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.

MSP-MVS		90.38 5	91.87 1	85.88 89	92.83 79	64.03 193	93.06 112	94.33 54	82.19 29	93.65 3	96.15 34	85.89 1	97.19 84	91.02 34	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
DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 160	76.68 2	97.29 1	95.35 15	82.87 22	91.58 13	97.22 3	79.93 5	99.10 9	83.12 102	97.64 2	97.94 1

OPU-MVS				89.97 3	97.52 3	73.15 14	96.89 6				97.00 9	83.82 2	99.15 2	95.72 5	97.63 3	97.62 2

DVP-MVS++		90.53 4	91.09 5	88.87 16	97.31 4	69.91 42	93.96 70	94.37 52	72.48 187	92.07 9	96.85 16	83.82 2	99.15 2	91.53 30	97.42 4	97.55 4

PC_three_1452									80.91 48	94.07 2	96.83 18	83.57 4	99.12 5	95.70 7	97.42 4	97.55 4

HPM-MVS++		89.37 14	89.95 13	87.64 34	95.10 30	68.23 86	95.24 33	94.49 44	82.43 26	88.90 32	96.35 27	71.89 36	98.63 26	88.76 48	96.40 6	96.06 41

SMA-MVS		88.14 18	88.29 22	87.67 33	93.21 67	68.72 72	93.85 77	94.03 62	74.18 150	91.74 12	96.67 21	65.61 74	98.42 33	89.24 44	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
DELS-MVS		90.05 8	90.09 11	89.94 4	93.14 70	73.88 9	97.01 4	94.40 50	88.32 3	85.71 55	94.91 73	74.11 20	98.91 18	87.26 62	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
MCST-MVS		91.08 1	91.46 3	89.94 4	97.66 2	73.37 10	97.13 2	95.58 10	89.33 1	85.77 54	96.26 30	72.84 28	99.38 1	92.64 20	95.93 9	97.08 11

balanced_conf03		89.08 15	88.84 17	89.81 6	93.66 54	75.15 5	90.61 224	93.43 87	84.06 14	86.20 49	90.17 181	72.42 31	96.98 101	93.09 16	95.92 10	97.29 7

CNVR-MVS		90.32 6	90.89 8	88.61 22	96.76 8	70.65 30	96.47 14	94.83 30	84.83 11	89.07 31	96.80 19	70.86 39	99.06 15	92.64 20	95.71 11	96.12 40

PHI-MVS		86.83 39	86.85 41	86.78 63	93.47 62	65.55 154	95.39 30	95.10 22	71.77 213	85.69 56	96.52 23	62.07 122	98.77 23	86.06 74	95.60 12	96.03 43

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 133	93.00 75	58.16 311	96.72 9	94.41 48	86.50 8	90.25 22	97.83 1	75.46 14	98.67 25	92.78 19	95.49 13	97.32 6

SED-MVS		89.94 9	90.36 10	88.70 18	96.45 12	69.38 55	96.89 6	94.44 46	71.65 217	92.11 7	97.21 4	76.79 9	99.11 6	92.34 22	95.36 14	97.62 2

IU-MVS					96.46 11	69.91 42		95.18 20	80.75 49	95.28 1				92.34 22	95.36 14	96.47 28

test_241102_TWO								94.41 48	71.65 217	92.07 9	97.21 4	74.58 17	99.11 6	92.34 22	95.36 14	96.59 19

MM		90.87 2	91.52 2	88.92 15	92.12 100	71.10 27	97.02 3	96.04 6	88.70 2	91.57 14	96.19 32	70.12 43	98.91 18	96.83 1	95.06 17	96.76 15

test_0728_THIRD									72.48 187	90.55 20	96.93 11	76.24 11	99.08 11	91.53 30	94.99 18	96.43 31

test9_res														89.41 40	94.96 19	95.29 70

ACMMP_NAP		86.05 52	85.80 57	86.80 62	91.58 119	67.53 104	91.79 170	93.49 84	74.93 141	84.61 66	95.30 56	59.42 150	97.92 41	86.13 72	94.92 20	94.94 88

DPE-MVS		88.77 17	89.21 16	87.45 43	96.26 20	67.56 102	94.17 58	94.15 59	68.77 266	90.74 18	97.27 2	76.09 12	98.49 29	90.58 38	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
DVP-MVS		89.41 13	89.73 14	88.45 25	96.40 15	69.99 38	96.64 10	94.52 42	71.92 203	90.55 20	96.93 11	73.77 22	99.08 11	91.91 28	94.90 22	96.29 35
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				88.70 18	96.45 12	70.43 33	96.64 10	94.37 52					99.15 2	91.91 28	94.90 22	96.51 24

train_agg		87.21 33	87.42 32	86.60 68	94.18 41	67.28 109	94.16 59	93.51 81	71.87 208	85.52 57	95.33 54	68.19 50	97.27 80	89.09 45	94.90 22	95.25 76

DeepC-MVS_fast	79.48 2	87.95 22	88.00 25	87.79 31	95.86 27	68.32 80	95.74 21	94.11 60	83.82 16	83.49 76	96.19 32	64.53 88	98.44 31	83.42 101	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
MSC_two_6792asdad				89.60 9	97.31 4	73.22 12		95.05 26					99.07 13	92.01 25	94.77 26	96.51 24

No_MVS				89.60 9	97.31 4	73.22 12		95.05 26					99.07 13	92.01 25	94.77 26	96.51 24

TSAR-MVS + MP.		88.11 20	88.64 18	86.54 72	91.73 115	68.04 90	90.36 230	93.55 80	82.89 21	91.29 16	92.89 124	72.27 33	96.03 147	87.99 52	94.77 26	95.54 57
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_prior2							95.10 38		75.40 135	85.25 63	95.61 45	67.94 53		87.47 59	94.77 26

agg_prior2														86.41 70	94.75 30	95.33 66

MVSMamba_PlusPlus		84.97 74	83.65 84	88.93 14	90.17 151	74.04 8	87.84 282	92.69 117	62.18 322	81.47 95	87.64 219	71.47 38	96.28 132	84.69 86	94.74 31	96.47 28

MVS		84.66 78	82.86 108	90.06 2	90.93 136	74.56 7	87.91 280	95.54 13	68.55 268	72.35 204	94.71 78	59.78 146	98.90 20	81.29 118	94.69 32	96.74 16

MVS_0304		90.32 6	90.90 7	88.55 23	94.05 45	70.23 36	97.00 5	93.73 73	87.30 4	92.15 6	96.15 34	66.38 65	98.94 17	96.71 2	94.67 33	96.47 28

SF-MVS		87.03 35	87.09 35	86.84 59	92.70 85	67.45 107	93.64 90	93.76 69	70.78 241	86.25 47	96.44 26	66.98 59	97.79 47	88.68 49	94.56 34	95.28 72

NCCC		89.07 16	89.46 15	87.91 28	96.60 10	69.05 63	96.38 15	94.64 39	84.42 12	86.74 45	96.20 31	66.56 64	98.76 24	89.03 47	94.56 34	95.92 46

3Dnovator	73.91 6	82.69 120	80.82 137	88.31 26	89.57 162	71.26 22	92.60 134	94.39 51	78.84 86	67.89 262	92.48 134	48.42 272	98.52 28	68.80 221	94.40 36	95.15 78

CDPH-MVS		85.71 60	85.46 62	86.46 74	94.75 34	67.19 111	93.89 75	92.83 112	70.90 237	83.09 81	95.28 57	63.62 100	97.36 71	80.63 122	94.18 37	94.84 92

MG-MVS		87.11 34	86.27 45	89.62 8	97.79 1	76.27 4	94.96 43	94.49 44	78.74 89	83.87 75	92.94 122	64.34 89	96.94 107	75.19 161	94.09 38	95.66 52

9.14			87.63 28		93.86 48		94.41 52	94.18 57	72.76 182	86.21 48	96.51 24	66.64 62	97.88 44	90.08 39	94.04 39

原ACMM1				84.42 146	93.21 67	64.27 188		93.40 90	65.39 292	79.51 120	92.50 131	58.11 168	96.69 117	65.27 259	93.96 40	92.32 183

MSLP-MVS++		86.27 48	85.91 55	87.35 45	92.01 105	68.97 66	95.04 40	92.70 115	79.04 84	81.50 93	96.50 25	58.98 159	96.78 115	83.49 100	93.93 41	96.29 35

CANet		89.61 12	89.99 12	88.46 24	94.39 39	69.71 50	96.53 13	93.78 66	86.89 6	89.68 28	95.78 40	65.94 70	99.10 9	92.99 17	93.91 42	96.58 21

MP-MVS-pluss		85.24 68	85.13 67	85.56 102	91.42 124	65.59 152	91.54 180	92.51 126	74.56 144	80.62 106	95.64 44	59.15 154	97.00 97	86.94 67	93.80 43	94.07 130
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MVP-Stereo		77.12 219	76.23 211	79.79 272	81.72 309	66.34 135	89.29 256	90.88 200	70.56 244	62.01 318	82.88 275	49.34 263	94.13 222	65.55 256	93.80 43	78.88 371
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
GG-mvs-BLEND				86.53 73	91.91 110	69.67 52	75.02 374	94.75 33		78.67 135	90.85 167	77.91 7	94.56 206	72.25 187	93.74 45	95.36 65

ZNCC-MVS		85.33 67	85.08 68	86.06 84	93.09 72	65.65 150	93.89 75	93.41 89	73.75 161	79.94 115	94.68 79	60.61 137	98.03 38	82.63 106	93.72 46	94.52 110

CSCG		86.87 36	86.26 46	88.72 17	95.05 31	70.79 29	93.83 82	95.33 16	68.48 270	77.63 143	94.35 91	73.04 26	98.45 30	84.92 84	93.71 47	96.92 14

test12				87.09 52	94.60 36	68.86 67		92.91 109		82.67 87		65.44 75	97.55 62		93.69 48	94.84 92

PAPM		85.89 57	85.46 62	87.18 49	88.20 203	72.42 15	92.41 142	92.77 113	82.11 30	80.34 111	93.07 119	68.27 49	95.02 185	78.39 143	93.59 49	94.09 128

SteuartSystems-ACMMP		86.82 41	86.90 39	86.58 70	90.42 145	66.38 133	96.09 17	93.87 64	77.73 102	84.01 74	95.66 43	63.39 105	97.94 40	87.40 60	93.55 50	95.42 59
Skip Steuart: Steuart Systems R&D Blog.
APDe-MVS		87.54 27	87.84 26	86.65 66	96.07 23	66.30 136	94.84 45	93.78 66	69.35 257	88.39 33	96.34 28	67.74 55	97.66 54	90.62 37	93.44 51	96.01 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SPE-MVS-test		86.14 51	87.01 36	83.52 175	92.63 87	59.36 300	95.49 27	91.92 150	80.09 60	85.46 59	95.53 49	61.82 126	95.77 155	86.77 69	93.37 52	95.41 60

PS-MVSNAJ		88.14 18	87.61 29	89.71 7	92.06 101	76.72 1	95.75 20	93.26 93	83.86 15	89.55 29	96.06 36	53.55 223	97.89 43	91.10 32	93.31 53	94.54 108

MAR-MVS		84.18 89	83.43 91	86.44 75	96.25 21	65.93 145	94.28 56	94.27 56	74.41 145	79.16 126	95.61 45	53.99 218	98.88 22	69.62 210	93.26 54	94.50 112
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
gg-mvs-nofinetune		77.18 217	74.31 238	85.80 94	91.42 124	68.36 79	71.78 379	94.72 34	49.61 379	77.12 150	45.92 405	77.41 8	93.98 234	67.62 231	93.16 55	95.05 83

ZD-MVS					96.63 9	65.50 156		93.50 83	70.74 242	85.26 62	95.19 65	64.92 82	97.29 76	87.51 57	93.01 56

APD-MVS		85.93 55	85.99 53	85.76 96	95.98 26	65.21 161	93.59 93	92.58 124	66.54 284	86.17 50	95.88 39	63.83 95	97.00 97	86.39 71	92.94 57	95.06 82
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
新几何1				84.73 132	92.32 92	64.28 187		91.46 176	59.56 343	79.77 117	92.90 123	56.95 182	96.57 121	63.40 269	92.91 58	93.34 152

DeepC-MVS	77.85 3	85.52 65	85.24 65	86.37 78	88.80 185	66.64 127	92.15 149	93.68 75	81.07 46	76.91 153	93.64 109	62.59 117	98.44 31	85.50 76	92.84 59	94.03 132
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 33	89.55 12	91.41 127	76.43 3	95.74 21	93.12 101	83.53 18	89.55 29	95.95 38	53.45 227	97.68 50	91.07 33	92.62 60	94.54 108

