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	85.88 121	92.83 89	64.03 254	93.06 138	94.33 68	82.19 47	93.65 4	96.15 52	85.89 1	97.19 101	91.02 54	97.75 1	96.43 33
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DVP-MVS++		90.53 4	91.09 5	88.87 17	97.31 4	69.91 48	93.96 92	94.37 66	72.48 254	92.07 13	96.85 29	83.82 2	99.15 3	91.53 50	97.42 4	97.55 5

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

PC_three_1452									80.91 68	94.07 3	96.83 31	83.57 4	99.12 6	95.70 10	97.42 4	97.55 5

TestfortrainingZip				90.29 2	97.24 8	73.67 10	94.47 65	95.75 10	69.78 325	95.97 1	98.23 1	80.55 5	99.42 1		93.26 58	97.76 2

DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 175	76.68 2	97.29 1	95.35 18	82.87 39	91.58 20	97.22 10	79.93 6	99.10 10	83.12 138	97.64 2	97.94 1

baseline2		83.68 140	83.42 127	84.48 199	87.37 262	66.00 188	90.06 306	95.93 8	79.71 98	69.08 315	90.39 225	77.92 7	96.28 158	78.91 195	81.38 237	91.16 280

GG-mvs-BLEND				86.53 98	91.91 123	69.67 59	75.02 467	94.75 41		78.67 184	90.85 217	77.91 8	94.56 269	72.25 253	93.74 49	95.36 79

gg-mvs-nofinetune		77.18 287	74.31 309	85.80 126	91.42 137	68.36 103	71.78 472	94.72 42	49.61 469	77.12 204	45.92 500	77.41 9	93.98 302	67.62 305	93.16 60	95.05 103

SED-MVS		89.94 9	90.36 10	88.70 19	96.45 13	69.38 66	96.89 6	94.44 57	71.65 284	92.11 11	97.21 11	76.79 10	99.11 7	92.34 38	95.36 14	97.62 3

test_241102_ONE					96.45 13	69.38 66		94.44 57	71.65 284	92.11 11	97.05 14	76.79 10	99.11 7

MED-MVS		89.02 18	89.57 16	87.38 50	94.76 36	67.28 140	94.47 65	94.87 34	70.68 311	91.27 25	96.93 21	76.77 12	98.98 17	91.55 46	94.82 26	95.88 56

test_0728_THIRD									72.48 254	90.55 31	96.93 21	76.24 13	99.08 12	91.53 50	94.99 18	96.43 33

DPE-MVS		88.77 19	89.21 20	87.45 48	96.26 22	67.56 131	94.17 78	94.15 73	68.77 340	90.74 29	97.27 8	76.09 14	98.49 35	90.58 58	94.91 21	96.30 37
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + GP.		87.96 28	88.37 30	86.70 79	93.51 68	65.32 208	95.15 38	93.84 80	78.17 139	85.93 74	94.80 97	75.80 15	98.21 42	89.38 61	88.78 128	96.59 21

fmvsm_l_mol_unc0.5_1		89.65 12	90.28 11	87.77 37	87.88 247	70.89 32	96.35 16	88.48 369	86.59 9	93.16 5	97.86 2	75.47 16	97.28 95	94.09 22	92.60 67	95.16 96

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 183	93.00 85	58.16 397	96.72 9	94.41 62	86.50 10	90.25 35	97.83 3	75.46 17	98.67 31	92.78 34	95.49 13	97.32 7

BP-MVS1		86.54 59	86.68 59	86.13 114	87.80 252	67.18 147	92.97 143	95.62 11	79.92 91	82.84 108	94.14 121	74.95 18	96.46 150	82.91 142	88.96 126	94.74 124

dcpmvs_2		87.37 42	87.55 43	86.85 67	95.04 35	68.20 112	90.36 297	90.66 262	79.37 113	81.20 126	93.67 133	74.73 19	96.55 144	90.88 55	92.00 78	95.82 59

MVSTER		82.47 171	82.05 165	83.74 227	92.68 96	69.01 83	91.90 212	93.21 111	79.83 93	72.14 278	85.71 319	74.72 20	94.72 255	75.72 218	72.49 322	87.50 332

test_241102_TWO								94.41 62	71.65 284	92.07 13	97.21 11	74.58 21	99.11 7	92.34 38	95.36 14	96.59 21

WBMVS		81.67 187	80.98 187	83.72 231	93.07 82	69.40 64	94.33 74	93.05 121	76.84 170	72.05 280	84.14 339	74.49 22	93.88 307	72.76 246	68.09 353	87.88 327

test_one_0601					96.32 20	69.74 56		94.18 71	71.42 295	90.67 30	96.85 29	74.45 23

DELS-MVS		90.05 8	90.09 12	89.94 5	93.14 78	73.88 9	97.01 4	94.40 64	88.32 3	85.71 76	94.91 94	74.11 24	98.91 22	87.26 83	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
patch_mono-2		89.71 11	90.99 6	85.85 124	96.04 26	63.70 271	95.04 44	95.19 24	86.74 8	91.53 22	95.15 86	73.86 25	97.58 71	93.38 28	92.00 78	96.28 40

DVP-MVS		89.41 14	89.73 15	88.45 27	96.40 16	69.99 44	96.64 10	94.52 53	71.92 270	90.55 31	96.93 21	73.77 26	99.08 12	91.91 44	94.90 22	96.29 38
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					96.40 16	69.99 44	96.76 8	94.33 68	71.92 270	91.89 16	97.11 13	73.77 26

ET-MVSNet_ETH3D		84.01 127	83.15 141	86.58 88	90.78 155	70.89 32	94.74 57	94.62 49	81.44 58	58.19 426	93.64 134	73.64 28	92.35 366	82.66 145	78.66 273	96.50 29

UBG		86.83 52	86.70 57	87.20 57	93.07 82	69.81 52	93.43 126	95.56 14	81.52 54	81.50 121	92.12 171	73.58 29	96.28 158	84.37 121	85.20 176	95.51 71

testing3-2		83.11 158	83.15 141	82.98 257	91.92 121	64.01 256	94.39 73	95.37 17	78.32 136	75.53 223	90.06 244	73.18 30	93.18 330	74.34 232	75.27 301	91.77 264

CSCG		86.87 49	86.26 65	88.72 18	95.05 34	70.79 34	93.83 105	95.33 19	68.48 344	77.63 194	94.35 112	73.04 31	98.45 36	84.92 111	93.71 51	96.92 15

tttt0517		79.50 236	78.53 237	82.41 274	87.22 266	61.43 338	89.75 315	94.76 40	69.29 330	67.91 336	88.06 282	72.92 32	95.63 209	62.91 357	73.90 313	90.16 294

GDP-MVS		85.54 85	85.32 85	86.18 112	87.64 255	67.95 119	92.91 150	92.36 153	77.81 147	83.69 98	94.31 115	72.84 33	96.41 152	80.39 177	85.95 165	94.19 166

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 75	96.26 48	72.84 33	99.38 2	92.64 35	95.93 9	97.08 12

thisisatest0515		83.41 150	82.49 161	86.16 113	89.46 181	68.26 107	93.54 118	94.70 44	74.31 212	75.75 216	90.92 215	72.62 35	96.52 146	69.64 277	81.50 236	93.71 196

thisisatest0530		81.15 200	80.07 203	84.39 202	88.26 231	65.63 199	91.40 241	94.62 49	71.27 298	70.93 293	89.18 258	72.47 36	96.04 174	65.62 332	76.89 292	91.49 269

myMVS_eth3d28		86.31 66	86.15 69	86.78 73	93.56 64	70.49 38	92.94 146	95.28 20	82.47 43	78.70 182	92.07 174	72.45 37	95.41 223	82.11 151	85.78 169	94.44 153

BridgeMVS		89.08 16	88.84 23	89.81 7	93.66 60	75.15 5	90.61 289	93.43 104	84.06 26	86.20 70	90.17 237	72.42 38	96.98 118	93.09 31	95.92 10	97.29 8

testing11		86.71 57	86.44 62	87.55 45	93.54 66	71.35 25	93.65 112	95.58 12	81.36 62	80.69 138	92.21 168	72.30 39	96.46 150	85.18 107	83.43 207	94.82 119

TSAR-MVS + MP.		88.11 26	88.64 26	86.54 97	91.73 128	68.04 115	90.36 297	93.55 96	82.89 37	91.29 24	92.89 149	72.27 40	96.03 175	87.99 73	94.77 28	95.54 70
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EPP-MVSNet		81.79 186	81.52 174	82.61 267	88.77 204	60.21 369	93.02 142	93.66 91	68.52 343	72.90 262	90.39 225	72.19 41	94.96 244	74.93 226	79.29 266	92.67 232

CostFormer		82.33 173	81.15 180	85.86 123	89.01 198	68.46 101	82.39 423	93.01 123	75.59 190	80.25 149	81.57 373	72.03 42	94.96 244	79.06 192	77.48 285	94.16 169

test-260524					95.84 30	67.84 121		94.64 47		89.45 44		71.94 43	98.96 19	91.55 46	94.82 26

HPM-MVS++		89.37 15	89.95 14	87.64 39	95.10 33	68.23 110	95.24 35	94.49 55	82.43 44	88.90 47	96.35 43	71.89 44	98.63 32	88.76 68	96.40 6	96.06 45

testing99		86.01 73	85.47 82	87.63 43	93.62 61	71.25 27	93.47 124	95.23 23	80.42 78	80.60 140	91.95 183	71.73 45	96.50 148	80.02 180	82.22 224	95.13 98

MVSMamba_PlusPlus		84.97 97	83.65 117	88.93 15	90.17 166	74.04 8	87.84 360	92.69 139	62.18 408	81.47 123	87.64 288	71.47 46	96.28 158	84.69 113	94.74 33	96.47 30

CNVR-MVS		90.32 6	90.89 8	88.61 24	96.76 9	70.65 35	96.47 14	94.83 37	84.83 19	89.07 45	96.80 32	70.86 47	99.06 16	92.64 35	95.71 11	96.12 44

IB-MVS	77.80 4	82.18 177	80.46 200	87.35 52	89.14 193	70.28 41	95.59 28	95.17 26	78.85 125	70.19 303	85.82 316	70.66 48	97.67 63	72.19 256	66.52 367	94.09 176
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
testing91		85.93 75	85.31 86	87.78 36	93.59 63	71.47 22	93.50 121	95.08 30	80.26 83	80.53 144	91.93 184	70.43 49	96.51 147	80.32 178	82.13 227	95.37 77

ETVMVS		84.22 121	83.71 115	85.76 128	92.58 99	68.25 109	92.45 181	95.53 16	79.54 107	79.46 165	91.64 197	70.29 50	94.18 288	69.16 285	82.76 216	94.84 115

aaEdge-Enhanced		88.25 20	88.55 27	87.33 54	96.33 19	67.28 140	93.93 94	94.81 38	70.09 319	88.91 46	96.95 19	70.12 51	98.73 30	91.55 46	94.28 39	95.99 50

MM		90.87 2	91.52 2	88.92 16	92.12 110	71.10 31	97.02 3	96.04 6	88.70 2	91.57 21	96.19 50	70.12 51	98.91 22	96.83 2	95.06 17	96.76 17

fmvsm_l_conf0.5_n		87.49 39	88.19 34	85.39 142	86.95 281	64.37 240	94.30 75	88.45 370	80.51 74	92.70 6	96.86 27	69.98 53	97.15 106	95.83 7	88.08 136	94.65 134

baseline1		81.84 185	81.03 185	84.28 208	91.60 131	66.62 171	91.08 264	91.66 195	81.87 50	74.86 234	91.67 195	69.98 53	94.92 247	71.76 259	64.75 384	91.29 278

fmvsm_l_conf0.5_n_a		87.44 41	88.15 35	85.30 150	87.10 273	64.19 249	94.41 70	88.14 381	80.24 86	92.54 7	96.97 18	69.52 55	97.17 102	95.89 6	88.51 131	94.56 138

fmvsm_s_conf0.5_n_9		88.14 23	89.21 20	84.92 166	89.29 186	61.41 339	92.97 143	88.36 372	86.96 6	91.49 23	97.49 5	69.48 56	97.46 78	97.00 1	89.88 115	95.89 55

TestfortrainingZip a		86.96 47	86.88 54	87.23 55	94.76 36	67.02 154	94.47 65	94.08 76	70.68 311	88.57 49	96.93 21	69.03 57	98.78 27	84.41 120	88.95 127	95.88 56

testing222		85.18 91	84.69 99	86.63 84	92.91 87	69.91 48	92.61 169	95.80 9	80.31 82	80.38 146	92.27 164	68.73 58	95.19 237	75.94 216	83.27 210	94.81 121

alignmvs		87.28 43	86.97 50	88.24 30	91.30 142	71.14 30	95.61 27	93.56 95	79.30 114	87.07 62	95.25 81	68.43 59	96.93 126	87.87 74	84.33 189	96.65 19

PAPM		85.89 77	85.46 83	87.18 58	88.20 235	72.42 18	92.41 183	92.77 134	82.11 48	80.34 148	93.07 144	68.27 60	95.02 240	78.39 200	93.59 53	94.09 176

fmvsm_s_conf0.5_n_11		87.99 27	89.25 19	84.23 211	89.07 194	61.60 332	94.87 52	89.06 342	85.65 12	91.09 27	97.41 6	68.26 61	97.43 82	95.07 13	92.74 65	93.66 198

train_agg		87.21 44	87.42 45	86.60 85	94.18 47	67.28 140	94.16 79	93.51 98	71.87 275	85.52 79	95.33 73	68.19 62	97.27 96	89.09 65	94.90 22	95.25 93

test_8					94.19 46	67.19 145	94.15 81	93.42 105	71.87 275	85.38 82	95.35 72	68.19 62	96.95 123

TEST9					94.18 47	67.28 140	94.16 79	93.51 98	71.75 281	85.52 79	95.33 73	68.01 64	97.27 96

test_prior2							95.10 40		75.40 195	85.25 85	95.61 64	67.94 65		87.47 80	94.77 28

WTY-MVS		86.32 64	85.81 76	87.85 33	92.82 91	69.37 68	95.20 36	95.25 22	82.71 40	81.91 117	94.73 98	67.93 66	97.63 68	79.55 184	82.25 223	96.54 24

FBQ-MVS		86.03 72	85.15 89	88.66 21	93.10 80	73.31 13	92.70 160	95.27 21	81.43 59	82.52 114	91.06 214	67.89 67	96.56 142	79.87 181	82.51 217	96.13 43

APDe-MVS		87.54 36	87.84 38	86.65 82	96.07 25	66.30 179	94.84 54	93.78 81	69.35 329	88.39 50	96.34 44	67.74 68	97.66 66	90.62 57	93.44 55	96.01 48
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsm_n_1920		87.69 35	88.50 28	85.27 153	87.05 275	63.55 278	93.69 110	91.08 233	84.18 25	90.17 37	97.04 16	67.58 69	97.99 48	95.72 8	90.03 112	94.26 162

fmvsm_l_conf0.5_n_9		88.24 22	89.36 18	84.85 171	88.15 236	61.94 322	95.65 26	89.70 312	85.54 13	92.07 13	97.33 7	67.51 70	97.27 96	96.23 5	92.07 77	95.35 80

tpm2		79.80 232	77.95 247	85.34 148	88.28 230	68.26 107	81.56 429	91.42 204	70.11 318	77.59 196	80.50 391	67.40 71	94.26 286	67.34 309	77.35 286	93.51 204

miper_enhance_ethall		78.86 253	77.97 245	81.54 302	88.00 242	65.17 212	91.41 239	89.15 333	75.19 199	68.79 323	83.98 342	67.17 72	92.82 344	72.73 247	65.30 374	86.62 355

SF-MVS		87.03 46	87.09 48	86.84 68	92.70 95	67.45 137	93.64 113	93.76 84	70.78 309	86.25 68	96.44 40	66.98 73	97.79 57	88.68 69	94.56 36	95.28 88

HY-MVS	76.49 5	84.28 117	83.36 130	87.02 64	92.22 105	67.74 126	84.65 393	94.50 54	79.15 118	82.23 115	87.93 283	66.88 74	96.94 124	80.53 175	82.20 225	96.39 35

EPNet		87.84 33	88.38 29	86.23 111	93.30 72	66.05 185	95.26 34	94.84 36	87.09 5	88.06 51	94.53 103	66.79 75	97.34 88	83.89 127	91.68 84	95.29 86
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
nomal-1		82.17 178	81.45 176	84.34 205	90.99 148	69.47 62	83.86 401	93.64 92	77.94 144	73.62 255	85.72 318	66.65 76	91.90 377	80.76 173	79.90 254	91.64 266

9.14			87.63 40		93.86 54		94.41 70	94.18 71	72.76 249	86.21 69	96.51 38	66.64 77	97.88 54	90.08 59	94.04 43

FIs		79.47 238	79.41 221	79.67 357	85.95 312	59.40 382	91.68 231	93.94 78	78.06 141	68.96 320	88.28 273	66.61 78	91.77 381	66.20 324	74.99 302	87.82 328

