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.

thres100view900		78.37 260	77.01 263	82.46 266	91.89 122	63.21 285	91.19 258	96.33 1	72.28 258	70.45 295	87.89 281	60.31 172	95.32 227	45.16 439	77.58 278	88.83 307

thres600view7		78.00 267	76.66 268	82.03 288	91.93 118	63.69 268	91.30 250	96.33 1	72.43 253	70.46 294	87.89 281	60.31 172	94.92 244	42.64 451	76.64 289	87.48 329

thres200		79.66 229	78.33 234	83.66 231	92.54 98	65.82 192	93.06 136	96.31 3	74.90 200	73.30 254	88.66 263	59.67 183	95.61 210	47.84 426	78.67 268	89.56 301

tfpn200view9		78.79 252	77.43 253	82.88 255	92.21 104	64.49 227	92.05 197	96.28 4	73.48 229	71.75 280	88.26 272	60.07 177	95.32 227	45.16 439	77.58 278	88.83 307

thres400		78.68 254	77.43 253	82.43 267	92.21 104	64.49 227	92.05 197	96.28 4	73.48 229	71.75 280	88.26 272	60.07 177	95.32 227	45.16 439	77.58 278	87.48 329

MM		90.87 2	91.52 2	88.92 16	92.12 108	71.10 29	97.02 3	96.04 6	88.70 2	91.57 20	96.19 49	70.12 50	98.91 22	96.83 2	95.06 17	96.76 16

VNet		86.20 66	85.65 78	87.84 32	93.92 53	69.99 41	95.73 23	95.94 7	78.43 132	86.00 71	93.07 142	58.22 212	97.00 113	85.22 103	84.33 187	96.52 24

baseline2		83.68 137	83.42 124	84.48 196	87.37 258	66.00 184	90.06 303	95.93 8	79.71 95	69.08 311	90.39 222	77.92 7	96.28 156	78.91 191	81.38 234	91.16 276

testing222		85.18 88	84.69 96	86.63 81	92.91 85	69.91 45	92.61 166	95.80 9	80.31 79	80.38 143	92.27 162	68.73 57	95.19 234	75.94 212	83.27 208	94.81 118

TestfortrainingZip				90.29 2	97.24 8	73.67 10	94.47 64	95.75 10	69.78 321	95.97 1	98.23 1	80.55 5	99.42 1		93.26 58	97.76 2

BP-MVS1		86.54 57	86.68 57	86.13 111	87.80 248	67.18 143	92.97 141	95.62 11	79.92 88	82.84 106	94.14 119	74.95 17	96.46 148	82.91 140	88.96 124	94.74 121

testing11		86.71 55	86.44 60	87.55 42	93.54 66	71.35 23	93.65 111	95.58 12	81.36 59	80.69 135	92.21 166	72.30 38	96.46 148	85.18 105	83.43 205	94.82 116

MCST-MVS		91.08 1	91.46 3	89.94 5	97.66 2	73.37 12	97.13 2	95.58 12	89.33 1	85.77 73	96.26 47	72.84 32	99.38 2	92.64 33	95.93 9	97.08 12

UBG		86.83 50	86.70 55	87.20 54	93.07 81	69.81 49	93.43 125	95.56 14	81.52 52	81.50 118	92.12 169	73.58 28	96.28 156	84.37 119	85.20 174	95.51 69

MVS		84.66 103	82.86 146	90.06 3	90.93 147	74.56 7	87.91 355	95.54 15	68.55 338	72.35 273	94.71 97	59.78 180	98.90 24	81.29 165	94.69 34	96.74 17

ETVMVS		84.22 118	83.71 112	85.76 125	92.58 97	68.25 105	92.45 178	95.53 16	79.54 104	79.46 162	91.64 195	70.29 49	94.18 285	69.16 281	82.76 214	94.84 112

testing3-2		83.11 155	83.15 138	82.98 253	91.92 119	64.01 252	94.39 72	95.37 17	78.32 133	75.53 220	90.06 241	73.18 29	93.18 327	74.34 228	75.27 297	91.77 261

DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 172	76.68 2	97.29 1	95.35 18	82.87 37	91.58 19	97.22 9	79.93 6	99.10 10	83.12 136	97.64 2	97.94 1

CSCG		86.87 47	86.26 63	88.72 18	95.05 34	70.79 31	93.83 104	95.33 19	68.48 340	77.63 191	94.35 110	73.04 30	98.45 36	84.92 109	93.71 51	96.92 15

myMVS_eth3d28		86.31 64	86.15 67	86.78 70	93.56 64	70.49 35	92.94 144	95.28 20	82.47 41	78.70 179	92.07 172	72.45 36	95.41 220	82.11 149	85.78 167	94.44 150

WTY-MVS		86.32 62	85.81 74	87.85 31	92.82 89	69.37 64	95.20 35	95.25 21	82.71 38	81.91 114	94.73 96	67.93 65	97.63 68	79.55 180	82.25 220	96.54 23

testing99		86.01 70	85.47 80	87.63 40	93.62 61	71.25 25	93.47 123	95.23 22	80.42 75	80.60 137	91.95 181	71.73 44	96.50 146	80.02 177	82.22 221	95.13 95

patch_mono-2		89.71 11	90.99 6	85.85 121	96.04 26	63.70 267	95.04 43	95.19 23	86.74 8	91.53 21	95.15 85	73.86 24	97.58 71	93.38 27	92.00 76	96.28 39

IU-MVS					96.46 12	69.91 45		95.18 24	80.75 67	95.28 2				92.34 36	95.36 14	96.47 29

IB-MVS	77.80 4	82.18 174	80.46 196	87.35 49	89.14 190	70.28 38	95.59 27	95.17 25	78.85 122	70.19 299	85.82 313	70.66 47	97.67 63	72.19 252	66.52 363	94.09 173
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
PHI-MVS		86.83 50	86.85 54	86.78 70	93.47 69	65.55 198	95.39 31	95.10 26	71.77 276	85.69 75	96.52 36	62.07 150	98.77 28	86.06 96	95.60 12	96.03 45

test_yl		84.28 114	83.16 136	87.64 36	94.52 43	69.24 71	95.78 18	95.09 27	69.19 328	81.09 125	92.88 148	57.00 230	97.44 80	81.11 168	81.76 230	96.23 40

DCV-MVSNet		84.28 114	83.16 136	87.64 36	94.52 43	69.24 71	95.78 18	95.09 27	69.19 328	81.09 125	92.88 148	57.00 230	97.44 80	81.11 168	81.76 230	96.23 40

testing91		85.93 72	85.31 84	87.78 34	93.59 63	71.47 21	93.50 120	95.08 29	80.26 80	80.53 141	91.93 182	70.43 48	96.51 145	80.32 175	82.13 224	95.37 75

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

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

sss		82.71 164	82.38 160	83.73 225	89.25 185	59.58 376	92.24 186	94.89 32	77.96 139	79.86 151	92.38 159	56.70 236	97.05 108	77.26 202	80.86 242	94.55 136

MED-MVS test				87.42 46	94.76 36	67.28 136	94.47 64	94.87 33	73.09 238	91.27 24	96.95 18		98.98 17	91.55 44	94.28 39	95.99 48

MED-MVS		89.02 17	89.57 15	87.38 47	94.76 36	67.28 136	94.47 64	94.87 33	70.68 307	91.27 24	96.93 20	76.77 12	98.98 17	91.55 44	94.82 26	95.88 54

EPNet		87.84 31	88.38 28	86.23 108	93.30 72	66.05 181	95.26 33	94.84 35	87.09 5	88.06 50	94.53 101	66.79 73	97.34 88	83.89 125	91.68 82	95.29 84
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		90.32 6	90.89 8	88.61 23	96.76 9	70.65 32	96.47 14	94.83 36	84.83 17	89.07 44	96.80 31	70.86 46	99.06 16	92.64 33	95.71 11	96.12 42

ME-MVS		88.25 19	88.55 26	87.33 51	96.33 19	67.28 136	93.93 93	94.81 37	70.09 315	88.91 45	96.95 18	70.12 50	98.73 30	91.55 44	94.28 39	95.99 48

EI-MVSNet-Vis-set		83.77 132	83.67 113	84.06 210	92.79 92	63.56 273	91.76 220	94.81 37	79.65 97	77.87 188	94.09 122	63.35 125	97.90 52	79.35 184	79.36 259	90.74 283

tttt0517		79.50 232	78.53 233	82.41 270	87.22 262	61.43 334	89.75 312	94.76 39	69.29 326	67.91 332	88.06 279	72.92 31	95.63 206	62.91 353	73.90 309	90.16 290

GG-mvs-BLEND				86.53 95	91.91 121	69.67 56	75.02 462	94.75 40		78.67 181	90.85 214	77.91 8	94.56 266	72.25 249	93.74 49	95.36 77

gg-mvs-nofinetune		77.18 283	74.31 305	85.80 123	91.42 135	68.36 99	71.78 467	94.72 41	49.61 465	77.12 201	45.92 496	77.41 9	93.98 299	67.62 301	93.16 60	95.05 100

UWE-MVS		80.81 206	81.01 182	80.20 336	89.33 181	57.05 409	91.91 208	94.71 42	75.67 185	75.01 227	89.37 251	63.13 132	91.44 390	67.19 308	82.80 213	92.12 253

thisisatest0515		83.41 147	82.49 158	86.16 110	89.46 178	68.26 103	93.54 117	94.70 43	74.31 208	75.75 213	90.92 212	72.62 34	96.52 144	69.64 273	81.50 233	93.71 193

EI-MVSNet-UG-set		83.14 154	82.96 141	83.67 230	92.28 101	63.19 286	91.38 242	94.68 44	79.22 113	76.60 207	93.75 128	62.64 138	97.76 58	78.07 198	78.01 272	90.05 292

VPA-MVSNet		79.03 244	78.00 240	82.11 286	85.95 308	64.48 229	93.22 132	94.66 45	75.05 198	74.04 246	84.95 324	52.17 293	93.52 315	74.90 224	67.04 359	88.32 320

test-260524					95.84 30	67.84 117		94.64 46		89.45 43		71.94 42	98.96 19	91.55 44	94.82 26

NCCC		89.07 16	89.46 16	87.91 30	96.60 11	69.05 78	96.38 15	94.64 46	84.42 21	86.74 63	96.20 48	66.56 76	98.76 29	89.03 65	94.56 36	95.92 51

ET-MVSNet_ETH3D		84.01 124	83.15 138	86.58 85	90.78 152	70.89 30	94.74 56	94.62 48	81.44 56	58.19 422	93.64 132	73.64 27	92.35 363	82.66 143	78.66 269	96.50 28

thisisatest0530		81.15 196	80.07 199	84.39 199	88.26 228	65.63 195	91.40 238	94.62 48	71.27 294	70.93 289	89.18 255	72.47 35	96.04 172	65.62 328	76.89 288	91.49 265

UWE-MVS-28		76.83 292	77.60 250	74.51 413	84.58 342	50.34 449	88.22 349	94.60 50	74.46 203	66.66 353	88.98 262	62.53 140	85.50 448	57.55 383	80.80 245	87.69 326

SymmetryMVS		86.32 62	86.39 61	86.12 112	90.52 155	65.95 187	94.88 49	94.58 51	84.69 19	83.67 97	94.10 120	63.16 130	96.91 129	85.31 101	86.59 156	95.51 69

DVP-MVS		89.41 13	89.73 14	88.45 26	96.40 16	69.99 41	96.64 10	94.52 52	71.92 266	90.55 30	96.93 20	73.77 25	99.08 12	91.91 42	94.90 22	96.29 37
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
HY-MVS	76.49 5	84.28 114	83.36 127	87.02 61	92.22 103	67.74 122	84.65 389	94.50 53	79.15 115	82.23 112	87.93 280	66.88 72	96.94 123	80.53 172	82.20 222	96.39 34

HPM-MVS++		89.37 14	89.95 13	87.64 36	95.10 33	68.23 106	95.24 34	94.49 54	82.43 42	88.90 46	96.35 42	71.89 43	98.63 32	88.76 66	96.40 6	96.06 43

MG-MVS		87.11 43	86.27 62	89.62 9	97.79 1	76.27 4	94.96 48	94.49 54	78.74 126	83.87 95	92.94 145	64.34 104	96.94 123	75.19 218	94.09 42	95.66 63

SED-MVS		89.94 9	90.36 10	88.70 19	96.45 13	69.38 62	96.89 6	94.44 56	71.65 280	92.11 10	97.21 10	76.79 10	99.11 7	92.34 36	95.36 14	97.62 3

test_241102_ONE					96.45 13	69.38 62		94.44 56	71.65 280	92.11 10	97.05 13	76.79 10	99.11 7

0.4-1-1-0.2		81.28 193	79.42 216	86.84 65	85.80 314	68.82 85	95.10 39	94.43 58	74.45 204	77.18 200	85.54 317	62.27 144	95.70 202	76.72 205	63.30 393	96.01 46

0.3-1-1-0.015		81.31 191	79.49 214	86.77 73	85.74 316	68.70 94	95.01 46	94.42 59	74.29 209	77.09 203	85.61 316	63.31 127	95.69 204	76.63 206	63.30 393	95.91 52

0.4-1-1-0.1		80.99 202	79.16 224	86.51 96	85.55 321	68.21 107	94.77 54	94.42 59	73.75 222	76.57 208	85.41 319	62.35 143	95.62 208	76.30 211	63.28 395	95.71 61

test_241102_TWO								94.41 61	71.65 280	92.07 12	97.21 10	74.58 20	99.11 7	92.34 36	95.36 14	96.59 20

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

DELS-MVS		90.05 8	90.09 11	89.94 5	93.14 78	73.88 9	97.01 4	94.40 63	88.32 3	85.71 74	94.91 92	74.11 23	98.91 22	87.26 81	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
3Dnovator	73.91 6	82.69 165	80.82 184	88.31 28	89.57 174	71.26 24	92.60 168	94.39 64	78.84 123	67.89 334	92.48 157	48.42 336	98.52 34	68.80 286	94.40 38	95.15 94

DVP-MVS++		90.53 4	91.09 5	88.87 17	97.31 4	69.91 45	93.96 91	94.37 65	72.48 250	92.07 12	96.85 28	83.82 2	99.15 3	91.53 48	97.42 4	97.55 5

test_0728_SECOND				88.70 19	96.45 13	70.43 36	96.64 10	94.37 65					99.15 3	91.91 42	94.90 22	96.51 25

test0726					96.40 16	69.99 41	96.76 8	94.33 67	71.92 266	91.89 15	97.11 12	73.77 25

MSP-MVS		90.38 5	91.87 1	85.88 118	92.83 87	64.03 250	93.06 136	94.33 67	82.19 45	93.65 4	96.15 51	85.89 1	97.19 100	91.02 52	97.75 1	96.43 32
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
MAR-MVS		84.18 119	83.43 122	86.44 100	96.25 23	65.93 189	94.28 75	94.27 69	74.41 205	79.16 170	95.61 63	53.99 274	98.88 26	69.62 275	93.26 58	94.50 146
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_one_0601					96.32 20	69.74 53		94.18 70	71.42 291	90.67 29	96.85 28	74.45 22

9.14			87.63 38		93.86 54		94.41 69	94.18 70	72.76 245	86.21 67	96.51 37	66.64 74	97.88 54	90.08 57	94.04 43

DPE-MVS		88.77 18	89.21 19	87.45 45	96.26 22	67.56 127	94.17 77	94.15 72	68.77 336	90.74 28	97.27 7	76.09 14	98.49 35	90.58 56	94.91 21	96.30 36
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
WB-MVSnew		77.14 284	76.18 280	80.01 342	86.18 302	63.24 283	91.26 251	94.11 73	71.72 278	73.52 252	87.29 292	45.14 376	93.00 331	56.98 384	79.42 257	83.80 402

DeepC-MVS_fast	79.48 2	87.95 28	88.00 34	87.79 33	95.86 29	68.32 100	95.74 21	94.11 73	83.82 26	83.49 99	96.19 49	64.53 103	98.44 37	83.42 134	94.88 25	96.61 19
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TestfortrainingZip a		86.96 45	86.88 52	87.23 52	94.76 36	67.02 150	94.47 64	94.08 75	70.68 307	88.57 48	96.93 20	69.03 56	98.78 27	84.41 118	88.95 125	95.88 54

