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		88.92 197	87.65 209	92.73 122	96.30 112	85.62 61	97.85 90	98.86 1	84.38 231	84.82 238	93.99 259	75.12 194	98.01 184	70.86 386	86.67 277	94.56 298

thres100view900		88.30 217	86.95 232	92.33 151	96.10 120	84.90 85	97.14 153	98.85 2	82.69 284	83.41 267	93.66 269	75.43 184	97.93 187	69.04 394	86.24 284	94.17 302

tfpn200view9		88.48 211	87.15 225	92.47 138	96.21 115	85.30 70	97.44 126	98.85 2	83.37 265	83.99 254	93.82 265	75.36 187	97.93 187	69.04 394	86.24 284	94.17 302

thres600view7		88.06 224	86.70 240	92.15 167	96.10 120	85.17 76	97.14 153	98.85 2	82.70 283	83.41 267	93.66 269	75.43 184	97.82 197	67.13 403	85.88 289	93.45 318

thres400		88.42 214	87.15 225	92.23 159	96.21 115	85.30 70	97.44 126	98.85 2	83.37 265	83.99 254	93.82 265	75.36 187	97.93 187	69.04 394	86.24 284	93.45 318

MVS_111021_HR		93.41 55	93.39 60	93.47 87	97.34 97	82.83 130	97.56 115	98.27 6	89.16 81	89.71 145	97.14 124	79.77 92	99.56 84	93.65 94	97.94 63	98.02 100

sss		90.87 136	89.96 153	93.60 77	94.15 198	83.84 104	97.14 153	98.13 7	85.93 179	89.68 146	96.09 158	71.67 252	99.30 102	87.69 208	89.16 237	97.66 139

MM		95.85 6	95.74 11	96.15 9	96.34 111	89.50 10	99.18 9	98.10 8	95.68 1	96.64 34	97.92 80	80.72 77	99.80 33	99.16 2	97.96 62	99.15 28

MG-MVS		94.25 37	93.72 49	95.85 13	99.38 4	89.35 12	97.98 81	98.09 9	89.99 69	92.34 102	96.97 134	81.30 75	98.99 129	88.54 195	98.88 20	99.20 26

VNet		92.11 99	91.22 111	94.79 29	96.91 103	86.98 32	97.91 87	97.96 10	86.38 162	93.65 81	95.74 166	70.16 273	98.95 133	93.39 96	88.87 242	98.43 70

test_yl		91.46 116	90.53 127	94.24 45	97.41 91	85.18 72	98.08 74	97.72 11	80.94 312	89.85 142	96.14 156	75.61 176	98.81 141	90.42 157	88.56 253	98.74 50

DCV-MVSNet		91.46 116	90.53 127	94.24 45	97.41 91	85.18 72	98.08 74	97.72 11	80.94 312	89.85 142	96.14 156	75.61 176	98.81 141	90.42 157	88.56 253	98.74 50

WTY-MVS		92.65 83	91.68 102	95.56 15	96.00 122	88.90 14	98.23 65	97.65 13	88.57 88	89.82 144	97.22 122	79.29 97	99.06 126	89.57 173	88.73 244	98.73 54

EPNet		94.06 43	94.15 44	93.76 63	97.27 99	84.35 93	98.29 63	97.64 14	94.57 11	95.36 51	96.88 137	79.96 91	99.12 122	91.30 133	96.11 126	97.82 124
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HY-MVS	84.06 6	91.63 112	90.37 135	95.39 20	96.12 119	88.25 18	90.22 421	97.58 15	88.33 96	90.50 134	91.96 301	79.26 98	99.06 126	90.29 161	89.07 238	98.88 44

testing3-2		91.37 119	91.01 119	92.44 142	95.93 128	83.77 105	98.83 36	97.45 16	86.88 147	86.63 213	94.69 233	84.57 44	97.75 200	89.65 171	84.44 299	95.80 255

SymmetryMVS		92.45 89	92.33 86	92.82 117	95.19 157	82.02 155	97.94 84	97.43 17	92.34 32	92.15 106	96.53 150	77.03 142	98.57 149	91.13 137	91.19 207	97.87 117

baseline2		90.39 153	90.21 141	90.93 238	90.86 340	80.99 198	95.20 311	97.41 18	86.03 173	80.07 311	94.61 234	90.58 7	97.47 233	87.29 212	89.86 226	94.35 300

test2506		90.96 132	90.39 133	92.65 126	93.54 218	82.46 142	96.37 223	97.35 19	86.78 152	87.55 191	95.25 195	77.83 126	97.50 229	84.07 238	94.80 145	97.98 108

PVSNet	82.34 9	89.02 193	87.79 207	92.71 123	95.49 145	81.50 183	97.70 103	97.29 20	87.76 112	85.47 230	95.12 209	56.90 395	98.90 137	80.33 280	94.02 156	97.71 135

testing222		91.09 127	90.49 130	92.87 112	95.82 131	85.04 80	96.51 212	97.28 21	86.05 171	89.13 158	95.34 192	80.16 87	96.62 307	85.82 224	88.31 261	96.96 212

PGM-MVS		91.93 103	91.80 100	92.32 153	98.27 56	79.74 254	95.28 303	97.27 22	83.83 253	90.89 130	97.78 90	76.12 167	99.56 84	88.82 188	97.93 65	97.66 139

IB-MVS	85.34 4	88.67 205	87.14 227	93.26 92	93.12 238	84.32 95	98.76 37	97.27 22	87.19 137	79.36 317	90.45 324	83.92 57	98.53 154	84.41 235	69.79 400	96.93 214
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
TestfortrainingZip				97.22 3	99.48 2	91.93 7	98.35 57	97.26 24	85.61 186	99.54 1	99.26 1	91.36 5	99.98 2		96.55 117	99.73 3

aaEdge-Enhanced		94.82 21	95.04 23	94.17 51	99.17 9	83.70 108	97.66 106	97.22 25	85.79 182	95.34 52	98.90 6	84.89 40	99.86 15	97.78 36	98.60 36	98.94 39

test_fmvsm_n_1920		94.81 22	95.60 12	92.45 140	95.29 152	80.96 204	99.29 4	97.21 26	94.50 13	97.29 23	98.44 41	82.15 69	99.78 40	98.56 12	97.68 72	96.61 232

patch_mono-2		95.14 14	96.08 7	92.33 151	98.44 49	77.84 324	98.43 52	97.21 26	92.58 29	97.68 16	97.65 98	86.88 29	99.83 23	98.25 18	97.60 74	99.33 19

MVS		90.60 143	88.64 184	96.50 6	94.25 194	90.53 9	93.33 373	97.21 26	77.59 378	78.88 320	97.31 114	71.52 256	99.69 66	89.60 172	98.03 60	99.27 23

ETVMVS		90.99 130	90.26 138	93.19 97	95.81 132	85.64 60	96.97 171	97.18 29	85.43 192	88.77 168	94.86 225	82.00 71	96.37 314	82.70 259	88.60 249	97.57 149

CSCG		92.02 100	91.65 103	93.12 100	98.53 42	80.59 216	97.47 123	97.18 29	77.06 387	84.64 244	97.98 77	83.98 55	99.52 87	90.72 148	97.33 86	99.23 25

aaatest				94.20 50	99.06 11	83.70 108	98.35 57	97.14 31	87.45 124	97.03 27	98.90 6		99.96 4	97.78 36	98.60 36	98.94 39

MED-MVS		95.59 9	96.05 8	94.21 47	99.06 11	83.70 108	98.35 57	97.14 31	87.65 118	97.03 27	98.83 10	89.87 13	99.96 4	97.78 36	98.71 31	98.97 36

fmvsm_s_conf0.5_n		93.69 48	94.13 45	92.34 149	94.56 178	82.01 157	99.07 22	97.13 33	92.09 37	96.25 39	98.53 32	76.47 155	99.80 33	98.39 14	94.71 147	95.22 279

PHI-MVS		93.59 50	93.63 52	93.48 85	98.05 64	81.76 173	98.64 44	97.13 33	82.60 286	94.09 76	98.49 36	80.35 81	99.85 17	94.74 79	98.62 35	98.83 45

CNVR-MVS		96.30 1	96.54 1	95.55 16	99.31 6	87.69 25	99.06 23	97.12 35	94.66 10	96.79 30	98.78 15	86.42 32	99.95 6	97.59 40	99.18 7	99.00 33

h-mvs33		89.30 186	88.95 179	90.36 260	95.07 164	76.04 362	96.96 173	97.11 36	90.39 64	92.22 104	95.10 210	74.70 200	98.86 138	93.14 105	65.89 437	96.16 245

MCST-MVS		96.17 3	96.12 6	96.32 8	99.42 3	89.36 11	98.94 31	97.10 37	95.17 4	92.11 108	98.46 40	87.33 27	99.97 3	97.21 48	99.31 4	99.63 8

testing11		92.48 88	92.04 97	93.78 62	95.94 127	86.00 45	97.56 115	97.08 38	87.52 122	89.32 154	95.40 190	84.60 43	98.02 182	91.93 129	89.04 239	97.32 180

VPA-MVSNet		85.32 286	83.83 289	89.77 283	90.25 353	82.63 134	96.36 226	97.07 39	83.03 275	81.21 295	89.02 344	61.58 352	96.31 317	85.02 232	70.95 389	90.36 340

UBG		92.68 82	92.35 84	93.70 70	95.61 141	85.65 59	97.25 140	97.06 40	87.92 107	89.28 155	95.03 213	86.06 36	98.07 178	92.24 120	90.69 217	97.37 175

UWE-MVS		88.56 210	88.91 181	87.50 342	94.17 197	72.19 405	95.82 280	97.05 41	84.96 211	84.78 239	93.51 273	81.33 73	94.75 402	79.43 292	89.17 236	95.57 267

UWE-MVS-28		85.41 284	86.36 243	82.59 423	91.12 333	66.81 451	93.88 358	97.03 42	83.86 252	78.55 322	93.84 264	77.76 128	88.55 472	73.47 367	87.69 268	92.41 326

DELS-MVS		94.98 15	94.49 34	96.44 7	96.42 109	90.59 8	99.21 8	97.02 43	94.40 14	91.46 117	97.08 129	83.32 61	99.69 66	92.83 110	98.70 33	99.04 31
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 84	94.94 168	86.26 39	81.62 477	97.00 44		88.32 176	94.30 245	91.23 6	96.21 322	88.49 197	97.43 81	98.00 106

myMVS_eth3d28		92.72 75	92.23 90	94.21 47	96.16 117	87.46 30	97.37 134	96.99 45	88.13 102	88.18 181	95.47 187	84.12 52	98.04 180	92.46 118	91.17 209	97.14 197

lecture		93.17 57	93.57 55	91.96 181	97.80 71	78.79 289	98.50 50	96.98 46	86.61 158	94.75 68	98.16 62	78.36 116	99.35 101	93.89 89	97.12 95	97.75 130

fmvsm_s_conf0.5_n_a		93.34 56	93.71 50	92.22 160	93.38 227	81.71 176	98.86 35	96.98 46	91.64 43	96.85 29	98.55 28	75.58 179	99.77 44	97.88 32	93.68 166	95.18 281

DPM-MVS		96.21 2	95.53 15	98.26 1	96.26 114	95.09 1	99.15 12	96.98 46	93.39 23	96.45 38	98.79 14	90.17 10	99.99 1	89.33 178	99.25 6	99.70 4

gg-mvs-nofinetune		85.48 282	82.90 312	93.24 93	94.51 185	85.82 51	79.22 484	96.97 49	61.19 477	87.33 195	53.01 512	90.58 7	96.07 326	86.07 223	97.23 89	97.81 126

NCCC		95.63 7	95.94 9	94.69 33	99.21 7	85.15 77	99.16 11	96.96 50	94.11 15	95.59 50	98.64 25	85.07 39	99.91 8	95.61 65	99.10 9	99.00 33

FIs		86.73 257	86.10 247	88.61 305	90.05 360	80.21 236	96.14 248	96.95 51	85.56 189	78.37 325	92.30 292	76.73 151	95.28 371	79.51 290	79.27 337	90.35 341

PVSNet_0	77.72 15	81.70 350	78.95 369	89.94 276	90.77 344	76.72 351	95.96 258	96.95 51	85.01 209	70.24 420	88.53 352	52.32 419	98.20 173	86.68 221	44.08 497	94.89 287

HPM-MVS++		95.32 12	95.48 16	94.85 27	98.62 40	86.04 44	97.81 94	96.93 53	92.45 30	95.69 48	98.50 35	85.38 37	99.85 17	94.75 78	99.18 7	98.65 58

MSLP-MVS++		94.28 35	94.39 37	93.97 56	98.30 55	84.06 100	98.64 44	96.93 53	90.71 57	93.08 90	98.70 23	79.98 90	99.21 109	94.12 87	99.07 11	98.63 59

testing99		91.91 104	91.35 108	93.60 77	95.98 124	85.70 54	97.31 138	96.92 55	86.82 150	88.91 163	95.25 195	84.26 51	97.89 195	88.80 189	87.94 265	97.21 190

testing91		91.90 105	91.31 110	93.66 73	95.99 123	85.68 56	97.39 133	96.89 56	86.75 154	88.85 165	95.23 199	83.93 56	97.90 194	88.91 182	87.89 266	97.41 171

UniMVSNet (Re)		85.31 287	84.23 282	88.55 306	89.75 367	80.55 220	96.72 195	96.89 56	85.42 193	78.40 324	88.93 345	75.38 186	95.52 361	78.58 304	68.02 417	89.57 358

FC-MVSNet-test		85.96 269	85.39 259	87.66 335	89.38 379	78.02 315	95.65 289	96.87 58	85.12 206	77.34 334	91.94 304	76.28 162	94.74 403	77.09 323	78.82 341	90.21 344

EI-MVSNet-Vis-set		91.84 107	91.77 101	92.04 178	97.60 80	81.17 191	96.61 202	96.87 58	88.20 100	89.19 157	97.55 106	78.69 110	99.14 119	90.29 161	90.94 213	95.80 255

IU-MVS					99.03 20	85.34 66		96.86 60	92.05 41	98.74 2				98.15 22	98.97 17	99.42 14

BP-MVS1		93.55 53	93.50 57	93.71 69	92.64 265	85.39 65	97.78 96	96.84 61	89.52 76	92.00 109	97.06 131	88.21 22	98.03 181	91.45 132	96.00 131	97.70 136

MSC_two_6792asdad				97.14 4	99.05 14	92.19 4		96.83 62					99.81 29	98.08 26	98.81 24	99.43 12

No_MVS				97.14 4	99.05 14	92.19 4		96.83 62					99.81 29	98.08 26	98.81 24	99.43 12

EI-MVSNet-UG-set		91.35 121	91.22 111	91.73 199	97.39 94	80.68 213	96.47 214	96.83 62	87.92 107	88.30 178	97.36 113	77.84 125	99.13 121	89.43 177	89.45 229	95.37 273

test-260524					99.01 23	85.87 50		96.82 65		95.25 54		86.23 34	99.92 7	97.87 33	98.71 31

TestfortrainingZip a		94.24 38	94.19 43	94.40 40	99.06 11	84.33 94	98.35 57	96.81 66	87.65 118	95.97 46	98.83 10	84.06 53	99.89 11	91.98 127	95.03 143	98.97 36

SED-MVS		95.88 5	96.22 4	94.87 26	99.03 20	85.03 81	99.12 16	96.78 67	88.72 85	97.79 11	98.91 3	88.48 19	99.82 25	98.15 22	98.97 17	99.74 1

test_241102_TWO								96.78 67	88.72 85	97.70 14	98.91 3	87.86 24	99.82 25	98.15 22	99.00 15	99.47 10

test_241102_ONE					99.03 20	85.03 81		96.78 67	88.72 85	97.79 11	98.90 6	88.48 19	99.82 25

test0726					99.05 14	85.18 72	99.11 19	96.78 67	88.75 83	97.65 18	98.91 3	87.69 25

MSP-MVS		95.62 8	96.54 1	92.86 113	98.31 54	80.10 242	97.42 130	96.78 67	92.20 36	97.11 24	98.29 53	93.46 1	99.10 123	96.01 58	99.30 5	99.38 15
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							96.87 180	96.78 67	77.39 380				99.52 87	79.95 287		98.43 70

DVP-MVS++		96.05 4	96.41 3	94.96 25	99.05 14	85.34 66	98.13 71	96.77 73	88.38 93	97.70 14	98.77 16	92.06 3	99.84 19	97.47 41	99.37 1	99.70 4

test_0728_SECOND				95.14 21	99.04 19	86.14 43	99.06 23	96.77 73					99.84 19	97.90 30	98.85 21	99.45 11

