64.00 189	86.76 158	91.77 77	68.84 196	77.13 140	89.50 106	67.63 64	94.88 72	67.55 164	88.52 96	93.09 62

MVS_Test		83.15 66	83.06 61	83.41 115	86.86 179	63.21 204	86.11 175	92.00 63	74.31 94	82.87 60	89.44 113	70.03 46	93.21 139	77.39 79	88.50 97	93.81 35

AdaColmap		80.58 111	79.42 114	84.06 94	93.09 40	68.91 86	89.36 66	88.97 167	69.27 185	75.70 168	89.69 102	57.20 181	95.77 39	63.06 197	88.41 98	87.50 239

VDDNet		81.52 89	80.67 90	84.05 95	90.44 73	64.13 185	89.73 60	85.91 220	71.11 157	83.18 56	93.48 33	50.54 251	93.49 129	73.40 119	88.25 99	94.54 10

PCF-MVS	73.52 7	80.38 117	78.84 130	85.01 69	87.71 162	68.99 84	83.65 234	91.46 88	63.00 256	77.77 126	90.28 91	66.10 75	95.09 64	61.40 213	88.22 100	90.94 117
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Effi-MVS+		83.62 60	83.08 60	85.24 63	88.38 137	67.45 115	88.89 79	89.15 157	75.50 77	82.27 66	88.28 137	69.61 51	94.45 83	77.81 74	87.84 101	93.84 34

gg-mvs-nofinetune		69.95 269	67.96 271	75.94 269	83.07 253	54.51 293	77.23 290	70.29 330	63.11 254	70.32 237	62.33 333	43.62 289	88.69 260	53.88 263	87.76 102	84.62 289

Regformer-3		85.23 50	85.07 48	85.70 57	88.95 116	69.01 83	88.29 103	89.91 136	80.95 9	85.01 28	90.01 98	72.45 30	94.19 92	82.50 45	87.57 103	93.90 32

Regformer-4		85.68 44	85.45 42	86.35 46	88.95 116	69.67 72	88.29 103	91.29 91	81.73 5	85.36 25	90.01 98	72.62 29	95.35 55	83.28 36	87.57 103	94.03 25

xiu_mvs_v1_base_debu		80.80 103	79.72 105	84.03 97	87.35 169	70.19 63	85.56 191	88.77 176	69.06 190	81.83 69	88.16 139	50.91 240	92.85 156	78.29 71	87.56 105	89.06 187

xiu_mvs_v1_base		80.80 103	79.72 105	84.03 97	87.35 169	70.19 63	85.56 191	88.77 176	69.06 190	81.83 69	88.16 139	50.91 240	92.85 156	78.29 71	87.56 105	89.06 187

xiu_mvs_v1_base_debi		80.80 103	79.72 105	84.03 97	87.35 169	70.19 63	85.56 191	88.77 176	69.06 190	81.83 69	88.16 139	50.91 240	92.85 156	78.29 71	87.56 105	89.06 187

CLD-MVS		82.31 76	81.65 79	84.29 88	88.47 133	67.73 113	85.81 185	92.35 50	75.78 70	78.33 110	86.58 191	64.01 92	94.35 84	76.05 90	87.48 108	90.79 120
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CDS-MVSNet		79.07 147	77.70 156	83.17 122	87.60 164	68.23 104	84.40 222	86.20 216	67.49 217	76.36 151	86.54 193	61.54 139	90.79 221	61.86 209	87.33 109	90.49 139
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EPP-MVSNet		83.40 64	83.02 62	84.57 78	90.13 77	64.47 179	92.32 16	90.73 102	74.45 93	79.35 92	91.10 76	69.05 56	95.12 59	72.78 124	87.22 110	94.13 20

TAMVS		78.89 151	77.51 159	83.03 130	87.80 157	67.79 112	84.72 209	85.05 227	67.63 213	76.75 142	87.70 150	62.25 131	90.82 220	58.53 237	87.13 111	90.49 139

TAPA-MVS	73.13 9	79.15 145	77.94 150	82.79 149	89.59 92	62.99 211	88.16 108	91.51 85	65.77 232	77.14 139	91.09 77	60.91 152	93.21 139	50.26 277	87.05 112	92.17 89
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PAPM		77.68 176	76.40 175	81.51 181	87.29 174	61.85 222	83.78 233	89.59 142	64.74 241	71.23 228	88.70 123	62.59 123	93.66 124	52.66 268	87.03 113	89.01 194

BH-untuned		79.47 139	78.60 133	82.05 163	89.19 111	65.91 139	86.07 176	88.52 183	72.18 144	75.42 172	87.69 151	61.15 148	93.54 127	60.38 220	86.83 114	86.70 258

BH-RMVSNet		79.61 134	78.44 140	83.14 124	89.38 100	65.93 138	84.95 206	87.15 205	73.56 112	78.19 117	89.79 101	56.67 184	93.36 135	59.53 228	86.74 115	90.13 151

LS3D		76.95 193	74.82 208	83.37 116	90.45 72	67.36 119	89.15 74	86.94 207	61.87 269	69.52 251	90.61 88	51.71 233	94.53 80	46.38 301	86.71 116	88.21 224

Fast-Effi-MVS+		80.81 101	79.92 100	83.47 111	88.85 118	64.51 173	85.53 196	89.39 148	70.79 161	78.49 103	85.06 233	67.54 65	93.58 125	67.03 172	86.58 117	92.32 82

EPNet_dtu		75.46 218	74.86 207	77.23 256	82.57 266	54.60 291	86.89 151	83.09 249	71.64 149	66.25 285	85.86 215	55.99 187	88.04 267	54.92 258	86.55 118	89.05 191
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OPM-MVS		83.50 61	82.95 63	85.14 65	88.79 124	70.95 50	89.13 75	91.52 84	77.55 38	80.96 82	91.75 62	60.71 154	94.50 82	79.67 61	86.51 119	89.97 167

OMC-MVS		82.69 72	81.97 77	84.85 74	88.75 126	67.42 116	87.98 110	90.87 100	74.92 88	79.72 88	91.65 64	62.19 133	93.96 100	75.26 103	86.42 120	93.16 61

HQP_MVS		83.64 59	83.14 59	85.14 65	90.08 80	68.71 93	91.25 30	92.44 45	79.12 23	78.92 96	91.00 82	60.42 160	95.38 52	78.71 65	86.32 121	91.33 107

plane_prior5								92.44 45					95.38 52	78.71 65	86.32 121	91.33 107

plane_prior						68.71 93	90.38 46		77.62 34						86.16 123

mvs_anonymous		79.42 141	79.11 126	80.34 200	84.45 210	57.97 250	82.59 247	87.62 198	67.40 219	76.17 159	88.56 130	68.47 58	89.59 236	70.65 144	86.05 124	93.47 50

HQP3-MVS								92.19 55							85.99 125

HQP-MVS		82.61 74	82.02 75	84.37 84	89.33 101	66.98 124	89.17 70	92.19 55	76.41 59	77.23 136	90.23 93	60.17 163	95.11 60	77.47 77	85.99 125	91.03 113

BH-w/o		78.21 160	77.33 162	80.84 193	88.81 122	65.13 158	84.87 207	87.85 195	69.75 177	74.52 190	84.74 240	61.34 143	93.11 147	58.24 240	85.84 127	84.27 290

CHOSEN 1792x2688		77.63 179	75.69 191	83.44 112	89.98 82	68.58 98	78.70 281	87.50 201	56.38 306	75.80 163	86.84 174	58.67 168	91.40 204	61.58 212	85.75 128	90.34 145

cascas		76.72 196	74.64 209	82.99 132	85.78 191	65.88 140	82.33 249	89.21 156	60.85 275	72.74 202	81.02 282	47.28 270	93.75 118	67.48 165	85.02 129	89.34 182

