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 65	82.99 131	52.71 164	85.04 178	88.63 49	66.08 114	86.77 4	92.75 47	72.05 1	91.46 79	83.35 29	93.53 1	92.23 39
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 18	84.98 182	88.88 38	58.00 282	83.60 7	93.39 27	67.21 2	96.39 4	81.64 43	91.98 4	93.98 6

OPU-MVS				81.71 14	92.05 3	55.97 50	92.48 3				94.01 10	67.21 2	95.10 16	89.82 3	92.55 3	94.06 4

PC_three_1452									66.58 99	87.27 3	93.70 18	66.82 4	94.95 18	89.74 4	91.98 4	93.98 6

TestfortrainingZip				83.28 1	90.91 7	58.80 9	87.61 72	91.34 10	56.28 328	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	80.12 230	59.50 5	92.24 8	90.72 17	69.37 56	83.22 9	94.47 4	63.81 6	93.18 39	74.02 115	93.25 2	94.80 1

WBMVS		73.93 135	73.39 127	75.55 191	87.82 42	55.21 68	89.37 39	87.29 80	67.27 85	63.70 232	80.30 319	60.32 7	86.47 300	61.58 231	62.85 323	84.97 285

DELS-MVS		82.32 5	82.50 5	81.79 13	86.80 51	56.89 30	92.77 2	86.30 107	77.83 1	77.88 48	92.13 58	60.24 8	94.78 20	78.97 63	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 23	78.94 23	80.49 26	89.75 13	56.54 38	84.83 190	83.68 204	67.85 77	69.36 151	90.24 110	60.20 9	92.10 66	84.14 23	80.40 91	92.82 26

baseline2		75.15 110	74.54 109	76.98 141	81.67 173	51.74 195	83.84 226	91.94 3	69.97 46	58.98 296	86.02 220	59.73 10	91.73 73	68.37 168	70.40 245	87.48 225

CSCG		80.41 15	79.72 16	82.49 6	89.12 26	57.67 16	89.29 45	91.54 5	59.19 258	71.82 106	90.05 118	59.72 11	96.04 11	78.37 69	88.40 14	93.75 8

GG-mvs-BLEND				77.77 112	86.68 52	50.61 222	68.67 433	88.45 58		68.73 159	87.45 195	59.15 12	90.67 111	54.83 305	87.67 18	92.03 48

testing3-2		72.30 173	72.35 147	72.15 308	83.07 126	47.64 327	85.46 158	89.81 25	66.17 110	61.96 258	84.88 242	58.93 13	82.27 371	55.87 295	64.97 293	86.54 253

SED-MVS		81.92 8	81.75 9	82.44 8	89.48 18	56.89 30	92.48 3	88.94 36	57.50 296	84.61 5	94.09 8	58.81 14	96.37 7	82.28 37	87.60 19	94.06 4

test_241102_ONE					89.48 18	56.89 30		88.94 36	57.53 294	84.61 5	93.29 31	58.81 14	96.45 1

gg-mvs-nofinetune		67.43 286	64.53 314	76.13 170	85.95 59	47.79 325	64.38 448	88.28 61	39.34 451	66.62 176	41.27 491	58.69 16	89.00 181	49.64 347	86.62 32	91.59 67

BridgeMVS		80.28 16	79.73 15	81.90 12	86.47 55	59.34 6	80.45 330	89.51 27	69.76 51	71.05 124	86.66 209	58.68 17	93.24 37	84.64 20	90.40 6	93.14 19

UBG		78.86 26	78.86 24	78.86 63	87.80 43	55.43 57	87.67 70	91.21 12	72.83 10	72.10 101	88.40 153	58.53 18	89.08 176	73.21 130	77.98 124	92.08 44

myMVS_eth3d28		77.77 41	77.94 33	77.27 129	87.58 45	52.89 158	86.06 124	91.33 11	74.15 7	68.16 164	88.24 163	58.17 19	88.31 220	69.88 155	77.87 125	90.61 118

MED-MVS		79.56 21	79.39 19	80.06 42	84.34 92	54.93 84	87.61 72	87.22 82	56.22 329	81.85 18	92.98 41	58.11 20	93.75 32	80.19 52	85.96 38	91.52 72

testing11		79.18 24	78.85 25	80.16 36	88.33 32	56.99 27	88.31 58	92.06 1	72.82 11	70.62 139	88.37 155	57.69 21	92.30 58	75.25 100	76.24 154	91.20 91

MVSMamba_PlusPlus		75.28 104	73.39 127	80.96 22	80.85 205	58.25 11	74.47 390	87.61 77	50.53 387	65.24 197	83.41 267	57.38 22	92.83 43	73.92 117	87.13 22	91.80 60

testing99		78.45 28	77.78 37	80.45 29	88.28 35	56.81 33	87.95 65	91.49 6	71.72 18	70.84 132	88.09 172	57.29 23	92.63 51	69.24 160	75.13 178	91.91 53

CostFormer		73.89 138	72.30 150	78.66 72	82.36 151	56.58 35	75.56 379	85.30 138	66.06 115	70.50 141	76.88 364	57.02 24	89.06 177	68.27 170	68.74 260	90.33 128

test_0728_THIRD									58.00 282	81.91 16	93.64 20	56.54 25	96.44 2	81.64 43	86.86 27	92.23 39

DPE-MVS		79.82 19	79.66 17	80.29 32	89.27 25	55.08 76	88.70 52	87.92 68	55.55 338	81.21 24	93.69 19	56.51 26	94.27 26	78.36 70	85.70 43	91.51 74
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ETVMVS		75.80 94	75.44 84	76.89 144	86.23 58	50.38 233	85.55 153	91.42 7	71.30 27	68.80 158	87.94 180	56.42 27	89.24 170	56.54 288	74.75 186	91.07 97

DeepPCF-MVS	69.37 1	80.65 13	81.56 11	77.94 108	85.46 71	49.56 255	90.99 21	86.66 98	70.58 36	80.07 33	95.30 2	56.18 28	90.97 102	82.57 36	86.22 37	93.28 14

test_241102_TWO								88.76 45	57.50 296	83.60 7	94.09 8	56.14 29	96.37 7	82.28 37	87.43 21	92.55 31

testing91		78.30 34	77.54 40	80.61 24	88.16 38	57.12 26	87.94 66	91.07 16	71.43 23	70.75 134	88.04 177	55.82 30	92.65 49	69.61 156	75.00 182	92.05 47

patch_mono-2		80.84 12	81.59 10	78.62 77	90.34 10	53.77 127	88.08 60	88.36 60	76.17 2	79.40 40	91.09 82	55.43 31	90.09 134	85.01 16	80.40 91	91.99 52

testing222		77.70 43	77.22 46	79.14 54	86.95 49	54.89 93	87.18 90	91.96 2	72.29 13	71.17 122	88.70 143	55.19 32	91.24 86	65.18 198	76.32 152	91.29 85

DVP-MVS		81.30 10	81.00 13	82.20 9	89.40 21	57.45 20	92.34 5	89.99 22	57.71 290	81.91 16	93.64 20	55.17 33	96.44 2	81.68 41	87.13 22	92.72 29
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 20	92.32 7	88.63 49	57.71 290	83.14 10	93.96 11	55.17 33

TSAR-MVS + MP.		78.31 33	78.26 28	78.48 89	81.33 190	56.31 44	81.59 305	86.41 104	69.61 53	81.72 20	88.16 168	55.09 35	88.04 230	74.12 114	86.31 35	91.09 95
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 81	75.55 80	77.71 114	79.49 245	52.27 177	84.70 194	90.49 19	64.44 141	69.86 148	90.31 109	55.05 36	91.35 81	70.07 153	75.58 171	89.53 160

baseline1		72.51 167	72.12 157	73.69 261	85.05 78	44.46 383	83.51 236	86.13 112	71.61 21	64.64 210	87.97 179	55.00 37	89.48 161	59.07 254	56.05 387	87.13 237

test_one_0601					89.39 23	57.29 23		88.09 65	57.21 304	82.06 15	93.39 27	54.94 38

MM		82.69 2	83.29 3	80.89 23	84.38 91	55.40 61	92.16 10	89.85 24	75.28 4	82.41 12	93.86 14	54.30 39	93.98 27	90.29 1	87.13 22	93.30 13

TSAR-MVS + GP.		77.82 40	77.59 39	78.49 88	85.25 76	50.27 240	90.02 26	90.57 18	56.58 321	74.26 71	91.60 77	54.26 40	92.16 63	75.87 92	79.91 99	93.05 21

EPP-MVSNet		71.14 198	70.07 201	74.33 238	79.18 256	46.52 351	83.81 227	86.49 102	56.32 327	57.95 319	84.90 241	54.23 41	89.14 175	58.14 268	69.65 251	87.33 229

MCST-MVS		83.01 1	83.30 2	82.15 11	92.84 2	57.58 17	93.77 1	91.10 13	75.95 3	77.10 52	93.09 36	54.15 42	95.57 13	85.80 13	85.87 41	93.31 12

alignmvs		78.08 37	77.98 32	78.39 95	83.53 111	53.22 145	89.77 32	85.45 130	66.11 112	76.59 56	91.99 65	54.07 43	89.05 178	77.34 80	77.00 137	92.89 24

test-260524					88.20 37	55.35 63		88.22 62		80.74 28		53.67 44	94.67 21	80.11 55	85.96 38

GDP-MVS		75.27 105	74.38 110	77.95 107	79.04 260	52.86 160	85.22 166	86.19 110	62.43 196	70.66 137	90.40 107	53.51 45	91.60 75	69.25 159	72.68 212	89.39 167

WTY-MVS		77.47 47	77.52 41	77.30 127	88.33 32	46.25 360	88.46 56	90.32 20	71.40 24	72.32 98	91.72 72	53.44 46	92.37 57	66.28 183	75.42 172	93.28 14

IB-MVS	68.87 2	74.01 133	72.03 161	79.94 43	83.04 128	55.50 55	90.24 25	88.65 47	67.14 88	61.38 263	81.74 304	53.21 47	94.28 24	60.45 245	62.41 326	90.03 145
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 44	87.34 47	55.20 71	89.93 29	87.55 78	66.04 117	79.46 38	93.00 40	53.10 48	91.76 71	80.40 51	89.56 9	92.68 30

miper_enhance_ethall		69.77 232	68.90 222	72.38 302	78.93 264	49.91 246	83.29 247	78.85 317	64.90 137	59.37 288	79.46 329	52.77 49	85.16 339	63.78 210	58.72 355	82.08 345

MVSTER		73.25 151	72.33 148	76.01 174	85.54 69	53.76 128	83.52 232	87.16 85	67.06 92	63.88 227	81.66 305	52.77 49	90.44 121	64.66 203	64.69 299	83.84 312

CNVR-MVS		81.76 9	81.90 8	81.33 19	90.04 11	57.70 15	91.71 11	88.87 40	70.31 38	77.64 51	93.87 13	52.58 51	93.91 30	84.17 22	87.92 17	92.39 34

FIs		70.00 227	70.24 198	69.30 361	77.93 289	38.55 438	83.99 220	87.72 74	66.86 97	57.66 326	84.17 251	52.28 52	85.31 334	52.72 327	68.80 259	84.02 302

tpm2		70.82 207	68.44 228	77.98 104	80.78 207	56.11 46	74.21 393	81.28 257	60.24 236	68.04 166	75.27 382	52.26 53	88.50 209	55.82 298	68.03 265	89.33 169

thisisatest0515		73.64 145	72.20 153	77.97 105	81.63 176	53.01 154	86.69 109	88.81 43	62.53 192	64.06 222	85.65 224	52.15 54	92.50 53	58.43 261	69.84 248	88.39 204

aaEdge-Enhanced		79.48 22	79.20 22	80.35 31	88.96 27	54.93 84	88.65 53	88.50 57	56.62 318	79.87 35	92.88 44	51.96 55	94.36 23	80.19 52	85.13 50	91.76 61

casdiffmvs_mvg		77.75 42	77.28 44	79.16 53	80.42 224	54.44 113	87.76 67	85.46 129	71.67 20	71.38 117	88.35 158	51.58 56	91.22 87	79.02 62	79.89 101	91.83 58
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		68.82 254	68.29 231	70.40 347	75.71 340	42.59 409	84.23 211	86.78 94	66.31 106	58.51 310	82.45 287	51.57 57	84.64 348	53.11 318	55.96 388	83.96 308

PAPM		76.76 63	76.07 70	78.81 64	80.20 228	59.11 7	86.86 102	86.23 108	68.60 64	70.18 146	88.84 141	51.57 57	87.16 274	65.48 191	86.68 31	90.15 137

tttt0517		68.33 266	66.29 278	74.46 231	78.08 284	49.06 269	80.88 323	89.08 34	54.40 356	54.75 364	80.77 314	51.31 59	90.33 125	49.35 349	58.01 367	83.99 304

mvs_anonymous		72.29 174	70.74 180	76.94 143	82.85 138	54.72 102	78.43 361	81.54 251	63.77 160	61.69 260	79.32 331	51.11 60	85.31 334	62.15 227	75.79 162	90.79 112

HY-MVS	67.03 5	73.90 137	73.14 133	76.18 169	84.70 84	47.36 335	75.56 379	86.36 106	66.27 107	70.66 137	83.91 256	51.05 61	89.31 167	67.10 177	72.61 213	91.88 55

thisisatest0530		70.47 218	68.56 224	76.20 167	79.78 239	51.52 201	83.49 238	88.58 55	57.62 293	58.60 309	82.79 275	51.03 62	91.48 78	52.84 322	62.36 328	85.59 276

sasdasda		78.17 35	77.86 35	79.12 56	84.30 95	54.22 117	87.71 68	84.57 181	67.70 81	77.70 49	92.11 61	50.90 63	89.95 138	78.18 73	77.54 129	93.20 16

miper_ehance_all_eth		68.70 260	67.58 249	72.08 310	76.91 316	49.48 261	82.47 277	78.45 332	62.68 190	58.28 318	77.88 345	50.90 63	85.01 342	61.91 228	58.72 355	81.75 350

canonicalmvs		78.17 35	77.86 35	79.12 56	84.30 95	54.22 117	87.71 68	84.57 181	67.70 81	77.70 49	92.11 61	50.90 63	89.95 138	78.18 73	77.54 129	93.20 16

casdiffmvs		77.36 49	76.85 53	78.88 62	80.40 225	54.66 107	87.06 93	85.88 116	72.11 16	71.57 110	88.63 148	50.89 66	90.35 124	76.00 90	79.11 110	91.63 66
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 28	86.63 53	54.69 104	92.20 9	86.66 98	74.48 5	82.63 11	93.80 16	50.83 67	93.70 34	90.11 2	86.44 34	93.01 22

fmvsm_s_conf0.5_n_9		76.66 66	76.94 52	75.85 179	79.54 244	48.30 301	82.63 269	71.84 416	70.25 40	80.63 30	94.53 3	50.78 68	87.42 264	88.32 5	73.92 194	91.82 59

baseline		76.86 59	76.24 66	78.71 68	80.47 219	54.20 121	83.90 224	84.88 165	71.38 25	71.51 113	89.15 136	50.51 69	90.55 117	75.71 93	78.65 115	91.39 77

TestfortrainingZip a		77.64 44	76.79 57	80.20 34	84.34 92	54.79 97	87.61 72	87.03 87	56.22 329	78.78 41	92.98 41	50.45 70	94.28 24	74.37 109	79.31 108	91.52 72

MVS_Test		75.85 90	74.93 98	78.62 77	84.08 100	55.20 71	83.99 220	85.17 145	68.07 73	73.38 80	82.76 276	50.44 71	89.00 181	65.90 187	80.61 87	91.64 65

FC-MVSNet-test		67.49 284	67.91 237	66.21 395	76.06 331	33.06 460	80.82 324	87.18 84	64.44 141	54.81 362	82.87 273	50.40 72	82.60 369	48.05 360	66.55 278	82.98 336

nrg030		72.27 176	71.56 165	74.42 233	75.93 337	50.60 223	86.97 95	83.21 216	62.75 187	67.15 172	84.38 247	50.07 73	86.66 294	71.19 145	62.37 327	85.99 265

fmvsm_l_conf0.5_n		75.95 86	76.16 68	75.31 204	76.01 335	48.44 294	84.98 182	71.08 426	63.50 169	81.70 21	93.52 23	50.00 74	87.18 273	87.80 6	76.87 141	90.32 129

cl22		68.85 252	67.69 247	72.35 303	78.07 285	49.98 245	82.45 278	78.48 331	62.50 194	58.46 314	77.95 343	49.99 75	85.17 338	62.55 221	58.72 355	81.90 348

fmvsm_l_conf0.5_n_a		75.88 89	76.07 70	75.31 204	76.08 330	48.34 297	85.24 165	70.62 429	63.13 177	81.45 22	93.62 22	49.98 76	87.40 266	87.76 7	76.77 143	90.20 134

tpmrst		71.04 203	69.77 205	74.86 222	83.19 122	55.86 52	75.64 376	78.73 324	67.88 76	64.99 203	73.73 394	49.96 77	79.56 405	65.92 186	67.85 268	89.14 176