SMA-MVS		88.14 21	88.29 30	87.67 35	93.21 75	68.72 90	93.85 99	94.03 76	74.18 211	91.74 16	96.67 34	65.61 87	98.42 39	89.24 62	96.08 7	95.88 54
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
FIs		79.47 234	79.41 217	79.67 353	85.95 308	59.40 378	91.68 228	93.94 77	78.06 138	68.96 316	88.28 270	66.61 75	91.77 377	66.20 320	74.99 298	87.82 324

SteuartSystems-ACMMP		86.82 52	86.90 51	86.58 85	90.42 157	66.38 172	96.09 17	93.87 78	77.73 146	84.01 94	95.66 61	63.39 123	97.94 49	87.40 79	93.55 54	95.42 71
Skip Steuart: Steuart Systems R&D Blog.
TSAR-MVS + GP.		87.96 26	88.37 29	86.70 76	93.51 68	65.32 204	95.15 37	93.84 79	78.17 136	85.93 72	94.80 95	75.80 15	98.21 42	89.38 59	88.78 126	96.59 20

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

APDe-MVS		87.54 34	87.84 36	86.65 79	96.07 25	66.30 175	94.84 53	93.78 80	69.35 325	88.39 49	96.34 43	67.74 66	97.66 66	90.62 55	93.44 55	96.01 46
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TESTMET0.1,1		82.41 169	81.98 166	83.72 227	88.08 234	63.74 261	92.70 158	93.77 82	79.30 111	77.61 192	87.57 287	58.19 213	94.08 290	73.91 230	86.68 155	93.33 207

h-mvs33		83.01 157	82.56 157	84.35 201	89.34 179	62.02 314	92.72 155	93.76 83	81.45 54	82.73 109	92.25 164	60.11 175	97.13 106	87.69 74	62.96 396	93.91 186

SF-MVS		87.03 44	87.09 46	86.84 65	92.70 93	67.45 133	93.64 112	93.76 83	70.78 305	86.25 66	96.44 39	66.98 71	97.79 57	88.68 67	94.56 36	95.28 86

MVS_111021_HR		86.19 67	85.80 75	87.37 48	93.17 77	69.79 50	93.99 90	93.76 83	79.08 118	78.88 175	93.99 125	62.25 146	98.15 44	85.93 97	91.15 93	94.15 167

FC-MVSNet-test		77.99 268	78.08 239	77.70 377	84.89 336	55.51 421	90.27 297	93.75 86	76.87 164	66.80 352	87.59 286	65.71 86	90.23 403	62.89 354	73.94 307	87.37 332

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

QAPM		79.95 226	77.39 257	87.64 36	89.63 173	71.41 22	93.30 129	93.70 88	65.34 376	67.39 344	91.75 188	47.83 345	98.96 19	57.71 381	89.81 114	92.54 235

DeepC-MVS	77.85 3	85.52 83	85.24 85	86.37 103	88.80 200	66.64 166	92.15 190	93.68 89	81.07 63	76.91 205	93.64 132	62.59 139	98.44 37	85.50 99	92.84 64	94.03 178
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EPP-MVSNet		81.79 182	81.52 171	82.61 263	88.77 201	60.21 365	93.02 140	93.66 90	68.52 339	72.90 258	90.39 222	72.19 40	94.96 241	74.93 222	79.29 262	92.67 229

PVSNet_BlendedMVS		83.38 148	83.43 122	83.22 248	93.76 56	67.53 129	94.06 83	93.61 91	79.13 116	81.00 130	85.14 322	63.19 128	97.29 91	87.08 87	73.91 308	84.83 393

PVSNet_Blended		86.73 54	86.86 53	86.31 107	93.76 56	67.53 129	96.33 16	93.61 91	82.34 44	81.00 130	93.08 141	63.19 128	97.29 91	87.08 87	91.38 89	94.13 169

alignmvs		87.28 41	86.97 48	88.24 29	91.30 140	71.14 28	95.61 26	93.56 93	79.30 111	87.07 60	95.25 80	68.43 58	96.93 125	87.87 72	84.33 187	96.65 18

TSAR-MVS + MP.		88.11 24	88.64 25	86.54 94	91.73 126	68.04 111	90.36 294	93.55 94	82.89 35	91.29 23	92.89 147	72.27 39	96.03 173	87.99 71	94.77 28	95.54 68
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
KinetiMVS		81.43 188	80.11 198	85.38 143	86.60 289	65.47 202	92.90 149	93.54 95	75.33 192	77.31 197	90.39 222	46.81 356	96.75 134	71.65 258	86.46 160	93.93 183

TEST9					94.18 47	67.28 136	94.16 78	93.51 96	71.75 277	85.52 77	95.33 72	68.01 63	97.27 95

train_agg		87.21 42	87.42 43	86.60 82	94.18 47	67.28 136	94.16 78	93.51 96	71.87 271	85.52 77	95.33 72	68.19 61	97.27 95	89.09 63	94.90 22	95.25 91

ZD-MVS					96.63 10	65.50 200		93.50 98	70.74 306	85.26 82	95.19 84	64.92 96	97.29 91	87.51 76	93.01 61

ACMMP_NAP		86.05 69	85.80 75	86.80 69	91.58 130	67.53 129	91.79 214	93.49 99	74.93 199	84.61 86	95.30 74	59.42 188	97.92 50	86.13 94	94.92 20	94.94 106

cdsmvs_eth3d_5k		19.86 477	26.47 475	0.00 534	0.00 558	0.00 560	0.00 545	93.45 100	0.00 552	0.00 554	95.27 78	49.56 325	0.00 554	0.00 552	0.00 551	0.00 549

3Dnovator+	73.60 7	82.10 178	80.60 192	86.60 82	90.89 149	66.80 162	95.20 35	93.44 101	74.05 213	67.42 342	92.49 156	49.46 326	97.65 67	70.80 265	91.68 82	95.33 79

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

test_8					94.19 46	67.19 141	94.15 80	93.42 103	71.87 271	85.38 80	95.35 71	68.19 61	96.95 122

ZNCC-MVS		85.33 85	85.08 88	86.06 113	93.09 80	65.65 194	93.89 97	93.41 104	73.75 222	79.94 150	94.68 98	60.61 169	98.03 47	82.63 144	93.72 50	94.52 140

原ACMM1				84.42 197	93.21 75	64.27 241		93.40 105	65.39 374	79.51 161	92.50 154	58.11 214	96.69 136	65.27 333	93.96 44	92.32 243

agg_prior					94.16 49	66.97 157		93.31 106		84.49 88			96.75 134

reproduce_monomvs		79.49 233	79.11 227	80.64 326	92.91 85	61.47 333	91.17 259	93.28 107	83.09 33	64.04 374	82.38 355	66.19 78	94.57 263	81.19 166	57.71 431	85.88 376

PS-MVSNAJ		88.14 21	87.61 40	89.71 8	92.06 111	76.72 1	95.75 20	93.26 108	83.86 25	89.55 41	96.06 53	53.55 279	97.89 53	91.10 50	93.31 57	94.54 138

EI-MVSNet		78.97 246	78.22 237	81.25 307	85.33 323	62.73 299	89.53 321	93.21 109	72.39 255	72.14 274	90.13 237	60.99 161	94.72 252	67.73 300	72.49 318	86.29 361

MVSTER		82.47 168	82.05 162	83.74 223	92.68 94	69.01 79	91.90 209	93.21 109	79.83 90	72.14 274	85.71 315	74.72 19	94.72 252	75.72 214	72.49 318	87.50 328

UniMVSNet_NR-MVSNet		78.15 264	77.55 251	79.98 343	84.46 346	60.26 363	92.25 184	93.20 111	77.50 153	68.88 317	86.61 301	66.10 80	92.13 369	66.38 317	62.55 400	87.54 327

HFP-MVS		84.73 102	84.40 99	85.72 127	93.75 58	65.01 213	93.50 120	93.19 112	72.19 260	79.22 168	94.93 90	59.04 198	97.67 63	81.55 159	92.21 70	94.49 147

UniMVSNet (Re)		77.58 278	76.78 266	79.98 343	84.11 352	60.80 344	91.76 220	93.17 113	76.56 177	69.93 305	84.78 326	63.32 126	92.36 362	64.89 335	62.51 402	86.78 345

ACMMPR		84.37 111	84.06 104	85.28 149	93.56 64	64.37 236	93.50 120	93.15 114	72.19 260	78.85 177	94.86 93	56.69 237	97.45 79	81.55 159	92.20 71	94.02 179

GST-MVS		84.63 105	84.29 101	85.66 130	92.82 89	65.27 205	93.04 138	93.13 115	73.20 232	78.89 172	94.18 118	59.41 189	97.85 55	81.45 161	92.48 69	93.86 189

xiu_mvs_v2_base		87.92 30	87.38 44	89.55 13	91.41 138	76.43 3	95.74 21	93.12 116	83.53 29	89.55 41	95.95 56	53.45 283	97.68 61	91.07 51	92.62 66	94.54 138

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

WBMVS		81.67 183	80.98 183	83.72 227	93.07 81	69.40 60	94.33 73	93.05 118	76.84 166	72.05 276	84.14 335	74.49 21	93.88 304	72.76 242	68.09 349	87.88 323

SDMVSNet		80.26 218	78.88 229	84.40 198	89.25 185	67.63 126	85.35 384	93.02 119	76.77 169	70.84 290	87.12 294	47.95 344	96.09 167	85.04 106	74.55 299	89.48 302

test11								93.01 120

CostFormer		82.33 170	81.15 176	85.86 120	89.01 195	68.46 97	82.39 418	93.01 120	75.59 186	80.25 146	81.57 369	72.03 41	94.96 241	79.06 188	77.48 281	94.16 166

usedtu_dtu_shiyan1		77.89 273	76.39 274	82.40 271	81.92 380	67.01 152	91.94 206	93.00 122	77.01 161	68.44 326	84.15 333	54.78 261	93.25 324	65.76 325	70.53 331	86.94 341

FE-MVSNET3		77.89 273	76.39 274	82.40 271	81.92 380	67.01 152	91.94 206	93.00 122	77.01 161	68.44 326	84.15 333	54.78 261	93.25 324	65.76 325	70.53 331	86.94 341

PAPR		85.15 89	84.47 97	87.18 55	96.02 27	68.29 101	91.85 212	93.00 122	76.59 176	79.03 171	95.00 87	61.59 156	97.61 70	78.16 197	89.00 123	95.63 64

region2R		84.36 112	84.03 105	85.36 144	93.54 66	64.31 239	93.43 125	92.95 125	72.16 263	78.86 176	94.84 94	56.97 232	97.53 75	81.38 163	92.11 73	94.24 161

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

lupinMVS		87.74 32	87.77 37	87.63 40	89.24 188	71.18 26	96.57 12	92.90 127	82.70 39	87.13 58	95.27 78	64.99 93	95.80 189	89.34 60	91.80 80	95.93 50

PAPM_NR		82.97 158	81.84 168	86.37 103	94.10 50	66.76 163	87.66 361	92.84 128	69.96 317	74.07 245	93.57 134	63.10 133	97.50 77	70.66 268	90.58 101	94.85 109

CDPH-MVS		85.71 77	85.46 81	86.46 98	94.75 40	67.19 141	93.89 97	92.83 129	70.90 301	83.09 104	95.28 76	63.62 118	97.36 86	80.63 171	94.18 41	94.84 112

guyue		81.23 194	80.57 193	83.21 250	86.64 286	61.85 319	92.52 176	92.78 130	78.69 127	74.92 230	89.42 250	50.07 318	95.35 224	80.79 170	79.31 261	92.42 238

tfpnnormal		70.10 375	67.36 383	78.32 371	83.45 363	60.97 342	88.85 337	92.77 131	64.85 378	60.83 401	78.53 406	43.52 384	93.48 316	31.73 487	61.70 412	80.52 443

PAPM		85.89 74	85.46 81	87.18 55	88.20 232	72.42 17	92.41 180	92.77 131	82.11 46	80.34 145	93.07 142	68.27 59	95.02 237	78.39 196	93.59 53	94.09 173

SSC-MVS3.2		74.92 326	73.32 326	79.74 352	86.53 291	60.31 362	89.03 336	92.70 133	78.61 129	68.98 315	83.34 345	41.93 390	92.23 367	52.77 403	65.97 366	86.69 346

MS-PatchMatch		77.90 272	76.50 270	82.12 283	85.99 307	69.95 44	91.75 222	92.70 133	73.97 216	62.58 391	84.44 331	41.11 394	95.78 192	63.76 346	92.17 72	80.62 442

MSLP-MVS++		86.27 65	85.91 73	87.35 49	92.01 115	68.97 81	95.04 43	92.70 133	79.04 121	81.50 118	96.50 38	58.98 199	96.78 133	83.49 133	93.93 45	96.29 37

MVSMamba_PlusPlus		84.97 94	83.65 114	88.93 15	90.17 163	74.04 8	87.84 357	92.69 136	62.18 404	81.47 120	87.64 285	71.47 45	96.28 156	84.69 111	94.74 33	96.47 29

ab-mvs		80.18 220	78.31 235	85.80 123	88.44 219	65.49 201	83.00 412	92.67 137	71.82 274	77.36 196	85.01 323	54.50 264	96.59 138	76.35 210	75.63 295	95.32 81

save fliter					93.84 55	67.89 116	95.05 41	92.66 138	78.19 135

XVS		83.87 129	83.47 120	85.05 158	93.22 73	63.78 259	92.92 146	92.66 138	73.99 214	78.18 185	94.31 113	55.25 253	97.41 83	79.16 186	91.58 84	93.95 181

X-MVStestdata		76.86 289	74.13 311	85.05 158	93.22 73	63.78 259	92.92 146	92.66 138	73.99 214	78.18 185	10.19 525	55.25 253	97.41 83	79.16 186	91.58 84	93.95 181

lecture		84.77 99	84.81 94	84.65 187	92.12 108	62.27 310	94.74 56	92.64 141	68.35 341	85.53 76	95.30 74	59.77 181	97.91 51	83.73 129	91.15 93	93.77 192

SD-MVS		87.49 37	87.49 42	87.50 44	93.60 62	68.82 85	93.90 96	92.63 142	76.86 165	87.90 52	95.76 59	66.17 79	97.63 68	89.06 64	91.48 86	96.05 44
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
无先验							92.71 156	92.61 143	62.03 407				97.01 112	66.63 312		93.97 180

APD-MVS		85.93 72	85.99 71	85.76 125	95.98 28	65.21 207	93.59 115	92.58 144	66.54 359	86.17 69	95.88 57	63.83 112	97.00 113	86.39 93	92.94 62	95.06 99
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
1314		80.70 208	78.95 228	85.94 117	87.77 250	67.56 127	87.91 355	92.55 145	72.17 262	67.44 341	93.09 140	50.27 316	97.04 111	71.68 257	87.64 139	93.23 209

MP-MVS-pluss		85.24 86	85.13 87	85.56 134	91.42 135	65.59 196	91.54 234	92.51 146	74.56 202	80.62 136	95.64 62	59.15 195	97.00 113	86.94 89	93.80 47	94.07 175
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
balanced_ft_v1		84.95 95	83.81 109	88.38 27	93.31 71	73.59 11	85.95 381	92.51 146	77.25 159	73.97 247	89.14 257	59.30 191	95.25 232	92.50 35	90.34 107	96.31 35

WR-MVS		76.76 294	75.74 286	79.82 349	84.60 340	62.27 310	92.60 168	92.51 146	76.06 181	67.87 335	85.34 320	56.76 234	90.24 402	62.20 358	63.69 391	86.94 341

OpenMVS	70.45 11	78.54 258	75.92 283	86.41 102	85.93 311	71.68 20	92.74 154	92.51 146	66.49 360	64.56 368	91.96 179	43.88 382	98.10 46	54.61 392	90.65 100	89.44 304

GDP-MVS		85.54 82	85.32 83	86.18 109	87.64 251	67.95 115	92.91 148	92.36 150	77.81 143	83.69 96	94.31 113	72.84 32	96.41 150	80.39 174	85.95 163	94.19 163

CHOSEN 1792x2688		84.98 93	83.45 121	89.57 12	89.94 167	75.14 6	92.07 196	92.32 151	81.87 48	75.68 215	88.27 271	60.18 174	98.60 33	80.46 173	90.27 108	94.96 104

CP-MVS		83.71 135	83.40 125	84.65 187	93.14 78	63.84 257	94.59 61	92.28 152	71.03 299	77.41 195	94.92 91	55.21 256	96.19 161	81.32 164	90.70 99	93.91 186

MP-MVS		85.02 91	84.97 90	85.17 154	92.60 96	64.27 241	93.24 130	92.27 153	73.13 234	79.63 160	94.43 104	61.90 151	97.17 101	85.00 107	92.56 67	94.06 176
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTGPA								92.23 154