FIs		82.07 79	82.42 67	81.04 191	88.80 123	58.34 244	88.26 105	93.49 12	76.93 49	78.47 104	91.04 79	69.92 48	92.34 172	69.87 150	84.97 130	92.44 79

test-LLR		72.94 249	72.43 231	74.48 281	81.35 281	58.04 248	78.38 282	77.46 302	66.66 221	69.95 246	79.00 297	48.06 267	79.24 308	66.13 175	84.83 131	86.15 269

test-mter		71.41 257	70.39 255	74.48 281	81.35 281	58.04 248	78.38 282	77.46 302	60.32 278	69.95 246	79.00 297	36.08 321	79.24 308	66.13 175	84.83 131	86.15 269

diffmvs		79.51 136	78.59 134	82.25 160	83.31 246	62.66 213	84.17 226	88.11 187	67.64 212	76.09 160	87.47 158	64.01 92	91.15 210	71.71 139	84.82 133	92.94 69

EI-MVSNet-Vis-set		84.19 54	83.81 54	85.31 60	88.18 141	67.85 110	87.66 118	89.73 140	80.05 17	82.95 58	89.59 105	70.74 42	94.82 74	80.66 55	84.72 134	93.28 55

GG-mvs-BLEND				75.38 275	81.59 276	55.80 286	79.32 274	69.63 332		67.19 276	73.67 320	43.24 290	88.90 259	50.41 274	84.50 135	81.45 312

FC-MVSNet-test		81.52 89	82.02 75	80.03 206	88.42 136	55.97 281	87.95 112	93.42 14	77.10 45	77.38 131	90.98 84	69.96 47	91.79 185	68.46 160	84.50 135	92.33 81

PVSNet	64.34 18	72.08 254	70.87 252	75.69 271	86.21 187	56.44 274	74.37 305	80.73 275	62.06 268	70.17 240	82.23 263	42.86 294	83.31 295	54.77 259	84.45 137	87.32 243

MS-PatchMatch		73.83 229	72.67 228	77.30 255	83.87 233	66.02 136	81.82 252	84.66 229	61.37 273	68.61 264	82.82 257	47.29 269	88.21 264	59.27 229	84.32 138	77.68 323

TESTMET0.1,1		69.89 270	69.00 261	72.55 291	79.27 305	56.85 266	78.38 282	74.71 318	57.64 298	68.09 268	77.19 308	37.75 315	76.70 319	63.92 192	84.09 139	84.10 294

EI-MVSNet-UG-set		83.81 56	83.38 57	85.09 67	87.87 148	67.53 114	87.44 129	89.66 141	79.74 18	82.23 67	89.41 114	70.24 45	94.74 76	79.95 59	83.92 140	92.99 68

LPG-MVS_test		82.08 78	81.27 82	84.50 80	89.23 109	68.76 89	90.22 50	91.94 67	75.37 80	76.64 145	91.51 69	54.29 201	94.91 69	78.44 67	83.78 141	89.83 171

LGP-MVS_train				84.50 80	89.23 109	68.76 89		91.94 67	75.37 80	76.64 145	91.51 69	54.29 201	94.91 69	78.44 67	83.78 141	89.83 171

conf200view11		76.55 197	75.55 194	79.57 217	89.52 94	56.99 264	85.83 182	83.23 245	73.94 100	76.32 152	87.12 169	51.89 225	91.95 179	48.33 284	83.75 143	89.78 174

thres100view900		76.50 199	75.55 194	79.33 219	89.52 94	56.99 264	85.83 182	83.23 245	73.94 100	76.32 152	87.12 169	51.89 225	91.95 179	48.33 284	83.75 143	89.07 185

tfpn200view9		76.42 202	75.37 199	79.55 218	89.13 113	57.65 256	85.17 201	83.60 238	73.41 116	76.45 147	86.39 197	52.12 219	91.95 179	48.33 284	83.75 143	89.07 185

thres400		76.50 199	75.37 199	79.86 208	89.13 113	57.65 256	85.17 201	83.60 238	73.41 116	76.45 147	86.39 197	52.12 219	91.95 179	48.33 284	83.75 143	90.00 160

thres600view7		76.50 199	75.44 196	79.68 212	89.40 99	57.16 261	85.53 196	83.23 245	73.79 108	76.26 154	87.09 171	51.89 225	91.89 183	48.05 290	83.72 147	90.00 160

thres200		75.55 217	74.47 213	78.82 231	87.78 160	57.85 253	83.07 245	83.51 241	72.44 140	75.84 162	84.42 242	52.08 221	91.75 188	47.41 292	83.64 148	86.86 254

XVG-OURS		80.41 113	79.23 124	83.97 101	85.64 193	69.02 82	83.03 246	90.39 112	71.09 158	77.63 128	91.49 71	54.62 200	91.35 205	75.71 96	83.47 149	91.54 102

view600		76.20 206	75.21 202	79.16 224	89.64 87	55.82 282	85.74 186	82.06 261	73.88 103	75.74 164	87.85 145	51.84 228	91.66 196	46.75 294	83.42 150	90.00 160

view800		76.20 206	75.21 202	79.16 224	89.64 87	55.82 282	85.74 186	82.06 261	73.88 103	75.74 164	87.85 145	51.84 228	91.66 196	46.75 294	83.42 150	90.00 160

conf0.05thres1000		76.20 206	75.21 202	79.16 224	89.64 87	55.82 282	85.74 186	82.06 261	73.88 103	75.74 164	87.85 145	51.84 228	91.66 196	46.75 294	83.42 150	90.00 160

tfpn		76.20 206	75.21 202	79.16 224	89.64 87	55.82 282	85.74 186	82.06 261	73.88 103	75.74 164	87.85 145	51.84 228	91.66 196	46.75 294	83.42 150	90.00 160

CNLPA		78.08 164	76.79 170	81.97 165	90.40 74	71.07 48	87.59 120	84.55 230	66.03 231	72.38 214	89.64 104	57.56 176	86.04 280	59.61 226	83.35 154	88.79 203

MVP-Stereo		76.12 210	74.46 214	81.13 190	85.37 197	69.79 69	84.42 221	87.95 193	65.03 239	67.46 273	85.33 228	53.28 210	91.73 189	58.01 242	83.27 155	81.85 310
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
1314		76.53 198	75.30 201	80.21 204	83.93 232	62.32 217	84.66 210	88.81 175	60.23 279	70.16 241	84.07 245	55.30 192	90.73 222	67.37 166	83.21 156	87.59 237

mvs-test1		80.88 96	79.40 115	85.29 61	85.13 201	69.75 71	89.28 67	88.10 189	74.99 86	76.44 150	86.72 178	57.27 178	94.26 90	73.53 117	83.18 157	91.87 95

HyFIR lowres test		77.53 180	75.40 198	83.94 103	89.59 92	66.62 128	80.36 265	88.64 181	56.29 307	76.45 147	85.17 230	57.64 175	93.28 137	61.34 215	83.10 158	91.91 94

ACMP	74.13 6	81.51 91	80.57 91	84.36 85	89.42 98	68.69 96	89.97 53	91.50 87	74.46 92	75.04 185	90.41 90	53.82 206	94.54 79	77.56 76	82.91 159	89.86 170
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	73.20 8	80.78 106	79.84 102	83.58 109	89.31 106	68.37 100	89.99 52	91.60 81	70.28 170	77.25 134	89.66 103	53.37 209	93.53 128	74.24 110	82.85 160	88.85 200
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PMMVS		69.34 272	68.67 263	71.35 298	75.67 318	62.03 220	75.17 299	73.46 323	50.00 328	68.68 261	79.05 295	52.07 222	78.13 313	61.16 216	82.77 161	73.90 331

PLC	70.83 11	78.05 165	76.37 176	83.08 127	91.88 59	67.80 111	88.19 106	89.46 147	64.33 246	69.87 248	88.38 134	53.66 207	93.58 125	58.86 233	82.73 162	87.86 231
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TR-MVS		77.44 187	76.18 182	81.20 187	88.24 140	63.24 203	84.61 214	86.40 213	67.55 216	77.81 124	86.48 196	54.10 203	93.15 144	57.75 244	82.72 163	87.20 246

pcd1.5k->3k		34.07 322	35.26 322	30.50 337	86.92 178	0.00 358	0.00 349	91.58 82	0.00 353	0.00 354	0.00 355	56.23 186	0.00 356	0.00 353	82.60 164	91.49 105

ab-mvs		79.51 136	78.97 129	81.14 189	88.46 134	60.91 226	83.84 232	89.24 155	70.36 168	79.03 94	88.87 121	63.23 101	90.21 228	65.12 184	82.57 165	92.28 84

