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.

DP-MVS Recon		91.72 111	90.85 122	94.34 41	99.50 1	85.00 84	98.51 49	95.96 176	80.57 324	88.08 186	97.63 100	76.84 149	99.89 11	85.67 228	94.88 144	98.13 94

TestfortrainingZip				97.22 3	99.48 2	91.93 7	98.35 57	97.26 24	85.61 187	99.54 1	99.26 1	91.36 5	99.98 2		96.55 116	99.73 3

MCST-MVS		96.17 3	96.12 6	96.32 8	99.42 3	89.36 11	98.94 31	97.10 37	95.17 4	92.11 109	98.46 40	87.33 27	99.97 3	97.21 47	99.31 4	99.63 8

MG-MVS		94.25 37	93.72 49	95.85 13	99.38 4	89.35 12	97.98 81	98.09 9	89.99 69	92.34 103	96.97 135	81.30 75	98.99 129	88.54 196	98.88 20	99.20 26

AdaColmap		88.81 203	87.61 215	92.39 148	99.33 5	79.95 248	96.70 201	95.58 203	77.51 381	83.05 275	96.69 148	61.90 353	99.72 59	84.29 238	93.47 170	97.50 161

CNVR-MVS		96.30 1	96.54 1	95.55 16	99.31 6	87.69 25	99.06 23	97.12 35	94.66 10	96.79 30	98.78 15	86.42 32	99.95 6	97.59 40	99.18 7	99.00 34

NCCC		95.63 7	95.94 9	94.69 33	99.21 7	85.15 78	99.16 11	96.96 50	94.11 15	95.59 50	98.64 25	85.07 39	99.91 8	95.61 65	99.10 9	99.00 34

OPU-MVS				97.30 2	99.19 8	92.31 3	99.12 16				98.54 30	92.06 3	99.84 19	99.11 5	99.37 1	99.74 1

aaEdge-Enhanced		94.82 21	95.04 23	94.17 52	99.17 9	83.70 110	97.66 106	97.22 25	85.79 183	95.34 53	98.90 6	84.89 40	99.86 15	97.78 36	98.60 36	98.94 39

ZD-MVS					99.09 10	83.22 123		96.60 102	82.88 281	93.61 84	98.06 72	82.93 65	99.14 119	95.51 68	98.49 43

aaatest				94.20 51	99.06 11	83.70 110	98.35 57	97.14 31	87.45 124	97.03 27	98.90 6		99.96 4	97.78 36	98.60 36	98.94 39

MED-MVS		95.59 9	96.05 8	94.21 48	99.06 11	83.70 110	98.35 57	97.14 31	87.65 118	97.03 27	98.83 10	89.87 13	99.96 4	97.78 36	98.71 31	98.97 37

TestfortrainingZip a		94.24 38	94.19 43	94.40 40	99.06 11	84.33 96	98.35 57	96.81 67	87.65 118	95.97 46	98.83 10	84.06 53	99.89 11	91.98 127	95.03 143	98.97 37

DVP-MVS++		96.05 4	96.41 3	94.96 25	99.05 14	85.34 67	98.13 71	96.77 74	88.38 93	97.70 14	98.77 16	92.06 3	99.84 19	97.47 41	99.37 1	99.70 4

MSC_two_6792asdad				97.14 4	99.05 14	92.19 4		96.83 63					99.81 29	98.08 26	98.81 24	99.43 12

No_MVS				97.14 4	99.05 14	92.19 4		96.83 63					99.81 29	98.08 26	98.81 24	99.43 12

DVP-MVS		95.58 10	95.91 10	94.57 36	99.05 14	85.18 73	99.06 23	96.46 123	88.75 83	96.69 31	98.76 18	87.69 25	99.76 46	97.90 30	98.85 21	98.77 48
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
test0726					99.05 14	85.18 73	99.11 19	96.78 68	88.75 83	97.65 18	98.91 3	87.69 25

test_0728_SECOND				95.14 21	99.04 19	86.14 44	99.06 23	96.77 74					99.84 19	97.90 30	98.85 21	99.45 11

SED-MVS		95.88 5	96.22 4	94.87 26	99.03 20	85.03 82	99.12 16	96.78 68	88.72 85	97.79 11	98.91 3	88.48 19	99.82 25	98.15 22	98.97 17	99.74 1

IU-MVS					99.03 20	85.34 67		96.86 61	92.05 42	98.74 2				98.15 22	98.97 17	99.42 14

test_241102_ONE					99.03 20	85.03 82		96.78 68	88.72 85	97.79 11	98.90 6	88.48 19	99.82 25

test-260524					99.01 23	85.87 51		96.82 66		95.25 55		86.23 34	99.92 7	97.87 33	98.71 31

test_one_0601					98.91 24	84.56 93		96.70 85	88.06 103	96.57 36	98.77 16	88.04 23

test_part2					98.90 25	85.14 79				96.07 43

PAPR		92.74 73	92.17 94	94.45 38	98.89 26	84.87 88	97.20 145	96.20 155	87.73 113	88.40 176	98.12 64	78.71 111	99.76 46	87.99 203	96.28 120	98.74 50

DeepC-MVS_fast	89.06 2	94.48 31	94.30 40	95.02 23	98.86 27	85.68 57	98.06 77	96.64 96	93.64 21	91.74 116	98.54 30	80.17 88	99.90 9	92.28 119	98.75 29	99.49 9
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		94.56 28	94.75 27	93.96 58	98.84 28	83.40 119	98.04 79	96.41 129	85.79 183	95.00 63	98.28 54	84.32 50	99.18 116	97.35 44	98.77 28	99.28 22
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPE-MVS		95.32 12	95.55 14	94.64 34	98.79 29	84.87 88	97.77 97	96.74 79	86.11 169	96.54 37	98.89 9	88.39 21	99.74 54	97.67 39	99.05 12	99.31 21
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APD-MVS		93.61 50	93.59 54	93.69 73	98.76 30	83.26 122	97.21 143	96.09 163	82.41 292	94.65 70	98.21 56	81.96 72	98.81 141	94.65 80	98.36 51	99.01 33
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HFP-MVS		92.89 67	92.86 74	92.98 109	98.71 31	81.12 195	97.58 113	96.70 85	85.20 201	91.75 115	97.97 79	78.47 115	99.71 62	90.95 139	98.41 47	98.12 95

region2R		92.72 76	92.70 76	92.79 120	98.68 32	80.53 228	97.53 118	96.51 116	85.22 199	91.94 113	97.98 77	77.26 137	99.67 70	90.83 146	98.37 50	98.18 88

test_prior				93.09 104	98.68 32	81.91 166		96.40 131					99.06 126			98.29 80

ACMMPR		92.69 81	92.67 77	92.75 122	98.66 34	80.57 222	97.58 113	96.69 87	85.20 201	91.57 117	97.92 80	77.01 146	99.67 70	90.95 139	98.41 47	98.00 107

API-MVS		90.18 162	88.97 179	93.80 62	98.66 34	82.95 129	97.50 122	95.63 202	75.16 406	86.31 221	97.69 92	72.49 237	99.90 9	81.26 277	96.07 127	98.56 62

CDPH-MVS		93.12 60	92.91 71	93.74 66	98.65 36	83.88 103	97.67 105	96.26 149	83.00 278	93.22 88	98.24 55	81.31 74	99.21 109	89.12 180	98.74 30	98.14 92

TEST9					98.64 37	83.71 108	97.82 92	96.65 93	84.29 238	95.16 57	98.09 67	84.39 46	99.36 99

train_agg		94.28 35	94.45 35	93.74 66	98.64 37	83.71 108	97.82 92	96.65 93	84.50 228	95.16 57	98.09 67	84.33 47	99.36 99	95.91 61	98.96 19	98.16 90

test_8					98.63 39	83.64 114	97.81 94	96.63 98	84.50 228	95.10 60	98.11 65	84.33 47	99.23 107

HPM-MVS++		95.32 12	95.48 16	94.85 27	98.62 40	86.04 45	97.81 94	96.93 54	92.45 31	95.69 48	98.50 35	85.38 37	99.85 17	94.75 78	99.18 7	98.65 58

agg_prior					98.59 41	83.13 125		96.56 108		94.19 75			99.16 118

CSCG		92.02 101	91.65 104	93.12 102	98.53 42	80.59 219	97.47 123	97.18 29	77.06 389	84.64 246	97.98 77	83.98 55	99.52 87	90.72 148	97.33 85	99.23 25

XVS		92.69 81	92.71 75	92.63 131	98.52 43	80.29 234	97.37 134	96.44 125	87.04 144	91.38 119	97.83 88	77.24 139	99.59 78	90.46 154	98.07 58	98.02 101

X-MVStestdata		86.26 267	84.14 288	92.63 131	98.52 43	80.29 234	97.37 134	96.44 125	87.04 144	91.38 119	20.73 537	77.24 139	99.59 78	90.46 154	98.07 58	98.02 101

FOURS1					98.51 45	78.01 319	98.13 71	96.21 154	83.04 275	94.39 73

CP-MVS		92.54 87	92.60 79	92.34 151	98.50 46	79.90 250	98.40 55	96.40 131	84.75 216	90.48 137	98.09 67	77.40 135	99.21 109	91.15 136	98.23 56	97.92 114

PAPM_NR		91.46 118	90.82 123	93.37 92	98.50 46	81.81 174	95.03 325	96.13 160	84.65 221	86.10 225	97.65 98	79.24 101	99.75 51	83.20 256	96.88 104	98.56 62

MAR-MVS		90.63 144	90.22 141	91.86 189	98.47 48	78.20 315	97.18 147	96.61 99	83.87 252	88.18 183	98.18 58	68.71 289	99.75 51	83.66 250	97.15 92	97.63 144
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
patch_mono-2		95.14 14	96.08 7	92.33 153	98.44 49	77.84 327	98.43 52	97.21 26	92.58 29	97.68 16	97.65 98	86.88 29	99.83 23	98.25 18	97.60 74	99.33 19

mPP-MVS		91.88 107	91.82 100	92.07 174	98.38 50	78.63 296	97.29 140	96.09 163	85.12 207	88.45 175	97.66 94	75.53 183	99.68 68	89.83 166	98.02 61	97.88 116

SR-MVS		92.16 98	92.27 89	91.83 196	98.37 51	78.41 303	96.67 203	95.76 193	82.19 296	91.97 111	98.07 71	76.44 158	98.64 145	93.71 93	97.27 87	98.45 68

test12				94.25 45	98.34 52	85.55 63		96.35 141		92.36 102		80.84 78	99.22 108		98.31 53	97.98 109

CPTT-MVS		89.72 174	89.87 159	89.29 293	98.33 53	73.30 395	97.70 103	95.35 224	75.68 401	87.40 195	97.44 110	70.43 273	98.25 171	89.56 175	96.90 102	96.33 243

MSP-MVS		95.62 8	96.54 1	92.86 115	98.31 54	80.10 245	97.42 130	96.78 68	92.20 37	97.11 24	98.29 53	93.46 1	99.10 123	96.01 58	99.30 5	99.38 15
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
MSLP-MVS++		94.28 35	94.39 37	93.97 57	98.30 55	84.06 102	98.64 44	96.93 54	90.71 58	93.08 91	98.70 23	79.98 92	99.21 109	94.12 87	99.07 11	98.63 59

PGM-MVS		91.93 104	91.80 101	92.32 155	98.27 56	79.74 257	95.28 305	97.27 22	83.83 255	90.89 131	97.78 90	76.12 169	99.56 84	88.82 189	97.93 65	97.66 140

ZNCC-MVS		92.75 72	92.60 79	93.23 96	98.24 57	81.82 173	97.63 107	96.50 118	85.00 212	91.05 127	97.74 91	78.38 116	99.80 33	90.48 152	98.34 52	98.07 98

save fliter					98.24 57	83.34 120	98.61 46	96.57 106	91.32 48

114514_t		88.79 205	87.57 217	92.45 142	98.21 59	81.74 176	96.99 167	95.45 214	75.16 406	82.48 279	95.69 172	68.59 290	98.50 155	80.33 282	95.18 141	97.10 201

GST-MVS		92.43 92	92.22 93	93.04 106	98.17 60	81.64 181	97.40 132	96.38 135	84.71 219	90.90 130	97.40 112	77.55 133	99.76 46	89.75 170	97.74 70	97.72 134

DP-MVS		81.47 355	78.28 374	91.04 236	98.14 61	78.48 299	95.09 324	86.97 468	61.14 480	71.12 411	92.78 288	59.59 364	99.38 96	53.11 472	86.61 280	95.27 280

MP-MVS		92.61 85	92.67 77	92.42 146	98.13 62	79.73 258	97.33 137	96.20 155	85.63 186	90.53 134	97.66 94	78.14 122	99.70 65	92.12 123	98.30 54	97.85 121
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
9.14			94.26 42		98.10 63		98.14 68	96.52 115	84.74 217	94.83 67	98.80 13	82.80 67	99.37 98	95.95 60	98.42 46

PHI-MVS		93.59 51	93.63 52	93.48 87	98.05 64	81.76 175	98.64 44	97.13 33	82.60 288	94.09 77	98.49 36	80.35 83	99.85 17	94.74 79	98.62 35	98.83 45

SMA-MVS		94.70 24	94.68 30	94.76 30	98.02 65	85.94 49	97.47 123	96.77 74	85.32 196	97.92 6	98.70 23	83.09 64	99.84 19	95.79 62	99.08 10	98.49 65
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
PLC	83.97 7	88.00 229	87.38 223	89.83 283	98.02 65	76.46 357	97.16 151	94.43 288	79.26 360	81.98 289	96.28 155	69.36 282	99.27 103	77.71 317	92.25 192	93.77 314
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MTAPA		92.45 90	92.31 88	92.86 115	97.90 67	80.85 212	92.88 387	96.33 142	87.92 107	90.20 142	98.18 58	76.71 154	99.76 46	92.57 116	98.09 57	97.96 113

APD-MVS_3200maxsize		91.23 126	91.35 109	90.89 245	97.89 68	76.35 361	96.30 234	95.52 208	79.82 347	91.03 128	97.88 85	74.70 203	98.54 153	92.11 124	96.89 103	97.77 129

HPM-MVS		91.62 115	91.53 107	91.89 187	97.88 69	79.22 272	96.99 167	95.73 196	82.07 298	89.50 155	97.19 124	75.59 181	98.93 136	90.91 141	97.94 63	97.54 153
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SD-MVS		94.84 20	95.02 25	94.29 43	97.87 70	84.61 91	97.76 99	96.19 157	89.59 75	96.66 33	98.17 61	84.33 47	99.60 77	96.09 57	98.50 42	98.66 57
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
NormalMVS		92.88 68	92.97 70	92.59 135	97.80 71	82.02 157	97.94 84	94.70 258	92.34 33	92.15 107	96.53 151	77.03 144	98.57 149	91.13 137	97.12 94	97.19 195

lecture		93.17 58	93.57 56	91.96 183	97.80 71	78.79 292	98.50 50	96.98 46	86.61 159	94.75 69	98.16 62	78.36 118	99.35 101	93.89 89	97.12 94	97.75 131

dcpmvs_2		93.10 61	93.46 60	92.02 181	97.77 73	79.73 258	94.82 331	93.86 338	86.91 147	91.33 122	96.76 144	85.20 38	98.06 179	96.90 52	97.60 74	98.27 82

原ACMM1				91.22 231	97.77 73	78.10 317		96.61 99	81.05 313	91.28 124	97.42 111	77.92 126	98.98 130	79.85 291	98.51 40	96.59 234

SR-MVS-dyc-post		91.29 124	91.45 108	90.80 247	97.76 75	76.03 366	96.20 244	95.44 215	80.56 325	90.72 132	97.84 86	75.76 177	98.61 146	91.99 125	96.79 109	97.75 131

RE-MVS-def			91.18 116		97.76 75	76.03 366	96.20 244	95.44 215	80.56 325	90.72 132	97.84 86	73.36 224		91.99 125	96.79 109	97.75 131

TSAR-MVS + MP.		94.79 23	95.17 22	93.64 76	97.66 77	84.10 101	95.85 280	96.42 128	91.26 49	97.49 21	96.80 143	86.50 31	98.49 156	95.54 67	99.03 13	98.33 74
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MGCNet		95.58 10	95.44 17	96.01 11	97.63 78	89.26 13	99.27 5	96.59 103	94.71 9	97.08 25	97.99 74	78.69 112	99.86 15	99.15 3	97.85 66	98.91 42

HPM-MVS_fast		90.38 157	90.17 144	91.03 237	97.61 79	77.35 342	97.15 153	95.48 211	79.51 353	88.79 168	96.90 136	71.64 257	98.81 141	87.01 218	97.44 79	96.94 214

EI-MVSNet-Vis-set		91.84 108	91.77 102	92.04 180	97.60 80	81.17 193	96.61 204	96.87 59	88.20 100	89.19 159	97.55 106	78.69 112	99.14 119	90.29 161	90.94 213	95.80 256

