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.

DELS-MVS		82.32 5	82.50 5	81.79 14	86.80 53	56.89 32	92.77 2	86.30 112	77.83 1	77.88 49	92.13 60	60.24 9	94.78 20	78.97 66	89.61 8	93.69 9
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
patch_mono-2		80.84 12	81.59 10	78.62 80	90.34 10	53.77 132	88.08 63	88.36 63	76.17 2	79.40 41	91.09 85	55.43 33	90.09 138	85.01 16	80.40 93	91.99 55

MCST-MVS		83.01 1	83.30 2	82.15 11	92.84 2	57.58 19	93.77 1	91.10 14	75.95 3	77.10 54	93.09 38	54.15 44	95.57 13	85.80 13	85.87 41	93.31 13

MM		82.69 2	83.29 3	80.89 25	84.38 96	55.40 64	92.16 10	89.85 26	75.28 4	82.41 12	93.86 15	54.30 41	93.98 27	90.29 1	87.13 22	93.30 14

MGCNet		82.10 7	82.64 4	80.47 30	86.63 55	54.69 108	92.20 9	86.66 103	74.48 5	82.63 11	93.80 17	50.83 70	93.70 34	90.11 2	86.44 34	93.01 23

CLD-MVS		75.60 104	75.39 91	76.24 169	80.69 215	52.40 176	90.69 23	86.20 114	74.40 6	65.01 207	88.93 142	42.05 217	90.58 120	76.57 89	73.96 196	85.73 275
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
myMVS_eth3d28		77.77 45	77.94 36	77.27 133	87.58 46	52.89 163	86.06 129	91.33 12	74.15 7	68.16 169	88.24 167	58.17 20	88.31 223	69.88 159	77.87 128	90.61 122

fmvsm_l_mol_unc0.5_1		78.65 29	79.09 25	77.33 128	78.55 281	53.79 131	88.87 52	71.62 427	74.12 8	81.93 16	95.02 3	57.79 22	86.96 283	80.83 52	83.10 65	91.23 92

EPNet		78.36 35	78.49 30	77.97 108	85.49 74	52.04 186	89.36 42	84.07 200	73.22 9	77.03 55	91.72 75	49.32 87	90.17 136	73.46 128	82.77 68	91.69 66
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CANet		80.90 11	81.17 12	80.09 43	87.62 45	54.21 123	91.60 14	86.47 108	73.13 10	79.89 35	93.10 36	49.88 81	92.98 40	84.09 25	84.75 56	93.08 21

FBQ-MVS		78.34 36	77.25 49	81.62 17	86.35 59	59.48 6	86.95 101	90.95 18	72.89 11	71.91 110	87.60 198	53.35 49	92.65 50	70.19 155	75.03 185	92.72 31

UBG		78.86 28	78.86 27	78.86 66	87.80 43	55.43 60	87.67 73	91.21 13	72.83 12	72.10 105	88.40 157	58.53 19	89.08 179	73.21 133	77.98 127	92.08 47

testing11		79.18 26	78.85 28	80.16 38	88.33 32	56.99 29	88.31 60	92.06 2	72.82 13	70.62 144	88.37 159	57.69 23	92.30 60	75.25 103	76.24 157	91.20 95

testing915		80.82 13	80.48 15	81.83 13	86.14 62	59.23 8	88.16 61	92.18 1	72.63 14	73.09 89	89.67 129	62.49 7	92.70 48	81.13 51	78.86 117	93.55 10

VPNet		72.07 183	71.42 174	74.04 252	78.64 279	47.17 345	89.91 31	87.97 71	72.56 15	64.66 214	85.04 243	41.83 222	88.33 221	61.17 240	60.97 340	86.62 256

testing222		77.70 47	77.22 51	79.14 57	86.95 51	54.89 97	87.18 94	91.96 3	72.29 16	71.17 127	88.70 147	55.19 34	91.24 90	65.18 203	76.32 155	91.29 88

NormalMVS		77.09 57	77.02 54	77.32 130	81.66 179	52.32 179	89.31 43	82.11 239	72.20 17	73.23 86	91.05 86	46.52 126	91.00 101	76.23 90	80.83 85	88.64 194

SymmetryMVS		77.43 52	77.09 53	78.44 96	82.56 152	52.32 179	89.31 43	84.15 198	72.20 17	73.23 86	91.05 86	46.52 126	91.00 101	76.23 90	78.55 120	92.00 54

casdiffmvs		77.36 53	76.85 58	78.88 65	80.40 230	54.66 111	87.06 97	85.88 121	72.11 19	71.57 115	88.63 152	50.89 69	90.35 128	76.00 93	79.11 112	91.63 69
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSC-MVS3.2		68.13 275	66.89 268	71.85 328	82.26 157	43.97 397	82.09 291	89.29 31	71.74 20	61.12 272	79.83 330	34.60 334	87.45 265	41.23 401	59.85 350	84.14 302

testing99		78.45 31	77.78 40	80.45 31	88.28 35	56.81 35	87.95 68	91.49 7	71.72 21	70.84 137	88.09 176	57.29 25	92.63 53	69.24 165	75.13 181	91.91 56

viewmanbaseed2359cas		76.71 69	76.16 73	78.37 100	81.16 197	55.05 81	86.96 100	85.32 141	71.71 22	72.25 104	88.50 155	46.86 116	88.96 188	74.55 108	78.08 126	91.08 100

casdiffmvs_mvg		77.75 46	77.28 48	79.16 56	80.42 229	54.44 117	87.76 70	85.46 134	71.67 23	71.38 122	88.35 162	51.58 59	91.22 91	79.02 65	79.89 103	91.83 61
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline1		72.51 171	72.12 162	73.69 266	85.05 82	44.46 389	83.51 241	86.13 117	71.61 24	64.64 215	87.97 183	55.00 39	89.48 164	59.07 259	56.05 392	87.13 240

E3new		76.85 64	76.24 71	78.66 75	81.62 182	55.01 83	86.94 102	85.10 159	71.55 25	71.93 109	88.61 153	48.40 91	89.60 159	74.50 109	77.53 134	91.36 83

testing91		78.30 38	77.54 43	80.61 26	88.16 38	57.12 28	87.94 69	91.07 17	71.43 26	70.75 139	88.04 181	55.82 32	92.65 50	69.61 160	75.00 186	92.05 50

WTY-MVS		77.47 51	77.52 44	77.30 131	88.33 32	46.25 366	88.46 58	90.32 22	71.40 27	72.32 102	91.72 75	53.44 48	92.37 59	66.28 188	75.42 175	93.28 15

baseline		76.86 63	76.24 71	78.71 71	80.47 224	54.20 125	83.90 229	84.88 170	71.38 28	71.51 118	89.15 140	50.51 72	90.55 121	75.71 96	78.65 118	91.39 80

viewcassd2359sk11		76.66 70	76.01 77	78.62 80	81.14 198	54.95 86	86.88 106	85.04 161	71.37 29	71.76 112	88.44 156	48.02 97	89.57 161	74.17 116	77.23 136	91.33 87

ETVMVS		75.80 98	75.44 89	76.89 148	86.23 61	50.38 239	85.55 158	91.42 8	71.30 30	68.80 163	87.94 184	56.42 29	89.24 173	56.54 293	74.75 190	91.07 101

PRO-TEST		79.94 19	79.98 16	79.81 47	87.63 44	55.24 69	87.59 80	88.40 62	71.10 31	76.93 56	91.92 70	46.57 124	91.41 83	84.32 21	85.41 47	92.79 29

E2		76.39 76	75.67 81	78.56 87	80.49 222	54.87 98	86.80 110	84.95 165	71.09 32	71.51 118	88.21 169	47.55 104	89.53 162	73.65 124	76.77 146	91.29 88

E3		76.39 76	75.67 81	78.56 87	80.49 222	54.87 98	86.80 110	84.95 165	71.09 32	71.51 118	88.21 169	47.55 104	89.53 162	73.65 124	76.77 146	91.29 88

Casviewmamba		76.27 80	75.48 87	78.63 79	79.14 262	54.27 120	85.81 139	83.09 223	70.96 34	70.41 148	88.36 161	48.71 90	90.81 110	75.92 94	76.95 141	90.80 115

gm-plane-assit					83.24 125	54.21 123			70.91 35		88.23 168		95.25 15	66.37 186

viewmacassd2359aftdt		75.91 92	75.14 97	78.21 103	79.40 252	54.82 100	86.71 113	84.98 163	70.89 36	71.52 117	87.89 186	45.43 158	88.85 197	72.35 139	77.08 138	90.97 109

hybridcas		76.66 70	75.99 78	78.65 77	79.25 258	54.46 116	86.82 109	85.53 131	70.88 37	70.40 149	88.21 169	49.55 84	90.12 137	74.42 111	78.88 116	91.37 82

E4		75.99 88	75.16 96	78.48 92	79.56 248	54.74 103	86.66 115	84.80 173	70.62 38	71.16 128	87.90 185	46.84 117	89.47 166	72.70 135	76.20 159	91.23 92

PS-MVSNAJ		80.06 18	79.52 20	81.68 16	85.58 72	60.97 3	91.69 12	87.02 92	70.62 38	80.75 28	93.22 35	37.77 268	92.50 55	82.75 34	86.25 36	91.57 72

DeepPCF-MVS	69.37 1	80.65 14	81.56 11	77.94 111	85.46 75	49.56 261	90.99 21	86.66 103	70.58 40	80.07 34	95.30 2	56.18 30	90.97 106	82.57 37	86.22 37	93.28 15

diffmvs		75.11 115	74.65 112	76.46 162	78.52 282	53.35 145	83.28 253	79.94 291	70.51 41	71.64 114	88.72 146	46.02 138	86.08 320	77.52 81	75.75 171	89.96 151
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CNVR-MVS		81.76 9	81.90 8	81.33 21	90.04 11	57.70 17	91.71 11	88.87 42	70.31 42	77.64 53	93.87 14	52.58 54	93.91 30	84.17 23	87.92 17	92.39 37

xiu_mvs_v2_base		79.86 20	79.31 22	81.53 18	85.03 84	60.73 4	91.65 13	86.86 95	70.30 43	80.77 27	93.07 40	37.63 274	92.28 62	82.73 35	85.71 42	91.57 72

fmvsm_s_conf0.5_n_9		76.66 70	76.94 57	75.85 184	79.54 249	48.30 307	82.63 274	71.84 420	70.25 44	80.63 31	94.53 4	50.78 71	87.42 267	88.32 5	73.92 198	91.82 62

E5new		75.74 99	74.80 108	78.57 85	79.85 239	54.93 88	85.87 134	84.72 178	70.19 45	70.90 133	87.74 190	45.97 143	89.71 152	72.15 142	75.79 165	91.06 102

E6new		75.74 99	74.80 108	78.56 87	79.85 239	54.92 93	85.87 134	84.72 178	70.19 45	70.90 133	87.73 192	45.98 140	89.71 152	72.16 140	75.78 168	91.06 102

E6		75.74 99	74.80 108	78.56 87	79.85 239	54.92 93	85.87 134	84.72 178	70.19 45	70.90 133	87.73 192	45.98 140	89.71 152	72.16 140	75.78 168	91.06 102

E5		75.74 99	74.80 108	78.57 85	79.85 239	54.93 88	85.87 134	84.72 178	70.19 45	70.90 133	87.74 190	45.97 143	89.71 152	72.15 142	75.79 165	91.06 102

viewdifsd2359ckpt13		75.96 89	75.07 98	78.65 77	81.14 198	55.21 72	86.15 126	84.95 165	69.98 49	70.49 147	88.16 172	46.10 134	89.86 144	72.39 138	76.23 158	90.89 112

baseline2		75.15 114	74.54 114	76.98 145	81.67 178	51.74 201	83.84 231	91.94 4	69.97 50	58.98 302	86.02 225	59.73 11	91.73 75	68.37 173	70.40 249	87.48 229

viewdifsd2359ckpt09		74.92 119	73.70 129	78.60 84	80.28 231	54.94 87	84.77 197	80.56 277	69.96 51	69.38 155	88.38 158	46.01 139	90.50 123	72.44 137	71.49 232	90.38 130

diffmvs_AUTHOR		74.80 123	74.30 117	76.29 166	77.34 308	53.19 151	83.17 258	79.50 305	69.93 52	71.55 116	88.57 154	45.85 148	86.03 323	77.17 85	75.64 172	89.67 157

CHOSEN 1792x2688		76.24 81	74.03 122	82.88 2	83.09 130	62.84 2	85.73 148	85.39 137	69.79 53	64.87 212	83.49 270	41.52 226	93.69 35	70.55 151	81.82 77	92.12 46

fmvsm_s_conf0.5_n_6		76.17 83	76.84 59	74.15 249	77.42 307	46.46 358	85.53 160	77.86 348	69.78 54	79.78 37	92.90 45	46.80 118	84.81 350	84.67 19	76.86 145	91.17 97

BridgeMVS		80.28 17	79.73 17	81.90 12	86.47 57	59.34 7	80.45 335	89.51 29	69.76 55	71.05 129	86.66 214	58.68 18	93.24 37	84.64 20	90.40 6	93.14 20

CANet_DTU		73.71 146	73.14 138	75.40 203	82.61 151	50.05 248	84.67 203	79.36 311	69.72 56	75.39 63	90.03 122	29.41 386	85.93 330	67.99 177	79.11 112	90.22 136

TSAR-MVS + MP.		78.31 37	78.26 31	78.48 92	81.33 195	56.31 46	81.59 310	86.41 109	69.61 57	81.72 21	88.16 172	55.09 37	88.04 233	74.12 117	86.31 35	91.09 99
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
dmvs_re		67.61 284	66.00 290	72.42 306	81.86 170	43.45 403	64.67 453	80.00 287	69.56 58	60.07 282	85.00 244	34.71 332	87.63 257	51.48 341	66.68 279	86.17 266

hybridnocas07		74.65 124	74.00 124	76.61 159	77.58 300	52.72 168	83.64 235	79.72 297	69.43 59	70.80 138	88.33 164	45.56 153	87.34 271	76.88 87	74.07 194	89.78 155

DPM-MVS		82.39 4	82.36 7	82.49 6	80.12 235	59.50 5	92.24 8	90.72 19	69.37 60	83.22 9	94.47 5	63.81 6	93.18 39	74.02 118	93.25 2	94.80 1

onestephybrid01		74.31 131	73.65 130	76.27 167	77.58 300	51.99 188	82.22 287	78.44 337	69.26 61	70.95 132	88.11 175	44.46 179	87.30 272	78.01 79	73.86 200	89.51 166

viewmamba		73.92 140	73.03 142	76.58 160	77.56 302	52.73 167	82.91 267	78.77 325	69.23 62	68.85 162	88.01 182	44.71 177	87.57 261	73.86 121	73.40 205	89.44 170

lupinMVS		78.38 34	78.11 34	79.19 54	83.02 134	55.24 69	91.57 15	84.82 171	69.12 63	76.67 57	92.02 65	44.82 173	90.23 134	80.83 52	80.09 97	92.08 47

casdiffseed414692147		74.22 132	72.73 145	78.69 72	79.85 239	54.64 112	85.13 176	83.67 212	69.07 64	69.41 154	86.47 219	43.27 200	90.69 113	63.77 216	73.91 199	90.73 117

fmvsm_s_conf0.5_n_11		76.28 79	76.81 60	74.71 231	79.21 259	46.90 347	85.03 184	73.96 400	69.00 65	79.70 38	93.88 13	48.07 94	87.71 253	84.26 22	78.15 125	89.50 167

fmvsm_s_conf0.5_n_10		76.80 65	76.81 60	76.78 155	78.91 270	47.85 327	83.44 244	74.66 391	68.93 66	81.31 24	94.12 8	47.44 108	90.82 109	83.43 29	79.06 114	91.66 67

fmvsm_l_conf0.5_n_9		77.10 56	77.48 45	75.98 181	77.54 304	47.77 332	86.35 120	73.46 411	68.69 67	81.07 26	94.40 6	49.06 88	88.89 193	87.39 8	79.32 109	91.27 91

PAPM		76.76 67	76.07 75	78.81 67	80.20 233	59.11 9	86.86 107	86.23 113	68.60 68	70.18 151	88.84 145	51.57 60	87.16 277	65.48 196	86.68 31	90.15 141

DeepC-MVS_fast	67.50 3	78.00 42	77.63 41	79.13 58	88.52 29	55.12 77	89.95 28	85.98 119	68.31 69	71.33 123	92.75 49	45.52 156	90.37 127	71.15 149	85.14 50	91.91 56
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
jason		77.01 59	76.45 67	78.69 72	79.69 245	54.74 103	90.56 24	83.99 203	68.26 70	74.10 75	90.91 96	42.14 215	89.99 140	79.30 63	79.12 111	91.36 83
jason: jason.
hybrid		74.44 127	73.79 128	76.39 163	77.31 310	52.89 163	83.37 251	79.79 295	68.21 71	71.01 130	88.14 174	44.93 169	86.68 296	77.29 84	74.11 193	89.59 160