HY-MVS	69.67 12	77.95 169	77.15 164	80.36 199	87.57 168	60.21 232	83.37 244	87.78 196	66.11 228	75.37 174	87.06 173	63.27 99	90.48 225	61.38 214	82.43 166	90.40 144

PS-MVSNAJss		82.07 79	81.31 81	84.34 87	86.51 184	67.27 120	89.27 68	91.51 85	71.75 148	79.37 91	90.22 94	63.15 103	94.27 87	77.69 75	82.36 167	91.49 105

PVSNet_BlendedMVS		80.60 109	80.02 98	82.36 159	88.85 118	65.40 148	86.16 173	92.00 63	69.34 184	78.11 119	86.09 207	66.02 78	94.27 87	71.52 140	82.06 168	87.39 240

WTY-MVS		75.65 216	75.68 192	75.57 273	86.40 185	56.82 267	77.92 287	82.40 255	65.10 238	76.18 157	87.72 149	63.13 106	80.90 302	60.31 221	81.96 169	89.00 196

ACMMP++_ref															81.95 170

DP-MVS		76.78 195	74.57 210	83.42 113	93.29 33	69.46 78	88.55 93	83.70 237	63.98 250	70.20 238	88.89 120	54.01 205	94.80 75	46.66 298	81.88 171	86.01 274

CMPMVS	51.72 21	70.19 268	68.16 268	76.28 267	73.15 327	57.55 258	79.47 273	83.92 235	48.02 330	56.48 322	84.81 238	43.13 291	86.42 278	62.67 201	81.81 172	84.89 285
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
tfpn_ndepth		73.70 230	72.75 227	76.52 260	87.78 160	54.92 290	84.32 224	80.28 282	67.57 215	72.50 205	84.82 237	50.12 254	89.44 240	45.73 304	81.66 173	85.20 280

XVG-OURS-SEG-HR		80.81 101	79.76 104	83.96 102	85.60 194	68.78 88	83.54 237	90.50 110	70.66 165	76.71 143	91.66 63	60.69 155	91.26 207	76.94 84	81.58 174	91.83 96

tfpn1000		73.44 236	72.49 230	76.29 266	87.81 156	53.69 298	84.05 231	78.81 296	67.99 211	72.09 220	86.27 203	49.95 256	89.04 252	44.09 314	81.38 175	86.15 269

MIMVSNet		70.69 262	69.30 258	74.88 278	84.52 208	56.35 277	75.87 297	79.42 288	64.59 242	67.76 269	82.41 260	41.10 303	81.54 301	46.64 300	81.34 176	86.75 257

ACMMP++															81.25 177

GA-MVS		76.87 194	75.17 206	81.97 165	82.75 261	62.58 214	81.44 259	86.35 215	72.16 146	74.74 188	82.89 255	46.20 276	92.02 178	68.85 157	81.09 178	91.30 109

sss		73.60 233	73.64 220	73.51 288	82.80 260	55.01 289	76.12 293	81.69 267	62.47 264	74.68 189	85.85 216	57.32 177	78.11 314	60.86 218	80.93 179	87.39 240

Effi-MVS+-dtu		80.03 127	78.57 136	84.42 83	85.13 201	68.74 91	88.77 84	88.10 189	74.99 86	74.97 186	83.49 252	57.27 178	93.36 135	73.53 117	80.88 180	91.18 111

EG-PatchMatch MVS		74.04 227	71.82 242	80.71 196	84.92 204	67.42 116	85.86 181	88.08 191	66.04 230	64.22 296	83.85 246	35.10 323	92.56 165	57.44 246	80.83 181	82.16 309

jajsoiax		79.29 143	77.96 149	83.27 119	84.68 207	66.57 130	89.25 69	90.16 126	69.20 187	75.46 170	89.49 107	45.75 281	93.13 146	76.84 86	80.80 182	90.11 152

1112_ss		77.40 189	76.43 174	80.32 201	89.11 115	60.41 231	83.65 234	87.72 197	62.13 267	73.05 200	86.72 178	62.58 124	89.97 230	62.11 207	80.80 182	90.59 133

mvs_tets		79.13 146	77.77 155	83.22 121	84.70 206	66.37 132	89.17 70	90.19 125	69.38 183	75.40 173	89.46 110	44.17 287	93.15 144	76.78 87	80.70 184	90.14 150

PatchMatch-RL		72.38 252	70.90 251	76.80 259	88.60 129	67.38 118	79.53 272	76.17 308	62.75 261	69.36 254	82.00 269	45.51 282	84.89 288	53.62 264	80.58 185	78.12 321

EI-MVSNet		80.52 112	79.98 99	82.12 161	84.28 211	63.19 206	86.41 167	88.95 169	74.18 96	78.69 98	87.54 156	66.62 71	92.43 167	72.57 129	80.57 186	90.74 123

MVSTER		79.01 148	77.88 151	82.38 158	83.07 253	64.80 165	84.08 230	88.95 169	69.01 194	78.69 98	87.17 168	54.70 198	92.43 167	74.69 106	80.57 186	89.89 169

testing_2		75.73 215	73.34 223	82.89 141	77.37 311	65.22 155	84.10 229	90.54 109	69.09 189	60.46 307	81.15 280	40.48 305	92.84 159	76.36 88	80.54 188	90.60 131

XVG-ACMP-BASELINE		76.11 211	74.27 216	81.62 178	83.20 249	64.67 167	83.60 236	89.75 139	69.75 177	71.85 222	87.09 171	32.78 324	92.11 177	69.99 149	80.43 189	88.09 226

Fast-Effi-MVS+-dtu		78.02 166	76.49 173	82.62 155	83.16 252	66.96 126	86.94 149	87.45 203	72.45 138	71.49 227	84.17 243	54.79 197	91.58 202	67.61 163	80.31 190	89.30 183

LTVRE_ROB	69.57 13	76.25 205	74.54 212	81.41 183	88.60 129	64.38 182	79.24 275	89.12 158	70.76 163	69.79 250	87.86 144	49.09 263	93.20 141	56.21 254	80.16 191	86.65 259
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
Test_1112_low_res		76.40 203	75.44 196	79.27 220	89.28 107	58.09 246	81.69 255	87.07 206	59.53 285	72.48 207	86.67 184	61.30 144	89.33 241	60.81 219	80.15 192	90.41 143

test_djsdf		80.30 119	79.32 118	83.27 119	83.98 231	65.37 151	90.50 42	90.38 113	68.55 200	76.19 156	88.70 123	56.44 185	93.46 130	78.98 63	80.14 193	90.97 116

CHOSEN 280x420		66.51 286	64.71 285	71.90 293	81.45 278	63.52 195	57.98 339	68.95 337	53.57 318	62.59 303	76.70 309	46.22 275	75.29 326	55.25 257	79.68 194	76.88 329

conf0.002		73.67 232	72.42 232	77.42 252	87.85 149	53.28 301	83.38 238	79.08 290	68.40 203	72.45 208	86.08 208	50.60 246	89.19 244	44.25 309	79.66 195	89.78 174

thresconf0.02		73.39 237	72.42 232	76.31 262	87.85 149	53.28 301	83.38 238	79.08 290	68.40 203	72.45 208	86.08 208	50.60 246	89.19 244	44.25 309	79.66 195	86.48 261

tfpn_n400		73.39 237	72.42 232	76.31 262	87.85 149	53.28 301	83.38 238	79.08 290	68.40 203	72.45 208	86.08 208	50.60 246	89.19 244	44.25 309	79.66 195	86.48 261

tfpnconf		73.39 237	72.42 232	76.31 262	87.85 149	53.28 301	83.38 238	79.08 290	68.40 203	72.45 208	86.08 208	50.60 246	89.19 244	44.25 309	79.66 195	86.48 261

tfpnview11		73.39 237	72.42 232	76.31 262	87.85 149	53.28 301	83.38 238	79.08 290	68.40 203	72.45 208	86.08 208	50.60 246	89.19 244	44.25 309	79.66 195	86.48 261

