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		88.92 159	87.65 171	92.73 109	96.30 103	85.62 56	97.85 76	98.86 1	84.38 183	84.82 193	93.99 210	75.12 179	98.01 169	70.86 319	86.67 224	94.56 242

thres100view900		88.30 179	86.95 193	92.33 129	96.10 111	84.90 78	97.14 138	98.85 2	82.69 232	83.41 211	93.66 219	75.43 169	97.93 172	69.04 327	86.24 231	94.17 245

tfpn200view9		88.48 173	87.15 187	92.47 120	96.21 106	85.30 64	97.44 111	98.85 2	83.37 215	83.99 203	93.82 215	75.36 172	97.93 172	69.04 327	86.24 231	94.17 245

thres600view7		88.06 184	86.70 199	92.15 142	96.10 111	85.17 70	97.14 138	98.85 2	82.70 231	83.41 211	93.66 219	75.43 169	97.82 181	67.13 336	85.88 235	93.45 261

thres400		88.42 176	87.15 187	92.23 135	96.21 106	85.30 64	97.44 111	98.85 2	83.37 215	83.99 203	93.82 215	75.36 172	97.93 172	69.04 327	86.24 231	93.45 261

MVS_111021_HR		93.41 48	93.39 52	93.47 81	97.34 89	82.83 114	97.56 100	98.27 6	89.16 72	89.71 129	97.14 114	79.77 87	99.56 74	93.65 82	97.94 59	98.02 89

sss		90.87 124	89.96 134	93.60 71	94.15 183	83.84 95	97.14 138	98.13 7	85.93 144	89.68 130	96.09 146	71.67 224	99.30 91	87.69 167	89.16 194	97.66 122

MM		95.85 6	95.74 10	96.15 8	96.34 102	89.50 9	99.18 7	98.10 8	95.68 1	96.64 27	97.92 70	80.72 72	99.80 26	99.16 2	97.96 58	99.15 27

MG-MVS		94.25 31	93.72 42	95.85 12	99.38 3	89.35 11	97.98 69	98.09 9	89.99 62	92.34 91	96.97 124	81.30 70	98.99 118	88.54 156	98.88 20	99.20 25

VNet		92.11 89	91.22 101	94.79 28	96.91 95	86.98 31	97.91 73	97.96 10	86.38 134	93.65 70	95.74 152	70.16 241	98.95 122	93.39 84	88.87 199	98.43 62

test_yl		91.46 105	90.53 116	94.24 42	97.41 83	85.18 66	98.08 62	97.72 11	80.94 257	89.85 126	96.14 144	75.61 161	98.81 130	90.42 134	88.56 205	98.74 42

DCV-MVSNet		91.46 105	90.53 116	94.24 42	97.41 83	85.18 66	98.08 62	97.72 11	80.94 257	89.85 126	96.14 144	75.61 161	98.81 130	90.42 134	88.56 205	98.74 42

WTY-MVS		92.65 74	91.68 92	95.56 14	96.00 113	88.90 13	98.23 53	97.65 13	88.57 79	89.82 128	97.22 112	79.29 91	99.06 115	89.57 145	88.73 201	98.73 46

EPNet		94.06 36	94.15 37	93.76 57	97.27 91	84.35 85	98.29 51	97.64 14	94.57 8	95.36 43	96.88 127	79.96 86	99.12 111	91.30 115	96.11 113	97.82 110
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HY-MVS	84.06 6	91.63 101	90.37 122	95.39 19	96.12 110	88.25 17	90.22 351	97.58 15	88.33 87	90.50 121	91.96 247	79.26 92	99.06 115	90.29 136	89.07 195	98.88 37

testing3-2		91.37 108	91.01 108	92.44 123	95.93 118	83.77 96	98.83 33	97.45 16	86.88 126	86.63 175	94.69 194	84.57 40	97.75 184	89.65 143	84.44 245	95.80 206

baseline2		90.39 133	90.21 126	90.93 188	90.86 291	80.99 160	95.20 258	97.41 17	86.03 142	80.07 253	94.61 195	90.58 6	97.47 205	87.29 171	89.86 189	94.35 244

test2506		90.96 121	90.39 120	92.65 113	93.54 202	82.46 123	96.37 197	97.35 18	86.78 130	87.55 163	95.25 168	77.83 118	97.50 202	84.07 193	94.80 131	97.98 96

PVSNet	82.34 9	89.02 156	87.79 169	92.71 110	95.49 133	81.50 148	97.70 89	97.29 19	87.76 103	85.47 186	95.12 180	56.90 331	98.90 126	80.33 228	94.02 142	97.71 118

testing222		91.09 116	90.49 118	92.87 102	95.82 121	85.04 73	96.51 187	97.28 20	86.05 140	89.13 140	95.34 167	80.16 82	96.62 252	85.82 179	88.31 209	96.96 167

PGM-MVS		91.93 92	91.80 90	92.32 131	98.27 50	79.74 201	95.28 252	97.27 21	83.83 204	90.89 117	97.78 80	76.12 153	99.56 74	88.82 153	97.93 61	97.66 122

IB-MVS	85.34 4	88.67 167	87.14 189	93.26 84	93.12 220	84.32 86	98.76 34	97.27 21	87.19 121	79.36 259	90.45 269	83.92 52	98.53 141	84.41 190	69.79 341	96.93 169
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	92.45 121	95.29 140	80.96 162	99.29 3	97.21 23	94.50 10	97.29 18	98.44 32	82.15 64	99.78 32	98.56 8	97.68 67	96.61 185

patch_mono-2		95.14 13	96.08 7	92.33 129	98.44 43	77.84 259	98.43 46	97.21 23	92.58 25	97.68 12	97.65 88	86.88 27	99.83 17	98.25 14	97.60 69	99.33 18

MVS		90.60 128	88.64 154	96.50 5	94.25 179	90.53 8	93.33 311	97.21 23	77.59 318	78.88 263	97.31 104	71.52 227	99.69 56	89.60 144	98.03 56	99.27 22

ETVMVS		90.99 119	90.26 123	93.19 88	95.81 122	85.64 55	96.97 155	97.18 26	85.43 152	88.77 149	94.86 189	82.00 66	96.37 259	82.70 214	88.60 202	97.57 129

CSCG		92.02 90	91.65 93	93.12 90	98.53 36	80.59 173	97.47 108	97.18 26	77.06 327	84.64 198	97.98 67	83.98 50	99.52 77	90.72 125	97.33 79	99.23 24

fmvsm_s_conf0.5_n		93.69 41	94.13 38	92.34 127	94.56 163	82.01 128	99.07 19	97.13 28	92.09 31	96.25 32	98.53 24	76.47 144	99.80 26	98.39 10	94.71 133	95.22 225

PHI-MVS		93.59 43	93.63 45	93.48 79	98.05 58	81.76 140	98.64 40	97.13 28	82.60 234	94.09 65	98.49 27	80.35 76	99.85 11	94.74 69	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 20	97.12 30	94.66 7	96.79 23	98.78 9	86.42 30	99.95 3	97.59 32	99.18 7	99.00 31

h-mvs33		89.30 152	88.95 149	90.36 206	95.07 149	76.04 297	96.96 157	97.11 31	90.39 57	92.22 93	95.10 181	74.70 185	98.86 127	93.14 92	65.89 374	96.16 198

MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 10	98.94 28	97.10 32	95.17 4	92.11 95	98.46 31	87.33 25	99.97 2	97.21 38	99.31 4	99.63 7

testing11		92.48 79	92.04 87	93.78 56	95.94 117	86.00 41	97.56 100	97.08 33	87.52 109	89.32 137	95.40 165	84.60 39	98.02 168	91.93 111	89.04 196	97.32 149

VPA-MVSNet		85.32 233	83.83 238	89.77 228	90.25 301	82.63 118	96.36 198	97.07 34	83.03 223	81.21 238	89.02 286	61.58 294	96.31 262	85.02 187	70.95 330	90.36 281

UBG		92.68 73	92.35 75	93.70 64	95.61 129	85.65 54	97.25 125	97.06 35	87.92 98	89.28 138	95.03 183	86.06 33	98.07 164	92.24 104	90.69 185	97.37 147

UWE-MVS		88.56 172	88.91 151	87.50 276	94.17 182	72.19 336	95.82 232	97.05 36	84.96 167	84.78 194	93.51 223	81.33 68	94.75 335	79.43 239	89.17 193	95.57 214

UWE-MVS-28		85.41 232	86.36 201	82.59 352	91.12 284	66.81 377	93.88 298	97.03 37	83.86 203	78.55 265	93.84 214	77.76 120	88.55 398	73.47 301	87.69 216	92.41 268

DELS-MVS		94.98 14	94.49 28	96.44 6	96.42 101	90.59 7	99.21 6	97.02 38	94.40 11	91.46 104	97.08 119	83.32 56	99.69 56	92.83 97	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 78	94.94 153	86.26 37	81.62 403	97.00 39		88.32 156	94.30 201	91.23 5	96.21 267	88.49 158	97.43 75	98.00 94

myMVS_eth3d28		92.72 66	92.23 80	94.21 44	96.16 108	87.46 29	97.37 119	96.99 40	88.13 93	88.18 158	95.47 163	84.12 48	98.04 166	92.46 102	91.17 180	97.14 161

fmvsm_s_conf0.5_n_a		93.34 49	93.71 43	92.22 136	93.38 211	81.71 143	98.86 32	96.98 41	91.64 37	96.85 22	98.55 21	75.58 164	99.77 34	97.88 28	93.68 151	95.18 227

DPM-MVS		96.21 2	95.53 13	98.26 1	96.26 105	95.09 1	99.15 9	96.98 41	93.39 19	96.45 31	98.79 8	90.17 9	99.99 1	89.33 149	99.25 6	99.70 3

gg-mvs-nofinetune		85.48 231	82.90 254	93.24 85	94.51 170	85.82 46	79.22 408	96.97 43	61.19 405	87.33 166	53.01 424	90.58 6	96.07 270	86.07 178	97.23 82	97.81 111

NCCC		95.63 7	95.94 8	94.69 32	99.21 6	85.15 71	99.16 8	96.96 44	94.11 12	95.59 42	98.64 18	85.07 36	99.91 4	95.61 55	99.10 9	99.00 31

FIs		86.73 209	86.10 204	88.61 246	90.05 307	80.21 187	96.14 214	96.95 45	85.56 151	78.37 268	92.30 239	76.73 140	95.28 315	79.51 237	79.27 283	90.35 282

PVSNet_0	77.72 15	81.70 291	78.95 309	89.94 221	90.77 294	76.72 286	95.96 221	96.95 45	85.01 165	70.24 352	88.53 294	52.32 353	98.20 159	86.68 177	44.08 420	94.89 231

HPM-MVS++		95.32 11	95.48 14	94.85 26	98.62 34	86.04 40	97.81 80	96.93 47	92.45 26	95.69 40	98.50 26	85.38 34	99.85 11	94.75 68	99.18 7	98.65 50

MSLP-MVS++		94.28 29	94.39 31	93.97 50	98.30 49	84.06 91	98.64 40	96.93 47	90.71 51	93.08 79	98.70 16	79.98 85	99.21 98	94.12 77	99.07 11	98.63 51

testing99		91.91 93	91.35 98	93.60 71	95.98 115	85.70 49	97.31 123	96.92 49	86.82 128	88.91 144	95.25 168	84.26 47	97.89 179	88.80 154	87.94 213	97.21 157

testing91		91.90 94	91.31 100	93.66 67	95.99 114	85.68 51	97.39 118	96.89 50	86.75 132	88.85 146	95.23 171	83.93 51	97.90 178	88.91 151	87.89 214	97.41 143

UniMVSNet (Re)		85.31 234	84.23 232	88.55 247	89.75 312	80.55 175	96.72 174	96.89 50	85.42 153	78.40 267	88.93 287	75.38 171	95.52 305	78.58 248	68.02 358	89.57 297

FC-MVSNet-test		85.96 219	85.39 212	87.66 269	89.38 323	78.02 250	95.65 239	96.87 52	85.12 162	77.34 277	91.94 249	76.28 151	94.74 336	77.09 263	78.82 287	90.21 285

EI-MVSNet-Vis-set		91.84 96	91.77 91	92.04 147	97.60 72	81.17 153	96.61 180	96.87 52	88.20 91	89.19 139	97.55 96	78.69 103	99.14 108	90.29 136	90.94 182	95.80 206

IU-MVS					99.03 15	85.34 61		96.86 54	92.05 35	98.74 1				98.15 18	98.97 17	99.42 13

BP-MVS1		93.55 46	93.50 49	93.71 63	92.64 238	85.39 60	97.78 82	96.84 55	89.52 67	92.00 96	97.06 121	88.21 20	98.03 167	91.45 114	96.00 118	97.70 119

MSC_two_6792asdad				97.14 3	99.05 9	92.19 4		96.83 56					99.81 22	98.08 22	98.81 24	99.43 11

No_MVS				97.14 3	99.05 9	92.19 4		96.83 56					99.81 22	98.08 22	98.81 24	99.43 11

EI-MVSNet-UG-set		91.35 110	91.22 101	91.73 161	97.39 86	80.68 170	96.47 189	96.83 56	87.92 98	88.30 157	97.36 103	77.84 117	99.13 110	89.43 148	89.45 191	95.37 220