NCCC		89.07 17	89.46 17	87.91 32	96.60 11	69.05 82	96.38 15	94.64 47	84.42 23	86.74 65	96.20 49	66.56 79	98.76 29	89.03 67	94.56 36	95.92 53

MGCNet		90.32 6	90.90 7	88.55 25	94.05 51	70.23 42	97.00 5	93.73 88	87.30 4	92.15 10	96.15 52	66.38 80	98.94 21	96.71 3	94.67 35	96.47 30

reproduce_monomvs		79.49 237	79.11 231	80.64 330	92.91 87	61.47 337	91.17 262	93.28 109	83.09 35	64.04 378	82.38 359	66.19 81	94.57 266	81.19 168	57.71 435	85.88 380

SD-MVS		87.49 39	87.49 44	87.50 47	93.60 62	68.82 89	93.90 97	92.63 145	76.86 169	87.90 53	95.76 60	66.17 82	97.63 68	89.06 66	91.48 88	96.05 46
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
UniMVSNet_NR-MVSNet		78.15 268	77.55 255	79.98 347	84.46 350	60.26 367	92.25 187	93.20 113	77.50 157	68.88 321	86.61 304	66.10 83	92.13 372	66.38 321	62.55 404	87.54 331

CHOSEN 280x420		77.35 285	76.95 269	78.55 373	87.07 274	62.68 304	69.71 478	82.95 447	68.80 339	71.48 289	87.27 296	66.03 84	84.00 460	76.47 212	82.81 214	88.95 310

CANet		89.61 13	89.99 13	88.46 26	94.39 45	69.71 57	96.53 13	93.78 81	86.89 7	89.68 41	95.78 59	65.94 85	99.10 10	92.99 32	93.91 46	96.58 23

segment_acmp												65.94 85

fmvsm_s_conf0.5_n_3		86.88 48	87.99 37	83.58 237	87.26 264	60.74 353	93.21 135	87.94 388	84.22 24	91.70 18	97.27 8	65.91 87	95.02 240	93.95 25	90.42 106	94.99 106

Vis-MVSNet (Re-imp)		79.24 244	79.57 214	78.24 378	88.46 221	52.29 441	90.41 294	89.12 337	74.24 214	69.13 313	91.91 185	65.77 88	90.09 410	59.00 381	88.09 135	92.33 245

FC-MVSNet-test		77.99 272	78.08 243	77.70 381	84.89 340	55.51 426	90.27 300	93.75 87	76.87 168	66.80 356	87.59 289	65.71 89	90.23 407	62.89 358	73.94 311	87.37 336

SMA-MVS		88.14 23	88.29 32	87.67 38	93.21 75	68.72 94	93.85 100	94.03 77	74.18 215	91.74 17	96.67 35	65.61 90	98.42 39	89.24 64	96.08 7	95.88 56
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
test12				87.09 61	94.60 42	68.86 86		92.91 129		82.67 113		65.44 91	97.55 74		93.69 52	94.84 115

fmvsm_l_conf0.5_n_3		87.54 36	88.29 32	85.30 150	86.92 286	62.63 305	95.02 46	90.28 283	84.95 18	90.27 34	96.86 27	65.36 92	97.52 76	94.93 15	90.03 112	95.76 61

test_fmvsmconf_n		86.58 58	87.17 47	84.82 173	85.28 330	62.55 306	94.26 77	89.78 303	83.81 29	87.78 55	96.33 45	65.33 93	96.98 118	94.40 20	87.55 142	94.95 108

旧先验1					91.94 119	60.74 353		91.50 201			94.36 108	65.23 94			91.84 81	94.55 139

1112_ss		80.56 215	79.83 210	82.77 261	88.65 206	60.78 349	92.29 186	88.36 372	72.58 252	72.46 274	94.95 90	65.09 95	93.42 325	66.38 321	77.71 278	94.10 175

MVSFormer		83.75 137	82.88 148	86.37 106	89.24 191	71.18 28	89.07 336	90.69 259	65.80 373	87.13 60	94.34 113	64.99 96	92.67 352	72.83 243	91.80 82	95.27 89

lupinMVS		87.74 34	87.77 39	87.63 43	89.24 191	71.18 28	96.57 12	92.90 130	82.70 41	87.13 60	95.27 79	64.99 96	95.80 192	89.34 62	91.80 82	95.93 52

tpmrst		80.57 214	79.14 230	84.84 172	90.10 167	68.28 106	81.70 427	89.72 310	77.63 154	75.96 215	79.54 405	64.94 98	92.71 349	75.43 220	77.28 288	93.55 201

ZD-MVS					96.63 10	65.50 204		93.50 100	70.74 310	85.26 84	95.19 85	64.92 99	97.29 91	87.51 78	93.01 61

testing3		70.38 378	70.83 357	69.03 453	85.82 317	43.93 485	90.72 281	90.56 266	68.06 347	60.24 413	86.82 303	64.83 100	84.12 456	26.33 497	64.10 390	79.04 460

casdiffmvs_mvg		85.66 82	85.18 88	87.09 61	88.22 234	69.35 69	93.74 109	91.89 179	81.47 55	80.10 151	91.45 199	64.80 101	96.35 155	87.23 84	87.69 140	95.58 68
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
miper_ehance_all_eth		77.60 281	76.44 275	81.09 321	85.70 322	64.41 238	90.65 284	88.64 364	72.31 260	67.37 349	82.52 357	64.77 102	92.64 355	70.67 271	65.30 374	86.24 367

fmvsm_s_conf0.5_n_6		87.50 38	88.72 24	83.84 223	86.89 288	60.04 373	95.05 42	92.17 166	84.80 20	92.27 8	96.37 41	64.62 103	96.54 145	94.43 19	91.86 80	94.94 109

Test_1112_low_res		79.56 235	78.60 236	82.43 271	88.24 233	60.39 365	92.09 197	87.99 385	72.10 268	71.84 282	87.42 292	64.62 103	93.04 332	65.80 328	77.30 287	93.85 193

test2506		83.29 152	82.92 147	84.37 203	88.39 226	63.18 291	92.01 202	91.35 208	77.66 152	78.49 187	91.42 200	64.58 105	95.09 239	73.19 239	89.23 120	94.85 112

DeepC-MVS_fast	79.48 2	87.95 30	88.00 36	87.79 35	95.86 29	68.32 104	95.74 22	94.11 74	83.82 28	83.49 101	96.19 50	64.53 106	98.44 37	83.42 136	94.88 25	96.61 20
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MG-MVS		87.11 45	86.27 64	89.62 9	97.79 1	76.27 4	94.96 49	94.49 55	78.74 129	83.87 97	92.94 147	64.34 107	96.94 124	75.19 222	94.09 42	95.66 65

fmvsm_s_conf0.5_n_4		86.79 55	87.63 40	84.27 209	86.15 308	61.48 336	94.69 61	91.16 219	83.79 30	90.51 33	96.28 46	64.24 108	98.22 41	95.00 14	86.88 149	93.11 217

casdiffmvs		85.37 87	84.87 95	86.84 68	88.25 232	69.07 79	93.04 140	91.76 186	81.27 63	80.84 136	92.07 174	64.23 109	96.06 173	84.98 110	87.43 144	95.39 75
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
cl22		77.94 274	76.78 270	81.42 304	87.57 256	64.93 220	90.67 283	88.86 354	72.45 256	67.63 342	82.68 356	64.07 110	92.91 341	71.79 257	65.30 374	86.44 358

fmvsm_s_conf0.5_n_8		87.96 28	88.93 22	85.07 160	88.43 223	61.78 325	94.73 60	91.74 187	85.87 11	91.66 19	97.50 4	64.03 111	98.33 40	96.28 4	90.08 111	95.10 100

tpm		78.58 261	77.03 266	83.22 252	85.94 314	64.56 229	83.21 413	91.14 223	78.31 137	73.67 254	79.68 403	64.01 112	92.09 374	66.07 325	71.26 332	93.03 221

CDS-MVSNet		81.43 192	80.74 190	83.52 238	86.26 304	64.45 234	92.09 197	90.65 263	75.83 188	73.95 251	89.81 248	63.97 113	92.91 341	71.27 263	82.82 213	93.20 214
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS_Test		84.16 123	83.20 136	87.05 63	91.56 133	69.82 51	89.99 311	92.05 168	77.77 149	82.84 108	86.57 305	63.93 114	96.09 169	74.91 227	89.18 122	95.25 93

APD-MVS		85.93 75	85.99 73	85.76 128	95.98 28	65.21 211	93.59 116	92.58 147	66.54 363	86.17 71	95.88 58	63.83 115	97.00 114	86.39 95	92.94 62	95.06 102
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mvs_anonymous		81.36 194	79.99 206	85.46 139	90.39 162	68.40 102	86.88 375	90.61 264	74.41 209	70.31 302	84.67 331	63.79 116	92.32 368	73.13 240	85.70 170	95.67 64

PVSNet_Blended_VisFu		83.97 129	83.50 120	85.39 142	90.02 168	66.59 173	93.77 107	91.73 188	77.43 159	77.08 207	89.81 248	63.77 117	96.97 121	79.67 183	88.21 134	92.60 235

baseline		85.01 95	84.44 101	86.71 78	88.33 229	68.73 93	90.24 302	91.82 185	81.05 67	81.18 127	92.50 156	63.69 118	96.08 172	84.45 119	86.71 156	95.32 83

fmvsm_s_conf0.5_n_10		87.93 31	88.67 25	85.71 131	88.69 205	63.71 269	94.56 63	90.22 288	85.04 17	92.27 8	97.05 14	63.67 119	98.15 44	95.09 12	91.39 90	95.27 89

myMVS_eth3d		72.58 360	72.74 338	72.10 439	87.87 248	49.45 460	88.07 354	89.01 345	72.91 245	63.11 387	88.10 279	63.63 120	85.54 449	32.73 488	69.23 344	81.32 438

CDPH-MVS		85.71 80	85.46 83	86.46 101	94.75 40	67.19 145	93.89 98	92.83 132	70.90 305	83.09 106	95.28 77	63.62 121	97.36 86	80.63 174	94.18 41	94.84 115

HyFIR lowres test		81.03 205	79.56 215	85.43 140	87.81 251	68.11 114	90.18 303	90.01 297	70.65 313	72.95 261	86.06 312	63.61 122	94.50 274	75.01 225	79.75 257	93.67 197

sasdasda		86.85 50	86.25 66	88.66 21	91.80 126	71.92 19	93.54 118	91.71 190	80.26 83	87.55 56	95.25 81	63.59 123	96.93 126	88.18 71	84.34 187	97.11 10

canonicalmvs		86.85 50	86.25 66	88.66 21	91.80 126	71.92 19	93.54 118	91.71 190	80.26 83	87.55 56	95.25 81	63.59 123	96.93 126	88.18 71	84.34 187	97.11 10

c3_l		76.83 296	75.47 292	80.93 325	85.02 338	64.18 250	90.39 295	88.11 382	71.66 283	66.65 358	81.64 371	63.58 125	92.56 356	69.31 283	62.86 401	86.04 373

SteuartSystems-ACMMP		86.82 54	86.90 53	86.58 88	90.42 160	66.38 176	96.09 18	93.87 79	77.73 150	84.01 96	95.66 62	63.39 126	97.94 49	87.40 81	93.55 54	95.42 73
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsmconf0.1_n		85.71 80	86.08 72	84.62 194	80.83 393	62.33 311	93.84 103	88.81 355	83.50 32	87.00 63	96.01 56	63.36 127	96.93 126	94.04 24	87.29 146	94.61 136

EI-MVSNet-Vis-set		83.77 135	83.67 116	84.06 214	92.79 94	63.56 277	91.76 223	94.81 38	79.65 100	77.87 191	94.09 124	63.35 128	97.90 52	79.35 188	79.36 263	90.74 287

UniMVSNet (Re)		77.58 282	76.78 270	79.98 347	84.11 356	60.80 348	91.76 223	93.17 116	76.56 181	69.93 309	84.78 330	63.32 129	92.36 365	64.89 339	62.51 406	86.78 349

0.3-1-1-0.015		81.31 195	79.49 218	86.77 76	85.74 320	68.70 98	95.01 47	94.42 60	74.29 213	77.09 206	85.61 320	63.31 130	95.69 207	76.63 210	63.30 397	95.91 54

PVSNet_BlendedMVS		83.38 151	83.43 125	83.22 252	93.76 56	67.53 133	94.06 84	93.61 93	79.13 119	81.00 133	85.14 326	63.19 131	97.29 91	87.08 89	73.91 312	84.83 397

PVSNet_Blended		86.73 56	86.86 55	86.31 110	93.76 56	67.53 133	96.33 17	93.61 93	82.34 46	81.00 133	93.08 143	63.19 131	97.29 91	87.08 89	91.38 91	94.13 172

NormalMVS		86.39 61	86.66 60	85.60 136	92.12 110	65.95 191	94.88 50	90.83 250	84.69 21	83.67 99	94.10 122	63.16 133	96.91 130	85.31 103	91.15 95	93.93 186

SymmetryMVS		86.32 64	86.39 63	86.12 115	90.52 158	65.95 191	94.88 50	94.58 52	84.69 21	83.67 99	94.10 122	63.16 133	96.91 130	85.31 103	86.59 158	95.51 71

UWE-MVS		80.81 210	81.01 186	80.20 340	89.33 184	57.05 413	91.91 211	94.71 43	75.67 189	75.01 230	89.37 254	63.13 135	91.44 394	67.19 312	82.80 215	92.12 256

PAPM_NR		82.97 161	81.84 171	86.37 106	94.10 50	66.76 167	87.66 364	92.84 131	69.96 321	74.07 248	93.57 136	63.10 136	97.50 77	70.66 272	90.58 103	94.85 112

nrg030		80.93 207	79.86 209	84.13 213	83.69 363	68.83 88	93.23 133	91.20 217	75.55 191	75.06 229	88.22 278	63.04 137	94.74 254	81.88 155	66.88 364	88.82 313

fmvsm_s_conf0.5_n		86.39 61	86.91 52	84.82 173	87.36 263	63.54 279	94.74 57	90.02 296	82.52 42	90.14 38	96.92 25	62.93 138	97.84 56	95.28 11	82.26 221	93.07 220

MGCFI-Net		85.59 84	85.73 79	85.17 157	91.41 140	62.44 307	92.87 152	91.31 209	79.65 100	86.99 64	95.14 87	62.90 139	96.12 167	87.13 86	84.13 195	96.96 14

fmvsm_s_conf0.5_n_5		86.38 63	86.94 51	84.71 185	84.67 342	63.29 285	94.04 88	89.99 298	82.88 38	87.85 54	96.03 55	62.89 140	96.36 154	94.15 21	89.95 114	94.48 151

EI-MVSNet-UG-set		83.14 157	82.96 144	83.67 234	92.28 103	63.19 290	91.38 245	94.68 45	79.22 116	76.60 210	93.75 130	62.64 141	97.76 58	78.07 202	78.01 276	90.05 296

DeepC-MVS	77.85 3	85.52 86	85.24 87	86.37 106	88.80 203	66.64 170	92.15 193	93.68 90	81.07 66	76.91 208	93.64 134	62.59 142	98.44 37	85.50 101	92.84 64	94.03 181
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
UWE-MVS-28		76.83 296	77.60 254	74.51 417	84.58 346	50.34 454	88.22 352	94.60 51	74.46 207	66.66 357	88.98 265	62.53 143	85.50 452	57.55 387	80.80 248	87.69 330

EIA-MVS		84.84 101	84.88 94	84.69 187	91.30 142	62.36 310	93.85 100	92.04 169	79.45 109	79.33 168	94.28 117	62.42 144	96.35 155	80.05 179	91.25 94	95.38 76

fmvsm_s_conf0.5_n_a		85.75 79	86.09 71	84.72 183	85.73 321	63.58 276	93.79 106	89.32 323	81.42 60	90.21 36	96.91 26	62.41 145	97.67 63	94.48 18	80.56 250	92.90 226

0.4-1-1-0.1		80.99 206	79.16 228	86.51 99	85.55 325	68.21 111	94.77 55	94.42 60	73.75 226	76.57 211	85.41 323	62.35 146	95.62 211	76.30 215	63.28 399	95.71 63

0.4-1-1-0.2		81.28 197	79.42 220	86.84 68	85.80 318	68.82 89	95.10 40	94.43 59	74.45 208	77.18 203	85.54 321	62.27 147	95.70 205	76.72 209	63.30 397	96.01 48

CS-MVS		85.80 78	86.65 61	83.27 250	92.00 118	58.92 389	95.31 33	91.86 181	79.97 88	84.82 87	95.40 71	62.26 148	95.51 222	86.11 97	92.08 76	95.37 77

MVS_111021_HR		86.19 69	85.80 77	87.37 51	93.17 77	69.79 53	93.99 91	93.76 84	79.08 121	78.88 178	93.99 127	62.25 149	98.15 44	85.93 99	91.15 95	94.15 170

