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	82.99 130	52.71 158	85.04 176	88.63 49	66.08 108	86.77 4	92.75 47	72.05 1	91.46 78	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	84.98 180	88.88 38	58.00 274	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 93	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	56.28 319	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	80.12 229	59.50 5	92.24 8	90.72 17	69.37 53	83.22 9	94.47 4	63.81 6	93.18 38	74.02 108	93.25 2	94.80 1

WBMVS		73.93 130	73.39 122	75.55 185	87.82 41	55.21 67	89.37 39	87.29 79	67.27 79	63.70 224	80.30 310	60.32 7	86.47 292	61.58 222	62.85 313	84.97 277

DELS-MVS		82.32 5	82.50 5	81.79 13	86.80 50	56.89 30	92.77 2	86.30 106	77.83 1	77.88 47	92.13 58	60.24 8	94.78 20	78.97 61	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	84.83 188	83.68 201	67.85 71	69.36 144	90.24 110	60.20 9	92.10 65	84.14 23	80.40 89	92.82 26

baseline2		75.15 108	74.54 107	76.98 139	81.67 172	51.74 187	83.84 224	91.94 3	69.97 44	58.98 288	86.02 213	59.73 10	91.73 72	68.37 159	70.40 236	87.48 218

CSCG		80.41 15	79.72 16	82.49 6	89.12 26	57.67 16	89.29 45	91.54 5	59.19 250	71.82 105	90.05 118	59.72 11	96.04 11	78.37 67	88.40 14	93.75 8

GG-mvs-BLEND				77.77 110	86.68 51	50.61 214	68.67 424	88.45 58		68.73 151	87.45 188	59.15 12	90.67 109	54.83 295	87.67 18	92.03 48

testing3-2		72.30 166	72.35 141	72.15 301	83.07 125	47.64 319	85.46 156	89.81 25	66.17 104	61.96 250	84.88 235	58.93 13	82.27 362	55.87 285	64.97 283	86.54 245

SED-MVS		81.92 8	81.75 9	82.44 8	89.48 18	56.89 30	92.48 3	88.94 36	57.50 288	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	57.53 286	84.61 5	93.29 31	58.81 14	96.45 1

gg-mvs-nofinetune		67.43 278	64.53 306	76.13 164	85.95 58	47.79 317	64.38 438	88.28 61	39.34 441	66.62 168	41.27 481	58.69 16	89.00 177	49.64 337	86.62 32	91.59 67

BridgeMVS		80.28 16	79.73 15	81.90 12	86.47 54	59.34 6	80.45 323	89.51 27	69.76 49	71.05 123	86.66 202	58.68 17	93.24 36	84.64 20	90.40 6	93.14 19

UBG		78.86 26	78.86 24	78.86 63	87.80 42	55.43 57	87.67 70	91.21 12	72.83 10	72.10 100	88.40 153	58.53 18	89.08 172	73.21 122	77.98 121	92.08 44

myMVS_eth3d28		77.77 41	77.94 33	77.27 127	87.58 44	52.89 155	86.06 123	91.33 11	74.15 7	68.16 156	88.24 161	58.17 19	88.31 216	69.88 146	77.87 122	90.61 116

MED-MVS		79.49 21	79.29 20	80.06 42	84.34 91	54.93 83	87.61 72	87.22 81	56.22 320	81.85 18	92.98 41	58.11 20	93.75 31	80.19 52	85.13 48	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	70.62 135	88.37 155	57.69 21	92.30 57	75.25 94	76.24 150	91.20 90

MVSMamba_PlusPlus		75.28 102	73.39 122	80.96 22	80.85 204	58.25 11	74.47 381	87.61 76	50.53 377	65.24 189	83.41 259	57.38 22	92.83 42	73.92 110	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	70.84 129	88.09 167	57.29 23	92.63 50	69.24 151	75.13 174	91.91 53

CostFormer		73.89 132	72.30 144	78.66 72	82.36 150	56.58 35	75.56 370	85.30 136	66.06 109	70.50 137	76.88 355	57.02 24	89.06 173	68.27 161	68.74 251	90.33 126

test_0728_THIRD									58.00 274	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 75	88.70 52	87.92 67	55.55 329	81.21 24	93.69 19	56.51 26	94.27 25	78.36 68	85.70 41	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 92	75.44 82	76.89 142	86.23 57	50.38 225	85.55 151	91.42 7	71.30 27	68.80 150	87.94 174	56.42 27	89.24 166	56.54 279	74.75 182	91.07 96

DeepPCF-MVS	69.37 1	80.65 13	81.56 11	77.94 106	85.46 70	49.56 247	90.99 21	86.66 97	70.58 34	80.07 32	95.30 2	56.18 28	90.97 101	82.57 36	86.22 37	93.28 14

test_241102_TWO								88.76 45	57.50 288	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 37	57.12 26	87.94 66	91.07 16	71.43 23	70.75 130	88.04 172	55.82 30	92.65 48	69.61 147	75.00 178	92.05 47

patch_mono-2		80.84 12	81.59 10	78.62 75	90.34 10	53.77 124	88.08 60	88.36 60	76.17 2	79.40 39	91.09 82	55.43 31	90.09 131	85.01 16	80.40 89	91.99 52

testing222		77.70 43	77.22 46	79.14 54	86.95 48	54.89 92	87.18 90	91.96 2	72.29 13	71.17 121	88.70 143	55.19 32	91.24 85	65.18 189	76.32 148	91.29 84

DVP-MVS		81.30 10	81.00 13	82.20 9	89.40 21	57.45 20	92.34 5	89.99 22	57.71 282	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	57.71 282	83.14 10	93.96 11	55.17 33

TSAR-MVS + MP.		78.31 33	78.26 28	78.48 87	81.33 189	56.31 44	81.59 298	86.41 103	69.61 51	81.72 20	88.16 165	55.09 35	88.04 226	74.12 107	86.31 35	91.09 94
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 79	75.55 79	77.71 112	79.49 244	52.27 171	84.70 192	90.49 19	64.44 133	69.86 141	90.31 109	55.05 36	91.35 80	70.07 144	75.58 167	89.53 156

baseline1		72.51 160	72.12 150	73.69 254	85.05 77	44.46 374	83.51 233	86.13 111	71.61 21	64.64 202	87.97 173	55.00 37	89.48 157	59.07 245	56.05 377	87.13 229

test_one_0601					89.39 23	57.29 23		88.09 64	57.21 295	82.06 15	93.39 27	54.94 38

MM		82.69 2	83.29 3	80.89 23	84.38 90	55.40 61	92.16 10	89.85 24	75.28 4	82.41 12	93.86 14	54.30 39	93.98 26	90.29 1	87.13 22	93.30 13

TSAR-MVS + GP.		77.82 40	77.59 39	78.49 86	85.25 75	50.27 232	90.02 26	90.57 18	56.58 312	74.26 70	91.60 77	54.26 40	92.16 62	75.87 86	79.91 97	93.05 21

EPP-MVSNet		71.14 191	70.07 193	74.33 231	79.18 254	46.52 343	83.81 225	86.49 101	56.32 318	57.95 311	84.90 234	54.23 41	89.14 171	58.14 259	69.65 242	87.33 222

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 51	93.09 36	54.15 42	95.57 13	85.80 13	85.87 39	93.31 12

alignmvs		78.08 37	77.98 32	78.39 93	83.53 110	53.22 142	89.77 32	85.45 128	66.11 106	76.59 55	91.99 65	54.07 43	89.05 174	77.34 77	77.00 134	92.89 24

GDP-MVS		75.27 103	74.38 108	77.95 105	79.04 257	52.86 156	85.22 164	86.19 109	62.43 188	70.66 133	90.40 107	53.51 44	91.60 74	69.25 150	72.68 204	89.39 161

WTY-MVS		77.47 47	77.52 41	77.30 125	88.33 32	46.25 352	88.46 56	90.32 20	71.40 24	72.32 97	91.72 72	53.44 45	92.37 56	66.28 174	75.42 168	93.28 14

IB-MVS	68.87 2	74.01 128	72.03 154	79.94 43	83.04 127	55.50 55	90.24 25	88.65 47	67.14 82	61.38 255	81.74 295	53.21 46	94.28 23	60.45 236	62.41 316	90.03 143
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 46	55.20 70	89.93 29	87.55 77	66.04 111	79.46 37	93.00 40	53.10 47	91.76 70	80.40 51	89.56 9	92.68 30

miper_enhance_ethall		69.77 224	68.90 214	72.38 295	78.93 261	49.91 238	83.29 243	78.85 310	64.90 129	59.37 280	79.46 320	52.77 48	85.16 330	63.78 201	58.72 345	82.08 337

MVSTER		73.25 145	72.33 142	76.01 168	85.54 68	53.76 125	83.52 229	87.16 84	67.06 86	63.88 219	81.66 296	52.77 48	90.44 119	64.66 194	64.69 289	83.84 304

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 36	77.64 50	93.87 13	52.58 50	93.91 29	84.17 22	87.92 17	92.39 34

FIs		70.00 219	70.24 190	69.30 353	77.93 285	38.55 428	83.99 218	87.72 73	66.86 91	57.66 318	84.17 244	52.28 51	85.31 325	52.72 317	68.80 250	84.02 294

tpm2		70.82 200	68.44 220	77.98 102	80.78 206	56.11 46	74.21 384	81.28 253	60.24 228	68.04 158	75.27 373	52.26 52	88.50 205	55.82 288	68.03 256	89.33 163

thisisatest0515		73.64 139	72.20 146	77.97 103	81.63 175	53.01 151	86.69 108	88.81 43	62.53 184	64.06 214	85.65 217	52.15 53	92.50 52	58.43 252	69.84 239	88.39 197

ME-MVS		79.48 22	79.20 22	80.35 31	88.96 27	54.93 83	88.65 53	88.50 57	56.62 309	79.87 34	92.88 44	51.96 54	94.36 22	80.19 52	85.13 48	91.76 61

casdiffmvs_mvg		77.75 42	77.28 44	79.16 53	80.42 223	54.44 111	87.76 67	85.46 127	71.67 20	71.38 116	88.35 157	51.58 55	91.22 86	79.02 60	79.89 99	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		68.82 246	68.29 223	70.40 339	75.71 331	42.59 400	84.23 209	86.78 93	66.31 100	58.51 302	82.45 278	51.57 56	84.64 339	53.11 308	55.96 378	83.96 300

PAPM		76.76 63	76.07 70	78.81 64	80.20 227	59.11 7	86.86 102	86.23 107	68.60 59	70.18 140	88.84 141	51.57 56	87.16 267	65.48 182	86.68 31	90.15 135

tttt0517		68.33 258	66.29 270	74.46 224	78.08 280	49.06 261	80.88 316	89.08 34	54.40 347	54.75 355	80.77 305	51.31 58	90.33 123	49.35 339	58.01 357	83.99 296

mvs_anonymous		72.29 167	70.74 173	76.94 141	82.85 137	54.72 101	78.43 353	81.54 247	63.77 152	61.69 252	79.32 322	51.11 59	85.31 325	62.15 218	75.79 158	90.79 110

HY-MVS	67.03 5	73.90 131	73.14 128	76.18 163	84.70 83	47.36 327	75.56 370	86.36 105	66.27 101	70.66 133	83.91 248	51.05 60	89.31 163	67.10 168	72.61 205	91.88 55

thisisatest0530		70.47 210	68.56 216	76.20 161	79.78 238	51.52 193	83.49 235	88.58 55	57.62 285	58.60 301	82.79 267	51.03 61	91.48 77	52.84 312	62.36 318	85.59 268

sasdasda		78.17 35	77.86 35	79.12 56	84.30 94	54.22 114	87.71 68	84.57 179	67.70 75	77.70 48	92.11 61	50.90 62	89.95 135	78.18 71	77.54 126	93.20 16

miper_ehance_all_eth		68.70 252	67.58 241	72.08 303	76.91 308	49.48 253	82.47 271	78.45 324	62.68 182	58.28 310	77.88 336	50.90 62	85.01 333	61.91 219	58.72 345	81.75 342

canonicalmvs		78.17 35	77.86 35	79.12 56	84.30 94	54.22 114	87.71 68	84.57 179	67.70 75	77.70 48	92.11 61	50.90 62	89.95 135	78.18 71	77.54 126	93.20 16

casdiffmvs		77.36 49	76.85 53	78.88 62	80.40 224	54.66 106	87.06 93	85.88 115	72.11 16	71.57 109	88.63 148	50.89 65	90.35 122	76.00 85	79.11 108	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 52	54.69 103	92.20 9	86.66 97	74.48 5	82.63 11	93.80 16	50.83 66	93.70 33	90.11 2	86.44 34	93.01 22

fmvsm_s_conf0.5_n_9		76.66 66	76.94 52	75.85 173	79.54 243	48.30 293	82.63 263	71.84 407	70.25 38	80.63 29	94.53 3	50.78 67	87.42 259	88.32 5	73.92 188	91.82 59

baseline		76.86 59	76.24 66	78.71 68	80.47 218	54.20 118	83.90 222	84.88 163	71.38 25	71.51 112	89.15 136	50.51 68	90.55 115	75.71 87	78.65 112	91.39 77

TestfortrainingZip a		77.64 44	76.79 57	80.20 34	84.34 91	54.79 96	87.61 72	87.03 86	56.22 320	78.78 40	92.98 41	50.45 69	94.28 23	74.37 102	79.31 106	91.52 72

MVS_Test		75.85 88	74.93 96	78.62 75	84.08 99	55.20 70	83.99 218	85.17 143	68.07 67	73.38 79	82.76 268	50.44 70	89.00 177	65.90 178	80.61 85	91.64 65

FC-MVSNet-test		67.49 276	67.91 229	66.21 387	76.06 322	33.06 449	80.82 317	87.18 83	64.44 133	54.81 353	82.87 265	50.40 71	82.60 360	48.05 350	66.55 269	82.98 328

nrg030		72.27 169	71.56 158	74.42 226	75.93 328	50.60 215	86.97 95	83.21 213	62.75 179	67.15 164	84.38 240	50.07 72	86.66 286	71.19 136	62.37 317	85.99 257

fmvsm_l_conf0.5_n		75.95 84	76.16 68	75.31 197	76.01 326	48.44 286	84.98 180	71.08 417	63.50 161	81.70 21	93.52 23	50.00 73	87.18 266	87.80 6	76.87 137	90.32 127

cl22		68.85 244	67.69 239	72.35 296	78.07 281	49.98 237	82.45 272	78.48 323	62.50 186	58.46 306	77.95 334	49.99 74	85.17 329	62.55 212	58.72 345	81.90 340

fmvsm_l_conf0.5_n_a		75.88 87	76.07 70	75.31 197	76.08 321	48.34 289	85.24 163	70.62 420	63.13 169	81.45 22	93.62 22	49.98 75	87.40 261	87.76 7	76.77 139	90.20 132

tpmrst		71.04 196	69.77 197	74.86 215	83.19 121	55.86 52	75.64 368	78.73 316	67.88 70	64.99 195	73.73 385	49.96 76	79.56 396	65.92 177	67.85 259	89.14 170

