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.

MSP-MVS		82.30 6	83.47 1	78.80 68	82.99 135	52.71 169	85.04 182	88.63 51	66.08 119	86.77 4	92.75 48	72.05 1	91.46 81	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
DVP-MVS++		82.44 3	82.38 6	82.62 5	91.77 4	57.49 20	84.98 186	88.88 40	58.00 286	83.60 7	93.39 28	67.21 2	96.39 4	81.64 44	91.98 4	93.98 6

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

PC_three_1452									66.58 104	87.27 3	93.70 19	66.82 4	94.95 18	89.74 4	91.98 4	93.98 6

TestfortrainingZip				83.28 1	90.91 7	58.80 11	87.61 74	91.34 11	56.28 332	88.36 1	95.55 1	65.41 5	96.39 4		88.20 15	94.63 3

DPM-MVS		82.39 4	82.36 7	82.49 6	80.12 234	59.50 5	92.24 8	90.72 19	69.37 60	83.22 9	94.47 5	63.81 6	93.18 39	74.02 117	93.25 2	94.80 1

testing915		80.82 13	80.48 15	81.83 13	86.14 61	59.23 8	88.16 60	92.18 1	72.63 14	73.09 88	89.67 128	62.49 7	92.70 48	81.13 51	78.86 116	93.55 10

WBMVS		73.93 139	73.39 131	75.55 196	87.82 42	55.21 72	89.37 39	87.29 84	67.27 89	63.70 236	80.30 322	60.32 8	86.47 303	61.58 235	62.85 327	84.97 289

DELS-MVS		82.32 5	82.50 5	81.79 14	86.80 52	56.89 32	92.77 2	86.30 111	77.83 1	77.88 49	92.13 59	60.24 9	94.78 20	78.97 65	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
dcpmvs_2		79.33 25	78.94 26	80.49 28	89.75 13	56.54 40	84.83 194	83.68 207	67.85 81	69.36 155	90.24 112	60.20 10	92.10 68	84.14 24	80.40 92	92.82 27

baseline2		75.15 114	74.54 113	76.98 145	81.67 177	51.74 200	83.84 230	91.94 4	69.97 50	58.98 301	86.02 224	59.73 11	91.73 75	68.37 172	70.40 248	87.48 229

CSCG		80.41 16	79.72 18	82.49 6	89.12 26	57.67 18	89.29 45	91.54 6	59.19 262	71.82 110	90.05 120	59.72 12	96.04 11	78.37 71	88.40 14	93.75 8

GG-mvs-BLEND				77.77 115	86.68 53	50.61 227	68.67 438	88.45 60		68.73 163	87.45 199	59.15 13	90.67 114	54.83 309	87.67 18	92.03 51

testing3-2		72.30 178	72.35 151	72.15 313	83.07 130	47.64 332	85.46 162	89.81 27	66.17 115	61.96 263	84.88 246	58.93 14	82.27 375	55.87 299	64.97 297	86.54 257

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

gg-mvs-nofinetune		67.43 290	64.53 318	76.13 175	85.95 62	47.79 330	64.38 453	88.28 64	39.34 455	66.62 180	41.27 495	58.69 17	89.00 183	49.64 351	86.62 32	91.59 70

BridgeMVS		80.28 17	79.73 17	81.90 12	86.47 56	59.34 7	80.45 334	89.51 29	69.76 55	71.05 128	86.66 213	58.68 18	93.24 37	84.64 20	90.40 6	93.14 20

UBG		78.86 28	78.86 27	78.86 66	87.80 43	55.43 60	87.67 72	91.21 13	72.83 12	72.10 104	88.40 156	58.53 19	89.08 178	73.21 132	77.98 126	92.08 47

myMVS_eth3d28		77.77 45	77.94 36	77.27 133	87.58 46	52.89 163	86.06 128	91.33 12	74.15 7	68.16 168	88.24 166	58.17 20	88.31 222	69.88 158	77.87 127	90.61 122

MED-MVS		79.56 23	79.39 21	80.06 44	84.34 96	54.93 88	87.61 74	87.22 86	56.22 333	81.85 19	92.98 42	58.11 21	93.75 32	80.19 55	85.96 38	91.52 75

fmvsm_l_mol_unc0.5_1		78.65 29	79.09 25	77.33 128	78.55 280	53.79 131	88.87 51	71.62 426	74.12 8	81.93 16	95.02 3	57.79 22	86.96 282	80.83 52	83.10 65	91.23 92

testing11		79.18 26	78.85 28	80.16 38	88.33 32	56.99 29	88.31 59	92.06 2	72.82 13	70.62 143	88.37 158	57.69 23	92.30 60	75.25 102	76.24 156	91.20 95

MVSMamba_PlusPlus		75.28 108	73.39 131	80.96 24	80.85 209	58.25 13	74.47 395	87.61 81	50.53 391	65.24 201	83.41 271	57.38 24	92.83 43	73.92 119	87.13 22	91.80 63

testing99		78.45 31	77.78 40	80.45 31	88.28 35	56.81 35	87.95 67	91.49 7	71.72 21	70.84 136	88.09 175	57.29 25	92.63 53	69.24 164	75.13 180	91.91 56

CostFormer		73.89 142	72.30 154	78.66 75	82.36 155	56.58 37	75.56 383	85.30 142	66.06 120	70.50 145	76.88 368	57.02 26	89.06 179	68.27 174	68.74 264	90.33 132

test_0728_THIRD									58.00 286	81.91 17	93.64 21	56.54 27	96.44 2	81.64 44	86.86 27	92.23 42

DPE-MVS		79.82 21	79.66 19	80.29 34	89.27 25	55.08 80	88.70 53	87.92 72	55.55 342	81.21 25	93.69 20	56.51 28	94.27 26	78.36 72	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
ETVMVS		75.80 98	75.44 88	76.89 148	86.23 60	50.38 238	85.55 157	91.42 8	71.30 30	68.80 162	87.94 183	56.42 29	89.24 172	56.54 292	74.75 189	91.07 101

DeepPCF-MVS	69.37 1	80.65 14	81.56 11	77.94 111	85.46 74	49.56 260	90.99 21	86.66 102	70.58 40	80.07 34	95.30 2	56.18 30	90.97 105	82.57 37	86.22 37	93.28 15

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

testing91		78.30 38	77.54 43	80.61 26	88.16 38	57.12 28	87.94 68	91.07 17	71.43 26	70.75 138	88.04 180	55.82 32	92.65 50	69.61 159	75.00 185	92.05 50

patch_mono-2		80.84 12	81.59 10	78.62 80	90.34 10	53.77 132	88.08 62	88.36 63	76.17 2	79.40 41	91.09 84	55.43 33	90.09 137	85.01 16	80.40 92	91.99 55

testing222		77.70 47	77.22 50	79.14 57	86.95 50	54.89 97	87.18 93	91.96 3	72.29 16	71.17 126	88.70 146	55.19 34	91.24 89	65.18 202	76.32 154	91.29 88

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 21	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

TSAR-MVS + MP.		78.31 37	78.26 31	78.48 92	81.33 194	56.31 46	81.59 309	86.41 108	69.61 57	81.72 21	88.16 171	55.09 37	88.04 232	74.12 116	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
BP-MVS1		76.09 85	75.55 84	77.71 117	79.49 249	52.27 182	84.70 198	90.49 21	64.44 145	69.86 152	90.31 111	55.05 38	91.35 84	70.07 156	75.58 173	89.53 164

baseline1		72.51 171	72.12 161	73.69 266	85.05 81	44.46 388	83.51 240	86.13 116	71.61 24	64.64 214	87.97 182	55.00 39	89.48 163	59.07 258	56.05 391	87.13 240

test_one_0601					89.39 23	57.29 25		88.09 69	57.21 308	82.06 15	93.39 28	54.94 40

MM		82.69 2	83.29 3	80.89 25	84.38 95	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

TSAR-MVS + GP.		77.82 44	77.59 42	78.49 91	85.25 79	50.27 245	90.02 26	90.57 20	56.58 325	74.26 73	91.60 79	54.26 42	92.16 65	75.87 94	79.91 100	93.05 22

EPP-MVSNet		71.14 203	70.07 205	74.33 243	79.18 260	46.52 356	83.81 231	86.49 106	56.32 331	57.95 324	84.90 245	54.23 43	89.14 177	58.14 272	69.65 254	87.33 233

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 53	93.09 37	54.15 44	95.57 13	85.80 13	85.87 41	93.31 13

alignmvs		78.08 41	77.98 35	78.39 98	83.53 115	53.22 150	89.77 32	85.45 134	66.11 117	76.59 58	91.99 66	54.07 45	89.05 180	77.34 82	77.00 139	92.89 25

test-260524					88.20 37	55.35 66		88.22 66		80.74 29		53.67 46	94.67 21	80.11 58	85.96 38

GDP-MVS		75.27 109	74.38 114	77.95 110	79.04 264	52.86 165	85.22 170	86.19 114	62.43 200	70.66 141	90.40 109	53.51 47	91.60 77	69.25 163	72.68 215	89.39 171

WTY-MVS		77.47 51	77.52 44	77.30 131	88.33 32	46.25 365	88.46 57	90.32 22	71.40 27	72.32 101	91.72 74	53.44 48	92.37 59	66.28 187	75.42 174	93.28 15

FBQ-MVS		78.34 36	77.25 48	81.62 17	86.35 58	59.48 6	86.95 100	90.95 18	72.89 11	71.91 109	87.60 197	53.35 49	92.65 50	70.19 154	75.03 184	92.72 31

IB-MVS	68.87 2	74.01 137	72.03 165	79.94 45	83.04 132	55.50 58	90.24 25	88.65 49	67.14 93	61.38 268	81.74 307	53.21 50	94.28 24	60.45 249	62.41 330	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
HPM-MVS++		80.50 15	80.71 14	79.88 46	87.34 48	55.20 75	89.93 29	87.55 82	66.04 122	79.46 39	93.00 41	53.10 51	91.76 73	80.40 54	89.56 9	92.68 33

miper_enhance_ethall		69.77 236	68.90 226	72.38 307	78.93 268	49.91 251	83.29 251	78.85 320	64.90 141	59.37 293	79.46 333	52.77 52	85.16 343	63.78 214	58.72 359	82.08 349

MVSTER		73.25 155	72.33 152	76.01 179	85.54 72	53.76 133	83.52 236	87.16 89	67.06 97	63.88 231	81.66 308	52.77 52	90.44 124	64.66 207	64.69 303	83.84 316

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 52	93.87 14	52.58 54	93.91 30	84.17 23	87.92 17	92.39 37

FIs		70.00 231	70.24 202	69.30 365	77.93 293	38.55 443	83.99 224	87.72 78	66.86 102	57.66 331	84.17 255	52.28 55	85.31 338	52.72 331	68.80 263	84.02 306

tpm2		70.82 212	68.44 232	77.98 107	80.78 211	56.11 49	74.21 398	81.28 260	60.24 240	68.04 170	75.27 386	52.26 56	88.50 211	55.82 302	68.03 269	89.33 173

thisisatest0515		73.64 149	72.20 157	77.97 108	81.63 180	53.01 159	86.69 113	88.81 45	62.53 196	64.06 226	85.65 228	52.15 57	92.50 55	58.43 265	69.84 251	88.39 208

aaEdge-Enhanced		79.48 24	79.20 24	80.35 33	88.96 27	54.93 88	88.65 54	88.50 59	56.62 322	79.87 36	92.88 45	51.96 58	94.36 23	80.19 55	85.13 51	91.76 64

casdiffmvs_mvg		77.75 46	77.28 47	79.16 56	80.42 228	54.44 117	87.76 69	85.46 133	71.67 23	71.38 121	88.35 161	51.58 59	91.22 90	79.02 64	79.89 102	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
UniMVSNet_NR-MVSNet		68.82 258	68.29 235	70.40 351	75.71 344	42.59 414	84.23 215	86.78 98	66.31 111	58.51 315	82.45 290	51.57 60	84.64 352	53.11 322	55.96 392	83.96 312

PAPM		76.76 67	76.07 74	78.81 67	80.20 232	59.11 9	86.86 106	86.23 112	68.60 68	70.18 150	88.84 144	51.57 60	87.16 276	65.48 195	86.68 31	90.15 141

tttt0517		68.33 270	66.29 282	74.46 236	78.08 288	49.06 274	80.88 327	89.08 36	54.40 360	54.75 369	80.77 317	51.31 62	90.33 128	49.35 353	58.01 371	83.99 308

mvs_anonymous		72.29 179	70.74 185	76.94 147	82.85 142	54.72 106	78.43 365	81.54 254	63.77 164	61.69 265	79.32 335	51.11 63	85.31 338	62.15 231	75.79 164	90.79 116

HY-MVS	67.03 5	73.90 141	73.14 137	76.18 174	84.70 87	47.36 340	75.56 383	86.36 110	66.27 112	70.66 141	83.91 260	51.05 64	89.31 169	67.10 181	72.61 216	91.88 58

thisisatest0530		70.47 222	68.56 228	76.20 172	79.78 243	51.52 206	83.49 242	88.58 57	57.62 297	58.60 314	82.79 279	51.03 65	91.48 80	52.84 326	62.36 332	85.59 280

sasdasda		78.17 39	77.86 38	79.12 59	84.30 99	54.22 121	87.71 70	84.57 185	67.70 85	77.70 50	92.11 62	50.90 66	89.95 141	78.18 75	77.54 131	93.20 17

miper_ehance_all_eth		68.70 264	67.58 253	72.08 315	76.91 320	49.48 266	82.47 281	78.45 335	62.68 194	58.28 323	77.88 349	50.90 66	85.01 346	61.91 232	58.72 359	81.75 354

canonicalmvs		78.17 39	77.86 38	79.12 59	84.30 99	54.22 121	87.71 70	84.57 185	67.70 85	77.70 50	92.11 62	50.90 66	89.95 141	78.18 75	77.54 131	93.20 17

casdiffmvs		77.36 53	76.85 57	78.88 65	80.40 229	54.66 111	87.06 96	85.88 120	72.11 19	71.57 114	88.63 151	50.89 69	90.35 127	76.00 92	79.11 111	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
MGCNet		82.10 7	82.64 4	80.47 30	86.63 54	54.69 108	92.20 9	86.66 102	74.48 5	82.63 11	93.80 17	50.83 70	93.70 34	90.11 2	86.44 34	93.01 23

fmvsm_s_conf0.5_n_9		76.66 70	76.94 56	75.85 184	79.54 248	48.30 306	82.63 273	71.84 419	70.25 44	80.63 31	94.53 4	50.78 71	87.42 266	88.32 5	73.92 197	91.82 62

baseline		76.86 63	76.24 70	78.71 71	80.47 223	54.20 125	83.90 228	84.88 169	71.38 28	71.51 117	89.15 139	50.51 72	90.55 120	75.71 95	78.65 117	91.39 80

TestfortrainingZip a		77.64 48	76.79 61	80.20 36	84.34 96	54.79 101	87.61 74	87.03 91	56.22 333	78.78 42	92.98 42	50.45 73	94.28 24	74.37 111	79.31 109	91.52 75

MVS_Test		75.85 94	74.93 102	78.62 80	84.08 104	55.20 75	83.99 224	85.17 149	68.07 77	73.38 82	82.76 280	50.44 74	89.00 183	65.90 191	80.61 88	91.64 68

FC-MVSNet-test		67.49 288	67.91 241	66.21 399	76.06 335	33.06 464	80.82 328	87.18 88	64.44 145	54.81 367	82.87 277	50.40 75	82.60 373	48.05 364	66.55 282	82.98 340

nrg030		72.27 181	71.56 169	74.42 238	75.93 341	50.60 228	86.97 98	83.21 219	62.75 191	67.15 176	84.38 251	50.07 76	86.66 297	71.19 147	62.37 331	85.99 269

fmvsm_l_conf0.5_n		75.95 90	76.16 72	75.31 209	76.01 339	48.44 299	84.98 186	71.08 430	63.50 173	81.70 22	93.52 24	50.00 77	87.18 275	87.80 6	76.87 143	90.32 133

cl22		68.85 256	67.69 251	72.35 308	78.07 289	49.98 250	82.45 282	78.48 334	62.50 198	58.46 319	77.95 347	49.99 78	85.17 342	62.55 225	58.72 359	81.90 352

fmvsm_l_conf0.5_n_a		75.88 93	76.07 74	75.31 209	76.08 334	48.34 302	85.24 169	70.62 433	63.13 181	81.45 23	93.62 23	49.98 79	87.40 268	87.76 7	76.77 145	90.20 138

tpmrst		71.04 208	69.77 209	74.86 227	83.19 126	55.86 55	75.64 380	78.73 327	67.88 80	64.99 207	73.73 398	49.96 80	79.56 409	65.92 190	67.85 272	89.14 180