SED-MVS		95.88 5	96.22 4	94.87 25	99.03 15	85.03 74	99.12 13	96.78 59	88.72 76	97.79 8	98.91 2	88.48 17	99.82 19	98.15 18	98.97 17	99.74 1

test_241102_TWO								96.78 59	88.72 76	97.70 10	98.91 2	87.86 22	99.82 19	98.15 18	99.00 15	99.47 9

test_241102_ONE					99.03 15	85.03 74		96.78 59	88.72 76	97.79 8	98.90 5	88.48 17	99.82 19

test0726					99.05 9	85.18 66	99.11 16	96.78 59	88.75 74	97.65 13	98.91 2	87.69 23

MSP-MVS		95.62 8	96.54 1	92.86 103	98.31 48	80.10 191	97.42 115	96.78 59	92.20 30	97.11 19	98.29 44	93.46 1	99.10 112	96.01 48	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							96.87 164	96.78 59	77.39 320				99.52 77	79.95 234		98.43 62

DVP-MVS++		96.05 4	96.41 3	94.96 24	99.05 9	85.34 61	98.13 59	96.77 65	88.38 84	97.70 10	98.77 10	92.06 3	99.84 13	97.47 33	99.37 1	99.70 3

test_0728_SECOND				95.14 20	99.04 14	86.14 39	99.06 20	96.77 65					99.84 13	97.90 26	98.85 21	99.45 10

SMA-MVS		94.70 21	94.68 24	94.76 29	98.02 59	85.94 44	97.47 108	96.77 65	85.32 155	97.92 4	98.70 16	83.09 59	99.84 13	95.79 52	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		91.60 103	91.64 94	91.47 173	95.74 125	78.79 228	96.15 213	96.77 65	88.49 81	88.64 151	97.07 120	72.33 216	99.19 104	93.13 94	96.48 107	96.43 190

3Dnovator	82.32 10	89.33 151	87.64 172	94.42 37	93.73 198	85.70 49	97.73 87	96.75 69	86.73 133	76.21 298	95.93 148	62.17 287	99.68 58	81.67 221	97.81 63	97.88 102

fmvsm_s_conf0.5_n_7		92.88 59	93.82 40	90.08 213	92.79 233	76.45 290	98.54 44	96.74 70	92.28 28	95.22 45	98.49 27	74.91 182	98.15 163	98.28 12	97.13 87	95.63 211

DPE-MVS		95.32 11	95.55 12	94.64 33	98.79 23	84.87 79	97.77 83	96.74 70	86.11 137	96.54 30	98.89 6	88.39 19	99.74 44	97.67 31	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		90.05 138	89.96 134	90.33 207	97.47 77	83.86 93	98.02 68	96.73 72	87.98 96	89.53 134	89.61 281	76.42 146	99.57 72	94.29 74	79.59 280	87.57 349

PVSNet_Blended		93.13 50	92.98 60	93.57 73	97.47 77	83.86 93	99.32 2	96.73 72	91.02 48	89.53 134	96.21 143	76.42 146	99.57 72	94.29 74	95.81 122	97.29 153

ACMMP		90.39 133	89.97 133	91.64 165	97.58 74	78.21 246	96.78 171	96.72 74	84.73 172	84.72 196	97.23 111	71.22 229	99.63 64	88.37 161	92.41 169	97.08 164
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 90	97.44 81	81.60 147		96.71 75	74.54 346	91.22 111	97.57 92	79.13 95	99.51 79	77.40 262	98.46 40	98.26 74

test_one_0601					98.91 18	84.56 84		96.70 76	88.06 94	96.57 29	98.77 10	88.04 21

HFP-MVS		92.89 58	92.86 64	92.98 97	98.71 25	81.12 155	97.58 98	96.70 76	85.20 160	91.75 101	97.97 69	78.47 106	99.71 52	90.95 118	98.41 43	98.12 85

ACMMPR		92.69 71	92.67 67	92.75 107	98.66 28	80.57 174	97.58 98	96.69 78	85.20 160	91.57 103	97.92 70	77.01 133	99.67 60	90.95 118	98.41 43	98.00 94

DeepPCF-MVS	89.82 1	94.61 22	96.17 5	89.91 222	97.09 94	70.21 356	98.99 26	96.69 78	95.57 2	95.08 50	99.23 1	86.40 31	99.87 8	97.84 29	98.66 32	99.65 6

thisisatest0530		89.65 146	89.02 146	91.53 170	93.46 209	80.78 168	96.52 185	96.67 80	81.69 250	83.79 208	94.90 188	88.85 14	97.68 187	77.80 251	87.49 220	96.14 199

tttt0517		88.57 171	88.19 162	89.71 229	93.00 222	75.99 301	95.67 237	96.67 80	80.78 261	81.82 233	94.40 199	88.97 13	97.58 193	76.05 276	86.31 228	95.57 214

thisisatest0515		90.95 122	90.26 123	93.01 95	94.03 192	84.27 89	97.91 73	96.67 80	83.18 218	86.87 173	95.51 162	88.66 15	97.85 180	80.46 227	89.01 197	96.92 171

fmvsm_s_conf0.5_n_8		94.52 26	95.04 19	92.96 98	95.15 146	81.14 154	99.09 17	96.66 83	95.53 3	97.84 7	98.71 15	76.33 149	99.81 22	99.24 1	96.85 98	97.92 100

ACMMP_NAP		93.46 47	93.23 55	94.17 46	97.16 92	84.28 88	96.82 168	96.65 84	86.24 135	94.27 62	97.99 64	77.94 114	99.83 17	93.39 84	98.57 34	98.39 64

TEST9					98.64 31	83.71 97	97.82 78	96.65 84	84.29 188	95.16 46	98.09 57	84.39 42	99.36 89

train_agg		94.28 29	94.45 29	93.74 59	98.64 31	83.71 97	97.82 78	96.65 84	84.50 179	95.16 46	98.09 57	84.33 43	99.36 89	95.91 51	98.96 19	98.16 80

1314		88.94 158	87.20 186	94.17 46	93.21 214	85.73 48	93.33 311	96.64 87	82.89 226	75.98 301	96.36 140	66.83 260	99.39 85	83.52 207	96.02 117	97.39 146

DeepC-MVS_fast	89.06 2	94.48 27	94.30 34	95.02 22	98.86 21	85.68 51	98.06 65	96.64 87	93.64 17	91.74 102	98.54 22	80.17 81	99.90 5	92.28 103	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	83.64 100	97.81 80	96.63 89	84.50 179	95.10 49	98.11 55	84.33 43	99.23 96

FE-MVS		86.06 218	84.15 235	91.78 158	94.33 178	79.81 196	84.58 395	96.61 90	76.69 330	85.00 190	87.38 312	70.71 237	98.37 152	70.39 322	91.70 177	97.17 160

原ACMM1				91.22 182	97.77 65	78.10 249		96.61 90	81.05 256	91.28 110	97.42 101	77.92 116	98.98 119	79.85 236	98.51 36	96.59 186

MAR-MVS		90.63 127	90.22 125	91.86 154	98.47 42	78.20 247	97.18 131	96.61 90	83.87 202	88.18 158	98.18 49	68.71 246	99.75 41	83.66 203	97.15 86	97.63 125
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	83.22 109		96.60 93	82.88 227	93.61 72	98.06 62	82.93 60	99.14 108	95.51 58	98.49 39

MVS_0304		95.58 9	95.44 15	96.01 10	97.63 70	89.26 12	99.27 4	96.59 94	94.71 6	97.08 20	97.99 64	78.69 103	99.86 10	99.15 3	97.85 62	98.91 35

SteuartSystems-ACMMP		94.13 35	94.44 30	93.20 87	95.41 135	81.35 150	99.02 24	96.59 94	89.50 68	94.18 64	98.36 41	83.68 54	99.45 83	94.77 67	98.45 41	98.81 39
Skip Steuart: Steuart Systems R&D Blog.
D2MVS		82.67 277	81.55 274	86.04 303	87.77 340	76.47 288	95.21 257	96.58 96	82.66 233	70.26 351	85.46 348	60.39 299	95.80 285	76.40 272	79.18 284	85.83 376

save fliter					98.24 51	83.34 106	98.61 42	96.57 97	91.32 41

TESTMET0.1,1		89.83 142	89.34 143	91.31 176	92.54 241	80.19 188	97.11 141	96.57 97	86.15 136	86.85 174	91.83 251	79.32 90	96.95 234	81.30 222	92.35 170	96.77 178

agg_prior					98.59 35	83.13 110		96.56 99		94.19 63			99.16 107

旧先验1					97.39 86	79.58 206		96.54 100			98.08 60	84.00 49			97.42 76	97.62 126

WR-MVS_H		81.02 301	80.09 294	83.79 338	88.08 337	71.26 351	94.46 277	96.54 100	80.08 280	72.81 333	86.82 322	70.36 239	92.65 368	64.18 352	67.50 364	87.46 354

fmvsm_s_conf0.5_n_4		93.59 43	94.32 33	91.41 174	93.89 193	79.24 213	98.89 31	96.53 102	92.82 23	97.37 17	98.47 30	77.21 132	99.78 32	98.11 21	95.59 125	95.21 226

9.14			94.26 36		98.10 57		98.14 56	96.52 103	84.74 171	94.83 56	98.80 7	82.80 62	99.37 88	95.95 50	98.42 42

region2R		92.72 66	92.70 66	92.79 106	98.68 26	80.53 179	97.53 103	96.51 104	85.22 158	91.94 99	97.98 67	77.26 127	99.67 60	90.83 123	98.37 46	98.18 78

EPP-MVSNet		89.76 143	89.72 139	89.87 223	93.78 195	76.02 300	97.22 126	96.51 104	79.35 293	85.11 188	95.01 185	84.82 37	97.10 227	87.46 170	88.21 211	96.50 188

ZNCC-MVS		92.75 62	92.60 69	93.23 86	98.24 51	81.82 138	97.63 92	96.50 106	85.00 166	91.05 113	97.74 81	78.38 107	99.80 26	90.48 129	98.34 48	98.07 87

test11								96.50 106

EPNet_dtu		87.65 195	87.89 166	86.93 289	94.57 162	71.37 350	96.72 174	96.50 106	88.56 80	87.12 170	95.02 184	75.91 158	94.01 352	66.62 340	90.00 187	95.42 219
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testdata				90.13 212	95.92 119	74.17 318		96.49 109	73.49 355	94.82 57	97.99 64	78.80 101	97.93 172	83.53 206	97.52 71	98.29 71

fmvsm_s_conf0.5_n_6		94.17 32	94.70 23	92.58 118	93.50 208	81.20 152	99.08 18	96.48 110	92.24 29	98.62 2	98.39 37	78.58 105	99.72 49	98.08 22	97.36 78	96.81 175

DVP-MVS		95.58 9	95.91 9	94.57 34	99.05 9	85.18 66	99.06 20	96.46 111	88.75 74	96.69 24	98.76 12	87.69 23	99.76 36	97.90 26	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					96.15 109	78.41 237	95.87 228	96.46 111	71.97 366	89.66 131	97.45 97	76.33 149			98.24 51	98.30 70

XVS		92.69 71	92.71 65	92.63 115	98.52 37	80.29 182	97.37 119	96.44 113	87.04 123	91.38 105	97.83 78	77.24 129	99.59 68	90.46 131	98.07 54	98.02 89

X-MVStestdata		86.26 215	84.14 236	92.63 115	98.52 37	80.29 182	97.37 119	96.44 113	87.04 123	91.38 105	20.73 435	77.24 129	99.59 68	90.46 131	98.07 54	98.02 89

SF-MVS		94.17 32	94.05 39	94.55 35	97.56 75	85.95 42	97.73 87	96.43 115	84.02 195	95.07 51	98.74 14	82.93 60	99.38 86	95.42 59	98.51 36	98.32 67

TSAR-MVS + MP.		94.79 20	95.17 18	93.64 68	97.66 69	84.10 90	95.85 230	96.42 116	91.26 42	97.49 16	96.80 132	86.50 29	98.49 143	95.54 57	99.03 13	98.33 66
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 25	94.75 22	93.96 51	98.84 22	83.40 105	98.04 67	96.41 117	85.79 146	95.00 52	98.28 45	84.32 46	99.18 105	97.35 35	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		85.49 230	84.59 225	88.21 258	89.44 322	79.36 210	96.71 176	96.41 117	85.22 158	78.11 271	90.98 262	76.97 135	95.14 322	79.14 243	68.30 355	90.12 288

test_prior				93.09 92	98.68 26	81.91 133		96.40 119					99.06 115			98.29 71

CP-MVS		92.54 77	92.60 69	92.34 127	98.50 40	79.90 195	98.40 48	96.40 119	84.75 170	90.48 122	98.09 57	77.40 125	99.21 98	91.15 117	98.23 52	97.92 100

CANet		94.89 16	94.64 25	95.63 13	97.55 76	88.12 18	99.06 20	96.39 121	94.07 14	95.34 44	97.80 79	76.83 138	99.87 8	97.08 40	97.64 68	98.89 36

