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 58	99.27 1	99.54 1

mamv4		95.37 2	94.51 2	97.96 1	96.31 10	98.41 1	91.05 46	97.23 2	95.32 2	99.01 2	97.26 6	80.16 133	98.99 1	95.15 1	99.14 2	96.47 30

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

DTE-MVSNet		89.98 47	91.91 17	84.21 160	96.51 7	57.84 319	88.93 90	92.84 94	91.92 4	96.16 4	96.23 21	86.95 51	95.99 12	79.05 126	98.57 15	98.80 6

PS-CasMVS		90.06 43	91.92 15	84.47 151	96.56 6	58.83 311	89.04 88	92.74 97	91.40 6	96.12 5	96.06 26	87.23 48	95.57 41	79.42 123	98.74 6	99.00 2

LCM-MVSNet-Re		83.48 165	85.06 131	78.75 265	85.94 265	55.75 336	80.05 259	94.27 24	76.47 136	96.09 6	94.54 67	83.31 88	89.75 241	59.95 319	94.89 169	90.75 233

PEN-MVS		90.03 45	91.88 18	84.48 150	96.57 5	58.88 308	88.95 89	93.19 75	91.62 5	96.01 7	96.16 24	87.02 50	95.60 40	78.69 129	98.72 9	98.97 3

CP-MVSNet		89.27 62	90.91 44	84.37 152	96.34 8	58.61 314	88.66 97	92.06 115	90.78 7	95.67 8	95.17 47	81.80 115	95.54 44	79.00 127	98.69 10	98.95 4

reproduce_model		92.89 5	93.18 7	92.01 13	94.20 49	88.23 9	92.87 13	94.32 21	90.25 11	95.65 9	95.74 30	87.75 41	95.72 36	89.60 4	98.27 26	92.08 195

LTVRE_ROB	86.10 1	93.04 4	93.44 3	91.82 22	93.73 64	85.72 34	96.79 1	95.51 9	88.86 16	95.63 10	96.99 10	84.81 72	93.16 137	91.10 2	97.53 72	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 50	91.31 33	85.71 128	96.32 9	62.39 264	89.54 79	93.31 70	90.21 12	95.57 11	95.66 33	81.42 119	95.90 17	80.94 103	98.80 3	98.84 5

reproduce-ours		92.86 6	93.22 5	91.76 23	94.39 44	87.71 11	92.40 27	94.38 19	89.82 13	95.51 12	95.49 38	89.64 21	95.82 26	89.13 6	98.26 28	91.76 206

our_new_method		92.86 6	93.22 5	91.76 23	94.39 44	87.71 11	92.40 27	94.38 19	89.82 13	95.51 12	95.49 38	89.64 21	95.82 26	89.13 6	98.26 28	91.76 206

OurMVSNet-221017-0		90.01 46	89.74 56	90.83 36	93.16 78	80.37 72	91.91 36	93.11 79	81.10 81	95.32 14	97.24 7	72.94 214	94.85 72	85.07 58	97.78 56	97.26 15

anonymousdsp		89.73 53	88.88 70	92.27 8	89.82 171	86.67 18	90.51 54	90.20 176	69.87 229	95.06 15	96.14 25	84.28 77	93.07 141	87.68 18	96.34 106	97.09 19

wuyk23d		75.13 280	79.30 233	62.63 385	75.56 385	75.18 126	80.89 251	73.10 356	75.06 158	94.76 16	95.32 41	87.73 43	52.85 416	34.16 415	97.11 82	59.85 412

ACMH	76.49 14	89.34 59	91.14 35	83.96 165	92.50 94	70.36 179	89.55 77	93.84 52	81.89 73	94.70 17	95.44 40	90.69 8	88.31 264	83.33 74	98.30 25	93.20 143
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SixPastTwentyTwo		87.20 89	87.45 87	86.45 108	92.52 93	69.19 192	87.84 107	88.05 213	81.66 75	94.64 18	96.53 17	65.94 258	94.75 74	83.02 80	96.83 89	95.41 51

mvs_tets		89.78 52	89.27 63	91.30 29	93.51 67	84.79 44	89.89 68	90.63 157	70.00 228	94.55 19	96.67 14	87.94 39	93.59 120	84.27 68	95.97 124	95.52 49

jajsoiax		89.41 57	88.81 73	91.19 32	93.38 71	84.72 45	89.70 71	90.29 173	69.27 232	94.39 20	96.38 18	86.02 65	93.52 124	83.96 70	95.92 130	95.34 53

test_0402		88.65 69	89.58 60	85.88 124	92.55 92	72.22 159	84.01 178	89.44 194	88.63 20	94.38 21	95.77 29	86.38 61	93.59 120	79.84 115	95.21 154	91.82 204

UniMVSNet_ETH3D		89.12 65	90.72 47	84.31 158	97.00 2	64.33 239	89.67 74	88.38 206	88.84 17	94.29 22	97.57 4	90.48 13	91.26 189	72.57 211	97.65 62	97.34 14

v7n		90.13 40	90.96 42	87.65 91	91.95 112	71.06 173	89.99 64	93.05 83	86.53 31	94.29 22	96.27 20	82.69 93	94.08 100	86.25 45	97.63 63	97.82 8

test_djsdf		89.62 54	89.01 67	91.45 26	92.36 97	82.98 57	91.98 34	90.08 179	71.54 208	94.28 24	96.54 16	81.57 117	94.27 89	86.26 43	96.49 100	97.09 19

PS-MVSNAJss		88.31 73	87.90 81	89.56 59	93.31 73	77.96 96	87.94 105	91.97 118	70.73 219	94.19 25	96.67 14	76.94 166	94.57 81	83.07 78	96.28 108	96.15 32

SED-MVS		90.46 37	91.64 21	86.93 99	94.18 50	72.65 145	90.47 55	93.69 56	83.77 52	94.11 26	94.27 79	90.28 14	95.84 24	86.03 49	97.92 49	92.29 185

test_241102_ONE					94.18 50	72.65 145		93.69 56	83.62 54	94.11 26	93.78 108	90.28 14	95.50 49

DPE-MVS		90.53 36	91.08 37	88.88 69	93.38 71	78.65 87	89.15 87	94.05 41	84.68 45	93.90 28	94.11 91	88.13 36	96.30 5	84.51 66	97.81 55	91.70 210
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		91.22 25	91.92 15	89.14 66	92.97 82	78.04 93	92.84 16	94.14 36	83.33 58	93.90 28	95.73 31	88.77 27	96.41 3	87.60 21	97.98 45	92.98 154
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMH+	77.89 11	90.73 31	91.50 25	88.44 78	93.00 81	76.26 119	89.65 75	95.55 8	87.72 26	93.89 30	94.94 52	91.62 3	93.44 128	78.35 133	98.76 4	95.61 48

ACMM	79.39 9	90.65 32	90.99 41	89.63 57	95.03 34	83.53 51	89.62 76	93.35 66	79.20 105	93.83 31	93.60 116	90.81 7	92.96 144	85.02 60	98.45 19	92.41 177
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SR-MVS-dyc-post		92.41 9	92.41 10	92.39 5	94.13 55	88.95 6	92.87 13	94.16 32	88.75 18	93.79 32	94.43 72	88.83 26	95.51 47	87.16 32	97.60 66	92.73 160

RE-MVS-def			92.61 8		94.13 55	88.95 6	92.87 13	94.16 32	88.75 18	93.79 32	94.43 72	90.64 10		87.16 32	97.60 66	92.73 160

DVP-MVS		90.06 43	91.32 32	86.29 111	94.16 53	72.56 151	90.54 52	91.01 147	83.61 55	93.75 34	94.65 61	89.76 18	95.78 32	86.42 39	97.97 46	90.55 242
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 38	93.75 34	94.65 61	87.44 46	95.78 32	87.41 25	98.21 32	92.98 154

test0726					94.16 53	72.56 151	90.63 49	93.90 48	83.61 55	93.75 34	94.49 69	89.76 18

LPG-MVS_test		91.47 21	91.68 20	90.82 37	94.75 41	81.69 63	90.00 62	94.27 24	82.35 68	93.67 37	94.82 56	91.18 4	95.52 45	85.36 55	98.73 7	95.23 59

LGP-MVS_train				90.82 37	94.75 41	81.69 63		94.27 24	82.35 68	93.67 37	94.82 56	91.18 4	95.52 45	85.36 55	98.73 7	95.23 59

DVP-MVS++		90.07 42	91.09 36	87.00 97	91.55 129	72.64 147	96.19 2	94.10 39	85.33 38	93.49 39	94.64 64	81.12 122	95.88 18	87.41 25	95.94 128	92.48 173

test_241102_TWO								93.71 55	83.77 52	93.49 39	94.27 79	89.27 23	95.84 24	86.03 49	97.82 54	92.04 197

test_one_0601					93.85 62	73.27 140		94.11 38	86.57 30	93.47 41	94.64 64	88.42 28

SR-MVS		92.23 10	92.34 11	91.91 17	94.89 38	87.85 10	92.51 24	93.87 51	88.20 23	93.24 42	94.02 94	90.15 16	95.67 38	86.82 36	97.34 76	92.19 191

APD-MVS_3200maxsize		92.05 12	92.24 12	91.48 25	93.02 80	85.17 39	92.47 26	95.05 14	87.65 27	93.21 43	94.39 77	90.09 17	95.08 66	86.67 38	97.60 66	94.18 97

testf1		89.30 60	89.12 64	89.84 52	88.67 195	85.64 35	90.61 50	93.17 76	86.02 34	93.12 44	95.30 42	84.94 69	89.44 246	74.12 186	96.10 119	94.45 84

APD_test2		89.30 60	89.12 64	89.84 52	88.67 195	85.64 35	90.61 50	93.17 76	86.02 34	93.12 44	95.30 42	84.94 69	89.44 246	74.12 186	96.10 119	94.45 84

Anonymous20231211		88.40 71	89.62 59	84.73 144	90.46 157	65.27 229	88.86 91	93.02 87	87.15 28	93.05 46	97.10 8	82.28 105	92.02 170	76.70 157	97.99 43	96.88 23

MP-MVS-pluss		90.81 30	91.08 37	89.99 50	95.97 14	79.88 75	88.13 102	94.51 18	75.79 147	92.94 47	94.96 51	88.36 30	95.01 68	90.70 3	98.40 20	95.09 64
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SD-MVS		88.96 67	89.88 53	86.22 115	91.63 123	77.07 109	89.82 69	93.77 53	78.90 109	92.88 48	92.29 157	86.11 63	90.22 222	86.24 46	97.24 79	91.36 218
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 35	90.60 49	90.35 45	94.36 46	80.98 69	89.16 86	94.05 41	79.03 108	92.87 49	93.74 111	90.60 11	95.21 61	82.87 82	98.76 4	94.87 68
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 50	96.29 19	88.16 35	94.17 97	86.07 48	98.48 18	97.22 17

SMA-MVS		90.31 38	90.48 50	89.83 54	95.31 30	79.52 81	90.98 47	93.24 74	75.37 155	92.84 51	95.28 44	85.58 67	96.09 8	87.92 14	97.76 57	93.88 110
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 61	77.77 98				92.84 51

v10		86.54 98	87.10 92	84.84 140	88.16 210	63.28 250	86.64 130	92.20 111	75.42 154	92.81 53	94.50 68	74.05 198	94.06 101	83.88 71	96.28 108	97.17 18

dcpmvs_2		84.23 146	85.14 130	81.50 226	88.61 199	61.98 272	82.90 213	93.11 79	68.66 241	92.77 54	92.39 151	78.50 144	87.63 270	76.99 156	92.30 233	94.90 66

v8		86.22 103	86.83 99	84.36 154	87.82 217	62.35 266	86.42 134	91.33 138	76.78 135	92.73 55	94.48 70	73.41 207	93.72 112	83.10 77	95.41 146	97.01 21

nrg030		87.85 82	88.49 75	85.91 122	90.07 166	69.73 183	87.86 106	94.20 30	74.04 166	92.70 56	94.66 60	85.88 66	91.50 181	79.72 117	97.32 77	96.50 29

SteuartSystems-ACMMP		91.16 27	91.36 28	90.55 41	93.91 60	80.97 70	91.49 40	93.48 63	82.82 65	92.60 57	93.97 96	88.19 33	96.29 6	87.61 20	98.20 34	94.39 89
Skip Steuart: Steuart Systems R&D Blog.
OPM-MVS		89.80 51	89.97 52	89.27 63	94.76 40	79.86 76	86.76 127	92.78 96	78.78 111	92.51 58	93.64 115	88.13 36	93.84 109	84.83 63	97.55 69	94.10 102
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HPM-MVS_fast		92.50 8	92.54 9	92.37 6	95.93 16	85.81 33	92.99 12	94.23 27	85.21 40	92.51 58	95.13 48	90.65 9	95.34 55	88.06 12	98.15 37	95.95 40

