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.

MCST-MVS		83.01 1	83.30 2	82.15 11	92.84 2	57.58 18	93.77 1	91.10 13	75.95 3	77.10 52	93.09 36	54.15 42	95.57 13	85.80 13	85.87 41	93.31 12

DELS-MVS		82.32 5	82.50 5	81.79 13	86.80 52	56.89 31	92.77 2	86.30 110	77.83 1	77.88 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
SED-MVS		81.92 8	81.75 9	82.44 8	89.48 18	56.89 31	92.48 3	88.94 37	57.50 298	84.61 5	94.09 8	58.81 14	96.37 7	82.28 38	87.60 19	94.06 4

OPU-MVS				81.71 14	92.05 3	55.97 52	92.48 3				94.01 10	67.21 2	95.10 16	89.82 3	92.55 3	94.06 4

DVP-MVS		81.30 10	81.00 13	82.20 9	89.40 21	57.45 21	92.34 5	89.99 23	57.71 292	81.91 16	93.64 20	55.17 33	96.44 2	81.68 42	87.13 22	92.72 30
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				82.20 9	89.50 16	57.73 15	92.34 5	88.88 39					96.39 4	81.68 42	87.13 22	92.47 34

test0726					89.40 21	57.45 21	92.32 7	88.63 50	57.71 292	83.14 10	93.96 11	55.17 33

DPM-MVS		82.39 4	82.36 7	82.49 6	80.12 233	59.50 5	92.24 8	90.72 18	69.37 58	83.22 9	94.47 4	63.81 6	93.18 39	74.02 115	93.25 2	94.80 1

MGCNet		82.10 7	82.64 4	80.47 29	86.63 54	54.69 107	92.20 9	86.66 101	74.48 5	82.63 11	93.80 16	50.83 68	93.70 34	90.11 2	86.44 34	93.01 22

MM		82.69 2	83.29 3	80.89 24	84.38 94	55.40 63	92.16 10	89.85 25	75.28 4	82.41 12	93.86 14	54.30 39	93.98 27	90.29 1	87.13 22	93.30 13

CNVR-MVS		81.76 9	81.90 8	81.33 20	90.04 11	57.70 16	91.71 11	88.87 41	70.31 40	77.64 51	93.87 13	52.58 52	93.91 30	84.17 23	87.92 17	92.39 36

PS-MVSNAJ		80.06 17	79.52 19	81.68 15	85.58 70	60.97 3	91.69 12	87.02 91	70.62 36	80.75 27	93.22 33	37.77 265	92.50 54	82.75 34	86.25 36	91.57 71

xiu_mvs_v2_base		79.86 19	79.31 21	81.53 17	85.03 82	60.73 4	91.65 13	86.86 94	70.30 41	80.77 26	93.07 38	37.63 271	92.28 61	82.73 35	85.71 42	91.57 71

CANet		80.90 11	81.17 12	80.09 42	87.62 45	54.21 122	91.60 14	86.47 106	73.13 9	79.89 34	93.10 34	49.88 79	92.98 40	84.09 25	84.75 56	93.08 20

lupinMVS		78.38 32	78.11 32	79.19 53	83.02 132	55.24 68	91.57 15	84.82 169	69.12 61	76.67 55	92.02 63	44.82 171	90.23 132	80.83 51	80.09 95	92.08 46

NCCC		79.57 21	79.23 22	80.59 26	89.50 16	56.99 28	91.38 16	88.17 66	67.71 82	73.81 76	92.75 47	46.88 113	93.28 36	78.79 66	84.07 61	91.50 77

test_yl		75.85 92	74.83 103	78.91 62	88.08 40	51.94 187	91.30 17	89.28 31	57.91 286	71.19 122	89.20 135	42.03 215	92.77 45	69.41 158	75.07 180	92.01 51

DCV-MVSNet		75.85 92	74.83 103	78.91 62	88.08 40	51.94 187	91.30 17	89.28 31	57.91 286	71.19 122	89.20 135	42.03 215	92.77 45	69.41 158	75.07 180	92.01 51

LFMVS		78.52 28	77.14 49	82.67 4	89.58 14	58.90 9	91.27 19	88.05 69	63.22 177	74.63 67	90.83 97	41.38 224	94.40 22	75.42 98	79.90 100	94.72 2

VDD-MVS		76.08 84	74.97 99	79.44 48	84.27 101	53.33 145	91.13 20	85.88 119	65.33 132	72.37 98	89.34 132	32.52 355	92.76 47	77.90 77	75.96 160	92.22 43

DeepPCF-MVS	69.37 1	80.65 13	81.56 11	77.94 110	85.46 73	49.56 258	90.99 21	86.66 101	70.58 38	80.07 33	95.30 2	56.18 28	90.97 104	82.57 37	86.22 37	93.28 14

VNet		77.99 41	77.92 35	78.19 103	87.43 47	50.12 244	90.93 22	91.41 8	67.48 86	75.12 62	90.15 117	46.77 118	91.00 99	73.52 123	78.46 118	93.44 10

CLD-MVS		75.60 102	75.39 88	76.24 167	80.69 213	52.40 173	90.69 23	86.20 112	74.40 6	65.01 204	88.93 139	42.05 214	90.58 118	76.57 86	73.96 193	85.73 273
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
jason		77.01 57	76.45 64	78.69 71	79.69 243	54.74 102	90.56 24	83.99 201	68.26 68	74.10 73	90.91 94	42.14 212	89.99 138	79.30 60	79.12 109	91.36 82
jason: jason.
IB-MVS	68.87 2	74.01 135	72.03 163	79.94 44	83.04 131	55.50 57	90.24 25	88.65 48	67.14 91	61.38 266	81.74 305	53.21 48	94.28 24	60.45 247	62.41 328	90.03 147
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
VDDNet		74.37 127	72.13 158	81.09 22	79.58 245	56.52 40	90.02 26	86.70 100	52.61 372	71.23 121	87.20 202	31.75 368	93.96 29	74.30 112	75.77 167	92.79 28

TSAR-MVS + GP.		77.82 42	77.59 40	78.49 90	85.25 78	50.27 243	90.02 26	90.57 19	56.58 323	74.26 72	91.60 78	54.26 40	92.16 64	75.87 92	79.91 99	93.05 21

DeepC-MVS_fast	67.50 3	78.00 40	77.63 39	79.13 57	88.52 29	55.12 76	89.95 28	85.98 117	68.31 67	71.33 120	92.75 47	45.52 154	90.37 125	71.15 146	85.14 50	91.91 55
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS++		80.50 14	80.71 14	79.88 45	87.34 48	55.20 74	89.93 29	87.55 81	66.04 120	79.46 38	93.00 40	53.10 49	91.76 72	80.40 52	89.56 9	92.68 32

MG-MVS		78.42 31	76.99 53	82.73 3	93.17 1	64.46 1	89.93 29	88.51 57	64.83 140	73.52 79	88.09 173	48.07 92	92.19 63	62.24 227	84.53 58	91.53 73

VPNet		72.07 181	71.42 171	74.04 250	78.64 277	47.17 342	89.91 31	87.97 70	72.56 13	64.66 211	85.04 240	41.83 219	88.33 219	61.17 237	60.97 337	86.62 254

alignmvs		78.08 39	77.98 33	78.39 97	83.53 114	53.22 148	89.77 32	85.45 133	66.11 115	76.59 57	91.99 65	54.07 43	89.05 179	77.34 80	77.00 137	92.89 24

APDe-MVS		78.44 30	78.20 30	79.19 53	88.56 28	54.55 113	89.76 33	87.77 75	55.91 335	78.56 44	92.49 53	48.20 91	92.65 49	79.49 58	83.04 66	90.39 127
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SteuartSystems-ACMMP		77.08 56	76.33 66	79.34 50	80.98 201	55.31 66	89.76 33	86.91 93	62.94 183	71.65 110	91.56 79	42.33 208	92.56 53	77.14 83	83.69 63	90.15 139
Skip Steuart: Steuart Systems R&D Blog.
0.4-1-1-0.2		72.79 162	71.07 178	77.94 110	80.58 217	50.83 220	89.59 35	88.63 50	63.94 159	65.74 193	81.80 304	46.05 134	90.68 112	62.98 220	60.35 341	92.31 40

Anonymous202405211		70.11 224	67.88 243	76.79 152	87.20 49	47.24 341	89.49 36	77.38 356	54.88 352	66.14 184	86.84 207	20.93 443	91.54 78	56.45 294	71.62 226	91.59 69

0.3-1-1-0.015		72.75 163	71.06 179	77.81 112	80.58 217	50.62 224	89.45 37	88.60 54	63.74 164	65.56 195	81.82 303	46.61 121	90.64 116	62.86 221	60.35 341	92.17 44

SPE-MVS-test		77.20 52	77.25 46	77.05 137	84.60 89	49.04 275	89.42 38	85.83 121	65.90 121	72.85 90	91.98 67	45.10 161	91.27 86	75.02 102	84.56 57	90.84 111

WBMVS		73.93 137	73.39 129	75.55 194	87.82 42	55.21 71	89.37 39	87.29 83	67.27 87	63.70 234	80.30 320	60.32 7	86.47 301	61.58 233	62.85 325	84.97 287

DP-MVS Recon		71.99 183	70.31 196	77.01 140	90.65 9	53.44 139	89.37 39	82.97 225	56.33 328	63.56 240	89.47 129	34.02 338	92.15 66	54.05 313	72.41 216	85.43 280

EPNet		78.36 33	78.49 28	77.97 107	85.49 72	52.04 183	89.36 41	84.07 198	73.22 8	77.03 53	91.72 73	49.32 85	90.17 134	73.46 125	82.77 67	91.69 65
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
NormalMVS		77.09 55	77.02 51	77.32 128	81.66 177	52.32 176	89.31 42	82.11 237	72.20 15	73.23 84	91.05 84	46.52 124	91.00 99	76.23 87	80.83 84	88.64 192

SymmetryMVS		77.43 50	77.09 50	78.44 95	82.56 150	52.32 176	89.31 42	84.15 196	72.20 15	73.23 84	91.05 84	46.52 124	91.00 99	76.23 87	78.55 117	92.00 53

save fliter					85.35 75	56.34 44	89.31 42	81.46 254	61.55 212

CSCG		80.41 15	79.72 17	82.49 6	89.12 26	57.67 17	89.29 45	91.54 5	59.19 260	71.82 108	90.05 119	59.72 11	96.04 11	78.37 69	88.40 14	93.75 8

MAR-MVS		76.76 65	75.60 81	80.21 34	90.87 8	54.68 108	89.14 46	89.11 34	62.95 182	70.54 142	92.33 56	41.05 225	94.95 18	57.90 276	86.55 33	91.00 105
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
0.4-1-1-0.1		72.39 171	70.70 184	77.46 124	80.45 223	50.04 246	89.09 47	88.45 59	63.06 180	64.91 208	81.60 308	45.98 138	90.46 122	62.40 224	60.34 343	91.88 57

test_prior2							89.04 48		61.88 207	73.55 78	91.46 82	48.01 96		74.73 103	85.46 45

ET-MVSNet_ETH3D		75.23 110	74.08 117	78.67 73	84.52 91	55.59 55	88.92 49	89.21 33	68.06 76	53.13 382	90.22 113	49.71 80	87.62 257	72.12 141	70.82 237	92.82 26

PVSNet_Blended		76.53 71	76.54 63	76.50 159	85.91 62	51.83 192	88.89 50	84.24 193	67.82 80	69.09 157	89.33 134	46.70 119	88.13 227	75.43 96	81.48 80	89.55 160

Anonymous20240529		69.71 235	67.28 260	77.00 141	83.78 110	50.36 238	88.87 51	85.10 157	47.22 413	64.03 225	83.37 270	27.93 391	92.10 67	57.78 279	67.44 272	88.53 201

DPE-MVS		79.82 20	79.66 18	80.29 33	89.27 25	55.08 79	88.70 52	87.92 71	55.55 340	81.21 24	93.69 19	56.51 26	94.27 26	78.36 70	85.70 43	91.51 76
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
aaEdge-Enhanced		79.48 23	79.20 23	80.35 32	88.96 27	54.93 87	88.65 53	88.50 58	56.62 320	79.87 35	92.88 44	51.96 56	94.36 23	80.19 53	85.13 51	91.76 63

CS-MVS		76.77 64	76.70 61	76.99 142	83.55 113	48.75 285	88.60 54	85.18 147	66.38 108	72.47 97	91.62 77	45.53 153	90.99 103	74.48 107	82.51 69	91.23 91

PHI-MVS		77.49 48	77.00 52	78.95 61	85.33 76	50.69 223	88.57 55	88.59 55	58.14 281	73.60 77	93.31 30	43.14 200	93.79 31	73.81 119	88.53 13	92.37 37

WTY-MVS		77.47 49	77.52 42	77.30 129	88.33 32	46.25 363	88.46 56	90.32 21	71.40 25	72.32 99	91.72 73	53.44 46	92.37 58	66.28 185	75.42 172	93.28 14

9.14			78.19 31		85.67 67		88.32 57	88.84 43	59.89 242	74.58 69	92.62 50	46.80 116	92.66 48	81.40 49	85.62 44

testing11		79.18 25	78.85 26	80.16 37	88.33 32	56.99 28	88.31 58	92.06 1	72.82 12	70.62 141	88.37 156	57.69 21	92.30 59	75.25 100	76.24 154	91.20 93

MVS_111021_HR		76.39 74	75.38 89	79.42 49	85.33 76	56.47 41	88.15 59	84.97 162	65.15 137	66.06 186	89.88 122	43.79 185	92.16 64	75.03 101	80.03 98	89.64 157

patch_mono-2		80.84 12	81.59 10	78.62 79	90.34 10	53.77 130	88.08 60	88.36 62	76.17 2	79.40 40	91.09 83	55.43 31	90.09 136	85.01 16	80.40 91	91.99 54

MS-PatchMatch		72.34 174	71.26 173	75.61 190	82.38 153	55.55 56	88.00 61	89.95 24	65.38 130	56.51 351	80.74 316	32.28 358	92.89 41	57.95 274	88.10 16	78.39 400

HQP-NCC					79.02 264		88.00 61		65.45 126	64.48 217

ACMP_Plane					79.02 264		88.00 61		65.45 126	64.48 217

HQP-MVS		72.34 174	71.44 170	75.03 219	79.02 264	51.56 202	88.00 61	83.68 206	65.45 126	64.48 217	85.13 235	37.35 278	88.62 200	66.70 180	73.12 206	84.91 289

testing99		78.45 29	77.78 38	80.45 30	88.28 35	56.81 34	87.95 65	91.49 6	71.72 19	70.84 134	88.09 173	57.29 23	92.63 52	69.24 162	75.13 178	91.91 55

testing91		78.30 36	77.54 41	80.61 25	88.16 38	57.12 27	87.94 66	91.07 16	71.43 24	70.75 136	88.04 178	55.82 30	92.65 49	69.61 157	75.00 183	92.05 49

casdiffmvs_mvg		77.75 44	77.28 45	79.16 55	80.42 227	54.44 116	87.76 67	85.46 132	71.67 21	71.38 119	88.35 159	51.58 57	91.22 89	79.02 62	79.89 101	91.83 60
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
sasdasda		78.17 37	77.86 36	79.12 58	84.30 98	54.22 120	87.71 68	84.57 184	67.70 83	77.70 49	92.11 61	50.90 64	89.95 140	78.18 73	77.54 129	93.20 16

canonicalmvs		78.17 37	77.86 36	79.12 58	84.30 98	54.22 120	87.71 68	84.57 184	67.70 83	77.70 49	92.11 61	50.90 64	89.95 140	78.18 73	77.54 129	93.20 16

UBG		78.86 27	78.86 25	78.86 65	87.80 43	55.43 59	87.67 70	91.21 12	72.83 11	72.10 102	88.40 154	58.53 18	89.08 177	73.21 130	77.98 124	92.08 46

VPA-MVSNet		71.12 202	70.66 186	72.49 300	78.75 271	44.43 388	87.64 71	90.02 22	63.97 157	65.02 203	81.58 309	42.14 212	87.42 265	63.42 216	63.38 316	85.63 277

aaatest				80.14 39	84.34 95	54.93 87	87.61 72	87.22 85	57.43 300	81.85 18	92.88 44		93.75 32	80.19 53	85.13 51	91.76 63

MED-MVS		79.56 22	79.39 20	80.06 43	84.34 95	54.93 87	87.61 72	87.22 85	56.22 331	81.85 18	92.98 41	58.11 20	93.75 32	80.19 53	85.96 38	91.52 74

TestfortrainingZip a		77.64 46	76.79 59	80.20 35	84.34 95	54.79 100	87.61 72	87.03 90	56.22 331	78.78 41	92.98 41	50.45 71	94.28 24	74.37 109	79.31 108	91.52 74

TestfortrainingZip				83.28 1	90.91 7	58.80 10	87.61 72	91.34 10	56.28 330	88.36 1	95.55 1	65.41 5	96.39 4		88.20 15	94.63 3

test_8					85.72 64	55.31 66	87.60 76	83.88 202	57.84 289	72.84 91	90.99 87	44.99 164	88.34 218

