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		78.37 212	77.01 215	82.46 211	91.89 113	63.21 224	91.19 214	96.33 1	72.28 210	70.45 239	87.89 229	60.31 150	95.32 187	45.16 367	77.58 225	88.83 250

thres600view7		78.00 217	76.66 220	82.03 231	91.93 109	63.69 208	91.30 207	96.33 1	72.43 205	70.46 238	87.89 229	60.31 150	94.92 202	42.64 379	76.64 235	87.48 271

thres200		79.66 185	78.33 190	83.66 182	92.54 91	65.82 151	93.06 122	96.31 3	74.90 156	73.30 200	88.66 212	59.67 159	95.61 174	47.84 356	78.67 216	89.56 245

tfpn200view9		78.79 204	77.43 206	82.88 201	92.21 97	64.49 177	92.05 169	96.28 4	73.48 182	71.75 224	88.26 220	60.07 155	95.32 187	45.16 367	77.58 225	88.83 250

thres400		78.68 206	77.43 206	82.43 212	92.21 97	64.49 177	92.05 169	96.28 4	73.48 182	71.75 224	88.26 220	60.07 155	95.32 187	45.16 367	77.58 225	87.48 271

MM		90.87 2	91.52 2	88.92 15	92.12 101	71.10 27	97.02 3	96.04 6	88.70 2	91.57 17	96.19 40	70.12 47	98.91 18	96.83 1	95.06 17	96.76 15

VNet		86.20 57	85.65 69	87.84 30	93.92 47	69.99 39	95.73 23	95.94 7	78.43 104	86.00 61	93.07 130	58.22 178	97.00 102	85.22 87	84.33 162	96.52 23

baseline2		83.68 114	83.42 105	84.48 151	87.37 228	66.00 145	90.06 252	95.93 8	79.71 77	69.08 255	90.39 187	77.92 6	96.28 141	78.91 150	81.38 192	91.16 223

testing222		85.18 79	84.69 86	86.63 68	92.91 78	69.91 43	92.61 146	95.80 9	80.31 65	80.38 121	92.27 150	68.73 51	95.19 192	75.94 167	83.27 172	94.81 100

BP-MVS1		86.54 50	86.68 50	86.13 86	87.80 218	67.18 115	92.97 127	95.62 10	79.92 72	82.84 93	94.14 109	74.95 15	96.46 134	82.91 113	88.96 112	94.74 101

testing11		86.71 48	86.44 52	87.55 40	93.54 60	71.35 21	93.65 97	95.58 11	81.36 53	80.69 116	92.21 153	72.30 36	96.46 134	85.18 89	83.43 170	94.82 99

MCST-MVS		91.08 1	91.46 3	89.94 4	97.66 2	73.37 10	97.13 2	95.58 11	89.33 1	85.77 63	96.26 38	72.84 30	99.38 1	92.64 29	95.93 9	97.08 11

UBG		86.83 43	86.70 48	87.20 48	93.07 74	69.81 47	93.43 111	95.56 13	81.52 46	81.50 104	92.12 154	73.58 26	96.28 141	84.37 99	85.20 152	95.51 59

MVS		84.66 89	82.86 121	90.06 2	90.93 138	74.56 7	87.91 295	95.54 14	68.55 283	72.35 217	94.71 87	59.78 158	98.90 20	81.29 129	94.69 32	96.74 16

ETVMVS		84.22 100	83.71 94	85.76 99	92.58 90	68.25 86	92.45 154	95.53 15	79.54 80	79.46 132	91.64 167	70.29 46	94.18 232	69.16 229	82.76 178	94.84 96

testing3-2		83.11 124	83.15 114	82.98 199	91.92 110	64.01 197	94.39 59	95.37 16	78.32 105	75.53 179	90.06 199	73.18 27	93.18 264	74.34 183	75.27 243	91.77 208

DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 162	76.68 2	97.29 1	95.35 17	82.87 31	91.58 16	97.22 5	79.93 5	99.10 9	83.12 111	97.64 2	97.94 1

CSCG		86.87 40	86.26 54	88.72 17	95.05 31	70.79 29	93.83 90	95.33 18	68.48 285	77.63 155	94.35 100	73.04 28	98.45 30	84.92 93	93.71 47	96.92 14

myMVS_eth3d28		86.31 55	86.15 58	86.78 63	93.56 58	70.49 33	92.94 129	95.28 19	82.47 35	78.70 146	92.07 156	72.45 34	95.41 183	82.11 119	85.78 148	94.44 121

WTY-MVS		86.32 54	85.81 65	87.85 29	92.82 82	69.37 58	95.20 34	95.25 20	82.71 32	81.91 101	94.73 86	67.93 58	97.63 60	79.55 142	82.25 181	96.54 22

testing99		86.01 61	85.47 71	87.63 38	93.62 55	71.25 23	93.47 109	95.23 21	80.42 64	80.60 118	91.95 159	71.73 41	96.50 132	80.02 139	82.22 182	95.13 80

patch_mono-2		89.71 11	90.99 6	85.85 95	96.04 24	63.70 207	95.04 41	95.19 22	86.74 7	91.53 18	95.15 75	73.86 22	97.58 63	93.38 23	92.00 69	96.28 37

IU-MVS					96.46 11	69.91 43		95.18 23	80.75 59	95.28 1				92.34 31	95.36 14	96.47 28

IB-MVS	77.80 4	82.18 139	80.46 160	87.35 45	89.14 179	70.28 36	95.59 26	95.17 24	78.85 96	70.19 243	85.82 259	70.66 44	97.67 55	72.19 203	66.52 305	94.09 136
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 43	86.85 47	86.78 63	93.47 63	65.55 157	95.39 30	95.10 25	71.77 228	85.69 65	96.52 27	62.07 133	98.77 23	86.06 83	95.60 12	96.03 43

test_yl		84.28 96	83.16 112	87.64 34	94.52 37	69.24 60	95.78 18	95.09 26	69.19 275	81.09 110	92.88 136	57.00 191	97.44 71	81.11 131	81.76 188	96.23 38

DCV-MVSNet		84.28 96	83.16 112	87.64 34	94.52 37	69.24 60	95.78 18	95.09 26	69.19 275	81.09 110	92.88 136	57.00 191	97.44 71	81.11 131	81.76 188	96.23 38

testing91		85.93 63	85.31 75	87.78 32	93.59 57	71.47 19	93.50 106	95.08 28	80.26 66	80.53 119	91.93 160	70.43 45	96.51 131	80.32 137	82.13 184	95.37 64

MSC_two_6792asdad				89.60 9	97.31 4	73.22 12		95.05 29					99.07 13	92.01 34	94.77 26	96.51 24

No_MVS				89.60 9	97.31 4	73.22 12		95.05 29					99.07 13	92.01 34	94.77 26	96.51 24

sss		82.71 132	82.38 129	83.73 176	89.25 174	59.58 309	92.24 159	94.89 31	77.96 110	79.86 127	92.38 147	56.70 197	97.05 97	77.26 161	80.86 196	94.55 111

EPNet		87.84 25	88.38 22	86.23 83	93.30 65	66.05 143	95.26 32	94.84 32	87.09 5	88.06 40	94.53 91	66.79 65	97.34 78	83.89 104	91.68 75	95.29 71
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 22	96.76 8	70.65 30	96.47 14	94.83 33	84.83 13	89.07 36	96.80 22	70.86 43	99.06 15	92.64 29	95.71 11	96.12 40

EI-MVSNet-Vis-set		83.77 110	83.67 95	84.06 164	92.79 85	63.56 213	91.76 186	94.81 34	79.65 78	77.87 152	94.09 110	63.35 116	97.90 44	79.35 144	79.36 209	90.74 227

tttt0517		79.50 188	78.53 189	82.41 215	87.22 232	61.43 268	89.75 261	94.76 35	69.29 273	67.91 274	88.06 227	72.92 29	95.63 172	62.91 288	73.90 255	90.16 234

GG-mvs-BLEND				86.53 74	91.91 112	69.67 53	75.02 389	94.75 36		78.67 147	90.85 179	77.91 7	94.56 217	72.25 200	93.74 45	95.36 66

gg-mvs-nofinetune		77.18 230	74.31 252	85.80 97	91.42 126	68.36 80	71.78 394	94.72 37	49.61 394	77.12 162	45.92 420	77.41 8	93.98 245	67.62 244	93.16 55	95.05 85

UWE-MVS		80.81 165	81.01 148	80.20 271	89.33 171	57.05 338	91.91 177	94.71 38	75.67 144	75.01 184	89.37 205	63.13 120	91.44 324	67.19 249	82.80 177	92.12 203

thisisatest0515		83.41 117	82.49 127	86.16 85	89.46 168	68.26 84	93.54 103	94.70 39	74.31 163	75.75 172	90.92 177	72.62 32	96.52 130	69.64 221	81.50 191	93.71 151

EI-MVSNet-UG-set		83.14 123	82.96 116	83.67 181	92.28 94	63.19 225	91.38 201	94.68 40	79.22 87	76.60 167	93.75 116	62.64 126	97.76 50	78.07 157	78.01 220	90.05 236

VPA-MVSNet		79.03 196	78.00 196	82.11 229	85.95 261	64.48 179	93.22 118	94.66 41	75.05 154	74.04 195	84.95 267	52.17 250	93.52 258	74.90 179	67.04 301	88.32 262

NCCC		89.07 16	89.46 15	87.91 28	96.60 10	69.05 64	96.38 15	94.64 42	84.42 15	86.74 53	96.20 39	66.56 68	98.76 24	89.03 56	94.56 34	95.92 46

ET-MVSNet_ETH3D		84.01 104	83.15 114	86.58 71	90.78 143	70.89 28	94.74 49	94.62 43	81.44 50	58.19 352	93.64 120	73.64 25	92.35 298	82.66 115	78.66 217	96.50 27

thisisatest0530		81.15 156	80.07 162	84.39 154	88.26 202	65.63 154	91.40 197	94.62 43	71.27 245	70.93 233	89.18 207	72.47 33	96.04 155	65.62 267	76.89 234	91.49 212

UWE-MVS-28		76.83 239	77.60 203	74.51 341	84.58 288	50.34 375	88.22 289	94.60 45	74.46 159	66.66 294	88.98 211	62.53 128	85.50 376	57.55 317	80.80 199	87.69 268

DVP-MVS		89.41 13	89.73 14	88.45 25	96.40 15	69.99 39	96.64 10	94.52 46	71.92 218	90.55 23	96.93 13	73.77 23	99.08 11	91.91 37	94.90 22	96.29 35
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 96	83.36 108	87.02 55	92.22 96	67.74 99	84.65 323	94.50 47	79.15 89	82.23 99	87.93 228	66.88 64	96.94 112	80.53 134	82.20 183	96.39 33

HPM-MVS++		89.37 14	89.95 13	87.64 34	95.10 30	68.23 87	95.24 33	94.49 48	82.43 36	88.90 37	96.35 33	71.89 40	98.63 26	88.76 57	96.40 6	96.06 41

MG-MVS		87.11 37	86.27 53	89.62 8	97.79 1	76.27 4	94.96 45	94.49 48	78.74 100	83.87 84	92.94 133	64.34 96	96.94 112	75.19 173	94.09 38	95.66 53

SED-MVS		89.94 9	90.36 10	88.70 18	96.45 12	69.38 56	96.89 6	94.44 50	71.65 232	92.11 8	97.21 6	76.79 9	99.11 6	92.34 31	95.36 14	97.62 2

test_241102_ONE					96.45 12	69.38 56		94.44 50	71.65 232	92.11 8	97.05 9	76.79 9	99.11 6

test_241102_TWO								94.41 52	71.65 232	92.07 10	97.21 6	74.58 18	99.11 6	92.34 31	95.36 14	96.59 19

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 138	93.00 76	58.16 325	96.72 9	94.41 52	86.50 8	90.25 27	97.83 1	75.46 14	98.67 25	92.78 28	95.49 13	97.32 6

DELS-MVS		90.05 8	90.09 11	89.94 4	93.14 71	73.88 9	97.01 4	94.40 54	88.32 3	85.71 64	94.91 82	74.11 21	98.91 18	87.26 71	95.94 8	97.03 12
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	82.69 133	80.82 150	88.31 26	89.57 164	71.26 22	92.60 147	94.39 55	78.84 97	67.89 276	92.48 145	48.42 286	98.52 28	68.80 234	94.40 36	95.15 79

DVP-MVS++		90.53 4	91.09 5	88.87 16	97.31 4	69.91 43	93.96 78	94.37 56	72.48 202	92.07 10	96.85 19	83.82 2	99.15 2	91.53 39	97.42 4	97.55 4

test_0728_SECOND				88.70 18	96.45 12	70.43 34	96.64 10	94.37 56					99.15 2	91.91 37	94.90 22	96.51 24

test0726					96.40 15	69.99 39	96.76 8	94.33 58	71.92 218	91.89 12	97.11 8	73.77 23

MSP-MVS		90.38 5	91.87 1	85.88 92	92.83 80	64.03 196	93.06 122	94.33 58	82.19 39	93.65 3	96.15 42	85.89 1	97.19 89	91.02 43	97.75 1	96.43 31
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		84.18 101	83.43 103	86.44 76	96.25 21	65.93 148	94.28 62	94.27 60	74.41 160	79.16 137	95.61 54	53.99 231	98.88 22	69.62 223	93.26 54	94.50 117
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 18	69.74 50		94.18 61	71.42 243	90.67 22	96.85 19	74.45 20