GST-MVS		92.43 81	92.22 82	93.04 94	98.17 54	81.64 145	97.40 117	96.38 122	84.71 173	90.90 116	97.40 102	77.55 123	99.76 36	89.75 142	97.74 65	97.72 116

alignmvs		92.97 55	92.26 79	95.12 21	95.54 132	87.77 22	98.67 38	96.38 122	88.04 95	93.01 80	97.45 97	79.20 94	98.60 136	93.25 90	88.76 200	98.99 33

PAPM		92.87 60	92.40 74	94.30 39	92.25 252	87.85 21	96.40 196	96.38 122	91.07 46	88.72 150	96.90 125	82.11 65	97.37 211	90.05 139	97.70 66	97.67 121

fmvsm_l_conf0.5_n_3		94.61 22	94.92 21	93.68 66	94.52 166	82.80 115	99.33 1	96.37 125	95.08 5	97.59 15	98.48 29	77.40 125	99.79 30	98.28 12	97.21 83	98.44 61

test_fmvsmconf_n		93.99 37	94.36 32	92.86 103	92.82 230	81.12 155	99.26 5	96.37 125	93.47 18	95.16 46	98.21 47	79.00 96	99.64 62	98.21 16	96.73 102	97.83 108

test12				94.25 41	98.34 46	85.55 57		96.35 127		92.36 90		80.84 71	99.22 97		98.31 49	97.98 96

MTGPA								96.33 128

MTAPA		92.45 80	92.31 77	92.86 103	97.90 61	80.85 166	92.88 323	96.33 128	87.92 98	90.20 125	98.18 49	76.71 141	99.76 36	92.57 101	98.09 53	97.96 99

reproduce_monomvs		87.80 190	87.60 176	88.40 250	96.56 98	80.26 185	95.80 233	96.32 130	91.56 39	73.60 320	88.36 297	88.53 16	96.25 265	90.47 130	67.23 367	88.67 324

ET-MVSNet_ETH3D		90.01 139	89.03 145	92.95 99	94.38 176	86.77 33	98.14 56	96.31 131	89.30 70	63.33 383	96.72 136	90.09 10	93.63 360	90.70 127	82.29 267	98.46 59

EPMVS		87.47 198	85.90 206	92.18 139	95.41 135	82.26 127	87.00 378	96.28 132	85.88 145	84.23 200	85.57 345	75.07 180	96.26 263	71.14 317	92.50 167	98.03 88

WB-MVSnew		84.08 253	83.51 246	85.80 305	91.34 279	76.69 287	95.62 241	96.27 133	81.77 248	81.81 234	92.81 231	58.23 315	94.70 337	66.66 339	87.06 221	85.99 373

CDPH-MVS		93.12 51	92.91 61	93.74 59	98.65 30	83.88 92	97.67 91	96.26 134	83.00 224	93.22 76	98.24 46	81.31 69	99.21 98	89.12 150	98.74 30	98.14 82

WR-MVS		84.32 249	82.96 252	88.41 249	89.38 323	80.32 181	96.59 181	96.25 135	83.97 197	76.63 287	90.36 271	67.53 252	94.86 332	75.82 279	70.09 339	90.06 292

fmvsm_s_conf0.1_n		92.93 57	93.16 57	92.24 134	90.52 297	81.92 132	98.42 47	96.24 136	91.17 43	96.02 37	98.35 42	75.34 175	99.74 44	97.84 29	94.58 135	95.05 228

UGNet		87.73 192	86.55 200	91.27 179	95.16 145	79.11 219	96.35 199	96.23 137	88.14 92	87.83 162	90.48 268	50.65 359	99.09 113	80.13 233	94.03 141	95.60 213
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		78.14 325	75.42 333	86.31 299	88.33 335	79.24 213	94.41 279	96.22 138	73.51 353	69.81 354	85.52 347	55.43 341	95.75 290	47.65 409	67.86 360	83.95 389

FOURS1					98.51 39	78.01 251	98.13 59	96.21 139	83.04 222	94.39 61

MP-MVS		92.61 75	92.67 67	92.42 125	98.13 56	79.73 202	97.33 122	96.20 140	85.63 148	90.53 120	97.66 84	78.14 112	99.70 55	92.12 106	98.30 50	97.85 106
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PAPR		92.74 63	92.17 83	94.45 36	98.89 20	84.87 79	97.20 129	96.20 140	87.73 104	88.40 154	98.12 54	78.71 102	99.76 36	87.99 163	96.28 108	98.74 42

SD-MVS		94.84 18	95.02 20	94.29 40	97.87 64	84.61 82	97.76 85	96.19 142	89.59 66	96.66 26	98.17 52	84.33 43	99.60 67	96.09 47	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		91.71 100	91.85 88	91.29 178	94.94 153	82.69 117	87.89 371	96.17 143	85.94 143	87.27 167	94.31 200	90.27 8	95.65 297	94.04 78	95.86 120	95.53 216

fmvsm_l_conf0.5_n		94.89 16	95.24 17	93.86 53	94.42 174	84.61 82	99.13 12	96.15 144	92.06 33	97.92 4	98.52 25	84.52 41	99.74 44	98.76 7	95.67 123	97.22 155

CHOSEN 1792x2688		91.07 118	90.21 126	93.64 68	95.18 144	83.53 102	96.26 205	96.13 145	88.92 73	84.90 192	93.10 229	72.86 208	99.62 66	88.86 152	95.67 123	97.79 112

PAPM_NR		91.46 105	90.82 110	93.37 82	98.50 40	81.81 139	95.03 268	96.13 145	84.65 175	86.10 180	97.65 88	79.24 93	99.75 41	83.20 209	96.88 95	98.56 54

CostFormer		89.08 155	88.39 159	91.15 183	93.13 219	79.15 218	88.61 363	96.11 147	83.14 219	89.58 133	86.93 321	83.83 53	96.87 240	88.22 162	85.92 234	97.42 142

mPP-MVS		91.88 95	91.82 89	92.07 144	98.38 44	78.63 231	97.29 124	96.09 148	85.12 162	88.45 153	97.66 84	75.53 165	99.68 58	89.83 140	98.02 57	97.88 102

APD-MVS		93.61 42	93.59 46	93.69 65	98.76 24	83.26 108	97.21 127	96.09 148	82.41 238	94.65 58	98.21 47	81.96 67	98.81 130	94.65 70	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			83.69 239		94.09 188	81.01 159	86.78 380	96.09 148	83.81 205	84.75 195	84.32 362	74.44 191	96.54 253	63.88 354	85.07 243

FA-MVS(test-final)		87.71 194	86.23 203	92.17 140	94.19 181	80.55 175	87.16 377	96.07 151	82.12 243	85.98 181	88.35 298	72.04 221	98.49 143	80.26 230	89.87 188	97.48 138

QAPM		86.88 204	84.51 226	93.98 49	94.04 190	85.89 45	97.19 130	96.05 152	73.62 352	75.12 312	95.62 158	62.02 290	99.74 44	70.88 318	96.06 115	96.30 197

MP-MVS-pluss		92.58 76	92.35 75	93.29 83	97.30 90	82.53 120	96.44 192	96.04 153	84.68 174	89.12 141	98.37 40	77.48 124	99.74 44	93.31 89	98.38 45	97.59 128
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.1_n_a		92.38 82	92.49 72	92.06 145	88.08 337	81.62 146	97.97 71	96.01 154	90.62 52	96.58 28	98.33 43	74.09 195	99.71 52	97.23 37	93.46 156	94.86 232

fmvsm_l_conf0.5_n_a		94.91 15	95.30 16	93.72 62	94.50 171	84.30 87	99.14 11	96.00 155	91.94 36	97.91 6	98.60 19	84.78 38	99.77 34	98.84 6	96.03 116	97.08 164

tpm2		87.35 199	86.26 202	90.62 198	92.93 227	78.67 230	88.06 370	95.99 156	79.33 294	87.40 164	86.43 332	80.28 78	96.40 257	80.23 231	85.73 238	96.79 176

SDMVSNet		87.02 201	85.61 208	91.24 180	94.14 184	83.30 107	93.88 298	95.98 157	84.30 186	79.63 256	92.01 243	58.23 315	97.68 187	90.28 138	82.02 268	92.75 264

DeepC-MVS	86.58 3	91.53 104	91.06 106	92.94 100	94.52 166	81.89 134	95.95 222	95.98 157	90.76 50	83.76 209	96.76 133	73.24 206	99.71 52	91.67 113	96.96 92	97.22 155
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.5_n_3		93.95 38	94.53 26	92.20 138	94.41 175	80.04 192	98.90 30	95.96 159	94.53 9	97.63 14	98.58 20	75.95 156	99.79 30	98.25 14	96.60 104	96.77 178

test-LLR		88.48 173	87.98 165	89.98 218	92.26 250	77.23 276	97.11 141	95.96 159	83.76 207	86.30 178	91.38 254	72.30 217	96.78 246	80.82 224	91.92 174	95.94 203

test-mter		88.95 157	88.60 155	89.98 218	92.26 250	77.23 276	97.11 141	95.96 159	85.32 155	86.30 178	91.38 254	76.37 148	96.78 246	80.82 224	91.92 174	95.94 203

DP-MVS Recon		91.72 99	90.85 109	94.34 38	99.50 1	85.00 76	98.51 45	95.96 159	80.57 266	88.08 160	97.63 90	76.84 136	99.89 7	85.67 181	94.88 130	98.13 84

reproduce-ours		92.70 69	93.02 58	91.75 159	97.45 79	77.77 263	96.16 211	95.94 163	84.12 191	92.45 86	98.43 33	80.06 83	99.24 94	95.35 60	97.18 84	98.24 75

our_new_method		92.70 69	93.02 58	91.75 159	97.45 79	77.77 263	96.16 211	95.94 163	84.12 191	92.45 86	98.43 33	80.06 83	99.24 94	95.35 60	97.18 84	98.24 75

cdsmvs_eth3d_5k		21.43 402	28.57 405	0.00 421	0.00 444	0.00 446	0.00 432	95.93 165	0.00 439	0.00 440	97.66 84	63.57 279	0.00 440	0.00 439	0.00 438	0.00 436

reproduce_model		92.53 78	92.87 62	91.50 171	97.41 83	77.14 280	96.02 218	95.91 166	83.65 211	92.45 86	98.39 37	79.75 88	99.21 98	95.27 63	96.98 91	98.14 82

fmvsm_s_conf0.5_n_5		93.57 45	93.75 41	93.01 95	92.87 229	82.73 116	98.93 29	95.90 167	90.96 49	95.61 41	98.39 37	76.57 142	99.63 64	98.32 11	96.24 109	96.68 184

fmvsm_s_conf0.5_n_2		92.97 55	93.38 53	91.73 161	94.10 187	80.64 172	98.96 27	95.89 168	94.09 13	97.05 21	98.40 36	68.92 245	99.80 26	98.53 9	94.50 137	94.74 236

hse-mvs2		88.22 182	88.21 161	88.25 256	93.54 202	73.41 321	95.41 250	95.89 168	90.39 57	92.22 93	94.22 203	74.70 185	96.66 251	93.14 92	64.37 379	94.69 241

AUN-MVS		86.25 216	85.57 209	88.26 255	93.57 201	73.38 322	95.45 248	95.88 170	83.94 199	85.47 186	94.21 204	73.70 202	96.67 250	83.54 205	64.41 378	94.73 240

TAMVS		88.48 173	87.79 169	90.56 200	91.09 285	79.18 216	96.45 191	95.88 170	83.64 212	83.12 215	93.33 224	75.94 157	95.74 293	82.40 216	88.27 210	96.75 181

PVSNet_Blended_VisFu		91.24 112	90.77 111	92.66 112	95.09 147	82.40 124	97.77 83	95.87 172	88.26 88	86.39 176	93.94 211	76.77 139	99.27 92	88.80 154	94.00 144	96.31 196

OpenMVS	79.58 14	86.09 217	83.62 243	93.50 77	90.95 287	86.71 35	97.44 111	95.83 173	75.35 337	72.64 334	95.72 153	57.42 328	99.64 62	71.41 312	95.85 121	94.13 248

CDS-MVSNet		89.50 148	88.96 148	91.14 184	91.94 269	80.93 163	97.09 145	95.81 174	84.26 189	84.72 196	94.20 205	80.31 77	95.64 298	83.37 208	88.96 198	96.85 174
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PS-MVSNAJ		94.17 32	93.52 48	96.10 9	95.65 128	92.35 2	98.21 54	95.79 175	92.42 27	96.24 33	98.18 49	71.04 232	99.17 106	96.77 43	97.39 77	96.79 176

testing3		80.74 305	81.17 280	79.44 372	91.15 283	63.48 391	97.16 135	95.76 176	80.83 259	71.36 342	93.15 228	78.22 110	87.30 407	43.19 415	79.67 279	87.55 352

SR-MVS		92.16 87	92.27 78	91.83 157	98.37 45	78.41 237	96.67 179	95.76 176	82.19 242	91.97 97	98.07 61	76.44 145	98.64 134	93.71 81	97.27 81	98.45 60

3Dnovator+	82.88 8	89.63 147	87.85 167	94.99 23	94.49 172	86.76 34	97.84 77	95.74 178	86.10 138	75.47 309	96.02 147	65.00 273	99.51 79	82.91 213	97.07 89	98.72 47

