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 67	82.99 134	52.71 168	85.04 181	88.63 50	66.08 118	86.77 4	92.75 48	72.05 1	91.46 80	83.35 30	93.53 1	92.23 41
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 19	84.98 185	88.88 39	58.00 285	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 14	92.05 3	55.97 52	92.48 3				94.01 11	67.21 2	95.10 16	89.82 3	92.55 3	94.06 4

PC_three_1452									66.58 103	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 10	87.61 73	91.34 10	56.28 331	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	80.12 233	59.50 5	92.24 8	90.72 18	69.37 59	83.22 9	94.47 5	63.81 6	93.18 39	74.02 116	93.25 2	94.80 1

WBMVS		73.93 138	73.39 130	75.55 195	87.82 42	55.21 71	89.37 39	87.29 83	67.27 88	63.70 235	80.30 321	60.32 7	86.47 302	61.58 234	62.85 326	84.97 288

DELS-MVS		82.32 5	82.50 5	81.79 13	86.80 52	56.89 31	92.77 2	86.30 110	77.83 1	77.88 49	92.13 59	60.24 8	94.78 20	78.97 64	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 24	78.94 25	80.49 27	89.75 13	56.54 39	84.83 193	83.68 206	67.85 80	69.36 154	90.24 112	60.20 9	92.10 67	84.14 24	80.40 92	92.82 26

baseline2		75.15 113	74.54 112	76.98 144	81.67 176	51.74 199	83.84 229	91.94 3	69.97 49	58.98 300	86.02 223	59.73 10	91.73 74	68.37 171	70.40 247	87.48 228

CSCG		80.41 15	79.72 17	82.49 6	89.12 26	57.67 17	89.29 45	91.54 5	59.19 261	71.82 109	90.05 120	59.72 11	96.04 11	78.37 70	88.40 14	93.75 8

GG-mvs-BLEND				77.77 114	86.68 53	50.61 226	68.67 437	88.45 59		68.73 162	87.45 198	59.15 12	90.67 113	54.83 308	87.67 18	92.03 50

testing3-2		72.30 177	72.35 150	72.15 312	83.07 129	47.64 331	85.46 161	89.81 26	66.17 114	61.96 262	84.88 245	58.93 13	82.27 374	55.87 298	64.97 296	86.54 256

SED-MVS		81.92 8	81.75 9	82.44 8	89.48 18	56.89 31	92.48 3	88.94 37	57.50 299	84.61 5	94.09 9	58.81 14	96.37 7	82.28 38	87.60 19	94.06 4

test_241102_ONE					89.48 18	56.89 31		88.94 37	57.53 297	84.61 5	93.29 32	58.81 14	96.45 1

gg-mvs-nofinetune		67.43 289	64.53 317	76.13 174	85.95 61	47.79 329	64.38 452	88.28 63	39.34 454	66.62 179	41.27 494	58.69 16	89.00 182	49.64 350	86.62 32	91.59 69

BridgeMVS		80.28 16	79.73 16	81.90 12	86.47 56	59.34 7	80.45 333	89.51 28	69.76 54	71.05 127	86.66 212	58.68 17	93.24 37	84.64 20	90.40 6	93.14 19

UBG		78.86 27	78.86 26	78.86 65	87.80 43	55.43 59	87.67 71	91.21 12	72.83 12	72.10 103	88.40 155	58.53 18	89.08 177	73.21 131	77.98 125	92.08 46

myMVS_eth3d28		77.77 44	77.94 35	77.27 132	87.58 46	52.89 162	86.06 127	91.33 11	74.15 7	68.16 167	88.24 165	58.17 19	88.31 221	69.88 157	77.87 126	90.61 121

MED-MVS		79.56 22	79.39 20	80.06 43	84.34 95	54.93 87	87.61 73	87.22 85	56.22 332	81.85 19	92.98 42	58.11 20	93.75 32	80.19 54	85.96 38	91.52 74

fmvsm_l_mol_unc0.5_1		78.65 28	79.09 24	77.33 127	78.55 279	53.79 130	88.87 51	71.62 425	74.12 8	81.93 16	95.02 3	57.79 21	86.96 281	80.83 51	83.10 65	91.23 91

testing11		79.18 25	78.85 27	80.16 37	88.33 32	56.99 28	88.31 59	92.06 1	72.82 13	70.62 142	88.37 157	57.69 22	92.30 59	75.25 101	76.24 155	91.20 94

MVSMamba_PlusPlus		75.28 107	73.39 130	80.96 23	80.85 208	58.25 12	74.47 394	87.61 80	50.53 390	65.24 200	83.41 270	57.38 23	92.83 43	73.92 118	87.13 22	91.80 62

testing99		78.45 30	77.78 39	80.45 30	88.28 35	56.81 34	87.95 66	91.49 6	71.72 20	70.84 135	88.09 174	57.29 24	92.63 52	69.24 163	75.13 179	91.91 55

CostFormer		73.89 141	72.30 153	78.66 74	82.36 154	56.58 36	75.56 382	85.30 141	66.06 119	70.50 144	76.88 367	57.02 25	89.06 178	68.27 173	68.74 263	90.33 131

test_0728_THIRD									58.00 285	81.91 17	93.64 21	56.54 26	96.44 2	81.64 44	86.86 27	92.23 41

DPE-MVS		79.82 20	79.66 18	80.29 33	89.27 25	55.08 79	88.70 53	87.92 71	55.55 341	81.21 25	93.69 20	56.51 27	94.27 26	78.36 71	85.70 43	91.51 76
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ETVMVS		75.80 97	75.44 87	76.89 147	86.23 60	50.38 237	85.55 156	91.42 7	71.30 29	68.80 161	87.94 182	56.42 28	89.24 171	56.54 291	74.75 188	91.07 100

DeepPCF-MVS	69.37 1	80.65 13	81.56 11	77.94 110	85.46 73	49.56 259	90.99 21	86.66 101	70.58 39	80.07 34	95.30 2	56.18 29	90.97 104	82.57 37	86.22 37	93.28 14

test_241102_TWO								88.76 46	57.50 299	83.60 7	94.09 9	56.14 30	96.37 7	82.28 38	87.43 21	92.55 33

testing91		78.30 37	77.54 42	80.61 25	88.16 38	57.12 27	87.94 67	91.07 16	71.43 25	70.75 137	88.04 179	55.82 31	92.65 49	69.61 158	75.00 184	92.05 49

patch_mono-2		80.84 12	81.59 10	78.62 79	90.34 10	53.77 131	88.08 61	88.36 62	76.17 2	79.40 41	91.09 84	55.43 32	90.09 136	85.01 16	80.40 92	91.99 54

testing222		77.70 46	77.22 49	79.14 56	86.95 50	54.89 96	87.18 92	91.96 2	72.29 15	71.17 125	88.70 145	55.19 33	91.24 88	65.18 201	76.32 153	91.29 87

DVP-MVS		81.30 10	81.00 13	82.20 9	89.40 21	57.45 21	92.34 5	89.99 23	57.71 293	81.91 17	93.64 21	55.17 34	96.44 2	81.68 42	87.13 22	92.72 30
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 21	92.32 7	88.63 50	57.71 293	83.14 10	93.96 12	55.17 34

TSAR-MVS + MP.		78.31 36	78.26 30	78.48 91	81.33 193	56.31 45	81.59 308	86.41 107	69.61 56	81.72 21	88.16 170	55.09 36	88.04 231	74.12 115	86.31 35	91.09 98
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 84	75.55 83	77.71 116	79.49 248	52.27 181	84.70 197	90.49 20	64.44 144	69.86 151	90.31 111	55.05 37	91.35 83	70.07 155	75.58 172	89.53 163

baseline1		72.51 170	72.12 160	73.69 265	85.05 80	44.46 387	83.51 239	86.13 115	71.61 23	64.64 213	87.97 181	55.00 38	89.48 162	59.07 257	56.05 390	87.13 239

test_one_0601					89.39 23	57.29 24		88.09 68	57.21 307	82.06 15	93.39 28	54.94 39

MM		82.69 2	83.29 3	80.89 24	84.38 94	55.40 63	92.16 10	89.85 25	75.28 4	82.41 12	93.86 15	54.30 40	93.98 27	90.29 1	87.13 22	93.30 13

TSAR-MVS + GP.		77.82 43	77.59 41	78.49 90	85.25 78	50.27 244	90.02 26	90.57 19	56.58 324	74.26 73	91.60 79	54.26 41	92.16 64	75.87 93	79.91 100	93.05 21

EPP-MVSNet		71.14 202	70.07 204	74.33 242	79.18 259	46.52 355	83.81 230	86.49 105	56.32 330	57.95 323	84.90 244	54.23 42	89.14 176	58.14 271	69.65 253	87.33 232

MCST-MVS		83.01 1	83.30 2	82.15 11	92.84 2	57.58 18	93.77 1	91.10 13	75.95 3	77.10 53	93.09 37	54.15 43	95.57 13	85.80 13	85.87 41	93.31 12

alignmvs		78.08 40	77.98 34	78.39 97	83.53 114	53.22 149	89.77 32	85.45 133	66.11 116	76.59 58	91.99 66	54.07 44	89.05 179	77.34 81	77.00 138	92.89 24

test-260524					88.20 37	55.35 65		88.22 65		80.74 29		53.67 45	94.67 21	80.11 57	85.96 38

GDP-MVS		75.27 108	74.38 113	77.95 109	79.04 263	52.86 164	85.22 169	86.19 113	62.43 199	70.66 140	90.40 109	53.51 46	91.60 76	69.25 162	72.68 214	89.39 170

WTY-MVS		77.47 50	77.52 43	77.30 130	88.33 32	46.25 364	88.46 57	90.32 21	71.40 26	72.32 100	91.72 74	53.44 47	92.37 58	66.28 186	75.42 173	93.28 14

FBQ-MVS		78.34 35	77.25 47	81.62 16	86.35 58	59.48 6	86.95 99	90.95 17	72.89 11	71.91 108	87.60 196	53.35 48	92.65 49	70.19 153	75.03 183	92.72 30

IB-MVS	68.87 2	74.01 136	72.03 164	79.94 44	83.04 131	55.50 57	90.24 25	88.65 48	67.14 92	61.38 267	81.74 306	53.21 49	94.28 24	60.45 248	62.41 329	90.03 148
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 14	80.71 14	79.88 45	87.34 48	55.20 74	89.93 29	87.55 81	66.04 121	79.46 39	93.00 41	53.10 50	91.76 72	80.40 53	89.56 9	92.68 32

miper_enhance_ethall		69.77 235	68.90 225	72.38 306	78.93 267	49.91 250	83.29 250	78.85 319	64.90 140	59.37 292	79.46 332	52.77 51	85.16 342	63.78 213	58.72 358	82.08 348

MVSTER		73.25 154	72.33 151	76.01 178	85.54 71	53.76 132	83.52 235	87.16 88	67.06 96	63.88 230	81.66 307	52.77 51	90.44 123	64.66 206	64.69 302	83.84 315

CNVR-MVS		81.76 9	81.90 8	81.33 20	90.04 11	57.70 16	91.71 11	88.87 41	70.31 41	77.64 52	93.87 14	52.58 53	93.91 30	84.17 23	87.92 17	92.39 36

FIs		70.00 230	70.24 201	69.30 364	77.93 292	38.55 442	83.99 223	87.72 77	66.86 101	57.66 330	84.17 254	52.28 54	85.31 337	52.72 330	68.80 262	84.02 305

tpm2		70.82 211	68.44 231	77.98 106	80.78 210	56.11 48	74.21 397	81.28 259	60.24 239	68.04 169	75.27 385	52.26 55	88.50 210	55.82 301	68.03 268	89.33 172

thisisatest0515		73.64 148	72.20 156	77.97 107	81.63 179	53.01 158	86.69 112	88.81 44	62.53 195	64.06 225	85.65 227	52.15 56	92.50 54	58.43 264	69.84 250	88.39 207

aaEdge-Enhanced		79.48 23	79.20 23	80.35 32	88.96 27	54.93 87	88.65 54	88.50 58	56.62 321	79.87 36	92.88 45	51.96 57	94.36 23	80.19 54	85.13 51	91.76 63

casdiffmvs_mvg		77.75 45	77.28 46	79.16 55	80.42 227	54.44 116	87.76 68	85.46 132	71.67 22	71.38 120	88.35 160	51.58 58	91.22 89	79.02 63	79.89 102	91.83 60
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		68.82 257	68.29 234	70.40 350	75.71 343	42.59 413	84.23 214	86.78 97	66.31 110	58.51 314	82.45 289	51.57 59	84.64 351	53.11 321	55.96 391	83.96 311

PAPM		76.76 66	76.07 73	78.81 66	80.20 231	59.11 8	86.86 105	86.23 111	68.60 67	70.18 149	88.84 143	51.57 59	87.16 275	65.48 194	86.68 31	90.15 140

tttt0517		68.33 269	66.29 281	74.46 235	78.08 287	49.06 273	80.88 326	89.08 35	54.40 359	54.75 368	80.77 316	51.31 61	90.33 127	49.35 352	58.01 370	83.99 307

mvs_anonymous		72.29 178	70.74 184	76.94 146	82.85 141	54.72 105	78.43 364	81.54 253	63.77 163	61.69 264	79.32 334	51.11 62	85.31 337	62.15 230	75.79 163	90.79 115

HY-MVS	67.03 5	73.90 140	73.14 136	76.18 173	84.70 86	47.36 339	75.56 382	86.36 109	66.27 111	70.66 140	83.91 259	51.05 63	89.31 168	67.10 180	72.61 215	91.88 57

thisisatest0530		70.47 221	68.56 227	76.20 171	79.78 242	51.52 205	83.49 241	88.58 56	57.62 296	58.60 313	82.79 278	51.03 64	91.48 79	52.84 325	62.36 331	85.59 279

sasdasda		78.17 38	77.86 37	79.12 58	84.30 98	54.22 120	87.71 69	84.57 184	67.70 84	77.70 50	92.11 62	50.90 65	89.95 140	78.18 74	77.54 130	93.20 16

miper_ehance_all_eth		68.70 263	67.58 252	72.08 314	76.91 319	49.48 265	82.47 280	78.45 334	62.68 193	58.28 322	77.88 348	50.90 65	85.01 345	61.91 231	58.72 358	81.75 353

canonicalmvs		78.17 38	77.86 37	79.12 58	84.30 98	54.22 120	87.71 69	84.57 184	67.70 84	77.70 50	92.11 62	50.90 65	89.95 140	78.18 74	77.54 130	93.20 16

casdiffmvs		77.36 52	76.85 56	78.88 64	80.40 228	54.66 110	87.06 95	85.88 119	72.11 18	71.57 113	88.63 150	50.89 68	90.35 126	76.00 91	79.11 111	91.63 68
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 29	86.63 54	54.69 107	92.20 9	86.66 101	74.48 5	82.63 11	93.80 17	50.83 69	93.70 34	90.11 2	86.44 34	93.01 22

fmvsm_s_conf0.5_n_9		76.66 69	76.94 55	75.85 183	79.54 247	48.30 305	82.63 272	71.84 418	70.25 43	80.63 31	94.53 4	50.78 70	87.42 265	88.32 5	73.92 196	91.82 61

baseline		76.86 62	76.24 69	78.71 70	80.47 222	54.20 124	83.90 227	84.88 168	71.38 27	71.51 116	89.15 138	50.51 71	90.55 119	75.71 94	78.65 116	91.39 79

TestfortrainingZip a		77.64 47	76.79 60	80.20 35	84.34 95	54.79 100	87.61 73	87.03 90	56.22 332	78.78 42	92.98 42	50.45 72	94.28 24	74.37 110	79.31 109	91.52 74

MVS_Test		75.85 93	74.93 101	78.62 79	84.08 103	55.20 74	83.99 223	85.17 148	68.07 76	73.38 82	82.76 279	50.44 73	89.00 182	65.90 190	80.61 88	91.64 67

FC-MVSNet-test		67.49 287	67.91 240	66.21 398	76.06 334	33.06 463	80.82 327	87.18 87	64.44 144	54.81 366	82.87 276	50.40 74	82.60 372	48.05 363	66.55 281	82.98 339

nrg030		72.27 180	71.56 168	74.42 237	75.93 340	50.60 227	86.97 97	83.21 218	62.75 190	67.15 175	84.38 250	50.07 75	86.66 296	71.19 146	62.37 330	85.99 268

fmvsm_l_conf0.5_n		75.95 89	76.16 71	75.31 208	76.01 338	48.44 298	84.98 185	71.08 429	63.50 172	81.70 22	93.52 24	50.00 76	87.18 274	87.80 6	76.87 142	90.32 132

cl22		68.85 255	67.69 250	72.35 307	78.07 288	49.98 249	82.45 281	78.48 333	62.50 197	58.46 318	77.95 346	49.99 77	85.17 341	62.55 224	58.72 358	81.90 351

fmvsm_l_conf0.5_n_a		75.88 92	76.07 73	75.31 208	76.08 333	48.34 301	85.24 168	70.62 432	63.13 180	81.45 23	93.62 23	49.98 78	87.40 267	87.76 7	76.77 144	90.20 137

tpmrst		71.04 207	69.77 208	74.86 226	83.19 125	55.86 54	75.64 379	78.73 326	67.88 79	64.99 206	73.73 397	49.96 79	79.56 408	65.92 189	67.85 271	89.14 179

