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.

IU-MVS					96.46 11	69.91 42		95.18 21	80.75 49	95.28 1				92.34 22	95.36 14	96.47 28

PC_three_1452									80.91 48	94.07 2	96.83 18	83.57 4	99.12 5	95.70 7	97.42 4	97.55 4

MSP-MVS		90.38 5	91.87 1	85.88 91	92.83 79	64.03 195	93.06 112	94.33 55	82.19 29	93.65 3	96.15 34	85.89 1	97.19 84	91.02 34	97.75 1	96.43 31
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
fmvsm_l_conf0.5_n		87.49 28	88.19 23	85.39 109	86.95 234	64.37 185	94.30 55	88.45 297	80.51 51	92.70 4	96.86 15	69.98 46	97.15 89	95.83 4	88.08 115	94.65 103

fmvsm_l_conf0.5_n_a		87.44 30	88.15 24	85.30 113	87.10 231	64.19 192	94.41 52	88.14 306	80.24 59	92.54 5	96.97 10	69.52 48	97.17 85	95.89 3	88.51 110	94.56 106

MVS_0304		90.32 6	90.90 7	88.55 23	94.05 45	70.23 36	97.00 5	93.73 74	87.30 4	92.15 6	96.15 34	66.38 67	98.94 17	96.71 2	94.67 33	96.47 28

SED-MVS		89.94 9	90.36 10	88.70 18	96.45 12	69.38 55	96.89 6	94.44 47	71.65 219	92.11 7	97.21 4	76.79 9	99.11 6	92.34 22	95.36 14	97.62 2

test_241102_ONE					96.45 12	69.38 55		94.44 47	71.65 219	92.11 7	97.05 7	76.79 9	99.11 6

DVP-MVS++		90.53 4	91.09 5	88.87 16	97.31 4	69.91 42	93.96 70	94.37 53	72.48 189	92.07 9	96.85 16	83.82 2	99.15 2	91.53 30	97.42 4	97.55 4

test_241102_TWO								94.41 49	71.65 219	92.07 9	97.21 4	74.58 18	99.11 6	92.34 22	95.36 14	96.59 19

test0726					96.40 15	69.99 38	96.76 8	94.33 55	71.92 205	91.89 11	97.11 6	73.77 23

SMA-MVS		88.14 18	88.29 22	87.67 33	93.21 67	68.72 72	93.85 77	94.03 63	74.18 152	91.74 12	96.67 21	65.61 76	98.42 33	89.24 44	96.08 7	95.88 47
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
DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 160	76.68 2	97.29 1	95.35 16	82.87 22	91.58 13	97.22 3	79.93 5	99.10 9	83.12 102	97.64 2	97.94 1

MM		90.87 2	91.52 2	88.92 15	92.12 100	71.10 27	97.02 3	96.04 6	88.70 2	91.57 14	96.19 32	70.12 45	98.91 18	96.83 1	95.06 17	96.76 15

patch_mono-2		89.71 11	90.99 6	85.85 94	96.04 24	63.70 205	95.04 40	95.19 20	86.74 7	91.53 15	95.15 66	73.86 22	97.58 59	93.38 14	92.00 69	96.28 37

TSAR-MVS + MP.		88.11 20	88.64 18	86.54 72	91.73 115	68.04 90	90.36 232	93.55 81	82.89 21	91.29 16	92.89 126	72.27 35	96.03 149	87.99 52	94.77 26	95.54 57
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_part2					96.29 19	68.16 88				90.78 17

DPE-MVS		88.77 17	89.21 16	87.45 43	96.26 20	67.56 103	94.17 58	94.15 60	68.77 268	90.74 18	97.27 2	76.09 12	98.49 29	90.58 38	94.91 21	96.30 34
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_one_0601					96.32 18	69.74 49		94.18 58	71.42 230	90.67 19	96.85 16	74.45 20

DVP-MVS		89.41 13	89.73 14	88.45 25	96.40 15	69.99 38	96.64 10	94.52 43	71.92 205	90.55 20	96.93 11	73.77 23	99.08 11	91.91 28	94.90 22	96.29 35
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									72.48 189	90.55 20	96.93 11	76.24 11	99.08 11	91.53 30	94.99 18	96.43 31

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 135	93.00 75	58.16 313	96.72 9	94.41 49	86.50 8	90.25 22	97.83 1	75.46 14	98.67 25	92.78 19	95.49 13	97.32 6

fmvsm_s_conf0.5_n_a		85.75 60	86.09 52	84.72 135	85.73 258	63.58 210	93.79 83	89.32 259	81.42 41	90.21 23	96.91 14	62.41 121	97.67 51	94.48 10	80.56 189	92.90 171

test_fmvsm_n_1920		87.69 26	88.50 19	85.27 115	87.05 233	63.55 212	93.69 87	91.08 196	84.18 13	90.17 24	97.04 8	67.58 58	97.99 39	95.72 5	90.03 95	94.26 119

fmvsm_s_conf0.5_n		86.39 47	86.91 38	84.82 128	87.36 226	63.54 213	94.74 47	90.02 235	82.52 25	90.14 25	96.92 13	62.93 116	97.84 46	95.28 8	82.26 170	93.07 165

fmvsm_s_conf0.1_n		85.61 64	85.93 55	84.68 138	82.95 301	63.48 215	94.03 68	89.46 253	81.69 34	89.86 26	96.74 20	61.85 127	97.75 49	94.74 9	82.01 176	92.81 173

fmvsm_s_conf0.1_n_a		84.76 78	84.84 75	84.53 144	80.23 328	63.50 214	92.79 124	88.73 288	80.46 52	89.84 27	96.65 22	60.96 135	97.57 61	93.80 13	80.14 191	92.53 180

CANet		89.61 12	89.99 12	88.46 24	94.39 39	69.71 50	96.53 13	93.78 67	86.89 6	89.68 28	95.78 40	65.94 72	99.10 9	92.99 17	93.91 42	96.58 21

xiu_mvs_v2_base		87.92 23	87.38 33	89.55 12	91.41 127	76.43 3	95.74 21	93.12 102	83.53 18	89.55 29	95.95 38	53.45 229	97.68 50	91.07 33	92.62 60	94.54 109

PS-MVSNAJ		88.14 18	87.61 29	89.71 7	92.06 101	76.72 1	95.75 20	93.26 94	83.86 15	89.55 29	96.06 36	53.55 225	97.89 43	91.10 32	93.31 53	94.54 109

CNVR-MVS		90.32 6	90.89 8	88.61 22	96.76 8	70.65 30	96.47 14	94.83 31	84.83 11	89.07 31	96.80 19	70.86 41	99.06 15	92.64 20	95.71 11	96.12 40

HPM-MVS++		89.37 14	89.95 13	87.64 34	95.10 30	68.23 86	95.24 33	94.49 45	82.43 26	88.90 32	96.35 27	71.89 38	98.63 26	88.76 48	96.40 6	96.06 41

APDe-MVS		87.54 27	87.84 26	86.65 66	96.07 23	66.30 138	94.84 45	93.78 67	69.35 259	88.39 33	96.34 28	67.74 57	97.66 54	90.62 37	93.44 51	96.01 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
EPNet		87.84 24	88.38 20	86.23 82	93.30 64	66.05 142	95.26 32	94.84 30	87.09 5	88.06 34	94.53 82	66.79 63	97.34 73	83.89 95	91.68 74	95.29 70
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SD-MVS		87.49 28	87.49 31	87.50 42	93.60 56	68.82 69	93.90 74	92.63 123	76.86 117	87.90 35	95.76 41	66.17 69	97.63 56	89.06 46	91.48 78	96.05 42
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
test_fmvsmconf_n		86.58 44	87.17 34	84.82 128	85.28 264	62.55 237	94.26 57	89.78 241	83.81 17	87.78 36	96.33 29	65.33 78	96.98 101	94.40 11	87.55 121	94.95 87

sasdasda		86.85 37	86.25 48	88.66 20	91.80 113	71.92 16	93.54 95	91.71 165	80.26 56	87.55 37	95.25 61	63.59 104	96.93 109	88.18 50	84.34 151	97.11 9

canonicalmvs		86.85 37	86.25 48	88.66 20	91.80 113	71.92 16	93.54 95	91.71 165	80.26 56	87.55 37	95.25 61	63.59 104	96.93 109	88.18 50	84.34 151	97.11 9

旧先验2							92.00 163		59.37 346	87.54 39			93.47 251	75.39 162

MVSFormer		83.75 101	82.88 109	86.37 78	89.24 175	71.18 24	89.07 264	90.69 205	65.80 291	87.13 40	94.34 92	64.99 81	92.67 275	72.83 180	91.80 72	95.27 73

lupinMVS		87.74 25	87.77 27	87.63 38	89.24 175	71.18 24	96.57 12	92.90 111	82.70 24	87.13 40	95.27 59	64.99 81	95.80 154	89.34 42	91.80 72	95.93 45

alignmvs		87.28 32	86.97 37	88.24 27	91.30 129	71.14 26	95.61 25	93.56 80	79.30 75	87.07 42	95.25 61	68.43 50	96.93 109	87.87 53	84.33 153	96.65 17

test_fmvsmconf0.1_n		85.71 61	86.08 53	84.62 142	80.83 318	62.33 242	93.84 80	88.81 285	83.50 19	87.00 43	96.01 37	63.36 108	96.93 109	94.04 12	87.29 124	94.61 105

MGCFI-Net		85.59 65	85.73 60	85.17 119	91.41 127	62.44 238	92.87 122	91.31 182	79.65 68	86.99 44	95.14 67	62.90 117	96.12 141	87.13 64	84.13 158	96.96 13

NCCC		89.07 16	89.46 15	87.91 28	96.60 10	69.05 63	96.38 15	94.64 40	84.42 12	86.74 45	96.20 31	66.56 66	98.76 24	89.03 47	94.56 34	95.92 46

FOURS1					93.95 46	61.77 253	93.96 70	91.92 152	62.14 326	86.57 46

SF-MVS		87.03 35	87.09 35	86.84 59	92.70 85	67.45 108	93.64 90	93.76 70	70.78 243	86.25 47	96.44 26	66.98 61	97.79 47	88.68 49	94.56 34	95.28 72

9.14			87.63 28		93.86 48		94.41 52	94.18 58	72.76 184	86.21 48	96.51 24	66.64 64	97.88 44	90.08 39	94.04 39

balanced_conf03		89.08 15	88.84 17	89.81 6	93.66 54	75.15 5	90.61 226	93.43 88	84.06 14	86.20 49	90.17 183	72.42 33	96.98 101	93.09 16	95.92 10	97.29 7

APD-MVS		85.93 56	85.99 54	85.76 98	95.98 26	65.21 163	93.59 93	92.58 125	66.54 286	86.17 50	95.88 39	63.83 97	97.00 97	86.39 71	92.94 57	95.06 82
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CANet_DTU		84.09 93	83.52 87	85.81 95	90.30 148	66.82 124	91.87 168	89.01 277	85.27 9	86.09 51	93.74 108	47.71 283	96.98 101	77.90 148	89.78 98	93.65 147

VNet		86.20 50	85.65 61	87.84 30	93.92 47	69.99 38	95.73 23	95.94 7	78.43 93	86.00 52	93.07 121	58.22 168	97.00 97	85.22 78	84.33 153	96.52 23

TSAR-MVS + GP.		87.96 21	88.37 21	86.70 65	93.51 61	65.32 160	95.15 36	93.84 66	78.17 96	85.93 53	94.80 76	75.80 13	98.21 34	89.38 41	88.78 107	96.59 19

MCST-MVS		91.08 1	91.46 3	89.94 4	97.66 2	73.37 10	97.13 2	95.58 11	89.33 1	85.77 54	96.26 30	72.84 29	99.38 1	92.64 20	95.93 9	97.08 11

DELS-MVS		90.05 8	90.09 11	89.94 4	93.14 70	73.88 9	97.01 4	94.40 51	88.32 3	85.71 55	94.91 73	74.11 21	98.91 18	87.26 62	95.94 8	97.03 12
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
PHI-MVS		86.83 39	86.85 41	86.78 63	93.47 62	65.55 156	95.39 30	95.10 23	71.77 215	85.69 56	96.52 23	62.07 124	98.77 23	86.06 74	95.60 12	96.03 43

TEST9					94.18 41	67.28 110	94.16 59	93.51 82	71.75 216	85.52 57	95.33 54	68.01 54	97.27 80

train_agg		87.21 33	87.42 32	86.60 68	94.18 41	67.28 110	94.16 59	93.51 82	71.87 210	85.52 57	95.33 54	68.19 52	97.27 80	89.09 45	94.90 22	95.25 76