HPM-MVS		91.62 102	91.53 96	91.89 152	97.88 63	79.22 215	96.99 150	95.73 179	82.07 244	89.50 136	97.19 113	75.59 163	98.93 125	90.91 120	97.94 59	97.54 130
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ab-mvs		87.08 200	84.94 222	93.48 79	93.34 212	83.67 99	88.82 360	95.70 180	81.18 254	84.55 199	90.14 276	62.72 284	98.94 124	85.49 183	82.54 264	97.85 106

xiu_mvs_v2_base		93.92 39	93.26 54	95.91 11	95.07 149	92.02 6	98.19 55	95.68 181	92.06 33	96.01 38	98.14 53	70.83 236	98.96 120	96.74 45	96.57 105	96.76 180

CP-MVSNet		81.01 302	80.08 295	83.79 338	87.91 339	70.51 353	94.29 289	95.65 182	80.83 259	72.54 336	88.84 288	63.71 278	92.32 371	68.58 331	68.36 354	88.55 326

PatchmatchNet		86.83 206	85.12 219	91.95 150	94.12 186	82.27 126	86.55 382	95.64 183	84.59 177	82.98 218	84.99 357	77.26 127	95.96 277	68.61 330	91.34 179	97.64 124
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
API-MVS		90.18 137	88.97 147	93.80 55	98.66 28	82.95 113	97.50 107	95.63 184	75.16 340	86.31 177	97.69 82	72.49 213	99.90 5	81.26 223	96.07 114	98.56 54

balanced_conf03		94.60 24	94.30 34	95.48 16	96.45 100	88.82 14	96.33 201	95.58 185	91.12 44	95.84 39	93.87 213	83.47 55	98.37 152	97.26 36	98.81 24	99.24 23

AdaColmap		88.81 163	87.61 175	92.39 126	99.33 4	79.95 193	96.70 178	95.58 185	77.51 319	83.05 217	96.69 137	61.90 293	99.72 49	84.29 191	93.47 155	97.50 136

SCA		85.63 226	83.64 242	91.60 168	92.30 247	81.86 136	92.88 323	95.56 187	84.85 168	82.52 219	85.12 355	58.04 318	95.39 308	73.89 296	87.58 219	97.54 130

dp		84.30 250	82.31 263	90.28 208	94.24 180	77.97 252	86.57 381	95.53 188	79.94 284	80.75 242	85.16 353	71.49 228	96.39 258	63.73 355	83.36 253	96.48 189

HyFIR lowres test		89.36 150	88.60 155	91.63 167	94.91 155	80.76 169	95.60 242	95.53 188	82.56 235	84.03 202	91.24 257	78.03 113	96.81 244	87.07 174	88.41 208	97.32 149

WBMVS		87.73 192	86.79 195	90.56 200	95.61 129	85.68 51	97.63 92	95.52 190	83.77 206	78.30 269	88.44 296	86.14 32	95.78 287	82.54 215	73.15 319	90.21 285

APD-MVS_3200maxsize		91.23 113	91.35 98	90.89 191	97.89 62	76.35 293	96.30 203	95.52 190	79.82 285	91.03 114	97.88 75	74.70 185	98.54 140	92.11 107	96.89 94	97.77 113

lupinMVS		93.87 40	93.58 47	94.75 30	93.00 222	88.08 19	99.15 9	95.50 192	91.03 47	94.90 53	97.66 84	78.84 99	97.56 194	94.64 71	97.46 72	98.62 52

tt0805		81.20 299	79.06 308	87.61 270	86.50 351	72.97 331	93.66 302	95.48 193	74.11 348	76.23 297	91.99 245	41.36 395	97.40 208	77.44 261	74.78 309	92.45 267

HPM-MVS_fast		90.38 135	90.17 128	91.03 186	97.61 71	77.35 274	97.15 137	95.48 193	79.51 291	88.79 147	96.90 125	71.64 226	98.81 130	87.01 175	97.44 74	96.94 168

VPNet		84.69 242	82.92 253	90.01 216	89.01 325	83.45 104	96.71 176	95.46 195	85.71 147	79.65 255	92.18 242	56.66 334	96.01 273	83.05 212	67.84 361	90.56 279

114514_t		88.79 165	87.57 177	92.45 121	98.21 53	81.74 141	96.99 150	95.45 196	75.16 340	82.48 220	95.69 155	68.59 247	98.50 142	80.33 228	95.18 128	97.10 163

SR-MVS-dyc-post		91.29 111	91.45 97	90.80 193	97.76 67	76.03 298	96.20 209	95.44 197	80.56 267	90.72 118	97.84 76	75.76 160	98.61 135	91.99 109	96.79 99	97.75 114

RE-MVS-def			91.18 105		97.76 67	76.03 298	96.20 209	95.44 197	80.56 267	90.72 118	97.84 76	73.36 205		91.99 109	96.79 99	97.75 114

JIA-IIPM		79.00 321	77.20 320	84.40 333	89.74 314	64.06 388	75.30 418	95.44 197	62.15 399	81.90 231	59.08 422	78.92 97	95.59 302	66.51 343	85.78 237	93.54 258

RPMNet		79.85 311	75.92 331	91.64 165	90.16 304	79.75 199	79.02 410	95.44 197	58.43 415	82.27 227	72.55 413	73.03 207	98.41 151	46.10 411	86.25 229	96.75 181

MVSMamba_PlusPlus		92.37 83	91.55 95	94.83 27	95.37 137	87.69 24	95.60 242	95.42 201	74.65 345	93.95 67	92.81 231	83.11 58	97.70 186	94.49 72	98.53 35	99.11 28

DU-MVS		84.57 245	83.33 249	88.28 254	88.76 326	79.36 210	96.43 194	95.41 202	85.42 153	78.11 271	90.82 263	67.61 249	95.14 322	79.14 243	68.30 355	90.33 283

EI-MVSNet		85.80 222	85.20 215	87.59 272	91.55 274	77.41 272	95.13 262	95.36 203	80.43 272	80.33 248	94.71 192	73.72 200	95.97 274	76.96 266	78.64 289	89.39 298

MVSTER		89.25 154	88.92 150	90.24 209	95.98 115	84.66 81	96.79 170	95.36 203	87.19 121	80.33 248	90.61 267	90.02 11	95.97 274	85.38 184	78.64 289	90.09 290

CPTT-MVS		89.72 144	89.87 138	89.29 233	98.33 47	73.30 324	97.70 89	95.35 205	75.68 336	87.40 164	97.44 100	70.43 238	98.25 157	89.56 146	96.90 93	96.33 195

EIA-MVS		91.73 97	92.05 86	90.78 195	94.52 166	76.40 292	98.06 65	95.34 206	89.19 71	88.90 145	97.28 109	77.56 122	97.73 185	90.77 124	96.86 97	98.20 77

tpmvs		83.04 271	80.77 284	89.84 224	95.43 134	77.96 253	85.59 388	95.32 207	75.31 339	76.27 296	83.70 368	73.89 197	97.41 207	59.53 370	81.93 270	94.14 247

PS-CasMVS		80.27 309	79.18 305	83.52 344	87.56 343	69.88 358	94.08 292	95.29 208	80.27 277	72.08 338	88.51 295	59.22 309	92.23 373	67.49 333	68.15 357	88.45 332

TSAR-MVS + GP.		94.35 28	94.50 27	93.89 52	97.38 88	83.04 112	98.10 61	95.29 208	91.57 38	93.81 68	97.45 97	86.64 28	99.43 84	96.28 46	94.01 143	99.20 25

tpmrst		88.36 177	87.38 183	91.31 176	94.36 177	79.92 194	87.32 375	95.26 210	85.32 155	88.34 155	86.13 338	80.60 75	96.70 248	83.78 197	85.34 242	97.30 152

SSC-MVS3.2		81.06 300	79.49 304	85.75 308	89.78 310	73.00 330	94.40 282	95.23 211	83.76 207	76.61 289	87.82 307	49.48 366	94.88 330	66.80 337	71.56 326	89.38 300

ETV-MVS		92.72 66	92.87 62	92.28 133	94.54 165	81.89 134	97.98 69	95.21 212	89.77 65	93.11 78	96.83 129	77.23 131	97.50 202	95.74 53	95.38 127	97.44 141

NR-MVSNet		83.35 263	81.52 276	88.84 241	88.76 326	81.31 151	94.45 278	95.16 213	84.65 175	67.81 360	90.82 263	70.36 239	94.87 331	74.75 287	66.89 371	90.33 283

test_fmvsmconf0.1_n		93.08 53	93.22 56	92.65 113	88.45 332	80.81 167	99.00 25	95.11 214	93.21 20	94.00 66	97.91 72	76.84 136	99.59 68	97.91 25	96.55 106	97.54 130

jason		92.73 64	92.23 80	94.21 44	90.50 298	87.30 30	98.65 39	95.09 215	90.61 53	92.76 85	97.13 115	75.28 176	97.30 214	93.32 88	96.75 101	98.02 89
jason: jason.
tpm cat1		83.63 260	81.38 277	90.39 205	93.53 207	78.19 248	85.56 389	95.09 215	70.78 372	78.51 266	83.28 372	74.80 184	97.03 228	66.77 338	84.05 248	95.95 202

cascas		86.50 210	84.48 228	92.55 119	92.64 238	85.95 42	97.04 149	95.07 217	75.32 338	80.50 244	91.02 260	54.33 349	97.98 171	86.79 176	87.62 217	93.71 256

GDP-MVS		92.85 61	92.55 71	93.75 58	92.82 230	85.76 47	97.63 92	95.05 218	88.34 86	93.15 77	97.10 118	86.92 26	98.01 169	87.95 164	94.00 144	97.47 139

CVMVSNet		84.83 240	85.57 209	82.63 351	91.55 274	60.38 402	95.13 262	95.03 219	80.60 265	82.10 229	94.71 192	66.40 263	90.19 393	74.30 293	90.32 186	97.31 151

test0.0.03 1		82.79 275	82.48 261	83.74 340	86.81 349	72.22 334	96.52 185	95.03 219	83.76 207	73.00 330	93.20 225	72.30 217	88.88 396	64.15 353	77.52 298	90.12 288

PMMVS		89.46 149	89.92 136	88.06 260	94.64 160	69.57 362	96.22 207	94.95 221	87.27 117	91.37 107	96.54 139	65.88 265	97.39 209	88.54 156	93.89 147	97.23 154

CS-MVS		92.73 64	93.48 50	90.48 203	96.27 104	75.93 303	98.55 43	94.93 222	89.32 69	94.54 60	97.67 83	78.91 98	97.02 229	93.80 79	97.32 80	98.49 57

Anonymous20240529		83.15 268	80.60 288	90.80 193	95.74 125	78.27 241	96.81 169	94.92 223	60.10 410	81.89 232	92.54 235	45.82 380	98.82 129	79.25 242	78.32 295	95.31 222

mvs_anonymous		88.68 166	87.62 174	91.86 154	94.80 158	81.69 144	93.53 307	94.92 223	82.03 245	78.87 264	90.43 270	75.77 159	95.34 311	85.04 186	93.16 160	98.55 56

CLD-MVS		87.97 187	87.48 180	89.44 231	92.16 257	80.54 178	98.14 56	94.92 223	91.41 40	79.43 258	95.40 165	62.34 286	97.27 217	90.60 128	82.90 259	90.50 280
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		90.54 129	89.54 140	93.55 74	92.31 244	87.58 26	96.99 150	94.87 226	87.23 118	93.27 73	97.56 93	57.43 325	98.32 154	92.72 98	93.46 156	94.74 236

xiu_mvs_v1_base		90.54 129	89.54 140	93.55 74	92.31 244	87.58 26	96.99 150	94.87 226	87.23 118	93.27 73	97.56 93	57.43 325	98.32 154	92.72 98	93.46 156	94.74 236

xiu_mvs_v1_base_debi		90.54 129	89.54 140	93.55 74	92.31 244	87.58 26	96.99 150	94.87 226	87.23 118	93.27 73	97.56 93	57.43 325	98.32 154	92.72 98	93.46 156	94.74 236

GA-MVS		85.79 223	84.04 237	91.02 187	89.47 321	80.27 184	96.90 163	94.84 229	85.57 149	80.88 240	89.08 284	56.56 335	96.47 256	77.72 254	85.35 241	96.34 193

TranMVSNet+NR-MVSNet		83.24 267	81.71 272	87.83 264	87.71 341	78.81 227	96.13 216	94.82 230	84.52 178	76.18 299	90.78 265	64.07 277	94.60 340	74.60 291	66.59 373	90.09 290

HQP3-MVS								94.80 231							83.01 256

HQP-MVS		87.91 189	87.55 178	88.98 239	92.08 261	78.48 233	97.63 92	94.80 231	90.52 54	82.30 223	94.56 196	65.40 269	97.32 212	87.67 168	83.01 256	91.13 273

