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 34	95.54 5	97.36 1	96.97 1	99.04 1	99.05 1	96.61 1	95.92 16	85.07 54	99.27 1	99.54 1

mamv4		95.37 2	94.51 2	97.96 1	96.31 10	98.41 1	91.05 45	97.23 2	95.32 2	99.01 2	97.26 5	80.16 130	98.99 1	95.15 1	99.14 2	96.47 30

FOURS1					96.08 12	87.41 11	96.19 2	95.83 5	92.95 3	96.57 3

DTE-MVSNet		89.98 44	91.91 14	84.21 156	96.51 7	57.84 313	88.93 89	92.84 91	91.92 4	96.16 4	96.23 19	86.95 48	95.99 12	79.05 122	98.57 15	98.80 6

PS-CasMVS		90.06 40	91.92 12	84.47 146	96.56 6	58.83 306	89.04 87	92.74 94	91.40 6	96.12 5	96.06 25	87.23 45	95.57 39	79.42 119	98.74 6	99.00 2

LCM-MVSNet-Re		83.48 162	85.06 128	78.75 259	85.94 262	55.75 329	80.05 252	94.27 22	76.47 131	96.09 6	94.54 63	83.31 85	89.75 237	59.95 309	94.89 165	90.75 225

PEN-MVS		90.03 42	91.88 15	84.48 145	96.57 5	58.88 303	88.95 88	93.19 73	91.62 5	96.01 7	96.16 23	87.02 47	95.60 38	78.69 125	98.72 9	98.97 3

CP-MVSNet		89.27 59	90.91 41	84.37 147	96.34 8	58.61 309	88.66 96	92.06 113	90.78 7	95.67 8	95.17 43	81.80 112	95.54 42	79.00 123	98.69 10	98.95 4

LTVRE_ROB	86.10 1	93.04 4	93.44 3	91.82 21	93.73 61	85.72 31	96.79 1	95.51 10	88.86 13	95.63 9	96.99 9	84.81 69	93.16 134	91.10 2	97.53 69	96.58 28
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
WR-MVS_H		89.91 47	91.31 30	85.71 123	96.32 9	62.39 257	89.54 78	93.31 68	90.21 11	95.57 10	95.66 31	81.42 116	95.90 17	80.94 100	98.80 3	98.84 5

OurMVSNet-221017-0		90.01 43	89.74 54	90.83 33	93.16 75	80.37 69	91.91 33	93.11 77	81.10 79	95.32 11	97.24 6	72.94 210	94.85 71	85.07 54	97.78 53	97.26 15

anonymousdsp		89.73 50	88.88 68	92.27 8	89.82 169	86.67 15	90.51 53	90.20 172	69.87 222	95.06 12	96.14 24	84.28 74	93.07 138	87.68 15	96.34 103	97.09 19

wuyk23d		75.13 273	79.30 227	62.63 373	75.56 375	75.18 123	80.89 244	73.10 348	75.06 152	94.76 13	95.32 37	87.73 40	52.85 404	34.16 403	97.11 79	59.85 400

ACMH	76.49 14	89.34 56	91.14 32	83.96 161	92.50 91	70.36 175	89.55 76	93.84 50	81.89 71	94.70 14	95.44 36	90.69 8	88.31 260	83.33 71	98.30 25	93.20 138
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SixPastTwentyTwo		87.20 87	87.45 85	86.45 105	92.52 90	69.19 188	87.84 106	88.05 208	81.66 73	94.64 15	96.53 15	65.94 256	94.75 73	83.02 77	96.83 86	95.41 51

iter_conf05		88.59 68	90.04 49	84.23 155	92.03 107	60.51 285	91.36 40	95.81 6	88.07 21	94.56 16	96.17 21	72.24 219	95.79 29	84.85 58	95.27 149	96.38 31

mvs_tets		89.78 49	89.27 61	91.30 26	93.51 64	84.79 41	89.89 67	90.63 155	70.00 221	94.55 17	96.67 12	87.94 37	93.59 117	84.27 65	95.97 120	95.52 49

jajsoiax		89.41 54	88.81 71	91.19 29	93.38 68	84.72 42	89.70 70	90.29 169	69.27 225	94.39 18	96.38 16	86.02 62	93.52 121	83.96 67	95.92 126	95.34 53

test_0402		88.65 66	89.58 58	85.88 119	92.55 89	72.22 155	84.01 171	89.44 189	88.63 17	94.38 19	95.77 28	86.38 58	93.59 117	79.84 112	95.21 150	91.82 199

UniMVSNet_ETH3D		89.12 62	90.72 44	84.31 153	97.00 2	64.33 232	89.67 73	88.38 201	88.84 14	94.29 20	97.57 3	90.48 13	91.26 185	72.57 204	97.65 59	97.34 14

v7n		90.13 37	90.96 39	87.65 88	91.95 110	71.06 169	89.99 63	93.05 81	86.53 29	94.29 20	96.27 18	82.69 90	94.08 97	86.25 42	97.63 60	97.82 8

test_djsdf		89.62 51	89.01 65	91.45 23	92.36 94	82.98 54	91.98 31	90.08 175	71.54 202	94.28 22	96.54 14	81.57 114	94.27 86	86.26 40	96.49 97	97.09 19

PS-MVSNAJss		88.31 71	87.90 79	89.56 56	93.31 70	77.96 93	87.94 104	91.97 116	70.73 212	94.19 23	96.67 12	76.94 162	94.57 80	83.07 75	96.28 105	96.15 33

SED-MVS		90.46 34	91.64 18	86.93 96	94.18 47	72.65 141	90.47 54	93.69 54	83.77 50	94.11 24	94.27 75	90.28 14	95.84 24	86.03 46	97.92 46	92.29 181

test_241102_ONE					94.18 47	72.65 141		93.69 54	83.62 52	94.11 24	93.78 104	90.28 14	95.50 48

DPE-MVS		90.53 33	91.08 34	88.88 66	93.38 68	78.65 84	89.15 86	94.05 39	84.68 43	93.90 26	94.11 87	88.13 34	96.30 5	84.51 63	97.81 52	91.70 203
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		91.22 22	91.92 12	89.14 63	92.97 79	78.04 90	92.84 15	94.14 34	83.33 56	93.90 26	95.73 29	88.77 25	96.41 3	87.60 18	97.98 42	92.98 149
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMH+	77.89 11	90.73 28	91.50 22	88.44 75	93.00 78	76.26 116	89.65 74	95.55 9	87.72 24	93.89 28	94.94 48	91.62 3	93.44 125	78.35 128	98.76 4	95.61 48

ACMM	79.39 9	90.65 29	90.99 38	89.63 54	95.03 34	83.53 48	89.62 75	93.35 64	79.20 102	93.83 29	93.60 110	90.81 7	92.96 140	85.02 56	98.45 19	92.41 173
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SR-MVS-dyc-post		92.41 6	92.41 7	92.39 5	94.13 52	88.95 6	92.87 13	94.16 30	88.75 15	93.79 30	94.43 68	88.83 24	95.51 45	87.16 29	97.60 63	92.73 155

RE-MVS-def			92.61 5		94.13 52	88.95 6	92.87 13	94.16 30	88.75 15	93.79 30	94.43 68	90.64 10		87.16 29	97.60 63	92.73 155

DVP-MVS		90.06 40	91.32 29	86.29 108	94.16 50	72.56 147	90.54 51	91.01 145	83.61 53	93.75 32	94.65 57	89.76 18	95.78 31	86.42 36	97.97 43	90.55 234
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_THIRD									85.33 36	93.75 32	94.65 57	87.44 43	95.78 31	87.41 22	98.21 29	92.98 149

test0726					94.16 50	72.56 147	90.63 48	93.90 46	83.61 53	93.75 32	94.49 65	89.76 18

LPG-MVS_test		91.47 18	91.68 17	90.82 34	94.75 41	81.69 60	90.00 61	94.27 22	82.35 66	93.67 35	94.82 52	91.18 4	95.52 43	85.36 52	98.73 7	95.23 59

LGP-MVS_train				90.82 34	94.75 41	81.69 60		94.27 22	82.35 66	93.67 35	94.82 52	91.18 4	95.52 43	85.36 52	98.73 7	95.23 59

DVP-MVS++		90.07 39	91.09 33	87.00 94	91.55 127	72.64 143	96.19 2	94.10 37	85.33 36	93.49 37	94.64 60	81.12 119	95.88 18	87.41 22	95.94 124	92.48 169

test_241102_TWO								93.71 53	83.77 50	93.49 37	94.27 75	89.27 21	95.84 24	86.03 46	97.82 51	92.04 192

test_one_0601					93.85 59	73.27 136		94.11 36	86.57 28	93.47 39	94.64 60	88.42 26

SR-MVS		92.23 7	92.34 8	91.91 16	94.89 38	87.85 9	92.51 23	93.87 49	88.20 20	93.24 40	94.02 90	90.15 16	95.67 36	86.82 33	97.34 73	92.19 187

APD-MVS_3200maxsize		92.05 9	92.24 9	91.48 22	93.02 77	85.17 36	92.47 25	95.05 15	87.65 25	93.21 41	94.39 73	90.09 17	95.08 65	86.67 35	97.60 63	94.18 94

testf1		89.30 57	89.12 62	89.84 49	88.67 194	85.64 32	90.61 49	93.17 74	86.02 32	93.12 42	95.30 38	84.94 66	89.44 242	74.12 180	96.10 115	94.45 82

APD_test2		89.30 57	89.12 62	89.84 49	88.67 194	85.64 32	90.61 49	93.17 74	86.02 32	93.12 42	95.30 38	84.94 66	89.44 242	74.12 180	96.10 115	94.45 82

Anonymous20231211		88.40 69	89.62 57	84.73 139	90.46 155	65.27 222	88.86 90	93.02 85	87.15 26	93.05 44	97.10 7	82.28 102	92.02 166	76.70 152	97.99 40	96.88 23

MP-MVS-pluss		90.81 27	91.08 34	89.99 47	95.97 14	79.88 72	88.13 101	94.51 19	75.79 142	92.94 45	94.96 47	88.36 28	95.01 67	90.70 3	98.40 20	95.09 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SD-MVS		88.96 64	89.88 51	86.22 111	91.63 121	77.07 106	89.82 68	93.77 51	78.90 106	92.88 46	92.29 150	86.11 60	90.22 218	86.24 43	97.24 76	91.36 211
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
ACMP	79.16 10	90.54 32	90.60 46	90.35 42	94.36 44	80.98 66	89.16 85	94.05 39	79.03 105	92.87 47	93.74 106	90.60 11	95.21 60	82.87 79	98.76 4	94.87 67
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TDRefinement		93.52 3	93.39 4	93.88 2	95.94 15	90.26 4	95.70 4	96.46 3	90.58 9	92.86 48	96.29 17	88.16 33	94.17 94	86.07 45	98.48 18	97.22 17

SMA-MVS		90.31 35	90.48 47	89.83 51	95.31 30	79.52 78	90.98 46	93.24 72	75.37 149	92.84 49	95.28 40	85.58 64	96.09 8	87.92 11	97.76 54	93.88 107
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
test_part2					93.86 58	77.77 95				92.84 49

v10		86.54 96	87.10 90	84.84 135	88.16 208	63.28 243	86.64 127	92.20 109	75.42 148	92.81 51	94.50 64	74.05 194	94.06 98	83.88 68	96.28 105	97.17 18

dcpmvs_2		84.23 143	85.14 127	81.50 220	88.61 197	61.98 266	82.90 206	93.11 77	68.66 234	92.77 52	92.39 144	78.50 141	87.63 266	76.99 151	92.30 228	94.90 65

v8		86.22 101	86.83 97	84.36 149	87.82 214	62.35 259	86.42 131	91.33 136	76.78 130	92.73 53	94.48 66	73.41 203	93.72 109	83.10 74	95.41 141	97.01 21

nrg030		87.85 80	88.49 73	85.91 117	90.07 164	69.73 179	87.86 105	94.20 28	74.04 160	92.70 54	94.66 56	85.88 63	91.50 177	79.72 114	97.32 74	96.50 29

SteuartSystems-ACMMP		91.16 24	91.36 25	90.55 38	93.91 57	80.97 67	91.49 37	93.48 61	82.82 63	92.60 55	93.97 92	88.19 31	96.29 6	87.61 17	98.20 31	94.39 87
Skip Steuart: Steuart Systems R&D Blog.
OPM-MVS		89.80 48	89.97 50	89.27 60	94.76 40	79.86 73	86.76 124	92.78 93	78.78 108	92.51 56	93.64 109	88.13 34	93.84 106	84.83 60	97.55 66	94.10 99
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HPM-MVS_fast		92.50 5	92.54 6	92.37 6	95.93 16	85.81 30	92.99 12	94.23 25	85.21 38	92.51 56	95.13 44	90.65 9	95.34 54	88.06 9	98.15 34	95.95 41