9.14			87.63 32		93.86 48		94.41 56	94.18 61	72.76 197	86.21 57	96.51 28	66.64 66	97.88 46	90.08 48	94.04 39

DPE-MVS		88.77 17	89.21 16	87.45 43	96.26 20	67.56 104	94.17 64	94.15 63	68.77 281	90.74 21	97.27 3	76.09 12	98.49 29	90.58 47	94.91 21	96.30 34
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
WB-MVSnew		77.14 231	76.18 227	80.01 277	86.18 256	63.24 222	91.26 208	94.11 64	71.72 230	73.52 198	87.29 240	45.14 314	93.00 268	56.98 318	79.42 207	83.80 333

DeepC-MVS_fast	79.48 2	87.95 23	88.00 28	87.79 31	95.86 27	68.32 81	95.74 21	94.11 64	83.82 20	83.49 86	96.19 40	64.53 95	98.44 31	83.42 110	94.88 25	96.61 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SMA-MVS		88.14 18	88.29 24	87.67 33	93.21 68	68.72 73	93.85 85	94.03 66	74.18 165	91.74 13	96.67 25	65.61 79	98.42 33	89.24 53	96.08 7	95.88 47
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		79.47 190	79.41 176	79.67 288	85.95 261	59.40 311	91.68 190	93.94 67	78.06 109	68.96 260	88.28 218	66.61 67	91.77 312	66.20 261	74.99 244	87.82 266

SteuartSystems-ACMMP		86.82 45	86.90 45	86.58 71	90.42 147	66.38 136	96.09 17	93.87 68	77.73 116	84.01 83	95.66 52	63.39 114	97.94 42	87.40 69	93.55 50	95.42 60
Skip Steuart: Steuart Systems R&D Blog.
TSAR-MVS + GP.		87.96 21	88.37 23	86.70 66	93.51 62	65.32 161	95.15 36	93.84 69	78.17 108	85.93 62	94.80 85	75.80 13	98.21 36	89.38 50	88.78 113	96.59 19

CANet		89.61 12	89.99 12	88.46 24	94.39 39	69.71 51	96.53 13	93.78 70	86.89 6	89.68 33	95.78 49	65.94 74	99.10 9	92.99 26	93.91 42	96.58 21

APDe-MVS		87.54 28	87.84 30	86.65 67	96.07 23	66.30 139	94.84 47	93.78 70	69.35 272	88.39 39	96.34 34	67.74 59	97.66 58	90.62 46	93.44 51	96.01 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TESTMET0.1,1		82.41 136	81.98 134	83.72 178	88.08 207	63.74 203	92.70 140	93.77 72	79.30 85	77.61 156	87.57 235	58.19 179	94.08 236	73.91 185	86.68 141	93.33 162

h-mvs33		83.01 126	82.56 126	84.35 156	89.34 169	62.02 252	92.72 138	93.76 73	81.45 48	82.73 96	92.25 152	60.11 153	97.13 95	87.69 64	62.96 334	93.91 145

SF-MVS		87.03 38	87.09 40	86.84 59	92.70 86	67.45 109	93.64 98	93.76 73	70.78 256	86.25 56	96.44 30	66.98 63	97.79 49	88.68 58	94.56 34	95.28 73

MVS_111021_HR		86.19 58	85.80 66	87.37 44	93.17 70	69.79 48	93.99 77	93.76 73	79.08 92	78.88 142	93.99 113	62.25 132	98.15 38	85.93 84	91.15 85	94.15 133

FC-MVSNet-test		77.99 218	78.08 195	77.70 311	84.89 282	55.51 349	90.27 246	93.75 76	76.87 128	66.80 293	87.59 234	65.71 78	90.23 336	62.89 289	73.94 253	87.37 274

MVS_0304		90.32 6	90.90 7	88.55 23	94.05 45	70.23 37	97.00 5	93.73 77	87.30 4	92.15 7	96.15 42	66.38 69	98.94 17	96.71 2	94.67 33	96.47 28

QAPM		79.95 182	77.39 210	87.64 34	89.63 163	71.41 20	93.30 115	93.70 78	65.34 309	67.39 285	91.75 164	47.83 293	98.96 16	57.71 315	89.81 102	92.54 187

DeepC-MVS	77.85 3	85.52 74	85.24 76	86.37 79	88.80 187	66.64 130	92.15 162	93.68 79	81.07 56	76.91 165	93.64 120	62.59 127	98.44 31	85.50 85	92.84 59	94.03 140
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EPP-MVSNet		81.79 147	81.52 138	82.61 209	88.77 188	60.21 298	93.02 126	93.66 80	68.52 284	72.90 204	90.39 187	72.19 38	94.96 199	74.93 177	79.29 211	92.67 182

PVSNet_BlendedMVS		83.38 118	83.43 103	83.22 195	93.76 50	67.53 106	94.06 70	93.61 81	79.13 90	81.00 113	85.14 265	63.19 118	97.29 81	87.08 74	73.91 254	84.83 325

PVSNet_Blended		86.73 47	86.86 46	86.31 82	93.76 50	67.53 106	96.33 16	93.61 81	82.34 38	81.00 113	93.08 129	63.19 118	97.29 81	87.08 74	91.38 81	94.13 134

alignmvs		87.28 35	86.97 42	88.24 27	91.30 131	71.14 26	95.61 25	93.56 83	79.30 85	87.07 50	95.25 70	68.43 52	96.93 114	87.87 62	84.33 162	96.65 17

TSAR-MVS + MP.		88.11 20	88.64 20	86.54 73	91.73 117	68.04 91	90.36 243	93.55 84	82.89 29	91.29 19	92.89 135	72.27 37	96.03 156	87.99 61	94.77 26	95.54 58
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
TEST9					94.18 41	67.28 111	94.16 65	93.51 85	71.75 229	85.52 66	95.33 63	68.01 56	97.27 85

train_agg		87.21 36	87.42 37	86.60 69	94.18 41	67.28 111	94.16 65	93.51 85	71.87 223	85.52 66	95.33 63	68.19 54	97.27 85	89.09 54	94.90 22	95.25 77

ZD-MVS					96.63 9	65.50 159		93.50 87	70.74 257	85.26 71	95.19 74	64.92 88	97.29 81	87.51 66	93.01 56

ACMMP_NAP		86.05 60	85.80 66	86.80 62	91.58 121	67.53 106	91.79 183	93.49 88	74.93 155	84.61 75	95.30 65	59.42 162	97.92 43	86.13 81	94.92 20	94.94 91

cdsmvs_eth3d_5k		19.86 402	26.47 401	0.00 421	0.00 444	0.00 446	0.00 432	93.45 89	0.00 439	0.00 440	95.27 68	49.56 275	0.00 440	0.00 439	0.00 437	0.00 436

3Dnovator+	73.60 7	82.10 143	80.60 157	86.60 69	90.89 140	66.80 127	95.20 34	93.44 90	74.05 167	67.42 283	92.49 144	49.46 276	97.65 59	70.80 213	91.68 75	95.33 67

balanced_conf03		89.08 15	88.84 18	89.81 6	93.66 54	75.15 5	90.61 237	93.43 91	84.06 18	86.20 58	90.17 193	72.42 35	96.98 106	93.09 25	95.92 10	97.29 7

test_8					94.19 40	67.19 113	94.15 67	93.42 92	71.87 223	85.38 69	95.35 62	68.19 54	96.95 111

ZNCC-MVS		85.33 76	85.08 79	86.06 87	93.09 73	65.65 153	93.89 83	93.41 93	73.75 176	79.94 126	94.68 88	60.61 148	98.03 40	82.63 116	93.72 46	94.52 115

原ACMM1				84.42 152	93.21 68	64.27 191		93.40 94	65.39 307	79.51 131	92.50 142	58.11 180	96.69 122	65.27 272	93.96 40	92.32 193

agg_prior					94.16 43	66.97 122		93.31 95		84.49 77			96.75 121

reproduce_monomvs		79.49 189	79.11 183	80.64 261	92.91 78	61.47 267	91.17 215	93.28 96	83.09 27	64.04 314	82.38 296	66.19 70	94.57 214	81.19 130	57.71 369	85.88 308

PS-MVSNAJ		88.14 18	87.61 34	89.71 7	92.06 102	76.72 1	95.75 20	93.26 97	83.86 19	89.55 34	96.06 44	53.55 236	97.89 45	91.10 41	93.31 53	94.54 113

EI-MVSNet		78.97 198	78.22 193	81.25 244	85.33 271	62.73 238	89.53 265	93.21 98	72.39 207	72.14 218	90.13 196	60.99 142	94.72 207	67.73 243	72.49 264	86.29 294

MVSTER		82.47 135	82.05 131	83.74 174	92.68 87	69.01 65	91.90 178	93.21 98	79.83 73	72.14 218	85.71 261	74.72 17	94.72 207	75.72 169	72.49 264	87.50 270

UniMVSNet_NR-MVSNet		78.15 216	77.55 204	79.98 278	84.46 292	60.26 296	92.25 158	93.20 100	77.50 122	68.88 261	86.61 249	66.10 72	92.13 304	66.38 258	62.55 338	87.54 269

HFP-MVS		84.73 88	84.40 89	85.72 101	93.75 52	65.01 170	93.50 106	93.19 101	72.19 212	79.22 136	94.93 80	59.04 169	97.67 55	81.55 123	92.21 64	94.49 118

UniMVSNet (Re)		77.58 225	76.78 218	79.98 278	84.11 298	60.80 277	91.76 186	93.17 102	76.56 137	69.93 249	84.78 269	63.32 117	92.36 297	64.89 274	62.51 340	86.78 285

ACMMPR		84.37 93	84.06 91	85.28 116	93.56 58	64.37 186	93.50 106	93.15 103	72.19 212	78.85 144	94.86 83	56.69 198	97.45 70	81.55 123	92.20 65	94.02 141

GST-MVS		84.63 90	84.29 90	85.66 103	92.82 82	65.27 162	93.04 124	93.13 104	73.20 185	78.89 139	94.18 108	59.41 163	97.85 47	81.45 125	92.48 63	93.86 148

xiu_mvs_v2_base		87.92 24	87.38 38	89.55 12	91.41 129	76.43 3	95.74 21	93.12 105	83.53 23	89.55 34	95.95 47	53.45 240	97.68 53	91.07 42	92.62 60	94.54 113

test_prior				86.42 77	94.71 35	67.35 110		93.10 106					96.84 118			95.05 85

WBMVS		81.67 148	80.98 149	83.72 178	93.07 74	69.40 54	94.33 60	93.05 107	76.84 130	72.05 220	84.14 276	74.49 19	93.88 250	72.76 194	68.09 293	87.88 265

SDMVSNet		80.26 174	78.88 185	84.40 153	89.25 174	67.63 103	85.35 319	93.02 108	76.77 133	70.84 234	87.12 242	47.95 292	96.09 150	85.04 90	74.55 245	89.48 246

test11								93.01 109

CostFormer		82.33 137	81.15 142	85.86 94	89.01 182	68.46 78	82.39 345	93.01 109	75.59 145	80.25 123	81.57 309	72.03 39	94.96 199	79.06 148	77.48 228	94.16 132

PAPR		85.15 80	84.47 87	87.18 49	96.02 25	68.29 82	91.85 181	93.00 111	76.59 136	79.03 138	95.00 77	61.59 138	97.61 62	78.16 156	89.00 111	95.63 54

region2R		84.36 94	84.03 92	85.36 112	93.54 60	64.31 189	93.43 111	92.95 112	72.16 215	78.86 143	94.84 84	56.97 193	97.53 67	81.38 127	92.11 67	94.24 127

test12				87.09 52	94.60 36	68.86 68		92.91 113		82.67 98		65.44 80	97.55 66		93.69 48	94.84 96

lupinMVS		87.74 26	87.77 31	87.63 38	89.24 177	71.18 24	96.57 12	92.90 114	82.70 33	87.13 48	95.27 68	64.99 85	95.80 161	89.34 51	91.80 73	95.93 45

PAPM_NR		82.97 127	81.84 135	86.37 79	94.10 44	66.76 128	87.66 301	92.84 115	69.96 265	74.07 194	93.57 122	63.10 121	97.50 69	70.66 216	90.58 91	94.85 93

CDPH-MVS		85.71 68	85.46 72	86.46 75	94.75 34	67.19 113	93.89 83	92.83 116	70.90 252	83.09 91	95.28 66	63.62 109	97.36 76	80.63 133	94.18 37	94.84 96

tfpnnormal		70.10 309	67.36 318	78.32 305	83.45 307	60.97 275	88.85 279	92.77 117	64.85 311	60.83 337	78.53 346	43.52 321	93.48 259	31.73 411	61.70 350	80.52 373

PAPM		85.89 65	85.46 72	87.18 49	88.20 206	72.42 15	92.41 155	92.77 117	82.11 40	80.34 122	93.07 130	68.27 53	95.02 195	78.39 155	93.59 49	94.09 136

SSC-MVS3.2		74.92 269	73.32 267	79.74 287	86.53 248	60.31 295	89.03 278	92.70 119	78.61 102	68.98 259	83.34 286	41.93 327	92.23 302	52.77 335	65.97 308	86.69 286

