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		88.92 138	87.65 150	92.73 100	96.30 99	85.62 49	97.85 67	98.86 1	84.38 166	84.82 170	93.99 193	75.12 160	98.01 152	70.86 295	86.67 201	94.56 220

thres100view900		88.30 159	86.95 171	92.33 117	96.10 106	84.90 71	97.14 126	98.85 2	82.69 210	83.41 188	93.66 200	75.43 150	97.93 154	69.04 303	86.24 208	94.17 222

tfpn200view9		88.48 152	87.15 165	92.47 109	96.21 102	85.30 57	97.44 100	98.85 2	83.37 193	83.99 180	93.82 196	75.36 153	97.93 154	69.04 303	86.24 208	94.17 222

thres600view7		88.06 164	86.70 175	92.15 129	96.10 106	85.17 63	97.14 126	98.85 2	82.70 209	83.41 188	93.66 200	75.43 150	97.82 163	67.13 312	85.88 212	93.45 238

thres400		88.42 155	87.15 165	92.23 123	96.21 102	85.30 57	97.44 100	98.85 2	83.37 193	83.99 180	93.82 196	75.36 153	97.93 154	69.04 303	86.24 208	93.45 238

MVS_111021_HR		93.41 40	93.39 43	93.47 74	97.34 85	82.83 107	97.56 89	98.27 6	89.16 63	89.71 112	97.14 102	79.77 77	99.56 66	93.65 69	97.94 59	98.02 81

sss		90.87 104	89.96 113	93.60 64	94.15 169	83.84 89	97.14 126	98.13 7	85.93 127	89.68 113	96.09 132	71.67 201	99.30 83	87.69 143	89.16 174	97.66 112

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 24

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 75	96.97 110	81.30 62	98.99 107	88.54 133	98.88 20	99.20 22

VNet		92.11 70	91.22 83	94.79 25	96.91 91	86.98 27	97.91 64	97.96 10	86.38 118	93.65 60	95.74 138	70.16 217	98.95 111	93.39 71	88.87 179	98.43 57

MVS_0304		95.36 10	95.20 17	95.85 11	94.89 145	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 52

test_yl		91.46 86	90.53 96	94.24 39	97.41 80	85.18 59	98.08 53	97.72 12	80.94 235	89.85 109	96.14 130	75.61 142	98.81 119	90.42 112	88.56 184	98.74 37

DCV-MVSNet		91.46 86	90.53 96	94.24 39	97.41 80	85.18 59	98.08 53	97.72 12	80.94 235	89.85 109	96.14 130	75.61 142	98.81 119	90.42 112	88.56 184	98.74 37

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	89.82 111	97.22 100	79.29 80	99.06 104	89.57 122	88.73 181	98.73 41

EPNet		94.06 32	94.15 31	93.76 54	97.27 87	84.35 79	98.29 42	97.64 15	94.57 6	95.36 34	96.88 113	79.96 76	99.12 100	91.30 95	96.11 102	97.82 101
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HY-MVS	84.06 6	91.63 82	90.37 102	95.39 17	96.12 105	88.25 15	90.22 327	97.58 16	88.33 76	90.50 104	91.96 225	79.26 81	99.06 104	90.29 114	89.07 175	98.88 33

baseline2		90.39 112	90.21 106	90.93 169	90.86 267	80.99 148	95.20 240	97.41 17	86.03 125	80.07 232	94.61 178	90.58 6	97.47 185	87.29 147	89.86 169	94.35 221

test2506		90.96 101	90.39 100	92.65 103	93.54 186	82.46 114	96.37 183	97.35 18	86.78 114	87.55 144	95.25 153	77.83 105	97.50 182	84.07 170	94.80 118	97.98 88

PVSNet	82.34 9	89.02 135	87.79 148	92.71 101	95.49 124	81.50 139	97.70 79	97.29 19	87.76 88	85.47 163	95.12 165	56.90 304	98.90 115	80.33 205	94.02 128	97.71 109

testing222		91.09 96	90.49 98	92.87 93	95.82 116	85.04 66	96.51 173	97.28 20	86.05 124	89.13 122	95.34 152	80.16 74	96.62 231	85.82 156	88.31 187	96.96 153

PGM-MVS		91.93 73	91.80 73	92.32 119	98.27 50	79.74 184	95.28 234	97.27 21	83.83 184	90.89 100	97.78 70	76.12 135	99.56 66	88.82 130	97.93 61	97.66 112

IB-MVS	85.34 4	88.67 146	87.14 167	93.26 77	93.12 202	84.32 80	98.76 27	97.27 21	87.19 105	79.36 238	90.45 249	83.92 46	98.53 129	84.41 167	69.79 318	96.93 155
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	92.45 110	95.29 130	80.96 150	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	96.61 168

patch_mono-2		95.14 13	96.08 7	92.33 117	98.44 43	77.84 241	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 17

MVS		90.60 108	88.64 133	96.50 5	94.25 165	90.53 8	93.33 289	97.21 23	77.59 296	78.88 241	97.31 94	71.52 204	99.69 49	89.60 121	98.03 55	99.27 20

ETVMVS		90.99 99	90.26 103	93.19 81	95.81 117	85.64 48	96.97 142	97.18 26	85.43 135	88.77 131	94.86 173	82.00 58	96.37 238	82.70 192	88.60 182	97.57 119

CSCG		92.02 71	91.65 76	93.12 83	98.53 36	80.59 159	97.47 97	97.18 26	77.06 305	84.64 175	97.98 57	83.98 44	99.52 69	90.72 104	97.33 77	99.23 21

fmvsm_s_conf0.5_n		93.69 36	94.13 32	92.34 115	94.56 152	82.01 119	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	95.22 205

PHI-MVS		93.59 38	93.63 37	93.48 72	98.05 58	81.76 131	98.64 32	97.13 28	82.60 212	94.09 56	98.49 26	80.35 68	99.85 10	94.74 57	98.62 33	98.83 34

CNVR-MVS		96.30 1	96.54 1	95.55 15	99.31 5	87.69 22	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 29

h-mvs33		89.30 131	88.95 129	90.36 186	95.07 138	76.04 274	96.96 144	97.11 31	90.39 48	92.22 77	95.10 166	74.70 165	98.86 116	93.14 77	65.89 350	96.16 181

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 79	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 53	95.94 112	86.00 37	97.56 89	97.08 33	87.52 94	89.32 120	95.40 150	84.60 35	98.02 151	91.93 92	89.04 176	97.32 136

VPA-MVSNet		85.32 208	83.83 214	89.77 206	90.25 277	82.63 109	96.36 184	97.07 34	83.03 201	81.21 217	89.02 266	61.58 266	96.31 241	85.02 164	70.95 307	90.36 258

UWE-MVS		88.56 151	88.91 131	87.50 253	94.17 168	72.19 313	95.82 215	97.05 35	84.96 150	84.78 171	93.51 204	81.33 60	94.75 312	79.43 216	89.17 173	95.57 194

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 87	97.08 106	83.32 49	99.69 49	92.83 81	98.70 31	99.04 27
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 71	94.94 142	86.26 33	81.62 374	97.00 37		88.32 138	94.30 184	91.23 5	96.21 245	88.49 135	97.43 74	98.00 86

fmvsm_s_conf0.5_n_a		93.34 41	93.71 35	92.22 124	93.38 194	81.71 134	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	95.18 206

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	89.33 126	99.25 6	99.70 3

gg-mvs-nofinetune		85.48 207	82.90 231	93.24 78	94.51 158	85.82 42	79.22 378	96.97 40	61.19 376	87.33 147	53.01 394	90.58 6	96.07 248	86.07 155	97.23 80	97.81 102

NCCC		95.63 7	95.94 8	94.69 28	99.21 6	85.15 64	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 29

FIs		86.73 187	86.10 180	88.61 224	90.05 283	80.21 171	96.14 198	96.95 42	85.56 134	78.37 246	92.30 218	76.73 124	95.28 293	79.51 214	79.27 262	90.35 259

PVSNet_0	77.72 15	81.70 268	78.95 285	89.94 199	90.77 270	76.72 264	95.96 204	96.95 42	85.01 148	70.24 326	88.53 274	52.32 325	98.20 147	86.68 154	44.08 391	94.89 210

HPM-MVS++		95.32 11	95.48 14	94.85 24	98.62 34	86.04 36	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 45

MSLP-MVS++		94.28 26	94.39 27	93.97 47	98.30 49	84.06 85	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 46

testing99		91.91 74	91.35 80	93.60 64	95.98 110	85.70 44	97.31 111	96.92 46	86.82 112	88.91 126	95.25 153	84.26 42	97.89 161	88.80 131	87.94 191	97.21 144

testing91		91.90 75	91.31 82	93.66 60	95.99 109	85.68 46	97.39 107	96.89 47	86.75 116	88.85 128	95.23 156	83.93 45	97.90 160	88.91 128	87.89 192	97.41 131

UniMVSNet (Re)		85.31 209	84.23 209	88.55 225	89.75 287	80.55 161	96.72 160	96.89 47	85.42 136	78.40 245	88.93 267	75.38 152	95.52 283	78.58 225	68.02 335	89.57 275

FC-MVSNet-test		85.96 197	85.39 188	87.66 246	89.38 296	78.02 232	95.65 221	96.87 49	85.12 145	77.34 253	91.94 227	76.28 133	94.74 313	77.09 240	78.82 266	90.21 262

EI-MVSNet-Vis-set		91.84 77	91.77 74	92.04 134	97.60 71	81.17 143	96.61 166	96.87 49	88.20 78	89.19 121	97.55 86	78.69 92	99.14 97	90.29 114	90.94 164	95.80 188

IU-MVS					99.03 15	85.34 54		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 90	91.22 83	91.73 145	97.39 82	80.68 157	96.47 175	96.83 52	87.92 84	88.30 139	97.36 93	77.84 104	99.13 99	89.43 125	89.45 171	95.37 200

SED-MVS		95.88 5	96.22 4	94.87 23	99.03 15	85.03 67	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 67		96.78 55	88.72 67	97.79 7	98.90 5	88.48 17	99.82 18

test0726					99.05 9	85.18 59	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 94	98.31 48	80.10 175	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							96.87 150	96.78 55	77.39 298				99.52 69	79.95 211		98.43 57

DVP-MVS++		96.05 4	96.41 3	94.96 22	99.05 9	85.34 54	98.13 50	96.77 61	88.38 74	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 18	99.04 14	86.14 35	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 26	98.02 59	85.94 40	97.47 97	96.77 61	85.32 138	97.92 3	98.70 15	83.09 51	99.84 12	95.79 44	99.08 10	98.49 53
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 84	91.64 77	91.47 154	95.74 119	78.79 210	96.15 197	96.77 61	88.49 72	88.64 133	97.07 107	72.33 194	99.19 93	93.13 79	96.48 97	96.43 173

3Dnovator	82.32 10	89.33 130	87.64 151	94.42 33	93.73 182	85.70 44	97.73 77	96.75 65	86.73 117	76.21 273	95.93 134	62.17 259	99.68 51	81.67 198	97.81 62	97.88 93

DPE-MVS		95.32 11	95.55 12	94.64 29	98.79 23	84.87 72	97.77 73	96.74 66	86.11 121	96.54 24	98.89 6	88.39 19	99.74 38	97.67 22	99.05 12	99.31 18
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
PVSNet_BlendedMVS		90.05 118	89.96 113	90.33 187	97.47 76	83.86 87	98.02 59	96.73 67	87.98 82	89.53 117	89.61 261	76.42 129	99.57 64	94.29 61	79.59 259	87.57 325

