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	85.88 118	92.83 87	64.03 250	93.06 136	94.33 67	82.19 45	93.65 4	96.15 51	85.89 1	97.19 100	91.02 53	97.75 1	96.43 32
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	89.68 173	76.68 2	97.29 1	95.35 18	82.87 37	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 16	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 45	93.96 91	94.37 65	72.48 251	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 66	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 36	95.10 33	68.23 106	95.24 34	94.49 54	82.43 42	88.90 46	96.35 42	71.89 43	98.63 32	88.76 67	96.40 6	96.06 43

SMA-MVS		88.14 21	88.29 30	87.67 35	93.21 75	68.72 90	93.85 99	94.03 76	74.18 212	91.74 16	96.67 34	65.61 87	98.42 39	89.24 63	96.08 7	95.88 54
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 63	88.32 3	85.71 74	94.91 92	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 73	96.26 47	72.84 32	99.38 2	92.64 33	95.93 9	97.08 12

BridgeMVS		89.08 15	88.84 22	89.81 7	93.66 60	75.15 5	90.61 286	93.43 102	84.06 24	86.20 68	90.17 234	72.42 37	96.98 117	93.09 29	95.92 10	97.29 8

CNVR-MVS		90.32 6	90.89 8	88.61 23	96.76 9	70.65 32	96.47 14	94.83 36	84.83 17	89.07 44	96.80 31	70.86 46	99.06 16	92.64 33	95.71 11	96.12 42

PHI-MVS		86.83 50	86.85 54	86.78 70	93.47 69	65.55 198	95.39 31	95.10 26	71.77 277	85.69 75	96.52 36	62.07 150	98.77 28	86.06 97	95.60 12	96.03 45

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 180	93.00 83	58.16 393	96.72 9	94.41 61	86.50 9	90.25 34	97.83 2	75.46 16	98.67 31	92.78 32	95.49 13	97.32 7

SED-MVS		89.94 9	90.36 10	88.70 19	96.45 13	69.38 62	96.89 6	94.44 56	71.65 281	92.11 10	97.21 10	76.79 10	99.11 7	92.34 36	95.36 14	97.62 3

IU-MVS					96.46 12	69.91 45		95.18 24	80.75 68	95.28 2				92.34 36	95.36 14	96.47 29

test_241102_TWO								94.41 61	71.65 281	92.07 12	97.21 10	74.58 20	99.11 7	92.34 36	95.36 14	96.59 20

MM		90.87 2	91.52 2	88.92 16	92.12 108	71.10 29	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 16

test_0728_THIRD									72.48 251	90.55 30	96.93 20	76.24 13	99.08 12	91.53 49	94.99 18	96.43 32

test9_res														89.41 59	94.96 19	95.29 84

ACMMP_NAP		86.05 69	85.80 75	86.80 69	91.58 130	67.53 129	91.79 214	93.49 99	74.93 200	84.61 86	95.30 74	59.42 188	97.92 50	86.13 95	94.92 20	94.94 106

DPE-MVS		88.77 18	89.21 19	87.45 45	96.26 22	67.56 127	94.17 77	94.15 72	68.77 337	90.74 28	97.27 7	76.09 14	98.49 35	90.58 57	94.91 21	96.30 36
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 26	96.40 16	69.99 41	96.64 10	94.52 52	71.92 267	90.55 30	96.93 20	73.77 25	99.08 12	91.91 42	94.90 22	96.29 37
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 36	96.64 10	94.37 65					99.15 3	91.91 42	94.90 22	96.51 25

train_agg		87.21 42	87.42 43	86.60 82	94.18 47	67.28 136	94.16 78	93.51 96	71.87 272	85.52 77	95.33 72	68.19 61	97.27 95	89.09 64	94.90 22	95.25 91

DeepC-MVS_fast	79.48 2	87.95 28	88.00 34	87.79 33	95.86 29	68.32 100	95.74 21	94.11 73	83.82 26	83.49 99	96.19 49	64.53 103	98.44 37	83.42 135	94.88 25	96.61 19
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	67.84 117		94.64 46		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 47	94.76 36	67.28 136	94.47 64	94.87 33	70.68 308	91.27 24	96.93 20	76.77 12	98.98 17	91.55 45	94.82 26	95.88 54

MSC_two_6792asdad				89.60 10	97.31 4	73.22 14		95.05 30					99.07 14	92.01 39	94.77 28	96.51 25

No_MVS				89.60 10	97.31 4	73.22 14		95.05 30					99.07 14	92.01 39	94.77 28	96.51 25

TSAR-MVS + MP.		88.11 24	88.64 25	86.54 94	91.73 126	68.04 111	90.36 294	93.55 94	82.89 35	91.29 23	92.89 147	72.27 39	96.03 173	87.99 72	94.77 28	95.54 68
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		75.40 192	85.25 83	95.61 63	67.94 64		87.47 79	94.77 28

agg_prior2														86.41 93	94.75 32	95.33 79

MVSMamba_PlusPlus		84.97 94	83.65 114	88.93 15	90.17 164	74.04 8	87.84 357	92.69 136	62.18 405	81.47 120	87.64 286	71.47 45	96.28 156	84.69 112	94.74 33	96.47 29

MVS		84.66 103	82.86 146	90.06 3	90.93 148	74.56 7	87.91 355	95.54 15	68.55 339	72.35 273	94.71 97	59.78 180	98.90 24	81.29 166	94.69 34	96.74 17

MGCNet		90.32 6	90.90 7	88.55 24	94.05 51	70.23 39	97.00 5	93.73 87	87.30 4	92.15 9	96.15 51	66.38 77	98.94 21	96.71 3	94.67 35	96.47 29

SF-MVS		87.03 44	87.09 46	86.84 65	92.70 93	67.45 133	93.64 112	93.76 83	70.78 306	86.25 66	96.44 39	66.98 71	97.79 57	88.68 68	94.56 36	95.28 86

NCCC		89.07 16	89.46 16	87.91 30	96.60 11	69.05 78	96.38 15	94.64 46	84.42 21	86.74 63	96.20 48	66.56 76	98.76 29	89.03 66	94.56 36	95.92 51

3Dnovator	73.91 6	82.69 165	80.82 185	88.31 28	89.57 175	71.26 24	92.60 168	94.39 64	78.84 124	67.89 334	92.48 157	48.42 337	98.52 34	68.80 287	94.40 38	95.15 94

aaatest				87.42 46	94.76 36	67.28 136	94.47 64	94.87 33	73.09 239	91.27 24	96.95 18		98.98 17	91.55 45	94.28 39	95.99 48

aaEdge-Enhanced		88.25 19	88.55 26	87.33 51	96.33 19	67.28 136	93.93 93	94.81 37	70.09 316	88.91 45	96.95 18	70.12 50	98.73 30	91.55 45	94.28 39	95.99 48

CDPH-MVS		85.71 77	85.46 81	86.46 98	94.75 40	67.19 141	93.89 97	92.83 129	70.90 302	83.09 104	95.28 76	63.62 118	97.36 86	80.63 172	94.18 41	94.84 112

MG-MVS		87.11 43	86.27 62	89.62 9	97.79 1	76.27 4	94.96 48	94.49 54	78.74 127	83.87 95	92.94 145	64.34 104	96.94 123	75.19 219	94.09 42	95.66 63

9.14			87.63 38		93.86 54		94.41 69	94.18 70	72.76 246	86.21 67	96.51 37	66.64 74	97.88 54	90.08 58	94.04 43

原ACMM1				84.42 197	93.21 75	64.27 241		93.40 105	65.39 375	79.51 161	92.50 154	58.11 215	96.69 136	65.27 334	93.96 44	92.32 244

MSLP-MVS++		86.27 65	85.91 73	87.35 49	92.01 115	68.97 81	95.04 43	92.70 133	79.04 122	81.50 118	96.50 38	58.98 199	96.78 133	83.49 134	93.93 45	96.29 37

CANet		89.61 12	89.99 12	88.46 25	94.39 45	69.71 54	96.53 13	93.78 80	86.89 7	89.68 40	95.78 58	65.94 82	99.10 10	92.99 30	93.91 46	96.58 22

MP-MVS-pluss		85.24 86	85.13 87	85.56 134	91.42 135	65.59 196	91.54 234	92.51 146	74.56 203	80.62 136	95.64 62	59.15 195	97.00 113	86.94 90	93.80 47	94.07 176
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MVP-Stereo		77.12 286	76.23 279	79.79 350	81.72 383	66.34 174	89.29 326	90.88 245	70.56 311	62.01 395	82.88 350	49.34 328	94.13 288	65.55 331	93.80 47	78.88 459
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
GG-mvs-BLEND				86.53 95	91.91 121	69.67 56	75.02 464	94.75 40		78.67 181	90.85 214	77.91 8	94.56 267	72.25 250	93.74 49	95.36 77

ZNCC-MVS		85.33 85	85.08 88	86.06 113	93.09 80	65.65 194	93.89 97	93.41 104	73.75 223	79.94 150	94.68 98	60.61 169	98.03 47	82.63 145	93.72 50	94.52 141

CSCG		86.87 47	86.26 63	88.72 18	95.05 34	70.79 31	93.83 104	95.33 19	68.48 341	77.63 191	94.35 110	73.04 30	98.45 36	84.92 110	93.71 51	96.92 15

test12				87.09 58	94.60 42	68.86 82		92.91 126		82.67 111		65.44 88	97.55 74		93.69 52	94.84 112

PAPM		85.89 74	85.46 81	87.18 55	88.20 233	72.42 17	92.41 180	92.77 131	82.11 46	80.34 145	93.07 142	68.27 59	95.02 238	78.39 197	93.59 53	94.09 174

SteuartSystems-ACMMP		86.82 52	86.90 51	86.58 85	90.42 158	66.38 172	96.09 17	93.87 78	77.73 147	84.01 94	95.66 61	63.39 123	97.94 49	87.40 80	93.55 54	95.42 71
Skip Steuart: Steuart Systems R&D Blog.
APDe-MVS		87.54 34	87.84 36	86.65 79	96.07 25	66.30 175	94.84 53	93.78 80	69.35 326	88.39 49	96.34 43	67.74 66	97.66 66	90.62 56	93.44 55	96.01 46
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SPE-MVS-test		86.14 68	87.01 47	83.52 234	92.63 95	59.36 381	95.49 28	91.92 173	80.09 85	85.46 79	95.53 67	61.82 155	95.77 194	86.77 92	93.37 56	95.41 72

PS-MVSNAJ		88.14 21	87.61 40	89.71 8	92.06 111	76.72 1	95.75 20	93.26 108	83.86 25	89.55 41	96.06 53	53.55 280	97.89 53	91.10 51	93.31 57	94.54 139

TestfortrainingZip				90.29 2	97.24 8	73.67 10	94.47 64	95.75 10	69.78 322	95.97 1	98.23 1	80.55 5	99.42 1		93.26 58	97.76 2

MAR-MVS		84.18 119	83.43 122	86.44 100	96.25 23	65.93 189	94.28 75	94.27 69	74.41 206	79.16 170	95.61 63	53.99 275	98.88 26	69.62 276	93.26 58	94.50 147
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		77.18 284	74.31 306	85.80 123	91.42 135	68.36 99	71.78 469	94.72 41	49.61 466	77.12 201	45.92 497	77.41 9	93.98 300	67.62 302	93.16 60	95.05 100

ZD-MVS					96.63 10	65.50 200		93.50 98	70.74 307	85.26 82	95.19 84	64.92 96	97.29 91	87.51 77	93.01 61

APD-MVS		85.93 72	85.99 71	85.76 125	95.98 28	65.21 207	93.59 115	92.58 144	66.54 360	86.17 69	95.88 57	63.83 112	97.00 113	86.39 94	92.94 62	95.06 99
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
新几何1				84.73 179	92.32 100	64.28 240		91.46 200	59.56 428	79.77 156	92.90 146	56.95 234	96.57 140	63.40 348	92.91 63	93.34 206

DeepC-MVS	77.85 3	85.52 83	85.24 85	86.37 103	88.80 201	66.64 166	92.15 190	93.68 89	81.07 64	76.91 205	93.64 132	62.59 139	98.44 37	85.50 100	92.84 64	94.03 179
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 25	89.25 18	84.23 207	89.07 192	61.60 328	94.87 51	89.06 340	85.65 11	91.09 26	97.41 5	68.26 60	97.43 82	95.07 13	92.74 65	93.66 196

xiu_mvs_v2_base		87.92 30	87.38 44	89.55 13	91.41 138	76.43 3	95.74 21	93.12 116	83.53 29	89.55 41	95.95 56	53.45 284	97.68 61	91.07 52	92.62 66	94.54 139

MP-MVS		85.02 91	84.97 90	85.17 154	92.60 96	64.27 241	93.24 130	92.27 153	73.13 235	79.63 160	94.43 104	61.90 151	97.17 101	85.00 108	92.56 67	94.06 177
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTAPA		83.91 128	83.38 126	85.50 135	91.89 122	65.16 209	81.75 423	92.23 154	75.32 194	80.53 141	95.21 83	56.06 247	97.16 104	84.86 111	92.55 68	94.18 165

GST-MVS		84.63 105	84.29 101	85.66 130	92.82 89	65.27 205	93.04 138	93.13 115	73.20 233	78.89 172	94.18 118	59.41 189	97.85 55	81.45 162	92.48 69	93.86 190

PRO-TEST		81.59 186	82.22 162	79.70 353	91.09 145	48.99 460	81.78 421	90.76 255	81.94 48	63.52 380	87.90 281	58.82 203	95.28 232	91.87 44	92.28 70	94.83 116

HFP-MVS		84.73 102	84.40 99	85.72 127	93.75 58	65.01 213	93.50 120	93.19 112	72.19 261	79.22 168	94.93 90	59.04 198	97.67 63	81.55 160	92.21 71	94.49 148

ACMMPR		84.37 111	84.06 104	85.28 149	93.56 64	64.37 236	93.50 120	93.15 114	72.19 261	78.85 177	94.86 93	56.69 238	97.45 79	81.55 160	92.20 72	94.02 180

MS-PatchMatch		77.90 273	76.50 271	82.12 283	85.99 308	69.95 44	91.75 222	92.70 133	73.97 217	62.58 392	84.44 332	41.11 395	95.78 192	63.76 347	92.17 73	80.62 443

region2R		84.36 112	84.03 105	85.36 144	93.54 66	64.31 239	93.43 125	92.95 125	72.16 264	78.86 176	94.84 94	56.97 233	97.53 75	81.38 164	92.11 74	94.24 162

CS-MVS		85.80 75	86.65 59	83.27 246	92.00 116	58.92 385	95.31 32	91.86 178	79.97 86	84.82 85	95.40 70	62.26 145	95.51 219	86.11 96	92.08 75	95.37 75

fmvsm_l_conf0.5_n_9		88.24 20	89.36 17	84.85 168	88.15 234	61.94 318	95.65 25	89.70 310	85.54 12	92.07 12	97.33 6	67.51 68	97.27 95	96.23 5	92.07 76	95.35 78

patch_mono-2		89.71 11	90.99 6	85.85 121	96.04 26	63.70 267	95.04 43	95.19 23	86.74 8	91.53 21	95.15 85	73.86 24	97.58 71	93.38 27	92.00 77	96.28 39

dcpmvs_2		87.37 40	87.55 41	86.85 64	95.04 35	68.20 108	90.36 294	90.66 260	79.37 111	81.20 123	93.67 131	74.73 18	96.55 142	90.88 54	92.00 77	95.82 57

fmvsm_s_conf0.5_n_6		87.50 36	88.72 23	83.84 219	86.89 285	60.04 369	95.05 41	92.17 163	84.80 18	92.27 7	96.37 40	64.62 100	96.54 143	94.43 19	91.86 79	94.94 106

旧先验1					91.94 117	60.74 349		91.50 198			94.36 106	65.23 91			91.84 80	94.55 137

MVSFormer		83.75 134	82.88 145	86.37 103	89.24 189	71.18 26	89.07 333	90.69 257	65.80 370	87.13 58	94.34 111	64.99 93	92.67 350	72.83 240	91.80 81	95.27 87

lupinMVS		87.74 32	87.77 37	87.63 40	89.24 189	71.18 26	96.57 12	92.90 127	82.70 39	87.13 58	95.27 78	64.99 93	95.80 189	89.34 61	91.80 81	95.93 50

EPNet		87.84 31	88.38 28	86.23 108	93.30 72	66.05 181	95.26 33	94.84 35	87.09 5	88.06 50	94.53 101	66.79 73	97.34 88	83.89 126	91.68 83	95.29 84
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
3Dnovator+	73.60 7	82.10 178	80.60 193	86.60 82	90.89 150	66.80 162	95.20 35	93.44 101	74.05 214	67.42 342	92.49 156	49.46 327	97.65 67	70.80 266	91.68 83	95.33 79