PRO-TEST		79.94 18	79.98 15	79.81 46	87.63 44	55.24 68	87.59 77	88.40 61	71.10 29	76.93 54	91.92 68	46.57 122	91.41 81	84.32 21	85.41 47	92.79 28

TEST9					85.68 65	55.42 60	87.59 77	84.00 199	57.72 291	72.99 87	90.98 88	44.87 169	88.58 203

train_agg		76.91 58	76.40 65	78.45 94	85.68 65	55.42 60	87.59 77	84.00 199	57.84 289	72.99 87	90.98 88	44.99 164	88.58 203	78.19 71	85.32 48	91.34 85

SMA-MVS		79.10 26	78.76 27	80.12 40	84.42 92	55.87 53	87.58 80	86.76 98	61.48 215	80.26 32	93.10 34	46.53 123	92.41 56	79.97 57	88.77 11	92.08 46
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
lecture		74.14 133	73.05 138	77.44 125	81.66 177	50.39 234	87.43 81	84.22 195	51.38 383	72.10 102	90.95 93	38.31 260	93.23 38	70.51 149	80.83 84	88.69 190

plane_prior						49.57 255	87.43 81		64.57 142						72.84 210

EC-MVSNet		75.30 105	75.20 90	75.62 189	80.98 201	49.00 276	87.43 81	84.68 181	63.49 172	70.97 128	90.15 117	42.86 205	91.14 93	74.33 111	81.90 75	86.71 253

TR-MVS		69.71 235	67.85 247	75.27 213	82.94 136	48.48 295	87.40 84	80.86 267	57.15 307	64.61 214	87.08 204	32.67 354	89.64 156	46.38 373	71.55 228	87.68 223

CDPH-MVS		76.05 85	75.19 91	78.62 79	86.51 55	54.98 84	87.32 85	84.59 183	58.62 275	70.75 136	90.85 96	43.10 202	90.63 117	70.50 150	84.51 59	90.24 133

3Dnovator+	62.71 7	72.29 177	70.50 189	77.65 118	83.40 119	51.29 210	87.32 85	86.40 108	59.01 267	58.49 316	88.32 162	32.40 356	91.27 86	57.04 285	82.15 74	90.38 128

API-MVS		74.17 132	72.07 160	80.49 27	90.02 12	58.55 11	87.30 87	84.27 190	57.51 297	65.77 192	87.77 186	41.61 221	95.97 12	51.71 336	82.63 68	86.94 241

BH-RMVSNet		70.08 226	68.01 237	76.27 165	84.21 102	51.22 212	87.29 88	79.33 312	58.96 269	63.63 238	86.77 208	33.29 346	90.30 130	44.63 382	73.96 193	87.30 233

MTMP							87.27 89	15.34 518

APD-MVS		76.15 82	75.68 77	77.54 121	88.52 29	53.44 139	87.26 90	85.03 160	53.79 362	74.91 65	91.68 75	43.80 184	90.31 128	74.36 110	81.82 76	88.87 185
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
testing222		77.70 45	77.22 48	79.14 56	86.95 50	54.89 96	87.18 91	91.96 2	72.29 14	71.17 124	88.70 144	55.19 32	91.24 88	65.18 200	76.32 152	91.29 87

EIA-MVS		75.92 89	75.18 92	78.13 104	85.14 79	51.60 201	87.17 92	85.32 139	64.69 141	68.56 162	90.53 102	45.79 147	91.58 77	67.21 178	82.18 73	91.20 93

test_prior4						56.39 43	87.15 93

casdiffmvs		77.36 51	76.85 55	78.88 64	80.40 228	54.66 110	87.06 94	85.88 119	72.11 17	71.57 112	88.63 149	50.89 67	90.35 126	76.00 90	79.11 110	91.63 68
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
cascas		69.01 252	66.13 284	77.66 117	79.36 251	55.41 62	86.99 95	83.75 204	56.69 318	58.92 302	81.35 310	24.31 423	92.10 67	53.23 319	70.61 239	85.46 279

nrg030		72.27 179	71.56 167	74.42 236	75.93 339	50.60 226	86.97 96	83.21 218	62.75 189	67.15 174	84.38 249	50.07 74	86.66 295	71.19 145	62.37 329	85.99 267

viewmanbaseed2359cas		76.71 67	76.16 70	78.37 99	81.16 195	55.05 80	86.96 97	85.32 139	71.71 20	72.25 101	88.50 152	46.86 114	88.96 186	74.55 105	78.08 123	91.08 98

FBQ-MVS		78.34 34	77.25 46	81.62 16	86.35 58	59.48 6	86.95 98	90.95 17	72.89 10	71.91 107	87.60 195	53.35 47	92.65 49	70.19 152	75.03 182	92.72 30

E3new		76.85 62	76.24 68	78.66 74	81.62 180	55.01 82	86.94 99	85.10 157	71.55 23	71.93 106	88.61 150	48.40 89	89.60 157	74.50 106	77.53 131	91.36 82

114514_t		69.87 233	67.88 243	75.85 182	88.38 31	52.35 175	86.94 99	83.68 206	53.70 363	55.68 357	85.60 227	30.07 381	91.20 90	55.84 299	71.02 235	83.99 306

CP-MVS		72.59 168	71.46 169	76.00 178	82.93 137	52.32 176	86.93 101	82.48 232	55.15 347	63.65 237	90.44 107	35.03 325	88.53 209	68.69 168	77.83 127	87.15 237

ZNCC-MVS		75.82 95	75.02 98	78.23 101	83.88 109	53.80 129	86.91 102	86.05 116	59.71 246	67.85 170	90.55 101	42.23 210	91.02 97	72.66 133	85.29 49	89.87 152

viewcassd2359sk11		76.66 68	76.01 74	78.62 79	81.14 196	54.95 85	86.88 103	85.04 159	71.37 27	71.76 109	88.44 153	48.02 95	89.57 159	74.17 113	77.23 133	91.33 86

PAPM		76.76 65	76.07 72	78.81 66	80.20 231	59.11 8	86.86 104	86.23 111	68.60 66	70.18 148	88.84 142	51.57 58	87.16 275	65.48 193	86.68 31	90.15 139

UWE-MVS		72.17 180	72.15 157	72.21 309	82.26 155	44.29 390	86.83 105	89.58 27	65.58 124	65.82 190	85.06 237	45.02 163	84.35 352	54.07 312	75.18 175	87.99 216

hybridcas		76.66 68	75.99 75	78.65 76	79.25 256	54.46 115	86.82 106	85.53 129	70.88 35	70.40 146	88.21 166	49.55 82	90.12 135	74.42 108	78.88 114	91.37 81

E2		76.39 74	75.67 78	78.56 86	80.49 220	54.87 97	86.80 107	84.95 163	71.09 30	71.51 115	88.21 166	47.55 102	89.53 160	73.65 121	76.77 143	91.29 87

E3		76.39 74	75.67 78	78.56 86	80.49 220	54.87 97	86.80 107	84.95 163	71.09 30	71.51 115	88.21 166	47.55 102	89.53 160	73.65 121	76.77 143	91.29 87

Fast-Effi-MVS+		72.73 164	71.15 176	77.48 122	82.75 144	54.76 101	86.77 109	80.64 271	63.05 181	65.93 188	84.01 255	44.42 178	89.03 180	56.45 294	76.36 151	88.64 192

viewmacassd2359aftdt		75.91 90	75.14 94	78.21 102	79.40 250	54.82 99	86.71 110	84.98 161	70.89 34	71.52 114	87.89 183	45.43 156	88.85 195	72.35 136	77.08 135	90.97 107

thisisatest0515		73.64 147	72.20 155	77.97 107	81.63 179	53.01 157	86.69 111	88.81 44	62.53 194	64.06 224	85.65 226	52.15 55	92.50 54	58.43 263	69.84 249	88.39 206

E4		75.99 86	75.16 93	78.48 91	79.56 246	54.74 102	86.66 112	84.80 171	70.62 36	71.16 125	87.90 182	46.84 115	89.47 164	72.70 132	76.20 156	91.23 91

SF-MVS		77.64 46	77.42 44	78.32 100	83.75 111	52.47 172	86.63 113	87.80 72	58.78 272	74.63 67	92.38 55	47.75 100	91.35 83	78.18 73	86.85 28	91.15 96

BH-w/o		70.02 228	68.51 229	74.56 232	82.77 143	50.39 234	86.60 114	78.14 340	59.77 245	59.65 284	85.57 228	39.27 251	87.30 270	49.86 347	74.94 184	85.99 267

DeepC-MVS	67.15 4	76.90 60	76.27 67	78.80 67	80.70 212	55.02 81	86.39 115	86.71 99	66.96 99	67.91 169	89.97 121	48.03 94	91.41 81	75.60 95	84.14 60	89.96 149
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TransMVSNet (Re)		62.82 352	60.76 354	69.02 365	73.98 372	41.61 423	86.36 116	79.30 313	56.90 309	52.53 385	76.44 371	41.85 218	87.60 258	38.83 406	40.61 463	77.86 407

fmvsm_l_conf0.5_n_9		77.10 54	77.48 43	75.98 179	77.54 301	47.77 329	86.35 117	73.46 409	68.69 65	81.07 25	94.40 5	49.06 86	88.89 191	87.39 8	79.32 107	91.27 90

MSLP-MVS++		74.21 131	72.25 154	80.11 41	81.45 190	56.47 41	86.32 118	79.65 300	58.19 280	66.36 183	92.29 57	36.11 307	90.66 114	67.39 176	82.49 70	93.18 18

QAPM		71.88 187	69.33 215	79.52 47	82.20 161	54.30 118	86.30 119	88.77 45	56.61 321	59.72 283	87.48 196	33.90 340	95.36 14	47.48 365	81.49 79	88.90 183

WR-MVS		67.58 283	66.76 270	70.04 356	75.92 340	45.06 383	86.23 120	85.28 143	64.31 146	58.50 315	81.00 311	44.80 173	82.00 378	49.21 353	55.57 395	83.06 335

blend_shiyan4		67.33 293	65.28 306	73.45 272	70.71 411	47.96 319	86.21 121	85.65 127	56.45 327	52.18 390	72.99 406	45.89 143	88.50 210	56.81 287	60.68 339	83.90 312

PVSNet_BlendedMVS		73.42 150	73.30 131	73.76 261	85.91 62	51.83 192	86.18 122	84.24 193	65.40 129	69.09 157	80.86 314	46.70 119	88.13 227	75.43 96	65.92 291	81.33 365

viewdifsd2359ckpt13		75.96 87	75.07 95	78.65 76	81.14 196	55.21 71	86.15 123	84.95 163	69.98 47	70.49 144	88.16 169	46.10 132	89.86 142	72.39 135	76.23 155	90.89 110

ETV-MVS		77.17 53	76.74 60	78.48 91	81.80 169	54.55 113	86.13 124	85.33 138	68.20 70	73.10 86	90.52 103	45.23 160	90.66 114	79.37 59	80.95 81	90.22 134

AdaColmap		67.86 276	65.48 300	75.00 221	88.15 39	54.99 83	86.10 125	76.63 371	49.30 397	57.80 325	86.65 212	29.39 384	88.94 189	45.10 379	70.21 247	81.06 370

myMVS_eth3d28		77.77 43	77.94 34	77.27 131	87.58 46	52.89 161	86.06 126	91.33 11	74.15 7	68.16 166	88.24 164	58.17 19	88.31 221	69.88 156	77.87 125	90.61 120

OPM-MVS		70.75 212	69.58 210	74.26 244	75.55 345	51.34 208	86.05 127	83.29 217	61.94 206	62.95 247	85.77 225	34.15 337	88.44 213	65.44 197	71.07 234	82.99 336
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet		70.61 216	69.34 214	74.42 236	80.95 206	48.49 294	86.03 128	77.51 353	58.74 273	65.55 196	87.78 185	34.37 335	85.95 326	52.53 332	80.61 87	88.80 187
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Anonymous20231211		66.08 320	63.67 323	73.31 275	83.07 129	48.75 285	86.01 129	84.67 182	45.27 430	56.54 349	76.67 369	28.06 390	88.95 187	52.78 326	59.95 344	82.23 346

gbinet_0.2-2-1-0.02		64.20 335	61.39 346	72.63 295	70.85 410	46.32 361	85.92 130	85.98 117	55.27 346	51.88 393	72.29 420	33.14 347	87.82 240	48.50 358	48.72 430	83.73 315

E5new		75.74 97	74.80 105	78.57 84	79.85 237	54.93 87	85.87 131	84.72 176	70.19 43	70.90 130	87.74 187	45.97 141	89.71 150	72.15 139	75.79 162	91.06 100

E6new		75.74 97	74.80 105	78.56 86	79.85 237	54.92 92	85.87 131	84.72 176	70.19 43	70.90 130	87.73 189	45.98 138	89.71 150	72.16 137	75.78 165	91.06 100

E6		75.74 97	74.80 105	78.56 86	79.85 237	54.92 92	85.87 131	84.72 176	70.19 43	70.90 130	87.73 189	45.98 138	89.71 150	72.16 137	75.78 165	91.06 100

E5		75.74 97	74.80 105	78.57 84	79.85 237	54.93 87	85.87 131	84.72 176	70.19 43	70.90 130	87.74 187	45.97 141	89.71 150	72.15 139	75.79 162	91.06 100

fmvsm_s_conf0.5_n_4		74.92 117	74.88 101	75.03 219	75.96 338	47.53 332	85.84 135	73.19 411	67.07 94	79.43 39	92.60 51	46.12 130	88.03 232	84.70 18	69.01 256	89.53 162

Casviewmamba		76.27 78	75.48 84	78.63 78	79.14 260	54.27 119	85.81 136	83.09 221	70.96 32	70.41 145	88.36 158	48.71 88	90.81 108	75.92 91	76.95 138	90.80 113

EG-PatchMatch MVS		62.40 360	59.59 364	70.81 342	73.29 377	49.05 273	85.81 136	84.78 172	51.85 379	44.19 439	73.48 402	15.52 472	89.85 144	40.16 402	67.24 273	73.54 448

PVSNet_Blended_VisFu		73.40 151	72.44 147	76.30 163	81.32 194	54.70 106	85.81 136	78.82 321	63.70 165	64.53 216	85.38 232	47.11 110	87.38 268	67.75 175	77.55 128	86.81 251

HQP_MVS		70.96 208	69.91 206	74.12 248	77.95 289	49.57 255	85.76 139	82.59 229	63.60 168	62.15 257	83.28 272	36.04 310	88.30 222	65.46 194	72.34 218	84.49 293

plane_prior2							85.76 139		63.60 168

GST-MVS		74.87 119	73.90 122	77.77 114	83.30 121	53.45 138	85.75 141	85.29 142	59.22 259	66.50 182	89.85 123	40.94 227	90.76 109	70.94 147	83.35 64	89.10 180

SD-MVS		76.18 80	74.85 102	80.18 36	85.39 74	56.90 30	85.75 141	82.45 233	56.79 316	74.48 70	91.81 70	43.72 188	90.75 110	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
usedtu_dtu_shiyan1		69.05 249	67.91 239	72.46 302	75.40 347	46.24 364	85.74 143	86.80 95	65.23 135	58.75 308	80.31 318	40.90 229	86.83 286	53.29 317	64.77 297	84.31 297

FE-MVSNET3		69.05 249	67.91 239	72.46 302	75.39 348	46.24 364	85.74 143	86.80 95	65.23 135	58.75 308	80.31 318	40.90 229	86.83 286	53.29 317	64.77 297	84.31 297

CHOSEN 1792x2688		76.24 79	74.03 119	82.88 2	83.09 128	62.84 2	85.73 145	85.39 135	69.79 51	64.87 209	83.49 267	41.52 223	93.69 35	70.55 148	81.82 76	92.12 45

WB-MVSnew		69.36 245	68.24 234	72.72 291	79.26 255	49.40 267	85.72 146	88.85 42	61.33 216	64.59 215	82.38 291	34.57 332	87.53 261	46.82 371	70.63 238	81.22 369

wanda-best-256-512		64.87 328	62.23 334	72.81 287	70.49 416	46.85 345	85.71 147	85.71 123	56.85 310	51.25 396	72.31 417	36.16 304	87.84 238	52.67 330	48.90 426	83.73 315

FE-blended-shiyan7		64.87 328	62.23 334	72.81 287	70.49 416	46.85 345	85.71 147	85.71 123	56.85 310	51.25 396	72.31 417	36.16 304	87.84 238	52.67 330	48.90 426	83.73 315

FMVSNet3		68.84 255	67.40 257	73.19 279	85.05 80	48.53 292	85.71 147	85.36 136	60.90 229	57.58 331	79.15 336	42.16 211	86.77 290	47.25 367	63.40 313	84.27 299

viewdifsd2359ckpt07		74.81 120	74.01 120	77.21 135	79.62 244	53.13 153	85.70 150	83.75 204	68.12 71	68.14 167	87.33 201	46.51 126	87.92 234	73.32 126	73.63 199	90.57 121

