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		88.92 146	87.65 158	92.73 103	96.30 103	85.62 54	97.85 66	98.86 1	84.38 170	84.82 180	93.99 197	75.12 168	98.01 158	70.86 305	86.67 211	94.56 230

thres100view900		88.30 166	86.95 180	92.33 121	96.10 110	84.90 75	97.14 125	98.85 2	82.69 217	83.41 198	93.66 205	75.43 158	97.93 160	69.04 313	86.24 218	94.17 232

tfpn200view9		88.48 160	87.15 174	92.47 113	96.21 106	85.30 61	97.44 99	98.85 2	83.37 200	83.99 190	93.82 201	75.36 161	97.93 160	69.04 313	86.24 218	94.17 232

thres600view7		88.06 171	86.70 186	92.15 133	96.10 110	85.17 67	97.14 125	98.85 2	82.70 216	83.41 198	93.66 205	75.43 158	97.82 169	67.13 322	85.88 222	93.45 248

thres400		88.42 163	87.15 174	92.23 127	96.21 106	85.30 61	97.44 99	98.85 2	83.37 200	83.99 190	93.82 201	75.36 161	97.93 160	69.04 313	86.24 218	93.45 248

MVS_111021_HR		93.41 41	93.39 44	93.47 77	97.34 89	82.83 110	97.56 88	98.27 6	89.16 62	89.71 118	97.14 105	79.77 83	99.56 66	93.65 73	97.94 59	98.02 88

sss		90.87 111	89.96 121	93.60 67	94.15 178	83.84 92	97.14 125	98.13 7	85.93 131	89.68 119	96.09 135	71.67 212	99.30 83	87.69 154	89.16 182	97.66 119

MM		95.85 6	95.74 10	96.15 8	96.34 102	89.50 9	99.18 6	98.10 8	95.68 1	96.64 21	97.92 61	80.72 68	99.80 25	99.16 1	97.96 58	99.15 27

MG-MVS		94.25 29	93.72 35	95.85 12	99.38 3	89.35 11	97.98 59	98.09 9	89.99 53	92.34 81	96.97 113	81.30 66	98.99 110	88.54 144	98.88 20	99.20 25

VNet		92.11 77	91.22 89	94.79 28	96.91 95	86.98 30	97.91 63	97.96 10	86.38 121	93.65 61	95.74 141	70.16 229	98.95 114	93.39 75	88.87 187	98.43 61

test_yl		91.46 93	90.53 103	94.24 42	97.41 83	85.18 63	98.08 52	97.72 11	80.94 242	89.85 115	96.14 133	75.61 150	98.81 122	90.42 123	88.56 193	98.74 42

DCV-MVSNet		91.46 93	90.53 103	94.24 42	97.41 83	85.18 63	98.08 52	97.72 11	80.94 242	89.85 115	96.14 133	75.61 150	98.81 122	90.42 123	88.56 193	98.74 42

WTY-MVS		92.65 63	91.68 80	95.56 14	96.00 112	88.90 13	98.23 43	97.65 13	88.57 69	89.82 117	97.22 103	79.29 87	99.06 107	89.57 133	88.73 189	98.73 46

EPNet		94.06 33	94.15 32	93.76 56	97.27 91	84.35 82	98.29 41	97.64 14	94.57 6	95.36 35	96.88 116	79.96 82	99.12 103	91.30 104	96.11 107	97.82 108
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HY-MVS	84.06 6	91.63 89	90.37 109	95.39 19	96.12 109	88.25 17	90.22 336	97.58 15	88.33 76	90.50 110	91.96 233	79.26 88	99.06 107	90.29 125	89.07 183	98.88 37

baseline2		90.39 120	90.21 113	90.93 176	90.86 277	80.99 152	95.20 245	97.41 16	86.03 129	80.07 240	94.61 182	90.58 6	97.47 192	87.29 158	89.86 177	94.35 231

test2506		90.96 108	90.39 107	92.65 107	93.54 195	82.46 117	96.37 184	97.35 17	86.78 117	87.55 151	95.25 156	77.83 113	97.50 189	84.07 180	94.80 123	97.98 95

PVSNet	82.34 9	89.02 143	87.79 156	92.71 104	95.49 131	81.50 142	97.70 78	97.29 18	87.76 91	85.47 173	95.12 168	56.90 317	98.90 118	80.33 215	94.02 133	97.71 116

testing222		91.09 103	90.49 105	92.87 96	95.82 119	85.04 70	96.51 174	97.28 19	86.05 127	89.13 129	95.34 155	80.16 78	96.62 239	85.82 166	88.31 197	96.96 162

PGM-MVS		91.93 80	91.80 78	92.32 123	98.27 50	79.74 190	95.28 239	97.27 20	83.83 190	90.89 106	97.78 71	76.12 143	99.56 66	88.82 141	97.93 61	97.66 119

IB-MVS	85.34 4	88.67 154	87.14 176	93.26 80	93.12 212	84.32 83	98.76 26	97.27 20	87.19 109	79.36 246	90.45 255	83.92 48	98.53 133	84.41 177	69.79 326	96.93 164
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	92.45 114	95.29 138	80.96 154	99.29 2	97.21 22	94.50 7	97.29 13	98.44 27	82.15 60	99.78 28	98.56 7	97.68 67	96.61 177

patch_mono-2		95.14 13	96.08 7	92.33 121	98.44 43	77.84 247	98.43 36	97.21 22	92.58 19	97.68 10	97.65 79	86.88 25	99.83 17	98.25 9	97.60 69	99.33 18

MVS		90.60 115	88.64 141	96.50 5	94.25 174	90.53 8	93.33 296	97.21 22	77.59 303	78.88 250	97.31 95	71.52 215	99.69 49	89.60 132	98.03 56	99.27 22

ETVMVS		90.99 106	90.26 110	93.19 84	95.81 120	85.64 53	96.97 142	97.18 25	85.43 139	88.77 138	94.86 177	82.00 62	96.37 246	82.70 201	88.60 190	97.57 126

CSCG		92.02 78	91.65 81	93.12 86	98.53 36	80.59 164	97.47 96	97.18 25	77.06 312	84.64 185	97.98 58	83.98 46	99.52 69	90.72 114	97.33 78	99.23 24

fmvsm_s_conf0.5_n		93.69 37	94.13 33	92.34 119	94.56 160	82.01 122	99.07 16	97.13 27	92.09 23	96.25 26	98.53 22	76.47 135	99.80 25	98.39 8	94.71 125	95.22 215

PHI-MVS		93.59 39	93.63 38	93.48 75	98.05 58	81.76 134	98.64 31	97.13 27	82.60 219	94.09 56	98.49 25	80.35 72	99.85 11	94.74 60	98.62 33	98.83 38

CNVR-MVS		96.30 1	96.54 1	95.55 15	99.31 5	87.69 24	99.06 17	97.12 29	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		89.30 139	88.95 136	90.36 194	95.07 146	76.04 284	96.96 144	97.11 30	90.39 48	92.22 83	95.10 169	74.70 173	98.86 119	93.14 83	65.89 359	96.16 190

MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 10	98.94 24	97.10 31	95.17 3	92.11 85	98.46 26	87.33 24	99.97 2	97.21 29	99.31 4	99.63 7

testing11		92.48 68	92.04 75	93.78 55	95.94 116	86.00 40	97.56 88	97.08 32	87.52 97	89.32 126	95.40 153	84.60 37	98.02 157	91.93 101	89.04 184	97.32 145

VPA-MVSNet		85.32 219	83.83 224	89.77 215	90.25 287	82.63 112	96.36 185	97.07 33	83.03 208	81.21 225	89.02 272	61.58 280	96.31 249	85.02 174	70.95 315	90.36 267

UBG		92.68 62	92.35 64	93.70 61	95.61 127	85.65 52	97.25 112	97.06 34	87.92 86	89.28 127	95.03 171	86.06 31	98.07 155	92.24 94	90.69 173	97.37 143

UWE-MVS		88.56 159	88.91 138	87.50 263	94.17 177	72.19 322	95.82 219	97.05 35	84.96 154	84.78 181	93.51 209	81.33 64	94.75 321	79.43 226	89.17 181	95.57 204

DELS-MVS		94.98 14	94.49 24	96.44 6	96.42 101	90.59 7	99.21 5	97.02 36	94.40 8	91.46 93	97.08 109	83.32 52	99.69 49	92.83 88	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 74	94.94 150	86.26 36	81.62 388	97.00 37		88.32 145	94.30 188	91.23 5	96.21 254	88.49 146	97.43 75	98.00 93

fmvsm_s_conf0.5_n_a		93.34 42	93.71 36	92.22 128	93.38 203	81.71 137	98.86 25	96.98 38	91.64 29	96.85 16	98.55 19	75.58 153	99.77 29	97.88 19	93.68 140	95.18 216

DPM-MVS		96.21 2	95.53 13	98.26 1	96.26 105	95.09 1	99.15 8	96.98 38	93.39 14	96.45 25	98.79 8	90.17 9	99.99 1	89.33 137	99.25 6	99.70 3

gg-mvs-nofinetune		85.48 218	82.90 240	93.24 81	94.51 166	85.82 45	79.22 393	96.97 40	61.19 390	87.33 154	53.01 409	90.58 6	96.07 257	86.07 165	97.23 81	97.81 109

NCCC		95.63 7	95.94 8	94.69 32	99.21 6	85.15 68	99.16 7	96.96 41	94.11 9	95.59 34	98.64 17	85.07 34	99.91 4	95.61 46	99.10 9	99.00 31

FIs		86.73 196	86.10 190	88.61 233	90.05 293	80.21 177	96.14 201	96.95 42	85.56 138	78.37 254	92.30 225	76.73 132	95.28 302	79.51 224	79.27 269	90.35 268

PVSNet_0	77.72 15	81.70 277	78.95 294	89.94 208	90.77 280	76.72 274	95.96 208	96.95 42	85.01 152	70.24 337	88.53 280	52.32 339	98.20 151	86.68 164	44.08 405	94.89 220

HPM-MVS++		95.32 11	95.48 14	94.85 26	98.62 34	86.04 39	97.81 70	96.93 44	92.45 20	95.69 33	98.50 24	85.38 32	99.85 11	94.75 59	99.18 7	98.65 50

MSLP-MVS++		94.28 27	94.39 27	93.97 49	98.30 49	84.06 88	98.64 31	96.93 44	90.71 42	93.08 69	98.70 15	79.98 81	99.21 90	94.12 68	99.07 11	98.63 51

testing99		91.91 81	91.35 86	93.60 67	95.98 114	85.70 47	97.31 110	96.92 46	86.82 115	88.91 133	95.25 156	84.26 44	97.89 167	88.80 142	87.94 201	97.21 153

testing91		91.90 82	91.31 88	93.66 63	95.99 113	85.68 49	97.39 106	96.89 47	86.75 119	88.85 135	95.23 159	83.93 47	97.90 166	88.91 139	87.89 202	97.41 139

UniMVSNet (Re)		85.31 220	84.23 218	88.55 234	89.75 297	80.55 166	96.72 161	96.89 47	85.42 140	78.40 253	88.93 273	75.38 160	95.52 292	78.58 235	68.02 343	89.57 283

FC-MVSNet-test		85.96 206	85.39 198	87.66 256	89.38 308	78.02 238	95.65 226	96.87 49	85.12 149	77.34 263	91.94 235	76.28 141	94.74 322	77.09 250	78.82 273	90.21 271

EI-MVSNet-Vis-set		91.84 84	91.77 79	92.04 138	97.60 72	81.17 146	96.61 167	96.87 49	88.20 80	89.19 128	97.55 87	78.69 99	99.14 100	90.29 125	90.94 170	95.80 198

IU-MVS					99.03 15	85.34 58		96.86 51	92.05 27	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 22	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 22	98.08 14	98.81 24	99.43 11

EI-MVSNet-UG-set		91.35 97	91.22 89	91.73 152	97.39 86	80.68 162	96.47 176	96.83 52	87.92 86	88.30 146	97.36 94	77.84 112	99.13 102	89.43 136	89.45 179	95.37 210

SED-MVS		95.88 5	96.22 4	94.87 25	99.03 15	85.03 71	99.12 12	96.78 55	88.72 66	97.79 6	98.91 2	88.48 17	99.82 19	98.15 11	98.97 17	99.74 1

test_241102_TWO								96.78 55	88.72 66	97.70 8	98.91 2	87.86 21	99.82 19	98.15 11	99.00 15	99.47 9

test_241102_ONE					99.03 15	85.03 71		96.78 55	88.72 66	97.79 6	98.90 5	88.48 17	99.82 19

test0726					99.05 9	85.18 63	99.11 15	96.78 55	88.75 64	97.65 11	98.91 2	87.69 22

