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.

LCM-MVSNet		95.70 1	96.40 1	93.61 3	98.67 1	85.39 37	95.54 5	97.36 1	96.97 1	99.04 1	99.05 1	96.61 1	95.92 16	85.07 69	99.27 1	99.54 1

XVG-OURS-SEG-HR		89.59 56	89.37 62	90.28 46	94.47 43	85.95 27	86.84 128	93.91 48	80.07 100	86.75 189	93.26 128	93.64 2	90.93 210	84.60 78	90.75 302	93.97 117

ACMH+	77.89 11	90.73 32	91.50 26	88.44 81	93.00 86	76.26 122	89.65 76	95.55 9	87.72 27	93.89 31	94.94 56	91.62 3	93.44 136	78.35 150	98.76 4	95.61 55

lecture		92.43 9	93.50 3	89.21 66	94.43 44	79.31 84	92.69 19	95.72 8	88.48 22	94.43 20	95.73 34	91.34 4	94.68 78	90.26 4	98.44 20	93.63 139

LPG-MVS_test		91.47 22	91.68 21	90.82 37	94.75 41	81.69 63	90.00 63	94.27 25	82.35 74	93.67 38	94.82 60	91.18 5	95.52 45	85.36 65	98.73 7	95.23 66

LGP-MVS_train				90.82 37	94.75 41	81.69 63		94.27 25	82.35 74	93.67 38	94.82 60	91.18 5	95.52 45	85.36 65	98.73 7	95.23 66

PMVS	80.48 6	90.08 42	90.66 49	88.34 84	96.71 3	92.97 2	90.31 60	89.57 208	88.51 21	90.11 102	95.12 53	90.98 7	88.92 269	77.55 164	97.07 88	83.13 392
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ACMM	79.39 9	90.65 33	90.99 42	89.63 58	95.03 34	83.53 51	89.62 77	93.35 70	79.20 112	93.83 32	93.60 122	90.81 8	92.96 152	85.02 72	98.45 19	92.41 198
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH	76.49 14	89.34 60	91.14 36	83.96 183	92.50 99	70.36 193	89.55 78	93.84 53	81.89 79	94.70 17	95.44 44	90.69 9	88.31 283	83.33 88	98.30 27	93.20 158
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS_fast		92.50 8	92.54 10	92.37 6	95.93 16	85.81 33	92.99 12	94.23 28	85.21 44	92.51 59	95.13 52	90.65 10	95.34 55	88.06 16	98.15 39	95.95 46

RE-MVS-def			92.61 9		94.13 57	88.95 6	92.87 13	94.16 33	88.75 18	93.79 33	94.43 76	90.64 11		87.16 37	97.60 71	92.73 178

ACMP	79.16 10	90.54 36	90.60 50	90.35 45	94.36 48	80.98 69	89.16 87	94.05 42	79.03 115	92.87 50	93.74 117	90.60 12	95.21 61	82.87 96	98.76 4	94.87 78
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HPM-MVS		92.13 12	92.20 14	91.91 17	95.58 26	84.67 46	93.51 8	94.85 16	82.88 70	91.77 72	93.94 108	90.55 13	95.73 35	88.50 12	98.23 33	95.33 61
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UniMVSNet_ETH3D		89.12 66	90.72 48	84.31 174	97.00 2	64.33 264	89.67 75	88.38 228	88.84 17	94.29 23	97.57 7	90.48 14	91.26 198	72.57 239	97.65 66	97.34 15

SED-MVS		90.46 38	91.64 22	86.93 105	94.18 52	72.65 152	90.47 56	93.69 57	83.77 58	94.11 27	94.27 83	90.28 15	95.84 24	86.03 55	97.92 52	92.29 210

test_241102_ONE					94.18 52	72.65 152		93.69 57	83.62 60	94.11 27	93.78 114	90.28 15	95.50 49

SR-MVS		92.23 11	92.34 12	91.91 17	94.89 38	87.85 10	92.51 25	93.87 52	88.20 24	93.24 43	94.02 100	90.15 17	95.67 38	86.82 41	97.34 81	92.19 216

APD-MVS_3200maxsize		92.05 13	92.24 13	91.48 25	93.02 85	85.17 39	92.47 27	95.05 15	87.65 28	93.21 44	94.39 81	90.09 18	95.08 66	86.67 43	97.60 71	94.18 109

DVP-MVS		90.06 44	91.32 33	86.29 117	94.16 55	72.56 158	90.54 53	91.01 159	83.61 61	93.75 35	94.65 65	89.76 19	95.78 32	86.42 45	97.97 49	90.55 273
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					94.16 55	72.56 158	90.63 50	93.90 49	83.61 61	93.75 35	94.49 73	89.76 19

COLMAP_ROB	83.01 3	91.97 14	91.95 15	92.04 11	93.68 67	86.15 24	93.37 10	95.10 14	90.28 10	92.11 64	95.03 54	89.75 21	94.93 70	79.95 128	98.27 28	95.04 74
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
reproduce-ours		92.86 6	93.22 6	91.76 23	94.39 46	87.71 11	92.40 28	94.38 20	89.82 13	95.51 12	95.49 42	89.64 22	95.82 26	89.13 7	98.26 30	91.76 232

our_new_method		92.86 6	93.22 6	91.76 23	94.39 46	87.71 11	92.40 28	94.38 20	89.82 13	95.51 12	95.49 42	89.64 22	95.82 26	89.13 7	98.26 30	91.76 232

test_241102_TWO								93.71 56	83.77 58	93.49 40	94.27 83	89.27 24	95.84 24	86.03 55	97.82 57	92.04 223

tt0805		88.09 80	89.79 56	82.98 214	93.26 80	63.94 268	91.10 46	89.64 205	85.07 45	90.91 88	91.09 210	89.16 25	91.87 183	82.03 107	95.87 139	93.13 161

ACMMP		91.91 15	91.87 20	92.03 12	95.53 27	85.91 28	93.35 11	94.16 33	82.52 73	92.39 62	94.14 93	89.15 26	95.62 39	87.35 32	98.24 32	94.56 89
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
SR-MVS-dyc-post		92.41 10	92.41 11	92.39 5	94.13 57	88.95 6	92.87 13	94.16 33	88.75 18	93.79 33	94.43 76	88.83 27	95.51 47	87.16 37	97.60 71	92.73 178

APDe-MVS		91.22 26	91.92 16	89.14 68	92.97 87	78.04 96	92.84 16	94.14 37	83.33 64	93.90 29	95.73 34	88.77 28	96.41 3	87.60 26	97.98 48	92.98 171
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_one_0601					93.85 64	73.27 145		94.11 39	86.57 34	93.47 42	94.64 68	88.42 29

ACMMP_NAP		90.65 33	91.07 40	89.42 62	95.93 16	79.54 82	89.95 67	93.68 59	77.65 134	91.97 68	94.89 57	88.38 30	95.45 51	89.27 6	97.87 56	93.27 154

MP-MVS-pluss		90.81 31	91.08 38	89.99 50	95.97 14	79.88 77	88.13 105	94.51 19	75.79 155	92.94 48	94.96 55	88.36 31	95.01 68	90.70 3	98.40 22	95.09 73
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		91.30 24	91.39 28	91.02 33	95.43 29	84.66 47	92.58 23	93.29 76	81.99 76	91.47 75	93.96 105	88.35 32	95.56 42	87.74 21	97.74 62	92.85 175

CP-MVS		91.67 17	91.58 24	91.96 14	95.29 31	87.62 13	93.38 9	93.36 69	83.16 66	91.06 84	94.00 101	88.26 33	95.71 37	87.28 35	98.39 23	92.55 191

SteuartSystems-ACMMP		91.16 28	91.36 29	90.55 41	93.91 62	80.97 70	91.49 41	93.48 67	82.82 71	92.60 58	93.97 102	88.19 34	96.29 6	87.61 25	98.20 36	94.39 101
Skip Steuart: Steuart Systems R&D Blog.
PGM-MVS		91.20 27	90.95 44	91.93 15	95.67 23	85.85 31	90.00 63	93.90 49	80.32 96	91.74 73	94.41 79	88.17 35	95.98 13	86.37 47	97.99 46	93.96 118

TDRefinement		93.52 3	93.39 5	93.88 2	95.94 15	90.26 4	95.70 4	96.46 3	90.58 9	92.86 51	96.29 22	88.16 36	94.17 102	86.07 54	98.48 18	97.22 18

DPE-MVS		90.53 37	91.08 38	88.88 71	93.38 76	78.65 90	89.15 88	94.05 42	84.68 49	93.90 29	94.11 95	88.13 37	96.30 5	84.51 79	97.81 58	91.70 236
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
OPM-MVS		89.80 52	89.97 53	89.27 64	94.76 40	79.86 78	86.76 132	92.78 100	78.78 118	92.51 59	93.64 121	88.13 37	93.84 116	84.83 75	97.55 74	94.10 114
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
pmmvs6		86.52 106	88.06 85	81.90 240	92.22 109	62.28 296	84.66 177	89.15 215	83.54 63	89.85 111	97.32 8	88.08 39	86.80 311	70.43 260	97.30 83	96.62 31

mvs_tets		89.78 53	89.27 64	91.30 29	93.51 70	84.79 44	89.89 69	90.63 169	70.00 247	94.55 19	96.67 17	87.94 40	93.59 128	84.27 81	95.97 129	95.52 56

ZNCC-MVS		91.26 25	91.34 32	91.01 34	95.73 21	83.05 56	92.18 32	94.22 30	80.14 99	91.29 80	93.97 102	87.93 41	95.87 20	88.65 10	97.96 51	94.12 113

reproduce_model		92.89 5	93.18 8	92.01 13	94.20 51	88.23 9	92.87 13	94.32 22	90.25 11	95.65 9	95.74 33	87.75 42	95.72 36	89.60 5	98.27 28	92.08 221

region2R		91.44 23	91.30 35	91.87 19	95.75 19	85.90 29	92.63 22	93.30 75	81.91 78	90.88 91	94.21 88	87.75 42	95.87 20	87.60 26	97.71 63	93.83 125

wuyk23d		75.13 316	79.30 266	62.63 424	75.56 424	75.18 131	80.89 278	73.10 392	75.06 167	94.76 16	95.32 45	87.73 44	52.85 456	34.16 454	97.11 87	59.85 452

mPP-MVS		91.69 16	91.47 27	92.37 6	96.04 13	88.48 8	92.72 18	92.60 107	83.09 67	91.54 74	94.25 87	87.67 45	95.51 47	87.21 36	98.11 40	93.12 163

ACMMPR		91.49 20	91.35 31	91.92 16	95.74 20	85.88 30	92.58 23	93.25 77	81.99 76	91.40 76	94.17 92	87.51 46	95.87 20	87.74 21	97.76 60	93.99 116

test_0728_THIRD									85.33 42	93.75 35	94.65 65	87.44 47	95.78 32	87.41 30	98.21 34	92.98 171

9.14			89.29 63		91.84 125		88.80 94	95.32 13	75.14 166	91.07 83	92.89 144	87.27 48	93.78 117	83.69 87	97.55 74

PS-CasMVS		90.06 44	91.92 16	84.47 167	96.56 6	58.83 346	89.04 89	92.74 101	91.40 6	96.12 5	96.06 29	87.23 49	95.57 41	79.42 138	98.74 6	99.00 2

GST-MVS		90.96 30	91.01 41	90.82 37	95.45 28	82.73 59	91.75 39	93.74 55	80.98 89	91.38 77	93.80 112	87.20 50	95.80 28	87.10 39	97.69 65	93.93 119

PEN-MVS		90.03 46	91.88 19	84.48 166	96.57 5	58.88 343	88.95 90	93.19 79	91.62 5	96.01 7	96.16 27	87.02 51	95.60 40	78.69 146	98.72 9	98.97 3

DTE-MVSNet		89.98 48	91.91 18	84.21 176	96.51 7	57.84 354	88.93 91	92.84 98	91.92 4	96.16 4	96.23 24	86.95 52	95.99 12	79.05 142	98.57 15	98.80 6

SF-MVS		90.27 40	90.80 47	88.68 78	92.86 91	77.09 111	91.19 45	95.74 6	81.38 84	92.28 63	93.80 112	86.89 53	94.64 81	85.52 64	97.51 78	94.30 105

MP-MVS		91.14 29	90.91 45	91.83 20	96.18 11	86.88 17	92.20 31	93.03 90	82.59 72	88.52 143	94.37 82	86.74 54	95.41 53	86.32 48	98.21 34	93.19 159
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTAPA		91.52 19	91.60 23	91.29 30	96.59 4	86.29 21	92.02 34	91.81 133	84.07 55	92.00 67	94.40 80	86.63 55	95.28 58	88.59 11	98.31 26	92.30 208

XVS		91.54 18	91.36 29	92.08 9	95.64 24	86.25 22	92.64 20	93.33 71	85.07 45	89.99 106	94.03 99	86.57 56	95.80 28	87.35 32	97.62 69	94.20 106

X-MVStestdata		85.04 138	82.70 201	92.08 9	95.64 24	86.25 22	92.64 20	93.33 71	85.07 45	89.99 106	16.05 461	86.57 56	95.80 28	87.35 32	97.62 69	94.20 106

MGCFI-Net		85.04 138	85.95 121	82.31 234	87.52 244	63.59 271	86.23 143	93.96 45	73.46 190	88.07 155	87.83 299	86.46 58	90.87 215	76.17 185	93.89 211	92.47 196

sasdasda		85.50 123	86.14 117	83.58 196	87.97 227	67.13 233	87.55 114	94.32 22	73.44 192	88.47 144	87.54 304	86.45 59	91.06 205	75.76 191	93.76 214	92.54 192

canonicalmvs		85.50 123	86.14 117	83.58 196	87.97 227	67.13 233	87.55 114	94.32 22	73.44 192	88.47 144	87.54 304	86.45 59	91.06 205	75.76 191	93.76 214	92.54 192

