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.

SMA-MVS		80.28 6	80.39 7	79.95 3	86.60 23	61.95 19	86.33 13	85.75 21	62.49 60	82.20 15	92.28 1	56.53 33	89.70 15	79.85 3	91.48 1	88.19 16
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
DVP-MVS++		81.67 1	82.40 1	79.47 9	87.24 14	59.15 59	88.18 1	87.15 3	65.04 14	84.26 5	91.86 6	67.01 1	90.84 3	79.48 4	91.38 2	88.42 9

PC_three_1452									55.09 193	84.46 4	89.84 41	66.68 5	89.41 16	74.24 31	91.38 2	88.42 9

OPU-MVS				79.83 6	87.54 11	60.93 35	87.82 7				89.89 40	67.01 1	90.33 11	73.16 41	91.15 4	88.23 14

SED-MVS		81.56 2	82.30 2	79.32 12	87.77 4	58.90 68	87.82 7	86.78 10	64.18 30	85.97 1	91.84 8	66.87 3	90.83 5	78.63 15	90.87 5	88.23 14

IU-MVS					87.77 4	59.15 59		85.53 25	53.93 212	84.64 3				79.07 9	90.87 5	88.37 11

test_241102_TWO								86.73 12	64.18 30	84.26 5	91.84 8	65.19 6	90.83 5	78.63 15	90.70 7	87.65 33

MSC_two_6792asdad				79.95 3	87.24 14	61.04 31		85.62 23					90.96 1	79.31 7	90.65 8	87.85 25

No_MVS				79.95 3	87.24 14	61.04 31		85.62 23					90.96 1	79.31 7	90.65 8	87.85 25

test_0728_THIRD									65.04 14	83.82 8	92.00 3	64.69 10	90.75 8	79.48 4	90.63 10	88.09 19

DVP-MVS		80.84 4	81.64 3	78.42 32	87.75 7	59.07 63	87.85 5	85.03 34	64.26 27	83.82 8	92.00 3	64.82 8	90.75 8	78.66 13	90.61 11	85.45 108
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				79.19 15	87.82 3	59.11 62	87.85 5	87.15 3					90.84 3	78.66 13	90.61 11	87.62 35

ACMMP_NAP		78.77 14	78.78 13	78.74 28	85.44 45	61.04 31	83.84 47	85.16 30	62.88 51	78.10 24	91.26 13	52.51 67	88.39 28	79.34 6	90.52 13	86.78 60

HPM-MVS++		79.88 8	80.14 8	79.10 20	88.17 1	64.80 1	86.59 12	83.70 60	65.37 11	78.78 22	90.64 17	58.63 24	87.24 49	79.00 10	90.37 14	85.26 118

SF-MVS		78.82 12	79.22 11	77.60 42	82.88 74	57.83 79	84.99 30	88.13 2	61.86 73	79.16 20	90.75 16	57.96 25	87.09 58	77.08 21	90.18 15	87.87 24

CNVR-MVS		79.84 9	79.97 9	79.45 10	87.90 2	62.17 17	84.37 34	85.03 34	66.96 3	77.58 27	90.06 34	59.47 20	89.13 20	78.67 12	89.73 16	87.03 51

PHI-MVS		75.87 42	75.36 43	77.41 44	80.62 105	55.91 110	84.28 37	85.78 20	56.08 171	73.41 59	86.58 88	50.94 89	88.54 26	70.79 55	89.71 17	87.79 29

DPE-MVS		80.56 5	80.98 5	79.29 14	87.27 13	60.56 41	85.71 25	86.42 14	63.28 42	83.27 13	91.83 10	64.96 7	90.47 10	76.41 24	89.67 18	86.84 57
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS-pluss		78.35 18	78.46 16	78.03 38	84.96 52	59.52 52	82.93 57	85.39 26	62.15 65	76.41 31	91.51 11	52.47 69	86.78 65	80.66 2	89.64 19	87.80 28
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ZNCC-MVS		78.82 12	78.67 15	79.30 13	86.43 28	62.05 18	86.62 11	86.01 18	63.32 41	75.08 37	90.47 24	53.96 54	88.68 25	76.48 23	89.63 20	87.16 49

9.14			78.75 14		83.10 69		84.15 41	88.26 1	59.90 104	78.57 23	90.36 25	57.51 30	86.86 62	77.39 18	89.52 21

DeepC-MVS	69.38 2	78.56 16	78.14 20	79.83 6	83.60 63	61.62 23	84.17 40	86.85 6	63.23 44	73.84 55	90.25 30	57.68 27	89.96 13	74.62 30	89.03 22	87.89 22
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SteuartSystems-ACMMP		79.48 10	79.31 10	79.98 2	83.01 72	62.18 16	87.60 9	85.83 19	66.69 7	78.03 26	90.98 14	54.26 50	90.06 12	78.42 17	89.02 23	87.69 31
Skip Steuart: Steuart Systems R&D Blog.
test_prior2							81.75 78		60.37 94	75.01 38	89.06 50	56.22 36		72.19 46	88.96 24

DPM-MVS		75.47 46	75.00 47	76.88 49	81.38 91	59.16 58	79.94 100	85.71 22	56.59 161	72.46 76	86.76 79	56.89 31	87.86 41	66.36 84	88.91 25	83.64 170

DeepPCF-MVS	69.58 1	79.03 11	79.00 12	79.13 18	84.92 56	60.32 44	83.03 55	85.33 27	62.86 52	80.17 17	90.03 36	61.76 14	88.95 22	74.21 32	88.67 26	88.12 18

MSP-MVS		81.06 3	81.40 4	80.02 1	86.21 31	62.73 9	86.09 17	86.83 8	65.51 10	83.81 10	90.51 21	63.71 12	89.23 18	81.51 1	88.44 27	88.09 19
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
CDPH-MVS		76.31 36	75.67 42	78.22 35	85.35 48	59.14 61	81.31 85	84.02 48	56.32 165	74.05 51	88.98 52	53.34 62	87.92 39	69.23 63	88.42 28	87.59 36

GST-MVS		78.14 20	77.85 22	78.99 24	86.05 38	61.82 22	85.84 20	85.21 29	63.56 39	74.29 50	90.03 36	52.56 66	88.53 27	74.79 29	88.34 29	86.63 63

train_agg		76.27 37	76.15 35	76.64 53	85.58 43	61.59 24	81.62 80	81.26 113	55.86 173	74.93 39	88.81 54	53.70 58	84.68 116	75.24 28	88.33 30	83.65 169

APDe-MVS		80.16 7	80.59 6	78.86 27	86.64 21	60.02 45	88.12 3	86.42 14	62.94 49	82.40 14	92.12 2	59.64 18	89.76 14	78.70 11	88.32 31	86.79 59

test9_res														75.28 27	88.31 32	83.81 158

MTAPA		76.90 32	76.42 33	78.35 33	86.08 37	63.57 2	74.92 195	80.97 121	65.13 13	75.77 33	90.88 15	48.63 109	86.66 68	77.23 19	88.17 33	84.81 130

test12				77.76 41	84.52 58	58.41 74		83.36 71		72.93 69		54.61 48	88.05 35		88.12 34	86.81 58

MP-MVS		78.35 18	78.26 19	78.64 29	86.54 25	63.47 4	86.02 19	83.55 64	63.89 35	73.60 57	90.60 18	54.85 46	86.72 66	77.20 20	88.06 35	85.74 97
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DeepC-MVS_fast	68.24 3	77.25 28	76.63 31	79.12 19	86.15 34	60.86 36	84.71 31	84.85 38	61.98 72	73.06 67	88.88 53	53.72 57	89.06 21	68.27 65	88.04 36	87.42 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
原ACMM1				74.69 87	85.39 47	59.40 53		83.42 68	51.47 237	70.27 95	86.61 86	48.61 110	86.51 74	53.85 182	87.96 37	78.16 253

agg_prior2														73.09 42	87.93 38	84.33 140

CSCG		76.92 31	76.75 29	77.41 44	83.96 62	59.60 50	82.95 56	86.50 13	60.78 85	75.27 35	84.83 120	60.76 15	86.56 71	67.86 71	87.87 39	86.06 82

MCST-MVS		77.48 26	77.45 25	77.54 43	86.67 20	58.36 75	83.22 53	86.93 5	56.91 153	74.91 41	88.19 59	59.15 22	87.68 44	73.67 38	87.45 40	86.57 64

NCCC		78.58 15	78.31 17	79.39 11	87.51 12	62.61 13	85.20 29	84.42 42	66.73 6	74.67 46	89.38 47	55.30 41	89.18 19	74.19 33	87.34 41	86.38 66

HFP-MVS		78.01 22	77.65 23	79.10 20	86.71 19	62.81 8	86.29 14	84.32 44	62.82 53	73.96 53	90.50 22	53.20 63	88.35 29	74.02 35	87.05 42	86.13 80

region2R		77.67 25	77.18 27	79.15 17	86.76 17	62.95 6	86.29 14	84.16 47	62.81 55	73.30 60	90.58 19	49.90 94	88.21 32	73.78 37	87.03 43	86.29 77

ACMMPR		77.71 23	77.23 26	79.16 16	86.75 18	62.93 7	86.29 14	84.24 45	62.82 53	73.55 58	90.56 20	49.80 96	88.24 31	74.02 35	87.03 43	86.32 74

APD-MVS		78.02 21	78.04 21	77.98 39	86.44 27	60.81 38	85.52 26	84.36 43	60.61 87	79.05 21	90.30 28	55.54 40	88.32 30	73.48 40	87.03 43	84.83 129
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ZD-MVS					86.64 21	60.38 43		82.70 85	57.95 138	78.10 24	90.06 34	56.12 37	88.84 24	74.05 34	87.00 46

CS-MVS-test		75.62 45	75.31 45	76.56 55	80.63 104	55.13 123	83.88 46	85.22 28	62.05 69	71.49 86	86.03 100	53.83 56	86.36 79	67.74 72	86.91 47	88.19 16

PGM-MVS		76.77 33	76.06 36	78.88 26	86.14 35	62.73 9	82.55 65	83.74 59	61.71 74	72.45 78	90.34 27	48.48 112	88.13 33	72.32 45	86.85 48	85.78 91

HPM-MVS		77.28 27	76.85 28	78.54 30	85.00 51	60.81 38	82.91 58	85.08 31	62.57 58	73.09 66	89.97 39	50.90 90	87.48 47	75.30 26	86.85 48	87.33 47
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
TSAR-MVS + MP.		78.44 17	78.28 18	78.90 25	84.96 52	61.41 26	84.03 43	83.82 58	59.34 115	79.37 19	89.76 43	59.84 16	87.62 45	76.69 22	86.74 50	87.68 32
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
XVS		77.17 29	76.56 32	79.00 22	86.32 29	62.62 11	85.83 21	83.92 51	64.55 21	72.17 79	90.01 38	47.95 116	88.01 36	71.55 52	86.74 50	86.37 68

X-MVStestdata		70.21 110	67.28 157	79.00 22	86.32 29	62.62 11	85.83 21	83.92 51	64.55 21	72.17 79	6.49 374	47.95 116	88.01 36	71.55 52	86.74 50	86.37 68

3Dnovator+	66.72 4	75.84 43	74.57 51	79.66 8	82.40 76	59.92 47	85.83 21	86.32 16	66.92 5	67.80 144	89.24 49	42.03 183	89.38 17	64.07 103	86.50 53	89.69 2

