High-res multi-view results

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

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

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

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

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

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

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

MSP-MVS		90.38 5	91.87 1	85.88 120	92.83 89	64.03 253	93.06 137	94.33 68	82.19 46	93.65 4	96.15 51	85.89 1	97.19 100	91.02 53	97.75 1	96.43 33
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 175	76.68 2	97.29 1	95.35 18	82.87 38	91.58 19	97.22 9	79.93 6	99.10 10	83.12 137	97.64 2	97.94 1

OPU-MVS				89.97 4	97.52 3	73.15 17	96.89 6				97.00 16	83.82 2	99.15 3	95.72 8	97.63 3	97.62 3

DVP-MVS++		90.53 4	91.09 5	88.87 17	97.31 4	69.91 47	93.96 91	94.37 66	72.48 253	92.07 12	96.85 28	83.82 2	99.15 3	91.53 49	97.42 4	97.55 5

PC_three_1452									80.91 67	94.07 3	96.83 30	83.57 4	99.12 6	95.70 10	97.42 4	97.55 5

HPM-MVS++		89.37 14	89.95 13	87.64 38	95.10 33	68.23 109	95.24 34	94.49 55	82.43 43	88.90 46	96.35 42	71.89 43	98.63 32	88.76 67	96.40 6	96.06 45

SMA-MVS		88.14 22	88.29 31	87.67 37	93.21 75	68.72 93	93.85 99	94.03 77	74.18 214	91.74 16	96.67 34	65.61 89	98.42 39	89.24 63	96.08 7	95.88 56
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
DELS-MVS		90.05 8	90.09 11	89.94 5	93.14 78	73.88 9	97.01 4	94.40 64	88.32 3	85.71 75	94.91 93	74.11 23	98.91 22	87.26 82	95.94 8	97.03 13
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
MCST-MVS		91.08 1	91.46 3	89.94 5	97.66 2	73.37 12	97.13 2	95.58 12	89.33 1	85.77 74	96.26 47	72.84 32	99.38 2	92.64 34	95.93 9	97.08 12

BridgeMVS		89.08 15	88.84 22	89.81 7	93.66 60	75.15 5	90.61 288	93.43 104	84.06 25	86.20 69	90.17 236	72.42 37	96.98 117	93.09 30	95.92 10	97.29 8

CNVR-MVS		90.32 6	90.89 8	88.61 24	96.76 9	70.65 34	96.47 14	94.83 37	84.83 18	89.07 44	96.80 31	70.86 46	99.06 16	92.64 34	95.71 11	96.12 44

PHI-MVS		86.83 51	86.85 55	86.78 72	93.47 69	65.55 201	95.39 31	95.10 27	71.77 279	85.69 76	96.52 36	62.07 153	98.77 28	86.06 97	95.60 12	96.03 47

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 182	93.00 85	58.16 396	96.72 9	94.41 62	86.50 9	90.25 34	97.83 2	75.46 16	98.67 31	92.78 33	95.49 13	97.32 7

SED-MVS		89.94 9	90.36 10	88.70 19	96.45 13	69.38 65	96.89 6	94.44 57	71.65 283	92.11 10	97.21 10	76.79 10	99.11 7	92.34 37	95.36 14	97.62 3

IU-MVS					96.46 12	69.91 47		95.18 25	80.75 69	95.28 2				92.34 37	95.36 14	96.47 30

test_241102_TWO								94.41 62	71.65 283	92.07 12	97.21 10	74.58 20	99.11 7	92.34 37	95.36 14	96.59 21

MM		90.87 2	91.52 2	88.92 16	92.12 110	71.10 31	97.02 3	96.04 6	88.70 2	91.57 20	96.19 49	70.12 50	98.91 22	96.83 2	95.06 17	96.76 17

test_0728_THIRD									72.48 253	90.55 30	96.93 20	76.24 13	99.08 12	91.53 49	94.99 18	96.43 33

test9_res														89.41 59	94.96 19	95.29 86

ACMMP_NAP		86.05 70	85.80 76	86.80 71	91.58 132	67.53 132	91.79 216	93.49 101	74.93 202	84.61 87	95.30 74	59.42 191	97.92 50	86.13 95	94.92 20	94.94 108

DPE-MVS		88.77 18	89.21 19	87.45 47	96.26 22	67.56 130	94.17 77	94.15 73	68.77 339	90.74 28	97.27 7	76.09 14	98.49 35	90.58 57	94.91 21	96.30 37
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		89.41 13	89.73 14	88.45 27	96.40 16	69.99 43	96.64 10	94.52 53	71.92 269	90.55 30	96.93 20	73.77 25	99.08 12	91.91 43	94.90 22	96.29 38
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				88.70 19	96.45 13	70.43 38	96.64 10	94.37 66					99.15 3	91.91 43	94.90 22	96.51 26

train_agg		87.21 43	87.42 44	86.60 84	94.18 47	67.28 139	94.16 78	93.51 98	71.87 274	85.52 78	95.33 72	68.19 61	97.27 95	89.09 64	94.90 22	95.25 93

DeepC-MVS_fast	79.48 2	87.95 29	88.00 35	87.79 35	95.86 29	68.32 103	95.74 21	94.11 74	83.82 27	83.49 100	96.19 49	64.53 105	98.44 37	83.42 135	94.88 25	96.61 20
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test-260524					95.84 30	67.84 120		94.64 47		89.45 43		71.94 42	98.96 19	91.55 45	94.82 26

MED-MVS		89.02 17	89.57 15	87.38 49	94.76 36	67.28 139	94.47 64	94.87 34	70.68 310	91.27 24	96.93 20	76.77 12	98.98 17	91.55 45	94.82 26	95.88 56

MSC_two_6792asdad				89.60 10	97.31 4	73.22 15		95.05 31					99.07 14	92.01 40	94.77 28	96.51 26

No_MVS				89.60 10	97.31 4	73.22 15		95.05 31					99.07 14	92.01 40	94.77 28	96.51 26

TSAR-MVS + MP.		88.11 25	88.64 25	86.54 96	91.73 128	68.04 114	90.36 296	93.55 96	82.89 36	91.29 23	92.89 148	72.27 39	96.03 174	87.99 72	94.77 28	95.54 70
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_prior2							95.10 39		75.40 194	85.25 84	95.61 63	67.94 64		87.47 79	94.77 28

agg_prior2														86.41 93	94.75 32	95.33 81

MVSMamba_PlusPlus		84.97 96	83.65 116	88.93 15	90.17 166	74.04 8	87.84 359	92.69 139	62.18 407	81.47 122	87.64 287	71.47 45	96.28 157	84.69 112	94.74 33	96.47 30

MVS		84.66 105	82.86 148	90.06 3	90.93 150	74.56 7	87.91 357	95.54 15	68.55 341	72.35 276	94.71 98	59.78 183	98.90 24	81.29 166	94.69 34	96.74 18

MGCNet		90.32 6	90.90 7	88.55 25	94.05 51	70.23 41	97.00 5	93.73 88	87.30 4	92.15 9	96.15 51	66.38 79	98.94 21	96.71 3	94.67 35	96.47 30

SF-MVS		87.03 45	87.09 47	86.84 67	92.70 95	67.45 136	93.64 112	93.76 84	70.78 308	86.25 67	96.44 39	66.98 72	97.79 57	88.68 68	94.56 36	95.28 88

NCCC		89.07 16	89.46 16	87.91 32	96.60 11	69.05 81	96.38 15	94.64 47	84.42 22	86.74 64	96.20 48	66.56 78	98.76 29	89.03 66	94.56 36	95.92 53

3Dnovator	73.91 6	82.69 167	80.82 187	88.31 29	89.57 177	71.26 26	92.60 170	94.39 65	78.84 125	67.89 337	92.48 158	48.42 339	98.52 34	68.80 289	94.40 38	95.15 96

aaatest				87.42 48	94.76 36	67.28 139	94.47 64	94.87 34	73.09 241	91.27 24	96.95 18		98.98 17	91.55 45	94.28 39	95.99 50

aaEdge-Enhanced		88.25 19	88.55 26	87.33 53	96.33 19	67.28 139	93.93 93	94.81 38	70.09 318	88.91 45	96.95 18	70.12 50	98.73 30	91.55 45	94.28 39	95.99 50

CDPH-MVS		85.71 79	85.46 82	86.46 100	94.75 40	67.19 144	93.89 97	92.83 132	70.90 304	83.09 105	95.28 76	63.62 120	97.36 86	80.63 173	94.18 41	94.84 114

MG-MVS		87.11 44	86.27 63	89.62 9	97.79 1	76.27 4	94.96 48	94.49 55	78.74 128	83.87 96	92.94 146	64.34 106	96.94 123	75.19 221	94.09 42	95.66 65

9.14			87.63 39		93.86 54		94.41 69	94.18 71	72.76 248	86.21 68	96.51 37	66.64 76	97.88 54	90.08 58	94.04 43

原ACMM1				84.42 199	93.21 75	64.27 244		93.40 107	65.39 377	79.51 163	92.50 155	58.11 217	96.69 136	65.27 336	93.96 44	92.32 245

MSLP-MVS++		86.27 66	85.91 74	87.35 51	92.01 117	68.97 84	95.04 43	92.70 136	79.04 123	81.50 120	96.50 38	58.98 202	96.78 133	83.49 134	93.93 45	96.29 38

CANet		89.61 12	89.99 12	88.46 26	94.39 45	69.71 56	96.53 13	93.78 81	86.89 7	89.68 40	95.78 58	65.94 84	99.10 10	92.99 31	93.91 46	96.58 23

MP-MVS-pluss		85.24 88	85.13 89	85.56 136	91.42 137	65.59 199	91.54 236	92.51 149	74.56 205	80.62 138	95.64 62	59.15 198	97.00 113	86.94 90	93.80 47	94.07 177
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MVP-Stereo		77.12 288	76.23 281	79.79 353	81.72 385	66.34 177	89.29 328	90.88 248	70.56 313	62.01 397	82.88 352	49.34 330	94.13 289	65.55 333	93.80 47	78.88 461
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
GG-mvs-BLEND				86.53 97	91.91 123	69.67 58	75.02 466	94.75 41		78.67 183	90.85 216	77.91 8	94.56 268	72.25 252	93.74 49	95.36 79

ZNCC-MVS		85.33 87	85.08 90	86.06 115	93.09 81	65.65 197	93.89 97	93.41 106	73.75 225	79.94 152	94.68 99	60.61 172	98.03 47	82.63 145	93.72 50	94.52 142

CSCG		86.87 48	86.26 64	88.72 18	95.05 34	70.79 33	93.83 104	95.33 19	68.48 343	77.63 193	94.35 111	73.04 30	98.45 36	84.92 110	93.71 51	96.92 15

test12				87.09 60	94.60 42	68.86 85		92.91 129		82.67 112		65.44 90	97.55 74		93.69 52	94.84 114

PAPM		85.89 76	85.46 82	87.18 57	88.20 235	72.42 18	92.41 182	92.77 134	82.11 47	80.34 147	93.07 143	68.27 59	95.02 239	78.39 199	93.59 53	94.09 175

SteuartSystems-ACMMP		86.82 53	86.90 52	86.58 87	90.42 160	66.38 175	96.09 17	93.87 79	77.73 149	84.01 95	95.66 61	63.39 125	97.94 49	87.40 80	93.55 54	95.42 73
Skip Steuart: Steuart Systems R&D Blog.
APDe-MVS		87.54 35	87.84 37	86.65 81	96.07 25	66.30 178	94.84 53	93.78 81	69.35 328	88.39 49	96.34 43	67.74 67	97.66 66	90.62 56	93.44 55	96.01 48
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SPE-MVS-test		86.14 69	87.01 48	83.52 237	92.63 97	59.36 384	95.49 28	91.92 176	80.09 86	85.46 80	95.53 67	61.82 158	95.77 196	86.77 92	93.37 56	95.41 74

PS-MVSNAJ		88.14 22	87.61 41	89.71 8	92.06 113	76.72 1	95.75 20	93.26 110	83.86 26	89.55 41	96.06 53	53.55 282	97.89 53	91.10 51	93.31 57	94.54 140

TestfortrainingZip				90.29 2	97.24 8	73.67 10	94.47 64	95.75 10	69.78 324	95.97 1	98.23 1	80.55 5	99.42 1		93.26 58	97.76 2

MAR-MVS		84.18 121	83.43 124	86.44 102	96.25 23	65.93 192	94.28 75	94.27 70	74.41 208	79.16 172	95.61 63	53.99 277	98.88 26	69.62 278	93.26 58	94.50 148
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
gg-mvs-nofinetune		77.18 286	74.31 308	85.80 125	91.42 137	68.36 102	71.78 471	94.72 42	49.61 468	77.12 203	45.92 499	77.41 9	93.98 301	67.62 304	93.16 60	95.05 102

ZD-MVS					96.63 10	65.50 203		93.50 100	70.74 309	85.26 83	95.19 84	64.92 98	97.29 91	87.51 77	93.01 61

APD-MVS		85.93 74	85.99 72	85.76 127	95.98 28	65.21 210	93.59 115	92.58 147	66.54 362	86.17 70	95.88 57	63.83 114	97.00 113	86.39 94	92.94 62	95.06 101
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
新几何1				84.73 181	92.32 102	64.28 243		91.46 203	59.56 430	79.77 158	92.90 147	56.95 236	96.57 140	63.40 350	92.91 63	93.34 207

DeepC-MVS	77.85 3	85.52 85	85.24 86	86.37 105	88.80 203	66.64 169	92.15 192	93.68 90	81.07 65	76.91 207	93.64 133	62.59 141	98.44 37	85.50 100	92.84 64	94.03 180
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.5_n_11		87.99 26	89.25 18	84.23 210	89.07 194	61.60 331	94.87 51	89.06 342	85.65 11	91.09 26	97.41 5	68.26 60	97.43 82	95.07 13	92.74 65	93.66 197

xiu_mvs_v2_base		87.92 31	87.38 45	89.55 13	91.41 140	76.43 3	95.74 21	93.12 119	83.53 30	89.55 41	95.95 56	53.45 286	97.68 61	91.07 52	92.62 66	94.54 140

MP-MVS		85.02 93	84.97 92	85.17 156	92.60 98	64.27 244	93.24 131	92.27 156	73.13 237	79.63 162	94.43 105	61.90 154	97.17 101	85.00 108	92.56 67	94.06 178
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTAPA		83.91 130	83.38 128	85.50 137	91.89 124	65.16 212	81.75 425	92.23 157	75.32 196	80.53 143	95.21 83	56.06 249	97.16 104	84.86 111	92.55 68	94.18 166

GST-MVS		84.63 107	84.29 103	85.66 132	92.82 91	65.27 208	93.04 139	93.13 118	73.20 235	78.89 174	94.18 119	59.41 192	97.85 55	81.45 162	92.48 69	93.86 191

HFP-MVS		84.73 104	84.40 101	85.72 129	93.75 58	65.01 216	93.50 120	93.19 114	72.19 263	79.22 170	94.93 91	59.04 201	97.67 63	81.55 160	92.21 70	94.49 149

ACMMPR		84.37 113	84.06 106	85.28 151	93.56 64	64.37 239	93.50 120	93.15 117	72.19 263	78.85 179	94.86 94	56.69 240	97.45 79	81.55 160	92.20 71	94.02 181

MS-PatchMatch		77.90 275	76.50 273	82.12 286	85.99 310	69.95 46	91.75 224	92.70 136	73.97 219	62.58 394	84.44 334	41.11 397	95.78 194	63.76 349	92.17 72	80.62 445

PRO-TEST		88.25 19	88.30 30	88.11 31	93.04 84	71.42 23	93.31 129	93.19 114	85.25 14	87.41 58	95.02 87	62.21 149	95.99 177	93.13 29	92.14 73	96.91 16

region2R		84.36 114	84.03 107	85.36 146	93.54 66	64.31 242	93.43 125	92.95 128	72.16 266	78.86 178	94.84 95	56.97 235	97.53 75	81.38 164	92.11 74	94.24 163

CS-MVS		85.80 77	86.65 60	83.27 249	92.00 118	58.92 388	95.31 32	91.86 181	79.97 87	84.82 86	95.40 70	62.26 147	95.51 221	86.11 96	92.08 75	95.37 77

fmvsm_l_conf0.5_n_9		88.24 21	89.36 17	84.85 170	88.15 236	61.94 321	95.65 25	89.70 312	85.54 12	92.07 12	97.33 6	67.51 69	97.27 95	96.23 5	92.07 76	95.35 80

patch_mono-2		89.71 11	90.99 6	85.85 123	96.04 26	63.70 270	95.04 43	95.19 24	86.74 8	91.53 21	95.15 85	73.86 24	97.58 71	93.38 27	92.00 77	96.28 40

dcpmvs_2		87.37 41	87.55 42	86.85 66	95.04 35	68.20 111	90.36 296	90.66 262	79.37 112	81.20 125	93.67 132	74.73 18	96.55 143	90.88 54	92.00 77	95.82 59

fmvsm_s_conf0.5_n_6		87.50 37	88.72 23	83.84 222	86.89 287	60.04 372	95.05 41	92.17 166	84.80 19	92.27 7	96.37 40	64.62 102	96.54 144	94.43 19	91.86 79	94.94 108