XVS		83.87 129	83.47 120	85.05 158	93.22 73	63.78 259	92.92 146	92.66 138	73.99 215	78.18 185	94.31 113	55.25 254	97.41 83	79.16 187	91.58 85	93.95 182

X-MVStestdata		76.86 290	74.13 312	85.05 158	93.22 73	63.78 259	92.92 146	92.66 138	73.99 215	78.18 185	10.19 527	55.25 254	97.41 83	79.16 187	91.58 85	93.95 182

SD-MVS		87.49 37	87.49 42	87.50 44	93.60 62	68.82 85	93.90 96	92.63 142	76.86 166	87.90 52	95.76 59	66.17 79	97.63 68	89.06 65	91.48 87	96.05 44
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		84.53 107	85.04 89	83.01 252	89.34 180	61.37 336	94.42 68	91.09 226	77.91 142	83.24 100	94.20 117	58.37 211	95.40 221	85.35 101	91.41 88	92.27 249

fmvsm_s_conf0.5_n_10		87.93 29	88.67 24	85.71 128	88.69 203	63.71 265	94.56 62	90.22 286	85.04 15	92.27 7	97.05 13	63.67 116	98.15 44	95.09 12	91.39 89	95.27 87

PGM-MVS		83.25 150	82.70 149	84.92 163	92.81 91	64.07 249	90.44 289	92.20 158	71.28 294	77.23 199	94.43 104	55.17 258	97.31 90	79.33 186	91.38 90	93.37 205

PVSNet_Blended		86.73 54	86.86 53	86.31 107	93.76 56	67.53 129	96.33 16	93.61 91	82.34 44	81.00 130	93.08 141	63.19 128	97.29 91	87.08 88	91.38 90	94.13 170

HPM-MVS		83.25 150	82.95 143	84.17 208	92.25 102	62.88 296	90.91 266	91.86 178	70.30 313	77.12 201	93.96 126	56.75 236	96.28 156	82.04 152	91.34 92	93.34 206
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EIA-MVS		84.84 98	84.88 91	84.69 184	91.30 140	62.36 306	93.85 99	92.04 166	79.45 107	79.33 165	94.28 115	62.42 141	96.35 153	80.05 177	91.25 93	95.38 74

NormalMVS		86.39 59	86.66 58	85.60 133	92.12 108	65.95 187	94.88 49	90.83 247	84.69 19	83.67 97	94.10 120	63.16 130	96.91 129	85.31 102	91.15 94	93.93 184

lecture		84.77 99	84.81 94	84.65 187	92.12 108	62.27 310	94.74 56	92.64 141	68.35 342	85.53 76	95.30 74	59.77 181	97.91 51	83.73 130	91.15 94	93.77 193

MVS_111021_HR		86.19 67	85.80 75	87.37 48	93.17 77	69.79 50	93.99 90	93.76 83	79.08 119	78.88 175	93.99 125	62.25 146	98.15 44	85.93 98	91.15 94	94.15 168

test222					89.77 171	61.60 328	89.55 317	89.42 318	56.83 444	77.28 198	92.43 158	52.76 288			91.14 97	93.09 216

jason		86.40 58	86.17 66	87.11 57	86.16 304	70.54 34	95.71 24	92.19 160	82.00 47	84.58 87	94.34 111	61.86 153	95.53 218	87.76 74	90.89 98	95.27 87
jason: jason.
mPP-MVS		82.96 159	82.44 159	84.52 194	92.83 87	62.92 294	92.76 153	91.85 180	71.52 289	75.61 218	94.24 116	53.48 283	96.99 116	78.97 190	90.73 99	93.64 198

CP-MVS		83.71 135	83.40 125	84.65 187	93.14 78	63.84 257	94.59 61	92.28 152	71.03 300	77.41 195	94.92 91	55.21 257	96.19 161	81.32 165	90.70 100	93.91 187

OpenMVS	70.45 11	78.54 259	75.92 284	86.41 102	85.93 312	71.68 20	92.74 154	92.51 146	66.49 361	64.56 368	91.96 179	43.88 383	98.10 46	54.61 393	90.65 101	89.44 305

PAPM_NR		82.97 158	81.84 169	86.37 103	94.10 50	66.76 163	87.66 361	92.84 128	69.96 318	74.07 245	93.57 134	63.10 133	97.50 77	70.66 269	90.58 102	94.85 109

testdata				81.34 304	89.02 195	57.72 397		89.84 300	58.65 433	85.32 81	94.09 122	57.03 229	93.28 324	69.34 279	90.56 103	93.03 219

mvsmamba		81.55 187	80.72 188	84.03 214	91.42 135	66.93 158	83.08 410	89.13 334	78.55 131	67.50 340	87.02 298	51.79 297	90.07 408	87.48 78	90.49 104	95.10 97

fmvsm_s_conf0.5_n_3		86.88 46	87.99 35	83.58 233	87.26 261	60.74 349	93.21 133	87.94 385	84.22 22	91.70 17	97.27 7	65.91 84	95.02 238	93.95 24	90.42 105	94.99 103

fmvsm_s_conf0.5_n_7		85.24 86	86.69 56	80.91 322	84.52 344	60.10 367	93.35 128	90.35 274	83.41 31	86.54 65	96.27 46	60.50 170	90.02 409	94.84 16	90.38 106	92.61 232

Vis-MVSNet		80.92 205	79.98 204	83.74 223	88.48 218	61.80 320	93.44 124	88.26 377	73.96 218	77.73 189	91.76 186	49.94 321	94.76 250	65.84 324	90.37 107	94.65 132
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
balanced_ft_v1		84.95 95	83.81 109	88.38 27	93.31 71	73.59 11	85.95 381	92.51 146	77.25 160	73.97 247	89.14 257	59.30 191	95.25 233	92.50 35	90.34 108	96.31 35

CHOSEN 1792x2688		84.98 93	83.45 121	89.57 12	89.94 168	75.14 6	92.07 196	92.32 151	81.87 49	75.68 215	88.27 271	60.18 174	98.60 33	80.46 174	90.27 109	94.96 104

fmvsm_s_conf0.5_n_8		87.96 26	88.93 21	85.07 157	88.43 221	61.78 321	94.73 59	91.74 184	85.87 10	91.66 18	97.50 3	64.03 108	98.33 40	96.28 4	90.08 110	95.10 97

fmvsm_l_conf0.5_n_3		87.54 34	88.29 30	85.30 147	86.92 283	62.63 301	95.02 45	90.28 281	84.95 16	90.27 33	96.86 26	65.36 89	97.52 76	94.93 15	90.03 111	95.76 59

test_fmvsm_n_1920		87.69 33	88.50 27	85.27 150	87.05 272	63.55 274	93.69 109	91.08 230	84.18 23	90.17 36	97.04 15	67.58 67	97.99 48	95.72 8	90.03 111	94.26 160

fmvsm_s_conf0.5_n_5		86.38 61	86.94 49	84.71 182	84.67 339	63.29 281	94.04 87	89.99 296	82.88 36	87.85 53	96.03 54	62.89 137	96.36 152	94.15 21	89.95 113	94.48 149

fmvsm_s_conf0.5_n_9		88.14 21	89.21 19	84.92 163	89.29 184	61.41 335	92.97 141	88.36 369	86.96 6	91.49 22	97.49 4	69.48 55	97.46 78	97.00 1	89.88 114	95.89 53

ETV-MVS		86.01 70	86.11 68	85.70 129	90.21 163	67.02 150	93.43 125	91.92 173	81.21 62	84.13 93	94.07 124	60.93 164	95.63 206	89.28 62	89.81 115	94.46 150

QAPM		79.95 227	77.39 258	87.64 36	89.63 174	71.41 22	93.30 129	93.70 88	65.34 377	67.39 344	91.75 188	47.83 346	98.96 19	57.71 382	89.81 115	92.54 236

CANet_DTU		84.09 121	83.52 115	85.81 122	90.30 161	66.82 160	91.87 210	89.01 343	85.27 13	86.09 70	93.74 129	47.71 348	96.98 117	77.90 200	89.78 117	93.65 197

API-MVS		82.28 171	80.53 195	87.54 43	96.13 24	70.59 33	93.63 113	91.04 236	65.72 372	75.45 221	92.83 150	56.11 246	98.89 25	64.10 344	89.75 118	93.15 213

test2506		83.29 149	82.92 144	84.37 200	88.39 224	63.18 287	92.01 199	91.35 205	77.66 149	78.49 184	91.42 198	64.58 102	95.09 237	73.19 236	89.23 119	94.85 109

ECVR-MVS		81.29 193	80.38 198	84.01 215	88.39 224	61.96 316	92.56 173	86.79 401	77.66 149	76.63 206	91.42 198	46.34 366	95.24 234	74.36 228	89.23 119	94.85 109

MVS_Test		84.16 120	83.20 133	87.05 60	91.56 131	69.82 48	89.99 308	92.05 165	77.77 146	82.84 106	86.57 303	63.93 111	96.09 167	74.91 224	89.18 121	95.25 91

reproduce-ours		83.51 145	83.33 128	84.06 210	92.18 106	60.49 357	90.74 276	92.04 166	64.35 382	83.24 100	95.59 65	59.05 196	97.27 95	83.61 131	89.17 122	94.41 156

our_new_method		83.51 145	83.33 128	84.06 210	92.18 106	60.49 357	90.74 276	92.04 166	64.35 382	83.24 100	95.59 65	59.05 196	97.27 95	83.61 131	89.17 122	94.41 156

PAPR		85.15 89	84.47 97	87.18 55	96.02 27	68.29 101	91.85 212	93.00 122	76.59 177	79.03 171	95.00 87	61.59 156	97.61 70	78.16 198	89.00 124	95.63 64

BP-MVS1		86.54 57	86.68 57	86.13 111	87.80 249	67.18 143	92.97 141	95.62 11	79.92 89	82.84 106	94.14 119	74.95 17	96.46 148	82.91 141	88.96 125	94.74 122

TestfortrainingZip a		86.96 45	86.88 52	87.23 52	94.76 36	67.02 150	94.47 64	94.08 75	70.68 308	88.57 48	96.93 20	69.03 56	98.78 27	84.41 119	88.95 126	95.88 54

TSAR-MVS + GP.		87.96 26	88.37 29	86.70 76	93.51 68	65.32 204	95.15 37	93.84 79	78.17 137	85.93 72	94.80 95	75.80 15	98.21 42	89.38 60	88.78 127	96.59 20

SR-MVS		82.81 161	82.58 155	83.50 237	93.35 70	61.16 339	92.23 187	91.28 212	64.48 381	81.27 122	95.28 76	53.71 279	95.86 181	82.87 142	88.77 128	93.49 203

test1111		80.84 206	80.02 201	83.33 241	87.87 245	60.76 347	92.62 165	86.86 400	77.86 143	75.73 214	91.39 200	46.35 365	94.70 259	72.79 242	88.68 129	94.52 141

fmvsm_l_conf0.5_n_a		87.44 39	88.15 33	85.30 147	87.10 270	64.19 245	94.41 69	88.14 378	80.24 84	92.54 6	96.97 17	69.52 54	97.17 101	95.89 6	88.51 130	94.56 136

reproduce_model		83.15 153	82.96 141	83.73 225	92.02 112	59.74 373	90.37 293	92.08 164	63.70 389	82.86 105	95.48 68	58.62 206	97.17 101	83.06 138	88.42 131	94.26 160

HPM-MVS_fast		80.25 220	79.55 214	82.33 273	91.55 132	59.95 370	91.32 249	89.16 330	65.23 378	74.71 235	93.07 142	47.81 347	95.74 195	74.87 226	88.23 132	91.31 274

PVSNet_Blended_VisFu		83.97 126	83.50 117	85.39 139	90.02 166	66.59 169	93.77 106	91.73 185	77.43 156	77.08 204	89.81 245	63.77 114	96.97 120	79.67 180	88.21 133	92.60 233

Vis-MVSNet (Re-imp)		79.24 241	79.57 211	78.24 375	88.46 219	52.29 437	90.41 291	89.12 335	74.24 211	69.13 309	91.91 183	65.77 85	90.09 407	59.00 378	88.09 134	92.33 243

fmvsm_l_conf0.5_n		87.49 37	88.19 32	85.39 139	86.95 278	64.37 236	94.30 74	88.45 367	80.51 72	92.70 5	96.86 26	69.98 52	97.15 105	95.83 7	88.08 135	94.65 132

APD-MVS_3200maxsize		81.64 185	81.32 175	82.59 265	92.36 99	58.74 387	91.39 240	91.01 238	63.35 393	79.72 158	94.62 100	51.82 295	96.14 164	79.71 179	87.93 136	92.89 225

RRT-MVS		82.61 166	81.16 176	86.96 63	91.10 144	68.75 88	87.70 360	92.20 158	76.97 164	72.68 260	87.10 297	51.30 306	96.41 150	83.56 133	87.84 137	95.74 60

Effi-MVS+		83.82 130	82.76 147	86.99 62	89.56 176	69.40 60	91.35 247	86.12 412	72.59 248	83.22 103	92.81 151	59.60 184	96.01 175	81.76 159	87.80 138	95.56 67

casdiffmvs_mvg		85.66 79	85.18 86	87.09 58	88.22 232	69.35 65	93.74 108	91.89 176	81.47 54	80.10 148	91.45 197	64.80 98	96.35 153	87.23 83	87.69 139	95.58 66
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		80.70 209	78.95 229	85.94 117	87.77 251	67.56 127	87.91 355	92.55 145	72.17 263	67.44 341	93.09 140	50.27 317	97.04 111	71.68 258	87.64 140	93.23 210

test_fmvsmconf_n		86.58 56	87.17 45	84.82 170	85.28 327	62.55 302	94.26 76	89.78 301	83.81 27	87.78 54	96.33 44	65.33 90	96.98 117	94.40 20	87.55 141	94.95 105

PMMVS		81.98 180	82.04 164	81.78 290	89.76 172	56.17 416	91.13 260	90.69 257	77.96 140	80.09 149	93.57 134	46.33 367	94.99 241	81.41 163	87.46 142	94.17 166

casdiffmvs		85.37 84	84.87 92	86.84 65	88.25 230	69.07 75	93.04 138	91.76 183	81.27 61	80.84 133	92.07 172	64.23 106	96.06 171	84.98 109	87.43 143	95.39 73
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
hybridcas		84.65 104	83.95 106	86.74 74	87.18 266	68.78 87	92.94 144	91.36 204	80.47 73	79.32 166	91.67 193	62.13 149	96.19 161	83.15 136	87.36 144	95.25 91

test_fmvsmconf0.1_n		85.71 77	86.08 70	84.62 191	80.83 390	62.33 307	93.84 102	88.81 353	83.50 30	87.00 61	96.01 55	63.36 124	96.93 125	94.04 23	87.29 145	94.61 134

UGNet		79.87 228	78.68 231	83.45 239	89.96 167	61.51 330	92.13 191	90.79 254	76.83 168	78.85 177	86.33 307	38.16 410	96.17 163	67.93 299	87.17 146	92.67 230
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		82.02 179	81.52 172	83.51 236	88.42 222	62.88 296	89.77 311	88.93 348	76.78 169	75.55 219	93.10 139	50.31 316	95.38 223	83.82 127	87.02 147	92.26 250

fmvsm_s_conf0.5_n_4		86.79 53	87.63 38	84.27 205	86.15 305	61.48 332	94.69 60	91.16 216	83.79 28	90.51 32	96.28 45	64.24 105	98.22 41	95.00 14	86.88 148	93.11 215

test_fmvsmvis_n_1920		83.80 131	83.48 119	84.77 175	82.51 374	63.72 264	91.37 243	83.99 436	81.42 58	77.68 190	95.74 60	58.37 211	97.58 71	93.38 27	86.87 149	93.00 221

xiu_mvs_v1_base_debu		82.16 175	81.12 178	85.26 151	86.42 295	68.72 90	92.59 170	90.44 270	73.12 236	84.20 90	94.36 106	38.04 412	95.73 196	84.12 123	86.81 150	91.33 270

xiu_mvs_v1_base		82.16 175	81.12 178	85.26 151	86.42 295	68.72 90	92.59 170	90.44 270	73.12 236	84.20 90	94.36 106	38.04 412	95.73 196	84.12 123	86.81 150	91.33 270

xiu_mvs_v1_base_debi		82.16 175	81.12 178	85.26 151	86.42 295	68.72 90	92.59 170	90.44 270	73.12 236	84.20 90	94.36 106	38.04 412	95.73 196	84.12 123	86.81 150	91.33 270