CANet		80.90 11	81.17 12	80.09 42	87.62 45	54.21 122	91.60 14	86.47 106	73.13 10	79.89 35	93.10 35	49.88 80	92.98 40	84.09 25	84.75 56	93.08 20

nomal-1		72.45 171	71.14 178	76.37 163	84.65 87	56.28 46	68.39 439	88.28 63	67.21 90	62.98 246	80.23 322	49.71 81	86.05 319	69.36 161	69.48 256	86.78 253

ET-MVSNet_ETH3D		75.23 111	74.08 118	78.67 73	84.52 91	55.59 55	88.92 49	89.21 33	68.06 77	53.13 383	90.22 114	49.71 81	87.62 257	72.12 142	70.82 238	92.82 26

hybridcas		76.66 69	75.99 76	78.65 76	79.25 256	54.46 115	86.82 107	85.53 129	70.88 36	70.40 147	88.21 167	49.55 83	90.12 135	74.42 109	78.88 115	91.37 81

c3_l		67.97 275	66.66 274	71.91 325	76.20 332	49.31 270	82.13 288	78.00 342	61.99 205	57.64 331	76.94 364	49.41 84	84.93 346	60.62 243	57.01 381	81.49 358

Vis-MVSNet (Re-imp)		65.52 326	65.63 298	65.17 408	77.49 303	30.54 473	75.49 385	77.73 349	59.34 256	52.26 390	86.69 211	49.38 85	80.53 395	37.07 414	75.28 175	84.42 296

EPNet		78.36 34	78.49 29	77.97 107	85.49 72	52.04 184	89.36 41	84.07 198	73.22 9	77.03 54	91.72 74	49.32 86	90.17 134	73.46 126	82.77 68	91.69 65
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_l_conf0.5_n_9		77.10 55	77.48 44	75.98 180	77.54 302	47.77 330	86.35 118	73.46 409	68.69 66	81.07 26	94.40 6	49.06 87	88.89 191	87.39 8	79.32 108	91.27 90

testing3		59.97 372	60.19 362	59.32 443	77.60 296	30.01 479	81.75 300	81.79 247	53.54 365	50.34 409	79.94 324	48.99 88	76.91 432	17.19 494	50.59 422	71.03 466

Casviewmamba		76.27 79	75.48 85	78.63 78	79.14 260	54.27 119	85.81 137	83.09 221	70.96 33	70.41 146	88.36 159	48.71 89	90.81 108	75.92 92	76.95 139	90.80 114

E3new		76.85 63	76.24 69	78.66 74	81.62 180	55.01 82	86.94 100	85.10 157	71.55 24	71.93 107	88.61 151	48.40 90	89.60 157	74.50 107	77.53 132	91.36 82

tpm		68.36 267	67.48 257	70.97 341	79.93 236	51.34 209	76.58 376	78.75 325	67.73 82	63.54 242	74.86 387	48.33 91	72.36 460	53.93 315	63.71 310	89.21 176

APDe-MVS		78.44 31	78.20 31	79.19 53	88.56 28	54.55 113	89.76 33	87.77 75	55.91 336	78.56 45	92.49 54	48.20 92	92.65 49	79.49 59	83.04 67	90.39 128
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 78	76.81 58	74.71 230	79.21 257	46.90 345	85.03 182	73.96 398	69.00 64	79.70 38	93.88 13	48.07 93	87.71 251	84.26 22	78.15 123	89.50 166

MG-MVS		78.42 32	76.99 54	82.73 3	93.17 1	64.46 1	89.93 29	88.51 57	64.83 141	73.52 80	88.09 174	48.07 93	92.19 63	62.24 228	84.53 58	91.53 73

DeepC-MVS	67.15 4	76.90 61	76.27 68	78.80 67	80.70 212	55.02 81	86.39 116	86.71 99	66.96 100	67.91 170	89.97 122	48.03 95	91.41 81	75.60 96	84.14 60	89.96 150
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 69	76.01 75	78.62 79	81.14 196	54.95 85	86.88 104	85.04 159	71.37 28	71.76 110	88.44 154	48.02 96	89.57 159	74.17 114	77.23 134	91.33 86

MGCFI-Net		74.07 135	74.64 111	72.34 308	82.90 138	43.33 405	80.04 342	79.96 288	65.61 124	74.93 65	91.85 70	48.01 97	80.86 387	71.41 145	77.10 135	92.84 25

test_prior2							89.04 48		61.88 208	73.55 79	91.46 83	48.01 97		74.73 104	85.46 45

myMVS_eth3d		63.52 345	63.56 326	63.40 421	81.73 171	34.28 455	80.97 323	81.02 262	60.93 228	55.06 362	82.64 284	48.00 99	80.81 388	23.42 479	58.32 362	75.10 437

balanced_ft_v1		75.25 109	73.90 123	79.29 51	85.59 69	56.72 35	74.35 396	87.27 84	60.24 239	59.07 299	85.17 235	47.76 100	90.51 120	82.62 36	83.06 66	90.64 119

SF-MVS		77.64 47	77.42 45	78.32 100	83.75 111	52.47 173	86.63 114	87.80 72	58.78 273	74.63 68	92.38 56	47.75 101	91.35 83	78.18 74	86.85 28	91.15 97

test2506		72.91 160	72.43 149	74.32 243	80.12 233	44.18 394	83.19 254	84.77 173	64.02 154	65.97 188	87.43 199	47.67 102	88.72 197	59.08 256	79.66 104	90.08 146

E2		76.39 75	75.67 79	78.56 86	80.49 220	54.87 97	86.80 108	84.95 163	71.09 31	71.51 116	88.21 167	47.55 103	89.53 160	73.65 122	76.77 144	91.29 87

E3		76.39 75	75.67 79	78.56 86	80.49 220	54.87 97	86.80 108	84.95 163	71.09 31	71.51 116	88.21 167	47.55 103	89.53 160	73.65 122	76.77 144	91.29 87

fmvsm_s_conf0.5_n_3		74.97 117	75.42 88	73.62 268	76.99 316	46.67 350	83.13 257	71.14 428	66.20 113	82.13 14	93.76 18	47.49 105	84.00 357	81.95 41	76.02 158	90.19 139

1112_ss		70.05 228	69.37 214	72.10 313	80.77 211	42.78 411	85.12 178	76.75 366	59.69 248	61.19 269	92.12 60	47.48 106	83.84 359	53.04 323	68.21 266	89.66 157

fmvsm_s_conf0.5_n_10		76.80 64	76.81 58	76.78 154	78.91 268	47.85 325	83.44 242	74.66 389	68.93 65	81.31 24	94.12 8	47.44 107	90.82 107	83.43 29	79.06 113	91.66 66

Effi-MVS+		75.24 110	73.61 129	80.16 37	81.92 166	57.42 23	85.21 170	76.71 369	60.68 234	73.32 83	89.34 133	47.30 108	91.63 75	68.28 172	79.72 103	91.42 78

UniMVSNet (Re)		67.71 281	66.80 270	70.45 348	74.44 364	42.93 409	82.42 282	84.90 167	63.69 167	59.63 286	80.99 313	47.18 109	85.23 340	51.17 342	56.75 382	83.19 333

test12				79.24 52	86.89 51	56.08 49		85.16 150		72.27 101		47.15 110	91.10 94		85.93 40	90.54 125

PVSNet_Blended_VisFu		73.40 152	72.44 148	76.30 164	81.32 194	54.70 106	85.81 137	78.82 321	63.70 166	64.53 217	85.38 233	47.11 111	87.38 268	67.75 176	77.55 129	86.81 252

fmvsm_s_conf0.5_n_8		76.50 73	76.68 63	75.94 181	78.67 273	47.92 323	85.18 172	74.71 388	68.09 73	80.67 30	94.26 7	47.09 112	89.26 170	86.62 10	74.85 186	90.65 118

test_fmvsm_n_1920		75.56 104	75.54 84	75.61 191	74.60 363	49.51 264	81.82 297	74.08 395	66.52 106	80.40 32	93.46 26	46.95 113	89.72 149	86.69 9	75.30 174	87.61 226

NCCC		79.57 21	79.23 22	80.59 26	89.50 16	56.99 28	91.38 16	88.17 66	67.71 83	73.81 77	92.75 48	46.88 114	93.28 36	78.79 67	84.07 61	91.50 77

viewmanbaseed2359cas		76.71 68	76.16 71	78.37 99	81.16 195	55.05 80	86.96 98	85.32 139	71.71 21	72.25 102	88.50 153	46.86 115	88.96 186	74.55 106	78.08 124	91.08 99

E4		75.99 87	75.16 94	78.48 91	79.56 246	54.74 102	86.66 113	84.80 171	70.62 37	71.16 126	87.90 183	46.84 116	89.47 164	72.70 133	76.20 157	91.23 91

fmvsm_s_conf0.5_n_6		76.17 82	76.84 57	74.15 248	77.42 305	46.46 356	85.53 158	77.86 346	69.78 53	79.78 37	92.90 44	46.80 117	84.81 348	84.67 19	76.86 143	91.17 96

9.14			78.19 32		85.67 67		88.32 58	88.84 43	59.89 243	74.58 70	92.62 51	46.80 117	92.66 48	81.40 49	85.62 44

VNet		77.99 42	77.92 36	78.19 103	87.43 47	50.12 245	90.93 22	91.41 8	67.48 87	75.12 63	90.15 118	46.77 119	91.00 99	73.52 124	78.46 119	93.44 10

PVSNet_BlendedMVS		73.42 151	73.30 132	73.76 262	85.91 62	51.83 193	86.18 123	84.24 193	65.40 130	69.09 158	80.86 315	46.70 120	88.13 227	75.43 97	65.92 292	81.33 366

PVSNet_Blended		76.53 72	76.54 64	76.50 160	85.91 62	51.83 193	88.89 50	84.24 193	67.82 81	69.09 158	89.33 135	46.70 120	88.13 227	75.43 97	81.48 81	89.55 161

0.3-1-1-0.015		72.75 164	71.06 180	77.81 112	80.58 217	50.62 225	89.45 37	88.60 54	63.74 165	65.56 196	81.82 304	46.61 122	90.64 116	62.86 222	60.35 342	92.17 44

PRO-TEST		79.94 18	79.98 15	79.81 46	87.63 44	55.24 68	87.59 78	88.40 61	71.10 30	76.93 55	91.92 69	46.57 123	91.41 81	84.32 21	85.41 47	92.79 28

SMA-MVS		79.10 26	78.76 28	80.12 40	84.42 92	55.87 53	87.58 81	86.76 98	61.48 216	80.26 33	93.10 35	46.53 124	92.41 56	79.97 58	88.77 11	92.08 46
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 56	77.02 52	77.32 129	81.66 177	52.32 177	89.31 42	82.11 237	72.20 16	73.23 85	91.05 85	46.52 125	91.00 99	76.23 88	80.83 85	88.64 193

SymmetryMVS		77.43 51	77.09 51	78.44 95	82.56 150	52.32 177	89.31 42	84.15 196	72.20 16	73.23 85	91.05 85	46.52 125	91.00 99	76.23 88	78.55 118	92.00 53

viewdifsd2359ckpt07		74.81 121	74.01 121	77.21 136	79.62 244	53.13 154	85.70 151	83.75 204	68.12 72	68.14 168	87.33 202	46.51 127	87.92 234	73.32 127	73.63 200	90.57 122

test_fmvsmconf_n		74.41 127	74.05 119	75.49 200	74.16 371	48.38 299	82.66 270	72.57 413	67.05 97	75.11 64	92.88 45	46.35 128	87.81 241	83.93 26	71.71 226	90.28 133

fmvsm_l_conf0.5_n_3		75.73 102	75.78 77	75.61 191	76.03 336	48.33 303	85.34 162	72.92 412	67.16 91	78.55 46	93.85 16	46.22 129	87.53 261	85.61 14	76.30 154	90.98 107

tpm cat1		66.28 317	62.78 329	76.77 155	81.40 191	57.14 26	70.03 430	77.19 358	53.00 370	58.76 308	70.73 434	46.17 130	86.73 293	43.27 390	64.46 304	86.44 260

fmvsm_s_conf0.5_n_4		74.92 118	74.88 102	75.03 220	75.96 339	47.53 333	85.84 136	73.19 411	67.07 95	79.43 40	92.60 52	46.12 131	88.03 232	84.70 18	69.01 257	89.53 163

cl____		67.43 289	65.93 291	71.95 322	76.33 326	48.02 316	82.58 273	79.12 314	61.30 219	56.72 347	76.92 365	46.12 131	86.44 304	57.98 273	56.31 385	81.38 365

viewdifsd2359ckpt13		75.96 88	75.07 96	78.65 76	81.14 196	55.21 71	86.15 124	84.95 163	69.98 48	70.49 145	88.16 170	46.10 133	89.86 142	72.39 136	76.23 156	90.89 111

DIV-MVS_self_test		67.43 289	65.93 291	71.94 323	76.33 326	48.01 317	82.57 274	79.11 315	61.31 218	56.73 346	76.92 365	46.09 134	86.43 305	57.98 273	56.31 385	81.39 364

0.4-1-1-0.2		72.79 163	71.07 179	77.94 110	80.58 217	50.83 221	89.59 35	88.63 50	63.94 160	65.74 194	81.80 305	46.05 135	90.68 112	62.98 221	60.35 342	92.31 40

IS-MVSNet		68.80 259	67.55 254	72.54 299	78.50 281	43.43 402	81.03 321	79.35 310	59.12 266	57.27 340	86.71 210	46.05 135	87.70 252	44.32 386	75.60 171	86.49 259

diffmvs		75.11 114	74.65 110	76.46 161	78.52 280	53.35 144	83.28 251	79.94 289	70.51 40	71.64 112	88.72 144	46.02 137	86.08 318	77.52 79	75.75 169	89.96 150
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		74.92 118	73.70 127	78.60 83	80.28 229	54.94 86	84.77 195	80.56 275	69.96 50	69.38 153	88.38 156	46.01 138	90.50 121	72.44 135	71.49 230	90.38 129

0.4-1-1-0.1		72.39 172	70.70 185	77.46 124	80.45 223	50.04 247	89.09 47	88.45 59	63.06 181	64.91 209	81.60 309	45.98 139	90.46 122	62.40 225	60.34 344	91.88 57

E6new		75.74 98	74.80 106	78.56 86	79.85 237	54.92 92	85.87 132	84.72 176	70.19 44	70.90 131	87.73 190	45.98 139	89.71 150	72.16 138	75.78 166	91.06 101

E6		75.74 98	74.80 106	78.56 86	79.85 237	54.92 92	85.87 132	84.72 176	70.19 44	70.90 131	87.73 190	45.98 139	89.71 150	72.16 138	75.78 166	91.06 101

E5new		75.74 98	74.80 106	78.57 84	79.85 237	54.93 87	85.87 132	84.72 176	70.19 44	70.90 131	87.74 188	45.97 142	89.71 150	72.15 140	75.79 163	91.06 101

E5		75.74 98	74.80 106	78.57 84	79.85 237	54.93 87	85.87 132	84.72 176	70.19 44	70.90 131	87.74 188	45.97 142	89.71 150	72.15 140	75.79 163	91.06 101

blend_shiyan4		67.33 294	65.28 307	73.45 273	70.71 412	47.96 320	86.21 122	85.65 127	56.45 328	52.18 391	72.99 407	45.89 144	88.50 210	56.81 288	60.68 340	83.90 313

EI-MVSNet		69.70 240	68.70 226	72.68 295	75.00 357	48.90 281	79.54 351	87.16 88	61.05 224	63.88 230	83.74 262	45.87 145	90.44 123	57.42 284	64.68 303	78.70 394

IterMVS-LS		66.63 310	65.36 306	70.42 349	75.10 355	48.90 281	81.45 316	76.69 370	61.05 224	55.71 357	77.10 361	45.86 146	83.65 363	57.44 283	57.88 374	78.70 394
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs_AUTHOR		74.80 122	74.30 115	76.29 165	77.34 306	53.19 150	83.17 256	79.50 303	69.93 51	71.55 114	88.57 152	45.85 147	86.03 321	77.17 83	75.64 170	89.67 156

EIA-MVS		75.92 90	75.18 93	78.13 104	85.14 79	51.60 202	87.17 93	85.32 139	64.69 142	68.56 163	90.53 103	45.79 148	91.58 77	67.21 179	82.18 74	91.20 94

MVS		76.91 59	75.48 85	81.23 21	84.56 90	55.21 71	80.23 339	91.64 4	58.65 275	65.37 198	91.48 82	45.72 149	95.05 17	72.11 143	89.52 10	93.44 10