TAPA-MVS	81.61 12	85.02 237	83.67 240	89.06 236	96.79 96	73.27 327	95.92 224	94.79 233	74.81 343	80.47 245	96.83 129	71.07 231	98.19 160	49.82 404	92.57 165	95.71 210
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PEN-MVS		79.47 317	78.26 313	83.08 347	86.36 353	68.58 366	93.85 300	94.77 234	79.76 286	71.37 341	88.55 292	59.79 301	92.46 369	64.50 351	65.40 375	88.19 337

SPE-MVS-test		92.98 54	93.67 44	90.90 190	96.52 99	76.87 282	98.68 37	94.73 235	90.36 59	94.84 55	97.89 74	77.94 114	97.15 225	94.28 76	97.80 64	98.70 48

HQP_MVS		87.50 197	87.09 190	88.74 244	91.86 270	77.96 253	97.18 131	94.69 236	89.89 63	81.33 236	94.15 206	64.77 274	97.30 214	87.08 172	82.82 260	90.96 275

plane_prior5								94.69 236					97.30 214	87.08 172	82.82 260	90.96 275

tpm		85.55 228	84.47 229	88.80 243	90.19 303	75.39 308	88.79 361	94.69 236	84.83 169	83.96 205	85.21 351	78.22 110	94.68 339	76.32 274	78.02 297	96.34 193

FMVSNet3		84.71 241	82.71 258	90.70 197	94.55 164	87.71 23	95.92 224	94.67 239	81.73 249	75.82 304	88.08 303	66.99 257	94.47 343	71.23 314	75.38 306	89.91 294

UA-Net		88.92 159	88.48 158	90.24 209	94.06 189	77.18 278	93.04 319	94.66 240	87.39 113	91.09 112	93.89 212	74.92 181	98.18 161	75.83 278	91.43 178	95.35 221

LFMVS		89.27 153	87.64 172	94.16 48	97.16 92	85.52 58	97.18 131	94.66 240	79.17 299	89.63 132	96.57 138	55.35 342	98.22 158	89.52 147	89.54 190	98.74 42

MVS_Test		90.29 136	89.18 144	93.62 70	95.23 141	84.93 77	94.41 279	94.66 240	84.31 184	90.37 124	91.02 260	75.13 178	97.82 181	83.11 211	94.42 138	98.12 85

sasdasda		92.27 84	91.22 101	95.41 17	95.80 123	88.31 15	97.09 145	94.64 243	88.49 81	92.99 81	97.31 104	72.68 210	98.57 138	93.38 86	88.58 203	99.36 16

canonicalmvs		92.27 84	91.22 101	95.41 17	95.80 123	88.31 15	97.09 145	94.64 243	88.49 81	92.99 81	97.31 104	72.68 210	98.57 138	93.38 86	88.58 203	99.36 16

VDDNet		86.44 211	84.51 226	92.22 136	91.56 273	81.83 137	97.10 144	94.64 243	69.50 379	87.84 161	95.19 175	48.01 370	97.92 177	89.82 141	86.92 222	96.89 172

baseline1		88.85 162	87.49 179	92.93 101	95.21 143	86.85 32	95.47 247	94.61 246	87.29 115	83.11 216	94.99 186	80.70 73	96.89 238	82.28 217	73.72 313	95.05 228

PatchT		79.75 312	76.85 324	88.42 248	89.55 319	75.49 307	77.37 414	94.61 246	63.07 395	82.46 221	73.32 410	75.52 166	93.41 364	51.36 398	84.43 246	96.36 191

MS-PatchMatch		83.05 270	81.82 271	86.72 294	89.64 316	79.10 220	94.88 271	94.59 248	79.70 288	70.67 348	89.65 280	50.43 361	96.82 243	70.82 321	95.99 119	84.25 386

casdiffmvs_mvg		91.13 115	90.45 119	93.17 89	92.99 225	83.58 101	97.46 110	94.56 249	87.69 105	87.19 169	94.98 187	74.50 190	97.60 191	91.88 112	92.79 163	98.34 65
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		90.76 125	90.10 129	92.74 108	92.90 228	82.56 119	94.60 276	94.56 249	87.69 105	89.06 143	95.67 156	73.76 199	97.51 201	90.43 133	92.23 172	98.16 80

OMC-MVS		88.80 164	88.16 163	90.72 196	95.30 139	77.92 256	94.81 273	94.51 251	86.80 129	84.97 191	96.85 128	67.53 252	98.60 136	85.08 185	87.62 217	95.63 211

MGCFI-Net		91.95 91	91.03 107	94.72 31	95.68 127	86.38 36	96.93 160	94.48 252	88.25 89	92.78 84	97.24 110	72.34 215	98.46 146	93.13 94	88.43 207	99.32 19

MVSFormer		91.36 109	90.57 115	93.73 61	93.00 222	88.08 19	94.80 274	94.48 252	80.74 262	94.90 53	97.13 115	78.84 99	95.10 325	83.77 198	97.46 72	98.02 89

test_djsdf		83.00 273	82.45 262	84.64 327	84.07 383	69.78 359	94.80 274	94.48 252	80.74 262	75.41 310	87.70 308	61.32 297	95.10 325	83.77 198	79.76 276	89.04 314

casdiffmvs		90.95 122	90.39 120	92.63 115	92.82 230	82.53 120	96.83 166	94.47 255	87.69 105	88.47 152	95.56 161	74.04 196	97.54 198	90.90 121	92.74 164	97.83 108
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	86.77 208	85.00 221	92.08 143	92.06 264	83.07 111	92.14 332	94.47 255	79.63 289	76.90 284	94.78 191	71.15 230	99.20 103	72.87 303	91.05 181	93.98 251
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
RRT-MVS		89.67 145	88.67 153	92.67 111	94.44 173	81.08 157	94.34 283	94.45 257	86.05 140	85.79 182	92.39 237	63.39 281	98.16 162	93.22 91	93.95 146	98.76 41

VDD-MVS		88.28 180	87.02 192	92.06 145	95.09 147	80.18 189	97.55 102	94.45 257	83.09 220	89.10 142	95.92 150	47.97 371	98.49 143	93.08 96	86.91 223	97.52 135

mvsmamba		90.53 132	90.08 130	91.88 153	94.81 157	80.93 163	93.94 296	94.45 257	88.24 90	87.02 172	92.35 238	68.04 248	95.80 285	94.86 66	97.03 90	98.92 34

test_cas_vis1_n_1920		89.90 141	90.02 132	89.54 230	90.14 306	74.63 313	98.71 36	94.43 260	93.04 22	92.40 89	96.35 141	53.41 352	99.08 114	95.59 56	96.16 111	94.90 230

PLC	83.97 7	88.00 186	87.38 183	89.83 225	98.02 59	76.46 289	97.16 135	94.43 260	79.26 298	81.98 230	96.28 142	69.36 243	99.27 92	77.71 255	92.25 171	93.77 255
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EC-MVSNet		91.73 97	92.11 84	90.58 199	93.54 202	77.77 263	98.07 64	94.40 262	87.44 111	92.99 81	97.11 117	74.59 189	96.87 240	93.75 80	97.08 88	97.11 162

sd_testset		84.62 243	83.11 251	89.17 234	94.14 184	77.78 262	91.54 342	94.38 263	84.30 186	79.63 256	92.01 243	52.28 354	96.98 232	77.67 256	82.02 268	92.75 264

FMVSNet2		82.79 275	80.44 290	89.83 225	92.66 235	85.43 59	95.42 249	94.35 264	79.06 302	74.46 316	87.28 313	56.38 337	94.31 346	69.72 326	74.68 310	89.76 295

test_vis1_n_1920		89.95 140	90.59 114	88.03 262	92.36 243	68.98 365	99.12 13	94.34 265	93.86 15	93.64 71	97.01 123	51.54 356	99.59 68	96.76 44	96.71 103	95.53 216

fmvsm_s_conf0.1_n_2		92.26 86	92.48 73	91.60 168	92.29 248	80.55 175	98.73 35	94.33 266	93.80 16	96.18 34	98.11 55	66.93 258	99.75 41	98.19 17	93.74 150	94.50 243

nrg030		86.79 207	85.43 211	90.87 192	88.76 326	85.34 61	97.06 148	94.33 266	84.31 184	80.45 246	91.98 246	72.36 214	96.36 260	88.48 159	71.13 328	90.93 277

ACMM	80.70 13	83.72 259	82.85 256	86.31 299	91.19 281	72.12 338	95.88 227	94.29 268	80.44 270	77.02 282	91.96 247	55.24 343	97.14 226	79.30 241	80.38 275	89.67 296
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XXY-MVS		83.84 256	82.00 268	89.35 232	87.13 346	81.38 149	95.72 235	94.26 269	80.15 279	75.92 303	90.63 266	61.96 292	96.52 254	78.98 245	73.28 318	90.14 287

Syy-MVS		77.97 329	78.05 314	77.74 380	92.13 258	56.85 409	93.97 294	94.23 270	82.43 236	73.39 323	93.57 221	57.95 321	87.86 402	32.40 423	82.34 265	88.51 327

myMVS_eth3d		81.93 288	82.18 264	81.18 362	92.13 258	67.18 372	93.97 294	94.23 270	82.43 236	73.39 323	93.57 221	76.98 134	87.86 402	50.53 402	82.34 265	88.51 327

cl22		85.11 236	84.17 234	87.92 263	95.06 151	78.82 225	95.51 245	94.22 272	79.74 287	76.77 285	87.92 305	75.96 155	95.68 294	79.93 235	72.42 321	89.27 306

OPM-MVS		85.84 221	85.10 220	88.06 260	88.34 334	77.83 260	95.72 235	94.20 273	87.89 101	80.45 246	94.05 208	58.57 312	97.26 218	83.88 195	82.76 262	89.09 311
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet (Re-imp)		88.88 161	88.87 152	88.91 240	93.89 193	74.43 316	96.93 160	94.19 274	84.39 182	83.22 214	95.67 156	78.24 109	94.70 337	78.88 246	94.40 139	97.61 127

Anonymous20231211		79.72 313	77.19 321	87.33 280	95.59 131	77.16 279	95.18 261	94.18 275	59.31 413	72.57 335	86.20 337	47.89 373	95.66 295	74.53 292	69.24 347	89.18 308

PS-MVSNAJss		84.91 239	84.30 231	86.74 290	85.89 363	74.40 317	94.95 269	94.16 276	83.93 200	76.45 291	90.11 277	71.04 232	95.77 288	83.16 210	79.02 286	90.06 292

LPG-MVS_test		84.20 251	83.49 247	86.33 296	90.88 288	73.06 328	95.28 252	94.13 277	82.20 240	76.31 293	93.20 225	54.83 347	96.95 234	83.72 200	80.83 273	88.98 317

LGP-MVS_train				86.33 296	90.88 288	73.06 328		94.13 277	82.20 240	76.31 293	93.20 225	54.83 347	96.95 234	83.72 200	80.83 273	88.98 317

V42		83.04 271	81.53 275	87.57 274	86.27 356	79.09 221	95.87 228	94.11 279	80.35 274	77.22 280	86.79 324	65.32 271	96.02 272	77.74 253	70.14 335	87.61 348

XVG-OURS-SEG-HR		85.74 224	85.16 218	87.49 278	90.22 302	71.45 348	91.29 343	94.09 280	81.37 252	83.90 207	95.22 172	60.30 300	97.53 200	85.58 182	84.42 247	93.50 259

XVG-OURS		85.18 235	84.38 230	87.59 272	90.42 300	71.73 345	91.06 346	94.07 281	82.00 246	83.29 213	95.08 182	56.42 336	97.55 196	83.70 202	83.42 252	93.49 260

miper_enhance_ethall		85.95 220	85.20 215	88.19 259	94.85 156	79.76 198	96.00 219	94.06 282	82.98 225	77.74 275	88.76 289	79.42 89	95.46 307	80.58 226	72.42 321	89.36 304

v2v482		83.46 262	81.86 270	88.25 256	86.19 357	79.65 204	96.34 200	94.02 283	81.56 251	77.32 278	88.23 300	65.62 266	96.03 271	77.77 252	69.72 343	89.09 311

jajsoiax		82.12 286	81.15 281	85.03 321	84.19 381	70.70 352	94.22 290	93.95 284	83.07 221	73.48 322	89.75 279	49.66 365	95.37 310	82.24 218	79.76 276	89.02 315

test_fmvsmconf0.01_n		91.08 117	90.68 113	92.29 132	82.43 391	80.12 190	97.94 72	93.93 285	92.07 32	91.97 97	97.60 91	67.56 251	99.53 76	97.09 39	95.56 126	97.21 157

v1144		82.90 274	81.27 279	87.78 266	86.29 355	79.07 222	96.14 214	93.93 285	80.05 281	77.38 276	86.80 323	65.50 267	95.93 279	75.21 284	70.13 336	88.33 335

KD-MVS_2432*1600		77.63 332	74.92 337	85.77 306	90.86 291	79.44 207	88.08 368	93.92 287	76.26 332	67.05 364	82.78 374	72.15 219	91.92 376	61.53 362	41.62 423	85.94 374

miper_refine_blended		77.63 332	74.92 337	85.77 306	90.86 291	79.44 207	88.08 368	93.92 287	76.26 332	67.05 364	82.78 374	72.15 219	91.92 376	61.53 362	41.62 423	85.94 374

test_fmvsmvis_n_1920		92.12 88	92.10 85	92.17 140	90.87 290	81.04 158	98.34 50	93.90 289	92.71 24	87.24 168	97.90 73	74.83 183	99.72 49	96.96 41	96.20 110	95.76 209