K. test v3		85.14 120	84.73 133	86.37 106	91.13 141	69.63 181	85.45 145	76.68 321	84.06 48	92.44 58	96.99 9	62.03 276	94.65 76	80.58 106	93.24 211	94.83 72

ACMMP		91.91 11	91.87 16	92.03 12	95.53 27	85.91 25	93.35 11	94.16 30	82.52 65	92.39 59	94.14 85	89.15 23	95.62 37	87.35 24	98.24 27	94.56 76
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
SF-MVS		90.27 36	90.80 43	88.68 73	92.86 83	77.09 105	91.19 43	95.74 7	81.38 76	92.28 60	93.80 102	86.89 49	94.64 77	85.52 51	97.51 70	94.30 90

COLMAP_ROB	83.01 3	91.97 10	91.95 11	92.04 11	93.68 62	86.15 21	93.37 10	95.10 14	90.28 10	92.11 61	95.03 46	89.75 20	94.93 69	79.95 111	98.27 26	95.04 64
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
XVG-ACMP-BASELINE		89.98 44	89.84 52	90.41 40	94.91 37	84.50 45	89.49 80	93.98 41	79.68 94	92.09 62	93.89 100	83.80 78	93.10 137	82.67 83	98.04 36	93.64 122

TranMVSNet+NR-MVSNet		87.86 79	88.76 72	85.18 131	94.02 55	64.13 233	84.38 165	91.29 137	84.88 42	92.06 63	93.84 101	86.45 55	93.73 108	73.22 195	98.66 11	97.69 9

MTAPA		91.52 15	91.60 19	91.29 27	96.59 4	86.29 18	92.02 30	91.81 124	84.07 47	92.00 64	94.40 72	86.63 51	95.28 57	88.59 6	98.31 24	92.30 180

ACMMP_NAP		90.65 29	91.07 36	89.42 58	95.93 16	79.54 77	89.95 65	93.68 56	77.65 121	91.97 65	94.89 49	88.38 27	95.45 50	89.27 4	97.87 50	93.27 135

FC-MVSNet-test		85.93 107	87.05 92	82.58 202	92.25 98	56.44 324	85.75 140	93.09 79	77.33 125	91.94 66	94.65 57	74.78 185	93.41 127	75.11 171	98.58 14	97.88 7

lessismore_v0				85.95 116	91.10 142	70.99 170		70.91 363		91.79 67	94.42 70	61.76 277	92.93 142	79.52 118	93.03 216	93.93 104

HPM-MVS		92.13 8	92.20 10	91.91 16	95.58 26	84.67 43	93.51 8	94.85 16	82.88 62	91.77 68	93.94 98	90.55 12	95.73 34	88.50 7	98.23 28	95.33 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
PGM-MVS		91.20 23	90.95 40	91.93 14	95.67 23	85.85 28	90.00 61	93.90 46	80.32 87	91.74 69	94.41 71	88.17 32	95.98 13	86.37 38	97.99 40	93.96 103

mPP-MVS		91.69 12	91.47 23	92.37 6	96.04 13	88.48 8	92.72 17	92.60 99	83.09 59	91.54 70	94.25 79	87.67 41	95.51 45	87.21 28	98.11 35	93.12 143

HFP-MVS		91.30 20	91.39 24	91.02 30	95.43 29	84.66 44	92.58 21	93.29 70	81.99 68	91.47 71	93.96 95	88.35 29	95.56 40	87.74 13	97.74 56	92.85 152

ACMMPR		91.49 16	91.35 27	91.92 15	95.74 20	85.88 27	92.58 21	93.25 71	81.99 68	91.40 72	94.17 84	87.51 42	95.87 20	87.74 13	97.76 54	93.99 101

GST-MVS		90.96 26	91.01 37	90.82 34	95.45 28	82.73 56	91.75 35	93.74 52	80.98 81	91.38 73	93.80 102	87.20 46	95.80 26	87.10 31	97.69 58	93.93 104

test_fmvsmvis_n_1920		85.22 117	85.36 125	84.81 136	85.80 264	76.13 119	85.15 151	92.32 106	61.40 301	91.33 74	90.85 196	83.76 80	86.16 292	84.31 64	93.28 210	92.15 189

ANet_high		83.17 168	85.68 118	75.65 303	81.24 325	45.26 386	79.94 254	92.91 88	83.83 49	91.33 74	96.88 11	80.25 129	85.92 295	68.89 237	95.89 127	95.76 43

ZNCC-MVS		91.26 21	91.34 28	91.01 31	95.73 21	83.05 53	92.18 28	94.22 27	80.14 90	91.29 76	93.97 92	87.93 38	95.87 20	88.65 5	97.96 45	94.12 98

casdiffmvs_mvg		86.72 93	87.51 84	84.36 149	87.09 235	65.22 223	84.16 167	94.23 25	77.89 118	91.28 77	93.66 108	84.35 73	92.71 146	80.07 108	94.87 168	95.16 61
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
APD-MVS		89.54 53	89.63 56	89.26 61	92.57 88	81.34 65	90.19 60	93.08 80	80.87 83	91.13 78	93.19 115	86.22 59	95.97 14	82.23 89	97.18 78	90.45 236
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
9.14			89.29 60		91.84 117		88.80 92	95.32 13	75.14 151	91.07 79	92.89 129	87.27 44	93.78 107	83.69 70	97.55 66

CP-MVS		91.67 13	91.58 20	91.96 13	95.29 31	87.62 10	93.38 9	93.36 63	83.16 58	91.06 80	94.00 91	88.26 30	95.71 35	87.28 27	98.39 21	92.55 166

FIs		85.35 116	86.27 104	82.60 201	91.86 114	57.31 317	85.10 152	93.05 81	75.83 141	91.02 81	93.97 92	73.57 199	92.91 144	73.97 183	98.02 39	97.58 12

UniMVSNet_NR-MVSNet		86.84 91	87.06 91	86.17 114	92.86 83	67.02 206	82.55 215	91.56 127	83.08 60	90.92 82	91.82 163	78.25 144	93.99 99	74.16 178	98.35 22	97.49 13

DU-MVS		86.80 92	86.99 93	86.21 112	93.24 73	67.02 206	83.16 198	92.21 108	81.73 72	90.92 82	91.97 157	77.20 156	93.99 99	74.16 178	98.35 22	97.61 10

tt0805		88.09 75	89.79 53	82.98 191	93.26 72	63.94 236	91.10 44	89.64 184	85.07 39	90.91 84	91.09 184	89.16 22	91.87 171	82.03 90	95.87 128	93.13 141

V42		83.47 163	83.37 160	83.75 167	83.16 308	63.33 242	81.31 237	90.23 171	69.51 224	90.91 84	90.81 198	74.16 192	92.29 160	80.06 109	90.22 272	95.62 47

region2R		91.44 19	91.30 31	91.87 18	95.75 19	85.90 26	92.63 20	93.30 69	81.91 70	90.88 86	94.21 80	87.75 39	95.87 20	87.60 18	97.71 57	93.83 110

APD_test1		88.40 69	87.91 78	89.88 48	89.50 173	86.65 17	89.98 64	91.91 119	84.26 45	90.87 87	93.92 99	82.18 103	89.29 246	73.75 187	94.81 169	93.70 118

WR-MVS		83.56 160	84.40 145	81.06 228	93.43 67	54.88 335	78.67 276	85.02 257	81.24 77	90.74 88	91.56 171	72.85 211	91.08 191	68.00 247	98.04 36	97.23 16

v1240		84.30 139	84.51 142	83.65 170	87.65 220	61.26 273	82.85 207	91.54 128	67.94 243	90.68 89	90.65 205	71.71 227	93.64 111	82.84 80	94.78 170	96.07 36

ZD-MVS					92.22 100	80.48 68		91.85 120	71.22 208	90.38 90	92.98 124	86.06 61	96.11 7	81.99 92	96.75 89

MIMVSNet1		83.63 158	84.59 138	80.74 232	94.06 54	62.77 250	82.72 209	84.53 266	77.57 123	90.34 91	95.92 27	76.88 168	85.83 300	61.88 297	97.42 71	93.62 123

LS3D		90.60 31	90.34 48	91.38 25	89.03 183	84.23 46	93.58 6	94.68 18	90.65 8	90.33 92	93.95 97	84.50 71	95.37 53	80.87 101	95.50 140	94.53 79

KD-MVS_self_test		81.93 190	83.14 165	78.30 268	84.75 279	52.75 347	80.37 249	89.42 190	70.24 219	90.26 93	93.39 113	74.55 190	86.77 280	68.61 242	96.64 91	95.38 52

PMVS	80.48 6	90.08 38	90.66 45	88.34 78	96.71 3	92.97 2	90.31 58	89.57 187	88.51 18	90.11 94	95.12 45	90.98 6	88.92 250	77.55 142	97.07 80	83.13 342
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PC_three_1452									58.96 323	90.06 95	91.33 176	80.66 125	93.03 139	75.78 162	95.94 124	92.48 169

v1921920		84.23 143	84.37 146	83.79 165	87.64 221	61.71 267	82.91 205	91.20 140	67.94 243	90.06 95	90.34 211	72.04 224	93.59 117	82.32 87	94.91 163	96.07 36

ITE_SJBPF				90.11 46	90.72 150	84.97 38		90.30 167	81.56 74	90.02 97	91.20 181	82.40 96	90.81 203	73.58 190	94.66 174	94.56 76

XVS		91.54 14	91.36 25	92.08 9	95.64 24	86.25 19	92.64 18	93.33 65	85.07 39	89.99 98	94.03 89	86.57 52	95.80 26	87.35 24	97.62 61	94.20 91

X-MVStestdata		85.04 122	82.70 172	92.08 9	95.64 24	86.25 19	92.64 18	93.33 65	85.07 39	89.99 98	16.05 409	86.57 52	95.80 26	87.35 24	97.62 61	94.20 91

v1192		84.57 132	84.69 137	84.21 156	87.75 216	62.88 247	83.02 201	91.43 131	69.08 228	89.98 100	90.89 193	72.70 214	93.62 115	82.41 86	94.97 162	96.13 34

Anonymous20240529		86.20 102	87.13 89	83.42 180	90.19 160	64.55 230	84.55 160	90.71 152	85.85 34	89.94 101	95.24 42	82.13 104	90.40 214	69.19 233	96.40 102	95.31 55

pmmvs6		86.52 97	88.06 77	81.90 212	92.22 100	62.28 260	84.66 158	89.15 192	83.54 55	89.85 102	97.32 4	88.08 36	86.80 279	70.43 221	97.30 75	96.62 26

v144192		84.24 142	84.41 144	83.71 169	87.59 222	61.57 268	82.95 204	91.03 144	67.82 246	89.80 103	90.49 208	73.28 207	93.51 122	81.88 95	94.89 165	96.04 38

v1144		84.54 134	84.72 135	84.00 159	87.67 219	62.55 254	82.97 203	90.93 148	70.32 217	89.80 103	90.99 187	73.50 200	93.48 123	81.69 96	94.65 175	95.97 39

DeepC-MVS	82.31 4	89.15 61	89.08 64	89.37 59	93.64 63	79.07 80	88.54 97	94.20 28	73.53 168	89.71 105	94.82 52	85.09 65	95.77 33	84.17 66	98.03 38	93.26 136
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
RPSCF		88.00 77	86.93 95	91.22 28	90.08 162	89.30 5	89.68 72	91.11 142	79.26 101	89.68 106	94.81 55	82.44 94	87.74 264	76.54 154	88.74 290	96.61 27

IU-MVS					94.18 47	72.64 143		90.82 150	56.98 339	89.67 107				85.78 49	97.92 46	93.28 134

FMVSNet1		84.55 133	85.45 122	81.85 214	90.27 159	61.05 276	86.83 121	88.27 205	78.57 112	89.66 108	95.64 32	75.43 176	90.68 207	69.09 234	95.33 144	93.82 111

IterMVS-LS		84.73 129	84.98 130	83.96 161	87.35 226	63.66 237	83.25 194	89.88 179	76.06 134	89.62 109	92.37 148	73.40 205	92.52 151	78.16 133	94.77 172	95.69 44
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		88.60 67	89.01 65	87.36 90	91.30 134	77.50 98	87.55 108	92.97 87	87.95 23	89.62 109	92.87 130	84.56 70	93.89 103	77.65 140	96.62 92	90.70 228