MP-MVS		85.02 71	84.97 70	85.17 117	92.60 88	64.27 188	93.24 107	92.27 131	73.13 172	79.63 119	94.43 85	61.90 123	97.17 85	85.00 82	92.56 61	94.06 131
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTAPA		83.91 94	83.38 95	85.50 103	91.89 111	65.16 163	81.75 333	92.23 132	75.32 136	80.53 108	95.21 64	56.06 195	97.16 88	84.86 85	92.55 62	94.18 122

GST-MVS		84.63 79	84.29 78	85.66 100	92.82 81	65.27 159	93.04 114	93.13 100	73.20 170	78.89 128	94.18 98	59.41 151	97.85 45	81.45 114	92.48 63	93.86 140

HFP-MVS		84.73 77	84.40 77	85.72 98	93.75 52	65.01 167	93.50 98	93.19 97	72.19 197	79.22 125	94.93 71	59.04 157	97.67 51	81.55 112	92.21 64	94.49 113

ACMMPR		84.37 81	84.06 79	85.28 112	93.56 58	64.37 183	93.50 98	93.15 99	72.19 197	78.85 133	94.86 74	56.69 186	97.45 65	81.55 112	92.20 65	94.02 133

MS-PatchMatch		77.90 209	76.50 207	82.12 214	85.99 249	69.95 41	91.75 175	92.70 115	73.97 155	62.58 315	84.44 260	41.11 315	95.78 153	63.76 268	92.17 66	80.62 357

region2R		84.36 82	84.03 80	85.36 109	93.54 59	64.31 186	93.43 103	92.95 108	72.16 200	78.86 132	94.84 75	56.97 181	97.53 63	81.38 116	92.11 67	94.24 120

CS-MVS		85.80 58	86.65 43	83.27 183	92.00 106	58.92 304	95.31 31	91.86 155	79.97 61	84.82 65	95.40 52	62.26 120	95.51 173	86.11 73	92.08 68	95.37 63

patch_mono-2		89.71 11	90.99 6	85.85 92	96.04 24	63.70 203	95.04 40	95.19 19	86.74 7	91.53 15	95.15 66	73.86 21	97.58 59	93.38 14	92.00 69	96.28 37

dcpmvs_2		87.37 31	87.55 30	86.85 58	95.04 32	68.20 87	90.36 230	90.66 206	79.37 73	81.20 97	93.67 108	74.73 15	96.55 123	90.88 35	92.00 69	95.82 48

旧先验1					91.94 107	60.74 274		91.50 174			94.36 87	65.23 77			91.84 71	94.55 106

MVSFormer		83.75 99	82.88 107	86.37 78	89.24 175	71.18 24	89.07 262	90.69 203	65.80 289	87.13 40	94.34 92	64.99 79	92.67 273	72.83 178	91.80 72	95.27 73

lupinMVS		87.74 25	87.77 27	87.63 38	89.24 175	71.18 24	96.57 12	92.90 110	82.70 24	87.13 40	95.27 59	64.99 79	95.80 152	89.34 42	91.80 72	95.93 45

EPNet		87.84 24	88.38 20	86.23 82	93.30 64	66.05 140	95.26 32	94.84 29	87.09 5	88.06 34	94.53 82	66.79 61	97.34 73	83.89 95	91.68 74	95.29 70
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
3Dnovator+	73.60 7	82.10 130	80.60 144	86.60 68	90.89 138	66.80 124	95.20 34	93.44 86	74.05 152	67.42 269	92.49 133	49.46 262	97.65 55	70.80 200	91.68 74	95.33 66

XVS		83.87 95	83.47 89	85.05 119	93.22 65	63.78 197	92.92 118	92.66 119	73.99 153	78.18 137	94.31 94	55.25 201	97.41 68	79.16 134	91.58 76	93.95 135

X-MVStestdata		76.86 223	74.13 242	85.05 119	93.22 65	63.78 197	92.92 118	92.66 119	73.99 153	78.18 137	10.19 420	55.25 201	97.41 68	79.16 134	91.58 76	93.95 135

SD-MVS		87.49 28	87.49 31	87.50 42	93.60 56	68.82 69	93.90 74	92.63 122	76.86 115	87.90 35	95.76 41	66.17 67	97.63 56	89.06 46	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
EC-MVSNet		84.53 80	85.04 69	83.01 187	89.34 167	61.37 261	94.42 51	91.09 192	77.91 99	83.24 77	94.20 97	58.37 164	95.40 174	85.35 77	91.41 79	92.27 188

PGM-MVS		83.25 108	82.70 111	84.92 122	92.81 83	64.07 192	90.44 225	92.20 136	71.28 229	77.23 149	94.43 85	55.17 205	97.31 75	79.33 133	91.38 80	93.37 151

PVSNet_Blended		86.73 42	86.86 40	86.31 81	93.76 50	67.53 104	96.33 16	93.61 77	82.34 28	81.00 102	93.08 118	63.19 109	97.29 76	87.08 65	91.38 80	94.13 126

HPM-MVS		83.25 108	82.95 105	84.17 155	92.25 94	62.88 230	90.91 207	91.86 155	70.30 246	77.12 150	93.96 103	56.75 184	96.28 132	82.04 109	91.34 82	93.34 152
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EIA-MVS		84.84 75	84.88 71	84.69 135	91.30 129	62.36 239	93.85 77	92.04 143	79.45 70	79.33 124	94.28 95	62.42 118	96.35 130	80.05 126	91.25 83	95.38 62

MVS_111021_HR		86.19 50	85.80 57	87.37 44	93.17 69	69.79 47	93.99 69	93.76 69	79.08 81	78.88 131	93.99 102	62.25 121	98.15 36	85.93 75	91.15 84	94.15 125

test222					89.77 158	61.60 256	89.55 250	89.42 254	56.83 358	77.28 148	92.43 135	52.76 231			91.14 85	93.09 161

jason		86.40 45	86.17 49	87.11 51	86.16 247	70.54 32	95.71 24	92.19 138	82.00 31	84.58 67	94.34 92	61.86 124	95.53 172	87.76 54	90.89 86	95.27 73
jason: jason.
mPP-MVS		82.96 115	82.44 115	84.52 143	92.83 79	62.92 228	92.76 123	91.85 157	71.52 225	75.61 165	94.24 96	53.48 226	96.99 100	78.97 137	90.73 87	93.64 146

CP-MVS		83.71 100	83.40 94	84.65 137	93.14 70	63.84 195	94.59 49	92.28 130	71.03 235	77.41 146	94.92 72	55.21 204	96.19 136	81.32 117	90.70 88	93.91 137

OpenMVS	70.45 11	78.54 197	75.92 216	86.41 77	85.93 253	71.68 18	92.74 124	92.51 126	66.49 285	64.56 293	91.96 146	43.88 305	98.10 37	54.61 312	90.65 89	89.44 235

PAPM_NR		82.97 114	81.84 122	86.37 78	94.10 44	66.76 125	87.66 286	92.84 111	69.96 250	74.07 181	93.57 111	63.10 112	97.50 64	70.66 203	90.58 90	94.85 89

testdata				81.34 231	89.02 179	57.72 315		89.84 238	58.65 347	85.32 61	94.09 99	57.03 177	93.28 251	69.34 213	90.56 91	93.03 164

mvsmamba		81.55 138	80.72 139	84.03 161	91.42 124	66.93 120	83.08 324	89.13 268	78.55 91	67.50 267	87.02 231	51.79 239	90.07 327	87.48 58	90.49 92	95.10 81

Vis-MVSNet		80.92 150	79.98 153	83.74 166	88.48 190	61.80 250	93.44 102	88.26 303	73.96 156	77.73 141	91.76 151	49.94 257	94.76 193	65.84 251	90.37 93	94.65 102
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CHOSEN 1792x2688		84.98 73	83.45 90	89.57 11	89.94 155	75.14 6	92.07 155	92.32 129	81.87 32	75.68 162	88.27 205	60.18 140	98.60 27	80.46 124	90.27 94	94.96 86

test_fmvsm_n_1920		87.69 26	88.50 19	85.27 113	87.05 231	63.55 210	93.69 87	91.08 194	84.18 13	90.17 24	97.04 8	67.58 56	97.99 39	95.72 5	90.03 95	94.26 118

ETV-MVS		86.01 53	86.11 50	85.70 99	90.21 150	67.02 118	93.43 103	91.92 150	81.21 45	84.13 73	94.07 101	60.93 134	95.63 163	89.28 43	89.81 96	94.46 114

QAPM		79.95 169	77.39 196	87.64 34	89.63 161	71.41 20	93.30 106	93.70 74	65.34 294	67.39 271	91.75 152	47.83 279	98.96 16	57.71 302	89.81 96	92.54 177

CANet_DTU		84.09 91	83.52 85	85.81 93	90.30 148	66.82 122	91.87 166	89.01 275	85.27 9	86.09 51	93.74 106	47.71 281	96.98 101	77.90 146	89.78 98	93.65 145

API-MVS		82.28 125	80.53 145	87.54 41	96.13 22	70.59 31	93.63 91	91.04 198	65.72 291	75.45 167	92.83 127	56.11 194	98.89 21	64.10 265	89.75 99	93.15 159

test2506		83.29 107	82.92 106	84.37 149	88.39 195	63.18 221	92.01 158	91.35 179	77.66 104	78.49 136	91.42 158	64.58 87	95.09 184	73.19 174	89.23 100	94.85 89

ECVR-MVS		81.29 142	80.38 148	84.01 162	88.39 195	61.96 248	92.56 139	86.79 321	77.66 104	76.63 154	91.42 158	46.34 290	95.24 181	74.36 170	89.23 100	94.85 89

MVS_Test		84.16 90	83.20 99	87.05 54	91.56 120	69.82 45	89.99 244	92.05 142	77.77 101	82.84 83	86.57 236	63.93 94	96.09 141	74.91 166	89.18 102	95.25 76

reproduce-ours		83.51 103	83.33 97	84.06 157	92.18 98	60.49 280	90.74 216	92.04 143	64.35 299	83.24 77	95.59 47	59.05 155	97.27 80	83.61 97	89.17 103	94.41 115

our_new_method		83.51 103	83.33 97	84.06 157	92.18 98	60.49 280	90.74 216	92.04 143	64.35 299	83.24 77	95.59 47	59.05 155	97.27 80	83.61 97	89.17 103	94.41 115

PAPR		85.15 70	84.47 75	87.18 49	96.02 25	68.29 81	91.85 168	93.00 107	76.59 122	79.03 127	95.00 68	61.59 127	97.61 58	78.16 144	89.00 105	95.63 53

TSAR-MVS + GP.		87.96 21	88.37 21	86.70 65	93.51 61	65.32 158	95.15 36	93.84 65	78.17 95	85.93 53	94.80 76	75.80 13	98.21 34	89.38 41	88.78 106	96.59 19

SR-MVS		82.81 116	82.58 112	83.50 178	93.35 63	61.16 264	92.23 147	91.28 184	64.48 298	81.27 96	95.28 57	53.71 222	95.86 151	82.87 104	88.77 107	93.49 149

test1111		80.84 151	80.02 150	83.33 181	87.87 211	60.76 272	92.62 132	86.86 320	77.86 100	75.73 161	91.39 160	46.35 289	94.70 199	72.79 180	88.68 108	94.52 110

fmvsm_l_conf0.5_n_a		87.44 30	88.15 24	85.30 111	87.10 229	64.19 190	94.41 52	88.14 304	80.24 59	92.54 5	96.97 10	69.52 46	97.17 85	95.89 3	88.51 109	94.56 105

reproduce_model		83.15 110	82.96 103	83.73 168	92.02 102	59.74 292	90.37 229	92.08 141	63.70 306	82.86 82	95.48 50	58.62 161	97.17 85	83.06 103	88.42 110	94.26 118

HPM-MVS_fast		80.25 162	79.55 161	82.33 204	91.55 121	59.95 289	91.32 193	89.16 265	65.23 295	74.71 174	93.07 119	47.81 280	95.74 156	74.87 168	88.23 111	91.31 207

PVSNet_Blended_VisFu		83.97 93	83.50 87	85.39 107	90.02 153	66.59 130	93.77 84	91.73 161	77.43 110	77.08 152	89.81 188	63.77 97	96.97 104	79.67 129	88.21 112	92.60 175

Vis-MVSNet (Re-imp)		79.24 180	79.57 158	78.24 294	88.46 191	52.29 349	90.41 227	89.12 269	74.24 149	69.13 240	91.91 149	65.77 72	90.09 326	59.00 298	88.09 113	92.33 182

fmvsm_l_conf0.5_n		87.49 28	88.19 23	85.39 107	86.95 232	64.37 183	94.30 55	88.45 295	80.51 51	92.70 4	96.86 15	69.98 44	97.15 89	95.83 4	88.08 114	94.65 102

APD-MVS_3200maxsize		81.64 137	81.32 127	82.59 198	92.36 91	58.74 306	91.39 186	91.01 199	63.35 310	79.72 118	94.62 81	51.82 237	96.14 138	79.71 128	87.93 115	92.89 170

