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		88.92 201	87.65 213	92.73 126	96.30 112	85.62 64	97.85 91	98.86 1	84.38 235	84.82 242	93.99 263	75.12 199	98.01 185	70.86 390	86.67 281	94.56 302

thres100view900		88.30 221	86.95 236	92.33 155	96.10 120	84.90 89	97.14 156	98.85 2	82.69 288	83.41 271	93.66 273	75.43 189	97.93 188	69.04 398	86.24 288	94.17 306

tfpn200view9		88.48 215	87.15 229	92.47 142	96.21 115	85.30 73	97.44 127	98.85 2	83.37 269	83.99 258	93.82 269	75.36 192	97.93 188	69.04 398	86.24 288	94.17 306

thres600view7		88.06 228	86.70 244	92.15 171	96.10 120	85.17 79	97.14 156	98.85 2	82.70 287	83.41 271	93.66 273	75.43 189	97.82 199	67.13 407	85.88 293	93.45 322

thres400		88.42 218	87.15 229	92.23 163	96.21 115	85.30 73	97.44 127	98.85 2	83.37 269	83.99 258	93.82 269	75.36 192	97.93 188	69.04 398	86.24 288	93.45 322

MVS_111021_HR		93.41 58	93.39 62	93.47 91	97.34 97	82.83 134	97.56 116	98.27 6	89.16 82	89.71 149	97.14 126	79.77 96	99.56 85	93.65 96	97.94 64	98.02 102

sss		90.87 140	89.96 156	93.60 81	94.15 202	83.84 108	97.14 156	98.13 7	85.93 182	89.68 150	96.09 160	71.67 257	99.30 103	87.69 211	89.16 239	97.66 142

MM		95.85 7	95.74 12	96.15 9	96.34 111	89.50 10	99.18 10	98.10 8	95.68 1	96.64 35	97.92 81	80.72 81	99.80 33	99.16 2	97.96 63	99.15 28

MG-MVS		94.25 38	93.72 50	95.85 13	99.38 4	89.35 12	97.98 82	98.09 9	89.99 70	92.34 104	96.97 136	81.30 77	98.99 130	88.54 198	98.88 20	99.20 26

VNet		92.11 102	91.22 114	94.79 31	96.91 103	86.98 34	97.91 88	97.96 10	86.38 165	93.65 83	95.74 168	70.16 278	98.95 134	93.39 98	88.87 244	98.43 71

test_yl		91.46 120	90.53 131	94.24 48	97.41 91	85.18 75	98.08 75	97.72 11	80.94 316	89.85 146	96.14 158	75.61 181	98.81 142	90.42 159	88.56 255	98.74 51

DCV-MVSNet		91.46 120	90.53 131	94.24 48	97.41 91	85.18 75	98.08 75	97.72 11	80.94 316	89.85 146	96.14 158	75.61 181	98.81 142	90.42 159	88.56 255	98.74 51

WTY-MVS		92.65 86	91.68 105	95.56 15	96.00 122	88.90 14	98.23 66	97.65 13	88.57 89	89.82 148	97.22 124	79.29 101	99.06 127	89.57 175	88.73 246	98.73 55

EPNet		94.06 44	94.15 45	93.76 66	97.27 99	84.35 97	98.29 64	97.64 14	94.57 12	95.36 53	96.88 139	79.96 95	99.12 123	91.30 135	96.11 127	97.82 127
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HY-MVS	84.06 6	91.63 116	90.37 138	95.39 21	96.12 119	88.25 19	90.22 425	97.58 15	88.33 97	90.50 138	91.96 304	79.26 102	99.06 127	90.29 163	89.07 240	98.88 45

testing3-2		91.37 123	91.01 122	92.44 146	95.93 127	83.77 109	98.83 37	97.45 16	86.88 150	86.63 217	94.69 236	84.57 46	97.75 202	89.65 173	84.44 303	95.80 258

SymmetryMVS		92.45 92	92.33 89	92.82 121	95.19 159	82.02 159	97.94 85	97.43 17	92.34 34	92.15 108	96.53 152	77.03 146	98.57 150	91.13 139	91.19 208	97.87 120

baseline2		90.39 157	90.21 144	90.93 243	90.86 344	80.99 203	95.20 315	97.41 18	86.03 176	80.07 315	94.61 237	90.58 7	97.47 235	87.29 216	89.86 228	94.35 304

test2506		90.96 136	90.39 136	92.65 130	93.54 222	82.46 146	96.37 227	97.35 19	86.78 155	87.55 195	95.25 198	77.83 130	97.50 231	84.07 242	94.80 146	97.98 111

PVSNet	82.34 9	89.02 197	87.79 211	92.71 127	95.49 146	81.50 187	97.70 104	97.29 20	87.76 113	85.47 234	95.12 212	56.90 399	98.90 138	80.33 284	94.02 157	97.71 138

testing915		93.45 57	92.94 72	94.98 26	95.44 147	87.97 23	97.33 138	97.28 21	87.45 125	91.88 115	95.54 184	85.11 40	97.87 197	95.44 70	91.00 214	99.11 29

testing222		91.09 131	90.49 133	92.87 116	95.82 131	85.04 83	96.51 216	97.28 21	86.05 174	89.13 162	95.34 195	80.16 91	96.62 311	85.82 228	88.31 265	96.96 215

PGM-MVS		91.93 106	91.80 103	92.32 157	98.27 56	79.74 259	95.28 307	97.27 23	83.83 257	90.89 133	97.78 91	76.12 171	99.56 85	88.82 191	97.93 66	97.66 142

IB-MVS	85.34 4	88.67 209	87.14 231	93.26 96	93.12 242	84.32 99	98.76 38	97.27 23	87.19 140	79.36 321	90.45 328	83.92 59	98.53 155	84.41 239	69.79 404	96.93 217
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 58	97.26 25	85.61 189	99.54 1	99.26 1	91.36 5	99.98 2		96.55 117	99.73 3

aaEdge-Enhanced		94.82 22	95.04 24	94.17 54	99.17 9	83.70 112	97.66 107	97.22 26	85.79 185	95.34 54	98.90 6	84.89 42	99.86 15	97.78 37	98.60 36	98.94 40

test_fmvsm_n_1920		94.81 23	95.60 13	92.45 144	95.29 154	80.96 209	99.29 5	97.21 27	94.50 14	97.29 24	98.44 42	82.15 71	99.78 40	98.56 13	97.68 73	96.61 235

patch_mono-2		95.14 15	96.08 8	92.33 155	98.44 49	77.84 329	98.43 53	97.21 27	92.58 30	97.68 17	97.65 99	86.88 30	99.83 23	98.25 19	97.60 75	99.33 19

MVS		90.60 147	88.64 188	96.50 6	94.25 198	90.53 9	93.33 377	97.21 27	77.59 382	78.88 324	97.31 116	71.52 261	99.69 67	89.60 174	98.03 61	99.27 23

ETVMVS		90.99 134	90.26 141	93.19 101	95.81 132	85.64 63	96.97 174	97.18 30	85.43 195	88.77 172	94.86 228	82.00 73	96.37 318	82.70 263	88.60 251	97.57 152

CSCG		92.02 103	91.65 106	93.12 104	98.53 42	80.59 221	97.47 124	97.18 30	77.06 391	84.64 248	97.98 78	83.98 57	99.52 88	90.72 150	97.33 86	99.23 25

aaatest				94.20 53	99.06 11	83.70 112	98.35 58	97.14 32	87.45 125	97.03 28	98.90 6		99.96 4	97.78 37	98.60 36	98.94 40

MED-MVS		95.59 10	96.05 9	94.21 50	99.06 11	83.70 112	98.35 58	97.14 32	87.65 119	97.03 28	98.83 11	89.87 13	99.96 4	97.78 37	98.71 31	98.97 38

fmvsm_s_conf0.5_n		93.69 50	94.13 46	92.34 153	94.56 181	82.01 161	99.07 23	97.13 34	92.09 39	96.25 40	98.53 33	76.47 159	99.80 33	98.39 15	94.71 148	95.22 283

PHI-MVS		93.59 52	93.63 53	93.48 89	98.05 64	81.76 177	98.64 45	97.13 34	82.60 290	94.09 78	98.49 37	80.35 85	99.85 17	94.74 81	98.62 35	98.83 46

CNVR-MVS		96.30 1	96.54 1	95.55 16	99.31 6	87.69 27	99.06 24	97.12 36	94.66 11	96.79 31	98.78 16	86.42 33	99.95 6	97.59 41	99.18 7	99.00 35

h-mvs33		89.30 190	88.95 183	90.36 265	95.07 166	76.04 367	96.96 176	97.11 37	90.39 65	92.22 106	95.10 213	74.70 205	98.86 139	93.14 107	65.89 441	96.16 248

MCST-MVS		96.17 4	96.12 7	96.32 8	99.42 3	89.36 11	98.94 32	97.10 38	95.17 4	92.11 110	98.46 41	87.33 28	99.97 3	97.21 48	99.31 4	99.63 8

testing11		92.48 91	92.04 100	93.78 65	95.94 126	86.00 48	97.56 116	97.08 39	87.52 123	89.32 158	95.40 193	84.60 45	98.02 183	91.93 131	89.04 241	97.32 183

VPA-MVSNet		85.32 290	83.83 293	89.77 288	90.25 357	82.63 138	96.36 230	97.07 40	83.03 279	81.21 299	89.02 348	61.58 356	96.31 321	85.02 236	70.95 393	90.36 344

UBG		92.68 85	92.35 87	93.70 74	95.61 141	85.65 62	97.25 143	97.06 41	87.92 108	89.28 159	95.03 216	86.06 37	98.07 179	92.24 122	90.69 219	97.37 178

UWE-MVS		88.56 214	88.91 185	87.50 347	94.17 201	72.19 410	95.82 284	97.05 42	84.96 215	84.78 243	93.51 277	81.33 75	94.75 406	79.43 296	89.17 238	95.57 271

UWE-MVS-28		85.41 288	86.36 247	82.59 427	91.12 337	66.81 456	93.88 362	97.03 43	83.86 256	78.55 326	93.84 268	77.76 132	88.55 476	73.47 371	87.69 272	92.41 330

DELS-MVS		94.98 16	94.49 35	96.44 7	96.42 109	90.59 8	99.21 9	97.02 44	94.40 15	91.46 120	97.08 131	83.32 63	99.69 67	92.83 112	98.70 33	99.04 33
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 88	94.94 170	86.26 42	81.62 481	97.00 45		88.32 180	94.30 249	91.23 6	96.21 326	88.49 200	97.43 81	98.00 109

myMVS_eth3d28		92.72 78	92.23 93	94.21 50	96.16 117	87.46 32	97.37 135	96.99 46	88.13 103	88.18 185	95.47 190	84.12 54	98.04 181	92.46 120	91.17 210	97.14 200

lecture		93.17 60	93.57 57	91.96 185	97.80 71	78.79 294	98.50 51	96.98 47	86.61 161	94.75 70	98.16 63	78.36 120	99.35 102	93.89 91	97.12 95	97.75 133

fmvsm_s_conf0.5_n_a		93.34 59	93.71 51	92.22 164	93.38 231	81.71 180	98.86 36	96.98 47	91.64 45	96.85 30	98.55 29	75.58 184	99.77 44	97.88 33	93.68 167	95.18 285

DPM-MVS		96.21 3	95.53 16	98.26 1	96.26 114	95.09 1	99.15 13	96.98 47	93.39 24	96.45 39	98.79 15	90.17 10	99.99 1	89.33 181	99.25 6	99.70 4

gg-mvs-nofinetune		85.48 286	82.90 316	93.24 97	94.51 188	85.82 54	79.22 488	96.97 50	61.19 481	87.33 199	53.01 518	90.58 7	96.07 330	86.07 227	97.23 89	97.81 129

NCCC		95.63 8	95.94 10	94.69 35	99.21 7	85.15 80	99.16 12	96.96 51	94.11 16	95.59 51	98.64 26	85.07 41	99.91 8	95.61 66	99.10 9	99.00 35

FBQ-MVS		91.64 115	90.94 123	93.73 70	95.88 129	84.93 87	96.78 194	96.95 52	87.21 139	90.53 136	94.44 246	80.88 78	97.92 193	87.30 215	88.50 261	98.33 75

FIs		86.73 261	86.10 251	88.61 310	90.05 364	80.21 241	96.14 252	96.95 52	85.56 192	78.37 329	92.30 295	76.73 155	95.28 375	79.51 294	79.27 341	90.35 345

PVSNet_0	77.72 15	81.70 354	78.95 373	89.94 281	90.77 348	76.72 356	95.96 262	96.95 52	85.01 213	70.24 424	88.53 356	52.32 423	98.20 174	86.68 225	44.08 501	94.89 291

HPM-MVS++		95.32 13	95.48 17	94.85 29	98.62 40	86.04 47	97.81 95	96.93 55	92.45 32	95.69 49	98.50 36	85.38 38	99.85 17	94.75 80	99.18 7	98.65 59

MSLP-MVS++		94.28 36	94.39 38	93.97 59	98.30 55	84.06 104	98.64 45	96.93 55	90.71 59	93.08 92	98.70 24	79.98 94	99.21 110	94.12 89	99.07 11	98.63 60

testing99		91.91 107	91.35 111	93.60 81	95.98 124	85.70 57	97.31 140	96.92 57	86.82 153	88.91 167	95.25 198	84.26 53	97.89 196	88.80 192	87.94 269	97.21 193

testing91		91.90 108	91.31 113	93.66 77	95.99 123	85.68 59	97.39 134	96.89 58	86.75 157	88.85 169	95.23 202	83.93 58	97.90 195	88.91 185	87.89 270	97.41 174

UniMVSNet (Re)		85.31 291	84.23 286	88.55 311	89.75 371	80.55 225	96.72 199	96.89 58	85.42 196	78.40 328	88.93 349	75.38 191	95.52 365	78.58 308	68.02 421	89.57 362

FC-MVSNet-test		85.96 273	85.39 263	87.66 340	89.38 383	78.02 320	95.65 293	96.87 60	85.12 209	77.34 338	91.94 307	76.28 166	94.74 407	77.09 327	78.82 345	90.21 348

EI-MVSNet-Vis-set		91.84 110	91.77 104	92.04 182	97.60 80	81.17 195	96.61 206	96.87 60	88.20 101	89.19 161	97.55 107	78.69 114	99.14 120	90.29 163	90.94 215	95.80 258

IU-MVS					99.03 20	85.34 69		96.86 62	92.05 43	98.74 2				98.15 23	98.97 17	99.42 14

BP-MVS1		93.55 55	93.50 59	93.71 73	92.64 269	85.39 68	97.78 97	96.84 63	89.52 77	92.00 111	97.06 133	88.21 23	98.03 182	91.45 134	96.00 132	97.70 139

MSC_two_6792asdad				97.14 4	99.05 14	92.19 4		96.83 64					99.81 29	98.08 27	98.81 24	99.43 12

No_MVS				97.14 4	99.05 14	92.19 4		96.83 64					99.81 29	98.08 27	98.81 24	99.43 12

EI-MVSNet-UG-set		91.35 125	91.22 114	91.73 203	97.39 94	80.68 218	96.47 218	96.83 64	87.92 108	88.30 182	97.36 114	77.84 129	99.13 122	89.43 180	89.45 231	95.37 277

test-260524					99.01 23	85.87 53		96.82 67		95.25 56		86.23 35	99.92 7	97.87 34	98.71 31

TestfortrainingZip a		94.24 39	94.19 44	94.40 42	99.06 11	84.33 98	98.35 58	96.81 68	87.65 119	95.97 47	98.83 11	84.06 55	99.89 11	91.98 129	95.03 144	98.97 38

SED-MVS		95.88 6	96.22 5	94.87 28	99.03 20	85.03 84	99.12 17	96.78 69	88.72 86	97.79 12	98.91 3	88.48 20	99.82 25	98.15 23	98.97 17	99.74 1

test_241102_TWO								96.78 69	88.72 86	97.70 15	98.91 3	87.86 25	99.82 25	98.15 23	99.00 15	99.47 10

test_241102_ONE					99.03 20	85.03 84		96.78 69	88.72 86	97.79 12	98.90 6	88.48 20	99.82 25

test0726					99.05 14	85.18 75	99.11 20	96.78 69	88.75 84	97.65 19	98.91 3	87.69 26

MSP-MVS		95.62 9	96.54 1	92.86 117	98.31 54	80.10 247	97.42 131	96.78 69	92.20 38	97.11 25	98.29 54	93.46 1	99.10 124	96.01 59	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							96.87 183	96.78 69	77.39 384				99.52 88	79.95 291		98.43 71

DVP-MVS++		96.05 5	96.41 4	94.96 27	99.05 14	85.34 69	98.13 72	96.77 75	88.38 94	97.70 15	98.77 17	92.06 3	99.84 19	97.47 42	99.37 1	99.70 4

test_0728_SECOND				95.14 22	99.04 19	86.14 46	99.06 24	96.77 75					99.84 19	97.90 31	98.85 21	99.45 11

