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.

DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 176	76.68 2	97.29 1	95.35 19	82.87 39	91.58 20	97.22 10	79.93 6	99.10 10	83.12 139	97.64 2	97.94 1

TestfortrainingZip				90.29 2	97.24 8	73.67 11	94.47 65	95.75 11	69.78 326	95.97 1	98.23 1	80.55 5	99.42 1		93.26 58	97.76 2

SED-MVS		89.94 9	90.36 10	88.70 20	96.45 13	69.38 67	96.89 6	94.44 58	71.65 285	92.11 11	97.21 11	76.79 10	99.11 7	92.34 38	95.36 14	97.62 3

OPU-MVS				89.97 4	97.52 3	73.15 18	96.89 6				97.00 17	83.82 2	99.15 3	95.72 8	97.63 3	97.62 3

DVP-MVS++		90.53 4	91.09 5	88.87 18	97.31 4	69.91 49	93.96 92	94.37 67	72.48 255	92.07 13	96.85 29	83.82 2	99.15 3	91.53 50	97.42 4	97.55 5

PC_three_1452									80.91 69	94.07 3	96.83 31	83.57 4	99.12 6	95.70 10	97.42 4	97.55 5

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 184	93.00 85	58.16 398	96.72 9	94.41 63	86.50 10	90.25 35	97.83 3	75.46 17	98.67 31	92.78 34	95.49 13	97.32 7

BridgeMVS		89.08 16	88.84 23	89.81 7	93.66 60	75.15 5	90.61 290	93.43 105	84.06 26	86.20 70	90.17 238	72.42 39	96.98 118	93.09 31	95.92 10	97.29 8

LFMVS		84.34 117	82.73 152	89.18 15	94.76 36	73.25 15	94.99 48	91.89 180	71.90 273	82.16 117	93.49 138	47.98 346	97.05 109	82.55 148	84.82 183	97.25 9

sasdasda		86.85 51	86.25 67	88.66 22	91.80 127	71.92 20	93.54 119	91.71 191	80.26 84	87.55 56	95.25 81	63.59 124	96.93 126	88.18 72	84.34 188	97.11 10

canonicalmvs		86.85 51	86.25 67	88.66 22	91.80 127	71.92 20	93.54 119	91.71 191	80.26 84	87.55 56	95.25 81	63.59 124	96.93 126	88.18 72	84.34 188	97.11 10

MCST-MVS		91.08 1	91.46 3	89.94 5	97.66 2	73.37 13	97.13 2	95.58 13	89.33 1	85.77 75	96.26 48	72.84 34	99.38 2	92.64 35	95.93 9	97.08 12

testing915		88.35 20	87.97 38	89.48 14	92.39 101	74.80 7	93.79 106	95.85 9	81.52 54	84.20 92	92.89 149	75.00 18	96.60 139	90.20 59	85.92 166	97.03 13

DELS-MVS		90.05 8	90.09 12	89.94 5	93.14 78	73.88 10	97.01 4	94.40 65	88.32 3	85.71 76	94.91 94	74.11 25	98.91 22	87.26 84	95.94 8	97.03 13
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
MGCFI-Net		85.59 85	85.73 80	85.17 158	91.41 141	62.44 308	92.87 153	91.31 210	79.65 101	86.99 64	95.14 87	62.90 140	96.12 168	87.13 87	84.13 196	96.96 15

CSCG		86.87 50	86.26 66	88.72 19	95.05 34	70.79 35	93.83 105	95.33 20	68.48 345	77.63 195	94.35 112	73.04 32	98.45 36	84.92 112	93.71 51	96.92 16

PRO-TEST		88.25 21	88.30 31	88.11 32	93.04 84	71.42 24	93.31 131	93.19 115	85.25 15	87.41 59	95.02 88	62.21 151	95.99 179	93.13 30	92.14 74	96.91 17

MM		90.87 2	91.52 2	88.92 17	92.12 111	71.10 32	97.02 3	96.04 6	88.70 2	91.57 21	96.19 50	70.12 52	98.91 22	96.83 2	95.06 17	96.76 18

MVS		84.66 107	82.86 150	90.06 3	90.93 151	74.56 8	87.91 359	95.54 16	68.55 343	72.35 278	94.71 99	59.78 185	98.90 24	81.29 168	94.69 34	96.74 19

alignmvs		87.28 44	86.97 51	88.24 31	91.30 143	71.14 31	95.61 27	93.56 96	79.30 115	87.07 62	95.25 81	68.43 60	96.93 126	87.87 75	84.33 190	96.65 20

DeepC-MVS_fast	79.48 2	87.95 31	88.00 36	87.79 36	95.86 29	68.32 105	95.74 22	94.11 75	83.82 28	83.49 102	96.19 50	64.53 107	98.44 37	83.42 137	94.88 25	96.61 21
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_241102_TWO								94.41 63	71.65 285	92.07 13	97.21 11	74.58 22	99.11 7	92.34 38	95.36 14	96.59 22

TSAR-MVS + GP.		87.96 29	88.37 30	86.70 80	93.51 68	65.32 209	95.15 38	93.84 81	78.17 140	85.93 74	94.80 97	75.80 15	98.21 42	89.38 62	88.78 128	96.59 22

CANet		89.61 13	89.99 13	88.46 27	94.39 45	69.71 58	96.53 13	93.78 82	86.89 7	89.68 41	95.78 59	65.94 86	99.10 10	92.99 32	93.91 46	96.58 24

WTY-MVS		86.32 65	85.81 77	87.85 34	92.82 91	69.37 69	95.20 36	95.25 23	82.71 40	81.91 118	94.73 98	67.93 67	97.63 68	79.55 185	82.25 224	96.54 25

VNet		86.20 69	85.65 81	87.84 35	93.92 53	69.99 45	95.73 24	95.94 7	78.43 136	86.00 73	93.07 144	58.22 217	97.00 114	85.22 106	84.33 190	96.52 26

MSC_two_6792asdad				89.60 10	97.31 4	73.22 16		95.05 32					99.07 14	92.01 41	94.77 28	96.51 27

No_MVS				89.60 10	97.31 4	73.22 16		95.05 32					99.07 14	92.01 41	94.77 28	96.51 27

test_0728_SECOND				88.70 20	96.45 13	70.43 40	96.64 10	94.37 67					99.15 3	91.91 44	94.90 22	96.51 27

ET-MVSNet_ETH3D		84.01 128	83.15 142	86.58 89	90.78 156	70.89 33	94.74 57	94.62 50	81.44 59	58.19 427	93.64 134	73.64 29	92.35 367	82.66 146	78.66 274	96.50 30

MVSMamba_PlusPlus		84.97 98	83.65 118	88.93 16	90.17 167	74.04 9	87.84 361	92.69 140	62.18 409	81.47 124	87.64 289	71.47 47	96.28 159	84.69 114	94.74 33	96.47 31

IU-MVS					96.46 12	69.91 49		95.18 26	80.75 71	95.28 2				92.34 38	95.36 14	96.47 31

MGCNet		90.32 6	90.90 7	88.55 26	94.05 51	70.23 43	97.00 5	93.73 89	87.30 4	92.15 10	96.15 52	66.38 81	98.94 21	96.71 3	94.67 35	96.47 31

test_0728_THIRD									72.48 255	90.55 31	96.93 21	76.24 13	99.08 12	91.53 50	94.99 18	96.43 34

MSP-MVS		90.38 5	91.87 1	85.88 122	92.83 89	64.03 255	93.06 139	94.33 69	82.19 47	93.65 4	96.15 52	85.89 1	97.19 101	91.02 54	97.75 1	96.43 34
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
HY-MVS	76.49 5	84.28 118	83.36 131	87.02 65	92.22 106	67.74 127	84.65 394	94.50 55	79.15 119	82.23 116	87.93 284	66.88 75	96.94 124	80.53 176	82.20 226	96.39 36

balanced_ft_v1		84.95 99	83.81 113	88.38 29	93.31 71	73.59 12	85.95 385	92.51 150	77.25 164	73.97 251	89.14 261	59.30 196	95.25 236	92.50 37	90.34 109	96.31 37

DPE-MVS		88.77 19	89.21 20	87.45 49	96.26 22	67.56 132	94.17 78	94.15 74	68.77 341	90.74 29	97.27 8	76.09 14	98.49 35	90.58 58	94.91 21	96.30 38
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		89.41 14	89.73 15	88.45 28	96.40 16	69.99 45	96.64 10	94.52 54	71.92 271	90.55 31	96.93 21	73.77 27	99.08 12	91.91 44	94.90 22	96.29 39
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
MSLP-MVS++		86.27 68	85.91 76	87.35 53	92.01 118	68.97 86	95.04 44	92.70 137	79.04 125	81.50 122	96.50 39	58.98 204	96.78 134	83.49 136	93.93 45	96.29 39

patch_mono-2		89.71 11	90.99 6	85.85 125	96.04 26	63.70 272	95.04 44	95.19 25	86.74 8	91.53 22	95.15 86	73.86 26	97.58 71	93.38 28	92.00 78	96.28 41

test_yl		84.28 118	83.16 140	87.64 40	94.52 43	69.24 76	95.78 19	95.09 29	69.19 333	81.09 129	92.88 151	57.00 235	97.44 80	81.11 171	81.76 234	96.23 42

DCV-MVSNet		84.28 118	83.16 140	87.64 40	94.52 43	69.24 76	95.78 19	95.09 29	69.19 333	81.09 129	92.88 151	57.00 235	97.44 80	81.11 171	81.76 234	96.23 42

FBQ-MVS		86.03 73	85.15 90	88.66 22	93.10 80	73.31 14	92.70 161	95.27 22	81.43 60	82.52 115	91.06 215	67.89 68	96.56 143	79.87 182	82.51 218	96.13 44

CNVR-MVS		90.32 6	90.89 8	88.61 25	96.76 9	70.65 36	96.47 14	94.83 38	84.83 19	89.07 45	96.80 32	70.86 48	99.06 16	92.64 35	95.71 11	96.12 45

HPM-MVS++		89.37 15	89.95 14	87.64 40	95.10 33	68.23 111	95.24 35	94.49 56	82.43 44	88.90 47	96.35 43	71.89 45	98.63 32	88.76 69	96.40 6	96.06 46

SD-MVS		87.49 40	87.49 45	87.50 48	93.60 62	68.82 90	93.90 97	92.63 146	76.86 170	87.90 53	95.76 60	66.17 83	97.63 68	89.06 67	91.48 88	96.05 47
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
PHI-MVS		86.83 53	86.85 57	86.78 74	93.47 69	65.55 203	95.39 32	95.10 28	71.77 281	85.69 77	96.52 37	62.07 155	98.77 28	86.06 99	95.60 12	96.03 48

0.4-1-1-0.2		81.28 198	79.42 221	86.84 69	85.80 319	68.82 90	95.10 40	94.43 60	74.45 209	77.18 204	85.54 322	62.27 148	95.70 206	76.72 210	63.30 398	96.01 49

APDe-MVS		87.54 37	87.84 39	86.65 83	96.07 25	66.30 180	94.84 54	93.78 82	69.35 330	88.39 50	96.34 44	67.74 69	97.66 66	90.62 57	93.44 55	96.01 49
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
aaatest				87.42 50	94.76 36	67.28 141	94.47 65	94.87 35	73.09 243	91.27 25	96.95 19		98.98 17	91.55 46	94.28 39	95.99 51

aaEdge-Enhanced		88.25 21	88.55 27	87.33 55	96.33 19	67.28 141	93.93 94	94.81 39	70.09 320	88.91 46	96.95 19	70.12 52	98.73 30	91.55 46	94.28 39	95.99 51

lupinMVS		87.74 35	87.77 40	87.63 44	89.24 192	71.18 29	96.57 12	92.90 131	82.70 41	87.13 60	95.27 79	64.99 97	95.80 193	89.34 63	91.80 82	95.93 53

NCCC		89.07 17	89.46 17	87.91 33	96.60 11	69.05 83	96.38 15	94.64 48	84.42 23	86.74 65	96.20 49	66.56 80	98.76 29	89.03 68	94.56 36	95.92 54

0.3-1-1-0.015		81.31 196	79.49 219	86.77 77	85.74 321	68.70 99	95.01 47	94.42 61	74.29 214	77.09 207	85.61 321	63.31 131	95.69 208	76.63 211	63.30 398	95.91 55

fmvsm_s_conf0.5_n_9		88.14 24	89.21 20	84.92 167	89.29 187	61.41 340	92.97 144	88.36 373	86.96 6	91.49 23	97.49 5	69.48 57	97.46 78	97.00 1	89.88 115	95.89 56

MED-MVS		89.02 18	89.57 16	87.38 51	94.76 36	67.28 141	94.47 65	94.87 35	70.68 312	91.27 25	96.93 21	76.77 12	98.98 17	91.55 46	94.82 26	95.88 57

TestfortrainingZip a		86.96 48	86.88 55	87.23 56	94.76 36	67.02 155	94.47 65	94.08 77	70.68 312	88.57 49	96.93 21	69.03 58	98.78 27	84.41 121	88.95 127	95.88 57

SMA-MVS		88.14 24	88.29 32	87.67 39	93.21 75	68.72 95	93.85 100	94.03 78	74.18 216	91.74 17	96.67 35	65.61 91	98.42 39	89.24 65	96.08 7	95.88 57
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
dcpmvs_2		87.37 43	87.55 44	86.85 68	95.04 35	68.20 113	90.36 298	90.66 263	79.37 114	81.20 127	93.67 133	74.73 20	96.55 145	90.88 55	92.00 78	95.82 60

Anonymous202405211		77.96 274	75.33 296	85.87 123	93.73 59	64.52 231	94.85 53	85.36 425	62.52 407	76.11 215	90.18 232	29.43 462	97.29 91	68.51 294	77.24 290	95.81 61

fmvsm_l_conf0.5_n_3		87.54 37	88.29 32	85.30 151	86.92 287	62.63 306	95.02 46	90.28 284	84.95 18	90.27 34	96.86 27	65.36 93	97.52 76	94.93 15	90.03 112	95.76 62

RRT-MVS		82.61 170	81.16 180	86.96 67	91.10 147	68.75 93	87.70 364	92.20 162	76.97 168	72.68 265	87.10 300	51.30 310	96.41 153	83.56 135	87.84 138	95.74 63

0.4-1-1-0.1		80.99 207	79.16 229	86.51 100	85.55 326	68.21 112	94.77 55	94.42 61	73.75 227	76.57 212	85.41 324	62.35 147	95.62 212	76.30 216	63.28 400	95.71 64

mvs_anonymous		81.36 195	79.99 207	85.46 140	90.39 163	68.40 103	86.88 376	90.61 265	74.41 210	70.31 303	84.67 332	63.79 117	92.32 369	73.13 241	85.70 171	95.67 65

MG-MVS		87.11 46	86.27 65	89.62 9	97.79 1	76.27 4	94.96 49	94.49 56	78.74 130	83.87 98	92.94 147	64.34 108	96.94 124	75.19 223	94.09 42	95.66 66

PAPR		85.15 93	84.47 101	87.18 59	96.02 27	68.29 106	91.85 216	93.00 126	76.59 181	79.03 175	95.00 89	61.59 161	97.61 70	78.16 202	89.00 125	95.63 67

VDD-MVS		83.06 160	81.81 173	86.81 72	90.86 154	67.70 128	95.40 31	91.50 202	75.46 193	81.78 119	92.34 164	40.09 403	97.13 107	86.85 93	82.04 229	95.60 68

casdiffmvs_mvg		85.66 83	85.18 89	87.09 62	88.22 235	69.35 70	93.74 110	91.89 180	81.47 56	80.10 152	91.45 200	64.80 102	96.35 156	87.23 85	87.69 140	95.58 69
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Effi-MVS+		83.82 134	82.76 151	86.99 66	89.56 179	69.40 65	91.35 251	86.12 416	72.59 252	83.22 106	92.81 154	59.60 189	96.01 178	81.76 161	87.80 139	95.56 70

TSAR-MVS + MP.		88.11 27	88.64 26	86.54 98	91.73 129	68.04 116	90.36 298	93.55 97	82.89 37	91.29 24	92.89 149	72.27 41	96.03 176	87.99 74	94.77 28	95.54 71
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SymmetryMVS		86.32 65	86.39 64	86.12 116	90.52 159	65.95 192	94.88 50	94.58 53	84.69 21	83.67 100	94.10 122	63.16 134	96.91 130	85.31 104	86.59 158	95.51 72

UBG		86.83 53	86.70 58	87.20 58	93.07 82	69.81 53	93.43 127	95.56 15	81.52 54	81.50 122	92.12 172	73.58 30	96.28 159	84.37 122	85.20 177	95.51 72