旧先验1					91.94 119	60.74 352		91.50 201			94.36 107	65.23 93			91.84 80	94.55 138

MVSFormer		83.75 136	82.88 147	86.37 105	89.24 191	71.18 28	89.07 335	90.69 259	65.80 372	87.13 59	94.34 112	64.99 95	92.67 351	72.83 242	91.80 81	95.27 89

lupinMVS		87.74 33	87.77 38	87.63 42	89.24 191	71.18 28	96.57 12	92.90 130	82.70 40	87.13 59	95.27 78	64.99 95	95.80 191	89.34 61	91.80 81	95.93 52

EPNet		87.84 32	88.38 28	86.23 110	93.30 72	66.05 184	95.26 33	94.84 36	87.09 5	88.06 50	94.53 102	66.79 74	97.34 88	83.89 126	91.68 83	95.29 86
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
3Dnovator+	73.60 7	82.10 181	80.60 195	86.60 84	90.89 152	66.80 165	95.20 35	93.44 103	74.05 216	67.42 345	92.49 157	49.46 329	97.65 67	70.80 268	91.68 83	95.33 81

XVS		83.87 131	83.47 122	85.05 160	93.22 73	63.78 262	92.92 147	92.66 141	73.99 217	78.18 187	94.31 114	55.25 256	97.41 83	79.16 189	91.58 85	93.95 183

X-MVStestdata		76.86 292	74.13 314	85.05 160	93.22 73	63.78 262	92.92 147	92.66 141	73.99 217	78.18 187	10.19 532	55.25 256	97.41 83	79.16 189	91.58 85	93.95 183

SD-MVS		87.49 38	87.49 43	87.50 46	93.60 62	68.82 88	93.90 96	92.63 145	76.86 168	87.90 52	95.76 59	66.17 81	97.63 68	89.06 65	91.48 87	96.05 46
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
EC-MVSNet		84.53 109	85.04 91	83.01 255	89.34 182	61.37 339	94.42 68	91.09 229	77.91 144	83.24 101	94.20 118	58.37 213	95.40 223	85.35 101	91.41 88	92.27 250

fmvsm_s_conf0.5_n_10		87.93 30	88.67 24	85.71 130	88.69 205	63.71 268	94.56 62	90.22 288	85.04 16	92.27 7	97.05 13	63.67 118	98.15 44	95.09 12	91.39 89	95.27 89

PGM-MVS		83.25 152	82.70 151	84.92 165	92.81 93	64.07 252	90.44 291	92.20 161	71.28 296	77.23 201	94.43 105	55.17 260	97.31 90	79.33 188	91.38 90	93.37 206

PVSNet_Blended		86.73 55	86.86 54	86.31 109	93.76 56	67.53 132	96.33 16	93.61 93	82.34 45	81.00 132	93.08 142	63.19 130	97.29 91	87.08 88	91.38 90	94.13 171

HPM-MVS		83.25 152	82.95 145	84.17 211	92.25 104	62.88 299	90.91 268	91.86 181	70.30 315	77.12 203	93.96 127	56.75 238	96.28 157	82.04 152	91.34 92	93.34 207
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EIA-MVS		84.84 100	84.88 93	84.69 186	91.30 142	62.36 309	93.85 99	92.04 169	79.45 108	79.33 167	94.28 116	62.42 143	96.35 154	80.05 178	91.25 93	95.38 76

NormalMVS		86.39 60	86.66 59	85.60 135	92.12 110	65.95 190	94.88 49	90.83 250	84.69 20	83.67 98	94.10 121	63.16 132	96.91 129	85.31 102	91.15 94	93.93 185

lecture		84.77 101	84.81 96	84.65 189	92.12 110	62.27 313	94.74 56	92.64 144	68.35 344	85.53 77	95.30 74	59.77 184	97.91 51	83.73 130	91.15 94	93.77 194

MVS_111021_HR		86.19 68	85.80 76	87.37 50	93.17 77	69.79 52	93.99 90	93.76 84	79.08 120	78.88 177	93.99 126	62.25 148	98.15 44	85.93 98	91.15 94	94.15 169

test222					89.77 173	61.60 331	89.55 319	89.42 320	56.83 446	77.28 200	92.43 159	52.76 290			91.14 97	93.09 217

jason		86.40 59	86.17 67	87.11 59	86.16 306	70.54 36	95.71 24	92.19 163	82.00 48	84.58 88	94.34 112	61.86 156	95.53 220	87.76 74	90.89 98	95.27 89
jason: jason.
mPP-MVS		82.96 161	82.44 161	84.52 196	92.83 89	62.92 297	92.76 154	91.85 183	71.52 291	75.61 220	94.24 117	53.48 285	96.99 116	78.97 192	90.73 99	93.64 199

CP-MVS		83.71 137	83.40 127	84.65 189	93.14 78	63.84 260	94.59 61	92.28 155	71.03 302	77.41 197	94.92 92	55.21 259	96.19 162	81.32 165	90.70 100	93.91 188

OpenMVS	70.45 11	78.54 261	75.92 286	86.41 104	85.93 314	71.68 21	92.74 155	92.51 149	66.49 363	64.56 371	91.96 180	43.88 385	98.10 46	54.61 395	90.65 101	89.44 307

PAPM_NR		82.97 160	81.84 170	86.37 105	94.10 50	66.76 166	87.66 363	92.84 131	69.96 320	74.07 247	93.57 135	63.10 135	97.50 77	70.66 271	90.58 102	94.85 111

testdata				81.34 307	89.02 197	57.72 400		89.84 302	58.65 435	85.32 82	94.09 123	57.03 231	93.28 325	69.34 281	90.56 103	93.03 220

mvsmamba		81.55 189	80.72 190	84.03 217	91.42 137	66.93 161	83.08 413	89.13 336	78.55 132	67.50 343	87.02 299	51.79 299	90.07 410	87.48 78	90.49 104	95.10 99

fmvsm_s_conf0.5_n_3		86.88 47	87.99 36	83.58 236	87.26 263	60.74 352	93.21 134	87.94 387	84.22 23	91.70 17	97.27 7	65.91 86	95.02 239	93.95 24	90.42 105	94.99 105

fmvsm_s_conf0.5_n_7		85.24 88	86.69 57	80.91 325	84.52 346	60.10 370	93.35 128	90.35 276	83.41 32	86.54 66	96.27 46	60.50 173	90.02 411	94.84 16	90.38 106	92.61 233

Vis-MVSNet		80.92 207	79.98 206	83.74 226	88.48 220	61.80 323	93.44 124	88.26 379	73.96 220	77.73 191	91.76 187	49.94 323	94.76 251	65.84 326	90.37 107	94.65 133
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
balanced_ft_v1		84.95 97	83.81 111	88.38 28	93.31 71	73.59 11	85.95 383	92.51 149	77.25 162	73.97 249	89.14 259	59.30 194	95.25 234	92.50 36	90.34 108	96.31 36

CHOSEN 1792x2688		84.98 95	83.45 123	89.57 12	89.94 170	75.14 6	92.07 198	92.32 154	81.87 49	75.68 217	88.27 273	60.18 177	98.60 33	80.46 175	90.27 109	94.96 106

fmvsm_s_conf0.5_n_8		87.96 27	88.93 21	85.07 159	88.43 223	61.78 324	94.73 59	91.74 187	85.87 10	91.66 18	97.50 3	64.03 110	98.33 40	96.28 4	90.08 110	95.10 99

fmvsm_l_conf0.5_n_3		87.54 35	88.29 31	85.30 149	86.92 285	62.63 304	95.02 45	90.28 283	84.95 17	90.27 33	96.86 26	65.36 91	97.52 76	94.93 15	90.03 111	95.76 61

test_fmvsm_n_1920		87.69 34	88.50 27	85.27 152	87.05 274	63.55 277	93.69 109	91.08 233	84.18 24	90.17 36	97.04 15	67.58 68	97.99 48	95.72 8	90.03 111	94.26 161

fmvsm_s_conf0.5_n_5		86.38 62	86.94 50	84.71 184	84.67 341	63.29 284	94.04 87	89.99 298	82.88 37	87.85 53	96.03 54	62.89 139	96.36 153	94.15 21	89.95 113	94.48 150

fmvsm_s_conf0.5_n_9		88.14 22	89.21 19	84.92 165	89.29 186	61.41 338	92.97 142	88.36 371	86.96 6	91.49 22	97.49 4	69.48 55	97.46 78	97.00 1	89.88 114	95.89 55

ETV-MVS		86.01 72	86.11 69	85.70 131	90.21 165	67.02 153	93.43 125	91.92 176	81.21 63	84.13 94	94.07 125	60.93 167	95.63 208	89.28 62	89.81 115	94.46 151

QAPM		79.95 229	77.39 260	87.64 38	89.63 176	71.41 24	93.30 130	93.70 89	65.34 379	67.39 347	91.75 189	47.83 348	98.96 19	57.71 384	89.81 115	92.54 237

CANet_DTU		84.09 123	83.52 117	85.81 124	90.30 163	66.82 163	91.87 212	89.01 345	85.27 13	86.09 71	93.74 130	47.71 350	96.98 117	77.90 202	89.78 117	93.65 198

API-MVS		82.28 173	80.53 197	87.54 45	96.13 24	70.59 35	93.63 113	91.04 239	65.72 374	75.45 223	92.83 151	56.11 248	98.89 25	64.10 346	89.75 118	93.15 214

test2506		83.29 151	82.92 146	84.37 202	88.39 226	63.18 290	92.01 201	91.35 208	77.66 151	78.49 186	91.42 199	64.58 104	95.09 238	73.19 238	89.23 119	94.85 111

ECVR-MVS		81.29 195	80.38 200	84.01 218	88.39 226	61.96 319	92.56 175	86.79 403	77.66 151	76.63 208	91.42 199	46.34 368	95.24 235	74.36 230	89.23 119	94.85 111

MVS_Test		84.16 122	83.20 135	87.05 62	91.56 133	69.82 50	89.99 310	92.05 168	77.77 148	82.84 107	86.57 304	63.93 113	96.09 168	74.91 226	89.18 121	95.25 93

reproduce-ours		83.51 147	83.33 130	84.06 213	92.18 108	60.49 360	90.74 278	92.04 169	64.35 384	83.24 101	95.59 65	59.05 199	97.27 95	83.61 131	89.17 122	94.41 157

our_new_method		83.51 147	83.33 130	84.06 213	92.18 108	60.49 360	90.74 278	92.04 169	64.35 384	83.24 101	95.59 65	59.05 199	97.27 95	83.61 131	89.17 122	94.41 157

PAPR		85.15 91	84.47 99	87.18 57	96.02 27	68.29 104	91.85 214	93.00 125	76.59 179	79.03 173	95.00 88	61.59 159	97.61 70	78.16 200	89.00 124	95.63 66

BP-MVS1		86.54 58	86.68 58	86.13 113	87.80 251	67.18 146	92.97 142	95.62 11	79.92 90	82.84 107	94.14 120	74.95 17	96.46 149	82.91 141	88.96 125	94.74 123

TestfortrainingZip a		86.96 46	86.88 53	87.23 54	94.76 36	67.02 153	94.47 64	94.08 76	70.68 310	88.57 48	96.93 20	69.03 56	98.78 27	84.41 119	88.95 126	95.88 56

TSAR-MVS + GP.		87.96 27	88.37 29	86.70 78	93.51 68	65.32 207	95.15 37	93.84 80	78.17 138	85.93 73	94.80 96	75.80 15	98.21 42	89.38 60	88.78 127	96.59 21

SR-MVS		82.81 163	82.58 157	83.50 240	93.35 70	61.16 342	92.23 189	91.28 215	64.48 383	81.27 124	95.28 76	53.71 281	95.86 183	82.87 142	88.77 128	93.49 204

test1111		80.84 208	80.02 203	83.33 244	87.87 247	60.76 350	92.62 167	86.86 402	77.86 145	75.73 216	91.39 201	46.35 367	94.70 260	72.79 244	88.68 129	94.52 142

fmvsm_l_conf0.5_n_a		87.44 40	88.15 34	85.30 149	87.10 272	64.19 248	94.41 69	88.14 380	80.24 85	92.54 6	96.97 17	69.52 54	97.17 101	95.89 6	88.51 130	94.56 137

reproduce_model		83.15 155	82.96 143	83.73 228	92.02 114	59.74 376	90.37 295	92.08 167	63.70 391	82.86 106	95.48 68	58.62 208	97.17 101	83.06 138	88.42 131	94.26 161

HPM-MVS_fast		80.25 222	79.55 216	82.33 276	91.55 134	59.95 373	91.32 251	89.16 332	65.23 380	74.71 237	93.07 143	47.81 349	95.74 197	74.87 228	88.23 132	91.31 276

PVSNet_Blended_VisFu		83.97 128	83.50 119	85.39 141	90.02 168	66.59 172	93.77 106	91.73 188	77.43 158	77.08 206	89.81 247	63.77 116	96.97 120	79.67 182	88.21 133	92.60 234

Vis-MVSNet (Re-imp)		79.24 243	79.57 213	78.24 377	88.46 221	52.29 440	90.41 293	89.12 337	74.24 213	69.13 312	91.91 184	65.77 87	90.09 409	59.00 380	88.09 134	92.33 244

fmvsm_l_conf0.5_n		87.49 38	88.19 33	85.39 141	86.95 280	64.37 239	94.30 74	88.45 369	80.51 73	92.70 5	96.86 26	69.98 52	97.15 105	95.83 7	88.08 135	94.65 133

APD-MVS_3200maxsize		81.64 188	81.32 177	82.59 268	92.36 101	58.74 390	91.39 242	91.01 241	63.35 395	79.72 160	94.62 101	51.82 297	96.14 165	79.71 181	87.93 136	92.89 226

RRT-MVS		82.61 168	81.16 178	86.96 65	91.10 146	68.75 91	87.70 362	92.20 161	76.97 166	72.68 263	87.10 298	51.30 308	96.41 151	83.56 133	87.84 137	95.74 62

Effi-MVS+		83.82 132	82.76 149	86.99 64	89.56 178	69.40 63	91.35 249	86.12 414	72.59 250	83.22 104	92.81 152	59.60 187	96.01 176	81.76 159	87.80 138	95.56 69

casdiffmvs_mvg		85.66 81	85.18 87	87.09 60	88.22 234	69.35 68	93.74 108	91.89 179	81.47 54	80.10 150	91.45 198	64.80 100	96.35 154	87.23 83	87.69 139	95.58 68
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
1314		80.70 211	78.95 231	85.94 119	87.77 253	67.56 130	87.91 357	92.55 148	72.17 265	67.44 344	93.09 141	50.27 319	97.04 111	71.68 260	87.64 140	93.23 211

test_fmvsmconf_n		86.58 57	87.17 46	84.82 172	85.28 329	62.55 305	94.26 76	89.78 303	83.81 28	87.78 54	96.33 44	65.33 92	96.98 117	94.40 20	87.55 141	94.95 107

PMMVS		81.98 183	82.04 165	81.78 293	89.76 174	56.17 419	91.13 262	90.69 259	77.96 141	80.09 151	93.57 135	46.33 369	94.99 242	81.41 163	87.46 142	94.17 167

casdiffmvs		85.37 86	84.87 94	86.84 67	88.25 232	69.07 78	93.04 139	91.76 186	81.27 62	80.84 135	92.07 173	64.23 108	96.06 172	84.98 109	87.43 143	95.39 75
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
hybridcas		84.65 106	83.95 108	86.74 76	87.18 268	68.78 90	92.94 145	91.36 207	80.47 74	79.32 168	91.67 194	62.13 152	96.19 162	83.15 136	87.36 144	95.25 93

test_fmvsmconf0.1_n		85.71 79	86.08 71	84.62 193	80.83 392	62.33 310	93.84 102	88.81 355	83.50 31	87.00 62	96.01 55	63.36 126	96.93 125	94.04 23	87.29 145	94.61 135