EPNet		73.09 67	72.16 71	75.90 63	75.95 212	56.28 101	83.05 54	72.39 249	66.53 8	65.27 192	87.00 76	50.40 92	85.47 100	62.48 119	86.32 54	85.94 84
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DELS-MVS		74.76 50	74.46 52	75.65 70	77.84 171	52.25 165	75.59 179	84.17 46	63.76 36	73.15 63	82.79 161	59.58 19	86.80 64	67.24 78	86.04 55	87.89 22
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
CP-MVS		77.12 30	76.68 30	78.43 31	86.05 38	63.18 5	87.55 10	83.45 67	62.44 62	72.68 72	90.50 22	48.18 114	87.34 48	73.59 39	85.71 56	84.76 133

mPP-MVS		76.54 34	75.93 38	78.34 34	86.47 26	63.50 3	85.74 24	82.28 89	62.90 50	71.77 82	90.26 29	46.61 139	86.55 72	71.71 50	85.66 57	84.97 126

DROMVSNet		75.84 43	75.87 40	75.74 67	78.86 140	52.65 155	83.73 48	86.08 17	63.47 40	72.77 71	87.25 75	53.13 64	87.93 38	71.97 48	85.57 58	86.66 62

MSLP-MVS++		73.77 62	73.47 62	74.66 89	83.02 71	59.29 57	82.30 72	81.88 94	59.34 115	71.59 85	86.83 77	45.94 143	83.65 135	65.09 97	85.22 59	81.06 219

SD-MVS		77.70 24	77.62 24	77.93 40	84.47 59	61.88 21	84.55 32	83.87 56	60.37 94	79.89 18	89.38 47	54.97 44	85.58 95	76.12 25	84.94 60	86.33 72
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
3Dnovator	64.47 5	72.49 74	71.39 81	75.79 64	77.70 174	58.99 67	80.66 92	83.15 78	62.24 64	65.46 188	86.59 87	42.38 181	85.52 96	59.59 144	84.72 61	82.85 188

CS-MVS		76.25 38	75.98 37	77.06 48	80.15 114	55.63 115	84.51 33	83.90 53	63.24 43	73.30 60	87.27 74	55.06 43	86.30 81	71.78 49	84.58 62	89.25 4

CANet		76.46 35	75.93 38	78.06 37	81.29 92	57.53 83	82.35 67	83.31 73	67.78 1	70.09 96	86.34 93	54.92 45	88.90 23	72.68 44	84.55 63	87.76 30

LFMVS		71.78 85	71.59 76	72.32 152	83.40 67	46.38 240	79.75 105	71.08 256	64.18 30	72.80 70	88.64 57	42.58 178	83.72 133	57.41 153	84.49 64	86.86 56

TSAR-MVS + GP.		74.90 48	74.15 55	77.17 47	82.00 80	58.77 71	81.80 77	78.57 159	58.58 126	74.32 49	84.51 130	55.94 38	87.22 50	67.11 79	84.48 65	85.52 104

test2506		65.33 207	64.61 200	67.50 228	79.46 125	34.19 342	74.43 205	51.92 345	58.72 122	66.75 163	88.05 63	25.99 325	80.92 196	51.94 197	84.25 66	87.39 42

ECVR-MVS		67.72 166	67.51 147	68.35 222	79.46 125	36.29 332	74.79 198	66.93 285	58.72 122	67.19 154	88.05 63	36.10 242	81.38 183	52.07 195	84.25 66	87.39 42

MAR-MVS		71.51 89	70.15 101	75.60 72	81.84 83	59.39 54	81.38 84	82.90 82	54.90 201	68.08 135	78.70 242	47.73 118	85.51 97	51.68 202	84.17 68	81.88 204
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
API-MVS		72.17 80	71.41 80	74.45 98	81.95 82	57.22 87	84.03 43	80.38 130	59.89 107	68.40 126	82.33 173	49.64 97	87.83 42	51.87 198	84.16 69	78.30 251

casdiffmvs_mvg		76.14 39	76.30 34	75.66 69	76.46 206	51.83 173	79.67 107	85.08 31	65.02 17	75.84 32	88.58 58	59.42 21	85.08 106	72.75 43	83.93 70	90.08 1
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test1111		67.21 173	67.14 164	67.42 230	79.24 131	34.76 337	73.89 216	65.65 292	58.71 124	66.96 158	87.95 65	36.09 243	80.53 203	52.03 196	83.79 71	86.97 52

IS-MVSNet		71.57 88	71.00 89	73.27 133	78.86 140	45.63 251	80.22 95	78.69 156	64.14 33	66.46 168	87.36 71	49.30 100	85.60 93	50.26 211	83.71 72	88.59 7

UA-Net		73.13 66	72.93 66	73.76 112	83.58 64	51.66 174	78.75 116	77.66 181	67.75 2	72.61 74	89.42 45	49.82 95	83.29 141	53.61 184	83.14 73	86.32 74

MG-MVS		73.96 60	73.89 58	74.16 103	85.65 42	49.69 204	81.59 82	81.29 112	61.45 76	71.05 88	88.11 60	51.77 78	87.73 43	61.05 132	83.09 74	85.05 123

OpenMVS	61.03 9	68.85 140	67.56 143	72.70 144	74.26 242	53.99 133	81.21 86	81.34 110	52.70 223	62.75 226	85.55 112	38.86 214	84.14 124	48.41 227	83.01 75	79.97 235

SR-MVS		76.13 40	75.70 41	77.40 46	85.87 40	61.20 29	85.52 26	82.19 90	59.99 103	75.10 36	90.35 26	47.66 120	86.52 73	71.64 51	82.99 76	84.47 139

VDDNet		71.81 84	71.33 83	73.26 134	82.80 75	47.60 231	78.74 117	75.27 213	59.59 112	72.94 68	89.40 46	41.51 193	83.91 130	58.75 148	82.99 76	88.26 12

MVS_111021_HR		74.02 59	73.46 63	75.69 68	83.01 72	60.63 40	77.29 147	78.40 170	61.18 80	70.58 91	85.97 102	54.18 52	84.00 129	67.52 76	82.98 78	82.45 194

ETV-MVS		74.46 56	73.84 59	76.33 58	79.27 130	55.24 122	79.22 113	85.00 36	64.97 19	72.65 73	79.46 233	53.65 61	87.87 40	67.45 77	82.91 79	85.89 88

HPM-MVS_fast		74.30 58	73.46 63	76.80 50	84.45 60	59.04 65	83.65 50	81.05 118	60.15 100	70.43 92	89.84 41	41.09 198	85.59 94	67.61 75	82.90 80	85.77 94

ACMMP		76.02 41	75.33 44	78.07 36	85.20 49	61.91 20	85.49 28	84.44 41	63.04 47	69.80 106	89.74 44	45.43 152	87.16 53	72.01 47	82.87 81	85.14 119
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
APD-MVS_3200maxsize		74.96 47	74.39 53	76.67 52	82.20 78	58.24 76	83.67 49	83.29 74	58.41 129	73.71 56	90.14 31	45.62 145	85.99 85	69.64 59	82.85 82	85.78 91

casdiffmvs		74.80 49	74.89 49	74.53 96	75.59 218	50.37 191	78.17 126	85.06 33	62.80 56	74.40 48	87.86 66	57.88 26	83.61 136	69.46 62	82.79 83	89.59 3
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		74.61 53	74.70 50	74.34 100	75.70 214	49.99 199	77.54 139	84.63 40	62.73 57	73.98 52	87.79 68	57.67 28	83.82 132	69.49 60	82.74 84	89.20 5

VDD-MVS		72.50 73	72.09 72	73.75 114	81.58 85	49.69 204	77.76 134	77.63 182	63.21 45	73.21 62	89.02 51	42.14 182	83.32 140	61.72 126	82.50 85	88.25 13

CLD-MVS		73.33 64	72.68 68	75.29 78	78.82 142	53.33 145	78.23 125	84.79 39	61.30 79	70.41 93	81.04 201	52.41 70	87.12 56	64.61 102	82.49 86	85.41 112
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
canonicalmvs		74.67 52	74.98 48	73.71 116	78.94 139	50.56 189	80.23 94	83.87 56	60.30 98	77.15 28	86.56 89	59.65 17	82.00 172	66.01 88	82.12 87	88.58 8

MVS		67.37 171	66.33 177	70.51 188	75.46 220	50.94 179	73.95 212	81.85 95	41.57 324	62.54 231	78.57 247	47.98 115	85.47 100	52.97 189	82.05 88	75.14 284

patch_mono-2		69.85 117	71.09 87	66.16 245	79.11 136	54.80 128	71.97 243	74.31 230	53.50 217	70.90 89	84.17 134	57.63 29	63.31 316	66.17 85	82.02 89	80.38 229

dcpmvs_2		74.55 55	75.23 46	72.48 147	82.34 77	53.34 144	77.87 130	81.46 102	57.80 142	75.49 34	86.81 78	62.22 13	77.75 246	71.09 54	82.02 89	86.34 70

alignmvs		73.86 61	73.99 56	73.45 127	78.20 159	50.50 190	78.57 121	82.43 87	59.40 113	76.57 29	86.71 83	56.42 35	81.23 188	65.84 90	81.79 91	88.62 6

SR-MVS-dyc-post		74.57 54	73.90 57	76.58 54	83.49 65	59.87 48	84.29 35	81.36 106	58.07 135	73.14 64	90.07 32	44.74 159	85.84 89	68.20 66	81.76 92	84.03 149

RE-MVS-def			73.71 61		83.49 65	59.87 48	84.29 35	81.36 106	58.07 135	73.14 64	90.07 32	43.06 174		68.20 66	81.76 92	84.03 149

新几何1				70.76 182	85.66 41	61.13 30		66.43 288	44.68 300	70.29 94	86.64 84	41.29 195	75.23 266	49.72 215	81.75 94	75.93 277

Vis-MVSNet		72.18 79	71.37 82	74.61 92	81.29 92	55.41 120	80.90 88	78.28 172	60.73 86	69.23 117	88.09 61	44.36 164	82.65 160	57.68 151	81.75 94	85.77 94
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
VNet		69.68 124	70.19 100	68.16 224	79.73 120	41.63 287	70.53 262	77.38 187	60.37 94	70.69 90	86.63 85	51.08 86	77.09 254	53.61 184	81.69 96	85.75 96

OPM-MVS		74.73 51	74.25 54	76.19 59	80.81 100	59.01 66	82.60 64	83.64 61	63.74 37	72.52 75	87.49 69	47.18 130	85.88 88	69.47 61	80.78 97	83.66 168
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
旧先验1					83.04 70	53.15 148		67.52 279			87.85 67	44.08 165			80.76 98	78.03 258

PAPM_NR		72.63 72	71.80 74	75.13 81	81.72 84	53.42 143	79.91 102	83.28 75	59.14 117	66.31 172	85.90 105	51.86 77	86.06 82	57.45 152	80.62 99	85.91 86

Vis-MVSNet (Re-imp)		63.69 222	63.88 205	63.14 273	74.75 231	31.04 355	71.16 254	63.64 305	56.32 165	59.80 258	84.99 118	44.51 161	75.46 265	39.12 296	80.62 99	82.92 185

HQP_MVS		74.31 57	73.73 60	76.06 60	81.41 89	56.31 99	84.22 38	84.01 49	64.52 23	69.27 114	86.10 97	45.26 156	87.21 51	68.16 68	80.58 101	84.65 134

plane_prior5								84.01 49					87.21 51	68.16 68	80.58 101	84.65 134

UGNet		68.81 141	67.39 152	73.06 136	78.33 156	54.47 130	79.77 104	75.40 212	60.45 90	63.22 220	84.40 131	32.71 278	80.91 197	51.71 201	80.56 103	83.81 158
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
plane_prior						56.31 99	83.58 51		63.19 46						80.48 104

HQP3-MVS								83.90 53							80.35 105

HQP-MVS		73.45 63	72.80 67	75.40 74	80.66 101	54.94 124	82.31 69	83.90 53	62.10 66	67.85 139	85.54 113	45.46 150	86.93 60	67.04 80	80.35 105	84.32 141