SteuartSystems-ACMMP		86.82 55	86.90 54	86.58 89	90.42 161	66.38 177	96.09 18	93.87 80	77.73 151	84.01 97	95.66 62	63.39 127	97.94 49	87.40 82	93.55 54	95.42 74
Skip Steuart: Steuart Systems R&D Blog.
SPE-MVS-test		86.14 71	87.01 50	83.52 239	92.63 97	59.36 386	95.49 29	91.92 177	80.09 88	85.46 81	95.53 68	61.82 160	95.77 198	86.77 94	93.37 56	95.41 75

casdiffmvs		85.37 88	84.87 96	86.84 69	88.25 233	69.07 80	93.04 141	91.76 187	81.27 64	80.84 137	92.07 175	64.23 110	96.06 174	84.98 111	87.43 144	95.39 76
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EIA-MVS		84.84 102	84.88 95	84.69 188	91.30 143	62.36 311	93.85 100	92.04 170	79.45 110	79.33 169	94.28 117	62.42 145	96.35 156	80.05 180	91.25 94	95.38 77

testing91		85.93 76	85.31 87	87.78 37	93.59 63	71.47 23	93.50 122	95.08 31	80.26 84	80.53 145	91.93 185	70.43 50	96.51 148	80.32 179	82.13 228	95.37 78

CS-MVS		85.80 79	86.65 62	83.27 251	92.00 119	58.92 390	95.31 33	91.86 182	79.97 89	84.82 87	95.40 71	62.26 149	95.51 223	86.11 98	92.08 76	95.37 78

GG-mvs-BLEND				86.53 99	91.91 124	69.67 60	75.02 468	94.75 42		78.67 185	90.85 218	77.91 8	94.56 270	72.25 254	93.74 49	95.36 80

fmvsm_l_conf0.5_n_9		88.24 23	89.36 18	84.85 172	88.15 237	61.94 323	95.65 26	89.70 313	85.54 13	92.07 13	97.33 7	67.51 71	97.27 96	96.23 5	92.07 77	95.35 81

agg_prior2														86.41 95	94.75 32	95.33 82

3Dnovator+	73.60 7	82.10 183	80.60 197	86.60 86	90.89 153	66.80 167	95.20 36	93.44 104	74.05 218	67.42 347	92.49 159	49.46 331	97.65 67	70.80 270	91.68 84	95.33 82

Casviewmamba		84.58 110	83.95 110	86.47 101	87.22 267	67.76 126	92.71 159	90.96 244	80.81 70	79.29 171	91.85 187	62.20 152	96.33 158	84.60 116	85.91 167	95.32 84

baseline		85.01 96	84.44 102	86.71 79	88.33 230	68.73 94	90.24 303	91.82 186	81.05 68	81.18 128	92.50 157	63.69 119	96.08 173	84.45 120	86.71 156	95.32 84

ab-mvs		80.18 225	78.31 240	85.80 127	88.44 223	65.49 206	83.00 418	92.67 141	71.82 279	77.36 200	85.01 328	54.50 269	96.59 140	76.35 215	75.63 300	95.32 84

test9_res														89.41 61	94.96 19	95.29 87

EPNet		87.84 34	88.38 29	86.23 112	93.30 72	66.05 186	95.26 34	94.84 37	87.09 5	88.06 51	94.53 103	66.79 76	97.34 88	83.89 128	91.68 84	95.29 87
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SF-MVS		87.03 47	87.09 49	86.84 69	92.70 95	67.45 138	93.64 114	93.76 85	70.78 310	86.25 68	96.44 40	66.98 74	97.79 57	88.68 70	94.56 36	95.28 89

fmvsm_s_conf0.5_n_10		87.93 32	88.67 25	85.71 132	88.69 206	63.71 270	94.56 63	90.22 289	85.04 17	92.27 8	97.05 14	63.67 120	98.15 44	95.09 12	91.39 90	95.27 90

VDDNet		80.50 217	78.26 241	87.21 57	86.19 306	69.79 54	94.48 64	91.31 210	60.42 425	79.34 168	90.91 217	38.48 411	96.56 143	82.16 150	81.05 240	95.27 90

MVSFormer		83.75 138	82.88 149	86.37 107	89.24 192	71.18 29	89.07 337	90.69 260	65.80 374	87.13 60	94.34 113	64.99 97	92.67 353	72.83 244	91.80 82	95.27 90

jason		86.40 61	86.17 69	87.11 61	86.16 308	70.54 38	95.71 25	92.19 164	82.00 49	84.58 89	94.34 113	61.86 158	95.53 222	87.76 76	90.89 99	95.27 90
jason: jason.
hybridcas		84.65 108	83.95 110	86.74 78	87.18 270	68.78 92	92.94 147	91.36 208	80.47 76	79.32 170	91.67 196	62.13 154	96.19 164	83.15 138	87.36 145	95.25 94

train_agg		87.21 45	87.42 46	86.60 86	94.18 47	67.28 141	94.16 79	93.51 99	71.87 276	85.52 79	95.33 73	68.19 63	97.27 96	89.09 66	94.90 22	95.25 94

MVS_Test		84.16 124	83.20 137	87.05 64	91.56 134	69.82 52	89.99 312	92.05 169	77.77 150	82.84 109	86.57 306	63.93 115	96.09 170	74.91 228	89.18 122	95.25 94

fmvsm_l_mol_unc0.5_1		89.65 12	90.28 11	87.77 38	87.88 248	70.89 33	96.35 16	88.48 370	86.59 9	93.16 5	97.86 2	75.47 16	97.28 95	94.09 22	92.60 67	95.16 97

3Dnovator	73.91 6	82.69 169	80.82 189	88.31 30	89.57 178	71.26 27	92.60 172	94.39 66	78.84 127	67.89 339	92.48 160	48.42 341	98.52 34	68.80 291	94.40 38	95.15 98

testing99		86.01 74	85.47 83	87.63 44	93.62 61	71.25 28	93.47 125	95.23 24	80.42 79	80.60 141	91.95 184	71.73 46	96.50 149	80.02 181	82.22 225	95.13 99

Patchmatch-test		65.86 414	60.94 429	80.62 333	83.75 363	58.83 391	58.91 498	75.26 473	44.50 486	50.95 462	77.09 427	58.81 208	87.90 430	35.13 477	64.03 392	95.12 100

fmvsm_s_conf0.5_n_8		87.96 29	88.93 22	85.07 161	88.43 224	61.78 326	94.73 60	91.74 188	85.87 11	91.66 19	97.50 4	64.03 112	98.33 40	96.28 4	90.08 111	95.10 101

mvsmamba		81.55 191	80.72 192	84.03 219	91.42 138	66.93 163	83.08 415	89.13 337	78.55 134	67.50 345	87.02 301	51.79 301	90.07 412	87.48 80	90.49 105	95.10 101

APD-MVS		85.93 76	85.99 74	85.76 129	95.98 28	65.21 212	93.59 117	92.58 148	66.54 364	86.17 71	95.88 58	63.83 116	97.00 114	86.39 96	92.94 62	95.06 103
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
gg-mvs-nofinetune		77.18 288	74.31 310	85.80 127	91.42 138	68.36 104	71.78 473	94.72 43	49.61 470	77.12 205	45.92 501	77.41 9	93.98 303	67.62 306	93.16 60	95.05 104

test_prior				86.42 105	94.71 41	67.35 140		93.10 121					96.84 132			95.05 104

Patchmatch-RL test		68.17 399	64.49 409	79.19 367	71.22 473	53.93 435	70.07 478	71.54 486	69.22 332	56.79 436	62.89 485	56.58 244	88.61 421	69.53 281	52.61 452	95.03 106

fmvsm_s_conf0.5_n_3		86.88 49	87.99 37	83.58 238	87.26 265	60.74 354	93.21 136	87.94 389	84.22 24	91.70 18	97.27 8	65.91 88	95.02 241	93.95 25	90.42 106	94.99 107

CHOSEN 1792x2688		84.98 97	83.45 125	89.57 12	89.94 171	75.14 6	92.07 200	92.32 155	81.87 50	75.68 219	88.27 275	60.18 179	98.60 33	80.46 177	90.27 110	94.96 108

test_fmvsmconf_n		86.58 59	87.17 48	84.82 174	85.28 331	62.55 307	94.26 77	89.78 304	83.81 29	87.78 55	96.33 45	65.33 94	96.98 118	94.40 20	87.55 142	94.95 109

fmvsm_s_conf0.5_n_6		87.50 39	88.72 24	83.84 224	86.89 289	60.04 374	95.05 42	92.17 167	84.80 20	92.27 8	96.37 41	64.62 104	96.54 146	94.43 19	91.86 80	94.94 110

ACMMP_NAP		86.05 72	85.80 78	86.80 73	91.58 133	67.53 134	91.79 218	93.49 102	74.93 204	84.61 88	95.30 75	59.42 193	97.92 50	86.13 97	94.92 20	94.94 110

E3new		84.94 100	84.36 104	86.69 82	89.06 196	69.31 71	92.68 167	91.29 215	80.72 72	81.03 131	92.14 171	61.89 157	95.91 181	84.59 117	85.85 169	94.86 112

test2506		83.29 153	82.92 148	84.37 204	88.39 227	63.18 292	92.01 203	91.35 209	77.66 153	78.49 188	91.42 201	64.58 106	95.09 240	73.19 240	89.23 120	94.85 113

ECVR-MVS		81.29 197	80.38 202	84.01 220	88.39 227	61.96 321	92.56 177	86.79 405	77.66 153	76.63 210	91.42 201	46.34 370	95.24 237	74.36 232	89.23 120	94.85 113

PAPM_NR		82.97 162	81.84 172	86.37 107	94.10 50	66.76 168	87.66 365	92.84 132	69.96 322	74.07 249	93.57 136	63.10 137	97.50 77	70.66 273	90.58 103	94.85 113

viewmanbaseed2359cas		84.89 101	84.26 106	86.78 74	88.50 215	69.77 56	92.69 166	91.13 226	81.11 66	81.54 121	91.98 181	60.35 176	95.73 200	84.47 119	86.56 159	94.84 116

ETVMVS		84.22 122	83.71 116	85.76 129	92.58 99	68.25 110	92.45 182	95.53 17	79.54 108	79.46 166	91.64 198	70.29 51	94.18 289	69.16 286	82.76 217	94.84 116

CDPH-MVS		85.71 81	85.46 84	86.46 102	94.75 40	67.19 146	93.89 98	92.83 133	70.90 306	83.09 107	95.28 77	63.62 122	97.36 86	80.63 175	94.18 41	94.84 116

test12				87.09 62	94.60 42	68.86 87		92.91 130		82.67 114		65.44 92	97.55 74		93.69 52	94.84 116

viewcassd2359sk11		84.74 105	84.11 107	86.64 84	88.57 209	69.20 78	92.61 170	91.23 217	80.58 73	80.85 136	91.96 182	61.39 163	95.89 183	84.28 123	85.49 174	94.82 120

testing11		86.71 58	86.44 63	87.55 46	93.54 66	71.35 26	93.65 113	95.58 13	81.36 63	80.69 139	92.21 169	72.30 40	96.46 151	85.18 108	83.43 208	94.82 120

testing222		85.18 92	84.69 100	86.63 85	92.91 87	69.91 49	92.61 170	95.80 10	80.31 83	80.38 147	92.27 165	68.73 59	95.19 238	75.94 217	83.27 211	94.81 122

E2		84.45 112	83.74 114	86.56 91	87.90 245	69.06 81	92.53 178	91.13 226	80.35 81	80.58 143	91.69 194	60.70 170	95.84 186	83.80 130	84.99 179	94.79 123

E3		84.45 112	83.74 114	86.56 91	87.90 245	69.06 81	92.53 178	91.13 226	80.35 81	80.58 143	91.69 194	60.70 170	95.84 186	83.80 130	84.99 179	94.79 123

E4		84.00 129	83.19 138	86.46 102	86.99 277	68.85 88	92.39 185	90.99 243	79.94 90	80.17 151	91.36 205	59.73 187	95.79 195	82.87 144	84.22 194	94.74 125

BP-MVS1		86.54 60	86.68 60	86.13 115	87.80 253	67.18 148	92.97 144	95.62 12	79.92 92	82.84 109	94.14 121	74.95 19	96.46 151	82.91 143	88.96 126	94.74 125

PatchmatchNet		77.46 284	74.63 303	85.96 120	89.55 180	70.35 41	79.97 447	89.55 316	72.23 264	70.94 293	76.91 429	57.03 233	92.79 348	54.27 399	81.17 239	94.74 125
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
viewmacassd2359aftdt		84.03 127	83.18 139	86.59 88	86.76 290	69.44 64	92.44 183	90.85 250	80.38 80	80.78 138	91.33 206	58.54 212	95.62 212	82.15 151	85.41 175	94.72 128

viewdifsd2359ckpt09		83.52 148	82.57 160	86.37 107	88.02 242	68.47 101	91.78 221	89.63 314	79.61 103	78.56 186	92.00 180	59.28 197	95.96 180	81.94 155	82.35 219	94.69 129

EPMVS		78.49 264	75.98 287	86.02 118	91.21 145	69.68 59	80.23 442	91.20 218	75.25 199	72.48 274	78.11 415	54.65 268	93.69 316	57.66 387	83.04 212	94.69 129

GSMVS																94.68 131

sam_mvs1												57.85 225				94.68 131

SCA		75.82 317	72.76 338	85.01 164	86.63 293	70.08 44	81.06 435	89.19 331	71.60 290	70.01 306	77.09 427	45.53 377	90.25 404	60.43 373	73.27 316	94.68 131

viewdifsd2359ckpt13		84.08 126	83.21 135	86.70 80	88.49 219	69.55 62	92.25 188	91.14 224	79.71 99	79.73 161	91.72 193	58.83 207	95.89 183	82.06 153	84.99 179	94.66 134

fmvsm_l_conf0.5_n		87.49 40	88.19 34	85.39 143	86.95 282	64.37 241	94.30 75	88.45 371	80.51 75	92.70 6	96.86 27	69.98 54	97.15 106	95.83 7	88.08 136	94.65 135

Vis-MVSNet		80.92 209	79.98 208	83.74 228	88.48 221	61.80 325	93.44 126	88.26 381	73.96 222	77.73 193	91.76 189	49.94 325	94.76 253	65.84 328	90.37 108	94.65 135
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_fmvsmconf0.1_n		85.71 81	86.08 73	84.62 195	80.83 394	62.33 312	93.84 103	88.81 356	83.50 32	87.00 63	96.01 56	63.36 128	96.93 126	94.04 24	87.29 146	94.61 137

viewdifsd2359ckpt07		82.95 164	82.04 167	85.66 134	87.19 269	66.73 169	91.56 237	90.39 276	77.58 156	77.58 198	91.19 212	58.57 211	95.65 209	82.32 149	82.01 230	94.60 138

fmvsm_l_conf0.5_n_a		87.44 42	88.15 35	85.30 151	87.10 274	64.19 250	94.41 70	88.14 382	80.24 87	92.54 7	96.97 18	69.52 56	97.17 102	95.89 6	88.51 131	94.56 139

旧先验1					91.94 120	60.74 354		91.50 202			94.36 108	65.23 95			91.84 81	94.55 140

sss		82.71 168	82.38 164	83.73 230	89.25 189	59.58 381	92.24 190	94.89 34	77.96 143	79.86 155	92.38 162	56.70 241	97.05 109	77.26 207	80.86 246	94.55 140

xiu_mvs_v2_base		87.92 33	87.38 47	89.55 13	91.41 141	76.43 3	95.74 22	93.12 120	83.53 31	89.55 42	95.95 57	53.45 288	97.68 61	91.07 53	92.62 66	94.54 142

PS-MVSNAJ		88.14 24	87.61 43	89.71 8	92.06 114	76.72 1	95.75 21	93.26 111	83.86 27	89.55 42	96.06 54	53.55 284	97.89 53	91.10 52	93.31 57	94.54 142

E5new		83.62 143	82.65 154	86.55 93	86.98 278	69.28 74	91.69 228	90.96 244	79.61 103	79.80 156	91.25 208	58.04 221	95.84 186	81.83 159	83.66 205	94.52 144

E6new		83.62 143	82.65 154	86.55 93	86.98 278	69.29 72	91.69 228	90.95 247	79.60 106	79.80 156	91.25 208	58.04 221	95.84 186	81.84 157	83.67 203	94.52 144

E6		83.62 143	82.65 154	86.55 93	86.98 278	69.29 72	91.69 228	90.95 247	79.60 106	79.80 156	91.25 208	58.04 221	95.84 186	81.84 157	83.67 203	94.52 144

E5		83.62 143	82.65 154	86.55 93	86.98 278	69.28 74	91.69 228	90.96 244	79.61 103	79.80 156	91.25 208	58.04 221	95.84 186	81.83 159	83.66 205	94.52 144

test1111		80.84 210	80.02 205	83.33 246	87.87 249	60.76 352	92.62 169	86.86 404	77.86 147	75.73 218	91.39 203	46.35 369	94.70 262	72.79 246	88.68 130	94.52 144

ZNCC-MVS		85.33 89	85.08 92	86.06 117	93.09 81	65.65 199	93.89 98	93.41 107	73.75 227	79.94 154	94.68 100	60.61 174	98.03 47	82.63 147	93.72 50	94.52 144