MS-PatchMatch		77.90 222	76.50 221	82.12 226	85.99 260	69.95 42	91.75 188	92.70 119	73.97 170	62.58 330	84.44 274	41.11 330	95.78 162	63.76 281	92.17 66	80.62 372

MSLP-MVS++		86.27 56	85.91 64	87.35 45	92.01 106	68.97 67	95.04 41	92.70 119	79.04 95	81.50 104	96.50 29	58.98 171	96.78 120	83.49 109	93.93 41	96.29 35

MVSMamba_PlusPlus		84.97 85	83.65 96	88.93 14	90.17 153	74.04 8	87.84 297	92.69 122	62.18 337	81.47 106	87.64 233	71.47 42	96.28 141	84.69 95	94.74 31	96.47 28

ab-mvs		80.18 176	78.31 191	85.80 97	88.44 194	65.49 160	83.00 342	92.67 123	71.82 226	77.36 159	85.01 266	54.50 222	96.59 124	76.35 166	75.63 241	95.32 69

save fliter					93.84 49	67.89 96	95.05 39	92.66 124	78.19 107

XVS		83.87 107	83.47 101	85.05 124	93.22 66	63.78 201	92.92 130	92.66 124	73.99 168	78.18 149	94.31 103	55.25 213	97.41 73	79.16 146	91.58 77	93.95 143

X-MVStestdata		76.86 236	74.13 256	85.05 124	93.22 66	63.78 201	92.92 130	92.66 124	73.99 168	78.18 149	10.19 435	55.25 213	97.41 73	79.16 146	91.58 77	93.95 143

SD-MVS		87.49 31	87.49 36	87.50 42	93.60 56	68.82 70	93.90 82	92.63 127	76.86 129	87.90 42	95.76 50	66.17 71	97.63 60	89.06 55	91.48 79	96.05 42
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							92.71 139	92.61 128	62.03 340				97.01 101	66.63 253		93.97 142

APD-MVS		85.93 63	85.99 62	85.76 99	95.98 26	65.21 164	93.59 101	92.58 129	66.54 299	86.17 59	95.88 48	63.83 104	97.00 102	86.39 80	92.94 57	95.06 84
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
1314		80.70 166	78.95 184	85.94 91	87.77 220	67.56 104	87.91 295	92.55 130	72.17 214	67.44 282	93.09 128	50.27 268	97.04 100	71.68 208	87.64 126	93.23 164

MP-MVS-pluss		85.24 77	85.13 78	85.56 105	91.42 126	65.59 155	91.54 193	92.51 131	74.56 158	80.62 117	95.64 53	59.15 166	97.00 102	86.94 76	93.80 43	94.07 138
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
WR-MVS		76.76 241	75.74 233	79.82 284	84.60 286	62.27 249	92.60 147	92.51 131	76.06 140	67.87 277	85.34 263	56.76 195	90.24 335	62.20 293	63.69 333	86.94 283

OpenMVS	70.45 11	78.54 210	75.92 230	86.41 78	85.93 264	71.68 18	92.74 137	92.51 131	66.49 300	64.56 308	91.96 158	43.88 319	98.10 39	54.61 326	90.65 90	89.44 248

GDP-MVS		85.54 73	85.32 74	86.18 84	87.64 221	67.95 95	92.91 132	92.36 134	77.81 114	83.69 85	94.31 103	72.84 30	96.41 136	80.39 136	85.95 146	94.19 129

CHOSEN 1792x2688		84.98 84	83.45 102	89.57 11	89.94 157	75.14 6	92.07 168	92.32 135	81.87 42	75.68 174	88.27 219	60.18 152	98.60 27	80.46 135	90.27 97	94.96 89

CP-MVS		83.71 112	83.40 106	84.65 143	93.14 71	63.84 199	94.59 53	92.28 136	71.03 250	77.41 158	94.92 81	55.21 216	96.19 145	81.32 128	90.70 89	93.91 145

MP-MVS		85.02 82	84.97 81	85.17 121	92.60 89	64.27 191	93.24 116	92.27 137	73.13 187	79.63 130	94.43 94	61.90 134	97.17 90	85.00 91	92.56 61	94.06 139
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTGPA								92.23 138

MTAPA		83.91 106	83.38 107	85.50 106	91.89 113	65.16 166	81.75 348	92.23 138	75.32 150	80.53 119	95.21 73	56.06 207	97.16 93	84.86 94	92.55 62	94.18 130

VPNet		78.82 202	77.53 205	82.70 206	84.52 289	66.44 135	93.93 80	92.23 138	80.46 62	72.60 209	88.38 217	49.18 280	93.13 265	72.47 199	63.97 331	88.55 257

ACMMP		81.49 152	80.67 154	83.93 170	91.71 118	62.90 234	92.13 163	92.22 141	71.79 227	71.68 226	93.49 124	50.32 266	96.96 110	78.47 154	84.22 166	91.93 206
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
RRT-MVS		82.61 134	81.16 141	86.96 57	91.10 135	68.75 71	87.70 300	92.20 142	76.97 127	72.68 206	87.10 244	51.30 260	96.41 136	83.56 108	87.84 123	95.74 51

PGM-MVS		83.25 120	82.70 124	84.92 127	92.81 84	64.07 195	90.44 238	92.20 142	71.28 244	77.23 161	94.43 94	55.17 217	97.31 80	79.33 145	91.38 81	93.37 159

jason		86.40 51	86.17 57	87.11 51	86.16 257	70.54 32	95.71 24	92.19 144	82.00 41	84.58 76	94.34 101	61.86 135	95.53 181	87.76 63	90.89 87	95.27 74
jason: jason.
tt0805		73.07 284	70.73 296	80.07 274	78.37 366	57.05 338	87.78 298	92.18 145	61.23 347	67.04 288	86.49 251	31.35 380	94.58 212	65.06 273	67.12 300	88.57 256

CLD-MVS		82.73 130	82.35 130	83.86 171	87.90 213	67.65 102	95.45 28	92.18 145	85.06 11	72.58 210	92.27 150	52.46 248	95.78 162	84.18 100	79.06 212	88.16 263
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 30	88.72 19	83.84 172	86.89 245	60.04 302	95.05 39	92.17 147	84.80 14	92.27 6	96.37 31	64.62 92	96.54 129	94.43 15	91.86 71	94.94 91

reproduce_model		83.15 122	82.96 116	83.73 176	92.02 103	59.74 306	90.37 242	92.08 148	63.70 321	82.86 92	95.48 59	58.62 173	97.17 90	83.06 112	88.42 117	94.26 125

MVS_Test		84.16 102	83.20 111	87.05 54	91.56 122	69.82 46	89.99 257	92.05 149	77.77 115	82.84 93	86.57 250	63.93 103	96.09 150	74.91 178	89.18 108	95.25 77

reproduce-ours		83.51 115	83.33 109	84.06 164	92.18 99	60.49 290	90.74 229	92.04 150	64.35 314	83.24 87	95.59 56	59.05 167	97.27 85	83.61 106	89.17 109	94.41 122

our_new_method		83.51 115	83.33 109	84.06 164	92.18 99	60.49 290	90.74 229	92.04 150	64.35 314	83.24 87	95.59 56	59.05 167	97.27 85	83.61 106	89.17 109	94.41 122

EIA-MVS		84.84 86	84.88 82	84.69 141	91.30 131	62.36 245	93.85 85	92.04 150	79.45 81	79.33 135	94.28 105	62.42 129	96.35 139	80.05 138	91.25 84	95.38 63

WR-MVS_H		70.59 305	69.94 302	72.53 357	81.03 329	51.43 368	87.35 305	92.03 153	67.38 292	60.23 341	80.70 323	55.84 210	83.45 388	46.33 363	58.58 368	82.72 350

FMVSNet3		77.73 223	76.04 228	82.80 202	91.20 134	68.99 66	91.87 179	91.99 154	73.35 184	67.04 288	83.19 288	56.62 199	92.14 303	59.80 307	69.34 281	87.28 277

DP-MVS Recon		82.73 130	81.65 137	85.98 89	97.31 4	67.06 118	95.15 36	91.99 154	69.08 278	76.50 169	93.89 115	54.48 225	98.20 37	70.76 214	85.66 150	92.69 181

EPNet_dtu		78.80 203	79.26 180	77.43 316	88.06 208	49.71 379	91.96 176	91.95 156	77.67 117	76.56 168	91.28 174	58.51 174	90.20 337	56.37 320	80.95 195	92.39 190
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FOURS1					93.95 46	61.77 258	93.96 78	91.92 157	62.14 339	86.57 54

ETV-MVS		86.01 61	86.11 59	85.70 102	90.21 152	67.02 121	93.43 111	91.92 157	81.21 55	84.13 82	94.07 112	60.93 145	95.63 172	89.28 52	89.81 102	94.46 120

SPE-MVS-test		86.14 59	87.01 41	83.52 184	92.63 88	59.36 314	95.49 27	91.92 157	80.09 70	85.46 68	95.53 58	61.82 137	95.77 164	86.77 78	93.37 52	95.41 61

LFMVS		84.34 95	82.73 123	89.18 13	94.76 33	73.25 11	94.99 44	91.89 160	71.90 220	82.16 100	93.49 124	47.98 291	97.05 97	82.55 117	84.82 155	97.25 8

casdiffmvs_mvg		85.66 70	85.18 77	87.09 52	88.22 205	69.35 59	93.74 94	91.89 160	81.47 47	80.10 124	91.45 169	64.80 90	96.35 139	87.23 72	87.69 125	95.58 56
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 66	86.65 51	83.27 193	92.00 107	58.92 318	95.31 31	91.86 162	79.97 71	84.82 74	95.40 61	62.26 131	95.51 182	86.11 82	92.08 68	95.37 64

HPM-MVS		83.25 120	82.95 118	84.17 162	92.25 95	62.88 235	90.91 220	91.86 162	70.30 261	77.12 162	93.96 114	56.75 196	96.28 141	82.04 120	91.34 83	93.34 160
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		82.96 128	82.44 128	84.52 149	92.83 80	62.92 233	92.76 136	91.85 164	71.52 240	75.61 177	94.24 106	53.48 239	96.99 105	78.97 149	90.73 88	93.64 154

XXY-MVS		77.94 220	76.44 222	82.43 212	82.60 316	64.44 181	92.01 171	91.83 165	73.59 181	70.00 246	85.82 259	54.43 226	94.76 204	69.63 222	68.02 295	88.10 264

baseline		85.01 83	84.44 88	86.71 65	88.33 200	68.73 72	90.24 248	91.82 166	81.05 57	81.18 109	92.50 142	63.69 107	96.08 153	84.45 98	86.71 140	95.32 69

casdiffmvs		85.37 75	84.87 83	86.84 59	88.25 203	69.07 63	93.04 124	91.76 167	81.27 54	80.84 115	92.07 156	64.23 98	96.06 154	84.98 92	87.43 129	95.39 62
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 21	88.93 17	85.07 123	88.43 195	61.78 257	94.73 51	91.74 168	85.87 9	91.66 15	97.50 2	64.03 100	98.33 34	96.28 3	90.08 98	95.10 82

NR-MVSNet		76.05 250	74.59 246	80.44 264	82.96 312	62.18 250	90.83 225	91.73 169	77.12 126	60.96 336	86.35 252	59.28 165	91.80 311	60.74 300	61.34 353	87.35 275

PVSNet_Blended_VisFu		83.97 105	83.50 99	85.39 110	90.02 155	66.59 133	93.77 92	91.73 169	77.43 124	77.08 164	89.81 201	63.77 106	96.97 109	79.67 141	88.21 119	92.60 185

sasdasda		86.85 41	86.25 55	88.66 20	91.80 115	71.92 16	93.54 103	91.71 171	80.26 66	87.55 45	95.25 70	63.59 111	96.93 114	88.18 59	84.34 160	97.11 9

FA-MVS(test-final)		79.12 195	77.23 212	84.81 134	90.54 145	63.98 198	81.35 354	91.71 171	71.09 249	74.85 186	82.94 289	52.85 243	97.05 97	67.97 239	81.73 190	93.41 158

canonicalmvs		86.85 41	86.25 55	88.66 20	91.80 115	71.92 16	93.54 103	91.71 171	80.26 66	87.55 45	95.25 70	63.59 111	96.93 114	88.18 59	84.34 160	97.11 9

HQP3-MVS								91.70 174							78.90 213

HQP-MVS		81.14 157	80.64 155	82.64 208	87.54 223	63.66 210	94.06 70	91.70 174	79.80 74	74.18 190	90.30 189	51.63 256	95.61 174	77.63 159	78.90 213	88.63 254

baseline1		81.84 146	81.03 147	84.28 159	91.60 120	66.62 131	91.08 217	91.66 176	81.87 42	74.86 185	91.67 166	69.98 48	94.92 202	71.76 206	64.75 321	91.29 221

FMVSNet2		76.07 247	74.01 258	82.26 220	88.85 184	67.66 101	91.33 205	91.61 177	70.84 253	65.98 297	82.25 298	48.03 288	92.00 308	58.46 312	68.73 289	87.10 280