PCF-MVS	61.88 8	70.95 97	69.49 111	75.35 75	77.63 177	55.71 112	76.04 174	81.81 96	50.30 250	69.66 107	85.40 116	52.51 67	84.89 112	51.82 199	80.24 107	85.45 108
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DP-MVS Recon		72.15 82	70.73 92	76.40 56	86.57 24	57.99 78	81.15 87	82.96 80	57.03 150	66.78 161	85.56 111	44.50 162	88.11 34	51.77 200	80.23 108	83.10 183

CPTT-MVS		72.78 69	72.08 73	74.87 84	84.88 57	61.41 26	84.15 41	77.86 177	55.27 188	67.51 150	88.08 62	41.93 185	81.85 174	69.04 64	80.01 109	81.35 212

114514_t		70.83 98	69.56 108	74.64 91	86.21 31	54.63 129	82.34 68	81.81 96	48.22 268	63.01 223	85.83 107	40.92 199	87.10 57	57.91 150	79.79 110	82.18 197

test_yl		69.69 122	69.13 116	71.36 169	78.37 154	45.74 247	74.71 199	80.20 132	57.91 140	70.01 101	83.83 143	42.44 179	82.87 152	54.97 171	79.72 111	85.48 106

DCV-MVSNet		69.69 122	69.13 116	71.36 169	78.37 154	45.74 247	74.71 199	80.20 132	57.91 140	70.01 101	83.83 143	42.44 179	82.87 152	54.97 171	79.72 111	85.48 106

MVS_Test		72.45 75	72.46 70	72.42 151	74.88 226	48.50 219	76.28 167	83.14 79	59.40 113	72.46 76	84.68 122	55.66 39	81.12 189	65.98 89	79.66 113	87.63 34

PS-MVSNAJ		70.51 104	69.70 107	72.93 138	81.52 86	55.79 111	74.92 195	79.00 148	55.04 198	69.88 104	78.66 243	47.05 132	82.19 169	61.61 127	79.58 114	80.83 222

PVSNet_Blended		68.59 146	67.72 139	71.19 174	77.03 194	50.57 187	72.51 235	81.52 99	51.91 230	64.22 213	77.77 259	49.13 104	82.87 152	55.82 162	79.58 114	80.14 233

EPP-MVSNet		72.16 81	71.31 84	74.71 86	78.68 146	49.70 202	82.10 74	81.65 98	60.40 91	65.94 177	85.84 106	51.74 79	86.37 78	55.93 161	79.55 116	88.07 21

xiu_mvs_v2_base		70.52 103	69.75 105	72.84 140	81.21 95	55.63 115	75.11 189	78.92 150	54.92 200	69.96 103	79.68 228	47.00 136	82.09 171	61.60 128	79.37 117	80.81 223

MVSFormer		71.50 90	70.38 98	74.88 83	78.76 143	57.15 92	82.79 59	78.48 163	51.26 241	69.49 109	83.22 155	43.99 167	83.24 142	66.06 86	79.37 117	84.23 144

lupinMVS		69.57 127	68.28 133	73.44 128	78.76 143	57.15 92	76.57 161	73.29 243	46.19 289	69.49 109	82.18 176	43.99 167	79.23 221	64.66 100	79.37 117	83.93 152

PAPM		67.92 162	66.69 167	71.63 162	78.09 163	49.02 212	77.09 151	81.24 115	51.04 244	60.91 247	83.98 140	47.71 119	84.99 107	40.81 287	79.32 120	80.90 221

FIs		70.82 99	71.43 79	68.98 214	78.33 156	38.14 309	76.96 154	83.59 63	61.02 81	67.33 152	86.73 81	55.07 42	81.64 177	54.61 177	79.22 121	87.14 50

jason		69.65 125	68.39 132	73.43 129	78.27 158	56.88 96	77.12 150	73.71 239	46.53 286	69.34 113	83.22 155	43.37 171	79.18 222	64.77 99	79.20 122	84.23 144
jason: jason.
PAPR		71.72 87	70.82 91	74.41 99	81.20 96	51.17 176	79.55 110	83.33 72	55.81 177	66.93 160	84.61 126	50.95 88	86.06 82	55.79 164	79.20 122	86.00 83

EIA-MVS		71.78 85	70.60 93	75.30 77	79.85 118	53.54 139	77.27 148	83.26 76	57.92 139	66.49 167	79.39 234	52.07 75	86.69 67	60.05 138	79.14 124	85.66 99

Effi-MVS+		73.31 65	72.54 69	75.62 71	77.87 170	53.64 136	79.62 109	79.61 139	61.63 75	72.02 81	82.61 166	56.44 34	85.97 86	63.99 106	79.07 125	87.25 48

gg-mvs-nofinetune		57.86 268	56.43 272	62.18 279	72.62 260	35.35 334	66.57 285	56.33 334	50.65 247	57.64 279	57.10 354	30.65 290	76.36 261	37.38 304	78.88 126	74.82 291

CDS-MVSNet		66.80 186	65.37 192	71.10 177	78.98 138	53.13 150	73.27 224	71.07 257	52.15 229	64.72 204	80.23 218	43.56 170	77.10 253	45.48 252	78.88 126	83.05 184
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
AdaColmap		69.99 114	68.66 125	73.97 106	84.94 54	57.83 79	82.63 63	78.71 155	56.28 167	64.34 208	84.14 135	41.57 190	87.06 59	46.45 240	78.88 126	77.02 268

Anonymous202405211		66.84 185	65.99 184	69.40 208	80.19 112	42.21 279	71.11 256	71.31 255	58.80 121	67.90 137	86.39 92	29.83 297	79.65 214	49.60 218	78.78 129	86.33 72

CANet_DTU		68.18 157	67.71 141	69.59 204	74.83 228	46.24 242	78.66 119	76.85 194	59.60 109	63.45 219	82.09 183	35.25 248	77.41 250	59.88 141	78.76 130	85.14 119

test222					83.14 68	58.68 72	72.57 234	63.45 306	41.78 320	67.56 149	86.12 96	37.13 235			78.73 131	74.98 288

TAMVS		66.78 187	65.27 195	71.33 172	79.16 135	53.67 135	73.84 218	69.59 267	52.32 228	65.28 191	81.72 189	44.49 163	77.40 251	42.32 278	78.66 132	82.92 185

PVSNet_Blended_VisFu		71.45 91	70.39 97	74.65 90	82.01 79	58.82 70	79.93 101	80.35 131	55.09 193	65.82 183	82.16 179	49.17 103	82.64 161	60.34 136	78.62 133	82.50 193

testdata				64.66 263	81.52 86	52.93 151		65.29 296	46.09 290	73.88 54	87.46 70	38.08 223	66.26 308	53.31 187	78.48 134	74.78 292

QAPM		70.05 112	68.81 122	73.78 110	76.54 204	53.43 142	83.23 52	83.48 65	52.89 222	65.90 179	86.29 94	41.55 192	86.49 75	51.01 205	78.40 135	81.42 208

FC-MVSNet-test		69.80 120	70.58 95	67.46 229	77.61 182	34.73 338	76.05 173	83.19 77	60.84 83	65.88 181	86.46 90	54.52 49	80.76 201	52.52 191	78.12 136	86.91 54

LCM-MVSNet-Re		61.88 242	61.35 236	63.46 269	74.58 234	31.48 354	61.42 314	58.14 327	58.71 124	53.02 319	79.55 231	43.07 173	76.80 257	45.69 247	77.96 137	82.11 200

diffmvs		70.69 101	70.43 96	71.46 164	69.45 302	48.95 214	72.93 227	78.46 165	57.27 147	71.69 83	83.97 141	51.48 81	77.92 243	70.70 56	77.95 138	87.53 38
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
OMC-MVS		71.40 92	70.60 93	73.78 110	76.60 202	53.15 148	79.74 106	79.78 135	58.37 130	68.75 121	86.45 91	45.43 152	80.60 202	62.58 117	77.73 139	87.58 37

iter_conf_final		69.82 118	68.02 136	75.23 79	79.38 127	52.91 152	80.11 97	73.96 236	54.99 199	68.04 136	83.59 148	29.05 302	87.16 53	65.41 95	77.62 140	85.63 101

MVS_111021_LR		69.50 129	68.78 123	71.65 161	78.38 153	59.33 55	74.82 197	70.11 263	58.08 134	67.83 143	84.68 122	41.96 184	76.34 262	65.62 93	77.54 141	79.30 245

Fast-Effi-MVS+		70.28 109	69.12 118	73.73 115	78.50 149	51.50 175	75.01 192	79.46 143	56.16 170	68.59 122	79.55 231	53.97 53	84.05 125	53.34 186	77.53 142	85.65 100

xiu_mvs_v1_base_debu		68.58 147	67.28 157	72.48 147	78.19 160	57.19 89	75.28 184	75.09 220	51.61 232	70.04 97	81.41 195	32.79 274	79.02 229	63.81 107	77.31 143	81.22 214

xiu_mvs_v1_base		68.58 147	67.28 157	72.48 147	78.19 160	57.19 89	75.28 184	75.09 220	51.61 232	70.04 97	81.41 195	32.79 274	79.02 229	63.81 107	77.31 143	81.22 214

xiu_mvs_v1_base_debi		68.58 147	67.28 157	72.48 147	78.19 160	57.19 89	75.28 184	75.09 220	51.61 232	70.04 97	81.41 195	32.79 274	79.02 229	63.81 107	77.31 143	81.22 214

LPG-MVS_test		72.74 70	71.74 75	75.76 65	80.22 109	57.51 84	82.55 65	83.40 69	61.32 77	66.67 165	87.33 72	39.15 211	86.59 69	67.70 73	77.30 146	83.19 180

LGP-MVS_train				75.76 65	80.22 109	57.51 84		83.40 69	61.32 77	66.67 165	87.33 72	39.15 211	86.59 69	67.70 73	77.30 146	83.19 180

Anonymous20240529		69.91 116	69.02 119	72.56 145	80.19 112	47.65 229	77.56 138	80.99 120	55.45 186	69.88 104	86.76 79	39.24 210	82.18 170	54.04 179	77.10 148	87.85 25

iter_conf05		69.40 133	67.62 142	74.73 85	77.84 171	51.13 177	79.28 112	73.71 239	54.62 203	68.17 131	83.59 148	28.68 307	87.16 53	65.74 92	76.95 149	85.91 86

EPNet_dtu		61.90 241	61.97 230	61.68 282	72.89 256	39.78 296	75.85 177	65.62 293	55.09 193	54.56 304	79.36 235	37.59 226	67.02 303	39.80 293	76.95 149	78.25 252
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TAPA-MVS	59.36 10	66.60 190	65.20 196	70.81 181	76.63 201	48.75 216	76.52 163	80.04 134	50.64 248	65.24 196	84.93 119	39.15 211	78.54 235	36.77 307	76.88 151	85.14 119
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	63.53 6	72.30 77	71.20 86	75.59 73	80.28 107	57.54 82	82.74 61	82.84 84	60.58 88	65.24 196	86.18 95	39.25 209	86.03 84	66.95 82	76.79 152	83.22 178
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
cascas		65.98 197	63.42 212	73.64 120	77.26 190	52.58 158	72.26 239	77.21 190	48.56 263	61.21 246	74.60 293	32.57 282	85.82 90	50.38 210	76.75 153	82.52 192

BH-untuned		68.27 154	67.29 156	71.21 173	79.74 119	53.22 147	76.06 172	77.46 186	57.19 148	66.10 174	81.61 191	45.37 154	83.50 138	45.42 254	76.68 154	76.91 272

ET-MVSNet_ETH3D		67.96 161	65.72 188	74.68 88	76.67 200	55.62 117	75.11 189	74.74 224	52.91 221	60.03 253	80.12 219	33.68 264	82.64 161	61.86 125	76.34 155	85.78 91