TranMVSNet+NR-MVSNet		87.86 84	88.76 78	85.18 146	94.02 60	64.13 265	84.38 185	91.29 148	84.88 48	92.06 66	93.84 111	86.45 59	93.73 118	73.22 230	98.66 11	97.69 9

test_0402		88.65 72	89.58 61	85.88 130	92.55 97	72.22 166	84.01 193	89.44 211	88.63 20	94.38 22	95.77 32	86.38 62	93.59 128	79.84 129	95.21 162	91.82 230

APD-MVS		89.54 57	89.63 59	89.26 65	92.57 96	81.34 68	90.19 62	93.08 86	80.87 91	91.13 82	93.19 130	86.22 63	95.97 14	82.23 106	97.18 86	90.45 275
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SD-MVS		88.96 68	89.88 54	86.22 121	91.63 129	77.07 112	89.82 70	93.77 54	78.90 116	92.88 49	92.29 168	86.11 64	90.22 235	86.24 52	97.24 84	91.36 245
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
ZD-MVS					92.22 109	80.48 71		91.85 129	71.22 233	90.38 98	92.98 139	86.06 65	96.11 7	81.99 109	96.75 97

jajsoiax		89.41 58	88.81 77	91.19 32	93.38 76	84.72 45	89.70 72	90.29 187	69.27 253	94.39 21	96.38 21	86.02 66	93.52 132	83.96 83	95.92 135	95.34 60

nrg030		87.85 85	88.49 79	85.91 128	90.07 175	69.73 201	87.86 111	94.20 31	74.04 181	92.70 57	94.66 64	85.88 67	91.50 190	79.72 131	97.32 82	96.50 34

tt0320-xc		86.67 102	88.41 81	81.44 253	93.45 72	60.44 322	83.96 195	88.50 224	87.26 29	90.90 90	97.90 3	85.61 68	86.40 320	70.14 263	98.01 45	97.47 14

SMA-MVS		90.31 39	90.48 51	89.83 55	95.31 30	79.52 83	90.98 48	93.24 78	75.37 164	92.84 52	95.28 48	85.58 69	96.09 8	87.92 18	97.76 60	93.88 122
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
tt0320		86.63 104	88.36 82	81.41 254	93.57 69	60.73 319	84.37 186	88.61 223	87.00 31	90.75 93	97.98 2	85.54 70	86.45 318	69.75 268	97.70 64	97.06 22

sc_t1		87.70 88	88.94 71	83.99 181	93.47 71	67.15 232	85.05 168	88.21 235	86.81 32	91.87 70	97.65 5	85.51 71	87.91 289	74.22 204	97.63 67	96.92 25

DeepC-MVS	82.31 4	89.15 65	89.08 67	89.37 63	93.64 68	79.07 86	88.54 101	94.20 31	73.53 189	89.71 114	94.82 60	85.09 72	95.77 34	84.17 82	98.03 43	93.26 156
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testf1		89.30 61	89.12 65	89.84 53	88.67 210	85.64 35	90.61 51	93.17 80	86.02 38	93.12 45	95.30 46	84.94 73	89.44 261	74.12 209	96.10 124	94.45 95

APD_test2		89.30 61	89.12 65	89.84 53	88.67 210	85.64 35	90.61 51	93.17 80	86.02 38	93.12 45	95.30 46	84.94 73	89.44 261	74.12 209	96.10 124	94.45 95

GeoE		85.45 127	85.81 126	84.37 168	90.08 173	67.07 235	85.86 150	91.39 145	72.33 219	87.59 171	90.25 247	84.85 75	92.37 168	78.00 158	91.94 271	93.66 134

LTVRE_ROB	86.10 1	93.04 4	93.44 4	91.82 22	93.73 66	85.72 34	96.79 1	95.51 10	88.86 16	95.63 10	96.99 13	84.81 76	93.16 145	91.10 2	97.53 77	96.58 33
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
DP-MVS		88.60 73	89.01 68	87.36 98	91.30 142	77.50 104	87.55 114	92.97 94	87.95 26	89.62 118	92.87 145	84.56 77	93.89 113	77.65 162	96.62 100	90.70 265

LS3D		90.60 35	90.34 52	91.38 28	89.03 199	84.23 49	93.58 6	94.68 18	90.65 8	90.33 100	93.95 107	84.50 78	95.37 54	80.87 118	95.50 153	94.53 92

EC-MVSNet		88.01 81	88.32 83	87.09 100	89.28 191	72.03 169	90.31 60	96.31 4	80.88 90	85.12 230	89.67 261	84.47 79	95.46 50	82.56 101	96.26 116	93.77 131

casdiffmvs_mvg		86.72 100	87.51 92	84.36 170	87.09 259	65.22 255	84.16 189	94.23 28	77.89 130	91.28 81	93.66 120	84.35 80	92.71 158	80.07 125	94.87 180	95.16 71
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
anonymousdsp		89.73 54	88.88 74	92.27 8	89.82 180	86.67 18	90.51 55	90.20 190	69.87 248	95.06 15	96.14 28	84.28 81	93.07 149	87.68 23	96.34 111	97.09 20

OMC-MVS		88.19 77	87.52 91	90.19 48	91.94 120	81.68 65	87.49 117	93.17 80	76.02 149	88.64 139	91.22 205	84.24 82	93.37 139	77.97 160	97.03 89	95.52 56

CS-MVS		88.14 78	87.67 90	89.54 61	89.56 184	79.18 85	90.47 56	94.77 17	79.37 110	84.32 254	89.33 267	83.87 83	94.53 87	82.45 102	94.89 177	94.90 76

XVG-OURS		89.18 64	88.83 76	90.23 47	94.28 49	86.11 26	85.91 147	93.60 62	80.16 98	89.13 131	93.44 124	83.82 84	90.98 207	83.86 85	95.30 161	93.60 142

XVG-ACMP-BASELINE		89.98 48	89.84 55	90.41 43	94.91 37	84.50 48	89.49 82	93.98 44	79.68 104	92.09 65	93.89 110	83.80 85	93.10 148	82.67 100	98.04 41	93.64 138

CDPH-MVS		86.17 115	85.54 133	88.05 91	92.25 107	75.45 129	83.85 200	92.01 123	65.91 299	86.19 206	91.75 187	83.77 86	94.98 69	77.43 167	96.71 98	93.73 132

test_fmvsmvis_n_1920		85.22 130	85.36 138	84.81 154	85.80 295	76.13 125	85.15 166	92.32 115	61.40 347	91.33 78	90.85 223	83.76 87	86.16 326	84.31 80	93.28 232	92.15 219

Effi-MVS+		83.90 176	84.01 173	83.57 198	87.22 252	65.61 253	86.55 137	92.40 110	78.64 121	81.34 318	84.18 361	83.65 88	92.93 154	74.22 204	87.87 350	92.17 218

MVS_111021_HR		84.63 148	84.34 167	85.49 141	90.18 171	75.86 127	79.23 304	87.13 256	73.35 194	85.56 223	89.34 266	83.60 89	90.50 227	76.64 176	94.05 208	90.09 285

UA-Net		91.49 20	91.53 25	91.39 27	94.98 35	82.95 58	93.52 7	92.79 99	88.22 23	88.53 142	97.64 6	83.45 90	94.55 86	86.02 58	98.60 13	96.67 30

AdaColmap		83.66 181	83.69 178	83.57 198	90.05 176	72.26 165	86.29 141	90.00 195	78.19 127	81.65 312	87.16 314	83.40 91	94.24 95	61.69 343	94.76 185	84.21 374

LCM-MVSNet-Re		83.48 187	85.06 143	78.75 297	85.94 293	55.75 371	80.05 288	94.27 25	76.47 144	96.09 6	94.54 71	83.31 92	89.75 256	59.95 354	94.89 177	90.75 262

test_fmvsmconf0.01_n		86.68 101	86.52 110	87.18 99	85.94 293	78.30 92	86.93 125	92.20 118	65.94 297	89.16 129	93.16 132	83.10 93	89.89 250	87.81 20	94.43 194	93.35 149

TransMVSNet (Re)		84.02 170	85.74 130	78.85 295	91.00 154	55.20 377	82.29 252	87.26 251	79.65 105	88.38 148	95.52 41	83.00 94	86.88 309	67.97 290	96.60 101	94.45 95

CNVR-MVS		87.81 86	87.68 89	88.21 86	92.87 89	77.30 110	85.25 163	91.23 152	77.31 139	87.07 183	91.47 197	82.94 95	94.71 77	84.67 77	96.27 115	92.62 186

DeepPCF-MVS	81.24 5	87.28 92	86.21 116	90.49 42	91.48 139	84.90 42	83.41 216	92.38 112	70.25 244	89.35 126	90.68 230	82.85 96	94.57 84	79.55 135	95.95 132	92.00 225

v7n		90.13 41	90.96 43	87.65 96	91.95 118	71.06 184	89.99 65	93.05 87	86.53 35	94.29 23	96.27 23	82.69 97	94.08 105	86.25 51	97.63 67	97.82 8

AllTest		87.97 83	87.40 95	89.68 56	91.59 130	83.40 52	89.50 81	95.44 11	79.47 106	88.00 158	93.03 137	82.66 98	91.47 191	70.81 252	96.14 121	94.16 110

TestCases				89.68 56	91.59 130	83.40 52		95.44 11	79.47 106	88.00 158	93.03 137	82.66 98	91.47 191	70.81 252	96.14 121	94.16 110

test_fmvsmconf0.1_n		86.18 114	85.88 124	87.08 101	85.26 307	78.25 93	85.82 151	91.82 131	65.33 311	88.55 141	92.35 167	82.62 100	89.80 252	86.87 40	94.32 198	93.18 160

RPSCF		88.00 82	86.93 105	91.22 31	90.08 173	89.30 5	89.68 74	91.11 155	79.26 111	89.68 115	94.81 63	82.44 101	87.74 294	76.54 179	88.74 336	96.61 32

SPE-MVS-test		87.00 95	86.43 112	88.71 76	89.46 187	77.46 105	89.42 85	95.73 7	77.87 132	81.64 313	87.25 312	82.43 102	94.53 87	77.65 162	96.46 107	94.14 112

ITE_SJBPF				90.11 49	90.72 160	84.97 41		90.30 185	81.56 82	90.02 105	91.20 207	82.40 103	90.81 217	73.58 223	94.66 187	94.56 89

SDMVSNet		81.90 223	83.17 191	78.10 310	88.81 207	62.45 292	76.08 356	86.05 276	73.67 186	83.41 275	93.04 135	82.35 104	80.65 378	70.06 265	95.03 170	91.21 247

test_fmvsmconf_n		85.88 120	85.51 134	86.99 104	84.77 316	78.21 94	85.40 161	91.39 145	65.32 312	87.72 169	91.81 183	82.33 105	89.78 253	86.68 42	94.20 201	92.99 169

Fast-Effi-MVS+		81.04 238	80.57 245	82.46 232	87.50 245	63.22 276	78.37 317	89.63 206	68.01 272	81.87 305	82.08 384	82.31 106	92.65 161	67.10 293	88.30 345	91.51 243

fmvsm_l_conf0.5_n_3		85.11 137	84.96 146	85.56 137	87.49 246	75.69 128	84.71 175	90.61 171	67.64 282	84.88 239	92.05 173	82.30 107	88.36 281	83.84 86	91.10 287	92.62 186

baseline		85.20 132	85.93 122	83.02 212	86.30 281	62.37 294	84.55 180	93.96 45	74.48 175	87.12 178	92.03 174	82.30 107	91.94 179	78.39 148	94.21 200	94.74 85

casdiffmvs		85.21 131	85.85 125	83.31 205	86.17 286	62.77 282	83.03 227	93.93 47	74.69 171	88.21 152	92.68 153	82.29 109	91.89 182	77.87 161	93.75 217	95.27 64
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Anonymous20231211		88.40 74	89.62 60	84.73 158	90.46 165	65.27 254	88.86 92	93.02 91	87.15 30	93.05 47	97.10 11	82.28 110	92.02 178	76.70 174	97.99 46	96.88 26

fmvsm_s_conf0.5_n_3		86.19 113	87.27 96	82.95 216	86.91 266	70.38 192	85.31 162	92.61 106	75.59 159	88.32 150	92.87 145	82.22 111	88.63 277	88.80 9	92.82 245	89.83 289

APD_test1		88.40 74	87.91 86	89.88 52	89.50 186	86.65 20	89.98 66	91.91 128	84.26 53	90.87 92	93.92 109	82.18 112	89.29 265	73.75 217	94.81 181	93.70 133

Anonymous20240529		86.20 112	87.13 98	83.42 202	90.19 170	64.55 262	84.55 180	90.71 166	85.85 40	89.94 109	95.24 50	82.13 113	90.40 231	69.19 275	96.40 110	95.31 62

CLD-MVS		83.18 193	82.64 203	84.79 155	89.05 198	67.82 229	77.93 322	92.52 108	68.33 267	85.07 233	81.54 390	82.06 114	92.96 152	69.35 271	97.91 54	93.57 144
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TEST9					92.34 104	79.70 80	83.94 196	90.32 182	65.41 310	84.49 248	90.97 214	82.03 115	93.63 123

segment_acmp												81.94 116

train_agg		85.98 117	85.28 140	88.07 90	92.34 104	79.70 80	83.94 196	90.32 182	65.79 301	84.49 248	90.97 214	81.93 117	93.63 123	81.21 114	96.54 103	90.88 259

test_8					92.09 113	78.87 88	83.82 201	90.31 184	65.79 301	84.36 252	90.96 216	81.93 117	93.44 136

test_prior2							83.37 217		75.43 162	84.58 245	91.57 191	81.92 119		79.54 136	96.97 90

EGC-MVSNET		74.79 323	69.99 367	89.19 67	94.89 38	87.00 15	91.89 38	86.28 270	1.09 462	2.23 464	95.98 30	81.87 120	89.48 257	79.76 130	95.96 130	91.10 250

CP-MVSNet		89.27 63	90.91 45	84.37 168	96.34 8	58.61 349	88.66 98	92.06 122	90.78 7	95.67 8	95.17 51	81.80 121	95.54 44	79.00 143	98.69 10	98.95 4