SMA-MVS		94.70 24	94.68 30	94.76 30	98.02 65	85.94 48	97.47 123	96.77 73	85.32 195	97.92 6	98.70 23	83.09 64	99.84 19	95.79 62	99.08 10	98.49 65
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		91.60 114	91.64 104	91.47 215	95.74 136	78.79 289	96.15 247	96.77 73	88.49 90	88.64 170	97.07 130	72.33 238	99.19 115	93.13 107	96.48 119	96.43 237

3Dnovator	82.32 10	89.33 185	87.64 210	94.42 39	93.73 213	85.70 54	97.73 101	96.75 77	86.73 155	76.21 357	95.93 160	62.17 341	99.68 68	81.67 268	97.81 67	97.88 115

fmvsm_s_conf0.5_n_7		92.88 67	93.82 47	90.08 268	92.79 257	76.45 355	98.54 48	96.74 78	92.28 34	95.22 55	98.49 36	74.91 197	98.15 177	98.28 16	97.13 94	95.63 263

DPE-MVS		95.32 12	95.55 14	94.64 34	98.79 29	84.87 86	97.77 97	96.74 78	86.11 168	96.54 37	98.89 9	88.39 21	99.74 54	97.67 39	99.05 12	99.31 21
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
PVSNet_BlendedMVS		90.05 162	89.96 153	90.33 261	97.47 85	83.86 102	98.02 80	96.73 80	87.98 105	89.53 151	89.61 338	76.42 157	99.57 82	94.29 84	79.59 334	87.57 418

PVSNet_Blended		93.13 58	92.98 68	93.57 79	97.47 85	83.86 102	99.32 3	96.73 80	91.02 54	89.53 151	96.21 155	76.42 157	99.57 82	94.29 84	95.81 135	97.29 185

ACMMP		90.39 153	89.97 152	91.64 204	97.58 82	78.21 311	96.78 191	96.72 82	84.73 216	84.72 241	97.23 121	71.22 258	99.63 74	88.37 200	92.41 188	97.08 205
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				93.12 100	97.44 89	81.60 182		96.71 83	74.54 410	91.22 124	97.57 102	79.13 101	99.51 89	77.40 322	98.46 44	98.26 82

test_one_0601					98.91 24	84.56 91		96.70 84	88.06 103	96.57 36	98.77 16	88.04 23

HFP-MVS		92.89 66	92.86 73	92.98 107	98.71 31	81.12 193	97.58 113	96.70 84	85.20 200	91.75 114	97.97 79	78.47 113	99.71 62	90.95 139	98.41 47	98.12 94

ACMMPR		92.69 80	92.67 76	92.75 120	98.66 34	80.57 219	97.58 113	96.69 86	85.20 200	91.57 116	97.92 80	77.01 144	99.67 70	90.95 139	98.41 47	98.00 106

DeepPCF-MVS	89.82 1	94.61 25	96.17 5	89.91 277	97.09 102	70.21 428	98.99 29	96.69 86	95.57 2	95.08 60	99.23 2	86.40 33	99.87 13	97.84 34	98.66 34	99.65 7

thisisatest0530		89.65 174	89.02 174	91.53 209	93.46 225	80.78 211	96.52 210	96.67 88	81.69 303	83.79 259	94.90 222	88.85 16	97.68 204	77.80 311	87.49 273	96.14 246

tttt0517		88.57 209	88.19 199	89.71 284	93.00 241	75.99 366	95.67 287	96.67 88	80.78 317	81.82 290	94.40 243	88.97 15	97.58 214	76.05 338	86.31 281	95.57 267

thisisatest0515		90.95 133	90.26 138	93.01 105	94.03 207	84.27 98	97.91 87	96.67 88	83.18 269	86.87 211	95.51 184	88.66 17	97.85 196	80.46 279	89.01 240	96.92 216

fmvsm_s_conf0.5_n_8		94.52 29	95.04 23	92.96 108	95.15 161	81.14 192	99.09 20	96.66 91	95.53 3	97.84 10	98.71 22	76.33 160	99.81 29	99.24 1	96.85 109	97.92 113

ACMMP_NAP		93.46 54	93.23 63	94.17 51	97.16 100	84.28 97	96.82 186	96.65 92	86.24 165	94.27 73	97.99 74	77.94 122	99.83 23	93.39 96	98.57 38	98.39 72

TEST9					98.64 37	83.71 106	97.82 92	96.65 92	84.29 236	95.16 56	98.09 67	84.39 46	99.36 99

train_agg		94.28 35	94.45 35	93.74 65	98.64 37	83.71 106	97.82 92	96.65 92	84.50 226	95.16 56	98.09 67	84.33 47	99.36 99	95.91 61	98.96 19	98.16 89

1314		88.94 196	87.20 224	94.17 51	93.21 232	85.73 53	93.33 373	96.64 95	82.89 278	75.98 360	96.36 152	66.83 307	99.39 95	83.52 252	96.02 130	97.39 174

DeepC-MVS_fast	89.06 2	94.48 31	94.30 40	95.02 23	98.86 27	85.68 56	98.06 77	96.64 95	93.64 21	91.74 115	98.54 30	80.17 86	99.90 9	92.28 119	98.75 29	99.49 9
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 39	83.64 112	97.81 94	96.63 97	84.50 226	95.10 59	98.11 65	84.33 47	99.23 107

FE-MVS		86.06 268	84.15 285	91.78 195	94.33 193	79.81 248	84.58 469	96.61 98	76.69 393	85.00 235	87.38 373	70.71 268	98.37 166	70.39 389	91.70 199	97.17 196

原ACMM1				91.22 228	97.77 73	78.10 314		96.61 98	81.05 311	91.28 123	97.42 111	77.92 124	98.98 130	79.85 289	98.51 40	96.59 233

MAR-MVS		90.63 142	90.22 140	91.86 187	98.47 48	78.20 312	97.18 146	96.61 98	83.87 250	88.18 181	98.18 58	68.71 287	99.75 51	83.66 248	97.15 93	97.63 143
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 10	83.22 121		96.60 101	82.88 279	93.61 83	98.06 72	82.93 65	99.14 119	95.51 68	98.49 43

MGCNet		95.58 10	95.44 17	96.01 11	97.63 78	89.26 13	99.27 5	96.59 102	94.71 9	97.08 25	97.99 74	78.69 110	99.86 15	99.15 3	97.85 66	98.91 42

SteuartSystems-ACMMP		94.13 42	94.44 36	93.20 96	95.41 147	81.35 188	99.02 27	96.59 102	89.50 77	94.18 75	98.36 50	83.68 59	99.45 93	94.77 77	98.45 45	98.81 47
Skip Steuart: Steuart Systems R&D Blog.
D2MVS		82.67 335	81.55 332	86.04 371	87.77 399	76.47 353	95.21 310	96.58 104	82.66 285	70.26 418	85.46 409	60.39 358	95.80 341	76.40 334	79.18 338	85.83 446

save fliter					98.24 57	83.34 118	98.61 46	96.57 105	91.32 47

TESTMET0.1,1		89.83 170	89.34 168	91.31 220	92.54 269	80.19 238	97.11 156	96.57 105	86.15 167	86.85 212	91.83 306	79.32 95	96.95 285	81.30 273	92.35 189	96.77 225

agg_prior					98.59 41	83.13 123		96.56 107		94.19 74			99.16 118

0.3-1-1-0.015		87.79 233	85.93 249	93.38 89	89.87 363	85.09 79	98.43 52	96.55 108	81.13 309	87.21 200	89.75 334	77.23 139	97.02 277	86.87 218	66.38 434	98.02 100

0.4-1-1-0.1		87.53 243	85.67 254	93.13 99	89.70 370	84.41 92	98.30 62	96.55 108	80.85 314	86.94 206	89.53 339	76.18 163	96.99 282	86.62 222	66.36 436	97.98 108

0.4-1-1-0.2		87.73 235	85.82 252	93.46 88	89.97 362	85.31 69	98.49 51	96.55 108	81.24 307	87.14 202	89.63 337	76.16 165	97.02 277	86.84 219	66.38 434	98.05 98

旧先验1					97.39 94	79.58 260		96.54 111			98.08 70	84.00 54			97.42 82	97.62 145

WR-MVS_H		81.02 361	80.09 353	83.79 407	88.08 396	71.26 421	94.46 335	96.54 111	80.08 340	72.81 393	86.82 383	70.36 271	92.65 436	64.18 421	67.50 423	87.46 423

fmvsm_s_conf0.5_n_4		93.59 50	94.32 39	91.41 217	93.89 208	79.24 267	98.89 34	96.53 113	92.82 27	97.37 22	98.47 39	77.21 141	99.78 40	98.11 25	95.59 138	95.21 280

9.14			94.26 42		98.10 63		98.14 68	96.52 114	84.74 215	94.83 66	98.80 13	82.80 67	99.37 98	95.95 60	98.42 46

region2R		92.72 75	92.70 75	92.79 118	98.68 32	80.53 225	97.53 118	96.51 115	85.22 198	91.94 112	97.98 77	77.26 135	99.67 70	90.83 146	98.37 50	98.18 87

EPP-MVSNet		89.76 171	89.72 160	89.87 278	93.78 210	76.02 365	97.22 141	96.51 115	79.35 353	85.11 233	95.01 215	84.82 41	97.10 275	87.46 211	88.21 263	96.50 235

ZNCC-MVS		92.75 71	92.60 78	93.23 94	98.24 57	81.82 171	97.63 107	96.50 117	85.00 210	91.05 126	97.74 91	78.38 114	99.80 33	90.48 152	98.34 52	98.07 97

test11								96.50 117

EPNet_dtu		87.65 240	87.89 204	86.93 355	94.57 177	71.37 420	96.72 195	96.50 117	88.56 89	87.12 203	95.02 214	75.91 172	94.01 420	66.62 407	90.00 223	95.42 272
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testdata				90.13 267	95.92 129	74.17 385		96.49 120	73.49 419	94.82 67	97.99 74	78.80 108	97.93 187	83.53 251	97.52 76	98.29 79

fmvsm_s_conf0.5_n_6		94.17 39	94.70 29	92.58 134	93.50 224	81.20 190	99.08 21	96.48 121	92.24 35	98.62 3	98.39 46	78.58 112	99.72 59	98.08 26	97.36 85	96.81 222

DVP-MVS		95.58 10	95.91 10	94.57 36	99.05 14	85.18 72	99.06 23	96.46 122	88.75 83	96.69 31	98.76 18	87.69 25	99.76 46	97.90 30	98.85 21	98.77 48
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					96.15 118	78.41 300	95.87 276	96.46 122	71.97 436	89.66 147	97.45 107	76.33 160			98.24 55	98.30 78

XVS		92.69 80	92.71 74	92.63 129	98.52 43	80.29 231	97.37 134	96.44 124	87.04 143	91.38 118	97.83 88	77.24 137	99.59 78	90.46 154	98.07 58	98.02 100

X-MVStestdata		86.26 265	84.14 286	92.63 129	98.52 43	80.29 231	97.37 134	96.44 124	87.04 143	91.38 118	20.73 532	77.24 137	99.59 78	90.46 154	98.07 58	98.02 100

SF-MVS		94.17 39	94.05 46	94.55 37	97.56 83	85.95 46	97.73 101	96.43 126	84.02 243	95.07 61	98.74 20	82.93 65	99.38 96	95.42 69	98.51 40	98.32 75

TSAR-MVS + MP.		94.79 23	95.17 22	93.64 74	97.66 77	84.10 99	95.85 278	96.42 127	91.26 48	97.49 21	96.80 142	86.50 31	98.49 156	95.54 67	99.03 13	98.33 74
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 28	94.75 27	93.96 57	98.84 28	83.40 117	98.04 79	96.41 128	85.79 182	95.00 62	98.28 54	84.32 50	99.18 116	97.35 44	98.77 28	99.28 22
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
UniMVSNet_NR-MVSNet		85.49 281	84.59 274	88.21 321	89.44 378	79.36 264	96.71 197	96.41 128	85.22 198	78.11 328	90.98 317	76.97 146	95.14 383	79.14 298	68.30 414	90.12 347

test_prior				93.09 102	98.68 32	81.91 164		96.40 130					99.06 126			98.29 79

CP-MVS		92.54 86	92.60 78	92.34 149	98.50 46	79.90 247	98.40 55	96.40 130	84.75 214	90.48 135	98.09 67	77.40 133	99.21 109	91.15 136	98.23 56	97.92 113

fmvsm_s_conf0.5_n_10		94.36 33	94.73 28	93.23 94	95.19 157	82.87 129	99.18 9	96.39 132	93.97 18	97.91 8	98.53 32	75.88 173	99.82 25	98.58 11	96.95 102	97.00 208

CANet		94.89 18	94.64 31	95.63 14	97.55 84	88.12 19	99.06 23	96.39 132	94.07 17	95.34 52	97.80 89	76.83 149	99.87 13	97.08 50	97.64 73	98.89 43

GST-MVS		92.43 91	92.22 92	93.04 104	98.17 60	81.64 179	97.40 132	96.38 134	84.71 217	90.90 129	97.40 112	77.55 131	99.76 46	89.75 170	97.74 70	97.72 133

alignmvs		92.97 63	92.26 89	95.12 22	95.54 144	87.77 23	98.67 42	96.38 134	88.04 104	93.01 91	97.45 107	79.20 100	98.60 147	93.25 102	88.76 243	98.99 35

PAPM		92.87 69	92.40 83	94.30 42	92.25 288	87.85 22	96.40 222	96.38 134	91.07 52	88.72 169	96.90 135	82.11 70	97.37 254	90.05 165	97.70 71	97.67 138

fmvsm_l_conf0.5_n_3		94.61 25	94.92 26	93.68 72	94.52 181	82.80 131	99.33 2	96.37 137	95.08 6	97.59 20	98.48 38	77.40 133	99.79 37	98.28 16	97.21 90	98.44 69

test_fmvsmconf_n		93.99 44	94.36 38	92.86 113	92.82 254	81.12 193	99.26 6	96.37 137	93.47 22	95.16 56	98.21 56	79.00 103	99.64 72	98.21 20	96.73 113	97.83 122

fmvsm_l_conf0.5_n_9		94.91 16	95.60 12	92.84 116	95.20 156	80.55 220	99.45 1	96.36 139	95.17 4	98.48 4	98.55 28	80.53 80	99.78 40	98.87 7	97.79 69	98.19 86

test12				94.25 44	98.34 52	85.55 62		96.35 140		92.36 101		80.84 76	99.22 108		98.31 53	97.98 108

MTGPA								96.33 141

MTAPA		92.45 89	92.31 87	92.86 113	97.90 67	80.85 209	92.88 385	96.33 141	87.92 107	90.20 140	98.18 58	76.71 152	99.76 46	92.57 116	98.09 57	97.96 112

reproduce_monomvs		87.80 232	87.60 214	88.40 309	96.56 106	80.26 234	95.80 281	96.32 143	91.56 45	73.60 380	88.36 357	88.53 18	96.25 320	90.47 153	67.23 426	88.67 393

ET-MVSNet_ETH3D		90.01 163	89.03 173	92.95 109	94.38 191	86.77 35	98.14 68	96.31 144	89.30 79	63.33 453	96.72 146	90.09 11	93.63 428	90.70 150	82.29 321	98.46 67

EPMVS		87.47 245	85.90 250	92.18 164	95.41 147	82.26 150	87.00 452	96.28 145	85.88 180	84.23 249	85.57 406	75.07 195	96.26 318	71.14 384	92.50 183	98.03 99

WB-MVSnew		84.08 311	83.51 300	85.80 373	91.34 328	76.69 352	95.62 291	96.27 146	81.77 301	81.81 291	92.81 283	58.23 374	94.70 404	66.66 406	87.06 274	85.99 443

CDPH-MVS		93.12 59	92.91 70	93.74 65	98.65 36	83.88 101	97.67 105	96.26 147	83.00 276	93.22 87	98.24 55	81.31 74	99.21 109	89.12 179	98.74 30	98.14 91

WR-MVS		84.32 307	82.96 310	88.41 308	89.38 379	80.32 230	96.59 203	96.25 148	83.97 245	76.63 346	90.36 326	67.53 297	94.86 398	75.82 341	70.09 398	90.06 351

fmvsm_s_conf0.1_n		92.93 65	93.16 65	92.24 157	90.52 347	81.92 163	98.42 54	96.24 149	91.17 49	96.02 44	98.35 51	75.34 190	99.74 54	97.84 34	94.58 149	95.05 284

UGNet		87.73 235	86.55 242	91.27 223	95.16 160	79.11 273	96.35 227	96.23 150	88.14 101	87.83 189	90.48 323	50.65 427	99.09 124	80.13 285	94.03 155	95.60 265
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		78.14 390	75.42 398	86.31 365	88.33 394	79.24 267	94.41 337	96.22 151	73.51 417	69.81 423	85.52 408	55.43 406	95.75 346	47.65 485	67.86 419	83.95 462