MSP-MVS		95.62 8	96.54 1	92.86 97	98.31 48	80.10 181	97.42 103	96.78 55	92.20 22	97.11 14	98.29 36	93.46 1	99.10 104	96.01 39	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							96.87 151	96.78 55	77.39 305				99.52 69	79.95 221		98.43 61

DVP-MVS++		96.05 4	96.41 3	94.96 24	99.05 9	85.34 58	98.13 49	96.77 61	88.38 74	97.70 8	98.77 10	92.06 3	99.84 13	97.47 24	99.37 1	99.70 3

test_0728_SECOND				95.14 20	99.04 14	86.14 38	99.06 17	96.77 61					99.84 13	97.90 17	98.85 21	99.45 10

SMA-MVS		94.70 21	94.68 21	94.76 29	98.02 59	85.94 43	97.47 96	96.77 61	85.32 142	97.92 3	98.70 15	83.09 55	99.84 13	95.79 43	99.08 10	98.49 57
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 91	91.64 82	91.47 162	95.74 123	78.79 216	96.15 200	96.77 61	88.49 71	88.64 140	97.07 110	72.33 204	99.19 96	93.13 85	96.48 102	96.43 182

3Dnovator	82.32 10	89.33 138	87.64 159	94.42 37	93.73 191	85.70 47	97.73 76	96.75 65	86.73 120	76.21 283	95.93 137	62.17 273	99.68 51	81.67 208	97.81 63	97.88 100

DPE-MVS		95.32 11	95.55 12	94.64 33	98.79 23	84.87 76	97.77 72	96.74 66	86.11 124	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		90.05 125	89.96 121	90.33 195	97.47 77	83.86 90	98.02 58	96.73 67	87.98 84	89.53 123	89.61 267	76.42 137	99.57 64	94.29 65	79.59 266	87.57 334

PVSNet_Blended		93.13 43	92.98 51	93.57 69	97.47 77	83.86 90	99.32 1	96.73 67	91.02 40	89.53 123	96.21 132	76.42 137	99.57 64	94.29 65	95.81 115	97.29 149

ACMMP		90.39 120	89.97 120	91.64 155	97.58 74	78.21 234	96.78 158	96.72 69	84.73 159	84.72 183	97.23 102	71.22 217	99.63 57	88.37 149	92.41 158	97.08 159
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 86	97.44 81	81.60 141		96.71 70	74.54 331	91.22 100	97.57 83	79.13 91	99.51 71	77.40 249	98.46 40	98.26 73

test_one_0601					98.91 18	84.56 81		96.70 71	88.06 82	96.57 23	98.77 10	88.04 20

HFP-MVS		92.89 50	92.86 55	92.98 92	98.71 25	81.12 147	97.58 86	96.70 71	85.20 147	91.75 90	97.97 60	78.47 101	99.71 45	90.95 107	98.41 43	98.12 84

ACMMPR		92.69 60	92.67 58	92.75 101	98.66 28	80.57 165	97.58 86	96.69 73	85.20 147	91.57 92	97.92 61	77.01 125	99.67 53	90.95 107	98.41 43	98.00 93

DeepPCF-MVS	89.82 1	94.61 22	96.17 5	89.91 209	97.09 94	70.21 342	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		89.65 133	89.02 133	91.53 159	93.46 201	80.78 160	96.52 172	96.67 75	81.69 235	83.79 195	94.90 176	88.85 14	97.68 174	77.80 238	87.49 207	96.14 191

tttt0517		88.57 158	88.19 149	89.71 216	93.00 214	75.99 288	95.67 224	96.67 75	80.78 246	81.82 220	94.40 186	88.97 13	97.58 180	76.05 263	86.31 215	95.57 204

thisisatest0515		90.95 109	90.26 110	93.01 91	94.03 186	84.27 86	97.91 63	96.67 75	83.18 203	86.87 161	95.51 151	88.66 15	97.85 168	80.46 214	89.01 185	96.92 166

ACMMP_NAP		93.46 40	93.23 46	94.17 45	97.16 92	84.28 85	96.82 155	96.65 78	86.24 122	94.27 53	97.99 55	77.94 109	99.83 17	93.39 75	98.57 34	98.39 63

TEST9					98.64 31	83.71 93	97.82 68	96.65 78	84.29 175	95.16 37	98.09 48	84.39 39	99.36 81

train_agg		94.28 27	94.45 25	93.74 57	98.64 31	83.71 93	97.82 68	96.65 78	84.50 166	95.16 37	98.09 48	84.33 40	99.36 81	95.91 42	98.96 19	98.16 79

1314		88.94 145	87.20 173	94.17 45	93.21 206	85.73 46	93.33 296	96.64 81	82.89 211	75.98 286	96.36 129	66.83 246	99.39 77	83.52 194	96.02 111	97.39 142

DeepC-MVS_fast	89.06 2	94.48 25	94.30 29	95.02 22	98.86 21	85.68 49	98.06 55	96.64 81	93.64 12	91.74 91	98.54 20	80.17 77	99.90 5	92.28 93	98.75 29	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 96	97.81 70	96.63 83	84.50 166	95.10 40	98.11 47	84.33 40	99.23 88

FE-MVS		86.06 205	84.15 221	91.78 149	94.33 173	79.81 185	84.58 380	96.61 84	76.69 315	85.00 177	87.38 297	70.71 225	98.37 144	70.39 308	91.70 166	97.17 156

原ACMM1				91.22 170	97.77 65	78.10 237		96.61 84	81.05 241	91.28 99	97.42 92	77.92 111	98.98 111	79.85 223	98.51 36	96.59 178

MAR-MVS		90.63 114	90.22 112	91.86 145	98.47 42	78.20 235	97.18 118	96.61 84	83.87 189	88.18 147	98.18 41	68.71 233	99.75 36	83.66 190	97.15 84	97.63 122
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	83.22 105		96.60 87	82.88 212	93.61 63	98.06 53	82.93 56	99.14 100	95.51 49	98.49 39

MVS_0304		95.58 9	95.44 15	96.01 10	97.63 70	89.26 12	99.27 3	96.59 88	94.71 4	97.08 15	97.99 55	78.69 99	99.86 10	99.15 2	97.85 62	98.91 35

SteuartSystems-ACMMP		94.13 32	94.44 26	93.20 83	95.41 133	81.35 144	99.02 21	96.59 88	89.50 58	94.18 55	98.36 33	83.68 50	99.45 75	94.77 58	98.45 41	98.81 39
Skip Steuart: Steuart Systems R&D Blog.
D2MVS		82.67 263	81.55 260	86.04 290	87.77 325	76.47 276	95.21 244	96.58 90	82.66 218	70.26 336	85.46 333	60.39 285	95.80 272	76.40 259	79.18 270	85.83 361

save fliter					98.24 51	83.34 102	98.61 33	96.57 91	91.32 33

TESTMET0.1,1		89.83 129	89.34 130	91.31 164	92.54 229	80.19 178	97.11 128	96.57 91	86.15 123	86.85 162	91.83 237	79.32 86	96.95 221	81.30 209	92.35 159	96.77 172

agg_prior					98.59 35	83.13 106		96.56 93		94.19 54			99.16 99

旧先验1					97.39 86	79.58 195		96.54 94			98.08 51	84.00 45			97.42 76	97.62 123

WR-MVS_H		81.02 286	80.09 280	83.79 324	88.08 322	71.26 337	94.46 264	96.54 94	80.08 265	72.81 318	86.82 307	70.36 227	92.65 354	64.18 337	67.50 349	87.46 339

9.14			94.26 31		98.10 57		98.14 46	96.52 96	84.74 158	94.83 47	98.80 7	82.80 58	99.37 80	95.95 41	98.42 42

region2R		92.72 56	92.70 57	92.79 100	98.68 26	80.53 169	97.53 91	96.51 97	85.22 145	91.94 88	97.98 58	77.26 120	99.67 53	90.83 112	98.37 46	98.18 77

EPP-MVSNet		89.76 130	89.72 126	89.87 210	93.78 188	76.02 287	97.22 113	96.51 97	79.35 278	85.11 175	95.01 173	84.82 35	97.10 214	87.46 157	88.21 199	96.50 180

ZNCC-MVS		92.75 52	92.60 60	93.23 82	98.24 51	81.82 132	97.63 81	96.50 99	85.00 153	91.05 102	97.74 72	78.38 102	99.80 25	90.48 118	98.34 48	98.07 86

test11								96.50 99

EPNet_dtu		87.65 182	87.89 153	86.93 276	94.57 159	71.37 336	96.72 161	96.50 99	88.56 70	87.12 158	95.02 172	75.91 147	94.01 338	66.62 325	90.00 175	95.42 209
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testdata				90.13 200	95.92 117	74.17 305		96.49 102	73.49 340	94.82 48	97.99 55	78.80 97	97.93 160	83.53 193	97.52 71	98.29 70

DVP-MVS		95.58 9	95.91 9	94.57 34	99.05 9	85.18 63	99.06 17	96.46 103	88.75 64	96.69 18	98.76 12	87.69 22	99.76 31	97.90 17	98.85 21	98.77 40
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					96.15 108	78.41 225	95.87 215	96.46 103	71.97 351	89.66 120	97.45 88	76.33 140			98.24 51	98.30 69

XVS		92.69 60	92.71 56	92.63 109	98.52 37	80.29 172	97.37 107	96.44 105	87.04 111	91.38 94	97.83 69	77.24 122	99.59 60	90.46 120	98.07 54	98.02 88

X-MVStestdata		86.26 202	84.14 222	92.63 109	98.52 37	80.29 172	97.37 107	96.44 105	87.04 111	91.38 94	20.73 420	77.24 122	99.59 60	90.46 120	98.07 54	98.02 88

SF-MVS		94.17 30	94.05 34	94.55 35	97.56 75	85.95 41	97.73 76	96.43 107	84.02 182	95.07 42	98.74 14	82.93 56	99.38 78	95.42 50	98.51 36	98.32 66

TSAR-MVS + MP.		94.79 20	95.17 18	93.64 64	97.66 69	84.10 87	95.85 217	96.42 108	91.26 34	97.49 12	96.80 121	86.50 27	98.49 135	95.54 48	99.03 13	98.33 65
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 24	94.75 20	93.96 50	98.84 22	83.40 101	98.04 57	96.41 109	85.79 133	95.00 43	98.28 37	84.32 43	99.18 97	97.35 26	98.77 28	99.28 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
UniMVSNet_NR-MVSNet		85.49 217	84.59 211	88.21 245	89.44 307	79.36 199	96.71 163	96.41 109	85.22 145	78.11 257	90.98 248	76.97 127	95.14 309	79.14 230	68.30 340	90.12 274

test_prior				93.09 88	98.68 26	81.91 127		96.40 111					99.06 107			98.29 70

CP-MVS		92.54 66	92.60 60	92.34 119	98.50 40	79.90 184	98.40 38	96.40 111	84.75 157	90.48 111	98.09 48	77.40 119	99.21 90	91.15 106	98.23 52	97.92 99

CANet		94.89 16	94.64 22	95.63 13	97.55 76	88.12 18	99.06 17	96.39 113	94.07 10	95.34 36	97.80 70	76.83 130	99.87 8	97.08 31	97.64 68	98.89 36

GST-MVS		92.43 70	92.22 70	93.04 90	98.17 54	81.64 139	97.40 105	96.38 114	84.71 160	90.90 105	97.40 93	77.55 117	99.76 31	89.75 131	97.74 65	97.72 114

alignmvs		92.97 48	92.26 68	95.12 21	95.54 130	87.77 22	98.67 29	96.38 114	88.04 83	93.01 70	97.45 88	79.20 90	98.60 128	93.25 81	88.76 188	98.99 33

PAPM		92.87 51	92.40 63	94.30 39	92.25 239	87.85 21	96.40 183	96.38 114	91.07 38	88.72 139	96.90 114	82.11 61	97.37 198	90.05 128	97.70 66	97.67 118

test_fmvsmconf_n		93.99 34	94.36 28	92.86 97	92.82 221	81.12 147	99.26 4	96.37 117	93.47 13	95.16 37	98.21 39	79.00 92	99.64 55	98.21 10	96.73 98	97.83 106

test12				94.25 41	98.34 46	85.55 55		96.35 118		92.36 80		80.84 67	99.22 89		98.31 49	97.98 95

MTGPA								96.33 119

MTAPA		92.45 69	92.31 66	92.86 97	97.90 61	80.85 158	92.88 308	96.33 119	87.92 86	90.20 114	98.18 41	76.71 133	99.76 31	92.57 92	98.09 53	97.96 98

reproduce_monomvs		87.80 177	87.60 163	88.40 237	96.56 98	80.26 175	95.80 220	96.32 121	91.56 31	73.60 305	88.36 283	88.53 16	96.25 252	90.47 119	67.23 352	88.67 309