PAPM_NR		71.80 190	69.98 206	77.26 134	81.54 186	53.34 145	78.60 363	85.25 145	53.46 366	60.53 277	88.66 146	45.69 150	89.24 171	56.49 292	79.62 106	89.19 177

UWE-MVS-28		67.43 289	67.98 239	65.75 401	75.66 344	34.74 453	80.00 345	88.17 66	64.21 150	57.27 340	84.14 255	45.68 151	78.82 411	44.33 384	72.40 218	83.70 321

hybridnocas07		74.65 123	74.00 122	76.61 158	77.58 298	52.72 167	83.64 233	79.72 295	69.43 58	70.80 136	88.33 162	45.56 152	87.34 269	76.88 85	74.07 192	89.78 154

viewmambaseed2359dif		73.51 150	72.78 142	75.71 188	76.93 318	51.89 191	82.81 267	79.66 298	65.46 126	70.29 148	88.05 177	45.55 153	85.85 329	73.49 125	72.76 213	89.39 170

CS-MVS		76.77 65	76.70 62	76.99 143	83.55 113	48.75 286	88.60 55	85.18 147	66.38 109	72.47 98	91.62 78	45.53 154	90.99 103	74.48 108	82.51 70	91.23 91

DeepC-MVS_fast	67.50 3	78.00 41	77.63 40	79.13 57	88.52 29	55.12 76	89.95 28	85.98 117	68.31 68	71.33 121	92.75 48	45.52 155	90.37 125	71.15 147	85.14 50	91.91 55
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		74.48 124	74.12 117	75.56 194	76.96 317	47.85 325	85.32 166	69.80 439	64.16 152	78.74 43	93.48 25	45.51 156	89.29 169	86.48 11	66.62 279	89.55 161

viewmacassd2359aftdt		75.91 91	75.14 95	78.21 102	79.40 250	54.82 99	86.71 111	84.98 161	70.89 35	71.52 115	87.89 184	45.43 157	88.85 195	72.35 137	77.08 136	90.97 108

fmvsm_s_conf0.5_n_5		75.02 115	75.07 96	74.88 225	74.33 368	47.83 327	83.99 223	73.54 404	67.10 93	76.32 59	92.43 55	45.42 158	86.35 308	82.98 32	79.50 107	90.47 127

fmvsm_s_conf0.5_n_a		73.68 147	73.15 134	75.29 211	75.45 347	48.05 315	83.88 228	68.84 444	63.43 174	78.60 44	93.37 30	45.32 159	88.92 190	85.39 15	64.04 306	88.89 185

Test_1112_low_res		67.18 298	66.23 283	70.02 358	78.75 271	41.02 430	83.43 243	73.69 401	57.29 303	58.45 319	82.39 291	45.30 160	80.88 386	50.50 344	66.26 289	88.16 210

ETV-MVS		77.17 54	76.74 61	78.48 91	81.80 169	54.55 113	86.13 125	85.33 138	68.20 71	73.10 87	90.52 104	45.23 161	90.66 114	79.37 60	80.95 82	90.22 135

SPE-MVS-test		77.20 53	77.25 47	77.05 138	84.60 89	49.04 276	89.42 38	85.83 121	65.90 122	72.85 91	91.98 68	45.10 162	91.27 86	75.02 103	84.56 57	90.84 112

NR-MVSNet		67.25 296	65.99 289	71.04 340	73.27 380	43.91 396	85.32 166	84.75 174	66.05 120	53.65 381	82.11 299	45.05 163	85.97 326	47.55 365	56.18 388	83.24 331

UWE-MVS		72.17 181	72.15 158	72.21 310	82.26 155	44.29 391	86.83 106	89.58 27	65.58 125	65.82 191	85.06 238	45.02 164	84.35 353	54.07 313	75.18 176	87.99 217

train_agg		76.91 59	76.40 66	78.45 94	85.68 65	55.42 60	87.59 78	84.00 199	57.84 290	72.99 88	90.98 89	44.99 165	88.58 203	78.19 72	85.32 48	91.34 85

test_8					85.72 64	55.31 66	87.60 77	83.88 202	57.84 290	72.84 92	90.99 88	44.99 165	88.34 218

segment_acmp												44.97 167

hybrid		74.44 126	73.79 126	76.39 162	77.31 308	52.89 162	83.37 249	79.79 293	68.21 70	71.01 128	88.14 172	44.93 168	86.68 294	77.29 82	74.11 191	89.59 159

test_fmvsmconf0.1_n		73.69 146	73.15 134	75.34 206	70.71 412	48.26 306	82.15 286	71.83 419	66.75 102	74.47 72	92.59 53	44.89 169	87.78 248	83.59 28	71.35 233	89.97 149

TEST9					85.68 65	55.42 60	87.59 78	84.00 199	57.72 292	72.99 88	90.98 89	44.87 170	88.58 203

eth_miper_zixun_eth		66.98 305	65.28 307	72.06 315	75.61 345	50.40 234	81.00 322	76.97 365	62.00 204	56.99 344	76.97 363	44.84 171	85.58 332	58.75 261	54.42 404	80.21 382

MVSFormer		73.53 149	72.19 157	77.57 119	83.02 132	55.24 68	81.63 305	81.44 255	50.28 391	76.67 56	90.91 95	44.82 172	86.11 313	60.83 240	80.09 96	91.36 82

lupinMVS		78.38 33	78.11 33	79.19 53	83.02 132	55.24 68	91.57 15	84.82 169	69.12 62	76.67 56	92.02 64	44.82 172	90.23 132	80.83 51	80.09 96	92.08 46

WR-MVS		67.58 284	66.76 271	70.04 357	75.92 341	45.06 384	86.23 121	85.28 143	64.31 147	58.50 316	81.00 312	44.80 174	82.00 379	49.21 354	55.57 396	83.06 336

fmvsm_s_conf0.1_n		73.80 142	73.26 133	75.43 201	73.28 379	47.80 328	84.57 205	69.43 441	63.34 175	78.40 47	93.29 32	44.73 175	89.22 173	85.99 12	66.28 288	89.26 173

viewmamba		73.92 139	73.03 140	76.58 159	77.56 300	52.73 166	82.91 265	78.77 323	69.23 61	68.85 160	88.01 180	44.71 176	87.57 259	73.86 119	73.40 203	89.44 169

ZD-MVS					89.55 15	53.46 137		84.38 187	57.02 309	73.97 75	91.03 87	44.57 177	91.17 91	75.41 100	81.78 79

onestephybrid01		74.31 130	73.65 128	76.27 166	77.58 298	51.99 186	82.22 285	78.44 335	69.26 60	70.95 130	88.11 173	44.46 178	87.30 270	78.01 77	73.86 198	89.51 165

Fast-Effi-MVS+		72.73 165	71.15 177	77.48 122	82.75 144	54.76 101	86.77 110	80.64 271	63.05 182	65.93 189	84.01 256	44.42 179	89.03 180	56.45 295	76.36 152	88.64 193

dtuplus		73.09 157	72.29 154	75.52 199	76.27 330	51.82 195	82.99 263	79.98 286	65.08 139	70.11 150	87.66 194	44.38 180	85.64 331	71.56 144	72.55 216	89.11 180

fmvsm_s_conf0.1_n_a		72.82 162	72.05 162	75.12 217	70.95 410	47.97 318	82.72 269	68.43 446	62.52 196	78.17 48	93.08 38	44.21 181	88.86 192	84.82 17	63.54 313	88.54 201

PCF-MVS	61.03 10	70.10 226	68.40 232	75.22 216	77.15 314	51.99 186	79.30 356	82.12 236	56.47 327	61.88 263	86.48 216	43.98 182	87.24 273	55.37 306	72.79 212	86.43 261
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CDS-MVSNet		70.48 220	69.43 212	73.64 266	77.56 300	48.83 283	83.51 239	77.45 354	63.27 177	62.33 254	85.54 230	43.85 183	83.29 369	57.38 285	74.00 193	88.79 189
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EI-MVSNet-Vis-set		73.19 155	72.60 145	74.99 223	82.56 150	49.80 254	82.55 276	89.00 36	66.17 114	65.89 190	88.98 139	43.83 184	92.29 60	65.38 200	69.01 257	82.87 341

APD-MVS		76.15 83	75.68 78	77.54 121	88.52 29	53.44 140	87.26 91	85.03 160	53.79 363	74.91 66	91.68 76	43.80 185	90.31 128	74.36 111	81.82 77	88.87 186
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_HR		76.39 75	75.38 90	79.42 49	85.33 76	56.47 41	88.15 60	84.97 162	65.15 138	66.06 187	89.88 123	43.79 186	92.16 64	75.03 102	80.03 99	89.64 158

thres100view900		66.87 307	65.42 305	71.24 335	83.29 122	43.15 407	81.67 304	87.78 73	59.04 267	55.92 356	82.18 298	43.73 187	87.80 244	28.80 455	66.36 285	82.78 343

thres600view7		66.46 314	65.12 311	70.47 347	83.41 116	43.80 398	82.15 286	87.78 73	59.37 255	56.02 355	82.21 297	43.73 187	86.90 285	26.51 467	64.94 297	80.71 376

v148		68.24 272	66.35 279	73.88 257	71.76 398	51.47 206	84.23 214	81.90 246	63.69 167	58.94 301	76.44 372	43.72 189	87.78 248	60.63 242	55.86 393	82.39 346

SD-MVS		76.18 81	74.85 103	80.18 36	85.39 74	56.90 30	85.75 142	82.45 233	56.79 317	74.48 71	91.81 71	43.72 189	90.75 110	74.61 105	78.65 116	92.91 23
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		70.18 222	69.28 218	72.89 287	77.64 294	42.88 410	85.06 179	87.50 82	62.58 194	62.66 252	82.34 296	43.64 191	89.83 145	58.42 266	63.70 311	85.96 270

tfpn200view9		67.57 285	66.13 285	71.89 326	84.05 104	45.07 381	83.40 245	87.71 78	60.79 231	57.79 327	82.76 279	43.53 192	87.80 244	28.80 455	66.36 285	82.78 343

thres400		67.40 293	66.13 285	71.19 337	84.05 104	45.07 381	83.40 245	87.71 78	60.79 231	57.79 327	82.76 279	43.53 192	87.80 244	28.80 455	66.36 285	80.71 376

PAPR		75.20 112	74.13 116	78.41 96	88.31 34	55.10 78	84.31 212	85.66 125	63.76 164	67.55 172	90.73 100	43.48 194	89.40 165	66.36 185	77.03 137	90.73 116

kuosan		50.20 437	50.09 422	50.52 463	73.09 382	29.09 486	65.25 447	74.89 386	48.27 406	41.34 456	60.85 471	43.45 195	67.48 471	18.59 492	25.07 495	55.01 489

fmvsm_s_conf0.5_n_7		73.10 156	73.89 125	70.72 344	74.17 370	46.03 369	83.28 251	74.19 393	67.10 93	73.94 76	91.73 73	43.42 196	77.61 427	83.92 27	73.26 205	88.53 202

MP-MVS		74.99 116	74.33 114	76.95 145	82.89 139	53.05 157	85.63 152	83.50 212	57.86 289	67.25 174	90.24 112	43.38 197	88.85 195	76.03 90	82.23 73	88.96 183
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
casdiffseed414692147		74.22 131	72.73 143	78.69 71	79.85 237	54.64 111	85.13 174	83.67 210	69.07 63	69.41 152	86.47 217	43.27 198	90.69 111	63.77 214	73.91 197	90.73 116

EI-MVSNet-UG-set		72.37 174	71.73 165	74.29 244	81.60 182	49.29 271	81.85 295	88.64 49	65.29 135	65.05 203	88.29 164	43.18 199	91.83 71	63.74 215	67.97 269	81.75 353

thres200		68.71 261	67.27 262	73.02 281	84.73 85	46.76 349	85.03 182	87.73 76	62.34 200	59.87 281	83.45 269	43.15 200	88.32 220	31.25 447	67.91 270	83.98 309

PHI-MVS		77.49 49	77.00 53	78.95 61	85.33 76	50.69 224	88.57 56	88.59 55	58.14 282	73.60 78	93.31 31	43.14 201	93.79 31	73.81 120	88.53 13	92.37 37

ab-mvs		70.65 216	69.11 221	75.29 211	80.87 207	46.23 367	73.48 403	85.24 146	59.99 242	66.65 178	80.94 314	43.13 202	88.69 198	63.58 216	68.07 267	90.95 109

CDPH-MVS		76.05 86	75.19 92	78.62 79	86.51 55	54.98 84	87.32 86	84.59 183	58.62 276	70.75 137	90.85 97	43.10 203	90.63 117	70.50 151	84.51 59	90.24 134

reproduce_monomvs		69.71 236	68.52 229	73.29 278	86.43 57	48.21 308	83.91 226	86.17 114	68.02 78	54.91 364	77.46 354	42.96 204	88.86 192	68.44 170	48.38 433	82.80 342

v8		67.25 296	64.99 313	74.04 251	72.89 386	53.31 147	82.37 283	80.11 284	61.54 214	54.29 374	76.02 381	42.89 205	88.41 214	58.43 264	56.36 383	80.39 380

EC-MVSNet		75.30 106	75.20 91	75.62 190	80.98 201	49.00 277	87.43 82	84.68 181	63.49 173	70.97 129	90.15 118	42.86 206	91.14 93	74.33 112	81.90 76	86.71 254

h-mvs33		73.95 137	72.89 141	77.15 137	80.17 232	50.37 238	84.68 199	83.33 213	68.08 74	71.97 105	88.65 149	42.50 207	91.15 92	78.82 65	57.78 376	89.91 152

hse-mvs2		71.44 198	70.68 186	73.73 264	76.34 325	47.44 338	79.45 354	79.47 305	68.08 74	71.97 105	86.01 225	42.50 207	86.93 284	78.82 65	53.46 414	86.83 250

SteuartSystems-ACMMP		77.08 57	76.33 67	79.34 50	80.98 201	55.31 66	89.76 33	86.91 93	62.94 184	71.65 111	91.56 80	42.33 209	92.56 53	77.14 84	83.69 63	90.15 140
Skip Steuart: Steuart Systems R&D Blog.
HyFIR lowres test		69.94 233	67.58 252	77.04 139	77.11 315	57.29 24	81.49 315	79.11 315	58.27 280	58.86 305	80.41 318	42.33 209	86.96 281	61.91 231	68.68 264	86.87 244

ZNCC-MVS		75.82 96	75.02 99	78.23 101	83.88 109	53.80 129	86.91 103	86.05 116	59.71 247	67.85 171	90.55 102	42.23 211	91.02 97	72.66 134	85.29 49	89.87 153

FMVSNet3		68.84 256	67.40 258	73.19 280	85.05 80	48.53 293	85.71 148	85.36 136	60.90 230	57.58 332	79.15 337	42.16 212	86.77 291	47.25 368	63.40 314	84.27 300

VPA-MVSNet		71.12 203	70.66 187	72.49 301	78.75 271	44.43 389	87.64 72	90.02 22	63.97 158	65.02 204	81.58 310	42.14 213	87.42 265	63.42 217	63.38 317	85.63 278

jason		77.01 58	76.45 65	78.69 71	79.69 243	54.74 102	90.56 24	83.99 201	68.26 69	74.10 74	90.91 95	42.14 213	89.99 138	79.30 61	79.12 110	91.36 82
jason: jason.
CLD-MVS		75.60 103	75.39 89	76.24 168	80.69 213	52.40 174	90.69 23	86.20 112	74.40 6	65.01 205	88.93 140	42.05 215	90.58 118	76.57 87	73.96 194	85.73 274
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 93	74.83 104	78.91 62	88.08 40	51.94 188	91.30 17	89.28 31	57.91 287	71.19 123	89.20 136	42.03 216	92.77 45	69.41 159	75.07 181	92.01 51

DCV-MVSNet		75.85 93	74.83 104	78.91 62	88.08 40	51.94 188	91.30 17	89.28 31	57.91 287	71.19 123	89.20 136	42.03 216	92.77 45	69.41 159	75.07 181	92.01 51

TAMVS		69.51 244	68.16 237	73.56 270	76.30 328	48.71 289	82.57 274	77.17 359	62.10 202	61.32 268	84.23 253	41.90 218	83.46 366	54.80 310	73.09 209	88.50 204

TransMVSNet (Re)		62.82 353	60.76 355	69.02 366	73.98 373	41.61 424	86.36 117	79.30 313	56.90 310	52.53 386	76.44 372	41.85 219	87.60 258	38.83 407	40.61 464	77.86 408

VPNet		72.07 182	71.42 172	74.04 251	78.64 277	47.17 343	89.91 31	87.97 70	72.56 14	64.66 212	85.04 241	41.83 220	88.33 219	61.17 238	60.97 338	86.62 255

v2v482		69.55 243	67.64 251	75.26 215	72.32 393	53.83 128	84.93 189	81.94 242	65.37 132	60.80 273	79.25 335	41.62 221	88.98 185	63.03 220	59.51 351	82.98 339

API-MVS		74.17 133	72.07 161	80.49 27	90.02 12	58.55 11	87.30 88	84.27 190	57.51 298	65.77 193	87.77 187	41.61 222	95.97 12	51.71 337	82.63 69	86.94 242