CNLPA		86.96 252	85.37 262	91.72 203	97.59 81	79.34 269	97.21 143	91.05 434	74.22 413	78.90 321	96.75 146	67.21 304	98.95 133	74.68 356	90.77 216	96.88 220

ACMMP		90.39 155	89.97 153	91.64 206	97.58 82	78.21 314	96.78 192	96.72 83	84.73 218	84.72 243	97.23 122	71.22 261	99.63 74	88.37 201	92.41 188	97.08 206
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
SF-MVS		94.17 39	94.05 46	94.55 37	97.56 83	85.95 47	97.73 101	96.43 127	84.02 245	95.07 62	98.74 20	82.93 65	99.38 96	95.42 69	98.51 40	98.32 76

CANet		94.89 18	94.64 31	95.63 14	97.55 84	88.12 19	99.06 23	96.39 133	94.07 17	95.34 53	97.80 89	76.83 151	99.87 13	97.08 50	97.64 73	98.89 43

PVSNet_BlendedMVS		90.05 164	89.96 154	90.33 264	97.47 85	83.86 104	98.02 80	96.73 81	87.98 105	89.53 153	89.61 340	76.42 159	99.57 82	94.29 84	79.59 336	87.57 420

PVSNet_Blended		93.13 59	92.98 69	93.57 81	97.47 85	83.86 104	99.32 3	96.73 81	91.02 55	89.53 153	96.21 156	76.42 159	99.57 82	94.29 84	95.81 135	97.29 186

reproduce-ours		92.70 79	93.02 67	91.75 198	97.45 87	77.77 331	96.16 247	95.94 180	84.12 241	92.45 98	98.43 42	80.06 90	99.24 105	95.35 70	97.18 90	98.24 84

our_new_method		92.70 79	93.02 67	91.75 198	97.45 87	77.77 331	96.16 247	95.94 180	84.12 241	92.45 98	98.43 42	80.06 90	99.24 105	95.35 70	97.18 90	98.24 84

新几何1				93.12 102	97.44 89	81.60 184		96.71 84	74.54 412	91.22 125	97.57 102	79.13 103	99.51 89	77.40 324	98.46 44	98.26 83

LS3D		82.22 345	79.94 360	89.06 297	97.43 90	74.06 390	93.20 381	92.05 412	61.90 474	73.33 389	95.21 202	59.35 367	99.21 109	54.54 468	92.48 184	93.90 312

reproduce_model		92.53 88	92.87 72	91.50 214	97.41 91	77.14 348	96.02 257	95.91 183	83.65 263	92.45 98	98.39 46	79.75 95	99.21 109	95.27 73	96.98 99	98.14 92

test_yl		91.46 118	90.53 129	94.24 46	97.41 91	85.18 73	98.08 74	97.72 11	80.94 314	89.85 144	96.14 157	75.61 179	98.81 141	90.42 157	88.56 253	98.74 50

DCV-MVSNet		91.46 118	90.53 129	94.24 46	97.41 91	85.18 73	98.08 74	97.72 11	80.94 314	89.85 144	96.14 157	75.61 179	98.81 141	90.42 157	88.56 253	98.74 50

EI-MVSNet-UG-set		91.35 123	91.22 112	91.73 201	97.39 94	80.68 216	96.47 216	96.83 63	87.92 107	88.30 180	97.36 113	77.84 127	99.13 121	89.43 178	89.45 229	95.37 275

旧先验1					97.39 94	79.58 263		96.54 112			98.08 70	84.00 54			97.42 81	97.62 146

TSAR-MVS + GP.		94.35 34	94.50 33	93.89 59	97.38 96	83.04 127	98.10 73	95.29 229	91.57 45	93.81 80	97.45 107	86.64 30	99.43 94	96.28 56	94.01 157	99.20 26

MVS_111021_HR		93.41 56	93.39 61	93.47 89	97.34 97	82.83 132	97.56 115	98.27 6	89.16 81	89.71 147	97.14 125	79.77 94	99.56 84	93.65 94	97.94 63	98.02 101

MP-MVS-pluss		92.58 86	92.35 85	93.29 93	97.30 98	82.53 138	96.44 219	96.04 169	84.68 220	89.12 161	98.37 49	77.48 134	99.74 54	93.31 101	98.38 49	97.59 149
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
EPNet		94.06 43	94.15 44	93.76 64	97.27 99	84.35 95	98.29 63	97.64 14	94.57 11	95.36 52	96.88 138	79.96 93	99.12 122	91.30 133	96.11 126	97.82 125
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		93.46 55	93.23 64	94.17 52	97.16 100	84.28 99	96.82 187	96.65 93	86.24 166	94.27 74	97.99 74	77.94 124	99.83 23	93.39 96	98.57 38	98.39 72

LFMVS		89.27 189	87.64 212	94.16 55	97.16 100	85.52 64	97.18 147	94.66 266	79.17 361	89.63 150	96.57 149	55.35 409	98.22 172	89.52 177	89.54 228	98.74 50

DeepPCF-MVS	89.82 1	94.61 25	96.17 5	89.91 280	97.09 102	70.21 431	98.99 29	96.69 87	95.57 2	95.08 61	99.23 2	86.40 33	99.87 13	97.84 34	98.66 34	99.65 7

VNet		92.11 100	91.22 112	94.79 29	96.91 103	86.98 32	97.91 87	97.96 10	86.38 163	93.65 82	95.74 167	70.16 276	98.95 133	93.39 96	88.87 242	98.43 70

TAPA-MVS	81.61 12	85.02 295	83.67 294	89.06 297	96.79 104	73.27 398	95.92 264	94.79 255	74.81 409	80.47 305	96.83 140	71.07 263	98.19 174	49.82 482	92.57 181	95.71 263
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Anonymous202405211		84.41 308	81.93 329	91.85 191	96.78 105	78.41 303	97.44 126	91.34 428	70.29 446	84.06 254	94.26 248	41.09 469	98.96 131	79.46 293	82.65 319	98.17 89

reproduce_monomvs		87.80 234	87.60 216	88.40 312	96.56 106	80.26 237	95.80 283	96.32 144	91.56 46	73.60 382	88.36 359	88.53 18	96.25 322	90.47 153	67.23 428	88.67 395

SPE-MVS-test		92.98 63	93.67 51	90.90 244	96.52 107	76.87 350	98.68 41	94.73 257	90.36 66	94.84 66	97.89 84	77.94 124	97.15 274	94.28 86	97.80 68	98.70 56

BridgeMVS		94.60 27	94.30 40	95.48 17	96.45 108	88.82 15	96.33 231	95.58 203	91.12 51	95.84 47	93.87 265	83.47 60	98.37 166	97.26 45	98.81 24	99.24 24

DELS-MVS		94.98 15	94.49 34	96.44 7	96.42 109	90.59 8	99.21 8	97.02 43	94.40 14	91.46 118	97.08 130	83.32 61	99.69 66	92.83 110	98.70 33	99.04 32
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
balanced_ft_v1		92.00 102	91.12 117	94.64 34	96.35 110	86.78 34	94.96 326	94.70 258	87.65 118	90.20 142	93.01 283	69.71 279	98.02 182	97.40 43	96.13 125	99.11 29

MM		95.85 6	95.74 11	96.15 9	96.34 111	89.50 10	99.18 9	98.10 8	95.68 1	96.64 34	97.92 80	80.72 79	99.80 33	99.16 2	97.96 62	99.15 28

thres200		88.92 199	87.65 211	92.73 124	96.30 112	85.62 62	97.85 90	98.86 1	84.38 233	84.82 240	93.99 261	75.12 197	98.01 184	70.86 388	86.67 279	94.56 300

CS-MVS		92.73 74	93.48 59	90.48 257	96.27 113	75.93 371	98.55 47	94.93 243	89.32 78	94.54 72	97.67 93	78.91 107	97.02 279	93.80 90	97.32 86	98.49 65

DPM-MVS		96.21 2	95.53 15	98.26 1	96.26 114	95.09 1	99.15 12	96.98 46	93.39 23	96.45 38	98.79 14	90.17 10	99.99 1	89.33 179	99.25 6	99.70 4

tfpn200view9		88.48 213	87.15 227	92.47 140	96.21 115	85.30 71	97.44 126	98.85 2	83.37 267	83.99 256	93.82 267	75.36 190	97.93 187	69.04 396	86.24 286	94.17 304

thres400		88.42 216	87.15 227	92.23 161	96.21 115	85.30 71	97.44 126	98.85 2	83.37 267	83.99 256	93.82 267	75.36 190	97.93 187	69.04 396	86.24 286	93.45 320

myMVS_eth3d28		92.72 76	92.23 91	94.21 48	96.16 117	87.46 30	97.37 134	96.99 45	88.13 102	88.18 183	95.47 188	84.12 52	98.04 180	92.46 118	91.17 209	97.14 198

test222					96.15 118	78.41 303	95.87 278	96.46 123	71.97 438	89.66 149	97.45 107	76.33 162			98.24 55	98.30 79

HY-MVS	84.06 6	91.63 114	90.37 136	95.39 20	96.12 119	88.25 18	90.22 423	97.58 15	88.33 96	90.50 136	91.96 302	79.26 100	99.06 126	90.29 161	89.07 238	98.88 44

thres100view900		88.30 219	86.95 234	92.33 153	96.10 120	84.90 87	97.14 154	98.85 2	82.69 286	83.41 269	93.66 271	75.43 187	97.93 187	69.04 396	86.24 286	94.17 304

thres600view7		88.06 226	86.70 242	92.15 169	96.10 120	85.17 77	97.14 154	98.85 2	82.70 285	83.41 269	93.66 271	75.43 187	97.82 197	67.13 405	85.88 291	93.45 320

WTY-MVS		92.65 84	91.68 103	95.56 15	96.00 122	88.90 14	98.23 65	97.65 13	88.57 88	89.82 146	97.22 123	79.29 99	99.06 126	89.57 173	88.73 244	98.73 54

testing91		91.90 106	91.31 111	93.66 75	95.99 123	85.68 57	97.39 133	96.89 57	86.75 155	88.85 167	95.23 200	83.93 56	97.90 194	88.91 183	87.89 268	97.41 172

testing99		91.91 105	91.35 109	93.60 79	95.98 124	85.70 55	97.31 138	96.92 56	86.82 151	88.91 165	95.25 196	84.26 51	97.89 195	88.80 190	87.94 267	97.21 191

MVSTER		89.25 190	88.92 182	90.24 267	95.98 124	84.66 90	96.79 190	95.36 222	87.19 138	80.33 308	90.61 324	90.02 12	95.97 332	85.38 231	78.64 345	90.09 351

testing11		92.48 89	92.04 98	93.78 63	95.94 126	86.00 46	97.56 115	97.08 38	87.52 122	89.32 156	95.40 191	84.60 43	98.02 182	91.93 129	89.04 239	97.32 181

testing3-2		91.37 121	91.01 120	92.44 144	95.93 127	83.77 107	98.83 36	97.45 16	86.88 148	86.63 215	94.69 234	84.57 44	97.75 200	89.65 171	84.44 301	95.80 256

testdata				90.13 270	95.92 128	74.17 388		96.49 121	73.49 421	94.82 68	97.99 74	78.80 110	97.93 187	83.53 253	97.52 76	98.29 80

FBQ-MVS		91.64 113	90.94 121	93.73 68	95.88 129	84.93 85	96.78 192	96.95 51	87.21 137	90.53 134	94.44 244	80.88 76	97.92 192	87.30 213	88.50 259	98.33 74

PatchMatch-RL		85.00 296	83.66 295	89.02 299	95.86 130	74.55 385	92.49 392	93.60 369	79.30 358	79.29 320	91.47 308	58.53 374	98.45 161	70.22 392	92.17 194	94.07 309

testing222		91.09 129	90.49 131	92.87 114	95.82 131	85.04 81	96.51 214	97.28 21	86.05 172	89.13 160	95.34 193	80.16 89	96.62 309	85.82 226	88.31 263	96.96 213

ETVMVS		90.99 132	90.26 139	93.19 99	95.81 132	85.64 61	96.97 172	97.18 29	85.43 193	88.77 170	94.86 226	82.00 71	96.37 316	82.70 261	88.60 249	97.57 150

sasdasda		92.27 95	91.22 112	95.41 18	95.80 133	88.31 16	97.09 161	94.64 269	88.49 90	92.99 93	97.31 115	72.68 233	98.57 149	93.38 98	88.58 251	99.36 17

canonicalmvs		92.27 95	91.22 112	95.41 18	95.80 133	88.31 16	97.09 161	94.64 269	88.49 90	92.99 93	97.31 115	72.68 233	98.57 149	93.38 98	88.58 251	99.36 17

fmvsm_s_conf0.5_n_9		94.52 29	95.22 20	92.41 147	95.79 135	78.61 297	98.73 38	96.00 171	94.91 8	97.73 13	98.73 21	79.09 104	99.79 37	99.14 4	96.86 106	98.83 45

Anonymous20240529		83.15 328	80.60 349	90.80 247	95.74 136	78.27 309	96.81 189	94.92 244	60.10 484	81.89 291	92.54 289	45.82 451	98.82 140	79.25 299	78.32 351	95.31 277

MVS_111021_LR		91.60 116	91.64 105	91.47 217	95.74 136	78.79 292	96.15 249	96.77 74	88.49 90	88.64 172	97.07 131	72.33 241	99.19 115	93.13 107	96.48 118	96.43 238

MGCFI-Net		91.95 103	91.03 119	94.72 32	95.68 138	86.38 39	96.93 177	94.48 279	88.25 98	92.78 96	97.24 121	72.34 240	98.46 159	93.13 107	88.43 260	99.32 20

fmvsm_s_conf0.5_n_11		94.41 32	95.19 21	92.09 171	95.65 139	80.91 210	99.23 7	94.85 250	94.92 7	97.68 16	98.82 12	79.31 98	99.78 40	98.83 9	97.38 83	95.60 267

PS-MVSNAJ		94.17 39	93.52 57	96.10 10	95.65 139	92.35 2	98.21 66	95.79 192	92.42 32	96.24 40	98.18 58	71.04 264	99.17 117	96.77 53	97.39 82	96.79 224

WBMVS		87.73 237	86.79 238	90.56 254	95.61 141	85.68 57	97.63 107	95.52 208	83.77 257	78.30 328	88.44 358	86.14 35	95.78 345	82.54 262	73.15 380	90.21 346

UBG		92.68 83	92.35 85	93.70 72	95.61 141	85.65 60	97.25 141	97.06 40	87.92 107	89.28 157	95.03 214	86.06 36	98.07 178	92.24 120	90.69 217	97.37 176

Anonymous20231211		79.72 375	77.19 383	87.33 349	95.59 143	77.16 347	95.18 316	94.18 317	59.31 488	72.57 397	86.20 400	47.89 444	95.66 353	74.53 360	69.24 408	89.18 372

PRO-TEST		93.79 48	93.63 52	94.29 43	95.54 144	86.59 38	97.30 139	95.42 219	92.49 30	95.39 51	97.33 114	75.72 178	97.16 269	97.19 48	96.29 119	99.11 29

alignmvs		92.97 64	92.26 90	95.12 22	95.54 144	87.77 23	98.67 42	96.38 135	88.04 104	93.01 92	97.45 107	79.20 102	98.60 147	93.25 102	88.76 243	98.99 36

PVSNet	82.34 9	89.02 195	87.79 209	92.71 125	95.49 146	81.50 185	97.70 103	97.29 20	87.76 112	85.47 232	95.12 210	56.90 397	98.90 137	80.33 282	94.02 156	97.71 136

tpmvs		83.04 331	80.77 345	89.84 282	95.43 147	77.96 321	85.59 464	95.32 226	75.31 405	76.27 357	83.70 431	73.89 215	97.41 244	59.53 446	81.93 326	94.14 306

SteuartSystems-ACMMP		94.13 42	94.44 36	93.20 98	95.41 148	81.35 190	99.02 27	96.59 103	89.50 77	94.18 76	98.36 50	83.68 59	99.45 93	94.77 77	98.45 45	98.81 47
Skip Steuart: Steuart Systems R&D Blog.
EPMVS		87.47 247	85.90 252	92.18 166	95.41 148	82.26 152	87.00 454	96.28 146	85.88 181	84.23 251	85.57 408	75.07 198	96.26 320	71.14 386	92.50 183	98.03 100

MVSMamba_PlusPlus		92.37 94	91.55 106	94.83 28	95.37 150	87.69 25	95.60 294	95.42 219	74.65 411	93.95 79	92.81 285	83.11 63	97.70 202	94.49 82	98.53 39	99.11 29

BH-RMVSNet		86.84 255	85.28 265	91.49 215	95.35 151	80.26 237	96.95 175	92.21 410	82.86 282	81.77 294	95.46 189	59.34 368	97.64 208	69.79 394	93.81 164	96.57 235