UniMVSNet (Re)		86.87 89	86.98 94	86.55 103	93.11 76	68.48 192	83.80 180	92.87 89	80.37 85	89.61 111	91.81 164	77.72 149	94.18 92	75.00 172	98.53 16	96.99 22

IS-MVSNet		86.66 95	86.82 98	86.17 114	92.05 106	66.87 209	91.21 42	88.64 198	86.30 31	89.60 112	92.59 138	69.22 239	94.91 70	73.89 184	97.89 49	96.72 24

v2v482		84.09 146	84.24 148	83.62 171	87.13 231	61.40 270	82.71 210	89.71 182	72.19 198	89.55 113	91.41 174	70.70 232	93.20 132	81.02 99	93.76 198	96.25 32

Baseline_NR-MVSNet		84.00 150	85.90 112	78.29 269	91.47 132	53.44 343	82.29 223	87.00 228	79.06 104	89.55 113	95.72 30	77.20 156	86.14 293	72.30 206	98.51 17	95.28 56

CSCG		86.26 99	86.47 101	85.60 125	90.87 147	74.26 127	87.98 103	91.85 120	80.35 86	89.54 115	88.01 248	79.09 137	92.13 162	75.51 165	95.06 157	90.41 237

ambc				82.98 191	90.55 154	64.86 226	88.20 99	89.15 192		89.40 116	93.96 95	71.67 228	91.38 184	78.83 124	96.55 94	92.71 158

DeepPCF-MVS	81.24 5	87.28 86	86.21 106	90.49 39	91.48 131	84.90 39	83.41 189	92.38 104	70.25 218	89.35 117	90.68 202	82.85 89	94.57 80	79.55 116	95.95 123	92.00 194

test_fmvsmconf0.01_n		86.68 94	86.52 100	87.18 91	85.94 262	78.30 86	86.93 118	92.20 109	65.94 257	89.16 118	93.16 117	83.10 86	89.89 231	87.81 12	94.43 180	93.35 131

MSP-MVS		89.08 63	88.16 76	91.83 19	95.76 18	86.14 22	92.75 16	93.90 46	78.43 113	89.16 118	92.25 152	72.03 225	96.36 4	88.21 8	90.93 259	92.98 149
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
XVG-OURS		89.18 60	88.83 70	90.23 44	94.28 45	86.11 23	85.91 136	93.60 59	80.16 89	89.13 120	93.44 112	83.82 77	90.98 194	83.86 69	95.30 148	93.60 124

MDA-MVSNet-bldmvs		77.47 248	76.90 253	79.16 255	79.03 350	64.59 227	66.58 377	75.67 327	73.15 181	88.86 121	88.99 236	66.94 250	81.23 333	64.71 275	88.22 299	91.64 205

EG-PatchMatch MVS		84.08 147	84.11 149	83.98 160	92.22 100	72.61 146	82.20 229	87.02 225	72.63 189	88.86 121	91.02 186	78.52 140	91.11 190	73.41 192	91.09 253	88.21 272

3Dnovator+	83.92 2	89.97 46	89.66 55	90.92 32	91.27 136	81.66 63	91.25 41	94.13 35	88.89 12	88.83 123	94.26 78	77.55 152	95.86 23	84.88 57	95.87 128	95.24 58

EI-MVSNet-UG-set		85.04 122	84.44 143	86.85 98	83.87 295	72.52 149	83.82 178	85.15 253	80.27 88	88.75 124	85.45 293	79.95 133	91.90 169	81.92 94	90.80 264	96.13 34

EI-MVSNet-Vis-set		85.12 121	84.53 141	86.88 97	84.01 291	72.76 140	83.91 176	85.18 252	80.44 84	88.75 124	85.49 291	80.08 131	91.92 168	82.02 91	90.85 263	95.97 39

balanced_conf03		84.80 127	85.40 123	83.00 190	88.95 186	61.44 269	90.42 57	92.37 105	71.48 204	88.72 126	93.13 118	70.16 235	95.15 62	79.26 121	94.11 190	92.41 173

OMC-MVS		88.19 72	87.52 83	90.19 45	91.94 112	81.68 62	87.49 111	93.17 74	76.02 136	88.64 127	91.22 179	84.24 75	93.37 128	77.97 138	97.03 81	95.52 49

test_fmvsmconf0.1_n		86.18 103	85.88 113	87.08 93	85.26 271	78.25 87	85.82 139	91.82 122	65.33 271	88.55 128	92.35 149	82.62 93	89.80 233	86.87 32	94.32 183	93.18 140

UA-Net		91.49 16	91.53 21	91.39 24	94.98 35	82.95 55	93.52 7	92.79 92	88.22 19	88.53 129	97.64 2	83.45 83	94.55 82	86.02 48	98.60 13	96.67 25

MP-MVS		91.14 25	90.91 41	91.83 19	96.18 11	86.88 14	92.20 27	93.03 84	82.59 64	88.52 130	94.37 74	86.74 50	95.41 52	86.32 39	98.21 29	93.19 139
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
sasdasda		85.50 111	86.14 107	83.58 173	87.97 210	67.13 203	87.55 108	94.32 20	73.44 171	88.47 131	87.54 259	86.45 55	91.06 192	75.76 163	93.76 198	92.54 167

canonicalmvs		85.50 111	86.14 107	83.58 173	87.97 210	67.13 203	87.55 108	94.32 20	73.44 171	88.47 131	87.54 259	86.45 55	91.06 192	75.76 163	93.76 198	92.54 167

NR-MVSNet		86.00 105	86.22 105	85.34 129	93.24 73	64.56 229	82.21 227	90.46 159	80.99 80	88.42 133	91.97 157	77.56 151	93.85 104	72.46 205	98.65 12	97.61 10

alignmvs		83.94 152	83.98 153	83.80 164	87.80 215	67.88 199	84.54 162	91.42 133	73.27 179	88.41 134	87.96 249	72.33 217	90.83 202	76.02 161	94.11 190	92.69 159

TransMVSNet (Re)		84.02 149	85.74 117	78.85 257	91.00 144	55.20 334	82.29 223	87.26 216	79.65 95	88.38 135	95.52 35	83.00 87	86.88 277	67.97 248	96.60 93	94.45 82

PM-MVS		80.20 220	79.00 229	83.78 166	88.17 207	86.66 16	81.31 237	66.81 381	69.64 223	88.33 136	90.19 216	64.58 261	83.63 321	71.99 208	90.03 274	81.06 368

tttt0517		81.07 201	79.58 224	85.52 126	88.99 185	66.45 213	87.03 117	75.51 329	73.76 164	88.32 137	90.20 215	37.96 390	94.16 96	79.36 120	95.13 153	95.93 42

casdiffmvs		85.21 118	85.85 114	83.31 183	86.17 257	62.77 250	83.03 200	93.93 44	74.69 155	88.21 138	92.68 137	82.29 101	91.89 170	77.87 139	93.75 201	95.27 57
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_vis3_rt		71.42 308	70.67 310	73.64 315	69.66 401	70.46 173	66.97 376	89.73 180	42.68 397	88.20 139	83.04 322	43.77 375	60.07 398	65.35 270	86.66 319	90.39 238

SSC-MVS		77.55 247	81.64 188	65.29 367	90.46 155	20.33 413	73.56 338	68.28 372	85.44 35	88.18 140	94.64 60	70.93 230	81.33 332	71.25 210	92.03 236	94.20 91

MVSMamba_PlusPlus		87.53 84	88.86 69	83.54 177	92.03 107	62.26 261	91.49 37	92.62 97	88.07 21	88.07 141	96.17 21	72.24 219	95.79 29	84.85 58	94.16 188	92.58 163

MGCFI-Net		85.04 122	85.95 110	82.31 208	87.52 223	63.59 239	86.23 134	93.96 42	73.46 169	88.07 141	87.83 254	86.46 54	90.87 201	76.17 158	93.89 196	92.47 171

bld_raw_conf03		83.86 154	83.99 152	83.45 178	88.77 193	62.26 261	91.49 37	92.62 97	65.43 266	88.07 141	92.18 155	68.44 244	95.51 45	74.78 174	94.16 188	92.58 163

v148		82.31 178	82.48 178	81.81 217	85.59 266	59.66 293	81.47 236	86.02 239	72.85 184	88.05 144	90.65 205	70.73 231	90.91 198	75.15 170	91.79 241	94.87 67

AllTest		87.97 78	87.40 87	89.68 52	91.59 122	83.40 49	89.50 79	95.44 11	79.47 96	88.00 145	93.03 122	82.66 91	91.47 178	70.81 213	96.14 112	94.16 95

TestCases				89.68 52	91.59 122	83.40 49		95.44 11	79.47 96	88.00 145	93.03 122	82.66 91	91.47 178	70.81 213	96.14 112	94.16 95

pm-mvs1		83.69 156	84.95 131	79.91 244	90.04 166	59.66 293	82.43 219	87.44 213	75.52 146	87.85 147	95.26 41	81.25 118	85.65 302	68.74 240	96.04 117	94.42 85

PCF-MVS	74.62 15	82.15 184	80.92 205	85.84 120	89.43 175	72.30 153	80.53 247	91.82 122	57.36 336	87.81 148	89.92 222	77.67 150	93.63 112	58.69 314	95.08 156	91.58 207
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_fmvsmconf_n		85.88 108	85.51 121	86.99 95	84.77 278	78.21 88	85.40 147	91.39 134	65.32 272	87.72 149	91.81 164	82.33 98	89.78 234	86.68 34	94.20 186	92.99 148

FMVSNet2		81.31 198	81.61 190	80.41 238	86.38 247	58.75 307	83.93 175	86.58 231	72.43 190	87.65 150	92.98 124	63.78 267	90.22 218	66.86 251	93.92 195	92.27 183

GeoE		85.45 114	85.81 115	84.37 147	90.08 162	67.07 205	85.86 138	91.39 134	72.33 195	87.59 151	90.25 214	84.85 68	92.37 156	78.00 136	91.94 240	93.66 119

VPA-MVSNet		83.47 163	84.73 133	79.69 248	90.29 158	57.52 316	81.30 239	88.69 197	76.29 132	87.58 152	94.44 67	80.60 126	87.20 271	66.60 256	96.82 87	94.34 88

CPTT-MVS		89.39 55	88.98 67	90.63 37	95.09 33	86.95 13	92.09 29	92.30 107	79.74 93	87.50 153	92.38 145	81.42 116	93.28 130	83.07 75	97.24 76	91.67 204

VDDNet		84.35 137	85.39 124	81.25 223	95.13 32	59.32 296	85.42 146	81.11 292	86.41 30	87.41 154	96.21 20	73.61 198	90.61 210	66.33 258	96.85 84	93.81 114

c3_l		81.64 194	81.59 191	81.79 218	80.86 331	59.15 300	78.61 277	90.18 173	68.36 235	87.20 155	87.11 270	69.39 237	91.62 175	78.16 133	94.43 180	94.60 75

VDD-MVS		84.23 143	84.58 139	83.20 186	91.17 140	65.16 225	83.25 194	84.97 260	79.79 92	87.18 156	94.27 75	74.77 186	90.89 199	69.24 230	96.54 95	93.55 129

MSLP-MVS++		85.00 125	86.03 109	81.90 212	91.84 117	71.56 166	86.75 125	93.02 85	75.95 139	87.12 157	89.39 228	77.98 145	89.40 245	77.46 143	94.78 170	84.75 315

baseline		85.20 119	85.93 111	83.02 189	86.30 252	62.37 258	84.55 160	93.96 42	74.48 157	87.12 157	92.03 156	82.30 100	91.94 167	78.39 126	94.21 185	94.74 73

YYNet1		70.06 320	70.44 313	68.90 347	73.76 386	53.42 344	58.99 394	67.20 377	58.42 326	87.10 159	85.39 295	59.82 290	67.32 383	59.79 310	83.50 354	85.96 300

MDA-MVSNet_test_wron		70.05 321	70.44 313	68.88 348	73.84 385	53.47 342	58.93 395	67.28 376	58.43 325	87.09 160	85.40 294	59.80 291	67.25 384	59.66 311	83.54 353	85.92 302

test_fmvs3		75.72 269	75.20 269	77.27 285	75.01 382	69.47 182	78.93 270	84.88 261	46.67 381	87.08 161	87.84 253	50.44 341	71.62 367	77.42 146	88.53 291	90.72 226