SR-MVS-dyc-post		81.06 201	80.70 189	82.15 281	92.02 112	58.56 390	90.90 267	90.45 266	62.76 400	78.89 172	94.46 102	51.26 307	95.61 210	78.77 194	86.77 153	92.28 246

RE-MVS-def			80.48 196		92.02 112	58.56 390	90.90 267	90.45 266	62.76 400	78.89 172	94.46 102	49.30 329		78.77 194	86.77 153	92.28 246

baseline		85.01 92	84.44 98	86.71 75	88.33 227	68.73 89	90.24 299	91.82 182	81.05 65	81.18 124	92.50 154	63.69 115	96.08 170	84.45 118	86.71 155	95.32 81

TESTMET0.1,1		82.41 169	81.98 167	83.72 227	88.08 235	63.74 261	92.70 158	93.77 82	79.30 112	77.61 192	87.57 288	58.19 214	94.08 291	73.91 231	86.68 156	93.33 208

SymmetryMVS		86.32 62	86.39 61	86.12 112	90.52 156	65.95 187	94.88 49	94.58 51	84.69 19	83.67 97	94.10 120	63.16 130	96.91 129	85.31 102	86.59 157	95.51 69

viewmanbaseed2359cas		84.89 97	84.26 102	86.78 70	88.50 212	69.77 52	92.69 162	91.13 222	81.11 63	81.54 117	91.98 178	60.35 171	95.73 196	84.47 117	86.56 158	94.84 112

IS-MVSNet		80.14 222	79.41 218	82.33 273	87.91 241	60.08 368	91.97 203	88.27 375	72.90 244	71.44 286	91.73 189	61.44 157	93.66 314	62.47 358	86.53 159	93.24 209

CPTT-MVS		79.59 231	79.16 225	80.89 324	91.54 133	59.80 372	92.10 193	88.54 366	60.42 421	72.96 256	93.28 138	48.27 338	92.80 344	78.89 193	86.50 160	90.06 292

KinetiMVS		81.43 189	80.11 199	85.38 143	86.60 290	65.47 202	92.90 149	93.54 95	75.33 193	77.31 197	90.39 222	46.81 357	96.75 134	71.65 259	86.46 161	93.93 184

BH-w/o		80.49 214	79.30 222	84.05 213	90.83 152	64.36 238	93.60 114	89.42 318	74.35 208	69.09 310	90.15 236	55.23 256	95.61 210	64.61 339	86.43 162	92.17 252

PVSNet	73.49 8	80.05 224	78.63 232	84.31 202	90.92 149	64.97 214	92.47 177	91.05 235	79.18 115	72.43 271	90.51 219	37.05 424	94.06 293	68.06 296	86.00 163	93.90 189

GDP-MVS		85.54 82	85.32 83	86.18 109	87.64 252	67.95 115	92.91 148	92.36 150	77.81 144	83.69 96	94.31 113	72.84 32	96.41 150	80.39 175	85.95 164	94.19 164

Casviewmamba		84.58 106	83.95 106	86.47 97	87.22 263	67.76 121	92.71 156	90.96 240	80.81 67	79.29 167	91.85 184	62.20 147	96.33 155	84.60 114	85.91 165	95.32 81

test_fmvsmconf0.01_n		83.70 136	83.52 115	84.25 206	75.26 454	61.72 325	92.17 189	87.24 395	82.36 43	84.91 84	95.41 69	55.60 252	96.83 132	92.85 31	85.87 166	94.21 163

E3new		84.94 96	84.36 100	86.69 78	89.06 193	69.31 66	92.68 163	91.29 211	80.72 69	81.03 127	92.14 168	61.89 152	95.91 177	84.59 115	85.85 167	94.86 108

myMVS_eth3d28		86.31 64	86.15 67	86.78 70	93.56 64	70.49 35	92.94 144	95.28 20	82.47 41	78.70 179	92.07 172	72.45 36	95.41 220	82.11 150	85.78 168	94.44 151

mvs_anonymous		81.36 191	79.99 203	85.46 136	90.39 160	68.40 98	86.88 372	90.61 262	74.41 206	70.31 298	84.67 328	63.79 113	92.32 366	73.13 237	85.70 169	95.67 62

DP-MVS Recon		82.73 162	81.65 171	85.98 115	97.31 4	67.06 146	95.15 37	91.99 170	69.08 334	76.50 210	93.89 127	54.48 268	98.20 43	70.76 267	85.66 170	92.69 229

BH-RMVSNet		79.46 236	77.65 248	84.89 166	91.68 128	65.66 193	93.55 116	88.09 380	72.93 241	73.37 253	91.12 211	46.20 369	96.12 165	56.28 388	85.61 171	92.91 223

viewcassd2359sk11		84.74 101	84.11 103	86.64 80	88.57 206	69.20 73	92.61 166	91.23 213	80.58 70	80.85 132	91.96 179	61.39 158	95.89 179	84.28 121	85.49 172	94.82 117

viewmacassd2359aftdt		84.03 123	83.18 135	86.59 84	86.76 286	69.44 59	92.44 179	90.85 246	80.38 77	80.78 134	91.33 203	58.54 208	95.62 208	82.15 149	85.41 173	94.72 125

diffmvs_AUTHOR		83.97 126	83.49 118	85.39 139	86.09 306	67.83 118	90.76 274	89.05 341	79.94 87	81.43 121	92.23 165	59.53 185	94.42 275	87.18 84	85.22 174	93.92 186

UBG		86.83 50	86.70 55	87.20 54	93.07 81	69.81 49	93.43 125	95.56 14	81.52 53	81.50 118	92.12 169	73.58 28	96.28 156	84.37 120	85.20 175	95.51 69

diffmvs		84.28 114	83.83 108	85.61 132	87.40 258	68.02 112	90.88 269	89.24 325	80.54 71	81.64 116	92.52 153	59.83 179	94.52 271	87.32 81	85.11 176	94.29 158
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		84.45 108	83.74 110	86.56 87	87.90 242	69.06 76	92.53 174	91.13 222	80.35 78	80.58 139	91.69 191	60.70 165	95.84 182	83.80 128	84.99 177	94.79 120

E3		84.45 108	83.74 110	86.56 87	87.90 242	69.06 76	92.53 174	91.13 222	80.35 78	80.58 139	91.69 191	60.70 165	95.84 182	83.80 128	84.99 177	94.79 120

viewdifsd2359ckpt13		84.08 122	83.21 131	86.70 76	88.49 216	69.55 58	92.25 184	91.14 220	79.71 96	79.73 157	91.72 190	58.83 202	95.89 179	82.06 151	84.99 177	94.66 131

Fast-Effi-MVS+		81.14 198	80.01 202	84.51 195	90.24 162	65.86 190	94.12 82	89.15 331	73.81 222	75.37 223	88.26 272	57.26 226	94.53 270	66.97 312	84.92 180	93.15 213

LFMVS		84.34 113	82.73 148	89.18 14	94.76 36	73.25 13	94.99 47	91.89 176	71.90 269	82.16 113	93.49 136	47.98 342	97.05 108	82.55 146	84.82 181	97.25 9

BH-untuned		78.68 255	77.08 262	83.48 238	89.84 169	63.74 261	92.70 158	88.59 363	71.57 287	66.83 351	88.65 264	51.75 298	95.39 222	59.03 377	84.77 182	91.32 273

test-LLR		80.10 223	79.56 212	81.72 292	86.93 281	61.17 337	92.70 158	91.54 195	71.51 290	75.62 216	86.94 299	53.83 276	92.38 361	72.21 251	84.76 183	91.60 264

test-mter		79.96 226	79.38 221	81.72 292	86.93 281	61.17 337	92.70 158	91.54 195	73.85 220	75.62 216	86.94 299	49.84 323	92.38 361	72.21 251	84.76 183	91.60 264

fmvsm_s_conf0.5_n_2		85.06 90	85.60 79	83.44 240	86.92 283	60.53 356	94.41 69	87.31 393	83.30 32	88.72 47	96.72 33	54.28 272	97.75 59	94.07 22	84.68 185	92.04 255

sasdasda		86.85 48	86.25 64	88.66 21	91.80 124	71.92 18	93.54 117	91.71 187	80.26 81	87.55 55	95.25 80	63.59 120	96.93 125	88.18 70	84.34 186	97.11 10

canonicalmvs		86.85 48	86.25 64	88.66 21	91.80 124	71.92 18	93.54 117	91.71 187	80.26 81	87.55 55	95.25 80	63.59 120	96.93 125	88.18 70	84.34 186	97.11 10

alignmvs		87.28 41	86.97 48	88.24 29	91.30 140	71.14 28	95.61 26	93.56 93	79.30 112	87.07 60	95.25 80	68.43 58	96.93 125	87.87 73	84.33 188	96.65 18

VNet		86.20 66	85.65 78	87.84 32	93.92 53	69.99 41	95.73 23	95.94 7	78.43 133	86.00 71	93.07 142	58.22 213	97.00 113	85.22 104	84.33 188	96.52 24

UA-Net		80.02 225	79.65 210	81.11 313	89.33 182	57.72 397	86.33 378	89.00 347	77.44 155	81.01 128	89.15 256	59.33 190	95.90 178	61.01 365	84.28 190	89.73 299

LCM-MVSNet-Re		72.93 348	71.84 347	76.18 399	88.49 216	48.02 462	80.07 441	70.17 484	73.96 218	52.25 449	80.09 396	49.98 320	88.24 424	67.35 305	84.23 191	92.28 246

E4		84.00 125	83.19 134	86.46 98	86.99 273	68.85 83	92.39 181	90.99 239	79.94 87	80.17 147	91.36 202	59.73 182	95.79 191	82.87 142	84.22 192	94.74 122

ACMMP		81.49 188	80.67 190	83.93 216	91.71 127	62.90 295	92.13 191	92.22 157	71.79 276	71.68 282	93.49 136	50.32 315	96.96 121	78.47 196	84.22 192	91.93 260
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 81	85.73 77	85.17 154	91.41 138	62.44 303	92.87 150	91.31 206	79.65 98	86.99 62	95.14 86	62.90 136	96.12 165	87.13 85	84.13 194	96.96 14

fmvsm_s_conf0.1_n_2		84.40 110	84.78 95	83.27 246	85.25 328	60.41 359	94.13 81	85.69 418	83.05 34	87.99 51	96.37 40	52.75 289	97.68 61	93.75 26	84.05 195	91.71 263

Elysia		76.45 299	74.17 309	83.30 242	80.43 397	64.12 247	89.58 314	90.83 247	61.78 413	72.53 265	85.92 312	34.30 436	94.81 248	68.10 294	84.01 196	90.97 280

StellarMVS		76.45 299	74.17 309	83.30 242	80.43 397	64.12 247	89.58 314	90.83 247	61.78 413	72.53 265	85.92 312	34.30 436	94.81 248	68.10 294	84.01 196	90.97 280

onestephybrid01		83.68 137	83.31 130	84.81 173	86.53 292	65.38 203	90.54 287	89.14 333	79.52 106	81.01 128	92.02 174	58.91 200	94.91 247	88.26 69	83.86 198	94.14 169

hybridnocas07		83.76 133	83.21 131	85.39 139	86.64 287	67.40 134	91.08 261	88.77 356	79.78 95	80.35 144	92.15 167	59.24 194	94.67 260	87.11 87	83.79 199	94.11 172

hybrid		83.58 143	83.00 140	85.34 145	86.38 299	67.51 132	90.92 265	88.87 351	78.49 132	80.59 138	92.09 171	58.77 205	94.46 273	87.12 86	83.74 200	94.06 177

E6new		83.62 139	82.65 150	86.55 89	86.98 274	69.29 67	91.69 224	90.95 243	79.60 103	79.80 152	91.25 205	58.04 217	95.84 182	81.84 155	83.67 201	94.52 141

E6		83.62 139	82.65 150	86.55 89	86.98 274	69.29 67	91.69 224	90.95 243	79.60 103	79.80 152	91.25 205	58.04 217	95.84 182	81.84 155	83.67 201	94.52 141

E5new		83.62 139	82.65 150	86.55 89	86.98 274	69.28 69	91.69 224	90.96 240	79.61 100	79.80 152	91.25 205	58.04 217	95.84 182	81.83 157	83.66 203	94.52 141

E5		83.62 139	82.65 150	86.55 89	86.98 274	69.28 69	91.69 224	90.96 240	79.61 100	79.80 152	91.25 205	58.04 217	95.84 182	81.83 157	83.66 203	94.52 141

114514_t		79.17 242	77.67 247	83.68 229	95.32 32	65.53 199	92.85 151	91.60 194	63.49 391	67.92 331	90.63 217	46.65 362	95.72 201	67.01 311	83.54 205	89.79 297

testing11		86.71 55	86.44 60	87.55 42	93.54 66	71.35 23	93.65 111	95.58 12	81.36 60	80.69 135	92.21 166	72.30 38	96.46 148	85.18 106	83.43 206	94.82 117

test_vis1_n_1920		81.66 184	82.01 166	80.64 326	82.24 376	55.09 425	94.76 55	86.87 399	81.67 52	84.40 89	94.63 99	38.17 409	94.67 260	91.98 41	83.34 207	92.16 253

viewmamba		83.23 152	82.64 154	85.00 161	86.40 298	66.16 179	90.68 279	88.35 371	79.92 89	78.68 180	92.02 174	58.86 201	94.72 253	85.55 99	83.31 208	94.12 171

testing222		85.18 88	84.69 96	86.63 81	92.91 85	69.91 45	92.61 166	95.80 9	80.31 80	80.38 143	92.27 162	68.73 57	95.19 235	75.94 213	83.27 209	94.81 119

EPMVS		78.49 260	75.98 283	86.02 114	91.21 142	69.68 55	80.23 438	91.20 214	75.25 195	72.48 269	78.11 411	54.65 264	93.69 313	57.66 383	83.04 210	94.69 126

AdaColmap		78.94 248	77.00 265	84.76 177	96.34 18	65.86 190	92.66 164	87.97 384	62.18 405	70.56 292	92.37 160	43.53 384	97.35 87	64.50 342	82.86 211	91.05 279

CDS-MVSNet		81.43 189	80.74 187	83.52 234	86.26 301	64.45 230	92.09 194	90.65 261	75.83 185	73.95 248	89.81 245	63.97 110	92.91 339	71.27 260	82.82 212	93.20 212
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CHOSEN 280x420		77.35 282	76.95 266	78.55 370	87.07 271	62.68 300	69.71 475	82.95 444	68.80 336	71.48 285	87.27 294	66.03 81	84.00 457	76.47 209	82.81 213	88.95 307

UWE-MVS		80.81 207	81.01 183	80.20 336	89.33 182	57.05 409	91.91 208	94.71 42	75.67 186	75.01 227	89.37 251	63.13 132	91.44 391	67.19 309	82.80 214	92.12 254

ETVMVS		84.22 118	83.71 112	85.76 125	92.58 97	68.25 105	92.45 178	95.53 16	79.54 105	79.46 162	91.64 195	70.29 49	94.18 286	69.16 282	82.76 215	94.84 112

viewdifsd2359ckpt09		83.52 144	82.57 156	86.37 103	88.02 239	68.47 96	91.78 217	89.63 311	79.61 100	78.56 182	92.00 177	59.28 192	95.96 176	81.94 153	82.35 216	94.69 126

PCF-MVS	73.15 9	79.29 240	77.63 250	84.29 203	86.06 307	65.96 186	87.03 368	91.10 225	69.86 320	69.79 306	90.64 215	57.54 225	96.59 138	64.37 343	82.29 217	90.32 289
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffseed414692147		82.20 173	80.75 186	86.55 89	87.13 269	69.57 57	91.79 214	90.48 265	78.12 138	78.52 183	90.10 240	55.92 249	95.80 189	72.42 249	82.28 218	94.28 159

viewmambaseed2359dif		82.60 167	81.91 168	84.67 186	85.83 313	66.09 180	90.50 288	89.01 343	75.46 189	79.64 159	92.01 176	59.51 186	94.38 277	82.99 140	82.26 219	93.54 200

fmvsm_s_conf0.5_n		86.39 59	86.91 50	84.82 170	87.36 260	63.54 275	94.74 56	90.02 294	82.52 40	90.14 37	96.92 24	62.93 135	97.84 56	95.28 11	82.26 219	93.07 218