MP-MVS		74.99 115	74.33 113	76.95 144	82.89 139	53.05 156	85.63 151	83.50 212	57.86 288	67.25 173	90.24 111	43.38 196	88.85 195	76.03 89	82.23 72	88.96 182
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HFP-MVS		74.37 127	73.13 137	78.10 105	84.30 98	53.68 132	85.58 152	84.36 188	56.82 314	65.78 191	90.56 100	40.70 234	90.90 105	69.18 163	80.88 82	89.71 154

ACMMPR		73.76 142	72.61 143	77.24 134	83.92 107	52.96 159	85.58 152	84.29 189	56.82 314	65.12 200	90.45 104	37.24 283	90.18 133	69.18 163	80.84 83	88.58 196

BH-untuned		68.28 269	66.40 277	73.91 255	81.62 180	50.01 247	85.56 154	77.39 355	57.63 294	57.47 336	83.69 264	36.36 301	87.08 277	44.81 380	73.08 209	84.65 292

ETVMVS		75.80 96	75.44 86	76.89 146	86.23 60	50.38 236	85.55 155	91.42 7	71.30 28	68.80 160	87.94 181	56.42 27	89.24 171	56.54 290	74.75 187	91.07 99

region2R		73.75 143	72.55 145	77.33 127	83.90 108	52.98 158	85.54 156	84.09 197	56.83 313	65.10 201	90.45 104	37.34 280	90.24 131	68.89 165	80.83 84	88.77 189

fmvsm_s_conf0.5_n_6		76.17 81	76.84 56	74.15 247	77.42 304	46.46 355	85.53 157	77.86 346	69.78 52	79.78 36	92.90 43	46.80 116	84.81 347	84.67 19	76.86 142	91.17 95

blended_shiyan8		64.70 330	62.04 338	72.69 292	70.33 420	46.62 351	85.48 158	85.66 125	56.58 323	50.94 403	72.18 421	35.81 314	87.80 244	52.47 333	48.91 425	83.65 324

blended_shiyan6		64.70 330	62.04 338	72.69 292	70.34 419	46.60 353	85.48 158	85.65 127	56.59 322	50.91 404	72.18 421	35.82 313	87.81 241	52.46 334	48.90 426	83.66 323

testing3-2		72.30 176	72.35 149	72.15 311	83.07 129	47.64 330	85.46 160	89.81 26	66.17 113	61.96 261	84.88 244	58.93 13	82.27 373	55.87 297	64.97 295	86.54 255

fmvsm_l_conf0.5_n_3		75.73 101	75.78 76	75.61 190	76.03 335	48.33 302	85.34 161	72.92 412	67.16 90	78.55 45	93.85 15	46.22 128	87.53 261	85.61 14	76.30 153	90.98 106

xiu_mvs_v1_base_debu		71.60 193	70.29 197	75.55 194	77.26 309	53.15 150	85.34 161	79.37 306	55.83 336	72.54 93	90.19 114	22.38 434	86.66 295	73.28 127	76.39 148	86.85 246

xiu_mvs_v1_base		71.60 193	70.29 197	75.55 194	77.26 309	53.15 150	85.34 161	79.37 306	55.83 336	72.54 93	90.19 114	22.38 434	86.66 295	73.28 127	76.39 148	86.85 246

xiu_mvs_v1_base_debi		71.60 193	70.29 197	75.55 194	77.26 309	53.15 150	85.34 161	79.37 306	55.83 336	72.54 93	90.19 114	22.38 434	86.66 295	73.28 127	76.39 148	86.85 246

fmvsm_s_conf0.5_n		74.48 123	74.12 116	75.56 193	76.96 316	47.85 324	85.32 165	69.80 438	64.16 151	78.74 42	93.48 24	45.51 155	89.29 169	86.48 11	66.62 278	89.55 160

NR-MVSNet		67.25 295	65.99 288	71.04 339	73.27 379	43.91 395	85.32 165	84.75 174	66.05 119	53.65 380	82.11 298	45.05 162	85.97 325	47.55 364	56.18 387	83.24 330

fmvsm_l_conf0.5_n_a		75.88 91	76.07 72	75.31 207	76.08 332	48.34 300	85.24 167	70.62 431	63.13 179	81.45 22	93.62 22	49.98 77	87.40 267	87.76 7	76.77 143	90.20 136

GDP-MVS		75.27 107	74.38 112	77.95 109	79.04 263	52.86 163	85.22 168	86.19 113	62.43 198	70.66 139	90.40 108	53.51 45	91.60 76	69.25 161	72.68 213	89.39 169

Effi-MVS+		75.24 109	73.61 128	80.16 37	81.92 166	57.42 23	85.21 169	76.71 369	60.68 233	73.32 82	89.34 132	47.30 107	91.63 75	68.28 171	79.72 102	91.42 78

无先验							85.19 170	78.00 342	49.08 398				85.13 342	52.78 326		87.45 229

fmvsm_s_conf0.5_n_8		76.50 72	76.68 62	75.94 180	78.67 273	47.92 322	85.18 171	74.71 388	68.09 72	80.67 29	94.26 6	47.09 111	89.26 170	86.62 10	74.85 185	90.65 117

FMVSNet2		67.57 284	65.79 293	72.90 284	82.71 145	47.97 317	85.15 172	84.93 166	58.55 276	56.71 347	78.26 344	36.72 296	86.67 294	46.15 375	62.94 324	84.07 303

casdiffseed414692147		74.22 130	72.73 142	78.69 71	79.85 237	54.64 111	85.13 173	83.67 210	69.07 62	69.41 151	86.47 216	43.27 197	90.69 111	63.77 213	73.91 196	90.73 115

test-LLR		69.65 240	69.01 223	71.60 328	78.67 273	48.17 308	85.13 173	79.72 295	59.18 262	63.13 243	82.58 285	36.91 291	80.24 397	60.56 243	75.17 176	86.39 261

TESTMET0.1,1		72.86 160	72.33 150	74.46 234	81.98 163	50.77 221	85.13 173	85.47 131	66.09 116	67.30 172	83.69 264	37.27 281	83.57 363	65.06 202	78.97 113	89.05 181

test-mter		68.36 266	67.29 259	71.60 328	78.67 273	48.17 308	85.13 173	79.72 295	53.38 366	63.13 243	82.58 285	27.23 397	80.24 397	60.56 243	75.17 176	86.39 261

1112_ss		70.05 227	69.37 213	72.10 312	80.77 211	42.78 410	85.12 177	76.75 366	59.69 247	61.19 268	92.12 59	47.48 105	83.84 358	53.04 322	68.21 265	89.66 156

XXY-MVS		70.18 221	69.28 217	72.89 286	77.64 293	42.88 409	85.06 178	87.50 82	62.58 193	62.66 251	82.34 295	43.64 190	89.83 145	58.42 265	63.70 310	85.96 269

KinetiMVS		71.15 200	69.25 218	76.82 148	77.99 288	50.49 229	85.05 179	86.51 104	59.78 244	64.10 223	85.34 233	32.16 359	91.33 85	58.82 259	73.54 201	88.64 192

MSP-MVS		82.30 6	83.47 1	78.80 67	82.99 134	52.71 167	85.04 180	88.63 50	66.08 117	86.77 4	92.75 47	72.05 1	91.46 80	83.35 30	93.53 1	92.23 41
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
fmvsm_s_conf0.5_n_11		76.28 77	76.81 57	74.71 229	79.21 257	46.90 344	85.03 181	73.96 398	69.00 63	79.70 37	93.88 12	48.07 92	87.71 251	84.26 22	78.15 122	89.50 165

thres200		68.71 260	67.27 261	73.02 280	84.73 85	46.76 348	85.03 181	87.73 76	62.34 199	59.87 280	83.45 268	43.15 199	88.32 220	31.25 446	67.91 269	83.98 308

MVP-Stereo		70.97 207	70.44 190	72.59 297	76.03 335	51.36 207	85.02 183	86.99 92	60.31 237	56.53 350	78.92 338	40.11 241	90.00 137	60.00 251	90.01 7	76.41 425
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
fmvsm_l_conf0.5_n		75.95 88	76.16 70	75.31 207	76.01 337	48.44 297	84.98 184	71.08 428	63.50 171	81.70 21	93.52 23	50.00 75	87.18 274	87.80 6	76.87 141	90.32 131

DVP-MVS++		82.44 3	82.38 6	82.62 5	91.77 4	57.49 19	84.98 184	88.88 39	58.00 284	83.60 7	93.39 27	67.21 2	96.39 4	81.64 44	91.98 4	93.98 6

FOURS1					83.24 123	49.90 250	84.98 184	78.76 324	47.71 409	73.42 80

PS-MVSNAJss		68.78 259	67.17 263	73.62 267	73.01 382	48.33 302	84.95 187	84.81 170	59.30 258	58.91 303	79.84 326	37.77 265	88.86 192	62.83 222	63.12 322	83.67 322

v2v482		69.55 242	67.64 250	75.26 214	72.32 392	53.83 128	84.93 188	81.94 242	65.37 131	60.80 272	79.25 334	41.62 220	88.98 185	63.03 219	59.51 350	82.98 338

XVS		72.92 158	71.62 166	76.81 149	83.41 116	52.48 170	84.88 189	83.20 219	58.03 282	63.91 227	89.63 127	35.50 318	89.78 146	65.50 191	80.50 89	88.16 209

X-MVStestdata		65.85 322	62.20 336	76.81 149	83.41 116	52.48 170	84.88 189	83.20 219	58.03 282	63.91 227	4.82 531	35.50 318	89.78 146	65.50 191	80.50 89	88.16 209

guyue		70.53 217	69.12 219	74.76 228	77.61 294	47.53 332	84.86 191	85.17 148	62.70 191	62.18 255	83.74 261	34.72 328	89.86 142	64.69 204	66.38 283	86.87 243

dcpmvs_2		79.33 24	78.94 24	80.49 27	89.75 13	56.54 39	84.83 192	83.68 206	67.85 79	69.36 153	90.24 111	60.20 9	92.10 67	84.14 24	80.40 91	92.82 26

test1111		71.06 205	70.42 193	72.97 282	79.48 249	41.49 425	84.82 193	82.74 228	64.20 150	62.98 245	87.43 198	35.20 321	87.92 234	58.54 262	78.42 119	89.49 166

viewdifsd2359ckpt09		74.92 117	73.70 126	78.60 83	80.28 229	54.94 86	84.77 194	80.56 275	69.96 49	69.38 152	88.38 155	46.01 137	90.50 121	72.44 134	71.49 229	90.38 128

Fast-Effi-MVS+-dtu		66.53 312	64.10 322	73.84 258	72.41 390	52.30 179	84.73 195	75.66 378	59.51 250	56.34 352	79.11 337	28.11 389	85.85 328	57.74 280	63.29 317	83.35 326

BP-MVS1		76.09 83	75.55 82	77.71 116	79.49 248	52.27 180	84.70 196	90.49 20	64.44 143	69.86 150	90.31 110	55.05 36	91.35 83	70.07 154	75.58 171	89.53 162

ECVR-MVS		71.81 188	71.00 181	74.26 244	80.12 233	43.49 399	84.69 197	82.16 234	64.02 153	64.64 212	87.43 198	35.04 324	89.21 174	61.24 236	79.66 103	90.08 145

h-mvs33		73.95 136	72.89 140	77.15 136	80.17 232	50.37 237	84.68 198	83.33 213	68.08 73	71.97 104	88.65 148	42.50 206	91.15 92	78.82 64	57.78 375	89.91 151

v1144		68.81 257	66.82 268	74.80 227	72.34 391	53.46 136	84.68 198	81.77 249	64.25 148	60.28 277	77.91 346	40.23 238	88.95 187	60.37 248	59.52 349	81.97 348

CANet_DTU		73.71 144	73.14 135	75.40 201	82.61 149	50.05 245	84.67 200	79.36 309	69.72 54	75.39 61	90.03 120	29.41 383	85.93 327	67.99 174	79.11 110	90.22 134

VortexMVS		68.49 264	66.84 267	73.46 271	81.10 200	48.75 285	84.63 201	84.73 175	62.05 202	57.22 341	77.08 361	34.54 334	89.20 175	63.08 217	57.12 379	82.43 344

test_vis1_n_1920		68.59 263	68.31 232	69.44 362	69.16 432	41.51 424	84.63 201	68.58 444	58.80 271	73.26 83	88.37 156	25.30 412	80.60 392	79.10 61	67.55 271	86.23 263

PVSNet	62.49 8	69.27 246	67.81 248	73.64 265	84.41 93	51.85 191	84.63 201	77.80 347	66.42 107	59.80 282	84.95 242	22.14 438	80.44 395	55.03 306	75.11 179	88.62 195

fmvsm_s_conf0.1_n		73.80 141	73.26 132	75.43 200	73.28 378	47.80 327	84.57 204	69.43 440	63.34 174	78.40 46	93.29 31	44.73 174	89.22 173	85.99 12	66.28 287	89.26 172

fmvsm_s_conf0.5_n_2		72.02 182	71.72 165	72.92 283	76.79 319	45.90 369	84.48 205	66.11 451	64.26 147	76.12 59	93.40 26	36.26 302	86.04 319	81.47 46	66.54 281	86.82 250

mPP-MVS		71.79 190	70.38 194	76.04 176	82.65 148	52.06 182	84.45 206	81.78 248	55.59 339	62.05 260	89.68 126	33.48 344	88.28 224	65.45 196	78.24 121	87.77 220

CL-MVSNet_self_test		62.98 350	61.14 351	68.50 377	65.86 450	42.96 407	84.37 207	82.98 224	60.98 225	53.95 376	72.70 410	40.43 236	83.71 361	41.10 399	47.93 436	78.83 392

OpenMVS	61.00 11	69.99 230	67.55 253	77.30 129	78.37 283	54.07 127	84.36 208	85.76 122	57.22 305	56.71 347	87.67 192	30.79 375	92.83 43	43.04 391	84.06 62	85.01 286

AstraMVS		70.12 223	68.56 226	74.81 226	76.48 322	47.48 334	84.35 209	82.58 231	63.80 161	62.09 259	84.54 245	31.39 371	89.96 139	68.24 173	63.58 311	87.00 240

MP-MVS-pluss		75.54 104	75.03 97	77.04 138	81.37 192	52.65 169	84.34 210	84.46 186	61.16 219	69.14 156	91.76 71	39.98 244	88.99 184	78.19 71	84.89 55	89.48 167
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PAPR		75.20 111	74.13 115	78.41 96	88.31 34	55.10 78	84.31 211	85.66 125	63.76 163	67.55 171	90.73 99	43.48 193	89.40 165	66.36 184	77.03 136	90.73 115

SR-MVS		70.92 209	69.73 208	74.50 233	83.38 120	50.48 231	84.27 212	79.35 310	48.96 400	66.57 181	90.45 104	33.65 343	87.11 276	66.42 182	74.56 188	85.91 270

v148		68.24 271	66.35 278	73.88 256	71.76 397	51.47 205	84.23 213	81.90 246	63.69 166	58.94 300	76.44 371	43.72 188	87.78 248	60.63 241	55.86 392	82.39 345

UniMVSNet_NR-MVSNet		68.82 256	68.29 233	70.40 349	75.71 342	42.59 412	84.23 213	86.78 97	66.31 109	58.51 313	82.45 288	51.57 58	84.64 350	53.11 320	55.96 390	83.96 310

fmvsm_s_conf0.1_n_2		71.45 196	71.01 180	72.78 289	75.37 349	45.82 373	84.18 215	64.59 459	64.02 153	75.67 60	93.02 39	34.99 326	85.99 322	81.18 50	66.04 290	86.52 257

GeoE		69.96 231	67.88 243	76.22 168	81.11 199	51.71 199	84.15 216	76.74 368	59.83 243	60.91 270	84.38 249	41.56 222	88.10 229	51.67 337	70.57 240	88.84 186

v144192		67.86 276	65.76 294	74.16 246	71.68 398	53.09 154	84.14 217	80.83 268	62.85 188	59.21 296	77.28 357	39.30 250	88.00 233	58.67 261	57.88 373	81.40 362

UGNet		68.71 260	67.11 264	73.50 270	80.55 219	47.61 331	84.08 218	78.51 332	59.45 251	65.68 194	82.73 281	23.78 425	85.08 343	52.80 325	76.40 147	87.80 219
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
PMMVS		72.98 157	72.05 161	75.78 184	83.57 112	48.60 289	84.08 218	82.85 227	61.62 211	68.24 165	90.33 109	28.35 387	87.78 248	72.71 131	76.69 146	90.95 108

ACMMP_NAP		76.43 73	75.66 80	78.73 69	81.92 166	54.67 109	84.06 220	85.35 137	61.10 222	72.99 87	91.50 80	40.25 237	91.00 99	76.84 85	86.98 26	90.51 125

v1192		67.96 275	65.74 295	74.63 231	71.79 396	53.43 141	84.06 220	80.99 266	63.19 178	59.56 287	77.46 353	37.50 277	88.65 199	58.20 269	58.93 356	81.79 351

fmvsm_s_conf0.5_n_5		75.02 114	75.07 95	74.88 224	74.33 367	47.83 326	83.99 222	73.54 404	67.10 92	76.32 58	92.43 54	45.42 157	86.35 307	82.98 32	79.50 106	90.47 126

