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 90	92.83 79	64.03 194	93.06 112	94.33 55	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 16	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 53	72.48 188	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 45	82.43 26	88.90 32	96.35 27	71.89 37	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 63	74.18 151	91.74 12	96.67 21	65.61 75	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 51	88.32 3	85.71 55	94.91 73	74.11 21	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 11	89.33 1	85.77 54	96.26 30	72.84 29	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	90.61 225	93.43 88	84.06 14	86.20 49	90.17 182	72.42 32	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 31	84.83 11	89.07 31	96.80 19	70.86 40	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	65.55 155	95.39 30	95.10 23	71.77 214	85.69 56	96.52 23	62.07 123	98.77 23	86.06 74	95.60 12	96.03 43

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 134	93.00 75	58.16 312	96.72 9	94.41 49	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 47	71.65 218	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 21	80.75 49	95.28 1				92.34 22	95.36 14	96.47 28

test_241102_TWO								94.41 49	71.65 218	92.07 9	97.21 4	74.58 18	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 44	98.91 18	96.83 1	95.06 17	96.76 15

test_0728_THIRD									72.48 188	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 53	85.80 58	86.80 62	91.58 119	67.53 104	91.79 171	93.49 85	74.93 142	84.61 66	95.30 56	59.42 151	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 60	68.77 267	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 43	71.92 204	90.55 20	96.93 11	73.77 23	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 53					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 82	71.87 209	85.52 57	95.33 54	68.19 51	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 61	83.82 16	83.49 76	96.19 32	64.53 89	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 27					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 27					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	90.36 231	93.55 81	82.89 21	91.29 16	92.89 125	72.27 34	96.03 148	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		75.40 136	85.25 63	95.61 45	67.94 54		87.47 59	94.77 26

agg_prior2														86.41 70	94.75 30	95.33 66

MVSMamba_PlusPlus		84.97 75	83.65 85	88.93 14	90.17 151	74.04 8	87.84 283	92.69 118	62.18 323	81.47 96	87.64 220	71.47 39	96.28 133	84.69 86	94.74 31	96.47 28

MVS		84.66 79	82.86 109	90.06 2	90.93 136	74.56 7	87.91 281	95.54 14	68.55 269	72.35 205	94.71 78	59.78 147	98.90 20	81.29 119	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 74	87.30 4	92.15 6	96.15 34	66.38 66	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 70	70.78 242	86.25 47	96.44 26	66.98 60	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 40	84.42 12	86.74 45	96.20 31	66.56 65	98.76 24	89.03 47	94.56 34	95.92 46

3Dnovator	73.91 6	82.69 121	80.82 138	88.31 26	89.57 162	71.26 22	92.60 135	94.39 52	78.84 87	67.89 263	92.48 135	48.42 273	98.52 28	68.80 222	94.40 36	95.15 78

CDPH-MVS		85.71 61	85.46 63	86.46 74	94.75 34	67.19 111	93.89 75	92.83 113	70.90 238	83.09 81	95.28 57	63.62 101	97.36 71	80.63 123	94.18 37	94.84 92

MG-MVS		87.11 34	86.27 46	89.62 8	97.79 1	76.27 4	94.96 43	94.49 45	78.74 90	83.87 75	92.94 123	64.34 90	96.94 107	75.19 162	94.09 38	95.66 52

9.14			87.63 28		93.86 48		94.41 52	94.18 58	72.76 183	86.21 48	96.51 24	66.64 63	97.88 44	90.08 39	94.04 39

原ACMM1				84.42 147	93.21 67	64.27 189		93.40 91	65.39 293	79.51 121	92.50 132	58.11 169	96.69 117	65.27 260	93.96 40	92.32 184

MSLP-MVS++		86.27 49	85.91 56	87.35 45	92.01 105	68.97 66	95.04 40	92.70 116	79.04 85	81.50 94	96.50 25	58.98 160	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 67	86.89 6	89.68 28	95.78 40	65.94 71	99.10 9	92.99 17	93.91 42	96.58 21

MP-MVS-pluss		85.24 69	85.13 68	85.56 103	91.42 124	65.59 153	91.54 181	92.51 127	74.56 145	80.62 107	95.64 44	59.15 155	97.00 97	86.94 67	93.80 43	94.07 131
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MVP-Stereo		77.12 220	76.23 212	79.79 273	81.72 310	66.34 136	89.29 257	90.88 201	70.56 245	62.01 319	82.88 276	49.34 264	94.13 223	65.55 257	93.80 43	78.88 372
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	75.02 375	94.75 34		78.67 136	90.85 168	77.91 7	94.56 207	72.25 188	93.74 45	95.36 65

ZNCC-MVS		85.33 68	85.08 69	86.06 85	93.09 72	65.65 151	93.89 75	93.41 90	73.75 162	79.94 116	94.68 79	60.61 138	98.03 38	82.63 107	93.72 46	94.52 111

CSCG		86.87 36	86.26 47	88.72 17	95.05 31	70.79 29	93.83 82	95.33 17	68.48 271	77.63 144	94.35 91	73.04 27	98.45 30	84.92 84	93.71 47	96.92 14

test12				87.09 52	94.60 36	68.86 67		92.91 110		82.67 88		65.44 76	97.55 62		93.69 48	94.84 92

PAPM		85.89 58	85.46 63	87.18 49	88.20 203	72.42 15	92.41 143	92.77 114	82.11 30	80.34 112	93.07 120	68.27 50	95.02 186	78.39 144	93.59 49	94.09 129

SteuartSystems-ACMMP		86.82 41	86.90 39	86.58 70	90.42 145	66.38 134	96.09 17	93.87 65	77.73 103	84.01 74	95.66 43	63.39 106	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	66.30 137	94.84 45	93.78 67	69.35 258	88.39 33	96.34 28	67.74 56	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 52	87.01 36	83.52 176	92.63 87	59.36 301	95.49 27	91.92 151	80.09 60	85.46 59	95.53 49	61.82 127	95.77 156	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 94	83.86 15	89.55 29	96.06 36	53.55 224	97.89 43	91.10 32	93.31 53	94.54 109

MAR-MVS		84.18 90	83.43 92	86.44 75	96.25 21	65.93 146	94.28 56	94.27 57	74.41 146	79.16 127	95.61 45	53.99 219	98.88 22	69.62 211	93.26 54	94.50 113
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		77.18 218	74.31 239	85.80 95	91.42 124	68.36 79	71.78 380	94.72 35	49.61 380	77.12 151	45.92 406	77.41 8	93.98 235	67.62 232	93.16 55	95.05 83

ZD-MVS					96.63 9	65.50 157		93.50 84	70.74 243	85.26 62	95.19 65	64.92 83	97.29 76	87.51 57	93.01 56

APD-MVS		85.93 56	85.99 54	85.76 97	95.98 26	65.21 162	93.59 93	92.58 125	66.54 285	86.17 50	95.88 39	63.83 96	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				84.73 133	92.32 92	64.28 188		91.46 177	59.56 344	79.77 118	92.90 124	56.95 183	96.57 121	63.40 270	92.91 58	93.34 153

DeepC-MVS	77.85 3	85.52 66	85.24 66	86.37 78	88.80 185	66.64 128	92.15 150	93.68 76	81.07 46	76.91 154	93.64 110	62.59 118	98.44 31	85.50 76	92.84 59	94.03 133
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	93.12 102	83.53 18	89.55 29	95.95 38	53.45 228	97.68 50	91.07 33	92.62 60	94.54 109

MP-MVS		85.02 72	84.97 71	85.17 118	92.60 88	64.27 189	93.24 107	92.27 132	73.13 173	79.63 120	94.43 85	61.90 124	97.17 85	85.00 82	92.56 61	94.06 132
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTAPA		83.91 95	83.38 96	85.50 104	91.89 111	65.16 164	81.75 334	92.23 133	75.32 137	80.53 109	95.21 64	56.06 196	97.16 88	84.86 85	92.55 62	94.18 123

GST-MVS		84.63 80	84.29 79	85.66 101	92.82 81	65.27 160	93.04 114	93.13 101	73.20 171	78.89 129	94.18 98	59.41 152	97.85 45	81.45 115	92.48 63	93.86 141

HFP-MVS		84.73 78	84.40 78	85.72 99	93.75 52	65.01 168	93.50 98	93.19 98	72.19 198	79.22 126	94.93 71	59.04 158	97.67 51	81.55 113	92.21 64	94.49 114

ACMMPR		84.37 82	84.06 80	85.28 113	93.56 58	64.37 184	93.50 98	93.15 100	72.19 198	78.85 134	94.86 74	56.69 187	97.45 65	81.55 113	92.20 65	94.02 134

MS-PatchMatch		77.90 210	76.50 208	82.12 215	85.99 250	69.95 41	91.75 176	92.70 116	73.97 156	62.58 316	84.44 261	41.11 316	95.78 154	63.76 269	92.17 66	80.62 358

region2R		84.36 83	84.03 81	85.36 110	93.54 59	64.31 187	93.43 103	92.95 109	72.16 201	78.86 133	94.84 75	56.97 182	97.53 63	81.38 117	92.11 67	94.24 121

CS-MVS		85.80 59	86.65 44	83.27 184	92.00 106	58.92 305	95.31 31	91.86 156	79.97 61	84.82 65	95.40 52	62.26 121	95.51 174	86.11 73	92.08 68	95.37 63

patch_mono-2		89.71 11	90.99 6	85.85 93	96.04 24	63.70 204	95.04 40	95.19 20	86.74 7	91.53 15	95.15 66	73.86 22	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	90.36 231	90.66 207	79.37 74	81.20 98	93.67 109	74.73 16	96.55 123	90.88 35	92.00 69	95.82 48

旧先验1					91.94 107	60.74 275		91.50 175			94.36 87	65.23 78			91.84 71	94.55 107

MVSFormer		83.75 100	82.88 108	86.37 78	89.24 175	71.18 24	89.07 263	90.69 204	65.80 290	87.13 40	94.34 92	64.99 80	92.67 274	72.83 179	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	92.90 111	82.70 24	87.13 40	95.27 59	64.99 80	95.80 153	89.34 42	91.80 72	95.93 45

EPNet		87.84 24	88.38 20	86.23 82	93.30 64	66.05 141	95.26 32	94.84 30	87.09 5	88.06 34	94.53 82	66.79 62	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	82.10 131	80.60 145	86.60 68	90.89 138	66.80 125	95.20 34	93.44 87	74.05 153	67.42 270	92.49 134	49.46 263	97.65 55	70.80 201	91.68 74	95.33 66

XVS		83.87 96	83.47 90	85.05 120	93.22 65	63.78 198	92.92 119	92.66 120	73.99 154	78.18 138	94.31 94	55.25 202	97.41 68	79.16 135	91.58 76	93.95 136

X-MVStestdata		76.86 224	74.13 243	85.05 120	93.22 65	63.78 198	92.92 119	92.66 120	73.99 154	78.18 138	10.19 421	55.25 202	97.41 68	79.16 135	91.58 76	93.95 136

SD-MVS		87.49 28	87.49 31	87.50 42	93.60 56	68.82 69	93.90 74	92.63 123	76.86 116	87.90 35	95.76 41	66.17 68	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 81	85.04 70	83.01 188	89.34 167	61.37 262	94.42 51	91.09 193	77.91 100	83.24 77	94.20 97	58.37 165	95.40 175	85.35 77	91.41 79	92.27 189

PGM-MVS		83.25 109	82.70 112	84.92 123	92.81 83	64.07 193	90.44 226	92.20 137	71.28 230	77.23 150	94.43 85	55.17 206	97.31 75	79.33 134	91.38 80	93.37 152

PVSNet_Blended		86.73 42	86.86 40	86.31 81	93.76 50	67.53 104	96.33 16	93.61 78	82.34 28	81.00 103	93.08 119	63.19 110	97.29 76	87.08 65	91.38 80	94.13 127

HPM-MVS		83.25 109	82.95 106	84.17 156	92.25 94	62.88 231	90.91 208	91.86 156	70.30 247	77.12 151	93.96 104	56.75 185	96.28 133	82.04 110	91.34 82	93.34 153
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EIA-MVS		84.84 76	84.88 72	84.69 136	91.30 129	62.36 240	93.85 77	92.04 144	79.45 71	79.33 125	94.28 95	62.42 119	96.35 131	80.05 127	91.25 83	95.38 62

