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		88.92 148	87.65 160	92.73 105	96.30 103	85.62 55	97.85 66	98.86 1	84.38 172	84.82 182	93.99 199	75.12 170	98.01 159	70.86 307	86.67 213	94.56 232

thres100view900		88.30 168	86.95 182	92.33 123	96.10 110	84.90 77	97.14 127	98.85 2	82.69 219	83.41 200	93.66 207	75.43 160	97.93 162	69.04 315	86.24 220	94.17 234

tfpn200view9		88.48 162	87.15 176	92.47 115	96.21 106	85.30 63	97.44 101	98.85 2	83.37 202	83.99 192	93.82 203	75.36 163	97.93 162	69.04 315	86.24 220	94.17 234

thres600view7		88.06 173	86.70 188	92.15 135	96.10 110	85.17 69	97.14 127	98.85 2	82.70 218	83.41 200	93.66 207	75.43 160	97.82 171	67.13 324	85.88 224	93.45 250

thres400		88.42 165	87.15 176	92.23 129	96.21 106	85.30 63	97.44 101	98.85 2	83.37 202	83.99 192	93.82 203	75.36 163	97.93 162	69.04 315	86.24 220	93.45 250

MVS_111021_HR		93.41 42	93.39 45	93.47 79	97.34 89	82.83 112	97.56 90	98.27 6	89.16 63	89.71 120	97.14 105	79.77 85	99.56 66	93.65 73	97.94 59	98.02 88

sss		90.87 113	89.96 123	93.60 69	94.15 178	83.84 94	97.14 127	98.13 7	85.93 133	89.68 121	96.09 137	71.67 214	99.30 83	87.69 156	89.16 184	97.66 120

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 70	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 82	96.97 115	81.30 68	98.99 110	88.54 145	98.88 20	99.20 25

VNet		92.11 79	91.22 91	94.79 28	96.91 95	86.98 30	97.91 63	97.96 10	86.38 123	93.65 61	95.74 143	70.16 231	98.95 114	93.39 75	88.87 189	98.43 61

test_yl		91.46 95	90.53 105	94.24 42	97.41 83	85.18 65	98.08 52	97.72 11	80.94 244	89.85 117	96.14 135	75.61 152	98.81 122	90.42 124	88.56 195	98.74 42

DCV-MVSNet		91.46 95	90.53 105	94.24 42	97.41 83	85.18 65	98.08 52	97.72 11	80.94 244	89.85 117	96.14 135	75.61 152	98.81 122	90.42 124	88.56 195	98.74 42

WTY-MVS		92.65 65	91.68 82	95.56 14	96.00 112	88.90 13	98.23 43	97.65 13	88.57 70	89.82 119	97.22 103	79.29 89	99.06 107	89.57 134	88.73 191	98.73 46

EPNet		94.06 33	94.15 32	93.76 56	97.27 91	84.35 84	98.29 41	97.64 14	94.57 6	95.36 35	96.88 118	79.96 84	99.12 103	91.30 105	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 91	90.37 111	95.39 19	96.12 109	88.25 17	90.22 338	97.58 15	88.33 78	90.50 112	91.96 235	79.26 90	99.06 107	90.29 126	89.07 185	98.88 37

baseline2		90.39 122	90.21 115	90.93 178	90.86 279	80.99 154	95.20 247	97.41 16	86.03 131	80.07 242	94.61 184	90.58 6	97.47 194	87.29 160	89.86 179	94.35 233

test2506		90.96 110	90.39 109	92.65 109	93.54 195	82.46 119	96.37 186	97.35 17	86.78 119	87.55 153	95.25 158	77.83 115	97.50 191	84.07 182	94.80 124	97.98 95

PVSNet	82.34 9	89.02 145	87.79 158	92.71 106	95.49 131	81.50 144	97.70 79	97.29 18	87.76 93	85.47 175	95.12 170	56.90 319	98.90 118	80.33 217	94.02 134	97.71 116

testing222		91.09 105	90.49 107	92.87 98	95.82 119	85.04 72	96.51 176	97.28 19	86.05 129	89.13 131	95.34 157	80.16 80	96.62 241	85.82 168	88.31 199	96.96 164

PGM-MVS		91.93 82	91.80 80	92.32 125	98.27 50	79.74 192	95.28 241	97.27 20	83.83 192	90.89 108	97.78 71	76.12 145	99.56 66	88.82 142	97.93 61	97.66 120

IB-MVS	85.34 4	88.67 156	87.14 178	93.26 82	93.12 212	84.32 85	98.76 26	97.27 20	87.19 111	79.36 248	90.45 257	83.92 50	98.53 133	84.41 179	69.79 328	96.93 166
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	92.45 116	95.29 138	80.96 156	99.29 2	97.21 22	94.50 7	97.29 13	98.44 27	82.15 62	99.78 28	98.56 7	97.68 67	96.61 179

patch_mono-2		95.14 13	96.08 7	92.33 123	98.44 43	77.84 249	98.43 36	97.21 22	92.58 19	97.68 10	97.65 79	86.88 27	99.83 17	98.25 9	97.60 69	99.33 18

MVS		90.60 117	88.64 143	96.50 5	94.25 174	90.53 8	93.33 298	97.21 22	77.59 305	78.88 252	97.31 95	71.52 217	99.69 49	89.60 133	98.03 56	99.27 22

ETVMVS		90.99 108	90.26 112	93.19 86	95.81 120	85.64 54	96.97 144	97.18 25	85.43 141	88.77 140	94.86 179	82.00 64	96.37 248	82.70 203	88.60 192	97.57 127

CSCG		92.02 80	91.65 83	93.12 88	98.53 36	80.59 166	97.47 98	97.18 25	77.06 314	84.64 187	97.98 58	83.98 48	99.52 69	90.72 115	97.33 78	99.23 24

fmvsm_s_conf0.5_n		93.69 37	94.13 33	92.34 121	94.56 160	82.01 124	99.07 16	97.13 27	92.09 23	96.25 26	98.53 22	76.47 137	99.80 25	98.39 8	94.71 126	95.22 217

PHI-MVS		93.59 39	93.63 38	93.48 77	98.05 58	81.76 136	98.64 31	97.13 27	82.60 221	94.09 56	98.49 25	80.35 74	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 30	99.95 3	97.59 23	99.18 7	99.00 31

h-mvs33		89.30 141	88.95 138	90.36 196	95.07 146	76.04 286	96.96 146	97.11 30	90.39 48	92.22 84	95.10 171	74.70 175	98.86 119	93.14 83	65.89 361	96.16 192

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 86	98.46 26	87.33 25	99.97 2	97.21 29	99.31 4	99.63 7

testing11		92.48 70	92.04 77	93.78 55	95.94 116	86.00 40	97.56 90	97.08 32	87.52 99	89.32 128	95.40 155	84.60 39	98.02 158	91.93 101	89.04 186	97.32 147

VPA-MVSNet		85.32 221	83.83 226	89.77 217	90.25 289	82.63 114	96.36 187	97.07 33	83.03 210	81.21 227	89.02 274	61.58 282	96.31 251	85.02 176	70.95 317	90.36 269

UBG		92.68 64	92.35 66	93.70 63	95.61 127	85.65 53	97.25 114	97.06 34	87.92 88	89.28 129	95.03 173	86.06 33	98.07 155	92.24 94	90.69 175	97.37 145

UWE-MVS		88.56 161	88.91 140	87.50 265	94.17 177	72.19 324	95.82 221	97.05 35	84.96 156	84.78 183	93.51 211	81.33 66	94.75 323	79.43 228	89.17 183	95.57 206

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 95	97.08 110	83.32 54	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 76	94.94 150	86.26 36	81.62 390	97.00 37		88.32 147	94.30 190	91.23 5	96.21 256	88.49 147	97.43 75	98.00 93

fmvsm_s_conf0.5_n_a		93.34 43	93.71 36	92.22 130	93.38 203	81.71 139	98.86 25	96.98 38	91.64 29	96.85 16	98.55 19	75.58 155	99.77 29	97.88 19	93.68 142	95.18 218

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	89.33 138	99.25 6	99.70 3

gg-mvs-nofinetune		85.48 220	82.90 242	93.24 83	94.51 166	85.82 45	79.22 395	96.97 40	61.19 392	87.33 156	53.01 411	90.58 6	96.07 259	86.07 167	97.23 81	97.81 109

NCCC		95.63 7	95.94 8	94.69 32	99.21 6	85.15 70	99.16 7	96.96 41	94.11 9	95.59 34	98.64 17	85.07 36	99.91 4	95.61 46	99.10 9	99.00 31

FIs		86.73 198	86.10 192	88.61 235	90.05 295	80.21 179	96.14 203	96.95 42	85.56 140	78.37 256	92.30 227	76.73 134	95.28 304	79.51 226	79.27 271	90.35 270

PVSNet_0	77.72 15	81.70 279	78.95 296	89.94 210	90.77 282	76.72 276	95.96 210	96.95 42	85.01 154	70.24 339	88.53 282	52.32 341	98.20 151	86.68 166	44.08 407	94.89 222

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 34	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 90	98.64 31	96.93 44	90.71 42	93.08 70	98.70 15	79.98 83	99.21 90	94.12 68	99.07 11	98.63 51

testing99		91.91 83	91.35 88	93.60 69	95.98 114	85.70 48	97.31 112	96.92 46	86.82 117	88.91 135	95.25 158	84.26 46	97.89 169	88.80 143	87.94 203	97.21 155

testing91		91.90 84	91.31 90	93.66 65	95.99 113	85.68 50	97.39 108	96.89 47	86.75 121	88.85 137	95.23 161	83.93 49	97.90 168	88.91 140	87.89 204	97.41 141

UniMVSNet (Re)		85.31 222	84.23 220	88.55 236	89.75 299	80.55 168	96.72 163	96.89 47	85.42 142	78.40 255	88.93 275	75.38 162	95.52 294	78.58 237	68.02 345	89.57 285

FC-MVSNet-test		85.96 208	85.39 200	87.66 258	89.38 310	78.02 240	95.65 228	96.87 49	85.12 151	77.34 265	91.94 237	76.28 143	94.74 324	77.09 252	78.82 275	90.21 273

EI-MVSNet-Vis-set		91.84 86	91.77 81	92.04 140	97.60 72	81.17 148	96.61 169	96.87 49	88.20 82	89.19 130	97.55 87	78.69 101	99.14 100	90.29 126	90.94 172	95.80 200

IU-MVS					99.03 15	85.34 60		96.86 51	92.05 27	98.74 1				98.15 11	98.97 17	99.42 13

BP-MVS1		93.55 40	93.50 42	93.71 62	92.64 228	85.39 59	97.78 72	96.84 52	89.52 58	92.00 87	97.06 112	88.21 20	98.03 157	91.45 104	96.00 112	97.70 117

MSC_two_6792asdad				97.14 3	99.05 9	92.19 4		96.83 53					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 53					99.81 22	98.08 14	98.81 24	99.43 11

EI-MVSNet-UG-set		91.35 99	91.22 91	91.73 154	97.39 86	80.68 164	96.47 178	96.83 53	87.92 88	88.30 148	97.36 94	77.84 114	99.13 102	89.43 137	89.45 181	95.37 212

SED-MVS		95.88 5	96.22 4	94.87 25	99.03 15	85.03 73	99.12 12	96.78 56	88.72 67	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 56	88.72 67	97.70 8	98.91 2	87.86 22	99.82 19	98.15 11	99.00 15	99.47 9

test_241102_ONE					99.03 15	85.03 73		96.78 56	88.72 67	97.79 6	98.90 5	88.48 17	99.82 19

test0726					99.05 9	85.18 65	99.11 15	96.78 56	88.75 65	97.65 11	98.91 2	87.69 23

MSP-MVS		95.62 8	96.54 1	92.86 99	98.31 48	80.10 183	97.42 105	96.78 56	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							96.87 153	96.78 56	77.39 307				99.52 69	79.95 223		98.43 61

DVP-MVS++		96.05 4	96.41 3	94.96 24	99.05 9	85.34 60	98.13 49	96.77 62	88.38 75	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 62					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 98	96.77 62	85.32 144	97.92 3	98.70 15	83.09 57	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 93	91.64 84	91.47 164	95.74 123	78.79 218	96.15 202	96.77 62	88.49 72	88.64 142	97.07 111	72.33 206	99.19 96	93.13 85	96.48 102	96.43 184