SMA-MVS		94.70 25	94.68 31	94.76 32	98.02 65	85.94 51	97.47 124	96.77 75	85.32 198	97.92 7	98.70 24	83.09 66	99.84 19	95.79 63	99.08 10	98.49 66
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		91.60 118	91.64 107	91.47 219	95.74 136	78.79 294	96.15 251	96.77 75	88.49 91	88.64 174	97.07 132	72.33 243	99.19 116	93.13 109	96.48 119	96.43 240

3Dnovator	82.32 10	89.33 189	87.64 214	94.42 41	93.73 217	85.70 57	97.73 102	96.75 79	86.73 158	76.21 361	95.93 162	62.17 345	99.68 69	81.67 272	97.81 68	97.88 118

fmvsm_s_conf0.5_n_7		92.88 70	93.82 48	90.08 273	92.79 261	76.45 360	98.54 49	96.74 80	92.28 36	95.22 57	98.49 37	74.91 202	98.15 178	98.28 17	97.13 94	95.63 267

DPE-MVS		95.32 13	95.55 15	94.64 36	98.79 29	84.87 90	97.77 98	96.74 80	86.11 171	96.54 38	98.89 9	88.39 22	99.74 55	97.67 40	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		90.05 166	89.96 156	90.33 266	97.47 85	83.86 106	98.02 81	96.73 82	87.98 106	89.53 155	89.61 342	76.42 161	99.57 83	94.29 86	79.59 338	87.57 422

PVSNet_Blended		93.13 61	92.98 70	93.57 83	97.47 85	83.86 106	99.32 4	96.73 82	91.02 56	89.53 155	96.21 157	76.42 161	99.57 83	94.29 86	95.81 136	97.29 188

ACMMP		90.39 157	89.97 155	91.64 208	97.58 82	78.21 316	96.78 194	96.72 84	84.73 220	84.72 245	97.23 123	71.22 263	99.63 75	88.37 203	92.41 189	97.08 208
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				93.12 104	97.44 89	81.60 186		96.71 85	74.54 414	91.22 127	97.57 103	79.13 105	99.51 90	77.40 326	98.46 44	98.26 84

test_one_0601					98.91 24	84.56 95		96.70 86	88.06 104	96.57 37	98.77 17	88.04 24

HFP-MVS		92.89 69	92.86 76	92.98 111	98.71 31	81.12 197	97.58 114	96.70 86	85.20 203	91.75 117	97.97 80	78.47 117	99.71 63	90.95 141	98.41 47	98.12 96

ACMMPR		92.69 83	92.67 79	92.75 124	98.66 34	80.57 224	97.58 114	96.69 88	85.20 203	91.57 119	97.92 81	77.01 148	99.67 71	90.95 141	98.41 47	98.00 109

DeepPCF-MVS	89.82 1	94.61 26	96.17 6	89.91 282	97.09 102	70.21 433	98.99 30	96.69 88	95.57 2	95.08 62	99.23 2	86.40 34	99.87 13	97.84 35	98.66 34	99.65 7

thisisatest0530		89.65 179	89.02 178	91.53 213	93.46 229	80.78 216	96.52 214	96.67 90	81.69 307	83.79 263	94.90 225	88.85 17	97.68 206	77.80 315	87.49 277	96.14 249

tttt0517		88.57 213	88.19 203	89.71 289	93.00 245	75.99 371	95.67 291	96.67 90	80.78 321	81.82 294	94.40 247	88.97 16	97.58 216	76.05 342	86.31 285	95.57 271

thisisatest0515		90.95 137	90.26 141	93.01 109	94.03 211	84.27 102	97.91 88	96.67 90	83.18 273	86.87 215	95.51 187	88.66 18	97.85 198	80.46 283	89.01 242	96.92 219

fmvsm_s_conf0.5_n_8		94.52 30	95.04 24	92.96 112	95.15 163	81.14 196	99.09 21	96.66 93	95.53 3	97.84 11	98.71 23	76.33 164	99.81 29	99.24 1	96.85 109	97.92 116

ACMMP_NAP		93.46 56	93.23 65	94.17 54	97.16 100	84.28 101	96.82 189	96.65 94	86.24 168	94.27 75	97.99 75	77.94 126	99.83 23	93.39 98	98.57 38	98.39 73

TEST9					98.64 37	83.71 110	97.82 93	96.65 94	84.29 240	95.16 58	98.09 68	84.39 48	99.36 100

train_agg		94.28 36	94.45 36	93.74 68	98.64 37	83.71 110	97.82 93	96.65 94	84.50 230	95.16 58	98.09 68	84.33 49	99.36 100	95.91 62	98.96 19	98.16 91

1314		88.94 200	87.20 228	94.17 54	93.21 236	85.73 56	93.33 377	96.64 97	82.89 282	75.98 364	96.36 154	66.83 311	99.39 96	83.52 256	96.02 131	97.39 177

DeepC-MVS_fast	89.06 2	94.48 32	94.30 41	95.02 24	98.86 27	85.68 59	98.06 78	96.64 97	93.64 22	91.74 118	98.54 31	80.17 90	99.90 9	92.28 121	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	83.64 116	97.81 95	96.63 99	84.50 230	95.10 61	98.11 66	84.33 49	99.23 108

FE-MVS		86.06 272	84.15 289	91.78 199	94.33 197	79.81 253	84.58 473	96.61 100	76.69 397	85.00 239	87.38 377	70.71 273	98.37 167	70.39 393	91.70 200	97.17 199

原ACMM1				91.22 233	97.77 73	78.10 319		96.61 100	81.05 315	91.28 126	97.42 112	77.92 128	98.98 131	79.85 293	98.51 40	96.59 236

MAR-MVS		90.63 146	90.22 143	91.86 191	98.47 48	78.20 317	97.18 149	96.61 100	83.87 254	88.18 185	98.18 59	68.71 291	99.75 52	83.66 252	97.15 93	97.63 146
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	83.22 125		96.60 103	82.88 283	93.61 85	98.06 73	82.93 67	99.14 120	95.51 69	98.49 43

MGCNet		95.58 11	95.44 18	96.01 11	97.63 78	89.26 13	99.27 6	96.59 104	94.71 10	97.08 26	97.99 75	78.69 114	99.86 15	99.15 3	97.85 67	98.91 43

SteuartSystems-ACMMP		94.13 43	94.44 37	93.20 100	95.41 149	81.35 192	99.02 28	96.59 104	89.50 78	94.18 77	98.36 51	83.68 61	99.45 94	94.77 79	98.45 45	98.81 48
Skip Steuart: Steuart Systems R&D Blog.
D2MVS		82.67 339	81.55 336	86.04 375	87.77 403	76.47 358	95.21 314	96.58 106	82.66 289	70.26 422	85.46 413	60.39 362	95.80 345	76.40 338	79.18 342	85.83 450

save fliter					98.24 57	83.34 122	98.61 47	96.57 107	91.32 49

TESTMET0.1,1		89.83 174	89.34 171	91.31 224	92.54 273	80.19 243	97.11 159	96.57 107	86.15 170	86.85 216	91.83 309	79.32 99	96.95 289	81.30 277	92.35 190	96.77 228

agg_prior					98.59 41	83.13 127		96.56 109		94.19 76			99.16 119

0.3-1-1-0.015		87.79 237	85.93 253	93.38 93	89.87 367	85.09 82	98.43 53	96.55 110	81.13 313	87.21 204	89.75 338	77.23 143	97.02 281	86.87 222	66.38 438	98.02 102

0.4-1-1-0.1		87.53 247	85.67 258	93.13 103	89.70 374	84.41 96	98.30 63	96.55 110	80.85 318	86.94 210	89.53 343	76.18 167	96.99 286	86.62 226	66.36 440	97.98 111

0.4-1-1-0.2		87.73 239	85.82 256	93.46 92	89.97 366	85.31 72	98.49 52	96.55 110	81.24 311	87.14 206	89.63 341	76.16 169	97.02 281	86.84 223	66.38 438	98.05 100

旧先验1					97.39 94	79.58 265		96.54 113			98.08 71	84.00 56			97.42 82	97.62 148

WR-MVS_H		81.02 365	80.09 357	83.79 411	88.08 400	71.26 426	94.46 339	96.54 113	80.08 344	72.81 397	86.82 387	70.36 276	92.65 440	64.18 425	67.50 427	87.46 427

fmvsm_s_conf0.5_n_4		93.59 52	94.32 40	91.41 221	93.89 212	79.24 272	98.89 35	96.53 115	92.82 28	97.37 23	98.47 40	77.21 145	99.78 40	98.11 26	95.59 139	95.21 284

9.14			94.26 43		98.10 63		98.14 69	96.52 116	84.74 219	94.83 68	98.80 14	82.80 69	99.37 99	95.95 61	98.42 46

region2R		92.72 78	92.70 78	92.79 122	98.68 32	80.53 230	97.53 119	96.51 117	85.22 201	91.94 114	97.98 78	77.26 139	99.67 71	90.83 148	98.37 50	98.18 89

EPP-MVSNet		89.76 175	89.72 163	89.87 283	93.78 214	76.02 370	97.22 144	96.51 117	79.35 357	85.11 237	95.01 218	84.82 43	97.10 279	87.46 214	88.21 267	96.50 238

ZNCC-MVS		92.75 74	92.60 81	93.23 98	98.24 57	81.82 175	97.63 108	96.50 119	85.00 214	91.05 129	97.74 92	78.38 118	99.80 33	90.48 154	98.34 52	98.07 99

test11								96.50 119

EPNet_dtu		87.65 244	87.89 208	86.93 360	94.57 180	71.37 425	96.72 199	96.50 119	88.56 90	87.12 207	95.02 217	75.91 176	94.01 424	66.62 411	90.00 225	95.42 276
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testdata				90.13 272	95.92 128	74.17 390		96.49 122	73.49 423	94.82 69	97.99 75	78.80 112	97.93 188	83.53 255	97.52 77	98.29 81

fmvsm_s_conf0.5_n_6		94.17 40	94.70 30	92.58 138	93.50 228	81.20 194	99.08 22	96.48 123	92.24 37	98.62 3	98.39 47	78.58 116	99.72 60	98.08 27	97.36 85	96.81 225

DVP-MVS		95.58 11	95.91 11	94.57 38	99.05 14	85.18 75	99.06 24	96.46 124	88.75 84	96.69 32	98.76 19	87.69 26	99.76 47	97.90 31	98.85 21	98.77 49
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	78.41 305	95.87 280	96.46 124	71.97 440	89.66 151	97.45 108	76.33 164			98.24 55	98.30 80

XVS		92.69 83	92.71 77	92.63 133	98.52 43	80.29 236	97.37 135	96.44 126	87.04 146	91.38 121	97.83 89	77.24 141	99.59 79	90.46 156	98.07 59	98.02 102

X-MVStestdata		86.26 269	84.14 290	92.63 133	98.52 43	80.29 236	97.37 135	96.44 126	87.04 146	91.38 121	20.73 539	77.24 141	99.59 79	90.46 156	98.07 59	98.02 102

SF-MVS		94.17 40	94.05 47	94.55 39	97.56 83	85.95 49	97.73 102	96.43 128	84.02 247	95.07 63	98.74 21	82.93 67	99.38 97	95.42 71	98.51 40	98.32 77

TSAR-MVS + MP.		94.79 24	95.17 23	93.64 78	97.66 77	84.10 103	95.85 282	96.42 129	91.26 50	97.49 22	96.80 144	86.50 32	98.49 157	95.54 68	99.03 13	98.33 75
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 29	94.75 28	93.96 60	98.84 28	83.40 121	98.04 80	96.41 130	85.79 185	95.00 64	98.28 55	84.32 52	99.18 117	97.35 45	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		85.49 285	84.59 278	88.21 326	89.44 382	79.36 269	96.71 201	96.41 130	85.22 201	78.11 332	90.98 320	76.97 150	95.14 387	79.14 302	68.30 418	90.12 351

test_prior				93.09 106	98.68 32	81.91 168		96.40 132					99.06 127			98.29 81

CP-MVS		92.54 89	92.60 81	92.34 153	98.50 46	79.90 252	98.40 56	96.40 132	84.75 218	90.48 139	98.09 68	77.40 137	99.21 110	91.15 138	98.23 56	97.92 116

fmvsm_s_conf0.5_n_10		94.36 34	94.73 29	93.23 98	95.19 159	82.87 133	99.18 10	96.39 134	93.97 19	97.91 9	98.53 33	75.88 177	99.82 25	98.58 12	96.95 102	97.00 211

CANet		94.89 19	94.64 32	95.63 14	97.55 84	88.12 20	99.06 24	96.39 134	94.07 18	95.34 54	97.80 90	76.83 153	99.87 13	97.08 51	97.64 74	98.89 44

GST-MVS		92.43 94	92.22 95	93.04 108	98.17 60	81.64 183	97.40 133	96.38 136	84.71 221	90.90 132	97.40 113	77.55 135	99.76 47	89.75 172	97.74 71	97.72 136

alignmvs		92.97 66	92.26 92	95.12 23	95.54 144	87.77 25	98.67 43	96.38 136	88.04 105	93.01 93	97.45 108	79.20 104	98.60 148	93.25 104	88.76 245	98.99 37

PAPM		92.87 72	92.40 86	94.30 44	92.25 292	87.85 24	96.40 226	96.38 136	91.07 54	88.72 173	96.90 137	82.11 72	97.37 256	90.05 167	97.70 72	97.67 141

fmvsm_l_conf0.5_n_3		94.61 26	94.92 27	93.68 76	94.52 184	82.80 135	99.33 3	96.37 139	95.08 6	97.59 21	98.48 39	77.40 137	99.79 37	98.28 17	97.21 90	98.44 70

test_fmvsmconf_n		93.99 45	94.36 39	92.86 117	92.82 258	81.12 197	99.26 7	96.37 139	93.47 23	95.16 58	98.21 57	79.00 107	99.64 73	98.21 21	96.73 113	97.83 125

fmvsm_l_conf0.5_n_9		94.91 17	95.60 13	92.84 120	95.20 158	80.55 225	99.45 2	96.36 141	95.17 4	98.48 4	98.55 29	80.53 84	99.78 40	98.87 7	97.79 70	98.19 88

test12				94.25 47	98.34 52	85.55 65		96.35 142		92.36 103		80.84 80	99.22 109		98.31 53	97.98 111

MTGPA								96.33 143

MTAPA		92.45 92	92.31 90	92.86 117	97.90 67	80.85 214	92.88 389	96.33 143	87.92 108	90.20 144	98.18 59	76.71 156	99.76 47	92.57 118	98.09 58	97.96 115

reproduce_monomvs		87.80 236	87.60 218	88.40 314	96.56 106	80.26 239	95.80 285	96.32 145	91.56 47	73.60 384	88.36 361	88.53 19	96.25 324	90.47 155	67.23 430	88.67 397

ET-MVSNet_ETH3D		90.01 167	89.03 177	92.95 113	94.38 195	86.77 37	98.14 69	96.31 146	89.30 80	63.33 457	96.72 148	90.09 11	93.63 432	90.70 152	82.29 325	98.46 68

EPMVS		87.47 249	85.90 254	92.18 168	95.41 149	82.26 154	87.00 456	96.28 147	85.88 183	84.23 253	85.57 410	75.07 200	96.26 322	71.14 388	92.50 184	98.03 101

nomal-1		89.71 177	89.18 174	91.30 226	94.43 192	81.03 201	94.35 345	96.27 148	85.05 211	83.05 277	90.78 323	80.87 79	97.21 267	89.53 178	88.34 264	95.66 266

WB-MVSnew		84.08 315	83.51 304	85.80 377	91.34 332	76.69 357	95.62 295	96.27 148	81.77 305	81.81 295	92.81 287	58.23 378	94.70 408	66.66 410	87.06 278	85.99 447

CDPH-MVS		93.12 62	92.91 73	93.74 68	98.65 36	83.88 105	97.67 106	96.26 150	83.00 280	93.22 89	98.24 56	81.31 76	99.21 110	89.12 182	98.74 30	98.14 93

WR-MVS		84.32 311	82.96 314	88.41 313	89.38 383	80.32 235	96.59 207	96.25 151	83.97 249	76.63 350	90.36 330	67.53 301	94.86 402	75.82 345	70.09 402	90.06 355

fmvsm_s_conf0.1_n		92.93 68	93.16 67	92.24 161	90.52 351	81.92 167	98.42 55	96.24 152	91.17 51	96.02 45	98.35 52	75.34 195	99.74 55	97.84 35	94.58 150	95.05 288

UGNet		87.73 239	86.55 246	91.27 228	95.16 162	79.11 278	96.35 231	96.23 153	88.14 102	87.83 193	90.48 327	50.65 431	99.09 125	80.13 289	94.03 156	95.60 269
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		78.14 394	75.42 402	86.31 370	88.33 398	79.24 272	94.41 341	96.22 154	73.51 421	69.81 427	85.52 412	55.43 410	95.75 350	47.65 489	67.86 423	83.95 466

