High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

MSP-MVS		90.38 5	91.87 1	85.88 122	92.83 90	64.03 255	93.06 140	94.33 69	82.19 47	93.65 4	96.15 53	85.89 1	97.19 102	91.02 55	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
MM		90.87 2	91.52 2	88.92 17	92.12 112	71.10 32	97.02 3	96.04 6	88.70 2	91.57 21	96.19 51	70.12 52	98.91 22	96.83 2	95.06 17	96.76 18

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 76	96.26 49	72.84 34	99.38 2	92.64 35	95.93 9	97.08 12

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 184	93.00 86	58.16 399	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

DVP-MVS++		90.53 4	91.09 5	88.87 18	97.31 4	69.91 49	93.96 93	94.37 67	72.48 255	92.07 13	96.85 30	83.82 2	99.15 3	91.53 50	97.42 4	97.55 5

patch_mono-2		89.71 11	90.99 6	85.85 125	96.04 27	63.70 272	95.04 45	95.19 25	86.74 8	91.53 22	95.15 87	73.86 26	97.58 72	93.38 28	92.00 79	96.28 41

MGCNet		90.32 6	90.90 7	88.55 26	94.05 52	70.23 43	97.00 5	93.73 90	87.30 4	92.15 10	96.15 53	66.38 81	98.94 21	96.71 3	94.67 35	96.47 31

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 46	96.80 33	70.86 48	99.06 16	92.64 35	95.71 11	96.12 45

DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 177	76.68 2	97.29 1	95.35 19	82.87 39	91.58 20	97.22 11	79.93 6	99.10 10	83.12 140	97.64 2	97.94 1

SED-MVS		89.94 9	90.36 10	88.70 20	96.45 13	69.38 67	96.89 6	94.44 58	71.65 286	92.11 11	97.21 12	76.79 10	99.11 7	92.34 38	95.36 14	97.62 3

fmvsm_l_mol_unc0.5_1		89.65 12	90.28 11	87.77 38	87.88 249	70.89 33	96.35 16	88.48 371	86.59 9	93.16 5	97.86 2	75.47 16	97.28 96	94.09 22	92.60 67	95.16 97

DELS-MVS		90.05 8	90.09 12	89.94 5	93.14 79	73.88 10	97.01 4	94.40 65	88.32 3	85.71 77	94.91 95	74.11 25	98.91 22	87.26 85	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
CANet		89.61 13	89.99 13	88.46 27	94.39 46	69.71 58	96.53 13	93.78 83	86.89 7	89.68 41	95.78 60	65.94 87	99.10 10	92.99 32	93.91 46	96.58 24

HPM-MVS++		89.37 15	89.95 14	87.64 40	95.10 34	68.23 111	95.24 36	94.49 56	82.43 44	88.90 48	96.35 44	71.89 45	98.63 32	88.76 70	96.40 6	96.06 46

DVP-MVS		89.41 14	89.73 15	88.45 28	96.40 16	69.99 45	96.64 10	94.52 54	71.92 272	90.55 31	96.93 22	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
MED-MVS		89.02 18	89.57 16	87.38 51	94.76 37	67.28 141	94.47 66	94.87 35	70.68 313	91.27 25	96.93 22	76.77 12	98.98 17	91.55 46	94.82 26	95.88 57

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 66	96.20 50	66.56 80	98.76 29	89.03 69	94.56 36	95.92 54

fmvsm_l_conf0.5_n_9		88.24 23	89.36 18	84.85 172	88.15 238	61.94 324	95.65 26	89.70 314	85.54 13	92.07 13	97.33 8	67.51 71	97.27 97	96.23 5	92.07 78	95.35 81

fmvsm_s_conf0.5_n_11		87.99 28	89.25 19	84.23 212	89.07 196	61.60 334	94.87 53	89.06 344	85.65 12	91.09 27	97.41 7	68.26 62	97.43 83	95.07 13	92.74 65	93.66 199

fmvsm_s_conf0.5_n_9		88.14 24	89.21 20	84.92 167	89.29 188	61.41 341	92.97 145	88.36 374	86.96 6	91.49 23	97.49 5	69.48 57	97.46 79	97.00 1	89.88 116	95.89 56

DPE-MVS		88.77 19	89.21 20	87.45 49	96.26 23	67.56 132	94.17 79	94.15 74	68.77 342	90.74 29	97.27 9	76.09 14	98.49 35	90.58 59	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
fmvsm_s_conf0.5_n_8		87.96 29	88.93 22	85.07 161	88.43 225	61.78 327	94.73 61	91.74 189	85.87 11	91.66 19	97.50 4	64.03 113	98.33 40	96.28 4	90.08 112	95.10 101

BridgeMVS		89.08 16	88.84 23	89.81 7	93.66 61	75.15 5	90.61 291	93.43 106	84.06 26	86.20 71	90.17 239	72.42 39	96.98 119	93.09 31	95.92 10	97.29 8

fmvsm_s_conf0.5_n_6		87.50 39	88.72 24	83.84 224	86.89 290	60.04 375	95.05 43	92.17 168	84.80 20	92.27 8	96.37 42	64.62 105	96.54 147	94.43 19	91.86 81	94.94 110

fmvsm_s_conf0.5_n_10		87.93 32	88.67 25	85.71 132	88.69 207	63.71 270	94.56 64	90.22 290	85.04 17	92.27 8	97.05 15	63.67 121	98.15 44	95.09 12	91.39 91	95.27 90

TSAR-MVS + MP.		88.11 27	88.64 26	86.54 98	91.73 130	68.04 116	90.36 299	93.55 98	82.89 37	91.29 24	92.89 150	72.27 41	96.03 177	87.99 75	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
aaEdge-Enhanced		88.25 21	88.55 27	87.33 55	96.33 19	67.28 141	93.93 95	94.81 39	70.09 321	88.91 47	96.95 20	70.12 52	98.73 30	91.55 46	94.28 39	95.99 51

test_fmvsm_n_1920		87.69 36	88.50 28	85.27 154	87.05 277	63.55 280	93.69 112	91.08 235	84.18 25	90.17 37	97.04 17	67.58 70	97.99 48	95.72 8	90.03 113	94.26 163

EPNet		87.84 34	88.38 29	86.23 112	93.30 73	66.05 186	95.26 35	94.84 37	87.09 5	88.06 52	94.53 104	66.79 76	97.34 89	83.89 129	91.68 85	95.29 87
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TSAR-MVS + GP.		87.96 29	88.37 30	86.70 80	93.51 69	65.32 209	95.15 39	93.84 82	78.17 140	85.93 75	94.80 98	75.80 15	98.21 42	89.38 63	88.78 129	96.59 22

PRO-TEST		88.25 21	88.30 31	88.11 32	93.04 85	71.42 24	93.31 132	93.19 116	85.25 15	87.41 60	95.02 89	62.21 152	95.99 180	93.13 30	92.14 75	96.91 17

fmvsm_l_conf0.5_n_3		87.54 37	88.29 32	85.30 151	86.92 288	62.63 307	95.02 47	90.28 285	84.95 18	90.27 34	96.86 28	65.36 94	97.52 77	94.93 15	90.03 113	95.76 62

SMA-MVS		88.14 24	88.29 32	87.67 39	93.21 76	68.72 95	93.85 101	94.03 78	74.18 216	91.74 17	96.67 36	65.61 92	98.42 39	89.24 66	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
RA-MVS			88.26 34		96.29 21	63.70 272	95.34 33	93.95 79	72.10 269	89.34 45	97.44 6	65.95 86	97.98 49	91.53 50	92.39 71

fmvsm_l_conf0.5_n		87.49 40	88.19 35	85.39 143	86.95 283	64.37 241	94.30 76	88.45 372	80.51 75	92.70 6	96.86 28	69.98 54	97.15 107	95.83 7	88.08 137	94.65 135

fmvsm_l_conf0.5_n_a		87.44 42	88.15 36	85.30 151	87.10 275	64.19 250	94.41 71	88.14 383	80.24 87	92.54 7	96.97 19	69.52 56	97.17 103	95.89 6	88.51 132	94.56 139

DeepC-MVS_fast	79.48 2	87.95 31	88.00 37	87.79 36	95.86 30	68.32 105	95.74 22	94.11 75	83.82 28	83.49 103	96.19 51	64.53 108	98.44 37	83.42 138	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
fmvsm_s_conf0.5_n_3		86.88 49	87.99 38	83.58 238	87.26 266	60.74 355	93.21 137	87.94 390	84.22 24	91.70 18	97.27 9	65.91 89	95.02 242	93.95 25	90.42 107	94.99 107

testing915		88.35 20	87.97 39	89.48 14	92.39 102	74.80 7	93.79 107	95.85 9	81.52 54	84.20 93	92.89 150	75.00 18	96.60 140	90.20 60	85.92 167	97.03 13

APDe-MVS		87.54 37	87.84 40	86.65 83	96.07 26	66.30 180	94.84 55	93.78 83	69.35 331	88.39 51	96.34 45	67.74 69	97.66 67	90.62 58	93.44 55	96.01 49
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
lupinMVS		87.74 35	87.77 41	87.63 44	89.24 193	71.18 29	96.57 12	92.90 132	82.70 41	87.13 61	95.27 80	64.99 98	95.80 194	89.34 64	91.80 83	95.93 53

fmvsm_s_conf0.5_n_4		86.79 56	87.63 42	84.27 210	86.15 310	61.48 338	94.69 62	91.16 221	83.79 30	90.51 33	96.28 47	64.24 110	98.22 41	95.00 14	86.88 150	93.11 218

9.14			87.63 42		93.86 55		94.41 71	94.18 72	72.76 250	86.21 70	96.51 39	66.64 78	97.88 55	90.08 61	94.04 43

PS-MVSNAJ		88.14 24	87.61 44	89.71 8	92.06 115	76.72 1	95.75 21	93.26 112	83.86 27	89.55 42	96.06 55	53.55 285	97.89 54	91.10 53	93.31 57	94.54 142

dcpmvs_2		87.37 43	87.55 45	86.85 68	95.04 36	68.20 113	90.36 299	90.66 264	79.37 114	81.20 128	93.67 134	74.73 20	96.55 146	90.88 56	92.00 79	95.82 60

SD-MVS		87.49 40	87.49 46	87.50 48	93.60 63	68.82 90	93.90 98	92.63 147	76.86 170	87.90 54	95.76 61	66.17 83	97.63 69	89.06 68	91.48 89	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
train_agg		87.21 45	87.42 47	86.60 86	94.18 48	67.28 141	94.16 80	93.51 100	71.87 277	85.52 80	95.33 74	68.19 63	97.27 97	89.09 67	94.90 22	95.25 94

xiu_mvs_v2_base		87.92 33	87.38 48	89.55 13	91.41 142	76.43 3	95.74 22	93.12 121	83.53 31	89.55 42	95.95 58	53.45 289	97.68 62	91.07 54	92.62 66	94.54 142

test_fmvsmconf_n		86.58 59	87.17 49	84.82 174	85.28 332	62.55 308	94.26 78	89.78 305	83.81 29	87.78 56	96.33 46	65.33 95	96.98 119	94.40 20	87.55 143	94.95 109

SF-MVS		87.03 47	87.09 50	86.84 69	92.70 96	67.45 138	93.64 115	93.76 86	70.78 311	86.25 69	96.44 41	66.98 74	97.79 58	88.68 71	94.56 36	95.28 89

SPE-MVS-test		86.14 71	87.01 51	83.52 239	92.63 98	59.36 387	95.49 29	91.92 178	80.09 88	85.46 82	95.53 69	61.82 161	95.77 199	86.77 95	93.37 56	95.41 75

alignmvs		87.28 44	86.97 52	88.24 31	91.30 144	71.14 31	95.61 27	93.56 97	79.30 115	87.07 63	95.25 82	68.43 60	96.93 127	87.87 76	84.33 191	96.65 20

fmvsm_s_conf0.5_n_5		86.38 64	86.94 53	84.71 186	84.67 344	63.29 287	94.04 89	89.99 300	82.88 38	87.85 55	96.03 56	62.89 142	96.36 156	94.15 21	89.95 115	94.48 152

fmvsm_s_conf0.5_n		86.39 62	86.91 54	84.82 174	87.36 265	63.54 281	94.74 58	90.02 298	82.52 42	90.14 38	96.92 26	62.93 140	97.84 57	95.28 11	82.26 223	93.07 221

SteuartSystems-ACMMP		86.82 55	86.90 55	86.58 89	90.42 162	66.38 177	96.09 18	93.87 81	77.73 151	84.01 98	95.66 63	63.39 128	97.94 50	87.40 83	93.55 54	95.42 74
Skip Steuart: Steuart Systems R&D Blog.
TestfortrainingZip a		86.96 48	86.88 56	87.23 56	94.76 37	67.02 155	94.47 66	94.08 77	70.68 313	88.57 50	96.93 22	69.03 58	98.78 27	84.41 122	88.95 128	95.88 57

PVSNet_Blended		86.73 57	86.86 57	86.31 111	93.76 57	67.53 134	96.33 17	93.61 95	82.34 46	81.00 135	93.08 144	63.19 133	97.29 92	87.08 91	91.38 92	94.13 173

PHI-MVS		86.83 53	86.85 58	86.78 74	93.47 70	65.55 203	95.39 32	95.10 28	71.77 282	85.69 78	96.52 38	62.07 156	98.77 28	86.06 100	95.60 12	96.03 48

UBG		86.83 53	86.70 59	87.20 58	93.07 83	69.81 53	93.43 128	95.56 15	81.52 54	81.50 123	92.12 173	73.58 30	96.28 160	84.37 123	85.20 178	95.51 72

fmvsm_s_conf0.5_n_7		85.24 90	86.69 60	80.91 327	84.52 349	60.10 373	93.35 131	90.35 278	83.41 33	86.54 68	96.27 48	60.50 176	90.02 414	94.84 16	90.38 108	92.61 235

BP-MVS1		86.54 60	86.68 61	86.13 115	87.80 254	67.18 148	92.97 145	95.62 12	79.92 92	82.84 110	94.14 122	74.95 19	96.46 152	82.91 144	88.96 127	94.74 125

NormalMVS		86.39 62	86.66 62	85.60 137	92.12 112	65.95 192	94.88 51	90.83 252	84.69 21	83.67 101	94.10 123	63.16 135	96.91 131	85.31 105	91.15 96	93.93 187

CS-MVS		85.80 79	86.65 63	83.27 251	92.00 120	58.92 391	95.31 34	91.86 183	79.97 89	84.82 88	95.40 72	62.26 150	95.51 224	86.11 99	92.08 77	95.37 78

testing11		86.71 58	86.44 64	87.55 46	93.54 67	71.35 26	93.65 114	95.58 13	81.36 63	80.69 140	92.21 170	72.30 40	96.46 152	85.18 109	83.43 209	94.82 120

SymmetryMVS		86.32 65	86.39 65	86.12 116	90.52 160	65.95 192	94.88 51	94.58 53	84.69 21	83.67 101	94.10 123	63.16 135	96.91 131	85.31 105	86.59 159	95.51 72

MG-MVS		87.11 46	86.27 66	89.62 9	97.79 1	76.27 4	94.96 50	94.49 56	78.74 130	83.87 99	92.94 148	64.34 109	96.94 125	75.19 224	94.09 42	95.66 66

CSCG		86.87 50	86.26 67	88.72 19	95.05 35	70.79 35	93.83 106	95.33 20	68.48 346	77.63 196	94.35 113	73.04 32	98.45 36	84.92 113	93.71 51	96.92 16

sasdasda		86.85 51	86.25 68	88.66 22	91.80 128	71.92 20	93.54 120	91.71 192	80.26 84	87.55 57	95.25 82	63.59 125	96.93 127	88.18 73	84.34 189	97.11 10

canonicalmvs		86.85 51	86.25 68	88.66 22	91.80 128	71.92 20	93.54 120	91.71 192	80.26 84	87.55 57	95.25 82	63.59 125	96.93 127	88.18 73	84.34 189	97.11 10

jason		86.40 61	86.17 70	87.11 61	86.16 309	70.54 38	95.71 25	92.19 165	82.00 49	84.58 90	94.34 114	61.86 159	95.53 223	87.76 77	90.89 100	95.27 90
jason: jason.
myMVS_eth3d28		86.31 67	86.15 71	86.78 74	93.56 65	70.49 39	92.94 148	95.28 21	82.47 43	78.70 184	92.07 176	72.45 38	95.41 225	82.11 153	85.78 171	94.44 154

ETV-MVS		86.01 74	86.11 72	85.70 133	90.21 167	67.02 155	93.43 128	91.92 178	81.21 65	84.13 97	94.07 127	60.93 170	95.63 211	89.28 65	89.81 117	94.46 153

fmvsm_s_conf0.5_n_a		85.75 80	86.09 73	84.72 184	85.73 323	63.58 278	93.79 107	89.32 325	81.42 61	90.21 36	96.91 27	62.41 147	97.67 64	94.48 18	80.56 252	92.90 227

test_fmvsmconf0.1_n		85.71 81	86.08 74	84.62 195	80.83 395	62.32 313	93.84 104	88.81 357	83.50 32	87.00 64	96.01 57	63.36 129	96.93 127	94.04 24	87.29 147	94.61 137