3Dnovator	82.32 10	89.33 140	87.64 161	94.42 37	93.73 191	85.70 48	97.73 77	96.75 66	86.73 122	76.21 285	95.93 139	62.17 275	99.68 51	81.67 210	97.81 63	97.88 100

DPE-MVS		95.32 11	95.55 12	94.64 33	98.79 23	84.87 78	97.77 73	96.74 67	86.11 126	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		90.05 127	89.96 123	90.33 197	97.47 77	83.86 92	98.02 58	96.73 68	87.98 86	89.53 125	89.61 269	76.42 139	99.57 64	94.29 65	79.59 268	87.57 336

PVSNet_Blended		93.13 44	92.98 52	93.57 71	97.47 77	83.86 92	99.32 1	96.73 68	91.02 40	89.53 125	96.21 134	76.42 139	99.57 64	94.29 65	95.81 116	97.29 151

ACMMP		90.39 122	89.97 122	91.64 157	97.58 74	78.21 236	96.78 160	96.72 70	84.73 161	84.72 185	97.23 102	71.22 219	99.63 57	88.37 150	92.41 160	97.08 161
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 88	97.44 81	81.60 143		96.71 71	74.54 333	91.22 102	97.57 83	79.13 93	99.51 71	77.40 251	98.46 40	98.26 73

test_one_0601					98.91 18	84.56 83		96.70 72	88.06 84	96.57 23	98.77 10	88.04 21

HFP-MVS		92.89 51	92.86 56	92.98 94	98.71 25	81.12 149	97.58 88	96.70 72	85.20 149	91.75 92	97.97 60	78.47 103	99.71 45	90.95 108	98.41 43	98.12 84

ACMMPR		92.69 62	92.67 59	92.75 103	98.66 28	80.57 167	97.58 88	96.69 74	85.20 149	91.57 94	97.92 61	77.01 127	99.67 53	90.95 108	98.41 43	98.00 93

DeepPCF-MVS	89.82 1	94.61 22	96.17 5	89.91 211	97.09 94	70.21 344	98.99 23	96.69 74	95.57 2	95.08 41	99.23 1	86.40 31	99.87 8	97.84 20	98.66 32	99.65 6

thisisatest0530		89.65 135	89.02 135	91.53 161	93.46 201	80.78 162	96.52 174	96.67 76	81.69 237	83.79 197	94.90 178	88.85 14	97.68 176	77.80 240	87.49 209	96.14 193

tttt0517		88.57 160	88.19 151	89.71 218	93.00 214	75.99 290	95.67 226	96.67 76	80.78 248	81.82 222	94.40 188	88.97 13	97.58 182	76.05 265	86.31 217	95.57 206

thisisatest0515		90.95 111	90.26 112	93.01 93	94.03 186	84.27 88	97.91 63	96.67 76	83.18 205	86.87 163	95.51 153	88.66 15	97.85 170	80.46 216	89.01 187	96.92 168

ACMMP_NAP		93.46 41	93.23 47	94.17 45	97.16 92	84.28 87	96.82 157	96.65 79	86.24 124	94.27 53	97.99 55	77.94 111	99.83 17	93.39 75	98.57 34	98.39 63

TEST9					98.64 31	83.71 95	97.82 68	96.65 79	84.29 177	95.16 37	98.09 48	84.39 41	99.36 81

train_agg		94.28 27	94.45 25	93.74 58	98.64 31	83.71 95	97.82 68	96.65 79	84.50 168	95.16 37	98.09 48	84.33 42	99.36 81	95.91 42	98.96 19	98.16 79

1314		88.94 147	87.20 175	94.17 45	93.21 206	85.73 47	93.33 298	96.64 82	82.89 213	75.98 288	96.36 131	66.83 248	99.39 77	83.52 196	96.02 111	97.39 144

DeepC-MVS_fast	89.06 2	94.48 25	94.30 29	95.02 22	98.86 21	85.68 50	98.06 55	96.64 82	93.64 12	91.74 93	98.54 20	80.17 79	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 98	97.81 70	96.63 84	84.50 168	95.10 40	98.11 47	84.33 42	99.23 88

FE-MVS		86.06 207	84.15 223	91.78 151	94.33 173	79.81 187	84.58 382	96.61 85	76.69 317	85.00 179	87.38 299	70.71 227	98.37 144	70.39 310	91.70 168	97.17 158

原ACMM1				91.22 172	97.77 65	78.10 239		96.61 85	81.05 243	91.28 101	97.42 92	77.92 113	98.98 111	79.85 225	98.51 36	96.59 180

MAR-MVS		90.63 116	90.22 114	91.86 147	98.47 42	78.20 237	97.18 120	96.61 85	83.87 191	88.18 149	98.18 41	68.71 235	99.75 36	83.66 192	97.15 84	97.63 123
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	83.22 107		96.60 88	82.88 214	93.61 63	98.06 53	82.93 58	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 89	94.71 4	97.08 15	97.99 55	78.69 101	99.86 10	99.15 2	97.85 62	98.91 35

SteuartSystems-ACMMP		94.13 32	94.44 26	93.20 85	95.41 133	81.35 146	99.02 21	96.59 89	89.50 59	94.18 55	98.36 33	83.68 52	99.45 75	94.77 58	98.45 41	98.81 39
Skip Steuart: Steuart Systems R&D Blog.
D2MVS		82.67 265	81.55 262	86.04 292	87.77 327	76.47 278	95.21 246	96.58 91	82.66 220	70.26 338	85.46 335	60.39 287	95.80 274	76.40 261	79.18 272	85.83 363

save fliter					98.24 51	83.34 104	98.61 33	96.57 92	91.32 33

TESTMET0.1,1		89.83 131	89.34 132	91.31 166	92.54 231	80.19 180	97.11 130	96.57 92	86.15 125	86.85 164	91.83 239	79.32 88	96.95 223	81.30 211	92.35 161	96.77 174

agg_prior					98.59 35	83.13 108		96.56 94		94.19 54			99.16 99

旧先验1					97.39 86	79.58 197		96.54 95			98.08 51	84.00 47			97.42 76	97.62 124

WR-MVS_H		81.02 288	80.09 282	83.79 326	88.08 324	71.26 339	94.46 266	96.54 95	80.08 267	72.81 320	86.82 309	70.36 229	92.65 356	64.18 339	67.50 351	87.46 341

9.14			94.26 31		98.10 57		98.14 46	96.52 97	84.74 160	94.83 47	98.80 7	82.80 60	99.37 80	95.95 41	98.42 42

region2R		92.72 58	92.70 58	92.79 102	98.68 26	80.53 171	97.53 93	96.51 98	85.22 147	91.94 90	97.98 58	77.26 122	99.67 53	90.83 113	98.37 46	98.18 77

EPP-MVSNet		89.76 132	89.72 128	89.87 212	93.78 188	76.02 289	97.22 115	96.51 98	79.35 280	85.11 177	95.01 175	84.82 37	97.10 216	87.46 159	88.21 201	96.50 182

ZNCC-MVS		92.75 54	92.60 61	93.23 84	98.24 51	81.82 134	97.63 82	96.50 100	85.00 155	91.05 104	97.74 72	78.38 104	99.80 25	90.48 119	98.34 48	98.07 86

test11								96.50 100

EPNet_dtu		87.65 184	87.89 155	86.93 278	94.57 159	71.37 338	96.72 163	96.50 100	88.56 71	87.12 160	95.02 174	75.91 149	94.01 340	66.62 327	90.00 177	95.42 211
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testdata				90.13 202	95.92 117	74.17 307		96.49 103	73.49 342	94.82 48	97.99 55	78.80 99	97.93 162	83.53 195	97.52 71	98.29 70

DVP-MVS		95.58 9	95.91 9	94.57 34	99.05 9	85.18 65	99.06 17	96.46 104	88.75 65	96.69 18	98.76 12	87.69 23	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	78.41 227	95.87 217	96.46 104	71.97 353	89.66 122	97.45 88	76.33 142			98.24 51	98.30 69

XVS		92.69 62	92.71 57	92.63 111	98.52 37	80.29 174	97.37 109	96.44 106	87.04 113	91.38 96	97.83 69	77.24 124	99.59 60	90.46 121	98.07 54	98.02 88

X-MVStestdata		86.26 204	84.14 224	92.63 111	98.52 37	80.29 174	97.37 109	96.44 106	87.04 113	91.38 96	20.73 422	77.24 124	99.59 60	90.46 121	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 77	96.43 108	84.02 184	95.07 42	98.74 14	82.93 58	99.38 78	95.42 50	98.51 36	98.32 66

TSAR-MVS + MP.		94.79 20	95.17 18	93.64 66	97.66 69	84.10 89	95.85 219	96.42 109	91.26 34	97.49 12	96.80 123	86.50 29	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	83.40 103	98.04 57	96.41 110	85.79 135	95.00 43	98.28 37	84.32 45	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		85.49 219	84.59 213	88.21 247	89.44 309	79.36 201	96.71 165	96.41 110	85.22 147	78.11 259	90.98 250	76.97 129	95.14 311	79.14 232	68.30 342	90.12 276

test_prior				93.09 90	98.68 26	81.91 129		96.40 112					99.06 107			98.29 70

CP-MVS		92.54 68	92.60 61	92.34 121	98.50 40	79.90 186	98.40 38	96.40 112	84.75 159	90.48 113	98.09 48	77.40 121	99.21 90	91.15 107	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	96.39 114	94.07 10	95.34 36	97.80 70	76.83 132	99.87 8	97.08 31	97.64 68	98.89 36

GST-MVS		92.43 72	92.22 72	93.04 92	98.17 54	81.64 141	97.40 107	96.38 115	84.71 162	90.90 107	97.40 93	77.55 119	99.76 31	89.75 132	97.74 65	97.72 114

alignmvs		92.97 49	92.26 70	95.12 21	95.54 130	87.77 22	98.67 29	96.38 115	88.04 85	93.01 71	97.45 88	79.20 92	98.60 128	93.25 81	88.76 190	98.99 33

PAPM		92.87 52	92.40 65	94.30 39	92.25 241	87.85 21	96.40 185	96.38 115	91.07 38	88.72 141	96.90 116	82.11 63	97.37 200	90.05 129	97.70 66	97.67 119

test_fmvsmconf_n		93.99 34	94.36 28	92.86 99	92.82 221	81.12 149	99.26 4	96.37 118	93.47 13	95.16 37	98.21 39	79.00 94	99.64 55	98.21 10	96.73 98	97.83 106

test12				94.25 41	98.34 46	85.55 56		96.35 119		92.36 81		80.84 69	99.22 89		98.31 49	97.98 95

MTGPA								96.33 120

MTAPA		92.45 71	92.31 68	92.86 99	97.90 61	80.85 160	92.88 310	96.33 120	87.92 88	90.20 116	98.18 41	76.71 135	99.76 31	92.57 92	98.09 53	97.96 98

reproduce_monomvs		87.80 179	87.60 165	88.40 239	96.56 98	80.26 177	95.80 222	96.32 122	91.56 31	73.60 307	88.36 285	88.53 16	96.25 254	90.47 120	67.23 354	88.67 311

ET-MVSNet_ETH3D		90.01 128	89.03 134	92.95 95	94.38 171	86.77 32	98.14 46	96.31 123	89.30 61	63.33 370	96.72 127	90.09 10	93.63 348	90.70 117	82.29 255	98.46 59

EPMVS		87.47 187	85.90 194	92.18 132	95.41 133	82.26 123	87.00 365	96.28 124	85.88 134	84.23 189	85.57 332	75.07 171	96.26 252	71.14 305	92.50 158	98.03 87

WB-MVSnew		84.08 241	83.51 234	85.80 294	91.34 268	76.69 277	95.62 230	96.27 125	81.77 235	81.81 223	92.81 219	58.23 303	94.70 325	66.66 326	87.06 210	85.99 360

CDPH-MVS		93.12 45	92.91 53	93.74 58	98.65 30	83.88 91	97.67 81	96.26 126	83.00 211	93.22 67	98.24 38	81.31 67	99.21 90	89.12 139	98.74 30	98.14 81

