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.

MM		89.16 7	89.23 9	88.97 4	90.79 104	73.65 10	92.66 28	91.17 156	86.57 1	87.39 59	94.97 25	71.70 66	97.68 1	92.19 1	95.63 32	95.57 2

fmvsm_s_conf0.5_n_9		87.39 33	87.95 23	85.70 83	89.48 141	67.88 156	88.59 148	89.05 243	80.19 13	90.70 20	95.40 17	74.56 30	93.92 156	91.54 2	92.07 93	95.31 6

fmvsm_s_conf0.5_n_4		85.39 78	85.75 71	84.30 149	86.70 279	65.83 210	88.77 137	89.78 202	75.46 125	88.35 38	93.73 74	69.19 108	93.06 217	91.30 3	88.44 165	94.02 85

fmvsm_s_conf0.5_n_3		86.36 53	87.46 32	83.09 214	87.08 268	65.21 231	89.09 124	90.21 190	79.67 20	89.98 25	95.02 24	73.17 44	91.71 278	91.30 3	91.60 101	92.34 184

fmvsm_s_conf0.5_n_8		86.56 47	87.17 38	84.73 125	87.76 227	65.62 217	89.20 115	92.21 106	79.94 18	89.74 28	94.86 26	68.63 118	94.20 141	90.83 5	91.39 107	94.38 64

MGCNet		87.69 24	87.55 29	88.12 13	89.45 142	71.76 54	91.47 57	89.54 213	82.14 3	86.65 68	94.28 46	68.28 124	97.46 6	90.81 6	95.31 38	95.15 9

fmvsm_s_conf0.5_n_10		86.38 52	86.76 46	85.24 98	87.33 253	67.30 178	89.50 101	90.98 161	76.25 106	90.56 23	94.75 29	68.38 121	94.24 140	90.80 7	92.32 90	94.19 75

test_fmvsmconf_n		85.92 63	86.04 63	85.57 89	85.03 323	69.51 102	89.62 98	90.58 174	73.42 192	87.75 52	94.02 61	72.85 50	93.24 201	90.37 8	90.75 120	93.96 87

test_fmvsmconf0.1_n		85.61 72	85.65 72	85.50 90	82.99 380	69.39 109	89.65 95	90.29 188	73.31 196	87.77 51	94.15 55	71.72 65	93.23 202	90.31 9	90.67 122	93.89 93

test_fmvsmconf0.01_n		84.73 91	84.52 93	85.34 95	80.25 425	69.03 112	89.47 102	89.65 209	73.24 200	86.98 64	94.27 47	66.62 143	93.23 202	90.26 10	89.95 136	93.78 102

fmvsm_l_conf0.5_n_9		85.84 67	86.63 49	83.46 195	87.12 267	66.01 203	88.56 150	89.43 217	75.59 121	89.32 29	94.32 44	72.89 48	91.21 307	90.11 11	92.33 88	93.16 142

fmvsm_s_conf0.5_n_2		84.04 101	84.11 101	83.81 186	86.17 292	65.00 239	86.96 214	87.28 301	74.35 163	88.25 41	94.23 50	61.82 215	92.60 235	89.85 12	88.09 175	93.84 96

fmvsm_s_conf0.5_n_5		85.22 82	85.55 74	84.25 156	86.26 288	67.40 174	89.18 116	89.31 226	72.50 212	88.31 39	93.86 70	69.66 97	91.96 265	89.81 13	91.05 113	93.38 126

fmvsm_s_conf0.1_n_2		83.80 109	83.79 108	83.83 184	85.62 304	64.94 244	87.03 211	86.62 325	74.32 164	87.97 49	94.33 43	60.67 239	92.60 235	89.72 14	87.79 182	93.96 87

MSC_two_6792asdad				89.16 1	94.34 32	75.53 2		92.99 56					97.53 2	89.67 15	96.44 9	94.41 61

No_MVS				89.16 1	94.34 32	75.53 2		92.99 56					97.53 2	89.67 15	96.44 9	94.41 61

MSP-MVS		89.51 5	89.91 6	88.30 10	94.28 35	73.46 17	92.90 21	94.11 11	80.27 11	91.35 16	94.16 54	78.35 15	96.77 29	89.59 17	94.22 66	94.67 42
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
fmvsm_s_conf0.5_n_6		85.55 73	86.20 56	83.60 190	87.32 255	65.13 234	88.86 131	91.63 139	75.41 126	88.23 42	93.45 82	68.56 119	92.47 243	89.52 18	92.78 80	93.20 139

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 32	71.25 66	95.06 1	94.23 6	78.38 39	92.78 4	95.74 8	82.45 3	97.49 4	89.42 19	96.68 2	94.95 15

test_0728_THIRD									78.38 39	92.12 11	95.78 6	81.46 8	97.40 9	89.42 19	96.57 7	94.67 42

APDe-MVS		89.15 8	89.63 7	87.73 31	94.49 23	71.69 55	93.83 4	93.96 18	75.70 119	91.06 19	96.03 1	76.84 19	97.03 21	89.09 21	95.65 31	94.47 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
fmvsm_s_conf0.5_n_11		86.06 57	86.75 47	84.00 177	87.78 224	66.09 200	89.96 86	90.80 169	77.37 59	86.72 67	94.20 52	72.51 54	92.78 231	89.08 22	92.33 88	93.13 146

DVP-MVS		89.60 4	90.35 4	87.33 45	95.27 5	71.25 66	93.49 10	92.73 72	77.33 60	92.12 11	95.78 6	80.98 10	97.40 9	89.08 22	96.41 12	93.33 130
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				87.71 35	95.34 1	71.43 61	93.49 10	94.23 6					97.49 4	89.08 22	96.41 12	94.21 74

SED-MVS		90.08 2	90.85 2	87.77 28	95.30 2	70.98 74	93.57 8	94.06 15	77.24 65	93.10 1	95.72 10	82.99 1	97.44 7	89.07 25	96.63 4	94.88 19

test_241102_TWO								94.06 15	77.24 65	92.78 4	95.72 10	81.26 9	97.44 7	89.07 25	96.58 6	94.26 73

fmvsm_l_conf0.5_n_3		86.02 58	86.32 53	85.14 101	87.20 259	68.54 132	89.57 99	90.44 179	75.31 130	87.49 56	94.39 42	72.86 49	92.72 232	89.04 27	90.56 124	94.16 76

IU-MVS					95.30 2	71.25 66		92.95 62	66.81 337	92.39 6				88.94 28	96.63 4	94.85 24

fmvsm_l_conf0.5_n		84.47 92	84.54 91	84.27 153	85.42 310	68.81 118	88.49 153	87.26 306	68.08 325	88.03 46	93.49 78	72.04 61	91.77 274	88.90 29	89.14 152	92.24 191

fmvsm_s_conf0.5_n		83.80 109	83.71 110	84.07 166	86.69 280	67.31 177	89.46 103	83.07 380	71.09 243	86.96 65	93.70 75	69.02 114	91.47 295	88.79 30	84.62 246	93.44 125

MP-MVS-pluss		87.67 25	87.72 25	87.54 40	93.64 49	72.04 51	89.80 90	93.50 31	75.17 139	86.34 70	95.29 19	70.86 78	96.00 61	88.78 31	96.04 18	94.58 51
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_fmvsmvis_n_1920		84.02 102	83.87 104	84.49 136	84.12 341	69.37 110	88.15 170	87.96 283	70.01 278	83.95 111	93.23 87	68.80 116	91.51 292	88.61 32	89.96 135	92.57 171

test-260524					94.58 16	71.43 61		94.16 8		90.64 21		78.62 14	97.13 17	88.60 33	96.28 16

SMA-MVS		89.08 9	89.23 9	88.61 6	94.25 36	73.73 9	92.40 29	93.63 27	74.77 153	92.29 7	95.97 2	74.28 35	97.24 15	88.58 34	96.91 1	94.87 21
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
fmvsm_s_conf0.1_n		83.56 121	83.38 119	84.10 160	84.86 325	67.28 179	89.40 109	83.01 381	70.67 257	87.08 62	93.96 67	68.38 121	91.45 296	88.56 35	84.50 247	93.56 118

test_fmvsm_n_1920		85.29 81	85.34 78	85.13 104	86.12 294	69.93 94	88.65 146	90.78 170	69.97 280	88.27 40	93.98 66	71.39 71	91.54 289	88.49 36	90.45 126	93.91 90

CNVR-MVS		88.93 12	89.13 13	88.33 8	94.77 12	73.82 8	90.51 70	93.00 53	80.90 7	88.06 45	94.06 59	76.43 21	96.84 26	88.48 37	95.99 20	94.34 67

fmvsm_l_conf0.5_n_a		84.13 99	84.16 96	84.06 169	85.38 311	68.40 135	88.34 161	86.85 318	67.48 332	87.48 57	93.40 83	70.89 77	91.61 280	88.38 38	89.22 149	92.16 198

fmvsm_s_conf0.5_n_a		83.63 118	83.41 118	84.28 151	86.14 293	68.12 145	89.43 105	82.87 385	70.27 273	87.27 61	93.80 73	69.09 109	91.58 282	88.21 39	83.65 267	93.14 145

aaatest				87.86 27	94.57 18	71.43 61	93.28 12	94.36 3	75.24 131	92.25 9	95.03 22		97.39 11	88.15 40	95.96 21	94.75 35

MED-MVS		89.78 3	90.41 3	87.89 24	94.57 18	71.43 61	93.28 12	94.36 3	77.30 62	92.25 9	95.87 3	81.59 7	97.39 11	88.15 40	96.28 16	94.85 24

aaEdge-Enhanced		88.98 11	89.39 8	87.75 30	94.54 21	71.43 61	91.61 49	94.25 5	76.30 104	90.62 22	95.03 22	78.06 16	97.07 20	88.15 40	95.96 21	94.75 35

fmvsm_s_conf0.1_n_a		83.32 130	82.99 127	84.28 151	83.79 349	68.07 147	89.34 112	82.85 386	69.80 284	87.36 60	94.06 59	68.34 123	91.56 285	87.95 43	83.46 273	93.21 137

TSAR-MVS + MP.		88.02 21	88.11 20	87.72 33	93.68 48	72.13 48	91.41 58	92.35 91	74.62 157	88.90 34	93.85 71	75.75 25	96.00 61	87.80 44	94.63 54	95.04 12
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
ACMMP_NAP		88.05 20	88.08 21	87.94 19	93.70 46	73.05 22	90.86 65	93.59 29	76.27 105	88.14 43	95.09 21	71.06 76	96.67 34	87.67 45	96.37 14	94.09 81

SD-MVS		88.06 18	88.50 18	86.71 61	92.60 77	72.71 29	91.81 46	93.19 42	77.87 44	90.32 24	94.00 63	74.83 28	93.78 164	87.63 46	94.27 65	93.65 111
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
SteuartSystems-ACMMP		88.72 14	88.86 14	88.32 9	92.14 80	72.96 25	93.73 5	93.67 26	80.19 13	88.10 44	94.80 27	73.76 39	97.11 18	87.51 47	95.82 25	94.90 18
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS++		89.02 10	89.15 12	88.63 5	95.01 9	76.03 1	92.38 32	92.85 66	80.26 12	87.78 50	94.27 47	75.89 24	96.81 28	87.45 48	96.44 9	93.05 152

DPE-MVS		89.48 6	89.98 5	88.01 16	94.80 11	72.69 31	91.59 51	94.10 13	75.90 112	92.29 7	95.66 12	81.67 6	97.38 13	87.44 49	96.34 15	93.95 89
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SF-MVS		88.46 15	88.74 15	87.64 39	92.78 72	71.95 52	92.40 29	94.74 2	75.71 117	89.16 30	95.10 20	75.65 26	96.19 53	87.07 50	96.01 19	94.79 28

lecture		88.09 17	88.59 16	86.58 63	93.26 57	69.77 98	93.70 6	94.16 8	77.13 70	89.76 27	95.52 16	72.26 56	96.27 50	86.87 51	94.65 52	93.70 105

9.14			88.26 19		92.84 71		91.52 56	94.75 1	73.93 177	88.57 37	94.67 30	75.57 27	95.79 65	86.77 52	95.76 27

MTAPA		87.23 36	87.00 39	87.90 22	94.18 40	74.25 5	86.58 233	92.02 115	79.45 23	85.88 72	94.80 27	68.07 126	96.21 52	86.69 53	95.34 36	93.23 134

fmvsm_s_conf0.5_n_7		83.34 128	84.03 102	81.28 278	85.73 301	65.13 234	85.40 274	89.90 200	74.96 146	82.13 149	93.89 69	66.65 142	87.92 382	86.56 54	91.05 113	90.80 241

reproduce-ours		87.47 27	87.61 27	87.07 51	93.27 55	71.60 56	91.56 54	93.19 42	74.98 144	88.96 31	95.54 14	71.20 74	96.54 42	86.28 55	93.49 71	93.06 150

our_new_method		87.47 27	87.61 27	87.07 51	93.27 55	71.60 56	91.56 54	93.19 42	74.98 144	88.96 31	95.54 14	71.20 74	96.54 42	86.28 55	93.49 71	93.06 150

reproduce_model		87.28 35	87.39 33	86.95 55	93.10 63	71.24 71	91.60 50	93.19 42	74.69 154	88.80 35	95.61 13	70.29 85	96.44 45	86.20 57	93.08 75	93.16 142

TestfortrainingZip a		88.83 13	89.21 11	87.68 37	94.57 18	71.25 66	93.28 12	93.91 20	77.30 62	91.13 18	95.87 3	77.62 17	96.95 23	86.12 58	93.07 76	94.85 24

DeepPCF-MVS	80.84 1	88.10 16	88.56 17	86.73 60	92.24 79	69.03 112	89.57 99	93.39 36	77.53 55	89.79 26	94.12 56	78.98 13	96.58 41	85.66 59	95.72 28	94.58 51

MP-MVS		87.71 23	87.64 26	87.93 21	94.36 31	73.88 6	92.71 27	92.65 78	77.57 51	83.84 113	94.40 41	72.24 57	96.28 49	85.65 60	95.30 39	93.62 114
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
BridgeMVS		86.78 42	86.99 40	86.15 72	91.24 92	67.61 165	90.51 70	92.90 63	77.26 64	87.44 58	91.63 139	71.27 73	96.06 56	85.62 61	95.01 41	94.78 29

ZNCC-MVS		87.94 22	87.85 24	88.20 12	94.39 29	73.33 19	93.03 19	93.81 23	76.81 80	85.24 79	94.32 44	71.76 64	96.93 24	85.53 62	95.79 26	94.32 69

HPM-MVS		87.11 38	86.98 41	87.50 43	93.88 44	72.16 47	92.19 38	93.33 37	76.07 109	83.81 114	93.95 68	69.77 96	96.01 60	85.15 63	94.66 51	94.32 69
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
train_agg		86.43 49	86.20 56	87.13 50	93.26 57	72.96 25	88.75 139	91.89 123	68.69 316	85.00 82	93.10 89	74.43 32	95.41 83	84.97 64	95.71 29	93.02 154

test9_res														84.90 65	95.70 30	92.87 161

NCCC		88.06 18	88.01 22	88.24 11	94.41 27	73.62 11	91.22 62	92.83 67	81.50 5	85.79 74	93.47 81	73.02 47	97.00 22	84.90 65	94.94 44	94.10 80

MCST-MVS		87.37 34	87.25 35	87.73 31	94.53 22	72.46 40	89.82 88	93.82 22	73.07 204	84.86 87	92.89 96	76.22 22	96.33 47	84.89 67	95.13 40	94.40 63

DeepC-MVS	79.81 2	87.08 40	86.88 45	87.69 36	91.16 93	72.32 45	90.31 79	93.94 19	77.12 71	82.82 139	94.23 50	72.13 60	97.09 19	84.83 68	95.37 35	93.65 111
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS		86.73 43	86.67 48	86.91 56	94.11 42	72.11 49	92.37 33	92.56 83	74.50 158	86.84 66	94.65 31	67.31 134	95.77 66	84.80 69	92.85 79	92.84 164

MVSMamba_PlusPlus		85.99 60	85.96 65	86.05 75	91.09 94	67.64 164	89.63 97	92.65 78	72.89 209	84.64 93	91.71 134	71.85 62	96.03 57	84.77 70	94.45 60	94.49 59

ZD-MVS					94.38 30	72.22 46		92.67 75	70.98 248	87.75 52	94.07 58	74.01 38	96.70 32	84.66 71	94.84 48

PC_three_1452									68.21 324	92.02 14	94.00 63	82.09 5	95.98 63	84.58 72	96.68 2	94.95 15

HFP-MVS		87.58 26	87.47 31	87.94 19	94.58 16	73.54 15	93.04 17	93.24 40	76.78 82	84.91 84	94.44 39	70.78 79	96.61 38	84.53 73	94.89 46	93.66 107