SPE-MVS-test		86.14 52	87.01 36	83.52 177	92.63 87	59.36 302	95.49 27	91.92 152	80.09 60	85.46 59	95.53 49	61.82 128	95.77 157	86.77 69	93.37 52	95.41 60

test_8					94.19 40	67.19 112	94.15 61	93.42 89	71.87 210	85.38 60	95.35 53	68.19 52	96.95 106

testdata				81.34 233	89.02 179	57.72 317		89.84 240	58.65 349	85.32 61	94.09 101	57.03 179	93.28 253	69.34 215	90.56 91	93.03 166

ZD-MVS					96.63 9	65.50 158		93.50 84	70.74 244	85.26 62	95.19 65	64.92 84	97.29 76	87.51 57	93.01 56

test_prior2							95.10 38		75.40 137	85.25 63	95.61 45	67.94 55		87.47 59	94.77 26

test_fmvsmconf0.01_n		83.70 103	83.52 87	84.25 156	75.26 371	61.72 256	92.17 150	87.24 319	82.36 27	84.91 64	95.41 51	55.60 201	96.83 114	92.85 18	85.87 140	94.21 122

CS-MVS		85.80 59	86.65 44	83.27 185	92.00 106	58.92 306	95.31 31	91.86 157	79.97 61	84.82 65	95.40 52	62.26 122	95.51 175	86.11 73	92.08 68	95.37 63

ACMMP_NAP		86.05 53	85.80 58	86.80 62	91.58 119	67.53 105	91.79 172	93.49 85	74.93 143	84.61 66	95.30 56	59.42 152	97.92 41	86.13 72	94.92 20	94.94 88

jason		86.40 46	86.17 50	87.11 51	86.16 249	70.54 32	95.71 24	92.19 140	82.00 31	84.58 67	94.34 92	61.86 126	95.53 174	87.76 54	90.89 86	95.27 73
jason: jason.
agg_prior					94.16 43	66.97 121		93.31 92		84.49 68			96.75 116

test_vis1_n_1920		81.66 138	82.01 122	80.64 250	82.24 306	55.09 340	94.76 46	86.87 321	81.67 35	84.40 69	94.63 80	38.17 330	94.67 202	91.98 27	83.34 161	92.16 194

xiu_mvs_v1_base_debu		82.16 129	81.12 132	85.26 116	86.42 242	68.72 72	92.59 138	90.44 215	73.12 175	84.20 70	94.36 87	38.04 333	95.73 159	84.12 92	86.81 128	91.33 205

xiu_mvs_v1_base		82.16 129	81.12 132	85.26 116	86.42 242	68.72 72	92.59 138	90.44 215	73.12 175	84.20 70	94.36 87	38.04 333	95.73 159	84.12 92	86.81 128	91.33 205

xiu_mvs_v1_base_debi		82.16 129	81.12 132	85.26 116	86.42 242	68.72 72	92.59 138	90.44 215	73.12 175	84.20 70	94.36 87	38.04 333	95.73 159	84.12 92	86.81 128	91.33 205

ETV-MVS		86.01 54	86.11 51	85.70 101	90.21 150	67.02 120	93.43 103	91.92 152	81.21 45	84.13 73	94.07 103	60.93 136	95.63 165	89.28 43	89.81 96	94.46 115

SteuartSystems-ACMMP		86.82 41	86.90 39	86.58 70	90.42 145	66.38 135	96.09 17	93.87 65	77.73 104	84.01 74	95.66 43	63.39 107	97.94 40	87.40 60	93.55 50	95.42 59
Skip Steuart: Steuart Systems R&D Blog.
MG-MVS		87.11 34	86.27 46	89.62 8	97.79 1	76.27 4	94.96 43	94.49 45	78.74 90	83.87 75	92.94 124	64.34 91	96.94 107	75.19 163	94.09 38	95.66 52

GDP-MVS		85.54 66	85.32 65	86.18 83	87.64 218	67.95 94	92.91 121	92.36 130	77.81 102	83.69 76	94.31 94	72.84 29	96.41 130	80.39 126	85.95 139	94.19 123

DeepC-MVS_fast	79.48 2	87.95 22	88.00 25	87.79 31	95.86 27	68.32 80	95.74 21	94.11 61	83.82 16	83.49 77	96.19 32	64.53 90	98.44 31	83.42 101	94.88 25	96.61 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
reproduce-ours		83.51 105	83.33 99	84.06 159	92.18 98	60.49 282	90.74 218	92.04 145	64.35 301	83.24 78	95.59 47	59.05 157	97.27 80	83.61 97	89.17 103	94.41 116

our_new_method		83.51 105	83.33 99	84.06 159	92.18 98	60.49 282	90.74 218	92.04 145	64.35 301	83.24 78	95.59 47	59.05 157	97.27 80	83.61 97	89.17 103	94.41 116

EC-MVSNet		84.53 82	85.04 71	83.01 189	89.34 167	61.37 263	94.42 51	91.09 194	77.91 100	83.24 78	94.20 98	58.37 166	95.40 176	85.35 77	91.41 79	92.27 190

Effi-MVS+		83.82 98	82.76 111	86.99 56	89.56 163	69.40 53	91.35 193	86.12 331	72.59 186	83.22 81	92.81 130	59.60 150	96.01 151	81.76 112	87.80 118	95.56 56

CDPH-MVS		85.71 61	85.46 63	86.46 74	94.75 34	67.19 112	93.89 75	92.83 113	70.90 239	83.09 82	95.28 57	63.62 102	97.36 71	80.63 123	94.18 37	94.84 92

reproduce_model		83.15 112	82.96 105	83.73 170	92.02 102	59.74 294	90.37 231	92.08 143	63.70 308	82.86 83	95.48 50	58.62 163	97.17 85	83.06 103	88.42 111	94.26 119

BP-MVS1		86.54 45	86.68 43	86.13 85	87.80 215	67.18 114	92.97 117	95.62 10	79.92 62	82.84 84	94.14 100	74.95 15	96.46 128	82.91 104	88.96 106	94.74 97

MVS_Test		84.16 92	83.20 101	87.05 54	91.56 120	69.82 45	89.99 246	92.05 144	77.77 103	82.84 84	86.57 238	63.93 96	96.09 143	74.91 168	89.18 102	95.25 76

test_cas_vis1_n_1920		80.45 160	80.61 145	79.97 269	78.25 354	57.01 328	94.04 67	88.33 300	79.06 84	82.81 86	93.70 109	38.65 325	91.63 305	90.82 36	79.81 193	91.27 211

h-mvs33		83.01 115	82.56 115	84.35 152	89.34 167	62.02 248	92.72 127	93.76 70	81.45 38	82.73 87	92.25 143	60.11 143	97.13 90	87.69 55	62.96 321	93.91 139

hse-mvs2		81.12 148	81.11 135	81.16 237	86.52 241	57.48 321	89.40 257	91.16 189	81.45 38	82.73 87	90.49 175	60.11 143	94.58 203	87.69 55	60.41 348	91.41 204

test12				87.09 52	94.60 36	68.86 67		92.91 110		82.67 89		65.44 77	97.55 62		93.69 48	94.84 92

HY-MVS	76.49 5	84.28 86	83.36 98	87.02 55	92.22 95	67.74 98	84.65 310	94.50 44	79.15 79	82.23 90	87.93 216	66.88 62	96.94 107	80.53 124	82.20 173	96.39 33

LFMVS		84.34 85	82.73 112	89.18 13	94.76 33	73.25 11	94.99 42	91.89 155	71.90 207	82.16 91	93.49 115	47.98 279	97.05 92	82.55 108	84.82 147	97.25 8

WTY-MVS		86.32 48	85.81 57	87.85 29	92.82 81	69.37 57	95.20 34	95.25 18	82.71 23	81.91 92	94.73 77	67.93 56	97.63 56	79.55 132	82.25 171	96.54 22

VDD-MVS		83.06 114	81.81 125	86.81 61	90.86 139	67.70 99	95.40 29	91.50 176	75.46 135	81.78 93	92.34 140	40.09 320	97.13 90	86.85 68	82.04 175	95.60 54

diffmvs		84.28 86	83.83 83	85.61 103	87.40 224	68.02 91	90.88 212	89.24 262	80.54 50	81.64 94	92.52 132	59.83 147	94.52 211	87.32 61	85.11 145	94.29 118
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UBG		86.83 39	86.70 42	87.20 48	93.07 73	69.81 46	93.43 103	95.56 13	81.52 36	81.50 95	92.12 145	73.58 26	96.28 134	84.37 90	85.20 144	95.51 58

MSLP-MVS++		86.27 49	85.91 56	87.35 45	92.01 105	68.97 66	95.04 40	92.70 116	79.04 85	81.50 95	96.50 25	58.98 161	96.78 115	83.49 100	93.93 41	96.29 35

MVSMamba_PlusPlus		84.97 76	83.65 86	88.93 14	90.17 151	74.04 8	87.84 284	92.69 118	62.18 324	81.47 97	87.64 221	71.47 40	96.28 134	84.69 86	94.74 31	96.47 28

SR-MVS		82.81 118	82.58 114	83.50 180	93.35 63	61.16 266	92.23 149	91.28 186	64.48 300	81.27 98	95.28 57	53.71 224	95.86 153	82.87 105	88.77 108	93.49 151

dcpmvs_2		87.37 31	87.55 30	86.85 58	95.04 32	68.20 87	90.36 232	90.66 208	79.37 74	81.20 99	93.67 110	74.73 16	96.55 123	90.88 35	92.00 69	95.82 48

baseline		85.01 74	84.44 78	86.71 64	88.33 197	68.73 71	90.24 237	91.82 161	81.05 47	81.18 100	92.50 133	63.69 100	96.08 146	84.45 89	86.71 133	95.32 68

test_yl		84.28 86	83.16 102	87.64 34	94.52 37	69.24 59	95.78 18	95.09 24	69.19 262	81.09 101	92.88 127	57.00 181	97.44 66	81.11 121	81.76 178	96.23 38

DCV-MVSNet		84.28 86	83.16 102	87.64 34	94.52 37	69.24 59	95.78 18	95.09 24	69.19 262	81.09 101	92.88 127	57.00 181	97.44 66	81.11 121	81.76 178	96.23 38

UA-Net		80.02 169	79.65 159	81.11 239	89.33 169	57.72 317	86.33 303	89.00 280	77.44 111	81.01 103	89.15 197	59.33 154	95.90 152	61.01 288	84.28 155	89.73 231

PVSNet_BlendedMVS		83.38 108	83.43 93	83.22 186	93.76 50	67.53 105	94.06 63	93.61 78	79.13 80	81.00 104	85.14 253	63.19 111	97.29 76	87.08 65	73.91 242	84.83 312

PVSNet_Blended		86.73 42	86.86 40	86.31 81	93.76 50	67.53 105	96.33 16	93.61 78	82.34 28	81.00 104	93.08 120	63.19 111	97.29 76	87.08 65	91.38 80	94.13 128

casdiffmvs		85.37 68	84.87 74	86.84 59	88.25 200	69.07 62	93.04 114	91.76 162	81.27 44	80.84 106	92.07 147	64.23 92	96.06 147	84.98 83	87.43 123	95.39 61
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
testing11		86.71 43	86.44 45	87.55 40	93.54 59	71.35 21	93.65 89	95.58 11	81.36 43	80.69 107	92.21 144	72.30 34	96.46 128	85.18 80	83.43 160	94.82 95

MP-MVS-pluss		85.24 70	85.13 69	85.56 104	91.42 124	65.59 154	91.54 182	92.51 127	74.56 146	80.62 108	95.64 44	59.15 156	97.00 97	86.94 67	93.80 43	94.07 132
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
testing99		86.01 54	85.47 62	87.63 38	93.62 55	71.25 23	93.47 101	95.23 19	80.42 54	80.60 109	91.95 149	71.73 39	96.50 126	80.02 129	82.22 172	95.13 79

testing91		85.93 56	85.31 66	87.78 32	93.59 57	71.47 19	93.50 98	95.08 26	80.26 56	80.53 110	91.93 150	70.43 43	96.51 125	80.32 127	82.13 174	95.37 63

MTAPA		83.91 96	83.38 97	85.50 105	91.89 111	65.16 165	81.75 335	92.23 134	75.32 138	80.53 110	95.21 64	56.06 197	97.16 88	84.86 85	92.55 62	94.18 124

testing222		85.18 71	84.69 76	86.63 67	92.91 77	69.91 42	92.61 135	95.80 9	80.31 55	80.38 112	92.27 141	68.73 49	95.19 184	75.94 157	83.27 162	94.81 96

PAPM		85.89 58	85.46 63	87.18 49	88.20 203	72.42 15	92.41 144	92.77 114	82.11 30	80.34 113	93.07 121	68.27 51	95.02 187	78.39 145	93.59 49	94.09 130

CostFormer		82.33 126	81.15 131	85.86 93	89.01 180	68.46 77	82.39 332	93.01 106	75.59 133	80.25 114	81.57 296	72.03 37	94.96 190	79.06 138	77.48 217	94.16 126

casdiffmvs_mvg		85.66 63	85.18 68	87.09 52	88.22 202	69.35 58	93.74 86	91.89 155	81.47 37	80.10 115	91.45 159	64.80 86	96.35 132	87.23 63	87.69 119	95.58 55
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PMMVS		81.98 134	82.04 121	81.78 223	89.76 159	56.17 332	91.13 205	90.69 205	77.96 98	80.09 116	93.57 113	46.33 293	94.99 189	81.41 116	87.46 122	94.17 125