CANet		80.90 11	81.17 12	80.09 43	87.62 45	54.21 123	91.60 14	86.47 107	73.13 10	79.89 35	93.10 35	49.88 81	92.98 40	84.09 25	84.75 56	93.08 21

nomal-1		72.45 172	71.14 179	76.37 164	84.65 88	56.28 47	68.39 440	88.28 64	67.21 91	62.98 247	80.23 323	49.71 82	86.05 320	69.36 162	69.48 257	86.78 254

ET-MVSNet_ETH3D		75.23 112	74.08 119	78.67 74	84.52 92	55.59 56	88.92 49	89.21 34	68.06 78	53.13 384	90.22 114	49.71 82	87.62 258	72.12 143	70.82 239	92.82 27

hybridcas		76.66 70	75.99 77	78.65 77	79.25 257	54.46 116	86.82 108	85.53 130	70.88 37	70.40 148	88.21 168	49.55 84	90.12 136	74.42 110	78.88 115	91.37 82

c3_l		67.97 276	66.66 275	71.91 326	76.20 333	49.31 271	82.13 289	78.00 343	61.99 206	57.64 332	76.94 365	49.41 85	84.93 347	60.62 244	57.01 382	81.49 359

Vis-MVSNet (Re-imp)		65.52 327	65.63 299	65.17 409	77.49 304	30.54 474	75.49 386	77.73 350	59.34 257	52.26 391	86.69 212	49.38 86	80.53 396	37.07 415	75.28 176	84.42 297

EPNet		78.36 35	78.49 30	77.97 108	85.49 73	52.04 185	89.36 41	84.07 199	73.22 9	77.03 54	91.72 74	49.32 87	90.17 135	73.46 127	82.77 68	91.69 66
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_l_conf0.5_n_9		77.10 56	77.48 45	75.98 181	77.54 303	47.77 331	86.35 119	73.46 410	68.69 67	81.07 26	94.40 6	49.06 88	88.89 192	87.39 8	79.32 108	91.27 91

testing3		59.97 373	60.19 363	59.32 444	77.60 297	30.01 480	81.75 301	81.79 248	53.54 366	50.34 410	79.94 325	48.99 89	76.91 433	17.19 495	50.59 423	71.03 467

Casviewmamba		76.27 80	75.48 86	78.63 79	79.14 261	54.27 120	85.81 138	83.09 222	70.96 34	70.41 147	88.36 160	48.71 90	90.81 109	75.92 93	76.95 140	90.80 115

E3new		76.85 64	76.24 70	78.66 75	81.62 181	55.01 83	86.94 101	85.10 158	71.55 25	71.93 108	88.61 152	48.40 91	89.60 158	74.50 108	77.53 133	91.36 83

tpm		68.36 268	67.48 258	70.97 342	79.93 237	51.34 210	76.58 377	78.75 326	67.73 83	63.54 243	74.86 388	48.33 92	72.36 461	53.93 316	63.71 311	89.21 177

APDe-MVS		78.44 32	78.20 32	79.19 54	88.56 28	54.55 114	89.76 33	87.77 76	55.91 337	78.56 45	92.49 54	48.20 93	92.65 50	79.49 60	83.04 67	90.39 129
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
fmvsm_s_conf0.5_n_11		76.28 79	76.81 59	74.71 231	79.21 258	46.90 346	85.03 183	73.96 399	69.00 65	79.70 38	93.88 13	48.07 94	87.71 252	84.26 22	78.15 124	89.50 167

MG-MVS		78.42 33	76.99 55	82.73 3	93.17 1	64.46 1	89.93 29	88.51 58	64.83 142	73.52 80	88.09 175	48.07 94	92.19 64	62.24 229	84.53 58	91.53 74

DeepC-MVS	67.15 4	76.90 62	76.27 69	78.80 68	80.70 213	55.02 82	86.39 117	86.71 100	66.96 101	67.91 171	89.97 122	48.03 96	91.41 82	75.60 97	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
viewcassd2359sk11		76.66 70	76.01 76	78.62 80	81.14 197	54.95 86	86.88 105	85.04 160	71.37 29	71.76 111	88.44 155	48.02 97	89.57 160	74.17 115	77.23 135	91.33 87

MGCFI-Net		74.07 136	74.64 112	72.34 309	82.90 139	43.33 406	80.04 343	79.96 289	65.61 125	74.93 65	91.85 70	48.01 98	80.86 388	71.41 146	77.10 136	92.84 26

test_prior2							89.04 48		61.88 209	73.55 79	91.46 83	48.01 98		74.73 105	85.46 45

myMVS_eth3d		63.52 346	63.56 327	63.40 422	81.73 172	34.28 456	80.97 324	81.02 263	60.93 229	55.06 363	82.64 285	48.00 100	80.81 389	23.42 480	58.32 363	75.10 438

balanced_ft_v1		75.25 110	73.90 124	79.29 52	85.59 70	56.72 36	74.35 397	87.27 85	60.24 240	59.07 300	85.17 236	47.76 101	90.51 121	82.62 36	83.06 66	90.64 120

SF-MVS		77.64 48	77.42 46	78.32 101	83.75 112	52.47 174	86.63 115	87.80 73	58.78 274	74.63 68	92.38 56	47.75 102	91.35 84	78.18 75	86.85 28	91.15 98

test2506		72.91 161	72.43 150	74.32 244	80.12 234	44.18 395	83.19 255	84.77 174	64.02 155	65.97 189	87.43 200	47.67 103	88.72 198	59.08 257	79.66 104	90.08 147

E2		76.39 76	75.67 80	78.56 87	80.49 221	54.87 98	86.80 109	84.95 164	71.09 32	71.51 117	88.21 168	47.55 104	89.53 161	73.65 123	76.77 145	91.29 88

E3		76.39 76	75.67 80	78.56 87	80.49 221	54.87 98	86.80 109	84.95 164	71.09 32	71.51 117	88.21 168	47.55 104	89.53 161	73.65 123	76.77 145	91.29 88

fmvsm_s_conf0.5_n_3		74.97 118	75.42 89	73.62 269	76.99 317	46.67 351	83.13 258	71.14 429	66.20 114	82.13 14	93.76 18	47.49 106	84.00 358	81.95 41	76.02 159	90.19 140

1112_ss		70.05 229	69.37 215	72.10 314	80.77 212	42.78 412	85.12 179	76.75 367	59.69 249	61.19 270	92.12 60	47.48 107	83.84 360	53.04 324	68.21 267	89.66 158

fmvsm_s_conf0.5_n_10		76.80 65	76.81 59	76.78 155	78.91 269	47.85 326	83.44 243	74.66 390	68.93 66	81.31 24	94.12 8	47.44 108	90.82 108	83.43 29	79.06 113	91.66 67

Effi-MVS+		75.24 111	73.61 130	80.16 38	81.92 167	57.42 24	85.21 171	76.71 370	60.68 235	73.32 83	89.34 134	47.30 109	91.63 76	68.28 173	79.72 103	91.42 79

UniMVSNet (Re)		67.71 282	66.80 271	70.45 349	74.44 365	42.93 410	82.42 283	84.90 168	63.69 168	59.63 287	80.99 314	47.18 110	85.23 341	51.17 343	56.75 383	83.19 334

test12				79.24 53	86.89 51	56.08 50		85.16 151		72.27 102		47.15 111	91.10 95		85.93 40	90.54 126

PVSNet_Blended_VisFu		73.40 153	72.44 149	76.30 165	81.32 195	54.70 107	85.81 138	78.82 322	63.70 167	64.53 218	85.38 234	47.11 112	87.38 269	67.75 177	77.55 130	86.81 253

fmvsm_s_conf0.5_n_8		76.50 74	76.68 64	75.94 182	78.67 274	47.92 324	85.18 173	74.71 389	68.09 74	80.67 30	94.26 7	47.09 113	89.26 171	86.62 10	74.85 187	90.65 119

test_fmvsm_n_1920		75.56 105	75.54 85	75.61 192	74.60 364	49.51 265	81.82 298	74.08 396	66.52 107	80.40 32	93.46 26	46.95 114	89.72 150	86.69 9	75.30 175	87.61 227

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 77	92.75 48	46.88 115	93.28 36	78.79 68	84.07 61	91.50 78

viewmanbaseed2359cas		76.71 69	76.16 72	78.37 100	81.16 196	55.05 81	86.96 99	85.32 140	71.71 22	72.25 103	88.50 154	46.86 116	88.96 187	74.55 107	78.08 125	91.08 100

E4		75.99 88	75.16 95	78.48 92	79.56 247	54.74 103	86.66 114	84.80 172	70.62 38	71.16 127	87.90 184	46.84 117	89.47 165	72.70 134	76.20 158	91.23 92

fmvsm_s_conf0.5_n_6		76.17 83	76.84 58	74.15 249	77.42 306	46.46 357	85.53 159	77.86 347	69.78 54	79.78 37	92.90 44	46.80 118	84.81 349	84.67 19	76.86 144	91.17 97

9.14			78.19 33		85.67 68		88.32 58	88.84 44	59.89 244	74.58 70	92.62 51	46.80 118	92.66 49	81.40 49	85.62 44

VNet		77.99 43	77.92 37	78.19 104	87.43 47	50.12 246	90.93 22	91.41 9	67.48 88	75.12 63	90.15 118	46.77 120	91.00 100	73.52 125	78.46 120	93.44 11

PVSNet_BlendedMVS		73.42 152	73.30 133	73.76 263	85.91 63	51.83 194	86.18 124	84.24 194	65.40 131	69.09 159	80.86 316	46.70 121	88.13 228	75.43 98	65.92 293	81.33 367

PVSNet_Blended		76.53 73	76.54 65	76.50 161	85.91 63	51.83 194	88.89 50	84.24 194	67.82 82	69.09 159	89.33 136	46.70 121	88.13 228	75.43 98	81.48 81	89.55 162

0.3-1-1-0.015		72.75 165	71.06 181	77.81 113	80.58 218	50.62 226	89.45 37	88.60 55	63.74 166	65.56 197	81.82 305	46.61 123	90.64 117	62.86 223	60.35 343	92.17 45

PRO-TEST		79.94 19	79.98 16	79.81 47	87.63 44	55.24 69	87.59 79	88.40 62	71.10 31	76.93 55	91.92 69	46.57 124	91.41 82	84.32 21	85.41 47	92.79 29

SMA-MVS		79.10 27	78.76 29	80.12 41	84.42 93	55.87 54	87.58 82	86.76 99	61.48 217	80.26 33	93.10 35	46.53 125	92.41 57	79.97 59	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
NormalMVS		77.09 57	77.02 53	77.32 130	81.66 178	52.32 178	89.31 42	82.11 238	72.20 17	73.23 85	91.05 85	46.52 126	91.00 100	76.23 89	80.83 85	88.64 194

SymmetryMVS		77.43 52	77.09 52	78.44 96	82.56 151	52.32 178	89.31 42	84.15 197	72.20 17	73.23 85	91.05 85	46.52 126	91.00 100	76.23 89	78.55 119	92.00 54

viewdifsd2359ckpt07		74.81 122	74.01 122	77.21 137	79.62 245	53.13 155	85.70 152	83.75 205	68.12 73	68.14 169	87.33 203	46.51 128	87.92 235	73.32 128	73.63 201	90.57 123

test_fmvsmconf_n		74.41 128	74.05 120	75.49 201	74.16 372	48.38 300	82.66 271	72.57 414	67.05 98	75.11 64	92.88 45	46.35 129	87.81 242	83.93 26	71.71 227	90.28 134

fmvsm_l_conf0.5_n_3		75.73 103	75.78 78	75.61 192	76.03 337	48.33 304	85.34 163	72.92 413	67.16 92	78.55 46	93.85 16	46.22 130	87.53 262	85.61 14	76.30 155	90.98 108

tpm cat1		66.28 318	62.78 330	76.77 156	81.40 192	57.14 27	70.03 431	77.19 359	53.00 371	58.76 309	70.73 435	46.17 131	86.73 294	43.27 391	64.46 305	86.44 261

fmvsm_s_conf0.5_n_4		74.92 119	74.88 103	75.03 221	75.96 340	47.53 334	85.84 137	73.19 412	67.07 96	79.43 40	92.60 52	46.12 132	88.03 233	84.70 18	69.01 258	89.53 164

cl____		67.43 290	65.93 292	71.95 323	76.33 327	48.02 317	82.58 274	79.12 315	61.30 220	56.72 348	76.92 366	46.12 132	86.44 305	57.98 274	56.31 386	81.38 366

viewdifsd2359ckpt13		75.96 89	75.07 97	78.65 77	81.14 197	55.21 72	86.15 125	84.95 164	69.98 49	70.49 146	88.16 171	46.10 134	89.86 143	72.39 137	76.23 157	90.89 112

DIV-MVS_self_test		67.43 290	65.93 292	71.94 324	76.33 327	48.01 318	82.57 275	79.11 316	61.31 219	56.73 347	76.92 366	46.09 135	86.43 306	57.98 274	56.31 386	81.39 365

0.4-1-1-0.2		72.79 164	71.07 180	77.94 111	80.58 218	50.83 222	89.59 35	88.63 51	63.94 161	65.74 195	81.80 306	46.05 136	90.68 113	62.98 222	60.35 343	92.31 41

IS-MVSNet		68.80 260	67.55 255	72.54 300	78.50 282	43.43 403	81.03 322	79.35 311	59.12 267	57.27 341	86.71 211	46.05 136	87.70 253	44.32 387	75.60 172	86.49 260

diffmvs		75.11 115	74.65 111	76.46 162	78.52 281	53.35 145	83.28 252	79.94 290	70.51 41	71.64 113	88.72 145	46.02 138	86.08 319	77.52 80	75.75 170	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
viewdifsd2359ckpt09		74.92 119	73.70 128	78.60 84	80.28 230	54.94 87	84.77 196	80.56 276	69.96 51	69.38 154	88.38 157	46.01 139	90.50 122	72.44 136	71.49 231	90.38 130

0.4-1-1-0.1		72.39 173	70.70 186	77.46 125	80.45 224	50.04 248	89.09 47	88.45 60	63.06 182	64.91 210	81.60 310	45.98 140	90.46 123	62.40 226	60.34 345	91.88 58

E6new		75.74 99	74.80 107	78.56 87	79.85 238	54.92 93	85.87 133	84.72 177	70.19 45	70.90 132	87.73 191	45.98 140	89.71 151	72.16 139	75.78 167	91.06 102

E6		75.74 99	74.80 107	78.56 87	79.85 238	54.92 93	85.87 133	84.72 177	70.19 45	70.90 132	87.73 191	45.98 140	89.71 151	72.16 139	75.78 167	91.06 102

E5new		75.74 99	74.80 107	78.57 85	79.85 238	54.93 88	85.87 133	84.72 177	70.19 45	70.90 132	87.74 189	45.97 143	89.71 151	72.15 141	75.79 164	91.06 102

E5		75.74 99	74.80 107	78.57 85	79.85 238	54.93 88	85.87 133	84.72 177	70.19 45	70.90 132	87.74 189	45.97 143	89.71 151	72.15 141	75.79 164	91.06 102

blend_shiyan4		67.33 295	65.28 308	73.45 274	70.71 413	47.96 321	86.21 123	85.65 128	56.45 329	52.18 392	72.99 408	45.89 145	88.50 211	56.81 289	60.68 341	83.90 314

EI-MVSNet		69.70 241	68.70 227	72.68 296	75.00 358	48.90 282	79.54 352	87.16 89	61.05 225	63.88 231	83.74 263	45.87 146	90.44 124	57.42 285	64.68 304	78.70 395

IterMVS-LS		66.63 311	65.36 307	70.42 350	75.10 356	48.90 282	81.45 317	76.69 371	61.05 225	55.71 358	77.10 362	45.86 147	83.65 364	57.44 284	57.88 375	78.70 395
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs_AUTHOR		74.80 123	74.30 116	76.29 166	77.34 307	53.19 151	83.17 257	79.50 304	69.93 52	71.55 115	88.57 153	45.85 148	86.03 322	77.17 84	75.64 171	89.67 157

EIA-MVS		75.92 91	75.18 94	78.13 105	85.14 80	51.60 203	87.17 94	85.32 140	64.69 143	68.56 164	90.53 103	45.79 149	91.58 78	67.21 180	82.18 74	91.20 95

MVS		76.91 60	75.48 86	81.23 22	84.56 91	55.21 72	80.23 340	91.64 5	58.65 276	65.37 199	91.48 82	45.72 150	95.05 17	72.11 144	89.52 10	93.44 11

PAPM_NR		71.80 191	69.98 207	77.26 135	81.54 187	53.34 146	78.60 364	85.25 146	53.46 367	60.53 278	88.66 147	45.69 151	89.24 172	56.49 293	79.62 106	89.19 178