CNVR-MVS		87.81 81	87.68 81	88.21 80	92.87 81	77.30 104	85.25 148	91.23 139	77.31 126	87.07 162	91.47 173	82.94 88	94.71 74	84.67 61	96.27 107	92.62 162

EPP-MVSNet		85.47 113	85.04 129	86.77 100	91.52 130	69.37 183	91.63 36	87.98 210	81.51 75	87.05 163	91.83 162	66.18 255	95.29 55	70.75 216	96.89 83	95.64 46

TinyColmap		81.25 199	82.34 180	77.99 275	85.33 269	60.68 283	82.32 222	88.33 203	71.26 207	86.97 164	92.22 154	77.10 159	86.98 275	62.37 291	95.17 152	86.31 298

eth_miper_zixun_eth		80.84 204	80.22 216	82.71 199	81.41 323	60.98 279	77.81 286	90.14 174	67.31 250	86.95 165	87.24 267	64.26 263	92.31 158	75.23 169	91.61 245	94.85 71

Anonymous20240521		80.18 221	81.25 199	76.95 288	83.15 309	60.84 281	82.46 218	85.99 240	68.76 232	86.78 166	93.73 107	59.13 295	77.44 351	73.71 188	97.55 66	92.56 165

Patchmatch-RL test		74.48 282	73.68 281	76.89 291	84.83 276	66.54 211	72.29 346	69.16 371	57.70 332	86.76 167	86.33 279	45.79 361	82.59 325	69.63 227	90.65 269	81.54 359

XVG-OURS-SEG-HR		89.59 52	89.37 59	90.28 43	94.47 43	85.95 24	86.84 120	93.91 45	80.07 91	86.75 168	93.26 114	93.64 2	90.93 196	84.60 62	90.75 265	93.97 102

h-mvs33		84.25 141	82.76 171	88.72 70	91.82 119	82.60 57	84.00 172	84.98 259	71.27 205	86.70 169	90.55 207	63.04 273	93.92 102	78.26 131	94.20 186	89.63 250

hse-mvs2		83.47 163	81.81 186	88.47 74	91.03 143	82.27 58	82.61 211	83.69 271	71.27 205	86.70 169	86.05 285	63.04 273	92.41 154	78.26 131	93.62 205	90.71 227

HPM-MVS++		88.93 65	88.45 74	90.38 41	94.92 36	85.85 28	89.70 70	91.27 138	78.20 115	86.69 171	92.28 151	80.36 128	95.06 66	86.17 44	96.49 97	90.22 240

TSAR-MVS + MP.		88.14 73	87.82 80	89.09 64	95.72 22	76.74 109	92.49 24	91.19 141	67.85 245	86.63 172	94.84 51	79.58 135	95.96 15	87.62 16	94.50 177	94.56 76
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EI-MVSNet		82.61 173	82.42 179	83.20 186	83.25 305	63.66 237	83.50 187	85.07 254	76.06 134	86.55 173	85.10 299	73.41 203	90.25 215	78.15 135	90.67 267	95.68 45

HQP_MVS		87.75 82	87.43 86	88.70 72	93.45 65	76.42 113	89.45 81	93.61 57	79.44 98	86.55 173	92.95 127	74.84 183	95.22 58	80.78 103	95.83 130	94.46 80

plane_prior3						76.85 108			77.79 120	86.55 173

BH-untuned		80.96 203	80.99 203	80.84 231	88.55 199	68.23 193	80.33 250	88.46 199	72.79 187	86.55 173	86.76 274	74.72 187	91.77 174	61.79 298	88.99 285	82.52 349

MVSTER		77.09 252	75.70 264	81.25 223	75.27 379	61.08 275	77.49 293	85.07 254	60.78 311	86.55 173	88.68 240	43.14 380	90.25 215	73.69 189	90.67 267	92.42 172

旧先验2							81.73 232		56.88 340	86.54 178			84.90 308	72.81 202

IterMVS-SCA-FT		80.64 208	79.41 225	84.34 151	83.93 293	69.66 180	76.28 310	81.09 293	72.43 190	86.47 179	90.19 216	60.46 283	93.15 135	77.45 144	86.39 323	90.22 240

WB-MVS		76.06 265	80.01 222	64.19 370	89.96 168	20.58 412	72.18 347	68.19 373	83.21 57	86.46 180	93.49 111	70.19 234	78.97 346	65.96 260	90.46 271	93.02 146

test_fmvsm_n_1920		83.60 159	82.89 169	85.74 122	85.22 272	77.74 96	84.12 169	90.48 158	59.87 320	86.45 181	91.12 183	75.65 174	85.89 298	82.28 88	90.87 261	93.58 125

DIV-MVS_self_test		80.43 211	80.23 214	81.02 229	79.99 339	59.25 297	77.07 297	87.02 225	67.38 247	86.19 182	89.22 231	63.09 271	90.16 220	76.32 155	95.80 132	93.66 119

CDPH-MVS		86.17 104	85.54 120	88.05 83	92.25 98	75.45 121	83.85 177	92.01 114	65.91 259	86.19 182	91.75 167	83.77 79	94.98 68	77.43 145	96.71 90	93.73 117

cl____		80.42 212	80.23 214	81.02 229	79.99 339	59.25 297	77.07 297	87.02 225	67.37 248	86.18 184	89.21 232	63.08 272	90.16 220	76.31 156	95.80 132	93.65 121

MVS_111021_LR		84.28 140	83.76 156	85.83 121	89.23 180	83.07 52	80.99 243	83.56 273	72.71 188	86.07 185	89.07 235	81.75 113	86.19 291	77.11 149	93.36 206	88.24 271

GBi-Net		82.02 187	82.07 181	81.85 214	86.38 247	61.05 276	86.83 121	88.27 205	72.43 190	86.00 186	95.64 32	63.78 267	90.68 207	65.95 261	93.34 207	93.82 111

test1		82.02 187	82.07 181	81.85 214	86.38 247	61.05 276	86.83 121	88.27 205	72.43 190	86.00 186	95.64 32	63.78 267	90.68 207	65.95 261	93.34 207	93.82 111

FMVSNet3		78.80 234	78.55 237	79.57 250	82.89 312	56.89 322	81.76 231	85.77 242	69.04 229	86.00 186	90.44 209	51.75 334	90.09 226	65.95 261	93.34 207	91.72 201

miper_ehance_all_eth		80.34 215	80.04 221	81.24 225	79.82 341	58.95 302	77.66 288	89.66 183	65.75 263	85.99 189	85.11 298	68.29 245	91.42 182	76.03 160	92.03 236	93.33 132

tfpnnormal		81.79 193	82.95 168	78.31 267	88.93 187	55.40 330	80.83 246	82.85 279	76.81 129	85.90 190	94.14 85	74.58 189	86.51 284	66.82 254	95.68 138	93.01 147

TAPA-MVS	77.73 12	85.71 110	84.83 132	88.37 77	88.78 192	79.72 74	87.15 115	93.50 60	69.17 226	85.80 191	89.56 227	80.76 123	92.13 162	73.21 200	95.51 139	93.25 137
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TSAR-MVS + GP.		83.95 151	82.69 173	87.72 86	89.27 179	81.45 64	83.72 182	81.58 291	74.73 154	85.66 192	86.06 284	72.56 216	92.69 148	75.44 167	95.21 150	89.01 266

EU-MVSNet		75.12 274	74.43 276	77.18 286	83.11 310	59.48 295	85.71 142	82.43 283	39.76 401	85.64 193	88.76 238	44.71 373	87.88 263	73.86 185	85.88 329	84.16 325

LF4IMVS		82.75 172	81.93 184	85.19 130	82.08 314	80.15 71	85.53 143	88.76 196	68.01 240	85.58 194	87.75 255	71.80 226	86.85 278	74.02 182	93.87 197	88.58 269

Patchmtry		76.56 260	77.46 246	73.83 313	79.37 347	46.60 379	82.41 220	76.90 318	73.81 163	85.56 195	92.38 145	48.07 348	83.98 318	63.36 286	95.31 147	90.92 221

MVS_111021_HR		84.63 130	84.34 147	85.49 128	90.18 161	75.86 120	79.23 268	87.13 220	73.35 173	85.56 195	89.34 229	83.60 82	90.50 212	76.64 153	94.05 193	90.09 245

testdata				79.54 251	92.87 81	72.34 152		80.14 299	59.91 319	85.47 197	91.75 167	67.96 247	85.24 304	68.57 244	92.18 235	81.06 368

mvsmamba		80.30 217	78.87 230	84.58 143	88.12 209	67.55 201	92.35 26	84.88 261	63.15 282	85.33 198	90.91 192	50.71 338	95.20 61	66.36 257	87.98 301	90.99 218

test1111		78.53 238	78.85 232	77.56 281	92.22 100	47.49 375	82.61 211	69.24 370	72.43 190	85.28 199	94.20 81	51.91 332	90.07 227	65.36 269	96.45 100	95.11 62

thisisatest0530		79.07 229	77.33 249	84.26 154	87.13 231	64.58 228	83.66 184	75.95 324	68.86 231	85.22 200	87.36 264	38.10 388	93.57 120	75.47 166	94.28 184	94.62 74

EC-MVSNet		88.01 76	88.32 75	87.09 92	89.28 178	72.03 157	90.31 58	96.31 4	80.88 82	85.12 201	89.67 226	84.47 72	95.46 49	82.56 84	96.26 108	93.77 116

CLD-MVS		83.18 167	82.64 174	84.79 137	89.05 182	67.82 200	77.93 284	92.52 100	68.33 236	85.07 202	81.54 341	82.06 105	92.96 140	69.35 229	97.91 48	93.57 126
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
fmvsm_s_conf0.1_n_a		82.58 175	81.93 184	84.50 144	87.68 218	73.35 133	86.14 135	77.70 310	61.64 299	85.02 203	91.62 169	77.75 148	86.24 288	82.79 81	87.07 312	93.91 106

FA-MVS(test-final)		83.13 169	83.02 167	83.43 179	86.16 259	66.08 216	88.00 102	88.36 202	75.55 145	85.02 203	92.75 135	65.12 260	92.50 152	74.94 173	91.30 251	91.72 201

DeepC-MVS_fast	80.27 8	86.23 100	85.65 119	87.96 84	91.30 134	76.92 107	87.19 113	91.99 115	70.56 213	84.96 205	90.69 201	80.01 132	95.14 63	78.37 127	95.78 134	91.82 199
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	80.37 7	84.80 127	84.71 136	85.06 133	86.36 250	74.71 124	88.77 93	90.00 177	75.65 144	84.96 205	93.17 116	74.06 193	91.19 187	78.28 130	91.09 253	89.29 258

QAPM		82.59 174	82.59 176	82.58 202	86.44 245	66.69 210	89.94 66	90.36 163	67.97 242	84.94 207	92.58 140	72.71 213	92.18 161	70.63 219	87.73 305	88.85 267

VPNet		80.25 218	81.68 187	75.94 301	92.46 92	47.98 373	76.70 302	81.67 289	73.45 170	84.87 208	92.82 131	74.66 188	86.51 284	61.66 300	96.85 84	93.33 132

NCCC		87.36 85	86.87 96	88.83 67	92.32 97	78.84 83	86.58 128	91.09 143	78.77 109	84.85 209	90.89 193	80.85 122	95.29 55	81.14 98	95.32 145	92.34 178

PHI-MVS		86.38 98	85.81 115	88.08 81	88.44 202	77.34 102	89.35 84	93.05 81	73.15 181	84.76 210	87.70 256	78.87 139	94.18 92	80.67 105	96.29 104	92.73 155

pmmvs-eth3d		78.42 240	77.04 251	82.57 204	87.44 225	74.41 126	80.86 245	79.67 301	55.68 343	84.69 211	90.31 213	60.91 281	85.42 303	62.20 293	91.59 246	87.88 281

test_prior2							83.37 190		75.43 147	84.58 212	91.57 170	81.92 110		79.54 117	96.97 82

fmvsm_s_conf0.5_n_a		82.21 181	81.51 195	84.32 152	86.56 243	73.35 133	85.46 144	77.30 314	61.81 295	84.51 213	90.88 195	77.36 154	86.21 290	82.72 82	86.97 317	93.38 130

TEST9					92.34 95	79.70 75	83.94 173	90.32 164	65.41 270	84.49 214	90.97 188	82.03 106	93.63 112

train_agg		85.98 106	85.28 126	88.07 82	92.34 95	79.70 75	83.94 173	90.32 164	65.79 260	84.49 214	90.97 188	81.93 108	93.63 112	81.21 97	96.54 95	90.88 222

fmvsm_s_conf0.1_n		82.17 183	81.59 191	83.94 163	86.87 241	71.57 165	85.19 150	77.42 313	62.27 293	84.47 216	91.33 176	76.43 170	85.91 296	83.14 72	87.14 310	94.33 89

