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 60	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	84.21 162	96.51 7	57.84 321	88.93 90	92.84 94	91.92 4	96.16 4	96.23 21	86.95 51	95.99 12	79.05 128	98.57 15	98.80 6

PS-CasMVS		90.06 43	91.92 15	84.47 153	96.56 6	58.83 313	89.04 88	92.74 97	91.40 6	96.12 5	96.06 26	87.23 48	95.57 41	79.42 125	98.74 6	99.00 2

LCM-MVSNet-Re		83.48 167	85.06 131	78.75 267	85.94 266	55.75 338	80.05 261	94.27 24	76.47 136	96.09 6	94.54 67	83.31 88	89.75 241	59.95 321	94.89 169	90.75 235

PEN-MVS		90.03 45	91.88 18	84.48 152	96.57 5	58.88 310	88.95 89	93.19 75	91.62 5	96.01 7	96.16 24	87.02 50	95.60 40	78.69 131	98.72 9	98.97 3

CP-MVSNet		89.27 62	90.91 44	84.37 154	96.34 8	58.61 316	88.66 97	92.06 115	90.78 7	95.67 8	95.17 47	81.80 115	95.54 44	79.00 129	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	92.08 197

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	62.39 266	89.54 79	93.31 70	90.21 12	95.57 11	95.66 33	81.42 119	95.90 17	80.94 105	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	91.76 208

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	91.76 208

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 60	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		75.13 282	79.30 235	62.63 387	75.56 387	75.18 126	80.89 252	73.10 358	75.06 158	94.76 16	95.32 41	87.73 43	52.85 418	34.16 417	97.11 82	59.85 414

ACMH	76.49 14	89.34 59	91.14 35	83.96 167	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 76	98.30 25	93.20 145
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	69.19 194	87.84 107	88.05 213	81.66 75	94.64 18	96.53 17	65.94 260	94.75 74	83.02 82	96.83 89	95.41 53

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 70	95.97 124	95.52 51

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 72	95.92 130	95.34 55

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	79.84 117	95.21 154	91.82 206

UniMVSNet_ETH3D		89.12 65	90.72 47	84.31 160	97.00 2	64.33 241	89.67 74	88.38 206	88.84 17	94.29 22	97.57 4	90.48 13	91.26 189	72.57 213	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 80	96.28 108	96.15 33

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	92.29 187

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 68	97.81 55	91.70 212
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	92.98 156
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	78.35 135	98.76 4	95.61 50

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 62	98.45 19	92.41 179
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	92.73 162

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	92.73 162

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	90.55 244
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	92.98 156

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 57	98.73 7	95.23 61

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 57	98.73 7	95.23 61

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	92.48 175

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	92.04 199

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	92.19 193

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 99

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	74.12 188	96.10 119	94.45 86

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	74.12 188	96.10 119	94.45 86

Anonymous20231211		88.40 71	89.62 59	84.73 145	90.46 157	65.27 231	88.86 91	93.02 87	87.15 28	93.05 46	97.10 8	82.28 105	92.02 170	76.70 159	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 66
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	92.29 158	86.11 63	90.22 222	86.24 46	97.24 79	91.36 220
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 84	98.76 4	94.87 70
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	93.88 112
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	63.28 252	86.64 130	92.20 111	75.42 154	92.81 53	94.50 68	74.05 198	94.06 101	83.88 73	96.28 108	97.17 18

dcpmvs_2		84.23 146	85.14 130	81.50 228	88.61 199	61.98 274	82.90 213	93.11 79	68.66 241	92.77 54	92.39 151	78.50 144	87.63 272	76.99 158	92.30 233	94.90 68

v8		86.22 103	86.83 99	84.36 156	87.82 217	62.35 268	86.42 134	91.33 138	76.78 135	92.73 55	94.48 70	73.41 207	93.72 112	83.10 79	95.41 146	97.01 21

nrg030		87.85 82	88.49 75	85.91 122	90.07 166	69.73 185	87.86 106	94.20 30	74.04 166	92.70 56	94.66 60	85.88 66	91.50 181	79.72 119	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 91
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 65	97.55 69	94.10 104
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 41

K. test v3		85.14 122	84.73 136	86.37 109	91.13 143	69.63 187	85.45 152	76.68 331	84.06 50	92.44 60	96.99 10	62.03 282	94.65 77	80.58 111	93.24 216	94.83 75

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 80
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 56	97.51 73	94.30 95

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	79.95 116	98.27 26	95.04 67
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 88	98.04 39	93.64 127

TranMVSNet+NR-MVSNet		87.86 81	88.76 74	85.18 136	94.02 58	64.13 242	84.38 172	91.29 139	84.88 44	92.06 65	93.84 105	86.45 58	93.73 111	73.22 204	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	92.30 186

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	93.27 142

FC-MVSNet-test		85.93 109	87.05 94	82.58 208	92.25 101	56.44 332	85.75 146	93.09 81	77.33 130	91.94 68	94.65 61	74.78 189	93.41 130	75.11 180	98.58 14	97.88 7

lessismore_v0				85.95 121	91.10 144	70.99 174		70.91 374		91.79 69	94.42 74	61.76 283	92.93 146	79.52 124	93.03 221	93.93 109

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 56
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	93.96 108

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	93.12 150

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	92.85 159

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	93.99 106

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	93.93 109

test_fmvsmvis_n_1920		85.22 119	85.36 128	84.81 142	85.80 268	76.13 122	85.15 158	92.32 108	61.40 311	91.33 76	90.85 204	83.76 83	86.16 298	84.31 69	93.28 215	92.15 195

ANet_high		83.17 173	85.68 121	75.65 312	81.24 335	45.26 398	79.94 263	92.91 91	83.83 51	91.33 76	96.88 13	80.25 132	85.92 302	68.89 247	95.89 131	95.76 43

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	94.12 103

casdiffmvs_mvg		86.72 95	87.51 86	84.36 156	87.09 238	65.22 232	84.16 174	94.23 27	77.89 122	91.28 79	93.66 114	84.35 76	92.71 150	80.07 113	94.87 172	95.16 64
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
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 94	97.18 81	90.45 246
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 75	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	92.55 172

FIs		85.35 118	86.27 106	82.60 207	91.86 116	57.31 325	85.10 159	93.05 83	75.83 146	91.02 83	93.97 96	73.57 203	92.91 148	73.97 192	98.02 42	97.58 12

UniMVSNet_NR-MVSNet		86.84 93	87.06 93	86.17 118	92.86 86	67.02 215	82.55 222	91.56 129	83.08 62	90.92 84	91.82 171	78.25 147	93.99 102	74.16 186	98.35 22	97.49 13

DU-MVS		86.80 94	86.99 95	86.21 116	93.24 76	67.02 215	83.16 205	92.21 110	81.73 74	90.92 84	91.97 164	77.20 160	93.99 102	74.16 186	98.35 22	97.61 10

tt0805		88.09 77	89.79 55	82.98 197	93.26 75	63.94 245	91.10 45	89.64 189	85.07 41	90.91 86	91.09 192	89.16 24	91.87 175	82.03 95	95.87 132	93.13 148

V42		83.47 168	83.37 165	83.75 173	83.16 317	63.33 251	81.31 244	90.23 175	69.51 231	90.91 86	90.81 206	74.16 196	92.29 164	80.06 114	90.22 281	95.62 49

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	93.83 115

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	73.75 196	94.81 173	93.70 123

WR-MVS		83.56 165	84.40 149	81.06 236	93.43 70	54.88 345	78.67 285	85.02 265	81.24 79	90.74 90	91.56 179	72.85 215	91.08 195	68.00 257	98.04 39	97.23 16

v1240		84.30 142	84.51 146	83.65 176	87.65 223	61.26 281	82.85 214	91.54 130	67.94 251	90.68 91	90.65 213	71.71 231	93.64 114	82.84 85	94.78 174	96.07 36

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 97	96.75 92

MIMVSNet1		83.63 162	84.59 141	80.74 240	94.06 57	62.77 259	82.72 216	84.53 274	77.57 128	90.34 93	95.92 28	76.88 172	85.83 307	61.88 308	97.42 74	93.62 128

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	80.87 106	95.50 145	94.53 83

KD-MVS_self_test		81.93 198	83.14 171	78.30 276	84.75 285	52.75 359	80.37 258	89.42 195	70.24 226	90.26 95	93.39 119	74.55 194	86.77 286	68.61 252	96.64 94	95.38 54

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	77.55 149	97.07 83	83.13 355
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PC_three_1452									58.96 333	90.06 97	91.33 184	80.66 128	93.03 143	75.78 171	95.94 128	92.48 175

v1921920		84.23 146	84.37 150	83.79 171	87.64 224	61.71 275	82.91 212	91.20 142	67.94 251	90.06 97	90.34 219	72.04 227	93.59 120	82.32 92	94.91 167	96.07 36

ITE_SJBPF				90.11 49	90.72 152	84.97 41		90.30 171	81.56 76	90.02 99	91.20 189	82.40 99	90.81 207	73.58 199	94.66 179	94.56 80

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 96

X-MVStestdata		85.04 125	82.70 178	92.08 9	95.64 24	86.25 22	92.64 19	93.33 67	85.07 41	89.99 100	16.05 423	86.57 55	95.80 28	87.35 27	97.62 64	94.20 96

v1192		84.57 135	84.69 140	84.21 162	87.75 219	62.88 256	83.02 208	91.43 133	69.08 235	89.98 102	90.89 201	72.70 218	93.62 118	82.41 91	94.97 166	96.13 34

Anonymous20240529		86.20 104	87.13 91	83.42 185	90.19 162	64.55 239	84.55 167	90.71 154	85.85 36	89.94 103	95.24 46	82.13 107	90.40 218	69.19 243	96.40 105	95.31 57

pmmvs6		86.52 99	88.06 79	81.90 218	92.22 103	62.28 269	84.66 165	89.15 197	83.54 57	89.85 104	97.32 5	88.08 38	86.80 285	70.43 230	97.30 78	96.62 26

v144192		84.24 145	84.41 148	83.71 175	87.59 225	61.57 276	82.95 211	91.03 146	67.82 254	89.80 105	90.49 216	73.28 211	93.51 125	81.88 100	94.89 169	96.04 38

v1144		84.54 137	84.72 138	84.00 165	87.67 222	62.55 263	82.97 210	90.93 150	70.32 224	89.80 105	90.99 195	73.50 204	93.48 126	81.69 101	94.65 180	95.97 39

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 71	98.03 41	93.26 143
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	87.74 270	76.54 161	88.74 301	96.61 27