UWE-MVS-28		67.43 290	67.98 240	65.75 402	75.66 345	34.74 454	80.00 346	88.17 67	64.21 151	57.27 341	84.14 256	45.68 152	78.82 412	44.33 385	72.40 219	83.70 322

hybridnocas07		74.65 124	74.00 123	76.61 159	77.58 299	52.72 168	83.64 234	79.72 296	69.43 59	70.80 137	88.33 163	45.56 153	87.34 270	76.88 86	74.07 193	89.78 155

viewmambaseed2359dif		73.51 151	72.78 143	75.71 189	76.93 319	51.89 192	82.81 268	79.66 299	65.46 127	70.29 149	88.05 178	45.55 154	85.85 330	73.49 126	72.76 214	89.39 171

CS-MVS		76.77 66	76.70 63	76.99 144	83.55 114	48.75 287	88.60 55	85.18 148	66.38 110	72.47 99	91.62 78	45.53 155	90.99 104	74.48 109	82.51 70	91.23 92

DeepC-MVS_fast	67.50 3	78.00 42	77.63 41	79.13 58	88.52 29	55.12 77	89.95 28	85.98 118	68.31 69	71.33 122	92.75 48	45.52 156	90.37 126	71.15 148	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
fmvsm_s_conf0.5_n		74.48 125	74.12 118	75.56 195	76.96 318	47.85 326	85.32 167	69.80 440	64.16 153	78.74 43	93.48 25	45.51 157	89.29 170	86.48 11	66.62 280	89.55 162

viewmacassd2359aftdt		75.91 92	75.14 96	78.21 103	79.40 251	54.82 100	86.71 112	84.98 162	70.89 36	71.52 116	87.89 185	45.43 158	88.85 196	72.35 138	77.08 137	90.97 109

fmvsm_s_conf0.5_n_5		75.02 116	75.07 97	74.88 226	74.33 369	47.83 328	83.99 224	73.54 405	67.10 94	76.32 59	92.43 55	45.42 159	86.35 309	82.98 32	79.50 107	90.47 128

fmvsm_s_conf0.5_n_a		73.68 148	73.15 135	75.29 212	75.45 348	48.05 316	83.88 229	68.84 445	63.43 175	78.60 44	93.37 30	45.32 160	88.92 191	85.39 15	64.04 307	88.89 186

Test_1112_low_res		67.18 299	66.23 284	70.02 359	78.75 272	41.02 431	83.43 244	73.69 402	57.29 304	58.45 320	82.39 292	45.30 161	80.88 387	50.50 345	66.26 290	88.16 211

ETV-MVS		77.17 55	76.74 62	78.48 92	81.80 170	54.55 114	86.13 126	85.33 139	68.20 72	73.10 87	90.52 104	45.23 162	90.66 115	79.37 61	80.95 82	90.22 136

SPE-MVS-test		77.20 54	77.25 48	77.05 139	84.60 90	49.04 277	89.42 38	85.83 122	65.90 123	72.85 92	91.98 68	45.10 163	91.27 87	75.02 104	84.56 57	90.84 113

NR-MVSNet		67.25 297	65.99 290	71.04 341	73.27 381	43.91 397	85.32 167	84.75 175	66.05 121	53.65 382	82.11 300	45.05 164	85.97 327	47.55 366	56.18 389	83.24 332

UWE-MVS		72.17 182	72.15 159	72.21 311	82.26 156	44.29 392	86.83 107	89.58 28	65.58 126	65.82 192	85.06 239	45.02 165	84.35 354	54.07 314	75.18 177	87.99 218

train_agg		76.91 60	76.40 67	78.45 95	85.68 66	55.42 61	87.59 79	84.00 200	57.84 291	72.99 89	90.98 89	44.99 166	88.58 204	78.19 73	85.32 48	91.34 86

test_8					85.72 65	55.31 67	87.60 78	83.88 203	57.84 291	72.84 93	90.99 88	44.99 166	88.34 219

segment_acmp												44.97 168

hybrid		74.44 127	73.79 127	76.39 163	77.31 309	52.89 163	83.37 250	79.79 294	68.21 71	71.01 129	88.14 173	44.93 169	86.68 295	77.29 83	74.11 192	89.59 160

test_fmvsmconf0.1_n		73.69 147	73.15 135	75.34 207	70.71 413	48.26 307	82.15 287	71.83 420	66.75 103	74.47 72	92.59 53	44.89 170	87.78 249	83.59 28	71.35 234	89.97 150

TEST9					85.68 66	55.42 61	87.59 79	84.00 200	57.72 293	72.99 89	90.98 89	44.87 171	88.58 204

eth_miper_zixun_eth		66.98 306	65.28 308	72.06 316	75.61 346	50.40 235	81.00 323	76.97 366	62.00 205	56.99 345	76.97 364	44.84 172	85.58 333	58.75 262	54.42 405	80.21 383

MVSFormer		73.53 150	72.19 158	77.57 120	83.02 133	55.24 69	81.63 306	81.44 256	50.28 392	76.67 56	90.91 95	44.82 173	86.11 314	60.83 241	80.09 96	91.36 83

lupinMVS		78.38 34	78.11 34	79.19 54	83.02 133	55.24 69	91.57 15	84.82 170	69.12 63	76.67 56	92.02 64	44.82 173	90.23 133	80.83 52	80.09 96	92.08 47

WR-MVS		67.58 285	66.76 272	70.04 358	75.92 342	45.06 385	86.23 122	85.28 144	64.31 148	58.50 317	81.00 313	44.80 175	82.00 380	49.21 355	55.57 397	83.06 337

fmvsm_s_conf0.1_n		73.80 143	73.26 134	75.43 202	73.28 380	47.80 329	84.57 206	69.43 442	63.34 176	78.40 47	93.29 32	44.73 176	89.22 174	85.99 12	66.28 289	89.26 174

viewmamba		73.92 140	73.03 141	76.58 160	77.56 301	52.73 167	82.91 266	78.77 324	69.23 62	68.85 161	88.01 181	44.71 177	87.57 260	73.86 120	73.40 204	89.44 170

ZD-MVS					89.55 15	53.46 138		84.38 188	57.02 310	73.97 75	91.03 87	44.57 178	91.17 92	75.41 101	81.78 79

onestephybrid01		74.31 131	73.65 129	76.27 167	77.58 299	51.99 187	82.22 286	78.44 336	69.26 61	70.95 131	88.11 174	44.46 179	87.30 271	78.01 78	73.86 199	89.51 166

Fast-Effi-MVS+		72.73 166	71.15 178	77.48 123	82.75 145	54.76 102	86.77 111	80.64 272	63.05 183	65.93 190	84.01 257	44.42 180	89.03 181	56.45 296	76.36 153	88.64 194

dtuplus		73.09 158	72.29 155	75.52 200	76.27 331	51.82 196	82.99 264	79.98 287	65.08 140	70.11 151	87.66 195	44.38 181	85.64 332	71.56 145	72.55 217	89.11 181

fmvsm_s_conf0.1_n_a		72.82 163	72.05 163	75.12 218	70.95 411	47.97 319	82.72 270	68.43 447	62.52 197	78.17 48	93.08 38	44.21 182	88.86 193	84.82 17	63.54 314	88.54 202

PCF-MVS	61.03 10	70.10 227	68.40 233	75.22 217	77.15 315	51.99 187	79.30 357	82.12 237	56.47 328	61.88 264	86.48 217	43.98 183	87.24 274	55.37 307	72.79 213	86.43 262
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CDS-MVSNet		70.48 221	69.43 213	73.64 267	77.56 301	48.83 284	83.51 240	77.45 355	63.27 178	62.33 255	85.54 231	43.85 184	83.29 370	57.38 286	74.00 194	88.79 190
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EI-MVSNet-Vis-set		73.19 156	72.60 146	74.99 224	82.56 151	49.80 255	82.55 277	89.00 37	66.17 115	65.89 191	88.98 140	43.83 185	92.29 61	65.38 201	69.01 258	82.87 342

APD-MVS		76.15 84	75.68 79	77.54 122	88.52 29	53.44 141	87.26 92	85.03 161	53.79 364	74.91 66	91.68 76	43.80 186	90.31 129	74.36 112	81.82 77	88.87 187
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_HR		76.39 76	75.38 91	79.42 50	85.33 77	56.47 42	88.15 61	84.97 163	65.15 139	66.06 188	89.88 123	43.79 187	92.16 65	75.03 103	80.03 99	89.64 159

thres100view900		66.87 308	65.42 306	71.24 336	83.29 123	43.15 408	81.67 305	87.78 74	59.04 268	55.92 357	82.18 299	43.73 188	87.80 245	28.80 456	66.36 286	82.78 344

thres600view7		66.46 315	65.12 312	70.47 348	83.41 117	43.80 399	82.15 287	87.78 74	59.37 256	56.02 356	82.21 298	43.73 188	86.90 286	26.51 468	64.94 298	80.71 377

v148		68.24 273	66.35 280	73.88 258	71.76 399	51.47 207	84.23 215	81.90 247	63.69 168	58.94 302	76.44 373	43.72 190	87.78 249	60.63 243	55.86 394	82.39 347

SD-MVS		76.18 82	74.85 104	80.18 37	85.39 75	56.90 31	85.75 143	82.45 234	56.79 318	74.48 71	91.81 71	43.72 190	90.75 111	74.61 106	78.65 117	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
XXY-MVS		70.18 223	69.28 219	72.89 288	77.64 295	42.88 411	85.06 180	87.50 83	62.58 195	62.66 253	82.34 297	43.64 192	89.83 146	58.42 267	63.70 312	85.96 271

tfpn200view9		67.57 286	66.13 286	71.89 327	84.05 105	45.07 382	83.40 246	87.71 79	60.79 232	57.79 328	82.76 280	43.53 193	87.80 245	28.80 456	66.36 286	82.78 344

thres400		67.40 294	66.13 286	71.19 338	84.05 105	45.07 382	83.40 246	87.71 79	60.79 232	57.79 328	82.76 280	43.53 193	87.80 245	28.80 456	66.36 286	80.71 377

PAPR		75.20 113	74.13 117	78.41 97	88.31 34	55.10 79	84.31 213	85.66 126	63.76 165	67.55 173	90.73 100	43.48 195	89.40 166	66.36 186	77.03 138	90.73 117

kuosan		50.20 438	50.09 423	50.52 464	73.09 383	29.09 487	65.25 448	74.89 387	48.27 407	41.34 457	60.85 472	43.45 196	67.48 472	18.59 493	25.07 496	55.01 490

fmvsm_s_conf0.5_n_7		73.10 157	73.89 126	70.72 345	74.17 371	46.03 370	83.28 252	74.19 394	67.10 94	73.94 76	91.73 73	43.42 197	77.61 428	83.92 27	73.26 206	88.53 203

MP-MVS		74.99 117	74.33 115	76.95 146	82.89 140	53.05 158	85.63 153	83.50 213	57.86 290	67.25 175	90.24 112	43.38 198	88.85 196	76.03 91	82.23 73	88.96 184
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
casdiffseed414692147		74.22 132	72.73 144	78.69 72	79.85 238	54.64 112	85.13 175	83.67 211	69.07 64	69.41 153	86.47 218	43.27 199	90.69 112	63.77 215	73.91 198	90.73 117

EI-MVSNet-UG-set		72.37 175	71.73 166	74.29 245	81.60 183	49.29 272	81.85 296	88.64 50	65.29 136	65.05 204	88.29 165	43.18 200	91.83 72	63.74 216	67.97 270	81.75 354

thres200		68.71 262	67.27 263	73.02 282	84.73 86	46.76 350	85.03 183	87.73 77	62.34 201	59.87 282	83.45 270	43.15 201	88.32 221	31.25 448	67.91 271	83.98 310

PHI-MVS		77.49 50	77.00 54	78.95 62	85.33 77	50.69 225	88.57 56	88.59 56	58.14 283	73.60 78	93.31 31	43.14 202	93.79 31	73.81 121	88.53 13	92.37 38

ab-mvs		70.65 217	69.11 222	75.29 212	80.87 208	46.23 368	73.48 404	85.24 147	59.99 243	66.65 179	80.94 315	43.13 203	88.69 199	63.58 217	68.07 268	90.95 110

CDPH-MVS		76.05 87	75.19 93	78.62 80	86.51 55	54.98 85	87.32 87	84.59 184	58.62 277	70.75 138	90.85 97	43.10 204	90.63 118	70.50 152	84.51 59	90.24 135

reproduce_monomvs		69.71 237	68.52 230	73.29 279	86.43 57	48.21 309	83.91 227	86.17 115	68.02 79	54.91 365	77.46 355	42.96 205	88.86 193	68.44 171	48.38 434	82.80 343

v8		67.25 297	64.99 314	74.04 252	72.89 387	53.31 148	82.37 284	80.11 285	61.54 215	54.29 375	76.02 382	42.89 206	88.41 215	58.43 265	56.36 384	80.39 381

EC-MVSNet		75.30 107	75.20 92	75.62 191	80.98 202	49.00 278	87.43 83	84.68 182	63.49 174	70.97 130	90.15 118	42.86 207	91.14 94	74.33 113	81.90 76	86.71 255

h-mvs33		73.95 138	72.89 142	77.15 138	80.17 233	50.37 239	84.68 200	83.33 214	68.08 75	71.97 106	88.65 150	42.50 208	91.15 93	78.82 66	57.78 377	89.91 153

hse-mvs2		71.44 199	70.68 187	73.73 265	76.34 326	47.44 339	79.45 355	79.47 306	68.08 75	71.97 106	86.01 226	42.50 208	86.93 285	78.82 66	53.46 415	86.83 251

SteuartSystems-ACMMP		77.08 58	76.33 68	79.34 51	80.98 202	55.31 67	89.76 33	86.91 94	62.94 185	71.65 112	91.56 80	42.33 210	92.56 54	77.14 85	83.69 63	90.15 141
Skip Steuart: Steuart Systems R&D Blog.
HyFIR lowres test		69.94 234	67.58 253	77.04 140	77.11 316	57.29 25	81.49 316	79.11 316	58.27 281	58.86 306	80.41 319	42.33 210	86.96 282	61.91 232	68.68 265	86.87 245

ZNCC-MVS		75.82 97	75.02 100	78.23 102	83.88 110	53.80 130	86.91 104	86.05 117	59.71 248	67.85 172	90.55 102	42.23 212	91.02 98	72.66 135	85.29 49	89.87 154

FMVSNet3		68.84 257	67.40 259	73.19 281	85.05 81	48.53 294	85.71 149	85.36 137	60.90 231	57.58 333	79.15 338	42.16 213	86.77 292	47.25 369	63.40 315	84.27 301

VPA-MVSNet		71.12 204	70.66 188	72.49 302	78.75 272	44.43 390	87.64 73	90.02 23	63.97 159	65.02 205	81.58 311	42.14 214	87.42 266	63.42 218	63.38 318	85.63 279

jason		77.01 59	76.45 66	78.69 72	79.69 244	54.74 103	90.56 24	83.99 202	68.26 70	74.10 74	90.91 95	42.14 214	89.99 139	79.30 62	79.12 110	91.36 83
jason: jason.
CLD-MVS		75.60 104	75.39 90	76.24 169	80.69 214	52.40 175	90.69 23	86.20 113	74.40 6	65.01 206	88.93 141	42.05 216	90.58 119	76.57 88	73.96 195	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
test_yl		75.85 94	74.83 105	78.91 63	88.08 40	51.94 189	91.30 17	89.28 32	57.91 288	71.19 124	89.20 137	42.03 217	92.77 45	69.41 160	75.07 182	92.01 52

DCV-MVSNet		75.85 94	74.83 105	78.91 63	88.08 40	51.94 189	91.30 17	89.28 32	57.91 288	71.19 124	89.20 137	42.03 217	92.77 45	69.41 160	75.07 182	92.01 52

TAMVS		69.51 245	68.16 238	73.56 271	76.30 329	48.71 290	82.57 275	77.17 360	62.10 203	61.32 269	84.23 254	41.90 219	83.46 367	54.80 311	73.09 210	88.50 205

TransMVSNet (Re)		62.82 354	60.76 356	69.02 367	73.98 374	41.61 425	86.36 118	79.30 314	56.90 311	52.53 387	76.44 373	41.85 220	87.60 259	38.83 408	40.61 465	77.86 409

VPNet		72.07 183	71.42 173	74.04 252	78.64 278	47.17 344	89.91 31	87.97 71	72.56 15	64.66 213	85.04 242	41.83 221	88.33 220	61.17 239	60.97 339	86.62 256

v2v482		69.55 244	67.64 252	75.26 216	72.32 394	53.83 129	84.93 190	81.94 243	65.37 133	60.80 274	79.25 336	41.62 222	88.98 186	63.03 221	59.51 352	82.98 340

API-MVS		74.17 134	72.07 162	80.49 28	90.02 12	58.55 12	87.30 89	84.27 191	57.51 299	65.77 194	87.77 188	41.61 223	95.97 12	51.71 338	82.63 69	86.94 243