Gipuma		84.44 135	86.33 103	78.78 258	84.20 289	73.57 131	89.55 76	90.44 160	84.24 46	84.38 217	94.89 49	76.35 173	80.40 339	76.14 159	96.80 88	82.36 351
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		64.31 356	65.85 346	59.67 381	66.54 406	62.24 264	57.76 397	70.96 362	40.13 399	84.36 218	82.09 334	46.93 350	51.67 405	61.99 296	81.89 364	65.12 396

test_8					92.09 104	78.87 82	83.82 178	90.31 166	65.79 260	84.36 218	90.96 190	81.93 108	93.44 125

cl22		78.97 230	78.21 242	81.24 225	77.74 355	59.01 301	77.46 294	87.13 220	65.79 260	84.32 220	85.10 299	58.96 297	90.88 200	75.36 168	92.03 236	93.84 109

CS-MVS		88.14 73	87.67 82	89.54 57	89.56 171	79.18 79	90.47 54	94.77 17	79.37 100	84.32 220	89.33 230	83.87 76	94.53 83	82.45 85	94.89 165	94.90 65

agg_prior					91.58 125	77.69 97		90.30 167		84.32 220			93.18 133

Anonymous202405211		80.51 210	81.19 202	78.49 264	88.48 200	57.26 318	76.63 304	82.49 282	81.21 78	84.30 223	92.24 153	67.99 246	86.24 288	62.22 292	95.13 153	91.98 196

LFMVS		80.15 222	80.56 208	78.89 256	89.19 181	55.93 326	85.22 149	73.78 341	82.96 61	84.28 224	92.72 136	57.38 307	90.07 227	63.80 282	95.75 135	90.68 229

Vis-MVSNet		86.86 90	86.58 99	87.72 86	92.09 104	77.43 101	87.35 112	92.09 112	78.87 107	84.27 225	94.05 88	78.35 143	93.65 110	80.54 107	91.58 247	92.08 191
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ECVR-MVS		78.44 239	78.63 236	77.88 277	91.85 115	48.95 369	83.68 183	69.91 367	72.30 196	84.26 226	94.20 81	51.89 333	89.82 232	63.58 283	96.02 118	94.87 67

FE-MVS		79.98 225	78.86 231	83.36 181	86.47 244	66.45 213	89.73 69	84.74 265	72.80 186	84.22 227	91.38 175	44.95 371	93.60 116	63.93 281	91.50 248	90.04 246

ETV-MVS		84.31 138	83.91 155	85.52 126	88.58 198	70.40 174	84.50 164	93.37 62	78.76 110	84.07 228	78.72 365	80.39 127	95.13 64	73.82 186	92.98 218	91.04 217

fmvsm_s_conf0.5_n		81.91 191	81.30 198	83.75 167	86.02 261	71.56 166	84.73 156	77.11 317	62.44 290	84.00 229	90.68 202	76.42 171	85.89 298	83.14 72	87.11 311	93.81 114

MCST-MVS		84.36 136	83.93 154	85.63 124	91.59 122	71.58 164	83.52 186	92.13 111	61.82 294	83.96 230	89.75 225	79.93 134	93.46 124	78.33 129	94.34 182	91.87 198

新几何1				82.95 193	93.96 56	78.56 85		80.24 298	55.45 344	83.93 231	91.08 185	71.19 229	88.33 259	65.84 264	93.07 215	81.95 355

fmvsm_l_conf0.5_n		82.06 186	81.54 194	83.60 172	83.94 292	73.90 129	83.35 191	86.10 236	58.97 322	83.80 232	90.36 210	74.23 191	86.94 276	82.90 78	90.22 272	89.94 247

BH-RMVSNet		80.53 209	80.22 216	81.49 221	87.19 230	66.21 215	77.79 287	86.23 234	74.21 159	83.69 233	88.50 242	73.25 208	90.75 204	63.18 288	87.90 302	87.52 285

USDC		76.63 258	76.73 255	76.34 297	83.46 299	57.20 319	80.02 253	88.04 209	52.14 363	83.65 234	91.25 178	63.24 270	86.65 282	54.66 341	94.11 190	85.17 310

miper_enhance_ethall		77.83 243	76.93 252	80.51 236	76.15 371	58.01 312	75.47 322	88.82 194	58.05 330	83.59 235	80.69 345	64.41 262	91.20 186	73.16 201	92.03 236	92.33 179

MM		87.64 83	87.15 88	89.09 64	89.51 172	76.39 115	88.68 95	86.76 229	84.54 44	83.58 236	93.78 104	73.36 206	96.48 2	87.98 10	96.21 109	94.41 86

Effi-MVS+-dtu		85.82 109	83.38 159	93.14 4	87.13 231	91.15 3	87.70 107	88.42 200	74.57 156	83.56 237	85.65 289	78.49 142	94.21 90	72.04 207	92.88 220	94.05 100

CNLPA		83.55 161	83.10 166	84.90 134	89.34 177	83.87 47	84.54 162	88.77 195	79.09 103	83.54 238	88.66 241	74.87 182	81.73 330	66.84 253	92.29 230	89.11 260

SDMVSNet		81.90 192	83.17 164	78.10 272	88.81 190	62.45 256	76.08 314	86.05 238	73.67 165	83.41 239	93.04 120	82.35 97	80.65 337	70.06 224	95.03 158	91.21 213

sd_testset		79.95 226	81.39 197	75.64 304	88.81 190	58.07 311	76.16 313	82.81 280	73.67 165	83.41 239	93.04 120	80.96 121	77.65 350	58.62 315	95.03 158	91.21 213

OpenMVS_ROB	70.19 17	77.77 246	77.46 246	78.71 260	84.39 285	61.15 274	81.18 241	82.52 281	62.45 289	83.34 241	87.37 263	66.20 254	88.66 256	64.69 276	85.02 339	86.32 297

thres100view900		75.45 270	75.05 270	76.66 294	87.27 227	51.88 355	81.07 242	73.26 346	75.68 143	83.25 242	86.37 278	45.54 362	88.80 251	51.98 357	90.99 255	89.31 256

miper_lstm_enhance		76.45 262	76.10 260	77.51 282	76.72 366	60.97 280	64.69 381	85.04 256	63.98 279	83.20 243	88.22 245	56.67 311	78.79 348	73.22 195	93.12 214	92.78 154

IterMVS		76.91 254	76.34 258	78.64 261	80.91 329	64.03 234	76.30 309	79.03 304	64.88 275	83.11 244	89.16 233	59.90 289	84.46 311	68.61 242	85.15 337	87.42 286
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres600view7		75.97 266	75.35 268	77.85 279	87.01 237	51.84 356	80.45 248	73.26 346	75.20 150	83.10 245	86.31 281	45.54 362	89.05 247	55.03 339	92.24 232	92.66 160

mvs_anonymous		78.13 241	78.76 234	76.23 300	79.24 348	50.31 366	78.69 275	84.82 263	61.60 300	83.09 246	92.82 131	73.89 196	87.01 272	68.33 246	86.41 322	91.37 210

fmvsm_l_conf0.5_n_a		81.46 196	80.87 206	83.25 184	83.73 297	73.21 138	83.00 202	85.59 246	58.22 328	82.96 247	90.09 220	72.30 218	86.65 282	81.97 93	89.95 276	89.88 248

test_fmvs2		73.57 289	72.80 291	75.90 302	72.74 394	68.84 191	77.07 297	84.32 268	45.14 387	82.89 248	84.22 311	48.37 346	70.36 370	73.40 193	87.03 314	88.52 270

MVS_Test		82.47 177	83.22 161	80.22 241	82.62 313	57.75 315	82.54 216	91.96 117	71.16 209	82.89 248	92.52 142	77.41 153	90.50 212	80.04 110	87.84 304	92.40 175

test12				86.57 102	90.74 149	72.63 145		90.69 153		82.76 250		79.20 136	94.80 72		95.32 145	92.27 183

原ACMM1				84.60 142	92.81 86	74.01 128		91.50 129	62.59 285	82.73 251	90.67 204	76.53 169	94.25 88	69.24 230	95.69 137	85.55 306

test_yl		78.71 236	78.51 238	79.32 253	84.32 286	58.84 304	78.38 278	85.33 249	75.99 137	82.49 252	86.57 275	58.01 301	90.02 229	62.74 289	92.73 223	89.10 261

DCV-MVSNet		78.71 236	78.51 238	79.32 253	84.32 286	58.84 304	78.38 278	85.33 249	75.99 137	82.49 252	86.57 275	58.01 301	90.02 229	62.74 289	92.73 223	89.10 261

diffmvs		80.40 213	80.48 211	80.17 242	79.02 351	60.04 288	77.54 291	90.28 170	66.65 255	82.40 254	87.33 265	73.50 200	87.35 269	77.98 137	89.62 279	93.13 141
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test222					93.31 70	76.54 110	79.38 263	77.79 309	52.59 358	82.36 255	90.84 197	66.83 252			91.69 243	81.25 363

D2MVS		76.84 255	75.67 265	80.34 239	80.48 337	62.16 265	73.50 339	84.80 264	57.61 334	82.24 256	87.54 259	51.31 335	87.65 265	70.40 222	93.19 213	91.23 212

VNet		79.31 228	80.27 213	76.44 295	87.92 213	53.95 339	75.58 320	84.35 267	74.39 158	82.23 257	90.72 200	72.84 212	84.39 313	60.38 308	93.98 194	90.97 219

Vis-MVSNet (Re-imp)		77.82 244	77.79 245	77.92 276	88.82 189	51.29 360	83.28 192	71.97 355	74.04 160	82.23 257	89.78 224	57.38 307	89.41 244	57.22 323	95.41 141	93.05 145

API-MVS		82.28 179	82.61 175	81.30 222	86.29 253	69.79 177	88.71 94	87.67 212	78.42 114	82.15 259	84.15 313	77.98 145	91.59 176	65.39 268	92.75 222	82.51 350

DP-MVS Recon		84.05 148	83.22 161	86.52 104	91.73 120	75.27 122	83.23 196	92.40 102	72.04 199	82.04 260	88.33 244	77.91 147	93.95 101	66.17 259	95.12 155	90.34 239

MSDG		80.06 224	79.99 223	80.25 240	83.91 294	68.04 198	77.51 292	89.19 191	77.65 121	81.94 261	83.45 319	76.37 172	86.31 287	63.31 287	86.59 320	86.41 296

test2506		74.12 285	73.39 285	76.28 298	91.85 115	44.20 389	84.06 170	48.20 408	72.30 196	81.90 262	94.20 81	27.22 409	89.77 235	64.81 274	96.02 118	94.87 67

Fast-Effi-MVS+		81.04 202	80.57 207	82.46 206	87.50 224	63.22 244	78.37 280	89.63 185	68.01 240	81.87 263	82.08 335	82.31 99	92.65 149	67.10 250	88.30 298	91.51 209

testgi		72.36 299	74.61 272	65.59 364	80.56 336	42.82 394	68.29 369	73.35 345	66.87 253	81.84 264	89.93 221	72.08 223	66.92 386	46.05 383	92.54 225	87.01 291

tfpn200view9		74.86 278	74.23 277	76.74 293	86.24 254	52.12 352	79.24 266	73.87 339	73.34 174	81.82 265	84.60 308	46.02 356	88.80 251	51.98 357	90.99 255	89.31 256

thres400		75.14 272	74.23 277	77.86 278	86.24 254	52.12 352	79.24 266	73.87 339	73.34 174	81.82 265	84.60 308	46.02 356	88.80 251	51.98 357	90.99 255	92.66 160

CL-MVSNet_self_test		76.81 256	77.38 248	75.12 307	86.90 239	51.34 358	73.20 342	80.63 297	68.30 237	81.80 267	88.40 243	66.92 251	80.90 334	55.35 336	94.90 164	93.12 143

OpenMVS	76.72 13	81.98 189	82.00 183	81.93 211	84.42 284	68.22 194	88.50 98	89.48 188	66.92 252	81.80 267	91.86 159	72.59 215	90.16 220	71.19 212	91.25 252	87.40 287

MVS_0304		85.37 115	84.58 139	87.75 85	85.28 270	73.36 132	86.54 130	85.71 243	77.56 124	81.78 269	92.47 143	70.29 233	96.02 11	85.59 50	95.96 121	93.87 108