PRO-TEST		88.25 20	88.30 31	88.11 31	93.04 84	71.42 23	93.31 130	93.19 114	85.25 15	87.41 59	95.02 88	62.21 150	95.99 178	93.13 30	92.14 74	96.91 16

Casviewmamba		84.58 109	83.95 109	86.47 100	87.22 266	67.76 125	92.71 158	90.96 243	80.81 69	79.29 170	91.85 186	62.20 151	96.33 157	84.60 115	85.91 166	95.32 83

blend_shiyan4		75.18 326	73.00 334	81.69 298	75.62 453	64.75 222	91.78 220	91.06 235	65.89 372	61.35 401	77.39 419	62.16 152	93.71 312	68.18 294	63.60 396	86.61 356

hybridcas		84.65 107	83.95 109	86.74 77	87.18 269	68.78 91	92.94 146	91.36 207	80.47 75	79.32 169	91.67 195	62.13 153	96.19 163	83.15 137	87.36 145	95.25 93

PHI-MVS		86.83 52	86.85 56	86.78 73	93.47 69	65.55 202	95.39 32	95.10 27	71.77 280	85.69 77	96.52 37	62.07 154	98.77 28	86.06 98	95.60 12	96.03 47

MP-MVS		85.02 94	84.97 93	85.17 157	92.60 98	64.27 245	93.24 132	92.27 156	73.13 238	79.63 163	94.43 106	61.90 155	97.17 102	85.00 109	92.56 68	94.06 179
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
E3new		84.94 99	84.36 103	86.69 81	89.06 195	69.31 70	92.68 166	91.29 214	80.72 71	81.03 130	92.14 170	61.89 156	95.91 180	84.59 116	85.85 168	94.86 111

jason		86.40 60	86.17 68	87.11 60	86.16 307	70.54 37	95.71 25	92.19 163	82.00 49	84.58 89	94.34 113	61.86 157	95.53 221	87.76 75	90.89 99	95.27 89
jason: jason.
fmvsm_s_conf0.1_n		85.61 83	85.93 74	84.68 188	82.95 374	63.48 281	94.03 90	89.46 317	81.69 52	89.86 39	96.74 33	61.85 158	97.75 59	94.74 17	82.01 229	92.81 230

SPE-MVS-test		86.14 70	87.01 49	83.52 238	92.63 97	59.36 385	95.49 29	91.92 176	80.09 87	85.46 81	95.53 68	61.82 159	95.77 197	86.77 93	93.37 56	95.41 74

PAPR		85.15 92	84.47 100	87.18 58	96.02 27	68.29 105	91.85 215	93.00 125	76.59 180	79.03 174	95.00 89	61.59 160	97.61 70	78.16 201	89.00 125	95.63 66

IS-MVSNet		80.14 225	79.41 221	82.33 277	87.91 243	60.08 372	91.97 206	88.27 378	72.90 247	71.44 290	91.73 191	61.44 161	93.66 316	62.47 361	86.53 160	93.24 211

viewcassd2359sk11		84.74 104	84.11 106	86.64 83	88.57 208	69.20 77	92.61 169	91.23 216	80.58 72	80.85 135	91.96 181	61.39 162	95.89 182	84.28 122	85.49 173	94.82 119

cl____		76.07 307	74.67 300	80.28 337	85.15 333	61.76 327	90.12 304	88.73 359	71.16 299	65.43 364	81.57 373	61.15 163	92.95 336	66.54 318	62.17 408	86.13 371

DIV-MVS_self_test		76.07 307	74.67 300	80.28 337	85.14 334	61.75 328	90.12 304	88.73 359	71.16 299	65.42 365	81.60 372	61.15 163	92.94 340	66.54 318	62.16 410	86.14 369

EI-MVSNet		78.97 250	78.22 241	81.25 311	85.33 327	62.73 303	89.53 324	93.21 111	72.39 259	72.14 278	90.13 240	60.99 165	94.72 255	67.73 304	72.49 322	86.29 365

IterMVS-LS		76.49 300	75.18 297	80.43 334	84.49 349	62.74 302	90.64 285	88.80 356	72.40 258	65.16 367	81.72 369	60.98 166	92.27 369	67.74 303	64.65 386	86.29 365
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.1_n_a		84.76 103	84.84 96	84.53 196	80.23 406	63.50 280	92.79 154	88.73 359	80.46 76	89.84 40	96.65 36	60.96 167	97.57 73	93.80 26	80.14 252	92.53 239

ETV-MVS		86.01 73	86.11 70	85.70 132	90.21 165	67.02 154	93.43 126	91.92 176	81.21 64	84.13 95	94.07 126	60.93 168	95.63 209	89.28 63	89.81 116	94.46 152

E2		84.45 111	83.74 113	86.56 90	87.90 244	69.06 80	92.53 177	91.13 225	80.35 80	80.58 142	91.69 193	60.70 169	95.84 185	83.80 129	84.99 178	94.79 122

E3		84.45 111	83.74 113	86.56 90	87.90 244	69.06 80	92.53 177	91.13 225	80.35 80	80.58 142	91.69 193	60.70 169	95.84 185	83.80 129	84.99 178	94.79 122

tpm cat1		75.30 323	72.21 346	84.58 195	88.52 213	67.77 124	78.16 455	88.02 384	61.88 414	68.45 329	76.37 437	60.65 171	94.03 300	53.77 402	74.11 309	91.93 262

TAMVS		80.37 220	79.45 219	83.13 255	85.14 334	63.37 282	91.23 257	90.76 258	74.81 205	72.65 266	88.49 268	60.63 172	92.95 336	69.41 281	81.95 231	93.08 219

ZNCC-MVS		85.33 88	85.08 91	86.06 116	93.09 81	65.65 198	93.89 98	93.41 106	73.75 226	79.94 153	94.68 100	60.61 173	98.03 47	82.63 146	93.72 50	94.52 143

fmvsm_s_conf0.5_n_7		85.24 89	86.69 58	80.91 326	84.52 347	60.10 371	93.35 129	90.35 276	83.41 33	86.54 67	96.27 47	60.50 174	90.02 412	94.84 16	90.38 107	92.61 234

viewmanbaseed2359cas		84.89 100	84.26 105	86.78 73	88.50 214	69.77 55	92.69 165	91.13 225	81.11 65	81.54 120	91.98 180	60.35 175	95.73 199	84.47 118	86.56 159	94.84 115

thres100view900		78.37 264	77.01 267	82.46 270	91.89 124	63.21 289	91.19 261	96.33 1	72.28 262	70.45 299	87.89 284	60.31 176	95.32 230	45.16 443	77.58 282	88.83 311

thres600view7		78.00 271	76.66 272	82.03 292	91.93 120	63.69 272	91.30 253	96.33 1	72.43 257	70.46 298	87.89 284	60.31 176	94.92 247	42.64 455	76.64 293	87.48 333

CHOSEN 1792x2688		84.98 96	83.45 124	89.57 12	89.94 170	75.14 6	92.07 199	92.32 154	81.87 50	75.68 218	88.27 274	60.18 178	98.60 33	80.46 176	90.27 110	94.96 107

h-mvs33		83.01 160	82.56 160	84.35 204	89.34 182	62.02 318	92.72 157	93.76 84	81.45 56	82.73 111	92.25 166	60.11 179	97.13 107	87.69 76	62.96 400	93.91 189

hse-mvs2		81.12 203	81.11 184	81.16 314	86.52 297	57.48 406	89.40 327	91.16 219	81.45 56	82.73 111	90.49 223	60.11 179	94.58 264	87.69 76	60.41 427	91.41 272

tfpn200view9		78.79 256	77.43 257	82.88 259	92.21 106	64.49 231	92.05 200	96.28 4	73.48 233	71.75 284	88.26 275	60.07 181	95.32 230	45.16 443	77.58 282	88.83 311

thres400		78.68 258	77.43 257	82.43 271	92.21 106	64.49 231	92.05 200	96.28 4	73.48 233	71.75 284	88.26 275	60.07 181	95.32 230	45.16 443	77.58 282	87.48 333

diffmvs		84.28 117	83.83 111	85.61 135	87.40 261	68.02 116	90.88 272	89.24 327	80.54 73	81.64 119	92.52 155	59.83 183	94.52 273	87.32 82	85.11 177	94.29 160
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS		84.66 106	82.86 149	90.06 3	90.93 150	74.56 7	87.91 358	95.54 15	68.55 342	72.35 277	94.71 99	59.78 184	98.90 24	81.29 167	94.69 34	96.74 18

lecture		84.77 102	84.81 97	84.65 190	92.12 110	62.27 314	94.74 57	92.64 144	68.35 345	85.53 78	95.30 75	59.77 185	97.91 51	83.73 131	91.15 95	93.77 195

E4		84.00 128	83.19 137	86.46 101	86.99 276	68.85 87	92.39 184	90.99 242	79.94 89	80.17 150	91.36 204	59.73 186	95.79 194	82.87 143	84.22 193	94.74 124

thres200		79.66 233	78.33 238	83.66 235	92.54 100	65.82 196	93.06 138	96.31 3	74.90 204	73.30 258	88.66 266	59.67 187	95.61 213	47.84 430	78.67 272	89.56 305

Effi-MVS+		83.82 133	82.76 150	86.99 65	89.56 178	69.40 64	91.35 250	86.12 415	72.59 251	83.22 105	92.81 153	59.60 188	96.01 177	81.76 160	87.80 139	95.56 69

diffmvs_AUTHOR		83.97 129	83.49 121	85.39 142	86.09 309	67.83 122	90.76 277	89.05 343	79.94 89	81.43 124	92.23 167	59.53 189	94.42 277	87.18 85	85.22 175	93.92 188

viewmambaseed2359dif		82.60 170	81.91 170	84.67 189	85.83 316	66.09 184	90.50 291	89.01 345	75.46 192	79.64 162	92.01 178	59.51 190	94.38 279	82.99 141	82.26 221	93.54 202

eth_miper_zixun_eth		75.96 314	74.40 308	80.66 329	84.66 343	63.02 293	89.28 330	88.27 378	71.88 274	65.73 362	81.65 370	59.45 191	92.81 345	68.13 296	60.53 424	86.14 369

ACMMP_NAP		86.05 71	85.80 77	86.80 72	91.58 132	67.53 133	91.79 217	93.49 101	74.93 203	84.61 88	95.30 75	59.42 192	97.92 50	86.13 96	94.92 20	94.94 109

GST-MVS		84.63 108	84.29 104	85.66 133	92.82 91	65.27 209	93.04 140	93.13 118	73.20 236	78.89 175	94.18 120	59.41 193	97.85 55	81.45 163	92.48 70	93.86 192

UA-Net		80.02 228	79.65 213	81.11 317	89.33 184	57.72 401	86.33 381	89.00 349	77.44 158	81.01 131	89.15 259	59.33 194	95.90 181	61.01 368	84.28 191	89.73 302

balanced_ft_v1		84.95 98	83.81 112	88.38 28	93.31 71	73.59 11	85.95 384	92.51 149	77.25 163	73.97 250	89.14 260	59.30 195	95.25 235	92.50 37	90.34 109	96.31 36

viewdifsd2359ckpt09		83.52 147	82.57 159	86.37 106	88.02 241	68.47 100	91.78 220	89.63 313	79.61 102	78.56 185	92.00 179	59.28 196	95.96 179	81.94 154	82.35 218	94.69 128

NR-MVSNet		76.05 310	74.59 303	80.44 333	82.96 372	62.18 316	90.83 274	91.73 188	77.12 164	60.96 404	86.35 307	59.28 196	91.80 380	60.74 370	61.34 419	87.35 337

hybridnocas07		83.76 136	83.21 134	85.39 142	86.64 290	67.40 138	91.08 264	88.77 358	79.78 97	80.35 147	92.15 169	59.24 198	94.67 262	87.11 88	83.79 200	94.11 174

MP-MVS-pluss		85.24 89	85.13 90	85.56 137	91.42 137	65.59 200	91.54 237	92.51 149	74.56 206	80.62 139	95.64 63	59.15 199	97.00 114	86.94 91	93.80 47	94.07 178
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
reproduce-ours		83.51 148	83.33 131	84.06 214	92.18 108	60.49 361	90.74 279	92.04 169	64.35 385	83.24 102	95.59 66	59.05 200	97.27 96	83.61 132	89.17 123	94.41 158

our_new_method		83.51 148	83.33 131	84.06 214	92.18 108	60.49 361	90.74 279	92.04 169	64.35 385	83.24 102	95.59 66	59.05 200	97.27 96	83.61 132	89.17 123	94.41 158

HFP-MVS		84.73 105	84.40 102	85.72 130	93.75 58	65.01 217	93.50 121	93.19 114	72.19 264	79.22 171	94.93 92	59.04 202	97.67 63	81.55 161	92.21 71	94.49 150

MSLP-MVS++		86.27 67	85.91 75	87.35 52	92.01 117	68.97 85	95.04 44	92.70 136	79.04 124	81.50 121	96.50 39	58.98 203	96.78 134	83.49 135	93.93 45	96.29 38

onestephybrid01		83.68 140	83.31 133	84.81 176	86.53 295	65.38 207	90.54 290	89.14 335	79.52 108	81.01 131	92.02 176	58.91 204	94.91 249	88.26 70	83.86 199	94.14 171

viewmamba		83.23 155	82.64 157	85.00 164	86.40 301	66.16 183	90.68 282	88.35 374	79.92 91	78.68 183	92.02 176	58.86 205	94.72 255	85.55 100	83.31 209	94.12 173

viewdifsd2359ckpt13		84.08 125	83.21 134	86.70 79	88.49 218	69.55 61	92.25 187	91.14 223	79.71 98	79.73 160	91.72 192	58.83 206	95.89 182	82.06 152	84.99 178	94.66 133

Patchmatch-test		65.86 413	60.94 428	80.62 332	83.75 362	58.83 390	58.91 497	75.26 472	44.50 485	50.95 461	77.09 426	58.81 207	87.90 429	35.13 476	64.03 391	95.12 99

hybrid		83.58 146	83.00 143	85.34 148	86.38 302	67.51 136	90.92 268	88.87 353	78.49 134	80.59 141	92.09 173	58.77 208	94.46 275	87.12 87	83.74 201	94.06 179

reproduce_model		83.15 156	82.96 144	83.73 229	92.02 114	59.74 377	90.37 296	92.08 167	63.70 392	82.86 107	95.48 69	58.62 209	97.17 102	83.06 139	88.42 132	94.26 162

viewdifsd2359ckpt07		82.95 163	82.04 166	85.66 133	87.19 268	66.73 168	91.56 236	90.39 275	77.58 155	77.58 197	91.19 211	58.57 210	95.65 208	82.32 148	82.01 229	94.60 137

viewmacassd2359aftdt		84.03 126	83.18 138	86.59 87	86.76 289	69.44 63	92.44 182	90.85 249	80.38 79	80.78 137	91.33 205	58.54 211	95.62 211	82.15 150	85.41 174	94.72 127

EPNet_dtu		78.80 255	79.26 226	77.43 386	88.06 238	49.71 458	91.96 207	91.95 175	77.67 151	76.56 212	91.28 206	58.51 212	90.20 408	56.37 390	80.95 240	92.39 242
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		60.86 439	60.24 429	62.71 469	81.57 387	46.43 476	75.70 465	85.88 417	57.98 438	48.95 469	69.53 468	58.42 213	76.53 487	28.25 496	35.87 493	65.15 494

test_fmvsmvis_n_1920		83.80 134	83.48 122	84.77 178	82.51 377	63.72 268	91.37 246	83.99 439	81.42 60	77.68 193	95.74 61	58.37 214	97.58 71	93.38 28	86.87 150	93.00 223

EC-MVSNet		84.53 110	85.04 92	83.01 256	89.34 182	61.37 340	94.42 69	91.09 229	77.91 145	83.24 102	94.20 119	58.37 214	95.40 224	85.35 102	91.41 89	92.27 251

VNet		86.20 68	85.65 80	87.84 34	93.92 53	69.99 44	95.73 24	95.94 7	78.43 135	86.00 73	93.07 144	58.22 216	97.00 114	85.22 105	84.33 189	96.52 25

TESTMET0.1,1		82.41 172	81.98 169	83.72 231	88.08 237	63.74 265	92.70 160	93.77 83	79.30 114	77.61 195	87.57 290	58.19 217	94.08 293	73.91 234	86.68 157	93.33 210

原ACMM1				84.42 200	93.21 75	64.27 245		93.40 107	65.39 378	79.51 164	92.50 156	58.11 218	96.69 137	65.27 337	93.96 44	92.32 246

dtuplus		82.25 175	81.42 177	84.71 185	85.38 326	66.05 185	90.62 288	89.27 325	75.16 200	79.22 171	91.76 188	58.05 219	94.56 269	81.18 169	82.19 226	93.52 203