GeoE		69.96 233	67.88 245	76.22 170	81.11 200	51.71 201	84.15 218	76.74 369	59.83 245	60.91 272	84.38 251	41.56 224	88.10 230	51.67 339	70.57 242	88.84 188

CHOSEN 1792x2688		76.24 81	74.03 121	82.88 2	83.09 129	62.84 2	85.73 147	85.39 136	69.79 53	64.87 211	83.49 269	41.52 225	93.69 35	70.55 150	81.82 77	92.12 46

LFMVS		78.52 30	77.14 51	82.67 4	89.58 14	58.90 10	91.27 19	88.05 70	63.22 179	74.63 68	90.83 98	41.38 226	94.40 22	75.42 100	79.90 101	94.72 2

MAR-MVS		76.76 67	75.60 83	80.21 35	90.87 8	54.68 109	89.14 46	89.11 35	62.95 184	70.54 144	92.33 57	41.05 227	94.95 18	57.90 278	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
dongtai		43.51 448	44.07 449	41.82 475	63.75 466	21.90 500	63.80 454	72.05 418	39.59 454	33.35 486	54.54 485	41.04 228	57.30 489	10.75 507	17.77 505	46.26 498

test_fmvsmvis_n_1920		71.29 200	70.38 196	74.00 254	71.04 410	48.79 286	79.19 358	64.62 459	62.75 191	66.73 177	91.99 66	40.94 229	88.35 218	83.00 31	73.18 207	84.85 293

GST-MVS		74.87 121	73.90 124	77.77 115	83.30 122	53.45 140	85.75 143	85.29 143	59.22 261	66.50 184	89.85 124	40.94 229	90.76 110	70.94 149	83.35 64	89.10 182

usedtu_dtu_shiyan1		69.05 251	67.91 241	72.46 304	75.40 349	46.24 366	85.74 145	86.80 96	65.23 137	58.75 310	80.31 320	40.90 231	86.83 288	53.29 319	64.77 299	84.31 299

FE-MVSNET3		69.05 251	67.91 241	72.46 304	75.39 350	46.24 366	85.74 145	86.80 96	65.23 137	58.75 310	80.31 320	40.90 231	86.83 288	53.29 319	64.77 299	84.31 299

DU-MVS		66.84 309	65.74 297	70.16 354	73.27 381	42.59 414	81.50 314	82.92 227	63.53 172	58.51 315	82.11 300	40.75 233	84.64 352	53.11 322	55.96 392	83.24 332

Baseline_NR-MVSNet		65.49 329	64.27 322	69.13 366	74.37 368	41.65 424	83.39 248	78.85 320	59.56 251	59.62 288	76.88 368	40.75 233	87.44 265	49.99 347	55.05 399	78.28 404

miper_lstm_enhance		63.91 341	62.30 335	68.75 373	75.06 357	46.78 349	69.02 435	81.14 261	59.68 250	52.76 386	72.39 416	40.71 235	77.99 422	56.81 289	53.09 416	81.48 361

HFP-MVS		74.37 129	73.13 139	78.10 106	84.30 99	53.68 134	85.58 154	84.36 189	56.82 316	65.78 193	90.56 101	40.70 236	90.90 106	69.18 165	80.88 83	89.71 156

RRT-MVS		73.29 154	71.37 174	79.07 61	84.63 89	54.16 126	78.16 366	86.64 104	61.67 212	60.17 280	82.35 296	40.63 237	92.26 63	70.19 154	77.87 127	90.81 114

CL-MVSNet_self_test		62.98 352	61.14 353	68.50 379	65.86 452	42.96 409	84.37 209	82.98 225	60.98 227	53.95 378	72.70 412	40.43 238	83.71 363	41.10 401	47.93 438	78.83 394

ACMMP_NAP		76.43 75	75.66 82	78.73 70	81.92 167	54.67 110	84.06 222	85.35 138	61.10 224	72.99 89	91.50 81	40.25 239	91.00 100	76.84 87	86.98 26	90.51 127

v1144		68.81 259	66.82 270	74.80 229	72.34 393	53.46 138	84.68 200	81.77 250	64.25 150	60.28 279	77.91 348	40.23 240	88.95 188	60.37 250	59.52 351	81.97 350

WR-MVS_H		58.91 385	58.04 377	61.54 435	69.07 435	33.83 461	76.91 373	81.99 242	51.40 384	48.17 419	74.67 389	40.23 240	74.15 448	31.78 445	48.10 436	76.64 424

原ACMM1				76.13 175	84.89 85	54.59 113		85.26 145	51.98 378	66.70 178	87.07 207	40.15 242	89.70 155	51.23 342	85.06 54	84.10 304

MVP-Stereo		70.97 209	70.44 192	72.59 299	76.03 337	51.36 209	85.02 185	86.99 93	60.31 239	56.53 352	78.92 340	40.11 243	90.00 138	60.00 253	90.01 7	76.41 427
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v10		66.61 312	64.20 323	73.83 261	72.59 390	53.37 144	81.88 295	79.91 292	61.11 223	54.09 377	75.60 384	40.06 244	88.26 226	56.47 294	56.10 390	79.86 387

test_fmvsmconf0.01_n		71.97 186	70.95 184	75.04 220	66.21 449	47.87 325	80.35 337	70.08 437	65.85 124	72.69 94	91.68 76	39.99 245	87.67 254	82.03 40	69.66 253	89.58 161

MP-MVS-pluss		75.54 106	75.03 99	77.04 140	81.37 193	52.65 171	84.34 212	84.46 187	61.16 221	69.14 158	91.76 72	39.98 246	88.99 185	78.19 73	84.89 55	89.48 169
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TranMVSNet+NR-MVSNet		66.94 307	65.61 300	70.93 343	73.45 377	43.38 404	83.02 263	84.25 192	65.31 135	58.33 322	81.90 304	39.92 247	85.52 334	49.43 352	54.89 401	83.89 315

Patchmatch-test		53.33 422	48.17 435	68.81 371	73.31 378	42.38 418	42.98 493	58.23 474	32.53 478	38.79 468	70.77 433	39.66 248	73.51 454	25.18 471	52.06 420	90.55 124

viewdifsd2359ckpt11		70.68 215	69.10 223	75.40 203	75.33 352	50.85 220	81.57 310	78.00 343	66.99 99	64.96 208	85.52 232	39.52 249	86.81 290	68.86 168	61.15 338	88.56 200

viewmsd2359difaftdt		70.68 215	69.10 223	75.40 203	75.33 352	50.85 220	81.57 310	78.00 343	66.99 99	64.96 208	85.52 232	39.52 249	86.81 290	68.86 168	61.16 337	88.56 200

Test By Simon												39.38 251

v144192		67.86 278	65.76 296	74.16 248	71.68 400	53.09 156	84.14 219	80.83 269	62.85 190	59.21 298	77.28 359	39.30 252	88.00 234	58.67 263	57.88 375	81.40 364

BH-w/o		70.02 230	68.51 231	74.56 234	82.77 144	50.39 236	86.60 116	78.14 341	59.77 247	59.65 286	85.57 230	39.27 253	87.30 271	49.86 349	74.94 186	85.99 269

dmvs_testset		57.65 396	58.21 376	55.97 456	74.62 363	9.82 518	63.75 455	63.34 465	67.23 90	48.89 417	83.68 268	39.12 254	76.14 440	23.43 478	59.80 350	81.96 351

CR-MVSNet		62.47 360	59.04 372	72.77 292	73.97 375	56.57 38	60.52 468	71.72 422	60.04 242	57.49 336	65.86 453	38.94 255	80.31 398	42.86 395	59.93 347	81.42 362

Patchmtry		56.56 402	52.95 409	67.42 386	72.53 391	50.59 229	59.05 472	71.72 422	37.86 462	46.92 431	65.86 453	38.94 255	80.06 402	36.94 417	46.72 448	71.60 463

sam_mvs1												38.86 257				88.13 214

UA-Net		67.32 296	66.23 284	70.59 347	78.85 270	41.23 430	73.60 402	75.45 383	61.54 215	66.61 181	84.53 250	38.73 258	86.57 302	42.48 398	74.24 191	83.98 310

cdsmvs_eth3d_5k		18.33 477	24.44 469	0.00 543	0.00 566	0.00 569	0.00 555	89.40 30	0.00 559	0.00 563	92.02 64	38.55 259	0.00 561	0.00 562	0.00 560	0.00 559

patchmatchnet-post											59.74 476	38.41 260	79.91 405

CHOSEN 280x420		57.53 398	56.38 390	60.97 440	74.01 373	48.10 314	46.30 488	54.31 481	48.18 409	50.88 407	77.43 357	38.37 261	59.16 487	54.83 309	63.14 323	75.66 431

lecture		74.14 135	73.05 140	77.44 126	81.66 178	50.39 236	87.43 83	84.22 196	51.38 385	72.10 104	90.95 94	38.31 262	93.23 38	70.51 151	80.83 85	88.69 192

SD_0403		65.51 328	65.18 311	66.48 398	78.37 285	29.94 481	74.64 394	78.55 332	66.47 108	54.87 366	84.35 253	38.20 263	82.47 374	38.90 407	72.30 222	87.05 241

V42		67.66 283	65.60 301	73.86 259	70.69 416	53.63 135	81.50 314	78.61 330	63.85 162	59.49 292	77.49 354	37.98 264	87.65 255	62.33 227	58.43 362	80.29 382

tpmvs		62.45 361	59.42 368	71.53 333	83.93 107	54.32 118	70.03 431	77.61 352	51.91 379	53.48 383	68.29 444	37.91 265	86.66 297	33.36 438	58.27 365	73.62 449

PatchmatchNet		67.07 304	63.63 326	77.40 127	83.10 127	58.03 14	72.11 422	77.77 349	58.85 272	59.37 293	70.83 432	37.84 266	84.93 347	42.96 394	69.83 252	89.26 174
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pcd_1.5k_mvsjas		3.15 496	4.20 498	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	0.00 561	37.77 267	0.00 561	0.00 562	0.00 560	0.00 559

PS-MVSNAJss		68.78 261	67.17 265	73.62 269	73.01 384	48.33 304	84.95 189	84.81 171	59.30 260	58.91 305	79.84 328	37.77 267	88.86 193	62.83 224	63.12 324	83.67 324

PS-MVSNAJ		80.06 18	79.52 20	81.68 16	85.58 71	60.97 3	91.69 12	87.02 92	70.62 38	80.75 28	93.22 34	37.77 267	92.50 55	82.75 34	86.25 36	91.57 72

pm-mvs1		64.12 339	62.56 333	68.78 372	71.68 400	38.87 441	82.89 267	81.57 253	55.54 343	53.89 379	77.82 350	37.73 270	86.74 293	48.46 362	53.49 413	80.72 376

RPMNet		59.29 377	54.25 402	74.42 238	73.97 375	56.57 38	60.52 468	76.98 363	35.72 472	57.49 336	58.87 479	37.73 270	85.26 340	27.01 467	59.93 347	81.42 362

IMVS_0403		72.39 173	70.59 190	77.79 114	82.26 156	50.87 216	81.76 299	85.16 151	62.91 186	64.87 211	86.07 220	37.71 272	92.40 58	64.03 210	70.55 243	90.09 143

SDMVSNet		71.89 188	70.62 189	75.70 190	81.70 174	51.61 202	73.89 399	88.72 48	66.58 104	61.64 266	82.38 293	37.63 273	89.48 163	77.44 81	65.60 294	86.01 267

xiu_mvs_v2_base		79.86 20	79.31 22	81.53 18	85.03 83	60.73 4	91.65 13	86.86 95	70.30 43	80.77 27	93.07 39	37.63 273	92.28 62	82.73 35	85.71 42	91.57 72

Patchmatch-RL test		58.72 388	54.32 401	71.92 325	63.91 465	44.25 393	61.73 464	55.19 479	57.38 303	49.31 415	54.24 486	37.60 275	80.89 386	62.19 230	47.28 443	90.63 121

HPM-MVS		72.60 168	71.50 170	75.89 183	82.02 163	51.42 208	80.70 331	83.05 223	56.12 336	64.03 227	89.53 130	37.55 276	88.37 216	70.48 153	80.04 98	87.88 219
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test_post											16.22 521	37.52 277	84.72 350

PatchT		56.60 401	52.97 408	67.48 385	72.94 386	46.16 369	57.30 476	73.78 401	38.77 457	54.37 373	57.26 482	37.52 277	78.06 419	32.02 443	52.79 417	78.23 406

v1192		67.96 277	65.74 297	74.63 233	71.79 398	53.43 143	84.06 222	80.99 267	63.19 180	59.56 289	77.46 355	37.50 279	88.65 200	58.20 271	58.93 358	81.79 353

HQP2-MVS												37.35 280

HQP-MVS		72.34 176	71.44 172	75.03 221	79.02 265	51.56 204	88.00 63	83.68 207	65.45 128	64.48 219	85.13 237	37.35 280	88.62 201	66.70 182	73.12 208	84.91 291

region2R		73.75 145	72.55 147	77.33 128	83.90 109	52.98 160	85.54 158	84.09 198	56.83 315	65.10 203	90.45 105	37.34 282	90.24 132	68.89 167	80.83 85	88.77 191

TESTMET0.1,1		72.86 162	72.33 152	74.46 236	81.98 164	50.77 223	85.13 175	85.47 132	66.09 118	67.30 174	83.69 266	37.27 283	83.57 365	65.06 204	78.97 114	89.05 183

mvsmamba		69.38 246	67.52 257	74.95 225	82.86 141	52.22 183	67.36 444	76.75 367	61.14 222	49.43 413	82.04 302	37.26 284	84.14 356	73.93 118	76.91 141	88.50 205

ACMMPR		73.76 144	72.61 145	77.24 136	83.92 108	52.96 161	85.58 154	84.29 190	56.82 316	65.12 202	90.45 105	37.24 285	90.18 134	69.18 165	80.84 84	88.58 198

MonoMVSNet		66.80 310	64.41 319	73.96 255	76.21 332	48.07 315	76.56 378	78.26 339	64.34 147	54.32 374	74.02 395	37.21 286	86.36 308	64.85 205	53.96 408	87.45 231

sss		70.49 220	70.13 203	71.58 332	81.59 184	39.02 439	80.78 329	84.71 181	59.34 257	66.61 181	88.09 175	37.17 287	85.52 334	61.82 234	71.02 237	90.20 138

reproduce-ours		71.77 193	70.43 193	75.78 186	81.96 165	49.54 263	82.54 278	81.01 265	48.77 404	69.21 156	90.96 91	37.13 288	89.40 166	66.28 187	76.01 160	88.39 208

our_new_method		71.77 193	70.43 193	75.78 186	81.96 165	49.54 263	82.54 278	81.01 265	48.77 404	69.21 156	90.96 91	37.13 288	89.40 166	66.28 187	76.01 160	88.39 208

EPNet_dtu		66.25 319	66.71 273	64.87 411	78.66 277	34.12 459	82.80 269	75.51 381	61.75 210	64.47 222	86.90 208	37.06 290	72.46 460	43.65 390	69.63 255	88.02 217
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v1921920		67.45 289	65.23 310	74.10 251	71.51 403	52.90 162	83.75 233	80.44 277	62.48 199	59.12 299	77.13 360	36.98 291	87.90 237	57.53 283	58.14 369	81.49 359

旧先验1					81.57 186	47.48 336		71.83 420			88.66 147	36.94 292			78.34 122	88.67 193

test-LLR		69.65 242	69.01 225	71.60 330	78.67 274	48.17 310	85.13 175	79.72 296	59.18 264	63.13 245	82.58 287	36.91 293	80.24 399	60.56 245	75.17 178	86.39 263

test0.0.03 1		62.54 357	62.44 334	62.86 427	72.28 396	29.51 484	82.93 265	78.78 323	59.18 264	53.07 385	82.41 291	36.91 293	77.39 429	37.45 411	58.96 357	81.66 357

MDTV_nov1_ep13_2view						43.62 400	71.13 427		54.95 353	59.29 297		36.76 295		46.33 376		87.32 234

KD-MVS_2432*1600		59.04 383	56.44 387	66.86 392	79.07 262	45.87 373	72.13 420	80.42 278	55.03 351	48.15 420	71.01 430	36.73 296	78.05 420	35.21 428	30.18 490	76.67 421

miper_refine_blended		59.04 383	56.44 387	66.86 392	79.07 262	45.87 373	72.13 420	80.42 278	55.03 351	48.15 420	71.01 430	36.73 296	78.05 420	35.21 428	30.18 490	76.67 421

GBi-Net		67.09 302	65.47 303	71.96 320	82.71 146	46.36 359	83.52 236	83.31 215	58.55 278	57.58 333	76.23 377	36.72 298	86.20 310	47.25 369	63.40 315	83.32 329

test1		67.09 302	65.47 303	71.96 320	82.71 146	46.36 359	83.52 236	83.31 215	58.55 278	57.58 333	76.23 377	36.72 298	86.20 310	47.25 369	63.40 315	83.32 329