K. test v3		85.14 122	84.73 136	86.37 109	91.13 143	69.63 185	85.45 152	76.68 329	84.06 50	92.44 60	96.99 10	62.03 280	94.65 77	80.58 109	93.24 216	94.83 73

ACMMP		91.91 14	91.87 19	92.03 12	95.53 27	85.91 28	93.35 11	94.16 32	82.52 67	92.39 61	94.14 89	89.15 25	95.62 39	87.35 27	98.24 30	94.56 78
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 39	90.80 46	88.68 76	92.86 86	77.09 108	91.19 44	95.74 6	81.38 78	92.28 62	93.80 106	86.89 52	94.64 78	85.52 54	97.51 73	94.30 93

COLMAP_ROB	83.01 3	91.97 13	91.95 14	92.04 11	93.68 65	86.15 24	93.37 10	95.10 13	90.28 10	92.11 63	95.03 50	89.75 20	94.93 70	79.95 114	98.27 26	95.04 65
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 47	89.84 54	90.41 43	94.91 37	84.50 48	89.49 81	93.98 43	79.68 97	92.09 64	93.89 104	83.80 81	93.10 140	82.67 86	98.04 39	93.64 125

TranMVSNet+NR-MVSNet		87.86 81	88.76 74	85.18 136	94.02 58	64.13 240	84.38 172	91.29 139	84.88 44	92.06 65	93.84 105	86.45 58	93.73 111	73.22 202	98.66 11	97.69 9

MTAPA		91.52 18	91.60 22	91.29 30	96.59 4	86.29 21	92.02 33	91.81 126	84.07 49	92.00 66	94.40 76	86.63 54	95.28 58	88.59 9	98.31 24	92.30 184

ACMMP_NAP		90.65 32	91.07 39	89.42 61	95.93 16	79.54 80	89.95 66	93.68 58	77.65 126	91.97 67	94.89 53	88.38 29	95.45 51	89.27 5	97.87 53	93.27 140

FC-MVSNet-test		85.93 109	87.05 94	82.58 206	92.25 101	56.44 330	85.75 146	93.09 81	77.33 130	91.94 68	94.65 61	74.78 189	93.41 130	75.11 178	98.58 14	97.88 7

lessismore_v0				85.95 121	91.10 144	70.99 174		70.91 372		91.79 69	94.42 74	61.76 281	92.93 146	79.52 122	93.03 221	93.93 107

HPM-MVS		92.13 11	92.20 13	91.91 17	95.58 26	84.67 46	93.51 8	94.85 15	82.88 64	91.77 70	93.94 102	90.55 12	95.73 35	88.50 10	98.23 31	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 26	90.95 43	91.93 15	95.67 23	85.85 31	90.00 62	93.90 48	80.32 89	91.74 71	94.41 75	88.17 34	95.98 13	86.37 41	97.99 43	93.96 106

mPP-MVS		91.69 15	91.47 26	92.37 6	96.04 13	88.48 8	92.72 18	92.60 101	83.09 61	91.54 72	94.25 83	87.67 44	95.51 47	87.21 31	98.11 38	93.12 148

HFP-MVS		91.30 23	91.39 27	91.02 33	95.43 29	84.66 47	92.58 22	93.29 72	81.99 70	91.47 73	93.96 99	88.35 31	95.56 42	87.74 16	97.74 59	92.85 157

ACMMPR		91.49 19	91.35 30	91.92 16	95.74 20	85.88 30	92.58 22	93.25 73	81.99 70	91.40 74	94.17 88	87.51 45	95.87 20	87.74 16	97.76 57	93.99 104

GST-MVS		90.96 29	91.01 40	90.82 37	95.45 28	82.73 59	91.75 38	93.74 54	80.98 83	91.38 75	93.80 106	87.20 49	95.80 28	87.10 34	97.69 61	93.93 107

test_fmvsmvis_n_1920		85.22 119	85.36 128	84.81 141	85.80 267	76.13 122	85.15 158	92.32 108	61.40 309	91.33 76	90.85 202	83.76 83	86.16 296	84.31 67	93.28 215	92.15 193

ANet_high		83.17 171	85.68 121	75.65 310	81.24 333	45.26 396	79.94 261	92.91 91	83.83 51	91.33 76	96.88 13	80.25 132	85.92 300	68.89 245	95.89 131	95.76 42

ZNCC-MVS		91.26 24	91.34 31	91.01 34	95.73 21	83.05 56	92.18 31	94.22 29	80.14 92	91.29 78	93.97 96	87.93 40	95.87 20	88.65 8	97.96 48	94.12 101

casdiffmvs_mvg		86.72 95	87.51 86	84.36 154	87.09 238	65.22 230	84.16 174	94.23 27	77.89 122	91.28 79	93.66 114	84.35 76	92.71 150	80.07 111	94.87 172	95.16 62
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 56	89.63 58	89.26 64	92.57 91	81.34 68	90.19 61	93.08 82	80.87 85	91.13 80	93.19 122	86.22 62	95.97 14	82.23 92	97.18 81	90.45 244
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
9.14			89.29 62		91.84 119		88.80 93	95.32 12	75.14 157	91.07 81	92.89 136	87.27 47	93.78 110	83.69 73	97.55 69

CP-MVS		91.67 16	91.58 23	91.96 14	95.29 31	87.62 13	93.38 9	93.36 65	83.16 60	91.06 82	94.00 95	88.26 32	95.71 37	87.28 30	98.39 21	92.55 170

FIs		85.35 118	86.27 106	82.60 205	91.86 116	57.31 323	85.10 159	93.05 83	75.83 146	91.02 83	93.97 96	73.57 203	92.91 148	73.97 190	98.02 42	97.58 12

UniMVSNet_NR-MVSNet		86.84 93	87.06 93	86.17 118	92.86 86	67.02 213	82.55 222	91.56 129	83.08 62	90.92 84	91.82 169	78.25 147	93.99 102	74.16 184	98.35 22	97.49 13

DU-MVS		86.80 94	86.99 95	86.21 116	93.24 76	67.02 213	83.16 205	92.21 110	81.73 74	90.92 84	91.97 163	77.20 160	93.99 102	74.16 184	98.35 22	97.61 10

tt0805		88.09 77	89.79 55	82.98 195	93.26 75	63.94 243	91.10 45	89.64 189	85.07 41	90.91 86	91.09 190	89.16 24	91.87 175	82.03 93	95.87 132	93.13 146

V42		83.47 166	83.37 164	83.75 171	83.16 315	63.33 249	81.31 244	90.23 175	69.51 231	90.91 86	90.81 204	74.16 196	92.29 164	80.06 112	90.22 279	95.62 47

region2R		91.44 22	91.30 34	91.87 19	95.75 19	85.90 29	92.63 21	93.30 71	81.91 72	90.88 88	94.21 84	87.75 41	95.87 20	87.60 21	97.71 60	93.83 113

APD_test1		88.40 71	87.91 80	89.88 51	89.50 175	86.65 20	89.98 65	91.91 121	84.26 47	90.87 89	93.92 103	82.18 106	89.29 250	73.75 194	94.81 173	93.70 121

WR-MVS		83.56 163	84.40 149	81.06 234	93.43 70	54.88 343	78.67 283	85.02 263	81.24 79	90.74 90	91.56 177	72.85 215	91.08 195	68.00 255	98.04 39	97.23 16

v1240		84.30 142	84.51 146	83.65 174	87.65 223	61.26 279	82.85 214	91.54 130	67.94 251	90.68 91	90.65 211	71.71 230	93.64 114	82.84 83	94.78 174	96.07 35

ZD-MVS					92.22 103	80.48 71		91.85 122	71.22 214	90.38 92	92.98 131	86.06 64	96.11 7	81.99 95	96.75 92

MIMVSNet1		83.63 161	84.59 141	80.74 238	94.06 57	62.77 257	82.72 216	84.53 272	77.57 128	90.34 93	95.92 28	76.88 172	85.83 305	61.88 306	97.42 74	93.62 126

LS3D		90.60 34	90.34 51	91.38 28	89.03 185	84.23 49	93.58 6	94.68 17	90.65 8	90.33 94	93.95 101	84.50 74	95.37 54	80.87 104	95.50 145	94.53 81

KD-MVS_self_test		81.93 196	83.14 169	78.30 274	84.75 283	52.75 357	80.37 256	89.42 195	70.24 226	90.26 95	93.39 119	74.55 194	86.77 284	68.61 250	96.64 94	95.38 52

PMVS	80.48 6	90.08 41	90.66 48	88.34 81	96.71 3	92.97 2	90.31 59	89.57 192	88.51 21	90.11 96	95.12 49	90.98 6	88.92 254	77.55 147	97.07 83	83.13 353
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PC_three_1452									58.96 331	90.06 97	91.33 182	80.66 128	93.03 143	75.78 169	95.94 128	92.48 173

v1921920		84.23 146	84.37 150	83.79 169	87.64 224	61.71 273	82.91 212	91.20 142	67.94 251	90.06 97	90.34 217	72.04 227	93.59 120	82.32 90	94.91 167	96.07 35

ITE_SJBPF				90.11 49	90.72 152	84.97 41		90.30 171	81.56 76	90.02 99	91.20 187	82.40 99	90.81 207	73.58 197	94.66 179	94.56 78

XVS		91.54 17	91.36 28	92.08 9	95.64 24	86.25 22	92.64 19	93.33 67	85.07 41	89.99 100	94.03 93	86.57 55	95.80 28	87.35 27	97.62 64	94.20 94

X-MVStestdata		85.04 125	82.70 176	92.08 9	95.64 24	86.25 22	92.64 19	93.33 67	85.07 41	89.99 100	16.05 421	86.57 55	95.80 28	87.35 27	97.62 64	94.20 94

v1192		84.57 135	84.69 140	84.21 160	87.75 219	62.88 254	83.02 208	91.43 133	69.08 235	89.98 102	90.89 199	72.70 218	93.62 118	82.41 89	94.97 166	96.13 33

Anonymous20240529		86.20 104	87.13 91	83.42 183	90.19 162	64.55 237	84.55 167	90.71 154	85.85 36	89.94 103	95.24 46	82.13 107	90.40 218	69.19 241	96.40 105	95.31 55

pmmvs6		86.52 99	88.06 79	81.90 216	92.22 103	62.28 267	84.66 165	89.15 197	83.54 57	89.85 104	97.32 5	88.08 38	86.80 283	70.43 228	97.30 78	96.62 26

v144192		84.24 145	84.41 148	83.71 173	87.59 225	61.57 274	82.95 211	91.03 146	67.82 254	89.80 105	90.49 214	73.28 211	93.51 125	81.88 98	94.89 169	96.04 37

v1144		84.54 137	84.72 138	84.00 163	87.67 222	62.55 261	82.97 210	90.93 150	70.32 224	89.80 105	90.99 193	73.50 204	93.48 126	81.69 99	94.65 180	95.97 38

DeepC-MVS	82.31 4	89.15 64	89.08 66	89.37 62	93.64 66	79.07 83	88.54 98	94.20 30	73.53 174	89.71 107	94.82 56	85.09 68	95.77 34	84.17 69	98.03 41	93.26 141
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 79	86.93 97	91.22 31	90.08 164	89.30 5	89.68 73	91.11 144	79.26 104	89.68 108	94.81 59	82.44 97	87.74 268	76.54 159	88.74 299	96.61 27

IU-MVS					94.18 50	72.64 147		90.82 152	56.98 348	89.67 109				85.78 52	97.92 49	93.28 139

FMVSNet1		84.55 136	85.45 125	81.85 218	90.27 161	61.05 282	86.83 124	88.27 210	78.57 115	89.66 110	95.64 34	75.43 180	90.68 211	69.09 242	95.33 149	93.82 114

IterMVS-LS		84.73 132	84.98 133	83.96 165	87.35 229	63.66 244	83.25 201	89.88 184	76.06 139	89.62 111	92.37 155	73.40 209	92.52 155	78.16 138	94.77 176	95.69 44
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		88.60 70	89.01 67	87.36 93	91.30 136	77.50 101	87.55 109	92.97 90	87.95 25	89.62 111	92.87 137	84.56 73	93.89 106	77.65 145	96.62 95	90.70 236

UniMVSNet (Re)		86.87 91	86.98 96	86.55 106	93.11 79	68.48 199	83.80 187	92.87 92	80.37 87	89.61 113	91.81 170	77.72 153	94.18 95	75.00 179	98.53 16	96.99 22