AdaColmap		83.66 157	83.69 157	83.57 175	90.05 165	72.26 154	86.29 133	90.00 177	78.19 116	81.65 270	87.16 268	83.40 84	94.24 89	61.69 299	94.76 173	84.21 324

CS-MVS-test		87.00 88	86.43 102	88.71 71	89.46 174	77.46 99	89.42 83	95.73 8	77.87 119	81.64 271	87.25 266	82.43 95	94.53 83	77.65 140	96.46 99	94.14 97

DELS-MVS		81.44 197	81.25 199	82.03 210	84.27 288	62.87 248	76.47 308	92.49 101	70.97 210	81.64 271	83.83 314	75.03 180	92.70 147	74.29 176	92.22 234	90.51 235
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
114514_t		83.10 170	82.54 177	84.77 138	92.90 80	69.10 190	86.65 126	90.62 156	54.66 349	81.46 273	90.81 198	76.98 161	94.38 85	72.62 203	96.18 110	90.82 224

TR-MVS		76.77 257	75.79 262	79.72 247	86.10 260	65.79 219	77.14 295	83.02 277	65.20 273	81.40 274	82.10 333	66.30 253	90.73 206	55.57 333	85.27 333	82.65 344

TAMVS		78.08 242	76.36 257	83.23 185	90.62 152	72.87 139	79.08 269	80.01 300	61.72 297	81.35 275	86.92 273	63.96 266	88.78 254	50.61 362	93.01 217	88.04 277

Effi-MVS+		83.90 153	84.01 151	83.57 175	87.22 229	65.61 221	86.55 129	92.40 102	78.64 111	81.34 276	84.18 312	83.65 81	92.93 142	74.22 177	87.87 303	92.17 188

testing3		71.53 307	70.79 309	73.77 314	88.89 188	41.86 396	76.60 306	59.12 398	72.83 185	80.97 277	82.08 335	19.80 414	87.33 270	65.12 271	91.68 244	92.13 190

new-patchmatchnet		70.10 319	73.37 286	60.29 380	81.23 326	16.95 415	59.54 391	74.62 332	62.93 283	80.97 277	87.93 251	62.83 275	71.90 365	55.24 337	95.01 161	92.00 194

PVSNet_Blended_VisFu		81.55 195	80.49 210	84.70 141	91.58 125	73.24 137	84.21 166	91.67 126	62.86 284	80.94 279	87.16 268	67.27 249	92.87 145	69.82 226	88.94 287	87.99 278

BH-w/o		76.57 259	76.07 261	78.10 272	86.88 240	65.92 218	77.63 289	86.33 232	65.69 264	80.89 280	79.95 354	68.97 242	90.74 205	53.01 352	85.25 334	77.62 379

PAPM_NR		83.23 166	83.19 163	83.33 182	90.90 146	65.98 217	88.19 100	90.78 151	78.13 117	80.87 281	87.92 252	73.49 202	92.42 153	70.07 223	88.40 292	91.60 206

ab-mvs		79.67 227	80.56 208	76.99 287	88.48 200	56.93 320	84.70 157	86.06 237	68.95 230	80.78 282	93.08 119	75.30 178	84.62 310	56.78 324	90.90 260	89.43 254

XXY-MVS		74.44 284	76.19 259	69.21 345	84.61 280	52.43 351	71.70 350	77.18 316	60.73 312	80.60 283	90.96 190	75.44 175	69.35 373	56.13 329	88.33 294	85.86 303

HQP4-MVS										80.56 284			94.61 78			93.56 127

HQP-NCC					91.19 137		84.77 153		73.30 176	80.55 285

ACMP_Plane					91.19 137		84.77 153		73.30 176	80.55 285

HQP-MVS		84.61 131	84.06 150	86.27 109	91.19 137	70.66 171	84.77 153	92.68 95	73.30 176	80.55 285	90.17 218	72.10 221	94.61 78	77.30 147	94.47 178	93.56 127

test_cas_vis1_n_1920		69.20 331	69.12 324	69.43 344	73.68 387	62.82 249	70.38 362	77.21 315	46.18 384	80.46 288	78.95 363	52.03 331	65.53 391	65.77 266	77.45 386	79.95 374

AUN-MVS		81.18 200	78.78 233	88.39 76	90.93 145	82.14 59	82.51 217	83.67 272	64.69 276	80.29 289	85.91 288	51.07 336	92.38 155	76.29 157	93.63 204	90.65 231

HyFIR lowres test		75.12 274	72.66 294	82.50 205	91.44 133	65.19 224	72.47 345	87.31 215	46.79 380	80.29 289	84.30 310	52.70 329	92.10 165	51.88 361	86.73 318	90.22 240

test20.03		73.75 288	74.59 274	71.22 333	81.11 327	51.12 362	70.15 363	72.10 354	70.42 214	80.28 291	91.50 172	64.21 264	74.72 361	46.96 380	94.58 176	87.82 283

mvsany_test3		65.48 351	62.97 359	73.03 320	69.99 400	76.17 118	64.83 379	43.71 410	43.68 392	80.25 292	87.05 272	52.83 328	63.09 397	51.92 360	72.44 392	79.84 375

F-COLMAP		84.97 126	83.42 158	89.63 54	92.39 93	83.40 49	88.83 91	91.92 118	73.19 180	80.18 293	89.15 234	77.04 160	93.28 130	65.82 265	92.28 231	92.21 186

GA-MVS		75.83 267	74.61 272	79.48 252	81.87 316	59.25 297	73.42 340	82.88 278	68.68 233	79.75 294	81.80 338	50.62 339	89.46 240	66.85 252	85.64 330	89.72 249

xiu_mvs_v1_base_debu		80.84 204	80.14 218	82.93 194	88.31 203	71.73 160	79.53 259	87.17 217	65.43 266	79.59 295	82.73 329	76.94 162	90.14 223	73.22 195	88.33 294	86.90 292

xiu_mvs_v1_base		80.84 204	80.14 218	82.93 194	88.31 203	71.73 160	79.53 259	87.17 217	65.43 266	79.59 295	82.73 329	76.94 162	90.14 223	73.22 195	88.33 294	86.90 292

xiu_mvs_v1_base_debi		80.84 204	80.14 218	82.93 194	88.31 203	71.73 160	79.53 259	87.17 217	65.43 266	79.59 295	82.73 329	76.94 162	90.14 223	73.22 195	88.33 294	86.90 292

test_fmvs1_n		70.94 312	70.41 315	72.53 326	73.92 384	66.93 208	75.99 315	84.21 270	43.31 394	79.40 298	79.39 359	43.47 376	68.55 378	69.05 235	84.91 342	82.10 353

patch_mono-2		78.89 231	79.39 226	77.41 284	84.78 277	68.11 196	75.60 318	83.11 276	60.96 309	79.36 299	89.89 223	75.18 179	72.97 362	73.32 194	92.30 228	91.15 215

UnsupCasMVSNet_eth		71.63 306	72.30 299	69.62 342	76.47 368	52.70 349	70.03 364	80.97 294	59.18 321	79.36 299	88.21 246	60.50 282	69.12 374	58.33 318	77.62 384	87.04 290

ppachtmachnet_test		74.73 281	74.00 279	76.90 290	80.71 334	56.89 322	71.53 353	78.42 306	58.24 327	79.32 301	82.92 326	57.91 304	84.26 315	65.60 267	91.36 250	89.56 251

MG-MVS		80.32 216	80.94 204	78.47 265	88.18 206	52.62 350	82.29 223	85.01 258	72.01 200	79.24 302	92.54 141	69.36 238	93.36 129	70.65 218	89.19 284	89.45 252

Fast-Effi-MVS+-dtu		82.54 176	81.41 196	85.90 118	85.60 265	76.53 112	83.07 199	89.62 186	73.02 183	79.11 303	83.51 317	80.74 124	90.24 217	68.76 239	89.29 281	90.94 220

CDS-MVSNet		77.32 250	75.40 266	83.06 188	89.00 184	72.48 150	77.90 285	82.17 285	60.81 310	78.94 304	83.49 318	59.30 293	88.76 255	54.64 342	92.37 227	87.93 280
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
baseline1		73.26 291	73.54 283	72.43 327	84.92 275	47.79 374	79.89 255	74.00 337	65.93 258	78.81 305	86.28 282	56.36 313	81.63 331	56.63 325	79.04 379	87.87 282

EIA-MVS		82.19 182	81.23 201	85.10 132	87.95 212	69.17 189	83.22 197	93.33 65	70.42 214	78.58 306	79.77 357	77.29 155	94.20 91	71.51 209	88.96 286	91.93 197

thres200		72.34 300	71.55 306	74.70 310	83.48 298	51.60 357	75.02 325	73.71 342	70.14 220	78.56 307	80.57 348	46.20 354	88.20 261	46.99 379	89.29 281	84.32 321

our_test_3		71.85 303	71.59 303	72.62 324	80.71 334	53.78 340	69.72 365	71.71 359	58.80 324	78.03 308	80.51 350	56.61 312	78.84 347	62.20 293	86.04 328	85.23 309

KD-MVS_2432*1600		66.87 341	65.81 347	70.04 338	67.50 403	47.49 375	62.56 385	79.16 302	61.21 307	77.98 309	80.61 346	25.29 411	82.48 326	53.02 350	84.92 340	80.16 372

miper_refine_blended		66.87 341	65.81 347	70.04 338	67.50 403	47.49 375	62.56 385	79.16 302	61.21 307	77.98 309	80.61 346	25.29 411	82.48 326	53.02 350	84.92 340	80.16 372

jason		77.42 249	75.75 263	82.43 207	87.10 234	69.27 184	77.99 283	81.94 287	51.47 367	77.84 311	85.07 302	60.32 285	89.00 248	70.74 217	89.27 283	89.03 264
jason: jason.
MAR-MVS		80.24 219	78.74 235	84.73 139	86.87 241	78.18 89	85.75 140	87.81 211	65.67 265	77.84 311	78.50 366	73.79 197	90.53 211	61.59 301	90.87 261	85.49 308
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
FPMVS		72.29 301	72.00 300	73.14 318	88.63 196	85.00 37	74.65 329	67.39 375	71.94 201	77.80 313	87.66 257	50.48 340	75.83 357	49.95 364	79.51 373	58.58 402

test_fmvs1		69.57 326	69.05 326	71.14 335	69.15 402	65.77 220	73.98 334	83.32 274	42.83 396	77.77 314	78.27 368	43.39 379	68.50 379	68.39 245	84.38 349	79.15 376

pmmvs4		74.92 277	72.98 290	80.73 233	84.95 274	71.71 163	76.23 311	77.59 311	52.83 357	77.73 315	86.38 277	56.35 314	84.97 307	57.72 322	87.05 313	85.51 307

ET-MVSNet_ETH3D		75.28 271	72.77 292	82.81 198	83.03 311	68.11 196	77.09 296	76.51 322	60.67 313	77.60 316	80.52 349	38.04 389	91.15 189	70.78 215	90.68 266	89.17 259

UnsupCasMVSNet_bld		69.21 330	69.68 322	67.82 355	79.42 345	51.15 361	67.82 373	75.79 325	54.15 351	77.47 317	85.36 297	59.26 294	70.64 369	48.46 373	79.35 375	81.66 357

Anonymous20231206		71.38 309	71.88 301	69.88 340	86.31 251	54.37 336	70.39 361	74.62 332	52.57 359	76.73 318	88.76 238	59.94 288	72.06 364	44.35 387	93.23 212	83.23 340

CMPMVS	59.41 20	75.12 274	73.57 282	79.77 245	75.84 374	67.22 202	81.21 240	82.18 284	50.78 372	76.50 319	87.66 257	55.20 321	82.99 324	62.17 295	90.64 270	89.09 263
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		72.10 302	71.69 302	73.32 316	81.57 321	53.02 346	76.77 301	78.37 307	63.31 280	76.37 320	91.85 160	36.68 392	78.98 345	47.87 376	92.45 226	87.95 279

CVMVSNet		72.62 297	71.41 307	76.28 298	83.25 305	60.34 286	83.50 187	79.02 305	37.77 405	76.33 321	85.10 299	49.60 344	87.41 268	70.54 220	77.54 385	81.08 366