FIs		70.00 229	70.24 200	69.30 363	77.93 291	38.55 441	83.99 222	87.72 77	66.86 100	57.66 329	84.17 253	52.28 53	85.31 336	52.72 329	68.80 261	84.02 304

MVS_Test		75.85 92	74.93 100	78.62 79	84.08 103	55.20 74	83.99 222	85.17 148	68.07 75	73.38 81	82.76 278	50.44 72	89.00 182	65.90 189	80.61 87	91.64 67

reproduce_monomvs		69.71 235	68.52 228	73.29 277	86.43 57	48.21 307	83.91 225	86.17 114	68.02 77	54.91 363	77.46 353	42.96 203	88.86 192	68.44 169	48.38 432	82.80 341

baseline		76.86 61	76.24 68	78.71 70	80.47 222	54.20 124	83.90 226	84.88 168	71.38 26	71.51 115	89.15 137	50.51 70	90.55 119	75.71 93	78.65 115	91.39 79

fmvsm_s_conf0.5_n_a		73.68 146	73.15 133	75.29 210	75.45 346	48.05 314	83.88 227	68.84 443	63.43 173	78.60 43	93.37 29	45.32 158	88.92 190	85.39 15	64.04 305	88.89 184

baseline2		75.15 112	74.54 111	76.98 143	81.67 176	51.74 198	83.84 228	91.94 3	69.97 48	58.98 299	86.02 222	59.73 10	91.73 74	68.37 170	70.40 246	87.48 227

EPP-MVSNet		71.14 201	70.07 203	74.33 241	79.18 259	46.52 354	83.81 229	86.49 105	56.32 329	57.95 322	84.90 243	54.23 41	89.14 176	58.14 270	69.65 252	87.33 231

原ACMM2							83.77 230

v1921920		67.45 287	65.23 308	74.10 249	71.51 401	52.90 160	83.75 231	80.44 276	62.48 197	59.12 297	77.13 358	36.98 289	87.90 236	57.53 281	58.14 367	81.49 357

hybridnocas07		74.65 122	74.00 121	76.61 157	77.58 297	52.72 166	83.64 232	79.72 295	69.43 57	70.80 135	88.33 161	45.56 151	87.34 269	76.88 84	74.07 191	89.78 153

OpenMVS_ROB	53.19 17	59.20 377	56.00 390	68.83 368	71.13 407	44.30 389	83.64 232	75.02 385	46.42 420	46.48 433	73.03 405	18.69 455	88.14 226	27.74 462	61.80 331	74.05 444

MVSTER		73.25 153	72.33 150	76.01 177	85.54 71	53.76 131	83.52 234	87.16 88	67.06 95	63.88 229	81.66 306	52.77 50	90.44 123	64.66 205	64.69 301	83.84 314

GBi-Net		67.09 300	65.47 301	71.96 318	82.71 145	46.36 357	83.52 234	83.31 214	58.55 276	57.58 331	76.23 375	36.72 296	86.20 308	47.25 367	63.40 313	83.32 327

test1		67.09 300	65.47 301	71.96 318	82.71 145	46.36 357	83.52 234	83.31 214	58.55 276	57.58 331	76.23 375	36.72 296	86.20 308	47.25 367	63.40 313	83.32 327

FMVSNet1		64.57 332	62.11 337	71.96 318	77.32 306	46.36 357	83.52 234	83.31 214	52.43 374	54.42 370	76.23 375	27.80 393	86.20 308	42.59 395	61.34 334	83.32 327

baseline1		72.51 169	72.12 159	73.69 264	85.05 80	44.46 386	83.51 238	86.13 115	71.61 22	64.64 212	87.97 180	55.00 37	89.48 162	59.07 256	56.05 389	87.13 238

CDS-MVSNet		70.48 219	69.43 211	73.64 265	77.56 299	48.83 282	83.51 238	77.45 354	63.27 176	62.33 253	85.54 229	43.85 182	83.29 368	57.38 284	74.00 192	88.79 188
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
thisisatest0530		70.47 220	68.56 226	76.20 170	79.78 242	51.52 204	83.49 240	88.58 56	57.62 295	58.60 312	82.79 277	51.03 63	91.48 79	52.84 324	62.36 330	85.59 278

fmvsm_s_conf0.5_n_10		76.80 63	76.81 57	76.78 153	78.91 268	47.85 324	83.44 241	74.66 389	68.93 64	81.31 23	94.12 7	47.44 106	90.82 107	83.43 29	79.06 112	91.66 66

Test_1112_low_res		67.18 297	66.23 282	70.02 357	78.75 271	41.02 429	83.43 242	73.69 401	57.29 302	58.45 318	82.39 290	45.30 159	80.88 385	50.50 343	66.26 288	88.16 209

ACMMP		70.81 211	69.29 216	75.39 204	81.52 188	51.92 189	83.43 242	83.03 223	56.67 319	58.80 306	88.91 140	31.92 364	88.58 203	65.89 190	73.39 203	85.67 274
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
tfpn200view9		67.57 284	66.13 284	71.89 325	84.05 104	45.07 380	83.40 244	87.71 78	60.79 230	57.79 326	82.76 278	43.53 191	87.80 244	28.80 454	66.36 284	82.78 342

thres400		67.40 292	66.13 284	71.19 336	84.05 104	45.07 380	83.40 244	87.71 78	60.79 230	57.79 326	82.76 278	43.53 191	87.80 244	28.80 454	66.36 284	80.71 375

v1240		66.99 303	64.68 314	73.93 254	71.38 405	52.66 168	83.39 246	79.98 286	61.97 205	58.44 319	77.11 359	35.25 320	87.81 241	56.46 293	58.15 365	81.33 365

Baseline_NR-MVSNet		65.49 327	64.27 320	69.13 364	74.37 366	41.65 422	83.39 246	78.85 319	59.56 249	59.62 286	76.88 366	40.75 231	87.44 264	49.99 345	55.05 397	78.28 402

hybrid		74.44 125	73.79 125	76.39 161	77.31 307	52.89 161	83.37 248	79.79 293	68.21 69	71.01 127	88.14 171	44.93 167	86.68 293	77.29 81	74.11 190	89.59 158

miper_enhance_ethall		69.77 234	68.90 224	72.38 305	78.93 267	49.91 249	83.29 249	78.85 319	64.90 139	59.37 291	79.46 331	52.77 50	85.16 341	63.78 212	58.72 357	82.08 347

fmvsm_s_conf0.5_n_7		73.10 155	73.89 124	70.72 343	74.17 369	46.03 368	83.28 250	74.19 393	67.10 92	73.94 75	91.73 72	43.42 195	77.61 426	83.92 27	73.26 204	88.53 201

diffmvs		75.11 113	74.65 109	76.46 160	78.52 279	53.35 143	83.28 250	79.94 289	70.51 39	71.64 111	88.72 143	46.02 136	86.08 317	77.52 78	75.75 168	89.96 149
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_cas_vis1_n_1920		67.10 299	66.60 275	68.59 375	65.17 455	43.23 405	83.23 252	69.84 437	55.34 345	70.67 138	87.71 191	24.70 420	76.66 435	78.57 68	64.20 304	85.89 271

test2506		72.91 159	72.43 148	74.32 242	80.12 233	44.18 393	83.19 253	84.77 173	64.02 153	65.97 187	87.43 198	47.67 101	88.72 197	59.08 255	79.66 103	90.08 145

ACMP	61.11 9	66.24 318	64.33 319	72.00 317	74.89 358	49.12 271	83.18 254	79.83 292	55.41 344	52.29 387	82.68 282	25.83 408	86.10 314	60.89 238	63.94 308	80.78 373
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
diffmvs_AUTHOR		74.80 121	74.30 114	76.29 164	77.34 305	53.19 149	83.17 255	79.50 303	69.93 50	71.55 113	88.57 151	45.85 146	86.03 320	77.17 82	75.64 169	89.67 155

fmvsm_s_conf0.5_n_3		74.97 116	75.42 87	73.62 267	76.99 315	46.67 349	83.13 256	71.14 427	66.20 112	82.13 14	93.76 17	47.49 104	84.00 356	81.95 41	76.02 157	90.19 138

GA-MVS		69.04 251	66.70 272	76.06 175	75.11 353	52.36 174	83.12 257	80.23 280	63.32 175	60.65 274	79.22 335	30.98 374	88.37 215	61.25 235	66.41 282	87.46 228

3Dnovator	64.70 6	74.46 124	72.48 146	80.41 31	82.84 142	55.40 63	83.08 258	88.61 53	67.61 85	59.85 281	88.66 145	34.57 332	93.97 28	58.42 265	88.70 12	91.85 59

PGM-MVS		72.60 166	71.20 175	76.80 151	82.95 135	52.82 164	83.07 259	82.14 235	56.51 325	63.18 242	89.81 124	35.68 315	89.76 148	67.30 177	80.19 94	87.83 218

LPG-MVS_test		66.44 314	64.58 315	72.02 315	74.42 364	48.60 289	83.07 259	80.64 271	54.69 354	53.75 378	83.83 259	25.73 410	86.98 279	60.33 249	64.71 299	80.48 377

TranMVSNet+NR-MVSNet		66.94 305	65.61 298	70.93 341	73.45 375	43.38 402	83.02 261	84.25 191	65.31 133	58.33 320	81.90 302	39.92 245	85.52 332	49.43 350	54.89 399	83.89 313

dtuplus		73.09 156	72.29 153	75.52 198	76.27 329	51.82 194	82.99 262	79.98 286	65.08 138	70.11 149	87.66 193	44.38 179	85.64 330	71.56 143	72.55 215	89.11 179

test0.0.03 1		62.54 355	62.44 332	62.86 425	72.28 394	29.51 482	82.93 263	78.78 322	59.18 262	53.07 383	82.41 289	36.91 291	77.39 427	37.45 409	58.96 355	81.66 355

viewmamba		73.92 138	73.03 139	76.58 158	77.56 299	52.73 165	82.91 264	78.77 323	69.23 60	68.85 159	88.01 179	44.71 175	87.57 259	73.86 118	73.40 202	89.44 168

pm-mvs1		64.12 337	62.56 331	68.78 370	71.68 398	38.87 439	82.89 265	81.57 252	55.54 341	53.89 377	77.82 348	37.73 268	86.74 291	48.46 360	53.49 411	80.72 374

viewmambaseed2359dif		73.51 149	72.78 141	75.71 187	76.93 317	51.89 190	82.81 266	79.66 298	65.46 125	70.29 147	88.05 176	45.55 152	85.85 328	73.49 124	72.76 212	89.39 169

EPNet_dtu		66.25 317	66.71 271	64.87 409	78.66 276	34.12 457	82.80 267	75.51 380	61.75 208	64.47 220	86.90 206	37.06 288	72.46 458	43.65 388	69.63 253	88.02 215
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.1_n_a		72.82 161	72.05 161	75.12 216	70.95 409	47.97 317	82.72 268	68.43 445	62.52 195	78.17 47	93.08 37	44.21 180	88.86 192	84.82 17	63.54 312	88.54 200

test_fmvsmconf_n		74.41 126	74.05 118	75.49 199	74.16 370	48.38 298	82.66 269	72.57 413	67.05 96	75.11 63	92.88 44	46.35 127	87.81 241	83.93 26	71.71 225	90.28 132

pmmvs5		62.80 353	61.18 350	67.66 381	69.53 429	42.37 417	82.65 270	75.19 384	54.30 359	52.03 391	78.51 341	31.64 369	80.67 389	48.60 357	58.15 365	79.95 384

fmvsm_s_conf0.5_n_9		76.66 68	76.94 54	75.85 182	79.54 247	48.30 304	82.63 271	71.84 418	70.25 42	80.63 30	94.53 3	50.78 69	87.42 265	88.32 5	73.92 195	91.82 61

cl____		67.43 288	65.93 290	71.95 321	76.33 325	48.02 315	82.58 272	79.12 314	61.30 218	56.72 346	76.92 364	46.12 130	86.44 303	57.98 272	56.31 384	81.38 364

DIV-MVS_self_test		67.43 288	65.93 290	71.94 322	76.33 325	48.01 316	82.57 273	79.11 315	61.31 217	56.73 345	76.92 364	46.09 133	86.43 304	57.98 272	56.31 384	81.39 363

TAMVS		69.51 243	68.16 236	73.56 269	76.30 327	48.71 288	82.57 273	77.17 359	62.10 201	61.32 267	84.23 252	41.90 217	83.46 365	54.80 309	73.09 208	88.50 203

EI-MVSNet-Vis-set		73.19 154	72.60 144	74.99 222	82.56 150	49.80 253	82.55 275	89.00 36	66.17 113	65.89 189	88.98 138	43.83 183	92.29 60	65.38 199	69.01 256	82.87 340

reproduce-ours		71.77 191	70.43 191	75.78 184	81.96 164	49.54 261	82.54 276	81.01 264	48.77 402	69.21 154	90.96 90	37.13 286	89.40 165	66.28 185	76.01 158	88.39 206

our_new_method		71.77 191	70.43 191	75.78 184	81.96 164	49.54 261	82.54 276	81.01 264	48.77 402	69.21 154	90.96 90	37.13 286	89.40 165	66.28 185	76.01 158	88.39 206

DP-MVS		59.24 376	56.12 389	68.63 373	88.24 36	50.35 239	82.51 278	64.43 460	41.10 450	46.70 431	78.77 339	24.75 419	88.57 206	22.26 480	56.29 386	66.96 472

miper_ehance_all_eth		68.70 262	67.58 251	72.08 313	76.91 318	49.48 264	82.47 279	78.45 334	62.68 192	58.28 321	77.88 347	50.90 64	85.01 344	61.91 230	58.72 357	81.75 352

cl22		68.85 254	67.69 249	72.35 306	78.07 287	49.98 248	82.45 280	78.48 333	62.50 196	58.46 317	77.95 345	49.99 76	85.17 340	62.55 223	58.72 357	81.90 350

UniMVSNet (Re)		67.71 280	66.80 269	70.45 347	74.44 363	42.93 408	82.42 281	84.90 167	63.69 166	59.63 285	80.99 312	47.18 108	85.23 339	51.17 341	56.75 381	83.19 332

v8		67.25 295	64.99 312	74.04 250	72.89 385	53.31 146	82.37 282	80.11 284	61.54 213	54.29 373	76.02 380	42.89 204	88.41 214	58.43 263	56.36 382	80.39 379

ACMM	58.35 12	64.35 334	62.01 340	71.38 332	74.21 368	48.51 293	82.25 283	79.66 298	47.61 410	54.54 369	80.11 322	25.26 413	86.00 321	51.26 339	63.16 320	79.64 386
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
onestephybrid01		74.31 129	73.65 127	76.27 165	77.58 297	51.99 185	82.22 284	78.44 335	69.26 59	70.95 129	88.11 172	44.46 177	87.30 270	78.01 76	73.86 197	89.51 164

test_fmvsmconf0.1_n		73.69 145	73.15 133	75.34 205	70.71 411	48.26 305	82.15 285	71.83 419	66.75 101	74.47 71	92.59 52	44.89 168	87.78 248	83.59 28	71.35 232	89.97 148

thres600view7		66.46 313	65.12 310	70.47 346	83.41 116	43.80 397	82.15 285	87.78 73	59.37 254	56.02 354	82.21 296	43.73 186	86.90 284	26.51 466	64.94 296	80.71 375

c3_l		67.97 274	66.66 273	71.91 324	76.20 331	49.31 269	82.13 287	78.00 342	61.99 204	57.64 330	76.94 363	49.41 83	84.93 345	60.62 242	57.01 380	81.49 357

SSC-MVS3.2		68.13 273	66.89 265	71.85 326	82.26 155	43.97 394	82.09 288	89.29 30	71.74 18	61.12 269	79.83 327	34.60 331	87.45 263	41.23 398	59.85 347	84.14 300

Effi-MVS+-dtu		66.24 318	64.96 313	70.08 354	75.17 352	49.64 254	82.01 289	74.48 391	62.15 200	57.83 324	76.08 379	30.59 376	83.79 359	65.40 198	60.93 338	76.81 418

our_test_3		59.11 379	55.08 396	71.18 337	71.42 403	53.29 147	81.96 290	74.52 390	48.32 404	42.08 449	69.28 440	28.14 388	82.15 375	34.35 432	45.68 450	78.11 405

CPTT-MVS		67.15 298	65.84 292	71.07 338	80.96 203	50.32 240	81.94 291	74.10 394	46.18 426	57.91 323	87.64 194	29.57 382	81.31 381	64.10 207	70.18 248	81.56 356

APD-MVS_3200maxsize		69.62 241	68.23 235	73.80 260	81.58 184	48.22 306	81.91 292	79.50 303	48.21 406	64.24 222	89.75 125	31.91 365	87.55 260	63.08 217	73.85 198	85.64 276

v10		66.61 310	64.20 321	73.83 259	72.59 388	53.37 142	81.88 293	79.91 291	61.11 221	54.09 375	75.60 382	40.06 242	88.26 225	56.47 292	56.10 388	79.86 385