ETV-MVS		77.17 55	76.74 63	78.48 92	81.80 171	54.55 114	86.13 127	85.33 140	68.20 72	73.10 88	90.52 105	45.23 162	90.66 116	79.37 62	80.95 82	90.22 136

viewdifsd2359ckpt07		74.81 122	74.01 123	77.21 137	79.62 246	53.13 155	85.70 153	83.75 206	68.12 73	68.14 170	87.33 204	46.51 128	87.92 236	73.32 129	73.63 202	90.57 123

fmvsm_s_conf0.5_n_8		76.50 74	76.68 65	75.94 182	78.67 275	47.92 325	85.18 174	74.71 390	68.09 74	80.67 30	94.26 7	47.09 113	89.26 172	86.62 10	74.85 188	90.65 119

h-mvs33		73.95 138	72.89 143	77.15 138	80.17 234	50.37 240	84.68 201	83.33 215	68.08 75	71.97 107	88.65 151	42.50 209	91.15 94	78.82 67	57.78 378	89.91 153

hse-mvs2		71.44 199	70.68 188	73.73 265	76.34 327	47.44 340	79.45 356	79.47 307	68.08 75	71.97 107	86.01 227	42.50 209	86.93 286	78.82 67	53.46 416	86.83 251

MVS_Test		75.85 94	74.93 103	78.62 80	84.08 105	55.20 75	83.99 225	85.17 150	68.07 77	73.38 83	82.76 281	50.44 74	89.00 184	65.90 192	80.61 88	91.64 68

ET-MVSNet_ETH3D		75.23 112	74.08 120	78.67 74	84.52 93	55.59 56	88.92 50	89.21 34	68.06 78	53.13 385	90.22 115	49.71 82	87.62 259	72.12 144	70.82 240	92.82 27

reproduce_monomvs		69.71 237	68.52 231	73.29 279	86.43 58	48.21 310	83.91 228	86.17 116	68.02 79	54.91 366	77.46 356	42.96 206	88.86 194	68.44 172	48.38 435	82.80 343

tpmrst		71.04 208	69.77 210	74.86 227	83.19 127	55.86 55	75.64 381	78.73 328	67.88 80	64.99 208	73.73 399	49.96 80	79.56 410	65.92 191	67.85 273	89.14 180

dcpmvs_2		79.33 25	78.94 26	80.49 28	89.75 13	56.54 40	84.83 195	83.68 208	67.85 81	69.36 156	90.24 113	60.20 10	92.10 68	84.14 24	80.40 93	92.82 27

PVSNet_Blended		76.53 73	76.54 66	76.50 161	85.91 64	51.83 195	88.89 51	84.24 195	67.82 82	69.09 160	89.33 137	46.70 121	88.13 229	75.43 99	81.48 81	89.55 162

tpm		68.36 268	67.48 259	70.97 342	79.93 238	51.34 211	76.58 378	78.75 327	67.73 83	63.54 244	74.86 389	48.33 92	72.36 462	53.93 317	63.71 312	89.21 177

NCCC		79.57 22	79.23 23	80.59 27	89.50 16	56.99 29	91.38 16	88.17 67	67.71 84	73.81 78	92.75 49	46.88 115	93.28 36	78.79 69	84.07 61	91.50 78

sasdasda		78.17 39	77.86 38	79.12 59	84.30 100	54.22 121	87.71 71	84.57 186	67.70 85	77.70 51	92.11 63	50.90 66	89.95 142	78.18 76	77.54 132	93.20 17

canonicalmvs		78.17 39	77.86 38	79.12 59	84.30 100	54.22 121	87.71 71	84.57 186	67.70 85	77.70 51	92.11 63	50.90 66	89.95 142	78.18 76	77.54 132	93.20 17

3Dnovator	64.70 6	74.46 126	72.48 149	80.41 32	82.84 144	55.40 64	83.08 261	88.61 54	67.61 87	59.85 284	88.66 148	34.57 335	93.97 28	58.42 268	88.70 12	91.85 60

VNet		77.99 43	77.92 37	78.19 104	87.43 48	50.12 247	90.93 22	91.41 9	67.48 88	75.12 64	90.15 119	46.77 120	91.00 101	73.52 126	78.46 121	93.44 11

WBMVS		73.93 139	73.39 132	75.55 196	87.82 42	55.21 72	89.37 40	87.29 84	67.27 89	63.70 237	80.30 323	60.32 8	86.47 304	61.58 236	62.85 328	84.97 289

dmvs_testset		57.65 396	58.21 377	55.97 456	74.62 364	9.82 519	63.75 456	63.34 466	67.23 90	48.89 418	83.68 269	39.12 255	76.14 441	23.43 479	59.80 351	81.96 351

nomal-1		72.45 172	71.14 180	76.37 164	84.65 89	56.28 47	68.39 441	88.28 64	67.21 91	62.98 248	80.23 324	49.71 82	86.05 321	69.36 163	69.48 258	86.78 254

fmvsm_l_conf0.5_n_3		75.73 103	75.78 79	75.61 192	76.03 338	48.33 305	85.34 164	72.92 414	67.16 92	78.55 46	93.85 16	46.22 130	87.53 263	85.61 14	76.30 156	90.98 108

IB-MVS	68.87 2	74.01 137	72.03 166	79.94 45	83.04 133	55.50 58	90.24 25	88.65 49	67.14 93	61.38 269	81.74 308	53.21 50	94.28 24	60.45 250	62.41 331	90.03 149
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
fmvsm_s_conf0.5_n_7		73.10 157	73.89 127	70.72 345	74.17 372	46.03 371	83.28 253	74.19 395	67.10 94	73.94 77	91.73 74	43.42 198	77.61 429	83.92 27	73.26 207	88.53 203

fmvsm_s_conf0.5_n_5		75.02 116	75.07 98	74.88 226	74.33 370	47.83 329	83.99 225	73.54 406	67.10 94	76.32 60	92.43 56	45.42 159	86.35 310	82.98 32	79.50 108	90.47 128

fmvsm_s_conf0.5_n_4		74.92 119	74.88 104	75.03 221	75.96 341	47.53 335	85.84 138	73.19 413	67.07 96	79.43 40	92.60 53	46.12 132	88.03 234	84.70 18	69.01 259	89.53 164

MVSTER		73.25 155	72.33 153	76.01 179	85.54 73	53.76 133	83.52 237	87.16 89	67.06 97	63.88 232	81.66 309	52.77 52	90.44 125	64.66 208	64.69 304	83.84 316

test_fmvsmconf_n		74.41 128	74.05 121	75.49 201	74.16 373	48.38 301	82.66 272	72.57 415	67.05 98	75.11 65	92.88 46	46.35 129	87.81 243	83.93 26	71.71 228	90.28 134

viewdifsd2359ckpt11		70.68 215	69.10 224	75.40 203	75.33 353	50.85 221	81.57 311	78.00 344	66.99 99	64.96 209	85.52 233	39.52 250	86.81 291	68.86 169	61.15 339	88.56 200

viewmsd2359difaftdt		70.68 215	69.10 224	75.40 203	75.33 353	50.85 221	81.57 311	78.00 344	66.99 99	64.96 209	85.52 233	39.52 250	86.81 291	68.86 169	61.16 338	88.56 200

DeepC-MVS	67.15 4	76.90 62	76.27 70	78.80 68	80.70 214	55.02 82	86.39 118	86.71 101	66.96 101	67.91 172	89.97 123	48.03 96	91.41 83	75.60 98	84.14 60	89.96 151
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FIs		70.00 231	70.24 203	69.30 365	77.93 294	38.55 444	83.99 225	87.72 78	66.86 102	57.66 332	84.17 256	52.28 55	85.31 339	52.72 332	68.80 264	84.02 306

test_fmvsmconf0.1_n		73.69 147	73.15 136	75.34 207	70.71 414	48.26 308	82.15 288	71.83 421	66.75 103	74.47 73	92.59 54	44.89 170	87.78 250	83.59 28	71.35 235	89.97 150

SDMVSNet		71.89 188	70.62 190	75.70 190	81.70 175	51.61 203	73.89 400	88.72 48	66.58 104	61.64 267	82.38 294	37.63 274	89.48 164	77.44 82	65.60 295	86.01 267

sd_testset		67.79 281	65.95 292	73.32 276	81.70 175	46.33 363	68.99 437	80.30 281	66.58 104	61.64 267	82.38 294	30.45 380	87.63 257	55.86 301	65.60 295	86.01 267

PC_three_1452									66.58 104	87.27 3	93.70 20	66.82 4	94.95 18	89.74 4	91.98 4	93.98 6

test_fmvsm_n_1920		75.56 105	75.54 86	75.61 192	74.60 365	49.51 266	81.82 299	74.08 397	66.52 107	80.40 32	93.46 27	46.95 114	89.72 151	86.69 9	75.30 176	87.61 227

SD_0403		65.51 328	65.18 312	66.48 398	78.37 286	29.94 482	74.64 395	78.55 333	66.47 108	54.87 367	84.35 254	38.20 264	82.47 375	38.90 408	72.30 223	87.05 241

PVSNet	62.49 8	69.27 248	67.81 251	73.64 267	84.41 95	51.85 194	84.63 204	77.80 349	66.42 109	59.80 285	84.95 245	22.14 441	80.44 398	55.03 309	75.11 182	88.62 197

CS-MVS		76.77 66	76.70 64	76.99 144	83.55 115	48.75 288	88.60 56	85.18 149	66.38 110	72.47 100	91.62 79	45.53 155	90.99 105	74.48 110	82.51 70	91.23 92

UniMVSNet_NR-MVSNet		68.82 258	68.29 236	70.40 351	75.71 345	42.59 415	84.23 216	86.78 99	66.31 111	58.51 316	82.45 291	51.57 60	84.64 353	53.11 323	55.96 393	83.96 312

HY-MVS	67.03 5	73.90 141	73.14 138	76.18 174	84.70 88	47.36 341	75.56 384	86.36 111	66.27 112	70.66 142	83.91 261	51.05 64	89.31 170	67.10 182	72.61 217	91.88 58

IU-MVS					89.48 18	57.49 20		91.38 10	66.22 113	88.26 2				82.83 33	87.60 19	92.44 36

fmvsm_s_conf0.5_n_3		74.97 118	75.42 90	73.62 269	76.99 318	46.67 352	83.13 259	71.14 430	66.20 114	82.13 14	93.76 18	47.49 106	84.00 359	81.95 41	76.02 160	90.19 140

testing3-2		72.30 178	72.35 152	72.15 313	83.07 131	47.64 333	85.46 163	89.81 27	66.17 115	61.96 264	84.88 247	58.93 14	82.27 376	55.87 300	64.97 298	86.54 257

EI-MVSNet-Vis-set		73.19 156	72.60 147	74.99 224	82.56 152	49.80 256	82.55 278	89.00 37	66.17 115	65.89 192	88.98 141	43.83 185	92.29 61	65.38 202	69.01 259	82.87 342

alignmvs		78.08 41	77.98 35	78.39 98	83.53 116	53.22 150	89.77 32	85.45 135	66.11 117	76.59 59	91.99 67	54.07 45	89.05 181	77.34 83	77.00 140	92.89 25

TESTMET0.1,1		72.86 162	72.33 153	74.46 236	81.98 165	50.77 224	85.13 176	85.47 133	66.09 118	67.30 175	83.69 267	37.27 284	83.57 366	65.06 205	78.97 115	89.05 183

MSP-MVS		82.30 6	83.47 1	78.80 68	82.99 136	52.71 169	85.04 183	88.63 51	66.08 119	86.77 4	92.75 49	72.05 1	91.46 82	83.35 30	93.53 1	92.23 42
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
CostFormer		73.89 142	72.30 155	78.66 75	82.36 156	56.58 37	75.56 384	85.30 143	66.06 120	70.50 146	76.88 369	57.02 26	89.06 180	68.27 175	68.74 265	90.33 132

NR-MVSNet		67.25 297	65.99 291	71.04 341	73.27 382	43.91 398	85.32 168	84.75 176	66.05 121	53.65 383	82.11 301	45.05 164	85.97 328	47.55 367	56.18 390	83.24 332

HPM-MVS++		80.50 15	80.71 14	79.88 46	87.34 49	55.20 75	89.93 29	87.55 82	66.04 122	79.46 39	93.00 42	53.10 51	91.76 73	80.40 55	89.56 9	92.68 33

SPE-MVS-test		77.20 54	77.25 49	77.05 139	84.60 91	49.04 278	89.42 39	85.83 123	65.90 123	72.85 93	91.98 69	45.10 163	91.27 88	75.02 105	84.56 57	90.84 113

test_fmvsmconf0.01_n		71.97 186	70.95 185	75.04 220	66.21 450	47.87 326	80.35 338	70.08 438	65.85 124	72.69 95	91.68 77	39.99 246	87.67 255	82.03 40	69.66 254	89.58 161

MGCFI-Net		74.07 136	74.64 113	72.34 309	82.90 140	43.33 407	80.04 344	79.96 290	65.61 125	74.93 66	91.85 71	48.01 98	80.86 389	71.41 147	77.10 137	92.84 26

UWE-MVS		72.17 182	72.15 160	72.21 311	82.26 157	44.29 393	86.83 108	89.58 28	65.58 126	65.82 193	85.06 240	45.02 165	84.35 355	54.07 315	75.18 178	87.99 218

viewmambaseed2359dif		73.51 151	72.78 144	75.71 189	76.93 320	51.89 193	82.81 269	79.66 300	65.46 127	70.29 150	88.05 179	45.55 154	85.85 331	73.49 127	72.76 215	89.39 171

HQP-NCC					79.02 266		88.00 64		65.45 128	64.48 220

ACMP_Plane					79.02 266		88.00 64		65.45 128	64.48 220

HQP-MVS		72.34 176	71.44 173	75.03 221	79.02 266	51.56 205	88.00 64	83.68 208	65.45 128	64.48 220	85.13 238	37.35 281	88.62 202	66.70 183	73.12 209	84.91 291

PVSNet_BlendedMVS		73.42 152	73.30 134	73.76 263	85.91 64	51.83 195	86.18 125	84.24 195	65.40 131	69.09 160	80.86 317	46.70 121	88.13 229	75.43 99	65.92 294	81.33 367

MS-PatchMatch		72.34 176	71.26 176	75.61 192	82.38 155	55.55 57	88.00 64	89.95 25	65.38 132	56.51 354	80.74 319	32.28 361	92.89 41	57.95 277	88.10 16	78.39 402

v2v482		69.55 244	67.64 253	75.26 216	72.32 395	53.83 129	84.93 191	81.94 244	65.37 133	60.80 275	79.25 337	41.62 223	88.98 187	63.03 222	59.51 353	82.98 340

VDD-MVS		76.08 86	74.97 102	79.44 49	84.27 103	53.33 147	91.13 20	85.88 121	65.33 134	72.37 101	89.34 135	32.52 358	92.76 47	77.90 80	75.96 163	92.22 44

TranMVSNet+NR-MVSNet		66.94 307	65.61 301	70.93 343	73.45 378	43.38 405	83.02 264	84.25 193	65.31 135	58.33 323	81.90 305	39.92 248	85.52 335	49.43 353	54.89 402	83.89 315

EI-MVSNet-UG-set		72.37 175	71.73 167	74.29 245	81.60 184	49.29 273	81.85 297	88.64 50	65.29 136	65.05 205	88.29 166	43.18 201	91.83 72	63.74 217	67.97 271	81.75 354

usedtu_dtu_shiyan1		69.05 251	67.91 242	72.46 304	75.40 350	46.24 367	85.74 146	86.80 97	65.23 137	58.75 311	80.31 321	40.90 232	86.83 289	53.29 320	64.77 300	84.31 299

FE-MVSNET3		69.05 251	67.91 242	72.46 304	75.39 351	46.24 367	85.74 146	86.80 97	65.23 137	58.75 311	80.31 321	40.90 232	86.83 289	53.29 320	64.77 300	84.31 299

MVS_111021_HR		76.39 76	75.38 92	79.42 50	85.33 78	56.47 42	88.15 62	84.97 164	65.15 139	66.06 189	89.88 124	43.79 187	92.16 65	75.03 104	80.03 100	89.64 159

dtuplus		73.09 158	72.29 156	75.52 200	76.27 332	51.82 197	82.99 265	79.98 288	65.08 140	70.11 152	87.66 196	44.38 181	85.64 333	71.56 146	72.55 218	89.11 181

miper_enhance_ethall		69.77 236	68.90 227	72.38 307	78.93 269	49.91 252	83.29 252	78.85 321	64.90 141	59.37 294	79.46 334	52.77 52	85.16 344	63.78 215	58.72 360	82.08 349

MG-MVS		78.42 33	76.99 56	82.73 3	93.17 1	64.46 1	89.93 29	88.51 58	64.83 142	73.52 81	88.09 176	48.07 94	92.19 64	62.24 230	84.53 58	91.53 74

EIA-MVS		75.92 91	75.18 95	78.13 105	85.14 81	51.60 204	87.17 95	85.32 141	64.69 143	68.56 165	90.53 104	45.79 149	91.58 78	67.21 181	82.18 74	91.20 95

plane_prior						49.57 258	87.43 84		64.57 144						72.84 213

BP-MVS1		76.09 85	75.55 85	77.71 117	79.49 250	52.27 183	84.70 199	90.49 21	64.44 145	69.86 153	90.31 112	55.05 38	91.35 85	70.07 157	75.58 174	89.53 164