CANet		80.90 11	81.17 12	80.09 41	87.62 44	54.21 119	91.60 14	86.47 103	73.13 9	79.89 34	93.10 34	49.88 78	92.98 40	84.09 24	84.75 55	93.08 20

ET-MVSNet_ETH3D		75.23 108	74.08 115	78.67 71	84.52 88	55.59 53	88.92 49	89.21 32	68.06 74	53.13 379	90.22 112	49.71 79	87.62 256	72.12 141	70.82 236	92.82 26

hybridcas		76.66 66	75.99 73	78.65 74	79.25 253	54.46 112	86.82 104	85.53 126	70.88 33	70.40 144	88.21 165	49.55 80	90.12 133	74.42 108	78.88 114	91.37 79

c3_l		67.97 272	66.66 271	71.91 321	76.20 329	49.31 266	82.13 285	78.00 340	61.99 202	57.64 327	76.94 361	49.41 81	84.93 343	60.62 240	57.01 378	81.49 355

Vis-MVSNet (Re-imp)		65.52 323	65.63 295	65.17 405	77.49 300	30.54 469	75.49 382	77.73 347	59.34 253	52.26 386	86.69 208	49.38 82	80.53 392	37.07 411	75.28 174	84.42 293

EPNet		78.36 32	78.49 27	77.97 105	85.49 70	52.04 180	89.36 41	84.07 196	73.22 8	77.03 53	91.72 72	49.32 83	90.17 132	73.46 125	82.77 67	91.69 63
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_l_conf0.5_n_9		77.10 52	77.48 42	75.98 176	77.54 299	47.77 326	86.35 115	73.46 407	68.69 63	81.07 25	94.40 5	49.06 84	88.89 190	87.39 8	79.32 107	91.27 88

testing3		59.97 369	60.19 359	59.32 440	77.60 293	30.01 475	81.75 297	81.79 245	53.54 362	50.34 405	79.94 321	48.99 85	76.91 429	17.19 490	50.59 419	71.03 463

Casviewmamba		76.27 76	75.48 82	78.63 76	79.14 257	54.27 116	85.81 134	83.09 219	70.96 30	70.41 143	88.36 157	48.71 86	90.81 106	75.92 91	76.95 138	90.80 111

E3new		76.85 60	76.24 66	78.66 72	81.62 177	55.01 79	86.94 97	85.10 154	71.55 22	71.93 105	88.61 149	48.40 87	89.60 155	74.50 106	77.53 131	91.36 80

tpm		68.36 264	67.48 254	70.97 338	79.93 233	51.34 205	76.58 373	78.75 323	67.73 79	63.54 239	74.86 384	48.33 88	72.36 457	53.93 312	63.71 307	89.21 173

APDe-MVS		78.44 29	78.20 29	79.19 51	88.56 28	54.55 110	89.76 33	87.77 72	55.91 333	78.56 44	92.49 53	48.20 89	92.65 49	79.49 57	83.04 66	90.39 125
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 75	76.81 55	74.71 226	79.21 254	46.90 341	85.03 179	73.96 396	69.00 61	79.70 37	93.88 12	48.07 90	87.71 250	84.26 21	78.15 122	89.50 163

MG-MVS		78.42 30	76.99 51	82.73 3	93.17 1	64.46 1	89.93 29	88.51 56	64.83 138	73.52 78	88.09 172	48.07 90	92.19 62	62.24 225	84.53 57	91.53 71

DeepC-MVS	67.15 4	76.90 58	76.27 65	78.80 65	80.70 209	55.02 78	86.39 113	86.71 96	66.96 96	67.91 167	89.97 120	48.03 92	91.41 80	75.60 95	84.14 59	89.96 147
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 66	76.01 72	78.62 77	81.14 193	54.95 82	86.88 101	85.04 156	71.37 26	71.76 107	88.44 152	48.02 93	89.57 158	74.17 113	77.23 133	91.33 84

MGCFI-Net		74.07 132	74.64 108	72.34 304	82.90 135	43.33 401	80.04 339	79.96 286	65.61 120	74.93 63	91.85 68	48.01 94	80.86 384	71.41 144	77.10 134	92.84 25

test_prior2							89.04 48		61.88 205	73.55 77	91.46 81	48.01 94		74.73 103	85.46 45

myMVS_eth3d		63.52 342	63.56 323	63.40 418	81.73 168	34.28 452	80.97 320	81.02 260	60.93 225	55.06 358	82.64 282	48.00 96	80.81 385	23.42 475	58.32 359	75.10 434

balanced_ft_v1		75.25 106	73.90 120	79.29 49	85.59 67	56.72 34	74.35 392	87.27 81	60.24 236	59.07 295	85.17 232	47.76 97	90.51 118	82.62 35	83.06 65	90.64 116

SF-MVS		77.64 44	77.42 43	78.32 98	83.75 108	52.47 169	86.63 111	87.80 69	58.78 270	74.63 66	92.38 55	47.75 98	91.35 81	78.18 73	86.85 28	91.15 94

test2506		72.91 157	72.43 146	74.32 239	80.12 230	44.18 390	83.19 251	84.77 170	64.02 151	65.97 185	87.43 196	47.67 99	88.72 196	59.08 253	79.66 103	90.08 143

E2		76.39 72	75.67 76	78.56 84	80.49 217	54.87 94	86.80 105	84.95 160	71.09 28	71.51 113	88.21 165	47.55 100	89.53 159	73.65 121	76.77 143	91.29 85

E3		76.39 72	75.67 76	78.56 84	80.49 217	54.87 94	86.80 105	84.95 160	71.09 28	71.51 113	88.21 165	47.55 100	89.53 159	73.65 121	76.77 143	91.29 85

fmvsm_s_conf0.5_n_3		74.97 114	75.42 85	73.62 264	76.99 313	46.67 346	83.13 254	71.14 425	66.20 109	82.13 14	93.76 17	47.49 102	84.00 354	81.95 40	76.02 157	90.19 136

1112_ss		70.05 225	69.37 211	72.10 309	80.77 208	42.78 407	85.12 175	76.75 364	59.69 245	61.19 265	92.12 59	47.48 103	83.84 356	53.04 320	68.21 263	89.66 154

fmvsm_s_conf0.5_n_10		76.80 61	76.81 55	76.78 151	78.91 265	47.85 321	83.44 239	74.66 387	68.93 62	81.31 23	94.12 7	47.44 104	90.82 105	83.43 28	79.06 112	91.66 64

Effi-MVS+		75.24 107	73.61 126	80.16 36	81.92 163	57.42 22	85.21 167	76.71 367	60.68 231	73.32 81	89.34 131	47.30 105	91.63 74	68.28 169	79.72 102	91.42 76

UniMVSNet (Re)		67.71 278	66.80 267	70.45 345	74.44 361	42.93 405	82.42 279	84.90 164	63.69 164	59.63 282	80.99 311	47.18 106	85.23 337	51.17 339	56.75 379	83.19 330

test12				79.24 50	86.89 50	56.08 47		85.16 147		72.27 99		47.15 107	91.10 92		85.93 40	90.54 122

PVSNet_Blended_VisFu		73.40 149	72.44 145	76.30 160	81.32 191	54.70 103	85.81 134	78.82 319	63.70 163	64.53 214	85.38 230	47.11 108	87.38 267	67.75 173	77.55 128	86.81 250

fmvsm_s_conf0.5_n_8		76.50 70	76.68 60	75.94 177	78.67 270	47.92 319	85.18 169	74.71 386	68.09 70	80.67 29	94.26 6	47.09 109	89.26 169	86.62 10	74.85 184	90.65 115

test_fmvsm_n_1920		75.56 101	75.54 81	75.61 187	74.60 360	49.51 260	81.82 294	74.08 393	66.52 102	80.40 31	93.46 25	46.95 110	89.72 147	86.69 9	75.30 173	87.61 223

NCCC		79.57 20	79.23 21	80.59 25	89.50 16	56.99 27	91.38 16	88.17 63	67.71 80	73.81 75	92.75 47	46.88 111	93.28 36	78.79 66	84.07 60	91.50 75

viewmanbaseed2359cas		76.71 65	76.16 68	78.37 97	81.16 192	55.05 77	86.96 96	85.32 136	71.71 19	72.25 100	88.50 151	46.86 112	88.96 185	74.55 105	78.08 123	91.08 96

E4		75.99 84	75.16 91	78.48 89	79.56 243	54.74 99	86.66 110	84.80 168	70.62 34	71.16 123	87.90 181	46.84 113	89.47 163	72.70 132	76.20 156	91.23 89

PRO-TEST		70.63 213	70.25 197	71.76 324	78.23 283	38.48 439	66.45 441	84.09 194	65.04 136	46.57 430	82.73 279	46.83 114	89.59 157	79.18 60	83.17 64	87.21 235

fmvsm_s_conf0.5_n_6		76.17 79	76.84 54	74.15 244	77.42 302	46.46 352	85.53 155	77.86 344	69.78 50	79.78 36	92.90 43	46.80 115	84.81 345	84.67 19	76.86 142	91.17 93

9.14			78.19 30		85.67 65		88.32 57	88.84 42	59.89 240	74.58 68	92.62 50	46.80 115	92.66 48	81.40 48	85.62 44

VNet		77.99 39	77.92 34	78.19 101	87.43 46	50.12 241	90.93 22	91.41 8	67.48 84	75.12 61	90.15 116	46.77 117	91.00 97	73.52 123	78.46 118	93.44 10

PVSNet_BlendedMVS		73.42 148	73.30 129	73.76 258	85.91 60	51.83 189	86.18 120	84.24 190	65.40 126	69.09 155	80.86 313	46.70 118	88.13 226	75.43 96	65.92 289	81.33 363

PVSNet_Blended		76.53 69	76.54 61	76.50 157	85.91 60	51.83 189	88.89 50	84.24 190	67.82 78	69.09 155	89.33 133	46.70 118	88.13 226	75.43 96	81.48 80	89.55 158

0.3-1-1-0.015		72.75 161	71.06 176	77.81 110	80.58 214	50.62 221	89.45 37	88.60 53	63.74 162	65.56 193	81.82 302	46.61 120	90.64 114	62.86 219	60.35 339	92.17 42

SMA-MVS		79.10 25	78.76 26	80.12 39	84.42 89	55.87 51	87.58 79	86.76 95	61.48 213	80.26 32	93.10 34	46.53 121	92.41 55	79.97 56	88.77 11	92.08 44
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 53	77.02 49	77.32 126	81.66 174	52.32 173	89.31 42	82.11 235	72.20 14	73.23 83	91.05 83	46.52 122	91.00 97	76.23 87	80.83 84	88.64 190

SymmetryMVS		77.43 48	77.09 48	78.44 93	82.56 147	52.32 173	89.31 42	84.15 193	72.20 14	73.23 83	91.05 83	46.52 122	91.00 97	76.23 87	78.55 117	92.00 51

viewdifsd2359ckpt07		74.81 118	74.01 118	77.21 133	79.62 241	53.13 150	85.70 148	83.75 202	68.12 69	68.14 165	87.33 199	46.51 124	87.92 233	73.32 126	73.63 198	90.57 119

test_fmvsmconf_n		74.41 124	74.05 116	75.49 196	74.16 368	48.38 295	82.66 267	72.57 411	67.05 93	75.11 62	92.88 44	46.35 125	87.81 240	83.93 25	71.71 224	90.28 130

fmvsm_l_conf0.5_n_3		75.73 99	75.78 74	75.61 187	76.03 333	48.33 299	85.34 159	72.92 410	67.16 87	78.55 45	93.85 15	46.22 126	87.53 260	85.61 14	76.30 153	90.98 104

tpm cat1		66.28 314	62.78 326	76.77 152	81.40 188	57.14 25	70.03 426	77.19 356	53.00 367	58.76 304	70.73 431	46.17 127	86.73 291	43.27 387	64.46 301	86.44 257

fmvsm_s_conf0.5_n_4		74.92 115	74.88 99	75.03 216	75.96 336	47.53 329	85.84 133	73.19 409	67.07 91	79.43 39	92.60 51	46.12 128	88.03 231	84.70 18	69.01 254	89.53 160

cl____		67.43 286	65.93 288	71.95 318	76.33 323	48.02 312	82.58 270	79.12 312	61.30 216	56.72 343	76.92 362	46.12 128	86.44 302	57.98 270	56.31 382	81.38 362

viewdifsd2359ckpt13		75.96 85	75.07 93	78.65 74	81.14 193	55.21 68	86.15 121	84.95 160	69.98 45	70.49 142	88.16 168	46.10 130	89.86 140	72.39 135	76.23 155	90.89 108

DIV-MVS_self_test		67.43 286	65.93 288	71.94 319	76.33 323	48.01 313	82.57 271	79.11 313	61.31 215	56.73 342	76.92 362	46.09 131	86.43 303	57.98 270	56.31 382	81.39 361

0.4-1-1-0.2		72.79 160	71.07 175	77.94 108	80.58 214	50.83 217	89.59 35	88.63 49	63.94 157	65.74 191	81.80 303	46.05 132	90.68 110	62.98 218	60.35 339	92.31 38

IS-MVSNet		68.80 256	67.55 251	72.54 295	78.50 277	43.43 398	81.03 318	79.35 308	59.12 263	57.27 336	86.71 207	46.05 132	87.70 251	44.32 383	75.60 170	86.49 256

diffmvs		75.11 111	74.65 107	76.46 158	78.52 276	53.35 140	83.28 248	79.94 287	70.51 37	71.64 109	88.72 142	46.02 134	86.08 316	77.52 78	75.75 168	89.96 147
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		74.92 115	73.70 124	78.60 81	80.28 226	54.94 83	84.77 192	80.56 273	69.96 47	69.38 150	88.38 154	46.01 135	90.50 119	72.44 134	71.49 228	90.38 126

0.4-1-1-0.1		72.39 168	70.70 181	77.46 122	80.45 220	50.04 243	89.09 47	88.45 58	63.06 178	64.91 206	81.60 307	45.98 136	90.46 120	62.40 222	60.34 341	91.88 55

E6new		75.74 95	74.80 103	78.56 84	79.85 234	54.92 89	85.87 129	84.72 173	70.19 41	70.90 128	87.73 188	45.98 136	89.71 148	72.16 137	75.78 165	91.06 98

E6		75.74 95	74.80 103	78.56 84	79.85 234	54.92 89	85.87 129	84.72 173	70.19 41	70.90 128	87.73 188	45.98 136	89.71 148	72.16 137	75.78 165	91.06 98

E5new		75.74 95	74.80 103	78.57 82	79.85 234	54.93 84	85.87 129	84.72 173	70.19 41	70.90 128	87.74 186	45.97 139	89.71 148	72.15 139	75.79 162	91.06 98

E5		75.74 95	74.80 103	78.57 82	79.85 234	54.93 84	85.87 129	84.72 173	70.19 41	70.90 128	87.74 186	45.97 139	89.71 148	72.15 139	75.79 162	91.06 98

blend_shiyan4		67.33 291	65.28 304	73.45 269	70.71 409	47.96 316	86.21 119	85.65 124	56.45 325	52.18 387	72.99 404	45.89 141	88.50 209	56.81 285	60.68 337	83.90 310

EI-MVSNet		69.70 237	68.70 223	72.68 291	75.00 354	48.90 277	79.54 348	87.16 85	61.05 221	63.88 227	83.74 259	45.87 142	90.44 121	57.42 281	64.68 300	78.70 391

IterMVS-LS		66.63 307	65.36 303	70.42 346	75.10 352	48.90 277	81.45 313	76.69 368	61.05 221	55.71 353	77.10 358	45.86 143	83.65 360	57.44 280	57.88 371	78.70 391
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs_AUTHOR		74.80 119	74.30 112	76.29 161	77.34 303	53.19 146	83.17 253	79.50 301	69.93 48	71.55 111	88.57 150	45.85 144	86.03 318	77.17 82	75.64 169	89.67 153

EIA-MVS		75.92 87	75.18 90	78.13 102	85.14 77	51.60 198	87.17 91	85.32 136	64.69 139	68.56 160	90.53 101	45.79 145	91.58 76	67.21 176	82.18 73	91.20 91

MVS		76.91 56	75.48 82	81.23 20	84.56 87	55.21 68	80.23 336	91.64 4	58.65 272	65.37 195	91.48 80	45.72 146	95.05 17	72.11 142	89.52 10	93.44 10

PAPM_NR		71.80 186	69.98 203	77.26 131	81.54 183	53.34 141	78.60 360	85.25 142	53.46 363	60.53 273	88.66 144	45.69 147	89.24 170	56.49 289	79.62 105	89.19 174