MAR-MVS		84.18 123	83.43 126	86.44 104	96.25 23	65.93 194	94.28 76	94.27 71	74.41 210	79.16 174	95.61 64	53.99 279	98.88 26	69.62 280	93.26 58	94.50 150
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
HFP-MVS		84.73 106	84.40 103	85.72 131	93.75 58	65.01 218	93.50 122	93.19 115	72.19 265	79.22 172	94.93 92	59.04 203	97.67 63	81.55 162	92.21 71	94.49 151

fmvsm_s_conf0.5_n_5		86.38 64	86.94 52	84.71 186	84.67 343	63.29 286	94.04 88	89.99 299	82.88 38	87.85 54	96.03 55	62.89 141	96.36 155	94.15 21	89.95 114	94.48 152

ETV-MVS		86.01 74	86.11 71	85.70 133	90.21 166	67.02 155	93.43 127	91.92 177	81.21 65	84.13 96	94.07 126	60.93 169	95.63 210	89.28 64	89.81 116	94.46 153

myMVS_eth3d28		86.31 67	86.15 70	86.78 74	93.56 64	70.49 39	92.94 147	95.28 21	82.47 43	78.70 183	92.07 175	72.45 38	95.41 224	82.11 152	85.78 170	94.44 154

icg_test_0407_2		80.38 220	79.22 228	83.88 222	88.54 210	64.75 223	86.79 377	90.80 254	76.73 176	73.95 252	90.18 232	51.55 306	92.45 362	73.47 236	80.95 241	94.43 155

IMVS_0407		80.80 212	79.39 224	85.00 165	88.54 210	64.75 223	88.40 350	90.80 254	76.73 176	73.95 252	90.18 232	51.55 306	95.81 192	73.47 236	80.95 241	94.43 155

IMVS_0404		78.11 271	76.29 282	83.59 237	88.54 210	64.75 223	84.63 395	90.80 254	76.73 176	61.16 403	90.18 232	40.17 402	91.58 388	73.47 236	80.95 241	94.43 155

IMVS_0403		81.19 200	79.88 209	85.13 160	88.54 210	64.75 223	88.84 342	90.80 254	76.73 176	75.21 228	90.18 232	54.22 277	96.21 163	73.47 236	80.95 241	94.43 155

reproduce-ours		83.51 149	83.33 132	84.06 215	92.18 109	60.49 362	90.74 280	92.04 170	64.35 386	83.24 103	95.59 66	59.05 201	97.27 96	83.61 133	89.17 123	94.41 159

our_new_method		83.51 149	83.33 132	84.06 215	92.18 109	60.49 362	90.74 280	92.04 170	64.35 386	83.24 103	95.59 66	59.05 201	97.27 96	83.61 133	89.17 123	94.41 159

diffmvs		84.28 118	83.83 112	85.61 136	87.40 262	68.02 117	90.88 273	89.24 328	80.54 74	81.64 120	92.52 156	59.83 184	94.52 274	87.32 83	85.11 178	94.29 161
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffseed414692147		82.20 177	80.75 190	86.55 93	87.13 273	69.57 61	91.79 218	90.48 268	78.12 141	78.52 187	90.10 244	55.92 253	95.80 193	72.42 253	82.28 221	94.28 162

reproduce_model		83.15 157	82.96 145	83.73 230	92.02 115	59.74 378	90.37 297	92.08 168	63.70 393	82.86 108	95.48 69	58.62 210	97.17 102	83.06 140	88.42 132	94.26 163

test_fmvsm_n_1920		87.69 36	88.50 28	85.27 154	87.05 276	63.55 279	93.69 111	91.08 234	84.18 25	90.17 37	97.04 16	67.58 70	97.99 48	95.72 8	90.03 112	94.26 163

region2R		84.36 116	84.03 109	85.36 148	93.54 66	64.31 244	93.43 127	92.95 129	72.16 268	78.86 180	94.84 96	56.97 237	97.53 75	81.38 166	92.11 75	94.24 165

test_fmvsmconf0.01_n		83.70 140	83.52 119	84.25 211	75.26 458	61.72 330	92.17 193	87.24 399	82.36 45	84.91 86	95.41 70	55.60 256	96.83 133	92.85 33	85.87 168	94.21 166

GDP-MVS		85.54 86	85.32 86	86.18 113	87.64 256	67.95 120	92.91 151	92.36 154	77.81 148	83.69 99	94.31 115	72.84 34	96.41 153	80.39 178	85.95 165	94.19 167

MTAPA		83.91 132	83.38 130	85.50 139	91.89 125	65.16 214	81.75 427	92.23 158	75.32 198	80.53 145	95.21 84	56.06 251	97.16 105	84.86 113	92.55 69	94.18 168

PMMVS		81.98 185	82.04 167	81.78 295	89.76 175	56.17 421	91.13 264	90.69 260	77.96 143	80.09 153	93.57 136	46.33 371	94.99 244	81.41 165	87.46 143	94.17 169

CostFormer		82.33 174	81.15 181	85.86 124	89.01 199	68.46 102	82.39 424	93.01 124	75.59 191	80.25 150	81.57 374	72.03 43	94.96 245	79.06 193	77.48 286	94.16 170

MVS_111021_HR		86.19 70	85.80 78	87.37 52	93.17 77	69.79 54	93.99 91	93.76 85	79.08 122	78.88 179	93.99 127	62.25 150	98.15 44	85.93 100	91.15 95	94.15 171

onestephybrid01		83.68 141	83.31 134	84.81 177	86.53 296	65.38 208	90.54 291	89.14 336	79.52 109	81.01 132	92.02 177	58.91 205	94.91 250	88.26 71	83.86 200	94.14 172

PVSNet_Blended		86.73 57	86.86 56	86.31 111	93.76 56	67.53 134	96.33 17	93.61 94	82.34 46	81.00 134	93.08 143	63.19 132	97.29 91	87.08 90	91.38 91	94.13 173

viewmamba		83.23 156	82.64 158	85.00 165	86.40 302	66.16 184	90.68 283	88.35 375	79.92 92	78.68 184	92.02 177	58.86 206	94.72 256	85.55 101	83.31 210	94.12 174

hybridnocas07		83.76 137	83.21 135	85.39 143	86.64 291	67.40 139	91.08 265	88.77 359	79.78 98	80.35 148	92.15 170	59.24 199	94.67 263	87.11 89	83.79 201	94.11 175

1112_ss		80.56 216	79.83 211	82.77 262	88.65 207	60.78 350	92.29 187	88.36 373	72.58 253	72.46 275	94.95 90	65.09 96	93.42 326	66.38 322	77.71 279	94.10 176

IB-MVS	77.80 4	82.18 178	80.46 201	87.35 53	89.14 194	70.28 42	95.59 28	95.17 27	78.85 126	70.19 304	85.82 317	70.66 49	97.67 63	72.19 257	66.52 368	94.09 177
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
PAPM		85.89 78	85.46 84	87.18 59	88.20 236	72.42 19	92.41 184	92.77 135	82.11 48	80.34 149	93.07 144	68.27 61	95.02 241	78.39 201	93.59 53	94.09 177

MP-MVS-pluss		85.24 90	85.13 91	85.56 138	91.42 138	65.59 201	91.54 238	92.51 150	74.56 207	80.62 140	95.64 63	59.15 200	97.00 114	86.94 92	93.80 47	94.07 179
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
hybrid		83.58 147	83.00 144	85.34 149	86.38 303	67.51 137	90.92 269	88.87 354	78.49 135	80.59 142	92.09 174	58.77 209	94.46 276	87.12 88	83.74 202	94.06 180

MP-MVS		85.02 95	84.97 94	85.17 158	92.60 98	64.27 246	93.24 133	92.27 157	73.13 239	79.63 164	94.43 106	61.90 156	97.17 102	85.00 110	92.56 68	94.06 180
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DeepC-MVS	77.85 3	85.52 87	85.24 88	86.37 107	88.80 204	66.64 171	92.15 194	93.68 91	81.07 67	76.91 209	93.64 134	62.59 143	98.44 37	85.50 102	92.84 64	94.03 182
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMPR		84.37 115	84.06 108	85.28 153	93.56 64	64.37 241	93.50 122	93.15 118	72.19 265	78.85 181	94.86 95	56.69 242	97.45 79	81.55 162	92.20 72	94.02 183

无先验							92.71 159	92.61 147	62.03 412				97.01 113	66.63 317		93.97 184

XVS		83.87 133	83.47 124	85.05 162	93.22 73	63.78 264	92.92 149	92.66 142	73.99 219	78.18 189	94.31 115	55.25 258	97.41 83	79.16 191	91.58 86	93.95 185

X-MVStestdata		76.86 294	74.13 316	85.05 162	93.22 73	63.78 264	92.92 149	92.66 142	73.99 219	78.18 189	10.19 534	55.25 258	97.41 83	79.16 191	91.58 86	93.95 185

NormalMVS		86.39 62	86.66 61	85.60 137	92.12 111	65.95 192	94.88 50	90.83 251	84.69 21	83.67 100	94.10 122	63.16 134	96.91 130	85.31 104	91.15 95	93.93 187

KinetiMVS		81.43 193	80.11 203	85.38 147	86.60 294	65.47 207	92.90 152	93.54 98	75.33 197	77.31 201	90.39 226	46.81 361	96.75 135	71.65 263	86.46 162	93.93 187

diffmvs_AUTHOR		83.97 130	83.49 122	85.39 143	86.09 310	67.83 123	90.76 278	89.05 344	79.94 90	81.43 125	92.23 168	59.53 190	94.42 278	87.18 86	85.22 176	93.92 189

h-mvs33		83.01 161	82.56 161	84.35 205	89.34 183	62.02 319	92.72 158	93.76 85	81.45 57	82.73 112	92.25 167	60.11 180	97.13 107	87.69 77	62.96 401	93.91 190

CP-MVS		83.71 139	83.40 129	84.65 191	93.14 78	63.84 262	94.59 62	92.28 156	71.03 304	77.41 199	94.92 93	55.21 261	96.19 164	81.32 167	90.70 101	93.91 190

PVSNet	73.49 8	80.05 228	78.63 236	84.31 207	90.92 152	64.97 219	92.47 181	91.05 239	79.18 118	72.43 276	90.51 223	37.05 428	94.06 296	68.06 300	86.00 164	93.90 192

GST-MVS		84.63 109	84.29 105	85.66 134	92.82 91	65.27 210	93.04 141	93.13 119	73.20 237	78.89 176	94.18 120	59.41 194	97.85 55	81.45 164	92.48 70	93.86 193

Test_1112_low_res		79.56 236	78.60 237	82.43 272	88.24 234	60.39 366	92.09 198	87.99 386	72.10 269	71.84 283	87.42 293	64.62 104	93.04 333	65.80 329	77.30 288	93.85 194

GeoE		78.90 253	77.43 258	83.29 249	88.95 200	62.02 319	92.31 186	86.23 412	70.24 318	71.34 292	89.27 258	54.43 273	94.04 299	63.31 354	80.81 248	93.81 195

lecture		84.77 103	84.81 98	84.65 191	92.12 111	62.27 315	94.74 57	92.64 145	68.35 346	85.53 78	95.30 75	59.77 186	97.91 51	83.73 132	91.15 95	93.77 196

thisisatest0515		83.41 151	82.49 162	86.16 114	89.46 182	68.26 108	93.54 119	94.70 45	74.31 213	75.75 217	90.92 216	72.62 36	96.52 147	69.64 278	81.50 237	93.71 197

HyFIR lowres test		81.03 206	79.56 216	85.43 141	87.81 252	68.11 115	90.18 304	90.01 298	70.65 314	72.95 262	86.06 313	63.61 123	94.50 275	75.01 226	79.75 258	93.67 198

fmvsm_s_conf0.5_n_11		87.99 28	89.25 19	84.23 212	89.07 195	61.60 333	94.87 52	89.06 343	85.65 12	91.09 27	97.41 6	68.26 62	97.43 82	95.07 13	92.74 65	93.66 199

CANet_DTU		84.09 125	83.52 119	85.81 126	90.30 164	66.82 165	91.87 214	89.01 346	85.27 14	86.09 72	93.74 131	47.71 352	96.98 118	77.90 204	89.78 118	93.65 200

mPP-MVS		82.96 163	82.44 163	84.52 198	92.83 89	62.92 299	92.76 156	91.85 184	71.52 293	75.61 222	94.24 118	53.48 287	96.99 117	78.97 194	90.73 100	93.64 201

tpmrst		80.57 215	79.14 231	84.84 173	90.10 168	68.28 107	81.70 428	89.72 311	77.63 155	75.96 216	79.54 406	64.94 99	92.71 350	75.43 221	77.28 289	93.55 202

viewmambaseed2359dif		82.60 171	81.91 171	84.67 190	85.83 317	66.09 185	90.50 292	89.01 346	75.46 193	79.64 163	92.01 179	59.51 191	94.38 280	82.99 142	82.26 222	93.54 203

dtuplus		82.25 176	81.42 178	84.71 186	85.38 327	66.05 186	90.62 289	89.27 326	75.16 201	79.22 172	91.76 189	58.05 220	94.56 270	81.18 170	82.19 227	93.52 204

tpm2		79.80 233	77.95 248	85.34 149	88.28 231	68.26 108	81.56 430	91.42 205	70.11 319	77.59 197	80.50 392	67.40 72	94.26 287	67.34 310	77.35 287	93.51 205

SR-MVS		82.81 165	82.58 159	83.50 242	93.35 70	61.16 344	92.23 191	91.28 216	64.48 385	81.27 126	95.28 77	53.71 283	95.86 185	82.87 144	88.77 129	93.49 206

FA-MVS(test-final)		79.12 247	77.23 264	84.81 177	90.54 158	63.98 259	81.35 433	91.71 191	71.09 303	74.85 236	82.94 353	52.85 291	97.05 109	67.97 301	81.73 236	93.41 207

PGM-MVS		83.25 154	82.70 153	84.92 167	92.81 93	64.07 254	90.44 293	92.20 162	71.28 298	77.23 203	94.43 106	55.17 262	97.31 90	79.33 190	91.38 91	93.37 208

新几何1				84.73 183	92.32 103	64.28 245		91.46 204	59.56 432	79.77 160	92.90 148	56.95 238	96.57 142	63.40 352	92.91 63	93.34 209

HPM-MVS		83.25 154	82.95 147	84.17 213	92.25 105	62.88 301	90.91 270	91.86 182	70.30 317	77.12 205	93.96 128	56.75 240	96.28 159	82.04 154	91.34 93	93.34 209
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
TESTMET0.1,1		82.41 173	81.98 170	83.72 232	88.08 238	63.74 266	92.70 161	93.77 84	79.30 115	77.61 196	87.57 291	58.19 218	94.08 294	73.91 235	86.68 157	93.33 211

IS-MVSNet		80.14 226	79.41 222	82.33 278	87.91 244	60.08 373	91.97 207	88.27 379	72.90 248	71.44 291	91.73 192	61.44 162	93.66 317	62.47 362	86.53 160	93.24 212

MonoMVSNet		76.99 292	75.08 299	82.73 263	83.32 369	63.24 288	86.47 381	86.37 408	79.08 122	66.31 360	79.30 408	49.80 328	91.72 383	79.37 188	65.70 373	93.23 213

1314		80.70 213	78.95 233	85.94 121	87.77 255	67.56 132	87.91 359	92.55 149	72.17 267	67.44 346	93.09 142	50.27 321	97.04 112	71.68 262	87.64 141	93.23 213

CDS-MVSNet		81.43 193	80.74 191	83.52 239	86.26 305	64.45 235	92.09 198	90.65 264	75.83 189	73.95 252	89.81 249	63.97 114	92.91 342	71.27 264	82.82 214	93.20 215
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+		81.14 202	80.01 206	84.51 199	90.24 165	65.86 195	94.12 83	89.15 334	73.81 226	75.37 227	88.26 276	57.26 230	94.53 273	66.97 316	84.92 182	93.15 216

API-MVS		82.28 175	80.53 199	87.54 47	96.13 24	70.59 37	93.63 115	91.04 240	65.72 376	75.45 225	92.83 153	56.11 250	98.89 25	64.10 348	89.75 119	93.15 216

fmvsm_s_conf0.5_n_4		86.79 56	87.63 41	84.27 210	86.15 309	61.48 337	94.69 61	91.16 220	83.79 30	90.51 33	96.28 46	64.24 109	98.22 41	95.00 14	86.88 149	93.11 218

test222					89.77 174	61.60 333	89.55 321	89.42 321	56.83 448	77.28 202	92.43 161	52.76 292			91.14 98	93.09 219