FOURS1					98.51 45	78.01 316	98.13 71	96.21 152	83.04 273	94.39 72

MP-MVS		92.61 84	92.67 76	92.42 144	98.13 62	79.73 255	97.33 137	96.20 153	85.63 185	90.53 133	97.66 94	78.14 120	99.70 65	92.12 123	98.30 54	97.85 120
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PAPR		92.74 72	92.17 93	94.45 38	98.89 26	84.87 86	97.20 144	96.20 153	87.73 113	88.40 174	98.12 64	78.71 109	99.76 46	87.99 202	96.28 120	98.74 50

SD-MVS		94.84 20	95.02 25	94.29 43	97.87 70	84.61 89	97.76 99	96.19 155	89.59 75	96.66 33	98.17 61	84.33 47	99.60 77	96.09 57	98.50 42	98.66 57
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		91.71 111	91.85 98	91.29 222	94.94 168	82.69 133	87.89 445	96.17 156	85.94 178	87.27 198	94.31 244	90.27 9	95.65 353	94.04 88	95.86 133	95.53 269

fmvsm_l_conf0.5_n		94.89 18	95.24 19	93.86 59	94.42 189	84.61 89	99.13 15	96.15 157	92.06 39	97.92 6	98.52 34	84.52 45	99.74 54	98.76 10	95.67 136	97.22 187

CHOSEN 1792x2688		91.07 129	90.21 141	93.64 74	95.18 159	83.53 114	96.26 235	96.13 158	88.92 82	84.90 237	93.10 279	72.86 226	99.62 76	88.86 183	95.67 136	97.79 127

PAPM_NR		91.46 116	90.82 121	93.37 90	98.50 46	81.81 172	95.03 323	96.13 158	84.65 219	86.10 223	97.65 98	79.24 99	99.75 51	83.20 254	96.88 105	98.56 62

CostFormer		89.08 191	88.39 194	91.15 230	93.13 237	79.15 272	88.61 437	96.11 160	83.14 270	89.58 149	86.93 382	83.83 58	96.87 294	88.22 201	85.92 288	97.42 170

mPP-MVS		91.88 106	91.82 99	92.07 172	98.38 50	78.63 293	97.29 139	96.09 161	85.12 206	88.45 173	97.66 94	75.53 180	99.68 68	89.83 166	98.02 61	97.88 115

APD-MVS		93.61 49	93.59 53	93.69 71	98.76 30	83.26 120	97.21 142	96.09 161	82.41 290	94.65 69	98.21 56	81.96 72	98.81 141	94.65 80	98.36 51	99.01 32
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MDTV_nov1_ep13			83.69 290		94.09 203	81.01 197	86.78 454	96.09 161	83.81 254	84.75 240	84.32 423	74.44 206	96.54 308	63.88 423	85.07 297

FA-MVS(test-final)		87.71 238	86.23 246	92.17 165	94.19 196	80.55 220	87.16 451	96.07 164	82.12 295	85.98 224	88.35 358	72.04 248	98.49 156	80.26 282	89.87 225	97.48 162

KinetiMVS		89.13 190	87.95 203	92.65 126	92.16 295	82.39 146	97.04 164	96.05 165	86.59 159	88.08 184	94.85 226	61.54 353	98.38 165	81.28 274	93.99 160	97.19 194

QAPM		86.88 252	84.51 275	93.98 55	94.04 205	85.89 49	97.19 145	96.05 165	73.62 416	75.12 371	95.62 178	62.02 348	99.74 54	70.88 385	96.06 128	96.30 244

MP-MVS-pluss		92.58 85	92.35 84	93.29 91	97.30 98	82.53 136	96.44 217	96.04 167	84.68 218	89.12 159	98.37 49	77.48 132	99.74 54	93.31 101	98.38 49	97.59 148
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.1_n_a		92.38 92	92.49 81	92.06 173	88.08 396	81.62 181	97.97 83	96.01 168	90.62 58	96.58 35	98.33 52	74.09 210	99.71 62	97.23 47	93.46 171	94.86 288

fmvsm_s_conf0.5_n_9		94.52 29	95.22 20	92.41 145	95.79 135	78.61 294	98.73 38	96.00 169	94.91 8	97.73 13	98.73 21	79.09 102	99.79 37	99.14 4	96.86 107	98.83 45

fmvsm_l_conf0.5_n_a		94.91 16	95.30 18	93.72 68	94.50 186	84.30 96	99.14 14	96.00 169	91.94 42	97.91 8	98.60 26	84.78 42	99.77 44	98.84 8	96.03 129	97.08 205

tpm2		87.35 246	86.26 244	90.62 249	92.93 251	78.67 292	88.06 444	95.99 171	79.33 354	87.40 193	86.43 393	80.28 83	96.40 312	80.23 283	85.73 292	96.79 223

SDMVSNet		87.02 249	85.61 255	91.24 225	94.14 199	83.30 119	93.88 358	95.98 172	84.30 234	79.63 314	92.01 297	58.23 374	97.68 204	90.28 163	82.02 322	92.75 322

DeepC-MVS	86.58 3	91.53 115	91.06 117	92.94 110	94.52 181	81.89 166	95.95 259	95.98 172	90.76 56	83.76 260	96.76 143	73.24 222	99.71 62	91.67 131	96.96 101	97.22 187
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 45	94.53 32	92.20 163	94.41 190	80.04 244	98.90 33	95.96 174	94.53 12	97.63 19	98.58 27	75.95 170	99.79 37	98.25 18	96.60 115	96.77 225

test-LLR		88.48 211	87.98 202	89.98 273	92.26 286	77.23 341	97.11 156	95.96 174	83.76 256	86.30 220	91.38 309	72.30 239	96.78 301	80.82 276	91.92 195	95.94 251

test-mter		88.95 195	88.60 185	89.98 273	92.26 286	77.23 341	97.11 156	95.96 174	85.32 195	86.30 220	91.38 309	76.37 159	96.78 301	80.82 276	91.92 195	95.94 251

DP-MVS Recon		91.72 110	90.85 120	94.34 41	99.50 1	85.00 83	98.51 49	95.96 174	80.57 322	88.08 184	97.63 100	76.84 147	99.89 11	85.67 226	94.88 144	98.13 93

reproduce-ours		92.70 78	93.02 66	91.75 196	97.45 87	77.77 328	96.16 245	95.94 178	84.12 239	92.45 97	98.43 42	80.06 88	99.24 105	95.35 70	97.18 91	98.24 83

our_new_method		92.70 78	93.02 66	91.75 196	97.45 87	77.77 328	96.16 245	95.94 178	84.12 239	92.45 97	98.43 42	80.06 88	99.24 105	95.35 70	97.18 91	98.24 83

cdsmvs_eth3d_5k		21.43 491	28.57 489	0.00 536	0.00 560	0.00 563	0.00 548	95.93 180	0.00 555	0.00 556	97.66 94	63.57 332	0.00 557	0.00 555	0.00 555	0.00 552

reproduce_model		92.53 87	92.87 71	91.50 212	97.41 91	77.14 345	96.02 255	95.91 181	83.65 261	92.45 97	98.39 46	79.75 93	99.21 109	95.27 73	96.98 100	98.14 91

fmvsm_s_conf0.5_n_5		93.57 52	93.75 48	93.01 105	92.87 253	82.73 132	98.93 32	95.90 182	90.96 55	95.61 49	98.39 46	76.57 153	99.63 74	98.32 15	96.24 121	96.68 231

fmvsm_s_conf0.5_n_2		92.97 63	93.38 61	91.73 199	94.10 202	80.64 215	98.96 30	95.89 183	94.09 16	97.05 26	98.40 45	68.92 286	99.80 33	98.53 13	94.50 151	94.74 292

hse-mvs2		88.22 220	88.21 198	88.25 317	93.54 218	73.41 389	95.41 300	95.89 183	90.39 64	92.22 104	94.22 248	74.70 200	96.66 306	93.14 105	64.37 442	94.69 297

AUN-MVS		86.25 266	85.57 256	88.26 315	93.57 217	73.38 390	95.45 298	95.88 185	83.94 247	85.47 230	94.21 249	73.70 218	96.67 305	83.54 250	64.41 441	94.73 296

TAMVS		88.48 211	87.79 207	90.56 251	91.09 334	79.18 270	96.45 216	95.88 185	83.64 262	83.12 272	93.33 274	75.94 171	95.74 349	82.40 261	88.27 262	96.75 228

PVSNet_Blended_VisFu		91.24 123	90.77 122	92.66 125	95.09 162	82.40 144	97.77 97	95.87 187	88.26 97	86.39 218	93.94 261	76.77 150	99.27 103	88.80 189	94.00 158	96.31 243

OpenMVS	79.58 14	86.09 267	83.62 297	93.50 83	90.95 336	86.71 37	97.44 126	95.83 188	75.35 401	72.64 394	95.72 168	57.42 392	99.64 72	71.41 379	95.85 134	94.13 305

CDS-MVSNet		89.50 177	88.96 178	91.14 231	91.94 311	80.93 205	97.09 160	95.81 189	84.26 237	84.72 241	94.20 250	80.31 82	95.64 354	83.37 253	88.96 241	96.85 221
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PS-MVSNAJ		94.17 39	93.52 56	96.10 10	95.65 139	92.35 2	98.21 66	95.79 190	92.42 31	96.24 40	98.18 58	71.04 261	99.17 117	96.77 53	97.39 83	96.79 223

testing3		80.74 365	81.17 338	79.44 444	91.15 332	63.48 466	97.16 150	95.76 191	80.83 315	71.36 405	93.15 278	78.22 118	87.30 482	43.19 492	79.67 333	87.55 421

SR-MVS		92.16 97	92.27 88	91.83 194	98.37 51	78.41 300	96.67 201	95.76 191	82.19 294	91.97 110	98.07 71	76.44 156	98.64 145	93.71 93	97.27 88	98.45 68

3Dnovator+	82.88 8	89.63 175	87.85 205	94.99 24	94.49 187	86.76 36	97.84 91	95.74 193	86.10 169	75.47 368	96.02 159	65.00 321	99.51 89	82.91 258	97.07 98	98.72 55

HPM-MVS		91.62 113	91.53 106	91.89 185	97.88 69	79.22 269	96.99 166	95.73 194	82.07 296	89.50 153	97.19 123	75.59 178	98.93 136	90.91 141	97.94 63	97.54 152
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ab-mvs		87.08 248	84.94 271	93.48 85	93.34 228	83.67 111	88.82 434	95.70 195	81.18 308	84.55 245	90.14 331	62.72 337	98.94 135	85.49 228	82.54 318	97.85 120

guyue		89.85 168	89.33 169	91.40 218	92.53 270	80.15 240	96.82 186	95.68 196	89.66 74	86.43 217	94.23 247	67.00 303	97.16 268	91.96 128	89.65 227	96.89 217

xiu_mvs_v2_base		93.92 46	93.26 62	95.91 12	95.07 164	92.02 6	98.19 67	95.68 196	92.06 39	96.01 45	98.14 63	70.83 266	98.96 131	96.74 55	96.57 116	96.76 227

CP-MVSNet		81.01 362	80.08 354	83.79 407	87.91 398	70.51 424	94.29 348	95.65 198	80.83 315	72.54 396	88.84 346	63.71 331	92.32 441	68.58 398	68.36 413	88.55 395

PatchmatchNet		86.83 254	85.12 268	91.95 182	94.12 201	82.27 149	86.55 456	95.64 199	84.59 221	82.98 275	84.99 418	77.26 135	95.96 333	68.61 397	91.34 206	97.64 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
API-MVS		90.18 160	88.97 177	93.80 61	98.66 34	82.95 127	97.50 122	95.63 200	75.16 404	86.31 219	97.69 92	72.49 234	99.90 9	81.26 275	96.07 127	98.56 62

BridgeMVS		94.60 27	94.30 40	95.48 17	96.45 108	88.82 15	96.33 229	95.58 201	91.12 50	95.84 47	93.87 263	83.47 60	98.37 166	97.26 46	98.81 24	99.24 24

AdaColmap		88.81 201	87.61 213	92.39 146	99.33 5	79.95 245	96.70 199	95.58 201	77.51 379	83.05 274	96.69 147	61.90 351	99.72 59	84.29 236	93.47 170	97.50 160

SCA		85.63 276	83.64 296	91.60 207	92.30 279	81.86 168	92.88 385	95.56 203	84.85 212	82.52 276	85.12 416	58.04 377	95.39 364	73.89 362	87.58 271	97.54 152

dp		84.30 308	82.31 321	90.28 263	94.24 195	77.97 317	86.57 455	95.53 204	79.94 344	80.75 300	85.16 414	71.49 257	96.39 313	63.73 424	83.36 307	96.48 236

HyFIR lowres test		89.36 184	88.60 185	91.63 206	94.91 170	80.76 212	95.60 292	95.53 204	82.56 287	84.03 253	91.24 312	78.03 121	96.81 298	87.07 215	88.41 260	97.32 180

WBMVS		87.73 235	86.79 236	90.56 251	95.61 141	85.68 56	97.63 107	95.52 206	83.77 255	78.30 326	88.44 356	86.14 35	95.78 343	82.54 260	73.15 378	90.21 344

APD-MVS_3200maxsize		91.23 124	91.35 108	90.89 242	97.89 68	76.35 358	96.30 232	95.52 206	79.82 345	91.03 127	97.88 85	74.70 200	98.54 153	92.11 124	96.89 104	97.77 128

lupinMVS		93.87 47	93.58 54	94.75 31	93.00 241	88.08 20	99.15 12	95.50 208	91.03 53	94.90 63	97.66 94	78.84 106	97.56 216	94.64 81	97.46 78	98.62 60

tt0805		81.20 359	79.06 368	87.61 336	86.50 412	72.97 399	93.66 362	95.48 209	74.11 412	76.23 356	91.99 299	41.36 466	97.40 246	77.44 321	74.78 367	92.45 325

HPM-MVS_fast		90.38 155	90.17 143	91.03 234	97.61 79	77.35 339	97.15 152	95.48 209	79.51 351	88.79 166	96.90 135	71.64 254	98.81 141	87.01 216	97.44 80	96.94 213

VPNet		84.69 298	82.92 311	90.01 271	89.01 381	83.45 116	96.71 197	95.46 211	85.71 184	79.65 313	92.18 296	56.66 398	96.01 329	83.05 257	67.84 420	90.56 338

114514_t		88.79 203	87.57 215	92.45 140	98.21 59	81.74 174	96.99 166	95.45 212	75.16 404	82.48 277	95.69 171	68.59 288	98.50 155	80.33 280	95.18 141	97.10 200

SR-MVS-dyc-post		91.29 122	91.45 107	90.80 244	97.76 75	76.03 363	96.20 242	95.44 213	80.56 323	90.72 131	97.84 86	75.76 175	98.61 146	91.99 125	96.79 110	97.75 130

RE-MVS-def			91.18 115		97.76 75	76.03 363	96.20 242	95.44 213	80.56 323	90.72 131	97.84 86	73.36 221		91.99 125	96.79 110	97.75 130

JIA-IIPM		79.00 381	77.20 380	84.40 402	89.74 369	64.06 463	75.30 494	95.44 213	62.15 471	81.90 288	59.08 506	78.92 104	95.59 358	66.51 410	85.78 291	93.54 315

RPMNet		79.85 371	75.92 391	91.64 204	90.16 357	79.75 252	79.02 486	95.44 213	58.43 489	82.27 284	72.55 489	73.03 225	98.41 164	46.10 487	86.25 282	96.75 228

MVSMamba_PlusPlus		92.37 93	91.55 105	94.83 28	95.37 149	87.69 25	95.60 292	95.42 217	74.65 409	93.95 78	92.81 283	83.11 63	97.70 202	94.49 82	98.53 39	99.11 29

DU-MVS		84.57 303	83.33 303	88.28 314	88.76 382	79.36 264	96.43 219	95.41 218	85.42 193	78.11 328	90.82 318	67.61 294	95.14 383	79.14 298	68.30 414	90.33 342

EI-MVSNet		85.80 272	85.20 264	87.59 338	91.55 323	77.41 337	95.13 317	95.36 219	80.43 328	80.33 306	94.71 231	73.72 216	95.97 330	76.96 326	78.64 343	89.39 359

MVSTER		89.25 188	88.92 180	90.24 264	95.98 124	84.66 88	96.79 189	95.36 219	87.19 137	80.33 306	90.61 322	90.02 12	95.97 330	85.38 229	78.64 343	90.09 349

CPTT-MVS		89.72 172	89.87 158	89.29 290	98.33 53	73.30 392	97.70 103	95.35 221	75.68 399	87.40 193	97.44 110	70.43 270	98.25 171	89.56 175	96.90 103	96.33 242