WR-MVS		84.32 237	82.96 240	88.41 238	89.38 310	80.32 173	96.59 170	96.25 127	83.97 186	76.63 275	90.36 259	67.53 241	94.86 320	75.82 268	70.09 326	90.06 280

fmvsm_s_conf0.1_n		92.93 50	93.16 49	92.24 128	90.52 285	81.92 128	98.42 37	96.24 128	91.17 35	96.02 30	98.35 34	75.34 166	99.74 38	97.84 20	94.58 128	95.05 219

UGNet		87.73 181	86.55 189	91.27 169	95.16 143	79.11 209	96.35 188	96.23 129	88.14 83	87.83 152	90.48 256	50.65 347	99.09 105	80.13 222	94.03 133	95.60 205
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		78.14 312	75.42 320	86.31 288	88.33 322	79.24 204	94.41 268	96.22 130	73.51 340	69.81 341	85.52 334	55.43 329	95.75 279	47.65 396	67.86 347	83.95 376

FOURS1					98.51 39	78.01 241	98.13 49	96.21 131	83.04 209	94.39 52

MP-MVS		92.61 66	92.67 59	92.42 119	98.13 56	79.73 193	97.33 111	96.20 132	85.63 137	90.53 111	97.66 75	78.14 109	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 55	92.17 73	94.45 36	98.89 20	84.87 78	97.20 118	96.20 132	87.73 94	88.40 145	98.12 46	78.71 100	99.76 31	87.99 152	96.28 103	98.74 42

SD-MVS		94.84 18	95.02 19	94.29 40	97.87 64	84.61 81	97.76 75	96.19 134	89.59 57	96.66 20	98.17 44	84.33 42	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 90	91.85 78	91.29 168	94.94 150	82.69 113	87.89 358	96.17 135	85.94 132	87.27 157	94.31 189	90.27 8	95.65 286	94.04 69	95.86 114	95.53 208

fmvsm_l_conf0.5_n		94.89 16	95.24 17	93.86 52	94.42 170	84.61 81	99.13 11	96.15 136	92.06 25	97.92 3	98.52 23	84.52 40	99.74 38	98.76 6	95.67 117	97.22 153

CHOSEN 1792x2688		91.07 107	90.21 115	93.64 66	95.18 142	83.53 100	96.26 194	96.13 137	88.92 64	84.90 181	93.10 217	72.86 198	99.62 58	88.86 141	95.67 117	97.79 110

PAPM_NR		91.46 95	90.82 99	93.37 80	98.50 40	81.81 135	95.03 257	96.13 137	84.65 164	86.10 169	97.65 79	79.24 91	99.75 36	83.20 198	96.88 92	98.56 54

CostFormer		89.08 144	88.39 148	91.15 173	93.13 211	79.15 208	88.61 350	96.11 139	83.14 206	89.58 124	86.93 308	83.83 51	96.87 229	88.22 151	85.92 223	97.42 140

mPP-MVS		91.88 85	91.82 79	92.07 137	98.38 44	78.63 221	97.29 113	96.09 140	85.12 151	88.45 144	97.66 75	75.53 156	99.68 51	89.83 130	98.02 57	97.88 100

APD-MVS		93.61 38	93.59 39	93.69 64	98.76 24	83.26 106	97.21 116	96.09 140	82.41 225	94.65 49	98.21 39	81.96 65	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			83.69 227		94.09 182	81.01 153	86.78 367	96.09 140	83.81 193	84.75 184	84.32 349	74.44 181	96.54 242	63.88 341	85.07 232

FA-MVS(test-final)		87.71 183	86.23 191	92.17 133	94.19 176	80.55 168	87.16 364	96.07 143	82.12 230	85.98 170	88.35 286	72.04 211	98.49 135	80.26 219	89.87 178	97.48 136

QAPM		86.88 193	84.51 214	93.98 48	94.04 184	85.89 44	97.19 119	96.05 144	73.62 339	75.12 299	95.62 149	62.02 278	99.74 38	70.88 306	96.06 109	96.30 191

MP-MVS-pluss		92.58 67	92.35 66	93.29 81	97.30 90	82.53 116	96.44 181	96.04 145	84.68 163	89.12 132	98.37 32	77.48 120	99.74 38	93.31 80	98.38 45	97.59 126
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.1_n_a		92.38 73	92.49 64	92.06 138	88.08 324	81.62 142	97.97 61	96.01 146	90.62 43	96.58 22	98.33 35	74.09 185	99.71 45	97.23 28	93.46 147	94.86 223

fmvsm_l_conf0.5_n_a		94.91 15	95.30 16	93.72 61	94.50 167	84.30 86	99.14 10	96.00 147	91.94 28	97.91 5	98.60 18	84.78 38	99.77 29	98.84 5	96.03 110	97.08 161

tpm2		87.35 188	86.26 190	90.62 188	92.93 219	78.67 220	88.06 357	95.99 148	79.33 281	87.40 154	86.43 319	80.28 76	96.40 246	80.23 220	85.73 227	96.79 172

SDMVSNet		87.02 190	85.61 196	91.24 170	94.14 179	83.30 105	93.88 286	95.98 149	84.30 175	79.63 245	92.01 231	58.23 303	97.68 176	90.28 128	82.02 256	92.75 253

DeepC-MVS	86.58 3	91.53 94	91.06 96	92.94 96	94.52 163	81.89 130	95.95 211	95.98 149	90.76 41	83.76 198	96.76 124	73.24 196	99.71 45	91.67 103	96.96 89	97.22 153
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test-LLR		88.48 162	87.98 154	89.98 207	92.26 239	77.23 266	97.11 130	95.96 151	83.76 195	86.30 167	91.38 242	72.30 207	96.78 235	80.82 213	91.92 165	95.94 197

test-mter		88.95 146	88.60 144	89.98 207	92.26 239	77.23 266	97.11 130	95.96 151	85.32 144	86.30 167	91.38 242	76.37 141	96.78 235	80.82 213	91.92 165	95.94 197

DP-MVS Recon		91.72 89	90.85 98	94.34 38	99.50 1	85.00 75	98.51 35	95.96 151	80.57 253	88.08 150	97.63 81	76.84 130	99.89 7	85.67 170	94.88 123	98.13 83

reproduce-ours		92.70 60	93.02 50	91.75 152	97.45 79	77.77 253	96.16 200	95.94 154	84.12 180	92.45 77	98.43 28	80.06 81	99.24 86	95.35 51	97.18 82	98.24 74

our_new_method		92.70 60	93.02 50	91.75 152	97.45 79	77.77 253	96.16 200	95.94 154	84.12 180	92.45 77	98.43 28	80.06 81	99.24 86	95.35 51	97.18 82	98.24 74

cdsmvs_eth3d_5k		21.43 389	28.57 392	0.00 408	0.00 431	0.00 433	0.00 419	95.93 156	0.00 426	0.00 427	97.66 75	63.57 267	0.00 427	0.00 426	0.00 425	0.00 423

reproduce_model		92.53 69	92.87 54	91.50 162	97.41 83	77.14 270	96.02 207	95.91 157	83.65 198	92.45 77	98.39 31	79.75 86	99.21 90	95.27 54	96.98 88	98.14 81

hse-mvs2		88.22 171	88.21 150	88.25 245	93.54 195	73.41 310	95.41 239	95.89 158	90.39 48	92.22 84	94.22 192	74.70 175	96.66 240	93.14 83	64.37 366	94.69 231

AUN-MVS		86.25 205	85.57 197	88.26 244	93.57 194	73.38 311	95.45 237	95.88 159	83.94 188	85.47 175	94.21 193	73.70 192	96.67 239	83.54 194	64.41 365	94.73 230

TAMVS		88.48 162	87.79 158	90.56 190	91.09 273	79.18 206	96.45 180	95.88 159	83.64 199	83.12 204	93.33 212	75.94 148	95.74 282	82.40 205	88.27 200	96.75 176

PVSNet_Blended_VisFu		91.24 101	90.77 100	92.66 108	95.09 144	82.40 120	97.77 73	95.87 161	88.26 79	86.39 165	93.94 200	76.77 133	99.27 84	88.80 143	94.00 136	96.31 190

OpenMVS	79.58 14	86.09 206	83.62 231	93.50 75	90.95 275	86.71 34	97.44 101	95.83 162	75.35 324	72.64 321	95.72 144	57.42 316	99.64 55	71.41 300	95.85 115	94.13 237

CDS-MVSNet		89.50 137	88.96 137	91.14 174	91.94 258	80.93 157	97.09 134	95.81 163	84.26 178	84.72 185	94.20 194	80.31 75	95.64 287	83.37 197	88.96 188	96.85 171
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	95.79 164	92.42 21	96.24 27	98.18 41	71.04 222	99.17 98	96.77 34	97.39 77	96.79 172

testing3		80.74 292	81.17 268	79.44 359	91.15 272	63.48 378	97.16 124	95.76 165	80.83 246	71.36 329	93.15 216	78.22 107	87.30 394	43.19 402	79.67 267	87.55 339

SR-MVS		92.16 77	92.27 69	91.83 150	98.37 45	78.41 227	96.67 168	95.76 165	82.19 229	91.97 88	98.07 52	76.44 138	98.64 126	93.71 72	97.27 80	98.45 60

3Dnovator+	82.88 8	89.63 136	87.85 156	94.99 23	94.49 168	86.76 33	97.84 67	95.74 167	86.10 127	75.47 296	96.02 138	65.00 261	99.51 71	82.91 202	97.07 86	98.72 47

HPM-MVS		91.62 92	91.53 86	91.89 145	97.88 63	79.22 205	96.99 139	95.73 168	82.07 231	89.50 127	97.19 104	75.59 154	98.93 117	90.91 110	97.94 59	97.54 128
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ab-mvs		87.08 189	84.94 210	93.48 77	93.34 204	83.67 97	88.82 347	95.70 169	81.18 241	84.55 188	90.14 264	62.72 272	98.94 116	85.49 172	82.54 252	97.85 104

xiu_mvs_v2_base		93.92 35	93.26 46	95.91 11	95.07 146	92.02 6	98.19 45	95.68 170	92.06 25	96.01 31	98.14 45	70.83 226	98.96 112	96.74 36	96.57 100	96.76 175

CP-MVSNet		81.01 289	80.08 283	83.79 326	87.91 326	70.51 341	94.29 277	95.65 171	80.83 246	72.54 323	88.84 276	63.71 266	92.32 359	68.58 319	68.36 341	88.55 313

PatchmatchNet		86.83 195	85.12 207	91.95 143	94.12 181	82.27 122	86.55 369	95.64 172	84.59 166	82.98 207	84.99 344	77.26 122	95.96 266	68.61 318	91.34 170	97.64 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
API-MVS		90.18 126	88.97 136	93.80 54	98.66 28	82.95 111	97.50 97	95.63 173	75.16 327	86.31 166	97.69 73	72.49 203	99.90 5	81.26 212	96.07 108	98.56 54

balanced_conf03		94.60 23	94.30 29	95.48 16	96.45 100	88.82 14	96.33 190	95.58 174	91.12 36	95.84 32	93.87 202	83.47 53	98.37 144	97.26 27	98.81 24	99.24 23

AdaColmap		88.81 152	87.61 164	92.39 120	99.33 4	79.95 184	96.70 167	95.58 174	77.51 306	83.05 206	96.69 128	61.90 281	99.72 43	84.29 180	93.47 146	97.50 134

SCA		85.63 215	83.64 230	91.60 160	92.30 237	81.86 132	92.88 310	95.56 176	84.85 157	82.52 208	85.12 342	58.04 306	95.39 297	73.89 285	87.58 208	97.54 128

dp		84.30 238	82.31 251	90.28 198	94.24 175	77.97 242	86.57 368	95.53 177	79.94 271	80.75 231	85.16 340	71.49 218	96.39 247	63.73 342	83.36 241	96.48 183

HyFIR lowres test		89.36 139	88.60 144	91.63 159	94.91 152	80.76 163	95.60 231	95.53 177	82.56 222	84.03 191	91.24 245	78.03 110	96.81 233	87.07 163	88.41 198	97.32 147

WBMVS		87.73 181	86.79 184	90.56 190	95.61 127	85.68 50	97.63 82	95.52 179	83.77 194	78.30 257	88.44 284	86.14 32	95.78 276	82.54 204	73.15 307	90.21 273