UWE-MVS-28		67.43 286	67.98 236	65.75 398	75.66 341	34.74 450	80.00 342	88.17 63	64.21 147	57.27 336	84.14 252	45.68 148	78.82 408	44.33 381	72.40 216	83.70 318

hybridnocas07		74.65 120	74.00 119	76.61 155	77.58 295	52.72 163	83.64 230	79.72 293	69.43 55	70.80 133	88.33 160	45.56 149	87.34 268	76.88 84	74.07 190	89.78 151

viewmambaseed2359dif		73.51 147	72.78 139	75.71 184	76.93 315	51.89 187	82.81 264	79.66 296	65.46 122	70.29 145	88.05 175	45.55 150	85.85 326	73.49 124	72.76 211	89.39 167

CS-MVS		76.77 62	76.70 59	76.99 140	83.55 110	48.75 282	88.60 54	85.18 144	66.38 105	72.47 96	91.62 76	45.53 151	90.99 101	74.48 107	82.51 69	91.23 89

DeepC-MVS_fast	67.50 3	78.00 38	77.63 38	79.13 55	88.52 29	55.12 73	89.95 28	85.98 114	68.31 65	71.33 118	92.75 47	45.52 152	90.37 123	71.15 146	85.14 49	91.91 53
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		74.48 121	74.12 114	75.56 190	76.96 314	47.85 321	85.32 163	69.80 436	64.16 149	78.74 42	93.48 24	45.51 153	89.29 168	86.48 11	66.62 276	89.55 158

viewmacassd2359aftdt		75.91 88	75.14 92	78.21 100	79.40 247	54.82 96	86.71 108	84.98 158	70.89 32	71.52 112	87.89 182	45.43 154	88.85 194	72.35 136	77.08 135	90.97 105

fmvsm_s_conf0.5_n_5		75.02 112	75.07 93	74.88 221	74.33 365	47.83 323	83.99 220	73.54 402	67.10 89	76.32 57	92.43 54	45.42 155	86.35 306	82.98 31	79.50 106	90.47 124

fmvsm_s_conf0.5_n_a		73.68 144	73.15 131	75.29 207	75.45 344	48.05 311	83.88 225	68.84 441	63.43 171	78.60 43	93.37 29	45.32 156	88.92 189	85.39 15	64.04 303	88.89 182

Test_1112_low_res		67.18 295	66.23 280	70.02 355	78.75 268	41.02 426	83.43 240	73.69 399	57.29 300	58.45 315	82.39 289	45.30 157	80.88 383	50.50 341	66.26 286	88.16 207

ETV-MVS		77.17 51	76.74 58	78.48 89	81.80 166	54.55 110	86.13 122	85.33 135	68.20 68	73.10 85	90.52 102	45.23 158	90.66 112	79.37 58	80.95 81	90.22 132

SPE-MVS-test		77.20 50	77.25 45	77.05 135	84.60 86	49.04 272	89.42 38	85.83 118	65.90 118	72.85 89	91.98 67	45.10 159	91.27 84	75.02 102	84.56 56	90.84 109

NR-MVSNet		67.25 293	65.99 286	71.04 337	73.27 377	43.91 392	85.32 163	84.75 171	66.05 116	53.65 377	82.11 297	45.05 160	85.97 323	47.55 362	56.18 385	83.24 328

UWE-MVS		72.17 177	72.15 155	72.21 306	82.26 152	44.29 387	86.83 103	89.58 26	65.58 121	65.82 188	85.06 235	45.02 161	84.35 350	54.07 310	75.18 175	87.99 214

train_agg		76.91 56	76.40 63	78.45 92	85.68 63	55.42 58	87.59 77	84.00 197	57.84 287	72.99 86	90.98 87	44.99 162	88.58 202	78.19 71	85.32 47	91.34 83

test_8					85.72 62	55.31 64	87.60 76	83.88 200	57.84 287	72.84 90	90.99 86	44.99 162	88.34 217

segment_acmp												44.97 164

hybrid		74.44 123	73.79 123	76.39 159	77.31 305	52.89 158	83.37 246	79.79 291	68.21 67	71.01 125	88.14 170	44.93 165	86.68 292	77.29 81	74.11 189	89.59 156

test_fmvsmconf0.1_n		73.69 143	73.15 131	75.34 202	70.71 409	48.26 302	82.15 283	71.83 417	66.75 98	74.47 70	92.59 52	44.89 166	87.78 247	83.59 27	71.35 231	89.97 146

TEST9					85.68 63	55.42 58	87.59 77	84.00 197	57.72 289	72.99 86	90.98 87	44.87 167	88.58 202

eth_miper_zixun_eth		66.98 302	65.28 304	72.06 311	75.61 342	50.40 230	81.00 319	76.97 363	62.00 201	56.99 340	76.97 360	44.84 168	85.58 329	58.75 258	54.42 401	80.21 379

MVSFormer		73.53 146	72.19 154	77.57 117	83.02 129	55.24 66	81.63 302	81.44 253	50.28 388	76.67 54	90.91 93	44.82 169	86.11 311	60.83 237	80.09 95	91.36 80

lupinMVS		78.38 31	78.11 31	79.19 51	83.02 129	55.24 66	91.57 15	84.82 166	69.12 59	76.67 54	92.02 63	44.82 169	90.23 130	80.83 50	80.09 95	92.08 44

WR-MVS		67.58 281	66.76 268	70.04 354	75.92 338	45.06 380	86.23 118	85.28 140	64.31 144	58.50 312	81.00 310	44.80 171	82.00 376	49.21 351	55.57 393	83.06 333

fmvsm_s_conf0.1_n		73.80 139	73.26 130	75.43 197	73.28 376	47.80 324	84.57 202	69.43 438	63.34 172	78.40 46	93.29 31	44.73 172	89.22 172	85.99 12	66.28 285	89.26 170

viewmamba		73.92 136	73.03 137	76.58 156	77.56 297	52.73 162	82.91 262	78.77 321	69.23 58	68.85 157	88.01 178	44.71 173	87.57 258	73.86 118	73.40 201	89.44 166

ZD-MVS					89.55 15	53.46 133		84.38 184	57.02 306	73.97 73	91.03 85	44.57 174	91.17 89	75.41 99	81.78 78

onestephybrid01		74.31 127	73.65 125	76.27 162	77.58 295	51.99 182	82.22 282	78.44 333	69.26 57	70.95 127	88.11 171	44.46 175	87.30 269	78.01 76	73.86 196	89.51 162

Fast-Effi-MVS+		72.73 162	71.15 174	77.48 120	82.75 141	54.76 98	86.77 107	80.64 269	63.05 179	65.93 186	84.01 253	44.42 176	89.03 179	56.45 292	76.36 151	88.64 190

dtuplus		73.09 154	72.29 151	75.52 195	76.27 327	51.82 191	82.99 260	79.98 284	65.08 135	70.11 147	87.66 192	44.38 177	85.64 328	71.56 143	72.55 214	89.11 177

fmvsm_s_conf0.1_n_a		72.82 159	72.05 159	75.12 213	70.95 407	47.97 314	82.72 266	68.43 443	62.52 193	78.17 47	93.08 37	44.21 178	88.86 191	84.82 17	63.54 310	88.54 198

PCF-MVS	61.03 10	70.10 223	68.40 229	75.22 212	77.15 311	51.99 182	79.30 353	82.12 234	56.47 324	61.88 259	86.48 213	43.98 179	87.24 272	55.37 303	72.79 210	86.43 258
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CDS-MVSNet		70.48 217	69.43 209	73.64 262	77.56 297	48.83 279	83.51 236	77.45 352	63.27 174	62.33 250	85.54 227	43.85 180	83.29 366	57.38 282	74.00 191	88.79 186
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EI-MVSNet-Vis-set		73.19 152	72.60 142	74.99 219	82.56 147	49.80 250	82.55 273	89.00 35	66.17 110	65.89 187	88.98 137	43.83 181	92.29 59	65.38 197	69.01 254	82.87 338

APD-MVS		76.15 80	75.68 75	77.54 119	88.52 29	53.44 136	87.26 89	85.03 157	53.79 360	74.91 64	91.68 74	43.80 182	90.31 126	74.36 110	81.82 76	88.87 183
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_HR		76.39 72	75.38 87	79.42 47	85.33 74	56.47 40	88.15 59	84.97 159	65.15 134	66.06 184	89.88 121	43.79 183	92.16 63	75.03 101	80.03 98	89.64 155

thres100view900		66.87 304	65.42 302	71.24 332	83.29 119	43.15 403	81.67 301	87.78 70	59.04 264	55.92 352	82.18 296	43.73 184	87.80 243	28.80 452	66.36 282	82.78 340

thres600view7		66.46 311	65.12 308	70.47 344	83.41 113	43.80 394	82.15 283	87.78 70	59.37 252	56.02 351	82.21 295	43.73 184	86.90 283	26.51 464	64.94 294	80.71 373

v148		68.24 269	66.35 276	73.88 253	71.76 395	51.47 202	84.23 211	81.90 244	63.69 164	58.94 297	76.44 369	43.72 186	87.78 247	60.63 239	55.86 390	82.39 343

SD-MVS		76.18 78	74.85 100	80.18 35	85.39 72	56.90 29	85.75 139	82.45 231	56.79 314	74.48 69	91.81 69	43.72 186	90.75 108	74.61 104	78.65 115	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		70.18 219	69.28 215	72.89 283	77.64 291	42.88 406	85.06 176	87.50 79	62.58 191	62.66 248	82.34 294	43.64 188	89.83 143	58.42 263	63.70 308	85.96 267

tfpn200view9		67.57 282	66.13 282	71.89 322	84.05 101	45.07 377	83.40 242	87.71 75	60.79 228	57.79 323	82.76 276	43.53 189	87.80 243	28.80 452	66.36 282	82.78 340

thres400		67.40 290	66.13 282	71.19 334	84.05 101	45.07 377	83.40 242	87.71 75	60.79 228	57.79 323	82.76 276	43.53 189	87.80 243	28.80 452	66.36 282	80.71 373

PAPR		75.20 109	74.13 113	78.41 94	88.31 34	55.10 75	84.31 209	85.66 122	63.76 161	67.55 169	90.73 98	43.48 191	89.40 164	66.36 182	77.03 136	90.73 113

kuosan		50.20 434	50.09 419	50.52 460	73.09 379	29.09 482	65.25 443	74.89 384	48.27 403	41.34 453	60.85 468	43.45 192	67.48 467	18.59 488	25.07 491	55.01 485

fmvsm_s_conf0.5_n_7		73.10 153	73.89 122	70.72 341	74.17 367	46.03 365	83.28 248	74.19 391	67.10 89	73.94 74	91.73 71	43.42 193	77.61 424	83.92 26	73.26 203	88.53 199

MP-MVS		74.99 113	74.33 111	76.95 142	82.89 136	53.05 153	85.63 149	83.50 210	57.86 286	67.25 171	90.24 110	43.38 194	88.85 194	76.03 89	82.23 72	88.96 180
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
casdiffseed414692147		74.22 128	72.73 140	78.69 69	79.85 234	54.64 108	85.13 171	83.67 208	69.07 60	69.41 149	86.47 214	43.27 195	90.69 109	63.77 211	73.91 195	90.73 113

EI-MVSNet-UG-set		72.37 170	71.73 162	74.29 240	81.60 179	49.29 267	81.85 292	88.64 48	65.29 131	65.05 200	88.29 162	43.18 196	91.83 70	63.74 212	67.97 266	81.75 350

thres200		68.71 258	67.27 259	73.02 277	84.73 83	46.76 345	85.03 179	87.73 73	62.34 197	59.87 277	83.45 266	43.15 197	88.32 219	31.25 444	67.91 267	83.98 306

PHI-MVS		77.49 46	77.00 50	78.95 59	85.33 74	50.69 220	88.57 55	88.59 54	58.14 279	73.60 76	93.31 30	43.14 198	93.79 31	73.81 119	88.53 13	92.37 35

ab-mvs		70.65 212	69.11 218	75.29 207	80.87 204	46.23 363	73.48 399	85.24 143	59.99 239	66.65 175	80.94 312	43.13 199	88.69 197	63.58 213	68.07 264	90.95 106

CDPH-MVS		76.05 83	75.19 89	78.62 77	86.51 54	54.98 81	87.32 84	84.59 180	58.62 273	70.75 134	90.85 95	43.10 200	90.63 115	70.50 150	84.51 58	90.24 131

reproduce_monomvs		69.71 233	68.52 226	73.29 274	86.43 56	48.21 304	83.91 223	86.17 111	68.02 75	54.91 360	77.46 351	42.96 201	88.86 191	68.44 167	48.38 430	82.80 339

v8		67.25 293	64.99 310	74.04 247	72.89 383	53.31 143	82.37 280	80.11 282	61.54 211	54.29 370	76.02 378	42.89 202	88.41 213	58.43 261	56.36 380	80.39 377

EC-MVSNet		75.30 103	75.20 88	75.62 186	80.98 198	49.00 273	87.43 80	84.68 178	63.49 170	70.97 126	90.15 116	42.86 203	91.14 91	74.33 111	81.90 75	86.71 251

h-mvs33		73.95 134	72.89 138	77.15 134	80.17 229	50.37 234	84.68 196	83.33 211	68.08 71	71.97 103	88.65 147	42.50 204	91.15 90	78.82 64	57.78 373	89.91 149

hse-mvs2		71.44 194	70.68 182	73.73 260	76.34 322	47.44 334	79.45 351	79.47 303	68.08 71	71.97 103	86.01 222	42.50 204	86.93 282	78.82 64	53.46 411	86.83 248

SteuartSystems-ACMMP		77.08 54	76.33 64	79.34 48	80.98 198	55.31 64	89.76 33	86.91 90	62.94 181	71.65 108	91.56 78	42.33 206	92.56 52	77.14 83	83.69 62	90.15 137
Skip Steuart: Steuart Systems R&D Blog.
HyFIR lowres test		69.94 230	67.58 249	77.04 136	77.11 312	57.29 23	81.49 312	79.11 313	58.27 277	58.86 301	80.41 316	42.33 206	86.96 280	61.91 228	68.68 261	86.87 242

ZNCC-MVS		75.82 93	75.02 96	78.23 99	83.88 106	53.80 126	86.91 100	86.05 113	59.71 244	67.85 168	90.55 100	42.23 208	91.02 95	72.66 133	85.29 48	89.87 150

FMVSNet3		68.84 253	67.40 255	73.19 276	85.05 78	48.53 289	85.71 145	85.36 133	60.90 227	57.58 328	79.15 334	42.16 209	86.77 289	47.25 365	63.40 311	84.27 297

VPA-MVSNet		71.12 199	70.66 183	72.49 297	78.75 268	44.43 385	87.64 71	90.02 21	63.97 155	65.02 201	81.58 308	42.14 210	87.42 264	63.42 214	63.38 314	85.63 275

jason		77.01 55	76.45 62	78.69 69	79.69 240	54.74 99	90.56 24	83.99 199	68.26 66	74.10 72	90.91 93	42.14 210	89.99 136	79.30 59	79.12 109	91.36 80
jason: jason.
CLD-MVS		75.60 100	75.39 86	76.24 164	80.69 210	52.40 170	90.69 23	86.20 109	74.40 6	65.01 202	88.93 138	42.05 212	90.58 116	76.57 86	73.96 192	85.73 271
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 90	74.83 101	78.91 60	88.08 40	51.94 184	91.30 17	89.28 30	57.91 284	71.19 120	89.20 134	42.03 213	92.77 45	69.41 157	75.07 180	92.01 49

DCV-MVSNet		75.85 90	74.83 101	78.91 60	88.08 40	51.94 184	91.30 17	89.28 30	57.91 284	71.19 120	89.20 134	42.03 213	92.77 45	69.41 157	75.07 180	92.01 49

TAMVS		69.51 241	68.16 234	73.56 266	76.30 325	48.71 285	82.57 271	77.17 357	62.10 199	61.32 264	84.23 250	41.90 215	83.46 363	54.80 307	73.09 207	88.50 201

TransMVSNet (Re)		62.82 350	60.76 352	69.02 363	73.98 370	41.61 420	86.36 114	79.30 311	56.90 307	52.53 382	76.44 369	41.85 216	87.60 257	38.83 404	40.61 460	77.86 405

VPNet		72.07 178	71.42 169	74.04 247	78.64 274	47.17 339	89.91 31	87.97 67	72.56 12	64.66 209	85.04 238	41.83 217	88.33 218	61.17 235	60.97 335	86.62 252

v2v482		69.55 240	67.64 248	75.26 211	72.32 390	53.83 125	84.93 186	81.94 240	65.37 128	60.80 269	79.25 332	41.62 218	88.98 184	63.03 217	59.51 348	82.98 336