E5new		83.62 142	82.65 153	86.55 92	86.98 277	69.28 73	91.69 227	90.96 243	79.61 102	79.80 155	91.25 207	58.04 220	95.84 185	81.83 158	83.66 204	94.52 143

E6new		83.62 142	82.65 153	86.55 92	86.98 277	69.29 71	91.69 227	90.95 246	79.60 105	79.80 155	91.25 207	58.04 220	95.84 185	81.84 156	83.67 202	94.52 143

E6		83.62 142	82.65 153	86.55 92	86.98 277	69.29 71	91.69 227	90.95 246	79.60 105	79.80 155	91.25 207	58.04 220	95.84 185	81.84 156	83.67 202	94.52 143

E5		83.62 142	82.65 153	86.55 92	86.98 277	69.28 73	91.69 227	90.96 243	79.61 102	79.80 155	91.25 207	58.04 220	95.84 185	81.83 158	83.66 204	94.52 143

sam_mvs1												57.85 224				94.68 130

CR-MVSNet		73.79 343	70.82 359	82.70 264	83.15 370	67.96 117	70.25 475	84.00 437	73.67 231	69.97 307	72.41 454	57.82 225	89.48 416	52.99 406	73.13 316	90.64 289

Patchmtry		67.53 404	63.93 412	78.34 374	82.12 381	64.38 239	68.72 479	84.00 437	48.23 475	59.24 418	72.41 454	57.82 225	89.27 417	46.10 439	56.68 440	81.36 437

patchmatchnet-post											67.62 475	57.62 227	90.25 403

PCF-MVS	73.15 9	79.29 243	77.63 253	84.29 207	86.06 310	65.96 190	87.03 371	91.10 228	69.86 323	69.79 310	90.64 218	57.54 228	96.59 139	64.37 346	82.29 219	90.32 292
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Fast-Effi-MVS+		81.14 201	80.01 205	84.51 198	90.24 164	65.86 194	94.12 83	89.15 333	73.81 225	75.37 226	88.26 275	57.26 229	94.53 272	66.97 315	84.92 181	93.15 215

miper_lstm_enhance		73.05 349	71.73 352	77.03 392	83.80 361	58.32 396	81.76 425	88.88 351	69.80 324	61.01 403	78.23 413	57.19 230	87.51 439	65.34 336	59.53 429	85.27 394

PatchT		69.11 388	65.37 401	80.32 335	82.07 382	63.68 273	67.96 484	87.62 390	50.86 466	69.37 311	65.18 479	57.09 231	88.53 423	41.59 459	66.60 366	88.74 314

testdata				81.34 308	89.02 197	57.72 401		89.84 302	58.65 436	85.32 83	94.09 124	57.03 232	93.28 326	69.34 282	90.56 104	93.03 221

PatchmatchNet		77.46 283	74.63 302	85.96 119	89.55 179	70.35 40	79.97 446	89.55 315	72.23 263	70.94 292	76.91 428	57.03 232	92.79 347	54.27 398	81.17 238	94.74 124
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_yl		84.28 117	83.16 139	87.64 39	94.52 43	69.24 75	95.78 19	95.09 28	69.19 332	81.09 128	92.88 150	57.00 234	97.44 80	81.11 170	81.76 233	96.23 41

DCV-MVSNet		84.28 117	83.16 139	87.64 39	94.52 43	69.24 75	95.78 19	95.09 28	69.19 332	81.09 128	92.88 150	57.00 234	97.44 80	81.11 170	81.76 233	96.23 41

region2R		84.36 115	84.03 108	85.36 147	93.54 66	64.31 243	93.43 126	92.95 128	72.16 267	78.86 179	94.84 96	56.97 236	97.53 75	81.38 165	92.11 75	94.24 164

新几何1				84.73 182	92.32 102	64.28 244		91.46 203	59.56 431	79.77 159	92.90 148	56.95 237	96.57 141	63.40 351	92.91 63	93.34 208

WR-MVS		76.76 298	75.74 290	79.82 353	84.60 344	62.27 314	92.60 171	92.51 149	76.06 185	67.87 339	85.34 324	56.76 238	90.24 406	62.20 362	63.69 395	86.94 345

HPM-MVS		83.25 153	82.95 146	84.17 212	92.25 104	62.88 300	90.91 269	91.86 181	70.30 316	77.12 204	93.96 128	56.75 239	96.28 158	82.04 153	91.34 93	93.34 208
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		82.71 167	82.38 163	83.73 229	89.25 188	59.58 380	92.24 189	94.89 33	77.96 142	79.86 154	92.38 161	56.70 240	97.05 109	77.26 206	80.86 245	94.55 139

ACMMPR		84.37 114	84.06 107	85.28 152	93.56 64	64.37 240	93.50 121	93.15 117	72.19 264	78.85 180	94.86 95	56.69 241	97.45 79	81.55 161	92.20 72	94.02 182

FMVSNet3		77.73 279	76.04 285	82.80 260	91.20 145	68.99 84	91.87 213	91.99 173	73.35 235	67.04 351	83.19 351	56.62 242	92.14 371	59.80 377	69.34 341	87.28 339

Patchmatch-RL test		68.17 398	64.49 408	79.19 366	71.22 472	53.93 434	70.07 477	71.54 485	69.22 331	56.79 435	62.89 484	56.58 243	88.61 420	69.53 280	52.61 451	95.03 105

dongtai		55.18 452	55.46 450	54.34 479	76.03 451	36.88 499	76.07 462	84.61 431	51.28 463	43.41 488	64.61 482	56.56 244	67.81 500	18.09 507	28.50 504	58.32 498

test_post											23.01 525	56.49 245	92.67 352

RPMNet		70.42 377	65.68 397	84.63 193	83.15 370	67.96 117	70.25 475	90.45 268	46.83 478	69.97 307	65.10 480	56.48 246	95.30 233	35.79 475	73.13 316	90.64 289

DU-MVS		76.86 293	75.84 288	79.91 350	82.96 372	60.26 367	91.26 254	91.54 198	76.46 183	68.88 321	86.35 307	56.16 247	92.13 372	66.38 321	62.55 404	87.35 337

Baseline_NR-MVSNet		73.99 340	72.83 336	77.48 385	80.78 395	59.29 386	91.79 217	84.55 432	68.85 338	68.99 318	80.70 387	56.16 247	92.04 375	62.67 359	60.98 421	81.11 440

API-MVS		82.28 174	80.53 198	87.54 46	96.13 24	70.59 36	93.63 114	91.04 239	65.72 375	75.45 224	92.83 152	56.11 249	98.89 25	64.10 347	89.75 119	93.15 215

MTAPA		83.91 131	83.38 129	85.50 138	91.89 124	65.16 213	81.75 426	92.23 157	75.32 197	80.53 144	95.21 84	56.06 250	97.16 105	84.86 112	92.55 69	94.18 167

JIA-IIPM		66.06 412	62.45 421	76.88 396	81.42 390	54.45 433	57.49 500	88.67 362	49.36 471	63.86 380	46.86 499	56.06 250	90.25 403	49.53 418	68.83 347	85.95 376

casdiffseed414692147		82.20 176	80.75 189	86.55 92	87.13 272	69.57 60	91.79 217	90.48 267	78.12 140	78.52 186	90.10 243	55.92 252	95.80 192	72.42 252	82.28 220	94.28 161

v148		76.19 305	74.47 307	81.36 307	80.05 408	64.44 235	91.75 225	90.23 286	73.68 230	67.13 350	80.84 386	55.92 252	93.86 310	68.95 288	61.73 415	85.76 384

WR-MVS_H		70.59 375	69.94 366	72.53 433	81.03 391	51.43 446	87.35 368	92.03 172	67.38 356	60.23 414	80.70 387	55.84 254	83.45 466	46.33 438	58.58 434	82.72 423

test_fmvsmconf0.01_n		83.70 139	83.52 118	84.25 210	75.26 457	61.72 329	92.17 192	87.24 398	82.36 45	84.91 86	95.41 70	55.60 255	96.83 133	92.85 33	85.87 167	94.21 165

AUN-MVS		78.37 264	77.43 257	81.17 313	86.60 293	57.45 407	89.46 326	91.16 219	74.11 216	74.40 240	90.49 223	55.52 256	94.57 266	74.73 230	60.43 426	91.48 270

XVS		83.87 132	83.47 123	85.05 161	93.22 73	63.78 263	92.92 148	92.66 141	73.99 218	78.18 188	94.31 115	55.25 257	97.41 83	79.16 190	91.58 86	93.95 184

X-MVStestdata		76.86 293	74.13 315	85.05 161	93.22 73	63.78 263	92.92 148	92.66 141	73.99 218	78.18 188	10.19 533	55.25 257	97.41 83	79.16 190	91.58 86	93.95 184

BH-w/o		80.49 217	79.30 225	84.05 217	90.83 154	64.36 242	93.60 115	89.42 320	74.35 211	69.09 314	90.15 239	55.23 259	95.61 213	64.61 342	86.43 163	92.17 254

CP-MVS		83.71 138	83.40 128	84.65 190	93.14 78	63.84 261	94.59 62	92.28 155	71.03 303	77.41 198	94.92 93	55.21 260	96.19 163	81.32 166	90.70 101	93.91 189

PGM-MVS		83.25 153	82.70 152	84.92 166	92.81 93	64.07 253	90.44 292	92.20 161	71.28 297	77.23 202	94.43 106	55.17 261	97.31 90	79.33 189	91.38 91	93.37 207

tpmvs		72.88 353	69.76 369	82.22 282	90.98 149	67.05 151	78.22 454	88.30 376	63.10 401	64.35 377	74.98 444	55.09 262	94.27 284	43.25 449	69.57 340	85.34 392

v8		75.35 322	73.26 331	81.61 300	80.67 397	66.82 164	89.54 321	89.27 325	71.65 284	63.30 386	80.30 395	54.99 263	94.06 295	67.33 310	62.33 407	83.94 404

sam_mvs												54.91 264

usedtu_dtu_shiyan1		77.89 277	76.39 278	82.40 275	81.92 384	67.01 156	91.94 209	93.00 125	77.01 165	68.44 330	84.15 337	54.78 265	93.25 327	65.76 329	70.53 335	86.94 345

FE-MVSNET3		77.89 277	76.39 278	82.40 275	81.92 384	67.01 156	91.94 209	93.00 125	77.01 165	68.44 330	84.15 337	54.78 265	93.25 327	65.76 329	70.53 335	86.94 345

EPMVS		78.49 263	75.98 286	86.02 117	91.21 144	69.68 58	80.23 441	91.20 217	75.25 198	72.48 273	78.11 414	54.65 267	93.69 315	57.66 386	83.04 211	94.69 128

ab-mvs		80.18 224	78.31 239	85.80 126	88.44 222	65.49 205	83.00 417	92.67 140	71.82 278	77.36 199	85.01 327	54.50 268	96.59 139	76.35 214	75.63 299	95.32 83

KD-MVS_2432*1600		69.03 389	66.37 392	77.01 393	85.56 323	61.06 344	81.44 430	90.25 284	67.27 357	58.00 429	76.53 435	54.49 269	87.63 435	48.04 427	35.77 494	82.34 429

miper_refine_blended		69.03 389	66.37 392	77.01 393	85.56 323	61.06 344	81.44 430	90.25 284	67.27 357	58.00 429	76.53 435	54.49 269	87.63 435	48.04 427	35.77 494	82.34 429

DP-MVS Recon		82.73 165	81.65 173	85.98 118	97.31 4	67.06 150	95.15 38	91.99 173	69.08 337	76.50 213	93.89 129	54.48 271	98.20 43	70.76 270	85.66 171	92.69 231

GeoE		78.90 252	77.43 257	83.29 248	88.95 199	62.02 318	92.31 185	86.23 411	70.24 317	71.34 291	89.27 257	54.43 272	94.04 298	63.31 353	80.81 247	93.81 194

XXY-MVS		77.94 274	76.44 275	82.43 271	82.60 376	64.44 235	92.01 202	91.83 184	73.59 232	70.00 306	85.82 316	54.43 272	94.76 252	69.63 278	68.02 355	88.10 326

MDTV_nov1_ep13_2view						59.90 375	80.13 443		67.65 354	72.79 263		54.33 274		59.83 376		92.58 237

fmvsm_s_conf0.5_n_2		85.06 93	85.60 81	83.44 244	86.92 286	60.53 360	94.41 70	87.31 396	83.30 34	88.72 48	96.72 34	54.28 275	97.75 59	94.07 23	84.68 186	92.04 257

IMVS_0403		81.19 199	79.88 208	85.13 159	88.54 209	64.75 222	88.84 341	90.80 253	76.73 175	75.21 227	90.18 231	54.22 276	96.21 162	73.47 235	80.95 240	94.43 154

Test By Simon												54.21 277

MAR-MVS		84.18 122	83.43 125	86.44 103	96.25 23	65.93 193	94.28 76	94.27 70	74.41 209	79.16 173	95.61 64	53.99 278	98.88 26	69.62 279	93.26 58	94.50 149
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
test-LLR		80.10 226	79.56 215	81.72 296	86.93 284	61.17 341	92.70 160	91.54 198	71.51 293	75.62 219	86.94 301	53.83 279	92.38 363	72.21 254	84.76 184	91.60 267

test0.0.03 1		72.76 354	72.71 340	72.88 431	80.25 405	47.99 466	91.22 258	89.45 318	71.51 293	62.51 396	87.66 287	53.83 279	85.06 454	50.16 415	67.84 360	85.58 385

v2v482		77.42 284	75.65 291	82.73 262	80.38 402	67.13 149	91.85 215	90.23 286	75.09 201	69.37 311	83.39 348	53.79 281	94.44 276	71.77 258	65.00 381	86.63 354

SR-MVS		82.81 164	82.58 158	83.50 241	93.35 70	61.16 343	92.23 190	91.28 215	64.48 384	81.27 125	95.28 77	53.71 282	95.86 184	82.87 143	88.77 129	93.49 205

pcd_1.5k_mvsjas		4.46 502	5.95 503	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	53.55 283	0.00 562	0.00 561	0.00 560	0.00 558

PS-MVSNAJss		77.26 286	76.31 280	80.13 342	80.64 398	59.16 387	90.63 287	91.06 235	72.80 248	68.58 327	84.57 333	53.55 283	93.96 303	72.97 241	71.96 326	87.27 340

PS-MVSNAJ		88.14 23	87.61 42	89.71 8	92.06 113	76.72 1	95.75 21	93.26 110	83.86 27	89.55 42	96.06 54	53.55 283	97.89 53	91.10 52	93.31 57	94.54 141

mPP-MVS		82.96 162	82.44 162	84.52 197	92.83 89	62.92 298	92.76 155	91.85 183	71.52 292	75.61 221	94.24 118	53.48 286	96.99 117	78.97 193	90.73 100	93.64 200

xiu_mvs_v2_base		87.92 32	87.38 46	89.55 13	91.41 140	76.43 3	95.74 22	93.12 119	83.53 31	89.55 42	95.95 57	53.45 287	97.68 61	91.07 53	92.62 66	94.54 141

test_post1							78.95 448				20.70 529	53.05 288	91.50 393	60.43 372

MDTV_nov1_ep13			72.61 341		89.06 195	68.48 99	80.33 439	90.11 291	71.84 277	71.81 283	75.92 441	53.01 289	93.92 305	48.04 427	73.38 314

FA-MVS(test-final)		79.12 246	77.23 263	84.81 176	90.54 157	63.98 258	81.35 432	91.71 190	71.09 302	74.85 235	82.94 352	52.85 290	97.05 109	67.97 300	81.73 235	93.41 206

test222					89.77 173	61.60 332	89.55 320	89.42 320	56.83 447	77.28 201	92.43 160	52.76 291			91.14 98	93.09 218

fmvsm_s_conf0.1_n_2		84.40 113	84.78 98	83.27 250	85.25 331	60.41 363	94.13 82	85.69 421	83.05 36	87.99 52	96.37 41	52.75 292	97.68 61	93.75 27	84.05 196	91.71 265

v1144		76.73 299	74.88 299	82.27 279	80.23 406	66.60 172	91.68 231	90.21 289	73.69 229	69.06 316	81.89 366	52.73 293	94.40 278	69.21 284	65.23 378	85.80 381

v10		74.77 332	72.54 343	81.46 303	80.33 404	66.71 169	89.15 335	89.08 340	70.94 304	63.08 389	79.86 400	52.52 294	94.04 298	65.70 331	62.17 408	83.64 407

CLD-MVS		82.73 165	82.35 164	83.86 222	87.90 244	67.65 129	95.45 30	92.18 164	85.06 16	72.58 268	92.27 164	52.46 295	95.78 195	84.18 123	79.06 268	88.16 325
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TranMVSNet+NR-MVSNet		75.86 315	74.52 306	79.89 351	82.44 378	60.64 358	91.37 246	91.37 206	76.63 179	67.65 341	86.21 310	52.37 296	91.55 388	61.84 364	60.81 422	87.48 333

