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.

thres200		88.92 140	87.65 152	92.73 102	96.30 99	85.62 51	97.85 67	98.86 1	84.38 168	84.82 172	93.99 195	75.12 160	98.01 154	70.86 297	86.67 203	94.56 222

thres100view900		88.30 161	86.95 173	92.33 119	96.10 106	84.90 73	97.14 126	98.85 2	82.69 212	83.41 190	93.66 202	75.43 150	97.93 156	69.04 305	86.24 210	94.17 224

tfpn200view9		88.48 154	87.15 167	92.47 111	96.21 102	85.30 59	97.44 100	98.85 2	83.37 195	83.99 182	93.82 198	75.36 153	97.93 156	69.04 305	86.24 210	94.17 224

thres600view7		88.06 166	86.70 177	92.15 131	96.10 106	85.17 65	97.14 126	98.85 2	82.70 211	83.41 190	93.66 202	75.43 150	97.82 165	67.13 314	85.88 214	93.45 240

thres400		88.42 157	87.15 167	92.23 125	96.21 102	85.30 59	97.44 100	98.85 2	83.37 195	83.99 182	93.82 198	75.36 153	97.93 156	69.04 305	86.24 210	93.45 240

MVS_111021_HR		93.41 40	93.39 43	93.47 76	97.34 85	82.83 109	97.56 89	98.27 6	89.16 63	89.71 114	97.14 104	79.77 77	99.56 66	93.65 69	97.94 59	98.02 83

sss		90.87 106	89.96 115	93.60 66	94.15 171	83.84 91	97.14 126	98.13 7	85.93 129	89.68 115	96.09 134	71.67 203	99.30 83	87.69 145	89.16 174	97.66 114

MM		95.85 6	95.74 10	96.15 8	96.34 96	89.50 9	99.18 6	98.10 8	95.68 1	96.64 21	97.92 60	80.72 65	99.80 25	99.16 1	97.96 57	99.15 26

MG-MVS		94.25 28	93.72 34	95.85 11	99.38 3	89.35 11	97.98 60	98.09 9	89.99 53	92.34 77	96.97 112	81.30 62	98.99 107	88.54 135	98.88 20	99.20 24

VNet		92.11 71	91.22 83	94.79 26	96.91 91	86.98 28	97.91 64	97.96 10	86.38 120	93.65 60	95.74 140	70.16 219	98.95 111	93.39 71	88.87 179	98.43 59

MVS_0304		95.36 10	95.20 17	95.85 11	94.89 147	89.22 12	98.83 26	97.88 11	94.68 4	95.14 39	97.99 54	80.80 64	99.81 21	98.60 6	97.95 58	98.50 54

test_yl		91.46 88	90.53 98	94.24 41	97.41 80	85.18 61	98.08 53	97.72 12	80.94 237	89.85 111	96.14 132	75.61 142	98.81 119	90.42 114	88.56 185	98.74 39

DCV-MVSNet		91.46 88	90.53 98	94.24 41	97.41 80	85.18 61	98.08 53	97.72 12	80.94 237	89.85 111	96.14 132	75.61 142	98.81 119	90.42 114	88.56 185	98.74 39

WTY-MVS		92.65 59	91.68 75	95.56 14	96.00 108	88.90 13	98.23 44	97.65 14	88.57 70	89.82 113	97.22 102	79.29 80	99.06 104	89.57 124	88.73 181	98.73 43

EPNet		94.06 32	94.15 31	93.76 56	97.27 87	84.35 81	98.29 42	97.64 15	94.57 6	95.36 34	96.88 115	79.96 76	99.12 100	91.30 97	96.11 102	97.82 103
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HY-MVS	84.06 6	91.63 84	90.37 104	95.39 18	96.12 105	88.25 16	90.22 329	97.58 16	88.33 77	90.50 106	91.96 227	79.26 81	99.06 104	90.29 116	89.07 175	98.88 35

baseline2		90.39 114	90.21 108	90.93 171	90.86 269	80.99 150	95.20 242	97.41 17	86.03 127	80.07 234	94.61 180	90.58 6	97.47 187	87.29 149	89.86 169	94.35 223

test2506		90.96 103	90.39 102	92.65 105	93.54 188	82.46 116	96.37 185	97.35 18	86.78 116	87.55 146	95.25 155	77.83 105	97.50 184	84.07 172	94.80 118	97.98 90

PVSNet	82.34 9	89.02 137	87.79 150	92.71 103	95.49 126	81.50 141	97.70 79	97.29 19	87.76 90	85.47 165	95.12 167	56.90 306	98.90 115	80.33 207	94.02 128	97.71 111

testing222		91.09 98	90.49 100	92.87 95	95.82 116	85.04 68	96.51 175	97.28 20	86.05 126	89.13 124	95.34 154	80.16 74	96.62 233	85.82 158	88.31 189	96.96 155

PGM-MVS		91.93 75	91.80 73	92.32 121	98.27 50	79.74 186	95.28 236	97.27 21	83.83 186	90.89 102	97.78 70	76.12 135	99.56 66	88.82 132	97.93 61	97.66 114

IB-MVS	85.34 4	88.67 148	87.14 169	93.26 79	93.12 204	84.32 82	98.76 27	97.27 21	87.19 107	79.36 240	90.45 251	83.92 46	98.53 130	84.41 169	69.79 320	96.93 157
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
test_fmvsm_n_1920		94.81 19	95.60 11	92.45 112	95.29 132	80.96 152	99.29 3	97.21 23	94.50 7	97.29 14	98.44 29	82.15 56	99.78 28	98.56 7	97.68 66	96.61 170

patch_mono-2		95.14 13	96.08 7	92.33 119	98.44 43	77.84 243	98.43 37	97.21 23	92.58 21	97.68 11	97.65 78	86.88 25	99.83 16	98.25 9	97.60 68	99.33 18

MVS		90.60 110	88.64 135	96.50 5	94.25 167	90.53 8	93.33 291	97.21 23	77.59 298	78.88 243	97.31 94	71.52 206	99.69 49	89.60 123	98.03 55	99.27 22

ETVMVS		90.99 101	90.26 105	93.19 83	95.81 117	85.64 50	96.97 143	97.18 26	85.43 137	88.77 133	94.86 175	82.00 58	96.37 240	82.70 194	88.60 182	97.57 121

CSCG		92.02 72	91.65 76	93.12 85	98.53 36	80.59 161	97.47 97	97.18 26	77.06 307	84.64 177	97.98 57	83.98 44	99.52 69	90.72 106	97.33 77	99.23 23

fmvsm_s_conf0.5_n		93.69 36	94.13 32	92.34 117	94.56 154	82.01 121	99.07 16	97.13 28	92.09 25	96.25 26	98.53 22	76.47 127	99.80 25	98.39 8	94.71 120	95.22 207

PHI-MVS		93.59 38	93.63 37	93.48 74	98.05 58	81.76 133	98.64 32	97.13 28	82.60 214	94.09 56	98.49 26	80.35 68	99.85 10	94.74 57	98.62 33	98.83 36

CNVR-MVS		96.30 1	96.54 1	95.55 15	99.31 5	87.69 23	99.06 17	97.12 30	94.66 5	96.79 17	98.78 9	86.42 28	99.95 3	97.59 23	99.18 7	99.00 31

h-mvs33		89.30 133	88.95 131	90.36 188	95.07 140	76.04 276	96.96 145	97.11 31	90.39 48	92.22 79	95.10 168	74.70 165	98.86 116	93.14 78	65.89 352	96.16 183

MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 10	98.94 24	97.10 32	95.17 3	92.11 81	98.46 28	87.33 24	99.97 2	97.21 28	99.31 4	99.63 7

testing11		92.48 63	92.04 70	93.78 55	95.94 112	86.00 39	97.56 89	97.08 33	87.52 96	89.32 122	95.40 152	84.60 35	98.02 153	91.93 94	89.04 176	97.32 138

VPA-MVSNet		85.32 210	83.83 216	89.77 208	90.25 279	82.63 111	96.36 186	97.07 34	83.03 203	81.21 219	89.02 268	61.58 268	96.31 243	85.02 166	70.95 309	90.36 260

UWE-MVS		88.56 153	88.91 133	87.50 255	94.17 170	72.19 315	95.82 217	97.05 35	84.96 152	84.78 173	93.51 206	81.33 60	94.75 314	79.43 218	89.17 173	95.57 196

DELS-MVS		94.98 14	94.49 24	96.44 6	96.42 95	90.59 7	99.21 5	97.02 36	94.40 9	91.46 89	97.08 108	83.32 49	99.69 49	92.83 83	98.70 31	99.04 29
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
GG-mvs-BLEND				93.49 73	94.94 144	86.26 35	81.62 376	97.00 37		88.32 140	94.30 186	91.23 5	96.21 247	88.49 137	97.43 74	98.00 88

fmvsm_s_conf0.5_n_a		93.34 41	93.71 35	92.22 126	93.38 196	81.71 136	98.86 25	96.98 38	91.64 31	96.85 16	98.55 19	75.58 145	99.77 29	97.88 19	93.68 134	95.18 208

DPM-MVS		96.21 2	95.53 13	98.26 1	96.26 101	95.09 1	99.15 8	96.98 38	93.39 16	96.45 25	98.79 8	90.17 10	99.99 1	89.33 128	99.25 6	99.70 3

gg-mvs-nofinetune		85.48 209	82.90 233	93.24 80	94.51 160	85.82 44	79.22 380	96.97 40	61.19 378	87.33 149	53.01 396	90.58 6	96.07 250	86.07 157	97.23 80	97.81 104

NCCC		95.63 7	95.94 8	94.69 30	99.21 6	85.15 66	99.16 7	96.96 41	94.11 11	95.59 33	98.64 17	85.07 32	99.91 4	95.61 47	99.10 9	99.00 31

FIs		86.73 189	86.10 182	88.61 226	90.05 285	80.21 173	96.14 200	96.95 42	85.56 136	78.37 248	92.30 220	76.73 124	95.28 295	79.51 216	79.27 264	90.35 261

PVSNet_0	77.72 15	81.70 270	78.95 287	89.94 201	90.77 272	76.72 266	95.96 206	96.95 42	85.01 150	70.24 328	88.53 276	52.32 327	98.20 149	86.68 156	44.08 393	94.89 212

HPM-MVS++		95.32 11	95.48 14	94.85 25	98.62 34	86.04 38	97.81 71	96.93 44	92.45 22	95.69 32	98.50 25	85.38 30	99.85 10	94.75 56	99.18 7	98.65 47

MSLP-MVS++		94.28 26	94.39 27	93.97 49	98.30 49	84.06 87	98.64 32	96.93 44	90.71 42	93.08 68	98.70 15	79.98 75	99.21 88	94.12 64	99.07 11	98.63 48

testing99		91.91 76	91.35 80	93.60 66	95.98 110	85.70 46	97.31 111	96.92 46	86.82 114	88.91 128	95.25 155	84.26 42	97.89 163	88.80 133	87.94 193	97.21 146

testing91		91.90 77	91.31 82	93.66 62	95.99 109	85.68 48	97.39 107	96.89 47	86.75 118	88.85 130	95.23 158	83.93 45	97.90 162	88.91 130	87.89 194	97.41 133

UniMVSNet (Re)		85.31 211	84.23 211	88.55 227	89.75 289	80.55 163	96.72 162	96.89 47	85.42 138	78.40 247	88.93 269	75.38 152	95.52 285	78.58 227	68.02 337	89.57 277

FC-MVSNet-test		85.96 199	85.39 190	87.66 248	89.38 298	78.02 234	95.65 223	96.87 49	85.12 147	77.34 255	91.94 229	76.28 133	94.74 315	77.09 242	78.82 268	90.21 264

EI-MVSNet-Vis-set		91.84 79	91.77 74	92.04 136	97.60 71	81.17 145	96.61 168	96.87 49	88.20 80	89.19 123	97.55 86	78.69 92	99.14 97	90.29 116	90.94 164	95.80 190

IU-MVS					99.03 15	85.34 56		96.86 51	92.05 29	98.74 1				98.15 11	98.97 17	99.42 13

MSC_two_6792asdad				97.14 3	99.05 9	92.19 4		96.83 52					99.81 21	98.08 14	98.81 24	99.43 11

No_MVS				97.14 3	99.05 9	92.19 4		96.83 52					99.81 21	98.08 14	98.81 24	99.43 11