ET-MVSNet_ETH3D		90.01 126	89.03 132	92.95 93	94.38 171	86.77 32	98.14 46	96.31 122	89.30 60	63.33 368	96.72 125	90.09 10	93.63 346	90.70 116	82.29 253	98.46 59

EPMVS		87.47 185	85.90 192	92.18 130	95.41 133	82.26 121	87.00 363	96.28 123	85.88 132	84.23 187	85.57 330	75.07 169	96.26 250	71.14 303	92.50 156	98.03 87

WB-MVSnew		84.08 239	83.51 232	85.80 292	91.34 266	76.69 275	95.62 228	96.27 124	81.77 233	81.81 221	92.81 217	58.23 301	94.70 323	66.66 324	87.06 208	85.99 358

CDPH-MVS		93.12 44	92.91 52	93.74 57	98.65 30	83.88 89	97.67 80	96.26 125	83.00 209	93.22 67	98.24 38	81.31 65	99.21 90	89.12 138	98.74 30	98.14 81

WR-MVS		84.32 235	82.96 238	88.41 236	89.38 308	80.32 171	96.59 168	96.25 126	83.97 184	76.63 273	90.36 257	67.53 239	94.86 318	75.82 266	70.09 324	90.06 278

fmvsm_s_conf0.1_n		92.93 49	93.16 48	92.24 126	90.52 283	81.92 126	98.42 37	96.24 127	91.17 35	96.02 30	98.35 34	75.34 164	99.74 38	97.84 20	94.58 127	95.05 217

UGNet		87.73 179	86.55 187	91.27 167	95.16 143	79.11 207	96.35 186	96.23 128	88.14 81	87.83 150	90.48 254	50.65 345	99.09 105	80.13 220	94.03 132	95.60 203
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		78.14 310	75.42 318	86.31 286	88.33 320	79.24 202	94.41 266	96.22 129	73.51 338	69.81 339	85.52 332	55.43 327	95.75 277	47.65 394	67.86 345	83.95 374

FOURS1					98.51 39	78.01 239	98.13 49	96.21 130	83.04 207	94.39 52

MP-MVS		92.61 64	92.67 58	92.42 117	98.13 56	79.73 191	97.33 109	96.20 131	85.63 135	90.53 109	97.66 75	78.14 107	99.70 48	92.12 96	98.30 50	97.85 104
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PAPR		92.74 53	92.17 71	94.45 36	98.89 20	84.87 76	97.20 116	96.20 131	87.73 92	88.40 143	98.12 46	78.71 98	99.76 31	87.99 151	96.28 103	98.74 42

SD-MVS		94.84 18	95.02 19	94.29 40	97.87 64	84.61 79	97.76 74	96.19 133	89.59 57	96.66 20	98.17 44	84.33 40	99.60 59	96.09 38	98.50 38	98.66 49
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 88	91.85 76	91.29 166	94.94 150	82.69 111	87.89 356	96.17 134	85.94 130	87.27 155	94.31 187	90.27 8	95.65 284	94.04 69	95.86 113	95.53 206

fmvsm_l_conf0.5_n		94.89 16	95.24 17	93.86 52	94.42 170	84.61 79	99.13 11	96.15 135	92.06 25	97.92 3	98.52 23	84.52 38	99.74 38	98.76 6	95.67 116	97.22 151

CHOSEN 1792x2688		91.07 105	90.21 113	93.64 64	95.18 142	83.53 98	96.26 192	96.13 136	88.92 63	84.90 179	93.10 215	72.86 196	99.62 58	88.86 140	95.67 116	97.79 110

PAPM_NR		91.46 93	90.82 97	93.37 78	98.50 40	81.81 133	95.03 255	96.13 136	84.65 162	86.10 167	97.65 79	79.24 89	99.75 36	83.20 196	96.88 92	98.56 54

CostFormer		89.08 142	88.39 146	91.15 171	93.13 211	79.15 206	88.61 348	96.11 138	83.14 204	89.58 122	86.93 306	83.83 49	96.87 227	88.22 150	85.92 221	97.42 138

mPP-MVS		91.88 83	91.82 77	92.07 135	98.38 44	78.63 219	97.29 111	96.09 139	85.12 149	88.45 142	97.66 75	75.53 154	99.68 51	89.83 129	98.02 57	97.88 100

APD-MVS		93.61 38	93.59 39	93.69 62	98.76 24	83.26 104	97.21 114	96.09 139	82.41 223	94.65 49	98.21 39	81.96 63	98.81 122	94.65 61	98.36 47	99.01 30
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MDTV_nov1_ep13			83.69 225		94.09 182	81.01 151	86.78 365	96.09 139	83.81 191	84.75 182	84.32 347	74.44 179	96.54 240	63.88 339	85.07 230

FA-MVS(test-final)		87.71 181	86.23 189	92.17 131	94.19 176	80.55 166	87.16 362	96.07 142	82.12 228	85.98 168	88.35 284	72.04 209	98.49 135	80.26 217	89.87 176	97.48 135

QAPM		86.88 191	84.51 212	93.98 48	94.04 184	85.89 44	97.19 117	96.05 143	73.62 337	75.12 297	95.62 147	62.02 276	99.74 38	70.88 304	96.06 109	96.30 189

MP-MVS-pluss		92.58 65	92.35 64	93.29 79	97.30 90	82.53 114	96.44 179	96.04 144	84.68 161	89.12 130	98.37 32	77.48 118	99.74 38	93.31 80	98.38 45	97.59 125
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.1_n_a		92.38 71	92.49 62	92.06 136	88.08 322	81.62 140	97.97 61	96.01 145	90.62 43	96.58 22	98.33 35	74.09 183	99.71 45	97.23 28	93.46 145	94.86 221

fmvsm_l_conf0.5_n_a		94.91 15	95.30 16	93.72 60	94.50 167	84.30 84	99.14 10	96.00 146	91.94 28	97.91 5	98.60 18	84.78 36	99.77 29	98.84 5	96.03 110	97.08 159

tpm2		87.35 186	86.26 188	90.62 186	92.93 219	78.67 218	88.06 355	95.99 147	79.33 279	87.40 152	86.43 317	80.28 74	96.40 244	80.23 218	85.73 225	96.79 170

SDMVSNet		87.02 188	85.61 194	91.24 168	94.14 179	83.30 103	93.88 284	95.98 148	84.30 173	79.63 243	92.01 229	58.23 301	97.68 174	90.28 127	82.02 254	92.75 251

DeepC-MVS	86.58 3	91.53 92	91.06 94	92.94 94	94.52 163	81.89 128	95.95 209	95.98 148	90.76 41	83.76 196	96.76 122	73.24 194	99.71 45	91.67 103	96.96 89	97.22 151
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test-LLR		88.48 160	87.98 152	89.98 205	92.26 237	77.23 264	97.11 128	95.96 150	83.76 193	86.30 165	91.38 240	72.30 205	96.78 233	80.82 211	91.92 163	95.94 195

test-mter		88.95 144	88.60 142	89.98 205	92.26 237	77.23 264	97.11 128	95.96 150	85.32 142	86.30 165	91.38 240	76.37 139	96.78 233	80.82 211	91.92 163	95.94 195

DP-MVS Recon		91.72 87	90.85 96	94.34 38	99.50 1	85.00 73	98.51 35	95.96 150	80.57 251	88.08 148	97.63 81	76.84 128	99.89 7	85.67 168	94.88 122	98.13 83

reproduce-ours		92.70 58	93.02 49	91.75 150	97.45 79	77.77 251	96.16 198	95.94 153	84.12 178	92.45 76	98.43 28	80.06 79	99.24 86	95.35 51	97.18 82	98.24 74

our_new_method		92.70 58	93.02 49	91.75 150	97.45 79	77.77 251	96.16 198	95.94 153	84.12 178	92.45 76	98.43 28	80.06 79	99.24 86	95.35 51	97.18 82	98.24 74

cdsmvs_eth3d_5k		21.43 387	28.57 390	0.00 406	0.00 429	0.00 431	0.00 417	95.93 155	0.00 424	0.00 425	97.66 75	63.57 265	0.00 425	0.00 424	0.00 423	0.00 421

reproduce_model		92.53 67	92.87 53	91.50 160	97.41 83	77.14 268	96.02 205	95.91 156	83.65 196	92.45 76	98.39 31	79.75 84	99.21 90	95.27 54	96.98 88	98.14 81

hse-mvs2		88.22 169	88.21 148	88.25 243	93.54 195	73.41 308	95.41 237	95.89 157	90.39 48	92.22 83	94.22 190	74.70 173	96.66 238	93.14 83	64.37 364	94.69 229

AUN-MVS		86.25 203	85.57 195	88.26 242	93.57 194	73.38 309	95.45 235	95.88 158	83.94 186	85.47 173	94.21 191	73.70 190	96.67 237	83.54 192	64.41 363	94.73 228

TAMVS		88.48 160	87.79 156	90.56 188	91.09 271	79.18 204	96.45 178	95.88 158	83.64 197	83.12 202	93.33 210	75.94 146	95.74 280	82.40 203	88.27 198	96.75 174

PVSNet_Blended_VisFu		91.24 99	90.77 98	92.66 106	95.09 144	82.40 118	97.77 72	95.87 160	88.26 77	86.39 163	93.94 198	76.77 131	99.27 84	88.80 142	94.00 135	96.31 188

OpenMVS	79.58 14	86.09 204	83.62 229	93.50 73	90.95 273	86.71 34	97.44 99	95.83 161	75.35 322	72.64 319	95.72 142	57.42 314	99.64 55	71.41 298	95.85 114	94.13 235

CDS-MVSNet		89.50 135	88.96 135	91.14 172	91.94 256	80.93 155	97.09 132	95.81 162	84.26 176	84.72 183	94.20 192	80.31 73	95.64 285	83.37 195	88.96 186	96.85 169
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PS-MVSNAJ		94.17 30	93.52 41	96.10 9	95.65 126	92.35 2	98.21 44	95.79 163	92.42 21	96.24 27	98.18 41	71.04 220	99.17 98	96.77 34	97.39 77	96.79 170

testing3		80.74 290	81.17 266	79.44 357	91.15 270	63.48 376	97.16 122	95.76 164	80.83 244	71.36 327	93.15 214	78.22 105	87.30 392	43.19 400	79.67 265	87.55 337

SR-MVS		92.16 75	92.27 67	91.83 148	98.37 45	78.41 225	96.67 166	95.76 164	82.19 227	91.97 86	98.07 52	76.44 136	98.64 126	93.71 72	97.27 80	98.45 60

3Dnovator+	82.88 8	89.63 134	87.85 154	94.99 23	94.49 168	86.76 33	97.84 67	95.74 166	86.10 125	75.47 294	96.02 136	65.00 259	99.51 71	82.91 200	97.07 86	98.72 47

HPM-MVS		91.62 90	91.53 84	91.89 143	97.88 63	79.22 203	96.99 137	95.73 167	82.07 229	89.50 125	97.19 104	75.59 152	98.93 117	90.91 109	97.94 59	97.54 127
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ab-mvs		87.08 187	84.94 208	93.48 75	93.34 204	83.67 95	88.82 345	95.70 168	81.18 239	84.55 186	90.14 262	62.72 270	98.94 116	85.49 170	82.54 250	97.85 104

xiu_mvs_v2_base		93.92 35	93.26 45	95.91 11	95.07 146	92.02 6	98.19 45	95.68 169	92.06 25	96.01 31	98.14 45	70.83 224	98.96 112	96.74 36	96.57 100	96.76 173

CP-MVSNet		81.01 287	80.08 281	83.79 324	87.91 324	70.51 339	94.29 275	95.65 170	80.83 244	72.54 321	88.84 274	63.71 264	92.32 357	68.58 317	68.36 339	88.55 311

PatchmatchNet		86.83 193	85.12 205	91.95 141	94.12 181	82.27 120	86.55 367	95.64 171	84.59 164	82.98 205	84.99 342	77.26 120	95.96 264	68.61 316	91.34 168	97.64 121
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
API-MVS		90.18 124	88.97 134	93.80 54	98.66 28	82.95 109	97.50 95	95.63 172	75.16 325	86.31 164	97.69 73	72.49 201	99.90 5	81.26 210	96.07 108	98.56 54

balanced_conf03		94.60 23	94.30 29	95.48 16	96.45 100	88.82 14	96.33 188	95.58 173	91.12 36	95.84 32	93.87 200	83.47 51	98.37 144	97.26 27	98.81 24	99.24 23