MVS_111021_HR		86.19 51	85.80 58	87.37 44	93.17 69	69.79 47	93.99 69	93.76 70	79.08 82	78.88 132	93.99 103	62.25 122	98.15 36	85.93 75	91.15 84	94.15 126

test222					89.77 158	61.60 257	89.55 251	89.42 255	56.83 359	77.28 149	92.43 136	52.76 232			91.14 85	93.09 162

jason		86.40 46	86.17 50	87.11 51	86.16 248	70.54 32	95.71 24	92.19 139	82.00 31	84.58 67	94.34 92	61.86 125	95.53 173	87.76 54	90.89 86	95.27 73
jason: jason.
mPP-MVS		82.96 116	82.44 116	84.52 144	92.83 79	62.92 229	92.76 124	91.85 158	71.52 226	75.61 166	94.24 96	53.48 227	96.99 100	78.97 138	90.73 87	93.64 147

CP-MVS		83.71 101	83.40 95	84.65 138	93.14 70	63.84 196	94.59 49	92.28 131	71.03 236	77.41 147	94.92 72	55.21 205	96.19 137	81.32 118	90.70 88	93.91 138

OpenMVS	70.45 11	78.54 198	75.92 217	86.41 77	85.93 254	71.68 18	92.74 125	92.51 127	66.49 286	64.56 294	91.96 147	43.88 306	98.10 37	54.61 313	90.65 89	89.44 236

PAPM_NR		82.97 115	81.84 123	86.37 78	94.10 44	66.76 126	87.66 287	92.84 112	69.96 251	74.07 182	93.57 112	63.10 113	97.50 64	70.66 204	90.58 90	94.85 89

testdata				81.34 232	89.02 179	57.72 316		89.84 239	58.65 348	85.32 61	94.09 100	57.03 178	93.28 252	69.34 214	90.56 91	93.03 165

mvsmamba		81.55 139	80.72 140	84.03 162	91.42 124	66.93 121	83.08 325	89.13 269	78.55 92	67.50 268	87.02 232	51.79 240	90.07 328	87.48 58	90.49 92	95.10 81

Vis-MVSNet		80.92 151	79.98 154	83.74 167	88.48 190	61.80 251	93.44 102	88.26 304	73.96 157	77.73 142	91.76 152	49.94 258	94.76 194	65.84 252	90.37 93	94.65 103
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CHOSEN 1792x2688		84.98 74	83.45 91	89.57 11	89.94 155	75.14 6	92.07 156	92.32 130	81.87 32	75.68 163	88.27 206	60.18 141	98.60 27	80.46 125	90.27 94	94.96 86

test_fmvsm_n_1920		87.69 26	88.50 19	85.27 114	87.05 232	63.55 211	93.69 87	91.08 195	84.18 13	90.17 24	97.04 8	67.58 57	97.99 39	95.72 5	90.03 95	94.26 119

ETV-MVS		86.01 54	86.11 51	85.70 100	90.21 150	67.02 119	93.43 103	91.92 151	81.21 45	84.13 73	94.07 102	60.93 135	95.63 164	89.28 43	89.81 96	94.46 115

QAPM		79.95 170	77.39 197	87.64 34	89.63 161	71.41 20	93.30 106	93.70 75	65.34 295	67.39 272	91.75 153	47.83 280	98.96 16	57.71 303	89.81 96	92.54 178

CANet_DTU		84.09 92	83.52 86	85.81 94	90.30 148	66.82 123	91.87 167	89.01 276	85.27 9	86.09 51	93.74 107	47.71 282	96.98 101	77.90 147	89.78 98	93.65 146

API-MVS		82.28 126	80.53 146	87.54 41	96.13 22	70.59 31	93.63 91	91.04 199	65.72 292	75.45 168	92.83 128	56.11 195	98.89 21	64.10 266	89.75 99	93.15 160

test2506		83.29 108	82.92 107	84.37 150	88.39 195	63.18 222	92.01 159	91.35 180	77.66 105	78.49 137	91.42 159	64.58 88	95.09 185	73.19 175	89.23 100	94.85 89

ECVR-MVS		81.29 143	80.38 149	84.01 163	88.39 195	61.96 249	92.56 140	86.79 322	77.66 105	76.63 155	91.42 159	46.34 291	95.24 182	74.36 171	89.23 100	94.85 89

MVS_Test		84.16 91	83.20 100	87.05 54	91.56 120	69.82 45	89.99 245	92.05 143	77.77 102	82.84 83	86.57 237	63.93 95	96.09 142	74.91 167	89.18 102	95.25 76

reproduce-ours		83.51 104	83.33 98	84.06 158	92.18 98	60.49 281	90.74 217	92.04 144	64.35 300	83.24 77	95.59 47	59.05 156	97.27 80	83.61 97	89.17 103	94.41 116

our_new_method		83.51 104	83.33 98	84.06 158	92.18 98	60.49 281	90.74 217	92.04 144	64.35 300	83.24 77	95.59 47	59.05 156	97.27 80	83.61 97	89.17 103	94.41 116

PAPR		85.15 71	84.47 76	87.18 49	96.02 25	68.29 81	91.85 169	93.00 108	76.59 123	79.03 128	95.00 68	61.59 128	97.61 58	78.16 145	89.00 105	95.63 53

BP-MVS1		86.54 45	86.68 43	86.13 84	87.80 215	67.18 113	92.97 117	95.62 10	79.92 62	82.84 83	94.14 99	74.95 15	96.46 128	82.91 104	88.96 106	94.74 97

TSAR-MVS + GP.		87.96 21	88.37 21	86.70 65	93.51 61	65.32 159	95.15 36	93.84 66	78.17 96	85.93 53	94.80 76	75.80 13	98.21 34	89.38 41	88.78 107	96.59 19

SR-MVS		82.81 117	82.58 113	83.50 179	93.35 63	61.16 265	92.23 148	91.28 185	64.48 299	81.27 97	95.28 57	53.71 223	95.86 152	82.87 105	88.77 108	93.49 150

test1111		80.84 152	80.02 151	83.33 182	87.87 211	60.76 273	92.62 133	86.86 321	77.86 101	75.73 162	91.39 161	46.35 290	94.70 200	72.79 181	88.68 109	94.52 111

fmvsm_l_conf0.5_n_a		87.44 30	88.15 24	85.30 112	87.10 230	64.19 191	94.41 52	88.14 305	80.24 59	92.54 5	96.97 10	69.52 47	97.17 85	95.89 3	88.51 110	94.56 106

reproduce_model		83.15 111	82.96 104	83.73 169	92.02 102	59.74 293	90.37 230	92.08 142	63.70 307	82.86 82	95.48 50	58.62 162	97.17 85	83.06 103	88.42 111	94.26 119

HPM-MVS_fast		80.25 163	79.55 162	82.33 205	91.55 121	59.95 290	91.32 194	89.16 266	65.23 296	74.71 175	93.07 120	47.81 281	95.74 157	74.87 169	88.23 112	91.31 208

PVSNet_Blended_VisFu		83.97 94	83.50 88	85.39 108	90.02 153	66.59 131	93.77 84	91.73 162	77.43 111	77.08 153	89.81 189	63.77 98	96.97 104	79.67 130	88.21 113	92.60 176

Vis-MVSNet (Re-imp)		79.24 181	79.57 159	78.24 295	88.46 191	52.29 350	90.41 228	89.12 270	74.24 150	69.13 241	91.91 150	65.77 73	90.09 327	59.00 299	88.09 114	92.33 183

fmvsm_l_conf0.5_n		87.49 28	88.19 23	85.39 108	86.95 233	64.37 184	94.30 55	88.45 296	80.51 51	92.70 4	96.86 15	69.98 45	97.15 89	95.83 4	88.08 115	94.65 103

APD-MVS_3200maxsize		81.64 138	81.32 128	82.59 199	92.36 91	58.74 307	91.39 187	91.01 200	63.35 311	79.72 119	94.62 81	51.82 238	96.14 139	79.71 129	87.93 116	92.89 171

RRT-MVS		82.61 122	81.16 129	86.96 57	91.10 133	68.75 70	87.70 286	92.20 137	76.97 114	72.68 194	87.10 231	51.30 247	96.41 130	83.56 99	87.84 117	95.74 50

Effi-MVS+		83.82 97	82.76 110	86.99 56	89.56 163	69.40 53	91.35 192	86.12 330	72.59 185	83.22 80	92.81 129	59.60 149	96.01 150	81.76 112	87.80 118	95.56 56

casdiffmvs_mvg		85.66 63	85.18 67	87.09 52	88.22 202	69.35 58	93.74 86	91.89 154	81.47 37	80.10 114	91.45 158	64.80 85	96.35 131	87.23 63	87.69 119	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		80.70 154	78.95 172	85.94 89	87.77 217	67.56 102	87.91 281	92.55 126	72.17 200	67.44 269	93.09 118	50.27 255	97.04 95	71.68 196	87.64 120	93.23 157

test_fmvsmconf_n		86.58 44	87.17 34	84.82 127	85.28 263	62.55 236	94.26 57	89.78 240	83.81 17	87.78 36	96.33 29	65.33 77	96.98 101	94.40 11	87.55 121	94.95 87

PMMVS		81.98 133	82.04 120	81.78 222	89.76 159	56.17 331	91.13 204	90.69 204	77.96 98	80.09 115	93.57 112	46.33 292	94.99 188	81.41 116	87.46 122	94.17 124

casdiffmvs		85.37 67	84.87 73	86.84 59	88.25 200	69.07 62	93.04 114	91.76 161	81.27 44	80.84 105	92.07 146	64.23 91	96.06 146	84.98 83	87.43 123	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 61	86.08 53	84.62 141	80.83 317	62.33 241	93.84 80	88.81 284	83.50 19	87.00 43	96.01 37	63.36 107	96.93 109	94.04 12	87.29 124	94.61 105

UGNet		79.87 171	78.68 174	83.45 181	89.96 154	61.51 258	92.13 151	90.79 202	76.83 118	78.85 134	86.33 241	38.16 330	96.17 138	67.93 229	87.17 125	92.67 174
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		82.02 132	81.52 126	83.51 178	88.42 193	62.88 231	89.77 248	88.93 280	76.78 119	75.55 167	93.10 117	50.31 254	95.38 177	83.82 96	87.02 126	92.26 190

test_fmvsmvis_n_1920		83.80 98	83.48 89	84.77 131	82.51 303	63.72 202	91.37 190	83.99 352	81.42 41	77.68 143	95.74 42	58.37 165	97.58 59	93.38 14	86.87 127	93.00 167

xiu_mvs_v1_base_debu		82.16 128	81.12 131	85.26 115	86.42 241	68.72 72	92.59 137	90.44 214	73.12 174	84.20 70	94.36 87	38.04 332	95.73 158	84.12 92	86.81 128	91.33 204

xiu_mvs_v1_base		82.16 128	81.12 131	85.26 115	86.42 241	68.72 72	92.59 137	90.44 214	73.12 174	84.20 70	94.36 87	38.04 332	95.73 158	84.12 92	86.81 128	91.33 204

xiu_mvs_v1_base_debi		82.16 128	81.12 131	85.26 115	86.42 241	68.72 72	92.59 137	90.44 214	73.12 174	84.20 70	94.36 87	38.04 332	95.73 158	84.12 92	86.81 128	91.33 204

SR-MVS-dyc-post		81.06 148	80.70 141	82.15 213	92.02 102	58.56 309	90.90 209	90.45 211	62.76 318	78.89 129	94.46 83	51.26 248	95.61 166	78.77 141	86.77 131	92.28 186

RE-MVS-def			80.48 147		92.02 102	58.56 309	90.90 209	90.45 211	62.76 318	78.89 129	94.46 83	49.30 265		78.77 141	86.77 131	92.28 186

baseline		85.01 73	84.44 77	86.71 64	88.33 197	68.73 71	90.24 236	91.82 160	81.05 47	81.18 99	92.50 132	63.69 99	96.08 145	84.45 89	86.71 133	95.32 68

TESTMET0.1,1		82.41 124	81.98 122	83.72 171	88.08 204	63.74 200	92.70 128	93.77 69	79.30 75	77.61 145	87.57 222	58.19 168	94.08 226	73.91 173	86.68 134	93.33 155