FC-MVSNet-test		67.49 288	67.91 242	66.21 399	76.06 336	33.06 465	80.82 329	87.18 88	64.44 145	54.81 368	82.87 278	50.40 75	82.60 374	48.05 365	66.55 283	82.98 340

MonoMVSNet		66.80 310	64.41 320	73.96 255	76.21 333	48.07 316	76.56 379	78.26 340	64.34 147	54.32 375	74.02 396	37.21 287	86.36 309	64.85 206	53.96 409	87.45 231

WR-MVS		67.58 285	66.76 273	70.04 358	75.92 343	45.06 386	86.23 123	85.28 145	64.31 148	58.50 318	81.00 314	44.80 175	82.00 381	49.21 356	55.57 398	83.06 337

fmvsm_s_conf0.5_n_2		72.02 184	71.72 168	72.92 285	76.79 322	45.90 372	84.48 208	66.11 454	64.26 149	76.12 61	93.40 28	36.26 305	86.04 322	81.47 46	66.54 284	86.82 252

v1144		68.81 259	66.82 271	74.80 229	72.34 394	53.46 138	84.68 201	81.77 251	64.25 150	60.28 280	77.91 349	40.23 241	88.95 189	60.37 251	59.52 352	81.97 350

UWE-MVS-28		67.43 290	67.98 241	65.75 402	75.66 346	34.74 455	80.00 347	88.17 67	64.21 151	57.27 342	84.14 257	45.68 152	78.82 413	44.33 386	72.40 220	83.70 322

test1111		71.06 207	70.42 196	72.97 284	79.48 251	41.49 428	84.82 196	82.74 230	64.20 152	62.98 248	87.43 201	35.20 324	87.92 236	58.54 265	78.42 122	89.49 168

fmvsm_s_conf0.5_n		74.48 125	74.12 119	75.56 195	76.96 319	47.85 327	85.32 168	69.80 441	64.16 153	78.74 43	93.48 26	45.51 157	89.29 171	86.48 11	66.62 281	89.55 162

testdata1							77.55 372		64.14 154

fmvsm_s_conf0.1_n_2		71.45 198	71.01 183	72.78 291	75.37 352	45.82 376	84.18 218	64.59 462	64.02 155	75.67 62	93.02 41	34.99 329	85.99 325	81.18 50	66.04 293	86.52 259

test2506		72.91 161	72.43 151	74.32 244	80.12 235	44.18 396	83.19 256	84.77 175	64.02 155	65.97 190	87.43 201	47.67 103	88.72 199	59.08 258	79.66 105	90.08 147

ECVR-MVS		71.81 190	71.00 184	74.26 246	80.12 235	43.49 402	84.69 200	82.16 236	64.02 155	64.64 215	87.43 201	35.04 327	89.21 176	61.24 239	79.66 105	90.08 147

plane_prior3						48.95 280			64.01 158	62.15 260

VPA-MVSNet		71.12 204	70.66 189	72.49 302	78.75 273	44.43 391	87.64 74	90.02 23	63.97 159	65.02 206	81.58 312	42.14 215	87.42 267	63.42 219	63.38 319	85.63 278

PVSNet_0	57.04 13	61.19 368	57.24 382	73.02 282	77.45 306	50.31 244	79.43 357	77.36 359	63.96 160	47.51 429	72.45 416	25.03 419	83.78 363	52.76 331	19.22 505	84.96 290

0.4-1-1-0.2		72.79 164	71.07 181	77.94 111	80.58 219	50.83 223	89.59 36	88.63 51	63.94 161	65.74 196	81.80 307	46.05 136	90.68 114	62.98 223	60.35 344	92.31 41

V42		67.66 283	65.60 302	73.86 259	70.69 417	53.63 135	81.50 315	78.61 331	63.85 162	59.49 293	77.49 355	37.98 265	87.65 256	62.33 228	58.43 363	80.29 382

AstraMVS		70.12 225	68.56 229	74.81 228	76.48 325	47.48 337	84.35 212	82.58 233	63.80 163	62.09 262	84.54 248	31.39 374	89.96 141	68.24 176	63.58 314	87.00 242

mvs_anonymous		72.29 179	70.74 186	76.94 147	82.85 143	54.72 106	78.43 366	81.54 255	63.77 164	61.69 266	79.32 336	51.11 63	85.31 339	62.15 232	75.79 165	90.79 116

PAPR		75.20 113	74.13 118	78.41 97	88.31 34	55.10 79	84.31 214	85.66 127	63.76 165	67.55 174	90.73 101	43.48 196	89.40 167	66.36 187	77.03 139	90.73 117

0.3-1-1-0.015		72.75 165	71.06 182	77.81 113	80.58 219	50.62 227	89.45 38	88.60 55	63.74 166	65.56 198	81.82 306	46.61 123	90.64 118	62.86 224	60.35 344	92.17 45

PVSNet_Blended_VisFu		73.40 153	72.44 150	76.30 165	81.32 196	54.70 107	85.81 139	78.82 323	63.70 167	64.53 219	85.38 235	47.11 112	87.38 270	67.75 178	77.55 131	86.81 253

v148		68.24 273	66.35 281	73.88 258	71.76 400	51.47 208	84.23 216	81.90 248	63.69 168	58.94 303	76.44 374	43.72 190	87.78 250	60.63 244	55.86 395	82.39 347

UniMVSNet (Re)		67.71 282	66.80 272	70.45 349	74.44 366	42.93 411	82.42 284	84.90 169	63.69 168	59.63 288	80.99 315	47.18 110	85.23 342	51.17 344	56.75 384	83.19 334

HQP_MVS		70.96 210	69.91 209	74.12 250	77.95 292	49.57 258	85.76 142	82.59 231	63.60 170	62.15 260	83.28 275	36.04 313	88.30 224	65.46 197	72.34 221	84.49 295

plane_prior2							85.76 142		63.60 170

DU-MVS		66.84 309	65.74 298	70.16 354	73.27 382	42.59 415	81.50 315	82.92 228	63.53 172	58.51 316	82.11 301	40.75 234	84.64 353	53.11 323	55.96 393	83.24 332

fmvsm_l_conf0.5_n		75.95 90	76.16 73	75.31 209	76.01 340	48.44 300	84.98 187	71.08 431	63.50 173	81.70 22	93.52 25	50.00 77	87.18 276	87.80 6	76.87 144	90.32 133

EC-MVSNet		75.30 107	75.20 93	75.62 191	80.98 203	49.00 279	87.43 84	84.68 183	63.49 174	70.97 131	90.15 119	42.86 208	91.14 95	74.33 114	81.90 76	86.71 255

fmvsm_s_conf0.5_n_a		73.68 148	73.15 136	75.29 212	75.45 349	48.05 317	83.88 230	68.84 446	63.43 175	78.60 44	93.37 31	45.32 160	88.92 192	85.39 15	64.04 308	88.89 186

fmvsm_s_conf0.1_n		73.80 143	73.26 135	75.43 202	73.28 381	47.80 330	84.57 207	69.43 443	63.34 176	78.40 47	93.29 33	44.73 176	89.22 175	85.99 12	66.28 290	89.26 174

GA-MVS		69.04 253	66.70 275	76.06 177	75.11 356	52.36 177	83.12 260	80.23 282	63.32 177	60.65 277	79.22 338	30.98 377	88.37 217	61.25 238	66.41 285	87.46 230

CDS-MVSNet		70.48 221	69.43 214	73.64 267	77.56 302	48.83 285	83.51 241	77.45 356	63.27 178	62.33 256	85.54 232	43.85 184	83.29 371	57.38 287	74.00 195	88.79 190
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
LFMVS		78.52 30	77.14 52	82.67 4	89.58 14	58.90 10	91.27 19	88.05 70	63.22 179	74.63 69	90.83 99	41.38 227	94.40 22	75.42 101	79.90 102	94.72 2

v1192		67.96 277	65.74 298	74.63 233	71.79 399	53.43 143	84.06 223	80.99 268	63.19 180	59.56 290	77.46 356	37.50 280	88.65 201	58.20 272	58.93 359	81.79 353

fmvsm_l_conf0.5_n_a		75.88 93	76.07 75	75.31 209	76.08 335	48.34 303	85.24 170	70.62 434	63.13 181	81.45 23	93.62 24	49.98 79	87.40 269	87.76 7	76.77 146	90.20 138

0.4-1-1-0.1		72.39 173	70.70 187	77.46 125	80.45 225	50.04 249	89.09 48	88.45 60	63.06 182	64.91 211	81.60 311	45.98 140	90.46 124	62.40 227	60.34 346	91.88 58

Fast-Effi-MVS+		72.73 166	71.15 179	77.48 123	82.75 146	54.76 102	86.77 112	80.64 273	63.05 183	65.93 191	84.01 258	44.42 180	89.03 182	56.45 297	76.36 154	88.64 194

MAR-MVS		76.76 67	75.60 84	80.21 35	90.87 8	54.68 109	89.14 47	89.11 35	62.95 184	70.54 145	92.33 58	41.05 228	94.95 18	57.89 279	86.55 33	91.00 107
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
SteuartSystems-ACMMP		77.08 58	76.33 69	79.34 51	80.98 203	55.31 67	89.76 33	86.91 94	62.94 185	71.65 113	91.56 81	42.33 211	92.56 54	77.14 86	83.69 63	90.15 141
Skip Steuart: Steuart Systems R&D Blog.
icg_test_0407_2		71.26 201	69.99 207	75.09 219	82.26 157	50.87 217	79.65 351	85.16 152	62.91 186	63.68 238	86.07 221	35.56 319	84.32 356	64.03 211	70.55 244	90.09 143

IMVS_0407		71.97 186	70.10 205	77.57 120	82.26 157	50.87 217	80.69 333	85.16 152	62.91 186	63.68 238	86.07 221	35.56 319	91.75 74	64.03 211	70.55 244	90.09 143

IMVS_0404		69.11 249	67.25 265	74.68 232	82.26 157	50.87 217	76.74 376	85.16 152	62.91 186	50.76 410	86.07 221	26.76 403	83.06 373	64.03 211	70.55 244	90.09 143

IMVS_0403		72.39 173	70.59 191	77.79 114	82.26 157	50.87 217	81.76 300	85.16 152	62.91 186	64.87 212	86.07 221	37.71 273	92.40 58	64.03 211	70.55 244	90.09 143

v144192		67.86 278	65.76 297	74.16 248	71.68 401	53.09 156	84.14 220	80.83 270	62.85 190	59.21 299	77.28 360	39.30 253	88.00 235	58.67 264	57.88 376	81.40 364

test_fmvsmvis_n_1920		71.29 200	70.38 197	74.00 254	71.04 411	48.79 287	79.19 359	64.62 460	62.75 191	66.73 178	91.99 67	40.94 230	88.35 219	83.00 31	73.18 208	84.85 293

nrg030		72.27 181	71.56 170	74.42 238	75.93 342	50.60 229	86.97 99	83.21 220	62.75 191	67.15 177	84.38 252	50.07 76	86.66 298	71.19 148	62.37 332	85.99 269

guyue		70.53 219	69.12 222	74.76 230	77.61 297	47.53 335	84.86 194	85.17 150	62.70 193	62.18 258	83.74 264	34.72 331	89.86 144	64.69 207	66.38 286	86.87 245

miper_ehance_all_eth		68.70 264	67.58 254	72.08 315	76.91 321	49.48 267	82.47 282	78.45 336	62.68 194	58.28 324	77.88 350	50.90 66	85.01 347	61.91 233	58.72 360	81.75 354

XXY-MVS		70.18 223	69.28 220	72.89 288	77.64 296	42.88 412	85.06 181	87.50 83	62.58 195	62.66 254	82.34 298	43.64 192	89.83 147	58.42 268	63.70 313	85.96 271

thisisatest0515		73.64 149	72.20 158	77.97 108	81.63 181	53.01 159	86.69 114	88.81 45	62.53 196	64.06 227	85.65 229	52.15 57	92.50 55	58.43 266	69.84 252	88.39 208

fmvsm_s_conf0.1_n_a		72.82 163	72.05 164	75.12 218	70.95 412	47.97 320	82.72 271	68.43 448	62.52 197	78.17 48	93.08 39	44.21 182	88.86 194	84.82 17	63.54 315	88.54 202

cl22		68.85 256	67.69 252	72.35 308	78.07 290	49.98 251	82.45 283	78.48 335	62.50 198	58.46 320	77.95 348	49.99 78	85.17 343	62.55 226	58.72 360	81.90 352

v1921920		67.45 289	65.23 311	74.10 251	71.51 404	52.90 162	83.75 234	80.44 278	62.48 199	59.12 300	77.13 361	36.98 292	87.90 238	57.53 284	58.14 370	81.49 359

GDP-MVS		75.27 109	74.38 115	77.95 110	79.04 265	52.86 165	85.22 171	86.19 115	62.43 200	70.66 142	90.40 110	53.51 47	91.60 77	69.25 164	72.68 216	89.39 171

thres200		68.71 262	67.27 264	73.02 282	84.73 87	46.76 351	85.03 184	87.73 77	62.34 201	59.87 283	83.45 271	43.15 202	88.32 222	31.25 449	67.91 272	83.98 310

Effi-MVS+-dtu		66.24 320	64.96 316	70.08 356	75.17 355	49.64 257	82.01 292	74.48 393	62.15 202	57.83 327	76.08 382	30.59 379	83.79 362	65.40 201	60.93 341	76.81 420

TAMVS		69.51 245	68.16 239	73.56 271	76.30 330	48.71 291	82.57 276	77.17 361	62.10 203	61.32 270	84.23 255	41.90 220	83.46 368	54.80 312	73.09 211	88.50 205

VortexMVS		68.49 266	66.84 270	73.46 273	81.10 202	48.75 288	84.63 204	84.73 177	62.05 204	57.22 344	77.08 364	34.54 337	89.20 177	63.08 220	57.12 382	82.43 346

eth_miper_zixun_eth		66.98 306	65.28 309	72.06 316	75.61 347	50.40 236	81.00 324	76.97 367	62.00 205	56.99 346	76.97 365	44.84 172	85.58 334	58.75 263	54.42 406	80.21 383

c3_l		67.97 276	66.66 276	71.91 326	76.20 334	49.31 272	82.13 290	78.00 344	61.99 206	57.64 333	76.94 366	49.41 85	84.93 348	60.62 245	57.01 383	81.49 359

v1240		66.99 305	64.68 317	73.93 256	71.38 408	52.66 170	83.39 249	79.98 288	61.97 207	58.44 322	77.11 362	35.25 323	87.81 243	56.46 296	58.15 368	81.33 367

OPM-MVS		70.75 214	69.58 213	74.26 246	75.55 348	51.34 211	86.05 130	83.29 219	61.94 208	62.95 250	85.77 228	34.15 340	88.44 215	65.44 200	71.07 237	82.99 338
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test_prior2							89.04 49		61.88 209	73.55 80	91.46 84	48.01 98		74.73 106	85.46 45

EPNet_dtu		66.25 319	66.71 274	64.87 411	78.66 278	34.12 460	82.80 270	75.51 382	61.75 210	64.47 223	86.90 209	37.06 291	72.46 461	43.65 391	69.63 256	88.02 217
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPMVS		68.45 267	65.44 306	77.47 124	84.91 85	56.17 48	71.89 425	81.91 247	61.72 211	60.85 274	72.49 414	36.21 306	87.06 280	47.32 369	71.62 229	89.17 179

RRT-MVS		73.29 154	71.37 175	79.07 61	84.63 90	54.16 126	78.16 367	86.64 105	61.67 212	60.17 281	82.35 297	40.63 238	92.26 63	70.19 155	77.87 128	90.81 114

PMMVS		72.98 159	72.05 164	75.78 186	83.57 114	48.60 292	84.08 221	82.85 229	61.62 213	68.24 168	90.33 111	28.35 390	87.78 250	72.71 134	76.69 149	90.95 110

save fliter					85.35 77	56.34 45	89.31 43	81.46 256	61.55 214

UA-Net		67.32 296	66.23 285	70.59 347	78.85 271	41.23 431	73.60 403	75.45 384	61.54 215	66.61 182	84.53 251	38.73 259	86.57 303	42.48 399	74.24 192	83.98 310

v8		67.25 297	64.99 315	74.04 252	72.89 388	53.31 148	82.37 285	80.11 286	61.54 215	54.29 376	76.02 383	42.89 207	88.41 216	58.43 266	56.36 385	80.39 381

SMA-MVS		79.10 27	78.76 29	80.12 41	84.42 94	55.87 54	87.58 83	86.76 100	61.48 217	80.26 33	93.10 36	46.53 125	92.41 57	79.97 60	88.77 11	92.08 47
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
WB-MVSnew		69.36 247	68.24 237	72.72 293	79.26 257	49.40 270	85.72 149	88.85 43	61.33 218	64.59 218	82.38 294	34.57 335	87.53 263	46.82 374	70.63 241	81.22 371

DIV-MVS_self_test		67.43 290	65.93 293	71.94 324	76.33 328	48.01 319	82.57 276	79.11 317	61.31 219	56.73 348	76.92 367	46.09 135	86.43 307	57.98 275	56.31 387	81.39 365

cl____		67.43 290	65.93 293	71.95 323	76.33 328	48.02 318	82.58 275	79.12 316	61.30 220	56.72 349	76.92 367	46.12 132	86.44 306	57.98 275	56.31 387	81.38 366