GeoE		69.96 232	67.88 244	76.22 169	81.11 199	51.71 200	84.15 217	76.74 368	59.83 244	60.91 271	84.38 250	41.56 223	88.10 229	51.67 338	70.57 241	88.84 187

CHOSEN 1792x2688		76.24 80	74.03 120	82.88 2	83.09 128	62.84 2	85.73 146	85.39 135	69.79 52	64.87 210	83.49 268	41.52 224	93.69 35	70.55 149	81.82 77	92.12 45

LFMVS		78.52 29	77.14 50	82.67 4	89.58 14	58.90 9	91.27 19	88.05 69	63.22 178	74.63 68	90.83 98	41.38 225	94.40 22	75.42 99	79.90 101	94.72 2

MAR-MVS		76.76 66	75.60 82	80.21 34	90.87 8	54.68 108	89.14 46	89.11 34	62.95 183	70.54 143	92.33 57	41.05 226	94.95 18	57.90 277	86.55 33	91.00 106
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		43.51 447	44.07 448	41.82 474	63.75 465	21.90 499	63.80 453	72.05 417	39.59 453	33.35 485	54.54 484	41.04 227	57.30 488	10.75 506	17.77 504	46.26 497

test_fmvsmvis_n_1920		71.29 199	70.38 195	74.00 253	71.04 409	48.79 285	79.19 357	64.62 458	62.75 190	66.73 176	91.99 66	40.94 228	88.35 217	83.00 31	73.18 206	84.85 292

GST-MVS		74.87 120	73.90 123	77.77 114	83.30 121	53.45 139	85.75 142	85.29 142	59.22 260	66.50 183	89.85 124	40.94 228	90.76 109	70.94 148	83.35 64	89.10 181

usedtu_dtu_shiyan1		69.05 250	67.91 240	72.46 303	75.40 348	46.24 365	85.74 144	86.80 95	65.23 136	58.75 309	80.31 319	40.90 230	86.83 287	53.29 318	64.77 298	84.31 298

FE-MVSNET3		69.05 250	67.91 240	72.46 303	75.39 349	46.24 365	85.74 144	86.80 95	65.23 136	58.75 309	80.31 319	40.90 230	86.83 287	53.29 318	64.77 298	84.31 298

DU-MVS		66.84 308	65.74 296	70.16 353	73.27 380	42.59 413	81.50 313	82.92 226	63.53 171	58.51 314	82.11 299	40.75 232	84.64 351	53.11 321	55.96 391	83.24 331

Baseline_NR-MVSNet		65.49 328	64.27 321	69.13 365	74.37 367	41.65 423	83.39 247	78.85 319	59.56 250	59.62 287	76.88 367	40.75 232	87.44 264	49.99 346	55.05 398	78.28 403

miper_lstm_enhance		63.91 340	62.30 334	68.75 372	75.06 356	46.78 348	69.02 434	81.14 260	59.68 249	52.76 385	72.39 415	40.71 234	77.99 421	56.81 288	53.09 415	81.48 360

HFP-MVS		74.37 128	73.13 138	78.10 105	84.30 98	53.68 133	85.58 153	84.36 188	56.82 315	65.78 192	90.56 101	40.70 235	90.90 105	69.18 164	80.88 83	89.71 155

RRT-MVS		73.29 153	71.37 173	79.07 60	84.63 88	54.16 125	78.16 365	86.64 103	61.67 211	60.17 279	82.35 295	40.63 236	92.26 62	70.19 153	77.87 126	90.81 113

CL-MVSNet_self_test		62.98 351	61.14 352	68.50 378	65.86 451	42.96 408	84.37 208	82.98 224	60.98 226	53.95 377	72.70 411	40.43 237	83.71 362	41.10 400	47.93 437	78.83 393

ACMMP_NAP		76.43 74	75.66 81	78.73 69	81.92 166	54.67 109	84.06 221	85.35 137	61.10 223	72.99 88	91.50 81	40.25 238	91.00 99	76.84 86	86.98 26	90.51 126

v1144		68.81 258	66.82 269	74.80 228	72.34 392	53.46 137	84.68 199	81.77 249	64.25 149	60.28 278	77.91 347	40.23 239	88.95 187	60.37 249	59.52 350	81.97 349

WR-MVS_H		58.91 384	58.04 376	61.54 434	69.07 434	33.83 460	76.91 372	81.99 241	51.40 383	48.17 418	74.67 388	40.23 239	74.15 447	31.78 444	48.10 435	76.64 423

原ACMM1				76.13 174	84.89 84	54.59 112		85.26 144	51.98 377	66.70 177	87.07 206	40.15 241	89.70 154	51.23 341	85.06 54	84.10 303

MVP-Stereo		70.97 208	70.44 191	72.59 298	76.03 336	51.36 208	85.02 184	86.99 92	60.31 238	56.53 351	78.92 339	40.11 242	90.00 137	60.00 252	90.01 7	76.41 426
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v10		66.61 311	64.20 322	73.83 260	72.59 389	53.37 143	81.88 294	79.91 291	61.11 222	54.09 376	75.60 383	40.06 243	88.26 225	56.47 293	56.10 389	79.86 386

test_fmvsmconf0.01_n		71.97 185	70.95 183	75.04 219	66.21 448	47.87 324	80.35 336	70.08 436	65.85 123	72.69 93	91.68 76	39.99 244	87.67 253	82.03 40	69.66 252	89.58 160

MP-MVS-pluss		75.54 105	75.03 98	77.04 139	81.37 192	52.65 170	84.34 211	84.46 186	61.16 220	69.14 157	91.76 72	39.98 245	88.99 184	78.19 72	84.89 55	89.48 168
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TranMVSNet+NR-MVSNet		66.94 306	65.61 299	70.93 342	73.45 376	43.38 403	83.02 262	84.25 191	65.31 134	58.33 321	81.90 303	39.92 246	85.52 333	49.43 351	54.89 400	83.89 314

Patchmatch-test		53.33 421	48.17 434	68.81 370	73.31 377	42.38 417	42.98 492	58.23 473	32.53 477	38.79 467	70.77 432	39.66 247	73.51 453	25.18 470	52.06 419	90.55 123

viewdifsd2359ckpt11		70.68 214	69.10 222	75.40 202	75.33 351	50.85 219	81.57 309	78.00 342	66.99 98	64.96 207	85.52 231	39.52 248	86.81 289	68.86 167	61.15 337	88.56 199

viewmsd2359difaftdt		70.68 214	69.10 222	75.40 202	75.33 351	50.85 219	81.57 309	78.00 342	66.99 98	64.96 207	85.52 231	39.52 248	86.81 289	68.86 167	61.16 336	88.56 199

Test By Simon												39.38 250

v144192		67.86 277	65.76 295	74.16 247	71.68 399	53.09 155	84.14 218	80.83 268	62.85 189	59.21 297	77.28 358	39.30 251	88.00 233	58.67 262	57.88 374	81.40 363

BH-w/o		70.02 229	68.51 230	74.56 233	82.77 143	50.39 235	86.60 115	78.14 340	59.77 246	59.65 285	85.57 229	39.27 252	87.30 270	49.86 348	74.94 185	85.99 268

dmvs_testset		57.65 395	58.21 375	55.97 455	74.62 362	9.82 517	63.75 454	63.34 464	67.23 89	48.89 416	83.68 267	39.12 253	76.14 439	23.43 477	59.80 349	81.96 350

CR-MVSNet		62.47 359	59.04 371	72.77 291	73.97 374	56.57 37	60.52 467	71.72 421	60.04 241	57.49 335	65.86 452	38.94 254	80.31 397	42.86 394	59.93 346	81.42 361

Patchmtry		56.56 401	52.95 408	67.42 385	72.53 390	50.59 228	59.05 471	71.72 421	37.86 461	46.92 430	65.86 452	38.94 254	80.06 401	36.94 416	46.72 447	71.60 462

sam_mvs1												38.86 256				88.13 213

UA-Net		67.32 295	66.23 283	70.59 346	78.85 269	41.23 429	73.60 401	75.45 382	61.54 214	66.61 180	84.53 249	38.73 257	86.57 301	42.48 397	74.24 190	83.98 309

cdsmvs_eth3d_5k		18.33 476	24.44 468	0.00 542	0.00 565	0.00 568	0.00 554	89.40 29	0.00 558	0.00 562	92.02 64	38.55 258	0.00 560	0.00 561	0.00 559	0.00 558

patchmatchnet-post											59.74 475	38.41 259	79.91 404

CHOSEN 280x420		57.53 397	56.38 389	60.97 439	74.01 372	48.10 313	46.30 487	54.31 480	48.18 408	50.88 406	77.43 356	38.37 260	59.16 486	54.83 308	63.14 322	75.66 430

lecture		74.14 134	73.05 139	77.44 125	81.66 177	50.39 235	87.43 82	84.22 195	51.38 384	72.10 103	90.95 94	38.31 261	93.23 38	70.51 150	80.83 85	88.69 191

SD_0403		65.51 327	65.18 310	66.48 397	78.37 284	29.94 480	74.64 393	78.55 331	66.47 107	54.87 365	84.35 252	38.20 262	82.47 373	38.90 406	72.30 221	87.05 240

V42		67.66 282	65.60 300	73.86 258	70.69 415	53.63 134	81.50 313	78.61 329	63.85 161	59.49 291	77.49 353	37.98 263	87.65 254	62.33 226	58.43 361	80.29 381

tpmvs		62.45 360	59.42 367	71.53 332	83.93 106	54.32 117	70.03 430	77.61 351	51.91 378	53.48 382	68.29 443	37.91 264	86.66 296	33.36 437	58.27 364	73.62 448

PatchmatchNet		67.07 303	63.63 325	77.40 126	83.10 126	58.03 13	72.11 421	77.77 348	58.85 271	59.37 292	70.83 431	37.84 265	84.93 346	42.96 393	69.83 251	89.26 173
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pcd_1.5k_mvsjas		3.15 495	4.20 497	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	0.00 560	37.77 266	0.00 560	0.00 561	0.00 559	0.00 558

PS-MVSNAJss		68.78 260	67.17 264	73.62 268	73.01 383	48.33 303	84.95 188	84.81 170	59.30 259	58.91 304	79.84 327	37.77 266	88.86 192	62.83 223	63.12 323	83.67 323

PS-MVSNAJ		80.06 17	79.52 19	81.68 15	85.58 70	60.97 3	91.69 12	87.02 91	70.62 37	80.75 28	93.22 34	37.77 266	92.50 54	82.75 34	86.25 36	91.57 71

pm-mvs1		64.12 338	62.56 332	68.78 371	71.68 399	38.87 440	82.89 266	81.57 252	55.54 342	53.89 378	77.82 349	37.73 269	86.74 292	48.46 361	53.49 412	80.72 375

RPMNet		59.29 376	54.25 401	74.42 237	73.97 374	56.57 37	60.52 467	76.98 362	35.72 471	57.49 335	58.87 478	37.73 269	85.26 339	27.01 466	59.93 346	81.42 361

IMVS_0403		72.39 172	70.59 189	77.79 113	82.26 155	50.87 215	81.76 298	85.16 150	62.91 185	64.87 210	86.07 219	37.71 271	92.40 57	64.03 209	70.55 242	90.09 142

SDMVSNet		71.89 187	70.62 188	75.70 189	81.70 173	51.61 201	73.89 398	88.72 47	66.58 103	61.64 265	82.38 292	37.63 272	89.48 162	77.44 80	65.60 293	86.01 266

xiu_mvs_v2_base		79.86 19	79.31 21	81.53 17	85.03 82	60.73 4	91.65 13	86.86 94	70.30 42	80.77 27	93.07 39	37.63 272	92.28 61	82.73 35	85.71 42	91.57 71

Patchmatch-RL test		58.72 387	54.32 400	71.92 324	63.91 464	44.25 392	61.73 463	55.19 478	57.38 302	49.31 414	54.24 485	37.60 274	80.89 385	62.19 229	47.28 442	90.63 120

HPM-MVS		72.60 167	71.50 169	75.89 182	82.02 162	51.42 207	80.70 330	83.05 222	56.12 335	64.03 226	89.53 129	37.55 275	88.37 215	70.48 152	80.04 98	87.88 218
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test_post											16.22 520	37.52 276	84.72 349

PatchT		56.60 400	52.97 407	67.48 384	72.94 385	46.16 368	57.30 475	73.78 400	38.77 456	54.37 372	57.26 481	37.52 276	78.06 418	32.02 442	52.79 416	78.23 405

v1192		67.96 276	65.74 296	74.63 232	71.79 397	53.43 142	84.06 221	80.99 266	63.19 179	59.56 288	77.46 354	37.50 278	88.65 199	58.20 270	58.93 357	81.79 352

HQP2-MVS												37.35 279

HQP-MVS		72.34 175	71.44 171	75.03 220	79.02 264	51.56 203	88.00 62	83.68 206	65.45 127	64.48 218	85.13 236	37.35 279	88.62 200	66.70 181	73.12 207	84.91 290

region2R		73.75 144	72.55 146	77.33 127	83.90 108	52.98 159	85.54 157	84.09 197	56.83 314	65.10 202	90.45 105	37.34 281	90.24 131	68.89 166	80.83 85	88.77 190

TESTMET0.1,1		72.86 161	72.33 151	74.46 235	81.98 163	50.77 222	85.13 174	85.47 131	66.09 117	67.30 173	83.69 265	37.27 282	83.57 364	65.06 203	78.97 114	89.05 182

mvsmamba		69.38 245	67.52 256	74.95 224	82.86 140	52.22 182	67.36 443	76.75 366	61.14 221	49.43 412	82.04 301	37.26 283	84.14 355	73.93 117	76.91 140	88.50 204

ACMMPR		73.76 143	72.61 144	77.24 135	83.92 107	52.96 160	85.58 153	84.29 189	56.82 315	65.12 201	90.45 105	37.24 284	90.18 133	69.18 164	80.84 84	88.58 197

MonoMVSNet		66.80 309	64.41 318	73.96 254	76.21 331	48.07 314	76.56 377	78.26 338	64.34 146	54.32 373	74.02 394	37.21 285	86.36 307	64.85 204	53.96 407	87.45 230

sss		70.49 219	70.13 202	71.58 331	81.59 183	39.02 438	80.78 328	84.71 180	59.34 256	66.61 180	88.09 174	37.17 286	85.52 333	61.82 233	71.02 236	90.20 137

reproduce-ours		71.77 192	70.43 192	75.78 185	81.96 164	49.54 262	82.54 277	81.01 264	48.77 403	69.21 155	90.96 91	37.13 287	89.40 165	66.28 186	76.01 159	88.39 207

our_new_method		71.77 192	70.43 192	75.78 185	81.96 164	49.54 262	82.54 277	81.01 264	48.77 403	69.21 155	90.96 91	37.13 287	89.40 165	66.28 186	76.01 159	88.39 207

EPNet_dtu		66.25 318	66.71 272	64.87 410	78.66 276	34.12 458	82.80 268	75.51 380	61.75 209	64.47 221	86.90 207	37.06 289	72.46 459	43.65 389	69.63 254	88.02 216
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v1921920		67.45 288	65.23 309	74.10 250	71.51 402	52.90 161	83.75 232	80.44 276	62.48 198	59.12 298	77.13 359	36.98 290	87.90 236	57.53 282	58.14 368	81.49 358

旧先验1					81.57 185	47.48 335		71.83 419			88.66 146	36.94 291			78.34 121	88.67 192

test-LLR		69.65 241	69.01 224	71.60 329	78.67 273	48.17 309	85.13 174	79.72 295	59.18 263	63.13 244	82.58 286	36.91 292	80.24 398	60.56 244	75.17 177	86.39 262

test0.0.03 1		62.54 356	62.44 333	62.86 426	72.28 395	29.51 483	82.93 264	78.78 322	59.18 263	53.07 384	82.41 290	36.91 292	77.39 428	37.45 410	58.96 356	81.66 356

MDTV_nov1_ep13_2view						43.62 399	71.13 426		54.95 352	59.29 296		36.76 294		46.33 375		87.32 233

KD-MVS_2432*1600		59.04 382	56.44 386	66.86 391	79.07 261	45.87 372	72.13 419	80.42 277	55.03 350	48.15 419	71.01 429	36.73 295	78.05 419	35.21 427	30.18 489	76.67 420

miper_refine_blended		59.04 382	56.44 386	66.86 391	79.07 261	45.87 372	72.13 419	80.42 277	55.03 350	48.15 419	71.01 429	36.73 295	78.05 419	35.21 427	30.18 489	76.67 420

GBi-Net		67.09 301	65.47 302	71.96 319	82.71 145	46.36 358	83.52 235	83.31 214	58.55 277	57.58 332	76.23 376	36.72 297	86.20 309	47.25 368	63.40 314	83.32 328

test1		67.09 301	65.47 302	71.96 319	82.71 145	46.36 358	83.52 235	83.31 214	58.55 277	57.58 332	76.23 376	36.72 297	86.20 309	47.25 368	63.40 314	83.32 328