FMVSNet2		67.57 286	65.79 295	72.90 286	82.71 146	47.97 319	85.15 174	84.93 167	58.55 278	56.71 349	78.26 346	36.72 298	86.67 296	46.15 377	62.94 326	84.07 305

AUN-MVS		68.20 274	66.35 280	73.76 263	76.37 325	47.45 338	79.52 354	79.52 303	60.98 227	62.34 254	86.02 224	36.59 301	86.94 284	62.32 228	53.47 414	86.89 244

reproduce_model		71.07 206	69.67 211	75.28 214	81.51 190	48.82 285	81.73 302	80.57 275	47.81 410	68.26 166	90.78 99	36.49 302	88.60 203	65.12 203	74.76 188	88.42 207

BH-untuned		68.28 271	66.40 279	73.91 257	81.62 181	50.01 249	85.56 156	77.39 356	57.63 296	57.47 338	83.69 266	36.36 303	87.08 278	44.81 382	73.08 211	84.65 294

fmvsm_s_conf0.5_n_2		72.02 184	71.72 167	72.92 285	76.79 321	45.90 371	84.48 207	66.11 453	64.26 149	76.12 60	93.40 27	36.26 304	86.04 321	81.47 46	66.54 283	86.82 252

EPMVS		68.45 267	65.44 305	77.47 124	84.91 84	56.17 48	71.89 424	81.91 246	61.72 211	60.85 273	72.49 413	36.21 305	87.06 279	47.32 368	71.62 228	89.17 179

wanda-best-256-512		64.87 330	62.23 336	72.81 289	70.49 418	46.85 347	85.71 149	85.71 124	56.85 312	51.25 398	72.31 419	36.16 306	87.84 239	52.67 332	48.90 428	83.73 317

FE-blended-shiyan7		64.87 330	62.23 336	72.81 289	70.49 418	46.85 347	85.71 149	85.71 124	56.85 312	51.25 398	72.31 419	36.16 306	87.84 239	52.67 332	48.90 428	83.73 317

usedtu_blend_shiyan5		63.62 345	60.36 361	73.40 275	70.49 418	47.96 321	79.13 359	80.68 271	47.51 414	51.25 398	72.31 419	36.16 306	88.50 211	56.81 289	48.90 428	83.73 317

MSLP-MVS++		74.21 133	72.25 156	80.11 42	81.45 191	56.47 42	86.32 120	79.65 301	58.19 282	66.36 185	92.29 58	36.11 309	90.66 115	67.39 178	82.49 71	93.18 19

FA-MVS(test-final)		69.00 255	66.60 277	76.19 173	83.48 116	47.96 321	74.73 391	82.07 241	57.27 305	62.18 257	78.47 344	36.09 310	92.89 41	53.76 318	71.32 235	87.73 223

MTAPA		72.73 166	71.22 176	77.27 133	81.54 187	53.57 136	67.06 446	81.31 258	59.41 255	68.39 165	90.96 91	36.07 311	89.01 182	73.80 122	82.45 72	89.23 176

HQP_MVS		70.96 210	69.91 208	74.12 250	77.95 291	49.57 257	85.76 141	82.59 230	63.60 170	62.15 259	83.28 274	36.04 312	88.30 223	65.46 196	72.34 220	84.49 295

plane_prior6					78.42 284	49.39 270						36.04 312

sam_mvs												35.99 314

blended_shiyan6		64.70 332	62.04 340	72.69 294	70.34 421	46.60 355	85.48 160	85.65 128	56.59 324	50.91 406	72.18 423	35.82 315	87.81 242	52.46 336	48.90 428	83.66 325

blended_shiyan8		64.70 332	62.04 340	72.69 294	70.33 422	46.62 353	85.48 160	85.66 126	56.58 325	50.94 405	72.18 423	35.81 316	87.80 245	52.47 335	48.91 427	83.65 326

PGM-MVS		72.60 168	71.20 177	76.80 153	82.95 136	52.82 166	83.07 261	82.14 236	56.51 327	63.18 244	89.81 125	35.68 317	89.76 149	67.30 179	80.19 95	87.83 220

icg_test_0407_2		71.26 201	69.99 206	75.09 219	82.26 156	50.87 216	79.65 350	85.16 151	62.91 186	63.68 237	86.07 220	35.56 318	84.32 355	64.03 210	70.55 243	90.09 143

IMVS_0407		71.97 186	70.10 204	77.57 120	82.26 156	50.87 216	80.69 332	85.16 151	62.91 186	63.68 237	86.07 220	35.56 318	91.75 74	64.03 210	70.55 243	90.09 143

XVS		72.92 160	71.62 168	76.81 151	83.41 117	52.48 172	84.88 191	83.20 220	58.03 284	63.91 229	89.63 129	35.50 320	89.78 147	65.50 193	80.50 90	88.16 211

X-MVStestdata		65.85 324	62.20 338	76.81 151	83.41 117	52.48 172	84.88 191	83.20 220	58.03 284	63.91 229	4.82 533	35.50 320	89.78 147	65.50 193	80.50 90	88.16 211

v1240		66.99 305	64.68 316	73.93 256	71.38 407	52.66 170	83.39 248	79.98 287	61.97 207	58.44 321	77.11 361	35.25 322	87.81 242	56.46 295	58.15 367	81.33 367

test1111		71.06 207	70.42 195	72.97 284	79.48 250	41.49 427	84.82 195	82.74 229	64.20 152	62.98 247	87.43 200	35.20 323	87.92 235	58.54 264	78.42 121	89.49 168

dp		64.41 335	61.58 345	72.90 286	82.40 153	54.09 127	72.53 412	76.59 373	60.39 238	55.68 359	70.39 436	35.18 324	76.90 435	39.34 406	61.71 334	87.73 223

Syy-MVS		61.51 366	61.35 350	62.00 431	81.73 172	30.09 478	80.97 324	81.02 263	60.93 229	55.06 363	82.64 285	35.09 325	80.81 389	16.40 497	58.32 363	75.10 438

ECVR-MVS		71.81 190	71.00 183	74.26 246	80.12 234	43.49 401	84.69 199	82.16 235	64.02 155	64.64 214	87.43 200	35.04 326	89.21 175	61.24 238	79.66 104	90.08 147

CP-MVS		72.59 170	71.46 171	76.00 180	82.93 138	52.32 178	86.93 103	82.48 233	55.15 349	63.65 239	90.44 108	35.03 327	88.53 210	68.69 170	77.83 129	87.15 239

fmvsm_s_conf0.1_n_2		71.45 198	71.01 182	72.78 291	75.37 351	45.82 375	84.18 217	64.59 461	64.02 155	75.67 61	93.02 40	34.99 328	85.99 324	81.18 50	66.04 292	86.52 259

CP-MVSNet		58.54 392	57.57 380	61.46 436	68.50 439	33.96 460	76.90 374	78.60 331	51.67 383	47.83 423	76.60 372	34.99 328	72.79 458	35.45 425	47.58 440	77.64 414

guyue		70.53 219	69.12 221	74.76 230	77.61 296	47.53 334	84.86 193	85.17 149	62.70 193	62.18 257	83.74 263	34.72 330	89.86 143	64.69 206	66.38 285	86.87 245

dmvs_re		67.61 284	66.00 289	72.42 306	81.86 169	43.45 402	64.67 452	80.00 286	69.56 58	60.07 281	85.00 243	34.71 331	87.63 256	51.48 340	66.68 278	86.17 266

MDTV_nov1_ep13			61.56 346		81.68 176	55.12 77	72.41 415	78.18 340	59.19 262	58.85 307	69.29 441	34.69 332	86.16 313	36.76 420	62.96 325

SSC-MVS3.2		68.13 275	66.89 267	71.85 328	82.26 156	43.97 396	82.09 290	89.29 31	71.74 20	61.12 271	79.83 329	34.60 333	87.45 264	41.23 400	59.85 349	84.14 302

WB-MVSnew		69.36 247	68.24 236	72.72 293	79.26 256	49.40 269	85.72 148	88.85 43	61.33 218	64.59 217	82.38 293	34.57 334	87.53 262	46.82 373	70.63 240	81.22 371

3Dnovator	64.70 6	74.46 126	72.48 148	80.41 32	82.84 143	55.40 64	83.08 260	88.61 54	67.61 87	59.85 283	88.66 147	34.57 334	93.97 28	58.42 267	88.70 12	91.85 60

VortexMVS		68.49 266	66.84 269	73.46 273	81.10 201	48.75 287	84.63 203	84.73 176	62.05 204	57.22 343	77.08 363	34.54 336	89.20 176	63.08 219	57.12 381	82.43 346

Vis-MVSNet		70.61 218	69.34 216	74.42 238	80.95 207	48.49 296	86.03 130	77.51 354	58.74 275	65.55 198	87.78 187	34.37 337	85.95 328	52.53 334	80.61 88	88.80 189
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_post1							70.84 428				14.72 524	34.33 338	83.86 359	48.80 357

OPM-MVS		70.75 214	69.58 212	74.26 246	75.55 347	51.34 210	86.05 129	83.29 218	61.94 208	62.95 249	85.77 227	34.15 339	88.44 214	65.44 199	71.07 236	82.99 338
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DP-MVS Recon		71.99 185	70.31 198	77.01 142	90.65 9	53.44 141	89.37 39	82.97 226	56.33 330	63.56 242	89.47 131	34.02 340	92.15 67	54.05 315	72.41 218	85.43 282

PEN-MVS		58.35 393	57.15 382	61.94 432	67.55 446	34.39 455	77.01 372	78.35 338	51.87 380	47.72 424	76.73 370	33.91 341	73.75 452	34.03 435	47.17 444	77.68 412

QAPM		71.88 189	69.33 217	79.52 48	82.20 162	54.30 119	86.30 121	88.77 46	56.61 323	59.72 285	87.48 198	33.90 342	95.36 14	47.48 367	81.49 80	88.90 185

新几何1				73.30 278	83.10 127	53.48 137		71.43 427	45.55 430	66.14 186	87.17 205	33.88 343	80.54 395	48.50 360	80.33 94	85.88 274

1314		71.11 205	69.41 214	76.22 170	79.32 254	50.49 231	80.23 340	85.14 157	59.44 254	58.93 303	88.89 143	33.83 344	89.60 158	61.49 236	77.42 134	88.57 199

SR-MVS		70.92 211	69.73 210	74.50 235	83.38 121	50.48 233	84.27 214	79.35 311	48.96 402	66.57 183	90.45 105	33.65 345	87.11 277	66.42 184	74.56 190	85.91 272

mPP-MVS		71.79 192	70.38 196	76.04 178	82.65 149	52.06 184	84.45 208	81.78 249	55.59 341	62.05 262	89.68 127	33.48 346	88.28 225	65.45 198	78.24 123	87.77 222

OMC-MVS		65.97 323	65.06 313	68.71 374	72.97 385	42.58 416	78.61 363	75.35 384	54.72 355	59.31 295	86.25 219	33.30 347	77.88 424	57.99 273	67.05 276	85.66 277

BH-RMVSNet		70.08 228	68.01 239	76.27 167	84.21 103	51.22 214	87.29 90	79.33 313	58.96 271	63.63 240	86.77 210	33.29 348	90.30 131	44.63 384	73.96 195	87.30 235

gbinet_0.2-2-1-0.02		64.20 337	61.39 348	72.63 297	70.85 412	46.32 363	85.92 132	85.98 118	55.27 348	51.88 395	72.29 422	33.14 349	87.82 241	48.50 360	48.72 432	83.73 317

SSM_0407		69.71 237	67.38 260	76.69 158	80.45 224	51.81 197	81.36 318	80.18 282	54.07 362	63.82 233	85.05 240	33.09 350	91.01 99	59.40 254	68.97 260	87.25 236

SSM_0404		70.13 224	67.87 248	76.88 149	80.22 231	52.00 186	81.71 304	80.18 282	54.07 362	65.36 200	85.05 240	33.09 350	91.03 96	59.40 254	71.80 226	87.63 226

JIA-IIPM		52.33 428	47.77 438	66.03 400	71.20 408	46.92 345	40.00 498	76.48 374	37.10 465	46.73 432	37.02 499	32.96 352	77.88 424	35.97 422	52.45 419	73.29 453

PS-CasMVS		58.12 394	57.03 384	61.37 437	68.24 443	33.80 462	76.73 376	78.01 342	51.20 386	47.54 427	76.20 380	32.85 353	72.76 459	35.17 430	47.37 442	77.55 415

DTE-MVSNet		57.03 399	55.73 394	60.95 441	65.94 451	32.57 467	75.71 379	77.09 362	51.16 387	46.65 434	76.34 375	32.84 354	73.22 457	30.94 449	44.87 453	77.06 417

pmmvs4		63.34 349	61.07 354	70.16 354	70.14 424	50.53 230	79.97 347	71.41 428	55.08 350	54.12 376	78.58 342	32.79 355	82.09 379	50.33 346	57.22 380	77.86 409

TR-MVS		69.71 237	67.85 249	75.27 215	82.94 137	48.48 297	87.40 86	80.86 268	57.15 309	64.61 216	87.08 206	32.67 356	89.64 157	46.38 375	71.55 230	87.68 225

VDD-MVS		76.08 86	74.97 101	79.44 49	84.27 102	53.33 147	91.13 20	85.88 120	65.33 134	72.37 100	89.34 134	32.52 357	92.76 47	77.90 79	75.96 162	92.22 44

3Dnovator+	62.71 7	72.29 179	70.50 191	77.65 119	83.40 120	51.29 212	87.32 87	86.40 109	59.01 269	58.49 318	88.32 164	32.40 358	91.27 87	57.04 287	82.15 75	90.38 130

tfpnnormal		61.47 367	59.09 371	68.62 376	76.29 330	41.69 423	81.14 321	85.16 151	54.48 358	51.32 397	73.63 402	32.32 359	86.89 287	21.78 484	55.71 396	77.29 416

MS-PatchMatch		72.34 176	71.26 175	75.61 192	82.38 154	55.55 57	88.00 63	89.95 25	65.38 132	56.51 353	80.74 318	32.28 360	92.89 41	57.95 276	88.10 16	78.39 402

KinetiMVS		71.15 202	69.25 220	76.82 150	77.99 290	50.49 231	85.05 181	86.51 105	59.78 246	64.10 225	85.34 235	32.16 361	91.33 86	58.82 261	73.54 203	88.64 194

v7n		62.50 359	59.27 370	72.20 312	67.25 447	49.83 254	77.87 369	80.12 284	52.50 375	48.80 418	73.07 406	32.10 362	87.90 237	46.83 372	54.92 400	78.86 393

IterMVS		63.77 344	61.67 344	70.08 356	72.68 389	51.24 213	80.44 335	75.51 381	60.51 237	51.41 396	73.70 401	32.08 363	78.91 410	54.30 313	54.35 406	80.08 385
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		59.12 380	58.81 374	60.08 442	70.68 417	45.07 382	80.42 336	74.25 393	43.54 445	50.02 411	73.73 398	31.97 364	56.74 491	51.06 344	53.60 412	78.42 401

SCA		63.84 342	60.01 365	75.32 208	78.58 279	57.92 15	61.61 465	77.53 353	56.71 319	57.75 330	70.77 433	31.97 364	79.91 405	48.80 357	56.36 384	88.13 214

ACMMP		70.81 213	69.29 218	75.39 206	81.52 189	51.92 191	83.43 244	83.03 224	56.67 321	58.80 308	88.91 142	31.92 366	88.58 204	65.89 192	73.39 205	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
mamba_0408		66.33 317	62.87 328	76.70 157	80.45 224	51.81 197	46.11 489	78.90 318	55.46 344	63.82 233	84.54 247	31.91 367	91.03 96	55.68 303	68.97 260	87.25 236

SSM_04072		64.04 340	62.87 328	67.56 384	80.45 224	51.81 197	46.11 489	78.90 318	55.46 344	63.82 233	84.54 247	31.91 367	63.62 476	55.68 303	68.97 260	87.25 236

APD-MVS_3200maxsize		69.62 243	68.23 237	73.80 262	81.58 185	48.22 308	81.91 294	79.50 304	48.21 408	64.24 224	89.75 126	31.91 367	87.55 261	63.08 219	73.85 200	85.64 278

VDDNet		74.37 129	72.13 160	81.09 23	79.58 246	56.52 41	90.02 26	86.70 101	52.61 374	71.23 123	87.20 204	31.75 370	93.96 29	74.30 114	75.77 169	92.79 29

pmmvs5		62.80 355	61.18 352	67.66 383	69.53 431	42.37 419	82.65 272	75.19 385	54.30 361	52.03 393	78.51 343	31.64 371	80.67 391	48.60 359	58.15 367	79.95 386