MP-MVS-pluss		75.54 106	75.03 100	77.04 140	81.37 194	52.65 171	84.34 213	84.46 188	61.16 221	69.14 159	91.76 73	39.98 247	88.99 186	78.19 74	84.89 55	89.48 169
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mvsmamba		69.38 246	67.52 258	74.95 225	82.86 142	52.22 184	67.36 445	76.75 368	61.14 222	49.43 414	82.04 303	37.26 285	84.14 357	73.93 119	76.91 142	88.50 205

v10		66.61 312	64.20 324	73.83 261	72.59 391	53.37 144	81.88 296	79.91 293	61.11 223	54.09 378	75.60 385	40.06 245	88.26 227	56.47 295	56.10 391	79.86 387

ACMMP_NAP		76.43 75	75.66 83	78.73 70	81.92 168	54.67 110	84.06 223	85.35 139	61.10 224	72.99 90	91.50 82	40.25 240	91.00 101	76.84 88	86.98 26	90.51 127

EI-MVSNet		69.70 241	68.70 228	72.68 296	75.00 359	48.90 283	79.54 353	87.16 89	61.05 225	63.88 232	83.74 264	45.87 146	90.44 125	57.42 286	64.68 305	78.70 395

IterMVS-LS		66.63 311	65.36 308	70.42 350	75.10 357	48.90 283	81.45 318	76.69 372	61.05 225	55.71 359	77.10 363	45.86 147	83.65 365	57.44 285	57.88 376	78.70 395
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CL-MVSNet_self_test		62.98 352	61.14 354	68.50 379	65.86 453	42.96 410	84.37 210	82.98 226	60.98 227	53.95 379	72.70 413	40.43 239	83.71 364	41.10 402	47.93 439	78.83 394

AUN-MVS		68.20 274	66.35 281	73.76 263	76.37 326	47.45 339	79.52 355	79.52 304	60.98 227	62.34 255	86.02 225	36.59 302	86.94 285	62.32 229	53.47 415	86.89 244

Syy-MVS		61.51 366	61.35 351	62.00 431	81.73 173	30.09 479	80.97 325	81.02 264	60.93 229	55.06 364	82.64 286	35.09 326	80.81 390	16.40 498	58.32 364	75.10 438

myMVS_eth3d		63.52 346	63.56 328	63.40 422	81.73 173	34.28 457	80.97 325	81.02 264	60.93 229	55.06 364	82.64 286	48.00 100	80.81 390	23.42 481	58.32 364	75.10 438

FMVSNet3		68.84 257	67.40 260	73.19 281	85.05 82	48.53 295	85.71 150	85.36 138	60.90 231	57.58 334	79.15 339	42.16 214	86.77 293	47.25 370	63.40 316	84.27 301

tfpn200view9		67.57 286	66.13 287	71.89 327	84.05 106	45.07 383	83.40 247	87.71 79	60.79 232	57.79 329	82.76 281	43.53 193	87.80 246	28.80 457	66.36 287	82.78 344

thres400		67.40 294	66.13 287	71.19 338	84.05 106	45.07 383	83.40 247	87.71 79	60.79 232	57.79 329	82.76 281	43.53 193	87.80 246	28.80 457	66.36 287	80.71 377

LCM-MVSNet-Re		58.82 386	56.54 386	65.68 403	79.31 256	29.09 488	61.39 468	45.79 489	60.73 234	37.65 472	72.47 415	31.42 373	81.08 386	49.66 351	70.41 248	86.87 245

Effi-MVS+		75.24 111	73.61 131	80.16 38	81.92 168	57.42 24	85.21 172	76.71 371	60.68 235	73.32 84	89.34 135	47.30 109	91.63 76	68.28 174	79.72 104	91.42 79

D2MVS		63.49 347	61.39 349	69.77 360	69.29 434	48.93 282	78.89 362	77.71 352	60.64 236	49.70 413	72.10 428	27.08 401	83.48 367	54.48 313	62.65 329	76.90 418

IterMVS		63.77 344	61.67 345	70.08 356	72.68 390	51.24 214	80.44 336	75.51 382	60.51 237	51.41 397	73.70 402	32.08 364	78.91 411	54.30 314	54.35 407	80.08 385
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dp		64.41 335	61.58 346	72.90 286	82.40 154	54.09 127	72.53 413	76.59 374	60.39 238	55.68 360	70.39 437	35.18 325	76.90 436	39.34 407	61.71 335	87.73 223

MVP-Stereo		70.97 209	70.44 193	72.59 299	76.03 338	51.36 210	85.02 186	86.99 93	60.31 239	56.53 353	78.92 341	40.11 244	90.00 139	60.00 254	90.01 7	76.41 427
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
balanced_ft_v1		75.25 110	73.90 125	79.29 52	85.59 71	56.72 36	74.35 398	87.27 85	60.24 240	59.07 301	85.17 237	47.76 101	90.51 122	82.62 36	83.06 66	90.64 120

tpm2		70.82 212	68.44 233	77.98 107	80.78 212	56.11 49	74.21 399	81.28 261	60.24 240	68.04 171	75.27 387	52.26 56	88.50 212	55.82 303	68.03 270	89.33 173

CR-MVSNet		62.47 360	59.04 373	72.77 292	73.97 376	56.57 38	60.52 469	71.72 423	60.04 242	57.49 337	65.86 454	38.94 256	80.31 399	42.86 396	59.93 348	81.42 362

ab-mvs		70.65 217	69.11 223	75.29 212	80.87 209	46.23 369	73.48 405	85.24 148	59.99 243	66.65 180	80.94 316	43.13 204	88.69 200	63.58 218	68.07 269	90.95 110

9.14			78.19 33		85.67 69		88.32 59	88.84 44	59.89 244	74.58 71	92.62 52	46.80 118	92.66 49	81.40 49	85.62 44

GeoE		69.96 233	67.88 246	76.22 170	81.11 201	51.71 202	84.15 219	76.74 370	59.83 245	60.91 273	84.38 252	41.56 225	88.10 231	51.67 340	70.57 243	88.84 188

KinetiMVS		71.15 202	69.25 221	76.82 150	77.99 291	50.49 232	85.05 182	86.51 106	59.78 246	64.10 226	85.34 236	32.16 362	91.33 87	58.82 262	73.54 204	88.64 194

BH-w/o		70.02 230	68.51 232	74.56 234	82.77 145	50.39 237	86.60 117	78.14 342	59.77 247	59.65 287	85.57 231	39.27 254	87.30 272	49.86 350	74.94 187	85.99 269

ZNCC-MVS		75.82 97	75.02 101	78.23 102	83.88 111	53.80 130	86.91 105	86.05 118	59.71 248	67.85 173	90.55 103	42.23 213	91.02 99	72.66 136	85.29 49	89.87 154

1112_ss		70.05 229	69.37 216	72.10 314	80.77 213	42.78 413	85.12 180	76.75 368	59.69 249	61.19 271	92.12 61	47.48 107	83.84 361	53.04 325	68.21 268	89.66 158

miper_lstm_enhance		63.91 341	62.30 336	68.75 373	75.06 358	46.78 350	69.02 436	81.14 262	59.68 250	52.76 387	72.39 417	40.71 236	77.99 423	56.81 290	53.09 417	81.48 361

Baseline_NR-MVSNet		65.49 329	64.27 323	69.13 366	74.37 369	41.65 425	83.39 249	78.85 321	59.56 251	59.62 289	76.88 369	40.75 234	87.44 266	49.99 348	55.05 400	78.28 404

Fast-Effi-MVS+-dtu		66.53 314	64.10 325	73.84 260	72.41 393	52.30 182	84.73 198	75.66 380	59.51 252	56.34 355	79.11 340	28.11 392	85.85 331	57.74 283	63.29 320	83.35 328

UGNet		68.71 262	67.11 267	73.50 272	80.55 221	47.61 334	84.08 221	78.51 334	59.45 253	65.68 197	82.73 284	23.78 428	85.08 346	52.80 328	76.40 150	87.80 221
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
1314		71.11 205	69.41 215	76.22 170	79.32 255	50.49 232	80.23 341	85.14 158	59.44 254	58.93 304	88.89 144	33.83 345	89.60 159	61.49 237	77.42 135	88.57 199

MTAPA		72.73 166	71.22 177	77.27 133	81.54 188	53.57 136	67.06 447	81.31 259	59.41 255	68.39 166	90.96 92	36.07 312	89.01 183	73.80 123	82.45 72	89.23 176

thres600view7		66.46 315	65.12 313	70.47 348	83.41 118	43.80 400	82.15 288	87.78 74	59.37 256	56.02 357	82.21 299	43.73 188	86.90 287	26.51 469	64.94 299	80.71 377

sss		70.49 220	70.13 204	71.58 332	81.59 185	39.02 440	80.78 330	84.71 182	59.34 257	66.61 182	88.09 176	37.17 288	85.52 335	61.82 235	71.02 238	90.20 138

Vis-MVSNet (Re-imp)		65.52 327	65.63 300	65.17 409	77.49 305	30.54 475	75.49 387	77.73 351	59.34 257	52.26 392	86.69 213	49.38 86	80.53 397	37.07 416	75.28 177	84.42 297

MVS_111021_LR		69.07 250	67.91 242	72.54 300	77.27 311	49.56 261	79.77 349	73.96 400	59.33 259	60.73 276	87.82 187	30.19 382	81.53 382	69.94 158	72.19 224	86.53 258

PS-MVSNAJss		68.78 261	67.17 266	73.62 269	73.01 385	48.33 305	84.95 190	84.81 172	59.30 260	58.91 306	79.84 329	37.77 268	88.86 194	62.83 225	63.12 325	83.67 324

GST-MVS		74.87 121	73.90 125	77.77 115	83.30 123	53.45 140	85.75 144	85.29 144	59.22 261	66.50 185	89.85 125	40.94 230	90.76 111	70.94 150	83.35 64	89.10 182

MDTV_nov1_ep13			61.56 347		81.68 177	55.12 77	72.41 415	78.18 341	59.19 262	58.85 308	69.29 442	34.69 333	86.16 314	36.76 421	62.96 326

CSCG		80.41 16	79.72 18	82.49 6	89.12 26	57.67 18	89.29 46	91.54 6	59.19 262	71.82 111	90.05 121	59.72 12	96.04 11	78.37 72	88.40 14	93.75 8

test-LLR		69.65 242	69.01 226	71.60 330	78.67 275	48.17 311	85.13 176	79.72 297	59.18 264	63.13 246	82.58 288	36.91 294	80.24 400	60.56 246	75.17 179	86.39 263

test0.0.03 1		62.54 357	62.44 335	62.86 427	72.28 397	29.51 485	82.93 266	78.78 324	59.18 264	53.07 386	82.41 292	36.91 294	77.39 430	37.45 412	58.96 358	81.66 357

MIMVSNet		63.12 351	60.29 363	71.61 329	75.92 343	46.65 353	65.15 450	81.94 244	59.14 266	54.65 371	69.47 440	25.74 412	80.63 394	41.03 403	69.56 257	87.55 228

IS-MVSNet		68.80 260	67.55 256	72.54 300	78.50 283	43.43 404	81.03 323	79.35 312	59.12 267	57.27 342	86.71 212	46.05 136	87.70 254	44.32 388	75.60 173	86.49 260

thres100view900		66.87 308	65.42 307	71.24 336	83.29 124	43.15 409	81.67 306	87.78 74	59.04 268	55.92 358	82.18 300	43.73 188	87.80 246	28.80 457	66.36 287	82.78 344

3Dnovator+	62.71 7	72.29 179	70.50 192	77.65 119	83.40 121	51.29 213	87.32 88	86.40 110	59.01 269	58.49 319	88.32 165	32.40 359	91.27 88	57.04 288	82.15 75	90.38 130

UnsupCasMVSNet_eth		57.56 397	55.15 397	64.79 412	64.57 463	33.12 464	73.17 408	83.87 205	58.98 270	41.75 456	70.03 438	22.54 436	79.92 404	46.12 379	35.31 478	81.32 369

BH-RMVSNet		70.08 228	68.01 240	76.27 167	84.21 104	51.22 215	87.29 91	79.33 314	58.96 271	63.63 241	86.77 211	33.29 349	90.30 132	44.63 385	73.96 196	87.30 235

PatchmatchNet		67.07 304	63.63 327	77.40 127	83.10 128	58.03 14	72.11 423	77.77 350	58.85 272	59.37 294	70.83 433	37.84 267	84.93 348	42.96 395	69.83 253	89.26 174
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_vis1_n_1920		68.59 265	68.31 235	69.44 364	69.16 435	41.51 427	84.63 204	68.58 447	58.80 273	73.26 85	88.37 159	25.30 415	80.60 395	79.10 64	67.55 274	86.23 265

SF-MVS		77.64 48	77.42 46	78.32 101	83.75 113	52.47 174	86.63 116	87.80 73	58.78 274	74.63 69	92.38 57	47.75 102	91.35 85	78.18 76	86.85 28	91.15 98

Vis-MVSNet		70.61 218	69.34 217	74.42 238	80.95 208	48.49 297	86.03 131	77.51 355	58.74 275	65.55 199	87.78 188	34.37 338	85.95 329	52.53 335	80.61 88	88.80 189
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MVS		76.91 60	75.48 87	81.23 22	84.56 92	55.21 72	80.23 341	91.64 5	58.65 276	65.37 200	91.48 83	45.72 150	95.05 17	72.11 145	89.52 10	93.44 11

CDPH-MVS		76.05 87	75.19 94	78.62 80	86.51 56	54.98 85	87.32 88	84.59 185	58.62 277	70.75 139	90.85 98	43.10 205	90.63 119	70.50 153	84.51 59	90.24 135

GBi-Net		67.09 302	65.47 304	71.96 320	82.71 147	46.36 360	83.52 237	83.30 216	58.55 278	57.58 334	76.23 378	36.72 299	86.20 311	47.25 370	63.40 316	83.32 329

test1		67.09 302	65.47 304	71.96 320	82.71 147	46.36 360	83.52 237	83.30 216	58.55 278	57.58 334	76.23 378	36.72 299	86.20 311	47.25 370	63.40 316	83.32 329

FMVSNet2		67.57 286	65.79 296	72.90 286	82.71 147	47.97 320	85.15 175	84.93 168	58.55 278	56.71 350	78.26 347	36.72 299	86.67 297	46.15 378	62.94 327	84.07 305

HyFIR lowres test		69.94 234	67.58 254	77.04 140	77.11 317	57.29 25	81.49 317	79.11 317	58.27 281	58.86 307	80.41 320	42.33 211	86.96 283	61.91 233	68.68 266	86.87 245

MSLP-MVS++		74.21 133	72.25 157	80.11 42	81.45 192	56.47 42	86.32 121	79.65 302	58.19 282	66.36 186	92.29 59	36.11 310	90.66 116	67.39 179	82.49 71	93.18 19

PHI-MVS		77.49 50	77.00 55	78.95 62	85.33 78	50.69 226	88.57 57	88.59 56	58.14 283	73.60 79	93.31 32	43.14 203	93.79 31	73.81 122	88.53 13	92.37 38

XVS		72.92 160	71.62 169	76.81 151	83.41 118	52.48 172	84.88 192	83.20 221	58.03 284	63.91 230	89.63 130	35.50 321	89.78 148	65.50 194	80.50 90	88.16 211

X-MVStestdata		65.85 324	62.20 339	76.81 151	83.41 118	52.48 172	84.88 192	83.20 221	58.03 284	63.91 230	4.82 534	35.50 321	89.78 148	65.50 194	80.50 90	88.16 211

DVP-MVS++		82.44 3	82.38 6	82.62 5	91.77 4	57.49 20	84.98 187	88.88 40	58.00 286	83.60 7	93.39 29	67.21 2	96.39 4	81.64 44	91.98 4	93.98 6

test_0728_THIRD									58.00 286	81.91 17	93.64 22	56.54 27	96.44 2	81.64 44	86.86 27	92.23 42

test_yl		75.85 94	74.83 106	78.91 63	88.08 40	51.94 190	91.30 17	89.28 32	57.91 288	71.19 125	89.20 138	42.03 218	92.77 45	69.41 161	75.07 183	92.01 52

DCV-MVSNet		75.85 94	74.83 106	78.91 63	88.08 40	51.94 190	91.30 17	89.28 32	57.91 288	71.19 125	89.20 138	42.03 218	92.77 45	69.41 161	75.07 183	92.01 52

MP-MVS		74.99 117	74.33 116	76.95 146	82.89 141	53.05 158	85.63 154	83.50 214	57.86 290	67.25 176	90.24 113	43.38 199	88.85 197	76.03 92	82.23 73	88.96 184
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
train_agg		76.91 60	76.40 68	78.45 95	85.68 67	55.42 61	87.59 80	84.00 201	57.84 291	72.99 90	90.98 90	44.99 166	88.58 205	78.19 74	85.32 48	91.34 86

test_8					85.72 66	55.31 67	87.60 79	83.88 204	57.84 291	72.84 94	90.99 89	44.99 166	88.34 220