ZNCC-MVS		85.33 69	85.08 70	86.06 86	93.09 72	65.65 152	93.89 75	93.41 90	73.75 163	79.94 117	94.68 79	60.61 139	98.03 38	82.63 107	93.72 46	94.52 111

sss		82.71 121	82.38 118	83.73 170	89.25 172	59.58 297	92.24 148	94.89 29	77.96 98	79.86 118	92.38 138	56.70 187	97.05 92	77.26 151	80.86 186	94.55 107

新几何1				84.73 134	92.32 92	64.28 189		91.46 178	59.56 345	79.77 119	92.90 125	56.95 184	96.57 121	63.40 271	92.91 58	93.34 154

APD-MVS_3200maxsize		81.64 139	81.32 129	82.59 200	92.36 91	58.74 308	91.39 188	91.01 201	63.35 312	79.72 120	94.62 81	51.82 239	96.14 140	79.71 130	87.93 116	92.89 172

MP-MVS		85.02 73	84.97 72	85.17 119	92.60 88	64.27 190	93.24 107	92.27 133	73.13 174	79.63 121	94.43 85	61.90 125	97.17 85	85.00 82	92.56 61	94.06 133
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
原ACMM1				84.42 148	93.21 67	64.27 190		93.40 91	65.39 294	79.51 122	92.50 133	58.11 170	96.69 117	65.27 261	93.96 40	92.32 185

ETVMVS		84.22 90	83.71 84	85.76 98	92.58 89	68.25 85	92.45 143	95.53 15	79.54 70	79.46 123	91.64 157	70.29 44	94.18 223	69.16 218	82.76 168	94.84 92

test_fmvs1		74.07 262	73.69 250	75.22 322	78.91 346	47.34 379	89.06 266	74.69 382	63.68 309	79.41 124	91.59 158	24.36 384	87.77 348	85.22 78	76.26 227	90.55 220

VDDNet		80.50 158	78.26 181	87.21 47	86.19 247	69.79 47	94.48 50	91.31 182	60.42 338	79.34 125	90.91 168	38.48 328	96.56 122	82.16 109	81.05 184	95.27 73

EIA-MVS		84.84 77	84.88 73	84.69 137	91.30 129	62.36 241	93.85 77	92.04 145	79.45 71	79.33 126	94.28 96	62.42 120	96.35 132	80.05 128	91.25 83	95.38 62

HFP-MVS		84.73 79	84.40 79	85.72 100	93.75 52	65.01 169	93.50 98	93.19 98	72.19 199	79.22 127	94.93 71	59.04 159	97.67 51	81.55 113	92.21 64	94.49 114

MAR-MVS		84.18 91	83.43 93	86.44 75	96.25 21	65.93 147	94.28 56	94.27 57	74.41 147	79.16 128	95.61 45	53.99 220	98.88 22	69.62 212	93.26 54	94.50 113
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
PAPR		85.15 72	84.47 77	87.18 49	96.02 25	68.29 81	91.85 170	93.00 108	76.59 124	79.03 129	95.00 68	61.59 129	97.61 58	78.16 146	89.00 105	95.63 53

SR-MVS-dyc-post		81.06 149	80.70 142	82.15 214	92.02 102	58.56 310	90.90 210	90.45 212	62.76 319	78.89 130	94.46 83	51.26 249	95.61 167	78.77 142	86.77 131	92.28 187

RE-MVS-def			80.48 148		92.02 102	58.56 310	90.90 210	90.45 212	62.76 319	78.89 130	94.46 83	49.30 266		78.77 142	86.77 131	92.28 187

GST-MVS		84.63 81	84.29 80	85.66 102	92.82 81	65.27 161	93.04 114	93.13 101	73.20 172	78.89 130	94.18 99	59.41 153	97.85 45	81.45 115	92.48 63	93.86 142

MVS_111021_HR		86.19 51	85.80 58	87.37 44	93.17 69	69.79 47	93.99 69	93.76 70	79.08 82	78.88 133	93.99 104	62.25 123	98.15 36	85.93 75	91.15 84	94.15 127

region2R		84.36 84	84.03 82	85.36 111	93.54 59	64.31 188	93.43 103	92.95 109	72.16 202	78.86 134	94.84 75	56.97 183	97.53 63	81.38 117	92.11 67	94.24 121

ACMMPR		84.37 83	84.06 81	85.28 114	93.56 58	64.37 185	93.50 98	93.15 100	72.19 199	78.85 135	94.86 74	56.69 188	97.45 65	81.55 113	92.20 65	94.02 135

UGNet		79.87 172	78.68 175	83.45 182	89.96 154	61.51 259	92.13 152	90.79 203	76.83 119	78.85 135	86.33 242	38.16 331	96.17 139	67.93 230	87.17 125	92.67 175
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
GG-mvs-BLEND				86.53 73	91.91 110	69.67 52	75.02 376	94.75 34		78.67 137	90.85 169	77.91 7	94.56 208	72.25 189	93.74 45	95.36 65

test2506		83.29 109	82.92 108	84.37 151	88.39 195	63.18 223	92.01 160	91.35 181	77.66 106	78.49 138	91.42 160	64.58 89	95.09 186	73.19 176	89.23 100	94.85 89

XVS		83.87 97	83.47 91	85.05 121	93.22 65	63.78 199	92.92 119	92.66 120	73.99 155	78.18 139	94.31 94	55.25 203	97.41 68	79.16 136	91.58 76	93.95 137

X-MVStestdata		76.86 225	74.13 244	85.05 121	93.22 65	63.78 199	92.92 119	92.66 120	73.99 155	78.18 139	10.19 422	55.25 203	97.41 68	79.16 136	91.58 76	93.95 137

test_fmvs1_n		72.69 281	71.92 272	74.99 325	71.15 384	47.08 381	87.34 293	75.67 377	63.48 311	78.08 141	91.17 165	20.16 396	87.87 345	84.65 87	75.57 231	90.01 226

EI-MVSNet-Vis-set		83.77 100	83.67 85	84.06 159	92.79 84	63.56 211	91.76 175	94.81 32	79.65 68	77.87 142	94.09 101	63.35 109	97.90 42	79.35 134	79.36 198	90.74 216

Vis-MVSNet		80.92 152	79.98 155	83.74 168	88.48 190	61.80 252	93.44 102	88.26 305	73.96 158	77.73 143	91.76 153	49.94 259	94.76 195	65.84 253	90.37 93	94.65 103
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_fmvsmvis_n_1920		83.80 99	83.48 90	84.77 132	82.51 304	63.72 203	91.37 191	83.99 353	81.42 41	77.68 144	95.74 42	58.37 166	97.58 59	93.38 14	86.87 127	93.00 168

CSCG		86.87 36	86.26 47	88.72 17	95.05 31	70.79 29	93.83 82	95.33 17	68.48 272	77.63 145	94.35 91	73.04 27	98.45 30	84.92 84	93.71 47	96.92 14

TESTMET0.1,1		82.41 125	81.98 123	83.72 172	88.08 204	63.74 201	92.70 129	93.77 69	79.30 75	77.61 146	87.57 223	58.19 169	94.08 227	73.91 174	86.68 134	93.33 156

tpm2		79.80 173	77.95 187	85.34 112	88.28 198	68.26 83	81.56 338	91.42 179	70.11 250	77.59 147	80.50 314	67.40 59	94.26 221	67.34 235	77.35 218	93.51 150

CP-MVS		83.71 102	83.40 96	84.65 139	93.14 70	63.84 197	94.59 49	92.28 132	71.03 237	77.41 148	94.92 72	55.21 206	96.19 138	81.32 118	90.70 88	93.91 139

ab-mvs		80.18 165	78.31 180	85.80 96	88.44 192	65.49 159	83.00 329	92.67 119	71.82 213	77.36 149	85.01 254	54.50 212	96.59 119	76.35 156	75.63 230	95.32 68

test222					89.77 158	61.60 258	89.55 252	89.42 256	56.83 360	77.28 150	92.43 137	52.76 233			91.14 85	93.09 163

PGM-MVS		83.25 110	82.70 113	84.92 124	92.81 83	64.07 194	90.44 227	92.20 138	71.28 231	77.23 151	94.43 85	55.17 207	97.31 75	79.33 135	91.38 80	93.37 153

gg-mvs-nofinetune		77.18 219	74.31 240	85.80 96	91.42 124	68.36 79	71.78 381	94.72 35	49.61 381	77.12 152	45.92 407	77.41 8	93.98 236	67.62 233	93.16 55	95.05 83

HPM-MVS		83.25 110	82.95 107	84.17 157	92.25 94	62.88 232	90.91 209	91.86 157	70.30 248	77.12 152	93.96 105	56.75 186	96.28 134	82.04 110	91.34 82	93.34 154
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
PVSNet_Blended_VisFu		83.97 95	83.50 89	85.39 109	90.02 153	66.59 132	93.77 84	91.73 163	77.43 112	77.08 154	89.81 190	63.77 99	96.97 104	79.67 131	88.21 113	92.60 177

DeepC-MVS	77.85 3	85.52 67	85.24 67	86.37 78	88.80 185	66.64 129	92.15 151	93.68 76	81.07 46	76.91 155	93.64 111	62.59 119	98.44 31	85.50 76	92.84 59	94.03 134
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ECVR-MVS		81.29 144	80.38 150	84.01 164	88.39 195	61.96 250	92.56 141	86.79 323	77.66 106	76.63 156	91.42 160	46.34 292	95.24 183	74.36 172	89.23 100	94.85 89

EI-MVSNet-UG-set		83.14 113	82.96 105	83.67 175	92.28 93	63.19 222	91.38 190	94.68 38	79.22 77	76.60 157	93.75 107	62.64 118	97.76 48	78.07 147	78.01 209	90.05 225

EPNet_dtu		78.80 192	79.26 169	77.43 304	88.06 205	49.71 366	91.96 165	91.95 151	77.67 105	76.56 158	91.28 164	58.51 164	90.20 326	56.37 308	80.95 185	92.39 182
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DP-MVS Recon		82.73 119	81.65 126	85.98 88	97.31 4	67.06 117	95.15 36	91.99 149	69.08 265	76.50 159	93.89 106	54.48 215	98.20 35	70.76 203	85.66 142	92.69 174

Anonymous202405211		77.96 208	75.33 226	85.87 92	93.73 53	64.52 175	94.85 44	85.36 338	62.52 322	76.11 160	90.18 182	29.43 374	97.29 76	68.51 225	77.24 221	95.81 49

tpmrst		80.57 156	79.14 171	84.84 127	90.10 152	68.28 82	81.70 336	89.72 248	77.63 108	75.96 161	79.54 328	64.94 83	92.71 272	75.43 161	77.28 220	93.55 149

thisisatest0515		83.41 107	82.49 116	86.16 84	89.46 166	68.26 83	93.54 95	94.70 37	74.31 150	75.75 162	90.92 167	72.62 31	96.52 124	69.64 210	81.50 181	93.71 145

test1111		80.84 153	80.02 152	83.33 183	87.87 211	60.76 274	92.62 134	86.86 322	77.86 101	75.73 163	91.39 162	46.35 291	94.70 201	72.79 182	88.68 109	94.52 111

CHOSEN 1792x2688		84.98 75	83.45 92	89.57 11	89.94 155	75.14 6	92.07 157	92.32 131	81.87 32	75.68 164	88.27 207	60.18 142	98.60 27	80.46 125	90.27 94	94.96 86

test-LLR		80.10 167	79.56 161	81.72 225	86.93 237	61.17 264	92.70 129	91.54 173	71.51 228	75.62 165	86.94 234	53.83 221	92.38 285	72.21 190	84.76 149	91.60 199

test-mter		79.96 170	79.38 167	81.72 225	86.93 237	61.17 264	92.70 129	91.54 173	73.85 160	75.62 165	86.94 234	49.84 261	92.38 285	72.21 190	84.76 149	91.60 199

mPP-MVS		82.96 117	82.44 117	84.52 145	92.83 79	62.92 230	92.76 125	91.85 159	71.52 227	75.61 167	94.24 97	53.48 228	96.99 100	78.97 139	90.73 87	93.64 148

MVS_111021_LR		82.02 133	81.52 127	83.51 179	88.42 193	62.88 232	89.77 249	88.93 281	76.78 120	75.55 168	93.10 118	50.31 255	95.38 178	83.82 96	87.02 126	92.26 191

API-MVS		82.28 127	80.53 147	87.54 41	96.13 22	70.59 31	93.63 91	91.04 200	65.72 293	75.45 169	92.83 129	56.11 196	98.89 21	64.10 267	89.75 99	93.15 161