IU-MVS					94.18 50	72.64 147		90.82 152	56.98 350	89.67 109				85.78 54	97.92 49	93.28 141

FMVSNet1		84.55 136	85.45 125	81.85 220	90.27 161	61.05 284	86.83 124	88.27 210	78.57 115	89.66 110	95.64 34	75.43 180	90.68 211	69.09 244	95.33 149	93.82 116

IterMVS-LS		84.73 132	84.98 133	83.96 167	87.35 229	63.66 246	83.25 201	89.88 184	76.06 139	89.62 111	92.37 155	73.40 209	92.52 155	78.16 140	94.77 176	95.69 46
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	77.65 147	96.62 95	90.70 238

UniMVSNet (Re)		86.87 91	86.98 96	86.55 106	93.11 79	68.48 201	83.80 187	92.87 92	80.37 87	89.61 113	91.81 172	77.72 153	94.18 95	75.00 181	98.53 16	96.99 22

IS-MVSNet		86.66 97	86.82 100	86.17 118	92.05 109	66.87 218	91.21 43	88.64 203	86.30 33	89.60 114	92.59 145	69.22 244	94.91 71	73.89 193	97.89 52	96.72 24

v2v482		84.09 149	84.24 152	83.62 177	87.13 234	61.40 278	82.71 217	89.71 187	72.19 204	89.55 115	91.41 182	70.70 237	93.20 135	81.02 104	93.76 203	96.25 32

Baseline_NR-MVSNet		84.00 153	85.90 114	78.29 277	91.47 134	53.44 355	82.29 230	87.00 235	79.06 107	89.55 115	95.72 32	77.20 160	86.14 299	72.30 215	98.51 17	95.28 58

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	88.01 259	79.09 140	92.13 166	75.51 174	95.06 161	90.41 247

ambc				82.98 197	90.55 156	64.86 235	88.20 100	89.15 197		89.40 118	93.96 99	71.67 232	91.38 188	78.83 130	96.55 97	92.71 165

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	90.68 210	82.85 92	94.57 81	79.55 122	95.95 127	92.00 201

MVStest1		70.05 332	69.26 335	72.41 339	58.62 426	55.59 339	76.61 317	65.58 395	53.44 367	89.28 120	93.32 120	22.91 426	71.44 382	74.08 190	89.52 290	90.21 254

test_fmvsmconf0.01_n		86.68 96	86.52 102	87.18 94	85.94 266	78.30 89	86.93 120	92.20 111	65.94 267	89.16 121	93.16 124	83.10 89	89.89 235	87.81 15	94.43 185	93.35 137

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	92.25 160	72.03 228	96.36 4	88.21 11	90.93 266	92.98 156
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 74	95.30 153	93.60 130

MDA-MVSNet-bldmvs		77.47 256	76.90 262	79.16 263	79.03 361	64.59 236	66.58 391	75.67 337	73.15 187	88.86 124	88.99 246	66.94 254	81.23 342	64.71 285	88.22 311	91.64 214

EG-PatchMatch MVS		84.08 150	84.11 153	83.98 166	92.22 103	72.61 150	82.20 236	87.02 232	72.63 195	88.86 124	91.02 194	78.52 143	91.11 194	73.41 201	91.09 260	88.21 284

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 63	95.87 132	95.24 60

EI-MVSNet-UG-set		85.04 125	84.44 147	86.85 101	83.87 302	72.52 153	83.82 185	85.15 261	80.27 90	88.75 127	85.45 306	79.95 136	91.90 173	81.92 99	90.80 272	96.13 34

EI-MVSNet-Vis-set		85.12 124	84.53 145	86.88 100	84.01 298	72.76 144	83.91 183	85.18 260	80.44 86	88.75 127	85.49 304	80.08 134	91.92 172	82.02 96	90.85 271	95.97 39

balanced_conf03		84.80 130	85.40 126	83.00 196	88.95 188	61.44 277	90.42 58	92.37 107	71.48 210	88.72 129	93.13 125	70.16 240	95.15 63	79.26 127	94.11 194	92.41 179

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	91.22 187	84.24 78	93.37 131	77.97 145	97.03 84	95.52 51

RRT-MVS		82.97 176	83.44 162	81.57 227	85.06 279	58.04 319	87.20 114	90.37 165	77.88 123	88.59 131	93.70 113	63.17 276	93.05 142	76.49 162	88.47 303	93.62 128

test_fmvsmconf0.1_n		86.18 105	85.88 115	87.08 96	85.26 276	78.25 90	85.82 145	91.82 124	65.33 281	88.55 132	92.35 157	82.62 96	89.80 237	86.87 35	94.32 188	93.18 147

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 52	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	93.19 146
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	83.58 179	87.97 212	67.13 212	87.55 109	94.32 21	73.44 177	88.47 135	87.54 270	86.45 58	91.06 196	75.76 172	93.76 203	92.54 173

canonicalmvs		85.50 113	86.14 109	83.58 179	87.97 212	67.13 212	87.55 109	94.32 21	73.44 177	88.47 135	87.54 270	86.45 58	91.06 196	75.76 172	93.76 203	92.54 173

NR-MVSNet		86.00 107	86.22 107	85.34 134	93.24 76	64.56 238	82.21 234	90.46 161	80.99 82	88.42 137	91.97 164	77.56 155	93.85 107	72.46 214	98.65 12	97.61 10

alignmvs		83.94 155	83.98 156	83.80 170	87.80 218	67.88 208	84.54 169	91.42 135	73.27 185	88.41 138	87.96 260	72.33 221	90.83 206	76.02 170	94.11 194	92.69 166

TransMVSNet (Re)		84.02 152	85.74 120	78.85 265	91.00 146	55.20 344	82.29 230	87.26 222	79.65 98	88.38 139	95.52 37	83.00 90	86.88 283	67.97 258	96.60 96	94.45 86

PM-MVS		80.20 228	79.00 237	83.78 172	88.17 209	86.66 19	81.31 244	66.81 393	69.64 230	88.33 140	90.19 224	64.58 265	83.63 329	71.99 217	90.03 283	81.06 382

tttt0517		81.07 209	79.58 232	85.52 131	88.99 187	66.45 222	87.03 119	75.51 339	73.76 170	88.32 141	90.20 223	37.96 400	94.16 99	79.36 126	95.13 157	95.93 42

casdiffmvs		85.21 120	85.85 116	83.31 188	86.17 260	62.77 259	83.03 207	93.93 46	74.69 161	88.21 142	92.68 144	82.29 104	91.89 174	77.87 146	93.75 206	95.27 59
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		71.42 319	70.67 320	73.64 326	69.66 414	70.46 177	66.97 390	89.73 185	42.68 411	88.20 143	83.04 335	43.77 384	60.07 412	65.35 280	86.66 331	90.39 248

SSC-MVS		77.55 255	81.64 195	65.29 381	90.46 157	20.33 427	73.56 350	68.28 384	85.44 37	88.18 144	94.64 64	70.93 235	81.33 341	71.25 219	92.03 241	94.20 96

MVSMamba_PlusPlus		87.53 86	88.86 71	83.54 183	92.03 110	62.26 270	91.49 40	92.62 100	88.07 24	88.07 145	96.17 23	72.24 223	95.79 31	84.85 64	94.16 193	92.58 170

MGCFI-Net		85.04 125	85.95 112	82.31 214	87.52 226	63.59 248	86.23 138	93.96 44	73.46 175	88.07 145	87.83 265	86.46 57	90.87 205	76.17 167	93.89 200	92.47 177

v148		82.31 185	82.48 184	81.81 223	85.59 270	59.66 300	81.47 243	86.02 247	72.85 190	88.05 147	90.65 213	70.73 236	90.91 202	75.15 179	91.79 247	94.87 70

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	70.81 222	96.14 116	94.16 100

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	70.81 222	96.14 116	94.16 100

fmvsm_s_conf0.1_n_2		83.82 157	83.49 161	84.84 140	85.99 265	70.19 181	80.93 251	87.58 218	67.26 259	87.94 150	92.37 155	71.40 233	88.01 266	86.03 49	91.87 246	96.31 31

pm-mvs1		83.69 160	84.95 134	79.91 252	90.04 168	59.66 300	82.43 226	87.44 219	75.52 152	87.85 151	95.26 45	81.25 121	85.65 309	68.74 250	96.04 121	94.42 89

PCF-MVS	74.62 15	82.15 192	80.92 212	85.84 125	89.43 177	72.30 157	80.53 256	91.82 124	57.36 346	87.81 152	89.92 231	77.67 154	93.63 115	58.69 326	95.08 160	91.58 216
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.5_n_2		83.62 163	83.29 166	84.62 148	85.43 273	70.18 182	80.61 255	87.24 223	67.14 260	87.79 153	91.87 166	71.79 230	87.98 267	86.00 53	91.77 249	95.71 45

mvs5depth		83.82 157	84.54 144	81.68 225	82.23 323	68.65 199	86.89 121	89.90 183	80.02 94	87.74 154	97.86 2	64.19 269	82.02 337	76.37 163	95.63 143	94.35 92

test_fmvsmconf_n		85.88 110	85.51 124	86.99 98	84.77 284	78.21 91	85.40 154	91.39 136	65.32 282	87.72 155	91.81 172	82.33 101	89.78 238	86.68 37	94.20 191	92.99 155

FMVSNet2		81.31 206	81.61 197	80.41 246	86.38 250	58.75 314	83.93 182	86.58 238	72.43 196	87.65 156	92.98 131	63.78 272	90.22 222	66.86 261	93.92 199	92.27 189

GeoE		85.45 116	85.81 117	84.37 154	90.08 164	67.07 214	85.86 144	91.39 136	72.33 201	87.59 157	90.25 222	84.85 71	92.37 160	78.00 143	91.94 245	93.66 124

VPA-MVSNet		83.47 168	84.73 136	79.69 256	90.29 160	57.52 324	81.30 246	88.69 202	76.29 137	87.58 158	94.44 71	80.60 129	87.20 277	66.60 266	96.82 90	94.34 93

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	87.50 159	92.38 152	81.42 119	93.28 133	83.07 80	97.24 79	91.67 213

VDDNet		84.35 140	85.39 127	81.25 231	95.13 32	59.32 303	85.42 153	81.11 302	86.41 32	87.41 160	96.21 22	73.61 202	90.61 214	66.33 268	96.85 87	93.81 119

c3_l		81.64 202	81.59 198	81.79 224	80.86 341	59.15 307	78.61 286	90.18 177	68.36 243	87.20 161	87.11 281	69.39 242	91.62 179	78.16 140	94.43 185	94.60 79