IS-MVSNet		80.14 165	79.41 164	82.33 205	87.91 209	60.08 289	91.97 163	88.27 302	72.90 181	71.44 218	91.73 154	61.44 129	93.66 246	62.47 280	86.53 135	93.24 156

CPTT-MVS		79.59 174	79.16 169	80.89 247	91.54 122	59.80 292	92.10 153	88.54 295	60.42 337	72.96 190	93.28 116	48.27 274	92.80 268	78.89 140	86.50 136	90.06 223

BH-w/o		80.49 158	79.30 167	84.05 161	90.83 140	64.36 186	93.60 92	89.42 255	74.35 148	69.09 242	90.15 184	55.23 204	95.61 166	64.61 263	86.43 137	92.17 192

PVSNet	73.49 8	80.05 167	78.63 175	84.31 152	90.92 137	64.97 169	92.47 141	91.05 198	79.18 78	72.43 203	90.51 173	37.05 344	94.06 228	68.06 226	86.00 138	93.90 140

test_fmvsmconf0.01_n		83.70 102	83.52 86	84.25 155	75.26 370	61.72 255	92.17 149	87.24 318	82.36 27	84.91 64	95.41 51	55.60 200	96.83 114	92.85 18	85.87 139	94.21 122

mvs_anonymous		81.36 142	79.99 153	85.46 105	90.39 147	68.40 78	86.88 298	90.61 209	74.41 146	70.31 230	84.67 257	63.79 97	92.32 289	73.13 176	85.70 140	95.67 51

DP-MVS Recon		82.73 118	81.65 125	85.98 87	97.31 4	67.06 116	95.15 36	91.99 148	69.08 264	76.50 158	93.89 105	54.48 214	98.20 35	70.76 202	85.66 141	92.69 173

BH-RMVSNet		79.46 179	77.65 189	84.89 124	91.68 117	65.66 150	93.55 94	88.09 307	72.93 178	73.37 187	91.12 165	46.20 294	96.12 140	56.28 308	85.61 142	92.91 169

UBG		86.83 39	86.70 42	87.20 48	93.07 73	69.81 46	93.43 103	95.56 13	81.52 36	81.50 94	92.12 144	73.58 26	96.28 133	84.37 90	85.20 143	95.51 58

diffmvs		84.28 85	83.83 82	85.61 102	87.40 223	68.02 91	90.88 211	89.24 261	80.54 50	81.64 93	92.52 131	59.83 146	94.52 210	87.32 61	85.11 144	94.29 118
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+		81.14 145	80.01 152	84.51 145	90.24 149	65.86 147	94.12 62	89.15 267	73.81 161	75.37 169	88.26 207	57.26 175	94.53 209	66.97 240	84.92 145	93.15 160

LFMVS		84.34 84	82.73 111	89.18 13	94.76 33	73.25 11	94.99 42	91.89 154	71.90 206	82.16 90	93.49 114	47.98 278	97.05 92	82.55 108	84.82 146	97.25 8

BH-untuned		78.68 194	77.08 200	83.48 180	89.84 156	63.74 200	92.70 128	88.59 293	71.57 224	66.83 279	88.65 200	51.75 241	95.39 176	59.03 298	84.77 147	91.32 207

test-LLR		80.10 166	79.56 160	81.72 224	86.93 236	61.17 263	92.70 128	91.54 172	71.51 227	75.62 164	86.94 233	53.83 220	92.38 284	72.21 189	84.76 148	91.60 198

test-mter		79.96 169	79.38 166	81.72 224	86.93 236	61.17 263	92.70 128	91.54 172	73.85 159	75.62 164	86.94 233	49.84 260	92.38 284	72.21 189	84.76 148	91.60 198

sasdasda		86.85 37	86.25 48	88.66 20	91.80 113	71.92 16	93.54 95	91.71 164	80.26 56	87.55 37	95.25 61	63.59 103	96.93 109	88.18 50	84.34 150	97.11 9

canonicalmvs		86.85 37	86.25 48	88.66 20	91.80 113	71.92 16	93.54 95	91.71 164	80.26 56	87.55 37	95.25 61	63.59 103	96.93 109	88.18 50	84.34 150	97.11 9

alignmvs		87.28 32	86.97 37	88.24 27	91.30 129	71.14 26	95.61 25	93.56 80	79.30 75	87.07 42	95.25 61	68.43 49	96.93 109	87.87 53	84.33 152	96.65 17

VNet		86.20 50	85.65 61	87.84 30	93.92 47	69.99 38	95.73 23	95.94 7	78.43 93	86.00 52	93.07 120	58.22 167	97.00 97	85.22 78	84.33 152	96.52 23

UA-Net		80.02 168	79.65 158	81.11 238	89.33 169	57.72 316	86.33 302	89.00 279	77.44 110	81.01 102	89.15 196	59.33 153	95.90 151	61.01 287	84.28 154	89.73 230

LCM-MVSNet-Re		72.93 273	71.84 272	76.18 317	88.49 189	48.02 373	80.07 352	70.17 393	73.96 157	52.25 363	80.09 321	49.98 257	88.24 341	67.35 233	84.23 155	92.28 186

ACMMP		81.49 140	80.67 142	83.93 164	91.71 116	62.90 230	92.13 151	92.22 136	71.79 213	71.68 214	93.49 114	50.32 253	96.96 105	78.47 143	84.22 156	91.93 196
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 65	85.73 60	85.17 118	91.41 127	62.44 237	92.87 121	91.31 181	79.65 68	86.99 44	95.14 67	62.90 116	96.12 140	87.13 64	84.13 157	96.96 13

114514_t		79.17 182	77.67 188	83.68 173	95.32 29	65.53 156	92.85 122	91.60 171	63.49 309	67.92 260	90.63 171	46.65 287	95.72 162	67.01 239	83.54 158	89.79 228

testing11		86.71 43	86.44 45	87.55 40	93.54 59	71.35 21	93.65 89	95.58 11	81.36 43	80.69 106	92.21 143	72.30 33	96.46 128	85.18 80	83.43 159	94.82 95

test_vis1_n_1920		81.66 137	82.01 121	80.64 249	82.24 305	55.09 339	94.76 46	86.87 320	81.67 35	84.40 69	94.63 80	38.17 329	94.67 201	91.98 27	83.34 160	92.16 193

testing222		85.18 70	84.69 75	86.63 67	92.91 77	69.91 42	92.61 134	95.80 9	80.31 55	80.38 111	92.27 140	68.73 48	95.19 183	75.94 156	83.27 161	94.81 96

EPMVS		78.49 199	75.98 216	86.02 86	91.21 131	69.68 51	80.23 349	91.20 186	75.25 138	72.48 201	78.11 336	54.65 210	93.69 245	57.66 304	83.04 162	94.69 99

AdaColmap		78.94 187	77.00 203	84.76 132	96.34 17	65.86 147	92.66 132	87.97 311	62.18 323	70.56 224	92.37 138	43.53 307	97.35 72	64.50 264	82.86 163	91.05 213

CDS-MVSNet		81.43 141	80.74 139	83.52 176	86.26 245	64.45 178	92.09 154	90.65 208	75.83 130	73.95 184	89.81 189	63.97 94	92.91 264	71.27 197	82.82 164	93.20 159
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CHOSEN 280x420		77.35 216	76.95 204	78.55 290	87.07 231	62.68 235	69.71 386	82.95 359	68.80 266	71.48 217	87.27 228	66.03 70	84.00 370	76.47 154	82.81 165	88.95 237

UWE-MVS		80.81 153	81.01 136	80.20 259	89.33 169	57.05 325	91.91 165	94.71 36	75.67 131	75.01 172	89.37 193	63.13 112	91.44 312	67.19 237	82.80 166	92.12 194

ETVMVS		84.22 89	83.71 83	85.76 97	92.58 89	68.25 85	92.45 142	95.53 15	79.54 70	79.46 122	91.64 156	70.29 43	94.18 222	69.16 217	82.76 167	94.84 92

PCF-MVS	73.15 9	79.29 180	77.63 190	84.29 153	86.06 249	65.96 145	87.03 294	91.10 192	69.86 253	69.79 238	90.64 169	57.54 174	96.59 119	64.37 265	82.29 168	90.32 220
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.5_n		86.39 47	86.91 38	84.82 127	87.36 225	63.54 212	94.74 47	90.02 234	82.52 25	90.14 25	96.92 13	62.93 115	97.84 46	95.28 8	82.26 169	93.07 164

WTY-MVS		86.32 48	85.81 57	87.85 29	92.82 81	69.37 57	95.20 34	95.25 18	82.71 23	81.91 91	94.73 77	67.93 55	97.63 56	79.55 131	82.25 170	96.54 22

testing99		86.01 54	85.47 62	87.63 38	93.62 55	71.25 23	93.47 101	95.23 19	80.42 54	80.60 108	91.95 148	71.73 38	96.50 126	80.02 128	82.22 171	95.13 79

HY-MVS	76.49 5	84.28 85	83.36 97	87.02 55	92.22 95	67.74 97	84.65 309	94.50 44	79.15 79	82.23 89	87.93 215	66.88 61	96.94 107	80.53 124	82.20 172	96.39 33

testing91		85.93 56	85.31 65	87.78 32	93.59 57	71.47 19	93.50 98	95.08 26	80.26 56	80.53 109	91.93 149	70.43 42	96.51 125	80.32 126	82.13 173	95.37 63

VDD-MVS		83.06 113	81.81 124	86.81 61	90.86 139	67.70 98	95.40 29	91.50 175	75.46 134	81.78 92	92.34 139	40.09 319	97.13 90	86.85 68	82.04 174	95.60 54

fmvsm_s_conf0.1_n		85.61 64	85.93 55	84.68 137	82.95 300	63.48 214	94.03 68	89.46 252	81.69 34	89.86 26	96.74 20	61.85 126	97.75 49	94.74 9	82.01 175	92.81 172

TAMVS		80.37 160	79.45 163	83.13 187	85.14 266	63.37 215	91.23 198	90.76 203	74.81 144	72.65 196	88.49 201	60.63 137	92.95 259	69.41 213	81.95 176	93.08 163

test_yl		84.28 85	83.16 101	87.64 34	94.52 37	69.24 59	95.78 18	95.09 24	69.19 261	81.09 100	92.88 126	57.00 180	97.44 66	81.11 121	81.76 177	96.23 38

DCV-MVSNet		84.28 85	83.16 101	87.64 34	94.52 37	69.24 59	95.78 18	95.09 24	69.19 261	81.09 100	92.88 126	57.00 180	97.44 66	81.11 121	81.76 177	96.23 38

FA-MVS(test-final)		79.12 183	77.23 199	84.81 130	90.54 143	63.98 195	81.35 340	91.71 164	71.09 235	74.85 174	82.94 275	52.85 231	97.05 92	67.97 227	81.73 179	93.41 151

thisisatest0515		83.41 106	82.49 115	86.16 83	89.46 166	68.26 83	93.54 95	94.70 37	74.31 149	75.75 161	90.92 166	72.62 30	96.52 124	69.64 209	81.50 180	93.71 144

baseline2		83.68 103	83.42 94	84.48 146	87.37 224	66.00 143	90.06 240	95.93 8	79.71 67	69.08 243	90.39 176	77.92 6	96.28 133	78.91 139	81.38 181	91.16 211

PatchmatchNet		77.46 214	74.63 232	85.96 88	89.55 164	70.35 34	79.97 354	89.55 250	72.23 197	70.94 220	76.91 348	57.03 178	92.79 269	54.27 315	81.17 182	94.74 97
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VDDNet		80.50 157	78.26 180	87.21 47	86.19 246	69.79 47	94.48 50	91.31 181	60.42 337	79.34 124	90.91 167	38.48 327	96.56 122	82.16 109	81.05 183	95.27 73

EPNet_dtu		78.80 191	79.26 168	77.43 303	88.06 205	49.71 365	91.96 164	91.95 150	77.67 104	76.56 157	91.28 163	58.51 163	90.20 325	56.37 307	80.95 184	92.39 181
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		82.71 120	82.38 117	83.73 169	89.25 172	59.58 296	92.24 147	94.89 29	77.96 98	79.86 117	92.38 137	56.70 186	97.05 92	77.26 150	80.86 185	94.55 107