RRT-MVS		82.61 121	81.16 128	86.96 57	91.10 133	68.75 70	87.70 285	92.20 136	76.97 113	72.68 193	87.10 230	51.30 246	96.41 129	83.56 99	87.84 116	95.74 50

Effi-MVS+		83.82 96	82.76 109	86.99 56	89.56 163	69.40 53	91.35 191	86.12 329	72.59 184	83.22 80	92.81 128	59.60 148	96.01 149	81.76 111	87.80 117	95.56 56

casdiffmvs_mvg		85.66 62	85.18 66	87.09 52	88.22 202	69.35 58	93.74 86	91.89 153	81.47 37	80.10 113	91.45 157	64.80 84	96.35 130	87.23 63	87.69 118	95.58 55
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
1314		80.70 153	78.95 171	85.94 88	87.77 216	67.56 102	87.91 280	92.55 125	72.17 199	67.44 268	93.09 117	50.27 254	97.04 95	71.68 195	87.64 119	93.23 156

test_fmvsmconf_n		86.58 44	87.17 34	84.82 126	85.28 262	62.55 235	94.26 57	89.78 239	83.81 17	87.78 36	96.33 29	65.33 76	96.98 101	94.40 11	87.55 120	94.95 87

PMMVS		81.98 132	82.04 119	81.78 221	89.76 159	56.17 330	91.13 203	90.69 203	77.96 97	80.09 114	93.57 111	46.33 291	94.99 187	81.41 115	87.46 121	94.17 123

casdiffmvs		85.37 66	84.87 72	86.84 59	88.25 200	69.07 62	93.04 114	91.76 160	81.27 44	80.84 104	92.07 145	64.23 90	96.06 145	84.98 83	87.43 122	95.39 61
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_fmvsmconf0.1_n		85.71 60	86.08 52	84.62 140	80.83 316	62.33 240	93.84 80	88.81 283	83.50 19	87.00 43	96.01 37	63.36 106	96.93 109	94.04 12	87.29 123	94.61 104

UGNet		79.87 170	78.68 173	83.45 180	89.96 154	61.51 257	92.13 150	90.79 201	76.83 117	78.85 133	86.33 240	38.16 329	96.17 137	67.93 228	87.17 124	92.67 173
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
MVS_111021_LR		82.02 131	81.52 125	83.51 177	88.42 193	62.88 230	89.77 247	88.93 279	76.78 118	75.55 166	93.10 116	50.31 253	95.38 176	83.82 96	87.02 125	92.26 189

test_fmvsmvis_n_1920		83.80 97	83.48 88	84.77 130	82.51 302	63.72 201	91.37 189	83.99 351	81.42 41	77.68 142	95.74 42	58.37 164	97.58 59	93.38 14	86.87 126	93.00 166

xiu_mvs_v1_base_debu		82.16 127	81.12 130	85.26 114	86.42 240	68.72 72	92.59 136	90.44 213	73.12 173	84.20 70	94.36 87	38.04 331	95.73 157	84.12 92	86.81 127	91.33 203

xiu_mvs_v1_base		82.16 127	81.12 130	85.26 114	86.42 240	68.72 72	92.59 136	90.44 213	73.12 173	84.20 70	94.36 87	38.04 331	95.73 157	84.12 92	86.81 127	91.33 203

xiu_mvs_v1_base_debi		82.16 127	81.12 130	85.26 114	86.42 240	68.72 72	92.59 136	90.44 213	73.12 173	84.20 70	94.36 87	38.04 331	95.73 157	84.12 92	86.81 127	91.33 203

SR-MVS-dyc-post		81.06 147	80.70 140	82.15 212	92.02 102	58.56 308	90.90 208	90.45 210	62.76 317	78.89 128	94.46 83	51.26 247	95.61 165	78.77 140	86.77 130	92.28 185

RE-MVS-def			80.48 146		92.02 102	58.56 308	90.90 208	90.45 210	62.76 317	78.89 128	94.46 83	49.30 264		78.77 140	86.77 130	92.28 185

baseline		85.01 72	84.44 76	86.71 64	88.33 197	68.73 71	90.24 235	91.82 159	81.05 47	81.18 98	92.50 131	63.69 98	96.08 144	84.45 89	86.71 132	95.32 68

TESTMET0.1,1		82.41 123	81.98 121	83.72 170	88.08 204	63.74 199	92.70 127	93.77 68	79.30 74	77.61 144	87.57 221	58.19 167	94.08 225	73.91 172	86.68 133	93.33 154

IS-MVSNet		80.14 164	79.41 163	82.33 204	87.91 209	60.08 288	91.97 162	88.27 301	72.90 180	71.44 217	91.73 153	61.44 128	93.66 245	62.47 279	86.53 134	93.24 155

CPTT-MVS		79.59 173	79.16 168	80.89 246	91.54 122	59.80 291	92.10 152	88.54 294	60.42 336	72.96 189	93.28 115	48.27 273	92.80 267	78.89 139	86.50 135	90.06 222

BH-w/o		80.49 157	79.30 166	84.05 160	90.83 140	64.36 185	93.60 92	89.42 254	74.35 147	69.09 241	90.15 183	55.23 203	95.61 165	64.61 262	86.43 136	92.17 191

PVSNet	73.49 8	80.05 166	78.63 174	84.31 151	90.92 137	64.97 168	92.47 140	91.05 197	79.18 77	72.43 202	90.51 172	37.05 343	94.06 227	68.06 225	86.00 137	93.90 139

test_fmvsmconf0.01_n		83.70 101	83.52 85	84.25 154	75.26 369	61.72 254	92.17 148	87.24 317	82.36 27	84.91 64	95.41 51	55.60 199	96.83 114	92.85 18	85.87 138	94.21 121

mvs_anonymous		81.36 141	79.99 152	85.46 104	90.39 147	68.40 78	86.88 297	90.61 208	74.41 145	70.31 229	84.67 256	63.79 96	92.32 288	73.13 175	85.70 139	95.67 51

DP-MVS Recon		82.73 117	81.65 124	85.98 86	97.31 4	67.06 115	95.15 36	91.99 147	69.08 263	76.50 157	93.89 104	54.48 213	98.20 35	70.76 201	85.66 140	92.69 172

BH-RMVSNet		79.46 178	77.65 188	84.89 123	91.68 117	65.66 149	93.55 94	88.09 306	72.93 177	73.37 186	91.12 164	46.20 293	96.12 139	56.28 307	85.61 141	92.91 168

UBG		86.83 39	86.70 42	87.20 48	93.07 73	69.81 46	93.43 103	95.56 12	81.52 36	81.50 93	92.12 143	73.58 25	96.28 132	84.37 90	85.20 142	95.51 58

diffmvs		84.28 84	83.83 81	85.61 101	87.40 222	68.02 91	90.88 210	89.24 260	80.54 50	81.64 92	92.52 130	59.83 145	94.52 209	87.32 61	85.11 143	94.29 117
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Fast-Effi-MVS+		81.14 144	80.01 151	84.51 144	90.24 149	65.86 146	94.12 62	89.15 266	73.81 160	75.37 168	88.26 206	57.26 174	94.53 208	66.97 239	84.92 144	93.15 159

LFMVS		84.34 83	82.73 110	89.18 13	94.76 33	73.25 11	94.99 42	91.89 153	71.90 205	82.16 89	93.49 113	47.98 277	97.05 92	82.55 107	84.82 145	97.25 8

BH-untuned		78.68 193	77.08 199	83.48 179	89.84 156	63.74 199	92.70 127	88.59 292	71.57 223	66.83 278	88.65 199	51.75 240	95.39 175	59.03 297	84.77 146	91.32 206

test-LLR		80.10 165	79.56 159	81.72 223	86.93 235	61.17 262	92.70 127	91.54 171	71.51 226	75.62 163	86.94 232	53.83 219	92.38 283	72.21 188	84.76 147	91.60 197

test-mter		79.96 168	79.38 165	81.72 223	86.93 235	61.17 262	92.70 127	91.54 171	73.85 158	75.62 163	86.94 232	49.84 259	92.38 283	72.21 188	84.76 147	91.60 197

sasdasda		86.85 37	86.25 47	88.66 20	91.80 113	71.92 16	93.54 95	91.71 163	80.26 56	87.55 37	95.25 61	63.59 102	96.93 109	88.18 50	84.34 149	97.11 9

canonicalmvs		86.85 37	86.25 47	88.66 20	91.80 113	71.92 16	93.54 95	91.71 163	80.26 56	87.55 37	95.25 61	63.59 102	96.93 109	88.18 50	84.34 149	97.11 9

alignmvs		87.28 32	86.97 37	88.24 27	91.30 129	71.14 26	95.61 25	93.56 79	79.30 74	87.07 42	95.25 61	68.43 48	96.93 109	87.87 53	84.33 151	96.65 17

VNet		86.20 49	85.65 60	87.84 30	93.92 47	69.99 38	95.73 23	95.94 7	78.43 92	86.00 52	93.07 119	58.22 166	97.00 97	85.22 78	84.33 151	96.52 23

UA-Net		80.02 167	79.65 157	81.11 237	89.33 169	57.72 315	86.33 301	89.00 278	77.44 109	81.01 101	89.15 195	59.33 152	95.90 150	61.01 286	84.28 153	89.73 229

LCM-MVSNet-Re		72.93 272	71.84 271	76.18 316	88.49 189	48.02 372	80.07 351	70.17 392	73.96 156	52.25 362	80.09 320	49.98 256	88.24 340	67.35 232	84.23 154	92.28 185

ACMMP		81.49 139	80.67 141	83.93 163	91.71 116	62.90 229	92.13 150	92.22 135	71.79 212	71.68 213	93.49 113	50.32 252	96.96 105	78.47 142	84.22 155	91.93 195
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
MGCFI-Net		85.59 64	85.73 59	85.17 117	91.41 127	62.44 236	92.87 120	91.31 180	79.65 67	86.99 44	95.14 67	62.90 115	96.12 139	87.13 64	84.13 156	96.96 13

114514_t		79.17 181	77.67 187	83.68 172	95.32 29	65.53 155	92.85 121	91.60 170	63.49 308	67.92 259	90.63 170	46.65 286	95.72 161	67.01 238	83.54 157	89.79 227

testing11		86.71 43	86.44 44	87.55 40	93.54 59	71.35 21	93.65 89	95.58 10	81.36 43	80.69 105	92.21 142	72.30 32	96.46 128	85.18 80	83.43 158	94.82 95

test_vis1_n_1920		81.66 136	82.01 120	80.64 248	82.24 304	55.09 338	94.76 46	86.87 319	81.67 35	84.40 69	94.63 80	38.17 328	94.67 200	91.98 27	83.34 159	92.16 192

testing222		85.18 69	84.69 74	86.63 67	92.91 77	69.91 42	92.61 133	95.80 9	80.31 55	80.38 110	92.27 139	68.73 47	95.19 182	75.94 155	83.27 160	94.81 96

EPMVS		78.49 198	75.98 215	86.02 85	91.21 131	69.68 51	80.23 348	91.20 185	75.25 137	72.48 200	78.11 335	54.65 209	93.69 244	57.66 303	83.04 161	94.69 98

AdaColmap		78.94 186	77.00 202	84.76 131	96.34 17	65.86 146	92.66 131	87.97 310	62.18 322	70.56 223	92.37 137	43.53 306	97.35 72	64.50 263	82.86 162	91.05 212

CDS-MVSNet		81.43 140	80.74 138	83.52 175	86.26 244	64.45 177	92.09 153	90.65 207	75.83 129	73.95 183	89.81 188	63.97 93	92.91 263	71.27 196	82.82 163	93.20 158
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CHOSEN 280x420		77.35 215	76.95 203	78.55 289	87.07 230	62.68 234	69.71 385	82.95 358	68.80 265	71.48 216	87.27 227	66.03 69	84.00 369	76.47 153	82.81 164	88.95 236

UWE-MVS		80.81 152	81.01 135	80.20 258	89.33 169	57.05 324	91.91 164	94.71 35	75.67 130	75.01 171	89.37 192	63.13 111	91.44 311	67.19 236	82.80 165	92.12 193

ETVMVS		84.22 88	83.71 82	85.76 96	92.58 89	68.25 85	92.45 141	95.53 14	79.54 69	79.46 121	91.64 155	70.29 42	94.18 221	69.16 216	82.76 166	94.84 92

PCF-MVS	73.15 9	79.29 179	77.63 189	84.29 152	86.06 248	65.96 144	87.03 293	91.10 191	69.86 252	69.79 237	90.64 168	57.54 173	96.59 119	64.37 264	82.29 167	90.32 219
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.5_n		86.39 46	86.91 38	84.82 126	87.36 224	63.54 211	94.74 47	90.02 233	82.52 25	90.14 25	96.92 13	62.93 114	97.84 46	95.28 8	82.26 168	93.07 163