VPA-MVSNet		79.03 248	78.00 244	82.11 290	85.95 312	64.48 233	93.22 134	94.66 46	75.05 202	74.04 249	84.95 328	52.17 297	93.52 318	74.90 228	67.04 363	88.32 324

APD-MVS_3200maxsize		81.64 189	81.32 178	82.59 269	92.36 101	58.74 391	91.39 243	91.01 241	63.35 396	79.72 161	94.62 102	51.82 298	96.14 166	79.71 182	87.93 137	92.89 227

dp		75.01 328	72.09 347	83.76 226	89.28 187	66.22 182	79.96 447	89.75 305	71.16 299	67.80 340	77.19 425	51.81 299	92.54 357	50.39 413	71.44 331	92.51 240

mvsmamba		81.55 190	80.72 191	84.03 218	91.42 137	66.93 162	83.08 414	89.13 336	78.55 133	67.50 344	87.02 300	51.79 300	90.07 411	87.48 79	90.49 105	95.10 100

v144192		76.05 310	74.03 316	82.12 287	79.50 414	66.55 174	91.39 243	89.71 311	72.30 261	68.17 332	81.33 378	51.75 301	94.03 300	67.94 301	64.19 388	85.77 382

BH-untuned		78.68 258	77.08 265	83.48 242	89.84 171	63.74 265	92.70 160	88.59 365	71.57 290	66.83 355	88.65 267	51.75 301	95.39 225	59.03 380	84.77 183	91.32 276

HQP2-MVS												51.63 303

HQP-MVS		81.14 201	80.64 194	82.64 266	87.54 257	63.66 274	94.06 84	91.70 193	79.80 94	74.18 241	90.30 228	51.63 303	95.61 213	77.63 204	78.90 269	88.63 315

icg_test_0407_2		80.38 219	79.22 227	83.88 221	88.54 209	64.75 222	86.79 376	90.80 253	76.73 175	73.95 251	90.18 231	51.55 305	92.45 361	73.47 235	80.95 240	94.43 154

IMVS_0407		80.80 211	79.39 223	85.00 164	88.54 209	64.75 222	88.40 349	90.80 253	76.73 175	73.95 251	90.18 231	51.55 305	95.81 191	73.47 235	80.95 240	94.43 154

dmvs_testset		65.55 416	66.45 390	62.86 468	79.87 409	22.35 517	76.55 459	71.74 483	77.42 160	55.85 437	87.77 286	51.39 307	80.69 482	31.51 494	65.92 371	85.55 387

V42		76.46 301	74.55 305	82.19 284	79.14 420	67.82 123	90.26 301	89.42 320	73.75 226	68.63 326	81.89 366	51.31 308	94.09 292	71.69 260	64.84 382	84.66 398

RRT-MVS		82.61 169	81.16 179	86.96 66	91.10 146	68.75 92	87.70 363	92.20 161	76.97 167	72.68 264	87.10 299	51.30 309	96.41 152	83.56 134	87.84 138	95.74 62

SR-MVS-dyc-post		81.06 204	80.70 192	82.15 285	92.02 114	58.56 394	90.90 270	90.45 268	62.76 403	78.89 175	94.46 104	51.26 310	95.61 213	78.77 197	86.77 154	92.28 248

viewdifsd2359ckpt11		79.42 241	77.95 247	83.81 224	83.87 360	63.85 259	89.54 321	87.38 392	77.39 161	74.94 231	89.95 245	51.11 311	94.72 255	79.52 185	67.90 356	92.88 228

viewmsd2359difaftdt		79.42 241	77.96 246	83.81 224	83.88 359	63.85 259	89.54 321	87.38 392	77.39 161	74.94 231	89.95 245	51.11 311	94.72 255	79.52 185	67.90 356	92.88 228

CL-MVSNet_self_test		69.92 381	68.09 384	75.41 405	73.25 466	55.90 424	90.05 307	89.90 300	69.96 321	61.96 399	76.54 434	51.05 313	87.64 434	49.51 419	50.59 463	82.70 425

TransMVSNet (Re)		70.07 380	67.66 385	77.31 389	80.62 399	59.13 388	91.78 220	84.94 428	65.97 371	60.08 415	80.44 392	50.78 314	91.87 378	48.84 422	45.46 476	80.94 442

HQP_MVS		80.34 221	79.75 212	82.12 287	86.94 282	62.42 308	93.13 136	91.31 209	78.81 127	72.53 269	89.14 260	50.66 315	95.55 219	76.74 207	78.53 274	88.39 321

plane_prior6					87.23 265	62.32 312						50.66 315

SD_0403		73.79 343	73.48 326	74.69 414	85.33 327	45.56 480	83.80 402	85.57 422	76.55 182	62.96 390	88.45 269	50.62 317	87.59 437	48.80 423	79.28 267	90.92 285

ACMMP		81.49 191	80.67 193	83.93 220	91.71 129	62.90 299	92.13 194	92.22 160	71.79 279	71.68 286	93.49 138	50.32 318	96.96 122	78.47 199	84.22 193	91.93 262
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
MVS_111021_LR		82.02 183	81.52 174	83.51 240	88.42 224	62.88 300	89.77 314	88.93 350	76.78 172	75.55 222	93.10 141	50.31 319	95.38 226	83.82 128	87.02 148	92.26 252

1314		80.70 212	78.95 232	85.94 120	87.77 254	67.56 131	87.91 358	92.55 148	72.17 266	67.44 345	93.09 142	50.27 320	97.04 112	71.68 261	87.64 141	93.23 212

CP-MVSNet		70.50 376	69.91 367	72.26 436	80.71 396	51.00 450	87.23 370	90.30 281	67.84 351	59.64 416	82.69 355	50.23 321	82.30 476	51.28 409	59.28 430	83.46 412

guyue		81.23 198	80.57 197	83.21 254	86.64 290	61.85 323	92.52 179	92.78 133	78.69 130	74.92 233	89.42 253	50.07 322	95.35 227	80.79 172	79.31 265	92.42 241

LCM-MVSNet-Re		72.93 351	71.84 350	76.18 402	88.49 218	48.02 465	80.07 444	70.17 487	73.96 221	52.25 452	80.09 399	49.98 323	88.24 427	67.35 308	84.23 192	92.28 248

Vis-MVSNet		80.92 208	79.98 207	83.74 227	88.48 220	61.80 324	93.44 125	88.26 380	73.96 221	77.73 192	91.76 188	49.94 324	94.76 252	65.84 327	90.37 108	94.65 134
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v1192		75.98 312	73.92 318	82.15 285	79.73 410	66.24 181	91.22 258	89.75 305	72.67 250	68.49 328	81.42 376	49.86 325	94.27 284	67.08 313	65.02 380	85.95 376

test-mter		79.96 229	79.38 224	81.72 296	86.93 284	61.17 341	92.70 160	91.54 198	73.85 223	75.62 219	86.94 301	49.84 326	92.38 363	72.21 254	84.76 184	91.60 267

MonoMVSNet		76.99 291	75.08 298	82.73 262	83.32 368	63.24 287	86.47 380	86.37 407	79.08 121	66.31 359	79.30 407	49.80 327	91.72 382	79.37 187	65.70 372	93.23 212

VortexMVS		77.62 280	76.44 275	81.13 315	88.58 207	63.73 267	91.24 256	91.30 213	77.81 147	65.76 361	81.97 365	49.69 328	93.72 311	76.40 213	65.26 377	85.94 378

cdsmvs_eth3d_5k		19.86 481	26.47 479	0.00 542	0.00 566	0.00 569	0.00 554	93.45 102	0.00 561	0.00 562	95.27 79	49.56 329	0.00 562	0.00 561	0.00 560	0.00 558

3Dnovator+	73.60 7	82.10 182	80.60 196	86.60 85	90.89 152	66.80 166	95.20 36	93.44 103	74.05 217	67.42 346	92.49 158	49.46 330	97.65 67	70.80 269	91.68 84	95.33 81

MVP-Stereo		77.12 289	76.23 282	79.79 354	81.72 386	66.34 178	89.29 329	90.88 248	70.56 314	62.01 398	82.88 353	49.34 331	94.13 290	65.55 334	93.80 47	78.88 462
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
RE-MVS-def			80.48 199		92.02 114	58.56 394	90.90 270	90.45 268	62.76 403	78.89 175	94.46 104	49.30 332		78.77 197	86.77 154	92.28 248

OMC-MVS		78.67 260	77.91 249	80.95 324	85.76 319	57.40 408	88.49 347	88.67 362	73.85 223	72.43 275	92.10 172	49.29 333	94.55 271	72.73 247	77.89 277	90.91 286

VPNet		78.82 254	77.53 256	82.70 264	84.52 347	66.44 175	93.93 94	92.23 157	80.46 76	72.60 267	88.38 272	49.18 334	93.13 331	72.47 251	63.97 393	88.55 318

CVMVSNet		74.04 339	74.27 310	73.33 427	85.33 327	43.94 484	89.53 324	88.39 371	54.33 456	70.37 300	90.13 240	49.17 335	84.05 458	61.83 365	79.36 263	91.99 258

v1921920		75.63 320	73.49 325	82.06 291	79.38 415	66.35 177	91.07 267	89.48 316	71.98 269	67.99 333	81.22 381	49.16 336	93.90 306	66.56 317	64.56 387	85.92 379

pm-mvs1		72.89 352	71.09 356	78.26 377	79.10 421	57.62 403	90.80 275	89.30 324	67.66 353	62.91 392	81.78 368	49.11 337	92.95 336	60.29 374	58.89 432	84.22 402

pmmvs4		73.92 341	71.81 351	80.25 339	79.17 418	65.24 210	87.43 367	87.26 397	67.64 355	63.46 384	83.91 343	48.96 338	91.53 392	62.94 356	65.49 373	83.96 403

TAPA-MVS	70.22 12	74.94 329	73.53 324	79.17 367	90.40 161	52.07 442	89.19 334	89.61 314	62.69 405	70.07 304	92.67 154	48.89 339	94.32 280	38.26 470	79.97 253	91.12 281
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
3Dnovator	73.91 6	82.69 168	80.82 188	88.31 29	89.57 177	71.26 26	92.60 171	94.39 65	78.84 126	67.89 338	92.48 159	48.42 340	98.52 34	68.80 290	94.40 38	95.15 97

CPTT-MVS		79.59 234	79.16 228	80.89 328	91.54 135	59.80 376	92.10 196	88.54 368	60.42 424	72.96 260	93.28 140	48.27 341	92.80 346	78.89 196	86.50 161	90.06 295

GBi-Net		75.65 318	73.83 320	81.10 318	88.85 200	65.11 214	90.01 308	90.32 277	70.84 306	67.04 351	80.25 396	48.03 342	91.54 389	59.80 377	69.34 341	86.64 351

test1		75.65 318	73.83 320	81.10 318	88.85 200	65.11 214	90.01 308	90.32 277	70.84 306	67.04 351	80.25 396	48.03 342	91.54 389	59.80 377	69.34 341	86.64 351

FMVSNet2		76.07 307	74.01 317	82.26 281	88.85 200	67.66 128	91.33 251	91.61 196	70.84 306	65.98 360	82.25 361	48.03 342	92.00 376	58.46 382	68.73 349	87.10 342

SSM_0407		79.09 247	77.21 264	84.75 181	88.50 214	66.98 158	89.21 332	87.03 399	67.99 348	74.12 245	89.32 255	47.98 345	95.29 234	71.23 264	79.52 258	91.98 259

SSM_0404		79.46 239	77.65 251	84.91 168	88.37 228	67.04 152	89.59 316	87.03 399	67.99 348	75.45 224	89.32 255	47.98 345	95.34 229	71.23 264	81.90 232	92.34 244

LFMVS		84.34 116	82.73 151	89.18 14	94.76 36	73.25 14	94.99 48	91.89 179	71.90 272	82.16 116	93.49 138	47.98 345	97.05 109	82.55 147	84.82 182	97.25 9

SDMVSNet		80.26 222	78.88 233	84.40 201	89.25 188	67.63 130	85.35 387	93.02 122	76.77 173	70.84 294	87.12 297	47.95 348	96.09 169	85.04 108	74.55 303	89.48 306

QAPM		79.95 230	77.39 261	87.64 39	89.63 176	71.41 24	93.30 131	93.70 89	65.34 380	67.39 348	91.75 190	47.83 349	98.96 19	57.71 385	89.81 116	92.54 238

HPM-MVS_fast		80.25 223	79.55 217	82.33 277	91.55 134	59.95 374	91.32 252	89.16 332	65.23 381	74.71 238	93.07 144	47.81 350	95.74 198	74.87 229	88.23 133	91.31 277

CANet_DTU		84.09 124	83.52 118	85.81 125	90.30 163	66.82 164	91.87 213	89.01 345	85.27 14	86.09 72	93.74 131	47.71 351	96.98 118	77.90 203	89.78 118	93.65 199

mamba_0408		76.22 304	73.37 327	84.77 178	88.50 214	66.98 158	58.80 498	86.18 413	69.12 335	74.12 245	89.01 263	47.50 352	95.35 227	67.57 306	79.52 258	91.98 259

SSM_04072		74.86 331	73.37 327	79.35 364	88.50 214	66.98 158	58.80 498	86.18 413	69.12 335	74.12 245	89.01 263	47.50 352	79.09 485	67.57 306	79.52 258	91.98 259

v1240		75.21 325	72.98 335	81.88 293	79.20 417	66.00 188	90.75 278	89.11 338	71.63 288	67.41 347	81.22 381	47.36 354	93.87 308	65.46 335	64.72 385	85.77 382

PEN-MVS		69.46 386	68.56 379	72.17 438	79.27 416	49.71 458	86.90 374	89.24 327	67.24 360	59.08 421	82.51 358	47.23 355	83.54 465	48.42 425	57.12 436	83.25 415

wanda-best-256-512		72.42 361	69.43 371	81.37 305	75.39 454	64.24 247	91.58 234	91.09 229	66.36 365	60.64 406	76.86 429	47.20 356	93.47 320	64.80 340	50.98 457	86.40 359

FE-blended-shiyan7		72.42 361	69.43 371	81.37 305	75.39 454	64.24 247	91.58 234	91.09 229	66.36 365	60.64 406	76.86 429	47.20 356	93.47 320	64.80 340	50.98 457	86.40 359

usedtu_blend_shiyan5		71.06 373	67.54 386	81.62 299	75.39 454	64.75 222	85.67 385	86.47 406	56.48 449	60.64 406	76.85 431	47.20 356	93.71 312	68.18 294	50.98 457	86.40 359

blended_shiyan6		72.26 363	69.26 374	81.27 310	75.24 458	64.00 257	91.37 246	91.06 235	66.12 369	60.34 412	76.75 432	46.82 359	93.45 323	64.61 342	50.98 457	86.37 362

KinetiMVS		81.43 192	80.11 202	85.38 146	86.60 293	65.47 206	92.90 151	93.54 97	75.33 196	77.31 200	90.39 225	46.81 360	96.75 135	71.65 262	86.46 162	93.93 186

blended_shiyan8		72.26 363	69.25 375	81.29 309	75.23 459	64.03 254	91.36 249	91.04 239	66.11 370	60.42 411	76.73 433	46.79 361	93.45 323	64.58 344	51.00 456	86.37 362

dmvs_re		76.93 292	75.36 294	81.61 300	87.78 253	60.71 355	80.00 445	87.99 385	79.42 110	69.02 317	89.47 252	46.77 362	94.32 280	63.38 352	74.45 306	89.81 299

CNLPA		74.31 336	72.30 345	80.32 335	91.49 136	61.66 330	90.85 273	80.72 454	56.67 448	63.85 381	90.64 218	46.75 363	90.84 397	53.79 401	75.99 298	88.47 320

dtuonly		74.56 334	73.92 318	76.48 398	77.15 444	57.27 410	85.09 390	81.23 450	71.37 296	67.61 343	89.65 250	46.68 364	83.84 462	68.79 291	77.69 280	88.33 323

114514_t		79.17 245	77.67 250	83.68 233	95.32 32	65.53 203	92.85 153	91.60 197	63.49 394	67.92 335	90.63 220	46.65 365	95.72 204	67.01 314	83.54 206	89.79 300

PS-CasMVS		69.86 383	69.13 376	72.07 440	80.35 403	50.57 453	87.02 372	89.75 305	67.27 357	59.19 420	82.28 360	46.58 366	82.24 477	50.69 412	59.02 431	83.39 414

DTE-MVSNet		68.46 395	67.33 388	71.87 442	77.94 437	49.00 463	86.16 383	88.58 366	66.36 365	58.19 426	82.21 362	46.36 367	83.87 461	44.97 446	55.17 443	82.73 422

test1111		80.84 209	80.02 204	83.33 245	87.87 248	60.76 351	92.62 168	86.86 403	77.86 146	75.73 217	91.39 202	46.35 368	94.70 261	72.79 245	88.68 130	94.52 143

ECVR-MVS		81.29 196	80.38 201	84.01 219	88.39 226	61.96 320	92.56 176	86.79 404	77.66 152	76.63 209	91.42 200	46.34 369	95.24 236	74.36 231	89.23 120	94.85 112