UnsupCasMVSNet_eth		73.25 357	70.57 362	81.30 360	77.53 406	66.33 379	87.24 376	93.89 290	80.38 273	57.90 405	81.59 379	42.91 390	90.56 390	65.18 349	48.51 411	87.01 359

v7n		79.32 319	77.34 319	85.28 317	84.05 384	72.89 333	93.38 309	93.87 291	75.02 342	70.68 347	84.37 361	59.58 304	95.62 300	67.60 332	67.50 364	87.32 356

dcpmvs_2		93.10 52	93.46 51	92.02 148	97.77 65	79.73 202	94.82 272	93.86 292	86.91 125	91.33 108	96.76 133	85.20 35	98.06 165	96.90 42	97.60 69	98.27 73

Vis-MVSNet		88.67 167	87.82 168	91.24 180	92.68 234	78.82 225	96.95 158	93.85 293	87.55 108	87.07 171	95.13 179	63.43 280	97.21 219	77.58 258	96.15 112	97.70 119
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v148		82.41 283	80.89 282	86.99 288	86.18 358	76.81 284	96.27 204	93.82 294	80.49 269	75.28 311	86.11 339	67.32 255	95.75 290	75.48 282	67.03 370	88.42 333

BH-w/o		88.24 181	87.47 181	90.54 202	95.03 152	78.54 232	97.41 116	93.82 294	84.08 193	78.23 270	94.51 198	69.34 244	97.21 219	80.21 232	94.58 135	95.87 205

TR-MVS		86.30 214	84.93 223	90.42 204	94.63 161	77.58 269	96.57 182	93.82 294	80.30 275	82.42 222	95.16 177	58.74 311	97.55 196	74.88 286	87.82 215	96.13 200

v1192		82.31 284	80.55 289	87.60 271	85.94 361	78.47 236	95.85 230	93.80 297	79.33 294	76.97 283	86.51 327	63.33 282	95.87 281	73.11 302	70.13 336	88.46 331

ACMP	81.66 11	84.00 254	83.22 250	86.33 296	91.53 276	72.95 332	95.91 226	93.79 298	83.70 210	73.79 319	92.22 240	54.31 350	96.89 238	83.98 194	79.74 278	89.16 309
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v144192		82.43 280	80.73 285	87.54 275	85.81 364	78.22 243	95.98 220	93.78 299	79.09 301	77.11 281	86.49 328	64.66 276	95.91 280	74.20 294	69.42 344	88.49 329

mvs_tets		81.74 290	80.71 286	84.84 322	84.22 380	70.29 355	93.91 297	93.78 299	82.77 230	73.37 325	89.46 282	47.36 376	95.31 314	81.99 219	79.55 282	88.92 321

F-COLMAP		84.50 247	83.44 248	87.67 268	95.22 142	72.22 334	95.95 222	93.78 299	75.74 335	76.30 295	95.18 176	59.50 305	98.45 148	72.67 305	86.59 226	92.35 270

UniMVSNet_ETH3D		80.86 304	78.75 310	87.22 285	86.31 354	72.02 339	91.95 333	93.76 302	73.51 353	75.06 313	90.16 275	43.04 389	95.66 295	76.37 273	78.55 292	93.98 251

Fast-Effi-MVS+		87.93 188	86.94 194	90.92 189	94.04 190	79.16 217	98.26 52	93.72 303	81.29 253	83.94 206	92.90 230	69.83 242	96.68 249	76.70 268	91.74 176	96.93 169

v1921920		82.02 287	80.23 293	87.41 279	85.62 365	77.92 256	95.79 234	93.69 304	78.86 305	76.67 286	86.44 330	62.50 285	95.83 283	72.69 304	69.77 342	88.47 330

DTE-MVSNet		78.37 323	77.06 322	82.32 355	85.22 372	67.17 375	93.40 308	93.66 305	78.71 307	70.53 349	88.29 299	59.06 310	92.23 373	61.38 365	63.28 384	87.56 350

v8		81.88 289	80.06 297	87.32 281	86.63 350	79.04 223	94.41 279	93.65 306	78.77 306	73.19 329	85.57 345	66.87 259	95.81 284	73.84 298	67.61 363	87.11 357

diffmvs		91.17 114	90.74 112	92.44 123	93.11 221	82.50 122	96.25 206	93.62 307	87.79 102	90.40 123	95.93 148	73.44 204	97.42 206	93.62 83	92.55 166	97.41 143
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		81.26 297	78.36 311	89.96 220	93.78 195	79.78 197	79.48 406	93.60 308	73.09 358	80.14 250	79.99 390	62.15 288	95.24 317	59.49 371	83.52 250	94.85 233

PatchMatch-RL		85.00 238	83.66 241	89.02 238	95.86 120	74.55 315	92.49 327	93.60 308	79.30 296	79.29 260	91.47 252	58.53 313	98.45 148	70.22 323	92.17 173	94.07 250

anonymousdsp		80.98 303	79.97 298	84.01 335	81.73 393	70.44 354	92.49 327	93.58 310	77.10 326	72.98 331	86.31 334	57.58 324	94.90 329	79.32 240	78.63 291	86.69 362

CL-MVSNet_self_test		75.81 344	74.14 346	80.83 365	78.33 404	67.79 369	94.22 290	93.52 311	77.28 323	69.82 353	81.54 381	61.47 296	89.22 395	57.59 379	53.51 401	85.48 378

miper_ehance_all_eth		84.57 245	83.60 244	87.50 276	92.64 238	78.25 242	95.40 251	93.47 312	79.28 297	76.41 292	87.64 309	76.53 143	95.24 317	78.58 248	72.42 321	89.01 316

kuosan		73.55 354	72.39 355	77.01 383	89.68 315	66.72 378	85.24 392	93.44 313	67.76 383	60.04 399	83.40 371	71.90 222	84.25 414	45.34 412	54.75 396	80.06 409

v1240		81.70 291	79.83 301	87.30 283	85.50 366	77.70 268	95.48 246	93.44 313	78.46 310	76.53 290	86.44 330	60.85 298	95.84 282	71.59 311	70.17 334	88.35 334

v10		81.43 295	79.53 303	87.11 286	86.38 352	78.87 224	94.31 285	93.43 315	77.88 314	73.24 328	85.26 349	65.44 268	95.75 290	72.14 308	67.71 362	86.72 361

IterMVS-LS		83.93 255	82.80 257	87.31 282	91.46 277	77.39 273	95.66 238	93.43 315	80.44 270	75.51 308	87.26 315	73.72 200	95.16 321	76.99 264	70.72 332	89.39 298
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		82.42 281	80.43 291	88.39 251	92.66 235	81.95 129	94.30 286	93.38 317	79.06 302	75.82 304	85.66 341	56.38 337	93.84 355	71.23 314	75.38 306	89.38 300

test1		82.42 281	80.43 291	88.39 251	92.66 235	81.95 129	94.30 286	93.38 317	79.06 302	75.82 304	85.66 341	56.38 337	93.84 355	71.23 314	75.38 306	89.38 300

FMVSNet1		79.50 316	76.54 327	88.39 251	88.47 331	81.95 129	94.30 286	93.38 317	73.14 357	72.04 339	85.66 341	43.86 383	93.84 355	65.48 347	72.53 320	89.38 300

BH-untuned		86.95 203	85.94 205	89.99 217	94.52 166	77.46 271	96.78 171	93.37 320	81.80 247	76.62 288	93.81 217	66.64 261	97.02 229	76.06 275	93.88 148	95.48 218

Effi-MVS+-dtu		84.61 244	84.90 224	83.72 341	91.96 267	63.14 393	94.95 269	93.34 321	85.57 149	79.79 254	87.12 318	61.99 291	95.61 301	83.55 204	85.83 236	92.41 268

CMPMVS	54.94 21	75.71 346	74.56 341	79.17 374	79.69 399	55.98 411	89.59 354	93.30 322	60.28 408	53.85 412	89.07 285	47.68 375	96.33 261	76.55 269	81.02 271	85.22 379
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
cl____		83.27 265	82.12 265	86.74 290	92.20 253	75.95 302	95.11 264	93.27 323	78.44 311	74.82 314	87.02 320	74.19 193	95.19 319	74.67 289	69.32 345	89.09 311

DIV-MVS_self_test		83.27 265	82.12 265	86.74 290	92.19 254	75.92 304	95.11 264	93.26 324	78.44 311	74.81 315	87.08 319	74.19 193	95.19 319	74.66 290	69.30 346	89.11 310

dmvs_re		84.10 252	82.90 254	87.70 267	91.41 278	73.28 325	90.59 349	93.19 325	85.02 164	77.96 274	93.68 218	57.92 323	96.18 268	75.50 281	80.87 272	93.63 257

miper_lstm_enhance		81.66 293	80.66 287	84.67 326	91.19 281	71.97 341	91.94 334	93.19 325	77.86 315	72.27 337	85.26 349	73.46 203	93.42 363	73.71 299	67.05 369	88.61 325

dongtai		69.47 372	68.98 371	70.93 394	86.87 348	58.45 407	88.19 366	93.18 327	63.98 394	56.04 408	80.17 389	70.97 235	79.24 421	33.46 422	47.94 413	75.09 415

eth_miper_zixun_eth		83.12 269	82.01 267	86.47 295	91.85 272	74.80 311	94.33 284	93.18 327	79.11 300	75.74 307	87.25 316	72.71 209	95.32 313	76.78 267	67.13 368	89.27 306

pmmvs4		82.54 279	80.79 283	87.79 265	86.11 359	80.49 180	93.55 306	93.18 327	77.29 322	73.35 326	89.40 283	65.26 272	95.05 328	75.32 283	73.61 314	87.83 343

XVG-ACMP-BASELINE		79.38 318	77.90 316	83.81 337	84.98 374	67.14 376	89.03 359	93.18 327	80.26 278	72.87 332	88.15 302	38.55 401	96.26 263	76.05 276	78.05 296	88.02 340

CANet_DTU		90.98 120	90.04 131	93.83 54	94.76 159	86.23 38	96.32 202	93.12 331	93.11 21	93.71 69	96.82 131	63.08 283	99.48 81	84.29 191	95.12 129	95.77 208

IS-MVSNet		88.67 167	88.16 163	90.20 211	93.61 199	76.86 283	96.77 173	93.07 332	84.02 195	83.62 210	95.60 159	74.69 188	96.24 266	78.43 250	93.66 153	97.49 137

c3_l		83.80 257	82.65 259	87.25 284	92.10 260	77.74 267	95.25 255	93.04 333	78.58 308	76.01 300	87.21 317	75.25 177	95.11 324	77.54 259	68.89 349	88.91 322

mamv4		85.50 229	86.76 196	81.72 359	93.23 213	54.93 416	89.95 353	92.94 334	69.96 376	79.00 261	92.20 241	80.69 74	94.22 348	92.06 108	90.77 183	96.01 201

UnsupCasMVSNet_bld		68.60 377	64.50 381	80.92 364	74.63 417	67.80 368	83.97 397	92.94 334	65.12 392	54.63 411	68.23 418	35.97 407	92.17 375	60.13 369	44.83 418	82.78 393

MVP-Stereo		82.65 278	81.67 273	85.59 313	86.10 360	78.29 240	93.33 311	92.82 336	77.75 316	69.17 358	87.98 304	59.28 308	95.76 289	71.77 309	96.88 95	82.73 394
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Effi-MVS+		90.70 126	89.90 137	93.09 92	93.61 199	83.48 103	95.20 258	92.79 337	83.22 217	91.82 100	95.70 154	71.82 223	97.48 204	91.25 116	93.67 152	98.32 67

EU-MVSNet		76.92 339	76.95 323	76.83 385	84.10 382	54.73 417	91.77 337	92.71 338	72.74 361	69.57 355	88.69 290	58.03 320	87.43 406	64.91 350	70.00 340	88.33 335

pm-mvs1		80.05 310	78.02 315	86.15 301	85.42 367	75.81 305	95.11 264	92.69 339	77.13 324	70.36 350	87.43 311	58.44 314	95.27 316	71.36 313	64.25 380	87.36 355

1112_ss		88.60 170	87.47 181	92.00 149	93.21 214	80.97 161	96.47 189	92.46 340	83.64 212	80.86 241	97.30 107	80.24 79	97.62 190	77.60 257	85.49 239	97.40 145

test_fmvs1		87.79 191	88.52 157	85.62 312	92.98 226	64.31 385	97.88 75	92.42 341	87.95 97	92.24 92	95.82 151	47.94 372	98.44 150	95.31 62	94.09 140	94.09 249

Test_1112_low_res		88.03 185	86.73 197	91.94 151	93.15 217	80.88 165	96.44 192	92.41 342	83.59 214	80.74 243	91.16 258	80.18 80	97.59 192	77.48 260	85.40 240	97.36 148

test_fmvs1_n		86.34 213	86.72 198	85.17 319	87.54 344	63.64 390	96.91 162	92.37 343	87.49 110	91.33 108	95.58 160	40.81 399	98.46 146	95.00 65	93.49 154	93.41 263