FE-MVS		75.97 240	73.02 256	84.82 127	89.78 157	65.56 154	77.44 365	91.07 196	64.55 298	72.66 195	79.85 323	46.05 295	96.69 117	54.97 312	80.82 186	92.21 191

GeoE		78.90 188	77.43 193	83.29 183	88.95 181	62.02 247	92.31 144	86.23 328	70.24 248	71.34 219	89.27 194	54.43 215	94.04 231	63.31 272	80.81 187	93.81 143

fmvsm_s_conf0.5_n_a		85.75 60	86.09 52	84.72 134	85.73 257	63.58 209	93.79 83	89.32 258	81.42 41	90.21 23	96.91 14	62.41 120	97.67 51	94.48 10	80.56 188	92.90 170

TR-MVS		78.77 193	77.37 198	82.95 189	90.49 144	60.88 269	93.67 88	90.07 230	70.08 250	74.51 176	91.37 162	45.69 296	95.70 163	60.12 293	80.32 189	92.29 185

fmvsm_s_conf0.1_n_a		84.76 77	84.84 74	84.53 143	80.23 327	63.50 213	92.79 123	88.73 287	80.46 52	89.84 27	96.65 22	60.96 134	97.57 61	93.80 13	80.14 190	92.53 179

TAPA-MVS	70.22 12	74.94 255	73.53 251	79.17 284	90.40 146	52.07 351	89.19 261	89.61 249	62.69 320	70.07 232	92.67 130	48.89 272	94.32 214	38.26 379	79.97 191	91.12 212
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_cas_vis1_n_1920		80.45 159	80.61 144	79.97 268	78.25 353	57.01 327	94.04 67	88.33 299	79.06 84	82.81 85	93.70 108	38.65 324	91.63 304	90.82 36	79.81 192	91.27 210

cascas		78.18 203	75.77 219	85.41 107	87.14 229	69.11 61	92.96 118	91.15 190	66.71 284	70.47 225	86.07 243	37.49 338	96.48 127	70.15 207	79.80 193	90.65 216

HyFIR lowres test		81.03 149	79.56 160	85.43 106	87.81 214	68.11 89	90.18 237	90.01 235	70.65 244	72.95 191	86.06 244	63.61 102	94.50 211	75.01 165	79.75 194	93.67 145

WB-MVSnew		77.14 219	76.18 214	80.01 265	86.18 247	63.24 218	91.26 196	94.11 61	71.72 216	73.52 186	87.29 227	45.14 301	93.00 257	56.98 305	79.42 195	83.80 319

LS3D		69.17 303	66.40 308	77.50 301	91.92 109	56.12 332	85.12 306	80.37 367	46.96 387	56.50 349	87.51 223	37.25 339	93.71 244	32.52 396	79.40 196	82.68 339

EI-MVSNet-Vis-set		83.77 99	83.67 84	84.06 158	92.79 84	63.56 210	91.76 174	94.81 32	79.65 68	77.87 141	94.09 100	63.35 108	97.90 42	79.35 133	79.36 197	90.74 215

CVMVSNet		74.04 262	74.27 240	73.33 337	85.33 261	43.94 391	89.53 253	88.39 297	54.33 367	70.37 228	90.13 185	49.17 268	84.05 368	61.83 284	79.36 197	91.99 195

EPP-MVSNet		81.79 135	81.52 126	82.61 198	88.77 186	60.21 287	93.02 116	93.66 77	68.52 270	72.90 192	90.39 176	72.19 35	94.96 189	74.93 166	79.29 199	92.67 174

CLD-MVS		82.73 118	82.35 118	83.86 165	87.90 210	67.65 100	95.45 28	92.18 140	85.06 10	72.58 198	92.27 140	52.46 235	95.78 154	84.18 91	79.06 200	88.16 251
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP3-MVS								91.70 167							78.90 201

HQP-MVS		81.14 145	80.64 143	82.64 197	87.54 219	63.66 207	94.06 63	91.70 167	79.80 64	74.18 178	90.30 178	51.63 243	95.61 166	77.63 148	78.90 201	88.63 242

plane_prior						62.42 238	93.85 77		79.38 73						78.80 203

thres200		79.66 173	78.33 178	83.66 175	92.54 90	65.82 149	93.06 112	96.31 3	74.90 143	73.30 188	88.66 199	59.67 148	95.61 166	47.84 342	78.67 204	89.56 233

ET-MVSNet_ETH3D		84.01 93	83.15 103	86.58 70	90.78 141	70.89 28	94.74 47	94.62 41	81.44 40	58.19 338	93.64 110	73.64 25	92.35 287	82.66 106	78.66 205	96.50 27

HQP_MVS		80.34 161	79.75 157	82.12 215	86.94 234	62.42 238	93.13 110	91.31 181	78.81 88	72.53 199	89.14 197	50.66 251	95.55 171	76.74 151	78.53 206	88.39 248

plane_prior5								91.31 181					95.55 171	76.74 151	78.53 206	88.39 248

EI-MVSNet-UG-set		83.14 112	82.96 104	83.67 174	92.28 93	63.19 221	91.38 189	94.68 38	79.22 77	76.60 156	93.75 106	62.64 117	97.76 48	78.07 146	78.01 208	90.05 224

OMC-MVS		78.67 196	77.91 187	80.95 245	85.76 256	57.40 322	88.49 272	88.67 290	73.85 159	72.43 203	92.10 145	49.29 266	94.55 208	72.73 183	77.89 209	90.91 214

1112_ss		80.56 156	79.83 156	82.77 192	88.65 187	60.78 271	92.29 145	88.36 298	72.58 186	72.46 202	94.95 69	65.09 79	93.42 251	66.38 246	77.71 210	94.10 128

OPM-MVS		79.00 185	78.09 182	81.73 223	83.52 292	63.83 197	91.64 180	90.30 221	76.36 126	71.97 209	89.93 188	46.30 293	95.17 184	75.10 163	77.70 211	86.19 283
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		72.06 283	69.98 286	78.28 293	89.51 165	55.70 335	83.49 317	83.39 357	61.24 332	63.72 304	82.76 277	34.77 352	93.03 256	53.37 320	77.59 212	86.12 287

thres100view900		78.37 200	77.01 202	82.46 200	91.89 111	63.21 220	91.19 202	96.33 1	72.28 196	70.45 227	87.89 216	60.31 139	95.32 178	45.16 353	77.58 213	88.83 238

tfpn200view9		78.79 192	77.43 193	82.88 190	92.21 96	64.49 175	92.05 157	96.28 4	73.48 168	71.75 212	88.26 207	60.07 144	95.32 178	45.16 353	77.58 213	88.83 238

thres400		78.68 194	77.43 193	82.43 201	92.21 96	64.49 175	92.05 157	96.28 4	73.48 168	71.75 212	88.26 207	60.07 144	95.32 178	45.16 353	77.58 213	87.48 258

CostFormer		82.33 125	81.15 130	85.86 92	89.01 180	68.46 77	82.39 331	93.01 106	75.59 132	80.25 113	81.57 295	72.03 36	94.96 189	79.06 137	77.48 216	94.16 125

tpm2		79.80 172	77.95 186	85.34 111	88.28 198	68.26 83	81.56 337	91.42 178	70.11 249	77.59 146	80.50 313	67.40 58	94.26 220	67.34 234	77.35 217	93.51 149

Test_1112_low_res		79.56 175	78.60 176	82.43 201	88.24 201	60.39 284	92.09 154	87.99 309	72.10 202	71.84 210	87.42 224	64.62 87	93.04 255	65.80 253	77.30 218	93.85 142

tpmrst		80.57 155	79.14 170	84.84 126	90.10 152	68.28 82	81.70 335	89.72 247	77.63 107	75.96 160	79.54 327	64.94 82	92.71 271	75.43 160	77.28 219	93.55 148

Anonymous202405211		77.96 207	75.33 225	85.87 91	93.73 53	64.52 174	94.85 44	85.36 337	62.52 321	76.11 159	90.18 181	29.43 373	97.29 76	68.51 224	77.24 220	95.81 49

GA-MVS		78.33 202	76.23 212	84.65 138	83.65 290	66.30 137	91.44 182	90.14 228	76.01 128	70.32 229	84.02 265	42.50 311	94.72 197	70.98 199	77.00 221	92.94 168

thisisatest0530		81.15 144	80.07 150	84.39 149	88.26 199	65.63 152	91.40 185	94.62 41	71.27 231	70.93 221	89.18 195	72.47 31	96.04 147	65.62 255	76.89 222	91.49 200

thres600view7		78.00 205	76.66 207	82.03 220	91.93 108	63.69 205	91.30 195	96.33 1	72.43 191	70.46 226	87.89 216	60.31 139	94.92 192	42.64 365	76.64 223	87.48 258

PLC	68.80 14	75.23 251	73.68 250	79.86 271	92.93 76	58.68 308	90.64 222	88.30 300	60.90 334	64.43 298	90.53 172	42.38 312	94.57 204	56.52 306	76.54 224	86.33 279
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MIMVSNet		71.64 285	68.44 298	81.23 234	81.97 309	64.44 179	73.05 377	88.80 285	69.67 255	64.59 293	74.79 361	32.79 358	87.82 345	53.99 316	76.35 225	91.42 202

test_fmvs1		74.07 261	73.69 249	75.22 321	78.91 345	47.34 378	89.06 265	74.69 381	63.68 308	79.41 123	91.59 157	24.36 383	87.77 347	85.22 78	76.26 226	90.55 219

MVS-HIRNet		60.25 353	55.55 360	74.35 329	84.37 280	56.57 330	71.64 381	74.11 382	34.44 403	45.54 388	42.24 411	31.11 368	89.81 329	40.36 373	76.10 227	76.67 383

CNLPA		74.31 259	72.30 267	80.32 254	91.49 123	61.66 256	90.85 212	80.72 365	56.67 360	63.85 303	90.64 169	46.75 286	90.84 315	53.79 317	75.99 228	88.47 247

ab-mvs		80.18 164	78.31 179	85.80 95	88.44 192	65.49 158	83.00 328	92.67 119	71.82 212	77.36 148	85.01 253	54.50 211	96.59 119	76.35 155	75.63 229	95.32 68

test_fmvs1_n		72.69 280	71.92 271	74.99 324	71.15 383	47.08 380	87.34 292	75.67 376	63.48 310	78.08 140	91.17 164	20.16 395	87.87 344	84.65 87	75.57 230	90.01 225

FIs		79.47 178	79.41 164	79.67 275	85.95 251	59.40 298	91.68 178	93.94 64	78.06 97	68.96 247	88.28 205	66.61 64	91.77 300	66.20 249	74.99 231	87.82 254

SDMVSNet		80.26 162	78.88 173	84.40 148	89.25 172	67.63 101	85.35 305	93.02 105	76.77 120	70.84 222	87.12 229	47.95 279	96.09 142	85.04 81	74.55 232	89.48 234

sd_testset		77.08 221	75.37 223	82.20 211	89.25 172	62.11 246	82.06 332	89.09 272	76.77 120	70.84 222	87.12 229	41.43 315	95.01 187	67.23 236	74.55 232	89.48 234

CMPMVS	48.56 21	66.77 324	64.41 326	73.84 334	70.65 386	50.31 362	77.79 364	85.73 335	45.54 391	44.76 390	82.14 286	35.40 350	90.14 326	63.18 274	74.54 234	81.07 353
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dmvs_re		76.93 223	75.36 224	81.61 226	87.78 216	60.71 276	80.00 353	87.99 309	79.42 72	69.02 245	89.47 192	46.77 285	94.32 214	63.38 271	74.45 235	89.81 227

test_vis1_n		71.63 286	70.73 282	74.31 331	69.63 389	47.29 379	86.91 296	72.11 387	63.21 314	75.18 170	90.17 182	20.40 393	85.76 359	84.59 88	74.42 236	89.87 226

XVG-OURS		74.25 260	72.46 266	79.63 276	78.45 351	57.59 319	80.33 347	87.39 314	63.86 305	68.76 251	89.62 191	40.50 318	91.72 301	69.00 219	74.25 237	89.58 231

tpm cat1		75.30 250	72.21 268	84.58 142	88.52 188	67.77 96	78.16 363	88.02 308	61.88 329	68.45 256	76.37 352	60.65 136	94.03 233	53.77 318	74.11 238	91.93 196

