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.

MSP-MVS		90.38 5	91.87 1	85.88 88	92.83 77	64.03 192	93.06 113	94.33 54	82.19 28	93.65 3	96.15 35	85.89 1	97.19 84	91.02 33	97.75 1	96.43 30
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
DVP-MVS++		90.53 4	91.09 5	88.87 16	97.31 4	69.91 43	93.96 72	94.37 52	72.48 184	92.07 8	96.85 16	83.82 2	99.15 2	91.53 29	97.42 4	97.55 4

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

PC_three_1452									80.91 46	94.07 2	96.83 18	83.57 4	99.12 5	95.70 7	97.42 4	97.55 4

DPM-MVS		90.70 3	90.52 8	91.24 1	89.68 153	76.68 2	97.29 1	95.35 15	82.87 21	91.58 12	97.22 3	79.93 5	99.10 9	83.12 98	97.64 2	97.94 1

baseline2		83.68 102	83.42 93	84.48 144	87.37 216	66.00 141	90.06 236	95.93 8	79.71 66	69.08 237	90.39 172	77.92 6	96.28 130	78.91 131	81.38 176	91.16 204

GG-mvs-BLEND				86.53 71	91.91 105	69.67 52	75.02 367	94.75 33		78.67 132	90.85 163	77.91 7	94.56 203	72.25 179	93.74 45	95.36 63

gg-mvs-nofinetune		77.18 211	74.31 233	85.80 93	91.42 119	68.36 78	71.78 371	94.72 34	49.61 372	77.12 148	45.92 395	77.41 8	93.98 232	67.62 224	93.16 55	95.05 80

SED-MVS		89.94 9	90.36 10	88.70 18	96.45 12	69.38 54	96.89 5	94.44 46	71.65 214	92.11 6	97.21 4	76.79 9	99.11 6	92.34 21	95.36 13	97.62 2

test_241102_ONE					96.45 12	69.38 54		94.44 46	71.65 214	92.11 6	97.05 7	76.79 9	99.11 6

test_0728_THIRD									72.48 184	90.55 19	96.93 11	76.24 11	99.08 11	91.53 29	94.99 17	96.43 30

DPE-MVS		88.77 17	89.21 16	87.45 43	96.26 20	67.56 101	94.17 60	94.15 59	68.77 264	90.74 17	97.27 2	76.09 12	98.49 29	90.58 37	94.91 20	96.30 33
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + GP.		87.96 22	88.37 22	86.70 63	93.51 61	65.32 157	95.15 36	93.84 65	78.17 93	85.93 54	94.80 73	75.80 13	98.21 34	89.38 42	88.78 104	96.59 19

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 132	93.00 74	58.16 306	96.72 8	94.41 48	86.50 8	90.25 23	97.83 1	75.46 14	98.67 25	92.78 18	95.49 12	97.32 6

dcpmvs_2		87.37 32	87.55 31	86.85 56	95.04 32	68.20 86	90.36 227	90.66 199	79.37 73	81.20 94	93.67 105	74.73 15	96.55 122	90.88 34	92.00 70	95.82 48

MVSTER		82.47 119	82.05 116	83.74 163	92.68 84	69.01 63	91.90 166	93.21 91	79.83 62	72.14 202	85.71 244	74.72 16	94.72 194	75.72 151	72.49 248	87.50 250

test_241102_TWO								94.41 48	71.65 214	92.07 8	97.21 4	74.58 17	99.11 6	92.34 21	95.36 13	96.59 19

test_one_0601					96.32 18	69.74 49		94.18 57	71.42 225	90.67 18	96.85 16	74.45 18

DELS-MVS		90.05 7	90.09 11	89.94 4	93.14 70	73.88 9	97.01 4	94.40 50	88.32 3	85.71 56	94.91 70	74.11 19	98.91 17	87.26 62	95.94 8	97.03 11
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
patch_mono-2		89.71 11	90.99 6	85.85 91	96.04 24	63.70 202	95.04 41	95.19 19	86.74 7	91.53 14	95.15 63	73.86 20	97.58 59	93.38 14	92.00 70	96.28 36

DVP-MVS		89.41 13	89.73 14	88.45 25	96.40 15	69.99 39	96.64 9	94.52 42	71.92 200	90.55 19	96.93 11	73.77 21	99.08 11	91.91 27	94.90 21	96.29 34
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					96.40 15	69.99 39	96.76 7	94.33 54	71.92 200	91.89 10	97.11 6	73.77 21

ET-MVSNet_ETH3D		84.01 92	83.15 101	86.58 68	90.78 134	70.89 30	94.74 50	94.62 40	81.44 38	58.19 330	93.64 106	73.64 23	92.35 283	82.66 100	78.66 200	96.50 27

CSCG		86.87 37	86.26 46	88.72 17	95.05 31	70.79 31	93.83 84	95.33 16	68.48 268	77.63 141	94.35 88	73.04 24	98.45 30	84.92 84	93.71 47	96.92 13

tttt0517		79.50 170	78.53 170	82.41 198	87.22 219	61.43 257	89.75 245	94.76 32	69.29 256	67.91 256	88.06 212	72.92 25	95.63 159	62.91 268	73.90 238	90.16 215

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 55	96.26 30	72.84 26	99.38 1	92.64 19	95.93 9	97.08 10

thisisatest0515		83.41 104	82.49 112	86.16 81	89.46 159	68.26 82	93.54 97	94.70 36	74.31 145	75.75 158	90.92 161	72.62 27	96.52 123	69.64 201	81.50 175	93.71 138

thisisatest0530		81.15 138	80.07 144	84.39 147	88.26 192	65.63 150	91.40 186	94.62 40	71.27 227	70.93 215	89.18 193	72.47 28	96.04 142	65.62 247	76.89 218	91.49 193

testing11		86.71 43	86.44 44	87.55 40	93.54 59	71.35 22	93.65 91	95.58 11	81.36 41	80.69 102	92.21 139	72.30 29	96.46 127	85.18 80	83.43 154	94.82 93