BH-RMVSNet		86.84 205	85.28 214	91.49 172	95.35 138	80.26 185	96.95 158	92.21 344	82.86 228	81.77 235	95.46 164	59.34 307	97.64 189	69.79 325	93.81 149	96.57 187

GeoE		86.36 212	85.20 215	89.83 225	93.17 216	76.13 295	97.53 103	92.11 345	79.58 290	80.99 239	94.01 209	66.60 262	96.17 269	73.48 300	89.30 192	97.20 159

LS3D		82.22 285	79.94 299	89.06 236	97.43 82	74.06 320	93.20 317	92.05 346	61.90 400	73.33 327	95.21 173	59.35 306	99.21 98	54.54 391	92.48 168	93.90 253

EG-PatchMatch MVS		74.92 348	72.02 356	83.62 342	83.76 388	73.28 325	93.62 304	92.04 347	68.57 382	58.88 401	83.80 367	31.87 415	95.57 304	56.97 383	78.67 288	82.00 402

IterMVS		80.67 306	79.16 306	85.20 318	89.79 309	76.08 296	92.97 321	91.86 348	80.28 276	71.20 344	85.14 354	57.93 322	91.34 383	72.52 306	70.74 331	88.18 338
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MIMVSNet		79.18 320	75.99 330	88.72 245	87.37 345	80.66 171	79.96 404	91.82 349	77.38 321	74.33 317	81.87 378	41.78 392	90.74 389	66.36 345	83.10 255	94.76 235

IterMVS-SCA-FT		80.51 308	79.10 307	84.73 324	89.63 317	74.66 312	92.98 320	91.81 350	80.05 281	71.06 346	85.18 352	58.04 318	91.40 382	72.48 307	70.70 333	88.12 339

our_test_3		77.90 330	75.37 334	85.48 315	85.39 368	76.74 285	93.63 303	91.67 351	73.39 356	65.72 373	84.65 360	58.20 317	93.13 366	57.82 377	67.87 359	86.57 364

pmmvs5		81.34 296	79.54 302	86.73 293	85.02 373	76.91 281	96.22 207	91.65 352	77.65 317	73.55 321	88.61 291	55.70 340	94.43 344	74.12 295	73.35 317	88.86 323

ACMH	75.40 17	77.99 327	74.96 335	87.10 287	90.67 295	76.41 291	93.19 318	91.64 353	72.47 364	63.44 382	87.61 310	43.34 386	97.16 222	58.34 375	73.94 312	87.72 344
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis1_n		85.60 227	85.70 207	85.33 316	84.79 375	64.98 383	96.83 166	91.61 354	87.36 114	91.00 115	94.84 190	36.14 406	97.18 221	95.66 54	93.03 161	93.82 254

MonoMVSNet		85.68 225	84.22 233	90.03 215	88.43 333	77.83 260	92.95 322	91.46 355	87.28 116	78.11 271	85.96 340	66.31 264	94.81 334	90.71 126	76.81 300	97.46 140

Fast-Effi-MVS+-dtu		83.33 264	82.60 260	85.50 314	89.55 319	69.38 363	96.09 217	91.38 356	82.30 239	75.96 302	91.41 253	56.71 332	95.58 303	75.13 285	84.90 244	91.54 271

YYNet1		73.53 356	70.43 363	82.85 349	84.52 378	71.73 345	91.69 339	91.37 357	67.63 384	46.79 416	81.21 383	55.04 345	90.43 391	55.93 386	59.70 391	86.38 366

ppachtmachnet_test		77.19 336	74.22 344	86.13 302	85.39 368	78.22 243	93.98 293	91.36 358	71.74 368	67.11 363	84.87 358	56.67 333	93.37 365	52.21 396	64.59 377	86.80 360

Anonymous202405211		84.41 248	81.93 269	91.85 156	96.78 97	78.41 237	97.44 111	91.34 359	70.29 374	84.06 201	94.26 202	41.09 396	98.96 120	79.46 238	82.65 263	98.17 79

MDA-MVSNet_test_wron		73.54 355	70.43 363	82.86 348	84.55 376	71.85 342	91.74 338	91.32 360	67.63 384	46.73 417	81.09 384	55.11 344	90.42 392	55.91 387	59.76 390	86.31 367

CR-MVSNet		83.53 261	81.36 278	90.06 214	90.16 304	79.75 199	79.02 410	91.12 361	84.24 190	82.27 227	80.35 387	75.45 167	93.67 359	63.37 358	86.25 229	96.75 181

Patchmtry		77.36 335	74.59 340	85.67 310	89.75 312	75.75 306	77.85 413	91.12 361	60.28 408	71.23 343	80.35 387	75.45 167	93.56 361	57.94 376	67.34 366	87.68 346

LTVRE_ROB	73.68 18	77.99 327	75.74 332	84.74 323	90.45 299	72.02 339	86.41 383	91.12 361	72.57 363	66.63 368	87.27 314	54.95 346	96.98 232	56.29 385	75.98 301	85.21 380
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		77.18 337	76.06 329	80.55 366	83.78 387	60.00 404	90.35 350	91.05 364	77.01 328	66.62 369	87.92 305	47.73 374	94.03 351	71.63 310	68.44 353	87.62 347

CNLPA		86.96 202	85.37 213	91.72 163	97.59 73	79.34 212	97.21 127	91.05 364	74.22 347	78.90 262	96.75 135	67.21 256	98.95 122	74.68 288	90.77 183	96.88 173

Anonymous20240521		72.06 364	69.91 365	78.50 378	77.11 409	61.67 399	91.62 341	90.97 366	65.52 391	62.37 388	79.05 393	36.32 405	90.96 387	57.75 378	68.52 352	82.87 391

KD-MVS_self_test		70.97 369	69.31 368	75.95 390	76.24 414	55.39 415	87.45 373	90.94 367	70.20 375	62.96 387	77.48 397	44.01 382	88.09 400	61.25 366	53.26 402	84.37 385

pmmvs6		74.65 350	71.67 357	83.60 343	79.13 401	69.94 357	93.31 314	90.88 368	61.05 407	65.83 372	84.15 364	43.43 385	94.83 333	66.62 340	60.63 389	86.02 372

test1111		88.11 183	87.04 191	91.35 175	93.15 217	78.79 228	96.57 182	90.78 369	86.88 126	85.04 189	95.20 174	57.23 330	97.39 209	83.88 195	94.59 134	97.87 104

ECVR-MVS		88.35 178	87.25 185	91.65 164	93.54 202	79.40 209	96.56 184	90.78 369	86.78 130	85.57 184	95.25 168	57.25 329	97.56 194	84.73 189	94.80 131	97.98 96

Anonymous20231206		75.29 347	73.64 348	80.22 368	80.75 394	63.38 392	93.36 310	90.71 371	73.09 358	67.12 362	83.70 368	50.33 362	90.85 388	53.63 394	70.10 338	86.44 365

USDC		78.65 322	76.25 328	85.85 304	87.58 342	74.60 314	89.58 355	90.58 372	84.05 194	63.13 384	88.23 300	40.69 400	96.86 242	66.57 342	75.81 304	86.09 371

MSDG		80.62 307	77.77 317	89.14 235	93.43 210	77.24 275	91.89 335	90.18 373	69.86 378	68.02 359	91.94 249	52.21 355	98.84 128	59.32 373	83.12 254	91.35 272

ACMH+	76.62 16	77.47 334	74.94 336	85.05 320	91.07 286	71.58 347	93.26 315	90.01 374	71.80 367	64.76 377	88.55 292	41.62 393	96.48 255	62.35 361	71.00 329	87.09 358

FMVSNet5		76.46 341	74.16 345	83.35 346	90.05 307	76.17 294	89.58 355	89.85 375	71.39 370	65.29 376	80.42 386	50.61 360	87.70 405	61.05 367	69.24 347	86.18 369

ambc				76.02 388	68.11 423	51.43 418	64.97 426	89.59 376		60.49 396	74.49 406	17.17 425	92.46 369	61.50 364	52.85 404	84.17 387

test_fmvs2		79.59 314	79.90 300	78.67 376	82.86 390	55.82 413	95.20 258	89.55 377	81.09 255	80.12 252	89.80 278	34.31 411	93.51 362	87.82 165	78.36 294	86.69 362

ITE_SJBPF				82.38 353	87.00 347	65.59 381		89.55 377	79.99 283	69.37 356	91.30 256	41.60 394	95.33 312	62.86 360	74.63 311	86.24 368

pmmvs-eth3d		73.59 353	70.66 361	82.38 353	76.40 412	73.38 322	89.39 358	89.43 379	72.69 362	60.34 397	77.79 396	46.43 379	91.26 385	66.42 344	57.06 394	82.51 395

test20.03		72.36 362	71.15 359	75.98 389	77.79 405	59.16 406	92.40 329	89.35 380	74.09 349	61.50 392	84.32 362	48.09 369	85.54 412	50.63 401	62.15 387	83.24 390

SixPastTwentyTwo		76.04 342	74.32 343	81.22 361	84.54 377	61.43 400	91.16 344	89.30 381	77.89 313	64.04 379	86.31 334	48.23 368	94.29 347	63.54 357	63.84 382	87.93 342

TransMVSNet (Re)		76.94 338	74.38 342	84.62 328	85.92 362	75.25 309	95.28 252	89.18 382	73.88 351	67.22 361	86.46 329	59.64 302	94.10 350	59.24 374	52.57 405	84.50 384

MIMVSNet1		69.44 373	66.65 377	77.84 379	76.48 411	62.84 394	87.42 374	88.97 383	66.96 389	57.75 406	79.72 392	32.77 414	85.83 411	46.32 410	63.42 383	84.85 382

K. test v3		73.62 352	71.59 358	79.69 370	82.98 389	59.85 405	90.85 348	88.83 384	77.13 324	58.90 400	82.11 376	43.62 384	91.72 380	65.83 346	54.10 400	87.50 353

Baseline_NR-MVSNet		81.22 298	80.07 296	84.68 325	85.32 371	75.12 310	96.48 188	88.80 385	76.24 334	77.28 279	86.40 333	67.61 249	94.39 345	75.73 280	66.73 372	84.54 383

MDA-MVSNet-bldmvs		71.45 366	67.94 373	81.98 357	85.33 370	68.50 367	92.35 330	88.76 386	70.40 373	42.99 420	81.96 377	46.57 378	91.31 384	48.75 408	54.39 399	86.11 370

new-patchmatchnet		68.85 376	65.93 378	77.61 381	73.57 419	63.94 389	90.11 352	88.73 387	71.62 369	55.08 410	73.60 408	40.84 398	87.22 408	51.35 399	48.49 412	81.67 406

Patchmatch-test		78.25 324	74.72 339	88.83 242	91.20 280	74.10 319	73.91 421	88.70 388	59.89 411	66.82 366	85.12 355	78.38 107	94.54 341	48.84 407	79.58 281	97.86 105

OpenMVS_ROB	68.52 20	73.02 359	69.57 366	83.37 345	80.54 397	71.82 343	93.60 305	88.22 389	62.37 398	61.98 390	83.15 373	35.31 410	95.47 306	45.08 413	75.88 303	82.82 392

mvsany_test1		87.58 196	88.22 160	85.67 310	89.78 310	67.18 372	95.25 255	87.93 390	83.96 198	88.79 147	97.06 121	72.52 212	94.53 342	92.21 105	86.45 227	95.30 223

RPSCF		77.73 331	76.63 326	81.06 363	88.66 330	55.76 414	87.77 372	87.88 391	64.82 393	74.14 318	92.79 233	49.22 367	96.81 244	67.47 334	76.88 299	90.62 278

MVS-HIRNet		71.36 368	67.00 374	84.46 332	90.58 296	69.74 360	79.15 409	87.74 392	46.09 421	61.96 391	50.50 425	45.14 381	95.64 298	53.74 393	88.11 212	88.00 341

mmtdpeth		78.04 326	76.76 325	81.86 358	89.60 318	66.12 380	92.34 331	87.18 393	76.83 329	85.55 185	76.49 401	46.77 377	97.02 229	90.85 122	45.24 417	82.43 398

DP-MVS		81.47 294	78.28 312	91.04 185	98.14 55	78.48 233	95.09 267	86.97 394	61.14 406	71.12 345	92.78 234	59.59 303	99.38 86	53.11 395	86.61 225	95.27 224

COLMAP_ROB	73.24 19	75.74 345	73.00 352	83.94 336	92.38 242	69.08 364	91.85 336	86.93 395	61.48 403	65.32 375	90.27 272	42.27 391	96.93 237	50.91 400	75.63 305	85.80 377
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MVStest1		66.93 379	63.01 383	78.69 375	78.56 402	71.43 349	85.51 390	86.81 396	49.79 420	48.57 415	84.15 364	53.46 351	83.31 415	43.14 416	37.15 426	81.34 407

test_fmvs3		69.56 371	69.19 369	70.67 395	69.01 421	47.05 421	90.87 347	86.81 396	71.31 371	66.79 367	77.15 398	16.40 426	83.17 417	81.84 220	62.51 386	81.79 404

test_0402		72.68 360	69.54 367	82.09 356	88.67 329	71.81 344	92.72 325	86.77 398	61.52 402	62.21 389	83.91 366	43.22 387	93.76 358	34.60 421	72.23 324	80.72 408

testgi		74.88 349	73.40 349	79.32 373	80.13 398	61.75 397	93.21 316	86.64 399	79.49 292	66.56 370	91.06 259	35.51 409	88.67 397	56.79 384	71.25 327	87.56 350