VDD-MVS		84.23 146	84.58 142	83.20 191	91.17 142	65.16 234	83.25 201	84.97 268	79.79 95	87.18 162	94.27 79	74.77 190	90.89 203	69.24 240	96.54 98	93.55 135

MSLP-MVS++		85.00 128	86.03 111	81.90 218	91.84 119	71.56 170	86.75 128	93.02 87	75.95 144	87.12 163	89.39 238	77.98 148	89.40 249	77.46 150	94.78 174	84.75 327

baseline		85.20 121	85.93 113	83.02 195	86.30 255	62.37 267	84.55 167	93.96 44	74.48 163	87.12 163	92.03 163	82.30 103	91.94 171	78.39 133	94.21 190	94.74 77

YYNet1		70.06 331	70.44 324	68.90 360	73.76 398	53.42 356	58.99 408	67.20 389	58.42 336	87.10 165	85.39 308	59.82 296	67.32 397	59.79 322	83.50 367	85.96 312

MDA-MVSNet_test_wron		70.05 332	70.44 324	68.88 361	73.84 397	53.47 354	58.93 409	67.28 388	58.43 335	87.09 166	85.40 307	59.80 297	67.25 398	59.66 323	83.54 366	85.92 314

test_fmvs3		75.72 278	75.20 278	77.27 293	75.01 394	69.47 188	78.93 279	84.88 269	46.67 395	87.08 167	87.84 264	50.44 348	71.62 380	77.42 153	88.53 302	90.72 236

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	87.07 168	91.47 181	82.94 91	94.71 75	84.67 66	96.27 110	92.62 169

EPP-MVSNet		85.47 115	85.04 132	86.77 103	91.52 132	69.37 189	91.63 39	87.98 215	81.51 77	87.05 169	91.83 170	66.18 259	95.29 56	70.75 225	96.89 86	95.64 48

TinyColmap		81.25 207	82.34 186	77.99 283	85.33 274	60.68 291	82.32 229	88.33 208	71.26 213	86.97 170	92.22 162	77.10 163	86.98 281	62.37 302	95.17 156	86.31 310

eth_miper_zixun_eth		80.84 212	80.22 224	82.71 205	81.41 333	60.98 287	77.81 295	90.14 178	67.31 258	86.95 171	87.24 278	64.26 267	92.31 162	75.23 178	91.61 252	94.85 74

Anonymous20240521		80.18 229	81.25 206	76.95 296	83.15 318	60.84 289	82.46 225	85.99 248	68.76 239	86.78 172	93.73 112	59.13 301	77.44 363	73.71 197	97.55 69	92.56 171

Patchmatch-RL test		74.48 291	73.68 290	76.89 299	84.83 282	66.54 220	72.29 358	69.16 383	57.70 342	86.76 173	86.33 291	45.79 369	82.59 333	69.63 237	90.65 278	81.54 373

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	86.75 174	93.26 121	93.64 2	90.93 200	84.60 67	90.75 273	93.97 107

h-mvs33		84.25 144	82.76 177	88.72 73	91.82 121	82.60 60	84.00 179	84.98 267	71.27 211	86.70 175	90.55 215	63.04 279	93.92 105	78.26 138	94.20 191	89.63 261

hse-mvs2		83.47 168	81.81 192	88.47 77	91.03 145	82.27 61	82.61 218	83.69 280	71.27 211	86.70 175	86.05 297	63.04 279	92.41 158	78.26 138	93.62 210	90.71 237

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	86.69 177	92.28 159	80.36 131	95.06 67	86.17 47	96.49 100	90.22 250

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	86.63 178	94.84 55	79.58 138	95.96 15	87.62 19	94.50 182	94.56 80
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EI-MVSNet		82.61 180	82.42 185	83.20 191	83.25 314	63.66 246	83.50 194	85.07 262	76.06 139	86.55 179	85.10 312	73.41 207	90.25 219	78.15 142	90.67 275	95.68 47

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	86.55 179	92.95 134	74.84 187	95.22 59	80.78 108	95.83 134	94.46 84

plane_prior3						76.85 111			77.79 125	86.55 179

BH-untuned		80.96 211	80.99 210	80.84 239	88.55 201	68.23 202	80.33 259	88.46 204	72.79 193	86.55 179	86.76 285	74.72 191	91.77 178	61.79 309	88.99 296	82.52 363

MVSTER		77.09 260	75.70 273	81.25 231	75.27 391	61.08 283	77.49 303	85.07 262	60.78 321	86.55 179	88.68 250	43.14 389	90.25 219	73.69 198	90.67 275	92.42 178

旧先验2							81.73 239		56.88 351	86.54 184			84.90 315	72.81 211

IterMVS-SCA-FT		80.64 216	79.41 233	84.34 158	83.93 300	69.66 186	76.28 322	81.09 303	72.43 196	86.47 185	90.19 224	60.46 289	93.15 138	77.45 151	86.39 335	90.22 250

WB-MVS		76.06 274	80.01 230	64.19 384	89.96 170	20.58 426	72.18 359	68.19 385	83.21 59	86.46 186	93.49 117	70.19 239	78.97 357	65.96 270	90.46 280	93.02 153

test_fmvsm_n_1920		83.60 164	82.89 175	85.74 127	85.22 277	77.74 99	84.12 176	90.48 160	59.87 330	86.45 187	91.12 191	75.65 178	85.89 305	82.28 93	90.87 269	93.58 131

DIV-MVS_self_test		80.43 219	80.23 222	81.02 237	79.99 349	59.25 304	77.07 308	87.02 232	67.38 255	86.19 188	89.22 241	63.09 277	90.16 224	76.32 164	95.80 136	93.66 124

CDPH-MVS		86.17 106	85.54 123	88.05 86	92.25 101	75.45 124	83.85 184	92.01 116	65.91 269	86.19 188	91.75 175	83.77 82	94.98 69	77.43 152	96.71 93	93.73 122

cl____		80.42 220	80.23 222	81.02 237	79.99 349	59.25 304	77.07 308	87.02 232	67.37 256	86.18 190	89.21 242	63.08 278	90.16 224	76.31 165	95.80 136	93.65 126

MVS_111021_LR		84.28 143	83.76 159	85.83 126	89.23 182	83.07 55	80.99 250	83.56 282	72.71 194	86.07 191	89.07 245	81.75 116	86.19 297	77.11 156	93.36 211	88.24 283

GBi-Net		82.02 195	82.07 187	81.85 220	86.38 250	61.05 284	86.83 124	88.27 210	72.43 196	86.00 192	95.64 34	63.78 272	90.68 211	65.95 271	93.34 212	93.82 116

test1		82.02 195	82.07 187	81.85 220	86.38 250	61.05 284	86.83 124	88.27 210	72.43 196	86.00 192	95.64 34	63.78 272	90.68 211	65.95 271	93.34 212	93.82 116

FMVSNet3		78.80 242	78.55 245	79.57 258	82.89 321	56.89 330	81.76 238	85.77 250	69.04 236	86.00 192	90.44 217	51.75 341	90.09 230	65.95 271	93.34 212	91.72 210

miper_ehance_all_eth		80.34 223	80.04 229	81.24 233	79.82 352	58.95 309	77.66 297	89.66 188	65.75 274	85.99 195	85.11 311	68.29 249	91.42 186	76.03 169	92.03 241	93.33 138

tfpnnormal		81.79 201	82.95 174	78.31 275	88.93 189	55.40 340	80.83 254	82.85 288	76.81 134	85.90 196	94.14 89	74.58 193	86.51 290	66.82 264	95.68 142	93.01 154

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	85.80 197	89.56 236	80.76 126	92.13 166	73.21 209	95.51 144	93.25 144
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TSAR-MVS + GP.		83.95 154	82.69 179	87.72 89	89.27 181	81.45 67	83.72 189	81.58 300	74.73 160	85.66 198	86.06 296	72.56 220	92.69 152	75.44 176	95.21 154	89.01 277

EU-MVSNet		75.12 283	74.43 285	77.18 294	83.11 319	59.48 302	85.71 148	82.43 292	39.76 415	85.64 199	88.76 248	44.71 382	87.88 269	73.86 194	85.88 341	84.16 338

MonoMVSNet		76.66 266	77.26 258	74.86 318	79.86 351	54.34 348	86.26 137	86.08 244	71.08 216	85.59 200	88.68 250	53.95 331	85.93 301	63.86 292	80.02 386	84.32 333

LF4IMVS		82.75 179	81.93 190	85.19 135	82.08 324	80.15 74	85.53 150	88.76 201	68.01 248	85.58 201	87.75 266	71.80 229	86.85 284	74.02 191	93.87 201	88.58 280

Patchmtry		76.56 269	77.46 254	73.83 324	79.37 358	46.60 391	82.41 227	76.90 328	73.81 169	85.56 202	92.38 152	48.07 355	83.98 326	63.36 297	95.31 152	90.92 230

MVS_111021_HR		84.63 133	84.34 151	85.49 133	90.18 163	75.86 123	79.23 277	87.13 227	73.35 179	85.56 202	89.34 239	83.60 85	90.50 216	76.64 160	94.05 197	90.09 256

testdata				79.54 259	92.87 84	72.34 156		80.14 309	59.91 329	85.47 204	91.75 175	67.96 251	85.24 311	68.57 254	92.18 240	81.06 382

mvsmamba		80.30 225	78.87 238	84.58 150	88.12 211	67.55 210	92.35 29	84.88 269	63.15 292	85.33 205	90.91 200	50.71 345	95.20 62	66.36 267	87.98 313	90.99 227

test1111		78.53 246	78.85 240	77.56 289	92.22 103	47.49 387	82.61 218	69.24 382	72.43 196	85.28 206	94.20 85	51.91 339	90.07 231	65.36 279	96.45 103	95.11 65

thisisatest0530		79.07 237	77.33 257	84.26 161	87.13 234	64.58 237	83.66 191	75.95 334	68.86 238	85.22 207	87.36 275	38.10 397	93.57 123	75.47 175	94.28 189	94.62 78

BP-MVS1		82.81 177	81.67 194	86.23 113	87.88 216	68.53 200	86.06 140	84.36 275	75.65 149	85.14 208	90.19 224	45.84 368	94.42 86	85.18 59	94.72 178	95.75 44

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	85.12 209	89.67 235	84.47 75	95.46 50	82.56 89	96.26 111	93.77 121