MTAPA		83.91 128	83.38 126	85.50 135	91.89 122	65.16 209	81.75 421	92.23 154	75.32 193	80.53 141	95.21 83	56.06 246	97.16 104	84.86 110	92.55 68	94.18 164

VPNet		78.82 250	77.53 252	82.70 260	84.52 343	66.44 171	93.93 93	92.23 154	80.46 73	72.60 263	88.38 269	49.18 330	93.13 328	72.47 247	63.97 389	88.55 314

ACMMP		81.49 187	80.67 189	83.93 216	91.71 127	62.90 295	92.13 191	92.22 157	71.79 275	71.68 282	93.49 136	50.32 314	96.96 121	78.47 195	84.22 191	91.93 259
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
RRT-MVS		82.61 166	81.16 175	86.96 63	91.10 144	68.75 88	87.70 360	92.20 158	76.97 163	72.68 260	87.10 296	51.30 305	96.41 150	83.56 132	87.84 136	95.74 60

PGM-MVS		83.25 150	82.70 149	84.92 163	92.81 91	64.07 249	90.44 289	92.20 158	71.28 293	77.23 199	94.43 104	55.17 257	97.31 90	79.33 185	91.38 89	93.37 204

jason		86.40 58	86.17 66	87.11 57	86.16 303	70.54 34	95.71 24	92.19 160	82.00 47	84.58 87	94.34 111	61.86 153	95.53 218	87.76 73	90.89 97	95.27 87
jason: jason.
tt0805		73.07 344	70.73 356	80.07 339	78.37 428	57.05 409	87.78 358	92.18 161	61.23 416	67.04 347	86.49 303	31.35 449	94.58 261	65.06 334	67.12 358	88.57 313

CLD-MVS		82.73 162	82.35 161	83.86 218	87.90 241	67.65 125	95.45 29	92.18 161	85.06 14	72.58 264	92.27 162	52.46 291	95.78 192	84.18 121	79.06 264	88.16 321
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
fmvsm_s_conf0.5_n_6		87.50 36	88.72 23	83.84 219	86.89 284	60.04 369	95.05 41	92.17 163	84.80 18	92.27 7	96.37 40	64.62 100	96.54 143	94.43 19	91.86 78	94.94 106

reproduce_model		83.15 153	82.96 141	83.73 225	92.02 112	59.74 373	90.37 293	92.08 164	63.70 388	82.86 105	95.48 68	58.62 205	97.17 101	83.06 137	88.42 130	94.26 159

MVS_Test		84.16 120	83.20 133	87.05 60	91.56 131	69.82 48	89.99 308	92.05 165	77.77 145	82.84 106	86.57 302	63.93 111	96.09 167	74.91 223	89.18 120	95.25 91

reproduce-ours		83.51 145	83.33 128	84.06 210	92.18 106	60.49 357	90.74 276	92.04 166	64.35 381	83.24 100	95.59 65	59.05 196	97.27 95	83.61 130	89.17 121	94.41 155

our_new_method		83.51 145	83.33 128	84.06 210	92.18 106	60.49 357	90.74 276	92.04 166	64.35 381	83.24 100	95.59 65	59.05 196	97.27 95	83.61 130	89.17 121	94.41 155

EIA-MVS		84.84 98	84.88 91	84.69 184	91.30 140	62.36 306	93.85 99	92.04 166	79.45 106	79.33 165	94.28 115	62.42 141	96.35 153	80.05 176	91.25 92	95.38 74

WR-MVS_H		70.59 371	69.94 362	72.53 429	81.03 387	51.43 441	87.35 365	92.03 169	67.38 352	60.23 410	80.70 383	55.84 250	83.45 462	46.33 434	58.58 430	82.72 419

FMVSNet3		77.73 275	76.04 281	82.80 256	91.20 143	68.99 80	91.87 210	91.99 170	73.35 231	67.04 347	83.19 347	56.62 238	92.14 368	59.80 373	69.34 337	87.28 335

DP-MVS Recon		82.73 162	81.65 170	85.98 115	97.31 4	67.06 146	95.15 37	91.99 170	69.08 333	76.50 210	93.89 127	54.48 267	98.20 43	70.76 266	85.66 169	92.69 228

EPNet_dtu		78.80 251	79.26 222	77.43 382	88.06 235	49.71 453	91.96 204	91.95 172	77.67 147	76.56 209	91.28 204	58.51 208	90.20 404	56.37 386	80.95 237	92.39 239
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FOURS1					93.95 52	61.77 322	93.96 91	91.92 173	62.14 406	86.57 64

ETV-MVS		86.01 70	86.11 68	85.70 129	90.21 162	67.02 150	93.43 125	91.92 173	81.21 61	84.13 93	94.07 124	60.93 164	95.63 206	89.28 61	89.81 114	94.46 149

SPE-MVS-test		86.14 68	87.01 47	83.52 234	92.63 95	59.36 381	95.49 28	91.92 173	80.09 84	85.46 79	95.53 67	61.82 155	95.77 194	86.77 91	93.37 56	95.41 72

LFMVS		84.34 113	82.73 148	89.18 14	94.76 36	73.25 13	94.99 47	91.89 176	71.90 268	82.16 113	93.49 136	47.98 341	97.05 108	82.55 145	84.82 180	97.25 9

casdiffmvs_mvg		85.66 79	85.18 86	87.09 58	88.22 231	69.35 65	93.74 108	91.89 176	81.47 53	80.10 148	91.45 197	64.80 98	96.35 153	87.23 82	87.69 138	95.58 66
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS		85.80 75	86.65 59	83.27 246	92.00 116	58.92 385	95.31 32	91.86 178	79.97 85	84.82 85	95.40 70	62.26 145	95.51 219	86.11 95	92.08 74	95.37 75

HPM-MVS		83.25 150	82.95 143	84.17 208	92.25 102	62.88 296	90.91 266	91.86 178	70.30 312	77.12 201	93.96 126	56.75 235	96.28 156	82.04 151	91.34 91	93.34 205
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		82.96 159	82.44 159	84.52 194	92.83 87	62.92 294	92.76 153	91.85 180	71.52 288	75.61 218	94.24 116	53.48 282	96.99 116	78.97 189	90.73 98	93.64 197

XXY-MVS		77.94 270	76.44 271	82.43 267	82.60 372	64.44 231	92.01 199	91.83 181	73.59 228	70.00 302	85.82 313	54.43 268	94.76 249	69.63 274	68.02 351	88.10 322

baseline		85.01 92	84.44 98	86.71 75	88.33 226	68.73 89	90.24 299	91.82 182	81.05 64	81.18 124	92.50 154	63.69 115	96.08 170	84.45 117	86.71 154	95.32 81

casdiffmvs		85.37 84	84.87 92	86.84 65	88.25 229	69.07 75	93.04 138	91.76 183	81.27 60	80.84 133	92.07 172	64.23 106	96.06 171	84.98 108	87.43 142	95.39 73
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.5_n_8		87.96 26	88.93 21	85.07 157	88.43 220	61.78 321	94.73 59	91.74 184	85.87 10	91.66 18	97.50 3	64.03 108	98.33 40	96.28 4	90.08 109	95.10 97

NR-MVSNet		76.05 306	74.59 299	80.44 329	82.96 368	62.18 312	90.83 271	91.73 185	77.12 160	60.96 400	86.35 304	59.28 192	91.80 376	60.74 366	61.34 415	87.35 333

PVSNet_Blended_VisFu		83.97 126	83.50 117	85.39 139	90.02 165	66.59 169	93.77 106	91.73 185	77.43 155	77.08 204	89.81 245	63.77 114	96.97 120	79.67 179	88.21 132	92.60 232

sasdasda		86.85 48	86.25 64	88.66 21	91.80 124	71.92 18	93.54 117	91.71 187	80.26 80	87.55 55	95.25 80	63.59 120	96.93 125	88.18 69	84.34 185	97.11 10

FA-MVS(test-final)		79.12 242	77.23 259	84.81 173	90.54 154	63.98 254	81.35 427	91.71 187	71.09 298	74.85 232	82.94 348	52.85 286	97.05 108	67.97 296	81.73 232	93.41 203

canonicalmvs		86.85 48	86.25 64	88.66 21	91.80 124	71.92 18	93.54 117	91.71 187	80.26 80	87.55 55	95.25 80	63.59 120	96.93 125	88.18 69	84.34 185	97.11 10

HQP3-MVS								91.70 190							78.90 265

HQP-MVS		81.14 197	80.64 190	82.64 262	87.54 253	63.66 270	94.06 83	91.70 190	79.80 91	74.18 238	90.30 225	51.63 299	95.61 210	77.63 200	78.90 265	88.63 311

baseline1		81.84 181	81.03 181	84.28 204	91.60 129	66.62 167	91.08 261	91.66 192	81.87 48	74.86 231	91.67 193	69.98 52	94.92 244	71.76 255	64.75 380	91.29 274

FMVSNet2		76.07 303	74.01 313	82.26 277	88.85 197	67.66 124	91.33 248	91.61 193	70.84 302	65.98 356	82.25 357	48.03 338	92.00 373	58.46 378	68.73 345	87.10 338

114514_t		79.17 241	77.67 246	83.68 229	95.32 32	65.53 199	92.85 151	91.60 194	63.49 390	67.92 331	90.63 217	46.65 361	95.72 201	67.01 310	83.54 204	89.79 296

test-LLR		80.10 222	79.56 211	81.72 292	86.93 280	61.17 337	92.70 158	91.54 195	71.51 289	75.62 216	86.94 298	53.83 275	92.38 360	72.21 250	84.76 182	91.60 263

test-mter		79.96 225	79.38 220	81.72 292	86.93 280	61.17 337	92.70 158	91.54 195	73.85 219	75.62 216	86.94 298	49.84 322	92.38 360	72.21 250	84.76 182	91.60 263

DU-MVS		76.86 289	75.84 284	79.91 346	82.96 368	60.26 363	91.26 251	91.54 195	76.46 179	68.88 317	86.35 304	56.16 243	92.13 369	66.38 317	62.55 400	87.35 333

旧先验1					91.94 117	60.74 349		91.50 198			94.36 106	65.23 91			91.84 79	94.55 136

VDD-MVS		83.06 156	81.81 169	86.81 68	90.86 150	67.70 123	95.40 30	91.50 198	75.46 188	81.78 115	92.34 161	40.09 398	97.13 106	86.85 90	82.04 225	95.60 65

新几何1				84.73 179	92.32 100	64.28 240		91.46 200	59.56 427	79.77 156	92.90 146	56.95 233	96.57 140	63.40 347	92.91 63	93.34 205

tpm2		79.80 228	77.95 243	85.34 145	88.28 227	68.26 103	81.56 424	91.42 201	70.11 314	77.59 193	80.50 387	67.40 69	94.26 283	67.34 305	77.35 282	93.51 201

gbinet_0.2-2-1-0.02		71.92 362	68.92 373	80.91 322	75.87 448	63.30 280	91.95 205	91.40 202	65.62 372	61.57 396	77.27 419	44.71 379	92.88 340	61.00 365	50.87 456	86.54 353

TranMVSNet+NR-MVSNet		75.86 311	74.52 302	79.89 347	82.44 374	60.64 354	91.37 243	91.37 203	76.63 175	67.65 337	86.21 307	52.37 292	91.55 384	61.84 360	60.81 418	87.48 329

hybridcas		84.65 104	83.95 106	86.74 74	87.18 265	68.78 87	92.94 144	91.36 204	80.47 72	79.32 166	91.67 193	62.13 149	96.19 161	83.15 135	87.36 143	95.25 91

test2506		83.29 149	82.92 144	84.37 200	88.39 223	63.18 287	92.01 199	91.35 205	77.66 148	78.49 184	91.42 198	64.58 102	95.09 236	73.19 235	89.23 118	94.85 109

MGCFI-Net		85.59 81	85.73 77	85.17 154	91.41 138	62.44 303	92.87 150	91.31 206	79.65 97	86.99 62	95.14 86	62.90 136	96.12 165	87.13 84	84.13 193	96.96 14

VDDNet		80.50 212	78.26 236	87.21 53	86.19 301	69.79 50	94.48 63	91.31 206	60.42 420	79.34 164	90.91 213	38.48 406	96.56 141	82.16 147	81.05 236	95.27 87

HQP_MVS		80.34 217	79.75 208	82.12 283	86.94 278	62.42 304	93.13 134	91.31 206	78.81 124	72.53 265	89.14 257	50.66 311	95.55 216	76.74 203	78.53 270	88.39 317

plane_prior5								91.31 206					95.55 216	76.74 203	78.53 270	88.39 317

VortexMVS		77.62 276	76.44 271	81.13 311	88.58 204	63.73 263	91.24 253	91.30 210	77.81 143	65.76 357	81.97 361	49.69 324	93.72 308	76.40 209	65.26 373	85.94 374

E3new		84.94 96	84.36 100	86.69 78	89.06 192	69.31 66	92.68 163	91.29 211	80.72 68	81.03 127	92.14 168	61.89 152	95.91 177	84.59 114	85.85 166	94.86 108

SR-MVS		82.81 161	82.58 155	83.50 237	93.35 70	61.16 339	92.23 187	91.28 212	64.48 380	81.27 122	95.28 76	53.71 278	95.86 181	82.87 141	88.77 127	93.49 202

viewcassd2359sk11		84.74 101	84.11 103	86.64 80	88.57 205	69.20 73	92.61 166	91.23 213	80.58 69	80.85 132	91.96 179	61.39 158	95.89 179	84.28 120	85.49 171	94.82 116

nrg030		80.93 203	79.86 205	84.13 209	83.69 359	68.83 84	93.23 131	91.20 214	75.55 187	75.06 226	88.22 275	63.04 134	94.74 251	81.88 153	66.88 360	88.82 309

EPMVS		78.49 259	75.98 282	86.02 114	91.21 142	69.68 55	80.23 436	91.20 214	75.25 194	72.48 269	78.11 410	54.65 263	93.69 312	57.66 382	83.04 209	94.69 125

fmvsm_s_conf0.5_n_4		86.79 53	87.63 38	84.27 205	86.15 304	61.48 332	94.69 60	91.16 216	83.79 28	90.51 32	96.28 45	64.24 105	98.22 41	95.00 14	86.88 147	93.11 214

hse-mvs2		81.12 199	81.11 180	81.16 310	86.52 293	57.48 402	89.40 324	91.16 216	81.45 54	82.73 109	90.49 220	60.11 175	94.58 261	87.69 74	60.41 423	91.41 268

AUN-MVS		78.37 260	77.43 253	81.17 309	86.60 289	57.45 403	89.46 323	91.16 216	74.11 212	74.40 237	90.49 220	55.52 252	94.57 263	74.73 226	60.43 422	91.48 266

cascas		78.18 263	75.77 285	85.41 138	87.14 267	69.11 74	92.96 143	91.15 219	66.71 358	70.47 293	86.07 308	37.49 417	96.48 147	70.15 271	79.80 252	90.65 284

viewdifsd2359ckpt13		84.08 122	83.21 131	86.70 76	88.49 215	69.55 58	92.25 184	91.14 220	79.71 95	79.73 157	91.72 190	58.83 202	95.89 179	82.06 150	84.99 176	94.66 130

tpm		78.58 257	77.03 262	83.22 248	85.94 310	64.56 225	83.21 408	91.14 220	78.31 134	73.67 251	79.68 399	64.01 109	92.09 371	66.07 321	71.26 328	93.03 218

E2		84.45 108	83.74 110	86.56 87	87.90 241	69.06 76	92.53 174	91.13 222	80.35 77	80.58 139	91.69 191	60.70 165	95.84 182	83.80 127	84.99 176	94.79 119

E3		84.45 108	83.74 110	86.56 87	87.90 241	69.06 76	92.53 174	91.13 222	80.35 77	80.58 139	91.69 191	60.70 165	95.84 182	83.80 127	84.99 176	94.79 119

viewmanbaseed2359cas		84.89 97	84.26 102	86.78 70	88.50 211	69.77 52	92.69 162	91.13 222	81.11 62	81.54 117	91.98 178	60.35 171	95.73 196	84.47 116	86.56 157	94.84 112

PCF-MVS	73.15 9	79.29 239	77.63 249	84.29 203	86.06 306	65.96 186	87.03 368	91.10 225	69.86 319	69.79 306	90.64 215	57.54 224	96.59 138	64.37 342	82.29 216	90.32 288
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
wanda-best-256-512		72.42 357	69.43 367	81.37 301	75.39 450	64.24 243	91.58 231	91.09 226	66.36 361	60.64 402	76.86 425	47.20 352	93.47 317	64.80 336	50.98 452	86.40 355