APD-MVS		85.93 76	85.99 75	85.76 129	95.98 29	65.21 212	93.59 118	92.58 149	66.54 365	86.17 72	95.88 59	63.83 117	97.00 115	86.39 97	92.94 62	95.06 103
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
fmvsm_s_conf0.1_n		85.61 84	85.93 76	84.68 189	82.95 376	63.48 283	94.03 91	89.46 319	81.69 52	89.86 39	96.74 34	61.85 160	97.75 60	94.74 17	82.01 231	92.81 231

MSLP-MVS++		86.27 68	85.91 77	87.35 53	92.01 119	68.97 86	95.04 45	92.70 138	79.04 125	81.50 123	96.50 40	58.98 205	96.78 135	83.49 137	93.93 45	96.29 39

WTY-MVS		86.32 65	85.81 78	87.85 34	92.82 92	69.37 69	95.20 37	95.25 23	82.71 40	81.91 119	94.73 99	67.93 67	97.63 69	79.55 186	82.25 225	96.54 25

ACMMP_NAP		86.05 72	85.80 79	86.80 73	91.58 134	67.53 134	91.79 219	93.49 103	74.93 204	84.61 89	95.30 76	59.42 194	97.92 51	86.13 98	94.92 20	94.94 110

MVS_111021_HR		86.19 70	85.80 79	87.37 52	93.17 78	69.79 54	93.99 92	93.76 86	79.08 122	78.88 180	93.99 128	62.25 151	98.15 44	85.93 101	91.15 96	94.15 171

MGCFI-Net		85.59 85	85.73 81	85.17 158	91.41 142	62.44 309	92.87 154	91.31 211	79.65 101	86.99 65	95.14 88	62.90 141	96.12 169	87.13 88	84.13 197	96.96 15

VNet		86.20 69	85.65 82	87.84 35	93.92 54	69.99 45	95.73 24	95.94 7	78.43 136	86.00 74	93.07 145	58.22 218	97.00 115	85.22 107	84.33 191	96.52 26

fmvsm_s_conf0.5_n_2		85.06 94	85.60 83	83.44 245	86.92 288	60.53 362	94.41 71	87.31 398	83.30 34	88.72 49	96.72 35	54.28 277	97.75 60	94.07 23	84.68 188	92.04 258

testing99		86.01 74	85.47 84	87.63 44	93.62 62	71.25 28	93.47 126	95.23 24	80.42 79	80.60 142	91.95 185	71.73 46	96.50 150	80.02 182	82.22 226	95.13 99

CDPH-MVS		85.71 81	85.46 85	86.46 102	94.75 41	67.19 146	93.89 99	92.83 134	70.90 307	83.09 108	95.28 78	63.62 123	97.36 87	80.63 176	94.18 41	94.84 116

PAPM		85.89 78	85.46 85	87.18 59	88.20 237	72.42 19	92.41 185	92.77 136	82.11 48	80.34 150	93.07 145	68.27 61	95.02 242	78.39 202	93.59 53	94.09 177

GDP-MVS		85.54 86	85.32 87	86.18 113	87.64 257	67.95 120	92.91 152	92.36 155	77.81 148	83.69 100	94.31 116	72.84 34	96.41 154	80.39 179	85.95 166	94.19 167

testing91		85.93 76	85.31 88	87.78 37	93.59 64	71.47 23	93.50 123	95.08 31	80.26 84	80.53 146	91.93 186	70.43 50	96.51 149	80.32 180	82.13 229	95.37 78

DeepC-MVS	77.85 3	85.52 87	85.24 89	86.37 107	88.80 205	66.64 171	92.15 195	93.68 92	81.07 67	76.91 210	93.64 135	62.59 144	98.44 37	85.50 103	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
casdiffmvs_mvg		85.66 83	85.18 90	87.09 62	88.22 236	69.35 70	93.74 111	91.89 181	81.47 56	80.10 153	91.45 201	64.80 103	96.35 157	87.23 86	87.69 141	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
FBQ-MVS		86.03 73	85.15 91	88.66 22	93.10 81	73.31 14	92.70 162	95.27 22	81.43 60	82.52 116	91.06 216	67.89 68	96.56 144	79.87 183	82.51 219	96.13 44

MP-MVS-pluss		85.24 90	85.13 92	85.56 138	91.42 139	65.59 201	91.54 239	92.51 151	74.56 207	80.62 141	95.64 64	59.15 201	97.00 115	86.94 93	93.80 47	94.07 179
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ZNCC-MVS		85.33 89	85.08 93	86.06 117	93.09 82	65.65 199	93.89 99	93.41 108	73.75 227	79.94 155	94.68 101	60.61 175	98.03 47	82.63 148	93.72 50	94.52 144

EC-MVSNet		84.53 111	85.04 94	83.01 257	89.34 184	61.37 342	94.42 70	91.09 231	77.91 146	83.24 104	94.20 120	58.37 216	95.40 226	85.35 104	91.41 90	92.27 252

MP-MVS		85.02 95	84.97 95	85.17 158	92.60 99	64.27 246	93.24 134	92.27 158	73.13 239	79.63 165	94.43 107	61.90 157	97.17 103	85.00 111	92.56 68	94.06 180
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EIA-MVS		84.84 102	84.88 96	84.69 188	91.30 144	62.36 312	93.85 101	92.04 171	79.45 110	79.33 170	94.28 118	62.42 146	96.35 157	80.05 181	91.25 95	95.38 77

casdiffmvs		85.37 88	84.87 97	86.84 69	88.25 234	69.07 80	93.04 142	91.76 188	81.27 64	80.84 138	92.07 176	64.23 111	96.06 175	84.98 112	87.43 145	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
fmvsm_s_conf0.1_n_a		84.76 104	84.84 98	84.53 197	80.23 408	63.50 282	92.79 156	88.73 361	80.46 77	89.84 40	96.65 37	60.96 169	97.57 74	93.80 26	80.14 254	92.53 240

lecture		84.77 103	84.81 99	84.65 191	92.12 112	62.27 316	94.74 58	92.64 146	68.35 347	85.53 79	95.30 76	59.77 187	97.91 52	83.73 133	91.15 96	93.77 196

fmvsm_s_conf0.1_n_2		84.40 114	84.78 100	83.27 251	85.25 333	60.41 365	94.13 83	85.69 423	83.05 36	87.99 53	96.37 42	52.75 294	97.68 62	93.75 27	84.05 198	91.71 266

testing222		85.18 92	84.69 101	86.63 85	92.91 88	69.91 49	92.61 171	95.80 10	80.31 83	80.38 148	92.27 166	68.73 59	95.19 239	75.94 218	83.27 212	94.81 122

PAPR		85.15 93	84.47 102	87.18 59	96.02 28	68.29 106	91.85 217	93.00 127	76.59 181	79.03 176	95.00 90	61.59 162	97.61 71	78.16 203	89.00 126	95.63 67

baseline		85.01 96	84.44 103	86.71 79	88.33 231	68.73 94	90.24 304	91.82 187	81.05 68	81.18 129	92.50 158	63.69 120	96.08 174	84.45 121	86.71 157	95.32 84

HFP-MVS		84.73 106	84.40 104	85.72 131	93.75 59	65.01 218	93.50 123	93.19 116	72.19 265	79.22 173	94.93 93	59.04 204	97.67 64	81.55 163	92.21 72	94.49 151

E3new		84.94 100	84.36 105	86.69 82	89.06 197	69.31 71	92.68 168	91.29 216	80.72 72	81.03 132	92.14 172	61.89 158	95.91 182	84.59 118	85.85 170	94.86 112

GST-MVS		84.63 109	84.29 106	85.66 134	92.82 92	65.27 210	93.04 142	93.13 120	73.20 237	78.89 177	94.18 121	59.41 195	97.85 56	81.45 165	92.48 70	93.86 193

viewmanbaseed2359cas		84.89 101	84.26 107	86.78 74	88.50 216	69.77 56	92.69 167	91.13 227	81.11 66	81.54 122	91.98 182	60.35 177	95.73 201	84.47 120	86.56 160	94.84 116

viewcassd2359sk11		84.74 105	84.11 108	86.64 84	88.57 210	69.20 78	92.61 171	91.23 218	80.58 73	80.85 137	91.96 183	61.39 164	95.89 184	84.28 124	85.49 175	94.82 120

ACMMPR		84.37 115	84.06 109	85.28 153	93.56 65	64.37 241	93.50 123	93.15 119	72.19 265	78.85 182	94.86 96	56.69 243	97.45 80	81.55 163	92.20 73	94.02 183

region2R		84.36 116	84.03 110	85.36 148	93.54 67	64.31 244	93.43 128	92.95 130	72.16 268	78.86 181	94.84 97	56.97 238	97.53 76	81.38 167	92.11 76	94.24 165

Casviewmamba		84.58 110	83.95 111	86.47 101	87.22 268	67.76 126	92.71 160	90.96 245	80.81 70	79.29 172	91.85 188	62.20 153	96.33 159	84.60 117	85.91 168	95.32 84

hybridcas		84.65 108	83.95 111	86.74 78	87.18 271	68.78 92	92.94 148	91.36 209	80.47 76	79.32 171	91.67 197	62.13 155	96.19 165	83.15 139	87.36 146	95.25 94

diffmvs		84.28 118	83.83 113	85.61 136	87.40 263	68.02 117	90.88 274	89.24 329	80.54 74	81.64 121	92.52 157	59.83 185	94.52 275	87.32 84	85.11 179	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
balanced_ft_v1		84.95 99	83.81 114	88.38 29	93.31 72	73.59 12	85.95 386	92.51 151	77.25 164	73.97 252	89.14 262	59.30 197	95.25 237	92.50 37	90.34 110	96.31 37

E2		84.45 112	83.74 115	86.56 91	87.90 246	69.06 81	92.53 179	91.13 227	80.35 81	80.58 144	91.69 195	60.70 171	95.84 187	83.80 131	84.99 180	94.79 123

E3		84.45 112	83.74 115	86.56 91	87.90 246	69.06 81	92.53 179	91.13 227	80.35 81	80.58 144	91.69 195	60.70 171	95.84 187	83.80 131	84.99 180	94.79 123

ETVMVS		84.22 122	83.71 117	85.76 129	92.58 100	68.25 110	92.45 183	95.53 17	79.54 108	79.46 167	91.64 199	70.29 51	94.18 290	69.16 287	82.76 218	94.84 116

EI-MVSNet-Vis-set		83.77 136	83.67 118	84.06 215	92.79 95	63.56 279	91.76 225	94.81 39	79.65 101	77.87 193	94.09 125	63.35 130	97.90 53	79.35 190	79.36 265	90.74 288

MVSMamba_PlusPlus		84.97 98	83.65 119	88.93 16	90.17 168	74.04 9	87.84 362	92.69 141	62.18 410	81.47 125	87.64 290	71.47 47	96.28 160	84.69 115	94.74 33	96.47 31

test_fmvsmconf0.01_n		83.70 140	83.52 120	84.25 211	75.26 459	61.72 331	92.17 194	87.24 400	82.36 45	84.91 87	95.41 71	55.60 257	96.83 134	92.85 33	85.87 169	94.21 166

CANet_DTU		84.09 125	83.52 120	85.81 126	90.30 165	66.82 165	91.87 215	89.01 347	85.27 14	86.09 73	93.74 132	47.71 353	96.98 119	77.90 205	89.78 119	93.65 200

PVSNet_Blended_VisFu		83.97 130	83.50 122	85.39 143	90.02 170	66.59 174	93.77 109	91.73 190	77.43 160	77.08 209	89.81 250	63.77 119	96.97 122	79.67 185	88.21 135	92.60 236

diffmvs_AUTHOR		83.97 130	83.49 123	85.39 143	86.09 311	67.83 123	90.76 279	89.05 345	79.94 90	81.43 126	92.23 169	59.53 191	94.42 279	87.18 87	85.22 177	93.92 189

test_fmvsmvis_n_1920		83.80 135	83.48 124	84.77 179	82.51 379	63.72 269	91.37 248	83.99 441	81.42 61	77.68 195	95.74 62	58.37 216	97.58 72	93.38 28	86.87 151	93.00 224

XVS		83.87 133	83.47 125	85.05 162	93.22 74	63.78 264	92.92 150	92.66 143	73.99 219	78.18 190	94.31 116	55.25 259	97.41 84	79.16 192	91.58 87	93.95 185

CHOSEN 1792x2688		84.98 97	83.45 126	89.57 12	89.94 172	75.14 6	92.07 201	92.32 156	81.87 50	75.68 220	88.27 276	60.18 180	98.60 33	80.46 178	90.27 111	94.96 108

PVSNet_BlendedMVS		83.38 152	83.43 127	83.22 253	93.76 57	67.53 134	94.06 85	93.61 95	79.13 120	81.00 135	85.14 328	63.19 133	97.29 92	87.08 91	73.91 314	84.83 398

MAR-MVS		84.18 123	83.43 127	86.44 104	96.25 24	65.93 194	94.28 77	94.27 71	74.41 210	79.16 175	95.61 65	53.99 280	98.88 26	69.62 281	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
baseline2		83.68 141	83.42 129	84.48 200	87.37 264	66.00 189	90.06 308	95.93 8	79.71 99	69.08 317	90.39 227	77.92 7	96.28 160	78.91 197	81.38 239	91.16 281

CP-MVS		83.71 139	83.40 130	84.65 191	93.14 79	63.84 262	94.59 63	92.28 157	71.03 305	77.41 200	94.92 94	55.21 262	96.19 165	81.32 168	90.70 102	93.91 190

MTAPA		83.91 132	83.38 131	85.50 139	91.89 126	65.16 214	81.75 428	92.23 159	75.32 198	80.53 146	95.21 85	56.06 252	97.16 106	84.86 114	92.55 69	94.18 168

HY-MVS	76.49 5	84.28 118	83.36 132	87.02 65	92.22 107	67.74 127	84.65 395	94.50 55	79.15 119	82.23 117	87.93 285	66.88 75	96.94 125	80.53 177	82.20 227	96.39 36

reproduce-ours		83.51 149	83.33 133	84.06 215	92.18 110	60.49 363	90.74 281	92.04 171	64.35 387	83.24 104	95.59 67	59.05 202	97.27 97	83.61 134	89.17 124	94.41 159

our_new_method		83.51 149	83.33 133	84.06 215	92.18 110	60.49 363	90.74 281	92.04 171	64.35 387	83.24 104	95.59 67	59.05 202	97.27 97	83.61 134	89.17 124	94.41 159

onestephybrid01		83.68 141	83.31 135	84.81 177	86.53 297	65.38 208	90.54 292	89.14 337	79.52 109	81.01 133	92.02 178	58.91 206	94.91 251	88.26 72	83.86 201	94.14 172

hybridnocas07		83.76 137	83.21 136	85.39 143	86.64 292	67.40 139	91.08 266	88.77 360	79.78 98	80.35 149	92.15 171	59.24 200	94.67 264	87.11 90	83.79 202	94.11 175

viewdifsd2359ckpt13		84.08 126	83.21 136	86.70 80	88.49 220	69.55 62	92.25 189	91.14 225	79.71 99	79.73 162	91.72 194	58.83 208	95.89 184	82.06 154	84.99 180	94.66 134

MVS_Test		84.16 124	83.20 138	87.05 64	91.56 135	69.82 52	89.99 313	92.05 170	77.77 150	82.84 110	86.57 307	63.93 116	96.09 171	74.91 229	89.18 123	95.25 94

E4		84.00 129	83.19 139	86.46 102	86.99 278	68.85 88	92.39 186	90.99 244	79.94 90	80.17 152	91.36 206	59.73 188	95.79 196	82.87 145	84.22 195	94.74 125

viewmacassd2359aftdt		84.03 127	83.18 140	86.59 88	86.76 291	69.44 64	92.44 184	90.85 251	80.38 80	80.78 139	91.33 207	58.54 213	95.62 213	82.15 152	85.41 176	94.72 128

test_yl		84.28 118	83.16 141	87.64 40	94.52 44	69.24 76	95.78 19	95.09 29	69.19 334	81.09 130	92.88 152	57.00 236	97.44 81	81.11 172	81.76 235	96.23 42

DCV-MVSNet		84.28 118	83.16 141	87.64 40	94.52 44	69.24 76	95.78 19	95.09 29	69.19 334	81.09 130	92.88 152	57.00 236	97.44 81	81.11 172	81.76 235	96.23 42

testing3-2		83.11 159	83.15 143	82.98 258	91.92 123	64.01 257	94.39 74	95.37 18	78.32 137	75.53 225	90.06 246	73.18 31	93.18 332	74.34 234	75.27 303	91.77 265