AdaColmap		88.81 150	87.61 162	92.39 118	99.33 4	79.95 182	96.70 165	95.58 173	77.51 304	83.05 204	96.69 126	61.90 279	99.72 43	84.29 178	93.47 144	97.50 133

SCA		85.63 213	83.64 228	91.60 158	92.30 235	81.86 130	92.88 308	95.56 175	84.85 155	82.52 206	85.12 340	58.04 304	95.39 295	73.89 283	87.58 206	97.54 127

dp		84.30 236	82.31 249	90.28 196	94.24 175	77.97 240	86.57 366	95.53 176	79.94 269	80.75 229	85.16 338	71.49 216	96.39 245	63.73 340	83.36 239	96.48 181

HyFIR lowres test		89.36 137	88.60 142	91.63 157	94.91 152	80.76 161	95.60 229	95.53 176	82.56 220	84.03 189	91.24 243	78.03 108	96.81 231	87.07 161	88.41 196	97.32 145

WBMVS		87.73 179	86.79 182	90.56 188	95.61 127	85.68 49	97.63 81	95.52 178	83.77 192	78.30 255	88.44 282	86.14 30	95.78 274	82.54 202	73.15 305	90.21 271

APD-MVS_3200maxsize		91.23 100	91.35 86	90.89 179	97.89 62	76.35 280	96.30 190	95.52 178	79.82 270	91.03 103	97.88 66	74.70 173	98.54 132	92.11 97	96.89 91	97.77 111

lupinMVS		93.87 36	93.58 40	94.75 30	93.00 214	88.08 19	99.15 8	95.50 180	91.03 39	94.90 44	97.66 75	78.84 95	97.56 181	94.64 62	97.46 72	98.62 52

tt0805		81.20 285	79.06 293	87.61 257	86.50 336	72.97 317	93.66 287	95.48 181	74.11 333	76.23 282	91.99 231	41.36 380	97.40 195	77.44 248	74.78 295	92.45 254

HPM-MVS_fast		90.38 122	90.17 115	91.03 174	97.61 71	77.35 262	97.15 124	95.48 181	79.51 276	88.79 136	96.90 114	71.64 214	98.81 122	87.01 162	97.44 74	96.94 163

VPNet		84.69 228	82.92 239	90.01 203	89.01 310	83.45 100	96.71 163	95.46 183	85.71 134	79.65 242	92.18 228	56.66 320	96.01 260	83.05 199	67.84 346	90.56 265

114514_t		88.79 152	87.57 164	92.45 114	98.21 53	81.74 135	96.99 137	95.45 184	75.16 325	82.48 207	95.69 144	68.59 234	98.50 134	80.33 215	95.18 120	97.10 158

SR-MVS-dyc-post		91.29 98	91.45 85	90.80 181	97.76 67	76.03 285	96.20 196	95.44 185	80.56 252	90.72 107	97.84 67	75.76 149	98.61 127	91.99 99	96.79 95	97.75 112

RE-MVS-def			91.18 93		97.76 67	76.03 285	96.20 196	95.44 185	80.56 252	90.72 107	97.84 67	73.36 193		91.99 99	96.79 95	97.75 112

JIA-IIPM		79.00 306	77.20 305	84.40 319	89.74 299	64.06 373	75.30 403	95.44 185	62.15 384	81.90 218	59.08 407	78.92 93	95.59 289	66.51 328	85.78 224	93.54 245

RPMNet		79.85 296	75.92 316	91.64 155	90.16 290	79.75 188	79.02 395	95.44 185	58.43 400	82.27 214	72.55 398	73.03 195	98.41 143	46.10 396	86.25 216	96.75 174

MVSMamba_PlusPlus		92.37 72	91.55 83	94.83 27	95.37 135	87.69 24	95.60 229	95.42 189	74.65 330	93.95 58	92.81 217	83.11 54	97.70 173	94.49 63	98.53 35	99.11 28

DU-MVS		84.57 231	83.33 235	88.28 241	88.76 311	79.36 199	96.43 181	95.41 190	85.42 140	78.11 257	90.82 249	67.61 236	95.14 309	79.14 230	68.30 340	90.33 269

EI-MVSNet		85.80 209	85.20 201	87.59 259	91.55 261	77.41 260	95.13 249	95.36 191	80.43 257	80.33 235	94.71 180	73.72 188	95.97 261	76.96 253	78.64 275	89.39 284

MVSTER		89.25 141	88.92 137	90.24 197	95.98 114	84.66 78	96.79 157	95.36 191	87.19 109	80.33 235	90.61 253	90.02 11	95.97 261	85.38 171	78.64 275	90.09 276

CPTT-MVS		89.72 131	89.87 125	89.29 220	98.33 47	73.30 311	97.70 78	95.35 193	75.68 321	87.40 152	97.44 91	70.43 226	98.25 149	89.56 134	96.90 90	96.33 187

EIA-MVS		91.73 85	92.05 74	90.78 183	94.52 163	76.40 279	98.06 55	95.34 194	89.19 61	88.90 134	97.28 100	77.56 116	97.73 172	90.77 113	96.86 94	98.20 76

tpmvs		83.04 257	80.77 270	89.84 211	95.43 132	77.96 241	85.59 373	95.32 195	75.31 324	76.27 281	83.70 353	73.89 185	97.41 194	59.53 355	81.93 256	94.14 234

PS-CasMVS		80.27 294	79.18 290	83.52 330	87.56 328	69.88 344	94.08 278	95.29 196	80.27 262	72.08 323	88.51 281	59.22 295	92.23 359	67.49 319	68.15 342	88.45 317

TSAR-MVS + GP.		94.35 26	94.50 23	93.89 51	97.38 88	83.04 108	98.10 51	95.29 196	91.57 30	93.81 59	97.45 88	86.64 26	99.43 76	96.28 37	94.01 134	99.20 25

tpmrst		88.36 164	87.38 170	91.31 164	94.36 172	79.92 183	87.32 360	95.26 198	85.32 142	88.34 144	86.13 323	80.60 71	96.70 235	83.78 184	85.34 229	97.30 148

ETV-MVS		92.72 56	92.87 53	92.28 125	94.54 162	81.89 128	97.98 59	95.21 199	89.77 56	93.11 68	96.83 118	77.23 124	97.50 189	95.74 44	95.38 119	97.44 137

NR-MVSNet		83.35 249	81.52 262	88.84 228	88.76 311	81.31 145	94.45 265	95.16 200	84.65 162	67.81 345	90.82 249	70.36 227	94.87 317	74.75 274	66.89 356	90.33 269

test_fmvsmconf0.1_n		93.08 46	93.22 47	92.65 107	88.45 317	80.81 159	99.00 22	95.11 201	93.21 15	94.00 57	97.91 63	76.84 128	99.59 60	97.91 16	96.55 101	97.54 127

jason		92.73 54	92.23 69	94.21 44	90.50 284	87.30 29	98.65 30	95.09 202	90.61 44	92.76 75	97.13 106	75.28 165	97.30 201	93.32 79	96.75 97	98.02 88
jason: jason.
tpm cat1		83.63 246	81.38 263	90.39 193	93.53 200	78.19 236	85.56 374	95.09 202	70.78 357	78.51 252	83.28 357	74.80 172	97.03 215	66.77 323	84.05 234	95.95 194

cascas		86.50 197	84.48 214	92.55 112	92.64 227	85.95 41	97.04 136	95.07 204	75.32 323	80.50 231	91.02 246	54.33 335	97.98 159	86.79 163	87.62 204	93.71 243

CVMVSNet		84.83 226	85.57 195	82.63 337	91.55 261	60.38 387	95.13 249	95.03 205	80.60 250	82.10 216	94.71 180	66.40 249	90.19 379	74.30 280	90.32 174	97.31 147

test0.0.03 1		82.79 261	82.48 247	83.74 326	86.81 334	72.22 320	96.52 172	95.03 205	83.76 193	73.00 315	93.20 211	72.30 205	88.88 382	64.15 338	77.52 284	90.12 274

PMMVS		89.46 136	89.92 123	88.06 247	94.64 157	69.57 348	96.22 194	94.95 207	87.27 105	91.37 96	96.54 128	65.88 251	97.39 196	88.54 144	93.89 137	97.23 150

CS-MVS		92.73 54	93.48 42	90.48 191	96.27 104	75.93 290	98.55 34	94.93 208	89.32 59	94.54 51	97.67 74	78.91 94	97.02 216	93.80 70	97.32 79	98.49 57

Anonymous20240529		83.15 254	80.60 274	90.80 181	95.74 123	78.27 229	96.81 156	94.92 209	60.10 395	81.89 219	92.54 221	45.82 365	98.82 121	79.25 229	78.32 281	95.31 212

mvs_anonymous		88.68 153	87.62 161	91.86 145	94.80 155	81.69 138	93.53 292	94.92 209	82.03 230	78.87 251	90.43 256	75.77 148	95.34 298	85.04 173	93.16 149	98.55 56

CLD-MVS		87.97 174	87.48 167	89.44 218	92.16 244	80.54 168	98.14 46	94.92 209	91.41 32	79.43 245	95.40 153	62.34 272	97.27 204	90.60 117	82.90 245	90.50 266
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		90.54 116	89.54 127	93.55 70	92.31 232	87.58 26	96.99 137	94.87 212	87.23 106	93.27 64	97.56 84	57.43 311	98.32 146	92.72 89	93.46 145	94.74 225

xiu_mvs_v1_base		90.54 116	89.54 127	93.55 70	92.31 232	87.58 26	96.99 137	94.87 212	87.23 106	93.27 64	97.56 84	57.43 311	98.32 146	92.72 89	93.46 145	94.74 225

xiu_mvs_v1_base_debi		90.54 116	89.54 127	93.55 70	92.31 232	87.58 26	96.99 137	94.87 212	87.23 106	93.27 64	97.56 84	57.43 311	98.32 146	92.72 89	93.46 145	94.74 225

GA-MVS		85.79 210	84.04 223	91.02 175	89.47 306	80.27 174	96.90 150	94.84 215	85.57 136	80.88 227	89.08 270	56.56 321	96.47 243	77.72 241	85.35 228	96.34 185

TranMVSNet+NR-MVSNet		83.24 253	81.71 258	87.83 251	87.71 326	78.81 215	96.13 203	94.82 216	84.52 165	76.18 284	90.78 251	64.07 263	94.60 326	74.60 278	66.59 358	90.09 276

HQP3-MVS								94.80 217							83.01 242

HQP-MVS		87.91 176	87.55 165	88.98 226	92.08 248	78.48 221	97.63 81	94.80 217	90.52 45	82.30 210	94.56 183	65.40 255	97.32 199	87.67 155	83.01 242	91.13 259

TAPA-MVS	81.61 12	85.02 223	83.67 226	89.06 223	96.79 96	73.27 314	95.92 211	94.79 219	74.81 328	80.47 232	96.83 118	71.07 219	98.19 152	49.82 389	92.57 154	95.71 201
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PEN-MVS		79.47 302	78.26 298	83.08 333	86.36 338	68.58 352	93.85 285	94.77 220	79.76 271	71.37 326	88.55 278	59.79 287	92.46 355	64.50 336	65.40 360	88.19 322

SPE-MVS-test		92.98 47	93.67 37	90.90 178	96.52 99	76.87 270	98.68 28	94.73 221	90.36 50	94.84 46	97.89 65	77.94 109	97.15 212	94.28 67	97.80 64	98.70 48

HQP_MVS		87.50 184	87.09 177	88.74 231	91.86 257	77.96 241	97.18 118	94.69 222	89.89 54	81.33 223	94.15 193	64.77 260	97.30 201	87.08 159	82.82 246	90.96 261

plane_prior5								94.69 222					97.30 201	87.08 159	82.82 246	90.96 261

tpm		85.55 215	84.47 215	88.80 230	90.19 289	75.39 295	88.79 346	94.69 222	84.83 156	83.96 192	85.21 336	78.22 105	94.68 325	76.32 261	78.02 283	96.34 185

FMVSNet3		84.71 227	82.71 244	90.70 185	94.55 161	87.71 23	95.92 211	94.67 225	81.73 234	75.82 289	88.08 289	66.99 244	94.47 329	71.23 300	75.38 292	89.91 280

UA-Net		88.92 146	88.48 145	90.24 197	94.06 183	77.18 266	93.04 304	94.66 226	87.39 101	91.09 101	93.89 199	74.92 170	98.18 153	75.83 265	91.43 167	95.35 211

LFMVS		89.27 140	87.64 159	94.16 47	97.16 92	85.52 56	97.18 118	94.66 226	79.17 284	89.63 121	96.57 127	55.35 328	98.22 150	89.52 135	89.54 178	98.74 42