TSAR-MVS + MP.		88.11 21	88.64 18	86.54 70	91.73 110	68.04 89	90.36 227	93.55 79	82.89 20	91.29 15	92.89 121	72.27 30	96.03 143	87.99 53	94.77 25	95.54 56
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EPP-MVSNet		81.79 131	81.52 123	82.61 192	88.77 179	60.21 281	93.02 117	93.66 75	68.52 267	72.90 189	90.39 172	72.19 31	94.96 186	74.93 159	79.29 194	92.67 167

CostFormer		82.33 121	81.15 126	85.86 90	89.01 173	68.46 76	82.39 323	93.01 101	75.59 128	80.25 109	81.57 289	72.03 32	94.96 186	79.06 129	77.48 211	94.16 119

HPM-MVS++		89.37 14	89.95 13	87.64 34	95.10 30	68.23 85	95.24 33	94.49 44	82.43 25	88.90 34	96.35 27	71.89 33	98.63 26	88.76 49	96.40 6	96.06 40

testing99		86.01 53	85.47 61	87.63 38	93.62 55	71.25 24	93.47 103	95.23 18	80.42 54	80.60 104	91.95 143	71.73 34	96.50 125	80.02 121	82.22 166	95.13 77

CNVR-MVS		90.32 6	90.89 7	88.61 22	96.76 8	70.65 32	96.47 13	94.83 30	84.83 12	89.07 33	96.80 19	70.86 35	99.06 15	92.64 19	95.71 10	96.12 39

IB-MVS	77.80 4	82.18 123	80.46 142	87.35 45	89.14 170	70.28 37	95.59 26	95.17 21	78.85 84	70.19 225	85.82 242	70.66 36	97.67 51	72.19 182	66.52 288	94.09 123
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
testing91		85.93 55	85.31 64	87.78 32	93.59 57	71.47 19	93.50 100	95.08 25	80.26 56	80.53 105	91.93 144	70.43 37	96.51 124	80.32 119	82.13 168	95.37 61

ETVMVS		84.22 87	83.71 82	85.76 95	92.58 87	68.25 84	92.45 142	95.53 14	79.54 69	79.46 118	91.64 151	70.29 38	94.18 219	69.16 209	82.76 162	94.84 90

MM		90.87 2	91.52 2	88.92 15	92.12 96	71.10 28	97.02 3	96.04 6	88.70 2	91.57 13	96.19 33	70.12 39	98.91 17	96.83 1	95.06 16	96.76 15

fmvsm_l_conf0.5_n		87.49 29	88.19 24	85.39 106	86.95 225	64.37 182	94.30 57	88.45 290	80.51 51	92.70 4	96.86 15	69.98 40	97.15 88	95.83 3	88.08 112	94.65 100

baseline1		81.84 130	81.03 131	84.28 152	91.60 113	66.62 127	91.08 205	91.66 161	81.87 31	74.86 170	91.67 150	69.98 40	94.92 189	71.76 186	64.75 302	91.29 202

fmvsm_l_conf0.5_n_a		87.44 31	88.15 25	85.30 110	87.10 222	64.19 189	94.41 55	88.14 299	80.24 59	92.54 5	96.97 10	69.52 42	97.17 85	95.89 2	88.51 107	94.56 103

iter_conf05		83.65 103	83.44 90	84.28 152	86.17 240	68.61 74	95.08 39	89.82 233	80.90 47	78.08 136	90.49 169	69.08 43	95.22 179	84.29 89	77.07 216	89.02 230

iter_conf05_11		84.06 91	83.37 96	86.15 82	93.04 73	66.63 126	87.84 279	90.21 219	71.10 231	81.47 92	89.48 189	68.80 44	96.96 103	75.97 149	92.39 64	94.87 86

testing222		85.18 69	84.69 74	86.63 65	92.91 76	69.91 43	92.61 134	95.80 9	80.31 55	80.38 107	92.27 136	68.73 45	95.19 180	75.94 150	83.27 156	94.81 94

MVS_0304		90.01 8	90.50 9	88.53 23	90.14 144	70.94 29	96.47 13	95.72 10	87.33 4	89.60 30	96.26 30	68.44 46	98.74 24	95.82 4	94.72 31	95.90 46

alignmvs		87.28 33	86.97 38	88.24 27	91.30 123	71.14 27	95.61 25	93.56 78	79.30 74	87.07 44	95.25 58	68.43 47	96.93 108	87.87 54	84.33 147	96.65 17

MVSMamba_pp		88.94 16	88.82 17	89.29 13	94.04 45	74.01 8	94.81 48	92.74 111	85.13 10	90.37 21	90.13 181	68.40 48	97.38 70	89.42 40	94.34 36	96.47 28

mamv4		88.66 18	88.41 20	89.39 12	94.02 46	74.04 7	94.94 45	92.69 114	80.90 47	90.32 22	90.30 174	68.33 49	97.28 81	89.47 39	94.74 30	96.84 14

PAPM		85.89 57	85.46 62	87.18 48	88.20 196	72.42 15	92.41 143	92.77 109	82.11 29	80.34 108	93.07 116	68.27 50	95.02 183	78.39 136	93.59 49	94.09 123

train_agg		87.21 34	87.42 33	86.60 66	94.18 41	67.28 108	94.16 61	93.51 80	71.87 205	85.52 58	95.33 51	68.19 51	97.27 82	89.09 46	94.90 21	95.25 74

test_8					94.19 40	67.19 110	94.15 63	93.42 86	71.87 205	85.38 61	95.35 50	68.19 51	96.95 105

TEST9					94.18 41	67.28 108	94.16 61	93.51 80	71.75 211	85.52 58	95.33 51	68.01 53	97.27 82

test_prior2							95.10 38		75.40 132	85.25 64	95.61 45	67.94 54		87.47 59	94.77 25

WTY-MVS		86.32 47	85.81 56	87.85 29	92.82 79	69.37 56	95.20 34	95.25 17	82.71 22	81.91 88	94.73 74	67.93 55	97.63 56	79.55 124	82.25 165	96.54 22