PMMVS		81.98 184	82.04 166	81.78 294	89.76 174	56.17 420	91.13 263	90.69 259	77.96 142	80.09 152	93.57 136	46.33 370	94.99 243	81.41 164	87.46 143	94.17 168

OPM-MVS		79.00 249	78.09 242	81.73 295	83.52 366	63.83 262	91.64 233	90.30 281	76.36 184	71.97 281	89.93 247	46.30 371	95.17 238	75.10 223	77.70 279	86.19 368
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BH-RMVSNet		79.46 239	77.65 251	84.89 169	91.68 130	65.66 197	93.55 117	88.09 383	72.93 244	73.37 257	91.12 213	46.20 372	96.12 167	56.28 391	85.61 172	92.91 225

FE-MVS		75.97 313	73.02 333	84.82 173	89.78 172	65.56 201	77.44 457	91.07 234	64.55 383	72.66 265	79.85 401	46.05 373	96.69 137	54.97 395	80.82 246	92.21 253

AstraMVS		80.66 213	79.79 211	83.28 249	85.07 337	61.64 331	92.19 191	90.58 265	79.40 111	74.77 236	90.18 231	45.93 374	95.61 213	83.04 140	76.96 291	92.60 235

TR-MVS		78.77 257	77.37 262	82.95 258	90.49 159	60.88 347	93.67 111	90.07 292	70.08 320	74.51 239	91.37 203	45.69 375	95.70 205	60.12 375	80.32 251	92.29 247

IterMVS-SCA-FT		71.55 370	69.97 365	76.32 400	81.48 388	60.67 357	87.64 365	85.99 416	66.17 368	59.50 417	78.88 408	45.53 376	83.65 463	62.58 360	61.93 411	84.63 401

SCA		75.82 316	72.76 337	85.01 163	86.63 292	70.08 43	81.06 434	89.19 330	71.60 289	70.01 305	77.09 426	45.53 376	90.25 403	60.43 372	73.27 315	94.68 130

IterMVS		72.65 359	70.83 357	78.09 379	82.17 380	62.96 295	87.64 365	86.28 409	71.56 291	60.44 410	78.85 409	45.42 378	86.66 443	63.30 354	61.83 412	84.65 399
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Syy-MVS		69.65 384	69.52 370	70.03 448	87.87 248	43.21 486	88.07 354	89.01 345	72.91 245	63.11 387	88.10 279	45.28 379	85.54 449	22.07 502	69.23 344	81.32 438

WB-MVSnew		77.14 288	76.18 284	80.01 346	86.18 306	63.24 287	91.26 254	94.11 74	71.72 282	73.52 256	87.29 295	45.14 380	93.00 334	56.98 388	79.42 261	83.80 406

Effi-MVS+-dtu		76.14 306	75.28 296	78.72 372	83.22 369	55.17 428	89.87 312	87.78 389	75.42 194	67.98 334	81.43 375	45.08 381	92.52 358	75.08 224	71.63 327	88.48 319

XVG-OURS-SEG-HR		74.70 333	73.08 332	79.57 360	78.25 433	57.33 409	80.49 437	87.32 394	63.22 398	68.76 324	90.12 242	44.89 382	91.59 386	70.55 273	74.09 310	89.79 300

gbinet_0.2-2-1-0.02		71.92 366	68.92 377	80.91 326	75.87 452	63.30 284	91.95 208	91.40 205	65.62 376	61.57 400	77.27 423	44.71 383	92.88 343	61.00 369	50.87 461	86.54 357

v7n		71.31 371	68.65 378	79.28 365	76.40 447	60.77 350	86.71 377	89.45 318	64.17 388	58.77 424	78.24 412	44.59 384	93.54 317	57.76 384	61.75 414	83.52 410

pmmvs5		73.35 346	71.52 353	78.86 371	78.64 428	60.61 359	91.08 264	86.90 401	67.69 352	63.32 385	83.64 344	44.33 385	90.53 400	62.04 363	66.02 369	85.46 389

OpenMVS	70.45 11	78.54 262	75.92 287	86.41 105	85.93 315	71.68 21	92.74 156	92.51 149	66.49 364	64.56 372	91.96 181	43.88 386	98.10 46	54.61 396	90.65 102	89.44 308

AdaColmap		78.94 251	77.00 268	84.76 180	96.34 18	65.86 194	92.66 167	87.97 387	62.18 408	70.56 296	92.37 162	43.53 387	97.35 87	64.50 345	82.86 212	91.05 282

tfpnnormal		70.10 379	67.36 387	78.32 375	83.45 367	60.97 346	88.85 340	92.77 134	64.85 382	60.83 405	78.53 410	43.52 388	93.48 319	31.73 491	61.70 416	80.52 447

mvsany_test1		68.77 391	68.56 379	69.39 451	73.57 465	45.88 479	80.93 435	60.88 501	59.65 430	71.56 287	90.26 230	43.22 389	75.05 489	74.26 233	62.70 403	87.25 341

test_djsdf		73.76 345	72.56 342	77.39 387	77.00 445	53.93 434	89.07 336	90.69 259	65.80 373	63.92 379	82.03 364	43.14 390	92.67 352	72.83 243	68.53 350	85.57 386

GA-MVS		78.33 266	76.23 282	84.65 190	83.65 364	66.30 179	91.44 238	90.14 290	76.01 186	70.32 301	84.02 341	42.50 391	94.72 255	70.98 267	77.00 290	92.94 224

PLC	68.80 14	75.23 324	73.68 323	79.86 352	92.93 86	58.68 392	90.64 285	88.30 376	60.90 421	64.43 376	90.53 221	42.38 392	94.57 266	56.52 389	76.54 294	86.33 364
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
D2MVS		73.80 342	72.02 348	79.15 369	79.15 419	62.97 294	88.58 346	90.07 292	72.94 243	59.22 419	78.30 411	42.31 393	92.70 351	65.59 333	72.00 325	81.79 435

SSC-MVS3.2		74.92 330	73.32 330	79.74 356	86.53 295	60.31 366	89.03 339	92.70 136	78.61 132	68.98 319	83.34 349	41.93 394	92.23 370	52.77 407	65.97 370	86.69 350

Fast-Effi-MVS+-dtu		75.04 327	73.37 327	80.07 343	80.86 392	59.52 381	91.20 260	85.38 423	71.90 272	65.20 366	84.84 329	41.46 395	92.97 335	66.50 320	72.96 318	87.73 329

sd_testset		77.08 290	75.37 293	82.20 283	89.25 188	62.11 317	82.06 424	89.09 339	76.77 173	70.84 294	87.12 297	41.43 396	95.01 242	67.23 311	74.55 303	89.48 306

LuminaMVS		78.14 269	76.66 272	82.60 268	80.82 394	64.64 228	89.33 328	90.45 268	68.25 346	74.73 237	85.51 322	41.15 397	94.14 289	78.96 194	80.69 249	89.04 309

MS-PatchMatch		77.90 276	76.50 274	82.12 287	85.99 311	69.95 47	91.75 225	92.70 136	73.97 220	62.58 395	84.44 335	41.11 398	95.78 195	63.76 350	92.17 73	80.62 446

our_test_3		68.29 397	64.69 405	79.11 370	78.92 422	64.85 221	88.40 349	85.06 426	60.32 426	52.68 450	76.12 439	40.81 399	89.80 415	44.25 448	55.65 441	82.67 427

XVG-OURS		74.25 337	72.46 344	79.63 358	78.45 431	57.59 405	80.33 439	87.39 391	63.86 390	68.76 324	89.62 251	40.50 400	91.72 382	69.00 287	74.25 308	89.58 303

IMVS_0404		78.11 270	76.29 281	83.59 236	88.54 209	64.75 222	84.63 394	90.80 253	76.73 175	61.16 402	90.18 231	40.17 401	91.58 387	73.47 235	80.95 240	94.43 154

VDD-MVS		83.06 159	81.81 172	86.81 71	90.86 153	67.70 127	95.40 31	91.50 201	75.46 192	81.78 118	92.34 163	40.09 402	97.13 107	86.85 92	82.04 228	95.60 67

DP-MVS		69.90 382	66.48 389	80.14 341	95.36 31	62.93 296	89.56 319	76.11 466	50.27 468	57.69 432	85.23 325	39.68 403	95.73 199	33.35 482	71.05 333	81.78 436

ppachtmachnet_test		67.72 401	63.70 413	79.77 355	78.92 422	66.04 187	88.68 344	82.90 448	60.11 428	55.45 438	75.96 440	39.19 404	90.55 399	39.53 465	52.55 452	82.71 424

ADS-MVSNet2		66.90 407	63.44 415	77.26 390	88.06 238	60.70 356	68.01 482	75.56 470	57.57 439	64.48 373	69.87 466	38.68 405	84.10 457	40.87 461	67.89 358	86.97 343

ADS-MVSNet		68.54 394	64.38 410	81.03 322	88.06 238	66.90 163	68.01 482	84.02 436	57.57 439	64.48 373	69.87 466	38.68 405	89.21 418	40.87 461	67.89 358	86.97 343

test_cas_vis1_n_1920		80.45 218	80.61 195	79.97 349	78.25 433	57.01 415	94.04 88	88.33 375	79.06 123	82.81 110	93.70 132	38.65 407	91.63 385	90.82 56	79.81 255	91.27 279

LPG-MVS_test		75.82 316	74.58 304	79.56 361	84.31 353	59.37 383	90.44 292	89.73 308	69.49 327	64.86 368	88.42 270	38.65 407	94.30 282	72.56 249	72.76 319	85.01 395

LGP-MVS_train				79.56 361	84.31 353	59.37 383		89.73 308	69.49 327	64.86 368	88.42 270	38.65 407	94.30 282	72.56 249	72.76 319	85.01 395

VDDNet		80.50 216	78.26 240	87.21 56	86.19 305	69.79 53	94.48 64	91.31 209	60.42 424	79.34 167	90.91 216	38.48 410	96.56 142	82.16 149	81.05 239	95.27 89

ACMP	71.68 10	75.58 321	74.23 311	79.62 359	84.97 339	59.64 378	90.80 275	89.07 341	70.39 315	62.95 391	87.30 294	38.28 411	93.87 308	72.89 242	71.45 330	85.36 391
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n_1920		81.66 188	82.01 168	80.64 330	82.24 379	55.09 429	94.76 56	86.87 402	81.67 53	84.40 91	94.63 101	38.17 412	94.67 262	91.98 43	83.34 208	92.16 255

UGNet		79.87 231	78.68 234	83.45 243	89.96 169	61.51 334	92.13 194	90.79 257	76.83 171	78.85 180	86.33 309	38.16 413	96.17 165	67.93 302	87.17 147	92.67 232
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
anonymousdsp		71.14 372	69.37 373	76.45 399	72.95 468	54.71 431	84.19 398	88.88 351	61.92 413	62.15 397	79.77 402	38.14 414	91.44 394	68.90 289	67.45 361	83.21 416

xiu_mvs_v1_base_debu		82.16 179	81.12 181	85.26 154	86.42 298	68.72 94	92.59 173	90.44 272	73.12 239	84.20 92	94.36 108	38.04 415	95.73 199	84.12 124	86.81 151	91.33 273

xiu_mvs_v1_base		82.16 179	81.12 181	85.26 154	86.42 298	68.72 94	92.59 173	90.44 272	73.12 239	84.20 92	94.36 108	38.04 415	95.73 199	84.12 124	86.81 151	91.33 273

xiu_mvs_v1_base_debi		82.16 179	81.12 181	85.26 154	86.42 298	68.72 94	92.59 173	90.44 272	73.12 239	84.20 92	94.36 108	38.04 415	95.73 199	84.12 124	86.81 151	91.33 273

PVSNet_0	68.08 15	71.81 367	68.32 383	82.27 279	84.68 341	62.31 313	88.68 344	90.31 280	75.84 187	57.93 431	80.65 390	37.85 418	94.19 287	69.94 276	29.05 503	90.31 293

Anonymous20231206		67.53 404	65.78 395	72.79 432	74.95 460	47.59 468	88.23 351	87.32 394	61.75 418	58.07 428	77.29 422	37.79 419	87.29 441	42.91 451	63.71 394	83.48 411

ACMM	69.62 13	74.34 335	72.73 339	79.17 367	84.25 355	57.87 399	90.36 297	89.93 299	63.17 400	65.64 363	86.04 313	37.79 419	94.10 291	65.89 326	71.52 329	85.55 387
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
cascas		78.18 267	75.77 289	85.41 141	87.14 271	69.11 78	92.96 145	91.15 222	66.71 362	70.47 297	86.07 311	37.49 421	96.48 149	70.15 275	79.80 256	90.65 288

LS3D		69.17 387	66.40 391	77.50 384	91.92 121	56.12 421	85.12 389	80.37 456	46.96 476	56.50 436	87.51 291	37.25 422	93.71 312	32.52 490	79.40 262	82.68 426

MDA-MVSNet_test_wron		63.78 426	60.16 430	74.64 415	78.15 435	60.41 363	83.49 406	84.03 435	56.17 452	39.17 493	71.59 461	37.22 423	83.24 469	42.87 453	48.73 465	80.26 451

YYNet1		63.76 427	60.14 431	74.62 416	78.06 436	60.19 370	83.46 408	83.99 439	56.18 451	39.25 492	71.56 462	37.18 424	83.34 467	42.90 452	48.70 466	80.32 450

FMVSNet5		68.04 399	65.66 398	75.18 409	84.43 351	57.89 398	83.54 404	86.26 410	61.83 415	53.64 447	73.30 449	37.15 425	85.08 453	48.99 421	61.77 413	82.56 428

test20.03		63.83 424	62.65 420	67.38 461	70.58 477	39.94 494	86.57 378	84.17 434	63.29 397	51.86 454	77.30 421	37.09 426	82.47 473	38.87 469	54.13 447	79.73 454

PVSNet	73.49 8	80.05 227	78.63 235	84.31 206	90.92 151	64.97 218	92.47 180	91.05 238	79.18 117	72.43 275	90.51 222	37.05 427	94.06 295	68.06 299	86.00 164	93.90 191

EU-MVSNet		64.01 423	63.01 417	67.02 462	74.40 463	38.86 498	83.27 410	86.19 412	45.11 483	54.27 442	81.15 384	36.91 428	80.01 484	48.79 424	57.02 437	82.19 432

dtuonlycased		63.47 428	62.08 424	67.64 459	73.22 467	52.55 439	86.25 382	79.10 460	65.40 377	49.47 467	67.33 476	36.80 429	82.37 475	53.47 404	47.68 468	68.01 489

Anonymous20231211		73.08 347	70.39 363	81.13 315	90.62 156	63.33 283	91.40 241	90.06 294	51.84 462	64.46 375	80.67 389	36.49 430	94.07 294	63.83 349	64.17 389	85.98 375

FMVSNet1		72.71 356	69.91 367	81.10 318	83.60 365	65.11 214	90.01 308	90.32 277	63.92 389	63.56 383	80.25 396	36.35 431	91.54 389	54.46 397	66.75 365	86.64 351

Anonymous20240529		76.84 295	74.15 314	84.88 170	91.02 147	64.95 219	93.84 103	91.09 229	53.57 457	73.00 259	87.42 292	35.91 432	97.32 89	69.14 286	72.41 324	92.36 243

WB-MVS		46.23 460	44.94 462	50.11 482	62.13 495	21.23 519	76.48 460	55.49 503	45.89 480	35.78 494	61.44 490	35.54 433	72.83 493	9.96 521	21.75 507	56.27 500

CMPMVS	48.56 21	66.77 409	64.41 409	73.84 424	70.65 476	50.31 455	77.79 456	85.73 420	45.54 481	44.76 482	82.14 363	35.40 434	90.14 409	63.18 355	74.54 305	81.07 441
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs6		67.57 403	64.76 404	76.00 403	72.82 470	53.37 436	88.71 343	86.78 405	53.19 458	57.58 433	78.03 415	35.33 435	92.41 362	55.56 393	54.88 445	82.21 431

PatchMatch-RL		72.06 365	69.98 364	78.28 376	89.51 180	55.70 425	83.49 406	83.39 445	61.24 419	63.72 382	82.76 354	34.77 436	93.03 333	53.37 405	77.59 281	86.12 372

LTVRE_ROB	59.60 19	66.27 411	63.54 414	74.45 418	84.00 358	51.55 445	67.08 486	83.53 442	58.78 435	54.94 440	80.31 394	34.54 437	93.23 329	40.64 463	68.03 354	78.58 466
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
SSC-MVS		44.51 462	43.35 464	47.99 486	61.01 498	18.90 521	74.12 468	54.36 504	43.42 490	34.10 498	60.02 493	34.42 438	70.39 496	9.14 523	19.57 508	54.68 501

Elysia		76.45 302	74.17 312	83.30 246	80.43 400	64.12 251	89.58 317	90.83 250	61.78 416	72.53 269	85.92 314	34.30 439	94.81 250	68.10 297	84.01 197	90.97 283