ET-MVSNet_ETH3D		84.01 128	83.15 143	86.58 89	90.78 157	70.89 33	94.74 58	94.62 50	81.44 59	58.19 428	93.64 135	73.64 29	92.35 368	82.66 147	78.66 275	96.50 30

hybrid		83.58 147	83.00 145	85.34 149	86.38 304	67.51 137	90.92 270	88.87 355	78.49 135	80.59 143	92.09 175	58.77 210	94.46 277	87.12 89	83.74 203	94.06 180

reproduce_model		83.15 157	82.96 146	83.73 230	92.02 116	59.74 379	90.37 298	92.08 169	63.70 394	82.86 109	95.48 70	58.62 211	97.17 103	83.06 141	88.42 133	94.26 163

EI-MVSNet-UG-set		83.14 158	82.96 146	83.67 235	92.28 105	63.19 292	91.38 247	94.68 46	79.22 117	76.60 212	93.75 131	62.64 143	97.76 59	78.07 204	78.01 278	90.05 297

HPM-MVS		83.25 154	82.95 148	84.17 213	92.25 106	62.88 302	90.91 271	91.86 183	70.30 318	77.12 206	93.96 129	56.75 241	96.28 160	82.04 155	91.34 94	93.34 209
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test2506		83.29 153	82.92 149	84.37 204	88.39 228	63.18 293	92.01 204	91.35 210	77.66 153	78.49 189	91.42 202	64.58 107	95.09 241	73.19 241	89.23 121	94.85 113

MVSFormer		83.75 138	82.88 150	86.37 107	89.24 193	71.18 29	89.07 338	90.69 261	65.80 375	87.13 61	94.34 114	64.99 98	92.67 354	72.83 245	91.80 83	95.27 90

MVS		84.66 107	82.86 151	90.06 3	90.93 152	74.56 8	87.91 360	95.54 16	68.55 344	72.35 279	94.71 100	59.78 186	98.90 24	81.29 169	94.69 34	96.74 19

Effi-MVS+		83.82 134	82.76 152	86.99 66	89.56 180	69.40 65	91.35 252	86.12 417	72.59 252	83.22 107	92.81 155	59.60 190	96.01 179	81.76 162	87.80 140	95.56 70

LFMVS		84.34 117	82.73 153	89.18 15	94.76 37	73.25 15	94.99 49	91.89 181	71.90 274	82.16 118	93.49 139	47.98 347	97.05 110	82.55 149	84.82 184	97.25 9

PGM-MVS		83.25 154	82.70 154	84.92 167	92.81 94	64.07 254	90.44 294	92.20 163	71.28 299	77.23 204	94.43 107	55.17 263	97.31 91	79.33 191	91.38 92	93.37 208

E5new		83.62 143	82.65 155	86.55 93	86.98 279	69.28 74	91.69 229	90.96 245	79.61 103	79.80 157	91.25 209	58.04 222	95.84 187	81.83 160	83.66 206	94.52 144

E6new		83.62 143	82.65 155	86.55 93	86.98 279	69.29 72	91.69 229	90.95 248	79.60 106	79.80 157	91.25 209	58.04 222	95.84 187	81.84 158	83.67 204	94.52 144

E6		83.62 143	82.65 155	86.55 93	86.98 279	69.29 72	91.69 229	90.95 248	79.60 106	79.80 157	91.25 209	58.04 222	95.84 187	81.84 158	83.67 204	94.52 144

E5		83.62 143	82.65 155	86.55 93	86.98 279	69.28 74	91.69 229	90.96 245	79.61 103	79.80 157	91.25 209	58.04 222	95.84 187	81.83 160	83.66 206	94.52 144

viewmamba		83.23 156	82.64 159	85.00 165	86.40 303	66.16 184	90.68 284	88.35 376	79.92 92	78.68 185	92.02 178	58.86 207	94.72 257	85.55 102	83.31 211	94.12 174

SR-MVS		82.81 165	82.58 160	83.50 242	93.35 71	61.16 345	92.23 192	91.28 217	64.48 386	81.27 127	95.28 78	53.71 284	95.86 186	82.87 145	88.77 130	93.49 206

viewdifsd2359ckpt09		83.52 148	82.57 161	86.37 107	88.02 243	68.47 101	91.78 222	89.63 315	79.61 103	78.56 187	92.00 181	59.28 198	95.96 181	81.94 156	82.35 220	94.69 129

h-mvs33		83.01 161	82.56 162	84.35 205	89.34 184	62.02 320	92.72 159	93.76 86	81.45 57	82.73 113	92.25 168	60.11 181	97.13 108	87.69 78	62.96 402	93.91 190

thisisatest0515		83.41 151	82.49 163	86.16 114	89.46 183	68.26 108	93.54 120	94.70 45	74.31 213	75.75 218	90.92 217	72.62 36	96.52 148	69.64 279	81.50 238	93.71 197

mPP-MVS		82.96 163	82.44 164	84.52 198	92.83 90	62.92 300	92.76 157	91.85 185	71.52 294	75.61 223	94.24 119	53.48 288	96.99 118	78.97 195	90.73 101	93.64 201

sss		82.71 168	82.38 165	83.73 230	89.25 190	59.58 382	92.24 191	94.89 34	77.96 143	79.86 156	92.38 163	56.70 242	97.05 110	77.26 208	80.86 247	94.55 140

CLD-MVS		82.73 166	82.35 166	83.86 223	87.90 246	67.65 130	95.45 30	92.18 166	85.06 16	72.58 270	92.27 166	52.46 297	95.78 197	84.18 125	79.06 270	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
MVSTER		82.47 172	82.05 167	83.74 228	92.68 97	69.01 84	91.90 214	93.21 113	79.83 94	72.14 280	85.71 321	74.72 21	94.72 257	75.72 220	72.49 324	87.50 333

viewdifsd2359ckpt07		82.95 164	82.04 168	85.66 134	87.19 270	66.73 169	91.56 238	90.39 277	77.58 156	77.58 199	91.19 213	58.57 212	95.65 210	82.32 150	82.01 231	94.60 138

PMMVS		81.98 185	82.04 168	81.78 295	89.76 176	56.17 422	91.13 265	90.69 261	77.96 143	80.09 154	93.57 137	46.33 372	94.99 245	81.41 166	87.46 144	94.17 169

test_vis1_n_1920		81.66 189	82.01 170	80.64 331	82.24 381	55.09 431	94.76 57	86.87 404	81.67 53	84.40 92	94.63 102	38.17 414	94.67 264	91.98 43	83.34 210	92.16 256

TESTMET0.1,1		82.41 173	81.98 171	83.72 232	88.08 239	63.74 266	92.70 162	93.77 85	79.30 115	77.61 197	87.57 292	58.19 219	94.08 295	73.91 236	86.68 158	93.33 211

viewmambaseed2359dif		82.60 171	81.91 172	84.67 190	85.83 318	66.09 185	90.50 293	89.01 347	75.46 193	79.64 164	92.01 180	59.51 192	94.38 281	82.99 143	82.26 223	93.54 203

PAPM_NR		82.97 162	81.84 173	86.37 107	94.10 51	66.76 168	87.66 366	92.84 133	69.96 323	74.07 250	93.57 137	63.10 138	97.50 78	70.66 274	90.58 104	94.85 113

VDD-MVS		83.06 160	81.81 174	86.81 72	90.86 155	67.70 128	95.40 31	91.50 203	75.46 193	81.78 120	92.34 165	40.09 404	97.13 108	86.85 94	82.04 230	95.60 68

DP-MVS Recon		82.73 166	81.65 175	85.98 119	97.31 4	67.06 151	95.15 39	91.99 175	69.08 339	76.50 215	93.89 130	54.48 273	98.20 43	70.76 272	85.66 173	92.69 232

MVS_111021_LR		82.02 184	81.52 176	83.51 241	88.42 226	62.88 302	89.77 316	88.93 352	76.78 173	75.55 224	93.10 142	50.31 321	95.38 228	83.82 130	87.02 149	92.26 253

EPP-MVSNet		81.79 187	81.52 176	82.61 268	88.77 206	60.21 371	93.02 144	93.66 93	68.52 345	72.90 264	90.39 227	72.19 42	94.96 246	74.93 228	79.29 268	92.67 233

nomal-1		82.17 179	81.45 178	84.34 206	90.99 150	69.47 63	83.86 403	93.64 94	77.94 145	73.62 257	85.72 320	66.65 77	91.90 379	80.76 175	79.90 256	91.64 267

dtuplus		82.25 176	81.42 179	84.71 186	85.38 328	66.05 186	90.62 290	89.27 327	75.16 201	79.22 173	91.76 190	58.05 221	94.56 271	81.18 171	82.19 228	93.52 204

APD-MVS_3200maxsize		81.64 190	81.32 180	82.59 270	92.36 103	58.74 393	91.39 245	91.01 243	63.35 398	79.72 163	94.62 103	51.82 300	96.14 168	79.71 184	87.93 138	92.89 228

RRT-MVS		82.61 170	81.16 181	86.96 67	91.10 148	68.75 93	87.70 365	92.20 163	76.97 168	72.68 266	87.10 301	51.30 311	96.41 154	83.56 136	87.84 139	95.74 63

CostFormer		82.33 174	81.15 182	85.86 124	89.01 200	68.46 102	82.39 425	93.01 125	75.59 191	80.25 151	81.57 375	72.03 43	94.96 246	79.06 194	77.48 287	94.16 170

xiu_mvs_v1_base_debu		82.16 180	81.12 183	85.26 155	86.42 300	68.72 95	92.59 175	90.44 274	73.12 240	84.20 93	94.36 109	38.04 417	95.73 201	84.12 126	86.81 152	91.33 274

xiu_mvs_v1_base		82.16 180	81.12 183	85.26 155	86.42 300	68.72 95	92.59 175	90.44 274	73.12 240	84.20 93	94.36 109	38.04 417	95.73 201	84.12 126	86.81 152	91.33 274

xiu_mvs_v1_base_debi		82.16 180	81.12 183	85.26 155	86.42 300	68.72 95	92.59 175	90.44 274	73.12 240	84.20 93	94.36 109	38.04 417	95.73 201	84.12 126	86.81 152	91.33 274

hse-mvs2		81.12 204	81.11 186	81.16 315	86.52 299	57.48 408	89.40 329	91.16 221	81.45 57	82.73 113	90.49 225	60.11 181	94.58 266	87.69 78	60.41 429	91.41 273

baseline1		81.84 186	81.03 187	84.28 209	91.60 133	66.62 172	91.08 266	91.66 197	81.87 50	74.86 236	91.67 197	69.98 54	94.92 249	71.76 261	64.75 386	91.29 279

UWE-MVS		80.81 211	81.01 188	80.20 341	89.33 186	57.05 415	91.91 213	94.71 44	75.67 190	75.01 232	89.37 256	63.13 137	91.44 396	67.19 314	82.80 217	92.12 257

WBMVS		81.67 188	80.98 189	83.72 232	93.07 83	69.40 65	94.33 75	93.05 123	76.84 171	72.05 282	84.14 341	74.49 23	93.88 309	72.76 248	68.09 355	87.88 328

3Dnovator	73.91 6	82.69 169	80.82 190	88.31 30	89.57 179	71.26 27	92.60 173	94.39 66	78.84 127	67.89 340	92.48 161	48.42 342	98.52 34	68.80 292	94.40 38	95.15 98

casdiffseed414692147		82.20 177	80.75 191	86.55 93	87.13 274	69.57 61	91.79 219	90.48 269	78.12 141	78.52 188	90.10 245	55.92 254	95.80 194	72.42 254	82.28 222	94.28 162

CDS-MVSNet		81.43 193	80.74 192	83.52 239	86.26 306	64.45 235	92.09 199	90.65 265	75.83 189	73.95 253	89.81 250	63.97 115	92.91 343	71.27 265	82.82 215	93.20 215
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
mvsmamba		81.55 191	80.72 193	84.03 219	91.42 139	66.93 163	83.08 416	89.13 338	78.55 134	67.50 346	87.02 302	51.79 302	90.07 413	87.48 81	90.49 106	95.10 101

SR-MVS-dyc-post		81.06 205	80.70 194	82.15 286	92.02 116	58.56 396	90.90 272	90.45 270	62.76 405	78.89 177	94.46 105	51.25 312	95.61 215	78.77 199	86.77 155	92.28 249

ACMMP		81.49 192	80.67 195	83.93 221	91.71 131	62.90 301	92.13 196	92.22 162	71.79 281	71.68 288	93.49 139	50.32 320	96.96 123	78.47 201	84.22 195	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
HQP-MVS		81.14 202	80.64 196	82.64 267	87.54 259	63.66 276	94.06 85	91.70 195	79.80 95	74.18 243	90.30 230	51.63 305	95.61 215	77.63 206	78.90 271	88.63 316

test_cas_vis1_n_1920		80.45 219	80.61 197	79.97 350	78.25 435	57.01 417	94.04 89	88.33 377	79.06 124	82.81 112	93.70 133	38.65 409	91.63 387	90.82 57	79.81 257	91.27 280

3Dnovator+	73.60 7	82.10 183	80.60 198	86.60 86	90.89 154	66.80 167	95.20 37	93.44 105	74.05 218	67.42 348	92.49 160	49.46 332	97.65 68	70.80 271	91.68 85	95.33 82

guyue		81.23 199	80.57 199	83.21 255	86.64 292	61.85 325	92.52 181	92.78 135	78.69 131	74.92 235	89.42 255	50.07 324	95.35 229	80.79 174	79.31 267	92.42 242

API-MVS		82.28 175	80.53 200	87.54 47	96.13 25	70.59 37	93.63 116	91.04 241	65.72 377	75.45 226	92.83 154	56.11 251	98.89 25	64.10 349	89.75 120	93.15 216

RE-MVS-def			80.48 201		92.02 116	58.56 396	90.90 272	90.45 270	62.76 405	78.89 177	94.46 105	49.30 334		78.77 199	86.77 155	92.28 249

IB-MVS	77.80 4	82.18 178	80.46 202	87.35 53	89.14 195	70.28 42	95.59 28	95.17 27	78.85 126	70.19 305	85.82 318	70.66 49	97.67 64	72.19 258	66.52 369	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
ECVR-MVS		81.29 197	80.38 203	84.01 220	88.39 228	61.96 322	92.56 178	86.79 406	77.66 153	76.63 211	91.42 202	46.34 371	95.24 238	74.36 233	89.23 121	94.85 113

KinetiMVS		81.43 193	80.11 204	85.38 147	86.60 295	65.47 207	92.90 153	93.54 99	75.33 197	77.31 202	90.39 227	46.81 362	96.75 136	71.65 264	86.46 163	93.93 187

thisisatest0530		81.15 201	80.07 205	84.39 203	88.26 233	65.63 200	91.40 243	94.62 50	71.27 300	70.93 295	89.18 260	72.47 37	96.04 176	65.62 334	76.89 294	91.49 270

test1111		80.84 210	80.02 206	83.33 246	87.87 250	60.76 353	92.62 170	86.86 405	77.86 147	75.73 219	91.39 204	46.35 370	94.70 263	72.79 247	88.68 131	94.52 144

Fast-Effi-MVS+		81.14 202	80.01 207	84.51 199	90.24 166	65.86 195	94.12 84	89.15 335	73.81 226	75.37 228	88.26 277	57.26 231	94.53 274	66.97 317	84.92 183	93.15 216

mvs_anonymous		81.36 195	79.99 208	85.46 140	90.39 164	68.40 103	86.88 377	90.61 266	74.41 210	70.31 304	84.67 333	63.79 118	92.32 370	73.13 242	85.70 172	95.67 65

Vis-MVSNet		80.92 209	79.98 209	83.74 228	88.48 222	61.80 326	93.44 127	88.26 382	73.96 222	77.73 194	91.76 190	49.94 326	94.76 254	65.84 329	90.37 109	94.65 135
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
IMVS_0403		81.19 200	79.88 210	85.13 160	88.54 211	64.75 223	88.84 343	90.80 255	76.73 176	75.21 229	90.18 233	54.22 278	96.21 164	73.47 237	80.95 242	94.43 155

nrg030		80.93 208	79.86 211	84.13 214	83.69 365	68.83 89	93.23 135	91.20 219	75.55 192	75.06 231	88.22 280	63.04 139	94.74 256	81.88 157	66.88 366	88.82 314

1112_ss		80.56 216	79.83 212	82.77 262	88.65 208	60.78 351	92.29 188	88.36 374	72.58 253	72.46 276	94.95 91	65.09 97	93.42 327	66.38 323	77.71 280	94.10 176

AstraMVS		80.66 214	79.79 213	83.28 250	85.07 339	61.64 333	92.19 193	90.58 267	79.40 112	74.77 238	90.18 233	45.93 376	95.61 215	83.04 142	76.96 293	92.60 236