API-MVS		74.17 130	72.07 158	80.49 26	90.02 12	58.55 10	87.30 86	84.27 187	57.51 295	65.77 190	87.77 185	41.61 219	95.97 12	51.71 334	82.63 68	86.94 240

GeoE		69.96 229	67.88 241	76.22 165	81.11 196	51.71 196	84.15 214	76.74 366	59.83 241	60.91 267	84.38 247	41.56 220	88.10 228	51.67 335	70.57 239	88.84 184

CHOSEN 1792x2688		76.24 77	74.03 117	82.88 2	83.09 125	62.84 2	85.73 143	85.39 132	69.79 49	64.87 207	83.49 265	41.52 221	93.69 35	70.55 148	81.82 76	92.12 43

LFMVS		78.52 27	77.14 47	82.67 4	89.58 14	58.90 8	91.27 19	88.05 66	63.22 175	74.63 66	90.83 96	41.38 222	94.40 22	75.42 98	79.90 100	94.72 2

MAR-MVS		76.76 63	75.60 79	80.21 33	90.87 8	54.68 105	89.14 46	89.11 33	62.95 180	70.54 140	92.33 56	41.05 223	94.95 18	57.90 274	86.55 33	91.00 103
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		43.51 444	44.07 445	41.82 471	63.75 462	21.90 495	63.80 449	72.05 415	39.59 450	33.35 482	54.54 481	41.04 224	57.30 484	10.75 501	17.77 500	46.26 493

test_fmvsmvis_n_1920		71.29 195	70.38 191	74.00 249	71.04 406	48.79 281	79.19 354	64.62 455	62.75 187	66.73 173	91.99 65	40.94 225	88.35 216	83.00 30	73.18 204	84.85 289

GST-MVS		74.87 117	73.90 120	77.77 112	83.30 118	53.45 135	85.75 139	85.29 139	59.22 257	66.50 180	89.85 122	40.94 225	90.76 107	70.94 147	83.35 63	89.10 178

usedtu_dtu_shiyan1		69.05 247	67.91 237	72.46 299	75.40 345	46.24 361	85.74 141	86.80 92	65.23 132	58.75 305	80.31 317	40.90 227	86.83 285	53.29 315	64.77 295	84.31 295

FE-MVSNET3		69.05 247	67.91 237	72.46 299	75.39 346	46.24 361	85.74 141	86.80 92	65.23 132	58.75 305	80.31 317	40.90 227	86.83 285	53.29 315	64.77 295	84.31 295

DU-MVS		66.84 305	65.74 293	70.16 350	73.27 377	42.59 409	81.50 310	82.92 224	63.53 168	58.51 310	82.11 297	40.75 229	84.64 348	53.11 318	55.96 388	83.24 328

Baseline_NR-MVSNet		65.49 325	64.27 318	69.13 362	74.37 364	41.65 419	83.39 244	78.85 317	59.56 247	59.62 283	76.88 364	40.75 229	87.44 263	49.99 343	55.05 395	78.28 400

miper_lstm_enhance		63.91 337	62.30 331	68.75 369	75.06 353	46.78 344	69.02 430	81.14 258	59.68 246	52.76 381	72.39 412	40.71 231	77.99 418	56.81 285	53.09 412	81.48 357

HFP-MVS		74.37 125	73.13 135	78.10 103	84.30 95	53.68 129	85.58 150	84.36 185	56.82 312	65.78 189	90.56 99	40.70 232	90.90 103	69.18 161	80.88 82	89.71 152

RRT-MVS		73.29 150	71.37 170	79.07 58	84.63 85	54.16 122	78.16 362	86.64 100	61.67 208	60.17 275	82.35 293	40.63 233	92.26 61	70.19 152	77.87 125	90.81 110

CL-MVSNet_self_test		62.98 348	61.14 349	68.50 375	65.86 448	42.96 404	84.37 205	82.98 222	60.98 223	53.95 373	72.70 408	40.43 234	83.71 359	41.10 397	47.93 434	78.83 390

ACMMP_NAP		76.43 71	75.66 78	78.73 67	81.92 163	54.67 106	84.06 218	85.35 134	61.10 220	72.99 86	91.50 79	40.25 235	91.00 97	76.84 85	86.98 26	90.51 123

v1144		68.81 255	66.82 266	74.80 224	72.34 389	53.46 133	84.68 196	81.77 247	64.25 146	60.28 274	77.91 344	40.23 236	88.95 186	60.37 246	59.52 347	81.97 346

WR-MVS_H		58.91 381	58.04 373	61.54 431	69.07 431	33.83 457	76.91 369	81.99 239	51.40 380	48.17 414	74.67 385	40.23 236	74.15 444	31.78 441	48.10 432	76.64 420

原ACMM1				76.13 170	84.89 82	54.59 109		85.26 141	51.98 374	66.70 174	87.07 203	40.15 238	89.70 152	51.23 338	85.06 53	84.10 300

MVP-Stereo		70.97 204	70.44 187	72.59 294	76.03 333	51.36 204	85.02 181	86.99 89	60.31 235	56.53 347	78.92 336	40.11 239	90.00 135	60.00 249	90.01 7	76.41 423
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v10		66.61 308	64.20 319	73.83 256	72.59 386	53.37 139	81.88 291	79.91 289	61.11 219	54.09 372	75.60 380	40.06 240	88.26 224	56.47 290	56.10 386	79.86 383

test_fmvsmconf0.01_n		71.97 181	70.95 179	75.04 215	66.21 445	47.87 320	80.35 333	70.08 433	65.85 119	72.69 91	91.68 74	39.99 241	87.67 252	82.03 39	69.66 250	89.58 157

MP-MVS-pluss		75.54 102	75.03 95	77.04 136	81.37 189	52.65 166	84.34 208	84.46 183	61.16 217	69.14 154	91.76 70	39.98 242	88.99 183	78.19 71	84.89 54	89.48 165
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TranMVSNet+NR-MVSNet		66.94 303	65.61 296	70.93 339	73.45 373	43.38 399	83.02 259	84.25 188	65.31 130	58.33 317	81.90 301	39.92 243	85.52 330	49.43 348	54.89 397	83.89 311

Patchmatch-test		53.33 418	48.17 431	68.81 367	73.31 374	42.38 413	42.98 488	58.23 469	32.53 473	38.79 464	70.77 429	39.66 244	73.51 450	25.18 467	52.06 416	90.55 120

viewdifsd2359ckpt11		70.68 210	69.10 219	75.40 198	75.33 348	50.85 215	81.57 306	78.00 340	66.99 94	64.96 204	85.52 228	39.52 245	86.81 287	68.86 164	61.15 334	88.56 196

viewmsd2359difaftdt		70.68 210	69.10 219	75.40 198	75.33 348	50.85 215	81.57 306	78.00 340	66.99 94	64.96 204	85.52 228	39.52 245	86.81 287	68.86 164	61.16 333	88.56 196

Test By Simon												39.38 247

v144192		67.86 274	65.76 292	74.16 243	71.68 396	53.09 151	84.14 215	80.83 266	62.85 186	59.21 293	77.28 355	39.30 248	88.00 232	58.67 259	57.88 371	81.40 360

BH-w/o		70.02 226	68.51 227	74.56 229	82.77 140	50.39 231	86.60 112	78.14 338	59.77 243	59.65 281	85.57 226	39.27 249	87.30 269	49.86 345	74.94 183	85.99 265

dmvs_testset		57.65 392	58.21 372	55.97 452	74.62 359	9.82 513	63.75 450	63.34 461	67.23 86	48.89 412	83.68 264	39.12 250	76.14 436	23.43 473	59.80 346	81.96 347

CR-MVSNet		62.47 356	59.04 368	72.77 287	73.97 371	56.57 36	60.52 463	71.72 419	60.04 238	57.49 331	65.86 449	38.94 251	80.31 394	42.86 391	59.93 343	81.42 358

Patchmtry		56.56 398	52.95 405	67.42 382	72.53 387	50.59 224	59.05 467	71.72 419	37.86 458	46.92 426	65.86 449	38.94 251	80.06 398	36.94 413	46.72 444	71.60 459

sam_mvs1												38.86 253				88.13 210

UA-Net		67.32 292	66.23 280	70.59 343	78.85 266	41.23 425	73.60 397	75.45 380	61.54 211	66.61 177	84.53 246	38.73 254	86.57 299	42.48 394	74.24 188	83.98 306

cdsmvs_eth3d_5k		18.33 473	24.44 465	0.00 535	0.00 558	0.00 560	0.00 546	89.40 28	0.00 551	0.00 555	92.02 63	38.55 255	0.00 553	0.00 553	0.00 551	0.00 550

patchmatchnet-post											59.74 472	38.41 256	79.91 401

CHOSEN 280x420		57.53 394	56.38 386	60.97 436	74.01 369	48.10 309	46.30 483	54.31 476	48.18 405	50.88 402	77.43 353	38.37 257	59.16 482	54.83 305	63.14 319	75.66 427

lecture		74.14 131	73.05 136	77.44 123	81.66 174	50.39 231	87.43 80	84.22 192	51.38 381	72.10 101	90.95 92	38.31 258	93.23 38	70.51 149	80.83 84	88.69 188

SD_0403		65.51 324	65.18 307	66.48 394	78.37 280	29.94 476	74.64 389	78.55 329	66.47 103	54.87 361	84.35 249	38.20 259	82.47 370	38.90 403	72.30 219	87.05 238

V42		67.66 279	65.60 297	73.86 254	70.69 412	53.63 130	81.50 310	78.61 327	63.85 158	59.49 287	77.49 350	37.98 260	87.65 253	62.33 223	58.43 358	80.29 378

tpmvs		62.45 357	59.42 364	71.53 329	83.93 103	54.32 114	70.03 426	77.61 349	51.91 375	53.48 378	68.29 440	37.91 261	86.66 294	33.36 434	58.27 361	73.62 445

PatchmatchNet		67.07 300	63.63 322	77.40 124	83.10 123	58.03 12	72.11 417	77.77 346	58.85 268	59.37 288	70.83 428	37.84 262	84.93 343	42.96 390	69.83 249	89.26 170
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pcd_1.5k_mvsjas		3.15 490	4.20 492	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	0.00 553	37.77 263	0.00 553	0.00 553	0.00 551	0.00 550

PS-MVSNAJss		68.78 257	67.17 261	73.62 264	73.01 380	48.33 299	84.95 185	84.81 167	59.30 256	58.91 300	79.84 324	37.77 263	88.86 191	62.83 220	63.12 320	83.67 320

PS-MVSNAJ		80.06 17	79.52 18	81.68 15	85.58 68	60.97 3	91.69 12	87.02 88	70.62 34	80.75 27	93.22 33	37.77 263	92.50 53	82.75 33	86.25 36	91.57 69

pm-mvs1		64.12 335	62.56 329	68.78 368	71.68 396	38.87 436	82.89 263	81.57 250	55.54 339	53.89 374	77.82 346	37.73 266	86.74 290	48.46 358	53.49 409	80.72 372

RPMNet		59.29 373	54.25 398	74.42 233	73.97 371	56.57 36	60.52 463	76.98 360	35.72 467	57.49 331	58.87 475	37.73 266	85.26 336	27.01 463	59.93 343	81.42 358

IMVS_0403		72.39 168	70.59 185	77.79 111	82.26 152	50.87 211	81.76 295	85.16 147	62.91 182	64.87 207	86.07 216	37.71 268	92.40 56	64.03 206	70.55 240	90.09 139

SDMVSNet		71.89 183	70.62 184	75.70 185	81.70 170	51.61 197	73.89 394	88.72 46	66.58 99	61.64 261	82.38 290	37.63 269	89.48 161	77.44 79	65.60 290	86.01 263

xiu_mvs_v2_base		79.86 18	79.31 20	81.53 16	85.03 80	60.73 4	91.65 13	86.86 91	70.30 39	80.77 26	93.07 38	37.63 269	92.28 60	82.73 34	85.71 42	91.57 69

Patchmatch-RL test		58.72 384	54.32 397	71.92 320	63.91 461	44.25 388	61.73 459	55.19 474	57.38 299	49.31 410	54.24 482	37.60 271	80.89 382	62.19 226	47.28 439	90.63 117

HPM-MVS		72.60 164	71.50 166	75.89 178	82.02 159	51.42 203	80.70 327	83.05 220	56.12 332	64.03 223	89.53 127	37.55 272	88.37 214	70.48 151	80.04 97	87.88 215
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test_post											16.22 515	37.52 273	84.72 346

PatchT		56.60 397	52.97 404	67.48 381	72.94 382	46.16 364	57.30 471	73.78 398	38.77 453	54.37 368	57.26 478	37.52 273	78.06 415	32.02 439	52.79 413	78.23 402

v1192		67.96 273	65.74 293	74.63 228	71.79 394	53.43 138	84.06 218	80.99 264	63.19 176	59.56 284	77.46 351	37.50 275	88.65 198	58.20 267	58.93 354	81.79 349

HQP2-MVS												37.35 276

HQP-MVS		72.34 171	71.44 168	75.03 216	79.02 261	51.56 199	88.00 61	83.68 204	65.45 123	64.48 215	85.13 233	37.35 276	88.62 199	66.70 178	73.12 205	84.91 287

region2R		73.75 141	72.55 143	77.33 125	83.90 105	52.98 155	85.54 154	84.09 194	56.83 311	65.10 199	90.45 103	37.34 278	90.24 129	68.89 163	80.83 84	88.77 187

TESTMET0.1,1		72.86 158	72.33 148	74.46 231	81.98 160	50.77 218	85.13 171	85.47 128	66.09 113	67.30 170	83.69 262	37.27 279	83.57 361	65.06 200	78.97 113	89.05 179

mvsmamba		69.38 242	67.52 253	74.95 220	82.86 137	52.22 178	67.36 438	76.75 364	61.14 218	49.43 408	82.04 299	37.26 280	84.14 352	73.93 116	76.91 139	88.50 201

ACMMPR		73.76 140	72.61 141	77.24 132	83.92 104	52.96 156	85.58 150	84.29 186	56.82 312	65.12 198	90.45 103	37.24 281	90.18 131	69.18 161	80.84 83	88.58 194

MonoMVSNet		66.80 306	64.41 315	73.96 250	76.21 328	48.07 310	76.56 374	78.26 336	64.34 143	54.32 369	74.02 391	37.21 282	86.36 305	64.85 201	53.96 404	87.45 227

sss		70.49 216	70.13 199	71.58 328	81.59 180	39.02 434	80.78 325	84.71 177	59.34 253	66.61 177	88.09 172	37.17 283	85.52 330	61.82 230	71.02 234	90.20 134

reproduce-ours		71.77 188	70.43 188	75.78 181	81.96 161	49.54 258	82.54 274	81.01 262	48.77 400	69.21 152	90.96 89	37.13 284	89.40 164	66.28 183	76.01 158	88.39 204

our_new_method		71.77 188	70.43 188	75.78 181	81.96 161	49.54 258	82.54 274	81.01 262	48.77 400	69.21 152	90.96 89	37.13 284	89.40 164	66.28 183	76.01 158	88.39 204

EPNet_dtu		66.25 315	66.71 269	64.87 407	78.66 273	34.12 455	82.80 265	75.51 378	61.75 206	64.47 218	86.90 204	37.06 286	72.46 456	43.65 386	69.63 252	88.02 213
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v1921920		67.45 285	65.23 306	74.10 246	71.51 399	52.90 157	83.75 229	80.44 274	62.48 195	59.12 294	77.13 356	36.98 287	87.90 235	57.53 279	58.14 365	81.49 355

旧先验1					81.57 182	47.48 331		71.83 417			88.66 144	36.94 288			78.34 120	88.67 189

test-LLR		69.65 238	69.01 221	71.60 326	78.67 270	48.17 305	85.13 171	79.72 293	59.18 260	63.13 241	82.58 284	36.91 289	80.24 395	60.56 241	75.17 176	86.39 259

test0.0.03 1		62.54 353	62.44 330	62.86 423	72.28 392	29.51 479	82.93 261	78.78 320	59.18 260	53.07 380	82.41 288	36.91 289	77.39 425	37.45 407	58.96 353	81.66 353

MDTV_nov1_ep13_2view						43.62 395	71.13 422		54.95 349	59.29 292		36.76 291		46.33 372		87.32 230

KD-MVS_2432*1600		59.04 379	56.44 383	66.86 388	79.07 258	45.87 368	72.13 415	80.42 275	55.03 347	48.15 415	71.01 426	36.73 292	78.05 416	35.21 424	30.18 485	76.67 417

miper_refine_blended		59.04 379	56.44 383	66.86 388	79.07 258	45.87 368	72.13 415	80.42 275	55.03 347	48.15 415	71.01 426	36.73 292	78.05 416	35.21 424	30.18 485	76.67 417