APDe-MVS		87.54 28	87.84 27	86.65 64	96.07 23	66.30 135	94.84 47	93.78 66	69.35 255	88.39 35	96.34 28	67.74 56	97.66 54	90.62 36	93.44 51	96.01 43
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsm_n_1920		87.69 27	88.50 19	85.27 112	87.05 224	63.55 209	93.69 89	91.08 187	84.18 14	90.17 25	97.04 8	67.58 57	97.99 39	95.72 5	90.03 95	94.26 114

bld_raw_dy_0_64		76.92 216	74.65 225	83.71 167	84.96 264	71.37 21	73.29 369	89.16 260	50.14 371	62.32 310	84.19 258	67.48 58	95.61 161	72.10 183	88.25 108	84.14 309

tpm2		79.80 166	77.95 179	85.34 109	88.28 191	68.26 82	81.56 329	91.42 170	70.11 246	77.59 143	80.50 307	67.40 59	94.26 216	67.34 226	77.35 212	93.51 143

miper_enhance_ethall		78.86 182	77.97 178	81.54 222	88.00 201	65.17 161	91.41 184	89.15 262	75.19 135	68.79 244	83.98 261	67.17 60	92.82 262	72.73 174	65.30 293	86.62 271

SF-MVS		87.03 36	87.09 36	86.84 57	92.70 83	67.45 106	93.64 92	93.76 69	70.78 239	86.25 49	96.44 26	66.98 61	97.79 47	88.68 50	94.56 33	95.28 70

HY-MVS	76.49 5	84.28 83	83.36 97	87.02 54	92.22 93	67.74 96	84.65 303	94.50 43	79.15 78	82.23 86	87.93 213	66.88 62	96.94 106	80.53 117	82.20 167	96.39 32

EPNet		87.84 25	88.38 21	86.23 80	93.30 64	66.05 139	95.26 32	94.84 29	87.09 5	88.06 36	94.53 79	66.79 63	97.34 74	83.89 94	91.68 75	95.29 68
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
9.14			87.63 29		93.86 49		94.41 55	94.18 57	72.76 179	86.21 50	96.51 24	66.64 64	97.88 44	90.08 38	94.04 39

FIs		79.47 171	79.41 158	79.67 269	85.95 244	59.40 291	91.68 178	93.94 63	78.06 94	68.96 241	88.28 203	66.61 65	91.77 295	66.20 241	74.99 227	87.82 247

NCCC		89.07 15	89.46 15	87.91 28	96.60 10	69.05 62	96.38 15	94.64 39	84.42 13	86.74 47	96.20 32	66.56 66	98.76 23	89.03 48	94.56 33	95.92 45

SD-MVS		87.49 29	87.49 32	87.50 42	93.60 56	68.82 68	93.90 76	92.63 119	76.86 112	87.90 37	95.76 41	66.17 67	97.63 56	89.06 47	91.48 79	96.05 41
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
UniMVSNet_NR-MVSNet		78.15 197	77.55 184	79.98 260	84.46 272	60.26 279	92.25 146	93.20 93	77.50 106	68.88 242	86.61 231	66.10 68	92.13 287	66.38 238	62.55 318	87.54 249

CHOSEN 280x420		77.35 209	76.95 197	78.55 284	87.07 223	62.68 232	69.71 377	82.95 352	68.80 263	71.48 211	87.27 225	66.03 69	84.00 362	76.47 146	82.81 160	88.95 231

CANet		89.61 12	89.99 12	88.46 24	94.39 39	69.71 50	96.53 12	93.78 66	86.89 6	89.68 29	95.78 40	65.94 70	99.10 9	92.99 16	93.91 42	96.58 21

segment_acmp												65.94 70

Vis-MVSNet (Re-imp)		79.24 174	79.57 153	78.24 289	88.46 184	52.29 344	90.41 225	89.12 264	74.24 146	69.13 235	91.91 145	65.77 72	90.09 321	59.00 291	88.09 111	92.33 176

FC-MVSNet-test		77.99 199	78.08 176	77.70 292	84.89 265	55.51 330	90.27 230	93.75 72	76.87 111	66.80 274	87.59 218	65.71 73	90.23 318	62.89 269	73.94 236	87.37 254

SMA-MVS		88.14 19	88.29 23	87.67 33	93.21 67	68.72 70	93.85 79	94.03 62	74.18 147	91.74 11	96.67 21	65.61 74	98.42 33	89.24 45	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
test12				87.09 51	94.60 36	68.86 66		92.91 105		82.67 85		65.44 75	97.55 62		93.69 48	94.84 90

test_fmvsmconf_n		86.58 44	87.17 35	84.82 125	85.28 256	62.55 233	94.26 59	89.78 234	83.81 17	87.78 38	96.33 29	65.33 76	96.98 100	94.40 11	87.55 117	94.95 84

旧先验1					91.94 102	60.74 271		91.50 167			94.36 84	65.23 77			91.84 72	94.55 104

1112_ss		80.56 150	79.83 150	82.77 187	88.65 180	60.78 267	92.29 145	88.36 292	72.58 182	72.46 198	94.95 66	65.09 78	93.42 247	66.38 238	77.71 205	94.10 122

MVSFormer		83.75 99	82.88 105	86.37 76	89.24 168	71.18 25	89.07 259	90.69 196	65.80 286	87.13 42	94.34 89	64.99 79	92.67 270	72.83 171	91.80 73	95.27 71

lupinMVS		87.74 26	87.77 28	87.63 38	89.24 168	71.18 25	96.57 11	92.90 106	82.70 23	87.13 42	95.27 56	64.99 79	95.80 148	89.34 43	91.80 73	95.93 44

tpmrst		80.57 149	79.14 164	84.84 124	90.10 145	68.28 81	81.70 327	89.72 241	77.63 104	75.96 157	79.54 321	64.94 81	92.71 267	75.43 153	77.28 214	93.55 142