EIA-MVS		91.73 108	92.05 96	90.78 246	94.52 181	76.40 357	98.06 77	95.34 222	89.19 80	88.90 164	97.28 119	77.56 130	97.73 201	90.77 147	96.86 107	98.20 85

tpmvs		83.04 329	80.77 343	89.84 279	95.43 146	77.96 318	85.59 462	95.32 223	75.31 403	76.27 355	83.70 429	73.89 212	97.41 244	59.53 444	81.93 324	94.14 304

usedtu_dtu_shiyan1		85.03 291	83.24 304	90.37 258	86.62 410	86.24 40	96.23 238	95.30 224	84.55 223	77.22 337	88.47 354	67.85 290	95.27 372	76.59 329	76.35 355	89.61 356

FE-MVSNET3		85.03 291	83.24 304	90.37 258	86.62 410	86.24 40	96.23 238	95.30 224	84.55 223	77.22 337	88.47 354	67.85 290	95.27 372	76.59 329	76.35 355	89.61 356

PS-CasMVS		80.27 369	79.18 365	83.52 413	87.56 402	69.88 430	94.08 352	95.29 226	80.27 335	72.08 399	88.51 353	59.22 368	92.23 443	67.49 400	68.15 416	88.45 401

TSAR-MVS + GP.		94.35 34	94.50 33	93.89 58	97.38 96	83.04 125	98.10 73	95.29 226	91.57 44	93.81 79	97.45 107	86.64 30	99.43 94	96.28 56	94.01 157	99.20 26

tpmrst		88.36 215	87.38 221	91.31 220	94.36 192	79.92 246	87.32 449	95.26 228	85.32 195	88.34 175	86.13 399	80.60 79	96.70 303	83.78 242	85.34 296	97.30 183

SSC-MVS3.2		81.06 360	79.49 364	85.75 376	89.78 365	73.00 398	94.40 340	95.23 229	83.76 256	76.61 348	87.82 367	49.48 434	94.88 396	66.80 404	71.56 385	89.38 361

ETV-MVS		92.72 75	92.87 71	92.28 155	94.54 180	81.89 166	97.98 81	95.21 230	89.77 73	93.11 89	96.83 139	77.23 139	97.50 229	95.74 63	95.38 140	97.44 169

NR-MVSNet		83.35 321	81.52 334	88.84 299	88.76 382	81.31 189	94.45 336	95.16 231	84.65 219	67.81 430	90.82 318	70.36 271	94.87 397	74.75 353	66.89 430	90.33 342

test_fmvsmconf0.1_n		93.08 61	93.22 64	92.65 126	88.45 391	80.81 210	99.00 28	95.11 232	93.21 24	94.00 77	97.91 82	76.84 147	99.59 78	97.91 29	96.55 117	97.54 152

jason		92.73 73	92.23 90	94.21 47	90.50 348	87.30 31	98.65 43	95.09 233	90.61 59	92.76 96	97.13 125	75.28 191	97.30 258	93.32 100	96.75 112	98.02 100
jason: jason.
tpm cat1		83.63 318	81.38 335	90.39 257	93.53 223	78.19 313	85.56 463	95.09 233	70.78 442	78.51 323	83.28 434	74.80 199	97.03 276	66.77 405	84.05 302	95.95 250

cascas		86.50 258	84.48 277	92.55 135	92.64 265	85.95 46	97.04 164	95.07 235	75.32 402	80.50 302	91.02 315	54.33 415	97.98 186	86.79 220	87.62 269	93.71 313

GDP-MVS		92.85 70	92.55 80	93.75 64	92.82 254	85.76 52	97.63 107	95.05 236	88.34 95	93.15 88	97.10 128	86.92 28	98.01 184	87.95 203	94.00 158	97.47 163

CVMVSNet		84.83 296	85.57 256	82.63 422	91.55 323	60.38 479	95.13 317	95.03 237	80.60 321	82.10 286	94.71 231	66.40 311	90.19 465	74.30 359	90.32 219	97.31 182

test0.0.03 1		82.79 333	82.48 319	83.74 409	86.81 408	72.22 402	96.52 210	95.03 237	83.76 256	73.00 390	93.20 275	72.30 239	88.88 470	64.15 422	77.52 352	90.12 347

PMMVS		89.46 179	89.92 155	88.06 325	94.64 175	69.57 435	96.22 240	94.95 239	87.27 133	91.37 120	96.54 149	65.88 313	97.39 248	88.54 195	93.89 162	97.23 186

CS-MVS		92.73 73	93.48 58	90.48 254	96.27 113	75.93 368	98.55 47	94.93 240	89.32 78	94.54 71	97.67 93	78.91 105	97.02 277	93.80 90	97.32 87	98.49 65

Anonymous20240529		83.15 326	80.60 347	90.80 244	95.74 136	78.27 306	96.81 188	94.92 241	60.10 482	81.89 289	92.54 288	45.82 449	98.82 140	79.25 297	78.32 349	95.31 275

mvs_anonymous		88.68 204	87.62 212	91.86 187	94.80 173	81.69 177	93.53 368	94.92 241	82.03 297	78.87 321	90.43 325	75.77 174	95.34 367	85.04 231	93.16 175	98.55 64

CLD-MVS		87.97 228	87.48 218	89.44 288	92.16 295	80.54 224	98.14 68	94.92 241	91.41 46	79.43 316	95.40 190	62.34 340	97.27 261	90.60 151	82.90 313	90.50 339
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		90.54 145	89.54 164	93.55 80	92.31 276	87.58 27	96.99 166	94.87 244	87.23 134	93.27 84	97.56 103	57.43 389	98.32 168	92.72 112	93.46 171	94.74 292

xiu_mvs_v1_base		90.54 145	89.54 164	93.55 80	92.31 276	87.58 27	96.99 166	94.87 244	87.23 134	93.27 84	97.56 103	57.43 389	98.32 168	92.72 112	93.46 171	94.74 292

xiu_mvs_v1_base_debi		90.54 145	89.54 164	93.55 80	92.31 276	87.58 27	96.99 166	94.87 244	87.23 134	93.27 84	97.56 103	57.43 389	98.32 168	92.72 112	93.46 171	94.74 292

fmvsm_s_conf0.5_n_11		94.41 32	95.19 21	92.09 169	95.65 139	80.91 207	99.23 7	94.85 247	94.92 7	97.68 16	98.82 12	79.31 96	99.78 40	98.83 9	97.38 84	95.60 265

GA-MVS		85.79 273	84.04 288	91.02 236	89.47 377	80.27 233	96.90 179	94.84 248	85.57 187	80.88 297	89.08 342	56.56 399	96.47 311	77.72 314	85.35 295	96.34 240

TranMVSNet+NR-MVSNet		83.24 325	81.71 330	87.83 329	87.71 400	78.81 283	96.13 250	94.82 249	84.52 225	76.18 358	90.78 320	64.07 329	94.60 408	74.60 357	66.59 433	90.09 349

HQP3-MVS								94.80 250							83.01 310

HQP-MVS		87.91 230	87.55 216	88.98 297	92.08 301	78.48 296	97.63 107	94.80 250	90.52 60	82.30 280	94.56 235	65.40 317	97.32 256	87.67 209	83.01 310	91.13 331

TAPA-MVS	81.61 12	85.02 293	83.67 292	89.06 294	96.79 104	73.27 395	95.92 262	94.79 252	74.81 407	80.47 303	96.83 139	71.07 260	98.19 174	49.82 480	92.57 181	95.71 262
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PEN-MVS		79.47 377	78.26 373	83.08 416	86.36 414	68.58 439	93.85 360	94.77 253	79.76 346	71.37 404	88.55 350	59.79 360	92.46 437	64.50 419	65.40 438	88.19 406

SPE-MVS-test		92.98 62	93.67 51	90.90 241	96.52 107	76.87 347	98.68 41	94.73 254	90.36 66	94.84 65	97.89 84	77.94 122	97.15 272	94.28 86	97.80 68	98.70 56

NormalMVS		92.88 67	92.97 69	92.59 133	97.80 71	82.02 155	97.94 84	94.70 255	92.34 32	92.15 106	96.53 150	77.03 142	98.57 149	91.13 137	97.12 95	97.19 194

Elysia		85.62 277	83.66 293	91.51 210	88.76 382	82.21 152	95.15 315	94.70 255	76.96 389	84.13 250	92.20 294	50.81 425	97.26 262	77.81 309	92.42 186	95.06 282

StellarMVS		85.62 277	83.66 293	91.51 210	88.76 382	82.21 152	95.15 315	94.70 255	76.96 389	84.13 250	92.20 294	50.81 425	97.26 262	77.81 309	92.42 186	95.06 282

balanced_ft_v1		92.00 101	91.12 116	94.64 34	96.35 110	86.78 34	94.96 324	94.70 255	87.65 118	90.20 140	93.01 281	69.71 276	98.02 182	97.40 43	96.13 125	99.11 29

HQP_MVS		87.50 244	87.09 228	88.74 302	91.86 313	77.96 318	97.18 146	94.69 259	89.89 71	81.33 293	94.15 253	64.77 324	97.30 258	87.08 213	82.82 314	90.96 333

plane_prior5								94.69 259					97.30 258	87.08 213	82.82 314	90.96 333

tpm		85.55 280	84.47 278	88.80 301	90.19 356	75.39 375	88.79 435	94.69 259	84.83 213	83.96 256	85.21 412	78.22 118	94.68 406	76.32 336	78.02 351	96.34 240

FMVSNet3		84.71 297	82.71 316	90.70 248	94.55 179	87.71 24	95.92 262	94.67 262	81.73 302	75.82 363	88.08 363	66.99 304	94.47 411	71.23 381	75.38 362	89.91 353

UA-Net		88.92 197	88.48 193	90.24 264	94.06 204	77.18 343	93.04 381	94.66 263	87.39 128	91.09 125	93.89 262	74.92 196	98.18 175	75.83 340	91.43 203	95.35 274

LFMVS		89.27 187	87.64 210	94.16 54	97.16 100	85.52 63	97.18 146	94.66 263	79.17 359	89.63 148	96.57 148	55.35 407	98.22 172	89.52 176	89.54 228	98.74 50

MVS_Test		90.29 159	89.18 171	93.62 76	95.23 153	84.93 84	94.41 337	94.66 263	84.31 232	90.37 139	91.02 315	75.13 193	97.82 197	83.11 256	94.42 152	98.12 94

sasdasda		92.27 94	91.22 111	95.41 18	95.80 133	88.31 16	97.09 160	94.64 266	88.49 90	92.99 92	97.31 114	72.68 230	98.57 149	93.38 98	88.58 251	99.36 17

canonicalmvs		92.27 94	91.22 111	95.41 18	95.80 133	88.31 16	97.09 160	94.64 266	88.49 90	92.99 92	97.31 114	72.68 230	98.57 149	93.38 98	88.58 251	99.36 17

VDDNet		86.44 259	84.51 275	92.22 160	91.56 321	81.83 170	97.10 159	94.64 266	69.50 449	87.84 188	95.19 203	48.01 439	97.92 192	89.82 167	86.92 275	96.89 217

baseline1		88.85 200	87.49 217	92.93 111	95.21 155	86.85 33	95.47 297	94.61 269	87.29 130	83.11 273	94.99 217	80.70 78	96.89 291	82.28 264	73.72 371	95.05 284

PatchT		79.75 372	76.85 384	88.42 307	89.55 375	75.49 374	77.37 490	94.61 269	63.07 466	82.46 278	73.32 486	75.52 181	93.41 432	51.36 474	84.43 300	96.36 238

MS-PatchMatch		83.05 328	81.82 329	86.72 360	89.64 372	79.10 274	94.88 327	94.59 271	79.70 348	70.67 412	89.65 336	50.43 429	96.82 297	70.82 388	95.99 132	84.25 459

casdiffmvs_mvg		91.13 126	90.45 131	93.17 98	92.99 244	83.58 113	97.46 125	94.56 272	87.69 115	87.19 201	94.98 218	74.50 205	97.60 210	91.88 130	92.79 179	98.34 73
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		90.76 138	90.10 144	92.74 121	92.90 252	82.56 135	94.60 334	94.56 272	87.69 115	89.06 161	95.67 172	73.76 215	97.51 228	90.43 156	92.23 193	98.16 89

OMC-MVS		88.80 202	88.16 200	90.72 247	95.30 151	77.92 321	94.81 330	94.51 274	86.80 151	84.97 236	96.85 138	67.53 297	98.60 147	85.08 230	87.62 269	95.63 263

E3new		90.90 135	90.35 137	92.55 135	93.63 214	82.40 144	96.79 189	94.49 275	87.07 142	88.54 171	95.70 169	73.85 213	97.60 210	91.23 135	91.86 197	97.64 141

MGCFI-Net		91.95 102	91.03 118	94.72 32	95.68 138	86.38 38	96.93 176	94.48 276	88.25 98	92.78 95	97.24 120	72.34 237	98.46 159	93.13 107	88.43 259	99.32 20

MVSFormer		91.36 120	90.57 126	93.73 67	93.00 241	88.08 20	94.80 331	94.48 276	80.74 318	94.90 63	97.13 125	78.84 106	95.10 386	83.77 243	97.46 78	98.02 100

test_djsdf		83.00 331	82.45 320	84.64 396	84.07 446	69.78 431	94.80 331	94.48 276	80.74 318	75.41 369	87.70 368	61.32 356	95.10 386	83.77 243	79.76 330	89.04 379

viewcassd2359sk11		90.66 141	90.06 147	92.47 138	93.22 231	82.21 152	96.70 199	94.47 279	86.94 145	88.22 180	95.50 185	73.15 223	97.59 212	90.86 143	91.48 201	97.60 147

casdiffmvs		90.95 133	90.39 133	92.63 129	92.82 254	82.53 136	96.83 183	94.47 279	87.69 115	88.47 172	95.56 181	74.04 211	97.54 223	90.90 142	92.74 180	97.83 122
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	86.77 256	85.00 270	92.08 170	92.06 304	83.07 124	92.14 397	94.47 279	79.63 349	76.90 343	94.78 228	71.15 259	99.20 114	72.87 370	91.05 212	93.98 308
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
RRT-MVS		89.67 173	88.67 183	92.67 124	94.44 188	81.08 195	94.34 341	94.45 282	86.05 171	85.79 225	92.39 290	63.39 334	98.16 176	93.22 103	93.95 161	98.76 49

VDD-MVS		88.28 218	87.02 230	92.06 173	95.09 162	80.18 239	97.55 117	94.45 282	83.09 271	89.10 160	95.92 162	47.97 440	98.49 156	93.08 109	86.91 276	97.52 158

mvsmamba		90.53 148	90.08 145	91.88 186	94.81 172	80.93 205	93.94 356	94.45 282	88.24 99	87.02 205	92.35 291	68.04 289	95.80 341	94.86 76	97.03 99	98.92 41

test_cas_vis1_n_1920		89.90 166	90.02 149	89.54 287	90.14 359	74.63 380	98.71 40	94.43 285	93.04 26	92.40 100	96.35 153	53.41 418	99.08 125	95.59 66	96.16 123	94.90 286

PLC	83.97 7	88.00 227	87.38 221	89.83 280	98.02 65	76.46 354	97.16 150	94.43 285	79.26 358	81.98 287	96.28 154	69.36 279	99.27 103	77.71 315	92.25 192	93.77 312
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LuminaMVS		88.02 226	86.89 235	91.43 216	88.65 389	83.16 122	94.84 328	94.41 287	83.67 260	86.56 216	91.95 303	62.04 347	96.88 293	89.78 168	90.06 222	94.24 301

EC-MVSNet		91.73 108	92.11 94	90.58 250	93.54 218	77.77 328	98.07 76	94.40 288	87.44 126	92.99 92	97.11 127	74.59 204	96.87 294	93.75 92	97.08 97	97.11 198

E2		90.33 156	89.65 162	92.37 147	92.66 261	81.99 158	96.58 204	94.39 289	86.71 156	87.88 186	95.25 195	72.18 241	97.56 216	90.37 159	90.88 214	97.57 149

E3		90.33 156	89.65 162	92.37 147	92.64 265	81.99 158	96.58 204	94.39 289	86.71 156	87.87 187	95.27 194	72.17 242	97.56 216	90.37 159	90.88 214	97.57 149

sd_testset		84.62 301	83.11 307	89.17 292	94.14 199	77.78 327	91.54 409	94.38 291	84.30 234	79.63 314	92.01 297	52.28 420	96.98 283	77.67 316	82.02 322	92.75 322