GBi-Net		78.40 156	77.40 160	81.40 184	87.60 164	63.01 208	88.39 98	89.28 151	71.63 150	75.34 175	87.28 161	54.80 194	91.11 211	62.72 198	79.57 200	90.09 154

test1		78.40 156	77.40 160	81.40 184	87.60 164	63.01 208	88.39 98	89.28 151	71.63 150	75.34 175	87.28 161	54.80 194	91.11 211	62.72 198	79.57 200	90.09 154

FMVSNet3		77.88 172	76.85 168	80.97 192	86.84 180	62.36 215	86.52 164	88.77 176	71.13 156	75.34 175	86.66 185	54.07 204	91.10 214	62.72 198	79.57 200	89.45 181

FMVSNet2		78.20 161	77.21 163	81.20 187	87.60 164	62.89 212	87.47 128	89.02 160	71.63 150	75.29 179	87.28 161	54.80 194	91.10 214	62.38 202	79.38 203	89.61 179

anonymousdsp		78.60 154	77.15 164	82.98 133	80.51 291	67.08 122	87.24 137	89.53 144	65.66 234	75.16 181	87.19 167	52.52 211	92.25 174	77.17 81	79.34 204	89.61 179

nrg030		83.88 55	83.53 55	84.96 70	86.77 182	69.28 80	90.46 44	92.67 40	74.79 89	82.95 58	91.33 74	72.70 28	93.09 148	80.79 54	79.28 205	92.50 77

VPA-MVSNet		80.60 109	80.55 92	80.76 195	88.07 143	60.80 228	86.86 152	91.58 82	75.67 73	80.24 86	89.45 112	63.34 97	90.25 227	70.51 145	79.22 206	91.23 110

F-COLMAP		76.38 204	74.33 215	82.50 156	89.28 107	66.95 127	88.41 97	89.03 159	64.05 248	66.83 279	88.61 127	46.78 273	92.89 155	57.48 245	78.55 207	87.67 234

FMVSNet1		77.44 187	76.12 183	81.40 184	86.81 181	63.01 208	88.39 98	89.28 151	70.49 167	74.39 191	87.28 161	49.06 264	91.11 211	60.91 217	78.52 208	90.09 154

MDTV_nov1_ep13			69.97 257		83.18 250	53.48 299	77.10 291	80.18 284	60.45 276	69.33 255	80.44 286	48.89 265	86.90 273	51.60 270	78.51 209

CVMVSNet		72.99 248	72.58 229	74.25 284	84.28 211	50.85 316	86.41 167	83.45 243	44.56 332	73.23 198	87.54 156	49.38 259	85.70 282	65.90 179	78.44 210	86.19 268

tpm2		73.26 244	71.46 244	78.63 233	83.34 245	56.71 270	80.65 263	80.40 279	56.63 305	73.55 194	82.02 268	51.80 232	91.24 208	56.35 253	78.42 211	87.95 228

CostFormer		75.24 221	73.90 219	79.27 220	82.65 265	58.27 245	80.80 260	82.73 253	61.57 270	75.33 178	83.13 254	55.52 190	91.07 217	64.98 187	78.34 212	88.45 220

ACMH	67.68 16	75.89 213	73.93 218	81.77 169	88.71 127	66.61 129	88.62 90	89.01 162	69.81 175	66.78 280	86.70 183	41.95 301	91.51 203	55.64 255	78.14 213	87.17 247
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CR-MVSNet		73.37 241	71.27 247	79.67 213	81.32 283	65.19 156	75.92 295	80.30 280	59.92 282	72.73 203	81.19 278	52.50 212	86.69 274	59.84 224	77.71 214	87.11 250

RPMNet		71.62 255	68.94 262	79.67 213	81.32 283	65.19 156	75.92 295	78.30 299	57.60 299	72.73 203	76.45 311	52.30 216	86.69 274	48.14 289	77.71 214	87.11 250

Patchmatch-test1		73.49 234	71.85 241	78.41 239	84.05 230	62.17 219	79.96 269	79.29 289	66.30 227	72.38 214	79.58 294	51.95 224	85.08 287	55.46 256	77.67 216	87.99 227

tpmp4_e23		73.45 235	71.17 249	80.31 202	83.55 241	59.56 236	81.88 251	82.33 256	57.94 296	70.51 235	81.62 276	51.19 238	91.63 200	53.96 262	77.51 217	89.75 177

v7		80.24 120	79.26 123	83.15 123	84.07 228	64.94 162	87.56 124	90.67 103	72.26 143	78.28 111	86.51 195	61.45 141	94.03 99	75.14 104	77.41 218	90.49 139

DWT-MVSNet_test		73.70 230	71.86 240	79.21 222	82.91 258	58.94 239	82.34 248	82.17 258	65.21 236	71.05 231	78.31 299	44.21 286	90.17 229	63.29 196	77.28 219	88.53 219

v1144		80.03 127	79.03 127	83.01 131	83.78 237	64.51 173	87.11 144	90.57 108	71.96 147	78.08 121	86.20 205	61.41 142	93.94 102	74.93 105	77.23 220	90.60 131

WR-MVS		79.49 138	79.22 125	80.27 203	88.79 124	58.35 243	85.06 204	88.61 182	78.56 29	77.65 127	88.34 135	63.81 95	90.66 223	64.98 187	77.22 221	91.80 99

v1192		79.59 135	78.43 141	83.07 128	83.55 241	64.52 171	86.93 150	90.58 107	70.83 160	77.78 125	85.90 213	59.15 166	93.94 102	73.96 112	77.19 222	90.76 121

VPNet		78.69 153	78.66 132	78.76 232	88.31 139	55.72 287	84.45 219	86.63 210	76.79 51	78.26 115	90.55 89	59.30 165	89.70 235	66.63 173	77.05 223	90.88 118

v1neww		80.40 114	79.54 109	82.98 133	84.10 222	64.51 173	87.57 121	90.22 122	73.25 119	78.47 104	86.65 186	62.83 111	93.86 108	75.72 94	77.02 224	90.58 134

v7new		80.40 114	79.54 109	82.98 133	84.10 222	64.51 173	87.57 121	90.22 122	73.25 119	78.47 104	86.65 186	62.83 111	93.86 108	75.72 94	77.02 224	90.58 134

v6		80.40 114	79.54 109	82.98 133	84.09 224	64.50 177	87.57 121	90.22 122	73.25 119	78.47 104	86.63 188	62.84 110	93.86 108	75.73 93	77.02 224	90.58 134

v1240		78.99 149	77.78 154	82.64 154	83.21 248	63.54 194	86.62 161	90.30 120	69.74 179	77.33 132	85.68 218	57.04 183	93.76 117	73.13 122	76.92 227	90.62 129

MSDG		73.36 243	70.99 250	80.49 197	84.51 209	65.80 141	80.71 262	86.13 218	65.70 233	65.46 288	83.74 249	44.60 284	90.91 219	51.13 272	76.89 228	84.74 287

IterMVS-LS		80.06 126	79.38 116	82.11 162	85.89 189	63.20 205	86.79 155	89.34 149	74.19 95	75.45 171	86.72 178	66.62 71	92.39 169	72.58 128	76.86 229	90.75 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		79.22 144	78.03 148	82.80 147	83.30 247	63.94 191	86.80 154	90.33 118	69.91 174	77.48 130	85.53 224	58.44 170	93.75 118	73.60 116	76.85 230	90.71 124

XXY-MVS		75.41 219	75.56 193	74.96 277	83.59 240	57.82 254	80.59 264	83.87 236	66.54 225	74.93 187	88.31 136	63.24 100	80.09 306	62.16 205	76.85 230	86.97 252

v1141		80.19 123	79.31 119	82.85 142	83.84 234	64.12 186	87.14 139	90.08 129	73.13 122	78.27 112	86.39 197	62.67 120	93.75 118	75.40 101	76.83 232	90.68 125

divwei89l23v2f112		80.19 123	79.31 119	82.85 142	83.84 234	64.11 188	87.13 142	90.08 129	73.13 122	78.27 112	86.39 197	62.69 118	93.75 118	75.40 101	76.82 233	90.68 125

v1		80.19 123	79.31 119	82.85 142	83.83 236	64.12 186	87.14 139	90.07 131	73.13 122	78.27 112	86.38 201	62.72 117	93.75 118	75.41 100	76.82 233	90.68 125

v2v482		80.23 121	79.29 122	83.05 129	83.62 239	64.14 184	87.04 146	89.97 133	73.61 110	78.18 118	87.22 165	61.10 149	93.82 111	76.11 89	76.78 235	91.18 111

v144192		79.47 139	78.37 142	82.78 150	83.35 244	63.96 190	86.96 148	90.36 116	69.99 173	77.50 129	85.67 219	60.66 156	93.77 116	74.27 109	76.58 236	90.62 129