ACMMPR		87.44 29	87.23 36	88.08 15	94.64 13	73.59 12	93.04 17	93.20 41	76.78 82	84.66 92	94.52 32	68.81 115	96.65 36	84.53 73	94.90 45	94.00 86

region2R		87.42 31	87.20 37	88.09 14	94.63 14	73.55 13	93.03 19	93.12 47	76.73 85	84.45 97	94.52 32	69.09 109	96.70 32	84.37 75	94.83 49	94.03 84

CANet		86.45 48	86.10 61	87.51 42	90.09 117	70.94 78	89.70 94	92.59 82	81.78 4	81.32 164	91.43 149	70.34 83	97.23 16	84.26 76	93.36 74	94.37 65

APD-MVS		87.44 29	87.52 30	87.19 48	94.24 37	72.39 41	91.86 45	92.83 67	73.01 206	88.58 36	94.52 32	73.36 40	96.49 44	84.26 76	95.01 41	92.70 166
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CS-MVS		86.69 44	86.95 42	85.90 80	90.76 105	67.57 167	92.83 22	93.30 39	79.67 20	84.57 96	92.27 110	71.47 69	95.02 104	84.24 78	93.46 73	95.13 11

CP-MVS		87.11 38	86.92 43	87.68 37	94.20 39	73.86 7	93.98 3	92.82 70	76.62 88	83.68 116	94.46 36	67.93 127	95.95 64	84.20 79	94.39 61	93.23 134

GST-MVS		87.42 31	87.26 34	87.89 24	94.12 41	72.97 24	92.39 31	93.43 34	76.89 78	84.68 89	93.99 65	70.67 81	96.82 27	84.18 80	95.01 41	93.90 92

BP-MVS1		84.32 93	83.71 110	86.17 70	87.84 219	67.85 157	89.38 110	89.64 210	77.73 47	83.98 110	92.12 121	56.89 277	95.43 80	84.03 81	91.75 100	95.24 8

EC-MVSNet		86.01 59	86.38 52	84.91 116	89.31 151	66.27 198	92.32 35	93.63 27	79.37 24	84.17 106	91.88 126	69.04 113	95.43 80	83.93 82	93.77 69	93.01 155

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 61	82.45 3	96.87 25	83.77 83	96.48 8	94.88 19

casdiffmvs_mvg		85.99 60	86.09 62	85.70 83	87.65 235	67.22 183	88.69 144	93.04 48	79.64 22	85.33 78	92.54 106	73.30 41	94.50 129	83.49 84	91.14 112	95.37 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
dcpmvs_2		85.63 71	86.15 60	84.06 169	91.71 86	64.94 244	86.47 237	91.87 125	73.63 184	86.60 69	93.02 94	76.57 20	91.87 272	83.36 85	92.15 91	95.35 4

test_prior2							88.85 133		75.41 126	84.91 84	93.54 76	74.28 35		83.31 86	95.86 24

PHI-MVS		86.43 49	86.17 59	87.24 47	90.88 101	70.96 76	92.27 37	94.07 14	72.45 213	85.22 80	91.90 125	69.47 99	96.42 46	83.28 87	95.94 23	94.35 66

XVS		87.18 37	86.91 44	88.00 17	94.42 25	73.33 19	92.78 23	92.99 56	79.14 27	83.67 117	94.17 53	67.45 132	96.60 39	83.06 88	94.50 57	94.07 82

X-MVStestdata		80.37 208	77.83 248	88.00 17	94.42 25	73.33 19	92.78 23	92.99 56	79.14 27	83.67 117	12.47 533	67.45 132	96.60 39	83.06 88	94.50 57	94.07 82

balanced_ft_v1		83.98 105	83.64 113	85.03 107	89.76 130	65.86 209	88.31 163	91.71 135	74.41 162	80.41 188	90.82 172	62.90 196	94.90 108	83.04 90	91.37 108	94.32 69

APD-MVS_3200maxsize		85.97 62	85.88 66	86.22 69	92.69 74	69.53 101	91.93 42	92.99 56	73.54 188	85.94 71	94.51 35	65.80 160	95.61 69	83.04 90	92.51 84	93.53 121

agg_prior2														82.91 92	95.45 33	92.70 166

mPP-MVS		86.67 46	86.32 53	87.72 33	94.41 27	73.55 13	92.74 25	92.22 104	76.87 79	82.81 140	94.25 49	66.44 147	96.24 51	82.88 93	94.28 64	93.38 126

Casviewmamba		86.09 56	86.04 63	86.24 67	88.17 200	68.05 149	89.44 104	92.79 71	80.30 10	84.71 88	92.78 103	72.83 51	95.05 102	82.81 94	90.57 123	95.62 1

diffmvs_AUTHOR		82.38 147	82.27 143	82.73 240	83.26 364	63.80 275	83.89 319	89.76 204	73.35 195	82.37 144	90.84 170	66.25 150	90.79 326	82.77 95	87.93 180	93.59 116

SR-MVS-dyc-post		85.77 68	85.61 73	86.23 68	93.06 65	70.63 84	91.88 43	92.27 97	73.53 189	85.69 75	94.45 37	65.00 169	95.56 71	82.75 96	91.87 97	92.50 177

RE-MVS-def			85.48 76		93.06 65	70.63 84	91.88 43	92.27 97	73.53 189	85.69 75	94.45 37	63.87 179		82.75 96	91.87 97	92.50 177

h-mvs33		83.15 133	82.19 144	86.02 78	90.56 107	70.85 81	88.15 170	89.16 237	76.02 110	84.67 90	91.39 150	61.54 220	95.50 76	82.71 98	75.48 381	91.72 211

hse-mvs2		81.72 162	80.94 168	84.07 166	88.72 180	67.68 163	85.87 259	87.26 306	76.02 110	84.67 90	88.22 257	61.54 220	93.48 189	82.71 98	73.44 409	91.06 231

PGM-MVS		86.68 45	86.27 55	87.90 22	94.22 38	73.38 18	90.22 81	93.04 48	75.53 122	83.86 112	94.42 40	67.87 129	96.64 37	82.70 100	94.57 56	93.66 107

ACMMP		85.89 66	85.39 77	87.38 44	93.59 50	72.63 33	92.74 25	93.18 46	76.78 82	80.73 180	93.82 72	64.33 175	96.29 48	82.67 101	90.69 121	93.23 134
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
diffmvs		82.10 153	81.88 154	82.76 238	83.00 376	63.78 277	83.68 324	89.76 204	72.94 207	82.02 151	89.85 201	65.96 159	90.79 326	82.38 102	87.30 192	93.71 104
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
patch_mono-2		83.65 116	84.54 91	80.99 287	90.06 122	65.83 210	84.21 311	88.74 262	71.60 231	85.01 81	92.44 108	74.51 31	83.50 429	82.15 103	92.15 91	93.64 113

SPE-MVS-test		86.29 54	86.48 51	85.71 82	91.02 97	67.21 184	92.36 34	93.78 24	78.97 34	83.51 124	91.20 157	70.65 82	95.15 94	81.96 104	94.89 46	94.77 30

TSAR-MVS + GP.		85.71 70	85.33 79	86.84 57	91.34 90	72.50 36	89.07 125	87.28 301	76.41 96	85.80 73	90.22 196	74.15 37	95.37 88	81.82 105	91.88 96	92.65 170

alignmvs		85.48 74	85.32 80	85.96 79	89.51 137	69.47 104	89.74 92	92.47 84	76.17 107	87.73 54	91.46 148	70.32 84	93.78 164	81.51 106	88.95 153	94.63 48

sasdasda		85.91 64	85.87 68	86.04 76	89.84 127	69.44 107	90.45 76	93.00 53	76.70 86	88.01 47	91.23 153	73.28 42	93.91 157	81.50 107	88.80 156	94.77 30

canonicalmvs		85.91 64	85.87 68	86.04 76	89.84 127	69.44 107	90.45 76	93.00 53	76.70 86	88.01 47	91.23 153	73.28 42	93.91 157	81.50 107	88.80 156	94.77 30

viewmamba		82.38 147	82.11 145	83.19 209	83.30 362	64.26 265	84.62 296	89.16 237	75.24 131	80.97 173	91.10 160	67.12 137	91.63 279	81.36 109	86.13 217	93.67 106

baseline		84.93 88	84.98 85	84.80 122	87.30 257	65.39 224	87.30 204	92.88 64	77.62 49	84.04 109	92.26 111	71.81 63	93.96 149	81.31 110	90.30 128	95.03 13

MGCFI-Net		85.06 87	85.51 75	83.70 188	89.42 143	63.01 301	89.43 105	92.62 81	76.43 95	87.53 55	91.34 151	72.82 52	93.42 194	81.28 111	88.74 159	94.66 45

casdiffmvs		85.11 84	85.14 84	85.01 109	87.20 259	65.77 214	87.75 184	92.83 67	77.84 45	84.36 102	92.38 109	72.15 59	93.93 155	81.27 112	90.48 125	95.33 5
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PRO-TEST		82.16 152	82.06 149	82.45 247	89.49 140	58.24 379	84.07 318	91.34 150	75.05 141	73.21 341	90.55 183	62.05 211	95.60 70	81.23 113	91.56 104	93.51 123

MVS_111021_HR		85.14 83	84.75 89	86.32 66	91.65 87	72.70 30	85.98 255	90.33 185	76.11 108	82.08 150	91.61 142	71.36 72	94.17 144	81.02 114	92.58 83	92.08 200

HPM-MVS_fast		85.35 80	84.95 87	86.57 64	93.69 47	70.58 86	92.15 40	91.62 140	73.89 178	82.67 143	94.09 57	62.60 198	95.54 73	80.93 115	92.93 78	93.57 117

CPTT-MVS		83.73 113	83.33 121	84.92 115	93.28 54	70.86 80	92.09 41	90.38 181	68.75 315	79.57 198	92.83 98	60.60 243	93.04 220	80.92 116	91.56 104	90.86 240

ETV-MVS		84.90 90	84.67 90	85.59 88	89.39 146	68.66 129	88.74 141	92.64 80	79.97 17	84.10 107	85.71 326	69.32 102	95.38 85	80.82 117	91.37 108	92.72 165

DeepC-MVS_fast	79.65 3	86.91 41	86.62 50	87.76 29	93.52 51	72.37 43	91.26 59	93.04 48	76.62 88	84.22 104	93.36 85	71.44 70	96.76 30	80.82 117	95.33 37	94.16 76
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
nrg030		83.88 107	83.53 116	84.96 111	86.77 277	69.28 111	90.46 75	92.67 75	74.79 152	82.95 134	91.33 152	72.70 53	93.09 215	80.79 119	79.28 330	92.50 177

NormalMVS		86.29 54	85.88 66	87.52 41	93.26 57	72.47 38	91.65 47	92.19 109	79.31 25	84.39 99	92.18 116	64.64 172	95.53 74	80.70 120	94.65 52	94.56 55

SymmetryMVS		85.38 79	84.81 88	87.07 51	91.47 89	72.47 38	91.65 47	88.06 279	79.31 25	84.39 99	92.18 116	64.64 172	95.53 74	80.70 120	90.91 118	93.21 137

EI-MVSNet-Vis-set		84.19 98	83.81 107	85.31 96	88.18 199	67.85 157	87.66 186	89.73 207	80.05 16	82.95 134	89.59 214	70.74 80	94.82 113	80.66 122	84.72 244	93.28 132

hybridcas		85.11 84	85.18 83	84.90 117	87.47 247	65.68 215	88.53 152	92.38 89	77.91 43	84.27 103	92.48 107	72.19 58	93.88 161	80.37 123	90.97 115	95.15 9

MSLP-MVS++		85.43 76	85.76 70	84.45 137	91.93 83	70.24 87	90.71 67	92.86 65	77.46 57	84.22 104	92.81 100	67.16 136	92.94 222	80.36 124	94.35 63	90.16 270

hybridnocas07		81.44 174	81.13 163	82.37 250	82.13 398	63.11 300	83.45 333	88.74 262	72.54 211	80.71 181	90.73 173	65.14 165	90.74 331	80.35 125	86.41 210	93.27 133

onestephybrid01		82.22 150	81.81 156	83.46 195	83.16 370	64.93 247	84.64 295	89.19 236	73.95 174	81.48 162	90.63 178	66.00 158	91.92 269	80.33 126	86.93 199	93.53 121

MVS_111021_LR		82.61 144	82.11 145	84.11 159	88.82 170	71.58 58	85.15 279	86.16 333	74.69 154	80.47 187	91.04 164	62.29 205	90.55 334	80.33 126	90.08 133	90.20 269

DELS-MVS		85.41 77	85.30 81	85.77 81	88.49 187	67.93 155	85.52 273	93.44 33	78.70 35	83.63 119	89.03 229	74.57 29	95.71 68	80.26 128	94.04 67	93.66 107
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
GDP-MVS		83.52 122	82.64 134	86.16 71	88.14 203	68.45 134	89.13 122	92.69 73	72.82 210	83.71 115	91.86 128	55.69 286	95.35 89	80.03 129	89.74 140	94.69 37

EI-MVSNet-UG-set		83.81 108	83.38 119	85.09 106	87.87 217	67.53 169	87.44 199	89.66 208	79.74 19	82.23 147	89.41 223	70.24 86	94.74 119	79.95 130	83.92 259	92.99 157

CSCG		86.41 51	86.19 58	87.07 51	92.91 68	72.48 37	90.81 66	93.56 30	73.95 174	83.16 131	91.07 163	75.94 23	95.19 92	79.94 131	94.38 62	93.55 119

E5new		84.22 94	84.12 97	84.51 132	87.60 237	65.36 226	87.45 194	92.31 93	76.51 91	83.53 120	92.26 111	69.25 106	93.50 184	79.88 132	88.26 167	94.69 37

E6new		84.22 94	84.12 97	84.52 130	87.60 237	65.36 226	87.45 194	92.30 95	76.51 91	83.53 120	92.26 111	69.26 104	93.49 186	79.88 132	88.26 167	94.69 37

E6		84.22 94	84.12 97	84.52 130	87.60 237	65.36 226	87.45 194	92.30 95	76.51 91	83.53 120	92.26 111	69.26 104	93.49 186	79.88 132	88.26 167	94.69 37

E5		84.22 94	84.12 97	84.51 132	87.60 237	65.36 226	87.45 194	92.31 93	76.51 91	83.53 120	92.26 111	69.25 106	93.50 184	79.88 132	88.26 167	94.69 37

RRT-MVS		82.60 146	82.10 147	84.10 160	87.98 213	62.94 307	87.45 194	91.27 152	77.42 58	79.85 194	90.28 192	56.62 280	94.70 122	79.87 136	88.15 173	94.67 42

E4		84.10 100	83.99 103	84.45 137	87.58 245	64.99 240	86.54 235	92.25 100	76.38 100	83.37 125	92.09 122	69.88 94	93.58 173	79.78 137	88.03 178	94.77 30

AstraMVS		80.81 187	80.14 188	82.80 232	86.05 296	63.96 270	86.46 238	85.90 337	73.71 182	80.85 178	90.56 182	54.06 303	91.57 284	79.72 138	83.97 258	92.86 162

OPM-MVS		83.50 123	82.95 128	85.14 101	88.79 176	70.95 77	89.13 122	91.52 144	77.55 54	80.96 174	91.75 132	60.71 237	94.50 129	79.67 139	86.51 208	89.97 286
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
hybrid		81.05 181	80.66 173	82.22 254	81.97 400	62.99 305	83.42 334	88.68 265	70.76 255	80.56 184	90.40 188	64.49 174	90.48 335	79.57 140	86.06 219	93.19 140

E2		84.00 103	83.87 104	84.39 140	87.70 232	64.95 241	86.40 242	92.23 101	75.85 113	83.21 127	91.78 130	70.09 89	93.55 178	79.52 141	88.05 176	94.66 45

E3		84.00 103	83.87 104	84.39 140	87.70 232	64.95 241	86.40 242	92.23 101	75.85 113	83.21 127	91.78 130	70.09 89	93.55 178	79.52 141	88.05 176	94.66 45

viewcassd2359sk11		83.89 106	83.74 109	84.34 145	87.76 227	64.91 248	86.30 246	92.22 104	75.47 124	83.04 133	91.52 144	70.15 87	93.53 181	79.26 143	87.96 179	94.57 53

E3new		83.78 111	83.60 114	84.31 147	87.76 227	64.89 249	86.24 249	92.20 107	75.15 140	82.87 136	91.23 153	70.11 88	93.52 183	79.05 144	87.79 182	94.51 58

viewmacassd2359aftdt		83.76 112	83.66 112	84.07 166	86.59 283	64.56 254	86.88 219	91.82 128	75.72 116	83.34 126	92.15 120	68.24 125	92.88 225	79.05 144	89.15 151	94.77 30

viewmanbaseed2359cas		83.66 115	83.55 115	84.00 177	86.81 275	64.53 255	86.65 229	91.75 133	74.89 148	83.15 132	91.68 135	68.74 117	92.83 229	79.02 146	89.24 148	94.63 48