IS-MVSNet		86.66 97	86.82 100	86.17 118	92.05 109	66.87 216	91.21 43	88.64 203	86.30 33	89.60 114	92.59 145	69.22 242	94.91 71	73.89 191	97.89 52	96.72 24

v2v482		84.09 149	84.24 152	83.62 175	87.13 234	61.40 276	82.71 217	89.71 187	72.19 204	89.55 115	91.41 180	70.70 235	93.20 135	81.02 102	93.76 203	96.25 31

Baseline_NR-MVSNet		84.00 153	85.90 114	78.29 275	91.47 134	53.44 353	82.29 230	87.00 233	79.06 107	89.55 115	95.72 32	77.20 160	86.14 297	72.30 213	98.51 17	95.28 56

CSCG		86.26 101	86.47 103	85.60 130	90.87 149	74.26 131	87.98 104	91.85 122	80.35 88	89.54 117	88.01 257	79.09 140	92.13 166	75.51 172	95.06 161	90.41 245

ambc				82.98 195	90.55 156	64.86 233	88.20 100	89.15 197		89.40 118	93.96 99	71.67 231	91.38 188	78.83 128	96.55 97	92.71 163

DeepPCF-MVS	81.24 5	87.28 88	86.21 108	90.49 42	91.48 133	84.90 42	83.41 196	92.38 106	70.25 225	89.35 119	90.68 208	82.85 92	94.57 81	79.55 120	95.95 127	92.00 199

MVStest1		70.05 330	69.26 333	72.41 337	58.62 424	55.59 337	76.61 315	65.58 393	53.44 365	89.28 120	93.32 120	22.91 424	71.44 380	74.08 188	89.52 288	90.21 252

test_fmvsmconf0.01_n		86.68 96	86.52 102	87.18 94	85.94 265	78.30 89	86.93 120	92.20 111	65.94 265	89.16 121	93.16 124	83.10 89	89.89 235	87.81 15	94.43 185	93.35 135

MSP-MVS		89.08 66	88.16 78	91.83 20	95.76 18	86.14 25	92.75 17	93.90 48	78.43 116	89.16 121	92.25 159	72.03 228	96.36 4	88.21 11	90.93 264	92.98 154
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 63	88.83 72	90.23 47	94.28 47	86.11 26	85.91 141	93.60 61	80.16 91	89.13 123	93.44 118	83.82 80	90.98 198	83.86 72	95.30 153	93.60 128

MDA-MVSNet-bldmvs		77.47 254	76.90 260	79.16 261	79.03 359	64.59 234	66.58 389	75.67 335	73.15 187	88.86 124	88.99 244	66.94 252	81.23 340	64.71 283	88.22 309	91.64 212

EG-PatchMatch MVS		84.08 150	84.11 153	83.98 164	92.22 103	72.61 150	82.20 236	87.02 230	72.63 195	88.86 124	91.02 192	78.52 143	91.11 194	73.41 199	91.09 258	88.21 282

3Dnovator+	83.92 2	89.97 49	89.66 57	90.92 35	91.27 138	81.66 66	91.25 42	94.13 37	88.89 15	88.83 126	94.26 82	77.55 156	95.86 23	84.88 61	95.87 132	95.24 58

EI-MVSNet-UG-set		85.04 125	84.44 147	86.85 101	83.87 300	72.52 153	83.82 185	85.15 259	80.27 90	88.75 127	85.45 304	79.95 136	91.90 173	81.92 97	90.80 270	96.13 33

EI-MVSNet-Vis-set		85.12 124	84.53 145	86.88 100	84.01 296	72.76 144	83.91 183	85.18 258	80.44 86	88.75 127	85.49 302	80.08 134	91.92 172	82.02 94	90.85 269	95.97 38

balanced_conf03		84.80 130	85.40 126	83.00 194	88.95 188	61.44 275	90.42 58	92.37 107	71.48 210	88.72 129	93.13 125	70.16 238	95.15 63	79.26 125	94.11 194	92.41 177

OMC-MVS		88.19 74	87.52 85	90.19 48	91.94 114	81.68 65	87.49 112	93.17 76	76.02 141	88.64 130	91.22 185	84.24 78	93.37 131	77.97 143	97.03 84	95.52 49

RRT-MVS		82.97 174	83.44 161	81.57 225	85.06 277	58.04 317	87.20 114	90.37 165	77.88 123	88.59 131	93.70 113	63.17 274	93.05 142	76.49 160	88.47 301	93.62 126

test_fmvsmconf0.1_n		86.18 105	85.88 115	87.08 96	85.26 274	78.25 90	85.82 145	91.82 124	65.33 279	88.55 132	92.35 156	82.62 96	89.80 237	86.87 35	94.32 188	93.18 145

UA-Net		91.49 19	91.53 24	91.39 27	94.98 35	82.95 58	93.52 7	92.79 95	88.22 22	88.53 133	97.64 3	83.45 86	94.55 83	86.02 51	98.60 13	96.67 25

MP-MVS		91.14 28	90.91 44	91.83 20	96.18 11	86.88 17	92.20 30	93.03 86	82.59 66	88.52 134	94.37 78	86.74 53	95.41 53	86.32 42	98.21 32	93.19 144
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
sasdasda		85.50 113	86.14 109	83.58 177	87.97 212	67.13 210	87.55 109	94.32 21	73.44 177	88.47 135	87.54 268	86.45 58	91.06 196	75.76 170	93.76 203	92.54 171

canonicalmvs		85.50 113	86.14 109	83.58 177	87.97 212	67.13 210	87.55 109	94.32 21	73.44 177	88.47 135	87.54 268	86.45 58	91.06 196	75.76 170	93.76 203	92.54 171

NR-MVSNet		86.00 107	86.22 107	85.34 134	93.24 76	64.56 236	82.21 234	90.46 161	80.99 82	88.42 137	91.97 163	77.56 155	93.85 107	72.46 212	98.65 12	97.61 10

alignmvs		83.94 155	83.98 156	83.80 168	87.80 218	67.88 206	84.54 169	91.42 135	73.27 185	88.41 138	87.96 258	72.33 221	90.83 206	76.02 168	94.11 194	92.69 164

TransMVSNet (Re)		84.02 152	85.74 120	78.85 263	91.00 146	55.20 342	82.29 230	87.26 221	79.65 98	88.38 139	95.52 37	83.00 90	86.88 281	67.97 256	96.60 96	94.45 84

PM-MVS		80.20 226	79.00 235	83.78 170	88.17 209	86.66 19	81.31 244	66.81 391	69.64 230	88.33 140	90.19 222	64.58 263	83.63 327	71.99 215	90.03 281	81.06 380

tttt0517		81.07 207	79.58 230	85.52 131	88.99 187	66.45 220	87.03 119	75.51 337	73.76 170	88.32 141	90.20 221	37.96 398	94.16 99	79.36 124	95.13 157	95.93 41

casdiffmvs		85.21 120	85.85 116	83.31 186	86.17 260	62.77 257	83.03 207	93.93 46	74.69 161	88.21 142	92.68 144	82.29 104	91.89 174	77.87 144	93.75 206	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		71.42 317	70.67 318	73.64 324	69.66 412	70.46 177	66.97 388	89.73 185	42.68 409	88.20 143	83.04 333	43.77 382	60.07 410	65.35 278	86.66 329	90.39 246

SSC-MVS		77.55 253	81.64 193	65.29 379	90.46 157	20.33 425	73.56 348	68.28 382	85.44 37	88.18 144	94.64 64	70.93 233	81.33 339	71.25 217	92.03 241	94.20 94

MVSMamba_PlusPlus		87.53 86	88.86 71	83.54 181	92.03 110	62.26 268	91.49 40	92.62 100	88.07 24	88.07 145	96.17 23	72.24 223	95.79 31	84.85 62	94.16 193	92.58 168

MGCFI-Net		85.04 125	85.95 112	82.31 212	87.52 226	63.59 246	86.23 138	93.96 44	73.46 175	88.07 145	87.83 263	86.46 57	90.87 205	76.17 165	93.89 200	92.47 175

v148		82.31 183	82.48 182	81.81 221	85.59 269	59.66 298	81.47 243	86.02 245	72.85 190	88.05 147	90.65 211	70.73 234	90.91 202	75.15 177	91.79 246	94.87 68

AllTest		87.97 80	87.40 89	89.68 55	91.59 124	83.40 52	89.50 80	95.44 10	79.47 99	88.00 148	93.03 129	82.66 94	91.47 182	70.81 220	96.14 116	94.16 98

TestCases				89.68 55	91.59 124	83.40 52		95.44 10	79.47 99	88.00 148	93.03 129	82.66 94	91.47 182	70.81 220	96.14 116	94.16 98

pm-mvs1		83.69 159	84.95 134	79.91 250	90.04 168	59.66 298	82.43 226	87.44 218	75.52 152	87.85 150	95.26 45	81.25 121	85.65 307	68.74 248	96.04 121	94.42 87

PCF-MVS	74.62 15	82.15 190	80.92 210	85.84 125	89.43 177	72.30 157	80.53 254	91.82 124	57.36 344	87.81 151	89.92 229	77.67 154	93.63 115	58.69 324	95.08 160	91.58 214
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
mvs5depth		83.82 157	84.54 144	81.68 223	82.23 321	68.65 197	86.89 121	89.90 183	80.02 94	87.74 152	97.86 2	64.19 267	82.02 335	76.37 161	95.63 143	94.35 90

test_fmvsmconf_n		85.88 110	85.51 124	86.99 98	84.77 282	78.21 91	85.40 154	91.39 136	65.32 280	87.72 153	91.81 170	82.33 101	89.78 238	86.68 37	94.20 191	92.99 153

FMVSNet2		81.31 204	81.61 195	80.41 244	86.38 250	58.75 312	83.93 182	86.58 236	72.43 196	87.65 154	92.98 131	63.78 270	90.22 222	66.86 259	93.92 199	92.27 187

GeoE		85.45 116	85.81 117	84.37 152	90.08 164	67.07 212	85.86 144	91.39 136	72.33 201	87.59 155	90.25 220	84.85 71	92.37 160	78.00 141	91.94 245	93.66 122

VPA-MVSNet		83.47 166	84.73 136	79.69 254	90.29 160	57.52 322	81.30 246	88.69 202	76.29 137	87.58 156	94.44 71	80.60 129	87.20 275	66.60 264	96.82 90	94.34 91

CPTT-MVS		89.39 58	88.98 69	90.63 40	95.09 33	86.95 16	92.09 32	92.30 109	79.74 96	87.50 157	92.38 152	81.42 119	93.28 133	83.07 78	97.24 79	91.67 211

VDDNet		84.35 140	85.39 127	81.25 229	95.13 32	59.32 301	85.42 153	81.11 300	86.41 32	87.41 158	96.21 22	73.61 202	90.61 214	66.33 266	96.85 87	93.81 117

c3_l		81.64 200	81.59 196	81.79 222	80.86 339	59.15 305	78.61 284	90.18 177	68.36 243	87.20 159	87.11 279	69.39 240	91.62 179	78.16 138	94.43 185	94.60 77

VDD-MVS		84.23 146	84.58 142	83.20 189	91.17 142	65.16 232	83.25 201	84.97 266	79.79 95	87.18 160	94.27 79	74.77 190	90.89 203	69.24 238	96.54 98	93.55 133

MSLP-MVS++		85.00 128	86.03 111	81.90 216	91.84 119	71.56 170	86.75 128	93.02 87	75.95 144	87.12 161	89.39 236	77.98 148	89.40 249	77.46 148	94.78 174	84.75 325

baseline		85.20 121	85.93 113	83.02 193	86.30 255	62.37 265	84.55 167	93.96 44	74.48 163	87.12 161	92.03 162	82.30 103	91.94 171	78.39 131	94.21 190	94.74 75

YYNet1		70.06 329	70.44 322	68.90 358	73.76 396	53.42 354	58.99 406	67.20 387	58.42 334	87.10 163	85.39 306	59.82 294	67.32 395	59.79 320	83.50 365	85.96 310

MDA-MVSNet_test_wron		70.05 330	70.44 322	68.88 359	73.84 395	53.47 352	58.93 407	67.28 386	58.43 333	87.09 164	85.40 305	59.80 295	67.25 396	59.66 321	83.54 364	85.92 312

test_fmvs3		75.72 276	75.20 276	77.27 291	75.01 392	69.47 186	78.93 277	84.88 267	46.67 393	87.08 165	87.84 262	50.44 346	71.62 378	77.42 151	88.53 300	90.72 234

CNVR-MVS		87.81 83	87.68 83	88.21 83	92.87 84	77.30 107	85.25 155	91.23 141	77.31 131	87.07 166	91.47 179	82.94 91	94.71 75	84.67 64	96.27 110	92.62 167

EPP-MVSNet		85.47 115	85.04 132	86.77 103	91.52 132	69.37 187	91.63 39	87.98 215	81.51 77	87.05 167	91.83 168	66.18 257	95.29 56	70.75 223	96.89 86	95.64 46