MVS_Test		90.29 123	89.18 131	93.62 66	95.23 139	84.93 74	94.41 266	94.66 226	84.31 171	90.37 113	91.02 246	75.13 167	97.82 169	83.11 198	94.42 129	98.12 84

sasdasda		92.27 73	91.22 89	95.41 17	95.80 121	88.31 15	97.09 132	94.64 229	88.49 71	92.99 71	97.31 95	72.68 198	98.57 130	93.38 77	88.58 191	99.36 16

canonicalmvs		92.27 73	91.22 89	95.41 17	95.80 121	88.31 15	97.09 132	94.64 229	88.49 71	92.99 71	97.31 95	72.68 198	98.57 130	93.38 77	88.58 191	99.36 16

VDDNet		86.44 198	84.51 212	92.22 128	91.56 260	81.83 131	97.10 131	94.64 229	69.50 364	87.84 149	95.19 163	48.01 355	97.92 165	89.82 130	86.92 209	96.89 167

baseline1		88.85 149	87.49 166	92.93 95	95.21 141	86.85 31	95.47 234	94.61 232	87.29 103	83.11 203	94.99 174	80.70 69	96.89 225	82.28 204	73.72 299	95.05 217

PatchT		79.75 297	76.85 309	88.42 235	89.55 304	75.49 294	77.37 399	94.61 232	63.07 380	82.46 208	73.32 395	75.52 155	93.41 350	51.36 383	84.43 232	96.36 183

MS-PatchMatch		83.05 256	81.82 257	86.72 281	89.64 301	79.10 208	94.88 258	94.59 234	79.70 273	70.67 333	89.65 266	50.43 347	96.82 230	70.82 307	95.99 112	84.25 371

casdiffmvs_mvg		91.13 102	90.45 106	93.17 85	92.99 217	83.58 97	97.46 98	94.56 235	87.69 93	87.19 157	94.98 175	74.50 178	97.60 178	91.88 102	92.79 152	98.34 64
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		90.76 112	90.10 116	92.74 102	92.90 220	82.56 113	94.60 263	94.56 235	87.69 93	89.06 132	95.67 145	73.76 187	97.51 188	90.43 122	92.23 161	98.16 79

OMC-MVS		88.80 151	88.16 150	90.72 184	95.30 137	77.92 244	94.81 260	94.51 237	86.80 116	84.97 178	96.85 117	67.53 239	98.60 128	85.08 172	87.62 204	95.63 202

MGCFI-Net		91.95 79	91.03 95	94.72 31	95.68 125	86.38 35	96.93 147	94.48 238	88.25 78	92.78 74	97.24 101	72.34 203	98.46 138	93.13 85	88.43 195	99.32 19

MVSFormer		91.36 96	90.57 102	93.73 59	93.00 214	88.08 19	94.80 261	94.48 238	80.74 247	94.90 44	97.13 106	78.84 95	95.10 312	83.77 185	97.46 72	98.02 88

test_djsdf		83.00 259	82.45 248	84.64 313	84.07 368	69.78 345	94.80 261	94.48 238	80.74 247	75.41 295	87.70 293	61.32 283	95.10 312	83.77 185	79.76 262	89.04 299

casdiffmvs		90.95 109	90.39 107	92.63 109	92.82 221	82.53 114	96.83 153	94.47 241	87.69 93	88.47 141	95.56 150	74.04 184	97.54 185	90.90 110	92.74 153	97.83 106
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	86.77 195	85.00 207	92.08 134	92.06 251	83.07 107	92.14 317	94.47 241	79.63 274	76.90 270	94.78 179	71.15 218	99.20 95	72.87 289	91.05 169	93.98 238
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
RRT-MVS		89.67 132	88.67 140	92.67 105	94.44 169	81.08 149	94.34 269	94.45 243	86.05 127	85.79 169	92.39 223	63.39 267	98.16 154	93.22 82	93.95 136	98.76 41

VDD-MVS		88.28 167	87.02 179	92.06 136	95.09 144	80.18 179	97.55 90	94.45 243	83.09 205	89.10 131	95.92 139	47.97 356	98.49 135	93.08 87	86.91 210	97.52 132

mvsmamba		90.53 119	90.08 117	91.88 144	94.81 154	80.93 155	93.94 282	94.45 243	88.24 79	87.02 160	92.35 224	68.04 235	95.80 272	94.86 57	97.03 87	98.92 34

test_cas_vis1_n_1920		89.90 128	90.02 119	89.54 217	90.14 292	74.63 300	98.71 27	94.43 246	93.04 17	92.40 79	96.35 130	53.41 338	99.08 106	95.59 47	96.16 105	94.90 219

PLC	83.97 7	88.00 173	87.38 170	89.83 212	98.02 59	76.46 277	97.16 122	94.43 246	79.26 283	81.98 217	96.28 131	69.36 231	99.27 84	77.71 242	92.25 160	93.77 242
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EC-MVSNet		91.73 85	92.11 72	90.58 187	93.54 195	77.77 251	98.07 54	94.40 248	87.44 99	92.99 71	97.11 108	74.59 177	96.87 227	93.75 71	97.08 85	97.11 157

sd_testset		84.62 229	83.11 237	89.17 221	94.14 179	77.78 250	91.54 327	94.38 249	84.30 173	79.63 243	92.01 229	52.28 340	96.98 219	77.67 243	82.02 254	92.75 251

FMVSNet2		82.79 261	80.44 276	89.83 212	92.66 224	85.43 57	95.42 236	94.35 250	79.06 287	74.46 301	87.28 298	56.38 323	94.31 332	69.72 312	74.68 296	89.76 281

test_vis1_n_1920		89.95 127	90.59 101	88.03 249	92.36 231	68.98 351	99.12 12	94.34 251	93.86 11	93.64 62	97.01 112	51.54 342	99.59 60	96.76 35	96.71 99	95.53 206

nrg030		86.79 194	85.43 197	90.87 180	88.76 311	85.34 58	97.06 135	94.33 252	84.31 171	80.45 233	91.98 232	72.36 202	96.36 247	88.48 147	71.13 313	90.93 263

ACMM	80.70 13	83.72 245	82.85 242	86.31 286	91.19 268	72.12 324	95.88 214	94.29 253	80.44 255	77.02 268	91.96 233	55.24 329	97.14 213	79.30 228	80.38 261	89.67 282
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XXY-MVS		83.84 242	82.00 254	89.35 219	87.13 331	81.38 143	95.72 222	94.26 254	80.15 264	75.92 288	90.63 252	61.96 278	96.52 241	78.98 232	73.28 304	90.14 273

Syy-MVS		77.97 314	78.05 299	77.74 365	92.13 245	56.85 394	93.97 280	94.23 255	82.43 221	73.39 308	93.57 207	57.95 307	87.86 387	32.40 408	82.34 251	88.51 312

myMVS_eth3d		81.93 274	82.18 250	81.18 347	92.13 245	67.18 358	93.97 280	94.23 255	82.43 221	73.39 308	93.57 207	76.98 126	87.86 387	50.53 387	82.34 251	88.51 312

cl22		85.11 222	84.17 220	87.92 250	95.06 148	78.82 213	95.51 232	94.22 257	79.74 272	76.77 271	87.92 291	75.96 145	95.68 281	79.93 222	72.42 307	89.27 291

OPM-MVS		85.84 208	85.10 206	88.06 247	88.34 319	77.83 248	95.72 222	94.20 258	87.89 89	80.45 233	94.05 195	58.57 298	97.26 205	83.88 182	82.76 248	89.09 296
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet (Re-imp)		88.88 148	88.87 139	88.91 227	93.89 187	74.43 303	96.93 147	94.19 259	84.39 169	83.22 201	95.67 145	78.24 104	94.70 323	78.88 233	94.40 130	97.61 124

Anonymous20231211		79.72 298	77.19 306	87.33 267	95.59 129	77.16 267	95.18 248	94.18 260	59.31 398	72.57 320	86.20 322	47.89 358	95.66 282	74.53 279	69.24 332	89.18 293

PS-MVSNAJss		84.91 225	84.30 217	86.74 277	85.89 348	74.40 304	94.95 256	94.16 261	83.93 187	76.45 276	90.11 263	71.04 220	95.77 275	83.16 197	79.02 272	90.06 278

LPG-MVS_test		84.20 237	83.49 233	86.33 283	90.88 274	73.06 315	95.28 239	94.13 262	82.20 225	76.31 278	93.20 211	54.83 333	96.95 221	83.72 187	80.83 259	88.98 302

LGP-MVS_train				86.33 283	90.88 274	73.06 315		94.13 262	82.20 225	76.31 278	93.20 211	54.83 333	96.95 221	83.72 187	80.83 259	88.98 302

V42		83.04 257	81.53 261	87.57 261	86.27 341	79.09 209	95.87 215	94.11 264	80.35 259	77.22 266	86.79 309	65.32 257	96.02 259	77.74 240	70.14 320	87.61 333

XVG-OURS-SEG-HR		85.74 211	85.16 204	87.49 265	90.22 288	71.45 334	91.29 328	94.09 265	81.37 237	83.90 194	95.22 160	60.30 286	97.53 187	85.58 169	84.42 233	93.50 246

XVG-OURS		85.18 221	84.38 216	87.59 259	90.42 286	71.73 331	91.06 331	94.07 266	82.00 231	83.29 200	95.08 170	56.42 322	97.55 183	83.70 189	83.42 238	93.49 247

miper_enhance_ethall		85.95 207	85.20 201	88.19 246	94.85 153	79.76 187	96.00 206	94.06 267	82.98 210	77.74 261	88.76 275	79.42 85	95.46 294	80.58 213	72.42 307	89.36 289

v2v482		83.46 248	81.86 256	88.25 243	86.19 342	79.65 193	96.34 187	94.02 268	81.56 236	77.32 264	88.23 286	65.62 252	96.03 258	77.77 239	69.72 328	89.09 296

jajsoiax		82.12 272	81.15 267	85.03 307	84.19 366	70.70 338	94.22 276	93.95 269	83.07 206	73.48 307	89.75 265	49.66 351	95.37 297	82.24 205	79.76 262	89.02 300

test_fmvsmconf0.01_n		91.08 104	90.68 100	92.29 124	82.43 376	80.12 180	97.94 62	93.93 270	92.07 24	91.97 86	97.60 82	67.56 238	99.53 68	97.09 30	95.56 118	97.21 153

v1144		82.90 260	81.27 265	87.78 253	86.29 340	79.07 210	96.14 201	93.93 270	80.05 266	77.38 262	86.80 308	65.50 253	95.93 266	75.21 271	70.13 321	88.33 320

KD-MVS_2432*1600		77.63 317	74.92 322	85.77 293	90.86 277	79.44 196	88.08 353	93.92 272	76.26 317	67.05 349	82.78 359	72.15 207	91.92 362	61.53 347	41.62 408	85.94 359

miper_refine_blended		77.63 317	74.92 322	85.77 293	90.86 277	79.44 196	88.08 353	93.92 272	76.26 317	67.05 349	82.78 359	72.15 207	91.92 362	61.53 347	41.62 408	85.94 359

test_fmvsmvis_n_1920		92.12 76	92.10 73	92.17 131	90.87 276	81.04 150	98.34 40	93.90 274	92.71 18	87.24 156	97.90 64	74.83 171	99.72 43	96.96 32	96.20 104	95.76 200

UnsupCasMVSNet_eth		73.25 342	70.57 347	81.30 345	77.53 391	66.33 364	87.24 361	93.89 275	80.38 258	57.90 390	81.59 364	42.91 375	90.56 376	65.18 334	48.51 396	87.01 344

v7n		79.32 304	77.34 304	85.28 303	84.05 369	72.89 319	93.38 294	93.87 276	75.02 327	70.68 332	84.37 346	59.58 290	95.62 287	67.60 318	67.50 349	87.32 341

dcpmvs_2		93.10 45	93.46 43	92.02 139	97.77 65	79.73 191	94.82 259	93.86 277	86.91 113	91.33 97	96.76 122	85.20 33	98.06 156	96.90 33	97.60 69	98.27 72

Vis-MVSNet		88.67 154	87.82 155	91.24 168	92.68 223	78.82 213	96.95 145	93.85 278	87.55 96	87.07 159	95.13 167	63.43 266	97.21 206	77.58 245	96.15 106	97.70 117
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v148		82.41 269	80.89 268	86.99 275	86.18 343	76.81 272	96.27 191	93.82 279	80.49 254	75.28 296	86.11 324	67.32 242	95.75 277	75.48 269	67.03 355	88.42 318

BH-w/o		88.24 168	87.47 168	90.54 190	95.03 149	78.54 220	97.41 104	93.82 279	84.08 180	78.23 256	94.51 185	69.34 232	97.21 206	80.21 219	94.58 127	95.87 197