LuminaMVS		80.68 195	79.62 204	83.83 184	85.07 322	68.01 151	86.99 213	88.83 253	70.36 268	81.38 163	87.99 265	50.11 357	92.51 242	79.02 146	86.89 202	90.97 236

CDPH-MVS		85.76 69	85.29 82	87.17 49	93.49 52	71.08 72	88.58 149	92.42 88	68.32 323	84.61 94	93.48 79	72.32 55	96.15 55	79.00 148	95.43 34	94.28 72

MVSFormer		82.85 140	82.05 150	85.24 98	87.35 248	70.21 88	90.50 72	90.38 181	68.55 318	81.32 164	89.47 217	61.68 217	93.46 191	78.98 149	90.26 129	92.05 201

test_djsdf		80.30 211	79.32 213	83.27 204	83.98 345	65.37 225	90.50 72	90.38 181	68.55 318	76.19 279	88.70 240	56.44 281	93.46 191	78.98 149	80.14 318	90.97 236

test_vis1_n_1920		75.52 320	75.78 294	74.75 408	79.84 432	57.44 396	83.26 339	85.52 341	62.83 402	79.34 205	86.17 319	45.10 412	79.71 453	78.75 151	81.21 302	87.10 384

HQP_MVS		83.64 117	83.14 122	85.14 101	90.08 118	68.71 125	91.25 60	92.44 85	79.12 29	78.92 210	91.00 167	60.42 245	95.38 85	78.71 152	86.32 211	91.33 223

plane_prior5								92.44 85					95.38 85	78.71 152	86.32 211	91.33 223

LPG-MVS_test		82.08 154	81.27 160	84.50 134	89.23 156	68.76 121	90.22 81	91.94 121	75.37 128	76.64 267	91.51 145	54.29 299	94.91 106	78.44 154	83.78 260	89.83 291

LGP-MVS_train				84.50 134	89.23 156	68.76 121		91.94 121	75.37 128	76.64 267	91.51 145	54.29 299	94.91 106	78.44 154	83.78 260	89.83 291

lupinMVS		81.39 175	80.27 184	84.76 124	87.35 248	70.21 88	85.55 269	86.41 327	62.85 401	81.32 164	88.61 244	61.68 217	92.24 255	78.41 156	90.26 129	91.83 204

jason		81.39 175	80.29 183	84.70 126	86.63 282	69.90 96	85.95 256	86.77 319	63.24 394	81.07 170	89.47 217	61.08 233	92.15 257	78.33 157	90.07 134	92.05 201
jason: jason.
xiu_mvs_v1_base_debu		80.80 190	79.72 201	84.03 174	87.35 248	70.19 90	85.56 266	88.77 256	69.06 306	81.83 152	88.16 258	50.91 345	92.85 226	78.29 158	87.56 186	89.06 311

xiu_mvs_v1_base		80.80 190	79.72 201	84.03 174	87.35 248	70.19 90	85.56 266	88.77 256	69.06 306	81.83 152	88.16 258	50.91 345	92.85 226	78.29 158	87.56 186	89.06 311

xiu_mvs_v1_base_debi		80.80 190	79.72 201	84.03 174	87.35 248	70.19 90	85.56 266	88.77 256	69.06 306	81.83 152	88.16 258	50.91 345	92.85 226	78.29 158	87.56 186	89.06 311

guyue		81.13 179	80.64 174	82.60 243	86.52 284	63.92 273	86.69 228	87.73 291	73.97 173	80.83 179	89.69 208	56.70 278	91.33 301	78.26 161	85.40 235	92.54 173

Effi-MVS+		83.62 119	83.08 123	85.24 98	88.38 193	67.45 171	88.89 130	89.15 239	75.50 123	82.27 146	88.28 254	69.61 98	94.45 132	77.81 162	87.84 181	93.84 96

KinetiMVS		83.31 131	82.61 135	85.39 94	87.08 268	67.56 168	88.06 172	91.65 138	77.80 46	82.21 148	91.79 129	57.27 272	94.07 147	77.77 163	89.89 138	94.56 55

viewdifsd2359ckpt07		82.83 141	82.78 133	82.99 221	86.51 285	62.58 311	85.09 282	90.83 168	75.22 133	82.28 145	91.63 139	69.43 100	92.03 261	77.71 164	86.32 211	94.34 67

PS-MVSNAJss		82.07 155	81.31 159	84.34 145	86.51 285	67.27 180	89.27 113	91.51 145	71.75 226	79.37 203	90.22 196	63.15 189	94.27 136	77.69 165	82.36 288	91.49 219

ACMP	74.13 6	81.51 173	80.57 175	84.36 143	89.42 143	68.69 128	89.97 85	91.50 148	74.46 160	75.04 314	90.41 187	53.82 305	94.54 126	77.56 166	82.91 280	89.86 290
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
BP-MVS														77.47 167

HQP-MVS		82.61 144	82.02 151	84.37 142	89.33 148	66.98 187	89.17 117	92.19 109	76.41 96	77.23 252	90.23 195	60.17 248	95.11 97	77.47 167	85.99 222	91.03 233

MVS_Test		83.15 133	83.06 124	83.41 200	86.86 272	63.21 296	86.11 253	92.00 117	74.31 165	82.87 136	89.44 222	70.03 91	93.21 204	77.39 169	88.50 164	93.81 98

3Dnovator+	77.84 4	85.48 74	84.47 94	88.51 7	91.08 95	73.49 16	93.18 16	93.78 24	80.79 8	76.66 266	93.37 84	60.40 247	96.75 31	77.20 170	93.73 70	95.29 7

anonymousdsp		78.60 253	77.15 268	82.98 223	80.51 423	67.08 185	87.24 206	89.53 214	65.66 359	75.16 309	87.19 287	52.52 314	92.25 254	77.17 171	79.34 329	89.61 298

mmtdpeth		74.16 336	73.01 340	77.60 375	83.72 352	61.13 338	85.10 281	85.10 346	72.06 222	77.21 256	80.33 427	43.84 421	85.75 405	77.14 172	52.61 490	85.91 409

VDD-MVS		83.01 138	82.36 140	84.96 111	91.02 97	66.40 195	88.91 129	88.11 275	77.57 51	84.39 99	93.29 86	52.19 320	93.91 157	77.05 173	88.70 160	94.57 53

XVG-OURS-SEG-HR		80.81 187	79.76 198	83.96 181	85.60 305	68.78 120	83.54 332	90.50 177	70.66 260	76.71 265	91.66 136	60.69 238	91.26 302	76.94 174	81.58 298	91.83 204

Elysia		81.53 169	80.16 186	85.62 86	85.51 307	68.25 141	88.84 134	92.19 109	71.31 236	80.50 185	89.83 202	46.89 389	94.82 113	76.85 175	89.57 142	93.80 100

StellarMVS		81.53 169	80.16 186	85.62 86	85.51 307	68.25 141	88.84 134	92.19 109	71.31 236	80.50 185	89.83 202	46.89 389	94.82 113	76.85 175	89.57 142	93.80 100

jajsoiax		79.29 235	77.96 242	83.27 204	84.68 330	66.57 194	89.25 114	90.16 192	69.20 302	75.46 294	89.49 216	45.75 407	93.13 213	76.84 177	80.80 308	90.11 274

SDMVSNet		80.38 206	80.18 185	80.99 287	89.03 165	64.94 244	80.45 388	89.40 218	75.19 137	76.61 269	89.98 198	60.61 242	87.69 386	76.83 178	83.55 269	90.33 264

viewdifsd2359ckpt11		80.37 208	79.73 199	82.30 252	83.70 353	62.39 315	84.20 312	86.67 321	73.22 201	80.90 175	90.62 179	63.00 194	91.56 285	76.81 179	78.44 337	92.95 159

viewmsd2359difaftdt		80.37 208	79.73 199	82.30 252	83.70 353	62.39 315	84.20 312	86.67 321	73.22 201	80.90 175	90.62 179	63.00 194	91.56 285	76.81 179	78.44 337	92.95 159

mvs_tets		79.13 239	77.77 252	83.22 208	84.70 329	66.37 196	89.17 117	90.19 191	69.38 294	75.40 297	89.46 219	44.17 419	93.15 211	76.78 181	80.70 310	90.14 271

DPM-MVS		84.93 88	84.29 95	86.84 57	90.20 115	73.04 23	87.12 208	93.04 48	69.80 284	82.85 138	91.22 156	73.06 46	96.02 59	76.72 182	94.63 54	91.46 222

test_cas_vis1_n_1920		73.76 342	73.74 331	73.81 419	75.90 465	59.77 364	80.51 386	82.40 390	58.30 446	81.62 160	85.69 327	44.35 418	76.41 471	76.29 183	78.61 333	85.23 421

ET-MVSNet_ETH3D		78.63 252	76.63 283	84.64 127	86.73 278	69.47 104	85.01 284	84.61 353	69.54 291	66.51 433	86.59 305	50.16 356	91.75 275	76.26 184	84.24 255	92.69 168

viewdifsd2359ckpt09		83.34 128	82.55 136	85.70 83	87.64 236	67.72 162	88.43 154	91.68 137	71.91 225	81.65 159	90.68 176	67.10 138	94.75 118	76.17 185	87.70 185	94.62 50

v2v482		80.23 212	79.29 214	83.05 218	83.62 355	64.14 267	87.04 210	89.97 197	73.61 185	78.18 229	87.22 285	61.10 232	93.82 162	76.11 186	76.78 360	91.18 227

test_fmvs1_n		70.86 385	70.24 380	72.73 430	72.51 489	55.28 428	81.27 374	79.71 429	51.49 478	78.73 212	84.87 349	27.54 485	77.02 465	76.06 187	79.97 320	85.88 410

CLD-MVS		82.31 149	81.65 157	84.29 150	88.47 188	67.73 161	85.81 263	92.35 91	75.78 115	78.33 225	86.58 307	64.01 178	94.35 133	76.05 188	87.48 189	90.79 242
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EPNet		83.72 114	82.92 129	86.14 74	84.22 339	69.48 103	91.05 64	85.27 343	81.30 6	76.83 261	91.65 137	66.09 154	95.56 71	76.00 189	93.85 68	93.38 126
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewdifsd2359ckpt13		82.91 139	82.29 142	84.77 123	86.96 271	66.90 191	87.47 191	91.62 140	72.19 218	81.68 158	90.71 175	66.92 139	93.28 197	75.90 190	87.15 195	94.12 79

test_fmvs1		70.93 383	70.52 375	72.16 433	73.71 477	55.05 430	80.82 377	78.77 439	51.21 479	78.58 217	84.41 357	31.20 479	76.94 466	75.88 191	80.12 319	84.47 433

XVG-OURS		80.41 204	79.23 216	83.97 180	85.64 303	69.02 114	83.03 348	90.39 180	71.09 243	77.63 242	91.49 147	54.62 298	91.35 299	75.71 192	83.47 272	91.54 216

V42		79.38 233	78.24 238	82.83 229	81.10 417	65.50 220	85.55 269	89.82 201	71.57 232	78.21 227	86.12 320	60.66 240	93.18 210	75.64 193	75.46 383	89.81 293

PS-MVSNAJ		81.69 164	81.02 166	83.70 188	89.51 137	68.21 144	84.28 310	90.09 194	70.79 253	81.26 168	85.62 331	63.15 189	94.29 134	75.62 194	88.87 155	88.59 335

xiu_mvs_v2_base		81.69 164	81.05 165	83.60 190	89.15 159	68.03 150	84.46 302	90.02 195	70.67 257	81.30 167	86.53 310	63.17 188	94.19 143	75.60 195	88.54 162	88.57 336

EIA-MVS		83.31 131	82.80 131	84.82 120	89.59 133	65.59 218	88.21 166	92.68 74	74.66 156	78.96 208	86.42 312	69.06 111	95.26 90	75.54 196	90.09 132	93.62 114

AUN-MVS		79.21 237	77.60 258	84.05 172	88.71 181	67.61 165	85.84 261	87.26 306	69.08 305	77.23 252	88.14 262	53.20 312	93.47 190	75.50 197	73.45 408	91.06 231

mvsmamba		80.60 199	79.38 210	84.27 153	89.74 131	67.24 182	87.47 191	86.95 314	70.02 277	75.38 298	88.93 234	51.24 342	92.56 238	75.47 198	89.22 149	93.00 156

reproduce_monomvs		75.40 324	74.38 322	78.46 356	83.92 347	57.80 389	83.78 321	86.94 315	73.47 191	72.25 356	84.47 355	38.74 454	89.27 358	75.32 199	70.53 428	88.31 341

OMC-MVS		82.69 142	81.97 153	84.85 119	88.75 179	67.42 172	87.98 174	90.87 166	74.92 147	79.72 196	91.65 137	62.19 208	93.96 149	75.26 200	86.42 209	93.16 142

VortexMVS		78.57 255	77.89 246	80.59 296	85.89 297	62.76 309	85.61 264	89.62 211	72.06 222	74.99 315	85.38 337	55.94 285	90.77 329	74.99 201	76.58 361	88.23 344

v1144		80.03 217	79.03 220	83.01 220	83.78 350	64.51 257	87.11 209	90.57 176	71.96 224	78.08 232	86.20 318	61.41 224	93.94 152	74.93 202	77.23 351	90.60 252

MVSTER		79.01 242	77.88 247	82.38 249	83.07 373	64.80 251	84.08 317	88.95 250	69.01 309	78.69 213	87.17 288	54.70 296	92.43 245	74.69 203	80.57 312	89.89 289

viewmambaseed2359dif		80.41 204	79.84 196	82.12 255	82.95 382	62.50 314	83.39 335	88.06 279	67.11 335	80.98 172	90.31 191	66.20 152	91.01 316	74.62 204	84.90 239	92.86 162

test_vis1_n		69.85 402	69.21 388	71.77 436	72.66 488	55.27 429	81.48 368	76.21 459	52.03 475	75.30 305	83.20 389	28.97 482	76.22 473	74.60 205	78.41 341	83.81 442

test_fmvs2		68.35 416	67.48 412	70.98 445	69.50 493	51.95 455	80.05 395	76.38 458	49.33 482	74.65 322	84.38 358	23.30 494	75.40 482	74.51 206	75.17 392	85.60 414

PVSNet_Blended_VisFu		82.62 143	81.83 155	84.96 111	90.80 103	69.76 99	88.74 141	91.70 136	69.39 293	78.96 208	88.46 249	65.47 162	94.87 112	74.42 207	88.57 161	90.24 268

v8		79.97 219	79.02 221	82.80 232	84.09 342	64.50 259	87.96 175	90.29 188	74.13 172	75.24 307	86.81 294	62.88 197	93.89 160	74.39 208	75.40 386	90.00 282

v144192		79.47 227	78.37 234	82.78 236	83.35 360	63.96 270	86.96 214	90.36 184	69.99 279	77.50 244	85.67 329	60.66 240	93.77 166	74.27 209	76.58 361	90.62 250

ACMM	73.20 8	80.78 194	79.84 196	83.58 192	89.31 151	68.37 136	89.99 84	91.60 142	70.28 272	77.25 250	89.66 210	53.37 310	93.53 181	74.24 210	82.85 281	88.85 324
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
旧先验2							86.56 234		58.10 449	87.04 63			88.98 365	74.07 211

v1192		79.59 224	78.43 233	83.07 217	83.55 357	64.52 256	86.93 217	90.58 174	70.83 252	77.78 239	85.90 322	59.15 254	93.94 152	73.96 212	77.19 353	90.76 244

v10		79.74 221	78.67 226	82.97 224	84.06 343	64.95 241	87.88 181	90.62 173	73.11 203	75.11 311	86.56 308	61.46 223	94.05 148	73.68 213	75.55 379	89.90 288

v1921920		79.22 236	78.03 241	82.80 232	83.30 362	63.94 272	86.80 222	90.33 185	69.91 282	77.48 245	85.53 333	58.44 260	93.75 168	73.60 214	76.85 358	90.71 248

cl22		78.07 267	77.01 270	81.23 280	82.37 396	61.83 328	83.55 330	87.98 281	68.96 312	75.06 313	83.87 371	61.40 225	91.88 271	73.53 215	76.39 366	89.98 285

Effi-MVS+-dtu		80.03 217	78.57 229	84.42 139	85.13 320	68.74 123	88.77 137	88.10 276	74.99 143	74.97 316	83.49 384	57.27 272	93.36 195	73.53 215	80.88 306	91.18 227

c3_l		78.75 248	77.91 244	81.26 279	82.89 383	61.56 332	84.09 316	89.13 241	69.97 280	75.56 290	84.29 361	66.36 148	92.09 260	73.47 217	75.48 381	90.12 273

VDDNet		81.52 171	80.67 172	84.05 172	90.44 110	64.13 268	89.73 93	85.91 336	71.11 242	83.18 130	93.48 79	50.54 352	93.49 186	73.40 218	88.25 171	94.54 57