114514_t		79.17 194	77.67 200	83.68 180	95.32 29	65.53 158	92.85 134	91.60 178	63.49 323	67.92 273	90.63 182	46.65 300	95.72 170	67.01 251	83.54 169	89.79 240

test-LLR		80.10 178	79.56 172	81.72 235	86.93 241	61.17 270	92.70 140	91.54 179	71.51 241	75.62 175	86.94 246	53.83 232	92.38 295	72.21 201	84.76 157	91.60 210

test-mter		79.96 181	79.38 178	81.72 235	86.93 241	61.17 270	92.70 140	91.54 179	73.85 173	75.62 175	86.94 246	49.84 273	92.38 295	72.21 201	84.76 157	91.60 210

DU-MVS		76.86 236	75.84 231	79.91 281	82.96 312	60.26 296	91.26 208	91.54 179	76.46 138	68.88 261	86.35 252	56.16 204	92.13 304	66.38 258	62.55 338	87.35 275

旧先验1					91.94 108	60.74 282		91.50 182			94.36 96	65.23 83			91.84 72	94.55 111

VDD-MVS		83.06 125	81.81 136	86.81 61	90.86 141	67.70 100	95.40 29	91.50 182	75.46 147	81.78 102	92.34 149	40.09 333	97.13 95	86.85 77	82.04 185	95.60 55

新几何1				84.73 137	92.32 93	64.28 190		91.46 184	59.56 358	79.77 128	92.90 134	56.95 194	96.57 126	63.40 282	92.91 58	93.34 160

tpm2		79.80 184	77.95 198	85.34 113	88.28 201	68.26 84	81.56 351	91.42 185	70.11 263	77.59 157	80.50 327	67.40 61	94.26 230	67.34 246	77.35 229	93.51 156

TranMVSNet+NR-MVSNet		75.86 255	74.52 249	79.89 282	82.44 318	60.64 287	91.37 202	91.37 186	76.63 135	67.65 279	86.21 255	52.37 249	91.55 318	61.84 295	60.81 356	87.48 271

test2506		83.29 119	82.92 119	84.37 155	88.39 198	63.18 226	92.01 171	91.35 187	77.66 118	78.49 148	91.42 170	64.58 94	95.09 194	73.19 187	89.23 106	94.85 93

MGCFI-Net		85.59 72	85.73 68	85.17 121	91.41 129	62.44 242	92.87 133	91.31 188	79.65 78	86.99 52	95.14 76	62.90 124	96.12 148	87.13 73	84.13 167	96.96 13

VDDNet		80.50 169	78.26 192	87.21 47	86.19 255	69.79 48	94.48 54	91.31 188	60.42 351	79.34 134	90.91 178	38.48 341	96.56 127	82.16 118	81.05 194	95.27 74

HQP_MVS		80.34 173	79.75 169	82.12 226	86.94 239	62.42 243	93.13 120	91.31 188	78.81 98	72.53 211	89.14 209	50.66 264	95.55 179	76.74 162	78.53 218	88.39 260

plane_prior5								91.31 188					95.55 179	76.74 162	78.53 218	88.39 260

SR-MVS		82.81 129	82.58 125	83.50 187	93.35 64	61.16 272	92.23 160	91.28 192	64.48 313	81.27 107	95.28 66	53.71 235	95.86 160	82.87 114	88.77 114	93.49 157

nrg030		80.93 162	79.86 167	84.13 163	83.69 303	68.83 69	93.23 117	91.20 193	75.55 146	75.06 183	88.22 223	63.04 122	94.74 206	81.88 121	66.88 302	88.82 252

EPMVS		78.49 211	75.98 229	86.02 88	91.21 133	69.68 52	80.23 363	91.20 193	75.25 151	72.48 213	78.11 350	54.65 221	93.69 255	57.66 316	83.04 173	94.69 103

fmvsm_s_conf0.5_n_4		86.79 46	87.63 32	84.27 160	86.15 258	61.48 266	94.69 52	91.16 195	83.79 22	90.51 25	96.28 36	64.24 97	98.22 35	95.00 10	86.88 133	93.11 169

hse-mvs2		81.12 159	81.11 146	81.16 247	86.52 249	57.48 333	89.40 268	91.16 195	81.45 48	82.73 96	90.49 185	60.11 153	94.58 212	87.69 64	60.41 361	91.41 215

AUN-MVS		78.37 212	77.43 206	81.17 246	86.60 247	57.45 334	89.46 267	91.16 195	74.11 166	74.40 189	90.49 185	55.52 212	94.57 214	74.73 181	60.43 360	91.48 213

cascas		78.18 215	75.77 232	85.41 109	87.14 234	69.11 62	92.96 128	91.15 198	66.71 298	70.47 237	86.07 256	37.49 352	96.48 133	70.15 219	79.80 205	90.65 228

tpm		78.58 209	77.03 214	83.22 195	85.94 263	64.56 175	83.21 338	91.14 199	78.31 106	73.67 197	79.68 339	64.01 101	92.09 306	66.07 262	71.26 274	93.03 173

PCF-MVS	73.15 9	79.29 192	77.63 202	84.29 158	86.06 259	65.96 147	87.03 308	91.10 200	69.86 267	69.79 250	90.64 180	57.54 185	96.59 124	64.37 277	82.29 179	90.32 232
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Anonymous20240529		76.84 238	74.15 255	84.88 129	91.02 136	64.95 172	93.84 88	91.09 201	53.57 382	73.00 201	87.42 237	35.91 362	97.32 79	69.14 230	72.41 266	92.36 191

EC-MVSNet		84.53 91	85.04 80	83.01 198	89.34 169	61.37 269	94.42 55	91.09 201	77.91 112	83.24 87	94.20 107	58.37 176	95.40 184	85.35 86	91.41 80	92.27 198

test_fmvsm_n_1920		87.69 27	88.50 21	85.27 117	87.05 237	63.55 214	93.69 95	91.08 203	84.18 17	90.17 29	97.04 10	67.58 60	97.99 41	95.72 6	90.03 99	94.26 125

FE-MVS		75.97 253	73.02 270	84.82 131	89.78 159	65.56 156	77.44 379	91.07 204	64.55 312	72.66 207	79.85 337	46.05 308	96.69 122	54.97 325	80.82 197	92.21 200

PS-MVSNAJss		77.26 229	76.31 224	80.13 273	80.64 335	59.16 316	90.63 236	91.06 205	72.80 196	68.58 267	84.57 272	53.55 236	93.96 246	72.97 189	71.96 268	87.27 278

PVSNet	73.49 8	80.05 179	78.63 187	84.31 157	90.92 139	64.97 171	92.47 153	91.05 206	79.18 88	72.43 215	90.51 184	37.05 358	94.06 238	68.06 238	86.00 145	93.90 147

API-MVS		82.28 138	80.53 158	87.54 41	96.13 22	70.59 31	93.63 99	91.04 207	65.72 306	75.45 180	92.83 138	56.11 206	98.89 21	64.10 278	89.75 105	93.15 167

APD-MVS_3200maxsize		81.64 150	81.32 140	82.59 210	92.36 92	58.74 320	91.39 199	91.01 208	63.35 325	79.72 129	94.62 90	51.82 251	96.14 147	79.71 140	87.93 122	92.89 179

MVP-Stereo		77.12 232	76.23 225	79.79 285	81.72 324	66.34 138	89.29 269	90.88 209	70.56 259	62.01 333	82.88 290	49.34 277	94.13 233	65.55 269	93.80 43	78.88 386
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UGNet		79.87 183	78.68 186	83.45 189	89.96 156	61.51 264	92.13 163	90.79 210	76.83 131	78.85 144	86.33 254	38.16 344	96.17 146	67.93 241	87.17 131	92.67 182
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		80.37 172	79.45 175	83.13 197	85.14 277	63.37 218	91.23 210	90.76 211	74.81 157	72.65 208	88.49 214	60.63 147	92.95 270	69.41 225	81.95 187	93.08 171

MVSFormer		83.75 111	82.88 120	86.37 79	89.24 177	71.18 24	89.07 275	90.69 212	65.80 304	87.13 48	94.34 101	64.99 85	92.67 285	72.83 191	91.80 73	95.27 74

test_djsdf		73.76 281	72.56 278	77.39 317	77.00 377	53.93 357	89.07 275	90.69 212	65.80 304	63.92 315	82.03 301	43.14 323	92.67 285	72.83 191	68.53 290	85.57 314

PMMVS		81.98 145	82.04 132	81.78 233	89.76 161	56.17 344	91.13 216	90.69 212	77.96 110	80.09 125	93.57 122	46.33 305	94.99 198	81.41 126	87.46 128	94.17 131

dcpmvs_2		87.37 34	87.55 35	86.85 58	95.04 32	68.20 88	90.36 243	90.66 215	79.37 84	81.20 108	93.67 119	74.73 16	96.55 128	90.88 44	92.00 69	95.82 48

CDS-MVSNet		81.43 153	80.74 151	83.52 184	86.26 254	64.45 180	92.09 166	90.65 216	75.83 143	73.95 196	89.81 201	63.97 102	92.91 275	71.27 209	82.82 175	93.20 166
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
mvs_anonymous		81.36 154	79.99 165	85.46 107	90.39 149	68.40 79	86.88 312	90.61 217	74.41 160	70.31 242	84.67 270	63.79 105	92.32 300	73.13 188	85.70 149	95.67 52

testing3		70.38 308	70.83 293	69.03 375	85.82 265	43.93 406	90.72 231	90.56 218	68.06 286	60.24 340	86.82 248	64.83 89	84.12 380	26.33 416	64.10 328	79.04 385

SR-MVS-dyc-post		81.06 160	80.70 153	82.15 224	92.02 103	58.56 322	90.90 221	90.45 219	62.76 332	78.89 139	94.46 92	51.26 261	95.61 174	78.77 152	86.77 138	92.28 195

RE-MVS-def			80.48 159		92.02 103	58.56 322	90.90 221	90.45 219	62.76 332	78.89 139	94.46 92	49.30 278		78.77 152	86.77 138	92.28 195

RPMNet		70.42 307	65.68 328	84.63 145	83.15 310	67.96 93	70.25 397	90.45 219	46.83 403	69.97 247	65.10 403	56.48 203	95.30 190	35.79 398	73.13 258	90.64 229

xiu_mvs_v1_base_debu		82.16 140	81.12 143	85.26 118	86.42 250	68.72 73	92.59 149	90.44 222	73.12 188	84.20 79	94.36 96	38.04 346	95.73 166	84.12 101	86.81 135	91.33 216

xiu_mvs_v1_base		82.16 140	81.12 143	85.26 118	86.42 250	68.72 73	92.59 149	90.44 222	73.12 188	84.20 79	94.36 96	38.04 346	95.73 166	84.12 101	86.81 135	91.33 216

xiu_mvs_v1_base_debi		82.16 140	81.12 143	85.26 118	86.42 250	68.72 73	92.59 149	90.44 222	73.12 188	84.20 79	94.36 96	38.04 346	95.73 166	84.12 101	86.81 135	91.33 216

fmvsm_s_conf0.5_n_7		85.24 77	86.69 49	80.91 258	84.52 289	60.10 300	93.35 114	90.35 225	83.41 25	86.54 55	96.27 37	60.50 149	90.02 341	94.84 12	90.38 95	92.61 184

GBi-Net		75.65 258	73.83 260	81.10 250	88.85 184	65.11 167	90.01 254	90.32 226	70.84 253	67.04 288	80.25 332	48.03 288	91.54 319	59.80 307	69.34 281	86.64 287

test1		75.65 258	73.83 260	81.10 250	88.85 184	65.11 167	90.01 254	90.32 226	70.84 253	67.04 288	80.25 332	48.03 288	91.54 319	59.80 307	69.34 281	86.64 287

FMVSNet1		72.71 292	69.91 303	81.10 250	83.60 305	65.11 167	90.01 254	90.32 226	63.92 318	63.56 319	80.25 332	36.35 361	91.54 319	54.46 327	66.75 303	86.64 287

PVSNet_0	68.08 15	71.81 298	68.32 314	82.27 218	84.68 283	62.31 248	88.68 282	90.31 229	75.84 142	57.93 357	80.65 326	37.85 349	94.19 231	69.94 220	29.05 423	90.31 233

OPM-MVS		79.00 197	78.09 194	81.73 234	83.52 306	63.83 200	91.64 192	90.30 230	76.36 139	71.97 221	89.93 200	46.30 306	95.17 193	75.10 174	77.70 223	86.19 297
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CP-MVSNet		70.50 306	69.91 303	72.26 360	80.71 333	51.00 372	87.23 307	90.30 230	67.84 287	59.64 343	82.69 292	50.23 269	82.30 396	51.28 337	59.28 364	83.46 339

fmvsm_l_conf0.5_n_3		87.54 28	88.29 24	85.30 114	86.92 243	62.63 240	95.02 43	90.28 232	84.95 12	90.27 26	96.86 17	65.36 81	97.52 68	94.93 11	90.03 99	95.76 50