HQP_MVS		80.34 222	79.75 214	82.12 288	86.94 284	62.42 310	93.13 138	91.31 211	78.81 128	72.53 271	89.14 262	50.66 317	95.55 221	76.74 209	78.53 276	88.39 322

UA-Net		80.02 229	79.65 215	81.11 318	89.33 186	57.72 403	86.33 383	89.00 351	77.44 159	81.01 133	89.15 261	59.33 196	95.90 183	61.01 370	84.28 193	89.73 303

Vis-MVSNet (Re-imp)		79.24 245	79.57 216	78.24 379	88.46 223	52.29 443	90.41 296	89.12 339	74.24 215	69.13 315	91.91 187	65.77 90	90.09 412	59.00 383	88.09 136	92.33 246

test-LLR		80.10 227	79.56 217	81.72 297	86.93 286	61.17 343	92.70 162	91.54 200	71.51 295	75.62 221	86.94 303	53.83 281	92.38 365	72.21 256	84.76 186	91.60 268

HyFIR lowres test		81.03 206	79.56 217	85.43 141	87.81 253	68.11 115	90.18 305	90.01 299	70.65 315	72.95 263	86.06 314	63.61 124	94.50 276	75.01 227	79.75 259	93.67 198

HPM-MVS_fast		80.25 224	79.55 219	82.33 278	91.55 136	59.95 376	91.32 254	89.16 334	65.23 383	74.71 240	93.07 145	47.81 352	95.74 200	74.87 231	88.23 134	91.31 278

0.3-1-1-0.015		81.31 196	79.49 220	86.77 77	85.74 322	68.70 99	95.01 48	94.42 61	74.29 214	77.09 208	85.61 322	63.31 132	95.69 209	76.63 212	63.30 399	95.91 55

TAMVS		80.37 221	79.45 221	83.13 256	85.14 336	63.37 284	91.23 259	90.76 260	74.81 206	72.65 268	88.49 270	60.63 174	92.95 338	69.41 283	81.95 233	93.08 220

0.4-1-1-0.2		81.28 198	79.42 222	86.84 69	85.80 320	68.82 90	95.10 41	94.43 60	74.45 209	77.18 205	85.54 323	62.27 149	95.70 207	76.72 211	63.30 399	96.01 49

FIs		79.47 239	79.41 223	79.67 358	85.95 314	59.40 384	91.68 233	93.94 80	78.06 142	68.96 322	88.28 275	66.61 79	91.77 383	66.20 326	74.99 304	87.82 329

IS-MVSNet		80.14 226	79.41 223	82.33 278	87.91 245	60.08 374	91.97 208	88.27 380	72.90 248	71.44 292	91.73 193	61.44 163	93.66 318	62.47 363	86.53 161	93.24 212

IMVS_0407		80.80 212	79.39 225	85.00 165	88.54 211	64.75 223	88.40 351	90.80 255	76.73 176	73.95 253	90.18 233	51.55 307	95.81 193	73.47 237	80.95 242	94.43 155

test-mter		79.96 230	79.38 226	81.72 297	86.93 286	61.17 343	92.70 162	91.54 200	73.85 224	75.62 221	86.94 303	49.84 328	92.38 365	72.21 256	84.76 186	91.60 268

BH-w/o		80.49 218	79.30 227	84.05 218	90.83 156	64.36 243	93.60 117	89.42 322	74.35 212	69.09 316	90.15 241	55.23 261	95.61 215	64.61 344	86.43 164	92.17 255

EPNet_dtu		78.80 256	79.26 228	77.43 387	88.06 240	49.71 460	91.96 209	91.95 177	77.67 152	76.56 214	91.28 208	58.51 214	90.20 410	56.37 392	80.95 242	92.39 243
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
icg_test_0407_2		80.38 220	79.22 229	83.88 222	88.54 211	64.75 223	86.79 378	90.80 255	76.73 176	73.95 253	90.18 233	51.55 307	92.45 363	73.47 237	80.95 242	94.43 155

0.4-1-1-0.1		80.99 207	79.16 230	86.51 100	85.55 327	68.21 112	94.77 56	94.42 61	73.75 227	76.57 213	85.41 325	62.35 148	95.62 213	76.30 217	63.28 401	95.71 64

CPTT-MVS		79.59 235	79.16 230	80.89 329	91.54 137	59.80 378	92.10 198	88.54 370	60.42 426	72.96 262	93.28 141	48.27 343	92.80 348	78.89 198	86.50 162	90.06 296

tpmrst		80.57 215	79.14 232	84.84 173	90.10 169	68.28 107	81.70 429	89.72 312	77.63 155	75.96 217	79.54 407	64.94 100	92.71 351	75.43 222	77.28 290	93.55 202

reproduce_monomvs		79.49 238	79.11 233	80.64 331	92.91 88	61.47 339	91.17 264	93.28 111	83.09 35	64.04 380	82.38 361	66.19 82	94.57 268	81.19 170	57.71 437	85.88 381

1314		80.70 213	78.95 234	85.94 121	87.77 256	67.56 132	87.91 360	92.55 150	72.17 267	67.44 347	93.09 143	50.27 322	97.04 113	71.68 263	87.64 142	93.23 213

SDMVSNet		80.26 223	78.88 235	84.40 202	89.25 190	67.63 131	85.35 389	93.02 124	76.77 174	70.84 296	87.12 299	47.95 350	96.09 171	85.04 110	74.55 305	89.48 307

UGNet		79.87 232	78.68 236	83.45 244	89.96 171	61.51 336	92.13 196	90.79 259	76.83 172	78.85 182	86.33 311	38.16 415	96.17 167	67.93 304	87.17 148	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
PVSNet	73.49 8	80.05 228	78.63 237	84.31 207	90.92 153	64.97 219	92.47 182	91.05 240	79.18 118	72.43 277	90.51 224	37.05 429	94.06 297	68.06 301	86.00 165	93.90 192

Test_1112_low_res		79.56 236	78.60 238	82.43 272	88.24 235	60.39 367	92.09 199	87.99 387	72.10 269	71.84 284	87.42 294	64.62 105	93.04 334	65.80 330	77.30 289	93.85 194

tttt0517		79.50 237	78.53 239	82.41 275	87.22 268	61.43 340	89.75 317	94.76 41	69.29 332	67.91 338	88.06 284	72.92 33	95.63 211	62.91 359	73.90 315	90.16 295

thres200		79.66 234	78.33 240	83.66 236	92.54 101	65.82 197	93.06 140	96.31 3	74.90 205	73.30 260	88.66 268	59.67 189	95.61 215	47.84 432	78.67 274	89.56 306

ab-mvs		80.18 225	78.31 241	85.80 127	88.44 224	65.49 206	83.00 419	92.67 142	71.82 280	77.36 201	85.01 329	54.50 270	96.59 141	76.35 216	75.63 301	95.32 84

VDDNet		80.50 217	78.26 242	87.21 57	86.19 307	69.79 54	94.48 65	91.31 211	60.42 426	79.34 169	90.91 218	38.48 412	96.56 144	82.16 151	81.05 241	95.27 90

EI-MVSNet		78.97 251	78.22 243	81.25 312	85.33 329	62.73 305	89.53 326	93.21 113	72.39 260	72.14 280	90.13 242	60.99 167	94.72 257	67.73 306	72.49 324	86.29 366

OPM-MVS		79.00 250	78.09 244	81.73 296	83.52 368	63.83 263	91.64 235	90.30 283	76.36 185	71.97 283	89.93 249	46.30 373	95.17 240	75.10 225	77.70 281	86.19 369
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
FC-MVSNet-test		77.99 273	78.08 245	77.70 382	84.89 342	55.51 428	90.27 302	93.75 89	76.87 169	66.80 358	87.59 291	65.71 91	90.23 409	62.89 360	73.94 313	87.37 337

VPA-MVSNet		79.03 249	78.00 246	82.11 291	85.95 314	64.48 234	93.22 136	94.66 47	75.05 203	74.04 251	84.95 330	52.17 299	93.52 320	74.90 230	67.04 365	88.32 325

miper_enhance_ethall		78.86 254	77.97 247	81.54 303	88.00 244	65.17 213	91.41 241	89.15 335	75.19 200	68.79 325	83.98 344	67.17 73	92.82 346	72.73 249	65.30 376	86.62 356

viewmsd2359difaftdt		79.42 242	77.96 248	83.81 225	83.88 361	63.85 260	89.54 323	87.38 394	77.39 162	74.94 233	89.95 247	51.11 313	94.72 257	79.52 187	67.90 358	92.88 229

viewdifsd2359ckpt11		79.42 242	77.95 249	83.81 225	83.87 362	63.85 260	89.54 323	87.38 394	77.39 162	74.94 233	89.95 247	51.11 313	94.72 257	79.52 187	67.90 358	92.88 229

tpm2		79.80 233	77.95 249	85.34 149	88.28 232	68.26 108	81.56 431	91.42 206	70.11 320	77.59 198	80.50 393	67.40 72	94.26 288	67.34 311	77.35 288	93.51 205

OMC-MVS		78.67 261	77.91 251	80.95 325	85.76 321	57.40 410	88.49 349	88.67 364	73.85 224	72.43 277	92.10 174	49.29 335	94.55 273	72.73 249	77.89 279	90.91 287

114514_t		79.17 246	77.67 252	83.68 234	95.32 33	65.53 204	92.85 155	91.60 199	63.49 396	67.92 337	90.63 222	46.65 367	95.72 206	67.01 316	83.54 208	89.79 301

SSM_0404		79.46 240	77.65 253	84.91 169	88.37 230	67.04 153	89.59 318	87.03 401	67.99 350	75.45 226	89.32 257	47.98 347	95.34 231	71.23 266	81.90 234	92.34 245

BH-RMVSNet		79.46 240	77.65 253	84.89 170	91.68 132	65.66 198	93.55 119	88.09 385	72.93 245	73.37 259	91.12 215	46.20 374	96.12 169	56.28 393	85.61 174	92.91 226

PCF-MVS	73.15 9	79.29 244	77.63 255	84.29 208	86.06 312	65.96 191	87.03 373	91.10 230	69.86 325	69.79 312	90.64 220	57.54 230	96.59 141	64.37 348	82.29 221	90.32 293
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		76.83 297	77.60 256	74.51 418	84.58 348	50.34 456	88.22 354	94.60 52	74.46 208	66.66 359	88.98 267	62.53 145	85.50 454	57.55 389	80.80 250	87.69 331

UniMVSNet_NR-MVSNet		78.15 269	77.55 257	79.98 348	84.46 352	60.26 369	92.25 189	93.20 115	77.50 158	68.88 323	86.61 306	66.10 84	92.13 374	66.38 323	62.55 406	87.54 332

VPNet		78.82 255	77.53 258	82.70 265	84.52 349	66.44 176	93.93 95	92.23 159	80.46 77	72.60 269	88.38 274	49.18 336	93.13 333	72.47 253	63.97 395	88.55 319

GeoE		78.90 253	77.43 259	83.29 249	88.95 201	62.02 320	92.31 187	86.23 413	70.24 319	71.34 293	89.27 259	54.43 274	94.04 300	63.31 355	80.81 249	93.81 195

AUN-MVS		78.37 265	77.43 259	81.17 314	86.60 295	57.45 409	89.46 328	91.16 221	74.11 217	74.40 242	90.49 225	55.52 258	94.57 268	74.73 232	60.43 428	91.48 271

tfpn200view9		78.79 257	77.43 259	82.88 260	92.21 108	64.49 232	92.05 202	96.28 4	73.48 234	71.75 286	88.26 277	60.07 183	95.32 232	45.16 445	77.58 284	88.83 312

thres400		78.68 259	77.43 259	82.43 272	92.21 108	64.49 232	92.05 202	96.28 4	73.48 234	71.75 286	88.26 277	60.07 183	95.32 232	45.16 445	77.58 284	87.48 334

QAPM		79.95 231	77.39 263	87.64 40	89.63 178	71.41 25	93.30 133	93.70 91	65.34 382	67.39 350	91.75 192	47.83 351	98.96 19	57.71 387	89.81 117	92.54 239

TR-MVS		78.77 258	77.37 264	82.95 259	90.49 161	60.88 349	93.67 113	90.07 294	70.08 322	74.51 241	91.37 205	45.69 377	95.70 207	60.12 377	80.32 253	92.29 248

FA-MVS(test-final)		79.12 247	77.23 265	84.81 177	90.54 159	63.98 259	81.35 434	91.71 192	71.09 304	74.85 237	82.94 354	52.85 292	97.05 110	67.97 302	81.73 237	93.41 207

SSM_0407		79.09 248	77.21 266	84.75 182	88.50 216	66.98 159	89.21 334	87.03 401	67.99 350	74.12 247	89.32 257	47.98 347	95.29 236	71.23 266	79.52 260	91.98 260

BH-untuned		78.68 259	77.08 267	83.48 243	89.84 173	63.74 266	92.70 162	88.59 367	71.57 292	66.83 357	88.65 269	51.75 303	95.39 227	59.03 382	84.77 185	91.32 277

tpm		78.58 262	77.03 268	83.22 253	85.94 316	64.56 230	83.21 415	91.14 225	78.31 138	73.67 256	79.68 405	64.01 114	92.09 376	66.07 327	71.26 334	93.03 222

thres100view900		78.37 265	77.01 269	82.46 271	91.89 126	63.21 291	91.19 263	96.33 1	72.28 263	70.45 301	87.89 286	60.31 178	95.32 232	45.16 445	77.58 284	88.83 312

AdaColmap		78.94 252	77.00 270	84.76 181	96.34 18	65.86 195	92.66 169	87.97 389	62.18 410	70.56 298	92.37 164	43.53 389	97.35 88	64.50 347	82.86 214	91.05 283

CHOSEN 280x420		77.35 286	76.95 271	78.55 374	87.07 276	62.68 306	69.71 480	82.95 449	68.80 341	71.48 291	87.27 298	66.03 85	84.00 462	76.47 214	82.81 216	88.95 311

cl22		77.94 275	76.78 272	81.42 305	87.57 258	64.93 221	90.67 285	88.86 356	72.45 257	67.63 344	82.68 358	64.07 112	92.91 343	71.79 259	65.30 376	86.44 359

UniMVSNet (Re)		77.58 283	76.78 272	79.98 348	84.11 358	60.80 350	91.76 225	93.17 118	76.56 182	69.93 311	84.78 332	63.32 131	92.36 367	64.89 341	62.51 408	86.78 350

LuminaMVS		78.14 270	76.66 274	82.60 269	80.82 396	64.64 229	89.33 330	90.45 270	68.25 348	74.73 239	85.51 324	41.15 399	94.14 291	78.96 196	80.69 251	89.04 310

thres600view7		78.00 272	76.66 274	82.03 293	91.93 122	63.69 274	91.30 255	96.33 1	72.43 258	70.46 300	87.89 286	60.31 178	94.92 249	42.64 457	76.64 295	87.48 334

MS-PatchMatch		77.90 277	76.50 276	82.12 288	85.99 313	69.95 48	91.75 227	92.70 138	73.97 221	62.58 397	84.44 337	41.11 400	95.78 197	63.76 352	92.17 74	80.62 447

VortexMVS		77.62 281	76.44 277	81.13 316	88.58 209	63.73 268	91.24 258	91.30 215	77.81 148	65.76 363	81.97 367	49.69 330	93.72 313	76.40 215	65.26 379	85.94 379

miper_ehance_all_eth		77.60 282	76.44 277	81.09 322	85.70 324	64.41 239	90.65 286	88.64 366	72.31 261	67.37 351	82.52 359	64.77 104	92.64 357	70.67 273	65.30 376	86.24 368

XXY-MVS		77.94 275	76.44 277	82.43 272	82.60 378	64.44 236	92.01 204	91.83 186	73.59 233	70.00 308	85.82 318	54.43 274	94.76 254	69.63 280	68.02 357	88.10 327

usedtu_dtu_shiyan1		77.89 278	76.39 280	82.40 276	81.92 386	67.01 157	91.94 211	93.00 127	77.01 166	68.44 332	84.15 339	54.78 267	93.25 329	65.76 331	70.53 337	86.94 346

FE-MVSNET3		77.89 278	76.39 280	82.40 276	81.92 386	67.01 157	91.94 211	93.00 127	77.01 166	68.44 332	84.15 339	54.78 267	93.25 329	65.76 331	70.53 337	86.94 346

PS-MVSNAJss		77.26 287	76.31 282	80.13 343	80.64 400	59.16 389	90.63 289	91.06 237	72.80 249	68.58 329	84.57 335	53.55 285	93.96 305	72.97 243	71.96 328	87.27 341

IMVS_0404		78.11 271	76.29 283	83.59 237	88.54 211	64.75 223	84.63 396	90.80 255	76.73 176	61.16 404	90.18 233	40.17 403	91.58 389	73.47 237	80.95 242	94.43 155