CANet		80.90 11	81.17 12	80.09 41	87.62 43	54.21 116	91.60 14	86.47 102	73.13 9	79.89 33	93.10 34	49.88 77	92.98 39	84.09 24	84.75 54	93.08 20

ET-MVSNet_ETH3D		75.23 106	74.08 113	78.67 71	84.52 87	55.59 53	88.92 49	89.21 32	68.06 68	53.13 370	90.22 112	49.71 78	87.62 252	72.12 133	70.82 227	92.82 26

c3_l		67.97 264	66.66 263	71.91 314	76.20 320	49.31 258	82.13 278	78.00 331	61.99 194	57.64 319	76.94 352	49.41 79	84.93 334	60.62 231	57.01 368	81.49 346

Vis-MVSNet (Re-imp)		65.52 315	65.63 287	65.17 397	77.49 293	30.54 458	75.49 373	77.73 338	59.34 245	52.26 377	86.69 201	49.38 80	80.53 383	37.07 400	75.28 170	84.42 285

EPNet		78.36 32	78.49 27	77.97 103	85.49 69	52.04 174	89.36 41	84.07 193	73.22 8	77.03 52	91.72 72	49.32 81	90.17 130	73.46 117	82.77 65	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	75.98 170	77.54 292	47.77 318	86.35 114	73.46 398	68.69 58	81.07 25	94.40 5	49.06 82	88.89 186	87.39 8	79.32 105	91.27 87

testing3		59.97 360	60.19 350	59.32 431	77.60 289	30.01 464	81.75 290	81.79 241	53.54 353	50.34 396	79.94 312	48.99 83	76.91 420	17.19 479	50.59 409	71.03 454

E3new		76.85 60	76.24 66	78.66 72	81.62 176	55.01 78	86.94 97	85.10 152	71.55 22	71.93 104	88.61 149	48.40 84	89.60 152	74.50 100	77.53 128	91.36 79

tpm		68.36 256	67.48 246	70.97 330	79.93 232	51.34 197	76.58 365	78.75 315	67.73 73	63.54 231	74.86 375	48.33 85	72.36 447	53.93 302	63.71 297	89.21 167

APDe-MVS		78.44 29	78.20 29	79.19 51	88.56 28	54.55 109	89.76 33	87.77 71	55.91 324	78.56 43	92.49 53	48.20 86	92.65 48	79.49 56	83.04 64	90.39 123
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 74	76.81 55	74.71 219	79.21 252	46.90 333	85.03 177	73.96 387	69.00 56	79.70 36	93.88 12	48.07 87	87.71 246	84.26 21	78.15 119	89.50 158

MG-MVS		78.42 30	76.99 51	82.73 3	93.17 1	64.46 1	89.93 29	88.51 56	64.83 130	73.52 77	88.09 167	48.07 87	92.19 61	62.24 216	84.53 56	91.53 71

DeepC-MVS	67.15 4	76.90 58	76.27 65	78.80 65	80.70 208	55.02 77	86.39 112	86.71 95	66.96 90	67.91 159	89.97 120	48.03 89	91.41 79	75.60 89	84.14 58	89.96 145
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 75	81.14 192	54.95 81	86.88 101	85.04 154	71.37 26	71.76 106	88.44 152	48.02 90	89.57 154	74.17 106	77.23 130	91.33 83

MGCFI-Net		74.07 127	74.64 106	72.34 297	82.90 134	43.33 392	80.04 332	79.96 281	65.61 114	74.93 62	91.85 68	48.01 91	80.86 375	71.41 135	77.10 131	92.84 25

test_prior2							89.04 48		61.88 197	73.55 76	91.46 81	48.01 91		74.73 97	85.46 43

myMVS_eth3d		63.52 334	63.56 315	63.40 409	81.73 167	34.28 441	80.97 313	81.02 256	60.93 217	55.06 349	82.64 273	48.00 93	80.81 376	23.42 464	58.32 349	75.10 425

balanced_ft_v1		75.25 104	73.90 117	79.29 49	85.59 66	56.72 34	74.35 383	87.27 80	60.24 228	59.07 287	85.17 225	47.76 94	90.51 116	82.62 35	83.06 63	90.64 114

SF-MVS		77.64 44	77.42 43	78.32 96	83.75 107	52.47 163	86.63 110	87.80 68	58.78 262	74.63 65	92.38 55	47.75 95	91.35 80	78.18 71	86.85 28	91.15 93

test2506		72.91 150	72.43 140	74.32 232	80.12 229	44.18 381	83.19 247	84.77 168	64.02 143	65.97 177	87.43 189	47.67 96	88.72 192	59.08 244	79.66 101	90.08 141

E2		76.39 71	75.67 75	78.56 82	80.49 216	54.87 93	86.80 104	84.95 158	71.09 28	71.51 112	88.21 163	47.55 97	89.53 155	73.65 113	76.77 139	91.29 84

E3		76.39 71	75.67 75	78.56 82	80.49 216	54.87 93	86.80 104	84.95 158	71.09 28	71.51 112	88.21 163	47.55 97	89.53 155	73.65 113	76.77 139	91.29 84

fmvsm_s_conf0.5_n_3		74.97 112	75.42 83	73.62 257	76.99 305	46.67 338	83.13 250	71.14 416	66.20 103	82.13 14	93.76 17	47.49 99	84.00 345	81.95 40	76.02 153	90.19 134

1112_ss		70.05 217	69.37 203	72.10 302	80.77 207	42.78 398	85.12 173	76.75 355	59.69 237	61.19 257	92.12 59	47.48 100	83.84 347	53.04 310	68.21 254	89.66 151

fmvsm_s_conf0.5_n_10		76.80 61	76.81 55	76.78 149	78.91 262	47.85 313	83.44 236	74.66 378	68.93 57	81.31 23	94.12 7	47.44 101	90.82 104	83.43 28	79.06 110	91.66 64

Effi-MVS+		75.24 105	73.61 121	80.16 36	81.92 162	57.42 22	85.21 165	76.71 358	60.68 223	73.32 80	89.34 131	47.30 102	91.63 73	68.28 160	79.72 100	91.42 76

UniMVSNet (Re)		67.71 270	66.80 259	70.45 337	74.44 352	42.93 396	82.42 273	84.90 162	63.69 156	59.63 274	80.99 302	47.18 103	85.23 328	51.17 329	56.75 369	83.19 322

test12				79.24 50	86.89 49	56.08 47		85.16 145		72.27 98		47.15 104	91.10 91		85.93 38	90.54 120

PVSNet_Blended_VisFu		73.40 143	72.44 139	76.30 155	81.32 190	54.70 102	85.81 133	78.82 312	63.70 155	64.53 206	85.38 223	47.11 105	87.38 262	67.75 164	77.55 125	86.81 242

fmvsm_s_conf0.5_n_8		76.50 69	76.68 60	75.94 171	78.67 267	47.92 311	85.18 167	74.71 377	68.09 64	80.67 28	94.26 6	47.09 106	89.26 165	86.62 10	74.85 180	90.65 113

test_fmvsm_n_1920		75.56 99	75.54 80	75.61 181	74.60 351	49.51 252	81.82 287	74.08 384	66.52 96	80.40 30	93.46 25	46.95 107	89.72 144	86.69 9	75.30 169	87.61 216

NCCC		79.57 20	79.23 21	80.59 25	89.50 16	56.99 27	91.38 16	88.17 62	67.71 74	73.81 74	92.75 47	46.88 108	93.28 35	78.79 64	84.07 59	91.50 75

viewmanbaseed2359cas		76.71 65	76.16 68	78.37 95	81.16 191	55.05 76	86.96 96	85.32 134	71.71 19	72.25 99	88.50 151	46.86 109	88.96 181	74.55 99	78.08 120	91.08 95

E4		75.99 82	75.16 89	78.48 87	79.56 242	54.74 98	86.66 109	84.80 166	70.62 32	71.16 122	87.90 175	46.84 110	89.47 159	72.70 124	76.20 152	91.23 88

fmvsm_s_conf0.5_n_6		76.17 77	76.84 54	74.15 237	77.42 295	46.46 344	85.53 153	77.86 335	69.78 48	79.78 35	92.90 43	46.80 111	84.81 336	84.67 19	76.86 138	91.17 92

9.14			78.19 30		85.67 64		88.32 57	88.84 42	59.89 232	74.58 67	92.62 50	46.80 111	92.66 47	81.40 48	85.62 42

VNet		77.99 39	77.92 34	78.19 99	87.43 45	50.12 233	90.93 22	91.41 8	67.48 78	75.12 60	90.15 116	46.77 113	91.00 96	73.52 115	78.46 115	93.44 10

PVSNet_BlendedMVS		73.42 142	73.30 124	73.76 251	85.91 59	51.83 182	86.18 119	84.24 188	65.40 120	69.09 148	80.86 304	46.70 114	88.13 222	75.43 90	65.92 279	81.33 354

PVSNet_Blended		76.53 68	76.54 61	76.50 153	85.91 59	51.83 182	88.89 50	84.24 188	67.82 72	69.09 148	89.33 133	46.70 114	88.13 222	75.43 90	81.48 78	89.55 154

0.3-1-1-0.015		72.75 154	71.06 169	77.81 108	80.58 213	50.62 213	89.45 37	88.60 53	63.74 154	65.56 185	81.82 293	46.61 116	90.64 112	62.86 210	60.35 329	92.17 42

SMA-MVS		79.10 25	78.76 26	80.12 39	84.42 88	55.87 51	87.58 79	86.76 94	61.48 205	80.26 31	93.10 34	46.53 117	92.41 54	79.97 55	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	77.32 124	81.66 173	52.32 167	89.31 42	82.11 231	72.20 14	73.23 82	91.05 83	46.52 118	91.00 96	76.23 82	80.83 82	88.64 183

SymmetryMVS		77.43 48	77.09 48	78.44 91	82.56 146	52.32 167	89.31 42	84.15 191	72.20 14	73.23 82	91.05 83	46.52 118	91.00 96	76.23 82	78.55 114	92.00 51

viewdifsd2359ckpt07		74.81 116	74.01 116	77.21 131	79.62 240	53.13 147	85.70 146	83.75 199	68.12 63	68.14 157	87.33 192	46.51 120	87.92 229	73.32 118	73.63 191	90.57 117

test_fmvsmconf_n		74.41 120	74.05 114	75.49 189	74.16 359	48.38 287	82.66 261	72.57 402	67.05 87	75.11 61	92.88 44	46.35 121	87.81 236	83.93 25	71.71 215	90.28 128

fmvsm_l_conf0.5_n_3		75.73 97	75.78 73	75.61 181	76.03 324	48.33 291	85.34 157	72.92 401	67.16 81	78.55 44	93.85 15	46.22 122	87.53 255	85.61 14	76.30 149	90.98 103

tpm cat1		66.28 306	62.78 318	76.77 150	81.40 187	57.14 25	70.03 417	77.19 347	53.00 358	58.76 296	70.73 422	46.17 123	86.73 284	43.27 377	64.46 291	86.44 249

fmvsm_s_conf0.5_n_4		74.92 113	74.88 97	75.03 209	75.96 327	47.53 321	85.84 132	73.19 400	67.07 85	79.43 38	92.60 51	46.12 124	88.03 227	84.70 18	69.01 245	89.53 156

cl____		67.43 278	65.93 280	71.95 311	76.33 315	48.02 304	82.58 264	79.12 305	61.30 208	56.72 335	76.92 353	46.12 124	86.44 294	57.98 261	56.31 372	81.38 353

viewdifsd2359ckpt13		75.96 83	75.07 91	78.65 74	81.14 192	55.21 67	86.15 120	84.95 158	69.98 43	70.49 138	88.16 165	46.10 126	89.86 137	72.39 127	76.23 151	90.89 107

DIV-MVS_self_test		67.43 278	65.93 280	71.94 312	76.33 315	48.01 305	82.57 265	79.11 306	61.31 207	56.73 334	76.92 353	46.09 127	86.43 295	57.98 261	56.31 372	81.39 352

0.4-1-1-0.2		72.79 153	71.07 168	77.94 106	80.58 213	50.83 209	89.59 35	88.63 49	63.94 149	65.74 183	81.80 294	46.05 128	90.68 108	62.98 209	60.35 329	92.31 38

IS-MVSNet		68.80 248	67.55 243	72.54 288	78.50 274	43.43 389	81.03 311	79.35 301	59.12 255	57.27 328	86.71 200	46.05 128	87.70 247	44.32 373	75.60 166	86.49 248

diffmvs		75.11 109	74.65 105	76.46 154	78.52 273	53.35 137	83.28 244	79.94 282	70.51 35	71.64 108	88.72 142	46.02 130	86.08 308	77.52 75	75.75 164	89.96 145
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		74.92 113	73.70 120	78.60 79	80.28 225	54.94 82	84.77 190	80.56 269	69.96 45	69.38 143	88.38 154	46.01 131	90.50 117	72.44 126	71.49 219	90.38 124

0.4-1-1-0.1		72.39 161	70.70 174	77.46 120	80.45 219	50.04 235	89.09 47	88.45 58	63.06 170	64.91 198	81.60 298	45.98 132	90.46 118	62.40 213	60.34 331	91.88 55

E6new		75.74 93	74.80 101	78.56 82	79.85 233	54.92 88	85.87 128	84.72 171	70.19 39	70.90 125	87.73 182	45.98 132	89.71 145	72.16 129	75.78 161	91.06 97

E6		75.74 93	74.80 101	78.56 82	79.85 233	54.92 88	85.87 128	84.72 171	70.19 39	70.90 125	87.73 182	45.98 132	89.71 145	72.16 129	75.78 161	91.06 97

E5new		75.74 93	74.80 101	78.57 80	79.85 233	54.93 83	85.87 128	84.72 171	70.19 39	70.90 125	87.74 180	45.97 135	89.71 145	72.15 131	75.79 158	91.06 97

E5		75.74 93	74.80 101	78.57 80	79.85 233	54.93 83	85.87 128	84.72 171	70.19 39	70.90 125	87.74 180	45.97 135	89.71 145	72.15 131	75.79 158	91.06 97

blend_shiyan4		67.33 283	65.28 296	73.45 262	70.71 400	47.96 308	86.21 118	85.65 123	56.45 316	52.18 378	72.99 395	45.89 137	88.50 205	56.81 276	60.68 327	83.90 302

EI-MVSNet		69.70 229	68.70 215	72.68 284	75.00 345	48.90 269	79.54 341	87.16 84	61.05 213	63.88 219	83.74 251	45.87 138	90.44 119	57.42 272	64.68 290	78.70 382

IterMVS-LS		66.63 299	65.36 295	70.42 338	75.10 343	48.90 269	81.45 306	76.69 359	61.05 213	55.71 345	77.10 349	45.86 139	83.65 351	57.44 271	57.88 361	78.70 382
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs_AUTHOR		74.80 117	74.30 110	76.29 156	77.34 296	53.19 143	83.17 249	79.50 294	69.93 46	71.55 110	88.57 150	45.85 140	86.03 310	77.17 78	75.64 165	89.67 150