TAMVS		80.37 221	79.45 220	83.13 256	85.14 335	63.37 283	91.23 258	90.76 259	74.81 206	72.65 267	88.49 269	60.63 173	92.95 337	69.41 282	81.95 232	93.08 220

fmvsm_s_conf0.5_n		86.39 62	86.91 53	84.82 174	87.36 264	63.54 280	94.74 57	90.02 297	82.52 42	90.14 38	96.92 25	62.93 139	97.84 56	95.28 11	82.26 222	93.07 221

testdata				81.34 309	89.02 198	57.72 402		89.84 303	58.65 437	85.32 83	94.09 124	57.03 233	93.28 327	69.34 283	90.56 104	93.03 222

tpm		78.58 262	77.03 267	83.22 253	85.94 315	64.56 230	83.21 414	91.14 224	78.31 138	73.67 255	79.68 404	64.01 113	92.09 375	66.07 326	71.26 333	93.03 222

test_fmvsmvis_n_1920		83.80 135	83.48 123	84.77 179	82.51 378	63.72 269	91.37 247	83.99 440	81.42 61	77.68 194	95.74 61	58.37 215	97.58 71	93.38 28	86.87 150	93.00 224

GA-MVS		78.33 267	76.23 283	84.65 191	83.65 365	66.30 180	91.44 239	90.14 291	76.01 187	70.32 302	84.02 342	42.50 392	94.72 256	70.98 268	77.00 291	92.94 225

BH-RMVSNet		79.46 240	77.65 252	84.89 170	91.68 131	65.66 198	93.55 118	88.09 384	72.93 245	73.37 258	91.12 214	46.20 373	96.12 168	56.28 392	85.61 173	92.91 226

fmvsm_s_conf0.5_n_a		85.75 80	86.09 72	84.72 184	85.73 322	63.58 277	93.79 106	89.32 324	81.42 61	90.21 36	96.91 26	62.41 146	97.67 63	94.48 18	80.56 251	92.90 227

APD-MVS_3200maxsize		81.64 190	81.32 179	82.59 270	92.36 102	58.74 392	91.39 244	91.01 242	63.35 397	79.72 162	94.62 102	51.82 299	96.14 167	79.71 183	87.93 137	92.89 228

viewdifsd2359ckpt11		79.42 242	77.95 248	83.81 225	83.87 361	63.85 260	89.54 322	87.38 393	77.39 162	74.94 232	89.95 246	51.11 312	94.72 256	79.52 186	67.90 357	92.88 229

viewmsd2359difaftdt		79.42 242	77.96 247	83.81 225	83.88 360	63.85 260	89.54 322	87.38 393	77.39 162	74.94 232	89.95 246	51.11 312	94.72 256	79.52 186	67.90 357	92.88 229

fmvsm_s_conf0.1_n		85.61 84	85.93 75	84.68 189	82.95 375	63.48 282	94.03 90	89.46 318	81.69 52	89.86 39	96.74 33	61.85 159	97.75 59	94.74 17	82.01 230	92.81 231

DP-MVS Recon		82.73 166	81.65 174	85.98 119	97.31 4	67.06 151	95.15 38	91.99 174	69.08 338	76.50 214	93.89 129	54.48 272	98.20 43	70.76 271	85.66 172	92.69 232

UGNet		79.87 232	78.68 235	83.45 244	89.96 170	61.51 335	92.13 195	90.79 258	76.83 172	78.85 181	86.33 310	38.16 414	96.17 166	67.93 303	87.17 147	92.67 233
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
EPP-MVSNet		81.79 187	81.52 175	82.61 268	88.77 205	60.21 370	93.02 143	93.66 92	68.52 344	72.90 263	90.39 226	72.19 42	94.96 245	74.93 227	79.29 267	92.67 233

fmvsm_s_conf0.5_n_7		85.24 90	86.69 59	80.91 327	84.52 348	60.10 372	93.35 130	90.35 277	83.41 33	86.54 67	96.27 47	60.50 175	90.02 413	94.84 16	90.38 107	92.61 235

AstraMVS		80.66 214	79.79 212	83.28 250	85.07 338	61.64 332	92.19 192	90.58 266	79.40 112	74.77 237	90.18 232	45.93 375	95.61 214	83.04 141	76.96 292	92.60 236

PVSNet_Blended_VisFu		83.97 130	83.50 121	85.39 143	90.02 169	66.59 174	93.77 108	91.73 189	77.43 160	77.08 208	89.81 249	63.77 118	96.97 121	79.67 184	88.21 134	92.60 236

MDTV_nov1_ep13_2view						59.90 376	80.13 444		67.65 355	72.79 264		54.33 275		59.83 377		92.58 238

QAPM		79.95 231	77.39 262	87.64 40	89.63 177	71.41 25	93.30 132	93.70 90	65.34 381	67.39 349	91.75 191	47.83 350	98.96 19	57.71 386	89.81 116	92.54 239

fmvsm_s_conf0.1_n_a		84.76 104	84.84 97	84.53 197	80.23 407	63.50 281	92.79 155	88.73 360	80.46 77	89.84 40	96.65 36	60.96 168	97.57 73	93.80 26	80.14 253	92.53 240

dp		75.01 329	72.09 348	83.76 227	89.28 188	66.22 183	79.96 448	89.75 306	71.16 300	67.80 341	77.19 426	51.81 300	92.54 358	50.39 414	71.44 332	92.51 241

guyue		81.23 199	80.57 198	83.21 255	86.64 291	61.85 324	92.52 180	92.78 134	78.69 131	74.92 234	89.42 254	50.07 323	95.35 228	80.79 173	79.31 266	92.42 242

EPNet_dtu		78.80 256	79.26 227	77.43 387	88.06 239	49.71 459	91.96 208	91.95 176	77.67 152	76.56 213	91.28 207	58.51 213	90.20 409	56.37 391	80.95 241	92.39 243
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20240529		76.84 296	74.15 315	84.88 171	91.02 148	64.95 220	93.84 103	91.09 230	53.57 458	73.00 260	87.42 293	35.91 433	97.32 89	69.14 287	72.41 325	92.36 244

SSM_0404		79.46 240	77.65 252	84.91 169	88.37 229	67.04 153	89.59 317	87.03 400	67.99 349	75.45 225	89.32 256	47.98 346	95.34 230	71.23 265	81.90 233	92.34 245

Vis-MVSNet (Re-imp)		79.24 245	79.57 215	78.24 379	88.46 222	52.29 442	90.41 295	89.12 338	74.24 215	69.13 314	91.91 186	65.77 89	90.09 411	59.00 382	88.09 135	92.33 246

原ACMM1				84.42 201	93.21 75	64.27 246		93.40 108	65.39 379	79.51 165	92.50 157	58.11 219	96.69 137	65.27 338	93.96 44	92.32 247

TR-MVS		78.77 258	77.37 263	82.95 259	90.49 160	60.88 348	93.67 112	90.07 293	70.08 321	74.51 240	91.37 204	45.69 376	95.70 206	60.12 376	80.32 252	92.29 248

SR-MVS-dyc-post		81.06 205	80.70 193	82.15 286	92.02 115	58.56 395	90.90 271	90.45 269	62.76 404	78.89 176	94.46 104	51.26 311	95.61 214	78.77 198	86.77 154	92.28 249

RE-MVS-def			80.48 200		92.02 115	58.56 395	90.90 271	90.45 269	62.76 404	78.89 176	94.46 104	49.30 333		78.77 198	86.77 154	92.28 249

LCM-MVSNet-Re		72.93 352	71.84 351	76.18 403	88.49 219	48.02 466	80.07 445	70.17 488	73.96 222	52.25 453	80.09 400	49.98 324	88.24 428	67.35 309	84.23 193	92.28 249

EC-MVSNet		84.53 111	85.04 93	83.01 257	89.34 183	61.37 341	94.42 69	91.09 230	77.91 146	83.24 103	94.20 119	58.37 215	95.40 225	85.35 103	91.41 89	92.27 252

MVS_111021_LR		82.02 184	81.52 175	83.51 241	88.42 225	62.88 301	89.77 315	88.93 351	76.78 173	75.55 223	93.10 141	50.31 320	95.38 227	83.82 129	87.02 148	92.26 253

FE-MVS		75.97 314	73.02 334	84.82 174	89.78 173	65.56 202	77.44 458	91.07 235	64.55 384	72.66 266	79.85 402	46.05 374	96.69 137	54.97 396	80.82 247	92.21 254

BH-w/o		80.49 218	79.30 226	84.05 218	90.83 155	64.36 243	93.60 116	89.42 321	74.35 212	69.09 315	90.15 240	55.23 260	95.61 214	64.61 343	86.43 163	92.17 255

test_vis1_n_1920		81.66 189	82.01 169	80.64 331	82.24 380	55.09 430	94.76 56	86.87 403	81.67 53	84.40 91	94.63 101	38.17 413	94.67 263	91.98 43	83.34 209	92.16 256

UWE-MVS		80.81 211	81.01 187	80.20 341	89.33 185	57.05 414	91.91 212	94.71 44	75.67 190	75.01 231	89.37 255	63.13 136	91.44 395	67.19 313	82.80 216	92.12 257

fmvsm_s_conf0.5_n_2		85.06 94	85.60 82	83.44 245	86.92 287	60.53 361	94.41 70	87.31 397	83.30 34	88.72 48	96.72 34	54.28 276	97.75 59	94.07 23	84.68 187	92.04 258

CVMVSNet		74.04 340	74.27 311	73.33 428	85.33 328	43.94 485	89.53 325	88.39 372	54.33 457	70.37 301	90.13 241	49.17 336	84.05 459	61.83 366	79.36 264	91.99 259

mamba_0408		76.22 305	73.37 328	84.77 179	88.50 215	66.98 159	58.80 499	86.18 414	69.12 336	74.12 246	89.01 264	47.50 353	95.35 228	67.57 307	79.52 259	91.98 260

SSM_04072		74.86 332	73.37 328	79.35 365	88.50 215	66.98 159	58.80 499	86.18 414	69.12 336	74.12 246	89.01 264	47.50 353	79.09 486	67.57 307	79.52 259	91.98 260

SSM_0407		79.09 248	77.21 265	84.75 182	88.50 215	66.98 159	89.21 333	87.03 400	67.99 349	74.12 246	89.32 256	47.98 346	95.29 235	71.23 265	79.52 259	91.98 260

tpm cat1		75.30 324	72.21 347	84.58 196	88.52 214	67.77 125	78.16 456	88.02 385	61.88 415	68.45 330	76.37 438	60.65 172	94.03 301	53.77 403	74.11 310	91.93 263

ACMMP		81.49 192	80.67 194	83.93 221	91.71 130	62.90 300	92.13 195	92.22 161	71.79 280	71.68 287	93.49 138	50.32 319	96.96 122	78.47 200	84.22 194	91.93 263
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
testing3-2		83.11 159	83.15 142	82.98 258	91.92 122	64.01 257	94.39 73	95.37 18	78.32 137	75.53 224	90.06 245	73.18 31	93.18 331	74.34 233	75.27 302	91.77 265

fmvsm_s_conf0.1_n_2		84.40 114	84.78 99	83.27 251	85.25 332	60.41 364	94.13 82	85.69 422	83.05 36	87.99 52	96.37 41	52.75 293	97.68 61	93.75 27	84.05 197	91.71 266

nomal-1		82.17 179	81.45 177	84.34 206	90.99 149	69.47 63	83.86 402	93.64 93	77.94 145	73.62 256	85.72 319	66.65 77	91.90 378	80.76 174	79.90 255	91.64 267

test-LLR		80.10 227	79.56 216	81.72 297	86.93 285	61.17 342	92.70 161	91.54 199	71.51 294	75.62 220	86.94 302	53.83 280	92.38 364	72.21 255	84.76 185	91.60 268

test-mter		79.96 230	79.38 225	81.72 297	86.93 285	61.17 342	92.70 161	91.54 199	73.85 224	75.62 220	86.94 302	49.84 327	92.38 364	72.21 255	84.76 185	91.60 268

thisisatest0530		81.15 201	80.07 204	84.39 203	88.26 232	65.63 200	91.40 242	94.62 50	71.27 299	70.93 294	89.18 259	72.47 37	96.04 175	65.62 333	76.89 293	91.49 270

AUN-MVS		78.37 265	77.43 258	81.17 314	86.60 294	57.45 408	89.46 327	91.16 220	74.11 217	74.40 241	90.49 224	55.52 257	94.57 267	74.73 231	60.43 427	91.48 271

MIMVSNet		71.64 369	68.44 382	81.23 313	81.97 384	64.44 236	73.05 470	88.80 357	69.67 327	64.59 372	74.79 447	32.79 446	87.82 432	53.99 400	76.35 296	91.42 272

hse-mvs2		81.12 204	81.11 185	81.16 315	86.52 298	57.48 407	89.40 328	91.16 220	81.45 57	82.73 112	90.49 224	60.11 180	94.58 265	87.69 77	60.41 428	91.41 273

xiu_mvs_v1_base_debu		82.16 180	81.12 182	85.26 155	86.42 299	68.72 95	92.59 174	90.44 273	73.12 240	84.20 92	94.36 108	38.04 416	95.73 200	84.12 125	86.81 151	91.33 274

xiu_mvs_v1_base		82.16 180	81.12 182	85.26 155	86.42 299	68.72 95	92.59 174	90.44 273	73.12 240	84.20 92	94.36 108	38.04 416	95.73 200	84.12 125	86.81 151	91.33 274

xiu_mvs_v1_base_debi		82.16 180	81.12 182	85.26 155	86.42 299	68.72 95	92.59 174	90.44 273	73.12 240	84.20 92	94.36 108	38.04 416	95.73 200	84.12 125	86.81 151	91.33 274

BH-untuned		78.68 259	77.08 266	83.48 243	89.84 172	63.74 266	92.70 161	88.59 366	71.57 291	66.83 356	88.65 268	51.75 302	95.39 226	59.03 381	84.77 184	91.32 277

HPM-MVS_fast		80.25 224	79.55 218	82.33 278	91.55 135	59.95 375	91.32 253	89.16 333	65.23 382	74.71 239	93.07 144	47.81 351	95.74 199	74.87 230	88.23 133	91.31 278

baseline1		81.84 186	81.03 186	84.28 209	91.60 132	66.62 172	91.08 265	91.66 196	81.87 50	74.86 235	91.67 196	69.98 54	94.92 248	71.76 260	64.75 385	91.29 279

test_cas_vis1_n_1920		80.45 219	80.61 196	79.97 350	78.25 434	57.01 416	94.04 88	88.33 376	79.06 124	82.81 111	93.70 132	38.65 408	91.63 386	90.82 56	79.81 256	91.27 280

baseline2		83.68 141	83.42 128	84.48 200	87.37 263	66.00 189	90.06 307	95.93 8	79.71 99	69.08 316	90.39 226	77.92 7	96.28 159	78.91 196	81.38 238	91.16 281

TAPA-MVS	70.22 12	74.94 330	73.53 325	79.17 368	90.40 162	52.07 443	89.19 335	89.61 315	62.69 406	70.07 305	92.67 155	48.89 340	94.32 281	38.26 471	79.97 254	91.12 282
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
AdaColmap		78.94 252	77.00 269	84.76 181	96.34 18	65.86 195	92.66 168	87.97 388	62.18 409	70.56 297	92.37 163	43.53 388	97.35 87	64.50 346	82.86 213	91.05 283

Elysia		76.45 303	74.17 313	83.30 247	80.43 401	64.12 252	89.58 318	90.83 251	61.78 417	72.53 270	85.92 315	34.30 440	94.81 251	68.10 298	84.01 198	90.97 284

StellarMVS		76.45 303	74.17 313	83.30 247	80.43 401	64.12 252	89.58 318	90.83 251	61.78 417	72.53 270	85.92 315	34.30 440	94.81 251	68.10 298	84.01 198	90.97 284

SD_0403		73.79 344	73.48 327	74.69 415	85.33 328	45.56 481	83.80 403	85.57 423	76.55 183	62.96 391	88.45 270	50.62 318	87.59 438	48.80 424	79.28 268	90.92 286

OMC-MVS		78.67 261	77.91 250	80.95 325	85.76 320	57.40 409	88.49 348	88.67 363	73.85 224	72.43 276	92.10 173	49.29 334	94.55 272	72.73 248	77.89 278	90.91 287

EI-MVSNet-Vis-set		83.77 136	83.67 117	84.06 215	92.79 94	63.56 278	91.76 224	94.81 39	79.65 101	77.87 192	94.09 124	63.35 129	97.90 52	79.35 189	79.36 264	90.74 288

cascas		78.18 268	75.77 290	85.41 142	87.14 272	69.11 79	92.96 146	91.15 223	66.71 363	70.47 298	86.07 312	37.49 422	96.48 150	70.15 276	79.80 257	90.65 289

CR-MVSNet		73.79 344	70.82 360	82.70 265	83.15 371	67.96 118	70.25 476	84.00 438	73.67 232	69.97 308	72.41 455	57.82 226	89.48 417	52.99 407	73.13 317	90.64 290

RPMNet		70.42 378	65.68 398	84.63 194	83.15 371	67.96 118	70.25 476	90.45 269	46.83 479	69.97 308	65.10 481	56.48 247	95.30 234	35.79 476	73.13 317	90.64 290

test_fmvs1		74.07 339	73.69 323	75.22 408	78.91 425	47.34 471	89.06 339	74.69 474	63.68 394	79.41 167	91.59 199	24.36 473	87.77 434	85.22 106	76.26 297	90.55 292