UGNet		79.87 230	78.68 233	83.45 242	89.96 169	61.51 333	92.13 193	90.79 257	76.83 170	78.85 179	86.33 308	38.16 412	96.17 164	67.93 301	87.17 146	92.67 231
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
MVS_111021_LR		82.02 182	81.52 173	83.51 239	88.42 224	62.88 299	89.77 313	88.93 350	76.78 171	75.55 221	93.10 140	50.31 318	95.38 225	83.82 127	87.02 147	92.26 251

fmvsm_s_conf0.5_n_4		86.79 54	87.63 39	84.27 208	86.15 307	61.48 335	94.69 60	91.16 219	83.79 29	90.51 32	96.28 45	64.24 107	98.22 41	95.00 14	86.88 148	93.11 216

test_fmvsmvis_n_1920		83.80 133	83.48 121	84.77 177	82.51 376	63.72 267	91.37 245	83.99 438	81.42 59	77.68 192	95.74 60	58.37 213	97.58 71	93.38 27	86.87 149	93.00 222

xiu_mvs_v1_base_debu		82.16 178	81.12 180	85.26 153	86.42 297	68.72 93	92.59 172	90.44 272	73.12 238	84.20 91	94.36 107	38.04 414	95.73 198	84.12 123	86.81 150	91.33 272

xiu_mvs_v1_base		82.16 178	81.12 180	85.26 153	86.42 297	68.72 93	92.59 172	90.44 272	73.12 238	84.20 91	94.36 107	38.04 414	95.73 198	84.12 123	86.81 150	91.33 272

xiu_mvs_v1_base_debi		82.16 178	81.12 180	85.26 153	86.42 297	68.72 93	92.59 172	90.44 272	73.12 238	84.20 91	94.36 107	38.04 414	95.73 198	84.12 123	86.81 150	91.33 272

SR-MVS-dyc-post		81.06 203	80.70 191	82.15 284	92.02 114	58.56 393	90.90 269	90.45 268	62.76 402	78.89 174	94.46 103	51.26 309	95.61 212	78.77 196	86.77 153	92.28 247

RE-MVS-def			80.48 198		92.02 114	58.56 393	90.90 269	90.45 268	62.76 402	78.89 174	94.46 103	49.30 331		78.77 196	86.77 153	92.28 247

baseline		85.01 94	84.44 100	86.71 77	88.33 229	68.73 92	90.24 301	91.82 185	81.05 66	81.18 126	92.50 155	63.69 117	96.08 171	84.45 118	86.71 155	95.32 83

TESTMET0.1,1		82.41 171	81.98 168	83.72 230	88.08 237	63.74 264	92.70 159	93.77 83	79.30 113	77.61 194	87.57 289	58.19 216	94.08 292	73.91 233	86.68 156	93.33 209

SymmetryMVS		86.32 63	86.39 62	86.12 114	90.52 158	65.95 190	94.88 49	94.58 52	84.69 20	83.67 98	94.10 121	63.16 132	96.91 129	85.31 102	86.59 157	95.51 71

viewmanbaseed2359cas		84.89 99	84.26 104	86.78 72	88.50 214	69.77 54	92.69 164	91.13 225	81.11 64	81.54 119	91.98 179	60.35 174	95.73 198	84.47 117	86.56 158	94.84 114

IS-MVSNet		80.14 224	79.41 220	82.33 276	87.91 243	60.08 371	91.97 205	88.27 377	72.90 246	71.44 289	91.73 190	61.44 160	93.66 315	62.47 360	86.53 159	93.24 210

CPTT-MVS		79.59 233	79.16 227	80.89 327	91.54 135	59.80 375	92.10 195	88.54 368	60.42 423	72.96 259	93.28 139	48.27 340	92.80 345	78.89 195	86.50 160	90.06 294

KinetiMVS		81.43 191	80.11 201	85.38 145	86.60 292	65.47 205	92.90 150	93.54 97	75.33 195	77.31 199	90.39 224	46.81 359	96.75 134	71.65 261	86.46 161	93.93 185

BH-w/o		80.49 216	79.30 224	84.05 216	90.83 154	64.36 241	93.60 114	89.42 320	74.35 210	69.09 313	90.15 238	55.23 258	95.61 212	64.61 341	86.43 162	92.17 253

PVSNet	73.49 8	80.05 226	78.63 234	84.31 205	90.92 151	64.97 217	92.47 179	91.05 238	79.18 116	72.43 274	90.51 221	37.05 426	94.06 294	68.06 298	86.00 163	93.90 190

GDP-MVS		85.54 84	85.32 84	86.18 111	87.64 254	67.95 118	92.91 149	92.36 153	77.81 146	83.69 97	94.31 114	72.84 32	96.41 151	80.39 176	85.95 164	94.19 165

Casviewmamba		84.58 108	83.95 108	86.47 99	87.22 265	67.76 124	92.71 157	90.96 243	80.81 68	79.29 169	91.85 185	62.20 150	96.33 156	84.60 114	85.91 165	95.32 83

test_fmvsmconf0.01_n		83.70 138	83.52 117	84.25 209	75.26 456	61.72 328	92.17 191	87.24 397	82.36 44	84.91 85	95.41 69	55.60 254	96.83 132	92.85 32	85.87 166	94.21 164

E3new		84.94 98	84.36 102	86.69 80	89.06 195	69.31 69	92.68 165	91.29 214	80.72 70	81.03 129	92.14 169	61.89 155	95.91 179	84.59 115	85.85 167	94.86 110

myMVS_eth3d28		86.31 65	86.15 68	86.78 72	93.56 64	70.49 37	92.94 145	95.28 20	82.47 42	78.70 181	92.07 173	72.45 36	95.41 222	82.11 150	85.78 168	94.44 152

mvs_anonymous		81.36 193	79.99 205	85.46 138	90.39 162	68.40 101	86.88 374	90.61 264	74.41 208	70.31 301	84.67 330	63.79 115	92.32 367	73.13 239	85.70 169	95.67 64

DP-MVS Recon		82.73 164	81.65 172	85.98 117	97.31 4	67.06 149	95.15 37	91.99 173	69.08 336	76.50 212	93.89 128	54.48 270	98.20 43	70.76 269	85.66 170	92.69 230

BH-RMVSNet		79.46 238	77.65 250	84.89 168	91.68 130	65.66 196	93.55 116	88.09 382	72.93 243	73.37 256	91.12 212	46.20 371	96.12 166	56.28 390	85.61 171	92.91 224

viewcassd2359sk11		84.74 103	84.11 105	86.64 82	88.57 208	69.20 76	92.61 168	91.23 216	80.58 71	80.85 134	91.96 180	61.39 161	95.89 181	84.28 121	85.49 172	94.82 118

viewmacassd2359aftdt		84.03 125	83.18 137	86.59 86	86.76 288	69.44 62	92.44 181	90.85 249	80.38 78	80.78 136	91.33 204	58.54 210	95.62 210	82.15 149	85.41 173	94.72 126

diffmvs_AUTHOR		83.97 128	83.49 120	85.39 141	86.09 308	67.83 121	90.76 276	89.05 343	79.94 88	81.43 123	92.23 166	59.53 188	94.42 276	87.18 84	85.22 174	93.92 187

UBG		86.83 51	86.70 56	87.20 56	93.07 82	69.81 51	93.43 125	95.56 14	81.52 53	81.50 120	92.12 170	73.58 28	96.28 157	84.37 120	85.20 175	95.51 71

diffmvs		84.28 116	83.83 110	85.61 134	87.40 260	68.02 115	90.88 271	89.24 327	80.54 72	81.64 118	92.52 154	59.83 182	94.52 272	87.32 81	85.11 176	94.29 159
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E2		84.45 110	83.74 112	86.56 89	87.90 244	69.06 79	92.53 176	91.13 225	80.35 79	80.58 141	91.69 192	60.70 168	95.84 184	83.80 128	84.99 177	94.79 121

E3		84.45 110	83.74 112	86.56 89	87.90 244	69.06 79	92.53 176	91.13 225	80.35 79	80.58 141	91.69 192	60.70 168	95.84 184	83.80 128	84.99 177	94.79 121

viewdifsd2359ckpt13		84.08 124	83.21 133	86.70 78	88.49 218	69.55 60	92.25 186	91.14 223	79.71 97	79.73 159	91.72 191	58.83 205	95.89 181	82.06 151	84.99 177	94.66 132

Fast-Effi-MVS+		81.14 200	80.01 204	84.51 197	90.24 164	65.86 193	94.12 82	89.15 333	73.81 224	75.37 225	88.26 274	57.26 228	94.53 271	66.97 314	84.92 180	93.15 214

LFMVS		84.34 115	82.73 150	89.18 14	94.76 36	73.25 14	94.99 47	91.89 179	71.90 271	82.16 115	93.49 137	47.98 344	97.05 108	82.55 146	84.82 181	97.25 9

BH-untuned		78.68 257	77.08 264	83.48 241	89.84 171	63.74 264	92.70 159	88.59 365	71.57 289	66.83 354	88.65 266	51.75 300	95.39 224	59.03 379	84.77 182	91.32 275

test-LLR		80.10 225	79.56 214	81.72 295	86.93 283	61.17 340	92.70 159	91.54 198	71.51 292	75.62 218	86.94 300	53.83 278	92.38 362	72.21 253	84.76 183	91.60 266

test-mter		79.96 228	79.38 223	81.72 295	86.93 283	61.17 340	92.70 159	91.54 198	73.85 222	75.62 218	86.94 300	49.84 325	92.38 362	72.21 253	84.76 183	91.60 266

fmvsm_s_conf0.5_n_2		85.06 92	85.60 80	83.44 243	86.92 285	60.53 359	94.41 69	87.31 395	83.30 33	88.72 47	96.72 33	54.28 274	97.75 59	94.07 22	84.68 185	92.04 256

sasdasda		86.85 49	86.25 65	88.66 21	91.80 126	71.92 19	93.54 117	91.71 190	80.26 82	87.55 55	95.25 80	63.59 122	96.93 125	88.18 70	84.34 186	97.11 10

canonicalmvs		86.85 49	86.25 65	88.66 21	91.80 126	71.92 19	93.54 117	91.71 190	80.26 82	87.55 55	95.25 80	63.59 122	96.93 125	88.18 70	84.34 186	97.11 10

alignmvs		87.28 42	86.97 49	88.24 30	91.30 142	71.14 30	95.61 26	93.56 95	79.30 113	87.07 61	95.25 80	68.43 58	96.93 125	87.87 73	84.33 188	96.65 19

VNet		86.20 67	85.65 79	87.84 34	93.92 53	69.99 43	95.73 23	95.94 7	78.43 134	86.00 72	93.07 143	58.22 215	97.00 113	85.22 104	84.33 188	96.52 25

UA-Net		80.02 227	79.65 212	81.11 316	89.33 184	57.72 400	86.33 380	89.00 349	77.44 157	81.01 130	89.15 258	59.33 193	95.90 180	61.01 367	84.28 190	89.73 301

LCM-MVSNet-Re		72.93 350	71.84 349	76.18 401	88.49 218	48.02 464	80.07 443	70.17 486	73.96 220	52.25 451	80.09 398	49.98 322	88.24 426	67.35 307	84.23 191	92.28 247

E4		84.00 127	83.19 136	86.46 100	86.99 275	68.85 86	92.39 183	90.99 242	79.94 88	80.17 149	91.36 203	59.73 185	95.79 193	82.87 142	84.22 192	94.74 123

ACMMP		81.49 190	80.67 192	83.93 219	91.71 129	62.90 298	92.13 193	92.22 160	71.79 278	71.68 285	93.49 137	50.32 317	96.96 121	78.47 198	84.22 192	91.93 261
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MGCFI-Net		85.59 83	85.73 78	85.17 156	91.41 140	62.44 306	92.87 151	91.31 209	79.65 99	86.99 63	95.14 86	62.90 138	96.12 166	87.13 85	84.13 194	96.96 14

fmvsm_s_conf0.1_n_2		84.40 112	84.78 97	83.27 249	85.25 330	60.41 362	94.13 81	85.69 420	83.05 35	87.99 51	96.37 40	52.75 291	97.68 61	93.75 26	84.05 195	91.71 264

Elysia		76.45 301	74.17 311	83.30 245	80.43 399	64.12 250	89.58 316	90.83 250	61.78 415	72.53 268	85.92 313	34.30 438	94.81 249	68.10 296	84.01 196	90.97 282

StellarMVS		76.45 301	74.17 311	83.30 245	80.43 399	64.12 250	89.58 316	90.83 250	61.78 415	72.53 268	85.92 313	34.30 438	94.81 249	68.10 296	84.01 196	90.97 282

onestephybrid01		83.68 139	83.31 132	84.81 175	86.53 294	65.38 206	90.54 289	89.14 335	79.52 107	81.01 130	92.02 175	58.91 203	94.91 248	88.26 69	83.86 198	94.14 170

hybridnocas07		83.76 135	83.21 133	85.39 141	86.64 289	67.40 137	91.08 263	88.77 358	79.78 96	80.35 146	92.15 168	59.24 197	94.67 261	87.11 87	83.79 199	94.11 173

hybrid		83.58 145	83.00 142	85.34 147	86.38 301	67.51 135	90.92 267	88.87 353	78.49 133	80.59 140	92.09 172	58.77 207	94.46 274	87.12 86	83.74 200	94.06 178

E6new		83.62 141	82.65 152	86.55 91	86.98 276	69.29 70	91.69 226	90.95 246	79.60 104	79.80 154	91.25 206	58.04 219	95.84 184	81.84 155	83.67 201	94.52 142

E6		83.62 141	82.65 152	86.55 91	86.98 276	69.29 70	91.69 226	90.95 246	79.60 104	79.80 154	91.25 206	58.04 219	95.84 184	81.84 155	83.67 201	94.52 142

E5new		83.62 141	82.65 152	86.55 91	86.98 276	69.28 72	91.69 226	90.96 243	79.61 101	79.80 154	91.25 206	58.04 219	95.84 184	81.83 157	83.66 203	94.52 142

E5		83.62 141	82.65 152	86.55 91	86.98 276	69.28 72	91.69 226	90.96 243	79.61 101	79.80 154	91.25 206	58.04 219	95.84 184	81.83 157	83.66 203	94.52 142

114514_t		79.17 244	77.67 249	83.68 232	95.32 32	65.53 202	92.85 152	91.60 197	63.49 393	67.92 334	90.63 219	46.65 364	95.72 203	67.01 313	83.54 205	89.79 299

testing11		86.71 56	86.44 61	87.55 44	93.54 66	71.35 25	93.65 111	95.58 12	81.36 61	80.69 137	92.21 167	72.30 38	96.46 149	85.18 106	83.43 206	94.82 118

test_vis1_n_1920		81.66 187	82.01 167	80.64 329	82.24 378	55.09 428	94.76 55	86.87 401	81.67 52	84.40 90	94.63 100	38.17 411	94.67 261	91.98 42	83.34 207	92.16 254

viewmamba		83.23 154	82.64 156	85.00 163	86.40 300	66.16 182	90.68 281	88.35 373	79.92 90	78.68 182	92.02 175	58.86 204	94.72 254	85.55 99	83.31 208	94.12 172

testing222		85.18 90	84.69 98	86.63 83	92.91 87	69.91 47	92.61 168	95.80 9	80.31 81	80.38 145	92.27 163	68.73 57	95.19 236	75.94 215	83.27 209	94.81 120

EPMVS		78.49 262	75.98 285	86.02 116	91.21 144	69.68 57	80.23 440	91.20 217	75.25 197	72.48 272	78.11 413	54.65 266	93.69 314	57.66 385	83.04 210	94.69 127

AdaColmap		78.94 250	77.00 267	84.76 179	96.34 18	65.86 193	92.66 166	87.97 386	62.18 407	70.56 295	92.37 161	43.53 386	97.35 87	64.50 344	82.86 211	91.05 281

CDS-MVSNet		81.43 191	80.74 189	83.52 237	86.26 303	64.45 233	92.09 196	90.65 263	75.83 187	73.95 250	89.81 247	63.97 112	92.91 340	71.27 262	82.82 212	93.20 213
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CHOSEN 280x420		77.35 284	76.95 268	78.55 372	87.07 273	62.68 303	69.71 477	82.95 446	68.80 338	71.48 288	87.27 295	66.03 83	84.00 459	76.47 211	82.81 213	88.95 309

UWE-MVS		80.81 209	81.01 185	80.20 339	89.33 184	57.05 412	91.91 210	94.71 43	75.67 188	75.01 229	89.37 253	63.13 134	91.44 393	67.19 311	82.80 214	92.12 255

ETVMVS		84.22 120	83.71 114	85.76 127	92.58 99	68.25 108	92.45 180	95.53 16	79.54 106	79.46 164	91.64 196	70.29 49	94.18 287	69.16 284	82.76 215	94.84 114

FBQ-MVS		86.03 71	85.15 88	88.66 21	93.10 80	73.31 13	92.70 159	95.27 21	81.43 58	82.52 113	91.06 213	67.89 66	96.56 141	79.87 180	82.51 216	96.13 43

viewdifsd2359ckpt09		83.52 146	82.57 158	86.37 105	88.02 241	68.47 99	91.78 219	89.63 313	79.61 101	78.56 184	92.00 178	59.28 195	95.96 178	81.94 153	82.35 217	94.69 127