GBi-Net		67.09 298	65.47 299	71.96 315	82.71 142	46.36 354	83.52 232	83.31 212	58.55 274	57.58 328	76.23 373	36.72 294	86.20 307	47.25 365	63.40 311	83.32 325

test1		67.09 298	65.47 299	71.96 315	82.71 142	46.36 354	83.52 232	83.31 212	58.55 274	57.58 328	76.23 373	36.72 294	86.20 307	47.25 365	63.40 311	83.32 325

FMVSNet2		67.57 282	65.79 291	72.90 281	82.71 142	47.97 314	85.15 170	84.93 163	58.55 274	56.71 344	78.26 342	36.72 294	86.67 293	46.15 373	62.94 322	84.07 301

AUN-MVS		68.20 270	66.35 276	73.76 258	76.37 321	47.45 333	79.52 350	79.52 300	60.98 223	62.34 249	86.02 220	36.59 297	86.94 281	62.32 224	53.47 410	86.89 241

reproduce_model		71.07 201	69.67 207	75.28 209	81.51 186	48.82 280	81.73 298	80.57 272	47.81 406	68.26 162	90.78 97	36.49 298	88.60 201	65.12 199	74.76 185	88.42 203

BH-untuned		68.28 267	66.40 275	73.91 252	81.62 177	50.01 244	85.56 152	77.39 353	57.63 292	57.47 333	83.69 262	36.36 299	87.08 276	44.81 378	73.08 208	84.65 290

fmvsm_s_conf0.5_n_2		72.02 179	71.72 163	72.92 280	76.79 317	45.90 366	84.48 203	66.11 449	64.26 145	76.12 58	93.40 26	36.26 300	86.04 317	81.47 45	66.54 279	86.82 249

EPMVS		68.45 263	65.44 301	77.47 121	84.91 81	56.17 45	71.89 419	81.91 243	61.72 207	60.85 268	72.49 409	36.21 301	87.06 277	47.32 364	71.62 225	89.17 175

wanda-best-256-512		64.87 326	62.23 332	72.81 284	70.49 414	46.85 342	85.71 145	85.71 120	56.85 308	51.25 393	72.31 415	36.16 302	87.84 237	52.67 328	48.90 424	83.73 313

FE-blended-shiyan7		64.87 326	62.23 332	72.81 284	70.49 414	46.85 342	85.71 145	85.71 120	56.85 308	51.25 393	72.31 415	36.16 302	87.84 237	52.67 328	48.90 424	83.73 313

usedtu_blend_shiyan5		63.62 341	60.36 357	73.40 270	70.49 414	47.96 316	79.13 355	80.68 268	47.51 410	51.25 393	72.31 415	36.16 302	88.50 209	56.81 285	48.90 424	83.73 313

MSLP-MVS++		74.21 129	72.25 152	80.11 40	81.45 187	56.47 40	86.32 116	79.65 298	58.19 278	66.36 181	92.29 57	36.11 305	90.66 112	67.39 174	82.49 70	93.18 18

FA-MVS(test-final)		69.00 251	66.60 273	76.19 168	83.48 112	47.96 316	74.73 386	82.07 238	57.27 301	62.18 252	78.47 340	36.09 306	92.89 41	53.76 314	71.32 232	87.73 219

MTAPA		72.73 162	71.22 172	77.27 129	81.54 183	53.57 131	67.06 440	81.31 255	59.41 251	68.39 161	90.96 89	36.07 307	89.01 180	73.80 120	82.45 71	89.23 172

HQP_MVS		70.96 205	69.91 204	74.12 245	77.95 287	49.57 252	85.76 137	82.59 227	63.60 166	62.15 254	83.28 270	36.04 308	88.30 221	65.46 192	72.34 217	84.49 291

plane_prior6					78.42 279	49.39 265						36.04 308

sam_mvs												35.99 310

blended_shiyan6		64.70 328	62.04 336	72.69 289	70.34 417	46.60 350	85.48 156	85.65 124	56.59 320	50.91 401	72.18 419	35.82 311	87.81 240	52.46 332	48.90 424	83.66 321

blended_shiyan8		64.70 328	62.04 336	72.69 289	70.33 418	46.62 348	85.48 156	85.66 122	56.58 321	50.94 400	72.18 419	35.81 312	87.80 243	52.47 331	48.91 423	83.65 322

PGM-MVS		72.60 164	71.20 173	76.80 149	82.95 132	52.82 161	83.07 257	82.14 233	56.51 323	63.18 240	89.81 123	35.68 313	89.76 146	67.30 175	80.19 94	87.83 216

icg_test_0407_2		71.26 196	69.99 202	75.09 214	82.26 152	50.87 211	79.65 346	85.16 147	62.91 182	63.68 233	86.07 216	35.56 314	84.32 351	64.03 206	70.55 240	90.09 139

IMVS_0407		71.97 181	70.10 200	77.57 117	82.26 152	50.87 211	80.69 328	85.16 147	62.91 182	63.68 233	86.07 216	35.56 314	91.75 72	64.03 206	70.55 240	90.09 139

XVS		72.92 156	71.62 164	76.81 147	83.41 113	52.48 167	84.88 187	83.20 217	58.03 280	63.91 225	89.63 126	35.50 316	89.78 144	65.50 189	80.50 89	88.16 207

X-MVStestdata		65.85 320	62.20 334	76.81 147	83.41 113	52.48 167	84.88 187	83.20 217	58.03 280	63.91 225	4.82 525	35.50 316	89.78 144	65.50 189	80.50 89	88.16 207

v1240		66.99 301	64.68 312	73.93 251	71.38 403	52.66 165	83.39 244	79.98 284	61.97 203	58.44 316	77.11 357	35.25 318	87.81 240	56.46 291	58.15 363	81.33 363

test1111		71.06 202	70.42 190	72.97 279	79.48 246	41.49 422	84.82 191	82.74 226	64.20 148	62.98 243	87.43 196	35.20 319	87.92 233	58.54 260	78.42 119	89.49 164

dp		64.41 331	61.58 341	72.90 281	82.40 149	54.09 123	72.53 407	76.59 370	60.39 234	55.68 354	70.39 432	35.18 320	76.90 431	39.34 402	61.71 330	87.73 219

Syy-MVS		61.51 362	61.35 346	62.00 427	81.73 168	30.09 473	80.97 320	81.02 260	60.93 225	55.06 358	82.64 282	35.09 321	80.81 385	16.40 492	58.32 359	75.10 434

ECVR-MVS		71.81 185	71.00 178	74.26 241	80.12 230	43.49 396	84.69 195	82.16 232	64.02 151	64.64 210	87.43 196	35.04 322	89.21 173	61.24 234	79.66 103	90.08 143

CP-MVS		72.59 166	71.46 167	76.00 175	82.93 134	52.32 173	86.93 99	82.48 230	55.15 345	63.65 235	90.44 106	35.03 323	88.53 208	68.69 166	77.83 127	87.15 236

fmvsm_s_conf0.1_n_2		71.45 193	71.01 177	72.78 286	75.37 347	45.82 370	84.18 213	64.59 457	64.02 151	75.67 59	93.02 39	34.99 324	85.99 320	81.18 49	66.04 288	86.52 255

CP-MVSNet		58.54 388	57.57 376	61.46 432	68.50 435	33.96 456	76.90 370	78.60 328	51.67 379	47.83 418	76.60 368	34.99 324	72.79 454	35.45 421	47.58 436	77.64 410

guyue		70.53 215	69.12 217	74.76 225	77.61 292	47.53 329	84.86 189	85.17 145	62.70 189	62.18 252	83.74 259	34.72 326	89.86 140	64.69 202	66.38 281	86.87 242

dmvs_re		67.61 280	66.00 285	72.42 301	81.86 165	43.45 397	64.67 447	80.00 283	69.56 54	60.07 276	85.00 239	34.71 327	87.63 254	51.48 336	66.68 274	86.17 262

MDTV_nov1_ep13			61.56 342		81.68 172	55.12 73	72.41 410	78.18 337	59.19 258	58.85 302	69.29 437	34.69 328	86.16 310	36.76 416	62.96 321

SSC-MVS3.2		68.13 271	66.89 263	71.85 323	82.26 152	43.97 391	82.09 286	89.29 29	71.74 17	61.12 266	79.83 325	34.60 329	87.45 262	41.23 396	59.85 345	84.14 298

WB-MVSnew		69.36 243	68.24 232	72.72 288	79.26 252	49.40 264	85.72 144	88.85 41	61.33 214	64.59 213	82.38 290	34.57 330	87.53 260	46.82 369	70.63 237	81.22 367

3Dnovator	64.70 6	74.46 122	72.48 144	80.41 30	82.84 139	55.40 61	83.08 256	88.61 52	67.61 83	59.85 278	88.66 144	34.57 330	93.97 28	58.42 263	88.70 12	91.85 57

VortexMVS		68.49 262	66.84 265	73.46 268	81.10 197	48.75 282	84.63 199	84.73 172	62.05 200	57.22 338	77.08 359	34.54 332	89.20 174	63.08 215	57.12 377	82.43 342

Vis-MVSNet		70.61 214	69.34 212	74.42 233	80.95 203	48.49 291	86.03 126	77.51 351	58.74 271	65.55 194	87.78 184	34.37 333	85.95 324	52.53 330	80.61 87	88.80 185
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_post1							70.84 423				14.72 518	34.33 334	83.86 355	48.80 353

OPM-MVS		70.75 209	69.58 208	74.26 241	75.55 343	51.34 205	86.05 125	83.29 215	61.94 204	62.95 244	85.77 223	34.15 335	88.44 212	65.44 195	71.07 233	82.99 334
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DP-MVS Recon		71.99 180	70.31 193	77.01 138	90.65 9	53.44 136	89.37 39	82.97 223	56.33 326	63.56 238	89.47 128	34.02 336	92.15 65	54.05 311	72.41 215	85.43 278

PEN-MVS		58.35 389	57.15 378	61.94 428	67.55 442	34.39 451	77.01 368	78.35 335	51.87 376	47.72 419	76.73 366	33.91 337	73.75 448	34.03 431	47.17 440	77.68 408

QAPM		71.88 184	69.33 213	79.52 45	82.20 158	54.30 115	86.30 117	88.77 44	56.61 319	59.72 280	87.48 194	33.90 338	95.36 14	47.48 363	81.49 79	88.90 181

新几何1				73.30 273	83.10 123	53.48 132		71.43 423	45.55 426	66.14 182	87.17 201	33.88 339	80.54 391	48.50 356	80.33 93	85.88 270

1314		71.11 200	69.41 210	76.22 165	79.32 250	50.49 226	80.23 336	85.14 153	59.44 250	58.93 298	88.89 140	33.83 340	89.60 155	61.49 232	77.42 132	88.57 195

SR-MVS		70.92 206	69.73 206	74.50 230	83.38 117	50.48 228	84.27 210	79.35 308	48.96 398	66.57 179	90.45 103	33.65 341	87.11 275	66.42 180	74.56 187	85.91 268

mPP-MVS		71.79 187	70.38 191	76.04 173	82.65 145	52.06 179	84.45 204	81.78 246	55.59 337	62.05 257	89.68 125	33.48 342	88.28 223	65.45 194	78.24 121	87.77 218

OMC-MVS		65.97 319	65.06 309	68.71 370	72.97 381	42.58 411	78.61 359	75.35 381	54.72 351	59.31 290	86.25 215	33.30 343	77.88 420	57.99 269	67.05 272	85.66 273

BH-RMVSNet		70.08 224	68.01 235	76.27 162	84.21 99	51.22 209	87.29 87	79.33 310	58.96 267	63.63 236	86.77 206	33.29 344	90.30 128	44.63 380	73.96 192	87.30 231

gbinet_0.2-2-1-0.02		64.20 333	61.39 344	72.63 292	70.85 408	46.32 358	85.92 128	85.98 114	55.27 344	51.88 390	72.29 418	33.14 345	87.82 239	48.50 356	48.72 428	83.73 313

SSM_0407		69.71 233	67.38 256	76.69 154	80.45 220	51.81 192	81.36 314	80.18 279	54.07 358	63.82 229	85.05 236	33.09 346	91.01 96	59.40 250	68.97 256	87.25 232

SSM_0404		70.13 220	67.87 244	76.88 145	80.22 227	52.00 181	81.71 300	80.18 279	54.07 358	65.36 196	85.05 236	33.09 346	91.03 93	59.40 250	71.80 223	87.63 222

JIA-IIPM		52.33 424	47.77 434	66.03 396	71.20 404	46.92 340	40.00 493	76.48 371	37.10 460	46.73 427	37.02 495	32.96 348	77.88 420	35.97 418	52.45 415	73.29 449

PS-CasMVS		58.12 390	57.03 380	61.37 433	68.24 439	33.80 458	76.73 372	78.01 339	51.20 382	47.54 422	76.20 376	32.85 349	72.76 455	35.17 426	47.37 438	77.55 411

DTE-MVSNet		57.03 395	55.73 390	60.95 437	65.94 447	32.57 463	75.71 375	77.09 359	51.16 383	46.65 429	76.34 371	32.84 350	73.22 453	30.94 445	44.87 449	77.06 413

pmmvs4		63.34 345	61.07 350	70.16 350	70.14 420	50.53 225	79.97 343	71.41 424	55.08 346	54.12 371	78.58 338	32.79 351	82.09 375	50.33 342	57.22 376	77.86 405

TR-MVS		69.71 233	67.85 245	75.27 210	82.94 133	48.48 292	87.40 83	80.86 265	57.15 305	64.61 212	87.08 202	32.67 352	89.64 154	46.38 371	71.55 227	87.68 221

VDD-MVS		76.08 82	74.97 97	79.44 46	84.27 98	53.33 142	91.13 20	85.88 116	65.33 129	72.37 97	89.34 131	32.52 353	92.76 47	77.90 77	75.96 160	92.22 41

3Dnovator+	62.71 7	72.29 174	70.50 186	77.65 116	83.40 116	51.29 207	87.32 84	86.40 105	59.01 265	58.49 313	88.32 161	32.40 354	91.27 84	57.04 283	82.15 74	90.38 126

tfpnnormal		61.47 363	59.09 367	68.62 372	76.29 326	41.69 418	81.14 317	85.16 147	54.48 354	51.32 392	73.63 398	32.32 355	86.89 284	21.78 479	55.71 392	77.29 412

MS-PatchMatch		72.34 171	71.26 171	75.61 187	82.38 150	55.55 54	88.00 61	89.95 23	65.38 127	56.51 348	80.74 315	32.28 356	92.89 41	57.95 272	88.10 16	78.39 398

KinetiMVS		71.15 197	69.25 216	76.82 146	77.99 286	50.49 226	85.05 177	86.51 101	59.78 242	64.10 221	85.34 231	32.16 357	91.33 83	58.82 257	73.54 200	88.64 190

v7n		62.50 355	59.27 366	72.20 307	67.25 443	49.83 249	77.87 365	80.12 281	52.50 371	48.80 413	73.07 402	32.10 358	87.90 235	46.83 368	54.92 396	78.86 389

IterMVS		63.77 340	61.67 340	70.08 352	72.68 385	51.24 208	80.44 331	75.51 378	60.51 233	51.41 391	73.70 397	32.08 359	78.91 406	54.30 309	54.35 402	80.08 381
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		59.12 376	58.81 370	60.08 438	70.68 413	45.07 377	80.42 332	74.25 390	43.54 441	50.02 406	73.73 394	31.97 360	56.74 486	51.06 340	53.60 408	78.42 397

SCA		63.84 338	60.01 361	75.32 203	78.58 275	57.92 13	61.61 460	77.53 350	56.71 315	57.75 325	70.77 429	31.97 360	79.91 401	48.80 353	56.36 380	88.13 210

ACMMP		70.81 208	69.29 214	75.39 201	81.52 185	51.92 186	83.43 240	83.03 221	56.67 317	58.80 303	88.91 139	31.92 362	88.58 202	65.89 188	73.39 202	85.67 272
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		66.33 313	62.87 324	76.70 153	80.45 220	51.81 192	46.11 484	78.90 315	55.46 340	63.82 229	84.54 243	31.91 363	91.03 93	55.68 299	68.97 256	87.25 232

SSM_04072		64.04 336	62.87 324	67.56 380	80.45 220	51.81 192	46.11 484	78.90 315	55.46 340	63.82 229	84.54 243	31.91 363	63.62 471	55.68 299	68.97 256	87.25 232

APD-MVS_3200maxsize		69.62 239	68.23 233	73.80 257	81.58 181	48.22 303	81.91 290	79.50 301	48.21 404	64.24 220	89.75 124	31.91 363	87.55 259	63.08 215	73.85 197	85.64 274