WTY-MVS		86.32 62	85.81 74	87.85 31	92.82 89	69.37 64	95.20 35	95.25 21	82.71 38	81.91 114	94.73 96	67.93 65	97.63 68	79.55 181	82.25 221	96.54 23

testing99		86.01 70	85.47 80	87.63 40	93.62 61	71.25 25	93.47 123	95.23 22	80.42 76	80.60 137	91.95 181	71.73 44	96.50 146	80.02 178	82.22 222	95.13 95

HY-MVS	76.49 5	84.28 114	83.36 127	87.02 61	92.22 103	67.74 122	84.65 390	94.50 53	79.15 116	82.23 112	87.93 280	66.88 72	96.94 123	80.53 173	82.20 223	96.39 34

dtuplus		82.25 172	81.42 174	84.71 182	85.38 323	66.05 181	90.62 285	89.27 323	75.16 197	79.22 168	91.76 186	58.05 216	94.56 267	81.18 168	82.19 224	93.52 201

testing91		85.93 72	85.31 84	87.78 34	93.59 63	71.47 21	93.50 120	95.08 29	80.26 81	80.53 141	91.93 182	70.43 48	96.51 145	80.32 176	82.13 225	95.37 75

VDD-MVS		83.06 156	81.81 170	86.81 68	90.86 151	67.70 123	95.40 30	91.50 198	75.46 189	81.78 115	92.34 161	40.09 399	97.13 106	86.85 91	82.04 226	95.60 65

viewdifsd2359ckpt07		82.95 160	82.04 164	85.66 130	87.19 265	66.73 164	91.56 233	90.39 273	77.58 152	77.58 194	91.19 209	58.57 207	95.65 205	82.32 147	82.01 227	94.60 135

fmvsm_s_conf0.1_n		85.61 80	85.93 72	84.68 185	82.95 371	63.48 277	94.03 89	89.46 315	81.69 51	89.86 38	96.74 32	61.85 154	97.75 59	94.74 17	82.01 227	92.81 228

TAMVS		80.37 217	79.45 216	83.13 251	85.14 331	63.37 278	91.23 254	90.76 255	74.81 202	72.65 262	88.49 265	60.63 168	92.95 334	69.41 278	81.95 229	93.08 217

SSM_0404		79.46 236	77.65 248	84.91 165	88.37 226	67.04 148	89.59 313	87.03 396	67.99 345	75.45 221	89.32 252	47.98 342	95.34 226	71.23 261	81.90 230	92.34 242

test_yl		84.28 114	83.16 136	87.64 36	94.52 43	69.24 71	95.78 18	95.09 27	69.19 329	81.09 125	92.88 148	57.00 231	97.44 80	81.11 169	81.76 231	96.23 40

DCV-MVSNet		84.28 114	83.16 136	87.64 36	94.52 43	69.24 71	95.78 18	95.09 27	69.19 329	81.09 125	92.88 148	57.00 231	97.44 80	81.11 169	81.76 231	96.23 40

FA-MVS(test-final)		79.12 243	77.23 260	84.81 173	90.54 155	63.98 254	81.35 429	91.71 187	71.09 299	74.85 232	82.94 349	52.85 287	97.05 108	67.97 297	81.73 233	93.41 204

thisisatest0515		83.41 147	82.49 158	86.16 110	89.46 179	68.26 103	93.54 117	94.70 43	74.31 209	75.75 213	90.92 212	72.62 34	96.52 144	69.64 274	81.50 234	93.71 194

baseline2		83.68 137	83.42 124	84.48 196	87.37 259	66.00 184	90.06 303	95.93 8	79.71 96	69.08 311	90.39 222	77.92 7	96.28 156	78.91 192	81.38 235	91.16 277

PatchmatchNet		77.46 280	74.63 299	85.96 116	89.55 177	70.35 37	79.97 443	89.55 313	72.23 260	70.94 288	76.91 425	57.03 229	92.79 345	54.27 395	81.17 236	94.74 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VDDNet		80.50 213	78.26 237	87.21 53	86.19 302	69.79 50	94.48 63	91.31 206	60.42 421	79.34 164	90.91 213	38.48 407	96.56 141	82.16 148	81.05 237	95.27 87

icg_test_0407_2		80.38 216	79.22 224	83.88 217	88.54 207	64.75 218	86.79 373	90.80 250	76.73 172	73.95 248	90.18 228	51.55 302	92.45 359	73.47 232	80.95 238	94.43 152

IMVS_0407		80.80 208	79.39 220	85.00 161	88.54 207	64.75 218	88.40 346	90.80 250	76.73 172	73.95 248	90.18 228	51.55 302	95.81 188	73.47 232	80.95 238	94.43 152

IMVS_0404		78.11 267	76.29 278	83.59 232	88.54 207	64.75 218	84.63 391	90.80 250	76.73 172	61.16 399	90.18 228	40.17 398	91.58 384	73.47 232	80.95 238	94.43 152

IMVS_0403		81.19 196	79.88 205	85.13 156	88.54 207	64.75 218	88.84 338	90.80 250	76.73 172	75.21 224	90.18 228	54.22 273	96.21 160	73.47 232	80.95 238	94.43 152

EPNet_dtu		78.80 252	79.26 223	77.43 383	88.06 236	49.71 454	91.96 204	91.95 172	77.67 148	76.56 209	91.28 204	58.51 209	90.20 405	56.37 387	80.95 238	92.39 240
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		82.71 164	82.38 160	83.73 225	89.25 186	59.58 376	92.24 186	94.89 32	77.96 140	79.86 151	92.38 159	56.70 237	97.05 108	77.26 203	80.86 243	94.55 137

FE-MVS		75.97 310	73.02 330	84.82 170	89.78 170	65.56 197	77.44 454	91.07 231	64.55 380	72.66 261	79.85 398	46.05 370	96.69 136	54.97 392	80.82 244	92.21 251

GeoE		78.90 249	77.43 254	83.29 244	88.95 197	62.02 314	92.31 182	86.23 408	70.24 314	71.34 287	89.27 254	54.43 269	94.04 296	63.31 350	80.81 245	93.81 192

UWE-MVS-28		76.83 293	77.60 251	74.51 414	84.58 343	50.34 450	88.22 349	94.60 50	74.46 204	66.66 353	88.98 262	62.53 140	85.50 449	57.55 384	80.80 246	87.69 327

LuminaMVS		78.14 266	76.66 269	82.60 264	80.82 391	64.64 224	89.33 325	90.45 266	68.25 343	74.73 234	85.51 319	41.15 394	94.14 287	78.96 191	80.69 247	89.04 306

fmvsm_s_conf0.5_n_a		85.75 76	86.09 69	84.72 180	85.73 318	63.58 272	93.79 105	89.32 321	81.42 58	90.21 35	96.91 25	62.41 142	97.67 63	94.48 18	80.56 248	92.90 224

TR-MVS		78.77 254	77.37 259	82.95 254	90.49 157	60.88 343	93.67 110	90.07 290	70.08 317	74.51 236	91.37 201	45.69 372	95.70 202	60.12 372	80.32 249	92.29 245

fmvsm_s_conf0.1_n_a		84.76 100	84.84 93	84.53 193	80.23 403	63.50 276	92.79 152	88.73 357	80.46 74	89.84 39	96.65 35	60.96 163	97.57 73	93.80 25	80.14 250	92.53 237

TAPA-MVS	70.22 12	74.94 326	73.53 321	79.17 364	90.40 159	52.07 438	89.19 331	89.61 312	62.69 402	70.07 300	92.67 152	48.89 336	94.32 278	38.26 467	79.97 251	91.12 278
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_cas_vis1_n_1920		80.45 215	80.61 192	79.97 345	78.25 430	57.01 411	94.04 87	88.33 372	79.06 121	82.81 108	93.70 130	38.65 404	91.63 382	90.82 55	79.81 252	91.27 276

cascas		78.18 264	75.77 286	85.41 138	87.14 268	69.11 74	92.96 143	91.15 219	66.71 359	70.47 293	86.07 309	37.49 418	96.48 147	70.15 272	79.80 253	90.65 285

HyFIR lowres test		81.03 202	79.56 212	85.43 137	87.81 248	68.11 110	90.18 300	90.01 295	70.65 310	72.95 257	86.06 310	63.61 119	94.50 272	75.01 222	79.75 254	93.67 195

mamba_0408		76.22 301	73.37 324	84.77 175	88.50 212	66.98 154	58.80 495	86.18 410	69.12 332	74.12 242	89.01 260	47.50 349	95.35 224	67.57 303	79.52 255	91.98 257

SSM_04072		74.86 328	73.37 324	79.35 361	88.50 212	66.98 154	58.80 495	86.18 410	69.12 332	74.12 242	89.01 260	47.50 349	79.09 482	67.57 303	79.52 255	91.98 257

SSM_0407		79.09 244	77.21 261	84.75 178	88.50 212	66.98 154	89.21 329	87.03 396	67.99 345	74.12 242	89.32 252	47.98 342	95.29 231	71.23 261	79.52 255	91.98 257

WB-MVSnew		77.14 285	76.18 281	80.01 342	86.18 303	63.24 283	91.26 251	94.11 73	71.72 279	73.52 252	87.29 293	45.14 377	93.00 332	56.98 385	79.42 258	83.80 403

LS3D		69.17 384	66.40 388	77.50 381	91.92 119	56.12 417	85.12 386	80.37 453	46.96 473	56.50 433	87.51 289	37.25 419	93.71 310	32.52 487	79.40 259	82.68 423

EI-MVSNet-Vis-set		83.77 132	83.67 113	84.06 210	92.79 92	63.56 273	91.76 220	94.81 37	79.65 98	77.87 188	94.09 122	63.35 125	97.90 52	79.35 185	79.36 260	90.74 284

CVMVSNet		74.04 336	74.27 307	73.33 424	85.33 324	43.94 481	89.53 321	88.39 368	54.33 453	70.37 296	90.13 237	49.17 332	84.05 455	61.83 362	79.36 260	91.99 256

guyue		81.23 195	80.57 194	83.21 250	86.64 287	61.85 319	92.52 176	92.78 130	78.69 128	74.92 230	89.42 250	50.07 319	95.35 224	80.79 171	79.31 262	92.42 239

EPP-MVSNet		81.79 182	81.52 172	82.61 263	88.77 202	60.21 365	93.02 140	93.66 90	68.52 340	72.90 258	90.39 222	72.19 40	94.96 242	74.93 223	79.29 263	92.67 230

SD_0403		73.79 340	73.48 323	74.69 411	85.33 324	45.56 477	83.80 398	85.57 419	76.55 179	62.96 387	88.45 266	50.62 314	87.59 434	48.80 420	79.28 264	90.92 282

CLD-MVS		82.73 162	82.35 161	83.86 218	87.90 242	67.65 125	95.45 29	92.18 161	85.06 14	72.58 264	92.27 162	52.46 292	95.78 192	84.18 122	79.06 265	88.16 322
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP3-MVS								91.70 190							78.90 266

HQP-MVS		81.14 198	80.64 191	82.64 262	87.54 254	63.66 270	94.06 83	91.70 190	79.80 92	74.18 238	90.30 225	51.63 300	95.61 210	77.63 201	78.90 266	88.63 312

plane_prior						62.42 304	93.85 99		79.38 110						78.80 268

thres200		79.66 230	78.33 235	83.66 231	92.54 98	65.82 192	93.06 136	96.31 3	74.90 201	73.30 254	88.66 263	59.67 183	95.61 210	47.84 427	78.67 269	89.56 302

ET-MVSNet_ETH3D		84.01 124	83.15 138	86.58 85	90.78 153	70.89 30	94.74 56	94.62 48	81.44 57	58.19 423	93.64 132	73.64 27	92.35 364	82.66 144	78.66 270	96.50 28

HQP_MVS		80.34 218	79.75 209	82.12 283	86.94 279	62.42 304	93.13 134	91.31 206	78.81 125	72.53 265	89.14 257	50.66 312	95.55 216	76.74 204	78.53 271	88.39 318

plane_prior5								91.31 206					95.55 216	76.74 204	78.53 271	88.39 318

EI-MVSNet-UG-set		83.14 154	82.96 141	83.67 230	92.28 101	63.19 286	91.38 242	94.68 44	79.22 114	76.60 207	93.75 128	62.64 138	97.76 58	78.07 199	78.01 273	90.05 293

OMC-MVS		78.67 257	77.91 246	80.95 320	85.76 316	57.40 404	88.49 344	88.67 360	73.85 220	72.43 271	92.10 170	49.29 330	94.55 269	72.73 244	77.89 274	90.91 283

1112_ss		80.56 212	79.83 207	82.77 257	88.65 204	60.78 345	92.29 183	88.36 369	72.58 249	72.46 270	94.95 88	65.09 92	93.42 323	66.38 318	77.71 275	94.10 173

OPM-MVS		79.00 246	78.09 239	81.73 291	83.52 363	63.83 258	91.64 230	90.30 279	76.36 181	71.97 277	89.93 244	46.30 368	95.17 236	75.10 220	77.70 276	86.19 365
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
dtuonly		74.56 331	73.92 315	76.48 395	77.15 441	57.27 406	85.09 387	81.23 447	71.37 293	67.61 339	89.65 247	46.68 361	83.84 459	68.79 288	77.69 277	88.33 320

PatchMatch-RL		72.06 362	69.98 361	78.28 373	89.51 178	55.70 421	83.49 402	83.39 442	61.24 416	63.72 378	82.76 351	34.77 433	93.03 331	53.37 402	77.59 278	86.12 369

thres100view900		78.37 261	77.01 264	82.46 266	91.89 122	63.21 285	91.19 258	96.33 1	72.28 259	70.45 295	87.89 282	60.31 172	95.32 227	45.16 440	77.58 279	88.83 308

tfpn200view9		78.79 253	77.43 254	82.88 255	92.21 104	64.49 227	92.05 197	96.28 4	73.48 230	71.75 280	88.26 272	60.07 177	95.32 227	45.16 440	77.58 279	88.83 308

thres400		78.68 255	77.43 254	82.43 267	92.21 104	64.49 227	92.05 197	96.28 4	73.48 230	71.75 280	88.26 272	60.07 177	95.32 227	45.16 440	77.58 279	87.48 330

CostFormer		82.33 170	81.15 177	85.86 120	89.01 196	68.46 97	82.39 419	93.01 120	75.59 187	80.25 146	81.57 370	72.03 41	94.96 242	79.06 189	77.48 282	94.16 167

tpm2		79.80 229	77.95 244	85.34 145	88.28 228	68.26 103	81.56 426	91.42 201	70.11 315	77.59 193	80.50 388	67.40 69	94.26 284	67.34 306	77.35 283	93.51 202

Test_1112_low_res		79.56 232	78.60 233	82.43 267	88.24 231	60.39 361	92.09 194	87.99 382	72.10 265	71.84 278	87.42 290	64.62 100	93.04 330	65.80 325	77.30 284	93.85 191

tpmrst		80.57 211	79.14 227	84.84 169	90.10 165	68.28 102	81.70 424	89.72 308	77.63 151	75.96 212	79.54 402	64.94 95	92.71 347	75.43 217	77.28 285	93.55 199

Anonymous202405211		77.96 270	75.33 292	85.87 119	93.73 59	64.52 226	94.85 52	85.36 421	62.52 403	76.11 211	90.18 228	29.43 458	97.29 91	68.51 290	77.24 286	95.81 58

GA-MVS		78.33 263	76.23 279	84.65 187	83.65 361	66.30 175	91.44 235	90.14 288	76.01 183	70.32 297	84.02 338	42.50 388	94.72 253	70.98 264	77.00 287	92.94 222

AstraMVS		80.66 210	79.79 208	83.28 245	85.07 334	61.64 327	92.19 188	90.58 263	79.40 109	74.77 233	90.18 228	45.93 371	95.61 210	83.04 139	76.96 288	92.60 233

thisisatest0530		81.15 197	80.07 200	84.39 199	88.26 229	65.63 195	91.40 238	94.62 48	71.27 295	70.93 289	89.18 255	72.47 35	96.04 172	65.62 329	76.89 289	91.49 266

thres600view7		78.00 268	76.66 269	82.03 288	91.93 118	63.69 268	91.30 250	96.33 1	72.43 254	70.46 294	87.89 282	60.31 172	94.92 245	42.64 452	76.64 290	87.48 330

PLC	68.80 14	75.23 321	73.68 320	79.86 348	92.93 84	58.68 388	90.64 282	88.30 373	60.90 418	64.43 372	90.53 218	42.38 389	94.57 264	56.52 386	76.54 291	86.33 361
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MIMVSNet		71.64 365	68.44 378	81.23 308	81.97 380	64.44 231	73.05 466	88.80 354	69.67 323	64.59 367	74.79 443	32.79 442	87.82 428	53.99 396	76.35 292	91.42 268

test_fmvs1		74.07 335	73.69 319	75.22 404	78.91 421	47.34 467	89.06 335	74.69 470	63.68 390	79.41 163	91.59 196	24.36 469	87.77 430	85.22 104	76.26 293	90.55 288