WTY-MVS		86.32 47	85.81 56	87.85 29	92.82 81	69.37 57	95.20 34	95.25 17	82.71 23	81.91 90	94.73 77	67.93 54	97.63 56	79.55 130	82.25 169	96.54 22

testing99		86.01 53	85.47 61	87.63 38	93.62 55	71.25 23	93.47 101	95.23 18	80.42 54	80.60 107	91.95 147	71.73 37	96.50 126	80.02 127	82.22 170	95.13 79

HY-MVS	76.49 5	84.28 84	83.36 96	87.02 55	92.22 95	67.74 97	84.65 308	94.50 43	79.15 78	82.23 88	87.93 214	66.88 60	96.94 107	80.53 123	82.20 171	96.39 33

testing91		85.93 55	85.31 64	87.78 32	93.59 57	71.47 19	93.50 98	95.08 25	80.26 56	80.53 108	91.93 148	70.43 41	96.51 125	80.32 125	82.13 172	95.37 63

VDD-MVS		83.06 112	81.81 123	86.81 61	90.86 139	67.70 98	95.40 29	91.50 174	75.46 133	81.78 91	92.34 138	40.09 318	97.13 90	86.85 68	82.04 173	95.60 54

fmvsm_s_conf0.1_n		85.61 63	85.93 54	84.68 136	82.95 299	63.48 213	94.03 68	89.46 251	81.69 34	89.86 26	96.74 20	61.85 125	97.75 49	94.74 9	82.01 174	92.81 171

TAMVS		80.37 159	79.45 162	83.13 186	85.14 265	63.37 214	91.23 197	90.76 202	74.81 143	72.65 195	88.49 200	60.63 136	92.95 258	69.41 212	81.95 175	93.08 162

test_yl		84.28 84	83.16 100	87.64 34	94.52 37	69.24 59	95.78 18	95.09 23	69.19 260	81.09 99	92.88 125	57.00 179	97.44 66	81.11 120	81.76 176	96.23 38

DCV-MVSNet		84.28 84	83.16 100	87.64 34	94.52 37	69.24 59	95.78 18	95.09 23	69.19 260	81.09 99	92.88 125	57.00 179	97.44 66	81.11 120	81.76 176	96.23 38

FA-MVS(test-final)		79.12 182	77.23 198	84.81 129	90.54 143	63.98 194	81.35 339	91.71 163	71.09 234	74.85 173	82.94 274	52.85 230	97.05 92	67.97 226	81.73 178	93.41 150

thisisatest0515		83.41 105	82.49 114	86.16 83	89.46 166	68.26 83	93.54 95	94.70 36	74.31 148	75.75 160	90.92 165	72.62 29	96.52 124	69.64 208	81.50 179	93.71 143

baseline2		83.68 102	83.42 93	84.48 145	87.37 223	66.00 142	90.06 239	95.93 8	79.71 66	69.08 242	90.39 175	77.92 6	96.28 132	78.91 138	81.38 180	91.16 210

PatchmatchNet		77.46 213	74.63 231	85.96 87	89.55 164	70.35 34	79.97 353	89.55 249	72.23 196	70.94 219	76.91 347	57.03 177	92.79 268	54.27 314	81.17 181	94.74 97
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VDDNet		80.50 156	78.26 179	87.21 47	86.19 245	69.79 47	94.48 50	91.31 180	60.42 336	79.34 123	90.91 166	38.48 326	96.56 122	82.16 108	81.05 182	95.27 73

EPNet_dtu		78.80 190	79.26 167	77.43 302	88.06 205	49.71 364	91.96 163	91.95 149	77.67 103	76.56 156	91.28 162	58.51 162	90.20 324	56.37 306	80.95 183	92.39 180
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		82.71 119	82.38 116	83.73 168	89.25 172	59.58 295	92.24 146	94.89 28	77.96 97	79.86 116	92.38 136	56.70 185	97.05 92	77.26 149	80.86 184	94.55 106

FE-MVS		75.97 239	73.02 255	84.82 126	89.78 157	65.56 153	77.44 364	91.07 195	64.55 297	72.66 194	79.85 322	46.05 294	96.69 117	54.97 311	80.82 185	92.21 190

GeoE		78.90 187	77.43 192	83.29 182	88.95 181	62.02 246	92.31 143	86.23 327	70.24 247	71.34 218	89.27 193	54.43 214	94.04 230	63.31 271	80.81 186	93.81 142

fmvsm_s_conf0.5_n_a		85.75 59	86.09 51	84.72 133	85.73 256	63.58 208	93.79 83	89.32 257	81.42 41	90.21 23	96.91 14	62.41 119	97.67 51	94.48 10	80.56 187	92.90 169

TR-MVS		78.77 192	77.37 197	82.95 188	90.49 144	60.88 268	93.67 88	90.07 229	70.08 249	74.51 175	91.37 161	45.69 295	95.70 162	60.12 292	80.32 188	92.29 184

fmvsm_s_conf0.1_n_a		84.76 76	84.84 73	84.53 142	80.23 326	63.50 212	92.79 122	88.73 286	80.46 52	89.84 27	96.65 22	60.96 133	97.57 61	93.80 13	80.14 189	92.53 178

TAPA-MVS	70.22 12	74.94 254	73.53 250	79.17 283	90.40 146	52.07 350	89.19 260	89.61 248	62.69 319	70.07 231	92.67 129	48.89 271	94.32 213	38.26 378	79.97 190	91.12 211
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_cas_vis1_n_1920		80.45 158	80.61 143	79.97 267	78.25 352	57.01 326	94.04 67	88.33 298	79.06 83	82.81 84	93.70 107	38.65 323	91.63 303	90.82 36	79.81 191	91.27 209

cascas		78.18 202	75.77 218	85.41 106	87.14 228	69.11 61	92.96 117	91.15 189	66.71 283	70.47 224	86.07 242	37.49 337	96.48 127	70.15 206	79.80 192	90.65 215

HyFIR lowres test		81.03 148	79.56 159	85.43 105	87.81 214	68.11 89	90.18 236	90.01 234	70.65 243	72.95 190	86.06 243	63.61 101	94.50 210	75.01 164	79.75 193	93.67 144

WB-MVSnew		77.14 218	76.18 213	80.01 264	86.18 246	63.24 217	91.26 195	94.11 60	71.72 215	73.52 185	87.29 226	45.14 300	93.00 256	56.98 304	79.42 194	83.80 318

LS3D		69.17 302	66.40 307	77.50 300	91.92 109	56.12 331	85.12 305	80.37 366	46.96 386	56.50 348	87.51 222	37.25 338	93.71 243	32.52 395	79.40 195	82.68 338

EI-MVSNet-Vis-set		83.77 98	83.67 83	84.06 157	92.79 84	63.56 209	91.76 173	94.81 31	79.65 67	77.87 140	94.09 99	63.35 107	97.90 42	79.35 132	79.36 196	90.74 214

CVMVSNet		74.04 261	74.27 239	73.33 336	85.33 260	43.94 390	89.53 252	88.39 296	54.33 366	70.37 227	90.13 184	49.17 267	84.05 367	61.83 283	79.36 196	91.99 194

EPP-MVSNet		81.79 134	81.52 125	82.61 197	88.77 186	60.21 286	93.02 116	93.66 76	68.52 269	72.90 191	90.39 175	72.19 34	94.96 188	74.93 165	79.29 198	92.67 173

CLD-MVS		82.73 117	82.35 117	83.86 164	87.90 210	67.65 100	95.45 28	92.18 139	85.06 10	72.58 197	92.27 139	52.46 234	95.78 153	84.18 91	79.06 199	88.16 250
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP3-MVS								91.70 166							78.90 200

HQP-MVS		81.14 144	80.64 142	82.64 196	87.54 218	63.66 206	94.06 63	91.70 166	79.80 63	74.18 177	90.30 177	51.63 242	95.61 165	77.63 147	78.90 200	88.63 241

plane_prior						62.42 237	93.85 77		79.38 72						78.80 202

thres200		79.66 172	78.33 177	83.66 174	92.54 90	65.82 148	93.06 112	96.31 3	74.90 142	73.30 187	88.66 198	59.67 147	95.61 165	47.84 341	78.67 203	89.56 232

ET-MVSNet_ETH3D		84.01 92	83.15 102	86.58 70	90.78 141	70.89 28	94.74 47	94.62 40	81.44 40	58.19 337	93.64 109	73.64 24	92.35 286	82.66 105	78.66 204	96.50 27

HQP_MVS		80.34 160	79.75 156	82.12 214	86.94 233	62.42 237	93.13 110	91.31 180	78.81 87	72.53 198	89.14 196	50.66 250	95.55 170	76.74 150	78.53 205	88.39 247

plane_prior5								91.31 180					95.55 170	76.74 150	78.53 205	88.39 247

EI-MVSNet-UG-set		83.14 111	82.96 103	83.67 173	92.28 93	63.19 220	91.38 188	94.68 37	79.22 76	76.60 155	93.75 105	62.64 116	97.76 48	78.07 145	78.01 207	90.05 223

OMC-MVS		78.67 195	77.91 186	80.95 244	85.76 255	57.40 321	88.49 271	88.67 289	73.85 158	72.43 202	92.10 144	49.29 265	94.55 207	72.73 182	77.89 208	90.91 213

1112_ss		80.56 155	79.83 155	82.77 191	88.65 187	60.78 270	92.29 144	88.36 297	72.58 185	72.46 201	94.95 69	65.09 78	93.42 250	66.38 245	77.71 209	94.10 127

OPM-MVS		79.00 184	78.09 181	81.73 222	83.52 291	63.83 196	91.64 179	90.30 220	76.36 125	71.97 208	89.93 187	46.30 292	95.17 183	75.10 162	77.70 210	86.19 282
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		72.06 282	69.98 285	78.28 292	89.51 165	55.70 334	83.49 316	83.39 356	61.24 331	63.72 303	82.76 276	34.77 351	93.03 255	53.37 319	77.59 211	86.12 286

thres100view900		78.37 199	77.01 201	82.46 199	91.89 111	63.21 219	91.19 201	96.33 1	72.28 195	70.45 226	87.89 215	60.31 138	95.32 177	45.16 352	77.58 212	88.83 237

tfpn200view9		78.79 191	77.43 192	82.88 189	92.21 96	64.49 174	92.05 156	96.28 4	73.48 167	71.75 211	88.26 206	60.07 143	95.32 177	45.16 352	77.58 212	88.83 237

thres400		78.68 193	77.43 192	82.43 200	92.21 96	64.49 174	92.05 156	96.28 4	73.48 167	71.75 211	88.26 206	60.07 143	95.32 177	45.16 352	77.58 212	87.48 257

CostFormer		82.33 124	81.15 129	85.86 91	89.01 180	68.46 77	82.39 330	93.01 105	75.59 131	80.25 112	81.57 294	72.03 35	94.96 188	79.06 136	77.48 215	94.16 124

tpm2		79.80 171	77.95 185	85.34 110	88.28 198	68.26 83	81.56 336	91.42 177	70.11 248	77.59 145	80.50 312	67.40 57	94.26 219	67.34 233	77.35 216	93.51 148

Test_1112_low_res		79.56 174	78.60 175	82.43 200	88.24 201	60.39 283	92.09 153	87.99 308	72.10 201	71.84 209	87.42 223	64.62 86	93.04 254	65.80 252	77.30 217	93.85 141

tpmrst		80.57 154	79.14 169	84.84 125	90.10 152	68.28 82	81.70 334	89.72 246	77.63 106	75.96 159	79.54 326	64.94 81	92.71 270	75.43 159	77.28 218	93.55 147

Anonymous202405211		77.96 206	75.33 224	85.87 90	93.73 53	64.52 173	94.85 44	85.36 336	62.52 320	76.11 158	90.18 180	29.43 372	97.29 76	68.51 223	77.24 219	95.81 49

GA-MVS		78.33 201	76.23 211	84.65 137	83.65 289	66.30 136	91.44 181	90.14 227	76.01 127	70.32 228	84.02 264	42.50 310	94.72 196	70.98 198	77.00 220	92.94 167

thisisatest0530		81.15 143	80.07 149	84.39 148	88.26 199	65.63 151	91.40 184	94.62 40	71.27 230	70.93 220	89.18 194	72.47 30	96.04 146	65.62 254	76.89 221	91.49 199

thres600view7		78.00 204	76.66 206	82.03 219	91.93 108	63.69 204	91.30 194	96.33 1	72.43 190	70.46 225	87.89 215	60.31 138	94.92 191	42.64 364	76.64 222	87.48 257