VDDNet		74.37 125	72.13 156	81.09 21	79.58 242	56.52 39	90.02 26	86.70 97	52.61 370	71.23 119	87.20 200	31.75 366	93.96 29	74.30 112	75.77 167	92.79 28

pmmvs5		62.80 351	61.18 348	67.66 379	69.53 427	42.37 414	82.65 268	75.19 382	54.30 357	52.03 388	78.51 339	31.64 367	80.67 387	48.60 355	58.15 363	79.95 382

LCM-MVSNet-Re		58.82 382	56.54 381	65.68 399	79.31 251	29.09 482	61.39 462	45.79 483	60.73 230	37.65 467	72.47 410	31.42 368	81.08 381	49.66 346	70.41 244	86.87 242

AstraMVS		70.12 221	68.56 224	74.81 223	76.48 320	47.48 331	84.35 207	82.58 229	63.80 159	62.09 256	84.54 243	31.39 369	89.96 137	68.24 171	63.58 309	87.00 239

testdata				67.08 386	77.59 294	45.46 374		69.20 439	44.47 434	71.50 116	88.34 159	31.21 370	70.76 462	52.20 333	75.88 161	85.03 283

SR-MVS-dyc-post		68.27 268	66.87 264	72.48 298	80.96 200	48.14 307	81.54 308	76.98 360	46.42 418	62.75 246	89.42 129	31.17 371	86.09 315	60.52 243	72.06 221	83.19 330

GA-MVS		69.04 249	66.70 270	76.06 172	75.11 351	52.36 171	83.12 255	80.23 278	63.32 173	60.65 271	79.22 333	30.98 372	88.37 214	61.25 233	66.41 280	87.46 226

OpenMVS	61.00 11	69.99 228	67.55 251	77.30 127	78.37 280	54.07 124	84.36 206	85.76 119	57.22 303	56.71 344	87.67 191	30.79 373	92.83 43	43.04 389	84.06 61	85.01 284

Effi-MVS+-dtu		66.24 316	64.96 311	70.08 352	75.17 350	49.64 251	82.01 287	74.48 389	62.15 198	57.83 321	76.08 377	30.59 374	83.79 357	65.40 196	60.93 336	76.81 416

sd_testset		67.79 277	65.95 287	73.32 271	81.70 170	46.33 357	68.99 431	80.30 277	66.58 99	61.64 261	82.38 290	30.45 375	87.63 254	55.86 296	65.60 290	86.01 263

test222					79.36 248	50.97 210	77.99 364	67.84 444	42.54 445	62.84 245	86.53 211	30.26 376			76.91 139	85.23 279

MVS_111021_LR		69.07 246	67.91 237	72.54 295	77.27 306	49.56 255	79.77 344	73.96 396	59.33 255	60.73 270	87.82 183	30.19 377	81.53 377	69.94 154	72.19 220	86.53 254

dtuonly		62.58 352	61.91 339	64.58 409	66.49 444	44.72 381	75.64 376	65.78 451	57.26 302	55.48 357	83.93 255	30.08 378	67.36 468	56.40 294	66.10 287	81.67 352

114514_t		69.87 231	67.88 241	75.85 179	88.38 31	52.35 172	86.94 97	83.68 204	53.70 361	55.68 354	85.60 225	30.07 379	91.20 88	55.84 297	71.02 234	83.99 304

CPTT-MVS		67.15 296	65.84 290	71.07 336	80.96 200	50.32 237	81.94 289	74.10 392	46.18 424	57.91 320	87.64 193	29.57 380	81.31 379	64.10 205	70.18 247	81.56 354

CANet_DTU		73.71 142	73.14 133	75.40 198	82.61 146	50.05 242	84.67 198	79.36 307	69.72 52	75.39 60	90.03 119	29.41 381	85.93 325	67.99 172	79.11 110	90.22 132

AdaColmap		67.86 274	65.48 298	75.00 218	88.15 39	54.99 80	86.10 123	76.63 369	49.30 395	57.80 322	86.65 210	29.39 382	88.94 188	45.10 377	70.21 246	81.06 368

RE-MVS-def			66.66 271		80.96 200	48.14 307	81.54 308	76.98 360	46.42 418	62.75 246	89.42 129	29.28 383		60.52 243	72.06 221	83.19 330

CVMVSNet		60.85 366	60.44 355	62.07 425	75.00 354	32.73 462	79.54 348	73.49 403	36.98 461	56.28 350	83.74 259	29.28 383	69.53 465	46.48 370	63.23 316	83.94 309

PMMVS		72.98 155	72.05 159	75.78 181	83.57 109	48.60 286	84.08 216	82.85 225	61.62 209	68.24 163	90.33 108	28.35 385	87.78 247	72.71 131	76.69 146	90.95 106

our_test_3		59.11 377	55.08 394	71.18 335	71.42 401	53.29 144	81.96 288	74.52 388	48.32 402	42.08 447	69.28 438	28.14 386	82.15 373	34.35 430	45.68 448	78.11 403

Fast-Effi-MVS+-dtu		66.53 310	64.10 320	73.84 255	72.41 388	52.30 176	84.73 193	75.66 376	59.51 248	56.34 349	79.11 335	28.11 387	85.85 326	57.74 278	63.29 315	83.35 324

Anonymous20231211		66.08 318	63.67 321	73.31 272	83.07 126	48.75 282	86.01 127	84.67 179	45.27 428	56.54 346	76.67 367	28.06 388	88.95 186	52.78 324	59.95 342	82.23 344

Anonymous20240529		69.71 233	67.28 258	77.00 139	83.78 107	50.36 235	88.87 51	85.10 154	47.22 411	64.03 223	83.37 268	27.93 389	92.10 66	57.78 277	67.44 270	88.53 199

HPM-MVS_fast		67.86 274	66.28 279	72.61 293	80.67 211	48.34 297	81.18 316	75.95 375	50.81 384	59.55 285	88.05 175	27.86 390	85.98 321	58.83 256	73.58 199	83.51 323

FMVSNet1		64.57 330	62.11 335	71.96 315	77.32 304	46.36 354	83.52 232	83.31 212	52.43 372	54.42 367	76.23 373	27.80 391	86.20 307	42.59 393	61.34 332	83.32 325

CNLPA		60.59 367	58.44 371	67.05 387	79.21 254	47.26 337	79.75 345	64.34 459	42.46 446	51.90 389	83.94 254	27.79 392	75.41 441	37.12 409	59.49 349	78.47 395

TAPA-MVS	56.12 14	61.82 361	60.18 360	66.71 390	78.48 278	37.97 442	75.19 384	76.41 372	46.82 414	57.04 339	86.52 212	27.67 393	77.03 428	26.50 465	67.02 273	85.14 282
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
pmmvs6		59.64 371	57.15 378	67.09 385	66.01 446	36.86 446	80.50 329	78.64 325	45.05 430	49.05 411	73.94 392	27.28 394	86.10 313	43.96 385	49.94 421	78.31 399

test-mter		68.36 264	67.29 257	71.60 326	78.67 270	48.17 305	85.13 171	79.72 293	53.38 364	63.13 241	82.58 284	27.23 395	80.24 395	60.56 241	75.17 176	86.39 259

D2MVS		63.49 343	61.39 344	69.77 356	69.29 429	48.93 276	78.89 357	77.71 348	60.64 232	49.70 407	72.10 423	27.08 396	83.48 362	54.48 308	62.65 324	76.90 414

XVG-OURS-SEG-HR		62.02 359	59.54 363	69.46 359	65.30 451	45.88 367	65.06 445	73.57 401	46.45 417	57.42 334	83.35 269	26.95 397	78.09 414	53.77 313	64.03 304	84.42 293

IMVS_0404		69.11 245	67.25 260	74.68 227	82.26 152	50.87 211	76.74 371	85.16 147	62.91 182	50.76 404	86.07 216	26.76 398	83.06 368	64.03 206	70.55 240	90.09 139

test_djsdf		63.84 338	61.56 342	70.70 342	68.78 432	44.69 382	81.63 302	81.44 253	50.28 388	52.27 385	76.26 372	26.72 399	86.11 311	60.83 237	55.84 391	81.29 366

Anonymous20231206		59.08 378	57.59 375	63.55 415	68.77 433	32.14 466	80.26 335	79.78 292	50.00 392	49.39 409	72.39 412	26.64 400	78.36 411	33.12 437	57.94 368	80.14 380

ppachtmachnet_test		58.56 386	54.34 396	71.24 332	71.42 401	54.74 99	81.84 293	72.27 413	49.02 397	45.86 434	68.99 439	26.27 401	83.30 365	30.12 447	43.23 454	75.69 426

test20.03		55.22 406	54.07 399	58.68 444	63.14 466	25.00 488	77.69 366	74.78 385	52.64 369	43.43 441	72.39 412	26.21 402	74.76 443	29.31 450	47.05 442	76.28 424

FE-MVS		64.15 334	60.43 356	75.30 206	80.85 205	49.86 248	68.28 435	78.37 334	50.26 391	59.31 290	73.79 393	26.19 403	91.92 69	40.19 399	66.67 275	84.12 299

FMVSNet5		58.61 385	56.45 382	65.10 406	77.20 310	39.74 430	74.77 385	77.12 358	50.27 390	43.28 443	67.71 442	26.15 404	76.90 431	36.78 415	54.78 398	78.65 393

dtuonlycased		54.12 411	52.39 411	59.30 441	64.31 459	41.80 417	78.63 358	65.85 450	50.56 386	42.00 448	60.21 470	26.14 405	73.31 451	43.06 388	40.73 458	62.79 480

ACMP	61.11 9	66.24 316	64.33 317	72.00 314	74.89 356	49.12 268	83.18 252	79.83 290	55.41 342	52.29 384	82.68 281	25.83 406	86.10 313	60.89 236	63.94 306	80.78 371
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MIMVSNet		63.12 347	60.29 358	71.61 325	75.92 338	46.65 347	65.15 444	81.94 240	59.14 262	54.65 365	69.47 435	25.74 407	80.63 389	41.03 398	69.56 253	87.55 224

LPG-MVS_test		66.44 312	64.58 313	72.02 312	74.42 362	48.60 286	83.07 257	80.64 269	54.69 352	53.75 375	83.83 257	25.73 408	86.98 278	60.33 247	64.71 297	80.48 375

LGP-MVS_train				72.02 312	74.42 362	48.60 286		80.64 269	54.69 352	53.75 375	83.83 257	25.73 408	86.98 278	60.33 247	64.71 297	80.48 375

test_vis1_n_1920		68.59 261	68.31 230	69.44 360	69.16 430	41.51 421	84.63 199	68.58 442	58.80 269	73.26 82	88.37 155	25.30 410	80.60 390	79.10 61	67.55 269	86.23 261

ACMM	58.35 12	64.35 332	62.01 338	71.38 330	74.21 366	48.51 290	82.25 281	79.66 296	47.61 408	54.54 366	80.11 320	25.26 411	86.00 319	51.26 337	63.16 318	79.64 384
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FE-MVSNET2		58.78 383	56.44 383	65.82 397	63.57 464	38.92 435	79.59 347	81.75 249	56.14 331	43.06 445	68.15 441	25.22 412	80.64 388	42.29 395	48.16 431	77.91 404

XVG-OURS		61.88 360	59.34 365	69.49 358	65.37 450	46.27 359	64.80 446	73.49 403	47.04 413	57.41 335	82.85 274	25.15 413	78.18 412	53.00 321	64.98 292	84.01 303

PVSNet_0	57.04 13	61.19 364	57.24 377	73.02 277	77.45 301	50.31 238	79.43 352	77.36 355	63.96 156	47.51 423	72.45 411	25.03 414	83.78 358	52.76 326	19.22 499	84.96 286

WB-MVS		37.41 453	36.37 453	40.54 474	54.23 482	10.43 512	65.29 442	43.75 486	34.86 472	27.81 491	54.63 480	24.94 415	63.21 472	6.81 508	15.00 502	47.98 492

UniMVSNet_ETH3D		62.51 354	60.49 354	68.57 374	68.30 438	40.88 428	73.89 394	79.93 288	51.81 378	54.77 363	79.61 328	24.80 416	81.10 380	49.93 344	61.35 331	83.73 313

DP-MVS		59.24 374	56.12 387	68.63 371	88.24 36	50.35 236	82.51 276	64.43 458	41.10 448	46.70 428	78.77 337	24.75 417	88.57 205	22.26 477	56.29 384	66.96 469

test_cas_vis1_n_1920		67.10 297	66.60 273	68.59 373	65.17 453	43.23 402	83.23 250	69.84 435	55.34 343	70.67 136	87.71 190	24.70 418	76.66 433	78.57 68	64.20 302	85.89 269

LuminaMVS		66.60 309	64.37 316	73.27 275	70.06 423	49.57 252	80.77 326	81.76 248	50.81 384	60.56 272	78.41 341	24.50 419	87.26 271	64.24 204	68.25 262	82.99 334

tt0805		63.39 344	61.31 347	69.64 357	69.36 428	38.87 436	78.00 363	85.48 127	48.82 399	55.66 356	81.66 305	24.38 420	86.37 304	49.04 352	59.36 351	83.68 319

cascas		69.01 250	66.13 282	77.66 115	79.36 248	55.41 60	86.99 94	83.75 202	56.69 316	58.92 299	81.35 309	24.31 421	92.10 66	53.23 317	70.61 238	85.46 277

CMPMVS	40.41 21	55.34 405	52.64 408	63.46 417	60.88 472	43.84 393	61.58 461	71.06 427	30.43 479	36.33 470	74.63 386	24.14 422	75.44 440	48.05 360	66.62 276	71.12 462
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UGNet		68.71 258	67.11 262	73.50 267	80.55 216	47.61 328	84.08 216	78.51 330	59.45 249	65.68 192	82.73 279	23.78 423	85.08 341	52.80 323	76.40 147	87.80 217
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		53.82 414	49.96 420	65.41 403	70.09 422	48.95 274	72.30 411	71.66 421	44.25 437	31.89 484	63.07 459	23.73 424	73.95 446	33.26 435	39.40 465	73.34 447

MDA-MVSNet_test_wron		53.82 414	49.95 421	65.43 402	70.13 421	49.05 270	72.30 411	71.65 422	44.23 438	31.85 485	63.13 458	23.68 425	74.01 445	33.25 436	39.35 466	73.23 450

PLC	52.38 18	60.89 365	58.97 369	66.68 392	81.77 167	45.70 372	78.96 356	74.04 395	43.66 440	47.63 420	83.19 272	23.52 426	77.78 423	37.47 406	60.46 338	76.55 422
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SSC-MVS		35.20 455	34.30 457	37.90 476	52.58 484	8.65 515	61.86 458	41.64 490	31.81 477	25.54 494	52.94 486	23.39 427	59.28 481	6.10 510	12.86 503	45.78 495

ADS-MVSNet2		55.21 407	51.44 413	66.51 393	80.60 212	49.56 255	55.03 475	65.44 452	44.72 432	51.00 397	61.19 466	22.83 428	75.41 441	28.54 455	53.63 406	74.57 439

ADS-MVSNet		56.17 401	51.95 412	68.84 365	80.60 212	53.07 152	55.03 475	70.02 434	44.72 432	51.00 397	61.19 466	22.83 428	78.88 407	28.54 455	53.63 406	74.57 439

test_0402		56.45 399	53.03 403	66.69 391	76.78 318	50.31 238	81.76 295	69.61 437	42.79 444	43.88 438	72.13 421	22.82 430	86.46 301	16.57 491	50.94 418	63.31 478

UnsupCasMVSNet_eth		57.56 393	55.15 392	64.79 408	64.57 458	33.12 459	73.17 402	83.87 201	58.98 266	41.75 451	70.03 433	22.54 431	79.92 399	46.12 374	35.31 472	81.32 365

xiu_mvs_v1_base_debu		71.60 190	70.29 194	75.55 191	77.26 307	53.15 147	85.34 159	79.37 304	55.83 334	72.54 92	90.19 113	22.38 432	86.66 294	73.28 127	76.39 148	86.85 245

xiu_mvs_v1_base		71.60 190	70.29 194	75.55 191	77.26 307	53.15 147	85.34 159	79.37 304	55.83 334	72.54 92	90.19 113	22.38 432	86.66 294	73.28 127	76.39 148	86.85 245

xiu_mvs_v1_base_debi		71.60 190	70.29 194	75.55 191	77.26 307	53.15 147	85.34 159	79.37 304	55.83 334	72.54 92	90.19 113	22.38 432	86.66 294	73.28 127	76.39 148	86.85 245

LS3D		56.40 400	53.82 400	64.12 411	81.12 195	45.69 373	73.42 400	66.14 448	35.30 471	43.24 444	79.88 322	22.18 435	79.62 404	19.10 486	64.00 305	67.05 468

PVSNet	62.49 8	69.27 244	67.81 246	73.64 262	84.41 90	51.85 188	84.63 199	77.80 345	66.42 104	59.80 279	84.95 240	22.14 436	80.44 393	55.03 304	75.11 179	88.62 193