EI-MVSNet-UG-set		72.37 173	71.73 164	74.29 243	81.60 182	49.29 270	81.85 294	88.64 49	65.29 134	65.05 202	88.29 163	43.18 198	91.83 71	63.74 214	67.97 268	81.75 352

ppachtmachnet_test		58.56 388	54.34 398	71.24 334	71.42 403	54.74 102	81.84 295	72.27 415	49.02 399	45.86 436	68.99 441	26.27 403	83.30 367	30.12 449	43.23 456	75.69 428

test_fmvsm_n_1920		75.56 103	75.54 83	75.61 190	74.60 362	49.51 263	81.82 296	74.08 395	66.52 105	80.40 31	93.46 25	46.95 112	89.72 149	86.69 9	75.30 173	87.61 225

IMVS_0403		72.39 171	70.59 188	77.79 113	82.26 155	50.87 214	81.76 297	85.16 150	62.91 184	64.87 209	86.07 218	37.71 270	92.40 57	64.03 208	70.55 241	90.09 141

test_0402		56.45 401	53.03 405	66.69 393	76.78 320	50.31 241	81.76 297	69.61 439	42.79 446	43.88 440	72.13 423	22.82 432	86.46 302	16.57 494	50.94 420	63.31 481

testing3		59.97 371	60.19 361	59.32 442	77.60 295	30.01 478	81.75 299	81.79 247	53.54 364	50.34 408	79.94 323	48.99 87	76.91 431	17.19 493	50.59 421	71.03 465

reproduce_model		71.07 204	69.67 209	75.28 212	81.51 189	48.82 283	81.73 300	80.57 274	47.81 408	68.26 164	90.78 98	36.49 300	88.60 202	65.12 201	74.76 186	88.42 205

旧先验2							81.73 300		45.53 429	74.66 66			70.48 465	58.31 267

SSM_0404		70.13 222	67.87 246	76.88 147	80.22 230	52.00 184	81.71 302	80.18 281	54.07 360	65.36 198	85.05 238	33.09 348	91.03 95	59.40 252	71.80 224	87.63 224

thres100view900		66.87 306	65.42 304	71.24 334	83.29 122	43.15 406	81.67 303	87.78 73	59.04 266	55.92 355	82.18 297	43.73 186	87.80 244	28.80 454	66.36 284	82.78 342

MVSFormer		73.53 148	72.19 156	77.57 119	83.02 132	55.24 68	81.63 304	81.44 255	50.28 390	76.67 55	90.91 94	44.82 171	86.11 312	60.83 239	80.09 95	91.36 82

test_djsdf		63.84 340	61.56 344	70.70 344	68.78 434	44.69 385	81.63 304	81.44 255	50.28 390	52.27 388	76.26 374	26.72 401	86.11 312	60.83 239	55.84 393	81.29 368

新几何2							81.61 306

TSAR-MVS + MP.		78.31 35	78.26 29	78.48 91	81.33 193	56.31 45	81.59 307	86.41 107	69.61 55	81.72 20	88.16 169	55.09 35	88.04 231	74.12 114	86.31 35	91.09 97
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
viewdifsd2359ckpt11		70.68 213	69.10 221	75.40 201	75.33 350	50.85 218	81.57 308	78.00 342	66.99 97	64.96 206	85.52 230	39.52 247	86.81 288	68.86 166	61.15 336	88.56 198

viewmsd2359difaftdt		70.68 213	69.10 221	75.40 201	75.33 350	50.85 218	81.57 308	78.00 342	66.99 97	64.96 206	85.52 230	39.52 247	86.81 288	68.86 166	61.16 335	88.56 198

SR-MVS-dyc-post		68.27 270	66.87 266	72.48 301	80.96 203	48.14 310	81.54 310	76.98 362	46.42 420	62.75 249	89.42 130	31.17 373	86.09 316	60.52 245	72.06 222	83.19 332

RE-MVS-def			66.66 273		80.96 203	48.14 310	81.54 310	76.98 362	46.42 420	62.75 249	89.42 130	29.28 385		60.52 245	72.06 222	83.19 332

V42		67.66 281	65.60 299	73.86 257	70.69 414	53.63 133	81.50 312	78.61 329	63.85 160	59.49 290	77.49 352	37.98 262	87.65 254	62.33 225	58.43 360	80.29 380

DU-MVS		66.84 307	65.74 295	70.16 352	73.27 379	42.59 412	81.50 312	82.92 226	63.53 170	58.51 313	82.11 298	40.75 231	84.64 350	53.11 320	55.96 390	83.24 330

HyFIR lowres test		69.94 232	67.58 251	77.04 138	77.11 314	57.29 24	81.49 314	79.11 315	58.27 279	58.86 304	80.41 317	42.33 208	86.96 281	61.91 230	68.68 263	86.87 243

IterMVS-LS		66.63 309	65.36 305	70.42 348	75.10 354	48.90 280	81.45 315	76.69 370	61.05 223	55.71 356	77.10 360	45.86 145	83.65 362	57.44 282	57.88 373	78.70 393
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSM_0407		69.71 235	67.38 258	76.69 156	80.45 223	51.81 195	81.36 316	80.18 281	54.07 360	63.82 231	85.05 238	33.09 348	91.01 98	59.40 252	68.97 258	87.25 234

jajsoiax		63.21 348	60.84 353	70.32 350	68.33 439	44.45 387	81.23 317	81.05 261	53.37 367	50.96 402	77.81 349	17.49 463	85.49 334	59.31 254	58.05 368	81.02 371

HPM-MVS_fast		67.86 276	66.28 281	72.61 296	80.67 214	48.34 300	81.18 318	75.95 377	50.81 386	59.55 288	88.05 176	27.86 392	85.98 323	58.83 258	73.58 200	83.51 325

tfpnnormal		61.47 365	59.09 369	68.62 374	76.29 328	41.69 421	81.14 319	85.16 150	54.48 356	51.32 395	73.63 400	32.32 357	86.89 285	21.78 482	55.71 394	77.29 414

IS-MVSNet		68.80 258	67.55 253	72.54 298	78.50 280	43.43 401	81.03 320	79.35 310	59.12 265	57.27 339	86.71 209	46.05 134	87.70 252	44.32 385	75.60 170	86.49 258

eth_miper_zixun_eth		66.98 304	65.28 306	72.06 314	75.61 344	50.40 233	81.00 321	76.97 365	62.00 203	56.99 343	76.97 362	44.84 170	85.58 331	58.75 260	54.42 403	80.21 381

Syy-MVS		61.51 364	61.35 348	62.00 429	81.73 171	30.09 476	80.97 322	81.02 262	60.93 227	55.06 361	82.64 283	35.09 323	80.81 387	16.40 495	58.32 361	75.10 436

myMVS_eth3d		63.52 344	63.56 325	63.40 420	81.73 171	34.28 454	80.97 322	81.02 262	60.93 227	55.06 361	82.64 283	48.00 98	80.81 387	23.42 478	58.32 361	75.10 436

mvs_tets		62.96 351	60.55 355	70.19 351	68.22 442	44.24 392	80.90 324	80.74 269	52.99 370	50.82 406	77.56 350	16.74 467	85.44 335	59.04 257	57.94 370	80.89 372

tttt0517		68.33 268	66.29 280	74.46 234	78.08 286	49.06 272	80.88 325	89.08 35	54.40 358	54.75 367	80.77 315	51.31 60	90.33 127	49.35 351	58.01 369	83.99 306

FC-MVSNet-test		67.49 286	67.91 239	66.21 397	76.06 333	33.06 462	80.82 326	87.18 87	64.44 143	54.81 365	82.87 275	50.40 73	82.60 371	48.05 362	66.55 280	82.98 338

sss		70.49 218	70.13 201	71.58 330	81.59 183	39.02 437	80.78 327	84.71 180	59.34 255	66.61 179	88.09 173	37.17 285	85.52 332	61.82 232	71.02 235	90.20 136

LuminaMVS		66.60 311	64.37 318	73.27 278	70.06 425	49.57 255	80.77 328	81.76 250	50.81 386	60.56 275	78.41 343	24.50 421	87.26 272	64.24 206	68.25 264	82.99 336

HPM-MVS		72.60 166	71.50 168	75.89 181	82.02 162	51.42 206	80.70 329	83.05 222	56.12 334	64.03 225	89.53 128	37.55 274	88.37 215	70.48 151	80.04 97	87.88 217
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
IMVS_0407		71.97 184	70.10 202	77.57 119	82.26 155	50.87 214	80.69 330	85.16 150	62.91 184	63.68 235	86.07 218	35.56 316	91.75 73	64.03 208	70.55 241	90.09 141

pmmvs6		59.64 373	57.15 380	67.09 387	66.01 448	36.86 448	80.50 331	78.64 327	45.05 432	49.05 414	73.94 394	27.28 396	86.10 314	43.96 387	49.94 423	78.31 401

BridgeMVS		80.28 16	79.73 16	81.90 12	86.47 56	59.34 7	80.45 332	89.51 28	69.76 53	71.05 126	86.66 211	58.68 17	93.24 37	84.64 20	90.40 6	93.14 19

IterMVS		63.77 342	61.67 342	70.08 354	72.68 387	51.24 211	80.44 333	75.51 380	60.51 235	51.41 394	73.70 399	32.08 361	78.91 408	54.30 311	54.35 404	80.08 383
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		59.12 378	58.81 372	60.08 440	70.68 415	45.07 380	80.42 334	74.25 392	43.54 443	50.02 409	73.73 396	31.97 362	56.74 489	51.06 342	53.60 410	78.42 399

test_fmvsmconf0.01_n		71.97 184	70.95 182	75.04 218	66.21 447	47.87 323	80.35 335	70.08 435	65.85 122	72.69 92	91.68 75	39.99 243	87.67 253	82.03 40	69.66 251	89.58 159

ACMH+	54.58 15	58.55 389	55.24 393	68.50 377	74.68 360	45.80 374	80.27 336	70.21 434	47.15 414	42.77 448	75.48 383	16.73 468	85.98 323	35.10 430	54.78 400	73.72 446

Anonymous20231206		59.08 380	57.59 377	63.55 417	68.77 435	32.14 468	80.26 337	79.78 294	50.00 394	49.39 412	72.39 414	26.64 402	78.36 413	33.12 439	57.94 370	80.14 382

1314		71.11 203	69.41 212	76.22 168	79.32 253	50.49 229	80.23 338	85.14 156	59.44 252	58.93 301	88.89 141	33.83 342	89.60 157	61.49 234	77.42 132	88.57 197

MVS		76.91 58	75.48 84	81.23 21	84.56 90	55.21 71	80.23 338	91.64 4	58.65 274	65.37 197	91.48 81	45.72 148	95.05 17	72.11 142	89.52 10	93.44 10

ACMH	53.70 16	59.78 372	55.94 391	71.28 333	76.59 321	48.35 299	80.15 340	76.11 375	49.74 395	41.91 452	73.45 403	16.50 469	90.31 128	31.42 444	57.63 376	75.17 434
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Elysia		65.59 323	62.65 329	74.42 236	69.85 426	49.46 265	80.04 341	82.11 237	46.32 423	58.74 310	79.64 328	20.30 446	88.57 206	55.48 303	71.37 230	85.22 282

StellarMVS		65.59 323	62.65 329	74.42 236	69.85 426	49.46 265	80.04 341	82.11 237	46.32 423	58.74 310	79.64 328	20.30 446	88.57 206	55.48 303	71.37 230	85.22 282

MGCFI-Net		74.07 134	74.64 110	72.34 307	82.90 138	43.33 404	80.04 341	79.96 288	65.61 123	74.93 64	91.85 69	48.01 96	80.86 386	71.41 144	77.10 134	92.84 25

UWE-MVS-28		67.43 288	67.98 238	65.75 400	75.66 343	34.74 452	80.00 344	88.17 66	64.21 149	57.27 339	84.14 254	45.68 150	78.82 410	44.33 383	72.40 217	83.70 320

pmmvs4		63.34 347	61.07 352	70.16 352	70.14 422	50.53 228	79.97 345	71.41 426	55.08 348	54.12 374	78.58 340	32.79 353	82.09 377	50.33 344	57.22 378	77.86 407

MVS_111021_LR		69.07 248	67.91 239	72.54 298	77.27 308	49.56 258	79.77 346	73.96 398	59.33 257	60.73 273	87.82 184	30.19 379	81.53 379	69.94 155	72.19 221	86.53 256

CNLPA		60.59 369	58.44 373	67.05 389	79.21 257	47.26 340	79.75 347	64.34 461	42.46 448	51.90 392	83.94 256	27.79 394	75.41 443	37.12 411	59.49 351	78.47 397

icg_test_0407_2		71.26 199	69.99 204	75.09 217	82.26 155	50.87 214	79.65 348	85.16 150	62.91 184	63.68 235	86.07 218	35.56 316	84.32 353	64.03 208	70.55 241	90.09 141

FE-MVSNET2		58.78 385	56.44 385	65.82 399	63.57 466	38.92 438	79.59 349	81.75 251	56.14 333	43.06 447	68.15 443	25.22 414	80.64 390	42.29 397	48.16 433	77.91 406

EI-MVSNet		69.70 239	68.70 225	72.68 294	75.00 356	48.90 280	79.54 350	87.16 88	61.05 223	63.88 229	83.74 261	45.87 144	90.44 123	57.42 283	64.68 302	78.70 393

CVMVSNet		60.85 368	60.44 357	62.07 427	75.00 356	32.73 464	79.54 350	73.49 405	36.98 464	56.28 353	83.74 261	29.28 385	69.53 467	46.48 372	63.23 318	83.94 311

AUN-MVS		68.20 272	66.35 278	73.76 261	76.37 323	47.45 336	79.52 352	79.52 302	60.98 225	62.34 252	86.02 222	36.59 299	86.94 282	62.32 226	53.47 412	86.89 242

hse-mvs2		71.44 197	70.68 185	73.73 263	76.34 324	47.44 337	79.45 353	79.47 305	68.08 73	71.97 104	86.01 224	42.50 206	86.93 283	78.82 64	53.46 413	86.83 249

PVSNet_0	57.04 13	61.19 366	57.24 379	73.02 280	77.45 303	50.31 241	79.43 354	77.36 357	63.96 158	47.51 426	72.45 413	25.03 416	83.78 360	52.76 328	19.22 502	84.96 288

PCF-MVS	61.03 10	70.10 225	68.40 231	75.22 215	77.15 313	51.99 185	79.30 355	82.12 236	56.47 326	61.88 262	86.48 215	43.98 181	87.24 273	55.37 305	72.79 211	86.43 260
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_fmvsmvis_n_1920		71.29 198	70.38 194	74.00 252	71.04 408	48.79 284	79.19 356	64.62 457	62.75 189	66.73 175	91.99 65	40.94 227	88.35 217	83.00 31	73.18 205	84.85 291

usedtu_blend_shiyan5		63.62 343	60.36 359	73.40 273	70.49 416	47.96 319	79.13 357	80.68 270	47.51 412	51.25 396	72.31 417	36.16 304	88.50 210	56.81 287	48.90 426	83.73 315

PLC	52.38 18	60.89 367	58.97 371	66.68 394	81.77 170	45.70 375	78.96 358	74.04 397	43.66 442	47.63 423	83.19 274	23.52 428	77.78 425	37.47 408	60.46 340	76.55 424
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
D2MVS		63.49 345	61.39 346	69.77 358	69.29 431	48.93 279	78.89 359	77.71 350	60.64 234	49.70 410	72.10 425	27.08 398	83.48 364	54.48 310	62.65 326	76.90 416

dtuonlycased		54.12 413	52.39 413	59.30 443	64.31 461	41.80 420	78.63 360	65.85 452	50.56 388	42.00 450	60.21 472	26.14 407	73.31 453	43.06 390	40.73 461	62.79 483

OMC-MVS		65.97 321	65.06 311	68.71 372	72.97 383	42.58 414	78.61 361	75.35 383	54.72 353	59.31 293	86.25 217	33.30 345	77.88 422	57.99 271	67.05 274	85.66 275

PAPM_NR		71.80 189	69.98 205	77.26 133	81.54 186	53.34 144	78.60 362	85.25 145	53.46 365	60.53 276	88.66 145	45.69 149	89.24 171	56.49 291	79.62 105	89.19 176

mvs_anonymous		72.29 177	70.74 183	76.94 145	82.85 141	54.72 105	78.43 363	81.54 253	63.77 162	61.69 263	79.32 333	51.11 61	85.31 336	62.15 229	75.79 162	90.79 114