CANet_DTU		80.61 197	79.87 195	82.83 229	85.60 305	63.17 299	87.36 201	88.65 268	76.37 101	75.88 285	88.44 250	53.51 308	93.07 216	73.30 219	89.74 140	92.25 189

miper_ehance_all_eth		78.59 254	77.76 253	81.08 285	82.66 388	61.56 332	83.65 325	89.15 239	68.87 313	75.55 291	83.79 375	66.49 146	92.03 261	73.25 220	76.39 366	89.64 297

3Dnovator	76.31 5	83.38 127	82.31 141	86.59 62	87.94 214	72.94 28	90.64 68	92.14 114	77.21 67	75.47 292	92.83 98	58.56 259	94.72 120	73.24 221	92.71 82	92.13 199

v1240		78.99 243	77.78 251	82.64 241	83.21 366	63.54 287	86.62 231	90.30 187	69.74 289	77.33 248	85.68 328	57.04 275	93.76 167	73.13 222	76.92 355	90.62 250

casdiffseed414692147		83.62 119	83.02 125	85.40 93	87.31 256	67.50 170	88.70 143	91.72 134	76.97 75	82.77 141	91.72 133	66.85 140	93.71 171	73.06 223	88.12 174	94.98 14

miper_enhance_ethall		77.87 274	76.86 274	80.92 290	81.65 405	61.38 336	82.68 349	88.98 247	65.52 361	75.47 292	82.30 405	65.76 161	92.00 264	72.95 224	76.39 366	89.39 304

MG-MVS		83.41 125	83.45 117	83.28 203	92.74 73	62.28 320	88.17 168	89.50 215	75.22 133	81.49 161	92.74 105	66.75 141	95.11 97	72.85 225	91.58 103	92.45 181

EPP-MVSNet		83.40 126	83.02 125	84.57 128	90.13 116	64.47 260	92.32 35	90.73 171	74.45 161	79.35 204	91.10 160	69.05 112	95.12 95	72.78 226	87.22 193	94.13 78

test_fmvs3		63.36 442	61.82 444	67.98 461	62.51 502	46.96 483	77.37 433	74.03 469	45.24 487	67.50 414	78.79 445	12.16 506	72.98 492	72.77 227	66.02 449	83.99 440

IterMVS-LS		80.06 215	79.38 210	82.11 257	85.89 297	63.20 297	86.79 223	89.34 220	74.19 169	75.45 295	86.72 297	66.62 143	92.39 247	72.58 228	76.86 357	90.75 245
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tt0805		78.73 249	77.83 248	81.43 272	85.17 316	60.30 359	89.41 108	90.90 164	71.21 240	77.17 257	88.73 239	46.38 396	93.21 204	72.57 229	78.96 332	90.79 242

EI-MVSNet		80.52 203	79.98 191	82.12 255	84.28 337	63.19 298	86.41 239	88.95 250	74.18 170	78.69 213	87.54 277	66.62 143	92.43 245	72.57 229	80.57 312	90.74 246

icg_test_0407_2		78.92 246	78.93 223	78.90 344	87.13 262	63.59 283	76.58 438	89.33 221	70.51 263	77.82 236	89.03 229	61.84 213	81.38 446	72.56 231	85.56 231	91.74 207

IMVS_0407		80.61 197	79.90 194	82.75 239	87.13 262	63.59 283	85.33 275	89.33 221	70.51 263	77.82 236	89.03 229	61.84 213	92.91 223	72.56 231	85.56 231	91.74 207

IMVS_0404		77.16 291	76.42 287	79.37 335	87.13 262	63.59 283	77.12 435	89.33 221	70.51 263	66.22 436	89.03 229	50.36 354	82.78 434	72.56 231	85.56 231	91.74 207

IMVS_0403		80.80 190	80.12 189	82.87 228	87.13 262	63.59 283	85.19 276	89.33 221	70.51 263	78.49 220	89.03 229	63.26 185	93.27 199	72.56 231	85.56 231	91.74 207

SSM_0407		81.58 168	80.48 178	84.87 118	88.81 171	67.96 152	87.37 200	89.25 231	71.06 245	79.48 200	90.39 189	59.57 250	94.48 131	72.45 235	85.93 224	92.18 194

SSM_0404		81.91 158	80.84 170	85.13 104	89.24 155	68.26 139	87.84 183	89.25 231	71.06 245	80.62 182	90.39 189	59.57 250	94.65 124	72.45 235	87.19 194	92.47 180

Vis-MVSNet		83.46 124	82.80 131	85.43 92	90.25 114	68.74 123	90.30 80	90.13 193	76.33 103	80.87 177	92.89 96	61.00 234	94.20 141	72.45 235	90.97 115	93.35 129
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
LFMVS		81.82 161	81.23 161	83.57 193	91.89 84	63.43 292	89.84 87	81.85 399	77.04 74	83.21 127	93.10 89	52.26 319	93.43 193	71.98 238	89.95 136	93.85 94

v148		78.72 250	77.80 250	81.47 271	82.73 386	61.96 326	86.30 246	88.08 277	73.26 198	76.18 280	85.47 335	62.46 202	92.36 249	71.92 239	73.82 405	90.09 276

PVSNet_BlendedMVS		80.60 199	80.02 190	82.36 251	88.85 167	65.40 222	86.16 252	92.00 117	69.34 295	78.11 230	86.09 321	66.02 156	94.27 136	71.52 240	82.06 291	87.39 366

PVSNet_Blended		80.98 182	80.34 181	82.90 226	88.85 167	65.40 222	84.43 305	92.00 117	67.62 329	78.11 230	85.05 347	66.02 156	94.27 136	71.52 240	89.50 144	89.01 316

eth_miper_zixun_eth		77.92 272	76.69 281	81.61 269	83.00 376	61.98 325	83.15 341	89.20 235	69.52 292	74.86 318	84.35 360	61.76 216	92.56 238	71.50 242	72.89 413	90.28 267

UA-Net		85.08 86	84.96 86	85.45 91	92.07 81	68.07 147	89.78 91	90.86 167	82.48 2	84.60 95	93.20 88	69.35 101	95.22 91	71.39 243	90.88 119	93.07 149

FA-MVS(test-final)		80.96 183	79.91 193	84.10 160	88.30 196	65.01 238	84.55 299	90.01 196	73.25 199	79.61 197	87.57 274	58.35 261	94.72 120	71.29 244	86.25 214	92.56 172

dtuplus		80.04 216	79.40 209	81.97 261	83.08 372	62.61 310	83.63 328	87.98 281	67.47 333	81.02 171	90.50 186	64.86 170	90.77 329	71.28 245	84.76 243	92.53 174

cl____		77.72 277	76.76 278	80.58 297	82.49 393	60.48 356	83.09 344	87.87 286	69.22 300	74.38 327	85.22 342	62.10 209	91.53 290	71.09 246	75.41 385	89.73 296

DIV-MVS_self_test		77.72 277	76.76 278	80.58 297	82.48 394	60.48 356	83.09 344	87.86 287	69.22 300	74.38 327	85.24 340	62.10 209	91.53 290	71.09 246	75.40 386	89.74 295

MonoMVSNet		76.49 304	75.80 293	78.58 350	81.55 408	58.45 375	86.36 244	86.22 331	74.87 151	74.73 320	83.73 377	51.79 334	88.73 370	70.78 248	72.15 418	88.55 337

test_yl		81.17 177	80.47 179	83.24 206	89.13 160	63.62 279	86.21 250	89.95 198	72.43 216	81.78 156	89.61 212	57.50 269	93.58 173	70.75 249	86.90 200	92.52 175

DCV-MVSNet		81.17 177	80.47 179	83.24 206	89.13 160	63.62 279	86.21 250	89.95 198	72.43 216	81.78 156	89.61 212	57.50 269	93.58 173	70.75 249	86.90 200	92.52 175

VNet		82.21 151	82.41 138	81.62 267	90.82 102	60.93 345	84.47 300	89.78 202	76.36 102	84.07 108	91.88 126	64.71 171	90.26 339	70.68 251	88.89 154	93.66 107

mvs_anonymous		79.42 230	79.11 219	80.34 303	84.45 336	57.97 384	82.59 350	87.62 293	67.40 334	76.17 282	88.56 247	68.47 120	89.59 352	70.65 252	86.05 220	93.47 124

VPA-MVSNet		80.60 199	80.55 176	80.76 293	88.07 208	60.80 348	86.86 220	91.58 143	75.67 120	80.24 190	89.45 221	63.34 182	90.25 340	70.51 253	79.22 331	91.23 226

PAPM_NR		83.02 137	82.41 138	84.82 120	92.47 78	66.37 196	87.93 178	91.80 129	73.82 179	77.32 249	90.66 177	67.90 128	94.90 108	70.37 254	89.48 145	93.19 140

mamba_0408		79.37 234	77.52 260	84.93 114	88.81 171	67.96 152	65.03 494	88.66 266	70.96 249	79.48 200	89.80 204	58.69 256	94.65 124	70.35 255	85.93 224	92.18 194

SSM_04072		77.67 281	77.52 260	78.12 361	88.81 171	67.96 152	65.03 494	88.66 266	70.96 249	79.48 200	89.80 204	58.69 256	74.23 487	70.35 255	85.93 224	92.18 194

thisisatest0530		79.40 231	77.76 253	84.31 147	87.69 234	65.10 237	87.36 201	84.26 360	70.04 276	77.42 246	88.26 256	49.94 360	94.79 117	70.20 257	84.70 245	93.03 153

tttt0517		79.40 231	77.91 244	83.90 183	88.10 206	63.84 274	88.37 160	84.05 362	71.45 234	76.78 263	89.12 226	49.93 362	94.89 110	70.18 258	83.18 278	92.96 158

UniMVSNet_NR-MVSNet		81.88 159	81.54 158	82.92 225	88.46 189	63.46 290	87.13 207	92.37 90	80.19 13	78.38 223	89.14 225	71.66 68	93.05 218	70.05 259	76.46 364	92.25 189

DU-MVS		81.12 180	80.52 177	82.90 226	87.80 221	63.46 290	87.02 212	91.87 125	79.01 32	78.38 223	89.07 227	65.02 167	93.05 218	70.05 259	76.46 364	92.20 192

XVG-ACMP-BASELINE		76.11 312	74.27 324	81.62 267	83.20 367	64.67 253	83.60 329	89.75 206	69.75 287	71.85 361	87.09 290	32.78 474	92.11 258	69.99 261	80.43 314	88.09 348

GeoE		81.71 163	81.01 167	83.80 187	89.51 137	64.45 261	88.97 127	88.73 264	71.27 239	78.63 216	89.76 207	66.32 149	93.20 207	69.89 262	86.02 221	93.74 103

FIs		82.07 155	82.42 137	81.04 286	88.80 175	58.34 377	88.26 165	93.49 32	76.93 77	78.47 222	91.04 164	69.92 93	92.34 251	69.87 263	84.97 238	92.44 182

114514_t		80.68 195	79.51 206	84.20 157	94.09 43	67.27 180	89.64 96	91.11 159	58.75 444	74.08 329	90.72 174	58.10 262	95.04 103	69.70 264	89.42 146	90.30 266

Anonymous20231211		78.97 244	77.69 256	82.81 231	90.54 108	64.29 264	90.11 83	91.51 145	65.01 373	76.16 283	88.13 263	50.56 351	93.03 221	69.68 265	77.56 350	91.11 229

Patchmatch-RL test		70.24 393	67.78 407	77.61 373	77.43 460	59.57 368	71.16 468	70.33 477	62.94 400	68.65 397	72.77 479	50.62 350	85.49 410	69.58 266	66.58 447	87.77 355

UniMVSNet (Re)		81.60 167	81.11 164	83.09 214	88.38 193	64.41 262	87.60 187	93.02 52	78.42 38	78.56 218	88.16 258	69.78 95	93.26 200	69.58 266	76.49 363	91.60 213

IterMVS-SCA-FT		75.43 322	73.87 329	80.11 311	82.69 387	64.85 250	81.57 367	83.47 371	69.16 303	70.49 373	84.15 369	51.95 327	88.15 379	69.23 268	72.14 419	87.34 371

v7n		78.97 244	77.58 259	83.14 212	83.45 359	65.51 219	88.32 162	91.21 154	73.69 183	72.41 353	86.32 315	57.93 263	93.81 163	69.18 269	75.65 377	90.11 274

Anonymous20240529		80.19 214	78.89 224	84.10 160	90.60 106	64.75 252	88.95 128	90.90 164	65.97 356	80.59 183	91.17 159	49.97 359	93.73 170	69.16 270	82.70 285	93.81 98

miper_lstm_enhance		74.11 337	73.11 339	77.13 381	80.11 428	59.62 366	72.23 464	86.92 317	66.76 339	70.40 374	82.92 394	56.93 276	82.92 433	69.06 271	72.63 414	88.87 323

testdata				79.97 315	90.90 100	64.21 266		84.71 351	59.27 437	85.40 77	92.91 95	62.02 212	89.08 363	68.95 272	91.37 108	86.63 396

test1111		79.43 229	79.18 218	80.15 310	89.99 123	53.31 447	87.33 203	77.05 453	75.04 142	80.23 191	92.77 104	48.97 376	92.33 252	68.87 273	92.40 87	94.81 27

GA-MVS		76.87 296	75.17 311	81.97 261	82.75 385	62.58 311	81.44 370	86.35 330	72.16 221	74.74 319	82.89 395	46.20 401	92.02 263	68.85 274	81.09 303	91.30 225

test2506		77.30 289	76.49 284	79.74 325	90.08 118	52.02 453	87.86 182	63.10 498	74.88 149	80.16 192	92.79 101	38.29 458	92.35 250	68.74 275	92.50 85	94.86 22

ECVR-MVS		79.61 222	79.26 215	80.67 295	90.08 118	54.69 434	87.89 180	77.44 449	74.88 149	80.27 189	92.79 101	48.96 377	92.45 244	68.55 276	92.50 85	94.86 22

UGNet		80.83 186	79.59 205	84.54 129	88.04 209	68.09 146	89.42 107	88.16 274	76.95 76	76.22 278	89.46 219	49.30 371	93.94 152	68.48 277	90.31 127	91.60 213
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
FC-MVSNet-test		81.52 171	82.02 151	80.03 312	88.42 192	55.97 418	87.95 176	93.42 35	77.10 72	77.38 247	90.98 169	69.96 92	91.79 273	68.46 278	84.50 247	92.33 185

DP-MVS Recon		83.11 136	82.09 148	86.15 72	94.44 24	70.92 79	88.79 136	92.20 107	70.53 262	79.17 206	91.03 166	64.12 177	96.03 57	68.39 279	90.14 131	91.50 218

UniMVSNet_ETH3D		79.10 240	78.24 238	81.70 266	86.85 273	60.24 360	87.28 205	88.79 255	74.25 168	76.84 260	90.53 185	49.48 366	91.56 285	67.98 280	82.15 289	93.29 131

D2MVS		74.82 329	73.21 337	79.64 330	79.81 433	62.56 313	80.34 390	87.35 300	64.37 381	68.86 395	82.66 400	46.37 397	90.10 342	67.91 281	81.24 301	86.25 399

IS-MVSNet		83.15 133	82.81 130	84.18 158	89.94 125	63.30 294	91.59 51	88.46 272	79.04 31	79.49 199	92.16 118	65.10 166	94.28 135	67.71 282	91.86 99	94.95 15

Fast-Effi-MVS+-dtu		78.02 269	76.49 284	82.62 242	83.16 370	66.96 189	86.94 216	87.45 298	72.45 213	71.49 366	84.17 368	54.79 295	91.58 282	67.61 283	80.31 315	89.30 307

PAPR		81.66 166	80.89 169	83.99 179	90.27 113	64.00 269	86.76 226	91.77 132	68.84 314	77.13 259	89.50 215	67.63 130	94.88 111	67.55 284	88.52 163	93.09 148

cascas		76.72 298	74.64 316	82.99 221	85.78 300	65.88 208	82.33 354	89.21 234	60.85 422	72.74 347	81.02 418	47.28 385	93.75 168	67.48 285	85.02 237	89.34 306

1314		76.53 300	75.30 309	80.21 308	83.93 346	62.32 319	84.66 292	88.81 254	60.23 427	70.16 379	84.07 370	55.30 289	90.73 332	67.37 286	83.21 277	87.59 360

无先验							87.48 190	88.98 247	60.00 430				94.12 145	67.28 287		88.97 319

thisisatest0515		77.33 288	75.38 304	83.18 210	85.27 315	63.80 275	82.11 358	83.27 374	65.06 371	75.91 284	83.84 373	49.54 365	94.27 136	67.24 288	86.19 215	91.48 220

原ACMM1				84.35 144	93.01 67	68.79 119		92.44 85	63.96 389	81.09 169	91.57 143	66.06 155	95.45 78	67.19 289	94.82 50	88.81 326