PCF-MVS	73.15 9	79.29 242	77.63 252	84.29 206	86.06 309	65.96 189	87.03 370	91.10 228	69.86 322	69.79 309	90.64 217	57.54 227	96.59 138	64.37 345	82.29 218	90.32 291
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffseed414692147		82.20 175	80.75 188	86.55 91	87.13 271	69.57 59	91.79 216	90.48 267	78.12 139	78.52 185	90.10 242	55.92 251	95.80 191	72.42 251	82.28 219	94.28 160

viewmambaseed2359dif		82.60 169	81.91 169	84.67 188	85.83 315	66.09 183	90.50 290	89.01 345	75.46 191	79.64 161	92.01 177	59.51 189	94.38 278	82.99 140	82.26 220	93.54 201

fmvsm_s_conf0.5_n		86.39 60	86.91 51	84.82 172	87.36 262	63.54 278	94.74 56	90.02 296	82.52 41	90.14 37	96.92 24	62.93 137	97.84 56	95.28 11	82.26 220	93.07 219

WTY-MVS		86.32 63	85.81 75	87.85 33	92.82 91	69.37 67	95.20 35	95.25 22	82.71 39	81.91 116	94.73 97	67.93 65	97.63 68	79.55 183	82.25 222	96.54 24

testing99		86.01 72	85.47 81	87.63 42	93.62 61	71.25 27	93.47 123	95.23 23	80.42 77	80.60 139	91.95 182	71.73 44	96.50 147	80.02 179	82.22 223	95.13 97

HY-MVS	76.49 5	84.28 116	83.36 129	87.02 63	92.22 105	67.74 125	84.65 392	94.50 54	79.15 117	82.23 114	87.93 282	66.88 73	96.94 123	80.53 174	82.20 224	96.39 35

dtuplus		82.25 174	81.42 176	84.71 184	85.38 325	66.05 184	90.62 287	89.27 325	75.16 199	79.22 170	91.76 187	58.05 218	94.56 268	81.18 168	82.19 225	93.52 202

testing91		85.93 74	85.31 85	87.78 36	93.59 63	71.47 22	93.50 120	95.08 30	80.26 82	80.53 143	91.93 183	70.43 48	96.51 146	80.32 177	82.13 226	95.37 77

VDD-MVS		83.06 158	81.81 171	86.81 70	90.86 153	67.70 126	95.40 30	91.50 201	75.46 191	81.78 117	92.34 162	40.09 401	97.13 106	86.85 91	82.04 227	95.60 67

viewdifsd2359ckpt07		82.95 162	82.04 165	85.66 132	87.19 267	66.73 167	91.56 235	90.39 275	77.58 154	77.58 196	91.19 210	58.57 209	95.65 207	82.32 147	82.01 228	94.60 136

fmvsm_s_conf0.1_n		85.61 82	85.93 73	84.68 187	82.95 373	63.48 280	94.03 89	89.46 317	81.69 51	89.86 38	96.74 32	61.85 157	97.75 59	94.74 17	82.01 228	92.81 229

TAMVS		80.37 219	79.45 218	83.13 254	85.14 333	63.37 281	91.23 256	90.76 258	74.81 204	72.65 265	88.49 267	60.63 171	92.95 335	69.41 280	81.95 230	93.08 218

SSM_0404		79.46 238	77.65 250	84.91 167	88.37 228	67.04 151	89.59 315	87.03 398	67.99 347	75.45 223	89.32 254	47.98 344	95.34 228	71.23 263	81.90 231	92.34 243

test_yl		84.28 116	83.16 138	87.64 38	94.52 43	69.24 74	95.78 18	95.09 28	69.19 331	81.09 127	92.88 149	57.00 233	97.44 80	81.11 169	81.76 232	96.23 41

DCV-MVSNet		84.28 116	83.16 138	87.64 38	94.52 43	69.24 74	95.78 18	95.09 28	69.19 331	81.09 127	92.88 149	57.00 233	97.44 80	81.11 169	81.76 232	96.23 41

FA-MVS(test-final)		79.12 245	77.23 262	84.81 175	90.54 157	63.98 257	81.35 431	91.71 190	71.09 301	74.85 234	82.94 351	52.85 289	97.05 108	67.97 299	81.73 234	93.41 205

thisisatest0515		83.41 149	82.49 160	86.16 112	89.46 181	68.26 106	93.54 117	94.70 44	74.31 211	75.75 215	90.92 214	72.62 34	96.52 145	69.64 276	81.50 235	93.71 195

baseline2		83.68 139	83.42 126	84.48 198	87.37 261	66.00 187	90.06 305	95.93 8	79.71 97	69.08 314	90.39 224	77.92 7	96.28 157	78.91 194	81.38 236	91.16 279

PatchmatchNet		77.46 282	74.63 301	85.96 118	89.55 179	70.35 39	79.97 445	89.55 315	72.23 262	70.94 291	76.91 427	57.03 231	92.79 346	54.27 397	81.17 237	94.74 123
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VDDNet		80.50 215	78.26 239	87.21 55	86.19 304	69.79 52	94.48 63	91.31 209	60.42 423	79.34 166	90.91 215	38.48 409	96.56 141	82.16 148	81.05 238	95.27 89

icg_test_0407_2		80.38 218	79.22 226	83.88 220	88.54 209	64.75 221	86.79 375	90.80 253	76.73 174	73.95 250	90.18 230	51.55 304	92.45 360	73.47 234	80.95 239	94.43 153

IMVS_0407		80.80 210	79.39 222	85.00 163	88.54 209	64.75 221	88.40 348	90.80 253	76.73 174	73.95 250	90.18 230	51.55 304	95.81 190	73.47 234	80.95 239	94.43 153

IMVS_0404		78.11 269	76.29 280	83.59 235	88.54 209	64.75 221	84.63 393	90.80 253	76.73 174	61.16 401	90.18 230	40.17 400	91.58 386	73.47 234	80.95 239	94.43 153

IMVS_0403		81.19 198	79.88 207	85.13 158	88.54 209	64.75 221	88.84 340	90.80 253	76.73 174	75.21 226	90.18 230	54.22 275	96.21 161	73.47 234	80.95 239	94.43 153

EPNet_dtu		78.80 254	79.26 225	77.43 385	88.06 238	49.71 457	91.96 206	91.95 175	77.67 150	76.56 211	91.28 205	58.51 211	90.20 407	56.37 389	80.95 239	92.39 241
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		82.71 166	82.38 162	83.73 228	89.25 188	59.58 379	92.24 188	94.89 33	77.96 141	79.86 153	92.38 160	56.70 239	97.05 108	77.26 205	80.86 244	94.55 138

FE-MVS		75.97 312	73.02 332	84.82 172	89.78 172	65.56 200	77.44 456	91.07 234	64.55 382	72.66 264	79.85 400	46.05 372	96.69 136	54.97 394	80.82 245	92.21 252

GeoE		78.90 251	77.43 256	83.29 247	88.95 199	62.02 317	92.31 184	86.23 410	70.24 316	71.34 290	89.27 256	54.43 271	94.04 297	63.31 352	80.81 246	93.81 193

UWE-MVS-28		76.83 295	77.60 253	74.51 416	84.58 345	50.34 453	88.22 351	94.60 51	74.46 206	66.66 356	88.98 264	62.53 142	85.50 451	57.55 386	80.80 247	87.69 329

LuminaMVS		78.14 268	76.66 271	82.60 267	80.82 393	64.64 227	89.33 327	90.45 268	68.25 345	74.73 236	85.51 321	41.15 396	94.14 288	78.96 193	80.69 248	89.04 308

fmvsm_s_conf0.5_n_a		85.75 78	86.09 70	84.72 182	85.73 320	63.58 275	93.79 105	89.32 323	81.42 59	90.21 35	96.91 25	62.41 144	97.67 63	94.48 18	80.56 249	92.90 225

TR-MVS		78.77 256	77.37 261	82.95 257	90.49 159	60.88 346	93.67 110	90.07 292	70.08 319	74.51 238	91.37 202	45.69 374	95.70 204	60.12 374	80.32 250	92.29 246

fmvsm_s_conf0.1_n_a		84.76 102	84.84 95	84.53 195	80.23 405	63.50 279	92.79 153	88.73 359	80.46 75	89.84 39	96.65 35	60.96 166	97.57 73	93.80 25	80.14 251	92.53 238

TAPA-MVS	70.22 12	74.94 328	73.53 323	79.17 366	90.40 161	52.07 441	89.19 333	89.61 314	62.69 404	70.07 303	92.67 153	48.89 338	94.32 279	38.26 469	79.97 252	91.12 280
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
nomal-1		82.17 177	81.45 175	84.34 204	90.99 148	69.47 61	83.86 400	93.64 92	77.94 143	73.62 254	85.72 317	66.65 75	91.90 376	80.76 172	79.90 253	91.64 265

test_cas_vis1_n_1920		80.45 217	80.61 194	79.97 348	78.25 432	57.01 414	94.04 87	88.33 374	79.06 122	82.81 109	93.70 131	38.65 406	91.63 384	90.82 55	79.81 254	91.27 278

cascas		78.18 266	75.77 288	85.41 140	87.14 270	69.11 77	92.96 144	91.15 222	66.71 361	70.47 296	86.07 310	37.49 420	96.48 148	70.15 274	79.80 255	90.65 287

HyFIR lowres test		81.03 204	79.56 214	85.43 139	87.81 250	68.11 113	90.18 302	90.01 297	70.65 312	72.95 260	86.06 311	63.61 121	94.50 273	75.01 224	79.75 256	93.67 196

mamba_0408		76.22 303	73.37 326	84.77 177	88.50 214	66.98 157	58.80 497	86.18 412	69.12 334	74.12 244	89.01 262	47.50 351	95.35 226	67.57 305	79.52 257	91.98 258

SSM_04072		74.86 330	73.37 326	79.35 363	88.50 214	66.98 157	58.80 497	86.18 412	69.12 334	74.12 244	89.01 262	47.50 351	79.09 484	67.57 305	79.52 257	91.98 258

SSM_0407		79.09 246	77.21 263	84.75 180	88.50 214	66.98 157	89.21 331	87.03 398	67.99 347	74.12 244	89.32 254	47.98 344	95.29 233	71.23 263	79.52 257	91.98 258

WB-MVSnew		77.14 287	76.18 283	80.01 345	86.18 305	63.24 286	91.26 253	94.11 74	71.72 281	73.52 255	87.29 294	45.14 379	93.00 333	56.98 387	79.42 260	83.80 405

LS3D		69.17 386	66.40 390	77.50 383	91.92 121	56.12 420	85.12 388	80.37 455	46.96 475	56.50 435	87.51 290	37.25 421	93.71 311	32.52 489	79.40 261	82.68 425

EI-MVSNet-Vis-set		83.77 134	83.67 115	84.06 213	92.79 94	63.56 276	91.76 222	94.81 38	79.65 99	77.87 190	94.09 123	63.35 127	97.90 52	79.35 187	79.36 262	90.74 286

CVMVSNet		74.04 338	74.27 309	73.33 426	85.33 326	43.94 483	89.53 323	88.39 370	54.33 455	70.37 299	90.13 239	49.17 334	84.05 457	61.83 364	79.36 262	91.99 257

guyue		81.23 197	80.57 196	83.21 253	86.64 289	61.85 322	92.52 178	92.78 133	78.69 129	74.92 232	89.42 252	50.07 321	95.35 226	80.79 171	79.31 264	92.42 240

EPP-MVSNet		81.79 185	81.52 173	82.61 266	88.77 204	60.21 368	93.02 141	93.66 91	68.52 342	72.90 261	90.39 224	72.19 40	94.96 243	74.93 225	79.29 265	92.67 231

SD_0403		73.79 342	73.48 325	74.69 413	85.33 326	45.56 479	83.80 401	85.57 421	76.55 181	62.96 389	88.45 268	50.62 316	87.59 436	48.80 422	79.28 266	90.92 284

CLD-MVS		82.73 164	82.35 163	83.86 221	87.90 244	67.65 128	95.45 29	92.18 164	85.06 15	72.58 267	92.27 163	52.46 294	95.78 194	84.18 122	79.06 267	88.16 324
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP3-MVS								91.70 193							78.90 268

HQP-MVS		81.14 200	80.64 193	82.64 265	87.54 256	63.66 273	94.06 83	91.70 193	79.80 93	74.18 240	90.30 227	51.63 302	95.61 212	77.63 203	78.90 268	88.63 314

plane_prior						62.42 307	93.85 99		79.38 111						78.80 270

thres200		79.66 232	78.33 237	83.66 234	92.54 100	65.82 195	93.06 137	96.31 3	74.90 203	73.30 257	88.66 265	59.67 186	95.61 212	47.84 429	78.67 271	89.56 304

ET-MVSNet_ETH3D		84.01 126	83.15 140	86.58 87	90.78 155	70.89 32	94.74 56	94.62 49	81.44 57	58.19 425	93.64 133	73.64 27	92.35 365	82.66 144	78.66 272	96.50 29

HQP_MVS		80.34 220	79.75 211	82.12 286	86.94 281	62.42 307	93.13 135	91.31 209	78.81 126	72.53 268	89.14 259	50.66 314	95.55 218	76.74 206	78.53 273	88.39 320

plane_prior5								91.31 209					95.55 218	76.74 206	78.53 273	88.39 320

EI-MVSNet-UG-set		83.14 156	82.96 143	83.67 233	92.28 103	63.19 289	91.38 244	94.68 45	79.22 115	76.60 209	93.75 129	62.64 140	97.76 58	78.07 201	78.01 275	90.05 295

OMC-MVS		78.67 259	77.91 248	80.95 323	85.76 318	57.40 407	88.49 346	88.67 362	73.85 222	72.43 274	92.10 171	49.29 332	94.55 270	72.73 246	77.89 276	90.91 285

1112_ss		80.56 214	79.83 209	82.77 260	88.65 206	60.78 348	92.29 185	88.36 371	72.58 251	72.46 273	94.95 89	65.09 94	93.42 324	66.38 320	77.71 277	94.10 174

OPM-MVS		79.00 248	78.09 241	81.73 294	83.52 365	63.83 261	91.64 232	90.30 281	76.36 183	71.97 280	89.93 246	46.30 370	95.17 237	75.10 222	77.70 278	86.19 367
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
dtuonly		74.56 333	73.92 317	76.48 397	77.15 443	57.27 409	85.09 389	81.23 449	71.37 295	67.61 342	89.65 249	46.68 363	83.84 461	68.79 290	77.69 279	88.33 322

PatchMatch-RL		72.06 364	69.98 363	78.28 375	89.51 180	55.70 424	83.49 405	83.39 444	61.24 418	63.72 381	82.76 353	34.77 435	93.03 332	53.37 404	77.59 280	86.12 371

thres100view900		78.37 263	77.01 266	82.46 269	91.89 124	63.21 288	91.19 260	96.33 1	72.28 261	70.45 298	87.89 283	60.31 175	95.32 229	45.16 442	77.58 281	88.83 310

tfpn200view9		78.79 255	77.43 256	82.88 258	92.21 106	64.49 230	92.05 199	96.28 4	73.48 232	71.75 283	88.26 274	60.07 180	95.32 229	45.16 442	77.58 281	88.83 310

thres400		78.68 257	77.43 256	82.43 270	92.21 106	64.49 230	92.05 199	96.28 4	73.48 232	71.75 283	88.26 274	60.07 180	95.32 229	45.16 442	77.58 281	87.48 332

CostFormer		82.33 172	81.15 179	85.86 122	89.01 198	68.46 100	82.39 422	93.01 123	75.59 189	80.25 148	81.57 372	72.03 41	94.96 243	79.06 191	77.48 284	94.16 168

tpm2		79.80 231	77.95 246	85.34 147	88.28 230	68.26 106	81.56 428	91.42 204	70.11 317	77.59 195	80.50 390	67.40 70	94.26 285	67.34 308	77.35 285	93.51 203

Test_1112_low_res		79.56 234	78.60 235	82.43 270	88.24 233	60.39 364	92.09 196	87.99 384	72.10 267	71.84 281	87.42 291	64.62 102	93.04 331	65.80 327	77.30 286	93.85 192

tpmrst		80.57 213	79.14 229	84.84 171	90.10 167	68.28 105	81.70 426	89.72 310	77.63 153	75.96 214	79.54 404	64.94 97	92.71 348	75.43 219	77.28 287	93.55 200

Anonymous202405211		77.96 272	75.33 294	85.87 121	93.73 59	64.52 229	94.85 52	85.36 423	62.52 405	76.11 213	90.18 230	29.43 460	97.29 91	68.51 292	77.24 288	95.81 60

GA-MVS		78.33 265	76.23 281	84.65 189	83.65 363	66.30 178	91.44 237	90.14 290	76.01 185	70.32 300	84.02 340	42.50 390	94.72 254	70.98 266	77.00 289	92.94 223

AstraMVS		80.66 212	79.79 210	83.28 248	85.07 336	61.64 330	92.19 190	90.58 265	79.40 110	74.77 235	90.18 230	45.93 373	95.61 212	83.04 139	76.96 290	92.60 234

thisisatest0530		81.15 199	80.07 202	84.39 201	88.26 231	65.63 198	91.40 240	94.62 49	71.27 297	70.93 292	89.18 257	72.47 35	96.04 173	65.62 331	76.89 291	91.49 268

thres600view7		78.00 270	76.66 271	82.03 291	91.93 120	63.69 271	91.30 252	96.33 1	72.43 256	70.46 297	87.89 283	60.31 175	94.92 246	42.64 454	76.64 292	87.48 332