FOURS1					98.51 45	78.01 321	98.13 72	96.21 155	83.04 277	94.39 74

MP-MVS		92.61 87	92.67 79	92.42 148	98.13 62	79.73 260	97.33 138	96.20 156	85.63 188	90.53 136	97.66 95	78.14 124	99.70 66	92.12 125	98.30 54	97.85 123
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PAPR		92.74 75	92.17 96	94.45 40	98.89 26	84.87 90	97.20 147	96.20 156	87.73 114	88.40 178	98.12 65	78.71 113	99.76 47	87.99 205	96.28 121	98.74 51

SD-MVS		94.84 21	95.02 26	94.29 45	97.87 70	84.61 93	97.76 100	96.19 158	89.59 76	96.66 34	98.17 62	84.33 49	99.60 78	96.09 58	98.50 42	98.66 58
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		91.71 114	91.85 101	91.29 227	94.94 170	82.69 137	87.89 449	96.17 159	85.94 181	87.27 202	94.31 248	90.27 9	95.65 357	94.04 90	95.86 134	95.53 273

fmvsm_l_conf0.5_n		94.89 19	95.24 20	93.86 62	94.42 193	84.61 93	99.13 16	96.15 160	92.06 41	97.92 7	98.52 35	84.52 47	99.74 55	98.76 10	95.67 137	97.22 190

CHOSEN 1792x2688		91.07 133	90.21 144	93.64 78	95.18 161	83.53 118	96.26 239	96.13 161	88.92 83	84.90 241	93.10 283	72.86 231	99.62 77	88.86 186	95.67 137	97.79 130

PAPM_NR		91.46 120	90.82 125	93.37 94	98.50 46	81.81 176	95.03 327	96.13 161	84.65 223	86.10 227	97.65 99	79.24 103	99.75 52	83.20 258	96.88 105	98.56 63

CostFormer		89.08 195	88.39 198	91.15 235	93.13 241	79.15 277	88.61 441	96.11 163	83.14 274	89.58 153	86.93 386	83.83 60	96.87 298	88.22 204	85.92 292	97.42 173

mPP-MVS		91.88 109	91.82 102	92.07 176	98.38 50	78.63 298	97.29 142	96.09 164	85.12 209	88.45 177	97.66 95	75.53 185	99.68 69	89.83 168	98.02 62	97.88 118

APD-MVS		93.61 51	93.59 55	93.69 75	98.76 30	83.26 124	97.21 145	96.09 164	82.41 294	94.65 71	98.21 57	81.96 74	98.81 142	94.65 82	98.36 51	99.01 34
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MDTV_nov1_ep13			83.69 294		94.09 207	81.01 202	86.78 458	96.09 164	83.81 258	84.75 244	84.32 427	74.44 211	96.54 312	63.88 427	85.07 301

FA-MVS(test-final)		87.71 242	86.23 250	92.17 169	94.19 200	80.55 225	87.16 455	96.07 167	82.12 299	85.98 228	88.35 362	72.04 253	98.49 157	80.26 286	89.87 227	97.48 165

KinetiMVS		89.13 194	87.95 207	92.65 130	92.16 299	82.39 150	97.04 167	96.05 168	86.59 162	88.08 188	94.85 229	61.54 357	98.38 166	81.28 278	93.99 161	97.19 197

QAPM		86.88 256	84.51 279	93.98 58	94.04 209	85.89 52	97.19 148	96.05 168	73.62 420	75.12 375	95.62 180	62.02 352	99.74 55	70.88 389	96.06 129	96.30 247

MP-MVS-pluss		92.58 88	92.35 87	93.29 95	97.30 98	82.53 140	96.44 221	96.04 170	84.68 222	89.12 163	98.37 50	77.48 136	99.74 55	93.31 103	98.38 49	97.59 151
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.1_n_a		92.38 95	92.49 84	92.06 177	88.08 400	81.62 185	97.97 84	96.01 171	90.62 60	96.58 36	98.33 53	74.09 215	99.71 63	97.23 47	93.46 172	94.86 292

fmvsm_s_conf0.5_n_9		94.52 30	95.22 21	92.41 149	95.79 135	78.61 299	98.73 39	96.00 172	94.91 9	97.73 14	98.73 22	79.09 106	99.79 37	99.14 4	96.86 107	98.83 46

fmvsm_l_conf0.5_n_a		94.91 17	95.30 19	93.72 72	94.50 189	84.30 100	99.14 15	96.00 172	91.94 44	97.91 9	98.60 27	84.78 44	99.77 44	98.84 8	96.03 130	97.08 208

tpm2		87.35 250	86.26 248	90.62 254	92.93 255	78.67 297	88.06 448	95.99 174	79.33 358	87.40 197	86.43 397	80.28 87	96.40 316	80.23 287	85.73 296	96.79 226

SDMVSNet		87.02 253	85.61 259	91.24 230	94.14 203	83.30 123	93.88 362	95.98 175	84.30 238	79.63 318	92.01 300	58.23 378	97.68 206	90.28 165	82.02 326	92.75 326

DeepC-MVS	86.58 3	91.53 119	91.06 120	92.94 114	94.52 184	81.89 170	95.95 263	95.98 175	90.76 58	83.76 264	96.76 145	73.24 227	99.71 63	91.67 133	96.96 101	97.22 190
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 46	94.53 33	92.20 167	94.41 194	80.04 249	98.90 34	95.96 177	94.53 13	97.63 20	98.58 28	75.95 174	99.79 37	98.25 19	96.60 115	96.77 228

test-LLR		88.48 215	87.98 206	89.98 278	92.26 290	77.23 346	97.11 159	95.96 177	83.76 260	86.30 224	91.38 312	72.30 244	96.78 305	80.82 280	91.92 196	95.94 254

test-mter		88.95 199	88.60 189	89.98 278	92.26 290	77.23 346	97.11 159	95.96 177	85.32 198	86.30 224	91.38 312	76.37 163	96.78 305	80.82 280	91.92 196	95.94 254

DP-MVS Recon		91.72 113	90.85 124	94.34 43	99.50 1	85.00 86	98.51 50	95.96 177	80.57 326	88.08 188	97.63 101	76.84 151	99.89 11	85.67 230	94.88 145	98.13 95

reproduce-ours		92.70 81	93.02 68	91.75 200	97.45 87	77.77 333	96.16 249	95.94 181	84.12 243	92.45 99	98.43 43	80.06 92	99.24 106	95.35 72	97.18 91	98.24 85

our_new_method		92.70 81	93.02 68	91.75 200	97.45 87	77.77 333	96.16 249	95.94 181	84.12 243	92.45 99	98.43 43	80.06 92	99.24 106	95.35 72	97.18 91	98.24 85

cdsmvs_eth3d_5k		21.43 497	28.57 494	0.00 543	0.00 567	0.00 570	0.00 555	95.93 183	0.00 562	0.00 563	97.66 95	63.57 336	0.00 563	0.00 562	0.00 562	0.00 559

reproduce_model		92.53 90	92.87 74	91.50 216	97.41 91	77.14 350	96.02 259	95.91 184	83.65 265	92.45 99	98.39 47	79.75 97	99.21 110	95.27 75	96.98 100	98.14 93

fmvsm_s_conf0.5_n_5		93.57 54	93.75 49	93.01 109	92.87 257	82.73 136	98.93 33	95.90 185	90.96 57	95.61 50	98.39 47	76.57 157	99.63 75	98.32 16	96.24 122	96.68 234

fmvsm_s_conf0.5_n_2		92.97 66	93.38 63	91.73 203	94.10 206	80.64 220	98.96 31	95.89 186	94.09 17	97.05 27	98.40 46	68.92 290	99.80 33	98.53 14	94.50 152	94.74 296

hse-mvs2		88.22 224	88.21 202	88.25 322	93.54 222	73.41 394	95.41 304	95.89 186	90.39 65	92.22 106	94.22 252	74.70 205	96.66 310	93.14 107	64.37 446	94.69 301

AUN-MVS		86.25 270	85.57 260	88.26 320	93.57 221	73.38 395	95.45 302	95.88 188	83.94 251	85.47 234	94.21 253	73.70 223	96.67 309	83.54 254	64.41 445	94.73 300

TAMVS		88.48 215	87.79 211	90.56 256	91.09 338	79.18 275	96.45 220	95.88 188	83.64 266	83.12 275	93.33 278	75.94 175	95.74 353	82.40 265	88.27 266	96.75 231

PVSNet_Blended_VisFu		91.24 127	90.77 126	92.66 129	95.09 164	82.40 148	97.77 98	95.87 190	88.26 98	86.39 222	93.94 265	76.77 154	99.27 104	88.80 192	94.00 159	96.31 246

OpenMVS	79.58 14	86.09 271	83.62 301	93.50 87	90.95 340	86.71 39	97.44 127	95.83 191	75.35 405	72.64 398	95.72 170	57.42 396	99.64 73	71.41 383	95.85 135	94.13 309

CDS-MVSNet		89.50 182	88.96 182	91.14 236	91.94 315	80.93 210	97.09 163	95.81 192	84.26 241	84.72 245	94.20 254	80.31 86	95.64 358	83.37 257	88.96 243	96.85 224
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PS-MVSNAJ		94.17 40	93.52 58	96.10 10	95.65 139	92.35 2	98.21 67	95.79 193	92.42 33	96.24 41	98.18 59	71.04 266	99.17 118	96.77 54	97.39 83	96.79 226

testing3		80.74 369	81.17 342	79.44 448	91.15 336	63.48 471	97.16 153	95.76 194	80.83 319	71.36 409	93.15 282	78.22 122	87.30 486	43.19 496	79.67 337	87.55 425

SR-MVS		92.16 100	92.27 91	91.83 198	98.37 51	78.41 305	96.67 205	95.76 194	82.19 298	91.97 112	98.07 72	76.44 160	98.64 146	93.71 95	97.27 88	98.45 69

3Dnovator+	82.88 8	89.63 180	87.85 209	94.99 25	94.49 190	86.76 38	97.84 92	95.74 196	86.10 172	75.47 372	96.02 161	65.00 325	99.51 90	82.91 262	97.07 98	98.72 56

HPM-MVS		91.62 117	91.53 109	91.89 189	97.88 69	79.22 274	96.99 169	95.73 197	82.07 300	89.50 157	97.19 125	75.59 183	98.93 137	90.91 143	97.94 64	97.54 155
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
fmvsm_l_mol_unc0.5_1		96.23 2	96.47 3	95.50 17	94.71 177	88.70 16	99.47 1	95.70 198	95.05 7	98.42 5	98.85 10	89.10 15	99.77 44	98.76 10	98.14 57	98.02 102

ab-mvs		87.08 252	84.94 275	93.48 89	93.34 232	83.67 115	88.82 438	95.70 198	81.18 312	84.55 249	90.14 335	62.72 341	98.94 136	85.49 232	82.54 322	97.85 123

guyue		89.85 172	89.33 172	91.40 222	92.53 274	80.15 245	96.82 189	95.68 200	89.66 75	86.43 221	94.23 251	67.00 307	97.16 271	91.96 130	89.65 229	96.89 220

xiu_mvs_v2_base		93.92 47	93.26 64	95.91 12	95.07 166	92.02 6	98.19 68	95.68 200	92.06 41	96.01 46	98.14 64	70.83 271	98.96 132	96.74 56	96.57 116	96.76 230

CP-MVSNet		81.01 366	80.08 358	83.79 411	87.91 402	70.51 429	94.29 353	95.65 202	80.83 319	72.54 400	88.84 350	63.71 335	92.32 445	68.58 402	68.36 417	88.55 399

PatchmatchNet		86.83 258	85.12 272	91.95 186	94.12 205	82.27 153	86.55 460	95.64 203	84.59 225	82.98 279	84.99 422	77.26 139	95.96 337	68.61 401	91.34 207	97.64 144
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
API-MVS		90.18 164	88.97 181	93.80 64	98.66 34	82.95 131	97.50 123	95.63 204	75.16 408	86.31 223	97.69 93	72.49 239	99.90 9	81.26 279	96.07 128	98.56 63

BridgeMVS		94.60 28	94.30 41	95.48 18	96.45 108	88.82 15	96.33 233	95.58 205	91.12 52	95.84 48	93.87 267	83.47 62	98.37 167	97.26 46	98.81 24	99.24 24

AdaColmap		88.81 205	87.61 217	92.39 150	99.33 5	79.95 250	96.70 203	95.58 205	77.51 383	83.05 277	96.69 149	61.90 355	99.72 60	84.29 240	93.47 171	97.50 163

SCA		85.63 280	83.64 300	91.60 211	92.30 283	81.86 172	92.88 389	95.56 207	84.85 216	82.52 280	85.12 420	58.04 381	95.39 368	73.89 366	87.58 275	97.54 155

dp		84.30 312	82.31 325	90.28 268	94.24 199	77.97 322	86.57 459	95.53 208	79.94 348	80.75 304	85.16 418	71.49 262	96.39 317	63.73 428	83.36 311	96.48 239

HyFIR lowres test		89.36 188	88.60 189	91.63 210	94.91 172	80.76 217	95.60 296	95.53 208	82.56 291	84.03 257	91.24 315	78.03 125	96.81 302	87.07 219	88.41 263	97.32 183

WBMVS		87.73 239	86.79 240	90.56 256	95.61 141	85.68 59	97.63 108	95.52 210	83.77 259	78.30 330	88.44 360	86.14 36	95.78 347	82.54 264	73.15 382	90.21 348

APD-MVS_3200maxsize		91.23 128	91.35 111	90.89 247	97.89 68	76.35 363	96.30 236	95.52 210	79.82 349	91.03 130	97.88 86	74.70 205	98.54 154	92.11 126	96.89 104	97.77 131

lupinMVS		93.87 48	93.58 56	94.75 33	93.00 245	88.08 21	99.15 13	95.50 212	91.03 55	94.90 65	97.66 95	78.84 110	97.56 218	94.64 83	97.46 78	98.62 61

tt0805		81.20 363	79.06 372	87.61 341	86.50 416	72.97 404	93.66 366	95.48 213	74.11 416	76.23 360	91.99 302	41.36 470	97.40 248	77.44 325	74.78 371	92.45 329

HPM-MVS_fast		90.38 159	90.17 146	91.03 239	97.61 79	77.35 344	97.15 155	95.48 213	79.51 355	88.79 170	96.90 137	71.64 259	98.81 142	87.01 220	97.44 80	96.94 216

VPNet		84.69 302	82.92 315	90.01 276	89.01 385	83.45 120	96.71 201	95.46 215	85.71 187	79.65 317	92.18 299	56.66 402	96.01 333	83.05 261	67.84 424	90.56 342

114514_t		88.79 207	87.57 219	92.45 144	98.21 59	81.74 178	96.99 169	95.45 216	75.16 408	82.48 281	95.69 173	68.59 292	98.50 156	80.33 284	95.18 142	97.10 203

SR-MVS-dyc-post		91.29 126	91.45 110	90.80 249	97.76 75	76.03 368	96.20 246	95.44 217	80.56 327	90.72 134	97.84 87	75.76 179	98.61 147	91.99 127	96.79 110	97.75 133

RE-MVS-def			91.18 118		97.76 75	76.03 368	96.20 246	95.44 217	80.56 327	90.72 134	97.84 87	73.36 226		91.99 127	96.79 110	97.75 133

JIA-IIPM		79.00 385	77.20 384	84.40 406	89.74 373	64.06 468	75.30 498	95.44 217	62.15 475	81.90 292	59.08 512	78.92 108	95.59 362	66.51 414	85.78 295	93.54 319

RPMNet		79.85 375	75.92 395	91.64 208	90.16 361	79.75 257	79.02 490	95.44 217	58.43 493	82.27 288	72.55 493	73.03 230	98.41 165	46.10 491	86.25 286	96.75 231

PRO-TEST		93.79 49	93.63 53	94.29 45	95.54 144	86.59 40	97.30 141	95.42 221	92.49 31	95.39 52	97.33 115	75.72 180	97.16 271	97.19 49	96.29 120	99.11 29

MVSMamba_PlusPlus		92.37 96	91.55 108	94.83 30	95.37 151	87.69 27	95.60 296	95.42 221	74.65 413	93.95 80	92.81 287	83.11 65	97.70 204	94.49 84	98.53 39	99.11 29

DU-MVS		84.57 307	83.33 307	88.28 319	88.76 386	79.36 269	96.43 223	95.41 223	85.42 196	78.11 332	90.82 321	67.61 298	95.14 387	79.14 302	68.30 418	90.33 346

EI-MVSNet		85.80 276	85.20 268	87.59 343	91.55 327	77.41 342	95.13 321	95.36 224	80.43 332	80.33 310	94.71 234	73.72 221	95.97 334	76.96 330	78.64 347	89.39 363