MVP-Stereo		77.12 290	76.23 284	79.79 355	81.72 388	66.34 179	89.29 331	90.88 250	70.56 316	62.01 400	82.88 355	49.34 333	94.13 292	65.55 336	93.80 47	78.88 463
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
GA-MVS		78.33 267	76.23 284	84.65 191	83.65 366	66.30 180	91.44 240	90.14 292	76.01 187	70.32 303	84.02 343	42.50 393	94.72 257	70.98 269	77.00 292	92.94 225

WB-MVSnew		77.14 289	76.18 286	80.01 347	86.18 308	63.24 289	91.26 256	94.11 75	71.72 284	73.52 258	87.29 297	45.14 382	93.00 336	56.98 390	79.42 263	83.80 407

FMVSNet3		77.73 280	76.04 287	82.80 261	91.20 147	68.99 85	91.87 215	91.99 175	73.35 236	67.04 353	83.19 353	56.62 244	92.14 373	59.80 379	69.34 343	87.28 340

EPMVS		78.49 264	75.98 288	86.02 118	91.21 146	69.68 59	80.23 443	91.20 219	75.25 199	72.48 275	78.11 416	54.65 269	93.69 317	57.66 388	83.04 213	94.69 129

OpenMVS	70.45 11	78.54 263	75.92 289	86.41 106	85.93 317	71.68 22	92.74 158	92.51 151	66.49 366	64.56 374	91.96 183	43.88 388	98.10 46	54.61 398	90.65 103	89.44 309

DU-MVS		76.86 294	75.84 290	79.91 351	82.96 374	60.26 369	91.26 256	91.54 200	76.46 184	68.88 323	86.35 309	56.16 249	92.13 374	66.38 323	62.55 406	87.35 338

cascas		78.18 268	75.77 291	85.41 142	87.14 273	69.11 79	92.96 147	91.15 224	66.71 364	70.47 299	86.07 313	37.49 423	96.48 151	70.15 277	79.80 258	90.65 289

WR-MVS		76.76 299	75.74 292	79.82 354	84.60 346	62.27 316	92.60 173	92.51 151	76.06 186	67.87 341	85.34 326	56.76 240	90.24 408	62.20 364	63.69 397	86.94 346

v2v482		77.42 285	75.65 293	82.73 263	80.38 404	67.13 150	91.85 217	90.23 288	75.09 202	69.37 313	83.39 350	53.79 283	94.44 278	71.77 260	65.00 383	86.63 355

c3_l		76.83 297	75.47 294	80.93 326	85.02 340	64.18 251	90.39 297	88.11 384	71.66 285	66.65 360	81.64 373	63.58 127	92.56 358	69.31 285	62.86 403	86.04 374

sd_testset		77.08 291	75.37 295	82.20 284	89.25 190	62.11 319	82.06 426	89.09 341	76.77 174	70.84 296	87.12 299	41.43 398	95.01 244	67.23 313	74.55 305	89.48 307

dmvs_re		76.93 293	75.36 296	81.61 301	87.78 255	60.71 357	80.00 447	87.99 387	79.42 111	69.02 319	89.47 254	46.77 364	94.32 282	63.38 354	74.45 308	89.81 300

Anonymous202405211		77.96 274	75.33 297	85.87 123	93.73 60	64.52 231	94.85 54	85.36 426	62.52 408	76.11 216	90.18 233	29.43 463	97.29 92	68.51 295	77.24 291	95.81 61

Effi-MVS+-dtu		76.14 307	75.28 298	78.72 373	83.22 371	55.17 430	89.87 314	87.78 391	75.42 195	67.98 336	81.43 377	45.08 383	92.52 360	75.08 226	71.63 329	88.48 320

IterMVS-LS		76.49 301	75.18 299	80.43 335	84.49 351	62.74 304	90.64 287	88.80 358	72.40 259	65.16 369	81.72 371	60.98 168	92.27 371	67.74 305	64.65 388	86.29 366
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MonoMVSNet		76.99 292	75.08 300	82.73 263	83.32 370	63.24 289	86.47 382	86.37 409	79.08 122	66.31 361	79.30 409	49.80 329	91.72 384	79.37 189	65.70 374	93.23 213

v1144		76.73 300	74.88 301	82.27 280	80.23 408	66.60 173	91.68 233	90.21 291	73.69 230	69.06 318	81.89 368	52.73 295	94.40 280	69.21 286	65.23 380	85.80 382

cl____		76.07 308	74.67 302	80.28 338	85.15 335	61.76 329	90.12 306	88.73 361	71.16 301	65.43 366	81.57 375	61.15 165	92.95 338	66.54 320	62.17 410	86.13 372

DIV-MVS_self_test		76.07 308	74.67 302	80.28 338	85.14 336	61.75 330	90.12 306	88.73 361	71.16 301	65.42 367	81.60 374	61.15 165	92.94 342	66.54 320	62.16 412	86.14 370

PatchmatchNet		77.46 284	74.63 304	85.96 120	89.55 181	70.35 41	79.97 448	89.55 317	72.23 264	70.94 294	76.91 430	57.03 234	92.79 349	54.27 400	81.17 240	94.74 125
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
NR-MVSNet		76.05 311	74.59 305	80.44 334	82.96 374	62.18 318	90.83 276	91.73 190	77.12 165	60.96 406	86.35 309	59.28 198	91.80 382	60.74 372	61.34 421	87.35 338

LPG-MVS_test		75.82 317	74.58 306	79.56 362	84.31 355	59.37 385	90.44 294	89.73 310	69.49 329	64.86 370	88.42 272	38.65 409	94.30 284	72.56 251	72.76 321	85.01 396

V42		76.46 302	74.55 307	82.19 285	79.14 422	67.82 124	90.26 303	89.42 322	73.75 227	68.63 328	81.89 368	51.31 310	94.09 294	71.69 262	64.84 384	84.66 399

TranMVSNet+NR-MVSNet		75.86 316	74.52 308	79.89 352	82.44 380	60.63 360	91.37 248	91.37 208	76.63 180	67.65 343	86.21 312	52.37 298	91.55 390	61.84 366	60.81 424	87.48 334

v148		76.19 306	74.47 309	81.36 308	80.05 410	64.44 236	91.75 227	90.23 288	73.68 231	67.13 352	80.84 388	55.92 254	93.86 312	68.95 290	61.73 417	85.76 385

eth_miper_zixun_eth		75.96 315	74.40 310	80.66 330	84.66 345	63.02 295	89.28 332	88.27 380	71.88 276	65.73 364	81.65 372	59.45 193	92.81 347	68.13 298	60.53 426	86.14 370

gg-mvs-nofinetune		77.18 288	74.31 311	85.80 127	91.42 139	68.36 104	71.78 474	94.72 43	49.61 471	77.12 206	45.92 502	77.41 9	93.98 304	67.62 307	93.16 60	95.05 104

CVMVSNet		74.04 340	74.27 312	73.33 428	85.33 329	43.94 486	89.53 326	88.39 373	54.33 458	70.37 302	90.13 242	49.17 337	84.05 460	61.83 367	79.36 265	91.99 259

ACMP	71.68 10	75.58 322	74.23 313	79.62 360	84.97 341	59.64 380	90.80 277	89.07 343	70.39 317	62.95 393	87.30 296	38.28 413	93.87 310	72.89 244	71.45 332	85.36 392
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Elysia		76.45 303	74.17 314	83.30 247	80.43 402	64.12 252	89.58 319	90.83 252	61.78 418	72.53 271	85.92 316	34.30 441	94.81 252	68.10 299	84.01 199	90.97 284

StellarMVS		76.45 303	74.17 314	83.30 247	80.43 402	64.12 252	89.58 319	90.83 252	61.78 418	72.53 271	85.92 316	34.30 441	94.81 252	68.10 299	84.01 199	90.97 284

Anonymous20240529		76.84 296	74.15 316	84.88 171	91.02 149	64.95 220	93.84 104	91.09 231	53.57 459	73.00 261	87.42 294	35.91 434	97.32 90	69.14 288	72.41 326	92.36 244

X-MVStestdata		76.86 294	74.13 317	85.05 162	93.22 74	63.78 264	92.92 150	92.66 143	73.99 219	78.18 190	10.19 535	55.25 259	97.41 84	79.16 192	91.58 87	93.95 185

v144192		76.05 311	74.03 318	82.12 288	79.50 416	66.55 175	91.39 245	89.71 313	72.30 262	68.17 334	81.33 380	51.75 303	94.03 302	67.94 303	64.19 390	85.77 383

FMVSNet2		76.07 308	74.01 319	82.26 282	88.85 202	67.66 129	91.33 253	91.61 198	70.84 308	65.98 362	82.25 363	48.03 344	92.00 378	58.46 384	68.73 351	87.10 343

dtuonly		74.56 335	73.92 320	76.48 399	77.15 446	57.27 412	85.09 392	81.23 452	71.37 298	67.61 345	89.65 252	46.68 366	83.84 464	68.79 293	77.69 282	88.33 324

v1192		75.98 313	73.92 320	82.15 286	79.73 412	66.24 182	91.22 260	89.75 307	72.67 251	68.49 330	81.42 378	49.86 327	94.27 286	67.08 315	65.02 382	85.95 377

GBi-Net		75.65 319	73.83 322	81.10 319	88.85 202	65.11 215	90.01 310	90.32 279	70.84 308	67.04 353	80.25 398	48.03 344	91.54 391	59.80 379	69.34 343	86.64 352

test1		75.65 319	73.83 322	81.10 319	88.85 202	65.11 215	90.01 310	90.32 279	70.84 308	67.04 353	80.25 398	48.03 344	91.54 391	59.80 379	69.34 343	86.64 352

test_fmvs1		74.07 339	73.69 324	75.22 408	78.91 426	47.34 472	89.06 340	74.69 475	63.68 395	79.41 168	91.59 200	24.36 474	87.77 435	85.22 107	76.26 298	90.55 292

PLC	68.80 14	75.23 325	73.68 325	79.86 353	92.93 87	58.68 394	90.64 287	88.30 378	60.90 423	64.43 378	90.53 223	42.38 394	94.57 268	56.52 391	76.54 296	86.33 365
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TAPA-MVS	70.22 12	74.94 330	73.53 326	79.17 368	90.40 163	52.07 444	89.19 336	89.61 316	62.69 407	70.07 306	92.67 156	48.89 341	94.32 282	38.26 472	79.97 255	91.12 282
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
v1921920		75.63 321	73.49 327	82.06 292	79.38 417	66.35 178	91.07 269	89.48 318	71.98 271	67.99 335	81.22 383	49.16 338	93.90 308	66.56 319	64.56 389	85.92 380

SD_0403		73.79 344	73.48 328	74.69 415	85.33 329	45.56 482	83.80 404	85.57 424	76.55 183	62.96 392	88.45 271	50.62 319	87.59 439	48.80 425	79.28 269	90.92 286

mamba_0408		76.22 305	73.37 329	84.77 179	88.50 216	66.98 159	58.80 500	86.18 415	69.12 337	74.12 247	89.01 265	47.50 354	95.35 229	67.57 308	79.52 260	91.98 260

SSM_04072		74.86 332	73.37 329	79.35 365	88.50 216	66.98 159	58.80 500	86.18 415	69.12 337	74.12 247	89.01 265	47.50 354	79.09 487	67.57 308	79.52 260	91.98 260

Fast-Effi-MVS+-dtu		75.04 328	73.37 329	80.07 344	80.86 394	59.52 383	91.20 262	85.38 425	71.90 274	65.20 368	84.84 331	41.46 397	92.97 337	66.50 322	72.96 320	87.73 330

SSC-MVS3.2		74.92 331	73.32 332	79.74 357	86.53 297	60.31 368	89.03 341	92.70 138	78.61 133	68.98 321	83.34 351	41.93 396	92.23 372	52.77 409	65.97 372	86.69 351

v8		75.35 323	73.26 333	81.61 301	80.67 399	66.82 165	89.54 323	89.27 327	71.65 286	63.30 388	80.30 397	54.99 265	94.06 297	67.33 312	62.33 409	83.94 405

XVG-OURS-SEG-HR		74.70 334	73.08 334	79.57 361	78.25 435	57.33 411	80.49 439	87.32 396	63.22 400	68.76 326	90.12 244	44.89 384	91.59 388	70.55 275	74.09 312	89.79 301

FE-MVS		75.97 314	73.02 335	84.82 174	89.78 174	65.56 202	77.44 459	91.07 236	64.55 385	72.66 267	79.85 403	46.05 375	96.69 138	54.97 397	80.82 248	92.21 254

blend_shiyan4		75.18 327	73.00 336	81.69 299	75.62 455	64.75 223	91.78 222	91.06 237	65.89 374	61.35 403	77.39 421	62.16 154	93.71 314	68.18 296	63.60 398	86.61 357

v1240		75.21 326	72.98 337	81.88 294	79.20 419	66.00 189	90.75 280	89.11 340	71.63 290	67.41 349	81.22 383	47.36 356	93.87 310	65.46 337	64.72 387	85.77 383

Baseline_NR-MVSNet		73.99 341	72.83 338	77.48 386	80.78 397	59.29 388	91.79 219	84.55 434	68.85 340	68.99 320	80.70 389	56.16 249	92.04 377	62.67 361	60.98 423	81.11 441

SCA		75.82 317	72.76 339	85.01 164	86.63 294	70.08 44	81.06 436	89.19 332	71.60 291	70.01 307	77.09 428	45.53 378	90.25 405	60.43 374	73.27 317	94.68 131

myMVS_eth3d		72.58 361	72.74 340	72.10 440	87.87 250	49.45 462	88.07 356	89.01 347	72.91 246	63.11 389	88.10 281	63.63 122	85.54 451	32.73 490	69.23 346	81.32 439

ACMM	69.62 13	74.34 336	72.73 341	79.17 368	84.25 357	57.87 401	90.36 299	89.93 301	63.17 402	65.64 365	86.04 315	37.79 421	94.10 293	65.89 328	71.52 331	85.55 388
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test0.0.03 1		72.76 355	72.71 342	72.88 432	80.25 407	47.99 468	91.22 260	89.45 320	71.51 295	62.51 398	87.66 289	53.83 281	85.06 456	50.16 417	67.84 362	85.58 386

MDTV_nov1_ep13			72.61 343		89.06 197	68.48 100	80.33 441	90.11 293	71.84 279	71.81 285	75.92 443	53.01 291	93.92 307	48.04 429	73.38 316

test_djsdf		73.76 346	72.56 344	77.39 388	77.00 447	53.93 436	89.07 338	90.69 261	65.80 375	63.92 381	82.03 366	43.14 392	92.67 354	72.83 245	68.53 352	85.57 387

v10		74.77 333	72.54 345	81.46 304	80.33 406	66.71 170	89.15 337	89.08 342	70.94 306	63.08 391	79.86 402	52.52 296	94.04 300	65.70 333	62.17 410	83.64 408

XVG-OURS		74.25 338	72.46 346	79.63 359	78.45 433	57.59 407	80.33 441	87.39 393	63.86 392	68.76 326	89.62 253	40.50 402	91.72 384	69.00 289	74.25 310	89.58 304

CNLPA		74.31 337	72.30 347	80.32 336	91.49 138	61.66 332	90.85 275	80.72 456	56.67 450	63.85 383	90.64 220	46.75 365	90.84 399	53.79 403	75.99 300	88.47 321

tpm cat1		75.30 324	72.21 348	84.58 196	88.52 215	67.77 125	78.16 457	88.02 386	61.88 416	68.45 331	76.37 439	60.65 173	94.03 302	53.77 404	74.11 311	91.93 263

dp		75.01 329	72.09 349	83.76 227	89.28 189	66.22 183	79.96 449	89.75 307	71.16 301	67.80 342	77.19 427	51.81 301	92.54 359	50.39 415	71.44 333	92.51 241

D2MVS		73.80 343	72.02 350	79.15 370	79.15 421	62.97 296	88.58 348	90.07 294	72.94 244	59.22 421	78.30 413	42.31 395	92.70 353	65.59 335	72.00 327	81.79 436

test_fmvs1_n		72.69 359	71.92 351	74.99 413	71.15 475	47.08 474	87.34 371	75.67 470	63.48 397	78.08 192	91.17 214	20.16 488	87.87 432	84.65 116	75.57 302	90.01 298