ZD-MVS					96.63 9	65.50 155		93.50 82	70.74 240	85.26 63	95.19 62	64.92 82	97.29 77	87.51 58	93.01 56

testing3		70.38 288	70.83 273	69.03 353	85.82 248	43.93 382	90.72 217	90.56 202	68.06 269	60.24 318	86.82 230	64.83 83	84.12 358	26.33 392	64.10 308	79.04 365

casdiffmvs_mvg		85.66 62	85.18 66	87.09 51	88.22 195	69.35 57	93.74 88	91.89 146	81.47 35	80.10 110	91.45 153	64.80 84	96.35 128	87.23 63	87.69 115	95.58 54
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
miper_ehance_all_eth		77.60 205	76.44 202	81.09 236	85.70 251	64.41 180	90.65 219	88.64 286	72.31 190	67.37 267	82.52 275	64.77 85	92.64 273	70.67 195	65.30 293	86.24 276

Test_1112_low_res		79.56 169	78.60 169	82.43 195	88.24 194	60.39 278	92.09 154	87.99 303	72.10 198	71.84 205	87.42 221	64.62 86	93.04 251	65.80 245	77.30 213	93.85 136

test2506		83.29 106	82.92 104	84.37 148	88.39 188	63.18 219	92.01 159	91.35 172	77.66 102	78.49 133	91.42 154	64.58 87	95.09 182	73.19 167	89.23 100	94.85 87

DeepC-MVS_fast	79.48 2	87.95 23	88.00 26	87.79 31	95.86 27	68.32 79	95.74 21	94.11 60	83.82 16	83.49 77	96.19 33	64.53 88	98.44 31	83.42 97	94.88 24	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
MG-MVS		87.11 35	86.27 45	89.62 7	97.79 1	76.27 4	94.96 44	94.49 44	78.74 88	83.87 76	92.94 119	64.34 89	96.94 106	75.19 155	94.09 38	95.66 51

casdiffmvs		85.37 66	84.87 72	86.84 57	88.25 193	69.07 61	93.04 115	91.76 153	81.27 42	80.84 101	92.07 141	64.23 90	96.06 141	84.98 83	87.43 119	95.39 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
cl22		77.94 201	76.78 198	81.42 224	87.57 210	64.93 169	90.67 218	88.86 277	72.45 186	67.63 262	82.68 274	64.07 91	92.91 260	71.79 184	65.30 293	86.44 272

tpm		78.58 190	77.03 194	83.22 180	85.94 246	64.56 171	83.21 317	91.14 183	78.31 91	73.67 182	79.68 319	64.01 92	92.09 289	66.07 242	71.26 258	93.03 158

CDS-MVSNet		81.43 135	80.74 134	83.52 171	86.26 237	64.45 176	92.09 154	90.65 200	75.83 126	73.95 181	89.81 186	63.97 93	92.91 260	71.27 189	82.82 159	93.20 152
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS_Test		84.16 89	83.20 98	87.05 53	91.56 115	69.82 46	89.99 241	92.05 137	77.77 99	82.84 81	86.57 232	63.93 94	96.09 137	74.91 160	89.18 102	95.25 74

APD-MVS		85.93 55	85.99 53	85.76 95	95.98 26	65.21 160	93.59 95	92.58 121	66.54 281	86.17 51	95.88 39	63.83 95	97.00 96	86.39 71	92.94 57	95.06 79
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mvs_anonymous		81.36 136	79.99 147	85.46 103	90.39 140	68.40 77	86.88 293	90.61 201	74.41 142	70.31 224	84.67 252	63.79 96	92.32 284	73.13 168	85.70 136	95.67 50

PVSNet_Blended_VisFu		83.97 93	83.50 86	85.39 106	90.02 146	66.59 129	93.77 86	91.73 154	77.43 108	77.08 150	89.81 186	63.77 97	96.97 102	79.67 123	88.21 110	92.60 169

baseline		85.01 72	84.44 76	86.71 62	88.33 190	68.73 69	90.24 232	91.82 152	81.05 45	81.18 95	92.50 128	63.69 98	96.08 140	84.45 88	86.71 129	95.32 66

myMVS_eth3d		72.58 276	72.74 254	72.10 342	87.87 204	49.45 359	88.07 273	89.01 270	72.91 175	63.11 301	88.10 209	63.63 99	85.54 352	32.73 384	69.23 268	81.32 344

CDPH-MVS		85.71 60	85.46 62	86.46 72	94.75 34	67.19 110	93.89 77	92.83 108	70.90 235	83.09 80	95.28 54	63.62 100	97.36 72	80.63 116	94.18 37	94.84 90

HyFIR lowres test		81.03 143	79.56 154	85.43 104	87.81 207	68.11 88	90.18 233	90.01 228	70.65 241	72.95 188	86.06 240	63.61 101	94.50 207	75.01 158	79.75 189	93.67 139

sasdasda		86.85 38	86.25 47	88.66 20	91.80 108	71.92 16	93.54 97	91.71 156	80.26 56	87.55 39	95.25 58	63.59 102	96.93 108	88.18 51	84.34 145	97.11 8

canonicalmvs		86.85 38	86.25 47	88.66 20	91.80 108	71.92 16	93.54 97	91.71 156	80.26 56	87.55 39	95.25 58	63.59 102	96.93 108	88.18 51	84.34 145	97.11 8

c3_l		76.83 221	75.47 216	80.93 240	85.02 262	64.18 190	90.39 226	88.11 300	71.66 213	66.65 275	81.64 287	63.58 104	92.56 274	69.31 207	62.86 315	86.04 282

SteuartSystems-ACMMP		86.82 41	86.90 40	86.58 68	90.42 138	66.38 132	96.09 17	93.87 64	77.73 100	84.01 75	95.66 43	63.39 105	97.94 40	87.40 60	93.55 50	95.42 57
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsmconf0.1_n		85.71 60	86.08 52	84.62 139	80.83 310	62.33 238	93.84 82	88.81 278	83.50 19	87.00 45	96.01 37	63.36 106	96.93 108	94.04 12	87.29 120	94.61 102