FE-blended-shiyan7		72.42 357	69.43 367	81.37 301	75.39 450	64.24 243	91.58 231	91.09 226	66.36 361	60.64 402	76.86 425	47.20 352	93.47 317	64.80 336	50.98 452	86.40 355

Anonymous20240529		76.84 291	74.15 310	84.88 167	91.02 145	64.95 215	93.84 102	91.09 226	53.57 453	73.00 255	87.42 289	35.91 428	97.32 89	69.14 282	72.41 320	92.36 240

EC-MVSNet		84.53 107	85.04 89	83.01 252	89.34 179	61.37 336	94.42 68	91.09 226	77.91 141	83.24 100	94.20 117	58.37 210	95.40 221	85.35 100	91.41 87	92.27 248

test_fmvsm_n_1920		87.69 33	88.50 27	85.27 150	87.05 271	63.55 274	93.69 109	91.08 230	84.18 23	90.17 36	97.04 15	67.58 67	97.99 48	95.72 8	90.03 110	94.26 159

FE-MVS		75.97 309	73.02 329	84.82 170	89.78 169	65.56 197	77.44 452	91.07 231	64.55 379	72.66 261	79.85 397	46.05 369	96.69 136	54.97 391	80.82 243	92.21 250

blended_shiyan6		72.26 359	69.26 370	81.27 306	75.24 454	64.00 253	91.37 243	91.06 232	66.12 365	60.34 408	76.75 428	46.82 355	93.45 320	64.61 338	50.98 452	86.37 358

blend_shiyan4		75.18 322	73.00 330	81.69 294	75.62 449	64.75 218	91.78 217	91.06 232	65.89 368	61.35 397	77.39 415	62.16 148	93.71 309	68.18 290	63.60 392	86.61 352

PS-MVSNAJss		77.26 282	76.31 276	80.13 338	80.64 394	59.16 383	90.63 284	91.06 232	72.80 244	68.58 323	84.57 329	53.55 279	93.96 300	72.97 237	71.96 322	87.27 336

PVSNet	73.49 8	80.05 223	78.63 231	84.31 202	90.92 148	64.97 214	92.47 177	91.05 235	79.18 114	72.43 271	90.51 219	37.05 423	94.06 292	68.06 295	86.00 162	93.90 188

blended_shiyan8		72.26 359	69.25 371	81.29 305	75.23 455	64.03 250	91.36 246	91.04 236	66.11 366	60.42 407	76.73 429	46.79 357	93.45 320	64.58 340	51.00 451	86.37 358

API-MVS		82.28 171	80.53 194	87.54 43	96.13 24	70.59 33	93.63 113	91.04 236	65.72 371	75.45 221	92.83 150	56.11 245	98.89 25	64.10 343	89.75 117	93.15 212

APD-MVS_3200maxsize		81.64 185	81.32 174	82.59 265	92.36 99	58.74 387	91.39 240	91.01 238	63.35 392	79.72 158	94.62 100	51.82 294	96.14 164	79.71 178	87.93 135	92.89 224

E4		84.00 125	83.19 134	86.46 98	86.99 272	68.85 83	92.39 181	90.99 239	79.94 86	80.17 147	91.36 202	59.73 182	95.79 191	82.87 141	84.22 191	94.74 121

Casviewmamba		84.58 106	83.95 106	86.47 97	87.22 262	67.76 121	92.71 156	90.96 240	80.81 66	79.29 167	91.85 184	62.20 147	96.33 155	84.60 113	85.91 164	95.32 81

E5new		83.62 139	82.65 150	86.55 89	86.98 273	69.28 69	91.69 224	90.96 240	79.61 99	79.80 152	91.25 205	58.04 216	95.84 182	81.83 156	83.66 202	94.52 140

E5		83.62 139	82.65 150	86.55 89	86.98 273	69.28 69	91.69 224	90.96 240	79.61 99	79.80 152	91.25 205	58.04 216	95.84 182	81.83 156	83.66 202	94.52 140

E6new		83.62 139	82.65 150	86.55 89	86.98 273	69.29 67	91.69 224	90.95 243	79.60 102	79.80 152	91.25 205	58.04 216	95.84 182	81.84 154	83.67 200	94.52 140

E6		83.62 139	82.65 150	86.55 89	86.98 273	69.29 67	91.69 224	90.95 243	79.60 102	79.80 152	91.25 205	58.04 216	95.84 182	81.84 154	83.67 200	94.52 140

MVP-Stereo		77.12 285	76.23 278	79.79 350	81.72 382	66.34 174	89.29 326	90.88 245	70.56 310	62.01 394	82.88 349	49.34 327	94.13 287	65.55 330	93.80 47	78.88 458
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
viewmacassd2359aftdt		84.03 123	83.18 135	86.59 84	86.76 285	69.44 59	92.44 179	90.85 246	80.38 76	80.78 134	91.33 203	58.54 207	95.62 208	82.15 148	85.41 172	94.72 124

NormalMVS		86.39 59	86.66 58	85.60 133	92.12 108	65.95 187	94.88 49	90.83 247	84.69 19	83.67 97	94.10 120	63.16 130	96.91 129	85.31 101	91.15 93	93.93 183

Elysia		76.45 298	74.17 308	83.30 242	80.43 396	64.12 247	89.58 314	90.83 247	61.78 412	72.53 265	85.92 311	34.30 435	94.81 247	68.10 293	84.01 195	90.97 279

StellarMVS		76.45 298	74.17 308	83.30 242	80.43 396	64.12 247	89.58 314	90.83 247	61.78 412	72.53 265	85.92 311	34.30 435	94.81 247	68.10 293	84.01 195	90.97 279

icg_test_0407_2		80.38 215	79.22 223	83.88 217	88.54 206	64.75 218	86.79 373	90.80 250	76.73 171	73.95 248	90.18 228	51.55 301	92.45 358	73.47 231	80.95 237	94.43 151

IMVS_0407		80.80 207	79.39 219	85.00 161	88.54 206	64.75 218	88.40 346	90.80 250	76.73 171	73.95 248	90.18 228	51.55 301	95.81 188	73.47 231	80.95 237	94.43 151

IMVS_0404		78.11 266	76.29 277	83.59 232	88.54 206	64.75 218	84.63 390	90.80 250	76.73 171	61.16 398	90.18 228	40.17 397	91.58 383	73.47 231	80.95 237	94.43 151

IMVS_0403		81.19 195	79.88 204	85.13 156	88.54 206	64.75 218	88.84 338	90.80 250	76.73 171	75.21 224	90.18 228	54.22 272	96.21 160	73.47 231	80.95 237	94.43 151

UGNet		79.87 227	78.68 230	83.45 239	89.96 166	61.51 330	92.13 191	90.79 254	76.83 167	78.85 177	86.33 306	38.16 409	96.17 163	67.93 298	87.17 145	92.67 229
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
TAMVS		80.37 216	79.45 215	83.13 251	85.14 330	63.37 278	91.23 254	90.76 255	74.81 201	72.65 262	88.49 265	60.63 168	92.95 333	69.41 277	81.95 228	93.08 216

MVSFormer		83.75 134	82.88 145	86.37 103	89.24 188	71.18 26	89.07 333	90.69 256	65.80 369	87.13 58	94.34 111	64.99 93	92.67 349	72.83 239	91.80 80	95.27 87

test_djsdf		73.76 341	72.56 338	77.39 383	77.00 441	53.93 429	89.07 333	90.69 256	65.80 369	63.92 375	82.03 360	43.14 386	92.67 349	72.83 239	68.53 346	85.57 382

PMMVS		81.98 180	82.04 163	81.78 290	89.76 171	56.17 415	91.13 260	90.69 256	77.96 139	80.09 149	93.57 134	46.33 366	94.99 240	81.41 162	87.46 141	94.17 165

dcpmvs_2		87.37 40	87.55 41	86.85 64	95.04 35	68.20 108	90.36 294	90.66 259	79.37 110	81.20 123	93.67 131	74.73 18	96.55 142	90.88 53	92.00 76	95.82 57

CDS-MVSNet		81.43 188	80.74 186	83.52 234	86.26 300	64.45 230	92.09 194	90.65 260	75.83 184	73.95 248	89.81 245	63.97 110	92.91 338	71.27 259	82.82 211	93.20 211
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
mvs_anonymous		81.36 190	79.99 202	85.46 136	90.39 159	68.40 98	86.88 372	90.61 261	74.41 205	70.31 298	84.67 327	63.79 113	92.32 365	73.13 236	85.70 168	95.67 62

AstraMVS		80.66 209	79.79 207	83.28 245	85.07 333	61.64 327	92.19 188	90.58 262	79.40 108	74.77 233	90.18 228	45.93 370	95.61 210	83.04 138	76.96 287	92.60 232

testing3		70.38 374	70.83 353	69.03 449	85.82 313	43.93 480	90.72 278	90.56 263	68.06 343	60.24 409	86.82 300	64.83 97	84.12 452	26.33 492	64.10 386	79.04 456

casdiffseed414692147		82.20 173	80.75 185	86.55 89	87.13 268	69.57 57	91.79 214	90.48 264	78.12 137	78.52 183	90.10 240	55.92 248	95.80 189	72.42 248	82.28 217	94.28 158

LuminaMVS		78.14 265	76.66 268	82.60 264	80.82 390	64.64 224	89.33 325	90.45 265	68.25 342	74.73 234	85.51 318	41.15 393	94.14 286	78.96 190	80.69 246	89.04 305

SR-MVS-dyc-post		81.06 200	80.70 188	82.15 281	92.02 112	58.56 390	90.90 267	90.45 265	62.76 399	78.89 172	94.46 102	51.26 306	95.61 210	78.77 193	86.77 152	92.28 245

RE-MVS-def			80.48 195		92.02 112	58.56 390	90.90 267	90.45 265	62.76 399	78.89 172	94.46 102	49.30 328		78.77 193	86.77 152	92.28 245

RPMNet		70.42 373	65.68 393	84.63 190	83.15 366	67.96 113	70.25 470	90.45 265	46.83 473	69.97 303	65.10 476	56.48 242	95.30 230	35.79 471	73.13 312	90.64 285

xiu_mvs_v1_base_debu		82.16 175	81.12 177	85.26 151	86.42 294	68.72 90	92.59 170	90.44 269	73.12 235	84.20 90	94.36 106	38.04 411	95.73 196	84.12 122	86.81 149	91.33 269

xiu_mvs_v1_base		82.16 175	81.12 177	85.26 151	86.42 294	68.72 90	92.59 170	90.44 269	73.12 235	84.20 90	94.36 106	38.04 411	95.73 196	84.12 122	86.81 149	91.33 269

xiu_mvs_v1_base_debi		82.16 175	81.12 177	85.26 151	86.42 294	68.72 90	92.59 170	90.44 269	73.12 235	84.20 90	94.36 106	38.04 411	95.73 196	84.12 122	86.81 149	91.33 269

viewdifsd2359ckpt07		82.95 160	82.04 163	85.66 130	87.19 264	66.73 164	91.56 233	90.39 272	77.58 151	77.58 194	91.19 209	58.57 206	95.65 205	82.32 146	82.01 226	94.60 134

fmvsm_s_conf0.5_n_7		85.24 86	86.69 56	80.91 322	84.52 343	60.10 367	93.35 128	90.35 273	83.41 31	86.54 65	96.27 46	60.50 170	90.02 408	94.84 16	90.38 105	92.61 231

GBi-Net		75.65 314	73.83 316	81.10 314	88.85 197	65.11 210	90.01 305	90.32 274	70.84 302	67.04 347	80.25 392	48.03 338	91.54 385	59.80 373	69.34 337	86.64 347

test1		75.65 314	73.83 316	81.10 314	88.85 197	65.11 210	90.01 305	90.32 274	70.84 302	67.04 347	80.25 392	48.03 338	91.54 385	59.80 373	69.34 337	86.64 347

FMVSNet1		72.71 352	69.91 363	81.10 314	83.60 361	65.11 210	90.01 305	90.32 274	63.92 385	63.56 379	80.25 392	36.35 427	91.54 385	54.46 393	66.75 361	86.64 347

PVSNet_0	68.08 15	71.81 363	68.32 379	82.27 275	84.68 337	62.31 309	88.68 341	90.31 277	75.84 183	57.93 427	80.65 386	37.85 414	94.19 284	69.94 272	29.05 498	90.31 289

OPM-MVS		79.00 245	78.09 238	81.73 291	83.52 362	63.83 258	91.64 230	90.30 278	76.36 180	71.97 277	89.93 244	46.30 367	95.17 235	75.10 219	77.70 275	86.19 364
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CP-MVSNet		70.50 372	69.91 363	72.26 432	80.71 392	51.00 445	87.23 367	90.30 278	67.84 347	59.64 412	82.69 351	50.23 317	82.30 471	51.28 405	59.28 426	83.46 408

fmvsm_l_conf0.5_n_3		87.54 34	88.29 30	85.30 147	86.92 282	62.63 301	95.02 45	90.28 280	84.95 16	90.27 33	96.86 26	65.36 89	97.52 76	94.93 15	90.03 110	95.76 59

KD-MVS_2432*1600		69.03 385	66.37 388	77.01 389	85.56 319	61.06 340	81.44 425	90.25 281	67.27 353	58.00 425	76.53 431	54.49 265	87.63 431	48.04 423	35.77 489	82.34 425

miper_refine_blended		69.03 385	66.37 388	77.01 389	85.56 319	61.06 340	81.44 425	90.25 281	67.27 353	58.00 425	76.53 431	54.49 265	87.63 431	48.04 423	35.77 489	82.34 425

v148		76.19 301	74.47 303	81.36 303	80.05 404	64.44 231	91.75 222	90.23 283	73.68 226	67.13 346	80.84 382	55.92 248	93.86 307	68.95 284	61.73 411	85.76 380

v2v482		77.42 280	75.65 287	82.73 258	80.38 398	67.13 145	91.85 212	90.23 283	75.09 197	69.37 307	83.39 344	53.79 277	94.44 273	71.77 254	65.00 377	86.63 350

fmvsm_s_conf0.5_n_10		87.93 29	88.67 24	85.71 128	88.69 202	63.71 265	94.56 62	90.22 285	85.04 15	92.27 7	97.05 13	63.67 116	98.15 44	95.09 12	91.39 88	95.27 87

v1144		76.73 295	74.88 295	82.27 275	80.23 402	66.60 168	91.68 228	90.21 286	73.69 225	69.06 312	81.89 362	52.73 289	94.40 275	69.21 280	65.23 374	85.80 377

GA-MVS		78.33 262	76.23 278	84.65 187	83.65 360	66.30 175	91.44 235	90.14 287	76.01 182	70.32 297	84.02 337	42.50 387	94.72 252	70.98 263	77.00 286	92.94 221

MDTV_nov1_ep13			72.61 337		89.06 192	68.48 95	80.33 434	90.11 288	71.84 273	71.81 279	75.92 437	53.01 285	93.92 302	48.04 423	73.38 310

D2MVS		73.80 338	72.02 344	79.15 365	79.15 415	62.97 290	88.58 343	90.07 289	72.94 239	59.22 415	78.30 407	42.31 389	92.70 348	65.59 329	72.00 321	81.79 431

TR-MVS		78.77 253	77.37 258	82.95 254	90.49 156	60.88 343	93.67 110	90.07 289	70.08 316	74.51 236	91.37 201	45.69 371	95.70 202	60.12 371	80.32 248	92.29 244

Anonymous20231211		73.08 343	70.39 359	81.13 311	90.62 153	63.33 279	91.40 238	90.06 291	51.84 458	64.46 371	80.67 385	36.49 426	94.07 291	63.83 345	64.17 385	85.98 371

jajsoiax		73.05 345	71.51 350	77.67 378	77.46 437	54.83 425	88.81 339	90.04 292	69.13 330	62.85 389	83.51 342	31.16 450	92.75 345	70.83 264	69.80 333	85.43 386

fmvsm_s_conf0.5_n		86.39 59	86.91 50	84.82 170	87.36 259	63.54 275	94.74 56	90.02 293	82.52 40	90.14 37	96.92 24	62.93 135	97.84 56	95.28 11	82.26 218	93.07 217

HyFIR lowres test		81.03 201	79.56 211	85.43 137	87.81 247	68.11 110	90.18 300	90.01 294	70.65 309	72.95 257	86.06 309	63.61 119	94.50 271	75.01 221	79.75 253	93.67 194

fmvsm_s_conf0.5_n_5		86.38 61	86.94 49	84.71 182	84.67 338	63.29 281	94.04 87	89.99 295	82.88 36	87.85 53	96.03 54	62.89 137	96.36 152	94.15 21	89.95 112	94.48 148