LCM-MVSNet-Re		72.93 352	71.84 352	76.18 403	88.49 220	48.02 467	80.07 446	70.17 489	73.96 222	52.25 454	80.09 401	49.98 325	88.24 429	67.35 310	84.23 194	92.28 249

pmmvs4		73.92 342	71.81 353	80.25 340	79.17 420	65.24 211	87.43 369	87.26 399	67.64 357	63.46 386	83.91 345	48.96 340	91.53 394	62.94 358	65.49 375	83.96 404

miper_lstm_enhance		73.05 350	71.73 354	77.03 393	83.80 363	58.32 398	81.76 427	88.88 353	69.80 326	61.01 405	78.23 415	57.19 232	87.51 441	65.34 338	59.53 431	85.27 395

pmmvs5		73.35 347	71.52 355	78.86 372	78.64 430	60.61 361	91.08 266	86.90 403	67.69 354	63.32 387	83.64 346	44.33 387	90.53 402	62.04 365	66.02 371	85.46 390

jajsoiax		73.05 350	71.51 356	77.67 383	77.46 443	54.83 432	88.81 344	90.04 297	69.13 336	62.85 395	83.51 348	31.16 456	92.75 350	70.83 270	69.80 339	85.43 391

mvs_tets		72.71 357	71.11 357	77.52 384	77.41 444	54.52 434	88.45 350	89.76 306	68.76 343	62.70 396	83.26 352	29.49 462	92.71 351	70.51 276	69.62 341	85.34 393

pm-mvs1		72.89 353	71.09 358	78.26 378	79.10 423	57.62 405	90.80 277	89.30 326	67.66 355	62.91 394	81.78 370	49.11 339	92.95 338	60.29 376	58.89 434	84.22 403

testing3		70.38 379	70.83 359	69.03 454	85.82 319	43.93 487	90.72 283	90.56 268	68.06 349	60.24 415	86.82 305	64.83 102	84.12 458	26.33 499	64.10 392	79.04 461

IterMVS		72.65 360	70.83 359	78.09 380	82.17 382	62.96 297	87.64 367	86.28 411	71.56 293	60.44 412	78.85 411	45.42 380	86.66 445	63.30 356	61.83 414	84.65 400
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CR-MVSNet		73.79 344	70.82 361	82.70 265	83.15 372	67.96 118	70.25 477	84.00 439	73.67 232	69.97 309	72.41 456	57.82 227	89.48 418	52.99 408	73.13 318	90.64 290

test_vis1_n		71.63 370	70.73 362	74.31 422	69.63 482	47.29 473	86.91 375	72.11 483	63.21 401	75.18 230	90.17 239	20.40 486	85.76 450	84.59 118	74.42 309	89.87 299

tt0805		73.07 349	70.73 362	80.07 344	78.37 434	57.05 415	87.78 363	92.18 166	61.23 422	67.04 353	86.49 308	31.35 455	94.58 266	65.06 340	67.12 364	88.57 318

UniMVSNet_ETH3D		72.74 356	70.53 364	79.36 364	78.62 431	56.64 419	85.01 393	89.20 331	63.77 393	64.84 372	84.44 337	34.05 443	91.86 381	63.94 350	70.89 336	89.57 305

Anonymous20231211		73.08 348	70.39 365	81.13 316	90.62 158	63.33 285	91.40 243	90.06 296	51.84 464	64.46 377	80.67 391	36.49 432	94.07 296	63.83 351	64.17 391	85.98 376

PatchMatch-RL		72.06 366	69.98 366	78.28 377	89.51 182	55.70 427	83.49 408	83.39 447	61.24 421	63.72 384	82.76 356	34.77 438	93.03 335	53.37 407	77.59 283	86.12 373

IterMVS-SCA-FT		71.55 371	69.97 367	76.32 401	81.48 390	60.67 359	87.64 367	85.99 418	66.17 370	59.50 419	78.88 410	45.53 378	83.65 465	62.58 362	61.93 413	84.63 402

WR-MVS_H		70.59 376	69.94 368	72.53 434	81.03 393	51.43 448	87.35 370	92.03 174	67.38 358	60.23 416	80.70 389	55.84 256	83.45 468	46.33 440	58.58 436	82.72 424

CP-MVSNet		70.50 377	69.91 369	72.26 437	80.71 398	51.00 452	87.23 372	90.30 283	67.84 353	59.64 418	82.69 357	50.23 323	82.30 478	51.28 411	59.28 432	83.46 413

FMVSNet1		72.71 357	69.91 369	81.10 319	83.60 367	65.11 215	90.01 310	90.32 279	63.92 391	63.56 385	80.25 398	36.35 433	91.54 391	54.46 399	66.75 367	86.64 352

tpmvs		72.88 354	69.76 371	82.22 283	90.98 151	67.05 152	78.22 456	88.30 378	63.10 403	64.35 379	74.98 446	55.09 264	94.27 286	43.25 451	69.57 342	85.34 393

Syy-MVS		69.65 385	69.52 372	70.03 449	87.87 250	43.21 488	88.07 356	89.01 347	72.91 246	63.11 389	88.10 281	45.28 381	85.54 451	22.07 504	69.23 346	81.32 439

wanda-best-256-512		72.42 362	69.43 373	81.37 306	75.39 456	64.24 248	91.58 236	91.09 231	66.36 367	60.64 408	76.85 431	47.20 358	93.47 322	64.80 342	50.98 459	86.40 360

FE-blended-shiyan7		72.42 362	69.43 373	81.37 306	75.39 456	64.24 248	91.58 236	91.09 231	66.36 367	60.64 408	76.85 431	47.20 358	93.47 322	64.80 342	50.98 459	86.40 360

anonymousdsp		71.14 373	69.37 375	76.45 400	72.95 470	54.71 433	84.19 400	88.88 353	61.92 415	62.15 399	79.77 404	38.14 416	91.44 396	68.90 291	67.45 363	83.21 417

blended_shiyan6		72.26 364	69.26 376	81.27 311	75.24 460	64.00 258	91.37 248	91.06 237	66.12 371	60.34 414	76.75 434	46.82 361	93.45 325	64.61 344	50.98 459	86.37 363

blended_shiyan8		72.26 364	69.25 377	81.29 310	75.23 461	64.03 255	91.36 251	91.04 241	66.11 372	60.42 413	76.73 435	46.79 363	93.45 325	64.58 346	51.00 458	86.37 363

PS-CasMVS		69.86 384	69.13 378	72.07 441	80.35 405	50.57 455	87.02 374	89.75 307	67.27 359	59.19 422	82.28 362	46.58 368	82.24 479	50.69 414	59.02 433	83.39 415

gbinet_0.2-2-1-0.02		71.92 367	68.92 379	80.91 327	75.87 454	63.30 286	91.95 210	91.40 207	65.62 378	61.57 402	77.27 425	44.71 385	92.88 345	61.00 371	50.87 463	86.54 358

v7n		71.30 372	68.65 380	79.28 366	76.40 449	60.77 352	86.71 379	89.45 320	64.17 390	58.77 426	78.24 414	44.59 386	93.54 319	57.76 386	61.75 416	83.52 411

mvsany_test1		68.77 392	68.56 381	69.39 452	73.57 467	45.88 481	80.93 437	60.88 503	59.65 432	71.56 289	90.26 232	43.22 391	75.05 491	74.26 235	62.70 405	87.25 342

PEN-MVS		69.46 387	68.56 381	72.17 439	79.27 418	49.71 460	86.90 376	89.24 329	67.24 362	59.08 423	82.51 360	47.23 357	83.54 467	48.42 427	57.12 438	83.25 416

MIMVSNet		71.64 369	68.44 383	81.23 313	81.97 385	64.44 236	73.05 471	88.80 358	69.67 328	64.59 373	74.79 448	32.79 447	87.82 433	53.99 401	76.35 297	91.42 272

F-COLMAP		70.66 375	68.44 383	77.32 389	86.37 305	55.91 425	88.00 358	86.32 410	56.94 448	57.28 436	88.07 283	33.58 445	92.49 361	51.02 412	68.37 353	83.55 409

PVSNet_0	68.08 15	71.81 368	68.32 385	82.27 280	84.68 343	62.31 315	88.68 346	90.31 282	75.84 188	57.93 433	80.65 392	37.85 420	94.19 289	69.94 278	29.05 505	90.31 294

CL-MVSNet_self_test		69.92 382	68.09 386	75.41 406	73.25 468	55.90 426	90.05 309	89.90 302	69.96 323	61.96 401	76.54 436	51.05 315	87.64 436	49.51 421	50.59 465	82.70 426

TransMVSNet (Re)		70.07 381	67.66 387	77.31 390	80.62 401	59.13 390	91.78 222	84.94 430	65.97 373	60.08 417	80.44 394	50.78 316	91.87 380	48.84 424	45.46 478	80.94 443

usedtu_blend_shiyan5		71.06 374	67.54 388	81.62 300	75.39 456	64.75 223	85.67 387	86.47 408	56.48 451	60.64 408	76.85 431	47.20 358	93.71 314	68.18 296	50.98 459	86.40 360

tfpnnormal		70.10 380	67.36 389	78.32 376	83.45 369	60.97 348	88.85 342	92.77 136	64.85 384	60.83 407	78.53 412	43.52 390	93.48 321	31.73 493	61.70 418	80.52 448

DTE-MVSNet		68.46 396	67.33 390	71.87 443	77.94 439	49.00 465	86.16 385	88.58 368	66.36 367	58.19 428	82.21 364	46.36 369	83.87 463	44.97 448	55.17 445	82.73 423

DP-MVS		69.90 383	66.48 391	80.14 342	95.36 32	62.93 298	89.56 321	76.11 468	50.27 470	57.69 434	85.23 327	39.68 405	95.73 201	33.35 484	71.05 335	81.78 437

dmvs_testset		65.55 417	66.45 392	62.86 469	79.87 411	22.35 519	76.55 461	71.74 485	77.42 161	55.85 439	87.77 288	51.39 309	80.69 484	31.51 496	65.92 373	85.55 388

LS3D		69.17 388	66.40 393	77.50 385	91.92 123	56.12 423	85.12 391	80.37 458	46.96 478	56.50 438	87.51 293	37.25 424	93.71 314	32.52 492	79.40 264	82.68 427

mmtdpeth		68.33 397	66.37 394	74.21 423	82.81 377	51.73 445	84.34 398	80.42 457	67.01 363	71.56 289	68.58 472	30.52 460	92.35 368	75.89 219	36.21 494	78.56 468

KD-MVS_2432*1600		69.03 390	66.37 394	77.01 394	85.56 325	61.06 346	81.44 432	90.25 286	67.27 359	58.00 431	76.53 437	54.49 271	87.63 437	48.04 429	35.77 496	82.34 430

miper_refine_blended		69.03 390	66.37 394	77.01 394	85.56 325	61.06 346	81.44 432	90.25 286	67.27 359	58.00 431	76.53 437	54.49 271	87.63 437	48.04 429	35.77 496	82.34 430

Anonymous20231206		67.53 405	65.78 397	72.79 433	74.95 462	47.59 470	88.23 353	87.32 396	61.75 420	58.07 430	77.29 424	37.79 421	87.29 443	42.91 453	63.71 396	83.48 412

MSDG		69.54 386	65.73 398	80.96 324	85.11 338	63.71 270	84.19 400	83.28 448	56.95 447	54.50 443	84.03 342	31.50 453	96.03 177	42.87 455	69.13 348	83.14 419

RPMNet		70.42 378	65.68 399	84.63 194	83.15 372	67.96 118	70.25 477	90.45 270	46.83 480	69.97 309	65.10 482	56.48 248	95.30 235	35.79 477	73.13 318	90.64 290

FMVSNet5		68.04 400	65.66 400	75.18 410	84.43 353	57.89 400	83.54 406	86.26 412	61.83 417	53.64 449	73.30 451	37.15 427	85.08 455	48.99 423	61.77 415	82.56 429

XVG-ACMP-BASELINE		68.04 400	65.53 401	75.56 405	74.06 466	52.37 442	78.43 453	85.88 419	62.03 413	58.91 425	81.21 385	20.38 487	91.15 398	60.69 373	68.18 354	83.16 418

EG-PatchMatch MVS		68.55 394	65.41 402	77.96 381	78.69 429	62.93 298	89.86 315	89.17 333	60.55 425	50.27 464	77.73 420	22.60 482	94.06 297	47.18 436	72.65 323	76.88 476

PatchT		69.11 389	65.37 403	80.32 336	82.07 384	63.68 275	67.96 486	87.62 392	50.86 468	69.37 313	65.18 481	57.09 233	88.53 425	41.59 461	66.60 368	88.74 315

test_fmvs2		65.78 416	64.84 404	68.60 456	66.54 489	41.71 491	83.27 412	69.81 490	54.38 457	67.91 338	84.54 336	15.35 494	81.22 483	75.65 221	66.16 370	82.88 420

ACMH	63.93 17	68.62 393	64.81 405	80.03 346	85.22 334	63.25 288	87.72 364	84.66 432	60.83 424	51.57 458	79.43 408	27.29 469	94.96 246	41.76 459	64.84 384	81.88 435
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs6		67.57 404	64.76 406	76.00 404	72.82 472	53.37 438	88.71 345	86.78 407	53.19 460	57.58 435	78.03 417	35.33 437	92.41 364	55.56 395	54.88 447	82.21 432

our_test_3		68.29 398	64.69 407	79.11 371	78.92 424	64.85 222	88.40 351	85.06 428	60.32 428	52.68 452	76.12 441	40.81 401	89.80 417	44.25 450	55.65 443	82.67 428

ACMH+	65.35 16	67.65 403	64.55 408	76.96 396	84.59 347	57.10 414	88.08 355	80.79 455	58.59 439	53.00 451	81.09 387	26.63 471	92.95 338	46.51 438	61.69 419	80.82 444

USDC		67.43 407	64.51 409	76.19 402	77.94 439	55.29 429	78.38 454	85.00 429	73.17 238	48.36 473	80.37 395	21.23 484	92.48 362	52.15 410	64.02 394	80.81 445

Patchmatch-RL test		68.17 399	64.49 410	79.19 367	71.22 474	53.93 436	70.07 479	71.54 487	69.22 333	56.79 437	62.89 486	56.58 245	88.61 422	69.53 282	52.61 453	95.03 106

CMPMVS	48.56 21	66.77 410	64.41 411	73.84 425	70.65 478	50.31 457	77.79 458	85.73 422	45.54 483	44.76 484	82.14 365	35.39 436	90.14 411	63.18 357	74.54 307	81.07 442
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ADS-MVSNet		68.54 395	64.38 412	81.03 323	88.06 240	66.90 164	68.01 484	84.02 438	57.57 441	64.48 375	69.87 468	38.68 407	89.21 420	40.87 463	67.89 360	86.97 344

FE-MVSNET2		66.80 409	64.06 413	75.03 411	69.84 480	57.11 413	86.57 380	88.57 369	67.94 352	50.97 462	72.16 460	33.79 444	87.55 440	53.94 402	52.74 451	80.45 449

Patchmtry		67.53 405	63.93 414	78.34 375	82.12 383	64.38 240	68.72 481	84.00 439	48.23 477	59.24 420	72.41 456	57.82 227	89.27 419	46.10 441	56.68 442	81.36 438

ppachtmachnet_test		67.72 402	63.70 415	79.77 356	78.92 424	66.04 188	88.68 346	82.90 450	60.11 430	55.45 440	75.96 442	39.19 406	90.55 401	39.53 467	52.55 454	82.71 425

LTVRE_ROB	59.60 19	66.27 412	63.54 416	74.45 419	84.00 360	51.55 447	67.08 488	83.53 444	58.78 437	54.94 442	80.31 396	34.54 439	93.23 331	40.64 465	68.03 356	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
ADS-MVSNet2		66.90 408	63.44 417	77.26 391	88.06 240	60.70 358	68.01 484	75.56 472	57.57 441	64.48 375	69.87 468	38.68 407	84.10 459	40.87 463	67.89 360	86.97 344

UnsupCasMVSNet_eth		65.79 415	63.10 418	73.88 424	70.71 477	50.29 458	81.09 435	89.88 303	72.58 253	49.25 470	74.77 449	32.57 449	87.43 442	55.96 394	41.04 486	83.90 406

EU-MVSNet		64.01 424	63.01 419	67.02 463	74.40 465	38.86 500	83.27 412	86.19 414	45.11 485	54.27 444	81.15 386	36.91 430	80.01 486	48.79 426	57.02 439	82.19 433

OpenMVS_ROB	61.12 18	66.39 411	62.92 420	76.80 398	76.51 448	57.77 402	89.22 333	83.41 446	55.48 455	53.86 447	77.84 418	26.28 472	93.95 306	34.90 479	68.76 350	78.68 466

testgi		64.48 422	62.87 421	69.31 453	71.24 473	40.62 494	85.49 388	79.92 459	65.36 381	54.18 445	83.49 349	23.74 477	84.55 457	41.60 460	60.79 425	82.77 422

test20.03		63.83 425	62.65 422	67.38 462	70.58 479	39.94 496	86.57 380	84.17 436	63.29 399	51.86 456	77.30 423	37.09 428	82.47 475	38.87 471	54.13 449	79.73 455