TR-MVS		86.30 201	84.93 209	90.42 192	94.63 158	77.58 257	96.57 169	93.82 279	80.30 260	82.42 209	95.16 165	58.74 297	97.55 183	74.88 273	87.82 203	96.13 192

v1192		82.31 270	80.55 275	87.60 258	85.94 346	78.47 224	95.85 217	93.80 282	79.33 279	76.97 269	86.51 312	63.33 268	95.87 268	73.11 288	70.13 321	88.46 316

ACMP	81.66 11	84.00 240	83.22 236	86.33 283	91.53 263	72.95 318	95.91 213	93.79 283	83.70 195	73.79 304	92.22 226	54.31 336	96.89 225	83.98 181	79.74 264	89.16 294
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v144192		82.43 266	80.73 271	87.54 262	85.81 349	78.22 231	95.98 207	93.78 284	79.09 286	77.11 267	86.49 313	64.66 262	95.91 267	74.20 281	69.42 329	88.49 314

mvs_tets		81.74 276	80.71 272	84.84 308	84.22 365	70.29 341	93.91 283	93.78 284	82.77 215	73.37 310	89.46 268	47.36 361	95.31 301	81.99 206	79.55 268	88.92 306

F-COLMAP		84.50 233	83.44 234	87.67 255	95.22 140	72.22 320	95.95 209	93.78 284	75.74 320	76.30 280	95.18 164	59.50 291	98.45 140	72.67 291	86.59 213	92.35 256

UniMVSNet_ETH3D		80.86 289	78.75 295	87.22 272	86.31 339	72.02 325	91.95 318	93.76 287	73.51 338	75.06 298	90.16 261	43.04 374	95.66 282	76.37 260	78.55 278	93.98 238

Fast-Effi-MVS+		87.93 175	86.94 181	90.92 177	94.04 184	79.16 205	98.26 42	93.72 288	81.29 238	83.94 193	92.90 216	69.83 230	96.68 236	76.70 255	91.74 165	96.93 164

v1921920		82.02 273	80.23 279	87.41 266	85.62 350	77.92 244	95.79 221	93.69 289	78.86 290	76.67 272	86.44 315	62.50 271	95.83 270	72.69 290	69.77 327	88.47 315

DTE-MVSNet		78.37 308	77.06 307	82.32 340	85.22 357	67.17 361	93.40 293	93.66 290	78.71 292	70.53 334	88.29 285	59.06 296	92.23 359	61.38 350	63.28 369	87.56 335

v8		81.88 275	80.06 283	87.32 268	86.63 335	79.04 211	94.41 266	93.65 291	78.77 291	73.19 314	85.57 330	66.87 245	95.81 271	73.84 285	67.61 348	87.11 342

diffmvs		91.17 101	90.74 99	92.44 116	93.11 213	82.50 116	96.25 193	93.62 292	87.79 90	90.40 112	95.93 137	73.44 192	97.42 193	93.62 74	92.55 155	97.41 139
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		81.26 283	78.36 296	89.96 207	93.78 188	79.78 186	79.48 391	93.60 293	73.09 343	80.14 237	79.99 375	62.15 274	95.24 304	59.49 356	83.52 236	94.85 222

PatchMatch-RL		85.00 224	83.66 227	89.02 225	95.86 118	74.55 302	92.49 312	93.60 293	79.30 281	79.29 247	91.47 238	58.53 299	98.45 140	70.22 309	92.17 162	94.07 237

anonymousdsp		80.98 288	79.97 284	84.01 321	81.73 378	70.44 340	92.49 312	93.58 295	77.10 311	72.98 316	86.31 319	57.58 310	94.90 316	79.32 227	78.63 277	86.69 347

CL-MVSNet_self_test		75.81 329	74.14 331	80.83 350	78.33 389	67.79 355	94.22 276	93.52 296	77.28 308	69.82 338	81.54 366	61.47 282	89.22 381	57.59 364	53.51 386	85.48 363

miper_ehance_all_eth		84.57 231	83.60 230	87.50 263	92.64 227	78.25 230	95.40 238	93.47 297	79.28 282	76.41 277	87.64 294	76.53 134	95.24 304	78.58 235	72.42 307	89.01 301

kuosan		73.55 339	72.39 340	77.01 368	89.68 300	66.72 363	85.24 377	93.44 298	67.76 368	60.04 384	83.40 356	71.90 210	84.25 399	45.34 397	54.75 381	80.06 394

v1240		81.70 277	79.83 287	87.30 270	85.50 351	77.70 256	95.48 233	93.44 298	78.46 295	76.53 275	86.44 315	60.85 284	95.84 269	71.59 297	70.17 319	88.35 319

v10		81.43 281	79.53 289	87.11 273	86.38 337	78.87 212	94.31 271	93.43 300	77.88 299	73.24 313	85.26 334	65.44 254	95.75 277	72.14 294	67.71 347	86.72 346

IterMVS-LS		83.93 241	82.80 243	87.31 269	91.46 264	77.39 261	95.66 225	93.43 300	80.44 255	75.51 293	87.26 300	73.72 188	95.16 308	76.99 251	70.72 317	89.39 284
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		82.42 267	80.43 277	88.39 238	92.66 224	81.95 123	94.30 272	93.38 302	79.06 287	75.82 289	85.66 326	56.38 323	93.84 341	71.23 300	75.38 292	89.38 286

test1		82.42 267	80.43 277	88.39 238	92.66 224	81.95 123	94.30 272	93.38 302	79.06 287	75.82 289	85.66 326	56.38 323	93.84 341	71.23 300	75.38 292	89.38 286

FMVSNet1		79.50 301	76.54 312	88.39 238	88.47 316	81.95 123	94.30 272	93.38 302	73.14 342	72.04 324	85.66 326	43.86 368	93.84 341	65.48 332	72.53 306	89.38 286

BH-untuned		86.95 190	85.94 191	89.99 204	94.52 163	77.46 259	96.78 158	93.37 305	81.80 232	76.62 274	93.81 203	66.64 247	97.02 216	76.06 262	93.88 138	95.48 208

Effi-MVS+-dtu		84.61 230	84.90 210	83.72 327	91.96 254	63.14 378	94.95 256	93.34 306	85.57 136	79.79 241	87.12 303	61.99 277	95.61 288	83.55 191	85.83 223	92.41 255

CMPMVS	54.94 21	75.71 331	74.56 326	79.17 359	79.69 384	55.98 396	89.59 339	93.30 307	60.28 393	53.85 397	89.07 271	47.68 360	96.33 248	76.55 256	81.02 257	85.22 364
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
cl____		83.27 251	82.12 251	86.74 277	92.20 240	75.95 289	95.11 251	93.27 308	78.44 296	74.82 299	87.02 305	74.19 181	95.19 306	74.67 276	69.32 330	89.09 296

DIV-MVS_self_test		83.27 251	82.12 251	86.74 277	92.19 241	75.92 291	95.11 251	93.26 309	78.44 296	74.81 300	87.08 304	74.19 181	95.19 306	74.66 277	69.30 331	89.11 295

dmvs_re		84.10 238	82.90 240	87.70 254	91.41 265	73.28 312	90.59 334	93.19 310	85.02 151	77.96 260	93.68 204	57.92 309	96.18 255	75.50 268	80.87 258	93.63 244

miper_lstm_enhance		81.66 279	80.66 273	84.67 312	91.19 268	71.97 327	91.94 319	93.19 310	77.86 300	72.27 322	85.26 334	73.46 191	93.42 349	73.71 286	67.05 354	88.61 310

dongtai		69.47 357	68.98 356	70.93 379	86.87 333	58.45 392	88.19 351	93.18 312	63.98 379	56.04 393	80.17 374	70.97 223	79.24 406	33.46 407	47.94 398	75.09 400

eth_miper_zixun_eth		83.12 255	82.01 253	86.47 282	91.85 259	74.80 298	94.33 270	93.18 312	79.11 285	75.74 292	87.25 301	72.71 197	95.32 300	76.78 254	67.13 353	89.27 291

pmmvs4		82.54 265	80.79 269	87.79 252	86.11 344	80.49 170	93.55 291	93.18 312	77.29 307	73.35 311	89.40 269	65.26 258	95.05 315	75.32 270	73.61 300	87.83 328

XVG-ACMP-BASELINE		79.38 303	77.90 301	83.81 323	84.98 359	67.14 362	89.03 344	93.18 312	80.26 263	72.87 317	88.15 288	38.55 386	96.26 250	76.05 263	78.05 282	88.02 325

CANet_DTU		90.98 107	90.04 118	93.83 53	94.76 156	86.23 37	96.32 189	93.12 316	93.11 16	93.71 60	96.82 120	63.08 269	99.48 73	84.29 178	95.12 121	95.77 199

IS-MVSNet		88.67 154	88.16 150	90.20 199	93.61 192	76.86 271	96.77 160	93.07 317	84.02 182	83.62 197	95.60 148	74.69 176	96.24 253	78.43 237	93.66 142	97.49 134

c3_l		83.80 243	82.65 245	87.25 271	92.10 247	77.74 255	95.25 242	93.04 318	78.58 293	76.01 285	87.21 302	75.25 166	95.11 311	77.54 246	68.89 334	88.91 307

mamv4		85.50 216	86.76 183	81.72 344	93.23 205	54.93 401	89.95 338	92.94 319	69.96 361	79.00 248	92.20 227	80.69 70	94.22 334	92.06 98	90.77 171	96.01 193

UnsupCasMVSNet_bld		68.60 362	64.50 366	80.92 349	74.63 402	67.80 354	83.97 382	92.94 319	65.12 377	54.63 396	68.23 403	35.97 392	92.17 361	60.13 354	44.83 403	82.78 378

MVP-Stereo		82.65 264	81.67 259	85.59 299	86.10 345	78.29 228	93.33 296	92.82 321	77.75 301	69.17 343	87.98 290	59.28 294	95.76 276	71.77 295	96.88 92	82.73 379
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Effi-MVS+		90.70 113	89.90 124	93.09 88	93.61 192	83.48 99	95.20 245	92.79 322	83.22 202	91.82 89	95.70 143	71.82 211	97.48 191	91.25 105	93.67 141	98.32 66

EU-MVSNet		76.92 324	76.95 308	76.83 370	84.10 367	54.73 402	91.77 322	92.71 323	72.74 346	69.57 340	88.69 276	58.03 306	87.43 391	64.91 335	70.00 325	88.33 320

pm-mvs1		80.05 295	78.02 300	86.15 288	85.42 352	75.81 292	95.11 251	92.69 324	77.13 309	70.36 335	87.43 296	58.44 300	95.27 303	71.36 299	64.25 365	87.36 340

1112_ss		88.60 157	87.47 168	92.00 140	93.21 206	80.97 153	96.47 176	92.46 325	83.64 197	80.86 228	97.30 98	80.24 75	97.62 177	77.60 244	85.49 226	97.40 141

test_fmvs1		87.79 178	88.52 144	85.62 298	92.98 218	64.31 370	97.88 65	92.42 326	87.95 85	92.24 82	95.82 140	47.94 357	98.44 142	95.31 53	94.09 131	94.09 236

Test_1112_low_res		88.03 172	86.73 184	91.94 142	93.15 209	80.88 157	96.44 179	92.41 327	83.59 199	80.74 230	91.16 244	80.18 76	97.59 179	77.48 247	85.40 227	97.36 144

test_fmvs1_n		86.34 200	86.72 185	85.17 305	87.54 329	63.64 375	96.91 149	92.37 328	87.49 98	91.33 97	95.58 149	40.81 384	98.46 138	95.00 56	93.49 143	93.41 250

BH-RMVSNet		86.84 192	85.28 200	91.49 161	95.35 136	80.26 175	96.95 145	92.21 329	82.86 213	81.77 222	95.46 152	59.34 293	97.64 176	69.79 311	93.81 139	96.57 179

GeoE		86.36 199	85.20 201	89.83 212	93.17 208	76.13 282	97.53 91	92.11 330	79.58 275	80.99 226	94.01 196	66.60 248	96.17 256	73.48 287	89.30 180	97.20 155

LS3D		82.22 271	79.94 285	89.06 223	97.43 82	74.06 307	93.20 302	92.05 331	61.90 385	73.33 312	95.21 161	59.35 292	99.21 90	54.54 376	92.48 157	93.90 240

EG-PatchMatch MVS		74.92 333	72.02 341	83.62 328	83.76 373	73.28 312	93.62 289	92.04 332	68.57 367	58.88 386	83.80 352	31.87 400	95.57 291	56.97 368	78.67 274	82.00 387