PVSNet_Blended		93.13 42	92.98 48	93.57 66	97.47 76	83.86 87	99.32 2	96.73 67	91.02 40	89.53 117	96.21 129	76.42 129	99.57 64	94.29 61	95.81 110	97.29 140

ACMMP		90.39 112	89.97 112	91.64 148	97.58 73	78.21 228	96.78 157	96.72 69	84.73 155	84.72 173	97.23 99	71.22 206	99.63 57	88.37 138	92.41 152	97.08 150
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 83	97.44 78	81.60 138		96.71 70	74.54 322	91.22 94	97.57 82	79.13 84	99.51 71	77.40 239	98.46 39	98.26 69

test_one_0601					98.91 18	84.56 78		96.70 71	88.06 80	96.57 23	98.77 10	88.04 20

HFP-MVS		92.89 49	92.86 51	92.98 89	98.71 25	81.12 144	97.58 87	96.70 71	85.20 143	91.75 84	97.97 59	78.47 93	99.71 45	90.95 98	98.41 42	98.12 77

ACMMPR		92.69 57	92.67 54	92.75 98	98.66 28	80.57 160	97.58 87	96.69 73	85.20 143	91.57 86	97.92 60	77.01 117	99.67 53	90.95 98	98.41 42	98.00 86

DeepPCF-MVS	89.82 1	94.61 22	96.17 5	89.91 200	97.09 90	70.21 333	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		89.65 125	89.02 126	91.53 152	93.46 192	80.78 155	96.52 171	96.67 75	81.69 228	83.79 185	94.90 172	88.85 15	97.68 167	77.80 228	87.49 197	96.14 182

tttt0517		88.57 150	88.19 141	89.71 207	93.00 204	75.99 278	95.67 219	96.67 75	80.78 239	81.82 211	94.40 182	88.97 14	97.58 173	76.05 253	86.31 205	95.57 194

thisisatest0515		90.95 102	90.26 103	93.01 88	94.03 177	84.27 83	97.91 64	96.67 75	83.18 196	86.87 153	95.51 148	88.66 16	97.85 162	80.46 204	89.01 177	96.92 157

ACMMP_NAP		93.46 39	93.23 45	94.17 42	97.16 88	84.28 82	96.82 154	96.65 78	86.24 119	94.27 53	97.99 54	77.94 101	99.83 16	93.39 71	98.57 34	98.39 59

TEST9					98.64 31	83.71 90	97.82 69	96.65 78	84.29 171	95.16 36	98.09 47	84.39 37	99.36 81

train_agg		94.28 26	94.45 25	93.74 55	98.64 31	83.71 90	97.82 69	96.65 78	84.50 162	95.16 36	98.09 47	84.33 38	99.36 81	95.91 43	98.96 19	98.16 73

1314		88.94 137	87.20 164	94.17 42	93.21 196	85.73 43	93.33 289	96.64 81	82.89 204	75.98 276	96.36 126	66.83 233	99.39 77	83.52 185	96.02 106	97.39 134

DeepC-MVS_fast	89.06 2	94.48 24	94.30 29	95.02 20	98.86 21	85.68 46	98.06 56	96.64 81	93.64 14	91.74 85	98.54 20	80.17 73	99.90 5	92.28 86	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 93	97.81 71	96.63 83	84.50 162	95.10 40	98.11 46	84.33 38	99.23 86

FE-MVS		86.06 196	84.15 211	91.78 144	94.33 164	79.81 179	84.58 366	96.61 84	76.69 307	85.00 167	87.38 289	70.71 213	98.37 139	70.39 298	91.70 160	97.17 147

原ACMM1				91.22 162	97.77 65	78.10 231		96.61 84	81.05 234	91.28 93	97.42 91	77.92 103	98.98 108	79.85 213	98.51 35	96.59 169

MAR-MVS		90.63 107	90.22 105	91.86 140	98.47 42	78.20 229	97.18 119	96.61 84	83.87 183	88.18 140	98.18 40	68.71 221	99.75 36	83.66 181	97.15 81	97.63 115
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	83.22 102		96.60 87	82.88 205	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 80	95.41 126	81.35 141	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 35
Skip Steuart: Steuart Systems R&D Blog.
D2MVS		82.67 254	81.55 251	86.04 281	87.77 313	76.47 266	95.21 239	96.58 89	82.66 211	70.26 325	85.46 323	60.39 272	95.80 265	76.40 249	79.18 263	85.83 352

save fliter					98.24 51	83.34 99	98.61 34	96.57 90	91.32 34

TESTMET0.1,1		89.83 122	89.34 123	91.31 156	92.54 219	80.19 172	97.11 129	96.57 90	86.15 120	86.85 154	91.83 229	79.32 79	96.95 213	81.30 199	92.35 153	96.77 163

agg_prior					98.59 35	83.13 103		96.56 92		94.19 54			99.16 96

旧先验1					97.39 82	79.58 189		96.54 93			98.08 50	84.00 43			97.42 75	97.62 116

WR-MVS_H		81.02 277	80.09 271	83.79 316	88.08 309	71.26 328	94.46 259	96.54 93	80.08 258	72.81 308	86.82 299	70.36 215	92.65 343	64.18 327	67.50 341	87.46 330

9.14			94.26 30		98.10 57		98.14 47	96.52 95	84.74 154	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 97	98.68 26	80.53 164	97.53 92	96.51 96	85.22 141	91.94 82	97.98 57	77.26 112	99.67 53	90.83 102	98.37 45	98.18 71

EPP-MVSNet		89.76 123	89.72 119	89.87 201	93.78 179	76.02 277	97.22 113	96.51 96	79.35 271	85.11 165	95.01 169	84.82 33	97.10 207	87.46 146	88.21 189	96.50 171

ZNCC-MVS		92.75 51	92.60 56	93.23 79	98.24 51	81.82 129	97.63 83	96.50 98	85.00 149	91.05 96	97.74 71	78.38 94	99.80 25	90.48 107	98.34 47	98.07 79

test11								96.50 98

EPNet_dtu		87.65 173	87.89 145	86.93 267	94.57 151	71.37 327	96.72 160	96.50 98	88.56 71	87.12 151	95.02 168	75.91 139	94.01 328	66.62 315	90.00 167	95.42 199
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testdata				90.13 192	95.92 113	74.17 296		96.49 101	73.49 331	94.82 48	97.99 54	78.80 90	97.93 154	83.53 184	97.52 70	98.29 66

DVP-MVS		95.58 9	95.91 9	94.57 30	99.05 9	85.18 59	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 36
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	78.41 219	95.87 211	96.46 102	71.97 342	89.66 114	97.45 87	76.33 132			98.24 50	98.30 65

XVS		92.69 57	92.71 52	92.63 105	98.52 37	80.29 167	97.37 108	96.44 104	87.04 107	91.38 88	97.83 68	77.24 114	99.59 60	90.46 108	98.07 53	98.02 81

X-MVStestdata		86.26 193	84.14 212	92.63 105	98.52 37	80.29 167	97.37 108	96.44 104	87.04 107	91.38 88	20.73 405	77.24 114	99.59 60	90.46 108	98.07 53	98.02 81

SF-MVS		94.17 29	94.05 33	94.55 31	97.56 74	85.95 38	97.73 77	96.43 106	84.02 176	95.07 42	98.74 14	82.93 52	99.38 78	95.42 51	98.51 35	98.32 62

TSAR-MVS + MP.		94.79 20	95.17 18	93.64 61	97.66 69	84.10 84	95.85 213	96.42 107	91.26 35	97.49 13	96.80 118	86.50 27	98.49 131	95.54 49	99.03 13	98.33 61
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 48	98.84 22	83.40 98	98.04 58	96.41 108	85.79 129	95.00 43	98.28 36	84.32 41	99.18 94	97.35 26	98.77 27	99.28 19
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
UniMVSNet_NR-MVSNet		85.49 206	84.59 201	88.21 235	89.44 295	79.36 193	96.71 162	96.41 108	85.22 141	78.11 248	90.98 242	76.97 119	95.14 300	79.14 220	68.30 332	90.12 264

test_prior				93.09 85	98.68 26	81.91 124		96.40 110					99.06 104			98.29 66

CP-MVS		92.54 62	92.60 56	92.34 115	98.50 40	79.90 178	98.40 39	96.40 110	84.75 153	90.48 105	98.09 47	77.40 111	99.21 88	91.15 97	98.23 51	97.92 92

CANet		94.89 16	94.64 22	95.63 13	97.55 75	88.12 16	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 32

GST-MVS		92.43 65	92.22 65	93.04 87	98.17 54	81.64 136	97.40 106	96.38 113	84.71 156	90.90 99	97.40 92	77.55 109	99.76 31	89.75 120	97.74 64	97.72 107

alignmvs		92.97 47	92.26 63	95.12 19	95.54 123	87.77 20	98.67 30	96.38 113	88.04 81	93.01 69	97.45 87	79.20 83	98.60 125	93.25 76	88.76 180	98.99 31

PAPM		92.87 50	92.40 59	94.30 35	92.25 229	87.85 19	96.40 182	96.38 113	91.07 38	88.72 132	96.90 111	82.11 57	97.37 191	90.05 117	97.70 65	97.67 111

test_fmvsmconf_n		93.99 33	94.36 28	92.86 94	92.82 211	81.12 144	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 99

test12				94.25 38	98.34 46	85.55 50		96.35 117		92.36 74		80.84 63	99.22 87		98.31 48	97.98 88

MTGPA								96.33 118

MTAPA		92.45 64	92.31 61	92.86 94	97.90 61	80.85 153	92.88 300	96.33 118	87.92 84	90.20 108	98.18 40	76.71 125	99.76 31	92.57 85	98.09 52	97.96 91

ET-MVSNet_ETH3D		90.01 119	89.03 125	92.95 90	94.38 162	86.77 30	98.14 47	96.31 120	89.30 61	63.33 356	96.72 122	90.09 11	93.63 335	90.70 105	82.29 243	98.46 55

EPMVS		87.47 176	85.90 182	92.18 126	95.41 126	82.26 118	87.00 351	96.28 121	85.88 128	84.23 177	85.57 320	75.07 161	96.26 242	71.14 293	92.50 150	98.03 80

WB-MVSnew		84.08 229	83.51 222	85.80 283	91.34 256	76.69 265	95.62 223	96.27 122	81.77 226	81.81 212	92.81 212	58.23 288	94.70 314	66.66 314	87.06 198	85.99 349

CDPH-MVS		93.12 43	92.91 49	93.74 55	98.65 30	83.88 86	97.67 82	96.26 123	83.00 202	93.22 66	98.24 37	81.31 61	99.21 88	89.12 127	98.74 30	98.14 75

WR-MVS		84.32 225	82.96 229	88.41 227	89.38 296	80.32 166	96.59 167	96.25 124	83.97 178	76.63 263	90.36 251	67.53 226	94.86 310	75.82 256	70.09 316	90.06 269

fmvsm_s_conf0.1_n		92.93 48	93.16 47	92.24 122	90.52 273	81.92 123	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	95.05 207

UGNet		87.73 171	86.55 176	91.27 159	95.16 135	79.11 201	96.35 185	96.23 126	88.14 79	87.83 143	90.48 248	50.65 331	99.09 102	80.13 210	94.03 127	95.60 193
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		78.14 301	75.42 308	86.31 277	88.33 307	79.24 196	94.41 261	96.22 127	73.51 329	69.81 328	85.52 322	55.43 314	95.75 268	47.65 382	67.86 337	83.95 365