MVS_111021_LR		84.28 160	83.76 177	85.83 132	89.23 193	83.07 55	80.99 276	83.56 313	72.71 211	86.07 209	89.07 273	81.75 122	86.19 325	77.11 171	93.36 228	88.24 318

test_djsdf		89.62 55	89.01 68	91.45 26	92.36 103	82.98 57	91.98 35	90.08 193	71.54 227	94.28 25	96.54 19	81.57 123	94.27 92	86.26 49	96.49 105	97.09 20

cdsmvs_eth3d_5k		20.81 429	27.75 432	0.00 448	0.00 471	0.00 473	0.00 459	85.44 285	0.00 466	0.00 467	82.82 376	81.46 124	0.00 467	0.00 466	0.00 465	0.00 463

WR-MVS_H		89.91 51	91.31 34	85.71 134	96.32 9	62.39 293	89.54 80	93.31 74	90.21 12	95.57 11	95.66 37	81.42 125	95.90 17	80.94 117	98.80 3	98.84 5

CPTT-MVS		89.39 59	88.98 70	90.63 40	95.09 33	86.95 16	92.09 33	92.30 116	79.74 103	87.50 173	92.38 161	81.42 125	93.28 141	83.07 92	97.24 84	91.67 237

pm-mvs1		83.69 180	84.95 147	79.91 281	90.04 177	59.66 332	82.43 248	87.44 247	75.52 161	87.85 163	95.26 49	81.25 127	85.65 339	68.74 282	96.04 126	94.42 99

DVP-MVS++		90.07 43	91.09 37	87.00 103	91.55 135	72.64 154	96.19 2	94.10 40	85.33 42	93.49 40	94.64 68	81.12 128	95.88 18	87.41 30	95.94 133	92.48 194

OPU-MVS				88.27 85	91.89 121	77.83 100	90.47 56				91.22 205	81.12 128	94.68 78	74.48 202	95.35 156	92.29 210

sd_testset		79.95 264	81.39 230	75.64 345	88.81 207	58.07 351	76.16 355	82.81 321	73.67 186	83.41 275	93.04 135	80.96 130	77.65 394	58.62 360	95.03 170	91.21 247

NCCC		87.36 91	86.87 106	88.83 72	92.32 106	78.84 89	86.58 136	91.09 157	78.77 119	84.85 241	90.89 220	80.85 131	95.29 56	81.14 115	95.32 158	92.34 206

TAPA-MVS	77.73 12	85.71 122	84.83 149	88.37 83	88.78 209	79.72 79	87.15 122	93.50 66	69.17 254	85.80 215	89.56 262	80.76 132	92.13 174	73.21 235	95.51 152	93.25 157
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+-dtu		82.54 205	81.41 228	85.90 129	85.60 300	76.53 118	83.07 226	89.62 207	73.02 204	79.11 345	83.51 366	80.74 133	90.24 234	68.76 281	89.29 326	90.94 256

PC_three_1452									58.96 370	90.06 103	91.33 201	80.66 134	93.03 151	75.78 190	95.94 133	92.48 194

VPA-MVSNet		83.47 188	84.73 150	79.69 286	90.29 168	57.52 357	81.30 272	88.69 220	76.29 145	87.58 172	94.44 75	80.60 135	87.20 303	66.60 299	96.82 95	94.34 103

fmvsm_s_conf0.5_n_9		87.04 94	87.02 102	87.08 101	89.67 182	75.87 126	84.60 178	89.74 200	74.40 178	89.92 110	93.41 125	80.45 136	90.63 224	86.66 44	94.37 196	94.73 86

ETV-MVS		84.31 158	83.91 176	85.52 138	88.58 215	70.40 191	84.50 184	93.37 68	78.76 120	84.07 262	78.72 415	80.39 137	95.13 65	73.82 216	92.98 241	91.04 252

HPM-MVS++		88.93 69	88.45 80	90.38 44	94.92 36	85.85 31	89.70 72	91.27 151	78.20 126	86.69 193	92.28 169	80.36 138	95.06 67	86.17 53	96.49 105	90.22 279

ANet_high		83.17 194	85.68 131	75.65 344	81.24 370	45.26 432	79.94 290	92.91 95	83.83 57	91.33 78	96.88 16	80.25 139	85.92 330	68.89 279	95.89 138	95.76 48

mamv4		95.37 2	94.51 2	97.96 1	96.31 10	98.41 1	91.05 47	97.23 2	95.32 2	99.01 2	97.26 9	80.16 140	98.99 1	95.15 1	99.14 2	96.47 35

EI-MVSNet-Vis-set		85.12 136	84.53 160	86.88 106	84.01 331	72.76 151	83.91 199	85.18 290	80.44 92	88.75 136	85.49 340	80.08 141	91.92 180	82.02 108	90.85 299	95.97 44

DeepC-MVS_fast	80.27 8	86.23 110	85.65 132	87.96 92	91.30 142	76.92 113	87.19 120	91.99 124	70.56 239	84.96 236	90.69 229	80.01 142	95.14 64	78.37 149	95.78 145	91.82 230
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EI-MVSNet-UG-set		85.04 138	84.44 163	86.85 107	83.87 335	72.52 160	83.82 201	85.15 291	80.27 97	88.75 136	85.45 342	79.95 143	91.90 181	81.92 111	90.80 301	96.13 39

MCST-MVS		84.36 156	83.93 175	85.63 135	91.59 130	71.58 177	83.52 212	92.13 120	61.82 340	83.96 264	89.75 260	79.93 144	93.46 135	78.33 151	94.34 197	91.87 229

viewmanbaseed2359cas		82.95 198	83.43 183	81.52 250	85.18 309	60.03 328	81.36 269	92.38 112	69.55 251	84.84 242	91.38 199	79.85 145	90.09 244	74.22 204	92.09 266	94.43 98

TSAR-MVS + MP.		88.14 78	87.82 88	89.09 69	95.72 22	76.74 115	92.49 26	91.19 154	67.85 278	86.63 194	94.84 59	79.58 146	95.96 15	87.62 24	94.50 190	94.56 89
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_l_conf0.5_n_9		83.98 172	84.46 162	82.53 229	86.11 289	70.65 189	82.45 247	89.17 214	67.72 281	86.74 190	91.49 194	79.20 147	85.86 336	84.71 76	92.60 251	91.07 251

test12				86.57 111	90.74 159	72.63 156		90.69 167		82.76 288		79.20 147	94.80 75		95.32 158	92.27 212

CSCG		86.26 109	86.47 111	85.60 136	90.87 157	74.26 136	87.98 109	91.85 129	80.35 95	89.54 124	88.01 288	79.09 149	92.13 174	75.51 193	95.06 169	90.41 276

Test By Simon												79.09 149

PHI-MVS		86.38 108	85.81 126	88.08 89	88.44 219	77.34 108	89.35 86	93.05 87	73.15 202	84.76 243	87.70 301	78.87 151	94.18 100	80.67 122	96.29 112	92.73 178

SSM_0407		84.89 143	84.85 148	85.01 150	89.13 195	68.97 214	85.60 156	91.58 136	74.41 176	85.68 216	91.49 194	78.54 152	93.69 120	73.71 218	93.47 225	92.38 203

SSM_0404		85.16 133	85.09 142	85.36 142	90.14 172	69.52 204	86.17 144	91.58 136	74.41 176	86.55 195	91.49 194	78.54 152	93.97 109	73.71 218	93.21 235	92.59 188

EG-PatchMatch MVS		84.08 167	84.11 171	83.98 182	92.22 109	72.61 157	82.20 258	87.02 262	72.63 212	88.86 132	91.02 212	78.52 154	91.11 203	73.41 225	91.09 288	88.21 319

dcpmvs_2		84.23 163	85.14 141	81.50 251	88.61 214	61.98 301	82.90 233	93.11 83	68.66 263	92.77 55	92.39 160	78.50 155	87.63 297	76.99 173	92.30 257	94.90 76

Effi-MVS+-dtu		85.82 121	83.38 185	93.14 4	87.13 254	91.15 3	87.70 113	88.42 227	74.57 172	83.56 273	85.65 336	78.49 156	94.21 96	72.04 242	92.88 243	94.05 115

Vis-MVSNet		86.86 97	86.58 109	87.72 94	92.09 113	77.43 107	87.35 118	92.09 121	78.87 117	84.27 259	94.05 98	78.35 157	93.65 121	80.54 124	91.58 281	92.08 221
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet_NR-MVSNet		86.84 98	87.06 100	86.17 124	92.86 91	67.02 236	82.55 242	91.56 138	83.08 68	90.92 86	91.82 182	78.25 158	93.99 107	74.16 207	98.35 24	97.49 13

fmvsm_s_conf0.5_n_5		84.56 151	84.71 153	84.11 179	87.92 230	72.09 168	84.80 169	88.64 221	64.43 321	88.77 135	91.78 185	78.07 159	87.95 288	85.85 61	92.18 264	92.30 208

MSLP-MVS++		85.00 141	86.03 120	81.90 240	91.84 125	71.56 179	86.75 133	93.02 91	75.95 152	87.12 178	89.39 265	77.98 160	89.40 264	77.46 165	94.78 182	84.75 364

API-MVS		82.28 208	82.61 204	81.30 255	86.29 282	69.79 198	88.71 96	87.67 245	78.42 124	82.15 298	84.15 362	77.98 160	91.59 188	65.39 311	92.75 246	82.51 401

DP-MVS Recon		84.05 168	83.22 188	86.52 113	91.73 128	75.27 130	83.23 223	92.40 110	72.04 224	82.04 302	88.33 284	77.91 162	93.95 111	66.17 302	95.12 167	90.34 278

mmtdpeth		85.13 135	85.78 128	83.17 210	84.65 318	74.71 132	85.87 149	90.35 181	77.94 129	83.82 266	96.96 15	77.75 163	80.03 384	78.44 147	96.21 117	94.79 84

fmvsm_s_conf0.1_n_a		82.58 204	81.93 214	84.50 165	87.68 238	73.35 142	86.14 145	77.70 354	61.64 345	85.02 234	91.62 189	77.75 163	86.24 322	82.79 98	87.07 361	93.91 121

UniMVSNet (Re)		86.87 96	86.98 104	86.55 112	93.11 84	68.48 221	83.80 203	92.87 96	80.37 94	89.61 120	91.81 183	77.72 165	94.18 100	75.00 200	98.53 16	96.99 24

PCF-MVS	74.62 15	82.15 214	80.92 241	85.84 131	89.43 188	72.30 164	80.53 283	91.82 131	57.36 383	87.81 164	89.92 257	77.67 166	93.63 123	58.69 359	95.08 168	91.58 240
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
NR-MVSNet		86.00 116	86.22 115	85.34 143	93.24 81	64.56 261	82.21 256	90.46 175	80.99 88	88.42 146	91.97 175	77.56 167	93.85 114	72.46 240	98.65 12	97.61 10

3Dnovator+	83.92 2	89.97 50	89.66 58	90.92 35	91.27 144	81.66 66	91.25 43	94.13 38	88.89 15	88.83 134	94.26 86	77.55 168	95.86 23	84.88 73	95.87 139	95.24 65

MVS_Test		82.47 206	83.22 188	80.22 277	82.62 357	57.75 356	82.54 243	91.96 126	71.16 234	82.89 285	92.52 158	77.41 169	90.50 227	80.04 127	87.84 352	92.40 200

fmvsm_s_conf0.5_n_a		82.21 210	81.51 227	84.32 173	86.56 271	73.35 142	85.46 158	77.30 358	61.81 341	84.51 247	90.88 222	77.36 170	86.21 324	82.72 99	86.97 366	93.38 148

EIA-MVS		82.19 211	81.23 235	85.10 148	87.95 229	69.17 212	83.22 224	93.33 71	70.42 240	78.58 350	79.77 406	77.29 171	94.20 97	71.51 248	88.96 332	91.93 228

icg_test_0407_2		78.46 278	79.68 262	74.78 352	85.76 296	62.46 288	68.51 416	87.91 240	65.23 313	82.12 299	87.92 293	77.27 172	72.67 411	71.67 244	90.74 303	89.20 300

IMVS_0407		81.08 236	81.23 235	80.62 270	85.76 296	62.46 288	82.46 245	87.91 240	65.23 313	82.12 299	87.92 293	77.27 172	90.18 237	71.67 244	90.74 303	89.20 300

xiu_mvs_v2_base		77.19 292	76.75 297	78.52 301	87.01 263	61.30 308	75.55 363	87.12 260	61.24 352	74.45 389	78.79 414	77.20 174	90.93 210	64.62 321	84.80 395	83.32 388

DU-MVS		86.80 99	86.99 103	86.21 122	93.24 81	67.02 236	83.16 225	92.21 117	81.73 80	90.92 86	91.97 175	77.20 174	93.99 107	74.16 207	98.35 24	97.61 10

Baseline_NR-MVSNet		84.00 171	85.90 123	78.29 307	91.47 140	53.44 388	82.29 252	87.00 265	79.06 114	89.55 122	95.72 36	77.20 174	86.14 327	72.30 241	98.51 17	95.28 63

TinyColmap		81.25 233	82.34 209	77.99 313	85.33 305	60.68 320	82.32 251	88.33 230	71.26 232	86.97 185	92.22 172	77.10 177	86.98 307	62.37 335	95.17 164	86.31 347

F-COLMAP		84.97 142	83.42 184	89.63 58	92.39 102	83.40 52	88.83 93	91.92 127	73.19 201	80.18 335	89.15 271	77.04 178	93.28 141	65.82 308	92.28 260	92.21 215

114514_t		83.10 196	82.54 206	84.77 156	92.90 88	69.10 213	86.65 134	90.62 170	54.66 399	81.46 315	90.81 225	76.98 179	94.38 90	72.62 238	96.18 119	90.82 261

xiu_mvs_v1_base_debu		80.84 241	80.14 256	82.93 218	88.31 220	71.73 173	79.53 295	87.17 253	65.43 307	79.59 337	82.73 378	76.94 180	90.14 241	73.22 230	88.33 341	86.90 341

xiu_mvs_v1_base		80.84 241	80.14 256	82.93 218	88.31 220	71.73 173	79.53 295	87.17 253	65.43 307	79.59 337	82.73 378	76.94 180	90.14 241	73.22 230	88.33 341	86.90 341

xiu_mvs_v1_base_debi		80.84 241	80.14 256	82.93 218	88.31 220	71.73 173	79.53 295	87.17 253	65.43 307	79.59 337	82.73 378	76.94 180	90.14 241	73.22 230	88.33 341	86.90 341

pcd_1.5k_mvsjas		6.41 432	8.55 435	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	76.94 180	0.00 467	0.00 466	0.00 465	0.00 463