StellarMVS		76.45 302	74.17 312	83.30 246	80.43 400	64.12 251	89.58 317	90.83 250	61.78 416	72.53 269	85.92 314	34.30 439	94.81 250	68.10 297	84.01 197	90.97 283

UniMVSNet_ETH3D		72.74 355	70.53 362	79.36 363	78.62 429	56.64 417	85.01 391	89.20 329	63.77 391	64.84 370	84.44 335	34.05 441	91.86 379	63.94 348	70.89 334	89.57 304

FE-MVSNET2		66.80 408	64.06 411	75.03 410	69.84 478	57.11 411	86.57 378	88.57 367	67.94 350	50.97 460	72.16 458	33.79 442	87.55 438	53.94 400	52.74 449	80.45 448

F-COLMAP		70.66 374	68.44 381	77.32 388	86.37 303	55.91 423	88.00 356	86.32 408	56.94 446	57.28 434	88.07 281	33.58 443	92.49 359	51.02 410	68.37 351	83.55 408

pmmvs-eth3d		65.53 417	62.32 422	75.19 408	69.39 481	59.59 379	82.80 418	83.43 443	62.52 406	51.30 458	72.49 452	32.86 444	87.16 442	55.32 394	50.73 462	78.83 463

MDA-MVSNet-bldmvs		61.54 435	57.70 439	73.05 429	79.53 413	57.00 416	83.08 414	81.23 450	57.57 439	34.91 497	72.45 453	32.79 445	86.26 446	35.81 474	41.95 482	75.89 477

MIMVSNet		71.64 368	68.44 381	81.23 312	81.97 383	64.44 235	73.05 469	88.80 356	69.67 326	64.59 371	74.79 446	32.79 445	87.82 431	53.99 399	76.35 295	91.42 271

UnsupCasMVSNet_eth		65.79 414	63.10 416	73.88 423	70.71 475	50.29 456	81.09 433	89.88 301	72.58 252	49.25 468	74.77 447	32.57 447	87.43 440	55.96 392	41.04 484	83.90 405

N_pmnet		50.55 456	49.11 458	54.88 477	77.17 443	4.02 539	84.36 395	2.00 536	48.59 472	45.86 478	68.82 469	32.22 448	82.80 472	31.58 492	51.38 455	77.81 472

test_0402		64.54 420	61.09 427	74.92 413	84.10 357	60.75 352	87.95 357	79.71 458	52.03 460	52.41 451	77.20 424	32.21 449	91.64 384	23.14 500	61.03 420	72.36 485

DSMNet-mixed		56.78 449	54.44 452	63.79 466	63.21 492	29.44 510	64.43 489	64.10 497	42.12 493	51.32 457	71.60 460	31.76 450	75.04 490	36.23 472	65.20 379	86.87 348

MSDG		69.54 385	65.73 396	80.96 323	85.11 336	63.71 269	84.19 398	83.28 446	56.95 445	54.50 441	84.03 340	31.50 451	96.03 175	42.87 453	69.13 346	83.14 418

RPSCF		64.24 422	61.98 425	71.01 445	76.10 449	45.00 481	75.83 464	75.94 467	46.94 477	58.96 422	84.59 332	31.40 452	82.00 478	47.76 432	60.33 428	86.04 373

tt0805		73.07 348	70.73 360	80.07 343	78.37 432	57.05 413	87.78 361	92.18 164	61.23 420	67.04 351	86.49 306	31.35 453	94.58 264	65.06 338	67.12 362	88.57 317

jajsoiax		73.05 349	71.51 354	77.67 382	77.46 441	54.83 430	88.81 342	90.04 295	69.13 334	62.85 393	83.51 346	31.16 454	92.75 348	70.83 268	69.80 337	85.43 390

MVS-HIRNet		60.25 442	55.55 449	74.35 419	84.37 352	56.57 419	71.64 473	74.11 474	34.44 496	45.54 480	42.24 509	31.11 455	89.81 413	40.36 464	76.10 297	76.67 476

SixPastTwentyTwo		64.92 418	61.78 426	74.34 420	78.74 426	49.76 457	83.42 409	79.51 459	62.86 402	50.27 462	77.35 420	30.92 456	90.49 401	45.89 440	47.06 470	82.78 420

FE-MVSNET		60.52 440	57.18 444	70.53 446	67.53 484	50.68 452	82.62 420	76.28 465	59.33 433	46.71 474	71.10 465	30.54 457	83.61 464	33.15 484	47.37 469	77.29 474

mmtdpeth		68.33 396	66.37 392	74.21 422	82.81 375	51.73 443	84.34 396	80.42 455	67.01 361	71.56 287	68.58 470	30.52 458	92.35 366	75.89 217	36.21 492	78.56 467

KD-MVS_self_test		60.87 438	58.60 436	67.68 458	66.13 488	39.93 495	75.63 466	84.70 429	57.32 443	49.57 465	68.45 471	29.55 459	82.87 470	48.09 426	47.94 467	80.25 452

mvs_tets		72.71 356	71.11 355	77.52 383	77.41 442	54.52 432	88.45 348	89.76 304	68.76 341	62.70 394	83.26 350	29.49 460	92.71 349	70.51 274	69.62 339	85.34 392

Anonymous202405211		77.96 273	75.33 295	85.87 122	93.73 59	64.52 230	94.85 53	85.36 424	62.52 406	76.11 214	90.18 231	29.43 461	97.29 91	68.51 293	77.24 289	95.81 60

K. test v3		63.09 429	59.61 433	73.53 426	76.26 448	49.38 462	83.27 410	77.15 464	64.35 385	47.77 473	72.32 456	28.73 462	87.79 432	49.93 417	36.69 491	83.41 413

UnsupCasMVSNet_bld		61.60 434	57.71 438	73.29 428	68.73 482	51.64 444	78.61 450	89.05 343	57.20 444	46.11 475	61.96 488	28.70 463	88.60 421	50.08 416	38.90 489	79.63 455

lessismore_v0				73.72 425	72.93 469	47.83 467		61.72 500		45.86 478	73.76 448	28.63 464	89.81 413	47.75 433	31.37 499	83.53 409

MVStest1		51.35 455	46.89 459	64.74 464	65.06 490	51.10 449	67.33 485	72.58 479	30.20 500	35.30 495	74.82 445	27.70 465	69.89 497	24.44 499	24.57 505	73.22 481

new-patchmatchnet		59.30 445	56.48 447	67.79 457	65.86 489	44.19 482	82.47 422	81.77 449	59.94 429	43.65 487	66.20 478	27.67 466	81.68 479	39.34 466	41.40 483	77.50 473

ACMH	63.93 17	68.62 392	64.81 403	80.03 345	85.22 332	63.25 286	87.72 362	84.66 430	60.83 422	51.57 456	79.43 406	27.29 467	94.96 244	41.76 457	64.84 382	81.88 434
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OurMVSNet-221017-0		64.68 419	62.17 423	72.21 437	76.08 450	47.35 469	80.67 436	81.02 452	56.19 450	51.60 455	79.66 404	27.05 468	88.56 422	53.60 403	53.63 448	80.71 445

ACMH+	65.35 16	67.65 402	64.55 406	76.96 395	84.59 345	57.10 412	88.08 353	80.79 453	58.59 437	53.00 449	81.09 385	26.63 469	92.95 336	46.51 436	61.69 417	80.82 443

OpenMVS_ROB	61.12 18	66.39 410	62.92 418	76.80 397	76.51 446	57.77 400	89.22 331	83.41 444	55.48 453	53.86 445	77.84 416	26.28 470	93.95 304	34.90 477	68.76 348	78.68 465

tt0320		61.85 432	57.45 441	75.03 410	77.49 440	57.60 404	82.74 419	73.65 476	43.65 489	53.65 446	68.18 472	25.47 471	88.66 419	45.56 442	46.68 472	78.81 464

test_fmvs1		74.07 338	73.69 322	75.22 407	78.91 424	47.34 470	89.06 338	74.69 473	63.68 393	79.41 166	91.59 198	24.36 472	87.77 433	85.22 105	76.26 296	90.55 291

COLMAP_ROB	57.96 20	62.98 430	59.65 432	72.98 430	81.44 389	53.00 438	83.75 403	75.53 471	48.34 474	48.81 470	81.40 377	24.14 473	90.30 402	32.95 485	60.52 425	75.65 478
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet1		60.16 443	57.33 442	68.67 454	69.71 479	44.13 483	78.92 449	84.21 433	55.05 454	44.63 483	71.85 459	23.91 474	81.54 480	32.63 489	55.03 444	80.35 449

testgi		64.48 421	62.87 419	69.31 452	71.24 471	40.62 492	85.49 386	79.92 457	65.36 379	54.18 443	83.49 347	23.74 475	84.55 455	41.60 458	60.79 423	82.77 421

tt0320-xc		61.51 436	56.89 445	75.37 406	78.50 430	58.61 393	82.61 421	71.27 486	44.31 486	53.17 448	68.03 474	23.38 476	88.46 424	47.77 431	43.00 481	79.03 461

ITE_SJBPF				70.43 447	74.44 462	47.06 473		77.32 463	60.16 427	54.04 444	83.53 345	23.30 477	84.01 459	43.07 450	61.58 418	80.21 453

sc_t1		63.81 425	59.39 434	77.10 391	77.62 439	56.03 422	84.32 397	73.56 477	46.66 479	58.22 425	73.06 450	23.28 478	90.62 398	50.93 411	46.84 471	84.64 400

mvs5depth		61.03 437	57.65 440	71.18 443	67.16 486	47.04 474	72.74 470	77.49 462	57.47 442	60.52 409	72.53 451	22.84 479	88.38 425	49.15 420	38.94 488	78.11 470

EG-PatchMatch MVS		68.55 393	65.41 400	77.96 380	78.69 427	62.93 296	89.86 313	89.17 331	60.55 423	50.27 462	77.73 418	22.60 480	94.06 295	47.18 434	72.65 321	76.88 475

tmp_tt		22.26 479	23.75 481	17.80 504	5.23 544	12.06 526	35.26 509	39.48 515	2.82 527	18.94 508	44.20 508	22.23 481	24.64 522	36.30 471	9.31 520	16.69 524

USDC		67.43 406	64.51 407	76.19 401	77.94 437	55.29 427	78.38 452	85.00 427	73.17 237	48.36 471	80.37 393	21.23 482	92.48 360	52.15 408	64.02 392	80.81 444

Anonymous20240521		62.09 431	59.08 435	71.10 444	67.19 485	48.72 464	83.91 400	85.23 425	50.38 467	47.84 472	71.22 464	20.74 483	85.51 451	46.47 437	58.75 433	79.06 459

test_vis1_n		71.63 369	70.73 360	74.31 421	69.63 480	47.29 471	86.91 373	72.11 481	63.21 399	75.18 228	90.17 237	20.40 484	85.76 448	84.59 116	74.42 307	89.87 298

XVG-ACMP-BASELINE		68.04 399	65.53 399	75.56 404	74.06 464	52.37 440	78.43 451	85.88 417	62.03 411	58.91 423	81.21 383	20.38 485	91.15 396	60.69 371	68.18 352	83.16 417

test_fmvs1_n		72.69 358	71.92 349	74.99 412	71.15 473	47.08 472	87.34 369	75.67 468	63.48 395	78.08 190	91.17 212	20.16 486	87.87 430	84.65 114	75.57 300	90.01 297

AllTest		61.66 433	58.06 437	72.46 434	79.57 411	51.42 447	80.17 442	68.61 490	51.25 464	45.88 476	81.23 379	19.86 487	86.58 444	38.98 467	57.01 438	79.39 456

TestCases				72.46 434	79.57 411	51.42 447		68.61 490	51.25 464	45.88 476	81.23 379	19.86 487	86.58 444	38.98 467	57.01 438	79.39 456

usedtu_dtu_shiyan2		57.76 447	53.69 453	69.95 449	57.60 501	41.80 488	83.50 405	83.67 441	45.26 482	43.79 486	62.82 485	17.63 489	85.93 447	42.56 456	46.40 474	82.12 433

test_vis1_rt		59.09 446	57.31 443	64.43 465	68.44 483	46.02 478	83.05 416	48.63 510	51.96 461	49.57 465	63.86 483	16.30 490	80.20 483	71.21 266	62.79 402	67.07 492

pmmvs3		55.51 450	51.50 456	67.53 460	57.90 500	50.93 451	80.37 438	73.66 475	40.63 494	44.15 485	64.75 481	16.30 490	78.97 486	44.77 447	40.98 486	72.69 483

test_fmvs2		65.78 415	64.84 402	68.60 455	66.54 487	41.71 489	83.27 410	69.81 488	54.38 455	67.91 336	84.54 334	15.35 492	81.22 481	75.65 219	66.16 368	82.88 419

TDRefinement		55.28 451	51.58 455	66.39 463	59.53 499	46.15 477	76.23 461	72.80 478	44.60 484	42.49 489	76.28 438	15.29 493	82.39 474	33.20 483	43.75 478	70.62 487

new_pmnet		49.31 457	46.44 460	57.93 472	62.84 493	40.74 491	68.47 481	62.96 499	36.48 495	35.09 496	57.81 494	14.97 494	72.18 494	32.86 487	46.44 473	60.88 497

TinyColmap		60.32 441	56.42 448	72.00 441	78.78 425	53.18 437	78.36 453	75.64 469	52.30 459	41.59 491	75.82 442	14.76 495	88.35 426	35.84 473	54.71 446	74.46 479

EGC-MVSNET		42.35 463	38.09 466	55.11 476	74.57 461	46.62 475	71.63 474	55.77 502	0.04 557	0.24 559	62.70 486	14.24 496	74.91 491	17.59 508	46.06 475	43.80 503

LF4IMVS		54.01 453	52.12 454	59.69 471	62.41 494	39.91 496	68.59 480	68.28 492	42.96 491	44.55 484	75.18 443	14.09 497	68.39 499	41.36 460	51.68 453	70.78 486

ttmdpeth		53.34 454	49.96 457	63.45 467	62.07 496	40.04 493	72.06 471	65.64 495	42.54 492	51.88 453	77.79 417	13.94 498	76.48 488	32.93 486	30.82 502	73.84 480

PM-MVS		59.40 444	56.59 446	67.84 456	63.63 491	41.86 487	76.76 458	63.22 498	59.01 434	51.07 459	72.27 457	11.72 499	83.25 468	61.34 366	50.28 464	78.39 468

mvsany_test3		48.86 458	46.35 461	56.41 473	46.00 509	31.67 506	62.26 491	47.25 511	43.71 488	45.54 480	68.15 473	10.84 500	64.44 508	57.95 383	35.44 496	73.13 482

ambc				69.61 450	61.38 497	41.35 490	49.07 506	85.86 419		50.18 464	66.40 477	10.16 501	88.14 428	45.73 441	44.20 477	79.32 458

FPMVS		45.64 461	43.10 465	53.23 480	51.42 506	36.46 500	64.97 488	71.91 482	29.13 501	27.53 503	61.55 489	9.83 502	65.01 506	16.00 513	55.58 442	58.22 499

ANet_high		40.27 467	35.20 470	55.47 475	34.74 519	34.47 503	63.84 490	71.56 484	48.42 473	18.80 509	41.08 511	9.52 503	64.45 507	20.18 503	8.66 521	67.49 491

test_method		38.59 468	35.16 471	48.89 484	54.33 502	21.35 518	45.32 508	53.71 505	7.41 520	28.74 501	51.62 497	8.70 504	52.87 511	33.73 480	32.89 498	72.47 484

EMVS		23.76 478	23.20 482	25.46 499	41.52 515	16.90 523	60.56 494	38.79 517	14.62 513	8.99 528	20.24 530	7.35 505	45.82 515	7.25 527	9.46 519	13.64 527

test_f		46.58 459	43.45 463	55.96 474	45.18 510	32.05 505	61.18 492	49.49 509	33.39 497	42.05 490	62.48 487	7.00 506	65.56 504	47.08 435	43.21 480	70.27 488

test_fmvs3		56.82 448	54.86 451	62.69 470	53.59 503	35.47 501	75.87 463	65.64 495	43.91 487	55.10 439	71.43 463	6.91 507	74.40 492	68.64 292	52.63 450	78.20 469

E-PMN		24.61 476	24.00 480	26.45 496	43.74 512	18.44 522	60.86 493	39.66 514	15.11 512	9.53 526	22.10 527	6.52 508	46.94 514	8.31 524	10.14 518	13.98 525

DeepMVS_CX				34.71 494	51.45 505	24.73 514		28.48 520	31.46 499	17.49 513	52.75 496	5.80 509	42.60 517	18.18 506	19.42 509	36.81 510