PCF-MVS	73.15 9	79.29 244	77.63 254	84.29 208	86.06 311	65.96 191	87.03 372	91.10 229	69.86 324	69.79 311	90.64 219	57.54 229	96.59 140	64.37 347	82.29 220	90.32 293
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_0	68.08 15	71.81 368	68.32 384	82.27 280	84.68 342	62.31 314	88.68 345	90.31 281	75.84 188	57.93 432	80.65 391	37.85 419	94.19 288	69.94 277	29.05 504	90.31 294

tttt0517		79.50 237	78.53 238	82.41 275	87.22 267	61.43 339	89.75 316	94.76 41	69.29 331	67.91 337	88.06 283	72.92 33	95.63 210	62.91 358	73.90 314	90.16 295

CPTT-MVS		79.59 235	79.16 229	80.89 329	91.54 136	59.80 377	92.10 197	88.54 369	60.42 425	72.96 261	93.28 140	48.27 342	92.80 347	78.89 197	86.50 161	90.06 296

EI-MVSNet-UG-set		83.14 158	82.96 145	83.67 235	92.28 104	63.19 291	91.38 246	94.68 46	79.22 117	76.60 211	93.75 130	62.64 142	97.76 58	78.07 203	78.01 277	90.05 297

test_fmvs1_n		72.69 359	71.92 350	74.99 413	71.15 474	47.08 473	87.34 370	75.67 469	63.48 396	78.08 191	91.17 213	20.16 487	87.87 431	84.65 115	75.57 301	90.01 298

test_vis1_n		71.63 370	70.73 361	74.31 422	69.63 481	47.29 472	86.91 374	72.11 482	63.21 400	75.18 229	90.17 238	20.40 485	85.76 449	84.59 117	74.42 308	89.87 299

dmvs_re		76.93 293	75.36 295	81.61 301	87.78 254	60.71 356	80.00 446	87.99 386	79.42 111	69.02 318	89.47 253	46.77 363	94.32 281	63.38 353	74.45 307	89.81 300

XVG-OURS-SEG-HR		74.70 334	73.08 333	79.57 361	78.25 434	57.33 410	80.49 438	87.32 395	63.22 399	68.76 325	90.12 243	44.89 383	91.59 387	70.55 274	74.09 311	89.79 301

114514_t		79.17 246	77.67 251	83.68 234	95.32 32	65.53 204	92.85 154	91.60 198	63.49 395	67.92 336	90.63 221	46.65 366	95.72 205	67.01 315	83.54 207	89.79 301

UA-Net		80.02 229	79.65 214	81.11 318	89.33 185	57.72 402	86.33 382	89.00 350	77.44 159	81.01 132	89.15 260	59.33 195	95.90 182	61.01 369	84.28 192	89.73 303

XVG-OURS		74.25 338	72.46 345	79.63 359	78.45 432	57.59 406	80.33 440	87.39 392	63.86 391	68.76 325	89.62 252	40.50 401	91.72 383	69.00 288	74.25 309	89.58 304

UniMVSNet_ETH3D		72.74 356	70.53 363	79.36 364	78.62 430	56.64 418	85.01 392	89.20 330	63.77 392	64.84 371	84.44 336	34.05 442	91.86 380	63.94 349	70.89 335	89.57 305

thres200		79.66 234	78.33 239	83.66 236	92.54 100	65.82 197	93.06 139	96.31 3	74.90 205	73.30 259	88.66 267	59.67 188	95.61 214	47.84 431	78.67 273	89.56 306

SDMVSNet		80.26 223	78.88 234	84.40 202	89.25 189	67.63 131	85.35 388	93.02 123	76.77 174	70.84 295	87.12 298	47.95 349	96.09 170	85.04 109	74.55 304	89.48 307

sd_testset		77.08 291	75.37 294	82.20 284	89.25 189	62.11 318	82.06 425	89.09 340	76.77 174	70.84 295	87.12 298	41.43 397	95.01 243	67.23 312	74.55 304	89.48 307

OpenMVS	70.45 11	78.54 263	75.92 288	86.41 106	85.93 316	71.68 22	92.74 157	92.51 150	66.49 365	64.56 373	91.96 182	43.88 387	98.10 46	54.61 397	90.65 102	89.44 309

LuminaMVS		78.14 270	76.66 273	82.60 269	80.82 395	64.64 229	89.33 329	90.45 269	68.25 347	74.73 238	85.51 323	41.15 398	94.14 290	78.96 195	80.69 250	89.04 310

CHOSEN 280x420		77.35 286	76.95 270	78.55 374	87.07 275	62.68 305	69.71 479	82.95 448	68.80 340	71.48 290	87.27 297	66.03 85	84.00 461	76.47 213	82.81 215	88.95 311

thres100view900		78.37 265	77.01 268	82.46 271	91.89 125	63.21 290	91.19 262	96.33 1	72.28 263	70.45 300	87.89 285	60.31 177	95.32 231	45.16 444	77.58 283	88.83 312

tfpn200view9		78.79 257	77.43 258	82.88 260	92.21 107	64.49 232	92.05 201	96.28 4	73.48 234	71.75 285	88.26 276	60.07 182	95.32 231	45.16 444	77.58 283	88.83 312

nrg030		80.93 208	79.86 210	84.13 214	83.69 364	68.83 89	93.23 134	91.20 218	75.55 192	75.06 230	88.22 279	63.04 138	94.74 255	81.88 156	66.88 365	88.82 314

PatchT		69.11 389	65.37 402	80.32 336	82.07 383	63.68 274	67.96 485	87.62 391	50.86 467	69.37 312	65.18 480	57.09 232	88.53 424	41.59 460	66.60 367	88.74 315

HQP4-MVS										74.18 242			95.61 214			88.63 316

HQP-MVS		81.14 202	80.64 195	82.64 267	87.54 258	63.66 275	94.06 84	91.70 194	79.80 95	74.18 242	90.30 229	51.63 304	95.61 214	77.63 205	78.90 270	88.63 316

tt0805		73.07 349	70.73 361	80.07 344	78.37 433	57.05 414	87.78 362	92.18 165	61.23 421	67.04 352	86.49 307	31.35 454	94.58 265	65.06 339	67.12 363	88.57 318

VPNet		78.82 255	77.53 257	82.70 265	84.52 348	66.44 176	93.93 94	92.23 158	80.46 77	72.60 268	88.38 273	49.18 335	93.13 332	72.47 252	63.97 394	88.55 319

Effi-MVS+-dtu		76.14 307	75.28 297	78.72 373	83.22 370	55.17 429	89.87 313	87.78 390	75.42 195	67.98 335	81.43 376	45.08 382	92.52 359	75.08 225	71.63 328	88.48 320

CNLPA		74.31 337	72.30 346	80.32 336	91.49 137	61.66 331	90.85 274	80.72 455	56.67 449	63.85 382	90.64 219	46.75 364	90.84 398	53.79 402	75.99 299	88.47 321

HQP_MVS		80.34 222	79.75 213	82.12 288	86.94 283	62.42 309	93.13 137	91.31 210	78.81 128	72.53 270	89.14 261	50.66 316	95.55 220	76.74 208	78.53 275	88.39 322

plane_prior5								91.31 210					95.55 220	76.74 208	78.53 275	88.39 322

dtuonly		74.56 335	73.92 319	76.48 399	77.15 445	57.27 411	85.09 391	81.23 451	71.37 297	67.61 344	89.65 251	46.68 365	83.84 463	68.79 292	77.69 281	88.33 324

VPA-MVSNet		79.03 249	78.00 245	82.11 291	85.95 313	64.48 234	93.22 135	94.66 47	75.05 203	74.04 250	84.95 329	52.17 298	93.52 319	74.90 229	67.04 364	88.32 325

CLD-MVS		82.73 166	82.35 165	83.86 223	87.90 245	67.65 130	95.45 30	92.18 165	85.06 16	72.58 269	92.27 165	52.46 296	95.78 196	84.18 124	79.06 269	88.16 326
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		77.94 275	76.44 276	82.43 272	82.60 377	64.44 236	92.01 203	91.83 185	73.59 233	70.00 307	85.82 317	54.43 273	94.76 253	69.63 279	68.02 356	88.10 327

WBMVS		81.67 188	80.98 188	83.72 232	93.07 82	69.40 65	94.33 74	93.05 122	76.84 171	72.05 281	84.14 340	74.49 23	93.88 308	72.76 247	68.09 354	87.88 328

FIs		79.47 239	79.41 222	79.67 358	85.95 313	59.40 383	91.68 232	93.94 79	78.06 142	68.96 321	88.28 274	66.61 79	91.77 382	66.20 325	74.99 303	87.82 329

Fast-Effi-MVS+-dtu		75.04 328	73.37 328	80.07 344	80.86 393	59.52 382	91.20 261	85.38 424	71.90 273	65.20 367	84.84 330	41.46 396	92.97 336	66.50 321	72.96 319	87.73 330

UWE-MVS-28		76.83 297	77.60 255	74.51 418	84.58 347	50.34 455	88.22 353	94.60 52	74.46 208	66.66 358	88.98 266	62.53 144	85.50 453	57.55 388	80.80 249	87.69 331

UniMVSNet_NR-MVSNet		78.15 269	77.55 256	79.98 348	84.46 351	60.26 368	92.25 188	93.20 114	77.50 158	68.88 322	86.61 305	66.10 84	92.13 373	66.38 322	62.55 405	87.54 332

MVSTER		82.47 172	82.05 166	83.74 228	92.68 96	69.01 84	91.90 213	93.21 112	79.83 94	72.14 279	85.71 320	74.72 21	94.72 256	75.72 219	72.49 323	87.50 333

thres600view7		78.00 272	76.66 273	82.03 293	91.93 121	63.69 273	91.30 254	96.33 1	72.43 258	70.46 299	87.89 285	60.31 177	94.92 248	42.64 456	76.64 294	87.48 334

thres400		78.68 259	77.43 258	82.43 272	92.21 107	64.49 232	92.05 201	96.28 4	73.48 234	71.75 285	88.26 276	60.07 182	95.32 231	45.16 444	77.58 283	87.48 334

TranMVSNet+NR-MVSNet		75.86 316	74.52 307	79.89 352	82.44 379	60.64 359	91.37 247	91.37 207	76.63 180	67.65 342	86.21 311	52.37 297	91.55 389	61.84 365	60.81 423	87.48 334

FC-MVSNet-test		77.99 273	78.08 244	77.70 382	84.89 341	55.51 427	90.27 301	93.75 88	76.87 169	66.80 357	87.59 290	65.71 90	90.23 408	62.89 359	73.94 312	87.37 337

DU-MVS		76.86 294	75.84 289	79.91 351	82.96 373	60.26 368	91.26 255	91.54 199	76.46 184	68.88 322	86.35 308	56.16 248	92.13 373	66.38 322	62.55 405	87.35 338

NR-MVSNet		76.05 311	74.59 304	80.44 334	82.96 373	62.18 317	90.83 275	91.73 189	77.12 165	60.96 405	86.35 308	59.28 197	91.80 381	60.74 371	61.34 420	87.35 338

FMVSNet3		77.73 280	76.04 286	82.80 261	91.20 146	68.99 85	91.87 214	91.99 174	73.35 236	67.04 352	83.19 352	56.62 243	92.14 372	59.80 378	69.34 342	87.28 340

PS-MVSNAJss		77.26 287	76.31 281	80.13 343	80.64 399	59.16 388	90.63 288	91.06 236	72.80 249	68.58 328	84.57 334	53.55 284	93.96 304	72.97 242	71.96 327	87.27 341

mvsany_test1		68.77 392	68.56 380	69.39 452	73.57 466	45.88 480	80.93 436	60.88 502	59.65 431	71.56 288	90.26 231	43.22 390	75.05 490	74.26 234	62.70 404	87.25 342

FMVSNet2		76.07 308	74.01 318	82.26 282	88.85 201	67.66 129	91.33 252	91.61 197	70.84 307	65.98 361	82.25 362	48.03 343	92.00 377	58.46 383	68.73 350	87.10 343

ADS-MVSNet2		66.90 408	63.44 416	77.26 391	88.06 239	60.70 357	68.01 483	75.56 471	57.57 440	64.48 374	69.87 467	38.68 406	84.10 458	40.87 462	67.89 359	86.97 344

ADS-MVSNet		68.54 395	64.38 411	81.03 323	88.06 239	66.90 164	68.01 483	84.02 437	57.57 440	64.48 374	69.87 467	38.68 406	89.21 419	40.87 462	67.89 359	86.97 344

usedtu_dtu_shiyan1		77.89 278	76.39 279	82.40 276	81.92 385	67.01 157	91.94 210	93.00 126	77.01 166	68.44 331	84.15 338	54.78 266	93.25 328	65.76 330	70.53 336	86.94 346

FE-MVSNET3		77.89 278	76.39 279	82.40 276	81.92 385	67.01 157	91.94 210	93.00 126	77.01 166	68.44 331	84.15 338	54.78 266	93.25 328	65.76 330	70.53 336	86.94 346

WR-MVS		76.76 299	75.74 291	79.82 354	84.60 345	62.27 315	92.60 172	92.51 150	76.06 186	67.87 340	85.34 325	56.76 239	90.24 407	62.20 363	63.69 396	86.94 346

DSMNet-mixed		56.78 450	54.44 453	63.79 467	63.21 493	29.44 511	64.43 490	64.10 498	42.12 494	51.32 458	71.60 461	31.76 451	75.04 491	36.23 473	65.20 380	86.87 349

UniMVSNet (Re)		77.58 283	76.78 271	79.98 348	84.11 357	60.80 349	91.76 224	93.17 117	76.56 182	69.93 310	84.78 331	63.32 130	92.36 366	64.89 340	62.51 407	86.78 350

SSC-MVS3.2		74.92 331	73.32 331	79.74 357	86.53 296	60.31 367	89.03 340	92.70 137	78.61 133	68.98 320	83.34 350	41.93 395	92.23 371	52.77 408	65.97 371	86.69 351

GBi-Net		75.65 319	73.83 321	81.10 319	88.85 201	65.11 215	90.01 309	90.32 278	70.84 307	67.04 352	80.25 397	48.03 343	91.54 390	59.80 378	69.34 342	86.64 352

test1		75.65 319	73.83 321	81.10 319	88.85 201	65.11 215	90.01 309	90.32 278	70.84 307	67.04 352	80.25 397	48.03 343	91.54 390	59.80 378	69.34 342	86.64 352

FMVSNet1		72.71 357	69.91 368	81.10 319	83.60 366	65.11 215	90.01 309	90.32 278	63.92 390	63.56 384	80.25 397	36.35 432	91.54 390	54.46 398	66.75 366	86.64 352

v2v482		77.42 285	75.65 292	82.73 263	80.38 403	67.13 150	91.85 216	90.23 287	75.09 202	69.37 312	83.39 349	53.79 282	94.44 277	71.77 259	65.00 382	86.63 355

miper_enhance_ethall		78.86 254	77.97 246	81.54 303	88.00 243	65.17 213	91.41 240	89.15 334	75.19 200	68.79 324	83.98 343	67.17 73	92.82 345	72.73 248	65.30 375	86.62 356

blend_shiyan4		75.18 327	73.00 335	81.69 299	75.62 454	64.75 223	91.78 221	91.06 236	65.89 373	61.35 402	77.39 420	62.16 153	93.71 313	68.18 295	63.60 397	86.61 357

gbinet_0.2-2-1-0.02		71.92 367	68.92 378	80.91 327	75.87 453	63.30 285	91.95 209	91.40 206	65.62 377	61.57 401	77.27 424	44.71 384	92.88 344	61.00 370	50.87 462	86.54 358

cl22		77.94 275	76.78 271	81.42 305	87.57 257	64.93 221	90.67 284	88.86 355	72.45 257	67.63 343	82.68 357	64.07 111	92.91 342	71.79 258	65.30 375	86.44 359

wanda-best-256-512		72.42 362	69.43 372	81.37 306	75.39 455	64.24 248	91.58 235	91.09 230	66.36 366	60.64 407	76.86 430	47.20 357	93.47 321	64.80 341	50.98 458	86.40 360

FE-blended-shiyan7		72.42 362	69.43 372	81.37 306	75.39 455	64.24 248	91.58 235	91.09 230	66.36 366	60.64 407	76.86 430	47.20 357	93.47 321	64.80 341	50.98 458	86.40 360

usedtu_blend_shiyan5		71.06 374	67.54 387	81.62 300	75.39 455	64.75 223	85.67 386	86.47 407	56.48 450	60.64 407	76.85 432	47.20 357	93.71 313	68.18 295	50.98 458	86.40 360

blended_shiyan8		72.26 364	69.25 376	81.29 310	75.23 460	64.03 255	91.36 250	91.04 240	66.11 371	60.42 412	76.73 434	46.79 362	93.45 324	64.58 345	51.00 457	86.37 363

blended_shiyan6		72.26 364	69.26 375	81.27 311	75.24 459	64.00 258	91.37 247	91.06 236	66.12 370	60.34 413	76.75 433	46.82 360	93.45 324	64.61 343	50.98 458	86.37 363