EI-MVSNet-UG-set		91.35 92	91.22 83	91.73 147	97.39 82	80.68 159	96.47 177	96.83 52	87.92 86	88.30 141	97.36 93	77.84 104	99.13 99	89.43 127	89.45 171	95.37 202

SED-MVS		95.88 5	96.22 4	94.87 24	99.03 15	85.03 69	99.12 12	96.78 55	88.72 67	97.79 7	98.91 2	88.48 17	99.82 18	98.15 11	98.97 17	99.74 1

test_241102_TWO								96.78 55	88.72 67	97.70 9	98.91 2	87.86 21	99.82 18	98.15 11	99.00 15	99.47 9

test_241102_ONE					99.03 15	85.03 69		96.78 55	88.72 67	97.79 7	98.90 5	88.48 17	99.82 18

test0726					99.05 9	85.18 61	99.11 15	96.78 55	88.75 65	97.65 12	98.91 2	87.69 22

MSP-MVS		95.62 8	96.54 1	92.86 96	98.31 48	80.10 177	97.42 104	96.78 55	92.20 24	97.11 15	98.29 35	93.46 1	99.10 101	96.01 40	99.30 5	99.38 14
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
无先验							96.87 152	96.78 55	77.39 300				99.52 69	79.95 213		98.43 59

DVP-MVS++		96.05 4	96.41 3	94.96 23	99.05 9	85.34 56	98.13 50	96.77 61	88.38 75	97.70 9	98.77 10	92.06 3	99.84 12	97.47 24	99.37 1	99.70 3

test_0728_SECOND				95.14 19	99.04 14	86.14 37	99.06 17	96.77 61					99.84 12	97.90 17	98.85 21	99.45 10

SMA-MVS		94.70 21	94.68 21	94.76 27	98.02 59	85.94 42	97.47 97	96.77 61	85.32 140	97.92 3	98.70 15	83.09 51	99.84 12	95.79 44	99.08 10	98.49 55
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
MVS_111021_LR		91.60 86	91.64 77	91.47 156	95.74 120	78.79 212	96.15 199	96.77 61	88.49 72	88.64 135	97.07 109	72.33 196	99.19 93	93.13 80	96.48 97	96.43 175

3Dnovator	82.32 10	89.33 132	87.64 153	94.42 35	93.73 184	85.70 46	97.73 77	96.75 65	86.73 119	76.21 275	95.93 136	62.17 261	99.68 51	81.67 200	97.81 62	97.88 95

DPE-MVS		95.32 11	95.55 12	94.64 31	98.79 23	84.87 74	97.77 73	96.74 66	86.11 123	96.54 24	98.89 6	88.39 19	99.74 38	97.67 22	99.05 12	99.31 20
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
PVSNet_BlendedMVS		90.05 120	89.96 115	90.33 189	97.47 76	83.86 89	98.02 59	96.73 67	87.98 84	89.53 119	89.61 263	76.42 129	99.57 64	94.29 61	79.59 261	87.57 327

PVSNet_Blended		93.13 42	92.98 48	93.57 68	97.47 76	83.86 89	99.32 2	96.73 67	91.02 40	89.53 119	96.21 131	76.42 129	99.57 64	94.29 61	95.81 110	97.29 142

ACMMP		90.39 114	89.97 114	91.64 150	97.58 73	78.21 230	96.78 159	96.72 69	84.73 157	84.72 175	97.23 101	71.22 208	99.63 57	88.37 140	92.41 152	97.08 152
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
新几何1				93.12 85	97.44 78	81.60 140		96.71 70	74.54 324	91.22 96	97.57 82	79.13 84	99.51 71	77.40 241	98.46 39	98.26 71

test_one_0601					98.91 18	84.56 80		96.70 71	88.06 82	96.57 23	98.77 10	88.04 20

HFP-MVS		92.89 49	92.86 51	92.98 91	98.71 25	81.12 146	97.58 87	96.70 71	85.20 145	91.75 86	97.97 59	78.47 93	99.71 45	90.95 100	98.41 42	98.12 79

ACMMPR		92.69 57	92.67 54	92.75 100	98.66 28	80.57 162	97.58 87	96.69 73	85.20 145	91.57 88	97.92 60	77.01 117	99.67 53	90.95 100	98.41 42	98.00 88

DeepPCF-MVS	89.82 1	94.61 22	96.17 5	89.91 202	97.09 90	70.21 335	98.99 23	96.69 73	95.57 2	95.08 41	99.23 1	86.40 29	99.87 8	97.84 20	98.66 32	99.65 6

thisisatest0530		89.65 127	89.02 128	91.53 154	93.46 194	80.78 157	96.52 173	96.67 75	81.69 230	83.79 187	94.90 174	88.85 15	97.68 169	77.80 230	87.49 199	96.14 184

tttt0517		88.57 152	88.19 143	89.71 209	93.00 206	75.99 280	95.67 221	96.67 75	80.78 241	81.82 213	94.40 184	88.97 14	97.58 175	76.05 255	86.31 207	95.57 196

thisisatest0515		90.95 104	90.26 105	93.01 90	94.03 179	84.27 85	97.91 64	96.67 75	83.18 198	86.87 155	95.51 150	88.66 16	97.85 164	80.46 206	89.01 177	96.92 159

ACMMP_NAP		93.46 39	93.23 45	94.17 44	97.16 88	84.28 84	96.82 156	96.65 78	86.24 121	94.27 53	97.99 54	77.94 101	99.83 16	93.39 71	98.57 34	98.39 61

TEST9					98.64 31	83.71 92	97.82 69	96.65 78	84.29 173	95.16 36	98.09 47	84.39 37	99.36 81

train_agg		94.28 26	94.45 25	93.74 57	98.64 31	83.71 92	97.82 69	96.65 78	84.50 164	95.16 36	98.09 47	84.33 38	99.36 81	95.91 43	98.96 19	98.16 75

1314		88.94 139	87.20 166	94.17 44	93.21 198	85.73 45	93.33 291	96.64 81	82.89 206	75.98 278	96.36 128	66.83 235	99.39 77	83.52 187	96.02 106	97.39 136

DeepC-MVS_fast	89.06 2	94.48 24	94.30 29	95.02 21	98.86 21	85.68 48	98.06 56	96.64 81	93.64 14	91.74 87	98.54 20	80.17 73	99.90 5	92.28 88	98.75 28	99.49 8
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_8					98.63 33	83.64 95	97.81 71	96.63 83	84.50 164	95.10 40	98.11 46	84.33 38	99.23 86

FE-MVS		86.06 198	84.15 213	91.78 146	94.33 166	79.81 181	84.58 368	96.61 84	76.69 309	85.00 169	87.38 291	70.71 215	98.37 141	70.39 300	91.70 160	97.17 149

原ACMM1				91.22 164	97.77 65	78.10 233		96.61 84	81.05 236	91.28 95	97.42 91	77.92 103	98.98 108	79.85 215	98.51 35	96.59 171

MAR-MVS		90.63 109	90.22 107	91.86 142	98.47 42	78.20 231	97.18 119	96.61 84	83.87 185	88.18 142	98.18 40	68.71 223	99.75 36	83.66 183	97.15 81	97.63 117
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
ZD-MVS					99.09 8	83.22 104		96.60 87	82.88 207	93.61 62	98.06 52	82.93 52	99.14 97	95.51 50	98.49 38

SteuartSystems-ACMMP		94.13 31	94.44 26	93.20 82	95.41 128	81.35 143	99.02 21	96.59 88	89.50 59	94.18 55	98.36 32	83.68 48	99.45 75	94.77 55	98.45 40	98.81 37
Skip Steuart: Steuart Systems R&D Blog.
D2MVS		82.67 256	81.55 253	86.04 283	87.77 315	76.47 268	95.21 241	96.58 89	82.66 213	70.26 327	85.46 325	60.39 274	95.80 267	76.40 251	79.18 265	85.83 354

save fliter					98.24 51	83.34 101	98.61 34	96.57 90	91.32 34

TESTMET0.1,1		89.83 124	89.34 125	91.31 158	92.54 221	80.19 174	97.11 129	96.57 90	86.15 122	86.85 156	91.83 231	79.32 79	96.95 215	81.30 201	92.35 153	96.77 165

agg_prior					98.59 35	83.13 105		96.56 92		94.19 54			99.16 96

旧先验1					97.39 82	79.58 191		96.54 93			98.08 50	84.00 43			97.42 75	97.62 118

WR-MVS_H		81.02 279	80.09 273	83.79 318	88.08 311	71.26 330	94.46 261	96.54 93	80.08 260	72.81 310	86.82 301	70.36 217	92.65 345	64.18 329	67.50 343	87.46 332

9.14			94.26 30		98.10 57		98.14 47	96.52 95	84.74 156	94.83 47	98.80 7	82.80 54	99.37 80	95.95 42	98.42 41

region2R		92.72 55	92.70 53	92.79 99	98.68 26	80.53 166	97.53 92	96.51 96	85.22 143	91.94 84	97.98 57	77.26 112	99.67 53	90.83 104	98.37 45	98.18 73

EPP-MVSNet		89.76 125	89.72 121	89.87 203	93.78 181	76.02 279	97.22 113	96.51 96	79.35 273	85.11 167	95.01 171	84.82 33	97.10 209	87.46 148	88.21 191	96.50 173

ZNCC-MVS		92.75 51	92.60 56	93.23 81	98.24 51	81.82 131	97.63 83	96.50 98	85.00 151	91.05 98	97.74 71	78.38 94	99.80 25	90.48 109	98.34 47	98.07 81

test11								96.50 98

EPNet_dtu		87.65 175	87.89 147	86.93 269	94.57 153	71.37 329	96.72 162	96.50 98	88.56 71	87.12 153	95.02 170	75.91 139	94.01 330	66.62 317	90.00 167	95.42 201
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testdata				90.13 194	95.92 113	74.17 298		96.49 101	73.49 333	94.82 48	97.99 54	78.80 90	97.93 156	83.53 186	97.52 70	98.29 68

DVP-MVS		95.58 9	95.91 9	94.57 32	99.05 9	85.18 61	99.06 17	96.46 102	88.75 65	96.69 18	98.76 12	87.69 22	99.76 31	97.90 17	98.85 21	98.77 38
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test222					96.15 104	78.41 221	95.87 213	96.46 102	71.97 344	89.66 116	97.45 87	76.33 132			98.24 50	98.30 67

XVS		92.69 57	92.71 52	92.63 107	98.52 37	80.29 169	97.37 108	96.44 104	87.04 109	91.38 90	97.83 68	77.24 114	99.59 60	90.46 110	98.07 53	98.02 83

X-MVStestdata		86.26 195	84.14 214	92.63 107	98.52 37	80.29 169	97.37 108	96.44 104	87.04 109	91.38 90	20.73 407	77.24 114	99.59 60	90.46 110	98.07 53	98.02 83

SF-MVS		94.17 29	94.05 33	94.55 33	97.56 74	85.95 40	97.73 77	96.43 106	84.02 178	95.07 42	98.74 14	82.93 52	99.38 78	95.42 51	98.51 35	98.32 64

TSAR-MVS + MP.		94.79 20	95.17 18	93.64 63	97.66 69	84.10 86	95.85 215	96.42 107	91.26 35	97.49 13	96.80 120	86.50 27	98.49 132	95.54 49	99.03 13	98.33 63
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
APDe-MVS		94.56 23	94.75 20	93.96 50	98.84 22	83.40 100	98.04 58	96.41 108	85.79 131	95.00 43	98.28 36	84.32 41	99.18 94	97.35 26	98.77 27	99.28 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
UniMVSNet_NR-MVSNet		85.49 208	84.59 203	88.21 237	89.44 297	79.36 195	96.71 164	96.41 108	85.22 143	78.11 250	90.98 244	76.97 119	95.14 302	79.14 222	68.30 334	90.12 266

test_prior				93.09 87	98.68 26	81.91 126		96.40 110					99.06 104			98.29 68

CP-MVS		92.54 62	92.60 56	92.34 117	98.50 40	79.90 180	98.40 39	96.40 110	84.75 155	90.48 107	98.09 47	77.40 111	99.21 88	91.15 99	98.23 51	97.92 94

CANet		94.89 16	94.64 22	95.63 13	97.55 75	88.12 17	99.06 17	96.39 112	94.07 12	95.34 35	97.80 69	76.83 122	99.87 8	97.08 30	97.64 67	98.89 34