Baseline_NR-MVSNet		78.15 265	78.33 236	77.61 373	85.79 299	56.21 416	86.78 224	85.76 339	73.60 186	77.93 235	87.57 274	65.02 167	88.99 364	67.14 290	75.33 388	87.63 357

TranMVSNet+NR-MVSNet		80.84 185	80.31 182	82.42 248	87.85 218	62.33 318	87.74 185	91.33 151	80.55 9	77.99 234	89.86 200	65.23 164	92.62 233	67.05 291	75.24 391	92.30 187

Fast-Effi-MVS+		80.81 187	79.92 192	83.47 194	88.85 167	64.51 257	85.53 271	89.39 219	70.79 253	78.49 220	85.06 346	67.54 131	93.58 173	67.03 292	86.58 206	92.32 186

VPNet		78.69 251	78.66 227	78.76 346	88.31 195	55.72 422	84.45 303	86.63 324	76.79 81	78.26 226	90.55 183	59.30 253	89.70 351	66.63 293	77.05 354	90.88 239

PM-MVS		66.41 429	64.14 432	73.20 425	73.92 476	56.45 409	78.97 411	64.96 495	63.88 390	64.72 447	80.24 429	19.84 498	83.44 430	66.24 294	64.52 462	79.71 474

test-LLR		72.94 362	72.43 346	74.48 409	81.35 413	58.04 382	78.38 419	77.46 447	66.66 341	69.95 383	79.00 442	48.06 380	79.24 454	66.13 295	84.83 240	86.15 402

test-mter		71.41 378	70.39 379	74.48 409	81.35 413	58.04 382	78.38 419	77.46 447	60.32 426	69.95 383	79.00 442	36.08 468	79.24 454	66.13 295	84.83 240	86.15 402

MVS		78.19 264	76.99 272	81.78 264	85.66 302	66.99 186	84.66 292	90.47 178	55.08 467	72.02 360	85.27 339	63.83 180	94.11 146	66.10 297	89.80 139	84.24 436

NR-MVSNet		80.23 212	79.38 210	82.78 236	87.80 221	63.34 293	86.31 245	91.09 160	79.01 32	72.17 357	89.07 227	67.20 135	92.81 230	66.08 298	75.65 377	92.20 192

CVMVSNet		72.99 361	72.58 345	74.25 413	84.28 337	50.85 467	86.41 239	83.45 372	44.56 488	73.23 340	87.54 277	49.38 368	85.70 406	65.90 299	78.44 337	86.19 401

IterMVS		74.29 333	72.94 341	78.35 357	81.53 409	63.49 289	81.58 366	82.49 389	68.06 326	69.99 382	83.69 379	51.66 336	85.54 409	65.85 300	71.64 422	86.01 406
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
OurMVSNet-221017-0		74.26 334	72.42 347	79.80 320	83.76 351	59.59 367	85.92 258	86.64 323	66.39 348	66.96 423	87.58 273	39.46 449	91.60 281	65.76 301	69.27 433	88.22 345

tpmrst		72.39 367	72.13 350	73.18 426	80.54 422	49.91 471	79.91 398	79.08 437	63.11 396	71.69 363	79.95 432	55.32 288	82.77 435	65.66 302	73.89 403	86.87 387

MAR-MVS		81.84 160	80.70 171	85.27 97	91.32 91	71.53 59	89.82 88	90.92 163	69.77 286	78.50 219	86.21 317	62.36 204	94.52 128	65.36 303	92.05 94	89.77 294
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
Anonymous202405211		78.25 260	77.01 270	81.99 260	91.03 96	60.67 352	84.77 289	83.90 364	70.65 261	80.00 193	91.20 157	41.08 440	91.43 297	65.21 304	85.26 236	93.85 94

ab-mvs		79.51 225	78.97 222	81.14 283	88.46 189	60.91 346	83.84 320	89.24 233	70.36 268	79.03 207	88.87 237	63.23 187	90.21 341	65.12 305	82.57 286	92.28 188

IB-MVS	68.01 15	75.85 316	73.36 336	83.31 202	84.76 328	66.03 201	83.38 336	85.06 347	70.21 275	69.40 389	81.05 417	45.76 406	94.66 123	65.10 306	75.49 380	89.25 308
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
WR-MVS		79.49 226	79.22 217	80.27 305	88.79 176	58.35 376	85.06 283	88.61 270	78.56 36	77.65 241	88.34 252	63.81 181	90.66 333	64.98 307	77.22 352	91.80 206

CostFormer		75.24 326	73.90 328	79.27 337	82.65 389	58.27 378	80.80 378	82.73 388	61.57 417	75.33 304	83.13 390	55.52 287	91.07 314	64.98 307	78.34 342	88.45 338

API-MVS		81.99 157	81.23 161	84.26 155	90.94 99	70.18 93	91.10 63	89.32 225	71.51 233	78.66 215	88.28 254	65.26 163	95.10 100	64.74 309	91.23 111	87.51 363

新几何1				83.42 198	93.13 61	70.71 82		85.48 342	57.43 456	81.80 155	91.98 123	63.28 183	92.27 253	64.60 310	92.99 77	87.27 374

testing91		76.54 299	75.66 298	79.18 340	88.43 191	55.89 419	81.08 375	83.00 382	73.76 181	75.34 300	84.29 361	46.20 401	90.07 343	64.33 311	84.50 247	91.58 215

testing99		76.09 313	75.12 312	79.00 341	88.16 201	55.50 425	80.79 379	81.40 404	73.30 197	75.17 308	84.27 364	44.48 416	90.02 344	64.28 312	84.22 256	91.48 220

pm-mvs1		77.25 290	76.68 282	78.93 343	84.22 339	58.62 374	86.41 239	88.36 273	71.37 235	73.31 338	88.01 264	61.22 230	89.15 362	64.24 313	73.01 412	89.03 315

TESTMET0.1,1		69.89 401	69.00 390	72.55 431	79.27 443	56.85 402	78.38 419	74.71 467	57.64 452	68.09 405	77.19 457	37.75 460	76.70 467	63.92 314	84.09 257	84.10 439

QAPM		80.88 184	79.50 207	85.03 107	88.01 212	68.97 116	91.59 51	92.00 117	66.63 346	75.15 310	92.16 118	57.70 266	95.45 78	63.52 315	88.76 158	90.66 249

baseline2		75.70 317	73.83 330	81.30 277	83.26 364	61.79 329	82.57 351	80.65 412	66.81 337	66.88 424	83.42 385	57.86 265	92.19 256	63.47 316	79.57 322	89.91 287

LCM-MVSNet-Re		77.05 292	76.94 273	77.36 377	87.20 259	51.60 460	80.06 394	80.46 417	75.20 136	67.69 412	86.72 297	62.48 201	88.98 365	63.44 317	89.25 147	91.51 217

gm-plane-assit					81.40 411	53.83 442			62.72 405		80.94 420		92.39 247	63.40 318

baseline1		76.98 294	76.75 280	77.66 371	88.13 204	55.66 423	85.12 280	81.89 397	73.04 205	76.79 262	88.90 235	62.43 203	87.78 385	63.30 319	71.18 425	89.55 300

blended_shiyan8		73.38 347	71.17 364	80.02 313	78.36 448	61.51 334	82.43 352	87.28 301	65.40 365	68.61 398	77.53 455	51.91 330	91.00 319	63.28 320	65.76 452	87.53 362

blended_shiyan6		73.38 347	71.17 364	80.01 314	78.36 448	61.48 335	82.43 352	87.27 304	65.40 365	68.56 400	77.55 454	51.94 329	91.01 316	63.27 321	65.76 452	87.55 361

usedtu_blend_shiyan5		73.29 353	70.96 368	80.25 306	77.80 455	62.16 322	84.44 304	87.38 299	64.41 379	68.09 405	76.28 464	51.32 338	91.23 304	63.21 322	65.76 452	87.35 368

blend_shiyan4		72.29 371	69.65 384	80.21 308	78.24 451	62.16 322	82.29 355	87.27 304	65.41 364	68.43 404	76.42 463	39.91 447	91.23 304	63.21 322	65.66 457	87.22 375

wanda-best-256-512		72.94 362	70.66 372	79.79 321	77.80 455	61.03 343	81.31 372	87.15 309	65.18 368	68.09 405	76.28 464	51.32 338	90.97 320	63.06 324	65.76 452	87.35 368

FE-blended-shiyan7		72.94 362	70.66 372	79.79 321	77.80 455	61.03 343	81.31 372	87.15 309	65.18 368	68.09 405	76.28 464	51.32 338	90.97 320	63.06 324	65.76 452	87.35 368

AdaColmap		80.58 202	79.42 208	84.06 169	93.09 64	68.91 117	89.36 111	88.97 249	69.27 297	75.70 288	89.69 208	57.20 274	95.77 66	63.06 324	88.41 166	87.50 364

test_vis1_rt		60.28 447	58.42 450	65.84 466	67.25 496	55.60 424	70.44 473	60.94 501	44.33 489	59.00 474	66.64 491	24.91 489	68.67 498	62.80 327	69.48 431	73.25 487

gbinet_0.2-2-1-0.02		73.24 355	70.86 371	80.39 300	78.03 453	61.62 331	83.10 343	86.69 320	65.98 355	69.29 392	76.15 467	49.77 363	91.51 292	62.75 328	66.00 450	88.03 349

GBi-Net		78.40 257	77.40 263	81.40 274	87.60 237	63.01 301	88.39 157	89.28 227	71.63 228	75.34 300	87.28 281	54.80 292	91.11 308	62.72 329	79.57 322	90.09 276

test1		78.40 257	77.40 263	81.40 274	87.60 237	63.01 301	88.39 157	89.28 227	71.63 228	75.34 300	87.28 281	54.80 292	91.11 308	62.72 329	79.57 322	90.09 276

FMVSNet3		77.88 273	76.85 275	80.97 289	86.84 274	62.36 317	86.52 236	88.77 256	71.13 241	75.34 300	86.66 303	54.07 302	91.10 311	62.72 329	79.57 322	89.45 302

CMPMVS	51.72 21	70.19 394	68.16 396	76.28 387	73.15 484	57.55 394	79.47 402	83.92 363	48.02 484	56.48 483	84.81 351	43.13 425	86.42 399	62.67 332	81.81 296	84.89 428
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
sd_testset		77.70 279	77.40 263	78.60 349	89.03 165	60.02 362	79.00 410	85.83 338	75.19 137	76.61 269	89.98 198	54.81 291	85.46 411	62.63 333	83.55 269	90.33 264

0.4-1-1-0.1		70.93 383	67.94 402	79.91 316	79.35 441	61.27 337	78.95 412	82.19 394	63.36 393	67.50 414	69.40 488	39.83 448	91.04 315	62.44 334	68.40 439	87.40 365

usedtu_dtu_shiyan1		76.43 305	75.32 307	79.76 323	83.00 376	60.72 349	81.74 362	88.76 260	68.99 310	72.98 344	84.19 366	56.41 282	90.27 337	62.39 335	79.40 326	88.31 341

FE-MVSNET3		76.43 305	75.32 307	79.76 323	83.00 376	60.72 349	81.74 362	88.76 260	68.99 310	72.98 344	84.19 366	56.41 282	90.27 337	62.39 335	79.40 326	88.31 341

FMVSNet2		78.20 263	77.21 267	81.20 281	87.60 237	62.89 308	87.47 191	89.02 245	71.63 228	75.29 306	87.28 281	54.80 292	91.10 311	62.38 337	79.38 328	89.61 298

testdata2													91.01 316	62.37 338

testing11		75.14 327	74.01 325	78.53 353	88.16 201	56.38 412	80.74 382	80.42 419	70.67 257	72.69 350	83.72 378	43.61 423	89.86 346	62.29 339	83.76 262	89.36 305

CP-MVSNet		78.22 261	78.34 235	77.84 367	87.83 220	54.54 436	87.94 177	91.17 156	77.65 48	73.48 337	88.49 248	62.24 207	88.43 376	62.19 340	74.07 400	90.55 254

XXY-MVS		75.41 323	75.56 299	74.96 403	83.59 356	57.82 388	80.59 385	83.87 365	66.54 347	74.93 317	88.31 253	63.24 186	80.09 452	62.16 341	76.85 358	86.97 386

pmmvs6		74.69 330	73.39 334	78.61 348	81.38 412	57.48 395	86.64 230	87.95 284	64.99 374	70.18 377	86.61 304	50.43 353	89.52 353	62.12 342	70.18 430	88.83 325

1112_ss		77.40 287	76.43 286	80.32 304	89.11 164	60.41 358	83.65 325	87.72 292	62.13 413	73.05 343	86.72 297	62.58 200	89.97 345	62.11 343	80.80 308	90.59 253

nomal-1		73.10 358	71.76 353	77.13 381	82.58 390	65.50 220	73.53 461	79.64 430	66.14 350	72.17 357	81.27 414	46.45 394	81.47 445	62.08 344	81.93 294	84.42 434

0.3-1-1-0.015		70.03 397	66.80 421	79.72 326	78.18 452	61.07 341	77.63 430	82.32 393	62.65 406	65.50 440	67.29 489	37.62 462	90.91 322	61.99 345	68.04 441	87.19 377

PS-CasMVS		78.01 270	78.09 240	77.77 369	87.71 230	54.39 438	88.02 173	91.22 153	77.50 56	73.26 339	88.64 243	60.73 236	88.41 377	61.88 346	73.88 404	90.53 255

CDS-MVSNet		79.07 241	77.70 255	83.17 211	87.60 237	68.23 143	84.40 308	86.20 332	67.49 331	76.36 275	86.54 309	61.54 220	90.79 326	61.86 347	87.33 191	90.49 257
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
OpenMVS	72.83 10	79.77 220	78.33 236	84.09 164	85.17 316	69.91 95	90.57 69	90.97 162	66.70 340	72.17 357	91.91 124	54.70 296	93.96 149	61.81 348	90.95 117	88.41 340

0.4-1-1-0.2		70.01 398	66.86 420	79.44 334	77.61 458	60.64 353	76.77 437	82.34 392	62.40 409	65.91 438	66.65 490	40.05 445	90.83 324	61.77 349	68.24 440	86.86 388

K. test v3		71.19 379	68.51 392	79.21 339	83.04 375	57.78 390	84.35 309	76.91 454	72.90 208	62.99 459	82.86 396	39.27 450	91.09 313	61.65 350	52.66 489	88.75 329

CHOSEN 1792x2688		77.63 283	75.69 295	83.44 197	89.98 124	68.58 131	78.70 415	87.50 296	56.38 461	75.80 287	86.84 293	58.67 258	91.40 298	61.58 351	85.75 229	90.34 263

dtuonly		69.95 399	69.98 382	69.85 449	73.09 485	49.46 474	74.55 456	76.40 457	57.56 455	67.82 409	86.31 316	50.89 349	74.23 487	61.46 352	81.71 297	85.86 412

PCF-MVS	73.52 7	80.38 206	78.84 225	85.01 109	87.71 230	68.99 115	83.65 325	91.46 149	63.00 398	77.77 240	90.28 192	66.10 153	95.09 101	61.40 353	88.22 172	90.94 238
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HY-MVS	69.67 12	77.95 271	77.15 268	80.36 302	87.57 246	60.21 361	83.37 337	87.78 290	66.11 351	75.37 299	87.06 292	63.27 184	90.48 335	61.38 354	82.43 287	90.40 261

HyFIR lowres test		77.53 284	75.40 303	83.94 182	89.59 133	66.62 192	80.36 389	88.64 269	56.29 462	76.45 272	85.17 343	57.64 267	93.28 197	61.34 355	83.10 279	91.91 203

PMMVS		69.34 405	68.67 391	71.35 441	75.67 468	62.03 324	75.17 448	73.46 470	50.00 481	68.68 396	79.05 440	52.07 325	78.13 459	61.16 356	82.77 282	73.90 486

FMVSNet1		77.44 285	76.12 291	81.40 274	86.81 275	63.01 301	88.39 157	89.28 227	70.49 267	74.39 326	87.28 281	49.06 375	91.11 308	60.91 357	78.52 335	90.09 276

sss		73.60 344	73.64 332	73.51 421	82.80 384	55.01 431	76.12 440	81.69 400	62.47 408	74.68 321	85.85 325	57.32 271	78.11 460	60.86 358	80.93 304	87.39 366

Test_1112_low_res		76.40 308	75.44 301	79.27 337	89.28 153	58.09 380	81.69 365	87.07 312	59.53 435	72.48 352	86.67 302	61.30 227	89.33 356	60.81 359	80.15 317	90.41 260

sc_t1		72.19 373	69.51 385	80.23 307	84.81 326	61.09 340	84.68 291	80.22 424	60.70 423	71.27 367	83.58 382	36.59 465	89.24 359	60.41 360	63.31 465	90.37 262

BH-untuned		79.47 227	78.60 228	82.05 258	89.19 158	65.91 207	86.07 254	88.52 271	72.18 219	75.42 296	87.69 271	61.15 231	93.54 180	60.38 361	86.83 203	86.70 393