TinyColmap		81.25 205	82.34 184	77.99 281	85.33 272	60.68 289	82.32 229	88.33 208	71.26 213	86.97 168	92.22 161	77.10 163	86.98 279	62.37 300	95.17 156	86.31 308

eth_miper_zixun_eth		80.84 210	80.22 222	82.71 203	81.41 331	60.98 285	77.81 293	90.14 178	67.31 258	86.95 169	87.24 276	64.26 265	92.31 162	75.23 176	91.61 250	94.85 72

Anonymous20240521		80.18 227	81.25 204	76.95 294	83.15 316	60.84 287	82.46 225	85.99 246	68.76 239	86.78 170	93.73 112	59.13 299	77.44 361	73.71 195	97.55 69	92.56 169

Patchmatch-RL test		74.48 289	73.68 288	76.89 297	84.83 280	66.54 218	72.29 356	69.16 381	57.70 340	86.76 171	86.33 289	45.79 367	82.59 331	69.63 235	90.65 276	81.54 371

XVG-OURS-SEG-HR		89.59 55	89.37 61	90.28 46	94.47 43	85.95 27	86.84 123	93.91 47	80.07 93	86.75 172	93.26 121	93.64 2	90.93 200	84.60 65	90.75 271	93.97 105

h-mvs33		84.25 144	82.76 175	88.72 73	91.82 121	82.60 60	84.00 179	84.98 265	71.27 211	86.70 173	90.55 213	63.04 277	93.92 105	78.26 136	94.20 191	89.63 259

hse-mvs2		83.47 166	81.81 190	88.47 77	91.03 145	82.27 61	82.61 218	83.69 278	71.27 211	86.70 173	86.05 295	63.04 277	92.41 158	78.26 136	93.62 210	90.71 235

HPM-MVS++		88.93 68	88.45 76	90.38 44	94.92 36	85.85 31	89.70 71	91.27 140	78.20 118	86.69 175	92.28 158	80.36 131	95.06 67	86.17 47	96.49 100	90.22 248

TSAR-MVS + MP.		88.14 75	87.82 82	89.09 67	95.72 22	76.74 112	92.49 25	91.19 143	67.85 253	86.63 176	94.84 55	79.58 138	95.96 15	87.62 19	94.50 182	94.56 78
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EI-MVSNet		82.61 178	82.42 183	83.20 189	83.25 312	63.66 244	83.50 194	85.07 260	76.06 139	86.55 177	85.10 310	73.41 207	90.25 219	78.15 140	90.67 273	95.68 45

HQP_MVS		87.75 84	87.43 88	88.70 75	93.45 68	76.42 116	89.45 82	93.61 59	79.44 101	86.55 177	92.95 134	74.84 187	95.22 59	80.78 106	95.83 134	94.46 82

plane_prior3						76.85 111			77.79 125	86.55 177

BH-untuned		80.96 209	80.99 208	80.84 237	88.55 201	68.23 200	80.33 257	88.46 204	72.79 193	86.55 177	86.76 283	74.72 191	91.77 178	61.79 307	88.99 294	82.52 361

MVSTER		77.09 258	75.70 271	81.25 229	75.27 389	61.08 281	77.49 301	85.07 260	60.78 319	86.55 177	88.68 248	43.14 387	90.25 219	73.69 196	90.67 273	92.42 176

旧先验2							81.73 239		56.88 349	86.54 182			84.90 313	72.81 209

IterMVS-SCA-FT		80.64 214	79.41 231	84.34 156	83.93 298	69.66 184	76.28 320	81.09 301	72.43 196	86.47 183	90.19 222	60.46 287	93.15 138	77.45 149	86.39 333	90.22 248

WB-MVS		76.06 272	80.01 228	64.19 382	89.96 170	20.58 424	72.18 357	68.19 383	83.21 59	86.46 184	93.49 117	70.19 237	78.97 355	65.96 268	90.46 278	93.02 151

test_fmvsm_n_1920		83.60 162	82.89 173	85.74 127	85.22 275	77.74 99	84.12 176	90.48 160	59.87 328	86.45 185	91.12 189	75.65 178	85.89 303	82.28 91	90.87 267	93.58 129

DIV-MVS_self_test		80.43 217	80.23 220	81.02 235	79.99 347	59.25 302	77.07 306	87.02 230	67.38 255	86.19 186	89.22 239	63.09 275	90.16 224	76.32 162	95.80 136	93.66 122

CDPH-MVS		86.17 106	85.54 123	88.05 86	92.25 101	75.45 124	83.85 184	92.01 116	65.91 267	86.19 186	91.75 173	83.77 82	94.98 69	77.43 150	96.71 93	93.73 120

cl____		80.42 218	80.23 220	81.02 235	79.99 347	59.25 302	77.07 306	87.02 230	67.37 256	86.18 188	89.21 240	63.08 276	90.16 224	76.31 163	95.80 136	93.65 124

MVS_111021_LR		84.28 143	83.76 159	85.83 126	89.23 182	83.07 55	80.99 250	83.56 280	72.71 194	86.07 189	89.07 243	81.75 116	86.19 295	77.11 154	93.36 211	88.24 281

GBi-Net		82.02 193	82.07 185	81.85 218	86.38 250	61.05 282	86.83 124	88.27 210	72.43 196	86.00 190	95.64 34	63.78 270	90.68 211	65.95 269	93.34 212	93.82 114

test1		82.02 193	82.07 185	81.85 218	86.38 250	61.05 282	86.83 124	88.27 210	72.43 196	86.00 190	95.64 34	63.78 270	90.68 211	65.95 269	93.34 212	93.82 114

FMVSNet3		78.80 240	78.55 243	79.57 256	82.89 319	56.89 328	81.76 238	85.77 248	69.04 236	86.00 190	90.44 215	51.75 339	90.09 230	65.95 269	93.34 212	91.72 208

miper_ehance_all_eth		80.34 221	80.04 227	81.24 231	79.82 350	58.95 307	77.66 295	89.66 188	65.75 272	85.99 193	85.11 309	68.29 247	91.42 186	76.03 167	92.03 241	93.33 136

tfpnnormal		81.79 199	82.95 172	78.31 273	88.93 189	55.40 338	80.83 253	82.85 286	76.81 134	85.90 194	94.14 89	74.58 193	86.51 288	66.82 262	95.68 142	93.01 152

TAPA-MVS	77.73 12	85.71 112	84.83 135	88.37 80	88.78 194	79.72 77	87.15 117	93.50 62	69.17 233	85.80 195	89.56 234	80.76 126	92.13 166	73.21 207	95.51 144	93.25 142
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TSAR-MVS + GP.		83.95 154	82.69 177	87.72 89	89.27 181	81.45 67	83.72 189	81.58 298	74.73 160	85.66 196	86.06 294	72.56 220	92.69 152	75.44 174	95.21 154	89.01 275

EU-MVSNet		75.12 281	74.43 283	77.18 292	83.11 317	59.48 300	85.71 148	82.43 290	39.76 413	85.64 197	88.76 246	44.71 380	87.88 267	73.86 192	85.88 339	84.16 336

MonoMVSNet		76.66 264	77.26 256	74.86 316	79.86 349	54.34 346	86.26 137	86.08 242	71.08 216	85.59 198	88.68 248	53.95 329	85.93 299	63.86 290	80.02 384	84.32 331

LF4IMVS		82.75 177	81.93 188	85.19 135	82.08 322	80.15 74	85.53 150	88.76 201	68.01 248	85.58 199	87.75 264	71.80 229	86.85 282	74.02 189	93.87 201	88.58 278

Patchmtry		76.56 267	77.46 252	73.83 322	79.37 356	46.60 389	82.41 227	76.90 326	73.81 169	85.56 200	92.38 152	48.07 353	83.98 324	63.36 295	95.31 152	90.92 228

MVS_111021_HR		84.63 133	84.34 151	85.49 133	90.18 163	75.86 123	79.23 275	87.13 225	73.35 179	85.56 200	89.34 237	83.60 85	90.50 216	76.64 158	94.05 197	90.09 254

testdata				79.54 257	92.87 84	72.34 156		80.14 307	59.91 327	85.47 202	91.75 173	67.96 249	85.24 309	68.57 252	92.18 240	81.06 380

mvsmamba		80.30 223	78.87 236	84.58 148	88.12 211	67.55 208	92.35 29	84.88 267	63.15 290	85.33 203	90.91 198	50.71 343	95.20 62	66.36 265	87.98 311	90.99 225

test1111		78.53 244	78.85 238	77.56 287	92.22 103	47.49 385	82.61 218	69.24 380	72.43 196	85.28 204	94.20 85	51.91 337	90.07 231	65.36 277	96.45 103	95.11 63

thisisatest0530		79.07 235	77.33 255	84.26 159	87.13 234	64.58 235	83.66 191	75.95 332	68.86 238	85.22 205	87.36 273	38.10 395	93.57 123	75.47 173	94.28 189	94.62 76

BP-MVS1		82.81 175	81.67 192	86.23 113	87.88 216	68.53 198	86.06 140	84.36 273	75.65 149	85.14 206	90.19 222	45.84 366	94.42 86	85.18 57	94.72 178	95.75 43

EC-MVSNet		88.01 78	88.32 77	87.09 95	89.28 180	72.03 161	90.31 59	96.31 4	80.88 84	85.12 207	89.67 233	84.47 75	95.46 50	82.56 87	96.26 111	93.77 119

CLD-MVS		83.18 170	82.64 178	84.79 142	89.05 184	67.82 207	77.93 291	92.52 102	68.33 244	85.07 208	81.54 352	82.06 108	92.96 144	69.35 237	97.91 51	93.57 130
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		82.58 180	81.93 188	84.50 149	87.68 221	73.35 137	86.14 139	77.70 318	61.64 307	85.02 209	91.62 175	77.75 151	86.24 292	82.79 84	87.07 322	93.91 109

FA-MVS(test-final)		83.13 172	83.02 171	83.43 182	86.16 262	66.08 223	88.00 103	88.36 207	75.55 151	85.02 209	92.75 142	65.12 262	92.50 156	74.94 180	91.30 256	91.72 208

DeepC-MVS_fast	80.27 8	86.23 102	85.65 122	87.96 87	91.30 136	76.92 110	87.19 115	91.99 117	70.56 220	84.96 211	90.69 207	80.01 135	95.14 64	78.37 132	95.78 138	91.82 204
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	84.80 130	84.71 139	85.06 138	86.36 253	74.71 127	88.77 94	90.00 181	75.65 149	84.96 211	93.17 123	74.06 197	91.19 191	78.28 135	91.09 258	89.29 267

QAPM		82.59 179	82.59 180	82.58 206	86.44 248	66.69 217	89.94 67	90.36 166	67.97 250	84.94 213	92.58 147	72.71 217	92.18 165	70.63 226	87.73 315	88.85 276

VPNet		80.25 224	81.68 191	75.94 308	92.46 95	47.98 383	76.70 311	81.67 296	73.45 176	84.87 214	92.82 138	74.66 192	86.51 288	61.66 309	96.85 87	93.33 136

NCCC		87.36 87	86.87 98	88.83 70	92.32 100	78.84 86	86.58 131	91.09 145	78.77 112	84.85 215	90.89 199	80.85 125	95.29 56	81.14 101	95.32 150	92.34 182

PHI-MVS		86.38 100	85.81 117	88.08 84	88.44 204	77.34 105	89.35 85	93.05 83	73.15 187	84.76 216	87.70 265	78.87 142	94.18 95	80.67 108	96.29 107	92.73 160

pmmvs-eth3d		78.42 246	77.04 258	82.57 208	87.44 228	74.41 130	80.86 252	79.67 309	55.68 353	84.69 217	90.31 219	60.91 285	85.42 308	62.20 302	91.59 251	87.88 291

test_prior2							83.37 197		75.43 153	84.58 218	91.57 176	81.92 113		79.54 121	96.97 85

fmvsm_s_conf0.5_n_a		82.21 186	81.51 200	84.32 157	86.56 246	73.35 137	85.46 151	77.30 322	61.81 303	84.51 219	90.88 201	77.36 158	86.21 294	82.72 85	86.97 327	93.38 134

TEST9					92.34 98	79.70 78	83.94 180	90.32 168	65.41 278	84.49 220	90.97 194	82.03 109	93.63 115

train_agg		85.98 108	85.28 129	88.07 85	92.34 98	79.70 78	83.94 180	90.32 168	65.79 269	84.49 220	90.97 194	81.93 111	93.63 115	81.21 100	96.54 98	90.88 230

fmvsm_s_conf0.1_n		82.17 188	81.59 196	83.94 167	86.87 244	71.57 169	85.19 157	77.42 321	62.27 301	84.47 222	91.33 182	76.43 174	85.91 301	83.14 75	87.14 320	94.33 92