LCM-MVSNet-Re		58.82 386	56.54 385	65.68 403	79.31 255	29.09 487	61.39 467	45.79 488	60.73 234	37.65 471	72.47 414	31.42 372	81.08 385	49.66 350	70.41 247	86.87 245

AstraMVS		70.12 225	68.56 228	74.81 228	76.48 324	47.48 336	84.35 211	82.58 232	63.80 163	62.09 261	84.54 247	31.39 373	89.96 140	68.24 175	63.58 313	87.00 242

testdata				67.08 390	77.59 298	45.46 379		69.20 443	44.47 438	71.50 120	88.34 162	31.21 374	70.76 466	52.20 337	75.88 163	85.03 287

SR-MVS-dyc-post		68.27 272	66.87 268	72.48 303	80.96 204	48.14 312	81.54 312	76.98 363	46.42 422	62.75 251	89.42 132	31.17 375	86.09 318	60.52 247	72.06 224	83.19 334

GA-MVS		69.04 253	66.70 274	76.06 177	75.11 355	52.36 176	83.12 259	80.23 281	63.32 177	60.65 276	79.22 337	30.98 376	88.37 216	61.25 237	66.41 284	87.46 230

OpenMVS	61.00 11	69.99 232	67.55 255	77.30 131	78.37 285	54.07 128	84.36 210	85.76 123	57.22 307	56.71 349	87.67 194	30.79 377	92.83 43	43.04 393	84.06 62	85.01 288

Effi-MVS+-dtu		66.24 320	64.96 315	70.08 356	75.17 354	49.64 256	82.01 291	74.48 392	62.15 202	57.83 326	76.08 381	30.59 378	83.79 361	65.40 200	60.93 340	76.81 420

sd_testset		67.79 281	65.95 291	73.32 276	81.70 174	46.33 362	68.99 436	80.30 280	66.58 104	61.64 266	82.38 293	30.45 379	87.63 256	55.86 300	65.60 294	86.01 267

test222					79.36 252	50.97 215	77.99 368	67.84 448	42.54 449	62.84 250	86.53 215	30.26 380			76.91 141	85.23 283

MVS_111021_LR		69.07 250	67.91 241	72.54 300	77.27 310	49.56 260	79.77 348	73.96 399	59.33 259	60.73 275	87.82 186	30.19 381	81.53 381	69.94 157	72.19 223	86.53 258

dtuonly		62.58 356	61.91 343	64.58 413	66.49 448	44.72 386	75.64 380	65.78 455	57.26 306	55.48 362	83.93 259	30.08 382	67.36 473	56.40 298	66.10 291	81.67 356

114514_t		69.87 235	67.88 245	75.85 184	88.38 31	52.35 177	86.94 101	83.68 207	53.70 365	55.68 359	85.60 229	30.07 383	91.20 91	55.84 301	71.02 237	83.99 308

CPTT-MVS		67.15 300	65.84 294	71.07 340	80.96 204	50.32 242	81.94 293	74.10 395	46.18 428	57.91 325	87.64 196	29.57 384	81.31 383	64.10 209	70.18 250	81.56 358

CANet_DTU		73.71 146	73.14 137	75.40 203	82.61 150	50.05 247	84.67 202	79.36 310	69.72 56	75.39 62	90.03 121	29.41 385	85.93 329	67.99 176	79.11 111	90.22 136

AdaColmap		67.86 278	65.48 302	75.00 223	88.15 39	54.99 84	86.10 127	76.63 372	49.30 399	57.80 327	86.65 214	29.39 386	88.94 190	45.10 381	70.21 249	81.06 372

RE-MVS-def			66.66 275		80.96 204	48.14 312	81.54 312	76.98 363	46.42 422	62.75 251	89.42 132	29.28 387		60.52 247	72.06 224	83.19 334

CVMVSNet		60.85 370	60.44 359	62.07 429	75.00 358	32.73 466	79.54 352	73.49 406	36.98 466	56.28 355	83.74 263	29.28 387	69.53 469	46.48 374	63.23 320	83.94 313

PMMVS		72.98 159	72.05 163	75.78 186	83.57 113	48.60 291	84.08 220	82.85 228	61.62 213	68.24 167	90.33 110	28.35 389	87.78 249	72.71 133	76.69 148	90.95 110

our_test_3		59.11 381	55.08 398	71.18 339	71.42 405	53.29 149	81.96 292	74.52 391	48.32 406	42.08 451	69.28 442	28.14 390	82.15 377	34.35 434	45.68 452	78.11 407

Fast-Effi-MVS+-dtu		66.53 314	64.10 324	73.84 260	72.41 392	52.30 181	84.73 197	75.66 379	59.51 252	56.34 354	79.11 339	28.11 391	85.85 330	57.74 282	63.29 319	83.35 328

Anonymous20231211		66.08 322	63.67 325	73.31 277	83.07 130	48.75 287	86.01 131	84.67 183	45.27 432	56.54 351	76.67 371	28.06 392	88.95 188	52.78 328	59.95 346	82.23 348

Anonymous20240529		69.71 237	67.28 262	77.00 143	83.78 111	50.36 240	88.87 51	85.10 158	47.22 415	64.03 227	83.37 272	27.93 393	92.10 68	57.78 281	67.44 274	88.53 203

HPM-MVS_fast		67.86 278	66.28 283	72.61 298	80.67 215	48.34 302	81.18 320	75.95 378	50.81 388	59.55 290	88.05 178	27.86 394	85.98 325	58.83 260	73.58 202	83.51 327

FMVSNet1		64.57 334	62.11 339	71.96 320	77.32 308	46.36 359	83.52 236	83.31 215	52.43 376	54.42 372	76.23 377	27.80 395	86.20 310	42.59 397	61.34 336	83.32 329

CNLPA		60.59 371	58.44 375	67.05 391	79.21 258	47.26 342	79.75 349	64.34 463	42.46 450	51.90 394	83.94 258	27.79 396	75.41 445	37.12 413	59.49 353	78.47 399

TAPA-MVS	56.12 14	61.82 365	60.18 364	66.71 394	78.48 283	37.97 446	75.19 388	76.41 375	46.82 418	57.04 344	86.52 216	27.67 397	77.03 432	26.50 469	67.02 277	85.14 286
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
pmmvs6		59.64 375	57.15 382	67.09 389	66.01 450	36.86 450	80.50 333	78.64 328	45.05 434	49.05 416	73.94 396	27.28 398	86.10 316	43.96 389	49.94 425	78.31 403

test-mter		68.36 268	67.29 261	71.60 330	78.67 274	48.17 310	85.13 175	79.72 296	53.38 368	63.13 245	82.58 287	27.23 399	80.24 399	60.56 245	75.17 178	86.39 263

D2MVS		63.49 347	61.39 348	69.77 360	69.29 433	48.93 281	78.89 361	77.71 351	60.64 236	49.70 412	72.10 427	27.08 400	83.48 366	54.48 312	62.65 328	76.90 418

XVG-OURS-SEG-HR		62.02 363	59.54 367	69.46 363	65.30 455	45.88 372	65.06 450	73.57 404	46.45 421	57.42 339	83.35 273	26.95 401	78.09 418	53.77 317	64.03 308	84.42 297

IMVS_0404		69.11 249	67.25 264	74.68 232	82.26 156	50.87 216	76.74 375	85.16 151	62.91 186	50.76 409	86.07 220	26.76 402	83.06 372	64.03 210	70.55 243	90.09 143

test_djsdf		63.84 342	61.56 346	70.70 346	68.78 436	44.69 387	81.63 306	81.44 256	50.28 392	52.27 390	76.26 376	26.72 403	86.11 314	60.83 241	55.84 395	81.29 370

Anonymous20231206		59.08 382	57.59 379	63.55 419	68.77 437	32.14 470	80.26 339	79.78 295	50.00 396	49.39 414	72.39 416	26.64 404	78.36 415	33.12 441	57.94 372	80.14 384

ppachtmachnet_test		58.56 390	54.34 400	71.24 336	71.42 405	54.74 103	81.84 297	72.27 416	49.02 401	45.86 438	68.99 443	26.27 405	83.30 369	30.12 451	43.23 458	75.69 430

test20.03		55.22 410	54.07 403	58.68 448	63.14 470	25.00 493	77.69 370	74.78 388	52.64 373	43.43 445	72.39 416	26.21 406	74.76 447	29.31 454	47.05 446	76.28 428

FE-MVS		64.15 338	60.43 360	75.30 211	80.85 209	49.86 253	68.28 441	78.37 337	50.26 395	59.31 295	73.79 397	26.19 407	91.92 71	40.19 403	66.67 279	84.12 303

FMVSNet5		58.61 389	56.45 386	65.10 410	77.20 314	39.74 435	74.77 390	77.12 361	50.27 394	43.28 447	67.71 446	26.15 408	76.90 435	36.78 419	54.78 402	78.65 397

dtuonlycased		54.12 415	52.39 415	59.30 445	64.31 463	41.80 422	78.63 362	65.85 454	50.56 390	42.00 452	60.21 474	26.14 409	73.31 455	43.06 392	40.73 463	62.79 485

ACMP	61.11 9	66.24 320	64.33 321	72.00 319	74.89 360	49.12 273	83.18 256	79.83 293	55.41 346	52.29 389	82.68 284	25.83 410	86.10 316	60.89 240	63.94 310	80.78 375
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MIMVSNet		63.12 351	60.29 362	71.61 329	75.92 342	46.65 352	65.15 449	81.94 243	59.14 266	54.65 370	69.47 439	25.74 411	80.63 393	41.03 402	69.56 256	87.55 228

LPG-MVS_test		66.44 316	64.58 317	72.02 317	74.42 366	48.60 291	83.07 261	80.64 272	54.69 356	53.75 380	83.83 261	25.73 412	86.98 280	60.33 251	64.71 301	80.48 379

LGP-MVS_train				72.02 317	74.42 366	48.60 291		80.64 272	54.69 356	53.75 380	83.83 261	25.73 412	86.98 280	60.33 251	64.71 301	80.48 379

test_vis1_n_1920		68.59 265	68.31 234	69.44 364	69.16 434	41.51 426	84.63 203	68.58 446	58.80 273	73.26 84	88.37 158	25.30 414	80.60 394	79.10 63	67.55 273	86.23 265

ACMM	58.35 12	64.35 336	62.01 342	71.38 334	74.21 370	48.51 295	82.25 285	79.66 299	47.61 412	54.54 371	80.11 324	25.26 415	86.00 323	51.26 341	63.16 322	79.64 388
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FE-MVSNET2		58.78 387	56.44 387	65.82 401	63.57 468	38.92 440	79.59 351	81.75 252	56.14 335	43.06 449	68.15 445	25.22 416	80.64 392	42.29 399	48.16 435	77.91 408

XVG-OURS		61.88 364	59.34 369	69.49 362	65.37 454	46.27 364	64.80 451	73.49 406	47.04 417	57.41 340	82.85 278	25.15 417	78.18 416	53.00 325	64.98 296	84.01 307

PVSNet_0	57.04 13	61.19 368	57.24 381	73.02 282	77.45 305	50.31 243	79.43 356	77.36 358	63.96 160	47.51 428	72.45 415	25.03 418	83.78 362	52.76 330	19.22 504	84.96 290

WB-MVS		37.41 457	36.37 457	40.54 478	54.23 486	10.43 517	65.29 447	43.75 491	34.86 477	27.81 495	54.63 484	24.94 419	63.21 477	6.81 514	15.00 507	47.98 497

UniMVSNet_ETH3D		62.51 358	60.49 358	68.57 378	68.30 442	40.88 433	73.89 399	79.93 291	51.81 382	54.77 368	79.61 332	24.80 420	81.10 384	49.93 348	61.35 335	83.73 317

DP-MVS		59.24 378	56.12 391	68.63 375	88.24 36	50.35 241	82.51 280	64.43 462	41.10 452	46.70 433	78.77 341	24.75 421	88.57 207	22.26 482	56.29 388	66.96 474

test_cas_vis1_n_1920		67.10 301	66.60 277	68.59 377	65.17 457	43.23 407	83.23 254	69.84 439	55.34 347	70.67 140	87.71 193	24.70 422	76.66 437	78.57 70	64.20 306	85.89 273

LuminaMVS		66.60 313	64.37 320	73.27 280	70.06 427	49.57 257	80.77 330	81.76 251	50.81 388	60.56 277	78.41 345	24.50 423	87.26 273	64.24 208	68.25 266	82.99 338

tt0805		63.39 348	61.31 351	69.64 361	69.36 432	38.87 441	78.00 367	85.48 131	48.82 403	55.66 361	81.66 308	24.38 424	86.37 307	49.04 356	59.36 355	83.68 323

cascas		69.01 254	66.13 286	77.66 118	79.36 252	55.41 63	86.99 97	83.75 205	56.69 320	58.92 304	81.35 312	24.31 425	92.10 68	53.23 321	70.61 241	85.46 281

CMPMVS	40.41 21	55.34 409	52.64 412	63.46 421	60.88 476	43.84 398	61.58 466	71.06 431	30.43 484	36.33 474	74.63 390	24.14 426	75.44 444	48.05 364	66.62 280	71.12 466
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UGNet		68.71 262	67.11 266	73.50 272	80.55 220	47.61 333	84.08 220	78.51 333	59.45 253	65.68 196	82.73 283	23.78 427	85.08 345	52.80 327	76.40 149	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
YYNet1		53.82 418	49.96 424	65.41 407	70.09 426	48.95 279	72.30 416	71.66 424	44.25 441	31.89 488	63.07 463	23.73 428	73.95 450	33.26 439	39.40 470	73.34 451

MDA-MVSNet_test_wron		53.82 418	49.95 425	65.43 406	70.13 425	49.05 275	72.30 416	71.65 425	44.23 442	31.85 489	63.13 462	23.68 429	74.01 449	33.25 440	39.35 471	73.23 454

PLC	52.38 18	60.89 369	58.97 373	66.68 396	81.77 171	45.70 377	78.96 360	74.04 398	43.66 444	47.63 425	83.19 276	23.52 430	77.78 427	37.47 410	60.46 342	76.55 426
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SSC-MVS		35.20 459	34.30 461	37.90 480	52.58 488	8.65 520	61.86 463	41.64 495	31.81 482	25.54 498	52.94 490	23.39 431	59.28 486	6.10 516	12.86 509	45.78 500

ADS-MVSNet2		55.21 411	51.44 417	66.51 397	80.60 216	49.56 260	55.03 480	65.44 456	44.72 436	51.00 402	61.19 470	22.83 432	75.41 445	28.54 459	53.63 410	74.57 443

ADS-MVSNet		56.17 405	51.95 416	68.84 369	80.60 216	53.07 157	55.03 480	70.02 438	44.72 436	51.00 402	61.19 470	22.83 432	78.88 411	28.54 459	53.63 410	74.57 443

test_0402		56.45 403	53.03 407	66.69 395	76.78 322	50.31 243	81.76 299	69.61 441	42.79 448	43.88 442	72.13 425	22.82 434	86.46 304	16.57 496	50.94 422	63.31 483

UnsupCasMVSNet_eth		57.56 397	55.15 396	64.79 412	64.57 462	33.12 463	73.17 407	83.87 204	58.98 270	41.75 455	70.03 437	22.54 435	79.92 403	46.12 378	35.31 477	81.32 369

xiu_mvs_v1_base_debu		71.60 195	70.29 199	75.55 196	77.26 311	53.15 152	85.34 163	79.37 307	55.83 338	72.54 95	90.19 115	22.38 436	86.66 297	73.28 129	76.39 150	86.85 248

xiu_mvs_v1_base		71.60 195	70.29 199	75.55 196	77.26 311	53.15 152	85.34 163	79.37 307	55.83 338	72.54 95	90.19 115	22.38 436	86.66 297	73.28 129	76.39 150	86.85 248

xiu_mvs_v1_base_debi		71.60 195	70.29 199	75.55 196	77.26 311	53.15 152	85.34 163	79.37 307	55.83 338	72.54 95	90.19 115	22.38 436	86.66 297	73.28 129	76.39 150	86.85 248

LS3D		56.40 404	53.82 404	64.12 415	81.12 199	45.69 378	73.42 405	66.14 452	35.30 476	43.24 448	79.88 326	22.18 439	79.62 408	19.10 491	64.00 309	67.05 473

PVSNet	62.49 8	69.27 248	67.81 250	73.64 267	84.41 94	51.85 193	84.63 203	77.80 348	66.42 109	59.80 284	84.95 244	22.14 440	80.44 397	55.03 308	75.11 181	88.62 197

MDA-MVSNet-bldmvs		51.56 431	47.75 439	63.00 424	71.60 402	47.32 341	69.70 434	72.12 417	43.81 443	27.65 496	63.38 461	21.97 441	75.96 441	27.30 466	32.19 485	65.70 479

pmmvs-eth3d		55.97 407	52.78 411	65.54 405	61.02 475	46.44 358	75.36 387	67.72 449	49.61 398	43.65 444	67.58 447	21.63 442	77.04 431	44.11 388	44.33 454	73.15 455

anonymousdsp		60.46 372	57.65 378	68.88 368	63.63 467	45.09 381	72.93 408	78.63 329	46.52 420	51.12 401	72.80 411	21.46 443	83.07 371	57.79 280	53.97 407	78.47 399