GST-MVS		92.43 65	92.22 65	93.04 89	98.17 54	81.64 138	97.40 106	96.38 113	84.71 158	90.90 101	97.40 92	77.55 109	99.76 31	89.75 122	97.74 64	97.72 109

alignmvs		92.97 47	92.26 63	95.12 20	95.54 125	87.77 21	98.67 30	96.38 113	88.04 83	93.01 69	97.45 87	79.20 83	98.60 125	93.25 77	88.76 180	98.99 33

PAPM		92.87 50	92.40 59	94.30 37	92.25 231	87.85 20	96.40 184	96.38 113	91.07 38	88.72 134	96.90 113	82.11 57	97.37 193	90.05 119	97.70 65	97.67 113

test_fmvsmconf_n		93.99 33	94.36 28	92.86 96	92.82 213	81.12 146	99.26 4	96.37 116	93.47 15	95.16 36	98.21 38	79.00 85	99.64 55	98.21 10	96.73 93	97.83 101

test12				94.25 40	98.34 46	85.55 52		96.35 117		92.36 76		80.84 63	99.22 87		98.31 48	97.98 90

MTGPA								96.33 118

MTAPA		92.45 64	92.31 61	92.86 96	97.90 61	80.85 155	92.88 302	96.33 118	87.92 86	90.20 110	98.18 40	76.71 125	99.76 31	92.57 87	98.09 52	97.96 93

ET-MVSNet_ETH3D		90.01 121	89.03 127	92.95 92	94.38 164	86.77 31	98.14 47	96.31 120	89.30 61	63.33 358	96.72 124	90.09 11	93.63 337	90.70 107	82.29 245	98.46 57

EPMVS		87.47 178	85.90 184	92.18 128	95.41 128	82.26 120	87.00 353	96.28 121	85.88 130	84.23 179	85.57 322	75.07 161	96.26 244	71.14 295	92.50 150	98.03 82

WB-MVSnew		84.08 231	83.51 224	85.80 285	91.34 258	76.69 267	95.62 225	96.27 122	81.77 228	81.81 214	92.81 214	58.23 290	94.70 316	66.66 316	87.06 200	85.99 351

CDPH-MVS		93.12 43	92.91 49	93.74 57	98.65 30	83.88 88	97.67 82	96.26 123	83.00 204	93.22 66	98.24 37	81.31 61	99.21 88	89.12 129	98.74 30	98.14 77

WR-MVS		84.32 227	82.96 231	88.41 229	89.38 298	80.32 168	96.59 169	96.25 124	83.97 180	76.63 265	90.36 253	67.53 228	94.86 312	75.82 258	70.09 318	90.06 271

fmvsm_s_conf0.1_n		92.93 48	93.16 47	92.24 124	90.52 275	81.92 125	98.42 38	96.24 125	91.17 36	96.02 30	98.35 33	75.34 156	99.74 38	97.84 20	94.58 122	95.05 209

UGNet		87.73 173	86.55 178	91.27 161	95.16 137	79.11 203	96.35 187	96.23 126	88.14 81	87.83 145	90.48 250	50.65 333	99.09 102	80.13 212	94.03 127	95.60 195
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
tfpnnormal		78.14 303	75.42 310	86.31 279	88.33 309	79.24 198	94.41 263	96.22 127	73.51 331	69.81 330	85.52 324	55.43 316	95.75 270	47.65 384	67.86 339	83.95 367

FOURS1					98.51 39	78.01 235	98.13 50	96.21 128	83.04 202	94.39 52

MP-MVS		92.61 60	92.67 54	92.42 115	98.13 56	79.73 187	97.33 110	96.20 129	85.63 133	90.53 105	97.66 74	78.14 99	99.70 48	92.12 90	98.30 49	97.85 99
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PAPR		92.74 52	92.17 66	94.45 34	98.89 20	84.87 74	97.20 116	96.20 129	87.73 91	88.40 138	98.12 45	78.71 91	99.76 31	87.99 142	96.28 98	98.74 39

SD-MVS		94.84 18	95.02 19	94.29 38	97.87 64	84.61 78	97.76 75	96.19 131	89.59 58	96.66 20	98.17 43	84.33 38	99.60 59	96.09 39	98.50 37	98.66 46
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
CHOSEN 280x420		91.71 83	91.85 71	91.29 160	94.94 144	82.69 110	87.89 346	96.17 132	85.94 128	87.27 150	94.31 185	90.27 9	95.65 277	94.04 65	95.86 108	95.53 198

fmvsm_l_conf0.5_n		94.89 16	95.24 16	93.86 52	94.42 163	84.61 78	99.13 11	96.15 133	92.06 27	97.92 3	98.52 23	84.52 36	99.74 38	98.76 5	95.67 111	97.22 144

CHOSEN 1792x2688		91.07 100	90.21 108	93.64 63	95.18 136	83.53 97	96.26 192	96.13 134	88.92 64	84.90 171	93.10 212	72.86 188	99.62 58	88.86 131	95.67 111	97.79 105

PAPM_NR		91.46 88	90.82 92	93.37 77	98.50 40	81.81 132	95.03 252	96.13 134	84.65 160	86.10 161	97.65 78	79.24 82	99.75 36	83.20 189	96.88 87	98.56 51

CostFormer		89.08 136	88.39 140	91.15 166	93.13 203	79.15 202	88.61 340	96.11 136	83.14 199	89.58 118	86.93 300	83.83 47	96.87 221	88.22 141	85.92 213	97.42 132

mPP-MVS		91.88 78	91.82 72	92.07 133	98.38 44	78.63 215	97.29 112	96.09 137	85.12 147	88.45 137	97.66 74	75.53 146	99.68 51	89.83 120	98.02 56	97.88 95

APD-MVS		93.61 37	93.59 38	93.69 61	98.76 24	83.26 103	97.21 114	96.09 137	82.41 218	94.65 49	98.21 38	81.96 59	98.81 119	94.65 58	98.36 46	99.01 30
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MDTV_nov1_ep13			83.69 217		94.09 175	81.01 149	86.78 355	96.09 137	83.81 187	84.75 174	84.32 339	74.44 171	96.54 234	63.88 331	85.07 222

FA-MVS(test-final)		87.71 174	86.23 181	92.17 129	94.19 169	80.55 163	87.16 352	96.07 140	82.12 223	85.98 162	88.35 278	72.04 201	98.49 132	80.26 209	89.87 168	97.48 130

QAPM		86.88 184	84.51 205	93.98 48	94.04 177	85.89 43	97.19 117	96.05 141	73.62 330	75.12 290	95.62 146	62.02 264	99.74 38	70.88 296	96.06 104	96.30 182

MP-MVS-pluss		92.58 61	92.35 60	93.29 78	97.30 86	82.53 113	96.44 180	96.04 142	84.68 159	89.12 125	98.37 31	77.48 110	99.74 38	93.31 76	98.38 44	97.59 120
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.1_n_a		92.38 66	92.49 58	92.06 134	88.08 311	81.62 139	97.97 62	96.01 143	90.62 43	96.58 22	98.33 34	74.09 175	99.71 45	97.23 27	93.46 139	94.86 213

fmvsm_l_conf0.5_n_a		94.91 15	95.30 15	93.72 60	94.50 161	84.30 83	99.14 10	96.00 144	91.94 30	97.91 5	98.60 18	84.78 34	99.77 29	98.84 4	96.03 105	97.08 152

tpm2		87.35 179	86.26 180	90.62 181	92.93 211	78.67 214	88.06 345	95.99 145	79.33 274	87.40 147	86.43 311	80.28 70	96.40 238	80.23 210	85.73 217	96.79 163

SDMVSNet		87.02 181	85.61 186	91.24 162	94.14 172	83.30 102	93.88 279	95.98 146	84.30 171	79.63 237	92.01 223	58.23 290	97.68 169	90.28 118	82.02 246	92.75 243

DeepC-MVS	86.58 3	91.53 87	91.06 89	92.94 93	94.52 157	81.89 127	95.95 207	95.98 146	90.76 41	83.76 188	96.76 121	73.24 186	99.71 45	91.67 96	96.96 84	97.22 144
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test-LLR		88.48 154	87.98 146	89.98 198	92.26 229	77.23 257	97.11 129	95.96 148	83.76 189	86.30 159	91.38 235	72.30 197	96.78 227	80.82 203	91.92 157	95.94 187

test-mter		88.95 138	88.60 136	89.98 198	92.26 229	77.23 257	97.11 129	95.96 148	85.32 140	86.30 159	91.38 235	76.37 131	96.78 227	80.82 203	91.92 157	95.94 187

DP-MVS Recon		91.72 82	90.85 91	94.34 36	99.50 1	85.00 71	98.51 36	95.96 148	80.57 246	88.08 143	97.63 80	76.84 120	99.89 7	85.67 160	94.88 117	98.13 78

cdsmvs_eth3d_5k		21.43 374	28.57 377	0.00 393	0.00 416	0.00 418	0.00 404	95.93 151	0.00 411	0.00 412	97.66 74	63.57 254	0.00 412	0.00 411	0.00 410	0.00 408

hse-mvs2		88.22 164	88.21 142	88.25 235	93.54 188	73.41 301	95.41 233	95.89 152	90.39 48	92.22 79	94.22 188	74.70 165	96.66 232	93.14 78	64.37 357	94.69 221

AUN-MVS		86.25 196	85.57 187	88.26 234	93.57 187	73.38 302	95.45 231	95.88 153	83.94 182	85.47 165	94.21 189	73.70 182	96.67 231	83.54 185	64.41 356	94.73 220

TAMVS		88.48 154	87.79 150	90.56 183	91.09 263	79.18 200	96.45 179	95.88 153	83.64 192	83.12 194	93.33 207	75.94 138	95.74 273	82.40 195	88.27 190	96.75 167

PVSNet_Blended_VisFu		91.24 94	90.77 93	92.66 104	95.09 138	82.40 117	97.77 73	95.87 155	88.26 78	86.39 157	93.94 196	76.77 123	99.27 84	88.80 133	94.00 130	96.31 181

OpenMVS	79.58 14	86.09 197	83.62 221	93.50 72	90.95 265	86.71 33	97.44 100	95.83 156	75.35 316	72.64 311	95.72 141	57.42 303	99.64 55	71.41 290	95.85 109	94.13 227

CDS-MVSNet		89.50 129	88.96 130	91.14 167	91.94 248	80.93 153	97.09 133	95.81 157	84.26 174	84.72 175	94.20 190	80.31 69	95.64 278	83.37 188	88.96 178	96.85 162
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PS-MVSNAJ		94.17 29	93.52 40	96.10 9	95.65 123	92.35 2	98.21 45	95.79 158	92.42 23	96.24 27	98.18 40	71.04 211	99.17 95	96.77 33	97.39 76	96.79 163

testing3		80.74 283	81.17 259	79.44 348	91.15 262	63.48 366	97.16 123	95.76 159	80.83 239	71.36 318	93.15 211	78.22 97	87.30 382	43.19 389	79.67 260	87.55 330

SR-MVS		92.16 69	92.27 62	91.83 145	98.37 45	78.41 221	96.67 167	95.76 159	82.19 222	91.97 82	98.07 51	76.44 128	98.64 123	93.71 68	97.27 79	98.45 58

3Dnovator+	82.88 8	89.63 128	87.85 148	94.99 22	94.49 162	86.76 32	97.84 68	95.74 161	86.10 124	75.47 287	96.02 135	65.00 247	99.51 71	82.91 193	97.07 83	98.72 44

HPM-MVS		91.62 85	91.53 78	91.89 141	97.88 63	79.22 199	96.99 138	95.73 162	82.07 224	89.50 121	97.19 103	75.59 144	98.93 114	90.91 102	97.94 59	97.54 122
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ab-mvs		87.08 180	84.94 200	93.48 74	93.34 197	83.67 94	88.82 337	95.70 163	81.18 234	84.55 178	90.14 258	62.72 258	98.94 113	85.49 162	82.54 242	97.85 99

xiu_mvs_v2_base		93.92 34	93.26 44	95.91 10	95.07 140	92.02 6	98.19 46	95.68 164	92.06 27	96.01 31	98.14 44	70.83 214	98.96 109	96.74 35	96.57 95	96.76 166

CP-MVSNet		81.01 280	80.08 274	83.79 318	87.91 314	70.51 332	94.29 271	95.65 165	80.83 239	72.54 313	88.84 270	63.71 253	92.32 348	68.58 309	68.36 333	88.55 304