EIA-MVS		75.92 85	75.18 88	78.13 100	85.14 76	51.60 190	87.17 91	85.32 134	64.69 131	68.56 152	90.53 101	45.79 141	91.58 75	67.21 167	82.18 71	91.20 90

MVS		76.91 56	75.48 81	81.23 20	84.56 86	55.21 67	80.23 329	91.64 4	58.65 264	65.37 187	91.48 80	45.72 142	95.05 17	72.11 134	89.52 10	93.44 10

PAPM_NR		71.80 179	69.98 195	77.26 129	81.54 182	53.34 138	78.60 352	85.25 140	53.46 354	60.53 265	88.66 144	45.69 143	89.24 166	56.49 280	79.62 103	89.19 168

UWE-MVS-28		67.43 278	67.98 228	65.75 390	75.66 332	34.74 439	80.00 335	88.17 62	64.21 139	57.27 328	84.14 245	45.68 144	78.82 399	44.33 371	72.40 207	83.70 310

viewmambaseed2359dif		73.51 141	72.78 133	75.71 178	76.93 307	51.89 180	82.81 258	79.66 289	65.46 116	70.29 139	88.05 170	45.55 145	85.85 318	73.49 116	72.76 203	89.39 161

CS-MVS		76.77 62	76.70 59	76.99 138	83.55 109	48.75 274	88.60 54	85.18 142	66.38 99	72.47 95	91.62 76	45.53 146	90.99 100	74.48 101	82.51 67	91.23 88

DeepC-MVS_fast	67.50 3	78.00 38	77.63 38	79.13 55	88.52 29	55.12 72	89.95 28	85.98 113	68.31 60	71.33 117	92.75 47	45.52 147	90.37 121	71.15 137	85.14 47	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		74.48 118	74.12 112	75.56 184	76.96 306	47.85 313	85.32 161	69.80 427	64.16 141	78.74 41	93.48 24	45.51 148	89.29 164	86.48 11	66.62 267	89.55 154

viewmacassd2359aftdt		75.91 86	75.14 90	78.21 98	79.40 246	54.82 95	86.71 107	84.98 156	70.89 31	71.52 111	87.89 176	45.43 149	88.85 190	72.35 128	77.08 132	90.97 104

fmvsm_s_conf0.5_n_5		75.02 110	75.07 91	74.88 214	74.33 356	47.83 315	83.99 218	73.54 393	67.10 83	76.32 56	92.43 54	45.42 150	86.35 298	82.98 31	79.50 104	90.47 122

fmvsm_s_conf0.5_n_a		73.68 138	73.15 126	75.29 200	75.45 335	48.05 303	83.88 223	68.84 432	63.43 163	78.60 42	93.37 29	45.32 151	88.92 185	85.39 15	64.04 293	88.89 175

Test_1112_low_res		67.18 287	66.23 272	70.02 347	78.75 265	41.02 416	83.43 237	73.69 390	57.29 292	58.45 307	82.39 280	45.30 152	80.88 374	50.50 331	66.26 277	88.16 200

ETV-MVS		77.17 51	76.74 58	78.48 87	81.80 165	54.55 109	86.13 121	85.33 133	68.20 62	73.10 84	90.52 102	45.23 153	90.66 110	79.37 57	80.95 79	90.22 130

SPE-MVS-test		77.20 50	77.25 45	77.05 133	84.60 85	49.04 264	89.42 38	85.83 117	65.90 112	72.85 88	91.98 67	45.10 154	91.27 83	75.02 96	84.56 55	90.84 108

NR-MVSNet		67.25 285	65.99 278	71.04 329	73.27 368	43.91 383	85.32 161	84.75 169	66.05 110	53.65 368	82.11 288	45.05 155	85.97 315	47.55 352	56.18 375	83.24 320

UWE-MVS		72.17 170	72.15 148	72.21 299	82.26 151	44.29 378	86.83 103	89.58 26	65.58 115	65.82 180	85.06 228	45.02 156	84.35 341	54.07 300	75.18 171	87.99 207

train_agg		76.91 56	76.40 63	78.45 90	85.68 62	55.42 58	87.59 77	84.00 194	57.84 279	72.99 85	90.98 87	44.99 157	88.58 198	78.19 69	85.32 45	91.34 82

test_8					85.72 61	55.31 63	87.60 76	83.88 197	57.84 279	72.84 89	90.99 86	44.99 157	88.34 213

segment_acmp												44.97 159

test_fmvsmconf0.1_n		73.69 137	73.15 126	75.34 195	70.71 400	48.26 294	82.15 276	71.83 408	66.75 92	74.47 69	92.59 52	44.89 160	87.78 243	83.59 27	71.35 222	89.97 144

TEST9					85.68 62	55.42 58	87.59 77	84.00 194	57.72 281	72.99 85	90.98 87	44.87 161	88.58 198

eth_miper_zixun_eth		66.98 294	65.28 296	72.06 304	75.61 333	50.40 222	81.00 312	76.97 354	62.00 193	56.99 332	76.97 351	44.84 162	85.58 320	58.75 249	54.42 391	80.21 370

MVSFormer		73.53 140	72.19 147	77.57 115	83.02 128	55.24 65	81.63 295	81.44 249	50.28 378	76.67 53	90.91 93	44.82 163	86.11 303	60.83 228	80.09 93	91.36 79

lupinMVS		78.38 31	78.11 31	79.19 51	83.02 128	55.24 65	91.57 15	84.82 164	69.12 54	76.67 53	92.02 63	44.82 163	90.23 128	80.83 50	80.09 93	92.08 44

WR-MVS		67.58 273	66.76 260	70.04 346	75.92 329	45.06 372	86.23 117	85.28 138	64.31 136	58.50 304	81.00 301	44.80 165	82.00 367	49.21 341	55.57 383	83.06 325

fmvsm_s_conf0.1_n		73.80 133	73.26 125	75.43 190	73.28 367	47.80 316	84.57 200	69.43 429	63.34 164	78.40 45	93.29 31	44.73 166	89.22 168	85.99 12	66.28 276	89.26 164

ZD-MVS					89.55 15	53.46 130		84.38 182	57.02 297	73.97 72	91.03 85	44.57 167	91.17 88	75.41 93	81.78 76

Fast-Effi-MVS+		72.73 155	71.15 167	77.48 118	82.75 140	54.76 97	86.77 106	80.64 265	63.05 171	65.93 178	84.01 246	44.42 168	89.03 175	56.45 283	76.36 147	88.64 183

fmvsm_s_conf0.1_n_a		72.82 152	72.05 152	75.12 206	70.95 398	47.97 306	82.72 260	68.43 434	62.52 185	78.17 46	93.08 37	44.21 169	88.86 187	84.82 17	63.54 300	88.54 191

PCF-MVS	61.03 10	70.10 215	68.40 221	75.22 205	77.15 303	51.99 176	79.30 346	82.12 230	56.47 315	61.88 251	86.48 206	43.98 170	87.24 265	55.37 293	72.79 202	86.43 250
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CDS-MVSNet		70.48 209	69.43 201	73.64 255	77.56 291	48.83 271	83.51 233	77.45 343	63.27 166	62.33 242	85.54 220	43.85 171	83.29 357	57.38 273	74.00 185	88.79 179
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EI-MVSNet-Vis-set		73.19 146	72.60 136	74.99 212	82.56 146	49.80 242	82.55 267	89.00 35	66.17 104	65.89 179	88.98 137	43.83 172	92.29 58	65.38 188	69.01 245	82.87 330

APD-MVS		76.15 78	75.68 74	77.54 117	88.52 29	53.44 133	87.26 89	85.03 155	53.79 351	74.91 63	91.68 74	43.80 173	90.31 124	74.36 103	81.82 74	88.87 176
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_HR		76.39 71	75.38 85	79.42 47	85.33 73	56.47 40	88.15 59	84.97 157	65.15 128	66.06 176	89.88 121	43.79 174	92.16 62	75.03 95	80.03 96	89.64 152

thres100view900		66.87 296	65.42 294	71.24 324	83.29 118	43.15 394	81.67 294	87.78 69	59.04 256	55.92 344	82.18 287	43.73 175	87.80 239	28.80 441	66.36 273	82.78 332

thres600view7		66.46 303	65.12 300	70.47 336	83.41 112	43.80 385	82.15 276	87.78 69	59.37 244	56.02 343	82.21 286	43.73 175	86.90 276	26.51 453	64.94 284	80.71 364

v148		68.24 261	66.35 268	73.88 246	71.76 386	51.47 194	84.23 209	81.90 240	63.69 156	58.94 289	76.44 360	43.72 177	87.78 243	60.63 230	55.86 380	82.39 335

SD-MVS		76.18 76	74.85 98	80.18 35	85.39 71	56.90 29	85.75 137	82.45 227	56.79 305	74.48 68	91.81 69	43.72 177	90.75 106	74.61 98	78.65 112	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		70.18 211	69.28 207	72.89 276	77.64 287	42.88 397	85.06 174	87.50 78	62.58 183	62.66 240	82.34 285	43.64 179	89.83 140	58.42 254	63.70 298	85.96 259

tfpn200view9		67.57 274	66.13 274	71.89 315	84.05 100	45.07 369	83.40 239	87.71 74	60.79 220	57.79 315	82.76 268	43.53 180	87.80 239	28.80 441	66.36 273	82.78 332

thres400		67.40 282	66.13 274	71.19 326	84.05 100	45.07 369	83.40 239	87.71 74	60.79 220	57.79 315	82.76 268	43.53 180	87.80 239	28.80 441	66.36 273	80.71 364

PAPR		75.20 107	74.13 111	78.41 92	88.31 34	55.10 74	84.31 207	85.66 121	63.76 153	67.55 161	90.73 98	43.48 182	89.40 160	66.36 173	77.03 133	90.73 111

kuosan		50.20 424	50.09 409	50.52 450	73.09 370	29.09 471	65.25 433	74.89 375	48.27 393	41.34 442	60.85 459	43.45 183	67.48 457	18.59 477	25.07 480	55.01 475

fmvsm_s_conf0.5_n_7		73.10 147	73.89 119	70.72 333	74.17 358	46.03 357	83.28 244	74.19 382	67.10 83	73.94 73	91.73 71	43.42 184	77.61 415	83.92 26	73.26 195	88.53 192

MP-MVS		74.99 111	74.33 109	76.95 140	82.89 135	53.05 150	85.63 147	83.50 207	57.86 278	67.25 163	90.24 110	43.38 185	88.85 190	76.03 84	82.23 70	88.96 173
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
casdiffseed414692147		74.22 123	72.73 134	78.69 69	79.85 233	54.64 107	85.13 169	83.67 205	69.07 55	69.41 142	86.47 207	43.27 186	90.69 107	63.77 202	73.91 189	90.73 111

EI-MVSNet-UG-set		72.37 163	71.73 155	74.29 233	81.60 178	49.29 259	81.85 285	88.64 48	65.29 125	65.05 192	88.29 160	43.18 187	91.83 69	63.74 203	67.97 257	81.75 342

thres200		68.71 250	67.27 251	73.02 270	84.73 82	46.76 337	85.03 177	87.73 72	62.34 189	59.87 269	83.45 258	43.15 188	88.32 215	31.25 433	67.91 258	83.98 298

PHI-MVS		77.49 46	77.00 50	78.95 59	85.33 73	50.69 212	88.57 55	88.59 54	58.14 271	73.60 75	93.31 30	43.14 189	93.79 30	73.81 111	88.53 13	92.37 35

ab-mvs		70.65 205	69.11 210	75.29 200	80.87 203	46.23 355	73.48 390	85.24 141	59.99 231	66.65 167	80.94 303	43.13 190	88.69 193	63.58 204	68.07 255	90.95 105

CDPH-MVS		76.05 81	75.19 87	78.62 75	86.51 53	54.98 80	87.32 84	84.59 178	58.62 265	70.75 130	90.85 95	43.10 191	90.63 113	70.50 141	84.51 57	90.24 129

reproduce_monomvs		69.71 225	68.52 218	73.29 267	86.43 55	48.21 296	83.91 221	86.17 110	68.02 69	54.91 351	77.46 342	42.96 192	88.86 187	68.44 158	48.38 420	82.80 331

v8		67.25 285	64.99 302	74.04 240	72.89 374	53.31 140	82.37 274	80.11 278	61.54 203	54.29 361	76.02 369	42.89 193	88.41 209	58.43 252	56.36 370	80.39 368

EC-MVSNet		75.30 101	75.20 86	75.62 180	80.98 197	49.00 265	87.43 80	84.68 176	63.49 162	70.97 124	90.15 116	42.86 194	91.14 90	74.33 104	81.90 73	86.71 243

h-mvs33		73.95 129	72.89 132	77.15 132	80.17 228	50.37 226	84.68 194	83.33 208	68.08 65	71.97 102	88.65 147	42.50 195	91.15 89	78.82 62	57.78 363	89.91 147

hse-mvs2		71.44 187	70.68 175	73.73 253	76.34 314	47.44 326	79.45 344	79.47 296	68.08 65	71.97 102	86.01 215	42.50 195	86.93 275	78.82 62	53.46 401	86.83 240

SteuartSystems-ACMMP		77.08 54	76.33 64	79.34 48	80.98 197	55.31 63	89.76 33	86.91 89	62.94 173	71.65 107	91.56 78	42.33 197	92.56 51	77.14 79	83.69 61	90.15 135
Skip Steuart: Steuart Systems R&D Blog.
HyFIR lowres test		69.94 222	67.58 241	77.04 134	77.11 304	57.29 23	81.49 305	79.11 306	58.27 269	58.86 293	80.41 307	42.33 197	86.96 273	61.91 219	68.68 252	86.87 234

ZNCC-MVS		75.82 91	75.02 94	78.23 97	83.88 105	53.80 123	86.91 100	86.05 112	59.71 236	67.85 160	90.55 100	42.23 199	91.02 94	72.66 125	85.29 46	89.87 148

FMVSNet3		68.84 245	67.40 247	73.19 269	85.05 77	48.53 281	85.71 143	85.36 131	60.90 219	57.58 320	79.15 325	42.16 200	86.77 282	47.25 355	63.40 301	84.27 289

VPA-MVSNet		71.12 192	70.66 176	72.49 290	78.75 265	44.43 376	87.64 71	90.02 21	63.97 147	65.02 193	81.58 299	42.14 201	87.42 259	63.42 205	63.38 304	85.63 267

jason		77.01 55	76.45 62	78.69 69	79.69 239	54.74 98	90.56 24	83.99 196	68.26 61	74.10 71	90.91 93	42.14 201	89.99 133	79.30 58	79.12 107	91.36 79
jason: jason.
CLD-MVS		75.60 98	75.39 84	76.24 158	80.69 209	52.40 164	90.69 23	86.20 108	74.40 6	65.01 194	88.93 138	42.05 203	90.58 114	76.57 81	73.96 186	85.73 263
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 88	74.83 99	78.91 60	88.08 39	51.94 177	91.30 17	89.28 30	57.91 276	71.19 119	89.20 134	42.03 204	92.77 44	69.41 148	75.07 176	92.01 49