IterMVS		80.67 291	79.16 291	85.20 304	89.79 295	76.08 283	92.97 306	91.86 333	80.28 261	71.20 329	85.14 339	57.93 308	91.34 369	72.52 292	70.74 316	88.18 323
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MIMVSNet		79.18 305	75.99 315	88.72 232	87.37 330	80.66 163	79.96 389	91.82 334	77.38 306	74.33 302	81.87 363	41.78 377	90.74 375	66.36 330	83.10 241	94.76 224

IterMVS-SCA-FT		80.51 293	79.10 292	84.73 310	89.63 302	74.66 299	92.98 305	91.81 335	80.05 266	71.06 331	85.18 337	58.04 304	91.40 368	72.48 293	70.70 318	88.12 324

our_test_3		77.90 315	75.37 319	85.48 301	85.39 353	76.74 273	93.63 288	91.67 336	73.39 341	65.72 358	84.65 345	58.20 303	93.13 352	57.82 362	67.87 344	86.57 349

pmmvs5		81.34 282	79.54 288	86.73 280	85.02 358	76.91 269	96.22 194	91.65 337	77.65 302	73.55 306	88.61 277	55.70 326	94.43 330	74.12 282	73.35 303	88.86 308

ACMH	75.40 17	77.99 312	74.96 320	87.10 274	90.67 281	76.41 278	93.19 303	91.64 338	72.47 349	63.44 367	87.61 295	43.34 371	97.16 209	58.34 360	73.94 298	87.72 329
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis1_n		85.60 214	85.70 193	85.33 302	84.79 360	64.98 368	96.83 153	91.61 339	87.36 102	91.00 104	94.84 178	36.14 391	97.18 208	95.66 45	93.03 150	93.82 241

MonoMVSNet		85.68 212	84.22 219	90.03 202	88.43 318	77.83 248	92.95 307	91.46 340	87.28 104	78.11 257	85.96 325	66.31 250	94.81 320	90.71 115	76.81 286	97.46 136

Fast-Effi-MVS+-dtu		83.33 250	82.60 246	85.50 300	89.55 304	69.38 349	96.09 204	91.38 341	82.30 224	75.96 287	91.41 239	56.71 318	95.58 290	75.13 272	84.90 231	91.54 257

YYNet1		73.53 341	70.43 348	82.85 335	84.52 363	71.73 331	91.69 324	91.37 342	67.63 369	46.79 401	81.21 368	55.04 331	90.43 377	55.93 371	59.70 376	86.38 351

ppachtmachnet_test		77.19 321	74.22 329	86.13 289	85.39 353	78.22 231	93.98 279	91.36 343	71.74 353	67.11 348	84.87 343	56.67 319	93.37 351	52.21 381	64.59 362	86.80 345

Anonymous202405211		84.41 234	81.93 255	91.85 147	96.78 97	78.41 225	97.44 99	91.34 344	70.29 359	84.06 188	94.26 189	41.09 381	98.96 112	79.46 225	82.65 249	98.17 78

MDA-MVSNet_test_wron		73.54 340	70.43 348	82.86 334	84.55 361	71.85 328	91.74 323	91.32 345	67.63 369	46.73 402	81.09 369	55.11 330	90.42 378	55.91 372	59.76 375	86.31 352

CR-MVSNet		83.53 247	81.36 264	90.06 201	90.16 290	79.75 188	79.02 395	91.12 346	84.24 177	82.27 214	80.35 372	75.45 156	93.67 345	63.37 343	86.25 216	96.75 174

Patchmtry		77.36 320	74.59 325	85.67 296	89.75 297	75.75 293	77.85 398	91.12 346	60.28 393	71.23 328	80.35 372	75.45 156	93.56 347	57.94 361	67.34 351	87.68 331

LTVRE_ROB	73.68 18	77.99 312	75.74 317	84.74 309	90.45 285	72.02 325	86.41 368	91.12 346	72.57 348	66.63 353	87.27 299	54.95 332	96.98 219	56.29 370	75.98 287	85.21 365
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		77.18 322	76.06 314	80.55 351	83.78 372	60.00 389	90.35 335	91.05 349	77.01 313	66.62 354	87.92 291	47.73 359	94.03 337	71.63 296	68.44 338	87.62 332

CNLPA		86.96 189	85.37 199	91.72 153	97.59 73	79.34 201	97.21 114	91.05 349	74.22 332	78.90 249	96.75 124	67.21 243	98.95 114	74.68 275	90.77 171	96.88 168

Anonymous20240521		72.06 349	69.91 350	78.50 363	77.11 394	61.67 384	91.62 326	90.97 351	65.52 376	62.37 373	79.05 378	36.32 390	90.96 373	57.75 363	68.52 337	82.87 376

KD-MVS_self_test		70.97 354	69.31 353	75.95 375	76.24 399	55.39 400	87.45 358	90.94 352	70.20 360	62.96 372	77.48 382	44.01 367	88.09 385	61.25 351	53.26 387	84.37 370

pmmvs6		74.65 335	71.67 342	83.60 329	79.13 386	69.94 343	93.31 299	90.88 353	61.05 392	65.83 357	84.15 349	43.43 370	94.83 319	66.62 325	60.63 374	86.02 357

test1111		88.11 170	87.04 178	91.35 163	93.15 209	78.79 216	96.57 169	90.78 354	86.88 114	85.04 176	95.20 162	57.23 316	97.39 196	83.88 182	94.59 126	97.87 102

ECVR-MVS		88.35 165	87.25 172	91.65 154	93.54 195	79.40 198	96.56 171	90.78 354	86.78 117	85.57 171	95.25 156	57.25 315	97.56 181	84.73 176	94.80 123	97.98 95

Anonymous20231206		75.29 332	73.64 333	80.22 353	80.75 379	63.38 377	93.36 295	90.71 356	73.09 343	67.12 347	83.70 353	50.33 348	90.85 374	53.63 379	70.10 323	86.44 350

USDC		78.65 307	76.25 313	85.85 291	87.58 327	74.60 301	89.58 340	90.58 357	84.05 181	63.13 369	88.23 286	40.69 385	96.86 229	66.57 327	75.81 290	86.09 356

MSDG		80.62 292	77.77 302	89.14 222	93.43 202	77.24 263	91.89 320	90.18 358	69.86 363	68.02 344	91.94 235	52.21 341	98.84 120	59.32 358	83.12 240	91.35 258

ACMH+	76.62 16	77.47 319	74.94 321	85.05 306	91.07 272	71.58 333	93.26 300	90.01 359	71.80 352	64.76 362	88.55 278	41.62 378	96.48 242	62.35 346	71.00 314	87.09 343

FMVSNet5		76.46 326	74.16 330	83.35 332	90.05 293	76.17 281	89.58 340	89.85 360	71.39 355	65.29 361	80.42 371	50.61 346	87.70 390	61.05 352	69.24 332	86.18 354

ambc				76.02 373	68.11 408	51.43 403	64.97 411	89.59 361		60.49 381	74.49 391	17.17 410	92.46 355	61.50 349	52.85 389	84.17 372

test_fmvs2		79.59 299	79.90 286	78.67 361	82.86 375	55.82 398	95.20 245	89.55 362	81.09 240	80.12 239	89.80 264	34.31 396	93.51 348	87.82 152	78.36 280	86.69 347

ITE_SJBPF				82.38 338	87.00 332	65.59 366		89.55 362	79.99 268	69.37 341	91.30 242	41.60 379	95.33 299	62.86 345	74.63 297	86.24 353

pmmvs-eth3d		73.59 338	70.66 346	82.38 338	76.40 397	73.38 309	89.39 343	89.43 364	72.69 347	60.34 382	77.79 381	46.43 364	91.26 371	66.42 329	57.06 379	82.51 380

test20.03		72.36 347	71.15 344	75.98 374	77.79 390	59.16 391	92.40 314	89.35 365	74.09 334	61.50 377	84.32 347	48.09 354	85.54 397	50.63 386	62.15 372	83.24 375

SixPastTwentyTwo		76.04 327	74.32 328	81.22 346	84.54 362	61.43 385	91.16 329	89.30 366	77.89 298	64.04 364	86.31 319	48.23 353	94.29 333	63.54 342	63.84 367	87.93 327

TransMVSNet (Re)		76.94 323	74.38 327	84.62 314	85.92 347	75.25 296	95.28 239	89.18 367	73.88 336	67.22 346	86.46 314	59.64 288	94.10 336	59.24 359	52.57 390	84.50 369

MIMVSNet1		69.44 358	66.65 362	77.84 364	76.48 396	62.84 379	87.42 359	88.97 368	66.96 374	57.75 391	79.72 377	32.77 399	85.83 396	46.32 395	63.42 368	84.85 367

K. test v3		73.62 337	71.59 343	79.69 355	82.98 374	59.85 390	90.85 333	88.83 369	77.13 309	58.90 385	82.11 361	43.62 369	91.72 366	65.83 331	54.10 385	87.50 338

Baseline_NR-MVSNet		81.22 284	80.07 282	84.68 311	85.32 356	75.12 297	96.48 175	88.80 370	76.24 319	77.28 265	86.40 318	67.61 236	94.39 331	75.73 267	66.73 357	84.54 368

MDA-MVSNet-bldmvs		71.45 351	67.94 358	81.98 342	85.33 355	68.50 353	92.35 315	88.76 371	70.40 358	42.99 405	81.96 362	46.57 363	91.31 370	48.75 393	54.39 384	86.11 355

new-patchmatchnet		68.85 361	65.93 363	77.61 366	73.57 404	63.94 374	90.11 337	88.73 372	71.62 354	55.08 395	73.60 393	40.84 383	87.22 393	51.35 384	48.49 397	81.67 391

Patchmatch-test		78.25 309	74.72 324	88.83 229	91.20 267	74.10 306	73.91 406	88.70 373	59.89 396	66.82 351	85.12 340	78.38 102	94.54 327	48.84 392	79.58 267	97.86 103

OpenMVS_ROB	68.52 20	73.02 344	69.57 351	83.37 331	80.54 382	71.82 329	93.60 290	88.22 374	62.37 383	61.98 375	83.15 358	35.31 395	95.47 293	45.08 398	75.88 289	82.82 377

mvsany_test1		87.58 183	88.22 147	85.67 296	89.78 296	67.18 358	95.25 242	87.93 375	83.96 185	88.79 136	97.06 111	72.52 200	94.53 328	92.21 95	86.45 214	95.30 213

RPSCF		77.73 316	76.63 311	81.06 348	88.66 315	55.76 399	87.77 357	87.88 376	64.82 378	74.14 303	92.79 219	49.22 352	96.81 231	67.47 320	76.88 285	90.62 264

MVS-HIRNet		71.36 353	67.00 359	84.46 318	90.58 282	69.74 346	79.15 394	87.74 377	46.09 406	61.96 376	50.50 410	45.14 366	95.64 285	53.74 378	88.11 200	88.00 326

mmtdpeth		78.04 311	76.76 310	81.86 343	89.60 303	66.12 365	92.34 316	87.18 378	76.83 314	85.55 172	76.49 386	46.77 362	97.02 216	90.85 111	45.24 402	82.43 383

DP-MVS		81.47 280	78.28 297	91.04 173	98.14 55	78.48 221	95.09 254	86.97 379	61.14 391	71.12 330	92.78 220	59.59 289	99.38 78	53.11 380	86.61 212	95.27 214

COLMAP_ROB	73.24 19	75.74 330	73.00 337	83.94 322	92.38 230	69.08 350	91.85 321	86.93 380	61.48 388	65.32 360	90.27 258	42.27 376	96.93 224	50.91 385	75.63 291	85.80 362
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MVStest1		66.93 364	63.01 368	78.69 360	78.56 387	71.43 335	85.51 375	86.81 381	49.79 405	48.57 400	84.15 349	53.46 337	83.31 400	43.14 401	37.15 411	81.34 392

test_fmvs3		69.56 356	69.19 354	70.67 380	69.01 406	47.05 406	90.87 332	86.81 381	71.31 356	66.79 352	77.15 383	16.40 411	83.17 402	81.84 207	62.51 371	81.79 389

test_0402		72.68 345	69.54 352	82.09 341	88.67 314	71.81 330	92.72 310	86.77 383	61.52 387	62.21 374	83.91 351	43.22 372	93.76 344	34.60 406	72.23 310	80.72 393

testgi		74.88 334	73.40 334	79.32 358	80.13 383	61.75 382	93.21 301	86.64 384	79.49 277	66.56 355	91.06 245	35.51 394	88.67 383	56.79 369	71.25 312	87.56 335

TDRefinement		69.20 360	65.78 364	79.48 356	66.04 411	62.21 381	88.21 350	86.12 385	62.92 381	61.03 380	85.61 329	33.23 397	94.16 335	55.82 373	53.02 388	82.08 386