MDA-MVSNet-bldmvs		51.56 427	47.75 435	63.00 420	71.60 398	47.32 336	69.70 429	72.12 414	43.81 439	27.65 492	63.38 457	21.97 437	75.96 437	27.30 462	32.19 480	65.70 474

pmmvs-eth3d		55.97 403	52.78 407	65.54 401	61.02 471	46.44 353	75.36 383	67.72 445	49.61 394	43.65 440	67.58 443	21.63 438	77.04 427	44.11 384	44.33 450	73.15 451

anonymousdsp		60.46 368	57.65 374	68.88 364	63.63 463	45.09 376	72.93 403	78.63 326	46.52 416	51.12 396	72.80 407	21.46 439	83.07 367	57.79 276	53.97 403	78.47 395

MVS-HIRNet		49.01 436	44.71 440	61.92 429	76.06 331	46.61 349	63.23 453	54.90 475	24.77 486	33.56 479	36.60 497	21.28 440	75.88 439	29.49 449	62.54 325	63.26 479

Anonymous202405211		70.11 222	67.88 241	76.79 150	87.20 48	47.24 338	89.49 36	77.38 354	54.88 350	66.14 182	86.84 205	20.93 441	91.54 77	56.45 292	71.62 225	91.59 67

FE-MVSNET		51.43 428	48.22 430	61.06 435	60.78 473	32.48 464	73.85 396	64.62 455	46.30 423	37.47 468	66.27 447	20.80 442	77.38 426	23.43 473	40.48 461	73.31 448

UnsupCasMVSNet_bld		53.86 413	50.53 417	63.84 412	63.52 465	34.75 449	71.38 420	81.92 242	46.53 415	38.95 463	57.93 476	20.55 443	80.20 397	39.91 401	34.09 479	76.57 421

Elysia		65.59 321	62.65 327	74.42 233	69.85 424	49.46 262	80.04 339	82.11 235	46.32 421	58.74 307	79.64 326	20.30 444	88.57 205	55.48 301	71.37 229	85.22 280

StellarMVS		65.59 321	62.65 327	74.42 233	69.85 424	49.46 262	80.04 339	82.11 235	46.32 421	58.74 307	79.64 326	20.30 444	88.57 205	55.48 301	71.37 229	85.22 280

EU-MVSNet		52.63 420	50.72 416	58.37 445	62.69 468	28.13 485	72.60 406	75.97 374	30.94 478	40.76 458	72.11 422	20.16 446	70.80 461	35.11 427	46.11 446	76.19 425

N_pmnet		41.25 446	39.77 449	45.66 467	68.50 435	0.82 533	72.51 408	0.38 532	35.61 468	35.26 474	61.51 465	20.07 447	67.74 466	23.51 472	40.63 459	68.42 467

MSDG		59.44 372	55.14 393	72.32 305	74.69 357	50.71 219	74.39 391	73.58 400	44.44 435	43.40 442	77.52 349	19.45 448	90.87 104	31.31 443	57.49 375	75.38 429

tt0320		52.45 422	48.75 426	63.55 415	71.47 400	41.85 416	72.42 409	59.73 467	36.33 466	44.52 435	61.55 464	19.34 449	76.45 435	33.53 432	39.85 463	72.36 454

K. test v3		54.04 412	49.42 425	67.92 378	68.55 434	42.57 412	75.51 381	63.07 462	52.07 373	39.21 461	64.59 455	19.34 449	82.21 372	37.11 410	25.31 490	78.97 388

lessismore_v0				67.98 377	64.76 457	41.25 424		45.75 484		36.03 472	65.63 452	19.29 451	84.11 353	35.67 419	21.24 496	78.59 394

KD-MVS_self_test		49.24 435	46.85 437	56.44 450	54.32 481	22.87 491	57.39 470	73.36 408	44.36 436	37.98 466	59.30 474	18.97 452	71.17 460	33.48 433	42.44 455	75.26 431

OpenMVS_ROB	53.19 17	59.20 375	56.00 388	68.83 366	71.13 405	44.30 386	83.64 230	75.02 383	46.42 418	46.48 431	73.03 403	18.69 453	88.14 225	27.74 460	61.80 329	74.05 442

mvsany_test1		43.38 445	42.57 447	45.82 466	50.96 490	26.10 487	55.80 473	27.74 506	27.15 483	47.41 424	74.39 388	18.67 454	44.95 498	44.66 379	36.31 470	66.40 471

LTVRE_ROB	45.45 19	52.73 419	49.74 423	61.69 430	69.78 426	34.99 448	44.52 486	67.60 446	43.11 443	43.79 439	74.03 390	18.54 455	81.45 378	28.39 457	57.94 368	68.62 466
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		54.37 408	50.10 418	67.21 384	70.70 411	41.46 423	74.73 386	64.69 454	47.56 409	39.12 462	69.49 434	18.49 456	84.69 347	31.87 440	34.20 478	75.48 428

new-patchmatchnet		48.21 437	46.55 438	53.18 456	57.73 477	18.19 505	70.24 424	71.02 428	45.70 425	33.70 478	60.23 469	18.00 457	69.86 464	27.97 459	34.35 476	71.49 461

tt0320-xc		52.22 425	48.38 429	63.75 414	72.19 393	42.25 415	72.19 414	57.59 471	37.24 459	44.41 436	61.56 463	17.90 458	75.89 438	35.60 420	36.73 469	73.12 452

F-COLMAP		55.96 404	53.65 402	62.87 422	72.76 384	42.77 408	74.70 388	70.37 431	40.03 449	41.11 456	79.36 330	17.77 459	73.70 449	32.80 438	53.96 404	72.15 455

sc_t1		53.51 417	49.92 422	64.29 410	70.33 418	39.55 433	72.93 403	59.60 468	38.74 454	47.16 425	66.47 446	17.59 460	76.50 434	36.83 414	39.62 464	76.82 415

jajsoiax		63.21 346	60.84 351	70.32 348	68.33 437	44.45 384	81.23 315	81.05 259	53.37 365	50.96 399	77.81 347	17.49 461	85.49 332	59.31 252	58.05 366	81.02 369

RPSCF		45.77 442	44.13 444	50.68 458	57.67 478	29.66 478	54.92 477	45.25 485	26.69 484	45.92 433	75.92 379	17.43 462	45.70 497	27.44 461	45.95 447	76.67 417

mmtdpeth		57.93 391	54.78 395	67.39 383	72.32 390	43.38 399	72.72 405	68.93 440	54.45 355	56.85 341	62.43 460	17.02 463	83.46 363	57.95 272	30.31 484	75.31 430

PatchMatch-RL		56.66 396	53.75 401	65.37 404	77.91 290	45.28 375	69.78 428	60.38 465	41.35 447	47.57 421	73.73 394	16.83 464	76.91 429	36.99 412	59.21 352	73.92 443

mvs_tets		62.96 349	60.55 353	70.19 349	68.22 440	44.24 389	80.90 322	80.74 267	52.99 368	50.82 403	77.56 348	16.74 465	85.44 333	59.04 255	57.94 368	80.89 370

ACMH+	54.58 15	58.55 387	55.24 391	68.50 375	74.68 358	45.80 371	80.27 334	70.21 432	47.15 412	42.77 446	75.48 381	16.73 466	85.98 321	35.10 428	54.78 398	73.72 444

ACMH	53.70 16	59.78 370	55.94 389	71.28 331	76.59 319	48.35 296	80.15 338	76.11 373	49.74 393	41.91 450	73.45 401	16.50 467	90.31 126	31.42 442	57.63 374	75.17 432
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MIMVSNet1		50.35 433	47.81 433	57.96 446	61.53 470	27.80 486	67.40 437	74.06 394	43.25 442	33.31 483	65.38 454	16.03 468	71.34 459	21.80 478	47.55 437	74.75 436

DSMNet-mixed		38.35 450	35.36 455	47.33 465	48.11 496	14.91 509	37.87 494	36.60 497	19.18 491	34.37 476	59.56 473	15.53 469	53.01 490	20.14 484	46.89 443	74.07 441

EG-PatchMatch MVS		62.40 358	59.59 362	70.81 340	73.29 375	49.05 270	85.81 134	84.78 169	51.85 377	44.19 437	73.48 400	15.52 470	89.85 142	40.16 400	67.24 271	73.54 446

testgi		54.25 410	52.57 409	59.29 442	62.76 467	21.65 497	72.21 413	70.47 430	53.25 366	41.94 449	77.33 354	14.28 471	77.95 419	29.18 451	51.72 417	78.28 400

COLMAP_ROB	43.60 20	50.90 431	48.05 432	59.47 439	67.81 441	40.57 429	71.25 421	62.72 464	36.49 464	36.19 471	73.51 399	13.48 472	73.92 447	20.71 481	50.26 420	63.92 477
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		52.39 423	48.73 427	63.35 419	65.21 452	38.42 440	68.54 434	64.95 453	38.19 455	39.57 460	71.43 425	13.23 473	79.92 399	37.16 408	40.32 462	71.72 458

usedtu_dtu_shiyan2		50.47 432	46.43 439	62.61 424	51.66 487	31.70 468	75.62 378	75.65 377	36.36 465	34.89 475	56.91 479	12.01 474	78.40 410	30.87 446	43.86 451	77.72 407

MVStest1		38.35 450	34.53 456	49.82 462	51.43 488	30.41 470	50.39 479	55.25 473	17.56 494	26.45 493	65.85 451	11.72 475	57.00 485	14.79 493	17.31 501	62.05 481

test_fmvs1		53.60 416	52.54 410	56.78 448	58.07 475	30.26 471	68.95 432	42.19 489	32.46 474	63.59 237	82.56 286	11.55 476	60.81 476	58.25 266	55.27 394	79.28 385

tmp_tt		9.44 477	10.68 480	5.73 500	2.49 529	4.21 521	10.48 509	18.04 513	0.34 523	12.59 505	20.49 511	11.39 477	7.03 517	13.84 496	6.46 510	5.95 517

ITE_SJBPF				51.84 457	58.03 476	31.94 467		53.57 479	36.67 462	41.32 454	75.23 383	11.17 478	51.57 491	25.81 466	48.04 433	72.02 457

Anonymous20240521		51.65 426	48.42 428	61.34 434	56.43 480	39.65 432	73.57 398	73.47 406	36.64 463	36.59 469	63.98 456	10.75 479	72.25 458	35.35 422	49.01 422	72.11 456

mvs5depth		50.97 430	46.98 436	62.95 421	56.63 479	34.23 454	62.73 457	67.35 447	45.03 431	48.00 417	65.41 453	10.40 480	79.88 403	36.00 417	31.27 483	74.73 437

AllTest		47.32 439	44.66 441	55.32 454	65.08 454	37.50 444	62.96 455	54.25 477	35.45 469	33.42 480	72.82 405	9.98 481	59.33 479	24.13 470	43.84 452	69.13 464

TestCases				55.32 454	65.08 454	37.50 444		54.25 477	35.45 469	33.42 480	72.82 405	9.98 481	59.33 479	24.13 470	43.84 452	69.13 464

USDC		54.36 409	51.23 414	63.76 413	64.29 460	37.71 443	62.84 456	73.48 405	56.85 308	35.47 473	71.94 424	9.23 483	78.43 409	38.43 405	48.57 429	75.13 433

XVG-ACMP-BASELINE		56.03 402	52.85 406	65.58 400	61.91 469	40.95 427	63.36 451	72.43 412	45.20 429	46.02 432	74.09 389	9.20 484	78.12 413	45.13 376	58.27 361	77.66 409

test_fmvs1_n		52.55 421	51.19 415	56.65 449	51.90 486	30.14 472	67.66 436	42.84 488	32.27 475	62.30 251	82.02 300	9.12 485	60.84 475	57.82 275	54.75 400	78.99 387

test_vis1_n		51.19 429	49.66 424	55.76 453	51.26 489	29.85 477	67.20 439	38.86 493	32.12 476	59.50 286	79.86 323	8.78 486	58.23 483	56.95 284	52.46 414	79.19 386

pmmvs3		45.53 443	41.55 448	57.44 447	48.97 494	39.68 431	70.06 425	57.66 470	28.32 482	34.06 477	57.29 477	8.50 487	66.85 469	34.86 429	34.26 477	65.80 473

EGC-MVSNET		33.75 457	30.42 461	43.75 470	64.94 456	36.21 447	60.47 465	40.70 492	0.02 550	0.10 547	53.79 483	7.39 488	60.26 477	11.09 500	35.23 474	34.79 497

test_fmvs2		45.89 441	44.32 443	50.62 459	45.85 498	24.70 489	58.87 469	37.84 496	25.22 485	52.46 383	74.56 387	7.07 489	54.69 487	49.28 350	47.70 435	72.48 453

ANet_high		34.39 456	29.59 462	48.78 463	30.34 508	22.28 493	55.53 474	63.79 460	38.11 456	15.47 500	36.56 498	6.94 490	59.98 478	13.93 495	5.64 511	64.08 476

FPMVS		35.40 454	33.67 458	40.57 473	46.34 497	28.74 484	41.05 490	57.05 472	20.37 490	22.27 496	53.38 484	6.87 491	44.94 499	8.62 502	47.11 441	48.01 491

test_vis1_rt		40.29 449	38.64 450	45.25 468	48.91 495	30.09 473	59.44 466	27.07 507	24.52 487	38.48 465	51.67 487	6.71 492	49.44 492	44.33 381	46.59 445	56.23 483

new_pmnet		33.56 458	31.89 460	38.59 475	49.01 493	20.42 498	51.01 478	37.92 495	20.58 488	23.45 495	46.79 489	6.66 493	49.28 494	20.00 485	31.57 482	46.09 494

TinyColmap		48.15 438	44.49 442	59.13 443	65.73 449	38.04 441	63.34 452	62.86 463	38.78 452	29.48 487	67.23 445	6.46 494	73.30 452	24.59 469	41.90 457	66.04 472

ambc				62.06 426	53.98 483	29.38 480	35.08 496	79.65 298		41.37 452	59.96 471	6.27 495	82.15 373	35.34 423	38.22 467	74.65 438

TDRefinement		40.91 447	38.37 451	48.55 464	50.45 491	33.03 461	58.98 468	50.97 480	28.50 480	29.89 486	67.39 444	6.21 496	54.51 488	17.67 489	35.25 473	58.11 482

ttmdpeth		40.58 448	37.50 452	49.85 461	49.40 492	22.71 492	56.65 472	46.78 481	28.35 481	40.29 459	69.42 436	5.35 497	61.86 474	20.16 483	21.06 497	64.96 475

PM-MVS		46.92 440	43.76 446	56.41 451	52.18 485	32.26 465	63.21 454	38.18 494	37.99 457	40.78 457	66.20 448	5.09 498	65.42 470	48.19 359	41.99 456	71.54 460

LF4IMVS		33.04 459	32.55 459	34.52 479	40.96 499	22.03 494	44.45 487	35.62 498	20.42 489	28.12 490	62.35 461	5.03 499	31.88 510	21.61 480	34.42 475	49.63 490

EMVS		18.42 472	17.66 476	20.71 490	34.13 505	12.64 511	46.94 482	29.94 504	10.46 504	5.58 517	14.93 517	4.23 500	38.83 502	5.24 514	7.51 508	10.67 511

E-PMN		19.16 471	18.40 475	21.44 489	36.19 503	13.63 510	47.59 481	30.89 502	10.73 502	5.91 515	16.59 514	3.66 501	39.77 501	5.95 511	8.14 506	10.92 510

test_method		24.09 468	21.07 472	33.16 482	27.67 512	8.35 518	26.63 502	35.11 500	3.40 512	14.35 501	36.98 496	3.46 502	35.31 505	19.08 487	22.95 493	55.81 484

mvsany_test3		28.00 461	25.98 463	34.05 480	28.97 509	15.31 507	34.54 497	18.17 512	16.24 495	29.30 488	53.37 485	2.79 503	33.38 509	30.01 448	20.41 498	53.45 487

test_f		27.12 463	24.85 464	33.93 481	26.17 514	15.25 508	30.24 501	22.38 511	12.53 500	28.23 489	49.43 488	2.59 504	34.34 508	25.12 468	26.99 488	52.20 488

test_fmvs3		37.95 452	35.75 454	44.55 469	35.50 504	18.92 501	48.32 480	34.00 501	18.36 493	41.31 455	61.58 462	2.29 505	48.06 496	42.72 392	37.71 468	66.66 470

PMMVS2		26.71 464	22.98 469	37.87 477	36.89 502	8.51 516	42.51 489	29.32 505	19.09 492	13.01 503	37.54 494	2.23 506	53.11 489	14.54 494	11.71 504	51.99 489