PLC	68.80 14	75.23 325	73.68 324	79.86 353	92.93 86	58.68 393	90.64 286	88.30 377	60.90 422	64.43 377	90.53 222	42.38 393	94.57 267	56.52 390	76.54 295	86.33 365
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EI-MVSNet		78.97 251	78.22 242	81.25 312	85.33 328	62.73 304	89.53 325	93.21 112	72.39 260	72.14 279	90.13 241	60.99 166	94.72 256	67.73 305	72.49 323	86.29 366

IterMVS-LS		76.49 301	75.18 298	80.43 335	84.49 350	62.74 303	90.64 286	88.80 357	72.40 259	65.16 368	81.72 370	60.98 167	92.27 370	67.74 304	64.65 387	86.29 366
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		77.60 282	76.44 276	81.09 322	85.70 323	64.41 239	90.65 285	88.64 365	72.31 261	67.37 350	82.52 358	64.77 103	92.64 356	70.67 272	65.30 375	86.24 368

OPM-MVS		79.00 250	78.09 243	81.73 296	83.52 367	63.83 263	91.64 234	90.30 282	76.36 185	71.97 282	89.93 248	46.30 372	95.17 239	75.10 224	77.70 280	86.19 369
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DIV-MVS_self_test		76.07 308	74.67 301	80.28 338	85.14 335	61.75 329	90.12 305	88.73 360	71.16 300	65.42 366	81.60 373	61.15 164	92.94 341	66.54 319	62.16 411	86.14 370

eth_miper_zixun_eth		75.96 315	74.40 309	80.66 330	84.66 344	63.02 294	89.28 331	88.27 379	71.88 275	65.73 363	81.65 371	59.45 192	92.81 346	68.13 297	60.53 425	86.14 370

cl____		76.07 308	74.67 301	80.28 338	85.15 334	61.76 328	90.12 305	88.73 360	71.16 300	65.43 365	81.57 374	61.15 164	92.95 337	66.54 319	62.17 409	86.13 372

PatchMatch-RL		72.06 366	69.98 365	78.28 377	89.51 181	55.70 426	83.49 407	83.39 446	61.24 420	63.72 383	82.76 355	34.77 437	93.03 334	53.37 406	77.59 282	86.12 373

c3_l		76.83 297	75.47 293	80.93 326	85.02 339	64.18 251	90.39 296	88.11 383	71.66 284	66.65 359	81.64 372	63.58 126	92.56 357	69.31 284	62.86 402	86.04 374

RPSCF		64.24 423	61.98 426	71.01 446	76.10 450	45.00 482	75.83 465	75.94 468	46.94 478	58.96 423	84.59 333	31.40 453	82.00 479	47.76 433	60.33 429	86.04 374

Anonymous20231211		73.08 348	70.39 364	81.13 316	90.62 157	63.33 284	91.40 242	90.06 295	51.84 463	64.46 376	80.67 390	36.49 431	94.07 295	63.83 350	64.17 390	85.98 376

v1192		75.98 313	73.92 319	82.15 286	79.73 411	66.24 182	91.22 259	89.75 306	72.67 251	68.49 329	81.42 377	49.86 326	94.27 285	67.08 314	65.02 381	85.95 377

JIA-IIPM		66.06 413	62.45 422	76.88 397	81.42 391	54.45 434	57.49 501	88.67 363	49.36 472	63.86 381	46.86 500	56.06 251	90.25 404	49.53 419	68.83 348	85.95 377

VortexMVS		77.62 281	76.44 276	81.13 316	88.58 208	63.73 268	91.24 257	91.30 214	77.81 148	65.76 362	81.97 366	49.69 329	93.72 312	76.40 214	65.26 378	85.94 379

v1921920		75.63 321	73.49 326	82.06 292	79.38 416	66.35 178	91.07 268	89.48 317	71.98 270	67.99 334	81.22 382	49.16 337	93.90 307	66.56 318	64.56 388	85.92 380

reproduce_monomvs		79.49 238	79.11 232	80.64 331	92.91 87	61.47 338	91.17 263	93.28 110	83.09 35	64.04 379	82.38 360	66.19 82	94.57 267	81.19 169	57.71 436	85.88 381

v1144		76.73 300	74.88 300	82.27 280	80.23 407	66.60 173	91.68 232	90.21 290	73.69 230	69.06 317	81.89 367	52.73 294	94.40 279	69.21 285	65.23 379	85.80 382

v144192		76.05 311	74.03 317	82.12 288	79.50 415	66.55 175	91.39 244	89.71 312	72.30 262	68.17 333	81.33 379	51.75 302	94.03 301	67.94 302	64.19 389	85.77 383

v1240		75.21 326	72.98 336	81.88 294	79.20 418	66.00 189	90.75 279	89.11 339	71.63 289	67.41 348	81.22 382	47.36 355	93.87 309	65.46 336	64.72 386	85.77 383

v148		76.19 306	74.47 308	81.36 308	80.05 409	64.44 236	91.75 226	90.23 287	73.68 231	67.13 351	80.84 387	55.92 253	93.86 311	68.95 289	61.73 416	85.76 385

test0.0.03 1		72.76 355	72.71 341	72.88 432	80.25 406	47.99 467	91.22 259	89.45 319	71.51 294	62.51 397	87.66 288	53.83 280	85.06 455	50.16 416	67.84 361	85.58 386

test_djsdf		73.76 346	72.56 343	77.39 388	77.00 446	53.93 435	89.07 337	90.69 260	65.80 374	63.92 380	82.03 365	43.14 391	92.67 353	72.83 244	68.53 351	85.57 387

dmvs_testset		65.55 417	66.45 391	62.86 469	79.87 410	22.35 518	76.55 460	71.74 484	77.42 161	55.85 438	87.77 287	51.39 308	80.69 483	31.51 495	65.92 372	85.55 388

ACMM	69.62 13	74.34 336	72.73 340	79.17 368	84.25 356	57.87 400	90.36 298	89.93 300	63.17 401	65.64 364	86.04 314	37.79 420	94.10 292	65.89 327	71.52 330	85.55 388
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs5		73.35 347	71.52 354	78.86 372	78.64 429	60.61 360	91.08 265	86.90 402	67.69 353	63.32 386	83.64 345	44.33 386	90.53 401	62.04 364	66.02 370	85.46 390

jajsoiax		73.05 350	71.51 355	77.67 383	77.46 442	54.83 431	88.81 343	90.04 296	69.13 335	62.85 394	83.51 347	31.16 455	92.75 349	70.83 269	69.80 338	85.43 391

ACMP	71.68 10	75.58 322	74.23 312	79.62 360	84.97 340	59.64 379	90.80 276	89.07 342	70.39 316	62.95 392	87.30 295	38.28 412	93.87 309	72.89 243	71.45 331	85.36 392
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
mvs_tets		72.71 357	71.11 356	77.52 384	77.41 443	54.52 433	88.45 349	89.76 305	68.76 342	62.70 395	83.26 351	29.49 461	92.71 350	70.51 275	69.62 340	85.34 393

tpmvs		72.88 354	69.76 370	82.22 283	90.98 150	67.05 152	78.22 455	88.30 377	63.10 402	64.35 378	74.98 445	55.09 263	94.27 285	43.25 450	69.57 341	85.34 393

miper_lstm_enhance		73.05 350	71.73 353	77.03 393	83.80 362	58.32 397	81.76 426	88.88 352	69.80 325	61.01 404	78.23 414	57.19 231	87.51 440	65.34 337	59.53 430	85.27 395

LPG-MVS_test		75.82 317	74.58 305	79.56 362	84.31 354	59.37 384	90.44 293	89.73 309	69.49 328	64.86 369	88.42 271	38.65 408	94.30 283	72.56 250	72.76 320	85.01 396

LGP-MVS_train				79.56 362	84.31 354	59.37 384		89.73 309	69.49 328	64.86 369	88.42 271	38.65 408	94.30 283	72.56 250	72.76 320	85.01 396

PVSNet_BlendedMVS		83.38 152	83.43 126	83.22 253	93.76 56	67.53 134	94.06 84	93.61 94	79.13 120	81.00 134	85.14 327	63.19 132	97.29 91	87.08 90	73.91 313	84.83 398

V42		76.46 302	74.55 306	82.19 285	79.14 421	67.82 124	90.26 302	89.42 321	73.75 227	68.63 327	81.89 367	51.31 309	94.09 293	71.69 261	64.84 383	84.66 399

IterMVS		72.65 360	70.83 358	78.09 380	82.17 381	62.96 296	87.64 366	86.28 410	71.56 292	60.44 411	78.85 410	45.42 379	86.66 444	63.30 355	61.83 413	84.65 400
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
sc_t1		63.81 426	59.39 435	77.10 392	77.62 440	56.03 423	84.32 398	73.56 478	46.66 480	58.22 426	73.06 451	23.28 479	90.62 399	50.93 412	46.84 472	84.64 401

IterMVS-SCA-FT		71.55 371	69.97 366	76.32 401	81.48 389	60.67 358	87.64 366	85.99 417	66.17 369	59.50 418	78.88 409	45.53 377	83.65 464	62.58 361	61.93 412	84.63 402

pm-mvs1		72.89 353	71.09 357	78.26 378	79.10 422	57.62 404	90.80 276	89.30 325	67.66 354	62.91 393	81.78 369	49.11 338	92.95 337	60.29 375	58.89 433	84.22 403

pmmvs4		73.92 342	71.81 352	80.25 340	79.17 419	65.24 211	87.43 368	87.26 398	67.64 356	63.46 385	83.91 344	48.96 339	91.53 393	62.94 357	65.49 374	83.96 404

v8		75.35 323	73.26 332	81.61 301	80.67 398	66.82 165	89.54 322	89.27 326	71.65 285	63.30 387	80.30 396	54.99 264	94.06 296	67.33 311	62.33 408	83.94 405

UnsupCasMVSNet_eth		65.79 415	63.10 417	73.88 424	70.71 476	50.29 457	81.09 434	89.88 302	72.58 253	49.25 469	74.77 448	32.57 448	87.43 441	55.96 393	41.04 485	83.90 406

WB-MVSnew		77.14 289	76.18 285	80.01 347	86.18 307	63.24 288	91.26 255	94.11 75	71.72 283	73.52 257	87.29 296	45.14 381	93.00 335	56.98 389	79.42 262	83.80 407

v10		74.77 333	72.54 344	81.46 304	80.33 405	66.71 170	89.15 336	89.08 341	70.94 305	63.08 390	79.86 401	52.52 295	94.04 299	65.70 332	62.17 409	83.64 408

F-COLMAP		70.66 375	68.44 382	77.32 389	86.37 304	55.91 424	88.00 357	86.32 409	56.94 447	57.28 435	88.07 282	33.58 444	92.49 360	51.02 411	68.37 352	83.55 409

lessismore_v0				73.72 426	72.93 470	47.83 468		61.72 501		45.86 479	73.76 449	28.63 465	89.81 414	47.75 434	31.37 500	83.53 410

v7n		71.31 372	68.65 379	79.28 366	76.40 448	60.77 351	86.71 378	89.45 319	64.17 389	58.77 425	78.24 413	44.59 385	93.54 318	57.76 385	61.75 415	83.52 411

Anonymous20231206		67.53 405	65.78 396	72.79 433	74.95 461	47.59 469	88.23 352	87.32 395	61.75 419	58.07 429	77.29 423	37.79 420	87.29 442	42.91 452	63.71 395	83.48 412

CP-MVSNet		70.50 377	69.91 368	72.26 437	80.71 397	51.00 451	87.23 371	90.30 282	67.84 352	59.64 417	82.69 356	50.23 322	82.30 477	51.28 410	59.28 431	83.46 413

K. test v3		63.09 430	59.61 434	73.53 427	76.26 449	49.38 463	83.27 411	77.15 465	64.35 386	47.77 474	72.32 457	28.73 463	87.79 433	49.93 418	36.69 492	83.41 414

PS-CasMVS		69.86 384	69.13 377	72.07 441	80.35 404	50.57 454	87.02 373	89.75 306	67.27 358	59.19 421	82.28 361	46.58 367	82.24 478	50.69 413	59.02 432	83.39 415

PEN-MVS		69.46 387	68.56 380	72.17 439	79.27 417	49.71 459	86.90 375	89.24 328	67.24 361	59.08 422	82.51 359	47.23 356	83.54 466	48.42 426	57.12 437	83.25 416

anonymousdsp		71.14 373	69.37 374	76.45 400	72.95 469	54.71 432	84.19 399	88.88 352	61.92 414	62.15 398	79.77 403	38.14 415	91.44 395	68.90 290	67.45 362	83.21 417

XVG-ACMP-BASELINE		68.04 400	65.53 400	75.56 405	74.06 465	52.37 441	78.43 452	85.88 418	62.03 412	58.91 424	81.21 384	20.38 486	91.15 397	60.69 372	68.18 353	83.16 418

MSDG		69.54 386	65.73 397	80.96 324	85.11 337	63.71 270	84.19 399	83.28 447	56.95 446	54.50 442	84.03 341	31.50 452	96.03 176	42.87 454	69.13 347	83.14 419

test_fmvs2		65.78 416	64.84 403	68.60 456	66.54 488	41.71 490	83.27 411	69.81 489	54.38 456	67.91 337	84.54 335	15.35 493	81.22 482	75.65 220	66.16 369	82.88 420

SixPastTwentyTwo		64.92 419	61.78 427	74.34 421	78.74 427	49.76 458	83.42 410	79.51 460	62.86 403	50.27 463	77.35 421	30.92 457	90.49 402	45.89 441	47.06 471	82.78 421

testgi		64.48 422	62.87 420	69.31 453	71.24 472	40.62 493	85.49 387	79.92 458	65.36 380	54.18 444	83.49 348	23.74 476	84.55 456	41.60 459	60.79 424	82.77 422

DTE-MVSNet		68.46 396	67.33 389	71.87 443	77.94 438	49.00 464	86.16 384	88.58 367	66.36 366	58.19 427	82.21 363	46.36 368	83.87 462	44.97 447	55.17 444	82.73 423

WR-MVS_H		70.59 376	69.94 367	72.53 434	81.03 392	51.43 447	87.35 369	92.03 173	67.38 357	60.23 415	80.70 388	55.84 255	83.45 467	46.33 439	58.58 435	82.72 424

ppachtmachnet_test		67.72 402	63.70 414	79.77 356	78.92 423	66.04 188	88.68 345	82.90 449	60.11 429	55.45 439	75.96 441	39.19 405	90.55 400	39.53 466	52.55 453	82.71 425

CL-MVSNet_self_test		69.92 382	68.09 385	75.41 406	73.25 467	55.90 425	90.05 308	89.90 301	69.96 322	61.96 400	76.54 435	51.05 314	87.64 435	49.51 420	50.59 464	82.70 426

LS3D		69.17 388	66.40 392	77.50 385	91.92 122	56.12 422	85.12 390	80.37 457	46.96 477	56.50 437	87.51 292	37.25 423	93.71 313	32.52 491	79.40 263	82.68 427

our_test_3		68.29 398	64.69 406	79.11 371	78.92 423	64.85 222	88.40 350	85.06 427	60.32 427	52.68 451	76.12 440	40.81 400	89.80 416	44.25 449	55.65 442	82.67 428

FMVSNet5		68.04 400	65.66 399	75.18 410	84.43 352	57.89 399	83.54 405	86.26 411	61.83 416	53.64 448	73.30 450	37.15 426	85.08 454	48.99 422	61.77 414	82.56 429

KD-MVS_2432*1600		69.03 390	66.37 393	77.01 394	85.56 324	61.06 345	81.44 431	90.25 285	67.27 358	58.00 430	76.53 436	54.49 270	87.63 436	48.04 428	35.77 495	82.34 430

miper_refine_blended		69.03 390	66.37 393	77.01 394	85.56 324	61.06 345	81.44 431	90.25 285	67.27 358	58.00 430	76.53 436	54.49 270	87.63 436	48.04 428	35.77 495	82.34 430

pmmvs6		67.57 404	64.76 405	76.00 404	72.82 471	53.37 437	88.71 344	86.78 406	53.19 459	57.58 434	78.03 416	35.33 436	92.41 363	55.56 394	54.88 446	82.21 432

EU-MVSNet		64.01 424	63.01 418	67.02 463	74.40 464	38.86 499	83.27 411	86.19 413	45.11 484	54.27 443	81.15 385	36.91 429	80.01 485	48.79 425	57.02 438	82.19 433

usedtu_dtu_shiyan2		57.76 448	53.69 454	69.95 450	57.60 502	41.80 489	83.50 406	83.67 442	45.26 483	43.79 487	62.82 486	17.63 490	85.93 448	42.56 457	46.40 475	82.12 434

ACMH	63.93 17	68.62 393	64.81 404	80.03 346	85.22 333	63.25 287	87.72 363	84.66 431	60.83 423	51.57 457	79.43 407	27.29 468	94.96 245	41.76 458	64.84 383	81.88 435
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
D2MVS		73.80 343	72.02 349	79.15 370	79.15 420	62.97 295	88.58 347	90.07 293	72.94 244	59.22 420	78.30 412	42.31 394	92.70 352	65.59 334	72.00 326	81.79 436