FOURS1					98.51 39	78.01 233	98.13 50	96.21 128	83.04 200	94.39 52

MP-MVS		92.61 60	92.67 54	92.42 113	98.13 56	79.73 185	97.33 110	96.20 129	85.63 131	90.53 103	97.66 74	78.14 99	99.70 48	92.12 88	98.30 49	97.85 97
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 32	98.89 20	84.87 72	97.20 116	96.20 129	87.73 89	88.40 136	98.12 45	78.71 91	99.76 31	87.99 140	96.28 98	98.74 37

SD-MVS		94.84 18	95.02 19	94.29 36	97.87 64	84.61 76	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 44
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
CHOSEN 280x420		91.71 81	91.85 71	91.29 158	94.94 142	82.69 108	87.89 344	96.17 132	85.94 126	87.27 148	94.31 183	90.27 9	95.65 275	94.04 65	95.86 108	95.53 196

fmvsm_l_conf0.5_n		94.89 16	95.24 16	93.86 50	94.42 161	84.61 76	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	97.22 142

CHOSEN 1792x2688		91.07 98	90.21 106	93.64 61	95.18 134	83.53 95	96.26 190	96.13 134	88.92 64	84.90 169	93.10 210	72.86 188	99.62 58	88.86 129	95.67 111	97.79 103

PAPM_NR		91.46 86	90.82 90	93.37 75	98.50 40	81.81 130	95.03 250	96.13 134	84.65 158	86.10 159	97.65 78	79.24 82	99.75 36	83.20 187	96.88 87	98.56 49

CostFormer		89.08 134	88.39 138	91.15 164	93.13 201	79.15 200	88.61 338	96.11 136	83.14 197	89.58 116	86.93 298	83.83 47	96.87 219	88.22 139	85.92 211	97.42 130

mPP-MVS		91.88 76	91.82 72	92.07 131	98.38 44	78.63 213	97.29 112	96.09 137	85.12 145	88.45 135	97.66 74	75.53 146	99.68 51	89.83 118	98.02 56	97.88 93

APD-MVS		93.61 37	93.59 38	93.69 59	98.76 24	83.26 101	97.21 114	96.09 137	82.41 216	94.65 49	98.21 38	81.96 59	98.81 119	94.65 58	98.36 46	99.01 28
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MDTV_nov1_ep13			83.69 215		94.09 173	81.01 147	86.78 353	96.09 137	83.81 185	84.75 172	84.32 337	74.44 171	96.54 232	63.88 329	85.07 220

FA-MVS(test-final)		87.71 172	86.23 179	92.17 127	94.19 167	80.55 161	87.16 350	96.07 140	82.12 221	85.98 160	88.35 276	72.04 199	98.49 131	80.26 207	89.87 168	97.48 128

QAPM		86.88 182	84.51 203	93.98 46	94.04 175	85.89 41	97.19 117	96.05 141	73.62 328	75.12 288	95.62 144	62.02 262	99.74 38	70.88 294	96.06 104	96.30 180

MP-MVS-pluss		92.58 61	92.35 60	93.29 76	97.30 86	82.53 111	96.44 178	96.04 142	84.68 157	89.12 123	98.37 31	77.48 110	99.74 38	93.31 75	98.38 44	97.59 118
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.1_n_a		92.38 66	92.49 58	92.06 132	88.08 309	81.62 137	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	94.86 211

fmvsm_l_conf0.5_n_a		94.91 15	95.30 15	93.72 58	94.50 159	84.30 81	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	97.08 150

tpm2		87.35 177	86.26 178	90.62 179	92.93 209	78.67 212	88.06 343	95.99 145	79.33 272	87.40 145	86.43 309	80.28 70	96.40 236	80.23 208	85.73 215	96.79 161

SDMVSNet		87.02 179	85.61 184	91.24 160	94.14 170	83.30 100	93.88 277	95.98 146	84.30 169	79.63 235	92.01 221	58.23 288	97.68 167	90.28 116	82.02 244	92.75 241

DeepC-MVS	86.58 3	91.53 85	91.06 88	92.94 91	94.52 155	81.89 125	95.95 205	95.98 146	90.76 41	83.76 186	96.76 119	73.24 186	99.71 45	91.67 94	96.96 84	97.22 142
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test-LLR		88.48 152	87.98 144	89.98 196	92.26 227	77.23 255	97.11 129	95.96 148	83.76 187	86.30 157	91.38 233	72.30 195	96.78 225	80.82 201	91.92 157	95.94 185

test-mter		88.95 136	88.60 134	89.98 196	92.26 227	77.23 255	97.11 129	95.96 148	85.32 138	86.30 157	91.38 233	76.37 131	96.78 225	80.82 201	91.92 157	95.94 185

DP-MVS Recon		91.72 80	90.85 89	94.34 34	99.50 1	85.00 69	98.51 36	95.96 148	80.57 244	88.08 141	97.63 80	76.84 120	99.89 7	85.67 158	94.88 117	98.13 76

cdsmvs_eth3d_5k		21.43 372	28.57 375	0.00 391	0.00 414	0.00 416	0.00 402	95.93 151	0.00 409	0.00 410	97.66 74	63.57 252	0.00 410	0.00 409	0.00 408	0.00 406

hse-mvs2		88.22 162	88.21 140	88.25 233	93.54 186	73.41 299	95.41 231	95.89 152	90.39 48	92.22 77	94.22 186	74.70 165	96.66 230	93.14 77	64.37 355	94.69 219

AUN-MVS		86.25 194	85.57 185	88.26 232	93.57 185	73.38 300	95.45 229	95.88 153	83.94 180	85.47 163	94.21 187	73.70 182	96.67 229	83.54 183	64.41 354	94.73 218

TAMVS		88.48 152	87.79 148	90.56 181	91.09 261	79.18 198	96.45 177	95.88 153	83.64 190	83.12 192	93.33 205	75.94 138	95.74 271	82.40 193	88.27 188	96.75 165

PVSNet_Blended_VisFu		91.24 92	90.77 91	92.66 102	95.09 136	82.40 115	97.77 73	95.87 155	88.26 77	86.39 155	93.94 194	76.77 123	99.27 84	88.80 131	94.00 130	96.31 179

OpenMVS	79.58 14	86.09 195	83.62 219	93.50 70	90.95 263	86.71 32	97.44 100	95.83 156	75.35 314	72.64 309	95.72 139	57.42 301	99.64 55	71.41 288	95.85 109	94.13 225

CDS-MVSNet		89.50 127	88.96 128	91.14 165	91.94 246	80.93 151	97.09 133	95.81 157	84.26 172	84.72 173	94.20 188	80.31 69	95.64 276	83.37 186	88.96 178	96.85 160
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	95.65 121	92.35 2	98.21 45	95.79 158	92.42 23	96.24 27	98.18 40	71.04 209	99.17 95	96.77 33	97.39 76	96.79 161

testing3		80.74 281	81.17 257	79.44 346	91.15 260	63.48 364	97.16 123	95.76 159	80.83 237	71.36 316	93.15 209	78.22 97	87.30 380	43.19 387	79.67 258	87.55 328

SR-MVS		92.16 68	92.27 62	91.83 143	98.37 45	78.41 219	96.67 165	95.76 159	82.19 220	91.97 80	98.07 51	76.44 128	98.64 123	93.71 68	97.27 79	98.45 56

3Dnovator+	82.88 8	89.63 126	87.85 146	94.99 21	94.49 160	86.76 31	97.84 68	95.74 161	86.10 122	75.47 285	96.02 133	65.00 245	99.51 71	82.91 191	97.07 83	98.72 42

HPM-MVS		91.62 83	91.53 78	91.89 139	97.88 63	79.22 197	96.99 137	95.73 162	82.07 222	89.50 119	97.19 101	75.59 144	98.93 114	90.91 100	97.94 59	97.54 120
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ab-mvs		87.08 178	84.94 198	93.48 72	93.34 195	83.67 92	88.82 335	95.70 163	81.18 232	84.55 176	90.14 256	62.72 256	98.94 113	85.49 160	82.54 240	97.85 97

xiu_mvs_v2_base		93.92 34	93.26 44	95.91 10	95.07 138	92.02 6	98.19 46	95.68 164	92.06 27	96.01 31	98.14 44	70.83 212	98.96 109	96.74 35	96.57 95	96.76 164

CP-MVSNet		81.01 278	80.08 272	83.79 316	87.91 312	70.51 330	94.29 269	95.65 165	80.83 237	72.54 311	88.84 268	63.71 251	92.32 346	68.58 307	68.36 331	88.55 302

PatchmatchNet		86.83 184	85.12 195	91.95 137	94.12 172	82.27 117	86.55 355	95.64 166	84.59 160	82.98 195	84.99 332	77.26 112	95.96 256	68.61 306	91.34 162	97.64 114
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
API-MVS		90.18 116	88.97 127	93.80 52	98.66 28	82.95 106	97.50 96	95.63 167	75.16 317	86.31 156	97.69 72	72.49 192	99.90 5	81.26 200	96.07 103	98.56 49

AdaColmap		88.81 142	87.61 154	92.39 114	99.33 4	79.95 176	96.70 164	95.58 168	77.51 297	83.05 194	96.69 123	61.90 265	99.72 43	84.29 168	93.47 138	97.50 126

SCA		85.63 203	83.64 218	91.60 151	92.30 225	81.86 127	92.88 300	95.56 169	84.85 151	82.52 196	85.12 330	58.04 291	95.39 286	73.89 273	87.58 196	97.54 120

dp		84.30 226	82.31 240	90.28 188	94.24 166	77.97 234	86.57 354	95.53 170	79.94 262	80.75 221	85.16 328	71.49 205	96.39 237	63.73 330	83.36 229	96.48 172

HyFIR lowres test		89.36 129	88.60 134	91.63 150	94.91 144	80.76 156	95.60 224	95.53 170	82.56 213	84.03 179	91.24 237	78.03 100	96.81 223	87.07 150	88.41 186	97.32 136

APD-MVS_3200maxsize		91.23 93	91.35 80	90.89 172	97.89 62	76.35 270	96.30 188	95.52 172	79.82 263	91.03 97	97.88 65	74.70 165	98.54 128	92.11 89	96.89 86	97.77 104

lupinMVS		93.87 35	93.58 39	94.75 27	93.00 204	88.08 17	99.15 8	95.50 173	91.03 39	94.90 44	97.66 74	78.84 88	97.56 174	94.64 59	97.46 71	98.62 47

tt0805		81.20 276	79.06 284	87.61 247	86.50 324	72.97 308	93.66 280	95.48 174	74.11 324	76.23 272	91.99 223	41.36 367	97.40 188	77.44 238	74.78 288	92.45 244

HPM-MVS_fast		90.38 114	90.17 108	91.03 167	97.61 70	77.35 253	97.15 125	95.48 174	79.51 269	88.79 129	96.90 111	71.64 203	98.81 119	87.01 151	97.44 73	96.94 154

VPNet		84.69 218	82.92 230	90.01 194	89.01 298	83.45 97	96.71 162	95.46 176	85.71 130	79.65 234	92.18 220	56.66 307	96.01 252	83.05 190	67.84 338	90.56 255

114514_t		88.79 144	87.57 155	92.45 110	98.21 53	81.74 132	96.99 137	95.45 177	75.16 317	82.48 197	95.69 141	68.59 222	98.50 130	80.33 205	95.18 115	97.10 149

SR-MVS-dyc-post		91.29 91	91.45 79	90.80 174	97.76 67	76.03 275	96.20 195	95.44 178	80.56 245	90.72 101	97.84 66	75.76 141	98.61 124	91.99 90	96.79 90	97.75 105