UniMVSNet (Re)		81.60 88	81.11 85	83.09 126	88.38 137	64.41 181	87.60 119	93.02 25	78.42 31	78.56 101	88.16 139	69.78 49	93.26 138	69.58 152	76.49 237	91.60 100

UniMVSNet_NR-MVSNet		81.88 82	81.54 80	82.92 138	88.46 134	63.46 197	87.13 142	92.37 49	80.19 15	78.38 108	89.14 116	71.66 35	93.05 150	70.05 147	76.46 238	92.25 85

DU-MVS		81.12 94	80.52 93	82.90 139	87.80 157	63.46 197	87.02 147	91.87 71	79.01 26	78.38 108	89.07 117	65.02 85	93.05 150	70.05 147	76.46 238	92.20 87

PatchmatchNet		73.12 246	71.33 246	78.49 238	83.18 250	60.85 227	79.63 271	78.57 297	64.13 247	71.73 223	79.81 293	51.20 237	85.97 281	57.40 247	76.36 240	88.66 206
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
USDC		70.33 266	68.37 265	76.21 268	80.60 289	56.23 278	79.19 277	86.49 211	60.89 274	61.29 304	85.47 226	31.78 327	89.47 239	53.37 265	76.21 241	82.94 306

OpenMVS_ROB	64.09 19	70.56 264	68.19 267	77.65 248	80.26 292	59.41 238	85.01 205	82.96 251	58.76 290	65.43 289	82.33 261	37.63 317	91.23 209	45.34 307	76.03 242	82.32 307

ACMH+	68.96 14	76.01 212	74.01 217	82.03 164	88.60 129	65.31 153	88.86 80	87.55 199	70.25 171	67.75 270	87.47 158	41.27 302	93.19 142	58.37 238	75.94 243	87.60 236

PatchFormer-LS_test		74.50 223	73.05 225	78.86 230	82.95 257	59.55 237	81.65 256	82.30 257	67.44 218	71.62 225	78.15 301	52.34 215	88.92 258	65.05 186	75.90 244	88.12 225

tpm		72.37 253	71.71 243	74.35 283	82.19 270	52.00 307	79.22 276	77.29 304	64.56 243	72.95 201	83.68 251	51.35 235	83.26 296	58.33 239	75.80 245	87.81 232

Anonymous20231206		68.60 274	67.80 275	71.02 300	80.23 294	50.75 317	78.30 285	80.47 277	56.79 304	66.11 286	82.63 259	46.35 274	78.95 310	43.62 316	75.70 246	83.36 298

v7n		78.97 150	77.58 158	83.14 124	83.45 243	65.51 146	88.32 101	91.21 93	73.69 109	72.41 213	86.32 202	57.93 173	93.81 112	69.18 155	75.65 247	90.11 152

NR-MVSNet		80.23 121	79.38 116	82.78 150	87.80 157	63.34 200	86.31 170	91.09 97	79.01 26	72.17 216	89.07 117	67.20 68	92.81 160	66.08 178	75.65 247	92.20 87

v10		79.74 133	78.67 131	82.97 137	84.06 229	64.95 161	87.88 116	90.62 106	73.11 125	75.11 183	86.56 192	61.46 140	94.05 98	73.68 113	75.55 249	89.90 168

IB-MVS	68.01 15	75.85 214	73.36 222	83.31 117	84.76 205	66.03 135	83.38 238	85.06 226	70.21 172	69.40 252	81.05 281	45.76 280	94.66 78	65.10 185	75.49 250	89.25 184
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
V42		79.38 142	78.24 146	82.83 145	81.10 285	65.50 147	85.55 194	89.82 137	71.57 153	78.21 116	86.12 206	60.66 156	93.18 143	75.64 97	75.46 251	89.81 173

v8		79.97 129	79.02 128	82.80 147	84.09 224	64.50 177	87.96 111	90.29 121	74.13 98	75.24 180	86.81 175	62.88 108	93.89 107	74.39 108	75.40 252	90.00 160

Baseline_NR-MVSNet		78.15 163	78.33 144	77.61 249	85.79 190	56.21 279	86.78 156	85.76 221	73.60 111	77.93 123	87.57 154	65.02 85	88.99 253	67.14 170	75.33 253	87.63 235

pmmvs5		71.55 256	70.20 256	75.61 272	77.83 308	56.39 275	81.74 254	80.89 272	57.76 297	67.46 273	84.49 241	49.26 262	85.32 286	57.08 250	75.29 254	85.11 284

EPMVS		69.02 273	68.16 268	71.59 294	79.61 299	49.80 322	77.40 289	66.93 339	62.82 260	70.01 243	79.05 295	45.79 279	77.86 316	56.58 252	75.26 255	87.13 249

TranMVSNet+NR-MVSNet		80.84 98	80.31 95	82.42 157	87.85 149	62.33 216	87.74 117	91.33 90	80.55 12	77.99 122	89.86 100	65.23 83	92.62 162	67.05 171	75.24 256	92.30 83

tfpnnormal		74.39 224	73.16 224	78.08 242	86.10 188	58.05 247	84.65 213	87.53 200	70.32 169	71.22 229	85.63 221	54.97 193	89.86 231	43.03 317	75.02 257	86.32 266

COLMAP_ROB	66.92 17	73.01 247	70.41 254	80.81 194	87.13 176	65.63 143	88.30 102	84.19 234	62.96 257	63.80 299	87.69 151	38.04 314	92.56 165	46.66 298	74.91 258	84.24 291
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PatchT		68.46 277	67.85 273	70.29 302	80.70 288	43.93 330	72.47 308	74.88 314	60.15 280	70.55 233	76.57 310	49.94 257	81.59 300	50.58 273	74.83 259	85.34 279

pmmvs4		74.03 228	71.91 239	80.39 198	81.96 272	68.32 101	81.45 258	82.14 259	59.32 286	69.87 248	85.13 231	52.40 214	88.13 266	60.21 222	74.74 260	84.73 288

ITE_SJBPF				78.22 241	81.77 274	60.57 229		83.30 244	69.25 186	67.54 272	87.20 166	36.33 320	87.28 272	54.34 260	74.62 261	86.80 255

test0.0.03 1		68.00 278	67.69 277	68.90 307	77.55 309	47.43 324	75.70 298	72.95 325	66.66 221	66.56 281	82.29 262	48.06 267	75.87 323	44.97 308	74.51 262	83.41 297

test_0402		72.79 250	70.44 253	79.84 209	88.13 142	65.99 137	85.93 179	84.29 232	65.57 235	67.40 275	85.49 225	46.92 272	92.61 163	35.88 328	74.38 263	80.94 313

CP-MVSNet		78.22 159	78.34 143	77.84 245	87.83 155	54.54 292	87.94 113	91.17 95	77.65 33	73.48 195	88.49 131	62.24 132	88.43 262	62.19 204	74.07 264	90.55 137

FMVSNet5		69.50 271	67.96 271	74.15 285	82.97 256	55.35 288	80.01 268	82.12 260	62.56 263	63.02 300	81.53 277	36.92 318	81.92 299	48.42 283	74.06 265	85.17 283

MVS-HIRNet		59.14 301	57.67 303	63.57 317	81.65 275	43.50 331	71.73 309	65.06 342	39.59 337	51.43 331	57.73 337	38.34 313	82.58 298	39.53 323	73.95 266	64.62 338

tpmrst		72.39 251	72.13 238	73.18 290	80.54 290	49.91 320	79.91 270	79.08 290	63.11 254	71.69 224	79.95 290	55.32 191	82.77 297	65.66 182	73.89 267	86.87 253

PS-CasMVS		78.01 167	78.09 147	77.77 247	87.71 162	54.39 294	88.02 109	91.22 92	77.50 40	73.26 197	88.64 126	60.73 153	88.41 263	61.88 208	73.88 268	90.53 138

v148		78.72 152	77.80 153	81.47 182	82.73 262	61.96 221	86.30 171	88.08 191	73.26 118	76.18 157	85.47 226	62.46 128	92.36 171	71.92 138	73.82 269	90.09 154