DP-MVS		69.90 383	66.48 390	80.14 342	95.36 31	62.93 297	89.56 320	76.11 467	50.27 469	57.69 433	85.23 326	39.68 404	95.73 200	33.35 483	71.05 334	81.78 437

Patchmtry		67.53 405	63.93 413	78.34 375	82.12 382	64.38 240	68.72 480	84.00 438	48.23 476	59.24 419	72.41 455	57.82 226	89.27 418	46.10 440	56.68 441	81.36 438

Syy-MVS		69.65 385	69.52 371	70.03 449	87.87 249	43.21 487	88.07 355	89.01 346	72.91 246	63.11 388	88.10 280	45.28 380	85.54 450	22.07 503	69.23 345	81.32 439

myMVS_eth3d		72.58 361	72.74 339	72.10 440	87.87 249	49.45 461	88.07 355	89.01 346	72.91 246	63.11 388	88.10 280	63.63 121	85.54 450	32.73 489	69.23 345	81.32 439

Baseline_NR-MVSNet		73.99 341	72.83 337	77.48 386	80.78 396	59.29 387	91.79 218	84.55 433	68.85 339	68.99 319	80.70 388	56.16 248	92.04 376	62.67 360	60.98 422	81.11 441

CMPMVS	48.56 21	66.77 410	64.41 410	73.84 425	70.65 477	50.31 456	77.79 457	85.73 421	45.54 482	44.76 483	82.14 364	35.40 435	90.14 410	63.18 356	74.54 306	81.07 442
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
TransMVSNet (Re)		70.07 381	67.66 386	77.31 390	80.62 400	59.13 389	91.78 221	84.94 429	65.97 372	60.08 416	80.44 393	50.78 315	91.87 379	48.84 423	45.46 477	80.94 443

ACMH+	65.35 16	67.65 403	64.55 407	76.96 396	84.59 346	57.10 413	88.08 354	80.79 454	58.59 438	53.00 450	81.09 386	26.63 470	92.95 337	46.51 437	61.69 418	80.82 444

USDC		67.43 407	64.51 408	76.19 402	77.94 438	55.29 428	78.38 453	85.00 428	73.17 238	48.36 472	80.37 394	21.23 483	92.48 361	52.15 409	64.02 393	80.81 445

OurMVSNet-221017-0		64.68 420	62.17 424	72.21 438	76.08 451	47.35 470	80.67 437	81.02 453	56.19 451	51.60 456	79.66 405	27.05 469	88.56 423	53.60 404	53.63 449	80.71 446

MS-PatchMatch		77.90 277	76.50 275	82.12 288	85.99 312	69.95 48	91.75 226	92.70 137	73.97 221	62.58 396	84.44 336	41.11 399	95.78 196	63.76 351	92.17 73	80.62 447

tfpnnormal		70.10 380	67.36 388	78.32 376	83.45 368	60.97 347	88.85 341	92.77 135	64.85 383	60.83 406	78.53 411	43.52 389	93.48 320	31.73 492	61.70 417	80.52 448

FE-MVSNET2		66.80 409	64.06 412	75.03 411	69.84 479	57.11 412	86.57 379	88.57 368	67.94 351	50.97 461	72.16 459	33.79 443	87.55 439	53.94 401	52.74 450	80.45 449

MIMVSNet1		60.16 444	57.33 443	68.67 455	69.71 480	44.13 484	78.92 450	84.21 434	55.05 455	44.63 484	71.85 460	23.91 475	81.54 481	32.63 490	55.03 445	80.35 450

YYNet1		63.76 428	60.14 432	74.62 417	78.06 437	60.19 371	83.46 409	83.99 440	56.18 452	39.25 493	71.56 463	37.18 425	83.34 468	42.90 453	48.70 467	80.32 451

MDA-MVSNet_test_wron		63.78 427	60.16 431	74.64 416	78.15 436	60.41 364	83.49 407	84.03 436	56.17 453	39.17 494	71.59 462	37.22 424	83.24 470	42.87 454	48.73 466	80.26 452

KD-MVS_self_test		60.87 439	58.60 437	67.68 459	66.13 489	39.93 496	75.63 467	84.70 430	57.32 444	49.57 466	68.45 472	29.55 460	82.87 471	48.09 427	47.94 468	80.25 453

ITE_SJBPF				70.43 448	74.44 463	47.06 474		77.32 464	60.16 428	54.04 445	83.53 346	23.30 478	84.01 460	43.07 451	61.58 419	80.21 454

test20.03		63.83 425	62.65 421	67.38 462	70.58 478	39.94 495	86.57 379	84.17 435	63.29 398	51.86 455	77.30 422	37.09 427	82.47 474	38.87 470	54.13 448	79.73 455

UnsupCasMVSNet_bld		61.60 435	57.71 439	73.29 429	68.73 483	51.64 445	78.61 451	89.05 344	57.20 445	46.11 476	61.96 489	28.70 464	88.60 422	50.08 417	38.90 490	79.63 456

AllTest		61.66 434	58.06 438	72.46 435	79.57 412	51.42 448	80.17 443	68.61 491	51.25 465	45.88 477	81.23 380	19.86 488	86.58 445	38.98 468	57.01 439	79.39 457

TestCases				72.46 435	79.57 412	51.42 448		68.61 491	51.25 465	45.88 477	81.23 380	19.86 488	86.58 445	38.98 468	57.01 439	79.39 457

ambc				69.61 451	61.38 498	41.35 491	49.07 507	85.86 420		50.18 465	66.40 478	10.16 502	88.14 429	45.73 442	44.20 478	79.32 459

Anonymous20240521		62.09 432	59.08 436	71.10 445	67.19 486	48.72 465	83.91 401	85.23 426	50.38 468	47.84 473	71.22 465	20.74 484	85.51 452	46.47 438	58.75 434	79.06 460

testing3		70.38 379	70.83 358	69.03 454	85.82 318	43.93 486	90.72 282	90.56 267	68.06 348	60.24 414	86.82 304	64.83 101	84.12 457	26.33 498	64.10 391	79.04 461

tt0320-xc		61.51 437	56.89 446	75.37 407	78.50 431	58.61 394	82.61 422	71.27 487	44.31 487	53.17 449	68.03 475	23.38 477	88.46 425	47.77 432	43.00 482	79.03 462

MVP-Stereo		77.12 290	76.23 283	79.79 355	81.72 387	66.34 179	89.29 330	90.88 249	70.56 315	62.01 399	82.88 354	49.34 332	94.13 291	65.55 335	93.80 47	78.88 463
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pmmvs-eth3d		65.53 418	62.32 423	75.19 409	69.39 482	59.59 380	82.80 419	83.43 444	62.52 407	51.30 459	72.49 453	32.86 445	87.16 443	55.32 395	50.73 463	78.83 464

tt0320		61.85 433	57.45 442	75.03 411	77.49 441	57.60 405	82.74 420	73.65 477	43.65 490	53.65 447	68.18 473	25.47 472	88.66 420	45.56 443	46.68 473	78.81 465

OpenMVS_ROB	61.12 18	66.39 411	62.92 419	76.80 398	76.51 447	57.77 401	89.22 332	83.41 445	55.48 454	53.86 446	77.84 417	26.28 471	93.95 305	34.90 478	68.76 349	78.68 466

LTVRE_ROB	59.60 19	66.27 412	63.54 415	74.45 419	84.00 359	51.55 446	67.08 487	83.53 443	58.78 436	54.94 441	80.31 395	34.54 438	93.23 330	40.64 464	68.03 355	78.58 467
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
mmtdpeth		68.33 397	66.37 393	74.21 423	82.81 376	51.73 444	84.34 397	80.42 456	67.01 362	71.56 288	68.58 471	30.52 459	92.35 367	75.89 218	36.21 493	78.56 468

PM-MVS		59.40 445	56.59 447	67.84 457	63.63 492	41.86 488	76.76 459	63.22 499	59.01 435	51.07 460	72.27 458	11.72 500	83.25 469	61.34 367	50.28 465	78.39 469

test_fmvs3		56.82 449	54.86 452	62.69 471	53.59 504	35.47 502	75.87 464	65.64 496	43.91 488	55.10 440	71.43 464	6.91 508	74.40 493	68.64 293	52.63 451	78.20 470

mvs5depth		61.03 438	57.65 441	71.18 444	67.16 487	47.04 475	72.74 471	77.49 463	57.47 443	60.52 410	72.53 452	22.84 480	88.38 426	49.15 421	38.94 489	78.11 471

PatchmatchNet1														31.49 496	51.52 455	77.88 472
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
N_pmnet		50.55 457	49.11 459	54.88 478	77.17 444	4.02 540	84.36 396	2.00 537	48.59 473	45.86 479	68.82 470	32.22 449	82.80 473	31.58 493	51.38 456	77.81 473

new-patchmatchnet		59.30 446	56.48 448	67.79 458	65.86 490	44.19 483	82.47 423	81.77 450	59.94 430	43.65 488	66.20 479	27.67 467	81.68 480	39.34 467	41.40 484	77.50 474

FE-MVSNET		60.52 441	57.18 445	70.53 447	67.53 485	50.68 453	82.62 421	76.28 466	59.33 434	46.71 475	71.10 466	30.54 458	83.61 465	33.15 485	47.37 470	77.29 475

EG-PatchMatch MVS		68.55 394	65.41 401	77.96 381	78.69 428	62.93 297	89.86 314	89.17 332	60.55 424	50.27 463	77.73 419	22.60 481	94.06 296	47.18 435	72.65 322	76.88 476

MVS-HIRNet		60.25 443	55.55 450	74.35 420	84.37 353	56.57 420	71.64 474	74.11 475	34.44 497	45.54 481	42.24 510	31.11 456	89.81 414	40.36 465	76.10 298	76.67 477

MDA-MVSNet-bldmvs		61.54 436	57.70 440	73.05 430	79.53 414	57.00 417	83.08 415	81.23 451	57.57 440	34.91 498	72.45 454	32.79 446	86.26 447	35.81 475	41.95 483	75.89 478

COLMAP_ROB	57.96 20	62.98 431	59.65 433	72.98 431	81.44 390	53.00 439	83.75 404	75.53 472	48.34 475	48.81 471	81.40 378	24.14 474	90.30 403	32.95 486	60.52 426	75.65 479
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TinyColmap		60.32 442	56.42 449	72.00 442	78.78 426	53.18 438	78.36 454	75.64 470	52.30 460	41.59 492	75.82 443	14.76 496	88.35 427	35.84 474	54.71 447	74.46 480

ttmdpeth		53.34 455	49.96 458	63.45 468	62.07 497	40.04 494	72.06 472	65.64 496	42.54 493	51.88 454	77.79 418	13.94 499	76.48 489	32.93 487	30.82 503	73.84 481

MVStest1		51.35 456	46.89 460	64.74 465	65.06 491	51.10 450	67.33 486	72.58 480	30.20 501	35.30 496	74.82 446	27.70 466	69.89 498	24.44 500	24.57 506	73.22 482

mvsany_test3		48.86 459	46.35 462	56.41 474	46.00 510	31.67 507	62.26 492	47.25 512	43.71 489	45.54 481	68.15 474	10.84 501	64.44 509	57.95 384	35.44 497	73.13 483

pmmvs3		55.51 451	51.50 457	67.53 461	57.90 501	50.93 452	80.37 439	73.66 476	40.63 495	44.15 486	64.75 482	16.30 491	78.97 487	44.77 448	40.98 487	72.69 484

test_method		38.59 469	35.16 472	48.89 485	54.33 503	21.35 519	45.32 509	53.71 506	7.41 521	28.74 502	51.62 498	8.70 505	52.87 512	33.73 481	32.89 499	72.47 485

test_0402		64.54 421	61.09 428	74.92 414	84.10 358	60.75 353	87.95 358	79.71 459	52.03 461	52.41 452	77.20 425	32.21 450	91.64 385	23.14 501	61.03 421	72.36 486

LF4IMVS		54.01 454	52.12 455	59.69 472	62.41 495	39.91 497	68.59 481	68.28 493	42.96 492	44.55 485	75.18 444	14.09 498	68.39 500	41.36 461	51.68 454	70.78 487

TDRefinement		55.28 452	51.58 456	66.39 464	59.53 500	46.15 478	76.23 462	72.80 479	44.60 485	42.49 490	76.28 439	15.29 494	82.39 475	33.20 484	43.75 479	70.62 488

test_f		46.58 460	43.45 464	55.96 475	45.18 511	32.05 506	61.18 493	49.49 510	33.39 498	42.05 491	62.48 488	7.00 507	65.56 505	47.08 436	43.21 481	70.27 489

dtuonlycased		63.47 429	62.08 425	67.64 460	73.22 468	52.55 440	86.25 383	79.10 461	65.40 378	49.47 468	67.33 477	36.80 430	82.37 476	53.47 405	47.68 469	68.01 490

LCM-MVSNet		40.54 465	35.79 470	54.76 479	36.92 518	30.81 508	51.41 504	69.02 490	22.07 506	24.63 506	45.37 503	4.56 512	65.81 504	33.67 482	34.50 498	67.67 491

ANet_high		40.27 468	35.20 471	55.47 476	34.74 520	34.47 504	63.84 491	71.56 485	48.42 474	18.80 510	41.08 512	9.52 504	64.45 508	20.18 504	8.66 522	67.49 492

test_vis1_rt		59.09 447	57.31 444	64.43 466	68.44 484	46.02 479	83.05 417	48.63 511	51.96 462	49.57 466	63.86 484	16.30 491	80.20 484	71.21 267	62.79 403	67.07 493

ArgMatch-SfM		33.21 472	29.25 478	45.06 489	35.86 519	22.89 517	48.07 508	16.80 523	23.93 505	27.57 503	61.10 493	1.59 523	47.14 514	34.29 479	14.08 513	65.16 494

kuosan		60.86 440	60.24 430	62.71 470	81.57 388	46.43 477	75.70 466	85.88 418	57.98 439	48.95 470	69.53 469	58.42 214	76.53 488	28.25 497	35.87 494	65.15 495

PMMVS2		37.93 470	33.61 473	50.92 482	46.31 509	24.76 514	60.55 496	50.05 508	28.94 503	20.93 508	47.59 499	4.41 514	65.13 506	25.14 499	18.55 511	62.87 496

ArgMatch-Sym		33.10 473	29.80 475	43.01 490	37.34 517	24.00 516	51.27 505	13.51 524	26.37 504	28.91 501	61.40 492	1.65 522	43.37 517	34.16 480	13.61 514	61.66 497

new_pmnet		49.31 458	46.44 461	57.93 473	62.84 494	40.74 492	68.47 482	62.96 500	36.48 496	35.09 497	57.81 495	14.97 495	72.18 495	32.86 488	46.44 474	60.88 498

dongtai		55.18 453	55.46 451	54.34 480	76.03 452	36.88 500	76.07 463	84.61 432	51.28 464	43.41 489	64.61 483	56.56 245	67.81 501	18.09 508	28.50 505	58.32 499

FPMVS		45.64 462	43.10 466	53.23 481	51.42 507	36.46 501	64.97 489	71.91 483	29.13 502	27.53 504	61.55 490	9.83 503	65.01 507	16.00 514	55.58 443	58.22 500

WB-MVS		46.23 461	44.94 463	50.11 483	62.13 496	21.23 520	76.48 461	55.49 504	45.89 481	35.78 495	61.44 491	35.54 434	72.83 494	9.96 522	21.75 508	56.27 501

SSC-MVS		44.51 463	43.35 465	47.99 487	61.01 499	18.90 522	74.12 469	54.36 505	43.42 491	34.10 499	60.02 494	34.42 439	70.39 497	9.14 524	19.57 509	54.68 502

APD_test1		40.50 466	37.31 469	50.09 484	51.88 505	35.27 503	59.45 497	52.59 507	21.64 507	26.12 505	57.80 496	4.56 512	66.56 503	22.64 502	39.09 488	48.43 503

EGC-MVSNET		42.35 464	38.09 467	55.11 477	74.57 462	46.62 476	71.63 475	55.77 503	0.04 558	0.24 560	62.70 487	14.24 497	74.91 492	17.59 509	46.06 476	43.80 504

test_vis3_rt		40.46 467	37.79 468	48.47 486	44.49 512	33.35 505	66.56 488	32.84 519	32.39 499	29.65 500	39.13 516	3.91 516	68.65 499	50.17 415	40.99 486	43.40 505

DenseAffine		21.45 481	18.65 486	29.86 496	28.31 522	16.04 525	32.25 511	6.12 527	15.38 512	16.38 515	44.57 508	0.55 527	32.44 519	16.82 510	7.46 524	41.09 506

LoFTR		18.06 485	15.31 489	26.33 498	21.95 525	10.94 528	21.35 518	12.80 525	6.90 522	12.24 521	41.28 511	0.46 529	27.67 522	7.81 526	12.96 515	40.38 507

testf1		32.77 474	29.47 476	42.67 492	41.89 514	30.81 508	52.07 502	43.45 513	15.45 510	18.52 511	44.82 504	2.12 518	58.38 510	16.05 512	30.87 501	38.83 508