KD-MVS_2432*1600		69.03 319	66.37 323	77.01 322	85.56 269	61.06 273	81.44 352	90.25 233	67.27 293	58.00 355	76.53 364	54.49 223	87.63 362	48.04 353	35.77 414	82.34 356

miper_refine_blended		69.03 319	66.37 323	77.01 322	85.56 269	61.06 273	81.44 352	90.25 233	67.27 293	58.00 355	76.53 364	54.49 223	87.63 362	48.04 353	35.77 414	82.34 356

v148		76.19 245	74.47 250	81.36 242	80.05 343	64.44 181	91.75 188	90.23 235	73.68 179	67.13 287	80.84 322	55.92 209	93.86 253	68.95 232	61.73 349	85.76 312

v2v482		77.42 227	75.65 234	82.73 204	80.38 337	67.13 117	91.85 181	90.23 235	75.09 153	69.37 251	83.39 285	53.79 234	94.44 222	71.77 205	65.00 318	86.63 290

v1144		76.73 242	74.88 242	82.27 218	80.23 341	66.60 132	91.68 190	90.21 237	73.69 178	69.06 256	81.89 302	52.73 246	94.40 223	69.21 228	65.23 315	85.80 309

GA-MVS		78.33 214	76.23 225	84.65 143	83.65 304	66.30 139	91.44 194	90.14 238	76.01 141	70.32 241	84.02 278	42.50 324	94.72 207	70.98 211	77.00 233	92.94 176

MDTV_nov1_ep13			72.61 277		89.06 180	68.48 77	80.33 361	90.11 239	71.84 225	71.81 223	75.92 370	53.01 242	93.92 248	48.04 353	73.38 256

D2MVS		73.80 279	72.02 284	79.15 299	79.15 354	62.97 229	88.58 284	90.07 240	72.94 191	59.22 346	78.30 347	42.31 326	92.70 284	65.59 268	72.00 267	81.79 361

TR-MVS		78.77 205	77.37 211	82.95 200	90.49 146	60.88 276	93.67 96	90.07 240	70.08 264	74.51 188	91.37 173	45.69 309	95.70 171	60.12 305	80.32 201	92.29 194

Anonymous20231211		73.08 283	70.39 299	81.13 248	90.62 144	63.33 219	91.40 197	90.06 242	51.84 387	64.46 311	80.67 325	36.49 360	94.07 237	63.83 280	64.17 327	85.98 304

jajsoiax		73.05 285	71.51 290	77.67 312	77.46 374	54.83 353	88.81 280	90.04 243	69.13 277	62.85 328	83.51 283	31.16 381	92.75 281	70.83 212	69.80 277	85.43 318

fmvsm_s_conf0.5_n		86.39 52	86.91 44	84.82 131	87.36 229	63.54 215	94.74 49	90.02 244	82.52 34	90.14 30	96.92 15	62.93 123	97.84 48	95.28 9	82.26 180	93.07 172

HyFIR lowres test		81.03 161	79.56 172	85.43 108	87.81 217	68.11 90	90.18 249	90.01 245	70.65 258	72.95 203	86.06 257	63.61 110	94.50 221	75.01 176	79.75 206	93.67 152

fmvsm_s_conf0.5_n_5		86.38 53	86.94 43	84.71 140	84.67 284	63.29 220	94.04 74	89.99 246	82.88 30	87.85 43	96.03 45	62.89 125	96.36 138	94.15 17	89.95 101	94.48 119

ACMM	69.62 13	74.34 272	72.73 275	79.17 297	84.25 297	57.87 327	90.36 243	89.93 247	63.17 329	65.64 299	86.04 258	37.79 350	94.10 234	65.89 263	71.52 271	85.55 315
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CL-MVSNet_self_test		69.92 311	68.09 315	75.41 333	73.25 391	55.90 347	90.05 253	89.90 248	69.96 265	61.96 334	76.54 363	51.05 262	87.64 361	49.51 346	50.59 389	82.70 352

UnsupCasMVSNet_eth		65.79 343	63.10 346	73.88 347	70.71 399	50.29 377	81.09 355	89.88 249	72.58 200	49.25 391	74.77 376	32.57 374	87.43 365	55.96 322	41.04 404	83.90 332

testdata				81.34 243	89.02 181	57.72 329		89.84 250	58.65 362	85.32 70	94.09 110	57.03 189	93.28 262	69.34 226	90.56 92	93.03 173

test_fmvsmconf_n		86.58 49	87.17 39	84.82 131	85.28 273	62.55 241	94.26 63	89.78 251	83.81 21	87.78 44	96.33 35	65.33 82	96.98 106	94.40 16	87.55 127	94.95 90

mvs_tets		72.71 292	71.11 291	77.52 313	77.41 375	54.52 355	88.45 286	89.76 252	68.76 282	62.70 329	83.26 287	29.49 386	92.71 282	70.51 218	69.62 279	85.34 320

v1192		75.98 252	73.92 259	82.15 224	79.73 345	66.24 141	91.22 211	89.75 253	72.67 198	68.49 268	81.42 312	49.86 272	94.27 228	67.08 250	65.02 317	85.95 305

PS-CasMVS		69.86 313	69.13 308	72.07 364	80.35 338	50.57 374	87.02 309	89.75 253	67.27 293	59.19 347	82.28 297	46.58 301	82.24 397	50.69 339	59.02 365	83.39 341

dp		75.01 267	72.09 283	83.76 173	89.28 173	66.22 142	79.96 369	89.75 253	71.16 246	67.80 278	77.19 359	51.81 252	92.54 290	50.39 340	71.44 273	92.51 189

LPG-MVS_test		75.82 256	74.58 247	79.56 292	84.31 295	59.37 312	90.44 238	89.73 256	69.49 270	64.86 304	88.42 215	38.65 338	94.30 226	72.56 197	72.76 261	85.01 323

LGP-MVS_train				79.56 292	84.31 295	59.37 312		89.73 256	69.49 270	64.86 304	88.42 215	38.65 338	94.30 226	72.56 197	72.76 261	85.01 323

tpmrst		80.57 167	79.14 182	84.84 130	90.10 154	68.28 83	81.70 349	89.72 258	77.63 120	75.96 171	79.54 341	64.94 87	92.71 282	75.43 171	77.28 231	93.55 155

v144192		76.05 250	74.03 257	82.12 226	79.50 349	66.55 134	91.39 199	89.71 259	72.30 209	68.17 270	81.33 314	51.75 254	94.03 243	67.94 240	64.19 326	85.77 310

TAPA-MVS	70.22 12	74.94 268	73.53 264	79.17 297	90.40 148	52.07 364	89.19 273	89.61 260	62.69 334	70.07 244	92.67 140	48.89 285	94.32 224	38.26 393	79.97 203	91.12 224
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PatchmatchNet		77.46 226	74.63 245	85.96 90	89.55 166	70.35 35	79.97 368	89.55 261	72.23 211	70.94 232	76.91 362	57.03 189	92.79 280	54.27 328	81.17 193	94.74 101
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v1921920		75.63 260	73.49 265	82.06 230	79.38 350	66.35 137	91.07 219	89.48 262	71.98 217	67.99 271	81.22 317	49.16 282	93.90 249	66.56 254	64.56 324	85.92 307

fmvsm_s_conf0.1_n		85.61 71	85.93 63	84.68 142	82.95 314	63.48 217	94.03 76	89.46 263	81.69 44	89.86 31	96.74 23	61.85 136	97.75 51	94.74 13	82.01 186	92.81 180

v7n		71.31 302	68.65 309	79.28 295	76.40 379	60.77 279	86.71 313	89.45 264	64.17 317	58.77 351	78.24 348	44.59 317	93.54 257	57.76 314	61.75 348	83.52 337

test0.0.03 1		72.76 290	72.71 276	72.88 355	80.25 340	47.99 388	91.22 211	89.45 264	71.51 241	62.51 331	87.66 232	53.83 232	85.06 378	50.16 342	67.84 298	85.58 313

test222					89.77 160	61.60 263	89.55 263	89.42 266	56.83 373	77.28 160	92.43 146	52.76 244			91.14 86	93.09 170

V42		76.46 244	74.55 248	82.19 223	79.14 355	67.82 97	90.26 247	89.42 266	73.75 176	68.63 266	81.89 302	51.31 259	94.09 235	71.69 207	64.84 319	84.66 326

BH-w/o		80.49 170	79.30 179	84.05 167	90.83 142	64.36 188	93.60 100	89.42 266	74.35 162	69.09 254	90.15 195	55.23 215	95.61 174	64.61 275	86.43 144	92.17 201

fmvsm_s_conf0.5_n_a		85.75 67	86.09 60	84.72 138	85.73 267	63.58 212	93.79 91	89.32 269	81.42 51	90.21 28	96.91 16	62.41 130	97.67 55	94.48 14	80.56 200	92.90 178

pm-mvs1		72.89 288	71.09 292	78.26 307	79.10 356	57.62 331	90.80 226	89.30 270	67.66 289	62.91 327	81.78 304	49.11 283	92.95 270	60.29 304	58.89 366	84.22 329

v8		75.35 262	73.26 268	81.61 237	80.67 334	66.82 125	89.54 264	89.27 271	71.65 232	63.30 322	80.30 331	54.99 219	94.06 238	67.33 247	62.33 341	83.94 331

diffmvs		84.28 96	83.83 93	85.61 104	87.40 227	68.02 92	90.88 223	89.24 272	80.54 60	81.64 103	92.52 141	59.83 157	94.52 220	87.32 70	85.11 153	94.29 124
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		69.46 316	68.56 310	72.17 362	79.27 351	49.71 379	86.90 311	89.24 272	67.24 296	59.08 348	82.51 295	47.23 297	83.54 387	48.42 351	57.12 370	83.25 342

UniMVSNet_ETH3D		72.74 291	70.53 298	79.36 294	78.62 364	56.64 342	85.01 321	89.20 274	63.77 320	64.84 306	84.44 274	34.05 369	91.86 310	63.94 279	70.89 276	89.57 244

SCA		75.82 256	72.76 273	85.01 126	86.63 246	70.08 38	81.06 356	89.19 275	71.60 237	70.01 245	77.09 360	45.53 310	90.25 332	60.43 302	73.27 257	94.68 104

EG-PatchMatch MVS		68.55 323	65.41 331	77.96 310	78.69 362	62.93 231	89.86 259	89.17 276	60.55 350	50.27 386	77.73 354	22.60 403	94.06 238	47.18 359	72.65 263	76.88 396

HPM-MVS_fast		80.25 175	79.55 174	82.33 216	91.55 123	59.95 303	91.32 206	89.16 277	65.23 310	74.71 187	93.07 130	47.81 294	95.74 165	74.87 180	88.23 118	91.31 220

miper_enhance_ethall		78.86 201	77.97 197	81.54 239	88.00 211	65.17 165	91.41 195	89.15 278	75.19 152	68.79 263	83.98 279	67.17 62	92.82 277	72.73 195	65.30 312	86.62 291

Fast-Effi-MVS+		81.14 157	80.01 164	84.51 150	90.24 151	65.86 149	94.12 69	89.15 278	73.81 175	75.37 181	88.26 220	57.26 186	94.53 219	66.97 252	84.92 154	93.15 167

mvsmamba		81.55 151	80.72 152	84.03 168	91.42 126	66.93 123	83.08 339	89.13 280	78.55 103	67.50 281	87.02 245	51.79 253	90.07 340	87.48 67	90.49 93	95.10 82

Vis-MVSNet (Re-imp)		79.24 193	79.57 171	78.24 308	88.46 193	52.29 363	90.41 240	89.12 281	74.24 164	69.13 253	91.91 161	65.77 77	90.09 339	59.00 311	88.09 120	92.33 192

v1240		75.21 265	72.98 271	81.88 232	79.20 352	66.00 145	90.75 228	89.11 282	71.63 236	67.41 284	81.22 317	47.36 296	93.87 251	65.46 270	64.72 322	85.77 310

sd_testset		77.08 233	75.37 236	82.20 222	89.25 174	62.11 251	82.06 346	89.09 283	76.77 133	70.84 234	87.12 242	41.43 329	95.01 197	67.23 248	74.55 245	89.48 246

v10		74.77 270	72.54 279	81.46 240	80.33 339	66.71 129	89.15 274	89.08 284	70.94 251	63.08 325	79.86 336	52.52 247	94.04 241	65.70 266	62.17 342	83.64 334

ACMP	71.68 10	75.58 261	74.23 254	79.62 290	84.97 281	59.64 307	90.80 226	89.07 285	70.39 260	62.95 326	87.30 239	38.28 342	93.87 251	72.89 190	71.45 272	85.36 319
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UnsupCasMVSNet_bld		61.60 361	57.71 366	73.29 352	68.73 405	51.64 366	78.61 372	89.05 286	57.20 370	46.11 397	61.96 410	28.70 389	88.60 349	50.08 343	38.90 409	79.63 380

Syy-MVS		69.65 314	69.52 306	70.03 371	87.87 214	43.21 407	88.07 291	89.01 287	72.91 193	63.11 323	88.10 224	45.28 313	85.54 373	22.07 421	69.23 284	81.32 364

myMVS_eth3d		72.58 296	72.74 274	72.10 363	87.87 214	49.45 381	88.07 291	89.01 287	72.91 193	63.11 323	88.10 224	63.63 108	85.54 373	32.73 408	69.23 284	81.32 364

CANet_DTU		84.09 103	83.52 97	85.81 96	90.30 150	66.82 125	91.87 179	89.01 287	85.27 10	86.09 60	93.74 117	47.71 295	96.98 106	77.90 158	89.78 104	93.65 153

UA-Net		80.02 180	79.65 170	81.11 249	89.33 171	57.72 329	86.33 316	89.00 290	77.44 123	81.01 112	89.15 208	59.33 164	95.90 159	61.01 299	84.28 164	89.73 242