Fast-Effi-MVS+		81.14 146	80.01 153	84.51 146	90.24 149	65.86 148	94.12 62	89.15 268	73.81 162	75.37 170	88.26 208	57.26 176	94.53 210	66.97 241	84.92 146	93.15 161

test_vis1_n		71.63 287	70.73 283	74.31 332	69.63 390	47.29 380	86.91 297	72.11 388	63.21 315	75.18 171	90.17 183	20.40 394	85.76 360	84.59 88	74.42 237	89.87 227

nrg030		80.93 151	79.86 156	84.13 158	83.69 290	68.83 68	93.23 108	91.20 187	75.55 134	75.06 172	88.22 211	63.04 115	94.74 197	81.88 111	66.88 290	88.82 241

UWE-MVS		80.81 154	81.01 137	80.20 260	89.33 169	57.05 326	91.91 166	94.71 36	75.67 132	75.01 173	89.37 194	63.13 113	91.44 313	67.19 238	82.80 167	92.12 195

baseline1		81.84 135	81.03 136	84.28 155	91.60 118	66.62 130	91.08 206	91.66 170	81.87 32	74.86 174	91.67 156	69.98 46	94.92 193	71.76 195	64.75 308	91.29 210

FA-MVS(test-final)		79.12 184	77.23 200	84.81 131	90.54 143	63.98 196	81.35 341	91.71 165	71.09 236	74.85 175	82.94 276	52.85 232	97.05 92	67.97 228	81.73 180	93.41 152

HPM-MVS_fast		80.25 164	79.55 163	82.33 206	91.55 121	59.95 291	91.32 195	89.16 267	65.23 297	74.71 176	93.07 121	47.81 282	95.74 158	74.87 170	88.23 112	91.31 209

TR-MVS		78.77 194	77.37 199	82.95 190	90.49 144	60.88 270	93.67 88	90.07 231	70.08 251	74.51 177	91.37 163	45.69 297	95.70 164	60.12 294	80.32 190	92.29 186

AUN-MVS		78.37 201	77.43 194	81.17 236	86.60 240	57.45 322	89.46 256	91.16 189	74.11 153	74.40 178	90.49 175	55.52 202	94.57 205	74.73 171	60.43 347	91.48 202

HQP-NCC					87.54 220		94.06 63		79.80 64	74.18 179

ACMP_Plane					87.54 220		94.06 63		79.80 64	74.18 179

HQP4-MVS										74.18 179			95.61 167			88.63 243

HQP-MVS		81.14 146	80.64 144	82.64 198	87.54 220	63.66 208	94.06 63	91.70 168	79.80 64	74.18 179	90.30 179	51.63 244	95.61 167	77.63 149	78.90 202	88.63 243

PAPM_NR		82.97 116	81.84 124	86.37 78	94.10 44	66.76 127	87.66 288	92.84 112	69.96 252	74.07 183	93.57 113	63.10 114	97.50 64	70.66 205	90.58 90	94.85 89

VPA-MVSNet		79.03 185	78.00 185	82.11 219	85.95 252	64.48 178	93.22 109	94.66 39	75.05 142	74.04 184	84.95 255	52.17 238	93.52 249	74.90 169	67.04 289	88.32 251

CDS-MVSNet		81.43 142	80.74 140	83.52 177	86.26 246	64.45 179	92.09 155	90.65 209	75.83 131	73.95 185	89.81 190	63.97 95	92.91 265	71.27 198	82.82 165	93.20 160
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tpm		78.58 198	77.03 202	83.22 186	85.94 254	64.56 174	83.21 325	91.14 192	78.31 94	73.67 186	79.68 326	64.01 94	92.09 295	66.07 251	71.26 262	93.03 166

WB-MVSnew		77.14 220	76.18 215	80.01 266	86.18 248	63.24 219	91.26 197	94.11 61	71.72 217	73.52 187	87.29 228	45.14 302	93.00 258	56.98 306	79.42 196	83.80 320

BH-RMVSNet		79.46 180	77.65 190	84.89 125	91.68 117	65.66 151	93.55 94	88.09 308	72.93 179	73.37 188	91.12 166	46.20 295	96.12 141	56.28 309	85.61 143	92.91 170

thres200		79.66 174	78.33 179	83.66 176	92.54 90	65.82 150	93.06 112	96.31 3	74.90 144	73.30 189	88.66 200	59.67 149	95.61 167	47.84 343	78.67 205	89.56 234

Anonymous20240529		76.84 227	74.15 243	84.88 126	91.02 134	64.95 171	93.84 80	91.09 194	53.57 369	73.00 190	87.42 225	35.91 349	97.32 74	69.14 219	72.41 254	92.36 183

CPTT-MVS		79.59 175	79.16 170	80.89 248	91.54 122	59.80 293	92.10 154	88.54 296	60.42 338	72.96 191	93.28 117	48.27 275	92.80 269	78.89 141	86.50 136	90.06 224

HyFIR lowres test		81.03 150	79.56 161	85.43 107	87.81 214	68.11 89	90.18 238	90.01 236	70.65 245	72.95 192	86.06 245	63.61 103	94.50 212	75.01 166	79.75 195	93.67 146

EPP-MVSNet		81.79 136	81.52 127	82.61 199	88.77 186	60.21 288	93.02 116	93.66 77	68.52 271	72.90 193	90.39 177	72.19 36	94.96 190	74.93 167	79.29 200	92.67 175

MDTV_nov1_ep13_2view						59.90 292	80.13 352		67.65 277	72.79 194		54.33 218		59.83 295		92.58 178

RRT-MVS		82.61 123	81.16 130	86.96 57	91.10 133	68.75 70	87.70 287	92.20 138	76.97 115	72.68 195	87.10 232	51.30 248	96.41 130	83.56 99	87.84 117	95.74 50

FE-MVS		75.97 241	73.02 257	84.82 128	89.78 157	65.56 155	77.44 366	91.07 197	64.55 299	72.66 196	79.85 324	46.05 296	96.69 117	54.97 313	80.82 187	92.21 192

TAMVS		80.37 161	79.45 164	83.13 188	85.14 267	63.37 216	91.23 199	90.76 204	74.81 145	72.65 197	88.49 202	60.63 138	92.95 260	69.41 214	81.95 177	93.08 164

VPNet		78.82 191	77.53 193	82.70 196	84.52 277	66.44 134	93.93 72	92.23 134	80.46 52	72.60 198	88.38 205	49.18 268	93.13 255	72.47 188	63.97 318	88.55 246

CLD-MVS		82.73 119	82.35 119	83.86 166	87.90 210	67.65 101	95.45 28	92.18 141	85.06 10	72.58 199	92.27 141	52.46 236	95.78 155	84.18 91	79.06 201	88.16 252
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP_MVS		80.34 162	79.75 158	82.12 216	86.94 235	62.42 239	93.13 110	91.31 182	78.81 88	72.53 200	89.14 198	50.66 252	95.55 172	76.74 152	78.53 207	88.39 249

plane_prior3						61.95 251			79.09 81	72.53 200

EPMVS		78.49 200	75.98 217	86.02 87	91.21 131	69.68 51	80.23 350	91.20 187	75.25 139	72.48 202	78.11 337	54.65 211	93.69 246	57.66 305	83.04 163	94.69 99

1112_ss		80.56 157	79.83 157	82.77 193	88.65 187	60.78 272	92.29 146	88.36 299	72.58 187	72.46 203	94.95 69	65.09 80	93.42 252	66.38 247	77.71 211	94.10 129

PVSNet	73.49 8	80.05 168	78.63 176	84.31 153	90.92 137	64.97 170	92.47 142	91.05 199	79.18 78	72.43 204	90.51 174	37.05 345	94.06 229	68.06 227	86.00 138	93.90 141

OMC-MVS		78.67 197	77.91 188	80.95 246	85.76 257	57.40 323	88.49 273	88.67 291	73.85 160	72.43 204	92.10 146	49.29 267	94.55 209	72.73 184	77.89 210	90.91 215

MVS		84.66 80	82.86 110	90.06 2	90.93 136	74.56 7	87.91 282	95.54 14	68.55 270	72.35 206	94.71 78	59.78 148	98.90 20	81.29 119	94.69 32	96.74 16

EI-MVSNet		78.97 187	78.22 182	81.25 234	85.33 262	62.73 235	89.53 254	93.21 95	72.39 194	72.14 207	90.13 186	60.99 133	94.72 198	67.73 232	72.49 252	86.29 281

MVSTER		82.47 124	82.05 120	83.74 168	92.68 86	69.01 64	91.90 167	93.21 95	79.83 63	72.14 207	85.71 249	74.72 17	94.72 198	75.72 159	72.49 252	87.50 258

WBMVS		81.67 137	80.98 138	83.72 172	93.07 73	69.40 53	94.33 54	93.05 104	76.84 118	72.05 209	84.14 264	74.49 19	93.88 241	72.76 183	68.09 281	87.88 254

OPM-MVS		79.00 186	78.09 183	81.73 224	83.52 293	63.83 198	91.64 181	90.30 222	76.36 127	71.97 210	89.93 189	46.30 294	95.17 185	75.10 164	77.70 212	86.19 284
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Test_1112_low_res		79.56 176	78.60 177	82.43 202	88.24 201	60.39 285	92.09 155	87.99 310	72.10 203	71.84 211	87.42 225	64.62 88	93.04 256	65.80 254	77.30 219	93.85 143

MDTV_nov1_ep13			72.61 264		89.06 178	68.48 76	80.33 348	90.11 230	71.84 212	71.81 212	75.92 357	53.01 231	93.92 239	48.04 340	73.38 244

tfpn200view9		78.79 193	77.43 194	82.88 191	92.21 96	64.49 176	92.05 158	96.28 4	73.48 169	71.75 213	88.26 208	60.07 145	95.32 179	45.16 354	77.58 214	88.83 239

thres400		78.68 195	77.43 194	82.43 202	92.21 96	64.49 176	92.05 158	96.28 4	73.48 169	71.75 213	88.26 208	60.07 145	95.32 179	45.16 354	77.58 214	87.48 259

ACMMP		81.49 141	80.67 143	83.93 165	91.71 116	62.90 231	92.13 152	92.22 137	71.79 214	71.68 215	93.49 115	50.32 254	96.96 105	78.47 144	84.22 157	91.93 197
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
mmtdpeth		68.33 313	66.37 310	74.21 333	82.81 302	51.73 353	84.34 312	80.42 367	67.01 284	71.56 216	68.58 383	30.52 371	92.35 288	75.89 158	36.21 399	78.56 377

mvsany_test1		68.77 308	68.56 297	69.39 360	73.57 377	45.88 388	80.93 344	60.88 408	59.65 344	71.56 216	90.26 181	43.22 310	75.05 395	74.26 173	62.70 324	87.25 267

CHOSEN 280x420		77.35 217	76.95 205	78.55 291	87.07 232	62.68 236	69.71 387	82.95 360	68.80 267	71.48 218	87.27 229	66.03 71	84.00 371	76.47 155	82.81 166	88.95 238

IS-MVSNet		80.14 166	79.41 165	82.33 206	87.91 209	60.08 290	91.97 164	88.27 303	72.90 182	71.44 219	91.73 155	61.44 130	93.66 247	62.47 281	86.53 135	93.24 157

GeoE		78.90 189	77.43 194	83.29 184	88.95 181	62.02 248	92.31 145	86.23 329	70.24 249	71.34 220	89.27 195	54.43 216	94.04 232	63.31 273	80.81 188	93.81 144

PatchmatchNet		77.46 215	74.63 233	85.96 89	89.55 164	70.35 34	79.97 355	89.55 251	72.23 198	70.94 221	76.91 349	57.03 179	92.79 270	54.27 316	81.17 183	94.74 97
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thisisatest0530		81.15 145	80.07 151	84.39 150	88.26 199	65.63 153	91.40 186	94.62 41	71.27 232	70.93 222	89.18 196	72.47 32	96.04 148	65.62 256	76.89 223	91.49 201

SDMVSNet		80.26 163	78.88 174	84.40 149	89.25 172	67.63 102	85.35 306	93.02 105	76.77 121	70.84 223	87.12 230	47.95 280	96.09 143	85.04 81	74.55 233	89.48 235

sd_testset		77.08 222	75.37 224	82.20 212	89.25 172	62.11 247	82.06 333	89.09 273	76.77 121	70.84 223	87.12 230	41.43 316	95.01 188	67.23 237	74.55 233	89.48 235

AdaColmap		78.94 188	77.00 204	84.76 133	96.34 17	65.86 148	92.66 133	87.97 312	62.18 324	70.56 225	92.37 139	43.53 308	97.35 72	64.50 265	82.86 164	91.05 214

cascas		78.18 204	75.77 220	85.41 108	87.14 230	69.11 61	92.96 118	91.15 191	66.71 285	70.47 226	86.07 244	37.49 339	96.48 127	70.15 208	79.80 194	90.65 217

thres600view7		78.00 206	76.66 208	82.03 221	91.93 108	63.69 206	91.30 196	96.33 1	72.43 192	70.46 227	87.89 217	60.31 140	94.92 193	42.64 366	76.64 224	87.48 259

thres100view900		78.37 201	77.01 203	82.46 201	91.89 111	63.21 221	91.19 203	96.33 1	72.28 197	70.45 228	87.89 217	60.31 140	95.32 179	45.16 354	77.58 214	88.83 239