MVSTER		89.25 192	88.92 184	90.24 269	95.98 124	84.66 92	96.79 192	95.36 224	87.19 140	80.33 310	90.61 326	90.02 12	95.97 334	85.38 233	78.64 347	90.09 353

CPTT-MVS		89.72 176	89.87 161	89.29 295	98.33 53	73.30 397	97.70 104	95.35 226	75.68 403	87.40 197	97.44 111	70.43 275	98.25 172	89.56 177	96.90 103	96.33 245

EIA-MVS		91.73 111	92.05 99	90.78 251	94.52 184	76.40 362	98.06 78	95.34 227	89.19 81	88.90 168	97.28 121	77.56 134	97.73 203	90.77 149	96.86 107	98.20 87

tpmvs		83.04 333	80.77 347	89.84 284	95.43 148	77.96 323	85.59 466	95.32 228	75.31 407	76.27 359	83.70 433	73.89 217	97.41 246	59.53 448	81.93 328	94.14 308

usedtu_dtu_shiyan1		85.03 295	83.24 308	90.37 263	86.62 414	86.24 43	96.23 242	95.30 229	84.55 227	77.22 341	88.47 358	67.85 294	95.27 376	76.59 333	76.35 359	89.61 360

FE-MVSNET3		85.03 295	83.24 308	90.37 263	86.62 414	86.24 43	96.23 242	95.30 229	84.55 227	77.22 341	88.47 358	67.85 294	95.27 376	76.59 333	76.35 359	89.61 360

PS-CasMVS		80.27 373	79.18 369	83.52 417	87.56 406	69.88 435	94.08 356	95.29 231	80.27 339	72.08 403	88.51 357	59.22 372	92.23 447	67.49 404	68.15 420	88.45 405

TSAR-MVS + GP.		94.35 35	94.50 34	93.89 61	97.38 96	83.04 129	98.10 74	95.29 231	91.57 46	93.81 81	97.45 108	86.64 31	99.43 95	96.28 57	94.01 158	99.20 26

tpmrst		88.36 219	87.38 225	91.31 224	94.36 196	79.92 251	87.32 453	95.26 233	85.32 198	88.34 179	86.13 403	80.60 83	96.70 307	83.78 246	85.34 300	97.30 186

SSC-MVS3.2		81.06 364	79.49 368	85.75 380	89.78 369	73.00 403	94.40 344	95.23 234	83.76 260	76.61 352	87.82 371	49.48 438	94.88 400	66.80 408	71.56 389	89.38 365

ETV-MVS		92.72 78	92.87 74	92.28 159	94.54 183	81.89 170	97.98 82	95.21 235	89.77 74	93.11 91	96.83 141	77.23 143	97.50 231	95.74 64	95.38 141	97.44 172

NR-MVSNet		83.35 325	81.52 338	88.84 304	88.76 386	81.31 193	94.45 340	95.16 236	84.65 223	67.81 434	90.82 321	70.36 276	94.87 401	74.75 357	66.89 434	90.33 346

test_fmvsmconf0.1_n		93.08 64	93.22 66	92.65 130	88.45 395	80.81 215	99.00 29	95.11 237	93.21 25	94.00 79	97.91 83	76.84 151	99.59 79	97.91 30	96.55 117	97.54 155

jason		92.73 76	92.23 93	94.21 50	90.50 352	87.30 33	98.65 44	95.09 238	90.61 61	92.76 98	97.13 127	75.28 196	97.30 260	93.32 102	96.75 112	98.02 102
jason: jason.
tpm cat1		83.63 322	81.38 339	90.39 262	93.53 227	78.19 318	85.56 467	95.09 238	70.78 446	78.51 327	83.28 438	74.80 204	97.03 280	66.77 409	84.05 306	95.95 253

cascas		86.50 262	84.48 281	92.55 139	92.64 269	85.95 49	97.04 167	95.07 240	75.32 406	80.50 306	91.02 318	54.33 419	97.98 187	86.79 224	87.62 273	93.71 317

GDP-MVS		92.85 73	92.55 83	93.75 67	92.82 258	85.76 55	97.63 108	95.05 241	88.34 96	93.15 90	97.10 130	86.92 29	98.01 185	87.95 206	94.00 159	97.47 166

CVMVSNet		84.83 300	85.57 260	82.63 426	91.55 327	60.38 483	95.13 321	95.03 242	80.60 325	82.10 290	94.71 234	66.40 315	90.19 469	74.30 363	90.32 221	97.31 185

test0.0.03 1		82.79 337	82.48 323	83.74 413	86.81 412	72.22 407	96.52 214	95.03 242	83.76 260	73.00 394	93.20 279	72.30 244	88.88 474	64.15 426	77.52 356	90.12 351

PMMVS		89.46 183	89.92 158	88.06 330	94.64 178	69.57 440	96.22 244	94.95 244	87.27 135	91.37 123	96.54 151	65.88 317	97.39 250	88.54 198	93.89 163	97.23 189

CS-MVS		92.73 76	93.48 60	90.48 259	96.27 113	75.93 373	98.55 48	94.93 245	89.32 79	94.54 73	97.67 94	78.91 109	97.02 281	93.80 92	97.32 87	98.49 66

Anonymous20240529		83.15 330	80.60 351	90.80 249	95.74 136	78.27 311	96.81 191	94.92 246	60.10 486	81.89 293	92.54 291	45.82 453	98.82 141	79.25 301	78.32 353	95.31 279

mvs_anonymous		88.68 208	87.62 216	91.86 191	94.80 175	81.69 181	93.53 372	94.92 246	82.03 301	78.87 325	90.43 329	75.77 178	95.34 371	85.04 235	93.16 176	98.55 65

CLD-MVS		87.97 232	87.48 222	89.44 293	92.16 299	80.54 229	98.14 69	94.92 246	91.41 48	79.43 320	95.40 193	62.34 344	97.27 263	90.60 153	82.90 317	90.50 343
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		90.54 149	89.54 167	93.55 84	92.31 280	87.58 29	96.99 169	94.87 249	87.23 136	93.27 86	97.56 104	57.43 393	98.32 169	92.72 114	93.46 172	94.74 296

xiu_mvs_v1_base		90.54 149	89.54 167	93.55 84	92.31 280	87.58 29	96.99 169	94.87 249	87.23 136	93.27 86	97.56 104	57.43 393	98.32 169	92.72 114	93.46 172	94.74 296

xiu_mvs_v1_base_debi		90.54 149	89.54 167	93.55 84	92.31 280	87.58 29	96.99 169	94.87 249	87.23 136	93.27 86	97.56 104	57.43 393	98.32 169	92.72 114	93.46 172	94.74 296

fmvsm_s_conf0.5_n_11		94.41 33	95.19 22	92.09 173	95.65 139	80.91 212	99.23 8	94.85 252	94.92 8	97.68 17	98.82 13	79.31 100	99.78 40	98.83 9	97.38 84	95.60 269

GA-MVS		85.79 277	84.04 292	91.02 241	89.47 381	80.27 238	96.90 182	94.84 253	85.57 190	80.88 301	89.08 346	56.56 403	96.47 315	77.72 318	85.35 299	96.34 243

TranMVSNet+NR-MVSNet		83.24 329	81.71 334	87.83 334	87.71 404	78.81 288	96.13 254	94.82 254	84.52 229	76.18 362	90.78 323	64.07 333	94.60 412	74.60 361	66.59 437	90.09 353

HQP3-MVS								94.80 255							83.01 314

HQP-MVS		87.91 234	87.55 220	88.98 302	92.08 305	78.48 301	97.63 108	94.80 255	90.52 62	82.30 284	94.56 238	65.40 321	97.32 258	87.67 212	83.01 314	91.13 335

TAPA-MVS	81.61 12	85.02 297	83.67 296	89.06 299	96.79 104	73.27 400	95.92 266	94.79 257	74.81 411	80.47 307	96.83 141	71.07 265	98.19 175	49.82 484	92.57 182	95.71 265
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PEN-MVS		79.47 381	78.26 377	83.08 420	86.36 418	68.58 444	93.85 364	94.77 258	79.76 350	71.37 408	88.55 354	59.79 364	92.46 441	64.50 423	65.40 442	88.19 410

SPE-MVS-test		92.98 65	93.67 52	90.90 246	96.52 107	76.87 352	98.68 42	94.73 259	90.36 67	94.84 67	97.89 85	77.94 126	97.15 276	94.28 88	97.80 69	98.70 57

NormalMVS		92.88 70	92.97 71	92.59 137	97.80 71	82.02 159	97.94 85	94.70 260	92.34 34	92.15 108	96.53 152	77.03 146	98.57 150	91.13 139	97.12 95	97.19 197

Elysia		85.62 281	83.66 297	91.51 214	88.76 386	82.21 156	95.15 319	94.70 260	76.96 393	84.13 254	92.20 297	50.81 429	97.26 264	77.81 313	92.42 187	95.06 286

StellarMVS		85.62 281	83.66 297	91.51 214	88.76 386	82.21 156	95.15 319	94.70 260	76.96 393	84.13 254	92.20 297	50.81 429	97.26 264	77.81 313	92.42 187	95.06 286

balanced_ft_v1		92.00 104	91.12 119	94.64 36	96.35 110	86.78 36	94.96 328	94.70 260	87.65 119	90.20 144	93.01 285	69.71 281	98.02 183	97.40 44	96.13 126	99.11 29

HQP_MVS		87.50 248	87.09 232	88.74 307	91.86 317	77.96 323	97.18 149	94.69 264	89.89 72	81.33 297	94.15 257	64.77 328	97.30 260	87.08 217	82.82 318	90.96 337

plane_prior5								94.69 264					97.30 260	87.08 217	82.82 318	90.96 337

tpm		85.55 284	84.47 282	88.80 306	90.19 360	75.39 380	88.79 439	94.69 264	84.83 217	83.96 260	85.21 416	78.22 122	94.68 410	76.32 340	78.02 355	96.34 243

FMVSNet3		84.71 301	82.71 320	90.70 253	94.55 182	87.71 26	95.92 266	94.67 267	81.73 306	75.82 367	88.08 367	66.99 308	94.47 415	71.23 385	75.38 366	89.91 357

UA-Net		88.92 201	88.48 197	90.24 269	94.06 208	77.18 348	93.04 385	94.66 268	87.39 130	91.09 128	93.89 266	74.92 201	98.18 176	75.83 344	91.43 204	95.35 278

LFMVS		89.27 191	87.64 214	94.16 57	97.16 100	85.52 66	97.18 149	94.66 268	79.17 363	89.63 152	96.57 150	55.35 411	98.22 173	89.52 179	89.54 230	98.74 51

MVS_Test		90.29 163	89.18 174	93.62 80	95.23 155	84.93 87	94.41 341	94.66 268	84.31 236	90.37 143	91.02 318	75.13 198	97.82 199	83.11 260	94.42 153	98.12 96

sasdasda		92.27 97	91.22 114	95.41 19	95.80 133	88.31 17	97.09 163	94.64 271	88.49 91	92.99 94	97.31 116	72.68 235	98.57 150	93.38 100	88.58 253	99.36 17

canonicalmvs		92.27 97	91.22 114	95.41 19	95.80 133	88.31 17	97.09 163	94.64 271	88.49 91	92.99 94	97.31 116	72.68 235	98.57 150	93.38 100	88.58 253	99.36 17

VDDNet		86.44 263	84.51 279	92.22 164	91.56 325	81.83 174	97.10 162	94.64 271	69.50 453	87.84 192	95.19 206	48.01 443	97.92 193	89.82 169	86.92 279	96.89 220

baseline1		88.85 204	87.49 221	92.93 115	95.21 157	86.85 35	95.47 301	94.61 274	87.29 132	83.11 276	94.99 220	80.70 82	96.89 295	82.28 268	73.72 375	95.05 288

PatchT		79.75 376	76.85 388	88.42 312	89.55 379	75.49 379	77.37 494	94.61 274	63.07 470	82.46 282	73.32 490	75.52 186	93.41 436	51.36 478	84.43 304	96.36 241

MS-PatchMatch		83.05 332	81.82 333	86.72 365	89.64 376	79.10 279	94.88 331	94.59 276	79.70 352	70.67 416	89.65 340	50.43 433	96.82 301	70.82 392	95.99 133	84.25 463

casdiffmvs_mvg		91.13 130	90.45 134	93.17 102	92.99 248	83.58 117	97.46 126	94.56 277	87.69 116	87.19 205	94.98 221	74.50 210	97.60 212	91.88 132	92.79 180	98.34 74
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		90.76 142	90.10 147	92.74 125	92.90 256	82.56 139	94.60 338	94.56 277	87.69 116	89.06 165	95.67 174	73.76 220	97.51 230	90.43 158	92.23 194	98.16 91

OMC-MVS		88.80 206	88.16 204	90.72 252	95.30 153	77.92 326	94.81 334	94.51 279	86.80 154	84.97 240	96.85 140	67.53 301	98.60 148	85.08 234	87.62 273	95.63 267

E3new		90.90 139	90.35 140	92.55 139	93.63 218	82.40 148	96.79 192	94.49 280	87.07 145	88.54 175	95.70 171	73.85 218	97.60 212	91.23 137	91.86 198	97.64 144

MGCFI-Net		91.95 105	91.03 121	94.72 34	95.68 138	86.38 41	96.93 179	94.48 281	88.25 99	92.78 97	97.24 122	72.34 242	98.46 160	93.13 109	88.43 262	99.32 20

MVSFormer		91.36 124	90.57 130	93.73 70	93.00 245	88.08 21	94.80 335	94.48 281	80.74 322	94.90 65	97.13 127	78.84 110	95.10 390	83.77 247	97.46 78	98.02 102

test_djsdf		83.00 335	82.45 324	84.64 400	84.07 450	69.78 436	94.80 335	94.48 281	80.74 322	75.41 373	87.70 372	61.32 360	95.10 390	83.77 247	79.76 334	89.04 383

viewcassd2359sk11		90.66 145	90.06 150	92.47 142	93.22 235	82.21 156	96.70 203	94.47 284	86.94 148	88.22 184	95.50 188	73.15 228	97.59 214	90.86 145	91.48 202	97.60 150

casdiffmvs		90.95 137	90.39 136	92.63 133	92.82 258	82.53 140	96.83 186	94.47 284	87.69 116	88.47 176	95.56 183	74.04 216	97.54 225	90.90 144	92.74 181	97.83 125
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	86.77 260	85.00 274	92.08 174	92.06 308	83.07 128	92.14 401	94.47 284	79.63 353	76.90 347	94.78 231	71.15 264	99.20 115	72.87 374	91.05 213	93.98 312
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
RRT-MVS		89.67 178	88.67 187	92.67 128	94.44 191	81.08 199	94.34 346	94.45 287	86.05 174	85.79 229	92.39 293	63.39 338	98.16 177	93.22 105	93.95 162	98.76 50

VDD-MVS		88.28 222	87.02 234	92.06 177	95.09 164	80.18 244	97.55 118	94.45 287	83.09 275	89.10 164	95.92 164	47.97 444	98.49 157	93.08 111	86.91 280	97.52 161

mvsmamba		90.53 152	90.08 148	91.88 190	94.81 174	80.93 210	93.94 360	94.45 287	88.24 100	87.02 209	92.35 294	68.04 293	95.80 345	94.86 78	97.03 99	98.92 42

test_cas_vis1_n_1920		89.90 170	90.02 152	89.54 292	90.14 363	74.63 385	98.71 41	94.43 290	93.04 27	92.40 102	96.35 155	53.41 422	99.08 126	95.59 67	96.16 124	94.90 290

PLC	83.97 7	88.00 231	87.38 225	89.83 285	98.02 65	76.46 359	97.16 153	94.43 290	79.26 362	81.98 291	96.28 156	69.36 284	99.27 104	77.71 319	92.25 193	93.77 316
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LuminaMVS		88.02 230	86.89 239	91.43 220	88.65 393	83.16 126	94.84 332	94.41 292	83.67 264	86.56 220	91.95 306	62.04 351	96.88 297	89.78 170	90.06 224	94.24 305

EC-MVSNet		91.73 111	92.11 97	90.58 255	93.54 222	77.77 333	98.07 77	94.40 293	87.44 128	92.99 94	97.11 129	74.59 209	96.87 298	93.75 94	97.08 97	97.11 201

E2		90.33 160	89.65 165	92.37 151	92.66 265	81.99 162	96.58 208	94.39 294	86.71 159	87.88 190	95.25 198	72.18 246	97.56 218	90.37 161	90.88 216	97.57 152

E3		90.33 160	89.65 165	92.37 151	92.64 269	81.99 162	96.58 208	94.39 294	86.71 159	87.87 191	95.27 197	72.17 247	97.56 218	90.37 161	90.88 216	97.57 152

sd_testset		84.62 305	83.11 311	89.17 297	94.14 203	77.78 332	91.54 413	94.38 296	84.30 238	79.63 318	92.01 300	52.28 424	96.98 287	77.67 320	82.02 326	92.75 326