ACMM	69.62 13	74.34 331	72.73 335	79.17 363	84.25 351	57.87 395	90.36 294	89.93 296	63.17 396	65.64 359	86.04 310	37.79 415	94.10 288	65.89 322	71.52 325	85.55 383
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CL-MVSNet_self_test		69.92 377	68.09 380	75.41 401	73.25 462	55.90 419	90.05 304	89.90 297	69.96 317	61.96 395	76.54 430	51.05 309	87.64 430	49.51 415	50.59 458	82.70 421

UnsupCasMVSNet_eth		65.79 410	63.10 412	73.88 419	70.71 471	50.29 451	81.09 428	89.88 298	72.58 248	49.25 464	74.77 443	32.57 443	87.43 436	55.96 388	41.04 479	83.90 401

testdata				81.34 304	89.02 194	57.72 397		89.84 299	58.65 432	85.32 81	94.09 122	57.03 228	93.28 323	69.34 278	90.56 102	93.03 218

test_fmvsmconf_n		86.58 56	87.17 45	84.82 170	85.28 326	62.55 302	94.26 76	89.78 300	83.81 27	87.78 54	96.33 44	65.33 90	96.98 117	94.40 20	87.55 140	94.95 105

mvs_tets		72.71 352	71.11 351	77.52 379	77.41 438	54.52 427	88.45 345	89.76 301	68.76 337	62.70 390	83.26 346	29.49 456	92.71 346	70.51 270	69.62 335	85.34 388

v1192		75.98 308	73.92 314	82.15 281	79.73 406	66.24 177	91.22 255	89.75 302	72.67 246	68.49 324	81.42 372	49.86 321	94.27 281	67.08 309	65.02 376	85.95 372

PS-CasMVS		69.86 379	69.13 372	72.07 436	80.35 399	50.57 448	87.02 369	89.75 302	67.27 353	59.19 416	82.28 356	46.58 362	82.24 472	50.69 408	59.02 427	83.39 410

dp		75.01 324	72.09 343	83.76 222	89.28 184	66.22 178	79.96 442	89.75 302	71.16 295	67.80 336	77.19 421	51.81 295	92.54 354	50.39 409	71.44 327	92.51 237

LPG-MVS_test		75.82 312	74.58 300	79.56 357	84.31 349	59.37 379	90.44 289	89.73 305	69.49 323	64.86 364	88.42 267	38.65 403	94.30 279	72.56 245	72.76 315	85.01 391

LGP-MVS_train				79.56 357	84.31 349	59.37 379		89.73 305	69.49 323	64.86 364	88.42 267	38.65 403	94.30 279	72.56 245	72.76 315	85.01 391

tpmrst		80.57 210	79.14 226	84.84 169	90.10 164	68.28 102	81.70 422	89.72 307	77.63 150	75.96 212	79.54 401	64.94 95	92.71 346	75.43 216	77.28 284	93.55 198

v144192		76.05 306	74.03 312	82.12 283	79.50 410	66.55 170	91.39 240	89.71 308	72.30 257	68.17 328	81.33 374	51.75 297	94.03 297	67.94 297	64.19 384	85.77 378

fmvsm_l_conf0.5_n_9		88.24 20	89.36 17	84.85 168	88.15 233	61.94 318	95.65 25	89.70 309	85.54 12	92.07 12	97.33 6	67.51 68	97.27 95	96.23 5	92.07 75	95.35 78

viewdifsd2359ckpt09		83.52 144	82.57 156	86.37 103	88.02 238	68.47 96	91.78 217	89.63 310	79.61 99	78.56 182	92.00 177	59.28 192	95.96 176	81.94 152	82.35 215	94.69 125

TAPA-MVS	70.22 12	74.94 325	73.53 320	79.17 363	90.40 158	52.07 437	89.19 331	89.61 311	62.69 401	70.07 300	92.67 152	48.89 335	94.32 277	38.26 466	79.97 250	91.12 277
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PatchmatchNet		77.46 279	74.63 298	85.96 116	89.55 176	70.35 37	79.97 441	89.55 312	72.23 259	70.94 288	76.91 424	57.03 228	92.79 344	54.27 394	81.17 235	94.74 121
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v1921920		75.63 316	73.49 321	82.06 287	79.38 411	66.35 173	91.07 264	89.48 313	71.98 265	67.99 329	81.22 377	49.16 332	93.90 303	66.56 313	64.56 383	85.92 375

fmvsm_s_conf0.1_n		85.61 80	85.93 72	84.68 185	82.95 370	63.48 277	94.03 89	89.46 314	81.69 50	89.86 38	96.74 32	61.85 154	97.75 59	94.74 17	82.01 226	92.81 227

v7n		71.31 367	68.65 374	79.28 361	76.40 443	60.77 346	86.71 374	89.45 315	64.17 384	58.77 420	78.24 408	44.59 380	93.54 314	57.76 380	61.75 410	83.52 406

test0.0.03 1		72.76 350	72.71 336	72.88 427	80.25 401	47.99 461	91.22 255	89.45 315	71.51 289	62.51 392	87.66 284	53.83 275	85.06 450	50.16 411	67.84 356	85.58 381

test222					89.77 170	61.60 328	89.55 317	89.42 317	56.83 443	77.28 198	92.43 158	52.76 287			91.14 96	93.09 215

V42		76.46 297	74.55 301	82.19 280	79.14 416	67.82 119	90.26 298	89.42 317	73.75 222	68.63 322	81.89 362	51.31 304	94.09 289	71.69 256	64.84 378	84.66 394

BH-w/o		80.49 213	79.30 221	84.05 213	90.83 151	64.36 238	93.60 114	89.42 317	74.35 207	69.09 310	90.15 236	55.23 255	95.61 210	64.61 338	86.43 161	92.17 251

fmvsm_s_conf0.5_n_a		85.75 76	86.09 69	84.72 180	85.73 317	63.58 272	93.79 105	89.32 320	81.42 57	90.21 35	96.91 25	62.41 142	97.67 63	94.48 18	80.56 247	92.90 223

pm-mvs1		72.89 348	71.09 352	78.26 373	79.10 417	57.62 399	90.80 272	89.30 321	67.66 349	62.91 388	81.78 364	49.11 333	92.95 333	60.29 370	58.89 428	84.22 398

dtuplus		82.25 172	81.42 173	84.71 182	85.38 322	66.05 181	90.62 285	89.27 322	75.16 196	79.22 168	91.76 186	58.05 215	94.56 266	81.18 167	82.19 223	93.52 200

v8		75.35 318	73.26 327	81.61 296	80.67 393	66.82 160	89.54 318	89.27 322	71.65 280	63.30 382	80.30 391	54.99 259	94.06 292	67.33 306	62.33 403	83.94 400

diffmvs		84.28 114	83.83 108	85.61 132	87.40 257	68.02 112	90.88 269	89.24 324	80.54 70	81.64 116	92.52 153	59.83 179	94.52 270	87.32 80	85.11 175	94.29 157
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PEN-MVS		69.46 382	68.56 375	72.17 434	79.27 412	49.71 453	86.90 371	89.24 324	67.24 356	59.08 417	82.51 354	47.23 351	83.54 461	48.42 421	57.12 432	83.25 411

UniMVSNet_ETH3D		72.74 351	70.53 358	79.36 359	78.62 425	56.64 413	85.01 387	89.20 326	63.77 387	64.84 366	84.44 331	34.05 437	91.86 375	63.94 344	70.89 330	89.57 300

SCA		75.82 312	72.76 333	85.01 160	86.63 288	70.08 40	81.06 429	89.19 327	71.60 285	70.01 301	77.09 422	45.53 372	90.25 399	60.43 368	73.27 311	94.68 127

EG-PatchMatch MVS		68.55 389	65.41 396	77.96 376	78.69 423	62.93 292	89.86 310	89.17 328	60.55 419	50.27 458	77.73 414	22.60 476	94.06 292	47.18 430	72.65 317	76.88 470

HPM-MVS_fast		80.25 219	79.55 213	82.33 273	91.55 132	59.95 370	91.32 249	89.16 329	65.23 377	74.71 235	93.07 142	47.81 346	95.74 195	74.87 225	88.23 131	91.31 273

miper_enhance_ethall		78.86 249	77.97 241	81.54 298	88.00 239	65.17 208	91.41 236	89.15 330	75.19 195	68.79 319	83.98 338	67.17 70	92.82 341	72.73 243	65.30 370	86.62 351

Fast-Effi-MVS+		81.14 197	80.01 201	84.51 195	90.24 161	65.86 190	94.12 82	89.15 330	73.81 221	75.37 223	88.26 272	57.26 225	94.53 269	66.97 311	84.92 179	93.15 212

onestephybrid01		83.68 137	83.31 130	84.81 173	86.53 291	65.38 203	90.54 287	89.14 332	79.52 105	81.01 128	92.02 174	58.91 200	94.91 246	88.26 68	83.86 197	94.14 168

mvsmamba		81.55 186	80.72 187	84.03 214	91.42 135	66.93 158	83.08 409	89.13 333	78.55 130	67.50 340	87.02 297	51.79 296	90.07 407	87.48 77	90.49 103	95.10 97

Vis-MVSNet (Re-imp)		79.24 240	79.57 210	78.24 374	88.46 218	52.29 436	90.41 291	89.12 334	74.24 210	69.13 309	91.91 183	65.77 85	90.09 406	59.00 377	88.09 133	92.33 242

v1240		75.21 321	72.98 331	81.88 289	79.20 413	66.00 184	90.75 275	89.11 335	71.63 284	67.41 343	81.22 377	47.36 350	93.87 305	65.46 331	64.72 381	85.77 378

sd_testset		77.08 286	75.37 289	82.20 279	89.25 185	62.11 313	82.06 419	89.09 336	76.77 169	70.84 290	87.12 294	41.43 392	95.01 239	67.23 307	74.55 299	89.48 302

v10		74.77 328	72.54 339	81.46 299	80.33 400	66.71 165	89.15 332	89.08 337	70.94 300	63.08 385	79.86 396	52.52 290	94.04 295	65.70 327	62.17 404	83.64 403

ACMP	71.68 10	75.58 317	74.23 307	79.62 355	84.97 335	59.64 374	90.80 272	89.07 338	70.39 311	62.95 387	87.30 291	38.28 407	93.87 305	72.89 238	71.45 326	85.36 387
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
fmvsm_s_conf0.5_n_11		87.99 25	89.25 18	84.23 207	89.07 191	61.60 328	94.87 51	89.06 339	85.65 11	91.09 26	97.41 5	68.26 60	97.43 82	95.07 13	92.74 65	93.66 195

diffmvs_AUTHOR		83.97 126	83.49 118	85.39 139	86.09 305	67.83 118	90.76 274	89.05 340	79.94 86	81.43 121	92.23 165	59.53 185	94.42 274	87.18 83	85.22 173	93.92 185

UnsupCasMVSNet_bld		61.60 430	57.71 434	73.29 424	68.73 478	51.64 439	78.61 445	89.05 340	57.20 440	46.11 471	61.96 484	28.70 459	88.60 417	50.08 412	38.90 484	79.63 451

viewmambaseed2359dif		82.60 167	81.91 167	84.67 186	85.83 312	66.09 180	90.50 288	89.01 342	75.46 188	79.64 159	92.01 176	59.51 186	94.38 276	82.99 139	82.26 218	93.54 199

Syy-MVS		69.65 380	69.52 366	70.03 444	87.87 244	43.21 481	88.07 351	89.01 342	72.91 241	63.11 383	88.10 276	45.28 375	85.54 445	22.07 497	69.23 340	81.32 434

myMVS_eth3d		72.58 356	72.74 334	72.10 435	87.87 244	49.45 455	88.07 351	89.01 342	72.91 241	63.11 383	88.10 276	63.63 117	85.54 445	32.73 484	69.23 340	81.32 434

CANet_DTU		84.09 121	83.52 115	85.81 122	90.30 160	66.82 160	91.87 210	89.01 342	85.27 13	86.09 70	93.74 129	47.71 347	96.98 117	77.90 199	89.78 116	93.65 196

UA-Net		80.02 224	79.65 209	81.11 313	89.33 181	57.72 397	86.33 378	89.00 346	77.44 154	81.01 128	89.15 256	59.33 190	95.90 178	61.01 364	84.28 189	89.73 298

MVS_111021_LR		82.02 179	81.52 171	83.51 236	88.42 221	62.88 296	89.77 311	88.93 347	76.78 168	75.55 219	93.10 139	50.31 315	95.38 223	83.82 126	87.02 146	92.26 249

miper_lstm_enhance		73.05 345	71.73 348	77.03 388	83.80 357	58.32 392	81.76 420	88.88 348	69.80 320	61.01 399	78.23 409	57.19 226	87.51 435	65.34 332	59.53 425	85.27 390

anonymousdsp		71.14 368	69.37 369	76.45 395	72.95 464	54.71 426	84.19 394	88.88 348	61.92 409	62.15 393	79.77 398	38.14 410	91.44 390	68.90 285	67.45 357	83.21 412

hybrid		83.58 143	83.00 140	85.34 145	86.38 298	67.51 132	90.92 265	88.87 350	78.49 131	80.59 138	92.09 171	58.77 204	94.46 272	87.12 85	83.74 199	94.06 176

cl22		77.94 270	76.78 266	81.42 300	87.57 252	64.93 216	90.67 280	88.86 351	72.45 252	67.63 338	82.68 352	64.07 107	92.91 338	71.79 253	65.30 370	86.44 354

test_fmvsmconf0.1_n		85.71 77	86.08 70	84.62 191	80.83 389	62.33 307	93.84 102	88.81 352	83.50 30	87.00 61	96.01 55	63.36 124	96.93 125	94.04 23	87.29 144	94.61 133

MIMVSNet		71.64 364	68.44 377	81.23 308	81.97 379	64.44 231	73.05 464	88.80 353	69.67 322	64.59 367	74.79 442	32.79 441	87.82 427	53.99 395	76.35 291	91.42 267

IterMVS-LS		76.49 296	75.18 293	80.43 330	84.49 345	62.74 298	90.64 282	88.80 353	72.40 254	65.16 363	81.72 365	60.98 162	92.27 366	67.74 299	64.65 382	86.29 361
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
hybridnocas07		83.76 133	83.21 131	85.39 139	86.64 286	67.40 134	91.08 261	88.77 355	79.78 94	80.35 144	92.15 167	59.24 194	94.67 259	87.11 86	83.79 198	94.11 171

fmvsm_s_conf0.1_n_a		84.76 100	84.84 93	84.53 193	80.23 402	63.50 276	92.79 152	88.73 356	80.46 73	89.84 39	96.65 35	60.96 163	97.57 73	93.80 25	80.14 249	92.53 236

cl____		76.07 303	74.67 296	80.28 333	85.15 329	61.76 323	90.12 301	88.73 356	71.16 295	65.43 360	81.57 369	61.15 159	92.95 333	66.54 314	62.17 404	86.13 367

DIV-MVS_self_test		76.07 303	74.67 296	80.28 333	85.14 330	61.75 324	90.12 301	88.73 356	71.16 295	65.42 361	81.60 368	61.15 159	92.94 337	66.54 314	62.16 406	86.14 365

JIA-IIPM		66.06 408	62.45 417	76.88 392	81.42 386	54.45 428	57.49 495	88.67 359	49.36 466	63.86 376	46.86 495	56.06 246	90.25 399	49.53 414	68.83 343	85.95 372

OMC-MVS		78.67 256	77.91 245	80.95 320	85.76 315	57.40 404	88.49 344	88.67 359	73.85 219	72.43 271	92.10 170	49.29 329	94.55 268	72.73 243	77.89 273	90.91 282

miper_ehance_all_eth		77.60 277	76.44 271	81.09 317	85.70 318	64.41 234	90.65 281	88.64 361	72.31 256	67.37 345	82.52 353	64.77 99	92.64 352	70.67 267	65.30 370	86.24 363

BH-untuned		78.68 254	77.08 261	83.48 238	89.84 168	63.74 261	92.70 158	88.59 362	71.57 286	66.83 351	88.65 264	51.75 297	95.39 222	59.03 376	84.77 181	91.32 272

DTE-MVSNet		68.46 391	67.33 384	71.87 438	77.94 433	49.00 458	86.16 380	88.58 363	66.36 361	58.19 422	82.21 358	46.36 363	83.87 457	44.97 442	55.17 439	82.73 418