Gipuma		84.44 138	86.33 105	78.78 264	84.20 294	73.57 135	89.55 77	90.44 162	84.24 48	84.38 223	94.89 53	76.35 177	80.40 347	76.14 166	96.80 91	82.36 363
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		64.31 368	65.85 357	59.67 393	66.54 417	62.24 270	57.76 409	70.96 371	40.13 411	84.36 224	82.09 345	46.93 355	51.67 417	61.99 305	81.89 375	65.12 408

test_8					92.09 107	78.87 85	83.82 185	90.31 170	65.79 269	84.36 224	90.96 196	81.93 111	93.44 128

cl22		78.97 236	78.21 248	81.24 231	77.74 364	59.01 306	77.46 302	87.13 225	65.79 269	84.32 226	85.10 310	58.96 301	90.88 204	75.36 175	92.03 241	93.84 112

CS-MVS		88.14 75	87.67 84	89.54 60	89.56 173	79.18 82	90.47 55	94.77 16	79.37 103	84.32 226	89.33 238	83.87 79	94.53 84	82.45 88	94.89 169	94.90 66

agg_prior					91.58 127	77.69 100		90.30 171		84.32 226			93.18 136

Anonymous202405211		80.51 216	81.19 207	78.49 270	88.48 202	57.26 324	76.63 313	82.49 289	81.21 80	84.30 229	92.24 160	67.99 248	86.24 292	62.22 301	95.13 157	91.98 201

LFMVS		80.15 228	80.56 214	78.89 262	89.19 183	55.93 332	85.22 156	73.78 349	82.96 63	84.28 230	92.72 143	57.38 311	90.07 231	63.80 291	95.75 139	90.68 237

Vis-MVSNet		86.86 92	86.58 101	87.72 89	92.09 107	77.43 104	87.35 113	92.09 114	78.87 110	84.27 231	94.05 92	78.35 146	93.65 113	80.54 110	91.58 252	92.08 195
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ECVR-MVS		78.44 245	78.63 242	77.88 283	91.85 117	48.95 379	83.68 190	69.91 376	72.30 202	84.26 232	94.20 85	51.89 338	89.82 236	63.58 292	96.02 122	94.87 68

FE-MVS		79.98 231	78.86 237	83.36 184	86.47 247	66.45 220	89.73 70	84.74 271	72.80 192	84.22 233	91.38 181	44.95 378	93.60 119	63.93 289	91.50 253	90.04 255

ETV-MVS		84.31 141	83.91 158	85.52 131	88.58 200	70.40 178	84.50 171	93.37 64	78.76 113	84.07 234	78.72 376	80.39 130	95.13 65	73.82 193	92.98 223	91.04 224

fmvsm_s_conf0.5_n		81.91 197	81.30 203	83.75 171	86.02 264	71.56 170	84.73 163	77.11 325	62.44 298	84.00 235	90.68 208	76.42 175	85.89 303	83.14 75	87.11 321	93.81 117

MCST-MVS		84.36 139	83.93 157	85.63 129	91.59 124	71.58 168	83.52 193	92.13 113	61.82 302	83.96 236	89.75 232	79.93 137	93.46 127	78.33 134	94.34 187	91.87 203

新几何1				82.95 197	93.96 59	78.56 88		80.24 306	55.45 354	83.93 237	91.08 191	71.19 232	88.33 263	65.84 272	93.07 220	81.95 367

mmtdpeth		85.13 123	85.78 119	83.17 191	84.65 284	74.71 127	85.87 143	90.35 167	77.94 121	83.82 238	96.96 12	77.75 151	80.03 350	78.44 130	96.21 112	94.79 74

fmvsm_l_conf0.5_n		82.06 192	81.54 199	83.60 176	83.94 297	73.90 133	83.35 198	86.10 241	58.97 330	83.80 239	90.36 216	74.23 195	86.94 280	82.90 81	90.22 279	89.94 256

GDP-MVS		82.17 188	80.85 212	86.15 120	88.65 197	68.95 195	85.65 149	93.02 87	68.42 242	83.73 240	89.54 235	45.07 377	94.31 88	79.66 119	93.87 201	95.19 61

BH-RMVSNet		80.53 215	80.22 222	81.49 227	87.19 233	66.21 222	77.79 294	86.23 239	74.21 165	83.69 241	88.50 251	73.25 212	90.75 208	63.18 297	87.90 312	87.52 295

USDC		76.63 265	76.73 262	76.34 304	83.46 305	57.20 325	80.02 260	88.04 214	52.14 375	83.65 242	91.25 184	63.24 273	86.65 286	54.66 351	94.11 194	85.17 320

miper_enhance_ethall		77.83 249	76.93 259	80.51 242	76.15 381	58.01 318	75.47 332	88.82 199	58.05 338	83.59 243	80.69 356	64.41 264	91.20 190	73.16 208	92.03 241	92.33 183

MM		87.64 85	87.15 90	89.09 67	89.51 174	76.39 118	88.68 96	86.76 234	84.54 46	83.58 244	93.78 108	73.36 210	96.48 2	87.98 13	96.21 112	94.41 88

Effi-MVS+-dtu		85.82 111	83.38 163	93.14 4	87.13 234	91.15 3	87.70 108	88.42 205	74.57 162	83.56 245	85.65 299	78.49 145	94.21 93	72.04 214	92.88 225	94.05 103

CNLPA		83.55 164	83.10 170	84.90 139	89.34 179	83.87 50	84.54 169	88.77 200	79.09 106	83.54 246	88.66 250	74.87 186	81.73 337	66.84 261	92.29 235	89.11 269

SDMVSNet		81.90 198	83.17 168	78.10 278	88.81 192	62.45 263	76.08 324	86.05 244	73.67 171	83.41 247	93.04 127	82.35 100	80.65 344	70.06 232	95.03 162	91.21 220

sd_testset		79.95 232	81.39 202	75.64 311	88.81 192	58.07 316	76.16 323	82.81 287	73.67 171	83.41 247	93.04 127	80.96 124	77.65 360	58.62 325	95.03 162	91.21 220

OpenMVS_ROB	70.19 17	77.77 252	77.46 252	78.71 266	84.39 290	61.15 280	81.18 248	82.52 288	62.45 297	83.34 249	87.37 272	66.20 256	88.66 260	64.69 284	85.02 349	86.32 307

thres100view900		75.45 277	75.05 277	76.66 300	87.27 230	51.88 365	81.07 249	73.26 354	75.68 148	83.25 250	86.37 288	45.54 368	88.80 255	51.98 367	90.99 260	89.31 265

miper_lstm_enhance		76.45 269	76.10 267	77.51 288	76.72 375	60.97 286	64.69 393	85.04 262	63.98 287	83.20 251	88.22 254	56.67 315	78.79 357	73.22 202	93.12 219	92.78 159

IterMVS		76.91 260	76.34 265	78.64 267	80.91 337	64.03 241	76.30 319	79.03 312	64.88 283	83.11 252	89.16 241	59.90 293	84.46 317	68.61 250	85.15 347	87.42 296
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres600view7		75.97 273	75.35 275	77.85 285	87.01 240	51.84 366	80.45 255	73.26 354	75.20 156	83.10 253	86.31 291	45.54 368	89.05 251	55.03 349	92.24 237	92.66 165

mvs_anonymous		78.13 247	78.76 240	76.23 307	79.24 357	50.31 376	78.69 282	84.82 269	61.60 308	83.09 254	92.82 138	73.89 200	87.01 276	68.33 254	86.41 332	91.37 217

fmvsm_l_conf0.5_n_a		81.46 202	80.87 211	83.25 187	83.73 302	73.21 142	83.00 209	85.59 252	58.22 336	82.96 255	90.09 227	72.30 222	86.65 286	81.97 96	89.95 283	89.88 257

test_fmvs2		73.57 297	72.80 299	75.90 309	72.74 405	68.84 196	77.07 306	84.32 275	45.14 399	82.89 256	84.22 322	48.37 351	70.36 382	73.40 200	87.03 324	88.52 279

MVS_Test		82.47 182	83.22 165	80.22 247	82.62 320	57.75 321	82.54 223	91.96 119	71.16 215	82.89 256	92.52 149	77.41 157	90.50 216	80.04 113	87.84 314	92.40 179

reproduce_monomvs		74.09 293	73.23 294	76.65 301	76.52 376	54.54 344	77.50 300	81.40 299	65.85 268	82.86 258	86.67 284	27.38 418	84.53 316	70.24 230	90.66 275	90.89 229

test12				86.57 105	90.74 151	72.63 149		90.69 155		82.76 259		79.20 139	94.80 73		95.32 150	92.27 187

原ACMM1				84.60 147	92.81 89	74.01 132		91.50 131	62.59 293	82.73 260	90.67 210	76.53 173	94.25 91	69.24 238	95.69 141	85.55 316

test_yl		78.71 242	78.51 244	79.32 259	84.32 291	58.84 309	78.38 285	85.33 255	75.99 142	82.49 261	86.57 285	58.01 305	90.02 233	62.74 298	92.73 228	89.10 270

DCV-MVSNet		78.71 242	78.51 244	79.32 259	84.32 291	58.84 309	78.38 285	85.33 255	75.99 142	82.49 261	86.57 285	58.01 305	90.02 233	62.74 298	92.73 228	89.10 270

diffmvs		80.40 219	80.48 217	80.17 248	79.02 360	60.04 293	77.54 298	90.28 174	66.65 263	82.40 263	87.33 274	73.50 204	87.35 273	77.98 142	89.62 287	93.13 146
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 73	76.54 113	79.38 270	77.79 317	52.59 370	82.36 264	90.84 203	66.83 254			91.69 248	81.25 375

D2MVS		76.84 261	75.67 272	80.34 245	80.48 345	62.16 271	73.50 349	84.80 270	57.61 342	82.24 265	87.54 268	51.31 340	87.65 269	70.40 229	93.19 218	91.23 219

VNet		79.31 234	80.27 219	76.44 302	87.92 215	53.95 349	75.58 330	84.35 274	74.39 164	82.23 266	90.72 206	72.84 216	84.39 319	60.38 317	93.98 198	90.97 226

Vis-MVSNet (Re-imp)		77.82 250	77.79 251	77.92 282	88.82 191	51.29 370	83.28 199	71.97 364	74.04 166	82.23 266	89.78 231	57.38 311	89.41 248	57.22 333	95.41 146	93.05 150

API-MVS		82.28 184	82.61 179	81.30 228	86.29 256	69.79 181	88.71 95	87.67 217	78.42 117	82.15 268	84.15 324	77.98 148	91.59 180	65.39 276	92.75 227	82.51 362

DP-MVS Recon		84.05 151	83.22 165	86.52 107	91.73 122	75.27 125	83.23 203	92.40 104	72.04 205	82.04 269	88.33 253	77.91 150	93.95 104	66.17 267	95.12 159	90.34 247

MSDG		80.06 230	79.99 229	80.25 246	83.91 299	68.04 205	77.51 299	89.19 196	77.65 126	81.94 270	83.45 330	76.37 176	86.31 291	63.31 296	86.59 330	86.41 306

test2506		74.12 292	73.39 292	76.28 305	91.85 117	44.20 399	84.06 177	48.20 420	72.30 202	81.90 271	94.20 85	27.22 420	89.77 239	64.81 282	96.02 122	94.87 68

Fast-Effi-MVS+		81.04 208	80.57 213	82.46 210	87.50 227	63.22 251	78.37 287	89.63 190	68.01 248	81.87 272	82.08 346	82.31 102	92.65 153	67.10 258	88.30 308	91.51 216

testgi		72.36 307	74.61 279	65.59 376	80.56 344	42.82 404	68.29 379	73.35 353	66.87 261	81.84 273	89.93 228	72.08 226	66.92 398	46.05 394	92.54 230	87.01 301

tfpn200view9		74.86 285	74.23 284	76.74 299	86.24 257	52.12 362	79.24 273	73.87 347	73.34 180	81.82 274	84.60 319	46.02 361	88.80 255	51.98 367	90.99 260	89.31 265

thres400		75.14 279	74.23 284	77.86 284	86.24 257	52.12 362	79.24 273	73.87 347	73.34 180	81.82 274	84.60 319	46.02 361	88.80 255	51.98 367	90.99 260	92.66 165

CL-MVSNet_self_test		76.81 262	77.38 254	75.12 314	86.90 242	51.34 368	73.20 352	80.63 305	68.30 245	81.80 276	88.40 252	66.92 253	80.90 341	55.35 346	94.90 168	93.12 148

OpenMVS	76.72 13	81.98 195	82.00 187	81.93 215	84.42 289	68.22 201	88.50 99	89.48 193	66.92 260	81.80 276	91.86 165	72.59 219	90.16 224	71.19 219	91.25 257	87.40 297