EI-MVSNet-Vis-set		83.77 98	83.67 83	84.06 157	92.79 82	63.56 208	91.76 174	94.81 31	79.65 67	77.87 138	94.09 96	63.35 107	97.90 42	79.35 125	79.36 192	90.74 208

UniMVSNet (Re)		77.58 206	76.78 198	79.98 260	84.11 278	60.80 266	91.76 174	93.17 95	76.56 120	69.93 231	84.78 251	63.32 108	92.36 282	64.89 254	62.51 320	86.78 266

PVSNet_BlendedMVS		83.38 105	83.43 91	83.22 180	93.76 51	67.53 103	94.06 65	93.61 76	79.13 79	81.00 99	85.14 247	63.19 109	97.29 77	87.08 65	73.91 237	84.83 304

PVSNet_Blended		86.73 42	86.86 41	86.31 79	93.76 51	67.53 103	96.33 16	93.61 76	82.34 27	81.00 99	93.08 115	63.19 109	97.29 77	87.08 65	91.38 81	94.13 121

UWE-MVS		80.81 147	81.01 132	80.20 253	89.33 162	57.05 319	91.91 165	94.71 35	75.67 127	75.01 169	89.37 191	63.13 111	91.44 306	67.19 229	82.80 161	92.12 187

PAPM_NR		82.97 112	81.84 120	86.37 76	94.10 44	66.76 123	87.66 282	92.84 107	69.96 248	74.07 179	93.57 108	63.10 112	97.50 64	70.66 196	90.58 91	94.85 87

nrg030		80.93 144	79.86 149	84.13 156	83.69 283	68.83 67	93.23 109	91.20 178	75.55 129	75.06 168	88.22 208	63.04 113	94.74 193	81.88 105	66.88 285	88.82 234

fmvsm_s_conf0.5_n		86.39 46	86.91 39	84.82 125	87.36 217	63.54 210	94.74 50	90.02 227	82.52 24	90.14 26	96.92 13	62.93 114	97.84 46	95.28 8	82.26 164	93.07 157

MGCFI-Net		85.59 64	85.73 59	85.17 116	91.41 121	62.44 234	92.87 121	91.31 173	79.65 67	86.99 46	95.14 64	62.90 115	96.12 135	87.13 64	84.13 152	96.96 12

EI-MVSNet-UG-set		83.14 109	82.96 102	83.67 169	92.28 91	63.19 218	91.38 190	94.68 37	79.22 76	76.60 153	93.75 102	62.64 116	97.76 48	78.07 138	78.01 203	90.05 217

DeepC-MVS	77.85 3	85.52 65	85.24 65	86.37 76	88.80 178	66.64 125	92.15 150	93.68 74	81.07 44	76.91 151	93.64 106	62.59 117	98.44 31	85.50 76	92.84 59	94.03 127
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EIA-MVS		84.84 74	84.88 71	84.69 134	91.30 123	62.36 237	93.85 79	92.04 138	79.45 70	79.33 121	94.28 92	62.42 118	96.35 128	80.05 120	91.25 84	95.38 60

fmvsm_s_conf0.5_n_a		85.75 59	86.09 51	84.72 132	85.73 250	63.58 207	93.79 85	89.32 252	81.42 39	90.21 24	96.91 14	62.41 119	97.67 51	94.48 10	80.56 183	92.90 163

CS-MVS		85.80 58	86.65 43	83.27 179	92.00 101	58.92 299	95.31 31	91.86 148	79.97 61	84.82 66	95.40 49	62.26 120	95.51 170	86.11 73	92.08 69	95.37 61

MVS_111021_HR		86.19 50	85.80 57	87.37 44	93.17 69	69.79 47	93.99 71	93.76 69	79.08 81	78.88 128	93.99 99	62.25 121	98.15 36	85.93 75	91.15 85	94.15 120

PHI-MVS		86.83 40	86.85 42	86.78 61	93.47 62	65.55 153	95.39 30	95.10 22	71.77 210	85.69 57	96.52 23	62.07 122	98.77 22	86.06 74	95.60 11	96.03 42

MP-MVS		85.02 71	84.97 70	85.17 116	92.60 86	64.27 187	93.24 108	92.27 128	73.13 169	79.63 116	94.43 82	61.90 123	97.17 85	85.00 82	92.56 61	94.06 126
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
jason		86.40 45	86.17 49	87.11 50	86.16 241	70.54 34	95.71 24	92.19 134	82.00 30	84.58 68	94.34 89	61.86 124	95.53 169	87.76 55	90.89 87	95.27 71
jason: jason.
fmvsm_s_conf0.1_n		85.61 63	85.93 54	84.68 135	82.95 294	63.48 212	94.03 70	89.46 246	81.69 33	89.86 27	96.74 20	61.85 125	97.75 49	94.74 9	82.01 170	92.81 165

CS-MVS-test		86.14 51	87.01 37	83.52 171	92.63 85	59.36 294	95.49 27	91.92 143	80.09 60	85.46 60	95.53 47	61.82 126	95.77 151	86.77 69	93.37 52	95.41 58

PAPR		85.15 70	84.47 75	87.18 48	96.02 25	68.29 80	91.85 169	93.00 103	76.59 119	79.03 124	95.00 65	61.59 127	97.61 58	78.16 137	89.00 103	95.63 52

IS-MVSNet		80.14 159	79.41 158	82.33 199	87.91 202	60.08 283	91.97 163	88.27 296	72.90 177	71.44 212	91.73 149	61.44 128	93.66 242	62.47 272	86.53 131	93.24 150

cl____		76.07 228	74.67 223	80.28 249	85.15 258	61.76 250	90.12 234	88.73 281	71.16 228	65.43 279	81.57 289	61.15 129	92.95 255	66.54 235	62.17 322	86.13 280

DIV-MVS_self_test		76.07 228	74.67 223	80.28 249	85.14 259	61.75 251	90.12 234	88.73 281	71.16 228	65.42 280	81.60 288	61.15 129	92.94 259	66.54 235	62.16 324	86.14 278