CLD-MVS		83.18 172	82.64 180	84.79 143	89.05 184	67.82 209	77.93 293	92.52 102	68.33 244	85.07 210	81.54 354	82.06 108	92.96 144	69.35 239	97.91 51	93.57 132
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		82.58 182	81.93 190	84.50 151	87.68 221	73.35 137	86.14 139	77.70 320	61.64 309	85.02 211	91.62 177	77.75 151	86.24 294	82.79 86	87.07 324	93.91 111

FA-MVS(test-final)		83.13 174	83.02 173	83.43 184	86.16 262	66.08 225	88.00 103	88.36 207	75.55 151	85.02 211	92.75 142	65.12 264	92.50 156	74.94 182	91.30 258	91.72 210

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	84.96 213	90.69 209	80.01 135	95.14 64	78.37 134	95.78 138	91.82 206
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	84.96 213	93.17 123	74.06 197	91.19 191	78.28 137	91.09 260	89.29 269

QAPM		82.59 181	82.59 182	82.58 208	86.44 248	66.69 219	89.94 67	90.36 166	67.97 250	84.94 215	92.58 147	72.71 217	92.18 165	70.63 228	87.73 317	88.85 278

VPNet		80.25 226	81.68 193	75.94 310	92.46 95	47.98 385	76.70 313	81.67 298	73.45 176	84.87 216	92.82 138	74.66 192	86.51 290	61.66 311	96.85 87	93.33 138

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	84.85 217	90.89 201	80.85 125	95.29 56	81.14 103	95.32 150	92.34 184

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	84.76 218	87.70 267	78.87 142	94.18 95	80.67 110	96.29 107	92.73 162

pmmvs-eth3d		78.42 248	77.04 260	82.57 210	87.44 228	74.41 130	80.86 253	79.67 311	55.68 355	84.69 219	90.31 221	60.91 287	85.42 310	62.20 304	91.59 253	87.88 293

test_prior2							83.37 197		75.43 153	84.58 220	91.57 178	81.92 113		79.54 123	96.97 85

fmvsm_s_conf0.5_n_a		82.21 188	81.51 202	84.32 159	86.56 246	73.35 137	85.46 151	77.30 324	61.81 305	84.51 221	90.88 203	77.36 158	86.21 296	82.72 87	86.97 329	93.38 136

TEST9					92.34 98	79.70 78	83.94 180	90.32 168	65.41 280	84.49 222	90.97 196	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	65.79 271	84.49 222	90.97 196	81.93 111	93.63 115	81.21 102	96.54 98	90.88 232

fmvsm_s_conf0.1_n		82.17 190	81.59 198	83.94 169	86.87 244	71.57 169	85.19 157	77.42 323	62.27 303	84.47 224	91.33 184	76.43 174	85.91 303	83.14 77	87.14 322	94.33 94

Gipuma		84.44 138	86.33 105	78.78 266	84.20 296	73.57 135	89.55 77	90.44 162	84.24 48	84.38 225	94.89 53	76.35 177	80.40 349	76.14 168	96.80 91	82.36 365
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		64.31 370	65.85 359	59.67 395	66.54 419	62.24 272	57.76 411	70.96 373	40.13 413	84.36 226	82.09 347	46.93 357	51.67 419	61.99 307	81.89 377	65.12 410

test_8					92.09 107	78.87 85	83.82 185	90.31 170	65.79 271	84.36 226	90.96 198	81.93 111	93.44 128

cl22		78.97 238	78.21 250	81.24 233	77.74 366	59.01 308	77.46 304	87.13 227	65.79 271	84.32 228	85.10 312	58.96 303	90.88 204	75.36 177	92.03 241	93.84 114

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	84.32 228	89.33 240	83.87 79	94.53 84	82.45 90	94.89 169	94.90 68

agg_prior					91.58 127	77.69 100		90.30 171		84.32 228			93.18 136

Anonymous202405211		80.51 218	81.19 209	78.49 272	88.48 202	57.26 326	76.63 315	82.49 291	81.21 80	84.30 231	92.24 161	67.99 250	86.24 294	62.22 303	95.13 157	91.98 203

LFMVS		80.15 230	80.56 216	78.89 264	89.19 183	55.93 334	85.22 156	73.78 351	82.96 63	84.28 232	92.72 143	57.38 313	90.07 231	63.80 293	95.75 139	90.68 239

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	84.27 233	94.05 92	78.35 146	93.65 113	80.54 112	91.58 254	92.08 197
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ECVR-MVS		78.44 247	78.63 244	77.88 285	91.85 117	48.95 381	83.68 190	69.91 378	72.30 202	84.26 234	94.20 85	51.89 340	89.82 236	63.58 294	96.02 122	94.87 70

FE-MVS		79.98 233	78.86 239	83.36 186	86.47 247	66.45 222	89.73 70	84.74 273	72.80 192	84.22 235	91.38 183	44.95 380	93.60 119	63.93 291	91.50 255	90.04 257

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	84.07 236	78.72 378	80.39 130	95.13 65	73.82 195	92.98 223	91.04 226

fmvsm_s_conf0.5_n		81.91 199	81.30 205	83.75 173	86.02 264	71.56 170	84.73 163	77.11 327	62.44 300	84.00 237	90.68 210	76.42 175	85.89 305	83.14 77	87.11 323	93.81 119

MCST-MVS		84.36 139	83.93 157	85.63 129	91.59 124	71.58 168	83.52 193	92.13 113	61.82 304	83.96 238	89.75 234	79.93 137	93.46 127	78.33 136	94.34 187	91.87 205

新几何1				82.95 199	93.96 59	78.56 88		80.24 308	55.45 356	83.93 239	91.08 193	71.19 234	88.33 263	65.84 274	93.07 220	81.95 369

mmtdpeth		85.13 123	85.78 119	83.17 193	84.65 286	74.71 127	85.87 143	90.35 167	77.94 121	83.82 240	96.96 12	77.75 151	80.03 352	78.44 132	96.21 112	94.79 76

fmvsm_l_conf0.5_n		82.06 194	81.54 201	83.60 178	83.94 299	73.90 133	83.35 198	86.10 243	58.97 332	83.80 241	90.36 218	74.23 195	86.94 282	82.90 83	90.22 281	89.94 258

GDP-MVS		82.17 190	80.85 214	86.15 120	88.65 197	68.95 197	85.65 149	93.02 87	68.42 242	83.73 242	89.54 237	45.07 379	94.31 88	79.66 121	93.87 201	95.19 63

BH-RMVSNet		80.53 217	80.22 224	81.49 229	87.19 233	66.21 224	77.79 296	86.23 241	74.21 165	83.69 243	88.50 253	73.25 212	90.75 208	63.18 299	87.90 314	87.52 297

USDC		76.63 267	76.73 264	76.34 306	83.46 307	57.20 327	80.02 262	88.04 214	52.14 377	83.65 244	91.25 186	63.24 275	86.65 288	54.66 353	94.11 194	85.17 322

miper_enhance_ethall		77.83 251	76.93 261	80.51 244	76.15 383	58.01 320	75.47 334	88.82 199	58.05 340	83.59 245	80.69 358	64.41 266	91.20 190	73.16 210	92.03 241	92.33 185

MM		87.64 85	87.15 90	89.09 67	89.51 174	76.39 118	88.68 96	86.76 236	84.54 46	83.58 246	93.78 108	73.36 210	96.48 2	87.98 13	96.21 112	94.41 90

Effi-MVS+-dtu		85.82 111	83.38 164	93.14 4	87.13 234	91.15 3	87.70 108	88.42 205	74.57 162	83.56 247	85.65 301	78.49 145	94.21 93	72.04 216	92.88 225	94.05 105

CNLPA		83.55 166	83.10 172	84.90 139	89.34 179	83.87 50	84.54 169	88.77 200	79.09 106	83.54 248	88.66 252	74.87 186	81.73 339	66.84 263	92.29 235	89.11 271

SDMVSNet		81.90 200	83.17 170	78.10 280	88.81 192	62.45 265	76.08 326	86.05 246	73.67 171	83.41 249	93.04 127	82.35 100	80.65 346	70.06 234	95.03 162	91.21 222

sd_testset		79.95 234	81.39 204	75.64 313	88.81 192	58.07 318	76.16 325	82.81 289	73.67 171	83.41 249	93.04 127	80.96 124	77.65 362	58.62 327	95.03 162	91.21 222

OpenMVS_ROB	70.19 17	77.77 254	77.46 254	78.71 268	84.39 292	61.15 282	81.18 248	82.52 290	62.45 299	83.34 251	87.37 274	66.20 258	88.66 260	64.69 286	85.02 351	86.32 309

thres100view900		75.45 279	75.05 279	76.66 302	87.27 230	51.88 367	81.07 249	73.26 356	75.68 148	83.25 252	86.37 290	45.54 370	88.80 255	51.98 369	90.99 262	89.31 267

miper_lstm_enhance		76.45 271	76.10 269	77.51 290	76.72 377	60.97 288	64.69 395	85.04 264	63.98 289	83.20 253	88.22 256	56.67 317	78.79 359	73.22 204	93.12 219	92.78 161

IterMVS		76.91 262	76.34 267	78.64 269	80.91 339	64.03 243	76.30 321	79.03 314	64.88 285	83.11 254	89.16 243	59.90 295	84.46 319	68.61 252	85.15 349	87.42 298
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres600view7		75.97 275	75.35 277	77.85 287	87.01 240	51.84 368	80.45 257	73.26 356	75.20 156	83.10 255	86.31 293	45.54 370	89.05 251	55.03 351	92.24 237	92.66 167

mvs_anonymous		78.13 249	78.76 242	76.23 309	79.24 359	50.31 378	78.69 284	84.82 271	61.60 310	83.09 256	92.82 138	73.89 200	87.01 278	68.33 256	86.41 334	91.37 219

fmvsm_l_conf0.5_n_a		81.46 204	80.87 213	83.25 189	83.73 304	73.21 142	83.00 209	85.59 254	58.22 338	82.96 257	90.09 229	72.30 222	86.65 288	81.97 98	89.95 285	89.88 259

test_fmvs2		73.57 299	72.80 301	75.90 311	72.74 407	68.84 198	77.07 308	84.32 277	45.14 401	82.89 258	84.22 324	48.37 353	70.36 384	73.40 202	87.03 326	88.52 281

MVS_Test		82.47 184	83.22 167	80.22 249	82.62 322	57.75 323	82.54 223	91.96 119	71.16 215	82.89 258	92.52 149	77.41 157	90.50 216	80.04 115	87.84 316	92.40 181

reproduce_monomvs		74.09 295	73.23 296	76.65 303	76.52 378	54.54 346	77.50 302	81.40 301	65.85 270	82.86 260	86.67 286	27.38 420	84.53 318	70.24 232	90.66 277	90.89 231

test12				86.57 105	90.74 151	72.63 149		90.69 155		82.76 261		79.20 139	94.80 73		95.32 150	92.27 189