MVS_111021_LR		82.02 144	81.52 138	83.51 186	88.42 196	62.88 235	89.77 260	88.93 291	76.78 132	75.55 178	93.10 127	50.31 267	95.38 186	83.82 105	87.02 132	92.26 199

miper_lstm_enhance		73.05 285	71.73 288	77.03 321	83.80 301	58.32 324	81.76 347	88.88 292	69.80 268	61.01 335	78.23 349	57.19 187	87.51 364	65.34 271	59.53 363	85.27 322

anonymousdsp		71.14 303	69.37 307	76.45 327	72.95 392	54.71 354	84.19 326	88.88 292	61.92 342	62.15 332	79.77 338	38.14 345	91.44 324	68.90 233	67.45 299	83.21 343

cl22		77.94 220	76.78 218	81.42 241	87.57 222	64.93 173	90.67 232	88.86 294	72.45 204	67.63 280	82.68 293	64.07 99	92.91 275	71.79 204	65.30 312	86.44 292

test_fmvsmconf0.1_n		85.71 68	86.08 61	84.62 146	80.83 331	62.33 246	93.84 88	88.81 295	83.50 24	87.00 51	96.01 46	63.36 115	96.93 114	94.04 19	87.29 130	94.61 109

MIMVSNet		71.64 299	68.44 312	81.23 245	81.97 323	64.44 181	73.05 391	88.80 296	69.67 269	64.59 307	74.79 375	32.79 372	87.82 358	53.99 329	76.35 237	91.42 214

IterMVS-LS		76.49 243	75.18 240	80.43 265	84.49 291	62.74 237	90.64 234	88.80 296	72.40 206	65.16 303	81.72 305	60.98 143	92.27 301	67.74 242	64.65 323	86.29 294
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.1_n_a		84.76 87	84.84 84	84.53 148	80.23 341	63.50 216	92.79 135	88.73 298	80.46 62	89.84 32	96.65 26	60.96 144	97.57 65	93.80 21	80.14 202	92.53 188

cl____		76.07 247	74.67 243	80.28 268	85.15 276	61.76 259	90.12 250	88.73 298	71.16 246	65.43 300	81.57 309	61.15 140	92.95 270	66.54 255	62.17 342	86.13 300

DIV-MVS_self_test		76.07 247	74.67 243	80.28 268	85.14 277	61.75 260	90.12 250	88.73 298	71.16 246	65.42 301	81.60 308	61.15 140	92.94 274	66.54 255	62.16 344	86.14 298

JIA-IIPM		66.06 341	62.45 351	76.88 325	81.42 328	54.45 356	57.49 421	88.67 301	49.36 395	63.86 316	46.86 419	56.06 207	90.25 332	49.53 345	68.83 287	85.95 305

OMC-MVS		78.67 208	77.91 199	80.95 256	85.76 266	57.40 335	88.49 285	88.67 301	73.85 173	72.43 215	92.10 155	49.29 279	94.55 218	72.73 195	77.89 221	90.91 226

miper_ehance_all_eth		77.60 224	76.44 222	81.09 253	85.70 268	64.41 184	90.65 233	88.64 303	72.31 208	67.37 286	82.52 294	64.77 91	92.64 288	70.67 215	65.30 312	86.24 296

BH-untuned		78.68 206	77.08 213	83.48 188	89.84 158	63.74 203	92.70 140	88.59 304	71.57 238	66.83 292	88.65 213	51.75 254	95.39 185	59.03 310	84.77 156	91.32 219

DTE-MVSNet		68.46 325	67.33 319	71.87 366	77.94 371	49.00 385	86.16 317	88.58 305	66.36 301	58.19 352	82.21 299	46.36 302	83.87 385	44.97 370	55.17 377	82.73 349

CPTT-MVS		79.59 186	79.16 181	80.89 259	91.54 124	59.80 305	92.10 165	88.54 306	60.42 351	72.96 202	93.28 126	48.27 287	92.80 279	78.89 151	86.50 143	90.06 235

fmvsm_l_conf0.5_n		87.49 31	88.19 26	85.39 110	86.95 238	64.37 186	94.30 61	88.45 307	80.51 61	92.70 4	96.86 17	69.98 48	97.15 94	95.83 5	88.08 121	94.65 107

CVMVSNet		74.04 276	74.27 253	73.33 351	85.33 271	43.94 405	89.53 265	88.39 308	54.33 381	70.37 240	90.13 196	49.17 281	84.05 382	61.83 296	79.36 209	91.99 205

1112_ss		80.56 168	79.83 168	82.77 203	88.65 189	60.78 278	92.29 157	88.36 309	72.58 200	72.46 214	94.95 78	65.09 84	93.42 261	66.38 258	77.71 222	94.10 135

test_cas_vis1_n_1920		80.45 171	80.61 156	79.97 280	78.25 367	57.01 340	94.04 74	88.33 310	79.06 94	82.81 95	93.70 118	38.65 338	91.63 316	90.82 45	79.81 204	91.27 222

tpmvs		72.88 289	69.76 305	82.22 221	90.98 137	67.05 119	78.22 376	88.30 311	63.10 330	64.35 313	74.98 373	55.09 218	94.27 228	43.25 373	69.57 280	85.34 320

PLC	68.80 14	75.23 264	73.68 263	79.86 283	92.93 77	58.68 321	90.64 234	88.30 311	60.90 348	64.43 312	90.53 183	42.38 325	94.57 214	56.52 319	76.54 236	86.33 293
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
eth_miper_zixun_eth		75.96 254	74.40 251	80.66 260	84.66 285	63.02 228	89.28 270	88.27 313	71.88 222	65.73 298	81.65 306	59.45 161	92.81 278	68.13 237	60.53 358	86.14 298

IS-MVSNet		80.14 177	79.41 176	82.33 216	87.91 212	60.08 301	91.97 175	88.27 313	72.90 195	71.44 230	91.73 165	61.44 139	93.66 256	62.47 292	86.53 142	93.24 163

Vis-MVSNet		80.92 163	79.98 166	83.74 174	88.48 192	61.80 256	93.44 110	88.26 315	73.96 171	77.73 153	91.76 163	49.94 271	94.76 204	65.84 264	90.37 96	94.65 107
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 33	88.15 27	85.30 114	87.10 235	64.19 193	94.41 56	88.14 316	80.24 69	92.54 5	96.97 12	69.52 50	97.17 90	95.89 4	88.51 116	94.56 110

c3_l		76.83 239	75.47 235	80.93 257	85.02 280	64.18 194	90.39 241	88.11 317	71.66 231	66.65 295	81.64 307	63.58 113	92.56 289	69.31 227	62.86 335	86.04 302

BH-RMVSNet		79.46 191	77.65 201	84.89 128	91.68 119	65.66 152	93.55 102	88.09 318	72.93 192	73.37 199	91.12 176	46.20 307	96.12 148	56.28 321	85.61 151	92.91 177

tpm cat1		75.30 263	72.21 282	84.58 147	88.52 190	67.77 98	78.16 377	88.02 319	61.88 343	68.45 269	76.37 366	60.65 146	94.03 243	53.77 331	74.11 251	91.93 206

dmvs_re		76.93 235	75.36 237	81.61 237	87.78 219	60.71 284	80.00 367	87.99 320	79.42 82	69.02 257	89.47 204	46.77 298	94.32 224	63.38 283	74.45 248	89.81 239

Test_1112_low_res		79.56 187	78.60 188	82.43 212	88.24 204	60.39 294	92.09 166	87.99 320	72.10 216	71.84 222	87.42 237	64.62 92	93.04 266	65.80 265	77.30 230	93.85 149

AdaColmap		78.94 199	77.00 216	84.76 136	96.34 17	65.86 149	92.66 144	87.97 322	62.18 337	70.56 236	92.37 148	43.53 320	97.35 77	64.50 276	82.86 174	91.05 225

fmvsm_s_conf0.5_n_3		86.88 39	87.99 29	83.58 183	87.26 230	60.74 282	93.21 119	87.94 323	84.22 16	91.70 14	97.27 3	65.91 76	95.02 195	93.95 20	90.42 94	94.99 88

Effi-MVS+-dtu		76.14 246	75.28 239	78.72 302	83.22 309	55.17 351	89.87 258	87.78 324	75.42 148	67.98 272	81.43 311	45.08 315	92.52 291	75.08 175	71.63 269	88.48 258

PatchT		69.11 318	65.37 332	80.32 266	82.07 322	63.68 209	67.96 407	87.62 325	50.86 391	69.37 251	65.18 402	57.09 188	88.53 351	41.59 382	66.60 304	88.74 253

XVG-OURS		74.25 274	72.46 280	79.63 289	78.45 365	57.59 332	80.33 361	87.39 326	63.86 319	68.76 264	89.62 203	40.50 332	91.72 313	69.00 231	74.25 250	89.58 243

Anonymous20231206		67.53 334	65.78 326	72.79 356	74.95 385	47.59 390	88.23 288	87.32 327	61.75 345	58.07 354	77.29 357	37.79 350	87.29 366	42.91 375	63.71 332	83.48 338

XVG-OURS-SEG-HR		74.70 271	73.08 269	79.57 291	78.25 367	57.33 336	80.49 359	87.32 327	63.22 327	68.76 264	90.12 198	44.89 316	91.59 317	70.55 217	74.09 252	89.79 240

fmvsm_s_conf0.5_n_2		85.06 81	85.60 70	83.44 190	86.92 243	60.53 289	94.41 56	87.31 329	83.30 26	88.72 38	96.72 24	54.28 229	97.75 51	94.07 18	84.68 159	92.04 204

pmmvs4		73.92 278	71.81 287	80.25 270	79.17 353	65.24 163	87.43 304	87.26 330	67.64 291	63.46 320	83.91 280	48.96 284	91.53 322	62.94 287	65.49 311	83.96 330

test_fmvsmconf0.01_n		83.70 113	83.52 97	84.25 161	75.26 384	61.72 261	92.17 161	87.24 331	82.36 37	84.91 73	95.41 60	55.60 211	96.83 119	92.85 27	85.87 147	94.21 128

pmmvs5		73.35 282	71.52 289	78.86 301	78.64 363	60.61 288	91.08 217	86.90 332	67.69 288	63.32 321	83.64 281	44.33 318	90.53 329	62.04 294	66.02 307	85.46 317

test_vis1_n_1920		81.66 149	82.01 133	80.64 261	82.24 319	55.09 352	94.76 48	86.87 333	81.67 45	84.40 78	94.63 89	38.17 343	94.67 211	91.98 36	83.34 171	92.16 202

test1111		80.84 164	80.02 163	83.33 191	87.87 214	60.76 280	92.62 145	86.86 334	77.86 113	75.73 173	91.39 172	46.35 303	94.70 210	72.79 193	88.68 115	94.52 115

ECVR-MVS		81.29 155	80.38 161	84.01 169	88.39 198	61.96 254	92.56 152	86.79 335	77.66 118	76.63 166	91.42 170	46.34 304	95.24 191	74.36 182	89.23 106	94.85 93

pmmvs6		67.57 333	64.76 335	76.00 331	72.82 394	53.37 359	88.71 281	86.78 336	53.19 383	57.58 360	78.03 351	35.33 365	92.41 294	55.56 323	54.88 379	82.21 358

MonoMVSNet		76.99 234	75.08 241	82.73 204	83.32 308	63.24 222	86.47 315	86.37 337	79.08 92	66.31 296	79.30 343	49.80 274	91.72 313	79.37 143	65.70 310	93.23 164

F-COLMAP		70.66 304	68.44 312	77.32 318	86.37 253	55.91 346	88.00 293	86.32 338	56.94 372	57.28 361	88.07 226	33.58 370	92.49 292	51.02 338	68.37 291	83.55 335

IterMVS		72.65 295	70.83 293	78.09 309	82.17 320	62.96 230	87.64 302	86.28 339	71.56 239	60.44 339	78.85 345	45.42 312	86.66 368	63.30 285	61.83 346	84.65 327
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet5		68.04 329	65.66 329	75.18 336	84.43 293	57.89 326	83.54 330	86.26 340	61.83 344	53.64 373	73.30 378	37.15 356	85.08 377	48.99 348	61.77 347	82.56 355

GeoE		78.90 200	77.43 206	83.29 192	88.95 183	62.02 252	92.31 156	86.23 341	70.24 262	71.34 231	89.27 206	54.43 226	94.04 241	63.31 284	80.81 198	93.81 150

EU-MVSNet		64.01 353	63.01 347	67.02 383	74.40 388	38.86 418	83.27 335	86.19 342	45.11 406	54.27 369	81.15 320	36.91 359	80.01 404	48.79 350	57.02 371	82.19 359

Effi-MVS+		83.82 108	82.76 122	86.99 56	89.56 165	69.40 54	91.35 204	86.12 343	72.59 199	83.22 90	92.81 139	59.60 160	96.01 158	81.76 122	87.80 124	95.56 57

IterMVS-SCA-FT		71.55 301	69.97 301	76.32 328	81.48 326	60.67 286	87.64 302	85.99 344	66.17 302	59.50 344	78.88 344	45.53 310	83.65 386	62.58 291	61.93 345	84.63 328

kuosan		60.86 365	60.24 358	62.71 390	81.57 325	46.43 398	75.70 387	85.88 345	57.98 364	48.95 392	69.53 394	58.42 175	76.53 406	28.25 415	35.87 413	65.15 414