EI-MVSNet		78.97 179	78.22 174	81.25 227	85.33 254	62.73 231	89.53 249	93.21 91	72.39 189	72.14 202	90.13 181	60.99 131	94.72 194	67.73 223	72.49 248	86.29 274

IterMVS-LS		76.49 224	75.18 221	80.43 246	84.49 271	62.74 230	90.64 220	88.80 279	72.40 188	65.16 282	81.72 285	60.98 132	92.27 285	67.74 222	64.65 304	86.29 274
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.1_n_a		84.76 75	84.84 73	84.53 141	80.23 320	63.50 211	92.79 123	88.73 281	80.46 52	89.84 28	96.65 22	60.96 133	97.57 61	93.80 13	80.14 185	92.53 172

ETV-MVS		86.01 53	86.11 50	85.70 98	90.21 143	67.02 117	93.43 105	91.92 143	81.21 43	84.13 74	94.07 98	60.93 134	95.63 159	89.28 44	89.81 96	94.46 112

tpm cat1		75.30 244	72.21 262	84.58 140	88.52 181	67.77 95	78.16 355	88.02 302	61.88 321	68.45 250	76.37 344	60.65 135	94.03 230	53.77 310	74.11 234	91.93 189

TAMVS		80.37 154	79.45 157	83.13 182	85.14 259	63.37 213	91.23 199	90.76 195	74.81 140	72.65 192	88.49 199	60.63 136	92.95 255	69.41 205	81.95 171	93.08 156

ZNCC-MVS		85.33 67	85.08 68	86.06 83	93.09 72	65.65 149	93.89 77	93.41 87	73.75 158	79.94 112	94.68 76	60.61 137	98.03 38	82.63 101	93.72 46	94.52 108

thres100view900		78.37 193	77.01 195	82.46 194	91.89 106	63.21 217	91.19 203	96.33 1	72.28 192	70.45 221	87.89 214	60.31 138	95.32 174	45.16 344	77.58 208	88.83 232

thres600view7		78.00 198	76.66 200	82.03 214	91.93 103	63.69 203	91.30 196	96.33 1	72.43 187	70.46 220	87.89 214	60.31 138	94.92 189	42.64 356	76.64 219	87.48 251

CHOSEN 1792x2688		84.98 73	83.45 89	89.57 10	89.94 148	75.14 5	92.07 156	92.32 126	81.87 31	75.68 160	88.27 204	60.18 140	98.60 27	80.46 118	90.27 94	94.96 83

h-mvs33		83.01 111	82.56 111	84.35 149	89.34 160	62.02 244	92.72 126	93.76 69	81.45 36	82.73 83	92.25 138	60.11 141	97.13 89	87.69 56	62.96 314	93.91 132

hse-mvs2		81.12 141	81.11 130	81.16 230	86.52 232	57.48 314	89.40 252	91.16 180	81.45 36	82.73 83	90.49 169	60.11 141	94.58 199	87.69 56	60.41 341	91.41 196

tfpn200view9		78.79 185	77.43 186	82.88 185	92.21 94	64.49 173	92.05 157	96.28 4	73.48 164	71.75 207	88.26 205	60.07 143	95.32 174	45.16 344	77.58 208	88.83 232

thres400		78.68 187	77.43 186	82.43 195	92.21 94	64.49 173	92.05 157	96.28 4	73.48 164	71.75 207	88.26 205	60.07 143	95.32 174	45.16 344	77.58 208	87.48 251

diffmvs		84.28 83	83.83 81	85.61 100	87.40 215	68.02 90	90.88 211	89.24 255	80.54 50	81.64 90	92.52 127	59.83 145	94.52 206	87.32 61	85.11 139	94.29 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS		84.66 77	82.86 106	90.06 2	90.93 129	74.56 6	87.91 277	95.54 13	68.55 266	72.35 201	94.71 75	59.78 146	98.90 19	81.29 113	94.69 32	96.74 16

thres200		79.66 167	78.33 171	83.66 170	92.54 88	65.82 147	93.06 113	96.31 3	74.90 139	73.30 185	88.66 197	59.67 147	95.61 161	47.84 333	78.67 199	89.56 226

Effi-MVS+		83.82 96	82.76 107	86.99 55	89.56 156	69.40 53	91.35 193	86.12 323	72.59 181	83.22 79	92.81 125	59.60 148	96.01 145	81.76 106	87.80 114	95.56 55

eth_miper_zixun_eth		75.96 235	74.40 232	80.66 242	84.66 267	63.02 221	89.28 254	88.27 296	71.88 204	65.73 277	81.65 286	59.45 149	92.81 263	68.13 217	60.53 338	86.14 278

ACMMP_NAP		86.05 52	85.80 57	86.80 60	91.58 114	67.53 103	91.79 171	93.49 83	74.93 138	84.61 67	95.30 53	59.42 150	97.92 41	86.13 72	94.92 19	94.94 85

GST-MVS		84.63 78	84.29 78	85.66 99	92.82 79	65.27 158	93.04 115	93.13 97	73.20 167	78.89 125	94.18 95	59.41 151	97.85 45	81.45 109	92.48 63	93.86 135

UA-Net		80.02 162	79.65 152	81.11 232	89.33 162	57.72 310	86.33 296	89.00 273	77.44 107	81.01 98	89.15 194	59.33 152	95.90 146	61.01 279	84.28 149	89.73 223

NR-MVSNet		76.05 231	74.59 227	80.44 245	82.96 292	62.18 242	90.83 213	91.73 154	77.12 110	60.96 315	86.35 234	59.28 153	91.80 294	60.74 280	61.34 333	87.35 256

MP-MVS-pluss		85.24 68	85.13 67	85.56 101	91.42 119	65.59 151	91.54 181	92.51 123	74.56 141	80.62 103	95.64 44	59.15 154	97.00 96	86.94 67	93.80 43	94.07 125
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		84.73 76	84.40 77	85.72 97	93.75 53	65.01 166	93.50 100	93.19 94	72.19 194	79.22 122	94.93 68	59.04 155	97.67 51	81.55 107	92.21 65	94.49 111