原ACMM1				84.60 149	92.81 89	74.01 132		91.50 131	62.59 295	82.73 262	90.67 212	76.53 173	94.25 91	69.24 240	95.69 141	85.55 318

test_yl		78.71 244	78.51 246	79.32 261	84.32 293	58.84 311	78.38 287	85.33 257	75.99 142	82.49 263	86.57 287	58.01 307	90.02 233	62.74 300	92.73 228	89.10 272

DCV-MVSNet		78.71 244	78.51 246	79.32 261	84.32 293	58.84 311	78.38 287	85.33 257	75.99 142	82.49 263	86.57 287	58.01 307	90.02 233	62.74 300	92.73 228	89.10 272

diffmvs		80.40 221	80.48 219	80.17 250	79.02 362	60.04 295	77.54 300	90.28 174	66.65 265	82.40 265	87.33 276	73.50 204	87.35 275	77.98 144	89.62 289	93.13 148
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	79.38 272	77.79 319	52.59 372	82.36 266	90.84 205	66.83 256			91.69 250	81.25 377

D2MVS		76.84 263	75.67 274	80.34 247	80.48 347	62.16 273	73.50 351	84.80 272	57.61 344	82.24 267	87.54 270	51.31 342	87.65 271	70.40 231	93.19 218	91.23 221

VNet		79.31 236	80.27 221	76.44 304	87.92 215	53.95 351	75.58 332	84.35 276	74.39 164	82.23 268	90.72 208	72.84 216	84.39 321	60.38 319	93.98 198	90.97 228

Vis-MVSNet (Re-imp)		77.82 252	77.79 253	77.92 284	88.82 191	51.29 372	83.28 199	71.97 366	74.04 166	82.23 268	89.78 233	57.38 313	89.41 248	57.22 335	95.41 146	93.05 152

API-MVS		82.28 186	82.61 181	81.30 230	86.29 256	69.79 183	88.71 95	87.67 217	78.42 117	82.15 270	84.15 326	77.98 148	91.59 180	65.39 278	92.75 227	82.51 364

DP-MVS Recon		84.05 151	83.22 167	86.52 107	91.73 122	75.27 125	83.23 203	92.40 104	72.04 205	82.04 271	88.33 255	77.91 150	93.95 104	66.17 269	95.12 159	90.34 249

MSDG		80.06 232	79.99 231	80.25 248	83.91 301	68.04 207	77.51 301	89.19 196	77.65 126	81.94 272	83.45 332	76.37 176	86.31 293	63.31 298	86.59 332	86.41 308

test2506		74.12 294	73.39 294	76.28 307	91.85 117	44.20 401	84.06 177	48.20 422	72.30 202	81.90 273	94.20 85	27.22 422	89.77 239	64.81 284	96.02 122	94.87 70

Fast-Effi-MVS+		81.04 210	80.57 215	82.46 212	87.50 227	63.22 253	78.37 289	89.63 190	68.01 248	81.87 274	82.08 348	82.31 102	92.65 153	67.10 260	88.30 310	91.51 218

testgi		72.36 309	74.61 281	65.59 378	80.56 346	42.82 406	68.29 381	73.35 355	66.87 263	81.84 275	89.93 230	72.08 226	66.92 400	46.05 396	92.54 230	87.01 303

tfpn200view9		74.86 287	74.23 286	76.74 301	86.24 257	52.12 364	79.24 275	73.87 349	73.34 180	81.82 276	84.60 321	46.02 363	88.80 255	51.98 369	90.99 262	89.31 267

thres400		75.14 281	74.23 286	77.86 286	86.24 257	52.12 364	79.24 275	73.87 349	73.34 180	81.82 276	84.60 321	46.02 363	88.80 255	51.98 369	90.99 262	92.66 167

CL-MVSNet_self_test		76.81 264	77.38 256	75.12 316	86.90 242	51.34 370	73.20 354	80.63 307	68.30 245	81.80 278	88.40 254	66.92 255	80.90 343	55.35 348	94.90 168	93.12 150

OpenMVS	76.72 13	81.98 197	82.00 189	81.93 217	84.42 291	68.22 203	88.50 99	89.48 193	66.92 262	81.80 278	91.86 167	72.59 219	90.16 224	71.19 221	91.25 259	87.40 299

MVS_0304		85.37 117	84.58 142	87.75 88	85.28 275	73.36 136	86.54 133	85.71 251	77.56 129	81.78 280	92.47 150	70.29 238	96.02 11	85.59 55	95.96 125	93.87 113

AdaColmap		83.66 161	83.69 160	83.57 181	90.05 167	72.26 158	86.29 136	90.00 181	78.19 119	81.65 281	87.16 279	83.40 87	94.24 92	61.69 310	94.76 177	84.21 337

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	81.64 282	87.25 277	82.43 98	94.53 84	77.65 147	96.46 102	94.14 102

DELS-MVS		81.44 205	81.25 206	82.03 216	84.27 295	62.87 257	76.47 320	92.49 103	70.97 217	81.64 282	83.83 327	75.03 184	92.70 151	74.29 184	92.22 239	90.51 245
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		83.10 175	82.54 183	84.77 144	92.90 83	69.10 196	86.65 129	90.62 158	54.66 362	81.46 284	90.81 206	76.98 165	94.38 87	72.62 212	96.18 114	90.82 234

TR-MVS		76.77 265	75.79 271	79.72 255	86.10 263	65.79 228	77.14 306	83.02 286	65.20 283	81.40 285	82.10 346	66.30 257	90.73 210	55.57 345	85.27 345	82.65 358

TAMVS		78.08 250	76.36 266	83.23 190	90.62 154	72.87 143	79.08 278	80.01 310	61.72 307	81.35 286	86.92 284	63.96 271	88.78 258	50.61 374	93.01 222	88.04 289

Effi-MVS+		83.90 156	84.01 155	83.57 181	87.22 232	65.61 230	86.55 132	92.40 104	78.64 114	81.34 287	84.18 325	83.65 84	92.93 146	74.22 185	87.87 315	92.17 194

testing3		71.53 318	70.79 319	73.77 325	88.89 190	41.86 408	76.60 318	59.12 412	72.83 191	80.97 288	82.08 348	19.80 428	87.33 276	65.12 281	91.68 251	92.13 196

new-patchmatchnet		70.10 330	73.37 295	60.29 394	81.23 336	16.95 429	59.54 405	74.62 342	62.93 293	80.97 288	87.93 262	62.83 281	71.90 378	55.24 349	95.01 165	92.00 201

PVSNet_Blended_VisFu		81.55 203	80.49 218	84.70 147	91.58 127	73.24 141	84.21 173	91.67 128	62.86 294	80.94 290	87.16 279	67.27 253	92.87 149	69.82 236	88.94 298	87.99 290

BH-w/o		76.57 268	76.07 270	78.10 280	86.88 243	65.92 227	77.63 298	86.33 239	65.69 275	80.89 291	79.95 367	68.97 247	90.74 209	53.01 364	85.25 346	77.62 393

PAPM_NR		83.23 171	83.19 169	83.33 187	90.90 148	65.98 226	88.19 101	90.78 153	78.13 120	80.87 292	87.92 263	73.49 206	92.42 157	70.07 233	88.40 304	91.60 215

ab-mvs		79.67 235	80.56 216	76.99 295	88.48 202	56.93 328	84.70 164	86.06 245	68.95 237	80.78 293	93.08 126	75.30 182	84.62 317	56.78 336	90.90 267	89.43 265

XXY-MVS		74.44 293	76.19 268	69.21 358	84.61 287	52.43 363	71.70 362	77.18 326	60.73 322	80.60 294	90.96 198	75.44 179	69.35 387	56.13 341	88.33 306	85.86 315

HQP4-MVS										80.56 295			94.61 79			93.56 133

HQP-NCC					91.19 139		84.77 160		73.30 182	80.55 296

ACMP_Plane					91.19 139		84.77 160		73.30 182	80.55 296

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	80.55 296	90.17 227	72.10 224	94.61 79	77.30 154	94.47 183	93.56 133

test_cas_vis1_n_1920		69.20 343	69.12 336	69.43 357	73.68 399	62.82 258	70.38 374	77.21 325	46.18 398	80.46 299	78.95 376	52.03 338	65.53 405	65.77 276	77.45 400	79.95 388

AUN-MVS		81.18 208	78.78 241	88.39 79	90.93 147	82.14 62	82.51 224	83.67 281	64.69 286	80.29 300	85.91 300	51.07 343	92.38 159	76.29 166	93.63 209	90.65 241

HyFIR lowres test		75.12 283	72.66 304	82.50 211	91.44 135	65.19 233	72.47 357	87.31 221	46.79 394	80.29 300	84.30 323	52.70 336	92.10 169	51.88 373	86.73 330	90.22 250

test20.03		73.75 298	74.59 283	71.22 345	81.11 337	51.12 374	70.15 375	72.10 365	70.42 221	80.28 302	91.50 180	64.21 268	74.72 374	46.96 393	94.58 181	87.82 295

mvsany_test3		65.48 364	62.97 373	73.03 331	69.99 413	76.17 121	64.83 393	43.71 424	43.68 406	80.25 303	87.05 283	52.83 335	63.09 411	51.92 372	72.44 406	79.84 389

F-COLMAP		84.97 129	83.42 163	89.63 57	92.39 96	83.40 52	88.83 92	91.92 120	73.19 186	80.18 304	89.15 244	77.04 164	93.28 133	65.82 275	92.28 236	92.21 192

GA-MVS		75.83 276	74.61 281	79.48 260	81.87 326	59.25 304	73.42 352	82.88 287	68.68 240	79.75 305	81.80 351	50.62 346	89.46 244	66.85 262	85.64 342	89.72 260

xiu_mvs_v1_base_debu		80.84 212	80.14 226	82.93 200	88.31 205	71.73 164	79.53 268	87.17 224	65.43 277	79.59 306	82.73 342	76.94 166	90.14 227	73.22 204	88.33 306	86.90 304

xiu_mvs_v1_base		80.84 212	80.14 226	82.93 200	88.31 205	71.73 164	79.53 268	87.17 224	65.43 277	79.59 306	82.73 342	76.94 166	90.14 227	73.22 204	88.33 306	86.90 304

xiu_mvs_v1_base_debi		80.84 212	80.14 226	82.93 200	88.31 205	71.73 164	79.53 268	87.17 224	65.43 277	79.59 306	82.73 342	76.94 166	90.14 227	73.22 204	88.33 306	86.90 304

test_fmvs1_n		70.94 323	70.41 326	72.53 337	73.92 396	66.93 217	75.99 327	84.21 279	43.31 408	79.40 309	79.39 372	43.47 385	68.55 392	69.05 245	84.91 354	82.10 367

patch_mono-2		78.89 239	79.39 234	77.41 292	84.78 283	68.11 205	75.60 330	83.11 285	60.96 319	79.36 310	89.89 232	75.18 183	72.97 375	73.32 203	92.30 233	91.15 224