FMVSNet2		82.79 337	80.44 353	89.83 285	92.66 265	85.43 67	95.42 303	94.35 297	79.06 366	74.46 380	87.28 378	56.38 405	94.31 419	69.72 397	74.68 372	89.76 358

viewdifsd2359ckpt13		90.08 165	89.36 170	92.26 160	93.03 244	81.90 169	96.37 227	94.34 298	86.16 169	87.44 196	95.30 196	70.93 270	97.55 222	89.05 183	91.59 201	97.35 181

VortexMVS		85.45 287	84.40 283	88.63 309	93.25 234	81.66 182	95.39 306	94.34 298	87.15 143	75.10 376	87.65 373	66.58 314	95.19 381	86.89 221	73.21 381	89.03 385

test_vis1_n_1920		89.95 169	90.59 129	88.03 332	92.36 277	68.98 443	99.12 17	94.34 298	93.86 20	93.64 84	97.01 135	51.54 426	99.59 79	96.76 55	96.71 114	95.53 273

fmvsm_s_conf0.1_n_2		92.26 99	92.48 85	91.60 211	92.29 288	80.55 225	98.73 39	94.33 301	93.80 21	96.18 42	98.11 66	66.93 309	99.75 52	98.19 22	93.74 166	94.50 303

nrg030		86.79 259	85.43 262	90.87 248	88.76 386	85.34 69	97.06 166	94.33 301	84.31 236	80.45 308	91.98 303	72.36 241	96.36 319	88.48 201	71.13 391	90.93 339

ACMM	80.70 13	83.72 321	82.85 318	86.31 370	91.19 334	72.12 412	95.88 279	94.29 303	80.44 330	77.02 345	91.96 304	55.24 412	97.14 277	79.30 300	80.38 333	89.67 359
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Casviewmamba		90.52 154	90.00 154	92.06 177	92.72 262	80.42 234	96.87 183	94.28 304	87.45 125	87.30 200	95.73 169	73.10 229	97.67 208	90.27 166	92.29 191	98.10 98

viewmanbaseed2359cas		90.74 143	90.07 149	92.76 123	92.98 249	82.93 132	96.53 213	94.28 304	87.08 144	88.96 166	95.64 176	72.03 254	97.58 216	90.85 146	92.26 192	97.76 132

E4		89.85 172	89.06 176	92.22 164	91.88 316	81.63 184	96.43 223	94.27 306	86.32 167	87.29 201	94.97 222	70.81 272	97.52 228	89.57 175	90.00 225	97.51 162

XXY-MVS		83.84 318	82.00 330	89.35 294	87.13 409	81.38 190	95.72 287	94.26 307	80.15 341	75.92 366	90.63 325	61.96 354	96.52 313	78.98 305	73.28 380	90.14 350

hybridcas		90.40 156	89.67 164	92.60 136	92.39 275	82.32 152	96.83 186	94.25 308	87.19 140	86.59 219	95.43 192	72.54 237	97.65 209	88.77 194	93.02 178	97.82 127

AstraMVS		88.99 198	88.35 199	90.92 244	90.81 347	78.29 309	96.73 198	94.24 309	89.96 71	86.13 226	95.04 215	62.12 350	97.41 246	92.54 119	87.57 276	97.06 210

Syy-MVS		77.97 398	78.05 378	77.74 457	92.13 302	56.85 491	93.97 358	94.23 310	82.43 292	73.39 387	93.57 275	57.95 384	87.86 481	32.40 511	82.34 323	88.51 400

myMVS_eth3d		81.93 350	82.18 326	81.18 438	92.13 302	67.18 451	93.97 358	94.23 310	82.43 292	73.39 387	93.57 275	76.98 149	87.86 481	50.53 482	82.34 323	88.51 400

E5new		89.38 184	88.55 192	91.85 193	91.77 321	80.97 204	95.90 272	94.22 312	86.03 176	86.88 211	94.90 225	69.05 286	97.47 235	88.86 186	89.35 232	97.10 203

E6new		89.37 186	88.55 192	91.85 193	91.75 323	80.97 204	95.90 272	94.22 312	86.03 176	86.88 211	94.91 223	69.05 286	97.47 235	88.86 186	89.34 234	97.10 203

E6		89.37 186	88.55 192	91.85 193	91.75 323	80.97 204	95.90 272	94.22 312	86.03 176	86.88 211	94.91 223	69.05 286	97.47 235	88.86 186	89.34 234	97.10 203

E5		89.38 184	88.55 192	91.85 193	91.77 321	80.97 204	95.90 272	94.22 312	86.03 176	86.88 211	94.90 225	69.05 286	97.47 235	88.86 186	89.35 232	97.10 203

cl22		85.11 294	84.17 288	87.92 333	95.06 168	78.82 286	95.51 299	94.22 312	79.74 351	76.77 348	87.92 369	75.96 173	95.68 354	79.93 292	72.42 384	89.27 371

OPM-MVS		85.84 275	85.10 273	88.06 330	88.34 397	77.83 330	95.72 287	94.20 317	87.89 111	80.45 308	94.05 259	58.57 375	97.26 264	83.88 244	82.76 320	89.09 377
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet (Re-imp)		88.88 203	88.87 186	88.91 303	93.89 212	74.43 388	96.93 179	94.19 318	84.39 234	83.22 274	95.67 174	78.24 121	94.70 408	78.88 306	94.40 154	97.61 149

Anonymous20231211		79.72 377	77.19 385	87.33 351	95.59 143	77.16 349	95.18 318	94.18 319	59.31 490	72.57 399	86.20 402	47.89 446	95.66 355	74.53 362	69.24 410	89.18 374

PS-MVSNAJss		84.91 299	84.30 285	86.74 361	85.89 429	74.40 389	94.95 329	94.16 320	83.93 252	76.45 354	90.11 336	71.04 266	95.77 348	83.16 259	79.02 344	90.06 355

LPG-MVS_test		84.20 313	83.49 305	86.33 367	90.88 341	73.06 401	95.28 307	94.13 321	82.20 296	76.31 356	93.20 279	54.83 416	96.95 289	83.72 249	80.83 331	88.98 390

LGP-MVS_train				86.33 367	90.88 341	73.06 401		94.13 321	82.20 296	76.31 356	93.20 279	54.83 416	96.95 289	83.72 249	80.83 331	88.98 390

V42		83.04 333	81.53 337	87.57 345	86.27 421	79.09 280	95.87 280	94.11 323	80.35 336	77.22 341	86.79 389	65.32 323	96.02 332	77.74 317	70.14 398	87.61 421

XVG-OURS-SEG-HR		85.74 278	85.16 271	87.49 349	90.22 358	71.45 423	91.29 414	94.09 324	81.37 309	83.90 262	95.22 203	60.30 363	97.53 227	85.58 231	84.42 305	93.50 320

casdiffseed414692147		88.22 224	86.93 238	92.08 174	92.04 309	81.84 173	96.08 257	94.08 325	84.56 226	85.59 231	93.98 264	67.37 303	97.42 244	80.12 290	88.52 257	96.99 212

XVG-OURS		85.18 293	84.38 284	87.59 343	90.42 354	71.73 420	91.06 418	94.07 326	82.00 302	83.29 273	95.08 214	56.42 404	97.55 222	83.70 251	83.42 310	93.49 321

viewmacassd2359aftdt		89.89 171	89.01 180	92.52 141	91.56 325	82.46 146	96.32 234	94.06 327	86.41 164	88.11 187	95.01 218	69.68 282	97.47 235	88.73 196	91.19 208	97.63 146

miper_enhance_ethall		85.95 274	85.20 268	88.19 327	94.85 173	79.76 255	96.00 260	94.06 327	82.98 281	77.74 336	88.76 351	79.42 98	95.46 367	80.58 282	72.42 384	89.36 369

gbinet_0.2-2-1-0.02		78.67 390	75.67 399	87.70 337	80.38 468	79.60 264	96.25 240	94.03 329	72.51 434	71.41 407	83.33 437	55.97 408	94.45 416	73.37 372	53.73 479	89.04 383

v2v482		83.46 324	81.86 332	88.25 322	86.19 422	79.65 262	96.34 232	94.02 330	81.56 308	77.32 339	88.23 364	65.62 318	96.03 331	77.77 316	69.72 406	89.09 377

jajsoiax		82.12 348	81.15 343	85.03 394	84.19 448	70.70 428	94.22 354	93.95 331	83.07 276	73.48 386	89.75 338	49.66 437	95.37 370	82.24 269	79.76 334	89.02 387

onestephybrid01		90.58 148	90.37 138	91.20 234	92.69 263	78.81 288	96.04 258	93.94 332	86.55 163	90.40 141	95.64 176	72.84 232	97.43 243	93.77 93	91.46 203	97.36 179

test_fmvsmconf0.01_n		91.08 132	90.68 128	92.29 158	82.43 460	80.12 246	97.94 85	93.93 333	92.07 40	91.97 112	97.60 102	67.56 300	99.53 87	97.09 50	95.56 140	97.21 193

v1144		82.90 336	81.27 341	87.78 336	86.29 420	79.07 281	96.14 252	93.93 333	80.05 345	77.38 337	86.80 388	65.50 319	95.93 339	75.21 354	70.13 399	88.33 408

KD-MVS_2432*1600		77.63 401	74.92 406	85.77 378	90.86 344	79.44 266	88.08 446	93.92 335	76.26 399	67.05 438	82.78 440	72.15 249	91.92 450	61.53 436	41.62 504	85.94 448

miper_refine_blended		77.63 401	74.92 406	85.77 378	90.86 344	79.44 266	88.08 446	93.92 335	76.26 399	67.05 438	82.78 440	72.15 249	91.92 450	61.53 436	41.62 504	85.94 448

test_fmvsmvis_n_1920		92.12 101	92.10 98	92.17 169	90.87 343	81.04 200	98.34 62	93.90 337	92.71 29	87.24 203	97.90 84	74.83 203	99.72 60	96.96 52	96.20 123	95.76 264

UnsupCasMVSNet_eth		73.25 428	70.57 434	81.30 436	77.53 483	66.33 458	87.24 454	93.89 338	80.38 333	57.90 483	81.59 452	42.91 463	90.56 465	65.18 420	48.51 492	87.01 432

v7n		79.32 383	77.34 383	85.28 390	84.05 451	72.89 406	93.38 374	93.87 339	75.02 410	70.68 415	84.37 426	59.58 367	95.62 360	67.60 403	67.50 427	87.32 429

dcpmvs_2		93.10 63	93.46 61	92.02 183	97.77 73	79.73 260	94.82 333	93.86 340	86.91 149	91.33 124	96.76 145	85.20 39	98.06 180	96.90 53	97.60 75	98.27 83

Vis-MVSNet		88.67 209	87.82 210	91.24 230	92.68 264	78.82 286	96.95 177	93.85 341	87.55 122	87.07 208	95.13 211	63.43 337	97.21 267	77.58 322	96.15 125	97.70 139
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
icg_test_0407_2		87.55 246	86.59 245	90.43 260	92.30 283	78.81 288	92.17 400	93.84 342	85.14 205	83.68 265	94.49 242	67.75 296	95.02 398	81.33 273	88.61 247	97.46 167

IMVS_0407		87.82 235	86.72 242	91.14 236	92.30 283	78.81 288	93.34 376	93.84 342	85.14 205	83.68 265	94.49 242	67.75 296	97.14 277	81.33 273	88.61 247	97.46 167

IMVS_0404		85.34 289	83.69 294	90.29 267	92.30 283	78.81 288	90.62 422	93.84 342	85.14 205	72.51 401	94.49 242	54.36 418	94.61 411	81.33 273	88.61 247	97.46 167

IMVS_0403		88.07 227	87.02 234	91.24 230	92.30 283	78.81 288	93.62 368	93.84 342	85.14 205	84.36 250	94.49 242	69.49 283	97.46 242	81.33 273	88.61 247	97.46 167

v148		82.41 345	80.89 345	86.99 359	86.18 423	76.81 354	96.27 237	93.82 346	80.49 329	75.28 374	86.11 404	67.32 305	95.75 350	75.48 351	67.03 433	88.42 406

BH-w/o		88.24 223	87.47 223	90.54 258	95.03 169	78.54 300	97.41 132	93.82 346	84.08 245	78.23 331	94.51 240	69.34 285	97.21 267	80.21 288	94.58 150	95.87 257

TR-MVS		86.30 268	84.93 276	90.42 261	94.63 179	77.58 339	96.57 210	93.82 346	80.30 337	82.42 283	95.16 208	58.74 374	97.55 222	74.88 356	87.82 271	96.13 250

dtuplus		89.18 193	88.59 191	90.96 242	91.84 320	78.40 308	95.89 276	93.81 349	83.26 271	87.77 194	95.53 185	70.57 274	97.49 233	88.57 197	90.08 223	96.99 212

v1192		82.31 346	80.55 352	87.60 342	85.94 427	78.47 304	95.85 282	93.80 350	79.33 358	76.97 346	86.51 392	63.33 339	95.87 341	73.11 373	70.13 399	88.46 404

ACMP	81.66 11	84.00 316	83.22 310	86.33 367	91.53 329	72.95 405	95.91 271	93.79 351	83.70 263	73.79 383	92.22 296	54.31 420	96.89 295	83.98 243	79.74 336	89.16 375
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v144192		82.43 342	80.73 348	87.54 346	85.81 430	78.22 313	95.98 261	93.78 352	79.09 365	77.11 344	86.49 393	64.66 332	95.91 340	74.20 364	69.42 407	88.49 402

mvs_tets		81.74 353	80.71 349	84.84 395	84.22 447	70.29 432	93.91 361	93.78 352	82.77 286	73.37 389	89.46 344	47.36 449	95.31 374	81.99 270	79.55 340	88.92 394

F-COLMAP		84.50 309	83.44 306	87.67 339	95.22 156	72.22 407	95.95 263	93.78 352	75.74 402	76.30 358	95.18 207	59.50 368	98.45 162	72.67 376	86.59 283	92.35 332

viewdifsd2359ckpt07		89.04 196	88.30 200	91.27 228	92.32 279	78.90 283	95.89 276	93.77 355	84.48 232	85.18 236	95.16 208	69.83 279	97.70 204	88.75 195	89.29 237	97.22 190

viewmambaseed2359dif		89.52 181	89.02 178	91.03 239	92.24 293	78.83 285	95.89 276	93.77 355	83.04 277	88.28 183	95.80 167	72.08 252	97.40 248	89.76 171	90.32 221	96.87 223

UniMVSNet_ETH3D		80.86 368	78.75 374	87.22 356	86.31 419	72.02 413	91.95 403	93.76 357	73.51 421	75.06 377	90.16 334	43.04 462	95.66 355	76.37 339	78.55 350	93.98 312

wanda-best-256-512		78.87 386	75.75 396	88.22 324	79.74 471	80.51 231	95.92 266	93.75 358	72.60 431	70.34 419	82.14 443	57.91 387	95.09 392	75.61 347	53.77 475	89.05 380

FE-blended-shiyan7		78.87 386	75.75 396	88.22 324	79.74 471	80.51 231	95.92 266	93.75 358	72.60 431	70.34 419	82.14 443	57.91 387	95.09 392	75.61 347	53.77 475	89.05 380

blended_shiyan6		78.74 389	75.63 401	88.07 329	79.63 475	80.10 247	95.72 287	93.73 360	72.43 436	70.17 425	82.09 448	57.69 390	95.07 395	75.47 352	53.77 475	89.03 385

blend_shiyan4		81.76 352	79.58 365	88.31 318	80.00 470	80.59 221	95.95 263	93.73 360	72.26 438	71.14 412	82.52 442	76.13 170	95.15 385	77.83 311	66.62 436	89.19 373

Fast-Effi-MVS+		87.93 233	86.94 237	90.92 244	94.04 209	79.16 276	98.26 65	93.72 362	81.29 310	83.94 261	92.90 286	69.83 279	96.68 308	76.70 332	91.74 199	96.93 217

blended_shiyan8		78.76 388	75.65 400	88.10 328	79.58 476	80.20 242	95.70 290	93.71 363	72.43 436	70.26 422	82.12 446	57.66 391	95.08 394	75.57 349	53.80 474	89.02 387

v1921920		82.02 349	80.23 356	87.41 350	85.62 431	77.92 326	95.79 286	93.69 364	78.86 369	76.67 349	86.44 395	62.50 343	95.83 343	72.69 375	69.77 405	88.47 403