PLC	68.80 14	75.23 323	73.68 322	79.86 351	92.93 86	58.68 391	90.64 284	88.30 375	60.90 420	64.43 375	90.53 220	42.38 391	94.57 265	56.52 388	76.54 293	86.33 363
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MIMVSNet		71.64 367	68.44 380	81.23 311	81.97 382	64.44 234	73.05 468	88.80 356	69.67 325	64.59 370	74.79 445	32.79 444	87.82 430	53.99 398	76.35 294	91.42 270

test_fmvs1		74.07 337	73.69 321	75.22 406	78.91 423	47.34 469	89.06 337	74.69 472	63.68 392	79.41 165	91.59 197	24.36 471	87.77 432	85.22 104	76.26 295	90.55 290

MVS-HIRNet		60.25 441	55.55 448	74.35 418	84.37 351	56.57 418	71.64 472	74.11 473	34.44 495	45.54 479	42.24 508	31.11 454	89.81 412	40.36 463	76.10 296	76.67 475

CNLPA		74.31 335	72.30 344	80.32 334	91.49 136	61.66 329	90.85 272	80.72 453	56.67 447	63.85 380	90.64 217	46.75 362	90.84 396	53.79 400	75.99 297	88.47 319

ab-mvs		80.18 223	78.31 238	85.80 125	88.44 222	65.49 204	83.00 416	92.67 140	71.82 277	77.36 198	85.01 326	54.50 267	96.59 138	76.35 213	75.63 298	95.32 83

test_fmvs1_n		72.69 357	71.92 348	74.99 411	71.15 472	47.08 471	87.34 368	75.67 467	63.48 394	78.08 189	91.17 211	20.16 485	87.87 429	84.65 113	75.57 299	90.01 296

testing3-2		83.11 157	83.15 140	82.98 256	91.92 121	64.01 255	94.39 72	95.37 17	78.32 135	75.53 222	90.06 243	73.18 29	93.18 329	74.34 231	75.27 300	91.77 263

FIs		79.47 237	79.41 220	79.67 356	85.95 311	59.40 381	91.68 230	93.94 78	78.06 140	68.96 319	88.28 272	66.61 77	91.77 380	66.20 323	74.99 301	87.82 327

SDMVSNet		80.26 221	78.88 232	84.40 200	89.25 188	67.63 129	85.35 386	93.02 122	76.77 172	70.84 293	87.12 296	47.95 347	96.09 168	85.04 107	74.55 302	89.48 305

sd_testset		77.08 289	75.37 292	82.20 282	89.25 188	62.11 316	82.06 423	89.09 339	76.77 172	70.84 293	87.12 296	41.43 395	95.01 241	67.23 310	74.55 302	89.48 305

CMPMVS	48.56 21	66.77 408	64.41 408	73.84 423	70.65 475	50.31 454	77.79 455	85.73 419	45.54 480	44.76 481	82.14 362	35.40 433	90.14 408	63.18 354	74.54 304	81.07 440
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dmvs_re		76.93 291	75.36 293	81.61 299	87.78 252	60.71 354	80.00 444	87.99 384	79.42 109	69.02 316	89.47 251	46.77 361	94.32 279	63.38 351	74.45 305	89.81 298

test_vis1_n		71.63 368	70.73 359	74.31 420	69.63 479	47.29 470	86.91 372	72.11 480	63.21 398	75.18 227	90.17 236	20.40 483	85.76 447	84.59 115	74.42 306	89.87 297

XVG-OURS		74.25 336	72.46 343	79.63 357	78.45 430	57.59 404	80.33 438	87.39 390	63.86 389	68.76 323	89.62 250	40.50 399	91.72 381	69.00 286	74.25 307	89.58 302

tpm cat1		75.30 322	72.21 345	84.58 194	88.52 213	67.77 123	78.16 454	88.02 383	61.88 413	68.45 328	76.37 436	60.65 170	94.03 299	53.77 401	74.11 308	91.93 261

XVG-OURS-SEG-HR		74.70 332	73.08 331	79.57 359	78.25 432	57.33 408	80.49 436	87.32 393	63.22 397	68.76 323	90.12 241	44.89 381	91.59 385	70.55 272	74.09 309	89.79 299

FC-MVSNet-test		77.99 271	78.08 242	77.70 380	84.89 339	55.51 425	90.27 299	93.75 87	76.87 167	66.80 355	87.59 288	65.71 88	90.23 406	62.89 357	73.94 310	87.37 335

PVSNet_BlendedMVS		83.38 150	83.43 124	83.22 251	93.76 56	67.53 132	94.06 83	93.61 93	79.13 118	81.00 132	85.14 325	63.19 130	97.29 91	87.08 88	73.91 311	84.83 396

tttt0517		79.50 235	78.53 236	82.41 273	87.22 265	61.43 337	89.75 314	94.76 40	69.29 329	67.91 335	88.06 281	72.92 31	95.63 208	62.91 356	73.90 312	90.16 293

MDTV_nov1_ep13			72.61 340		89.06 195	68.48 98	80.33 438	90.11 291	71.84 276	71.81 282	75.92 440	53.01 288	93.92 304	48.04 426	73.38 313

SCA		75.82 315	72.76 336	85.01 162	86.63 291	70.08 42	81.06 433	89.19 330	71.60 288	70.01 304	77.09 425	45.53 375	90.25 402	60.43 371	73.27 314	94.68 129

CR-MVSNet		73.79 342	70.82 358	82.70 263	83.15 369	67.96 116	70.25 474	84.00 436	73.67 230	69.97 306	72.41 453	57.82 224	89.48 415	52.99 405	73.13 315	90.64 288

RPMNet		70.42 376	65.68 396	84.63 192	83.15 369	67.96 116	70.25 474	90.45 268	46.83 477	69.97 306	65.10 479	56.48 245	95.30 232	35.79 474	73.13 315	90.64 288

Fast-Effi-MVS+-dtu		75.04 326	73.37 326	80.07 342	80.86 391	59.52 380	91.20 259	85.38 422	71.90 271	65.20 365	84.84 328	41.46 394	92.97 334	66.50 319	72.96 317	87.73 328

LPG-MVS_test		75.82 315	74.58 303	79.56 360	84.31 352	59.37 382	90.44 291	89.73 308	69.49 326	64.86 367	88.42 269	38.65 406	94.30 281	72.56 248	72.76 318	85.01 394

LGP-MVS_train				79.56 360	84.31 352	59.37 382		89.73 308	69.49 326	64.86 367	88.42 269	38.65 406	94.30 281	72.56 248	72.76 318	85.01 394

EG-PatchMatch MVS		68.55 392	65.41 399	77.96 379	78.69 426	62.93 295	89.86 312	89.17 331	60.55 422	50.27 461	77.73 417	22.60 479	94.06 294	47.18 433	72.65 320	76.88 474

EI-MVSNet		78.97 249	78.22 240	81.25 310	85.33 326	62.73 302	89.53 323	93.21 111	72.39 258	72.14 277	90.13 239	60.99 164	94.72 254	67.73 303	72.49 321	86.29 364

MVSTER		82.47 170	82.05 164	83.74 226	92.68 96	69.01 82	91.90 211	93.21 111	79.83 92	72.14 277	85.71 318	74.72 19	94.72 254	75.72 217	72.49 321	87.50 331

Anonymous20240529		76.84 294	74.15 313	84.88 169	91.02 147	64.95 218	93.84 102	91.09 229	53.57 456	73.00 258	87.42 291	35.91 431	97.32 89	69.14 285	72.41 323	92.36 242

D2MVS		73.80 341	72.02 347	79.15 368	79.15 418	62.97 293	88.58 345	90.07 292	72.94 242	59.22 418	78.30 410	42.31 392	92.70 350	65.59 332	72.00 324	81.79 434

PS-MVSNAJss		77.26 285	76.31 279	80.13 341	80.64 397	59.16 386	90.63 286	91.06 235	72.80 247	68.58 326	84.57 332	53.55 282	93.96 302	72.97 240	71.96 325	87.27 339

Effi-MVS+-dtu		76.14 305	75.28 295	78.72 371	83.22 368	55.17 427	89.87 311	87.78 388	75.42 193	67.98 333	81.43 374	45.08 380	92.52 357	75.08 223	71.63 326	88.48 318

ACMMP++_ref															71.63 326

ACMM	69.62 13	74.34 334	72.73 338	79.17 366	84.25 354	57.87 398	90.36 296	89.93 299	63.17 399	65.64 362	86.04 312	37.79 418	94.10 290	65.89 325	71.52 328	85.55 386
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	71.68 10	75.58 320	74.23 310	79.62 358	84.97 338	59.64 377	90.80 274	89.07 341	70.39 314	62.95 390	87.30 293	38.28 410	93.87 307	72.89 241	71.45 329	85.36 390
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
dp		75.01 327	72.09 346	83.76 225	89.28 187	66.22 181	79.96 446	89.75 305	71.16 298	67.80 339	77.19 424	51.81 298	92.54 356	50.39 412	71.44 330	92.51 239

tpm		78.58 260	77.03 265	83.22 251	85.94 313	64.56 228	83.21 412	91.14 223	78.31 136	73.67 253	79.68 402	64.01 111	92.09 373	66.07 324	71.26 331	93.03 220

DP-MVS		69.90 381	66.48 388	80.14 340	95.36 31	62.93 295	89.56 318	76.11 465	50.27 467	57.69 431	85.23 324	39.68 402	95.73 198	33.35 481	71.05 332	81.78 435

UniMVSNet_ETH3D		72.74 354	70.53 361	79.36 362	78.62 428	56.64 416	85.01 390	89.20 329	63.77 390	64.84 369	84.44 334	34.05 440	91.86 378	63.94 347	70.89 333	89.57 303

usedtu_dtu_shiyan1		77.89 276	76.39 277	82.40 274	81.92 383	67.01 155	91.94 208	93.00 125	77.01 164	68.44 329	84.15 336	54.78 264	93.25 326	65.76 328	70.53 334	86.94 344

FE-MVSNET3		77.89 276	76.39 277	82.40 274	81.92 383	67.01 155	91.94 208	93.00 125	77.01 164	68.44 329	84.15 336	54.78 264	93.25 326	65.76 328	70.53 334	86.94 344

jajsoiax		73.05 348	71.51 353	77.67 381	77.46 440	54.83 429	88.81 341	90.04 295	69.13 333	62.85 392	83.51 345	31.16 453	92.75 347	70.83 267	69.80 336	85.43 389

ACMMP++															69.72 337

mvs_tets		72.71 355	71.11 354	77.52 382	77.41 441	54.52 431	88.45 347	89.76 304	68.76 340	62.70 393	83.26 349	29.49 459	92.71 348	70.51 273	69.62 338	85.34 391

tpmvs		72.88 352	69.76 368	82.22 281	90.98 149	67.05 150	78.22 453	88.30 375	63.10 400	64.35 376	74.98 443	55.09 261	94.27 283	43.25 448	69.57 339	85.34 391

GBi-Net		75.65 317	73.83 319	81.10 317	88.85 200	65.11 213	90.01 307	90.32 277	70.84 305	67.04 350	80.25 395	48.03 341	91.54 388	59.80 376	69.34 340	86.64 350

test1		75.65 317	73.83 319	81.10 317	88.85 200	65.11 213	90.01 307	90.32 277	70.84 305	67.04 350	80.25 395	48.03 341	91.54 388	59.80 376	69.34 340	86.64 350

FMVSNet3		77.73 278	76.04 284	82.80 259	91.20 145	68.99 83	91.87 212	91.99 173	73.35 234	67.04 350	83.19 350	56.62 241	92.14 370	59.80 376	69.34 340	87.28 338

Syy-MVS		69.65 383	69.52 369	70.03 447	87.87 247	43.21 485	88.07 353	89.01 345	72.91 244	63.11 386	88.10 278	45.28 378	85.54 448	22.07 501	69.23 343	81.32 437

myMVS_eth3d		72.58 359	72.74 337	72.10 438	87.87 247	49.45 459	88.07 353	89.01 345	72.91 244	63.11 386	88.10 278	63.63 119	85.54 448	32.73 487	69.23 343	81.32 437

MSDG		69.54 384	65.73 395	80.96 322	85.11 335	63.71 268	84.19 397	83.28 445	56.95 444	54.50 440	84.03 339	31.50 450	96.03 174	42.87 452	69.13 345	83.14 417

JIA-IIPM		66.06 411	62.45 420	76.88 395	81.42 389	54.45 432	57.49 499	88.67 362	49.36 470	63.86 379	46.86 498	56.06 249	90.25 402	49.53 417	68.83 346	85.95 375

OpenMVS_ROB	61.12 18	66.39 409	62.92 417	76.80 396	76.51 445	57.77 399	89.22 330	83.41 443	55.48 452	53.86 444	77.84 415	26.28 469	93.95 303	34.90 476	68.76 347	78.68 464

FMVSNet2		76.07 306	74.01 316	82.26 280	88.85 200	67.66 127	91.33 250	91.61 196	70.84 305	65.98 359	82.25 360	48.03 341	92.00 375	58.46 381	68.73 348	87.10 341

test_djsdf		73.76 344	72.56 341	77.39 386	77.00 444	53.93 433	89.07 335	90.69 259	65.80 372	63.92 378	82.03 363	43.14 389	92.67 351	72.83 242	68.53 349	85.57 385

F-COLMAP		70.66 373	68.44 380	77.32 387	86.37 302	55.91 422	88.00 355	86.32 407	56.94 445	57.28 433	88.07 280	33.58 442	92.49 358	51.02 409	68.37 350	83.55 407

XVG-ACMP-BASELINE		68.04 398	65.53 398	75.56 403	74.06 463	52.37 439	78.43 450	85.88 416	62.03 410	58.91 422	81.21 382	20.38 484	91.15 395	60.69 370	68.18 351	83.16 416

WBMVS		81.67 186	80.98 186	83.72 230	93.07 82	69.40 63	94.33 73	93.05 121	76.84 169	72.05 279	84.14 338	74.49 21	93.88 306	72.76 245	68.09 352	87.88 326

LTVRE_ROB	59.60 19	66.27 410	63.54 413	74.45 417	84.00 357	51.55 444	67.08 485	83.53 441	58.78 434	54.94 439	80.31 393	34.54 436	93.23 328	40.64 462	68.03 353	78.58 465
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
XXY-MVS		77.94 273	76.44 274	82.43 270	82.60 375	64.44 234	92.01 201	91.83 184	73.59 231	70.00 305	85.82 315	54.43 271	94.76 251	69.63 277	68.02 354	88.10 325

viewdifsd2359ckpt11		79.42 240	77.95 246	83.81 223	83.87 359	63.85 258	89.54 320	87.38 391	77.39 160	74.94 230	89.95 244	51.11 310	94.72 254	79.52 184	67.90 355	92.88 227

viewmsd2359difaftdt		79.42 240	77.96 245	83.81 223	83.88 358	63.85 258	89.54 320	87.38 391	77.39 160	74.94 230	89.95 244	51.11 310	94.72 254	79.52 184	67.90 355	92.88 227

ADS-MVSNet2		66.90 406	63.44 414	77.26 389	88.06 238	60.70 355	68.01 481	75.56 469	57.57 438	64.48 372	69.87 465	38.68 404	84.10 456	40.87 460	67.89 357	86.97 342

ADS-MVSNet		68.54 393	64.38 409	81.03 321	88.06 238	66.90 162	68.01 481	84.02 435	57.57 438	64.48 372	69.87 465	38.68 404	89.21 417	40.87 460	67.89 357	86.97 342

test0.0.03 1		72.76 353	72.71 339	72.88 430	80.25 404	47.99 465	91.22 257	89.45 318	71.51 292	62.51 395	87.66 286	53.83 278	85.06 453	50.16 414	67.84 359	85.58 384

anonymousdsp		71.14 371	69.37 372	76.45 398	72.95 467	54.71 430	84.19 397	88.88 351	61.92 412	62.15 396	79.77 401	38.14 413	91.44 393	68.90 288	67.45 360	83.21 415

tt0805		73.07 347	70.73 359	80.07 342	78.37 431	57.05 412	87.78 360	92.18 164	61.23 419	67.04 350	86.49 305	31.35 452	94.58 263	65.06 337	67.12 361	88.57 316

VPA-MVSNet		79.03 247	78.00 243	82.11 289	85.95 311	64.48 232	93.22 133	94.66 46	75.05 201	74.04 248	84.95 327	52.17 296	93.52 317	74.90 227	67.04 362	88.32 323

nrg030		80.93 206	79.86 208	84.13 212	83.69 362	68.83 87	93.23 132	91.20 217	75.55 190	75.06 228	88.22 277	63.04 136	94.74 253	81.88 154	66.88 363	88.82 312