DCV-MVSNet		75.85 88	74.83 99	78.91 60	88.08 39	51.94 177	91.30 17	89.28 30	57.91 276	71.19 119	89.20 134	42.03 204	92.77 44	69.41 148	75.07 176	92.01 49

TAMVS		69.51 233	68.16 226	73.56 259	76.30 317	48.71 277	82.57 265	77.17 348	62.10 191	61.32 256	84.23 243	41.90 206	83.46 354	54.80 297	73.09 199	88.50 194

TransMVSNet (Re)		62.82 342	60.76 343	69.02 355	73.98 361	41.61 410	86.36 113	79.30 304	56.90 298	52.53 373	76.44 360	41.85 207	87.60 253	38.83 393	40.61 449	77.86 396

VPNet		72.07 171	71.42 162	74.04 240	78.64 271	47.17 331	89.91 31	87.97 66	72.56 12	64.66 201	85.04 231	41.83 208	88.33 214	61.17 226	60.97 325	86.62 244

v2v482		69.55 232	67.64 240	75.26 204	72.32 381	53.83 122	84.93 184	81.94 236	65.37 122	60.80 261	79.25 323	41.62 209	88.98 180	63.03 208	59.51 338	82.98 328

API-MVS		74.17 125	72.07 151	80.49 26	90.02 12	58.55 10	87.30 86	84.27 185	57.51 287	65.77 182	87.77 179	41.61 210	95.97 12	51.71 324	82.63 66	86.94 232

GeoE		69.96 221	67.88 233	76.22 159	81.11 195	51.71 188	84.15 212	76.74 357	59.83 233	60.91 259	84.38 240	41.56 211	88.10 224	51.67 325	70.57 230	88.84 177

CHOSEN 1792x2688		76.24 75	74.03 115	82.88 2	83.09 124	62.84 2	85.73 141	85.39 130	69.79 47	64.87 199	83.49 257	41.52 212	93.69 34	70.55 139	81.82 74	92.12 43

LFMVS		78.52 27	77.14 47	82.67 4	89.58 14	58.90 8	91.27 19	88.05 65	63.22 167	74.63 65	90.83 96	41.38 213	94.40 21	75.42 92	79.90 98	94.72 2

MAR-MVS		76.76 63	75.60 78	80.21 33	90.87 8	54.68 104	89.14 46	89.11 33	62.95 172	70.54 136	92.33 56	41.05 214	94.95 18	57.90 265	86.55 33	91.00 102
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		43.51 434	44.07 435	41.82 461	63.75 451	21.90 484	63.80 439	72.05 406	39.59 440	33.35 471	54.54 471	41.04 215	57.30 473	10.75 488	17.77 489	46.26 483

test_fmvsmvis_n_1920		71.29 188	70.38 184	74.00 242	71.04 397	48.79 273	79.19 347	64.62 444	62.75 179	66.73 165	91.99 65	40.94 216	88.35 212	83.00 30	73.18 196	84.85 281

GST-MVS		74.87 115	73.90 117	77.77 110	83.30 117	53.45 132	85.75 137	85.29 137	59.22 249	66.50 172	89.85 122	40.94 216	90.76 105	70.94 138	83.35 62	89.10 171

usedtu_dtu_shiyan1		69.05 239	67.91 229	72.46 292	75.40 336	46.24 353	85.74 139	86.80 91	65.23 126	58.75 297	80.31 308	40.90 218	86.83 278	53.29 305	64.77 285	84.31 287

FE-MVSNET3		69.05 239	67.91 229	72.46 292	75.39 337	46.24 353	85.74 139	86.80 91	65.23 126	58.75 297	80.31 308	40.90 218	86.83 278	53.29 305	64.77 285	84.31 287

DU-MVS		66.84 297	65.74 285	70.16 342	73.27 368	42.59 400	81.50 303	82.92 220	63.53 160	58.51 302	82.11 288	40.75 220	84.64 339	53.11 308	55.96 378	83.24 320

Baseline_NR-MVSNet		65.49 317	64.27 310	69.13 354	74.37 355	41.65 409	83.39 241	78.85 310	59.56 239	59.62 275	76.88 355	40.75 220	87.44 258	49.99 333	55.05 385	78.28 391

miper_lstm_enhance		63.91 329	62.30 323	68.75 361	75.06 344	46.78 336	69.02 421	81.14 254	59.68 238	52.76 372	72.39 403	40.71 222	77.99 409	56.81 276	53.09 402	81.48 348

HFP-MVS		74.37 121	73.13 130	78.10 101	84.30 94	53.68 126	85.58 148	84.36 183	56.82 303	65.78 181	90.56 99	40.70 223	90.90 102	69.18 152	80.88 80	89.71 149

RRT-MVS		73.29 144	71.37 163	79.07 58	84.63 84	54.16 119	78.16 354	86.64 99	61.67 200	60.17 267	82.35 284	40.63 224	92.26 60	70.19 143	77.87 122	90.81 109

CL-MVSNet_self_test		62.98 340	61.14 340	68.50 367	65.86 438	42.96 395	84.37 203	82.98 218	60.98 215	53.95 364	72.70 399	40.43 225	83.71 350	41.10 386	47.93 424	78.83 381

ACMMP_NAP		76.43 70	75.66 77	78.73 67	81.92 162	54.67 105	84.06 216	85.35 132	61.10 212	72.99 85	91.50 79	40.25 226	91.00 96	76.84 80	86.98 26	90.51 121

v1144		68.81 247	66.82 258	74.80 217	72.34 380	53.46 130	84.68 194	81.77 243	64.25 138	60.28 266	77.91 335	40.23 227	88.95 182	60.37 237	59.52 337	81.97 338

WR-MVS_H		58.91 372	58.04 364	61.54 422	69.07 422	33.83 446	76.91 361	81.99 235	51.40 371	48.17 405	74.67 376	40.23 227	74.15 435	31.78 430	48.10 422	76.64 411

原ACMM1				76.13 164	84.89 81	54.59 108		85.26 139	51.98 365	66.70 166	87.07 196	40.15 229	89.70 149	51.23 328	85.06 52	84.10 292

MVP-Stereo		70.97 197	70.44 180	72.59 287	76.03 324	51.36 196	85.02 179	86.99 88	60.31 227	56.53 339	78.92 327	40.11 230	90.00 132	60.00 240	90.01 7	76.41 414
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v10		66.61 300	64.20 311	73.83 249	72.59 377	53.37 136	81.88 284	79.91 284	61.11 211	54.09 363	75.60 371	40.06 231	88.26 220	56.47 281	56.10 376	79.86 374

test_fmvsmconf0.01_n		71.97 174	70.95 172	75.04 208	66.21 435	47.87 312	80.35 326	70.08 424	65.85 113	72.69 90	91.68 74	39.99 232	87.67 248	82.03 39	69.66 241	89.58 153

MP-MVS-pluss		75.54 100	75.03 93	77.04 134	81.37 188	52.65 160	84.34 206	84.46 181	61.16 209	69.14 147	91.76 70	39.98 233	88.99 179	78.19 69	84.89 53	89.48 160
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TranMVSNet+NR-MVSNet		66.94 295	65.61 288	70.93 331	73.45 364	43.38 390	83.02 255	84.25 186	65.31 124	58.33 309	81.90 292	39.92 234	85.52 321	49.43 338	54.89 387	83.89 303

Patchmatch-test		53.33 408	48.17 421	68.81 359	73.31 365	42.38 404	42.98 478	58.23 458	32.53 463	38.79 453	70.77 420	39.66 235	73.51 441	25.18 456	52.06 406	90.55 118

viewdifsd2359ckpt11		70.68 203	69.10 211	75.40 191	75.33 339	50.85 207	81.57 299	78.00 331	66.99 88	64.96 196	85.52 221	39.52 236	86.81 280	68.86 155	61.15 324	88.56 189

viewmsd2359difaftdt		70.68 203	69.10 211	75.40 191	75.33 339	50.85 207	81.57 299	78.00 331	66.99 88	64.96 196	85.52 221	39.52 236	86.81 280	68.86 155	61.16 323	88.56 189

Test By Simon												39.38 238

v144192		67.86 266	65.76 284	74.16 236	71.68 387	53.09 148	84.14 213	80.83 262	62.85 178	59.21 285	77.28 346	39.30 239	88.00 228	58.67 250	57.88 361	81.40 351

BH-w/o		70.02 218	68.51 219	74.56 222	82.77 139	50.39 223	86.60 111	78.14 329	59.77 235	59.65 273	85.57 219	39.27 240	87.30 263	49.86 335	74.94 179	85.99 257

dmvs_testset		57.65 383	58.21 363	55.97 442	74.62 350	9.82 502	63.75 440	63.34 450	67.23 80	48.89 403	83.68 256	39.12 241	76.14 427	23.43 462	59.80 336	81.96 339

CR-MVSNet		62.47 347	59.04 359	72.77 280	73.97 362	56.57 36	60.52 453	71.72 410	60.04 230	57.49 323	65.86 440	38.94 242	80.31 385	42.86 380	59.93 333	81.42 349

Patchmtry		56.56 389	52.95 396	67.42 374	72.53 378	50.59 216	59.05 457	71.72 410	37.86 448	46.92 417	65.86 440	38.94 242	80.06 389	36.94 402	46.72 434	71.60 450

sam_mvs1												38.86 244				88.13 203

UA-Net		67.32 284	66.23 272	70.59 335	78.85 263	41.23 415	73.60 388	75.45 371	61.54 203	66.61 169	84.53 239	38.73 245	86.57 291	42.48 383	74.24 184	83.98 298

cdsmvs_eth3d_5k		18.33 463	24.44 455	0.00 486	0.00 508	0.00 510	0.00 497	89.40 28	0.00 502	0.00 505	92.02 63	38.55 246	0.00 503	0.00 503	0.00 501	0.00 501

patchmatchnet-post											59.74 462	38.41 247	79.91 392

CHOSEN 280x420		57.53 385	56.38 377	60.97 427	74.01 360	48.10 301	46.30 473	54.31 465	48.18 395	50.88 393	77.43 344	38.37 248	59.16 471	54.83 295	63.14 309	75.66 418

lecture		74.14 126	73.05 131	77.44 121	81.66 173	50.39 223	87.43 80	84.22 190	51.38 372	72.10 100	90.95 92	38.31 249	93.23 37	70.51 140	80.83 82	88.69 181

SD_0403		65.51 316	65.18 299	66.48 386	78.37 277	29.94 465	74.64 380	78.55 321	66.47 97	54.87 352	84.35 242	38.20 250	82.47 361	38.90 392	72.30 210	87.05 230

V42		67.66 271	65.60 289	73.86 247	70.69 403	53.63 127	81.50 303	78.61 319	63.85 150	59.49 279	77.49 341	37.98 251	87.65 249	62.33 214	58.43 348	80.29 369

tpmvs		62.45 348	59.42 355	71.53 321	83.93 102	54.32 112	70.03 417	77.61 340	51.91 366	53.48 369	68.29 431	37.91 252	86.66 286	33.36 423	58.27 351	73.62 436

PatchmatchNet		67.07 292	63.63 314	77.40 122	83.10 122	58.03 12	72.11 408	77.77 337	58.85 260	59.37 280	70.83 419	37.84 253	84.93 334	42.96 379	69.83 240	89.26 164
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pcd_1.5k_mvsjas		3.15 470	4.20 473	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	0.00 504	37.77 254	0.00 503	0.00 503	0.00 501	0.00 501

PS-MVSNAJss		68.78 249	67.17 253	73.62 257	73.01 371	48.33 291	84.95 183	84.81 165	59.30 248	58.91 292	79.84 315	37.77 254	88.86 187	62.83 211	63.12 310	83.67 312

PS-MVSNAJ		80.06 17	79.52 18	81.68 15	85.58 67	60.97 3	91.69 12	87.02 87	70.62 32	80.75 27	93.22 33	37.77 254	92.50 52	82.75 33	86.25 36	91.57 69

pm-mvs1		64.12 327	62.56 321	68.78 360	71.68 387	38.87 426	82.89 257	81.57 246	55.54 330	53.89 365	77.82 337	37.73 257	86.74 283	48.46 348	53.49 399	80.72 363

RPMNet		59.29 364	54.25 389	74.42 226	73.97 362	56.57 36	60.52 453	76.98 351	35.72 457	57.49 323	58.87 465	37.73 257	85.26 327	27.01 452	59.93 333	81.42 349

IMVS_0403		72.39 161	70.59 178	77.79 109	82.26 151	50.87 203	81.76 288	85.16 145	62.91 174	64.87 199	86.07 209	37.71 259	92.40 55	64.03 197	70.55 231	90.09 137

SDMVSNet		71.89 176	70.62 177	75.70 179	81.70 169	51.61 189	73.89 385	88.72 46	66.58 93	61.64 253	82.38 281	37.63 260	89.48 157	77.44 76	65.60 280	86.01 255

xiu_mvs_v2_base		79.86 18	79.31 19	81.53 16	85.03 79	60.73 4	91.65 13	86.86 90	70.30 37	80.77 26	93.07 38	37.63 260	92.28 59	82.73 34	85.71 40	91.57 69

Patchmatch-RL test		58.72 375	54.32 388	71.92 313	63.91 450	44.25 379	61.73 449	55.19 463	57.38 291	49.31 401	54.24 472	37.60 262	80.89 373	62.19 217	47.28 429	90.63 115

HPM-MVS		72.60 157	71.50 159	75.89 172	82.02 158	51.42 195	80.70 320	83.05 216	56.12 323	64.03 215	89.53 127	37.55 263	88.37 210	70.48 142	80.04 95	87.88 208
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test_post											16.22 496	37.52 264	84.72 337

PatchT		56.60 388	52.97 395	67.48 373	72.94 373	46.16 356	57.30 461	73.78 389	38.77 443	54.37 359	57.26 468	37.52 264	78.06 406	32.02 428	52.79 403	78.23 393

v1192		67.96 265	65.74 285	74.63 221	71.79 385	53.43 135	84.06 216	80.99 260	63.19 168	59.56 276	77.46 342	37.50 266	88.65 194	58.20 258	58.93 344	81.79 341

HQP2-MVS												37.35 267

HQP-MVS		72.34 164	71.44 161	75.03 209	79.02 258	51.56 191	88.00 61	83.68 201	65.45 117	64.48 207	85.13 226	37.35 267	88.62 195	66.70 169	73.12 197	84.91 279

region2R		73.75 135	72.55 137	77.33 123	83.90 104	52.98 152	85.54 152	84.09 192	56.83 302	65.10 191	90.45 103	37.34 269	90.24 127	68.89 154	80.83 82	88.77 180