XVG-ACMP-BASELINE		68.04 329	65.53 330	75.56 332	74.06 389	52.37 362	78.43 373	85.88 345	62.03 340	58.91 350	81.21 319	20.38 408	91.15 326	60.69 301	68.18 292	83.16 344

ambc				69.61 372	61.38 419	41.35 410	49.07 426	85.86 347		50.18 388	66.40 400	10.16 423	88.14 355	45.73 366	44.20 398	79.32 383

CMPMVS	48.56 21	66.77 338	64.41 340	73.84 348	70.65 400	50.31 376	77.79 378	85.73 348	45.54 405	44.76 404	82.14 300	35.40 364	90.14 338	63.18 286	74.54 247	81.07 367
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
fmvsm_s_conf0.1_n_2		84.40 92	84.78 85	83.27 193	85.25 274	60.41 292	94.13 68	85.69 349	83.05 28	87.99 41	96.37 31	52.75 245	97.68 53	93.75 22	84.05 168	91.71 209

Fast-Effi-MVS+-dtu		75.04 266	73.37 266	80.07 274	80.86 330	59.52 310	91.20 213	85.38 350	71.90 220	65.20 302	84.84 268	41.46 328	92.97 269	66.50 257	72.96 260	87.73 267

Anonymous202405211		77.96 219	75.33 238	85.87 93	93.73 53	64.52 176	94.85 46	85.36 351	62.52 335	76.11 170	90.18 192	29.43 387	97.29 81	68.51 236	77.24 232	95.81 49

Anonymous20240521		62.09 359	59.08 363	71.10 368	67.19 407	48.72 386	83.91 328	85.23 352	50.38 392	47.84 395	71.22 391	20.74 406	85.51 375	46.47 362	58.75 367	79.06 384

our_test_3		68.29 327	64.69 336	79.11 300	78.92 357	64.85 174	88.40 287	85.06 353	60.32 353	52.68 375	76.12 368	40.81 331	89.80 344	44.25 372	55.65 375	82.67 354

USDC		67.43 336	64.51 338	76.19 329	77.94 371	55.29 350	78.38 374	85.00 354	73.17 186	48.36 394	80.37 329	21.23 405	92.48 293	52.15 336	64.02 330	80.81 370

TransMVSNet (Re)		70.07 310	67.66 316	77.31 319	80.62 336	59.13 317	91.78 185	84.94 355	65.97 303	60.08 342	80.44 328	50.78 263	91.87 309	48.84 349	45.46 397	80.94 368

KD-MVS_self_test		60.87 364	58.60 364	67.68 380	66.13 410	39.93 415	75.63 388	84.70 356	57.32 369	49.57 389	68.45 397	29.55 385	82.87 392	48.09 352	47.94 393	80.25 377

ACMH	63.93 17	68.62 322	64.81 334	80.03 276	85.22 275	63.25 221	87.72 299	84.66 357	60.83 349	51.57 381	79.43 342	27.29 393	94.96 199	41.76 380	64.84 319	81.88 360
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
dongtai		55.18 376	55.46 375	54.34 401	76.03 383	36.88 419	76.07 384	84.61 358	51.28 388	43.41 409	64.61 405	56.56 201	67.81 419	18.09 424	28.50 424	58.32 417

Baseline_NR-MVSNet		73.99 277	72.83 272	77.48 315	80.78 332	59.29 315	91.79 183	84.55 359	68.85 279	68.99 258	80.70 323	56.16 204	92.04 307	62.67 290	60.98 355	81.11 366

MIMVSNet1		60.16 368	57.33 369	68.67 376	69.71 402	44.13 404	78.92 371	84.21 360	55.05 379	44.63 405	71.85 386	23.91 399	81.54 400	32.63 409	55.03 378	80.35 374

test20.03		63.83 354	62.65 350	67.38 382	70.58 401	39.94 414	86.57 314	84.17 361	63.29 326	51.86 379	77.30 356	37.09 357	82.47 394	38.87 392	54.13 381	79.73 379

MDA-MVSNet_test_wron		63.78 355	60.16 359	74.64 339	78.15 369	60.41 292	83.49 331	84.03 362	56.17 377	39.17 414	71.59 388	37.22 354	83.24 391	42.87 377	48.73 391	80.26 376

ADS-MVSNet		68.54 324	64.38 341	81.03 254	88.06 208	66.90 124	68.01 405	84.02 363	57.57 365	64.48 309	69.87 392	38.68 336	89.21 347	40.87 384	67.89 296	86.97 281

CR-MVSNet		73.79 280	70.82 295	82.70 206	83.15 310	67.96 93	70.25 397	84.00 364	73.67 180	69.97 247	72.41 382	57.82 182	89.48 345	52.99 334	73.13 258	90.64 229

Patchmtry		67.53 334	63.93 342	78.34 304	82.12 321	64.38 185	68.72 402	84.00 364	48.23 400	59.24 345	72.41 382	57.82 182	89.27 346	46.10 364	56.68 374	81.36 363

test_fmvsmvis_n_1920		83.80 109	83.48 100	84.77 135	82.51 317	63.72 205	91.37 202	83.99 366	81.42 51	77.68 154	95.74 51	58.37 176	97.58 63	93.38 23	86.87 134	93.00 175

YYNet1		63.76 356	60.14 360	74.62 340	78.06 370	60.19 299	83.46 333	83.99 366	56.18 376	39.25 413	71.56 389	37.18 355	83.34 389	42.90 376	48.70 392	80.32 375

LTVRE_ROB	59.60 19	66.27 340	63.54 344	74.45 342	84.00 300	51.55 367	67.08 409	83.53 368	58.78 361	54.94 367	80.31 330	34.54 367	93.23 263	40.64 386	68.03 294	78.58 389
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		65.53 346	62.32 352	75.19 335	69.39 404	59.59 308	82.80 343	83.43 369	62.52 335	51.30 383	72.49 380	32.86 371	87.16 367	55.32 324	50.73 388	78.83 387

OpenMVS_ROB	61.12 18	66.39 339	62.92 348	76.80 326	76.51 378	57.77 328	89.22 271	83.41 370	55.48 378	53.86 372	77.84 352	26.28 396	93.95 247	34.90 400	68.76 288	78.68 388

PatchMatch-RL		72.06 297	69.98 300	78.28 306	89.51 167	55.70 348	83.49 331	83.39 371	61.24 346	63.72 318	82.76 291	34.77 366	93.03 267	53.37 333	77.59 224	86.12 301

MSDG		69.54 315	65.73 327	80.96 255	85.11 279	63.71 206	84.19 326	83.28 372	56.95 371	54.50 368	84.03 277	31.50 378	96.03 156	42.87 377	69.13 286	83.14 345

CHOSEN 280x420		77.35 228	76.95 217	78.55 303	87.07 236	62.68 239	69.71 400	82.95 373	68.80 280	71.48 229	87.27 241	66.03 73	84.00 384	76.47 165	82.81 176	88.95 249

ppachtmachnet_test		67.72 331	63.70 343	79.77 286	78.92 357	66.04 144	88.68 282	82.90 374	60.11 355	55.45 365	75.96 369	39.19 335	90.55 328	39.53 388	52.55 385	82.71 351

new-patchmatchnet		59.30 370	56.48 372	67.79 379	65.86 411	44.19 403	82.47 344	81.77 375	59.94 356	43.65 408	66.20 401	27.67 392	81.68 399	39.34 389	41.40 403	77.50 395

MDA-MVSNet-bldmvs		61.54 362	57.70 367	73.05 353	79.53 348	57.00 341	83.08 339	81.23 376	57.57 365	34.91 418	72.45 381	32.79 372	86.26 371	35.81 397	41.95 402	75.89 398

OurMVSNet-221017-0		64.68 349	62.17 353	72.21 361	76.08 382	47.35 391	80.67 358	81.02 377	56.19 375	51.60 380	79.66 340	27.05 394	88.56 350	53.60 332	53.63 382	80.71 371

ACMH+	65.35 16	67.65 332	64.55 337	76.96 324	84.59 287	57.10 337	88.08 290	80.79 378	58.59 363	53.00 374	81.09 321	26.63 395	92.95 270	46.51 361	61.69 351	80.82 369

CNLPA		74.31 273	72.30 281	80.32 266	91.49 125	61.66 262	90.85 224	80.72 379	56.67 374	63.85 317	90.64 180	46.75 299	90.84 327	53.79 330	75.99 240	88.47 259

mmtdpeth		68.33 326	66.37 323	74.21 346	82.81 315	51.73 365	84.34 325	80.42 380	67.01 297	71.56 227	68.58 396	30.52 384	92.35 298	75.89 168	36.21 412	78.56 390

LS3D		69.17 317	66.40 322	77.50 314	91.92 110	56.12 345	85.12 320	80.37 381	46.96 401	56.50 363	87.51 236	37.25 353	93.71 254	32.52 410	79.40 208	82.68 353

testgi		64.48 351	62.87 349	69.31 374	71.24 395	40.62 412	85.49 318	79.92 382	65.36 308	54.18 370	83.49 284	23.74 400	84.55 379	41.60 381	60.79 357	82.77 348

test_0402		64.54 350	61.09 356	74.92 338	84.10 299	60.75 281	87.95 294	79.71 383	52.03 385	52.41 376	77.20 358	32.21 376	91.64 315	23.14 419	61.03 354	72.36 407

SixPastTwentyTwo		64.92 348	61.78 355	74.34 344	78.74 361	49.76 378	83.42 334	79.51 384	62.86 331	50.27 386	77.35 355	30.92 383	90.49 330	45.89 365	47.06 394	82.78 347

mvs5depth		61.03 363	57.65 368	71.18 367	67.16 408	47.04 396	72.74 392	77.49 385	57.47 368	60.52 338	72.53 379	22.84 402	88.38 352	49.15 347	38.94 408	78.11 393

ITE_SJBPF				70.43 370	74.44 387	47.06 395		77.32 386	60.16 354	54.04 371	83.53 282	23.30 401	84.01 383	43.07 374	61.58 352	80.21 378

K. test v3		63.09 357	59.61 362	73.53 350	76.26 380	49.38 383	83.27 335	77.15 387	64.35 314	47.77 396	72.32 384	28.73 388	87.79 359	49.93 344	36.69 411	83.41 340

DP-MVS		69.90 312	66.48 320	80.14 272	95.36 28	62.93 231	89.56 262	76.11 388	50.27 393	57.69 359	85.23 264	39.68 334	95.73 166	33.35 403	71.05 275	81.78 362

RPSCF		64.24 352	61.98 354	71.01 369	76.10 381	45.00 402	75.83 386	75.94 389	46.94 402	58.96 349	84.59 271	31.40 379	82.00 398	47.76 357	60.33 362	86.04 302

test_fmvs1_n		72.69 294	71.92 285	74.99 337	71.15 397	47.08 394	87.34 306	75.67 390	63.48 324	78.08 151	91.17 175	20.16 409	87.87 357	84.65 96	75.57 242	90.01 237

TinyColmap		60.32 366	56.42 373	72.00 365	78.78 360	53.18 360	78.36 375	75.64 391	52.30 384	41.59 412	75.82 371	14.76 417	88.35 353	35.84 396	54.71 380	74.46 400

ADS-MVSNet2		66.90 337	63.44 345	77.26 320	88.06 208	60.70 285	68.01 405	75.56 392	57.57 365	64.48 309	69.87 392	38.68 336	84.10 381	40.87 384	67.89 296	86.97 281

COLMAP_ROB	57.96 20	62.98 358	59.65 361	72.98 354	81.44 327	53.00 361	83.75 329	75.53 393	48.34 398	48.81 393	81.40 313	24.14 398	90.30 331	32.95 405	60.52 359	75.65 399
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Patchmatch-test		65.86 342	60.94 357	80.62 263	83.75 302	58.83 319	58.91 420	75.26 394	44.50 408	50.95 385	77.09 360	58.81 172	87.90 356	35.13 399	64.03 329	95.12 81

test_fmvs1		74.07 275	73.69 262	75.22 334	78.91 359	47.34 392	89.06 277	74.69 395	63.68 322	79.41 133	91.59 168	24.36 397	87.77 360	85.22 87	76.26 238	90.55 231

MVS-HIRNet		60.25 367	55.55 374	74.35 343	84.37 294	56.57 343	71.64 395	74.11 396	34.44 417	45.54 402	42.24 425	31.11 382	89.81 342	40.36 387	76.10 239	76.67 397

pmmvs3		55.51 374	51.50 380	67.53 381	57.90 422	50.93 373	80.37 360	73.66 397	40.63 415	44.15 407	64.75 404	16.30 412	78.97 405	44.77 371	40.98 406	72.69 405

TDRefinement		55.28 375	51.58 379	66.39 384	59.53 421	46.15 399	76.23 383	72.80 398	44.60 407	42.49 410	76.28 367	15.29 415	82.39 395	33.20 404	43.75 399	70.62 409

MVStest1		51.35 379	46.89 383	64.74 385	65.06 412	51.10 371	67.33 408	72.58 399	30.20 421	35.30 416	74.82 374	27.70 391	69.89 416	24.44 418	24.57 425	73.22 403