Patchmatch-test		64.82 292	63.24 290	69.57 304	79.42 301	49.82 321	63.49 334	69.05 336	51.98 324	59.95 310	80.13 289	50.91 240	70.98 337	40.66 322	73.57 270	87.90 230

WR-MVS_H		78.51 155	78.49 137	78.56 235	88.02 145	56.38 276	88.43 94	92.67 40	77.14 43	73.89 193	87.55 155	66.25 74	89.24 243	58.92 232	73.55 271	90.06 158

testgi		66.67 285	66.53 281	67.08 312	75.62 319	41.69 335	75.93 294	76.50 307	66.11 228	65.20 292	86.59 190	35.72 322	74.71 327	43.71 315	73.38 272	84.84 286

pm-mvs1		77.25 190	76.68 171	78.93 229	84.22 214	58.62 241	86.41 167	88.36 185	71.37 155	73.31 196	88.01 143	61.22 147	89.15 250	64.24 191	73.01 273	89.03 193

V4		77.95 169	76.37 176	82.67 152	79.40 302	65.52 144	86.43 165	89.94 134	72.28 141	72.14 219	84.95 235	55.72 188	93.44 132	73.64 114	72.86 274	89.05 191

v52		77.94 171	76.37 176	82.67 152	79.39 303	65.52 144	86.43 165	89.94 134	72.28 141	72.15 218	84.94 236	55.70 189	93.44 132	73.64 114	72.84 275	89.06 187

v748		77.97 168	76.65 172	81.92 167	82.29 269	63.28 202	87.53 125	90.35 117	73.50 115	70.76 232	85.55 223	58.28 171	92.81 160	68.81 158	72.76 276	89.67 178

tpmvs		71.09 259	69.29 259	76.49 261	82.04 271	56.04 280	78.92 279	81.37 271	64.05 248	67.18 277	78.28 300	49.74 258	89.77 232	49.67 280	72.37 277	83.67 295

PEN-MVS		77.73 174	77.69 157	77.84 245	87.07 177	53.91 296	87.91 115	91.18 94	77.56 37	73.14 199	88.82 122	61.23 146	89.17 249	59.95 223	72.37 277	90.43 142

DSMNet-mixed		57.77 305	56.90 305	60.38 321	67.70 337	35.61 341	69.18 319	53.97 346	32.30 343	57.49 318	79.88 291	40.39 307	68.57 341	38.78 324	72.37 277	76.97 326

semantic-postprocess				80.11 205	82.69 264	64.85 164		83.47 242	69.16 188	70.49 236	84.15 244	50.83 244	88.15 265	69.23 154	72.14 280	87.34 242

tpm cat1		70.57 263	68.31 266	77.35 254	82.41 268	57.95 251	78.08 286	80.22 283	52.04 323	68.54 265	77.66 306	52.00 223	87.84 269	51.77 269	72.07 281	86.25 267

RPSCF		73.23 245	71.46 244	78.54 236	82.50 267	59.85 233	82.18 250	82.84 252	58.96 288	71.15 230	89.41 114	45.48 283	84.77 289	58.82 234	71.83 282	91.02 115

IterMVS		74.29 225	72.94 226	78.35 240	81.53 277	63.49 196	81.58 257	82.49 254	68.06 210	69.99 245	83.69 250	51.66 234	85.54 283	65.85 180	71.64 283	86.01 274
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AllTest		70.96 260	68.09 270	79.58 215	85.15 199	63.62 192	84.58 215	79.83 285	62.31 265	60.32 308	86.73 176	32.02 325	88.96 256	50.28 275	71.57 284	86.15 269

TestCases				79.58 215	85.15 199	63.62 192		79.83 285	62.31 265	60.32 308	86.73 176	32.02 325	88.96 256	50.28 275	71.57 284	86.15 269

Patchmtry		70.74 261	69.16 260	75.49 274	80.72 287	54.07 295	74.94 304	80.30 280	58.34 292	70.01 243	81.19 278	52.50 212	86.54 276	53.37 265	71.09 286	85.87 276

test2356		59.50 300	58.08 300	63.74 316	71.23 331	41.88 333	67.59 326	72.42 327	53.72 317	57.65 317	70.74 325	26.31 331	72.40 334	32.03 335	71.06 287	76.93 327

DTE-MVSNet		76.99 192	76.80 169	77.54 251	86.24 186	53.06 306	87.52 126	90.66 105	77.08 46	72.50 205	88.67 125	60.48 159	89.52 237	57.33 248	70.74 288	90.05 159

MIMVSNet1		68.58 275	66.78 280	73.98 286	80.07 295	51.82 308	80.77 261	84.37 231	64.40 245	59.75 311	82.16 264	36.47 319	83.63 293	42.73 318	70.33 289	86.48 261

pmmvs6		74.69 222	73.39 221	78.61 234	81.38 280	57.48 259	86.64 160	87.95 193	64.99 240	70.18 239	86.61 189	50.43 252	89.52 237	62.12 206	70.18 290	88.83 201

TinyColmap		67.30 282	64.81 284	74.76 280	81.92 273	56.68 271	80.29 266	81.49 270	60.33 277	56.27 323	83.22 253	24.77 334	87.66 271	45.52 305	69.47 291	79.95 317

OurMVSNet-221017-0		74.26 226	72.42 232	79.80 210	83.76 238	59.59 234	85.92 180	86.64 209	66.39 226	66.96 278	87.58 153	39.46 308	91.60 201	65.76 181	69.27 292	88.22 223

JIA-IIPM		66.32 288	62.82 294	76.82 258	77.09 314	61.72 223	65.34 331	75.38 310	58.04 295	64.51 294	62.32 334	42.05 300	86.51 277	51.45 271	69.22 293	82.21 308

ADS-MVSNet2		66.20 289	63.33 289	74.82 279	79.92 296	58.75 240	67.55 327	75.19 312	53.37 319	65.25 290	75.86 312	42.32 297	80.53 304	41.57 320	68.91 294	85.18 281

ADS-MVSNet		64.36 294	62.88 293	68.78 309	79.92 296	47.17 325	67.55 327	71.18 328	53.37 319	65.25 290	75.86 312	42.32 297	73.99 331	41.57 320	68.91 294	85.18 281

test20.03		67.45 280	66.95 279	68.94 306	75.48 321	44.84 328	77.50 288	77.67 301	66.66 221	63.01 301	83.80 247	47.02 271	78.40 312	42.53 319	68.86 296	83.58 296

testus		59.00 302	57.91 301	62.25 319	72.25 329	39.09 338	69.74 315	75.02 313	53.04 321	57.21 319	73.72 319	18.76 342	70.33 338	32.86 331	68.57 297	77.35 324

EU-MVSNet		68.53 276	67.61 278	71.31 299	78.51 307	47.01 326	84.47 216	84.27 233	42.27 333	66.44 284	84.79 239	40.44 306	83.76 291	58.76 235	68.54 298	83.17 299

v16		77.69 175	76.36 179	81.68 175	84.15 219	64.63 170	87.33 132	88.99 164	72.69 136	69.31 256	82.08 265	62.80 114	91.79 185	72.70 126	67.23 299	88.63 208

v18		77.67 178	76.35 180	81.64 177	84.09 224	64.47 179	87.27 135	89.01 162	72.59 137	69.39 253	82.04 267	62.85 109	91.80 184	72.72 125	67.20 300	88.63 208

v17		77.68 176	76.35 180	81.69 174	84.15 219	64.65 168	87.33 132	88.99 164	72.70 135	69.25 257	82.07 266	62.82 113	91.79 185	72.69 127	67.15 301	88.63 208

v11		77.45 186	76.06 189	81.59 180	84.22 214	64.52 171	87.11 144	89.02 160	72.76 133	68.76 260	81.90 275	62.09 134	91.71 193	71.98 136	66.73 302	88.56 217

LF4IMVS		64.02 295	62.19 295	69.50 305	70.90 332	53.29 300	76.13 292	77.18 305	52.65 322	58.59 312	80.98 283	23.55 335	76.52 320	53.06 267	66.66 303	78.68 320