FMVSNet2		67.57 285	65.79 294	72.90 285	82.71 145	47.97 318	85.15 173	84.93 166	58.55 277	56.71 348	78.26 345	36.72 297	86.67 295	46.15 376	62.94 325	84.07 304

AUN-MVS		68.20 273	66.35 279	73.76 262	76.37 324	47.45 337	79.52 353	79.52 302	60.98 226	62.34 253	86.02 223	36.59 300	86.94 283	62.32 227	53.47 413	86.89 243

reproduce_model		71.07 205	69.67 210	75.28 213	81.51 189	48.82 284	81.73 301	80.57 274	47.81 409	68.26 165	90.78 99	36.49 301	88.60 202	65.12 202	74.76 187	88.42 206

BH-untuned		68.28 270	66.40 278	73.91 256	81.62 180	50.01 248	85.56 155	77.39 355	57.63 295	57.47 337	83.69 265	36.36 302	87.08 277	44.81 381	73.08 210	84.65 293

fmvsm_s_conf0.5_n_2		72.02 183	71.72 166	72.92 284	76.79 320	45.90 370	84.48 206	66.11 452	64.26 148	76.12 60	93.40 27	36.26 303	86.04 320	81.47 46	66.54 282	86.82 251

EPMVS		68.45 266	65.44 304	77.47 123	84.91 83	56.17 47	71.89 423	81.91 245	61.72 210	60.85 272	72.49 412	36.21 304	87.06 278	47.32 367	71.62 227	89.17 178

wanda-best-256-512		64.87 329	62.23 335	72.81 288	70.49 417	46.85 346	85.71 148	85.71 123	56.85 311	51.25 397	72.31 418	36.16 305	87.84 238	52.67 331	48.90 427	83.73 316

FE-blended-shiyan7		64.87 329	62.23 335	72.81 288	70.49 417	46.85 346	85.71 148	85.71 123	56.85 311	51.25 397	72.31 418	36.16 305	87.84 238	52.67 331	48.90 427	83.73 316

usedtu_blend_shiyan5		63.62 344	60.36 360	73.40 274	70.49 417	47.96 320	79.13 358	80.68 270	47.51 413	51.25 397	72.31 418	36.16 305	88.50 210	56.81 288	48.90 427	83.73 316

MSLP-MVS++		74.21 132	72.25 155	80.11 41	81.45 190	56.47 41	86.32 119	79.65 300	58.19 281	66.36 184	92.29 58	36.11 308	90.66 114	67.39 177	82.49 71	93.18 18

FA-MVS(test-final)		69.00 254	66.60 276	76.19 172	83.48 115	47.96 320	74.73 390	82.07 240	57.27 304	62.18 256	78.47 343	36.09 309	92.89 41	53.76 317	71.32 234	87.73 222

MTAPA		72.73 165	71.22 175	77.27 132	81.54 186	53.57 135	67.06 445	81.31 257	59.41 254	68.39 164	90.96 91	36.07 310	89.01 181	73.80 121	82.45 72	89.23 175

HQP_MVS		70.96 209	69.91 207	74.12 249	77.95 290	49.57 256	85.76 140	82.59 229	63.60 169	62.15 258	83.28 273	36.04 311	88.30 222	65.46 195	72.34 219	84.49 294

plane_prior6					78.42 283	49.39 269						36.04 311

sam_mvs												35.99 313

blended_shiyan6		64.70 331	62.04 339	72.69 293	70.34 420	46.60 354	85.48 159	85.65 127	56.59 323	50.91 405	72.18 422	35.82 314	87.81 241	52.46 335	48.90 427	83.66 324

blended_shiyan8		64.70 331	62.04 339	72.69 293	70.33 421	46.62 352	85.48 159	85.66 125	56.58 324	50.94 404	72.18 422	35.81 315	87.80 244	52.47 334	48.91 426	83.65 325

PGM-MVS		72.60 167	71.20 176	76.80 152	82.95 135	52.82 165	83.07 260	82.14 235	56.51 326	63.18 243	89.81 125	35.68 316	89.76 148	67.30 178	80.19 95	87.83 219

icg_test_0407_2		71.26 200	69.99 205	75.09 218	82.26 155	50.87 215	79.65 349	85.16 150	62.91 185	63.68 236	86.07 219	35.56 317	84.32 354	64.03 209	70.55 242	90.09 142

IMVS_0407		71.97 185	70.10 203	77.57 119	82.26 155	50.87 215	80.69 331	85.16 150	62.91 185	63.68 236	86.07 219	35.56 317	91.75 73	64.03 209	70.55 242	90.09 142

XVS		72.92 159	71.62 167	76.81 150	83.41 116	52.48 171	84.88 190	83.20 219	58.03 283	63.91 228	89.63 128	35.50 319	89.78 146	65.50 192	80.50 90	88.16 210

X-MVStestdata		65.85 323	62.20 337	76.81 150	83.41 116	52.48 171	84.88 190	83.20 219	58.03 283	63.91 228	4.82 532	35.50 319	89.78 146	65.50 192	80.50 90	88.16 210

v1240		66.99 304	64.68 315	73.93 255	71.38 406	52.66 169	83.39 247	79.98 286	61.97 206	58.44 320	77.11 360	35.25 321	87.81 241	56.46 294	58.15 366	81.33 366

test1111		71.06 206	70.42 194	72.97 283	79.48 249	41.49 426	84.82 194	82.74 228	64.20 151	62.98 246	87.43 199	35.20 322	87.92 234	58.54 263	78.42 120	89.49 167

dp		64.41 334	61.58 344	72.90 285	82.40 152	54.09 126	72.53 411	76.59 372	60.39 237	55.68 358	70.39 435	35.18 323	76.90 434	39.34 405	61.71 333	87.73 222

Syy-MVS		61.51 365	61.35 349	62.00 430	81.73 171	30.09 477	80.97 323	81.02 262	60.93 228	55.06 362	82.64 284	35.09 324	80.81 388	16.40 496	58.32 362	75.10 437

ECVR-MVS		71.81 189	71.00 182	74.26 245	80.12 233	43.49 400	84.69 198	82.16 234	64.02 154	64.64 213	87.43 199	35.04 325	89.21 174	61.24 237	79.66 104	90.08 146

CP-MVS		72.59 169	71.46 170	76.00 179	82.93 137	52.32 177	86.93 102	82.48 232	55.15 348	63.65 238	90.44 108	35.03 326	88.53 209	68.69 169	77.83 128	87.15 238

fmvsm_s_conf0.1_n_2		71.45 197	71.01 181	72.78 290	75.37 350	45.82 374	84.18 216	64.59 460	64.02 154	75.67 61	93.02 40	34.99 327	85.99 323	81.18 50	66.04 291	86.52 258

CP-MVSNet		58.54 391	57.57 379	61.46 435	68.50 438	33.96 459	76.90 373	78.60 330	51.67 382	47.83 422	76.60 371	34.99 327	72.79 457	35.45 424	47.58 439	77.64 413

guyue		70.53 218	69.12 220	74.76 229	77.61 295	47.53 333	84.86 192	85.17 148	62.70 192	62.18 256	83.74 262	34.72 329	89.86 142	64.69 205	66.38 284	86.87 244

dmvs_re		67.61 283	66.00 288	72.42 305	81.86 168	43.45 401	64.67 451	80.00 285	69.56 57	60.07 280	85.00 242	34.71 330	87.63 255	51.48 339	66.68 277	86.17 265

MDTV_nov1_ep13			61.56 345		81.68 175	55.12 76	72.41 414	78.18 339	59.19 261	58.85 306	69.29 440	34.69 331	86.16 312	36.76 419	62.96 324

SSC-MVS3.2		68.13 274	66.89 266	71.85 327	82.26 155	43.97 395	82.09 289	89.29 30	71.74 19	61.12 270	79.83 328	34.60 332	87.45 263	41.23 399	59.85 348	84.14 301

WB-MVSnew		69.36 246	68.24 235	72.72 292	79.26 255	49.40 268	85.72 147	88.85 42	61.33 217	64.59 216	82.38 292	34.57 333	87.53 261	46.82 372	70.63 239	81.22 370

3Dnovator	64.70 6	74.46 125	72.48 147	80.41 31	82.84 142	55.40 63	83.08 259	88.61 53	67.61 86	59.85 282	88.66 146	34.57 333	93.97 28	58.42 266	88.70 12	91.85 59

VortexMVS		68.49 265	66.84 268	73.46 272	81.10 200	48.75 286	84.63 202	84.73 175	62.05 203	57.22 342	77.08 362	34.54 335	89.20 175	63.08 218	57.12 380	82.43 345

Vis-MVSNet		70.61 217	69.34 215	74.42 237	80.95 206	48.49 295	86.03 129	77.51 353	58.74 274	65.55 197	87.78 186	34.37 336	85.95 327	52.53 333	80.61 88	88.80 188
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_post1							70.84 427				14.72 523	34.33 337	83.86 358	48.80 356

OPM-MVS		70.75 213	69.58 211	74.26 245	75.55 346	51.34 209	86.05 128	83.29 217	61.94 207	62.95 248	85.77 226	34.15 338	88.44 213	65.44 198	71.07 235	82.99 337
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DP-MVS Recon		71.99 184	70.31 197	77.01 141	90.65 9	53.44 140	89.37 39	82.97 225	56.33 329	63.56 241	89.47 130	34.02 339	92.15 66	54.05 314	72.41 217	85.43 281

PEN-MVS		58.35 392	57.15 381	61.94 431	67.55 445	34.39 454	77.01 371	78.35 337	51.87 379	47.72 423	76.73 369	33.91 340	73.75 451	34.03 434	47.17 443	77.68 411

QAPM		71.88 188	69.33 216	79.52 47	82.20 161	54.30 118	86.30 120	88.77 45	56.61 322	59.72 284	87.48 197	33.90 341	95.36 14	47.48 366	81.49 80	88.90 184

新几何1				73.30 277	83.10 126	53.48 136		71.43 426	45.55 429	66.14 185	87.17 204	33.88 342	80.54 394	48.50 359	80.33 94	85.88 273

1314		71.11 204	69.41 213	76.22 169	79.32 253	50.49 230	80.23 339	85.14 156	59.44 253	58.93 302	88.89 142	33.83 343	89.60 157	61.49 235	77.42 133	88.57 198

SR-MVS		70.92 210	69.73 209	74.50 234	83.38 120	50.48 232	84.27 213	79.35 310	48.96 401	66.57 182	90.45 105	33.65 344	87.11 276	66.42 183	74.56 189	85.91 271

mPP-MVS		71.79 191	70.38 195	76.04 177	82.65 148	52.06 183	84.45 207	81.78 248	55.59 340	62.05 261	89.68 127	33.48 345	88.28 224	65.45 197	78.24 122	87.77 221

OMC-MVS		65.97 322	65.06 312	68.71 373	72.97 384	42.58 415	78.61 362	75.35 383	54.72 354	59.31 294	86.25 218	33.30 346	77.88 423	57.99 272	67.05 275	85.66 276

BH-RMVSNet		70.08 227	68.01 238	76.27 166	84.21 102	51.22 213	87.29 89	79.33 312	58.96 270	63.63 239	86.77 209	33.29 347	90.30 130	44.63 383	73.96 194	87.30 234

gbinet_0.2-2-1-0.02		64.20 336	61.39 347	72.63 296	70.85 411	46.32 362	85.92 131	85.98 117	55.27 347	51.88 394	72.29 421	33.14 348	87.82 240	48.50 359	48.72 431	83.73 316

SSM_0407		69.71 236	67.38 259	76.69 157	80.45 223	51.81 196	81.36 317	80.18 281	54.07 361	63.82 232	85.05 239	33.09 349	91.01 98	59.40 253	68.97 259	87.25 235

SSM_0404		70.13 223	67.87 247	76.88 148	80.22 230	52.00 185	81.71 303	80.18 281	54.07 361	65.36 199	85.05 239	33.09 349	91.03 95	59.40 253	71.80 225	87.63 225

JIA-IIPM		52.33 427	47.77 437	66.03 399	71.20 407	46.92 344	40.00 497	76.48 373	37.10 464	46.73 431	37.02 498	32.96 351	77.88 423	35.97 421	52.45 418	73.29 452

PS-CasMVS		58.12 393	57.03 383	61.37 436	68.24 442	33.80 461	76.73 375	78.01 341	51.20 385	47.54 426	76.20 379	32.85 352	72.76 458	35.17 429	47.37 441	77.55 414

DTE-MVSNet		57.03 398	55.73 393	60.95 440	65.94 450	32.57 466	75.71 378	77.09 361	51.16 386	46.65 433	76.34 374	32.84 353	73.22 456	30.94 448	44.87 452	77.06 416

pmmvs4		63.34 348	61.07 353	70.16 353	70.14 423	50.53 229	79.97 346	71.41 427	55.08 349	54.12 375	78.58 341	32.79 354	82.09 378	50.33 345	57.22 379	77.86 408

TR-MVS		69.71 236	67.85 248	75.27 214	82.94 136	48.48 296	87.40 85	80.86 267	57.15 308	64.61 215	87.08 205	32.67 355	89.64 156	46.38 374	71.55 229	87.68 224

VDD-MVS		76.08 85	74.97 100	79.44 48	84.27 101	53.33 146	91.13 20	85.88 119	65.33 133	72.37 99	89.34 133	32.52 356	92.76 47	77.90 78	75.96 161	92.22 43

3Dnovator+	62.71 7	72.29 178	70.50 190	77.65 118	83.40 119	51.29 211	87.32 86	86.40 108	59.01 268	58.49 317	88.32 163	32.40 357	91.27 86	57.04 286	82.15 75	90.38 129

tfpnnormal		61.47 366	59.09 370	68.62 375	76.29 329	41.69 422	81.14 320	85.16 150	54.48 357	51.32 396	73.63 401	32.32 358	86.89 286	21.78 483	55.71 395	77.29 415

MS-PatchMatch		72.34 175	71.26 174	75.61 191	82.38 153	55.55 56	88.00 62	89.95 24	65.38 131	56.51 352	80.74 317	32.28 359	92.89 41	57.95 275	88.10 16	78.39 401

KinetiMVS		71.15 201	69.25 219	76.82 149	77.99 289	50.49 230	85.05 180	86.51 104	59.78 245	64.10 224	85.34 234	32.16 360	91.33 85	58.82 260	73.54 202	88.64 193

v7n		62.50 358	59.27 369	72.20 311	67.25 446	49.83 253	77.87 368	80.12 283	52.50 374	48.80 417	73.07 405	32.10 361	87.90 236	46.83 371	54.92 399	78.86 392

IterMVS		63.77 343	61.67 343	70.08 355	72.68 388	51.24 212	80.44 334	75.51 380	60.51 236	51.41 395	73.70 400	32.08 362	78.91 409	54.30 312	54.35 405	80.08 384
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		59.12 379	58.81 373	60.08 441	70.68 416	45.07 381	80.42 335	74.25 392	43.54 444	50.02 410	73.73 397	31.97 363	56.74 490	51.06 343	53.60 411	78.42 400

SCA		63.84 341	60.01 364	75.32 207	78.58 278	57.92 14	61.61 464	77.53 352	56.71 318	57.75 329	70.77 432	31.97 363	79.91 404	48.80 356	56.36 383	88.13 213

ACMMP		70.81 212	69.29 217	75.39 205	81.52 188	51.92 190	83.43 243	83.03 223	56.67 320	58.80 307	88.91 141	31.92 365	88.58 203	65.89 191	73.39 204	85.67 275
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		66.33 316	62.87 327	76.70 156	80.45 223	51.81 196	46.11 488	78.90 317	55.46 343	63.82 232	84.54 246	31.91 366	91.03 95	55.68 302	68.97 259	87.25 235

SSM_04072		64.04 339	62.87 327	67.56 383	80.45 223	51.81 196	46.11 488	78.90 317	55.46 343	63.82 232	84.54 246	31.91 366	63.62 475	55.68 302	68.97 259	87.25 235

APD-MVS_3200maxsize		69.62 242	68.23 236	73.80 261	81.58 184	48.22 307	81.91 293	79.50 303	48.21 407	64.24 223	89.75 126	31.91 366	87.55 260	63.08 218	73.85 199	85.64 277

VDDNet		74.37 128	72.13 159	81.09 22	79.58 245	56.52 40	90.02 26	86.70 100	52.61 373	71.23 122	87.20 203	31.75 369	93.96 29	74.30 113	75.77 168	92.79 28

pmmvs5		62.80 354	61.18 351	67.66 382	69.53 430	42.37 418	82.65 271	75.19 384	54.30 360	52.03 392	78.51 342	31.64 370	80.67 390	48.60 358	58.15 366	79.95 385

LCM-MVSNet-Re		58.82 385	56.54 384	65.68 402	79.31 254	29.09 486	61.39 466	45.79 487	60.73 233	37.65 470	72.47 413	31.42 371	81.08 384	49.66 349	70.41 246	86.87 244