UnsupCasMVSNet_eth		71.63 317	72.30 309	69.62 355	76.47 380	52.70 361	70.03 376	80.97 304	59.18 331	79.36 310	88.21 257	60.50 288	69.12 388	58.33 330	77.62 398	87.04 302

ppachtmachnet_test		74.73 290	74.00 288	76.90 298	80.71 344	56.89 330	71.53 365	78.42 316	58.24 337	79.32 312	82.92 339	57.91 310	84.26 323	65.60 277	91.36 257	89.56 262

MG-MVS		80.32 224	80.94 211	78.47 273	88.18 208	52.62 362	82.29 230	85.01 266	72.01 206	79.24 313	92.54 148	69.36 243	93.36 132	70.65 227	89.19 295	89.45 263

Fast-Effi-MVS+-dtu		82.54 183	81.41 203	85.90 123	85.60 269	76.53 115	83.07 206	89.62 191	73.02 189	79.11 314	83.51 330	80.74 127	90.24 221	68.76 249	89.29 292	90.94 229

CDS-MVSNet		77.32 258	75.40 275	83.06 194	89.00 186	72.48 154	77.90 294	82.17 294	60.81 320	78.94 315	83.49 331	59.30 299	88.76 259	54.64 354	92.37 232	87.93 292
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
baseline1		73.26 301	73.54 292	72.43 338	84.92 281	47.79 386	79.89 264	74.00 347	65.93 268	78.81 316	86.28 294	56.36 319	81.63 340	56.63 337	79.04 393	87.87 294

ttmdpeth		71.72 315	70.67 320	74.86 318	73.08 404	55.88 335	77.41 305	69.27 381	55.86 354	78.66 317	93.77 110	38.01 399	75.39 371	60.12 320	89.87 286	93.31 140

EIA-MVS		82.19 189	81.23 208	85.10 137	87.95 214	69.17 195	83.22 204	93.33 67	70.42 221	78.58 318	79.77 370	77.29 159	94.20 94	71.51 218	88.96 297	91.93 204

thres200		72.34 310	71.55 316	74.70 321	83.48 306	51.60 369	75.02 337	73.71 352	70.14 227	78.56 319	80.57 361	46.20 361	88.20 265	46.99 392	89.29 292	84.32 333

our_test_3		71.85 313	71.59 313	72.62 335	80.71 344	53.78 352	69.72 377	71.71 370	58.80 334	78.03 320	80.51 363	56.61 318	78.84 358	62.20 304	86.04 340	85.23 321

KD-MVS_2432*1600		66.87 354	65.81 360	70.04 350	67.50 416	47.49 387	62.56 399	79.16 312	61.21 317	77.98 321	80.61 359	25.29 424	82.48 334	53.02 362	84.92 352	80.16 386

miper_refine_blended		66.87 354	65.81 360	70.04 350	67.50 416	47.49 387	62.56 399	79.16 312	61.21 317	77.98 321	80.61 359	25.29 424	82.48 334	53.02 362	84.92 352	80.16 386

jason		77.42 257	75.75 272	82.43 213	87.10 237	69.27 190	77.99 292	81.94 296	51.47 381	77.84 323	85.07 315	60.32 291	89.00 252	70.74 226	89.27 294	89.03 275
jason: jason.
MAR-MVS		80.24 227	78.74 243	84.73 145	86.87 244	78.18 92	85.75 146	87.81 216	65.67 276	77.84 323	78.50 379	73.79 201	90.53 215	61.59 312	90.87 269	85.49 320
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		72.29 311	72.00 310	73.14 329	88.63 198	85.00 40	74.65 341	67.39 387	71.94 207	77.80 325	87.66 268	50.48 347	75.83 369	49.95 376	79.51 387	58.58 416

test_fmvs1		69.57 338	69.05 338	71.14 347	69.15 415	65.77 229	73.98 346	83.32 283	42.83 410	77.77 326	78.27 381	43.39 388	68.50 393	68.39 255	84.38 361	79.15 390

pmmvs4		74.92 286	72.98 300	80.73 241	84.95 280	71.71 167	76.23 323	77.59 321	52.83 371	77.73 327	86.38 289	56.35 320	84.97 314	57.72 334	87.05 325	85.51 319

ET-MVSNet_ETH3D		75.28 280	72.77 302	82.81 204	83.03 320	68.11 205	77.09 307	76.51 332	60.67 323	77.60 328	80.52 362	38.04 398	91.15 193	70.78 224	90.68 274	89.17 270

UnsupCasMVSNet_bld		69.21 342	69.68 333	67.82 368	79.42 356	51.15 373	67.82 385	75.79 335	54.15 364	77.47 329	85.36 310	59.26 300	70.64 383	48.46 386	79.35 389	81.66 371

WBMVS		68.76 345	68.43 345	69.75 354	83.29 312	40.30 411	67.36 387	72.21 364	57.09 349	77.05 330	85.53 303	33.68 407	80.51 347	48.79 384	90.90 267	88.45 282

Anonymous20231206		71.38 320	71.88 311	69.88 352	86.31 254	54.37 347	70.39 373	74.62 342	52.57 373	76.73 331	88.76 248	59.94 294	72.06 377	44.35 400	93.23 217	83.23 353

CMPMVS	59.41 20	75.12 283	73.57 291	79.77 253	75.84 386	67.22 211	81.21 247	82.18 293	50.78 386	76.50 332	87.66 268	55.20 327	82.99 332	62.17 306	90.64 279	89.09 274
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		72.10 312	71.69 312	73.32 327	81.57 331	53.02 358	76.77 312	78.37 317	63.31 290	76.37 333	91.85 168	36.68 402	78.98 356	47.87 389	92.45 231	87.95 291

CVMVSNet		72.62 307	71.41 317	76.28 307	83.25 314	60.34 293	83.50 194	79.02 315	37.77 419	76.33 334	85.10 312	49.60 351	87.41 274	70.54 229	77.54 399	81.08 380

PLC	73.85 16	82.09 193	80.31 220	87.45 92	90.86 150	80.29 73	85.88 142	90.65 156	68.17 247	76.32 335	86.33 291	73.12 213	92.61 154	61.40 313	90.02 284	89.44 264
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSFormer		82.23 187	81.57 200	84.19 164	85.54 271	69.26 191	91.98 34	90.08 179	71.54 208	76.23 336	85.07 315	58.69 304	94.27 89	86.26 43	88.77 299	89.03 275

lupinMVS		76.37 272	74.46 284	82.09 215	85.54 271	69.26 191	76.79 311	80.77 306	50.68 388	76.23 336	82.82 340	58.69 304	88.94 253	69.85 235	88.77 299	88.07 286

UWE-MVS		66.43 358	65.56 363	69.05 359	84.15 297	40.98 409	73.06 356	64.71 399	54.84 360	76.18 338	79.62 371	29.21 415	80.50 348	38.54 412	89.75 287	85.66 317

PatchMatch-RL		74.48 291	73.22 297	78.27 278	87.70 220	85.26 38	75.92 328	70.09 376	64.34 287	76.09 339	81.25 356	65.87 261	78.07 361	53.86 356	83.82 364	71.48 402

thisisatest0515		73.00 305	70.52 323	80.46 245	81.45 332	59.90 298	73.16 355	74.31 346	57.86 341	76.08 340	77.78 383	37.60 401	92.12 168	65.00 282	91.45 256	89.35 266

MS-PatchMatch		70.93 324	70.22 327	73.06 330	81.85 327	62.50 264	73.82 349	77.90 318	52.44 374	75.92 341	81.27 355	55.67 324	81.75 338	55.37 347	77.70 397	74.94 398

CHOSEN 1792x2688		72.45 308	70.56 322	78.13 279	90.02 169	63.08 254	68.72 380	83.16 284	42.99 409	75.92 341	85.46 305	57.22 315	85.18 313	49.87 378	81.67 378	86.14 311

CR-MVSNet		74.00 296	73.04 299	76.85 300	79.58 353	62.64 261	82.58 220	76.90 328	50.50 389	75.72 343	92.38 152	48.07 355	84.07 325	68.72 251	82.91 371	83.85 342

RPMNet		78.88 240	78.28 249	80.68 243	79.58 353	62.64 261	82.58 220	94.16 32	74.80 159	75.72 343	92.59 145	48.69 352	95.56 42	73.48 200	82.91 371	83.85 342

DPM-MVS		80.10 231	79.18 236	82.88 203	90.71 153	69.74 184	78.87 282	90.84 151	60.29 326	75.64 345	85.92 299	67.28 252	93.11 139	71.24 220	91.79 247	85.77 316

test_vis1_n		70.29 327	69.99 331	71.20 346	75.97 385	66.50 221	76.69 314	80.81 305	44.22 404	75.43 346	77.23 389	50.00 349	68.59 391	66.71 265	82.85 373	78.52 392

PVSNet_BlendedMVS		78.80 242	77.84 252	81.65 226	84.43 289	63.41 249	79.49 271	90.44 162	61.70 308	75.43 346	87.07 282	69.11 245	91.44 184	60.68 317	92.24 237	90.11 255

PVSNet_Blended		76.49 270	75.40 275	79.76 254	84.43 289	63.41 249	75.14 336	90.44 162	57.36 346	75.43 346	78.30 380	69.11 245	91.44 184	60.68 317	87.70 318	84.42 332

PAPR		78.84 241	78.10 251	81.07 235	85.17 278	60.22 294	82.21 234	90.57 159	62.51 296	75.32 349	84.61 320	74.99 185	92.30 163	59.48 324	88.04 312	90.68 239

N_pmnet		70.20 328	68.80 343	74.38 322	80.91 339	84.81 43	59.12 407	76.45 333	55.06 358	75.31 350	82.36 345	55.74 323	54.82 417	47.02 391	87.24 321	83.52 346

cascas		76.29 273	74.81 280	80.72 242	84.47 288	62.94 255	73.89 348	87.34 220	55.94 353	75.16 351	76.53 395	63.97 270	91.16 192	65.00 282	90.97 265	88.06 288