MVS-HIRNet		49.01 440	44.71 444	61.92 433	76.06 335	46.61 354	63.23 458	54.90 480	24.77 491	33.56 483	36.60 501	21.28 444	75.88 443	29.49 453	62.54 329	63.26 484

Anonymous202405211		70.11 226	67.88 245	76.79 154	87.20 49	47.24 343	89.49 36	77.38 357	54.88 354	66.14 186	86.84 209	20.93 445	91.54 79	56.45 296	71.62 228	91.59 70

FE-MVSNET		51.43 432	48.22 434	61.06 439	60.78 477	32.48 468	73.85 401	64.62 459	46.30 427	37.47 472	66.27 451	20.80 446	77.38 430	23.43 478	40.48 466	73.31 452

UnsupCasMVSNet_bld		53.86 417	50.53 421	63.84 416	63.52 469	34.75 453	71.38 425	81.92 245	46.53 419	38.95 467	57.93 480	20.55 447	80.20 401	39.91 405	34.09 484	76.57 425

Elysia		65.59 325	62.65 331	74.42 238	69.85 428	49.46 267	80.04 343	82.11 238	46.32 425	58.74 312	79.64 330	20.30 448	88.57 207	55.48 305	71.37 232	85.22 284

StellarMVS		65.59 325	62.65 331	74.42 238	69.85 428	49.46 267	80.04 343	82.11 238	46.32 425	58.74 312	79.64 330	20.30 448	88.57 207	55.48 305	71.37 232	85.22 284

EU-MVSNet		52.63 424	50.72 420	58.37 449	62.69 472	28.13 490	72.60 411	75.97 377	30.94 483	40.76 462	72.11 426	20.16 450	70.80 465	35.11 431	46.11 450	76.19 429

N_pmnet		41.25 450	39.77 453	45.66 471	68.50 439	0.82 541	72.51 413	0.38 539	35.61 473	35.26 478	61.51 469	20.07 451	67.74 470	23.51 476	40.63 464	68.42 472

MSDG		59.44 376	55.14 397	72.32 310	74.69 361	50.71 224	74.39 396	73.58 403	44.44 439	43.40 446	77.52 353	19.45 452	90.87 107	31.31 447	57.49 379	75.38 433

tt0320		52.45 426	48.75 430	63.55 419	71.47 404	41.85 421	72.42 414	59.73 472	36.33 471	44.52 439	61.55 468	19.34 453	76.45 439	33.53 436	39.85 468	72.36 458

K. test v3		54.04 416	49.42 429	67.92 382	68.55 438	42.57 417	75.51 385	63.07 466	52.07 377	39.21 465	64.59 459	19.34 453	82.21 376	37.11 414	25.31 495	78.97 392

lessismore_v0				67.98 381	64.76 461	41.25 429		45.75 489		36.03 476	65.63 456	19.29 455	84.11 357	35.67 423	21.24 501	78.59 398

KD-MVS_self_test		49.24 439	46.85 441	56.44 454	54.32 485	22.87 496	57.39 475	73.36 411	44.36 440	37.98 470	59.30 478	18.97 456	71.17 464	33.48 437	42.44 459	75.26 435

OpenMVS_ROB	53.19 17	59.20 379	56.00 392	68.83 370	71.13 409	44.30 391	83.64 234	75.02 386	46.42 422	46.48 435	73.03 407	18.69 457	88.14 227	27.74 464	61.80 333	74.05 446

mvsany_test1		43.38 449	42.57 451	45.82 470	50.96 494	26.10 492	55.80 478	27.74 511	27.15 488	47.41 429	74.39 392	18.67 458	44.95 503	44.66 383	36.31 475	66.40 476

LTVRE_ROB	45.45 19	52.73 423	49.74 427	61.69 434	69.78 430	34.99 452	44.52 491	67.60 450	43.11 447	43.79 443	74.03 394	18.54 459	81.45 382	28.39 461	57.94 372	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
SixPastTwentyTwo		54.37 412	50.10 422	67.21 388	70.70 415	41.46 428	74.73 391	64.69 458	47.56 413	39.12 466	69.49 438	18.49 460	84.69 351	31.87 444	34.20 483	75.48 432

new-patchmatchnet		48.21 441	46.55 442	53.18 460	57.73 481	18.19 510	70.24 429	71.02 432	45.70 429	33.70 482	60.23 473	18.00 461	69.86 468	27.97 463	34.35 481	71.49 465

tt0320-xc		52.22 429	48.38 433	63.75 418	72.19 397	42.25 420	72.19 419	57.59 476	37.24 464	44.41 440	61.56 467	17.90 462	75.89 442	35.60 424	36.73 474	73.12 456

F-COLMAP		55.96 408	53.65 406	62.87 426	72.76 388	42.77 413	74.70 393	70.37 435	40.03 453	41.11 460	79.36 334	17.77 463	73.70 453	32.80 442	53.96 408	72.15 459

sc_t1		53.51 421	49.92 426	64.29 414	70.33 422	39.55 438	72.93 408	59.60 473	38.74 458	47.16 430	66.47 450	17.59 464	76.50 438	36.83 418	39.62 469	76.82 419

jajsoiax		63.21 350	60.84 355	70.32 352	68.33 441	44.45 389	81.23 319	81.05 262	53.37 369	50.96 404	77.81 351	17.49 465	85.49 336	59.31 256	58.05 370	81.02 373

RPSCF		45.77 446	44.13 448	50.68 462	57.67 482	29.66 483	54.92 482	45.25 490	26.69 489	45.92 437	75.92 383	17.43 466	45.70 502	27.44 465	45.95 451	76.67 421

mmtdpeth		57.93 395	54.78 399	67.39 387	72.32 394	43.38 404	72.72 410	68.93 444	54.45 359	56.85 346	62.43 464	17.02 467	83.46 367	57.95 276	30.31 489	75.31 434

PatchMatch-RL		56.66 400	53.75 405	65.37 408	77.91 294	45.28 380	69.78 433	60.38 470	41.35 451	47.57 426	73.73 398	16.83 468	76.91 433	36.99 416	59.21 356	73.92 447

mvs_tets		62.96 353	60.55 357	70.19 353	68.22 444	44.24 394	80.90 326	80.74 270	52.99 372	50.82 408	77.56 352	16.74 469	85.44 337	59.04 259	57.94 372	80.89 374

ACMH+	54.58 15	58.55 391	55.24 395	68.50 379	74.68 362	45.80 376	80.27 338	70.21 436	47.15 416	42.77 450	75.48 385	16.73 470	85.98 325	35.10 432	54.78 402	73.72 448

ACMH	53.70 16	59.78 374	55.94 393	71.28 335	76.59 323	48.35 301	80.15 342	76.11 376	49.74 397	41.91 454	73.45 405	16.50 471	90.31 129	31.42 446	57.63 378	75.17 436
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MIMVSNet1		50.35 437	47.81 437	57.96 450	61.53 474	27.80 491	67.40 443	74.06 397	43.25 446	33.31 487	65.38 458	16.03 472	71.34 463	21.80 483	47.55 441	74.75 440

DSMNet-mixed		38.35 454	35.36 459	47.33 469	48.11 500	14.91 514	37.87 499	36.60 502	19.18 496	34.37 480	59.56 477	15.53 473	53.01 495	20.14 489	46.89 447	74.07 445

EG-PatchMatch MVS		62.40 362	59.59 366	70.81 344	73.29 379	49.05 275	85.81 138	84.78 173	51.85 381	44.19 441	73.48 404	15.52 474	89.85 145	40.16 404	67.24 275	73.54 450

testgi		54.25 414	52.57 413	59.29 446	62.76 471	21.65 502	72.21 418	70.47 434	53.25 370	41.94 453	77.33 358	14.28 475	77.95 423	29.18 455	51.72 421	78.28 404

COLMAP_ROB	43.60 20	50.90 435	48.05 436	59.47 443	67.81 445	40.57 434	71.25 426	62.72 468	36.49 469	36.19 475	73.51 403	13.48 476	73.92 451	20.71 486	50.26 424	63.92 482
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		52.39 427	48.73 431	63.35 423	65.21 456	38.42 444	68.54 439	64.95 457	38.19 459	39.57 464	71.43 429	13.23 477	79.92 403	37.16 412	40.32 467	71.72 462

usedtu_dtu_shiyan2		50.47 436	46.43 443	62.61 428	51.66 491	31.70 473	75.62 382	75.65 380	36.36 470	34.89 479	56.91 483	12.01 478	78.40 414	30.87 450	43.86 455	77.72 411

MVStest1		38.35 454	34.53 460	49.82 466	51.43 492	30.41 475	50.39 484	55.25 478	17.56 499	26.45 497	65.85 455	11.72 479	57.00 490	14.79 498	17.31 506	62.05 486

test_fmvs1		53.60 420	52.54 414	56.78 452	58.07 479	30.26 476	68.95 437	42.19 494	32.46 479	63.59 241	82.56 289	11.55 480	60.81 481	58.25 270	55.27 398	79.28 389

tmp_tt		9.44 482	10.68 485	5.73 505	2.49 536	4.21 526	10.48 515	18.04 518	0.34 529	12.59 510	20.49 517	11.39 481	7.03 523	13.84 501	6.46 516	5.95 524

ITE_SJBPF				51.84 461	58.03 480	31.94 472		53.57 484	36.67 467	41.32 458	75.23 387	11.17 482	51.57 496	25.81 470	48.04 437	72.02 461

Anonymous20240521		51.65 430	48.42 432	61.34 438	56.43 484	39.65 437	73.57 403	73.47 409	36.64 468	36.59 473	63.98 460	10.75 483	72.25 462	35.35 426	49.01 426	72.11 460

mvs5depth		50.97 434	46.98 440	62.95 425	56.63 483	34.23 458	62.73 462	67.35 451	45.03 435	48.00 422	65.41 457	10.40 484	79.88 407	36.00 421	31.27 488	74.73 441

AllTest		47.32 443	44.66 445	55.32 458	65.08 458	37.50 448	62.96 460	54.25 482	35.45 474	33.42 484	72.82 409	9.98 485	59.33 484	24.13 474	43.84 456	69.13 468

TestCases				55.32 458	65.08 458	37.50 448		54.25 482	35.45 474	33.42 484	72.82 409	9.98 485	59.33 484	24.13 474	43.84 456	69.13 468

USDC		54.36 413	51.23 418	63.76 417	64.29 464	37.71 447	62.84 461	73.48 408	56.85 312	35.47 477	71.94 428	9.23 487	78.43 413	38.43 409	48.57 433	75.13 437

XVG-ACMP-BASELINE		56.03 406	52.85 410	65.58 404	61.91 473	40.95 432	63.36 456	72.43 415	45.20 433	46.02 436	74.09 393	9.20 488	78.12 417	45.13 380	58.27 365	77.66 413

test_fmvs1_n		52.55 425	51.19 419	56.65 453	51.90 490	30.14 477	67.66 442	42.84 493	32.27 480	62.30 256	82.02 303	9.12 489	60.84 480	57.82 279	54.75 404	78.99 391

test_vis1_n		51.19 433	49.66 428	55.76 457	51.26 493	29.85 482	67.20 445	38.86 498	32.12 481	59.50 291	79.86 327	8.78 490	58.23 488	56.95 288	52.46 418	79.19 390

pmmvs3		45.53 447	41.55 452	57.44 451	48.97 498	39.68 436	70.06 430	57.66 475	28.32 487	34.06 481	57.29 481	8.50 491	66.85 474	34.86 433	34.26 482	65.80 478

EGC-MVSNET		33.75 461	30.42 465	43.75 474	64.94 460	36.21 451	60.47 470	40.70 497	0.02 558	0.10 555	53.79 487	7.39 492	60.26 482	11.09 505	35.23 479	34.79 502

test_fmvs2		45.89 445	44.32 447	50.62 463	45.85 502	24.70 494	58.87 474	37.84 501	25.22 490	52.46 388	74.56 391	7.07 493	54.69 492	49.28 354	47.70 439	72.48 457

ANet_high		34.39 460	29.59 466	48.78 467	30.34 512	22.28 498	55.53 479	63.79 464	38.11 460	15.47 505	36.56 502	6.94 494	59.98 483	13.93 500	5.64 517	64.08 481

FPMVS		35.40 458	33.67 462	40.57 477	46.34 501	28.74 489	41.05 495	57.05 477	20.37 495	22.27 500	53.38 488	6.87 495	44.94 504	8.62 508	47.11 445	48.01 496

test_vis1_rt		40.29 453	38.64 454	45.25 472	48.91 499	30.09 478	59.44 471	27.07 512	24.52 492	38.48 469	51.67 491	6.71 496	49.44 497	44.33 385	46.59 449	56.23 488

new_pmnet		33.56 462	31.89 464	38.59 479	49.01 497	20.42 503	51.01 483	37.92 500	20.58 493	23.45 499	46.79 493	6.66 497	49.28 499	20.00 490	31.57 487	46.09 499

TinyColmap		48.15 442	44.49 446	59.13 447	65.73 453	38.04 445	63.34 457	62.86 467	38.78 456	29.48 491	67.23 449	6.46 498	73.30 456	24.59 473	41.90 461	66.04 477

ambc				62.06 430	53.98 487	29.38 485	35.08 501	79.65 301		41.37 456	59.96 475	6.27 499	82.15 377	35.34 427	38.22 472	74.65 442

TDRefinement		40.91 451	38.37 455	48.55 468	50.45 495	33.03 465	58.98 473	50.97 485	28.50 485	29.89 490	67.39 448	6.21 500	54.51 493	17.67 494	35.25 478	58.11 487

ttmdpeth		40.58 452	37.50 456	49.85 465	49.40 496	22.71 497	56.65 477	46.78 486	28.35 486	40.29 463	69.42 440	5.35 501	61.86 479	20.16 488	21.06 502	64.96 480

PM-MVS		46.92 444	43.76 450	56.41 455	52.18 489	32.26 469	63.21 459	38.18 499	37.99 461	40.78 461	66.20 452	5.09 502	65.42 475	48.19 363	41.99 460	71.54 464

LF4IMVS		33.04 463	32.55 463	34.52 483	40.96 503	22.03 499	44.45 492	35.62 503	20.42 494	28.12 494	62.35 465	5.03 503	31.88 515	21.61 485	34.42 480	49.63 495

EMVS		18.42 476	17.66 480	20.71 494	34.13 509	12.64 516	46.94 487	29.94 509	10.46 509	5.58 523	14.93 523	4.23 504	38.83 507	5.24 520	7.51 514	10.67 518

E-PMN		19.16 475	18.40 479	21.44 493	36.19 507	13.63 515	47.59 486	30.89 507	10.73 507	5.91 521	16.59 520	3.66 505	39.77 506	5.95 517	8.14 512	10.92 517

test_method		24.09 472	21.07 476	33.16 486	27.67 516	8.35 523	26.63 507	35.11 505	3.40 517	14.35 506	36.98 500	3.46 506	35.31 510	19.08 492	22.95 498	55.81 489

mvsany_test3		28.00 465	25.98 467	34.05 484	28.97 513	15.31 512	34.54 502	18.17 517	16.24 500	29.30 492	53.37 489	2.79 507	33.38 514	30.01 452	20.41 503	53.45 492

test_f		27.12 467	24.85 468	33.93 485	26.17 518	15.25 513	30.24 506	22.38 516	12.53 505	28.23 493	49.43 492	2.59 508	34.34 513	25.12 472	26.99 493	52.20 493

test_fmvs3		37.95 456	35.75 458	44.55 473	35.50 508	18.92 506	48.32 485	34.00 506	18.36 498	41.31 459	61.58 466	2.29 509	48.06 501	42.72 396	37.71 473	66.66 475

PMMVS2		26.71 468	22.98 473	37.87 481	36.89 506	8.51 521	42.51 494	29.32 510	19.09 497	13.01 508	37.54 498	2.23 510	53.11 494	14.54 499	11.71 510	51.99 494

Gipuma		27.47 466	24.26 471	37.12 482	60.55 478	29.17 486	11.68 513	60.00 471	14.18 502	10.52 514	15.12 522	2.20 511	63.01 478	8.39 509	35.65 476	19.18 510
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		28.07 464	23.85 472	40.71 476	27.46 517	18.93 505	30.82 505	46.19 487	12.76 504	16.40 502	34.70 504	1.90 512	48.69 500	20.25 487	24.22 497	54.51 491

DeepMVS_CX				13.10 497	21.34 520	8.99 519		10.02 522	10.59 508	7.53 518	30.55 508	1.82 513	14.55 516	6.83 513	7.52 513	15.75 512