PLC	68.80 14	75.23 250	73.68 249	79.86 270	92.93 76	58.68 307	90.64 221	88.30 299	60.90 333	64.43 297	90.53 171	42.38 311	94.57 203	56.52 305	76.54 223	86.33 278
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MIMVSNet		71.64 284	68.44 297	81.23 233	81.97 308	64.44 178	73.05 376	88.80 284	69.67 254	64.59 292	74.79 360	32.79 357	87.82 344	53.99 315	76.35 224	91.42 201

test_fmvs1		74.07 260	73.69 248	75.22 320	78.91 344	47.34 377	89.06 264	74.69 380	63.68 307	79.41 122	91.59 156	24.36 382	87.77 346	85.22 78	76.26 225	90.55 218

MVS-HIRNet		60.25 352	55.55 359	74.35 328	84.37 279	56.57 329	71.64 380	74.11 381	34.44 402	45.54 387	42.24 410	31.11 367	89.81 328	40.36 372	76.10 226	76.67 382

CNLPA		74.31 258	72.30 266	80.32 253	91.49 123	61.66 255	90.85 211	80.72 364	56.67 359	63.85 302	90.64 168	46.75 285	90.84 314	53.79 316	75.99 227	88.47 246

ab-mvs		80.18 163	78.31 178	85.80 94	88.44 192	65.49 157	83.00 327	92.67 118	71.82 211	77.36 147	85.01 252	54.50 210	96.59 119	76.35 154	75.63 228	95.32 68

test_fmvs1_n		72.69 279	71.92 270	74.99 323	71.15 382	47.08 379	87.34 291	75.67 375	63.48 309	78.08 139	91.17 163	20.16 394	87.87 343	84.65 87	75.57 229	90.01 224

FIs		79.47 177	79.41 163	79.67 274	85.95 250	59.40 297	91.68 177	93.94 63	78.06 96	68.96 246	88.28 204	66.61 63	91.77 299	66.20 248	74.99 230	87.82 253

SDMVSNet		80.26 161	78.88 172	84.40 147	89.25 172	67.63 101	85.35 304	93.02 104	76.77 119	70.84 221	87.12 228	47.95 278	96.09 141	85.04 81	74.55 231	89.48 233

sd_testset		77.08 220	75.37 222	82.20 210	89.25 172	62.11 245	82.06 331	89.09 271	76.77 119	70.84 221	87.12 228	41.43 314	95.01 186	67.23 235	74.55 231	89.48 233

CMPMVS	48.56 21	66.77 323	64.41 325	73.84 333	70.65 385	50.31 361	77.79 363	85.73 334	45.54 390	44.76 389	82.14 285	35.40 349	90.14 325	63.18 273	74.54 233	81.07 352
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dmvs_re		76.93 222	75.36 223	81.61 225	87.78 215	60.71 275	80.00 352	87.99 308	79.42 71	69.02 244	89.47 191	46.77 284	94.32 213	63.38 270	74.45 234	89.81 226

test_vis1_n		71.63 285	70.73 281	74.31 330	69.63 388	47.29 378	86.91 295	72.11 386	63.21 313	75.18 169	90.17 181	20.40 392	85.76 358	84.59 88	74.42 235	89.87 225

XVG-OURS		74.25 259	72.46 265	79.63 275	78.45 350	57.59 318	80.33 346	87.39 313	63.86 304	68.76 250	89.62 190	40.50 317	91.72 300	69.00 218	74.25 236	89.58 230

tpm cat1		75.30 249	72.21 267	84.58 141	88.52 188	67.77 96	78.16 362	88.02 307	61.88 328	68.45 255	76.37 351	60.65 135	94.03 232	53.77 317	74.11 237	91.93 195

XVG-OURS-SEG-HR		74.70 256	73.08 254	79.57 277	78.25 352	57.33 322	80.49 344	87.32 314	63.22 312	68.76 250	90.12 186	44.89 302	91.59 304	70.55 204	74.09 238	89.79 227

FC-MVSNet-test		77.99 205	78.08 182	77.70 297	84.89 270	55.51 335	90.27 233	93.75 72	76.87 114	66.80 279	87.59 220	65.71 73	90.23 323	62.89 276	73.94 239	87.37 260

PVSNet_BlendedMVS		83.38 106	83.43 91	83.22 184	93.76 50	67.53 104	94.06 63	93.61 77	79.13 79	81.00 102	85.14 251	63.19 109	97.29 76	87.08 65	73.91 240	84.83 310

tttt0517		79.50 175	78.53 176	82.41 203	87.22 226	61.43 260	89.75 248	94.76 32	69.29 258	67.91 260	88.06 213	72.92 27	95.63 163	62.91 275	73.90 241	90.16 221

MDTV_nov1_ep13			72.61 262		89.06 178	68.48 76	80.33 346	90.11 228	71.84 210	71.81 210	75.92 355	53.01 229	93.92 237	48.04 338	73.38 242

SCA		75.82 242	72.76 258	85.01 121	86.63 237	70.08 37	81.06 341	89.19 263	71.60 222	70.01 232	77.09 345	45.53 296	90.25 319	60.43 289	73.27 243	94.68 99

CR-MVSNet		73.79 265	70.82 280	82.70 194	83.15 295	67.96 92	70.25 382	84.00 349	73.67 165	69.97 234	72.41 367	57.82 170	89.48 331	52.99 320	73.13 244	90.64 216

RPMNet		70.42 292	65.68 313	84.63 139	83.15 295	67.96 92	70.25 382	90.45 210	46.83 388	69.97 234	65.10 388	56.48 191	95.30 180	35.79 383	73.13 244	90.64 216

Fast-Effi-MVS+-dtu		75.04 252	73.37 252	80.07 261	80.86 315	59.52 296	91.20 200	85.38 335	71.90 205	65.20 287	84.84 254	41.46 313	92.97 257	66.50 244	72.96 246	87.73 254

LPG-MVS_test		75.82 242	74.58 233	79.56 278	84.31 280	59.37 298	90.44 225	89.73 244	69.49 255	64.86 289	88.42 201	38.65 323	94.30 215	72.56 184	72.76 247	85.01 308

LGP-MVS_train				79.56 278	84.31 280	59.37 298		89.73 244	69.49 255	64.86 289	88.42 201	38.65 323	94.30 215	72.56 184	72.76 247	85.01 308

EG-PatchMatch MVS		68.55 308	65.41 316	77.96 296	78.69 347	62.93 226	89.86 246	89.17 264	60.55 335	50.27 371	77.73 339	22.60 388	94.06 227	47.18 344	72.65 249	76.88 381

EI-MVSNet		78.97 185	78.22 180	81.25 232	85.33 260	62.73 233	89.53 252	93.21 94	72.39 192	72.14 205	90.13 184	60.99 131	94.72 196	67.73 230	72.49 250	86.29 279

MVSTER		82.47 122	82.05 118	83.74 166	92.68 86	69.01 64	91.90 165	93.21 94	79.83 62	72.14 205	85.71 247	74.72 16	94.72 196	75.72 157	72.49 250	87.50 256

Anonymous20240529		76.84 225	74.15 241	84.88 124	91.02 134	64.95 169	93.84 80	91.09 192	53.57 367	73.00 188	87.42 223	35.91 347	97.32 74	69.14 217	72.41 252	92.36 181

D2MVS		73.80 264	72.02 269	79.15 285	79.15 339	62.97 224	88.58 270	90.07 229	72.94 176	59.22 331	78.30 332	42.31 312	92.70 272	65.59 255	72.00 253	81.79 346

PS-MVSNAJss		77.26 216	76.31 210	80.13 260	80.64 320	59.16 302	90.63 223	91.06 196	72.80 181	68.58 253	84.57 258	53.55 223	93.96 235	72.97 176	71.96 254	87.27 264

Effi-MVS+-dtu		76.14 232	75.28 225	78.72 288	83.22 294	55.17 337	89.87 245	87.78 311	75.42 134	67.98 258	81.43 296	45.08 301	92.52 279	75.08 163	71.63 255	88.48 245

ACMMP++_ref															71.63 255

ACMM	69.62 13	74.34 257	72.73 260	79.17 283	84.25 282	57.87 313	90.36 230	89.93 235	63.17 314	65.64 284	86.04 244	37.79 335	94.10 223	65.89 250	71.52 257	85.55 300
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	71.68 10	75.58 247	74.23 240	79.62 276	84.97 269	59.64 293	90.80 213	89.07 273	70.39 245	62.95 311	87.30 225	38.28 327	93.87 240	72.89 177	71.45 258	85.36 304
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
dp		75.01 253	72.09 268	83.76 165	89.28 171	66.22 139	79.96 354	89.75 241	71.16 231	67.80 264	77.19 344	51.81 238	92.54 278	50.39 325	71.44 259	92.51 179

tpm		78.58 196	77.03 200	83.22 184	85.94 252	64.56 172	83.21 323	91.14 190	78.31 93	73.67 184	79.68 324	64.01 92	92.09 293	66.07 249	71.26 260	93.03 164

DP-MVS		69.90 297	66.48 305	80.14 259	95.36 28	62.93 226	89.56 249	76.11 373	50.27 378	57.69 344	85.23 250	39.68 319	95.73 157	33.35 388	71.05 261	81.78 347

UniMVSNet_ETH3D		72.74 276	70.53 283	79.36 280	78.62 349	56.64 328	85.01 306	89.20 262	63.77 305	64.84 291	84.44 260	34.05 354	91.86 297	63.94 266	70.89 262	89.57 231

jajsoiax		73.05 270	71.51 275	77.67 298	77.46 359	54.83 339	88.81 266	90.04 232	69.13 262	62.85 313	83.51 269	31.16 366	92.75 269	70.83 199	69.80 263	85.43 303

ACMMP++															69.72 264

mvs_tets		72.71 277	71.11 276	77.52 299	77.41 360	54.52 341	88.45 272	89.76 240	68.76 267	62.70 314	83.26 272	29.49 371	92.71 270	70.51 205	69.62 265	85.34 305

tpmvs		72.88 274	69.76 290	82.22 209	90.98 135	67.05 116	78.22 361	88.30 299	63.10 315	64.35 298	74.98 358	55.09 206	94.27 217	43.25 358	69.57 266	85.34 305

GBi-Net		75.65 244	73.83 246	81.10 238	88.85 182	65.11 164	90.01 241	90.32 216	70.84 238	67.04 274	80.25 317	48.03 274	91.54 306	59.80 294	69.34 267	86.64 272

test1		75.65 244	73.83 246	81.10 238	88.85 182	65.11 164	90.01 241	90.32 216	70.84 238	67.04 274	80.25 317	48.03 274	91.54 306	59.80 294	69.34 267	86.64 272

FMVSNet3		77.73 210	76.04 214	82.80 190	91.20 132	68.99 65	91.87 166	91.99 147	73.35 169	67.04 274	83.19 273	56.62 187	92.14 290	59.80 294	69.34 267	87.28 263

Syy-MVS		69.65 299	69.52 291	70.03 356	87.87 211	43.21 392	88.07 276	89.01 275	72.91 178	63.11 308	88.10 210	45.28 299	85.54 359	22.07 406	69.23 270	81.32 349

myMVS_eth3d		72.58 281	72.74 259	72.10 348	87.87 211	49.45 366	88.07 276	89.01 275	72.91 178	63.11 308	88.10 210	63.63 99	85.54 359	32.73 393	69.23 270	81.32 349

MSDG		69.54 300	65.73 312	80.96 243	85.11 267	63.71 202	84.19 311	83.28 357	56.95 356	54.50 353	84.03 263	31.50 363	96.03 147	42.87 362	69.13 272	83.14 330

JIA-IIPM		66.06 326	62.45 336	76.88 311	81.42 313	54.45 342	57.49 406	88.67 289	49.36 380	63.86 301	46.86 404	56.06 195	90.25 319	49.53 330	68.83 273	85.95 290

OpenMVS_ROB	61.12 18	66.39 324	62.92 333	76.80 312	76.51 363	57.77 314	89.22 258	83.41 355	55.48 363	53.86 357	77.84 337	26.28 381	93.95 236	34.90 385	68.76 274	78.68 373

FMVSNet2		76.07 233	74.01 244	82.26 208	88.85 182	67.66 99	91.33 192	91.61 169	70.84 238	65.98 282	82.25 283	48.03 274	92.00 295	58.46 299	68.73 275	87.10 266

test_djsdf		73.76 266	72.56 263	77.39 303	77.00 362	53.93 343	89.07 262	90.69 203	65.80 289	63.92 300	82.03 286	43.14 309	92.67 273	72.83 178	68.53 276	85.57 299

F-COLMAP		70.66 289	68.44 297	77.32 304	86.37 243	55.91 332	88.00 278	86.32 324	56.94 357	57.28 346	88.07 212	33.58 355	92.49 280	51.02 323	68.37 277	83.55 320

XVG-ACMP-BASELINE		68.04 314	65.53 315	75.56 318	74.06 374	52.37 348	78.43 358	85.88 331	62.03 325	58.91 335	81.21 304	20.38 393	91.15 313	60.69 288	68.18 278	83.16 329