FE-MVSNET2		66.80 404	64.06 407	75.03 406	69.84 474	57.11 407	86.57 375	88.57 364	67.94 346	50.97 456	72.16 454	33.79 438	87.55 434	53.94 396	52.74 445	80.45 444

CPTT-MVS		79.59 230	79.16 224	80.89 324	91.54 133	59.80 372	92.10 193	88.54 365	60.42 420	72.96 256	93.28 138	48.27 337	92.80 343	78.89 192	86.50 159	90.06 291

fmvsm_l_conf0.5_n		87.49 37	88.19 32	85.39 139	86.95 277	64.37 236	94.30 74	88.45 366	80.51 71	92.70 5	96.86 26	69.98 52	97.15 105	95.83 7	88.08 134	94.65 131

CVMVSNet		74.04 335	74.27 306	73.33 423	85.33 323	43.94 479	89.53 321	88.39 367	54.33 452	70.37 296	90.13 237	49.17 331	84.05 454	61.83 361	79.36 259	91.99 255

fmvsm_s_conf0.5_n_9		88.14 21	89.21 19	84.92 163	89.29 183	61.41 335	92.97 141	88.36 368	86.96 6	91.49 22	97.49 4	69.48 55	97.46 78	97.00 1	89.88 113	95.89 53

1112_ss		80.56 211	79.83 206	82.77 257	88.65 203	60.78 345	92.29 183	88.36 368	72.58 248	72.46 270	94.95 88	65.09 92	93.42 322	66.38 317	77.71 274	94.10 172

viewmamba		83.23 152	82.64 154	85.00 161	86.40 297	66.16 179	90.68 279	88.35 370	79.92 88	78.68 180	92.02 174	58.86 201	94.72 252	85.55 98	83.31 207	94.12 170

test_cas_vis1_n_1920		80.45 214	80.61 191	79.97 345	78.25 429	57.01 411	94.04 87	88.33 371	79.06 120	82.81 108	93.70 130	38.65 403	91.63 381	90.82 54	79.81 251	91.27 275

tpmvs		72.88 349	69.76 365	82.22 278	90.98 146	67.05 147	78.22 449	88.30 372	63.10 397	64.35 373	74.98 440	55.09 258	94.27 281	43.25 445	69.57 336	85.34 388

PLC	68.80 14	75.23 320	73.68 319	79.86 348	92.93 84	58.68 388	90.64 282	88.30 372	60.90 417	64.43 372	90.53 218	42.38 388	94.57 263	56.52 385	76.54 290	86.33 360
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
eth_miper_zixun_eth		75.96 310	74.40 304	80.66 325	84.66 339	63.02 289	89.28 327	88.27 374	71.88 270	65.73 358	81.65 366	59.45 187	92.81 342	68.13 292	60.53 420	86.14 365

IS-MVSNet		80.14 221	79.41 217	82.33 273	87.91 240	60.08 368	91.97 203	88.27 374	72.90 243	71.44 286	91.73 189	61.44 157	93.66 313	62.47 357	86.53 158	93.24 208

Vis-MVSNet		80.92 204	79.98 203	83.74 223	88.48 217	61.80 320	93.44 124	88.26 376	73.96 217	77.73 189	91.76 186	49.94 320	94.76 249	65.84 323	90.37 106	94.65 131
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
fmvsm_l_conf0.5_n_a		87.44 39	88.15 33	85.30 147	87.10 269	64.19 245	94.41 69	88.14 377	80.24 83	92.54 6	96.97 17	69.52 54	97.17 101	95.89 6	88.51 129	94.56 135

c3_l		76.83 292	75.47 288	80.93 321	85.02 334	64.18 246	90.39 292	88.11 378	71.66 279	66.65 354	81.64 367	63.58 122	92.56 353	69.31 279	62.86 397	86.04 369

BH-RMVSNet		79.46 235	77.65 247	84.89 166	91.68 128	65.66 193	93.55 116	88.09 379	72.93 240	73.37 253	91.12 211	46.20 368	96.12 165	56.28 387	85.61 170	92.91 222

tpm cat1		75.30 319	72.21 342	84.58 192	88.52 210	67.77 120	78.16 450	88.02 380	61.88 410	68.45 325	76.37 433	60.65 167	94.03 297	53.77 398	74.11 305	91.93 259

dmvs_re		76.93 288	75.36 290	81.61 296	87.78 249	60.71 351	80.00 440	87.99 381	79.42 107	69.02 313	89.47 249	46.77 358	94.32 277	63.38 348	74.45 302	89.81 295

Test_1112_low_res		79.56 231	78.60 232	82.43 267	88.24 230	60.39 361	92.09 194	87.99 381	72.10 264	71.84 278	87.42 289	64.62 100	93.04 329	65.80 324	77.30 283	93.85 190

AdaColmap		78.94 247	77.00 264	84.76 177	96.34 18	65.86 190	92.66 164	87.97 383	62.18 404	70.56 292	92.37 160	43.53 383	97.35 87	64.50 341	82.86 210	91.05 278

fmvsm_s_conf0.5_n_3		86.88 46	87.99 35	83.58 233	87.26 260	60.74 349	93.21 133	87.94 384	84.22 22	91.70 17	97.27 7	65.91 84	95.02 237	93.95 24	90.42 104	94.99 103

Effi-MVS+-dtu		76.14 302	75.28 292	78.72 368	83.22 365	55.17 423	89.87 309	87.78 385	75.42 190	67.98 330	81.43 371	45.08 377	92.52 355	75.08 220	71.63 323	88.48 315

PatchT		69.11 384	65.37 397	80.32 331	82.07 378	63.68 269	67.96 479	87.62 386	50.86 462	69.37 307	65.18 475	57.09 227	88.53 419	41.59 455	66.60 362	88.74 310

XVG-OURS		74.25 333	72.46 340	79.63 354	78.45 427	57.59 401	80.33 434	87.39 387	63.86 386	68.76 320	89.62 248	40.50 396	91.72 378	69.00 283	74.25 304	89.58 299

viewdifsd2359ckpt11		79.42 237	77.95 243	83.81 220	83.87 356	63.85 255	89.54 318	87.38 388	77.39 157	74.94 228	89.95 242	51.11 307	94.72 252	79.52 181	67.90 352	92.88 225

viewmsd2359difaftdt		79.42 237	77.96 242	83.81 220	83.88 355	63.85 255	89.54 318	87.38 388	77.39 157	74.94 228	89.95 242	51.11 307	94.72 252	79.52 181	67.90 352	92.88 225

Anonymous20231206		67.53 400	65.78 391	72.79 428	74.95 456	47.59 463	88.23 348	87.32 390	61.75 414	58.07 424	77.29 418	37.79 415	87.29 437	42.91 447	63.71 390	83.48 407

XVG-OURS-SEG-HR		74.70 329	73.08 328	79.57 356	78.25 429	57.33 405	80.49 432	87.32 390	63.22 394	68.76 320	90.12 239	44.89 378	91.59 382	70.55 269	74.09 306	89.79 296

fmvsm_s_conf0.5_n_2		85.06 90	85.60 79	83.44 240	86.92 282	60.53 356	94.41 69	87.31 392	83.30 32	88.72 47	96.72 33	54.28 271	97.75 59	94.07 22	84.68 184	92.04 254

pmmvs4		73.92 337	71.81 347	80.25 335	79.17 414	65.24 206	87.43 364	87.26 393	67.64 351	63.46 380	83.91 339	48.96 334	91.53 388	62.94 352	65.49 369	83.96 399

test_fmvsmconf0.01_n		83.70 136	83.52 115	84.25 206	75.26 453	61.72 325	92.17 189	87.24 394	82.36 43	84.91 84	95.41 69	55.60 251	96.83 132	92.85 31	85.87 165	94.21 162

SSM_0407		79.09 243	77.21 260	84.75 178	88.50 211	66.98 154	89.21 329	87.03 395	67.99 344	74.12 242	89.32 252	47.98 341	95.29 231	71.23 260	79.52 254	91.98 256

SSM_0404		79.46 235	77.65 247	84.91 165	88.37 225	67.04 148	89.59 313	87.03 395	67.99 344	75.45 221	89.32 252	47.98 341	95.34 226	71.23 260	81.90 229	92.34 241

pmmvs5		73.35 342	71.52 349	78.86 367	78.64 424	60.61 355	91.08 261	86.90 397	67.69 348	63.32 381	83.64 340	44.33 381	90.53 396	62.04 359	66.02 365	85.46 385

test_vis1_n_1920		81.66 184	82.01 165	80.64 326	82.24 375	55.09 424	94.76 55	86.87 398	81.67 51	84.40 89	94.63 99	38.17 408	94.67 259	91.98 41	83.34 206	92.16 252

test1111		80.84 205	80.02 200	83.33 241	87.87 244	60.76 347	92.62 165	86.86 399	77.86 142	75.73 214	91.39 200	46.35 364	94.70 258	72.79 241	88.68 128	94.52 140

ECVR-MVS		81.29 192	80.38 197	84.01 215	88.39 223	61.96 316	92.56 173	86.79 400	77.66 148	76.63 206	91.42 198	46.34 365	95.24 233	74.36 227	89.23 118	94.85 109

pmmvs6		67.57 399	64.76 400	76.00 399	72.82 466	53.37 431	88.71 340	86.78 401	53.19 454	57.58 429	78.03 411	35.33 431	92.41 359	55.56 389	54.88 441	82.21 427

usedtu_blend_shiyan5		71.06 369	67.54 382	81.62 295	75.39 450	64.75 218	85.67 382	86.47 402	56.48 445	60.64 402	76.85 427	47.20 352	93.71 309	68.18 290	50.98 452	86.40 355

MonoMVSNet		76.99 287	75.08 294	82.73 258	83.32 364	63.24 283	86.47 377	86.37 403	79.08 118	66.31 355	79.30 403	49.80 323	91.72 378	79.37 183	65.70 368	93.23 209

F-COLMAP		70.66 370	68.44 377	77.32 384	86.37 299	55.91 418	88.00 353	86.32 404	56.94 442	57.28 430	88.07 278	33.58 439	92.49 356	51.02 406	68.37 347	83.55 404

IterMVS		72.65 355	70.83 353	78.09 375	82.17 376	62.96 291	87.64 362	86.28 405	71.56 287	60.44 406	78.85 405	45.42 374	86.66 439	63.30 350	61.83 408	84.65 395
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet5		68.04 395	65.66 394	75.18 405	84.43 347	57.89 394	83.54 399	86.26 406	61.83 411	53.64 443	73.30 445	37.15 421	85.08 449	48.99 417	61.77 409	82.56 424

GeoE		78.90 248	77.43 253	83.29 244	88.95 196	62.02 314	92.31 182	86.23 407	70.24 313	71.34 287	89.27 254	54.43 268	94.04 295	63.31 349	80.81 244	93.81 191

EU-MVSNet		64.01 419	63.01 413	67.02 458	74.40 459	38.86 493	83.27 405	86.19 408	45.11 478	54.27 438	81.15 380	36.91 424	80.01 479	48.79 420	57.02 433	82.19 428

mamba_0408		76.22 300	73.37 323	84.77 175	88.50 211	66.98 154	58.80 493	86.18 409	69.12 331	74.12 242	89.01 260	47.50 348	95.35 224	67.57 302	79.52 254	91.98 256

SSM_04072		74.86 327	73.37 323	79.35 360	88.50 211	66.98 154	58.80 493	86.18 409	69.12 331	74.12 242	89.01 260	47.50 348	79.09 480	67.57 302	79.52 254	91.98 256

Effi-MVS+		83.82 130	82.76 147	86.99 62	89.56 175	69.40 60	91.35 247	86.12 411	72.59 247	83.22 103	92.81 151	59.60 184	96.01 175	81.76 158	87.80 137	95.56 67

IterMVS-SCA-FT		71.55 366	69.97 361	76.32 396	81.48 384	60.67 353	87.64 362	85.99 412	66.17 364	59.50 413	78.88 404	45.53 372	83.65 459	62.58 356	61.93 407	84.63 397

kuosan		60.86 435	60.24 425	62.71 465	81.57 383	46.43 471	75.70 460	85.88 413	57.98 434	48.95 465	69.53 464	58.42 209	76.53 482	28.25 491	35.87 488	65.15 489

XVG-ACMP-BASELINE		68.04 395	65.53 395	75.56 400	74.06 460	52.37 435	78.43 446	85.88 413	62.03 407	58.91 419	81.21 379	20.38 481	91.15 392	60.69 367	68.18 348	83.16 413

ambc				69.61 446	61.38 493	41.35 485	49.07 501	85.86 415		50.18 460	66.40 473	10.16 497	88.14 424	45.73 437	44.20 472	79.32 454

CMPMVS	48.56 21	66.77 405	64.41 405	73.84 420	70.65 472	50.31 450	77.79 451	85.73 416	45.54 476	44.76 478	82.14 359	35.40 430	90.14 405	63.18 351	74.54 301	81.07 437
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
fmvsm_s_conf0.1_n_2		84.40 110	84.78 95	83.27 246	85.25 327	60.41 359	94.13 81	85.69 417	83.05 34	87.99 51	96.37 40	52.75 288	97.68 61	93.75 26	84.05 194	91.71 262

SD_0403		73.79 339	73.48 322	74.69 410	85.33 323	45.56 475	83.80 397	85.57 418	76.55 178	62.96 386	88.45 266	50.62 313	87.59 433	48.80 419	79.28 263	90.92 281

Fast-Effi-MVS+-dtu		75.04 323	73.37 323	80.07 339	80.86 388	59.52 377	91.20 257	85.38 419	71.90 268	65.20 362	84.84 325	41.46 391	92.97 332	66.50 316	72.96 314	87.73 325

Anonymous202405211		77.96 269	75.33 291	85.87 119	93.73 59	64.52 226	94.85 52	85.36 420	62.52 402	76.11 211	90.18 228	29.43 457	97.29 91	68.51 289	77.24 285	95.81 58

Anonymous20240521		62.09 427	59.08 431	71.10 440	67.19 481	48.72 459	83.91 396	85.23 421	50.38 463	47.84 468	71.22 460	20.74 479	85.51 447	46.47 433	58.75 429	79.06 455

our_test_3		68.29 393	64.69 401	79.11 366	78.92 418	64.85 217	88.40 346	85.06 422	60.32 422	52.68 446	76.12 435	40.81 395	89.80 411	44.25 444	55.65 437	82.67 423

USDC		67.43 402	64.51 403	76.19 397	77.94 433	55.29 422	78.38 447	85.00 423	73.17 233	48.36 467	80.37 389	21.23 478	92.48 357	52.15 404	64.02 388	80.81 440

TransMVSNet (Re)		70.07 376	67.66 381	77.31 385	80.62 395	59.13 384	91.78 217	84.94 424	65.97 367	60.08 411	80.44 388	50.78 310	91.87 374	48.84 418	45.46 471	80.94 438

KD-MVS_self_test		60.87 434	58.60 432	67.68 454	66.13 484	39.93 490	75.63 461	84.70 425	57.32 439	49.57 461	68.45 467	29.55 455	82.87 466	48.09 422	47.94 462	80.25 448

ACMH	63.93 17	68.62 388	64.81 399	80.03 341	85.22 328	63.25 282	87.72 359	84.66 426	60.83 418	51.57 452	79.43 402	27.29 463	94.96 241	41.76 453	64.84 378	81.88 430
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
dongtai		55.18 448	55.46 446	54.34 475	76.03 447	36.88 494	76.07 457	84.61 427	51.28 459	43.41 484	64.61 478	56.56 240	67.81 495	18.09 501	28.50 499	58.32 493

Baseline_NR-MVSNet		73.99 336	72.83 332	77.48 381	80.78 391	59.29 382	91.79 214	84.55 428	68.85 334	68.99 314	80.70 383	56.16 243	92.04 372	62.67 355	60.98 417	81.11 436

MIMVSNet1		60.16 439	57.33 438	68.67 450	69.71 475	44.13 478	78.92 444	84.21 429	55.05 450	44.63 479	71.85 455	23.91 470	81.54 475	32.63 485	55.03 440	80.35 445

test20.03		63.83 420	62.65 416	67.38 457	70.58 473	39.94 489	86.57 375	84.17 430	63.29 393	51.86 450	77.30 417	37.09 422	82.47 468	38.87 465	54.13 443	79.73 450

MDA-MVSNet_test_wron		63.78 422	60.16 426	74.64 411	78.15 431	60.41 359	83.49 401	84.03 431	56.17 448	39.17 489	71.59 457	37.22 419	83.24 465	42.87 449	48.73 460	80.26 447