TEST9					85.68 67	55.42 61	87.59 80	84.00 201	57.72 293	72.99 90	90.98 90	44.87 171	88.58 205

DVP-MVS		81.30 10	81.00 13	82.20 9	89.40 21	57.45 22	92.34 5	89.99 24	57.71 294	81.91 17	93.64 22	55.17 35	96.44 2	81.68 42	87.13 22	92.72 31
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
test0726					89.40 21	57.45 22	92.32 7	88.63 51	57.71 294	83.14 10	93.96 12	55.17 35

BH-untuned		68.28 271	66.40 280	73.91 257	81.62 182	50.01 250	85.56 157	77.39 357	57.63 296	57.47 339	83.69 267	36.36 304	87.08 279	44.81 383	73.08 212	84.65 294

thisisatest0530		70.47 222	68.56 229	76.20 172	79.78 244	51.52 207	83.49 243	88.58 57	57.62 297	58.60 315	82.79 280	51.03 65	91.48 81	52.84 327	62.36 333	85.59 280

test_241102_ONE					89.48 18	56.89 32		88.94 38	57.53 298	84.61 5	93.29 33	58.81 15	96.45 1

API-MVS		74.17 134	72.07 163	80.49 28	90.02 12	58.55 12	87.30 90	84.27 192	57.51 299	65.77 195	87.77 189	41.61 224	95.97 12	51.71 339	82.63 69	86.94 243

SED-MVS		81.92 8	81.75 9	82.44 8	89.48 18	56.89 32	92.48 3	88.94 38	57.50 300	84.61 5	94.09 9	58.81 15	96.37 7	82.28 38	87.60 19	94.06 4

test_241102_TWO								88.76 47	57.50 300	83.60 7	94.09 9	56.14 31	96.37 7	82.28 38	87.43 21	92.55 34

aaatest				80.14 40	84.34 97	54.93 88	87.61 75	87.22 86	57.43 302	81.85 19	92.88 46		93.75 32	80.19 56	85.13 51	91.76 64

Patchmatch-RL test		58.72 388	54.32 402	71.92 325	63.91 466	44.25 394	61.73 465	55.19 480	57.38 303	49.31 416	54.24 487	37.60 276	80.89 387	62.19 231	47.28 444	90.63 121

Test_1112_low_res		67.18 299	66.23 285	70.02 359	78.75 273	41.02 432	83.43 245	73.69 403	57.29 304	58.45 321	82.39 293	45.30 161	80.88 388	50.50 346	66.26 291	88.16 211

FA-MVS(test-final)		69.00 255	66.60 278	76.19 173	83.48 117	47.96 322	74.73 392	82.07 242	57.27 305	62.18 258	78.47 345	36.09 311	92.89 41	53.76 319	71.32 236	87.73 223

dtuonly		62.58 356	61.91 344	64.58 413	66.49 449	44.72 387	75.64 381	65.78 456	57.26 306	55.48 363	83.93 260	30.08 383	67.36 474	56.40 299	66.10 292	81.67 356

OpenMVS	61.00 11	69.99 232	67.55 256	77.30 131	78.37 286	54.07 128	84.36 211	85.76 124	57.22 307	56.71 350	87.67 195	30.79 378	92.83 43	43.04 394	84.06 62	85.01 288

test_one_0601					89.39 23	57.29 25		88.09 69	57.21 308	82.06 15	93.39 29	54.94 40

TR-MVS		69.71 237	67.85 250	75.27 215	82.94 138	48.48 298	87.40 87	80.86 269	57.15 309	64.61 217	87.08 207	32.67 357	89.64 158	46.38 376	71.55 231	87.68 225

ZD-MVS					89.55 15	53.46 138		84.38 189	57.02 310	73.97 76	91.03 88	44.57 178	91.17 93	75.41 102	81.78 79

TransMVSNet (Re)		62.82 354	60.76 357	69.02 367	73.98 375	41.61 426	86.36 119	79.30 315	56.90 311	52.53 388	76.44 374	41.85 221	87.60 260	38.83 409	40.61 466	77.86 409

wanda-best-256-512		64.87 330	62.23 337	72.81 289	70.49 419	46.85 348	85.71 150	85.71 125	56.85 312	51.25 399	72.31 420	36.16 307	87.84 240	52.67 333	48.90 429	83.73 317

FE-blended-shiyan7		64.87 330	62.23 337	72.81 289	70.49 419	46.85 348	85.71 150	85.71 125	56.85 312	51.25 399	72.31 420	36.16 307	87.84 240	52.67 333	48.90 429	83.73 317

USDC		54.36 413	51.23 419	63.76 417	64.29 465	37.71 448	62.84 462	73.48 409	56.85 312	35.47 478	71.94 429	9.23 488	78.43 414	38.43 410	48.57 434	75.13 437

region2R		73.75 145	72.55 148	77.33 128	83.90 110	52.98 160	85.54 159	84.09 199	56.83 315	65.10 204	90.45 106	37.34 283	90.24 133	68.89 168	80.83 85	88.77 191

HFP-MVS		74.37 129	73.13 140	78.10 106	84.30 100	53.68 134	85.58 155	84.36 190	56.82 316	65.78 194	90.56 102	40.70 237	90.90 107	69.18 166	80.88 83	89.71 156

ACMMPR		73.76 144	72.61 146	77.24 136	83.92 109	52.96 161	85.58 155	84.29 191	56.82 316	65.12 203	90.45 106	37.24 286	90.18 135	69.18 166	80.84 84	88.58 198

SD-MVS		76.18 82	74.85 105	80.18 37	85.39 76	56.90 31	85.75 144	82.45 235	56.79 318	74.48 72	91.81 72	43.72 190	90.75 112	74.61 107	78.65 118	92.91 24
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
SCA		63.84 342	60.01 366	75.32 208	78.58 280	57.92 15	61.61 466	77.53 354	56.71 319	57.75 331	70.77 434	31.97 365	79.91 406	48.80 358	56.36 385	88.13 214

cascas		69.01 254	66.13 287	77.66 118	79.36 253	55.41 63	86.99 98	83.75 206	56.69 320	58.92 305	81.35 313	24.31 426	92.10 68	53.23 322	70.61 242	85.46 281

ACMMP		70.81 213	69.29 219	75.39 206	81.52 190	51.92 192	83.43 245	83.03 225	56.67 321	58.80 309	88.91 143	31.92 367	88.58 205	65.89 193	73.39 206	85.67 276
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
aaEdge-Enhanced		79.48 24	79.20 24	80.35 33	88.96 27	54.93 88	88.65 55	88.50 59	56.62 322	79.87 36	92.88 46	51.96 58	94.36 23	80.19 56	85.13 51	91.76 64

QAPM		71.88 189	69.33 218	79.52 48	82.20 163	54.30 119	86.30 122	88.77 46	56.61 323	59.72 286	87.48 199	33.90 343	95.36 14	47.48 368	81.49 80	88.90 185

blended_shiyan6		64.70 332	62.04 341	72.69 294	70.34 422	46.60 356	85.48 161	85.65 129	56.59 324	50.91 407	72.18 424	35.82 316	87.81 243	52.46 337	48.90 429	83.66 325

blended_shiyan8		64.70 332	62.04 341	72.69 294	70.33 423	46.62 354	85.48 161	85.66 127	56.58 325	50.94 406	72.18 424	35.81 317	87.80 246	52.47 336	48.91 428	83.65 326

TSAR-MVS + GP.		77.82 44	77.59 42	78.49 91	85.25 80	50.27 246	90.02 26	90.57 20	56.58 325	74.26 74	91.60 80	54.26 42	92.16 65	75.87 95	79.91 101	93.05 22

PGM-MVS		72.60 168	71.20 178	76.80 153	82.95 137	52.82 166	83.07 262	82.14 237	56.51 327	63.18 245	89.81 126	35.68 318	89.76 150	67.30 180	80.19 96	87.83 220

PCF-MVS	61.03 10	70.10 227	68.40 234	75.22 217	77.15 316	51.99 188	79.30 358	82.12 238	56.47 328	61.88 265	86.48 218	43.98 183	87.24 275	55.37 308	72.79 214	86.43 262
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
blend_shiyan4		67.33 295	65.28 309	73.45 274	70.71 414	47.96 322	86.21 124	85.65 129	56.45 329	52.18 393	72.99 409	45.89 145	88.50 212	56.81 290	60.68 342	83.90 314

DP-MVS Recon		71.99 185	70.31 199	77.01 142	90.65 9	53.44 141	89.37 40	82.97 227	56.33 330	63.56 243	89.47 132	34.02 341	92.15 67	54.05 316	72.41 219	85.43 282

EPP-MVSNet		71.14 203	70.07 206	74.33 243	79.18 261	46.52 357	83.81 232	86.49 107	56.32 331	57.95 325	84.90 246	54.23 43	89.14 178	58.14 273	69.65 255	87.33 233

TestfortrainingZip				83.28 1	90.91 7	58.80 11	87.61 75	91.34 11	56.28 332	88.36 1	95.55 1	65.41 5	96.39 4		88.20 15	94.63 3

MED-MVS		79.56 23	79.39 21	80.06 44	84.34 97	54.93 88	87.61 75	87.22 86	56.22 333	81.85 19	92.98 43	58.11 21	93.75 32	80.19 56	85.96 38	91.52 75

TestfortrainingZip a		77.64 48	76.79 62	80.20 36	84.34 97	54.79 101	87.61 75	87.03 91	56.22 333	78.78 42	92.98 43	50.45 73	94.28 24	74.37 112	79.31 110	91.52 75

RA-MVS			77.36 47		87.50 47	52.47 174	89.69 35	86.81 96	56.21 335	77.72 50	93.76 18	43.52 195	91.51 80	80.53 54	80.50 90

FE-MVSNET2		58.78 387	56.44 388	65.82 401	63.57 469	38.92 441	79.59 352	81.75 253	56.14 336	43.06 450	68.15 446	25.22 417	80.64 393	42.29 400	48.16 436	77.91 408

HPM-MVS		72.60 168	71.50 171	75.89 183	82.02 164	51.42 209	80.70 332	83.05 224	56.12 337	64.03 228	89.53 131	37.55 277	88.37 217	70.48 154	80.04 99	87.88 219
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
APDe-MVS		78.44 32	78.20 32	79.19 54	88.56 28	54.55 114	89.76 33	87.77 76	55.91 338	78.56 45	92.49 55	48.20 93	92.65 50	79.49 61	83.04 67	90.39 129
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
xiu_mvs_v1_base_debu		71.60 195	70.29 200	75.55 196	77.26 312	53.15 152	85.34 164	79.37 308	55.83 339	72.54 96	90.19 116	22.38 437	86.66 298	73.28 130	76.39 151	86.85 248

xiu_mvs_v1_base		71.60 195	70.29 200	75.55 196	77.26 312	53.15 152	85.34 164	79.37 308	55.83 339	72.54 96	90.19 116	22.38 437	86.66 298	73.28 130	76.39 151	86.85 248

xiu_mvs_v1_base_debi		71.60 195	70.29 200	75.55 196	77.26 312	53.15 152	85.34 164	79.37 308	55.83 339	72.54 96	90.19 116	22.38 437	86.66 298	73.28 130	76.39 151	86.85 248

mPP-MVS		71.79 192	70.38 197	76.04 178	82.65 150	52.06 185	84.45 209	81.78 250	55.59 342	62.05 263	89.68 128	33.48 347	88.28 226	65.45 199	78.24 124	87.77 222

DPE-MVS		79.82 21	79.66 19	80.29 34	89.27 25	55.08 80	88.70 54	87.92 72	55.55 343	81.21 25	93.69 21	56.51 28	94.27 26	78.36 73	85.70 43	91.51 77
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
pm-mvs1		64.12 339	62.56 334	68.78 372	71.68 401	38.87 442	82.89 268	81.57 254	55.54 344	53.89 380	77.82 351	37.73 271	86.74 294	48.46 363	53.49 414	80.72 376

mamba_0408		66.33 317	62.87 329	76.70 157	80.45 225	51.81 198	46.11 490	78.90 319	55.46 345	63.82 234	84.54 248	31.91 368	91.03 97	55.68 304	68.97 261	87.25 236

SSM_04072		64.04 340	62.87 329	67.56 384	80.45 225	51.81 198	46.11 490	78.90 319	55.46 345	63.82 234	84.54 248	31.91 368	63.62 477	55.68 304	68.97 261	87.25 236

ACMP	61.11 9	66.24 320	64.33 322	72.00 319	74.89 361	49.12 274	83.18 257	79.83 294	55.41 347	52.29 390	82.68 285	25.83 411	86.10 317	60.89 241	63.94 311	80.78 375
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_cas_vis1_n_1920		67.10 301	66.60 278	68.59 377	65.17 458	43.23 408	83.23 255	69.84 440	55.34 348	70.67 141	87.71 194	24.70 423	76.66 438	78.57 71	64.20 307	85.89 273

gbinet_0.2-2-1-0.02		64.20 337	61.39 349	72.63 297	70.85 413	46.32 364	85.92 133	85.98 119	55.27 349	51.88 396	72.29 423	33.14 350	87.82 242	48.50 361	48.72 433	83.73 317

CP-MVS		72.59 170	71.46 172	76.00 180	82.93 139	52.32 179	86.93 104	82.48 234	55.15 350	63.65 240	90.44 109	35.03 328	88.53 211	68.69 171	77.83 130	87.15 239

pmmvs4		63.34 349	61.07 355	70.16 354	70.14 425	50.53 231	79.97 348	71.41 429	55.08 351	54.12 377	78.58 343	32.79 356	82.09 380	50.33 347	57.22 381	77.86 409

KD-MVS_2432*1600		59.04 383	56.44 388	66.86 392	79.07 263	45.87 374	72.13 421	80.42 279	55.03 352	48.15 421	71.01 431	36.73 297	78.05 421	35.21 429	30.18 491	76.67 421

miper_refine_blended		59.04 383	56.44 388	66.86 392	79.07 263	45.87 374	72.13 421	80.42 279	55.03 352	48.15 421	71.01 431	36.73 297	78.05 421	35.21 429	30.18 491	76.67 421

MDTV_nov1_ep13_2view						43.62 401	71.13 428		54.95 354	59.29 298		36.76 296		46.33 377		87.32 234

Anonymous202405211		70.11 226	67.88 246	76.79 154	87.20 50	47.24 344	89.49 37	77.38 358	54.88 355	66.14 187	86.84 210	20.93 446	91.54 79	56.45 297	71.62 229	91.59 70

OMC-MVS		65.97 323	65.06 314	68.71 374	72.97 386	42.58 417	78.61 364	75.35 385	54.72 356	59.31 296	86.25 220	33.30 348	77.88 425	57.99 274	67.05 277	85.66 277

LPG-MVS_test		66.44 316	64.58 318	72.02 317	74.42 367	48.60 292	83.07 262	80.64 273	54.69 357	53.75 381	83.83 262	25.73 413	86.98 281	60.33 252	64.71 302	80.48 379

LGP-MVS_train				72.02 317	74.42 367	48.60 292		80.64 273	54.69 357	53.75 381	83.83 262	25.73 413	86.98 281	60.33 252	64.71 302	80.48 379

tfpnnormal		61.47 367	59.09 372	68.62 376	76.29 331	41.69 424	81.14 322	85.16 152	54.48 359	51.32 398	73.63 403	32.32 360	86.89 288	21.78 485	55.71 397	77.29 416

mmtdpeth		57.93 395	54.78 400	67.39 387	72.32 395	43.38 405	72.72 411	68.93 445	54.45 360	56.85 347	62.43 465	17.02 468	83.46 368	57.95 277	30.31 490	75.31 434

tttt0517		68.33 270	66.29 283	74.46 236	78.08 289	49.06 275	80.88 328	89.08 36	54.40 361	54.75 370	80.77 318	51.31 62	90.33 129	49.35 354	58.01 372	83.99 308

pmmvs5		62.80 355	61.18 353	67.66 383	69.53 432	42.37 420	82.65 273	75.19 386	54.30 362	52.03 394	78.51 344	31.64 372	80.67 392	48.60 360	58.15 368	79.95 386

SSM_0407		69.71 237	67.38 261	76.69 158	80.45 225	51.81 198	81.36 319	80.18 283	54.07 363	63.82 234	85.05 241	33.09 351	91.01 100	59.40 255	68.97 261	87.25 236

SSM_0404		70.13 224	67.87 249	76.88 149	80.22 232	52.00 187	81.71 305	80.18 283	54.07 363	65.36 201	85.05 241	33.09 351	91.03 97	59.40 255	71.80 227	87.63 226

APD-MVS		76.15 84	75.68 80	77.54 122	88.52 29	53.44 141	87.26 93	85.03 162	53.79 365	74.91 67	91.68 77	43.80 186	90.31 130	74.36 113	81.82 77	88.87 187
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
114514_t		69.87 235	67.88 246	75.85 184	88.38 31	52.35 178	86.94 102	83.68 208	53.70 366	55.68 360	85.60 230	30.07 384	91.20 92	55.84 302	71.02 238	83.99 308

testing3		59.97 373	60.19 364	59.32 444	77.60 298	30.01 481	81.75 302	81.79 249	53.54 367	50.34 411	79.94 326	48.99 89	76.91 434	17.19 496	50.59 424	71.03 467