RE-MVS-def			91.18 86		97.76 67	76.03 275	96.20 195	95.44 178	80.56 245	90.72 101	97.84 66	73.36 185		91.99 90	96.79 90	97.75 105

JIA-IIPM		79.00 297	77.20 296	84.40 311	89.74 289	64.06 361	75.30 388	95.44 178	62.15 370	81.90 209	59.08 392	78.92 86	95.59 280	66.51 318	85.78 214	93.54 235

RPMNet		79.85 287	75.92 306	91.64 148	90.16 280	79.75 182	79.02 380	95.44 178	58.43 386	82.27 205	72.55 383	73.03 187	98.41 138	46.10 384	86.25 206	96.75 165

DU-MVS		84.57 221	83.33 225	88.28 231	88.76 299	79.36 193	96.43 180	95.41 182	85.42 136	78.11 248	90.82 243	67.61 223	95.14 300	79.14 220	68.30 332	90.33 260

EI-MVSNet		85.80 200	85.20 191	87.59 249	91.55 251	77.41 251	95.13 244	95.36 183	80.43 250	80.33 227	94.71 176	73.72 180	95.97 253	76.96 243	78.64 268	89.39 276

MVSTER		89.25 133	88.92 130	90.24 189	95.98 110	84.66 75	96.79 156	95.36 183	87.19 105	80.33 227	90.61 247	90.02 12	95.97 253	85.38 161	78.64 268	90.09 267

CPTT-MVS		89.72 124	89.87 117	89.29 211	98.33 47	73.30 302	97.70 79	95.35 185	75.68 313	87.40 145	97.44 90	70.43 214	98.25 144	89.56 123	96.90 85	96.33 178

EIA-MVS		91.73 78	92.05 69	90.78 176	94.52 155	76.40 269	98.06 56	95.34 186	89.19 62	88.90 127	97.28 98	77.56 108	97.73 166	90.77 103	96.86 89	98.20 70

tpmvs		83.04 248	80.77 261	89.84 202	95.43 125	77.96 235	85.59 361	95.32 187	75.31 316	76.27 271	83.70 342	73.89 177	97.41 187	59.53 344	81.93 246	94.14 224

PS-CasMVS		80.27 285	79.18 281	83.52 322	87.56 316	69.88 335	94.08 272	95.29 188	80.27 255	72.08 313	88.51 275	59.22 282	92.23 348	67.49 309	68.15 334	88.45 308

TSAR-MVS + GP.		94.35 25	94.50 23	93.89 49	97.38 84	83.04 105	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 22

tpmrst		88.36 156	87.38 161	91.31 156	94.36 163	79.92 177	87.32 348	95.26 190	85.32 138	88.34 137	86.13 314	80.60 67	96.70 227	83.78 175	85.34 219	97.30 139

ETV-MVS		92.72 55	92.87 50	92.28 121	94.54 154	81.89 125	97.98 60	95.21 191	89.77 57	93.11 67	96.83 115	77.23 116	97.50 182	95.74 45	95.38 114	97.44 129

NR-MVSNet		83.35 240	81.52 253	88.84 219	88.76 299	81.31 142	94.45 260	95.16 192	84.65 158	67.81 334	90.82 243	70.36 215	94.87 309	74.75 264	66.89 347	90.33 260

test_fmvsmconf0.1_n		93.08 45	93.22 46	92.65 103	88.45 305	80.81 154	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	97.54 120

jason		92.73 53	92.23 64	94.21 41	90.50 274	87.30 26	98.65 31	95.09 194	90.61 44	92.76 72	97.13 103	75.28 157	97.30 194	93.32 74	96.75 92	98.02 81
jason: jason.
tpm cat1		83.63 237	81.38 254	90.39 185	93.53 191	78.19 230	85.56 362	95.09 194	70.78 348	78.51 244	83.28 345	74.80 164	97.03 208	66.77 313	84.05 224	95.95 184

cascas		86.50 188	84.48 205	92.55 108	92.64 217	85.95 38	97.04 136	95.07 196	75.32 315	80.50 223	91.02 240	54.33 322	97.98 153	86.79 153	87.62 194	93.71 233

CVMVSNet		84.83 216	85.57 185	82.63 329	91.55 251	60.38 374	95.13 244	95.03 197	80.60 243	82.10 207	94.71 176	66.40 236	90.19 368	74.30 270	90.32 166	97.31 138

test0.0.03 1		82.79 252	82.48 238	83.74 318	86.81 322	72.22 311	96.52 171	95.03 197	83.76 187	73.00 305	93.20 206	72.30 195	88.88 371	64.15 328	77.52 277	90.12 264

PMMVS		89.46 128	89.92 115	88.06 237	94.64 149	69.57 339	96.22 192	94.95 199	87.27 101	91.37 90	96.54 125	65.88 237	97.39 189	88.54 133	93.89 131	97.23 141

CS-MVS		92.73 53	93.48 41	90.48 183	96.27 100	75.93 280	98.55 35	94.93 200	89.32 60	94.54 51	97.67 73	78.91 87	97.02 209	93.80 66	97.32 78	98.49 53

Anonymous20240529		83.15 245	80.60 265	90.80 174	95.74 119	78.27 223	96.81 155	94.92 201	60.10 381	81.89 210	92.54 216	45.82 352	98.82 118	79.25 219	78.32 274	95.31 202

mvs_anonymous		88.68 145	87.62 153	91.86 140	94.80 147	81.69 135	93.53 285	94.92 201	82.03 223	78.87 242	90.43 250	75.77 140	95.34 289	85.04 163	93.16 143	98.55 51

CLD-MVS		87.97 167	87.48 158	89.44 209	92.16 234	80.54 163	98.14 47	94.92 201	91.41 33	79.43 237	95.40 150	62.34 258	97.27 197	90.60 106	82.90 235	90.50 257
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		90.54 109	89.54 120	93.55 67	92.31 222	87.58 23	96.99 137	94.87 204	87.23 102	93.27 63	97.56 83	57.43 298	98.32 140	92.72 82	93.46 139	94.74 215

xiu_mvs_v1_base		90.54 109	89.54 120	93.55 67	92.31 222	87.58 23	96.99 137	94.87 204	87.23 102	93.27 63	97.56 83	57.43 298	98.32 140	92.72 82	93.46 139	94.74 215

xiu_mvs_v1_base_debi		90.54 109	89.54 120	93.55 67	92.31 222	87.58 23	96.99 137	94.87 204	87.23 102	93.27 63	97.56 83	57.43 298	98.32 140	92.72 82	93.46 139	94.74 215

GA-MVS		85.79 201	84.04 213	91.02 168	89.47 294	80.27 169	96.90 149	94.84 207	85.57 132	80.88 219	89.08 264	56.56 308	96.47 235	77.72 231	85.35 218	96.34 176

TranMVSNet+NR-MVSNet		83.24 244	81.71 249	87.83 241	87.71 314	78.81 209	96.13 200	94.82 208	84.52 161	76.18 274	90.78 245	64.07 250	94.60 317	74.60 268	66.59 349	90.09 267

HQP3-MVS								94.80 209							83.01 232

HQP-MVS		87.91 169	87.55 156	88.98 217	92.08 238	78.48 215	97.63 83	94.80 209	90.52 45	82.30 201	94.56 179	65.40 241	97.32 192	87.67 144	83.01 232	91.13 249

TAPA-MVS	81.61 12	85.02 213	83.67 216	89.06 214	96.79 92	73.27 305	95.92 207	94.79 211	74.81 320	80.47 224	96.83 115	71.07 208	98.19 148	49.82 377	92.57 148	95.71 191
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PEN-MVS		79.47 293	78.26 289	83.08 325	86.36 326	68.58 343	93.85 278	94.77 212	79.76 264	71.37 315	88.55 272	59.79 274	92.46 344	64.50 326	65.40 351	88.19 313

CS-MVS-test		92.98 46	93.67 36	90.90 171	96.52 94	76.87 260	98.68 29	94.73 213	90.36 50	94.84 46	97.89 64	77.94 101	97.15 205	94.28 63	97.80 63	98.70 43

HQP_MVS		87.50 175	87.09 168	88.74 222	91.86 247	77.96 235	97.18 119	94.69 214	89.89 55	81.33 215	94.15 189	64.77 247	97.30 194	87.08 148	82.82 236	90.96 251

plane_prior5								94.69 214					97.30 194	87.08 148	82.82 236	90.96 251

tpm		85.55 205	84.47 206	88.80 221	90.19 279	75.39 285	88.79 336	94.69 214	84.83 152	83.96 182	85.21 326	78.22 97	94.68 316	76.32 251	78.02 276	96.34 176

FMVSNet3		84.71 217	82.71 235	90.70 178	94.55 153	87.71 21	95.92 207	94.67 217	81.73 227	75.82 280	88.08 281	66.99 231	94.47 320	71.23 290	75.38 285	89.91 271

UA-Net		88.92 138	88.48 137	90.24 189	94.06 174	77.18 257	93.04 297	94.66 218	87.39 98	91.09 95	93.89 195	74.92 162	98.18 149	75.83 255	91.43 161	95.35 201

LFMVS		89.27 132	87.64 151	94.16 44	97.16 88	85.52 51	97.18 119	94.66 218	79.17 277	89.63 115	96.57 124	55.35 315	98.22 146	89.52 124	89.54 170	98.74 37

MVS_Test		90.29 115	89.18 124	93.62 63	95.23 131	84.93 70	94.41 261	94.66 218	84.31 167	90.37 107	91.02 240	75.13 159	97.82 163	83.11 189	94.42 124	98.12 77

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		86.44 189	84.51 203	92.22 124	91.56 250	81.83 128	97.10 132	94.64 221	69.50 354	87.84 142	95.19 160	48.01 341	97.92 159	89.82 119	86.92 199	96.89 158

baseline1		88.85 141	87.49 157	92.93 92	95.21 133	86.85 29	95.47 228	94.61 223	87.29 100	83.11 193	94.99 170	80.70 66	96.89 217	82.28 194	73.72 292	95.05 207

PatchT		79.75 288	76.85 300	88.42 226	89.55 292	75.49 284	77.37 384	94.61 223	63.07 367	82.46 198	73.32 380	75.52 147	93.41 339	51.36 371	84.43 222	96.36 174

MS-PatchMatch		83.05 247	81.82 248	86.72 272	89.64 290	79.10 202	94.88 253	94.59 225	79.70 266	70.67 322	89.65 260	50.43 333	96.82 222	70.82 297	95.99 107	84.25 362

casdiffmvs_mvg		91.13 95	90.45 99	93.17 82	92.99 207	83.58 94	97.46 99	94.56 226	87.69 90	87.19 150	94.98 171	74.50 170	97.60 171	91.88 93	92.79 146	98.34 60
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		90.76 105	90.10 109	92.74 99	92.90 210	82.56 110	94.60 258	94.56 226	87.69 90	89.06 125	95.67 142	73.76 179	97.51 181	90.43 111	92.23 155	98.16 73

OMC-MVS		88.80 143	88.16 142	90.72 177	95.30 129	77.92 238	94.81 255	94.51 228	86.80 113	84.97 168	96.85 114	67.53 226	98.60 125	85.08 162	87.62 194	95.63 192