OMC-MVS		88.80 204	88.16 202	90.72 250	95.30 152	77.92 324	94.81 332	94.51 277	86.80 152	84.97 238	96.85 139	67.53 299	98.60 147	85.08 232	87.62 271	95.63 265

test_fmvsm_n_1920		94.81 22	95.60 12	92.45 142	95.29 153	80.96 207	99.29 4	97.21 26	94.50 13	97.29 23	98.44 41	82.15 69	99.78 40	98.56 12	97.68 72	96.61 233

MVS_Test		90.29 161	89.18 172	93.62 78	95.23 154	84.93 85	94.41 339	94.66 266	84.31 234	90.37 141	91.02 316	75.13 196	97.82 197	83.11 258	94.42 152	98.12 95

F-COLMAP		84.50 307	83.44 304	87.67 337	95.22 155	72.22 405	95.95 261	93.78 350	75.74 400	76.30 356	95.18 205	59.50 366	98.45 161	72.67 374	86.59 281	92.35 330

baseline1		88.85 202	87.49 219	92.93 113	95.21 156	86.85 33	95.47 299	94.61 272	87.29 130	83.11 274	94.99 218	80.70 80	96.89 293	82.28 266	73.72 373	95.05 286

fmvsm_l_conf0.5_n_9		94.91 16	95.60 12	92.84 118	95.20 157	80.55 223	99.45 1	96.36 140	95.17 4	98.48 4	98.55 28	80.53 82	99.78 40	98.87 7	97.79 69	98.19 87

fmvsm_s_conf0.5_n_10		94.36 33	94.73 28	93.23 96	95.19 158	82.87 131	99.18 9	96.39 133	93.97 18	97.91 8	98.53 32	75.88 175	99.82 25	98.58 11	96.95 101	97.00 209

SymmetryMVS		92.45 90	92.33 87	92.82 119	95.19 158	82.02 157	97.94 84	97.43 17	92.34 33	92.15 107	96.53 151	77.03 144	98.57 149	91.13 137	91.19 207	97.87 118

CHOSEN 1792x2688		91.07 131	90.21 142	93.64 76	95.18 160	83.53 116	96.26 237	96.13 160	88.92 82	84.90 239	93.10 281	72.86 229	99.62 76	88.86 184	95.67 136	97.79 128

UGNet		87.73 237	86.55 244	91.27 226	95.16 161	79.11 276	96.35 229	96.23 152	88.14 101	87.83 191	90.48 325	50.65 429	99.09 124	80.13 287	94.03 155	95.60 267
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
fmvsm_s_conf0.5_n_8		94.52 29	95.04 23	92.96 110	95.15 162	81.14 194	99.09 20	96.66 92	95.53 3	97.84 10	98.71 22	76.33 162	99.81 29	99.24 1	96.85 108	97.92 114

VDD-MVS		88.28 220	87.02 232	92.06 175	95.09 163	80.18 242	97.55 117	94.45 285	83.09 273	89.10 162	95.92 163	47.97 442	98.49 156	93.08 109	86.91 278	97.52 159

PVSNet_Blended_VisFu		91.24 125	90.77 124	92.66 127	95.09 163	82.40 146	97.77 97	95.87 189	88.26 97	86.39 220	93.94 263	76.77 152	99.27 103	88.80 190	94.00 158	96.31 244

h-mvs33		89.30 188	88.95 181	90.36 263	95.07 165	76.04 365	96.96 174	97.11 36	90.39 64	92.22 105	95.10 211	74.70 203	98.86 138	93.14 105	65.89 439	96.16 246

xiu_mvs_v2_base		93.92 46	93.26 63	95.91 12	95.07 165	92.02 6	98.19 67	95.68 198	92.06 40	96.01 45	98.14 63	70.83 269	98.96 131	96.74 55	96.57 115	96.76 228

cl22		85.11 292	84.17 286	87.92 331	95.06 167	78.82 284	95.51 297	94.22 310	79.74 349	76.77 346	87.92 367	75.96 171	95.68 352	79.93 290	72.42 382	89.27 369

BH-w/o		88.24 221	87.47 221	90.54 256	95.03 168	78.54 298	97.41 131	93.82 344	84.08 243	78.23 329	94.51 238	69.34 283	97.21 265	80.21 286	94.58 149	95.87 255

CHOSEN 280x420		91.71 112	91.85 99	91.29 225	94.94 169	82.69 135	87.89 447	96.17 158	85.94 179	87.27 200	94.31 246	90.27 9	95.65 355	94.04 88	95.86 133	95.53 271

GG-mvs-BLEND				93.49 86	94.94 169	86.26 40	81.62 479	97.00 44		88.32 178	94.30 247	91.23 6	96.21 324	88.49 198	97.43 80	98.00 107

HyFIR lowres test		89.36 186	88.60 187	91.63 208	94.91 171	80.76 215	95.60 294	95.53 206	82.56 289	84.03 255	91.24 313	78.03 123	96.81 300	87.07 217	88.41 261	97.32 181

miper_enhance_ethall		85.95 272	85.20 266	88.19 325	94.85 172	79.76 253	96.00 258	94.06 325	82.98 279	77.74 334	88.76 349	79.42 96	95.46 365	80.58 280	72.42 382	89.36 367

mvsmamba		90.53 150	90.08 146	91.88 188	94.81 173	80.93 208	93.94 358	94.45 285	88.24 99	87.02 207	92.35 292	68.04 291	95.80 343	94.86 76	97.03 98	98.92 41

mvs_anonymous		88.68 206	87.62 214	91.86 189	94.80 174	81.69 179	93.53 370	94.92 244	82.03 299	78.87 323	90.43 327	75.77 176	95.34 369	85.04 233	93.16 175	98.55 64

CANet_DTU		90.98 133	90.04 149	93.83 61	94.76 175	86.23 43	96.32 232	93.12 394	93.11 25	93.71 81	96.82 142	63.08 338	99.48 91	84.29 238	95.12 142	95.77 261

PMMVS		89.46 181	89.92 156	88.06 328	94.64 176	69.57 438	96.22 242	94.95 242	87.27 133	91.37 121	96.54 150	65.88 315	97.39 248	88.54 196	93.89 162	97.23 187

TR-MVS		86.30 266	84.93 274	90.42 259	94.63 177	77.58 337	96.57 208	93.82 344	80.30 335	82.42 281	95.16 206	58.74 372	97.55 220	74.88 354	87.82 269	96.13 248

EPNet_dtu		87.65 242	87.89 206	86.93 358	94.57 178	71.37 423	96.72 197	96.50 118	88.56 89	87.12 205	95.02 215	75.91 174	94.01 422	66.62 409	90.00 223	95.42 274
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n		93.69 49	94.13 45	92.34 151	94.56 179	82.01 159	99.07 22	97.13 33	92.09 38	96.25 39	98.53 32	76.47 157	99.80 33	98.39 14	94.71 147	95.22 281

FMVSNet3		84.71 299	82.71 318	90.70 251	94.55 180	87.71 24	95.92 264	94.67 265	81.73 304	75.82 365	88.08 365	66.99 306	94.47 413	71.23 383	75.38 364	89.91 355

ETV-MVS		92.72 76	92.87 72	92.28 157	94.54 181	81.89 168	97.98 81	95.21 233	89.77 73	93.11 90	96.83 140	77.23 141	97.50 229	95.74 63	95.38 140	97.44 170

fmvsm_l_conf0.5_n_3		94.61 25	94.92 26	93.68 74	94.52 182	82.80 133	99.33 2	96.37 138	95.08 6	97.59 20	98.48 38	77.40 135	99.79 37	98.28 16	97.21 89	98.44 69

EIA-MVS		91.73 109	92.05 97	90.78 249	94.52 182	76.40 360	98.06 77	95.34 225	89.19 80	88.90 166	97.28 120	77.56 132	97.73 201	90.77 147	96.86 106	98.20 86

BH-untuned		86.95 253	85.94 250	89.99 275	94.52 182	77.46 339	96.78 192	93.37 383	81.80 302	76.62 349	93.81 269	66.64 310	97.02 279	76.06 339	93.88 163	95.48 273

DeepC-MVS	86.58 3	91.53 117	91.06 118	92.94 112	94.52 182	81.89 168	95.95 261	95.98 174	90.76 57	83.76 262	96.76 144	73.24 225	99.71 62	91.67 131	96.96 100	97.22 188
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
gg-mvs-nofinetune		85.48 284	82.90 314	93.24 95	94.51 186	85.82 52	79.22 486	96.97 49	61.19 479	87.33 197	53.01 516	90.58 7	96.07 328	86.07 225	97.23 88	97.81 127

fmvsm_l_conf0.5_n_a		94.91 16	95.30 18	93.72 70	94.50 187	84.30 98	99.14 14	96.00 171	91.94 43	97.91 8	98.60 26	84.78 42	99.77 44	98.84 8	96.03 129	97.08 206

3Dnovator+	82.88 8	89.63 178	87.85 207	94.99 24	94.49 188	86.76 36	97.84 91	95.74 195	86.10 170	75.47 370	96.02 160	65.00 323	99.51 89	82.91 260	97.07 97	98.72 55

RRT-MVS		89.67 176	88.67 185	92.67 126	94.44 189	81.08 197	94.34 344	94.45 285	86.05 172	85.79 227	92.39 291	63.39 336	98.16 176	93.22 103	93.95 161	98.76 49

nomal-1		89.71 175	89.18 172	91.30 224	94.43 190	81.03 199	94.35 343	96.27 147	85.05 209	83.05 275	90.78 321	80.87 77	97.21 265	89.53 176	88.34 262	95.66 264

fmvsm_l_conf0.5_n		94.89 18	95.24 19	93.86 60	94.42 191	84.61 91	99.13 15	96.15 159	92.06 40	97.92 6	98.52 34	84.52 45	99.74 54	98.76 10	95.67 136	97.22 188

fmvsm_s_conf0.5_n_3		93.95 45	94.53 32	92.20 165	94.41 192	80.04 247	98.90 33	95.96 176	94.53 12	97.63 19	98.58 27	75.95 172	99.79 37	98.25 18	96.60 114	96.77 226

ET-MVSNet_ETH3D		90.01 165	89.03 175	92.95 111	94.38 193	86.77 35	98.14 68	96.31 145	89.30 79	63.33 455	96.72 147	90.09 11	93.63 430	90.70 150	82.29 323	98.46 67

tpmrst		88.36 217	87.38 223	91.31 222	94.36 194	79.92 249	87.32 451	95.26 231	85.32 196	88.34 177	86.13 401	80.60 81	96.70 305	83.78 244	85.34 298	97.30 184

FE-MVS		86.06 270	84.15 287	91.78 197	94.33 195	79.81 251	84.58 471	96.61 99	76.69 395	85.00 237	87.38 375	70.71 271	98.37 166	70.39 391	91.70 199	97.17 197

MVS		90.60 145	88.64 186	96.50 6	94.25 196	90.53 9	93.33 375	97.21 26	77.59 380	78.88 322	97.31 115	71.52 259	99.69 66	89.60 172	98.03 60	99.27 23

dp		84.30 310	82.31 323	90.28 266	94.24 197	77.97 320	86.57 457	95.53 206	79.94 346	80.75 302	85.16 416	71.49 260	96.39 315	63.73 426	83.36 309	96.48 237

FA-MVS(test-final)		87.71 240	86.23 248	92.17 167	94.19 198	80.55 223	87.16 453	96.07 166	82.12 297	85.98 226	88.35 360	72.04 251	98.49 156	80.26 284	89.87 225	97.48 163

UWE-MVS		88.56 212	88.91 183	87.50 345	94.17 199	72.19 408	95.82 282	97.05 41	84.96 213	84.78 241	93.51 275	81.33 73	94.75 404	79.43 294	89.17 236	95.57 269

sss		90.87 138	89.96 154	93.60 79	94.15 200	83.84 106	97.14 154	98.13 7	85.93 180	89.68 148	96.09 159	71.67 255	99.30 102	87.69 209	89.16 237	97.66 140

SDMVSNet		87.02 251	85.61 257	91.24 228	94.14 201	83.30 121	93.88 360	95.98 174	84.30 236	79.63 316	92.01 298	58.23 376	97.68 204	90.28 163	82.02 324	92.75 324

sd_testset		84.62 303	83.11 309	89.17 295	94.14 201	77.78 330	91.54 411	94.38 294	84.30 236	79.63 316	92.01 298	52.28 422	96.98 285	77.67 318	82.02 324	92.75 324

PatchmatchNet		86.83 256	85.12 270	91.95 184	94.12 203	82.27 151	86.55 458	95.64 201	84.59 223	82.98 277	84.99 420	77.26 137	95.96 335	68.61 399	91.34 206	97.64 142
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
fmvsm_s_conf0.5_n_2		92.97 64	93.38 62	91.73 201	94.10 204	80.64 218	98.96 30	95.89 185	94.09 16	97.05 26	98.40 45	68.92 288	99.80 33	98.53 13	94.50 151	94.74 294

MDTV_nov1_ep13			83.69 292		94.09 205	81.01 200	86.78 456	96.09 163	83.81 256	84.75 242	84.32 425	74.44 209	96.54 310	63.88 425	85.07 299

UA-Net		88.92 199	88.48 195	90.24 267	94.06 206	77.18 346	93.04 383	94.66 266	87.39 128	91.09 126	93.89 264	74.92 199	98.18 175	75.83 342	91.43 203	95.35 276

Fast-Effi-MVS+		87.93 231	86.94 235	90.92 242	94.04 207	79.16 274	98.26 64	93.72 360	81.29 308	83.94 259	92.90 284	69.83 277	96.68 306	76.70 330	91.74 198	96.93 215

QAPM		86.88 254	84.51 277	93.98 56	94.04 207	85.89 50	97.19 146	96.05 167	73.62 418	75.12 373	95.62 179	62.02 350	99.74 54	70.88 387	96.06 128	96.30 245

thisisatest0515		90.95 135	90.26 139	93.01 107	94.03 209	84.27 100	97.91 87	96.67 89	83.18 271	86.87 213	95.51 185	88.66 17	97.85 196	80.46 281	89.01 240	96.92 217

fmvsm_s_conf0.5_n_4		93.59 51	94.32 39	91.41 219	93.89 210	79.24 270	98.89 34	96.53 114	92.82 27	97.37 22	98.47 39	77.21 143	99.78 40	98.11 25	95.59 138	95.21 282

Vis-MVSNet (Re-imp)		88.88 201	88.87 184	88.91 301	93.89 210	74.43 386	96.93 177	94.19 316	84.39 232	83.22 272	95.67 173	78.24 119	94.70 406	78.88 304	94.40 153	97.61 147

ADS-MVSNet2		79.57 377	77.53 380	85.71 379	93.78 212	72.13 409	79.48 484	86.11 476	73.09 424	80.14 310	79.99 463	62.15 346	90.14 468	59.49 447	83.52 306	94.85 291

ADS-MVSNet		81.26 359	78.36 373	89.96 278	93.78 212	79.78 252	79.48 484	93.60 369	73.09 424	80.14 310	79.99 463	62.15 346	95.24 377	59.49 447	83.52 306	94.85 291

EPP-MVSNet		89.76 173	89.72 161	89.87 281	93.78 212	76.02 368	97.22 142	96.51 116	79.35 355	85.11 235	95.01 216	84.82 41	97.10 277	87.46 212	88.21 265	96.50 236

3Dnovator	82.32 10	89.33 187	87.64 212	94.42 39	93.73 215	85.70 55	97.73 101	96.75 78	86.73 156	76.21 359	95.93 161	62.17 343	99.68 68	81.67 270	97.81 67	97.88 116

E3new		90.90 137	90.35 138	92.55 137	93.63 216	82.40 146	96.79 190	94.49 278	87.07 143	88.54 173	95.70 170	73.85 216	97.60 210	91.23 135	91.86 197	97.64 142

Effi-MVS+		90.70 142	89.90 157	93.09 104	93.61 217	83.48 117	95.20 313	92.79 399	83.22 270	91.82 114	95.70 170	71.82 254	97.48 232	91.25 134	93.67 167	98.32 76

IS-MVSNet		88.67 207	88.16 202	90.20 269	93.61 217	76.86 351	96.77 195	93.07 395	84.02 245	83.62 265	95.60 180	74.69 206	96.24 323	78.43 308	93.66 168	97.49 162

AUN-MVS		86.25 268	85.57 258	88.26 318	93.57 219	73.38 393	95.45 300	95.88 187	83.94 249	85.47 232	94.21 251	73.70 221	96.67 307	83.54 252	64.41 443	94.73 298

test2506		90.96 134	90.39 134	92.65 128	93.54 220	82.46 144	96.37 225	97.35 19	86.78 153	87.55 193	95.25 196	77.83 128	97.50 229	84.07 240	94.80 145	97.98 109