FA-MVS(test-final)		69.82 118	68.48 127	73.84 108	78.44 152	50.04 197	75.58 181	78.99 149	58.16 133	67.59 148	82.14 180	42.66 176	85.63 92	56.60 156	76.19 156	85.84 89

ACMM	61.98 7	70.80 100	69.73 106	74.02 104	80.59 106	58.59 73	82.68 62	82.02 93	55.46 185	67.18 155	84.39 132	38.51 216	83.17 144	60.65 134	76.10 157	80.30 230
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
BH-RMVSNet		68.81 141	67.42 151	72.97 137	80.11 115	52.53 160	74.26 206	76.29 200	58.48 128	68.38 127	84.20 133	42.59 177	83.83 131	46.53 239	75.91 158	82.56 189

GeoE		71.01 96	70.15 101	73.60 123	79.57 123	52.17 166	78.93 115	78.12 174	58.02 137	67.76 147	83.87 142	52.36 71	82.72 158	56.90 155	75.79 159	85.92 85

XVG-OURS		68.76 144	67.37 153	72.90 139	74.32 241	57.22 87	70.09 268	78.81 152	55.24 189	67.79 145	85.81 109	36.54 241	78.28 238	62.04 123	75.74 160	83.19 180

mvs_anonymous		68.03 159	67.51 147	69.59 204	72.08 268	44.57 260	71.99 242	75.23 215	51.67 231	67.06 156	82.57 167	54.68 47	77.94 242	56.56 157	75.71 161	86.26 78

BH-w/o		66.85 184	65.83 186	69.90 199	79.29 128	52.46 162	74.66 201	76.65 198	54.51 208	64.85 203	78.12 249	45.59 147	82.95 148	43.26 270	75.54 162	74.27 297

thisisatest0515		65.83 199	63.50 211	72.82 142	73.75 245	49.50 207	71.32 250	73.12 245	49.39 256	63.82 215	76.50 275	34.95 252	84.84 115	53.20 188	75.49 163	84.13 148

mvsmamba		71.15 93	69.54 109	75.99 61	77.61 182	53.46 141	81.95 76	75.11 219	57.73 143	66.95 159	85.96 103	37.14 234	87.56 46	67.94 70	75.49 163	86.97 52

LS3D		64.71 214	62.50 224	71.34 171	79.72 121	55.71 112	79.82 103	74.72 225	48.50 265	56.62 284	84.62 125	33.59 266	82.34 168	29.65 348	75.23 165	75.97 276

GG-mvs-BLEND				62.34 278	71.36 280	37.04 322	69.20 275	57.33 331		54.73 302	65.48 342	30.37 292	77.82 244	34.82 320	74.93 166	72.17 318

nrg030		72.96 68	73.01 65	72.84 140	75.41 221	50.24 192	80.02 98	82.89 83	58.36 131	74.44 47	86.73 81	58.90 23	80.83 198	65.84 90	74.46 167	87.44 40

VPA-MVSNet		69.02 138	69.47 112	67.69 227	77.42 186	41.00 291	74.04 209	79.68 137	60.06 101	69.26 116	84.81 121	51.06 87	77.58 248	54.44 178	74.43 168	84.48 138

PS-MVSNAJss		72.24 78	71.21 85	75.31 76	78.50 149	55.93 109	81.63 79	82.12 91	56.24 168	70.02 100	85.68 110	47.05 132	84.34 122	65.27 96	74.41 169	85.67 98

EI-MVSNet-Vis-set		72.42 76	71.59 76	74.91 82	78.47 151	54.02 132	77.05 152	79.33 145	65.03 16	71.68 84	79.35 236	52.75 65	84.89 112	66.46 83	74.23 170	85.83 90

CHOSEN 1792x2688		65.08 211	62.84 220	71.82 156	81.49 88	56.26 102	66.32 288	74.20 233	40.53 329	63.16 222	78.65 244	41.30 194	77.80 245	45.80 246	74.09 171	81.40 209

ACMMP++_ref															74.07 172

PVSNet_BlendedMVS		68.56 150	67.72 139	71.07 178	77.03 194	50.57 187	74.50 203	81.52 99	53.66 216	64.22 213	79.72 227	49.13 104	82.87 152	55.82 162	73.92 173	79.77 240

CMPMVS	42.80 21	57.81 269	55.97 274	63.32 270	60.98 347	47.38 233	64.66 301	69.50 268	32.06 344	46.83 340	77.80 257	29.50 299	71.36 282	48.68 224	73.75 174	71.21 327
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		62.42 235	61.46 235	65.31 260	75.21 224	52.10 167	72.05 241	74.05 234	46.41 287	57.42 281	74.36 294	34.35 258	77.57 249	45.62 249	73.67 175	66.26 343

test-LLR		58.15 266	58.13 261	58.22 299	68.57 308	44.80 256	65.46 294	57.92 328	50.08 252	55.44 292	69.82 323	32.62 279	57.44 336	49.66 216	73.62 176	72.41 314

test-mter		56.42 276	55.82 275	58.22 299	68.57 308	44.80 256	65.46 294	57.92 328	39.94 334	55.44 292	69.82 323	21.92 340	57.44 336	49.66 216	73.62 176	72.41 314

EI-MVSNet-UG-set		71.92 83	71.06 88	74.52 97	77.98 168	53.56 138	76.62 160	79.16 146	64.40 25	71.18 87	78.95 241	52.19 73	84.66 118	65.47 94	73.57 178	85.32 115

TR-MVS		66.59 192	65.07 197	71.17 175	79.18 133	49.63 206	73.48 221	75.20 217	52.95 220	67.90 137	80.33 216	39.81 204	83.68 134	43.20 271	73.56 179	80.20 231

UniMVSNet_ETH3D		67.60 168	67.07 165	69.18 213	77.39 187	42.29 278	74.18 208	75.59 209	60.37 94	66.77 162	86.06 99	37.64 225	78.93 234	52.16 194	73.49 180	86.32 74

FE-MVS		65.91 198	63.33 214	73.63 121	77.36 188	51.95 172	72.62 232	75.81 205	53.70 214	65.31 190	78.96 240	28.81 306	86.39 77	43.93 263	73.48 181	82.55 190

ab-mvs		66.65 189	66.42 173	67.37 231	76.17 209	41.73 284	70.41 265	76.14 202	53.99 211	65.98 176	83.51 152	49.48 98	76.24 263	48.60 225	73.46 182	84.14 147

EG-PatchMatch MVS		64.71 214	62.87 219	70.22 190	77.68 175	53.48 140	77.99 129	78.82 151	53.37 218	56.03 288	77.41 262	24.75 332	84.04 126	46.37 241	73.42 183	73.14 304

XVG-OURS-SEG-HR		68.81 141	67.47 150	72.82 142	74.40 239	56.87 97	70.59 261	79.04 147	54.77 202	66.99 157	86.01 101	39.57 206	78.21 239	62.54 118	73.33 184	83.37 174

thres200		62.20 238	61.16 240	65.34 259	75.38 222	39.99 294	69.60 271	69.29 271	55.64 183	61.87 240	76.99 264	37.07 237	78.96 233	31.28 341	73.28 185	77.06 267

thres100view900		63.28 227	62.41 225	65.89 252	77.31 189	38.66 305	72.65 230	69.11 273	57.07 149	62.45 234	81.03 202	37.01 238	79.17 223	31.84 333	73.25 186	79.83 238

tfpn200view9		63.18 229	62.18 228	66.21 244	76.85 197	39.62 297	71.96 244	69.44 269	56.63 156	62.61 229	79.83 223	37.18 231	79.17 223	31.84 333	73.25 186	79.83 238

thres400		63.31 225	62.18 228	66.72 236	76.85 197	39.62 297	71.96 244	69.44 269	56.63 156	62.61 229	79.83 223	37.18 231	79.17 223	31.84 333	73.25 186	81.36 210

TESTMET0.1,1		55.28 284	54.90 281	56.42 307	66.56 321	43.67 267	65.46 294	56.27 335	39.18 336	53.83 310	67.44 335	24.21 333	55.46 346	48.04 229	73.11 189	70.13 334

thres600view7		63.30 226	62.27 226	66.41 240	77.18 191	38.87 303	72.35 237	69.11 273	56.98 151	62.37 236	80.96 204	37.01 238	79.00 232	31.43 340	73.05 190	81.36 210

VPNet		67.52 169	68.11 135	65.74 254	79.18 133	36.80 324	72.17 240	72.83 246	62.04 70	67.79 145	85.83 107	48.88 108	76.60 259	51.30 203	72.97 191	83.81 158

Anonymous20231211		69.28 134	68.47 129	71.73 158	80.28 107	47.18 235	79.98 99	82.37 88	54.61 204	67.24 153	84.01 139	39.43 207	82.41 167	55.45 169	72.83 192	85.62 102

GBi-Net		67.21 173	66.55 168	69.19 210	77.63 177	43.33 269	77.31 144	77.83 178	56.62 158	65.04 199	82.70 162	41.85 186	80.33 208	47.18 234	72.76 193	83.92 153

test1		67.21 173	66.55 168	69.19 210	77.63 177	43.33 269	77.31 144	77.83 178	56.62 158	65.04 199	82.70 162	41.85 186	80.33 208	47.18 234	72.76 193	83.92 153

FMVSNet3		66.32 195	65.61 190	68.46 220	76.48 205	42.34 277	74.98 194	77.15 191	55.83 176	65.04 199	81.16 198	39.91 202	80.14 212	47.18 234	72.76 193	82.90 187

FMVSNet2		66.93 183	66.31 179	68.79 217	77.63 177	42.98 273	76.11 170	77.47 184	56.62 158	65.22 198	82.17 178	41.85 186	80.18 211	47.05 237	72.72 196	83.20 179

thisisatest0530		67.92 162	65.78 187	74.33 101	76.29 207	51.03 178	76.89 157	74.25 232	53.67 215	65.59 186	81.76 188	35.15 249	85.50 98	55.94 160	72.47 197	86.47 65

PVSNet	50.76 19	58.40 263	57.39 263	61.42 284	75.53 219	44.04 264	61.43 313	63.45 306	47.04 284	56.91 282	73.61 300	27.00 319	64.76 312	39.12 296	72.40 198	75.47 282

MIMVSNet		57.35 270	57.07 266	58.22 299	74.21 243	37.18 318	62.46 308	60.88 320	48.88 261	55.29 295	75.99 280	31.68 286	62.04 321	31.87 332	72.35 199	75.43 283

bld_raw_dy_0_64		64.87 212	63.22 215	69.83 201	74.79 230	53.32 146	78.15 127	62.02 316	51.20 243	60.17 251	83.12 159	24.15 334	74.20 273	63.08 113	72.33 200	81.96 201

1314		64.61 216	63.21 216	68.80 216	71.87 272	47.46 232	73.95 212	78.39 171	42.88 317	59.97 254	76.60 272	38.11 222	79.39 219	54.84 173	72.32 201	79.55 241

FMVSNet1		66.70 188	65.87 185	69.19 210	77.49 185	43.33 269	77.31 144	77.83 178	56.45 163	64.60 207	82.70 162	38.08 223	80.33 208	46.08 243	72.31 202	83.92 153

tt0805		67.77 165	67.24 161	69.34 209	74.87 227	40.08 293	77.36 143	81.37 105	55.31 187	66.33 171	84.65 124	37.35 229	82.55 163	55.65 167	72.28 203	85.39 113

ACMMP++															72.16 204

MVP-Stereo		65.41 205	63.80 207	70.22 190	77.62 181	55.53 118	76.30 166	78.53 161	50.59 249	56.47 286	78.65 244	39.84 203	82.68 159	44.10 262	72.12 205	72.44 313
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HyFIR lowres test		65.67 201	63.01 218	73.67 117	79.97 117	55.65 114	69.07 276	75.52 210	42.68 318	63.53 218	77.95 251	40.43 200	81.64 177	46.01 244	71.91 206	83.73 164