FMVSNet2		82.79 333	80.44 349	89.83 280	92.66 261	85.43 64	95.42 299	94.35 292	79.06 362	74.46 376	87.28 374	56.38 401	94.31 415	69.72 393	74.68 368	89.76 354

viewdifsd2359ckpt13		90.08 161	89.36 167	92.26 156	93.03 240	81.90 165	96.37 223	94.34 293	86.16 166	87.44 192	95.30 193	70.93 265	97.55 220	89.05 180	91.59 200	97.35 178

VortexMVS		85.45 283	84.40 279	88.63 304	93.25 230	81.66 178	95.39 302	94.34 293	87.15 140	75.10 372	87.65 369	66.58 310	95.19 377	86.89 217	73.21 377	89.03 381

test_vis1_n_1920		89.95 165	90.59 125	88.03 327	92.36 273	68.98 438	99.12 16	94.34 293	93.86 19	93.64 82	97.01 133	51.54 422	99.59 78	96.76 54	96.71 114	95.53 269

fmvsm_s_conf0.1_n_2		92.26 96	92.48 82	91.60 207	92.29 284	80.55 220	98.73 38	94.33 296	93.80 20	96.18 41	98.11 65	66.93 305	99.75 51	98.19 21	93.74 165	94.50 299

nrg030		86.79 255	85.43 258	90.87 243	88.76 382	85.34 66	97.06 163	94.33 296	84.31 232	80.45 304	91.98 300	72.36 236	96.36 315	88.48 198	71.13 387	90.93 335

ACMM	80.70 13	83.72 317	82.85 314	86.31 365	91.19 330	72.12 407	95.88 275	94.29 298	80.44 326	77.02 341	91.96 301	55.24 408	97.14 273	79.30 296	80.38 329	89.67 355
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Casviewmamba		90.52 150	90.00 151	92.06 173	92.72 258	80.42 229	96.87 180	94.28 299	87.45 124	87.30 196	95.73 167	73.10 224	97.67 206	90.27 164	92.29 190	98.10 96

viewmanbaseed2359cas		90.74 139	90.07 146	92.76 119	92.98 245	82.93 128	96.53 209	94.28 299	87.08 141	88.96 162	95.64 174	72.03 249	97.58 214	90.85 144	92.26 191	97.76 129

E4		89.85 168	89.06 172	92.22 160	91.88 312	81.63 180	96.43 219	94.27 301	86.32 164	87.29 197	94.97 219	70.81 267	97.52 226	89.57 173	90.00 223	97.51 159

XXY-MVS		83.84 314	82.00 326	89.35 289	87.13 405	81.38 186	95.72 283	94.26 302	80.15 337	75.92 362	90.63 321	61.96 350	96.52 309	78.98 301	73.28 376	90.14 346

hybridcas		90.40 152	89.67 161	92.60 132	92.39 271	82.32 148	96.83 183	94.25 303	87.19 137	86.59 215	95.43 189	72.54 232	97.65 207	88.77 191	93.02 177	97.82 124

AstraMVS		88.99 194	88.35 195	90.92 239	90.81 343	78.29 304	96.73 194	94.24 304	89.96 70	86.13 222	95.04 212	62.12 346	97.41 244	92.54 117	87.57 272	97.06 207

Syy-MVS		77.97 394	78.05 374	77.74 453	92.13 298	56.85 487	93.97 354	94.23 305	82.43 288	73.39 383	93.57 271	57.95 380	87.86 477	32.40 506	82.34 319	88.51 396

myMVS_eth3d		81.93 346	82.18 322	81.18 434	92.13 298	67.18 446	93.97 354	94.23 305	82.43 288	73.39 383	93.57 271	76.98 145	87.86 477	50.53 478	82.34 319	88.51 396

E5new		89.38 180	88.55 188	91.85 189	91.77 317	80.97 199	95.90 268	94.22 307	86.03 173	86.88 207	94.90 222	69.05 282	97.47 233	88.86 183	89.35 230	97.10 200

E6new		89.37 182	88.55 188	91.85 189	91.75 319	80.97 199	95.90 268	94.22 307	86.03 173	86.88 207	94.91 220	69.05 282	97.47 233	88.86 183	89.34 232	97.10 200

E6		89.37 182	88.55 188	91.85 189	91.75 319	80.97 199	95.90 268	94.22 307	86.03 173	86.88 207	94.91 220	69.05 282	97.47 233	88.86 183	89.34 232	97.10 200

E5		89.38 180	88.55 188	91.85 189	91.77 317	80.97 199	95.90 268	94.22 307	86.03 173	86.88 207	94.90 222	69.05 282	97.47 233	88.86 183	89.35 230	97.10 200

cl22		85.11 290	84.17 284	87.92 328	95.06 166	78.82 281	95.51 295	94.22 307	79.74 347	76.77 344	87.92 365	75.96 169	95.68 350	79.93 288	72.42 380	89.27 367

PRO-TEST		89.47 178	90.53 127	86.28 368	95.98 124	61.97 472	94.18 351	94.20 312	90.44 63	83.39 269	92.72 287	69.11 281	97.91 193	97.29 45	97.48 77	98.96 38

OPM-MVS		85.84 271	85.10 269	88.06 325	88.34 393	77.83 325	95.72 283	94.20 312	87.89 110	80.45 304	94.05 255	58.57 371	97.26 262	83.88 240	82.76 316	89.09 373
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet (Re-imp)		88.88 199	88.87 182	88.91 298	93.89 208	74.43 383	96.93 176	94.19 314	84.39 230	83.22 271	95.67 172	78.24 117	94.70 404	78.88 302	94.40 153	97.61 146

Anonymous20231211		79.72 373	77.19 381	87.33 346	95.59 143	77.16 344	95.18 314	94.18 315	59.31 486	72.57 395	86.20 398	47.89 442	95.66 351	74.53 358	69.24 406	89.18 370

PS-MVSNAJss		84.91 295	84.30 281	86.74 356	85.89 425	74.40 384	94.95 325	94.16 316	83.93 248	76.45 350	90.11 332	71.04 261	95.77 344	83.16 255	79.02 340	90.06 351

LPG-MVS_test		84.20 309	83.49 301	86.33 362	90.88 337	73.06 396	95.28 303	94.13 317	82.20 292	76.31 352	93.20 275	54.83 412	96.95 285	83.72 245	80.83 327	88.98 386

LGP-MVS_train				86.33 362	90.88 337	73.06 396		94.13 317	82.20 292	76.31 352	93.20 275	54.83 412	96.95 285	83.72 245	80.83 327	88.98 386

V42		83.04 329	81.53 333	87.57 340	86.27 417	79.09 275	95.87 276	94.11 319	80.35 332	77.22 337	86.79 385	65.32 319	96.02 328	77.74 313	70.14 394	87.61 417

XVG-OURS-SEG-HR		85.74 274	85.16 267	87.49 344	90.22 354	71.45 418	91.29 410	94.09 320	81.37 305	83.90 258	95.22 200	60.30 359	97.53 225	85.58 227	84.42 301	93.50 316

casdiffseed414692147		88.22 220	86.93 234	92.08 170	92.04 305	81.84 169	96.08 253	94.08 321	84.56 222	85.59 227	93.98 260	67.37 299	97.42 242	80.12 286	88.52 255	96.99 209

XVG-OURS		85.18 289	84.38 280	87.59 338	90.42 350	71.73 415	91.06 414	94.07 322	82.00 298	83.29 270	95.08 211	56.42 400	97.55 220	83.70 247	83.42 306	93.49 317

viewmacassd2359aftdt		89.89 167	89.01 176	92.52 137	91.56 321	82.46 142	96.32 230	94.06 323	86.41 161	88.11 183	95.01 215	69.68 277	97.47 233	88.73 193	91.19 207	97.63 143

miper_enhance_ethall		85.95 270	85.20 264	88.19 322	94.85 171	79.76 250	96.00 256	94.06 323	82.98 277	77.74 332	88.76 347	79.42 94	95.46 363	80.58 278	72.42 380	89.36 365

gbinet_0.2-2-1-0.02		78.67 386	75.67 395	87.70 332	80.38 464	79.60 259	96.25 236	94.03 325	72.51 430	71.41 403	83.33 433	55.97 404	94.45 412	73.37 368	53.73 475	89.04 379

v2v482		83.46 320	81.86 328	88.25 317	86.19 418	79.65 257	96.34 228	94.02 326	81.56 304	77.32 335	88.23 360	65.62 314	96.03 327	77.77 312	69.72 402	89.09 373

jajsoiax		82.12 344	81.15 339	85.03 390	84.19 444	70.70 423	94.22 349	93.95 327	83.07 272	73.48 382	89.75 334	49.66 433	95.37 366	82.24 265	79.76 330	89.02 383

onestephybrid01		90.58 144	90.37 135	91.20 229	92.69 259	78.81 283	96.04 254	93.94 328	86.55 160	90.40 137	95.64 174	72.84 227	97.43 241	93.77 91	91.46 202	97.36 176

test_fmvsmconf0.01_n		91.08 128	90.68 124	92.29 154	82.43 456	80.12 241	97.94 84	93.93 329	92.07 38	91.97 110	97.60 101	67.56 296	99.53 86	97.09 49	95.56 139	97.21 190

v1144		82.90 332	81.27 337	87.78 331	86.29 416	79.07 276	96.14 248	93.93 329	80.05 341	77.38 333	86.80 384	65.50 315	95.93 335	75.21 350	70.13 395	88.33 404

KD-MVS_2432*1600		77.63 397	74.92 402	85.77 374	90.86 340	79.44 261	88.08 442	93.92 331	76.26 395	67.05 434	82.78 436	72.15 244	91.92 446	61.53 432	41.62 500	85.94 444

miper_refine_blended		77.63 397	74.92 402	85.77 374	90.86 340	79.44 261	88.08 442	93.92 331	76.26 395	67.05 434	82.78 436	72.15 244	91.92 446	61.53 432	41.62 500	85.94 444

test_fmvsmvis_n_1920		92.12 98	92.10 95	92.17 165	90.87 339	81.04 196	98.34 61	93.90 333	92.71 28	87.24 199	97.90 83	74.83 198	99.72 59	96.96 51	96.20 122	95.76 261

UnsupCasMVSNet_eth		73.25 424	70.57 430	81.30 432	77.53 479	66.33 453	87.24 450	93.89 334	80.38 329	57.90 479	81.59 448	42.91 459	90.56 461	65.18 416	48.51 488	87.01 428

v7n		79.32 379	77.34 379	85.28 386	84.05 447	72.89 401	93.38 370	93.87 335	75.02 406	70.68 411	84.37 422	59.58 363	95.62 356	67.60 399	67.50 423	87.32 425

dcpmvs_2		93.10 60	93.46 59	92.02 179	97.77 73	79.73 255	94.82 329	93.86 336	86.91 146	91.33 121	96.76 143	85.20 38	98.06 179	96.90 52	97.60 74	98.27 81

Vis-MVSNet		88.67 205	87.82 206	91.24 225	92.68 260	78.82 281	96.95 174	93.85 337	87.55 121	87.07 204	95.13 208	63.43 333	97.21 265	77.58 318	96.15 124	97.70 136
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
icg_test_0407_2		87.55 242	86.59 241	90.43 255	92.30 279	78.81 283	92.17 396	93.84 338	85.14 202	83.68 261	94.49 239	67.75 292	95.02 394	81.33 269	88.61 245	97.46 164

IMVS_0407		87.82 231	86.72 238	91.14 231	92.30 279	78.81 283	93.34 372	93.84 338	85.14 202	83.68 261	94.49 239	67.75 292	97.14 273	81.33 269	88.61 245	97.46 164

IMVS_0404		85.34 285	83.69 290	90.29 262	92.30 279	78.81 283	90.62 418	93.84 338	85.14 202	72.51 397	94.49 239	54.36 414	94.61 407	81.33 269	88.61 245	97.46 164

IMVS_0403		88.07 223	87.02 230	91.24 225	92.30 279	78.81 283	93.62 364	93.84 338	85.14 202	84.36 246	94.49 239	69.49 278	97.46 240	81.33 269	88.61 245	97.46 164

v148		82.41 341	80.89 341	86.99 354	86.18 419	76.81 349	96.27 233	93.82 342	80.49 325	75.28 370	86.11 400	67.32 301	95.75 346	75.48 347	67.03 429	88.42 402

BH-w/o		88.24 219	87.47 219	90.54 253	95.03 167	78.54 295	97.41 131	93.82 342	84.08 241	78.23 327	94.51 237	69.34 280	97.21 265	80.21 284	94.58 149	95.87 254

TR-MVS		86.30 264	84.93 272	90.42 256	94.63 176	77.58 334	96.57 206	93.82 342	80.30 333	82.42 279	95.16 205	58.74 370	97.55 220	74.88 352	87.82 267	96.13 247

dtuplus		89.18 189	88.59 187	90.96 237	91.84 316	78.40 303	95.89 272	93.81 345	83.26 267	87.77 190	95.53 182	70.57 269	97.49 231	88.57 194	90.08 221	96.99 209

v1192		82.31 342	80.55 348	87.60 337	85.94 423	78.47 299	95.85 278	93.80 346	79.33 354	76.97 342	86.51 388	63.33 335	95.87 337	73.11 369	70.13 395	88.46 400

ACMP	81.66 11	84.00 312	83.22 306	86.33 362	91.53 325	72.95 400	95.91 267	93.79 347	83.70 259	73.79 379	92.22 293	54.31 416	96.89 291	83.98 239	79.74 332	89.16 371
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v144192		82.43 338	80.73 344	87.54 341	85.81 426	78.22 308	95.98 257	93.78 348	79.09 361	77.11 340	86.49 389	64.66 328	95.91 336	74.20 360	69.42 403	88.49 398

mvs_tets		81.74 349	80.71 345	84.84 391	84.22 443	70.29 427	93.91 357	93.78 348	82.77 282	73.37 385	89.46 340	47.36 445	95.31 370	81.99 266	79.55 336	88.92 390

F-COLMAP		84.50 305	83.44 302	87.67 334	95.22 154	72.22 402	95.95 259	93.78 348	75.74 398	76.30 354	95.18 204	59.50 364	98.45 161	72.67 372	86.59 279	92.35 328

viewdifsd2359ckpt07		89.04 192	88.30 196	91.27 223	92.32 275	78.90 278	95.89 272	93.77 351	84.48 228	85.18 232	95.16 205	69.83 274	97.70 202	88.75 192	89.29 235	97.22 187

viewmambaseed2359dif		89.52 176	89.02 174	91.03 234	92.24 289	78.83 280	95.89 272	93.77 351	83.04 273	88.28 179	95.80 165	72.08 247	97.40 246	89.76 169	90.32 219	96.87 220

UniMVSNet_ETH3D		80.86 364	78.75 370	87.22 351	86.31 415	72.02 408	91.95 399	93.76 353	73.51 417	75.06 373	90.16 330	43.04 458	95.66 351	76.37 335	78.55 346	93.98 308

wanda-best-256-512		78.87 382	75.75 392	88.22 319	79.74 467	80.51 226	95.92 262	93.75 354	72.60 427	70.34 415	82.14 439	57.91 383	95.09 388	75.61 343	53.77 471	89.05 376

FE-blended-shiyan7		78.87 382	75.75 392	88.22 319	79.74 467	80.51 226	95.92 262	93.75 354	72.60 427	70.34 415	82.14 439	57.91 383	95.09 388	75.61 343	53.77 471	89.05 376

blended_shiyan6		78.74 385	75.63 397	88.07 324	79.63 471	80.10 242	95.72 283	93.73 356	72.43 432	70.17 421	82.09 444	57.69 386	95.07 391	75.47 348	53.77 471	89.03 381

blend_shiyan4		81.76 348	79.58 361	88.31 313	80.00 466	80.59 216	95.95 259	93.73 356	72.26 434	71.14 408	82.52 438	76.13 166	95.15 381	77.83 307	66.62 432	89.19 369

Fast-Effi-MVS+		87.93 229	86.94 233	90.92 239	94.04 205	79.16 271	98.26 64	93.72 358	81.29 306	83.94 257	92.90 282	69.83 274	96.68 304	76.70 328	91.74 198	96.93 214

blended_shiyan8		78.76 384	75.65 396	88.10 323	79.58 472	80.20 237	95.70 286	93.71 359	72.43 432	70.26 418	82.12 442	57.66 387	95.08 390	75.57 345	53.80 470	89.02 383

v1921920		82.02 345	80.23 352	87.41 345	85.62 427	77.92 321	95.79 282	93.69 360	78.86 365	76.67 345	86.44 391	62.50 339	95.83 339	72.69 371	69.77 401	88.47 399