CVMVSNet		74.04 263	74.27 241	73.33 338	85.33 262	43.94 392	89.53 254	88.39 298	54.33 368	70.37 229	90.13 186	49.17 269	84.05 369	61.83 285	79.36 198	91.99 196

GA-MVS		78.33 203	76.23 213	84.65 139	83.65 291	66.30 138	91.44 183	90.14 229	76.01 129	70.32 230	84.02 266	42.50 312	94.72 198	70.98 200	77.00 222	92.94 169

mvs_anonymous		81.36 143	79.99 154	85.46 106	90.39 147	68.40 78	86.88 299	90.61 210	74.41 147	70.31 231	84.67 258	63.79 98	92.32 290	73.13 177	85.70 141	95.67 51

IB-MVS	77.80 4	82.18 128	80.46 149	87.35 45	89.14 177	70.28 35	95.59 26	95.17 22	78.85 86	70.19 232	85.82 247	70.66 42	97.67 51	72.19 192	66.52 293	94.09 130
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
TAPA-MVS	70.22 12	74.94 256	73.53 252	79.17 285	90.40 146	52.07 352	89.19 262	89.61 250	62.69 321	70.07 233	92.67 131	48.89 273	94.32 215	38.26 380	79.97 192	91.12 213
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SCA		75.82 244	72.76 260	85.01 123	86.63 239	70.08 37	81.06 343	89.19 265	71.60 224	70.01 234	77.09 347	45.53 298	90.25 321	60.43 291	73.27 245	94.68 100

XXY-MVS		77.94 209	76.44 210	82.43 202	82.60 303	64.44 180	92.01 160	91.83 160	73.59 168	70.00 235	85.82 247	54.43 216	94.76 195	69.63 211	68.02 283	88.10 253

CR-MVSNet		73.79 267	70.82 282	82.70 196	83.15 297	67.96 92	70.25 384	84.00 351	73.67 167	69.97 236	72.41 369	57.82 172	89.48 333	52.99 322	73.13 246	90.64 218

RPMNet		70.42 294	65.68 315	84.63 141	83.15 297	67.96 92	70.25 384	90.45 212	46.83 390	69.97 236	65.10 390	56.48 193	95.30 182	35.79 385	73.13 246	90.64 218

UniMVSNet (Re)		77.58 214	76.78 206	79.98 267	84.11 285	60.80 271	91.76 175	93.17 99	76.56 125	69.93 238	84.78 257	63.32 110	92.36 287	64.89 263	62.51 327	86.78 273

PCF-MVS	73.15 9	79.29 181	77.63 191	84.29 154	86.06 250	65.96 146	87.03 295	91.10 193	69.86 254	69.79 239	90.64 170	57.54 175	96.59 119	64.37 266	82.29 169	90.32 221
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
v2v482		77.42 216	75.65 222	82.73 194	80.38 324	67.13 116	91.85 170	90.23 226	75.09 141	69.37 240	83.39 273	53.79 223	94.44 213	71.77 194	65.00 305	86.63 277

PatchT		69.11 305	65.37 319	80.32 255	82.07 309	63.68 207	67.96 394	87.62 314	50.86 378	69.37 240	65.18 389	57.09 178	88.53 339	41.59 369	66.60 292	88.74 242

Vis-MVSNet (Re-imp)		79.24 182	79.57 160	78.24 296	88.46 191	52.29 351	90.41 229	89.12 271	74.24 151	69.13 242	91.91 151	65.77 74	90.09 328	59.00 300	88.09 114	92.33 184

BH-w/o		80.49 159	79.30 168	84.05 162	90.83 140	64.36 187	93.60 92	89.42 256	74.35 149	69.09 243	90.15 185	55.23 205	95.61 167	64.61 264	86.43 137	92.17 193

baseline2		83.68 104	83.42 95	84.48 147	87.37 225	66.00 144	90.06 241	95.93 8	79.71 67	69.08 244	90.39 177	77.92 6	96.28 134	78.91 140	81.38 182	91.16 212

v1144		76.73 230	74.88 230	82.27 208	80.23 328	66.60 131	91.68 179	90.21 228	73.69 165	69.06 245	81.89 289	52.73 234	94.40 214	69.21 217	65.23 302	85.80 296

dmvs_re		76.93 224	75.36 225	81.61 227	87.78 216	60.71 277	80.00 354	87.99 310	79.42 72	69.02 246	89.47 193	46.77 286	94.32 215	63.38 272	74.45 236	89.81 228

Baseline_NR-MVSNet		73.99 264	72.83 259	77.48 303	80.78 319	59.29 303	91.79 172	84.55 346	68.85 266	68.99 247	80.70 310	56.16 194	92.04 296	62.67 279	60.98 342	81.11 353

FIs		79.47 179	79.41 165	79.67 276	85.95 252	59.40 299	91.68 179	93.94 64	78.06 97	68.96 248	88.28 206	66.61 65	91.77 301	66.20 250	74.99 232	87.82 255

UniMVSNet_NR-MVSNet		78.15 205	77.55 192	79.98 267	84.46 279	60.26 286	92.25 147	93.20 97	77.50 110	68.88 249	86.61 237	66.10 70	92.13 293	66.38 247	62.55 325	87.54 257

DU-MVS		76.86 225	75.84 219	79.91 270	82.96 299	60.26 286	91.26 197	91.54 173	76.46 126	68.88 249	86.35 240	56.16 194	92.13 293	66.38 247	62.55 325	87.35 263

miper_enhance_ethall		78.86 190	77.97 186	81.54 229	88.00 208	65.17 164	91.41 184	89.15 268	75.19 140	68.79 251	83.98 267	67.17 60	92.82 267	72.73 184	65.30 299	86.62 278

XVG-OURS-SEG-HR		74.70 258	73.08 256	79.57 279	78.25 354	57.33 324	80.49 346	87.32 316	63.22 314	68.76 252	90.12 188	44.89 304	91.59 306	70.55 206	74.09 240	89.79 229

XVG-OURS		74.25 261	72.46 267	79.63 277	78.45 352	57.59 320	80.33 348	87.39 315	63.86 306	68.76 252	89.62 192	40.50 319	91.72 302	69.00 220	74.25 238	89.58 232

V42		76.46 232	74.55 236	82.19 213	79.14 342	67.82 96	90.26 236	89.42 256	73.75 163	68.63 254	81.89 289	51.31 247	94.09 226	71.69 196	64.84 306	84.66 313

PS-MVSNAJss		77.26 218	76.31 212	80.13 262	80.64 322	59.16 304	90.63 225	91.06 198	72.80 183	68.58 255	84.57 260	53.55 225	93.96 237	72.97 178	71.96 256	87.27 266

v1192		75.98 240	73.92 247	82.15 214	79.73 332	66.24 140	91.22 200	89.75 243	72.67 185	68.49 256	81.42 299	49.86 260	94.27 219	67.08 239	65.02 304	85.95 292

tpm cat1		75.30 251	72.21 269	84.58 143	88.52 188	67.77 97	78.16 364	88.02 309	61.88 330	68.45 257	76.37 353	60.65 137	94.03 234	53.77 319	74.11 239	91.93 197

v144192		76.05 238	74.03 245	82.12 216	79.50 336	66.55 133	91.39 188	89.71 249	72.30 196	68.17 258	81.33 301	51.75 242	94.03 234	67.94 229	64.19 313	85.77 297

v1921920		75.63 248	73.49 253	82.06 220	79.38 337	66.35 136	91.07 208	89.48 252	71.98 204	67.99 259	81.22 304	49.16 270	93.90 240	66.56 243	64.56 311	85.92 294

Effi-MVS+-dtu		76.14 234	75.28 227	78.72 290	83.22 296	55.17 339	89.87 247	87.78 313	75.42 136	67.98 260	81.43 298	45.08 303	92.52 281	75.08 165	71.63 257	88.48 247

114514_t		79.17 183	77.67 189	83.68 174	95.32 29	65.53 157	92.85 123	91.60 172	63.49 310	67.92 261	90.63 172	46.65 288	95.72 163	67.01 240	83.54 159	89.79 229

test_fmvs2		65.78 331	64.84 320	68.60 364	66.54 396	41.71 396	83.27 322	69.81 395	54.38 367	67.91 262	84.54 261	15.35 401	81.22 388	75.65 160	66.16 294	82.88 333

tttt0517		79.50 177	78.53 178	82.41 205	87.22 228	61.43 262	89.75 250	94.76 33	69.29 260	67.91 262	88.06 215	72.92 28	95.63 165	62.91 277	73.90 243	90.16 223

3Dnovator	73.91 6	82.69 122	80.82 139	88.31 26	89.57 162	71.26 22	92.60 136	94.39 52	78.84 87	67.89 264	92.48 136	48.42 274	98.52 28	68.80 223	94.40 36	95.15 78

WR-MVS		76.76 229	75.74 221	79.82 273	84.60 275	62.27 245	92.60 136	92.51 127	76.06 128	67.87 265	85.34 251	56.76 185	90.24 324	62.20 282	63.69 320	86.94 271

dp		75.01 255	72.09 270	83.76 167	89.28 171	66.22 141	79.96 356	89.75 243	71.16 233	67.80 266	77.19 346	51.81 240	92.54 280	50.39 327	71.44 261	92.51 181

TranMVSNet+NR-MVSNet		75.86 243	74.52 237	79.89 271	82.44 305	60.64 280	91.37 191	91.37 180	76.63 123	67.65 267	86.21 243	52.37 237	91.55 307	61.84 284	60.81 343	87.48 259

cl22		77.94 209	76.78 206	81.42 231	87.57 219	64.93 172	90.67 221	88.86 284	72.45 191	67.63 268	82.68 280	64.07 93	92.91 265	71.79 193	65.30 299	86.44 279

mvsmamba		81.55 140	80.72 141	84.03 163	91.42 124	66.93 122	83.08 326	89.13 270	78.55 92	67.50 269	87.02 233	51.79 241	90.07 329	87.48 58	90.49 92	95.10 81

1314		80.70 155	78.95 173	85.94 90	87.77 217	67.56 103	87.91 282	92.55 126	72.17 201	67.44 270	93.09 119	50.27 256	97.04 95	71.68 197	87.64 120	93.23 158

3Dnovator+	73.60 7	82.10 132	80.60 146	86.60 68	90.89 138	66.80 126	95.20 34	93.44 87	74.05 154	67.42 271	92.49 135	49.46 264	97.65 55	70.80 202	91.68 74	95.33 66

v1240		75.21 253	72.98 258	81.88 222	79.20 339	66.00 144	90.75 217	89.11 272	71.63 223	67.41 272	81.22 304	47.36 284	93.87 242	65.46 259	64.72 309	85.77 297

QAPM		79.95 171	77.39 198	87.64 34	89.63 161	71.41 20	93.30 106	93.70 75	65.34 296	67.39 273	91.75 154	47.83 281	98.96 16	57.71 304	89.81 96	92.54 179

miper_ehance_all_eth		77.60 213	76.44 210	81.09 243	85.70 259	64.41 183	90.65 222	88.64 293	72.31 195	67.37 274	82.52 281	64.77 87	92.64 278	70.67 204	65.30 299	86.24 283

v148		76.19 233	74.47 238	81.36 232	80.05 330	64.44 180	91.75 177	90.23 226	73.68 166	67.13 275	80.84 309	55.92 199	93.86 244	68.95 221	61.73 336	85.76 299

tt0805		73.07 271	70.73 283	80.07 263	78.37 353	57.05 326	87.78 285	92.18 141	61.23 334	67.04 276	86.49 239	31.35 367	94.58 203	65.06 262	67.12 288	88.57 245

GBi-Net		75.65 246	73.83 248	81.10 240	88.85 182	65.11 166	90.01 243	90.32 218	70.84 240	67.04 276	80.25 319	48.03 276	91.54 308	59.80 296	69.34 269	86.64 274

test1		75.65 246	73.83 248	81.10 240	88.85 182	65.11 166	90.01 243	90.32 218	70.84 240	67.04 276	80.25 319	48.03 276	91.54 308	59.80 296	69.34 269	86.64 274

FMVSNet3		77.73 212	76.04 216	82.80 192	91.20 132	68.99 65	91.87 168	91.99 149	73.35 171	67.04 276	83.19 275	56.62 189	92.14 292	59.80 296	69.34 269	87.28 265

BH-untuned		78.68 195	77.08 201	83.48 181	89.84 156	63.74 201	92.70 129	88.59 294	71.57 225	66.83 280	88.65 201	51.75 242	95.39 177	59.03 299	84.77 148	91.32 208