ADS-MVSNet		68.54 390	64.38 406	81.03 318	88.06 235	66.90 159	68.01 477	84.02 432	57.57 435	64.48 369	69.87 462	38.68 401	89.21 414	40.87 457	67.89 354	86.97 339

CR-MVSNet		73.79 339	70.82 355	82.70 260	83.15 366	67.96 113	70.25 470	84.00 433	73.67 227	69.97 303	72.41 450	57.82 221	89.48 412	52.99 402	73.13 312	90.64 285

Patchmtry		67.53 400	63.93 408	78.34 370	82.12 377	64.38 235	68.72 474	84.00 433	48.23 470	59.24 414	72.41 450	57.82 221	89.27 413	46.10 435	56.68 436	81.36 433

test_fmvsmvis_n_1920		83.80 131	83.48 119	84.77 175	82.51 373	63.72 264	91.37 243	83.99 435	81.42 57	77.68 190	95.74 60	58.37 210	97.58 71	93.38 27	86.87 148	93.00 220

YYNet1		63.76 423	60.14 427	74.62 412	78.06 432	60.19 366	83.46 403	83.99 435	56.18 447	39.25 488	71.56 458	37.18 420	83.34 463	42.90 448	48.70 461	80.32 446

usedtu_dtu_shiyan2		57.76 443	53.69 449	69.95 445	57.60 497	41.80 483	83.50 400	83.67 437	45.26 477	43.79 482	62.82 481	17.63 485	85.93 443	42.56 452	46.40 469	82.12 429

LTVRE_ROB	59.60 19	66.27 407	63.54 410	74.45 414	84.00 354	51.55 440	67.08 481	83.53 438	58.78 431	54.94 436	80.31 390	34.54 433	93.23 326	40.64 459	68.03 350	78.58 462
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
pmmvs-eth3d		65.53 413	62.32 418	75.19 404	69.39 477	59.59 375	82.80 413	83.43 439	62.52 402	51.30 454	72.49 448	32.86 440	87.16 438	55.32 390	50.73 457	78.83 459

OpenMVS_ROB	61.12 18	66.39 406	62.92 414	76.80 393	76.51 442	57.77 396	89.22 328	83.41 440	55.48 449	53.86 441	77.84 412	26.28 466	93.95 301	34.90 473	68.76 344	78.68 461

PatchMatch-RL		72.06 361	69.98 360	78.28 372	89.51 177	55.70 420	83.49 401	83.39 441	61.24 415	63.72 378	82.76 350	34.77 432	93.03 330	53.37 401	77.59 277	86.12 368

MSDG		69.54 381	65.73 392	80.96 319	85.11 332	63.71 265	84.19 394	83.28 442	56.95 441	54.50 437	84.03 336	31.50 447	96.03 173	42.87 449	69.13 342	83.14 414

CHOSEN 280x420		77.35 281	76.95 265	78.55 369	87.07 270	62.68 300	69.71 473	82.95 443	68.80 335	71.48 285	87.27 293	66.03 81	84.00 456	76.47 208	82.81 212	88.95 306

ppachtmachnet_test		67.72 397	63.70 409	79.77 351	78.92 418	66.04 183	88.68 341	82.90 444	60.11 424	55.45 434	75.96 436	39.19 400	90.55 395	39.53 461	52.55 448	82.71 420

new-patchmatchnet		59.30 441	56.48 443	67.79 453	65.86 485	44.19 477	82.47 417	81.77 445	59.94 425	43.65 483	66.20 474	27.67 462	81.68 474	39.34 462	41.40 478	77.50 468

dtuonly		74.56 330	73.92 314	76.48 394	77.15 440	57.27 406	85.09 386	81.23 446	71.37 292	67.61 339	89.65 247	46.68 360	83.84 458	68.79 287	77.69 276	88.33 319

MDA-MVSNet-bldmvs		61.54 431	57.70 435	73.05 425	79.53 409	57.00 412	83.08 409	81.23 446	57.57 435	34.91 493	72.45 449	32.79 441	86.26 442	35.81 470	41.95 477	75.89 472

OurMVSNet-221017-0		64.68 415	62.17 419	72.21 433	76.08 446	47.35 464	80.67 431	81.02 448	56.19 446	51.60 451	79.66 400	27.05 464	88.56 418	53.60 399	53.63 444	80.71 441

ACMH+	65.35 16	67.65 398	64.55 402	76.96 391	84.59 341	57.10 408	88.08 350	80.79 449	58.59 433	53.00 445	81.09 381	26.63 465	92.95 333	46.51 432	61.69 413	80.82 439

CNLPA		74.31 332	72.30 341	80.32 331	91.49 134	61.66 326	90.85 270	80.72 450	56.67 444	63.85 377	90.64 215	46.75 359	90.84 393	53.79 397	75.99 294	88.47 316

mmtdpeth		68.33 392	66.37 388	74.21 418	82.81 371	51.73 438	84.34 392	80.42 451	67.01 357	71.56 283	68.58 466	30.52 454	92.35 363	75.89 213	36.21 487	78.56 463

LS3D		69.17 383	66.40 387	77.50 380	91.92 119	56.12 416	85.12 385	80.37 452	46.96 471	56.50 432	87.51 288	37.25 418	93.71 309	32.52 486	79.40 258	82.68 422

testgi		64.48 417	62.87 415	69.31 448	71.24 467	40.62 487	85.49 383	79.92 453	65.36 375	54.18 439	83.49 343	23.74 471	84.55 451	41.60 454	60.79 419	82.77 417

test_0402		64.54 416	61.09 423	74.92 409	84.10 353	60.75 348	87.95 354	79.71 454	52.03 456	52.41 447	77.20 420	32.21 445	91.64 380	23.14 495	61.03 416	72.36 480

SixPastTwentyTwo		64.92 414	61.78 422	74.34 416	78.74 422	49.76 452	83.42 404	79.51 455	62.86 398	50.27 458	77.35 416	30.92 452	90.49 397	45.89 436	47.06 465	82.78 416

dtuonlycased		63.47 424	62.08 420	67.64 455	73.22 463	52.55 434	86.25 379	79.10 456	65.40 373	49.47 463	67.33 472	36.80 425	82.37 470	53.47 400	47.68 463	68.01 484

mvs5depth		61.03 433	57.65 436	71.18 439	67.16 482	47.04 469	72.74 465	77.49 457	57.47 438	60.52 405	72.53 447	22.84 475	88.38 421	49.15 416	38.94 483	78.11 466

ITE_SJBPF				70.43 443	74.44 458	47.06 468		77.32 458	60.16 423	54.04 440	83.53 341	23.30 473	84.01 455	43.07 446	61.58 414	80.21 449

K. test v3		63.09 425	59.61 429	73.53 422	76.26 444	49.38 457	83.27 405	77.15 459	64.35 381	47.77 469	72.32 452	28.73 458	87.79 428	49.93 413	36.69 486	83.41 409

FE-MVSNET		60.52 436	57.18 440	70.53 442	67.53 480	50.68 447	82.62 415	76.28 460	59.33 429	46.71 470	71.10 461	30.54 453	83.61 460	33.15 480	47.37 464	77.29 469

DP-MVS		69.90 378	66.48 385	80.14 337	95.36 31	62.93 292	89.56 316	76.11 461	50.27 464	57.69 428	85.23 321	39.68 399	95.73 196	33.35 478	71.05 329	81.78 432

RPSCF		64.24 418	61.98 421	71.01 441	76.10 445	45.00 476	75.83 459	75.94 462	46.94 472	58.96 418	84.59 328	31.40 448	82.00 473	47.76 428	60.33 424	86.04 369

test_fmvs1_n		72.69 354	71.92 345	74.99 408	71.15 469	47.08 467	87.34 366	75.67 463	63.48 391	78.08 187	91.17 210	20.16 482	87.87 426	84.65 112	75.57 296	90.01 293

TinyColmap		60.32 437	56.42 444	72.00 437	78.78 421	53.18 432	78.36 448	75.64 464	52.30 455	41.59 487	75.82 438	14.76 491	88.35 422	35.84 469	54.71 442	74.46 474

ADS-MVSNet2		66.90 403	63.44 411	77.26 386	88.06 235	60.70 352	68.01 477	75.56 465	57.57 435	64.48 369	69.87 462	38.68 401	84.10 453	40.87 457	67.89 354	86.97 339

COLMAP_ROB	57.96 20	62.98 426	59.65 428	72.98 426	81.44 385	53.00 433	83.75 398	75.53 466	48.34 469	48.81 466	81.40 373	24.14 469	90.30 398	32.95 481	60.52 421	75.65 473
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Patchmatch-test		65.86 409	60.94 424	80.62 328	83.75 358	58.83 386	58.91 492	75.26 467	44.50 480	50.95 457	77.09 422	58.81 203	87.90 425	35.13 472	64.03 387	95.12 96

test_fmvs1		74.07 334	73.69 318	75.22 403	78.91 420	47.34 465	89.06 335	74.69 468	63.68 389	79.41 163	91.59 196	24.36 468	87.77 429	85.22 103	76.26 292	90.55 287

MVS-HIRNet		60.25 438	55.55 445	74.35 415	84.37 348	56.57 414	71.64 468	74.11 469	34.44 491	45.54 476	42.24 503	31.11 451	89.81 409	40.36 460	76.10 293	76.67 471

pmmvs3		55.51 446	51.50 452	67.53 456	57.90 496	50.93 446	80.37 433	73.66 470	40.63 489	44.15 481	64.75 477	16.30 486	78.97 481	44.77 443	40.98 481	72.69 478

tt0320		61.85 428	57.45 437	75.03 406	77.49 436	57.60 400	82.74 414	73.65 471	43.65 484	53.65 442	68.18 468	25.47 467	88.66 415	45.56 438	46.68 467	78.81 460

sc_t1		63.81 421	59.39 430	77.10 387	77.62 435	56.03 417	84.32 393	73.56 472	46.66 474	58.22 421	73.06 446	23.28 474	90.62 394	50.93 407	46.84 466	84.64 396

TDRefinement		55.28 447	51.58 451	66.39 459	59.53 495	46.15 472	76.23 456	72.80 473	44.60 479	42.49 485	76.28 434	15.29 489	82.39 469	33.20 479	43.75 473	70.62 482

MVStest1		51.35 451	46.89 455	64.74 460	65.06 486	51.10 444	67.33 480	72.58 474	30.20 495	35.30 491	74.82 441	27.70 461	69.89 492	24.44 494	24.57 500	73.22 476

Gipuma		34.91 466	31.44 469	45.30 483	70.99 470	39.64 492	19.85 513	72.56 475	20.10 503	16.16 509	21.47 521	5.08 506	71.16 490	13.07 509	43.70 474	25.08 514
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_vis1_n		71.63 365	70.73 356	74.31 417	69.63 476	47.29 466	86.91 370	72.11 476	63.21 395	75.18 225	90.17 234	20.40 480	85.76 444	84.59 114	74.42 303	89.87 294

FPMVS		45.64 457	43.10 461	53.23 476	51.42 502	36.46 495	64.97 483	71.91 477	29.13 496	27.53 499	61.55 485	9.83 498	65.01 501	16.00 507	55.58 438	58.22 494

dmvs_testset		65.55 412	66.45 386	62.86 464	79.87 405	22.35 512	76.55 454	71.74 478	77.42 156	55.85 433	87.77 283	51.39 303	80.69 477	31.51 490	65.92 367	85.55 383

ANet_high		40.27 463	35.20 466	55.47 471	34.74 515	34.47 498	63.84 485	71.56 479	48.42 468	18.80 504	41.08 505	9.52 499	64.45 502	20.18 498	8.66 513	67.49 486

Patchmatch-RL test		68.17 394	64.49 404	79.19 362	71.22 468	53.93 429	70.07 472	71.54 480	69.22 327	56.79 431	62.89 480	56.58 239	88.61 416	69.53 276	52.61 447	95.03 102

tt0320-xc		61.51 432	56.89 441	75.37 402	78.50 426	58.61 389	82.61 416	71.27 481	44.31 481	53.17 444	68.03 470	23.38 472	88.46 420	47.77 427	43.00 476	79.03 457

LCM-MVSNet-Re		72.93 347	71.84 346	76.18 398	88.49 215	48.02 460	80.07 439	70.17 482	73.96 217	52.25 448	80.09 395	49.98 319	88.24 423	67.35 304	84.23 190	92.28 245

test_fmvs2		65.78 411	64.84 398	68.60 451	66.54 483	41.71 484	83.27 405	69.81 483	54.38 451	67.91 332	84.54 330	15.35 488	81.22 476	75.65 215	66.16 364	82.88 415

LCM-MVSNet		40.54 460	35.79 465	54.76 474	36.92 513	30.81 502	51.41 498	69.02 484	22.07 500	24.63 501	45.37 498	4.56 507	65.81 498	33.67 477	34.50 492	67.67 485

AllTest		61.66 429	58.06 433	72.46 430	79.57 407	51.42 442	80.17 437	68.61 485	51.25 460	45.88 472	81.23 375	19.86 483	86.58 440	38.98 463	57.01 434	79.39 452

TestCases				72.46 430	79.57 407	51.42 442		68.61 485	51.25 460	45.88 472	81.23 375	19.86 483	86.58 440	38.98 463	57.01 434	79.39 452

LF4IMVS		54.01 449	52.12 450	59.69 467	62.41 490	39.91 491	68.59 475	68.28 487	42.96 486	44.55 480	75.18 439	14.09 493	68.39 494	41.36 456	51.68 449	70.78 481

door								66.57 488

door-mid								66.01 489

ttmdpeth		53.34 450	49.96 453	63.45 463	62.07 492	40.04 488	72.06 466	65.64 490	42.54 487	51.88 449	77.79 413	13.94 494	76.48 483	32.93 482	30.82 497	73.84 475

test_fmvs3		56.82 444	54.86 447	62.69 466	53.59 499	35.47 496	75.87 458	65.64 490	43.91 482	55.10 435	71.43 459	6.91 503	74.40 487	68.64 288	52.63 446	78.20 465

DSMNet-mixed		56.78 445	54.44 448	63.79 462	63.21 488	29.44 505	64.43 484	64.10 492	42.12 488	51.32 453	71.60 456	31.76 446	75.04 485	36.23 468	65.20 375	86.87 344

PM-MVS		59.40 440	56.59 442	67.84 452	63.63 487	41.86 482	76.76 453	63.22 493	59.01 430	51.07 455	72.27 453	11.72 495	83.25 464	61.34 362	50.28 459	78.39 464

new_pmnet		49.31 453	46.44 456	57.93 468	62.84 489	40.74 486	68.47 476	62.96 494	36.48 490	35.09 492	57.81 490	14.97 490	72.18 489	32.86 483	46.44 468	60.88 492

lessismore_v0				73.72 421	72.93 465	47.83 462		61.72 495		45.86 474	73.76 444	28.63 460	89.81 409	47.75 429	31.37 494	83.53 405

mvsany_test1		68.77 387	68.56 375	69.39 447	73.57 461	45.88 474	80.93 430	60.88 496	59.65 426	71.56 283	90.26 227	43.22 385	75.05 484	74.26 229	62.70 399	87.25 337

EGC-MVSNET		42.35 459	38.09 462	55.11 472	74.57 457	46.62 470	71.63 469	55.77 497	0.04 549	0.24 551	62.70 482	14.24 492	74.91 486	17.59 502	46.06 470	43.80 498

WB-MVS		46.23 456	44.94 458	50.11 478	62.13 491	21.23 514	76.48 455	55.49 498	45.89 475	35.78 490	61.44 486	35.54 429	72.83 488	9.96 513	21.75 501	56.27 495

SSC-MVS		44.51 458	43.35 460	47.99 482	61.01 494	18.90 516	74.12 463	54.36 499	43.42 485	34.10 494	60.02 489	34.42 434	70.39 491	9.14 515	19.57 502	54.68 496

test_method		38.59 464	35.16 467	48.89 480	54.33 498	21.35 513	45.32 503	53.71 500	7.41 515	28.74 497	51.62 493	8.70 500	52.87 506	33.73 476	32.89 493	72.47 479

APD_test1		40.50 461	37.31 464	50.09 479	51.88 500	35.27 497	59.45 491	52.59 501	21.64 501	26.12 500	57.80 491	4.56 507	66.56 497	22.64 496	39.09 482	48.43 497

PMMVS2		37.93 465	33.61 468	50.92 477	46.31 504	24.76 508	60.55 490	50.05 502	28.94 497	20.93 502	47.59 494	4.41 509	65.13 500	25.14 493	18.55 504	62.87 490