MVS-HIRNet		60.25 439	55.55 446	74.35 416	84.37 349	56.57 415	71.64 470	74.11 471	34.44 493	45.54 477	42.24 505	31.11 452	89.81 410	40.36 461	76.10 294	76.67 473

CNLPA		74.31 333	72.30 342	80.32 331	91.49 134	61.66 326	90.85 270	80.72 451	56.67 445	63.85 377	90.64 215	46.75 360	90.84 394	53.79 398	75.99 295	88.47 317

ab-mvs		80.18 221	78.31 236	85.80 123	88.44 220	65.49 201	83.00 413	92.67 137	71.82 275	77.36 196	85.01 324	54.50 265	96.59 138	76.35 211	75.63 296	95.32 81

test_fmvs1_n		72.69 355	71.92 346	74.99 409	71.15 470	47.08 469	87.34 366	75.67 465	63.48 392	78.08 187	91.17 210	20.16 483	87.87 427	84.65 113	75.57 297	90.01 294

testing3-2		83.11 155	83.15 138	82.98 253	91.92 119	64.01 252	94.39 72	95.37 17	78.32 134	75.53 220	90.06 241	73.18 29	93.18 328	74.34 229	75.27 298	91.77 262

FIs		79.47 235	79.41 218	79.67 354	85.95 309	59.40 378	91.68 228	93.94 77	78.06 139	68.96 316	88.28 270	66.61 75	91.77 378	66.20 321	74.99 299	87.82 325

SDMVSNet		80.26 219	78.88 230	84.40 198	89.25 186	67.63 126	85.35 384	93.02 119	76.77 170	70.84 290	87.12 295	47.95 345	96.09 167	85.04 107	74.55 300	89.48 303

sd_testset		77.08 287	75.37 290	82.20 279	89.25 186	62.11 313	82.06 420	89.09 337	76.77 170	70.84 290	87.12 295	41.43 393	95.01 240	67.23 308	74.55 300	89.48 303

CMPMVS	48.56 21	66.77 406	64.41 406	73.84 421	70.65 473	50.31 451	77.79 453	85.73 417	45.54 478	44.76 479	82.14 360	35.40 431	90.14 406	63.18 352	74.54 302	81.07 438
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dmvs_re		76.93 289	75.36 291	81.61 296	87.78 250	60.71 351	80.00 442	87.99 382	79.42 108	69.02 313	89.47 249	46.77 359	94.32 278	63.38 349	74.45 303	89.81 296

test_vis1_n		71.63 366	70.73 357	74.31 418	69.63 477	47.29 468	86.91 370	72.11 478	63.21 396	75.18 225	90.17 234	20.40 481	85.76 445	84.59 115	74.42 304	89.87 295

XVG-OURS		74.25 334	72.46 341	79.63 355	78.45 428	57.59 401	80.33 436	87.39 388	63.86 387	68.76 320	89.62 248	40.50 397	91.72 379	69.00 284	74.25 305	89.58 300

tpm cat1		75.30 320	72.21 343	84.58 192	88.52 211	67.77 120	78.16 452	88.02 381	61.88 411	68.45 325	76.37 434	60.65 167	94.03 298	53.77 399	74.11 306	91.93 260

XVG-OURS-SEG-HR		74.70 330	73.08 329	79.57 357	78.25 430	57.33 405	80.49 434	87.32 391	63.22 395	68.76 320	90.12 239	44.89 379	91.59 383	70.55 270	74.09 307	89.79 297

FC-MVSNet-test		77.99 269	78.08 240	77.70 378	84.89 337	55.51 422	90.27 297	93.75 86	76.87 165	66.80 352	87.59 287	65.71 86	90.23 404	62.89 355	73.94 308	87.37 333

PVSNet_BlendedMVS		83.38 148	83.43 122	83.22 248	93.76 56	67.53 129	94.06 83	93.61 91	79.13 117	81.00 130	85.14 323	63.19 128	97.29 91	87.08 88	73.91 309	84.83 394

tttt0517		79.50 233	78.53 234	82.41 270	87.22 263	61.43 334	89.75 312	94.76 39	69.29 327	67.91 332	88.06 279	72.92 31	95.63 206	62.91 354	73.90 310	90.16 291

MDTV_nov1_ep13			72.61 338		89.06 193	68.48 95	80.33 436	90.11 289	71.84 274	71.81 279	75.92 438	53.01 286	93.92 303	48.04 424	73.38 311

SCA		75.82 313	72.76 334	85.01 160	86.63 289	70.08 40	81.06 431	89.19 328	71.60 286	70.01 301	77.09 423	45.53 373	90.25 400	60.43 369	73.27 312	94.68 128

CR-MVSNet		73.79 340	70.82 356	82.70 260	83.15 367	67.96 113	70.25 472	84.00 434	73.67 228	69.97 303	72.41 451	57.82 222	89.48 413	52.99 403	73.13 313	90.64 286

RPMNet		70.42 374	65.68 394	84.63 190	83.15 367	67.96 113	70.25 472	90.45 266	46.83 475	69.97 303	65.10 477	56.48 243	95.30 230	35.79 472	73.13 313	90.64 286

Fast-Effi-MVS+-dtu		75.04 324	73.37 324	80.07 339	80.86 389	59.52 377	91.20 257	85.38 420	71.90 269	65.20 362	84.84 326	41.46 392	92.97 333	66.50 317	72.96 315	87.73 326

LPG-MVS_test		75.82 313	74.58 301	79.56 358	84.31 350	59.37 379	90.44 289	89.73 306	69.49 324	64.86 364	88.42 267	38.65 404	94.30 280	72.56 246	72.76 316	85.01 392

LGP-MVS_train				79.56 358	84.31 350	59.37 379		89.73 306	69.49 324	64.86 364	88.42 267	38.65 404	94.30 280	72.56 246	72.76 316	85.01 392

EG-PatchMatch MVS		68.55 390	65.41 397	77.96 377	78.69 424	62.93 292	89.86 310	89.17 329	60.55 420	50.27 459	77.73 415	22.60 477	94.06 293	47.18 431	72.65 318	76.88 472

EI-MVSNet		78.97 247	78.22 238	81.25 307	85.33 324	62.73 299	89.53 321	93.21 109	72.39 256	72.14 274	90.13 237	60.99 161	94.72 253	67.73 301	72.49 319	86.29 362

MVSTER		82.47 168	82.05 163	83.74 223	92.68 94	69.01 79	91.90 209	93.21 109	79.83 91	72.14 274	85.71 316	74.72 19	94.72 253	75.72 215	72.49 319	87.50 329

Anonymous20240529		76.84 292	74.15 311	84.88 167	91.02 146	64.95 215	93.84 102	91.09 226	53.57 454	73.00 255	87.42 290	35.91 429	97.32 89	69.14 283	72.41 321	92.36 241

D2MVS		73.80 339	72.02 345	79.15 366	79.15 416	62.97 290	88.58 343	90.07 290	72.94 240	59.22 416	78.30 408	42.31 390	92.70 349	65.59 330	72.00 322	81.79 432

PS-MVSNAJss		77.26 283	76.31 277	80.13 338	80.64 395	59.16 383	90.63 284	91.06 232	72.80 245	68.58 323	84.57 330	53.55 280	93.96 301	72.97 238	71.96 323	87.27 337

Effi-MVS+-dtu		76.14 303	75.28 293	78.72 369	83.22 366	55.17 424	89.87 309	87.78 386	75.42 191	67.98 330	81.43 372	45.08 378	92.52 356	75.08 221	71.63 324	88.48 316

ACMMP++_ref															71.63 324

ACMM	69.62 13	74.34 332	72.73 336	79.17 364	84.25 352	57.87 395	90.36 294	89.93 297	63.17 397	65.64 359	86.04 311	37.79 416	94.10 289	65.89 323	71.52 326	85.55 384
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	71.68 10	75.58 318	74.23 308	79.62 356	84.97 336	59.64 374	90.80 272	89.07 339	70.39 312	62.95 388	87.30 292	38.28 408	93.87 306	72.89 239	71.45 327	85.36 388
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
dp		75.01 325	72.09 344	83.76 222	89.28 185	66.22 178	79.96 444	89.75 303	71.16 296	67.80 336	77.19 422	51.81 296	92.54 355	50.39 410	71.44 328	92.51 238

tpm		78.58 258	77.03 263	83.22 248	85.94 311	64.56 225	83.21 409	91.14 220	78.31 135	73.67 251	79.68 400	64.01 109	92.09 372	66.07 322	71.26 329	93.03 219

DP-MVS		69.90 379	66.48 386	80.14 337	95.36 31	62.93 292	89.56 316	76.11 463	50.27 465	57.69 429	85.23 322	39.68 400	95.73 196	33.35 479	71.05 330	81.78 433

UniMVSNet_ETH3D		72.74 352	70.53 359	79.36 360	78.62 426	56.64 413	85.01 388	89.20 327	63.77 388	64.84 366	84.44 332	34.05 438	91.86 376	63.94 345	70.89 331	89.57 301

usedtu_dtu_shiyan1		77.89 274	76.39 275	82.40 271	81.92 381	67.01 152	91.94 206	93.00 122	77.01 162	68.44 326	84.15 334	54.78 262	93.25 325	65.76 326	70.53 332	86.94 342

FE-MVSNET3		77.89 274	76.39 275	82.40 271	81.92 381	67.01 152	91.94 206	93.00 122	77.01 162	68.44 326	84.15 334	54.78 262	93.25 325	65.76 326	70.53 332	86.94 342

jajsoiax		73.05 346	71.51 351	77.67 379	77.46 438	54.83 426	88.81 339	90.04 293	69.13 331	62.85 390	83.51 343	31.16 451	92.75 346	70.83 265	69.80 334	85.43 387

ACMMP++															69.72 335

mvs_tets		72.71 353	71.11 352	77.52 380	77.41 439	54.52 428	88.45 345	89.76 302	68.76 338	62.70 391	83.26 347	29.49 457	92.71 347	70.51 271	69.62 336	85.34 389

tpmvs		72.88 350	69.76 366	82.22 278	90.98 147	67.05 147	78.22 451	88.30 373	63.10 398	64.35 373	74.98 441	55.09 259	94.27 282	43.25 446	69.57 337	85.34 389

GBi-Net		75.65 315	73.83 317	81.10 314	88.85 198	65.11 210	90.01 305	90.32 275	70.84 303	67.04 347	80.25 393	48.03 339	91.54 386	59.80 374	69.34 338	86.64 348

test1		75.65 315	73.83 317	81.10 314	88.85 198	65.11 210	90.01 305	90.32 275	70.84 303	67.04 347	80.25 393	48.03 339	91.54 386	59.80 374	69.34 338	86.64 348

FMVSNet3		77.73 276	76.04 282	82.80 256	91.20 143	68.99 80	91.87 210	91.99 170	73.35 232	67.04 347	83.19 348	56.62 239	92.14 369	59.80 374	69.34 338	87.28 336

Syy-MVS		69.65 381	69.52 367	70.03 445	87.87 245	43.21 483	88.07 351	89.01 343	72.91 242	63.11 384	88.10 276	45.28 376	85.54 446	22.07 499	69.23 341	81.32 435

myMVS_eth3d		72.58 357	72.74 335	72.10 436	87.87 245	49.45 456	88.07 351	89.01 343	72.91 242	63.11 384	88.10 276	63.63 117	85.54 446	32.73 485	69.23 341	81.32 435

MSDG		69.54 382	65.73 393	80.96 319	85.11 333	63.71 265	84.19 395	83.28 443	56.95 442	54.50 438	84.03 337	31.50 448	96.03 173	42.87 450	69.13 343	83.14 415

JIA-IIPM		66.06 409	62.45 418	76.88 393	81.42 387	54.45 429	57.49 497	88.67 360	49.36 468	63.86 376	46.86 496	56.06 247	90.25 400	49.53 415	68.83 344	85.95 373

OpenMVS_ROB	61.12 18	66.39 407	62.92 415	76.80 394	76.51 443	57.77 396	89.22 328	83.41 441	55.48 450	53.86 442	77.84 413	26.28 467	93.95 302	34.90 474	68.76 345	78.68 462

FMVSNet2		76.07 304	74.01 314	82.26 277	88.85 198	67.66 124	91.33 248	91.61 193	70.84 303	65.98 356	82.25 358	48.03 339	92.00 374	58.46 379	68.73 346	87.10 339

test_djsdf		73.76 342	72.56 339	77.39 384	77.00 442	53.93 430	89.07 333	90.69 257	65.80 370	63.92 375	82.03 361	43.14 387	92.67 350	72.83 240	68.53 347	85.57 383

F-COLMAP		70.66 371	68.44 378	77.32 385	86.37 300	55.91 419	88.00 353	86.32 405	56.94 443	57.28 431	88.07 278	33.58 440	92.49 357	51.02 407	68.37 348	83.55 405

XVG-ACMP-BASELINE		68.04 396	65.53 396	75.56 401	74.06 461	52.37 436	78.43 448	85.88 414	62.03 408	58.91 420	81.21 380	20.38 482	91.15 393	60.69 368	68.18 349	83.16 414

WBMVS		81.67 183	80.98 184	83.72 227	93.07 81	69.40 60	94.33 73	93.05 118	76.84 167	72.05 276	84.14 336	74.49 21	93.88 305	72.76 243	68.09 350	87.88 324

LTVRE_ROB	59.60 19	66.27 408	63.54 411	74.45 415	84.00 355	51.55 441	67.08 483	83.53 439	58.78 432	54.94 437	80.31 391	34.54 434	93.23 327	40.64 460	68.03 351	78.58 463
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		77.94 271	76.44 272	82.43 267	82.60 373	64.44 231	92.01 199	91.83 181	73.59 229	70.00 302	85.82 314	54.43 269	94.76 250	69.63 275	68.02 352	88.10 323

viewdifsd2359ckpt11		79.42 238	77.95 244	83.81 220	83.87 357	63.85 255	89.54 318	87.38 389	77.39 158	74.94 228	89.95 242	51.11 308	94.72 253	79.52 182	67.90 353	92.88 226

viewmsd2359difaftdt		79.42 238	77.96 243	83.81 220	83.88 356	63.85 255	89.54 318	87.38 389	77.39 158	74.94 228	89.95 242	51.11 308	94.72 253	79.52 182	67.90 353	92.88 226

ADS-MVSNet2		66.90 404	63.44 412	77.26 387	88.06 236	60.70 352	68.01 479	75.56 467	57.57 436	64.48 369	69.87 463	38.68 402	84.10 454	40.87 458	67.89 355	86.97 340

ADS-MVSNet		68.54 391	64.38 407	81.03 318	88.06 236	66.90 159	68.01 479	84.02 433	57.57 436	64.48 369	69.87 463	38.68 402	89.21 415	40.87 458	67.89 355	86.97 340

test0.0.03 1		72.76 351	72.71 337	72.88 428	80.25 402	47.99 463	91.22 255	89.45 316	71.51 290	62.51 393	87.66 285	53.83 276	85.06 451	50.16 412	67.84 357	85.58 382

anonymousdsp		71.14 369	69.37 370	76.45 396	72.95 465	54.71 427	84.19 395	88.88 349	61.92 410	62.15 394	79.77 399	38.14 411	91.44 391	68.90 286	67.45 358	83.21 413

tt0805		73.07 345	70.73 357	80.07 339	78.37 429	57.05 409	87.78 358	92.18 161	61.23 417	67.04 347	86.49 304	31.35 450	94.58 262	65.06 335	67.12 359	88.57 314

VPA-MVSNet		79.03 245	78.00 241	82.11 286	85.95 309	64.48 229	93.22 132	94.66 45	75.05 199	74.04 246	84.95 325	52.17 294	93.52 316	74.90 225	67.04 360	88.32 321

nrg030		80.93 204	79.86 206	84.13 209	83.69 360	68.83 84	93.23 131	91.20 214	75.55 188	75.06 226	88.22 275	63.04 134	94.74 252	81.88 154	66.88 361	88.82 310

FMVSNet1		72.71 353	69.91 364	81.10 314	83.60 362	65.11 210	90.01 305	90.32 275	63.92 386	63.56 379	80.25 393	36.35 428	91.54 386	54.46 394	66.75 362	86.64 348

PatchT		69.11 385	65.37 398	80.32 331	82.07 379	63.68 269	67.96 481	87.62 387	50.86 463	69.37 307	65.18 476	57.09 228	88.53 420	41.59 456	66.60 363	88.74 311