ECVR-MVS		88.35 218	87.25 225	91.65 205	93.54 220	79.40 266	96.56 210	90.78 439	86.78 153	85.57 230	95.25 196	57.25 395	97.56 216	84.73 236	94.80 145	97.98 109

hse-mvs2		88.22 222	88.21 200	88.25 320	93.54 220	73.41 392	95.41 302	95.89 185	90.39 64	92.22 105	94.22 250	74.70 203	96.66 308	93.14 105	64.37 444	94.69 299

LCM-MVSNet-Re		83.75 318	83.54 301	84.39 405	93.54 220	64.14 465	92.51 391	84.03 487	83.90 251	66.14 443	86.59 389	67.36 302	92.68 437	84.89 235	92.87 178	96.35 240

EC-MVSNet		91.73 109	92.11 95	90.58 253	93.54 220	77.77 331	98.07 76	94.40 291	87.44 126	92.99 93	97.11 128	74.59 207	96.87 296	93.75 92	97.08 96	97.11 199

tpm cat1		83.63 320	81.38 337	90.39 260	93.53 225	78.19 316	85.56 465	95.09 236	70.78 444	78.51 325	83.28 436	74.80 202	97.03 278	66.77 407	84.05 304	95.95 251

fmvsm_s_conf0.5_n_6		94.17 39	94.70 29	92.58 136	93.50 226	81.20 192	99.08 21	96.48 122	92.24 36	98.62 3	98.39 46	78.58 114	99.72 59	98.08 26	97.36 84	96.81 223

thisisatest0530		89.65 177	89.02 176	91.53 211	93.46 227	80.78 214	96.52 212	96.67 89	81.69 305	83.79 261	94.90 223	88.85 16	97.68 204	77.80 313	87.49 275	96.14 247

MSDG		80.62 369	77.77 379	89.14 296	93.43 228	77.24 343	91.89 403	90.18 444	69.86 450	68.02 431	91.94 305	52.21 423	98.84 139	59.32 449	83.12 310	91.35 332

fmvsm_s_conf0.5_n_a		93.34 57	93.71 50	92.22 162	93.38 229	81.71 178	98.86 35	96.98 46	91.64 44	96.85 29	98.55 28	75.58 182	99.77 44	97.88 32	93.68 166	95.18 283

ab-mvs		87.08 250	84.94 273	93.48 87	93.34 230	83.67 113	88.82 436	95.70 197	81.18 310	84.55 247	90.14 333	62.72 339	98.94 135	85.49 230	82.54 320	97.85 121

viewdifsd2359ckpt09		90.00 166	89.28 171	92.15 169	93.31 231	81.38 188	96.37 225	93.64 365	86.34 164	86.62 216	95.64 175	71.58 258	97.52 226	88.93 182	91.06 211	97.54 153

VortexMVS		85.45 285	84.40 281	88.63 307	93.25 232	81.66 180	95.39 304	94.34 296	87.15 141	75.10 374	87.65 371	66.58 312	95.19 379	86.89 219	73.21 379	89.03 383

viewcassd2359sk11		90.66 143	90.06 148	92.47 140	93.22 233	82.21 154	96.70 201	94.47 282	86.94 146	88.22 182	95.50 186	73.15 226	97.59 212	90.86 143	91.48 201	97.60 148

1314		88.94 198	87.20 226	94.17 52	93.21 234	85.73 54	93.33 375	96.64 96	82.89 280	75.98 362	96.36 153	66.83 309	99.39 95	83.52 254	96.02 130	97.39 175

1112_ss		88.60 210	87.47 221	92.00 182	93.21 234	80.97 202	96.47 216	92.46 402	83.64 264	80.86 301	97.30 118	80.24 86	97.62 209	77.60 319	85.49 295	97.40 174

GeoE		86.36 264	85.20 266	89.83 283	93.17 236	76.13 363	97.53 118	92.11 411	79.58 352	80.99 298	94.01 258	66.60 311	96.17 327	73.48 368	89.30 234	97.20 194

test1111		88.11 224	87.04 231	91.35 221	93.15 237	78.79 292	96.57 208	90.78 439	86.88 148	85.04 236	95.20 203	57.23 396	97.39 248	83.88 242	94.59 148	97.87 118

Test_1112_low_res		88.03 227	86.73 239	91.94 186	93.15 237	80.88 211	96.44 219	92.41 406	83.59 266	80.74 303	91.16 314	80.18 87	97.59 212	77.48 322	85.40 296	97.36 177

CostFormer		89.08 193	88.39 196	91.15 233	93.13 239	79.15 275	88.61 439	96.11 162	83.14 272	89.58 151	86.93 384	83.83 58	96.87 296	88.22 202	85.92 290	97.42 171

IB-MVS	85.34 4	88.67 207	87.14 229	93.26 94	93.12 240	84.32 97	98.76 37	97.27 22	87.19 138	79.36 319	90.45 326	83.92 57	98.53 154	84.41 237	69.79 402	96.93 215
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
diffmvs		91.17 127	90.74 125	92.44 144	93.11 241	82.50 143	96.25 238	93.62 367	87.79 111	90.40 139	95.93 161	73.44 223	97.42 242	93.62 95	92.55 182	97.41 172
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt13		90.08 163	89.36 168	92.26 158	93.03 242	81.90 167	96.37 225	94.34 296	86.16 167	87.44 194	95.30 194	70.93 268	97.55 220	89.05 181	91.59 200	97.35 179

tttt0517		88.57 211	88.19 201	89.71 287	93.00 243	75.99 369	95.67 289	96.67 89	80.78 319	81.82 292	94.40 245	88.97 15	97.58 214	76.05 340	86.31 283	95.57 269

MVSFormer		91.36 122	90.57 128	93.73 68	93.00 243	88.08 20	94.80 333	94.48 279	80.74 320	94.90 64	97.13 126	78.84 108	95.10 388	83.77 245	97.46 77	98.02 101

lupinMVS		93.87 47	93.58 55	94.75 31	93.00 243	88.08 20	99.15 12	95.50 210	91.03 54	94.90 64	97.66 94	78.84 108	97.56 216	94.64 81	97.46 77	98.62 60

casdiffmvs_mvg		91.13 128	90.45 132	93.17 100	92.99 246	83.58 115	97.46 125	94.56 275	87.69 115	87.19 203	94.98 219	74.50 208	97.60 210	91.88 130	92.79 179	98.34 73
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmanbaseed2359cas		90.74 141	90.07 147	92.76 121	92.98 247	82.93 130	96.53 211	94.28 302	87.08 142	88.96 164	95.64 175	72.03 252	97.58 214	90.85 144	92.26 191	97.76 130

test_fmvs1		87.79 235	88.52 194	85.62 382	92.98 247	64.31 463	97.88 89	92.42 405	87.95 106	92.24 104	95.82 164	47.94 443	98.44 163	95.31 72	94.09 154	94.09 308

mamba_0408		85.26 290	83.10 310	91.74 200	92.94 249	82.53 138	72.52 501	91.77 417	80.36 332	83.50 266	94.01 258	64.97 324	96.90 291	79.37 295	88.51 256	95.79 258

SSM_04072		84.64 301	83.10 310	89.25 294	92.94 249	82.53 138	72.52 501	91.77 417	80.36 332	83.50 266	94.01 258	64.97 324	89.41 470	79.37 295	88.51 256	95.79 258

SSM_0407		87.33 249	85.87 253	91.71 204	92.94 249	82.53 138	94.30 347	92.33 408	80.11 340	83.50 266	94.18 253	64.68 328	96.80 302	82.34 264	88.51 256	95.79 258

SSM_0404		87.69 241	86.26 246	91.95 184	92.94 249	83.02 128	94.69 335	92.33 408	80.11 340	84.65 245	94.18 253	64.68 328	96.90 291	82.34 264	90.44 218	95.94 252

tpm2		87.35 248	86.26 246	90.62 252	92.93 253	78.67 295	88.06 446	95.99 173	79.33 356	87.40 195	86.43 395	80.28 85	96.40 314	80.23 285	85.73 294	96.79 224

baseline		90.76 140	90.10 145	92.74 123	92.90 254	82.56 137	94.60 336	94.56 275	87.69 115	89.06 163	95.67 173	73.76 218	97.51 228	90.43 156	92.23 193	98.16 90

fmvsm_s_conf0.5_n_5		93.57 53	93.75 48	93.01 107	92.87 255	82.73 134	98.93 32	95.90 184	90.96 56	95.61 49	98.39 46	76.57 155	99.63 74	98.32 15	96.24 121	96.68 232

GDP-MVS		92.85 71	92.55 81	93.75 65	92.82 256	85.76 53	97.63 107	95.05 239	88.34 95	93.15 89	97.10 129	86.92 28	98.01 184	87.95 204	94.00 158	97.47 164

test_fmvsmconf_n		93.99 44	94.36 38	92.86 115	92.82 256	81.12 195	99.26 6	96.37 138	93.47 22	95.16 57	98.21 56	79.00 105	99.64 72	98.21 20	96.73 112	97.83 123

casdiffmvs		90.95 135	90.39 134	92.63 131	92.82 256	82.53 138	96.83 184	94.47 282	87.69 115	88.47 174	95.56 182	74.04 214	97.54 223	90.90 142	92.74 180	97.83 123
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_conf0.5_n_7		92.88 68	93.82 47	90.08 271	92.79 259	76.45 358	98.54 48	96.74 79	92.28 35	95.22 56	98.49 36	74.91 200	98.15 177	98.28 16	97.13 93	95.63 265

Casviewmamba		90.52 152	90.00 152	92.06 175	92.72 260	80.42 232	96.87 181	94.28 302	87.45 124	87.30 198	95.73 168	73.10 227	97.67 206	90.27 164	92.29 190	98.10 97

onestephybrid01		90.58 146	90.37 136	91.20 232	92.69 261	78.81 286	96.04 256	93.94 330	86.55 161	90.40 139	95.64 175	72.84 230	97.43 241	93.77 91	91.46 202	97.36 177

Vis-MVSNet		88.67 207	87.82 208	91.24 228	92.68 262	78.82 284	96.95 175	93.85 339	87.55 121	87.07 206	95.13 209	63.43 335	97.21 265	77.58 320	96.15 124	97.70 137
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
E2		90.33 158	89.65 163	92.37 149	92.66 263	81.99 160	96.58 206	94.39 292	86.71 157	87.88 188	95.25 196	72.18 244	97.56 216	90.37 159	90.88 214	97.57 150

GBi-Net		82.42 341	80.43 352	88.39 313	92.66 263	81.95 162	94.30 347	93.38 380	79.06 364	75.82 365	85.66 404	56.38 403	93.84 425	71.23 383	75.38 364	89.38 363

test1		82.42 341	80.43 352	88.39 313	92.66 263	81.95 162	94.30 347	93.38 380	79.06 364	75.82 365	85.66 404	56.38 403	93.84 425	71.23 383	75.38 364	89.38 363

FMVSNet2		82.79 335	80.44 351	89.83 283	92.66 263	85.43 65	95.42 301	94.35 295	79.06 364	74.46 378	87.28 376	56.38 403	94.31 417	69.72 395	74.68 370	89.76 356

E3		90.33 158	89.65 163	92.37 149	92.64 267	81.99 160	96.58 206	94.39 292	86.71 157	87.87 189	95.27 195	72.17 245	97.56 216	90.37 159	90.88 214	97.57 150

BP-MVS1		93.55 54	93.50 58	93.71 71	92.64 267	85.39 66	97.78 96	96.84 62	89.52 76	92.00 110	97.06 132	88.21 22	98.03 181	91.45 132	96.00 131	97.70 137

miper_ehance_all_eth		84.57 305	83.60 300	87.50 345	92.64 267	78.25 310	95.40 303	93.47 375	79.28 359	76.41 353	87.64 372	76.53 156	95.24 377	78.58 306	72.42 382	89.01 387

cascas		86.50 260	84.48 279	92.55 137	92.64 267	85.95 47	97.04 165	95.07 238	75.32 404	80.50 304	91.02 316	54.33 417	97.98 186	86.79 222	87.62 271	93.71 315

TESTMET0.1,1		89.83 172	89.34 169	91.31 222	92.54 271	80.19 241	97.11 157	96.57 106	86.15 168	86.85 214	91.83 307	79.32 97	96.95 287	81.30 275	92.35 189	96.77 226

guyue		89.85 170	89.33 170	91.40 220	92.53 272	80.15 243	96.82 187	95.68 198	89.66 74	86.43 219	94.23 249	67.00 305	97.16 269	91.96 128	89.65 227	96.89 218

hybridcas		90.40 154	89.67 162	92.60 134	92.39 273	82.32 150	96.83 184	94.25 306	87.19 138	86.59 217	95.43 190	72.54 235	97.65 207	88.77 192	93.02 177	97.82 125

COLMAP_ROB	73.24 19	75.74 413	73.00 420	83.94 407	92.38 274	69.08 440	91.85 405	86.93 469	61.48 477	65.32 447	90.27 329	42.27 462	96.93 290	50.91 478	75.63 363	85.80 449
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
hybridnocas07		90.53 150	90.02 150	92.05 179	92.36 275	81.48 186	96.27 235	93.57 372	86.86 150	89.28 157	95.48 187	72.17 245	97.47 233	92.77 111	91.41 204	97.21 191

test_vis1_n_1920		89.95 167	90.59 127	88.03 330	92.36 275	68.98 441	99.12 16	94.34 296	93.86 19	93.64 83	97.01 134	51.54 424	99.59 78	96.76 54	96.71 113	95.53 271

viewdifsd2359ckpt07		89.04 194	88.30 198	91.27 226	92.32 277	78.90 281	95.89 274	93.77 353	84.48 230	85.18 234	95.16 206	69.83 277	97.70 202	88.75 193	89.29 235	97.22 188

xiu_mvs_v1_base_debu		90.54 147	89.54 165	93.55 82	92.31 278	87.58 27	96.99 167	94.87 247	87.23 134	93.27 85	97.56 103	57.43 391	98.32 168	92.72 112	93.46 171	94.74 294

xiu_mvs_v1_base		90.54 147	89.54 165	93.55 82	92.31 278	87.58 27	96.99 167	94.87 247	87.23 134	93.27 85	97.56 103	57.43 391	98.32 168	92.72 112	93.46 171	94.74 294

xiu_mvs_v1_base_debi		90.54 147	89.54 165	93.55 82	92.31 278	87.58 27	96.99 167	94.87 247	87.23 134	93.27 85	97.56 103	57.43 391	98.32 168	92.72 112	93.46 171	94.74 294

icg_test_0407_2		87.55 244	86.59 243	90.43 258	92.30 281	78.81 286	92.17 398	93.84 340	85.14 203	83.68 263	94.49 240	67.75 294	95.02 396	81.33 271	88.61 245	97.46 165

IMVS_0407		87.82 233	86.72 240	91.14 234	92.30 281	78.81 286	93.34 374	93.84 340	85.14 203	83.68 263	94.49 240	67.75 294	97.14 275	81.33 271	88.61 245	97.46 165

IMVS_0404		85.34 287	83.69 292	90.29 265	92.30 281	78.81 286	90.62 420	93.84 340	85.14 203	72.51 399	94.49 240	54.36 416	94.61 409	81.33 271	88.61 245	97.46 165

IMVS_0403		88.07 225	87.02 232	91.24 228	92.30 281	78.81 286	93.62 366	93.84 340	85.14 203	84.36 248	94.49 240	69.49 281	97.46 240	81.33 271	88.61 245	97.46 165

SCA		85.63 278	83.64 298	91.60 209	92.30 281	81.86 170	92.88 387	95.56 205	84.85 214	82.52 278	85.12 418	58.04 379	95.39 366	73.89 364	87.58 273	97.54 153

fmvsm_s_conf0.1_n_2		92.26 97	92.48 83	91.60 209	92.29 286	80.55 223	98.73 38	94.33 299	93.80 20	96.18 41	98.11 65	66.93 307	99.75 51	98.19 21	93.74 165	94.50 301

gm-plane-assit					92.27 287	79.64 261			84.47 231		95.15 208		97.93 187	85.81 227

test-LLR		88.48 213	87.98 204	89.98 276	92.26 288	77.23 344	97.11 157	95.96 176	83.76 258	86.30 222	91.38 310	72.30 242	96.78 303	80.82 278	91.92 195	95.94 252

test-mter		88.95 197	88.60 187	89.98 276	92.26 288	77.23 344	97.11 157	95.96 176	85.32 196	86.30 222	91.38 310	76.37 161	96.78 303	80.82 278	91.92 195	95.94 252

PAPM		92.87 70	92.40 84	94.30 42	92.25 290	87.85 22	96.40 224	96.38 135	91.07 53	88.72 171	96.90 136	82.11 70	97.37 254	90.05 165	97.70 71	97.67 139

viewmambaseed2359dif		89.52 179	89.02 176	91.03 237	92.24 291	78.83 283	95.89 274	93.77 353	83.04 275	88.28 181	95.80 166	72.08 250	97.40 246	89.76 169	90.32 219	96.87 221

hybrid		90.42 153	89.87 159	92.06 175	92.20 292	81.45 187	96.09 253	93.61 368	85.80 182	89.55 152	95.52 184	72.14 249	97.39 248	92.60 115	91.36 205	97.34 180

cl____		83.27 325	82.12 325	86.74 359	92.20 292	75.95 370	95.11 321	93.27 386	78.44 373	74.82 376	87.02 383	74.19 211	95.19 379	74.67 357	69.32 406	89.09 375