XVG-ACMP-BASELINE		64.36 218	62.23 227	70.74 183	72.35 265	52.45 163	70.80 260	78.45 166	53.84 213	59.87 256	81.10 200	16.24 349	79.32 220	55.64 168	71.76 207	80.47 226

HY-MVS	56.14 13	64.55 217	63.89 204	66.55 239	74.73 232	41.02 289	69.96 269	74.43 227	49.29 257	61.66 242	80.92 205	47.43 126	76.68 258	44.91 257	71.69 208	81.94 202

D2MVS		62.30 237	60.29 246	68.34 223	66.46 322	48.42 220	65.70 291	73.42 241	47.71 274	58.16 276	75.02 289	30.51 291	77.71 247	53.96 181	71.68 209	78.90 249

ACMH	55.70 15	65.20 209	63.57 210	70.07 194	78.07 164	52.01 171	79.48 111	79.69 136	55.75 179	56.59 285	80.98 203	27.12 317	80.94 194	42.90 275	71.58 210	77.25 266
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVSTER		67.16 178	65.58 191	71.88 155	70.37 289	49.70 202	70.25 267	78.45 166	51.52 235	69.16 118	80.37 213	38.45 217	82.50 164	60.19 137	71.46 211	83.44 173

EI-MVSNet		69.27 135	68.44 131	71.73 158	74.47 236	49.39 209	75.20 187	78.45 166	59.60 109	69.16 118	76.51 273	51.29 82	82.50 164	59.86 143	71.45 212	83.30 175

LTVRE_ROB	55.42 16	63.15 230	61.23 239	68.92 215	76.57 203	47.80 226	59.92 322	76.39 199	54.35 210	58.67 271	82.46 171	29.44 300	81.49 181	42.12 280	71.14 213	77.46 261
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
UniMVSNet (Re)		70.63 102	70.20 99	71.89 154	78.55 148	45.29 253	75.94 176	82.92 81	63.68 38	68.16 132	83.59 148	53.89 55	83.49 139	53.97 180	71.12 214	86.89 55

Effi-MVS+-dtu		69.64 126	67.53 146	75.95 62	76.10 210	62.29 15	80.20 96	76.06 204	59.83 108	65.26 195	77.09 263	41.56 191	84.02 128	60.60 135	71.09 215	81.53 207

NR-MVSNet		69.54 128	68.85 121	71.59 163	78.05 165	43.81 266	74.20 207	80.86 123	65.18 12	62.76 225	84.52 128	52.35 72	83.59 137	50.96 207	70.78 216	87.37 44

v1144		70.42 106	69.31 114	73.76 112	73.22 248	50.64 186	77.83 132	81.43 103	58.58 126	69.40 112	81.16 198	47.53 123	85.29 105	64.01 105	70.64 217	85.34 114

jajsoiax		68.25 155	66.45 170	73.66 118	75.62 216	55.49 119	80.82 89	78.51 162	52.33 227	64.33 209	84.11 136	28.28 309	81.81 176	63.48 111	70.62 218	83.67 166

h-mvs33		72.71 71	71.49 78	76.40 56	81.99 81	59.58 51	76.92 156	76.74 197	60.40 91	74.81 42	85.95 104	45.54 148	85.76 91	70.41 57	70.61 219	83.86 157

mvs_tets		68.18 157	66.36 176	73.63 121	75.61 217	55.35 121	80.77 90	78.56 160	52.48 226	64.27 211	84.10 137	27.45 315	81.84 175	63.45 112	70.56 220	83.69 165

UniMVSNet_NR-MVSNet		71.11 94	71.00 89	71.44 165	79.20 132	44.13 262	76.02 175	82.60 86	66.48 9	68.20 129	84.60 127	56.82 32	82.82 156	54.62 175	70.43 221	87.36 46

DU-MVS		70.01 113	69.53 110	71.44 165	78.05 165	44.13 262	75.01 192	81.51 101	64.37 26	68.20 129	84.52 128	49.12 106	82.82 156	54.62 175	70.43 221	87.37 44

v1192		69.97 115	68.68 124	73.85 107	73.19 249	50.94 179	77.68 135	81.36 106	57.51 145	68.95 120	80.85 208	45.28 155	85.33 104	62.97 115	70.37 223	85.27 117

PLC	56.13 14	65.09 210	63.21 216	70.72 184	81.04 98	54.87 127	78.57 121	77.47 184	48.51 264	55.71 289	81.89 185	33.71 263	79.71 213	41.66 284	70.37 223	77.58 260
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
GA-MVS		65.53 203	63.70 208	71.02 179	70.87 282	48.10 223	70.48 263	74.40 228	56.69 154	64.70 205	76.77 268	33.66 265	81.10 190	55.42 170	70.32 225	83.87 156

Fast-Effi-MVS+-dtu		67.37 171	65.33 194	73.48 126	72.94 255	57.78 81	77.47 141	76.88 193	57.60 144	61.97 238	76.85 267	39.31 208	80.49 206	54.72 174	70.28 226	82.17 199

v2v482		70.50 105	69.45 113	73.66 118	72.62 260	50.03 198	77.58 136	80.51 128	59.90 104	69.52 108	82.14 180	47.53 123	84.88 114	65.07 98	70.17 227	86.09 81

IB-MVS	56.42 12	65.40 206	62.73 222	73.40 130	74.89 225	52.78 154	73.09 226	75.13 218	55.69 180	58.48 274	73.73 299	32.86 273	86.32 80	50.63 208	70.11 228	81.10 218
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
CNLPA		65.43 204	64.02 203	69.68 202	78.73 145	58.07 77	77.82 133	70.71 260	51.49 236	61.57 244	83.58 151	38.23 221	70.82 284	43.90 264	70.10 229	80.16 232

RRT_MVS		69.42 132	67.49 149	75.21 80	78.01 167	52.56 159	82.23 73	78.15 173	55.84 175	65.65 184	85.07 117	30.86 289	86.83 63	61.56 130	70.00 230	86.24 79

1112_ss		64.00 220	63.36 213	65.93 251	79.28 129	42.58 276	71.35 249	72.36 250	46.41 287	60.55 249	77.89 255	46.27 142	73.28 274	46.18 242	69.97 231	81.92 203

DP-MVS		65.68 200	63.66 209	71.75 157	84.93 55	56.87 97	80.74 91	73.16 244	53.06 219	59.09 267	82.35 172	36.79 240	85.94 87	32.82 329	69.96 232	72.45 312

tttt0517		67.83 164	65.66 189	74.33 101	76.69 199	50.82 183	77.86 131	73.99 235	54.54 207	64.64 206	82.53 169	35.06 250	85.50 98	55.71 165	69.91 233	86.67 61

IterMVS-LS		69.22 137	68.48 127	71.43 167	74.44 238	49.40 208	76.23 168	77.55 183	59.60 109	65.85 182	81.59 193	51.28 83	81.58 180	59.87 142	69.90 234	83.30 175
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		69.47 130	68.17 134	73.36 131	73.06 252	50.10 196	77.39 142	80.56 126	56.58 162	68.59 122	80.37 213	44.72 160	84.98 109	62.47 120	69.82 235	85.00 124

Baseline_NR-MVSNet		67.05 180	67.56 143	65.50 256	75.65 215	37.70 315	75.42 182	74.65 226	59.90 104	68.14 133	83.15 158	49.12 106	77.20 252	52.23 193	69.78 236	81.60 206

ACMH+	57.40 11	66.12 196	64.06 202	72.30 153	77.79 173	52.83 153	80.39 93	78.03 175	57.30 146	57.47 280	82.55 168	27.68 313	84.17 123	45.54 250	69.78 236	79.90 236

v1240		69.24 136	67.91 137	73.25 135	73.02 254	49.82 200	77.21 149	80.54 127	56.43 164	68.34 128	80.51 212	43.33 172	84.99 107	62.03 124	69.77 238	84.95 127

TranMVSNet+NR-MVSNet		70.36 107	70.10 103	71.17 175	78.64 147	42.97 274	76.53 162	81.16 117	66.95 4	68.53 125	85.42 115	51.61 80	83.07 145	52.32 192	69.70 239	87.46 39

v144192		69.71 121	68.51 126	73.33 132	73.10 251	50.13 195	77.54 139	80.64 125	56.65 155	68.57 124	80.55 211	46.87 137	84.96 111	62.98 114	69.66 240	84.89 128

WR-MVS		68.47 151	68.47 129	68.44 221	80.20 111	39.84 295	73.75 219	76.07 203	64.68 20	68.11 134	83.63 147	50.39 93	79.14 227	49.78 212	69.66 240	86.34 70

WTY-MVS		59.75 256	60.39 245	57.85 303	72.32 266	37.83 312	61.05 319	64.18 303	45.95 294	61.91 239	79.11 239	47.01 135	60.88 324	42.50 277	69.49 242	74.83 290

cl22		67.47 170	66.45 170	70.54 187	69.85 298	46.49 239	73.85 217	77.35 188	55.07 196	65.51 187	77.92 253	47.64 121	81.10 190	61.58 129	69.32 243	84.01 151

miper_ehance_all_eth		68.03 159	67.24 161	70.40 189	70.54 285	46.21 243	73.98 210	78.68 157	55.07 196	66.05 175	77.80 257	52.16 74	81.31 185	61.53 131	69.32 243	83.67 166

miper_enhance_ethall		67.11 179	66.09 183	70.17 193	69.21 304	45.98 245	72.85 229	78.41 169	51.38 238	65.65 184	75.98 281	51.17 85	81.25 186	60.82 133	69.32 243	83.29 177

test_djsdf		69.45 131	67.74 138	74.58 94	74.57 235	54.92 126	82.79 59	78.48 163	51.26 241	65.41 189	83.49 153	38.37 218	83.24 142	66.06 86	69.25 246	85.56 103

cl____		67.18 176	66.26 181	69.94 196	70.20 290	45.74 247	73.30 222	76.83 195	55.10 191	65.27 192	79.57 230	47.39 127	80.53 203	59.41 147	69.22 247	83.53 172

DIV-MVS_self_test		67.18 176	66.26 181	69.94 196	70.20 290	45.74 247	73.29 223	76.83 195	55.10 191	65.27 192	79.58 229	47.38 128	80.53 203	59.43 146	69.22 247	83.54 171

c3_l		68.33 153	67.56 143	70.62 185	70.87 282	46.21 243	74.47 204	78.80 153	56.22 169	66.19 173	78.53 248	51.88 76	81.40 182	62.08 121	69.04 249	84.25 143

CostFormer		64.04 219	62.51 223	68.61 219	71.88 271	45.77 246	71.30 251	70.60 261	47.55 276	64.31 210	76.61 271	41.63 189	79.62 216	49.74 214	69.00 250	80.42 227

tpm2		62.07 239	60.10 247	67.99 225	72.79 257	43.86 265	71.05 258	66.85 286	43.14 315	62.77 224	75.39 287	38.32 219	80.80 199	41.69 283	68.88 251	79.32 244

v10		70.21 110	69.02 119	73.81 109	73.51 247	50.92 181	78.74 117	81.39 104	60.05 102	66.39 170	81.83 187	47.58 122	85.41 103	62.80 116	68.86 252	85.09 122

v8		70.33 108	69.28 115	73.49 125	73.15 250	50.22 193	78.62 120	80.78 124	60.79 84	66.45 169	82.11 182	49.35 99	84.98 109	63.58 110	68.71 253	85.28 116

v7n		69.01 139	67.36 154	73.98 105	72.51 263	52.65 155	78.54 123	81.30 111	60.26 99	62.67 227	81.62 190	43.61 169	84.49 119	57.01 154	68.70 254	84.79 131