WBMVS		81.67 135	80.98 136	83.72 170	93.07 73	69.40 53	94.33 54	93.05 103	76.84 116	72.05 207	84.14 262	74.49 18	93.88 239	72.76 181	68.09 279	87.88 252

LTVRE_ROB	59.60 19	66.27 325	63.54 329	74.45 327	84.00 285	51.55 353	67.08 394	83.53 353	58.78 346	54.94 352	80.31 315	34.54 352	93.23 252	40.64 371	68.03 280	78.58 374
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
XXY-MVS		77.94 207	76.44 208	82.43 200	82.60 301	64.44 178	92.01 158	91.83 158	73.59 166	70.00 233	85.82 245	54.43 214	94.76 193	69.63 209	68.02 281	88.10 251

ADS-MVSNet2		66.90 322	63.44 330	77.26 306	88.06 205	60.70 276	68.01 390	75.56 377	57.57 350	64.48 294	69.87 377	38.68 321	84.10 366	40.87 369	67.89 282	86.97 267

ADS-MVSNet		68.54 309	64.38 326	81.03 242	88.06 205	66.90 121	68.01 390	84.02 348	57.57 350	64.48 294	69.87 377	38.68 321	89.21 333	40.87 369	67.89 282	86.97 267

test0.0.03 1		72.76 275	72.71 261	72.88 340	80.25 325	47.99 373	91.22 198	89.45 252	71.51 226	62.51 316	87.66 218	53.83 219	85.06 363	50.16 327	67.84 284	85.58 298

anonymousdsp		71.14 288	69.37 292	76.45 313	72.95 377	54.71 340	84.19 311	88.88 280	61.92 327	62.15 317	79.77 323	38.14 330	91.44 311	68.90 220	67.45 285	83.21 328

tt0805		73.07 269	70.73 281	80.07 261	78.37 351	57.05 324	87.78 283	92.18 139	61.23 332	67.04 274	86.49 237	31.35 365	94.58 201	65.06 260	67.12 286	88.57 243

VPA-MVSNet		79.03 183	78.00 183	82.11 217	85.95 250	64.48 176	93.22 109	94.66 38	75.05 140	74.04 182	84.95 253	52.17 236	93.52 247	74.90 167	67.04 287	88.32 249

nrg030		80.93 149	79.86 154	84.13 156	83.69 288	68.83 68	93.23 108	91.20 185	75.55 132	75.06 170	88.22 209	63.04 113	94.74 195	81.88 110	66.88 288	88.82 239

FMVSNet1		72.71 277	69.91 288	81.10 238	83.60 290	65.11 164	90.01 241	90.32 216	63.92 303	63.56 304	80.25 317	36.35 346	91.54 306	54.46 313	66.75 289	86.64 272

PatchT		69.11 303	65.37 317	80.32 253	82.07 307	63.68 205	67.96 392	87.62 312	50.86 376	69.37 238	65.18 387	57.09 176	88.53 337	41.59 367	66.60 290	88.74 240

IB-MVS	77.80 4	82.18 126	80.46 147	87.35 45	89.14 177	70.28 35	95.59 26	95.17 21	78.85 85	70.19 230	85.82 245	70.66 40	97.67 51	72.19 190	66.52 291	94.09 128
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
test_fmvs2		65.78 329	64.84 318	68.60 362	66.54 394	41.71 394	83.27 320	69.81 393	54.38 365	67.91 260	84.54 259	15.35 399	81.22 386	75.65 158	66.16 292	82.88 331

pmmvs5		73.35 267	71.52 274	78.86 287	78.64 348	60.61 279	91.08 204	86.90 318	67.69 273	63.32 306	83.64 267	44.33 304	90.53 316	62.04 281	66.02 293	85.46 302

dmvs_testset		65.55 330	66.45 306	62.86 374	79.87 329	22.35 420	76.55 366	71.74 388	77.42 111	55.85 349	87.77 217	51.39 244	80.69 387	31.51 399	65.92 294	85.55 300

MonoMVSNet		76.99 221	75.08 227	82.73 192	83.32 293	63.24 217	86.47 300	86.37 323	79.08 81	66.31 281	79.30 328	49.80 260	91.72 300	79.37 131	65.70 295	93.23 156

pmmvs4		73.92 263	71.81 272	80.25 257	79.17 338	65.24 160	87.43 289	87.26 316	67.64 276	63.46 305	83.91 266	48.96 270	91.53 309	62.94 274	65.49 296	83.96 315

cl22		77.94 207	76.78 204	81.42 229	87.57 217	64.93 170	90.67 219	88.86 282	72.45 189	67.63 266	82.68 278	64.07 91	92.91 263	71.79 191	65.30 297	86.44 277

miper_ehance_all_eth		77.60 211	76.44 208	81.09 241	85.70 257	64.41 181	90.65 220	88.64 291	72.31 193	67.37 272	82.52 279	64.77 85	92.64 276	70.67 202	65.30 297	86.24 281

miper_enhance_ethall		78.86 188	77.97 184	81.54 227	88.00 208	65.17 162	91.41 182	89.15 266	75.19 138	68.79 249	83.98 265	67.17 58	92.82 265	72.73 182	65.30 297	86.62 276

v1144		76.73 228	74.88 228	82.27 206	80.23 326	66.60 129	91.68 177	90.21 226	73.69 163	69.06 243	81.89 287	52.73 232	94.40 212	69.21 215	65.23 300	85.80 294

DSMNet-mixed		56.78 358	54.44 362	63.79 372	63.21 399	29.44 415	64.43 397	64.10 402	42.12 399	51.32 367	71.60 372	31.76 362	75.04 394	36.23 380	65.20 301	86.87 270

v1192		75.98 238	73.92 245	82.15 212	79.73 330	66.24 138	91.22 198	89.75 241	72.67 183	68.49 254	81.42 297	49.86 258	94.27 217	67.08 237	65.02 302	85.95 290

v2v482		77.42 214	75.65 220	82.73 192	80.38 322	67.13 114	91.85 168	90.23 224	75.09 139	69.37 238	83.39 271	53.79 221	94.44 211	71.77 192	65.00 303	86.63 275

V42		76.46 230	74.55 234	82.19 211	79.14 340	67.82 95	90.26 234	89.42 254	73.75 161	68.63 252	81.89 287	51.31 245	94.09 224	71.69 194	64.84 304	84.66 311

ACMH	63.93 17	68.62 307	64.81 319	80.03 263	85.22 263	63.25 216	87.72 284	84.66 342	60.83 334	51.57 366	79.43 327	27.29 378	94.96 188	41.76 365	64.84 304	81.88 345
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline1		81.84 133	81.03 134	84.28 153	91.60 118	66.62 128	91.08 204	91.66 168	81.87 32	74.86 172	91.67 154	69.98 44	94.92 191	71.76 193	64.75 306	91.29 208

v1240		75.21 251	72.98 256	81.88 220	79.20 337	66.00 142	90.75 215	89.11 270	71.63 221	67.41 270	81.22 302	47.36 282	93.87 240	65.46 257	64.72 307	85.77 295

IterMVS-LS		76.49 229	75.18 226	80.43 252	84.49 276	62.74 232	90.64 221	88.80 284	72.40 191	65.16 288	81.72 290	60.98 132	92.27 289	67.74 229	64.65 308	86.29 279
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		75.63 246	73.49 251	82.06 218	79.38 335	66.35 134	91.07 206	89.48 250	71.98 202	67.99 257	81.22 302	49.16 268	93.90 238	66.56 241	64.56 309	85.92 292

mamv4		65.18 332	67.43 302	58.44 378	77.88 358	49.36 369	69.40 386	70.99 391	48.31 384	57.78 343	85.53 248	59.01 158	51.88 416	73.67 173	64.32 310	74.07 386

v144192		76.05 236	74.03 243	82.12 214	79.50 334	66.55 131	91.39 186	89.71 247	72.30 194	68.17 256	81.33 299	51.75 240	94.03 232	67.94 227	64.19 311	85.77 295

Anonymous20231211		73.08 268	70.39 284	81.13 236	90.62 142	63.33 215	91.40 184	90.06 231	51.84 372	64.46 296	80.67 310	36.49 345	94.07 226	63.83 267	64.17 312	85.98 289

testing3		70.38 293	70.83 278	69.03 360	85.82 254	43.93 391	90.72 218	90.56 209	68.06 271	60.24 325	86.82 234	64.83 83	84.12 365	26.33 401	64.10 313	79.04 370

Patchmatch-test		65.86 327	60.94 342	80.62 250	83.75 287	58.83 305	58.91 405	75.26 379	44.50 393	50.95 370	77.09 345	58.81 160	87.90 342	35.13 384	64.03 314	95.12 80

USDC		67.43 321	64.51 323	76.19 315	77.94 356	55.29 336	78.38 359	85.00 339	73.17 171	48.36 379	80.37 314	21.23 390	92.48 281	52.15 321	64.02 315	80.81 355

VPNet		78.82 189	77.53 191	82.70 194	84.52 275	66.44 132	93.93 72	92.23 132	80.46 52	72.60 196	88.38 203	49.18 266	93.13 253	72.47 186	63.97 316	88.55 244

Anonymous20231206		67.53 319	65.78 311	72.79 341	74.95 370	47.59 375	88.23 274	87.32 314	61.75 330	58.07 339	77.29 342	37.79 335	87.29 352	42.91 360	63.71 317	83.48 323

WR-MVS		76.76 227	75.74 219	79.82 271	84.60 273	62.27 243	92.60 134	92.51 126	76.06 126	67.87 263	85.34 249	56.76 183	90.24 322	62.20 280	63.69 318	86.94 269

h-mvs33		83.01 113	82.56 113	84.35 150	89.34 167	62.02 246	92.72 125	93.76 69	81.45 38	82.73 85	92.25 141	60.11 141	97.13 90	87.69 55	62.96 319	93.91 137

c3_l		76.83 226	75.47 221	80.93 245	85.02 268	64.18 191	90.39 228	88.11 305	71.66 216	66.65 280	81.64 292	63.58 104	92.56 277	69.31 214	62.86 320	86.04 287

test_vis1_rt		59.09 356	57.31 355	64.43 371	68.44 391	46.02 385	83.05 326	48.63 415	51.96 371	49.57 374	63.86 391	16.30 397	80.20 388	71.21 197	62.79 321	67.07 398

mvsany_test1		68.77 306	68.56 295	69.39 358	73.57 375	45.88 386	80.93 342	60.88 406	59.65 342	71.56 214	90.26 179	43.22 308	75.05 393	74.26 171	62.70 322	87.25 265

UniMVSNet_NR-MVSNet		78.15 203	77.55 190	79.98 265	84.46 277	60.26 284	92.25 145	93.20 96	77.50 108	68.88 247	86.61 235	66.10 68	92.13 291	66.38 245	62.55 323	87.54 255

DU-MVS		76.86 223	75.84 217	79.91 268	82.96 297	60.26 284	91.26 195	91.54 171	76.46 124	68.88 247	86.35 238	56.16 192	92.13 291	66.38 245	62.55 323	87.35 261

UniMVSNet (Re)		77.58 212	76.78 204	79.98 265	84.11 283	60.80 269	91.76 173	93.17 98	76.56 123	69.93 236	84.78 255	63.32 108	92.36 285	64.89 261	62.51 325	86.78 271

v8		75.35 248	73.26 253	81.61 225	80.67 319	66.82 122	89.54 251	89.27 259	71.65 217	63.30 307	80.30 316	54.99 207	94.06 227	67.33 234	62.33 326	83.94 316

cl____		76.07 233	74.67 229	80.28 255	85.15 264	61.76 252	90.12 237	88.73 286	71.16 231	65.43 285	81.57 294	61.15 129	92.95 258	66.54 242	62.17 327	86.13 285

v10		74.77 255	72.54 264	81.46 228	80.33 324	66.71 126	89.15 261	89.08 272	70.94 236	63.08 310	79.86 321	52.52 233	94.04 230	65.70 253	62.17 327	83.64 319

DIV-MVS_self_test		76.07 233	74.67 229	80.28 255	85.14 265	61.75 253	90.12 237	88.73 286	71.16 231	65.42 286	81.60 293	61.15 129	92.94 262	66.54 242	62.16 329	86.14 283

IterMVS-SCA-FT		71.55 286	69.97 286	76.32 314	81.48 311	60.67 277	87.64 287	85.99 330	66.17 287	59.50 329	78.88 329	45.53 296	83.65 371	62.58 278	61.93 330	84.63 313