TESTMET0.1,1		72.86 151	72.33 142	74.46 224	81.98 159	50.77 210	85.13 169	85.47 126	66.09 107	67.30 162	83.69 254	37.27 270	83.57 352	65.06 191	78.97 111	89.05 172

mvsmamba		69.38 234	67.52 245	74.95 213	82.86 136	52.22 172	67.36 429	76.75 355	61.14 210	49.43 399	82.04 290	37.26 271	84.14 343	73.93 109	76.91 135	88.50 194

ACMMPR		73.76 134	72.61 135	77.24 130	83.92 103	52.96 153	85.58 148	84.29 184	56.82 303	65.12 190	90.45 103	37.24 272	90.18 129	69.18 152	80.84 81	88.58 187

MonoMVSNet		66.80 298	64.41 307	73.96 243	76.21 319	48.07 302	76.56 366	78.26 327	64.34 135	54.32 360	74.02 382	37.21 273	86.36 297	64.85 192	53.96 394	87.45 220

sss		70.49 208	70.13 191	71.58 320	81.59 179	39.02 424	80.78 318	84.71 175	59.34 245	66.61 169	88.09 167	37.17 274	85.52 321	61.82 221	71.02 225	90.20 132

reproduce-ours		71.77 181	70.43 181	75.78 175	81.96 160	49.54 250	82.54 268	81.01 258	48.77 390	69.21 145	90.96 89	37.13 275	89.40 160	66.28 174	76.01 154	88.39 197

our_new_method		71.77 181	70.43 181	75.78 175	81.96 160	49.54 250	82.54 268	81.01 258	48.77 390	69.21 145	90.96 89	37.13 275	89.40 160	66.28 174	76.01 154	88.39 197

EPNet_dtu		66.25 307	66.71 261	64.87 399	78.66 270	34.12 444	82.80 259	75.51 369	61.75 198	64.47 210	86.90 197	37.06 277	72.46 446	43.65 376	69.63 243	88.02 206
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v1921920		67.45 277	65.23 298	74.10 239	71.51 390	52.90 154	83.75 227	80.44 270	62.48 187	59.12 286	77.13 347	36.98 278	87.90 231	57.53 270	58.14 355	81.49 346

旧先验1					81.57 181	47.48 323		71.83 408			88.66 144	36.94 279			78.34 117	88.67 182

test-LLR		69.65 230	69.01 213	71.60 318	78.67 267	48.17 297	85.13 169	79.72 287	59.18 252	63.13 233	82.58 275	36.91 280	80.24 386	60.56 232	75.17 172	86.39 251

test0.0.03 1		62.54 344	62.44 322	62.86 414	72.28 383	29.51 468	82.93 256	78.78 313	59.18 252	53.07 371	82.41 279	36.91 280	77.39 416	37.45 396	58.96 343	81.66 344

MDTV_nov1_ep13_2view						43.62 386	71.13 413		54.95 340	59.29 284		36.76 282		46.33 362		87.32 223

KD-MVS_2432*1600		59.04 370	56.44 374	66.86 380	79.07 255	45.87 360	72.13 406	80.42 271	55.03 338	48.15 406	71.01 417	36.73 283	78.05 407	35.21 413	30.18 474	76.67 408

miper_refine_blended		59.04 370	56.44 374	66.86 380	79.07 255	45.87 360	72.13 406	80.42 271	55.03 338	48.15 406	71.01 417	36.73 283	78.05 407	35.21 413	30.18 474	76.67 408

GBi-Net		67.09 290	65.47 291	71.96 308	82.71 141	46.36 346	83.52 229	83.31 209	58.55 266	57.58 320	76.23 364	36.72 285	86.20 299	47.25 355	63.40 301	83.32 317

test1		67.09 290	65.47 291	71.96 308	82.71 141	46.36 346	83.52 229	83.31 209	58.55 266	57.58 320	76.23 364	36.72 285	86.20 299	47.25 355	63.40 301	83.32 317

FMVSNet2		67.57 274	65.79 283	72.90 274	82.71 141	47.97 306	85.15 168	84.93 161	58.55 266	56.71 336	78.26 333	36.72 285	86.67 285	46.15 363	62.94 312	84.07 293

AUN-MVS		68.20 262	66.35 268	73.76 251	76.37 313	47.45 325	79.52 343	79.52 293	60.98 215	62.34 241	86.02 213	36.59 288	86.94 274	62.32 215	53.47 400	86.89 233

reproduce_model		71.07 194	69.67 199	75.28 202	81.51 185	48.82 272	81.73 291	80.57 268	47.81 396	68.26 154	90.78 97	36.49 289	88.60 197	65.12 190	74.76 181	88.42 196

BH-untuned		68.28 259	66.40 267	73.91 245	81.62 176	50.01 236	85.56 150	77.39 344	57.63 284	57.47 325	83.69 254	36.36 290	87.08 269	44.81 368	73.08 200	84.65 282

fmvsm_s_conf0.5_n_2		72.02 172	71.72 156	72.92 273	76.79 309	45.90 358	84.48 201	66.11 440	64.26 137	76.12 57	93.40 26	36.26 291	86.04 309	81.47 45	66.54 270	86.82 241

EPMVS		68.45 255	65.44 293	77.47 119	84.91 80	56.17 45	71.89 410	81.91 239	61.72 199	60.85 260	72.49 400	36.21 292	87.06 270	47.32 354	71.62 216	89.17 169

wanda-best-256-512		64.87 318	62.23 324	72.81 277	70.49 405	46.85 334	85.71 143	85.71 119	56.85 299	51.25 384	72.31 406	36.16 293	87.84 233	52.67 318	48.90 414	83.73 305

FE-blended-shiyan7		64.87 318	62.23 324	72.81 277	70.49 405	46.85 334	85.71 143	85.71 119	56.85 299	51.25 384	72.31 406	36.16 293	87.84 233	52.67 318	48.90 414	83.73 305

usedtu_blend_shiyan5		63.62 333	60.36 348	73.40 263	70.49 405	47.96 308	79.13 348	80.68 264	47.51 400	51.25 384	72.31 406	36.16 293	88.50 205	56.81 276	48.90 414	83.73 305

MSLP-MVS++		74.21 124	72.25 145	80.11 40	81.45 186	56.47 40	86.32 115	79.65 291	58.19 270	66.36 173	92.29 57	36.11 296	90.66 110	67.39 165	82.49 68	93.18 18

FA-MVS(test-final)		69.00 243	66.60 265	76.19 162	83.48 111	47.96 308	74.73 377	82.07 234	57.27 293	62.18 244	78.47 331	36.09 297	92.89 40	53.76 304	71.32 223	87.73 212

MTAPA		72.73 155	71.22 165	77.27 127	81.54 182	53.57 128	67.06 431	81.31 251	59.41 243	68.39 153	90.96 89	36.07 298	89.01 176	73.80 112	82.45 69	89.23 166

HQP_MVS		70.96 198	69.91 196	74.12 238	77.95 283	49.57 244	85.76 135	82.59 223	63.60 158	62.15 246	83.28 262	36.04 299	88.30 217	65.46 183	72.34 208	84.49 283

plane_prior6					78.42 276	49.39 257						36.04 299

sam_mvs												35.99 301

blended_shiyan6		64.70 320	62.04 328	72.69 282	70.34 408	46.60 342	85.48 154	85.65 123	56.59 311	50.91 392	72.18 410	35.82 302	87.81 236	52.46 322	48.90 414	83.66 313

blended_shiyan8		64.70 320	62.04 328	72.69 282	70.33 409	46.62 340	85.48 154	85.66 121	56.58 312	50.94 391	72.18 410	35.81 303	87.80 239	52.47 321	48.91 413	83.65 314

PGM-MVS		72.60 157	71.20 166	76.80 147	82.95 131	52.82 157	83.07 253	82.14 229	56.51 314	63.18 232	89.81 123	35.68 304	89.76 143	67.30 166	80.19 92	87.83 209

icg_test_0407_2		71.26 189	69.99 194	75.09 207	82.26 151	50.87 203	79.65 339	85.16 145	62.91 174	63.68 225	86.07 209	35.56 305	84.32 342	64.03 197	70.55 231	90.09 137

IMVS_0407		71.97 174	70.10 192	77.57 115	82.26 151	50.87 203	80.69 321	85.16 145	62.91 174	63.68 225	86.07 209	35.56 305	91.75 71	64.03 197	70.55 231	90.09 137

XVS		72.92 149	71.62 157	76.81 145	83.41 112	52.48 161	84.88 185	83.20 214	58.03 272	63.91 217	89.63 126	35.50 307	89.78 141	65.50 180	80.50 87	88.16 200

X-MVStestdata		65.85 312	62.20 326	76.81 145	83.41 112	52.48 161	84.88 185	83.20 214	58.03 272	63.91 217	4.82 500	35.50 307	89.78 141	65.50 180	80.50 87	88.16 200

v1240		66.99 293	64.68 304	73.93 244	71.38 394	52.66 159	83.39 241	79.98 280	61.97 195	58.44 308	77.11 348	35.25 309	87.81 236	56.46 282	58.15 353	81.33 354

test1111		71.06 195	70.42 183	72.97 272	79.48 245	41.49 412	84.82 189	82.74 222	64.20 140	62.98 235	87.43 189	35.20 310	87.92 229	58.54 251	78.42 116	89.49 159

dp		64.41 323	61.58 332	72.90 274	82.40 148	54.09 120	72.53 398	76.59 361	60.39 226	55.68 346	70.39 423	35.18 311	76.90 422	39.34 391	61.71 320	87.73 212

Syy-MVS		61.51 353	61.35 337	62.00 418	81.73 167	30.09 462	80.97 313	81.02 256	60.93 217	55.06 349	82.64 273	35.09 312	80.81 376	16.40 481	58.32 349	75.10 425

ECVR-MVS		71.81 178	71.00 171	74.26 234	80.12 229	43.49 387	84.69 193	82.16 228	64.02 143	64.64 202	87.43 189	35.04 313	89.21 169	61.24 225	79.66 101	90.08 141

CP-MVS		72.59 159	71.46 160	76.00 169	82.93 133	52.32 167	86.93 99	82.48 226	55.15 336	63.65 227	90.44 106	35.03 314	88.53 204	68.69 157	77.83 124	87.15 228

fmvsm_s_conf0.1_n_2		71.45 186	71.01 170	72.78 279	75.37 338	45.82 362	84.18 211	64.59 446	64.02 143	75.67 58	93.02 39	34.99 315	85.99 312	81.18 49	66.04 278	86.52 247

CP-MVSNet		58.54 379	57.57 367	61.46 423	68.50 426	33.96 445	76.90 362	78.60 320	51.67 370	47.83 409	76.60 359	34.99 315	72.79 444	35.45 410	47.58 426	77.64 401

guyue		70.53 207	69.12 209	74.76 218	77.61 288	47.53 321	84.86 187	85.17 143	62.70 181	62.18 244	83.74 251	34.72 317	89.86 137	64.69 193	66.38 272	86.87 234

dmvs_re		67.61 272	66.00 277	72.42 294	81.86 164	43.45 388	64.67 437	80.00 279	69.56 52	60.07 268	85.00 232	34.71 318	87.63 250	51.48 326	66.68 265	86.17 254

MDTV_nov1_ep13			61.56 333		81.68 171	55.12 72	72.41 401	78.18 328	59.19 250	58.85 294	69.29 428	34.69 319	86.16 302	36.76 405	62.96 311

SSC-MVS3.2		68.13 263	66.89 255	71.85 316	82.26 151	43.97 382	82.09 279	89.29 29	71.74 17	61.12 258	79.83 316	34.60 320	87.45 257	41.23 385	59.85 335	84.14 290

WB-MVSnew		69.36 235	68.24 224	72.72 281	79.26 251	49.40 256	85.72 142	88.85 41	61.33 206	64.59 205	82.38 281	34.57 321	87.53 255	46.82 359	70.63 228	81.22 358

3Dnovator	64.70 6	74.46 119	72.48 138	80.41 30	82.84 138	55.40 61	83.08 252	88.61 52	67.61 77	59.85 270	88.66 144	34.57 321	93.97 27	58.42 254	88.70 12	91.85 57

VortexMVS		68.49 254	66.84 257	73.46 261	81.10 196	48.75 274	84.63 197	84.73 170	62.05 192	57.22 330	77.08 350	34.54 323	89.20 170	63.08 206	57.12 367	82.43 334

Vis-MVSNet		70.61 206	69.34 204	74.42 226	80.95 202	48.49 283	86.03 125	77.51 342	58.74 263	65.55 186	87.78 178	34.37 324	85.95 316	52.53 320	80.61 85	88.80 178
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_post1							70.84 414				14.72 499	34.33 325	83.86 346	48.80 343

OPM-MVS		70.75 202	69.58 200	74.26 234	75.55 334	51.34 197	86.05 124	83.29 212	61.94 196	62.95 236	85.77 216	34.15 326	88.44 208	65.44 186	71.07 224	82.99 326
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DP-MVS Recon		71.99 173	70.31 186	77.01 136	90.65 9	53.44 133	89.37 39	82.97 219	56.33 317	63.56 230	89.47 128	34.02 327	92.15 64	54.05 301	72.41 206	85.43 270

PEN-MVS		58.35 380	57.15 369	61.94 419	67.55 433	34.39 440	77.01 360	78.35 326	51.87 367	47.72 410	76.73 357	33.91 328	73.75 439	34.03 420	47.17 430	77.68 399

QAPM		71.88 177	69.33 205	79.52 45	82.20 157	54.30 113	86.30 116	88.77 44	56.61 310	59.72 272	87.48 187	33.90 329	95.36 14	47.48 353	81.49 77	88.90 174

新几何1				73.30 266	83.10 122	53.48 129		71.43 414	45.55 416	66.14 174	87.17 194	33.88 330	80.54 382	48.50 346	80.33 91	85.88 262

1314		71.11 193	69.41 202	76.22 159	79.32 249	50.49 218	80.23 329	85.14 151	59.44 242	58.93 290	88.89 140	33.83 331	89.60 152	61.49 223	77.42 129	88.57 188

SR-MVS		70.92 199	69.73 198	74.50 223	83.38 116	50.48 220	84.27 208	79.35 301	48.96 388	66.57 171	90.45 103	33.65 332	87.11 268	66.42 171	74.56 183	85.91 260

mPP-MVS		71.79 180	70.38 184	76.04 167	82.65 144	52.06 173	84.45 202	81.78 242	55.59 328	62.05 249	89.68 125	33.48 333	88.28 219	65.45 185	78.24 118	87.77 211

OMC-MVS		65.97 311	65.06 301	68.71 362	72.97 372	42.58 402	78.61 351	75.35 372	54.72 342	59.31 282	86.25 208	33.30 334	77.88 411	57.99 260	67.05 263	85.66 265

BH-RMVSNet		70.08 216	68.01 227	76.27 157	84.21 98	51.22 201	87.29 87	79.33 303	58.96 259	63.63 228	86.77 199	33.29 335	90.30 126	44.63 370	73.96 186	87.30 224

gbinet_0.2-2-1-0.02		64.20 325	61.39 335	72.63 285	70.85 399	46.32 350	85.92 127	85.98 113	55.27 335	51.88 381	72.29 409	33.14 336	87.82 235	48.50 346	48.72 418	83.73 305