JIA-IIPM		66.06 413	62.45 423	76.88 397	81.42 392	54.45 435	57.49 502	88.67 364	49.36 473	63.86 382	46.86 501	56.06 252	90.25 405	49.53 420	68.83 349	85.95 377

pmmvs-eth3d		65.53 418	62.32 424	75.19 409	69.39 483	59.59 381	82.80 420	83.43 445	62.52 408	51.30 460	72.49 454	32.86 446	87.16 444	55.32 396	50.73 464	78.83 464

OurMVSNet-221017-0		64.68 420	62.17 425	72.21 438	76.08 452	47.35 471	80.67 438	81.02 454	56.19 452	51.60 457	79.66 406	27.05 470	88.56 424	53.60 405	53.63 450	80.71 446

dtuonlycased		63.47 429	62.08 426	67.64 460	73.22 469	52.55 441	86.25 384	79.10 462	65.40 379	49.47 469	67.33 478	36.80 431	82.37 477	53.47 406	47.68 470	68.01 490

RPSCF		64.24 423	61.98 427	71.01 446	76.10 451	45.00 483	75.83 466	75.94 469	46.94 479	58.96 424	84.59 334	31.40 454	82.00 480	47.76 434	60.33 430	86.04 374

SixPastTwentyTwo		64.92 419	61.78 428	74.34 421	78.74 428	49.76 459	83.42 411	79.51 461	62.86 404	50.27 464	77.35 422	30.92 458	90.49 403	45.89 442	47.06 472	82.78 421

test_0402		64.54 421	61.09 429	74.92 414	84.10 359	60.75 354	87.95 359	79.71 460	52.03 462	52.41 453	77.20 426	32.21 451	91.64 386	23.14 502	61.03 422	72.36 486

Patchmatch-test		65.86 414	60.94 430	80.62 333	83.75 364	58.83 392	58.91 499	75.26 474	44.50 487	50.95 463	77.09 428	58.81 209	87.90 431	35.13 478	64.03 393	95.12 100

kuosan		60.86 440	60.24 431	62.71 470	81.57 389	46.43 478	75.70 467	85.88 419	57.98 440	48.95 471	69.53 470	58.42 215	76.53 489	28.25 498	35.87 495	65.15 495

MDA-MVSNet_test_wron		63.78 427	60.16 432	74.64 416	78.15 437	60.41 365	83.49 408	84.03 437	56.17 454	39.17 495	71.59 463	37.22 425	83.24 471	42.87 455	48.73 467	80.26 452

YYNet1		63.76 428	60.14 433	74.62 417	78.06 438	60.19 372	83.46 410	83.99 441	56.18 453	39.25 494	71.56 464	37.18 426	83.34 469	42.90 454	48.70 468	80.32 451

COLMAP_ROB	57.96 20	62.98 431	59.65 434	72.98 431	81.44 391	53.00 440	83.75 405	75.53 473	48.34 476	48.81 472	81.40 379	24.14 475	90.30 404	32.95 487	60.52 427	75.65 479
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
K. test v3		63.09 430	59.61 435	73.53 427	76.26 450	49.38 464	83.27 412	77.15 466	64.35 387	47.77 475	72.32 458	28.73 464	87.79 434	49.93 419	36.69 493	83.41 414

sc_t1		63.81 426	59.39 436	77.10 392	77.62 441	56.03 424	84.32 399	73.56 479	46.66 481	58.22 427	73.06 452	23.28 480	90.62 400	50.93 413	46.84 473	84.64 401

Anonymous20240521		62.09 432	59.08 437	71.10 445	67.19 487	48.72 466	83.91 402	85.23 427	50.38 469	47.84 474	71.22 466	20.74 485	85.51 453	46.47 439	58.75 435	79.06 460

KD-MVS_self_test		60.87 439	58.60 438	67.68 459	66.13 490	39.93 497	75.63 468	84.70 431	57.32 445	49.57 467	68.45 473	29.55 461	82.87 472	48.09 428	47.94 469	80.25 453

AllTest		61.66 434	58.06 439	72.46 435	79.57 413	51.42 449	80.17 444	68.61 492	51.25 466	45.88 478	81.23 381	19.86 489	86.58 446	38.98 469	57.01 440	79.39 457

UnsupCasMVSNet_bld		61.60 435	57.71 440	73.29 429	68.73 484	51.64 446	78.61 452	89.05 345	57.20 446	46.11 477	61.96 490	28.70 465	88.60 423	50.08 418	38.90 491	79.63 456

MDA-MVSNet-bldmvs		61.54 436	57.70 441	73.05 430	79.53 415	57.00 418	83.08 416	81.23 452	57.57 441	34.91 499	72.45 455	32.79 447	86.26 448	35.81 476	41.95 484	75.89 478

mvs5depth		61.03 438	57.65 442	71.18 444	67.16 488	47.04 476	72.74 472	77.49 464	57.47 444	60.52 411	72.53 453	22.84 481	88.38 427	49.15 422	38.94 490	78.11 471

tt0320		61.85 433	57.45 443	75.03 411	77.49 442	57.60 406	82.74 421	73.65 478	43.65 491	53.65 448	68.18 474	25.47 473	88.66 421	45.56 444	46.68 474	78.81 465

MIMVSNet1		60.16 444	57.33 444	68.67 455	69.71 481	44.13 485	78.92 451	84.21 435	55.05 456	44.63 485	71.85 461	23.91 476	81.54 482	32.63 491	55.03 446	80.35 450

test_vis1_rt		59.09 447	57.31 445	64.43 466	68.44 485	46.02 480	83.05 418	48.63 512	51.96 463	49.57 467	63.86 485	16.30 492	80.20 485	71.21 268	62.79 404	67.07 493

FE-MVSNET		60.52 441	57.18 446	70.53 447	67.53 486	50.68 454	82.62 422	76.28 467	59.33 435	46.71 476	71.10 467	30.54 459	83.61 466	33.15 486	47.37 471	77.29 475

tt0320-xc		61.51 437	56.89 447	75.37 407	78.50 432	58.61 395	82.61 423	71.27 488	44.31 488	53.17 450	68.03 476	23.38 478	88.46 426	47.77 433	43.00 483	79.03 462

PM-MVS		59.40 445	56.59 448	67.84 457	63.63 493	41.86 489	76.76 460	63.22 500	59.01 436	51.07 461	72.27 459	11.72 501	83.25 470	61.34 368	50.28 466	78.39 469

new-patchmatchnet		59.30 446	56.48 449	67.79 458	65.86 491	44.19 484	82.47 424	81.77 451	59.94 431	43.65 489	66.20 480	27.67 468	81.68 481	39.34 468	41.40 485	77.50 474

TinyColmap		60.32 442	56.42 450	72.00 442	78.78 427	53.18 439	78.36 455	75.64 471	52.30 461	41.59 493	75.82 444	14.75 497	88.35 428	35.84 475	54.71 448	74.46 480

MVS-HIRNet		60.25 443	55.55 451	74.35 420	84.37 354	56.57 421	71.64 475	74.11 476	34.44 498	45.54 482	42.24 511	31.11 457	89.81 415	40.36 466	76.10 299	76.67 477

dongtai		55.18 453	55.46 452	54.34 480	76.03 453	36.88 501	76.07 464	84.61 433	51.28 465	43.41 490	64.61 484	56.56 246	67.81 502	18.09 509	28.50 506	58.32 499

test_fmvs3		56.82 449	54.86 453	62.69 471	53.59 505	35.47 503	75.87 465	65.64 497	43.91 489	55.10 441	71.43 465	6.91 509	74.40 494	68.64 294	52.63 452	78.20 470

DSMNet-mixed		56.78 450	54.44 454	63.79 467	63.21 494	29.44 512	64.43 491	64.10 499	42.12 495	51.32 459	71.60 462	31.76 452	75.04 492	36.23 474	65.20 381	86.87 349

usedtu_dtu_shiyan2		57.76 448	53.69 455	69.95 450	57.60 503	41.80 490	83.50 407	83.67 443	45.26 484	43.79 488	62.82 487	17.63 491	85.93 449	42.56 458	46.40 476	82.12 434

LF4IMVS		54.01 454	52.12 456	59.69 472	62.41 496	39.91 498	68.59 482	68.28 494	42.96 493	44.55 486	75.18 445	14.09 499	68.39 501	41.36 462	51.68 455	70.78 487

TDRefinement		55.28 452	51.58 457	66.39 464	59.53 501	46.15 479	76.23 463	72.80 480	44.60 486	42.49 491	76.28 440	15.29 495	82.39 476	33.20 485	43.75 480	70.62 488

pmmvs3		55.51 451	51.50 458	67.53 461	57.90 502	50.93 453	80.37 440	73.66 477	40.63 496	44.15 487	64.75 483	16.30 492	78.97 488	44.77 449	40.98 488	72.69 484

ttmdpeth		53.34 455	49.96 459	63.45 468	62.07 498	40.04 495	72.06 473	65.64 497	42.54 494	51.88 455	77.79 419	13.94 500	76.48 490	32.93 488	30.82 504	73.84 481

N_pmnet		50.55 457	49.11 460	54.88 478	77.17 445	4.02 541	84.36 397	2.00 538	48.59 474	45.86 480	68.82 471	32.22 450	82.80 474	31.57 494	51.38 457	77.81 473

MVStest1		51.35 456	46.89 461	64.74 465	65.06 492	51.10 451	67.33 487	72.58 481	30.20 502	35.30 497	74.82 447	27.70 467	69.89 499	24.44 501	24.57 507	73.22 482

new_pmnet		49.31 458	46.44 462	57.93 473	62.84 495	40.74 493	68.47 483	62.96 501	36.48 497	35.09 498	57.81 496	14.97 496	72.18 496	32.86 489	46.44 475	60.88 498

mvsany_test3		48.86 459	46.35 463	56.41 474	46.00 511	31.67 508	62.26 493	47.25 513	43.71 490	45.54 482	68.15 475	10.84 502	64.44 510	57.95 385	35.44 498	73.13 483

WB-MVS		46.23 461	44.94 464	50.11 483	62.13 497	21.23 521	76.48 462	55.49 505	45.89 482	35.78 496	61.44 492	35.54 435	72.83 495	9.96 523	21.75 509	56.27 501

test_f		46.58 460	43.45 465	55.96 475	45.18 512	32.05 507	61.18 494	49.49 511	33.39 499	42.05 492	62.48 489	7.00 508	65.56 506	47.08 437	43.21 482	70.27 489

SSC-MVS		44.51 463	43.35 466	47.99 487	61.01 500	18.90 523	74.12 470	54.36 506	43.42 492	34.10 500	60.02 495	34.42 440	70.39 498	9.14 525	19.57 510	54.68 502

FPMVS		45.64 462	43.10 467	53.23 481	51.42 508	36.46 502	64.97 490	71.91 484	29.13 503	27.53 505	61.55 491	9.83 504	65.01 508	16.00 515	55.58 444	58.22 500

EGC-MVSNET		42.35 464	38.09 468	55.11 477	74.57 463	46.62 477	71.63 476	55.77 504	0.04 559	0.24 561	62.70 488	14.24 498	74.91 493	17.59 510	46.06 477	43.80 504

test_vis3_rt		40.46 467	37.79 469	48.47 486	44.49 513	33.35 506	66.56 489	32.84 520	32.39 500	29.65 501	39.13 517	3.91 517	68.65 500	50.17 416	40.99 487	43.40 505

APD_test1		40.50 466	37.31 470	50.09 484	51.88 506	35.27 504	59.45 498	52.59 508	21.64 508	26.12 506	57.80 497	4.56 513	66.56 504	22.64 503	39.09 489	48.43 503

LCM-MVSNet		40.54 465	35.79 471	54.76 479	36.92 519	30.81 509	51.41 505	69.02 491	22.07 507	24.63 507	45.37 504	4.56 513	65.81 505	33.67 483	34.50 499	67.67 491

ANet_high		40.27 468	35.20 472	55.47 476	34.74 521	34.47 505	63.84 492	71.56 486	48.42 475	18.80 511	41.08 513	9.52 505	64.45 509	20.18 505	8.66 523	67.49 492

test_method		38.59 469	35.16 473	48.89 485	54.33 504	21.35 520	45.32 510	53.71 507	7.41 522	28.74 503	51.62 499	8.70 506	52.87 513	33.73 482	32.89 500	72.47 485

PMMVS2		37.93 470	33.61 474	50.92 482	46.31 510	24.76 515	60.55 497	50.05 509	28.94 504	20.93 509	47.59 500	4.41 515	65.13 507	25.14 500	18.55 512	62.87 496

Gipuma		34.91 471	31.44 475	45.30 488	70.99 476	39.64 499	19.85 521	72.56 482	20.10 510	16.16 517	21.47 530	5.08 512	71.16 497	13.07 517	43.70 481	25.08 521
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ArgMatch-Sym		33.10 473	29.80 476	43.01 490	37.34 518	24.00 517	51.27 506	13.51 525	26.37 505	28.90 502	61.40 493	1.65 523	43.36 518	34.16 481	13.61 515	61.66 497

testf1		32.77 474	29.47 477	42.67 492	41.89 515	30.81 509	52.07 503	43.45 514	15.45 511	18.52 512	44.82 505	2.12 519	58.38 511	16.05 513	30.87 502	38.83 508

APD_test2		32.77 474	29.47 477	42.67 492	41.89 515	30.81 509	52.07 503	43.45 514	15.45 511	18.52 512	44.82 505	2.12 519	58.38 511	16.05 513	30.87 502	38.83 508

ArgMatch-SfM		33.21 472	29.25 479	45.06 489	35.86 520	22.89 518	48.07 509	16.80 524	23.93 506	27.57 504	61.10 494	1.59 524	47.14 515	34.29 480	14.08 514	65.16 494

PMVS	26.43 22	31.84 476	28.16 480	42.89 491	25.87 525	27.58 513	50.92 507	49.78 510	21.37 509	14.17 520	40.81 514	2.01 521	66.62 503	9.61 524	38.88 492	34.49 513
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
cdsmvs_eth3d_5k		19.86 482	26.47 481	0.00 543	0.00 568	0.00 571	0.00 556	93.45 104	0.00 563	0.00 564	95.27 80	49.56 331	0.00 564	0.00 563	0.00 562	0.00 559

E-PMN		24.61 477	24.00 482	26.45 497	43.74 514	18.44 524	60.86 495	39.66 516	15.11 514	9.53 528	22.10 529	6.52 510	46.94 516	8.31 526	10.14 520	13.98 526

tmp_tt		22.26 480	23.75 483	17.80 505	5.23 546	12.06 528	35.26 511	39.48 517	2.82 529	18.94 510	44.20 510	22.23 483	24.64 524	36.30 473	9.31 522	16.69 525

EMVS		23.76 479	23.20 484	25.46 500	41.52 517	16.90 525	60.56 496	38.79 519	14.62 515	8.99 530	20.24 532	7.35 507	45.82 517	7.25 529	9.46 521	13.64 528

MVE	24.84 23	24.35 478	19.77 485	38.09 494	34.56 522	26.92 514	26.57 513	38.87 518	11.73 518	11.37 524	27.44 524	1.37 525	50.42 514	11.41 522	14.60 513	36.93 510
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
VLMVS_CLIP		19.60 483	19.74 486	19.17 504	13.13 532	5.80 535	23.18 517	23.62 523	3.86 525	24.51 508	44.74 507	2.91 518	29.01 521	19.90 506	21.84 508	22.70 523

DenseAffine		21.45 481	18.65 487	29.86 496	28.31 523	16.04 526	32.25 512	6.12 528	15.38 513	16.38 516	44.57 509	0.55 528	32.44 520	16.82 511	7.46 525	41.09 506

RoMa-SfM		18.71 484	16.37 488	25.74 499	19.88 527	12.86 527	26.27 514	3.78 533	13.07 516	15.56 518	45.71 503	0.48 529	28.39 522	16.22 512	6.37 526	35.97 512

PDCNetPlus		17.19 486	15.58 489	22.00 501	25.94 524	10.36 531	23.05 518	5.04 530	12.02 517	10.87 526	39.50 516	0.88 526	23.24 525	18.38 507	4.57 531	32.39 515

LoFTR		18.06 485	15.31 490	26.33 498	21.95 526	10.94 529	21.35 519	12.80 526	6.90 523	12.24 522	41.28 512	0.46 530	27.67 523	7.81 527	12.96 516	40.38 507

DKM		16.33 487	14.55 491	21.65 502	19.49 528	10.79 530	24.23 516	2.86 535	10.86 519	13.52 521	40.31 515	0.32 535	21.73 527	14.27 516	5.12 528	32.43 514

VLMVS		13.23 490	13.55 492	12.28 511	12.68 534	2.77 545	12.60 524	3.80 532	0.44 541	17.98 514	44.70 508	4.14 516	6.39 534	12.99 518	12.66 517	27.68 517

MatchFormer		14.02 488	12.22 493	19.42 503	17.64 529	8.79 532	19.96 520	10.04 527	4.23 524	10.54 527	32.75 522	0.31 537	22.88 526	4.03 534	10.48 519	26.57 518