RRT-MVS		73.29 152	71.37 172	79.07 60	84.63 88	54.16 125	78.16 364	86.64 103	61.67 210	60.17 278	82.35 294	40.63 235	92.26 62	70.19 152	77.87 125	90.81 112

tt0805		63.39 346	61.31 349	69.64 359	69.36 430	38.87 439	78.00 365	85.48 130	48.82 401	55.66 359	81.66 306	24.38 422	86.37 305	49.04 354	59.36 353	83.68 321

test222					79.36 251	50.97 213	77.99 366	67.84 446	42.54 447	62.84 248	86.53 213	30.26 378			76.91 139	85.23 281

v7n		62.50 357	59.27 368	72.20 310	67.25 445	49.83 252	77.87 367	80.12 283	52.50 373	48.80 416	73.07 404	32.10 360	87.90 236	46.83 370	54.92 398	78.86 391

test20.03		55.22 408	54.07 401	58.68 446	63.14 468	25.00 491	77.69 368	74.78 387	52.64 371	43.43 443	72.39 414	26.21 404	74.76 445	29.31 452	47.05 444	76.28 426

testdata1							77.55 369		64.14 152

PEN-MVS		58.35 391	57.15 380	61.94 430	67.55 444	34.39 453	77.01 370	78.35 337	51.87 378	47.72 422	76.73 368	33.91 339	73.75 450	34.03 433	47.17 442	77.68 410

WR-MVS_H		58.91 383	58.04 375	61.54 433	69.07 433	33.83 459	76.91 371	81.99 241	51.40 382	48.17 417	74.67 387	40.23 238	74.15 446	31.78 443	48.10 434	76.64 422

CP-MVSNet		58.54 390	57.57 378	61.46 434	68.50 437	33.96 458	76.90 372	78.60 330	51.67 381	47.83 421	76.60 370	34.99 326	72.79 456	35.45 423	47.58 438	77.64 412

IMVS_0404		69.11 247	67.25 262	74.68 230	82.26 155	50.87 214	76.74 373	85.16 150	62.91 184	50.76 407	86.07 218	26.76 400	83.06 370	64.03 208	70.55 241	90.09 141

PS-CasMVS		58.12 392	57.03 382	61.37 435	68.24 441	33.80 460	76.73 374	78.01 341	51.20 384	47.54 425	76.20 378	32.85 351	72.76 457	35.17 428	47.37 440	77.55 413

tpm		68.36 266	67.48 256	70.97 340	79.93 236	51.34 208	76.58 375	78.75 325	67.73 81	63.54 241	74.86 386	48.33 90	72.36 459	53.93 314	63.71 309	89.21 175

MonoMVSNet		66.80 308	64.41 317	73.96 253	76.21 330	48.07 313	76.56 376	78.26 338	64.34 145	54.32 372	74.02 393	37.21 284	86.36 306	64.85 203	53.96 406	87.45 229

DTE-MVSNet		57.03 397	55.73 392	60.95 439	65.94 449	32.57 465	75.71 377	77.09 361	51.16 385	46.65 432	76.34 373	32.84 352	73.22 455	30.94 447	44.87 451	77.06 415

dtuonly		62.58 354	61.91 341	64.58 411	66.49 446	44.72 384	75.64 378	65.78 453	57.26 304	55.48 360	83.93 257	30.08 380	67.36 471	56.40 296	66.10 289	81.67 354

tpmrst		71.04 206	69.77 207	74.86 225	83.19 125	55.86 54	75.64 378	78.73 326	67.88 78	64.99 205	73.73 396	49.96 78	79.56 407	65.92 188	67.85 270	89.14 178

usedtu_dtu_shiyan2		50.47 434	46.43 441	62.61 426	51.66 489	31.70 471	75.62 380	75.65 379	36.36 468	34.89 477	56.91 481	12.01 476	78.40 412	30.87 448	43.86 453	77.72 409

CostFormer		73.89 140	72.30 152	78.66 74	82.36 154	56.58 36	75.56 381	85.30 141	66.06 118	70.50 143	76.88 366	57.02 24	89.06 178	68.27 172	68.74 262	90.33 130

HY-MVS	67.03 5	73.90 139	73.14 135	76.18 172	84.70 86	47.36 338	75.56 381	86.36 109	66.27 110	70.66 139	83.91 258	51.05 62	89.31 168	67.10 179	72.61 214	91.88 57

K. test v3		54.04 414	49.42 427	67.92 380	68.55 436	42.57 415	75.51 383	63.07 464	52.07 375	39.21 463	64.59 457	19.34 451	82.21 374	37.11 412	25.31 493	78.97 390

Vis-MVSNet (Re-imp)		65.52 325	65.63 297	65.17 407	77.49 302	30.54 472	75.49 384	77.73 349	59.34 255	52.26 389	86.69 210	49.38 84	80.53 394	37.07 413	75.28 174	84.42 295

pmmvs-eth3d		55.97 405	52.78 409	65.54 403	61.02 473	46.44 356	75.36 385	67.72 447	49.61 396	43.65 442	67.58 445	21.63 440	77.04 429	44.11 386	44.33 452	73.15 453

TAPA-MVS	56.12 14	61.82 363	60.18 362	66.71 392	78.48 281	37.97 444	75.19 386	76.41 374	46.82 416	57.04 342	86.52 214	27.67 395	77.03 430	26.50 467	67.02 275	85.14 284
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PatchmatchNet2					0.00 564	32.03 469	74.85 387	61.13 467	37.29 461
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
FMVSNet5		58.61 387	56.45 384	65.10 408	77.20 312	39.74 433	74.77 388	77.12 360	50.27 392	43.28 445	67.71 444	26.15 406	76.90 433	36.78 417	54.78 400	78.65 395

FA-MVS(test-final)		69.00 253	66.60 275	76.19 171	83.48 115	47.96 319	74.73 389	82.07 240	57.27 303	62.18 255	78.47 342	36.09 308	92.89 41	53.76 316	71.32 233	87.73 221

SixPastTwentyTwo		54.37 410	50.10 420	67.21 386	70.70 413	41.46 426	74.73 389	64.69 456	47.56 411	39.12 464	69.49 436	18.49 458	84.69 349	31.87 442	34.20 481	75.48 430

F-COLMAP		55.96 406	53.65 404	62.87 424	72.76 386	42.77 411	74.70 391	70.37 433	40.03 451	41.11 458	79.36 332	17.77 461	73.70 451	32.80 440	53.96 406	72.15 457

SD_0403		65.51 326	65.18 309	66.48 396	78.37 283	29.94 479	74.64 392	78.55 331	66.47 106	54.87 364	84.35 251	38.20 261	82.47 372	38.90 405	72.30 220	87.05 239

MVSMamba_PlusPlus		75.28 106	73.39 129	80.96 23	80.85 208	58.25 12	74.47 393	87.61 80	50.53 389	65.24 199	83.41 269	57.38 22	92.83 43	73.92 117	87.13 22	91.80 62

MSDG		59.44 374	55.14 395	72.32 308	74.69 359	50.71 222	74.39 394	73.58 402	44.44 437	43.40 444	77.52 351	19.45 450	90.87 106	31.31 445	57.49 377	75.38 431

balanced_ft_v1		75.25 108	73.90 122	79.29 51	85.59 69	56.72 35	74.35 395	87.27 84	60.24 238	59.07 298	85.17 234	47.76 99	90.51 120	82.62 36	83.06 65	90.64 118

tpm2		70.82 210	68.44 230	77.98 106	80.78 210	56.11 48	74.21 396	81.28 259	60.24 238	68.04 168	75.27 384	52.26 54	88.50 210	55.82 300	68.03 267	89.33 171

SDMVSNet		71.89 186	70.62 187	75.70 188	81.70 173	51.61 200	73.89 397	88.72 47	66.58 102	61.64 264	82.38 291	37.63 271	89.48 162	77.44 79	65.60 292	86.01 265

UniMVSNet_ETH3D		62.51 356	60.49 356	68.57 376	68.30 440	40.88 431	73.89 397	79.93 290	51.81 380	54.77 366	79.61 330	24.80 418	81.10 382	49.93 346	61.35 333	83.73 315

FE-MVSNET		51.43 430	48.22 432	61.06 437	60.78 475	32.48 466	73.85 399	64.62 457	46.30 425	37.47 470	66.27 449	20.80 444	77.38 428	23.43 476	40.48 464	73.31 450

UA-Net		67.32 294	66.23 282	70.59 345	78.85 269	41.23 428	73.60 400	75.45 382	61.54 213	66.61 179	84.53 248	38.73 256	86.57 300	42.48 396	74.24 189	83.98 308

Anonymous20240521		51.65 428	48.42 430	61.34 436	56.43 482	39.65 435	73.57 401	73.47 408	36.64 466	36.59 471	63.98 458	10.75 481	72.25 460	35.35 424	49.01 424	72.11 458

ab-mvs		70.65 215	69.11 220	75.29 210	80.87 207	46.23 366	73.48 402	85.24 146	59.99 241	66.65 177	80.94 313	43.13 201	88.69 198	63.58 215	68.07 266	90.95 108

LS3D		56.40 402	53.82 402	64.12 413	81.12 198	45.69 376	73.42 403	66.14 450	35.30 474	43.24 446	79.88 324	22.18 437	79.62 406	19.10 489	64.00 307	67.05 471

testmvs		6.14 485	8.18 486	0.01 539	0.01 563	0.00 567	73.40 404	0.00 565	0.00 557	0.02 559	0.15 557	0.00 561	0.00 559	0.02 544	0.00 558	0.02 555

UnsupCasMVSNet_eth		57.56 395	55.15 394	64.79 410	64.57 460	33.12 461	73.17 405	83.87 203	58.98 268	41.75 453	70.03 435	22.54 433	79.92 401	46.12 376	35.31 475	81.32 367

sc_t1		53.51 419	49.92 424	64.29 412	70.33 420	39.55 436	72.93 406	59.60 471	38.74 456	47.16 428	66.47 448	17.59 462	76.50 436	36.83 416	39.62 467	76.82 417

anonymousdsp		60.46 370	57.65 376	68.88 366	63.63 465	45.09 379	72.93 406	78.63 328	46.52 418	51.12 399	72.80 409	21.46 441	83.07 369	57.79 278	53.97 405	78.47 397

mmtdpeth		57.93 393	54.78 397	67.39 385	72.32 392	43.38 402	72.72 408	68.93 442	54.45 357	56.85 344	62.43 462	17.02 465	83.46 365	57.95 274	30.31 487	75.31 432

EU-MVSNet		52.63 422	50.72 418	58.37 447	62.69 470	28.13 488	72.60 409	75.97 376	30.94 481	40.76 460	72.11 424	20.16 448	70.80 463	35.11 429	46.11 448	76.19 427

dp		64.41 333	61.58 343	72.90 284	82.40 152	54.09 126	72.53 410	76.59 372	60.39 236	55.68 357	70.39 434	35.18 322	76.90 433	39.34 404	61.71 332	87.73 221

N_pmnet		41.25 448	39.77 451	45.66 469	68.50 437	0.82 539	72.51 411	0.38 537	35.61 471	35.26 476	61.51 467	20.07 449	67.74 468	23.51 474	40.63 462	68.42 470

tt0320		52.45 424	48.75 428	63.55 417	71.47 402	41.85 419	72.42 412	59.73 470	36.33 469	44.52 437	61.55 466	19.34 451	76.45 437	33.53 434	39.85 466	72.36 456

MDTV_nov1_ep13			61.56 344		81.68 175	55.12 76	72.41 413	78.18 339	59.19 260	58.85 305	69.29 439	34.69 330	86.16 311	36.76 418	62.96 323

YYNet1		53.82 416	49.96 422	65.41 405	70.09 424	48.95 277	72.30 414	71.66 423	44.25 439	31.89 486	63.07 461	23.73 426	73.95 448	33.26 437	39.40 468	73.34 449

MDA-MVSNet_test_wron		53.82 416	49.95 423	65.43 404	70.13 423	49.05 273	72.30 414	71.65 424	44.23 440	31.85 487	63.13 460	23.68 427	74.01 447	33.25 438	39.35 469	73.23 452

testgi		54.25 412	52.57 411	59.29 444	62.76 469	21.65 500	72.21 416	70.47 432	53.25 368	41.94 451	77.33 356	14.28 473	77.95 421	29.18 453	51.72 419	78.28 402

tt0320-xc		52.22 427	48.38 431	63.75 416	72.19 395	42.25 418	72.19 417	57.59 474	37.24 462	44.41 438	61.56 465	17.90 460	75.89 440	35.60 422	36.73 472	73.12 454

KD-MVS_2432*1600		59.04 381	56.44 385	66.86 390	79.07 261	45.87 371	72.13 418	80.42 277	55.03 349	48.15 418	71.01 428	36.73 294	78.05 418	35.21 426	30.18 488	76.67 419

miper_refine_blended		59.04 381	56.44 385	66.86 390	79.07 261	45.87 371	72.13 418	80.42 277	55.03 349	48.15 418	71.01 428	36.73 294	78.05 418	35.21 426	30.18 488	76.67 419

PatchmatchNet		67.07 302	63.63 324	77.40 126	83.10 126	58.03 13	72.11 420	77.77 348	58.85 270	59.37 291	70.83 430	37.84 264	84.93 345	42.96 392	69.83 250	89.26 172
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test123		6.01 486	8.01 487	0.01 539	0.00 564	0.01 565	71.93 421	0.00 565	0.00 557	0.02 559	0.11 558	0.00 561	0.00 559	0.02 544	0.00 558	0.02 555

EPMVS		68.45 265	65.44 303	77.47 123	84.91 83	56.17 47	71.89 422	81.91 245	61.72 209	60.85 271	72.49 411	36.21 303	87.06 278	47.32 366	71.62 226	89.17 177

UnsupCasMVSNet_bld		53.86 415	50.53 419	63.84 414	63.52 467	34.75 451	71.38 423	81.92 244	46.53 417	38.95 465	57.93 478	20.55 445	80.20 399	39.91 403	34.09 482	76.57 423

COLMAP_ROB	43.60 20	50.90 433	48.05 434	59.47 441	67.81 443	40.57 432	71.25 424	62.72 466	36.49 467	36.19 473	73.51 401	13.48 474	73.92 449	20.71 484	50.26 422	63.92 480
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MDTV_nov1_ep13_2view						43.62 398	71.13 425		54.95 351	59.29 295		36.76 293		46.33 374		87.32 232

test_post1							70.84 426				14.72 522	34.33 336	83.86 357	48.80 355

new-patchmatchnet		48.21 439	46.55 440	53.18 458	57.73 479	18.19 508	70.24 427	71.02 430	45.70 427	33.70 480	60.23 471	18.00 459	69.86 466	27.97 461	34.35 479	71.49 463

pmmvs3		45.53 445	41.55 450	57.44 449	48.97 496	39.68 434	70.06 428	57.66 473	28.32 485	34.06 479	57.29 479	8.50 489	66.85 472	34.86 431	34.26 480	65.80 476

tpmvs		62.45 359	59.42 366	71.53 331	83.93 106	54.32 117	70.03 429	77.61 351	51.91 377	53.48 381	68.29 442	37.91 263	86.66 295	33.36 436	58.27 363	73.62 447

tpm cat1		66.28 316	62.78 328	76.77 154	81.40 191	57.14 26	70.03 429	77.19 358	53.00 369	58.76 307	70.73 433	46.17 129	86.73 292	43.27 389	64.46 303	86.44 259

PatchMatch-RL		56.66 398	53.75 403	65.37 406	77.91 292	45.28 378	69.78 431	60.38 468	41.35 449	47.57 424	73.73 396	16.83 466	76.91 431	36.99 414	59.21 354	73.92 445

MDA-MVSNet-bldmvs		51.56 429	47.75 437	63.00 422	71.60 400	47.32 339	69.70 432	72.12 416	43.81 441	27.65 494	63.38 459	21.97 439	75.96 439	27.30 464	32.19 483	65.70 477

miper_lstm_enhance		63.91 339	62.30 333	68.75 371	75.06 355	46.78 347	69.02 433	81.14 260	59.68 248	52.76 384	72.39 414	40.71 233	77.99 420	56.81 287	53.09 414	81.48 359

sd_testset		67.79 279	65.95 289	73.32 274	81.70 173	46.33 360	68.99 434	80.30 279	66.58 102	61.64 264	82.38 291	30.45 377	87.63 255	55.86 298	65.60 292	86.01 265

test_fmvs1		53.60 418	52.54 412	56.78 450	58.07 477	30.26 474	68.95 435	42.19 492	32.46 477	63.59 239	82.56 287	11.55 478	60.81 479	58.25 268	55.27 396	79.28 387

GG-mvs-BLEND				77.77 114	86.68 53	50.61 225	68.67 436	88.45 59		68.73 161	87.45 197	59.15 12	90.67 113	54.83 307	87.67 18	92.03 50

OurMVSNet-221017-0		52.39 425	48.73 429	63.35 421	65.21 454	38.42 442	68.54 437	64.95 455	38.19 457	39.57 462	71.43 427	13.23 475	79.92 401	37.16 410	40.32 465	71.72 460

nomal-1		72.45 170	71.14 177	76.37 162	84.65 87	56.28 46	68.39 438	88.28 63	67.21 89	62.98 245	80.23 321	49.71 80	86.05 318	69.36 160	69.48 255	86.78 252