PS-MVSNAJss		88.31 76	87.90 87	89.56 60	93.31 78	77.96 99	87.94 110	91.97 125	70.73 238	94.19 26	96.67 17	76.94 180	94.57 84	83.07 92	96.28 113	96.15 38

PS-MVSNAJ		77.04 294	76.53 299	78.56 300	87.09 259	61.40 306	75.26 365	87.13 256	61.25 351	74.38 391	77.22 428	76.94 180	90.94 209	64.63 320	84.83 394	83.35 387

MIMVSNet1		83.63 182	84.59 156	80.74 265	94.06 59	62.77 282	82.72 236	84.53 305	77.57 136	90.34 99	95.92 31	76.88 186	85.83 337	61.88 341	97.42 79	93.62 140

mamba_0408		83.44 191	82.88 197	85.11 147	89.13 195	68.97 214	72.73 387	91.28 149	72.90 205	85.68 216	90.61 235	76.78 187	93.97 109	73.37 227	93.47 225	92.38 203

SSM_04072		81.44 230	82.88 197	77.10 325	89.13 195	68.97 214	72.73 387	91.28 149	72.90 205	85.68 216	90.61 235	76.78 187	69.94 421	73.37 227	93.47 225	92.38 203

原ACMM1				84.60 163	92.81 94	74.01 137		91.50 140	62.59 331	82.73 289	90.67 232	76.53 189	94.25 94	69.24 272	95.69 148	85.55 355

fmvsm_s_conf0.1_n		82.17 212	81.59 222	83.94 185	86.87 269	71.57 178	85.19 165	77.42 357	62.27 339	84.47 250	91.33 201	76.43 190	85.91 332	83.14 89	87.14 359	94.33 104

fmvsm_s_conf0.5_n		81.91 222	81.30 232	83.75 190	86.02 291	71.56 179	84.73 174	77.11 361	62.44 336	84.00 263	90.68 230	76.42 191	85.89 334	83.14 89	87.11 360	93.81 129

MSDG		80.06 262	79.99 261	80.25 276	83.91 334	68.04 227	77.51 330	89.19 213	77.65 134	81.94 303	83.45 368	76.37 192	86.31 321	63.31 331	86.59 369	86.41 345

Gipuma		84.44 154	86.33 113	78.78 296	84.20 328	73.57 140	89.55 78	90.44 176	84.24 54	84.38 251	94.89 57	76.35 193	80.40 381	76.14 186	96.80 96	82.36 402
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
IMVS_0403		80.93 240	81.00 238	80.72 267	85.76 296	62.46 288	81.82 260	87.91 240	65.23 313	82.07 301	87.92 293	75.91 194	90.50 227	71.67 244	90.74 303	89.20 300

test_fmvsm_n_1920		83.60 184	82.89 196	85.74 133	85.22 308	77.74 102	84.12 191	90.48 173	59.87 367	86.45 204	91.12 209	75.65 195	85.89 334	82.28 105	90.87 297	93.58 143

XXY-MVS		74.44 327	76.19 302	69.21 393	84.61 319	52.43 396	71.70 394	77.18 360	60.73 358	80.60 325	90.96 216	75.44 196	69.35 424	56.13 374	88.33 341	85.86 352

FMVSNet1		84.55 152	85.45 135	81.85 242	90.27 169	61.05 312	86.83 129	88.27 232	78.57 122	89.66 117	95.64 38	75.43 197	90.68 221	69.09 276	95.33 157	93.82 126

CANet		83.79 179	82.85 199	86.63 110	86.17 286	72.21 167	83.76 204	91.43 142	77.24 140	74.39 390	87.45 308	75.36 198	95.42 52	77.03 172	92.83 244	92.25 214

ab-mvs		79.67 265	80.56 246	76.99 326	88.48 217	56.93 361	84.70 176	86.06 275	68.95 258	80.78 324	93.08 134	75.30 199	84.62 347	56.78 369	90.90 295	89.43 295

patch_mono-2		78.89 269	79.39 265	77.41 322	84.78 315	68.11 225	75.60 360	83.11 317	60.96 355	79.36 341	89.89 258	75.18 200	72.97 410	73.32 229	92.30 257	91.15 249

DELS-MVS		81.44 230	81.25 233	82.03 237	84.27 327	62.87 280	76.47 350	92.49 109	70.97 236	81.64 313	83.83 363	75.03 201	92.70 159	74.29 203	92.22 263	90.51 274
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
PAPR		78.84 271	78.10 283	81.07 260	85.17 310	60.22 324	82.21 256	90.57 172	62.51 332	75.32 383	84.61 356	74.99 202	92.30 171	59.48 357	88.04 347	90.68 266

fmvsm_s_conf0.5_n_4		84.38 155	84.27 168	84.74 157	87.25 250	70.84 186	83.55 211	88.45 226	68.64 264	86.29 205	91.31 203	74.97 203	88.42 279	87.87 19	90.07 316	94.95 75

CNLPA		83.55 186	83.10 193	84.90 151	89.34 190	83.87 50	84.54 182	88.77 218	79.09 113	83.54 274	88.66 281	74.87 204	81.73 371	66.84 296	92.29 259	89.11 305

HQP_MVS		87.75 87	87.43 94	88.70 77	93.45 72	76.42 119	89.45 83	93.61 60	79.44 108	86.55 195	92.95 142	74.84 205	95.22 59	80.78 120	95.83 141	94.46 93

plane_prior6					92.61 95	76.54 116						74.84 205

FC-MVSNet-test		85.93 119	87.05 101	82.58 226	92.25 107	56.44 365	85.75 152	93.09 85	77.33 138	91.94 69	94.65 65	74.78 207	93.41 138	75.11 199	98.58 14	97.88 7

VDD-MVS		84.23 163	84.58 157	83.20 208	91.17 150	65.16 257	83.25 221	84.97 298	79.79 102	87.18 177	94.27 83	74.77 208	90.89 213	69.24 272	96.54 103	93.55 147

BH-untuned		80.96 239	80.99 239	80.84 264	88.55 216	68.23 222	80.33 286	88.46 225	72.79 210	86.55 195	86.76 320	74.72 209	91.77 186	61.79 342	88.99 331	82.52 400

diffmvs_AUTHOR		81.24 234	81.55 225	80.30 275	80.61 381	60.22 324	77.98 321	90.48 173	67.77 280	83.34 277	89.50 264	74.69 210	87.42 299	78.78 145	90.81 300	93.27 154

VPNet		80.25 256	81.68 217	75.94 341	92.46 100	47.98 419	76.70 343	81.67 332	73.45 191	84.87 240	92.82 147	74.66 211	86.51 316	61.66 344	96.85 92	93.33 150

viewmambaseed2359dif		78.80 272	78.47 279	79.78 282	80.26 385	59.28 336	77.31 335	87.13 256	60.42 361	82.37 293	88.67 280	74.58 212	87.87 292	67.78 292	87.73 353	92.19 216

tfpnnormal		81.79 224	82.95 195	78.31 305	88.93 203	55.40 373	80.83 280	82.85 320	76.81 142	85.90 214	94.14 93	74.58 212	86.51 316	66.82 297	95.68 149	93.01 168

KD-MVS_self_test		81.93 221	83.14 192	78.30 306	84.75 317	52.75 392	80.37 285	89.42 212	70.24 245	90.26 101	93.39 126	74.55 214	86.77 312	68.61 284	96.64 99	95.38 59

fmvsm_l_conf0.5_n		82.06 216	81.54 226	83.60 195	83.94 332	73.90 138	83.35 218	86.10 273	58.97 369	83.80 267	90.36 241	74.23 215	86.94 308	82.90 95	90.22 314	89.94 287

fmvsm_s_conf0.5_n_7		82.04 217	82.05 212	82.01 238	86.98 265	71.07 183	78.70 311	89.45 210	68.07 271	78.14 352	91.61 190	74.19 216	85.92 330	79.61 134	91.73 276	89.05 309

V42		83.47 188	83.37 186	83.75 190	83.16 352	63.33 274	81.31 270	90.23 189	69.51 252	90.91 88	90.81 225	74.16 217	92.29 172	80.06 126	90.22 314	95.62 54

Elysia		88.71 70	88.89 72	88.19 87	91.26 145	72.96 148	88.10 106	93.59 63	84.31 51	90.42 96	94.10 96	74.07 218	94.82 73	88.19 14	95.92 135	96.80 27

StellarMVS		88.71 70	88.89 72	88.19 87	91.26 145	72.96 148	88.10 106	93.59 63	84.31 51	90.42 96	94.10 96	74.07 218	94.82 73	88.19 14	95.92 135	96.80 27

3Dnovator	80.37 7	84.80 144	84.71 153	85.06 149	86.36 279	74.71 132	88.77 95	90.00 195	75.65 157	84.96 236	93.17 131	74.06 220	91.19 200	78.28 152	91.09 288	89.29 299

v10		86.54 105	87.10 99	84.84 152	88.16 225	63.28 275	86.64 135	92.20 118	75.42 163	92.81 54	94.50 72	74.05 221	94.06 106	83.88 84	96.28 113	97.17 19

fmvsm_s_conf0.5_n_8		85.48 125	85.75 129	84.68 161	87.10 257	69.98 197	84.28 187	92.68 102	74.77 169	87.90 162	92.36 166	73.94 222	90.41 230	85.95 60	92.74 247	93.66 134

旧先验1					91.97 117	71.77 171		81.78 330			91.84 180	73.92 223			93.65 221	83.61 382

mvs_anonymous		78.13 281	78.76 273	76.23 340	79.24 396	50.31 411	78.69 312	84.82 301	61.60 346	83.09 283	92.82 147	73.89 224	87.01 304	68.33 288	86.41 371	91.37 244

MAR-MVS		80.24 257	78.74 274	84.73 158	86.87 269	78.18 95	85.75 152	87.81 244	65.67 306	77.84 356	78.50 416	73.79 225	90.53 226	61.59 345	90.87 297	85.49 357
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
KinetiMVS		85.95 118	86.10 119	85.50 140	87.56 243	69.78 199	83.70 206	89.83 199	80.42 93	87.76 167	93.24 129	73.76 226	91.54 189	85.03 71	93.62 223	95.19 68

VDDNet		84.35 157	85.39 137	81.25 256	95.13 32	59.32 335	85.42 160	81.11 336	86.41 36	87.41 174	96.21 25	73.61 227	90.61 225	66.33 301	96.85 92	93.81 129

FIs		85.35 129	86.27 114	82.60 225	91.86 122	57.31 358	85.10 167	93.05 87	75.83 154	91.02 85	93.97 102	73.57 228	92.91 156	73.97 213	98.02 44	97.58 12

v1144		84.54 153	84.72 152	84.00 180	87.67 239	62.55 286	82.97 230	90.93 162	70.32 243	89.80 112	90.99 213	73.50 229	93.48 134	81.69 113	94.65 188	95.97 44

diffmvs		80.40 251	80.48 249	80.17 278	79.02 399	60.04 326	77.54 329	90.28 188	66.65 295	82.40 292	87.33 311	73.50 229	87.35 301	77.98 159	89.62 323	93.13 161
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PAPM_NR		83.23 192	83.19 190	83.33 204	90.90 156	65.98 249	88.19 104	90.78 165	78.13 128	80.87 323	87.92 293	73.49 231	92.42 165	70.07 264	88.40 339	91.60 239

v8		86.22 111	86.83 107	84.36 170	87.82 233	62.35 295	86.42 139	91.33 147	76.78 143	92.73 56	94.48 74	73.41 232	93.72 119	83.10 91	95.41 154	97.01 23

EI-MVSNet		82.61 202	82.42 208	83.20 208	83.25 349	63.66 269	83.50 213	85.07 292	76.06 147	86.55 195	85.10 348	73.41 232	90.25 232	78.15 157	90.67 308	95.68 52

IterMVS-LS		84.73 147	84.98 145	83.96 183	87.35 248	63.66 269	83.25 221	89.88 198	76.06 147	89.62 118	92.37 164	73.40 234	92.52 163	78.16 155	94.77 184	95.69 51
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MM		87.64 89	87.15 97	89.09 69	89.51 185	76.39 121	88.68 97	86.76 266	84.54 50	83.58 272	93.78 114	73.36 235	96.48 2	87.98 17	96.21 117	94.41 100

v144192		84.24 162	84.41 164	83.71 192	87.59 242	61.57 304	82.95 231	91.03 158	67.82 279	89.80 112	90.49 239	73.28 236	93.51 133	81.88 112	94.89 177	96.04 43

BH-RMVSNet		80.53 246	80.22 254	81.49 252	87.19 253	66.21 246	77.79 325	86.23 271	74.21 180	83.69 269	88.50 282	73.25 237	90.75 218	63.18 332	87.90 349	87.52 333

PLC	73.85 16	82.09 215	80.31 250	87.45 97	90.86 158	80.29 75	85.88 148	90.65 168	68.17 270	76.32 369	86.33 326	73.12 238	92.61 162	61.40 346	90.02 318	89.44 294
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
fmvsm_s_conf0.5_n_6		84.05 168	84.14 170	83.81 186	87.75 235	71.17 182	83.42 215	91.10 156	67.90 277	84.53 246	90.70 228	73.01 239	88.73 275	85.09 68	93.72 219	91.53 242

OurMVSNet-221017-0		90.01 47	89.74 57	90.83 36	93.16 83	80.37 74	91.91 37	93.11 83	81.10 87	95.32 14	97.24 10	72.94 240	94.85 72	85.07 69	97.78 59	97.26 16

WR-MVS		83.56 185	84.40 165	81.06 261	93.43 75	54.88 378	78.67 313	85.02 295	81.24 85	90.74 94	91.56 192	72.85 241	91.08 204	68.00 289	98.04 41	97.23 17