FMVSNet1		72.71 355	69.91 366	81.10 317	83.60 364	65.11 213	90.01 307	90.32 277	63.92 388	63.56 382	80.25 395	36.35 430	91.54 388	54.46 396	66.75 364	86.64 350

PatchT		69.11 387	65.37 400	80.32 334	82.07 381	63.68 272	67.96 483	87.62 389	50.86 465	69.37 310	65.18 478	57.09 230	88.53 422	41.59 458	66.60 365	88.74 313

IB-MVS	77.80 4	82.18 176	80.46 199	87.35 51	89.14 193	70.28 40	95.59 27	95.17 26	78.85 124	70.19 302	85.82 315	70.66 47	97.67 63	72.19 255	66.52 366	94.09 175
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
test_fmvs2		65.78 414	64.84 401	68.60 454	66.54 486	41.71 488	83.27 409	69.81 487	54.38 454	67.91 335	84.54 333	15.35 491	81.22 480	75.65 218	66.16 367	82.88 418

pmmvs5		73.35 345	71.52 352	78.86 370	78.64 427	60.61 358	91.08 263	86.90 400	67.69 351	63.32 384	83.64 343	44.33 384	90.53 399	62.04 362	66.02 368	85.46 388

SSC-MVS3.2		74.92 329	73.32 329	79.74 355	86.53 294	60.31 365	89.03 338	92.70 136	78.61 131	68.98 318	83.34 348	41.93 393	92.23 369	52.77 406	65.97 369	86.69 349

dmvs_testset		65.55 415	66.45 389	62.86 467	79.87 408	22.35 516	76.55 458	71.74 482	77.42 159	55.85 436	87.77 285	51.39 306	80.69 481	31.51 493	65.92 370	85.55 386

MonoMVSNet		76.99 290	75.08 297	82.73 261	83.32 367	63.24 286	86.47 379	86.37 406	79.08 120	66.31 358	79.30 406	49.80 326	91.72 381	79.37 186	65.70 371	93.23 211

pmmvs4		73.92 340	71.81 350	80.25 338	79.17 417	65.24 209	87.43 366	87.26 396	67.64 354	63.46 383	83.91 342	48.96 337	91.53 391	62.94 355	65.49 372	83.96 402

cl22		77.94 273	76.78 269	81.42 303	87.57 255	64.93 219	90.67 282	88.86 354	72.45 255	67.63 341	82.68 355	64.07 109	92.91 340	71.79 256	65.30 373	86.44 357

miper_ehance_all_eth		77.60 280	76.44 274	81.09 320	85.70 321	64.41 237	90.65 283	88.64 364	72.31 259	67.37 348	82.52 356	64.77 101	92.64 354	70.67 270	65.30 373	86.24 366

miper_enhance_ethall		78.86 252	77.97 244	81.54 301	88.00 242	65.17 211	91.41 238	89.15 333	75.19 198	68.79 322	83.98 341	67.17 71	92.82 343	72.73 246	65.30 373	86.62 354

VortexMVS		77.62 279	76.44 274	81.13 314	88.58 207	63.73 266	91.24 255	91.30 213	77.81 146	65.76 360	81.97 364	49.69 327	93.72 310	76.40 212	65.26 376	85.94 377

v1144		76.73 298	74.88 298	82.27 278	80.23 405	66.60 171	91.68 230	90.21 289	73.69 228	69.06 315	81.89 365	52.73 292	94.40 277	69.21 283	65.23 377	85.80 380

DSMNet-mixed		56.78 448	54.44 451	63.79 465	63.21 491	29.44 509	64.43 488	64.10 496	42.12 492	51.32 456	71.60 459	31.76 449	75.04 489	36.23 471	65.20 378	86.87 347

v1192		75.98 311	73.92 317	82.15 284	79.73 409	66.24 180	91.22 257	89.75 305	72.67 249	68.49 327	81.42 375	49.86 324	94.27 283	67.08 312	65.02 379	85.95 375

v2v482		77.42 283	75.65 290	82.73 261	80.38 401	67.13 148	91.85 214	90.23 286	75.09 200	69.37 310	83.39 347	53.79 280	94.44 275	71.77 257	65.00 380	86.63 353

V42		76.46 300	74.55 304	82.19 283	79.14 419	67.82 122	90.26 300	89.42 320	73.75 225	68.63 325	81.89 365	51.31 307	94.09 291	71.69 259	64.84 381	84.66 397

ACMH	63.93 17	68.62 391	64.81 402	80.03 344	85.22 331	63.25 285	87.72 361	84.66 429	60.83 421	51.57 455	79.43 405	27.29 466	94.96 243	41.76 456	64.84 381	81.88 433
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline1		81.84 184	81.03 184	84.28 207	91.60 131	66.62 170	91.08 263	91.66 195	81.87 49	74.86 233	91.67 194	69.98 52	94.92 246	71.76 258	64.75 383	91.29 277

v1240		75.21 324	72.98 334	81.88 292	79.20 416	66.00 187	90.75 277	89.11 338	71.63 287	67.41 346	81.22 380	47.36 353	93.87 307	65.46 334	64.72 384	85.77 381

IterMVS-LS		76.49 299	75.18 296	80.43 333	84.49 348	62.74 301	90.64 284	88.80 356	72.40 257	65.16 366	81.72 368	60.98 165	92.27 368	67.74 302	64.65 385	86.29 364
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		75.63 319	73.49 324	82.06 290	79.38 414	66.35 176	91.07 266	89.48 316	71.98 268	67.99 332	81.22 380	49.16 335	93.90 305	66.56 316	64.56 386	85.92 378

v144192		76.05 309	74.03 315	82.12 286	79.50 413	66.55 173	91.39 242	89.71 311	72.30 260	68.17 331	81.33 377	51.75 300	94.03 299	67.94 300	64.19 387	85.77 381

Anonymous20231211		73.08 346	70.39 362	81.13 314	90.62 156	63.33 282	91.40 240	90.06 294	51.84 461	64.46 374	80.67 388	36.49 429	94.07 293	63.83 348	64.17 388	85.98 374

testing3		70.38 377	70.83 356	69.03 452	85.82 316	43.93 484	90.72 280	90.56 266	68.06 346	60.24 412	86.82 302	64.83 99	84.12 455	26.33 496	64.10 389	79.04 459

Patchmatch-test		65.86 412	60.94 427	80.62 331	83.75 361	58.83 389	58.91 496	75.26 471	44.50 484	50.95 460	77.09 425	58.81 206	87.90 428	35.13 475	64.03 390	95.12 98

USDC		67.43 405	64.51 406	76.19 400	77.94 436	55.29 426	78.38 451	85.00 426	73.17 236	48.36 470	80.37 392	21.23 481	92.48 359	52.15 407	64.02 391	80.81 443

VPNet		78.82 253	77.53 255	82.70 263	84.52 346	66.44 174	93.93 93	92.23 157	80.46 75	72.60 266	88.38 271	49.18 333	93.13 330	72.47 250	63.97 392	88.55 317

Anonymous20231206		67.53 403	65.78 394	72.79 431	74.95 459	47.59 467	88.23 350	87.32 393	61.75 417	58.07 427	77.29 421	37.79 418	87.29 440	42.91 450	63.71 393	83.48 410

WR-MVS		76.76 297	75.74 289	79.82 352	84.60 343	62.27 313	92.60 170	92.51 149	76.06 184	67.87 338	85.34 323	56.76 237	90.24 405	62.20 361	63.69 394	86.94 344

blend_shiyan4		75.18 325	73.00 333	81.69 297	75.62 452	64.75 221	91.78 219	91.06 235	65.89 371	61.35 400	77.39 418	62.16 151	93.71 311	68.18 293	63.60 395	86.61 355

0.3-1-1-0.015		81.31 194	79.49 217	86.77 75	85.74 319	68.70 97	95.01 46	94.42 60	74.29 212	77.09 205	85.61 319	63.31 129	95.69 206	76.63 209	63.30 396	95.91 54

0.4-1-1-0.2		81.28 196	79.42 219	86.84 67	85.80 317	68.82 88	95.10 39	94.43 59	74.45 207	77.18 202	85.54 320	62.27 146	95.70 204	76.72 208	63.30 396	96.01 48

0.4-1-1-0.1		80.99 205	79.16 227	86.51 98	85.55 324	68.21 110	94.77 54	94.42 60	73.75 225	76.57 210	85.41 322	62.35 145	95.62 210	76.30 214	63.28 398	95.71 63

h-mvs33		83.01 159	82.56 159	84.35 203	89.34 182	62.02 317	92.72 156	93.76 84	81.45 55	82.73 110	92.25 165	60.11 178	97.13 106	87.69 75	62.96 399	93.91 188

c3_l		76.83 295	75.47 291	80.93 324	85.02 337	64.18 249	90.39 294	88.11 381	71.66 282	66.65 357	81.64 370	63.58 124	92.56 355	69.31 282	62.86 400	86.04 372

test_vis1_rt		59.09 445	57.31 442	64.43 464	68.44 482	46.02 477	83.05 415	48.63 509	51.96 460	49.57 464	63.86 482	16.30 489	80.20 482	71.21 265	62.79 401	67.07 491

mvsany_test1		68.77 390	68.56 378	69.39 450	73.57 464	45.88 478	80.93 434	60.88 500	59.65 429	71.56 286	90.26 229	43.22 388	75.05 488	74.26 232	62.70 402	87.25 340

UniMVSNet_NR-MVSNet		78.15 267	77.55 254	79.98 346	84.46 349	60.26 366	92.25 186	93.20 113	77.50 156	68.88 320	86.61 303	66.10 82	92.13 371	66.38 320	62.55 403	87.54 330

DU-MVS		76.86 292	75.84 287	79.91 349	82.96 371	60.26 366	91.26 253	91.54 198	76.46 182	68.88 320	86.35 306	56.16 246	92.13 371	66.38 320	62.55 403	87.35 336

UniMVSNet (Re)		77.58 281	76.78 269	79.98 346	84.11 355	60.80 347	91.76 222	93.17 116	76.56 180	69.93 308	84.78 329	63.32 128	92.36 364	64.89 338	62.51 405	86.78 348

v8		75.35 321	73.26 330	81.61 299	80.67 396	66.82 163	89.54 320	89.27 325	71.65 283	63.30 385	80.30 394	54.99 262	94.06 294	67.33 309	62.33 406	83.94 403

cl____		76.07 306	74.67 299	80.28 336	85.15 332	61.76 326	90.12 303	88.73 359	71.16 298	65.43 363	81.57 372	61.15 162	92.95 335	66.54 317	62.17 407	86.13 370

v10		74.77 331	72.54 342	81.46 302	80.33 403	66.71 168	89.15 334	89.08 340	70.94 303	63.08 388	79.86 399	52.52 293	94.04 297	65.70 330	62.17 407	83.64 406

DIV-MVS_self_test		76.07 306	74.67 299	80.28 336	85.14 333	61.75 327	90.12 303	88.73 359	71.16 298	65.42 364	81.60 371	61.15 162	92.94 339	66.54 317	62.16 409	86.14 368

IterMVS-SCA-FT		71.55 369	69.97 364	76.32 399	81.48 387	60.67 356	87.64 364	85.99 415	66.17 367	59.50 416	78.88 407	45.53 375	83.65 462	62.58 359	61.93 410	84.63 400

IterMVS		72.65 358	70.83 356	78.09 378	82.17 379	62.96 294	87.64 364	86.28 408	71.56 290	60.44 409	78.85 408	45.42 377	86.66 442	63.30 353	61.83 411	84.65 398
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet5		68.04 398	65.66 397	75.18 408	84.43 350	57.89 397	83.54 403	86.26 409	61.83 414	53.64 446	73.30 448	37.15 424	85.08 452	48.99 420	61.77 412	82.56 427

v7n		71.31 370	68.65 377	79.28 364	76.40 446	60.77 349	86.71 376	89.45 318	64.17 387	58.77 423	78.24 411	44.59 383	93.54 316	57.76 383	61.75 413	83.52 409

v148		76.19 304	74.47 306	81.36 306	80.05 407	64.44 234	91.75 224	90.23 286	73.68 229	67.13 349	80.84 385	55.92 251	93.86 309	68.95 287	61.73 414	85.76 383

tfpnnormal		70.10 378	67.36 386	78.32 374	83.45 366	60.97 345	88.85 339	92.77 134	64.85 381	60.83 404	78.53 409	43.52 387	93.48 318	31.73 490	61.70 415	80.52 446

ACMH+	65.35 16	67.65 401	64.55 405	76.96 394	84.59 344	57.10 411	88.08 352	80.79 452	58.59 436	53.00 448	81.09 384	26.63 468	92.95 335	46.51 435	61.69 416	80.82 442

ITE_SJBPF				70.43 446	74.44 461	47.06 472		77.32 462	60.16 426	54.04 443	83.53 344	23.30 476	84.01 458	43.07 449	61.58 417	80.21 452

NR-MVSNet		76.05 309	74.59 302	80.44 332	82.96 371	62.18 315	90.83 273	91.73 188	77.12 163	60.96 403	86.35 306	59.28 195	91.80 379	60.74 369	61.34 418	87.35 336

test_0402		64.54 419	61.09 426	74.92 412	84.10 356	60.75 351	87.95 356	79.71 457	52.03 459	52.41 450	77.20 423	32.21 448	91.64 383	23.14 499	61.03 419	72.36 484

Baseline_NR-MVSNet		73.99 339	72.83 335	77.48 384	80.78 394	59.29 385	91.79 216	84.55 431	68.85 337	68.99 317	80.70 386	56.16 246	92.04 374	62.67 358	60.98 420	81.11 439

TranMVSNet+NR-MVSNet		75.86 314	74.52 305	79.89 350	82.44 377	60.64 357	91.37 245	91.37 206	76.63 178	67.65 340	86.21 309	52.37 295	91.55 387	61.84 363	60.81 421	87.48 332

testgi		64.48 420	62.87 418	69.31 451	71.24 470	40.62 491	85.49 385	79.92 456	65.36 378	54.18 442	83.49 346	23.74 474	84.55 454	41.60 457	60.79 422	82.77 420

eth_miper_zixun_eth		75.96 313	74.40 307	80.66 328	84.66 342	63.02 292	89.28 329	88.27 377	71.88 273	65.73 361	81.65 369	59.45 190	92.81 344	68.13 295	60.53 423	86.14 368

COLMAP_ROB	57.96 20	62.98 429	59.65 431	72.98 429	81.44 388	53.00 437	83.75 402	75.53 470	48.34 473	48.81 469	81.40 376	24.14 472	90.30 401	32.95 484	60.52 424	75.65 477
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AUN-MVS		78.37 263	77.43 256	81.17 312	86.60 292	57.45 406	89.46 325	91.16 219	74.11 215	74.40 239	90.49 222	55.52 255	94.57 265	74.73 229	60.43 425	91.48 269

hse-mvs2		81.12 202	81.11 183	81.16 313	86.52 296	57.48 405	89.40 326	91.16 219	81.45 55	82.73 110	90.49 222	60.11 178	94.58 263	87.69 75	60.41 426	91.41 271

RPSCF		64.24 421	61.98 424	71.01 444	76.10 448	45.00 480	75.83 463	75.94 466	46.94 476	58.96 421	84.59 331	31.40 451	82.00 477	47.76 431	60.33 427	86.04 372

miper_lstm_enhance		73.05 348	71.73 351	77.03 391	83.80 360	58.32 395	81.76 424	88.88 351	69.80 323	61.01 402	78.23 412	57.19 229	87.51 438	65.34 335	59.53 428	85.27 393

CP-MVSNet		70.50 375	69.91 366	72.26 435	80.71 395	51.00 449	87.23 369	90.30 281	67.84 350	59.64 415	82.69 354	50.23 320	82.30 475	51.28 408	59.28 429	83.46 411

PS-CasMVS		69.86 382	69.13 375	72.07 439	80.35 402	50.57 452	87.02 371	89.75 305	67.27 356	59.19 419	82.28 359	46.58 365	82.24 476	50.69 411	59.02 430	83.39 413

pm-mvs1		72.89 351	71.09 355	78.26 376	79.10 420	57.62 402	90.80 274	89.30 324	67.66 352	62.91 391	81.78 367	49.11 336	92.95 335	60.29 373	58.89 431	84.22 401

Anonymous20240521		62.09 430	59.08 434	71.10 443	67.19 484	48.72 463	83.91 399	85.23 424	50.38 466	47.84 471	71.22 463	20.74 482	85.51 450	46.47 436	58.75 432	79.06 458

WR-MVS_H		70.59 374	69.94 365	72.53 432	81.03 390	51.43 445	87.35 367	92.03 172	67.38 355	60.23 413	80.70 386	55.84 253	83.45 465	46.33 437	58.58 433	82.72 422

reproduce_monomvs		79.49 236	79.11 230	80.64 329	92.91 87	61.47 336	91.17 261	93.28 109	83.09 34	64.04 377	82.38 358	66.19 80	94.57 265	81.19 167	57.71 434	85.88 379