TDRefinement		69.20 375	65.78 379	79.48 371	66.04 426	62.21 396	88.21 365	86.12 400	62.92 396	61.03 395	85.61 344	33.23 412	94.16 349	55.82 388	53.02 403	82.08 401

ADS-MVSNet2		79.57 315	77.53 318	85.71 309	93.78 195	72.13 337	79.48 406	86.11 401	73.09 358	80.14 250	79.99 390	62.15 288	90.14 394	59.49 371	83.52 250	94.85 233

LF4IMVS		72.36 362	70.82 360	76.95 384	79.18 400	56.33 410	86.12 385	86.11 401	69.30 380	63.06 385	86.66 325	33.03 413	92.25 372	65.33 348	68.64 351	82.28 399

TinyColmap		72.41 361	68.99 370	82.68 350	88.11 336	69.59 361	88.41 364	85.20 403	65.55 390	57.91 404	84.82 359	30.80 417	95.94 278	51.38 397	68.70 350	82.49 397

mvs5depth		71.40 367	68.36 372	80.54 367	75.31 416	65.56 382	79.94 405	85.14 404	69.11 381	71.75 340	81.59 379	41.02 397	93.94 353	60.90 368	50.46 407	82.10 400

pmmvs3		65.75 381	62.18 384	76.45 387	67.12 425	64.54 384	88.68 362	85.05 405	54.77 419	57.54 407	73.79 407	29.40 418	86.21 410	55.49 390	47.77 414	78.62 411

new_pmnet		66.18 380	63.18 382	75.18 392	76.27 413	61.74 398	83.79 398	84.66 406	56.64 417	51.57 413	71.85 416	31.29 416	87.93 401	49.98 403	62.55 385	75.86 414

AllTest		75.92 343	73.06 351	84.47 330	92.18 255	67.29 370	91.07 345	84.43 407	67.63 384	63.48 380	90.18 273	38.20 402	97.16 222	57.04 381	73.37 315	88.97 319

TestCases				84.47 330	92.18 255	67.29 370		84.43 407	67.63 384	63.48 380	90.18 273	38.20 402	97.16 222	57.04 381	73.37 315	88.97 319

ttmdpeth		69.58 370	66.92 376	77.54 382	75.95 415	62.40 395	88.09 367	84.32 409	62.87 397	65.70 374	86.25 336	36.53 404	88.53 399	55.65 389	46.96 416	81.70 405

LCM-MVSNet-Re		83.75 258	83.54 245	84.39 334	93.54 202	64.14 387	92.51 326	84.03 410	83.90 201	66.14 371	86.59 326	67.36 254	92.68 367	84.89 188	92.87 162	96.35 192

Gipuma		45.11 396	42.05 398	54.30 412	80.69 395	51.30 419	35.80 430	83.81 411	28.13 426	27.94 430	34.53 430	11.41 433	76.70 426	21.45 429	54.65 397	34.90 430
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		52.52 390	48.24 393	65.35 400	47.63 437	41.45 429	72.55 422	83.62 412	31.75 425	37.66 423	57.92 423	9.19 435	76.76 425	49.26 405	44.60 419	77.84 412

FPMVS		55.09 388	52.93 391	61.57 406	55.98 430	40.51 431	83.11 401	83.41 413	37.61 424	34.95 425	71.95 414	14.40 427	76.95 424	29.81 424	65.16 376	67.25 419

Patchmatch-RL test		76.65 340	74.01 347	84.55 329	77.37 408	64.23 386	78.49 412	82.84 414	78.48 309	64.63 378	73.40 409	76.05 154	91.70 381	76.99 264	57.84 393	97.72 116

DSMNet-mixed		73.13 358	72.45 353	75.19 391	77.51 407	46.82 422	85.09 393	82.01 415	67.61 388	69.27 357	81.33 382	50.89 358	86.28 409	54.54 391	83.80 249	92.46 266

lessismore_v0				79.98 369	80.59 396	58.34 408		80.87 416		58.49 402	83.46 370	43.10 388	93.89 354	63.11 359	48.68 410	87.72 344

test_f		64.01 382	62.13 385	69.65 396	63.00 428	45.30 427	83.66 399	80.68 417	61.30 404	55.70 409	72.62 412	14.23 428	84.64 413	69.84 324	58.11 392	79.00 410

door								80.13 418

door-mid								79.75 419

PM-MVS		69.32 374	66.93 375	76.49 386	73.60 418	55.84 412	85.91 386	79.32 420	74.72 344	61.09 394	78.18 395	21.76 422	91.10 386	70.86 319	56.90 395	82.51 395

mvsany_test3		67.19 378	65.34 380	72.72 393	63.08 427	48.57 420	83.12 400	78.09 421	72.07 365	61.21 393	77.11 399	22.94 421	87.78 404	78.59 247	51.88 406	81.80 403

dmvs_testset		72.00 365	73.36 350	67.91 397	83.83 386	31.90 437	85.30 391	77.12 422	82.80 229	63.05 386	92.46 236	61.54 295	82.55 419	42.22 418	71.89 325	89.29 305

ANet_high		46.22 393	41.28 400	61.04 407	39.91 439	46.25 425	70.59 423	76.18 423	58.87 414	23.09 431	48.00 428	12.58 431	66.54 431	28.65 426	13.62 432	70.35 417

test_method		56.77 385	54.53 389	63.49 404	76.49 410	40.70 430	75.68 417	74.24 424	19.47 432	48.73 414	71.89 415	19.31 423	65.80 432	57.46 380	47.51 415	83.97 388

APD_test1		56.56 386	53.58 390	65.50 399	67.93 424	46.51 424	77.24 416	72.95 425	38.09 423	42.75 421	75.17 403	13.38 429	82.78 418	40.19 419	54.53 398	67.23 420

EGC-MVSNET		52.46 391	47.56 394	67.15 398	81.98 392	60.11 403	82.54 402	72.44 426	0.11 438	0.70 439	74.59 405	25.11 420	83.26 416	29.04 425	61.51 388	58.09 423

PMMVS2		50.90 392	46.31 395	64.67 401	55.53 431	46.67 423	77.30 415	71.02 427	40.89 422	34.16 426	59.32 421	9.83 434	76.14 427	40.09 420	28.63 429	71.21 416

WB-MVS		57.26 384	56.22 387	60.39 408	69.29 420	35.91 435	86.39 384	70.06 428	59.84 412	46.46 418	72.71 411	51.18 357	78.11 422	15.19 432	34.89 427	67.14 421

SSC-MVS		56.01 387	54.96 388	59.17 409	68.42 422	34.13 436	84.98 394	69.23 429	58.08 416	45.36 419	71.67 417	50.30 363	77.46 423	14.28 433	32.33 428	65.91 422

test_vis1_rt		73.96 351	72.40 354	78.64 377	83.91 385	61.16 401	95.63 240	68.18 430	76.32 331	60.09 398	74.77 404	29.01 419	97.54 198	87.74 166	75.94 302	77.22 413

MTMP							97.53 103	68.16 431

DeepMVS_CX				64.06 403	78.53 403	43.26 428		68.11 432	69.94 377	38.55 422	76.14 402	18.53 424	79.34 420	43.72 414	41.62 423	69.57 418

PMVS	34.80 23	39.19 398	35.53 401	50.18 413	29.72 440	30.30 438	59.60 428	66.20 433	26.06 429	17.91 433	49.53 426	3.12 439	74.09 428	18.19 431	49.40 409	46.14 427
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testf1		45.70 394	42.41 396	55.58 410	53.29 434	40.02 432	68.96 424	62.67 434	27.45 427	29.85 427	61.58 419	5.98 437	73.83 429	28.49 427	43.46 421	52.90 424

APD_test2		45.70 394	42.41 396	55.58 410	53.29 434	40.02 432	68.96 424	62.67 434	27.45 427	29.85 427	61.58 419	5.98 437	73.83 429	28.49 427	43.46 421	52.90 424

tmp_tt		41.54 397	41.93 399	40.38 415	20.10 441	26.84 439	61.93 427	59.09 436	14.81 434	28.51 429	80.58 385	35.53 408	48.33 436	63.70 356	13.11 433	45.96 429

MVE	35.65 22	33.85 399	29.49 404	46.92 414	41.86 438	36.28 434	50.45 429	56.52 437	18.75 433	18.28 432	37.84 429	2.41 440	58.41 433	18.71 430	20.62 430	46.06 428
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		32.70 400	32.39 402	33.65 416	53.35 433	25.70 440	74.07 420	53.33 438	21.08 430	17.17 434	33.63 432	11.85 432	54.84 434	12.98 434	14.04 431	20.42 431

EMVS		31.70 401	31.45 403	32.48 417	50.72 436	23.95 441	74.78 419	52.30 439	20.36 431	16.08 435	31.48 433	12.80 430	53.60 435	11.39 435	13.10 434	19.88 432

test_vis3_rt		54.10 389	51.04 392	63.27 405	58.16 429	46.08 426	84.17 396	49.32 440	56.48 418	36.56 424	49.48 427	8.03 436	91.91 378	67.29 335	49.87 408	51.82 426

N_pmnet		61.30 383	60.20 386	64.60 402	84.32 379	17.00 443	91.67 340	10.98 441	61.77 401	58.45 403	78.55 394	49.89 364	91.83 379	42.27 417	63.94 381	84.97 381

wuyk23d		14.10 403	13.89 406	14.72 418	55.23 432	22.91 442	33.83 431	3.56 442	4.94 435	4.11 436	2.28 438	2.06 441	19.66 437	10.23 436	8.74 435	1.59 435

testmvs		9.92 404	12.94 407	0.84 420	0.65 442	0.29 445	93.78 301	0.39 443	0.42 436	2.85 437	15.84 436	0.17 443	0.30 439	2.18 437	0.21 436	1.91 434

test123		9.07 405	11.73 408	1.11 419	0.50 443	0.77 444	89.44 357	0.20 444	0.34 437	2.15 438	10.72 437	0.34 442	0.32 438	1.79 438	0.08 437	2.23 433

mmdepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet_test		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

pcd_1.5k_mvsjas		5.92 407	7.89 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	71.04 232	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

n2								0.00 445

nn								0.00 445

ab-mvs-re		8.11 406	10.81 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	97.30 107	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

WAC-MVS						67.18 372								49.00 406

PC_three_1452									91.12 44	98.33 3	98.42 35	92.51 2	99.81 22	98.96 5	99.37 1	99.70 3

eth-test2					0.00 444

eth-test					0.00 444

OPU-MVS				97.30 2	99.19 7	92.31 3	99.12 13				98.54 22	92.06 3	99.84 13	99.11 4	99.37 1	99.74 1

test_0728_THIRD									88.38 84	96.69 24	98.76 12	89.64 12	99.76 36	97.47 33	98.84 23	99.38 14

GSMVS																97.54 130

test_part2					98.90 19	85.14 72				96.07 36

sam_mvs1												77.59 121				97.54 130

sam_mvs												75.35 174

test_post1							85.88 387				30.24 434	73.77 198	95.07 327	73.89 296

test_post											33.80 431	76.17 152	95.97 274

patchmatchnet-post											77.09 400	77.78 119	95.39 308

gm-plane-assit					92.27 249	79.64 205			84.47 181		95.15 178		97.93 172	85.81 180

test9_res														96.00 49	99.03 13	98.31 69

agg_prior2														94.30 73	99.00 15	98.57 53

test_prior4						82.34 125	97.75 86

test_prior2							98.37 49		86.08 139	94.57 59	98.02 63	83.14 57		95.05 64	98.79 27

旧先验2							96.97 155		74.06 350	96.10 35			97.76 183	88.38 160

新几何2							96.42 195

原ACMM2							96.84 165

testdata2													99.48 81	76.45 271

segment_acmp												82.69 63

testdata1							95.57 244		87.44 111

plane_prior7					91.86 270	77.55 270

plane_prior6					91.98 266	77.92 256						64.77 274

plane_prior4											94.15 206

plane_prior3						77.75 266			90.17 61	81.33 236

plane_prior2							97.18 131		89.89 63

plane_prior1					91.95 268

plane_prior						77.96 253	97.52 106		90.36 59						82.96 258

HQP5-MVS						78.48 233

HQP-NCC					92.08 261		97.63 92		90.52 54	82.30 223

ACMP_Plane					92.08 261		97.63 92		90.52 54	82.30 223

BP-MVS														87.67 168

HQP4-MVS										82.30 223			97.32 212			91.13 273

HQP2-MVS												65.40 269

NP-MVS					92.04 265	78.22 243					94.56 196

MDTV_nov1_ep13_2view						81.74 141	86.80 379		80.65 264	85.65 183		74.26 192		76.52 270		96.98 166

ACMMP++_ref															78.45 293

ACMMP++															79.05 285

Test By Simon												71.65 225

High-resolution multi-view benchmark