DTE-MVSNet		78.37 388	77.06 382	82.32 427	85.22 434	67.17 449	93.40 369	93.66 361	78.71 367	70.53 413	88.29 359	59.06 369	92.23 443	61.38 435	63.28 448	87.56 419

v8		81.88 347	80.06 356	87.32 347	86.63 409	79.04 277	94.41 337	93.65 362	78.77 366	73.19 389	85.57 406	66.87 306	95.81 340	73.84 364	67.61 422	87.11 426

viewdifsd2359ckpt09		90.00 164	89.28 170	92.15 167	93.31 229	81.38 186	96.37 223	93.64 363	86.34 163	86.62 214	95.64 174	71.58 255	97.52 226	88.93 181	91.06 211	97.54 152

diffmvs_AUTHOR		90.86 137	90.41 132	92.24 157	92.01 307	82.22 151	96.18 244	93.64 363	87.28 131	90.46 136	95.64 174	72.82 228	97.39 248	93.17 104	92.46 185	97.11 198

diffmvs		91.17 125	90.74 123	92.44 142	93.11 239	82.50 141	96.25 236	93.62 365	87.79 111	90.40 137	95.93 160	73.44 220	97.42 242	93.62 95	92.55 182	97.41 171
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
hybrid		90.42 151	89.87 158	92.06 173	92.20 290	81.45 185	96.09 251	93.61 366	85.80 181	89.55 150	95.52 183	72.14 246	97.39 248	92.60 115	91.36 205	97.34 179

ADS-MVSNet		81.26 357	78.36 371	89.96 275	93.78 210	79.78 249	79.48 482	93.60 367	73.09 422	80.14 308	79.99 461	62.15 344	95.24 375	59.49 445	83.52 304	94.85 289

PatchMatch-RL		85.00 294	83.66 293	89.02 296	95.86 130	74.55 382	92.49 390	93.60 367	79.30 356	79.29 318	91.47 307	58.53 372	98.45 161	70.22 390	92.17 194	94.07 307

anonymousdsp		80.98 363	79.97 357	84.01 404	81.73 458	70.44 426	92.49 390	93.58 369	77.10 386	72.98 391	86.31 395	57.58 388	94.90 395	79.32 295	78.63 345	86.69 431

hybridnocas07		90.53 148	90.02 149	92.05 177	92.36 273	81.48 184	96.27 233	93.57 370	86.86 149	89.28 155	95.48 186	72.17 242	97.47 233	92.77 111	91.41 204	97.21 190

CL-MVSNet_self_test		75.81 410	74.14 411	80.83 437	78.33 477	67.79 443	94.22 349	93.52 371	77.28 383	69.82 422	81.54 450	61.47 355	89.22 469	57.59 454	53.51 476	85.48 448

viewmamba		90.30 158	89.90 156	91.48 214	92.14 297	79.76 250	95.92 262	93.50 372	87.73 113	88.32 176	95.82 163	72.39 235	97.36 255	92.19 122	91.12 210	97.30 183

miper_ehance_all_eth		84.57 303	83.60 298	87.50 342	92.64 265	78.25 307	95.40 301	93.47 373	79.28 357	76.41 351	87.64 370	76.53 154	95.24 375	78.58 304	72.42 380	89.01 385

kuosan		73.55 421	72.39 421	77.01 457	89.68 371	66.72 452	85.24 466	93.44 374	67.76 453	60.04 471	83.40 432	71.90 250	84.25 491	45.34 489	54.75 464	80.06 486

v1240		81.70 350	79.83 360	87.30 349	85.50 428	77.70 333	95.48 296	93.44 374	78.46 370	76.53 349	86.44 391	60.85 357	95.84 338	71.59 378	70.17 393	88.35 403

v10		81.43 354	79.53 363	87.11 352	86.38 413	78.87 279	94.31 343	93.43 376	77.88 374	73.24 388	85.26 410	65.44 316	95.75 346	72.14 375	67.71 421	86.72 430

IterMVS-LS		83.93 313	82.80 315	87.31 348	91.46 326	77.39 338	95.66 288	93.43 376	80.44 326	75.51 367	87.26 376	73.72 216	95.16 380	76.99 324	70.72 391	89.39 359
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		82.42 339	80.43 350	88.39 310	92.66 261	81.95 160	94.30 344	93.38 378	79.06 362	75.82 363	85.66 402	56.38 401	93.84 423	71.23 381	75.38 362	89.38 361

test1		82.42 339	80.43 350	88.39 310	92.66 261	81.95 160	94.30 344	93.38 378	79.06 362	75.82 363	85.66 402	56.38 401	93.84 423	71.23 381	75.38 362	89.38 361

FMVSNet1		79.50 376	76.54 387	88.39 310	88.47 390	81.95 160	94.30 344	93.38 378	73.14 421	72.04 400	85.66 402	43.86 452	93.84 423	65.48 414	72.53 379	89.38 361

BH-untuned		86.95 251	85.94 248	89.99 272	94.52 181	77.46 336	96.78 191	93.37 381	81.80 300	76.62 347	93.81 267	66.64 308	97.02 277	76.06 337	93.88 163	95.48 271

Effi-MVS+-dtu		84.61 302	84.90 273	83.72 410	91.96 309	63.14 468	94.95 325	93.34 382	85.57 187	79.79 312	87.12 379	61.99 349	95.61 357	83.55 249	85.83 290	92.41 326

CMPMVS	54.94 21	75.71 412	74.56 406	79.17 446	79.69 470	55.98 489	89.59 426	93.30 383	60.28 480	53.85 487	89.07 343	47.68 444	96.33 316	76.55 331	81.02 325	85.22 449
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
cl____		83.27 323	82.12 323	86.74 356	92.20 290	75.95 367	95.11 319	93.27 384	78.44 371	74.82 374	87.02 381	74.19 208	95.19 377	74.67 355	69.32 404	89.09 373

DIV-MVS_self_test		83.27 323	82.12 323	86.74 356	92.19 292	75.92 369	95.11 319	93.26 385	78.44 371	74.81 375	87.08 380	74.19 208	95.19 377	74.66 356	69.30 405	89.11 372

dmvs_re		84.10 310	82.90 312	87.70 332	91.41 327	73.28 393	90.59 419	93.19 386	85.02 208	77.96 331	93.68 268	57.92 382	96.18 323	75.50 346	80.87 326	93.63 314

miper_lstm_enhance		81.66 352	80.66 346	84.67 395	91.19 330	71.97 410	91.94 400	93.19 386	77.86 375	72.27 398	85.26 410	73.46 219	93.42 431	73.71 365	67.05 428	88.61 394

dongtai		69.47 443	68.98 439	70.93 469	86.87 407	58.45 484	88.19 440	93.18 388	63.98 464	56.04 483	80.17 460	70.97 264	79.24 498	33.46 504	47.94 490	75.09 493

eth_miper_zixun_eth		83.12 327	82.01 325	86.47 361	91.85 315	74.80 378	94.33 342	93.18 388	79.11 360	75.74 366	87.25 377	72.71 229	95.32 369	76.78 327	67.13 427	89.27 367

pmmvs4		82.54 337	80.79 342	87.79 330	86.11 421	80.49 228	93.55 367	93.18 388	77.29 382	73.35 386	89.40 341	65.26 320	95.05 393	75.32 349	73.61 372	87.83 412

XVG-ACMP-BASELINE		79.38 378	77.90 376	83.81 406	84.98 436	67.14 450	89.03 433	93.18 388	80.26 336	72.87 392	88.15 362	38.55 472	96.26 318	76.05 338	78.05 350	88.02 409

CANet_DTU		90.98 131	90.04 148	93.83 60	94.76 174	86.23 42	96.32 230	93.12 392	93.11 25	93.71 80	96.82 141	63.08 336	99.48 91	84.29 236	95.12 142	95.77 260

IS-MVSNet		88.67 205	88.16 200	90.20 266	93.61 215	76.86 348	96.77 193	93.07 393	84.02 243	83.62 263	95.60 179	74.69 203	96.24 321	78.43 306	93.66 168	97.49 161

c3_l		83.80 315	82.65 317	87.25 350	92.10 300	77.74 332	95.25 308	93.04 394	78.58 368	76.01 359	87.21 378	75.25 192	95.11 385	77.54 319	68.89 408	88.91 391

UnsupCasMVSNet_bld		68.60 449	64.50 453	80.92 436	74.63 491	67.80 442	83.97 471	92.94 395	65.12 462	54.63 486	68.23 496	35.97 478	92.17 445	60.13 442	44.83 495	82.78 467

MVP-Stereo		82.65 336	81.67 331	85.59 381	86.10 422	78.29 304	93.33 373	92.82 396	77.75 376	69.17 427	87.98 364	59.28 367	95.76 345	71.77 376	96.88 105	82.73 468
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Effi-MVS+		90.70 140	89.90 156	93.09 102	93.61 215	83.48 115	95.20 311	92.79 397	83.22 268	91.82 113	95.70 169	71.82 251	97.48 232	91.25 134	93.67 167	98.32 75

EU-MVSNet		76.92 405	76.95 383	76.83 459	84.10 445	54.73 494	91.77 404	92.71 398	72.74 425	69.57 424	88.69 348	58.03 379	87.43 481	64.91 417	70.00 399	88.33 404

pm-mvs1		80.05 370	78.02 375	86.15 369	85.42 429	75.81 370	95.11 319	92.69 399	77.13 384	70.36 414	87.43 372	58.44 373	95.27 372	71.36 380	64.25 443	87.36 424

1112_ss		88.60 208	87.47 219	92.00 180	93.21 232	80.97 199	96.47 214	92.46 400	83.64 262	80.86 299	97.30 117	80.24 84	97.62 209	77.60 317	85.49 293	97.40 173

viewdifsd2359ckpt11		86.38 260	85.29 261	89.66 286	90.42 350	75.65 372	95.27 306	92.45 401	85.54 190	84.27 248	94.73 229	62.16 342	97.39 248	87.78 205	74.97 365	95.96 248

viewmsd2359difaftdt		86.38 260	85.29 261	89.67 285	90.42 350	75.65 372	95.27 306	92.45 401	85.54 190	84.28 247	94.73 229	62.16 342	97.39 248	87.78 205	74.97 365	95.96 248

test_fmvs1		87.79 233	88.52 192	85.62 380	92.98 245	64.31 460	97.88 89	92.42 403	87.95 106	92.24 103	95.82 163	47.94 441	98.44 163	95.31 72	94.09 154	94.09 306

Test_1112_low_res		88.03 225	86.73 237	91.94 184	93.15 235	80.88 208	96.44 217	92.41 404	83.59 264	80.74 301	91.16 313	80.18 85	97.59 212	77.48 320	85.40 294	97.36 176

test_fmvs1_n		86.34 263	86.72 238	85.17 388	87.54 403	63.64 465	96.91 178	92.37 405	87.49 123	91.33 121	95.58 180	40.81 470	98.46 159	95.00 75	93.49 169	93.41 320

SSM_0407		87.33 247	85.87 251	91.71 202	92.94 247	82.53 136	94.30 344	92.33 406	80.11 338	83.50 264	94.18 251	64.68 326	96.80 300	82.34 262	88.51 256	95.79 257

SSM_0404		87.69 239	86.26 244	91.95 182	92.94 247	83.02 126	94.69 333	92.33 406	80.11 338	84.65 243	94.18 251	64.68 326	96.90 289	82.34 262	90.44 218	95.94 251

BH-RMVSNet		86.84 253	85.28 263	91.49 213	95.35 150	80.26 234	96.95 174	92.21 408	82.86 280	81.77 292	95.46 188	59.34 366	97.64 208	69.79 392	93.81 164	96.57 234

GeoE		86.36 262	85.20 264	89.83 280	93.17 234	76.13 360	97.53 118	92.11 409	79.58 350	80.99 296	94.01 256	66.60 309	96.17 325	73.48 366	89.30 234	97.20 193

LS3D		82.22 343	79.94 358	89.06 294	97.43 90	74.06 387	93.20 379	92.05 410	61.90 472	73.33 387	95.21 201	59.35 365	99.21 109	54.54 466	92.48 184	93.90 310

EG-PatchMatch MVS		74.92 414	72.02 422	83.62 411	83.76 452	73.28 393	93.62 364	92.04 411	68.57 452	58.88 475	83.80 428	31.87 487	95.57 360	56.97 458	78.67 342	82.00 477

IterMVS		80.67 366	79.16 366	85.20 387	89.79 364	76.08 361	92.97 383	91.86 412	80.28 334	71.20 407	85.14 415	57.93 381	91.34 454	72.52 373	70.74 390	88.18 407
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MIMVSNet		79.18 380	75.99 390	88.72 303	87.37 404	80.66 214	79.96 480	91.82 413	77.38 381	74.33 377	81.87 447	41.78 462	90.74 460	66.36 412	83.10 309	94.76 291

IterMVS-SCA-FT		80.51 368	79.10 367	84.73 393	89.63 373	74.66 379	92.98 382	91.81 414	80.05 341	71.06 410	85.18 413	58.04 377	91.40 453	72.48 374	70.70 392	88.12 408

mamba_0408		85.26 288	83.10 308	91.74 198	92.94 247	82.53 136	72.52 499	91.77 415	80.36 330	83.50 264	94.01 256	64.97 322	96.90 289	79.37 293	88.51 256	95.79 257

SSM_04072		84.64 299	83.10 308	89.25 291	92.94 247	82.53 136	72.52 499	91.77 415	80.36 330	83.50 264	94.01 256	64.97 322	89.41 468	79.37 293	88.51 256	95.79 257

FE-MVSNET2		73.72 418	70.80 428	82.46 424	74.97 490	73.81 388	91.88 402	91.73 417	76.70 392	59.74 473	77.41 471	42.26 461	90.52 462	64.75 418	57.79 459	83.06 464

our_test_3		77.90 395	75.37 399	85.48 383	85.39 430	76.74 350	93.63 363	91.67 418	73.39 420	65.72 443	84.65 421	58.20 376	93.13 434	57.82 452	67.87 418	86.57 433

pmmvs5		81.34 355	79.54 362	86.73 359	85.02 435	76.91 346	96.22 240	91.65 419	77.65 377	73.55 381	88.61 349	55.70 405	94.43 413	74.12 361	73.35 375	88.86 392

ACMH	75.40 17	77.99 392	74.96 400	87.10 353	90.67 345	76.41 356	93.19 380	91.64 420	72.47 431	63.44 452	87.61 371	43.34 455	97.16 268	58.34 450	73.94 370	87.72 413
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis1_n		85.60 279	85.70 253	85.33 385	84.79 437	64.98 457	96.83 183	91.61 421	87.36 129	91.00 128	94.84 227	36.14 477	97.18 267	95.66 64	93.03 176	93.82 311

MonoMVSNet		85.68 275	84.22 283	90.03 270	88.43 392	77.83 325	92.95 384	91.46 422	87.28 131	78.11 328	85.96 401	66.31 312	94.81 400	90.71 149	76.81 354	97.46 164

Fast-Effi-MVS+-dtu		83.33 322	82.60 318	85.50 382	89.55 375	69.38 436	96.09 251	91.38 423	82.30 291	75.96 361	91.41 308	56.71 396	95.58 359	75.13 351	84.90 298	91.54 329

YYNet1		73.53 423	70.43 431	82.85 419	84.52 440	71.73 415	91.69 406	91.37 424	67.63 454	46.79 494	81.21 453	55.04 410	90.43 463	55.93 461	59.70 455	86.38 435

ppachtmachnet_test		77.19 402	74.22 409	86.13 370	85.39 430	78.22 308	93.98 353	91.36 425	71.74 438	67.11 433	84.87 419	56.67 397	93.37 433	52.21 471	64.59 440	86.80 429

Anonymous202405211		84.41 306	81.93 327	91.85 189	96.78 105	78.41 300	97.44 126	91.34 426	70.29 444	84.06 252	94.26 246	41.09 467	98.96 131	79.46 291	82.65 317	98.17 88

MDA-MVSNet_test_wron		73.54 422	70.43 431	82.86 418	84.55 438	71.85 412	91.74 405	91.32 427	67.63 454	46.73 495	81.09 454	55.11 409	90.42 464	55.91 462	59.76 454	86.31 436

SD_0403		81.29 356	81.13 340	81.78 431	90.20 355	60.43 478	89.97 423	91.31 428	83.87 250	71.78 401	93.08 280	63.86 330	89.61 467	60.00 443	86.07 287	95.30 276

CR-MVSNet		83.53 319	81.36 336	90.06 269	90.16 357	79.75 252	79.02 486	91.12 429	84.24 238	82.27 284	80.35 458	75.45 182	93.67 427	63.37 428	86.25 282	96.75 228

Patchmtry		77.36 401	74.59 405	85.67 378	89.75 367	75.75 371	77.85 489	91.12 429	60.28 480	71.23 406	80.35 458	75.45 182	93.56 429	57.94 451	67.34 425	87.68 415