PEN-MVS		69.46 385	68.56 378	72.17 437	79.27 415	49.71 457	86.90 373	89.24 327	67.24 359	59.08 420	82.51 357	47.23 354	83.54 464	48.42 424	57.12 435	83.25 414

EU-MVSNet		64.01 422	63.01 416	67.02 461	74.40 462	38.86 497	83.27 409	86.19 411	45.11 482	54.27 441	81.15 383	36.91 427	80.01 483	48.79 423	57.02 436	82.19 431

AllTest		61.66 432	58.06 436	72.46 433	79.57 410	51.42 446	80.17 441	68.61 489	51.25 463	45.88 475	81.23 378	19.86 486	86.58 443	38.98 466	57.01 437	79.39 455

TestCases				72.46 433	79.57 410	51.42 446		68.61 489	51.25 463	45.88 475	81.23 378	19.86 486	86.58 443	38.98 466	57.01 437	79.39 455

Patchmtry		67.53 403	63.93 411	78.34 373	82.12 380	64.38 238	68.72 478	84.00 436	48.23 474	59.24 417	72.41 453	57.82 224	89.27 416	46.10 438	56.68 439	81.36 436

our_test_3		68.29 396	64.69 404	79.11 369	78.92 421	64.85 220	88.40 348	85.06 425	60.32 425	52.68 449	76.12 438	40.81 398	89.80 414	44.25 447	55.65 440	82.67 426

FPMVS		45.64 460	43.10 464	53.23 479	51.42 505	36.46 499	64.97 487	71.91 481	29.13 500	27.53 502	61.55 488	9.83 501	65.01 505	16.00 512	55.58 441	58.22 498

DTE-MVSNet		68.46 394	67.33 387	71.87 441	77.94 436	49.00 462	86.16 382	88.58 366	66.36 364	58.19 425	82.21 361	46.36 366	83.87 460	44.97 445	55.17 442	82.73 421

MIMVSNet1		60.16 442	57.33 441	68.67 453	69.71 478	44.13 482	78.92 448	84.21 432	55.05 453	44.63 482	71.85 458	23.91 473	81.54 479	32.63 488	55.03 443	80.35 448

pmmvs6		67.57 402	64.76 403	76.00 402	72.82 469	53.37 435	88.71 342	86.78 404	53.19 457	57.58 432	78.03 414	35.33 434	92.41 361	55.56 392	54.88 444	82.21 430

TinyColmap		60.32 440	56.42 447	72.00 440	78.78 424	53.18 436	78.36 452	75.64 468	52.30 458	41.59 490	75.82 441	14.76 494	88.35 425	35.84 472	54.71 445	74.46 478

test20.03		63.83 423	62.65 419	67.38 460	70.58 476	39.94 493	86.57 377	84.17 433	63.29 396	51.86 453	77.30 420	37.09 425	82.47 472	38.87 468	54.13 446	79.73 453

OurMVSNet-221017-0		64.68 418	62.17 422	72.21 436	76.08 449	47.35 468	80.67 435	81.02 451	56.19 449	51.60 454	79.66 403	27.05 467	88.56 421	53.60 402	53.63 447	80.71 444

FE-MVSNET2		66.80 407	64.06 410	75.03 409	69.84 477	57.11 410	86.57 377	88.57 367	67.94 349	50.97 459	72.16 457	33.79 441	87.55 437	53.94 399	52.74 448	80.45 447

test_fmvs3		56.82 447	54.86 450	62.69 469	53.59 502	35.47 500	75.87 462	65.64 494	43.91 486	55.10 438	71.43 462	6.91 506	74.40 491	68.64 291	52.63 449	78.20 468

Patchmatch-RL test		68.17 397	64.49 407	79.19 365	71.22 471	53.93 433	70.07 476	71.54 484	69.22 330	56.79 434	62.89 483	56.58 242	88.61 419	69.53 279	52.61 450	95.03 104

ppachtmachnet_test		67.72 400	63.70 412	79.77 354	78.92 421	66.04 186	88.68 343	82.90 447	60.11 427	55.45 437	75.96 439	39.19 403	90.55 398	39.53 464	52.55 451	82.71 423

LF4IMVS		54.01 452	52.12 453	59.69 470	62.41 493	39.91 495	68.59 479	68.28 491	42.96 490	44.55 483	75.18 442	14.09 496	68.39 498	41.36 459	51.68 452	70.78 485

PatchmatchNet1														31.49 494	51.52 453	77.88 470
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
N_pmnet		50.55 455	49.11 457	54.88 476	77.17 442	4.02 538	84.36 394	2.00 535	48.59 471	45.86 477	68.82 468	32.22 447	82.80 471	31.58 491	51.38 454	77.81 471

blended_shiyan8		72.26 362	69.25 374	81.29 308	75.23 458	64.03 253	91.36 248	91.04 239	66.11 369	60.42 410	76.73 432	46.79 360	93.45 322	64.58 343	51.00 455	86.37 361

wanda-best-256-512		72.42 360	69.43 370	81.37 304	75.39 453	64.24 246	91.58 233	91.09 229	66.36 364	60.64 405	76.86 428	47.20 355	93.47 319	64.80 339	50.98 456	86.40 358

FE-blended-shiyan7		72.42 360	69.43 370	81.37 304	75.39 453	64.24 246	91.58 233	91.09 229	66.36 364	60.64 405	76.86 428	47.20 355	93.47 319	64.80 339	50.98 456	86.40 358

blended_shiyan6		72.26 362	69.26 373	81.27 309	75.24 457	64.00 256	91.37 245	91.06 235	66.12 368	60.34 411	76.75 431	46.82 358	93.45 322	64.61 341	50.98 456	86.37 361

usedtu_blend_shiyan5		71.06 372	67.54 385	81.62 298	75.39 453	64.75 221	85.67 384	86.47 405	56.48 448	60.64 405	76.85 430	47.20 355	93.71 311	68.18 293	50.98 456	86.40 358

gbinet_0.2-2-1-0.02		71.92 365	68.92 376	80.91 325	75.87 451	63.30 283	91.95 207	91.40 205	65.62 375	61.57 399	77.27 422	44.71 382	92.88 342	61.00 368	50.87 460	86.54 356

pmmvs-eth3d		65.53 416	62.32 421	75.19 407	69.39 480	59.59 378	82.80 417	83.43 442	62.52 405	51.30 457	72.49 451	32.86 443	87.16 441	55.32 393	50.73 461	78.83 462

CL-MVSNet_self_test		69.92 380	68.09 383	75.41 404	73.25 465	55.90 423	90.05 306	89.90 300	69.96 320	61.96 398	76.54 433	51.05 312	87.64 433	49.51 418	50.59 462	82.70 424

PM-MVS		59.40 443	56.59 445	67.84 455	63.63 490	41.86 486	76.76 457	63.22 497	59.01 433	51.07 458	72.27 456	11.72 498	83.25 467	61.34 365	50.28 463	78.39 467

MDA-MVSNet_test_wron		63.78 425	60.16 429	74.64 414	78.15 434	60.41 362	83.49 405	84.03 434	56.17 451	39.17 492	71.59 460	37.22 422	83.24 468	42.87 452	48.73 464	80.26 450

YYNet1		63.76 426	60.14 430	74.62 415	78.06 435	60.19 369	83.46 407	83.99 438	56.18 450	39.25 491	71.56 461	37.18 423	83.34 466	42.90 451	48.70 465	80.32 449

KD-MVS_self_test		60.87 437	58.60 435	67.68 457	66.13 487	39.93 494	75.63 465	84.70 428	57.32 442	49.57 464	68.45 470	29.55 458	82.87 469	48.09 425	47.94 466	80.25 451

dtuonlycased		63.47 427	62.08 423	67.64 458	73.22 466	52.55 438	86.25 381	79.10 459	65.40 376	49.47 466	67.33 475	36.80 428	82.37 474	53.47 403	47.68 467	68.01 488

FE-MVSNET		60.52 439	57.18 443	70.53 445	67.53 483	50.68 451	82.62 419	76.28 464	59.33 432	46.71 473	71.10 464	30.54 456	83.61 463	33.15 483	47.37 468	77.29 473

SixPastTwentyTwo		64.92 417	61.78 425	74.34 419	78.74 425	49.76 456	83.42 408	79.51 458	62.86 401	50.27 461	77.35 419	30.92 455	90.49 400	45.89 439	47.06 469	82.78 419

sc_t1		63.81 424	59.39 433	77.10 390	77.62 438	56.03 421	84.32 396	73.56 476	46.66 478	58.22 424	73.06 449	23.28 477	90.62 397	50.93 410	46.84 470	84.64 399

tt0320		61.85 431	57.45 440	75.03 409	77.49 439	57.60 403	82.74 418	73.65 475	43.65 488	53.65 445	68.18 471	25.47 470	88.66 418	45.56 441	46.68 471	78.81 463

new_pmnet		49.31 456	46.44 459	57.93 471	62.84 492	40.74 490	68.47 480	62.96 498	36.48 494	35.09 495	57.81 493	14.97 493	72.18 493	32.86 486	46.44 472	60.88 496

usedtu_dtu_shiyan2		57.76 446	53.69 452	69.95 448	57.60 500	41.80 487	83.50 404	83.67 440	45.26 481	43.79 485	62.82 484	17.63 488	85.93 446	42.56 455	46.40 473	82.12 432

EGC-MVSNET		42.35 462	38.09 465	55.11 475	74.57 460	46.62 474	71.63 473	55.77 501	0.04 556	0.24 558	62.70 485	14.24 495	74.91 490	17.59 507	46.06 474	43.80 502

TransMVSNet (Re)		70.07 379	67.66 384	77.31 388	80.62 398	59.13 387	91.78 219	84.94 427	65.97 370	60.08 414	80.44 391	50.78 313	91.87 377	48.84 421	45.46 475	80.94 441

ambc				69.61 449	61.38 496	41.35 489	49.07 505	85.86 418		50.18 463	66.40 476	10.16 500	88.14 427	45.73 440	44.20 476	79.32 457

TDRefinement		55.28 450	51.58 454	66.39 462	59.53 498	46.15 476	76.23 460	72.80 477	44.60 483	42.49 488	76.28 437	15.29 492	82.39 473	33.20 482	43.75 477	70.62 486

Gipuma		34.91 469	31.44 472	45.30 486	70.99 473	39.64 496	19.85 518	72.56 479	20.10 507	16.16 514	21.47 527	5.08 509	71.16 494	13.07 514	43.70 478	25.08 519
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		46.58 458	43.45 462	55.96 473	45.18 509	32.05 504	61.18 491	49.49 508	33.39 496	42.05 489	62.48 486	7.00 505	65.56 503	47.08 434	43.21 479	70.27 487

tt0320-xc		61.51 435	56.89 444	75.37 405	78.50 429	58.61 392	82.61 420	71.27 485	44.31 485	53.17 447	68.03 473	23.38 475	88.46 423	47.77 430	43.00 480	79.03 460

MDA-MVSNet-bldmvs		61.54 434	57.70 438	73.05 428	79.53 412	57.00 415	83.08 413	81.23 449	57.57 438	34.91 496	72.45 452	32.79 444	86.26 445	35.81 473	41.95 481	75.89 476

new-patchmatchnet		59.30 444	56.48 446	67.79 456	65.86 488	44.19 481	82.47 421	81.77 448	59.94 428	43.65 486	66.20 477	27.67 465	81.68 478	39.34 465	41.40 482	77.50 472

UnsupCasMVSNet_eth		65.79 413	63.10 415	73.88 422	70.71 474	50.29 455	81.09 432	89.88 301	72.58 251	49.25 467	74.77 446	32.57 446	87.43 439	55.96 391	41.04 483	83.90 404

test_vis3_rt		40.46 465	37.79 466	48.47 484	44.49 510	33.35 503	66.56 486	32.84 517	32.39 497	29.65 498	39.13 514	3.91 514	68.65 497	50.17 413	40.99 484	43.40 503

pmmvs3		55.51 449	51.50 455	67.53 459	57.90 499	50.93 450	80.37 437	73.66 474	40.63 493	44.15 484	64.75 480	16.30 489	78.97 485	44.77 446	40.98 485	72.69 482

APD_test1		40.50 464	37.31 467	50.09 482	51.88 503	35.27 501	59.45 495	52.59 505	21.64 505	26.12 503	57.80 494	4.56 510	66.56 501	22.64 500	39.09 486	48.43 501

mvs5depth		61.03 436	57.65 439	71.18 442	67.16 485	47.04 473	72.74 469	77.49 461	57.47 441	60.52 408	72.53 450	22.84 478	88.38 424	49.15 419	38.94 487	78.11 469

UnsupCasMVSNet_bld		61.60 433	57.71 437	73.29 427	68.73 481	51.64 443	78.61 449	89.05 343	57.20 443	46.11 474	61.96 487	28.70 462	88.60 420	50.08 415	38.90 488	79.63 454

PMVS	26.43 22	31.84 474	28.16 477	42.89 489	25.87 522	27.58 510	50.92 504	49.78 507	21.37 506	14.17 517	40.81 511	2.01 518	66.62 500	9.61 521	38.88 489	34.49 511
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
K. test v3		63.09 428	59.61 432	73.53 425	76.26 447	49.38 461	83.27 409	77.15 463	64.35 384	47.77 472	72.32 455	28.73 461	87.79 431	49.93 416	36.69 490	83.41 412

mmtdpeth		68.33 395	66.37 391	74.21 421	82.81 374	51.73 442	84.34 395	80.42 454	67.01 360	71.56 286	68.58 469	30.52 457	92.35 365	75.89 216	36.21 491	78.56 466

kuosan		60.86 438	60.24 428	62.71 468	81.57 386	46.43 475	75.70 464	85.88 416	57.98 437	48.95 468	69.53 467	58.42 212	76.53 486	28.25 495	35.87 492	65.15 493

KD-MVS_2432*1600		69.03 388	66.37 391	77.01 392	85.56 322	61.06 343	81.44 429	90.25 284	67.27 356	58.00 428	76.53 434	54.49 268	87.63 434	48.04 426	35.77 493	82.34 428

miper_refine_blended		69.03 388	66.37 391	77.01 392	85.56 322	61.06 343	81.44 429	90.25 284	67.27 356	58.00 428	76.53 434	54.49 268	87.63 434	48.04 426	35.77 493	82.34 428

mvsany_test3		48.86 457	46.35 460	56.41 472	46.00 508	31.67 505	62.26 490	47.25 510	43.71 487	45.54 479	68.15 472	10.84 499	64.44 507	57.95 382	35.44 495	73.13 481

LCM-MVSNet		40.54 463	35.79 468	54.76 477	36.92 516	30.81 506	51.41 502	69.02 488	22.07 504	24.63 504	45.37 501	4.56 510	65.81 502	33.67 480	34.50 496	67.67 489

test_method		38.59 467	35.16 470	48.89 483	54.33 501	21.35 517	45.32 507	53.71 504	7.41 519	28.74 500	51.62 496	8.70 503	52.87 510	33.73 479	32.89 497	72.47 483

lessismore_v0				73.72 424	72.93 468	47.83 466		61.72 499		45.86 477	73.76 447	28.63 463	89.81 412	47.75 432	31.37 498	83.53 408

testf1		32.77 472	29.47 474	42.67 490	41.89 512	30.81 506	52.07 500	43.45 511	15.45 508	18.52 509	44.82 502	2.12 516	58.38 508	16.05 510	30.87 499	38.83 506

APD_test2		32.77 472	29.47 474	42.67 490	41.89 512	30.81 506	52.07 500	43.45 511	15.45 508	18.52 509	44.82 502	2.12 516	58.38 508	16.05 510	30.87 499	38.83 506

ttmdpeth		53.34 453	49.96 456	63.45 466	62.07 495	40.04 492	72.06 470	65.64 494	42.54 491	51.88 452	77.79 416	13.94 497	76.48 487	32.93 485	30.82 501	73.84 479

PVSNet_0	68.08 15	71.81 366	68.32 382	82.27 278	84.68 340	62.31 312	88.68 343	90.31 280	75.84 186	57.93 430	80.65 389	37.85 417	94.19 286	69.94 275	29.05 502	90.31 292

dongtai		55.18 451	55.46 449	54.34 478	76.03 450	36.88 498	76.07 461	84.61 430	51.28 462	43.41 487	64.61 481	56.56 243	67.81 499	18.09 506	28.50 503	58.32 497

MVStest1		51.35 454	46.89 458	64.74 463	65.06 489	51.10 448	67.33 484	72.58 478	30.20 499	35.30 494	74.82 444	27.70 464	69.89 496	24.44 498	24.57 504	73.22 480

VLMVS_CLIP		19.60 481	19.74 483	19.17 502	13.13 529	5.80 532	23.18 514	23.62 520	3.86 522	24.51 505	44.74 504	2.91 515	29.01 518	19.90 503	21.84 505	22.70 521