XVG-OURS-SEG-HR		74.70 257	73.08 255	79.57 278	78.25 353	57.33 323	80.49 345	87.32 315	63.22 313	68.76 251	90.12 187	44.89 303	91.59 305	70.55 205	74.09 239	89.79 228

FC-MVSNet-test		77.99 206	78.08 183	77.70 298	84.89 271	55.51 336	90.27 234	93.75 73	76.87 115	66.80 280	87.59 221	65.71 74	90.23 324	62.89 277	73.94 240	87.37 261

PVSNet_BlendedMVS		83.38 107	83.43 92	83.22 185	93.76 50	67.53 104	94.06 63	93.61 78	79.13 80	81.00 103	85.14 252	63.19 110	97.29 76	87.08 65	73.91 241	84.83 311

tttt0517		79.50 176	78.53 177	82.41 204	87.22 227	61.43 261	89.75 249	94.76 33	69.29 259	67.91 261	88.06 214	72.92 28	95.63 164	62.91 276	73.90 242	90.16 222

MDTV_nov1_ep13			72.61 263		89.06 178	68.48 76	80.33 347	90.11 229	71.84 211	71.81 211	75.92 356	53.01 230	93.92 238	48.04 339	73.38 243

SCA		75.82 243	72.76 259	85.01 122	86.63 238	70.08 37	81.06 342	89.19 264	71.60 223	70.01 233	77.09 346	45.53 297	90.25 320	60.43 290	73.27 244	94.68 100

CR-MVSNet		73.79 266	70.82 281	82.70 195	83.15 296	67.96 92	70.25 383	84.00 350	73.67 166	69.97 235	72.41 368	57.82 171	89.48 332	52.99 321	73.13 245	90.64 217

RPMNet		70.42 293	65.68 314	84.63 140	83.15 296	67.96 92	70.25 383	90.45 211	46.83 389	69.97 235	65.10 389	56.48 192	95.30 181	35.79 384	73.13 245	90.64 217

Fast-Effi-MVS+-dtu		75.04 253	73.37 253	80.07 262	80.86 316	59.52 297	91.20 201	85.38 336	71.90 206	65.20 288	84.84 255	41.46 314	92.97 258	66.50 245	72.96 247	87.73 255

LPG-MVS_test		75.82 243	74.58 234	79.56 279	84.31 281	59.37 299	90.44 226	89.73 245	69.49 256	64.86 290	88.42 202	38.65 324	94.30 216	72.56 185	72.76 248	85.01 309

LGP-MVS_train				79.56 279	84.31 281	59.37 299		89.73 245	69.49 256	64.86 290	88.42 202	38.65 324	94.30 216	72.56 185	72.76 248	85.01 309

EG-PatchMatch MVS		68.55 309	65.41 317	77.96 297	78.69 348	62.93 227	89.86 247	89.17 265	60.55 336	50.27 372	77.73 340	22.60 389	94.06 228	47.18 345	72.65 250	76.88 382

EI-MVSNet		78.97 186	78.22 181	81.25 233	85.33 261	62.73 234	89.53 253	93.21 95	72.39 193	72.14 206	90.13 185	60.99 132	94.72 197	67.73 231	72.49 251	86.29 280

MVSTER		82.47 123	82.05 119	83.74 167	92.68 86	69.01 64	91.90 166	93.21 95	79.83 63	72.14 206	85.71 248	74.72 17	94.72 197	75.72 158	72.49 251	87.50 257

Anonymous20240529		76.84 226	74.15 242	84.88 125	91.02 134	64.95 170	93.84 80	91.09 193	53.57 368	73.00 189	87.42 224	35.91 348	97.32 74	69.14 218	72.41 253	92.36 182

D2MVS		73.80 265	72.02 270	79.15 286	79.15 340	62.97 225	88.58 271	90.07 230	72.94 177	59.22 332	78.30 333	42.31 313	92.70 273	65.59 256	72.00 254	81.79 347

PS-MVSNAJss		77.26 217	76.31 211	80.13 261	80.64 321	59.16 303	90.63 224	91.06 197	72.80 182	68.58 254	84.57 259	53.55 224	93.96 236	72.97 177	71.96 255	87.27 265

Effi-MVS+-dtu		76.14 233	75.28 226	78.72 289	83.22 295	55.17 338	89.87 246	87.78 312	75.42 135	67.98 259	81.43 297	45.08 302	92.52 280	75.08 164	71.63 256	88.48 246

ACMMP++_ref															71.63 256

ACMM	69.62 13	74.34 258	72.73 261	79.17 284	84.25 283	57.87 314	90.36 231	89.93 236	63.17 315	65.64 285	86.04 245	37.79 336	94.10 224	65.89 251	71.52 258	85.55 301
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	71.68 10	75.58 248	74.23 241	79.62 277	84.97 270	59.64 294	90.80 214	89.07 274	70.39 246	62.95 312	87.30 226	38.28 328	93.87 241	72.89 178	71.45 259	85.36 305
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
dp		75.01 254	72.09 269	83.76 166	89.28 171	66.22 140	79.96 355	89.75 242	71.16 232	67.80 265	77.19 345	51.81 239	92.54 279	50.39 326	71.44 260	92.51 180

tpm		78.58 197	77.03 201	83.22 185	85.94 253	64.56 173	83.21 324	91.14 191	78.31 94	73.67 185	79.68 325	64.01 93	92.09 294	66.07 250	71.26 261	93.03 165

DP-MVS		69.90 298	66.48 306	80.14 260	95.36 28	62.93 227	89.56 250	76.11 374	50.27 379	57.69 345	85.23 251	39.68 320	95.73 158	33.35 389	71.05 262	81.78 348

UniMVSNet_ETH3D		72.74 277	70.53 284	79.36 281	78.62 350	56.64 329	85.01 307	89.20 263	63.77 306	64.84 292	84.44 261	34.05 355	91.86 298	63.94 267	70.89 263	89.57 232

jajsoiax		73.05 271	71.51 276	77.67 299	77.46 360	54.83 340	88.81 267	90.04 233	69.13 263	62.85 314	83.51 270	31.16 367	92.75 270	70.83 200	69.80 264	85.43 304

ACMMP++															69.72 265

mvs_tets		72.71 278	71.11 277	77.52 300	77.41 361	54.52 342	88.45 273	89.76 241	68.76 268	62.70 315	83.26 273	29.49 372	92.71 271	70.51 206	69.62 266	85.34 306

tpmvs		72.88 275	69.76 291	82.22 210	90.98 135	67.05 117	78.22 362	88.30 300	63.10 316	64.35 299	74.98 359	55.09 207	94.27 218	43.25 359	69.57 267	85.34 306

GBi-Net		75.65 245	73.83 247	81.10 239	88.85 182	65.11 165	90.01 242	90.32 217	70.84 239	67.04 275	80.25 318	48.03 275	91.54 307	59.80 295	69.34 268	86.64 273

test1		75.65 245	73.83 247	81.10 239	88.85 182	65.11 165	90.01 242	90.32 217	70.84 239	67.04 275	80.25 318	48.03 275	91.54 307	59.80 295	69.34 268	86.64 273

FMVSNet3		77.73 211	76.04 215	82.80 191	91.20 132	68.99 65	91.87 167	91.99 148	73.35 170	67.04 275	83.19 274	56.62 188	92.14 291	59.80 295	69.34 268	87.28 264

Syy-MVS		69.65 300	69.52 292	70.03 357	87.87 211	43.21 393	88.07 277	89.01 276	72.91 179	63.11 309	88.10 211	45.28 300	85.54 360	22.07 407	69.23 271	81.32 350

myMVS_eth3d		72.58 282	72.74 260	72.10 349	87.87 211	49.45 367	88.07 277	89.01 276	72.91 179	63.11 309	88.10 211	63.63 100	85.54 360	32.73 394	69.23 271	81.32 350

MSDG		69.54 301	65.73 313	80.96 244	85.11 268	63.71 203	84.19 312	83.28 358	56.95 357	54.50 354	84.03 264	31.50 364	96.03 148	42.87 363	69.13 273	83.14 331

JIA-IIPM		66.06 327	62.45 337	76.88 312	81.42 314	54.45 343	57.49 407	88.67 290	49.36 381	63.86 302	46.86 405	56.06 196	90.25 320	49.53 331	68.83 274	85.95 291

OpenMVS_ROB	61.12 18	66.39 325	62.92 334	76.80 313	76.51 364	57.77 315	89.22 259	83.41 356	55.48 364	53.86 358	77.84 338	26.28 382	93.95 237	34.90 386	68.76 275	78.68 374

FMVSNet2		76.07 234	74.01 245	82.26 209	88.85 182	67.66 99	91.33 193	91.61 170	70.84 239	65.98 283	82.25 284	48.03 275	92.00 296	58.46 300	68.73 276	87.10 267

test_djsdf		73.76 267	72.56 264	77.39 304	77.00 363	53.93 344	89.07 263	90.69 204	65.80 290	63.92 301	82.03 287	43.14 310	92.67 274	72.83 179	68.53 277	85.57 300

F-COLMAP		70.66 290	68.44 298	77.32 305	86.37 244	55.91 333	88.00 279	86.32 325	56.94 358	57.28 347	88.07 213	33.58 356	92.49 281	51.02 324	68.37 278	83.55 321

XVG-ACMP-BASELINE		68.04 315	65.53 316	75.56 319	74.06 375	52.37 349	78.43 359	85.88 332	62.03 326	58.91 336	81.21 305	20.38 394	91.15 314	60.69 289	68.18 279	83.16 330

WBMVS		81.67 136	80.98 137	83.72 171	93.07 73	69.40 53	94.33 54	93.05 104	76.84 117	72.05 208	84.14 263	74.49 19	93.88 240	72.76 182	68.09 280	87.88 253

LTVRE_ROB	59.60 19	66.27 326	63.54 330	74.45 328	84.00 286	51.55 354	67.08 395	83.53 354	58.78 347	54.94 353	80.31 316	34.54 353	93.23 253	40.64 372	68.03 281	78.58 375
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		77.94 208	76.44 209	82.43 201	82.60 302	64.44 179	92.01 159	91.83 159	73.59 167	70.00 234	85.82 246	54.43 215	94.76 194	69.63 210	68.02 282	88.10 252

ADS-MVSNet2		66.90 323	63.44 331	77.26 307	88.06 205	60.70 277	68.01 391	75.56 378	57.57 351	64.48 295	69.87 378	38.68 322	84.10 367	40.87 370	67.89 283	86.97 268

ADS-MVSNet		68.54 310	64.38 327	81.03 243	88.06 205	66.90 122	68.01 391	84.02 349	57.57 351	64.48 295	69.87 378	38.68 322	89.21 334	40.87 370	67.89 283	86.97 268

test0.0.03 1		72.76 276	72.71 262	72.88 341	80.25 326	47.99 374	91.22 199	89.45 253	71.51 227	62.51 317	87.66 219	53.83 220	85.06 364	50.16 328	67.84 285	85.58 299

anonymousdsp		71.14 289	69.37 293	76.45 314	72.95 378	54.71 341	84.19 312	88.88 281	61.92 328	62.15 318	79.77 324	38.14 331	91.44 312	68.90 221	67.45 286	83.21 329

tt0805		73.07 270	70.73 282	80.07 262	78.37 352	57.05 325	87.78 284	92.18 140	61.23 333	67.04 275	86.49 238	31.35 366	94.58 202	65.06 261	67.12 287	88.57 244

VPA-MVSNet		79.03 184	78.00 184	82.11 218	85.95 251	64.48 177	93.22 109	94.66 39	75.05 141	74.04 183	84.95 254	52.17 237	93.52 248	74.90 168	67.04 288	88.32 250

nrg030		80.93 150	79.86 155	84.13 157	83.69 289	68.83 68	93.23 108	91.20 186	75.55 133	75.06 171	88.22 210	63.04 114	94.74 196	81.88 111	66.88 289	88.82 240

FMVSNet1		72.71 278	69.91 289	81.10 239	83.60 291	65.11 165	90.01 242	90.32 217	63.92 304	63.56 305	80.25 318	36.35 347	91.54 307	54.46 314	66.75 290	86.64 273