SSM_0407		69.71 225	67.38 248	76.69 152	80.45 219	51.81 184	81.36 307	80.18 275	54.07 349	63.82 221	85.05 229	33.09 337	91.01 95	59.40 241	68.97 247	87.25 225

SSM_0404		70.13 212	67.87 236	76.88 143	80.22 226	52.00 175	81.71 293	80.18 275	54.07 349	65.36 188	85.05 229	33.09 337	91.03 92	59.40 241	71.80 214	87.63 215

JIA-IIPM		52.33 414	47.77 424	66.03 388	71.20 395	46.92 332	40.00 483	76.48 362	37.10 450	46.73 418	37.02 483	32.96 339	77.88 411	35.97 407	52.45 405	73.29 440

PS-CasMVS		58.12 381	57.03 371	61.37 424	68.24 430	33.80 447	76.73 364	78.01 330	51.20 373	47.54 413	76.20 367	32.85 340	72.76 445	35.17 415	47.37 428	77.55 402

DTE-MVSNet		57.03 386	55.73 381	60.95 428	65.94 437	32.57 452	75.71 367	77.09 350	51.16 374	46.65 420	76.34 362	32.84 341	73.22 443	30.94 434	44.87 439	77.06 404

pmmvs4		63.34 337	61.07 341	70.16 342	70.14 411	50.53 217	79.97 336	71.41 415	55.08 337	54.12 362	78.58 329	32.79 342	82.09 366	50.33 332	57.22 366	77.86 396

TR-MVS		69.71 225	67.85 237	75.27 203	82.94 132	48.48 284	87.40 83	80.86 261	57.15 296	64.61 204	87.08 195	32.67 343	89.64 151	46.38 361	71.55 218	87.68 214

VDD-MVS		76.08 80	74.97 95	79.44 46	84.27 97	53.33 139	91.13 20	85.88 115	65.33 123	72.37 96	89.34 131	32.52 344	92.76 46	77.90 74	75.96 156	92.22 41

3Dnovator+	62.71 7	72.29 167	70.50 179	77.65 114	83.40 115	51.29 199	87.32 84	86.40 104	59.01 257	58.49 305	88.32 159	32.40 345	91.27 83	57.04 274	82.15 72	90.38 124

tfpnnormal		61.47 354	59.09 358	68.62 364	76.29 318	41.69 408	81.14 310	85.16 145	54.48 345	51.32 383	73.63 389	32.32 346	86.89 277	21.78 468	55.71 382	77.29 403

MS-PatchMatch		72.34 164	71.26 164	75.61 181	82.38 149	55.55 54	88.00 61	89.95 23	65.38 121	56.51 340	80.74 306	32.28 347	92.89 40	57.95 263	88.10 16	78.39 389

KinetiMVS		71.15 190	69.25 208	76.82 144	77.99 282	50.49 218	85.05 175	86.51 100	59.78 234	64.10 213	85.34 224	32.16 348	91.33 82	58.82 248	73.54 193	88.64 183

v7n		62.50 346	59.27 357	72.20 300	67.25 434	49.83 241	77.87 357	80.12 277	52.50 362	48.80 404	73.07 393	32.10 349	87.90 231	46.83 358	54.92 386	78.86 380

IterMVS		63.77 332	61.67 331	70.08 344	72.68 376	51.24 200	80.44 324	75.51 369	60.51 225	51.41 382	73.70 388	32.08 350	78.91 397	54.30 299	54.35 392	80.08 372
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		59.12 367	58.81 361	60.08 429	70.68 404	45.07 369	80.42 325	74.25 381	43.54 431	50.02 397	73.73 385	31.97 351	56.74 475	51.06 330	53.60 398	78.42 388

SCA		63.84 330	60.01 352	75.32 196	78.58 272	57.92 13	61.61 450	77.53 341	56.71 306	57.75 317	70.77 420	31.97 351	79.91 392	48.80 343	56.36 370	88.13 203

ACMMP		70.81 201	69.29 206	75.39 194	81.52 184	51.92 179	83.43 237	83.03 217	56.67 308	58.80 295	88.91 139	31.92 353	88.58 198	65.89 179	73.39 194	85.67 264
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		66.33 305	62.87 316	76.70 151	80.45 219	51.81 184	46.11 474	78.90 308	55.46 331	63.82 221	84.54 236	31.91 354	91.03 92	55.68 289	68.97 247	87.25 225

SSM_04072		64.04 328	62.87 316	67.56 372	80.45 219	51.81 184	46.11 474	78.90 308	55.46 331	63.82 221	84.54 236	31.91 354	63.62 460	55.68 289	68.97 247	87.25 225

APD-MVS_3200maxsize		69.62 231	68.23 225	73.80 250	81.58 180	48.22 295	81.91 283	79.50 294	48.21 394	64.24 212	89.75 124	31.91 354	87.55 254	63.08 206	73.85 190	85.64 266

VDDNet		74.37 121	72.13 149	81.09 21	79.58 241	56.52 39	90.02 26	86.70 96	52.61 361	71.23 118	87.20 193	31.75 357	93.96 28	74.30 105	75.77 163	92.79 28

pmmvs5		62.80 343	61.18 339	67.66 371	69.53 418	42.37 405	82.65 262	75.19 373	54.30 348	52.03 379	78.51 330	31.64 358	80.67 378	48.60 345	58.15 353	79.95 373

LCM-MVSNet-Re		58.82 373	56.54 372	65.68 391	79.31 250	29.09 471	61.39 452	45.79 472	60.73 222	37.65 456	72.47 401	31.42 359	81.08 372	49.66 336	70.41 235	86.87 234

AstraMVS		70.12 213	68.56 216	74.81 216	76.48 312	47.48 323	84.35 205	82.58 225	63.80 151	62.09 248	84.54 236	31.39 360	89.96 134	68.24 162	63.58 299	87.00 231

testdata				67.08 378	77.59 290	45.46 366		69.20 430	44.47 424	71.50 115	88.34 158	31.21 361	70.76 452	52.20 323	75.88 157	85.03 275

SR-MVS-dyc-post		68.27 260	66.87 256	72.48 291	80.96 199	48.14 299	81.54 301	76.98 351	46.42 408	62.75 238	89.42 129	31.17 362	86.09 307	60.52 234	72.06 212	83.19 322

GA-MVS		69.04 241	66.70 262	76.06 166	75.11 342	52.36 165	83.12 251	80.23 274	63.32 165	60.65 263	79.22 324	30.98 363	88.37 210	61.25 224	66.41 271	87.46 219

OpenMVS	61.00 11	69.99 220	67.55 243	77.30 125	78.37 277	54.07 121	84.36 204	85.76 118	57.22 294	56.71 336	87.67 185	30.79 364	92.83 42	43.04 378	84.06 60	85.01 276

Effi-MVS+-dtu		66.24 308	64.96 303	70.08 344	75.17 341	49.64 243	82.01 280	74.48 380	62.15 190	57.83 313	76.08 368	30.59 365	83.79 348	65.40 187	60.93 326	76.81 407

sd_testset		67.79 269	65.95 279	73.32 264	81.70 169	46.33 349	68.99 422	80.30 273	66.58 93	61.64 253	82.38 281	30.45 366	87.63 250	55.86 286	65.60 280	86.01 255

test222					79.36 247	50.97 202	77.99 356	67.84 435	42.54 435	62.84 237	86.53 204	30.26 367			76.91 135	85.23 271

MVS_111021_LR		69.07 238	67.91 229	72.54 288	77.27 298	49.56 247	79.77 337	73.96 387	59.33 247	60.73 262	87.82 177	30.19 368	81.53 368	69.94 145	72.19 211	86.53 246

114514_t		69.87 223	67.88 233	75.85 173	88.38 31	52.35 166	86.94 97	83.68 201	53.70 352	55.68 346	85.60 218	30.07 369	91.20 87	55.84 287	71.02 225	83.99 296

CPTT-MVS		67.15 288	65.84 282	71.07 328	80.96 199	50.32 229	81.94 282	74.10 383	46.18 414	57.91 312	87.64 186	29.57 370	81.31 370	64.10 196	70.18 238	81.56 345

CANet_DTU		73.71 136	73.14 128	75.40 191	82.61 145	50.05 234	84.67 196	79.36 300	69.72 50	75.39 59	90.03 119	29.41 371	85.93 317	67.99 163	79.11 108	90.22 130

AdaColmap		67.86 266	65.48 290	75.00 211	88.15 38	54.99 79	86.10 122	76.63 360	49.30 385	57.80 314	86.65 203	29.39 372	88.94 184	45.10 367	70.21 237	81.06 359

RE-MVS-def			66.66 263		80.96 199	48.14 299	81.54 301	76.98 351	46.42 408	62.75 238	89.42 129	29.28 373		60.52 234	72.06 212	83.19 322

CVMVSNet		60.85 357	60.44 346	62.07 416	75.00 345	32.73 451	79.54 341	73.49 394	36.98 451	56.28 342	83.74 251	29.28 373	69.53 455	46.48 360	63.23 306	83.94 301

PMMVS		72.98 148	72.05 152	75.78 175	83.57 108	48.60 278	84.08 214	82.85 221	61.62 201	68.24 155	90.33 108	28.35 375	87.78 243	72.71 123	76.69 142	90.95 105

our_test_3		59.11 368	55.08 385	71.18 327	71.42 392	53.29 141	81.96 281	74.52 379	48.32 392	42.08 437	69.28 429	28.14 376	82.15 364	34.35 419	45.68 438	78.11 394

Fast-Effi-MVS+-dtu		66.53 302	64.10 312	73.84 248	72.41 379	52.30 170	84.73 191	75.66 367	59.51 240	56.34 341	79.11 326	28.11 377	85.85 318	57.74 269	63.29 305	83.35 316

Anonymous20231211		66.08 310	63.67 313	73.31 265	83.07 125	48.75 274	86.01 126	84.67 177	45.27 418	56.54 338	76.67 358	28.06 378	88.95 182	52.78 314	59.95 332	82.23 336

Anonymous20240529		69.71 225	67.28 250	77.00 137	83.78 106	50.36 227	88.87 51	85.10 152	47.22 401	64.03 215	83.37 260	27.93 379	92.10 65	57.78 268	67.44 261	88.53 192

HPM-MVS_fast		67.86 266	66.28 271	72.61 286	80.67 210	48.34 289	81.18 309	75.95 366	50.81 375	59.55 277	88.05 170	27.86 380	85.98 313	58.83 247	73.58 192	83.51 315

FMVSNet1		64.57 322	62.11 327	71.96 308	77.32 297	46.36 346	83.52 229	83.31 209	52.43 363	54.42 358	76.23 364	27.80 381	86.20 299	42.59 382	61.34 322	83.32 317

CNLPA		60.59 358	58.44 362	67.05 379	79.21 252	47.26 329	79.75 338	64.34 448	42.46 436	51.90 380	83.94 247	27.79 382	75.41 432	37.12 398	59.49 339	78.47 386

TAPA-MVS	56.12 14	61.82 352	60.18 351	66.71 382	78.48 275	37.97 431	75.19 375	76.41 363	46.82 404	57.04 331	86.52 205	27.67 383	77.03 419	26.50 454	67.02 264	85.14 274
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
pmmvs6		59.64 362	57.15 369	67.09 377	66.01 436	36.86 435	80.50 322	78.64 317	45.05 420	49.05 402	73.94 383	27.28 384	86.10 305	43.96 375	49.94 411	78.31 390

test-mter		68.36 256	67.29 249	71.60 318	78.67 267	48.17 297	85.13 169	79.72 287	53.38 355	63.13 233	82.58 275	27.23 385	80.24 386	60.56 232	75.17 172	86.39 251

D2MVS		63.49 335	61.39 335	69.77 348	69.29 420	48.93 268	78.89 350	77.71 339	60.64 224	49.70 398	72.10 414	27.08 386	83.48 353	54.48 298	62.65 314	76.90 405

XVG-OURS-SEG-HR		62.02 350	59.54 354	69.46 351	65.30 441	45.88 359	65.06 435	73.57 392	46.45 407	57.42 326	83.35 261	26.95 387	78.09 405	53.77 303	64.03 294	84.42 285

IMVS_0404		69.11 237	67.25 252	74.68 220	82.26 151	50.87 203	76.74 363	85.16 145	62.91 174	50.76 395	86.07 209	26.76 388	83.06 359	64.03 197	70.55 231	90.09 137

test_djsdf		63.84 330	61.56 333	70.70 334	68.78 423	44.69 373	81.63 295	81.44 249	50.28 378	52.27 376	76.26 363	26.72 389	86.11 303	60.83 228	55.84 381	81.29 357

Anonymous20231206		59.08 369	57.59 366	63.55 406	68.77 424	32.14 455	80.26 328	79.78 286	50.00 382	49.39 400	72.39 403	26.64 390	78.36 402	33.12 426	57.94 358	80.14 371

ppachtmachnet_test		58.56 377	54.34 387	71.24 324	71.42 392	54.74 98	81.84 286	72.27 404	49.02 387	45.86 424	68.99 430	26.27 391	83.30 356	30.12 436	43.23 444	75.69 417

test20.03		55.22 397	54.07 390	58.68 434	63.14 455	25.00 477	77.69 358	74.78 376	52.64 360	43.43 431	72.39 403	26.21 392	74.76 434	29.31 439	47.05 432	76.28 415

FE-MVS		64.15 326	60.43 347	75.30 199	80.85 204	49.86 240	68.28 426	78.37 325	50.26 381	59.31 282	73.79 384	26.19 393	91.92 68	40.19 388	66.67 266	84.12 291

FMVSNet5		58.61 376	56.45 373	65.10 398	77.20 302	39.74 420	74.77 376	77.12 349	50.27 380	43.28 433	67.71 433	26.15 394	76.90 422	36.78 404	54.78 388	78.65 384

ACMP	61.11 9	66.24 308	64.33 309	72.00 307	74.89 347	49.12 260	83.18 248	79.83 285	55.41 333	52.29 375	82.68 272	25.83 395	86.10 305	60.89 227	63.94 296	80.78 362
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MIMVSNet		63.12 339	60.29 349	71.61 317	75.92 329	46.65 339	65.15 434	81.94 236	59.14 254	54.65 356	69.47 426	25.74 396	80.63 380	41.03 387	69.56 244	87.55 217

LPG-MVS_test		66.44 304	64.58 305	72.02 305	74.42 353	48.60 278	83.07 253	80.64 265	54.69 343	53.75 366	83.83 249	25.73 397	86.98 271	60.33 238	64.71 287	80.48 366

LGP-MVS_train				72.02 305	74.42 353	48.60 278		80.64 265	54.69 343	53.75 366	83.83 249	25.73 397	86.98 271	60.33 238	64.71 287	80.48 366

test_vis1_n_1920		68.59 253	68.31 222	69.44 352	69.16 421	41.51 411	84.63 197	68.58 433	58.80 261	73.26 81	88.37 155	25.30 399	80.60 381	79.10 59	67.55 260	86.23 253