LTVRE_ROB	73.68 18	77.99 392	75.74 394	84.74 392	90.45 349	72.02 408	86.41 457	91.12 429	72.57 429	66.63 438	87.27 375	54.95 411	96.98 283	56.29 460	75.98 357	85.21 450
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		77.18 403	76.06 389	80.55 438	83.78 450	60.00 481	90.35 420	91.05 432	77.01 388	66.62 439	87.92 365	47.73 443	94.03 419	71.63 377	68.44 412	87.62 416

CNLPA		86.96 250	85.37 260	91.72 201	97.59 81	79.34 266	97.21 142	91.05 432	74.22 411	78.90 319	96.75 145	67.21 302	98.95 133	74.68 354	90.77 216	96.88 219

Anonymous20240521		72.06 433	69.91 433	78.50 451	77.11 482	61.67 475	91.62 408	90.97 434	65.52 461	62.37 459	79.05 464	36.32 476	90.96 458	57.75 453	68.52 411	82.87 465

KD-MVS_self_test		70.97 438	69.31 436	75.95 464	76.24 487	55.39 493	87.45 447	90.94 435	70.20 446	62.96 457	77.48 470	44.01 451	88.09 475	61.25 436	53.26 477	84.37 458

pmmvs6		74.65 416	71.67 423	83.60 412	79.13 474	69.94 429	93.31 376	90.88 436	61.05 479	65.83 442	84.15 425	43.43 454	94.83 399	66.62 407	60.63 453	86.02 442

test1111		88.11 222	87.04 229	91.35 219	93.15 235	78.79 289	96.57 206	90.78 437	86.88 147	85.04 234	95.20 202	57.23 394	97.39 248	83.88 240	94.59 148	97.87 117

ECVR-MVS		88.35 216	87.25 223	91.65 203	93.54 218	79.40 263	96.56 208	90.78 437	86.78 152	85.57 228	95.25 195	57.25 393	97.56 216	84.73 234	94.80 145	97.98 108

Anonymous20231206		75.29 413	73.64 414	80.22 440	80.75 460	63.38 467	93.36 371	90.71 439	73.09 422	67.12 432	83.70 429	50.33 430	90.85 459	53.63 469	70.10 397	86.44 434

USDC		78.65 387	76.25 388	85.85 372	87.58 401	74.60 381	89.58 427	90.58 440	84.05 242	63.13 454	88.23 360	40.69 471	96.86 296	66.57 409	75.81 360	86.09 440

dtuonly		84.63 300	84.08 287	86.30 367	86.14 420	69.59 433	92.71 388	90.28 441	82.00 298	80.87 298	94.51 237	62.61 338	96.18 323	79.00 300	88.60 249	93.14 321

MSDG		80.62 367	77.77 377	89.14 293	93.43 226	77.24 340	91.89 401	90.18 442	69.86 448	68.02 429	91.94 304	52.21 421	98.84 139	59.32 447	83.12 308	91.35 330

ACMH+	76.62 16	77.47 400	74.94 401	85.05 389	91.07 335	71.58 417	93.26 377	90.01 443	71.80 437	64.76 447	88.55 350	41.62 463	96.48 310	62.35 431	71.00 388	87.09 427

FMVSNet5		76.46 407	74.16 410	83.35 415	90.05 360	76.17 359	89.58 427	89.85 444	71.39 440	65.29 446	80.42 457	50.61 428	87.70 480	61.05 438	69.24 406	86.18 438

usedtu_blend_shiyan5		77.51 399	73.93 413	88.26 315	79.74 467	80.59 216	90.76 417	89.69 445	63.21 465	70.34 415	82.14 439	57.91 383	95.15 381	77.83 307	53.77 471	89.05 376

ambc				76.02 462	68.11 500	51.43 495	64.97 505	89.59 446		60.49 468	74.49 482	17.17 500	92.46 437	61.50 434	52.85 479	84.17 460

test_fmvs2		79.59 374	79.90 359	78.67 449	82.86 455	55.82 491	95.20 311	89.55 447	81.09 310	80.12 310	89.80 333	34.31 482	93.51 430	87.82 204	78.36 348	86.69 431

ITE_SJBPF				82.38 425	87.00 406	65.59 455		89.55 447	79.99 343	69.37 425	91.30 311	41.60 464	95.33 368	62.86 430	74.63 369	86.24 437

pmmvs-eth3d		73.59 420	70.66 429	82.38 425	76.40 485	73.38 390	89.39 431	89.43 449	72.69 426	60.34 469	77.79 468	46.43 448	91.26 456	66.42 411	57.06 460	82.51 469

test20.03		72.36 431	71.15 426	75.98 463	77.79 478	59.16 483	92.40 393	89.35 450	74.09 413	61.50 464	84.32 423	48.09 438	85.54 489	50.63 477	62.15 451	83.24 463

SixPastTwentyTwo		76.04 408	74.32 408	81.22 433	84.54 439	61.43 476	91.16 412	89.30 451	77.89 373	64.04 449	86.31 395	48.23 437	94.29 416	63.54 427	63.84 446	87.93 411

PatchmatchNet2					0.00 560	72.22 402	92.05 398	89.18 452	62.36 470
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TransMVSNet (Re)		76.94 404	74.38 407	84.62 397	85.92 424	75.25 376	95.28 303	89.18 452	73.88 415	67.22 431	86.46 390	59.64 361	94.10 418	59.24 448	52.57 480	84.50 457

MIMVSNet1		69.44 444	66.65 446	77.84 452	76.48 484	62.84 469	87.42 448	88.97 454	66.96 459	57.75 481	79.72 463	32.77 486	85.83 488	46.32 486	63.42 447	84.85 453

K. test v3		73.62 419	71.59 424	79.69 442	82.98 454	59.85 482	90.85 416	88.83 455	77.13 384	58.90 474	82.11 443	43.62 453	91.72 451	65.83 413	54.10 469	87.50 422

Baseline_NR-MVSNet		81.22 358	80.07 355	84.68 394	85.32 433	75.12 377	96.48 213	88.80 456	76.24 397	77.28 336	86.40 394	67.61 294	94.39 414	75.73 342	66.73 431	84.54 456

MDA-MVSNet-bldmvs		71.45 435	67.94 442	81.98 429	85.33 432	68.50 440	92.35 394	88.76 457	70.40 443	42.99 498	81.96 446	46.57 447	91.31 455	48.75 484	54.39 468	86.11 439

new-patchmatchnet		68.85 448	65.93 449	77.61 454	73.57 494	63.94 464	90.11 422	88.73 458	71.62 439	55.08 485	73.60 484	40.84 469	87.22 483	51.35 475	48.49 489	81.67 481

Patchmatch-test		78.25 389	74.72 404	88.83 300	91.20 329	74.10 386	73.91 497	88.70 459	59.89 483	66.82 436	85.12 416	78.38 114	94.54 409	48.84 483	79.58 335	97.86 119

OpenMVS_ROB	68.52 20	73.02 426	69.57 434	83.37 414	80.54 463	71.82 413	93.60 366	88.22 460	62.37 469	61.98 461	83.15 435	35.31 481	95.47 362	45.08 490	75.88 359	82.82 466

mvsany_test1		87.58 241	88.22 197	85.67 378	89.78 365	67.18 446	95.25 308	87.93 461	83.96 246	88.79 166	97.06 131	72.52 233	94.53 410	92.21 121	86.45 280	95.30 276

RPSCF		77.73 396	76.63 386	81.06 435	88.66 388	55.76 492	87.77 446	87.88 462	64.82 463	74.14 378	92.79 285	49.22 435	96.81 298	67.47 401	76.88 353	90.62 337

MVS-HIRNet		71.36 437	67.00 443	84.46 401	90.58 346	69.74 432	79.15 485	87.74 463	46.09 499	61.96 462	50.50 513	45.14 450	95.64 354	53.74 468	88.11 264	88.00 410

usedtu_dtu_shiyan2		64.65 454	60.40 458	77.38 456	64.24 504	57.84 486	89.16 432	87.60 464	52.95 494	53.43 488	71.31 495	23.41 495	88.27 474	51.95 472	49.58 485	86.03 441

mmtdpeth		78.04 391	76.76 385	81.86 430	89.60 374	66.12 454	92.34 395	87.18 465	76.83 391	85.55 229	76.49 477	46.77 446	97.02 277	90.85 144	45.24 494	82.43 472

DP-MVS		81.47 353	78.28 372	91.04 233	98.14 61	78.48 296	95.09 322	86.97 466	61.14 478	71.12 409	92.78 286	59.59 362	99.38 96	53.11 470	86.61 278	95.27 278

COLMAP_ROB	73.24 19	75.74 411	73.00 418	83.94 405	92.38 272	69.08 437	91.85 403	86.93 467	61.48 475	65.32 445	90.27 327	42.27 460	96.93 288	50.91 476	75.63 361	85.80 447
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MVStest1		66.93 451	63.01 455	78.69 448	78.56 475	71.43 419	85.51 464	86.81 468	49.79 497	48.57 493	84.15 425	53.46 417	83.31 492	43.14 493	37.15 503	81.34 483

test_fmvs3		69.56 442	69.19 437	70.67 470	69.01 498	47.05 498	90.87 415	86.81 468	71.31 441	66.79 437	77.15 473	16.40 501	83.17 494	81.84 267	62.51 450	81.79 479

test_0402		72.68 427	69.54 435	82.09 428	88.67 387	71.81 414	92.72 387	86.77 470	61.52 474	62.21 460	83.91 427	43.22 456	93.76 426	34.60 502	72.23 383	80.72 485

testgi		74.88 415	73.40 415	79.32 445	80.13 465	61.75 473	93.21 378	86.64 471	79.49 352	66.56 440	91.06 314	35.51 480	88.67 471	56.79 459	71.25 386	87.56 419

dtuonlycased		72.49 428	71.58 425	75.22 465	81.04 459	64.71 458	92.43 392	86.46 472	75.62 400	59.79 472	78.43 466	48.54 436	85.84 487	63.66 426	58.28 456	75.10 492

TDRefinement		69.20 447	65.78 450	79.48 443	66.04 503	62.21 471	88.21 439	86.12 473	62.92 467	61.03 467	85.61 405	33.23 484	94.16 417	55.82 463	53.02 478	82.08 475

ADS-MVSNet2		79.57 375	77.53 378	85.71 377	93.78 210	72.13 406	79.48 482	86.11 474	73.09 422	80.14 308	79.99 461	62.15 344	90.14 466	59.49 445	83.52 304	94.85 289

LF4IMVS		72.36 431	70.82 427	76.95 458	79.18 473	56.33 488	86.12 459	86.11 474	69.30 450	63.06 455	86.66 386	33.03 485	92.25 442	65.33 415	68.64 410	82.28 473

TinyColmap		72.41 429	68.99 438	82.68 420	88.11 395	69.59 433	88.41 438	85.20 476	65.55 460	57.91 478	84.82 420	30.80 489	95.94 334	51.38 473	68.70 409	82.49 471

mvs5depth		71.40 436	68.36 440	80.54 439	75.31 489	65.56 456	79.94 481	85.14 477	69.11 451	71.75 402	81.59 448	41.02 468	93.94 421	60.90 439	50.46 483	82.10 474

pmmvs3		65.75 453	62.18 456	76.45 461	67.12 502	64.54 459	88.68 436	85.05 478	54.77 493	57.54 482	73.79 483	29.40 492	86.21 486	55.49 465	47.77 491	78.62 488

new_pmnet		66.18 452	63.18 454	75.18 467	76.27 486	61.74 474	83.79 472	84.66 479	56.64 491	51.57 490	71.85 492	31.29 488	87.93 476	49.98 479	62.55 449	75.86 491

AllTest		75.92 409	73.06 417	84.47 399	92.18 293	67.29 444	91.07 413	84.43 480	67.63 454	63.48 450	90.18 328	38.20 473	97.16 268	57.04 456	73.37 373	88.97 388

TestCases				84.47 399	92.18 293	67.29 444		84.43 480	67.63 454	63.48 450	90.18 328	38.20 473	97.16 268	57.04 456	73.37 373	88.97 388

ttmdpeth		69.58 441	66.92 445	77.54 455	75.95 488	62.40 470	88.09 441	84.32 482	62.87 468	65.70 444	86.25 397	36.53 475	88.53 473	55.65 464	46.96 493	81.70 480

tt0320		70.21 439	66.07 447	82.64 421	83.42 453	70.82 422	89.63 425	84.10 483	49.75 498	62.71 458	77.28 472	33.35 483	92.45 439	58.78 449	55.62 463	84.64 455

FE-MVSNET		69.26 446	66.03 448	78.93 447	73.82 492	68.33 441	89.65 424	84.06 484	70.21 445	57.79 480	76.94 476	41.48 465	86.98 484	45.85 488	54.51 467	81.48 482

LCM-MVSNet-Re		83.75 316	83.54 299	84.39 403	93.54 218	64.14 462	92.51 389	84.03 485	83.90 249	66.14 441	86.59 387	67.36 300	92.68 435	84.89 233	92.87 178	96.35 239

Gipuma		45.11 472	42.05 473	54.30 491	80.69 461	51.30 496	35.80 518	83.81 486	28.13 509	27.94 512	34.53 521	11.41 509	76.70 505	21.45 518	54.65 465	34.90 522
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
sc_t1		72.37 430	68.03 441	85.39 384	83.78 450	70.51 424	91.27 411	83.70 487	52.46 495	68.29 428	82.02 445	30.58 490	94.81 400	64.50 419	55.69 462	90.85 336

LCM-MVSNet		52.52 465	48.24 468	65.35 477	47.63 521	41.45 508	72.55 498	83.62 488	31.75 506	37.66 501	57.92 508	9.19 512	76.76 503	49.26 481	44.60 496	77.84 489

FPMVS		55.09 463	52.93 466	61.57 483	55.98 510	40.51 510	83.11 475	83.41 489	37.61 502	34.95 503	71.95 490	14.40 502	76.95 502	29.81 508	65.16 439	67.25 498

Patchmatch-RL test		76.65 406	74.01 412	84.55 398	77.37 481	64.23 461	78.49 488	82.84 490	78.48 369	64.63 448	73.40 485	76.05 168	91.70 452	76.99 324	57.84 458	97.72 133

tt0320-xc		69.70 440	65.27 452	82.99 417	84.33 441	71.92 411	89.56 429	82.08 491	50.11 496	61.87 463	77.50 469	30.48 491	92.34 440	60.30 441	51.20 482	84.71 454

DSMNet-mixed		73.13 425	72.45 419	75.19 466	77.51 480	46.82 499	85.09 467	82.01 492	67.61 458	69.27 426	81.33 452	50.89 424	86.28 485	54.54 466	83.80 303	92.46 324

lessismore_v0				79.98 441	80.59 462	58.34 485		80.87 493		58.49 476	83.46 431	43.10 457	93.89 422	63.11 429	48.68 487	87.72 413

test_f		64.01 455	62.13 457	69.65 471	63.00 506	45.30 505	83.66 473	80.68 494	61.30 476	55.70 484	72.62 488	14.23 503	84.64 490	69.84 391	58.11 457	79.00 487

door								80.13 495

door-mid								79.75 496

PM-MVS		69.32 445	66.93 444	76.49 460	73.60 493	55.84 490	85.91 460	79.32 497	74.72 408	61.09 466	78.18 467	21.76 497	91.10 457	70.86 386	56.90 461	82.51 469

mvsany_test3		67.19 450	65.34 451	72.72 468	63.08 505	48.57 497	83.12 474	78.09 498	72.07 435	61.21 465	77.11 474	22.94 496	87.78 479	78.59 303	51.88 481	81.80 478

dmvs_testset		72.00 434	73.36 416	67.91 473	83.83 449	31.90 519	85.30 465	77.12 499	82.80 281	63.05 456	92.46 289	61.54 353	82.55 496	42.22 495	71.89 384	89.29 366

ANet_high		46.22 468	41.28 475	61.04 484	39.91 527	46.25 502	70.59 501	76.18 500	58.87 487	23.09 519	48.00 518	12.58 506	66.54 513	28.65 511	13.62 521	70.35 496

test_method		56.77 460	54.53 464	63.49 481	76.49 483	40.70 509	75.68 493	74.24 501	19.47 519	48.73 492	71.89 491	19.31 498	65.80 514	57.46 455	47.51 492	83.97 461

APD_test1		56.56 461	53.58 465	65.50 476	67.93 501	46.51 501	77.24 492	72.95 502	38.09 501	42.75 499	75.17 479	13.38 504	82.78 495	40.19 498	54.53 466	67.23 499

EGC-MVSNET		52.46 466	47.56 469	67.15 475	81.98 457	60.11 480	82.54 476	72.44 503	0.11 554	0.70 555	74.59 481	25.11 494	83.26 493	29.04 509	61.51 452	58.09 507

PMMVS2		50.90 467	46.31 470	64.67 478	55.53 511	46.67 500	77.30 491	71.02 504	40.89 500	34.16 504	59.32 505	9.83 511	76.14 506	40.09 499	28.63 509	71.21 495