PatchT		69.11 304	65.37 318	80.32 254	82.07 308	63.68 206	67.96 393	87.62 313	50.86 377	69.37 239	65.18 388	57.09 177	88.53 338	41.59 368	66.60 291	88.74 241

IB-MVS	77.80 4	82.18 127	80.46 148	87.35 45	89.14 177	70.28 35	95.59 26	95.17 22	78.85 86	70.19 231	85.82 246	70.66 41	97.67 51	72.19 191	66.52 292	94.09 129
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		65.78 330	64.84 319	68.60 363	66.54 395	41.71 395	83.27 321	69.81 394	54.38 366	67.91 261	84.54 260	15.35 400	81.22 387	75.65 159	66.16 293	82.88 332

pmmvs5		73.35 268	71.52 275	78.86 288	78.64 349	60.61 280	91.08 205	86.90 319	67.69 274	63.32 307	83.64 268	44.33 305	90.53 317	62.04 282	66.02 294	85.46 303

dmvs_testset		65.55 331	66.45 307	62.86 375	79.87 330	22.35 421	76.55 367	71.74 389	77.42 112	55.85 350	87.77 218	51.39 245	80.69 388	31.51 400	65.92 295	85.55 301

MonoMVSNet		76.99 222	75.08 228	82.73 193	83.32 294	63.24 218	86.47 301	86.37 324	79.08 82	66.31 282	79.30 329	49.80 261	91.72 301	79.37 132	65.70 296	93.23 157

pmmvs4		73.92 264	71.81 273	80.25 258	79.17 339	65.24 161	87.43 290	87.26 317	67.64 277	63.46 306	83.91 267	48.96 271	91.53 310	62.94 275	65.49 297	83.96 316

cl22		77.94 208	76.78 205	81.42 230	87.57 218	64.93 171	90.67 220	88.86 283	72.45 190	67.63 267	82.68 279	64.07 92	92.91 264	71.79 192	65.30 298	86.44 278

miper_ehance_all_eth		77.60 212	76.44 209	81.09 242	85.70 258	64.41 182	90.65 221	88.64 292	72.31 194	67.37 273	82.52 280	64.77 86	92.64 277	70.67 203	65.30 298	86.24 282

miper_enhance_ethall		78.86 189	77.97 185	81.54 228	88.00 208	65.17 163	91.41 183	89.15 267	75.19 139	68.79 250	83.98 266	67.17 59	92.82 266	72.73 183	65.30 298	86.62 277

v1144		76.73 229	74.88 229	82.27 207	80.23 327	66.60 130	91.68 178	90.21 227	73.69 164	69.06 244	81.89 288	52.73 233	94.40 213	69.21 216	65.23 301	85.80 295

DSMNet-mixed		56.78 359	54.44 363	63.79 373	63.21 400	29.44 416	64.43 398	64.10 403	42.12 400	51.32 368	71.60 373	31.76 363	75.04 395	36.23 381	65.20 302	86.87 271

v1192		75.98 239	73.92 246	82.15 213	79.73 331	66.24 139	91.22 199	89.75 242	72.67 184	68.49 255	81.42 298	49.86 259	94.27 218	67.08 238	65.02 303	85.95 291

v2v482		77.42 215	75.65 221	82.73 193	80.38 323	67.13 115	91.85 169	90.23 225	75.09 140	69.37 239	83.39 272	53.79 222	94.44 212	71.77 193	65.00 304	86.63 276

V42		76.46 231	74.55 235	82.19 212	79.14 341	67.82 95	90.26 235	89.42 255	73.75 162	68.63 253	81.89 288	51.31 246	94.09 225	71.69 195	64.84 305	84.66 312

ACMH	63.93 17	68.62 308	64.81 320	80.03 264	85.22 264	63.25 217	87.72 285	84.66 343	60.83 335	51.57 367	79.43 328	27.29 379	94.96 189	41.76 366	64.84 305	81.88 346
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline1		81.84 134	81.03 135	84.28 154	91.60 118	66.62 129	91.08 205	91.66 169	81.87 32	74.86 173	91.67 155	69.98 45	94.92 192	71.76 194	64.75 307	91.29 209

v1240		75.21 252	72.98 257	81.88 221	79.20 338	66.00 143	90.75 216	89.11 271	71.63 222	67.41 271	81.22 303	47.36 283	93.87 241	65.46 258	64.72 308	85.77 296

IterMVS-LS		76.49 230	75.18 227	80.43 253	84.49 277	62.74 233	90.64 222	88.80 285	72.40 192	65.16 289	81.72 291	60.98 133	92.27 290	67.74 230	64.65 309	86.29 280
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		75.63 247	73.49 252	82.06 219	79.38 336	66.35 135	91.07 207	89.48 251	71.98 203	67.99 258	81.22 303	49.16 269	93.90 239	66.56 242	64.56 310	85.92 293

mamv4		65.18 333	67.43 303	58.44 379	77.88 359	49.36 370	69.40 387	70.99 392	48.31 385	57.78 344	85.53 249	59.01 159	51.88 417	73.67 174	64.32 311	74.07 387

v144192		76.05 237	74.03 244	82.12 215	79.50 335	66.55 132	91.39 187	89.71 248	72.30 195	68.17 257	81.33 300	51.75 241	94.03 233	67.94 228	64.19 312	85.77 296

Anonymous20231211		73.08 269	70.39 285	81.13 237	90.62 142	63.33 216	91.40 185	90.06 232	51.84 373	64.46 297	80.67 311	36.49 346	94.07 227	63.83 268	64.17 313	85.98 290

testing3		70.38 294	70.83 279	69.03 361	85.82 255	43.93 392	90.72 219	90.56 210	68.06 272	60.24 326	86.82 235	64.83 84	84.12 366	26.33 402	64.10 314	79.04 371

Patchmatch-test		65.86 328	60.94 343	80.62 251	83.75 288	58.83 306	58.91 406	75.26 380	44.50 394	50.95 371	77.09 346	58.81 161	87.90 343	35.13 385	64.03 315	95.12 80

USDC		67.43 322	64.51 324	76.19 316	77.94 357	55.29 337	78.38 360	85.00 340	73.17 172	48.36 380	80.37 315	21.23 391	92.48 282	52.15 322	64.02 316	80.81 356

VPNet		78.82 190	77.53 192	82.70 195	84.52 276	66.44 133	93.93 72	92.23 133	80.46 52	72.60 197	88.38 204	49.18 267	93.13 254	72.47 187	63.97 317	88.55 245

Anonymous20231206		67.53 320	65.78 312	72.79 342	74.95 371	47.59 376	88.23 275	87.32 315	61.75 331	58.07 340	77.29 343	37.79 336	87.29 353	42.91 361	63.71 318	83.48 324

WR-MVS		76.76 228	75.74 220	79.82 272	84.60 274	62.27 244	92.60 135	92.51 127	76.06 127	67.87 264	85.34 250	56.76 184	90.24 323	62.20 281	63.69 319	86.94 270

h-mvs33		83.01 114	82.56 114	84.35 151	89.34 167	62.02 247	92.72 126	93.76 70	81.45 38	82.73 86	92.25 142	60.11 142	97.13 90	87.69 55	62.96 320	93.91 138

c3_l		76.83 227	75.47 222	80.93 246	85.02 269	64.18 192	90.39 229	88.11 306	71.66 217	66.65 281	81.64 293	63.58 105	92.56 278	69.31 215	62.86 321	86.04 288

test_vis1_rt		59.09 357	57.31 356	64.43 372	68.44 392	46.02 386	83.05 327	48.63 416	51.96 372	49.57 375	63.86 392	16.30 398	80.20 389	71.21 198	62.79 322	67.07 399

mvsany_test1		68.77 307	68.56 296	69.39 359	73.57 376	45.88 387	80.93 343	60.88 407	59.65 343	71.56 215	90.26 180	43.22 309	75.05 394	74.26 172	62.70 323	87.25 266

UniMVSNet_NR-MVSNet		78.15 204	77.55 191	79.98 266	84.46 278	60.26 285	92.25 146	93.20 97	77.50 109	68.88 248	86.61 236	66.10 69	92.13 292	66.38 246	62.55 324	87.54 256

DU-MVS		76.86 224	75.84 218	79.91 269	82.96 298	60.26 285	91.26 196	91.54 172	76.46 125	68.88 248	86.35 239	56.16 193	92.13 292	66.38 246	62.55 324	87.35 262

UniMVSNet (Re)		77.58 213	76.78 205	79.98 266	84.11 284	60.80 270	91.76 174	93.17 99	76.56 124	69.93 237	84.78 256	63.32 109	92.36 286	64.89 262	62.51 326	86.78 272

v8		75.35 249	73.26 254	81.61 226	80.67 320	66.82 123	89.54 252	89.27 260	71.65 218	63.30 308	80.30 317	54.99 208	94.06 228	67.33 235	62.33 327	83.94 317

cl____		76.07 234	74.67 230	80.28 256	85.15 265	61.76 253	90.12 238	88.73 287	71.16 232	65.43 286	81.57 295	61.15 130	92.95 259	66.54 243	62.17 328	86.13 286

v10		74.77 256	72.54 265	81.46 229	80.33 325	66.71 127	89.15 262	89.08 273	70.94 237	63.08 311	79.86 322	52.52 234	94.04 231	65.70 254	62.17 328	83.64 320

DIV-MVS_self_test		76.07 234	74.67 230	80.28 256	85.14 266	61.75 254	90.12 238	88.73 287	71.16 232	65.42 287	81.60 294	61.15 130	92.94 263	66.54 243	62.16 330	86.14 284

IterMVS-SCA-FT		71.55 287	69.97 287	76.32 315	81.48 312	60.67 278	87.64 288	85.99 331	66.17 288	59.50 330	78.88 330	45.53 297	83.65 372	62.58 279	61.93 331	84.63 314

IterMVS		72.65 281	70.83 279	78.09 296	82.17 306	62.96 226	87.64 288	86.28 326	71.56 225	60.44 325	78.85 331	45.42 299	86.66 355	63.30 273	61.83 332	84.65 313
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet5		68.04 315	65.66 315	75.18 323	84.43 279	57.89 313	83.54 316	86.26 327	61.83 330	53.64 359	73.30 364	37.15 342	85.08 363	48.99 334	61.77 333	82.56 341

v7n		71.31 288	68.65 295	79.28 282	76.40 365	60.77 272	86.71 299	89.45 253	64.17 303	58.77 337	78.24 334	44.59 304	93.54 247	57.76 302	61.75 334	83.52 323

v148		76.19 232	74.47 237	81.36 231	80.05 329	64.44 179	91.75 176	90.23 225	73.68 165	67.13 274	80.84 308	55.92 198	93.86 243	68.95 220	61.73 335	85.76 298

tfpnnormal		70.10 295	67.36 304	78.32 292	83.45 293	60.97 268	88.85 266	92.77 114	64.85 297	60.83 323	78.53 332	43.52 308	93.48 249	31.73 397	61.70 336	80.52 359

ACMH+	65.35 16	67.65 318	64.55 323	76.96 311	84.59 275	57.10 324	88.08 276	80.79 364	58.59 349	53.00 360	81.09 307	26.63 381	92.95 259	46.51 347	61.69 337	80.82 355

ITE_SJBPF				70.43 356	74.44 373	47.06 381		77.32 372	60.16 340	54.04 357	83.53 269	23.30 387	84.01 369	43.07 360	61.58 338	80.21 364

NR-MVSNet		76.05 237	74.59 233	80.44 252	82.96 298	62.18 245	90.83 213	91.73 162	77.12 113	60.96 322	86.35 239	59.28 154	91.80 299	60.74 288	61.34 339	87.35 262

test_0402		64.54 336	61.09 342	74.92 325	84.10 285	60.75 274	87.95 280	79.71 369	52.03 371	52.41 362	77.20 344	32.21 362	91.64 303	23.14 405	61.03 340	72.36 393

Baseline_NR-MVSNet		73.99 263	72.83 258	77.48 302	80.78 318	59.29 302	91.79 171	84.55 345	68.85 265	68.99 246	80.70 309	56.16 193	92.04 295	62.67 278	60.98 341	81.11 352