PatchmatchNet		86.83 186	85.12 197	91.95 139	94.12 174	82.27 119	86.55 357	95.64 166	84.59 162	82.98 197	84.99 334	77.26 112	95.96 258	68.61 308	91.34 162	97.64 116
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
API-MVS		90.18 118	88.97 129	93.80 54	98.66 28	82.95 108	97.50 96	95.63 167	75.16 319	86.31 158	97.69 72	72.49 193	99.90 5	81.26 202	96.07 103	98.56 51

AdaColmap		88.81 144	87.61 156	92.39 116	99.33 4	79.95 178	96.70 166	95.58 168	77.51 299	83.05 196	96.69 125	61.90 267	99.72 43	84.29 170	93.47 138	97.50 128

SCA		85.63 205	83.64 220	91.60 153	92.30 227	81.86 129	92.88 302	95.56 169	84.85 153	82.52 198	85.12 332	58.04 293	95.39 288	73.89 275	87.58 198	97.54 122

dp		84.30 228	82.31 242	90.28 190	94.24 168	77.97 236	86.57 356	95.53 170	79.94 264	80.75 223	85.16 330	71.49 207	96.39 239	63.73 332	83.36 231	96.48 174

HyFIR lowres test		89.36 131	88.60 136	91.63 152	94.91 146	80.76 158	95.60 226	95.53 170	82.56 215	84.03 181	91.24 239	78.03 100	96.81 225	87.07 152	88.41 188	97.32 138

APD-MVS_3200maxsize		91.23 95	91.35 80	90.89 174	97.89 62	76.35 272	96.30 190	95.52 172	79.82 265	91.03 99	97.88 65	74.70 165	98.54 129	92.11 91	96.89 86	97.77 106

lupinMVS		93.87 35	93.58 39	94.75 28	93.00 206	88.08 18	99.15 8	95.50 173	91.03 39	94.90 44	97.66 74	78.84 88	97.56 176	94.64 59	97.46 71	98.62 49

tt0805		81.20 278	79.06 286	87.61 249	86.50 326	72.97 310	93.66 282	95.48 174	74.11 326	76.23 274	91.99 225	41.36 369	97.40 190	77.44 240	74.78 290	92.45 246

HPM-MVS_fast		90.38 116	90.17 110	91.03 169	97.61 70	77.35 255	97.15 125	95.48 174	79.51 271	88.79 131	96.90 113	71.64 205	98.81 119	87.01 153	97.44 73	96.94 156

VPNet		84.69 220	82.92 232	90.01 196	89.01 300	83.45 99	96.71 164	95.46 176	85.71 132	79.65 236	92.18 222	56.66 309	96.01 254	83.05 192	67.84 340	90.56 257

114514_t		88.79 146	87.57 157	92.45 112	98.21 53	81.74 134	96.99 138	95.45 177	75.16 319	82.48 199	95.69 143	68.59 224	98.50 131	80.33 207	95.18 115	97.10 151

SR-MVS-dyc-post		91.29 93	91.45 79	90.80 176	97.76 67	76.03 277	96.20 197	95.44 178	80.56 247	90.72 103	97.84 66	75.76 141	98.61 124	91.99 92	96.79 90	97.75 107

RE-MVS-def			91.18 87		97.76 67	76.03 277	96.20 197	95.44 178	80.56 247	90.72 103	97.84 66	73.36 185		91.99 92	96.79 90	97.75 107

JIA-IIPM		79.00 299	77.20 298	84.40 313	89.74 291	64.06 363	75.30 390	95.44 178	62.15 372	81.90 211	59.08 394	78.92 86	95.59 282	66.51 320	85.78 216	93.54 237

RPMNet		79.85 289	75.92 308	91.64 150	90.16 282	79.75 184	79.02 382	95.44 178	58.43 388	82.27 207	72.55 385	73.03 187	98.41 140	46.10 386	86.25 208	96.75 167

DU-MVS		84.57 223	83.33 227	88.28 233	88.76 301	79.36 195	96.43 182	95.41 182	85.42 138	78.11 250	90.82 245	67.61 225	95.14 302	79.14 222	68.30 334	90.33 262

EI-MVSNet		85.80 202	85.20 193	87.59 251	91.55 253	77.41 253	95.13 246	95.36 183	80.43 252	80.33 229	94.71 178	73.72 180	95.97 255	76.96 245	78.64 270	89.39 278

MVSTER		89.25 135	88.92 132	90.24 191	95.98 110	84.66 77	96.79 158	95.36 183	87.19 107	80.33 229	90.61 249	90.02 12	95.97 255	85.38 163	78.64 270	90.09 269

CPTT-MVS		89.72 126	89.87 119	89.29 213	98.33 47	73.30 304	97.70 79	95.35 185	75.68 315	87.40 147	97.44 90	70.43 216	98.25 146	89.56 125	96.90 85	96.33 180

EIA-MVS		91.73 80	92.05 69	90.78 178	94.52 157	76.40 271	98.06 56	95.34 186	89.19 62	88.90 129	97.28 99	77.56 108	97.73 168	90.77 105	96.86 89	98.20 72

tpmvs		83.04 250	80.77 263	89.84 204	95.43 127	77.96 237	85.59 363	95.32 187	75.31 318	76.27 273	83.70 344	73.89 177	97.41 189	59.53 346	81.93 248	94.14 226

PS-CasMVS		80.27 287	79.18 283	83.52 324	87.56 318	69.88 337	94.08 274	95.29 188	80.27 257	72.08 315	88.51 277	59.22 284	92.23 350	67.49 311	68.15 336	88.45 310

TSAR-MVS + GP.		94.35 25	94.50 23	93.89 51	97.38 84	83.04 107	98.10 52	95.29 188	91.57 32	93.81 58	97.45 87	86.64 26	99.43 76	96.28 38	94.01 129	99.20 24

tpmrst		88.36 158	87.38 163	91.31 158	94.36 165	79.92 179	87.32 350	95.26 190	85.32 140	88.34 139	86.13 316	80.60 67	96.70 229	83.78 177	85.34 221	97.30 141

ETV-MVS		92.72 55	92.87 50	92.28 123	94.54 156	81.89 127	97.98 60	95.21 191	89.77 57	93.11 67	96.83 117	77.23 116	97.50 184	95.74 45	95.38 114	97.44 131

NR-MVSNet		83.35 242	81.52 255	88.84 221	88.76 301	81.31 144	94.45 262	95.16 192	84.65 160	67.81 336	90.82 245	70.36 217	94.87 311	74.75 266	66.89 349	90.33 262

test_fmvsmconf0.1_n		93.08 45	93.22 46	92.65 105	88.45 307	80.81 156	99.00 22	95.11 193	93.21 17	94.00 57	97.91 62	76.84 120	99.59 60	97.91 16	96.55 96	97.54 122

jason		92.73 53	92.23 64	94.21 43	90.50 276	87.30 27	98.65 31	95.09 194	90.61 44	92.76 74	97.13 105	75.28 157	97.30 196	93.32 75	96.75 92	98.02 83
jason: jason.
tpm cat1		83.63 239	81.38 256	90.39 187	93.53 193	78.19 232	85.56 364	95.09 194	70.78 350	78.51 246	83.28 347	74.80 164	97.03 210	66.77 315	84.05 226	95.95 186

cascas		86.50 190	84.48 207	92.55 110	92.64 219	85.95 40	97.04 137	95.07 196	75.32 317	80.50 225	91.02 242	54.33 324	97.98 155	86.79 155	87.62 196	93.71 235

CVMVSNet		84.83 218	85.57 187	82.63 331	91.55 253	60.38 376	95.13 246	95.03 197	80.60 245	82.10 209	94.71 178	66.40 238	90.19 370	74.30 272	90.32 166	97.31 140

test0.0.03 1		82.79 254	82.48 240	83.74 320	86.81 324	72.22 313	96.52 173	95.03 197	83.76 189	73.00 307	93.20 208	72.30 197	88.88 373	64.15 330	77.52 279	90.12 266

PMMVS		89.46 130	89.92 117	88.06 239	94.64 151	69.57 341	96.22 194	94.95 199	87.27 103	91.37 92	96.54 127	65.88 239	97.39 191	88.54 135	93.89 131	97.23 143

CS-MVS		92.73 53	93.48 41	90.48 185	96.27 100	75.93 282	98.55 35	94.93 200	89.32 60	94.54 51	97.67 73	78.91 87	97.02 211	93.80 66	97.32 78	98.49 55

Anonymous20240529		83.15 247	80.60 267	90.80 176	95.74 120	78.27 225	96.81 157	94.92 201	60.10 383	81.89 212	92.54 218	45.82 354	98.82 118	79.25 221	78.32 276	95.31 204

mvs_anonymous		88.68 147	87.62 155	91.86 142	94.80 149	81.69 137	93.53 287	94.92 201	82.03 225	78.87 244	90.43 252	75.77 140	95.34 291	85.04 165	93.16 143	98.55 53

CLD-MVS		87.97 169	87.48 160	89.44 211	92.16 236	80.54 165	98.14 47	94.92 201	91.41 33	79.43 239	95.40 152	62.34 260	97.27 199	90.60 108	82.90 237	90.50 259
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
xiu_mvs_v1_base_debu		90.54 111	89.54 122	93.55 69	92.31 224	87.58 24	96.99 138	94.87 204	87.23 104	93.27 63	97.56 83	57.43 300	98.32 142	92.72 84	93.46 139	94.74 217

xiu_mvs_v1_base		90.54 111	89.54 122	93.55 69	92.31 224	87.58 24	96.99 138	94.87 204	87.23 104	93.27 63	97.56 83	57.43 300	98.32 142	92.72 84	93.46 139	94.74 217

xiu_mvs_v1_base_debi		90.54 111	89.54 122	93.55 69	92.31 224	87.58 24	96.99 138	94.87 204	87.23 104	93.27 63	97.56 83	57.43 300	98.32 142	92.72 84	93.46 139	94.74 217

GA-MVS		85.79 203	84.04 215	91.02 170	89.47 296	80.27 171	96.90 151	94.84 207	85.57 134	80.88 221	89.08 266	56.56 310	96.47 237	77.72 233	85.35 220	96.34 178

TranMVSNet+NR-MVSNet		83.24 246	81.71 251	87.83 243	87.71 316	78.81 211	96.13 202	94.82 208	84.52 163	76.18 276	90.78 247	64.07 252	94.60 319	74.60 270	66.59 351	90.09 269

HQP3-MVS								94.80 209							83.01 234

HQP-MVS		87.91 171	87.55 158	88.98 219	92.08 240	78.48 217	97.63 83	94.80 209	90.52 45	82.30 203	94.56 181	65.40 243	97.32 194	87.67 146	83.01 234	91.13 251

TAPA-MVS	81.61 12	85.02 215	83.67 218	89.06 216	96.79 92	73.27 307	95.92 209	94.79 211	74.81 322	80.47 226	96.83 117	71.07 210	98.19 150	49.82 379	92.57 148	95.71 193
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PEN-MVS		79.47 295	78.26 291	83.08 327	86.36 328	68.58 345	93.85 280	94.77 212	79.76 266	71.37 317	88.55 274	59.79 276	92.46 346	64.50 328	65.40 353	88.19 315

CS-MVS-test		92.98 46	93.67 36	90.90 173	96.52 94	76.87 262	98.68 29	94.73 213	90.36 50	94.84 46	97.89 64	77.94 101	97.15 207	94.28 63	97.80 63	98.70 45

HQP_MVS		87.50 177	87.09 170	88.74 224	91.86 249	77.96 237	97.18 119	94.69 214	89.89 55	81.33 217	94.15 191	64.77 249	97.30 196	87.08 150	82.82 238	90.96 253

plane_prior5								94.69 214					97.30 196	87.08 150	82.82 238	90.96 253

tpm		85.55 207	84.47 208	88.80 223	90.19 281	75.39 287	88.79 338	94.69 214	84.83 154	83.96 184	85.21 328	78.22 97	94.68 318	76.32 253	78.02 278	96.34 178

FMVSNet3		84.71 219	82.71 237	90.70 180	94.55 155	87.71 22	95.92 209	94.67 217	81.73 229	75.82 282	88.08 283	66.99 233	94.47 322	71.23 292	75.38 287	89.91 273

UA-Net		88.92 140	88.48 139	90.24 191	94.06 176	77.18 259	93.04 299	94.66 218	87.39 100	91.09 97	93.89 197	74.92 162	98.18 151	75.83 257	91.43 161	95.35 203

LFMVS		89.27 134	87.64 153	94.16 46	97.16 88	85.52 53	97.18 119	94.66 218	79.17 279	89.63 117	96.57 126	55.35 317	98.22 148	89.52 126	89.54 170	98.74 39