PLC	73.85 16	82.09 185	80.31 212	87.45 89	90.86 148	80.29 70	85.88 137	90.65 154	68.17 239	76.32 322	86.33 279	73.12 209	92.61 150	61.40 302	90.02 275	89.44 253
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSFormer		82.23 180	81.57 193	84.19 158	85.54 267	69.26 185	91.98 31	90.08 175	71.54 202	76.23 323	85.07 302	58.69 298	94.27 86	86.26 40	88.77 288	89.03 264

lupinMVS		76.37 263	74.46 275	82.09 209	85.54 267	69.26 185	76.79 300	80.77 296	50.68 374	76.23 323	82.82 327	58.69 298	88.94 249	69.85 225	88.77 288	88.07 274

UWE-MVS		66.43 345	65.56 350	69.05 346	84.15 290	40.98 397	73.06 344	64.71 385	54.84 348	76.18 325	79.62 358	29.21 403	80.50 338	38.54 398	89.75 277	85.66 305

PatchMatch-RL		74.48 282	73.22 287	78.27 270	87.70 217	85.26 35	75.92 316	70.09 365	64.34 277	76.09 326	81.25 343	65.87 257	78.07 349	53.86 344	83.82 352	71.48 388

thisisatest0515		73.00 295	70.52 312	80.46 237	81.45 322	59.90 291	73.16 343	74.31 336	57.86 331	76.08 327	77.78 370	37.60 391	92.12 164	65.00 272	91.45 249	89.35 255

MS-PatchMatch		70.93 313	70.22 316	73.06 319	81.85 317	62.50 255	73.82 337	77.90 308	52.44 360	75.92 328	81.27 342	55.67 318	81.75 329	55.37 335	77.70 383	74.94 384

CHOSEN 1792x2688		72.45 298	70.56 311	78.13 271	90.02 167	63.08 245	68.72 368	83.16 275	42.99 395	75.92 328	85.46 292	57.22 309	85.18 306	49.87 366	81.67 365	86.14 299

CR-MVSNet		74.00 286	73.04 289	76.85 292	79.58 342	62.64 252	82.58 213	76.90 318	50.50 375	75.72 330	92.38 145	48.07 348	84.07 317	68.72 241	82.91 358	83.85 329

RPMNet		78.88 232	78.28 241	80.68 235	79.58 342	62.64 252	82.58 213	94.16 30	74.80 153	75.72 330	92.59 138	48.69 345	95.56 40	73.48 191	82.91 358	83.85 329

DPM-MVS		80.10 223	79.18 228	82.88 197	90.71 151	69.74 178	78.87 273	90.84 149	60.29 316	75.64 332	85.92 287	67.28 248	93.11 136	71.24 211	91.79 241	85.77 304

test_vis1_n		70.29 316	69.99 320	71.20 334	75.97 373	66.50 212	76.69 303	80.81 295	44.22 390	75.43 333	77.23 376	50.00 342	68.59 377	66.71 255	82.85 360	78.52 378

PVSNet_BlendedMVS		78.80 234	77.84 244	81.65 219	84.43 282	63.41 240	79.49 262	90.44 160	61.70 298	75.43 333	87.07 271	69.11 240	91.44 180	60.68 306	92.24 232	90.11 244

PVSNet_Blended		76.49 261	75.40 266	79.76 246	84.43 282	63.41 240	75.14 324	90.44 160	57.36 336	75.43 333	78.30 367	69.11 240	91.44 180	60.68 306	87.70 306	84.42 320

PAPR		78.84 233	78.10 243	81.07 227	85.17 273	60.22 287	82.21 227	90.57 157	62.51 286	75.32 336	84.61 307	74.99 181	92.30 159	59.48 312	88.04 300	90.68 229

N_pmnet		70.20 317	68.80 331	74.38 311	80.91 329	84.81 40	59.12 393	76.45 323	55.06 346	75.31 337	82.36 332	55.74 317	54.82 403	47.02 378	87.24 309	83.52 333

cascas		76.29 264	74.81 271	80.72 234	84.47 281	62.94 246	73.89 336	87.34 214	55.94 342	75.16 338	76.53 382	63.97 265	91.16 188	65.00 272	90.97 258	88.06 276

SCA		73.32 290	72.57 296	75.58 305	81.62 320	55.86 327	78.89 272	71.37 360	61.73 296	74.93 339	83.42 320	60.46 283	87.01 272	58.11 320	82.63 363	83.88 326

test_vis1_n_1920		71.30 310	71.58 305	70.47 336	77.58 358	59.99 290	74.25 330	84.22 269	51.06 369	74.85 340	79.10 361	55.10 322	68.83 376	68.86 238	79.20 378	82.58 346

xiu_mvs_v2_base		77.19 251	76.75 254	78.52 263	87.01 237	61.30 272	75.55 321	87.12 223	61.24 306	74.45 341	78.79 364	77.20 156	90.93 196	64.62 278	84.80 346	83.32 338

CANet		83.79 155	82.85 170	86.63 101	86.17 257	72.21 156	83.76 181	91.43 131	77.24 127	74.39 342	87.45 262	75.36 177	95.42 51	77.03 150	92.83 221	92.25 185

PS-MVSNAJ		77.04 253	76.53 256	78.56 262	87.09 235	61.40 270	75.26 323	87.13 220	61.25 305	74.38 343	77.22 377	76.94 162	90.94 195	64.63 277	84.83 345	83.35 337

MVP-Stereo		75.81 268	73.51 284	82.71 199	89.35 176	73.62 130	80.06 251	85.20 251	60.30 315	73.96 344	87.94 250	57.89 305	89.45 241	52.02 356	74.87 390	85.06 312
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WB-MVSnew		68.72 333	69.01 327	67.85 354	83.22 307	43.98 390	74.93 326	65.98 382	55.09 345	73.83 345	79.11 360	65.63 258	71.89 366	38.21 399	85.04 338	87.69 284

UGNet		82.78 171	81.64 188	86.21 112	86.20 256	76.24 117	86.86 119	85.68 244	77.07 128	73.76 346	92.82 131	69.64 236	91.82 173	69.04 236	93.69 202	90.56 233
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
1112_ss		74.82 279	73.74 280	78.04 274	89.57 170	60.04 288	76.49 307	87.09 224	54.31 350	73.66 347	79.80 355	60.25 286	86.76 281	58.37 316	84.15 350	87.32 288

Test_1112_low_res		73.90 287	73.08 288	76.35 296	90.35 157	55.95 325	73.40 341	86.17 235	50.70 373	73.14 348	85.94 286	58.31 300	85.90 297	56.51 326	83.22 355	87.20 289

1314		73.22 292	72.56 297	75.20 306	80.41 338	57.84 313	81.64 234	85.36 248	51.68 366	73.10 349	76.65 381	61.45 278	85.19 305	63.54 284	79.21 377	82.59 345

test_vis1_rt		65.64 350	64.09 354	70.31 337	66.09 407	70.20 176	61.16 388	81.60 290	38.65 402	72.87 350	69.66 395	52.84 327	60.04 399	56.16 328	77.77 382	80.68 370

Patchmatch-test		65.91 348	67.38 337	61.48 378	75.51 376	43.21 393	68.84 367	63.79 387	62.48 287	72.80 351	83.42 320	44.89 372	59.52 400	48.27 375	86.45 321	81.70 356

PatchmatchNet		69.71 325	68.83 330	72.33 328	77.66 357	53.60 341	79.29 264	69.99 366	57.66 333	72.53 352	82.93 325	46.45 353	80.08 341	60.91 305	72.09 393	83.31 339
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm		67.95 335	68.08 336	67.55 356	78.74 353	43.53 392	75.60 318	67.10 380	54.92 347	72.23 353	88.10 247	42.87 381	75.97 356	52.21 355	80.95 372	83.15 341

pmmvs5		70.73 314	70.07 317	72.72 322	77.03 363	52.73 348	74.14 331	75.65 328	50.36 376	72.17 354	85.37 296	55.42 320	80.67 336	52.86 353	87.59 307	84.77 314

PatchT		70.52 315	72.76 293	63.79 372	79.38 346	33.53 406	77.63 289	65.37 384	73.61 167	71.77 355	92.79 134	44.38 374	75.65 358	64.53 279	85.37 332	82.18 352

MVS		73.21 293	72.59 295	75.06 308	80.97 328	60.81 282	81.64 234	85.92 241	46.03 385	71.68 356	77.54 372	68.47 243	89.77 235	55.70 332	85.39 331	74.60 385

MIMVSNet		71.09 311	71.59 303	69.57 343	87.23 228	50.07 367	78.91 271	71.83 356	60.20 318	71.26 357	91.76 166	55.08 323	76.09 355	41.06 392	87.02 315	82.54 348

WTY-MVS		67.91 336	68.35 333	66.58 361	80.82 332	48.12 372	65.96 378	72.60 349	53.67 353	71.20 358	81.68 340	58.97 296	69.06 375	48.57 372	81.67 365	82.55 347

test0.0.03 1		64.66 354	64.36 353	65.57 365	75.03 381	46.89 378	64.69 381	61.58 395	62.43 291	71.18 359	77.54 372	43.41 377	68.47 380	40.75 393	82.65 361	81.35 360

CostFormer		69.98 322	68.68 332	73.87 312	77.14 361	50.72 364	79.26 265	74.51 334	51.94 365	70.97 360	84.75 305	45.16 370	87.49 267	55.16 338	79.23 376	83.40 336

Syy-MVS		69.40 328	70.03 319	67.49 357	81.72 318	38.94 399	71.00 355	61.99 389	61.38 302	70.81 361	72.36 392	61.37 279	79.30 343	64.50 280	85.18 335	84.22 322

myMVS_eth3d		64.66 354	63.89 355	66.97 359	81.72 318	37.39 402	71.00 355	61.99 389	61.38 302	70.81 361	72.36 392	20.96 413	79.30 343	49.59 367	85.18 335	84.22 322

testing91		69.94 323	68.99 328	72.80 321	83.81 296	45.89 382	71.57 352	73.64 344	68.24 238	70.77 363	77.82 369	34.37 395	84.44 312	53.64 346	87.00 316	88.07 274

testing99		69.27 329	68.15 335	72.63 323	83.29 304	45.45 384	71.15 354	71.08 361	67.34 249	70.43 364	77.77 371	32.24 398	84.35 314	53.72 345	86.33 324	88.10 273

tpmvs		70.16 318	69.56 323	71.96 329	74.71 383	48.13 371	79.63 257	75.45 330	65.02 274	70.26 365	81.88 337	45.34 367	85.68 301	58.34 317	75.39 389	82.08 354

sss		66.92 340	67.26 338	65.90 363	77.23 360	51.10 363	64.79 380	71.72 358	52.12 364	70.13 366	80.18 352	57.96 303	65.36 392	50.21 363	81.01 371	81.25 363

tpm2		68.45 334	66.83 341	73.30 317	78.93 352	48.50 370	79.76 256	71.76 357	47.50 379	69.92 367	83.60 316	42.07 382	88.40 258	48.44 374	79.51 373	83.01 343

testing222		66.93 339	65.30 351	71.81 330	83.38 301	45.83 383	72.06 348	67.50 374	64.12 278	69.68 368	76.37 383	27.34 408	83.00 323	38.88 395	88.38 293	86.62 295

HY-MVS	64.64 18	73.03 294	72.47 298	74.71 309	83.36 303	54.19 337	82.14 230	81.96 286	56.76 341	69.57 369	86.21 283	60.03 287	84.83 309	49.58 368	82.65 361	85.11 311

dmvs_re		66.81 343	66.98 339	66.28 362	76.87 364	58.68 308	71.66 351	72.24 352	60.29 316	69.52 370	73.53 389	52.38 330	64.40 394	44.90 385	81.44 368	75.76 382

ETVMVS		64.67 353	63.34 358	68.64 350	83.44 300	41.89 395	69.56 366	61.70 394	61.33 304	68.74 371	75.76 385	28.76 404	79.35 342	34.65 402	86.16 327	84.67 316

tpm cat1		66.76 344	65.21 352	71.42 332	77.09 362	50.62 365	78.01 282	73.68 343	44.89 388	68.64 372	79.00 362	45.51 364	82.42 328	49.91 365	70.15 396	81.23 365

IB-MVS	62.13 19	71.64 305	68.97 329	79.66 249	80.80 333	62.26 261	73.94 335	76.90 318	63.27 281	68.63 373	76.79 379	33.83 396	91.84 172	59.28 313	87.26 308	84.88 313
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
EPNet		80.37 214	78.41 240	86.23 110	76.75 365	73.28 135	87.18 114	77.45 312	76.24 133	68.14 374	88.93 237	65.41 259	93.85 104	69.47 228	96.12 114	91.55 208
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet	58.17 21	66.41 346	65.63 349	68.75 349	81.96 315	49.88 368	62.19 387	72.51 351	51.03 370	68.04 375	75.34 387	50.84 337	74.77 359	45.82 384	82.96 356	81.60 358

tpmrst		66.28 347	66.69 343	65.05 368	72.82 393	39.33 398	78.20 281	70.69 364	53.16 356	67.88 376	80.36 351	48.18 347	74.75 360	58.13 319	70.79 395	81.08 366