MVSFormer		91.36 89	90.57 95	93.73 57	93.00 204	88.08 17	94.80 256	94.48 229	80.74 240	94.90 44	97.13 103	78.84 88	95.10 303	83.77 176	97.46 71	98.02 81

test_djsdf		83.00 250	82.45 239	84.64 305	84.07 356	69.78 336	94.80 256	94.48 229	80.74 240	75.41 286	87.70 285	61.32 269	95.10 303	83.77 176	79.76 255	89.04 291

casdiffmvs		90.95 102	90.39 100	92.63 105	92.82 211	82.53 111	96.83 152	94.47 231	87.69 90	88.47 134	95.56 147	74.04 176	97.54 178	90.90 101	92.74 147	97.83 99
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	86.77 186	85.00 197	92.08 130	92.06 241	83.07 104	92.14 308	94.47 231	79.63 267	76.90 260	94.78 175	71.15 207	99.20 92	72.87 279	91.05 163	93.98 228
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VDD-MVS		88.28 160	87.02 170	92.06 132	95.09 136	80.18 173	97.55 91	94.45 233	83.09 198	89.10 124	95.92 136	47.97 342	98.49 131	93.08 80	86.91 200	97.52 125

test_cas_vis1_n_1920		89.90 121	90.02 111	89.54 208	90.14 282	74.63 291	98.71 28	94.43 234	93.04 19	92.40 73	96.35 127	53.41 324	99.08 103	95.59 48	96.16 100	94.90 209

PLC	83.97 7	88.00 166	87.38 161	89.83 203	98.02 59	76.46 267	97.16 123	94.43 234	79.26 276	81.98 208	96.28 128	69.36 219	99.27 84	77.71 232	92.25 154	93.77 232
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EC-MVSNet		91.73 78	92.11 67	90.58 180	93.54 186	77.77 244	98.07 55	94.40 236	87.44 96	92.99 70	97.11 105	74.59 169	96.87 219	93.75 67	97.08 82	97.11 148

sd_testset		84.62 219	83.11 228	89.17 212	94.14 170	77.78 243	91.54 318	94.38 237	84.30 169	79.63 235	92.01 221	52.28 326	96.98 211	77.67 233	82.02 244	92.75 241

FMVSNet2		82.79 252	80.44 267	89.83 203	92.66 214	85.43 53	95.42 230	94.35 238	79.06 280	74.46 292	87.28 290	56.38 310	94.31 323	69.72 302	74.68 289	89.76 273

test_vis1_n_1920		89.95 120	90.59 94	88.03 239	92.36 221	68.98 342	99.12 12	94.34 239	93.86 13	93.64 61	97.01 109	51.54 328	99.59 60	96.76 34	96.71 94	95.53 196

nrg030		86.79 185	85.43 187	90.87 173	88.76 299	85.34 54	97.06 135	94.33 240	84.31 167	80.45 225	91.98 224	72.36 193	96.36 239	88.48 136	71.13 305	90.93 253

RRT_MVS		83.88 232	83.27 226	85.71 286	87.53 318	72.12 315	95.35 233	94.33 240	83.81 185	75.86 279	91.28 236	60.55 271	95.09 305	83.93 172	76.76 279	89.90 272

ACMM	80.70 13	83.72 236	82.85 233	86.31 277	91.19 258	72.12 315	95.88 210	94.29 242	80.44 248	77.02 258	91.96 225	55.24 316	97.14 206	79.30 218	80.38 253	89.67 274
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XXY-MVS		83.84 233	82.00 245	89.35 210	87.13 320	81.38 140	95.72 217	94.26 243	80.15 257	75.92 278	90.63 246	61.96 264	96.52 233	78.98 222	73.28 297	90.14 263

Syy-MVS		77.97 304	78.05 290	77.74 353	92.13 235	56.85 380	93.97 274	94.23 244	82.43 214	73.39 298	93.57 202	57.95 294	87.86 375	32.40 393	82.34 241	88.51 303

myMVS_eth3d		81.93 265	82.18 241	81.18 337	92.13 235	67.18 349	93.97 274	94.23 244	82.43 214	73.39 298	93.57 202	76.98 118	87.86 375	50.53 375	82.34 241	88.51 303

cl22		85.11 212	84.17 210	87.92 240	95.06 140	78.82 207	95.51 226	94.22 246	79.74 265	76.77 261	87.92 283	75.96 137	95.68 272	79.93 212	72.42 299	89.27 283

OPM-MVS		85.84 199	85.10 196	88.06 237	88.34 306	77.83 242	95.72 217	94.20 247	87.89 86	80.45 225	94.05 191	58.57 285	97.26 198	83.88 173	82.76 238	89.09 288
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet (Re-imp)		88.88 140	88.87 132	88.91 218	93.89 178	74.43 294	96.93 147	94.19 248	84.39 165	83.22 191	95.67 142	78.24 96	94.70 314	78.88 223	94.40 125	97.61 117

Anonymous20231211		79.72 289	77.19 297	87.33 257	95.59 122	77.16 258	95.18 243	94.18 249	59.31 384	72.57 310	86.20 313	47.89 344	95.66 273	74.53 269	69.24 324	89.18 285

PS-MVSNAJss		84.91 215	84.30 208	86.74 268	85.89 336	74.40 295	94.95 251	94.16 250	83.93 181	76.45 266	90.11 257	71.04 209	95.77 266	83.16 188	79.02 265	90.06 269

LPG-MVS_test		84.20 227	83.49 223	86.33 274	90.88 264	73.06 306	95.28 234	94.13 251	82.20 218	76.31 268	93.20 206	54.83 320	96.95 213	83.72 178	80.83 250	88.98 294

LGP-MVS_train				86.33 274	90.88 264	73.06 306		94.13 251	82.20 218	76.31 268	93.20 206	54.83 320	96.95 213	83.72 178	80.83 250	88.98 294

V42		83.04 248	81.53 252	87.57 251	86.27 329	79.09 203	95.87 211	94.11 253	80.35 252	77.22 256	86.79 301	65.32 243	96.02 251	77.74 230	70.14 312	87.61 324

XVG-OURS-SEG-HR		85.74 202	85.16 194	87.49 255	90.22 278	71.45 326	91.29 319	94.09 254	81.37 230	83.90 184	95.22 157	60.30 273	97.53 180	85.58 159	84.42 223	93.50 236

XVG-OURS		85.18 210	84.38 207	87.59 249	90.42 276	71.73 323	91.06 322	94.07 255	82.00 224	83.29 190	95.08 167	56.42 309	97.55 176	83.70 180	83.42 228	93.49 237

miper_enhance_ethall		85.95 198	85.20 191	88.19 236	94.85 146	79.76 181	96.00 202	94.06 256	82.98 203	77.74 251	88.76 269	79.42 78	95.46 285	80.58 203	72.42 299	89.36 281

v2v482		83.46 239	81.86 247	88.25 233	86.19 330	79.65 187	96.34 186	94.02 257	81.56 229	77.32 254	88.23 278	65.62 238	96.03 249	77.77 229	69.72 320	89.09 288

jajsoiax		82.12 263	81.15 258	85.03 299	84.19 354	70.70 329	94.22 270	93.95 258	83.07 199	73.48 297	89.75 259	49.66 337	95.37 288	82.24 195	79.76 255	89.02 292

test_fmvsmconf0.01_n		91.08 97	90.68 93	92.29 120	82.43 364	80.12 174	97.94 63	93.93 259	92.07 26	91.97 80	97.60 81	67.56 225	99.53 68	97.09 29	95.56 113	97.21 144

v1144		82.90 251	81.27 256	87.78 243	86.29 328	79.07 204	96.14 198	93.93 259	80.05 259	77.38 252	86.80 300	65.50 239	95.93 258	75.21 261	70.13 313	88.33 311

KD-MVS_2432*1600		77.63 307	74.92 312	85.77 284	90.86 267	79.44 190	88.08 341	93.92 261	76.26 309	67.05 338	82.78 347	72.15 197	91.92 351	61.53 337	41.62 394	85.94 350

miper_refine_blended		77.63 307	74.92 312	85.77 284	90.86 267	79.44 190	88.08 341	93.92 261	76.26 309	67.05 338	82.78 347	72.15 197	91.92 351	61.53 337	41.62 394	85.94 350

test_fmvsmvis_n_1920		92.12 69	92.10 68	92.17 127	90.87 266	81.04 146	98.34 41	93.90 263	92.71 20	87.24 149	97.90 63	74.83 163	99.72 43	96.96 31	96.20 99	95.76 190

UnsupCasMVSNet_eth		73.25 331	70.57 336	81.30 335	77.53 378	66.33 354	87.24 349	93.89 264	80.38 251	57.90 377	81.59 352	42.91 362	90.56 365	65.18 324	48.51 385	87.01 335

v7n		79.32 295	77.34 295	85.28 295	84.05 357	72.89 310	93.38 287	93.87 265	75.02 319	70.68 321	84.37 336	59.58 277	95.62 278	67.60 308	67.50 341	87.32 332

dcpmvs_2		93.10 44	93.46 42	92.02 135	97.77 65	79.73 185	94.82 254	93.86 266	86.91 109	91.33 91	96.76 119	85.20 31	98.06 150	96.90 32	97.60 68	98.27 68

Vis-MVSNet		88.67 146	87.82 147	91.24 160	92.68 213	78.82 207	96.95 145	93.85 267	87.55 93	87.07 152	95.13 164	63.43 253	97.21 199	77.58 235	96.15 101	97.70 110
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v148		82.41 260	80.89 259	86.99 266	86.18 331	76.81 262	96.27 189	93.82 268	80.49 247	75.28 287	86.11 315	67.32 229	95.75 268	75.48 259	67.03 346	88.42 309

BH-w/o		88.24 161	87.47 159	90.54 182	95.03 141	78.54 214	97.41 105	93.82 268	84.08 174	78.23 247	94.51 181	69.34 220	97.21 199	80.21 209	94.58 122	95.87 187

TR-MVS		86.30 192	84.93 199	90.42 184	94.63 150	77.58 248	96.57 168	93.82 268	80.30 253	82.42 199	95.16 162	58.74 284	97.55 176	74.88 263	87.82 193	96.13 183

v1192		82.31 261	80.55 266	87.60 248	85.94 334	78.47 218	95.85 213	93.80 271	79.33 272	76.97 259	86.51 304	63.33 254	95.87 261	73.11 278	70.13 313	88.46 307

ACMP	81.66 11	84.00 230	83.22 227	86.33 274	91.53 253	72.95 309	95.91 209	93.79 272	83.70 189	73.79 295	92.22 219	54.31 323	96.89 217	83.98 171	79.74 257	89.16 286
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v144192		82.43 257	80.73 262	87.54 252	85.81 337	78.22 225	95.98 203	93.78 273	79.09 279	77.11 257	86.49 305	64.66 249	95.91 259	74.20 271	69.42 321	88.49 305

mvs_tets		81.74 267	80.71 263	84.84 300	84.22 353	70.29 332	93.91 276	93.78 273	82.77 208	73.37 300	89.46 262	47.36 347	95.31 292	81.99 196	79.55 261	88.92 298

F-COLMAP		84.50 223	83.44 224	87.67 245	95.22 132	72.22 311	95.95 205	93.78 273	75.74 312	76.30 270	95.18 161	59.50 278	98.45 135	72.67 281	86.59 203	92.35 246

UniMVSNet_ETH3D		80.86 280	78.75 286	87.22 262	86.31 327	72.02 317	91.95 309	93.76 276	73.51 329	75.06 289	90.16 255	43.04 361	95.66 273	76.37 250	78.55 271	93.98 228

Fast-Effi-MVS+		87.93 168	86.94 172	90.92 170	94.04 175	79.16 199	98.26 43	93.72 277	81.29 231	83.94 183	92.90 211	69.83 218	96.68 228	76.70 245	91.74 159	96.93 155

v1921920		82.02 264	80.23 270	87.41 256	85.62 338	77.92 238	95.79 216	93.69 278	78.86 283	76.67 262	86.44 307	62.50 257	95.83 263	72.69 280	69.77 319	88.47 306