MVS_Test		90.29 117	89.18 126	93.62 65	95.23 133	84.93 72	94.41 263	94.66 218	84.31 169	90.37 109	91.02 242	75.13 159	97.82 165	83.11 191	94.42 124	98.12 79

sasdasda		92.27 67	91.22 83	95.41 16	95.80 118	88.31 14	97.09 133	94.64 221	88.49 72	92.99 70	97.31 94	72.68 190	98.57 127	93.38 73	88.58 183	99.36 16

canonicalmvs		92.27 67	91.22 83	95.41 16	95.80 118	88.31 14	97.09 133	94.64 221	88.49 72	92.99 70	97.31 94	72.68 190	98.57 127	93.38 73	88.58 183	99.36 16

VDDNet		86.44 191	84.51 205	92.22 126	91.56 252	81.83 130	97.10 132	94.64 221	69.50 356	87.84 144	95.19 162	48.01 343	97.92 161	89.82 121	86.92 201	96.89 160

baseline1		88.85 143	87.49 159	92.93 94	95.21 135	86.85 30	95.47 230	94.61 224	87.29 102	83.11 195	94.99 172	80.70 66	96.89 219	82.28 196	73.72 294	95.05 209

PatchT		79.75 290	76.85 302	88.42 228	89.55 294	75.49 286	77.37 386	94.61 224	63.07 369	82.46 200	73.32 382	75.52 147	93.41 341	51.36 373	84.43 224	96.36 176

MS-PatchMatch		83.05 249	81.82 250	86.72 274	89.64 292	79.10 204	94.88 255	94.59 226	79.70 268	70.67 324	89.65 262	50.43 335	96.82 224	70.82 299	95.99 107	84.25 364

casdiffmvs_mvg		91.13 97	90.45 101	93.17 84	92.99 209	83.58 96	97.46 99	94.56 227	87.69 92	87.19 152	94.98 173	74.50 170	97.60 173	91.88 95	92.79 146	98.34 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
baseline		90.76 107	90.10 111	92.74 101	92.90 212	82.56 112	94.60 260	94.56 227	87.69 92	89.06 127	95.67 144	73.76 179	97.51 183	90.43 113	92.23 155	98.16 75

OMC-MVS		88.80 145	88.16 144	90.72 179	95.30 131	77.92 240	94.81 257	94.51 229	86.80 115	84.97 170	96.85 116	67.53 228	98.60 125	85.08 164	87.62 196	95.63 194

MGCFI-Net		91.95 73	91.03 90	94.72 29	95.68 122	86.38 34	96.93 148	94.48 230	88.25 79	92.78 73	97.24 100	72.34 195	98.46 135	93.13 80	88.43 187	99.32 19

MVSFormer		91.36 91	90.57 97	93.73 59	93.00 206	88.08 18	94.80 258	94.48 230	80.74 242	94.90 44	97.13 105	78.84 88	95.10 305	83.77 178	97.46 71	98.02 83

test_djsdf		83.00 252	82.45 241	84.64 307	84.07 358	69.78 338	94.80 258	94.48 230	80.74 242	75.41 288	87.70 287	61.32 271	95.10 305	83.77 178	79.76 257	89.04 293

casdiffmvs		90.95 104	90.39 102	92.63 107	92.82 213	82.53 113	96.83 154	94.47 233	87.69 92	88.47 136	95.56 149	74.04 176	97.54 180	90.90 103	92.74 147	97.83 101
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PCF-MVS	84.09 5	86.77 188	85.00 199	92.08 132	92.06 243	83.07 106	92.14 310	94.47 233	79.63 269	76.90 262	94.78 177	71.15 209	99.20 92	72.87 281	91.05 163	93.98 230
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VDD-MVS		88.28 162	87.02 172	92.06 134	95.09 138	80.18 175	97.55 91	94.45 235	83.09 200	89.10 126	95.92 138	47.97 344	98.49 132	93.08 82	86.91 202	97.52 127

test_cas_vis1_n_1920		89.90 123	90.02 113	89.54 210	90.14 284	74.63 293	98.71 28	94.43 236	93.04 19	92.40 75	96.35 129	53.41 326	99.08 103	95.59 48	96.16 100	94.90 211

PLC	83.97 7	88.00 168	87.38 163	89.83 205	98.02 59	76.46 269	97.16 123	94.43 236	79.26 278	81.98 210	96.28 130	69.36 221	99.27 84	77.71 234	92.25 154	93.77 234
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EC-MVSNet		91.73 80	92.11 67	90.58 182	93.54 188	77.77 246	98.07 55	94.40 238	87.44 98	92.99 70	97.11 107	74.59 169	96.87 221	93.75 67	97.08 82	97.11 150

sd_testset		84.62 221	83.11 230	89.17 214	94.14 172	77.78 245	91.54 320	94.38 239	84.30 171	79.63 237	92.01 223	52.28 328	96.98 213	77.67 235	82.02 246	92.75 243

FMVSNet2		82.79 254	80.44 269	89.83 205	92.66 216	85.43 55	95.42 232	94.35 240	79.06 282	74.46 294	87.28 292	56.38 312	94.31 325	69.72 304	74.68 291	89.76 275

test_vis1_n_1920		89.95 122	90.59 96	88.03 241	92.36 223	68.98 344	99.12 12	94.34 241	93.86 13	93.64 61	97.01 111	51.54 330	99.59 60	96.76 34	96.71 94	95.53 198

nrg030		86.79 187	85.43 189	90.87 175	88.76 301	85.34 56	97.06 136	94.33 242	84.31 169	80.45 227	91.98 226	72.36 194	96.36 241	88.48 138	71.13 307	90.93 255

RRT_MVS		83.88 234	83.27 228	85.71 288	87.53 320	72.12 317	95.35 235	94.33 242	83.81 187	75.86 281	91.28 238	60.55 273	95.09 307	83.93 174	76.76 281	89.90 274

ACMM	80.70 13	83.72 238	82.85 235	86.31 279	91.19 260	72.12 317	95.88 212	94.29 244	80.44 250	77.02 260	91.96 227	55.24 318	97.14 208	79.30 220	80.38 255	89.67 276
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XXY-MVS		83.84 235	82.00 247	89.35 212	87.13 322	81.38 142	95.72 219	94.26 245	80.15 259	75.92 280	90.63 248	61.96 266	96.52 235	78.98 224	73.28 299	90.14 265

Syy-MVS		77.97 306	78.05 292	77.74 355	92.13 237	56.85 382	93.97 276	94.23 246	82.43 216	73.39 300	93.57 204	57.95 296	87.86 377	32.40 395	82.34 243	88.51 305

myMVS_eth3d		81.93 267	82.18 243	81.18 339	92.13 237	67.18 351	93.97 276	94.23 246	82.43 216	73.39 300	93.57 204	76.98 118	87.86 377	50.53 377	82.34 243	88.51 305

cl22		85.11 214	84.17 212	87.92 242	95.06 142	78.82 209	95.51 228	94.22 248	79.74 267	76.77 263	87.92 285	75.96 137	95.68 274	79.93 214	72.42 301	89.27 285

OPM-MVS		85.84 201	85.10 198	88.06 239	88.34 308	77.83 244	95.72 219	94.20 249	87.89 88	80.45 227	94.05 193	58.57 287	97.26 200	83.88 175	82.76 240	89.09 290
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet (Re-imp)		88.88 142	88.87 134	88.91 220	93.89 180	74.43 296	96.93 148	94.19 250	84.39 167	83.22 193	95.67 144	78.24 96	94.70 316	78.88 225	94.40 125	97.61 119

Anonymous20231211		79.72 291	77.19 299	87.33 259	95.59 124	77.16 260	95.18 245	94.18 251	59.31 386	72.57 312	86.20 315	47.89 346	95.66 275	74.53 271	69.24 326	89.18 287

PS-MVSNAJss		84.91 217	84.30 210	86.74 270	85.89 338	74.40 297	94.95 253	94.16 252	83.93 183	76.45 268	90.11 259	71.04 211	95.77 268	83.16 190	79.02 267	90.06 271

LPG-MVS_test		84.20 229	83.49 225	86.33 276	90.88 266	73.06 308	95.28 236	94.13 253	82.20 220	76.31 270	93.20 208	54.83 322	96.95 215	83.72 180	80.83 252	88.98 296

LGP-MVS_train				86.33 276	90.88 266	73.06 308		94.13 253	82.20 220	76.31 270	93.20 208	54.83 322	96.95 215	83.72 180	80.83 252	88.98 296

V42		83.04 250	81.53 254	87.57 253	86.27 331	79.09 205	95.87 213	94.11 255	80.35 254	77.22 258	86.79 303	65.32 245	96.02 253	77.74 232	70.14 314	87.61 326

XVG-OURS-SEG-HR		85.74 204	85.16 196	87.49 257	90.22 280	71.45 328	91.29 321	94.09 256	81.37 232	83.90 186	95.22 159	60.30 275	97.53 182	85.58 161	84.42 225	93.50 238

XVG-OURS		85.18 212	84.38 209	87.59 251	90.42 278	71.73 325	91.06 324	94.07 257	82.00 226	83.29 192	95.08 169	56.42 311	97.55 178	83.70 182	83.42 230	93.49 239

miper_enhance_ethall		85.95 200	85.20 193	88.19 238	94.85 148	79.76 183	96.00 204	94.06 258	82.98 205	77.74 253	88.76 271	79.42 78	95.46 287	80.58 205	72.42 301	89.36 283

v2v482		83.46 241	81.86 249	88.25 235	86.19 332	79.65 189	96.34 188	94.02 259	81.56 231	77.32 256	88.23 280	65.62 240	96.03 251	77.77 231	69.72 322	89.09 290

jajsoiax		82.12 265	81.15 260	85.03 301	84.19 356	70.70 331	94.22 272	93.95 260	83.07 201	73.48 299	89.75 261	49.66 339	95.37 290	82.24 197	79.76 257	89.02 294

test_fmvsmconf0.01_n		91.08 99	90.68 95	92.29 122	82.43 366	80.12 176	97.94 63	93.93 261	92.07 26	91.97 82	97.60 81	67.56 227	99.53 68	97.09 29	95.56 113	97.21 146

v1144		82.90 253	81.27 258	87.78 245	86.29 330	79.07 206	96.14 200	93.93 261	80.05 261	77.38 254	86.80 302	65.50 241	95.93 260	75.21 263	70.13 315	88.33 313

KD-MVS_2432*1600		77.63 309	74.92 314	85.77 286	90.86 269	79.44 192	88.08 343	93.92 263	76.26 311	67.05 340	82.78 349	72.15 199	91.92 353	61.53 339	41.62 396	85.94 352

miper_refine_blended		77.63 309	74.92 314	85.77 286	90.86 269	79.44 192	88.08 343	93.92 263	76.26 311	67.05 340	82.78 349	72.15 199	91.92 353	61.53 339	41.62 396	85.94 352

test_fmvsmvis_n_1920		92.12 70	92.10 68	92.17 129	90.87 268	81.04 148	98.34 41	93.90 265	92.71 20	87.24 151	97.90 63	74.83 163	99.72 43	96.96 31	96.20 99	95.76 192

UnsupCasMVSNet_eth		73.25 333	70.57 338	81.30 337	77.53 380	66.33 356	87.24 351	93.89 266	80.38 253	57.90 379	81.59 354	42.91 364	90.56 367	65.18 326	48.51 387	87.01 337

v7n		79.32 297	77.34 297	85.28 297	84.05 359	72.89 312	93.38 289	93.87 267	75.02 321	70.68 323	84.37 338	59.58 279	95.62 280	67.60 310	67.50 343	87.32 334

dcpmvs_2		93.10 44	93.46 42	92.02 137	97.77 65	79.73 187	94.82 256	93.86 268	86.91 111	91.33 93	96.76 121	85.20 31	98.06 152	96.90 32	97.60 68	98.27 70

Vis-MVSNet		88.67 148	87.82 149	91.24 162	92.68 215	78.82 209	96.95 146	93.85 269	87.55 95	87.07 154	95.13 166	63.43 255	97.21 201	77.58 237	96.15 101	97.70 112
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v148		82.41 262	80.89 261	86.99 268	86.18 333	76.81 264	96.27 191	93.82 270	80.49 249	75.28 289	86.11 317	67.32 231	95.75 270	75.48 261	67.03 348	88.42 311