IB-MVS	77.80 4	82.18 174	80.46 197	87.35 49	89.14 191	70.28 38	95.59 27	95.17 25	78.85 123	70.19 299	85.82 314	70.66 47	97.67 63	72.19 253	66.52 364	94.09 174
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		65.78 412	64.84 399	68.60 452	66.54 484	41.71 486	83.27 406	69.81 485	54.38 452	67.91 332	84.54 331	15.35 489	81.22 478	75.65 216	66.16 365	82.88 416

pmmvs5		73.35 343	71.52 350	78.86 368	78.64 425	60.61 355	91.08 261	86.90 398	67.69 349	63.32 382	83.64 341	44.33 382	90.53 397	62.04 360	66.02 366	85.46 386

SSC-MVS3.2		74.92 327	73.32 327	79.74 352	86.53 292	60.31 362	89.03 336	92.70 133	78.61 130	68.98 315	83.34 346	41.93 391	92.23 368	52.77 404	65.97 367	86.69 347

dmvs_testset		65.55 413	66.45 387	62.86 465	79.87 406	22.35 514	76.55 456	71.74 480	77.42 157	55.85 434	87.77 284	51.39 304	80.69 479	31.51 491	65.92 368	85.55 384

MonoMVSNet		76.99 288	75.08 295	82.73 258	83.32 365	63.24 283	86.47 377	86.37 404	79.08 119	66.31 355	79.30 404	49.80 324	91.72 379	79.37 184	65.70 369	93.23 210

pmmvs4		73.92 338	71.81 348	80.25 335	79.17 415	65.24 206	87.43 364	87.26 394	67.64 352	63.46 381	83.91 340	48.96 335	91.53 389	62.94 353	65.49 370	83.96 400

cl22		77.94 271	76.78 267	81.42 300	87.57 253	64.93 216	90.67 280	88.86 352	72.45 253	67.63 338	82.68 353	64.07 107	92.91 339	71.79 254	65.30 371	86.44 355

miper_ehance_all_eth		77.60 278	76.44 272	81.09 317	85.70 319	64.41 234	90.65 281	88.64 362	72.31 257	67.37 345	82.52 354	64.77 99	92.64 353	70.67 268	65.30 371	86.24 364

miper_enhance_ethall		78.86 250	77.97 242	81.54 298	88.00 240	65.17 208	91.41 236	89.15 331	75.19 196	68.79 319	83.98 339	67.17 70	92.82 342	72.73 244	65.30 371	86.62 352

VortexMVS		77.62 277	76.44 272	81.13 311	88.58 205	63.73 263	91.24 253	91.30 210	77.81 144	65.76 357	81.97 362	49.69 325	93.72 309	76.40 210	65.26 374	85.94 375

v1144		76.73 296	74.88 296	82.27 275	80.23 403	66.60 168	91.68 228	90.21 287	73.69 226	69.06 312	81.89 363	52.73 290	94.40 276	69.21 281	65.23 375	85.80 378

DSMNet-mixed		56.78 446	54.44 449	63.79 463	63.21 489	29.44 507	64.43 486	64.10 494	42.12 490	51.32 454	71.60 457	31.76 447	75.04 487	36.23 469	65.20 376	86.87 345

v1192		75.98 309	73.92 315	82.15 281	79.73 407	66.24 177	91.22 255	89.75 303	72.67 247	68.49 324	81.42 373	49.86 322	94.27 282	67.08 310	65.02 377	85.95 373

v2v482		77.42 281	75.65 288	82.73 258	80.38 399	67.13 145	91.85 212	90.23 284	75.09 198	69.37 307	83.39 345	53.79 278	94.44 274	71.77 255	65.00 378	86.63 351

V42		76.46 298	74.55 302	82.19 280	79.14 417	67.82 119	90.26 298	89.42 318	73.75 223	68.63 322	81.89 363	51.31 305	94.09 290	71.69 257	64.84 379	84.66 395

ACMH	63.93 17	68.62 389	64.81 400	80.03 341	85.22 329	63.25 282	87.72 359	84.66 427	60.83 419	51.57 453	79.43 403	27.29 464	94.96 242	41.76 454	64.84 379	81.88 431
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline1		81.84 181	81.03 182	84.28 204	91.60 129	66.62 167	91.08 261	91.66 192	81.87 49	74.86 231	91.67 193	69.98 52	94.92 245	71.76 256	64.75 381	91.29 275

v1240		75.21 322	72.98 332	81.88 289	79.20 414	66.00 184	90.75 275	89.11 336	71.63 285	67.41 343	81.22 378	47.36 351	93.87 306	65.46 332	64.72 382	85.77 379

IterMVS-LS		76.49 297	75.18 294	80.43 330	84.49 346	62.74 298	90.64 282	88.80 354	72.40 255	65.16 363	81.72 366	60.98 162	92.27 367	67.74 300	64.65 383	86.29 362
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		75.63 317	73.49 322	82.06 287	79.38 412	66.35 173	91.07 264	89.48 314	71.98 266	67.99 329	81.22 378	49.16 333	93.90 304	66.56 314	64.56 384	85.92 376

v144192		76.05 307	74.03 313	82.12 283	79.50 411	66.55 170	91.39 240	89.71 309	72.30 258	68.17 328	81.33 375	51.75 298	94.03 298	67.94 298	64.19 385	85.77 379

Anonymous20231211		73.08 344	70.39 360	81.13 311	90.62 154	63.33 279	91.40 238	90.06 292	51.84 459	64.46 371	80.67 386	36.49 427	94.07 292	63.83 346	64.17 386	85.98 372

testing3		70.38 375	70.83 354	69.03 450	85.82 314	43.93 482	90.72 278	90.56 264	68.06 344	60.24 410	86.82 301	64.83 97	84.12 453	26.33 494	64.10 387	79.04 457

Patchmatch-test		65.86 410	60.94 425	80.62 328	83.75 359	58.83 386	58.91 494	75.26 469	44.50 482	50.95 458	77.09 423	58.81 204	87.90 426	35.13 473	64.03 388	95.12 96

USDC		67.43 403	64.51 404	76.19 398	77.94 434	55.29 423	78.38 449	85.00 424	73.17 234	48.36 468	80.37 390	21.23 479	92.48 358	52.15 405	64.02 389	80.81 441

VPNet		78.82 251	77.53 253	82.70 260	84.52 344	66.44 171	93.93 93	92.23 154	80.46 74	72.60 263	88.38 269	49.18 331	93.13 329	72.47 248	63.97 390	88.55 315

Anonymous20231206		67.53 401	65.78 392	72.79 429	74.95 457	47.59 465	88.23 348	87.32 391	61.75 415	58.07 425	77.29 419	37.79 416	87.29 438	42.91 448	63.71 391	83.48 408

WR-MVS		76.76 295	75.74 287	79.82 349	84.60 341	62.27 310	92.60 168	92.51 146	76.06 182	67.87 335	85.34 321	56.76 235	90.24 403	62.20 359	63.69 392	86.94 342

blend_shiyan4		75.18 323	73.00 331	81.69 294	75.62 450	64.75 218	91.78 217	91.06 232	65.89 369	61.35 398	77.39 416	62.16 148	93.71 310	68.18 291	63.60 393	86.61 353

0.3-1-1-0.015		81.31 192	79.49 215	86.77 73	85.74 317	68.70 94	95.01 46	94.42 59	74.29 210	77.09 203	85.61 317	63.31 127	95.69 204	76.63 207	63.30 394	95.91 52

0.4-1-1-0.2		81.28 194	79.42 217	86.84 65	85.80 315	68.82 85	95.10 39	94.43 58	74.45 205	77.18 200	85.54 318	62.27 144	95.70 202	76.72 206	63.30 394	96.01 46

0.4-1-1-0.1		80.99 203	79.16 225	86.51 96	85.55 322	68.21 107	94.77 54	94.42 59	73.75 223	76.57 208	85.41 320	62.35 143	95.62 208	76.30 212	63.28 396	95.71 61

h-mvs33		83.01 157	82.56 157	84.35 201	89.34 180	62.02 314	92.72 155	93.76 83	81.45 55	82.73 109	92.25 164	60.11 175	97.13 106	87.69 75	62.96 397	93.91 187

c3_l		76.83 293	75.47 289	80.93 321	85.02 335	64.18 246	90.39 292	88.11 379	71.66 280	66.65 354	81.64 368	63.58 122	92.56 354	69.31 280	62.86 398	86.04 370

test_vis1_rt		59.09 443	57.31 440	64.43 462	68.44 480	46.02 475	83.05 412	48.63 507	51.96 458	49.57 462	63.86 480	16.30 487	80.20 480	71.21 263	62.79 399	67.07 489

mvsany_test1		68.77 388	68.56 376	69.39 448	73.57 462	45.88 476	80.93 432	60.88 498	59.65 427	71.56 283	90.26 227	43.22 386	75.05 486	74.26 230	62.70 400	87.25 338

UniMVSNet_NR-MVSNet		78.15 265	77.55 252	79.98 343	84.46 347	60.26 363	92.25 184	93.20 111	77.50 154	68.88 317	86.61 302	66.10 80	92.13 370	66.38 318	62.55 401	87.54 328

DU-MVS		76.86 290	75.84 285	79.91 346	82.96 369	60.26 363	91.26 251	91.54 195	76.46 180	68.88 317	86.35 305	56.16 244	92.13 370	66.38 318	62.55 401	87.35 334

UniMVSNet (Re)		77.58 279	76.78 267	79.98 343	84.11 353	60.80 344	91.76 220	93.17 113	76.56 178	69.93 305	84.78 327	63.32 126	92.36 363	64.89 336	62.51 403	86.78 346

v8		75.35 319	73.26 328	81.61 296	80.67 394	66.82 160	89.54 318	89.27 323	71.65 281	63.30 383	80.30 392	54.99 260	94.06 293	67.33 307	62.33 404	83.94 401

cl____		76.07 304	74.67 297	80.28 333	85.15 330	61.76 323	90.12 301	88.73 357	71.16 296	65.43 360	81.57 370	61.15 159	92.95 334	66.54 315	62.17 405	86.13 368

v10		74.77 329	72.54 340	81.46 299	80.33 401	66.71 165	89.15 332	89.08 338	70.94 301	63.08 386	79.86 397	52.52 291	94.04 296	65.70 328	62.17 405	83.64 404

DIV-MVS_self_test		76.07 304	74.67 297	80.28 333	85.14 331	61.75 324	90.12 301	88.73 357	71.16 296	65.42 361	81.60 369	61.15 159	92.94 338	66.54 315	62.16 407	86.14 366

IterMVS-SCA-FT		71.55 367	69.97 362	76.32 397	81.48 385	60.67 353	87.64 362	85.99 413	66.17 365	59.50 414	78.88 405	45.53 373	83.65 460	62.58 357	61.93 408	84.63 398

IterMVS		72.65 356	70.83 354	78.09 376	82.17 377	62.96 291	87.64 362	86.28 406	71.56 288	60.44 407	78.85 406	45.42 375	86.66 440	63.30 351	61.83 409	84.65 396
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet5		68.04 396	65.66 395	75.18 406	84.43 348	57.89 394	83.54 400	86.26 407	61.83 412	53.64 444	73.30 446	37.15 422	85.08 450	48.99 418	61.77 410	82.56 425

v7n		71.31 368	68.65 375	79.28 362	76.40 444	60.77 346	86.71 374	89.45 316	64.17 385	58.77 421	78.24 409	44.59 381	93.54 315	57.76 381	61.75 411	83.52 407

v148		76.19 302	74.47 304	81.36 303	80.05 405	64.44 231	91.75 222	90.23 284	73.68 227	67.13 346	80.84 383	55.92 249	93.86 308	68.95 285	61.73 412	85.76 381

tfpnnormal		70.10 376	67.36 384	78.32 372	83.45 364	60.97 342	88.85 337	92.77 131	64.85 379	60.83 402	78.53 407	43.52 385	93.48 317	31.73 488	61.70 413	80.52 444

ACMH+	65.35 16	67.65 399	64.55 403	76.96 392	84.59 342	57.10 408	88.08 350	80.79 450	58.59 434	53.00 446	81.09 382	26.63 466	92.95 334	46.51 433	61.69 414	80.82 440

ITE_SJBPF				70.43 444	74.44 459	47.06 470		77.32 460	60.16 424	54.04 441	83.53 342	23.30 474	84.01 456	43.07 447	61.58 415	80.21 450

NR-MVSNet		76.05 307	74.59 300	80.44 329	82.96 369	62.18 312	90.83 271	91.73 185	77.12 161	60.96 401	86.35 305	59.28 192	91.80 377	60.74 367	61.34 416	87.35 334

test_0402		64.54 417	61.09 424	74.92 410	84.10 354	60.75 348	87.95 354	79.71 455	52.03 457	52.41 448	77.20 421	32.21 446	91.64 381	23.14 497	61.03 417	72.36 482

Baseline_NR-MVSNet		73.99 337	72.83 333	77.48 382	80.78 392	59.29 382	91.79 214	84.55 429	68.85 335	68.99 314	80.70 384	56.16 244	92.04 373	62.67 356	60.98 418	81.11 437

TranMVSNet+NR-MVSNet		75.86 312	74.52 303	79.89 347	82.44 375	60.64 354	91.37 243	91.37 203	76.63 176	67.65 337	86.21 308	52.37 293	91.55 385	61.84 361	60.81 419	87.48 330

testgi		64.48 418	62.87 416	69.31 449	71.24 468	40.62 489	85.49 383	79.92 454	65.36 376	54.18 440	83.49 344	23.74 472	84.55 452	41.60 455	60.79 420	82.77 418

eth_miper_zixun_eth		75.96 311	74.40 305	80.66 325	84.66 340	63.02 289	89.28 327	88.27 375	71.88 271	65.73 358	81.65 367	59.45 187	92.81 343	68.13 293	60.53 421	86.14 366

COLMAP_ROB	57.96 20	62.98 427	59.65 429	72.98 427	81.44 386	53.00 434	83.75 399	75.53 468	48.34 471	48.81 467	81.40 374	24.14 470	90.30 399	32.95 482	60.52 422	75.65 475
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AUN-MVS		78.37 261	77.43 254	81.17 309	86.60 290	57.45 403	89.46 323	91.16 216	74.11 213	74.40 237	90.49 220	55.52 253	94.57 264	74.73 227	60.43 423	91.48 267

hse-mvs2		81.12 200	81.11 181	81.16 310	86.52 294	57.48 402	89.40 324	91.16 216	81.45 55	82.73 109	90.49 220	60.11 175	94.58 262	87.69 75	60.41 424	91.41 269

RPSCF		64.24 419	61.98 422	71.01 442	76.10 446	45.00 478	75.83 461	75.94 464	46.94 474	58.96 419	84.59 329	31.40 449	82.00 475	47.76 429	60.33 425	86.04 370

miper_lstm_enhance		73.05 346	71.73 349	77.03 389	83.80 358	58.32 392	81.76 422	88.88 349	69.80 321	61.01 400	78.23 410	57.19 227	87.51 436	65.34 333	59.53 426	85.27 391

CP-MVSNet		70.50 373	69.91 364	72.26 433	80.71 393	51.00 446	87.23 367	90.30 279	67.84 348	59.64 413	82.69 352	50.23 318	82.30 473	51.28 406	59.28 427	83.46 409

PS-CasMVS		69.86 380	69.13 373	72.07 437	80.35 400	50.57 449	87.02 369	89.75 303	67.27 354	59.19 417	82.28 357	46.58 363	82.24 474	50.69 409	59.02 428	83.39 411

pm-mvs1		72.89 349	71.09 353	78.26 374	79.10 418	57.62 399	90.80 272	89.30 322	67.66 350	62.91 389	81.78 365	49.11 334	92.95 334	60.29 371	58.89 429	84.22 399

Anonymous20240521		62.09 428	59.08 432	71.10 441	67.19 482	48.72 461	83.91 397	85.23 422	50.38 464	47.84 469	71.22 461	20.74 480	85.51 448	46.47 434	58.75 430	79.06 456

WR-MVS_H		70.59 372	69.94 363	72.53 430	81.03 388	51.43 442	87.35 365	92.03 169	67.38 353	60.23 411	80.70 384	55.84 251	83.45 463	46.33 435	58.58 431	82.72 420

reproduce_monomvs		79.49 234	79.11 228	80.64 326	92.91 85	61.47 333	91.17 259	93.28 107	83.09 33	64.04 374	82.38 356	66.19 78	94.57 264	81.19 167	57.71 432	85.88 377