PAPM_NR		71.80 191	69.98 208	77.26 135	81.54 188	53.34 146	78.60 365	85.25 147	53.46 368	60.53 279	88.66 148	45.69 151	89.24 173	56.49 294	79.62 107	89.19 178

test-mter		68.36 268	67.29 262	71.60 330	78.67 275	48.17 311	85.13 176	79.72 297	53.38 369	63.13 246	82.58 288	27.23 400	80.24 400	60.56 246	75.17 179	86.39 263

jajsoiax		63.21 350	60.84 356	70.32 352	68.33 442	44.45 390	81.23 320	81.05 263	53.36 370	50.96 405	77.81 352	17.49 466	85.49 337	59.31 257	58.05 371	81.02 373

testgi		54.25 414	52.57 414	59.29 446	62.76 472	21.65 503	72.21 419	70.47 435	53.25 371	41.94 454	77.33 359	14.28 476	77.95 424	29.18 456	51.72 422	78.28 404

tpm cat1		66.28 318	62.78 331	76.77 156	81.40 193	57.14 27	70.03 432	77.19 360	53.00 372	58.76 310	70.73 436	46.17 131	86.73 295	43.27 392	64.46 306	86.44 261

mvs_tets		62.96 353	60.55 358	70.19 353	68.22 445	44.24 395	80.90 327	80.74 271	52.99 373	50.82 409	77.56 353	16.74 470	85.44 338	59.04 260	57.94 373	80.89 374

test20.03		55.22 410	54.07 404	58.68 448	63.14 471	25.00 494	77.69 371	74.78 389	52.64 374	43.43 446	72.39 417	26.21 407	74.76 448	29.31 455	47.05 447	76.28 428

VDDNet		74.37 129	72.13 161	81.09 23	79.58 247	56.52 41	90.02 26	86.70 102	52.61 375	71.23 124	87.20 205	31.75 371	93.96 29	74.30 115	75.77 170	92.79 29

v7n		62.50 359	59.27 371	72.20 312	67.25 448	49.83 255	77.87 370	80.12 285	52.50 376	48.80 419	73.07 407	32.10 363	87.90 238	46.83 373	54.92 401	78.86 393

FMVSNet1		64.57 334	62.11 340	71.96 320	77.32 309	46.36 360	83.52 237	83.30 216	52.43 377	54.42 373	76.23 378	27.80 396	86.20 311	42.59 398	61.34 337	83.32 329

K. test v3		54.04 416	49.42 430	67.92 382	68.55 439	42.57 418	75.51 386	63.07 467	52.07 378	39.21 466	64.59 460	19.34 454	82.21 377	37.11 415	25.31 496	78.97 392

原ACMM1				76.13 175	84.89 86	54.59 113		85.26 146	51.98 379	66.70 179	87.07 208	40.15 243	89.70 156	51.23 343	85.06 54	84.10 304

tpmvs		62.45 361	59.42 369	71.53 333	83.93 108	54.32 118	70.03 432	77.61 353	51.91 380	53.48 384	68.29 445	37.91 266	86.66 298	33.36 439	58.27 366	73.62 449

PEN-MVS		58.35 393	57.15 383	61.94 432	67.55 447	34.39 456	77.01 373	78.35 339	51.87 381	47.72 425	76.73 371	33.91 342	73.75 453	34.03 436	47.17 445	77.68 412

EG-PatchMatch MVS		62.40 362	59.59 367	70.81 344	73.29 380	49.05 276	85.81 139	84.78 174	51.85 382	44.19 442	73.48 405	15.52 475	89.85 146	40.16 405	67.24 276	73.54 450

UniMVSNet_ETH3D		62.51 358	60.49 359	68.57 378	68.30 443	40.88 434	73.89 400	79.93 292	51.81 383	54.77 369	79.61 333	24.80 421	81.10 385	49.93 349	61.35 336	83.73 317

CP-MVSNet		58.54 392	57.57 381	61.46 436	68.50 440	33.96 461	76.90 375	78.60 332	51.67 384	47.83 424	76.60 373	34.99 329	72.79 459	35.45 426	47.58 441	77.64 414

WR-MVS_H		58.91 385	58.04 378	61.54 435	69.07 436	33.83 462	76.91 374	81.99 243	51.40 385	48.17 420	74.67 390	40.23 241	74.15 449	31.78 446	48.10 437	76.64 424

lecture		74.14 135	73.05 141	77.44 126	81.66 179	50.39 237	87.43 84	84.22 197	51.38 386	72.10 105	90.95 95	38.31 263	93.23 38	70.51 152	80.83 85	88.69 192

PS-CasMVS		58.12 394	57.03 385	61.37 437	68.24 444	33.80 463	76.73 377	78.01 343	51.20 387	47.54 428	76.20 381	32.85 354	72.76 460	35.17 431	47.37 443	77.55 415

DTE-MVSNet		57.03 399	55.73 395	60.95 441	65.94 452	32.57 468	75.71 380	77.09 363	51.16 388	46.65 435	76.34 376	32.84 355	73.22 458	30.94 450	44.87 454	77.06 417

LuminaMVS		66.60 313	64.37 321	73.27 280	70.06 428	49.57 258	80.77 331	81.76 252	50.81 389	60.56 278	78.41 346	24.50 424	87.26 274	64.24 209	68.25 267	82.99 338

HPM-MVS_fast		67.86 278	66.28 284	72.61 298	80.67 216	48.34 303	81.18 321	75.95 379	50.81 389	59.55 291	88.05 179	27.86 395	85.98 326	58.83 261	73.58 203	83.51 327

dtuonlycased		54.12 415	52.39 416	59.30 445	64.31 464	41.80 423	78.63 363	65.85 455	50.56 391	42.00 453	60.21 475	26.14 410	73.31 456	43.06 393	40.73 464	62.79 485

MVSMamba_PlusPlus		75.28 108	73.39 132	80.96 24	80.85 210	58.25 13	74.47 396	87.61 81	50.53 392	65.24 202	83.41 272	57.38 24	92.83 43	73.92 120	87.13 22	91.80 63

MVSFormer		73.53 150	72.19 159	77.57 120	83.02 134	55.24 69	81.63 307	81.44 257	50.28 393	76.67 57	90.91 96	44.82 173	86.11 315	60.83 242	80.09 97	91.36 83

test_djsdf		63.84 342	61.56 347	70.70 346	68.78 437	44.69 388	81.63 307	81.44 257	50.28 393	52.27 391	76.26 377	26.72 404	86.11 315	60.83 242	55.84 396	81.29 370

FMVSNet5		58.61 389	56.45 387	65.10 410	77.20 315	39.74 436	74.77 391	77.12 362	50.27 395	43.28 448	67.71 447	26.15 409	76.90 436	36.78 420	54.78 403	78.65 397

FE-MVS		64.15 338	60.43 361	75.30 211	80.85 210	49.86 254	68.28 442	78.37 338	50.26 396	59.31 296	73.79 398	26.19 408	91.92 71	40.19 404	66.67 280	84.12 303

Anonymous20231206		59.08 382	57.59 380	63.55 419	68.77 438	32.14 471	80.26 340	79.78 296	50.00 397	49.39 415	72.39 417	26.64 405	78.36 416	33.12 442	57.94 373	80.14 384

ACMH	53.70 16	59.78 374	55.94 394	71.28 335	76.59 324	48.35 302	80.15 343	76.11 377	49.74 398	41.91 455	73.45 406	16.50 472	90.31 130	31.42 447	57.63 379	75.17 436
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs-eth3d		55.97 407	52.78 412	65.54 405	61.02 476	46.44 359	75.36 388	67.72 450	49.61 399	43.65 445	67.58 448	21.63 443	77.04 432	44.11 389	44.33 455	73.15 455

AdaColmap		67.86 278	65.48 303	75.00 223	88.15 39	54.99 84	86.10 128	76.63 373	49.30 400	57.80 328	86.65 215	29.39 387	88.94 191	45.10 382	70.21 250	81.06 372

无先验							85.19 173	78.00 344	49.08 401				85.13 345	52.78 329		87.45 231

ppachtmachnet_test		58.56 390	54.34 401	71.24 336	71.42 406	54.74 103	81.84 298	72.27 417	49.02 402	45.86 439	68.99 444	26.27 406	83.30 370	30.12 452	43.23 459	75.69 430

SR-MVS		70.92 211	69.73 211	74.50 235	83.38 122	50.48 234	84.27 215	79.35 312	48.96 403	66.57 184	90.45 106	33.65 346	87.11 278	66.42 185	74.56 191	85.91 272

tt0805		63.39 348	61.31 352	69.64 361	69.36 433	38.87 442	78.00 368	85.48 132	48.82 404	55.66 362	81.66 309	24.38 425	86.37 308	49.04 357	59.36 356	83.68 323

reproduce-ours		71.77 193	70.43 194	75.78 186	81.96 166	49.54 264	82.54 279	81.01 266	48.77 405	69.21 157	90.96 92	37.13 289	89.40 167	66.28 188	76.01 161	88.39 208

our_new_method		71.77 193	70.43 194	75.78 186	81.96 166	49.54 264	82.54 279	81.01 266	48.77 405	69.21 157	90.96 92	37.13 289	89.40 167	66.28 188	76.01 161	88.39 208

our_test_3		59.11 381	55.08 399	71.18 339	71.42 406	53.29 149	81.96 293	74.52 392	48.32 407	42.08 452	69.28 443	28.14 391	82.15 378	34.35 435	45.68 453	78.11 407

kuosan		50.20 438	50.09 424	50.52 464	73.09 384	29.09 488	65.25 449	74.89 388	48.27 408	41.34 458	60.85 473	43.45 197	67.48 473	18.59 494	25.07 497	55.01 490

APD-MVS_3200maxsize		69.62 243	68.23 238	73.80 262	81.58 186	48.22 309	81.91 295	79.50 305	48.21 409	64.24 225	89.75 127	31.91 368	87.55 262	63.08 220	73.85 201	85.63 278

CHOSEN 280x420		57.53 398	56.38 391	60.97 440	74.01 374	48.10 315	46.30 489	54.31 482	48.18 410	50.88 408	77.43 358	38.37 262	59.16 488	54.83 310	63.14 324	75.66 431

reproduce_model		71.07 206	69.67 212	75.28 214	81.51 191	48.82 286	81.73 303	80.57 276	47.81 411	68.26 167	90.78 100	36.49 303	88.60 204	65.12 204	74.76 189	88.42 207

FOURS1					83.24 125	49.90 253	84.98 187	78.76 326	47.71 412	73.42 82

ACMM	58.35 12	64.35 336	62.01 343	71.38 334	74.21 371	48.51 296	82.25 286	79.66 300	47.61 413	54.54 372	80.11 325	25.26 416	86.00 324	51.26 342	63.16 323	79.64 388
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SixPastTwentyTwo		54.37 412	50.10 423	67.21 388	70.70 416	41.46 429	74.73 392	64.69 459	47.56 414	39.12 467	69.49 439	18.49 461	84.69 352	31.87 445	34.20 484	75.48 432

usedtu_blend_shiyan5		63.62 345	60.36 362	73.40 275	70.49 419	47.96 322	79.13 360	80.68 272	47.51 415	51.25 399	72.31 420	36.16 307	88.50 212	56.81 290	48.90 429	83.73 317

Anonymous20240529		69.71 237	67.28 263	77.00 143	83.78 112	50.36 241	88.87 52	85.10 159	47.22 416	64.03 228	83.37 273	27.93 394	92.10 68	57.78 282	67.44 275	88.53 203

ACMH+	54.58 15	58.55 391	55.24 396	68.50 379	74.68 363	45.80 377	80.27 339	70.21 437	47.15 417	42.77 451	75.48 386	16.73 471	85.98 326	35.10 433	54.78 403	73.72 448

XVG-OURS		61.88 364	59.34 370	69.49 362	65.37 455	46.27 365	64.80 452	73.49 407	47.04 418	57.41 341	82.85 279	25.15 418	78.18 417	53.00 326	64.98 297	84.01 307

TAPA-MVS	56.12 14	61.82 365	60.18 365	66.71 394	78.48 284	37.97 447	75.19 389	76.41 376	46.82 419	57.04 345	86.52 217	27.67 398	77.03 433	26.50 470	67.02 278	85.14 286
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UnsupCasMVSNet_bld		53.86 417	50.53 422	63.84 416	63.52 470	34.75 454	71.38 426	81.92 246	46.53 420	38.95 468	57.93 481	20.55 448	80.20 402	39.91 406	34.09 485	76.57 425

anonymousdsp		60.46 372	57.65 379	68.88 368	63.63 468	45.09 382	72.93 409	78.63 330	46.52 421	51.12 402	72.80 412	21.46 444	83.07 372	57.79 281	53.97 408	78.47 399

XVG-OURS-SEG-HR		62.02 363	59.54 368	69.46 363	65.30 456	45.88 373	65.06 451	73.57 405	46.45 422	57.42 340	83.35 274	26.95 402	78.09 419	53.77 318	64.03 309	84.42 297

SR-MVS-dyc-post		68.27 272	66.87 269	72.48 303	80.96 205	48.14 313	81.54 313	76.98 364	46.42 423	62.75 252	89.42 133	31.17 376	86.09 319	60.52 248	72.06 225	83.19 334

RE-MVS-def			66.66 276		80.96 205	48.14 313	81.54 313	76.98 364	46.42 423	62.75 252	89.42 133	29.28 388		60.52 248	72.06 225	83.19 334

OpenMVS_ROB	53.19 17	59.20 379	56.00 393	68.83 370	71.13 410	44.30 392	83.64 235	75.02 387	46.42 423	46.48 436	73.03 408	18.69 458	88.14 228	27.74 465	61.80 334	74.05 446

Elysia		65.59 325	62.65 332	74.42 238	69.85 429	49.46 268	80.04 344	82.11 239	46.32 426	58.74 313	79.64 331	20.30 449	88.57 208	55.48 306	71.37 233	85.22 284

StellarMVS		65.59 325	62.65 332	74.42 238	69.85 429	49.46 268	80.04 344	82.11 239	46.32 426	58.74 313	79.64 331	20.30 449	88.57 208	55.48 306	71.37 233	85.22 284

FE-MVSNET		51.43 432	48.22 435	61.06 439	60.78 478	32.48 469	73.85 402	64.62 460	46.30 428	37.47 473	66.27 452	20.80 447	77.38 431	23.43 479	40.48 467	73.31 452

CPTT-MVS		67.15 300	65.84 295	71.07 340	80.96 205	50.32 243	81.94 294	74.10 396	46.18 429	57.91 326	87.64 197	29.57 385	81.31 384	64.10 210	70.18 251	81.56 358

new-patchmatchnet		48.21 441	46.55 443	53.18 460	57.73 482	18.19 511	70.24 430	71.02 433	45.70 430	33.70 483	60.23 474	18.00 462	69.86 469	27.97 464	34.35 482	71.49 465

新几何1				73.30 278	83.10 128	53.48 137		71.43 428	45.55 431	66.14 187	87.17 206	33.88 344	80.54 396	48.50 361	80.33 95	85.88 274

旧先验2							81.73 303		45.53 432	74.66 68			70.48 468	58.31 270

Anonymous20231211		66.08 322	63.67 326	73.31 277	83.07 131	48.75 288	86.01 132	84.67 184	45.27 433	56.54 352	76.67 372	28.06 393	88.95 189	52.78 329	59.95 347	82.23 348

XVG-ACMP-BASELINE		56.03 406	52.85 411	65.58 404	61.91 474	40.95 433	63.36 457	72.43 416	45.20 434	46.02 437	74.09 394	9.20 489	78.12 418	45.13 381	58.27 366	77.66 413

pmmvs6		59.64 375	57.15 383	67.09 389	66.01 451	36.86 451	80.50 334	78.64 329	45.05 435	49.05 417	73.94 397	27.28 399	86.10 317	43.96 390	49.94 426	78.31 403

mvs5depth		50.97 434	46.98 441	62.95 425	56.63 484	34.23 459	62.73 463	67.35 452	45.03 436	48.00 423	65.41 458	10.40 485	79.88 408	36.00 422	31.27 489	74.73 441

ADS-MVSNet2		55.21 411	51.44 418	66.51 397	80.60 217	49.56 261	55.03 481	65.44 457	44.72 437	51.00 403	61.19 471	22.83 433	75.41 446	28.54 460	53.63 411	74.57 443

ADS-MVSNet		56.17 405	51.95 417	68.84 369	80.60 217	53.07 157	55.03 481	70.02 439	44.72 437	51.00 403	61.19 471	22.83 433	78.88 412	28.54 460	53.63 411	74.57 443

testdata				67.08 390	77.59 299	45.46 380		69.20 444	44.47 439	71.50 121	88.34 163	31.21 375	70.76 467	52.20 338	75.88 164	85.03 287

MSDG		59.44 376	55.14 398	72.32 310	74.69 362	50.71 225	74.39 397	73.58 404	44.44 440	43.40 447	77.52 354	19.45 453	90.87 108	31.31 448	57.49 380	75.38 433

KD-MVS_self_test		49.24 439	46.85 442	56.44 454	54.32 486	22.87 497	57.39 476	73.36 412	44.36 441	37.98 471	59.30 479	18.97 457	71.17 465	33.48 438	42.44 460	75.26 435