FC-MVSNet-test		77.99 207	78.08 184	77.70 299	84.89 272	55.51 337	90.27 235	93.75 73	76.87 116	66.80 281	87.59 222	65.71 75	90.23 325	62.89 278	73.94 241	87.37 262

c3_l		76.83 228	75.47 223	80.93 247	85.02 270	64.18 193	90.39 230	88.11 307	71.66 218	66.65 282	81.64 294	63.58 106	92.56 279	69.31 216	62.86 322	86.04 289

MonoMVSNet		76.99 223	75.08 229	82.73 194	83.32 295	63.24 219	86.47 302	86.37 325	79.08 82	66.31 283	79.30 330	49.80 262	91.72 302	79.37 133	65.70 297	93.23 158

FMVSNet2		76.07 235	74.01 246	82.26 210	88.85 182	67.66 100	91.33 194	91.61 171	70.84 240	65.98 284	82.25 285	48.03 276	92.00 297	58.46 301	68.73 277	87.10 268

eth_miper_zixun_eth		75.96 242	74.40 239	80.66 249	84.66 274	63.02 225	89.28 259	88.27 303	71.88 209	65.73 285	81.65 293	59.45 151	92.81 268	68.13 226	60.53 345	86.14 285

ACMM	69.62 13	74.34 259	72.73 262	79.17 285	84.25 284	57.87 315	90.36 232	89.93 237	63.17 316	65.64 286	86.04 246	37.79 337	94.10 225	65.89 252	71.52 259	85.55 302
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
cl____		76.07 235	74.67 231	80.28 257	85.15 266	61.76 254	90.12 239	88.73 288	71.16 233	65.43 287	81.57 296	61.15 131	92.95 260	66.54 244	62.17 329	86.13 287

DIV-MVS_self_test		76.07 235	74.67 231	80.28 257	85.14 267	61.75 255	90.12 239	88.73 288	71.16 233	65.42 288	81.60 295	61.15 131	92.94 264	66.54 244	62.16 331	86.14 285

Fast-Effi-MVS+-dtu		75.04 254	73.37 254	80.07 263	80.86 317	59.52 298	91.20 202	85.38 337	71.90 207	65.20 289	84.84 256	41.46 315	92.97 259	66.50 246	72.96 248	87.73 256

IterMVS-LS		76.49 231	75.18 228	80.43 254	84.49 278	62.74 234	90.64 223	88.80 286	72.40 193	65.16 290	81.72 292	60.98 134	92.27 291	67.74 231	64.65 310	86.29 281
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LPG-MVS_test		75.82 244	74.58 235	79.56 280	84.31 282	59.37 300	90.44 227	89.73 246	69.49 257	64.86 291	88.42 203	38.65 325	94.30 217	72.56 186	72.76 249	85.01 310

LGP-MVS_train				79.56 280	84.31 282	59.37 300		89.73 246	69.49 257	64.86 291	88.42 203	38.65 325	94.30 217	72.56 186	72.76 249	85.01 310

UniMVSNet_ETH3D		72.74 278	70.53 285	79.36 282	78.62 351	56.64 330	85.01 308	89.20 264	63.77 307	64.84 293	84.44 262	34.05 356	91.86 299	63.94 268	70.89 264	89.57 233

MIMVSNet		71.64 286	68.44 299	81.23 235	81.97 310	64.44 180	73.05 378	88.80 286	69.67 256	64.59 294	74.79 362	32.79 359	87.82 346	53.99 317	76.35 226	91.42 203

OpenMVS	70.45 11	78.54 199	75.92 218	86.41 77	85.93 255	71.68 18	92.74 126	92.51 127	66.49 287	64.56 295	91.96 148	43.88 307	98.10 37	54.61 314	90.65 89	89.44 237

ADS-MVSNet2		66.90 324	63.44 332	77.26 308	88.06 205	60.70 278	68.01 392	75.56 379	57.57 352	64.48 296	69.87 379	38.68 323	84.10 368	40.87 371	67.89 284	86.97 269

ADS-MVSNet		68.54 311	64.38 328	81.03 244	88.06 205	66.90 123	68.01 392	84.02 350	57.57 352	64.48 296	69.87 379	38.68 323	89.21 335	40.87 371	67.89 284	86.97 269

Anonymous20231211		73.08 270	70.39 286	81.13 238	90.62 142	63.33 217	91.40 186	90.06 233	51.84 374	64.46 298	80.67 312	36.49 347	94.07 228	63.83 269	64.17 314	85.98 291

PLC	68.80 14	75.23 252	73.68 251	79.86 272	92.93 76	58.68 309	90.64 223	88.30 301	60.90 335	64.43 299	90.53 173	42.38 313	94.57 205	56.52 307	76.54 225	86.33 280
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpmvs		72.88 276	69.76 292	82.22 211	90.98 135	67.05 118	78.22 363	88.30 301	63.10 317	64.35 300	74.98 360	55.09 208	94.27 219	43.25 360	69.57 268	85.34 307

reproduce_monomvs		79.49 178	79.11 172	80.64 250	92.91 77	61.47 261	91.17 204	93.28 93	83.09 20	64.04 301	82.38 283	66.19 68	94.57 205	81.19 120	57.71 356	85.88 295

test_djsdf		73.76 268	72.56 265	77.39 305	77.00 364	53.93 345	89.07 264	90.69 205	65.80 291	63.92 302	82.03 288	43.14 311	92.67 275	72.83 180	68.53 278	85.57 301

JIA-IIPM		66.06 328	62.45 338	76.88 313	81.42 315	54.45 344	57.49 408	88.67 291	49.36 382	63.86 303	46.86 406	56.06 197	90.25 321	49.53 332	68.83 275	85.95 292

CNLPA		74.31 260	72.30 268	80.32 255	91.49 123	61.66 257	90.85 213	80.72 366	56.67 361	63.85 304	90.64 170	46.75 287	90.84 316	53.79 318	75.99 229	88.47 248

PatchMatch-RL		72.06 284	69.98 287	78.28 294	89.51 165	55.70 336	83.49 318	83.39 358	61.24 333	63.72 305	82.76 278	34.77 353	93.03 257	53.37 321	77.59 213	86.12 288

FMVSNet1		72.71 279	69.91 290	81.10 240	83.60 292	65.11 166	90.01 243	90.32 218	63.92 305	63.56 306	80.25 319	36.35 348	91.54 308	54.46 315	66.75 291	86.64 274

pmmvs4		73.92 265	71.81 274	80.25 259	79.17 340	65.24 162	87.43 291	87.26 318	67.64 278	63.46 307	83.91 268	48.96 272	91.53 311	62.94 276	65.49 298	83.96 317

pmmvs5		73.35 269	71.52 276	78.86 289	78.64 350	60.61 281	91.08 206	86.90 320	67.69 275	63.32 308	83.64 269	44.33 306	90.53 318	62.04 283	66.02 295	85.46 304

v8		75.35 250	73.26 255	81.61 227	80.67 321	66.82 124	89.54 253	89.27 261	71.65 219	63.30 309	80.30 318	54.99 209	94.06 229	67.33 236	62.33 328	83.94 318

Syy-MVS		69.65 301	69.52 293	70.03 358	87.87 211	43.21 394	88.07 278	89.01 277	72.91 180	63.11 310	88.10 212	45.28 301	85.54 361	22.07 408	69.23 272	81.32 351

myMVS_eth3d		72.58 283	72.74 261	72.10 350	87.87 211	49.45 368	88.07 278	89.01 277	72.91 180	63.11 310	88.10 212	63.63 101	85.54 361	32.73 395	69.23 272	81.32 351

v10		74.77 257	72.54 266	81.46 230	80.33 326	66.71 128	89.15 263	89.08 274	70.94 238	63.08 312	79.86 323	52.52 235	94.04 232	65.70 255	62.17 329	83.64 321

ACMP	71.68 10	75.58 249	74.23 242	79.62 278	84.97 271	59.64 295	90.80 215	89.07 275	70.39 247	62.95 313	87.30 227	38.28 329	93.87 242	72.89 179	71.45 260	85.36 306
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
pm-mvs1		72.89 275	71.09 279	78.26 295	79.10 343	57.62 319	90.80 215	89.30 260	67.66 276	62.91 314	81.78 291	49.11 271	92.95 260	60.29 293	58.89 353	84.22 316

jajsoiax		73.05 272	71.51 277	77.67 300	77.46 361	54.83 341	88.81 268	90.04 234	69.13 264	62.85 315	83.51 271	31.16 368	92.75 271	70.83 201	69.80 265	85.43 305

mvs_tets		72.71 279	71.11 278	77.52 301	77.41 362	54.52 343	88.45 274	89.76 242	68.76 269	62.70 316	83.26 274	29.49 373	92.71 272	70.51 207	69.62 267	85.34 307

MS-PatchMatch		77.90 211	76.50 209	82.12 216	85.99 251	69.95 41	91.75 177	92.70 116	73.97 157	62.58 317	84.44 262	41.11 317	95.78 155	63.76 270	92.17 66	80.62 359

test0.0.03 1		72.76 277	72.71 263	72.88 342	80.25 327	47.99 375	91.22 200	89.45 254	71.51 228	62.51 318	87.66 220	53.83 221	85.06 365	50.16 329	67.84 286	85.58 300

anonymousdsp		71.14 290	69.37 294	76.45 315	72.95 379	54.71 342	84.19 313	88.88 282	61.92 329	62.15 319	79.77 325	38.14 332	91.44 313	68.90 222	67.45 287	83.21 330

MVP-Stereo		77.12 221	76.23 213	79.79 274	81.72 311	66.34 137	89.29 258	90.88 202	70.56 246	62.01 320	82.88 277	49.34 265	94.13 224	65.55 258	93.80 43	78.88 373
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CL-MVSNet_self_test		69.92 298	68.09 302	75.41 321	73.25 378	55.90 335	90.05 242	89.90 238	69.96 252	61.96 321	76.54 350	51.05 250	87.64 349	49.51 333	50.59 376	82.70 339

miper_lstm_enhance		73.05 272	71.73 275	77.03 309	83.80 288	58.32 312	81.76 334	88.88 282	69.80 255	61.01 322	78.23 336	57.19 177	87.51 352	65.34 260	59.53 350	85.27 309

NR-MVSNet		76.05 238	74.59 234	80.44 253	82.96 299	62.18 246	90.83 214	91.73 163	77.12 114	60.96 323	86.35 240	59.28 155	91.80 300	60.74 289	61.34 340	87.35 263

tfpnnormal		70.10 296	67.36 305	78.32 293	83.45 294	60.97 269	88.85 267	92.77 114	64.85 298	60.83 324	78.53 333	43.52 309	93.48 250	31.73 398	61.70 337	80.52 360

mvs5depth		61.03 350	57.65 355	71.18 354	67.16 395	47.04 383	72.74 379	77.49 372	57.47 355	60.52 325	72.53 366	22.84 389	88.38 340	49.15 334	38.94 395	78.11 380

IterMVS		72.65 282	70.83 280	78.09 297	82.17 307	62.96 227	87.64 289	86.28 327	71.56 226	60.44 326	78.85 332	45.42 300	86.66 356	63.30 274	61.83 333	84.65 314
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3		70.38 295	70.83 280	69.03 362	85.82 256	43.93 393	90.72 220	90.56 211	68.06 273	60.24 327	86.82 236	64.83 85	84.12 367	26.33 403	64.10 315	79.04 372

WR-MVS_H		70.59 292	69.94 289	72.53 344	81.03 316	51.43 356	87.35 292	92.03 148	67.38 279	60.23 328	80.70 310	55.84 200	83.45 375	46.33 350	58.58 355	82.72 337

TransMVSNet (Re)		70.07 297	67.66 303	77.31 307	80.62 323	59.13 305	91.78 174	84.94 342	65.97 290	60.08 329	80.44 315	50.78 251	91.87 298	48.84 336	45.46 384	80.94 355

CP-MVSNet		70.50 293	69.91 290	72.26 347	80.71 320	51.00 360	87.23 294	90.30 222	67.84 274	59.64 330	82.69 279	50.23 257	82.30 383	51.28 324	59.28 351	83.46 326

IterMVS-SCA-FT		71.55 288	69.97 288	76.32 316	81.48 313	60.67 279	87.64 289	85.99 332	66.17 289	59.50 331	78.88 331	45.53 298	83.65 373	62.58 280	61.93 332	84.63 315

Patchmtry		67.53 321	63.93 329	78.34 292	82.12 308	64.38 184	68.72 389	84.00 351	48.23 387	59.24 332	72.41 369	57.82 172	89.27 334	46.10 351	56.68 361	81.36 350

D2MVS		73.80 266	72.02 271	79.15 287	79.15 341	62.97 226	88.58 272	90.07 231	72.94 178	59.22 333	78.30 334	42.31 314	92.70 274	65.59 257	72.00 255	81.79 348