VNet		79.31 266	80.27 251	76.44 335	87.92 230	53.95 384	75.58 362	84.35 307	74.39 179	82.23 296	90.72 227	72.84 242	84.39 352	60.38 352	93.98 209	90.97 255

QAPM		82.59 203	82.59 205	82.58 226	86.44 273	66.69 240	89.94 68	90.36 180	67.97 274	84.94 238	92.58 156	72.71 243	92.18 173	70.63 258	87.73 353	88.85 313

v1192		84.57 150	84.69 155	84.21 176	87.75 235	62.88 279	83.02 228	91.43 142	69.08 256	89.98 108	90.89 220	72.70 244	93.62 126	82.41 103	94.97 174	96.13 39

OpenMVS	76.72 13	81.98 220	82.00 213	81.93 239	84.42 323	68.22 223	88.50 102	89.48 209	66.92 292	81.80 309	91.86 178	72.59 245	90.16 238	71.19 251	91.25 286	87.40 335

TSAR-MVS + GP.		83.95 173	82.69 202	87.72 94	89.27 192	81.45 67	83.72 205	81.58 334	74.73 170	85.66 219	86.06 331	72.56 246	92.69 160	75.44 195	95.21 162	89.01 312

alignmvs		83.94 174	83.98 174	83.80 187	87.80 234	67.88 228	84.54 182	91.42 144	73.27 200	88.41 147	87.96 289	72.33 247	90.83 216	76.02 188	94.11 204	92.69 182

fmvsm_l_conf0.5_n_a		81.46 229	80.87 242	83.25 206	83.73 337	73.21 147	83.00 229	85.59 284	58.22 375	82.96 284	90.09 254	72.30 248	86.65 314	81.97 110	89.95 319	89.88 288

MVSMamba_PlusPlus		87.53 90	88.86 75	83.54 200	92.03 116	62.26 297	91.49 41	92.62 105	88.07 25	88.07 155	96.17 26	72.24 249	95.79 31	84.85 74	94.16 203	92.58 189

HQP2-MVS												72.10 250

HQP-MVS		84.61 149	84.06 172	86.27 118	91.19 147	70.66 187	84.77 170	92.68 102	73.30 197	80.55 327	90.17 252	72.10 250	94.61 82	77.30 169	94.47 192	93.56 145

testgi		72.36 344	74.61 316	65.59 415	80.56 382	42.82 440	68.29 417	73.35 389	66.87 293	81.84 306	89.93 256	72.08 252	66.92 438	46.05 432	92.54 252	87.01 340

v1921920		84.23 163	84.37 166	83.79 188	87.64 241	61.71 303	82.91 232	91.20 153	67.94 275	90.06 103	90.34 242	72.04 253	93.59 128	82.32 104	94.91 175	96.07 41

MSP-MVS		89.08 67	88.16 84	91.83 20	95.76 18	86.14 25	92.75 17	93.90 49	78.43 123	89.16 129	92.25 170	72.03 254	96.36 4	88.21 13	90.93 294	92.98 171
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
SD_0403		76.08 307	76.77 296	73.98 356	87.08 261	49.45 414	83.62 209	84.68 304	63.31 325	75.13 386	87.47 307	71.85 255	84.56 348	49.97 410	87.86 351	87.94 327

LF4IMVS		82.75 201	81.93 214	85.19 145	82.08 359	80.15 76	85.53 157	88.76 219	68.01 272	85.58 222	87.75 300	71.80 256	86.85 310	74.02 212	93.87 212	88.58 315

fmvsm_s_conf0.5_n_2		83.62 183	83.29 187	84.62 162	85.43 304	70.18 196	80.61 282	87.24 252	67.14 289	87.79 165	91.87 177	71.79 257	87.98 287	86.00 59	91.77 275	95.71 50

v1240		84.30 159	84.51 161	83.65 193	87.65 240	61.26 309	82.85 234	91.54 139	67.94 275	90.68 95	90.65 233	71.71 258	93.64 122	82.84 97	94.78 182	96.07 41

ambc				82.98 214	90.55 164	64.86 258	88.20 103	89.15 215		89.40 125	93.96 105	71.67 259	91.38 197	78.83 144	96.55 102	92.71 181

fmvsm_s_conf0.1_n_2		83.82 177	83.49 181	84.84 152	85.99 292	70.19 195	80.93 277	87.58 246	67.26 288	87.94 161	92.37 164	71.40 260	88.01 285	86.03 55	91.87 272	96.31 36

新几何1				82.95 216	93.96 61	78.56 91		80.24 342	55.45 393	83.93 265	91.08 211	71.19 261	88.33 282	65.84 307	93.07 238	81.95 407

SSC-MVS		77.55 287	81.64 219	65.29 418	90.46 165	20.33 465	73.56 380	68.28 419	85.44 41	88.18 154	94.64 68	70.93 262	81.33 373	71.25 249	92.03 267	94.20 106

v148		82.31 207	82.48 207	81.81 245	85.59 301	59.66 332	81.47 267	86.02 277	72.85 207	88.05 157	90.65 233	70.73 263	90.91 212	75.15 198	91.79 273	94.87 78

v2v482		84.09 166	84.24 169	83.62 194	87.13 254	61.40 306	82.71 237	89.71 203	72.19 222	89.55 122	91.41 198	70.70 264	93.20 143	81.02 116	93.76 214	96.25 37

SSC-MVS3.2		73.90 331	75.67 308	68.61 401	84.11 330	41.28 443	64.17 434	72.83 393	72.09 223	79.08 346	87.94 290	70.31 265	73.89 409	55.99 375	94.49 191	90.67 268

MVS_0304		85.37 128	84.58 157	87.75 93	85.28 306	73.36 141	86.54 138	85.71 281	77.56 137	81.78 311	92.47 159	70.29 266	96.02 11	85.59 63	95.96 130	93.87 123

WB-MVS		76.06 308	80.01 260	64.19 421	89.96 179	20.58 464	72.18 391	68.19 420	83.21 65	86.46 203	93.49 123	70.19 267	78.97 389	65.96 303	90.46 313	93.02 167

balanced_conf03		84.80 144	85.40 136	83.00 213	88.95 202	61.44 305	90.42 59	92.37 114	71.48 229	88.72 138	93.13 133	70.16 268	95.15 63	79.26 140	94.11 204	92.41 198

UGNet		82.78 200	81.64 219	86.21 122	86.20 285	76.24 123	86.86 127	85.68 282	77.07 141	73.76 394	92.82 147	69.64 269	91.82 185	69.04 278	93.69 220	90.56 272
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
c3_l		81.64 226	81.59 222	81.79 246	80.86 376	59.15 340	78.61 314	90.18 191	68.36 266	87.20 176	87.11 316	69.39 270	91.62 187	78.16 155	94.43 194	94.60 88

MG-MVS		80.32 254	80.94 240	78.47 303	88.18 223	52.62 395	82.29 252	85.01 296	72.01 225	79.24 344	92.54 157	69.36 271	93.36 140	70.65 257	89.19 329	89.45 293

IS-MVSNet		86.66 103	86.82 108	86.17 124	92.05 115	66.87 239	91.21 44	88.64 221	86.30 37	89.60 121	92.59 154	69.22 272	94.91 71	73.89 214	97.89 55	96.72 29

PVSNet_BlendedMVS		78.80 272	77.84 284	81.65 248	84.43 321	63.41 272	79.49 298	90.44 176	61.70 344	75.43 380	87.07 317	69.11 273	91.44 193	60.68 350	92.24 261	90.11 284

PVSNet_Blended		76.49 303	75.40 310	79.76 284	84.43 321	63.41 272	75.14 366	90.44 176	57.36 383	75.43 380	78.30 417	69.11 273	91.44 193	60.68 350	87.70 355	84.42 369

BH-w/o		76.57 301	76.07 304	78.10 310	86.88 268	65.92 250	77.63 327	86.33 269	65.69 305	80.89 322	79.95 403	68.97 275	90.74 219	53.01 398	85.25 383	77.62 431

MVS		73.21 338	72.59 340	75.06 349	80.97 373	60.81 318	81.64 264	85.92 279	46.03 437	71.68 405	77.54 423	68.47 276	89.77 254	55.70 378	85.39 380	74.60 437

miper_ehance_all_eth		80.34 253	80.04 259	81.24 258	79.82 389	58.95 342	77.66 326	89.66 204	65.75 304	85.99 213	85.11 347	68.29 277	91.42 195	76.03 187	92.03 267	93.33 150

Anonymous202405211		80.51 247	81.19 237	78.49 302	88.48 217	57.26 359	76.63 345	82.49 323	81.21 86	84.30 257	92.24 171	67.99 278	86.24 322	62.22 336	95.13 165	91.98 227

testdata				79.54 289	92.87 89	72.34 163		80.14 343	59.91 366	85.47 225	91.75 187	67.96 279	85.24 341	68.57 286	92.18 264	81.06 420

IMVS_0404		77.24 291	77.75 286	75.73 343	85.76 296	62.46 288	70.84 402	87.91 240	65.23 313	72.21 402	87.92 293	67.48 280	75.53 403	71.67 244	90.74 303	89.20 300

DPM-MVS		80.10 261	79.18 267	82.88 221	90.71 161	69.74 200	78.87 309	90.84 163	60.29 363	75.64 379	85.92 334	67.28 281	93.11 147	71.24 250	91.79 273	85.77 353

PVSNet_Blended_VisFu		81.55 228	80.49 248	84.70 160	91.58 133	73.24 146	84.21 188	91.67 135	62.86 330	80.94 321	87.16 314	67.27 282	92.87 157	69.82 267	88.94 333	87.99 325

MDA-MVSNet-bldmvs		77.47 288	76.90 295	79.16 293	79.03 398	64.59 259	66.58 428	75.67 371	73.15 202	88.86 132	88.99 274	66.94 283	81.23 374	64.71 318	88.22 346	91.64 238

CL-MVSNet_self_test		76.81 297	77.38 289	75.12 348	86.90 267	51.34 403	73.20 384	80.63 341	68.30 268	81.80 309	88.40 283	66.92 284	80.90 375	55.35 382	94.90 176	93.12 163

test222					93.31 78	76.54 116	79.38 299	77.79 353	52.59 410	82.36 294	90.84 224	66.83 285			91.69 277	81.25 415

TR-MVS		76.77 298	75.79 305	79.72 285	86.10 290	65.79 251	77.14 336	83.02 318	65.20 317	81.40 316	82.10 382	66.30 286	90.73 220	55.57 379	85.27 382	82.65 395

OpenMVS_ROB	70.19 17	77.77 286	77.46 287	78.71 298	84.39 324	61.15 310	81.18 274	82.52 322	62.45 335	83.34 277	87.37 309	66.20 287	88.66 276	64.69 319	85.02 388	86.32 346

NormalMVS		86.47 107	85.32 139	89.94 51	94.43 44	80.42 72	88.63 99	93.59 63	74.56 173	85.12 230	90.34 242	66.19 288	94.20 97	76.57 177	98.44 20	95.19 68

SymmetryMVS		84.79 146	83.54 179	88.55 79	92.44 101	80.42 72	88.63 99	82.37 325	74.56 173	85.12 230	90.34 242	66.19 288	94.20 97	76.57 177	95.68 149	91.03 253

EPP-MVSNet		85.47 126	85.04 144	86.77 109	91.52 138	69.37 206	91.63 40	87.98 239	81.51 83	87.05 184	91.83 181	66.18 290	95.29 56	70.75 255	96.89 91	95.64 53

SixPastTwentyTwo		87.20 93	87.45 93	86.45 114	92.52 98	69.19 211	87.84 112	88.05 236	81.66 81	94.64 18	96.53 20	65.94 291	94.75 76	83.02 94	96.83 94	95.41 58

PatchMatch-RL		74.48 325	73.22 332	78.27 308	87.70 237	85.26 38	75.92 358	70.09 411	64.34 322	76.09 373	81.25 392	65.87 292	78.07 393	53.86 390	83.82 401	71.48 440

AstraMVS		81.67 225	81.40 229	82.48 231	87.06 262	66.47 243	81.41 268	81.68 331	68.78 260	88.00 158	90.95 218	65.70 293	87.86 293	76.66 175	92.38 255	93.12 163

WB-MVSnew		68.72 382	69.01 375	67.85 403	83.22 351	43.98 436	74.93 368	65.98 431	55.09 394	73.83 393	79.11 409	65.63 294	71.89 415	38.21 449	85.04 387	87.69 332

EPNet		80.37 252	78.41 280	86.23 119	76.75 413	73.28 144	87.18 121	77.45 356	76.24 146	68.14 424	88.93 275	65.41 295	93.85 114	69.47 270	96.12 123	91.55 241
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
guyue		81.57 227	81.37 231	82.15 235	86.39 274	66.13 247	81.54 266	83.21 315	69.79 249	87.77 166	89.95 255	65.36 296	87.64 296	75.88 189	92.49 253	92.67 183

FA-MVS(test-final)		83.13 195	83.02 194	83.43 201	86.16 288	66.08 248	88.00 108	88.36 229	75.55 160	85.02 234	92.75 151	65.12 297	92.50 164	74.94 201	91.30 285	91.72 234

PM-MVS		80.20 258	79.00 268	83.78 189	88.17 224	86.66 19	81.31 270	66.81 429	69.64 250	88.33 149	90.19 249	64.58 298	83.63 360	71.99 243	90.03 317	81.06 420

miper_enhance_ethall		77.83 283	76.93 294	80.51 271	76.15 420	58.01 353	75.47 364	88.82 217	58.05 377	83.59 271	80.69 394	64.41 299	91.20 199	73.16 236	92.03 267	92.33 207

eth_miper_zixun_eth		80.84 241	80.22 254	82.71 223	81.41 368	60.98 315	77.81 324	90.14 192	67.31 287	86.95 186	87.24 313	64.26 300	92.31 170	75.23 197	91.61 279	94.85 82

test20.03		73.75 333	74.59 318	71.22 379	81.11 372	51.12 407	70.15 408	72.10 400	70.42 240	80.28 333	91.50 193	64.21 301	74.72 407	46.96 428	94.58 189	87.82 331

mvs5depth		83.82 177	84.54 159	81.68 247	82.23 358	68.65 219	86.89 126	89.90 197	80.02 101	87.74 168	97.86 4	64.19 302	82.02 369	76.37 181	95.63 151	94.35 102