DTE-MVSNet		78.37 392	77.06 386	82.32 431	85.22 438	67.17 454	93.40 373	93.66 365	78.71 371	70.53 417	88.29 363	59.06 373	92.23 447	61.38 439	63.28 452	87.56 423

v8		81.88 351	80.06 360	87.32 352	86.63 413	79.04 282	94.41 341	93.65 366	78.77 370	73.19 393	85.57 410	66.87 310	95.81 344	73.84 368	67.61 426	87.11 430

viewdifsd2359ckpt09		90.00 168	89.28 173	92.15 171	93.31 233	81.38 190	96.37 227	93.64 367	86.34 166	86.62 218	95.64 176	71.58 260	97.52 228	88.93 184	91.06 212	97.54 155

diffmvs_AUTHOR		90.86 141	90.41 135	92.24 161	92.01 311	82.22 155	96.18 248	93.64 367	87.28 133	90.46 140	95.64 176	72.82 233	97.39 250	93.17 106	92.46 186	97.11 201

diffmvs		91.17 129	90.74 127	92.44 146	93.11 243	82.50 145	96.25 240	93.62 369	87.79 112	90.40 141	95.93 162	73.44 225	97.42 244	93.62 97	92.55 183	97.41 174
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		90.42 155	89.87 161	92.06 177	92.20 294	81.45 189	96.09 255	93.61 370	85.80 184	89.55 154	95.52 186	72.14 251	97.39 250	92.60 117	91.36 206	97.34 182

ADS-MVSNet		81.26 361	78.36 375	89.96 280	93.78 214	79.78 254	79.48 486	93.60 371	73.09 426	80.14 312	79.99 465	62.15 348	95.24 379	59.49 449	83.52 308	94.85 293

PatchMatch-RL		85.00 298	83.66 297	89.02 301	95.86 130	74.55 387	92.49 394	93.60 371	79.30 360	79.29 322	91.47 310	58.53 376	98.45 162	70.22 394	92.17 195	94.07 311

anonymousdsp		80.98 367	79.97 361	84.01 408	81.73 462	70.44 431	92.49 394	93.58 373	77.10 390	72.98 395	86.31 399	57.58 392	94.90 399	79.32 299	78.63 349	86.69 435

hybridnocas07		90.53 152	90.02 152	92.05 181	92.36 277	81.48 188	96.27 237	93.57 374	86.86 152	89.28 159	95.48 189	72.17 247	97.47 235	92.77 113	91.41 205	97.21 193

CL-MVSNet_self_test		75.81 414	74.14 415	80.83 441	78.33 481	67.79 448	94.22 354	93.52 375	77.28 387	69.82 426	81.54 454	61.47 359	89.22 473	57.59 458	53.51 480	85.48 452

viewmamba		90.30 162	89.90 159	91.48 218	92.14 301	79.76 255	95.92 266	93.50 376	87.73 114	88.32 180	95.82 165	72.39 240	97.36 257	92.19 124	91.12 211	97.30 186

miper_ehance_all_eth		84.57 307	83.60 302	87.50 347	92.64 269	78.25 312	95.40 305	93.47 377	79.28 361	76.41 355	87.64 374	76.53 158	95.24 379	78.58 308	72.42 384	89.01 389

kuosan		73.55 425	72.39 425	77.01 461	89.68 375	66.72 457	85.24 470	93.44 378	67.76 457	60.04 475	83.40 436	71.90 255	84.25 495	45.34 493	54.75 468	80.06 490

v1240		81.70 354	79.83 364	87.30 354	85.50 432	77.70 338	95.48 300	93.44 378	78.46 374	76.53 353	86.44 395	60.85 361	95.84 342	71.59 382	70.17 397	88.35 407

v10		81.43 358	79.53 367	87.11 357	86.38 417	78.87 284	94.31 348	93.43 380	77.88 378	73.24 392	85.26 414	65.44 320	95.75 350	72.14 379	67.71 425	86.72 434

IterMVS-LS		83.93 317	82.80 319	87.31 353	91.46 330	77.39 343	95.66 292	93.43 380	80.44 330	75.51 371	87.26 380	73.72 221	95.16 384	76.99 328	70.72 395	89.39 363
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		82.42 343	80.43 354	88.39 315	92.66 265	81.95 164	94.30 349	93.38 382	79.06 366	75.82 367	85.66 406	56.38 405	93.84 427	71.23 385	75.38 366	89.38 365

test1		82.42 343	80.43 354	88.39 315	92.66 265	81.95 164	94.30 349	93.38 382	79.06 366	75.82 367	85.66 406	56.38 405	93.84 427	71.23 385	75.38 366	89.38 365

FMVSNet1		79.50 380	76.54 391	88.39 315	88.47 394	81.95 164	94.30 349	93.38 382	73.14 425	72.04 404	85.66 406	43.86 456	93.84 427	65.48 418	72.53 383	89.38 365

BH-untuned		86.95 255	85.94 252	89.99 277	94.52 184	77.46 341	96.78 194	93.37 385	81.80 304	76.62 351	93.81 271	66.64 312	97.02 281	76.06 341	93.88 164	95.48 275

Effi-MVS+-dtu		84.61 306	84.90 277	83.72 414	91.96 313	63.14 473	94.95 329	93.34 386	85.57 190	79.79 316	87.12 383	61.99 353	95.61 361	83.55 253	85.83 294	92.41 330

CMPMVS	54.94 21	75.71 416	74.56 410	79.17 450	79.69 474	55.98 493	89.59 430	93.30 387	60.28 484	53.85 491	89.07 347	47.68 448	96.33 320	76.55 335	81.02 329	85.22 453
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
cl____		83.27 327	82.12 327	86.74 361	92.20 294	75.95 372	95.11 323	93.27 388	78.44 375	74.82 378	87.02 385	74.19 213	95.19 381	74.67 359	69.32 408	89.09 377

DIV-MVS_self_test		83.27 327	82.12 327	86.74 361	92.19 296	75.92 374	95.11 323	93.26 389	78.44 375	74.81 379	87.08 384	74.19 213	95.19 381	74.66 360	69.30 409	89.11 376

dmvs_re		84.10 314	82.90 316	87.70 337	91.41 331	73.28 398	90.59 423	93.19 390	85.02 212	77.96 335	93.68 272	57.92 386	96.18 327	75.50 350	80.87 330	93.63 318

miper_lstm_enhance		81.66 356	80.66 350	84.67 399	91.19 334	71.97 415	91.94 404	93.19 390	77.86 379	72.27 402	85.26 414	73.46 224	93.42 435	73.71 369	67.05 432	88.61 398

dongtai		69.47 447	68.98 443	70.93 473	86.87 411	58.45 488	88.19 444	93.18 392	63.98 468	56.04 487	80.17 464	70.97 269	79.24 502	33.46 509	47.94 494	75.09 497

eth_miper_zixun_eth		83.12 331	82.01 329	86.47 366	91.85 319	74.80 383	94.33 347	93.18 392	79.11 364	75.74 370	87.25 381	72.71 234	95.32 373	76.78 331	67.13 431	89.27 371

pmmvs4		82.54 341	80.79 346	87.79 335	86.11 425	80.49 233	93.55 371	93.18 392	77.29 386	73.35 390	89.40 345	65.26 324	95.05 397	75.32 353	73.61 376	87.83 416

XVG-ACMP-BASELINE		79.38 382	77.90 380	83.81 410	84.98 440	67.14 455	89.03 437	93.18 392	80.26 340	72.87 396	88.15 366	38.55 476	96.26 322	76.05 342	78.05 354	88.02 413

CANet_DTU		90.98 135	90.04 151	93.83 63	94.76 176	86.23 45	96.32 234	93.12 396	93.11 26	93.71 82	96.82 143	63.08 340	99.48 92	84.29 240	95.12 143	95.77 263

IS-MVSNet		88.67 209	88.16 204	90.20 271	93.61 219	76.86 353	96.77 197	93.07 397	84.02 247	83.62 267	95.60 181	74.69 208	96.24 325	78.43 310	93.66 169	97.49 164

c3_l		83.80 319	82.65 321	87.25 355	92.10 304	77.74 337	95.25 312	93.04 398	78.58 372	76.01 363	87.21 382	75.25 197	95.11 389	77.54 323	68.89 412	88.91 395

UnsupCasMVSNet_bld		68.60 453	64.50 457	80.92 440	74.63 495	67.80 447	83.97 475	92.94 399	65.12 466	54.63 490	68.23 500	35.97 482	92.17 449	60.13 446	44.83 499	82.78 471

MVP-Stereo		82.65 340	81.67 335	85.59 385	86.10 426	78.29 309	93.33 377	92.82 400	77.75 380	69.17 431	87.98 368	59.28 371	95.76 349	71.77 380	96.88 105	82.73 472
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Effi-MVS+		90.70 144	89.90 159	93.09 106	93.61 219	83.48 119	95.20 315	92.79 401	83.22 272	91.82 116	95.70 171	71.82 256	97.48 234	91.25 136	93.67 168	98.32 77

EU-MVSNet		76.92 409	76.95 387	76.83 463	84.10 449	54.73 498	91.77 408	92.71 402	72.74 429	69.57 428	88.69 352	58.03 383	87.43 485	64.91 421	70.00 403	88.33 408

pm-mvs1		80.05 374	78.02 379	86.15 373	85.42 433	75.81 375	95.11 323	92.69 403	77.13 388	70.36 418	87.43 376	58.44 377	95.27 376	71.36 384	64.25 447	87.36 428

1112_ss		88.60 212	87.47 223	92.00 184	93.21 236	80.97 204	96.47 218	92.46 404	83.64 266	80.86 303	97.30 119	80.24 88	97.62 211	77.60 321	85.49 297	97.40 176

viewdifsd2359ckpt11		86.38 264	85.29 265	89.66 291	90.42 354	75.65 377	95.27 310	92.45 405	85.54 193	84.27 252	94.73 232	62.16 346	97.39 250	87.78 208	74.97 369	95.96 251

viewmsd2359difaftdt		86.38 264	85.29 265	89.67 290	90.42 354	75.65 377	95.27 310	92.45 405	85.54 193	84.28 251	94.73 232	62.16 346	97.39 250	87.78 208	74.97 369	95.96 251

test_fmvs1		87.79 237	88.52 196	85.62 384	92.98 249	64.31 465	97.88 90	92.42 407	87.95 107	92.24 105	95.82 165	47.94 445	98.44 164	95.31 74	94.09 155	94.09 310

Test_1112_low_res		88.03 229	86.73 241	91.94 188	93.15 239	80.88 213	96.44 221	92.41 408	83.59 268	80.74 305	91.16 316	80.18 89	97.59 214	77.48 324	85.40 298	97.36 179

test_fmvs1_n		86.34 267	86.72 242	85.17 392	87.54 407	63.64 470	96.91 181	92.37 409	87.49 124	91.33 124	95.58 182	40.81 474	98.46 160	95.00 77	93.49 170	93.41 324

SSM_0407		87.33 251	85.87 255	91.71 206	92.94 251	82.53 140	94.30 349	92.33 410	80.11 342	83.50 268	94.18 255	64.68 330	96.80 304	82.34 266	88.51 258	95.79 260

SSM_0404		87.69 243	86.26 248	91.95 186	92.94 251	83.02 130	94.69 337	92.33 410	80.11 342	84.65 247	94.18 255	64.68 330	96.90 293	82.34 266	90.44 220	95.94 254

BH-RMVSNet		86.84 257	85.28 267	91.49 217	95.35 152	80.26 239	96.95 177	92.21 412	82.86 284	81.77 296	95.46 191	59.34 370	97.64 210	69.79 396	93.81 165	96.57 237

GeoE		86.36 266	85.20 268	89.83 285	93.17 238	76.13 365	97.53 119	92.11 413	79.58 354	80.99 300	94.01 260	66.60 313	96.17 329	73.48 370	89.30 236	97.20 196

LS3D		82.22 347	79.94 362	89.06 299	97.43 90	74.06 392	93.20 383	92.05 414	61.90 476	73.33 391	95.21 204	59.35 369	99.21 110	54.54 470	92.48 185	93.90 314

EG-PatchMatch MVS		74.92 418	72.02 426	83.62 415	83.76 456	73.28 398	93.62 368	92.04 415	68.57 456	58.88 479	83.80 432	31.87 491	95.57 364	56.97 462	78.67 346	82.00 481

IterMVS		80.67 370	79.16 370	85.20 391	89.79 368	76.08 366	92.97 387	91.86 416	80.28 338	71.20 411	85.14 419	57.93 385	91.34 458	72.52 377	70.74 394	88.18 411
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MIMVSNet		79.18 384	75.99 394	88.72 308	87.37 408	80.66 219	79.96 484	91.82 417	77.38 385	74.33 381	81.87 451	41.78 466	90.74 464	66.36 416	83.10 313	94.76 295

IterMVS-SCA-FT		80.51 372	79.10 371	84.73 397	89.63 377	74.66 384	92.98 386	91.81 418	80.05 345	71.06 414	85.18 417	58.04 381	91.40 457	72.48 378	70.70 396	88.12 412

mamba_0408		85.26 292	83.10 312	91.74 202	92.94 251	82.53 140	72.52 503	91.77 419	80.36 334	83.50 268	94.01 260	64.97 326	96.90 293	79.37 297	88.51 258	95.79 260

SSM_04072		84.64 303	83.10 312	89.25 296	92.94 251	82.53 140	72.52 503	91.77 419	80.36 334	83.50 268	94.01 260	64.97 326	89.41 472	79.37 297	88.51 258	95.79 260

FE-MVSNET2		73.72 422	70.80 432	82.46 428	74.97 494	73.81 393	91.88 406	91.73 421	76.70 396	59.74 477	77.41 475	42.26 465	90.52 466	64.75 422	57.79 463	83.06 468

our_test_3		77.90 399	75.37 403	85.48 387	85.39 434	76.74 355	93.63 367	91.67 422	73.39 424	65.72 447	84.65 425	58.20 380	93.13 438	57.82 456	67.87 422	86.57 437

pmmvs5		81.34 359	79.54 366	86.73 364	85.02 439	76.91 351	96.22 244	91.65 423	77.65 381	73.55 385	88.61 353	55.70 409	94.43 417	74.12 365	73.35 379	88.86 396

ACMH	75.40 17	77.99 396	74.96 404	87.10 358	90.67 349	76.41 361	93.19 384	91.64 424	72.47 435	63.44 456	87.61 375	43.34 459	97.16 271	58.34 454	73.94 374	87.72 417
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis1_n		85.60 283	85.70 257	85.33 389	84.79 441	64.98 462	96.83 186	91.61 425	87.36 131	91.00 131	94.84 230	36.14 481	97.18 270	95.66 65	93.03 177	93.82 315

MonoMVSNet		85.68 279	84.22 287	90.03 275	88.43 396	77.83 330	92.95 388	91.46 426	87.28 133	78.11 332	85.96 405	66.31 316	94.81 404	90.71 151	76.81 358	97.46 167

Fast-Effi-MVS+-dtu		83.33 326	82.60 322	85.50 386	89.55 379	69.38 441	96.09 255	91.38 427	82.30 295	75.96 365	91.41 311	56.71 400	95.58 363	75.13 355	84.90 302	91.54 333

YYNet1		73.53 427	70.43 435	82.85 423	84.52 444	71.73 420	91.69 410	91.37 428	67.63 458	46.79 498	81.21 457	55.04 414	90.43 467	55.93 465	59.70 459	86.38 439

ppachtmachnet_test		77.19 406	74.22 413	86.13 374	85.39 434	78.22 313	93.98 357	91.36 429	71.74 442	67.11 437	84.87 423	56.67 401	93.37 437	52.21 475	64.59 444	86.80 433

Anonymous202405211		84.41 310	81.93 331	91.85 193	96.78 105	78.41 305	97.44 127	91.34 430	70.29 448	84.06 256	94.26 250	41.09 471	98.96 132	79.46 295	82.65 321	98.17 90

MDA-MVSNet_test_wron		73.54 426	70.43 435	82.86 422	84.55 442	71.85 417	91.74 409	91.32 431	67.63 458	46.73 499	81.09 458	55.11 413	90.42 468	55.91 466	59.76 458	86.31 440

SD_0403		81.29 360	81.13 344	81.78 435	90.20 359	60.43 482	89.97 427	91.31 432	83.87 254	71.78 405	93.08 284	63.86 334	89.61 471	60.00 447	86.07 291	95.30 280

CR-MVSNet		83.53 323	81.36 340	90.06 274	90.16 361	79.75 257	79.02 490	91.12 433	84.24 242	82.27 288	80.35 462	75.45 187	93.67 431	63.37 432	86.25 286	96.75 231

Patchmtry		77.36 405	74.59 409	85.67 382	89.75 371	75.75 376	77.85 493	91.12 433	60.28 484	71.23 410	80.35 462	75.45 187	93.56 433	57.94 455	67.34 429	87.68 419

LTVRE_ROB	73.68 18	77.99 396	75.74 398	84.74 396	90.45 353	72.02 413	86.41 461	91.12 433	72.57 433	66.63 442	87.27 379	54.95 415	96.98 287	56.29 464	75.98 361	85.21 454
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		77.18 407	76.06 393	80.55 442	83.78 454	60.00 485	90.35 424	91.05 436	77.01 392	66.62 443	87.92 369	47.73 447	94.03 423	71.63 381	68.44 416	87.62 420

CNLPA		86.96 254	85.37 264	91.72 205	97.59 81	79.34 271	97.21 145	91.05 436	74.22 415	78.90 323	96.75 147	67.21 306	98.95 134	74.68 358	90.77 218	96.88 222