DTE-MVSNet		78.37 299	77.06 298	82.32 332	85.22 345	67.17 352	93.40 286	93.66 279	78.71 285	70.53 323	88.29 277	59.06 283	92.23 348	61.38 340	63.28 360	87.56 326

v8		81.88 266	80.06 274	87.32 258	86.63 323	79.04 205	94.41 261	93.65 280	78.77 284	73.19 304	85.57 320	66.87 232	95.81 264	73.84 275	67.61 340	87.11 333

diffmvs		91.17 94	90.74 92	92.44 112	93.11 203	82.50 113	96.25 191	93.62 281	87.79 87	90.40 106	95.93 134	73.44 184	97.42 186	93.62 70	92.55 149	97.41 131
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		81.26 274	78.36 287	89.96 198	93.78 179	79.78 180	79.48 376	93.60 282	73.09 334	80.14 229	79.99 361	62.15 260	95.24 295	59.49 345	83.52 226	94.85 212

PatchMatch-RL		85.00 214	83.66 217	89.02 216	95.86 114	74.55 293	92.49 304	93.60 282	79.30 274	79.29 239	91.47 231	58.53 286	98.45 135	70.22 299	92.17 156	94.07 227

anonymousdsp		80.98 279	79.97 275	84.01 313	81.73 366	70.44 331	92.49 304	93.58 284	77.10 304	72.98 306	86.31 311	57.58 297	94.90 308	79.32 217	78.63 270	86.69 338

CL-MVSNet_self_test		75.81 319	74.14 321	80.83 340	78.33 376	67.79 346	94.22 270	93.52 285	77.28 301	69.82 327	81.54 353	61.47 268	89.22 370	57.59 353	53.51 376	85.48 354

miper_ehance_all_eth		84.57 221	83.60 220	87.50 253	92.64 217	78.25 224	95.40 232	93.47 286	79.28 275	76.41 267	87.64 286	76.53 126	95.24 295	78.58 225	72.42 299	89.01 293

v1240		81.70 268	79.83 278	87.30 260	85.50 339	77.70 247	95.48 227	93.44 287	78.46 288	76.53 265	86.44 307	60.85 270	95.84 262	71.59 287	70.17 311	88.35 310

v10		81.43 272	79.53 280	87.11 263	86.38 325	78.87 206	94.31 265	93.43 288	77.88 292	73.24 303	85.26 324	65.44 240	95.75 268	72.14 284	67.71 339	86.72 337

IterMVS-LS		83.93 231	82.80 234	87.31 259	91.46 254	77.39 252	95.66 220	93.43 288	80.44 248	75.51 284	87.26 292	73.72 180	95.16 299	76.99 241	70.72 309	89.39 276
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		82.42 258	80.43 268	88.39 228	92.66 214	81.95 120	94.30 266	93.38 290	79.06 280	75.82 280	85.66 316	56.38 310	93.84 330	71.23 290	75.38 285	89.38 278

test1		82.42 258	80.43 268	88.39 228	92.66 214	81.95 120	94.30 266	93.38 290	79.06 280	75.82 280	85.66 316	56.38 310	93.84 330	71.23 290	75.38 285	89.38 278

FMVSNet1		79.50 292	76.54 302	88.39 228	88.47 304	81.95 120	94.30 266	93.38 290	73.14 333	72.04 314	85.66 316	43.86 355	93.84 330	65.48 322	72.53 298	89.38 278

BH-untuned		86.95 181	85.94 181	89.99 195	94.52 155	77.46 250	96.78 157	93.37 293	81.80 225	76.62 264	93.81 198	66.64 234	97.02 209	76.06 252	93.88 132	95.48 198

Effi-MVS+-dtu		84.61 220	84.90 200	83.72 319	91.96 244	63.14 366	94.95 251	93.34 294	85.57 132	79.79 233	87.12 295	61.99 263	95.61 279	83.55 182	85.83 213	92.41 245

CMPMVS	54.94 21	75.71 321	74.56 316	79.17 348	79.69 372	55.98 382	89.59 329	93.30 295	60.28 379	53.85 383	89.07 265	47.68 346	96.33 240	76.55 246	81.02 248	85.22 355
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
cl____		83.27 242	82.12 242	86.74 268	92.20 230	75.95 279	95.11 246	93.27 296	78.44 289	74.82 290	87.02 297	74.19 173	95.19 297	74.67 266	69.32 322	89.09 288

DIV-MVS_self_test		83.27 242	82.12 242	86.74 268	92.19 231	75.92 281	95.11 246	93.26 297	78.44 289	74.81 291	87.08 296	74.19 173	95.19 297	74.66 267	69.30 323	89.11 287

dmvs_re		84.10 228	82.90 231	87.70 244	91.41 255	73.28 303	90.59 325	93.19 298	85.02 147	77.96 250	93.68 199	57.92 296	96.18 246	75.50 258	80.87 249	93.63 234

miper_lstm_enhance		81.66 270	80.66 264	84.67 304	91.19 258	71.97 319	91.94 310	93.19 298	77.86 293	72.27 312	85.26 324	73.46 183	93.42 338	73.71 276	67.05 345	88.61 301

eth_miper_zixun_eth		83.12 246	82.01 244	86.47 273	91.85 249	74.80 289	94.33 264	93.18 300	79.11 278	75.74 283	87.25 293	72.71 189	95.32 291	76.78 244	67.13 344	89.27 283

pmmvs4		82.54 256	80.79 260	87.79 242	86.11 332	80.49 165	93.55 284	93.18 300	77.29 300	73.35 301	89.40 263	65.26 244	95.05 307	75.32 260	73.61 293	87.83 319

XVG-ACMP-BASELINE		79.38 294	77.90 292	83.81 315	84.98 347	67.14 353	89.03 334	93.18 300	80.26 256	72.87 307	88.15 280	38.55 372	96.26 242	76.05 253	78.05 275	88.02 316

CANet_DTU		90.98 100	90.04 110	93.83 51	94.76 148	86.23 34	96.32 187	93.12 303	93.11 18	93.71 59	96.82 117	63.08 255	99.48 73	84.29 168	95.12 116	95.77 189

IS-MVSNet		88.67 146	88.16 142	90.20 191	93.61 183	76.86 261	96.77 159	93.07 304	84.02 176	83.62 187	95.60 145	74.69 168	96.24 244	78.43 227	93.66 136	97.49 127

c3_l		83.80 234	82.65 236	87.25 261	92.10 237	77.74 246	95.25 237	93.04 305	78.58 286	76.01 275	87.21 294	75.25 158	95.11 302	77.54 236	68.89 326	88.91 299

UnsupCasMVSNet_bld		68.60 348	64.50 352	80.92 339	74.63 387	67.80 345	83.97 368	92.94 306	65.12 365	54.63 382	68.23 388	35.97 377	92.17 350	60.13 343	44.83 389	82.78 369

MVP-Stereo		82.65 255	81.67 250	85.59 291	86.10 333	78.29 222	93.33 289	92.82 307	77.75 294	69.17 332	87.98 282	59.28 281	95.76 267	71.77 285	96.88 87	82.73 370
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Effi-MVS+		90.70 106	89.90 116	93.09 85	93.61 183	83.48 96	95.20 240	92.79 308	83.22 195	91.82 83	95.70 140	71.82 200	97.48 184	91.25 96	93.67 135	98.32 62

EU-MVSNet		76.92 314	76.95 299	76.83 356	84.10 355	54.73 387	91.77 313	92.71 309	72.74 337	69.57 329	88.69 270	58.03 293	87.43 379	64.91 325	70.00 317	88.33 311

pm-mvs1		80.05 286	78.02 291	86.15 279	85.42 340	75.81 282	95.11 246	92.69 310	77.13 302	70.36 324	87.43 288	58.44 287	95.27 294	71.36 289	64.25 356	87.36 331

1112_ss		88.60 149	87.47 159	92.00 136	93.21 196	80.97 149	96.47 175	92.46 311	83.64 190	80.86 220	97.30 96	80.24 71	97.62 170	77.60 234	85.49 216	97.40 133

test_fmvs1		87.79 170	88.52 136	85.62 290	92.98 208	64.31 358	97.88 66	92.42 312	87.95 83	92.24 76	95.82 137	47.94 343	98.44 137	95.31 52	94.09 126	94.09 226

Test_1112_low_res		88.03 165	86.73 173	91.94 138	93.15 199	80.88 152	96.44 178	92.41 313	83.59 192	80.74 222	91.16 238	80.18 72	97.59 172	77.48 237	85.40 217	97.36 135

test_fmvs1_n		86.34 191	86.72 174	85.17 297	87.54 317	63.64 363	96.91 148	92.37 314	87.49 95	91.33 91	95.58 146	40.81 370	98.46 134	95.00 54	93.49 137	93.41 240

BH-RMVSNet		86.84 183	85.28 190	91.49 153	95.35 128	80.26 170	96.95 145	92.21 315	82.86 206	81.77 213	95.46 149	59.34 280	97.64 169	69.79 301	93.81 133	96.57 170

GeoE		86.36 190	85.20 191	89.83 203	93.17 198	76.13 272	97.53 92	92.11 316	79.58 268	80.99 218	94.01 192	66.60 235	96.17 247	73.48 277	89.30 172	97.20 146

LS3D		82.22 262	79.94 276	89.06 214	97.43 79	74.06 298	93.20 295	92.05 317	61.90 371	73.33 302	95.21 158	59.35 279	99.21 88	54.54 364	92.48 151	93.90 230

EG-PatchMatch MVS		74.92 323	72.02 330	83.62 320	83.76 361	73.28 303	93.62 282	92.04 318	68.57 356	58.88 373	83.80 341	31.87 385	95.57 282	56.97 357	78.67 267	82.00 376

IterMVS		80.67 282	79.16 282	85.20 296	89.79 285	76.08 273	92.97 299	91.86 319	80.28 254	71.20 318	85.14 329	57.93 295	91.34 358	72.52 282	70.74 308	88.18 314
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
iter_conf05_11		91.95 72	91.17 87	94.29 36	96.33 97	85.50 52	99.61 1	91.84 320	94.36 10	97.89 6	98.51 24	46.72 348	98.24 145	96.54 36	98.75 28	99.13 25

MIMVSNet		79.18 296	75.99 305	88.72 223	87.37 319	80.66 158	79.96 375	91.82 321	77.38 299	74.33 293	81.87 351	41.78 364	90.74 364	66.36 320	83.10 231	94.76 214

IterMVS-SCA-FT		80.51 284	79.10 283	84.73 302	89.63 291	74.66 290	92.98 298	91.81 322	80.05 259	71.06 320	85.18 327	58.04 291	91.40 357	72.48 283	70.70 310	88.12 315

our_test_3		77.90 305	75.37 309	85.48 293	85.39 341	76.74 263	93.63 281	91.67 323	73.39 332	65.72 347	84.65 335	58.20 290	93.13 341	57.82 351	67.87 336	86.57 340

pmmvs5		81.34 273	79.54 279	86.73 271	85.02 346	76.91 259	96.22 192	91.65 324	77.65 295	73.55 296	88.61 271	55.70 313	94.43 321	74.12 272	73.35 296	88.86 300

ACMH	75.40 17	77.99 302	74.96 310	87.10 264	90.67 271	76.41 268	93.19 296	91.64 325	72.47 340	63.44 355	87.61 287	43.34 358	97.16 202	58.34 349	73.94 291	87.72 320
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis1_n		85.60 204	85.70 183	85.33 294	84.79 348	64.98 356	96.83 152	91.61 326	87.36 99	91.00 98	94.84 174	36.14 376	97.18 201	95.66 46	93.03 144	93.82 231