LuminaMVS		83.94 174	83.51 180	85.23 144	89.78 181	71.74 172	84.76 173	87.27 250	72.60 213	89.31 127	90.60 237	64.04 303	90.95 208	79.08 141	94.11 204	92.99 169

VortexMVS		80.51 247	80.63 244	80.15 279	83.36 345	61.82 302	80.63 281	88.00 238	67.11 290	87.23 175	89.10 272	63.98 304	88.00 286	73.63 222	92.63 250	90.64 270

cascas		76.29 306	74.81 315	80.72 267	84.47 320	62.94 278	73.89 378	87.34 248	55.94 390	75.16 385	76.53 433	63.97 305	91.16 201	65.00 315	90.97 293	88.06 323

TAMVS		78.08 282	76.36 300	83.23 207	90.62 162	72.87 150	79.08 305	80.01 344	61.72 343	81.35 317	86.92 319	63.96 306	88.78 273	50.61 408	93.01 240	88.04 324

GBi-Net		82.02 218	82.07 210	81.85 242	86.38 276	61.05 312	86.83 129	88.27 232	72.43 214	86.00 210	95.64 38	63.78 307	90.68 221	65.95 304	93.34 229	93.82 126

test1		82.02 218	82.07 210	81.85 242	86.38 276	61.05 312	86.83 129	88.27 232	72.43 214	86.00 210	95.64 38	63.78 307	90.68 221	65.95 304	93.34 229	93.82 126

FMVSNet2		81.31 232	81.61 221	80.41 273	86.38 276	58.75 347	83.93 198	86.58 268	72.43 214	87.65 170	92.98 139	63.78 307	90.22 235	66.86 294	93.92 210	92.27 212

USDC		76.63 300	76.73 298	76.34 337	83.46 340	57.20 360	80.02 289	88.04 237	52.14 415	83.65 270	91.25 204	63.24 310	86.65 314	54.66 387	94.11 204	85.17 359

RRT-MVS		82.97 197	83.44 182	81.57 249	85.06 311	58.04 352	87.20 119	90.37 179	77.88 131	88.59 140	93.70 119	63.17 311	93.05 150	76.49 180	88.47 338	93.62 140

DIV-MVS_self_test		80.43 249	80.23 252	81.02 262	79.99 386	59.25 337	77.07 338	87.02 262	67.38 284	86.19 206	89.22 268	63.09 312	90.16 238	76.32 182	95.80 143	93.66 134

cl____		80.42 250	80.23 252	81.02 262	79.99 386	59.25 337	77.07 338	87.02 262	67.37 285	86.18 208	89.21 269	63.08 313	90.16 238	76.31 183	95.80 143	93.65 137

h-mvs33		84.25 161	82.76 200	88.72 75	91.82 127	82.60 60	84.00 194	84.98 297	71.27 230	86.70 191	90.55 238	63.04 314	93.92 112	78.26 153	94.20 201	89.63 291

hse-mvs2		83.47 188	81.81 216	88.47 80	91.03 153	82.27 61	82.61 238	83.69 311	71.27 230	86.70 191	86.05 332	63.04 314	92.41 166	78.26 153	93.62 223	90.71 264

new-patchmatchnet		70.10 366	73.37 330	60.29 432	81.23 371	16.95 467	59.54 443	74.62 376	62.93 329	80.97 319	87.93 292	62.83 316	71.90 414	55.24 383	95.01 173	92.00 225

K. test v3		85.14 134	84.73 150	86.37 115	91.13 151	69.63 203	85.45 159	76.68 365	84.06 56	92.44 61	96.99 13	62.03 317	94.65 80	80.58 123	93.24 233	94.83 83

lessismore_v0				85.95 127	91.10 152	70.99 185		70.91 409		91.79 71	94.42 78	61.76 318	92.93 154	79.52 137	93.03 239	93.93 119

1314		73.22 337	72.56 342	75.20 347	80.41 384	57.84 354	81.64 264	85.36 286	51.68 418	73.10 397	76.65 432	61.45 319	85.19 342	63.54 328	79.21 429	82.59 396

Syy-MVS		69.40 376	70.03 366	67.49 406	81.72 363	38.94 448	71.00 399	61.99 440	61.38 348	70.81 410	72.36 444	61.37 320	79.30 386	64.50 323	85.18 384	84.22 372

CANet_DTU		77.81 285	77.05 292	80.09 280	81.37 369	59.90 330	83.26 220	88.29 231	69.16 255	67.83 427	83.72 364	60.93 321	89.47 258	69.22 274	89.70 322	90.88 259

pmmvs-eth3d		78.42 280	77.04 293	82.57 228	87.44 247	74.41 135	80.86 279	79.67 345	55.68 392	84.69 244	90.31 246	60.91 322	85.42 340	62.20 337	91.59 280	87.88 329

UnsupCasMVSNet_eth		71.63 352	72.30 344	69.62 390	76.47 417	52.70 394	70.03 409	80.97 338	59.18 368	79.36 341	88.21 286	60.50 323	69.12 425	58.33 363	77.62 436	87.04 339

IterMVS-SCA-FT		80.64 245	79.41 264	84.34 172	83.93 333	69.66 202	76.28 352	81.09 337	72.43 214	86.47 202	90.19 249	60.46 324	93.15 146	77.45 166	86.39 372	90.22 279

SCA		73.32 335	72.57 341	75.58 346	81.62 365	55.86 369	78.89 308	71.37 406	61.73 342	74.93 387	83.42 369	60.46 324	87.01 304	58.11 365	82.63 413	83.88 376

jason		77.42 289	75.75 306	82.43 233	87.10 257	69.27 207	77.99 320	81.94 329	51.47 419	77.84 356	85.07 351	60.32 326	89.00 267	70.74 256	89.27 328	89.03 310
jason: jason.
1112_ss		74.82 322	73.74 324	78.04 312	89.57 183	60.04 326	76.49 349	87.09 261	54.31 400	73.66 395	79.80 404	60.25 327	86.76 313	58.37 361	84.15 399	87.32 336

HY-MVS	64.64 18	73.03 339	72.47 343	74.71 353	83.36 345	54.19 382	82.14 259	81.96 328	56.76 389	69.57 419	86.21 330	60.03 328	84.83 346	49.58 415	82.65 411	85.11 360

Anonymous20231206		71.38 355	71.88 346	69.88 387	86.31 280	54.37 380	70.39 406	74.62 376	52.57 411	76.73 365	88.76 276	59.94 329	72.06 413	44.35 436	93.23 234	83.23 390

IterMVS		76.91 295	76.34 301	78.64 299	80.91 374	64.03 266	76.30 351	79.03 348	64.88 319	83.11 281	89.16 270	59.90 330	84.46 350	68.61 284	85.15 386	87.42 334
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
YYNet1		70.06 367	70.44 360	68.90 395	73.76 435	53.42 389	58.99 446	67.20 425	58.42 373	87.10 180	85.39 344	59.82 331	67.32 435	59.79 355	83.50 404	85.96 349

MDA-MVSNet_test_wron		70.05 368	70.44 360	68.88 396	73.84 434	53.47 387	58.93 447	67.28 424	58.43 372	87.09 181	85.40 343	59.80 332	67.25 436	59.66 356	83.54 403	85.92 351

PMMVS		61.65 411	60.38 418	65.47 417	65.40 461	69.26 208	63.97 435	61.73 444	36.80 458	60.11 450	68.43 449	59.42 333	66.35 440	48.97 418	78.57 432	60.81 451

CDS-MVSNet		77.32 290	75.40 310	83.06 211	89.00 200	72.48 161	77.90 323	82.17 327	60.81 356	78.94 347	83.49 367	59.30 334	88.76 274	54.64 388	92.37 256	87.93 328
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
UnsupCasMVSNet_bld		69.21 378	69.68 369	67.82 404	79.42 393	51.15 406	67.82 421	75.79 369	54.15 401	77.47 363	85.36 346	59.26 335	70.64 419	48.46 421	79.35 427	81.66 409

Anonymous20240521		80.18 259	81.25 233	76.95 327	83.15 353	60.84 317	82.46 245	85.99 278	68.76 261	86.78 187	93.73 118	59.13 336	77.44 395	73.71 218	97.55 74	92.56 190

WTY-MVS		67.91 385	68.35 382	66.58 411	80.82 377	48.12 418	65.96 429	72.60 394	53.67 403	71.20 407	81.68 389	58.97 337	69.06 426	48.57 420	81.67 415	82.55 398

cl22		78.97 268	78.21 282	81.24 258	77.74 403	59.01 341	77.46 333	87.13 256	65.79 301	84.32 254	85.10 348	58.96 338	90.88 214	75.36 196	92.03 267	93.84 124

MVSFormer		82.23 209	81.57 224	84.19 178	85.54 302	69.26 208	91.98 35	90.08 193	71.54 227	76.23 370	85.07 351	58.69 339	94.27 92	86.26 49	88.77 334	89.03 310

lupinMVS		76.37 305	74.46 319	82.09 236	85.54 302	69.26 208	76.79 341	80.77 340	50.68 426	76.23 370	82.82 376	58.69 339	88.94 268	69.85 266	88.77 334	88.07 321

Test_1112_low_res		73.90 331	73.08 333	76.35 336	90.35 167	55.95 366	73.40 383	86.17 272	50.70 425	73.14 396	85.94 333	58.31 341	85.90 333	56.51 371	83.22 405	87.20 338

test_yl		78.71 275	78.51 277	79.32 291	84.32 325	58.84 344	78.38 315	85.33 287	75.99 150	82.49 290	86.57 322	58.01 342	90.02 248	62.74 333	92.73 248	89.10 306

DCV-MVSNet		78.71 275	78.51 277	79.32 291	84.32 325	58.84 344	78.38 315	85.33 287	75.99 150	82.49 290	86.57 322	58.01 342	90.02 248	62.74 333	92.73 248	89.10 306

sss		66.92 389	67.26 387	65.90 413	77.23 408	51.10 408	64.79 431	71.72 404	52.12 416	70.13 415	80.18 401	57.96 344	65.36 444	50.21 409	81.01 421	81.25 415

ppachtmachnet_test		74.73 324	74.00 323	76.90 329	80.71 379	56.89 363	71.53 397	78.42 350	58.24 374	79.32 343	82.92 375	57.91 345	84.26 354	65.60 310	91.36 284	89.56 292

MVP-Stereo		75.81 311	73.51 328	82.71 223	89.35 189	73.62 139	80.06 287	85.20 289	60.30 362	73.96 392	87.94 290	57.89 346	89.45 260	52.02 402	74.87 442	85.06 361
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PAPM		71.77 349	70.06 365	76.92 328	86.39 274	53.97 383	76.62 346	86.62 267	53.44 404	63.97 444	84.73 355	57.79 347	92.34 169	39.65 444	81.33 419	84.45 368

LFMVS		80.15 260	80.56 246	78.89 294	89.19 194	55.93 367	85.22 164	73.78 385	82.96 69	84.28 258	92.72 152	57.38 348	90.07 246	63.80 326	95.75 146	90.68 266

Vis-MVSNet (Re-imp)		77.82 284	77.79 285	77.92 314	88.82 206	51.29 405	83.28 219	71.97 401	74.04 181	82.23 296	89.78 259	57.38 348	89.41 263	57.22 368	95.41 154	93.05 166

CHOSEN 1792x2688		72.45 343	70.56 358	78.13 309	90.02 178	63.08 277	68.72 415	83.16 316	42.99 447	75.92 375	85.46 341	57.22 350	85.18 343	49.87 413	81.67 415	86.14 348

mvsany_test1		58.48 420	56.47 426	64.50 420	65.90 460	68.21 224	56.95 450	42.11 463	38.30 455	65.69 435	77.19 429	56.96 351	59.35 453	46.16 430	58.96 456	65.93 447

miper_lstm_enhance		76.45 304	76.10 303	77.51 320	76.72 414	60.97 316	64.69 432	85.04 294	63.98 324	83.20 280	88.22 285	56.67 352	78.79 391	73.22 230	93.12 237	92.78 177

our_test_3		71.85 348	71.59 348	72.62 369	80.71 379	53.78 385	69.72 411	71.71 405	58.80 371	78.03 353	80.51 399	56.61 353	78.84 390	62.20 337	86.04 377	85.23 358

baseline1		73.26 336	73.54 327	72.43 372	84.92 313	47.79 420	79.89 291	74.00 381	65.93 298	78.81 348	86.28 329	56.36 354	81.63 372	56.63 370	79.04 431	87.87 330

pmmvs4		74.92 320	72.98 335	80.73 266	84.95 312	71.71 176	76.23 353	77.59 355	52.83 409	77.73 360	86.38 324	56.35 355	84.97 344	57.72 367	87.05 362	85.51 356

MVE	40.22 23	51.82 425	50.47 428	55.87 436	62.66 463	51.91 399	31.61 457	39.28 464	40.65 450	50.76 459	74.98 439	56.24 356	44.67 460	33.94 455	64.11 454	71.04 442
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		60.59 418	62.54 413	54.72 438	77.26 407	27.74 461	74.05 375	61.00 447	60.48 360	65.62 436	67.03 451	55.93 357	68.23 433	32.07 457	69.46 452	68.17 445

N_pmnet		70.20 364	68.80 379	74.38 355	80.91 374	84.81 43	59.12 445	76.45 367	55.06 395	75.31 384	82.36 381	55.74 358	54.82 455	47.02 426	87.24 358	83.52 383

MS-PatchMatch		70.93 359	70.22 363	73.06 364	81.85 362	62.50 287	73.82 379	77.90 352	52.44 412	75.92 375	81.27 391	55.67 359	81.75 370	55.37 381	77.70 435	74.94 436

DSMNet-mixed		60.98 416	61.61 416	59.09 435	72.88 443	45.05 433	74.70 370	46.61 461	26.20 459	65.34 437	90.32 245	55.46 360	63.12 448	41.72 440	81.30 420	69.09 444

pmmvs5		70.73 360	70.07 364	72.72 367	77.03 411	52.73 393	74.14 373	75.65 372	50.36 428	72.17 403	85.37 345	55.42 361	80.67 377	52.86 399	87.59 356	84.77 363