MVS_0304		58.51 261	57.36 264	61.96 281	70.04 294	41.83 282	69.40 274	65.46 294	50.73 245	53.30 318	74.06 297	22.65 337	70.18 291	42.16 279	68.44 255	73.86 302

Test_1112_low_res		62.32 236	61.77 231	64.00 267	79.08 137	39.53 299	68.17 278	70.17 262	43.25 313	59.03 268	79.90 222	44.08 165	71.24 283	43.79 266	68.42 256	81.25 213

PMMVS		53.96 289	53.26 295	56.04 308	62.60 340	50.92 181	61.17 317	56.09 336	32.81 343	53.51 316	66.84 338	34.04 260	59.93 328	44.14 261	68.18 257	57.27 352

tfpnnormal		62.47 234	61.63 233	64.99 262	74.81 229	39.01 302	71.22 252	73.72 238	55.22 190	60.21 250	80.09 221	41.26 197	76.98 256	30.02 346	68.09 258	78.97 248

Anonymous20231206		55.10 287	55.30 279	54.48 315	69.81 299	33.94 344	62.91 307	62.13 315	41.08 326	55.18 296	75.65 283	32.75 277	56.59 341	30.32 345	67.86 259	72.91 305

V42		68.65 145	67.35 155	72.56 145	68.93 307	50.18 194	72.90 228	79.47 142	56.92 152	69.45 111	80.26 217	46.29 141	82.99 146	64.07 103	67.82 260	84.53 136

MDTV_nov1_ep13			57.00 267		72.73 258	38.26 308	65.02 300	64.73 300	44.74 299	55.46 291	72.48 304	32.61 281	70.47 286	37.47 303	67.75 261

anonymousdsp		67.00 182	64.82 199	73.57 124	70.09 293	56.13 104	76.35 165	77.35 188	48.43 266	64.99 202	80.84 209	33.01 271	80.34 207	64.66 100	67.64 262	84.23 144

OpenMVS_ROB	52.78 18	60.03 253	58.14 260	65.69 255	70.47 286	44.82 255	75.33 183	70.86 259	45.04 297	56.06 287	76.00 278	26.89 320	79.65 214	35.36 319	67.29 263	72.60 309

XXY-MVS		60.68 250	61.67 232	57.70 305	70.43 287	38.45 307	64.19 303	66.47 287	48.05 271	63.22 220	80.86 207	49.28 101	60.47 325	45.25 256	67.28 264	74.19 298

baseline2		63.42 224	61.26 238	69.89 200	72.55 262	47.62 230	71.54 247	68.38 277	50.11 251	54.82 300	75.55 285	43.06 174	80.96 193	48.13 228	67.16 265	81.11 217

AUN-MVS		68.45 152	66.41 174	74.57 95	79.53 124	57.08 95	73.93 214	75.23 215	54.44 209	66.69 164	81.85 186	37.10 236	82.89 150	62.07 122	66.84 266	83.75 163

hse-mvs2		71.04 95	69.86 104	74.60 93	79.58 122	57.12 94	73.96 211	75.25 214	60.40 91	74.81 42	81.95 184	45.54 148	82.90 149	70.41 57	66.83 267	83.77 162

F-COLMAP		63.05 231	60.87 244	69.58 206	76.99 196	53.63 137	78.12 128	76.16 201	47.97 272	52.41 320	81.61 191	27.87 311	78.11 240	40.07 290	66.66 268	77.00 269

pm-mvs1		65.24 208	64.97 198	66.04 249	72.38 264	39.40 300	72.62 232	75.63 208	55.53 184	62.35 237	83.18 157	47.45 125	76.47 260	49.06 222	66.54 269	82.24 196

v148		68.24 156	67.19 163	71.40 168	70.43 287	47.77 228	75.76 178	77.03 192	58.91 119	67.36 151	80.10 220	48.60 111	81.89 173	60.01 139	66.52 270	84.53 136

eth_miper_zixun_eth		67.63 167	66.28 180	71.67 160	71.60 274	48.33 221	73.68 220	77.88 176	55.80 178	65.91 178	78.62 246	47.35 129	82.88 151	59.45 145	66.25 271	83.81 158

sss		56.17 279	56.57 270	54.96 312	66.93 318	36.32 330	57.94 328	61.69 317	41.67 322	58.64 272	75.32 288	38.72 215	56.25 342	42.04 281	66.19 272	72.31 317

COLMAP_ROB	52.97 17	61.27 249	58.81 252	68.64 218	74.63 233	52.51 161	78.42 124	73.30 242	49.92 254	50.96 325	81.51 194	23.06 336	79.40 218	31.63 337	65.85 273	74.01 300
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CVMVSNet		59.63 257	59.14 250	61.08 287	74.47 236	38.84 304	75.20 187	68.74 275	31.15 345	58.24 275	76.51 273	32.39 283	68.58 296	49.77 213	65.84 274	75.81 278

MSDG		61.81 243	59.23 249	69.55 207	72.64 259	52.63 157	70.45 264	75.81 205	51.38 238	53.70 311	76.11 277	29.52 298	81.08 192	37.70 302	65.79 275	74.93 289

FMVSNet5		55.86 280	54.93 280	58.66 297	71.05 281	36.35 328	64.18 304	62.48 313	46.76 285	50.66 330	74.73 292	25.80 326	64.04 314	33.11 327	65.57 276	75.59 281

pmmvs5		56.47 275	55.68 276	58.86 295	61.41 344	36.71 325	66.37 287	62.75 311	40.38 330	53.70 311	76.62 270	34.56 254	67.05 302	40.02 292	65.27 277	72.83 307

miper_lstm_enhance		62.03 240	60.88 243	65.49 257	66.71 320	46.25 241	56.29 335	75.70 207	50.68 246	61.27 245	75.48 286	40.21 201	68.03 298	56.31 159	65.25 278	82.18 197

tpm		57.34 271	58.16 259	54.86 313	71.80 273	34.77 336	67.47 284	56.04 337	48.20 269	60.10 252	76.92 265	37.17 233	53.41 351	40.76 288	65.01 279	76.40 275

test_vis1_n_1920		58.86 259	59.06 251	58.25 298	63.76 334	43.14 272	67.49 283	66.36 289	40.22 331	65.89 180	71.95 309	31.04 287	59.75 329	59.94 140	64.90 280	71.85 321

pmmvs4		61.48 247	59.39 248	67.76 226	71.57 275	53.86 134	71.42 248	65.34 295	44.20 305	59.46 262	77.92 253	35.90 244	74.71 268	43.87 265	64.87 281	74.71 293

test_0402		63.25 228	61.01 241	69.96 195	80.00 116	54.37 131	76.86 158	72.02 251	54.58 206	58.71 270	80.79 210	35.00 251	84.36 121	26.41 357	64.71 282	71.15 328

CR-MVSNet		59.91 254	57.90 262	65.96 250	69.96 296	52.07 168	65.31 297	63.15 309	42.48 319	59.36 263	74.84 290	35.83 245	70.75 285	45.50 251	64.65 283	75.06 285

RPMNet		61.53 245	58.42 256	70.86 180	69.96 296	52.07 168	65.31 297	81.36 106	43.20 314	59.36 263	70.15 321	35.37 247	85.47 100	36.42 314	64.65 283	75.06 285

pmmvs6		63.69 222	62.82 221	66.27 243	70.63 284	39.27 301	73.13 225	75.47 211	52.69 224	59.75 260	82.30 174	39.71 205	77.03 255	47.40 232	64.35 285	82.53 191

Anonymous20240521		55.30 283	54.41 285	57.96 302	60.92 349	41.73 284	71.09 257	71.06 258	41.18 325	48.65 334	73.31 301	16.93 347	59.25 331	42.54 276	64.01 286	72.90 306

WR-MVS_H		67.02 181	66.92 166	67.33 233	77.95 169	37.75 313	77.57 137	82.11 92	62.03 71	62.65 228	82.48 170	50.57 91	79.46 217	42.91 274	64.01 286	84.79 131

test0.0.03 1		53.32 296	53.59 293	52.50 327	62.81 339	29.45 358	59.51 323	54.11 341	50.08 252	54.40 306	74.31 295	32.62 279	55.92 344	30.50 344	63.95 288	72.15 319

PatchMatch-RL		56.25 278	54.55 283	61.32 286	77.06 193	56.07 106	65.57 293	54.10 342	44.13 307	53.49 317	71.27 313	25.20 329	66.78 304	36.52 313	63.66 289	61.12 346

PatchmatchNet		59.84 255	58.24 258	64.65 264	73.05 253	46.70 238	69.42 273	62.18 314	47.55 276	58.88 269	71.96 308	34.49 256	69.16 293	42.99 273	63.60 290	78.07 254
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
IterMVS-SCA-FT		62.49 233	61.52 234	65.40 258	71.99 270	50.80 184	71.15 255	69.63 266	45.71 295	60.61 248	77.93 252	37.45 227	65.99 309	55.67 166	63.50 291	79.42 243

CP-MVSNet		66.49 193	66.41 174	66.72 236	77.67 176	36.33 329	76.83 159	79.52 141	62.45 61	62.54 231	83.47 154	46.32 140	78.37 236	45.47 253	63.43 292	85.45 108

PS-CasMVS		66.42 194	66.32 178	66.70 238	77.60 184	36.30 331	76.94 155	79.61 139	62.36 63	62.43 235	83.66 146	45.69 144	78.37 236	45.35 255	63.26 293	85.42 111

IterMVS		62.79 232	61.27 237	67.35 232	69.37 303	52.04 170	71.17 253	68.24 278	52.63 225	59.82 257	76.91 266	37.32 230	72.36 277	52.80 190	63.19 294	77.66 259
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PEN-MVS		66.60 190	66.45 170	67.04 234	77.11 192	36.56 326	77.03 153	80.42 129	62.95 48	62.51 233	84.03 138	46.69 138	79.07 228	44.22 258	63.08 295	85.51 105

tpmrst		58.24 264	58.70 254	56.84 306	66.97 317	34.32 340	69.57 272	61.14 319	47.17 283	58.58 273	71.60 310	41.28 196	60.41 326	49.20 220	62.84 296	75.78 279

testgi		51.90 300	52.37 297	50.51 333	60.39 350	23.55 372	58.42 326	58.15 326	49.03 260	51.83 322	79.21 238	22.39 338	55.59 345	29.24 350	62.64 297	72.40 316

SCA		60.49 251	58.38 257	66.80 235	74.14 244	48.06 224	63.35 305	63.23 308	49.13 259	59.33 266	72.10 306	37.45 227	74.27 271	44.17 259	62.57 298	78.05 255

EPMVS		53.96 289	53.69 292	54.79 314	66.12 325	31.96 353	62.34 310	49.05 351	44.42 304	55.54 290	71.33 312	30.22 294	56.70 339	41.65 285	62.54 299	75.71 280

ITE_SJBPF				62.09 280	66.16 324	44.55 261		64.32 302	47.36 279	55.31 294	80.34 215	19.27 344	62.68 319	36.29 315	62.39 300	79.04 246

MIMVSNet1		55.17 286	54.31 287	57.77 304	70.03 295	32.01 352	65.68 292	64.81 298	49.19 258	46.75 341	76.00 278	25.53 328	64.04 314	28.65 351	62.13 301	77.26 265

CL-MVSNet_self_test		61.53 245	60.94 242	63.30 271	68.95 306	36.93 323	67.60 282	72.80 247	55.67 181	59.95 255	76.63 269	45.01 158	72.22 280	39.74 294	62.09 302	80.74 224

baseline1		63.81 221	63.87 206	63.62 268	76.29 207	36.36 327	71.78 246	67.29 282	56.05 172	64.23 212	82.95 160	47.11 131	74.41 270	47.30 233	61.85 303	80.10 234