ACMM	58.35 12	64.35 324	62.01 330	71.38 322	74.21 357	48.51 282	82.25 275	79.66 289	47.61 398	54.54 357	80.11 311	25.26 400	86.00 311	51.26 327	63.16 308	79.64 375
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FE-MVSNET2		58.78 374	56.44 374	65.82 389	63.57 453	38.92 425	79.59 340	81.75 245	56.14 322	43.06 435	68.15 432	25.22 401	80.64 379	42.29 384	48.16 421	77.91 395

XVG-OURS		61.88 351	59.34 356	69.49 350	65.37 440	46.27 351	64.80 436	73.49 394	47.04 403	57.41 327	82.85 266	25.15 402	78.18 403	53.00 311	64.98 282	84.01 295

PVSNet_0	57.04 13	61.19 355	57.24 368	73.02 270	77.45 294	50.31 230	79.43 345	77.36 346	63.96 148	47.51 414	72.45 402	25.03 403	83.78 349	52.76 316	19.22 488	84.96 278

WB-MVS		37.41 443	36.37 443	40.54 464	54.23 471	10.43 501	65.29 432	43.75 475	34.86 462	27.81 480	54.63 470	24.94 404	63.21 461	6.81 495	15.00 491	47.98 482

UniMVSNet_ETH3D		62.51 345	60.49 345	68.57 366	68.30 429	40.88 418	73.89 385	79.93 283	51.81 369	54.77 354	79.61 319	24.80 405	81.10 371	49.93 334	61.35 321	83.73 305

DP-MVS		59.24 365	56.12 378	68.63 363	88.24 36	50.35 228	82.51 270	64.43 447	41.10 438	46.70 419	78.77 328	24.75 406	88.57 201	22.26 466	56.29 374	66.96 460

test_cas_vis1_n_1920		67.10 289	66.60 265	68.59 365	65.17 443	43.23 393	83.23 246	69.84 426	55.34 334	70.67 132	87.71 184	24.70 407	76.66 424	78.57 66	64.20 292	85.89 261

LuminaMVS		66.60 301	64.37 308	73.27 268	70.06 414	49.57 244	80.77 319	81.76 244	50.81 375	60.56 264	78.41 332	24.50 408	87.26 264	64.24 195	68.25 253	82.99 326

tt0805		63.39 336	61.31 338	69.64 349	69.36 419	38.87 426	78.00 355	85.48 125	48.82 389	55.66 348	81.66 296	24.38 409	86.37 296	49.04 342	59.36 341	83.68 311

cascas		69.01 242	66.13 274	77.66 113	79.36 247	55.41 60	86.99 94	83.75 199	56.69 307	58.92 291	81.35 300	24.31 410	92.10 65	53.23 307	70.61 229	85.46 269

CMPMVS	40.41 21	55.34 396	52.64 399	63.46 408	60.88 461	43.84 384	61.58 451	71.06 418	30.43 469	36.33 459	74.63 377	24.14 411	75.44 431	48.05 350	66.62 267	71.12 453
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UGNet		68.71 250	67.11 254	73.50 260	80.55 215	47.61 320	84.08 214	78.51 322	59.45 241	65.68 184	82.73 271	23.78 412	85.08 332	52.80 313	76.40 143	87.80 210
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		53.82 404	49.96 410	65.41 395	70.09 413	48.95 266	72.30 402	71.66 412	44.25 427	31.89 473	63.07 450	23.73 413	73.95 437	33.26 424	39.40 454	73.34 438

MDA-MVSNet_test_wron		53.82 404	49.95 411	65.43 394	70.13 412	49.05 262	72.30 402	71.65 413	44.23 428	31.85 474	63.13 449	23.68 414	74.01 436	33.25 425	39.35 455	73.23 441

PLC	52.38 18	60.89 356	58.97 360	66.68 384	81.77 166	45.70 364	78.96 349	74.04 386	43.66 430	47.63 411	83.19 264	23.52 415	77.78 414	37.47 395	60.46 328	76.55 413
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SSC-MVS		35.20 445	34.30 447	37.90 466	52.58 473	8.65 504	61.86 448	41.64 479	31.81 467	25.54 483	52.94 476	23.39 416	59.28 470	6.10 496	12.86 492	45.78 485

ADS-MVSNet2		55.21 398	51.44 403	66.51 385	80.60 211	49.56 247	55.03 465	65.44 441	44.72 422	51.00 388	61.19 457	22.83 417	75.41 432	28.54 444	53.63 396	74.57 430

ADS-MVSNet		56.17 392	51.95 402	68.84 357	80.60 211	53.07 149	55.03 465	70.02 425	44.72 422	51.00 388	61.19 457	22.83 417	78.88 398	28.54 444	53.63 396	74.57 430

test_0402		56.45 390	53.03 394	66.69 383	76.78 310	50.31 230	81.76 288	69.61 428	42.79 434	43.88 428	72.13 412	22.82 419	86.46 293	16.57 480	50.94 408	63.31 469

UnsupCasMVSNet_eth		57.56 384	55.15 383	64.79 400	64.57 448	33.12 448	73.17 393	83.87 198	58.98 258	41.75 440	70.03 424	22.54 420	79.92 390	46.12 364	35.31 461	81.32 356

xiu_mvs_v1_base_debu		71.60 183	70.29 187	75.55 185	77.26 299	53.15 144	85.34 157	79.37 297	55.83 325	72.54 91	90.19 113	22.38 421	86.66 286	73.28 119	76.39 144	86.85 237

xiu_mvs_v1_base		71.60 183	70.29 187	75.55 185	77.26 299	53.15 144	85.34 157	79.37 297	55.83 325	72.54 91	90.19 113	22.38 421	86.66 286	73.28 119	76.39 144	86.85 237

xiu_mvs_v1_base_debi		71.60 183	70.29 187	75.55 185	77.26 299	53.15 144	85.34 157	79.37 297	55.83 325	72.54 91	90.19 113	22.38 421	86.66 286	73.28 119	76.39 144	86.85 237

LS3D		56.40 391	53.82 391	64.12 402	81.12 194	45.69 365	73.42 391	66.14 439	35.30 461	43.24 434	79.88 313	22.18 424	79.62 395	19.10 475	64.00 295	67.05 459

PVSNet	62.49 8	69.27 236	67.81 238	73.64 255	84.41 89	51.85 181	84.63 197	77.80 336	66.42 98	59.80 271	84.95 233	22.14 425	80.44 384	55.03 294	75.11 175	88.62 186

MDA-MVSNet-bldmvs		51.56 417	47.75 425	63.00 411	71.60 389	47.32 328	69.70 420	72.12 405	43.81 429	27.65 481	63.38 448	21.97 426	75.96 428	27.30 451	32.19 469	65.70 465

pmmvs-eth3d		55.97 394	52.78 398	65.54 393	61.02 460	46.44 345	75.36 374	67.72 436	49.61 384	43.65 430	67.58 434	21.63 427	77.04 418	44.11 374	44.33 440	73.15 442

anonymousdsp		60.46 359	57.65 365	68.88 356	63.63 452	45.09 368	72.93 394	78.63 318	46.52 406	51.12 387	72.80 398	21.46 428	83.07 358	57.79 267	53.97 393	78.47 386

MVS-HIRNet		49.01 426	44.71 430	61.92 420	76.06 322	46.61 341	63.23 443	54.90 464	24.77 476	33.56 468	36.60 485	21.28 429	75.88 430	29.49 438	62.54 315	63.26 470

Anonymous202405211		70.11 214	67.88 233	76.79 148	87.20 47	47.24 330	89.49 36	77.38 345	54.88 341	66.14 174	86.84 198	20.93 430	91.54 76	56.45 283	71.62 216	91.59 67

FE-MVSNET		51.43 418	48.22 420	61.06 426	60.78 462	32.48 453	73.85 387	64.62 444	46.30 413	37.47 457	66.27 438	20.80 431	77.38 417	23.43 462	40.48 450	73.31 439

UnsupCasMVSNet_bld		53.86 403	50.53 407	63.84 403	63.52 454	34.75 438	71.38 411	81.92 238	46.53 405	38.95 452	57.93 466	20.55 432	80.20 388	39.91 390	34.09 468	76.57 412

Elysia		65.59 313	62.65 319	74.42 226	69.85 415	49.46 254	80.04 332	82.11 231	46.32 411	58.74 299	79.64 317	20.30 433	88.57 201	55.48 291	71.37 220	85.22 272

StellarMVS		65.59 313	62.65 319	74.42 226	69.85 415	49.46 254	80.04 332	82.11 231	46.32 411	58.74 299	79.64 317	20.30 433	88.57 201	55.48 291	71.37 220	85.22 272

EU-MVSNet		52.63 410	50.72 406	58.37 435	62.69 457	28.13 474	72.60 397	75.97 365	30.94 468	40.76 447	72.11 413	20.16 435	70.80 451	35.11 416	46.11 436	76.19 416

N_pmnet		41.25 436	39.77 439	45.66 457	68.50 426	0.82 508	72.51 399	0.38 507	35.61 458	35.26 463	61.51 456	20.07 436	67.74 456	23.51 461	40.63 448	68.42 458

MSDG		59.44 363	55.14 384	72.32 298	74.69 348	50.71 211	74.39 382	73.58 391	44.44 425	43.40 432	77.52 340	19.45 437	90.87 103	31.31 432	57.49 365	75.38 420

tt0320		52.45 412	48.75 416	63.55 406	71.47 391	41.85 407	72.42 400	59.73 456	36.33 456	44.52 425	61.55 455	19.34 438	76.45 426	33.53 421	39.85 452	72.36 445

K. test v3		54.04 402	49.42 415	67.92 370	68.55 425	42.57 403	75.51 372	63.07 451	52.07 364	39.21 450	64.59 446	19.34 438	82.21 363	37.11 399	25.31 479	78.97 379

lessismore_v0				67.98 369	64.76 447	41.25 414		45.75 473		36.03 461	65.63 443	19.29 440	84.11 344	35.67 408	21.24 485	78.59 385

KD-MVS_self_test		49.24 425	46.85 427	56.44 440	54.32 470	22.87 480	57.39 460	73.36 399	44.36 426	37.98 455	59.30 464	18.97 441	71.17 450	33.48 422	42.44 445	75.26 422

OpenMVS_ROB	53.19 17	59.20 366	56.00 379	68.83 358	71.13 396	44.30 377	83.64 228	75.02 374	46.42 408	46.48 421	73.03 394	18.69 442	88.14 221	27.74 449	61.80 319	74.05 433

mvsany_test1		43.38 435	42.57 437	45.82 456	50.96 479	26.10 476	55.80 463	27.74 495	27.15 473	47.41 415	74.39 379	18.67 443	44.95 487	44.66 369	36.31 459	66.40 462

LTVRE_ROB	45.45 19	52.73 409	49.74 413	61.69 421	69.78 417	34.99 437	44.52 476	67.60 437	43.11 433	43.79 429	74.03 381	18.54 444	81.45 369	28.39 446	57.94 358	68.62 457
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		54.37 399	50.10 408	67.21 376	70.70 402	41.46 413	74.73 377	64.69 443	47.56 399	39.12 451	69.49 425	18.49 445	84.69 338	31.87 429	34.20 467	75.48 419

new-patchmatchnet		48.21 427	46.55 428	53.18 446	57.73 466	18.19 494	70.24 415	71.02 419	45.70 415	33.70 467	60.23 460	18.00 446	69.86 454	27.97 448	34.35 465	71.49 452

tt0320-xc		52.22 415	48.38 419	63.75 405	72.19 384	42.25 406	72.19 405	57.59 460	37.24 449	44.41 426	61.56 454	17.90 447	75.89 429	35.60 409	36.73 458	73.12 443

F-COLMAP		55.96 395	53.65 393	62.87 413	72.76 375	42.77 399	74.70 379	70.37 422	40.03 439	41.11 445	79.36 321	17.77 448	73.70 440	32.80 427	53.96 394	72.15 446

sc_t1		53.51 407	49.92 412	64.29 401	70.33 409	39.55 423	72.93 394	59.60 457	38.74 444	47.16 416	66.47 437	17.59 449	76.50 425	36.83 403	39.62 453	76.82 406

jajsoiax		63.21 338	60.84 342	70.32 340	68.33 428	44.45 375	81.23 308	81.05 255	53.37 356	50.96 390	77.81 338	17.49 450	85.49 323	59.31 243	58.05 356	81.02 360

RPSCF		45.77 432	44.13 434	50.68 448	57.67 467	29.66 467	54.92 467	45.25 474	26.69 474	45.92 423	75.92 370	17.43 451	45.70 486	27.44 450	45.95 437	76.67 408

mmtdpeth		57.93 382	54.78 386	67.39 375	72.32 381	43.38 390	72.72 396	68.93 431	54.45 346	56.85 333	62.43 451	17.02 452	83.46 354	57.95 263	30.31 473	75.31 421

PatchMatch-RL		56.66 387	53.75 392	65.37 396	77.91 286	45.28 367	69.78 419	60.38 454	41.35 437	47.57 412	73.73 385	16.83 453	76.91 420	36.99 401	59.21 342	73.92 434

mvs_tets		62.96 341	60.55 344	70.19 341	68.22 431	44.24 380	80.90 315	80.74 263	52.99 359	50.82 394	77.56 339	16.74 454	85.44 324	59.04 246	57.94 358	80.89 361

ACMH+	54.58 15	58.55 378	55.24 382	68.50 367	74.68 349	45.80 363	80.27 327	70.21 423	47.15 402	42.77 436	75.48 372	16.73 455	85.98 313	35.10 417	54.78 388	73.72 435

ACMH	53.70 16	59.78 361	55.94 380	71.28 323	76.59 311	48.35 288	80.15 331	76.11 364	49.74 383	41.91 439	73.45 392	16.50 456	90.31 124	31.42 431	57.63 364	75.17 423
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MIMVSNet1		50.35 423	47.81 423	57.96 436	61.53 459	27.80 475	67.40 428	74.06 385	43.25 432	33.31 472	65.38 445	16.03 457	71.34 449	21.80 467	47.55 427	74.75 427

DSMNet-mixed		38.35 440	35.36 445	47.33 455	48.11 485	14.91 498	37.87 484	36.60 486	19.18 481	34.37 465	59.56 463	15.53 458	53.01 479	20.14 473	46.89 433	74.07 432

EG-PatchMatch MVS		62.40 349	59.59 353	70.81 332	73.29 366	49.05 262	85.81 133	84.78 167	51.85 368	44.19 427	73.48 391	15.52 459	89.85 139	40.16 389	67.24 262	73.54 437

testgi		54.25 401	52.57 400	59.29 432	62.76 456	21.65 486	72.21 404	70.47 421	53.25 357	41.94 438	77.33 345	14.28 460	77.95 410	29.18 440	51.72 407	78.28 391