DIV-MVS_self_test		83.27 325	82.12 325	86.74 359	92.19 294	75.92 372	95.11 321	93.26 387	78.44 373	74.81 377	87.08 382	74.19 211	95.19 379	74.66 358	69.30 407	89.11 374

AllTest		75.92 411	73.06 419	84.47 401	92.18 295	67.29 447	91.07 415	84.43 482	67.63 456	63.48 452	90.18 330	38.20 475	97.16 269	57.04 458	73.37 375	88.97 390

TestCases				84.47 401	92.18 295	67.29 447		84.43 482	67.63 456	63.48 452	90.18 330	38.20 475	97.16 269	57.04 458	73.37 375	88.97 390

KinetiMVS		89.13 192	87.95 205	92.65 128	92.16 297	82.39 148	97.04 165	96.05 167	86.59 160	88.08 186	94.85 227	61.54 355	98.38 165	81.28 276	93.99 160	97.19 195

CLD-MVS		87.97 230	87.48 220	89.44 291	92.16 297	80.54 227	98.14 68	94.92 244	91.41 47	79.43 318	95.40 191	62.34 342	97.27 261	90.60 151	82.90 315	90.50 341
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
viewmamba		90.30 160	89.90 157	91.48 216	92.14 299	79.76 253	95.92 264	93.50 374	87.73 113	88.32 178	95.82 164	72.39 238	97.36 255	92.19 122	91.12 210	97.30 184

Syy-MVS		77.97 396	78.05 376	77.74 455	92.13 300	56.85 489	93.97 356	94.23 308	82.43 290	73.39 385	93.57 273	57.95 382	87.86 479	32.40 509	82.34 321	88.51 398

myMVS_eth3d		81.93 348	82.18 324	81.18 436	92.13 300	67.18 449	93.97 356	94.23 308	82.43 290	73.39 385	93.57 273	76.98 147	87.86 479	50.53 480	82.34 321	88.51 398

c3_l		83.80 317	82.65 319	87.25 353	92.10 302	77.74 335	95.25 310	93.04 396	78.58 370	76.01 361	87.21 380	75.25 195	95.11 387	77.54 321	68.89 410	88.91 393

HQP-NCC					92.08 303		97.63 107		90.52 61	82.30 282

ACMP_Plane					92.08 303		97.63 107		90.52 61	82.30 282

HQP-MVS		87.91 232	87.55 218	88.98 300	92.08 303	78.48 299	97.63 107	94.80 253	90.52 61	82.30 282	94.56 236	65.40 319	97.32 256	87.67 210	83.01 312	91.13 333

PCF-MVS	84.09 5	86.77 258	85.00 272	92.08 172	92.06 306	83.07 126	92.14 399	94.47 282	79.63 351	76.90 345	94.78 229	71.15 262	99.20 114	72.87 372	91.05 212	93.98 310
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffseed414692147		88.22 222	86.93 236	92.08 172	92.04 307	81.84 171	96.08 255	94.08 323	84.56 224	85.59 229	93.98 262	67.37 301	97.42 242	80.12 288	88.52 255	96.99 210

NP-MVS					92.04 307	78.22 311					94.56 236

diffmvs_AUTHOR		90.86 139	90.41 133	92.24 159	92.01 309	82.22 153	96.18 246	93.64 365	87.28 131	90.46 138	95.64 175	72.82 231	97.39 248	93.17 104	92.46 185	97.11 199

plane_prior6					91.98 310	77.92 324						64.77 326

Effi-MVS+-dtu		84.61 304	84.90 275	83.72 412	91.96 311	63.14 471	94.95 327	93.34 384	85.57 188	79.79 314	87.12 381	61.99 351	95.61 359	83.55 251	85.83 292	92.41 328

plane_prior1					91.95 312

CDS-MVSNet		89.50 180	88.96 180	91.14 234	91.94 313	80.93 208	97.09 161	95.81 191	84.26 239	84.72 243	94.20 252	80.31 84	95.64 356	83.37 255	88.96 241	96.85 222
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
E4		89.85 170	89.06 174	92.22 162	91.88 314	81.63 182	96.43 221	94.27 304	86.32 165	87.29 199	94.97 220	70.81 270	97.52 226	89.57 173	90.00 223	97.51 160

HQP_MVS		87.50 246	87.09 230	88.74 305	91.86 315	77.96 321	97.18 147	94.69 262	89.89 71	81.33 295	94.15 255	64.77 326	97.30 258	87.08 215	82.82 316	90.96 335

plane_prior7					91.86 315	77.55 338

eth_miper_zixun_eth		83.12 329	82.01 327	86.47 364	91.85 317	74.80 381	94.33 345	93.18 390	79.11 362	75.74 368	87.25 379	72.71 232	95.32 371	76.78 329	67.13 429	89.27 369

dtuplus		89.18 191	88.59 189	90.96 240	91.84 318	78.40 306	95.89 274	93.81 347	83.26 269	87.77 192	95.53 183	70.57 272	97.49 231	88.57 195	90.08 221	96.99 210

E5new		89.38 182	88.55 190	91.85 191	91.77 319	80.97 202	95.90 270	94.22 310	86.03 174	86.88 209	94.90 223	69.05 284	97.47 233	88.86 184	89.35 230	97.10 201

E5		89.38 182	88.55 190	91.85 191	91.77 319	80.97 202	95.90 270	94.22 310	86.03 174	86.88 209	94.90 223	69.05 284	97.47 233	88.86 184	89.35 230	97.10 201

E6new		89.37 184	88.55 190	91.85 191	91.75 321	80.97 202	95.90 270	94.22 310	86.03 174	86.88 209	94.91 221	69.05 284	97.47 233	88.86 184	89.34 232	97.10 201

E6		89.37 184	88.55 190	91.85 191	91.75 321	80.97 202	95.90 270	94.22 310	86.03 174	86.88 209	94.91 221	69.05 284	97.47 233	88.86 184	89.34 232	97.10 201

viewmacassd2359aftdt		89.89 169	89.01 178	92.52 139	91.56 323	82.46 144	96.32 232	94.06 325	86.41 162	88.11 185	95.01 216	69.68 280	97.47 233	88.73 194	91.19 207	97.63 144

VDDNet		86.44 261	84.51 277	92.22 162	91.56 323	81.83 172	97.10 160	94.64 269	69.50 451	87.84 190	95.19 204	48.01 441	97.92 192	89.82 167	86.92 277	96.89 218

EI-MVSNet		85.80 274	85.20 266	87.59 341	91.55 325	77.41 340	95.13 319	95.36 222	80.43 330	80.33 308	94.71 232	73.72 219	95.97 332	76.96 328	78.64 345	89.39 361

CVMVSNet		84.83 298	85.57 258	82.63 424	91.55 325	60.38 481	95.13 319	95.03 240	80.60 323	82.10 288	94.71 232	66.40 313	90.19 467	74.30 361	90.32 219	97.31 183

ACMP	81.66 11	84.00 314	83.22 308	86.33 365	91.53 327	72.95 403	95.91 269	93.79 349	83.70 261	73.79 381	92.22 294	54.31 418	96.89 293	83.98 241	79.74 334	89.16 373
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
IterMVS-LS		83.93 315	82.80 317	87.31 351	91.46 328	77.39 341	95.66 290	93.43 378	80.44 328	75.51 369	87.26 378	73.72 219	95.16 382	76.99 326	70.72 393	89.39 361
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		84.10 312	82.90 314	87.70 335	91.41 329	73.28 396	90.59 421	93.19 388	85.02 210	77.96 333	93.68 270	57.92 384	96.18 325	75.50 348	80.87 328	93.63 316

WB-MVSnew		84.08 313	83.51 302	85.80 375	91.34 330	76.69 355	95.62 293	96.27 147	81.77 303	81.81 293	92.81 285	58.23 376	94.70 406	66.66 408	87.06 276	85.99 445

Patchmatch-test		78.25 391	74.72 406	88.83 303	91.20 331	74.10 389	73.91 499	88.70 461	59.89 485	66.82 438	85.12 418	78.38 116	94.54 411	48.84 485	79.58 337	97.86 120

miper_lstm_enhance		81.66 354	80.66 348	84.67 397	91.19 332	71.97 413	91.94 402	93.19 388	77.86 377	72.27 400	85.26 412	73.46 222	93.42 433	73.71 367	67.05 430	88.61 396

ACMM	80.70 13	83.72 319	82.85 316	86.31 368	91.19 332	72.12 410	95.88 277	94.29 301	80.44 328	77.02 343	91.96 302	55.24 410	97.14 275	79.30 298	80.38 331	89.67 357
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
testing3		80.74 367	81.17 340	79.44 446	91.15 334	63.48 469	97.16 151	95.76 193	80.83 317	71.36 407	93.15 280	78.22 120	87.30 484	43.19 494	79.67 335	87.55 423

UWE-MVS-28		85.41 286	86.36 245	82.59 425	91.12 335	66.81 454	93.88 360	97.03 42	83.86 254	78.55 324	93.84 266	77.76 130	88.55 474	73.47 369	87.69 270	92.41 328

TAMVS		88.48 213	87.79 209	90.56 254	91.09 336	79.18 273	96.45 218	95.88 187	83.64 264	83.12 273	93.33 276	75.94 173	95.74 351	82.40 263	88.27 264	96.75 229

ACMH+	76.62 16	77.47 402	74.94 403	85.05 391	91.07 337	71.58 420	93.26 379	90.01 445	71.80 439	64.76 449	88.55 352	41.62 465	96.48 312	62.35 433	71.00 390	87.09 429

OpenMVS	79.58 14	86.09 269	83.62 299	93.50 85	90.95 338	86.71 37	97.44 126	95.83 190	75.35 403	72.64 396	95.72 169	57.42 394	99.64 72	71.41 381	95.85 134	94.13 307

LPG-MVS_test		84.20 311	83.49 303	86.33 365	90.88 339	73.06 399	95.28 305	94.13 319	82.20 294	76.31 354	93.20 277	54.83 414	96.95 287	83.72 247	80.83 329	88.98 388

LGP-MVS_train				86.33 365	90.88 339	73.06 399		94.13 319	82.20 294	76.31 354	93.20 277	54.83 414	96.95 287	83.72 247	80.83 329	88.98 388

test_fmvsmvis_n_1920		92.12 99	92.10 96	92.17 167	90.87 341	81.04 198	98.34 61	93.90 335	92.71 28	87.24 201	97.90 83	74.83 201	99.72 59	96.96 51	96.20 122	95.76 262

KD-MVS_2432*1600		77.63 399	74.92 404	85.77 376	90.86 342	79.44 264	88.08 444	93.92 333	76.26 397	67.05 436	82.78 438	72.15 247	91.92 448	61.53 434	41.62 502	85.94 446

miper_refine_blended		77.63 399	74.92 404	85.77 376	90.86 342	79.44 264	88.08 444	93.92 333	76.26 397	67.05 436	82.78 438	72.15 247	91.92 448	61.53 434	41.62 502	85.94 446

baseline2		90.39 155	90.21 142	90.93 241	90.86 342	80.99 201	95.20 313	97.41 18	86.03 174	80.07 313	94.61 235	90.58 7	97.47 233	87.29 214	89.86 226	94.35 302

AstraMVS		88.99 196	88.35 197	90.92 242	90.81 345	78.29 307	96.73 196	94.24 307	89.96 70	86.13 224	95.04 213	62.12 348	97.41 244	92.54 117	87.57 274	97.06 208

PVSNet_0	77.72 15	81.70 352	78.95 371	89.94 279	90.77 346	76.72 354	95.96 260	96.95 51	85.01 211	70.24 422	88.53 354	52.32 421	98.20 173	86.68 223	44.08 499	94.89 289

ACMH	75.40 17	77.99 394	74.96 402	87.10 356	90.67 347	76.41 359	93.19 382	91.64 422	72.47 433	63.44 454	87.61 373	43.34 457	97.16 269	58.34 452	73.94 372	87.72 415
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS-HIRNet		71.36 439	67.00 445	84.46 403	90.58 348	69.74 435	79.15 487	87.74 465	46.09 501	61.96 464	50.50 517	45.14 452	95.64 356	53.74 470	88.11 266	88.00 412

fmvsm_s_conf0.1_n		92.93 66	93.16 66	92.24 159	90.52 349	81.92 165	98.42 54	96.24 151	91.17 50	96.02 44	98.35 51	75.34 193	99.74 54	97.84 34	94.58 149	95.05 286

jason		92.73 74	92.23 91	94.21 48	90.50 350	87.30 31	98.65 43	95.09 236	90.61 60	92.76 97	97.13 126	75.28 194	97.30 258	93.32 100	96.75 111	98.02 101
jason: jason.
LTVRE_ROB	73.68 18	77.99 394	75.74 396	84.74 394	90.45 351	72.02 411	86.41 459	91.12 431	72.57 431	66.63 440	87.27 377	54.95 413	96.98 285	56.29 462	75.98 359	85.21 452
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
viewdifsd2359ckpt11		86.38 262	85.29 263	89.66 289	90.42 352	75.65 375	95.27 308	92.45 403	85.54 191	84.27 250	94.73 230	62.16 344	97.39 248	87.78 206	74.97 367	95.96 249

viewmsd2359difaftdt		86.38 262	85.29 263	89.67 288	90.42 352	75.65 375	95.27 308	92.45 403	85.54 191	84.28 249	94.73 230	62.16 344	97.39 248	87.78 206	74.97 367	95.96 249

XVG-OURS		85.18 291	84.38 282	87.59 341	90.42 352	71.73 418	91.06 416	94.07 324	82.00 300	83.29 271	95.08 212	56.42 402	97.55 220	83.70 249	83.42 308	93.49 319

VPA-MVSNet		85.32 288	83.83 291	89.77 286	90.25 355	82.63 136	96.36 228	97.07 39	83.03 277	81.21 297	89.02 346	61.58 354	96.31 319	85.02 234	70.95 391	90.36 342

XVG-OURS-SEG-HR		85.74 276	85.16 269	87.49 347	90.22 356	71.45 421	91.29 412	94.09 322	81.37 307	83.90 260	95.22 201	60.30 361	97.53 225	85.58 229	84.42 303	93.50 318

SD_0403		81.29 358	81.13 342	81.78 433	90.20 357	60.43 480	89.97 425	91.31 430	83.87 252	71.78 403	93.08 282	63.86 332	89.61 469	60.00 445	86.07 289	95.30 278

tpm		85.55 282	84.47 280	88.80 304	90.19 358	75.39 378	88.79 437	94.69 262	84.83 215	83.96 258	85.21 414	78.22 120	94.68 408	76.32 338	78.02 353	96.34 241

CR-MVSNet		83.53 321	81.36 338	90.06 272	90.16 359	79.75 255	79.02 488	91.12 431	84.24 240	82.27 286	80.35 460	75.45 185	93.67 429	63.37 430	86.25 284	96.75 229

RPMNet		79.85 373	75.92 393	91.64 206	90.16 359	79.75 255	79.02 488	95.44 215	58.43 491	82.27 286	72.55 491	73.03 228	98.41 164	46.10 489	86.25 284	96.75 229

test_cas_vis1_n_1920		89.90 168	90.02 150	89.54 290	90.14 361	74.63 383	98.71 40	94.43 288	93.04 26	92.40 101	96.35 154	53.41 420	99.08 125	95.59 66	96.16 123	94.90 288

FIs		86.73 259	86.10 249	88.61 308	90.05 362	80.21 239	96.14 250	96.95 51	85.56 190	78.37 327	92.30 293	76.73 153	95.28 373	79.51 292	79.27 339	90.35 343

FMVSNet5		76.46 409	74.16 412	83.35 417	90.05 362	76.17 362	89.58 429	89.85 446	71.39 442	65.29 448	80.42 459	50.61 430	87.70 482	61.05 440	69.24 408	86.18 440

0.4-1-1-0.2		87.73 237	85.82 254	93.46 90	89.97 364	85.31 70	98.49 51	96.55 109	81.24 309	87.14 204	89.63 339	76.16 167	97.02 279	86.84 221	66.38 436	98.05 99

0.3-1-1-0.015		87.79 235	85.93 251	93.38 91	89.87 365	85.09 80	98.43 52	96.55 109	81.13 311	87.21 202	89.75 336	77.23 141	97.02 279	86.87 220	66.38 436	98.02 101