Patchmatch-RL test		70.24 267	67.78 276	77.61 249	77.43 310	59.57 235	71.16 310	70.33 329	62.94 258	68.65 262	72.77 321	50.62 245	85.49 284	69.58 152	66.58 304	87.77 233

dp		66.80 283	65.43 283	70.90 301	79.74 298	48.82 323	75.12 302	74.77 316	59.61 284	64.08 297	77.23 307	42.89 293	80.72 303	48.86 282	66.58 304	83.16 300

v15		77.51 183	76.12 183	81.66 176	84.09 224	64.65 168	87.14 139	88.96 168	72.76 133	68.90 258	81.91 274	62.74 116	91.73 189	72.32 131	66.29 306	88.61 211

V14		77.52 181	76.12 183	81.70 173	84.15 219	64.77 166	87.21 138	88.95 169	72.80 132	68.79 259	81.94 273	62.69 118	91.72 191	72.31 132	66.27 307	88.60 212

V9		77.52 181	76.11 186	81.73 172	84.19 218	64.89 163	87.26 136	88.94 172	72.87 131	68.65 262	81.96 272	62.65 121	91.72 191	72.27 133	66.24 308	88.60 212

v13		77.50 185	76.07 188	81.77 169	84.23 213	65.07 159	87.34 131	88.91 174	72.92 128	68.35 267	81.97 270	62.53 126	91.69 195	72.20 135	66.22 309	88.56 217

v12		77.51 183	76.09 187	81.76 171	84.22 214	64.99 160	87.30 134	88.93 173	72.92 128	68.48 266	81.97 270	62.54 125	91.70 194	72.24 134	66.21 310	88.58 215

FPMVS		53.68 310	51.64 310	59.81 322	65.08 338	51.03 314	69.48 318	69.58 333	41.46 334	40.67 336	72.32 322	16.46 345	70.00 339	24.24 343	65.42 311	58.40 340

pmmvs-eth3d		70.50 265	67.83 274	78.52 237	77.37 311	66.18 134	81.82 252	81.51 269	58.90 289	63.90 298	80.42 287	42.69 295	86.28 279	58.56 236	65.30 312	83.11 301

N_pmnet		52.79 311	53.26 309	51.40 330	78.99 306	7.68 355	69.52 317	3.89 355	51.63 326	57.01 320	74.98 315	40.83 304	65.96 344	37.78 326	64.67 313	80.56 316

PM-MVS		66.41 287	64.14 287	73.20 289	73.92 322	56.45 273	78.97 278	64.96 343	63.88 252	64.72 293	80.24 288	19.84 340	83.44 294	66.24 174	64.52 314	79.71 318

SixPastTwentyTwo		73.37 241	71.26 248	79.70 211	85.08 203	57.89 252	85.57 190	83.56 240	71.03 159	65.66 287	85.88 214	42.10 299	92.57 164	59.11 231	63.34 315	88.65 207

test1235678		58.74 303	56.89 306	64.30 314	69.70 333	41.87 334	71.05 311	74.87 315	54.06 314	50.63 332	71.53 324	25.30 333	74.10 330	31.80 336	63.10 316	76.93 327

testpf		56.51 307	57.58 304	53.30 327	71.99 330	41.19 336	46.89 344	69.32 335	58.06 294	52.87 330	69.45 329	27.99 329	72.73 333	59.59 227	62.07 317	45.98 343

TransMVSNet (Re)		75.39 220	74.56 211	77.86 244	85.50 196	57.10 263	86.78 156	86.09 219	72.17 145	71.53 226	87.34 160	63.01 107	89.31 242	56.84 251	61.83 318	87.17 247

MDA-MVSNet_test_wron		65.03 290	62.92 291	71.37 296	75.93 316	56.73 268	69.09 322	74.73 317	57.28 302	54.03 326	77.89 303	45.88 277	74.39 329	49.89 279	61.55 319	82.99 304

YYNet1		65.03 290	62.91 292	71.38 295	75.85 317	56.60 272	69.12 321	74.66 320	57.28 302	54.12 325	77.87 304	45.85 278	74.48 328	49.95 278	61.52 320	83.05 302

1111		57.11 306	56.82 307	57.97 324	69.10 334	28.28 346	68.90 323	74.54 321	54.01 315	53.71 327	74.51 316	23.09 336	67.90 342	32.28 333	61.26 321	77.73 322

ambc				75.24 276	73.16 326	50.51 318	63.05 335	87.47 202		64.28 295	77.81 305	17.80 343	89.73 234	57.88 243	60.64 322	85.49 277

TDRefinement		67.49 279	64.34 286	76.92 257	73.47 325	61.07 224	84.86 208	82.98 250	59.77 283	58.30 314	85.13 231	26.06 332	87.89 268	47.92 291	60.59 323	81.81 311

Gipuma		45.18 317	41.86 318	55.16 326	77.03 315	51.52 311	32.50 347	80.52 276	32.46 341	27.12 342	35.02 344	9.52 351	75.50 324	22.31 344	60.21 324	38.45 345
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
new-patchmatchnet		61.73 297	61.73 297	61.70 320	72.74 328	24.50 351	69.16 320	78.03 300	61.40 271	56.72 321	75.53 314	38.42 312	76.48 321	45.95 303	57.67 325	84.13 293

Anonymous20231211		64.82 292	61.79 296	73.91 287	77.11 313	50.92 315	85.29 199	81.53 268	54.19 313	57.98 315	78.03 302	26.90 330	87.83 270	37.92 325	57.12 326	82.99 304

MDA-MVSNet-bldmvs		66.68 284	63.66 288	75.75 270	79.28 304	60.56 230	73.92 306	78.35 298	64.43 244	50.13 333	79.87 292	44.02 288	83.67 292	46.10 302	56.86 327	83.03 303

new_pmnet		50.91 313	50.29 312	52.78 328	68.58 336	34.94 344	63.71 333	56.63 345	39.73 336	44.95 334	65.47 332	21.93 338	58.48 346	34.98 329	56.62 328	64.92 337

LP		61.36 299	57.78 302	72.09 292	75.54 320	58.53 242	67.16 329	75.22 311	51.90 325	54.13 324	69.97 327	37.73 316	80.45 305	32.74 332	55.63 329	77.29 325

PMVS	37.38 22	44.16 318	40.28 319	55.82 325	40.82 352	42.54 332	65.12 332	63.99 344	34.43 340	24.48 343	57.12 339	3.92 354	76.17 322	17.10 346	55.52 330	48.75 341
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmmvs3		57.79 304	54.26 308	68.37 310	64.02 339	56.72 269	75.12 302	65.17 341	40.20 335	52.93 329	69.86 328	20.36 339	75.48 325	45.45 306	55.25 331	72.90 332

UnsupCasMVSNet_eth		67.33 281	65.99 282	71.37 296	73.48 324	51.47 312	75.16 300	85.19 225	65.20 237	60.78 306	80.93 285	42.35 296	77.20 318	57.12 249	53.69 332	85.44 278

K. test v3		71.19 258	68.51 264	79.21 222	83.04 255	57.78 255	84.35 223	76.91 306	72.90 130	62.99 302	82.86 256	39.27 309	91.09 216	61.65 211	52.66 333	88.75 204

UnsupCasMVSNet_bld		63.70 296	61.53 298	70.21 303	73.69 323	51.39 313	72.82 307	81.89 265	55.63 309	57.81 316	71.80 323	38.67 311	78.61 311	49.26 281	52.21 334	80.63 314

LCM-MVSNet		54.25 308	49.68 314	67.97 311	53.73 346	45.28 327	66.85 330	80.78 274	35.96 339	39.45 338	62.23 335	8.70 352	78.06 315	48.24 288	51.20 335	80.57 315

testmv		53.85 309	51.03 311	62.31 318	61.46 341	38.88 339	70.95 314	74.69 319	51.11 327	41.26 335	66.85 330	14.28 346	72.13 335	29.19 338	49.51 336	75.93 330

lessismore_v0				78.97 228	81.01 286	57.15 262		65.99 340		61.16 305	82.82 257	39.12 310	91.34 206	59.67 225	46.92 337	88.43 221

test12356		49.28 315	48.51 315	51.59 329	62.06 340	19.11 352	60.40 336	72.45 326	47.60 331	40.64 337	65.68 331	13.84 347	68.72 340	27.29 340	46.67 338	66.94 336