APD_test2		32.77 474	29.47 476	42.67 492	41.89 514	30.81 508	52.07 502	43.45 513	15.45 510	18.52 511	44.82 504	2.12 518	58.38 510	16.05 512	30.87 501	38.83 508

MVE	24.84 23	24.35 478	19.77 484	38.09 494	34.56 521	26.92 513	26.57 512	38.87 517	11.73 517	11.37 523	27.44 523	1.37 524	50.42 513	11.41 521	14.60 512	36.93 510
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				34.71 495	51.45 506	24.73 515		28.48 521	31.46 500	17.49 514	52.75 497	5.80 510	42.60 518	18.18 507	19.42 510	36.81 511

RoMa-SfM		18.71 484	16.37 487	25.74 499	19.88 526	12.86 526	26.27 513	3.78 532	13.07 515	15.56 517	45.71 502	0.48 528	28.39 521	16.22 511	6.37 525	35.97 512

PMVS	26.43 22	31.84 476	28.16 479	42.89 491	25.87 524	27.58 512	50.92 506	49.78 509	21.37 508	14.17 519	40.81 513	2.01 520	66.62 502	9.61 523	38.88 491	34.49 513
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DKM		16.33 487	14.55 490	21.65 502	19.49 527	10.79 529	24.23 515	2.86 534	10.86 518	13.52 520	40.31 514	0.32 534	21.73 526	14.27 515	5.12 527	32.43 514

PDCNetPlus		17.19 486	15.58 488	22.00 501	25.94 523	10.36 530	23.05 517	5.04 529	12.02 516	10.87 525	39.50 515	0.88 525	23.24 524	18.38 506	4.57 530	32.39 515

GLUNet-SfM		8.91 494	6.39 503	16.47 507	9.50 537	4.77 535	5.87 532	5.53 528	2.45 529	6.66 531	22.23 527	0.25 540	15.78 528	2.84 534	2.14 544	28.86 516

VLMVS		13.23 490	13.55 491	12.28 511	12.68 533	2.77 544	12.60 523	3.80 531	0.44 540	17.98 513	44.70 507	4.14 515	6.39 533	12.99 517	12.66 516	27.68 517

MatchFormer		14.02 488	12.22 492	19.42 503	17.64 528	8.79 531	19.96 519	10.04 526	4.23 523	10.54 526	32.75 521	0.31 536	22.88 525	4.03 533	10.48 518	26.57 518

DKM-HiRes		12.72 491	11.70 494	15.79 508	14.70 529	7.68 533	18.04 521	1.85 541	8.12 520	11.31 524	35.19 519	0.24 542	14.23 531	12.15 519	3.71 534	25.48 519

RoMa-HiRes		13.29 489	12.09 493	16.86 506	12.76 532	7.74 532	17.91 522	2.10 536	8.64 519	11.87 522	39.11 517	0.36 532	17.55 527	12.17 518	3.91 533	25.30 520

Gipuma		34.91 471	31.44 474	45.30 488	70.99 475	39.64 498	19.85 520	72.56 481	20.10 509	16.16 516	21.47 529	5.08 511	71.16 496	13.07 516	43.70 480	25.08 521
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ELoFTR		8.49 495	6.65 502	14.00 509	5.91 539	3.43 542	7.42 529	4.01 530	2.94 527	6.41 532	25.06 524	0.11 547	15.41 530	5.10 532	2.92 537	23.17 522

VLMVS_CLIP		19.60 483	19.74 485	19.17 504	13.13 531	5.80 534	23.18 516	23.62 522	3.86 524	24.51 507	44.74 506	2.91 517	29.01 520	19.90 505	21.84 507	22.70 523

PMatch-SfM		8.29 496	7.44 501	10.83 512	6.92 538	3.67 541	9.75 525	1.15 543	3.49 526	6.97 530	28.70 522	0.04 559	8.89 532	7.67 527	2.24 543	19.92 524

tmp_tt		22.26 480	23.75 482	17.80 505	5.23 545	12.06 527	35.26 510	39.48 516	2.82 528	18.94 509	44.20 509	22.23 482	24.64 523	36.30 472	9.31 521	16.69 525

E-PMN		24.61 477	24.00 481	26.45 497	43.74 513	18.44 523	60.86 494	39.66 515	15.11 513	9.53 527	22.10 528	6.52 509	46.94 515	8.31 525	10.14 519	13.98 526

MVS_clip		10.33 493	11.48 495	6.89 515	13.99 530	4.67 537	11.14 524	0.96 549	1.27 532	14.61 518	35.92 518	1.90 521	2.27 540	11.90 520	11.60 517	13.74 527

EMVS		23.76 479	23.20 483	25.46 500	41.52 516	16.90 524	60.56 495	38.79 518	14.62 514	8.99 529	20.24 531	7.35 506	45.82 516	7.25 528	9.46 520	13.64 528

PMatch-Up-SfM		6.11 501	5.72 505	7.28 513	5.02 546	2.48 545	7.03 531	0.71 551	2.41 530	5.37 533	23.67 525	0.03 563	5.84 534	5.77 531	1.48 554	13.50 529

MASt3R-SfM		8.20 497	8.57 500	7.11 514	5.75 542	3.12 543	9.54 526	3.21 533	2.39 531	9.18 528	34.80 520	0.37 531	5.21 535	6.46 529	5.41 526	12.99 530

MVS_baseline		3.15 506	3.66 509	1.62 526	2.62 561	0.05 567	0.90 554	0.14 566	0.02 560	4.44 534	18.48 532	0.16 546	0.00 563	1.30 535	4.85 528	4.80 531

ALIKED-LG		4.67 502	4.76 506	4.39 516	11.74 534	4.58 538	8.52 527	2.37 535	1.12 533	3.02 536	10.43 533	0.40 530	4.25 536	0.52 543	4.70 529	4.35 532

SP-LightGlue		2.23 509	2.31 512	1.99 520	5.90 540	1.01 554	4.31 533	1.04 546	0.50 538	1.20 543	4.36 540	0.28 538	1.06 543	0.64 539	2.57 539	3.91 533

SP-MNN		2.16 511	2.22 514	1.97 521	5.52 543	0.92 559	4.28 535	1.01 547	0.41 542	1.13 544	4.35 541	0.23 543	1.09 542	0.61 541	2.45 541	3.91 533

ALIKED-MNN		4.24 504	4.26 507	4.20 517	10.96 535	4.68 536	7.92 528	2.00 537	0.81 534	2.44 541	9.09 535	0.30 537	4.03 537	0.46 544	4.36 532	3.88 535

SP-SuperGlue		2.21 510	2.29 513	1.97 521	5.76 541	1.01 554	4.31 533	1.06 545	0.50 538	1.22 542	4.35 541	0.28 538	1.04 545	0.64 539	2.52 540	3.86 536

SP-DiffGlue		2.24 508	2.34 511	1.94 523	1.88 562	1.08 552	3.10 537	1.13 544	0.55 536	2.52 538	7.60 538	0.33 533	0.99 546	1.25 536	2.70 538	3.76 537

SP-NN		2.08 512	2.16 515	1.87 524	5.30 544	0.91 560	4.18 536	0.96 549	0.43 541	1.09 545	4.20 543	0.25 540	1.06 543	0.60 542	2.38 542	3.63 538

ALIKED-NN		4.04 505	4.13 508	3.78 518	10.26 536	4.26 539	7.33 530	1.98 539	0.76 535	2.52 538	9.08 536	0.32 534	3.67 538	0.44 545	4.45 531	3.40 539

XFeat-MNN		2.31 507	2.37 510	2.13 519	1.47 563	0.97 558	3.08 538	1.31 542	0.53 537	2.60 537	7.72 537	0.22 544	2.31 539	1.02 537	3.40 535	3.10 540

XFeat-NN		1.98 513	2.09 516	1.67 525	1.35 564	0.77 563	2.62 539	0.97 548	0.41 542	2.46 540	6.79 539	0.19 545	1.75 541	0.84 538	3.18 536	2.48 541

wuyk23d		11.30 492	10.95 496	12.33 510	48.05 508	19.89 521	25.89 514	1.92 540	3.58 525	3.12 535	1.37 558	0.64 526	15.77 529	6.23 530	7.77 523	1.35 542

SIFT-NN		1.43 514	1.51 517	1.19 527	4.60 547	1.57 546	2.30 540	0.51 552	0.34 544	0.74 546	2.84 544	0.08 548	0.84 547	0.13 547	2.07 545	1.15 543

SIFT-MNN		1.35 515	1.42 518	1.14 528	4.26 548	1.44 547	2.10 541	0.51 552	0.34 544	0.64 547	2.76 545	0.07 549	0.83 548	0.13 547	1.98 547	1.15 543

SIFT-NN-CMatch		1.18 518	1.24 521	1.01 531	3.44 554	1.19 551	1.78 545	0.42 555	0.33 546	0.64 547	2.63 546	0.07 549	0.77 551	0.12 549	1.73 550	1.08 545

SIFT-NN-PointCN		1.06 522	1.12 525	0.88 534	2.98 557	0.84 562	1.67 547	0.37 559	0.30 554	0.54 550	2.38 552	0.07 549	0.72 555	0.11 552	1.64 551	1.07 546

SIFT-NN-UMatch		1.16 519	1.23 522	0.96 532	3.23 556	1.06 553	1.93 543	0.42 555	0.33 546	0.53 551	2.63 546	0.07 549	0.77 551	0.11 552	1.79 549	1.05 547

SIFT-NN-NCMNet		1.29 516	1.36 519	1.08 529	3.95 550	1.39 548	2.05 542	0.49 554	0.33 546	0.63 549	2.62 548	0.07 549	0.81 549	0.12 549	2.02 546	1.05 547

SIFT-NCM-Cal		1.23 517	1.30 520	1.04 530	4.06 549	1.29 549	1.92 544	0.42 555	0.33 546	0.45 554	2.46 551	0.06 554	0.81 549	0.10 556	1.89 548	1.02 549

SIFT-ConvMatch		1.15 520	1.22 523	0.96 532	3.82 551	1.20 550	1.64 548	0.38 558	0.33 546	0.52 552	2.53 549	0.06 554	0.76 553	0.11 552	1.59 552	0.91 550

SIFT-PCN-Cal		0.88 525	0.93 529	0.70 538	2.93 558	0.60 565	1.22 552	0.27 564	0.28 555	0.36 557	2.00 555	0.04 559	0.61 559	0.09 558	1.23 558	0.89 551

SIFT-UMatch		1.11 521	1.18 524	0.87 535	3.66 552	1.00 557	1.70 546	0.35 560	0.32 551	0.46 553	2.50 550	0.06 554	0.75 554	0.11 552	1.51 553	0.87 552

SIFT-CM-Cal		1.03 523	1.10 526	0.85 536	3.54 553	1.01 554	1.42 550	0.32 561	0.32 551	0.44 555	2.30 554	0.06 554	0.71 556	0.09 558	1.37 555	0.82 553

SIFT-PointCN		0.88 525	0.94 528	0.69 539	2.88 559	0.61 564	1.32 551	0.30 562	0.28 555	0.36 557	1.93 556	0.04 559	0.62 558	0.09 558	1.26 557	0.82 553

SIFT-UM-Cal		1.01 524	1.09 527	0.77 537	3.43 555	0.85 561	1.49 549	0.29 563	0.31 553	0.42 556	2.34 553	0.06 554	0.69 557	0.10 556	1.37 555	0.77 555

SIFT-NCMNet		0.73 527	0.80 530	0.54 540	2.66 560	0.54 566	1.00 553	0.16 565	0.28 555	0.32 559	1.65 557	0.04 559	0.51 560	0.07 561	0.98 559	0.58 556

test123		6.92 500	9.21 499	0.08 541	0.03 566	0.05 567	81.65 429	0.01 568	0.02 560	0.14 562	0.85 560	0.03 563	0.02 561	0.12 549	0.00 561	0.16 557

testmvs		7.23 499	9.62 498	0.06 542	0.04 565	0.02 569	84.98 393	0.02 567	0.03 559	0.18 561	1.21 559	0.01 565	0.02 561	0.14 546	0.01 560	0.13 558

mmdepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 561	0.00 559

monomultidepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 561	0.00 559

test_blank		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 561	0.00 559

uanet_test		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 561	0.00 559

DCPMVS		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 561	0.00 559

cdsmvs_eth3d_5k		19.86 482	26.47 480	0.00 543	0.00 567	0.00 570	0.00 555	93.45 103	0.00 562	0.00 563	95.27 79	49.56 330	0.00 563	0.00 562	0.00 561	0.00 559

pcd_1.5k_mvsjas		4.46 503	5.95 504	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	53.55 284	0.00 563	0.00 562	0.00 561	0.00 559

sosnet-low-res		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 561	0.00 559

sosnet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 561	0.00 559

uncertanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 561	0.00 559

Regformer		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 561	0.00 559

ab-mvs-re		7.91 498	10.55 497	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	94.95 90	0.00 566	0.00 563	0.00 562	0.00 561	0.00 559

uanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 561	0.00 559

Meshroom													0.00 563
: In preparation.
AliceVision / Meshro													0.00 563
: In preparation.
AliceVision_Meshroom													0.00 563
: In preparation.
PatchmatchNet2					0.00 567	56.61 419	85.20 389	78.52 462	49.54 471
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													82.83 472
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					95.84 30	67.84 122		94.64 48		89.45 44		71.94 44	98.96 19	91.55 46	94.82 26

WAC-MVS						49.45 461								31.56 494

FOURS1					93.95 52	61.77 327	93.96 92	91.92 177	62.14 411	86.57 66

test_one_0601					96.32 20	69.74 57		94.18 72	71.42 296	90.67 30	96.85 29	74.45 24

eth-test2					0.00 567

eth-test					0.00 567

ZD-MVS					96.63 10	65.50 205		93.50 101	70.74 311	85.26 84	95.19 85	64.92 100	97.29 91	87.51 79	93.01 61

test_241102_ONE					96.45 13	69.38 67		94.44 58	71.65 285	92.11 11	97.05 14	76.79 10	99.11 7

9.14			87.63 41		93.86 54		94.41 70	94.18 72	72.76 250	86.21 69	96.51 38	66.64 78	97.88 54	90.08 60	94.04 43

save fliter					93.84 55	67.89 121	95.05 42	92.66 142	78.19 139

test0726					96.40 16	69.99 45	96.76 8	94.33 69	71.92 271	91.89 16	97.11 13	73.77 27

test_part2					96.29 21	68.16 114				90.78 28

sam_mvs												54.91 265

MTGPA								92.23 158

test_post1							78.95 449				20.70 530	53.05 289	91.50 394	60.43 373

test_post											23.01 526	56.49 246	92.67 353

patchmatchnet-post											67.62 476	57.62 228	90.25 404

MTMP							93.77 108	32.52 520

gm-plane-assit					88.42 225	67.04 153			78.62 132		91.83 188		97.37 85	76.57 212

TEST9					94.18 47	67.28 141	94.16 79	93.51 99	71.75 282	85.52 79	95.33 73	68.01 65	97.27 96

test_8					94.19 46	67.19 146	94.15 81	93.42 106	71.87 276	85.38 82	95.35 72	68.19 63	96.95 123

agg_prior					94.16 49	66.97 162		93.31 109		84.49 90			96.75 135

test_prior4						67.18 148	93.92 96

test_prior2							95.10 40		75.40 196	85.25 85	95.61 64	67.94 66		87.47 81	94.77 28

旧先验2							92.00 206		59.37 433	87.54 58			93.47 321	75.39 222

新几何2							91.41 240

原ACMM2							92.01 203

testdata2													96.09 170	61.26 368

segment_acmp												65.94 86

testdata1							89.21 333		77.55 157

plane_prior7					86.94 283	61.51 335

plane_prior6					87.23 266	62.32 313						50.66 316

plane_prior4											89.14 261

plane_prior3						61.95 322			79.09 121	72.53 270

plane_prior2							93.13 137		78.81 128

plane_prior1					87.15 271

plane_prior						62.42 309	93.85 100		79.38 113						78.80 272

n2								0.00 569

nn								0.00 569

door-mid								66.01 495

test11								93.01 124

door								66.57 494

HQP5-MVS						63.66 275

HQP-NCC					87.54 258		94.06 84		79.80 95	74.18 242

ACMP_Plane					87.54 258		94.06 84		79.80 95	74.18 242

BP-MVS														77.63 205

HQP3-MVS								91.70 194							78.90 270

HQP2-MVS												51.63 304

NP-MVS					87.41 261	63.04 293					90.30 229

MDTV_nov1_ep13			72.61 342		89.06 196	68.48 100	80.33 440	90.11 292	71.84 278	71.81 284	75.92 442	53.01 290	93.92 306	48.04 428	73.38 315

ACMMP++_ref															71.63 328

ACMMP++															69.72 339

Test By Simon												54.21 278

High-resolution multi-view benchmark