Gipuma		34.91 394	31.44 397	45.30 409	70.99 398	39.64 417	19.85 431	72.56 400	20.10 427	16.16 431	21.47 432	5.08 432	71.16 414	13.07 429	43.70 400	25.08 429
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_vis1_n		71.63 300	70.73 296	74.31 345	69.63 403	47.29 393	86.91 310	72.11 401	63.21 328	75.18 182	90.17 193	20.40 407	85.76 372	84.59 97	74.42 249	89.87 238

FPMVS		45.64 385	43.10 389	53.23 402	51.42 427	36.46 420	64.97 411	71.91 402	29.13 422	27.53 422	61.55 411	9.83 424	65.01 425	16.00 428	55.58 376	58.22 418

dmvs_testset		65.55 345	66.45 321	62.86 389	79.87 344	22.35 435	76.55 381	71.74 403	77.42 125	55.85 364	87.77 231	51.39 258	80.69 402	31.51 414	65.92 309	85.55 315

ANet_high		40.27 391	35.20 394	55.47 397	34.74 438	34.47 423	63.84 413	71.56 404	48.42 397	18.80 427	41.08 426	9.52 425	64.45 426	20.18 422	8.66 434	67.49 412

Patchmatch-RL test		68.17 328	64.49 339	79.19 296	71.22 396	53.93 357	70.07 399	71.54 405	69.22 274	56.79 362	62.89 407	56.58 200	88.61 348	69.53 224	52.61 384	95.03 87

mamv4		65.18 347	67.43 317	58.44 393	77.88 373	49.36 384	69.40 401	70.99 406	48.31 399	57.78 358	85.53 262	59.01 170	51.88 431	73.67 186	64.32 325	74.07 401

LCM-MVSNet-Re		72.93 287	71.84 286	76.18 330	88.49 191	48.02 387	80.07 366	70.17 407	73.96 171	52.25 377	80.09 335	49.98 270	88.24 354	67.35 245	84.23 165	92.28 195

test_fmvs2		65.78 344	64.84 333	68.60 377	66.54 409	41.71 409	83.27 335	69.81 408	54.38 380	67.91 274	84.54 273	15.35 414	81.22 401	75.65 170	66.16 306	82.88 346

LCM-MVSNet		40.54 388	35.79 393	54.76 400	36.92 437	30.81 427	51.41 424	69.02 409	22.07 424	24.63 424	45.37 421	4.56 433	65.81 422	33.67 402	34.50 417	67.67 411

AllTest		61.66 360	58.06 365	72.46 358	79.57 346	51.42 369	80.17 364	68.61 410	51.25 389	45.88 398	81.23 315	19.86 410	86.58 369	38.98 390	57.01 372	79.39 381

TestCases				72.46 358	79.57 346	51.42 369		68.61 410	51.25 389	45.88 398	81.23 315	19.86 410	86.58 369	38.98 390	57.01 372	79.39 381

LF4IMVS		54.01 377	52.12 378	59.69 392	62.41 416	39.91 416	68.59 403	68.28 412	42.96 412	44.55 406	75.18 372	14.09 419	68.39 418	41.36 383	51.68 386	70.78 408

door								66.57 413

door-mid								66.01 414

ttmdpeth		53.34 378	49.96 381	63.45 388	62.07 418	40.04 413	72.06 393	65.64 415	42.54 413	51.88 378	77.79 353	13.94 420	76.48 407	32.93 406	30.82 422	73.84 402

test_fmvs3		56.82 372	54.86 376	62.69 391	53.59 424	35.47 421	75.87 385	65.64 415	43.91 409	55.10 366	71.43 390	6.91 429	74.40 411	68.64 235	52.63 383	78.20 392

DSMNet-mixed		56.78 373	54.44 377	63.79 387	63.21 414	29.44 430	64.43 412	64.10 417	42.12 414	51.32 382	71.60 387	31.76 377	75.04 409	36.23 395	65.20 316	86.87 284

PM-MVS		59.40 369	56.59 371	67.84 378	63.63 413	41.86 408	76.76 380	63.22 418	59.01 360	51.07 384	72.27 385	11.72 421	83.25 390	61.34 297	50.28 390	78.39 391

new_pmnet		49.31 381	46.44 384	57.93 394	62.84 415	40.74 411	68.47 404	62.96 419	36.48 416	35.09 417	57.81 414	14.97 416	72.18 413	32.86 407	46.44 395	60.88 416

lessismore_v0				73.72 349	72.93 393	47.83 389		61.72 420		45.86 400	73.76 377	28.63 390	89.81 342	47.75 358	31.37 419	83.53 336

mvsany_test1		68.77 321	68.56 310	69.39 373	73.57 390	45.88 401	80.93 357	60.88 421	59.65 357	71.56 227	90.26 191	43.22 322	75.05 408	74.26 184	62.70 337	87.25 279

EGC-MVSNET		42.35 387	38.09 390	55.11 398	74.57 386	46.62 397	71.63 396	55.77 422	0.04 436	0.24 437	62.70 408	14.24 418	74.91 410	17.59 425	46.06 396	43.80 422

WB-MVS		46.23 384	44.94 386	50.11 404	62.13 417	21.23 437	76.48 382	55.49 423	45.89 404	35.78 415	61.44 412	35.54 363	72.83 412	9.96 431	21.75 426	56.27 419

SSC-MVS		44.51 386	43.35 388	47.99 408	61.01 420	18.90 439	74.12 390	54.36 424	43.42 411	34.10 419	60.02 413	34.42 368	70.39 415	9.14 433	19.57 427	54.68 420

test_method		38.59 392	35.16 395	48.89 406	54.33 423	21.35 436	45.32 427	53.71 425	7.41 433	28.74 421	51.62 417	8.70 426	52.87 430	33.73 401	32.89 418	72.47 406

APD_test1		40.50 389	37.31 392	50.09 405	51.88 425	35.27 422	59.45 419	52.59 426	21.64 425	26.12 423	57.80 415	4.56 433	66.56 421	22.64 420	39.09 407	48.43 421

PMMVS2		37.93 393	33.61 396	50.92 403	46.31 429	24.76 433	60.55 418	50.05 427	28.94 423	20.93 425	47.59 418	4.41 435	65.13 424	25.14 417	18.55 429	62.87 415

PMVS	26.43 22	31.84 397	28.16 400	42.89 410	25.87 440	27.58 431	50.92 425	49.78 428	21.37 426	14.17 432	40.81 427	2.01 439	66.62 420	9.61 432	38.88 410	34.49 428
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_f		46.58 383	43.45 387	55.96 396	45.18 431	32.05 425	61.18 415	49.49 429	33.39 418	42.05 411	62.48 409	7.00 428	65.56 423	47.08 360	43.21 401	70.27 410

test_vis1_rt		59.09 371	57.31 370	64.43 386	68.44 406	46.02 400	83.05 341	48.63 430	51.96 386	49.57 389	63.86 406	16.30 412	80.20 403	71.21 210	62.79 336	67.07 413

mvsany_test3		48.86 382	46.35 385	56.41 395	46.00 430	31.67 426	62.26 414	47.25 431	43.71 410	45.54 402	68.15 398	10.84 422	64.44 427	57.95 313	35.44 416	73.13 404

testf1		32.77 395	29.47 398	42.67 411	41.89 434	30.81 427	52.07 422	43.45 432	15.45 428	18.52 428	44.82 422	2.12 437	58.38 428	16.05 426	30.87 420	38.83 424

APD_test2		32.77 395	29.47 398	42.67 411	41.89 434	30.81 427	52.07 422	43.45 432	15.45 428	18.52 428	44.82 422	2.12 437	58.38 428	16.05 426	30.87 420	38.83 424

E-PMN		24.61 398	24.00 402	26.45 415	43.74 433	18.44 440	60.86 416	39.66 434	15.11 430	9.53 434	22.10 431	6.52 430	46.94 433	8.31 434	10.14 431	13.98 431

tmp_tt		22.26 401	23.75 403	17.80 417	5.23 441	12.06 442	35.26 428	39.48 435	2.82 435	18.94 426	44.20 424	22.23 404	24.64 436	36.30 394	9.31 433	16.69 430

MVE	24.84 23	24.35 399	19.77 405	38.09 413	34.56 439	26.92 432	26.57 429	38.87 436	11.73 432	11.37 433	27.44 429	1.37 440	50.42 432	11.41 430	14.60 430	36.93 426
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		23.76 400	23.20 404	25.46 416	41.52 436	16.90 441	60.56 417	38.79 437	14.62 431	8.99 435	20.24 434	7.35 427	45.82 434	7.25 435	9.46 432	13.64 432

test_vis3_rt		40.46 390	37.79 391	48.47 407	44.49 432	33.35 424	66.56 410	32.84 438	32.39 419	29.65 420	39.13 428	3.91 436	68.65 417	50.17 341	40.99 405	43.40 423

MTMP							93.77 92	32.52 439

DeepMVS_CX				34.71 414	51.45 426	24.73 434		28.48 440	31.46 420	17.49 430	52.75 416	5.80 431	42.60 435	18.18 423	19.42 428	36.81 427

N_pmnet		50.55 380	49.11 382	54.88 399	77.17 376	4.02 443	84.36 324	2.00 441	48.59 396	45.86 400	68.82 395	32.22 375	82.80 393	31.58 412	51.38 387	77.81 394

wuyk23d		11.30 403	10.95 406	12.33 418	48.05 428	19.89 438	25.89 430	1.92 442	3.58 434	3.12 436	1.37 436	0.64 441	15.77 437	6.23 436	7.77 435	1.35 433

testmvs		7.23 405	9.62 408	0.06 420	0.04 442	0.02 445	84.98 322	0.02 443	0.03 437	0.18 438	1.21 437	0.01 443	0.02 438	0.14 437	0.01 436	0.13 435

test123		6.92 406	9.21 409	0.08 419	0.03 443	0.05 444	81.65 350	0.01 444	0.02 438	0.14 439	0.85 438	0.03 442	0.02 438	0.12 438	0.00 437	0.16 434

mmdepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 437	0.00 436

monomultidepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 437	0.00 436

test_blank		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 437	0.00 436

uanet_test		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 437	0.00 436

DCPMVS		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 437	0.00 436

pcd_1.5k_mvsjas		4.46 407	5.95 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	53.55 236	0.00 440	0.00 439	0.00 437	0.00 436

sosnet-low-res		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 437	0.00 436

sosnet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 437	0.00 436

uncertanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 437	0.00 436

Regformer		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 437	0.00 436

n2								0.00 445

nn								0.00 445

ab-mvs-re		7.91 404	10.55 407	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	94.95 78	0.00 444	0.00 440	0.00 439	0.00 437	0.00 436

uanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 437	0.00 436

WAC-MVS						49.45 381								31.56 413

PC_three_1452									80.91 58	94.07 2	96.83 21	83.57 4	99.12 5	95.70 8	97.42 4	97.55 4

eth-test2					0.00 444

eth-test					0.00 444

OPU-MVS				89.97 3	97.52 3	73.15 14	96.89 6				97.00 11	83.82 2	99.15 2	95.72 6	97.63 3	97.62 2

test_0728_THIRD									72.48 202	90.55 23	96.93 13	76.24 11	99.08 11	91.53 39	94.99 18	96.43 31

GSMVS																94.68 104

test_part2					96.29 19	68.16 89				90.78 20

sam_mvs1												57.85 181				94.68 104

sam_mvs												54.91 220

test_post1							78.95 370				20.70 433	53.05 241	91.50 323	60.43 302

test_post											23.01 430	56.49 202	92.67 285

patchmatchnet-post											67.62 399	57.62 184	90.25 332

gm-plane-assit					88.42 196	67.04 120			78.62 101		91.83 162		97.37 75	76.57 164

test9_res														89.41 49	94.96 19	95.29 71

agg_prior2														86.41 79	94.75 30	95.33 67

test_prior4						67.18 115	93.92 81

test_prior2							95.10 38		75.40 149	85.25 72	95.61 54	67.94 57		87.47 68	94.77 26

旧先验2							92.00 174		59.37 359	87.54 47			93.47 260	75.39 172

新几何2							91.41 195

原ACMM2							92.01 171

testdata2													96.09 150	61.26 298

segment_acmp												65.94 74

testdata1							89.21 272		77.55 121

plane_prior7					86.94 239	61.51 264

plane_prior6					87.23 231	62.32 247						50.66 264

plane_prior4											89.14 209

plane_prior3						61.95 255			79.09 91	72.53 211

plane_prior2							93.13 120		78.81 98

plane_prior1					87.15 233

plane_prior						62.42 243	93.85 85		79.38 83						78.80 215

HQP5-MVS						63.66 210

HQP-NCC					87.54 223		94.06 70		79.80 74	74.18 190

ACMP_Plane					87.54 223		94.06 70		79.80 74	74.18 190

BP-MVS														77.63 159

HQP4-MVS										74.18 190			95.61 174			88.63 254

HQP2-MVS												51.63 256

NP-MVS					87.41 226	63.04 227					90.30 189

MDTV_nov1_ep13_2view						59.90 304	80.13 365		67.65 290	72.79 205		54.33 228		59.83 306		92.58 186

ACMMP++_ref															71.63 269

ACMMP++															69.72 278

Test By Simon												54.21 230

High-resolution multi-view benchmark