MVS_0304		85.37 117	84.58 142	87.75 88	85.28 273	73.36 136	86.54 133	85.71 249	77.56 129	81.78 278	92.47 150	70.29 236	96.02 11	85.59 53	95.96 125	93.87 111

AdaColmap		83.66 160	83.69 160	83.57 179	90.05 167	72.26 158	86.29 136	90.00 181	78.19 119	81.65 279	87.16 277	83.40 87	94.24 92	61.69 308	94.76 177	84.21 335

SPE-MVS-test		87.00 90	86.43 104	88.71 74	89.46 176	77.46 102	89.42 84	95.73 7	77.87 124	81.64 280	87.25 275	82.43 98	94.53 84	77.65 145	96.46 102	94.14 100

DELS-MVS		81.44 203	81.25 204	82.03 214	84.27 293	62.87 255	76.47 318	92.49 103	70.97 217	81.64 280	83.83 325	75.03 184	92.70 151	74.29 182	92.22 239	90.51 243
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		83.10 173	82.54 181	84.77 143	92.90 83	69.10 194	86.65 129	90.62 158	54.66 360	81.46 282	90.81 204	76.98 165	94.38 87	72.62 210	96.18 114	90.82 232

TR-MVS		76.77 263	75.79 269	79.72 253	86.10 263	65.79 226	77.14 304	83.02 284	65.20 281	81.40 283	82.10 344	66.30 255	90.73 210	55.57 343	85.27 343	82.65 356

TAMVS		78.08 248	76.36 264	83.23 188	90.62 154	72.87 143	79.08 276	80.01 308	61.72 305	81.35 284	86.92 282	63.96 269	88.78 258	50.61 372	93.01 222	88.04 287

Effi-MVS+		83.90 156	84.01 155	83.57 179	87.22 232	65.61 228	86.55 132	92.40 104	78.64 114	81.34 285	84.18 323	83.65 84	92.93 146	74.22 183	87.87 313	92.17 192

testing3		71.53 316	70.79 317	73.77 323	88.89 190	41.86 406	76.60 316	59.12 410	72.83 191	80.97 286	82.08 346	19.80 426	87.33 274	65.12 279	91.68 249	92.13 194

new-patchmatchnet		70.10 328	73.37 293	60.29 392	81.23 334	16.95 427	59.54 403	74.62 340	62.93 291	80.97 286	87.93 260	62.83 279	71.90 376	55.24 347	95.01 165	92.00 199

PVSNet_Blended_VisFu		81.55 201	80.49 216	84.70 146	91.58 127	73.24 141	84.21 173	91.67 128	62.86 292	80.94 288	87.16 277	67.27 251	92.87 149	69.82 234	88.94 296	87.99 288

BH-w/o		76.57 266	76.07 268	78.10 278	86.88 243	65.92 225	77.63 296	86.33 237	65.69 273	80.89 289	79.95 365	68.97 245	90.74 209	53.01 362	85.25 344	77.62 391

PAPM_NR		83.23 169	83.19 167	83.33 185	90.90 148	65.98 224	88.19 101	90.78 153	78.13 120	80.87 290	87.92 261	73.49 206	92.42 157	70.07 231	88.40 302	91.60 213

ab-mvs		79.67 233	80.56 214	76.99 293	88.48 202	56.93 326	84.70 164	86.06 243	68.95 237	80.78 291	93.08 126	75.30 182	84.62 315	56.78 334	90.90 265	89.43 263

XXY-MVS		74.44 291	76.19 266	69.21 356	84.61 285	52.43 361	71.70 360	77.18 324	60.73 320	80.60 292	90.96 196	75.44 179	69.35 385	56.13 339	88.33 304	85.86 313

HQP4-MVS										80.56 293			94.61 79			93.56 131

HQP-NCC					91.19 139		84.77 160		73.30 182	80.55 294

ACMP_Plane					91.19 139		84.77 160		73.30 182	80.55 294

HQP-MVS		84.61 134	84.06 154	86.27 112	91.19 139	70.66 175	84.77 160	92.68 98	73.30 182	80.55 294	90.17 225	72.10 224	94.61 79	77.30 152	94.47 183	93.56 131

test_cas_vis1_n_1920		69.20 341	69.12 334	69.43 355	73.68 397	62.82 256	70.38 372	77.21 323	46.18 396	80.46 297	78.95 374	52.03 336	65.53 403	65.77 274	77.45 398	79.95 386

AUN-MVS		81.18 206	78.78 239	88.39 79	90.93 147	82.14 62	82.51 224	83.67 279	64.69 284	80.29 298	85.91 298	51.07 341	92.38 159	76.29 164	93.63 209	90.65 239

HyFIR lowres test		75.12 281	72.66 302	82.50 209	91.44 135	65.19 231	72.47 355	87.31 220	46.79 392	80.29 298	84.30 321	52.70 334	92.10 169	51.88 371	86.73 328	90.22 248

test20.03		73.75 296	74.59 281	71.22 343	81.11 335	51.12 372	70.15 373	72.10 363	70.42 221	80.28 300	91.50 178	64.21 266	74.72 372	46.96 391	94.58 181	87.82 293

mvsany_test3		65.48 362	62.97 371	73.03 329	69.99 411	76.17 121	64.83 391	43.71 422	43.68 404	80.25 301	87.05 281	52.83 333	63.09 409	51.92 370	72.44 404	79.84 387

F-COLMAP		84.97 129	83.42 162	89.63 57	92.39 96	83.40 52	88.83 92	91.92 120	73.19 186	80.18 302	89.15 242	77.04 164	93.28 133	65.82 273	92.28 236	92.21 190

GA-MVS		75.83 274	74.61 279	79.48 258	81.87 324	59.25 302	73.42 350	82.88 285	68.68 240	79.75 303	81.80 349	50.62 344	89.46 244	66.85 260	85.64 340	89.72 258

xiu_mvs_v1_base_debu		80.84 210	80.14 224	82.93 198	88.31 205	71.73 164	79.53 266	87.17 222	65.43 275	79.59 304	82.73 340	76.94 166	90.14 227	73.22 202	88.33 304	86.90 302

xiu_mvs_v1_base		80.84 210	80.14 224	82.93 198	88.31 205	71.73 164	79.53 266	87.17 222	65.43 275	79.59 304	82.73 340	76.94 166	90.14 227	73.22 202	88.33 304	86.90 302

xiu_mvs_v1_base_debi		80.84 210	80.14 224	82.93 198	88.31 205	71.73 164	79.53 266	87.17 222	65.43 275	79.59 304	82.73 340	76.94 166	90.14 227	73.22 202	88.33 304	86.90 302

test_fmvs1_n		70.94 321	70.41 324	72.53 335	73.92 394	66.93 215	75.99 325	84.21 277	43.31 406	79.40 307	79.39 370	43.47 383	68.55 390	69.05 243	84.91 352	82.10 365

patch_mono-2		78.89 237	79.39 232	77.41 290	84.78 281	68.11 203	75.60 328	83.11 283	60.96 317	79.36 308	89.89 230	75.18 183	72.97 373	73.32 201	92.30 233	91.15 222

UnsupCasMVSNet_eth		71.63 315	72.30 307	69.62 353	76.47 378	52.70 359	70.03 374	80.97 302	59.18 329	79.36 308	88.21 255	60.50 286	69.12 386	58.33 328	77.62 396	87.04 300

ppachtmachnet_test		74.73 288	74.00 286	76.90 296	80.71 342	56.89 328	71.53 363	78.42 314	58.24 335	79.32 310	82.92 337	57.91 308	84.26 321	65.60 275	91.36 255	89.56 260

MG-MVS		80.32 222	80.94 209	78.47 271	88.18 208	52.62 360	82.29 230	85.01 264	72.01 206	79.24 311	92.54 148	69.36 241	93.36 132	70.65 225	89.19 293	89.45 261

Fast-Effi-MVS+-dtu		82.54 181	81.41 201	85.90 123	85.60 268	76.53 115	83.07 206	89.62 191	73.02 189	79.11 312	83.51 328	80.74 127	90.24 221	68.76 247	89.29 290	90.94 227

CDS-MVSNet		77.32 256	75.40 273	83.06 192	89.00 186	72.48 154	77.90 292	82.17 292	60.81 318	78.94 313	83.49 329	59.30 297	88.76 259	54.64 352	92.37 232	87.93 290
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
baseline1		73.26 299	73.54 290	72.43 336	84.92 279	47.79 384	79.89 262	74.00 345	65.93 266	78.81 314	86.28 292	56.36 317	81.63 338	56.63 335	79.04 391	87.87 292

ttmdpeth		71.72 313	70.67 318	74.86 316	73.08 402	55.88 333	77.41 303	69.27 379	55.86 352	78.66 315	93.77 110	38.01 397	75.39 369	60.12 318	89.87 284	93.31 138

EIA-MVS		82.19 187	81.23 206	85.10 137	87.95 214	69.17 193	83.22 204	93.33 67	70.42 221	78.58 316	79.77 368	77.29 159	94.20 94	71.51 216	88.96 295	91.93 202

thres200		72.34 308	71.55 314	74.70 319	83.48 304	51.60 367	75.02 335	73.71 350	70.14 227	78.56 317	80.57 359	46.20 359	88.20 265	46.99 390	89.29 290	84.32 331

our_test_3		71.85 311	71.59 311	72.62 333	80.71 342	53.78 350	69.72 375	71.71 368	58.80 332	78.03 318	80.51 361	56.61 316	78.84 356	62.20 302	86.04 338	85.23 319

KD-MVS_2432*1600		66.87 352	65.81 358	70.04 348	67.50 414	47.49 385	62.56 397	79.16 310	61.21 315	77.98 319	80.61 357	25.29 422	82.48 332	53.02 360	84.92 350	80.16 384

miper_refine_blended		66.87 352	65.81 358	70.04 348	67.50 414	47.49 385	62.56 397	79.16 310	61.21 315	77.98 319	80.61 357	25.29 422	82.48 332	53.02 360	84.92 350	80.16 384

jason		77.42 255	75.75 270	82.43 211	87.10 237	69.27 188	77.99 290	81.94 294	51.47 379	77.84 321	85.07 313	60.32 289	89.00 252	70.74 224	89.27 292	89.03 273
jason: jason.
MAR-MVS		80.24 225	78.74 241	84.73 144	86.87 244	78.18 92	85.75 146	87.81 216	65.67 274	77.84 321	78.50 377	73.79 201	90.53 215	61.59 310	90.87 267	85.49 318
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		72.29 309	72.00 308	73.14 327	88.63 198	85.00 40	74.65 339	67.39 385	71.94 207	77.80 323	87.66 266	50.48 345	75.83 367	49.95 374	79.51 385	58.58 414

test_fmvs1		69.57 336	69.05 336	71.14 345	69.15 413	65.77 227	73.98 344	83.32 281	42.83 408	77.77 324	78.27 379	43.39 386	68.50 391	68.39 253	84.38 359	79.15 388

pmmvs4		74.92 284	72.98 298	80.73 239	84.95 278	71.71 167	76.23 321	77.59 319	52.83 369	77.73 325	86.38 287	56.35 318	84.97 312	57.72 332	87.05 323	85.51 317

ET-MVSNet_ETH3D		75.28 278	72.77 300	82.81 202	83.03 318	68.11 203	77.09 305	76.51 330	60.67 321	77.60 326	80.52 360	38.04 396	91.15 193	70.78 222	90.68 272	89.17 268

UnsupCasMVSNet_bld		69.21 340	69.68 331	67.82 366	79.42 354	51.15 371	67.82 383	75.79 333	54.15 362	77.47 327	85.36 308	59.26 298	70.64 381	48.46 384	79.35 387	81.66 369

WBMVS		68.76 343	68.43 343	69.75 352	83.29 310	40.30 409	67.36 385	72.21 362	57.09 347	77.05 328	85.53 301	33.68 405	80.51 345	48.79 382	90.90 265	88.45 280

Anonymous20231206		71.38 318	71.88 309	69.88 350	86.31 254	54.37 345	70.39 371	74.62 340	52.57 371	76.73 329	88.76 246	59.94 292	72.06 375	44.35 398	93.23 217	83.23 351

CMPMVS	59.41 20	75.12 281	73.57 289	79.77 251	75.84 384	67.22 209	81.21 247	82.18 291	50.78 384	76.50 330	87.66 266	55.20 325	82.99 330	62.17 304	90.64 277	89.09 272
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		72.10 310	71.69 310	73.32 325	81.57 329	53.02 356	76.77 310	78.37 315	63.31 288	76.37 331	91.85 166	36.68 400	78.98 354	47.87 387	92.45 231	87.95 289

CVMVSNet		72.62 305	71.41 315	76.28 305	83.25 312	60.34 291	83.50 194	79.02 313	37.77 417	76.33 332	85.10 310	49.60 349	87.41 272	70.54 227	77.54 397	81.08 378