CMPMVS	59.41 20	75.12 317	73.57 326	79.77 283	75.84 423	67.22 231	81.21 273	82.18 326	50.78 424	76.50 366	87.66 302	55.20 362	82.99 363	62.17 339	90.64 312	89.09 308
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_vis1_n_1920		71.30 356	71.58 350	70.47 382	77.58 406	59.99 329	74.25 372	84.22 309	51.06 421	74.85 388	79.10 410	55.10 363	68.83 427	68.86 280	79.20 430	82.58 397

MIMVSNet		71.09 357	71.59 348	69.57 391	87.23 251	50.07 412	78.91 307	71.83 402	60.20 365	71.26 406	91.76 186	55.08 364	76.09 399	41.06 441	87.02 364	82.54 399

PVSNet_0	51.08 22	56.10 422	54.97 427	59.48 434	75.12 429	53.28 390	55.16 451	61.89 442	44.30 441	59.16 451	62.48 454	54.22 365	65.91 442	35.40 452	47.01 457	59.25 453

MonoMVSNet		76.66 299	77.26 291	74.86 350	79.86 388	54.34 381	86.26 142	86.08 274	71.08 235	85.59 221	88.68 278	53.95 366	85.93 329	63.86 325	80.02 424	84.32 370

EPNet_dtu		72.87 341	71.33 353	77.49 321	77.72 404	60.55 321	82.35 250	75.79 369	66.49 296	58.39 455	81.06 393	53.68 367	85.98 328	53.55 393	92.97 242	85.95 350
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PMMVS2		55.64 424	59.27 422	44.74 440	64.30 462	12.32 468	40.60 455	49.79 458	53.19 406	65.06 441	84.81 353	53.60 368	49.76 458	32.68 456	89.41 325	72.15 439

test_vis1_rt		65.64 400	64.09 404	70.31 383	66.09 458	70.20 194	61.16 440	81.60 333	38.65 454	72.87 398	69.66 447	52.84 369	60.04 451	56.16 373	77.77 434	80.68 422

mvsany_test3		65.48 401	62.97 410	73.03 365	69.99 451	76.17 124	64.83 430	43.71 462	43.68 444	80.25 334	87.05 318	52.83 370	63.09 449	51.92 406	72.44 444	79.84 427

HyFIR lowres test		75.12 317	72.66 339	82.50 230	91.44 141	65.19 256	72.47 389	87.31 249	46.79 432	80.29 331	84.30 359	52.70 371	92.10 177	51.88 407	86.73 367	90.22 279

dmvs_re		66.81 392	66.98 388	66.28 412	76.87 412	58.68 348	71.66 395	72.24 397	60.29 363	69.52 420	73.53 441	52.38 372	64.40 446	44.90 434	81.44 418	75.76 434

test_cas_vis1_n_1920		69.20 379	69.12 372	69.43 392	73.68 436	62.82 281	70.38 407	77.21 359	46.18 436	80.46 330	78.95 412	52.03 373	65.53 443	65.77 309	77.45 438	79.95 426

test1111		78.53 277	78.85 271	77.56 319	92.22 109	47.49 421	82.61 238	69.24 417	72.43 214	85.28 227	94.20 89	51.91 374	90.07 246	65.36 312	96.45 108	95.11 72

ECVR-MVS		78.44 279	78.63 275	77.88 315	91.85 123	48.95 415	83.68 207	69.91 413	72.30 220	84.26 260	94.20 89	51.89 375	89.82 251	63.58 327	96.02 127	94.87 78

FMVSNet3		78.80 272	78.55 276	79.57 288	82.89 356	56.89 363	81.76 261	85.77 280	69.04 257	86.00 210	90.44 240	51.75 376	90.09 244	65.95 304	93.34 229	91.72 234

D2MVS		76.84 296	75.67 308	80.34 274	80.48 383	62.16 300	73.50 381	84.80 302	57.61 381	82.24 295	87.54 304	51.31 377	87.65 295	70.40 261	93.19 236	91.23 246

AUN-MVS		81.18 235	78.78 272	88.39 82	90.93 155	82.14 62	82.51 244	83.67 312	64.69 320	80.29 331	85.91 335	51.07 378	92.38 167	76.29 184	93.63 222	90.65 269

PVSNet	58.17 21	66.41 395	65.63 399	68.75 397	81.96 360	49.88 413	62.19 439	72.51 396	51.03 422	68.04 425	75.34 438	50.84 379	74.77 405	45.82 433	82.96 406	81.60 410

mvsmamba		80.30 255	78.87 269	84.58 164	88.12 226	67.55 230	92.35 30	84.88 299	63.15 328	85.33 226	90.91 219	50.71 380	95.20 62	66.36 300	87.98 348	90.99 254

GA-MVS		75.83 310	74.61 316	79.48 290	81.87 361	59.25 337	73.42 382	82.88 319	68.68 262	79.75 336	81.80 387	50.62 381	89.46 259	66.85 295	85.64 379	89.72 290

FPMVS		72.29 346	72.00 345	73.14 363	88.63 213	85.00 40	74.65 371	67.39 423	71.94 226	77.80 358	87.66 302	50.48 382	75.83 401	49.95 411	79.51 425	58.58 454

test_fmvs3		75.72 312	75.20 313	77.27 323	75.01 431	69.47 205	78.93 306	84.88 299	46.67 433	87.08 182	87.84 298	50.44 383	71.62 416	77.42 168	88.53 337	90.72 263

test_vis1_n		70.29 363	69.99 367	71.20 380	75.97 422	66.50 242	76.69 344	80.81 339	44.22 442	75.43 380	77.23 427	50.00 384	68.59 428	66.71 298	82.85 410	78.52 430

MVS-HIRNet		61.16 414	62.92 411	55.87 436	79.09 397	35.34 455	71.83 393	57.98 453	46.56 434	59.05 452	91.14 208	49.95 385	76.43 398	38.74 446	71.92 446	55.84 455

CVMVSNet		72.62 342	71.41 352	76.28 338	83.25 349	60.34 323	83.50 213	79.02 349	37.77 457	76.33 368	85.10 348	49.60 386	87.41 300	70.54 259	77.54 437	81.08 418

RPMNet		78.88 270	78.28 281	80.68 269	79.58 390	62.64 284	82.58 240	94.16 33	74.80 168	75.72 377	92.59 154	48.69 387	95.56 42	73.48 224	82.91 408	83.85 379

test_fmvs2		73.57 334	72.80 336	75.90 342	72.74 445	68.84 218	77.07 338	84.32 308	45.14 439	82.89 285	84.22 360	48.37 388	70.36 420	73.40 226	87.03 363	88.52 316

tpmrst		66.28 396	66.69 392	65.05 419	72.82 444	39.33 447	78.20 318	70.69 410	53.16 407	67.88 426	80.36 400	48.18 389	74.75 406	58.13 364	70.79 447	81.08 418

CR-MVSNet		74.00 330	73.04 334	76.85 331	79.58 390	62.64 284	82.58 240	76.90 362	50.50 427	75.72 377	92.38 161	48.07 390	84.07 356	68.72 283	82.91 408	83.85 379

Patchmtry		76.56 302	77.46 287	73.83 358	79.37 395	46.60 425	82.41 249	76.90 362	73.81 184	85.56 223	92.38 161	48.07 390	83.98 357	63.36 330	95.31 160	90.92 257

test_f		64.31 407	65.85 395	59.67 433	66.54 457	62.24 299	57.76 449	70.96 408	40.13 451	84.36 252	82.09 383	46.93 392	51.67 457	61.99 340	81.89 414	65.12 448

ADS-MVSNet2		65.87 398	63.64 407	72.55 370	73.16 440	56.92 362	67.10 425	74.81 375	49.74 429	66.04 433	82.97 372	46.71 393	77.26 396	42.29 438	69.96 449	83.46 384

ADS-MVSNet		61.90 410	62.19 414	61.03 430	73.16 440	36.42 453	67.10 425	61.75 443	49.74 429	66.04 433	82.97 372	46.71 393	63.21 447	42.29 438	69.96 449	83.46 384

PatchmatchNet		69.71 373	68.83 378	72.33 374	77.66 405	53.60 386	79.29 300	69.99 412	57.66 380	72.53 400	82.93 374	46.45 395	80.08 383	60.91 349	72.09 445	83.31 389
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thres200		72.34 345	71.55 351	74.70 354	83.48 339	51.60 402	75.02 367	73.71 386	70.14 246	78.56 351	80.57 397	46.20 396	88.20 284	46.99 427	89.29 326	84.32 370

sam_mvs1												46.11 397				83.88 376

tfpn200view9		74.86 321	74.23 321	76.74 332	86.24 283	52.12 397	79.24 302	73.87 383	73.34 195	81.82 307	84.60 357	46.02 398	88.80 270	51.98 403	90.99 290	89.31 297

thres400		75.14 315	74.23 321	77.86 316	86.24 283	52.12 397	79.24 302	73.87 383	73.34 195	81.82 307	84.60 357	46.02 398	88.80 270	51.98 403	90.99 290	92.66 184

baseline2		69.77 372	66.89 389	78.41 304	79.51 392	58.09 350	76.23 353	69.57 414	57.50 382	64.82 442	77.45 425	46.02 398	88.44 278	53.08 395	77.83 433	88.70 314

patchmatchnet-post											81.71 388	45.93 401	87.01 304

sam_mvs												45.92 402

BP-MVS1		82.81 199	81.67 218	86.23 119	87.88 232	68.53 220	86.06 146	84.36 306	75.65 157	85.14 229	90.19 249	45.84 403	94.42 89	85.18 67	94.72 186	95.75 49

Patchmatch-RL test		74.48 325	73.68 325	76.89 330	84.83 314	66.54 241	72.29 390	69.16 418	57.70 379	86.76 188	86.33 326	45.79 404	82.59 364	69.63 269	90.65 311	81.54 411

thres100view900		75.45 313	75.05 314	76.66 333	87.27 249	51.88 400	81.07 275	73.26 390	75.68 156	83.25 279	86.37 325	45.54 405	88.80 270	51.98 403	90.99 290	89.31 297

thres600view7		75.97 309	75.35 312	77.85 317	87.01 263	51.84 401	80.45 284	73.26 390	75.20 165	83.10 282	86.31 328	45.54 405	89.05 266	55.03 385	92.24 261	92.66 184

tpm cat1		66.76 393	65.21 402	71.42 378	77.09 410	50.62 410	78.01 319	73.68 387	44.89 440	68.64 422	79.00 411	45.51 407	82.42 367	49.91 412	70.15 448	81.23 417

test_post											3.10 463	45.43 408	77.22 397

MDTV_nov1_ep13			68.29 383		78.03 402	43.87 437	74.12 374	72.22 398	52.17 413	67.02 430	85.54 338	45.36 409	80.85 376	55.73 376	84.42 397

tpmvs		70.16 365	69.56 370	71.96 375	74.71 432	48.13 417	79.63 293	75.45 374	65.02 318	70.26 414	81.88 386	45.34 410	85.68 338	58.34 362	75.39 441	82.08 406

MDTV_nov1_ep13_2view						27.60 462	70.76 404		46.47 435	61.27 447		45.20 411		49.18 416		83.75 381

test_post1							78.85 310				3.13 462	45.19 412	80.13 382	58.11 365

CostFormer		69.98 370	68.68 380	73.87 357	77.14 409	50.72 409	79.26 301	74.51 378	51.94 417	70.97 409	84.75 354	45.16 413	87.49 298	55.16 384	79.23 428	83.40 386

GDP-MVS		82.17 212	80.85 243	86.15 126	88.65 212	68.95 217	85.65 155	93.02 91	68.42 265	83.73 268	89.54 263	45.07 414	94.31 91	79.66 133	93.87 212	95.19 68

FE-MVS		79.98 263	78.86 270	83.36 203	86.47 272	66.45 244	89.73 71	84.74 303	72.80 209	84.22 261	91.38 199	44.95 415	93.60 127	63.93 324	91.50 282	90.04 286

Patchmatch-test		65.91 397	67.38 386	61.48 429	75.51 425	43.21 439	68.84 414	63.79 438	62.48 333	72.80 399	83.42 369	44.89 416	59.52 452	48.27 423	86.45 370	81.70 408

EU-MVSNet		75.12 317	74.43 320	77.18 324	83.11 354	59.48 334	85.71 154	82.43 324	39.76 453	85.64 220	88.76 276	44.71 417	87.88 291	73.86 215	85.88 378	84.16 375

PatchT		70.52 362	72.76 338	63.79 423	79.38 394	33.53 457	77.63 327	65.37 434	73.61 188	71.77 404	92.79 150	44.38 418	75.65 402	64.53 322	85.37 381	82.18 404

test_vis3_rt		71.42 354	70.67 356	73.64 360	69.66 452	70.46 190	66.97 427	89.73 201	42.68 449	88.20 153	83.04 371	43.77 419	60.07 450	65.35 313	86.66 368	90.39 277

test_fmvs1_n		70.94 358	70.41 362	72.53 371	73.92 433	66.93 238	75.99 357	84.21 310	43.31 446	79.40 340	79.39 408	43.47 420	68.55 429	69.05 277	84.91 391	82.10 405

test-LLR		67.21 387	66.74 391	68.63 399	76.45 418	55.21 375	67.89 418	67.14 426	62.43 337	65.08 439	72.39 442	43.41 421	69.37 422	61.00 347	84.89 392	81.31 413

test0.0.03 1		64.66 404	64.36 403	65.57 416	75.03 430	46.89 424	64.69 432	61.58 446	62.43 337	71.18 408	77.54 423	43.41 421	68.47 431	40.75 443	82.65 411	81.35 412

test_fmvs1		69.57 374	69.05 374	71.14 381	69.15 453	65.77 252	73.98 376	83.32 314	42.83 448	77.77 359	78.27 418	43.39 423	68.50 430	68.39 287	84.38 398	79.15 428