TranMVSNet+NR-MVSNet		75.86 242	74.52 236	79.89 270	82.44 304	60.64 279	91.37 190	91.37 179	76.63 122	67.65 266	86.21 242	52.37 236	91.55 306	61.84 283	60.81 342	87.48 258

testgi		64.48 337	62.87 335	69.31 360	71.24 381	40.62 398	85.49 304	79.92 368	65.36 294	54.18 356	83.49 271	23.74 386	84.55 365	41.60 367	60.79 343	82.77 334

eth_miper_zixun_eth		75.96 241	74.40 238	80.66 248	84.66 273	63.02 224	89.28 258	88.27 302	71.88 208	65.73 284	81.65 292	59.45 150	92.81 267	68.13 225	60.53 344	86.14 284

COLMAP_ROB	57.96 20	62.98 344	59.65 347	72.98 340	81.44 313	53.00 348	83.75 315	75.53 379	48.34 384	48.81 379	81.40 299	24.14 384	90.30 319	32.95 391	60.52 345	75.65 385
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AUN-MVS		78.37 200	77.43 193	81.17 235	86.60 239	57.45 321	89.46 255	91.16 188	74.11 152	74.40 177	90.49 174	55.52 201	94.57 204	74.73 170	60.43 346	91.48 201

hse-mvs2		81.12 147	81.11 134	81.16 236	86.52 240	57.48 320	89.40 256	91.16 188	81.45 38	82.73 86	90.49 174	60.11 142	94.58 202	87.69 55	60.41 347	91.41 203

RPSCF		64.24 338	61.98 340	71.01 355	76.10 367	45.00 388	75.83 372	75.94 375	46.94 388	58.96 335	84.59 258	31.40 365	82.00 384	47.76 343	60.33 348	86.04 288

miper_lstm_enhance		73.05 271	71.73 274	77.03 308	83.80 287	58.32 311	81.76 333	88.88 281	69.80 254	61.01 321	78.23 335	57.19 176	87.51 351	65.34 259	59.53 349	85.27 308

CP-MVSNet		70.50 292	69.91 289	72.26 346	80.71 319	51.00 359	87.23 293	90.30 221	67.84 273	59.64 329	82.69 278	50.23 256	82.30 382	51.28 323	59.28 350	83.46 325

PS-CasMVS		69.86 299	69.13 294	72.07 350	80.35 324	50.57 361	87.02 295	89.75 242	67.27 279	59.19 333	82.28 283	46.58 288	82.24 383	50.69 325	59.02 351	83.39 327

pm-mvs1		72.89 274	71.09 278	78.26 294	79.10 342	57.62 318	90.80 214	89.30 259	67.66 275	62.91 313	81.78 290	49.11 270	92.95 259	60.29 292	58.89 352	84.22 315

Anonymous20240521		62.09 345	59.08 349	71.10 354	67.19 393	48.72 372	83.91 314	85.23 338	50.38 378	47.84 381	71.22 377	20.74 392	85.51 362	46.47 348	58.75 353	79.06 370

WR-MVS_H		70.59 291	69.94 288	72.53 343	81.03 315	51.43 355	87.35 291	92.03 147	67.38 278	60.23 327	80.70 309	55.84 199	83.45 374	46.33 349	58.58 354	82.72 336

reproduce_monomvs		79.49 177	79.11 171	80.64 249	92.91 77	61.47 260	91.17 203	93.28 93	83.09 20	64.04 300	82.38 282	66.19 67	94.57 204	81.19 120	57.71 355	85.88 294

PEN-MVS		69.46 302	68.56 296	72.17 348	79.27 337	49.71 365	86.90 297	89.24 261	67.24 282	59.08 334	82.51 281	47.23 284	83.54 373	48.42 337	57.12 356	83.25 328

EU-MVSNet		64.01 339	63.01 333	67.02 369	74.40 374	38.86 404	83.27 321	86.19 329	45.11 392	54.27 355	81.15 306	36.91 345	80.01 390	48.79 336	57.02 357	82.19 345

AllTest		61.66 346	58.06 351	72.46 344	79.57 332	51.42 356	80.17 350	68.61 396	51.25 375	45.88 384	81.23 301	19.86 396	86.58 356	38.98 376	57.01 358	79.39 367

TestCases				72.46 344	79.57 332	51.42 356		68.61 396	51.25 375	45.88 384	81.23 301	19.86 396	86.58 356	38.98 376	57.01 358	79.39 367

Patchmtry		67.53 320	63.93 328	78.34 291	82.12 307	64.38 183	68.72 388	84.00 350	48.23 386	59.24 331	72.41 368	57.82 171	89.27 333	46.10 350	56.68 360	81.36 349

our_test_3		68.29 313	64.69 322	79.11 287	78.92 343	64.85 172	88.40 274	85.06 339	60.32 339	52.68 361	76.12 354	40.81 317	89.80 331	44.25 358	55.65 361	82.67 340

FPMVS		45.64 371	43.10 375	53.23 388	51.42 413	36.46 406	64.97 397	71.91 388	29.13 408	27.53 408	61.55 397	9.83 410	65.01 411	16.00 414	55.58 362	58.22 404

DTE-MVSNet		68.46 311	67.33 305	71.87 352	77.94 357	49.00 371	86.16 303	88.58 294	66.36 287	58.19 338	82.21 285	46.36 289	83.87 371	44.97 356	55.17 363	82.73 335

MIMVSNet1		60.16 354	57.33 355	68.67 362	69.71 388	44.13 390	78.92 357	84.21 346	55.05 365	44.63 391	71.85 372	23.91 385	81.54 386	32.63 395	55.03 364	80.35 360

pmmvs6		67.57 319	64.76 321	76.00 318	72.82 380	53.37 346	88.71 268	86.78 323	53.19 369	57.58 346	78.03 337	35.33 351	92.41 283	55.56 310	54.88 365	82.21 344

TinyColmap		60.32 352	56.42 359	72.00 351	78.78 346	53.18 347	78.36 361	75.64 377	52.30 370	41.59 398	75.82 357	14.76 403	88.35 340	35.84 382	54.71 366	74.46 386

test20.03		63.83 340	62.65 336	67.38 368	70.58 387	39.94 400	86.57 300	84.17 347	63.29 312	51.86 365	77.30 342	37.09 343	82.47 380	38.87 378	54.13 367	79.73 365

OurMVSNet-221017-0		64.68 335	62.17 339	72.21 347	76.08 368	47.35 377	80.67 344	81.02 363	56.19 361	51.60 366	79.66 326	27.05 380	88.56 337	53.60 319	53.63 368	80.71 357

test_fmvs3		56.82 358	54.86 362	62.69 377	53.59 410	35.47 407	75.87 371	65.64 401	43.91 395	55.10 352	71.43 376	6.91 415	74.40 397	68.64 223	52.63 369	78.20 378

Patchmatch-RL test		68.17 314	64.49 325	79.19 283	71.22 382	53.93 344	70.07 385	71.54 391	69.22 260	56.79 348	62.89 393	56.58 189	88.61 335	69.53 212	52.61 370	95.03 85

ppachtmachnet_test		67.72 317	63.70 329	79.77 274	78.92 343	66.04 142	88.68 269	82.90 360	60.11 341	55.45 351	75.96 355	39.19 321	90.55 316	39.53 374	52.55 371	82.71 337

LF4IMVS		54.01 363	52.12 364	59.69 378	62.41 402	39.91 402	68.59 389	68.28 398	42.96 398	44.55 392	75.18 358	14.09 405	68.39 404	41.36 369	51.68 372	70.78 394

N_pmnet		50.55 366	49.11 368	54.88 385	77.17 362	4.02 429	84.36 310	2.00 427	48.59 382	45.86 386	68.82 381	32.22 361	82.80 379	31.58 398	51.38 373	77.81 380

pmmvs-eth3d		65.53 332	62.32 338	75.19 322	69.39 390	59.59 295	82.80 329	83.43 355	62.52 321	51.30 369	72.49 366	32.86 357	87.16 354	55.32 311	50.73 374	78.83 373

CL-MVSNet_self_test		69.92 297	68.09 301	75.41 320	73.25 377	55.90 334	90.05 241	89.90 237	69.96 251	61.96 320	76.54 349	51.05 249	87.64 348	49.51 332	50.59 375	82.70 338

PM-MVS		59.40 355	56.59 357	67.84 364	63.63 399	41.86 394	76.76 366	63.22 404	59.01 346	51.07 370	72.27 371	11.72 407	83.25 376	61.34 285	50.28 376	78.39 377

MDA-MVSNet_test_wron		63.78 341	60.16 345	74.64 326	78.15 355	60.41 283	83.49 317	84.03 348	56.17 363	39.17 400	71.59 374	37.22 340	83.24 377	42.87 363	48.73 377	80.26 362

YYNet1		63.76 342	60.14 346	74.62 327	78.06 356	60.19 288	83.46 319	83.99 352	56.18 362	39.25 399	71.56 375	37.18 341	83.34 375	42.90 362	48.70 378	80.32 361

KD-MVS_self_test		60.87 350	58.60 350	67.68 366	66.13 396	39.93 401	75.63 374	84.70 342	57.32 355	49.57 375	68.45 383	29.55 371	82.87 378	48.09 338	47.94 379	80.25 363

SixPastTwentyTwo		64.92 334	61.78 341	74.34 330	78.74 347	49.76 364	83.42 320	79.51 370	62.86 317	50.27 372	77.35 341	30.92 369	90.49 318	45.89 351	47.06 380	82.78 333

new_pmnet		49.31 367	46.44 370	57.93 380	62.84 401	40.74 397	68.47 390	62.96 405	36.48 402	35.09 403	57.81 400	14.97 402	72.18 399	32.86 393	46.44 381	60.88 402

EGC-MVSNET		42.35 373	38.09 376	55.11 384	74.57 372	46.62 383	71.63 382	55.77 408	0.04 422	0.24 423	62.70 394	14.24 404	74.91 396	17.59 411	46.06 382	43.80 408

TransMVSNet (Re)		70.07 296	67.66 302	77.31 306	80.62 322	59.13 304	91.78 173	84.94 341	65.97 289	60.08 328	80.44 314	50.78 250	91.87 297	48.84 335	45.46 383	80.94 354

ambc				69.61 358	61.38 405	41.35 396	49.07 412	85.86 334		50.18 374	66.40 386	10.16 409	88.14 342	45.73 352	44.20 384	79.32 369

TDRefinement		55.28 361	51.58 365	66.39 370	59.53 407	46.15 385	76.23 369	72.80 384	44.60 393	42.49 396	76.28 353	15.29 401	82.39 381	33.20 390	43.75 385	70.62 395

Gipuma		34.91 380	31.44 383	45.30 395	70.99 384	39.64 403	19.85 417	72.56 386	20.10 413	16.16 417	21.47 418	5.08 418	71.16 400	13.07 415	43.70 386	25.08 415
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		46.58 369	43.45 373	55.96 382	45.18 417	32.05 411	61.18 401	49.49 415	33.39 404	42.05 397	62.48 395	7.00 414	65.56 409	47.08 346	43.21 387	70.27 396

MDA-MVSNet-bldmvs		61.54 348	57.70 353	73.05 339	79.53 334	57.00 328	83.08 325	81.23 362	57.57 351	34.91 404	72.45 367	32.79 358	86.26 358	35.81 383	41.95 388	75.89 384

new-patchmatchnet		59.30 356	56.48 358	67.79 365	65.86 397	44.19 389	82.47 330	81.77 361	59.94 342	43.65 394	66.20 387	27.67 378	81.68 385	39.34 375	41.40 389	77.50 381

UnsupCasMVSNet_eth		65.79 329	63.10 332	73.88 333	70.71 385	50.29 363	81.09 341	89.88 238	72.58 186	49.25 377	74.77 362	32.57 360	87.43 352	55.96 309	41.04 390	83.90 318

test_vis3_rt		40.46 376	37.79 377	48.47 393	44.49 418	33.35 410	66.56 396	32.84 424	32.39 405	29.65 406	39.13 414	3.91 422	68.65 403	50.17 327	40.99 391	43.40 409

pmmvs3		55.51 360	51.50 366	67.53 367	57.90 408	50.93 360	80.37 346	73.66 383	40.63 401	44.15 393	64.75 390	16.30 398	78.97 391	44.77 357	40.98 392	72.69 391