APD-MVS_3200maxsize		91.23 102	91.35 88	90.89 181	97.89 62	76.35 282	96.30 192	95.52 179	79.82 272	91.03 105	97.88 66	74.70 175	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	95.50 181	91.03 39	94.90 44	97.66 75	78.84 97	97.56 183	94.64 62	97.46 72	98.62 52

tt0805		81.20 287	79.06 295	87.61 259	86.50 338	72.97 319	93.66 289	95.48 182	74.11 335	76.23 284	91.99 233	41.36 382	97.40 197	77.44 250	74.78 297	92.45 256

HPM-MVS_fast		90.38 124	90.17 117	91.03 176	97.61 71	77.35 264	97.15 126	95.48 182	79.51 278	88.79 138	96.90 116	71.64 216	98.81 122	87.01 164	97.44 74	96.94 165

VPNet		84.69 230	82.92 241	90.01 205	89.01 312	83.45 102	96.71 165	95.46 184	85.71 136	79.65 244	92.18 230	56.66 322	96.01 262	83.05 201	67.84 348	90.56 267

114514_t		88.79 154	87.57 166	92.45 116	98.21 53	81.74 137	96.99 139	95.45 185	75.16 327	82.48 209	95.69 146	68.59 236	98.50 134	80.33 217	95.18 121	97.10 160

SR-MVS-dyc-post		91.29 100	91.45 87	90.80 183	97.76 67	76.03 287	96.20 198	95.44 186	80.56 254	90.72 109	97.84 67	75.76 151	98.61 127	91.99 99	96.79 95	97.75 112

RE-MVS-def			91.18 95		97.76 67	76.03 287	96.20 198	95.44 186	80.56 254	90.72 109	97.84 67	73.36 195		91.99 99	96.79 95	97.75 112

JIA-IIPM		79.00 308	77.20 307	84.40 321	89.74 301	64.06 375	75.30 405	95.44 186	62.15 386	81.90 220	59.08 409	78.92 95	95.59 291	66.51 330	85.78 226	93.54 247

RPMNet		79.85 298	75.92 318	91.64 157	90.16 292	79.75 190	79.02 397	95.44 186	58.43 402	82.27 216	72.55 400	73.03 197	98.41 143	46.10 398	86.25 218	96.75 176

MVSMamba_PlusPlus		92.37 74	91.55 85	94.83 27	95.37 135	87.69 24	95.60 231	95.42 190	74.65 332	93.95 58	92.81 219	83.11 56	97.70 175	94.49 63	98.53 35	99.11 28

DU-MVS		84.57 233	83.33 237	88.28 243	88.76 313	79.36 201	96.43 183	95.41 191	85.42 142	78.11 259	90.82 251	67.61 238	95.14 311	79.14 232	68.30 342	90.33 271

EI-MVSNet		85.80 211	85.20 203	87.59 261	91.55 263	77.41 262	95.13 251	95.36 192	80.43 259	80.33 237	94.71 182	73.72 190	95.97 263	76.96 255	78.64 277	89.39 286

MVSTER		89.25 143	88.92 139	90.24 199	95.98 114	84.66 80	96.79 159	95.36 192	87.19 111	80.33 237	90.61 255	90.02 11	95.97 263	85.38 173	78.64 277	90.09 278

CPTT-MVS		89.72 133	89.87 127	89.29 222	98.33 47	73.30 313	97.70 79	95.35 194	75.68 323	87.40 154	97.44 91	70.43 228	98.25 149	89.56 135	96.90 90	96.33 189

EIA-MVS		91.73 87	92.05 76	90.78 185	94.52 163	76.40 281	98.06 55	95.34 195	89.19 62	88.90 136	97.28 100	77.56 118	97.73 174	90.77 114	96.86 94	98.20 76

tpmvs		83.04 259	80.77 272	89.84 213	95.43 132	77.96 243	85.59 375	95.32 196	75.31 326	76.27 283	83.70 355	73.89 187	97.41 196	59.53 357	81.93 258	94.14 236

PS-CasMVS		80.27 296	79.18 292	83.52 332	87.56 330	69.88 346	94.08 280	95.29 197	80.27 264	72.08 325	88.51 283	59.22 297	92.23 361	67.49 321	68.15 344	88.45 319

TSAR-MVS + GP.		94.35 26	94.50 23	93.89 51	97.38 88	83.04 110	98.10 51	95.29 197	91.57 30	93.81 59	97.45 88	86.64 28	99.43 76	96.28 37	94.01 135	99.20 25

tpmrst		88.36 166	87.38 172	91.31 166	94.36 172	79.92 185	87.32 362	95.26 199	85.32 144	88.34 146	86.13 325	80.60 73	96.70 237	83.78 186	85.34 231	97.30 150

ETV-MVS		92.72 58	92.87 54	92.28 127	94.54 162	81.89 130	97.98 59	95.21 200	89.77 56	93.11 69	96.83 120	77.23 126	97.50 191	95.74 44	95.38 120	97.44 139

NR-MVSNet		83.35 251	81.52 264	88.84 230	88.76 313	81.31 147	94.45 267	95.16 201	84.65 164	67.81 347	90.82 251	70.36 229	94.87 319	74.75 276	66.89 358	90.33 271

test_fmvsmconf0.1_n		93.08 47	93.22 48	92.65 109	88.45 319	80.81 161	99.00 22	95.11 202	93.21 15	94.00 57	97.91 63	76.84 130	99.59 60	97.91 16	96.55 101	97.54 128

jason		92.73 56	92.23 71	94.21 44	90.50 286	87.30 29	98.65 30	95.09 203	90.61 44	92.76 76	97.13 106	75.28 167	97.30 203	93.32 79	96.75 97	98.02 88
jason: jason.
tpm cat1		83.63 248	81.38 265	90.39 195	93.53 200	78.19 238	85.56 376	95.09 203	70.78 359	78.51 254	83.28 359	74.80 174	97.03 217	66.77 325	84.05 236	95.95 196

cascas		86.50 199	84.48 216	92.55 114	92.64 228	85.95 41	97.04 138	95.07 205	75.32 325	80.50 233	91.02 248	54.33 337	97.98 161	86.79 165	87.62 206	93.71 245

GDP-MVS		92.85 53	92.55 63	93.75 57	92.82 221	85.76 46	97.63 82	95.05 206	88.34 77	93.15 68	97.10 109	86.92 26	98.01 159	87.95 153	94.00 136	97.47 137

CVMVSNet		84.83 228	85.57 197	82.63 339	91.55 263	60.38 389	95.13 251	95.03 207	80.60 252	82.10 218	94.71 182	66.40 251	90.19 381	74.30 282	90.32 176	97.31 149

test0.0.03 1		82.79 263	82.48 249	83.74 328	86.81 336	72.22 322	96.52 174	95.03 207	83.76 195	73.00 317	93.20 213	72.30 207	88.88 384	64.15 340	77.52 286	90.12 276

PMMVS		89.46 138	89.92 125	88.06 249	94.64 157	69.57 350	96.22 196	94.95 209	87.27 107	91.37 98	96.54 130	65.88 253	97.39 198	88.54 145	93.89 139	97.23 152

CS-MVS		92.73 56	93.48 43	90.48 193	96.27 104	75.93 292	98.55 34	94.93 210	89.32 60	94.54 51	97.67 74	78.91 96	97.02 218	93.80 70	97.32 79	98.49 57

Anonymous20240529		83.15 256	80.60 276	90.80 183	95.74 123	78.27 231	96.81 158	94.92 211	60.10 397	81.89 221	92.54 223	45.82 367	98.82 121	79.25 231	78.32 283	95.31 214

mvs_anonymous		88.68 155	87.62 163	91.86 147	94.80 155	81.69 140	93.53 294	94.92 211	82.03 232	78.87 253	90.43 258	75.77 150	95.34 300	85.04 175	93.16 151	98.55 56

CLD-MVS		87.97 176	87.48 169	89.44 220	92.16 246	80.54 170	98.14 46	94.92 211	91.41 32	79.43 247	95.40 155	62.34 274	97.27 206	90.60 118	82.90 247	90.50 268
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		90.54 118	89.54 129	93.55 72	92.31 234	87.58 26	96.99 139	94.87 214	87.23 108	93.27 64	97.56 84	57.43 313	98.32 146	92.72 89	93.46 147	94.74 227

xiu_mvs_v1_base		90.54 118	89.54 129	93.55 72	92.31 234	87.58 26	96.99 139	94.87 214	87.23 108	93.27 64	97.56 84	57.43 313	98.32 146	92.72 89	93.46 147	94.74 227

xiu_mvs_v1_base_debi		90.54 118	89.54 129	93.55 72	92.31 234	87.58 26	96.99 139	94.87 214	87.23 108	93.27 64	97.56 84	57.43 313	98.32 146	92.72 89	93.46 147	94.74 227

GA-MVS		85.79 212	84.04 225	91.02 177	89.47 308	80.27 176	96.90 152	94.84 217	85.57 138	80.88 229	89.08 272	56.56 323	96.47 245	77.72 243	85.35 230	96.34 187

TranMVSNet+NR-MVSNet		83.24 255	81.71 260	87.83 253	87.71 328	78.81 217	96.13 205	94.82 218	84.52 167	76.18 286	90.78 253	64.07 265	94.60 328	74.60 280	66.59 360	90.09 278

HQP3-MVS								94.80 219							83.01 244

HQP-MVS		87.91 178	87.55 167	88.98 228	92.08 250	78.48 223	97.63 82	94.80 219	90.52 45	82.30 212	94.56 185	65.40 257	97.32 201	87.67 157	83.01 244	91.13 261

TAPA-MVS	81.61 12	85.02 225	83.67 228	89.06 225	96.79 96	73.27 316	95.92 213	94.79 221	74.81 330	80.47 234	96.83 120	71.07 221	98.19 152	49.82 391	92.57 156	95.71 203
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PEN-MVS		79.47 304	78.26 300	83.08 335	86.36 340	68.58 354	93.85 287	94.77 222	79.76 273	71.37 328	88.55 280	59.79 289	92.46 357	64.50 338	65.40 362	88.19 324

SPE-MVS-test		92.98 48	93.67 37	90.90 180	96.52 99	76.87 272	98.68 28	94.73 223	90.36 50	94.84 46	97.89 65	77.94 111	97.15 214	94.28 67	97.80 64	98.70 48

HQP_MVS		87.50 186	87.09 179	88.74 233	91.86 259	77.96 243	97.18 120	94.69 224	89.89 54	81.33 225	94.15 195	64.77 262	97.30 203	87.08 161	82.82 248	90.96 263

plane_prior5								94.69 224					97.30 203	87.08 161	82.82 248	90.96 263

tpm		85.55 217	84.47 217	88.80 232	90.19 291	75.39 297	88.79 348	94.69 224	84.83 158	83.96 194	85.21 338	78.22 107	94.68 327	76.32 263	78.02 285	96.34 187

FMVSNet3		84.71 229	82.71 246	90.70 187	94.55 161	87.71 23	95.92 213	94.67 227	81.73 236	75.82 291	88.08 291	66.99 246	94.47 331	71.23 302	75.38 294	89.91 282

UA-Net		88.92 148	88.48 147	90.24 199	94.06 183	77.18 268	93.04 306	94.66 228	87.39 103	91.09 103	93.89 201	74.92 172	98.18 153	75.83 267	91.43 169	95.35 213

LFMVS		89.27 142	87.64 161	94.16 47	97.16 92	85.52 57	97.18 120	94.66 228	79.17 286	89.63 123	96.57 129	55.35 330	98.22 150	89.52 136	89.54 180	98.74 42

MVS_Test		90.29 125	89.18 133	93.62 68	95.23 139	84.93 76	94.41 268	94.66 228	84.31 173	90.37 115	91.02 248	75.13 169	97.82 171	83.11 200	94.42 130	98.12 84

sasdasda		92.27 75	91.22 91	95.41 17	95.80 121	88.31 15	97.09 134	94.64 231	88.49 72	92.99 72	97.31 95	72.68 200	98.57 130	93.38 77	88.58 193	99.36 16

canonicalmvs		92.27 75	91.22 91	95.41 17	95.80 121	88.31 15	97.09 134	94.64 231	88.49 72	92.99 72	97.31 95	72.68 200	98.57 130	93.38 77	88.58 193	99.36 16