USDC		56.35 277	54.24 288	62.69 276	64.74 330	40.31 292	65.05 299	73.83 237	43.93 309	47.58 336	77.71 260	15.36 351	75.05 267	38.19 301	61.81 304	72.70 308

PatchT		53.17 297	53.44 294	52.33 328	68.29 312	25.34 369	58.21 327	54.41 340	44.46 303	54.56 304	69.05 329	33.32 268	60.94 323	36.93 306	61.76 305	70.73 331

tpm cat1		59.25 258	56.95 268	66.15 246	72.19 267	46.96 236	68.09 279	65.76 291	40.03 333	57.81 278	70.56 316	38.32 219	74.51 269	38.26 300	61.50 306	77.00 269

tpmvs		58.47 262	56.95 268	63.03 275	70.20 290	41.21 288	67.90 281	67.23 283	49.62 255	54.73 302	70.84 314	34.14 259	76.24 263	36.64 311	61.29 307	71.64 322

Patchmtry		57.16 272	56.47 271	59.23 291	69.17 305	34.58 339	62.98 306	63.15 309	44.53 301	56.83 283	74.84 290	35.83 245	68.71 295	40.03 291	60.91 308	74.39 296

DTE-MVSNet		65.58 202	65.34 193	66.31 241	76.06 211	34.79 335	76.43 164	79.38 144	62.55 59	61.66 242	83.83 143	45.60 146	79.15 226	41.64 286	60.88 309	85.00 124

CHOSEN 280x420		47.83 313	46.36 317	52.24 330	67.37 316	49.78 201	38.91 364	43.11 363	35.00 341	43.27 351	63.30 347	28.95 303	49.19 358	36.53 312	60.80 310	57.76 351

test_fmvs1		51.32 305	50.48 304	53.81 319	53.57 356	37.51 316	60.63 321	51.16 346	28.02 351	63.62 217	69.23 328	16.41 348	53.93 350	51.01 205	60.70 311	69.99 335

test_fmvs1_n		51.37 303	50.35 305	54.42 317	52.85 357	37.71 314	61.16 318	51.93 344	28.15 349	63.81 216	69.73 325	13.72 352	53.95 349	51.16 204	60.65 312	71.59 323

Patchmatch-test		49.08 310	48.28 312	51.50 331	64.40 332	30.85 356	45.68 356	48.46 354	35.60 340	46.10 344	72.10 306	34.47 257	46.37 361	27.08 355	60.65 312	77.27 264

test20.03		53.87 291	54.02 290	53.41 323	61.47 343	28.11 362	61.30 315	59.21 323	51.34 240	52.09 321	77.43 261	33.29 269	58.55 333	29.76 347	60.27 314	73.58 303

MVS-HIRNet		45.52 316	44.48 319	48.65 335	68.49 310	34.05 343	59.41 325	44.50 361	27.03 352	37.96 359	50.47 362	26.16 324	64.10 313	26.74 356	59.52 315	47.82 361

Patchmatch-RL test		58.16 265	55.49 277	66.15 246	67.92 313	48.89 215	60.66 320	51.07 348	47.86 273	59.36 263	62.71 348	34.02 261	72.27 279	56.41 158	59.40 316	77.30 263

AllTest		57.08 273	54.65 282	64.39 265	71.44 276	49.03 210	69.92 270	67.30 280	45.97 292	47.16 338	79.77 225	17.47 345	67.56 300	33.65 324	59.16 317	76.57 273

TestCases				64.39 265	71.44 276	49.03 210		67.30 280	45.97 292	47.16 338	79.77 225	17.47 345	67.56 300	33.65 324	59.16 317	76.57 273

RPSCF		55.80 281	54.22 289	60.53 288	65.13 329	42.91 275	64.30 302	57.62 330	36.84 339	58.05 277	82.28 175	28.01 310	56.24 343	37.14 305	58.61 319	82.44 195

EU-MVSNet		55.61 282	54.41 285	59.19 293	65.41 328	33.42 346	72.44 236	71.91 252	28.81 347	51.27 323	73.87 298	24.76 331	69.08 294	43.04 272	58.20 320	75.06 285

KD-MVS_self_test		55.22 285	53.89 291	59.21 292	57.80 354	27.47 364	57.75 330	74.32 229	47.38 278	50.90 326	70.00 322	28.45 308	70.30 289	40.44 289	57.92 321	79.87 237

test_vis1_n		49.89 309	48.69 311	53.50 322	53.97 355	37.38 317	61.53 312	47.33 357	28.54 348	59.62 261	67.10 337	13.52 353	52.27 354	49.07 221	57.52 322	70.84 330

pmmvs-eth3d		58.81 260	56.31 273	66.30 242	67.61 314	52.42 164	72.30 238	64.76 299	43.55 311	54.94 299	74.19 296	28.95 303	72.60 276	43.31 268	57.21 323	73.88 301

test_fmvs2		48.69 311	47.49 316	52.29 329	48.63 363	33.06 349	57.76 329	48.05 355	25.71 355	59.76 259	69.60 326	11.57 358	52.23 355	49.45 219	56.86 324	71.58 324

our_test_3		56.49 274	54.42 284	62.68 277	69.51 300	45.48 252	66.08 289	61.49 318	44.11 308	50.73 329	69.60 326	33.05 270	68.15 297	38.38 299	56.86 324	74.40 295

TinyColmap		54.14 288	51.72 298	61.40 285	66.84 319	41.97 280	66.52 286	68.51 276	44.81 298	42.69 352	75.77 282	11.66 357	72.94 275	31.96 331	56.77 326	69.27 339

ppachtmachnet_test		58.06 267	55.38 278	66.10 248	69.51 300	48.99 213	68.01 280	66.13 290	44.50 302	54.05 309	70.74 315	32.09 285	72.34 278	36.68 310	56.71 327	76.99 271

OurMVSNet-221017-0		61.37 248	58.63 255	69.61 203	72.05 269	48.06 224	73.93 214	72.51 248	47.23 282	54.74 301	80.92 205	21.49 343	81.24 187	48.57 226	56.22 328	79.53 242

TransMVSNet (Re)		64.72 213	64.33 201	65.87 253	75.22 223	38.56 306	74.66 201	75.08 223	58.90 120	61.79 241	82.63 165	51.18 84	78.07 241	43.63 267	55.87 329	80.99 220

FPMVS		42.18 321	41.11 323	45.39 338	58.03 353	41.01 290	49.50 348	53.81 343	30.07 346	33.71 360	64.03 344	11.69 356	52.08 356	14.01 367	55.11 330	43.09 363

dp		51.89 301	51.60 299	52.77 326	68.44 311	32.45 351	62.36 309	54.57 339	44.16 306	49.31 333	67.91 331	28.87 305	56.61 340	33.89 323	54.89 331	69.24 340

ADS-MVSNet2		51.33 304	48.76 310	59.07 294	66.02 326	44.60 259	50.90 346	59.76 322	36.90 337	50.74 327	66.18 340	26.38 321	63.11 317	27.17 353	54.76 332	69.50 337

ADS-MVSNet		48.48 312	47.77 313	50.63 332	66.02 326	29.92 357	50.90 346	50.87 350	36.90 337	50.74 327	66.18 340	26.38 321	52.47 353	27.17 353	54.76 332	69.50 337

PM-MVS		52.33 299	50.19 306	58.75 296	62.10 341	45.14 254	65.75 290	40.38 365	43.60 310	53.52 315	72.65 303	9.16 365	65.87 310	50.41 209	54.18 334	65.24 345

JIA-IIPM		51.56 302	47.68 315	63.21 272	64.61 331	50.73 185	47.71 352	58.77 325	42.90 316	48.46 335	51.72 358	24.97 330	70.24 290	36.06 316	53.89 335	68.64 341

ambc				65.13 261	63.72 336	37.07 321	47.66 353	78.78 154		54.37 307	71.42 311	11.24 360	80.94 194	45.64 248	53.85 336	77.38 262

test_vis1_rt		41.35 323	39.45 325	47.03 337	46.65 366	37.86 311	47.76 351	38.65 366	23.10 358	44.21 349	51.22 360	11.20 361	44.08 363	39.27 295	53.02 337	59.14 348

DSMNet-mixed		39.30 327	38.72 326	41.03 344	51.22 360	19.66 375	45.53 357	31.35 372	15.83 369	39.80 357	67.42 336	22.19 339	45.13 362	22.43 359	52.69 338	58.31 350

N_pmnet		39.35 326	40.28 324	36.54 349	63.76 334	1.62 383	49.37 349	0.76 383	34.62 342	43.61 350	66.38 339	26.25 323	42.57 365	26.02 358	51.77 339	65.44 344

TDRefinement		53.44 295	50.72 303	61.60 283	64.31 333	46.96 236	70.89 259	65.27 297	41.78 320	44.61 347	77.98 250	11.52 359	66.36 307	28.57 352	51.59 340	71.49 325

Gipuma		34.77 330	31.91 334	43.33 342	62.05 342	37.87 310	20.39 369	67.03 284	23.23 357	18.41 370	25.84 370	4.24 371	62.73 318	14.71 366	51.32 341	29.38 369
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
YYNet1		50.73 306	48.96 307	56.03 309	61.10 346	41.78 283	51.94 344	56.44 333	40.94 328	44.84 345	67.80 333	30.08 295	55.08 347	36.77 307	50.71 342	71.22 326

MDA-MVSNet_test_wron		50.71 307	48.95 308	56.00 310	61.17 345	41.84 281	51.90 345	56.45 332	40.96 327	44.79 346	67.84 332	30.04 296	55.07 348	36.71 309	50.69 343	71.11 329

EGC-MVSNET		42.47 320	38.48 327	54.46 316	74.33 240	48.73 217	70.33 266	51.10 347	0.03 377	0.18 378	67.78 334	13.28 354	66.49 306	18.91 363	50.36 344	48.15 359

test_fmvs3		44.30 318	42.55 320	49.55 334	42.83 367	27.15 365	53.03 342	44.93 360	22.03 362	53.69 313	64.94 343	4.21 372	49.63 357	47.47 230	49.82 345	71.88 320

SixPastTwentyTwo		61.65 244	58.80 253	70.20 192	75.80 213	47.22 234	75.59 179	69.68 265	54.61 204	54.11 308	79.26 237	27.07 318	82.96 147	43.27 269	49.79 346	80.41 228

new-patchmatchnet		47.56 314	47.73 314	47.06 336	58.81 352	9.37 379	48.78 350	59.21 323	43.28 312	44.22 348	68.66 330	25.67 327	57.20 338	31.57 339	49.35 347	74.62 294

LF4IMVS		42.95 319	42.26 321	45.04 339	48.30 364	32.50 350	54.80 338	48.49 353	28.03 350	40.51 355	70.16 320	9.24 364	43.89 364	31.63 337	49.18 348	58.72 349

PMVS	28.69 22	36.22 329	33.29 333	45.02 340	36.82 375	35.98 333	54.68 339	48.74 352	26.31 353	21.02 368	51.61 359	2.88 377	60.10 327	9.99 373	47.58 349	38.99 368
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmmvs3		44.92 317	41.95 322	53.86 318	52.58 359	43.55 268	62.11 311	46.90 359	26.05 354	40.63 354	60.19 350	11.08 362	57.91 335	31.83 336	46.15 350	60.11 347

MDA-MVSNet-bldmvs		53.87 291	50.81 302	63.05 274	66.25 323	48.58 218	56.93 333	63.82 304	48.09 270	41.22 353	70.48 319	30.34 293	68.00 299	34.24 322	45.92 351	72.57 310

UnsupCasMVSNet_eth		53.16 298	52.47 296	55.23 311	59.45 351	33.39 347	59.43 324	69.13 272	45.98 291	50.35 332	72.32 305	29.30 301	58.26 334	42.02 282	44.30 352	74.05 299