VLMVS		5.96 489	6.29 492	4.99 506	5.31 529	1.01 536	4.24 523	0.93 529	0.06 542	8.90 515	26.22 512	1.69 514	1.62 533	3.76 526	5.49 518	12.33 514

APD_test1		26.46 469	24.41 470	32.62 488	37.58 505	21.74 501	40.50 497	30.39 508	11.45 506	16.33 503	43.76 494	1.63 515	41.62 505	11.24 504	26.82 494	34.51 503

VLMVS_CLIP		11.28 481	11.90 484	9.42 500	7.54 525	3.26 528	13.10 512	10.36 521	1.51 523	15.95 504	32.54 507	1.51 516	12.70 518	10.98 506	13.62 508	12.29 515

PMVS	19.57 22	25.07 470	22.43 475	32.99 487	23.12 519	22.98 495	40.98 496	35.19 504	15.99 501	11.95 513	35.87 503	1.47 517	49.29 498	5.41 519	31.90 486	26.70 509
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		24.79 471	22.95 474	30.31 489	28.59 514	18.92 506	37.43 500	17.27 519	12.90 503	21.28 501	29.92 509	1.02 518	36.35 508	28.28 462	29.82 492	35.65 501

MVE	16.60 23	17.34 478	13.39 481	29.16 490	28.43 515	19.72 504	13.73 511	23.63 515	7.23 512	7.96 517	21.41 515	0.80 519	36.08 509	6.97 512	10.39 511	31.69 504
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testf1		21.11 473	19.08 477	27.18 491	30.56 510	18.28 508	33.43 503	24.48 513	8.02 510	12.02 511	33.50 505	0.75 520	35.09 511	7.68 510	21.32 499	28.17 506

APD_test2		21.11 473	19.08 477	27.18 491	30.56 510	18.28 508	33.43 503	24.48 513	8.02 510	12.02 511	33.50 505	0.75 520	35.09 511	7.68 510	21.32 499	28.17 506

MVS_clip		3.10 497	3.65 500	1.44 513	3.78 532	1.17 535	2.78 524	0.19 543	0.20 532	4.48 527	14.54 525	0.35 522	0.47 539	2.92 527	3.64 522	2.67 529

ArgMatch-Sym		13.78 479	13.16 482	15.65 496	13.75 521	8.38 522	21.56 508	2.56 524	7.09 513	14.16 507	40.67 496	0.28 523	11.85 520	13.55 502	4.84 519	26.71 508

ArgMatch-SfM		13.59 480	12.41 483	17.15 495	12.50 522	7.57 524	19.17 510	3.21 523	5.58 514	12.94 509	39.91 497	0.26 524	13.40 517	13.23 503	4.84 519	30.48 505

wuyk23d		9.11 483	8.77 487	10.15 498	40.18 504	16.76 511	20.28 509	1.01 528	2.58 519	2.66 530	0.98 544	0.23 525	12.49 519	4.08 525	6.90 515	1.19 531

PDCNetPlus		5.70 491	5.56 494	6.14 503	8.32 524	1.98 531	7.37 518	0.76 531	2.18 520	3.69 528	20.81 516	0.12 526	4.60 526	4.55 522	2.21 525	11.83 516

DenseAffine		8.44 484	7.90 490	10.07 499	9.51 523	4.71 525	11.43 514	1.10 527	4.32 515	8.26 516	27.67 511	0.09 527	8.71 521	6.30 515	2.41 524	16.80 511

RoMa-SfM		7.02 486	6.78 491	7.74 501	5.47 528	3.55 527	8.83 516	0.67 532	3.41 516	7.06 519	27.85 510	0.08 528	7.13 522	5.86 518	1.82 526	12.53 513

LoFTR		5.36 492	5.09 495	6.17 502	5.52 527	2.23 530	6.04 519	2.15 525	1.23 524	5.61 522	19.15 518	0.07 529	5.98 524	1.61 529	4.48 521	10.30 520

RoMa-HiRes		4.68 493	4.75 496	4.46 507	3.18 533	1.88 532	5.38 521	0.37 540	2.04 521	4.84 524	21.68 514	0.06 530	3.78 528	4.17 524	1.04 533	7.71 523

ALIKED-LG		1.21 503	1.31 507	0.90 516	2.88 534	0.91 538	1.96 526	0.48 536	0.17 533	0.94 536	3.75 534	0.06 530	0.81 535	0.10 543	1.43 529	0.99 532

SP-DiffGlue		0.50 508	0.53 511	0.38 523	0.41 562	0.20 552	0.62 537	0.19 543	0.09 536	0.64 541	1.95 538	0.06 530	0.17 546	0.26 536	0.60 539	0.77 538

MASt3R-SfM		1.80 501	2.02 503	1.14 515	1.03 545	0.52 544	1.83 528	0.53 534	0.34 529	2.55 531	9.61 529	0.05 533	0.77 536	1.06 531	1.16 532	2.14 530

ALIKED-NN		1.00 506	1.09 509	0.75 518	2.44 537	0.84 540	1.63 532	0.39 537	0.12 534	0.72 539	3.04 536	0.05 533	0.70 538	0.08 545	1.32 531	0.72 540

DKM		5.93 490	5.87 493	6.10 504	5.64 526	2.81 529	7.85 517	0.52 535	2.62 518	6.30 520	23.31 513	0.05 533	4.93 525	5.11 521	1.45 528	10.57 519

SP-LightGlue		0.48 509	0.50 512	0.40 519	1.33 540	0.19 553	0.86 533	0.17 546	0.08 538	0.25 543	1.08 540	0.05 533	0.19 543	0.13 539	0.57 540	0.80 535

SP-SuperGlue		0.47 510	0.50 512	0.39 520	1.30 541	0.19 553	0.86 533	0.17 546	0.09 536	0.26 542	1.08 540	0.05 533	0.18 545	0.13 539	0.55 541	0.79 537

ALIKED-MNN		1.07 505	1.15 508	0.84 517	2.67 535	0.92 537	1.81 529	0.39 537	0.12 534	0.73 538	3.13 535	0.05 533	0.77 536	0.09 544	1.34 530	0.84 534

DKM-HiRes		4.42 494	4.49 497	4.23 508	3.85 531	1.83 533	5.38 521	0.33 541	1.86 522	4.78 525	18.85 519	0.04 539	2.97 530	4.34 523	0.97 534	7.88 522

SP-NN		0.43 513	0.45 516	0.37 524	1.13 544	0.17 557	0.82 536	0.16 548	0.07 540	0.24 544	1.00 543	0.04 539	0.19 543	0.12 541	0.51 544	0.74 539

GLUNet-SfM		2.60 498	2.13 502	4.01 510	1.95 538	0.86 539	1.72 530	0.81 530	0.34 529	3.35 529	9.72 528	0.04 539	3.15 529	0.50 534	0.73 537	8.02 521

MatchFormer		3.89 495	3.84 499	4.03 509	4.08 530	1.73 534	5.52 520	1.59 526	0.67 525	4.77 526	13.56 526	0.04 539	4.50 527	0.74 533	3.60 523	5.85 525

SP-MNN		0.45 511	0.47 515	0.39 520	1.18 543	0.17 557	0.85 535	0.16 548	0.07 540	0.24 544	1.05 542	0.04 539	0.20 542	0.12 541	0.54 543	0.80 535

MVS_baseline		1.13 504	1.40 506	0.34 525	0.74 552	0.01 567	0.24 552	0.03 565	0.00 559	1.75 534	7.74 532	0.03 544	0.00 561	0.31 535	1.74 527	0.99 532

XFeat-NN		0.44 512	0.49 514	0.30 526	0.24 564	0.12 563	0.48 539	0.15 550	0.06 542	0.71 540	1.78 539	0.03 544	0.28 541	0.14 538	0.83 536	0.48 542

XFeat-MNN		0.55 507	0.60 510	0.39 520	0.26 563	0.16 560	0.58 538	0.20 542	0.08 538	0.82 537	2.26 537	0.03 544	0.39 540	0.19 537	0.95 535	0.62 541

ELoFTR		2.17 500	1.90 504	2.99 511	1.19 542	0.63 543	1.84 527	0.60 533	0.46 527	2.17 533	9.10 530	0.02 547	2.92 531	1.00 532	0.72 538	5.42 526

PMatch-SfM		2.38 499	2.41 501	2.29 512	1.48 539	0.76 542	2.51 525	0.18 545	0.59 526	2.43 532	12.04 527	0.01 548	1.67 532	1.93 528	0.55 541	4.44 527

SIFT-UM-Cal		0.21 523	0.23 526	0.14 537	0.68 555	0.15 561	0.29 549	0.04 562	0.05 544	0.10 555	0.56 554	0.01 548	0.12 556	0.02 546	0.34 555	0.15 555

SIFT-NCM-Cal		0.26 517	0.28 520	0.19 530	0.84 549	0.23 549	0.38 543	0.06 555	0.05 544	0.11 553	0.59 552	0.01 548	0.14 547	0.02 546	0.45 548	0.21 549

SIFT-CM-Cal		0.21 523	0.23 526	0.15 536	0.71 554	0.18 555	0.28 550	0.05 558	0.05 544	0.10 555	0.55 555	0.01 548	0.12 556	0.01 558	0.33 556	0.17 553

SIFT-PCN-Cal		0.18 525	0.20 528	0.13 538	0.58 559	0.10 565	0.23 553	0.04 562	0.04 554	0.08 558	0.47 556	0.01 548	0.10 558	0.01 558	0.30 557	0.19 550

SIFT-NN-UMatch		0.24 519	0.26 521	0.18 532	0.64 557	0.18 555	0.38 543	0.06 555	0.05 544	0.12 552	0.65 547	0.01 548	0.13 551	0.02 546	0.43 549	0.22 547

SIFT-NN-NCMNet		0.27 516	0.29 519	0.20 529	0.81 550	0.24 548	0.40 542	0.08 552	0.05 544	0.14 549	0.65 547	0.01 548	0.14 547	0.02 546	0.47 546	0.22 547

SIFT-NN-CMatch		0.25 518	0.26 521	0.19 530	0.68 555	0.21 550	0.35 545	0.06 555	0.05 544	0.15 547	0.65 547	0.01 548	0.13 551	0.02 546	0.41 550	0.23 545

SIFT-NN-PointCN		0.22 522	0.24 525	0.17 534	0.59 558	0.14 562	0.32 547	0.05 558	0.04 554	0.13 550	0.57 553	0.01 548	0.13 551	0.02 546	0.39 551	0.23 545

SIFT-NN		0.30 514	0.33 517	0.22 527	0.96 547	0.28 546	0.45 540	0.08 552	0.05 544	0.17 546	0.72 545	0.01 548	0.14 547	0.02 546	0.48 545	0.25 543

SIFT-UMatch		0.23 521	0.25 524	0.16 535	0.74 552	0.17 557	0.33 546	0.05 558	0.05 544	0.11 553	0.60 551	0.01 548	0.13 551	0.02 546	0.37 553	0.18 552

SIFT-NCMNet		0.15 527	0.17 530	0.10 540	0.52 561	0.09 566	0.19 554	0.02 566	0.04 554	0.07 560	0.39 558	0.01 548	0.08 560	0.01 558	0.24 559	0.11 556

SIFT-ConvMatch		0.24 519	0.26 521	0.18 532	0.76 551	0.21 550	0.32 547	0.05 558	0.05 544	0.13 550	0.63 550	0.01 548	0.13 551	0.02 546	0.38 552	0.19 550

SIFT-PointCN		0.18 525	0.20 528	0.13 538	0.58 559	0.11 564	0.25 551	0.04 562	0.04 554	0.08 558	0.45 557	0.01 548	0.10 558	0.01 558	0.30 557	0.17 553

SIFT-MNN		0.28 515	0.31 518	0.21 528	0.89 548	0.25 547	0.41 541	0.08 552	0.05 544	0.15 547	0.70 546	0.01 548	0.14 547	0.02 546	0.46 547	0.25 543

PMatch-Up-SfM		1.67 502	1.74 505	1.44 513	1.00 546	0.50 545	1.72 530	0.11 551	0.40 528	1.75 534	8.98 531	0.00 563	1.07 534	1.34 530	0.35 554	2.76 528

mmdepth		0.00 528	0.00 531	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	0.00 561	0.00 563	0.00 561	0.00 562	0.00 560	0.00 559

monomultidepth		0.00 528	0.00 531	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	0.00 561	0.00 563	0.00 561	0.00 562	0.00 560	0.00 559

test_blank		0.00 528	0.00 531	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	0.00 561	0.00 563	0.00 561	0.00 562	0.00 560	0.00 559

uanet_test		0.00 528	0.00 531	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	0.00 561	0.00 563	0.00 561	0.00 562	0.00 560	0.00 559

DCPMVS		0.00 528	0.00 531	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	0.00 561	0.00 563	0.00 561	0.00 562	0.00 560	0.00 559

sosnet-low-res		0.00 528	0.00 531	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	0.00 561	0.00 563	0.00 561	0.00 562	0.00 560	0.00 559

sosnet		0.00 528	0.00 531	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	0.00 561	0.00 563	0.00 561	0.00 562	0.00 560	0.00 559

uncertanet		0.00 528	0.00 531	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	0.00 561	0.00 563	0.00 561	0.00 562	0.00 560	0.00 559

Regformer		0.00 528	0.00 531	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	0.00 561	0.00 563	0.00 561	0.00 562	0.00 560	0.00 559

testmvs		6.14 487	8.18 488	0.01 541	0.01 565	0.00 569	73.40 406	0.00 567	0.00 559	0.02 561	0.15 559	0.00 563	0.00 561	0.02 546	0.00 560	0.02 557

test123		6.01 488	8.01 489	0.01 541	0.00 566	0.01 567	71.93 423	0.00 567	0.00 559	0.02 561	0.11 560	0.00 563	0.00 561	0.02 546	0.00 560	0.02 557

ab-mvs-re		7.68 485	10.24 486	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	92.12 60	0.00 563	0.00 561	0.00 562	0.00 560	0.00 559

uanet		0.00 528	0.00 531	0.00 543	0.00 566	0.00 569	0.00 555	0.00 567	0.00 559	0.00 563	0.00 561	0.00 563	0.00 561	0.00 562	0.00 560	0.00 559

Meshroom													0.00 561
: In preparation.
AliceVision / Meshro													0.00 561
: In preparation.
AliceVision_Meshroom													0.00 561
: In preparation.
PatchmatchNet2					0.00 566	32.03 471	74.85 389	61.13 469	37.29 463
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														23.45 477	40.77 462	68.54 471
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													67.71 471
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
aaatest				80.14 40	84.34 96	54.93 88	87.61 74	87.22 86	57.43 302	81.85 19	92.88 45		93.75 32	80.19 55	85.13 51	91.76 64

WAC-MVS						34.28 456								22.56 481

FOURS1					83.24 124	49.90 252	84.98 186	78.76 325	47.71 411	73.42 81

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					0.00 566

eth-test					0.00 566

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

save fliter					85.35 76	56.34 45	89.31 42	81.46 255	61.55 214

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

MTGPA								81.31 258

MTMP							87.27 91	15.34 520

gm-plane-assit					83.24 124	54.21 123			70.91 35		88.23 167		95.25 15	66.37 185

test9_res														78.72 69	85.44 46	91.39 80

agg_prior2														75.65 96	85.11 53	91.01 106

agg_prior					85.64 69	54.92 93		83.61 212		72.53 98			88.10 230

test_prior4						56.39 44	87.15 95

test_prior				78.39 98	86.35 58	54.91 96		85.45 134					89.70 155			90.55 124

旧先验2							81.73 302		45.53 431	74.66 67			70.48 467	58.31 269

新几何2							81.61 308

无先验							85.19 172	78.00 343	49.08 400				85.13 344	52.78 328		87.45 231

原ACMM2							83.77 232

testdata2													77.81 426	45.64 379

testdata1							77.55 371		64.14 154

plane_prior7					77.95 291	48.46 298

plane_prior5								82.59 230					88.30 223	65.46 196	72.34 220	84.49 295

plane_prior4											83.28 274

plane_prior3						48.95 279			64.01 158	62.15 259

plane_prior2							85.76 141		63.60 170

plane_prior1					78.31 287

plane_prior						49.57 257	87.43 83		64.57 144						72.84 212

n2								0.00 567

nn								0.00 567

door-mid								41.31 496

test11								84.25 192

door								43.27 492

HQP5-MVS						51.56 204

HQP-NCC					79.02 265		88.00 63		65.45 128	64.48 219

ACMP_Plane					79.02 265		88.00 63		65.45 128	64.48 219

BP-MVS														66.70 182

HQP4-MVS										64.47 222			88.61 202			84.91 291

HQP3-MVS								83.68 207							73.12 208

NP-MVS					78.76 271	50.43 234					85.12 238

ACMMP++_ref															63.20 321

ACMMP++															59.38 354

High-resolution multi-view benchmark