MSLP-MVS++		86.27 48	85.91 55	87.35 45	92.01 100	68.97 65	95.04 41	92.70 112	79.04 83	81.50 91	96.50 25	58.98 156	96.78 114	83.49 96	93.93 41	96.29 34

Patchmatch-test		65.86 321	60.94 335	80.62 244	83.75 282	58.83 300	58.91 395	75.26 372	44.50 385	50.95 361	77.09 338	58.81 157	87.90 335	35.13 376	64.03 309	95.12 78

EPNet_dtu		78.80 184	79.26 162	77.43 297	88.06 198	49.71 357	91.96 164	91.95 142	77.67 101	76.56 154	91.28 158	58.51 158	90.20 319	56.37 299	80.95 179	92.39 174
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		60.86 342	60.24 336	62.71 366	81.57 304	46.43 374	75.70 365	85.88 325	57.98 342	48.95 368	69.53 370	58.42 159	76.53 384	28.25 391	35.87 390	65.15 389

test_fmvsmvis_n_1920		83.80 97	83.48 87	84.77 129	82.51 296	63.72 200	91.37 191	83.99 345	81.42 39	77.68 140	95.74 42	58.37 160	97.58 59	93.38 14	86.87 123	93.00 160

EC-MVSNet		84.53 79	85.04 69	83.01 183	89.34 160	61.37 258	94.42 54	91.09 185	77.91 97	83.24 78	94.20 94	58.37 160	95.40 171	85.35 77	91.41 80	92.27 182

VNet		86.20 49	85.65 60	87.84 30	93.92 48	69.99 39	95.73 23	95.94 7	78.43 90	86.00 53	93.07 116	58.22 162	97.00 96	85.22 78	84.33 147	96.52 23

TESTMET0.1,1		82.41 120	81.98 119	83.72 166	88.08 197	63.74 198	92.70 128	93.77 68	79.30 74	77.61 142	87.57 219	58.19 163	94.08 223	73.91 166	86.68 130	93.33 149

原ACMM1				84.42 145	93.21 67	64.27 187		93.40 88	65.39 289	79.51 117	92.50 128	58.11 164	96.69 116	65.27 252	93.96 40	92.32 177

sam_mvs1												57.85 165				94.68 97

CR-MVSNet		73.79 260	70.82 275	82.70 189	83.15 289	67.96 91	70.25 374	84.00 343	73.67 162	69.97 229	72.41 358	57.82 166	89.48 325	52.99 313	73.13 241	90.64 210

Patchmtry		67.53 313	63.93 320	78.34 285	82.12 300	64.38 181	68.72 378	84.00 343	48.23 377	59.24 323	72.41 358	57.82 166	89.27 326	46.10 341	56.68 353	81.36 343

patchmatchnet-post											67.62 374	57.62 168	90.25 314

PCF-MVS	73.15 9	79.29 173	77.63 183	84.29 151	86.06 242	65.96 143	87.03 289	91.10 184	69.86 250	69.79 232	90.64 164	57.54 169	96.59 118	64.37 257	82.29 163	90.32 213
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Fast-Effi-MVS+		81.14 139	80.01 146	84.51 143	90.24 142	65.86 145	94.12 64	89.15 262	73.81 157	75.37 166	88.26 205	57.26 170	94.53 205	66.97 232	84.92 140	93.15 153

miper_lstm_enhance		73.05 265	71.73 268	77.03 302	83.80 281	58.32 305	81.76 325	88.88 275	69.80 251	61.01 314	78.23 328	57.19 171	87.51 343	65.34 251	59.53 343	85.27 301

PatchT		69.11 298	65.37 310	80.32 247	82.07 301	63.68 204	67.96 383	87.62 307	50.86 368	69.37 233	65.18 377	57.09 172	88.53 331	41.59 359	66.60 287	88.74 235

testdata				81.34 226	89.02 172	57.72 310		89.84 232	58.65 340	85.32 62	94.09 96	57.03 173	93.28 248	69.34 206	90.56 92	93.03 158

PatchmatchNet		77.46 207	74.63 226	85.96 86	89.55 157	70.35 36	79.97 346	89.55 244	72.23 193	70.94 214	76.91 340	57.03 173	92.79 265	54.27 307	81.17 177	94.74 95
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_yl		84.28 83	83.16 99	87.64 34	94.52 37	69.24 58	95.78 18	95.09 23	69.19 258	81.09 96	92.88 122	57.00 175	97.44 66	81.11 114	81.76 172	96.23 37

DCV-MVSNet		84.28 83	83.16 99	87.64 34	94.52 37	69.24 58	95.78 18	95.09 23	69.19 258	81.09 96	92.88 122	57.00 175	97.44 66	81.11 114	81.76 172	96.23 37

region2R		84.36 81	84.03 80	85.36 108	93.54 59	64.31 185	93.43 105	92.95 104	72.16 197	78.86 129	94.84 72	56.97 177	97.53 63	81.38 111	92.11 68	94.24 115

新几何1				84.73 131	92.32 90	64.28 186		91.46 169	59.56 336	79.77 114	92.90 120	56.95 178	96.57 120	63.40 262	92.91 58	93.34 147

WR-MVS		76.76 222	75.74 213	79.82 266	84.60 268	62.27 241	92.60 135	92.51 123	76.06 123	67.87 259	85.34 245	56.76 179	90.24 317	62.20 273	63.69 313	86.94 264

HPM-MVS		83.25 107	82.95 103	84.17 155	92.25 92	62.88 228	90.91 208	91.86 148	70.30 244	77.12 148	93.96 100	56.75 180	96.28 130	82.04 104	91.34 83	93.34 147
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		82.71 117	82.38 114	83.73 165	89.25 165	59.58 289	92.24 147	94.89 28	77.96 95	79.86 113	92.38 133	56.70 181	97.05 91	77.26 142	80.86 180	94.55 104

ACMMPR		84.37 80	84.06 79	85.28 111	93.56 58	64.37 182	93.50 100	93.15 96	72.19 194	78.85 130	94.86 71	56.69 182	97.45 65	81.55 107	92.20 66	94.02 128