UnsupCasMVSNet_bld		50.07 308	48.87 309	53.66 320	60.97 348	33.67 345	57.62 331	64.56 301	39.47 335	47.38 337	64.02 346	27.47 314	59.32 330	34.69 321	43.68 353	67.98 342

KD-MVS_2432*1600		53.45 293	51.50 300	59.30 289	62.82 337	37.14 319	55.33 336	71.79 253	47.34 280	55.09 297	70.52 317	21.91 341	70.45 287	35.72 317	42.97 354	70.31 332

miper_refine_blended		53.45 293	51.50 300	59.30 289	62.82 337	37.14 319	55.33 336	71.79 253	47.34 280	55.09 297	70.52 317	21.91 341	70.45 287	35.72 317	42.97 354	70.31 332

test_vis3_rt		32.09 333	30.20 337	37.76 348	35.36 377	27.48 363	40.60 363	28.29 375	16.69 367	32.52 361	40.53 366	1.96 378	37.40 370	33.64 326	42.21 356	48.39 358

APD_test1		37.39 328	34.94 331	44.72 341	48.88 362	33.19 348	52.95 343	44.00 362	19.49 363	27.28 364	58.59 352	3.18 376	52.84 352	18.92 362	41.17 357	48.14 360

new_pmnet		34.13 331	34.29 332	33.64 351	52.63 358	18.23 377	44.43 359	33.90 371	22.81 359	30.89 362	53.18 356	10.48 363	35.72 372	20.77 361	39.51 358	46.98 362

K. test v3		60.47 252	57.11 265	70.56 186	73.74 246	48.22 222	75.10 191	62.55 312	58.27 132	53.62 314	76.31 276	27.81 312	81.59 179	47.42 231	39.18 359	81.88 204

LCM-MVSNet		40.30 324	35.88 330	53.57 321	42.24 368	29.15 359	45.21 358	60.53 321	22.23 361	28.02 363	50.98 361	3.72 374	61.78 322	31.22 342	38.76 360	69.78 336

test_f		31.86 334	31.05 335	34.28 350	32.33 379	21.86 373	32.34 366	30.46 373	16.02 368	39.78 358	55.45 355	4.80 370	32.36 373	30.61 343	37.66 361	48.64 357

mvsany_test1		39.38 325	38.16 328	43.02 343	49.05 361	34.28 341	44.16 360	25.94 376	22.74 360	46.57 342	62.21 349	23.85 335	41.16 368	33.01 328	35.91 362	53.63 355

testf1		31.46 335	28.89 338	39.16 345	41.99 370	28.78 360	46.45 354	37.56 367	14.28 370	21.10 366	48.96 363	1.48 380	47.11 359	13.63 368	34.56 363	41.60 364

APD_test2		31.46 335	28.89 338	39.16 345	41.99 370	28.78 360	46.45 354	37.56 367	14.28 370	21.10 366	48.96 363	1.48 380	47.11 359	13.63 368	34.56 363	41.60 364

lessismore_v0				69.91 198	71.42 278	47.80 226		50.90 349		50.39 331	75.56 284	27.43 316	81.33 184	45.91 245	34.10 365	80.59 225

mvsany_test3		32.62 332	30.57 336	38.77 347	36.16 376	24.20 371	38.10 365	20.63 378	19.14 364	40.36 356	57.43 353	5.06 369	36.63 371	29.59 349	28.66 366	55.49 353

PVSNet_0	43.31 20	47.46 315	45.64 318	52.92 325	67.60 315	44.65 258	54.06 340	54.64 338	41.59 323	46.15 343	58.75 351	30.99 288	58.66 332	32.18 330	24.81 367	55.46 354

test_method		19.68 341	18.10 344	24.41 356	13.68 381	3.11 382	12.06 372	42.37 364	2.00 375	11.97 373	36.38 367	5.77 368	29.35 375	15.06 365	23.65 368	40.76 366

PMMVS2		27.40 337	25.91 340	31.87 353	39.46 374	6.57 380	31.17 367	28.52 374	23.96 356	20.45 369	48.94 365	4.20 373	37.94 369	16.51 364	19.97 369	51.09 356

MVE	17.77 23	21.41 340	17.77 345	32.34 352	34.34 378	25.44 368	16.11 370	24.11 377	11.19 372	13.22 372	31.92 368	1.58 379	30.95 374	10.47 371	17.03 370	40.62 367
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		23.77 338	22.73 342	26.90 354	42.02 369	20.67 374	42.66 361	35.70 369	17.43 365	10.28 375	25.05 371	6.42 367	42.39 366	10.28 372	14.71 371	17.63 370

EMVS		22.97 339	21.84 343	26.36 355	40.20 372	19.53 376	41.95 362	34.64 370	17.09 366	9.73 376	22.83 372	7.29 366	42.22 367	9.18 374	13.66 372	17.32 371

wuyk23d		13.32 343	12.52 346	15.71 357	47.54 365	26.27 366	31.06 368	1.98 382	4.93 374	5.18 377	1.94 377	0.45 382	18.54 376	6.81 376	12.83 373	2.33 374

ANet_high		41.38 322	37.47 329	53.11 324	39.73 373	24.45 370	56.94 332	69.69 264	47.65 275	26.04 365	52.32 357	12.44 355	62.38 320	21.80 360	10.61 374	72.49 311

tmp_tt		9.43 344	11.14 347	4.30 359	2.38 382	4.40 381	13.62 371	16.08 380	0.39 376	15.89 371	13.06 373	15.80 350	5.54 378	12.63 370	10.46 375	2.95 373

DeepMVS_CX				12.03 358	17.97 380	10.91 378		10.60 381	7.46 373	11.07 374	28.36 369	3.28 375	11.29 377	8.01 375	9.74 376	13.89 372

test_blank		0.00 349	0.00 352	0.00 362	0.00 385	0.00 385	0.00 373	0.00 384	0.00 380	0.00 381	0.00 380	0.00 384	0.00 379	0.00 379	0.00 377	0.00 377

uanet_test		0.00 349	0.00 352	0.00 362	0.00 385	0.00 385	0.00 373	0.00 384	0.00 380	0.00 381	0.00 380	0.00 384	0.00 379	0.00 379	0.00 377	0.00 377

DCPMVS		0.00 349	0.00 352	0.00 362	0.00 385	0.00 385	0.00 373	0.00 384	0.00 380	0.00 381	0.00 380	0.00 384	0.00 379	0.00 379	0.00 377	0.00 377

cdsmvs_eth3d_5k		17.50 342	23.34 341	0.00 362	0.00 385	0.00 385	0.00 373	78.63 158	0.00 380	0.00 381	82.18 176	49.25 102	0.00 379	0.00 379	0.00 377	0.00 377

pcd_1.5k_mvsjas		3.92 348	5.23 351	0.00 362	0.00 385	0.00 385	0.00 373	0.00 384	0.00 380	0.00 381	0.00 380	47.05 132	0.00 379	0.00 379	0.00 377	0.00 377

sosnet-low-res		0.00 349	0.00 352	0.00 362	0.00 385	0.00 385	0.00 373	0.00 384	0.00 380	0.00 381	0.00 380	0.00 384	0.00 379	0.00 379	0.00 377	0.00 377

sosnet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 385	0.00 373	0.00 384	0.00 380	0.00 381	0.00 380	0.00 384	0.00 379	0.00 379	0.00 377	0.00 377

uncertanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 385	0.00 373	0.00 384	0.00 380	0.00 381	0.00 380	0.00 384	0.00 379	0.00 379	0.00 377	0.00 377

Regformer		0.00 349	0.00 352	0.00 362	0.00 385	0.00 385	0.00 373	0.00 384	0.00 380	0.00 381	0.00 380	0.00 384	0.00 379	0.00 379	0.00 377	0.00 377

testmvs		4.52 347	6.03 350	0.01 361	0.01 383	0.00 385	53.86 341	0.00 384	0.01 378	0.04 379	0.27 378	0.00 384	0.00 379	0.04 377	0.00 377	0.03 376

test123		4.73 346	6.30 349	0.02 360	0.01 383	0.01 384	56.36 334	0.00 384	0.01 378	0.04 379	0.21 379	0.01 383	0.00 379	0.03 378	0.00 377	0.04 375

ab-mvs-re		6.49 345	8.65 348	0.00 362	0.00 385	0.00 385	0.00 373	0.00 384	0.00 380	0.00 381	77.89 255	0.00 384	0.00 379	0.00 379	0.00 377	0.00 377

uanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 385	0.00 373	0.00 384	0.00 380	0.00 381	0.00 380	0.00 384	0.00 379	0.00 379	0.00 377	0.00 377

FOURS1					86.12 36	60.82 37	88.18 1	83.61 62	60.87 82	81.50 16

test_one_0601					87.58 9	59.30 56		86.84 7	65.01 18	83.80 11	91.86 6	64.03 11

eth-test2					0.00 385

eth-test					0.00 385

test_241102_ONE					87.77 4	58.90 68		86.78 10	64.20 29	85.97 1	91.34 12	66.87 3	90.78 7

save fliter					86.17 33	61.30 28	83.98 45	79.66 138	59.00 118

test0726					87.75 7	59.07 63	87.86 4	86.83 8	64.26 27	84.19 7	91.92 5	64.82 8

GSMVS																78.05 255

test_part2					87.58 9	60.47 42				83.42 12

sam_mvs1												34.74 253				78.05 255

sam_mvs												33.43 267

MTGPA								80.97 121

test_post1							68.67 277				3.64 375	32.39 283	69.49 292	44.17 259

test_post											3.55 376	33.90 262	66.52 305

patchmatchnet-post											64.03 344	34.50 255	74.27 271

MTMP							86.03 18	17.08 379

gm-plane-assit					71.40 279	41.72 286			48.85 262		73.31 301		82.48 166	48.90 223

TEST9					85.58 43	61.59 24	81.62 80	81.26 113	55.65 182	74.93 39	88.81 54	53.70 58	84.68 116

test_8					85.40 46	60.96 34	81.54 83	81.18 116	55.86 173	74.81 42	88.80 56	53.70 58	84.45 120

agg_prior					85.04 50	59.96 46		81.04 119		74.68 45			84.04 126

test_prior4						62.51 14	82.08 75

test_prior				76.69 51	84.20 61	57.27 86		84.88 37					86.43 76			86.38 66

旧先验2							76.08 171		45.32 296	76.55 30			65.56 311	58.75 148

新几何2							76.12 169

无先验							79.66 108	74.30 231	48.40 267				80.78 200	53.62 183		79.03 247

原ACMM2							79.02 114

testdata2													72.18 281	46.95 238

segment_acmp												54.23 51

testdata1							72.65 230		60.50 89

plane_prior7					81.41 89	55.96 108

plane_prior6					81.20 96	56.24 103						45.26 156

plane_prior4											86.10 97

plane_prior3						56.09 105			63.92 34	69.27 114

plane_prior2							84.22 38		64.52 23

plane_prior1					81.27 94

n2								0.00 384

nn								0.00 384

door-mid								47.19 358

test11								83.47 66

door								47.60 356

HQP5-MVS						54.94 124

HQP-NCC					80.66 101		82.31 69		62.10 66	67.85 139

ACMP_Plane					80.66 101		82.31 69		62.10 66	67.85 139

BP-MVS														67.04 80

HQP4-MVS										67.85 139			86.93 60			84.32 141

HQP2-MVS												45.46 150

NP-MVS					80.98 99	56.05 107					85.54 113

MDTV_nov1_ep13_2view						25.89 367	61.22 316		40.10 332	51.10 324		32.97 272		38.49 298		78.61 250

Test By Simon												48.33 113

High-resolution multi-view benchmark