FE-MVS		64.15 336	60.43 358	75.30 209	80.85 208	49.86 251	68.28 439	78.37 336	50.26 393	59.31 293	73.79 395	26.19 405	91.92 70	40.19 401	66.67 277	84.12 301

test_fmvs1_n		52.55 423	51.19 417	56.65 451	51.90 488	30.14 475	67.66 440	42.84 491	32.27 478	62.30 254	82.02 301	9.12 487	60.84 478	57.82 277	54.75 402	78.99 389

MIMVSNet1		50.35 435	47.81 435	57.96 448	61.53 472	27.80 489	67.40 441	74.06 396	43.25 444	33.31 485	65.38 456	16.03 470	71.34 461	21.80 481	47.55 439	74.75 438

mvsmamba		69.38 244	67.52 255	74.95 223	82.86 140	52.22 181	67.36 442	76.75 366	61.14 220	49.43 411	82.04 300	37.26 282	84.14 354	73.93 116	76.91 139	88.50 203

test_vis1_n		51.19 431	49.66 426	55.76 455	51.26 491	29.85 480	67.20 443	38.86 496	32.12 479	59.50 289	79.86 325	8.78 488	58.23 486	56.95 286	52.46 416	79.19 388

MTAPA		72.73 164	71.22 174	77.27 131	81.54 186	53.57 134	67.06 444	81.31 257	59.41 253	68.39 163	90.96 90	36.07 309	89.01 181	73.80 120	82.45 71	89.23 174

WB-MVS		37.41 455	36.37 455	40.54 476	54.23 484	10.43 515	65.29 445	43.75 489	34.86 475	27.81 493	54.63 482	24.94 417	63.21 475	6.81 512	15.00 505	47.98 495

kuosan		50.20 436	50.09 421	50.52 462	73.09 381	29.09 485	65.25 446	74.89 386	48.27 405	41.34 455	60.85 470	43.45 194	67.48 470	18.59 491	25.07 494	55.01 488

MIMVSNet		63.12 349	60.29 360	71.61 327	75.92 340	46.65 350	65.15 447	81.94 242	59.14 264	54.65 368	69.47 437	25.74 409	80.63 391	41.03 400	69.56 254	87.55 226

XVG-OURS-SEG-HR		62.02 361	59.54 365	69.46 361	65.30 453	45.88 370	65.06 448	73.57 403	46.45 419	57.42 337	83.35 271	26.95 399	78.09 416	53.77 315	64.03 306	84.42 295

XVG-OURS		61.88 362	59.34 367	69.49 360	65.37 452	46.27 362	64.80 449	73.49 405	47.04 415	57.41 338	82.85 276	25.15 415	78.18 414	53.00 323	64.98 294	84.01 305

dmvs_re		67.61 282	66.00 287	72.42 304	81.86 168	43.45 400	64.67 450	80.00 285	69.56 56	60.07 279	85.00 241	34.71 329	87.63 255	51.48 338	66.68 276	86.17 264

gg-mvs-nofinetune		67.43 288	64.53 316	76.13 173	85.95 61	47.79 328	64.38 451	88.28 63	39.34 453	66.62 178	41.27 493	58.69 16	89.00 182	49.64 349	86.62 32	91.59 69

dongtai		43.51 446	44.07 447	41.82 473	63.75 464	21.90 498	63.80 452	72.05 417	39.59 452	33.35 484	54.54 483	41.04 226	57.30 487	10.75 505	17.77 503	46.26 496

dmvs_testset		57.65 394	58.21 374	55.97 454	74.62 361	9.82 516	63.75 453	63.34 463	67.23 88	48.89 415	83.68 266	39.12 252	76.14 438	23.43 476	59.80 348	81.96 349

XVG-ACMP-BASELINE		56.03 404	52.85 408	65.58 402	61.91 471	40.95 430	63.36 454	72.43 414	45.20 431	46.02 434	74.09 391	9.20 486	78.12 415	45.13 378	58.27 363	77.66 411

TinyColmap		48.15 440	44.49 444	59.13 445	65.73 451	38.04 443	63.34 455	62.86 465	38.78 454	29.48 489	67.23 447	6.46 496	73.30 454	24.59 471	41.90 459	66.04 475

MVS-HIRNet		49.01 438	44.71 442	61.92 431	76.06 333	46.61 352	63.23 456	54.90 478	24.77 489	33.56 481	36.60 499	21.28 442	75.88 441	29.49 451	62.54 327	63.26 482

PM-MVS		46.92 442	43.76 448	56.41 453	52.18 487	32.26 467	63.21 457	38.18 497	37.99 459	40.78 459	66.20 450	5.09 500	65.42 473	48.19 361	41.99 458	71.54 462

AllTest		47.32 441	44.66 443	55.32 456	65.08 456	37.50 446	62.96 458	54.25 480	35.45 472	33.42 482	72.82 407	9.98 483	59.33 482	24.13 472	43.84 454	69.13 466

USDC		54.36 411	51.23 416	63.76 415	64.29 462	37.71 445	62.84 459	73.48 407	56.85 310	35.47 475	71.94 426	9.23 485	78.43 411	38.43 407	48.57 431	75.13 435

mvs5depth		50.97 432	46.98 438	62.95 423	56.63 481	34.23 456	62.73 460	67.35 449	45.03 433	48.00 420	65.41 455	10.40 482	79.88 405	36.00 419	31.27 486	74.73 439

SSC-MVS		35.20 457	34.30 459	37.90 478	52.58 486	8.65 518	61.86 461	41.64 493	31.81 480	25.54 496	52.94 488	23.39 429	59.28 484	6.10 514	12.86 507	45.78 498

Patchmatch-RL test		58.72 386	54.32 399	71.92 323	63.91 463	44.25 391	61.73 462	55.19 477	57.38 301	49.31 413	54.24 484	37.60 273	80.89 384	62.19 228	47.28 441	90.63 119

SCA		63.84 340	60.01 363	75.32 206	78.58 278	57.92 14	61.61 463	77.53 352	56.71 317	57.75 328	70.77 431	31.97 362	79.91 403	48.80 355	56.36 382	88.13 212

CMPMVS	40.41 21	55.34 407	52.64 410	63.46 419	60.88 474	43.84 396	61.58 464	71.06 429	30.43 482	36.33 472	74.63 388	24.14 424	75.44 442	48.05 362	66.62 278	71.12 464
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LCM-MVSNet-Re		58.82 384	56.54 383	65.68 401	79.31 254	29.09 485	61.39 465	45.79 486	60.73 232	37.65 469	72.47 412	31.42 370	81.08 383	49.66 348	70.41 245	86.87 243

CR-MVSNet		62.47 358	59.04 370	72.77 290	73.97 373	56.57 37	60.52 466	71.72 421	60.04 240	57.49 334	65.86 451	38.94 253	80.31 396	42.86 393	59.93 345	81.42 360

RPMNet		59.29 375	54.25 400	74.42 236	73.97 373	56.57 37	60.52 466	76.98 362	35.72 470	57.49 334	58.87 477	37.73 268	85.26 338	27.01 465	59.93 345	81.42 360

EGC-MVSNET		33.75 459	30.42 463	43.75 472	64.94 458	36.21 449	60.47 468	40.70 495	0.02 556	0.10 553	53.79 485	7.39 490	60.26 480	11.09 503	35.23 477	34.79 500

test_vis1_rt		40.29 451	38.64 452	45.25 470	48.91 497	30.09 476	59.44 469	27.07 510	24.52 490	38.48 467	51.67 489	6.71 494	49.44 495	44.33 383	46.59 447	56.23 486

Patchmtry		56.56 400	52.95 407	67.42 384	72.53 389	50.59 227	59.05 470	71.72 421	37.86 460	46.92 429	65.86 451	38.94 253	80.06 400	36.94 415	46.72 446	71.60 461

TDRefinement		40.91 449	38.37 453	48.55 466	50.45 493	33.03 463	58.98 471	50.97 483	28.50 483	29.89 488	67.39 446	6.21 498	54.51 491	17.67 492	35.25 476	58.11 485

test_fmvs2		45.89 443	44.32 445	50.62 461	45.85 500	24.70 492	58.87 472	37.84 499	25.22 488	52.46 386	74.56 389	7.07 491	54.69 490	49.28 352	47.70 437	72.48 455

KD-MVS_self_test		49.24 437	46.85 439	56.44 452	54.32 483	22.87 494	57.39 473	73.36 410	44.36 438	37.98 468	59.30 476	18.97 454	71.17 462	33.48 435	42.44 457	75.26 433

PatchT		56.60 399	52.97 406	67.48 383	72.94 384	46.16 367	57.30 474	73.78 400	38.77 455	54.37 371	57.26 480	37.52 275	78.06 417	32.02 441	52.79 415	78.23 404

ttmdpeth		40.58 450	37.50 454	49.85 463	49.40 494	22.71 495	56.65 475	46.78 484	28.35 484	40.29 461	69.42 438	5.35 499	61.86 477	20.16 486	21.06 500	64.96 478

mvsany_test1		43.38 447	42.57 449	45.82 468	50.96 492	26.10 490	55.80 476	27.74 509	27.15 486	47.41 427	74.39 390	18.67 456	44.95 501	44.66 381	36.31 473	66.40 474

ANet_high		34.39 458	29.59 464	48.78 465	30.34 510	22.28 496	55.53 477	63.79 462	38.11 458	15.47 503	36.56 500	6.94 492	59.98 481	13.93 498	5.64 515	64.08 479

ADS-MVSNet2		55.21 409	51.44 415	66.51 395	80.60 215	49.56 258	55.03 478	65.44 454	44.72 434	51.00 400	61.19 468	22.83 430	75.41 443	28.54 457	53.63 408	74.57 441

ADS-MVSNet		56.17 403	51.95 414	68.84 367	80.60 215	53.07 155	55.03 478	70.02 436	44.72 434	51.00 400	61.19 468	22.83 430	78.88 409	28.54 457	53.63 408	74.57 441

RPSCF		45.77 444	44.13 446	50.68 460	57.67 480	29.66 481	54.92 480	45.25 488	26.69 487	45.92 435	75.92 381	17.43 464	45.70 500	27.44 463	45.95 449	76.67 419

new_pmnet		33.56 460	31.89 462	38.59 477	49.01 495	20.42 501	51.01 481	37.92 498	20.58 491	23.45 497	46.79 491	6.66 495	49.28 497	20.00 488	31.57 485	46.09 497

MVStest1		38.35 452	34.53 458	49.82 464	51.43 490	30.41 473	50.39 482	55.25 476	17.56 497	26.45 495	65.85 453	11.72 477	57.00 488	14.79 496	17.31 504	62.05 484

test_fmvs3		37.95 454	35.75 456	44.55 471	35.50 506	18.92 504	48.32 483	34.00 504	18.36 496	41.31 457	61.58 464	2.29 507	48.06 499	42.72 394	37.71 471	66.66 473

E-PMN		19.16 473	18.40 477	21.44 491	36.19 505	13.63 513	47.59 484	30.89 505	10.73 505	5.91 519	16.59 518	3.66 503	39.77 504	5.95 515	8.14 510	10.92 515

EMVS		18.42 474	17.66 478	20.71 492	34.13 507	12.64 514	46.94 485	29.94 507	10.46 507	5.58 521	14.93 521	4.23 502	38.83 505	5.24 518	7.51 512	10.67 516

CHOSEN 280x420		57.53 396	56.38 388	60.97 438	74.01 371	48.10 312	46.30 486	54.31 479	48.18 407	50.88 405	77.43 355	38.37 259	59.16 485	54.83 307	63.14 321	75.66 429

mamba_0408		66.33 315	62.87 326	76.70 155	80.45 223	51.81 195	46.11 487	78.90 317	55.46 342	63.82 231	84.54 245	31.91 365	91.03 95	55.68 301	68.97 258	87.25 234

SSM_04072		64.04 338	62.87 326	67.56 382	80.45 223	51.81 195	46.11 487	78.90 317	55.46 342	63.82 231	84.54 245	31.91 365	63.62 474	55.68 301	68.97 258	87.25 234

LTVRE_ROB	45.45 19	52.73 421	49.74 425	61.69 432	69.78 428	34.99 450	44.52 489	67.60 448	43.11 445	43.79 441	74.03 392	18.54 457	81.45 380	28.39 459	57.94 370	68.62 468
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
LF4IMVS		33.04 461	32.55 461	34.52 481	40.96 501	22.03 497	44.45 490	35.62 501	20.42 492	28.12 492	62.35 463	5.03 501	31.88 513	21.61 483	34.42 478	49.63 493

Patchmatch-test		53.33 420	48.17 433	68.81 369	73.31 376	42.38 416	42.98 491	58.23 472	32.53 476	38.79 466	70.77 431	39.66 246	73.51 452	25.18 469	52.06 418	90.55 122

PMMVS2		26.71 466	22.98 471	37.87 479	36.89 504	8.51 519	42.51 492	29.32 508	19.09 495	13.01 506	37.54 496	2.23 508	53.11 492	14.54 497	11.71 508	51.99 492

FPMVS		35.40 456	33.67 460	40.57 475	46.34 499	28.74 487	41.05 493	57.05 475	20.37 493	22.27 498	53.38 486	6.87 493	44.94 502	8.62 506	47.11 443	48.01 494

PMVS	19.57 22	25.07 468	22.43 473	32.99 485	23.12 517	22.98 493	40.98 494	35.19 502	15.99 499	11.95 511	35.87 501	1.47 515	49.29 496	5.41 517	31.90 484	26.70 507
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
APD_test1		26.46 467	24.41 468	32.62 486	37.58 503	21.74 499	40.50 495	30.39 506	11.45 504	16.33 501	43.76 492	1.63 513	41.62 503	11.24 502	26.82 492	34.51 501

JIA-IIPM		52.33 426	47.77 436	66.03 398	71.20 406	46.92 343	40.00 496	76.48 373	37.10 463	46.73 430	37.02 497	32.96 350	77.88 422	35.97 420	52.45 417	73.29 451

DSMNet-mixed		38.35 452	35.36 457	47.33 467	48.11 498	14.91 512	37.87 497	36.60 500	19.18 494	34.37 478	59.56 475	15.53 471	53.01 493	20.14 487	46.89 445	74.07 443

test_vis3_rt		24.79 469	22.95 472	30.31 487	28.59 512	18.92 504	37.43 498	17.27 517	12.90 501	21.28 499	29.92 507	1.02 516	36.35 506	28.28 460	29.82 490	35.65 499

ambc				62.06 428	53.98 485	29.38 483	35.08 499	79.65 300		41.37 454	59.96 473	6.27 497	82.15 375	35.34 425	38.22 470	74.65 440

mvsany_test3		28.00 463	25.98 465	34.05 482	28.97 511	15.31 510	34.54 500	18.17 515	16.24 498	29.30 490	53.37 487	2.79 505	33.38 512	30.01 450	20.41 501	53.45 490

testf1		21.11 471	19.08 475	27.18 489	30.56 508	18.28 506	33.43 501	24.48 511	8.02 508	12.02 509	33.50 503	0.75 518	35.09 509	7.68 508	21.32 497	28.17 504

APD_test2		21.11 471	19.08 475	27.18 489	30.56 508	18.28 506	33.43 501	24.48 511	8.02 508	12.02 509	33.50 503	0.75 518	35.09 509	7.68 508	21.32 497	28.17 504

LCM-MVSNet		28.07 462	23.85 470	40.71 474	27.46 515	18.93 503	30.82 503	46.19 485	12.76 502	16.40 500	34.70 502	1.90 510	48.69 498	20.25 485	24.22 495	54.51 489

test_f		27.12 465	24.85 466	33.93 483	26.17 516	15.25 511	30.24 504	22.38 514	12.53 503	28.23 491	49.43 490	2.59 506	34.34 511	25.12 470	26.99 491	52.20 491

test_method		24.09 470	21.07 474	33.16 484	27.67 514	8.35 521	26.63 505	35.11 503	3.40 515	14.35 504	36.98 498	3.46 504	35.31 508	19.08 490	22.95 496	55.81 487

ArgMatch-Sym		13.78 477	13.16 480	15.65 494	13.75 519	8.38 520	21.56 506	2.56 522	7.09 511	14.16 505	40.67 494	0.28 521	11.85 518	13.55 500	4.84 517	26.71 506

wuyk23d		9.11 481	8.77 485	10.15 496	40.18 502	16.76 509	20.28 507	1.01 526	2.58 517	2.66 528	0.98 542	0.23 523	12.49 517	4.08 523	6.90 513	1.19 529

ArgMatch-SfM		13.59 478	12.41 481	17.15 493	12.50 520	7.57 522	19.17 508	3.21 521	5.58 512	12.94 507	39.91 495	0.26 522	13.40 515	13.23 501	4.84 517	30.48 503

MVE	16.60 23	17.34 476	13.39 479	29.16 488	28.43 513	19.72 502	13.73 509	23.63 513	7.23 510	7.96 515	21.41 513	0.80 517	36.08 507	6.97 510	10.39 509	31.69 502
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
VLMVS_CLIP		11.28 479	11.90 482	9.42 498	7.54 523	3.26 526	13.10 510	10.36 519	1.51 521	15.95 502	32.54 505	1.51 514	12.70 516	10.98 504	13.62 506	12.29 513