PEN-MVS		69.46 383	68.56 376	72.17 435	79.27 413	49.71 454	86.90 371	89.24 325	67.24 357	59.08 418	82.51 355	47.23 352	83.54 462	48.42 422	57.12 433	83.25 412

EU-MVSNet		64.01 420	63.01 414	67.02 459	74.40 460	38.86 495	83.27 406	86.19 409	45.11 480	54.27 439	81.15 381	36.91 425	80.01 481	48.79 421	57.02 434	82.19 429

AllTest		61.66 430	58.06 434	72.46 431	79.57 408	51.42 443	80.17 439	68.61 487	51.25 461	45.88 473	81.23 376	19.86 484	86.58 441	38.98 464	57.01 435	79.39 453

TestCases				72.46 431	79.57 408	51.42 443		68.61 487	51.25 461	45.88 473	81.23 376	19.86 484	86.58 441	38.98 464	57.01 435	79.39 453

Patchmtry		67.53 401	63.93 409	78.34 371	82.12 378	64.38 235	68.72 476	84.00 434	48.23 472	59.24 415	72.41 451	57.82 222	89.27 414	46.10 436	56.68 437	81.36 434

our_test_3		68.29 394	64.69 402	79.11 367	78.92 419	64.85 217	88.40 346	85.06 423	60.32 423	52.68 447	76.12 436	40.81 396	89.80 412	44.25 445	55.65 438	82.67 424

FPMVS		45.64 458	43.10 462	53.23 477	51.42 503	36.46 497	64.97 485	71.91 479	29.13 498	27.53 500	61.55 486	9.83 499	65.01 503	16.00 509	55.58 439	58.22 496

DTE-MVSNet		68.46 392	67.33 385	71.87 439	77.94 434	49.00 459	86.16 380	88.58 364	66.36 362	58.19 423	82.21 359	46.36 364	83.87 458	44.97 443	55.17 440	82.73 419

MIMVSNet1		60.16 440	57.33 439	68.67 451	69.71 476	44.13 480	78.92 446	84.21 430	55.05 451	44.63 480	71.85 456	23.91 471	81.54 477	32.63 486	55.03 441	80.35 446

pmmvs6		67.57 400	64.76 401	76.00 400	72.82 467	53.37 432	88.71 340	86.78 402	53.19 455	57.58 430	78.03 412	35.33 432	92.41 360	55.56 390	54.88 442	82.21 428

TinyColmap		60.32 438	56.42 445	72.00 438	78.78 422	53.18 433	78.36 450	75.64 466	52.30 456	41.59 488	75.82 439	14.76 492	88.35 423	35.84 470	54.71 443	74.46 476

test20.03		63.83 421	62.65 417	67.38 458	70.58 474	39.94 491	86.57 375	84.17 431	63.29 394	51.86 451	77.30 418	37.09 423	82.47 470	38.87 466	54.13 444	79.73 451

OurMVSNet-221017-0		64.68 416	62.17 420	72.21 434	76.08 447	47.35 466	80.67 433	81.02 449	56.19 447	51.60 452	79.66 401	27.05 465	88.56 419	53.60 400	53.63 445	80.71 442

FE-MVSNET2		66.80 405	64.06 408	75.03 407	69.84 475	57.11 407	86.57 375	88.57 365	67.94 347	50.97 457	72.16 455	33.79 439	87.55 435	53.94 397	52.74 446	80.45 445

test_fmvs3		56.82 445	54.86 448	62.69 467	53.59 500	35.47 498	75.87 460	65.64 492	43.91 484	55.10 436	71.43 460	6.91 504	74.40 489	68.64 289	52.63 447	78.20 466

Patchmatch-RL test		68.17 395	64.49 405	79.19 363	71.22 469	53.93 430	70.07 474	71.54 482	69.22 328	56.79 432	62.89 481	56.58 240	88.61 417	69.53 277	52.61 448	95.03 102

ppachtmachnet_test		67.72 398	63.70 410	79.77 351	78.92 419	66.04 183	88.68 341	82.90 445	60.11 425	55.45 435	75.96 437	39.19 401	90.55 396	39.53 462	52.55 449	82.71 421

LF4IMVS		54.01 450	52.12 451	59.69 468	62.41 491	39.91 493	68.59 477	68.28 489	42.96 488	44.55 481	75.18 440	14.09 494	68.39 496	41.36 457	51.68 450	70.78 483

PatchmatchNet1														31.49 492	51.52 451	77.88 468
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
N_pmnet		50.55 453	49.11 455	54.88 474	77.17 440	4.02 534	84.36 392	2.00 532	48.59 469	45.86 475	68.82 466	32.22 445	82.80 469	31.58 489	51.38 452	77.81 469

blended_shiyan8		72.26 360	69.25 372	81.29 305	75.23 456	64.03 250	91.36 246	91.04 236	66.11 367	60.42 408	76.73 430	46.79 358	93.45 321	64.58 341	51.00 453	86.37 359

wanda-best-256-512		72.42 358	69.43 368	81.37 301	75.39 451	64.24 243	91.58 231	91.09 226	66.36 362	60.64 403	76.86 426	47.20 353	93.47 318	64.80 337	50.98 454	86.40 356

FE-blended-shiyan7		72.42 358	69.43 368	81.37 301	75.39 451	64.24 243	91.58 231	91.09 226	66.36 362	60.64 403	76.86 426	47.20 353	93.47 318	64.80 337	50.98 454	86.40 356

blended_shiyan6		72.26 360	69.26 371	81.27 306	75.24 455	64.00 253	91.37 243	91.06 232	66.12 366	60.34 409	76.75 429	46.82 356	93.45 321	64.61 339	50.98 454	86.37 359

usedtu_blend_shiyan5		71.06 370	67.54 383	81.62 295	75.39 451	64.75 218	85.67 382	86.47 403	56.48 446	60.64 403	76.85 428	47.20 353	93.71 310	68.18 291	50.98 454	86.40 356

gbinet_0.2-2-1-0.02		71.92 363	68.92 374	80.91 322	75.87 449	63.30 280	91.95 205	91.40 202	65.62 373	61.57 397	77.27 420	44.71 380	92.88 341	61.00 366	50.87 458	86.54 354

pmmvs-eth3d		65.53 414	62.32 419	75.19 405	69.39 478	59.59 375	82.80 414	83.43 440	62.52 403	51.30 455	72.49 449	32.86 441	87.16 439	55.32 391	50.73 459	78.83 460

CL-MVSNet_self_test		69.92 378	68.09 381	75.41 402	73.25 463	55.90 420	90.05 304	89.90 298	69.96 318	61.96 396	76.54 431	51.05 310	87.64 431	49.51 416	50.59 460	82.70 422

PM-MVS		59.40 441	56.59 443	67.84 453	63.63 488	41.86 484	76.76 455	63.22 495	59.01 431	51.07 456	72.27 454	11.72 496	83.25 465	61.34 363	50.28 461	78.39 465

MDA-MVSNet_test_wron		63.78 423	60.16 427	74.64 412	78.15 432	60.41 359	83.49 402	84.03 432	56.17 449	39.17 490	71.59 458	37.22 420	83.24 466	42.87 450	48.73 462	80.26 448

YYNet1		63.76 424	60.14 428	74.62 413	78.06 433	60.19 366	83.46 404	83.99 436	56.18 448	39.25 489	71.56 459	37.18 421	83.34 464	42.90 449	48.70 463	80.32 447

KD-MVS_self_test		60.87 435	58.60 433	67.68 455	66.13 485	39.93 492	75.63 463	84.70 426	57.32 440	49.57 462	68.45 468	29.55 456	82.87 467	48.09 423	47.94 464	80.25 449

dtuonlycased		63.47 425	62.08 421	67.64 456	73.22 464	52.55 435	86.25 379	79.10 457	65.40 374	49.47 464	67.33 473	36.80 426	82.37 472	53.47 401	47.68 465	68.01 486

FE-MVSNET		60.52 437	57.18 441	70.53 443	67.53 481	50.68 448	82.62 416	76.28 462	59.33 430	46.71 471	71.10 462	30.54 454	83.61 461	33.15 481	47.37 466	77.29 471

SixPastTwentyTwo		64.92 415	61.78 423	74.34 417	78.74 423	49.76 453	83.42 405	79.51 456	62.86 399	50.27 459	77.35 417	30.92 453	90.49 398	45.89 437	47.06 467	82.78 417

sc_t1		63.81 422	59.39 431	77.10 388	77.62 436	56.03 418	84.32 394	73.56 474	46.66 476	58.22 422	73.06 447	23.28 475	90.62 395	50.93 408	46.84 468	84.64 397

tt0320		61.85 429	57.45 438	75.03 407	77.49 437	57.60 400	82.74 415	73.65 473	43.65 486	53.65 443	68.18 469	25.47 468	88.66 416	45.56 439	46.68 469	78.81 461

new_pmnet		49.31 454	46.44 457	57.93 469	62.84 490	40.74 488	68.47 478	62.96 496	36.48 492	35.09 493	57.81 491	14.97 491	72.18 491	32.86 484	46.44 470	60.88 494

usedtu_dtu_shiyan2		57.76 444	53.69 450	69.95 446	57.60 498	41.80 485	83.50 401	83.67 438	45.26 479	43.79 483	62.82 482	17.63 486	85.93 444	42.56 453	46.40 471	82.12 430

EGC-MVSNET		42.35 460	38.09 463	55.11 473	74.57 458	46.62 472	71.63 471	55.77 499	0.04 552	0.24 553	62.70 483	14.24 493	74.91 488	17.59 504	46.06 472	43.80 500

TransMVSNet (Re)		70.07 377	67.66 382	77.31 386	80.62 396	59.13 384	91.78 217	84.94 425	65.97 368	60.08 412	80.44 389	50.78 311	91.87 375	48.84 419	45.46 473	80.94 439

ambc				69.61 447	61.38 494	41.35 487	49.07 503	85.86 416		50.18 461	66.40 474	10.16 498	88.14 425	45.73 438	44.20 474	79.32 455

TDRefinement		55.28 448	51.58 452	66.39 460	59.53 496	46.15 474	76.23 458	72.80 475	44.60 481	42.49 486	76.28 435	15.29 490	82.39 471	33.20 480	43.75 475	70.62 484

Gipuma		34.91 467	31.44 470	45.30 484	70.99 471	39.64 494	19.85 515	72.56 477	20.10 505	16.16 511	21.47 523	5.08 507	71.16 492	13.07 511	43.70 476	25.08 517
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		46.58 456	43.45 460	55.96 471	45.18 507	32.05 502	61.18 489	49.49 506	33.39 494	42.05 487	62.48 484	7.00 503	65.56 501	47.08 432	43.21 477	70.27 485

tt0320-xc		61.51 433	56.89 442	75.37 403	78.50 427	58.61 389	82.61 417	71.27 483	44.31 483	53.17 445	68.03 471	23.38 473	88.46 421	47.77 428	43.00 478	79.03 458

MDA-MVSNet-bldmvs		61.54 432	57.70 436	73.05 426	79.53 410	57.00 412	83.08 410	81.23 447	57.57 436	34.91 494	72.45 450	32.79 442	86.26 443	35.81 471	41.95 479	75.89 474

new-patchmatchnet		59.30 442	56.48 444	67.79 454	65.86 486	44.19 479	82.47 418	81.77 446	59.94 426	43.65 484	66.20 475	27.67 463	81.68 476	39.34 463	41.40 480	77.50 470

UnsupCasMVSNet_eth		65.79 411	63.10 413	73.88 420	70.71 472	50.29 452	81.09 430	89.88 299	72.58 249	49.25 465	74.77 444	32.57 444	87.43 437	55.96 389	41.04 481	83.90 402

test_vis3_rt		40.46 463	37.79 464	48.47 482	44.49 508	33.35 501	66.56 484	32.84 515	32.39 495	29.65 496	39.13 511	3.91 512	68.65 495	50.17 411	40.99 482	43.40 501

pmmvs3		55.51 447	51.50 453	67.53 457	57.90 497	50.93 447	80.37 435	73.66 472	40.63 491	44.15 482	64.75 478	16.30 487	78.97 483	44.77 444	40.98 483	72.69 480

APD_test1		40.50 462	37.31 465	50.09 480	51.88 501	35.27 499	59.45 493	52.59 503	21.64 503	26.12 501	57.80 492	4.56 508	66.56 499	22.64 498	39.09 484	48.43 499

mvs5depth		61.03 434	57.65 437	71.18 440	67.16 483	47.04 471	72.74 467	77.49 459	57.47 439	60.52 406	72.53 448	22.84 476	88.38 422	49.15 417	38.94 485	78.11 467

UnsupCasMVSNet_bld		61.60 431	57.71 435	73.29 425	68.73 479	51.64 440	78.61 447	89.05 341	57.20 441	46.11 472	61.96 485	28.70 460	88.60 418	50.08 413	38.90 486	79.63 452

PMVS	26.43 22	31.84 472	28.16 475	42.89 487	25.87 520	27.58 508	50.92 502	49.78 505	21.37 504	14.17 513	40.81 508	2.01 515	66.62 498	9.61 517	38.88 487	34.49 509
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
K. test v3		63.09 426	59.61 430	73.53 423	76.26 445	49.38 458	83.27 406	77.15 461	64.35 382	47.77 470	72.32 453	28.73 459	87.79 429	49.93 414	36.69 488	83.41 410

mmtdpeth		68.33 393	66.37 389	74.21 419	82.81 372	51.73 439	84.34 393	80.42 452	67.01 358	71.56 283	68.58 467	30.52 455	92.35 364	75.89 214	36.21 489	78.56 464

kuosan		60.86 436	60.24 426	62.71 466	81.57 384	46.43 473	75.70 462	85.88 414	57.98 435	48.95 466	69.53 465	58.42 210	76.53 484	28.25 493	35.87 490	65.15 491

KD-MVS_2432*1600		69.03 386	66.37 389	77.01 390	85.56 320	61.06 340	81.44 427	90.25 282	67.27 354	58.00 426	76.53 432	54.49 266	87.63 432	48.04 424	35.77 491	82.34 426

miper_refine_blended		69.03 386	66.37 389	77.01 390	85.56 320	61.06 340	81.44 427	90.25 282	67.27 354	58.00 426	76.53 432	54.49 266	87.63 432	48.04 424	35.77 491	82.34 426

mvsany_test3		48.86 455	46.35 458	56.41 470	46.00 506	31.67 503	62.26 488	47.25 508	43.71 485	45.54 477	68.15 470	10.84 497	64.44 505	57.95 380	35.44 493	73.13 479

LCM-MVSNet		40.54 461	35.79 466	54.76 475	36.92 514	30.81 504	51.41 500	69.02 486	22.07 502	24.63 502	45.37 499	4.56 508	65.81 500	33.67 478	34.50 494	67.67 487

test_method		38.59 465	35.16 468	48.89 481	54.33 499	21.35 515	45.32 505	53.71 502	7.41 517	28.74 498	51.62 494	8.70 501	52.87 508	33.73 477	32.89 495	72.47 481

lessismore_v0				73.72 422	72.93 466	47.83 464		61.72 497		45.86 475	73.76 445	28.63 461	89.81 410	47.75 430	31.37 496	83.53 406

testf1		32.77 470	29.47 472	42.67 488	41.89 510	30.81 504	52.07 498	43.45 509	15.45 506	18.52 506	44.82 500	2.12 513	58.38 506	16.05 507	30.87 497	38.83 504

APD_test2		32.77 470	29.47 472	42.67 488	41.89 510	30.81 504	52.07 498	43.45 509	15.45 506	18.52 506	44.82 500	2.12 513	58.38 506	16.05 507	30.87 497	38.83 504

ttmdpeth		53.34 451	49.96 454	63.45 464	62.07 493	40.04 490	72.06 468	65.64 492	42.54 489	51.88 450	77.79 414	13.94 495	76.48 485	32.93 483	30.82 499	73.84 477

PVSNet_0	68.08 15	71.81 364	68.32 380	82.27 275	84.68 338	62.31 309	88.68 341	90.31 278	75.84 184	57.93 428	80.65 387	37.85 415	94.19 285	69.94 273	29.05 500	90.31 290

dongtai		55.18 449	55.46 447	54.34 476	76.03 448	36.88 496	76.07 459	84.61 428	51.28 460	43.41 485	64.61 479	56.56 241	67.81 497	18.09 503	28.50 501	58.32 495

MVStest1		51.35 452	46.89 456	64.74 461	65.06 487	51.10 445	67.33 482	72.58 476	30.20 497	35.30 492	74.82 442	27.70 462	69.89 494	24.44 496	24.57 502	73.22 478