PS-CasMVS		69.86 300	69.13 295	72.07 351	80.35 325	50.57 362	87.02 296	89.75 243	67.27 280	59.19 334	82.28 284	46.58 289	82.24 384	50.69 326	59.02 352	83.39 328

PEN-MVS		69.46 303	68.56 297	72.17 349	79.27 338	49.71 366	86.90 298	89.24 262	67.24 283	59.08 335	82.51 282	47.23 285	83.54 374	48.42 338	57.12 357	83.25 329

RPSCF		64.24 339	61.98 341	71.01 356	76.10 368	45.00 389	75.83 373	75.94 376	46.94 389	58.96 336	84.59 259	31.40 366	82.00 385	47.76 344	60.33 349	86.04 289

XVG-ACMP-BASELINE		68.04 316	65.53 317	75.56 320	74.06 376	52.37 350	78.43 360	85.88 333	62.03 327	58.91 337	81.21 306	20.38 395	91.15 315	60.69 290	68.18 280	83.16 331

v7n		71.31 289	68.65 296	79.28 283	76.40 366	60.77 273	86.71 300	89.45 254	64.17 304	58.77 338	78.24 335	44.59 305	93.54 248	57.76 303	61.75 335	83.52 324

ET-MVSNet_ETH3D		84.01 94	83.15 104	86.58 70	90.78 141	70.89 28	94.74 47	94.62 41	81.44 40	58.19 339	93.64 111	73.64 25	92.35 288	82.66 106	78.66 206	96.50 27

DTE-MVSNet		68.46 312	67.33 306	71.87 353	77.94 358	49.00 372	86.16 304	88.58 295	66.36 288	58.19 339	82.21 286	46.36 290	83.87 372	44.97 357	55.17 364	82.73 336

Anonymous20231206		67.53 321	65.78 313	72.79 343	74.95 372	47.59 377	88.23 276	87.32 316	61.75 332	58.07 341	77.29 344	37.79 337	87.29 354	42.91 362	63.71 319	83.48 325

KD-MVS_2432*1600		69.03 306	66.37 310	77.01 310	85.56 260	61.06 267	81.44 339	90.25 224	67.27 280	58.00 342	76.53 351	54.49 213	87.63 350	48.04 340	35.77 401	82.34 343

miper_refine_blended		69.03 306	66.37 310	77.01 310	85.56 260	61.06 267	81.44 339	90.25 224	67.27 280	58.00 342	76.53 351	54.49 213	87.63 350	48.04 340	35.77 401	82.34 343

PVSNet_0	68.08 15	71.81 285	68.32 301	82.27 208	84.68 273	62.31 244	88.68 270	90.31 221	75.84 130	57.93 344	80.65 313	37.85 336	94.19 222	69.94 209	29.05 410	90.31 222

mamv4		65.18 334	67.43 304	58.44 380	77.88 360	49.36 371	69.40 388	70.99 393	48.31 386	57.78 345	85.53 250	59.01 160	51.88 418	73.67 175	64.32 312	74.07 388

DP-MVS		69.90 299	66.48 307	80.14 261	95.36 28	62.93 228	89.56 251	76.11 375	50.27 380	57.69 346	85.23 252	39.68 321	95.73 159	33.35 390	71.05 263	81.78 349

pmmvs6		67.57 320	64.76 322	76.00 319	72.82 381	53.37 347	88.71 269	86.78 324	53.19 370	57.58 347	78.03 338	35.33 352	92.41 284	55.56 311	54.88 366	82.21 345

F-COLMAP		70.66 291	68.44 299	77.32 306	86.37 245	55.91 334	88.00 280	86.32 326	56.94 359	57.28 348	88.07 214	33.58 357	92.49 282	51.02 325	68.37 279	83.55 322

Patchmatch-RL test		68.17 315	64.49 326	79.19 284	71.22 383	53.93 345	70.07 386	71.54 392	69.22 261	56.79 349	62.89 394	56.58 190	88.61 336	69.53 213	52.61 371	95.03 85

LS3D		69.17 304	66.40 309	77.50 302	91.92 109	56.12 333	85.12 307	80.37 368	46.96 388	56.50 350	87.51 224	37.25 340	93.71 245	32.52 397	79.40 197	82.68 340

dmvs_testset		65.55 332	66.45 308	62.86 376	79.87 331	22.35 422	76.55 368	71.74 390	77.42 113	55.85 351	87.77 219	51.39 246	80.69 389	31.51 401	65.92 296	85.55 302

ppachtmachnet_test		67.72 318	63.70 330	79.77 275	78.92 344	66.04 143	88.68 270	82.90 361	60.11 342	55.45 352	75.96 356	39.19 322	90.55 317	39.53 375	52.55 372	82.71 338

test_fmvs3		56.82 359	54.86 363	62.69 378	53.59 411	35.47 408	75.87 372	65.64 402	43.91 396	55.10 353	71.43 377	6.91 416	74.40 398	68.64 224	52.63 370	78.20 379

LTVRE_ROB	59.60 19	66.27 327	63.54 331	74.45 329	84.00 287	51.55 355	67.08 396	83.53 355	58.78 348	54.94 354	80.31 317	34.54 354	93.23 254	40.64 373	68.03 282	78.58 376
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
MSDG		69.54 302	65.73 314	80.96 245	85.11 269	63.71 204	84.19 313	83.28 359	56.95 358	54.50 355	84.03 265	31.50 365	96.03 149	42.87 364	69.13 274	83.14 332

EU-MVSNet		64.01 340	63.01 334	67.02 370	74.40 375	38.86 405	83.27 322	86.19 330	45.11 393	54.27 356	81.15 307	36.91 346	80.01 391	48.79 337	57.02 358	82.19 346

testgi		64.48 338	62.87 336	69.31 361	71.24 382	40.62 399	85.49 305	79.92 369	65.36 295	54.18 357	83.49 272	23.74 387	84.55 366	41.60 368	60.79 344	82.77 335

ITE_SJBPF				70.43 357	74.44 374	47.06 382		77.32 373	60.16 341	54.04 358	83.53 270	23.30 388	84.01 370	43.07 361	61.58 339	80.21 365

OpenMVS_ROB	61.12 18	66.39 326	62.92 335	76.80 314	76.51 365	57.77 316	89.22 260	83.41 357	55.48 365	53.86 359	77.84 339	26.28 383	93.95 238	34.90 387	68.76 276	78.68 375

FMVSNet5		68.04 316	65.66 316	75.18 324	84.43 280	57.89 314	83.54 317	86.26 328	61.83 331	53.64 360	73.30 365	37.15 343	85.08 364	48.99 335	61.77 334	82.56 342

ACMH+	65.35 16	67.65 319	64.55 324	76.96 312	84.59 276	57.10 325	88.08 277	80.79 365	58.59 350	53.00 361	81.09 308	26.63 382	92.95 260	46.51 348	61.69 338	80.82 356

our_test_3		68.29 314	64.69 323	79.11 288	78.92 344	64.85 173	88.40 275	85.06 340	60.32 340	52.68 362	76.12 355	40.81 318	89.80 332	44.25 359	55.65 362	82.67 341

test_0402		64.54 337	61.09 343	74.92 326	84.10 286	60.75 275	87.95 281	79.71 370	52.03 372	52.41 363	77.20 345	32.21 363	91.64 304	23.14 406	61.03 341	72.36 394

LCM-MVSNet-Re		72.93 274	71.84 273	76.18 318	88.49 189	48.02 374	80.07 353	70.17 394	73.96 158	52.25 364	80.09 322	49.98 258	88.24 342	67.35 234	84.23 156	92.28 187

ttmdpeth		53.34 365	49.96 368	63.45 375	62.07 405	40.04 400	72.06 380	65.64 402	42.54 400	51.88 365	77.79 340	13.94 407	76.48 394	32.93 393	30.82 409	73.84 389

test20.03		63.83 341	62.65 337	67.38 369	70.58 388	39.94 401	86.57 301	84.17 348	63.29 313	51.86 366	77.30 343	37.09 344	82.47 381	38.87 379	54.13 368	79.73 366

OurMVSNet-221017-0		64.68 336	62.17 340	72.21 348	76.08 369	47.35 378	80.67 345	81.02 364	56.19 362	51.60 367	79.66 327	27.05 381	88.56 338	53.60 320	53.63 369	80.71 358

ACMH	63.93 17	68.62 309	64.81 321	80.03 265	85.22 265	63.25 218	87.72 286	84.66 344	60.83 336	51.57 368	79.43 329	27.29 380	94.96 190	41.76 367	64.84 306	81.88 347
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DSMNet-mixed		56.78 360	54.44 364	63.79 374	63.21 401	29.44 417	64.43 399	64.10 404	42.12 401	51.32 369	71.60 374	31.76 364	75.04 396	36.23 382	65.20 303	86.87 272

pmmvs-eth3d		65.53 333	62.32 339	75.19 323	69.39 391	59.59 296	82.80 330	83.43 356	62.52 322	51.30 370	72.49 367	32.86 358	87.16 355	55.32 312	50.73 375	78.83 374

PM-MVS		59.40 356	56.59 358	67.84 365	63.63 400	41.86 395	76.76 367	63.22 405	59.01 347	51.07 371	72.27 372	11.72 408	83.25 377	61.34 286	50.28 377	78.39 378

Patchmatch-test		65.86 329	60.94 344	80.62 252	83.75 289	58.83 307	58.91 407	75.26 381	44.50 395	50.95 372	77.09 347	58.81 162	87.90 344	35.13 386	64.03 316	95.12 80

SixPastTwentyTwo		64.92 335	61.78 342	74.34 331	78.74 348	49.76 365	83.42 321	79.51 371	62.86 318	50.27 373	77.35 342	30.92 370	90.49 319	45.89 352	47.06 381	82.78 334

EG-PatchMatch MVS		68.55 310	65.41 318	77.96 298	78.69 349	62.93 228	89.86 248	89.17 266	60.55 337	50.27 373	77.73 341	22.60 390	94.06 229	47.18 346	72.65 251	76.88 383

ambc				69.61 359	61.38 406	41.35 397	49.07 413	85.86 335		50.18 375	66.40 387	10.16 410	88.14 343	45.73 353	44.20 385	79.32 370

test_vis1_rt		59.09 358	57.31 357	64.43 373	68.44 393	46.02 387	83.05 328	48.63 417	51.96 373	49.57 376	63.86 393	16.30 399	80.20 390	71.21 199	62.79 323	67.07 400

KD-MVS_self_test		60.87 351	58.60 351	67.68 367	66.13 397	39.93 402	75.63 375	84.70 343	57.32 356	49.57 376	68.45 384	29.55 372	82.87 379	48.09 339	47.94 380	80.25 364

UnsupCasMVSNet_eth		65.79 330	63.10 333	73.88 334	70.71 386	50.29 364	81.09 342	89.88 239	72.58 187	49.25 378	74.77 363	32.57 361	87.43 353	55.96 310	41.04 391	83.90 319

kuosan		60.86 352	60.24 345	62.71 377	81.57 312	46.43 385	75.70 374	85.88 333	57.98 351	48.95 379	69.53 381	58.42 165	76.53 393	28.25 402	35.87 400	65.15 401

COLMAP_ROB	57.96 20	62.98 345	59.65 348	72.98 341	81.44 314	53.00 349	83.75 316	75.53 380	48.34 385	48.81 380	81.40 300	24.14 385	90.30 320	32.95 392	60.52 346	75.65 386
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
USDC		67.43 323	64.51 325	76.19 317	77.94 358	55.29 338	78.38 361	85.00 341	73.17 173	48.36 381	80.37 316	21.23 392	92.48 283	52.15 323	64.02 317	80.81 357

Anonymous20240521		62.09 346	59.08 350	71.10 355	67.19 394	48.72 373	83.91 315	85.23 339	50.38 379	47.84 382	71.22 378	20.74 393	85.51 363	46.47 349	58.75 354	79.06 371

K. test v3		63.09 344	59.61 349	73.53 337	76.26 367	49.38 370	83.27 322	77.15 374	64.35 301	47.77 383	72.32 371	28.73 375	87.79 347	49.93 331	36.69 398	83.41 327

UnsupCasMVSNet_bld		61.60 348	57.71 353	73.29 339	68.73 392	51.64 354	78.61 359	89.05 276	57.20 357	46.11 384	61.96 397	28.70 376	88.60 337	50.08 330	38.90 396	79.63 367

AllTest		61.66 347	58.06 352	72.46 345	79.57 333	51.42 357	80.17 351	68.61 397	51.25 376	45.88 385	81.23 302	19.86 397	86.58 357	38.98 377	57.01 359	79.39 368

TestCases				72.46 345	79.57 333	51.42 357		68.61 397	51.25 376	45.88 385	81.23 302	19.86 397	86.58 357	38.98 377	57.01 359	79.39 368

lessismore_v0				73.72 336	72.93 380	47.83 376		61.72 407		45.86 387	73.76 364	28.63 377	89.81 330	47.75 345	31.37 406	83.53 323