AstraMVS		70.12 224	68.56 227	74.81 227	76.48 323	47.48 335	84.35 210	82.58 231	63.80 162	62.09 260	84.54 246	31.39 372	89.96 139	68.24 174	63.58 312	87.00 241

testdata				67.08 389	77.59 297	45.46 378		69.20 442	44.47 437	71.50 119	88.34 161	31.21 373	70.76 465	52.20 336	75.88 162	85.03 286

SR-MVS-dyc-post		68.27 271	66.87 267	72.48 302	80.96 203	48.14 311	81.54 311	76.98 362	46.42 421	62.75 250	89.42 131	31.17 374	86.09 317	60.52 246	72.06 223	83.19 333

GA-MVS		69.04 252	66.70 273	76.06 176	75.11 354	52.36 175	83.12 258	80.23 280	63.32 176	60.65 275	79.22 336	30.98 375	88.37 215	61.25 236	66.41 283	87.46 229

OpenMVS	61.00 11	69.99 231	67.55 254	77.30 130	78.37 284	54.07 127	84.36 209	85.76 122	57.22 306	56.71 348	87.67 193	30.79 376	92.83 43	43.04 392	84.06 62	85.01 287

Effi-MVS+-dtu		66.24 319	64.96 314	70.08 355	75.17 353	49.64 255	82.01 290	74.48 391	62.15 201	57.83 325	76.08 380	30.59 377	83.79 360	65.40 199	60.93 339	76.81 419

sd_testset		67.79 280	65.95 290	73.32 275	81.70 173	46.33 361	68.99 435	80.30 279	66.58 103	61.64 265	82.38 292	30.45 378	87.63 255	55.86 299	65.60 293	86.01 266

test222					79.36 251	50.97 214	77.99 367	67.84 447	42.54 448	62.84 249	86.53 214	30.26 379			76.91 140	85.23 282

MVS_111021_LR		69.07 249	67.91 240	72.54 299	77.27 309	49.56 259	79.77 347	73.96 398	59.33 258	60.73 274	87.82 185	30.19 380	81.53 380	69.94 156	72.19 222	86.53 257

dtuonly		62.58 355	61.91 342	64.58 412	66.49 447	44.72 385	75.64 379	65.78 454	57.26 305	55.48 361	83.93 258	30.08 381	67.36 472	56.40 297	66.10 290	81.67 355

114514_t		69.87 234	67.88 244	75.85 183	88.38 31	52.35 176	86.94 100	83.68 206	53.70 364	55.68 358	85.60 228	30.07 382	91.20 90	55.84 300	71.02 236	83.99 307

CPTT-MVS		67.15 299	65.84 293	71.07 339	80.96 203	50.32 241	81.94 292	74.10 394	46.18 427	57.91 324	87.64 195	29.57 383	81.31 382	64.10 208	70.18 249	81.56 357

CANet_DTU		73.71 145	73.14 136	75.40 202	82.61 149	50.05 246	84.67 201	79.36 309	69.72 55	75.39 62	90.03 121	29.41 384	85.93 328	67.99 175	79.11 111	90.22 135

AdaColmap		67.86 277	65.48 301	75.00 222	88.15 39	54.99 83	86.10 126	76.63 371	49.30 398	57.80 326	86.65 213	29.39 385	88.94 189	45.10 380	70.21 248	81.06 371

RE-MVS-def			66.66 274		80.96 203	48.14 311	81.54 311	76.98 362	46.42 421	62.75 250	89.42 131	29.28 386		60.52 246	72.06 223	83.19 333

CVMVSNet		60.85 369	60.44 358	62.07 428	75.00 357	32.73 465	79.54 351	73.49 405	36.98 465	56.28 354	83.74 262	29.28 386	69.53 468	46.48 373	63.23 319	83.94 312

PMMVS		72.98 158	72.05 162	75.78 185	83.57 112	48.60 290	84.08 219	82.85 227	61.62 212	68.24 166	90.33 110	28.35 388	87.78 248	72.71 132	76.69 147	90.95 109

our_test_3		59.11 380	55.08 397	71.18 338	71.42 404	53.29 148	81.96 291	74.52 390	48.32 405	42.08 450	69.28 441	28.14 389	82.15 376	34.35 433	45.68 451	78.11 406

Fast-Effi-MVS+-dtu		66.53 313	64.10 323	73.84 259	72.41 391	52.30 180	84.73 196	75.66 378	59.51 251	56.34 353	79.11 338	28.11 390	85.85 329	57.74 281	63.29 318	83.35 327

Anonymous20231211		66.08 321	63.67 324	73.31 276	83.07 129	48.75 286	86.01 130	84.67 182	45.27 431	56.54 350	76.67 370	28.06 391	88.95 187	52.78 327	59.95 345	82.23 347

Anonymous20240529		69.71 236	67.28 261	77.00 142	83.78 110	50.36 239	88.87 51	85.10 157	47.22 414	64.03 226	83.37 271	27.93 392	92.10 67	57.78 280	67.44 273	88.53 202

HPM-MVS_fast		67.86 277	66.28 282	72.61 297	80.67 214	48.34 301	81.18 319	75.95 377	50.81 387	59.55 289	88.05 177	27.86 393	85.98 324	58.83 259	73.58 201	83.51 326

FMVSNet1		64.57 333	62.11 338	71.96 319	77.32 307	46.36 358	83.52 235	83.31 214	52.43 375	54.42 371	76.23 376	27.80 394	86.20 309	42.59 396	61.34 335	83.32 328

CNLPA		60.59 370	58.44 374	67.05 390	79.21 257	47.26 341	79.75 348	64.34 462	42.46 449	51.90 393	83.94 257	27.79 395	75.41 444	37.12 412	59.49 352	78.47 398

TAPA-MVS	56.12 14	61.82 364	60.18 363	66.71 393	78.48 282	37.97 445	75.19 387	76.41 374	46.82 417	57.04 343	86.52 215	27.67 396	77.03 431	26.50 468	67.02 276	85.14 285
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
pmmvs6		59.64 374	57.15 381	67.09 388	66.01 449	36.86 449	80.50 332	78.64 327	45.05 433	49.05 415	73.94 395	27.28 397	86.10 315	43.96 388	49.94 424	78.31 402

test-mter		68.36 267	67.29 260	71.60 329	78.67 273	48.17 309	85.13 174	79.72 295	53.38 367	63.13 244	82.58 286	27.23 398	80.24 398	60.56 244	75.17 177	86.39 262

D2MVS		63.49 346	61.39 347	69.77 359	69.29 432	48.93 280	78.89 360	77.71 350	60.64 235	49.70 411	72.10 426	27.08 399	83.48 365	54.48 311	62.65 327	76.90 417

XVG-OURS-SEG-HR		62.02 362	59.54 366	69.46 362	65.30 454	45.88 371	65.06 449	73.57 403	46.45 420	57.42 338	83.35 272	26.95 400	78.09 417	53.77 316	64.03 307	84.42 296

IMVS_0404		69.11 248	67.25 263	74.68 231	82.26 155	50.87 215	76.74 374	85.16 150	62.91 185	50.76 408	86.07 219	26.76 401	83.06 371	64.03 209	70.55 242	90.09 142

test_djsdf		63.84 341	61.56 345	70.70 345	68.78 435	44.69 386	81.63 305	81.44 255	50.28 391	52.27 389	76.26 375	26.72 402	86.11 313	60.83 240	55.84 394	81.29 369

Anonymous20231206		59.08 381	57.59 378	63.55 418	68.77 436	32.14 469	80.26 338	79.78 294	50.00 395	49.39 413	72.39 415	26.64 403	78.36 414	33.12 440	57.94 371	80.14 383

ppachtmachnet_test		58.56 389	54.34 399	71.24 335	71.42 404	54.74 102	81.84 296	72.27 415	49.02 400	45.86 437	68.99 442	26.27 404	83.30 368	30.12 450	43.23 457	75.69 429

test20.03		55.22 409	54.07 402	58.68 447	63.14 469	25.00 492	77.69 369	74.78 387	52.64 372	43.43 444	72.39 415	26.21 405	74.76 446	29.31 453	47.05 445	76.28 427

FE-MVS		64.15 337	60.43 359	75.30 210	80.85 208	49.86 252	68.28 440	78.37 336	50.26 394	59.31 294	73.79 396	26.19 406	91.92 70	40.19 402	66.67 278	84.12 302

FMVSNet5		58.61 388	56.45 385	65.10 409	77.20 313	39.74 434	74.77 389	77.12 360	50.27 393	43.28 446	67.71 445	26.15 407	76.90 434	36.78 418	54.78 401	78.65 396

dtuonlycased		54.12 414	52.39 414	59.30 444	64.31 462	41.80 421	78.63 361	65.85 453	50.56 389	42.00 451	60.21 473	26.14 408	73.31 454	43.06 391	40.73 462	62.79 484

ACMP	61.11 9	66.24 319	64.33 320	72.00 318	74.89 359	49.12 272	83.18 255	79.83 292	55.41 345	52.29 388	82.68 283	25.83 409	86.10 315	60.89 239	63.94 309	80.78 374
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MIMVSNet		63.12 350	60.29 361	71.61 328	75.92 341	46.65 351	65.15 448	81.94 242	59.14 265	54.65 369	69.47 438	25.74 410	80.63 392	41.03 401	69.56 255	87.55 227

LPG-MVS_test		66.44 315	64.58 316	72.02 316	74.42 365	48.60 290	83.07 260	80.64 271	54.69 355	53.75 379	83.83 260	25.73 411	86.98 279	60.33 250	64.71 300	80.48 378

LGP-MVS_train				72.02 316	74.42 365	48.60 290		80.64 271	54.69 355	53.75 379	83.83 260	25.73 411	86.98 279	60.33 250	64.71 300	80.48 378

test_vis1_n_1920		68.59 264	68.31 233	69.44 363	69.16 433	41.51 425	84.63 202	68.58 445	58.80 272	73.26 84	88.37 157	25.30 413	80.60 393	79.10 62	67.55 272	86.23 264

ACMM	58.35 12	64.35 335	62.01 341	71.38 333	74.21 369	48.51 294	82.25 284	79.66 298	47.61 411	54.54 370	80.11 323	25.26 414	86.00 322	51.26 340	63.16 321	79.64 387
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FE-MVSNET2		58.78 386	56.44 386	65.82 400	63.57 467	38.92 439	79.59 350	81.75 251	56.14 334	43.06 448	68.15 444	25.22 415	80.64 391	42.29 398	48.16 434	77.91 407

XVG-OURS		61.88 363	59.34 368	69.49 361	65.37 453	46.27 363	64.80 450	73.49 405	47.04 416	57.41 339	82.85 277	25.15 416	78.18 415	53.00 324	64.98 295	84.01 306

PVSNet_0	57.04 13	61.19 367	57.24 380	73.02 281	77.45 304	50.31 242	79.43 355	77.36 357	63.96 159	47.51 427	72.45 414	25.03 417	83.78 361	52.76 329	19.22 503	84.96 289

WB-MVS		37.41 456	36.37 456	40.54 477	54.23 485	10.43 516	65.29 446	43.75 490	34.86 476	27.81 494	54.63 483	24.94 418	63.21 476	6.81 513	15.00 506	47.98 496

UniMVSNet_ETH3D		62.51 357	60.49 357	68.57 377	68.30 441	40.88 432	73.89 398	79.93 290	51.81 381	54.77 367	79.61 331	24.80 419	81.10 383	49.93 347	61.35 334	83.73 316

DP-MVS		59.24 377	56.12 390	68.63 374	88.24 36	50.35 240	82.51 279	64.43 461	41.10 451	46.70 432	78.77 340	24.75 420	88.57 206	22.26 481	56.29 387	66.96 473

test_cas_vis1_n_1920		67.10 300	66.60 276	68.59 376	65.17 456	43.23 406	83.23 253	69.84 438	55.34 346	70.67 139	87.71 192	24.70 421	76.66 436	78.57 69	64.20 305	85.89 272

LuminaMVS		66.60 312	64.37 319	73.27 279	70.06 426	49.57 256	80.77 329	81.76 250	50.81 387	60.56 276	78.41 344	24.50 422	87.26 272	64.24 207	68.25 265	82.99 337

tt0805		63.39 347	61.31 350	69.64 360	69.36 431	38.87 440	78.00 366	85.48 130	48.82 402	55.66 360	81.66 307	24.38 423	86.37 306	49.04 355	59.36 354	83.68 322

cascas		69.01 253	66.13 285	77.66 117	79.36 251	55.41 62	86.99 96	83.75 204	56.69 319	58.92 303	81.35 311	24.31 424	92.10 67	53.23 320	70.61 240	85.46 280

CMPMVS	40.41 21	55.34 408	52.64 411	63.46 420	60.88 475	43.84 397	61.58 465	71.06 430	30.43 483	36.33 473	74.63 389	24.14 425	75.44 443	48.05 363	66.62 279	71.12 465
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UGNet		68.71 261	67.11 265	73.50 271	80.55 219	47.61 332	84.08 219	78.51 332	59.45 252	65.68 195	82.73 282	23.78 426	85.08 344	52.80 326	76.40 148	87.80 220
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		53.82 417	49.96 423	65.41 406	70.09 425	48.95 278	72.30 415	71.66 423	44.25 440	31.89 487	63.07 462	23.73 427	73.95 449	33.26 438	39.40 469	73.34 450

MDA-MVSNet_test_wron		53.82 417	49.95 424	65.43 405	70.13 424	49.05 274	72.30 415	71.65 424	44.23 441	31.85 488	63.13 461	23.68 428	74.01 448	33.25 439	39.35 470	73.23 453

PLC	52.38 18	60.89 368	58.97 372	66.68 395	81.77 170	45.70 376	78.96 359	74.04 397	43.66 443	47.63 424	83.19 275	23.52 429	77.78 426	37.47 409	60.46 341	76.55 425
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SSC-MVS		35.20 458	34.30 460	37.90 479	52.58 487	8.65 519	61.86 462	41.64 494	31.81 481	25.54 497	52.94 489	23.39 430	59.28 485	6.10 515	12.86 508	45.78 499

ADS-MVSNet2		55.21 410	51.44 416	66.51 396	80.60 215	49.56 259	55.03 479	65.44 455	44.72 435	51.00 401	61.19 469	22.83 431	75.41 444	28.54 458	53.63 409	74.57 442

ADS-MVSNet		56.17 404	51.95 415	68.84 368	80.60 215	53.07 156	55.03 479	70.02 437	44.72 435	51.00 401	61.19 469	22.83 431	78.88 410	28.54 458	53.63 409	74.57 442

test_0402		56.45 402	53.03 406	66.69 394	76.78 321	50.31 242	81.76 298	69.61 440	42.79 447	43.88 441	72.13 424	22.82 433	86.46 303	16.57 495	50.94 421	63.31 482

UnsupCasMVSNet_eth		57.56 396	55.15 395	64.79 411	64.57 461	33.12 462	73.17 406	83.87 203	58.98 269	41.75 454	70.03 436	22.54 434	79.92 402	46.12 377	35.31 476	81.32 368

xiu_mvs_v1_base_debu		71.60 194	70.29 198	75.55 195	77.26 310	53.15 151	85.34 162	79.37 306	55.83 337	72.54 94	90.19 115	22.38 435	86.66 296	73.28 128	76.39 149	86.85 247

xiu_mvs_v1_base		71.60 194	70.29 198	75.55 195	77.26 310	53.15 151	85.34 162	79.37 306	55.83 337	72.54 94	90.19 115	22.38 435	86.66 296	73.28 128	76.39 149	86.85 247

xiu_mvs_v1_base_debi		71.60 194	70.29 198	75.55 195	77.26 310	53.15 151	85.34 162	79.37 306	55.83 337	72.54 94	90.19 115	22.38 435	86.66 296	73.28 128	76.39 149	86.85 247

LS3D		56.40 403	53.82 403	64.12 414	81.12 198	45.69 377	73.42 404	66.14 451	35.30 475	43.24 447	79.88 325	22.18 438	79.62 407	19.10 490	64.00 308	67.05 472

PVSNet	62.49 8	69.27 247	67.81 249	73.64 266	84.41 93	51.85 192	84.63 202	77.80 347	66.42 108	59.80 283	84.95 243	22.14 439	80.44 396	55.03 307	75.11 180	88.62 196

MDA-MVSNet-bldmvs		51.56 430	47.75 438	63.00 423	71.60 401	47.32 340	69.70 433	72.12 416	43.81 442	27.65 495	63.38 460	21.97 440	75.96 440	27.30 465	32.19 484	65.70 478

pmmvs-eth3d		55.97 406	52.78 410	65.54 404	61.02 474	46.44 357	75.36 386	67.72 448	49.61 397	43.65 443	67.58 446	21.63 441	77.04 430	44.11 387	44.33 453	73.15 454

anonymousdsp		60.46 371	57.65 377	68.88 367	63.63 466	45.09 380	72.93 407	78.63 328	46.52 419	51.12 400	72.80 410	21.46 442	83.07 370	57.79 279	53.97 406	78.47 398