CANet_DTU		77.81 245	77.05 250	80.09 243	81.37 324	59.90 291	83.26 193	88.29 204	69.16 227	67.83 377	83.72 315	60.93 280	89.47 239	69.22 232	89.70 278	90.88 222

EPMVS		62.47 357	62.63 361	62.01 374	70.63 399	38.74 400	74.76 327	52.86 405	53.91 352	67.71 378	80.01 353	39.40 386	66.60 387	55.54 334	68.81 401	80.68 370

MDTV_nov1_ep13			68.29 334		78.03 354	43.87 391	74.12 332	72.22 353	52.17 361	67.02 379	85.54 290	45.36 366	80.85 335	55.73 330	84.42 348

testing11		67.38 337	65.93 345	71.73 331	83.37 302	46.60 379	70.95 357	69.40 369	62.47 288	66.14 380	76.66 380	31.22 399	84.10 316	49.10 370	84.10 351	84.49 317

pmmvs3		62.47 357	60.02 370	69.80 341	71.58 397	64.00 235	70.52 360	58.44 401	39.77 400	66.05 381	75.84 384	27.10 410	72.28 363	46.15 382	84.77 347	73.11 386

ADS-MVSNet2		65.87 349	63.64 357	72.55 325	73.16 390	56.92 321	67.10 374	74.81 331	49.74 377	66.04 382	82.97 323	46.71 351	77.26 352	42.29 389	69.96 397	83.46 334

ADS-MVSNet		61.90 359	62.19 363	61.03 379	73.16 390	36.42 404	67.10 374	61.75 392	49.74 377	66.04 382	82.97 323	46.71 351	63.21 395	42.29 389	69.96 397	83.46 334

mvsany_test1		58.48 369	56.47 374	64.50 369	65.90 409	68.21 195	56.95 398	42.11 411	38.30 403	65.69 384	77.19 378	56.96 310	59.35 401	46.16 381	58.96 404	65.93 395

dmvs_testset		60.59 367	62.54 362	54.72 386	77.26 359	27.74 409	74.05 333	61.00 396	60.48 314	65.62 385	67.03 399	55.93 316	68.23 381	32.07 406	69.46 400	68.17 393

DSMNet-mixed		60.98 365	61.61 365	59.09 383	72.88 392	45.05 387	74.70 328	46.61 409	26.20 407	65.34 386	90.32 212	55.46 319	63.12 396	41.72 391	81.30 370	69.09 392

JIA-IIPM		69.41 327	66.64 344	77.70 280	73.19 389	71.24 168	75.67 317	65.56 383	70.42 214	65.18 387	92.97 126	33.64 397	83.06 322	53.52 348	69.61 399	78.79 377

test-LLR		67.21 338	66.74 342	68.63 351	76.45 369	55.21 332	67.89 370	67.14 378	62.43 291	65.08 388	72.39 390	43.41 377	69.37 371	61.00 303	84.89 343	81.31 361

test-mter		65.00 352	63.79 356	68.63 351	76.45 369	55.21 332	67.89 370	67.14 378	50.98 371	65.08 388	72.39 390	28.27 406	69.37 371	61.00 303	84.89 343	81.31 361

PMMVS2		55.64 372	59.27 371	44.74 388	64.30 411	12.32 416	40.60 403	49.79 407	53.19 355	65.06 390	84.81 304	53.60 326	49.76 406	32.68 405	89.41 280	72.15 387

baseline2		69.77 324	66.89 340	78.41 266	79.51 344	58.09 310	76.23 311	69.57 368	57.50 335	64.82 391	77.45 374	46.02 356	88.44 257	53.08 349	77.83 381	88.70 268

gg-mvs-nofinetune		68.96 332	69.11 325	68.52 353	76.12 372	45.32 385	83.59 185	55.88 403	86.68 27	64.62 392	97.01 8	30.36 401	83.97 319	44.78 386	82.94 357	76.26 381

PAPM		71.77 304	70.06 318	76.92 289	86.39 246	53.97 338	76.62 305	86.62 230	53.44 354	63.97 393	84.73 306	57.79 306	92.34 157	39.65 394	81.33 369	84.45 319

new_pmnet		55.69 371	57.66 372	49.76 387	75.47 377	30.59 407	59.56 390	51.45 406	43.62 393	62.49 394	75.48 386	40.96 384	49.15 407	37.39 400	72.52 391	69.55 391

MDTV_nov1_ep13_2view						27.60 410	70.76 359		46.47 383	61.27 395		45.20 368		49.18 369		83.75 331

dp		60.70 366	60.29 369	61.92 376	72.04 396	38.67 401	70.83 358	64.08 386	51.28 368	60.75 396	77.28 375	36.59 393	71.58 368	47.41 377	62.34 403	75.52 383

TESTMET0.1,1		61.29 362	60.32 368	64.19 370	72.06 395	51.30 359	67.89 370	62.09 388	45.27 386	60.65 397	69.01 396	27.93 407	64.74 393	56.31 327	81.65 367	76.53 380

PMMVS		61.65 360	60.38 367	65.47 366	65.40 410	69.26 185	63.97 383	61.73 393	36.80 406	60.11 398	68.43 397	59.42 292	66.35 388	48.97 371	78.57 380	60.81 399

PVSNet_0	51.08 22	56.10 370	54.97 375	59.48 382	75.12 380	53.28 345	55.16 399	61.89 391	44.30 389	59.16 399	62.48 402	54.22 324	65.91 390	35.40 401	47.01 405	59.25 401

MVS-HIRNet		61.16 363	62.92 360	55.87 384	79.09 349	35.34 405	71.83 349	57.98 402	46.56 382	59.05 400	91.14 182	49.95 343	76.43 354	38.74 396	71.92 394	55.84 403

E-PMN		61.59 361	61.62 364	61.49 377	66.81 405	55.40 330	53.77 400	60.34 397	66.80 254	58.90 401	65.50 400	40.48 385	66.12 389	55.72 331	86.25 325	62.95 398

GG-mvs-BLEND				67.16 358	73.36 388	46.54 381	84.15 168	55.04 404		58.64 402	61.95 403	29.93 402	83.87 320	38.71 397	76.92 387	71.07 389

EPNet_dtu		72.87 296	71.33 308	77.49 283	77.72 356	60.55 284	82.35 221	75.79 325	66.49 256	58.39 403	81.06 344	53.68 325	85.98 294	53.55 347	92.97 219	85.95 301
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		41.90 374	42.65 377	39.67 389	70.86 398	21.11 411	61.01 389	21.42 416	57.36 336	57.97 404	50.06 405	16.40 415	58.73 402	21.03 409	27.69 409	39.17 405

EMVS		61.10 364	60.81 366	61.99 375	65.96 408	55.86 327	53.10 401	58.97 400	67.06 251	56.89 405	63.33 401	40.98 383	67.03 385	54.79 340	86.18 326	63.08 397

CHOSEN 280x420		59.08 368	56.52 373	66.76 360	76.51 367	64.39 231	49.62 402	59.00 399	43.86 391	55.66 406	68.41 398	35.55 394	68.21 382	43.25 388	76.78 388	67.69 394

MVE	40.22 23	51.82 373	50.47 376	55.87 384	62.66 412	51.91 354	31.61 405	39.28 412	40.65 398	50.76 407	74.98 388	56.24 315	44.67 408	33.94 404	64.11 402	71.04 390
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
kuosan		30.83 375	32.17 378	26.83 391	53.36 413	19.02 414	57.90 396	20.44 417	38.29 404	38.01 408	37.82 407	15.18 416	33.45 410	7.74 411	20.76 410	28.03 406

DeepMVS_CX				24.13 392	32.95 414	29.49 408		21.63 415	12.07 408	37.95 409	45.07 406	30.84 400	19.21 411	17.94 410	33.06 408	23.69 407

tmp_tt		20.25 378	24.50 381	7.49 393	4.47 416	8.70 417	34.17 404	25.16 414	1.00 411	32.43 410	18.49 408	39.37 387	9.21 412	21.64 408	43.75 406	4.57 408

test_method		30.46 376	29.60 379	33.06 390	17.99 415	3.84 418	13.62 406	73.92 338	2.79 409	18.29 411	53.41 404	28.53 405	43.25 409	22.56 407	35.27 407	52.11 404

EGC-MVSNET		74.79 280	69.99 320	89.19 62	94.89 38	87.00 12	91.89 34	86.28 233	1.09 410	2.23 412	95.98 26	81.87 111	89.48 238	79.76 113	95.96 121	91.10 216

testmvs		5.91 382	7.65 385	0.72 395	1.20 417	0.37 420	59.14 392	0.67 419	0.49 413	1.11 413	2.76 412	0.94 418	0.24 414	1.02 413	1.47 411	1.55 410

test123		6.27 381	8.08 384	0.84 394	1.11 418	0.57 419	62.90 384	0.82 418	0.54 412	1.07 414	2.75 413	1.26 417	0.30 413	1.04 412	1.26 412	1.66 409

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

cdsmvs_eth3d_5k		20.81 377	27.75 380	0.00 396	0.00 419	0.00 421	0.00 407	85.44 247	0.00 414	0.00 415	82.82 327	81.46 115	0.00 415	0.00 414	0.00 413	0.00 411

pcd_1.5k_mvsjas		6.41 380	8.55 383	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	76.94 162	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		6.65 379	8.87 382	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	79.80 355	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

WAC-MVS						37.39 402								52.61 354

MSC_two_6792asdad				88.81 68	91.55 127	77.99 91		91.01 145					96.05 9	87.45 20	98.17 32	92.40 175

No_MVS				88.81 68	91.55 127	77.99 91		91.01 145					96.05 9	87.45 20	98.17 32	92.40 175

eth-test2					0.00 419

eth-test					0.00 419

OPU-MVS				88.27 79	91.89 113	77.83 94	90.47 54				91.22 179	81.12 119	94.68 75	74.48 175	95.35 143	92.29 181

save fliter					93.75 60	77.44 100	86.31 132	89.72 181	70.80 211

test_0728_SECOND				86.79 99	94.25 46	72.45 151	90.54 51	94.10 37					95.88 18	86.42 36	97.97 43	92.02 193

GSMVS																83.88 326

sam_mvs1												46.11 355				83.88 326

sam_mvs												45.92 360

MTGPA								91.81 124

test_post1							78.85 274				3.13 410	45.19 369	80.13 340	58.11 320

test_post											3.10 411	45.43 365	77.22 353

patchmatchnet-post											81.71 339	45.93 359	87.01 272

MTMP							90.66 47	33.14 413

gm-plane-assit					75.42 378	44.97 388			52.17 361		72.36 392		87.90 262	54.10 343

test9_res														80.83 102	96.45 100	90.57 232

agg_prior2														79.68 115	96.16 111	90.22 240

test_prior4						78.97 81	84.59 159

test_prior				86.32 107	90.59 153	71.99 158		92.85 90					94.17 94			92.80 153

新几何2							81.72 233

旧先验1					91.97 109	71.77 159		81.78 288			91.84 161	73.92 195			93.65 203	83.61 332

无先验							82.81 208	85.62 245	58.09 329				91.41 183	67.95 249		84.48 318

原ACMM2							82.26 226

testdata2													86.43 286	63.52 285

segment_acmp												81.94 107

testdata1							79.62 258		73.95 162

plane_prior7					93.45 65	77.31 103

plane_prior6					92.61 87	76.54 110						74.84 183

plane_prior5								93.61 57					95.22 58	80.78 103	95.83 130	94.46 80

plane_prior4											92.95 127

plane_prior2							89.45 81		79.44 98

plane_prior1					92.83 85

plane_prior						76.42 113	87.15 115		75.94 140						95.03 158

n2								0.00 420

nn								0.00 420

door-mid								74.45 335

test11								91.46 130

door								72.57 350

HQP5-MVS						70.66 171

BP-MVS														77.30 147

HQP3-MVS								92.68 95							94.47 178

HQP2-MVS												72.10 221

NP-MVS					91.95 110	74.55 125					90.17 218

ACMMP++_ref															95.74 136

ACMMP++															97.35 72

Test By Simon												79.09 137

High-resolution multi-view benchmark