IterMVS		80.67 368	79.16 368	85.20 389	89.79 366	76.08 364	92.97 385	91.86 414	80.28 336	71.20 409	85.14 417	57.93 383	91.34 456	72.52 375	70.74 392	88.18 409
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSC-MVS3.2		81.06 362	79.49 366	85.75 378	89.78 367	73.00 401	94.40 342	95.23 232	83.76 258	76.61 350	87.82 369	49.48 436	94.88 398	66.80 406	71.56 387	89.38 363

mvsany_test1		87.58 243	88.22 199	85.67 380	89.78 367	67.18 449	95.25 310	87.93 463	83.96 248	88.79 168	97.06 132	72.52 236	94.53 412	92.21 121	86.45 282	95.30 278

UniMVSNet (Re)		85.31 289	84.23 284	88.55 309	89.75 369	80.55 223	96.72 197	96.89 57	85.42 194	78.40 326	88.93 347	75.38 189	95.52 363	78.58 306	68.02 419	89.57 360

Patchmtry		77.36 403	74.59 407	85.67 380	89.75 369	75.75 374	77.85 491	91.12 431	60.28 482	71.23 408	80.35 460	75.45 185	93.56 431	57.94 453	67.34 427	87.68 417

JIA-IIPM		79.00 383	77.20 382	84.40 404	89.74 371	64.06 466	75.30 496	95.44 215	62.15 473	81.90 290	59.08 510	78.92 106	95.59 360	66.51 412	85.78 293	93.54 317

0.4-1-1-0.1		87.53 245	85.67 256	93.13 101	89.70 372	84.41 94	98.30 62	96.55 109	80.85 316	86.94 208	89.53 341	76.18 165	96.99 284	86.62 224	66.36 438	97.98 109

kuosan		73.55 423	72.39 423	77.01 459	89.68 373	66.72 455	85.24 468	93.44 376	67.76 455	60.04 473	83.40 434	71.90 253	84.25 493	45.34 491	54.75 466	80.06 488

MS-PatchMatch		83.05 330	81.82 331	86.72 363	89.64 374	79.10 277	94.88 329	94.59 274	79.70 350	70.67 414	89.65 338	50.43 431	96.82 299	70.82 390	95.99 132	84.25 461

IterMVS-SCA-FT		80.51 370	79.10 369	84.73 395	89.63 375	74.66 382	92.98 384	91.81 416	80.05 343	71.06 412	85.18 415	58.04 379	91.40 455	72.48 376	70.70 394	88.12 410

mmtdpeth		78.04 393	76.76 387	81.86 432	89.60 376	66.12 457	92.34 397	87.18 467	76.83 393	85.55 231	76.49 479	46.77 448	97.02 279	90.85 144	45.24 496	82.43 474

Fast-Effi-MVS+-dtu		83.33 324	82.60 320	85.50 384	89.55 377	69.38 439	96.09 253	91.38 425	82.30 293	75.96 363	91.41 309	56.71 398	95.58 361	75.13 353	84.90 300	91.54 331

PatchT		79.75 374	76.85 386	88.42 310	89.55 377	75.49 377	77.37 492	94.61 272	63.07 468	82.46 280	73.32 488	75.52 184	93.41 434	51.36 476	84.43 302	96.36 239

GA-MVS		85.79 275	84.04 290	91.02 239	89.47 379	80.27 236	96.90 180	94.84 251	85.57 188	80.88 299	89.08 344	56.56 401	96.47 313	77.72 316	85.35 297	96.34 241

UniMVSNet_NR-MVSNet		85.49 283	84.59 276	88.21 324	89.44 380	79.36 267	96.71 199	96.41 129	85.22 199	78.11 330	90.98 318	76.97 148	95.14 385	79.14 300	68.30 416	90.12 349

FC-MVSNet-test		85.96 271	85.39 261	87.66 338	89.38 381	78.02 318	95.65 291	96.87 59	85.12 207	77.34 336	91.94 305	76.28 164	94.74 405	77.09 325	78.82 343	90.21 346

WR-MVS		84.32 309	82.96 312	88.41 311	89.38 381	80.32 233	96.59 205	96.25 150	83.97 247	76.63 348	90.36 328	67.53 299	94.86 400	75.82 343	70.09 400	90.06 353

VPNet		84.69 300	82.92 313	90.01 274	89.01 383	83.45 118	96.71 199	95.46 213	85.71 185	79.65 315	92.18 297	56.66 400	96.01 331	83.05 259	67.84 422	90.56 340

Elysia		85.62 279	83.66 295	91.51 212	88.76 384	82.21 154	95.15 317	94.70 258	76.96 391	84.13 252	92.20 295	50.81 427	97.26 262	77.81 311	92.42 186	95.06 284

StellarMVS		85.62 279	83.66 295	91.51 212	88.76 384	82.21 154	95.15 317	94.70 258	76.96 391	84.13 252	92.20 295	50.81 427	97.26 262	77.81 311	92.42 186	95.06 284

nrg030		86.79 257	85.43 260	90.87 246	88.76 384	85.34 67	97.06 164	94.33 299	84.31 234	80.45 306	91.98 301	72.36 239	96.36 317	88.48 199	71.13 389	90.93 337

DU-MVS		84.57 305	83.33 305	88.28 317	88.76 384	79.36 267	96.43 221	95.41 221	85.42 194	78.11 330	90.82 319	67.61 296	95.14 385	79.14 300	68.30 416	90.33 344

NR-MVSNet		83.35 323	81.52 336	88.84 302	88.76 384	81.31 191	94.45 338	95.16 234	84.65 221	67.81 432	90.82 319	70.36 274	94.87 399	74.75 355	66.89 432	90.33 344

test_0402		72.68 429	69.54 437	82.09 430	88.67 389	71.81 417	92.72 389	86.77 472	61.52 476	62.21 462	83.91 429	43.22 458	93.76 428	34.60 505	72.23 385	80.72 487

RPSCF		77.73 398	76.63 388	81.06 437	88.66 390	55.76 494	87.77 448	87.88 464	64.82 465	74.14 380	92.79 287	49.22 437	96.81 300	67.47 403	76.88 355	90.62 339

LuminaMVS		88.02 228	86.89 237	91.43 218	88.65 391	83.16 124	94.84 330	94.41 290	83.67 262	86.56 218	91.95 304	62.04 349	96.88 295	89.78 168	90.06 222	94.24 303

FMVSNet1		79.50 378	76.54 389	88.39 313	88.47 392	81.95 162	94.30 347	93.38 380	73.14 423	72.04 402	85.66 404	43.86 454	93.84 425	65.48 416	72.53 381	89.38 363

test_fmvsmconf0.1_n		93.08 62	93.22 65	92.65 128	88.45 393	80.81 213	99.00 28	95.11 235	93.21 24	94.00 78	97.91 82	76.84 149	99.59 78	97.91 29	96.55 116	97.54 153

MonoMVSNet		85.68 277	84.22 285	90.03 273	88.43 394	77.83 328	92.95 386	91.46 424	87.28 131	78.11 330	85.96 403	66.31 314	94.81 402	90.71 149	76.81 356	97.46 165

OPM-MVS		85.84 273	85.10 271	88.06 328	88.34 395	77.83 328	95.72 285	94.20 315	87.89 110	80.45 306	94.05 257	58.57 373	97.26 262	83.88 242	82.76 318	89.09 375
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tfpnnormal		78.14 392	75.42 400	86.31 368	88.33 396	79.24 270	94.41 339	96.22 153	73.51 419	69.81 425	85.52 410	55.43 408	95.75 348	47.65 487	67.86 421	83.95 464

TinyColmap		72.41 431	68.99 440	82.68 422	88.11 397	69.59 436	88.41 440	85.20 478	65.55 462	57.91 480	84.82 422	30.80 491	95.94 336	51.38 475	68.70 411	82.49 473

fmvsm_s_conf0.1_n_a		92.38 93	92.49 82	92.06 175	88.08 398	81.62 183	97.97 83	96.01 170	90.62 59	96.58 35	98.33 52	74.09 213	99.71 62	97.23 46	93.46 171	94.86 290

WR-MVS_H		81.02 363	80.09 355	83.79 409	88.08 398	71.26 424	94.46 337	96.54 112	80.08 342	72.81 395	86.82 385	70.36 274	92.65 438	64.18 423	67.50 425	87.46 425

CP-MVSNet		81.01 364	80.08 356	83.79 409	87.91 400	70.51 427	94.29 351	95.65 200	80.83 317	72.54 398	88.84 348	63.71 333	92.32 443	68.58 400	68.36 415	88.55 397

D2MVS		82.67 337	81.55 334	86.04 373	87.77 401	76.47 356	95.21 312	96.58 105	82.66 287	70.26 420	85.46 411	60.39 360	95.80 343	76.40 336	79.18 340	85.83 448

TranMVSNet+NR-MVSNet		83.24 327	81.71 332	87.83 332	87.71 402	78.81 286	96.13 252	94.82 252	84.52 227	76.18 360	90.78 321	64.07 331	94.60 410	74.60 359	66.59 435	90.09 351

USDC		78.65 389	76.25 390	85.85 374	87.58 403	74.60 384	89.58 429	90.58 442	84.05 244	63.13 456	88.23 362	40.69 473	96.86 298	66.57 411	75.81 362	86.09 442

PS-CasMVS		80.27 371	79.18 367	83.52 415	87.56 404	69.88 433	94.08 354	95.29 229	80.27 337	72.08 401	88.51 355	59.22 370	92.23 445	67.49 402	68.15 418	88.45 403

test_fmvs1_n		86.34 265	86.72 240	85.17 390	87.54 405	63.64 468	96.91 179	92.37 407	87.49 123	91.33 122	95.58 181	40.81 472	98.46 159	95.00 75	93.49 169	93.41 322

MIMVSNet		79.18 382	75.99 392	88.72 306	87.37 406	80.66 217	79.96 482	91.82 415	77.38 383	74.33 379	81.87 449	41.78 464	90.74 462	66.36 414	83.10 311	94.76 293

XXY-MVS		83.84 316	82.00 328	89.35 292	87.13 407	81.38 188	95.72 285	94.26 305	80.15 339	75.92 364	90.63 323	61.96 352	96.52 311	78.98 303	73.28 378	90.14 348

ITE_SJBPF				82.38 427	87.00 408	65.59 458		89.55 449	79.99 345	69.37 427	91.30 312	41.60 466	95.33 370	62.86 432	74.63 371	86.24 439

dongtai		69.47 445	68.98 441	70.93 471	86.87 409	58.45 486	88.19 442	93.18 390	63.98 466	56.04 485	80.17 462	70.97 267	79.24 500	33.46 507	47.94 492	75.09 495

test0.0.03 1		82.79 335	82.48 321	83.74 411	86.81 410	72.22 405	96.52 212	95.03 240	83.76 258	73.00 392	93.20 277	72.30 242	88.88 472	64.15 424	77.52 354	90.12 349

v8		81.88 349	80.06 358	87.32 350	86.63 411	79.04 280	94.41 339	93.65 364	78.77 368	73.19 391	85.57 408	66.87 308	95.81 342	73.84 366	67.61 424	87.11 428

usedtu_dtu_shiyan1		85.03 293	83.24 306	90.37 261	86.62 412	86.24 41	96.23 240	95.30 227	84.55 225	77.22 339	88.47 356	67.85 292	95.27 374	76.59 331	76.35 357	89.61 358

FE-MVSNET3		85.03 293	83.24 306	90.37 261	86.62 412	86.24 41	96.23 240	95.30 227	84.55 225	77.22 339	88.47 356	67.85 292	95.27 374	76.59 331	76.35 357	89.61 358

tt0805		81.20 361	79.06 370	87.61 339	86.50 414	72.97 402	93.66 364	95.48 211	74.11 414	76.23 358	91.99 300	41.36 468	97.40 246	77.44 323	74.78 369	92.45 327

v10		81.43 356	79.53 365	87.11 355	86.38 415	78.87 282	94.31 346	93.43 378	77.88 376	73.24 390	85.26 412	65.44 318	95.75 348	72.14 377	67.71 423	86.72 432

PEN-MVS		79.47 379	78.26 375	83.08 418	86.36 416	68.58 442	93.85 362	94.77 256	79.76 348	71.37 406	88.55 352	59.79 362	92.46 439	64.50 421	65.40 440	88.19 408

UniMVSNet_ETH3D		80.86 366	78.75 372	87.22 354	86.31 417	72.02 411	91.95 401	93.76 355	73.51 419	75.06 375	90.16 332	43.04 460	95.66 353	76.37 337	78.55 348	93.98 310

v1144		82.90 334	81.27 339	87.78 334	86.29 418	79.07 279	96.14 250	93.93 331	80.05 343	77.38 335	86.80 386	65.50 317	95.93 337	75.21 352	70.13 397	88.33 406

V42		83.04 331	81.53 335	87.57 343	86.27 419	79.09 278	95.87 278	94.11 321	80.35 334	77.22 339	86.79 387	65.32 321	96.02 330	77.74 315	70.14 396	87.61 419

v2v482		83.46 322	81.86 330	88.25 320	86.19 420	79.65 260	96.34 230	94.02 328	81.56 306	77.32 337	88.23 362	65.62 316	96.03 329	77.77 314	69.72 404	89.09 375

v148		82.41 343	80.89 343	86.99 357	86.18 421	76.81 352	96.27 235	93.82 344	80.49 327	75.28 372	86.11 402	67.32 303	95.75 348	75.48 349	67.03 431	88.42 404

dtuonly		84.63 302	84.08 289	86.30 370	86.14 422	69.59 436	92.71 390	90.28 443	82.00 300	80.87 300	94.51 238	62.61 340	96.18 325	79.00 302	88.60 249	93.14 323

pmmvs4		82.54 339	80.79 344	87.79 333	86.11 423	80.49 231	93.55 369	93.18 390	77.29 384	73.35 388	89.40 343	65.26 322	95.05 395	75.32 351	73.61 374	87.83 414

MVP-Stereo		82.65 338	81.67 333	85.59 383	86.10 424	78.29 307	93.33 375	92.82 398	77.75 378	69.17 429	87.98 366	59.28 369	95.76 347	71.77 378	96.88 104	82.73 470
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		82.31 344	80.55 350	87.60 340	85.94 425	78.47 302	95.85 280	93.80 348	79.33 356	76.97 344	86.51 390	63.33 337	95.87 339	73.11 371	70.13 397	88.46 402

TransMVSNet (Re)		76.94 406	74.38 409	84.62 399	85.92 426	75.25 379	95.28 305	89.18 454	73.88 417	67.22 433	86.46 392	59.64 363	94.10 420	59.24 450	52.57 482	84.50 459

PS-MVSNAJss		84.91 297	84.30 283	86.74 359	85.89 427	74.40 387	94.95 327	94.16 318	83.93 250	76.45 352	90.11 334	71.04 264	95.77 346	83.16 257	79.02 342	90.06 353

v144192		82.43 340	80.73 346	87.54 344	85.81 428	78.22 311	95.98 259	93.78 350	79.09 363	77.11 342	86.49 391	64.66 330	95.91 338	74.20 362	69.42 405	88.49 400

v1921920		82.02 347	80.23 354	87.41 348	85.62 429	77.92 324	95.79 284	93.69 362	78.86 367	76.67 347	86.44 393	62.50 341	95.83 341	72.69 373	69.77 403	88.47 401

v1240		81.70 352	79.83 362	87.30 352	85.50 430	77.70 336	95.48 298	93.44 376	78.46 372	76.53 351	86.44 393	60.85 359	95.84 340	71.59 380	70.17 395	88.35 405

pm-mvs1		80.05 372	78.02 377	86.15 371	85.42 431	75.81 373	95.11 321	92.69 401	77.13 386	70.36 416	87.43 374	58.44 375	95.27 374	71.36 382	64.25 445	87.36 426

our_test_3		77.90 397	75.37 401	85.48 385	85.39 432	76.74 353	93.63 365	91.67 420	73.39 422	65.72 445	84.65 423	58.20 378	93.13 436	57.82 454	67.87 420	86.57 435

ppachtmachnet_test		77.19 404	74.22 411	86.13 372	85.39 432	78.22 311	93.98 355	91.36 427	71.74 440	67.11 435	84.87 421	56.67 399	93.37 435	52.21 473	64.59 442	86.80 431

MDA-MVSNet-bldmvs		71.45 437	67.94 444	81.98 431	85.33 434	68.50 443	92.35 396	88.76 459	70.40 445	42.99 500	81.96 448	46.57 449	91.31 457	48.75 486	54.39 470	86.11 441

Baseline_NR-MVSNet		81.22 360	80.07 357	84.68 396	85.32 435	75.12 380	96.48 215	88.80 458	76.24 399	77.28 338	86.40 396	67.61 296	94.39 416	75.73 344	66.73 433	84.54 458

DTE-MVSNet		78.37 390	77.06 384	82.32 429	85.22 436	67.17 452	93.40 371	93.66 363	78.71 369	70.53 415	88.29 361	59.06 371	92.23 445	61.38 437	63.28 450	87.56 421

pmmvs5		81.34 357	79.54 364	86.73 362	85.02 437	76.91 349	96.22 242	91.65 421	77.65 379	73.55 383	88.61 351	55.70 407	94.43 415	74.12 363	73.35 377	88.86 394