RoMa-HiRes		13.29 489	12.09 494	16.86 506	12.76 533	7.74 533	17.91 523	2.10 537	8.64 520	11.87 523	39.11 518	0.36 533	17.55 528	12.17 519	3.91 534	25.30 520

DKM-HiRes		12.72 491	11.70 495	15.79 508	14.70 530	7.68 534	18.04 522	1.85 542	8.12 521	11.31 525	35.19 520	0.24 543	14.23 532	12.15 520	3.71 535	25.47 519

MVS_clip		10.33 493	11.48 496	6.89 515	13.99 531	4.67 538	11.14 525	0.96 550	1.27 533	14.61 519	35.92 519	1.90 522	2.27 541	11.90 521	11.60 518	13.74 527

wuyk23d		11.30 492	10.95 497	12.33 510	48.05 509	19.89 522	25.89 515	1.92 541	3.58 526	3.12 536	1.37 559	0.64 527	15.77 530	6.23 531	7.77 524	1.35 542

ab-mvs-re		7.91 498	10.55 498	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	94.95 91	0.00 567	0.00 564	0.00 563	0.00 562	0.00 559

testmvs		7.23 499	9.62 499	0.06 542	0.04 566	0.02 570	84.98 394	0.02 568	0.03 560	0.18 562	1.21 560	0.01 566	0.02 562	0.14 547	0.01 561	0.13 558

test123		6.92 500	9.21 500	0.08 541	0.03 567	0.05 568	81.65 430	0.01 569	0.02 561	0.14 563	0.85 561	0.03 564	0.02 562	0.12 550	0.00 562	0.16 557

MASt3R-SfM		8.20 497	8.57 501	7.11 514	5.75 543	3.12 544	9.54 527	3.21 534	2.39 532	9.18 529	34.80 521	0.37 532	5.21 536	6.46 530	5.41 527	12.99 530

PMatch-SfM		8.29 496	7.44 502	10.83 512	6.92 539	3.67 542	9.75 526	1.15 544	3.49 527	6.97 531	28.70 523	0.04 560	8.89 533	7.67 528	2.24 544	19.92 524

ELoFTR		8.49 495	6.65 503	14.00 509	5.91 540	3.43 543	7.42 530	4.01 531	2.94 528	6.41 533	25.06 525	0.11 548	15.41 531	5.10 533	2.92 538	23.17 522

GLUNet-SfM		8.91 494	6.39 504	16.47 507	9.50 538	4.77 536	5.87 533	5.53 529	2.45 530	6.66 532	22.23 528	0.25 541	15.78 529	2.84 535	2.14 545	28.86 516

pcd_1.5k_mvsjas		4.46 503	5.95 505	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	53.55 285	0.00 564	0.00 563	0.00 562	0.00 559

PMatch-Up-SfM		6.11 501	5.72 506	7.28 513	5.02 547	2.48 546	7.03 532	0.71 552	2.41 531	5.37 534	23.67 526	0.03 564	5.84 535	5.77 532	1.48 555	13.50 529

ALIKED-LG		4.67 502	4.76 507	4.39 516	11.74 535	4.58 539	8.52 528	2.37 536	1.12 534	3.02 537	10.43 534	0.40 531	4.25 537	0.52 544	4.70 530	4.35 532

ALIKED-MNN		4.24 504	4.26 508	4.20 517	10.96 536	4.68 537	7.92 529	2.00 538	0.81 535	2.44 542	9.09 536	0.30 538	4.03 538	0.46 545	4.36 533	3.88 535

ALIKED-NN		4.04 505	4.13 509	3.78 518	10.26 537	4.26 540	7.33 531	1.98 540	0.76 536	2.52 539	9.08 537	0.32 535	3.67 539	0.44 546	4.45 532	3.40 539

MVS_baseline		3.15 506	3.66 510	1.62 526	2.62 562	0.05 568	0.90 555	0.14 567	0.02 561	4.44 535	18.48 533	0.16 547	0.00 564	1.30 536	4.85 529	4.80 531

XFeat-MNN		2.31 507	2.37 511	2.13 519	1.47 564	0.97 559	3.08 539	1.31 543	0.53 538	2.60 538	7.72 538	0.22 545	2.31 540	1.02 538	3.40 536	3.10 540

SP-DiffGlue		2.24 508	2.34 512	1.94 523	1.88 563	1.08 553	3.10 538	1.13 545	0.55 537	2.52 539	7.60 539	0.33 534	0.99 547	1.25 537	2.70 539	3.76 537

SP-LightGlue		2.23 509	2.31 513	1.99 520	5.90 541	1.01 555	4.31 534	1.04 547	0.50 539	1.20 544	4.36 541	0.28 539	1.06 544	0.64 540	2.57 540	3.91 533

SP-SuperGlue		2.21 510	2.29 514	1.97 521	5.76 542	1.01 555	4.31 534	1.06 546	0.50 539	1.22 543	4.35 542	0.28 539	1.04 546	0.64 540	2.52 541	3.86 536

SP-MNN		2.16 511	2.22 515	1.97 521	5.52 544	0.92 560	4.28 536	1.01 548	0.41 543	1.13 545	4.35 542	0.23 544	1.09 543	0.61 542	2.45 542	3.91 533

SP-NN		2.08 512	2.16 516	1.87 524	5.30 545	0.91 561	4.18 537	0.96 550	0.43 542	1.09 546	4.20 544	0.25 541	1.06 544	0.60 543	2.38 543	3.63 538

XFeat-NN		1.98 513	2.09 517	1.67 525	1.35 565	0.77 564	2.62 540	0.97 549	0.41 543	2.46 541	6.79 540	0.19 546	1.75 542	0.84 539	3.18 537	2.48 541

SIFT-NN		1.43 514	1.51 518	1.19 527	4.60 548	1.57 547	2.30 541	0.51 553	0.34 545	0.74 547	2.84 545	0.08 549	0.84 548	0.13 548	2.07 546	1.15 543

SIFT-MNN		1.35 515	1.42 519	1.14 528	4.26 549	1.44 548	2.10 542	0.51 553	0.34 545	0.64 548	2.76 546	0.07 550	0.83 549	0.13 548	1.98 548	1.15 543

SIFT-NN-NCMNet		1.29 516	1.36 520	1.08 529	3.95 551	1.39 549	2.05 543	0.49 555	0.33 547	0.63 550	2.62 549	0.07 550	0.81 550	0.12 550	2.02 547	1.05 547

SIFT-NCM-Cal		1.23 517	1.30 521	1.04 530	4.06 550	1.29 550	1.92 545	0.42 556	0.33 547	0.45 555	2.46 552	0.06 555	0.81 550	0.10 557	1.89 549	1.02 549

SIFT-NN-CMatch		1.18 518	1.24 522	1.01 531	3.44 555	1.19 552	1.78 546	0.42 556	0.33 547	0.64 548	2.63 547	0.07 550	0.77 552	0.12 550	1.73 551	1.08 545

SIFT-NN-UMatch		1.16 519	1.23 523	0.96 532	3.23 557	1.06 554	1.93 544	0.42 556	0.33 547	0.53 552	2.63 547	0.07 550	0.77 552	0.11 553	1.79 550	1.05 547

SIFT-ConvMatch		1.15 520	1.22 524	0.96 532	3.82 552	1.20 551	1.64 549	0.38 559	0.33 547	0.52 553	2.53 550	0.06 555	0.76 554	0.11 553	1.59 553	0.91 550

SIFT-UMatch		1.11 521	1.18 525	0.87 535	3.66 553	1.00 558	1.70 547	0.35 561	0.32 552	0.46 554	2.50 551	0.06 555	0.75 555	0.11 553	1.51 554	0.87 552

SIFT-NN-PointCN		1.06 522	1.12 526	0.88 534	2.98 558	0.84 563	1.67 548	0.37 560	0.30 555	0.54 551	2.38 553	0.07 550	0.72 556	0.11 553	1.64 552	1.07 546

SIFT-CM-Cal		1.03 523	1.10 527	0.85 536	3.54 554	1.01 555	1.42 551	0.32 562	0.32 552	0.43 556	2.30 555	0.06 555	0.71 557	0.09 559	1.37 556	0.82 553

SIFT-UM-Cal		1.01 524	1.09 528	0.77 537	3.43 556	0.85 562	1.49 550	0.29 564	0.31 554	0.42 557	2.34 554	0.06 555	0.69 558	0.10 557	1.37 556	0.77 555

SIFT-PointCN		0.88 525	0.94 529	0.69 539	2.88 560	0.61 565	1.32 552	0.30 563	0.28 556	0.36 558	1.93 557	0.04 560	0.62 559	0.09 559	1.26 558	0.82 553

SIFT-PCN-Cal		0.88 525	0.93 530	0.70 538	2.93 559	0.60 566	1.22 553	0.27 565	0.28 556	0.36 558	2.00 556	0.04 560	0.61 560	0.09 559	1.23 559	0.89 551

SIFT-NCMNet		0.73 527	0.80 531	0.54 540	2.66 561	0.54 567	1.00 554	0.16 566	0.28 556	0.32 560	1.65 558	0.04 560	0.51 561	0.07 562	0.98 560	0.58 556

mmdepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 562	0.00 559

monomultidepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 562	0.00 559

test_blank		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 562	0.00 559

uanet_test		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 562	0.00 559

DCPMVS		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 562	0.00 559

sosnet-low-res		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 562	0.00 559

sosnet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 562	0.00 559

uncertanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 562	0.00 559

Regformer		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 562	0.00 559

uanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 562	0.00 559

Meshroom													0.00 564
: In preparation.
AliceVision / Meshro													0.00 564
: In preparation.
AliceVision_Meshroom													0.00 564
: In preparation.
PatchmatchNet2					0.00 568	56.61 420	85.20 390	78.52 463	49.54 472
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														31.49 497	51.52 456	77.88 472
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													82.83 473
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					95.84 31	67.84 122		94.64 48		89.45 44		71.94 44	98.96 19	91.55 46	94.82 26

aaatest				87.42 50	94.76 37	67.28 141	94.47 66	94.87 35	73.09 243	91.27 25	96.95 20		98.98 17	91.55 46	94.28 39	95.99 51

TestfortrainingZip				90.29 2	97.24 8	73.67 11	94.47 66	95.75 11	69.78 327	95.97 1	98.23 1	80.55 5	99.42 1		93.26 58	97.76 2

WAC-MVS						49.45 462								31.56 495

FOURS1					93.95 53	61.77 328	93.96 93	91.92 178	62.14 412	86.57 67

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

PC_three_1452									80.91 69	94.07 3	96.83 32	83.57 4	99.12 6	95.70 10	97.42 4	97.55 5

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_one_0601					96.32 20	69.74 57		94.18 72	71.42 297	90.67 30	96.85 30	74.45 24

eth-test2					0.00 568

eth-test					0.00 568

ZD-MVS					96.63 10	65.50 205		93.50 102	70.74 312	85.26 85	95.19 86	64.92 101	97.29 92	87.51 80	93.01 61

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

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

test_241102_TWO								94.41 63	71.65 286	92.07 13	97.21 12	74.58 22	99.11 7	92.34 38	95.36 14	96.59 22

test_241102_ONE					96.45 13	69.38 67		94.44 58	71.65 286	92.11 11	97.05 15	76.79 10	99.11 7

save fliter					93.84 56	67.89 121	95.05 43	92.66 143	78.19 139

test_0728_THIRD									72.48 255	90.55 31	96.93 22	76.24 13	99.08 12	91.53 50	94.99 18	96.43 34

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

test0726					96.40 16	69.99 45	96.76 8	94.33 69	71.92 272	91.89 16	97.11 14	73.77 27

GSMVS																94.68 131

test_part2					96.29 21	68.16 114				90.78 28

sam_mvs1												57.85 226				94.68 131

sam_mvs												54.91 266

ambc				69.61 451	61.38 499	41.35 492	49.07 508	85.86 421		50.18 466	66.40 479	10.16 503	88.14 430	45.73 443	44.20 479	79.32 459

MTGPA								92.23 159

test_post1							78.95 450				20.70 531	53.05 290	91.50 395	60.43 374

test_post											23.01 527	56.49 247	92.67 354

patchmatchnet-post											67.62 477	57.62 229	90.25 405

GG-mvs-BLEND				86.53 99	91.91 125	69.67 60	75.02 469	94.75 42		78.67 186	90.85 219	77.91 8	94.56 271	72.25 255	93.74 49	95.36 80

MTMP							93.77 109	32.52 521

gm-plane-assit					88.42 226	67.04 153			78.62 132		91.83 189		97.37 86	76.57 213

test9_res														89.41 62	94.96 19	95.29 87

TEST9					94.18 48	67.28 141	94.16 80	93.51 100	71.75 283	85.52 80	95.33 74	68.01 65	97.27 97

test_8					94.19 47	67.19 146	94.15 82	93.42 107	71.87 277	85.38 83	95.35 73	68.19 63	96.95 124

agg_prior2														86.41 96	94.75 32	95.33 82

agg_prior					94.16 50	66.97 162		93.31 110		84.49 91			96.75 136

TestCases				72.46 435	79.57 413	51.42 449		68.61 492	51.25 466	45.88 478	81.23 381	19.86 489	86.58 446	38.98 469	57.01 440	79.39 457

test_prior4						67.18 148	93.92 97

test_prior2							95.10 41		75.40 196	85.25 86	95.61 65	67.94 66		87.47 82	94.77 28

test_prior				86.42 105	94.71 42	67.35 140		93.10 122					96.84 133			95.05 104

旧先验2							92.00 207		59.37 434	87.54 59			93.47 322	75.39 223

新几何2							91.41 241

新几何1				84.73 183	92.32 104	64.28 245		91.46 205	59.56 433	79.77 161	92.90 149	56.95 239	96.57 143	63.40 353	92.91 63	93.34 209

旧先验1					91.94 121	60.74 355		91.50 203			94.36 109	65.23 96			91.84 82	94.55 140

无先验							92.71 160	92.61 148	62.03 413				97.01 114	66.63 318		93.97 184

原ACMM2							92.01 204

原ACMM1				84.42 201	93.21 76	64.27 246		93.40 109	65.39 380	79.51 166	92.50 158	58.11 220	96.69 138	65.27 339	93.96 44	92.32 247

test222					89.77 175	61.60 334	89.55 322	89.42 322	56.83 449	77.28 203	92.43 162	52.76 293			91.14 99	93.09 219

testdata2													96.09 171	61.26 369

segment_acmp												65.94 87

testdata				81.34 309	89.02 199	57.72 403		89.84 304	58.65 438	85.32 84	94.09 125	57.03 234	93.28 328	69.34 284	90.56 105	93.03 222

testdata1							89.21 334		77.55 157

test12				87.09 62	94.60 43	68.86 87		92.91 131		82.67 115		65.44 93	97.55 75		93.69 52	94.84 116

plane_prior7					86.94 284	61.51 336

plane_prior6					87.23 267	62.32 313						50.66 317

plane_prior5								91.31 211					95.55 221	76.74 209	78.53 276	88.39 322

plane_prior4											89.14 262

plane_prior3						61.95 323			79.09 121	72.53 271

plane_prior2							93.13 138		78.81 128

plane_prior1					87.15 272

plane_prior						62.42 310	93.85 101		79.38 113						78.80 273

n2								0.00 570

nn								0.00 570

door-mid								66.01 496

lessismore_v0				73.72 426	72.93 471	47.83 469		61.72 502		45.86 480	73.76 450	28.63 466	89.81 415	47.75 435	31.37 501	83.53 410

LGP-MVS_train				79.56 362	84.31 355	59.37 385		89.73 310	69.49 329	64.86 370	88.42 272	38.65 409	94.30 284	72.56 251	72.76 321	85.01 396

test11								93.01 125

door								66.57 495

HQP5-MVS						63.66 276

HQP-NCC					87.54 259		94.06 85		79.80 95	74.18 243

ACMP_Plane					87.54 259		94.06 85		79.80 95	74.18 243

BP-MVS														77.63 206

HQP4-MVS										74.18 243			95.61 215			88.63 316

HQP3-MVS								91.70 195							78.90 271

HQP2-MVS												51.63 305

NP-MVS					87.41 262	63.04 294					90.30 230

MDTV_nov1_ep13_2view						59.90 377	80.13 445		67.65 356	72.79 265		54.33 276		59.83 378		92.58 238

ACMMP++_ref															71.63 329

ACMMP++															69.72 340

Test By Simon												54.21 279

ITE_SJBPF				70.43 448	74.44 464	47.06 475		77.32 465	60.16 429	54.04 446	83.53 347	23.30 479	84.01 461	43.07 452	61.58 420	80.21 454

DeepMVS_CX				34.71 495	51.45 507	24.73 516		28.48 522	31.46 501	17.49 515	52.75 498	5.80 511	42.60 519	18.18 508	19.42 511	36.81 511

High-resolution multi-view benchmark