IterMVS		72.65 280	70.83 278	78.09 295	82.17 305	62.96 225	87.64 287	86.28 325	71.56 224	60.44 324	78.85 330	45.42 298	86.66 354	63.30 272	61.83 331	84.65 312
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet5		68.04 314	65.66 314	75.18 322	84.43 278	57.89 312	83.54 315	86.26 326	61.83 329	53.64 358	73.30 363	37.15 341	85.08 362	48.99 333	61.77 332	82.56 340

v7n		71.31 287	68.65 294	79.28 281	76.40 364	60.77 271	86.71 298	89.45 252	64.17 302	58.77 336	78.24 333	44.59 303	93.54 246	57.76 301	61.75 333	83.52 322

v148		76.19 231	74.47 236	81.36 230	80.05 328	64.44 178	91.75 175	90.23 224	73.68 164	67.13 273	80.84 307	55.92 197	93.86 242	68.95 219	61.73 334	85.76 297

tfpnnormal		70.10 294	67.36 303	78.32 291	83.45 292	60.97 267	88.85 265	92.77 113	64.85 296	60.83 322	78.53 331	43.52 307	93.48 248	31.73 396	61.70 335	80.52 358

ACMH+	65.35 16	67.65 317	64.55 322	76.96 310	84.59 274	57.10 323	88.08 275	80.79 363	58.59 348	53.00 359	81.09 306	26.63 380	92.95 258	46.51 346	61.69 336	80.82 354

ITE_SJBPF				70.43 355	74.44 372	47.06 380		77.32 371	60.16 339	54.04 356	83.53 268	23.30 386	84.01 368	43.07 359	61.58 337	80.21 363

NR-MVSNet		76.05 236	74.59 232	80.44 251	82.96 297	62.18 244	90.83 212	91.73 161	77.12 112	60.96 321	86.35 238	59.28 153	91.80 298	60.74 287	61.34 338	87.35 261

test_0402		64.54 335	61.09 341	74.92 324	84.10 284	60.75 273	87.95 279	79.71 368	52.03 370	52.41 361	77.20 343	32.21 361	91.64 302	23.14 404	61.03 339	72.36 392

Baseline_NR-MVSNet		73.99 262	72.83 257	77.48 301	80.78 317	59.29 301	91.79 170	84.55 344	68.85 264	68.99 245	80.70 308	56.16 192	92.04 294	62.67 277	60.98 340	81.11 351

TranMVSNet+NR-MVSNet		75.86 241	74.52 235	79.89 269	82.44 303	60.64 278	91.37 189	91.37 178	76.63 121	67.65 265	86.21 241	52.37 235	91.55 305	61.84 282	60.81 341	87.48 257

testgi		64.48 336	62.87 334	69.31 359	71.24 380	40.62 397	85.49 303	79.92 367	65.36 293	54.18 355	83.49 270	23.74 385	84.55 364	41.60 366	60.79 342	82.77 333

eth_miper_zixun_eth		75.96 240	74.40 237	80.66 247	84.66 272	63.02 223	89.28 257	88.27 301	71.88 207	65.73 283	81.65 291	59.45 149	92.81 266	68.13 224	60.53 343	86.14 283

COLMAP_ROB	57.96 20	62.98 343	59.65 346	72.98 339	81.44 312	53.00 347	83.75 314	75.53 378	48.34 383	48.81 378	81.40 298	24.14 383	90.30 318	32.95 390	60.52 344	75.65 384
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AUN-MVS		78.37 199	77.43 192	81.17 234	86.60 238	57.45 320	89.46 254	91.16 187	74.11 151	74.40 176	90.49 173	55.52 200	94.57 203	74.73 169	60.43 345	91.48 200

hse-mvs2		81.12 146	81.11 133	81.16 235	86.52 239	57.48 319	89.40 255	91.16 187	81.45 38	82.73 85	90.49 173	60.11 141	94.58 201	87.69 55	60.41 346	91.41 202

RPSCF		64.24 337	61.98 339	71.01 354	76.10 366	45.00 387	75.83 371	75.94 374	46.94 387	58.96 334	84.59 257	31.40 364	82.00 383	47.76 342	60.33 347	86.04 287

miper_lstm_enhance		73.05 270	71.73 273	77.03 307	83.80 286	58.32 310	81.76 332	88.88 280	69.80 253	61.01 320	78.23 334	57.19 175	87.51 350	65.34 258	59.53 348	85.27 307

CP-MVSNet		70.50 291	69.91 288	72.26 345	80.71 318	51.00 358	87.23 292	90.30 220	67.84 272	59.64 328	82.69 277	50.23 255	82.30 381	51.28 322	59.28 349	83.46 324

PS-CasMVS		69.86 298	69.13 293	72.07 349	80.35 323	50.57 360	87.02 294	89.75 241	67.27 278	59.19 332	82.28 282	46.58 287	82.24 382	50.69 324	59.02 350	83.39 326

pm-mvs1		72.89 273	71.09 277	78.26 293	79.10 341	57.62 317	90.80 213	89.30 258	67.66 274	62.91 312	81.78 289	49.11 269	92.95 258	60.29 291	58.89 351	84.22 314

Anonymous20240521		62.09 344	59.08 348	71.10 353	67.19 392	48.72 371	83.91 313	85.23 337	50.38 377	47.84 380	71.22 376	20.74 391	85.51 361	46.47 347	58.75 352	79.06 369

WR-MVS_H		70.59 290	69.94 287	72.53 342	81.03 314	51.43 354	87.35 290	92.03 146	67.38 277	60.23 326	80.70 308	55.84 198	83.45 373	46.33 348	58.58 353	82.72 335

reproduce_monomvs		79.49 176	79.11 170	80.64 248	92.91 77	61.47 259	91.17 202	93.28 92	83.09 20	64.04 299	82.38 281	66.19 66	94.57 203	81.19 119	57.71 354	85.88 293

PEN-MVS		69.46 301	68.56 295	72.17 347	79.27 336	49.71 364	86.90 296	89.24 260	67.24 281	59.08 333	82.51 280	47.23 283	83.54 372	48.42 336	57.12 355	83.25 327

EU-MVSNet		64.01 338	63.01 332	67.02 368	74.40 373	38.86 403	83.27 320	86.19 328	45.11 391	54.27 354	81.15 305	36.91 344	80.01 389	48.79 335	57.02 356	82.19 344

AllTest		61.66 345	58.06 350	72.46 343	79.57 331	51.42 355	80.17 349	68.61 395	51.25 374	45.88 383	81.23 300	19.86 395	86.58 355	38.98 375	57.01 357	79.39 366

TestCases				72.46 343	79.57 331	51.42 355		68.61 395	51.25 374	45.88 383	81.23 300	19.86 395	86.58 355	38.98 375	57.01 357	79.39 366

Patchmtry		67.53 319	63.93 327	78.34 290	82.12 306	64.38 182	68.72 387	84.00 349	48.23 385	59.24 330	72.41 367	57.82 170	89.27 332	46.10 349	56.68 359	81.36 348

our_test_3		68.29 312	64.69 321	79.11 286	78.92 342	64.85 171	88.40 273	85.06 338	60.32 338	52.68 360	76.12 353	40.81 316	89.80 330	44.25 357	55.65 360	82.67 339

FPMVS		45.64 370	43.10 374	53.23 387	51.42 412	36.46 405	64.97 396	71.91 387	29.13 407	27.53 407	61.55 396	9.83 409	65.01 410	16.00 413	55.58 361	58.22 403

DTE-MVSNet		68.46 310	67.33 304	71.87 351	77.94 356	49.00 370	86.16 302	88.58 293	66.36 286	58.19 337	82.21 284	46.36 288	83.87 370	44.97 355	55.17 362	82.73 334

MIMVSNet1		60.16 353	57.33 354	68.67 361	69.71 387	44.13 389	78.92 356	84.21 345	55.05 364	44.63 390	71.85 371	23.91 384	81.54 385	32.63 394	55.03 363	80.35 359

pmmvs6		67.57 318	64.76 320	76.00 317	72.82 379	53.37 345	88.71 267	86.78 322	53.19 368	57.58 345	78.03 336	35.33 350	92.41 282	55.56 309	54.88 364	82.21 343

TinyColmap		60.32 351	56.42 358	72.00 350	78.78 345	53.18 346	78.36 360	75.64 376	52.30 369	41.59 397	75.82 356	14.76 402	88.35 339	35.84 381	54.71 365	74.46 385

test20.03		63.83 339	62.65 335	67.38 367	70.58 386	39.94 399	86.57 299	84.17 346	63.29 311	51.86 364	77.30 341	37.09 342	82.47 379	38.87 377	54.13 366	79.73 364

OurMVSNet-221017-0		64.68 334	62.17 338	72.21 346	76.08 367	47.35 376	80.67 343	81.02 362	56.19 360	51.60 365	79.66 325	27.05 379	88.56 336	53.60 318	53.63 367	80.71 356

test_fmvs3		56.82 357	54.86 361	62.69 376	53.59 409	35.47 406	75.87 370	65.64 400	43.91 394	55.10 351	71.43 375	6.91 414	74.40 396	68.64 222	52.63 368	78.20 377

Patchmatch-RL test		68.17 313	64.49 324	79.19 282	71.22 381	53.93 343	70.07 384	71.54 390	69.22 259	56.79 347	62.89 392	56.58 188	88.61 334	69.53 211	52.61 369	95.03 85

ppachtmachnet_test		67.72 316	63.70 328	79.77 273	78.92 342	66.04 141	88.68 268	82.90 359	60.11 340	55.45 350	75.96 354	39.19 320	90.55 315	39.53 373	52.55 370	82.71 336

LF4IMVS		54.01 362	52.12 363	59.69 377	62.41 401	39.91 401	68.59 388	68.28 397	42.96 397	44.55 391	75.18 357	14.09 404	68.39 403	41.36 368	51.68 371	70.78 393

N_pmnet		50.55 365	49.11 367	54.88 384	77.17 361	4.02 428	84.36 309	2.00 426	48.59 381	45.86 385	68.82 380	32.22 360	82.80 378	31.58 397	51.38 372	77.81 379

pmmvs-eth3d		65.53 331	62.32 337	75.19 321	69.39 389	59.59 294	82.80 328	83.43 354	62.52 320	51.30 368	72.49 365	32.86 356	87.16 353	55.32 310	50.73 373	78.83 372

CL-MVSNet_self_test		69.92 296	68.09 300	75.41 319	73.25 376	55.90 333	90.05 240	89.90 236	69.96 250	61.96 319	76.54 348	51.05 248	87.64 347	49.51 331	50.59 374	82.70 337

PM-MVS		59.40 354	56.59 356	67.84 363	63.63 398	41.86 393	76.76 365	63.22 403	59.01 345	51.07 369	72.27 370	11.72 406	83.25 375	61.34 284	50.28 375	78.39 376

MDA-MVSNet_test_wron		63.78 340	60.16 344	74.64 325	78.15 354	60.41 282	83.49 316	84.03 347	56.17 362	39.17 399	71.59 373	37.22 339	83.24 376	42.87 362	48.73 376	80.26 361

YYNet1		63.76 341	60.14 345	74.62 326	78.06 355	60.19 287	83.46 318	83.99 351	56.18 361	39.25 398	71.56 374	37.18 340	83.34 374	42.90 361	48.70 377	80.32 360

KD-MVS_self_test		60.87 349	58.60 349	67.68 365	66.13 395	39.93 400	75.63 373	84.70 341	57.32 354	49.57 374	68.45 382	29.55 370	82.87 377	48.09 337	47.94 378	80.25 362

SixPastTwentyTwo		64.92 333	61.78 340	74.34 329	78.74 346	49.76 363	83.42 319	79.51 369	62.86 316	50.27 371	77.35 340	30.92 368	90.49 317	45.89 350	47.06 379	82.78 332

new_pmnet		49.31 366	46.44 369	57.93 379	62.84 400	40.74 396	68.47 389	62.96 404	36.48 401	35.09 402	57.81 399	14.97 401	72.18 398	32.86 392	46.44 380	60.88 401

EGC-MVSNET		42.35 372	38.09 375	55.11 383	74.57 371	46.62 382	71.63 381	55.77 407	0.04 421	0.24 422	62.70 393	14.24 403	74.91 395	17.59 410	46.06 381	43.80 407

TransMVSNet (Re)		70.07 295	67.66 301	77.31 305	80.62 321	59.13 303	91.78 172	84.94 340	65.97 288	60.08 327	80.44 313	50.78 249	91.87 296	48.84 334	45.46 382	80.94 353

ambc				69.61 357	61.38 404	41.35 395	49.07 411	85.86 333		50.18 373	66.40 385	10.16 408	88.14 341	45.73 351	44.20 383	79.32 368

TDRefinement		55.28 360	51.58 364	66.39 369	59.53 406	46.15 384	76.23 368	72.80 383	44.60 392	42.49 395	76.28 352	15.29 400	82.39 380	33.20 389	43.75 384	70.62 394