XVG-ACMP-BASELINE		79.38 380	77.90 378	83.81 408	84.98 438	67.14 453	89.03 435	93.18 390	80.26 338	72.87 394	88.15 364	38.55 474	96.26 320	76.05 340	78.05 352	88.02 411

test_vis1_n		85.60 281	85.70 255	85.33 387	84.79 439	64.98 460	96.83 184	91.61 423	87.36 129	91.00 129	94.84 228	36.14 479	97.18 268	95.66 64	93.03 176	93.82 313

MDA-MVSNet_test_wron		73.54 424	70.43 433	82.86 420	84.55 440	71.85 415	91.74 407	91.32 429	67.63 456	46.73 497	81.09 456	55.11 411	90.42 466	55.91 464	59.76 456	86.31 438

SixPastTwentyTwo		76.04 410	74.32 410	81.22 435	84.54 441	61.43 478	91.16 414	89.30 453	77.89 375	64.04 451	86.31 397	48.23 439	94.29 418	63.54 429	63.84 448	87.93 413

YYNet1		73.53 425	70.43 433	82.85 421	84.52 442	71.73 418	91.69 408	91.37 426	67.63 456	46.79 496	81.21 455	55.04 412	90.43 465	55.93 463	59.70 457	86.38 437

tt0320-xc		69.70 442	65.27 454	82.99 419	84.33 443	71.92 414	89.56 431	82.08 493	50.11 498	61.87 465	77.50 471	30.48 493	92.34 442	60.30 443	51.20 484	84.71 456

N_pmnet		61.30 458	60.20 461	64.60 481	84.32 444	17.00 536	91.67 409	10.98 536	61.77 475	58.45 479	78.55 467	49.89 434	91.83 451	42.27 496	63.94 447	84.97 454

mvs_tets		81.74 351	80.71 347	84.84 393	84.22 445	70.29 430	93.91 359	93.78 350	82.77 284	73.37 387	89.46 342	47.36 447	95.31 372	81.99 268	79.55 338	88.92 392

jajsoiax		82.12 346	81.15 341	85.03 392	84.19 446	70.70 426	94.22 352	93.95 329	83.07 274	73.48 384	89.75 336	49.66 435	95.37 368	82.24 267	79.76 332	89.02 385

EU-MVSNet		76.92 407	76.95 385	76.83 461	84.10 447	54.73 496	91.77 406	92.71 400	72.74 427	69.57 426	88.69 350	58.03 381	87.43 483	64.91 419	70.00 401	88.33 406

test_djsdf		83.00 333	82.45 322	84.64 398	84.07 448	69.78 434	94.80 333	94.48 279	80.74 320	75.41 371	87.70 370	61.32 358	95.10 388	83.77 245	79.76 332	89.04 381

v7n		79.32 381	77.34 381	85.28 388	84.05 449	72.89 404	93.38 372	93.87 337	75.02 408	70.68 413	84.37 424	59.58 365	95.62 358	67.60 401	67.50 425	87.32 427

test_vis1_rt		73.96 419	72.40 422	78.64 452	83.91 450	61.16 479	95.63 292	68.18 509	76.32 396	60.09 472	74.77 482	29.01 495	97.54 223	87.74 208	75.94 360	77.22 492

dmvs_testset		72.00 436	73.36 418	67.91 475	83.83 451	31.90 521	85.30 467	77.12 501	82.80 283	63.05 458	92.46 290	61.54 355	82.55 498	42.22 497	71.89 386	89.29 368

sc_t1		72.37 432	68.03 443	85.39 386	83.78 452	70.51 427	91.27 413	83.70 489	52.46 497	68.29 430	82.02 447	30.58 492	94.81 402	64.50 421	55.69 464	90.85 338

OurMVSNet-221017-0		77.18 405	76.06 391	80.55 440	83.78 452	60.00 483	90.35 422	91.05 434	77.01 390	66.62 441	87.92 367	47.73 445	94.03 421	71.63 379	68.44 414	87.62 418

EG-PatchMatch MVS		74.92 416	72.02 424	83.62 413	83.76 454	73.28 396	93.62 366	92.04 413	68.57 454	58.88 477	83.80 430	31.87 489	95.57 362	56.97 460	78.67 344	82.00 479

tt0320		70.21 441	66.07 449	82.64 423	83.42 455	70.82 425	89.63 427	84.10 485	49.75 500	62.71 460	77.28 474	33.35 485	92.45 441	58.78 451	55.62 465	84.64 457

K. test v3		73.62 421	71.59 426	79.69 444	82.98 456	59.85 484	90.85 418	88.83 457	77.13 386	58.90 476	82.11 445	43.62 455	91.72 453	65.83 415	54.10 471	87.50 424

test_fmvs2		79.59 376	79.90 361	78.67 451	82.86 457	55.82 493	95.20 313	89.55 449	81.09 312	80.12 312	89.80 335	34.31 484	93.51 432	87.82 205	78.36 350	86.69 433

test_fmvsmconf0.01_n		91.08 130	90.68 126	92.29 156	82.43 458	80.12 244	97.94 84	93.93 331	92.07 39	91.97 111	97.60 101	67.56 298	99.53 86	97.09 49	95.56 139	97.21 191

EGC-MVSNET		52.46 468	47.56 471	67.15 477	81.98 459	60.11 482	82.54 478	72.44 505	0.11 558	0.70 560	74.59 483	25.11 496	83.26 495	29.04 512	61.51 454	58.09 509

anonymousdsp		80.98 365	79.97 359	84.01 406	81.73 460	70.44 429	92.49 392	93.58 371	77.10 388	72.98 393	86.31 397	57.58 390	94.90 397	79.32 297	78.63 347	86.69 433

dtuonlycased		72.49 430	71.58 427	75.22 467	81.04 461	64.71 461	92.43 394	86.46 474	75.62 402	59.79 474	78.43 468	48.54 438	85.84 489	63.66 428	58.28 458	75.10 494

Anonymous20231206		75.29 415	73.64 416	80.22 442	80.75 462	63.38 470	93.36 373	90.71 441	73.09 424	67.12 434	83.70 431	50.33 432	90.85 461	53.63 471	70.10 399	86.44 436

Gipuma		45.11 474	42.05 475	54.30 493	80.69 463	51.30 498	35.80 521	83.81 488	28.13 511	27.94 516	34.53 526	11.41 511	76.70 507	21.45 522	54.65 467	34.90 526
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
lessismore_v0				79.98 443	80.59 464	58.34 487		80.87 495		58.49 478	83.46 433	43.10 459	93.89 424	63.11 431	48.68 489	87.72 415

OpenMVS_ROB	68.52 20	73.02 428	69.57 436	83.37 416	80.54 465	71.82 416	93.60 368	88.22 462	62.37 471	61.98 463	83.15 437	35.31 483	95.47 364	45.08 492	75.88 361	82.82 468

gbinet_0.2-2-1-0.02		78.67 388	75.67 397	87.70 335	80.38 466	79.60 262	96.25 238	94.03 327	72.51 432	71.41 405	83.33 435	55.97 406	94.45 414	73.37 370	53.73 477	89.04 381

testgi		74.88 417	73.40 417	79.32 447	80.13 467	61.75 475	93.21 380	86.64 473	79.49 354	66.56 442	91.06 315	35.51 482	88.67 473	56.79 461	71.25 388	87.56 421

blend_shiyan4		81.76 350	79.58 363	88.31 316	80.00 468	80.59 219	95.95 261	93.73 358	72.26 436	71.14 410	82.52 440	76.13 168	95.15 383	77.83 309	66.62 434	89.19 371

wanda-best-256-512		78.87 384	75.75 394	88.22 322	79.74 469	80.51 229	95.92 264	93.75 356	72.60 429	70.34 417	82.14 441	57.91 385	95.09 390	75.61 345	53.77 473	89.05 378

FE-blended-shiyan7		78.87 384	75.75 394	88.22 322	79.74 469	80.51 229	95.92 264	93.75 356	72.60 429	70.34 417	82.14 441	57.91 385	95.09 390	75.61 345	53.77 473	89.05 378

usedtu_blend_shiyan5		77.51 401	73.93 415	88.26 318	79.74 469	80.59 219	90.76 419	89.69 447	63.21 467	70.34 417	82.14 441	57.91 385	95.15 383	77.83 309	53.77 473	89.05 378

CMPMVS	54.94 21	75.71 414	74.56 408	79.17 448	79.69 472	55.98 491	89.59 428	93.30 385	60.28 482	53.85 489	89.07 345	47.68 446	96.33 318	76.55 333	81.02 327	85.22 451
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
blended_shiyan6		78.74 387	75.63 399	88.07 327	79.63 473	80.10 245	95.72 285	93.73 358	72.43 434	70.17 423	82.09 446	57.69 388	95.07 393	75.47 350	53.77 473	89.03 383

blended_shiyan8		78.76 386	75.65 398	88.10 326	79.58 474	80.20 240	95.70 288	93.71 361	72.43 434	70.26 420	82.12 444	57.66 389	95.08 392	75.57 347	53.80 472	89.02 385

LF4IMVS		72.36 433	70.82 429	76.95 460	79.18 475	56.33 490	86.12 461	86.11 476	69.30 452	63.06 457	86.66 388	33.03 487	92.25 444	65.33 417	68.64 412	82.28 475

pmmvs6		74.65 418	71.67 425	83.60 414	79.13 476	69.94 432	93.31 378	90.88 438	61.05 481	65.83 444	84.15 427	43.43 456	94.83 401	66.62 409	60.63 455	86.02 444

MVStest1		66.93 453	63.01 457	78.69 450	78.56 477	71.43 422	85.51 466	86.81 470	49.79 499	48.57 495	84.15 427	53.46 419	83.31 494	43.14 495	37.15 505	81.34 485

DeepMVS_CX				64.06 482	78.53 478	43.26 509		68.11 511	69.94 449	38.55 502	76.14 480	18.53 501	79.34 499	43.72 493	41.62 502	69.57 499

CL-MVSNet_self_test		75.81 412	74.14 413	80.83 439	78.33 479	67.79 446	94.22 352	93.52 373	77.28 385	69.82 424	81.54 452	61.47 357	89.22 471	57.59 456	53.51 478	85.48 450

test20.03		72.36 433	71.15 428	75.98 465	77.79 480	59.16 485	92.40 395	89.35 452	74.09 415	61.50 466	84.32 425	48.09 440	85.54 491	50.63 479	62.15 453	83.24 465

UnsupCasMVSNet_eth		73.25 426	70.57 432	81.30 434	77.53 481	66.33 456	87.24 452	93.89 336	80.38 331	57.90 481	81.59 450	42.91 461	90.56 463	65.18 418	48.51 490	87.01 430

DSMNet-mixed		73.13 427	72.45 421	75.19 468	77.51 482	46.82 501	85.09 469	82.01 494	67.61 460	69.27 428	81.33 454	50.89 426	86.28 487	54.54 468	83.80 305	92.46 326

Patchmatch-RL test		76.65 408	74.01 414	84.55 400	77.37 483	64.23 464	78.49 490	82.84 492	78.48 371	64.63 450	73.40 487	76.05 170	91.70 454	76.99 326	57.84 460	97.72 134

Anonymous20240521		72.06 435	69.91 435	78.50 453	77.11 484	61.67 477	91.62 410	90.97 436	65.52 463	62.37 461	79.05 466	36.32 478	90.96 460	57.75 455	68.52 413	82.87 467

test_method		56.77 462	54.53 466	63.49 483	76.49 485	40.70 511	75.68 495	74.24 503	19.47 521	48.73 494	71.89 493	19.31 500	65.80 516	57.46 457	47.51 494	83.97 463

MIMVSNet1		69.44 446	66.65 448	77.84 454	76.48 486	62.84 472	87.42 450	88.97 456	66.96 461	57.75 483	79.72 465	32.77 488	85.83 490	46.32 488	63.42 449	84.85 455

pmmvs-eth3d		73.59 422	70.66 431	82.38 427	76.40 487	73.38 393	89.39 433	89.43 451	72.69 428	60.34 471	77.79 470	46.43 450	91.26 458	66.42 413	57.06 462	82.51 471

new_pmnet		66.18 454	63.18 456	75.18 469	76.27 488	61.74 476	83.79 474	84.66 481	56.64 493	51.57 492	71.85 494	31.29 490	87.93 478	49.98 481	62.55 451	75.86 493

KD-MVS_self_test		70.97 440	69.31 438	75.95 466	76.24 489	55.39 495	87.45 449	90.94 437	70.20 448	62.96 459	77.48 472	44.01 453	88.09 477	61.25 438	53.26 479	84.37 460

ttmdpeth		69.58 443	66.92 447	77.54 457	75.95 490	62.40 473	88.09 443	84.32 484	62.87 470	65.70 446	86.25 399	36.53 477	88.53 475	55.65 466	46.96 495	81.70 482

mvs5depth		71.40 438	68.36 442	80.54 441	75.31 491	65.56 459	79.94 483	85.14 479	69.11 453	71.75 404	81.59 450	41.02 470	93.94 423	60.90 441	50.46 485	82.10 476

FE-MVSNET2		73.72 420	70.80 430	82.46 426	74.97 492	73.81 391	91.88 404	91.73 419	76.70 394	59.74 475	77.41 473	42.26 463	90.52 464	64.75 420	57.79 461	83.06 466

UnsupCasMVSNet_bld		68.60 451	64.50 455	80.92 438	74.63 493	67.80 445	83.97 473	92.94 397	65.12 464	54.63 488	68.23 498	35.97 480	92.17 447	60.13 444	44.83 497	82.78 469

FE-MVSNET		69.26 448	66.03 450	78.93 449	73.82 494	68.33 444	89.65 426	84.06 486	70.21 447	57.79 482	76.94 478	41.48 467	86.98 486	45.85 490	54.51 469	81.48 484

PM-MVS		69.32 447	66.93 446	76.49 462	73.60 495	55.84 492	85.91 462	79.32 499	74.72 410	61.09 468	78.18 469	21.76 499	91.10 459	70.86 388	56.90 463	82.51 471

new-patchmatchnet		68.85 450	65.93 451	77.61 456	73.57 496	63.94 467	90.11 424	88.73 460	71.62 441	55.08 487	73.60 486	40.84 471	87.22 485	51.35 477	48.49 491	81.67 483

ArgMatch-Sym		59.60 460	56.89 463	67.74 476	71.40 497	45.64 506	81.24 480	58.34 517	58.65 490	52.79 491	81.51 453	11.35 512	76.76 505	60.83 442	35.86 507	80.81 486

ArgMatch-SfM		60.14 459	57.35 462	68.50 474	71.14 498	45.17 508	80.16 481	63.06 513	59.74 487	51.33 493	80.81 457	11.74 510	78.30 501	61.13 439	37.05 506	82.04 478

WB-MVS		57.26 461	56.22 464	60.39 488	69.29 499	35.91 517	86.39 460	70.06 507	59.84 486	46.46 498	72.71 489	51.18 425	78.11 502	15.19 527	34.89 508	67.14 502

test_fmvs3		69.56 444	69.19 439	70.67 472	69.01 500	47.05 500	90.87 417	86.81 470	71.31 443	66.79 439	77.15 475	16.40 503	83.17 496	81.84 269	62.51 452	81.79 481

SSC-MVS		56.01 464	54.96 465	59.17 489	68.42 501	34.13 518	84.98 470	69.23 508	58.08 492	45.36 499	71.67 495	50.30 433	77.46 503	14.28 528	32.33 509	65.91 504

ambc				76.02 464	68.11 502	51.43 497	64.97 507	89.59 448		60.49 470	74.49 484	17.17 502	92.46 439	61.50 436	52.85 481	84.17 462

APD_test1		56.56 463	53.58 467	65.50 478	67.93 503	46.51 503	77.24 494	72.95 504	38.09 503	42.75 501	75.17 481	13.38 506	82.78 497	40.19 500	54.53 468	67.23 501

pmmvs3		65.75 455	62.18 458	76.45 463	67.12 504	64.54 462	88.68 438	85.05 480	54.77 495	57.54 484	73.79 485	29.40 494	86.21 488	55.49 467	47.77 493	78.62 490

TDRefinement		69.20 449	65.78 452	79.48 445	66.04 505	62.21 474	88.21 441	86.12 475	62.92 469	61.03 469	85.61 407	33.23 486	94.16 419	55.82 465	53.02 480	82.08 477

usedtu_dtu_shiyan2		64.65 456	60.40 460	77.38 458	64.24 506	57.84 488	89.16 434	87.60 466	52.95 496	53.43 490	71.31 497	23.41 497	88.27 476	51.95 474	49.58 487	86.03 443

mvsany_test3		67.19 452	65.34 453	72.72 470	63.08 507	48.57 499	83.12 476	78.09 500	72.07 437	61.21 467	77.11 476	22.94 498	87.78 481	78.59 305	51.88 483	81.80 480

test_f		64.01 457	62.13 459	69.65 473	63.00 508	45.30 507	83.66 475	80.68 496	61.30 478	55.70 486	72.62 490	14.23 505	84.64 492	69.84 393	58.11 459	79.00 489