Fast-Effi-MVS+-dtu		83.33 241	82.60 237	85.50 292	89.55 292	69.38 340	96.09 201	91.38 327	82.30 217	75.96 277	91.41 232	56.71 305	95.58 281	75.13 262	84.90 221	91.54 247

YYNet1		73.53 330	70.43 337	82.85 327	84.52 351	71.73 323	91.69 315	91.37 328	67.63 357	46.79 386	81.21 355	55.04 318	90.43 366	55.93 360	59.70 367	86.38 342

ppachtmachnet_test		77.19 311	74.22 319	86.13 280	85.39 341	78.22 225	93.98 273	91.36 329	71.74 344	67.11 337	84.87 333	56.67 306	93.37 340	52.21 369	64.59 353	86.80 336

Anonymous202405211		84.41 224	81.93 246	91.85 142	96.78 93	78.41 219	97.44 100	91.34 330	70.29 350	84.06 178	94.26 185	41.09 368	98.96 109	79.46 215	82.65 239	98.17 72

MDA-MVSNet_test_wron		73.54 329	70.43 337	82.86 326	84.55 349	71.85 320	91.74 314	91.32 331	67.63 357	46.73 387	81.09 356	55.11 317	90.42 367	55.91 361	59.76 366	86.31 343

CR-MVSNet		83.53 238	81.36 255	90.06 193	90.16 280	79.75 182	79.02 380	91.12 332	84.24 173	82.27 205	80.35 359	75.45 148	93.67 334	63.37 333	86.25 206	96.75 165

Patchmtry		77.36 310	74.59 315	85.67 288	89.75 287	75.75 283	77.85 383	91.12 332	60.28 379	71.23 317	80.35 359	75.45 148	93.56 336	57.94 350	67.34 343	87.68 322

LTVRE_ROB	73.68 18	77.99 302	75.74 307	84.74 301	90.45 275	72.02 317	86.41 356	91.12 332	72.57 339	66.63 342	87.27 291	54.95 319	96.98 211	56.29 359	75.98 280	85.21 356
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		77.18 312	76.06 304	80.55 341	83.78 360	60.00 376	90.35 326	91.05 335	77.01 306	66.62 343	87.92 283	47.73 345	94.03 327	71.63 286	68.44 330	87.62 323

CNLPA		86.96 180	85.37 189	91.72 146	97.59 72	79.34 195	97.21 114	91.05 335	74.22 323	78.90 240	96.75 121	67.21 230	98.95 111	74.68 265	90.77 165	96.88 159

Anonymous20240521		72.06 338	69.91 339	78.50 351	77.11 381	61.67 371	91.62 317	90.97 337	65.52 364	62.37 361	79.05 364	36.32 375	90.96 362	57.75 352	68.52 329	82.87 367

KD-MVS_self_test		70.97 342	69.31 342	75.95 361	76.24 386	55.39 386	87.45 346	90.94 338	70.20 351	62.96 360	77.48 368	44.01 354	88.09 373	61.25 341	53.26 377	84.37 361

pmmvs6		74.65 325	71.67 331	83.60 321	79.13 374	69.94 334	93.31 292	90.88 339	61.05 378	65.83 346	84.15 339	43.43 357	94.83 311	66.62 315	60.63 365	86.02 348

test1111		88.11 163	87.04 169	91.35 155	93.15 199	78.79 210	96.57 168	90.78 340	86.88 111	85.04 166	95.20 159	57.23 303	97.39 189	83.88 173	94.59 121	97.87 95

ECVR-MVS		88.35 157	87.25 163	91.65 147	93.54 186	79.40 192	96.56 170	90.78 340	86.78 114	85.57 162	95.25 153	57.25 302	97.56 174	84.73 166	94.80 118	97.98 88

Anonymous20231206		75.29 322	73.64 323	80.22 342	80.75 367	63.38 365	93.36 288	90.71 342	73.09 334	67.12 336	83.70 342	50.33 334	90.85 363	53.63 367	70.10 315	86.44 341

USDC		78.65 298	76.25 303	85.85 282	87.58 315	74.60 292	89.58 330	90.58 343	84.05 175	63.13 357	88.23 278	40.69 371	96.86 221	66.57 317	75.81 283	86.09 347

MSDG		80.62 283	77.77 293	89.14 213	93.43 193	77.24 254	91.89 311	90.18 344	69.86 353	68.02 333	91.94 227	52.21 327	98.84 117	59.32 347	83.12 230	91.35 248

ACMH+	76.62 16	77.47 309	74.94 311	85.05 298	91.07 262	71.58 325	93.26 293	90.01 345	71.80 343	64.76 350	88.55 272	41.62 365	96.48 234	62.35 336	71.00 306	87.09 334

FMVSNet5		76.46 316	74.16 320	83.35 324	90.05 283	76.17 271	89.58 330	89.85 346	71.39 346	65.29 349	80.42 358	50.61 332	87.70 378	61.05 342	69.24 324	86.18 345

ambc				76.02 359	68.11 393	51.43 388	64.97 396	89.59 347		60.49 369	74.49 376	17.17 395	92.46 344	61.50 339	52.85 379	84.17 363

test_fmvs2		79.59 290	79.90 277	78.67 349	82.86 363	55.82 384	95.20 240	89.55 348	81.09 233	80.12 231	89.80 258	34.31 381	93.51 337	87.82 141	78.36 273	86.69 338

ITE_SJBPF				82.38 330	87.00 321	65.59 355		89.55 348	79.99 261	69.37 330	91.30 235	41.60 366	95.33 290	62.86 335	74.63 290	86.24 344

pmmvs-eth3d		73.59 328	70.66 335	82.38 330	76.40 384	73.38 300	89.39 333	89.43 350	72.69 338	60.34 370	77.79 367	46.43 350	91.26 360	66.42 319	57.06 370	82.51 371

test20.03		72.36 336	71.15 333	75.98 360	77.79 377	59.16 378	92.40 306	89.35 351	74.09 325	61.50 365	84.32 337	48.09 340	85.54 385	50.63 374	62.15 363	83.24 366

SixPastTwentyTwo		76.04 317	74.32 318	81.22 336	84.54 350	61.43 372	91.16 320	89.30 352	77.89 291	64.04 352	86.31 311	48.23 339	94.29 324	63.54 332	63.84 358	87.93 318

TransMVSNet (Re)		76.94 313	74.38 317	84.62 306	85.92 335	75.25 286	95.28 234	89.18 353	73.88 327	67.22 335	86.46 306	59.64 275	94.10 326	59.24 348	52.57 380	84.50 360

MIMVSNet1		69.44 344	66.65 348	77.84 352	76.48 383	62.84 367	87.42 347	88.97 354	66.96 362	57.75 378	79.72 363	32.77 384	85.83 384	46.32 383	63.42 359	84.85 358

K. test v3		73.62 327	71.59 332	79.69 344	82.98 362	59.85 377	90.85 324	88.83 355	77.13 302	58.90 372	82.11 349	43.62 356	91.72 355	65.83 321	54.10 375	87.50 329

Baseline_NR-MVSNet		81.22 275	80.07 273	84.68 303	85.32 344	75.12 287	96.48 174	88.80 356	76.24 311	77.28 255	86.40 310	67.61 223	94.39 322	75.73 257	66.73 348	84.54 359

MDA-MVSNet-bldmvs		71.45 340	67.94 345	81.98 334	85.33 343	68.50 344	92.35 307	88.76 357	70.40 349	42.99 390	81.96 350	46.57 349	91.31 359	48.75 381	54.39 374	86.11 346

new-patchmatchnet		68.85 347	65.93 349	77.61 354	73.57 389	63.94 362	90.11 328	88.73 358	71.62 345	55.08 381	73.60 378	40.84 369	87.22 381	51.35 372	48.49 386	81.67 379

Patchmatch-test		78.25 300	74.72 314	88.83 220	91.20 257	74.10 297	73.91 391	88.70 359	59.89 382	66.82 340	85.12 330	78.38 94	94.54 318	48.84 380	79.58 260	97.86 96

iter_conf05		90.14 117	89.79 118	91.17 163	95.85 115	86.93 28	97.68 81	88.67 360	89.93 54	81.73 214	92.80 213	90.37 8	96.03 249	90.44 110	80.65 252	90.56 255

OpenMVS_ROB	68.52 20	73.02 333	69.57 340	83.37 323	80.54 370	71.82 321	93.60 283	88.22 361	62.37 369	61.98 363	83.15 346	35.31 380	95.47 284	45.08 385	75.88 282	82.82 368

mvsany_test1		87.58 174	88.22 139	85.67 288	89.78 286	67.18 349	95.25 237	87.93 362	83.96 179	88.79 129	97.06 108	72.52 191	94.53 319	92.21 87	86.45 204	95.30 203

RPSCF		77.73 306	76.63 301	81.06 338	88.66 303	55.76 385	87.77 345	87.88 363	64.82 366	74.14 294	92.79 214	49.22 338	96.81 223	67.47 310	76.88 278	90.62 254

mvsmamba		85.17 211	84.54 202	87.05 265	87.94 311	75.11 288	96.22 192	87.79 364	86.91 109	78.55 243	91.77 230	64.93 246	95.91 259	86.94 152	79.80 254	90.12 264

MVS-HIRNet		71.36 341	67.00 346	84.46 310	90.58 272	69.74 337	79.15 379	87.74 365	46.09 391	61.96 364	50.50 395	45.14 353	95.64 276	53.74 366	88.11 190	88.00 317

DP-MVS		81.47 271	78.28 288	91.04 166	98.14 55	78.48 215	95.09 249	86.97 366	61.14 377	71.12 319	92.78 215	59.59 276	99.38 78	53.11 368	86.61 202	95.27 204

COLMAP_ROB	73.24 19	75.74 320	73.00 327	83.94 314	92.38 220	69.08 341	91.85 312	86.93 367	61.48 374	65.32 348	90.27 252	42.27 363	96.93 216	50.91 373	75.63 284	85.80 353
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvs3		69.56 343	69.19 343	70.67 365	69.01 391	47.05 391	90.87 323	86.81 368	71.31 347	66.79 341	77.15 369	16.40 396	83.17 388	81.84 197	62.51 362	81.79 378

test_0402		72.68 334	69.54 341	82.09 333	88.67 302	71.81 322	92.72 302	86.77 369	61.52 373	62.21 362	83.91 340	43.22 359	93.76 333	34.60 392	72.23 302	80.72 380

testgi		74.88 324	73.40 324	79.32 347	80.13 371	61.75 369	93.21 294	86.64 370	79.49 270	66.56 344	91.06 239	35.51 379	88.67 372	56.79 358	71.25 304	87.56 326

TDRefinement		69.20 346	65.78 350	79.48 345	66.04 396	62.21 368	88.21 340	86.12 371	62.92 368	61.03 368	85.61 319	33.23 382	94.16 325	55.82 362	53.02 378	82.08 375

ADS-MVSNet2		79.57 291	77.53 294	85.71 286	93.78 179	72.13 314	79.48 376	86.11 372	73.09 334	80.14 229	79.99 361	62.15 260	90.14 369	59.49 345	83.52 226	94.85 212

LF4IMVS		72.36 336	70.82 334	76.95 355	79.18 373	56.33 381	86.12 358	86.11 372	69.30 355	63.06 358	86.66 302	33.03 383	92.25 347	65.33 323	68.64 328	82.28 374