SCA		73.32 300	72.57 306	75.58 314	81.62 330	55.86 336	78.89 281	71.37 371	61.73 306	74.93 352	83.42 333	60.46 289	87.01 278	58.11 332	82.63 376	83.88 339

test_vis1_n_1920		71.30 321	71.58 315	70.47 348	77.58 369	59.99 297	74.25 342	84.22 278	51.06 383	74.85 353	79.10 374	55.10 328	68.83 390	68.86 248	79.20 392	82.58 360

xiu_mvs_v2_base		77.19 259	76.75 263	78.52 271	87.01 240	61.30 280	75.55 333	87.12 230	61.24 316	74.45 354	78.79 377	77.20 160	90.93 200	64.62 288	84.80 358	83.32 351

CANet		83.79 159	82.85 176	86.63 104	86.17 260	72.21 160	83.76 188	91.43 133	77.24 132	74.39 355	87.45 273	75.36 181	95.42 52	77.03 157	92.83 226	92.25 191

PS-MVSNAJ		77.04 261	76.53 265	78.56 270	87.09 238	61.40 278	75.26 335	87.13 227	61.25 315	74.38 356	77.22 390	76.94 166	90.94 199	64.63 287	84.83 357	83.35 350

MVP-Stereo		75.81 277	73.51 293	82.71 205	89.35 178	73.62 134	80.06 260	85.20 259	60.30 325	73.96 357	87.94 261	57.89 311	89.45 245	52.02 368	74.87 404	85.06 324
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WB-MVSnew		68.72 346	69.01 339	67.85 367	83.22 316	43.98 402	74.93 338	65.98 394	55.09 357	73.83 358	79.11 373	65.63 262	71.89 379	38.21 413	85.04 350	87.69 296

UGNet		82.78 178	81.64 195	86.21 116	86.20 259	76.24 120	86.86 122	85.68 252	77.07 133	73.76 359	92.82 138	69.64 241	91.82 177	69.04 246	93.69 207	90.56 243
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		74.82 288	73.74 289	78.04 282	89.57 172	60.04 295	76.49 319	87.09 231	54.31 363	73.66 360	79.80 368	60.25 292	86.76 287	58.37 328	84.15 362	87.32 300

Test_1112_low_res		73.90 297	73.08 298	76.35 305	90.35 159	55.95 333	73.40 353	86.17 242	50.70 387	73.14 361	85.94 298	58.31 306	85.90 304	56.51 338	83.22 368	87.20 301

1314		73.22 302	72.56 307	75.20 315	80.41 348	57.84 321	81.64 241	85.36 256	51.68 380	73.10 362	76.65 394	61.45 284	85.19 312	63.54 295	79.21 391	82.59 359

test_vis1_rt		65.64 363	64.09 367	70.31 349	66.09 420	70.20 180	61.16 402	81.60 299	38.65 416	72.87 363	69.66 409	52.84 334	60.04 413	56.16 340	77.77 396	80.68 384

Patchmatch-test		65.91 361	67.38 350	61.48 392	75.51 388	43.21 405	68.84 379	63.79 401	62.48 297	72.80 364	83.42 333	44.89 381	59.52 414	48.27 388	86.45 333	81.70 370

PatchmatchNet		69.71 337	68.83 342	72.33 340	77.66 368	53.60 353	79.29 273	69.99 377	57.66 343	72.53 365	82.93 338	46.45 360	80.08 351	60.91 316	72.09 407	83.31 352
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm		67.95 348	68.08 349	67.55 369	78.74 364	43.53 404	75.60 330	67.10 392	54.92 359	72.23 366	88.10 258	42.87 390	75.97 368	52.21 367	80.95 385	83.15 354

pmmvs5		70.73 325	70.07 328	72.72 333	77.03 374	52.73 360	74.14 343	75.65 338	50.36 390	72.17 367	85.37 309	55.42 326	80.67 345	52.86 365	87.59 319	84.77 326

PatchT		70.52 326	72.76 303	63.79 386	79.38 357	33.53 420	77.63 298	65.37 397	73.61 173	71.77 368	92.79 141	44.38 383	75.65 370	64.53 289	85.37 344	82.18 366

MVS		73.21 303	72.59 305	75.06 317	80.97 338	60.81 290	81.64 241	85.92 249	46.03 399	71.68 369	77.54 385	68.47 248	89.77 239	55.70 344	85.39 343	74.60 399

MIMVSNet		71.09 322	71.59 313	69.57 356	87.23 231	50.07 379	78.91 280	71.83 367	60.20 328	71.26 370	91.76 174	55.08 329	76.09 367	41.06 405	87.02 327	82.54 362

WTY-MVS		67.91 349	68.35 346	66.58 375	80.82 342	48.12 384	65.96 392	72.60 359	53.67 366	71.20 371	81.68 353	58.97 302	69.06 389	48.57 385	81.67 378	82.55 361

test0.0.03 1		64.66 367	64.36 366	65.57 379	75.03 393	46.89 390	64.69 395	61.58 409	62.43 301	71.18 372	77.54 385	43.41 386	68.47 394	40.75 407	82.65 374	81.35 374

CostFormer		69.98 334	68.68 344	73.87 323	77.14 372	50.72 376	79.26 274	74.51 344	51.94 379	70.97 373	84.75 318	45.16 378	87.49 273	55.16 350	79.23 390	83.40 349

Syy-MVS		69.40 340	70.03 330	67.49 370	81.72 328	38.94 413	71.00 367	61.99 403	61.38 312	70.81 374	72.36 406	61.37 285	79.30 354	64.50 290	85.18 347	84.22 335

myMVS_eth3d		64.66 367	63.89 368	66.97 373	81.72 328	37.39 416	71.00 367	61.99 403	61.38 312	70.81 374	72.36 406	20.96 427	79.30 354	49.59 379	85.18 347	84.22 335

testing91		69.94 335	68.99 340	72.80 332	83.81 303	45.89 394	71.57 364	73.64 354	68.24 246	70.77 376	77.82 382	34.37 405	84.44 320	53.64 358	87.00 328	88.07 286

testing99		69.27 341	68.15 348	72.63 334	83.29 312	45.45 396	71.15 366	71.08 372	67.34 257	70.43 377	77.77 384	32.24 410	84.35 322	53.72 357	86.33 336	88.10 285

tpmvs		70.16 329	69.56 334	71.96 341	74.71 395	48.13 383	79.63 266	75.45 340	65.02 284	70.26 378	81.88 350	45.34 375	85.68 308	58.34 329	75.39 403	82.08 368

sss		66.92 353	67.26 351	65.90 377	77.23 371	51.10 375	64.79 394	71.72 369	52.12 378	70.13 379	80.18 365	57.96 309	65.36 406	50.21 375	81.01 384	81.25 377

tpm2		68.45 347	66.83 354	73.30 328	78.93 363	48.50 382	79.76 265	71.76 368	47.50 393	69.92 380	83.60 329	42.07 391	88.40 262	48.44 387	79.51 387	83.01 356

testing222		66.93 352	65.30 364	71.81 342	83.38 309	45.83 395	72.06 360	67.50 386	64.12 288	69.68 381	76.37 396	27.34 421	83.00 331	38.88 409	88.38 305	86.62 307

HY-MVS	64.64 18	73.03 304	72.47 308	74.71 320	83.36 311	54.19 349	82.14 237	81.96 295	56.76 352	69.57 382	86.21 295	60.03 293	84.83 316	49.58 380	82.65 374	85.11 323

dmvs_re		66.81 356	66.98 352	66.28 376	76.87 375	58.68 315	71.66 363	72.24 362	60.29 326	69.52 383	73.53 403	52.38 337	64.40 408	44.90 398	81.44 381	75.76 396

ETVMVS		64.67 366	63.34 372	68.64 363	83.44 308	41.89 407	69.56 378	61.70 408	61.33 314	68.74 384	75.76 398	28.76 416	79.35 353	34.65 416	86.16 339	84.67 328

tpm cat1		66.76 357	65.21 365	71.42 344	77.09 373	50.62 377	78.01 291	73.68 353	44.89 402	68.64 385	79.00 375	45.51 372	82.42 336	49.91 377	70.15 410	81.23 379

IB-MVS	62.13 19	71.64 316	68.97 341	79.66 257	80.80 343	62.26 270	73.94 347	76.90 328	63.27 291	68.63 386	76.79 392	33.83 406	91.84 176	59.28 325	87.26 320	84.88 325
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		80.37 222	78.41 248	86.23 113	76.75 376	73.28 139	87.18 116	77.45 322	76.24 138	68.14 387	88.93 247	65.41 263	93.85 107	69.47 238	96.12 118	91.55 217
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet	58.17 21	66.41 359	65.63 362	68.75 362	81.96 325	49.88 380	62.19 401	72.51 361	51.03 384	68.04 388	75.34 400	50.84 344	74.77 372	45.82 397	82.96 369	81.60 372

tpmrst		66.28 360	66.69 356	65.05 382	72.82 406	39.33 412	78.20 290	70.69 375	53.16 370	67.88 389	80.36 364	48.18 354	74.75 373	58.13 331	70.79 409	81.08 380

CANet_DTU		77.81 253	77.05 259	80.09 251	81.37 334	59.90 298	83.26 200	88.29 209	69.16 234	67.83 390	83.72 328	60.93 286	89.47 243	69.22 242	89.70 288	90.88 232

EPMVS		62.47 371	62.63 375	62.01 388	70.63 412	38.74 414	74.76 339	52.86 419	53.91 365	67.71 391	80.01 366	39.40 395	66.60 401	55.54 346	68.81 415	80.68 384

UBG		64.34 369	63.35 371	67.30 371	83.50 305	40.53 410	67.46 386	65.02 398	54.77 361	67.54 392	74.47 402	32.99 409	78.50 360	40.82 406	83.58 365	82.88 357

MDTV_nov1_ep13			68.29 347		78.03 365	43.87 403	74.12 344	72.22 363	52.17 375	67.02 393	85.54 302	45.36 374	80.85 344	55.73 342	84.42 360

testing11		67.38 350	65.93 358	71.73 343	83.37 310	46.60 391	70.95 369	69.40 380	62.47 298	66.14 394	76.66 393	31.22 411	84.10 324	49.10 382	84.10 363	84.49 329

pmmvs3		62.47 371	60.02 384	69.80 353	71.58 410	64.00 244	70.52 372	58.44 415	39.77 414	66.05 395	75.84 397	27.10 423	72.28 376	46.15 395	84.77 359	73.11 400