WB-MVS		46.23 459	44.94 461	50.11 481	62.13 494	21.23 518	76.48 459	55.49 502	45.89 479	35.78 493	61.44 489	35.54 432	72.83 492	9.96 520	21.75 506	56.27 499

SSC-MVS		44.51 461	43.35 463	47.99 485	61.01 497	18.90 520	74.12 467	54.36 503	43.42 489	34.10 497	60.02 492	34.42 437	70.39 495	9.14 522	19.57 507	54.68 500

DeepMVS_CX				34.71 493	51.45 504	24.73 513		28.48 519	31.46 498	17.49 512	52.75 495	5.80 508	42.60 516	18.18 505	19.42 508	36.81 509

PMMVS2		37.93 468	33.61 471	50.92 480	46.31 507	24.76 512	60.55 494	50.05 506	28.94 501	20.93 506	47.59 497	4.41 512	65.13 504	25.14 497	18.55 509	62.87 494

MVE	24.84 23	24.35 476	19.77 482	38.09 492	34.56 519	26.92 511	26.57 510	38.87 515	11.73 515	11.37 521	27.44 521	1.37 522	50.42 511	11.41 519	14.60 510	36.93 508
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ArgMatch-SfM		33.21 470	29.25 476	45.06 487	35.86 517	22.89 515	48.07 506	16.80 521	23.93 503	27.57 501	61.10 491	1.59 521	47.14 512	34.29 477	14.08 511	65.16 492

ArgMatch-Sym		33.10 471	29.80 473	43.01 488	37.34 515	24.00 514	51.27 503	13.51 522	26.37 502	28.91 499	61.40 490	1.65 520	43.37 515	34.16 478	13.61 512	61.66 495

LoFTR		18.06 483	15.31 487	26.33 496	21.95 523	10.94 526	21.35 516	12.80 523	6.90 520	12.24 519	41.28 509	0.46 527	27.67 520	7.81 524	12.96 513	40.38 505

VLMVS		13.23 488	13.55 489	12.28 509	12.68 531	2.77 542	12.60 521	3.80 529	0.44 538	17.98 511	44.70 505	4.14 513	6.39 531	12.99 515	12.66 514	27.68 515

MVS_clip		10.33 491	11.48 493	6.89 513	13.99 528	4.67 535	11.14 522	0.96 547	1.27 530	14.61 516	35.92 516	1.90 519	2.27 538	11.90 518	11.60 515	13.74 525

MatchFormer		14.02 486	12.22 490	19.42 501	17.64 526	8.79 529	19.96 517	10.04 524	4.23 521	10.54 524	32.75 519	0.31 534	22.88 523	4.03 531	10.48 516	26.57 516

E-PMN		24.61 475	24.00 479	26.45 495	43.74 511	18.44 521	60.86 492	39.66 513	15.11 511	9.53 525	22.10 526	6.52 507	46.94 513	8.31 523	10.14 517	13.98 524

EMVS		23.76 477	23.20 481	25.46 498	41.52 514	16.90 522	60.56 493	38.79 516	14.62 512	8.99 527	20.24 529	7.35 504	45.82 514	7.25 526	9.46 518	13.64 526

tmp_tt		22.26 478	23.75 480	17.80 503	5.23 543	12.06 525	35.26 508	39.48 514	2.82 526	18.94 507	44.20 507	22.23 480	24.64 521	36.30 470	9.31 519	16.69 523

ANet_high		40.27 466	35.20 469	55.47 474	34.74 518	34.47 502	63.84 489	71.56 483	48.42 472	18.80 508	41.08 510	9.52 502	64.45 506	20.18 502	8.66 520	67.49 490

wuyk23d		11.30 490	10.95 494	12.33 508	48.05 506	19.89 519	25.89 512	1.92 538	3.58 523	3.12 533	1.37 556	0.64 524	15.77 527	6.23 528	7.77 521	1.35 540

DenseAffine		21.45 479	18.65 484	29.86 494	28.31 520	16.04 523	32.25 509	6.12 525	15.38 510	16.38 513	44.57 506	0.55 525	32.44 517	16.82 508	7.46 522	41.09 504

RoMa-SfM		18.71 482	16.37 485	25.74 497	19.88 524	12.86 524	26.27 511	3.78 530	13.07 513	15.56 515	45.71 500	0.48 526	28.39 519	16.22 509	6.37 523	35.97 510

MASt3R-SfM		8.20 495	8.57 498	7.11 512	5.75 540	3.12 541	9.54 524	3.21 531	2.39 529	9.18 526	34.80 518	0.37 529	5.21 533	6.46 527	5.41 524	12.99 528

DKM		16.33 485	14.55 488	21.65 500	19.49 525	10.79 527	24.23 513	2.86 532	10.86 516	13.52 518	40.31 512	0.32 532	21.73 524	14.27 513	5.12 525	32.43 512

MVS_baseline		3.15 504	3.66 507	1.62 524	2.62 559	0.05 565	0.90 552	0.14 564	0.02 558	4.44 532	18.48 530	0.16 544	0.00 561	1.30 533	4.85 526	4.80 529

ALIKED-LG		4.67 500	4.76 504	4.39 514	11.74 532	4.58 536	8.52 525	2.37 533	1.12 531	3.02 534	10.43 531	0.40 528	4.25 534	0.52 541	4.70 527	4.35 530

PDCNetPlus		17.19 484	15.58 486	22.00 499	25.94 521	10.36 528	23.05 515	5.04 527	12.02 514	10.87 523	39.50 513	0.88 523	23.24 522	18.38 504	4.57 528	32.39 513

ALIKED-NN		4.04 503	4.13 506	3.78 516	10.26 534	4.26 537	7.33 528	1.98 537	0.76 533	2.52 536	9.08 534	0.32 532	3.67 536	0.44 543	4.45 529	3.40 537

ALIKED-MNN		4.24 502	4.26 505	4.20 515	10.96 533	4.68 534	7.92 526	2.00 535	0.81 532	2.44 539	9.09 533	0.30 535	4.03 535	0.46 542	4.36 530	3.88 533

RoMa-HiRes		13.29 487	12.09 491	16.86 504	12.76 530	7.74 530	17.91 520	2.10 534	8.64 517	11.87 520	39.11 515	0.36 530	17.55 525	12.17 516	3.91 531	25.30 518

DKM-HiRes		12.72 489	11.70 492	15.79 506	14.70 527	7.68 531	18.04 519	1.85 539	8.12 518	11.31 522	35.19 517	0.24 540	14.23 529	12.15 517	3.71 532	25.48 517

XFeat-MNN		2.31 505	2.37 508	2.13 517	1.47 561	0.97 556	3.08 536	1.31 540	0.53 535	2.60 535	7.72 535	0.22 542	2.31 537	1.02 535	3.40 533	3.10 538

XFeat-NN		1.98 511	2.09 514	1.67 523	1.35 562	0.77 561	2.62 537	0.97 546	0.41 540	2.46 538	6.79 537	0.19 543	1.75 539	0.84 536	3.18 534	2.48 539

ELoFTR		8.49 493	6.65 500	14.00 507	5.91 537	3.43 540	7.42 527	4.01 528	2.94 525	6.41 530	25.06 522	0.11 545	15.41 528	5.10 530	2.92 535	23.17 520

SP-DiffGlue		2.24 506	2.34 509	1.94 521	1.88 560	1.08 550	3.10 535	1.13 542	0.55 534	2.52 536	7.60 536	0.33 531	0.99 544	1.25 534	2.70 536	3.76 535

SP-LightGlue		2.23 507	2.31 510	1.99 518	5.90 538	1.01 552	4.31 531	1.04 544	0.50 536	1.20 541	4.36 538	0.28 536	1.06 541	0.64 537	2.57 537	3.91 531

SP-SuperGlue		2.21 508	2.29 511	1.97 519	5.76 539	1.01 552	4.31 531	1.06 543	0.50 536	1.22 540	4.35 539	0.28 536	1.04 543	0.64 537	2.52 538	3.86 534

SP-MNN		2.16 509	2.22 512	1.97 519	5.52 541	0.92 557	4.28 533	1.01 545	0.41 540	1.13 542	4.35 539	0.23 541	1.09 540	0.61 539	2.45 539	3.91 531

SP-NN		2.08 510	2.16 513	1.87 522	5.30 542	0.91 558	4.18 534	0.96 547	0.43 539	1.09 543	4.20 541	0.25 538	1.06 541	0.60 540	2.38 540	3.63 536

PMatch-SfM		8.29 494	7.44 499	10.83 510	6.92 536	3.67 539	9.75 523	1.15 541	3.49 524	6.97 528	28.70 520	0.04 557	8.89 530	7.67 525	2.24 541	19.92 522

GLUNet-SfM		8.91 492	6.39 501	16.47 505	9.50 535	4.77 533	5.87 530	5.53 526	2.45 527	6.66 529	22.23 525	0.25 538	15.78 526	2.84 532	2.14 542	28.86 514

SIFT-NN		1.43 512	1.51 515	1.19 525	4.60 545	1.57 544	2.30 538	0.51 550	0.34 542	0.74 544	2.84 542	0.08 546	0.84 545	0.13 545	2.07 543	1.15 541

SIFT-NN-NCMNet		1.29 514	1.36 517	1.08 527	3.95 548	1.39 546	2.05 540	0.49 552	0.33 544	0.63 547	2.62 546	0.07 547	0.81 547	0.12 547	2.02 544	1.05 545

SIFT-MNN		1.35 513	1.42 516	1.14 526	4.26 546	1.44 545	2.10 539	0.51 550	0.34 542	0.64 545	2.76 543	0.07 547	0.83 546	0.13 545	1.98 545	1.15 541

SIFT-NCM-Cal		1.23 515	1.30 518	1.04 528	4.06 547	1.29 547	1.92 542	0.42 553	0.33 544	0.45 552	2.46 549	0.06 552	0.81 547	0.10 554	1.89 546	1.02 547

SIFT-NN-UMatch		1.16 517	1.23 520	0.96 530	3.23 554	1.06 551	1.93 541	0.42 553	0.33 544	0.53 549	2.63 544	0.07 547	0.77 549	0.11 550	1.79 547	1.05 545

SIFT-NN-CMatch		1.18 516	1.24 519	1.01 529	3.44 552	1.19 549	1.78 543	0.42 553	0.33 544	0.64 545	2.63 544	0.07 547	0.77 549	0.12 547	1.73 548	1.08 543

SIFT-NN-PointCN		1.06 520	1.12 523	0.88 532	2.98 555	0.84 560	1.67 545	0.37 557	0.30 552	0.54 548	2.38 550	0.07 547	0.72 553	0.11 550	1.64 549	1.07 544

SIFT-ConvMatch		1.15 518	1.22 521	0.96 530	3.82 549	1.20 548	1.64 546	0.38 556	0.33 544	0.52 550	2.53 547	0.06 552	0.76 551	0.11 550	1.59 550	0.91 548

SIFT-UMatch		1.11 519	1.18 522	0.87 533	3.66 550	1.00 555	1.70 544	0.35 558	0.32 549	0.46 551	2.50 548	0.06 552	0.75 552	0.11 550	1.51 551	0.87 550

PMatch-Up-SfM		6.11 499	5.72 503	7.28 511	5.02 544	2.48 543	7.03 529	0.71 549	2.41 528	5.37 531	23.67 523	0.03 561	5.84 532	5.77 529	1.48 552	13.50 527

SIFT-UM-Cal		1.01 522	1.09 525	0.77 535	3.43 553	0.85 559	1.49 547	0.29 561	0.31 551	0.42 554	2.34 551	0.06 552	0.69 555	0.10 554	1.37 553	0.77 553

SIFT-CM-Cal		1.03 521	1.10 524	0.85 534	3.54 551	1.01 552	1.42 548	0.32 559	0.32 549	0.44 553	2.30 552	0.06 552	0.71 554	0.09 556	1.37 553	0.82 551

SIFT-PointCN		0.88 523	0.94 526	0.69 537	2.88 557	0.61 562	1.32 549	0.30 560	0.28 553	0.36 555	1.93 554	0.04 557	0.62 556	0.09 556	1.26 555	0.82 551

SIFT-PCN-Cal		0.88 523	0.93 527	0.70 536	2.93 556	0.60 563	1.22 550	0.27 562	0.28 553	0.36 555	2.00 553	0.04 557	0.61 557	0.09 556	1.23 556	0.89 549

SIFT-NCMNet		0.73 525	0.80 528	0.54 538	2.66 558	0.54 564	1.00 551	0.16 563	0.28 553	0.32 557	1.65 555	0.04 557	0.51 558	0.07 559	0.98 557	0.58 554

testmvs		7.23 497	9.62 496	0.06 540	0.04 563	0.02 567	84.98 391	0.02 565	0.03 557	0.18 559	1.21 557	0.01 563	0.02 559	0.14 544	0.01 558	0.13 556

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	0.00 559	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	0.00 559	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	0.00 559	0.00 557

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

cdsmvs_eth3d_5k		19.86 480	26.47 478	0.00 541	0.00 565	0.00 568	0.00 553	93.45 102	0.00 560	0.00 561	95.27 78	49.56 328	0.00 561	0.00 560	0.00 559	0.00 557

pcd_1.5k_mvsjas		4.46 501	5.95 502	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	53.55 282	0.00 561	0.00 560	0.00 559	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	0.00 559	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	0.00 559	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	0.00 559	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	0.00 559	0.00 557

test123		6.92 498	9.21 497	0.08 539	0.03 564	0.05 565	81.65 427	0.01 566	0.02 558	0.14 560	0.85 558	0.03 561	0.02 559	0.12 547	0.00 559	0.16 555

ab-mvs-re		7.91 496	10.55 495	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	94.95 89	0.00 564	0.00 561	0.00 560	0.00 559	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	0.00 559	0.00 557

PatchmatchNet2					0.00 565	56.61 417	85.20 387	78.52 460	49.54 469
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													82.83 470
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						49.45 459								31.56 492

FOURS1					93.95 52	61.77 325	93.96 91	91.92 176	62.14 409	86.57 65

test_one_0601					96.32 20	69.74 55		94.18 71	71.42 294	90.67 29	96.85 28	74.45 22

eth-test2					0.00 565

eth-test					0.00 565

test_241102_ONE					96.45 13	69.38 65		94.44 57	71.65 283	92.11 10	97.05 13	76.79 10	99.11 7

save fliter					93.84 55	67.89 119	95.05 41	92.66 141	78.19 137

test0726					96.40 16	69.99 43	96.76 8	94.33 68	71.92 269	91.89 15	97.11 12	73.77 25

GSMVS																94.68 129

test_part2					96.29 21	68.16 112				90.78 27

sam_mvs1												57.85 223				94.68 129

sam_mvs												54.91 263

MTGPA								92.23 157

test_post1							78.95 447				20.70 528	53.05 287	91.50 392	60.43 371

test_post											23.01 524	56.49 244	92.67 351

patchmatchnet-post											67.62 474	57.62 226	90.25 402

MTMP							93.77 106	32.52 518

gm-plane-assit					88.42 224	67.04 151			78.62 130		91.83 186		97.37 85	76.57 210

TEST9					94.18 47	67.28 139	94.16 78	93.51 98	71.75 280	85.52 78	95.33 72	68.01 63	97.27 95

test_8					94.19 46	67.19 144	94.15 80	93.42 105	71.87 274	85.38 81	95.35 71	68.19 61	96.95 122

agg_prior					94.16 49	66.97 160		93.31 108		84.49 89			96.75 134

test_prior4						67.18 146	93.92 95

test_prior				86.42 103	94.71 41	67.35 138		93.10 120					96.84 131			95.05 102

旧先验2							92.00 204		59.37 431	87.54 57			93.47 319	75.39 220

新几何2							91.41 238

无先验							92.71 157	92.61 146	62.03 410				97.01 112	66.63 315		93.97 182

原ACMM2							92.01 201

testdata2													96.09 168	61.26 366

segment_acmp												65.94 84

testdata1							89.21 331		77.55 155

plane_prior7					86.94 281	61.51 333

plane_prior6					87.23 264	62.32 311						50.66 314

plane_prior4											89.14 259

plane_prior3						61.95 320			79.09 119	72.53 268

plane_prior2							93.13 135		78.81 126

plane_prior1					87.15 269

n2								0.00 567

nn								0.00 567

door-mid								66.01 493

test11								93.01 123

door								66.57 492

HQP5-MVS						63.66 273

HQP-NCC					87.54 256		94.06 83		79.80 93	74.18 240

ACMP_Plane					87.54 256		94.06 83		79.80 93	74.18 240

BP-MVS														77.63 203

HQP4-MVS										74.18 240			95.61 212			88.63 314

HQP2-MVS												51.63 302

NP-MVS					87.41 259	63.04 291					90.30 227

MDTV_nov1_ep13_2view						59.90 374	80.13 442		67.65 353	72.79 262		54.33 273		59.83 375		92.58 236

Test By Simon												54.21 276

High-resolution multi-view benchmark