YYNet1		53.82 418	49.96 425	65.41 407	70.09 427	48.95 280	72.30 417	71.66 425	44.25 442	31.89 489	63.07 464	23.73 429	73.95 451	33.26 440	39.40 471	73.34 451

MDA-MVSNet_test_wron		53.82 418	49.95 426	65.43 406	70.13 426	49.05 276	72.30 417	71.65 426	44.23 443	31.85 490	63.13 463	23.68 430	74.01 450	33.25 441	39.35 472	73.23 454

MDA-MVSNet-bldmvs		51.56 431	47.75 440	63.00 424	71.60 403	47.32 342	69.70 435	72.12 418	43.81 444	27.65 497	63.38 462	21.97 442	75.96 442	27.30 467	32.19 486	65.70 479

PLC	52.38 18	60.89 369	58.97 374	66.68 396	81.77 172	45.70 378	78.96 361	74.04 399	43.66 445	47.63 426	83.19 277	23.52 431	77.78 428	37.47 411	60.46 343	76.55 426
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
IterMVS-SCA-FT		59.12 380	58.81 375	60.08 442	70.68 418	45.07 383	80.42 337	74.25 394	43.54 446	50.02 412	73.73 399	31.97 365	56.74 492	51.06 345	53.60 413	78.42 401

MIMVSNet1		50.35 437	47.81 438	57.96 450	61.53 475	27.80 492	67.40 444	74.06 398	43.25 447	33.31 488	65.38 459	16.03 473	71.34 464	21.80 484	47.55 442	74.75 440

LTVRE_ROB	45.45 19	52.73 423	49.74 428	61.69 434	69.78 431	34.99 453	44.52 492	67.60 451	43.11 448	43.79 444	74.03 395	18.54 460	81.45 383	28.39 462	57.94 373	68.62 470
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
test_0402		56.45 403	53.03 408	66.69 395	76.78 323	50.31 244	81.76 300	69.61 442	42.79 449	43.88 443	72.13 426	22.82 435	86.46 305	16.57 497	50.94 423	63.31 483

test222					79.36 253	50.97 216	77.99 369	67.84 449	42.54 450	62.84 251	86.53 216	30.26 381			76.91 142	85.23 283

CNLPA		60.59 371	58.44 376	67.05 391	79.21 259	47.26 343	79.75 350	64.34 464	42.46 451	51.90 395	83.94 259	27.79 397	75.41 446	37.12 414	59.49 354	78.47 399

PatchMatch-RL		56.66 400	53.75 406	65.37 408	77.91 295	45.28 381	69.78 434	60.38 471	41.35 452	47.57 427	73.73 399	16.83 469	76.91 434	36.99 417	59.21 357	73.92 447

DP-MVS		59.24 378	56.12 392	68.63 375	88.24 36	50.35 242	82.51 281	64.43 463	41.10 453	46.70 434	78.77 342	24.75 422	88.57 208	22.26 483	56.29 389	66.96 474

F-COLMAP		55.96 408	53.65 407	62.87 426	72.76 389	42.77 414	74.70 394	70.37 436	40.03 454	41.11 461	79.36 335	17.77 464	73.70 454	32.80 443	53.96 409	72.15 459

dongtai		43.51 448	44.07 450	41.82 475	63.75 467	21.90 501	63.80 455	72.05 419	39.59 455	33.35 487	54.54 486	41.04 229	57.30 490	10.75 508	17.77 506	46.26 498

gg-mvs-nofinetune		67.43 290	64.53 319	76.13 175	85.95 63	47.79 331	64.38 454	88.28 64	39.34 456	66.62 181	41.27 496	58.69 17	89.00 184	49.64 352	86.62 32	91.59 70

TinyColmap		48.15 442	44.49 447	59.13 447	65.73 454	38.04 446	63.34 458	62.86 468	38.78 457	29.48 492	67.23 450	6.46 499	73.30 457	24.59 474	41.90 462	66.04 477

PatchT		56.60 401	52.97 409	67.48 385	72.94 387	46.16 370	57.30 477	73.78 402	38.77 458	54.37 374	57.26 483	37.52 278	78.06 420	32.02 444	52.79 418	78.23 406

sc_t1		53.51 421	49.92 427	64.29 414	70.33 423	39.55 439	72.93 409	59.60 474	38.74 459	47.16 431	66.47 451	17.59 465	76.50 439	36.83 419	39.62 470	76.82 419

OurMVSNet-221017-0		52.39 427	48.73 432	63.35 423	65.21 457	38.42 445	68.54 440	64.95 458	38.19 460	39.57 465	71.43 430	13.23 478	79.92 404	37.16 413	40.32 468	71.72 462

ANet_high		34.39 460	29.59 467	48.78 467	30.34 513	22.28 499	55.53 480	63.79 465	38.11 461	15.47 506	36.56 503	6.94 495	59.98 484	13.93 501	5.64 518	64.08 481

PM-MVS		46.92 444	43.76 451	56.41 455	52.18 490	32.26 470	63.21 460	38.18 500	37.99 462	40.78 462	66.20 453	5.09 503	65.42 476	48.19 364	41.99 461	71.54 464

Patchmtry		56.56 402	52.95 410	67.42 386	72.53 392	50.59 230	59.05 473	71.72 423	37.86 463	46.92 432	65.86 454	38.94 256	80.06 403	36.94 418	46.72 449	71.60 463

PatchmatchNet2					0.00 567	32.03 472	74.85 390	61.13 470	37.29 464
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
tt0320-xc		52.22 429	48.38 434	63.75 418	72.19 398	42.25 421	72.19 420	57.59 477	37.24 465	44.41 441	61.56 468	17.90 463	75.89 443	35.60 425	36.73 475	73.12 456

JIA-IIPM		52.33 428	47.77 439	66.03 400	71.20 409	46.92 346	40.00 499	76.48 375	37.10 466	46.73 433	37.02 500	32.96 353	77.88 425	35.97 423	52.45 420	73.29 453

CVMVSNet		60.85 370	60.44 360	62.07 429	75.00 359	32.73 467	79.54 353	73.49 407	36.98 467	56.28 356	83.74 264	29.28 388	69.53 470	46.48 375	63.23 321	83.94 313

ITE_SJBPF				51.84 461	58.03 481	31.94 473		53.57 485	36.67 468	41.32 459	75.23 388	11.17 483	51.57 497	25.81 471	48.04 438	72.02 461

Anonymous20240521		51.65 430	48.42 433	61.34 438	56.43 485	39.65 438	73.57 404	73.47 410	36.64 469	36.59 474	63.98 461	10.75 484	72.25 463	35.35 427	49.01 427	72.11 460

COLMAP_ROB	43.60 20	50.90 435	48.05 437	59.47 443	67.81 446	40.57 435	71.25 427	62.72 469	36.49 470	36.19 476	73.51 404	13.48 477	73.92 452	20.71 487	50.26 425	63.92 482
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
usedtu_dtu_shiyan2		50.47 436	46.43 444	62.61 428	51.66 492	31.70 474	75.62 383	75.65 381	36.36 471	34.89 480	56.91 484	12.01 479	78.40 415	30.87 451	43.86 456	77.72 411

tt0320		52.45 426	48.75 431	63.55 419	71.47 405	41.85 422	72.41 415	59.73 473	36.33 472	44.52 440	61.55 469	19.34 454	76.45 440	33.53 437	39.85 469	72.36 458

RPMNet		59.29 377	54.25 403	74.42 238	73.97 376	56.57 38	60.52 469	76.98 364	35.72 473	57.49 337	58.87 480	37.73 271	85.26 341	27.01 468	59.93 348	81.42 362

N_pmnet		41.25 450	39.77 454	45.66 471	68.50 440	0.82 542	72.51 414	0.38 540	35.61 474	35.26 479	61.51 470	20.07 452	67.74 471	23.51 477	40.63 465	68.42 472

AllTest		47.32 443	44.66 446	55.32 458	65.08 459	37.50 449	62.96 461	54.25 483	35.45 475	33.42 485	72.82 410	9.98 486	59.33 485	24.13 475	43.84 457	69.13 468

TestCases				55.32 458	65.08 459	37.50 449		54.25 483	35.45 475	33.42 485	72.82 410	9.98 486	59.33 485	24.13 475	43.84 457	69.13 468

LS3D		56.40 404	53.82 405	64.12 415	81.12 200	45.69 379	73.42 406	66.14 453	35.30 477	43.24 449	79.88 327	22.18 440	79.62 409	19.10 492	64.00 310	67.05 473

WB-MVS		37.41 457	36.37 458	40.54 478	54.23 487	10.43 518	65.29 448	43.75 492	34.86 478	27.81 496	54.63 485	24.94 420	63.21 478	6.81 515	15.00 508	47.98 497

Patchmatch-test		53.33 422	48.17 436	68.81 371	73.31 379	42.38 419	42.98 494	58.23 475	32.53 479	38.79 469	70.77 434	39.66 249	73.51 455	25.18 472	52.06 421	90.55 124

test_fmvs1		53.60 420	52.54 415	56.78 452	58.07 480	30.26 477	68.95 438	42.19 495	32.46 480	63.59 242	82.56 290	11.55 481	60.81 482	58.25 271	55.27 399	79.28 389

test_fmvs1_n		52.55 425	51.19 420	56.65 453	51.90 491	30.14 478	67.66 443	42.84 494	32.27 481	62.30 257	82.02 304	9.12 490	60.84 481	57.82 280	54.75 405	78.99 391

test_vis1_n		51.19 433	49.66 429	55.76 457	51.26 494	29.85 483	67.20 446	38.86 499	32.12 482	59.50 292	79.86 328	8.78 491	58.23 489	56.95 289	52.46 419	79.19 390

SSC-MVS		35.20 459	34.30 462	37.90 480	52.58 489	8.65 521	61.86 464	41.64 496	31.81 483	25.54 499	52.94 491	23.39 432	59.28 487	6.10 517	12.86 510	45.78 500

EU-MVSNet		52.63 424	50.72 421	58.37 449	62.69 473	28.13 491	72.60 412	75.97 378	30.94 484	40.76 463	72.11 427	20.16 451	70.80 466	35.11 432	46.11 451	76.19 429

CMPMVS	40.41 21	55.34 409	52.64 413	63.46 421	60.88 477	43.84 399	61.58 467	71.06 432	30.43 485	36.33 475	74.63 391	24.14 427	75.44 445	48.05 365	66.62 281	71.12 466
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
TDRefinement		40.91 451	38.37 456	48.55 468	50.45 496	33.03 466	58.98 474	50.97 486	28.50 486	29.89 491	67.39 449	6.21 501	54.51 494	17.67 495	35.25 479	58.11 487

ttmdpeth		40.58 452	37.50 457	49.85 465	49.40 497	22.71 498	56.65 478	46.78 487	28.35 487	40.29 464	69.42 441	5.35 502	61.86 480	20.16 489	21.06 503	64.96 480

pmmvs3		45.53 447	41.55 453	57.44 451	48.97 499	39.68 437	70.06 431	57.66 476	28.32 488	34.06 482	57.29 482	8.50 492	66.85 475	34.86 434	34.26 483	65.80 478

mvsany_test1		43.38 449	42.57 452	45.82 470	50.96 495	26.10 493	55.80 479	27.74 512	27.15 489	47.41 430	74.39 393	18.67 459	44.95 504	44.66 384	36.31 476	66.40 476

RPSCF		45.77 446	44.13 449	50.68 462	57.67 483	29.66 484	54.92 483	45.25 491	26.69 490	45.92 438	75.92 384	17.43 467	45.70 503	27.44 466	45.95 452	76.67 421

test_fmvs2		45.89 445	44.32 448	50.62 463	45.85 503	24.70 495	58.87 475	37.84 502	25.22 491	52.46 389	74.56 392	7.07 494	54.69 493	49.28 355	47.70 440	72.48 457

MVS-HIRNet		49.01 440	44.71 445	61.92 433	76.06 336	46.61 355	63.23 459	54.90 481	24.77 492	33.56 484	36.60 502	21.28 445	75.88 444	29.49 454	62.54 330	63.26 484

test_vis1_rt		40.29 453	38.64 455	45.25 472	48.91 500	30.09 479	59.44 472	27.07 513	24.52 493	38.48 470	51.67 492	6.71 497	49.44 498	44.33 386	46.59 450	56.23 488

new_pmnet		33.56 462	31.89 465	38.59 479	49.01 498	20.42 504	51.01 484	37.92 501	20.58 494	23.45 500	46.79 494	6.66 498	49.28 500	20.00 491	31.57 488	46.09 499

LF4IMVS		33.04 463	32.55 464	34.52 483	40.96 504	22.03 500	44.45 493	35.62 504	20.42 495	28.12 495	62.35 466	5.03 504	31.88 516	21.61 486	34.42 481	49.63 495

FPMVS		35.40 458	33.67 463	40.57 477	46.34 502	28.74 490	41.05 496	57.05 478	20.37 496	22.27 501	53.38 489	6.87 496	44.94 505	8.62 509	47.11 446	48.01 496

DSMNet-mixed		38.35 454	35.36 460	47.33 469	48.11 501	14.91 515	37.87 500	36.60 503	19.18 497	34.37 481	59.56 478	15.53 474	53.01 496	20.14 490	46.89 448	74.07 445

PMMVS2		26.71 468	22.98 474	37.87 481	36.89 507	8.51 522	42.51 495	29.32 511	19.09 498	13.01 509	37.54 499	2.23 511	53.11 495	14.54 500	11.71 511	51.99 494

test_fmvs3		37.95 456	35.75 459	44.55 473	35.50 509	18.92 507	48.32 486	34.00 507	18.36 499	41.31 460	61.58 467	2.29 510	48.06 502	42.72 397	37.71 474	66.66 475

MVStest1		38.35 454	34.53 461	49.82 466	51.43 493	30.41 476	50.39 485	55.25 479	17.56 500	26.45 498	65.85 456	11.72 480	57.00 491	14.79 499	17.31 507	62.05 486

mvsany_test3		28.00 465	25.98 468	34.05 484	28.97 514	15.31 513	34.54 503	18.17 518	16.24 501	29.30 493	53.37 490	2.79 508	33.38 515	30.01 453	20.41 504	53.45 492

PMVS	19.57 22	25.07 470	22.43 476	32.99 487	23.12 520	22.98 496	40.98 497	35.19 505	15.99 502	11.95 514	35.87 504	1.47 518	49.29 499	5.41 520	31.90 487	26.70 509
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		27.47 466	24.26 472	37.12 482	60.55 479	29.17 487	11.68 514	60.00 472	14.18 503	10.52 515	15.12 523	2.20 512	63.01 479	8.39 510	35.65 477	19.18 510
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_vis3_rt		24.79 471	22.95 475	30.31 489	28.59 515	18.92 507	37.43 501	17.27 520	12.90 504	21.28 502	29.92 510	1.02 519	36.35 509	28.28 463	29.82 493	35.65 501

LCM-MVSNet		28.07 464	23.85 473	40.71 476	27.46 518	18.93 506	30.82 506	46.19 488	12.76 505	16.40 503	34.70 505	1.90 513	48.69 501	20.25 488	24.22 498	54.51 491

test_f		27.12 467	24.85 469	33.93 485	26.17 519	15.25 514	30.24 507	22.38 517	12.53 506	28.23 494	49.43 493	2.59 509	34.34 514	25.12 473	26.99 494	52.20 493

APD_test1		26.46 469	24.41 471	32.62 488	37.58 506	21.74 502	40.50 498	30.39 509	11.45 507	16.33 504	43.76 495	1.63 516	41.62 506	11.24 505	26.82 495	34.51 503

E-PMN		19.16 475	18.40 480	21.44 493	36.19 508	13.63 516	47.59 487	30.89 508	10.73 508	5.91 522	16.59 521	3.66 506	39.77 507	5.95 518	8.14 513	10.92 517

DeepMVS_CX				13.10 497	21.34 521	8.99 520		10.02 523	10.59 509	7.53 519	30.55 509	1.82 514	14.55 517	6.83 514	7.52 514	15.75 512

EMVS		18.42 476	17.66 481	20.71 494	34.13 510	12.64 517	46.94 488	29.94 510	10.46 510	5.58 524	14.93 524	4.23 505	38.83 508	5.24 521	7.51 515	10.67 518

testf1		21.11 473	19.08 478	27.18 491	30.56 511	18.28 509	33.43 504	24.48 514	8.02 511	12.02 512	33.50 506	0.75 521	35.09 512	7.68 511	21.32 500	28.17 506

APD_test2		21.11 473	19.08 478	27.18 491	30.56 511	18.28 509	33.43 504	24.48 514	8.02 511	12.02 512	33.50 506	0.75 521	35.09 512	7.68 511	21.32 500	28.17 506

MVE	16.60 23	17.34 478	13.39 482	29.16 490	28.43 516	19.72 505	13.73 512	23.63 516	7.23 513	7.96 518	21.41 516	0.80 520	36.08 510	6.97 513	10.39 512	31.69 504
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ArgMatch-Sym		13.78 479	13.16 483	15.65 496	13.75 522	8.38 523	21.56 509	2.56 525	7.09 514	14.16 508	40.67 497	0.28 524	11.85 521	13.55 503	4.84 520	26.71 508