VDDNet		86.44 200	84.51 214	92.22 130	91.56 262	81.83 133	97.10 133	94.64 231	69.50 366	87.84 151	95.19 165	48.01 357	97.92 167	89.82 131	86.92 211	96.89 169

baseline1		88.85 151	87.49 168	92.93 97	95.21 141	86.85 31	95.47 236	94.61 234	87.29 105	83.11 205	94.99 176	80.70 71	96.89 227	82.28 206	73.72 301	95.05 219

PatchT		79.75 299	76.85 311	88.42 237	89.55 306	75.49 296	77.37 401	94.61 234	63.07 382	82.46 210	73.32 397	75.52 157	93.41 352	51.36 385	84.43 234	96.36 185

MS-PatchMatch		83.05 258	81.82 259	86.72 283	89.64 303	79.10 210	94.88 260	94.59 236	79.70 275	70.67 335	89.65 268	50.43 349	96.82 232	70.82 309	95.99 113	84.25 373

casdiffmvs_mvg		91.13 104	90.45 108	93.17 87	92.99 217	83.58 99	97.46 100	94.56 237	87.69 95	87.19 159	94.98 177	74.50 180	97.60 180	91.88 102	92.79 154	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		90.76 114	90.10 118	92.74 104	92.90 220	82.56 115	94.60 265	94.56 237	87.69 95	89.06 134	95.67 147	73.76 189	97.51 190	90.43 123	92.23 163	98.16 79

OMC-MVS		88.80 153	88.16 152	90.72 186	95.30 137	77.92 246	94.81 262	94.51 239	86.80 118	84.97 180	96.85 119	67.53 241	98.60 128	85.08 174	87.62 206	95.63 204

MGCFI-Net		91.95 81	91.03 97	94.72 31	95.68 125	86.38 35	96.93 149	94.48 240	88.25 80	92.78 75	97.24 101	72.34 205	98.46 138	93.13 85	88.43 197	99.32 19

MVSFormer		91.36 98	90.57 104	93.73 60	93.00 214	88.08 19	94.80 263	94.48 240	80.74 249	94.90 44	97.13 106	78.84 97	95.10 314	83.77 187	97.46 72	98.02 88

test_djsdf		83.00 261	82.45 250	84.64 315	84.07 370	69.78 347	94.80 263	94.48 240	80.74 249	75.41 297	87.70 295	61.32 285	95.10 314	83.77 187	79.76 264	89.04 301

casdiffmvs		90.95 111	90.39 109	92.63 111	92.82 221	82.53 116	96.83 155	94.47 243	87.69 95	88.47 143	95.56 152	74.04 186	97.54 187	90.90 111	92.74 155	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	86.77 197	85.00 209	92.08 136	92.06 253	83.07 109	92.14 319	94.47 243	79.63 276	76.90 272	94.78 181	71.15 220	99.20 95	72.87 291	91.05 171	93.98 240
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
RRT-MVS		89.67 134	88.67 142	92.67 107	94.44 169	81.08 151	94.34 271	94.45 245	86.05 129	85.79 171	92.39 225	63.39 269	98.16 154	93.22 82	93.95 138	98.76 41

VDD-MVS		88.28 169	87.02 181	92.06 138	95.09 144	80.18 181	97.55 92	94.45 245	83.09 207	89.10 133	95.92 141	47.97 358	98.49 135	93.08 87	86.91 212	97.52 133

mvsmamba		90.53 121	90.08 119	91.88 146	94.81 154	80.93 157	93.94 284	94.45 245	88.24 81	87.02 162	92.35 226	68.04 237	95.80 274	94.86 57	97.03 87	98.92 34

test_cas_vis1_n_1920		89.90 130	90.02 121	89.54 219	90.14 294	74.63 302	98.71 27	94.43 248	93.04 17	92.40 80	96.35 132	53.41 340	99.08 106	95.59 47	96.16 105	94.90 221

PLC	83.97 7	88.00 175	87.38 172	89.83 214	98.02 59	76.46 279	97.16 124	94.43 248	79.26 285	81.98 219	96.28 133	69.36 233	99.27 84	77.71 244	92.25 162	93.77 244
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EC-MVSNet		91.73 87	92.11 74	90.58 189	93.54 195	77.77 253	98.07 54	94.40 250	87.44 101	92.99 72	97.11 108	74.59 179	96.87 229	93.75 71	97.08 85	97.11 159

sd_testset		84.62 231	83.11 239	89.17 223	94.14 179	77.78 252	91.54 329	94.38 251	84.30 175	79.63 245	92.01 231	52.28 342	96.98 221	77.67 245	82.02 256	92.75 253

FMVSNet2		82.79 263	80.44 278	89.83 214	92.66 225	85.43 58	95.42 238	94.35 252	79.06 289	74.46 303	87.28 300	56.38 325	94.31 334	69.72 314	74.68 298	89.76 283

test_vis1_n_1920		89.95 129	90.59 103	88.03 251	92.36 233	68.98 353	99.12 12	94.34 253	93.86 11	93.64 62	97.01 114	51.54 344	99.59 60	96.76 35	96.71 99	95.53 208

nrg030		86.79 196	85.43 199	90.87 182	88.76 313	85.34 60	97.06 137	94.33 254	84.31 173	80.45 235	91.98 234	72.36 204	96.36 249	88.48 148	71.13 315	90.93 265

ACMM	80.70 13	83.72 247	82.85 244	86.31 288	91.19 270	72.12 326	95.88 216	94.29 255	80.44 257	77.02 270	91.96 235	55.24 331	97.14 215	79.30 230	80.38 263	89.67 284
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XXY-MVS		83.84 244	82.00 256	89.35 221	87.13 333	81.38 145	95.72 224	94.26 256	80.15 266	75.92 290	90.63 254	61.96 280	96.52 243	78.98 234	73.28 306	90.14 275

Syy-MVS		77.97 316	78.05 301	77.74 367	92.13 247	56.85 396	93.97 282	94.23 257	82.43 223	73.39 310	93.57 209	57.95 309	87.86 389	32.40 410	82.34 253	88.51 314

myMVS_eth3d		81.93 276	82.18 252	81.18 349	92.13 247	67.18 360	93.97 282	94.23 257	82.43 223	73.39 310	93.57 209	76.98 128	87.86 389	50.53 389	82.34 253	88.51 314

cl22		85.11 224	84.17 222	87.92 252	95.06 148	78.82 215	95.51 234	94.22 259	79.74 274	76.77 273	87.92 293	75.96 147	95.68 283	79.93 224	72.42 309	89.27 293

OPM-MVS		85.84 210	85.10 208	88.06 249	88.34 321	77.83 250	95.72 224	94.20 260	87.89 91	80.45 235	94.05 197	58.57 300	97.26 207	83.88 184	82.76 250	89.09 298
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet (Re-imp)		88.88 150	88.87 141	88.91 229	93.89 187	74.43 305	96.93 149	94.19 261	84.39 171	83.22 203	95.67 147	78.24 106	94.70 325	78.88 235	94.40 131	97.61 125

Anonymous20231211		79.72 300	77.19 308	87.33 269	95.59 129	77.16 269	95.18 250	94.18 262	59.31 400	72.57 322	86.20 324	47.89 360	95.66 284	74.53 281	69.24 334	89.18 295

PS-MVSNAJss		84.91 227	84.30 219	86.74 279	85.89 350	74.40 306	94.95 258	94.16 263	83.93 189	76.45 278	90.11 265	71.04 222	95.77 277	83.16 199	79.02 274	90.06 280

LPG-MVS_test		84.20 239	83.49 235	86.33 285	90.88 276	73.06 317	95.28 241	94.13 264	82.20 227	76.31 280	93.20 213	54.83 335	96.95 223	83.72 189	80.83 261	88.98 304

LGP-MVS_train				86.33 285	90.88 276	73.06 317		94.13 264	82.20 227	76.31 280	93.20 213	54.83 335	96.95 223	83.72 189	80.83 261	88.98 304

V42		83.04 259	81.53 263	87.57 263	86.27 343	79.09 211	95.87 217	94.11 266	80.35 261	77.22 268	86.79 311	65.32 259	96.02 261	77.74 242	70.14 322	87.61 335

XVG-OURS-SEG-HR		85.74 213	85.16 206	87.49 267	90.22 290	71.45 336	91.29 330	94.09 267	81.37 239	83.90 196	95.22 162	60.30 288	97.53 189	85.58 171	84.42 235	93.50 248

XVG-OURS		85.18 223	84.38 218	87.59 261	90.42 288	71.73 333	91.06 333	94.07 268	82.00 233	83.29 202	95.08 172	56.42 324	97.55 185	83.70 191	83.42 240	93.49 249

miper_enhance_ethall		85.95 209	85.20 203	88.19 248	94.85 153	79.76 189	96.00 208	94.06 269	82.98 212	77.74 263	88.76 277	79.42 87	95.46 296	80.58 215	72.42 309	89.36 291

v2v482		83.46 250	81.86 258	88.25 245	86.19 344	79.65 195	96.34 189	94.02 270	81.56 238	77.32 266	88.23 288	65.62 254	96.03 260	77.77 241	69.72 330	89.09 298

jajsoiax		82.12 274	81.15 269	85.03 309	84.19 368	70.70 340	94.22 278	93.95 271	83.07 208	73.48 309	89.75 267	49.66 353	95.37 299	82.24 207	79.76 264	89.02 302

test_fmvsmconf0.01_n		91.08 106	90.68 102	92.29 126	82.43 378	80.12 182	97.94 62	93.93 272	92.07 24	91.97 88	97.60 82	67.56 240	99.53 68	97.09 30	95.56 119	97.21 155

v1144		82.90 262	81.27 267	87.78 255	86.29 342	79.07 212	96.14 203	93.93 272	80.05 268	77.38 264	86.80 310	65.50 255	95.93 268	75.21 273	70.13 323	88.33 322

KD-MVS_2432*1600		77.63 319	74.92 324	85.77 295	90.86 279	79.44 198	88.08 355	93.92 274	76.26 319	67.05 351	82.78 361	72.15 209	91.92 364	61.53 349	41.62 410	85.94 361

miper_refine_blended		77.63 319	74.92 324	85.77 295	90.86 279	79.44 198	88.08 355	93.92 274	76.26 319	67.05 351	82.78 361	72.15 209	91.92 364	61.53 349	41.62 410	85.94 361

test_fmvsmvis_n_1920		92.12 78	92.10 75	92.17 133	90.87 278	81.04 152	98.34 40	93.90 276	92.71 18	87.24 158	97.90 64	74.83 173	99.72 43	96.96 32	96.20 104	95.76 202

UnsupCasMVSNet_eth		73.25 344	70.57 349	81.30 347	77.53 393	66.33 366	87.24 363	93.89 277	80.38 260	57.90 392	81.59 366	42.91 377	90.56 378	65.18 336	48.51 398	87.01 346

v7n		79.32 306	77.34 306	85.28 305	84.05 371	72.89 321	93.38 296	93.87 278	75.02 329	70.68 334	84.37 348	59.58 292	95.62 289	67.60 320	67.50 351	87.32 343

dcpmvs_2		93.10 46	93.46 44	92.02 141	97.77 65	79.73 193	94.82 261	93.86 279	86.91 115	91.33 99	96.76 124	85.20 35	98.06 156	96.90 33	97.60 69	98.27 72

Vis-MVSNet		88.67 156	87.82 157	91.24 170	92.68 224	78.82 215	96.95 147	93.85 280	87.55 98	87.07 161	95.13 169	63.43 268	97.21 208	77.58 247	96.15 106	97.70 117
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v148		82.41 271	80.89 270	86.99 277	86.18 345	76.81 274	96.27 193	93.82 281	80.49 256	75.28 298	86.11 326	67.32 244	95.75 279	75.48 271	67.03 357	88.42 320

BH-w/o		88.24 170	87.47 170	90.54 192	95.03 149	78.54 222	97.41 106	93.82 281	84.08 182	78.23 258	94.51 187	69.34 234	97.21 208	80.21 221	94.58 128	95.87 199

TR-MVS		86.30 203	84.93 211	90.42 194	94.63 158	77.58 259	96.57 171	93.82 281	80.30 262	82.42 211	95.16 167	58.74 299	97.55 185	74.88 275	87.82 205	96.13 194

v1192		82.31 272	80.55 277	87.60 260	85.94 348	78.47 226	95.85 219	93.80 284	79.33 281	76.97 271	86.51 314	63.33 270	95.87 270	73.11 290	70.13 323	88.46 318