DenseAffine		43.98 475	39.51 479	57.39 490	60.41 509	37.29 515	67.44 506	34.50 525	35.36 506	31.38 511	65.55 500	4.21 523	67.77 514	35.59 503	21.11 517	67.10 503

LoFTR		45.13 473	39.91 478	60.78 487	58.50 510	33.07 519	59.69 511	57.64 518	30.48 510	25.92 519	63.30 502	4.30 522	74.96 509	28.23 519	31.12 511	74.31 496

test_vis3_rt		54.10 466	51.04 469	63.27 484	58.16 511	46.08 505	84.17 472	49.32 523	56.48 494	36.56 504	49.48 520	8.03 515	91.91 450	67.29 404	49.87 486	51.82 517

FPMVS		55.09 465	52.93 468	61.57 485	55.98 512	40.51 512	83.11 477	83.41 491	37.61 504	34.95 506	71.95 492	14.40 504	76.95 504	29.81 511	65.16 441	67.25 500

PMMVS2		50.90 469	46.31 472	64.67 480	55.53 513	46.67 502	77.30 493	71.02 506	40.89 502	34.16 507	59.32 509	9.83 513	76.14 508	40.09 501	28.63 512	71.21 497

wuyk23d		14.10 499	13.89 502	14.72 516	55.23 514	22.91 531	33.83 522	3.56 554	4.94 533	4.11 543	2.28 558	2.06 540	19.66 536	10.23 532	8.74 541	1.59 556

E-PMN		32.70 486	32.39 485	33.65 507	53.35 515	25.70 527	74.07 498	53.33 520	21.08 519	17.17 528	33.63 528	11.85 509	54.84 521	12.98 530	14.04 523	20.42 531

testf1		45.70 471	42.41 473	55.58 491	53.29 516	40.02 513	68.96 504	62.67 514	27.45 512	29.85 513	61.58 506	5.98 519	73.83 511	28.49 516	43.46 500	52.90 513

APD_test2		45.70 471	42.41 473	55.58 491	53.29 516	40.02 513	68.96 504	62.67 514	27.45 512	29.85 513	61.58 506	5.98 519	73.83 511	28.49 516	43.46 500	52.90 513

MatchFormer		39.45 478	34.61 482	54.00 494	53.28 518	28.79 525	58.06 514	51.35 522	21.48 517	23.10 522	55.83 514	3.50 527	70.37 513	19.01 524	25.84 514	62.84 505

RoMa-SfM		40.68 477	36.49 480	53.24 495	52.27 519	33.01 520	62.88 508	23.78 530	32.85 507	31.33 512	67.39 499	3.87 524	64.89 517	33.77 506	20.24 519	61.82 507

EMVS		31.70 487	31.45 488	32.48 508	50.72 520	23.95 530	74.78 497	52.30 521	20.36 520	16.08 529	31.48 529	12.80 507	53.60 523	11.39 531	13.10 528	19.88 533

DKM		38.02 480	33.59 484	51.32 496	50.45 521	30.46 522	61.04 510	19.18 531	30.65 509	26.88 517	61.89 505	2.55 533	61.16 518	32.68 508	16.95 520	62.34 506

PDCNetPlus		37.10 481	34.54 483	44.76 499	50.06 522	29.19 524	58.72 513	23.89 529	37.05 505	24.11 521	58.95 511	6.11 518	55.29 520	40.76 499	11.21 536	49.81 518

LCM-MVSNet		52.52 467	48.24 470	65.35 479	47.63 523	41.45 510	72.55 500	83.62 490	31.75 508	37.66 503	57.92 512	9.19 514	76.76 505	49.26 483	44.60 498	77.84 491

DKM-HiRes		32.92 485	29.13 491	44.31 500	42.93 524	25.35 528	53.22 515	13.26 534	25.92 515	24.31 520	57.58 513	1.88 542	50.95 525	28.87 513	14.19 522	56.63 512

ALIKED-LG		17.53 496	16.82 499	19.64 513	42.07 525	19.09 532	31.53 524	11.93 535	7.76 529	10.68 533	26.90 532	3.52 526	22.14 532	3.10 541	13.89 524	17.68 534

MVE	35.65 22	33.85 482	29.49 490	46.92 498	41.86 526	36.28 516	50.45 517	56.52 519	18.75 522	18.28 525	37.84 524	2.41 536	58.41 519	18.71 525	20.62 518	46.06 522
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
RoMa-HiRes		33.28 484	29.63 489	44.22 501	41.01 527	25.30 529	51.82 516	14.13 533	25.85 516	26.34 518	61.96 504	2.78 531	54.52 522	28.42 518	14.36 521	52.83 516

ALIKED-MNN		16.35 497	15.48 501	18.95 514	40.20 528	19.09 532	30.16 526	10.63 538	6.03 530	9.48 536	24.90 534	2.59 532	21.29 533	2.88 543	12.46 530	16.48 535

ANet_high		46.22 470	41.28 477	61.04 486	39.91 529	46.25 504	70.59 503	76.18 502	58.87 489	23.09 523	48.00 522	12.58 508	66.54 515	28.65 515	13.62 525	70.35 498

ALIKED-NN		16.22 498	15.63 500	17.99 515	39.36 530	18.31 534	29.26 528	10.71 537	5.97 531	10.10 534	26.06 533	2.80 530	20.08 535	2.91 542	13.46 526	15.60 537

MVS_clip		23.81 493	25.14 494	19.82 512	33.23 531	11.41 541	26.86 529	4.32 548	5.29 532	31.51 510	63.24 503	7.08 517	7.43 544	28.82 514	25.90 513	40.62 524

MASt3R-SfM		33.79 483	32.03 486	39.08 504	30.86 532	18.05 535	44.70 518	25.59 528	21.32 518	31.97 509	71.52 496	3.78 525	38.14 530	35.97 502	22.58 516	61.06 508

PMVS	34.80 23	39.19 479	35.53 481	50.18 497	29.72 533	30.30 523	59.60 512	66.20 512	26.06 514	17.91 527	49.53 519	3.12 528	74.09 510	18.19 526	49.40 488	46.14 521
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GLUNet-SfM		23.82 492	18.93 497	38.50 505	29.22 534	15.72 539	24.44 532	26.94 527	12.76 527	13.93 531	40.99 523	2.01 541	46.93 527	13.88 529	6.19 549	52.85 515

SP-LightGlue		12.02 500	12.06 505	11.90 517	28.59 535	6.58 551	24.58 531	7.89 543	3.94 537	6.94 540	17.94 539	2.45 534	7.82 540	3.96 537	12.26 531	21.30 527

SP-SuperGlue		12.00 501	12.07 504	11.81 518	28.37 536	6.58 551	24.63 530	8.02 542	3.99 536	7.02 539	18.00 538	2.44 535	7.72 542	3.95 538	12.19 532	21.13 529

PMatch-SfM		26.26 490	22.21 496	38.43 506	28.29 537	16.65 538	37.61 520	8.91 540	18.02 524	18.64 524	53.32 515	0.55 557	41.01 529	24.74 520	9.79 538	57.63 511

SP-MNN		11.64 503	11.60 508	11.74 519	27.48 538	6.11 557	24.23 533	7.72 544	3.40 540	6.22 542	17.81 541	2.13 538	7.94 539	3.69 540	11.73 534	21.18 528

SP-NN		11.53 504	11.59 509	11.38 521	27.20 539	6.14 556	24.02 534	7.42 546	3.57 538	6.38 541	17.94 539	2.17 537	7.78 541	3.71 539	11.86 533	20.23 532

ELoFTR		28.06 489	23.17 495	42.73 502	26.41 540	16.73 537	32.43 523	29.00 526	18.06 523	18.03 526	50.11 518	1.10 544	53.50 524	21.73 521	11.65 535	57.96 510

VLMVS		26.26 490	26.52 493	25.45 511	25.35 541	7.91 546	30.71 525	15.37 532	3.37 541	34.11 508	65.40 501	8.03 515	21.07 534	32.40 509	23.95 515	47.39 520

VLMVS_CLIP		31.24 488	31.62 487	30.09 510	23.48 542	9.99 542	39.45 519	43.68 524	8.32 528	35.12 505	61.15 508	5.95 521	42.45 528	35.23 504	32.16 510	37.83 525

PMatch-Up-SfM		21.53 494	18.34 498	31.10 509	23.05 543	12.66 540	29.81 527	5.63 547	13.87 526	16.04 530	48.08 521	0.39 561	31.11 531	21.09 523	7.09 546	49.53 519

SIFT-NN		7.34 510	7.57 515	6.67 524	22.83 544	8.78 543	12.92 538	4.04 550	2.52 542	3.88 544	11.56 543	0.86 545	6.16 545	0.95 546	8.56 542	5.09 540

SIFT-MNN		6.97 512	7.12 516	6.51 525	21.26 545	8.28 544	11.89 539	4.05 549	2.50 543	3.39 546	11.27 544	0.76 546	6.14 546	0.95 546	8.05 544	5.09 540

SIFT-NCM-Cal		6.46 514	6.58 518	6.10 527	20.43 546	7.62 547	11.15 542	3.59 552	2.40 548	2.33 554	10.33 551	0.68 551	6.03 547	0.77 554	7.51 545	4.64 546

tmp_tt		41.54 476	41.93 476	40.38 503	20.10 547	26.84 526	61.93 509	59.09 516	14.81 525	28.51 515	80.58 458	35.53 481	48.33 526	63.70 427	13.11 527	45.96 523

SIFT-NN-NCMNet		6.77 513	6.92 517	6.30 526	19.98 548	8.05 545	11.79 540	3.97 551	2.43 545	3.43 545	10.93 545	0.75 547	5.95 548	0.88 548	8.15 543	4.90 542

SIFT-ConvMatch		6.05 517	6.14 521	5.78 529	19.43 549	7.31 548	9.58 546	3.30 556	2.42 546	2.67 551	10.54 549	0.65 552	5.73 549	0.83 552	5.84 551	4.29 547

SIFT-UMatch		5.86 519	6.01 522	5.38 531	18.70 550	6.22 555	10.07 544	3.07 558	2.39 549	2.42 552	10.54 549	0.63 555	5.65 552	0.84 551	5.49 552	4.28 548

SIFT-CM-Cal		5.56 521	5.66 524	5.26 533	18.45 551	6.34 554	8.44 548	2.81 559	2.36 550	2.42 552	9.99 554	0.64 553	5.41 553	0.74 556	5.05 553	4.02 549

SIFT-NN-CMatch		6.23 515	6.33 519	5.94 528	18.10 552	7.22 549	10.34 543	3.54 555	2.42 546	3.36 547	10.93 545	0.72 549	5.71 550	0.87 549	6.67 548	4.89 543

SIFT-UM-Cal		5.40 522	5.58 525	4.87 535	18.00 553	5.37 559	9.03 547	2.49 561	2.33 551	2.14 556	10.11 553	0.60 556	5.27 555	0.77 554	4.78 555	3.95 550

SIFT-NN-UMatch		6.11 516	6.25 520	5.68 530	17.01 554	6.50 553	11.20 541	3.58 553	2.44 544	2.68 550	10.88 547	0.74 548	5.70 551	0.87 549	6.85 547	4.82 544

SIFT-NN-PointCN		5.63 520	5.80 523	5.10 534	16.00 555	5.22 561	10.00 545	3.21 557	2.26 552	2.92 548	10.15 552	0.72 549	5.35 554	0.81 553	6.14 550	4.74 545

SIFT-PCN-Cal		4.71 524	4.89 527	4.18 536	15.70 556	3.90 563	7.58 550	2.37 562	2.09 554	1.95 557	8.68 555	0.51 558	4.71 556	0.68 557	4.45 556	3.93 551

SIFT-PointCN		4.77 523	4.97 526	4.17 537	15.53 557	3.97 562	8.20 549	2.62 560	2.10 553	1.91 558	8.44 556	0.47 559	4.70 557	0.67 558	4.79 554	3.85 552

SIFT-NCMNet		4.03 525	4.21 528	3.50 538	14.53 558	3.56 564	6.14 551	1.51 563	2.08 555	1.72 559	7.39 557	0.42 560	4.00 558	0.57 559	3.56 557	2.93 553

SP-DiffGlue		11.69 502	11.68 507	11.70 520	11.01 559	7.08 550	18.35 535	8.44 541	4.41 534	11.18 532	28.64 531	2.84 529	7.44 543	7.44 533	12.85 529	20.56 530

XFeat-MNN		10.03 505	9.79 511	10.74 522	9.46 560	6.05 558	16.60 536	9.52 539	4.29 535	8.53 538	22.45 535	2.10 539	13.28 537	5.47 534	9.68 539	12.89 538

XFeat-NN		9.17 507	9.18 512	9.14 523	8.78 561	5.26 560	15.30 537	7.57 545	3.56 539	8.63 537	22.05 536	1.87 543	11.03 538	4.95 535	9.92 537	11.13 539

MVS_baseline		7.08 511	7.68 514	5.28 532	7.84 562	0.20 567	2.38 552	0.52 564	0.10 559	10.02 535	34.66 525	0.64 553	0.00 561	4.06 536	8.92 540	15.64 536

testmvs		9.92 506	12.94 503	0.84 540	0.65 563	0.29 566	93.78 363	0.39 565	0.42 556	2.85 549	15.84 542	0.17 563	0.30 560	2.18 544	0.21 558	1.91 555

test123		9.07 508	11.73 506	1.11 539	0.50 564	0.77 565	89.44 432	0.20 566	0.34 557	2.15 555	10.72 548	0.34 562	0.32 559	1.79 545	0.08 559	2.23 554

PatchmatchNet2					0.00 565	72.22 405	92.05 400	89.18 454	62.36 472
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
mmdepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

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

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

eth-test2					0.00 565

eth-test					0.00 565

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

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

cdsmvs_eth3d_5k		21.43 495	28.57 492	0.00 541	0.00 565	0.00 568	0.00 553	95.93 182	0.00 560	0.00 561	97.66 94	63.57 334	0.00 561	0.00 560	0.00 560	0.00 557

pcd_1.5k_mvsjas		5.92 518	7.89 513	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	71.04 264	0.00 561	0.00 560	0.00 560	0.00 557

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

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

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

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

ab-mvs-re		8.11 509	10.81 510	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	97.30 118	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

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

PatchmatchNet1														42.17 498	64.00 446	85.01 453
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													91.74 452
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						67.18 449								49.00 484

PC_three_1452									91.12 51	98.33 5	98.42 44	92.51 2	99.81 29	98.96 6	99.37 1	99.70 4

test_241102_TWO								96.78 68	88.72 85	97.70 14	98.91 3	87.86 24	99.82 25	98.15 22	99.00 15	99.47 10

test_0728_THIRD									88.38 93	96.69 31	98.76 18	89.64 14	99.76 46	97.47 41	98.84 23	99.38 15

GSMVS																97.54 153

sam_mvs1												77.59 131				97.54 153

sam_mvs												75.35 192

MTGPA								96.33 142

test_post1							85.88 463				30.24 530	73.77 217	95.07 393	73.89 364

test_post											33.80 527	76.17 166	95.97 332

patchmatchnet-post											77.09 477	77.78 129	95.39 366

MTMP							97.53 118	68.16 510

test9_res														96.00 59	99.03 13	98.31 78

agg_prior2														94.30 83	99.00 15	98.57 61

test_prior4						82.34 149	97.75 100

test_prior2							98.37 56		86.08 171	94.57 71	98.02 73	83.14 62		95.05 74	98.79 27

旧先验2							96.97 172		74.06 416	96.10 42			97.76 199	88.38 200

新几何2							96.42 223

无先验							96.87 181	96.78 68	77.39 382				99.52 87	79.95 289		98.43 70

原ACMM2							96.84 183

testdata2													99.48 91	76.45 335

segment_acmp												82.69 68

testdata1							95.57 296		87.44 126

plane_prior5								94.69 262					97.30 258	87.08 215	82.82 316	90.96 335

plane_prior4											94.15 255

plane_prior3						77.75 334			90.17 68	81.33 295

plane_prior2							97.18 147		89.89 71

plane_prior						77.96 321	97.52 121		90.36 66						82.96 314

n2								0.00 567

nn								0.00 567

door-mid								79.75 498

test11								96.50 118

door								80.13 497

HQP5-MVS						78.48 299

BP-MVS														87.67 210

HQP4-MVS										82.30 282			97.32 256			91.13 333

HQP3-MVS								94.80 253							83.01 312

HQP2-MVS												65.40 319

MDTV_nov1_ep13_2view						81.74 176	86.80 455		80.65 322	85.65 228		74.26 210		76.52 334		96.98 212

ACMMP++_ref															78.45 349

ACMMP++															79.05 341

Test By Simon												71.65 256

High-resolution multi-view benchmark