WTY-MVS		75.65 318	75.68 296	75.57 394	86.40 287	56.82 403	77.92 428	82.40 390	65.10 370	76.18 280	87.72 269	63.13 192	80.90 449	60.31 362	81.96 292	89.00 318

pmmvs4		74.03 340	71.91 351	80.39 300	81.96 401	68.32 137	81.45 369	82.14 395	59.32 436	69.87 385	85.13 344	52.40 317	88.13 380	60.21 363	74.74 396	84.73 431

FBQ-MVS		77.66 282	76.04 292	82.50 245	88.78 178	63.76 278	86.60 232	84.86 350	70.85 251	77.63 242	82.83 397	47.83 382	92.10 259	60.18 364	84.82 242	91.65 212

PEN-MVS		77.73 276	77.69 256	77.84 367	87.07 270	53.91 441	87.91 179	91.18 155	77.56 53	73.14 342	88.82 238	61.23 229	89.17 361	59.95 365	72.37 415	90.43 259

CR-MVSNet		73.37 349	71.27 362	79.67 329	81.32 415	65.19 232	75.92 442	80.30 422	59.92 431	72.73 348	81.19 415	52.50 315	86.69 394	59.84 366	77.71 346	87.11 382

mvs5depth		69.45 404	67.45 413	75.46 398	73.93 475	55.83 420	79.19 407	83.23 375	66.89 336	71.63 364	83.32 386	33.69 473	85.09 414	59.81 367	55.34 486	85.46 417

lessismore_v0				78.97 342	81.01 418	57.15 399		65.99 491		61.16 466	82.82 398	39.12 452	91.34 300	59.67 368	46.92 496	88.43 339

CNLPA		78.08 266	76.79 277	81.97 261	90.40 111	71.07 73	87.59 188	84.55 354	66.03 354	72.38 354	89.64 211	57.56 268	86.04 403	59.61 369	83.35 274	88.79 327

BH-RMVSNet		79.61 222	78.44 232	83.14 212	89.38 147	65.93 206	84.95 286	87.15 309	73.56 187	78.19 228	89.79 206	56.67 279	93.36 195	59.53 370	86.74 204	90.13 272

FE-MVSNET2		72.88 365	71.28 361	77.67 370	78.30 450	57.78 390	84.43 305	88.92 252	69.56 290	64.61 448	81.67 412	46.73 393	88.54 375	59.33 371	67.99 442	86.69 394

MS-PatchMatch		73.83 341	72.67 343	77.30 379	83.87 348	66.02 202	81.82 360	84.66 352	61.37 420	68.61 398	82.82 398	47.29 384	88.21 378	59.27 372	84.32 254	77.68 479

test_post1							78.90 414				5.43 542	48.81 379	85.44 412	59.25 373

SCA		74.22 335	72.33 348	79.91 316	84.05 344	62.17 321	79.96 397	79.29 435	66.30 349	72.38 354	80.13 430	51.95 327	88.60 373	59.25 373	77.67 349	88.96 320

FE-MVS		77.78 275	75.68 296	84.08 165	88.09 207	66.00 204	83.13 342	87.79 289	68.42 322	78.01 233	85.23 341	45.50 410	95.12 95	59.11 375	85.83 228	91.11 229

SixPastTwentyTwo		73.37 349	71.26 363	79.70 327	85.08 321	57.89 386	85.57 265	83.56 369	71.03 247	65.66 439	85.88 323	42.10 433	92.57 237	59.11 375	63.34 464	88.65 333

WR-MVS_H		78.51 256	78.49 230	78.56 351	88.02 210	56.38 412	88.43 154	92.67 75	77.14 69	73.89 331	87.55 276	66.25 150	89.24 359	58.92 377	73.55 407	90.06 280

PLC	70.83 11	78.05 268	76.37 289	83.08 216	91.88 85	67.80 159	88.19 167	89.46 216	64.33 382	69.87 385	88.38 251	53.66 306	93.58 173	58.86 378	82.73 283	87.86 353
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
RPSCF		73.23 356	71.46 357	78.54 352	82.50 392	59.85 363	82.18 357	82.84 387	58.96 440	71.15 370	89.41 223	45.48 411	84.77 418	58.82 379	71.83 421	91.02 235

EU-MVSNet		68.53 413	67.61 410	71.31 442	78.51 447	47.01 482	84.47 300	84.27 359	42.27 491	66.44 434	84.79 352	40.44 443	83.76 424	58.76 380	68.54 438	83.17 447

pmmvs-eth3d		70.50 390	67.83 405	78.52 354	77.37 461	66.18 199	81.82 360	81.51 402	58.90 441	63.90 455	80.42 425	42.69 428	86.28 400	58.56 381	65.30 459	83.11 449

TAMVS		78.89 247	77.51 262	83.03 219	87.80 221	67.79 160	84.72 290	85.05 348	67.63 328	76.75 264	87.70 270	62.25 206	90.82 325	58.53 382	87.13 196	90.49 257

WBMVS		73.43 346	72.81 342	75.28 400	87.91 215	50.99 466	78.59 418	81.31 406	65.51 363	74.47 325	84.83 350	46.39 395	86.68 395	58.41 383	77.86 344	88.17 347

ACMH+	68.96 14	76.01 314	74.01 325	82.03 259	88.60 184	65.31 230	88.86 131	87.55 294	70.25 274	67.75 411	87.47 279	41.27 438	93.19 209	58.37 384	75.94 374	87.60 358

tpm		72.37 369	71.71 354	74.35 411	82.19 397	52.00 454	79.22 406	77.29 451	64.56 377	72.95 346	83.68 380	51.35 337	83.26 432	58.33 385	75.80 375	87.81 354

BH-w/o		78.21 262	77.33 266	80.84 291	88.81 171	65.13 234	84.87 287	87.85 288	69.75 287	74.52 324	84.74 353	61.34 226	93.11 214	58.24 386	85.84 227	84.27 435

Vis-MVSNet (Re-imp)		78.36 259	78.45 231	78.07 363	88.64 183	51.78 459	86.70 227	79.63 431	74.14 171	75.11 311	90.83 171	61.29 228	89.75 349	58.10 387	91.60 101	92.69 168

MVP-Stereo		76.12 311	74.46 321	81.13 284	85.37 312	69.79 97	84.42 307	87.95 284	65.03 372	67.46 416	85.33 338	53.28 311	91.73 277	58.01 388	83.27 276	81.85 462
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ambc				75.24 401	73.16 483	50.51 469	63.05 499	87.47 297		64.28 450	77.81 452	17.80 500	89.73 350	57.88 389	60.64 475	85.49 416

TR-MVS		77.44 285	76.18 290	81.20 281	88.24 197	63.24 295	84.61 297	86.40 328	67.55 330	77.81 238	86.48 311	54.10 301	93.15 211	57.75 390	82.72 284	87.20 376

F-COLMAP		76.38 309	74.33 323	82.50 245	89.28 153	66.95 190	88.41 156	89.03 244	64.05 386	66.83 425	88.61 244	46.78 391	92.89 224	57.48 391	78.55 334	87.67 356

EG-PatchMatch MVS		74.04 338	71.82 352	80.71 294	84.92 324	67.42 172	85.86 260	88.08 277	66.04 353	64.22 451	83.85 372	35.10 470	92.56 238	57.44 392	80.83 307	82.16 460

PatchmatchNet		73.12 357	71.33 360	78.49 355	83.18 368	60.85 347	79.63 400	78.57 440	64.13 383	71.73 362	79.81 435	51.20 343	85.97 404	57.40 393	76.36 371	88.66 332
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DTE-MVSNet		76.99 293	76.80 276	77.54 376	86.24 289	53.06 451	87.52 189	90.66 172	77.08 73	72.50 351	88.67 242	60.48 244	89.52 353	57.33 394	70.74 427	90.05 281

UnsupCasMVSNet_eth		67.33 421	65.99 425	71.37 439	73.48 480	51.47 462	75.16 449	85.19 344	65.20 367	60.78 467	80.93 422	42.35 429	77.20 464	57.12 395	53.69 488	85.44 418

pmmvs5		71.55 377	70.20 381	75.61 393	77.83 454	56.39 411	81.74 362	80.89 408	57.76 451	67.46 416	84.49 354	49.26 372	85.32 413	57.08 396	75.29 389	85.11 425

testing3-2		75.12 328	75.19 310	74.91 404	90.40 111	45.09 490	80.29 391	78.42 441	78.37 41	76.54 271	87.75 268	44.36 417	87.28 391	57.04 397	83.49 271	92.37 183

Anonymous20240521		68.80 409	67.22 417	73.55 420	74.33 473	54.11 439	83.18 340	85.61 340	58.15 447	61.68 464	80.94 420	30.71 480	81.27 447	57.00 398	73.34 411	85.28 420

mvsany_test1		62.30 444	61.26 448	65.41 467	69.52 492	54.86 433	66.86 486	49.78 509	46.65 485	68.50 402	83.21 388	49.15 373	66.28 500	56.93 399	60.77 474	75.11 484

TransMVSNet (Re)		75.39 325	74.56 318	77.86 366	85.50 309	57.10 400	86.78 224	86.09 335	72.17 220	71.53 365	87.34 280	63.01 193	89.31 357	56.84 400	61.83 470	87.17 378

tt0320-xc		70.11 395	67.45 413	78.07 363	85.33 313	59.51 369	83.28 338	78.96 438	58.77 442	67.10 422	80.28 428	36.73 464	87.42 389	56.83 401	59.77 478	87.29 373

test_vis3_rt		49.26 464	47.02 466	56.00 479	54.30 508	45.27 489	66.76 488	48.08 510	36.83 498	44.38 497	53.20 508	7.17 513	64.07 503	56.77 402	55.66 483	58.65 500

EPMVS		69.02 407	68.16 396	71.59 437	79.61 437	49.80 473	77.40 432	66.93 489	62.82 403	70.01 380	79.05 440	45.79 405	77.86 462	56.58 403	75.26 390	87.13 381

KD-MVS_self_test		68.81 408	67.59 411	72.46 432	74.29 474	45.45 485	77.93 427	87.00 313	63.12 395	63.99 454	78.99 444	42.32 430	84.77 418	56.55 404	64.09 463	87.16 380

tpm2		73.26 354	71.46 357	78.63 347	83.34 361	56.71 406	80.65 384	80.40 420	56.63 460	73.55 336	82.02 410	51.80 333	91.24 303	56.35 405	78.42 340	87.95 350

LTVRE_ROB	69.57 13	76.25 310	74.54 319	81.41 273	88.60 184	64.38 263	79.24 405	89.12 242	70.76 255	69.79 387	87.86 267	49.09 374	93.20 207	56.21 406	80.16 316	86.65 395
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
ACMH	67.68 16	75.89 315	73.93 327	81.77 265	88.71 181	66.61 193	88.62 147	89.01 246	69.81 283	66.78 426	86.70 301	41.95 435	91.51 292	55.64 407	78.14 343	87.17 378
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CHOSEN 280x420		66.51 428	64.71 430	71.90 435	81.45 410	63.52 288	57.98 503	68.95 484	53.57 470	62.59 461	76.70 458	46.22 400	75.29 483	55.25 408	79.68 321	76.88 481

tt0320		70.49 391	68.03 399	77.89 365	84.78 327	59.12 371	83.55 330	80.44 418	58.13 448	67.43 418	80.41 426	39.26 451	87.54 388	55.12 409	63.18 466	86.99 385

dtuonlycased		68.45 415	67.29 416	71.92 434	80.18 427	54.90 432	79.76 399	80.38 421	60.11 429	62.57 462	76.44 462	49.34 369	82.31 437	55.05 410	61.77 471	78.53 477

UBG		73.08 359	72.27 349	75.51 396	88.02 210	51.29 464	78.35 422	77.38 450	65.52 361	73.87 332	82.36 403	45.55 408	86.48 398	55.02 411	84.39 253	88.75 329

EPNet_dtu		75.46 321	74.86 313	77.23 380	82.57 391	54.60 435	86.89 218	83.09 379	71.64 227	66.25 435	85.86 324	55.99 284	88.04 381	54.92 412	86.55 207	89.05 314
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsany_test3		53.99 455	51.45 460	61.61 472	55.51 507	44.74 492	63.52 497	45.41 513	43.69 490	58.11 478	76.45 460	17.99 499	63.76 504	54.77 413	47.59 495	76.34 482

PVSNet	64.34 18	72.08 375	70.87 370	75.69 392	86.21 290	56.44 410	74.37 457	80.73 411	62.06 414	70.17 378	82.23 407	42.86 427	83.31 431	54.77 413	84.45 251	87.32 372

ITE_SJBPF				78.22 358	81.77 404	60.57 354		83.30 373	69.25 299	67.54 413	87.20 286	36.33 467	87.28 391	54.34 415	74.62 397	86.80 390

SSC-MVS3.2		73.35 352	73.39 334	73.23 422	85.30 314	49.01 475	74.58 455	81.57 401	75.21 135	73.68 334	85.58 332	52.53 313	82.05 440	54.33 416	77.69 348	88.63 334

MDTV_nov1_ep13_2view						37.79 504	75.16 449		55.10 466	66.53 430		49.34 369		53.98 417		87.94 351

gg-mvs-nofinetune		69.95 399	67.96 400	75.94 389	83.07 373	54.51 437	77.23 434	70.29 478	63.11 396	70.32 375	62.33 493	43.62 422	88.69 371	53.88 418	87.76 184	84.62 432

PatchMatch-RL		72.38 368	70.90 369	76.80 385	88.60 184	67.38 175	79.53 401	76.17 460	62.75 404	69.36 390	82.00 411	45.51 409	84.89 417	53.62 419	80.58 311	78.12 478

test_f		52.09 460	50.82 461	55.90 480	53.82 510	42.31 499	59.42 502	58.31 505	36.45 499	56.12 486	70.96 484	12.18 505	57.79 508	53.51 420	56.57 482	67.60 493

Patchmtry		70.74 386	69.16 389	75.49 397	80.72 419	54.07 440	74.94 453	80.30 422	58.34 445	70.01 380	81.19 415	52.50 315	86.54 396	53.37 421	71.09 426	85.87 411

USDC		70.33 392	68.37 393	76.21 388	80.60 421	56.23 415	79.19 407	86.49 326	60.89 421	61.29 465	85.47 335	31.78 477	89.47 355	53.37 421	76.21 372	82.94 453

LF4IMVS		64.02 440	62.19 443	69.50 451	70.90 490	53.29 448	76.13 439	77.18 452	52.65 473	58.59 475	80.98 419	23.55 493	76.52 469	53.06 423	66.66 446	78.68 476

PAPM		77.68 280	76.40 288	81.51 270	87.29 258	61.85 327	83.78 321	89.59 212	64.74 375	71.23 368	88.70 240	62.59 199	93.66 172	52.66 424	87.03 198	89.01 316

dmvs_re		71.14 380	70.58 374	72.80 429	81.96 401	59.68 365	75.60 446	79.34 434	68.55 318	69.27 393	80.72 423	49.42 367	76.54 468	52.56 425	77.79 345	82.19 459

CL-MVSNet_self_test		72.37 369	71.46 357	75.09 402	79.49 439	53.53 443	80.76 381	85.01 349	69.12 304	70.51 372	82.05 409	57.92 264	84.13 422	52.27 426	66.00 450	87.60 358

tpm cat1		70.57 388	68.31 394	77.35 378	82.41 395	57.95 385	78.08 424	80.22 424	52.04 474	68.54 401	77.66 453	52.00 326	87.84 384	51.77 427	72.07 420	86.25 399

our_test_3		69.14 406	67.00 418	75.57 394	79.80 434	58.80 372	77.96 426	77.81 444	59.55 434	62.90 460	78.25 449	47.43 383	83.97 423	51.71 428	67.58 444	83.93 441

MDTV_nov1_ep13			69.97 383		83.18 368	53.48 444	77.10 436	80.18 426	60.45 424	69.33 391	80.44 424	48.89 378	86.90 393	51.60 429	78.51 336

myMVS_eth3d28		73.62 343	73.53 333	73.90 418	88.20 198	47.41 480	78.06 425	79.37 433	74.29 167	73.98 330	84.29 361	44.67 413	83.54 428	51.47 430	87.39 190	90.74 246

JIA-IIPM		66.32 430	62.82 442	76.82 384	77.09 462	61.72 330	65.34 492	75.38 461	58.04 450	64.51 449	62.32 494	42.05 434	86.51 397	51.45 431	69.22 434	82.21 458

testing222		74.04 338	72.66 344	78.19 359	87.89 216	55.36 426	81.06 376	79.20 436	71.30 238	74.65 322	83.57 383	39.11 453	88.67 372	51.43 432	85.75 229	90.53 255

MSDG		73.36 351	70.99 367	80.49 299	84.51 335	65.80 212	80.71 383	86.13 334	65.70 358	65.46 441	83.74 376	44.60 414	90.91 322	51.13 433	76.89 356	84.74 430