MVS-HIRNet		49.01 439	44.71 443	61.92 432	76.06 334	46.61 353	63.23 457	54.90 479	24.77 490	33.56 482	36.60 500	21.28 443	75.88 442	29.49 452	62.54 328	63.26 483

Anonymous202405211		70.11 225	67.88 244	76.79 153	87.20 49	47.24 342	89.49 36	77.38 356	54.88 353	66.14 185	86.84 208	20.93 444	91.54 78	56.45 295	71.62 227	91.59 69

FE-MVSNET		51.43 431	48.22 433	61.06 438	60.78 476	32.48 467	73.85 400	64.62 458	46.30 426	37.47 471	66.27 450	20.80 445	77.38 429	23.43 477	40.48 465	73.31 451

UnsupCasMVSNet_bld		53.86 416	50.53 420	63.84 415	63.52 468	34.75 452	71.38 424	81.92 244	46.53 418	38.95 466	57.93 479	20.55 446	80.20 400	39.91 404	34.09 483	76.57 424

Elysia		65.59 324	62.65 330	74.42 237	69.85 427	49.46 266	80.04 342	82.11 237	46.32 424	58.74 311	79.64 329	20.30 447	88.57 206	55.48 304	71.37 231	85.22 283

StellarMVS		65.59 324	62.65 330	74.42 237	69.85 427	49.46 266	80.04 342	82.11 237	46.32 424	58.74 311	79.64 329	20.30 447	88.57 206	55.48 304	71.37 231	85.22 283

EU-MVSNet		52.63 423	50.72 419	58.37 448	62.69 471	28.13 489	72.60 410	75.97 376	30.94 482	40.76 461	72.11 425	20.16 449	70.80 464	35.11 430	46.11 449	76.19 428

N_pmnet		41.25 449	39.77 452	45.66 470	68.50 438	0.82 540	72.51 412	0.38 538	35.61 472	35.26 477	61.51 468	20.07 450	67.74 469	23.51 475	40.63 463	68.42 471

MSDG		59.44 375	55.14 396	72.32 309	74.69 360	50.71 223	74.39 395	73.58 402	44.44 438	43.40 445	77.52 352	19.45 451	90.87 106	31.31 446	57.49 378	75.38 432

tt0320		52.45 425	48.75 429	63.55 418	71.47 403	41.85 420	72.42 413	59.73 471	36.33 470	44.52 438	61.55 467	19.34 452	76.45 438	33.53 435	39.85 467	72.36 457

K. test v3		54.04 415	49.42 428	67.92 381	68.55 437	42.57 416	75.51 384	63.07 465	52.07 376	39.21 464	64.59 458	19.34 452	82.21 375	37.11 413	25.31 494	78.97 391

lessismore_v0				67.98 380	64.76 460	41.25 428		45.75 488		36.03 475	65.63 455	19.29 454	84.11 356	35.67 422	21.24 500	78.59 397

KD-MVS_self_test		49.24 438	46.85 440	56.44 453	54.32 484	22.87 495	57.39 474	73.36 410	44.36 439	37.98 469	59.30 477	18.97 455	71.17 463	33.48 436	42.44 458	75.26 434

OpenMVS_ROB	53.19 17	59.20 378	56.00 391	68.83 369	71.13 408	44.30 390	83.64 233	75.02 385	46.42 421	46.48 434	73.03 406	18.69 456	88.14 226	27.74 463	61.80 332	74.05 445

mvsany_test1		43.38 448	42.57 450	45.82 469	50.96 493	26.10 491	55.80 477	27.74 510	27.15 487	47.41 428	74.39 391	18.67 457	44.95 502	44.66 382	36.31 474	66.40 475

LTVRE_ROB	45.45 19	52.73 422	49.74 426	61.69 433	69.78 429	34.99 451	44.52 490	67.60 449	43.11 446	43.79 442	74.03 393	18.54 458	81.45 381	28.39 460	57.94 371	68.62 469
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		54.37 411	50.10 421	67.21 387	70.70 414	41.46 427	74.73 390	64.69 457	47.56 412	39.12 465	69.49 437	18.49 459	84.69 350	31.87 443	34.20 482	75.48 431

new-patchmatchnet		48.21 440	46.55 441	53.18 459	57.73 480	18.19 509	70.24 428	71.02 431	45.70 428	33.70 481	60.23 472	18.00 460	69.86 467	27.97 462	34.35 480	71.49 464

tt0320-xc		52.22 428	48.38 432	63.75 417	72.19 396	42.25 419	72.19 418	57.59 475	37.24 463	44.41 439	61.56 466	17.90 461	75.89 441	35.60 423	36.73 473	73.12 455

F-COLMAP		55.96 407	53.65 405	62.87 425	72.76 387	42.77 412	74.70 392	70.37 434	40.03 452	41.11 459	79.36 333	17.77 462	73.70 452	32.80 441	53.96 407	72.15 458

sc_t1		53.51 420	49.92 425	64.29 413	70.33 421	39.55 437	72.93 407	59.60 472	38.74 457	47.16 429	66.47 449	17.59 463	76.50 437	36.83 417	39.62 468	76.82 418

jajsoiax		63.21 349	60.84 354	70.32 351	68.33 440	44.45 388	81.23 318	81.05 261	53.37 368	50.96 403	77.81 350	17.49 464	85.49 335	59.31 255	58.05 369	81.02 372

RPSCF		45.77 445	44.13 447	50.68 461	57.67 481	29.66 482	54.92 481	45.25 489	26.69 488	45.92 436	75.92 382	17.43 465	45.70 501	27.44 464	45.95 450	76.67 420

mmtdpeth		57.93 394	54.78 398	67.39 386	72.32 393	43.38 403	72.72 409	68.93 443	54.45 358	56.85 345	62.43 463	17.02 466	83.46 366	57.95 275	30.31 488	75.31 433

PatchMatch-RL		56.66 399	53.75 404	65.37 407	77.91 293	45.28 379	69.78 432	60.38 469	41.35 450	47.57 425	73.73 397	16.83 467	76.91 432	36.99 415	59.21 355	73.92 446

mvs_tets		62.96 352	60.55 356	70.19 352	68.22 443	44.24 393	80.90 325	80.74 269	52.99 371	50.82 407	77.56 351	16.74 468	85.44 336	59.04 258	57.94 371	80.89 373

ACMH+	54.58 15	58.55 390	55.24 394	68.50 378	74.68 361	45.80 375	80.27 337	70.21 435	47.15 415	42.77 449	75.48 384	16.73 469	85.98 324	35.10 431	54.78 401	73.72 447

ACMH	53.70 16	59.78 373	55.94 392	71.28 334	76.59 322	48.35 300	80.15 341	76.11 375	49.74 396	41.91 453	73.45 404	16.50 470	90.31 128	31.42 445	57.63 377	75.17 435
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MIMVSNet1		50.35 436	47.81 436	57.96 449	61.53 473	27.80 490	67.40 442	74.06 396	43.25 445	33.31 486	65.38 457	16.03 471	71.34 462	21.80 482	47.55 440	74.75 439

DSMNet-mixed		38.35 453	35.36 458	47.33 468	48.11 499	14.91 513	37.87 498	36.60 501	19.18 495	34.37 479	59.56 476	15.53 472	53.01 494	20.14 488	46.89 446	74.07 444

EG-PatchMatch MVS		62.40 361	59.59 365	70.81 343	73.29 378	49.05 274	85.81 137	84.78 172	51.85 380	44.19 440	73.48 403	15.52 473	89.85 144	40.16 403	67.24 274	73.54 449

testgi		54.25 413	52.57 412	59.29 445	62.76 470	21.65 501	72.21 417	70.47 433	53.25 369	41.94 452	77.33 357	14.28 474	77.95 422	29.18 454	51.72 420	78.28 403

COLMAP_ROB	43.60 20	50.90 434	48.05 435	59.47 442	67.81 444	40.57 433	71.25 425	62.72 467	36.49 468	36.19 474	73.51 402	13.48 475	73.92 450	20.71 485	50.26 423	63.92 481
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		52.39 426	48.73 430	63.35 422	65.21 455	38.42 443	68.54 438	64.95 456	38.19 458	39.57 463	71.43 428	13.23 476	79.92 402	37.16 411	40.32 466	71.72 461

usedtu_dtu_shiyan2		50.47 435	46.43 442	62.61 427	51.66 490	31.70 472	75.62 381	75.65 379	36.36 469	34.89 478	56.91 482	12.01 477	78.40 413	30.87 449	43.86 454	77.72 410

MVStest1		38.35 453	34.53 459	49.82 465	51.43 491	30.41 474	50.39 483	55.25 477	17.56 498	26.45 496	65.85 454	11.72 478	57.00 489	14.79 497	17.31 505	62.05 485

test_fmvs1		53.60 419	52.54 413	56.78 451	58.07 478	30.26 475	68.95 436	42.19 493	32.46 478	63.59 240	82.56 288	11.55 479	60.81 480	58.25 269	55.27 397	79.28 388

tmp_tt		9.44 481	10.68 484	5.73 504	2.49 535	4.21 525	10.48 514	18.04 517	0.34 528	12.59 509	20.49 516	11.39 480	7.03 522	13.84 500	6.46 515	5.95 523

ITE_SJBPF				51.84 460	58.03 479	31.94 471		53.57 483	36.67 466	41.32 457	75.23 386	11.17 481	51.57 495	25.81 469	48.04 436	72.02 460

Anonymous20240521		51.65 429	48.42 431	61.34 437	56.43 483	39.65 436	73.57 402	73.47 408	36.64 467	36.59 472	63.98 459	10.75 482	72.25 461	35.35 425	49.01 425	72.11 459

mvs5depth		50.97 433	46.98 439	62.95 424	56.63 482	34.23 457	62.73 461	67.35 450	45.03 434	48.00 421	65.41 456	10.40 483	79.88 406	36.00 420	31.27 487	74.73 440

AllTest		47.32 442	44.66 444	55.32 457	65.08 457	37.50 447	62.96 459	54.25 481	35.45 473	33.42 483	72.82 408	9.98 484	59.33 483	24.13 473	43.84 455	69.13 467

TestCases				55.32 457	65.08 457	37.50 447		54.25 481	35.45 473	33.42 483	72.82 408	9.98 484	59.33 483	24.13 473	43.84 455	69.13 467

USDC		54.36 412	51.23 417	63.76 416	64.29 463	37.71 446	62.84 460	73.48 407	56.85 311	35.47 476	71.94 427	9.23 486	78.43 412	38.43 408	48.57 432	75.13 436

XVG-ACMP-BASELINE		56.03 405	52.85 409	65.58 403	61.91 472	40.95 431	63.36 455	72.43 414	45.20 432	46.02 435	74.09 392	9.20 487	78.12 416	45.13 379	58.27 364	77.66 412

test_fmvs1_n		52.55 424	51.19 418	56.65 452	51.90 489	30.14 476	67.66 441	42.84 492	32.27 479	62.30 255	82.02 302	9.12 488	60.84 479	57.82 278	54.75 403	78.99 390

test_vis1_n		51.19 432	49.66 427	55.76 456	51.26 492	29.85 481	67.20 444	38.86 497	32.12 480	59.50 290	79.86 326	8.78 489	58.23 487	56.95 287	52.46 417	79.19 389

pmmvs3		45.53 446	41.55 451	57.44 450	48.97 497	39.68 435	70.06 429	57.66 474	28.32 486	34.06 480	57.29 480	8.50 490	66.85 473	34.86 432	34.26 481	65.80 477

EGC-MVSNET		33.75 460	30.42 464	43.75 473	64.94 459	36.21 450	60.47 469	40.70 496	0.02 557	0.10 554	53.79 486	7.39 491	60.26 481	11.09 504	35.23 478	34.79 501

test_fmvs2		45.89 444	44.32 446	50.62 462	45.85 501	24.70 493	58.87 473	37.84 500	25.22 489	52.46 387	74.56 390	7.07 492	54.69 491	49.28 353	47.70 438	72.48 456

ANet_high		34.39 459	29.59 465	48.78 466	30.34 511	22.28 497	55.53 478	63.79 463	38.11 459	15.47 504	36.56 501	6.94 493	59.98 482	13.93 499	5.64 516	64.08 480

FPMVS		35.40 457	33.67 461	40.57 476	46.34 500	28.74 488	41.05 494	57.05 476	20.37 494	22.27 499	53.38 487	6.87 494	44.94 503	8.62 507	47.11 444	48.01 495

test_vis1_rt		40.29 452	38.64 453	45.25 471	48.91 498	30.09 477	59.44 470	27.07 511	24.52 491	38.48 468	51.67 490	6.71 495	49.44 496	44.33 384	46.59 448	56.23 487

new_pmnet		33.56 461	31.89 463	38.59 478	49.01 496	20.42 502	51.01 482	37.92 499	20.58 492	23.45 498	46.79 492	6.66 496	49.28 498	20.00 489	31.57 486	46.09 498

TinyColmap		48.15 441	44.49 445	59.13 446	65.73 452	38.04 444	63.34 456	62.86 466	38.78 455	29.48 490	67.23 448	6.46 497	73.30 455	24.59 472	41.90 460	66.04 476

ambc				62.06 429	53.98 486	29.38 484	35.08 500	79.65 300		41.37 455	59.96 474	6.27 498	82.15 376	35.34 426	38.22 471	74.65 441

TDRefinement		40.91 450	38.37 454	48.55 467	50.45 494	33.03 464	58.98 472	50.97 484	28.50 484	29.89 489	67.39 447	6.21 499	54.51 492	17.67 493	35.25 477	58.11 486

ttmdpeth		40.58 451	37.50 455	49.85 464	49.40 495	22.71 496	56.65 476	46.78 485	28.35 485	40.29 462	69.42 439	5.35 500	61.86 478	20.16 487	21.06 501	64.96 479

PM-MVS		46.92 443	43.76 449	56.41 454	52.18 488	32.26 468	63.21 458	38.18 498	37.99 460	40.78 460	66.20 451	5.09 501	65.42 474	48.19 362	41.99 459	71.54 463

LF4IMVS		33.04 462	32.55 462	34.52 482	40.96 502	22.03 498	44.45 491	35.62 502	20.42 493	28.12 493	62.35 464	5.03 502	31.88 514	21.61 484	34.42 479	49.63 494

EMVS		18.42 475	17.66 479	20.71 493	34.13 508	12.64 515	46.94 486	29.94 508	10.46 508	5.58 522	14.93 522	4.23 503	38.83 506	5.24 519	7.51 513	10.67 517

E-PMN		19.16 474	18.40 478	21.44 492	36.19 506	13.63 514	47.59 485	30.89 506	10.73 506	5.91 520	16.59 519	3.66 504	39.77 505	5.95 516	8.14 511	10.92 516

test_method		24.09 471	21.07 475	33.16 485	27.67 515	8.35 522	26.63 506	35.11 504	3.40 516	14.35 505	36.98 499	3.46 505	35.31 509	19.08 491	22.95 497	55.81 488

mvsany_test3		28.00 464	25.98 466	34.05 483	28.97 512	15.31 511	34.54 501	18.17 516	16.24 499	29.30 491	53.37 488	2.79 506	33.38 513	30.01 451	20.41 502	53.45 491

test_f		27.12 466	24.85 467	33.93 484	26.17 517	15.25 512	30.24 505	22.38 515	12.53 504	28.23 492	49.43 491	2.59 507	34.34 512	25.12 471	26.99 492	52.20 492

test_fmvs3		37.95 455	35.75 457	44.55 472	35.50 507	18.92 505	48.32 484	34.00 505	18.36 497	41.31 458	61.58 465	2.29 508	48.06 500	42.72 395	37.71 472	66.66 474

PMMVS2		26.71 467	22.98 472	37.87 480	36.89 505	8.51 520	42.51 493	29.32 509	19.09 496	13.01 507	37.54 497	2.23 509	53.11 493	14.54 498	11.71 509	51.99 493

Gipuma		27.47 465	24.26 470	37.12 481	60.55 477	29.17 485	11.68 512	60.00 470	14.18 501	10.52 513	15.12 521	2.20 510	63.01 477	8.39 508	35.65 475	19.18 509
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		28.07 463	23.85 471	40.71 475	27.46 516	18.93 504	30.82 504	46.19 486	12.76 503	16.40 501	34.70 503	1.90 511	48.69 499	20.25 486	24.22 496	54.51 490

DeepMVS_CX				13.10 496	21.34 519	8.99 518		10.02 521	10.59 507	7.53 517	30.55 507	1.82 512	14.55 515	6.83 512	7.52 512	15.75 511

VLMVS		5.96 488	6.29 491	4.99 505	5.31 528	1.01 535	4.24 522	0.93 528	0.06 541	8.90 514	26.22 511	1.69 513	1.62 532	3.76 525	5.49 517	12.33 513

APD_test1		26.46 468	24.41 469	32.62 487	37.58 504	21.74 500	40.50 496	30.39 507	11.45 505	16.33 502	43.76 493	1.63 514	41.62 504	11.24 503	26.82 493	34.51 502