Gipuma		34.91 379	31.44 382	45.30 394	70.99 383	39.64 402	19.85 416	72.56 385	20.10 412	16.16 416	21.47 417	5.08 417	71.16 399	13.07 414	43.70 385	25.08 414
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		46.58 368	43.45 372	55.96 381	45.18 416	32.05 410	61.18 400	49.49 414	33.39 403	42.05 396	62.48 394	7.00 413	65.56 408	47.08 345	43.21 386	70.27 395

MDA-MVSNet-bldmvs		61.54 347	57.70 352	73.05 338	79.53 333	57.00 327	83.08 324	81.23 361	57.57 350	34.91 403	72.45 366	32.79 357	86.26 357	35.81 382	41.95 387	75.89 383

new-patchmatchnet		59.30 355	56.48 357	67.79 364	65.86 396	44.19 388	82.47 329	81.77 360	59.94 341	43.65 393	66.20 386	27.67 377	81.68 384	39.34 374	41.40 388	77.50 380

UnsupCasMVSNet_eth		65.79 328	63.10 331	73.88 332	70.71 384	50.29 362	81.09 340	89.88 237	72.58 185	49.25 376	74.77 361	32.57 359	87.43 351	55.96 308	41.04 389	83.90 317

test_vis3_rt		40.46 375	37.79 376	48.47 392	44.49 417	33.35 409	66.56 395	32.84 423	32.39 404	29.65 405	39.13 413	3.91 421	68.65 402	50.17 326	40.99 390	43.40 408

pmmvs3		55.51 359	51.50 365	67.53 366	57.90 407	50.93 359	80.37 345	73.66 382	40.63 400	44.15 392	64.75 389	16.30 397	78.97 390	44.77 356	40.98 391	72.69 390

APD_test1		40.50 374	37.31 377	50.09 390	51.88 410	35.27 407	59.45 404	52.59 411	21.64 410	26.12 408	57.80 400	4.56 418	66.56 406	22.64 405	39.09 392	48.43 406

mvs5depth		61.03 348	57.65 353	71.18 352	67.16 393	47.04 381	72.74 377	77.49 370	57.47 353	60.52 323	72.53 364	22.84 387	88.38 338	49.15 332	38.94 393	78.11 378

UnsupCasMVSNet_bld		61.60 346	57.71 351	73.29 337	68.73 390	51.64 352	78.61 357	89.05 274	57.20 355	46.11 382	61.96 395	28.70 374	88.60 335	50.08 328	38.90 394	79.63 365

PMVS	26.43 22	31.84 382	28.16 385	42.89 395	25.87 425	27.58 416	50.92 410	49.78 413	21.37 411	14.17 417	40.81 412	2.01 424	66.62 405	9.61 417	38.88 395	34.49 413
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
K. test v3		63.09 342	59.61 347	73.53 335	76.26 365	49.38 368	83.27 320	77.15 372	64.35 299	47.77 381	72.32 369	28.73 373	87.79 345	49.93 329	36.69 396	83.41 325

mmtdpeth		68.33 311	66.37 308	74.21 331	82.81 300	51.73 351	84.34 310	80.42 365	67.01 282	71.56 214	68.58 381	30.52 369	92.35 286	75.89 156	36.21 397	78.56 375

kuosan		60.86 350	60.24 343	62.71 375	81.57 310	46.43 383	75.70 372	85.88 331	57.98 349	48.95 377	69.53 379	58.42 163	76.53 391	28.25 400	35.87 398	65.15 399

KD-MVS_2432*1600		69.03 304	66.37 308	77.01 308	85.56 258	61.06 265	81.44 337	90.25 222	67.27 278	58.00 340	76.53 349	54.49 211	87.63 348	48.04 338	35.77 399	82.34 341

miper_refine_blended		69.03 304	66.37 308	77.01 308	85.56 258	61.06 265	81.44 337	90.25 222	67.27 278	58.00 340	76.53 349	54.49 211	87.63 348	48.04 338	35.77 399	82.34 341

mvsany_test3		48.86 367	46.35 370	56.41 380	46.00 415	31.67 411	62.26 399	47.25 416	43.71 395	45.54 387	68.15 383	10.84 407	64.44 412	57.95 300	35.44 401	73.13 389

LCM-MVSNet		40.54 373	35.79 378	54.76 385	36.92 422	30.81 412	51.41 409	69.02 394	22.07 409	24.63 409	45.37 406	4.56 418	65.81 407	33.67 387	34.50 402	67.67 396

test_method		38.59 377	35.16 380	48.89 391	54.33 408	21.35 421	45.32 412	53.71 410	7.41 418	28.74 406	51.62 402	8.70 411	52.87 415	33.73 386	32.89 403	72.47 391

lessismore_v0				73.72 334	72.93 378	47.83 374		61.72 405		45.86 385	73.76 362	28.63 375	89.81 328	47.75 343	31.37 404	83.53 321

testf1		32.77 380	29.47 383	42.67 396	41.89 419	30.81 412	52.07 407	43.45 417	15.45 413	18.52 413	44.82 407	2.12 422	58.38 413	16.05 411	30.87 405	38.83 409

APD_test2		32.77 380	29.47 383	42.67 396	41.89 419	30.81 412	52.07 407	43.45 417	15.45 413	18.52 413	44.82 407	2.12 422	58.38 413	16.05 411	30.87 405	38.83 409

ttmdpeth		53.34 363	49.96 366	63.45 373	62.07 403	40.04 398	72.06 378	65.64 400	42.54 398	51.88 363	77.79 338	13.94 405	76.48 392	32.93 391	30.82 407	73.84 387

PVSNet_0	68.08 15	71.81 283	68.32 299	82.27 206	84.68 271	62.31 242	88.68 268	90.31 219	75.84 128	57.93 342	80.65 311	37.85 334	94.19 220	69.94 207	29.05 408	90.31 220

dongtai		55.18 361	55.46 360	54.34 386	76.03 368	36.88 404	76.07 369	84.61 343	51.28 373	43.41 394	64.61 390	56.56 189	67.81 404	18.09 409	28.50 409	58.32 402

MVStest1		51.35 364	46.89 368	64.74 370	65.06 397	51.10 357	67.33 393	72.58 384	30.20 406	35.30 401	74.82 359	27.70 376	69.89 401	24.44 403	24.57 410	73.22 388

WB-MVS		46.23 369	44.94 371	50.11 389	62.13 402	21.23 422	76.48 367	55.49 408	45.89 389	35.78 400	61.44 397	35.54 348	72.83 397	9.96 416	21.75 411	56.27 404

SSC-MVS		44.51 371	43.35 373	47.99 393	61.01 405	18.90 424	74.12 375	54.36 409	43.42 396	34.10 404	60.02 398	34.42 353	70.39 400	9.14 418	19.57 412	54.68 405

DeepMVS_CX				34.71 399	51.45 411	24.73 419		28.48 425	31.46 405	17.49 415	52.75 401	5.80 416	42.60 420	18.18 408	19.42 413	36.81 412

PMMVS2		37.93 378	33.61 381	50.92 388	46.31 414	24.76 418	60.55 403	50.05 412	28.94 408	20.93 410	47.59 403	4.41 420	65.13 409	25.14 402	18.55 414	62.87 400

MVE	24.84 23	24.35 384	19.77 390	38.09 398	34.56 424	26.92 417	26.57 414	38.87 421	11.73 417	11.37 418	27.44 414	1.37 425	50.42 417	11.41 415	14.60 415	36.93 411
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		24.61 383	24.00 387	26.45 400	43.74 418	18.44 425	60.86 401	39.66 419	15.11 415	9.53 419	22.10 416	6.52 415	46.94 418	8.31 419	10.14 416	13.98 416

EMVS		23.76 385	23.20 389	25.46 401	41.52 421	16.90 426	60.56 402	38.79 422	14.62 416	8.99 420	20.24 419	7.35 412	45.82 419	7.25 420	9.46 417	13.64 417

tmp_tt		22.26 386	23.75 388	17.80 402	5.23 426	12.06 427	35.26 413	39.48 420	2.82 420	18.94 411	44.20 409	22.23 389	24.64 421	36.30 379	9.31 418	16.69 415

ANet_high		40.27 376	35.20 379	55.47 382	34.74 423	34.47 408	63.84 398	71.56 389	48.42 382	18.80 412	41.08 411	9.52 410	64.45 411	20.18 407	8.66 419	67.49 397

wuyk23d		11.30 388	10.95 391	12.33 403	48.05 413	19.89 423	25.89 415	1.92 427	3.58 419	3.12 421	1.37 421	0.64 426	15.77 422	6.23 421	7.77 420	1.35 418

testmvs		7.23 390	9.62 393	0.06 405	0.04 427	0.02 430	84.98 307	0.02 428	0.03 422	0.18 423	1.21 422	0.01 428	0.02 423	0.14 422	0.01 421	0.13 420

mmdepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 422	0.00 421

monomultidepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 422	0.00 421

test_blank		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 422	0.00 421

uanet_test		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 422	0.00 421

DCPMVS		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 422	0.00 421

cdsmvs_eth3d_5k		19.86 387	26.47 386	0.00 406	0.00 429	0.00 431	0.00 417	93.45 85	0.00 424	0.00 425	95.27 59	49.56 261	0.00 425	0.00 424	0.00 422	0.00 421

pcd_1.5k_mvsjas		4.46 392	5.95 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	53.55 223	0.00 425	0.00 424	0.00 422	0.00 421

sosnet-low-res		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 422	0.00 421

sosnet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 422	0.00 421

uncertanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 422	0.00 421

Regformer		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 422	0.00 421

test123		6.92 391	9.21 394	0.08 404	0.03 428	0.05 429	81.65 335	0.01 429	0.02 423	0.14 424	0.85 423	0.03 427	0.02 423	0.12 423	0.00 422	0.16 419

ab-mvs-re		7.91 389	10.55 392	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	94.95 69	0.00 429	0.00 425	0.00 424	0.00 422	0.00 421

uanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 422	0.00 421

WAC-MVS						49.45 366								31.56 398

FOURS1					93.95 46	61.77 251	93.96 70	91.92 150	62.14 324	86.57 46

test_one_0601					96.32 18	69.74 49		94.18 57	71.42 228	90.67 19	96.85 16	74.45 19

eth-test2					0.00 429

eth-test					0.00 429

test_241102_ONE					96.45 12	69.38 55		94.44 46	71.65 217	92.11 7	97.05 7	76.79 9	99.11 6

save fliter					93.84 49	67.89 94	95.05 39	92.66 119	78.19 94

test0726					96.40 15	69.99 38	96.76 8	94.33 54	71.92 203	91.89 11	97.11 6	73.77 22

GSMVS																94.68 99

test_part2					96.29 19	68.16 88				90.78 17

sam_mvs1												57.85 169				94.68 99

sam_mvs												54.91 208

MTGPA								92.23 132

test_post1							78.95 355				20.70 418	53.05 228	91.50 310	60.43 289

test_post											23.01 415	56.49 190	92.67 273

patchmatchnet-post											67.62 384	57.62 172	90.25 319

MTMP							93.77 84	32.52 424

gm-plane-assit					88.42 193	67.04 117			78.62 90		91.83 150		97.37 70	76.57 152

TEST9					94.18 41	67.28 109	94.16 59	93.51 81	71.75 214	85.52 57	95.33 54	68.01 52	97.27 80

test_8					94.19 40	67.19 111	94.15 61	93.42 88	71.87 208	85.38 60	95.35 53	68.19 50	96.95 106

agg_prior					94.16 43	66.97 119		93.31 91		84.49 68			96.75 116

test_prior4						67.18 113	93.92 73

test_prior				86.42 76	94.71 35	67.35 108		93.10 102					96.84 113			95.05 83

旧先验2							92.00 161		59.37 344	87.54 39			93.47 249	75.39 160

新几何2							91.41 182

无先验							92.71 126	92.61 123	62.03 325				97.01 96	66.63 240		93.97 134

原ACMM2							92.01 158

testdata2													96.09 141	61.26 285

segment_acmp												65.94 70

testdata1							89.21 259		77.55 107

plane_prior7					86.94 233	61.51 257

plane_prior6					87.23 225	62.32 241						50.66 250

plane_prior4											89.14 196

plane_prior3						61.95 249			79.09 80	72.53 198

plane_prior2							93.13 110		78.81 87

plane_prior1					87.15 227

n2								0.00 430

nn								0.00 430

door-mid								66.01 399

test11								93.01 105

door								66.57 398

HQP5-MVS						63.66 206

HQP-NCC					87.54 218		94.06 63		79.80 63	74.18 177

ACMP_Plane					87.54 218		94.06 63		79.80 63	74.18 177

BP-MVS														77.63 147

HQP4-MVS										74.18 177			95.61 165			88.63 241

HQP2-MVS												51.63 242

NP-MVS					87.41 221	63.04 222					90.30 177

MDTV_nov1_ep13_2view						59.90 290	80.13 350		67.65 275	72.79 192		54.33 216		59.83 293		92.58 176

Test By Simon												54.21 217

High-resolution multi-view benchmark