PVSNet_0	57.27 20	61.67 298	59.27 299	68.85 308	79.61 299	57.44 260	68.01 325	73.44 324	55.93 308	58.54 313	70.41 326	44.58 285	77.55 317	47.01 293	35.91 339	71.55 333

PMMVS2		40.82 319	38.86 320	46.69 332	53.84 345	16.45 353	48.61 343	49.92 348	37.49 338	31.67 340	60.97 336	8.14 353	56.42 347	28.42 339	30.72 340	67.19 335

no-one		51.08 312	45.79 317	66.95 313	57.92 344	50.49 319	59.63 338	76.04 309	48.04 329	31.85 339	56.10 340	19.12 341	80.08 307	36.89 327	26.52 341	70.29 334

DeepMVS_CX				27.40 338	40.17 353	26.90 349		24.59 354	17.44 348	23.95 344	48.61 341	9.77 350	26.48 351	18.06 345	24.47 342	28.83 346

MVE	26.22 23	30.37 325	25.89 327	43.81 333	44.55 351	35.46 343	28.87 348	39.07 351	18.20 347	18.58 347	40.18 343	2.68 355	47.37 350	17.07 347	23.78 343	48.60 342
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuykxyi23d		39.76 320	33.18 323	59.51 323	46.98 350	44.01 329	57.70 340	67.74 338	24.13 345	13.98 350	34.33 345	1.27 357	71.33 336	34.23 330	18.23 344	63.18 339

E-PMN		31.77 323	30.64 324	35.15 334	52.87 347	27.67 348	57.09 341	47.86 349	24.64 344	16.40 348	33.05 346	11.23 349	54.90 348	14.46 348	18.15 345	22.87 347

PNet_i23d		38.26 321	35.42 321	46.79 331	58.74 342	35.48 342	59.65 337	51.25 347	32.45 342	23.44 346	47.53 342	2.04 356	58.96 345	25.60 342	18.09 346	45.92 344

EMVS		30.81 324	29.65 325	34.27 335	50.96 348	25.95 350	56.58 342	46.80 350	24.01 346	15.53 349	30.68 347	12.47 348	54.43 349	12.81 349	17.05 347	22.43 348

ANet_high		50.57 314	46.10 316	63.99 315	48.67 349	39.13 337	70.99 313	80.85 273	61.39 272	31.18 341	57.70 338	17.02 344	73.65 332	31.22 337	15.89 348	79.18 319

tmp_tt		18.61 327	21.40 328	10.23 340	4.82 354	10.11 354	34.70 346	30.74 353	1.48 350	23.91 345	26.07 348	28.42 328	13.41 353	27.12 341	15.35 349	7.17 349

wuyk23d		16.82 328	15.94 329	19.46 339	58.74 342	31.45 345	39.22 345	3.74 356	6.84 349	6.04 351	2.70 352	1.27 357	24.29 352	10.54 350	14.40 350	2.63 350

.test1245		45.55 316	50.02 313	32.14 336	69.10 334	28.28 346	68.90 323	74.54 321	54.01 315	53.71 327	74.51 316	23.09 336	67.90 342	32.28 333	0.02 351	0.25 352

testmvs		6.04 331	8.02 332	0.10 342	0.08 355	0.03 357	69.74 315	0.04 357	0.05 351	0.31 352	1.68 353	0.02 360	0.04 354	0.24 351	0.02 351	0.25 352

test123		6.12 330	8.11 331	0.14 341	0.06 356	0.09 356	71.05 311	0.03 358	0.04 352	0.25 353	1.30 354	0.05 359	0.03 355	0.21 352	0.01 353	0.29 351

cdsmvs_eth3d_5k		19.96 326	26.61 326	0.00 343	0.00 357	0.00 358	0.00 349	89.26 154	0.00 353	0.00 354	88.61 127	61.62 138	0.00 356	0.00 353	0.00 354	0.00 354

pcd_1.5k_mvsjas		5.26 332	7.02 333	0.00 343	0.00 357	0.00 358	0.00 349	0.00 359	0.00 353	0.00 354	0.00 355	63.15 103	0.00 356	0.00 353	0.00 354	0.00 354

sosnet-low-res		0.00 333	0.00 334	0.00 343	0.00 357	0.00 358	0.00 349	0.00 359	0.00 353	0.00 354	0.00 355	0.00 361	0.00 356	0.00 353	0.00 354	0.00 354

sosnet		0.00 333	0.00 334	0.00 343	0.00 357	0.00 358	0.00 349	0.00 359	0.00 353	0.00 354	0.00 355	0.00 361	0.00 356	0.00 353	0.00 354	0.00 354

uncertanet		0.00 333	0.00 334	0.00 343	0.00 357	0.00 358	0.00 349	0.00 359	0.00 353	0.00 354	0.00 355	0.00 361	0.00 356	0.00 353	0.00 354	0.00 354

Regformer		0.00 333	0.00 334	0.00 343	0.00 357	0.00 358	0.00 349	0.00 359	0.00 353	0.00 354	0.00 355	0.00 361	0.00 356	0.00 353	0.00 354	0.00 354

ab-mvs-re		7.23 329	9.64 330	0.00 343	0.00 357	0.00 358	0.00 349	0.00 359	0.00 353	0.00 354	86.72 178	0.00 361	0.00 356	0.00 353	0.00 354	0.00 354

uanet		0.00 333	0.00 334	0.00 343	0.00 357	0.00 358	0.00 349	0.00 359	0.00 353	0.00 354	0.00 355	0.00 361	0.00 356	0.00 353	0.00 354	0.00 354

GSMVS																88.96 198

test_part3							92.22 18		75.63 74		95.29 2		97.56 1	86.60 12

test_part2					95.06 1	72.65 26				91.80 1

sam_mvs1												51.32 236				88.96 198

sam_mvs												50.01 255

MTGPA								92.02 60

test_post1							78.90 280				5.43 351	48.81 266	85.44 285	59.25 230

test_post											5.46 350	50.36 253	84.24 290

patchmatchnet-post											74.00 318	51.12 239	88.60 261

MTMP								32.83 352

gm-plane-assit					81.40 279	53.83 297			62.72 262		80.94 284		92.39 169	63.40 195

TEST9					93.26 35	72.96 19	88.75 86	91.89 69	68.44 202	85.00 29	93.10 41	74.36 18	95.41 50

test_8					93.13 37	72.57 30	88.68 89	91.84 72	68.69 198	84.87 35	93.10 41	74.43 15	95.16 58

agg_prior					92.85 43	71.94 41		91.78 75		84.41 41			94.93 67

test_prior4						72.60 29	89.01 77

test_prior				86.33 47	92.61 48	69.59 73		92.97 31					95.48 45			93.91 30

旧先验2							86.56 163		58.10 293	87.04 15			88.98 254	74.07 111

新几何2							86.29 172

无先验							87.48 127	88.98 166	60.00 281				94.12 95	67.28 167		88.97 197

原ACMM2							86.86 152

testdata2													91.01 218	62.37 203

segment_acmp												73.08 25

testdata1							84.14 228		75.71 71

plane_prior7					90.08 80	68.51 99

plane_prior6					89.84 85	68.70 95						60.42 160

plane_prior4											91.00 82

plane_prior3						68.60 97			78.44 30	78.92 96

plane_prior2							91.25 30		79.12 23

plane_prior1					89.90 84

n2								0.00 359

nn								0.00 359

door-mid								69.98 331

test11								92.23 52

door								69.44 334

HQP5-MVS						66.98 124

HQP-NCC					89.33 101		89.17 70		76.41 59	77.23 136

ACMP_Plane					89.33 101		89.17 70		76.41 59	77.23 136

BP-MVS														77.47 77

HQP4-MVS										77.24 135			95.11 60			91.03 113

HQP2-MVS												60.17 163

NP-MVS					89.62 91	68.32 101					90.24 92

MDTV_nov1_ep13_2view						37.79 340	75.16 300		55.10 310	66.53 282		49.34 260		53.98 261		87.94 229

Test By Simon												64.33 89

High-resolution multi-view benchmark