VLMVS_CLIP		11.28 480	11.90 483	9.42 499	7.54 524	3.26 527	13.10 511	10.36 520	1.51 522	15.95 503	32.54 506	1.51 515	12.70 517	10.98 505	13.62 507	12.29 514

PMVS	19.57 22	25.07 469	22.43 474	32.99 486	23.12 518	22.98 494	40.98 495	35.19 503	15.99 500	11.95 512	35.87 502	1.47 516	49.29 497	5.41 518	31.90 485	26.70 508
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		24.79 470	22.95 473	30.31 488	28.59 513	18.92 505	37.43 499	17.27 518	12.90 502	21.28 500	29.92 508	1.02 517	36.35 507	28.28 461	29.82 491	35.65 500

MVE	16.60 23	17.34 477	13.39 480	29.16 489	28.43 514	19.72 503	13.73 510	23.63 514	7.23 511	7.96 516	21.41 514	0.80 518	36.08 508	6.97 511	10.39 510	31.69 503
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testf1		21.11 472	19.08 476	27.18 490	30.56 509	18.28 507	33.43 502	24.48 512	8.02 509	12.02 510	33.50 504	0.75 519	35.09 510	7.68 509	21.32 498	28.17 505

APD_test2		21.11 472	19.08 476	27.18 490	30.56 509	18.28 507	33.43 502	24.48 512	8.02 509	12.02 510	33.50 504	0.75 519	35.09 510	7.68 509	21.32 498	28.17 505

MVS_clip		3.10 496	3.65 499	1.44 512	3.78 531	1.17 534	2.78 523	0.19 542	0.20 531	4.48 526	14.54 524	0.35 521	0.47 538	2.92 526	3.64 521	2.67 528

ArgMatch-Sym		13.78 478	13.16 481	15.65 495	13.75 520	8.38 521	21.56 507	2.56 523	7.09 512	14.16 506	40.67 495	0.28 522	11.85 519	13.55 501	4.84 518	26.71 507

ArgMatch-SfM		13.59 479	12.41 482	17.15 494	12.50 521	7.57 523	19.17 509	3.21 522	5.58 513	12.94 508	39.91 496	0.26 523	13.40 516	13.23 502	4.84 518	30.48 504

wuyk23d		9.11 482	8.77 486	10.15 497	40.18 503	16.76 510	20.28 508	1.01 527	2.58 518	2.66 529	0.98 543	0.23 524	12.49 518	4.08 524	6.90 514	1.19 530

PDCNetPlus		5.70 490	5.56 493	6.14 502	8.32 523	1.98 530	7.37 517	0.76 530	2.18 519	3.69 527	20.81 515	0.12 525	4.60 525	4.55 521	2.21 524	11.83 515

DenseAffine		8.44 483	7.90 489	10.07 498	9.51 522	4.71 524	11.43 513	1.10 526	4.32 514	8.26 515	27.67 510	0.09 526	8.71 520	6.30 514	2.41 523	16.80 510

RoMa-SfM		7.02 485	6.78 490	7.74 500	5.47 527	3.55 526	8.83 515	0.67 531	3.41 515	7.06 518	27.85 509	0.08 527	7.13 521	5.86 517	1.82 525	12.53 512

LoFTR		5.36 491	5.09 494	6.17 501	5.52 526	2.23 529	6.04 518	2.15 524	1.23 523	5.61 521	19.15 517	0.07 528	5.98 523	1.61 528	4.48 520	10.30 519

RoMa-HiRes		4.68 492	4.75 495	4.46 506	3.18 532	1.88 531	5.38 520	0.37 539	2.04 520	4.84 523	21.68 513	0.06 529	3.78 527	4.17 523	1.04 532	7.71 522

ALIKED-LG		1.21 502	1.31 506	0.90 515	2.88 533	0.91 537	1.96 525	0.48 535	0.17 532	0.94 535	3.75 533	0.06 529	0.81 534	0.10 542	1.43 528	0.99 531

SP-DiffGlue		0.50 507	0.53 510	0.38 522	0.41 561	0.20 551	0.62 536	0.19 542	0.09 535	0.64 540	1.95 537	0.06 529	0.17 545	0.26 535	0.60 538	0.77 537

MASt3R-SfM		1.80 500	2.02 502	1.14 514	1.03 544	0.52 543	1.83 527	0.53 533	0.34 528	2.55 530	9.61 528	0.05 532	0.77 535	1.06 530	1.16 531	2.14 529

ALIKED-NN		1.00 505	1.09 508	0.75 517	2.44 536	0.84 539	1.63 531	0.39 536	0.12 533	0.72 538	3.04 535	0.05 532	0.70 537	0.08 544	1.32 530	0.72 539

DKM		5.93 489	5.87 492	6.10 503	5.64 525	2.81 528	7.85 516	0.52 534	2.62 517	6.30 519	23.31 512	0.05 532	4.93 524	5.11 520	1.45 527	10.57 518

SP-LightGlue		0.48 508	0.50 511	0.40 518	1.33 539	0.19 552	0.86 532	0.17 545	0.08 537	0.25 542	1.08 539	0.05 532	0.19 542	0.13 538	0.57 539	0.80 534

SP-SuperGlue		0.47 509	0.50 511	0.39 519	1.30 540	0.19 552	0.86 532	0.17 545	0.09 535	0.26 541	1.08 539	0.05 532	0.18 544	0.13 538	0.55 540	0.79 536

ALIKED-MNN		1.07 504	1.15 507	0.84 516	2.67 534	0.92 536	1.81 528	0.39 536	0.12 533	0.73 537	3.13 534	0.05 532	0.77 535	0.09 543	1.34 529	0.84 533

DKM-HiRes		4.42 493	4.49 496	4.23 507	3.85 530	1.83 532	5.38 520	0.33 540	1.86 521	4.78 524	18.85 518	0.04 538	2.97 529	4.34 522	0.97 533	7.88 521

SP-NN		0.43 512	0.45 515	0.37 523	1.13 543	0.17 556	0.82 535	0.16 547	0.07 539	0.24 543	1.00 542	0.04 538	0.19 542	0.12 540	0.51 543	0.74 538

GLUNet-SfM		2.60 497	2.13 501	4.01 509	1.95 537	0.86 538	1.72 529	0.81 529	0.34 528	3.35 528	9.72 527	0.04 538	3.15 528	0.50 533	0.73 536	8.02 520

MatchFormer		3.89 494	3.84 498	4.03 508	4.08 529	1.73 533	5.52 519	1.59 525	0.67 524	4.77 525	13.56 525	0.04 538	4.50 526	0.74 532	3.60 522	5.85 524

SP-MNN		0.45 510	0.47 514	0.39 519	1.18 542	0.17 556	0.85 534	0.16 547	0.07 539	0.24 543	1.05 541	0.04 538	0.20 541	0.12 540	0.54 542	0.80 534

MVS_baseline		1.13 503	1.40 505	0.34 524	0.74 551	0.01 566	0.24 551	0.03 564	0.00 558	1.75 533	7.74 531	0.03 543	0.00 560	0.31 534	1.74 526	0.99 531

XFeat-NN		0.44 511	0.49 513	0.30 525	0.24 563	0.12 562	0.48 538	0.15 549	0.06 541	0.71 539	1.78 538	0.03 543	0.28 540	0.14 537	0.83 535	0.48 541

XFeat-MNN		0.55 506	0.60 509	0.39 519	0.26 562	0.16 559	0.58 537	0.20 541	0.08 537	0.82 536	2.26 536	0.03 543	0.39 539	0.19 536	0.95 534	0.62 540

ELoFTR		2.17 499	1.90 503	2.99 510	1.19 541	0.63 542	1.84 526	0.60 532	0.46 526	2.17 532	9.10 529	0.02 546	2.92 530	1.00 531	0.72 537	5.42 525

PMatch-SfM		2.38 498	2.41 500	2.29 511	1.48 538	0.76 541	2.51 524	0.18 544	0.59 525	2.43 531	12.04 526	0.01 547	1.67 531	1.93 527	0.55 540	4.44 526

SIFT-UM-Cal		0.21 522	0.23 525	0.14 536	0.68 554	0.15 560	0.29 548	0.04 561	0.05 543	0.10 554	0.56 553	0.01 547	0.12 555	0.02 545	0.34 554	0.15 554

SIFT-NCM-Cal		0.26 516	0.28 519	0.19 529	0.84 548	0.23 548	0.38 542	0.06 554	0.05 543	0.11 552	0.59 551	0.01 547	0.14 546	0.02 545	0.45 547	0.21 548

SIFT-CM-Cal		0.21 522	0.23 525	0.15 535	0.71 553	0.18 554	0.28 549	0.05 557	0.05 543	0.10 554	0.55 554	0.01 547	0.12 555	0.01 557	0.33 555	0.17 552

SIFT-PCN-Cal		0.18 524	0.20 527	0.13 537	0.58 558	0.10 564	0.23 552	0.04 561	0.04 553	0.08 557	0.47 555	0.01 547	0.10 557	0.01 557	0.30 556	0.19 549

SIFT-NN-UMatch		0.24 518	0.26 520	0.18 531	0.64 556	0.18 554	0.38 542	0.06 554	0.05 543	0.12 551	0.65 546	0.01 547	0.13 550	0.02 545	0.43 548	0.22 546

SIFT-NN-NCMNet		0.27 515	0.29 518	0.20 528	0.81 549	0.24 547	0.40 541	0.08 551	0.05 543	0.14 548	0.65 546	0.01 547	0.14 546	0.02 545	0.47 545	0.22 546

SIFT-NN-CMatch		0.25 517	0.26 520	0.19 529	0.68 554	0.21 549	0.35 544	0.06 554	0.05 543	0.15 546	0.65 546	0.01 547	0.13 550	0.02 545	0.41 549	0.23 544

SIFT-NN-PointCN		0.22 521	0.24 524	0.17 533	0.59 557	0.14 561	0.32 546	0.05 557	0.04 553	0.13 549	0.57 552	0.01 547	0.13 550	0.02 545	0.39 550	0.23 544

SIFT-NN		0.30 513	0.33 516	0.22 526	0.96 546	0.28 545	0.45 539	0.08 551	0.05 543	0.17 545	0.72 544	0.01 547	0.14 546	0.02 545	0.48 544	0.25 542

SIFT-UMatch		0.23 520	0.25 523	0.16 534	0.74 551	0.17 556	0.33 545	0.05 557	0.05 543	0.11 552	0.60 550	0.01 547	0.13 550	0.02 545	0.37 552	0.18 551

SIFT-NCMNet		0.15 526	0.17 529	0.10 539	0.52 560	0.09 565	0.19 553	0.02 565	0.04 553	0.07 559	0.39 557	0.01 547	0.08 559	0.01 557	0.24 558	0.11 555

SIFT-ConvMatch		0.24 518	0.26 520	0.18 531	0.76 550	0.21 549	0.32 546	0.05 557	0.05 543	0.13 549	0.63 549	0.01 547	0.13 550	0.02 545	0.38 551	0.19 549

SIFT-PointCN		0.18 524	0.20 527	0.13 537	0.58 558	0.11 563	0.25 550	0.04 561	0.04 553	0.08 557	0.45 556	0.01 547	0.10 557	0.01 557	0.30 556	0.17 552

SIFT-MNN		0.28 514	0.31 517	0.21 527	0.89 547	0.25 546	0.41 540	0.08 551	0.05 543	0.15 546	0.70 545	0.01 547	0.14 546	0.02 545	0.46 546	0.25 542

PMatch-Up-SfM		1.67 501	1.74 504	1.44 512	1.00 545	0.50 544	1.72 529	0.11 550	0.40 527	1.75 533	8.98 530	0.00 562	1.07 533	1.34 529	0.35 553	2.76 527

mmdepth		0.00 527	0.00 530	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	0.00 560	0.00 562	0.00 560	0.00 561	0.00 559	0.00 558

monomultidepth		0.00 527	0.00 530	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	0.00 560	0.00 562	0.00 560	0.00 561	0.00 559	0.00 558

test_blank		0.00 527	0.00 530	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	0.00 560	0.00 562	0.00 560	0.00 561	0.00 559	0.00 558

uanet_test		0.00 527	0.00 530	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	0.00 560	0.00 562	0.00 560	0.00 561	0.00 559	0.00 558

DCPMVS		0.00 527	0.00 530	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	0.00 560	0.00 562	0.00 560	0.00 561	0.00 559	0.00 558

sosnet-low-res		0.00 527	0.00 530	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	0.00 560	0.00 562	0.00 560	0.00 561	0.00 559	0.00 558

sosnet		0.00 527	0.00 530	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	0.00 560	0.00 562	0.00 560	0.00 561	0.00 559	0.00 558

uncertanet		0.00 527	0.00 530	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	0.00 560	0.00 562	0.00 560	0.00 561	0.00 559	0.00 558

Regformer		0.00 527	0.00 530	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	0.00 560	0.00 562	0.00 560	0.00 561	0.00 559	0.00 558

testmvs		6.14 486	8.18 487	0.01 540	0.01 564	0.00 568	73.40 405	0.00 566	0.00 558	0.02 560	0.15 558	0.00 562	0.00 560	0.02 545	0.00 559	0.02 556

test123		6.01 487	8.01 488	0.01 540	0.00 565	0.01 566	71.93 422	0.00 566	0.00 558	0.02 560	0.11 559	0.00 562	0.00 560	0.02 545	0.00 559	0.02 556

ab-mvs-re		7.68 484	10.24 485	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	92.12 60	0.00 562	0.00 560	0.00 561	0.00 559	0.00 558

uanet		0.00 527	0.00 530	0.00 542	0.00 565	0.00 568	0.00 554	0.00 566	0.00 558	0.00 562	0.00 560	0.00 562	0.00 560	0.00 561	0.00 559	0.00 558

Meshroom													0.00 560
: In preparation.
AliceVision / Meshro													0.00 560
: In preparation.
AliceVision_Meshroom													0.00 560
: In preparation.
PatchmatchNet2					0.00 565	32.03 470	74.85 388	61.13 468	37.29 462
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														23.45 476	40.77 461	68.54 470
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													67.71 470
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
aaatest				80.14 39	84.34 95	54.93 87	87.61 73	87.22 85	57.43 301	81.85 19	92.88 45		93.75 32	80.19 54	85.13 51	91.76 63

WAC-MVS						34.28 455								22.56 480

FOURS1					83.24 123	49.90 251	84.98 185	78.76 324	47.71 410	73.42 81

MSC_two_6792asdad				81.53 17	91.77 4	56.03 50		91.10 13					96.22 9	81.46 47	86.80 29	92.34 38

No_MVS				81.53 17	91.77 4	56.03 50		91.10 13					96.22 9	81.46 47	86.80 29	92.34 38

eth-test2					0.00 565

eth-test					0.00 565

IU-MVS					89.48 18	57.49 19		91.38 9	66.22 112	88.26 2				82.83 33	87.60 19	92.44 35

save fliter					85.35 75	56.34 44	89.31 42	81.46 254	61.55 213

test_0728_SECOND				82.20 9	89.50 16	57.73 15	92.34 5	88.88 39					96.39 4	81.68 42	87.13 22	92.47 34

GSMVS																88.13 213

test_part2					89.33 24	55.48 58				82.27 13

MTGPA								81.31 257

MTMP							87.27 90	15.34 519

gm-plane-assit					83.24 123	54.21 122			70.91 34		88.23 166		95.25 15	66.37 184

test9_res														78.72 68	85.44 46	91.39 79

agg_prior2														75.65 95	85.11 53	91.01 105

agg_prior					85.64 68	54.92 92		83.61 211		72.53 97			88.10 229

test_prior4						56.39 43	87.15 94

test_prior				78.39 97	86.35 58	54.91 95		85.45 133					89.70 154			90.55 123

旧先验2							81.73 301		45.53 430	74.66 67			70.48 466	58.31 268

新几何2							81.61 307

无先验							85.19 171	78.00 342	49.08 399				85.13 343	52.78 327		87.45 230

原ACMM2							83.77 231

testdata2													77.81 425	45.64 378

testdata1							77.55 370		64.14 153

plane_prior7					77.95 290	48.46 297

plane_prior5								82.59 229					88.30 222	65.46 195	72.34 219	84.49 294

plane_prior4											83.28 273

plane_prior3						48.95 278			64.01 157	62.15 258

plane_prior2							85.76 140		63.60 169

plane_prior1					78.31 286

plane_prior						49.57 256	87.43 82		64.57 143						72.84 211

n2								0.00 566

nn								0.00 566

door-mid								41.31 495

test11								84.25 191

door								43.27 491

HQP5-MVS						51.56 203

HQP-NCC					79.02 264		88.00 62		65.45 127	64.48 218

ACMP_Plane					79.02 264		88.00 62		65.45 127	64.48 218

BP-MVS														66.70 181

HQP4-MVS										64.47 221			88.61 201			84.91 290

HQP3-MVS								83.68 206							73.12 207

NP-MVS					78.76 270	50.43 233					85.12 237

ACMMP++_ref															63.20 320

ACMMP++															59.38 353

High-resolution multi-view benchmark