PLC	73.85 16	82.09 191	80.31 218	87.45 92	90.86 150	80.29 73	85.88 142	90.65 156	68.17 247	76.32 333	86.33 289	73.12 213	92.61 154	61.40 311	90.02 282	89.44 262
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSFormer		82.23 185	81.57 198	84.19 162	85.54 270	69.26 189	91.98 34	90.08 179	71.54 208	76.23 334	85.07 313	58.69 302	94.27 89	86.26 43	88.77 297	89.03 273

lupinMVS		76.37 270	74.46 282	82.09 213	85.54 270	69.26 189	76.79 309	80.77 304	50.68 386	76.23 334	82.82 338	58.69 302	88.94 253	69.85 233	88.77 297	88.07 284

UWE-MVS		66.43 356	65.56 361	69.05 357	84.15 295	40.98 407	73.06 354	64.71 397	54.84 358	76.18 336	79.62 369	29.21 413	80.50 346	38.54 410	89.75 285	85.66 315

PatchMatch-RL		74.48 289	73.22 295	78.27 276	87.70 220	85.26 38	75.92 326	70.09 374	64.34 285	76.09 337	81.25 354	65.87 259	78.07 359	53.86 354	83.82 362	71.48 400

thisisatest0515		73.00 303	70.52 321	80.46 243	81.45 330	59.90 296	73.16 353	74.31 344	57.86 339	76.08 338	77.78 381	37.60 399	92.12 168	65.00 280	91.45 254	89.35 264

MS-PatchMatch		70.93 322	70.22 325	73.06 328	81.85 325	62.50 262	73.82 347	77.90 316	52.44 372	75.92 339	81.27 353	55.67 322	81.75 336	55.37 345	77.70 395	74.94 396

CHOSEN 1792x2688		72.45 306	70.56 320	78.13 277	90.02 169	63.08 252	68.72 378	83.16 282	42.99 407	75.92 339	85.46 303	57.22 313	85.18 311	49.87 376	81.67 376	86.14 309

CR-MVSNet		74.00 294	73.04 297	76.85 298	79.58 351	62.64 259	82.58 220	76.90 326	50.50 387	75.72 341	92.38 152	48.07 353	84.07 323	68.72 249	82.91 369	83.85 340

RPMNet		78.88 238	78.28 247	80.68 241	79.58 351	62.64 259	82.58 220	94.16 32	74.80 159	75.72 341	92.59 145	48.69 350	95.56 42	73.48 198	82.91 369	83.85 340

DPM-MVS		80.10 229	79.18 234	82.88 201	90.71 153	69.74 182	78.87 280	90.84 151	60.29 324	75.64 343	85.92 297	67.28 250	93.11 139	71.24 218	91.79 246	85.77 314

test_vis1_n		70.29 325	69.99 329	71.20 344	75.97 383	66.50 219	76.69 312	80.81 303	44.22 402	75.43 344	77.23 387	50.00 347	68.59 389	66.71 263	82.85 371	78.52 390

PVSNet_BlendedMVS		78.80 240	77.84 250	81.65 224	84.43 287	63.41 247	79.49 269	90.44 162	61.70 306	75.43 344	87.07 280	69.11 243	91.44 184	60.68 315	92.24 237	90.11 253

PVSNet_Blended		76.49 268	75.40 273	79.76 252	84.43 287	63.41 247	75.14 334	90.44 162	57.36 344	75.43 344	78.30 378	69.11 243	91.44 184	60.68 315	87.70 316	84.42 330

PAPR		78.84 239	78.10 249	81.07 233	85.17 276	60.22 292	82.21 234	90.57 159	62.51 294	75.32 347	84.61 318	74.99 185	92.30 163	59.48 322	88.04 310	90.68 237

N_pmnet		70.20 326	68.80 341	74.38 320	80.91 337	84.81 43	59.12 405	76.45 331	55.06 356	75.31 348	82.36 343	55.74 321	54.82 415	47.02 389	87.24 319	83.52 344

cascas		76.29 271	74.81 278	80.72 240	84.47 286	62.94 253	73.89 346	87.34 219	55.94 351	75.16 349	76.53 393	63.97 268	91.16 192	65.00 280	90.97 263	88.06 286

SCA		73.32 298	72.57 304	75.58 312	81.62 328	55.86 334	78.89 279	71.37 369	61.73 304	74.93 350	83.42 331	60.46 287	87.01 276	58.11 330	82.63 374	83.88 337

test_vis1_n_1920		71.30 319	71.58 313	70.47 346	77.58 367	59.99 295	74.25 340	84.22 276	51.06 381	74.85 351	79.10 372	55.10 326	68.83 388	68.86 246	79.20 390	82.58 358

xiu_mvs_v2_base		77.19 257	76.75 261	78.52 269	87.01 240	61.30 278	75.55 331	87.12 228	61.24 314	74.45 352	78.79 375	77.20 160	90.93 200	64.62 286	84.80 356	83.32 349

CANet		83.79 158	82.85 174	86.63 104	86.17 260	72.21 160	83.76 188	91.43 133	77.24 132	74.39 353	87.45 271	75.36 181	95.42 52	77.03 155	92.83 226	92.25 189

PS-MVSNAJ		77.04 259	76.53 263	78.56 268	87.09 238	61.40 276	75.26 333	87.13 225	61.25 313	74.38 354	77.22 388	76.94 166	90.94 199	64.63 285	84.83 355	83.35 348

MVP-Stereo		75.81 275	73.51 291	82.71 203	89.35 178	73.62 134	80.06 258	85.20 257	60.30 323	73.96 355	87.94 259	57.89 309	89.45 245	52.02 366	74.87 402	85.06 322
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WB-MVSnew		68.72 344	69.01 337	67.85 365	83.22 314	43.98 400	74.93 336	65.98 392	55.09 355	73.83 356	79.11 371	65.63 260	71.89 377	38.21 411	85.04 348	87.69 294

UGNet		82.78 176	81.64 193	86.21 116	86.20 259	76.24 120	86.86 122	85.68 250	77.07 133	73.76 357	92.82 138	69.64 239	91.82 177	69.04 244	93.69 207	90.56 241
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		74.82 286	73.74 287	78.04 280	89.57 172	60.04 293	76.49 317	87.09 229	54.31 361	73.66 358	79.80 366	60.25 290	86.76 285	58.37 326	84.15 360	87.32 298

Test_1112_low_res		73.90 295	73.08 296	76.35 303	90.35 159	55.95 331	73.40 351	86.17 240	50.70 385	73.14 359	85.94 296	58.31 304	85.90 302	56.51 336	83.22 366	87.20 299

1314		73.22 300	72.56 305	75.20 313	80.41 346	57.84 319	81.64 241	85.36 254	51.68 378	73.10 360	76.65 392	61.45 282	85.19 310	63.54 293	79.21 389	82.59 357

test_vis1_rt		65.64 361	64.09 365	70.31 347	66.09 418	70.20 180	61.16 400	81.60 297	38.65 414	72.87 361	69.66 407	52.84 332	60.04 411	56.16 338	77.77 394	80.68 382

Patchmatch-test		65.91 359	67.38 348	61.48 390	75.51 386	43.21 403	68.84 377	63.79 399	62.48 295	72.80 362	83.42 331	44.89 379	59.52 412	48.27 386	86.45 331	81.70 368

PatchmatchNet		69.71 335	68.83 340	72.33 338	77.66 366	53.60 351	79.29 271	69.99 375	57.66 341	72.53 363	82.93 336	46.45 358	80.08 349	60.91 314	72.09 405	83.31 350
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm		67.95 346	68.08 347	67.55 367	78.74 362	43.53 402	75.60 328	67.10 390	54.92 357	72.23 364	88.10 256	42.87 388	75.97 366	52.21 365	80.95 383	83.15 352

pmmvs5		70.73 323	70.07 326	72.72 331	77.03 372	52.73 358	74.14 341	75.65 336	50.36 388	72.17 365	85.37 307	55.42 324	80.67 343	52.86 363	87.59 317	84.77 324

PatchT		70.52 324	72.76 301	63.79 384	79.38 355	33.53 418	77.63 296	65.37 395	73.61 173	71.77 366	92.79 141	44.38 381	75.65 368	64.53 287	85.37 342	82.18 364

MVS		73.21 301	72.59 303	75.06 315	80.97 336	60.81 288	81.64 241	85.92 247	46.03 397	71.68 367	77.54 383	68.47 246	89.77 239	55.70 342	85.39 341	74.60 397

MIMVSNet		71.09 320	71.59 311	69.57 354	87.23 231	50.07 377	78.91 278	71.83 365	60.20 326	71.26 368	91.76 172	55.08 327	76.09 365	41.06 403	87.02 325	82.54 360

WTY-MVS		67.91 347	68.35 344	66.58 373	80.82 340	48.12 382	65.96 390	72.60 357	53.67 364	71.20 369	81.68 351	58.97 300	69.06 387	48.57 383	81.67 376	82.55 359

test0.0.03 1		64.66 365	64.36 364	65.57 377	75.03 391	46.89 388	64.69 393	61.58 407	62.43 299	71.18 370	77.54 383	43.41 384	68.47 392	40.75 405	82.65 372	81.35 372

CostFormer		69.98 332	68.68 342	73.87 321	77.14 370	50.72 374	79.26 272	74.51 342	51.94 377	70.97 371	84.75 316	45.16 376	87.49 271	55.16 348	79.23 388	83.40 347

Syy-MVS		69.40 338	70.03 328	67.49 368	81.72 326	38.94 411	71.00 365	61.99 401	61.38 310	70.81 372	72.36 404	61.37 283	79.30 352	64.50 288	85.18 345	84.22 333

myMVS_eth3d		64.66 365	63.89 366	66.97 371	81.72 326	37.39 414	71.00 365	61.99 401	61.38 310	70.81 372	72.36 404	20.96 425	79.30 352	49.59 377	85.18 345	84.22 333

testing91		69.94 333	68.99 338	72.80 330	83.81 301	45.89 392	71.57 362	73.64 352	68.24 246	70.77 374	77.82 380	34.37 403	84.44 318	53.64 356	87.00 326	88.07 284

testing99		69.27 339	68.15 346	72.63 332	83.29 310	45.45 394	71.15 364	71.08 370	67.34 257	70.43 375	77.77 382	32.24 408	84.35 320	53.72 355	86.33 334	88.10 283

tpmvs		70.16 327	69.56 332	71.96 339	74.71 393	48.13 381	79.63 264	75.45 338	65.02 282	70.26 376	81.88 348	45.34 373	85.68 306	58.34 327	75.39 401	82.08 366

sss		66.92 351	67.26 349	65.90 375	77.23 369	51.10 373	64.79 392	71.72 367	52.12 376	70.13 377	80.18 363	57.96 307	65.36 404	50.21 373	81.01 382	81.25 375

tpm2		68.45 345	66.83 352	73.30 326	78.93 361	48.50 380	79.76 263	71.76 366	47.50 391	69.92 378	83.60 327	42.07 389	88.40 262	48.44 385	79.51 385	83.01 354

testing222		66.93 350	65.30 362	71.81 340	83.38 307	45.83 393	72.06 358	67.50 384	64.12 286	69.68 379	76.37 394	27.34 419	83.00 329	38.88 407	88.38 303	86.62 305

HY-MVS	64.64 18	73.03 302	72.47 306	74.71 318	83.36 309	54.19 347	82.14 237	81.96 293	56.76 350	69.57 380	86.21 293	60.03 291	84.83 314	49.58 378	82.65 372	85.11 321

dmvs_re		66.81 354	66.98 350	66.28 374	76.87 373	58.68 313	71.66 361	72.24 360	60.29 324	69.52 381	73.53 401	52.38 335	64.40 406	44.90 396	81.44 379	75.76 394

ETVMVS		64.67 364	63.34 370	68.64 361	83.44 306	41.89 405	69.56 376	61.70 406	61.33 312	68.74 382	75.76 396	28.76 414	79.35 351	34.65 414	86.16 337	84.67 326

tpm cat1		66.76 355	65.21 363	71.42 342	77.09 371	50.62 375	78.01 289	73.68 351	44.89 400	68.64 383	79.00 373	45.51 370	82.42 334	49.91 375	70.15 408	81.23 377