COLMAP_ROB	43.60 20	50.90 421	48.05 422	59.47 430	67.81 432	40.57 419	71.25 412	62.72 453	36.49 454	36.19 460	73.51 390	13.48 461	73.92 438	20.71 470	50.26 410	63.92 468
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		52.39 413	48.73 417	63.35 410	65.21 442	38.42 429	68.54 425	64.95 442	38.19 445	39.57 449	71.43 416	13.23 462	79.92 390	37.16 397	40.32 451	71.72 449

usedtu_dtu_shiyan2		50.47 422	46.43 429	62.61 415	51.66 476	31.70 457	75.62 369	75.65 368	36.36 455	34.89 464	56.91 469	12.01 463	78.40 401	30.87 435	43.86 441	77.72 398

MVStest1		38.35 440	34.53 446	49.82 452	51.43 477	30.41 459	50.39 469	55.25 462	17.56 484	26.45 482	65.85 442	11.72 464	57.00 474	14.79 482	17.31 490	62.05 471

test_fmvs1		53.60 406	52.54 401	56.78 438	58.07 464	30.26 460	68.95 423	42.19 478	32.46 464	63.59 229	82.56 277	11.55 465	60.81 465	58.25 257	55.27 384	79.28 376

tmp_tt		9.44 465	10.68 468	5.73 483	2.49 506	4.21 507	10.48 496	18.04 502	0.34 500	12.59 492	20.49 494	11.39 466	7.03 502	13.84 485	6.46 499	5.95 497

ITE_SJBPF				51.84 447	58.03 465	31.94 456		53.57 468	36.67 452	41.32 443	75.23 374	11.17 467	51.57 480	25.81 455	48.04 423	72.02 448

Anonymous20240521		51.65 416	48.42 418	61.34 425	56.43 469	39.65 422	73.57 389	73.47 397	36.64 453	36.59 458	63.98 447	10.75 468	72.25 448	35.35 411	49.01 412	72.11 447

mvs5depth		50.97 420	46.98 426	62.95 412	56.63 468	34.23 443	62.73 447	67.35 438	45.03 421	48.00 408	65.41 444	10.40 469	79.88 394	36.00 406	31.27 472	74.73 428

AllTest		47.32 429	44.66 431	55.32 444	65.08 444	37.50 433	62.96 445	54.25 466	35.45 459	33.42 469	72.82 396	9.98 470	59.33 468	24.13 459	43.84 442	69.13 455

TestCases				55.32 444	65.08 444	37.50 433		54.25 466	35.45 459	33.42 469	72.82 396	9.98 470	59.33 468	24.13 459	43.84 442	69.13 455

USDC		54.36 400	51.23 404	63.76 404	64.29 449	37.71 432	62.84 446	73.48 396	56.85 299	35.47 462	71.94 415	9.23 472	78.43 400	38.43 394	48.57 419	75.13 424

XVG-ACMP-BASELINE		56.03 393	52.85 397	65.58 392	61.91 458	40.95 417	63.36 441	72.43 403	45.20 419	46.02 422	74.09 380	9.20 473	78.12 404	45.13 366	58.27 351	77.66 400

test_fmvs1_n		52.55 411	51.19 405	56.65 439	51.90 475	30.14 461	67.66 427	42.84 477	32.27 465	62.30 243	82.02 291	9.12 474	60.84 464	57.82 266	54.75 390	78.99 378

test_vis1_n		51.19 419	49.66 414	55.76 443	51.26 478	29.85 466	67.20 430	38.86 482	32.12 466	59.50 278	79.86 314	8.78 475	58.23 472	56.95 275	52.46 404	79.19 377

pmmvs3		45.53 433	41.55 438	57.44 437	48.97 483	39.68 421	70.06 416	57.66 459	28.32 472	34.06 466	57.29 467	8.50 476	66.85 458	34.86 418	34.26 466	65.80 464

EGC-MVSNET		33.75 447	30.42 451	43.75 460	64.94 446	36.21 436	60.47 455	40.70 481	0.02 501	0.10 502	53.79 473	7.39 477	60.26 466	11.09 487	35.23 463	34.79 487

test_fmvs2		45.89 431	44.32 433	50.62 449	45.85 487	24.70 478	58.87 459	37.84 485	25.22 475	52.46 374	74.56 378	7.07 478	54.69 476	49.28 340	47.70 425	72.48 444

ANet_high		34.39 446	29.59 452	48.78 453	30.34 497	22.28 482	55.53 464	63.79 449	38.11 446	15.47 489	36.56 486	6.94 479	59.98 467	13.93 484	5.64 500	64.08 467

FPMVS		35.40 444	33.67 448	40.57 463	46.34 486	28.74 473	41.05 480	57.05 461	20.37 480	22.27 485	53.38 474	6.87 480	44.94 488	8.62 489	47.11 431	48.01 481

test_vis1_rt		40.29 439	38.64 440	45.25 458	48.91 484	30.09 462	59.44 456	27.07 496	24.52 477	38.48 454	51.67 477	6.71 481	49.44 481	44.33 371	46.59 435	56.23 473

new_pmnet		33.56 448	31.89 450	38.59 465	49.01 482	20.42 487	51.01 468	37.92 484	20.58 478	23.45 484	46.79 479	6.66 482	49.28 483	20.00 474	31.57 471	46.09 484

TinyColmap		48.15 428	44.49 432	59.13 433	65.73 439	38.04 430	63.34 442	62.86 452	38.78 442	29.48 476	67.23 436	6.46 483	73.30 442	24.59 458	41.90 447	66.04 463

ambc				62.06 417	53.98 472	29.38 469	35.08 486	79.65 291		41.37 441	59.96 461	6.27 484	82.15 364	35.34 412	38.22 456	74.65 429

TDRefinement		40.91 437	38.37 441	48.55 454	50.45 480	33.03 450	58.98 458	50.97 469	28.50 470	29.89 475	67.39 435	6.21 485	54.51 477	17.67 478	35.25 462	58.11 472

ttmdpeth		40.58 438	37.50 442	49.85 451	49.40 481	22.71 481	56.65 462	46.78 470	28.35 471	40.29 448	69.42 427	5.35 486	61.86 463	20.16 472	21.06 486	64.96 466

PM-MVS		46.92 430	43.76 436	56.41 441	52.18 474	32.26 454	63.21 444	38.18 483	37.99 447	40.78 446	66.20 439	5.09 487	65.42 459	48.19 349	41.99 446	71.54 451

LF4IMVS		33.04 449	32.55 449	34.52 469	40.96 488	22.03 483	44.45 477	35.62 487	20.42 479	28.12 479	62.35 452	5.03 488	31.88 499	21.61 469	34.42 464	49.63 480

EMVS		18.42 462	17.66 466	20.71 480	34.13 494	12.64 500	46.94 472	29.94 493	10.46 494	5.58 500	14.93 498	4.23 489	38.83 491	5.24 499	7.51 497	10.67 496

E-PMN		19.16 461	18.40 465	21.44 479	36.19 492	13.63 499	47.59 471	30.89 491	10.73 492	5.91 499	16.59 495	3.66 490	39.77 490	5.95 497	8.14 495	10.92 495

test_method		24.09 458	21.07 462	33.16 472	27.67 501	8.35 506	26.63 492	35.11 489	3.40 498	14.35 490	36.98 484	3.46 491	35.31 494	19.08 476	22.95 482	55.81 474

mvsany_test3		28.00 451	25.98 453	34.05 470	28.97 498	15.31 496	34.54 487	18.17 501	16.24 485	29.30 477	53.37 475	2.79 492	33.38 498	30.01 437	20.41 487	53.45 477

test_f		27.12 453	24.85 454	33.93 471	26.17 503	15.25 497	30.24 491	22.38 500	12.53 490	28.23 478	49.43 478	2.59 493	34.34 497	25.12 457	26.99 477	52.20 478

test_fmvs3		37.95 442	35.75 444	44.55 459	35.50 493	18.92 490	48.32 470	34.00 490	18.36 483	41.31 444	61.58 453	2.29 494	48.06 485	42.72 381	37.71 457	66.66 461

PMMVS2		26.71 454	22.98 459	37.87 467	36.89 491	8.51 505	42.51 479	29.32 494	19.09 482	13.01 491	37.54 482	2.23 495	53.11 478	14.54 483	11.71 493	51.99 479

Gipuma		27.47 452	24.26 457	37.12 468	60.55 463	29.17 470	11.68 495	60.00 455	14.18 487	10.52 496	15.12 497	2.20 496	63.01 462	8.39 490	35.65 460	19.18 493
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		28.07 450	23.85 458	40.71 462	27.46 502	18.93 489	30.82 490	46.19 471	12.76 489	16.40 487	34.70 488	1.90 497	48.69 484	20.25 471	24.22 481	54.51 476

DeepMVS_CX				13.10 481	21.34 505	8.99 503		10.02 505	10.59 493	7.53 498	30.55 491	1.82 498	14.55 500	6.83 494	7.52 496	15.75 494

APD_test1		26.46 455	24.41 456	32.62 474	37.58 490	21.74 485	40.50 482	30.39 492	11.45 491	16.33 488	43.76 480	1.63 499	41.62 489	11.24 486	26.82 478	34.51 488

PMVS	19.57 22	25.07 456	22.43 461	32.99 473	23.12 504	22.98 479	40.98 481	35.19 488	15.99 486	11.95 495	35.87 487	1.47 500	49.29 482	5.41 498	31.90 470	26.70 492
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		24.79 457	22.95 460	30.31 475	28.59 499	18.92 490	37.43 485	17.27 503	12.90 488	21.28 486	29.92 492	1.02 501	36.35 492	28.28 447	29.82 476	35.65 486

MVE	16.60 23	17.34 464	13.39 467	29.16 476	28.43 500	19.72 488	13.73 494	23.63 499	7.23 497	7.96 497	21.41 493	0.80 502	36.08 493	6.97 493	10.39 494	31.69 489
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testf1		21.11 459	19.08 463	27.18 477	30.56 495	18.28 492	33.43 488	24.48 497	8.02 495	12.02 493	33.50 489	0.75 503	35.09 495	7.68 491	21.32 483	28.17 490

APD_test2		21.11 459	19.08 463	27.18 477	30.56 495	18.28 492	33.43 488	24.48 497	8.02 495	12.02 493	33.50 489	0.75 503	35.09 495	7.68 491	21.32 483	28.17 490

wuyk23d		9.11 466	8.77 470	10.15 482	40.18 489	16.76 495	20.28 493	1.01 506	2.58 499	2.66 501	0.98 501	0.23 505	12.49 501	4.08 500	6.90 498	1.19 498

mmdepth		0.00 471	0.00 474	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	0.00 504	0.00 506	0.00 503	0.00 503	0.00 501	0.00 501

monomultidepth		0.00 471	0.00 474	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	0.00 504	0.00 506	0.00 503	0.00 503	0.00 501	0.00 501

test_blank		0.00 471	0.00 474	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	0.00 504	0.00 506	0.00 503	0.00 503	0.00 501	0.00 501

uanet_test		0.00 471	0.00 474	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	0.00 504	0.00 506	0.00 503	0.00 503	0.00 501	0.00 501

DCPMVS		0.00 471	0.00 474	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	0.00 504	0.00 506	0.00 503	0.00 503	0.00 501	0.00 501

sosnet-low-res		0.00 471	0.00 474	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	0.00 504	0.00 506	0.00 503	0.00 503	0.00 501	0.00 501

sosnet		0.00 471	0.00 474	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	0.00 504	0.00 506	0.00 503	0.00 503	0.00 501	0.00 501

uncertanet		0.00 471	0.00 474	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	0.00 504	0.00 506	0.00 503	0.00 503	0.00 501	0.00 501

Regformer		0.00 471	0.00 474	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	0.00 504	0.00 506	0.00 503	0.00 503	0.00 501	0.00 501

testmvs		6.14 468	8.18 471	0.01 484	0.01 507	0.00 510	73.40 392	0.00 508	0.00 502	0.02 503	0.15 502	0.00 506	0.00 503	0.02 501	0.00 501	0.02 499

test123		6.01 469	8.01 472	0.01 484	0.00 508	0.01 509	71.93 409	0.00 508	0.00 502	0.02 503	0.11 503	0.00 506	0.00 503	0.02 501	0.00 501	0.02 499

ab-mvs-re		7.68 467	10.24 469	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	92.12 59	0.00 506	0.00 503	0.00 503	0.00 501	0.00 501

uanet		0.00 471	0.00 474	0.00 486	0.00 508	0.00 510	0.00 497	0.00 508	0.00 502	0.00 505	0.00 504	0.00 506	0.00 503	0.00 503	0.00 501	0.00 501

MED-MVS test				80.14 38	84.34 91	54.93 83	87.61 72	87.22 81	57.43 290	81.85 18	92.88 44		93.75 31	80.19 52	85.13 48	91.76 61

WAC-MVS						34.28 441								22.56 465

FOURS1					83.24 119	49.90 239	84.98 180	78.76 314	47.71 397	73.42 78

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					0.00 508

eth-test					0.00 508

IU-MVS					89.48 18	57.49 18		91.38 9	66.22 102	88.26 2				82.83 32	87.60 19	92.44 33

save fliter					85.35 72	56.34 43	89.31 42	81.46 248	61.55 202

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																88.13 203

test_part2					89.33 24	55.48 56				82.27 13

MTGPA								81.31 251

MTMP							87.27 88	15.34 504

gm-plane-assit					83.24 119	54.21 116			70.91 30		88.23 162		95.25 15	66.37 172

test9_res														78.72 65	85.44 44	91.39 77

agg_prior2														75.65 88	85.11 51	91.01 101

agg_prior					85.64 65	54.92 88		83.61 206		72.53 94			88.10 224

test_prior4						56.39 42	87.15 92

test_prior				78.39 93	86.35 56	54.91 91		85.45 128					89.70 149			90.55 118

旧先验2							81.73 291		45.53 417	74.66 64			70.48 453	58.31 256

新几何2							81.61 297

无先验							85.19 166	78.00 331	49.08 386				85.13 331	52.78 314		87.45 220

原ACMM2							83.77 226

testdata2													77.81 413	45.64 365

testdata1							77.55 359		64.14 142

plane_prior7					77.95 283	48.46 285

plane_prior5								82.59 223					88.30 217	65.46 183	72.34 208	84.49 283

plane_prior4											83.28 262

plane_prior3						48.95 266			64.01 146	62.15 246

plane_prior2							85.76 135		63.60 158

plane_prior1					78.31 279

plane_prior						49.57 244	87.43 80		64.57 132						72.84 201

n2								0.00 508

nn								0.00 508

door-mid								41.31 480

test11								84.25 186

door								43.27 476

HQP5-MVS						51.56 191

HQP-NCC					79.02 258		88.00 61		65.45 117	64.48 207

ACMP_Plane					79.02 258		88.00 61		65.45 117	64.48 207

BP-MVS														66.70 169

HQP4-MVS										64.47 210			88.61 196			84.91 279

HQP3-MVS								83.68 201							73.12 197

NP-MVS					78.76 264	50.43 221					85.12 227

ACMMP++_ref															63.20 307

ACMMP++															59.38 340

High-resolution multi-view benchmark