PatchT		68.46 414	67.85 403	70.29 447	80.70 420	43.93 493	72.47 463	74.88 464	60.15 428	70.55 371	76.57 459	49.94 360	81.59 442	50.58 434	74.83 395	85.34 419

GG-mvs-BLEND				75.38 399	81.59 407	55.80 421	79.32 404	69.63 480		67.19 420	73.67 477	43.24 424	88.90 369	50.41 435	84.50 247	81.45 464

KD-MVS_2432*1600		66.22 431	63.89 434	73.21 423	75.47 471	53.42 445	70.76 471	84.35 356	64.10 384	66.52 431	78.52 446	34.55 471	84.98 415	50.40 436	50.33 493	81.23 465

miper_refine_blended		66.22 431	63.89 434	73.21 423	75.47 471	53.42 445	70.76 471	84.35 356	64.10 384	66.52 431	78.52 446	34.55 471	84.98 415	50.40 436	50.33 493	81.23 465

AllTest		70.96 382	68.09 398	79.58 331	85.15 318	63.62 279	84.58 298	79.83 427	62.31 410	60.32 470	86.73 295	32.02 475	88.96 367	50.28 438	71.57 423	86.15 402

TestCases				79.58 331	85.15 318	63.62 279		79.83 427	62.31 410	60.32 470	86.73 295	32.02 475	88.96 367	50.28 438	71.57 423	86.15 402

TAPA-MVS	73.13 9	79.15 238	77.94 243	82.79 235	89.59 133	62.99 305	88.16 169	91.51 145	65.77 357	77.14 258	91.09 162	60.91 235	93.21 204	50.26 440	87.05 197	92.17 197
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
YYNet1		65.03 435	62.91 440	71.38 438	75.85 467	56.60 408	69.12 479	74.66 468	57.28 457	54.12 487	77.87 451	45.85 404	74.48 485	49.95 441	61.52 473	83.05 450

MDA-MVSNet_test_wron		65.03 435	62.92 439	71.37 439	75.93 464	56.73 404	69.09 480	74.73 466	57.28 457	54.03 488	77.89 450	45.88 403	74.39 486	49.89 442	61.55 472	82.99 452

tpmvs		71.09 381	69.29 387	76.49 386	82.04 399	56.04 417	78.92 413	81.37 405	64.05 386	67.18 421	78.28 448	49.74 364	89.77 348	49.67 443	72.37 415	83.67 443

SD_0403		74.65 331	74.77 315	74.29 412	86.20 291	47.42 479	83.71 323	85.12 345	69.30 296	68.50 402	87.95 266	59.40 252	86.05 402	49.38 444	83.35 274	89.40 303

ppachtmachnet_test		70.04 396	67.34 415	78.14 360	79.80 434	61.13 338	79.19 407	80.59 413	59.16 438	65.27 443	79.29 439	46.75 392	87.29 390	49.33 445	66.72 445	86.00 408

UnsupCasMVSNet_bld		63.70 441	61.53 447	70.21 448	73.69 478	51.39 463	72.82 462	81.89 397	55.63 465	57.81 479	71.80 481	38.67 455	78.61 457	49.26 446	52.21 491	80.63 469

UWE-MVS		72.13 374	71.49 356	74.03 416	86.66 281	47.70 477	81.40 371	76.89 455	63.60 392	75.59 289	84.22 365	39.94 446	85.62 408	48.98 447	86.13 217	88.77 328

dp		66.80 425	65.43 426	70.90 446	79.74 436	48.82 476	75.12 451	74.77 465	59.61 433	64.08 453	77.23 456	42.89 426	80.72 450	48.86 448	66.58 447	83.16 448

FMVSNet5		69.50 403	67.96 400	74.15 414	82.97 381	55.35 427	80.01 396	82.12 396	62.56 407	63.02 457	81.53 413	36.92 463	81.92 441	48.42 449	74.06 401	85.17 424

thres100view900		76.50 301	75.55 300	79.33 336	89.52 136	56.99 401	85.83 262	83.23 375	73.94 176	76.32 276	87.12 289	51.89 331	91.95 266	48.33 450	83.75 263	89.07 309

tfpn200view9		76.42 307	75.37 305	79.55 333	89.13 160	57.65 392	85.17 277	83.60 367	73.41 193	76.45 272	86.39 313	52.12 321	91.95 266	48.33 450	83.75 263	89.07 309

thres400		76.50 301	75.37 305	79.86 318	89.13 160	57.65 392	85.17 277	83.60 367	73.41 193	76.45 272	86.39 313	52.12 321	91.95 266	48.33 450	83.75 263	90.00 282

LCM-MVSNet		54.25 454	49.68 464	67.97 462	53.73 511	45.28 488	66.85 487	80.78 410	35.96 500	39.45 503	62.23 495	8.70 510	78.06 461	48.24 453	51.20 492	80.57 471

RPMNet		73.51 345	70.49 376	82.58 244	81.32 415	65.19 232	75.92 442	92.27 97	57.60 453	72.73 348	76.45 460	52.30 318	95.43 80	48.14 454	77.71 346	87.11 382

thres600view7		76.50 301	75.44 301	79.68 328	89.40 145	57.16 398	85.53 271	83.23 375	73.79 180	76.26 277	87.09 290	51.89 331	91.89 270	48.05 455	83.72 266	90.00 282

TDRefinement		67.49 419	64.34 431	76.92 383	73.47 481	61.07 341	84.86 288	82.98 383	59.77 432	58.30 477	85.13 344	26.06 486	87.89 383	47.92 456	60.59 476	81.81 463

thres200		75.55 319	74.47 320	78.82 345	87.78 224	57.85 387	83.07 346	83.51 370	72.44 215	75.84 286	84.42 356	52.08 324	91.75 275	47.41 457	83.64 268	86.86 388

PVSNet_0	57.27 20	61.67 446	59.27 449	68.85 455	79.61 437	57.44 396	68.01 481	73.44 471	55.93 464	58.54 476	70.41 485	44.58 415	77.55 463	47.01 458	35.91 501	71.55 490

DP-MVS		76.78 297	74.57 317	83.42 198	93.29 53	69.46 106	88.55 151	83.70 366	63.98 388	70.20 376	88.89 236	54.01 304	94.80 116	46.66 459	81.88 295	86.01 406

COLMAP_ROB	66.92 17	73.01 360	70.41 378	80.81 292	87.13 262	65.63 216	88.30 164	84.19 361	62.96 399	63.80 456	87.69 271	38.04 459	92.56 238	46.66 459	74.91 394	84.24 436
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet		70.69 387	69.30 386	74.88 405	84.52 334	56.35 414	75.87 444	79.42 432	64.59 376	67.76 410	82.41 402	41.10 439	81.54 443	46.64 461	81.34 299	86.75 392

LS3D		76.95 295	74.82 314	83.37 201	90.45 109	67.36 176	89.15 121	86.94 315	61.87 416	69.52 388	90.61 181	51.71 335	94.53 127	46.38 462	86.71 205	88.21 346

ETVMVS		72.25 372	71.05 366	75.84 390	87.77 226	51.91 456	79.39 403	74.98 463	69.26 298	73.71 333	82.95 393	40.82 442	86.14 401	46.17 463	84.43 252	89.47 301

MDA-MVSNet-bldmvs		66.68 426	63.66 436	75.75 391	79.28 442	60.56 355	73.92 459	78.35 442	64.43 378	50.13 493	79.87 434	44.02 420	83.67 425	46.10 464	56.86 480	83.03 451

new-patchmatchnet		61.73 445	61.73 445	61.70 471	72.74 487	24.50 519	69.16 478	78.03 443	61.40 418	56.72 482	75.53 472	38.42 456	76.48 470	45.95 465	57.67 479	84.13 438

ArgMatch-SfM		44.04 470	39.87 475	56.58 478	50.92 515	36.22 506	59.86 501	27.68 519	33.67 504	42.15 500	71.07 483	3.10 521	59.10 506	45.79 466	24.54 508	74.41 485

WB-MVSnew		71.96 376	71.65 355	72.89 428	84.67 333	51.88 457	82.29 355	77.57 446	62.31 410	73.67 335	83.00 392	53.49 309	81.10 448	45.75 467	82.13 290	85.70 413

TinyColmap		67.30 422	64.81 429	74.76 407	81.92 403	56.68 407	80.29 391	81.49 403	60.33 425	56.27 485	83.22 387	24.77 490	87.66 387	45.52 468	69.47 432	79.95 473

pmmvs3		57.79 450	54.26 455	68.37 458	64.02 501	56.72 405	75.12 451	65.17 493	40.20 493	52.93 489	69.86 487	20.36 497	75.48 480	45.45 469	55.25 487	72.90 488

ArgMatch-Sym		43.72 471	39.92 474	55.10 484	52.36 513	37.56 505	61.93 500	23.00 521	35.80 501	43.62 498	70.22 486	3.22 519	55.93 510	45.35 470	23.80 510	71.81 489

OpenMVS_ROB	64.09 19	70.56 389	68.19 395	77.65 372	80.26 424	59.41 370	85.01 284	82.96 384	58.76 443	65.43 442	82.33 404	37.63 461	91.23 304	45.34 471	76.03 373	82.32 457

test0.0.03 1		68.00 418	67.69 408	68.90 454	77.55 459	47.43 478	75.70 445	72.95 474	66.66 341	66.56 429	82.29 406	48.06 380	75.87 477	44.97 472	74.51 398	83.41 445

testgi		66.67 427	66.53 423	67.08 464	75.62 469	41.69 500	75.93 441	76.50 456	66.11 351	65.20 446	86.59 305	35.72 469	74.71 484	43.71 473	73.38 410	84.84 429

Anonymous20231206		68.60 410	67.80 406	71.02 444	80.23 426	50.75 468	78.30 423	80.47 416	56.79 459	66.11 437	82.63 401	46.35 398	78.95 456	43.62 474	75.70 376	83.36 446

FE-MVSNET		67.25 423	65.33 427	73.02 427	75.86 466	52.54 452	80.26 393	80.56 414	63.80 391	60.39 468	79.70 436	41.41 437	84.66 420	43.34 475	62.62 468	81.86 461

tfpnnormal		74.39 332	73.16 338	78.08 362	86.10 295	58.05 381	84.65 294	87.53 295	70.32 271	71.22 369	85.63 330	54.97 290	89.86 346	43.03 476	75.02 393	86.32 398

MIMVSNet1		68.58 411	66.78 422	73.98 417	80.07 429	51.82 458	80.77 380	84.37 355	64.40 380	59.75 473	82.16 408	36.47 466	83.63 426	42.73 477	70.33 429	86.48 397

usedtu_dtu_shiyan2		64.75 438	61.63 446	74.10 415	70.64 491	53.18 450	82.10 359	81.27 407	56.22 463	56.39 484	74.67 474	27.94 484	83.56 427	42.71 478	62.73 467	85.57 415

ttmdpeth		59.91 448	57.10 452	68.34 459	67.13 497	46.65 484	74.64 454	67.41 488	48.30 483	62.52 463	85.04 348	20.40 496	75.93 476	42.55 479	45.90 499	82.44 456

test20.03		67.45 420	66.95 419	68.94 453	75.48 470	44.84 491	77.50 431	77.67 445	66.66 341	63.01 458	83.80 374	47.02 387	78.40 458	42.53 480	68.86 437	83.58 444

ADS-MVSNet2		66.20 433	63.33 437	74.82 406	79.92 430	58.75 373	67.55 483	75.19 462	53.37 471	65.25 444	75.86 469	42.32 430	80.53 451	41.57 481	68.91 435	85.18 422

ADS-MVSNet		64.36 439	62.88 441	68.78 456	79.92 430	47.17 481	67.55 483	71.18 476	53.37 471	65.25 444	75.86 469	42.32 430	73.99 489	41.57 481	68.91 435	85.18 422

Patchmatch-test		64.82 437	63.24 438	69.57 450	79.42 440	49.82 472	63.49 498	69.05 483	51.98 476	59.95 472	80.13 430	50.91 345	70.98 493	40.66 483	73.57 406	87.90 352

MVS-HIRNet		59.14 449	57.67 451	63.57 469	81.65 405	43.50 494	71.73 465	65.06 494	39.59 495	51.43 490	57.73 501	38.34 457	82.58 436	39.53 484	73.95 402	64.62 496

WAC-MVS						42.58 496								39.46 485

myMVS_eth3d		67.02 424	66.29 424	69.21 452	84.68 330	42.58 496	78.62 416	73.08 472	66.65 344	66.74 427	79.46 437	31.53 478	82.30 438	39.43 486	76.38 369	82.75 454

DSMNet-mixed		57.77 451	56.90 453	60.38 473	67.70 495	35.61 507	69.18 477	53.97 507	32.30 506	57.49 480	79.88 433	40.39 444	68.57 499	38.78 487	72.37 415	76.97 480

N_pmnet		52.79 459	53.26 457	51.40 487	78.99 444	7.68 535	69.52 475	3.89 535	51.63 477	57.01 481	74.98 473	40.83 441	65.96 501	37.78 488	64.67 461	80.56 472

PatchmatchNet1														37.67 489	64.79 460	80.58 470
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
testing3		68.56 412	67.67 409	71.22 443	87.33 253	42.87 495	83.06 347	71.54 475	70.36 268	69.08 394	84.38 358	30.33 481	85.69 407	37.50 490	75.45 384	85.09 426

MVStest1		56.63 452	52.76 458	68.25 460	61.67 503	53.25 449	71.67 466	68.90 485	38.59 496	50.59 492	83.05 391	25.08 488	70.66 494	36.76 491	38.56 500	80.83 468

test_0402		72.79 366	70.44 377	79.84 319	88.13 204	65.99 205	85.93 257	84.29 358	65.57 360	67.40 419	85.49 334	46.92 388	92.61 234	35.88 492	74.38 399	80.94 467

new_pmnet		50.91 462	50.29 462	52.78 486	68.58 494	34.94 509	63.71 496	56.63 506	39.73 494	44.95 496	65.47 492	21.93 495	58.48 507	34.98 493	56.62 481	64.92 495

APD_test1		53.31 458	49.93 463	63.42 470	65.68 498	50.13 470	71.59 467	66.90 490	34.43 502	40.58 502	71.56 482	8.65 511	76.27 472	34.64 494	55.36 485	63.86 497

Syy-MVS		68.05 417	67.85 403	68.67 457	84.68 330	40.97 501	78.62 416	73.08 472	66.65 344	66.74 427	79.46 437	52.11 323	82.30 438	32.89 495	76.38 369	82.75 454

dmvs_testset		62.63 443	64.11 433	58.19 475	78.55 446	24.76 518	75.28 447	65.94 492	67.91 327	60.34 469	76.01 468	53.56 307	73.94 490	31.79 496	67.65 443	75.88 483

UWE-MVS-28		65.32 434	64.93 428	66.49 465	78.70 445	38.55 503	77.86 429	64.39 496	62.00 415	64.13 452	83.60 381	41.44 436	76.00 475	31.39 497	80.89 305	84.92 427

ANet_high		50.57 463	46.10 467	63.99 468	48.67 516	39.13 502	70.99 470	80.85 409	61.39 419	31.18 505	57.70 502	17.02 501	73.65 491	31.22 498	15.89 517	79.18 475

EGC-MVSNET		52.07 461	47.05 465	67.14 463	83.51 358	60.71 351	80.50 387	67.75 486	0.07 556	0.43 558	75.85 471	24.26 491	81.54 443	28.82 499	62.25 469	59.16 499

PMMVS2		40.82 472	38.86 476	46.69 488	53.84 509	16.45 526	48.61 506	49.92 508	37.49 497	31.67 504	60.97 496	8.14 512	56.42 509	28.42 500	30.72 505	67.19 494

tmp_tt		18.61 487	21.40 487	10.23 511	4.82 558	10.11 530	34.70 511	30.74 518	1.48 533	23.91 513	26.07 526	28.42 483	13.41 530	27.12 501	15.35 519	7.17 533

test_method		31.52 476	29.28 479	38.23 493	27.03 526	6.50 540	20.94 519	62.21 499	4.05 527	22.35 515	52.50 509	13.33 503	47.58 513	27.04 502	34.04 503	60.62 498

DenseAffine		31.97 474	28.22 480	43.21 491	43.10 518	27.10 513	46.21 507	11.36 525	24.92 509	27.70 508	58.81 500	1.09 525	46.50 516	26.95 503	13.85 521	56.02 502

PDCNetPlus		24.75 482	22.46 486	31.64 499	35.53 521	17.00 525	32.00 514	9.46 526	18.43 514	18.56 523	51.31 510	1.65 523	33.00 521	26.51 504	8.70 526	44.91 511

RoMa-SfM		28.67 479	25.38 483	38.54 492	32.61 523	22.48 520	40.24 508	7.23 529	21.81 512	26.66 510	60.46 499	0.96 526	41.72 517	26.47 505	11.95 522	51.40 506

testf1		45.72 465	41.96 469	57.00 476	56.90 505	45.32 486	66.14 489	59.26 503	26.19 507	30.89 506	60.96 497	4.14 516	70.64 495	26.39 506	46.73 497	55.04 503