Gipuma		34.91 470	31.44 473	45.30 487	70.99 474	39.64 497	19.85 519	72.56 480	20.10 508	16.16 515	21.47 528	5.08 510	71.16 495	13.07 515	43.70 479	25.08 520
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
APD_test1		40.50 465	37.31 468	50.09 483	51.88 504	35.27 502	59.45 496	52.59 506	21.64 506	26.12 504	57.80 495	4.56 511	66.56 502	22.64 501	39.09 487	48.43 502

LCM-MVSNet		40.54 464	35.79 469	54.76 478	36.92 517	30.81 507	51.41 503	69.02 489	22.07 505	24.63 505	45.37 502	4.56 511	65.81 503	33.67 481	34.50 497	67.67 490

PMMVS2		37.93 469	33.61 472	50.92 481	46.31 508	24.76 513	60.55 495	50.05 507	28.94 502	20.93 507	47.59 498	4.41 513	65.13 505	25.14 498	18.55 510	62.87 495

VLMVS		13.23 489	13.55 490	12.28 510	12.68 532	2.77 543	12.60 522	3.80 530	0.44 539	17.98 512	44.70 506	4.14 514	6.39 532	12.99 516	12.66 515	27.68 516

test_vis3_rt		40.46 466	37.79 467	48.47 485	44.49 511	33.35 504	66.56 487	32.84 518	32.39 498	29.65 499	39.13 515	3.91 515	68.65 498	50.17 414	40.99 485	43.40 504

VLMVS_CLIP		19.60 482	19.74 484	19.17 503	13.13 530	5.80 533	23.18 515	23.62 521	3.86 523	24.51 506	44.74 505	2.91 516	29.01 519	19.90 504	21.84 506	22.70 522

testf1		32.77 473	29.47 475	42.67 491	41.89 513	30.81 507	52.07 501	43.45 512	15.45 509	18.52 510	44.82 503	2.12 517	58.38 509	16.05 511	30.87 500	38.83 507

APD_test2		32.77 473	29.47 475	42.67 491	41.89 513	30.81 507	52.07 501	43.45 512	15.45 509	18.52 510	44.82 503	2.12 517	58.38 509	16.05 511	30.87 500	38.83 507

PMVS	26.43 22	31.84 475	28.16 478	42.89 490	25.87 523	27.58 511	50.92 505	49.78 508	21.37 507	14.17 518	40.81 512	2.01 519	66.62 501	9.61 522	38.88 490	34.49 512
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVS_clip		10.33 492	11.48 494	6.89 514	13.99 529	4.67 536	11.14 523	0.96 548	1.27 531	14.61 517	35.92 517	1.90 520	2.27 539	11.90 519	11.60 516	13.74 526

ArgMatch-Sym		33.10 472	29.80 474	43.01 489	37.34 516	24.00 515	51.27 504	13.51 523	26.37 503	28.91 500	61.40 491	1.65 521	43.37 516	34.16 479	13.61 513	61.66 496

ArgMatch-SfM		33.21 471	29.25 477	45.06 488	35.86 518	22.89 516	48.07 507	16.80 522	23.93 504	27.57 502	61.10 492	1.59 522	47.14 513	34.29 478	14.08 512	65.16 493

MVE	24.84 23	24.35 477	19.77 483	38.09 493	34.56 520	26.92 512	26.57 511	38.87 516	11.73 516	11.37 522	27.44 522	1.37 523	50.42 512	11.41 520	14.60 511	36.93 509
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PDCNetPlus		17.19 485	15.58 487	22.00 500	25.94 522	10.36 529	23.05 516	5.04 528	12.02 515	10.87 524	39.50 514	0.88 524	23.24 523	18.38 505	4.57 529	32.39 514

wuyk23d		11.30 491	10.95 495	12.33 509	48.05 507	19.89 520	25.89 513	1.92 539	3.58 524	3.12 534	1.37 557	0.64 525	15.77 528	6.23 529	7.77 522	1.35 541

DenseAffine		21.45 480	18.65 485	29.86 495	28.31 521	16.04 524	32.25 510	6.12 526	15.38 511	16.38 514	44.57 507	0.55 526	32.44 518	16.82 509	7.46 523	41.09 505

RoMa-SfM		18.71 483	16.37 486	25.74 498	19.88 525	12.86 525	26.27 512	3.78 531	13.07 514	15.56 516	45.71 501	0.48 527	28.39 520	16.22 510	6.37 524	35.97 511

LoFTR		18.06 484	15.31 488	26.33 497	21.95 524	10.94 527	21.35 517	12.80 524	6.90 521	12.24 520	41.28 510	0.46 528	27.67 521	7.81 525	12.96 514	40.38 506

ALIKED-LG		4.67 501	4.76 505	4.39 515	11.74 533	4.58 537	8.52 526	2.37 534	1.12 532	3.02 535	10.43 532	0.40 529	4.25 535	0.52 542	4.70 528	4.35 531

MASt3R-SfM		8.20 496	8.57 499	7.11 513	5.75 541	3.12 542	9.54 525	3.21 532	2.39 530	9.18 527	34.80 519	0.37 530	5.21 534	6.46 528	5.41 525	12.99 529

RoMa-HiRes		13.29 488	12.09 492	16.86 505	12.76 531	7.74 531	17.91 521	2.10 535	8.64 518	11.87 521	39.11 516	0.36 531	17.55 526	12.17 517	3.91 532	25.30 519

SP-DiffGlue		2.24 507	2.34 510	1.94 522	1.88 561	1.08 551	3.10 536	1.13 543	0.55 535	2.52 537	7.60 537	0.33 532	0.99 545	1.25 535	2.70 537	3.76 536

ALIKED-NN		4.04 504	4.13 507	3.78 517	10.26 535	4.26 538	7.33 529	1.98 538	0.76 534	2.52 537	9.08 535	0.32 533	3.67 537	0.44 544	4.45 530	3.40 538

DKM		16.33 486	14.55 489	21.65 501	19.49 526	10.79 528	24.23 514	2.86 533	10.86 517	13.52 519	40.31 513	0.32 533	21.73 525	14.27 514	5.12 526	32.43 513

MatchFormer		14.02 487	12.22 491	19.42 502	17.64 527	8.79 530	19.96 518	10.04 525	4.23 522	10.54 525	32.75 520	0.31 535	22.88 524	4.03 532	10.48 517	26.57 517

ALIKED-MNN		4.24 503	4.26 506	4.20 516	10.96 534	4.68 535	7.92 527	2.00 536	0.81 533	2.44 540	9.09 534	0.30 536	4.03 536	0.46 543	4.36 531	3.88 534

SP-LightGlue		2.23 508	2.31 511	1.99 519	5.90 539	1.01 553	4.31 532	1.04 545	0.50 537	1.20 542	4.36 539	0.28 537	1.06 542	0.64 538	2.57 538	3.91 532

SP-SuperGlue		2.21 509	2.29 512	1.97 520	5.76 540	1.01 553	4.31 532	1.06 544	0.50 537	1.22 541	4.35 540	0.28 537	1.04 544	0.64 538	2.52 539	3.86 535

SP-NN		2.08 511	2.16 514	1.87 523	5.30 543	0.91 559	4.18 535	0.96 548	0.43 540	1.09 544	4.20 542	0.25 539	1.06 542	0.60 541	2.38 541	3.63 537

GLUNet-SfM		8.91 493	6.39 502	16.47 506	9.50 536	4.77 534	5.87 531	5.53 527	2.45 528	6.66 530	22.23 526	0.25 539	15.78 527	2.84 533	2.14 543	28.86 515

DKM-HiRes		12.72 490	11.70 493	15.79 507	14.70 528	7.68 532	18.04 520	1.85 540	8.12 519	11.31 523	35.19 518	0.24 541	14.23 530	12.15 518	3.71 533	25.48 518

SP-MNN		2.16 510	2.22 513	1.97 520	5.52 542	0.92 558	4.28 534	1.01 546	0.41 541	1.13 543	4.35 540	0.23 542	1.09 541	0.61 540	2.45 540	3.91 532

XFeat-MNN		2.31 506	2.37 509	2.13 518	1.47 562	0.97 557	3.08 537	1.31 541	0.53 536	2.60 536	7.72 536	0.22 543	2.31 538	1.02 536	3.40 534	3.10 539

XFeat-NN		1.98 512	2.09 515	1.67 524	1.35 563	0.77 562	2.62 538	0.97 547	0.41 541	2.46 539	6.79 538	0.19 544	1.75 540	0.84 537	3.18 535	2.48 540

MVS_baseline		3.15 505	3.66 508	1.62 525	2.62 560	0.05 566	0.90 553	0.14 565	0.02 559	4.44 533	18.48 531	0.16 545	0.00 562	1.30 534	4.85 527	4.80 530

ELoFTR		8.49 494	6.65 501	14.00 508	5.91 538	3.43 541	7.42 528	4.01 529	2.94 526	6.41 531	25.06 523	0.11 546	15.41 529	5.10 531	2.92 536	23.17 521

SIFT-NN		1.43 513	1.51 516	1.19 526	4.60 546	1.57 545	2.30 539	0.51 551	0.34 543	0.74 545	2.84 543	0.08 547	0.84 546	0.13 546	2.07 544	1.15 542

SIFT-NN-UMatch		1.16 518	1.23 521	0.96 531	3.23 555	1.06 552	1.93 542	0.42 554	0.33 545	0.53 550	2.63 545	0.07 548	0.77 550	0.11 551	1.79 548	1.05 546

SIFT-NN-NCMNet		1.29 515	1.36 518	1.08 528	3.95 549	1.39 547	2.05 541	0.49 553	0.33 545	0.63 548	2.62 547	0.07 548	0.81 548	0.12 548	2.02 545	1.05 546

SIFT-NN-CMatch		1.18 517	1.24 520	1.01 530	3.44 553	1.19 550	1.78 544	0.42 554	0.33 545	0.64 546	2.63 545	0.07 548	0.77 550	0.12 548	1.73 549	1.08 544

SIFT-NN-PointCN		1.06 521	1.12 524	0.88 533	2.98 556	0.84 561	1.67 546	0.37 558	0.30 553	0.54 549	2.38 551	0.07 548	0.72 554	0.11 551	1.64 550	1.07 545

SIFT-MNN		1.35 514	1.42 517	1.14 527	4.26 547	1.44 546	2.10 540	0.51 551	0.34 543	0.64 546	2.76 544	0.07 548	0.83 547	0.13 546	1.98 546	1.15 542

SIFT-UM-Cal		1.01 523	1.09 526	0.77 536	3.43 554	0.85 560	1.49 548	0.29 562	0.31 552	0.42 555	2.34 552	0.06 553	0.69 556	0.10 555	1.37 554	0.77 554

SIFT-NCM-Cal		1.23 516	1.30 519	1.04 529	4.06 548	1.29 548	1.92 543	0.42 554	0.33 545	0.45 553	2.46 550	0.06 553	0.81 548	0.10 555	1.89 547	1.02 548

SIFT-CM-Cal		1.03 522	1.10 525	0.85 535	3.54 552	1.01 553	1.42 549	0.32 560	0.32 550	0.44 554	2.30 553	0.06 553	0.71 555	0.09 557	1.37 554	0.82 552

SIFT-UMatch		1.11 520	1.18 523	0.87 534	3.66 551	1.00 556	1.70 545	0.35 559	0.32 550	0.46 552	2.50 549	0.06 553	0.75 553	0.11 551	1.51 552	0.87 551

SIFT-ConvMatch		1.15 519	1.22 522	0.96 531	3.82 550	1.20 549	1.64 547	0.38 557	0.33 545	0.52 551	2.53 548	0.06 553	0.76 552	0.11 551	1.59 551	0.91 549

PMatch-SfM		8.29 495	7.44 500	10.83 511	6.92 537	3.67 540	9.75 524	1.15 542	3.49 525	6.97 529	28.70 521	0.04 558	8.89 531	7.67 526	2.24 542	19.92 523

SIFT-PCN-Cal		0.88 524	0.93 528	0.70 537	2.93 557	0.60 564	1.22 551	0.27 563	0.28 554	0.36 556	2.00 554	0.04 558	0.61 558	0.09 557	1.23 557	0.89 550

SIFT-NCMNet		0.73 526	0.80 529	0.54 539	2.66 559	0.54 565	1.00 552	0.16 564	0.28 554	0.32 558	1.65 556	0.04 558	0.51 559	0.07 560	0.98 558	0.58 555

SIFT-PointCN		0.88 524	0.94 527	0.69 538	2.88 558	0.61 563	1.32 550	0.30 561	0.28 554	0.36 556	1.93 555	0.04 558	0.62 557	0.09 557	1.26 556	0.82 552

PMatch-Up-SfM		6.11 500	5.72 504	7.28 512	5.02 545	2.48 544	7.03 530	0.71 550	2.41 529	5.37 532	23.67 524	0.03 562	5.84 533	5.77 530	1.48 553	13.50 528

test123		6.92 499	9.21 498	0.08 540	0.03 565	0.05 566	81.65 428	0.01 567	0.02 559	0.14 561	0.85 559	0.03 562	0.02 560	0.12 548	0.00 560	0.16 556

testmvs		7.23 498	9.62 497	0.06 541	0.04 564	0.02 568	84.98 392	0.02 566	0.03 558	0.18 560	1.21 558	0.01 564	0.02 560	0.14 545	0.01 559	0.13 557

mmdepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 560	0.00 558

monomultidepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 560	0.00 558

test_blank		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 560	0.00 558

uanet_test		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 560	0.00 558

DCPMVS		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 560	0.00 558

sosnet-low-res		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 560	0.00 558

sosnet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 560	0.00 558

uncertanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 560	0.00 558

Regformer		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 560	0.00 558

ab-mvs-re		7.91 497	10.55 496	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	94.95 90	0.00 565	0.00 562	0.00 561	0.00 560	0.00 558

uanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 560	0.00 558

Meshroom													0.00 562
: In preparation.
AliceVision / Meshro													0.00 562
: In preparation.
AliceVision_Meshroom													0.00 562
: In preparation.
PatchmatchNet2					0.00 566	56.61 418	85.20 388	78.52 461	49.54 470
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														31.49 495	51.52 454	77.88 471
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													82.83 471
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
aaatest				87.42 49	94.76 36	67.28 140	94.47 65	94.87 34	73.09 242	91.27 25	96.95 19		98.98 17	91.55 46	94.28 39	95.99 50

WAC-MVS						49.45 460								31.56 493

FOURS1					93.95 52	61.77 326	93.96 92	91.92 176	62.14 410	86.57 66

MSC_two_6792asdad				89.60 10	97.31 4	73.22 15		95.05 31					99.07 14	92.01 41	94.77 28	96.51 26

No_MVS				89.60 10	97.31 4	73.22 15		95.05 31					99.07 14	92.01 41	94.77 28	96.51 26

eth-test2					0.00 566

eth-test					0.00 566

IU-MVS					96.46 12	69.91 48		95.18 25	80.75 70	95.28 2				92.34 38	95.36 14	96.47 30

save fliter					93.84 55	67.89 120	95.05 42	92.66 141	78.19 138

test_0728_SECOND				88.70 19	96.45 13	70.43 39	96.64 10	94.37 66					99.15 3	91.91 44	94.90 22	96.51 26

GSMVS																94.68 130

test_part2					96.29 21	68.16 113				90.78 28

MTGPA								92.23 157

MTMP							93.77 107	32.52 519

gm-plane-assit					88.42 224	67.04 152			78.62 131		91.83 187		97.37 85	76.57 211

test9_res														89.41 60	94.96 19	95.29 86

agg_prior2														86.41 94	94.75 32	95.33 81

agg_prior					94.16 49	66.97 161		93.31 108		84.49 90			96.75 135

test_prior4						67.18 147	93.92 96

test_prior				86.42 104	94.71 41	67.35 139		93.10 120					96.84 132			95.05 103

旧先验2							92.00 205		59.37 432	87.54 58			93.47 320	75.39 221

新几何2							91.41 239

无先验							92.71 158	92.61 146	62.03 411				97.01 113	66.63 316		93.97 183

原ACMM2							92.01 202

testdata2													96.09 169	61.26 367

testdata1							89.21 332		77.55 156

plane_prior7					86.94 282	61.51 334

plane_prior5								91.31 209					95.55 219	76.74 207	78.53 274	88.39 321

plane_prior4											89.14 260

plane_prior3						61.95 321			79.09 120	72.53 269

plane_prior2							93.13 136		78.81 127

plane_prior1					87.15 270

plane_prior						62.42 308	93.85 100		79.38 112						78.80 271

n2								0.00 568

nn								0.00 568

door-mid								66.01 494

test11								93.01 123

door								66.57 493

HQP5-MVS						63.66 274

HQP-NCC					87.54 257		94.06 84		79.80 94	74.18 241

ACMP_Plane					87.54 257		94.06 84		79.80 94	74.18 241

BP-MVS														77.63 204

HQP4-MVS										74.18 241			95.61 213			88.63 315

HQP3-MVS								91.70 193							78.90 269

NP-MVS					87.41 260	63.04 292					90.30 228

ACMMP++_ref															71.63 327

ACMMP++															69.72 338

High-resolution multi-view benchmark