N_pmnet		50.55 367	49.11 369	54.88 386	77.17 363	4.02 430	84.36 311	2.00 428	48.59 383	45.86 387	68.82 382	32.22 362	82.80 380	31.58 399	51.38 374	77.81 381

mvsany_test3		48.86 369	46.35 372	56.41 382	46.00 417	31.67 413	62.26 401	47.25 418	43.71 397	45.54 389	68.15 385	10.84 409	64.44 414	57.95 302	35.44 403	73.13 391

MVS-HIRNet		60.25 354	55.55 361	74.35 330	84.37 281	56.57 331	71.64 382	74.11 383	34.44 404	45.54 389	42.24 412	31.11 369	89.81 330	40.36 374	76.10 228	76.67 384

CMPMVS	48.56 21	66.77 325	64.41 327	73.84 335	70.65 387	50.31 363	77.79 365	85.73 336	45.54 392	44.76 391	82.14 287	35.40 351	90.14 327	63.18 275	74.54 235	81.07 354
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		60.16 355	57.33 356	68.67 363	69.71 389	44.13 391	78.92 358	84.21 347	55.05 366	44.63 392	71.85 373	23.91 386	81.54 387	32.63 396	55.03 365	80.35 361

LF4IMVS		54.01 364	52.12 365	59.69 379	62.41 403	39.91 403	68.59 390	68.28 399	42.96 399	44.55 393	75.18 359	14.09 406	68.39 405	41.36 370	51.68 373	70.78 395

pmmvs3		55.51 361	51.50 367	67.53 368	57.90 409	50.93 361	80.37 347	73.66 384	40.63 402	44.15 394	64.75 391	16.30 399	78.97 392	44.77 358	40.98 393	72.69 392

new-patchmatchnet		59.30 357	56.48 359	67.79 366	65.86 398	44.19 390	82.47 331	81.77 362	59.94 343	43.65 395	66.20 388	27.67 379	81.68 386	39.34 376	41.40 390	77.50 382

dongtai		55.18 363	55.46 362	54.34 388	76.03 370	36.88 406	76.07 371	84.61 345	51.28 375	43.41 396	64.61 392	56.56 191	67.81 406	18.09 411	28.50 411	58.32 404

TDRefinement		55.28 362	51.58 366	66.39 371	59.53 408	46.15 386	76.23 370	72.80 385	44.60 394	42.49 397	76.28 354	15.29 402	82.39 382	33.20 391	43.75 386	70.62 396

test_f		46.58 370	43.45 374	55.96 383	45.18 418	32.05 412	61.18 402	49.49 416	33.39 405	42.05 398	62.48 396	7.00 415	65.56 410	47.08 347	43.21 388	70.27 397

TinyColmap		60.32 353	56.42 360	72.00 352	78.78 347	53.18 348	78.36 362	75.64 378	52.30 371	41.59 399	75.82 358	14.76 404	88.35 341	35.84 383	54.71 367	74.46 387

YYNet1		63.76 343	60.14 347	74.62 328	78.06 357	60.19 289	83.46 320	83.99 353	56.18 363	39.25 400	71.56 376	37.18 342	83.34 376	42.90 363	48.70 379	80.32 362

MDA-MVSNet_test_wron		63.78 342	60.16 346	74.64 327	78.15 356	60.41 284	83.49 318	84.03 349	56.17 364	39.17 401	71.59 375	37.22 341	83.24 378	42.87 364	48.73 378	80.26 363

WB-MVS		46.23 371	44.94 373	50.11 391	62.13 404	21.23 424	76.48 369	55.49 410	45.89 391	35.78 402	61.44 399	35.54 350	72.83 399	9.96 418	21.75 413	56.27 406

MVStest1		51.35 366	46.89 370	64.74 372	65.06 399	51.10 359	67.33 395	72.58 386	30.20 408	35.30 403	74.82 361	27.70 378	69.89 403	24.44 405	24.57 412	73.22 390

new_pmnet		49.31 368	46.44 371	57.93 381	62.84 402	40.74 398	68.47 391	62.96 406	36.48 403	35.09 404	57.81 401	14.97 403	72.18 400	32.86 394	46.44 382	60.88 403

MDA-MVSNet-bldmvs		61.54 349	57.70 354	73.05 340	79.53 335	57.00 329	83.08 326	81.23 363	57.57 352	34.91 405	72.45 368	32.79 359	86.26 359	35.81 384	41.95 389	75.89 385

SSC-MVS		44.51 373	43.35 375	47.99 395	61.01 407	18.90 426	74.12 377	54.36 411	43.42 398	34.10 406	60.02 400	34.42 355	70.39 402	9.14 420	19.57 414	54.68 407

test_vis3_rt		40.46 377	37.79 378	48.47 394	44.49 419	33.35 411	66.56 397	32.84 425	32.39 406	29.65 407	39.13 415	3.91 423	68.65 404	50.17 328	40.99 392	43.40 410

test_method		38.59 379	35.16 382	48.89 393	54.33 410	21.35 423	45.32 414	53.71 412	7.41 420	28.74 408	51.62 404	8.70 413	52.87 417	33.73 388	32.89 405	72.47 393

FPMVS		45.64 372	43.10 376	53.23 389	51.42 414	36.46 407	64.97 398	71.91 389	29.13 409	27.53 409	61.55 398	9.83 411	65.01 412	16.00 415	55.58 363	58.22 405

APD_test1		40.50 376	37.31 379	50.09 392	51.88 412	35.27 409	59.45 406	52.59 413	21.64 412	26.12 410	57.80 402	4.56 420	66.56 408	22.64 407	39.09 394	48.43 408

LCM-MVSNet		40.54 375	35.79 380	54.76 387	36.92 424	30.81 414	51.41 411	69.02 396	22.07 411	24.63 411	45.37 408	4.56 420	65.81 409	33.67 389	34.50 404	67.67 398

PMMVS2		37.93 380	33.61 383	50.92 390	46.31 416	24.76 420	60.55 405	50.05 414	28.94 410	20.93 412	47.59 405	4.41 422	65.13 411	25.14 404	18.55 416	62.87 402

tmp_tt		22.26 388	23.75 390	17.80 404	5.23 428	12.06 429	35.26 415	39.48 422	2.82 422	18.94 413	44.20 411	22.23 391	24.64 423	36.30 381	9.31 420	16.69 417

ANet_high		40.27 378	35.20 381	55.47 384	34.74 425	34.47 410	63.84 400	71.56 391	48.42 384	18.80 414	41.08 413	9.52 412	64.45 413	20.18 409	8.66 421	67.49 399

testf1		32.77 382	29.47 385	42.67 398	41.89 421	30.81 414	52.07 409	43.45 419	15.45 415	18.52 415	44.82 409	2.12 424	58.38 415	16.05 413	30.87 407	38.83 411

APD_test2		32.77 382	29.47 385	42.67 398	41.89 421	30.81 414	52.07 409	43.45 419	15.45 415	18.52 415	44.82 409	2.12 424	58.38 415	16.05 413	30.87 407	38.83 411

DeepMVS_CX				34.71 401	51.45 413	24.73 421		28.48 427	31.46 407	17.49 417	52.75 403	5.80 418	42.60 422	18.18 410	19.42 415	36.81 414

Gipuma		34.91 381	31.44 384	45.30 396	70.99 385	39.64 404	19.85 418	72.56 387	20.10 414	16.16 418	21.47 419	5.08 419	71.16 401	13.07 416	43.70 387	25.08 416
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	26.43 22	31.84 384	28.16 387	42.89 397	25.87 427	27.58 418	50.92 412	49.78 415	21.37 413	14.17 419	40.81 414	2.01 426	66.62 407	9.61 419	38.88 397	34.49 415
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	24.84 23	24.35 386	19.77 392	38.09 400	34.56 426	26.92 419	26.57 416	38.87 423	11.73 419	11.37 420	27.44 416	1.37 427	50.42 419	11.41 417	14.60 417	36.93 413
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		24.61 385	24.00 389	26.45 402	43.74 420	18.44 427	60.86 403	39.66 421	15.11 417	9.53 421	22.10 418	6.52 417	46.94 420	8.31 421	10.14 418	13.98 418

EMVS		23.76 387	23.20 391	25.46 403	41.52 423	16.90 428	60.56 404	38.79 424	14.62 418	8.99 422	20.24 421	7.35 414	45.82 421	7.25 422	9.46 419	13.64 419

wuyk23d		11.30 390	10.95 393	12.33 405	48.05 415	19.89 425	25.89 417	1.92 429	3.58 421	3.12 423	1.37 423	0.64 428	15.77 424	6.23 423	7.77 422	1.35 420

EGC-MVSNET		42.35 374	38.09 377	55.11 385	74.57 373	46.62 384	71.63 383	55.77 409	0.04 423	0.24 424	62.70 395	14.24 405	74.91 397	17.59 412	46.06 383	43.80 409

testmvs		7.23 392	9.62 395	0.06 407	0.04 429	0.02 432	84.98 309	0.02 430	0.03 424	0.18 425	1.21 424	0.01 430	0.02 425	0.14 424	0.01 423	0.13 422

test123		6.92 393	9.21 396	0.08 406	0.03 430	0.05 431	81.65 337	0.01 431	0.02 425	0.14 426	0.85 425	0.03 429	0.02 425	0.12 425	0.00 424	0.16 421

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	0.00 424	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	0.00 424	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	0.00 424	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	0.00 424	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	0.00 424	0.00 423

cdsmvs_eth3d_5k		19.86 389	26.47 388	0.00 408	0.00 431	0.00 433	0.00 419	93.45 86	0.00 426	0.00 427	95.27 59	49.56 263	0.00 427	0.00 426	0.00 424	0.00 423

pcd_1.5k_mvsjas		4.46 394	5.95 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	53.55 225	0.00 427	0.00 426	0.00 424	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	0.00 424	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	0.00 424	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	0.00 424	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	0.00 424	0.00 423

ab-mvs-re		7.91 391	10.55 394	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	94.95 69	0.00 431	0.00 427	0.00 426	0.00 424	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	0.00 424	0.00 423

WAC-MVS						49.45 368								31.56 400

MSC_two_6792asdad				89.60 9	97.31 4	73.22 12		95.05 27					99.07 13	92.01 25	94.77 26	96.51 24

No_MVS				89.60 9	97.31 4	73.22 12		95.05 27					99.07 13	92.01 25	94.77 26	96.51 24

eth-test2					0.00 431

eth-test					0.00 431

OPU-MVS				89.97 3	97.52 3	73.15 14	96.89 6				97.00 9	83.82 2	99.15 2	95.72 5	97.63 3	97.62 2

save fliter					93.84 49	67.89 95	95.05 39	92.66 120	78.19 95

test_0728_SECOND				88.70 18	96.45 12	70.43 33	96.64 10	94.37 53					99.15 2	91.91 28	94.90 22	96.51 24

GSMVS																94.68 100

sam_mvs1												57.85 171				94.68 100

sam_mvs												54.91 210

MTGPA								92.23 134

test_post1							78.95 357				20.70 420	53.05 230	91.50 312	60.43 291

test_post											23.01 417	56.49 192	92.67 275

patchmatchnet-post											67.62 386	57.62 174	90.25 321

MTMP							93.77 84	32.52 426

gm-plane-assit					88.42 193	67.04 119			78.62 91		91.83 152		97.37 70	76.57 154

test9_res														89.41 40	94.96 19	95.29 70

agg_prior2														86.41 70	94.75 30	95.33 66

test_prior4						67.18 114	93.92 73

test_prior				86.42 76	94.71 35	67.35 109		93.10 103					96.84 113			95.05 83

新几何2							91.41 184

旧先验1					91.94 107	60.74 276		91.50 176			94.36 87	65.23 79			91.84 71	94.55 107

无先验							92.71 128	92.61 124	62.03 327				97.01 96	66.63 242		93.97 136

原ACMM2							92.01 160

testdata2													96.09 143	61.26 287

segment_acmp												65.94 72

testdata1							89.21 261		77.55 109

plane_prior7					86.94 235	61.51 259

plane_prior6					87.23 227	62.32 243						50.66 252

plane_prior5								91.31 182					95.55 172	76.74 152	78.53 207	88.39 249

plane_prior4											89.14 198

plane_prior2							93.13 110		78.81 88

plane_prior1					87.15 229

plane_prior						62.42 239	93.85 77		79.38 73						78.80 204

n2								0.00 432

nn								0.00 432

door-mid								66.01 401

test11								93.01 106

door								66.57 400

HQP5-MVS						63.66 208

BP-MVS														77.63 149

HQP3-MVS								91.70 168							78.90 202

HQP2-MVS												51.63 244

NP-MVS					87.41 223	63.04 224					90.30 179

ACMMP++_ref															71.63 257

ACMMP++															69.72 266

Test By Simon												54.21 219

High-resolution multi-view benchmark