PMVS	26.43 22	31.84 471	28.16 474	42.89 486	25.87 519	27.58 506	50.92 500	49.78 503	21.37 502	14.17 511	40.81 506	2.01 513	66.62 496	9.61 514	38.88 485	34.49 507
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_f		46.58 455	43.45 459	55.96 470	45.18 506	32.05 500	61.18 487	49.49 504	33.39 492	42.05 486	62.48 483	7.00 502	65.56 499	47.08 431	43.21 475	70.27 483

test_vis1_rt		59.09 442	57.31 439	64.43 461	68.44 479	46.02 473	83.05 411	48.63 505	51.96 457	49.57 461	63.86 479	16.30 486	80.20 478	71.21 262	62.79 398	67.07 487

mvsany_test3		48.86 454	46.35 457	56.41 469	46.00 505	31.67 501	62.26 486	47.25 506	43.71 483	45.54 476	68.15 469	10.84 496	64.44 503	57.95 379	35.44 491	73.13 477

testf1		32.77 469	29.47 471	42.67 487	41.89 509	30.81 502	52.07 496	43.45 507	15.45 504	18.52 505	44.82 499	2.12 511	58.38 504	16.05 505	30.87 495	38.83 502

APD_test2		32.77 469	29.47 471	42.67 487	41.89 509	30.81 502	52.07 496	43.45 507	15.45 504	18.52 505	44.82 499	2.12 511	58.38 504	16.05 505	30.87 495	38.83 502

E-PMN		24.61 472	24.00 476	26.45 492	43.74 508	18.44 517	60.86 488	39.66 509	15.11 507	9.53 519	22.10 520	6.52 504	46.94 509	8.31 516	10.14 510	13.98 518

tmp_tt		22.26 475	23.75 477	17.80 499	5.23 537	12.06 521	35.26 504	39.48 510	2.82 521	18.94 503	44.20 502	22.23 477	24.64 516	36.30 467	9.31 512	16.69 517

MVE	24.84 23	24.35 473	19.77 479	38.09 489	34.56 516	26.92 507	26.57 506	38.87 511	11.73 511	11.37 515	27.44 515	1.37 516	50.42 507	11.41 512	14.60 505	36.93 504
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		23.76 474	23.20 478	25.46 495	41.52 511	16.90 518	60.56 489	38.79 512	14.62 508	8.99 521	20.24 523	7.35 501	45.82 510	7.25 519	9.46 511	13.64 519

test_vis3_rt		40.46 462	37.79 463	48.47 481	44.49 507	33.35 499	66.56 482	32.84 513	32.39 493	29.65 495	39.13 509	3.91 510	68.65 493	50.17 410	40.99 480	43.40 499

MTMP							93.77 106	32.52 514

DeepMVS_CX				34.71 490	51.45 501	24.73 509		28.48 515	31.46 494	17.49 507	52.75 492	5.80 505	42.60 512	18.18 500	19.42 503	36.81 505

ArgMatch-SfM		33.21 467	29.25 473	45.06 484	35.86 514	22.89 511	48.07 502	16.80 516	23.93 499	27.57 498	61.10 488	1.59 515	47.14 508	34.29 474	14.08 506	65.16 488

ArgMatch-Sym		33.10 468	29.80 470	43.01 485	37.34 512	24.00 510	51.27 499	13.51 517	26.37 498	28.91 496	61.40 487	1.65 514	43.37 511	34.16 475	13.61 507	61.66 491

LoFTR		18.06 479	15.31 483	26.33 493	21.95 520	10.94 522	21.35 511	12.80 518	6.90 516	12.24 513	41.28 504	0.46 521	27.67 515	7.81 517	12.96 508	40.38 501

MatchFormer		14.02 482	12.22 485	19.42 498	17.64 523	8.79 525	19.96 512	10.04 519	4.23 517	10.54 518	32.75 513	0.31 528	22.88 518	4.03 524	10.48 509	26.57 511

DenseAffine		21.45 476	18.65 480	29.86 491	28.31 517	16.04 519	32.25 505	6.12 520	15.38 506	16.38 508	44.57 501	0.55 519	32.44 513	16.82 503	7.46 515	41.09 500

GLUNet-SfM		8.91 486	6.39 495	16.47 501	9.50 529	4.77 528	5.87 523	5.53 521	2.45 522	6.66 523	22.23 519	0.25 532	15.78 521	2.84 525	2.14 534	28.86 510

PDCNetPlus		17.19 480	15.58 482	22.00 496	25.94 518	10.36 524	23.05 510	5.04 522	12.02 510	10.87 517	39.50 508	0.88 517	23.24 517	18.38 499	4.57 520	32.39 509

ELoFTR		8.49 487	6.65 494	14.00 503	5.91 531	3.43 534	7.42 520	4.01 523	2.94 520	6.41 524	25.06 516	0.11 538	15.41 523	5.10 523	2.92 527	23.17 515

RoMa-SfM		18.71 478	16.37 481	25.74 494	19.88 521	12.86 520	26.27 507	3.78 524	13.07 509	15.56 510	45.71 497	0.48 520	28.39 514	16.22 504	6.37 516	35.97 506

MASt3R-SfM		8.20 489	8.57 492	7.11 507	5.75 534	3.12 535	9.54 517	3.21 525	2.39 524	9.18 520	34.80 512	0.37 523	5.21 527	6.46 520	5.41 517	12.99 521

DKM		16.33 481	14.55 484	21.65 497	19.49 522	10.79 523	24.23 509	2.86 526	10.86 512	13.52 512	40.31 507	0.32 526	21.73 519	14.27 508	5.12 518	32.43 508

ALIKED-LG		4.67 494	4.76 498	4.39 508	11.74 526	4.58 530	8.52 518	2.37 527	1.12 525	3.02 527	10.43 524	0.40 522	4.25 528	0.52 533	4.70 519	4.35 522

RoMa-HiRes		13.29 483	12.09 486	16.86 500	12.76 525	7.74 526	17.91 515	2.10 528	8.64 513	11.87 514	39.11 510	0.36 524	17.55 520	12.17 510	3.91 523	25.30 513

ALIKED-MNN		4.24 496	4.26 499	4.20 509	10.96 527	4.68 529	7.92 519	2.00 529	0.81 526	2.44 532	9.09 526	0.30 529	4.03 529	0.46 534	4.36 522	3.88 525

N_pmnet		50.55 452	49.11 454	54.88 473	77.17 439	4.02 532	84.36 391	2.00 529	48.59 467	45.86 474	68.82 465	32.22 444	82.80 467	31.58 488	51.38 450	77.81 467

ALIKED-NN		4.04 497	4.13 500	3.78 510	10.26 528	4.26 531	7.33 521	1.98 531	0.76 527	2.52 529	9.08 527	0.32 526	3.67 530	0.44 535	4.45 521	3.40 529

wuyk23d		11.30 485	10.95 488	12.33 504	48.05 503	19.89 515	25.89 508	1.92 532	3.58 518	3.12 526	1.37 549	0.64 518	15.77 522	6.23 521	7.77 514	1.35 532

DKM-HiRes		12.72 484	11.70 487	15.79 502	14.70 524	7.68 527	18.04 514	1.85 533	8.12 514	11.31 516	35.19 511	0.24 534	14.23 524	12.15 511	3.71 524	25.48 512

XFeat-MNN		2.31 498	2.37 501	2.13 511	1.47 554	0.97 549	3.08 529	1.31 534	0.53 529	2.60 528	7.72 528	0.22 536	2.31 531	1.02 527	3.40 525	3.10 530

PMatch-SfM		8.29 488	7.44 493	10.83 505	6.92 530	3.67 533	9.75 516	1.15 535	3.49 519	6.97 522	28.70 514	0.04 550	8.89 525	7.67 518	2.24 533	19.92 516

SP-DiffGlue		2.24 499	2.34 502	1.94 515	1.88 553	1.08 543	3.10 528	1.13 536	0.55 528	2.52 529	7.60 529	0.33 525	0.99 537	1.25 526	2.70 528	3.76 527

SP-SuperGlue		2.21 501	2.29 504	1.97 513	5.76 533	1.01 545	4.31 524	1.06 537	0.50 530	1.22 533	4.35 532	0.28 530	1.04 536	0.64 529	2.52 530	3.86 526

SP-LightGlue		2.23 500	2.31 503	1.99 512	5.90 532	1.01 545	4.31 524	1.04 538	0.50 530	1.20 534	4.36 531	0.28 530	1.06 534	0.64 529	2.57 529	3.91 523

SP-MNN		2.16 502	2.22 505	1.97 513	5.52 535	0.92 550	4.28 526	1.01 539	0.41 533	1.13 535	4.35 532	0.23 535	1.09 533	0.61 531	2.45 531	3.91 523

XFeat-NN		1.98 504	2.09 507	1.67 517	1.35 555	0.77 554	2.62 530	0.97 540	0.41 533	2.46 531	6.79 530	0.19 537	1.75 532	0.84 528	3.18 526	2.48 531

SP-NN		2.08 503	2.16 506	1.87 516	5.30 536	0.91 551	4.18 527	0.96 541	0.43 532	1.09 536	4.20 534	0.25 532	1.06 534	0.60 532	2.38 532	3.63 528

PMatch-Up-SfM		6.11 493	5.72 497	7.28 506	5.02 538	2.48 536	7.03 522	0.71 542	2.41 523	5.37 525	23.67 517	0.03 554	5.84 526	5.77 522	1.48 544	13.50 520

SIFT-NN		1.43 505	1.51 508	1.19 518	4.60 539	1.57 537	2.30 531	0.51 543	0.34 535	0.74 537	2.84 535	0.08 539	0.84 538	0.13 537	2.07 535	1.15 533

SIFT-MNN		1.35 506	1.42 509	1.14 519	4.26 540	1.44 538	2.10 532	0.51 543	0.34 535	0.64 538	2.76 536	0.07 540	0.83 539	0.13 537	1.98 537	1.15 533

SIFT-NN-NCMNet		1.29 507	1.36 510	1.08 520	3.95 542	1.39 539	2.05 533	0.49 545	0.33 537	0.63 540	2.62 539	0.07 540	0.81 540	0.12 539	2.02 536	1.05 537

SIFT-NCM-Cal		1.23 508	1.30 511	1.04 521	4.06 541	1.29 540	1.92 535	0.42 546	0.33 537	0.45 545	2.46 542	0.06 545	0.81 540	0.10 546	1.89 538	1.02 539

SIFT-NN-UMatch		1.16 510	1.23 513	0.96 523	3.23 548	1.06 544	1.93 534	0.42 546	0.33 537	0.53 542	2.63 537	0.07 540	0.77 542	0.11 542	1.79 539	1.05 537

SIFT-NN-CMatch		1.18 509	1.24 512	1.01 522	3.44 546	1.19 542	1.78 536	0.42 546	0.33 537	0.64 538	2.63 537	0.07 540	0.77 542	0.12 539	1.73 540	1.08 535

SIFT-ConvMatch		1.15 511	1.22 514	0.96 523	3.82 543	1.20 541	1.64 539	0.38 549	0.33 537	0.52 543	2.53 540	0.06 545	0.76 544	0.11 542	1.59 542	0.91 540

SIFT-NN-PointCN		1.06 513	1.12 516	0.88 525	2.98 549	0.84 553	1.67 538	0.37 550	0.30 545	0.54 541	2.38 543	0.07 540	0.72 546	0.11 542	1.64 541	1.07 536

SIFT-UMatch		1.11 512	1.18 515	0.87 526	3.66 544	1.00 548	1.70 537	0.35 551	0.32 542	0.46 544	2.50 541	0.06 545	0.75 545	0.11 542	1.51 543	0.87 542

SIFT-CM-Cal		1.03 514	1.10 517	0.85 527	3.54 545	1.01 545	1.42 541	0.32 552	0.32 542	0.44 546	2.30 545	0.06 545	0.71 547	0.09 548	1.37 545	0.82 543

SIFT-PointCN		0.88 516	0.94 519	0.69 530	2.88 551	0.61 555	1.32 542	0.30 553	0.28 546	0.36 548	1.93 547	0.04 550	0.62 549	0.09 548	1.26 547	0.82 543

SIFT-UM-Cal		1.01 515	1.09 518	0.77 528	3.43 547	0.85 552	1.49 540	0.29 554	0.31 544	0.42 547	2.34 544	0.06 545	0.69 548	0.10 546	1.37 545	0.77 545

SIFT-PCN-Cal		0.88 516	0.93 520	0.70 529	2.93 550	0.60 556	1.22 543	0.27 555	0.28 546	0.36 548	2.00 546	0.04 550	0.61 550	0.09 548	1.23 548	0.89 541

SIFT-NCMNet		0.73 518	0.80 521	0.54 531	2.66 552	0.54 557	1.00 544	0.16 556	0.28 546	0.32 550	1.65 548	0.04 550	0.51 551	0.07 551	0.98 549	0.58 546

testmvs		7.23 491	9.62 490	0.06 533	0.04 556	0.02 559	84.98 388	0.02 557	0.03 550	0.18 552	1.21 550	0.01 556	0.02 552	0.14 536	0.01 550	0.13 548

test123		6.92 492	9.21 491	0.08 532	0.03 557	0.05 558	81.65 423	0.01 558	0.02 551	0.14 553	0.85 551	0.03 554	0.02 552	0.12 539	0.00 551	0.16 547

mmdepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 551	0.00 549

monomultidepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 551	0.00 549

test_blank		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 551	0.00 549

uanet_test		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 551	0.00 549

DCPMVS		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 551	0.00 549

pcd_1.5k_mvsjas		4.46 495	5.95 496	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	53.55 279	0.00 554	0.00 552	0.00 551	0.00 549

sosnet-low-res		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 551	0.00 549

sosnet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 551	0.00 549

uncertanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 551	0.00 549

Regformer		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 551	0.00 549

n2								0.00 559

nn								0.00 559

ab-mvs-re		7.91 490	10.55 489	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	94.95 88	0.00 557	0.00 554	0.00 552	0.00 551	0.00 549

uanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 551	0.00 549

WAC-MVS						49.45 455								31.56 489

PC_three_1452									80.91 65	94.07 3	96.83 30	83.57 4	99.12 6	95.70 10	97.42 4	97.55 5

eth-test2					0.00 558

eth-test					0.00 558

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

test_0728_THIRD									72.48 250	90.55 30	96.93 20	76.24 13	99.08 12	91.53 48	94.99 18	96.43 32

GSMVS																94.68 127

test_part2					96.29 21	68.16 109				90.78 27

sam_mvs1												57.85 220				94.68 127

sam_mvs												54.91 260

test_post1							78.95 443				20.70 522	53.05 284	91.50 389	60.43 368

test_post											23.01 518	56.49 241	92.67 349

patchmatchnet-post											67.62 471	57.62 223	90.25 399

gm-plane-assit					88.42 221	67.04 148			78.62 128		91.83 185		97.37 85	76.57 207

test9_res														89.41 58	94.96 19	95.29 84

agg_prior2														86.41 92	94.75 32	95.33 79

test_prior4						67.18 143	93.92 95

test_prior2							95.10 39		75.40 191	85.25 83	95.61 63	67.94 64		87.47 78	94.77 28

旧先验2							92.00 202		59.37 428	87.54 57			93.47 317	75.39 217

新几何2							91.41 236

原ACMM2							92.01 199

testdata2													96.09 167	61.26 363

segment_acmp												65.94 82

testdata1							89.21 329		77.55 152

plane_prior7					86.94 278	61.51 330

plane_prior6					87.23 261	62.32 308						50.66 311

plane_prior4											89.14 257

plane_prior3						61.95 317			79.09 117	72.53 265

plane_prior2							93.13 134		78.81 124

plane_prior1					87.15 266

plane_prior						62.42 304	93.85 99		79.38 109						78.80 267

HQP5-MVS						63.66 270

HQP-NCC					87.54 253		94.06 83		79.80 91	74.18 238

ACMP_Plane					87.54 253		94.06 83		79.80 91	74.18 238

BP-MVS														77.63 200

HQP4-MVS										74.18 238			95.61 210			88.63 311

HQP2-MVS												51.63 299

NP-MVS					87.41 256	63.04 288					90.30 225

MDTV_nov1_ep13_2view						59.90 371	80.13 438		67.65 350	72.79 259		54.33 270		59.83 372		92.58 234

ACMMP++_ref															71.63 323

ACMMP++															69.72 334

Test By Simon												54.21 273

High-resolution multi-view benchmark