Anonymous20240521		72.06 437	69.91 437	78.50 455	77.11 486	61.67 479	91.62 412	90.97 438	65.52 465	62.37 463	79.05 468	36.32 480	90.96 462	57.75 457	68.52 415	82.87 469

KD-MVS_self_test		70.97 442	69.31 440	75.95 468	76.24 491	55.39 497	87.45 451	90.94 439	70.20 450	62.96 461	77.48 474	44.01 455	88.09 479	61.25 440	53.26 481	84.37 462

pmmvs6		74.65 420	71.67 427	83.60 416	79.13 478	69.94 434	93.31 380	90.88 440	61.05 483	65.83 446	84.15 429	43.43 458	94.83 403	66.62 411	60.63 457	86.02 446

test1111		88.11 226	87.04 233	91.35 223	93.15 239	78.79 294	96.57 210	90.78 441	86.88 150	85.04 238	95.20 205	57.23 398	97.39 250	83.88 244	94.59 149	97.87 120

ECVR-MVS		88.35 220	87.25 227	91.65 207	93.54 222	79.40 268	96.56 212	90.78 441	86.78 155	85.57 232	95.25 198	57.25 397	97.56 218	84.73 238	94.80 146	97.98 111

Anonymous20231206		75.29 417	73.64 418	80.22 444	80.75 464	63.38 472	93.36 375	90.71 443	73.09 426	67.12 436	83.70 433	50.33 434	90.85 463	53.63 473	70.10 401	86.44 438

USDC		78.65 391	76.25 392	85.85 376	87.58 405	74.60 386	89.58 431	90.58 444	84.05 246	63.13 458	88.23 364	40.69 475	96.86 300	66.57 413	75.81 364	86.09 444

dtuonly		84.63 304	84.08 291	86.30 372	86.14 424	69.59 438	92.71 392	90.28 445	82.00 302	80.87 302	94.51 240	62.61 342	96.18 327	79.00 304	88.60 251	93.14 325

MSDG		80.62 371	77.77 381	89.14 298	93.43 230	77.24 345	91.89 405	90.18 446	69.86 452	68.02 433	91.94 307	52.21 425	98.84 140	59.32 451	83.12 312	91.35 334

ACMH+	76.62 16	77.47 404	74.94 405	85.05 393	91.07 339	71.58 422	93.26 381	90.01 447	71.80 441	64.76 451	88.55 354	41.62 467	96.48 314	62.35 435	71.00 392	87.09 431

FMVSNet5		76.46 411	74.16 414	83.35 419	90.05 364	76.17 364	89.58 431	89.85 448	71.39 444	65.29 450	80.42 461	50.61 432	87.70 484	61.05 442	69.24 410	86.18 442

usedtu_blend_shiyan5		77.51 403	73.93 417	88.26 320	79.74 471	80.59 221	90.76 421	89.69 449	63.21 469	70.34 419	82.14 443	57.91 387	95.15 385	77.83 311	53.77 475	89.05 380

ambc				76.02 466	68.11 504	51.43 499	64.97 509	89.59 450		60.49 472	74.49 486	17.17 504	92.46 441	61.50 438	52.85 483	84.17 464

test_fmvs2		79.59 378	79.90 363	78.67 453	82.86 459	55.82 495	95.20 315	89.55 451	81.09 314	80.12 314	89.80 337	34.31 486	93.51 434	87.82 207	78.36 352	86.69 435

ITE_SJBPF				82.38 429	87.00 410	65.59 460		89.55 451	79.99 347	69.37 429	91.30 314	41.60 468	95.33 372	62.86 434	74.63 373	86.24 441

pmmvs-eth3d		73.59 424	70.66 433	82.38 429	76.40 489	73.38 395	89.39 435	89.43 453	72.69 430	60.34 473	77.79 472	46.43 452	91.26 460	66.42 415	57.06 464	82.51 473

test20.03		72.36 435	71.15 430	75.98 467	77.79 482	59.16 487	92.40 397	89.35 454	74.09 417	61.50 468	84.32 427	48.09 442	85.54 493	50.63 481	62.15 455	83.24 467

SixPastTwentyTwo		76.04 412	74.32 412	81.22 437	84.54 443	61.43 480	91.16 416	89.30 455	77.89 377	64.04 453	86.31 399	48.23 441	94.29 420	63.54 431	63.84 450	87.93 415

PatchmatchNet2					0.00 567	72.22 407	92.05 402	89.18 456	62.36 474
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TransMVSNet (Re)		76.94 408	74.38 411	84.62 401	85.92 428	75.25 381	95.28 307	89.18 456	73.88 419	67.22 435	86.46 394	59.64 365	94.10 422	59.24 452	52.57 484	84.50 461

MIMVSNet1		69.44 448	66.65 450	77.84 456	76.48 488	62.84 474	87.42 452	88.97 458	66.96 463	57.75 485	79.72 467	32.77 490	85.83 492	46.32 490	63.42 451	84.85 457

K. test v3		73.62 423	71.59 428	79.69 446	82.98 458	59.85 486	90.85 420	88.83 459	77.13 388	58.90 478	82.11 447	43.62 457	91.72 455	65.83 417	54.10 473	87.50 426

Baseline_NR-MVSNet		81.22 362	80.07 359	84.68 398	85.32 437	75.12 382	96.48 217	88.80 460	76.24 401	77.28 340	86.40 398	67.61 298	94.39 418	75.73 346	66.73 435	84.54 460

MDA-MVSNet-bldmvs		71.45 439	67.94 446	81.98 433	85.33 436	68.50 445	92.35 398	88.76 461	70.40 447	42.99 502	81.96 450	46.57 451	91.31 459	48.75 488	54.39 472	86.11 443

new-patchmatchnet		68.85 452	65.93 453	77.61 458	73.57 498	63.94 469	90.11 426	88.73 462	71.62 443	55.08 489	73.60 488	40.84 473	87.22 487	51.35 479	48.49 493	81.67 485

Patchmatch-test		78.25 393	74.72 408	88.83 305	91.20 333	74.10 391	73.91 501	88.70 463	59.89 487	66.82 440	85.12 420	78.38 118	94.54 413	48.84 487	79.58 339	97.86 122

OpenMVS_ROB	68.52 20	73.02 430	69.57 438	83.37 418	80.54 467	71.82 418	93.60 370	88.22 464	62.37 473	61.98 465	83.15 439	35.31 485	95.47 366	45.08 494	75.88 363	82.82 470

mvsany_test1		87.58 245	88.22 201	85.67 382	89.78 369	67.18 451	95.25 312	87.93 465	83.96 250	88.79 170	97.06 133	72.52 238	94.53 414	92.21 123	86.45 284	95.30 280

RPSCF		77.73 400	76.63 390	81.06 439	88.66 392	55.76 496	87.77 450	87.88 466	64.82 467	74.14 382	92.79 289	49.22 439	96.81 302	67.47 405	76.88 357	90.62 341

MVS-HIRNet		71.36 441	67.00 447	84.46 405	90.58 350	69.74 437	79.15 489	87.74 467	46.09 503	61.96 466	50.50 519	45.14 454	95.64 358	53.74 472	88.11 268	88.00 414

usedtu_dtu_shiyan2		64.65 458	60.40 462	77.38 460	64.24 508	57.84 490	89.16 436	87.60 468	52.95 498	53.43 492	71.31 499	23.41 499	88.27 478	51.95 476	49.58 489	86.03 445

mmtdpeth		78.04 395	76.76 389	81.86 434	89.60 378	66.12 459	92.34 399	87.18 469	76.83 395	85.55 233	76.49 481	46.77 450	97.02 281	90.85 146	45.24 498	82.43 476

DP-MVS		81.47 357	78.28 376	91.04 238	98.14 61	78.48 301	95.09 326	86.97 470	61.14 482	71.12 413	92.78 290	59.59 366	99.38 97	53.11 474	86.61 282	95.27 282

COLMAP_ROB	73.24 19	75.74 415	73.00 422	83.94 409	92.38 276	69.08 442	91.85 407	86.93 471	61.48 479	65.32 449	90.27 331	42.27 464	96.93 292	50.91 480	75.63 365	85.80 451
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MVStest1		66.93 455	63.01 459	78.69 452	78.56 479	71.43 424	85.51 468	86.81 472	49.79 501	48.57 497	84.15 429	53.46 421	83.31 496	43.14 497	37.15 507	81.34 487

test_fmvs3		69.56 446	69.19 441	70.67 474	69.01 502	47.05 502	90.87 419	86.81 472	71.31 445	66.79 441	77.15 477	16.40 505	83.17 498	81.84 271	62.51 454	81.79 483

test_0402		72.68 431	69.54 439	82.09 432	88.67 391	71.81 419	92.72 391	86.77 474	61.52 478	62.21 464	83.91 431	43.22 460	93.76 430	34.60 507	72.23 387	80.72 489

testgi		74.88 419	73.40 419	79.32 449	80.13 469	61.75 477	93.21 382	86.64 475	79.49 356	66.56 444	91.06 317	35.51 484	88.67 475	56.79 463	71.25 390	87.56 423

dtuonlycased		72.49 432	71.58 429	75.22 469	81.04 463	64.71 463	92.43 396	86.46 476	75.62 404	59.79 476	78.43 470	48.54 440	85.84 491	63.66 430	58.28 460	75.10 496

TDRefinement		69.20 451	65.78 454	79.48 447	66.04 507	62.21 476	88.21 443	86.12 477	62.92 471	61.03 471	85.61 409	33.23 488	94.16 421	55.82 467	53.02 482	82.08 479

ADS-MVSNet2		79.57 379	77.53 382	85.71 381	93.78 214	72.13 411	79.48 486	86.11 478	73.09 426	80.14 312	79.99 465	62.15 348	90.14 470	59.49 449	83.52 308	94.85 293

LF4IMVS		72.36 435	70.82 431	76.95 462	79.18 477	56.33 492	86.12 463	86.11 478	69.30 454	63.06 459	86.66 390	33.03 489	92.25 446	65.33 419	68.64 414	82.28 477

TinyColmap		72.41 433	68.99 442	82.68 424	88.11 399	69.59 438	88.41 442	85.20 480	65.55 464	57.91 482	84.82 424	30.80 493	95.94 338	51.38 477	68.70 413	82.49 475

mvs5depth		71.40 440	68.36 444	80.54 443	75.31 493	65.56 461	79.94 485	85.14 481	69.11 455	71.75 406	81.59 452	41.02 472	93.94 425	60.90 443	50.46 487	82.10 478

pmmvs3		65.75 457	62.18 460	76.45 465	67.12 506	64.54 464	88.68 440	85.05 482	54.77 497	57.54 486	73.79 487	29.40 496	86.21 490	55.49 469	47.77 495	78.62 492

new_pmnet		66.18 456	63.18 458	75.18 471	76.27 490	61.74 478	83.79 476	84.66 483	56.64 495	51.57 494	71.85 496	31.29 492	87.93 480	49.98 483	62.55 453	75.86 495

AllTest		75.92 413	73.06 421	84.47 403	92.18 297	67.29 449	91.07 417	84.43 484	67.63 458	63.48 454	90.18 332	38.20 477	97.16 271	57.04 460	73.37 377	88.97 392

TestCases				84.47 403	92.18 297	67.29 449		84.43 484	67.63 458	63.48 454	90.18 332	38.20 477	97.16 271	57.04 460	73.37 377	88.97 392

ttmdpeth		69.58 445	66.92 449	77.54 459	75.95 492	62.40 475	88.09 445	84.32 486	62.87 472	65.70 448	86.25 401	36.53 479	88.53 477	55.65 468	46.96 497	81.70 484

tt0320		70.21 443	66.07 451	82.64 425	83.42 457	70.82 427	89.63 429	84.10 487	49.75 502	62.71 462	77.28 476	33.35 487	92.45 443	58.78 453	55.62 467	84.64 459

FE-MVSNET		69.26 450	66.03 452	78.93 451	73.82 496	68.33 446	89.65 428	84.06 488	70.21 449	57.79 484	76.94 480	41.48 469	86.98 488	45.85 492	54.51 471	81.48 486

LCM-MVSNet-Re		83.75 320	83.54 303	84.39 407	93.54 222	64.14 467	92.51 393	84.03 489	83.90 253	66.14 445	86.59 391	67.36 304	92.68 439	84.89 237	92.87 179	96.35 242

Gipuma		45.11 476	42.05 477	54.30 495	80.69 465	51.30 500	35.80 523	83.81 490	28.13 513	27.94 518	34.53 528	11.41 513	76.70 509	21.45 524	54.65 469	34.90 528
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
sc_t1		72.37 434	68.03 445	85.39 388	83.78 454	70.51 429	91.27 415	83.70 491	52.46 499	68.29 432	82.02 449	30.58 494	94.81 404	64.50 423	55.69 466	90.85 340

LCM-MVSNet		52.52 469	48.24 472	65.35 481	47.63 525	41.45 512	72.55 502	83.62 492	31.75 510	37.66 505	57.92 514	9.19 516	76.76 507	49.26 485	44.60 500	77.84 493

FPMVS		55.09 467	52.93 470	61.57 487	55.98 514	40.51 514	83.11 479	83.41 493	37.61 506	34.95 508	71.95 494	14.40 506	76.95 506	29.81 513	65.16 443	67.25 502

Patchmatch-RL test		76.65 410	74.01 416	84.55 402	77.37 485	64.23 466	78.49 492	82.84 494	78.48 373	64.63 452	73.40 489	76.05 172	91.70 456	76.99 328	57.84 462	97.72 136

tt0320-xc		69.70 444	65.27 456	82.99 421	84.33 445	71.92 416	89.56 433	82.08 495	50.11 500	61.87 467	77.50 473	30.48 495	92.34 444	60.30 445	51.20 486	84.71 458

DSMNet-mixed		73.13 429	72.45 423	75.19 470	77.51 484	46.82 503	85.09 471	82.01 496	67.61 462	69.27 430	81.33 456	50.89 428	86.28 489	54.54 470	83.80 307	92.46 328

lessismore_v0				79.98 445	80.59 466	58.34 489		80.87 497		58.49 480	83.46 435	43.10 461	93.89 426	63.11 433	48.68 491	87.72 417

test_f		64.01 459	62.13 461	69.65 475	63.00 510	45.30 509	83.66 477	80.68 498	61.30 480	55.70 488	72.62 492	14.23 507	84.64 494	69.84 395	58.11 461	79.00 491

door								80.13 499

door-mid								79.75 500

PM-MVS		69.32 449	66.93 448	76.49 464	73.60 497	55.84 494	85.91 464	79.32 501	74.72 412	61.09 470	78.18 471	21.76 501	91.10 461	70.86 390	56.90 465	82.51 473

mvsany_test3		67.19 454	65.34 455	72.72 472	63.08 509	48.57 501	83.12 478	78.09 502	72.07 439	61.21 469	77.11 478	22.94 500	87.78 483	78.59 307	51.88 485	81.80 482

dmvs_testset		72.00 438	73.36 420	67.91 477	83.83 453	31.90 523	85.30 469	77.12 503	82.80 285	63.05 460	92.46 292	61.54 357	82.55 500	42.22 499	71.89 388	89.29 370

ANet_high		46.22 472	41.28 479	61.04 488	39.91 531	46.25 506	70.59 505	76.18 504	58.87 491	23.09 525	48.00 524	12.58 510	66.54 517	28.65 517	13.62 527	70.35 500

test_method		56.77 464	54.53 468	63.49 485	76.49 487	40.70 513	75.68 497	74.24 505	19.47 523	48.73 496	71.89 495	19.31 502	65.80 518	57.46 459	47.51 496	83.97 465

APD_test1		56.56 465	53.58 469	65.50 480	67.93 505	46.51 505	77.24 496	72.95 506	38.09 505	42.75 503	75.17 483	13.38 508	82.78 499	40.19 502	54.53 470	67.23 503

EGC-MVSNET		52.46 470	47.56 473	67.15 479	81.98 461	60.11 484	82.54 480	72.44 507	0.11 560	0.70 562	74.59 485	25.11 498	83.26 497	29.04 514	61.51 456	58.09 511

PMMVS2		50.90 471	46.31 474	64.67 482	55.53 515	46.67 504	77.30 495	71.02 508	40.89 504	34.16 509	59.32 511	9.83 515	76.14 510	40.09 503	28.63 514	71.21 499

WB-MVS		57.26 463	56.22 466	60.39 490	69.29 501	35.91 519	86.39 462	70.06 509	59.84 488	46.46 500	72.71 491	51.18 427	78.11 504	15.19 529	34.89 510	67.14 504

SSC-MVS		56.01 466	54.96 467	59.17 491	68.42 503	34.13 520	84.98 472	69.23 510	58.08 494	45.36 501	71.67 497	50.30 435	77.46 505	14.28 530	32.33 511	65.91 506

test_vis1_rt		73.96 421	72.40 424	78.64 454	83.91 452	61.16 481	95.63 294	68.18 511	76.32 398	60.09 474	74.77 484	29.01 497	97.54 225	87.74 210	75.94 362	77.22 494