IB-MVS	62.13 19	71.64 314	68.97 339	79.66 255	80.80 341	62.26 268	73.94 345	76.90 326	63.27 289	68.63 384	76.79 390	33.83 404	91.84 176	59.28 323	87.26 318	84.88 323
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		80.37 220	78.41 246	86.23 113	76.75 374	73.28 139	87.18 116	77.45 320	76.24 138	68.14 385	88.93 245	65.41 261	93.85 107	69.47 236	96.12 118	91.55 215
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet	58.17 21	66.41 357	65.63 360	68.75 360	81.96 323	49.88 378	62.19 399	72.51 359	51.03 382	68.04 386	75.34 398	50.84 342	74.77 370	45.82 395	82.96 367	81.60 370

tpmrst		66.28 358	66.69 354	65.05 380	72.82 404	39.33 410	78.20 288	70.69 373	53.16 368	67.88 387	80.36 362	48.18 352	74.75 371	58.13 329	70.79 407	81.08 378

CANet_DTU		77.81 251	77.05 257	80.09 249	81.37 332	59.90 296	83.26 200	88.29 209	69.16 234	67.83 388	83.72 326	60.93 284	89.47 243	69.22 240	89.70 286	90.88 230

EPMVS		62.47 369	62.63 373	62.01 386	70.63 410	38.74 412	74.76 337	52.86 417	53.91 363	67.71 389	80.01 364	39.40 393	66.60 399	55.54 344	68.81 413	80.68 382

UBG		64.34 367	63.35 369	67.30 369	83.50 303	40.53 408	67.46 384	65.02 396	54.77 359	67.54 390	74.47 400	32.99 407	78.50 358	40.82 404	83.58 363	82.88 355

MDTV_nov1_ep13			68.29 345		78.03 363	43.87 401	74.12 342	72.22 361	52.17 373	67.02 391	85.54 300	45.36 372	80.85 342	55.73 340	84.42 358

testing11		67.38 348	65.93 356	71.73 341	83.37 308	46.60 389	70.95 367	69.40 378	62.47 296	66.14 392	76.66 391	31.22 409	84.10 322	49.10 380	84.10 361	84.49 327

pmmvs3		62.47 369	60.02 382	69.80 351	71.58 408	64.00 242	70.52 370	58.44 413	39.77 412	66.05 393	75.84 395	27.10 421	72.28 374	46.15 393	84.77 357	73.11 398

ADS-MVSNet2		65.87 360	63.64 368	72.55 334	73.16 400	56.92 327	67.10 386	74.81 339	49.74 389	66.04 394	82.97 334	46.71 356	77.26 362	42.29 400	69.96 409	83.46 345

ADS-MVSNet		61.90 371	62.19 375	61.03 391	73.16 400	36.42 416	67.10 386	61.75 404	49.74 389	66.04 394	82.97 334	46.71 356	63.21 407	42.29 400	69.96 409	83.46 345

mvsany_test1		58.48 381	56.47 386	64.50 381	65.90 420	68.21 202	56.95 410	42.11 423	38.30 415	65.69 396	77.19 389	56.96 314	59.35 413	46.16 392	58.96 416	65.93 407

dmvs_testset		60.59 379	62.54 374	54.72 398	77.26 368	27.74 421	74.05 343	61.00 408	60.48 322	65.62 397	67.03 411	55.93 320	68.23 393	32.07 418	69.46 412	68.17 405

DSMNet-mixed		60.98 377	61.61 377	59.09 395	72.88 403	45.05 397	74.70 338	46.61 421	26.20 419	65.34 398	90.32 218	55.46 323	63.12 408	41.72 402	81.30 381	69.09 404

JIA-IIPM		69.41 337	66.64 355	77.70 286	73.19 399	71.24 172	75.67 327	65.56 394	70.42 221	65.18 399	92.97 133	33.64 406	83.06 328	53.52 358	69.61 411	78.79 389

test-LLR		67.21 349	66.74 353	68.63 362	76.45 379	55.21 340	67.89 380	67.14 388	62.43 299	65.08 400	72.39 402	43.41 384	69.37 383	61.00 312	84.89 353	81.31 373

test-mter		65.00 363	63.79 367	68.63 362	76.45 379	55.21 340	67.89 380	67.14 388	50.98 383	65.08 400	72.39 402	28.27 416	69.37 383	61.00 312	84.89 353	81.31 373

PMMVS2		55.64 384	59.27 383	44.74 400	64.30 422	12.32 428	40.60 415	49.79 419	53.19 367	65.06 402	84.81 315	53.60 331	49.76 418	32.68 417	89.41 289	72.15 399

baseline2		69.77 334	66.89 351	78.41 272	79.51 353	58.09 315	76.23 321	69.57 377	57.50 343	64.82 403	77.45 385	46.02 361	88.44 261	53.08 359	77.83 393	88.70 277

gg-mvs-nofinetune		68.96 342	69.11 335	68.52 364	76.12 382	45.32 395	83.59 192	55.88 415	86.68 29	64.62 404	97.01 9	30.36 411	83.97 325	44.78 397	82.94 368	76.26 393

PAPM		71.77 312	70.06 327	76.92 295	86.39 249	53.97 348	76.62 314	86.62 235	53.44 365	63.97 405	84.73 317	57.79 310	92.34 161	39.65 406	81.33 380	84.45 329

new_pmnet		55.69 383	57.66 384	49.76 399	75.47 387	30.59 419	59.56 402	51.45 418	43.62 405	62.49 406	75.48 397	40.96 391	49.15 419	37.39 412	72.52 403	69.55 403

MDTV_nov1_ep13_2view						27.60 422	70.76 369		46.47 395	61.27 407		45.20 374		49.18 379		83.75 342

dp		60.70 378	60.29 381	61.92 388	72.04 407	38.67 413	70.83 368	64.08 398	51.28 380	60.75 408	77.28 386	36.59 401	71.58 379	47.41 388	62.34 415	75.52 395

TESTMET0.1,1		61.29 374	60.32 380	64.19 382	72.06 406	51.30 369	67.89 380	62.09 400	45.27 398	60.65 409	69.01 408	27.93 417	64.74 405	56.31 337	81.65 378	76.53 392

PMMVS		61.65 372	60.38 379	65.47 378	65.40 421	69.26 189	63.97 395	61.73 405	36.80 418	60.11 410	68.43 409	59.42 296	66.35 400	48.97 381	78.57 392	60.81 411

PVSNet_0	51.08 22	56.10 382	54.97 387	59.48 394	75.12 390	53.28 355	55.16 411	61.89 403	44.30 401	59.16 411	62.48 414	54.22 328	65.91 402	35.40 413	47.01 417	59.25 413

MVS-HIRNet		61.16 375	62.92 372	55.87 396	79.09 358	35.34 417	71.83 359	57.98 414	46.56 394	59.05 412	91.14 188	49.95 348	76.43 364	38.74 408	71.92 406	55.84 415

E-PMN		61.59 373	61.62 376	61.49 389	66.81 416	55.40 338	53.77 412	60.34 409	66.80 262	58.90 413	65.50 412	40.48 392	66.12 401	55.72 341	86.25 335	62.95 410

GG-mvs-BLEND				67.16 370	73.36 398	46.54 391	84.15 175	55.04 416		58.64 414	61.95 415	29.93 412	83.87 326	38.71 409	76.92 399	71.07 401

EPNet_dtu		72.87 304	71.33 316	77.49 289	77.72 365	60.55 290	82.35 228	75.79 333	66.49 264	58.39 415	81.06 355	53.68 330	85.98 298	53.55 357	92.97 224	85.95 311
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		41.90 386	42.65 389	39.67 401	70.86 409	21.11 423	61.01 401	21.42 428	57.36 344	57.97 416	50.06 417	16.40 427	58.73 414	21.03 421	27.69 421	39.17 417

EMVS		61.10 376	60.81 378	61.99 387	65.96 419	55.86 334	53.10 413	58.97 412	67.06 259	56.89 417	63.33 413	40.98 390	67.03 397	54.79 350	86.18 336	63.08 409

CHOSEN 280x420		59.08 380	56.52 385	66.76 372	76.51 377	64.39 238	49.62 414	59.00 411	43.86 403	55.66 418	68.41 410	35.55 402	68.21 394	43.25 399	76.78 400	67.69 406

MVE	40.22 23	51.82 385	50.47 388	55.87 396	62.66 423	51.91 364	31.61 417	39.28 424	40.65 410	50.76 419	74.98 399	56.24 319	44.67 420	33.94 416	64.11 414	71.04 402
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
kuosan		30.83 387	32.17 390	26.83 403	53.36 425	19.02 426	57.90 408	20.44 429	38.29 416	38.01 420	37.82 419	15.18 428	33.45 422	7.74 423	20.76 422	28.03 418

DeepMVS_CX				24.13 404	32.95 426	29.49 420		21.63 427	12.07 420	37.95 421	45.07 418	30.84 410	19.21 423	17.94 422	33.06 420	23.69 419

tmp_tt		20.25 390	24.50 393	7.49 405	4.47 428	8.70 429	34.17 416	25.16 426	1.00 423	32.43 422	18.49 420	39.37 394	9.21 424	21.64 420	43.75 418	4.57 420

test_method		30.46 388	29.60 391	33.06 402	17.99 427	3.84 430	13.62 418	73.92 346	2.79 421	18.29 423	53.41 416	28.53 415	43.25 421	22.56 419	35.27 419	52.11 416

EGC-MVSNET		74.79 287	69.99 329	89.19 65	94.89 38	87.00 15	91.89 37	86.28 238	1.09 422	2.23 424	95.98 27	81.87 114	89.48 242	79.76 116	95.96 125	91.10 223

testmvs		5.91 394	7.65 397	0.72 407	1.20 429	0.37 432	59.14 404	0.67 431	0.49 425	1.11 425	2.76 424	0.94 430	0.24 426	1.02 425	1.47 423	1.55 422

test123		6.27 393	8.08 396	0.84 406	1.11 430	0.57 431	62.90 396	0.82 430	0.54 424	1.07 426	2.75 425	1.26 429	0.30 425	1.04 424	1.26 424	1.66 421

mmdepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

cdsmvs_eth3d_5k		20.81 389	27.75 392	0.00 408	0.00 431	0.00 433	0.00 419	85.44 253	0.00 426	0.00 427	82.82 338	81.46 118	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		6.41 392	8.55 395	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	76.94 166	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

ab-mvs-re		6.65 391	8.87 394	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	79.80 366	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						37.39 414								52.61 364

MSC_two_6792asdad				88.81 71	91.55 129	77.99 94		91.01 147					96.05 9	87.45 23	98.17 35	92.40 179

No_MVS				88.81 71	91.55 129	77.99 94		91.01 147					96.05 9	87.45 23	98.17 35	92.40 179

eth-test2					0.00 431

eth-test					0.00 431

OPU-MVS				88.27 82	91.89 115	77.83 97	90.47 55				91.22 185	81.12 122	94.68 76	74.48 181	95.35 148	92.29 185

save fliter					93.75 63	77.44 103	86.31 135	89.72 186	70.80 218

test_0728_SECOND				86.79 102	94.25 48	72.45 155	90.54 52	94.10 39					95.88 18	86.42 39	97.97 46	92.02 198

GSMVS																83.88 337

sam_mvs1												46.11 360				83.88 337

sam_mvs												45.92 365

MTGPA								91.81 126

test_post1							78.85 281				3.13 422	45.19 375	80.13 348	58.11 330

test_post											3.10 423	45.43 371	77.22 363

patchmatchnet-post											81.71 350	45.93 364	87.01 276

MTMP							90.66 48	33.14 425

gm-plane-assit					75.42 388	44.97 398			52.17 373		72.36 404		87.90 266	54.10 353

test9_res														80.83 105	96.45 103	90.57 240

agg_prior2														79.68 118	96.16 115	90.22 248

test_prior4						78.97 84	84.59 166

test_prior				86.32 110	90.59 155	71.99 162		92.85 93					94.17 97			92.80 158

新几何2							81.72 240

旧先验1					91.97 111	71.77 163		81.78 295			91.84 167	73.92 199			93.65 208	83.61 343

无先验							82.81 215	85.62 251	58.09 337				91.41 187	67.95 257		84.48 328

原ACMM2							82.26 233

testdata2													86.43 290	63.52 294

segment_acmp												81.94 110

testdata1							79.62 265		73.95 168

plane_prior7					93.45 68	77.31 106

plane_prior6					92.61 90	76.54 113						74.84 187

plane_prior5								93.61 59					95.22 59	80.78 106	95.83 134	94.46 82

plane_prior4											92.95 134

plane_prior2							89.45 82		79.44 101

plane_prior1					92.83 88

plane_prior						76.42 116	87.15 117		75.94 145						95.03 162

n2								0.00 432

nn								0.00 432

door-mid								74.45 343

test11								91.46 132

door								72.57 358

HQP5-MVS						70.66 175

BP-MVS														77.30 152

HQP3-MVS								92.68 98							94.47 183

HQP2-MVS												72.10 224

NP-MVS					91.95 112	74.55 129					90.17 225

ACMMP++_ref															95.74 140

ACMMP++															97.35 75

Test By Simon												79.09 140

High-resolution multi-view benchmark