ArgMatch-SfM		13.59 480	12.41 484	17.15 495	12.50 523	7.57 525	19.17 511	3.21 524	5.58 515	12.94 510	39.91 498	0.26 525	13.40 518	13.23 504	4.84 520	30.48 505

DenseAffine		8.44 484	7.90 491	10.07 499	9.51 524	4.71 526	11.43 515	1.10 528	4.32 516	8.26 517	27.67 512	0.09 528	8.71 522	6.30 516	2.41 525	16.80 511

RoMa-SfM		7.02 486	6.78 492	7.74 501	5.47 529	3.55 528	8.83 517	0.67 533	3.41 517	7.06 520	27.85 511	0.08 529	7.13 523	5.86 519	1.82 527	12.53 513

test_method		24.09 472	21.07 477	33.16 486	27.67 517	8.35 524	26.63 508	35.11 506	3.40 518	14.35 507	36.98 501	3.46 507	35.31 511	19.08 493	22.95 499	55.81 489

DKM		5.93 490	5.87 494	6.10 504	5.64 527	2.81 530	7.85 518	0.52 536	2.62 519	6.30 521	23.31 514	0.05 534	4.93 526	5.11 522	1.45 529	10.57 519

wuyk23d		9.11 483	8.77 488	10.15 498	40.18 505	16.76 512	20.28 510	1.01 529	2.58 520	2.66 531	0.98 545	0.23 526	12.49 520	4.08 526	6.90 516	1.19 531

PDCNetPlus		5.70 491	5.56 495	6.14 503	8.32 525	1.98 532	7.37 519	0.76 532	2.18 521	3.69 529	20.81 517	0.12 527	4.60 527	4.55 523	2.21 526	11.83 516

RoMa-HiRes		4.68 493	4.75 497	4.46 507	3.18 534	1.88 533	5.38 522	0.37 541	2.04 522	4.84 525	21.68 515	0.06 531	3.78 529	4.17 525	1.04 534	7.71 523

DKM-HiRes		4.42 494	4.49 498	4.23 508	3.85 532	1.83 534	5.38 522	0.33 542	1.86 523	4.78 526	18.85 520	0.04 540	2.97 531	4.34 524	0.97 535	7.88 522

VLMVS_CLIP		11.28 481	11.90 485	9.42 500	7.54 526	3.26 529	13.10 513	10.36 522	1.51 524	15.95 505	32.54 508	1.51 517	12.70 519	10.98 507	13.62 509	12.29 515

LoFTR		5.36 492	5.09 496	6.17 502	5.52 528	2.23 531	6.04 520	2.15 526	1.23 525	5.61 523	19.15 519	0.07 530	5.98 525	1.61 530	4.48 522	10.30 520

MatchFormer		3.89 495	3.84 500	4.03 509	4.08 531	1.73 535	5.52 521	1.59 527	0.67 526	4.77 527	13.56 527	0.04 540	4.50 528	0.74 534	3.60 524	5.85 525

PMatch-SfM		2.38 499	2.41 502	2.29 512	1.48 540	0.76 543	2.51 526	0.18 546	0.59 527	2.43 533	12.04 528	0.01 549	1.67 533	1.93 529	0.55 542	4.44 527

ELoFTR		2.17 500	1.90 505	2.99 511	1.19 543	0.63 544	1.84 528	0.60 534	0.46 528	2.17 534	9.10 531	0.02 548	2.92 532	1.00 533	0.72 539	5.42 526

PMatch-Up-SfM		1.67 502	1.74 506	1.44 513	1.00 547	0.50 546	1.72 531	0.11 552	0.40 529	1.75 535	8.98 532	0.00 564	1.07 535	1.34 531	0.35 555	2.76 528

MASt3R-SfM		1.80 501	2.02 504	1.14 515	1.03 546	0.52 545	1.83 529	0.53 535	0.34 530	2.55 532	9.61 530	0.05 534	0.77 537	1.06 532	1.16 533	2.14 530

GLUNet-SfM		2.60 498	2.13 503	4.01 510	1.95 539	0.86 540	1.72 531	0.81 531	0.34 530	3.35 530	9.72 529	0.04 540	3.15 530	0.50 535	0.73 538	8.02 521

tmp_tt		9.44 482	10.68 486	5.73 505	2.49 537	4.21 527	10.48 516	18.04 519	0.34 530	12.59 511	20.49 518	11.39 482	7.03 524	13.84 502	6.46 517	5.95 524

MVS_clip		3.10 497	3.65 501	1.44 513	3.78 533	1.17 536	2.78 525	0.19 544	0.20 533	4.48 528	14.54 526	0.35 523	0.47 540	2.92 528	3.64 523	2.67 529

ALIKED-LG		1.21 503	1.31 508	0.90 516	2.88 535	0.91 539	1.96 527	0.48 537	0.17 534	0.94 537	3.75 535	0.06 531	0.81 536	0.10 544	1.43 530	0.99 532

ALIKED-NN		1.00 506	1.09 510	0.75 518	2.44 538	0.84 541	1.63 533	0.39 538	0.12 535	0.72 540	3.04 537	0.05 534	0.70 539	0.08 546	1.32 532	0.72 540

ALIKED-MNN		1.07 505	1.15 509	0.84 517	2.67 536	0.92 538	1.81 530	0.39 538	0.12 535	0.73 539	3.13 536	0.05 534	0.77 537	0.09 545	1.34 531	0.84 534

SP-DiffGlue		0.50 508	0.53 512	0.38 523	0.41 563	0.20 553	0.62 538	0.19 544	0.09 537	0.64 542	1.95 539	0.06 531	0.17 547	0.26 537	0.60 540	0.77 538

SP-SuperGlue		0.47 510	0.50 513	0.39 520	1.30 542	0.19 554	0.86 534	0.17 547	0.09 537	0.26 543	1.08 541	0.05 534	0.18 546	0.13 540	0.55 542	0.79 537

SP-LightGlue		0.48 509	0.50 513	0.40 519	1.33 541	0.19 554	0.86 534	0.17 547	0.08 539	0.25 544	1.08 541	0.05 534	0.19 544	0.13 540	0.57 541	0.80 535

XFeat-MNN		0.55 507	0.60 511	0.39 520	0.26 564	0.16 561	0.58 539	0.20 543	0.08 539	0.82 538	2.26 538	0.03 545	0.39 541	0.19 538	0.95 536	0.62 541

SP-NN		0.43 513	0.45 517	0.37 524	1.13 545	0.17 558	0.82 537	0.16 549	0.07 541	0.24 545	1.00 544	0.04 540	0.19 544	0.12 542	0.51 545	0.74 539

SP-MNN		0.45 511	0.47 516	0.39 520	1.18 544	0.17 558	0.85 536	0.16 549	0.07 541	0.24 545	1.05 543	0.04 540	0.20 543	0.12 542	0.54 544	0.80 535

VLMVS		5.96 489	6.29 493	4.99 506	5.31 530	1.01 537	4.24 524	0.93 530	0.06 543	8.90 516	26.22 513	1.69 515	1.62 534	3.76 527	5.49 519	12.33 514

XFeat-NN		0.44 512	0.49 515	0.30 526	0.24 565	0.12 564	0.48 540	0.15 551	0.06 543	0.71 541	1.78 540	0.03 545	0.28 542	0.14 539	0.83 537	0.48 542

SIFT-UM-Cal		0.21 523	0.23 527	0.14 537	0.68 556	0.15 562	0.29 550	0.04 563	0.05 545	0.10 556	0.56 555	0.01 549	0.12 557	0.02 547	0.34 556	0.15 555

SIFT-NCM-Cal		0.26 517	0.28 521	0.19 530	0.84 550	0.23 550	0.38 544	0.06 556	0.05 545	0.11 554	0.59 553	0.01 549	0.14 548	0.02 547	0.45 549	0.21 549

SIFT-CM-Cal		0.21 523	0.23 527	0.15 536	0.71 555	0.18 556	0.28 551	0.05 559	0.05 545	0.10 556	0.55 556	0.01 549	0.12 557	0.01 559	0.33 557	0.17 553

SIFT-NN-UMatch		0.24 519	0.26 522	0.18 532	0.64 558	0.18 556	0.38 544	0.06 556	0.05 545	0.12 553	0.65 548	0.01 549	0.13 552	0.02 547	0.43 550	0.22 547

SIFT-NN-NCMNet		0.27 516	0.29 520	0.20 529	0.81 551	0.24 549	0.40 543	0.08 553	0.05 545	0.14 550	0.65 548	0.01 549	0.14 548	0.02 547	0.47 547	0.22 547

SIFT-NN-CMatch		0.25 518	0.26 522	0.19 530	0.68 556	0.21 551	0.35 546	0.06 556	0.05 545	0.15 548	0.65 548	0.01 549	0.13 552	0.02 547	0.41 551	0.23 545

SIFT-NN		0.30 514	0.33 518	0.22 527	0.96 548	0.28 547	0.45 541	0.08 553	0.05 545	0.17 547	0.72 546	0.01 549	0.14 548	0.02 547	0.48 546	0.25 543

SIFT-UMatch		0.23 521	0.25 525	0.16 535	0.74 553	0.17 558	0.33 547	0.05 559	0.05 545	0.11 554	0.60 552	0.01 549	0.13 552	0.02 547	0.37 554	0.18 552

SIFT-ConvMatch		0.24 519	0.26 522	0.18 532	0.76 552	0.21 551	0.32 548	0.05 559	0.05 545	0.13 551	0.63 551	0.01 549	0.13 552	0.02 547	0.38 553	0.19 550

SIFT-MNN		0.28 515	0.31 519	0.21 528	0.89 549	0.25 548	0.41 542	0.08 553	0.05 545	0.15 548	0.70 547	0.01 549	0.14 548	0.02 547	0.46 548	0.25 543

SIFT-PCN-Cal		0.18 525	0.20 529	0.13 538	0.58 560	0.10 566	0.23 554	0.04 563	0.04 555	0.08 559	0.47 557	0.01 549	0.10 559	0.01 559	0.30 558	0.19 550

SIFT-NN-PointCN		0.22 522	0.24 526	0.17 534	0.59 559	0.14 563	0.32 548	0.05 559	0.04 555	0.13 551	0.57 554	0.01 549	0.13 552	0.02 547	0.39 552	0.23 545

SIFT-NCMNet		0.15 527	0.17 531	0.10 540	0.52 562	0.09 567	0.19 555	0.02 567	0.04 555	0.07 561	0.39 559	0.01 549	0.08 561	0.01 559	0.24 560	0.11 556

SIFT-PointCN		0.18 525	0.20 529	0.13 538	0.58 560	0.11 565	0.25 552	0.04 563	0.04 555	0.08 559	0.45 558	0.01 549	0.10 559	0.01 559	0.30 558	0.17 553

EGC-MVSNET		33.75 461	30.42 466	43.75 474	64.94 461	36.21 452	60.47 471	40.70 498	0.02 559	0.10 556	53.79 488	7.39 493	60.26 483	11.09 506	35.23 480	34.79 502

MVS_baseline		1.13 504	1.40 507	0.34 525	0.74 553	0.01 568	0.24 553	0.03 566	0.00 560	1.75 535	7.74 533	0.03 545	0.00 562	0.31 536	1.74 528	0.99 532

mmdepth		0.00 528	0.00 532	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	0.00 562	0.00 564	0.00 562	0.00 563	0.00 561	0.00 559

monomultidepth		0.00 528	0.00 532	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	0.00 562	0.00 564	0.00 562	0.00 563	0.00 561	0.00 559

test_blank		0.00 528	0.00 532	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	0.00 562	0.00 564	0.00 562	0.00 563	0.00 561	0.00 559

uanet_test		0.00 528	0.00 532	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	0.00 562	0.00 564	0.00 562	0.00 563	0.00 561	0.00 559

DCPMVS		0.00 528	0.00 532	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	0.00 562	0.00 564	0.00 562	0.00 563	0.00 561	0.00 559

cdsmvs_eth3d_5k		18.33 477	24.44 470	0.00 543	0.00 567	0.00 570	0.00 556	89.40 30	0.00 560	0.00 564	92.02 65	38.55 260	0.00 562	0.00 563	0.00 561	0.00 559

pcd_1.5k_mvsjas		3.15 496	4.20 499	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	0.00 562	37.77 268	0.00 562	0.00 563	0.00 561	0.00 559

sosnet-low-res		0.00 528	0.00 532	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	0.00 562	0.00 564	0.00 562	0.00 563	0.00 561	0.00 559

sosnet		0.00 528	0.00 532	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	0.00 562	0.00 564	0.00 562	0.00 563	0.00 561	0.00 559

uncertanet		0.00 528	0.00 532	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	0.00 562	0.00 564	0.00 562	0.00 563	0.00 561	0.00 559

Regformer		0.00 528	0.00 532	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	0.00 562	0.00 564	0.00 562	0.00 563	0.00 561	0.00 559

testmvs		6.14 487	8.18 489	0.01 541	0.01 566	0.00 570	73.40 407	0.00 568	0.00 560	0.02 562	0.15 560	0.00 564	0.00 562	0.02 547	0.00 561	0.02 557

test123		6.01 488	8.01 490	0.01 541	0.00 567	0.01 568	71.93 424	0.00 568	0.00 560	0.02 562	0.11 561	0.00 564	0.00 562	0.02 547	0.00 561	0.02 557

ab-mvs-re		7.68 485	10.24 487	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	92.12 61	0.00 564	0.00 562	0.00 563	0.00 561	0.00 559

uanet		0.00 528	0.00 532	0.00 543	0.00 567	0.00 570	0.00 556	0.00 568	0.00 560	0.00 564	0.00 562	0.00 564	0.00 562	0.00 563	0.00 561	0.00 559

Meshroom													0.00 562
: In preparation.
AliceVision / Meshro													0.00 562
: In preparation.
AliceVision_Meshroom													0.00 562
: In preparation.
PatchmatchNet1														23.45 478	40.77 463	68.54 471
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													67.71 472
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					88.20 37	55.35 66		88.22 66		80.74 29		53.67 46	94.67 21	80.11 59	85.96 38

WAC-MVS						34.28 457								22.56 482

MSC_two_6792asdad				81.53 18	91.77 4	56.03 51		91.10 14					96.22 9	81.46 47	86.80 29	92.34 39

No_MVS				81.53 18	91.77 4	56.03 51		91.10 14					96.22 9	81.46 47	86.80 29	92.34 39

eth-test2					0.00 567

eth-test					0.00 567

OPU-MVS				81.71 15	92.05 3	55.97 53	92.48 3				94.01 11	67.21 2	95.10 16	89.82 3	92.55 3	94.06 4

test_0728_SECOND				82.20 9	89.50 16	57.73 16	92.34 5	88.88 40					96.39 4	81.68 42	87.13 22	92.47 35

GSMVS																88.13 214

test_part2					89.33 24	55.48 59				82.27 13

sam_mvs1												38.86 258				88.13 214

sam_mvs												35.99 315

ambc				62.06 430	53.98 488	29.38 486	35.08 502	79.65 302		41.37 457	59.96 476	6.27 500	82.15 378	35.34 428	38.22 473	74.65 442

MTGPA								81.31 259

test_post1							70.84 429				14.72 525	34.33 339	83.86 360	48.80 358

test_post											16.22 522	37.52 278	84.72 351

patchmatchnet-post											59.74 477	38.41 261	79.91 406

GG-mvs-BLEND				77.77 115	86.68 54	50.61 228	68.67 439	88.45 60		68.73 164	87.45 200	59.15 13	90.67 115	54.83 310	87.67 18	92.03 51

MTMP							87.27 92	15.34 521

test9_res														78.72 70	85.44 46	91.39 80

agg_prior2														75.65 97	85.11 53	91.01 106

agg_prior					85.64 70	54.92 93		83.61 213		72.53 99			88.10 231

test_prior4						56.39 44	87.15 96

test_prior				78.39 98	86.35 59	54.91 96		85.45 135					89.70 156			90.55 124

新几何2							81.61 309

旧先验1					81.57 187	47.48 337		71.83 421			88.66 148	36.94 293			78.34 123	88.67 193

原ACMM2							83.77 233

testdata2													77.81 427	45.64 380

segment_acmp												44.97 168

test12				79.24 53	86.89 52	56.08 50		85.16 152		72.27 103		47.15 111	91.10 96		85.93 40	90.54 126

plane_prior7					77.95 292	48.46 299

plane_prior6					78.42 285	49.39 271						36.04 313

plane_prior5								82.59 231					88.30 224	65.46 197	72.34 221	84.49 295

plane_prior4											83.28 275

plane_prior1					78.31 288

n2								0.00 568

nn								0.00 568

door-mid								41.31 497

lessismore_v0				67.98 381	64.76 462	41.25 430		45.75 490		36.03 477	65.63 457	19.29 456	84.11 358	35.67 424	21.24 502	78.59 398

test11								84.25 193

door								43.27 493

HQP5-MVS						51.56 205

BP-MVS														66.70 183

HQP4-MVS										64.47 223			88.61 203			84.91 291

HQP3-MVS								83.68 208							73.12 209

HQP2-MVS												37.35 281

NP-MVS					78.76 272	50.43 235					85.12 239

ACMMP++_ref															63.20 322

ACMMP++															59.38 355

Test By Simon												39.38 252

High-resolution multi-view benchmark