WB-MVS		46.23 457	44.94 459	50.11 479	62.13 492	21.23 516	76.48 457	55.49 500	45.89 477	35.78 491	61.44 487	35.54 430	72.83 490	9.96 516	21.75 503	56.27 497

SSC-MVS		44.51 459	43.35 461	47.99 483	61.01 495	18.90 518	74.12 465	54.36 501	43.42 487	34.10 495	60.02 490	34.42 435	70.39 493	9.14 518	19.57 504	54.68 498

DeepMVS_CX				34.71 491	51.45 502	24.73 511		28.48 517	31.46 496	17.49 509	52.75 493	5.80 506	42.60 514	18.18 502	19.42 505	36.81 507

PMMVS2		37.93 466	33.61 469	50.92 478	46.31 505	24.76 510	60.55 492	50.05 504	28.94 499	20.93 503	47.59 495	4.41 510	65.13 502	25.14 495	18.55 506	62.87 492

MVE	24.84 23	24.35 474	19.77 480	38.09 490	34.56 517	26.92 509	26.57 508	38.87 513	11.73 513	11.37 517	27.44 517	1.37 518	50.42 509	11.41 515	14.60 507	36.93 506
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ArgMatch-SfM		33.21 468	29.25 474	45.06 485	35.86 515	22.89 513	48.07 504	16.80 518	23.93 501	27.57 499	61.10 489	1.59 517	47.14 510	34.29 475	14.08 508	65.16 490

ArgMatch-Sym		33.10 469	29.80 471	43.01 486	37.34 513	24.00 512	51.27 501	13.51 519	26.37 500	28.91 497	61.40 488	1.65 516	43.37 513	34.16 476	13.61 509	61.66 493

LoFTR		18.06 480	15.31 484	26.33 494	21.95 521	10.94 524	21.35 513	12.80 520	6.90 518	12.24 515	41.28 506	0.46 523	27.67 517	7.81 520	12.96 510	40.38 503

VLMVS		13.23 485	13.55 486	12.28 506	12.68 527	2.77 538	12.60 518	3.80 526	0.44 534	17.98 508	44.70 502	4.14 511	6.39 528	12.99 512	12.66 511	27.68 513

MatchFormer		14.02 483	12.22 487	19.42 499	17.64 524	8.79 527	19.96 514	10.04 521	4.23 519	10.54 520	32.75 515	0.31 530	22.88 520	4.03 527	10.48 512	26.57 514

E-PMN		24.61 473	24.00 477	26.45 493	43.74 509	18.44 519	60.86 490	39.66 511	15.11 509	9.53 521	22.10 522	6.52 505	46.94 511	8.31 519	10.14 513	13.98 521

EMVS		23.76 475	23.20 479	25.46 496	41.52 512	16.90 520	60.56 491	38.79 514	14.62 510	8.99 523	20.24 525	7.35 502	45.82 512	7.25 522	9.46 514	13.64 522

tmp_tt		22.26 476	23.75 478	17.80 500	5.23 539	12.06 523	35.26 506	39.48 512	2.82 523	18.94 504	44.20 504	22.23 478	24.64 518	36.30 468	9.31 515	16.69 520

ANet_high		40.27 464	35.20 467	55.47 472	34.74 516	34.47 500	63.84 487	71.56 481	48.42 470	18.80 505	41.08 507	9.52 500	64.45 504	20.18 500	8.66 516	67.49 488

wuyk23d		11.30 487	10.95 490	12.33 505	48.05 504	19.89 517	25.89 510	1.92 535	3.58 520	3.12 528	1.37 551	0.64 520	15.77 524	6.23 524	7.77 517	1.35 535

DenseAffine		21.45 477	18.65 481	29.86 492	28.31 518	16.04 521	32.25 507	6.12 522	15.38 508	16.38 510	44.57 503	0.55 521	32.44 515	16.82 505	7.46 518	41.09 502

RoMa-SfM		18.71 479	16.37 482	25.74 495	19.88 522	12.86 522	26.27 509	3.78 527	13.07 511	15.56 512	45.71 498	0.48 522	28.39 516	16.22 506	6.37 519	35.97 508

MASt3R-SfM		8.20 491	8.57 494	7.11 509	5.75 536	3.12 537	9.54 520	3.21 528	2.39 526	9.18 522	34.80 514	0.37 525	5.21 530	6.46 523	5.41 520	12.99 524

DKM		16.33 482	14.55 485	21.65 498	19.49 523	10.79 525	24.23 511	2.86 529	10.86 514	13.52 514	40.31 509	0.32 528	21.73 521	14.27 510	5.12 521	32.43 510

ALIKED-LG		4.67 496	4.76 500	4.39 510	11.74 528	4.58 532	8.52 521	2.37 530	1.12 527	3.02 529	10.43 526	0.40 524	4.25 531	0.52 536	4.70 522	4.35 525

PDCNetPlus		17.19 481	15.58 483	22.00 497	25.94 519	10.36 526	23.05 512	5.04 524	12.02 512	10.87 519	39.50 510	0.88 519	23.24 519	18.38 501	4.57 523	32.39 511

ALIKED-NN		4.04 499	4.13 502	3.78 512	10.26 530	4.26 533	7.33 524	1.98 534	0.76 529	2.52 531	9.08 529	0.32 528	3.67 533	0.44 538	4.45 524	3.40 532

ALIKED-MNN		4.24 498	4.26 501	4.20 511	10.96 529	4.68 531	7.92 522	2.00 532	0.81 528	2.44 534	9.09 528	0.30 531	4.03 532	0.46 537	4.36 525	3.88 528

RoMa-HiRes		13.29 484	12.09 488	16.86 501	12.76 526	7.74 528	17.91 517	2.10 531	8.64 515	11.87 516	39.11 512	0.36 526	17.55 522	12.17 513	3.91 526	25.30 516

DKM-HiRes		12.72 486	11.70 489	15.79 503	14.70 525	7.68 529	18.04 516	1.85 536	8.12 516	11.31 518	35.19 513	0.24 536	14.23 526	12.15 514	3.71 527	25.48 515

XFeat-MNN		2.31 500	2.37 503	2.13 513	1.47 556	0.97 552	3.08 532	1.31 537	0.53 531	2.60 530	7.72 530	0.22 538	2.31 534	1.02 530	3.40 528	3.10 533

XFeat-NN		1.98 506	2.09 509	1.67 519	1.35 557	0.77 557	2.62 533	0.97 543	0.41 536	2.46 533	6.79 532	0.19 539	1.75 535	0.84 531	3.18 529	2.48 534

ELoFTR		8.49 489	6.65 496	14.00 504	5.91 533	3.43 536	7.42 523	4.01 525	2.94 522	6.41 526	25.06 518	0.11 540	15.41 525	5.10 526	2.92 530	23.17 518

SP-DiffGlue		2.24 501	2.34 504	1.94 517	1.88 555	1.08 546	3.10 531	1.13 539	0.55 530	2.52 531	7.60 531	0.33 527	0.99 540	1.25 529	2.70 531	3.76 530

SP-LightGlue		2.23 502	2.31 505	1.99 514	5.90 534	1.01 548	4.31 527	1.04 541	0.50 532	1.20 536	4.36 533	0.28 532	1.06 537	0.64 532	2.57 532	3.91 526

SP-SuperGlue		2.21 503	2.29 506	1.97 515	5.76 535	1.01 548	4.31 527	1.06 540	0.50 532	1.22 535	4.35 534	0.28 532	1.04 539	0.64 532	2.52 533	3.86 529

SP-MNN		2.16 504	2.22 507	1.97 515	5.52 537	0.92 553	4.28 529	1.01 542	0.41 536	1.13 537	4.35 534	0.23 537	1.09 536	0.61 534	2.45 534	3.91 526

SP-NN		2.08 505	2.16 508	1.87 518	5.30 538	0.91 554	4.18 530	0.96 544	0.43 535	1.09 538	4.20 536	0.25 534	1.06 537	0.60 535	2.38 535	3.63 531

PMatch-SfM		8.29 490	7.44 495	10.83 507	6.92 532	3.67 535	9.75 519	1.15 538	3.49 521	6.97 524	28.70 516	0.04 552	8.89 527	7.67 521	2.24 536	19.92 519

GLUNet-SfM		8.91 488	6.39 497	16.47 502	9.50 531	4.77 530	5.87 526	5.53 523	2.45 524	6.66 525	22.23 521	0.25 534	15.78 523	2.84 528	2.14 537	28.86 512

SIFT-NN		1.43 507	1.51 510	1.19 520	4.60 541	1.57 540	2.30 534	0.51 546	0.34 538	0.74 539	2.84 537	0.08 541	0.84 541	0.13 540	2.07 538	1.15 536

SIFT-NN-NCMNet		1.29 509	1.36 512	1.08 522	3.95 544	1.39 542	2.05 536	0.49 548	0.33 540	0.63 542	2.62 541	0.07 542	0.81 543	0.12 542	2.02 539	1.05 540

SIFT-MNN		1.35 508	1.42 511	1.14 521	4.26 542	1.44 541	2.10 535	0.51 546	0.34 538	0.64 540	2.76 538	0.07 542	0.83 542	0.13 540	1.98 540	1.15 536

SIFT-NCM-Cal		1.23 510	1.30 513	1.04 523	4.06 543	1.29 543	1.92 538	0.42 549	0.33 540	0.45 547	2.46 544	0.06 547	0.81 543	0.10 549	1.89 541	1.02 542

SIFT-NN-UMatch		1.16 512	1.23 515	0.96 525	3.23 550	1.06 547	1.93 537	0.42 549	0.33 540	0.53 544	2.63 539	0.07 542	0.77 545	0.11 545	1.79 542	1.05 540

SIFT-NN-CMatch		1.18 511	1.24 514	1.01 524	3.44 548	1.19 545	1.78 539	0.42 549	0.33 540	0.64 540	2.63 539	0.07 542	0.77 545	0.12 542	1.73 543	1.08 538

SIFT-NN-PointCN		1.06 515	1.12 518	0.88 527	2.98 551	0.84 556	1.67 541	0.37 553	0.30 548	0.54 543	2.38 545	0.07 542	0.72 549	0.11 545	1.64 544	1.07 539

SIFT-ConvMatch		1.15 513	1.22 516	0.96 525	3.82 545	1.20 544	1.64 542	0.38 552	0.33 540	0.52 545	2.53 542	0.06 547	0.76 547	0.11 545	1.59 545	0.91 543

SIFT-UMatch		1.11 514	1.18 517	0.87 528	3.66 546	1.00 551	1.70 540	0.35 554	0.32 545	0.46 546	2.50 543	0.06 547	0.75 548	0.11 545	1.51 546	0.87 545

PMatch-Up-SfM		6.11 495	5.72 499	7.28 508	5.02 540	2.48 539	7.03 525	0.71 545	2.41 525	5.37 527	23.67 519	0.03 556	5.84 529	5.77 525	1.48 547	13.50 523

SIFT-UM-Cal		1.01 517	1.09 520	0.77 530	3.43 549	0.85 555	1.49 543	0.29 557	0.31 547	0.42 549	2.34 546	0.06 547	0.69 551	0.10 549	1.37 548	0.77 548

SIFT-CM-Cal		1.03 516	1.10 519	0.85 529	3.54 547	1.01 548	1.42 544	0.32 555	0.32 545	0.44 548	2.30 547	0.06 547	0.71 550	0.09 551	1.37 548	0.82 546

SIFT-PointCN		0.88 518	0.94 521	0.69 532	2.88 553	0.61 558	1.32 545	0.30 556	0.28 549	0.36 550	1.93 549	0.04 552	0.62 552	0.09 551	1.26 550	0.82 546

SIFT-PCN-Cal		0.88 518	0.93 522	0.70 531	2.93 552	0.60 559	1.22 546	0.27 558	0.28 549	0.36 550	2.00 548	0.04 552	0.61 553	0.09 551	1.23 551	0.89 544

SIFT-NCMNet		0.73 520	0.80 523	0.54 533	2.66 554	0.54 560	1.00 547	0.16 559	0.28 549	0.32 552	1.65 550	0.04 552	0.51 554	0.07 554	0.98 552	0.58 549

testmvs		7.23 493	9.62 492	0.06 535	0.04 558	0.02 562	84.98 389	0.02 560	0.03 553	0.18 554	1.21 552	0.01 558	0.02 555	0.14 539	0.01 553	0.13 551

mmdepth		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 554	0.00 552

monomultidepth		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 554	0.00 552

test_blank		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 554	0.00 552

uanet_test		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 554	0.00 552

DCPMVS		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 554	0.00 552

cdsmvs_eth3d_5k		19.86 478	26.47 476	0.00 536	0.00 560	0.00 563	0.00 548	93.45 100	0.00 555	0.00 556	95.27 78	49.56 326	0.00 557	0.00 555	0.00 554	0.00 552

pcd_1.5k_mvsjas		4.46 497	5.95 498	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	53.55 280	0.00 557	0.00 555	0.00 554	0.00 552

sosnet-low-res		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 554	0.00 552

sosnet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 554	0.00 552

uncertanet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 554	0.00 552

Regformer		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 554	0.00 552

test123		6.92 494	9.21 493	0.08 534	0.03 559	0.05 561	81.65 425	0.01 561	0.02 554	0.14 555	0.85 553	0.03 556	0.02 555	0.12 542	0.00 554	0.16 550

ab-mvs-re		7.91 492	10.55 491	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	94.95 88	0.00 559	0.00 557	0.00 555	0.00 554	0.00 552

uanet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 554	0.00 552

PatchmatchNet2					0.00 560	56.61 414	85.20 385	78.52 458	49.54 467
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													82.83 468
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						49.45 456								31.56 490

FOURS1					93.95 52	61.77 322	93.96 91	91.92 173	62.14 407	86.57 64

test_one_0601					96.32 20	69.74 53		94.18 70	71.42 292	90.67 29	96.85 28	74.45 22

eth-test2					0.00 560

eth-test					0.00 560

test_241102_ONE					96.45 13	69.38 62		94.44 56	71.65 281	92.11 10	97.05 13	76.79 10	99.11 7

save fliter					93.84 55	67.89 116	95.05 41	92.66 138	78.19 136

test0726					96.40 16	69.99 41	96.76 8	94.33 67	71.92 267	91.89 15	97.11 12	73.77 25

GSMVS																94.68 128

test_part2					96.29 21	68.16 109				90.78 27

sam_mvs1												57.85 221				94.68 128

sam_mvs												54.91 261

MTGPA								92.23 154

test_post1							78.95 445				20.70 524	53.05 285	91.50 390	60.43 369

test_post											23.01 520	56.49 242	92.67 350

patchmatchnet-post											67.62 472	57.62 224	90.25 400

MTMP							93.77 106	32.52 516

gm-plane-assit					88.42 222	67.04 148			78.62 129		91.83 185		97.37 85	76.57 208

TEST9					94.18 47	67.28 136	94.16 78	93.51 96	71.75 278	85.52 77	95.33 72	68.01 63	97.27 95

test_8					94.19 46	67.19 141	94.15 80	93.42 103	71.87 272	85.38 80	95.35 71	68.19 61	96.95 122

agg_prior					94.16 49	66.97 157		93.31 106		84.49 88			96.75 134

test_prior4						67.18 143	93.92 95

test_prior				86.42 101	94.71 41	67.35 135		93.10 117					96.84 131			95.05 100

旧先验2							92.00 202		59.37 429	87.54 57			93.47 318	75.39 218

新几何2							91.41 236

无先验							92.71 156	92.61 143	62.03 408				97.01 112	66.63 313		93.97 181

原ACMM2							92.01 199

testdata2													96.09 167	61.26 364

segment_acmp												65.94 82

testdata1							89.21 329		77.55 153

plane_prior7					86.94 279	61.51 330

plane_prior6					87.23 262	62.32 308						50.66 312

plane_prior4											89.14 257

plane_prior3						61.95 317			79.09 118	72.53 265

plane_prior2							93.13 134		78.81 125

plane_prior1					87.15 267

n2								0.00 562

nn								0.00 562

door-mid								66.01 491

test11								93.01 120

door								66.57 490

HQP5-MVS						63.66 270

HQP-NCC					87.54 254		94.06 83		79.80 92	74.18 238

ACMP_Plane					87.54 254		94.06 83		79.80 92	74.18 238

BP-MVS														77.63 201

HQP4-MVS										74.18 238			95.61 210			88.63 312

HQP2-MVS												51.63 300

NP-MVS					87.41 257	63.04 288					90.30 225

MDTV_nov1_ep13_2view						59.90 371	80.13 440		67.65 351	72.79 259		54.33 271		59.83 373		92.58 235

Test By Simon												54.21 274

High-resolution multi-view benchmark