MTMP							97.53 119	68.16 512

DeepMVS_CX				64.06 484	78.53 480	43.26 511		68.11 513	69.94 451	38.55 504	76.14 482	18.53 503	79.34 501	43.72 495	41.62 504	69.57 501

PMVS	34.80 23	39.19 481	35.53 483	50.18 499	29.72 535	30.30 525	59.60 514	66.20 514	26.06 516	17.91 529	49.53 521	3.12 530	74.09 512	18.19 528	49.40 490	46.14 523
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ArgMatch-SfM		60.14 461	57.35 464	68.50 476	71.14 500	45.17 510	80.16 483	63.06 515	59.74 489	51.33 495	80.81 459	11.74 512	78.30 503	61.13 441	37.05 508	82.04 480

testf1		45.70 473	42.41 475	55.58 493	53.29 518	40.02 515	68.96 506	62.67 516	27.45 514	29.85 515	61.58 508	5.98 521	73.83 513	28.49 518	43.46 502	52.90 515

APD_test2		45.70 473	42.41 475	55.58 493	53.29 518	40.02 515	68.96 506	62.67 516	27.45 514	29.85 515	61.58 508	5.98 521	73.83 513	28.49 518	43.46 502	52.90 515

tmp_tt		41.54 478	41.93 478	40.38 505	20.10 549	26.84 528	61.93 511	59.09 518	14.81 527	28.51 517	80.58 460	35.53 483	48.33 528	63.70 429	13.11 529	45.96 525

ArgMatch-Sym		59.60 462	56.89 465	67.74 478	71.40 499	45.64 508	81.24 482	58.34 519	58.65 492	52.79 493	81.51 455	11.35 514	76.76 507	60.83 444	35.86 509	80.81 488

LoFTR		45.13 475	39.91 480	60.78 489	58.50 512	33.07 521	59.69 513	57.64 520	30.48 512	25.92 521	63.30 504	4.30 524	74.96 511	28.23 521	31.12 513	74.31 498

MVE	35.65 22	33.85 484	29.49 492	46.92 500	41.86 528	36.28 518	50.45 519	56.52 521	18.75 524	18.28 527	37.84 526	2.41 538	58.41 521	18.71 527	20.62 520	46.06 524
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		32.70 488	32.39 487	33.65 509	53.35 517	25.70 529	74.07 500	53.33 522	21.08 521	17.17 530	33.63 530	11.85 511	54.84 523	12.98 532	14.04 525	20.42 533

EMVS		31.70 489	31.45 490	32.48 510	50.72 522	23.95 532	74.78 499	52.30 523	20.36 522	16.08 531	31.48 531	12.80 509	53.60 525	11.39 533	13.10 530	19.88 535

MatchFormer		39.45 480	34.61 484	54.00 496	53.28 520	28.79 527	58.06 516	51.35 524	21.48 519	23.10 524	55.83 516	3.50 529	70.37 515	19.01 526	25.84 516	62.84 507

test_vis3_rt		54.10 468	51.04 471	63.27 486	58.16 513	46.08 507	84.17 474	49.32 525	56.48 496	36.56 506	49.48 522	8.03 517	91.91 452	67.29 406	49.87 488	51.82 519

VLMVS_CLIP		31.24 490	31.62 489	30.09 512	23.48 544	9.99 544	39.45 521	43.68 526	8.32 530	35.12 507	61.15 510	5.95 523	42.45 530	35.23 506	32.16 512	37.83 527

DenseAffine		43.98 477	39.51 481	57.39 492	60.41 511	37.29 517	67.44 508	34.50 527	35.36 508	31.38 513	65.55 502	4.21 525	67.77 516	35.59 505	21.11 519	67.10 505

ELoFTR		28.06 491	23.17 497	42.73 504	26.41 542	16.73 539	32.43 525	29.00 528	18.06 525	18.03 528	50.11 520	1.10 546	53.50 526	21.73 523	11.65 537	57.96 512

GLUNet-SfM		23.82 494	18.93 499	38.50 507	29.22 536	15.72 541	24.44 534	26.94 529	12.76 529	13.93 533	40.99 525	2.01 543	46.93 529	13.88 531	6.19 551	52.85 517

MASt3R-SfM		33.79 485	32.03 488	39.08 506	30.86 534	18.05 537	44.70 520	25.59 530	21.32 520	31.97 511	71.52 498	3.78 527	38.14 532	35.97 504	22.58 518	61.06 510

PDCNetPlus		37.10 483	34.54 485	44.76 501	50.06 524	29.19 526	58.72 515	23.89 531	37.05 507	24.11 523	58.95 513	6.11 520	55.29 522	40.76 501	11.21 538	49.81 520

RoMa-SfM		40.68 479	36.49 482	53.24 497	52.27 521	33.01 522	62.88 510	23.78 532	32.85 509	31.33 514	67.39 501	3.87 526	64.89 519	33.77 508	20.24 521	61.82 509

DKM		38.02 482	33.59 486	51.32 498	50.45 523	30.46 524	61.04 512	19.18 533	30.65 511	26.88 519	61.89 507	2.55 535	61.16 520	32.68 510	16.95 522	62.34 508

VLMVS		26.26 492	26.52 495	25.45 513	25.35 543	7.91 548	30.71 527	15.37 534	3.37 543	34.11 510	65.40 503	8.03 517	21.07 536	32.40 511	23.95 517	47.39 522

RoMa-HiRes		33.28 486	29.63 491	44.22 503	41.01 529	25.30 531	51.82 518	14.13 535	25.85 518	26.34 520	61.96 506	2.78 533	54.52 524	28.42 520	14.36 523	52.83 518

DKM-HiRes		32.92 487	29.13 493	44.31 502	42.93 526	25.35 530	53.22 517	13.26 536	25.92 517	24.31 522	57.58 515	1.88 544	50.95 527	28.87 515	14.19 524	56.63 514

ALIKED-LG		17.53 498	16.82 501	19.64 515	42.07 527	19.09 534	31.53 526	11.93 537	7.76 531	10.68 535	26.90 534	3.52 528	22.14 534	3.10 543	13.89 526	17.68 536

N_pmnet		61.30 460	60.20 463	64.60 483	84.32 446	17.00 538	91.67 411	10.98 538	61.77 477	58.45 481	78.55 469	49.89 436	91.83 453	42.27 498	63.94 449	84.97 456

ALIKED-NN		16.22 500	15.63 502	17.99 517	39.36 532	18.31 536	29.26 530	10.71 539	5.97 533	10.10 536	26.06 535	2.80 532	20.08 537	2.91 544	13.46 528	15.60 539

ALIKED-MNN		16.35 499	15.48 503	18.95 516	40.20 530	19.09 534	30.16 528	10.63 540	6.03 532	9.48 538	24.90 536	2.59 534	21.29 535	2.88 545	12.46 532	16.48 537

XFeat-MNN		10.03 507	9.79 513	10.74 524	9.46 562	6.05 560	16.60 538	9.52 541	4.29 537	8.53 540	22.45 537	2.10 541	13.28 539	5.47 536	9.68 541	12.89 540

PMatch-SfM		26.26 492	22.21 498	38.43 508	28.29 539	16.65 540	37.61 522	8.91 542	18.02 526	18.64 526	53.32 517	0.55 559	41.01 531	24.74 522	9.79 540	57.63 513

SP-DiffGlue		11.69 504	11.68 509	11.70 522	11.01 561	7.08 552	18.35 537	8.44 543	4.41 536	11.18 534	28.64 533	2.84 531	7.44 545	7.44 535	12.85 531	20.56 532

SP-SuperGlue		12.00 503	12.07 506	11.81 520	28.37 538	6.58 553	24.63 532	8.02 544	3.99 538	7.02 541	18.00 540	2.44 537	7.72 544	3.95 540	12.19 534	21.13 531

SP-LightGlue		12.02 502	12.06 507	11.90 519	28.59 537	6.58 553	24.58 533	7.89 545	3.94 539	6.94 542	17.94 541	2.45 536	7.82 542	3.96 539	12.26 533	21.30 529

SP-MNN		11.64 505	11.60 510	11.74 521	27.48 540	6.11 559	24.23 535	7.72 546	3.40 542	6.22 544	17.81 543	2.13 540	7.94 541	3.69 542	11.73 536	21.18 530

XFeat-NN		9.17 509	9.18 514	9.14 525	8.78 563	5.26 562	15.30 539	7.57 547	3.56 541	8.63 539	22.05 538	1.87 545	11.03 540	4.95 537	9.92 539	11.13 541

SP-NN		11.53 506	11.59 511	11.38 523	27.20 541	6.14 558	24.02 536	7.42 548	3.57 540	6.38 543	17.94 541	2.17 539	7.78 543	3.71 541	11.86 535	20.23 534

PMatch-Up-SfM		21.53 496	18.34 500	31.10 511	23.05 545	12.66 542	29.81 529	5.63 549	13.87 528	16.04 532	48.08 523	0.39 563	31.11 533	21.09 525	7.09 548	49.53 521

MVS_clip		23.81 495	25.14 496	19.82 514	33.23 533	11.41 543	26.86 531	4.32 550	5.29 534	31.51 512	63.24 505	7.08 519	7.43 546	28.82 516	25.90 515	40.62 526

SIFT-MNN		6.97 514	7.12 518	6.51 527	21.26 547	8.28 546	11.89 541	4.05 551	2.50 545	3.39 548	11.27 546	0.76 548	6.14 548	0.95 548	8.05 546	5.09 542

SIFT-NN		7.34 512	7.57 517	6.67 526	22.83 546	8.78 545	12.92 540	4.04 552	2.52 544	3.88 546	11.56 545	0.86 547	6.16 547	0.95 548	8.56 544	5.09 542

SIFT-NN-NCMNet		6.77 515	6.92 519	6.30 528	19.98 550	8.05 547	11.79 542	3.97 553	2.43 547	3.43 547	10.93 547	0.75 549	5.95 550	0.88 550	8.15 545	4.90 544

SIFT-NCM-Cal		6.46 516	6.58 520	6.10 529	20.43 548	7.62 549	11.15 544	3.59 554	2.40 550	2.33 556	10.33 553	0.68 553	6.03 549	0.77 556	7.51 547	4.64 548

SIFT-NN-UMatch		6.11 518	6.25 522	5.68 532	17.01 556	6.50 555	11.20 543	3.58 555	2.44 546	2.68 552	10.88 549	0.74 550	5.70 553	0.87 551	6.85 549	4.82 546

wuyk23d		14.10 501	13.89 504	14.72 518	55.23 516	22.91 533	33.83 524	3.56 556	4.94 535	4.11 545	2.28 560	2.06 542	19.66 538	10.23 534	8.74 543	1.59 558

SIFT-NN-CMatch		6.23 517	6.33 521	5.94 530	18.10 554	7.22 551	10.34 545	3.54 557	2.42 548	3.36 549	10.93 547	0.72 551	5.71 552	0.87 551	6.67 550	4.89 545

SIFT-ConvMatch		6.05 519	6.14 523	5.78 531	19.43 551	7.31 550	9.58 548	3.30 558	2.42 548	2.67 553	10.54 551	0.65 554	5.73 551	0.83 554	5.84 553	4.29 549

SIFT-NN-PointCN		5.63 522	5.80 525	5.10 536	16.00 557	5.22 563	10.00 547	3.21 559	2.26 554	2.92 550	10.15 554	0.72 551	5.35 556	0.81 555	6.14 552	4.74 547

SIFT-UMatch		5.86 521	6.01 524	5.38 533	18.70 552	6.22 557	10.07 546	3.07 560	2.39 551	2.42 554	10.54 551	0.63 557	5.65 554	0.84 553	5.49 554	4.28 550

SIFT-CM-Cal		5.56 523	5.66 526	5.26 535	18.45 553	6.34 556	8.44 550	2.81 561	2.36 552	2.42 554	9.99 556	0.64 555	5.41 555	0.74 558	5.05 555	4.02 551

SIFT-PointCN		4.77 525	4.97 528	4.17 539	15.53 559	3.97 564	8.20 551	2.62 562	2.10 555	1.91 560	8.44 558	0.47 561	4.70 559	0.67 560	4.79 556	3.85 554

SIFT-UM-Cal		5.40 524	5.58 527	4.87 537	18.00 555	5.37 561	9.03 549	2.49 563	2.33 553	2.14 558	10.11 555	0.60 558	5.27 557	0.77 556	4.78 557	3.95 552

SIFT-PCN-Cal		4.71 526	4.89 529	4.18 538	15.70 558	3.90 565	7.58 552	2.37 564	2.09 556	1.95 559	8.68 557	0.51 560	4.71 558	0.68 559	4.45 558	3.93 553

SIFT-NCMNet		4.03 527	4.21 530	3.50 540	14.53 560	3.56 566	6.14 553	1.51 565	2.08 557	1.72 561	7.39 559	0.42 562	4.00 560	0.57 561	3.56 559	2.93 555

MVS_baseline		7.08 513	7.68 516	5.28 534	7.84 564	0.20 569	2.38 554	0.52 566	0.10 561	10.02 537	34.66 527	0.64 555	0.00 563	4.06 538	8.92 542	15.64 538

testmvs		9.92 508	12.94 505	0.84 542	0.65 565	0.29 568	93.78 365	0.39 567	0.42 558	2.85 551	15.84 544	0.17 565	0.30 562	2.18 546	0.21 560	1.91 557

test123		9.07 510	11.73 508	1.11 541	0.50 566	0.77 567	89.44 434	0.20 568	0.34 559	2.15 557	10.72 550	0.34 564	0.32 561	1.79 547	0.08 561	2.23 556

mmdepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

monomultidepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

test_blank		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uanet_test		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

DCPMVS		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

pcd_1.5k_mvsjas		5.92 520	7.89 515	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	71.04 266	0.00 563	0.00 562	0.00 562	0.00 559

sosnet-low-res		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

sosnet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uncertanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

Regformer		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

n2								0.00 569

nn								0.00 569

ab-mvs-re		8.11 511	10.81 512	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	97.30 119	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

Meshroom													0.00 563
: In preparation.
AliceVision / Meshro													0.00 563
: In preparation.
AliceVision_Meshroom													0.00 563
: In preparation.
PatchmatchNet1														42.17 500	64.00 448	85.01 455
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													91.74 454
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						67.18 451								49.00 486

PC_three_1452									91.12 52	98.33 6	98.42 45	92.51 2	99.81 29	98.96 6	99.37 1	99.70 4

eth-test2					0.00 567

eth-test					0.00 567

OPU-MVS				97.30 2	99.19 8	92.31 3	99.12 17				98.54 31	92.06 3	99.84 19	99.11 5	99.37 1	99.74 1

test_0728_THIRD									88.38 94	96.69 32	98.76 19	89.64 14	99.76 47	97.47 42	98.84 23	99.38 15

GSMVS																97.54 155

test_part2					98.90 25	85.14 81				96.07 44

sam_mvs1												77.59 133				97.54 155

sam_mvs												75.35 194

test_post1							85.88 465				30.24 532	73.77 219	95.07 395	73.89 366

test_post											33.80 529	76.17 168	95.97 334

patchmatchnet-post											77.09 479	77.78 131	95.39 368

gm-plane-assit					92.27 289	79.64 263			84.47 233		95.15 210		97.93 188	85.81 229

test9_res														96.00 60	99.03 13	98.31 79

agg_prior2														94.30 85	99.00 15	98.57 62

test_prior4						82.34 151	97.75 101

test_prior2							98.37 57		86.08 173	94.57 72	98.02 74	83.14 64		95.05 76	98.79 27

旧先验2							96.97 174		74.06 418	96.10 43			97.76 201	88.38 202

新几何2							96.42 225

原ACMM2							96.84 185

testdata2													99.48 92	76.45 337

segment_acmp												82.69 70

testdata1							95.57 298		87.44 128

plane_prior7					91.86 317	77.55 340

plane_prior6					91.98 312	77.92 326						64.77 328

plane_prior4											94.15 257

plane_prior3						77.75 336			90.17 69	81.33 297

plane_prior2							97.18 149		89.89 72

plane_prior1					91.95 314

plane_prior						77.96 323	97.52 122		90.36 67						82.96 316

HQP5-MVS						78.48 301

HQP-NCC					92.08 305		97.63 108		90.52 62	82.30 284

ACMP_Plane					92.08 305		97.63 108		90.52 62	82.30 284

BP-MVS														87.67 212

HQP4-MVS										82.30 284			97.32 258			91.13 335

HQP2-MVS												65.40 321

NP-MVS					92.04 309	78.22 313					94.56 238

MDTV_nov1_ep13_2view						81.74 178	86.80 457		80.65 324	85.65 230		74.26 212		76.52 336		96.98 214

ACMMP++_ref															78.45 351

ACMMP++															79.05 343

Test By Simon												71.65 258

High-resolution multi-view benchmark