MVSTER		77.09 293	75.70 307	81.25 256	75.27 428	61.08 311	77.49 332	85.07 292	60.78 357	86.55 195	88.68 278	43.14 424	90.25 232	73.69 221	90.67 308	92.42 197

tpm		67.95 384	68.08 385	67.55 405	78.74 401	43.53 438	75.60 360	67.10 428	54.92 396	72.23 401	88.10 287	42.87 425	75.97 400	52.21 401	80.95 423	83.15 391

tpm2		68.45 383	66.83 390	73.30 362	78.93 400	48.50 416	79.76 292	71.76 403	47.50 431	69.92 416	83.60 365	42.07 426	88.40 280	48.44 422	79.51 425	83.01 393

EMVS		61.10 415	60.81 417	61.99 426	65.96 459	55.86 369	53.10 453	58.97 451	67.06 291	56.89 457	63.33 453	40.98 427	67.03 437	54.79 386	86.18 375	63.08 449

new_pmnet		55.69 423	57.66 424	49.76 439	75.47 426	30.59 459	59.56 442	51.45 457	43.62 445	62.49 445	75.48 437	40.96 428	49.15 459	37.39 451	72.52 443	69.55 443

E-PMN		61.59 412	61.62 415	61.49 428	66.81 456	55.40 373	53.77 452	60.34 448	66.80 294	58.90 453	65.50 452	40.48 429	66.12 441	55.72 377	86.25 374	62.95 450

EPMVS		62.47 408	62.63 412	62.01 425	70.63 450	38.74 449	74.76 369	52.86 456	53.91 402	67.71 428	80.01 402	39.40 430	66.60 439	55.54 380	68.81 453	80.68 422

tmp_tt		20.25 430	24.50 433	7.49 445	4.47 468	8.70 469	34.17 456	25.16 466	1.00 463	32.43 462	18.49 460	39.37 431	9.21 464	21.64 459	43.75 458	4.57 460

thisisatest0530		79.07 267	77.33 290	84.26 175	87.13 254	64.58 260	83.66 208	75.95 368	68.86 259	85.22 228	87.36 310	38.10 432	93.57 131	75.47 194	94.28 199	94.62 87

ET-MVSNet_ETH3D		75.28 314	72.77 337	82.81 222	83.03 355	68.11 225	77.09 337	76.51 366	60.67 359	77.60 361	80.52 398	38.04 433	91.15 202	70.78 254	90.68 307	89.17 304

ttmdpeth		71.72 350	70.67 356	74.86 350	73.08 442	55.88 368	77.41 334	69.27 416	55.86 391	78.66 349	93.77 116	38.01 434	75.39 404	60.12 353	89.87 320	93.31 152

tttt0517		81.07 237	79.58 263	85.52 138	88.99 201	66.45 244	87.03 124	75.51 373	73.76 185	88.32 150	90.20 248	37.96 435	94.16 104	79.36 139	95.13 165	95.93 47

thisisatest0515		73.00 340	70.52 359	80.46 272	81.45 367	59.90 330	73.16 385	74.31 380	57.86 378	76.08 374	77.78 420	37.60 436	92.12 176	65.00 315	91.45 283	89.35 296

FMVSNet5		72.10 347	71.69 347	73.32 361	81.57 366	53.02 391	76.77 342	78.37 351	63.31 325	76.37 367	91.85 179	36.68 437	78.98 388	47.87 424	92.45 254	87.95 326

dp		60.70 417	60.29 420	61.92 427	72.04 447	38.67 450	70.83 403	64.08 437	51.28 420	60.75 448	77.28 426	36.59 438	71.58 417	47.41 425	62.34 455	75.52 435

CHOSEN 280x420		59.08 419	56.52 425	66.76 410	76.51 416	64.39 263	49.62 454	59.00 450	43.86 443	55.66 458	68.41 450	35.55 439	68.21 434	43.25 437	76.78 440	67.69 446

testing91		69.94 371	68.99 376	72.80 366	83.81 336	45.89 428	71.57 396	73.64 388	68.24 269	70.77 412	77.82 419	34.37 440	84.44 351	53.64 392	87.00 365	88.07 321

IB-MVS	62.13 19	71.64 351	68.97 377	79.66 287	80.80 378	62.26 297	73.94 377	76.90 362	63.27 327	68.63 423	76.79 430	33.83 441	91.84 184	59.28 358	87.26 357	84.88 362
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
WBMVS		68.76 381	68.43 381	69.75 389	83.29 347	40.30 446	67.36 423	72.21 399	57.09 386	77.05 364	85.53 339	33.68 442	80.51 379	48.79 419	90.90 295	88.45 317

JIA-IIPM		69.41 375	66.64 393	77.70 318	73.19 439	71.24 181	75.67 359	65.56 433	70.42 240	65.18 438	92.97 141	33.64 443	83.06 361	53.52 394	69.61 451	78.79 429

UBG		64.34 406	63.35 408	67.30 407	83.50 338	40.53 445	67.46 422	65.02 435	54.77 398	67.54 429	74.47 440	32.99 444	78.50 392	40.82 442	83.58 402	82.88 394

myMVS_eth3d28		65.83 399	65.85 395	65.78 414	83.42 342	35.71 454	67.29 424	68.01 421	67.58 283	69.80 417	77.72 422	32.29 445	74.30 408	37.49 450	89.06 330	87.32 336

testing99		69.27 377	68.15 384	72.63 368	83.29 347	45.45 430	71.15 398	71.08 407	67.34 286	70.43 413	77.77 421	32.24 446	84.35 353	53.72 391	86.33 373	88.10 320

testing3-2		70.72 361	70.97 354	69.95 386	88.93 203	34.80 456	69.85 410	66.59 430	78.42 124	77.58 362	85.55 337	31.83 447	82.08 368	46.28 429	93.73 218	92.98 171

testing11		67.38 386	65.93 394	71.73 377	83.37 344	46.60 425	70.95 401	69.40 415	62.47 334	66.14 431	76.66 431	31.22 448	84.10 355	49.10 417	84.10 400	84.49 366

UWE-MVS-28		58.44 421	57.71 423	60.65 431	73.58 437	31.23 458	69.68 412	48.80 459	53.12 408	61.79 446	78.83 413	30.98 449	68.40 432	21.58 460	80.99 422	82.33 403

DeepMVS_CX				24.13 444	32.95 466	29.49 460		21.63 467	12.07 460	37.95 461	45.07 458	30.84 450	19.21 463	17.94 462	33.06 460	23.69 459

gg-mvs-nofinetune		68.96 380	69.11 373	68.52 402	76.12 421	45.32 431	83.59 210	55.88 454	86.68 33	64.62 443	97.01 12	30.36 451	83.97 358	44.78 435	82.94 407	76.26 433

GG-mvs-BLEND				67.16 408	73.36 438	46.54 427	84.15 190	55.04 455		58.64 454	61.95 455	29.93 452	83.87 359	38.71 447	76.92 439	71.07 441

UWE-MVS		66.43 394	65.56 400	69.05 394	84.15 329	40.98 444	73.06 386	64.71 436	54.84 397	76.18 372	79.62 407	29.21 453	80.50 380	38.54 448	89.75 321	85.66 354

ETVMVS		64.67 403	63.34 409	68.64 398	83.44 341	41.89 441	69.56 413	61.70 445	61.33 350	68.74 421	75.76 436	28.76 454	79.35 385	34.65 453	86.16 376	84.67 365

test_method		30.46 428	29.60 431	33.06 442	17.99 467	3.84 470	13.62 458	73.92 382	2.79 461	18.29 463	53.41 456	28.53 455	43.25 461	22.56 458	35.27 459	52.11 456

test-mter		65.00 402	63.79 406	68.63 399	76.45 418	55.21 375	67.89 418	67.14 426	50.98 423	65.08 439	72.39 442	28.27 456	69.37 422	61.00 347	84.89 392	81.31 413

TESTMET0.1,1		61.29 413	60.32 419	64.19 421	72.06 446	51.30 404	67.89 418	62.09 439	45.27 438	60.65 449	69.01 448	27.93 457	64.74 445	56.31 372	81.65 417	76.53 432

reproduce_monomvs		74.09 329	73.23 331	76.65 334	76.52 415	54.54 379	77.50 331	81.40 335	65.85 300	82.86 287	86.67 321	27.38 458	84.53 349	70.24 262	90.66 310	90.89 258

testing222		66.93 388	65.30 401	71.81 376	83.38 343	45.83 429	72.06 392	67.50 422	64.12 323	69.68 418	76.37 434	27.34 459	83.00 362	38.88 445	88.38 340	86.62 344

test2506		74.12 328	73.39 329	76.28 338	91.85 123	44.20 435	84.06 192	48.20 460	72.30 220	81.90 304	94.20 89	27.22 460	89.77 254	64.81 317	96.02 127	94.87 78

pmmvs3		62.47 408	60.02 421	69.80 388	71.58 448	64.00 267	70.52 405	58.44 452	39.77 452	66.05 432	75.84 435	27.10 461	72.28 412	46.15 431	84.77 396	73.11 438

KD-MVS_2432*1600		66.87 390	65.81 397	70.04 384	67.50 454	47.49 421	62.56 437	79.16 346	61.21 353	77.98 354	80.61 395	25.29 462	82.48 365	53.02 396	84.92 389	80.16 424

miper_refine_blended		66.87 390	65.81 397	70.04 384	67.50 454	47.49 421	62.56 437	79.16 346	61.21 353	77.98 354	80.61 395	25.29 462	82.48 365	53.02 396	84.92 389	80.16 424

MVStest1		70.05 368	69.26 371	72.41 373	58.62 464	55.59 372	76.61 347	65.58 432	53.44 404	89.28 128	93.32 127	22.91 464	71.44 418	74.08 211	89.52 324	90.21 283

myMVS_eth3d		64.66 404	63.89 405	66.97 409	81.72 363	37.39 451	71.00 399	61.99 440	61.38 348	70.81 410	72.36 444	20.96 465	79.30 386	49.59 414	85.18 384	84.22 372

testing3		71.53 353	70.79 355	73.77 359	88.89 205	41.86 442	76.60 348	59.12 449	72.83 208	80.97 319	82.08 384	19.80 466	87.33 302	65.12 314	91.68 278	92.13 220

dongtai		41.90 426	42.65 429	39.67 441	70.86 449	21.11 463	61.01 441	21.42 468	57.36 383	57.97 456	50.06 457	16.40 467	58.73 454	21.03 461	27.69 461	39.17 457

kuosan		30.83 427	32.17 430	26.83 443	53.36 465	19.02 466	57.90 448	20.44 469	38.29 456	38.01 460	37.82 459	15.18 468	33.45 462	7.74 463	20.76 462	28.03 458

test123		6.27 433	8.08 436	0.84 446	1.11 470	0.57 471	62.90 436	0.82 470	0.54 464	1.07 466	2.75 465	1.26 469	0.30 465	1.04 464	1.26 464	1.66 461

testmvs		5.91 434	7.65 437	0.72 447	1.20 469	0.37 472	59.14 444	0.67 471	0.49 465	1.11 465	2.76 464	0.94 470	0.24 466	1.02 465	1.47 463	1.55 462

mmdepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

monomultidepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

test_blank		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet_test		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

DCPMVS		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

sosnet-low-res		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

sosnet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uncertanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

Regformer		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

ab-mvs-re		6.65 431	8.87 434	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	79.80 404	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

WAC-MVS						37.39 451								52.61 400

FOURS1					96.08 12	87.41 14	96.19 2	95.83 5	92.95 3	96.57 3

MSC_two_6792asdad				88.81 73	91.55 135	77.99 97		91.01 159					96.05 9	87.45 28	98.17 37	92.40 200

No_MVS				88.81 73	91.55 135	77.99 97		91.01 159					96.05 9	87.45 28	98.17 37	92.40 200

eth-test2					0.00 471

eth-test					0.00 471

IU-MVS					94.18 52	72.64 154		90.82 164	56.98 387	89.67 116				85.78 62	97.92 52	93.28 153

save fliter					93.75 65	77.44 106	86.31 140	89.72 202	70.80 237

test_0728_SECOND				86.79 108	94.25 50	72.45 162	90.54 53	94.10 40					95.88 18	86.42 45	97.97 49	92.02 224

GSMVS																83.88 376

test_part2					93.86 63	77.77 101				92.84 52

MTGPA								91.81 133

MTMP							90.66 49	33.14 465

gm-plane-assit					75.42 427	44.97 434			52.17 413		72.36 444		87.90 290	54.10 389

test9_res														80.83 119	96.45 108	90.57 271

agg_prior2														79.68 132	96.16 120	90.22 279

agg_prior					91.58 133	77.69 103		90.30 185		84.32 254			93.18 144

test_prior4						78.97 87	84.59 179

test_prior				86.32 116	90.59 163	71.99 170		92.85 97					94.17 102			92.80 176

旧先验2							81.73 262		56.88 388	86.54 201			84.90 345	72.81 237

新几何2							81.72 263

无先验							82.81 235	85.62 283	58.09 376				91.41 196	67.95 291		84.48 367

原ACMM2							82.26 255

testdata2													86.43 319	63.52 329

testdata1							79.62 294		73.95 183

plane_prior7					93.45 72	77.31 109

plane_prior5								93.61 60					95.22 59	80.78 120	95.83 141	94.46 93

plane_prior4											92.95 142

plane_prior3						76.85 114			77.79 133	86.55 195

plane_prior2							89.45 83		79.44 108

plane_prior1					92.83 93

plane_prior						76.42 119	87.15 122		75.94 153						95.03 170

n2								0.00 472

nn								0.00 472

door-mid								74.45 379

test11								91.46 141

door								72.57 395

HQP5-MVS						70.66 187

HQP-NCC					91.19 147		84.77 170		73.30 197	80.55 327

ACMP_Plane					91.19 147		84.77 170		73.30 197	80.55 327

BP-MVS														77.30 169

HQP4-MVS										80.56 326			94.61 82			93.56 145

HQP3-MVS								92.68 102							94.47 192

NP-MVS					91.95 118	74.55 134					90.17 252

ACMMP++_ref															95.74 147

ACMMP++															97.35 80

High-resolution multi-view benchmark