APD_test1		40.50 375	37.31 378	50.09 391	51.88 411	35.27 408	59.45 405	52.59 412	21.64 411	26.12 409	57.80 401	4.56 419	66.56 407	22.64 406	39.09 393	48.43 407

mvs5depth		61.03 349	57.65 354	71.18 353	67.16 394	47.04 382	72.74 378	77.49 371	57.47 354	60.52 324	72.53 365	22.84 388	88.38 339	49.15 333	38.94 394	78.11 379

UnsupCasMVSNet_bld		61.60 347	57.71 352	73.29 338	68.73 391	51.64 353	78.61 358	89.05 275	57.20 356	46.11 383	61.96 396	28.70 375	88.60 336	50.08 329	38.90 395	79.63 366

PMVS	26.43 22	31.84 383	28.16 386	42.89 396	25.87 426	27.58 417	50.92 411	49.78 414	21.37 412	14.17 418	40.81 413	2.01 425	66.62 406	9.61 418	38.88 396	34.49 414
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
K. test v3		63.09 343	59.61 348	73.53 336	76.26 366	49.38 369	83.27 321	77.15 373	64.35 300	47.77 382	72.32 370	28.73 374	87.79 346	49.93 330	36.69 397	83.41 326

mmtdpeth		68.33 312	66.37 309	74.21 332	82.81 301	51.73 352	84.34 311	80.42 366	67.01 283	71.56 215	68.58 382	30.52 370	92.35 287	75.89 157	36.21 398	78.56 376

kuosan		60.86 351	60.24 344	62.71 376	81.57 311	46.43 384	75.70 373	85.88 332	57.98 350	48.95 378	69.53 380	58.42 164	76.53 392	28.25 401	35.87 399	65.15 400

KD-MVS_2432*1600		69.03 305	66.37 309	77.01 309	85.56 259	61.06 266	81.44 338	90.25 223	67.27 279	58.00 341	76.53 350	54.49 212	87.63 349	48.04 339	35.77 400	82.34 342

miper_refine_blended		69.03 305	66.37 309	77.01 309	85.56 259	61.06 266	81.44 338	90.25 223	67.27 279	58.00 341	76.53 350	54.49 212	87.63 349	48.04 339	35.77 400	82.34 342

mvsany_test3		48.86 368	46.35 371	56.41 381	46.00 416	31.67 412	62.26 400	47.25 417	43.71 396	45.54 388	68.15 384	10.84 408	64.44 413	57.95 301	35.44 402	73.13 390

LCM-MVSNet		40.54 374	35.79 379	54.76 386	36.92 423	30.81 413	51.41 410	69.02 395	22.07 410	24.63 410	45.37 407	4.56 419	65.81 408	33.67 388	34.50 403	67.67 397

test_method		38.59 378	35.16 381	48.89 392	54.33 409	21.35 422	45.32 413	53.71 411	7.41 419	28.74 407	51.62 403	8.70 412	52.87 416	33.73 387	32.89 404	72.47 392

lessismore_v0				73.72 335	72.93 379	47.83 375		61.72 406		45.86 386	73.76 363	28.63 376	89.81 329	47.75 344	31.37 405	83.53 322

testf1		32.77 381	29.47 384	42.67 397	41.89 420	30.81 413	52.07 408	43.45 418	15.45 414	18.52 414	44.82 408	2.12 423	58.38 414	16.05 412	30.87 406	38.83 410

APD_test2		32.77 381	29.47 384	42.67 397	41.89 420	30.81 413	52.07 408	43.45 418	15.45 414	18.52 414	44.82 408	2.12 423	58.38 414	16.05 412	30.87 406	38.83 410

ttmdpeth		53.34 364	49.96 367	63.45 374	62.07 404	40.04 399	72.06 379	65.64 401	42.54 399	51.88 364	77.79 339	13.94 406	76.48 393	32.93 392	30.82 408	73.84 388

PVSNet_0	68.08 15	71.81 284	68.32 300	82.27 207	84.68 272	62.31 243	88.68 269	90.31 220	75.84 129	57.93 343	80.65 312	37.85 335	94.19 221	69.94 208	29.05 409	90.31 221

dongtai		55.18 362	55.46 361	54.34 387	76.03 369	36.88 405	76.07 370	84.61 344	51.28 374	43.41 395	64.61 391	56.56 190	67.81 405	18.09 410	28.50 410	58.32 403

MVStest1		51.35 365	46.89 369	64.74 371	65.06 398	51.10 358	67.33 394	72.58 385	30.20 407	35.30 402	74.82 360	27.70 377	69.89 402	24.44 404	24.57 411	73.22 389

WB-MVS		46.23 370	44.94 372	50.11 390	62.13 403	21.23 423	76.48 368	55.49 409	45.89 390	35.78 401	61.44 398	35.54 349	72.83 398	9.96 417	21.75 412	56.27 405

SSC-MVS		44.51 372	43.35 374	47.99 394	61.01 406	18.90 425	74.12 376	54.36 410	43.42 397	34.10 405	60.02 399	34.42 354	70.39 401	9.14 419	19.57 413	54.68 406

DeepMVS_CX				34.71 400	51.45 412	24.73 420		28.48 426	31.46 406	17.49 416	52.75 402	5.80 417	42.60 421	18.18 409	19.42 414	36.81 413

PMMVS2		37.93 379	33.61 382	50.92 389	46.31 415	24.76 419	60.55 404	50.05 413	28.94 409	20.93 411	47.59 404	4.41 421	65.13 410	25.14 403	18.55 415	62.87 401

MVE	24.84 23	24.35 385	19.77 391	38.09 399	34.56 425	26.92 418	26.57 415	38.87 422	11.73 418	11.37 419	27.44 415	1.37 426	50.42 418	11.41 416	14.60 416	36.93 412
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		24.61 384	24.00 388	26.45 401	43.74 419	18.44 426	60.86 402	39.66 420	15.11 416	9.53 420	22.10 417	6.52 416	46.94 419	8.31 420	10.14 417	13.98 417

EMVS		23.76 386	23.20 390	25.46 402	41.52 422	16.90 427	60.56 403	38.79 423	14.62 417	8.99 421	20.24 420	7.35 413	45.82 420	7.25 421	9.46 418	13.64 418

tmp_tt		22.26 387	23.75 389	17.80 403	5.23 427	12.06 428	35.26 414	39.48 421	2.82 421	18.94 412	44.20 410	22.23 390	24.64 422	36.30 380	9.31 419	16.69 416

ANet_high		40.27 377	35.20 380	55.47 383	34.74 424	34.47 409	63.84 399	71.56 390	48.42 383	18.80 413	41.08 412	9.52 411	64.45 412	20.18 408	8.66 420	67.49 398

wuyk23d		11.30 389	10.95 392	12.33 404	48.05 414	19.89 424	25.89 416	1.92 428	3.58 420	3.12 422	1.37 422	0.64 427	15.77 423	6.23 422	7.77 421	1.35 419

testmvs		7.23 391	9.62 394	0.06 406	0.04 428	0.02 431	84.98 308	0.02 429	0.03 423	0.18 424	1.21 423	0.01 429	0.02 424	0.14 423	0.01 422	0.13 421

mmdepth		0.00 394	0.00 397	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	0.00 425	0.00 430	0.00 426	0.00 425	0.00 423	0.00 422

monomultidepth		0.00 394	0.00 397	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	0.00 425	0.00 430	0.00 426	0.00 425	0.00 423	0.00 422

test_blank		0.00 394	0.00 397	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	0.00 425	0.00 430	0.00 426	0.00 425	0.00 423	0.00 422

uanet_test		0.00 394	0.00 397	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	0.00 425	0.00 430	0.00 426	0.00 425	0.00 423	0.00 422

DCPMVS		0.00 394	0.00 397	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	0.00 425	0.00 430	0.00 426	0.00 425	0.00 423	0.00 422

cdsmvs_eth3d_5k		19.86 388	26.47 387	0.00 407	0.00 430	0.00 432	0.00 418	93.45 86	0.00 425	0.00 426	95.27 59	49.56 262	0.00 426	0.00 425	0.00 423	0.00 422

pcd_1.5k_mvsjas		4.46 393	5.95 396	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	0.00 425	53.55 224	0.00 426	0.00 425	0.00 423	0.00 422

sosnet-low-res		0.00 394	0.00 397	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	0.00 425	0.00 430	0.00 426	0.00 425	0.00 423	0.00 422

sosnet		0.00 394	0.00 397	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	0.00 425	0.00 430	0.00 426	0.00 425	0.00 423	0.00 422

uncertanet		0.00 394	0.00 397	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	0.00 425	0.00 430	0.00 426	0.00 425	0.00 423	0.00 422

Regformer		0.00 394	0.00 397	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	0.00 425	0.00 430	0.00 426	0.00 425	0.00 423	0.00 422

test123		6.92 392	9.21 395	0.08 405	0.03 429	0.05 430	81.65 336	0.01 430	0.02 424	0.14 425	0.85 424	0.03 428	0.02 424	0.12 424	0.00 423	0.16 420

ab-mvs-re		7.91 390	10.55 393	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	94.95 69	0.00 430	0.00 426	0.00 425	0.00 423	0.00 422

uanet		0.00 394	0.00 397	0.00 407	0.00 430	0.00 432	0.00 418	0.00 431	0.00 425	0.00 426	0.00 425	0.00 430	0.00 426	0.00 425	0.00 423	0.00 422

WAC-MVS						49.45 367								31.56 399

FOURS1					93.95 46	61.77 252	93.96 70	91.92 151	62.14 325	86.57 46

test_one_0601					96.32 18	69.74 49		94.18 58	71.42 229	90.67 19	96.85 16	74.45 20

eth-test2					0.00 430

eth-test					0.00 430

test_241102_ONE					96.45 12	69.38 55		94.44 47	71.65 218	92.11 7	97.05 7	76.79 9	99.11 6

save fliter					93.84 49	67.89 94	95.05 39	92.66 120	78.19 95

test0726					96.40 15	69.99 38	96.76 8	94.33 55	71.92 204	91.89 11	97.11 6	73.77 23

GSMVS																94.68 100

test_part2					96.29 19	68.16 88				90.78 17

sam_mvs1												57.85 170				94.68 100

sam_mvs												54.91 209

MTGPA								92.23 133

test_post1							78.95 356				20.70 419	53.05 229	91.50 311	60.43 290

test_post											23.01 416	56.49 191	92.67 274

patchmatchnet-post											67.62 385	57.62 173	90.25 320

MTMP							93.77 84	32.52 425

gm-plane-assit					88.42 193	67.04 118			78.62 91		91.83 151		97.37 70	76.57 153

TEST9					94.18 41	67.28 109	94.16 59	93.51 82	71.75 215	85.52 57	95.33 54	68.01 53	97.27 80

test_8					94.19 40	67.19 111	94.15 61	93.42 89	71.87 209	85.38 60	95.35 53	68.19 51	96.95 106

agg_prior					94.16 43	66.97 120		93.31 92		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		93.10 103					96.84 113			95.05 83

旧先验2							92.00 162		59.37 345	87.54 39			93.47 250	75.39 161

新几何2							91.41 183

无先验							92.71 127	92.61 124	62.03 326				97.01 96	66.63 241		93.97 135

原ACMM2							92.01 159

testdata2													96.09 142	61.26 286

segment_acmp												65.94 71

testdata1							89.21 260		77.55 108

plane_prior7					86.94 234	61.51 258

plane_prior6					87.23 226	62.32 242						50.66 251

plane_prior4											89.14 197

plane_prior3						61.95 250			79.09 81	72.53 199

plane_prior2							93.13 110		78.81 88

plane_prior1					87.15 228

n2								0.00 431

nn								0.00 431

door-mid								66.01 400

test11								93.01 106

door								66.57 399

HQP5-MVS						63.66 207

HQP-NCC					87.54 219		94.06 63		79.80 64	74.18 178

ACMP_Plane					87.54 219		94.06 63		79.80 64	74.18 178

BP-MVS														77.63 148

HQP4-MVS										74.18 178			95.61 166			88.63 242

HQP2-MVS												51.63 243

NP-MVS					87.41 222	63.04 223					90.30 178

MDTV_nov1_ep13_2view						59.90 291	80.13 351		67.65 276	72.79 193		54.33 217		59.83 294		92.58 177

Test By Simon												54.21 218

High-resolution multi-view benchmark