TinyColmap		72.41 335	68.99 344	82.68 328	88.11 308	69.59 338	88.41 339	85.20 374	65.55 363	57.91 376	84.82 334	30.80 387	95.94 257	51.38 370	68.70 327	82.49 373

pmmvs3		65.75 351	62.18 354	76.45 358	67.12 395	64.54 357	88.68 337	85.05 375	54.77 390	57.54 379	73.79 377	29.40 388	86.21 383	55.49 363	47.77 387	78.62 382

bld_raw_dy_0_64		88.31 158	86.38 177	94.07 45	96.33 97	84.79 74	97.19 117	84.75 376	94.48 8	82.36 200	98.47 27	46.18 351	98.30 143	96.54 36	81.13 247	99.13 25

new_pmnet		66.18 350	63.18 353	75.18 363	76.27 385	61.74 370	83.79 369	84.66 377	56.64 388	51.57 384	71.85 386	31.29 386	87.93 374	49.98 376	62.55 361	75.86 385

AllTest		75.92 318	73.06 326	84.47 308	92.18 232	67.29 347	91.07 321	84.43 378	67.63 357	63.48 353	90.18 253	38.20 373	97.16 202	57.04 355	73.37 294	88.97 296

TestCases				84.47 308	92.18 232	67.29 347		84.43 378	67.63 357	63.48 353	90.18 253	38.20 373	97.16 202	57.04 355	73.37 294	88.97 296

LCM-MVSNet-Re		83.75 235	83.54 221	84.39 312	93.54 186	64.14 360	92.51 303	84.03 380	83.90 182	66.14 345	86.59 303	67.36 228	92.68 342	84.89 165	92.87 145	96.35 175

Gipuma		45.11 366	42.05 368	54.30 382	80.69 368	51.30 389	35.80 400	83.81 381	28.13 396	27.94 400	34.53 400	11.41 403	76.70 396	21.45 399	54.65 372	34.90 400
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		52.52 360	48.24 363	65.35 370	47.63 407	41.45 399	72.55 392	83.62 382	31.75 395	37.66 393	57.92 393	9.19 405	76.76 395	49.26 378	44.60 390	77.84 383

FPMVS		55.09 358	52.93 361	61.57 376	55.98 400	40.51 401	83.11 372	83.41 383	37.61 394	34.95 395	71.95 384	14.40 397	76.95 394	29.81 394	65.16 352	67.25 389

Patchmatch-RL test		76.65 315	74.01 322	84.55 307	77.37 380	64.23 359	78.49 382	82.84 384	78.48 287	64.63 351	73.40 379	76.05 136	91.70 356	76.99 241	57.84 369	97.72 107

DSMNet-mixed		73.13 332	72.45 328	75.19 362	77.51 379	46.82 392	85.09 364	82.01 385	67.61 361	69.27 331	81.33 354	50.89 330	86.28 382	54.54 364	83.80 225	92.46 243

lessismore_v0				79.98 343	80.59 369	58.34 379		80.87 386		58.49 374	83.46 344	43.10 360	93.89 329	63.11 334	48.68 384	87.72 320

test_f		64.01 352	62.13 355	69.65 366	63.00 398	45.30 397	83.66 370	80.68 387	61.30 375	55.70 380	72.62 382	14.23 398	84.64 386	69.84 300	58.11 368	79.00 381

door								80.13 388

door-mid								79.75 389

PM-MVS		69.32 345	66.93 347	76.49 357	73.60 388	55.84 383	85.91 359	79.32 390	74.72 321	61.09 367	78.18 366	21.76 392	91.10 361	70.86 295	56.90 371	82.51 371

mvsany_test3		67.19 349	65.34 351	72.72 364	63.08 397	48.57 390	83.12 371	78.09 391	72.07 341	61.21 366	77.11 370	22.94 391	87.78 377	78.59 224	51.88 381	81.80 377

dmvs_testset		72.00 339	73.36 325	67.91 367	83.83 359	31.90 407	85.30 363	77.12 392	82.80 207	63.05 359	92.46 217	61.54 267	82.55 390	42.22 389	71.89 303	89.29 282

ANet_high		46.22 363	41.28 370	61.04 377	39.91 409	46.25 395	70.59 393	76.18 393	58.87 385	23.09 401	48.00 398	12.58 401	66.54 401	28.65 396	13.62 402	70.35 387

test_method		56.77 355	54.53 359	63.49 374	76.49 382	40.70 400	75.68 387	74.24 394	19.47 402	48.73 385	71.89 385	19.31 393	65.80 402	57.46 354	47.51 388	83.97 364

APD_test1		56.56 356	53.58 360	65.50 369	67.93 394	46.51 394	77.24 386	72.95 395	38.09 393	42.75 391	75.17 373	13.38 399	82.78 389	40.19 390	54.53 373	67.23 390

EGC-MVSNET		52.46 361	47.56 364	67.15 368	81.98 365	60.11 375	82.54 373	72.44 396	0.11 408	0.70 409	74.59 375	25.11 390	83.26 387	29.04 395	61.51 364	58.09 393

PMMVS2		50.90 362	46.31 365	64.67 371	55.53 401	46.67 393	77.30 385	71.02 397	40.89 392	34.16 396	59.32 391	9.83 404	76.14 397	40.09 391	28.63 399	71.21 386

WB-MVS		57.26 354	56.22 357	60.39 378	69.29 390	35.91 405	86.39 357	70.06 398	59.84 383	46.46 388	72.71 381	51.18 329	78.11 392	15.19 402	34.89 397	67.14 391

SSC-MVS		56.01 357	54.96 358	59.17 379	68.42 392	34.13 406	84.98 365	69.23 399	58.08 387	45.36 389	71.67 387	50.30 335	77.46 393	14.28 403	32.33 398	65.91 392

test_vis1_rt		73.96 326	72.40 329	78.64 350	83.91 358	61.16 373	95.63 222	68.18 400	76.32 308	60.09 371	74.77 374	29.01 389	97.54 178	87.74 142	75.94 281	77.22 384

MTMP							97.53 92	68.16 401

DeepMVS_CX				64.06 373	78.53 375	43.26 398		68.11 402	69.94 352	38.55 392	76.14 372	18.53 394	79.34 391	43.72 386	41.62 394	69.57 388

PMVS	34.80 23	39.19 368	35.53 371	50.18 383	29.72 410	30.30 408	59.60 398	66.20 403	26.06 399	17.91 403	49.53 396	3.12 409	74.09 398	18.19 401	49.40 383	46.14 397
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testf1		45.70 364	42.41 366	55.58 380	53.29 404	40.02 402	68.96 394	62.67 404	27.45 397	29.85 397	61.58 389	5.98 407	73.83 399	28.49 397	43.46 392	52.90 394

APD_test2		45.70 364	42.41 366	55.58 380	53.29 404	40.02 402	68.96 394	62.67 404	27.45 397	29.85 397	61.58 389	5.98 407	73.83 399	28.49 397	43.46 392	52.90 394

tmp_tt		41.54 367	41.93 369	40.38 385	20.10 411	26.84 409	61.93 397	59.09 406	14.81 404	28.51 399	80.58 357	35.53 378	48.33 406	63.70 331	13.11 403	45.96 399

MVE	35.65 22	33.85 369	29.49 374	46.92 384	41.86 408	36.28 404	50.45 399	56.52 407	18.75 403	18.28 402	37.84 399	2.41 410	58.41 403	18.71 400	20.62 400	46.06 398
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		32.70 370	32.39 372	33.65 386	53.35 403	25.70 410	74.07 390	53.33 408	21.08 400	17.17 404	33.63 402	11.85 402	54.84 404	12.98 404	14.04 401	20.42 401

EMVS		31.70 371	31.45 373	32.48 387	50.72 406	23.95 411	74.78 389	52.30 409	20.36 401	16.08 405	31.48 403	12.80 400	53.60 405	11.39 405	13.10 404	19.88 402

test_vis3_rt		54.10 359	51.04 362	63.27 375	58.16 399	46.08 396	84.17 367	49.32 410	56.48 389	36.56 394	49.48 397	8.03 406	91.91 353	67.29 311	49.87 382	51.82 396

N_pmnet		61.30 353	60.20 356	64.60 372	84.32 352	17.00 413	91.67 316	10.98 411	61.77 372	58.45 375	78.55 365	49.89 336	91.83 354	42.27 388	63.94 357	84.97 357

wuyk23d		14.10 373	13.89 376	14.72 388	55.23 402	22.91 412	33.83 401	3.56 412	4.94 405	4.11 406	2.28 408	2.06 411	19.66 407	10.23 406	8.74 405	1.59 405

testmvs		9.92 374	12.94 377	0.84 390	0.65 412	0.29 415	93.78 279	0.39 413	0.42 406	2.85 407	15.84 406	0.17 413	0.30 409	2.18 407	0.21 406	1.91 404

test123		9.07 375	11.73 378	1.11 389	0.50 413	0.77 414	89.44 332	0.20 414	0.34 407	2.15 408	10.72 407	0.34 412	0.32 408	1.79 408	0.08 407	2.23 403

test_blank		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet_test		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

DCPMVS		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

pcd_1.5k_mvsjas		5.92 377	7.89 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	71.04 209	0.00 410	0.00 409	0.00 408	0.00 406

sosnet-low-res		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

sosnet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uncertanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

Regformer		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

n2								0.00 415

nn								0.00 415

ab-mvs-re		8.11 376	10.81 379	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	97.30 96	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

WAC-MVS						67.18 349								49.00 379

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					0.00 414

eth-test					0.00 414

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 74	96.69 18	98.76 12	89.64 13	99.76 31	97.47 24	98.84 23	99.38 14

GSMVS																97.54 120

test_part2					98.90 19	85.14 65				96.07 29

sam_mvs1												77.59 107				97.54 120

sam_mvs												75.35 155

test_post1							85.88 360				30.24 404	73.77 178	95.07 306	73.89 273

test_post											33.80 401	76.17 134	95.97 253

patchmatchnet-post											77.09 371	77.78 106	95.39 286

gm-plane-assit					92.27 226	79.64 188			84.47 164		95.15 163		97.93 154	85.81 157

test9_res														96.00 41	99.03 13	98.31 64

agg_prior2														94.30 60	99.00 15	98.57 48

test_prior4						82.34 116	97.75 76

test_prior2							98.37 40		86.08 123	94.57 50	98.02 53	83.14 50		95.05 53	98.79 26

旧先验2							96.97 142		74.06 326	96.10 28			97.76 165	88.38 137

新几何2							96.42 181

原ACMM2							96.84 151

testdata2													99.48 73	76.45 248

segment_acmp												82.69 55

testdata1							95.57 225		87.44 96

plane_prior7					91.86 247	77.55 249

plane_prior6					91.98 243	77.92 238						64.77 247

plane_prior4											94.15 189

plane_prior3						77.75 245			90.17 52	81.33 215

plane_prior2							97.18 119		89.89 55

plane_prior1					91.95 245

plane_prior						77.96 235	97.52 95		90.36 50						82.96 234

HQP5-MVS						78.48 215

HQP-NCC					92.08 238		97.63 83		90.52 45	82.30 201

ACMP_Plane					92.08 238		97.63 83		90.52 45	82.30 201

BP-MVS														87.67 144

HQP4-MVS										82.30 201			97.32 192			91.13 249

HQP2-MVS												65.40 241

NP-MVS					92.04 242	78.22 225					94.56 179

MDTV_nov1_ep13_2view						81.74 132	86.80 352		80.65 242	85.65 161		74.26 172		76.52 247		96.98 152

ACMMP++_ref															78.45 272

ACMMP++															79.05 264

Test By Simon												71.65 202

High-resolution multi-view benchmark