APD_test2		45.72 465	41.96 469	57.00 476	56.90 505	45.32 486	66.14 489	59.26 503	26.19 507	30.89 506	60.96 497	4.14 516	70.64 495	26.39 506	46.73 497	55.04 503

FPMVS		53.68 457	51.64 459	59.81 474	65.08 499	51.03 465	69.48 476	69.58 481	41.46 492	40.67 501	72.32 480	16.46 502	70.00 497	24.24 508	65.42 458	58.40 501

DKM		25.67 481	23.01 485	33.64 498	32.08 524	19.25 524	37.50 510	5.52 531	18.67 513	23.58 514	55.44 506	0.64 532	34.02 519	23.95 509	9.73 524	47.66 509

Gipuma		45.18 468	41.86 471	55.16 483	77.03 463	51.52 461	32.50 513	80.52 415	32.46 505	27.12 509	35.02 521	9.52 509	75.50 479	22.31 510	60.21 477	38.45 515
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
RoMa-HiRes		21.63 484	19.64 489	27.59 501	22.40 528	14.25 528	29.71 516	4.10 533	15.42 517	21.09 518	54.77 507	0.72 530	28.87 522	21.01 511	7.52 530	39.65 513

DKM-HiRes		20.87 485	19.15 490	26.02 503	25.34 527	14.13 529	29.63 517	3.62 538	14.53 518	20.13 519	50.55 511	0.47 540	24.22 526	20.96 512	7.15 531	39.70 512

dongtai		45.42 467	45.38 468	45.55 489	73.36 482	26.85 516	67.72 482	34.19 515	54.15 469	49.65 494	56.41 505	25.43 487	62.94 505	19.45 513	28.09 506	46.86 510

DeepMVS_CX				27.40 502	40.17 520	26.90 515		24.59 520	17.44 516	23.95 512	48.61 514	9.77 508	26.48 523	18.06 514	24.47 509	28.83 520

WB-MVS		54.94 453	54.72 454	55.60 482	73.50 479	20.90 521	74.27 458	61.19 500	59.16 438	50.61 491	74.15 475	47.19 386	75.78 478	17.31 515	35.07 502	70.12 491

PMVS	37.38 22	44.16 469	40.28 473	55.82 481	40.82 519	42.54 498	65.12 493	63.99 497	34.43 502	24.48 511	57.12 503	3.92 518	76.17 474	17.10 516	55.52 484	48.75 507
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 478	25.89 482	43.81 490	44.55 517	35.46 508	28.87 518	39.07 514	18.20 515	18.58 522	40.18 517	2.68 522	47.37 514	17.07 517	23.78 511	48.60 508
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SSC-MVS		53.88 456	53.59 456	54.75 485	72.87 486	19.59 522	73.84 460	60.53 502	57.58 454	49.18 495	73.45 478	46.34 399	75.47 481	16.20 518	32.28 504	69.20 492

E-PMN		31.77 475	30.64 477	35.15 496	52.87 512	27.67 512	57.09 504	47.86 511	24.64 510	16.40 525	33.05 522	11.23 507	54.90 511	14.46 519	18.15 515	22.87 522

LoFTR		27.52 480	24.27 484	37.29 495	34.75 522	19.27 523	33.78 512	21.60 522	12.42 519	21.61 517	56.59 504	0.91 527	40.37 518	13.94 520	22.80 512	52.22 505

PMatch-SfM		14.15 491	12.67 495	18.59 507	12.84 534	7.03 537	17.41 520	2.28 540	6.63 522	12.96 527	43.56 516	0.09 557	16.11 529	13.90 521	4.38 541	32.63 519

EMVS		30.81 477	29.65 478	34.27 497	50.96 514	25.95 517	56.58 505	46.80 512	24.01 511	15.53 526	30.68 525	12.47 504	54.43 512	12.81 522	17.05 516	22.43 523

kuosan		39.70 473	40.40 472	37.58 494	64.52 500	26.98 514	65.62 491	33.02 516	46.12 486	42.79 499	48.99 512	24.10 492	46.56 515	12.16 523	26.30 507	39.20 514

MVS_clip		11.37 494	13.03 494	6.40 515	15.78 532	6.79 538	11.98 528	1.47 548	1.89 530	19.38 520	35.95 520	3.13 520	3.09 538	12.10 524	15.54 518	9.34 525

VLMVS_CLIP		15.14 489	16.11 491	12.23 510	12.32 535	7.35 536	15.53 522	20.73 523	4.02 528	22.32 516	31.59 523	4.37 515	21.02 528	11.59 525	22.52 513	8.32 526

MASt3R-SfM		13.55 492	13.93 493	12.41 509	10.54 539	5.97 541	16.61 521	6.07 530	4.50 525	16.53 524	48.67 513	0.73 529	9.44 532	11.56 526	10.18 523	21.81 524

PMatch-Up-SfM		10.76 495	9.99 498	13.09 508	9.50 542	4.83 542	12.94 527	1.40 549	4.65 524	10.16 530	37.54 519	0.07 560	10.94 531	10.71 527	2.92 552	23.50 521

wuyk23d		16.82 488	15.94 492	19.46 506	58.74 504	31.45 510	39.22 509	3.74 537	6.84 521	6.04 533	2.70 556	1.27 524	24.29 525	10.54 528	14.40 520	2.63 540

ELoFTR		14.23 490	11.56 496	22.24 504	11.02 536	6.56 539	13.59 525	7.57 528	5.55 523	11.96 529	39.09 518	0.21 545	24.93 524	9.43 529	5.66 535	35.22 517

MatchFormer		22.13 483	19.86 488	28.93 500	28.66 525	15.74 527	31.91 515	17.10 524	7.75 520	18.87 521	47.50 515	0.62 534	33.92 520	7.49 530	18.87 514	37.14 516

GLUNet-SfM		12.90 493	10.00 497	21.62 505	13.58 533	8.30 533	10.19 529	9.30 527	4.31 526	12.18 528	30.90 524	0.50 538	22.76 527	4.89 531	4.14 542	33.79 518

SP-DiffGlue		4.29 505	4.46 508	3.77 520	3.68 559	2.12 550	5.97 534	2.22 541	1.10 534	4.89 536	13.93 532	0.66 531	1.95 544	2.47 532	5.24 536	7.22 532

VLMVS		4.54 503	4.93 506	3.37 522	4.86 557	2.23 549	3.38 543	1.77 547	0.23 555	7.94 531	11.34 535	4.62 514	2.44 539	2.43 533	7.76 529	5.44 537

XFeat-MNN		4.39 504	4.49 507	4.10 516	2.88 561	1.91 556	5.86 535	2.57 539	1.06 535	5.04 535	13.99 531	0.43 542	4.47 536	2.00 534	6.55 533	5.92 536

XFeat-NN		3.78 510	3.96 514	3.23 523	2.65 562	1.53 561	4.99 536	1.92 545	0.81 540	4.77 538	12.37 534	0.38 543	3.39 537	1.64 535	6.13 534	4.77 538

MVS_baseline		3.29 511	4.00 513	1.16 537	3.08 560	0.09 565	1.26 552	0.24 564	0.04 558	6.52 532	16.19 530	0.30 544	0.00 561	1.53 536	6.83 532	3.39 539

SP-LightGlue		4.27 506	4.41 509	3.86 517	10.99 537	1.99 553	8.19 530	2.06 543	0.98 537	2.37 541	8.29 536	0.56 536	2.10 541	1.27 537	4.99 537	7.48 529

SP-SuperGlue		4.24 507	4.38 510	3.81 519	10.75 538	2.00 552	8.18 531	2.09 542	1.00 536	2.41 540	8.29 536	0.56 536	2.05 543	1.27 537	4.91 538	7.39 530

SP-NN		4.00 509	4.12 512	3.63 521	9.92 541	1.81 558	7.94 533	1.90 546	0.86 538	2.15 543	8.00 539	0.50 538	2.09 542	1.20 539	4.63 540	6.98 534

SP-MNN		4.14 508	4.24 511	3.82 518	10.32 540	1.83 557	8.11 532	1.99 544	0.82 539	2.23 542	8.27 538	0.47 540	2.14 540	1.20 539	4.77 539	7.49 528

ALIKED-LG		8.61 496	8.70 500	8.33 512	20.63 529	8.70 532	15.50 523	4.61 532	2.19 529	5.84 534	18.70 527	0.80 528	8.06 533	1.03 541	8.97 525	8.25 527

ALIKED-MNN		7.86 497	7.83 503	7.97 513	19.40 530	8.86 531	14.48 524	3.90 534	1.59 531	4.74 539	16.49 528	0.59 535	7.65 534	0.91 542	8.34 528	7.39 530

ALIKED-NN		7.51 498	7.61 504	7.21 514	18.26 531	8.10 534	13.45 526	3.88 536	1.50 532	4.87 537	16.47 529	0.64 532	7.00 535	0.88 543	8.50 527	6.52 535

SIFT-NN		2.77 512	2.92 515	2.34 524	8.70 543	3.08 543	4.46 537	1.01 551	0.68 541	1.46 544	5.49 540	0.16 546	1.65 545	0.26 544	4.04 543	2.27 541

SIFT-MNN		2.63 513	2.75 516	2.25 525	8.10 544	2.84 544	4.08 538	1.02 550	0.68 541	1.28 545	5.34 543	0.15 547	1.64 546	0.26 544	3.88 545	2.27 541

testmvs		6.04 501	8.02 502	0.10 540	0.08 563	0.03 567	69.74 474	0.04 565	0.05 557	0.31 559	1.68 557	0.02 563	0.04 559	0.24 546	0.02 558	0.25 556

SIFT-NN-UMatch		2.26 517	2.39 520	1.89 530	6.21 552	2.08 551	3.76 540	0.83 554	0.66 543	1.04 549	5.09 544	0.14 548	1.52 549	0.23 547	3.51 547	2.07 545

SIFT-NN-NCMNet		2.52 514	2.64 517	2.14 526	7.53 546	2.74 545	4.00 539	0.98 552	0.65 544	1.24 547	5.08 546	0.14 548	1.60 547	0.23 547	3.94 544	2.07 545

SIFT-NN-CMatch		2.31 516	2.41 519	2.00 528	6.59 550	2.34 548	3.48 542	0.83 554	0.65 544	1.28 545	5.09 544	0.14 548	1.52 549	0.23 547	3.41 548	2.14 543

SIFT-UMatch		2.16 519	2.30 522	1.72 532	6.99 548	1.97 555	3.32 544	0.70 558	0.64 548	0.91 551	4.86 548	0.12 554	1.49 552	0.22 550	2.97 551	1.72 550

SIFT-ConvMatch		2.25 518	2.37 521	1.90 529	7.29 547	2.37 547	3.21 546	0.75 556	0.65 544	1.03 550	4.91 547	0.12 554	1.51 551	0.22 550	3.13 550	1.81 548

SIFT-NN-PointCN		2.07 520	2.18 523	1.74 531	5.75 553	1.65 560	3.27 545	0.73 557	0.60 551	1.07 548	4.62 550	0.13 551	1.43 553	0.21 552	3.22 549	2.12 544

test123		6.12 500	8.11 501	0.14 539	0.06 564	0.09 565	71.05 469	0.03 566	0.04 558	0.25 560	1.30 558	0.05 562	0.03 560	0.21 552	0.01 559	0.29 555

SIFT-UM-Cal		1.97 522	2.12 525	1.52 534	6.57 551	1.67 559	2.93 547	0.57 561	0.62 550	0.83 554	4.55 551	0.11 556	1.37 555	0.20 554	2.69 554	1.53 553

SIFT-NCM-Cal		2.40 515	2.52 518	2.05 527	7.74 545	2.54 546	3.75 541	0.84 553	0.65 544	0.89 552	4.78 549	0.13 551	1.60 547	0.19 555	3.71 546	2.01 547

SIFT-CM-Cal		2.02 521	2.13 524	1.67 533	6.79 549	1.99 553	2.79 548	0.64 559	0.63 549	0.87 553	4.48 552	0.13 551	1.41 554	0.19 555	2.70 553	1.61 552

SIFT-PCN-Cal		1.72 523	1.82 527	1.39 535	5.64 554	1.19 563	2.39 550	0.53 562	0.55 553	0.72 555	3.90 553	0.09 557	1.22 557	0.17 557	2.42 556	1.76 549

SIFT-PointCN		1.72 523	1.83 526	1.36 536	5.55 555	1.22 562	2.59 549	0.59 560	0.55 553	0.71 556	3.77 554	0.08 559	1.24 556	0.17 557	2.48 555	1.63 551

SIFT-NCMNet		1.44 525	1.56 528	1.08 538	5.14 556	1.07 564	1.97 551	0.32 563	0.56 552	0.64 557	3.23 555	0.07 560	1.01 558	0.14 559	1.95 557	1.15 554

mmdepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

monomultidepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

test_blank		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uanet_test		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

DCPMVS		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

cdsmvs_eth3d_5k		19.96 486	26.61 481	0.00 541	0.00 565	0.00 568	0.00 553	89.26 230	0.00 560	0.00 561	88.61 244	61.62 219	0.00 561	0.00 560	0.00 560	0.00 557

pcd_1.5k_mvsjas		5.26 502	7.02 505	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	63.15 189	0.00 561	0.00 560	0.00 560	0.00 557

sosnet-low-res		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

sosnet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uncertanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

Regformer		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

ab-mvs-re		7.23 499	9.64 499	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	86.72 297	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

PatchmatchNet2					0.00 565	30.51 511	67.30 485	67.46 487	50.92 480
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													65.90 502
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip				87.28 46	92.85 69	72.05 50	93.28 12	93.32 38	76.52 90	88.91 33	93.52 77	77.30 18	96.67 34		91.98 95	93.13 146

FOURS1					95.00 10	72.39 41	95.06 1	93.84 21	74.49 159	91.30 17

test_one_0601					95.07 7	71.46 60		94.14 10	78.27 42	92.05 13	95.74 8	80.83 12

eth-test2					0.00 565

eth-test					0.00 565

test_241102_ONE					95.30 2	70.98 74		94.06 15	77.17 68	93.10 1	95.39 18	82.99 1	97.27 14

save fliter					93.80 45	72.35 44	90.47 74	91.17 156	74.31 165

test0726					95.27 5	71.25 66	93.60 7	94.11 11	77.33 60	92.81 3	95.79 5	80.98 10

GSMVS																88.96 320

test_part2					95.06 8	72.65 32				91.80 15

sam_mvs1												51.32 338				88.96 320

sam_mvs												50.01 358

MTGPA								92.02 115

test_post											5.46 541	50.36 354	84.24 421

patchmatchnet-post											74.00 476	51.12 344	88.60 373

MTMP							92.18 39	32.83 517

TEST9					93.26 57	72.96 25	88.75 139	91.89 123	68.44 321	85.00 82	93.10 89	74.36 34	95.41 83

test_8					93.13 61	72.57 35	88.68 145	91.84 127	68.69 316	84.87 86	93.10 89	74.43 32	95.16 93

agg_prior					92.85 69	71.94 53		91.78 131		84.41 98			94.93 105

test_prior4						72.60 34	89.01 126

test_prior				86.33 65	92.61 76	69.59 100		92.97 61					95.48 77			93.91 90

新几何2							86.29 248

旧先验1					91.96 82	65.79 213		86.37 329			93.08 93	69.31 103			92.74 81	88.74 331

原ACMM2							86.86 220

test222					91.50 88	68.26 139	84.16 314	83.20 378	54.63 468	79.74 195	91.63 139	58.97 255			91.42 106	86.77 391

segment_acmp												73.08 45

testdata1							84.14 315		75.71 117

test12				86.80 59	92.63 75	70.70 83		91.79 130		82.71 142		71.67 67	96.16 54		94.50 57	93.54 120

plane_prior7					90.08 118	68.51 133

plane_prior6					89.84 127	68.70 127						60.42 245

plane_prior4											91.00 167

plane_prior3						68.60 130			78.44 37	78.92 210

plane_prior2							91.25 60		79.12 29

plane_prior1					89.90 126

plane_prior						68.71 125	90.38 78		77.62 49						86.16 216

n2								0.00 567

nn								0.00 567

door-mid								69.98 479

test11								92.23 101

door								69.44 482

HQP5-MVS						66.98 187

HQP-NCC					89.33 148		89.17 117		76.41 96	77.23 252

ACMP_Plane					89.33 148		89.17 117		76.41 96	77.23 252

HQP4-MVS										77.24 251			95.11 97			91.03 233

HQP3-MVS								92.19 109							85.99 222

HQP2-MVS												60.17 248

NP-MVS					89.62 132	68.32 137					90.24 194

ACMMP++_ref															81.95 293

ACMMP++															81.25 300

Test By Simon												64.33 175

High-resolution multi-view benchmark