ACMP	81.66 11	84.00 242	83.22 238	86.33 285	91.53 265	72.95 320	95.91 215	93.79 285	83.70 197	73.79 306	92.22 228	54.31 338	96.89 227	83.98 183	79.74 266	89.16 296
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v144192		82.43 268	80.73 273	87.54 264	85.81 351	78.22 233	95.98 209	93.78 286	79.09 288	77.11 269	86.49 315	64.66 264	95.91 269	74.20 283	69.42 331	88.49 316

mvs_tets		81.74 278	80.71 274	84.84 310	84.22 367	70.29 343	93.91 285	93.78 286	82.77 217	73.37 312	89.46 270	47.36 363	95.31 303	81.99 208	79.55 270	88.92 308

F-COLMAP		84.50 235	83.44 236	87.67 257	95.22 140	72.22 322	95.95 211	93.78 286	75.74 322	76.30 282	95.18 166	59.50 293	98.45 140	72.67 293	86.59 215	92.35 258

UniMVSNet_ETH3D		80.86 291	78.75 297	87.22 274	86.31 341	72.02 327	91.95 320	93.76 289	73.51 340	75.06 300	90.16 263	43.04 376	95.66 284	76.37 262	78.55 280	93.98 240

Fast-Effi-MVS+		87.93 177	86.94 183	90.92 179	94.04 184	79.16 207	98.26 42	93.72 290	81.29 240	83.94 195	92.90 218	69.83 232	96.68 238	76.70 257	91.74 167	96.93 166

v1921920		82.02 275	80.23 281	87.41 268	85.62 352	77.92 246	95.79 223	93.69 291	78.86 292	76.67 274	86.44 317	62.50 273	95.83 272	72.69 292	69.77 329	88.47 317

DTE-MVSNet		78.37 310	77.06 309	82.32 342	85.22 359	67.17 363	93.40 295	93.66 292	78.71 294	70.53 336	88.29 287	59.06 298	92.23 361	61.38 352	63.28 371	87.56 337

v8		81.88 277	80.06 285	87.32 270	86.63 337	79.04 213	94.41 268	93.65 293	78.77 293	73.19 316	85.57 332	66.87 247	95.81 273	73.84 287	67.61 350	87.11 344

diffmvs		91.17 103	90.74 101	92.44 118	93.11 213	82.50 118	96.25 195	93.62 294	87.79 92	90.40 114	95.93 139	73.44 194	97.42 195	93.62 74	92.55 157	97.41 141
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		81.26 285	78.36 298	89.96 209	93.78 188	79.78 188	79.48 393	93.60 295	73.09 345	80.14 239	79.99 377	62.15 276	95.24 306	59.49 358	83.52 238	94.85 224

PatchMatch-RL		85.00 226	83.66 229	89.02 227	95.86 118	74.55 304	92.49 314	93.60 295	79.30 283	79.29 249	91.47 240	58.53 301	98.45 140	70.22 311	92.17 164	94.07 239

anonymousdsp		80.98 290	79.97 286	84.01 323	81.73 380	70.44 342	92.49 314	93.58 297	77.10 313	72.98 318	86.31 321	57.58 312	94.90 318	79.32 229	78.63 279	86.69 349

CL-MVSNet_self_test		75.81 331	74.14 333	80.83 352	78.33 391	67.79 357	94.22 278	93.52 298	77.28 310	69.82 340	81.54 368	61.47 284	89.22 383	57.59 366	53.51 388	85.48 365

miper_ehance_all_eth		84.57 233	83.60 232	87.50 265	92.64 228	78.25 232	95.40 240	93.47 299	79.28 284	76.41 279	87.64 296	76.53 136	95.24 306	78.58 237	72.42 309	89.01 303

kuosan		73.55 341	72.39 342	77.01 370	89.68 302	66.72 365	85.24 379	93.44 300	67.76 370	60.04 386	83.40 358	71.90 212	84.25 401	45.34 399	54.75 383	80.06 396

v1240		81.70 279	79.83 289	87.30 272	85.50 353	77.70 258	95.48 235	93.44 300	78.46 297	76.53 277	86.44 317	60.85 286	95.84 271	71.59 299	70.17 321	88.35 321

v10		81.43 283	79.53 291	87.11 275	86.38 339	78.87 214	94.31 273	93.43 302	77.88 301	73.24 315	85.26 336	65.44 256	95.75 279	72.14 296	67.71 349	86.72 348

IterMVS-LS		83.93 243	82.80 245	87.31 271	91.46 266	77.39 263	95.66 227	93.43 302	80.44 257	75.51 295	87.26 302	73.72 190	95.16 310	76.99 253	70.72 319	89.39 286
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		82.42 269	80.43 279	88.39 240	92.66 225	81.95 125	94.30 274	93.38 304	79.06 289	75.82 291	85.66 328	56.38 325	93.84 343	71.23 302	75.38 294	89.38 288

test1		82.42 269	80.43 279	88.39 240	92.66 225	81.95 125	94.30 274	93.38 304	79.06 289	75.82 291	85.66 328	56.38 325	93.84 343	71.23 302	75.38 294	89.38 288

FMVSNet1		79.50 303	76.54 314	88.39 240	88.47 318	81.95 125	94.30 274	93.38 304	73.14 344	72.04 326	85.66 328	43.86 370	93.84 343	65.48 334	72.53 308	89.38 288

BH-untuned		86.95 192	85.94 193	89.99 206	94.52 163	77.46 261	96.78 160	93.37 307	81.80 234	76.62 276	93.81 205	66.64 249	97.02 218	76.06 264	93.88 140	95.48 210

Effi-MVS+-dtu		84.61 232	84.90 212	83.72 329	91.96 256	63.14 380	94.95 258	93.34 308	85.57 138	79.79 243	87.12 305	61.99 279	95.61 290	83.55 193	85.83 225	92.41 257

CMPMVS	54.94 21	75.71 333	74.56 328	79.17 361	79.69 386	55.98 398	89.59 341	93.30 309	60.28 395	53.85 399	89.07 273	47.68 362	96.33 250	76.55 258	81.02 259	85.22 366
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
cl____		83.27 253	82.12 253	86.74 279	92.20 242	75.95 291	95.11 253	93.27 310	78.44 298	74.82 301	87.02 307	74.19 183	95.19 308	74.67 278	69.32 332	89.09 298

DIV-MVS_self_test		83.27 253	82.12 253	86.74 279	92.19 243	75.92 293	95.11 253	93.26 311	78.44 298	74.81 302	87.08 306	74.19 183	95.19 308	74.66 279	69.30 333	89.11 297

dmvs_re		84.10 240	82.90 242	87.70 256	91.41 267	73.28 314	90.59 336	93.19 312	85.02 153	77.96 262	93.68 206	57.92 311	96.18 257	75.50 270	80.87 260	93.63 246

miper_lstm_enhance		81.66 281	80.66 275	84.67 314	91.19 270	71.97 329	91.94 321	93.19 312	77.86 302	72.27 324	85.26 336	73.46 193	93.42 351	73.71 288	67.05 356	88.61 312

dongtai		69.47 359	68.98 358	70.93 381	86.87 335	58.45 394	88.19 353	93.18 314	63.98 381	56.04 395	80.17 376	70.97 225	79.24 408	33.46 409	47.94 400	75.09 402

eth_miper_zixun_eth		83.12 257	82.01 255	86.47 284	91.85 261	74.80 300	94.33 272	93.18 314	79.11 287	75.74 294	87.25 303	72.71 199	95.32 302	76.78 256	67.13 355	89.27 293

pmmvs4		82.54 267	80.79 271	87.79 254	86.11 346	80.49 172	93.55 293	93.18 314	77.29 309	73.35 313	89.40 271	65.26 260	95.05 317	75.32 272	73.61 302	87.83 330

XVG-ACMP-BASELINE		79.38 305	77.90 303	83.81 325	84.98 361	67.14 364	89.03 346	93.18 314	80.26 265	72.87 319	88.15 290	38.55 388	96.26 252	76.05 265	78.05 284	88.02 327

CANet_DTU		90.98 109	90.04 120	93.83 53	94.76 156	86.23 37	96.32 191	93.12 318	93.11 16	93.71 60	96.82 122	63.08 271	99.48 73	84.29 180	95.12 122	95.77 201

IS-MVSNet		88.67 156	88.16 152	90.20 201	93.61 192	76.86 273	96.77 162	93.07 319	84.02 184	83.62 199	95.60 150	74.69 178	96.24 255	78.43 239	93.66 144	97.49 135

c3_l		83.80 245	82.65 247	87.25 273	92.10 249	77.74 257	95.25 244	93.04 320	78.58 295	76.01 287	87.21 304	75.25 168	95.11 313	77.54 248	68.89 336	88.91 309

mamv4		85.50 218	86.76 185	81.72 346	93.23 205	54.93 403	89.95 340	92.94 321	69.96 363	79.00 250	92.20 229	80.69 72	94.22 336	92.06 98	90.77 173	96.01 195

UnsupCasMVSNet_bld		68.60 364	64.50 368	80.92 351	74.63 404	67.80 356	83.97 384	92.94 321	65.12 379	54.63 398	68.23 405	35.97 394	92.17 363	60.13 356	44.83 405	82.78 380

MVP-Stereo		82.65 266	81.67 261	85.59 301	86.10 347	78.29 230	93.33 298	92.82 323	77.75 303	69.17 345	87.98 292	59.28 296	95.76 278	71.77 297	96.88 92	82.73 381
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Effi-MVS+		90.70 115	89.90 126	93.09 90	93.61 192	83.48 101	95.20 247	92.79 324	83.22 204	91.82 91	95.70 145	71.82 213	97.48 193	91.25 106	93.67 143	98.32 66

EU-MVSNet		76.92 326	76.95 310	76.83 372	84.10 369	54.73 404	91.77 324	92.71 325	72.74 348	69.57 342	88.69 278	58.03 308	87.43 393	64.91 337	70.00 327	88.33 322

pm-mvs1		80.05 297	78.02 302	86.15 290	85.42 354	75.81 294	95.11 253	92.69 326	77.13 311	70.36 337	87.43 298	58.44 302	95.27 305	71.36 301	64.25 367	87.36 342

1112_ss		88.60 159	87.47 170	92.00 142	93.21 206	80.97 155	96.47 178	92.46 327	83.64 199	80.86 230	97.30 98	80.24 77	97.62 179	77.60 246	85.49 228	97.40 143

test_fmvs1		87.79 180	88.52 146	85.62 300	92.98 218	64.31 372	97.88 65	92.42 328	87.95 87	92.24 83	95.82 142	47.94 359	98.44 142	95.31 53	94.09 132	94.09 238

Test_1112_low_res		88.03 174	86.73 186	91.94 144	93.15 209	80.88 159	96.44 181	92.41 329	83.59 201	80.74 232	91.16 246	80.18 78	97.59 181	77.48 249	85.40 229	97.36 146

test_fmvs1_n		86.34 202	86.72 187	85.17 307	87.54 331	63.64 377	96.91 151	92.37 330	87.49 100	91.33 99	95.58 151	40.81 386	98.46 138	95.00 56	93.49 145	93.41 252

BH-RMVSNet		86.84 194	85.28 202	91.49 163	95.35 136	80.26 177	96.95 147	92.21 331	82.86 215	81.77 224	95.46 154	59.34 295	97.64 178	69.79 313	93.81 141	96.57 181

GeoE		86.36 201	85.20 203	89.83 214	93.17 208	76.13 284	97.53 93	92.11 332	79.58 277	80.99 228	94.01 198	66.60 250	96.17 258	73.48 289	89.30 182	97.20 157

LS3D		82.22 273	79.94 287	89.06 225	97.43 82	74.06 309	93.20 304	92.05 333	61.90 387	73.33 314	95.21 163	59.35 294	99.21 90	54.54 378	92.48 159	93.90 242

EG-PatchMatch MVS		74.92 335	72.02 343	83.62 330	83.76 375	73.28 314	93.62 291	92.04 334	68.57 369	58.88 388	83.80 354	31.87 402	95.57 293	56.97 370	78.67 276	82.00 389