Gipuma		27.47 462	24.26 467	37.12 478	60.55 474	29.17 481	11.68 507	60.00 466	14.18 497	10.52 509	15.12 516	2.20 507	63.01 473	8.39 503	35.65 471	19.18 505
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		28.07 460	23.85 468	40.71 472	27.46 513	18.93 500	30.82 500	46.19 482	12.76 499	16.40 498	34.70 500	1.90 508	48.69 495	20.25 482	24.22 492	54.51 486

DeepMVS_CX				13.10 493	21.34 516	8.99 514		10.02 516	10.59 503	7.53 512	30.55 503	1.82 509	14.55 511	6.83 507	7.52 507	15.75 507

APD_test1		26.46 465	24.41 466	32.62 484	37.58 501	21.74 496	40.50 492	30.39 503	11.45 501	16.33 499	43.76 490	1.63 510	41.62 500	11.24 499	26.82 489	34.51 498

PMVS	19.57 22	25.07 466	22.43 471	32.99 483	23.12 515	22.98 490	40.98 491	35.19 499	15.99 496	11.95 508	35.87 499	1.47 511	49.29 493	5.41 513	31.90 481	26.70 504
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		24.79 467	22.95 470	30.31 485	28.59 510	18.92 501	37.43 495	17.27 514	12.90 498	21.28 497	29.92 504	1.02 512	36.35 503	28.28 458	29.82 487	35.65 496

MVE	16.60 23	17.34 474	13.39 477	29.16 486	28.43 511	19.72 499	13.73 506	23.63 510	7.23 507	7.96 511	21.41 509	0.80 513	36.08 504	6.97 506	10.39 505	31.69 499
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testf1		21.11 469	19.08 473	27.18 487	30.56 506	18.28 503	33.43 498	24.48 508	8.02 505	12.02 506	33.50 501	0.75 514	35.09 506	7.68 504	21.32 494	28.17 501

APD_test2		21.11 469	19.08 473	27.18 487	30.56 506	18.28 503	33.43 498	24.48 508	8.02 505	12.02 506	33.50 501	0.75 514	35.09 506	7.68 504	21.32 494	28.17 501

ArgMatch-Sym		13.78 475	13.16 478	15.65 492	13.75 517	8.38 517	21.56 503	2.56 518	7.09 508	14.16 502	40.67 492	0.28 516	11.85 514	13.55 497	4.84 512	26.71 503

ArgMatch-SfM		13.59 476	12.41 479	17.15 491	12.50 518	7.57 519	19.17 505	3.21 517	5.58 509	12.94 504	39.91 493	0.26 517	13.40 512	13.23 498	4.84 512	30.48 500

wuyk23d		9.11 478	8.77 482	10.15 494	40.18 500	16.76 506	20.28 504	1.01 522	2.58 514	2.66 523	0.98 536	0.23 518	12.49 513	4.08 519	6.90 509	1.19 523

PDCNetPlus		5.70 485	5.56 488	6.14 498	8.32 520	1.98 525	7.37 512	0.76 524	2.18 515	3.69 521	20.81 510	0.12 519	4.60 520	4.55 516	2.21 517	11.83 509

DenseAffine		8.44 479	7.90 485	10.07 495	9.51 519	4.71 520	11.43 508	1.10 521	4.32 510	8.26 510	27.67 506	0.09 520	8.71 515	6.30 509	2.41 516	16.80 506

RoMa-SfM		7.02 481	6.78 486	7.74 496	5.47 523	3.55 522	8.83 510	0.67 525	3.41 511	7.06 513	27.85 505	0.08 521	7.13 516	5.86 512	1.82 518	12.53 508

LoFTR		5.36 486	5.09 489	6.17 497	5.52 522	2.23 524	6.04 513	2.15 519	1.23 518	5.61 516	19.15 512	0.07 522	5.98 518	1.61 521	4.48 514	10.30 513

RoMa-HiRes		4.68 487	4.75 490	4.46 501	3.18 526	1.88 526	5.38 515	0.37 533	2.04 516	4.84 518	21.68 508	0.06 523	3.78 522	4.17 518	1.04 524	7.71 516

ALIKED-LG		1.21 496	1.31 499	0.90 509	2.88 527	0.91 530	1.96 518	0.48 529	0.17 526	0.94 528	3.75 526	0.06 523	0.81 528	0.10 534	1.43 520	0.99 524

SP-DiffGlue		0.50 500	0.53 503	0.38 516	0.41 554	0.20 544	0.62 529	0.19 536	0.09 529	0.64 533	1.95 530	0.06 523	0.17 538	0.26 527	0.60 530	0.77 529

MASt3R-SfM		1.80 494	2.02 496	1.14 508	1.03 538	0.52 536	1.83 520	0.53 527	0.34 523	2.55 524	9.61 522	0.05 526	0.77 529	1.06 523	1.16 523	2.14 522

ALIKED-NN		1.00 498	1.09 501	0.75 511	2.44 530	0.84 532	1.63 524	0.39 530	0.12 527	0.72 531	3.04 528	0.05 526	0.70 531	0.08 536	1.32 522	0.72 531

DKM		5.93 484	5.87 487	6.10 499	5.64 521	2.81 523	7.85 511	0.52 528	2.62 513	6.30 514	23.31 507	0.05 526	4.93 519	5.11 515	1.45 519	10.57 512

SP-LightGlue		0.48 501	0.50 504	0.40 512	1.33 533	0.19 545	0.86 525	0.17 538	0.08 531	0.25 535	1.08 532	0.05 526	0.19 535	0.13 530	0.57 531	0.80 526

SP-SuperGlue		0.47 502	0.50 504	0.39 513	1.30 534	0.19 545	0.86 525	0.17 538	0.09 529	0.26 534	1.08 532	0.05 526	0.18 537	0.13 530	0.55 532	0.79 528

ALIKED-MNN		1.07 497	1.15 500	0.84 510	2.67 528	0.92 529	1.81 521	0.39 530	0.12 527	0.73 530	3.13 527	0.05 526	0.77 529	0.09 535	1.34 521	0.84 525

DKM-HiRes		4.42 488	4.49 491	4.23 502	3.85 525	1.83 527	5.38 515	0.33 534	1.86 517	4.78 519	18.85 513	0.04 532	2.97 524	4.34 517	0.97 525	7.88 515

SP-NN		0.43 505	0.45 508	0.37 517	1.13 537	0.17 549	0.82 528	0.16 540	0.07 533	0.24 536	1.00 535	0.04 532	0.19 535	0.12 532	0.51 535	0.74 530

GLUNet-SfM		2.60 491	2.13 495	4.01 504	1.95 531	0.86 531	1.72 522	0.81 523	0.34 523	3.35 522	9.72 521	0.04 532	3.15 523	0.50 526	0.73 528	8.02 514

MatchFormer		3.89 489	3.84 493	4.03 503	4.08 524	1.73 528	5.52 514	1.59 520	0.67 519	4.77 520	13.56 519	0.04 532	4.50 521	0.74 525	3.60 515	5.85 518

SP-MNN		0.45 503	0.47 507	0.39 513	1.18 536	0.17 549	0.85 527	0.16 540	0.07 533	0.24 536	1.05 534	0.04 532	0.20 534	0.12 532	0.54 534	0.80 526

XFeat-NN		0.44 504	0.49 506	0.30 518	0.24 556	0.12 555	0.48 531	0.15 542	0.06 535	0.71 532	1.78 531	0.03 537	0.28 533	0.14 529	0.83 527	0.48 533

XFeat-MNN		0.55 499	0.60 502	0.39 513	0.26 555	0.16 552	0.58 530	0.20 535	0.08 531	0.82 529	2.26 529	0.03 537	0.39 532	0.19 528	0.95 526	0.62 532

ELoFTR		2.17 493	1.90 497	2.99 505	1.19 535	0.63 535	1.84 519	0.60 526	0.46 521	2.17 526	9.10 523	0.02 539	2.92 525	1.00 524	0.72 529	5.42 519

PMatch-SfM		2.38 492	2.41 494	2.29 506	1.48 532	0.76 534	2.51 517	0.18 537	0.59 520	2.43 525	12.04 520	0.01 540	1.67 526	1.93 520	0.55 532	4.44 520

SIFT-UM-Cal		0.21 515	0.23 518	0.14 529	0.68 547	0.15 553	0.29 541	0.04 554	0.05 536	0.10 547	0.56 546	0.01 540	0.12 548	0.02 537	0.34 546	0.15 546

SIFT-NCM-Cal		0.26 509	0.28 512	0.19 522	0.84 542	0.23 541	0.38 535	0.06 547	0.05 536	0.11 545	0.59 544	0.01 540	0.14 539	0.02 537	0.45 539	0.21 540

SIFT-CM-Cal		0.21 515	0.23 518	0.15 528	0.71 546	0.18 547	0.28 542	0.05 550	0.05 536	0.10 547	0.55 547	0.01 540	0.12 548	0.01 549	0.33 547	0.17 544

SIFT-PCN-Cal		0.18 517	0.20 520	0.13 530	0.58 551	0.10 557	0.23 544	0.04 554	0.04 546	0.08 550	0.47 548	0.01 540	0.10 550	0.01 549	0.30 548	0.19 541

SIFT-NN-UMatch		0.24 511	0.26 513	0.18 524	0.64 549	0.18 547	0.38 535	0.06 547	0.05 536	0.12 544	0.65 539	0.01 540	0.13 543	0.02 537	0.43 540	0.22 538

SIFT-NN-NCMNet		0.27 508	0.29 511	0.20 521	0.81 543	0.24 540	0.40 534	0.08 544	0.05 536	0.14 541	0.65 539	0.01 540	0.14 539	0.02 537	0.47 537	0.22 538

SIFT-NN-CMatch		0.25 510	0.26 513	0.19 522	0.68 547	0.21 542	0.35 537	0.06 547	0.05 536	0.15 539	0.65 539	0.01 540	0.13 543	0.02 537	0.41 541	0.23 536

SIFT-NN-PointCN		0.22 514	0.24 517	0.17 526	0.59 550	0.14 554	0.32 539	0.05 550	0.04 546	0.13 542	0.57 545	0.01 540	0.13 543	0.02 537	0.39 542	0.23 536

SIFT-NN		0.30 506	0.33 509	0.22 519	0.96 540	0.28 538	0.45 532	0.08 544	0.05 536	0.17 538	0.72 537	0.01 540	0.14 539	0.02 537	0.48 536	0.25 534

SIFT-UMatch		0.23 513	0.25 516	0.16 527	0.74 545	0.17 549	0.33 538	0.05 550	0.05 536	0.11 545	0.60 543	0.01 540	0.13 543	0.02 537	0.37 544	0.18 543

SIFT-NCMNet		0.15 519	0.17 522	0.10 532	0.52 553	0.09 558	0.19 545	0.02 557	0.04 546	0.07 552	0.39 550	0.01 540	0.08 552	0.01 549	0.24 550	0.11 547

SIFT-ConvMatch		0.24 511	0.26 513	0.18 524	0.76 544	0.21 542	0.32 539	0.05 550	0.05 536	0.13 542	0.63 542	0.01 540	0.13 543	0.02 537	0.38 543	0.19 541

SIFT-PointCN		0.18 517	0.20 520	0.13 530	0.58 551	0.11 556	0.25 543	0.04 554	0.04 546	0.08 550	0.45 549	0.01 540	0.10 550	0.01 549	0.30 548	0.17 544

SIFT-MNN		0.28 507	0.31 510	0.21 520	0.89 541	0.25 539	0.41 533	0.08 544	0.05 536	0.15 539	0.70 538	0.01 540	0.14 539	0.02 537	0.46 538	0.25 534

PMatch-Up-SfM		1.67 495	1.74 498	1.44 507	1.00 539	0.50 537	1.72 522	0.11 543	0.40 522	1.75 527	8.98 524	0.00 555	1.07 527	1.34 522	0.35 545	2.76 521

mmdepth		0.00 520	0.00 523	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	0.00 553	0.00 555	0.00 553	0.00 553	0.00 551	0.00 550

monomultidepth		0.00 520	0.00 523	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	0.00 553	0.00 555	0.00 553	0.00 553	0.00 551	0.00 550

test_blank		0.00 520	0.00 523	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	0.00 553	0.00 555	0.00 553	0.00 553	0.00 551	0.00 550

uanet_test		0.00 520	0.00 523	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	0.00 553	0.00 555	0.00 553	0.00 553	0.00 551	0.00 550

DCPMVS		0.00 520	0.00 523	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	0.00 553	0.00 555	0.00 553	0.00 553	0.00 551	0.00 550

sosnet-low-res		0.00 520	0.00 523	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	0.00 553	0.00 555	0.00 553	0.00 553	0.00 551	0.00 550

sosnet		0.00 520	0.00 523	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	0.00 553	0.00 555	0.00 553	0.00 553	0.00 551	0.00 550

uncertanet		0.00 520	0.00 523	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	0.00 553	0.00 555	0.00 553	0.00 553	0.00 551	0.00 550

Regformer		0.00 520	0.00 523	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	0.00 553	0.00 555	0.00 553	0.00 553	0.00 551	0.00 550

testmvs		6.14 482	8.18 483	0.01 533	0.01 557	0.00 560	73.40 401	0.00 558	0.00 551	0.02 553	0.15 551	0.00 555	0.00 553	0.02 537	0.00 551	0.02 548

test123		6.01 483	8.01 484	0.01 533	0.00 558	0.01 559	71.93 418	0.00 558	0.00 551	0.02 553	0.11 552	0.00 555	0.00 553	0.02 537	0.00 551	0.02 548

ab-mvs-re		7.68 480	10.24 481	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	92.12 59	0.00 555	0.00 553	0.00 553	0.00 551	0.00 550

uanet		0.00 520	0.00 523	0.00 535	0.00 558	0.00 560	0.00 546	0.00 558	0.00 551	0.00 555	0.00 553	0.00 555	0.00 553	0.00 553	0.00 551	0.00 550

aaatest				80.14 38	84.34 92	54.93 84	87.61 72	87.22 82	57.43 298	81.85 18	92.88 44		93.75 32	80.19 52	85.13 50	91.76 61

WAC-MVS						34.28 452								22.56 476

FOURS1					83.24 120	49.90 247	84.98 182	78.76 322	47.71 407	73.42 79

MSC_two_6792asdad				81.53 16	91.77 4	56.03 48		91.10 13					96.22 9	81.46 46	86.80 29	92.34 36

No_MVS				81.53 16	91.77 4	56.03 48		91.10 13					96.22 9	81.46 46	86.80 29	92.34 36

eth-test2					0.00 558

eth-test					0.00 558

IU-MVS					89.48 18	57.49 18		91.38 9	66.22 108	88.26 2				82.83 32	87.60 19	92.44 33

save fliter					85.35 73	56.34 43	89.31 42	81.46 252	61.55 210

test_0728_SECOND				82.20 9	89.50 16	57.73 14	92.34 5	88.88 38					96.39 4	81.68 41	87.13 22	92.47 32

GSMVS																88.13 210

test_part2					89.33 24	55.48 56				82.27 13

MTGPA								81.31 255

MTMP							87.27 88	15.34 515

gm-plane-assit					83.24 120	54.21 119			70.91 31		88.23 164		95.25 15	66.37 181

test9_res														78.72 67	85.44 46	91.39 77

agg_prior2														75.65 94	85.11 52	91.01 102

agg_prior					85.64 66	54.92 89		83.61 209		72.53 95			88.10 228

test_prior4						56.39 42	87.15 92

test_prior				78.39 95	86.35 57	54.91 92		85.45 130					89.70 152			90.55 120

旧先验2							81.73 298		45.53 427	74.66 65			70.48 463	58.31 265

新几何2							81.61 304

无先验							85.19 168	78.00 340	49.08 396				85.13 340	52.78 324		87.45 227

原ACMM2							83.77 228

testdata2													77.81 422	45.64 375

testdata1							77.55 367		64.14 150

plane_prior7					77.95 287	48.46 293

plane_prior5								82.59 227					88.30 221	65.46 192	72.34 217	84.49 291

plane_prior4											83.28 270

plane_prior3						48.95 274			64.01 154	62.15 254

plane_prior2							85.76 137		63.60 166

plane_prior1					78.31 282

plane_prior						49.57 252	87.43 80		64.57 140						72.84 209

n2								0.00 558

nn								0.00 558

door-mid								41.31 491

test11								84.25 188

door								43.27 487

HQP5-MVS						51.56 199

HQP-NCC					79.02 261		88.00 61		65.45 123	64.48 215

ACMP_Plane					79.02 261		88.00 61		65.45 123	64.48 215

BP-MVS														66.70 178

HQP4-MVS										64.47 218			88.61 200			84.91 287

HQP3-MVS								83.68 204							73.12 205

NP-MVS					78.76 267	50.43 229					85.12 234

ACMMP++_ref															63.20 317

ACMMP++															59.38 350

High-resolution multi-view benchmark