Gipuma		27.47 464	24.26 469	37.12 480	60.55 476	29.17 484	11.68 511	60.00 469	14.18 500	10.52 512	15.12 520	2.20 509	63.01 476	8.39 507	35.65 474	19.18 508
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DenseAffine		8.44 482	7.90 488	10.07 497	9.51 521	4.71 523	11.43 512	1.10 525	4.32 513	8.26 514	27.67 509	0.09 525	8.71 519	6.30 513	2.41 522	16.80 509

tmp_tt		9.44 480	10.68 483	5.73 503	2.49 534	4.21 524	10.48 513	18.04 516	0.34 527	12.59 508	20.49 515	11.39 479	7.03 521	13.84 499	6.46 514	5.95 522

RoMa-SfM		7.02 484	6.78 489	7.74 499	5.47 526	3.55 525	8.83 514	0.67 530	3.41 514	7.06 517	27.85 508	0.08 526	7.13 520	5.86 516	1.82 524	12.53 511

DKM		5.93 488	5.87 491	6.10 502	5.64 524	2.81 527	7.85 515	0.52 533	2.62 516	6.30 518	23.31 511	0.05 531	4.93 523	5.11 519	1.45 526	10.57 517

PDCNetPlus		5.70 489	5.56 492	6.14 501	8.32 522	1.98 529	7.37 516	0.76 529	2.18 518	3.69 526	20.81 514	0.12 524	4.60 524	4.55 520	2.21 523	11.83 514

LoFTR		5.36 490	5.09 493	6.17 500	5.52 525	2.23 528	6.04 517	2.15 523	1.23 522	5.61 520	19.15 516	0.07 527	5.98 522	1.61 527	4.48 519	10.30 518

MatchFormer		3.89 493	3.84 497	4.03 507	4.08 528	1.73 532	5.52 518	1.59 524	0.67 523	4.77 524	13.56 524	0.04 537	4.50 525	0.74 531	3.60 521	5.85 523

RoMa-HiRes		4.68 491	4.75 494	4.46 505	3.18 531	1.88 530	5.38 519	0.37 538	2.04 519	4.84 522	21.68 512	0.06 528	3.78 526	4.17 522	1.04 531	7.71 521

DKM-HiRes		4.42 492	4.49 495	4.23 506	3.85 529	1.83 531	5.38 519	0.33 539	1.86 520	4.78 523	18.85 517	0.04 537	2.97 528	4.34 521	0.97 532	7.88 520

VLMVS		5.96 487	6.29 490	4.99 504	5.31 527	1.01 534	4.24 521	0.93 527	0.06 540	8.90 513	26.22 510	1.69 512	1.62 531	3.76 524	5.49 516	12.33 512

MVS_clip		3.10 495	3.65 498	1.44 511	3.78 530	1.17 533	2.78 522	0.19 541	0.20 530	4.48 525	14.54 523	0.35 520	0.47 537	2.92 525	3.64 520	2.67 527

PMatch-SfM		2.38 497	2.41 499	2.29 510	1.48 537	0.76 540	2.51 523	0.18 543	0.59 524	2.43 530	12.04 525	0.01 546	1.67 530	1.93 526	0.55 539	4.44 525

ALIKED-LG		1.21 501	1.31 505	0.90 514	2.88 532	0.91 536	1.96 524	0.48 534	0.17 531	0.94 534	3.75 532	0.06 528	0.81 533	0.10 541	1.43 527	0.99 530

ELoFTR		2.17 498	1.90 502	2.99 509	1.19 540	0.63 541	1.84 525	0.60 531	0.46 525	2.17 531	9.10 528	0.02 545	2.92 529	1.00 530	0.72 536	5.42 524

MASt3R-SfM		1.80 499	2.02 501	1.14 513	1.03 543	0.52 542	1.83 526	0.53 532	0.34 527	2.55 529	9.61 527	0.05 531	0.77 534	1.06 529	1.16 530	2.14 528

ALIKED-MNN		1.07 503	1.15 506	0.84 515	2.67 533	0.92 535	1.81 527	0.39 535	0.12 532	0.73 536	3.13 533	0.05 531	0.77 534	0.09 542	1.34 528	0.84 532

PMatch-Up-SfM		1.67 500	1.74 503	1.44 511	1.00 544	0.50 543	1.72 528	0.11 549	0.40 526	1.75 532	8.98 529	0.00 561	1.07 532	1.34 528	0.35 552	2.76 526

GLUNet-SfM		2.60 496	2.13 500	4.01 508	1.95 536	0.86 537	1.72 528	0.81 528	0.34 527	3.35 527	9.72 526	0.04 537	3.15 527	0.50 532	0.73 535	8.02 519

ALIKED-NN		1.00 504	1.09 507	0.75 516	2.44 535	0.84 538	1.63 530	0.39 535	0.12 532	0.72 537	3.04 534	0.05 531	0.70 536	0.08 543	1.32 529	0.72 538

SP-LightGlue		0.48 507	0.50 510	0.40 517	1.33 538	0.19 551	0.86 531	0.17 544	0.08 536	0.25 541	1.08 538	0.05 531	0.19 541	0.13 537	0.57 538	0.80 533

SP-SuperGlue		0.47 508	0.50 510	0.39 518	1.30 539	0.19 551	0.86 531	0.17 544	0.09 534	0.26 540	1.08 538	0.05 531	0.18 543	0.13 537	0.55 539	0.79 535

SP-MNN		0.45 509	0.47 513	0.39 518	1.18 541	0.17 555	0.85 533	0.16 546	0.07 538	0.24 542	1.05 540	0.04 537	0.20 540	0.12 539	0.54 541	0.80 533

SP-NN		0.43 511	0.45 514	0.37 522	1.13 542	0.17 555	0.82 534	0.16 546	0.07 538	0.24 542	1.00 541	0.04 537	0.19 541	0.12 539	0.51 542	0.74 537

SP-DiffGlue		0.50 506	0.53 509	0.38 521	0.41 560	0.20 550	0.62 535	0.19 541	0.09 534	0.64 539	1.95 536	0.06 528	0.17 544	0.26 534	0.60 537	0.77 536

XFeat-MNN		0.55 505	0.60 508	0.39 518	0.26 561	0.16 558	0.58 536	0.20 540	0.08 536	0.82 535	2.26 535	0.03 542	0.39 538	0.19 535	0.95 533	0.62 539

XFeat-NN		0.44 510	0.49 512	0.30 524	0.24 562	0.12 561	0.48 537	0.15 548	0.06 540	0.71 538	1.78 537	0.03 542	0.28 539	0.14 536	0.83 534	0.48 540

SIFT-NN		0.30 512	0.33 515	0.22 525	0.96 545	0.28 544	0.45 538	0.08 550	0.05 542	0.17 544	0.72 543	0.01 546	0.14 545	0.02 544	0.48 543	0.25 541

SIFT-MNN		0.28 513	0.31 516	0.21 526	0.89 546	0.25 545	0.41 539	0.08 550	0.05 542	0.15 545	0.70 544	0.01 546	0.14 545	0.02 544	0.46 545	0.25 541

SIFT-NN-NCMNet		0.27 514	0.29 517	0.20 527	0.81 548	0.24 546	0.40 540	0.08 550	0.05 542	0.14 547	0.65 545	0.01 546	0.14 545	0.02 544	0.47 544	0.22 545

SIFT-NCM-Cal		0.26 515	0.28 518	0.19 528	0.84 547	0.23 547	0.38 541	0.06 553	0.05 542	0.11 551	0.59 550	0.01 546	0.14 545	0.02 544	0.45 546	0.21 547

SIFT-NN-UMatch		0.24 517	0.26 519	0.18 530	0.64 555	0.18 553	0.38 541	0.06 553	0.05 542	0.12 550	0.65 545	0.01 546	0.13 549	0.02 544	0.43 547	0.22 545

SIFT-NN-CMatch		0.25 516	0.26 519	0.19 528	0.68 553	0.21 548	0.35 543	0.06 553	0.05 542	0.15 545	0.65 545	0.01 546	0.13 549	0.02 544	0.41 548	0.23 543

SIFT-UMatch		0.23 519	0.25 522	0.16 533	0.74 550	0.17 555	0.33 544	0.05 556	0.05 542	0.11 551	0.60 549	0.01 546	0.13 549	0.02 544	0.37 551	0.18 550

SIFT-NN-PointCN		0.22 520	0.24 523	0.17 532	0.59 556	0.14 560	0.32 545	0.05 556	0.04 552	0.13 548	0.57 551	0.01 546	0.13 549	0.02 544	0.39 549	0.23 543

SIFT-ConvMatch		0.24 517	0.26 519	0.18 530	0.76 549	0.21 548	0.32 545	0.05 556	0.05 542	0.13 548	0.63 548	0.01 546	0.13 549	0.02 544	0.38 550	0.19 548

SIFT-UM-Cal		0.21 521	0.23 524	0.14 535	0.68 553	0.15 559	0.29 547	0.04 560	0.05 542	0.10 553	0.56 552	0.01 546	0.12 554	0.02 544	0.34 553	0.15 553

SIFT-CM-Cal		0.21 521	0.23 524	0.15 534	0.71 552	0.18 553	0.28 548	0.05 556	0.05 542	0.10 553	0.55 553	0.01 546	0.12 554	0.01 556	0.33 554	0.17 551

SIFT-PointCN		0.18 523	0.20 526	0.13 536	0.58 557	0.11 562	0.25 549	0.04 560	0.04 552	0.08 556	0.45 555	0.01 546	0.10 556	0.01 556	0.30 555	0.17 551

MVS_baseline		1.13 502	1.40 504	0.34 523	0.74 550	0.01 565	0.24 550	0.03 563	0.00 557	1.75 532	7.74 530	0.03 542	0.00 559	0.31 533	1.74 525	0.99 530

SIFT-PCN-Cal		0.18 523	0.20 526	0.13 536	0.58 557	0.10 563	0.23 551	0.04 560	0.04 552	0.08 556	0.47 554	0.01 546	0.10 556	0.01 556	0.30 555	0.19 548

SIFT-NCMNet		0.15 525	0.17 528	0.10 538	0.52 559	0.09 564	0.19 552	0.02 564	0.04 552	0.07 558	0.39 556	0.01 546	0.08 558	0.01 556	0.24 557	0.11 554

mmdepth		0.00 526	0.00 529	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	0.00 559	0.00 561	0.00 559	0.00 560	0.00 558	0.00 557

monomultidepth		0.00 526	0.00 529	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	0.00 559	0.00 561	0.00 559	0.00 560	0.00 558	0.00 557

test_blank		0.00 526	0.00 529	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	0.00 559	0.00 561	0.00 559	0.00 560	0.00 558	0.00 557

uanet_test		0.00 526	0.00 529	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	0.00 559	0.00 561	0.00 559	0.00 560	0.00 558	0.00 557

DCPMVS		0.00 526	0.00 529	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	0.00 559	0.00 561	0.00 559	0.00 560	0.00 558	0.00 557

cdsmvs_eth3d_5k		18.33 475	24.44 467	0.00 541	0.00 564	0.00 567	0.00 553	89.40 29	0.00 557	0.00 561	92.02 63	38.55 257	0.00 559	0.00 560	0.00 558	0.00 557

pcd_1.5k_mvsjas		3.15 494	4.20 496	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	0.00 559	37.77 265	0.00 559	0.00 560	0.00 558	0.00 557

sosnet-low-res		0.00 526	0.00 529	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	0.00 559	0.00 561	0.00 559	0.00 560	0.00 558	0.00 557

sosnet		0.00 526	0.00 529	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	0.00 559	0.00 561	0.00 559	0.00 560	0.00 558	0.00 557

uncertanet		0.00 526	0.00 529	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	0.00 559	0.00 561	0.00 559	0.00 560	0.00 558	0.00 557

Regformer		0.00 526	0.00 529	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	0.00 559	0.00 561	0.00 559	0.00 560	0.00 558	0.00 557

ab-mvs-re		7.68 483	10.24 484	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	92.12 59	0.00 561	0.00 559	0.00 560	0.00 558	0.00 557

uanet		0.00 526	0.00 529	0.00 541	0.00 564	0.00 567	0.00 553	0.00 565	0.00 557	0.00 561	0.00 559	0.00 561	0.00 559	0.00 560	0.00 558	0.00 557

PatchmatchNet1														23.45 475	40.77 460	68.54 469
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													67.71 469
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					88.20 37	55.35 65		88.22 65		80.74 28		53.67 44	94.67 21	80.11 56	85.96 38

WAC-MVS						34.28 454								22.56 479

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

PC_three_1452									66.58 102	87.27 3	93.70 18	66.82 4	94.95 18	89.74 4	91.98 4	93.98 6

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

test_one_0601					89.39 23	57.29 24		88.09 68	57.21 306	82.06 15	93.39 27	54.94 38

eth-test2					0.00 564

eth-test					0.00 564

ZD-MVS					89.55 15	53.46 136		84.38 187	57.02 308	73.97 74	91.03 86	44.57 176	91.17 91	75.41 99	81.78 78

IU-MVS					89.48 18	57.49 19		91.38 9	66.22 111	88.26 2				82.83 33	87.60 19	92.44 35

test_241102_TWO								88.76 46	57.50 298	83.60 7	94.09 8	56.14 29	96.37 7	82.28 38	87.43 21	92.55 33

test_241102_ONE					89.48 18	56.89 31		88.94 37	57.53 296	84.61 5	93.29 31	58.81 14	96.45 1

test_0728_THIRD									58.00 284	81.91 16	93.64 20	56.54 25	96.44 2	81.64 44	86.86 27	92.23 41

GSMVS																88.13 212

test_part2					89.33 24	55.48 58				82.27 13

sam_mvs1												38.86 255				88.13 212

sam_mvs												35.99 312

MTGPA								81.31 257

test_post											16.22 519	37.52 275	84.72 348

patchmatchnet-post											59.74 474	38.41 258	79.91 403

gm-plane-assit					83.24 123	54.21 122			70.91 33		88.23 165		95.25 15	66.37 183

test9_res														78.72 67	85.44 46	91.39 79

agg_prior2														75.65 94	85.11 53	91.01 104

agg_prior					85.64 68	54.92 92		83.61 211		72.53 96			88.10 229

TestCases				55.32 456	65.08 456	37.50 446		54.25 480	35.45 472	33.42 482	72.82 407	9.98 483	59.33 482	24.13 472	43.84 454	69.13 466

test_prior				78.39 97	86.35 58	54.91 95		85.45 133					89.70 154			90.55 122

新几何1				73.30 276	83.10 126	53.48 135		71.43 425	45.55 428	66.14 184	87.17 203	33.88 341	80.54 393	48.50 358	80.33 93	85.88 272

旧先验1					81.57 185	47.48 334		71.83 419			88.66 145	36.94 290			78.34 120	88.67 191

原ACMM1				76.13 173	84.89 84	54.59 112		85.26 144	51.98 376	66.70 176	87.07 205	40.15 240	89.70 154	51.23 340	85.06 54	84.10 302

testdata2													77.81 424	45.64 377

segment_acmp												44.97 166

testdata				67.08 388	77.59 296	45.46 377		69.20 441	44.47 436	71.50 118	88.34 160	31.21 372	70.76 464	52.20 335	75.88 161	85.03 285

test12				79.24 52	86.89 51	56.08 49		85.16 150		72.27 100		47.15 109	91.10 94		85.93 40	90.54 124

plane_prior7					77.95 289	48.46 296

plane_prior6					78.42 282	49.39 268						36.04 310

plane_prior5								82.59 229					88.30 222	65.46 194	72.34 218	84.49 293

plane_prior4											83.28 272

plane_prior3						48.95 277			64.01 156	62.15 257

plane_prior1					78.31 285

n2								0.00 565

nn								0.00 565

door-mid								41.31 494

lessismore_v0				67.98 379	64.76 459	41.25 427		45.75 487		36.03 474	65.63 454	19.29 453	84.11 355	35.67 421	21.24 499	78.59 396

LGP-MVS_train				72.02 315	74.42 364	48.60 289		80.64 271	54.69 354	53.75 378	83.83 259	25.73 410	86.98 279	60.33 249	64.71 299	80.48 377

test11								84.25 191

door								43.27 490

HQP5-MVS						51.56 202

BP-MVS														66.70 180

HQP4-MVS										64.47 220			88.61 201			84.91 289

HQP3-MVS								83.68 206							73.12 206

HQP2-MVS												37.35 278

NP-MVS					78.76 270	50.43 232					85.12 236

ACMMP++_ref															63.20 319

ACMMP++															59.38 352

Test By Simon												39.38 249

ITE_SJBPF				51.84 459	58.03 478	31.94 470		53.57 482	36.67 465	41.32 456	75.23 385	11.17 480	51.57 494	25.81 468	48.04 435	72.02 459

DeepMVS_CX				13.10 495	21.34 518	8.99 517		10.02 520	10.59 506	7.53 516	30.55 506	1.82 511	14.55 514	6.83 511	7.52 511	15.75 510

High-resolution multi-view benchmark