IterMVS		80.67 293	79.16 293	85.20 306	89.79 297	76.08 285	92.97 308	91.86 335	80.28 263	71.20 331	85.14 341	57.93 310	91.34 371	72.52 294	70.74 318	88.18 325
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MIMVSNet		79.18 307	75.99 317	88.72 234	87.37 332	80.66 165	79.96 391	91.82 336	77.38 308	74.33 304	81.87 365	41.78 379	90.74 377	66.36 332	83.10 243	94.76 226

IterMVS-SCA-FT		80.51 295	79.10 294	84.73 312	89.63 304	74.66 301	92.98 307	91.81 337	80.05 268	71.06 333	85.18 339	58.04 306	91.40 370	72.48 295	70.70 320	88.12 326

our_test_3		77.90 317	75.37 321	85.48 303	85.39 355	76.74 275	93.63 290	91.67 338	73.39 343	65.72 360	84.65 347	58.20 305	93.13 354	57.82 364	67.87 346	86.57 351

pmmvs5		81.34 284	79.54 290	86.73 282	85.02 360	76.91 271	96.22 196	91.65 339	77.65 304	73.55 308	88.61 279	55.70 328	94.43 332	74.12 284	73.35 305	88.86 310

ACMH	75.40 17	77.99 314	74.96 322	87.10 276	90.67 283	76.41 280	93.19 305	91.64 340	72.47 351	63.44 369	87.61 297	43.34 373	97.16 211	58.34 362	73.94 300	87.72 331
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis1_n		85.60 216	85.70 195	85.33 304	84.79 362	64.98 370	96.83 155	91.61 341	87.36 104	91.00 106	94.84 180	36.14 393	97.18 210	95.66 45	93.03 152	93.82 243

MonoMVSNet		85.68 214	84.22 221	90.03 204	88.43 320	77.83 250	92.95 309	91.46 342	87.28 106	78.11 259	85.96 327	66.31 252	94.81 322	90.71 116	76.81 288	97.46 138

Fast-Effi-MVS+-dtu		83.33 252	82.60 248	85.50 302	89.55 306	69.38 351	96.09 206	91.38 343	82.30 226	75.96 289	91.41 241	56.71 320	95.58 292	75.13 274	84.90 233	91.54 259

YYNet1		73.53 343	70.43 350	82.85 337	84.52 365	71.73 333	91.69 326	91.37 344	67.63 371	46.79 403	81.21 370	55.04 333	90.43 379	55.93 373	59.70 378	86.38 353

ppachtmachnet_test		77.19 323	74.22 331	86.13 291	85.39 355	78.22 233	93.98 281	91.36 345	71.74 355	67.11 350	84.87 345	56.67 321	93.37 353	52.21 383	64.59 364	86.80 347

Anonymous202405211		84.41 236	81.93 257	91.85 149	96.78 97	78.41 227	97.44 101	91.34 346	70.29 361	84.06 190	94.26 191	41.09 383	98.96 112	79.46 227	82.65 251	98.17 78

MDA-MVSNet_test_wron		73.54 342	70.43 350	82.86 336	84.55 363	71.85 330	91.74 325	91.32 347	67.63 371	46.73 404	81.09 371	55.11 332	90.42 380	55.91 374	59.76 377	86.31 354

CR-MVSNet		83.53 249	81.36 266	90.06 203	90.16 292	79.75 190	79.02 397	91.12 348	84.24 179	82.27 216	80.35 374	75.45 158	93.67 347	63.37 345	86.25 218	96.75 176

Patchmtry		77.36 322	74.59 327	85.67 298	89.75 299	75.75 295	77.85 400	91.12 348	60.28 395	71.23 330	80.35 374	75.45 158	93.56 349	57.94 363	67.34 353	87.68 333

LTVRE_ROB	73.68 18	77.99 314	75.74 319	84.74 311	90.45 287	72.02 327	86.41 370	91.12 348	72.57 350	66.63 355	87.27 301	54.95 334	96.98 221	56.29 372	75.98 289	85.21 367
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		77.18 324	76.06 316	80.55 353	83.78 374	60.00 391	90.35 337	91.05 351	77.01 315	66.62 356	87.92 293	47.73 361	94.03 339	71.63 298	68.44 340	87.62 334

CNLPA		86.96 191	85.37 201	91.72 155	97.59 73	79.34 203	97.21 116	91.05 351	74.22 334	78.90 251	96.75 126	67.21 245	98.95 114	74.68 277	90.77 173	96.88 170

Anonymous20240521		72.06 351	69.91 352	78.50 365	77.11 396	61.67 386	91.62 328	90.97 353	65.52 378	62.37 375	79.05 380	36.32 392	90.96 375	57.75 365	68.52 339	82.87 378

KD-MVS_self_test		70.97 356	69.31 355	75.95 377	76.24 401	55.39 402	87.45 360	90.94 354	70.20 362	62.96 374	77.48 384	44.01 369	88.09 387	61.25 353	53.26 389	84.37 372

pmmvs6		74.65 337	71.67 344	83.60 331	79.13 388	69.94 345	93.31 301	90.88 355	61.05 394	65.83 359	84.15 351	43.43 372	94.83 321	66.62 327	60.63 376	86.02 359

test1111		88.11 172	87.04 180	91.35 165	93.15 209	78.79 218	96.57 171	90.78 356	86.88 116	85.04 178	95.20 164	57.23 318	97.39 198	83.88 184	94.59 127	97.87 102

ECVR-MVS		88.35 167	87.25 174	91.65 156	93.54 195	79.40 200	96.56 173	90.78 356	86.78 119	85.57 173	95.25 158	57.25 317	97.56 183	84.73 178	94.80 124	97.98 95

Anonymous20231206		75.29 334	73.64 335	80.22 355	80.75 381	63.38 379	93.36 297	90.71 358	73.09 345	67.12 349	83.70 355	50.33 350	90.85 376	53.63 381	70.10 325	86.44 352

USDC		78.65 309	76.25 315	85.85 293	87.58 329	74.60 303	89.58 342	90.58 359	84.05 183	63.13 371	88.23 288	40.69 387	96.86 231	66.57 329	75.81 292	86.09 358

MSDG		80.62 294	77.77 304	89.14 224	93.43 202	77.24 265	91.89 322	90.18 360	69.86 365	68.02 346	91.94 237	52.21 343	98.84 120	59.32 360	83.12 242	91.35 260

ACMH+	76.62 16	77.47 321	74.94 323	85.05 308	91.07 274	71.58 335	93.26 302	90.01 361	71.80 354	64.76 364	88.55 280	41.62 380	96.48 244	62.35 348	71.00 316	87.09 345

FMVSNet5		76.46 328	74.16 332	83.35 334	90.05 295	76.17 283	89.58 342	89.85 362	71.39 357	65.29 363	80.42 373	50.61 348	87.70 392	61.05 354	69.24 334	86.18 356

ambc				76.02 375	68.11 410	51.43 405	64.97 413	89.59 363		60.49 383	74.49 393	17.17 412	92.46 357	61.50 351	52.85 391	84.17 374

test_fmvs2		79.59 301	79.90 288	78.67 363	82.86 377	55.82 400	95.20 247	89.55 364	81.09 242	80.12 241	89.80 266	34.31 398	93.51 350	87.82 154	78.36 282	86.69 349

ITE_SJBPF				82.38 340	87.00 334	65.59 368		89.55 364	79.99 270	69.37 343	91.30 244	41.60 381	95.33 301	62.86 347	74.63 299	86.24 355

pmmvs-eth3d		73.59 340	70.66 348	82.38 340	76.40 399	73.38 311	89.39 345	89.43 366	72.69 349	60.34 384	77.79 383	46.43 366	91.26 373	66.42 331	57.06 381	82.51 382

test20.03		72.36 349	71.15 346	75.98 376	77.79 392	59.16 393	92.40 316	89.35 367	74.09 336	61.50 379	84.32 349	48.09 356	85.54 399	50.63 388	62.15 374	83.24 377

SixPastTwentyTwo		76.04 329	74.32 330	81.22 348	84.54 364	61.43 387	91.16 331	89.30 368	77.89 300	64.04 366	86.31 321	48.23 355	94.29 335	63.54 344	63.84 369	87.93 329

TransMVSNet (Re)		76.94 325	74.38 329	84.62 316	85.92 349	75.25 298	95.28 241	89.18 369	73.88 338	67.22 348	86.46 316	59.64 290	94.10 338	59.24 361	52.57 392	84.50 371

MIMVSNet1		69.44 360	66.65 364	77.84 366	76.48 398	62.84 381	87.42 361	88.97 370	66.96 376	57.75 393	79.72 379	32.77 401	85.83 398	46.32 397	63.42 370	84.85 369

K. test v3		73.62 339	71.59 345	79.69 357	82.98 376	59.85 392	90.85 335	88.83 371	77.13 311	58.90 387	82.11 363	43.62 371	91.72 368	65.83 333	54.10 387	87.50 340

Baseline_NR-MVSNet		81.22 286	80.07 284	84.68 313	85.32 358	75.12 299	96.48 177	88.80 372	76.24 321	77.28 267	86.40 320	67.61 238	94.39 333	75.73 269	66.73 359	84.54 370

MDA-MVSNet-bldmvs		71.45 353	67.94 360	81.98 344	85.33 357	68.50 355	92.35 317	88.76 373	70.40 360	42.99 407	81.96 364	46.57 365	91.31 372	48.75 395	54.39 386	86.11 357

new-patchmatchnet		68.85 363	65.93 365	77.61 368	73.57 406	63.94 376	90.11 339	88.73 374	71.62 356	55.08 397	73.60 395	40.84 385	87.22 395	51.35 386	48.49 399	81.67 393

Patchmatch-test		78.25 311	74.72 326	88.83 231	91.20 269	74.10 308	73.91 408	88.70 375	59.89 398	66.82 353	85.12 342	78.38 104	94.54 329	48.84 394	79.58 269	97.86 103

OpenMVS_ROB	68.52 20	73.02 346	69.57 353	83.37 333	80.54 384	71.82 331	93.60 292	88.22 376	62.37 385	61.98 377	83.15 360	35.31 397	95.47 295	45.08 400	75.88 291	82.82 379

mvsany_test1		87.58 185	88.22 149	85.67 298	89.78 298	67.18 360	95.25 244	87.93 377	83.96 187	88.79 138	97.06 112	72.52 202	94.53 330	92.21 95	86.45 216	95.30 215

RPSCF		77.73 318	76.63 313	81.06 350	88.66 317	55.76 401	87.77 359	87.88 378	64.82 380	74.14 305	92.79 221	49.22 354	96.81 233	67.47 322	76.88 287	90.62 266

MVS-HIRNet		71.36 355	67.00 361	84.46 320	90.58 284	69.74 348	79.15 396	87.74 379	46.09 408	61.96 378	50.50 412	45.14 368	95.64 287	53.74 380	88.11 202	88.00 328

mmtdpeth		78.04 313	76.76 312	81.86 345	89.60 305	66.12 367	92.34 318	87.18 380	76.83 316	85.55 174	76.49 388	46.77 364	97.02 218	90.85 112	45.24 404	82.43 385

DP-MVS		81.47 282	78.28 299	91.04 175	98.14 55	78.48 223	95.09 256	86.97 381	61.14 393	71.12 332	92.78 222	59.59 291	99.38 78	53.11 382	86.61 214	95.27 216

COLMAP_ROB	73.24 19	75.74 332	73.00 339	83.94 324	92.38 232	69.08 352	91.85 323	86.93 382	61.48 390	65.32 362	90.27 260	42.27 378	96.93 226	50.91 387	75.63 293	85.80 364
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MVStest1		66.93 366	63.01 370	78.69 362	78.56 389	71.43 337	85.51 377	86.81 383	49.79 407	48.57 402	84.15 351	53.46 339	83.31 402	43.14 403	37.15 413	81.34 394

test_fmvs3		69.56 358	69.19 356	70.67 382	69.01 408	47.05 408	90.87 334	86.81 383	71.31 358	66.79 354	77.15 385	16.40 413	83.17 404	81.84 209	62.51 373	81.79 391

test_0402		72.68 347	69.54 354	82.09 343	88.67 316	71.81 332	92.72 312	86.77 385	61.52 389	62.21 376	83.91 353	43.22 374	93.76 346	34.60 408	72.23 312	80.72 395

testgi		74.88 336	73.40 336	79.32 360	80.13 385	61.75 384	93.21 303	86.64 386	79.49 279	66.56 357	91.06 247	35.51 396	88.67 385	56.79 371	71.25 314	87.56 337