ADS-MVSNet2		79.57 300	77.53 303	85.71 295	93.78 188	72.13 323	79.48 391	86.11 386	73.09 343	80.14 237	79.99 375	62.15 274	90.14 380	59.49 356	83.52 236	94.85 222

LF4IMVS		72.36 347	70.82 345	76.95 369	79.18 385	56.33 395	86.12 370	86.11 386	69.30 365	63.06 370	86.66 310	33.03 398	92.25 358	65.33 333	68.64 336	82.28 384

TinyColmap		72.41 346	68.99 355	82.68 336	88.11 321	69.59 347	88.41 349	85.20 388	65.55 375	57.91 389	84.82 344	30.80 402	95.94 265	51.38 382	68.70 335	82.49 382

mvs5depth		71.40 352	68.36 357	80.54 352	75.31 401	65.56 367	79.94 390	85.14 389	69.11 366	71.75 325	81.59 364	41.02 382	93.94 339	60.90 353	50.46 392	82.10 385

pmmvs3		65.75 366	62.18 369	76.45 372	67.12 410	64.54 369	88.68 347	85.05 390	54.77 404	57.54 392	73.79 392	29.40 403	86.21 395	55.49 375	47.77 399	78.62 396

new_pmnet		66.18 365	63.18 367	75.18 377	76.27 398	61.74 383	83.79 383	84.66 391	56.64 402	51.57 398	71.85 401	31.29 401	87.93 386	49.98 388	62.55 370	75.86 399

AllTest		75.92 328	73.06 336	84.47 316	92.18 242	67.29 356	91.07 330	84.43 392	67.63 369	63.48 365	90.18 259	38.20 387	97.16 209	57.04 366	73.37 301	88.97 304

TestCases				84.47 316	92.18 242	67.29 356		84.43 392	67.63 369	63.48 365	90.18 259	38.20 387	97.16 209	57.04 366	73.37 301	88.97 304

ttmdpeth		69.58 355	66.92 361	77.54 367	75.95 400	62.40 380	88.09 352	84.32 394	62.87 382	65.70 359	86.25 321	36.53 389	88.53 384	55.65 374	46.96 401	81.70 390

LCM-MVSNet-Re		83.75 244	83.54 231	84.39 320	93.54 195	64.14 372	92.51 311	84.03 395	83.90 188	66.14 356	86.59 311	67.36 241	92.68 353	84.89 175	92.87 151	96.35 184

Gipuma		45.11 381	42.05 383	54.30 397	80.69 380	51.30 404	35.80 415	83.81 396	28.13 411	27.94 415	34.53 415	11.41 418	76.70 411	21.45 414	54.65 382	34.90 415
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		52.52 375	48.24 378	65.35 385	47.63 422	41.45 414	72.55 407	83.62 397	31.75 410	37.66 408	57.92 408	9.19 420	76.76 410	49.26 390	44.60 404	77.84 397

FPMVS		55.09 373	52.93 376	61.57 391	55.98 415	40.51 416	83.11 386	83.41 398	37.61 409	34.95 410	71.95 399	14.40 412	76.95 409	29.81 409	65.16 361	67.25 404

Patchmatch-RL test		76.65 325	74.01 332	84.55 315	77.37 393	64.23 371	78.49 397	82.84 399	78.48 294	64.63 363	73.40 394	76.05 144	91.70 367	76.99 251	57.84 378	97.72 114

DSMNet-mixed		73.13 343	72.45 338	75.19 376	77.51 392	46.82 407	85.09 378	82.01 400	67.61 373	69.27 342	81.33 367	50.89 344	86.28 394	54.54 376	83.80 235	92.46 253

lessismore_v0				79.98 354	80.59 381	58.34 393		80.87 401		58.49 387	83.46 355	43.10 373	93.89 340	63.11 344	48.68 395	87.72 329

test_f		64.01 367	62.13 370	69.65 381	63.00 413	45.30 412	83.66 384	80.68 402	61.30 389	55.70 394	72.62 397	14.23 413	84.64 398	69.84 310	58.11 377	79.00 395

door								80.13 403

door-mid								79.75 404

PM-MVS		69.32 359	66.93 360	76.49 371	73.60 403	55.84 397	85.91 371	79.32 405	74.72 329	61.09 379	78.18 380	21.76 407	91.10 372	70.86 305	56.90 380	82.51 380

mvsany_test3		67.19 363	65.34 365	72.72 378	63.08 412	48.57 405	83.12 385	78.09 406	72.07 350	61.21 378	77.11 384	22.94 406	87.78 389	78.59 234	51.88 391	81.80 388

dmvs_testset		72.00 350	73.36 335	67.91 382	83.83 371	31.90 422	85.30 376	77.12 407	82.80 214	63.05 371	92.46 222	61.54 281	82.55 404	42.22 403	71.89 311	89.29 290

ANet_high		46.22 378	41.28 385	61.04 392	39.91 424	46.25 410	70.59 408	76.18 408	58.87 399	23.09 416	48.00 413	12.58 416	66.54 416	28.65 411	13.62 417	70.35 402

test_method		56.77 370	54.53 374	63.49 389	76.49 395	40.70 415	75.68 402	74.24 409	19.47 417	48.73 399	71.89 400	19.31 408	65.80 417	57.46 365	47.51 400	83.97 373

APD_test1		56.56 371	53.58 375	65.50 384	67.93 409	46.51 409	77.24 401	72.95 410	38.09 408	42.75 406	75.17 388	13.38 414	82.78 403	40.19 404	54.53 383	67.23 405

EGC-MVSNET		52.46 376	47.56 379	67.15 383	81.98 377	60.11 388	82.54 387	72.44 411	0.11 423	0.70 424	74.59 390	25.11 405	83.26 401	29.04 410	61.51 373	58.09 408

PMMVS2		50.90 377	46.31 380	64.67 386	55.53 416	46.67 408	77.30 400	71.02 412	40.89 407	34.16 411	59.32 406	9.83 419	76.14 412	40.09 405	28.63 414	71.21 401

WB-MVS		57.26 369	56.22 372	60.39 393	69.29 405	35.91 420	86.39 369	70.06 413	59.84 397	46.46 403	72.71 396	51.18 343	78.11 407	15.19 417	34.89 412	67.14 406

SSC-MVS		56.01 372	54.96 373	59.17 394	68.42 407	34.13 421	84.98 379	69.23 414	58.08 401	45.36 404	71.67 402	50.30 349	77.46 408	14.28 418	32.33 413	65.91 407

test_vis1_rt		73.96 336	72.40 339	78.64 362	83.91 370	61.16 386	95.63 227	68.18 415	76.32 316	60.09 383	74.77 389	29.01 404	97.54 185	87.74 153	75.94 288	77.22 398

MTMP							97.53 91	68.16 416

DeepMVS_CX				64.06 388	78.53 388	43.26 413		68.11 417	69.94 362	38.55 407	76.14 387	18.53 409	79.34 405	43.72 399	41.62 408	69.57 403

PMVS	34.80 23	39.19 383	35.53 386	50.18 398	29.72 425	30.30 423	59.60 413	66.20 418	26.06 414	17.91 418	49.53 411	3.12 424	74.09 413	18.19 416	49.40 394	46.14 412
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testf1		45.70 379	42.41 381	55.58 395	53.29 419	40.02 417	68.96 409	62.67 419	27.45 412	29.85 412	61.58 404	5.98 422	73.83 414	28.49 412	43.46 406	52.90 409

APD_test2		45.70 379	42.41 381	55.58 395	53.29 419	40.02 417	68.96 409	62.67 419	27.45 412	29.85 412	61.58 404	5.98 422	73.83 414	28.49 412	43.46 406	52.90 409

tmp_tt		41.54 382	41.93 384	40.38 400	20.10 426	26.84 424	61.93 412	59.09 421	14.81 419	28.51 414	80.58 370	35.53 393	48.33 421	63.70 341	13.11 418	45.96 414

MVE	35.65 22	33.85 384	29.49 389	46.92 399	41.86 423	36.28 419	50.45 414	56.52 422	18.75 418	18.28 417	37.84 414	2.41 425	58.41 418	18.71 415	20.62 415	46.06 413
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		32.70 385	32.39 387	33.65 401	53.35 418	25.70 425	74.07 405	53.33 423	21.08 415	17.17 419	33.63 417	11.85 417	54.84 419	12.98 419	14.04 416	20.42 416

EMVS		31.70 386	31.45 388	32.48 402	50.72 421	23.95 426	74.78 404	52.30 424	20.36 416	16.08 420	31.48 418	12.80 415	53.60 420	11.39 420	13.10 419	19.88 417

test_vis3_rt		54.10 374	51.04 377	63.27 390	58.16 414	46.08 411	84.17 381	49.32 425	56.48 403	36.56 409	49.48 412	8.03 421	91.91 364	67.29 321	49.87 393	51.82 411

N_pmnet		61.30 368	60.20 371	64.60 387	84.32 364	17.00 428	91.67 325	10.98 426	61.77 386	58.45 388	78.55 379	49.89 350	91.83 365	42.27 402	63.94 366	84.97 366

wuyk23d		14.10 388	13.89 391	14.72 403	55.23 417	22.91 427	33.83 416	3.56 427	4.94 420	4.11 421	2.28 423	2.06 426	19.66 422	10.23 421	8.74 420	1.59 420

testmvs		9.92 389	12.94 392	0.84 405	0.65 427	0.29 430	93.78 286	0.39 428	0.42 421	2.85 422	15.84 421	0.17 428	0.30 424	2.18 422	0.21 421	1.91 419

test123		9.07 390	11.73 393	1.11 404	0.50 428	0.77 429	89.44 342	0.20 429	0.34 422	2.15 423	10.72 422	0.34 427	0.32 423	1.79 423	0.08 422	2.23 418

mmdepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

monomultidepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

test_blank		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet_test		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

DCPMVS		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

pcd_1.5k_mvsjas		5.92 392	7.89 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	71.04 220	0.00 425	0.00 424	0.00 423	0.00 421

sosnet-low-res		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

sosnet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uncertanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

Regformer		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

n2								0.00 430

nn								0.00 430

ab-mvs-re		8.11 391	10.81 394	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	97.30 98	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

WAC-MVS						67.18 358								49.00 391

PC_three_1452									91.12 36	98.33 2	98.42 30	92.51 2	99.81 22	98.96 4	99.37 1	99.70 3

eth-test2					0.00 429

eth-test					0.00 429

OPU-MVS				97.30 2	99.19 7	92.31 3	99.12 12				98.54 20	92.06 3	99.84 13	99.11 3	99.37 1	99.74 1

test_0728_THIRD									88.38 74	96.69 18	98.76 12	89.64 12	99.76 31	97.47 24	98.84 23	99.38 14

GSMVS																97.54 127

test_part2					98.90 19	85.14 69				96.07 29

sam_mvs1												77.59 115				97.54 127

sam_mvs												75.35 163

test_post1							85.88 372				30.24 419	73.77 186	95.07 314	73.89 283

test_post											33.80 416	76.17 142	95.97 261

patchmatchnet-post											77.09 385	77.78 114	95.39 295

gm-plane-assit					92.27 236	79.64 194			84.47 168		95.15 166		97.93 160	85.81 167

test9_res														96.00 40	99.03 13	98.31 68

agg_prior2														94.30 64	99.00 15	98.57 53

test_prior4						82.34 119	97.75 75

test_prior2							98.37 39		86.08 126	94.57 50	98.02 54	83.14 53		95.05 55	98.79 27

旧先验2							96.97 142		74.06 335	96.10 28			97.76 171	88.38 148

新几何2							96.42 182

原ACMM2							96.84 152

testdata2													99.48 73	76.45 258

segment_acmp												82.69 59

testdata1							95.57 231		87.44 99

plane_prior7					91.86 257	77.55 258

plane_prior6					91.98 253	77.92 244						64.77 260

plane_prior4											94.15 193

plane_prior3						77.75 254			90.17 52	81.33 223

plane_prior2							97.18 118		89.89 54

plane_prior1					91.95 255

plane_prior						77.96 241	97.52 94		90.36 50						82.96 244

HQP5-MVS						78.48 221

HQP-NCC					92.08 248		97.63 81		90.52 45	82.30 210

ACMP_Plane					92.08 248		97.63 81		90.52 45	82.30 210

BP-MVS														87.67 155

HQP4-MVS										82.30 210			97.32 199			91.13 259

HQP2-MVS												65.40 255

NP-MVS					92.04 252	78.22 231					94.56 183

MDTV_nov1_ep13_2view						81.74 135	86.80 364		80.65 249	85.65 170		74.26 180		76.52 257		96.98 161

ACMMP++_ref															78.45 279

ACMMP++															79.05 271

Test By Simon												71.65 213

High-resolution multi-view benchmark