WB-MVS		57.26 459	56.22 462	60.39 486	69.29 497	35.91 515	86.39 458	70.06 505	59.84 484	46.46 496	72.71 487	51.18 423	78.11 500	15.19 523	34.89 506	67.14 500

SSC-MVS		56.01 462	54.96 463	59.17 487	68.42 499	34.13 516	84.98 468	69.23 506	58.08 490	45.36 497	71.67 493	50.30 431	77.46 501	14.28 524	32.33 507	65.91 502

test_vis1_rt		73.96 417	72.40 420	78.64 450	83.91 448	61.16 477	95.63 290	68.18 507	76.32 394	60.09 470	74.77 480	29.01 493	97.54 223	87.74 207	75.94 358	77.22 490

MTMP							97.53 118	68.16 508

DeepMVS_CX				64.06 480	78.53 476	43.26 507		68.11 509	69.94 447	38.55 500	76.14 478	18.53 499	79.34 497	43.72 491	41.62 500	69.57 497

PMVS	34.80 23	39.19 477	35.53 479	50.18 495	29.72 530	30.30 521	59.60 510	66.20 510	26.06 512	17.91 523	49.53 515	3.12 524	74.09 508	18.19 522	49.40 486	46.14 519
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ArgMatch-SfM		60.14 457	57.35 460	68.50 472	71.14 496	45.17 506	80.16 479	63.06 511	59.74 485	51.33 491	80.81 455	11.74 508	78.30 499	61.13 437	37.05 504	82.04 476

testf1		45.70 469	42.41 471	55.58 489	53.29 514	40.02 511	68.96 502	62.67 512	27.45 510	29.85 509	61.58 503	5.98 516	73.83 509	28.49 512	43.46 498	52.90 511

APD_test2		45.70 469	42.41 471	55.58 489	53.29 514	40.02 511	68.96 502	62.67 512	27.45 510	29.85 509	61.58 503	5.98 516	73.83 509	28.49 512	43.46 498	52.90 511

tmp_tt		41.54 474	41.93 474	40.38 501	20.10 543	26.84 524	61.93 507	59.09 514	14.81 523	28.51 511	80.58 456	35.53 479	48.33 524	63.70 425	13.11 523	45.96 521

ArgMatch-Sym		59.60 458	56.89 461	67.74 474	71.40 495	45.64 504	81.24 478	58.34 515	58.65 488	52.79 489	81.51 451	11.35 510	76.76 503	60.83 440	35.86 505	80.81 484

LoFTR		45.13 471	39.91 476	60.78 485	58.50 508	33.07 517	59.69 509	57.64 516	30.48 508	25.92 515	63.30 500	4.30 518	74.96 507	28.23 515	31.12 508	74.31 494

MVE	35.65 22	33.85 480	29.49 487	46.92 496	41.86 524	36.28 514	50.45 515	56.52 517	18.75 520	18.28 521	37.84 520	2.41 532	58.41 517	18.71 521	20.62 514	46.06 520
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		32.70 484	32.39 483	33.65 505	53.35 513	25.70 525	74.07 496	53.33 518	21.08 517	17.17 524	33.63 523	11.85 507	54.84 519	12.98 526	14.04 519	20.42 527

EMVS		31.70 485	31.45 485	32.48 506	50.72 518	23.95 528	74.78 495	52.30 519	20.36 518	16.08 525	31.48 524	12.80 505	53.60 521	11.39 527	13.10 524	19.88 529

MatchFormer		39.45 476	34.61 480	54.00 492	53.28 516	28.79 523	58.06 512	51.35 520	21.48 515	23.10 518	55.83 510	3.50 523	70.37 511	19.01 520	25.84 510	62.84 503

test_vis3_rt		54.10 464	51.04 467	63.27 482	58.16 509	46.08 503	84.17 470	49.32 521	56.48 492	36.56 502	49.48 516	8.03 513	91.91 448	67.29 402	49.87 484	51.82 515

DenseAffine		43.98 473	39.51 477	57.39 488	60.41 507	37.29 513	67.44 504	34.50 522	35.36 504	31.38 507	65.55 498	4.21 519	67.77 512	35.59 501	21.11 513	67.10 501

ELoFTR		28.06 486	23.17 491	42.73 500	26.41 537	16.73 535	32.43 520	29.00 523	18.06 521	18.03 522	50.11 514	1.10 540	53.50 522	21.73 517	11.65 531	57.96 508

GLUNet-SfM		23.82 489	18.93 493	38.50 503	29.22 531	15.72 537	24.44 528	26.94 524	12.76 525	13.93 527	40.99 519	2.01 537	46.93 525	13.88 525	6.19 544	52.85 513

MASt3R-SfM		33.79 481	32.03 484	39.08 502	30.86 529	18.05 533	44.70 516	25.59 525	21.32 516	31.97 506	71.52 494	3.78 521	38.14 527	35.97 500	22.58 512	61.06 506

PDCNetPlus		37.10 479	34.54 481	44.76 497	50.06 520	29.19 522	58.72 511	23.89 526	37.05 503	24.11 517	58.95 507	6.11 515	55.29 518	40.76 497	11.21 532	49.81 516

RoMa-SfM		40.68 475	36.49 478	53.24 493	52.27 517	33.01 518	62.88 506	23.78 527	32.85 505	31.33 508	67.39 497	3.87 520	64.89 515	33.77 503	20.24 515	61.82 505

DKM		38.02 478	33.59 482	51.32 494	50.45 519	30.46 520	61.04 508	19.18 528	30.65 507	26.88 513	61.89 502	2.55 529	61.16 516	32.68 505	16.95 516	62.34 504

VLMVS		26.26 487	26.52 490	25.45 508	25.35 538	7.91 542	30.71 522	15.37 529	3.37 537	34.11 505	65.40 499	8.03 513	21.07 531	32.40 506	23.95 511	47.39 518

RoMa-HiRes		33.28 482	29.63 486	44.22 499	41.01 525	25.30 527	51.82 514	14.13 530	25.85 514	26.34 514	61.96 501	2.78 527	54.52 520	28.42 514	14.36 517	52.83 514

DKM-HiRes		32.92 483	29.13 488	44.31 498	42.93 522	25.35 526	53.22 513	13.26 531	25.92 513	24.31 516	57.58 509	1.88 538	50.95 523	28.87 510	14.19 518	56.63 510

ALIKED-LG		17.53 492	16.82 495	19.64 509	42.07 523	19.09 530	31.53 521	11.93 532	7.76 526	10.68 529	26.90 527	3.52 522	22.14 529	3.10 536	13.89 520	17.68 530

N_pmnet		61.30 456	60.20 459	64.60 479	84.32 442	17.00 534	91.67 407	10.98 533	61.77 473	58.45 477	78.55 465	49.89 432	91.83 449	42.27 494	63.94 445	84.97 452

ALIKED-NN		16.22 494	15.63 496	17.99 511	39.36 528	18.31 532	29.26 525	10.71 534	5.97 528	10.10 530	26.06 528	2.80 526	20.08 532	2.91 537	13.46 522	15.60 532

ALIKED-MNN		16.35 493	15.48 497	18.95 510	40.20 526	19.09 530	30.16 523	10.63 535	6.03 527	9.48 531	24.90 529	2.59 528	21.29 530	2.88 538	12.46 526	16.48 531

XFeat-MNN		10.03 501	9.79 507	10.74 518	9.46 556	6.05 554	16.60 532	9.52 536	4.29 531	8.53 533	22.45 530	2.10 535	13.28 534	5.47 530	9.68 535	12.89 533

PMatch-SfM		26.26 487	22.21 492	38.43 504	28.29 534	16.65 536	37.61 517	8.91 537	18.02 522	18.64 520	53.32 511	0.55 552	41.01 526	24.74 516	9.79 534	57.63 509

SP-DiffGlue		11.69 498	11.68 503	11.70 516	11.01 555	7.08 546	18.35 531	8.44 538	4.41 530	11.18 528	28.64 526	2.84 525	7.44 540	7.44 529	12.85 525	20.56 526

SP-SuperGlue		12.00 497	12.07 500	11.81 514	28.37 533	6.58 547	24.63 526	8.02 539	3.99 532	7.02 534	18.00 533	2.44 531	7.72 539	3.95 533	12.19 528	21.13 525

SP-LightGlue		12.02 496	12.06 501	11.90 513	28.59 532	6.58 547	24.58 527	7.89 540	3.94 533	6.94 535	17.94 534	2.45 530	7.82 537	3.96 532	12.26 527	21.30 523

SP-MNN		11.64 499	11.60 504	11.74 515	27.48 535	6.11 553	24.23 529	7.72 541	3.40 536	6.22 537	17.81 536	2.13 534	7.94 536	3.69 535	11.73 530	21.18 524

XFeat-NN		9.17 503	9.18 508	9.14 519	8.78 557	5.26 556	15.30 533	7.57 542	3.56 535	8.63 532	22.05 531	1.87 539	11.03 535	4.95 531	9.92 533	11.13 534

SP-NN		11.53 500	11.59 505	11.38 517	27.20 536	6.14 552	24.02 530	7.42 543	3.57 534	6.38 536	17.94 534	2.17 533	7.78 538	3.71 534	11.86 529	20.23 528

PMatch-Up-SfM		21.53 490	18.34 494	31.10 507	23.05 539	12.66 538	29.81 524	5.63 544	13.87 524	16.04 526	48.08 517	0.39 556	31.11 528	21.09 519	7.09 541	49.53 517

SIFT-MNN		6.97 507	7.12 511	6.51 521	21.26 541	8.28 540	11.89 535	4.05 545	2.50 539	3.39 541	11.27 539	0.76 542	6.14 542	0.95 541	8.05 539	5.09 535

SIFT-NN		7.34 506	7.57 510	6.67 520	22.83 540	8.78 539	12.92 534	4.04 546	2.52 538	3.88 539	11.56 538	0.86 541	6.16 541	0.95 541	8.56 537	5.09 535

SIFT-NN-NCMNet		6.77 508	6.92 512	6.30 522	19.98 544	8.05 541	11.79 536	3.97 547	2.43 541	3.43 540	10.93 540	0.75 543	5.95 544	0.88 543	8.15 538	4.90 537

SIFT-NCM-Cal		6.46 509	6.58 513	6.10 523	20.43 542	7.62 543	11.15 538	3.59 548	2.40 544	2.33 549	10.33 546	0.68 547	6.03 543	0.77 549	7.51 540	4.64 541

SIFT-NN-UMatch		6.11 511	6.25 515	5.68 526	17.01 550	6.50 549	11.20 537	3.58 549	2.44 540	2.68 545	10.88 542	0.74 544	5.70 547	0.87 544	6.85 542	4.82 539

wuyk23d		14.10 495	13.89 498	14.72 512	55.23 512	22.91 529	33.83 519	3.56 550	4.94 529	4.11 538	2.28 553	2.06 536	19.66 533	10.23 528	8.74 536	1.59 551

SIFT-NN-CMatch		6.23 510	6.33 514	5.94 524	18.10 548	7.22 545	10.34 539	3.54 551	2.42 542	3.36 542	10.93 540	0.72 545	5.71 546	0.87 544	6.67 543	4.89 538

SIFT-ConvMatch		6.05 512	6.14 516	5.78 525	19.43 545	7.31 544	9.58 542	3.30 552	2.42 542	2.67 546	10.54 544	0.65 548	5.73 545	0.83 547	5.84 546	4.29 542

SIFT-NN-PointCN		5.63 515	5.80 518	5.10 529	16.00 551	5.22 557	10.00 541	3.21 553	2.26 548	2.92 543	10.15 547	0.72 545	5.35 550	0.81 548	6.14 545	4.74 540

SIFT-UMatch		5.86 514	6.01 517	5.38 527	18.70 546	6.22 551	10.07 540	3.07 554	2.39 545	2.42 547	10.54 544	0.63 550	5.65 548	0.84 546	5.49 547	4.28 543

SIFT-CM-Cal		5.56 516	5.66 519	5.26 528	18.45 547	6.34 550	8.44 544	2.81 555	2.36 546	2.42 547	9.99 549	0.64 549	5.41 549	0.74 551	5.05 548	4.02 544

SIFT-PointCN		4.77 518	4.97 521	4.17 532	15.53 553	3.97 558	8.20 545	2.62 556	2.10 549	1.91 553	8.44 551	0.47 554	4.70 553	0.67 553	4.79 549	3.85 547

SIFT-UM-Cal		5.40 517	5.58 520	4.87 530	18.00 549	5.37 555	9.03 543	2.49 557	2.33 547	2.14 551	10.11 548	0.60 551	5.27 551	0.77 549	4.78 550	3.95 545

SIFT-PCN-Cal		4.71 519	4.89 522	4.18 531	15.70 552	3.90 559	7.58 546	2.37 558	2.09 550	1.95 552	8.68 550	0.51 553	4.71 552	0.68 552	4.45 551	3.93 546

SIFT-NCMNet		4.03 520	4.21 523	3.50 533	14.53 554	3.56 560	6.14 547	1.51 559	2.08 551	1.72 554	7.39 552	0.42 555	4.00 554	0.57 554	3.56 552	2.93 548

testmvs		9.92 502	12.94 499	0.84 535	0.65 558	0.29 562	93.78 361	0.39 560	0.42 552	2.85 544	15.84 537	0.17 558	0.30 556	2.18 539	0.21 553	1.91 550

test123		9.07 504	11.73 502	1.11 534	0.50 559	0.77 561	89.44 430	0.20 561	0.34 553	2.15 550	10.72 543	0.34 557	0.32 555	1.79 540	0.08 554	2.23 549

mmdepth		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

monomultidepth		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

test_blank		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

uanet_test		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

DCPMVS		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

pcd_1.5k_mvsjas		5.92 513	7.89 509	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	71.04 261	0.00 557	0.00 555	0.00 555	0.00 552

sosnet-low-res		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

sosnet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

uncertanet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

Regformer		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

n2								0.00 562

nn								0.00 562

ab-mvs-re		8.11 505	10.81 506	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	97.30 117	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

uanet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

PatchmatchNet1														42.17 496	64.00 444	85.01 451
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													91.74 450
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						67.18 446								49.00 482

PC_three_1452									91.12 50	98.33 5	98.42 44	92.51 2	99.81 29	98.96 6	99.37 1	99.70 4

eth-test2					0.00 560

eth-test					0.00 560

OPU-MVS				97.30 2	99.19 8	92.31 3	99.12 16				98.54 30	92.06 3	99.84 19	99.11 5	99.37 1	99.74 1

test_0728_THIRD									88.38 93	96.69 31	98.76 18	89.64 14	99.76 46	97.47 41	98.84 23	99.38 15

GSMVS																97.54 152

test_part2					98.90 25	85.14 78				96.07 43

sam_mvs1												77.59 129				97.54 152

sam_mvs												75.35 189

test_post1							85.88 461				30.24 525	73.77 214	95.07 391	73.89 362

test_post											33.80 522	76.17 164	95.97 330

patchmatchnet-post											77.09 475	77.78 127	95.39 364

gm-plane-assit					92.27 285	79.64 258			84.47 229		95.15 207		97.93 187	85.81 225

test9_res														96.00 59	99.03 13	98.31 77

agg_prior2														94.30 83	99.00 15	98.57 61

test_prior4						82.34 147	97.75 100

test_prior2							98.37 56		86.08 170	94.57 70	98.02 73	83.14 62		95.05 74	98.79 27

旧先验2							96.97 171		74.06 414	96.10 42			97.76 199	88.38 199

新几何2							96.42 221

原ACMM2							96.84 182

testdata2													99.48 91	76.45 333

segment_acmp												82.69 68

testdata1							95.57 294		87.44 126

plane_prior7					91.86 313	77.55 335

plane_prior6					91.98 308	77.92 321						64.77 324

plane_prior4											94.15 253

plane_prior3						77.75 331			90.17 68	81.33 293

plane_prior2							97.18 146		89.89 71

plane_prior1					91.95 310

plane_prior						77.96 318	97.52 121		90.36 66						82.96 312

HQP5-MVS						78.48 296

HQP-NCC					92.08 301		97.63 107		90.52 60	82.30 280

ACMP_Plane					92.08 301		97.63 107		90.52 60	82.30 280

BP-MVS														87.67 209

HQP4-MVS										82.30 280			97.32 256			91.13 331

HQP2-MVS												65.40 317

NP-MVS					92.04 305	78.22 308					94.56 235

MDTV_nov1_ep13_2view						81.74 174	86.80 453		80.65 320	85.65 226		74.26 207		76.52 332		96.98 211

ACMMP++_ref															78.45 347

ACMMP++															79.05 339

Test By Simon												71.65 253

High-resolution multi-view benchmark