TDRefinement		69.20 362	65.78 366	79.48 358	66.04 413	62.21 383	88.21 352	86.12 387	62.92 383	61.03 382	85.61 331	33.23 399	94.16 337	55.82 375	53.02 390	82.08 388

ADS-MVSNet2		79.57 302	77.53 305	85.71 297	93.78 188	72.13 325	79.48 393	86.11 388	73.09 345	80.14 239	79.99 377	62.15 276	90.14 382	59.49 358	83.52 238	94.85 224

LF4IMVS		72.36 349	70.82 347	76.95 371	79.18 387	56.33 397	86.12 372	86.11 388	69.30 367	63.06 372	86.66 312	33.03 400	92.25 360	65.33 335	68.64 338	82.28 386

TinyColmap		72.41 348	68.99 357	82.68 338	88.11 323	69.59 349	88.41 351	85.20 390	65.55 377	57.91 391	84.82 346	30.80 404	95.94 267	51.38 384	68.70 337	82.49 384

mvs5depth		71.40 354	68.36 359	80.54 354	75.31 403	65.56 369	79.94 392	85.14 391	69.11 368	71.75 327	81.59 366	41.02 384	93.94 341	60.90 355	50.46 394	82.10 387

pmmvs3		65.75 368	62.18 371	76.45 374	67.12 412	64.54 371	88.68 349	85.05 392	54.77 406	57.54 394	73.79 394	29.40 405	86.21 397	55.49 377	47.77 401	78.62 398

new_pmnet		66.18 367	63.18 369	75.18 379	76.27 400	61.74 385	83.79 385	84.66 393	56.64 404	51.57 400	71.85 403	31.29 403	87.93 388	49.98 390	62.55 372	75.86 401

AllTest		75.92 330	73.06 338	84.47 318	92.18 244	67.29 358	91.07 332	84.43 394	67.63 371	63.48 367	90.18 261	38.20 389	97.16 211	57.04 368	73.37 303	88.97 306

TestCases				84.47 318	92.18 244	67.29 358		84.43 394	67.63 371	63.48 367	90.18 261	38.20 389	97.16 211	57.04 368	73.37 303	88.97 306

ttmdpeth		69.58 357	66.92 363	77.54 369	75.95 402	62.40 382	88.09 354	84.32 396	62.87 384	65.70 361	86.25 323	36.53 391	88.53 386	55.65 376	46.96 403	81.70 392

LCM-MVSNet-Re		83.75 246	83.54 233	84.39 322	93.54 195	64.14 374	92.51 313	84.03 397	83.90 190	66.14 358	86.59 313	67.36 243	92.68 355	84.89 177	92.87 153	96.35 186

Gipuma		45.11 383	42.05 385	54.30 399	80.69 382	51.30 406	35.80 417	83.81 398	28.13 413	27.94 417	34.53 417	11.41 420	76.70 413	21.45 416	54.65 384	34.90 417
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		52.52 377	48.24 380	65.35 387	47.63 424	41.45 416	72.55 409	83.62 399	31.75 412	37.66 410	57.92 410	9.19 422	76.76 412	49.26 392	44.60 406	77.84 399

FPMVS		55.09 375	52.93 378	61.57 393	55.98 417	40.51 418	83.11 388	83.41 400	37.61 411	34.95 412	71.95 401	14.40 414	76.95 411	29.81 411	65.16 363	67.25 406

Patchmatch-RL test		76.65 327	74.01 334	84.55 317	77.37 395	64.23 373	78.49 399	82.84 401	78.48 296	64.63 365	73.40 396	76.05 146	91.70 369	76.99 253	57.84 380	97.72 114

DSMNet-mixed		73.13 345	72.45 340	75.19 378	77.51 394	46.82 409	85.09 380	82.01 402	67.61 375	69.27 344	81.33 369	50.89 346	86.28 396	54.54 378	83.80 237	92.46 255

lessismore_v0				79.98 356	80.59 383	58.34 395		80.87 403		58.49 389	83.46 357	43.10 375	93.89 342	63.11 346	48.68 397	87.72 331

test_f		64.01 369	62.13 372	69.65 383	63.00 415	45.30 414	83.66 386	80.68 404	61.30 391	55.70 396	72.62 399	14.23 415	84.64 400	69.84 312	58.11 379	79.00 397

door								80.13 405

door-mid								79.75 406

PM-MVS		69.32 361	66.93 362	76.49 373	73.60 405	55.84 399	85.91 373	79.32 407	74.72 331	61.09 381	78.18 382	21.76 409	91.10 374	70.86 307	56.90 382	82.51 382

mvsany_test3		67.19 365	65.34 367	72.72 380	63.08 414	48.57 407	83.12 387	78.09 408	72.07 352	61.21 380	77.11 386	22.94 408	87.78 391	78.59 236	51.88 393	81.80 390

dmvs_testset		72.00 352	73.36 337	67.91 384	83.83 373	31.90 424	85.30 378	77.12 409	82.80 216	63.05 373	92.46 224	61.54 283	82.55 406	42.22 405	71.89 313	89.29 292

ANet_high		46.22 380	41.28 387	61.04 394	39.91 426	46.25 412	70.59 410	76.18 410	58.87 401	23.09 418	48.00 415	12.58 418	66.54 418	28.65 413	13.62 419	70.35 404

test_method		56.77 372	54.53 376	63.49 391	76.49 397	40.70 417	75.68 404	74.24 411	19.47 419	48.73 401	71.89 402	19.31 410	65.80 419	57.46 367	47.51 402	83.97 375

APD_test1		56.56 373	53.58 377	65.50 386	67.93 411	46.51 411	77.24 403	72.95 412	38.09 410	42.75 408	75.17 390	13.38 416	82.78 405	40.19 406	54.53 385	67.23 407

EGC-MVSNET		52.46 378	47.56 381	67.15 385	81.98 379	60.11 390	82.54 389	72.44 413	0.11 425	0.70 426	74.59 392	25.11 407	83.26 403	29.04 412	61.51 375	58.09 410

PMMVS2		50.90 379	46.31 382	64.67 388	55.53 418	46.67 410	77.30 402	71.02 414	40.89 409	34.16 413	59.32 408	9.83 421	76.14 414	40.09 407	28.63 416	71.21 403

WB-MVS		57.26 371	56.22 374	60.39 395	69.29 407	35.91 422	86.39 371	70.06 415	59.84 399	46.46 405	72.71 398	51.18 345	78.11 409	15.19 419	34.89 414	67.14 408

SSC-MVS		56.01 374	54.96 375	59.17 396	68.42 409	34.13 423	84.98 381	69.23 416	58.08 403	45.36 406	71.67 404	50.30 351	77.46 410	14.28 420	32.33 415	65.91 409

test_vis1_rt		73.96 338	72.40 341	78.64 364	83.91 372	61.16 388	95.63 229	68.18 417	76.32 318	60.09 385	74.77 391	29.01 406	97.54 187	87.74 155	75.94 290	77.22 400

MTMP							97.53 93	68.16 418

DeepMVS_CX				64.06 390	78.53 390	43.26 415		68.11 419	69.94 364	38.55 409	76.14 389	18.53 411	79.34 407	43.72 401	41.62 410	69.57 405

PMVS	34.80 23	39.19 385	35.53 388	50.18 400	29.72 427	30.30 425	59.60 415	66.20 420	26.06 416	17.91 420	49.53 413	3.12 426	74.09 415	18.19 418	49.40 396	46.14 414
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testf1		45.70 381	42.41 383	55.58 397	53.29 421	40.02 419	68.96 411	62.67 421	27.45 414	29.85 414	61.58 406	5.98 424	73.83 416	28.49 414	43.46 408	52.90 411

APD_test2		45.70 381	42.41 383	55.58 397	53.29 421	40.02 419	68.96 411	62.67 421	27.45 414	29.85 414	61.58 406	5.98 424	73.83 416	28.49 414	43.46 408	52.90 411

tmp_tt		41.54 384	41.93 386	40.38 402	20.10 428	26.84 426	61.93 414	59.09 423	14.81 421	28.51 416	80.58 372	35.53 395	48.33 423	63.70 343	13.11 420	45.96 416

MVE	35.65 22	33.85 386	29.49 391	46.92 401	41.86 425	36.28 421	50.45 416	56.52 424	18.75 420	18.28 419	37.84 416	2.41 427	58.41 420	18.71 417	20.62 417	46.06 415
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		32.70 387	32.39 389	33.65 403	53.35 420	25.70 427	74.07 407	53.33 425	21.08 417	17.17 421	33.63 419	11.85 419	54.84 421	12.98 421	14.04 418	20.42 418

EMVS		31.70 388	31.45 390	32.48 404	50.72 423	23.95 428	74.78 406	52.30 426	20.36 418	16.08 422	31.48 420	12.80 417	53.60 422	11.39 422	13.10 421	19.88 419

test_vis3_rt		54.10 376	51.04 379	63.27 392	58.16 416	46.08 413	84.17 383	49.32 427	56.48 405	36.56 411	49.48 414	8.03 423	91.91 366	67.29 323	49.87 395	51.82 413

N_pmnet		61.30 370	60.20 373	64.60 389	84.32 366	17.00 430	91.67 327	10.98 428	61.77 388	58.45 390	78.55 381	49.89 352	91.83 367	42.27 404	63.94 368	84.97 368

wuyk23d		14.10 390	13.89 393	14.72 405	55.23 419	22.91 429	33.83 418	3.56 429	4.94 422	4.11 423	2.28 425	2.06 428	19.66 424	10.23 423	8.74 422	1.59 422

testmvs		9.92 391	12.94 394	0.84 407	0.65 429	0.29 432	93.78 288	0.39 430	0.42 423	2.85 424	15.84 423	0.17 430	0.30 426	2.18 424	0.21 423	1.91 421

test123		9.07 392	11.73 395	1.11 406	0.50 430	0.77 431	89.44 344	0.20 431	0.34 424	2.15 425	10.72 424	0.34 429	0.32 425	1.79 425	0.08 424	2.23 420

mmdepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		5.92 394	7.89 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	71.04 222	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

n2								0.00 432

nn								0.00 432

ab-mvs-re		8.11 393	10.81 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	97.30 98	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						67.18 360								49.00 393

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					0.00 431

eth-test					0.00 431

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

GSMVS																97.54 128

test_part2					98.90 19	85.14 71				96.07 29

sam_mvs1												77.59 117				97.54 128

sam_mvs												75.35 165

test_post1							85.88 374				30.24 421	73.77 188	95.07 316	73.89 285

test_post											33.80 418	76.17 144	95.97 263

patchmatchnet-post											77.09 387	77.78 116	95.39 297

gm-plane-assit					92.27 238	79.64 196			84.47 170		95.15 168		97.93 162	85.81 169

test9_res														96.00 40	99.03 13	98.31 68

agg_prior2														94.30 64	99.00 15	98.57 53

test_prior4						82.34 121	97.75 76

test_prior2							98.37 39		86.08 128	94.57 50	98.02 54	83.14 55		95.05 55	98.79 27

旧先验2							96.97 144		74.06 337	96.10 28			97.76 173	88.38 149

新几何2							96.42 184

原ACMM2							96.84 154

testdata2													99.48 73	76.45 260

segment_acmp												82.69 61

testdata1							95.57 233		87.44 101

plane_prior7					91.86 259	77.55 260

plane_prior6					91.98 255	77.92 246						64.77 262

plane_prior4											94.15 195

plane_prior3						77.75 256			90.17 52	81.33 225

plane_prior2							97.18 120		89.89 54

plane_prior1					91.95 257

plane_prior						77.96 243	97.52 96		90.36 50						82.96 246

HQP5-MVS						78.48 223

HQP-NCC					92.08 250		97.63 82		90.52 45	82.30 212

ACMP_Plane					92.08 250		97.63 82		90.52 45	82.30 212

BP-MVS														87.67 157

HQP4-MVS										82.30 212			97.32 201			91.13 261

HQP2-MVS												65.40 257

NP-MVS					92.04 254	78.22 233					94.56 185

MDTV_nov1_ep13_2view						81.74 137	86.80 366		80.65 251	85.65 172		74.26 182		76.52 259		96.98 163

ACMMP++_ref															78.45 281

ACMMP++															79.05 273

Test By Simon												71.65 215

High-resolution multi-view benchmark