BH-w/o		88.24 163	87.47 161	90.54 184	95.03 143	78.54 216	97.41 105	93.82 270	84.08 176	78.23 249	94.51 183	69.34 222	97.21 201	80.21 211	94.58 122	95.87 189

TR-MVS		86.30 194	84.93 201	90.42 186	94.63 152	77.58 250	96.57 170	93.82 270	80.30 255	82.42 201	95.16 164	58.74 286	97.55 178	74.88 265	87.82 195	96.13 185

v1192		82.31 263	80.55 268	87.60 250	85.94 336	78.47 220	95.85 215	93.80 273	79.33 274	76.97 261	86.51 306	63.33 256	95.87 263	73.11 280	70.13 315	88.46 309

ACMP	81.66 11	84.00 232	83.22 229	86.33 276	91.53 255	72.95 311	95.91 211	93.79 274	83.70 191	73.79 297	92.22 221	54.31 325	96.89 219	83.98 173	79.74 259	89.16 288
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v144192		82.43 259	80.73 264	87.54 254	85.81 339	78.22 227	95.98 205	93.78 275	79.09 281	77.11 259	86.49 307	64.66 251	95.91 261	74.20 273	69.42 323	88.49 307

mvs_tets		81.74 269	80.71 265	84.84 302	84.22 355	70.29 334	93.91 278	93.78 275	82.77 210	73.37 302	89.46 264	47.36 349	95.31 294	81.99 198	79.55 263	88.92 300

F-COLMAP		84.50 225	83.44 226	87.67 247	95.22 134	72.22 313	95.95 207	93.78 275	75.74 314	76.30 272	95.18 163	59.50 280	98.45 137	72.67 283	86.59 205	92.35 248

UniMVSNet_ETH3D		80.86 282	78.75 288	87.22 264	86.31 329	72.02 319	91.95 311	93.76 278	73.51 331	75.06 291	90.16 257	43.04 363	95.66 275	76.37 252	78.55 273	93.98 230

Fast-Effi-MVS+		87.93 170	86.94 174	90.92 172	94.04 177	79.16 201	98.26 43	93.72 279	81.29 233	83.94 185	92.90 213	69.83 220	96.68 230	76.70 247	91.74 159	96.93 157

v1921920		82.02 266	80.23 272	87.41 258	85.62 340	77.92 240	95.79 218	93.69 280	78.86 285	76.67 264	86.44 309	62.50 259	95.83 265	72.69 282	69.77 321	88.47 308

DTE-MVSNet		78.37 301	77.06 300	82.32 334	85.22 347	67.17 354	93.40 288	93.66 281	78.71 287	70.53 325	88.29 279	59.06 285	92.23 350	61.38 342	63.28 362	87.56 328

v8		81.88 268	80.06 276	87.32 260	86.63 325	79.04 207	94.41 263	93.65 282	78.77 286	73.19 306	85.57 322	66.87 234	95.81 266	73.84 277	67.61 342	87.11 335

diffmvs		91.17 96	90.74 94	92.44 114	93.11 205	82.50 115	96.25 193	93.62 283	87.79 89	90.40 108	95.93 136	73.44 184	97.42 188	93.62 70	92.55 149	97.41 133
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ADS-MVSNet		81.26 276	78.36 289	89.96 200	93.78 181	79.78 182	79.48 378	93.60 284	73.09 336	80.14 231	79.99 363	62.15 262	95.24 297	59.49 347	83.52 228	94.85 214

PatchMatch-RL		85.00 216	83.66 219	89.02 218	95.86 114	74.55 295	92.49 306	93.60 284	79.30 276	79.29 241	91.47 233	58.53 288	98.45 137	70.22 301	92.17 156	94.07 229

anonymousdsp		80.98 281	79.97 277	84.01 315	81.73 368	70.44 333	92.49 306	93.58 286	77.10 306	72.98 308	86.31 313	57.58 299	94.90 310	79.32 219	78.63 272	86.69 340

CL-MVSNet_self_test		75.81 321	74.14 323	80.83 342	78.33 378	67.79 348	94.22 272	93.52 287	77.28 303	69.82 329	81.54 355	61.47 270	89.22 372	57.59 355	53.51 378	85.48 356

miper_ehance_all_eth		84.57 223	83.60 222	87.50 255	92.64 219	78.25 226	95.40 234	93.47 288	79.28 277	76.41 269	87.64 288	76.53 126	95.24 297	78.58 227	72.42 301	89.01 295

v1240		81.70 270	79.83 280	87.30 262	85.50 341	77.70 249	95.48 229	93.44 289	78.46 290	76.53 267	86.44 309	60.85 272	95.84 264	71.59 289	70.17 313	88.35 312

v10		81.43 274	79.53 282	87.11 265	86.38 327	78.87 208	94.31 267	93.43 290	77.88 294	73.24 305	85.26 326	65.44 242	95.75 270	72.14 286	67.71 341	86.72 339

IterMVS-LS		83.93 233	82.80 236	87.31 261	91.46 256	77.39 254	95.66 222	93.43 290	80.44 250	75.51 286	87.26 294	73.72 180	95.16 301	76.99 243	70.72 311	89.39 278
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		82.42 260	80.43 270	88.39 230	92.66 216	81.95 122	94.30 268	93.38 292	79.06 282	75.82 282	85.66 318	56.38 312	93.84 332	71.23 292	75.38 287	89.38 280

test1		82.42 260	80.43 270	88.39 230	92.66 216	81.95 122	94.30 268	93.38 292	79.06 282	75.82 282	85.66 318	56.38 312	93.84 332	71.23 292	75.38 287	89.38 280

FMVSNet1		79.50 294	76.54 304	88.39 230	88.47 306	81.95 122	94.30 268	93.38 292	73.14 335	72.04 316	85.66 318	43.86 357	93.84 332	65.48 324	72.53 300	89.38 280

BH-untuned		86.95 183	85.94 183	89.99 197	94.52 157	77.46 252	96.78 159	93.37 295	81.80 227	76.62 266	93.81 200	66.64 236	97.02 211	76.06 254	93.88 132	95.48 200

Effi-MVS+-dtu		84.61 222	84.90 202	83.72 321	91.96 246	63.14 368	94.95 253	93.34 296	85.57 134	79.79 235	87.12 297	61.99 265	95.61 281	83.55 184	85.83 215	92.41 247

CMPMVS	54.94 21	75.71 323	74.56 318	79.17 350	79.69 374	55.98 384	89.59 331	93.30 297	60.28 381	53.85 385	89.07 267	47.68 348	96.33 242	76.55 248	81.02 250	85.22 357
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
cl____		83.27 244	82.12 244	86.74 270	92.20 232	75.95 281	95.11 248	93.27 298	78.44 291	74.82 292	87.02 299	74.19 173	95.19 299	74.67 268	69.32 324	89.09 290

DIV-MVS_self_test		83.27 244	82.12 244	86.74 270	92.19 233	75.92 283	95.11 248	93.26 299	78.44 291	74.81 293	87.08 298	74.19 173	95.19 299	74.66 269	69.30 325	89.11 289

dmvs_re		84.10 230	82.90 233	87.70 246	91.41 257	73.28 305	90.59 327	93.19 300	85.02 149	77.96 252	93.68 201	57.92 298	96.18 248	75.50 260	80.87 251	93.63 236

miper_lstm_enhance		81.66 272	80.66 266	84.67 306	91.19 260	71.97 321	91.94 312	93.19 300	77.86 295	72.27 314	85.26 326	73.46 183	93.42 340	73.71 278	67.05 347	88.61 303

eth_miper_zixun_eth		83.12 248	82.01 246	86.47 275	91.85 251	74.80 291	94.33 266	93.18 302	79.11 280	75.74 285	87.25 295	72.71 189	95.32 293	76.78 246	67.13 346	89.27 285

pmmvs4		82.54 258	80.79 262	87.79 244	86.11 334	80.49 167	93.55 286	93.18 302	77.29 302	73.35 303	89.40 265	65.26 246	95.05 309	75.32 262	73.61 295	87.83 321

XVG-ACMP-BASELINE		79.38 296	77.90 294	83.81 317	84.98 349	67.14 355	89.03 336	93.18 302	80.26 258	72.87 309	88.15 282	38.55 374	96.26 244	76.05 255	78.05 277	88.02 318

CANet_DTU		90.98 102	90.04 112	93.83 53	94.76 150	86.23 36	96.32 189	93.12 305	93.11 18	93.71 59	96.82 119	63.08 257	99.48 73	84.29 170	95.12 116	95.77 191

IS-MVSNet		88.67 148	88.16 144	90.20 193	93.61 185	76.86 263	96.77 161	93.07 306	84.02 178	83.62 189	95.60 147	74.69 168	96.24 246	78.43 229	93.66 136	97.49 129

c3_l		83.80 236	82.65 238	87.25 263	92.10 239	77.74 248	95.25 239	93.04 307	78.58 288	76.01 277	87.21 296	75.25 158	95.11 304	77.54 238	68.89 328	88.91 301

UnsupCasMVSNet_bld		68.60 350	64.50 354	80.92 341	74.63 389	67.80 347	83.97 370	92.94 308	65.12 367	54.63 384	68.23 390	35.97 379	92.17 352	60.13 345	44.83 391	82.78 371

MVP-Stereo		82.65 257	81.67 252	85.59 293	86.10 335	78.29 224	93.33 291	92.82 309	77.75 296	69.17 334	87.98 284	59.28 283	95.76 269	71.77 287	96.88 87	82.73 372
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Effi-MVS+		90.70 108	89.90 118	93.09 87	93.61 185	83.48 98	95.20 242	92.79 310	83.22 197	91.82 85	95.70 142	71.82 202	97.48 186	91.25 98	93.67 135	98.32 64

EU-MVSNet		76.92 316	76.95 301	76.83 358	84.10 357	54.73 389	91.77 315	92.71 311	72.74 339	69.57 331	88.69 272	58.03 295	87.43 381	64.91 327	70.00 319	88.33 313

pm-mvs1		80.05 288	78.02 293	86.15 281	85.42 342	75.81 284	95.11 248	92.69 312	77.13 304	70.36 326	87.43 290	58.44 289	95.27 296	71.36 291	64.25 358	87.36 333

1112_ss		88.60 151	87.47 161	92.00 138	93.21 198	80.97 151	96.47 177	92.46 313	83.64 192	80.86 222	97.30 97	80.24 71	97.62 172	77.60 236	85.49 218	97.40 135

test_fmvs1		87.79 172	88.52 138	85.62 292	92.98 210	64.31 360	97.88 66	92.42 314	87.95 85	92.24 78	95.82 139	47.94 345	98.44 139	95.31 52	94.09 126	94.09 228

Test_1112_low_res		88.03 167	86.73 175	91.94 140	93.15 201	80.88 154	96.44 180	92.41 315	83.59 194	80.74 224	91.16 240	80.18 72	97.59 174	77.48 239	85.40 219	97.36 137

test_fmvs1_n		86.34 193	86.72 176	85.17 299	87.54 319	63.64 365	96.91 150	92.37 316	87.49 97	91.33 93	95.58 148	40.81 372	98.46 135	95.00 54	93.49 137	93.41 242

BH-RMVSNet		86.84 185	85.28 192	91.49 155	95.35 130	80.26 172	96.95 146	92.21 317	82.86 208	81.77 215	95.46 151	59.34 282	97.64 171	69.79 303	93.81 133	96.57 172

GeoE		86.36 192	85.20 193	89.83 205	93.17 200	76.13 274	97.53 92	92.11 318	79.58 270	80.99 220	94.01 194	66.60 237	96.17 249	73.48 279	89.30 172	97.20 148

LS3D		82.22 264	79.94 278	89.06 216	97.43 79	74.06 300	93.20 297	92.05 319	61.90 373	73.33 304	95.21 160	59.35 281	99.21 88	54.54 366	92.48 151	93.90 232

EG-PatchMatch MVS		74.92 325	72.02 332	83.62 322	83.76 363	73.28 305	93.62 284	92.04 320	68.57 358	58.88 375	83.80 343	31.87 387	95.57 284	56.97 359	78.67 269	82.00 378

IterMVS		80.67 284	79.16 284	85.20 298	89.79 287	76.08 275	92.97 301	91.86 321	80.28 256	71.20 320	85.14 331	57.93 297	91.34 360	72.52 284	70.74 310	88.18 316
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
iter_conf05_11		91.95 73	91.17 88	94.29 38	96.33 97	85.50 54	99.61 1	91.84 322	94.36 10	97.89 6	98.51 24	46.72 350	98.24 147	96.54 36	98.75 28	99.13 27