ADS-MVSNet2		65.87 362	63.64 370	72.55 336	73.16 402	56.92 329	67.10 388	74.81 341	49.74 391	66.04 396	82.97 336	46.71 358	77.26 364	42.29 402	69.96 411	83.46 347

ADS-MVSNet		61.90 373	62.19 377	61.03 393	73.16 402	36.42 418	67.10 388	61.75 406	49.74 391	66.04 396	82.97 336	46.71 358	63.21 409	42.29 402	69.96 411	83.46 347

mvsany_test1		58.48 383	56.47 388	64.50 383	65.90 422	68.21 204	56.95 412	42.11 425	38.30 417	65.69 398	77.19 391	56.96 316	59.35 415	46.16 394	58.96 418	65.93 409

dmvs_testset		60.59 381	62.54 376	54.72 400	77.26 370	27.74 423	74.05 345	61.00 410	60.48 324	65.62 399	67.03 413	55.93 322	68.23 395	32.07 420	69.46 414	68.17 407

DSMNet-mixed		60.98 379	61.61 379	59.09 397	72.88 405	45.05 399	74.70 340	46.61 423	26.20 421	65.34 400	90.32 220	55.46 325	63.12 410	41.72 404	81.30 383	69.09 406

JIA-IIPM		69.41 339	66.64 357	77.70 288	73.19 401	71.24 172	75.67 329	65.56 396	70.42 221	65.18 401	92.97 133	33.64 408	83.06 330	53.52 360	69.61 413	78.79 391

test-LLR		67.21 351	66.74 355	68.63 364	76.45 381	55.21 342	67.89 382	67.14 390	62.43 301	65.08 402	72.39 404	43.41 386	69.37 385	61.00 314	84.89 355	81.31 375

test-mter		65.00 365	63.79 369	68.63 364	76.45 381	55.21 342	67.89 382	67.14 390	50.98 385	65.08 402	72.39 404	28.27 418	69.37 385	61.00 314	84.89 355	81.31 375

PMMVS2		55.64 386	59.27 385	44.74 402	64.30 424	12.32 430	40.60 417	49.79 421	53.19 369	65.06 404	84.81 317	53.60 333	49.76 420	32.68 419	89.41 291	72.15 401

baseline2		69.77 336	66.89 353	78.41 274	79.51 355	58.09 317	76.23 323	69.57 379	57.50 345	64.82 405	77.45 387	46.02 363	88.44 261	53.08 361	77.83 395	88.70 279

gg-mvs-nofinetune		68.96 344	69.11 337	68.52 366	76.12 384	45.32 397	83.59 192	55.88 417	86.68 29	64.62 406	97.01 9	30.36 413	83.97 327	44.78 399	82.94 370	76.26 395

PAPM		71.77 314	70.06 329	76.92 297	86.39 249	53.97 350	76.62 316	86.62 237	53.44 367	63.97 407	84.73 319	57.79 312	92.34 161	39.65 408	81.33 382	84.45 331

new_pmnet		55.69 385	57.66 386	49.76 401	75.47 389	30.59 421	59.56 404	51.45 420	43.62 407	62.49 408	75.48 399	40.96 393	49.15 421	37.39 414	72.52 405	69.55 405

MDTV_nov1_ep13_2view						27.60 424	70.76 371		46.47 397	61.27 409		45.20 376		49.18 381		83.75 344

dp		60.70 380	60.29 383	61.92 390	72.04 409	38.67 415	70.83 370	64.08 400	51.28 382	60.75 410	77.28 388	36.59 403	71.58 381	47.41 390	62.34 417	75.52 397

TESTMET0.1,1		61.29 376	60.32 382	64.19 384	72.06 408	51.30 371	67.89 382	62.09 402	45.27 400	60.65 411	69.01 410	27.93 419	64.74 407	56.31 339	81.65 380	76.53 394

PMMVS		61.65 374	60.38 381	65.47 380	65.40 423	69.26 191	63.97 397	61.73 407	36.80 420	60.11 412	68.43 411	59.42 298	66.35 402	48.97 383	78.57 394	60.81 413

PVSNet_0	51.08 22	56.10 384	54.97 389	59.48 396	75.12 392	53.28 357	55.16 413	61.89 405	44.30 403	59.16 413	62.48 416	54.22 330	65.91 404	35.40 415	47.01 419	59.25 415

MVS-HIRNet		61.16 377	62.92 374	55.87 398	79.09 360	35.34 419	71.83 361	57.98 416	46.56 396	59.05 414	91.14 190	49.95 350	76.43 366	38.74 410	71.92 408	55.84 417

E-PMN		61.59 375	61.62 378	61.49 391	66.81 418	55.40 340	53.77 414	60.34 411	66.80 264	58.90 415	65.50 414	40.48 394	66.12 403	55.72 343	86.25 337	62.95 412

GG-mvs-BLEND				67.16 372	73.36 400	46.54 393	84.15 175	55.04 418		58.64 416	61.95 417	29.93 414	83.87 328	38.71 411	76.92 401	71.07 403

EPNet_dtu		72.87 306	71.33 318	77.49 291	77.72 367	60.55 292	82.35 228	75.79 335	66.49 266	58.39 417	81.06 357	53.68 332	85.98 300	53.55 359	92.97 224	85.95 313
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		41.90 388	42.65 391	39.67 403	70.86 411	21.11 425	61.01 403	21.42 430	57.36 346	57.97 418	50.06 419	16.40 429	58.73 416	21.03 423	27.69 423	39.17 419

EMVS		61.10 378	60.81 380	61.99 389	65.96 421	55.86 336	53.10 415	58.97 414	67.06 261	56.89 419	63.33 415	40.98 392	67.03 399	54.79 352	86.18 338	63.08 411

CHOSEN 280x420		59.08 382	56.52 387	66.76 374	76.51 379	64.39 240	49.62 416	59.00 413	43.86 405	55.66 420	68.41 412	35.55 404	68.21 396	43.25 401	76.78 402	67.69 408

MVE	40.22 23	51.82 387	50.47 390	55.87 398	62.66 425	51.91 366	31.61 419	39.28 426	40.65 412	50.76 421	74.98 401	56.24 321	44.67 422	33.94 418	64.11 416	71.04 404
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
kuosan		30.83 389	32.17 392	26.83 405	53.36 427	19.02 428	57.90 410	20.44 431	38.29 418	38.01 422	37.82 421	15.18 430	33.45 424	7.74 425	20.76 424	28.03 420

DeepMVS_CX				24.13 406	32.95 428	29.49 422		21.63 429	12.07 422	37.95 423	45.07 420	30.84 412	19.21 425	17.94 424	33.06 422	23.69 421

tmp_tt		20.25 392	24.50 395	7.49 407	4.47 430	8.70 431	34.17 418	25.16 428	1.00 425	32.43 424	18.49 422	39.37 396	9.21 426	21.64 422	43.75 420	4.57 422

test_method		30.46 390	29.60 393	33.06 404	17.99 429	3.84 432	13.62 420	73.92 348	2.79 423	18.29 425	53.41 418	28.53 417	43.25 423	22.56 421	35.27 421	52.11 418

EGC-MVSNET		74.79 289	69.99 331	89.19 65	94.89 38	87.00 15	91.89 37	86.28 240	1.09 424	2.23 426	95.98 27	81.87 114	89.48 242	79.76 118	95.96 125	91.10 225

testmvs		5.91 396	7.65 399	0.72 409	1.20 431	0.37 434	59.14 406	0.67 433	0.49 427	1.11 427	2.76 426	0.94 432	0.24 428	1.02 427	1.47 425	1.55 424

test123		6.27 395	8.08 398	0.84 408	1.11 432	0.57 433	62.90 398	0.82 432	0.54 426	1.07 428	2.75 427	1.26 431	0.30 427	1.04 426	1.26 426	1.66 423

mmdepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

monomultidepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

test_blank		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet_test		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

DCPMVS		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

cdsmvs_eth3d_5k		20.81 391	27.75 394	0.00 410	0.00 433	0.00 435	0.00 421	85.44 255	0.00 428	0.00 429	82.82 340	81.46 118	0.00 429	0.00 428	0.00 427	0.00 425

pcd_1.5k_mvsjas		6.41 394	8.55 397	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	76.94 166	0.00 429	0.00 428	0.00 427	0.00 425

sosnet-low-res		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

sosnet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uncertanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

Regformer		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

ab-mvs-re		6.65 393	8.87 396	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	79.80 368	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

WAC-MVS						37.39 416								52.61 366

MSC_two_6792asdad				88.81 71	91.55 129	77.99 94		91.01 147					96.05 9	87.45 23	98.17 35	92.40 181

No_MVS				88.81 71	91.55 129	77.99 94		91.01 147					96.05 9	87.45 23	98.17 35	92.40 181

eth-test2					0.00 433

eth-test					0.00 433

OPU-MVS				88.27 82	91.89 115	77.83 97	90.47 55				91.22 187	81.12 122	94.68 76	74.48 183	95.35 148	92.29 187

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	92.02 200

GSMVS																83.88 339

sam_mvs1												46.11 362				83.88 339

sam_mvs												45.92 367

MTGPA								91.81 126

test_post1							78.85 283				3.13 424	45.19 377	80.13 350	58.11 332

test_post											3.10 425	45.43 373	77.22 365

patchmatchnet-post											81.71 352	45.93 366	87.01 278

MTMP							90.66 48	33.14 427

gm-plane-assit					75.42 390	44.97 400			52.17 375		72.36 406		87.90 268	54.10 355

test9_res														80.83 107	96.45 103	90.57 242

agg_prior2														79.68 120	96.16 115	90.22 250

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			92.80 160

新几何2							81.72 240

旧先验1					91.97 111	71.77 163		81.78 297			91.84 169	73.92 199			93.65 208	83.61 345

无先验							82.81 215	85.62 253	58.09 339				91.41 187	67.95 259		84.48 330

原ACMM2							82.26 233

testdata2													86.43 292	63.52 296

segment_acmp												81.94 110

testdata1							79.62 267		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	80.78 108	95.83 134	94.46 84

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								0.00 434

nn								0.00 434

door-mid								74.45 345

test11								91.46 132

door								72.57 360

HQP5-MVS						70.66 175

BP-MVS														77.30 154

HQP3-MVS								92.68 98							94.47 183

HQP2-MVS												72.10 224

NP-MVS					91.95 112	74.55 129					90.17 227

ACMMP++_ref															95.74 140

ACMMP++															97.35 75

Test By Simon												79.09 140

High-resolution multi-view benchmark