MIMVSNet		79.18 298	75.99 307	88.72 225	87.37 321	80.66 160	79.96 377	91.82 323	77.38 301	74.33 295	81.87 353	41.78 366	90.74 366	66.36 322	83.10 233	94.76 216

IterMVS-SCA-FT		80.51 286	79.10 285	84.73 304	89.63 293	74.66 292	92.98 300	91.81 324	80.05 261	71.06 322	85.18 329	58.04 293	91.40 359	72.48 285	70.70 312	88.12 317

our_test_3		77.90 307	75.37 311	85.48 295	85.39 343	76.74 265	93.63 283	91.67 325	73.39 334	65.72 349	84.65 337	58.20 292	93.13 343	57.82 353	67.87 338	86.57 342

pmmvs5		81.34 275	79.54 281	86.73 273	85.02 348	76.91 261	96.22 194	91.65 326	77.65 297	73.55 298	88.61 273	55.70 315	94.43 323	74.12 274	73.35 298	88.86 302

ACMH	75.40 17	77.99 304	74.96 312	87.10 266	90.67 273	76.41 270	93.19 298	91.64 327	72.47 342	63.44 357	87.61 289	43.34 360	97.16 204	58.34 351	73.94 293	87.72 322
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis1_n		85.60 206	85.70 185	85.33 296	84.79 350	64.98 358	96.83 154	91.61 328	87.36 101	91.00 100	94.84 176	36.14 378	97.18 203	95.66 46	93.03 144	93.82 233

Fast-Effi-MVS+-dtu		83.33 243	82.60 239	85.50 294	89.55 294	69.38 342	96.09 203	91.38 329	82.30 219	75.96 279	91.41 234	56.71 307	95.58 283	75.13 264	84.90 223	91.54 249

YYNet1		73.53 332	70.43 339	82.85 329	84.52 353	71.73 325	91.69 317	91.37 330	67.63 359	46.79 388	81.21 357	55.04 320	90.43 368	55.93 362	59.70 369	86.38 344

ppachtmachnet_test		77.19 313	74.22 321	86.13 282	85.39 343	78.22 227	93.98 275	91.36 331	71.74 346	67.11 339	84.87 335	56.67 308	93.37 342	52.21 371	64.59 355	86.80 338

Anonymous202405211		84.41 226	81.93 248	91.85 144	96.78 93	78.41 221	97.44 100	91.34 332	70.29 352	84.06 180	94.26 187	41.09 370	98.96 109	79.46 217	82.65 241	98.17 74

MDA-MVSNet_test_wron		73.54 331	70.43 339	82.86 328	84.55 351	71.85 322	91.74 316	91.32 333	67.63 359	46.73 389	81.09 358	55.11 319	90.42 369	55.91 363	59.76 368	86.31 345

CR-MVSNet		83.53 240	81.36 257	90.06 195	90.16 282	79.75 184	79.02 382	91.12 334	84.24 175	82.27 207	80.35 361	75.45 148	93.67 336	63.37 335	86.25 208	96.75 167

Patchmtry		77.36 312	74.59 317	85.67 290	89.75 289	75.75 285	77.85 385	91.12 334	60.28 381	71.23 319	80.35 361	75.45 148	93.56 338	57.94 352	67.34 345	87.68 324

LTVRE_ROB	73.68 18	77.99 304	75.74 309	84.74 303	90.45 277	72.02 319	86.41 358	91.12 334	72.57 341	66.63 344	87.27 293	54.95 321	96.98 213	56.29 361	75.98 282	85.21 358
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
OurMVSNet-221017-0		77.18 314	76.06 306	80.55 343	83.78 362	60.00 378	90.35 328	91.05 337	77.01 308	66.62 345	87.92 285	47.73 347	94.03 329	71.63 288	68.44 332	87.62 325

CNLPA		86.96 182	85.37 191	91.72 148	97.59 72	79.34 197	97.21 114	91.05 337	74.22 325	78.90 242	96.75 123	67.21 232	98.95 111	74.68 267	90.77 165	96.88 161

Anonymous20240521		72.06 340	69.91 341	78.50 353	77.11 383	61.67 373	91.62 319	90.97 339	65.52 366	62.37 363	79.05 366	36.32 377	90.96 364	57.75 354	68.52 331	82.87 369

KD-MVS_self_test		70.97 344	69.31 344	75.95 363	76.24 388	55.39 388	87.45 348	90.94 340	70.20 353	62.96 362	77.48 370	44.01 356	88.09 375	61.25 343	53.26 379	84.37 363

pmmvs6		74.65 327	71.67 333	83.60 323	79.13 376	69.94 336	93.31 294	90.88 341	61.05 380	65.83 348	84.15 341	43.43 359	94.83 313	66.62 317	60.63 367	86.02 350

test1111		88.11 165	87.04 171	91.35 157	93.15 201	78.79 212	96.57 170	90.78 342	86.88 113	85.04 168	95.20 161	57.23 305	97.39 191	83.88 175	94.59 121	97.87 97

ECVR-MVS		88.35 159	87.25 165	91.65 149	93.54 188	79.40 194	96.56 172	90.78 342	86.78 116	85.57 164	95.25 155	57.25 304	97.56 176	84.73 168	94.80 118	97.98 90

Anonymous20231206		75.29 324	73.64 325	80.22 344	80.75 369	63.38 367	93.36 290	90.71 344	73.09 336	67.12 338	83.70 344	50.33 336	90.85 365	53.63 369	70.10 317	86.44 343

USDC		78.65 300	76.25 305	85.85 284	87.58 317	74.60 294	89.58 332	90.58 345	84.05 177	63.13 359	88.23 280	40.69 373	96.86 223	66.57 319	75.81 285	86.09 349

MSDG		80.62 285	77.77 295	89.14 215	93.43 195	77.24 256	91.89 313	90.18 346	69.86 355	68.02 335	91.94 229	52.21 329	98.84 117	59.32 349	83.12 232	91.35 250

ACMH+	76.62 16	77.47 311	74.94 313	85.05 300	91.07 264	71.58 327	93.26 295	90.01 347	71.80 345	64.76 352	88.55 274	41.62 367	96.48 236	62.35 338	71.00 308	87.09 336

FMVSNet5		76.46 318	74.16 322	83.35 326	90.05 285	76.17 273	89.58 332	89.85 348	71.39 348	65.29 351	80.42 360	50.61 334	87.70 380	61.05 344	69.24 326	86.18 347

ambc				76.02 361	68.11 395	51.43 390	64.97 398	89.59 349		60.49 371	74.49 378	17.17 397	92.46 346	61.50 341	52.85 381	84.17 365

test_fmvs2		79.59 292	79.90 279	78.67 351	82.86 365	55.82 386	95.20 242	89.55 350	81.09 235	80.12 233	89.80 260	34.31 383	93.51 339	87.82 143	78.36 275	86.69 340

ITE_SJBPF				82.38 332	87.00 323	65.59 357		89.55 350	79.99 263	69.37 332	91.30 237	41.60 368	95.33 292	62.86 337	74.63 292	86.24 346

pmmvs-eth3d		73.59 330	70.66 337	82.38 332	76.40 386	73.38 302	89.39 335	89.43 352	72.69 340	60.34 372	77.79 369	46.43 352	91.26 362	66.42 321	57.06 372	82.51 373

test20.03		72.36 338	71.15 335	75.98 362	77.79 379	59.16 380	92.40 308	89.35 353	74.09 327	61.50 367	84.32 339	48.09 342	85.54 387	50.63 376	62.15 365	83.24 368

SixPastTwentyTwo		76.04 319	74.32 320	81.22 338	84.54 352	61.43 374	91.16 322	89.30 354	77.89 293	64.04 354	86.31 313	48.23 341	94.29 326	63.54 334	63.84 360	87.93 320

TransMVSNet (Re)		76.94 315	74.38 319	84.62 308	85.92 337	75.25 288	95.28 236	89.18 355	73.88 329	67.22 337	86.46 308	59.64 277	94.10 328	59.24 350	52.57 382	84.50 362

MIMVSNet1		69.44 346	66.65 350	77.84 354	76.48 385	62.84 369	87.42 349	88.97 356	66.96 364	57.75 380	79.72 365	32.77 386	85.83 386	46.32 385	63.42 361	84.85 360

K. test v3		73.62 329	71.59 334	79.69 346	82.98 364	59.85 379	90.85 326	88.83 357	77.13 304	58.90 374	82.11 351	43.62 358	91.72 357	65.83 323	54.10 377	87.50 331

Baseline_NR-MVSNet		81.22 277	80.07 275	84.68 305	85.32 346	75.12 289	96.48 176	88.80 358	76.24 313	77.28 257	86.40 312	67.61 225	94.39 324	75.73 259	66.73 350	84.54 361

MDA-MVSNet-bldmvs		71.45 342	67.94 347	81.98 336	85.33 345	68.50 346	92.35 309	88.76 359	70.40 351	42.99 392	81.96 352	46.57 351	91.31 361	48.75 383	54.39 376	86.11 348

new-patchmatchnet		68.85 349	65.93 351	77.61 356	73.57 391	63.94 364	90.11 330	88.73 360	71.62 347	55.08 383	73.60 380	40.84 371	87.22 383	51.35 374	48.49 388	81.67 381

Patchmatch-test		78.25 302	74.72 316	88.83 222	91.20 259	74.10 299	73.91 393	88.70 361	59.89 384	66.82 342	85.12 332	78.38 94	94.54 320	48.84 382	79.58 262	97.86 98

iter_conf05		90.14 119	89.79 120	91.17 165	95.85 115	86.93 29	97.68 81	88.67 362	89.93 54	81.73 216	92.80 215	90.37 8	96.03 251	90.44 112	80.65 254	90.56 257

OpenMVS_ROB	68.52 20	73.02 335	69.57 342	83.37 325	80.54 372	71.82 323	93.60 285	88.22 363	62.37 371	61.98 365	83.15 348	35.31 382	95.47 286	45.08 387	75.88 284	82.82 370

mvsany_test1		87.58 176	88.22 141	85.67 290	89.78 288	67.18 351	95.25 239	87.93 364	83.96 181	88.79 131	97.06 110	72.52 192	94.53 321	92.21 89	86.45 206	95.30 205

RPSCF		77.73 308	76.63 303	81.06 340	88.66 305	55.76 387	87.77 347	87.88 365	64.82 368	74.14 296	92.79 216	49.22 340	96.81 225	67.47 312	76.88 280	90.62 256

mvsmamba		85.17 213	84.54 204	87.05 267	87.94 313	75.11 290	96.22 194	87.79 366	86.91 111	78.55 245	91.77 232	64.93 248	95.91 261	86.94 154	79.80 256	90.12 266

MVS-HIRNet		71.36 343	67.00 348	84.46 312	90.58 274	69.74 339	79.15 381	87.74 367	46.09 393	61.96 366	50.50 397	45.14 355	95.64 278	53.74 368	88.11 192	88.00 319

DP-MVS		81.47 273	78.28 290	91.04 168	98.14 55	78.48 217	95.09 251	86.97 368	61.14 379	71.12 321	92.78 217	59.59 278	99.38 78	53.11 370	86.61 204	95.27 206

COLMAP_ROB	73.24 19	75.74 322	73.00 329	83.94 316	92.38 222	69.08 343	91.85 314	86.93 369	61.48 376	65.32 350	90.27 254	42.27 365	96.93 218	50.91 375	75.63 286	85.80 355
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvs3		69.56 345	69.19 345	70.67 367	69.01 393	47.05 393	90.87 325	86.81 370	71.31 349	66.79 343	77.15 371	16.40 398	83.17 390	81.84 199	62.51 364	81.79 380

test_0402		72.68 336	69.54 343	82.09 335	88.67 304	71.81 324	92.72 304	86.77 371	61.52 375	62.21 364	83.91 342	43.22 361	93.76 335	34.60 394	72.23 304	80.72 382

testgi		74.88 326	73.40 326	79.32 349	80.13 373	61.75 371	93.21 296	86.64 372	79.49 272	66.56 346	91.06 241	35.51 381	88.67 374	56.79 360	71.25 306	87.56 328

TDRefinement		69.20 348	65.78 352	79.48 347	66.04 398	62.21 370	88.21 342	86.12 373	62.92 370	61.03 370	85.61 321	33.23 384	94.16 327	55.82 364	53.02 380	82.08 377

ADS-MVSNet2		79.57 293	77.53 296	85.71 288	93.78 181	72.13 316	79.48 378	86.11 374	73.09 336	80.14 231	79.99 363	62.15 262	90.14 371	59.49 347	83.52 228	94.85 214

LF4IMVS		72.36 338	70.82 336	76.95 357	79.18 375	56.33 383	86.12 360	86.11 374	69.30 357	63.06 360	86.66 304	33.03 385	92.25 349	65.33 325	68.64 330	82.28 376

TinyColmap		72.41 337	68.99 346	82.68 330	88.11 310	69.59 340	88.41 341	85.20 376	65.55 365	57.91 378	84.82 336	30.80 389	95.94 259	51.38 372	68.70 329	82.49 375

pmmvs3		65.75 353	62.18 356	76.45 360	67.12 397	64.54 359	88.68 339	85.05 377	54.77 392	57.54 381	73.79 379	29.40 390	86.21 385	55.49 365	47.77 389	78.62 384

bld_raw_dy_0_64		88.31 160	86.38 179	94.07 47	96.33 97	84.79 76	97.19 117	84.75 378	94.48 8	82.36 202	98.47 27	46.18 353	98.30 145	96.54 36	81.13 249	99.13 27

new_pmnet		66.18 352	63.18 355	75.18 365	76.27 387	61.74 372	83.79 371	84.66 379	56.64 390	51.57 386	71.85 388	31.29 388	87.93 376	49.98 378	62.55 363	75.86 387

AllTest		75.92 320	73.06 328	84.47 310	92.18 234	67.29 349	91.07 323	84.43 380	67.63 359	63.48 355	90.18 255	38.20 375	97.16 204	57.04 357	73.37 296	88.97 298

TestCases				84.47 310	92.18 234	67.29 349		84.43 380	67.63 359	63.48 355	90.18 255	38.20 375	97.16 204	57.04 357	73.37 296	88.97 298

LCM-MVSNet-Re		83.75 237	83.54 223	84.39 314	93.54 188	64.14 362	92.51 305	84.03 382	83.90 184	66.14 347	86.59 305	67.36 230	92.68 344	84.89 167	92.87 145	96.35 177

Gipuma		45.11 368	42.05 370	54.30 384	80.69 370	51.30 391	35.80 402	83.81 383	28.13 398	27.94 402	34.53 402	11.41 405	76.70 398	21.45 401	54.65 374	34.90 402
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		52.52 362	48.24 365	65.35 372	47.63 409	41.45 401	72.55 394	83.62 384	31.75 397	37.66 395	57.92 395	9.19 407	76.76 397	49.26 380	44.60 392	77.84 385

FPMVS		55.09 360	52.93 363	61.57 378	55.98 402	40.51 403	83.11 374	83.41 385	37.61 396	34.95 397	71.95 386	14.40 399	76.95 396	29.81 396	65.16 354	67.25 391

Patchmatch-RL test		76.65 317	74.01 324	84.55 309	77.37 382	64.23 361	78.49 384	82.84 386	78.48 289	64.63 353	73.40 381	76.05 136	91.70 358	76.99 243	57.84 371	97.72 109

DSMNet-mixed		73.13 334	72.45 330	75.19 364	77.51 381	46.82 394	85.09 366	82.01 387	67.61 363	69.27 333	81.33 356	50.89 332	86.28 384	54.54 366	83.80 227	92.46 245

lessismore_v0				79.98 345	80.59 371	58.34 381		80.87 388		58.49 376	83.46 346	43.10 362	93.89 331	63.11 336	48.68 386	87.72 322

test_f		64.01 354	62.13 357	69.65 368	63.00 400	45.30 399	83.66 372	80.68 389	61.30 377	55.70 382	72.62 384	14.23 400	84.64 388	69.84 302	58.11 370	79.00 383

door								80.13 390

door-mid								79.75 391

PM-MVS		69.32 347	66.93 349	76.49 359	73.60 390	55.84 385	85.91 361	79.32 392	74.72 323	61.09 369	78.18 368	21.76 394	91.10 363	70.86 297	56.90 373	82.51 373

mvsany_test3		67.19 351	65.34 353	72.72 366	63.08 399	48.57 392	83.12 373	78.09 393	72.07 343	61.21 368	77.11 372	22.94 393	87.78 379	78.59 226	51.88 383	81.80 379

dmvs_testset		72.00 341	73.36 327	67.91 369	83.83 361	31.90 409	85.30 365	77.12 394	82.80 209	63.05 361	92.46 219	61.54 269	82.55 392	42.22 391	71.89 305	89.29 284

ANet_high		46.22 365	41.28 372	61.04 379	39.91 411	46.25 397	70.59 395	76.18 395	58.87 387	23.09 403	48.00 400	12.58 403	66.54 403	28.65 398	13.62 404	70.35 389

test_method		56.77 357	54.53 361	63.49 376	76.49 384	40.70 402	75.68 389	74.24 396	19.47 404	48.73 387	71.89 387	19.31 395	65.80 404	57.46 356	47.51 390	83.97 366

APD_test1		56.56 358	53.58 362	65.50 371	67.93 396	46.51 396	77.24 388	72.95 397	38.09 395	42.75 393	75.17 375	13.38 401	82.78 391	40.19 392	54.53 375	67.23 392

EGC-MVSNET		52.46 363	47.56 366	67.15 370	81.98 367	60.11 377	82.54 375	72.44 398	0.11 410	0.70 411	74.59 377	25.11 392	83.26 389	29.04 397	61.51 366	58.09 395

PMMVS2		50.90 364	46.31 367	64.67 373	55.53 403	46.67 395	77.30 387	71.02 399	40.89 394	34.16 398	59.32 393	9.83 406	76.14 399	40.09 393	28.63 401	71.21 388

WB-MVS		57.26 356	56.22 359	60.39 380	69.29 392	35.91 407	86.39 359	70.06 400	59.84 385	46.46 390	72.71 383	51.18 331	78.11 394	15.19 404	34.89 399	67.14 393

SSC-MVS		56.01 359	54.96 360	59.17 381	68.42 394	34.13 408	84.98 367	69.23 401	58.08 389	45.36 391	71.67 389	50.30 337	77.46 395	14.28 405	32.33 400	65.91 394

test_vis1_rt		73.96 328	72.40 331	78.64 352	83.91 360	61.16 375	95.63 224	68.18 402	76.32 310	60.09 373	74.77 376	29.01 391	97.54 180	87.74 144	75.94 283	77.22 386

MTMP							97.53 92	68.16 403

DeepMVS_CX				64.06 375	78.53 377	43.26 400		68.11 404	69.94 354	38.55 394	76.14 374	18.53 396	79.34 393	43.72 388	41.62 396	69.57 390

PMVS	34.80 23	39.19 370	35.53 373	50.18 385	29.72 412	30.30 410	59.60 400	66.20 405	26.06 401	17.91 405	49.53 398	3.12 411	74.09 400	18.19 403	49.40 385	46.14 399
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testf1		45.70 366	42.41 368	55.58 382	53.29 406	40.02 404	68.96 396	62.67 406	27.45 399	29.85 399	61.58 391	5.98 409	73.83 401	28.49 399	43.46 394	52.90 396

APD_test2		45.70 366	42.41 368	55.58 382	53.29 406	40.02 404	68.96 396	62.67 406	27.45 399	29.85 399	61.58 391	5.98 409	73.83 401	28.49 399	43.46 394	52.90 396

tmp_tt		41.54 369	41.93 371	40.38 387	20.10 413	26.84 411	61.93 399	59.09 408	14.81 406	28.51 401	80.58 359	35.53 380	48.33 408	63.70 333	13.11 405	45.96 401

MVE	35.65 22	33.85 371	29.49 376	46.92 386	41.86 410	36.28 406	50.45 401	56.52 409	18.75 405	18.28 404	37.84 401	2.41 412	58.41 405	18.71 402	20.62 402	46.06 400
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		32.70 372	32.39 374	33.65 388	53.35 405	25.70 412	74.07 392	53.33 410	21.08 402	17.17 406	33.63 404	11.85 404	54.84 406	12.98 406	14.04 403	20.42 403

EMVS		31.70 373	31.45 375	32.48 389	50.72 408	23.95 413	74.78 391	52.30 411	20.36 403	16.08 407	31.48 405	12.80 402	53.60 407	11.39 407	13.10 406	19.88 404

test_vis3_rt		54.10 361	51.04 364	63.27 377	58.16 401	46.08 398	84.17 369	49.32 412	56.48 391	36.56 396	49.48 399	8.03 408	91.91 355	67.29 313	49.87 384	51.82 398

N_pmnet		61.30 355	60.20 358	64.60 374	84.32 354	17.00 415	91.67 318	10.98 413	61.77 374	58.45 377	78.55 367	49.89 338	91.83 356	42.27 390	63.94 359	84.97 359

wuyk23d		14.10 375	13.89 378	14.72 390	55.23 404	22.91 414	33.83 403	3.56 414	4.94 407	4.11 408	2.28 410	2.06 413	19.66 409	10.23 408	8.74 407	1.59 407

testmvs		9.92 376	12.94 379	0.84 392	0.65 414	0.29 417	93.78 281	0.39 415	0.42 408	2.85 409	15.84 408	0.17 415	0.30 411	2.18 409	0.21 408	1.91 406

test123		9.07 377	11.73 380	1.11 391	0.50 415	0.77 416	89.44 334	0.20 416	0.34 409	2.15 410	10.72 409	0.34 414	0.32 410	1.79 410	0.08 409	2.23 405

test_blank		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet_test		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

DCPMVS		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

pcd_1.5k_mvsjas		5.92 379	7.89 382	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	71.04 211	0.00 412	0.00 411	0.00 410	0.00 408

sosnet-low-res		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uncertanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

Regformer		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

n2								0.00 417

nn								0.00 417

ab-mvs-re		8.11 378	10.81 381	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	97.30 97	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

WAC-MVS						67.18 351								49.00 381

PC_three_1452									91.12 37	98.33 2	98.42 30	92.51 2	99.81 21	98.96 3	99.37 1	99.70 3

eth-test2					0.00 416

eth-test					0.00 416

OPU-MVS				97.30 2	99.19 7	92.31 3	99.12 12				98.54 20	92.06 3	99.84 12	99.11 2	99.37 1	99.74 1

test_0728_THIRD									88.38 75	96.69 18	98.76 12	89.64 13	99.76 31	97.47 24	98.84 23	99.38 14

GSMVS																97.54 122

test_part2					98.90 19	85.14 67				96.07 29

sam_mvs1												77.59 107				97.54 122

sam_mvs												75.35 155

test_post1							85.88 362				30.24 406	73.77 178	95.07 308	73.89 275

test_post											33.80 403	76.17 134	95.97 255

patchmatchnet-post											77.09 373	77.78 106	95.39 288

gm-plane-assit					92.27 228	79.64 190			84.47 166		95.15 165		97.93 156	85.81 159

test9_res														96.00 41	99.03 13	98.31 66

agg_prior2														94.30 60	99.00 15	98.57 50

test_prior4						82.34 118	97.75 76

test_prior2							98.37 40		86.08 125	94.57 50	98.02 53	83.14 50		95.05 53	98.79 26

旧先验2							96.97 143		74.06 328	96.10 28			97.76 167	88.38 139

新几何2							96.42 183

原ACMM2							96.84 153

testdata2													99.48 73	76.45 250

segment_acmp												82.69 55

testdata1							95.57 227		87.44 98

plane_prior7					91.86 249	77.55 251

plane_prior6					91.98 245	77.92 240						64.77 249

plane_prior4											94.15 191

plane_prior3						77.75 247			90.17 52	81.33 217

plane_prior2							97.18 119		89.89 55

plane_prior1					91.95 247

plane_prior						77.96 237	97.52 95		90.36 50						82.96 236

HQP5-MVS						78.48 217

HQP-NCC					92.08 240		97.63 83		90.52 45	82.30 203

ACMP_Plane					92.08 240		97.63 83		90.52 45	82.30 203

BP-MVS														87.67 146

HQP4-MVS										82.30 203			97.32 194			91.13 251

HQP2-MVS												65.40 243

NP-MVS					92.04 244	78.22 227					94.56 181

MDTV_nov1_ep13_2view						81.74 134	86.80 354		80.65 244	85.65 163		74.26 172		76.52 249		96.98 154

ACMMP++_ref															78.45 274

ACMMP++															79.05 266

Test By Simon												71.65 204

High-resolution multi-view benchmark