FMVSNet3		77.73 204	76.04 208	82.80 186	91.20 126	68.99 64	91.87 167	91.99 140	73.35 166	67.04 269	83.19 269	56.62 183	92.14 286	59.80 287	69.34 265	87.28 258

Patchmatch-RL test		68.17 307	64.49 317	79.19 277	71.22 374	53.93 338	70.07 376	71.54 382	69.22 257	56.79 339	62.89 382	56.58 184	88.61 328	69.53 204	52.61 363	95.03 82

dongtai		55.18 353	55.46 352	54.34 376	76.03 361	36.88 394	76.07 362	84.61 337	51.28 365	43.41 385	64.61 380	56.56 185	67.81 395	18.09 399	28.50 400	58.32 392

test_post											23.01 405	56.49 186	92.67 270

RPMNet		70.42 287	65.68 306	84.63 138	83.15 289	67.96 91	70.25 374	90.45 203	46.83 380	69.97 229	65.10 378	56.48 187	95.30 177	35.79 375	73.13 241	90.64 210

DU-MVS		76.86 217	75.84 211	79.91 263	82.96 292	60.26 279	91.26 197	91.54 164	76.46 121	68.88 242	86.35 234	56.16 188	92.13 287	66.38 238	62.55 318	87.35 256

Baseline_NR-MVSNet		73.99 257	72.83 252	77.48 296	80.78 311	59.29 295	91.79 171	84.55 338	68.85 262	68.99 240	80.70 303	56.16 188	92.04 290	62.67 270	60.98 335	81.11 346

API-MVS		82.28 122	80.53 140	87.54 41	96.13 22	70.59 33	93.63 93	91.04 191	65.72 288	75.45 165	92.83 124	56.11 190	98.89 20	64.10 258	89.75 99	93.15 153

MTAPA		83.91 94	83.38 95	85.50 102	91.89 106	65.16 162	81.75 326	92.23 129	75.32 133	80.53 105	95.21 61	56.06 191	97.16 87	84.86 85	92.55 62	94.18 117

JIA-IIPM		66.06 320	62.45 329	76.88 306	81.42 307	54.45 337	57.49 396	88.67 284	49.36 373	63.86 294	46.86 394	56.06 191	90.25 314	49.53 323	68.83 271	85.95 285

v148		76.19 226	74.47 231	81.36 225	80.05 322	64.44 177	91.75 176	90.23 217	73.68 161	67.13 268	80.84 302	55.92 193	93.86 239	68.95 212	61.73 329	85.76 291

WR-MVS_H		70.59 285	69.94 282	72.53 336	81.03 308	51.43 348	87.35 286	92.03 139	67.38 275	60.23 319	80.70 303	55.84 194	83.45 366	46.33 340	58.58 348	82.72 330

test_fmvsmconf0.01_n		83.70 101	83.52 84	84.25 154	75.26 362	61.72 252	92.17 149	87.24 312	82.36 26	84.91 65	95.41 48	55.60 195	96.83 113	92.85 17	85.87 135	94.21 116

AUN-MVS		78.37 193	77.43 186	81.17 229	86.60 231	57.45 315	89.46 251	91.16 180	74.11 148	74.40 174	90.49 169	55.52 196	94.57 201	74.73 163	60.43 340	91.48 194

XVS		83.87 95	83.47 88	85.05 118	93.22 65	63.78 196	92.92 119	92.66 116	73.99 150	78.18 134	94.31 91	55.25 197	97.41 68	79.16 127	91.58 77	93.95 130

X-MVStestdata		76.86 217	74.13 237	85.05 118	93.22 65	63.78 196	92.92 119	92.66 116	73.99 150	78.18 134	10.19 410	55.25 197	97.41 68	79.16 127	91.58 77	93.95 130

BH-w/o		80.49 152	79.30 161	84.05 158	90.83 133	64.36 184	93.60 94	89.42 249	74.35 144	69.09 236	90.15 180	55.23 199	95.61 161	64.61 255	86.43 133	92.17 185

CP-MVS		83.71 100	83.40 94	84.65 136	93.14 70	63.84 194	94.59 52	92.28 127	71.03 233	77.41 144	94.92 69	55.21 200	96.19 132	81.32 112	90.70 89	93.91 132

PGM-MVS		83.25 107	82.70 109	84.92 121	92.81 81	64.07 191	90.44 223	92.20 133	71.28 226	77.23 147	94.43 82	55.17 201	97.31 76	79.33 126	91.38 81	93.37 146

tpmvs		72.88 269	69.76 285	82.22 204	90.98 128	67.05 115	78.22 354	88.30 294	63.10 309	64.35 292	74.98 351	55.09 202	94.27 214	43.25 350	69.57 264	85.34 299

v8		75.35 243	73.26 248	81.61 220	80.67 313	66.82 120	89.54 248	89.27 254	71.65 214	63.30 300	80.30 311	54.99 203	94.06 225	67.33 227	62.33 321	83.94 311

sam_mvs												54.91 204

EPMVS		78.49 192	75.98 209	86.02 84	91.21 125	69.68 51	80.23 341	91.20 178	75.25 134	72.48 197	78.11 329	54.65 205	93.69 241	57.66 296	83.04 157	94.69 96

ab-mvs		80.18 158	78.31 172	85.80 93	88.44 185	65.49 156	83.00 320	92.67 115	71.82 208	77.36 145	85.01 248	54.50 206	96.59 118	76.35 147	75.63 225	95.32 66

KD-MVS_2432*1600		69.03 299	66.37 302	77.01 303	85.56 252	61.06 262	81.44 330	90.25 215	67.27 276	58.00 333	76.53 342	54.49 207	87.63 341	48.04 330	35.77 391	82.34 336

miper_refine_blended		69.03 299	66.37 302	77.01 303	85.56 252	61.06 262	81.44 330	90.25 215	67.27 276	58.00 333	76.53 342	54.49 207	87.63 341	48.04 330	35.77 391	82.34 336

DP-MVS Recon		82.73 115	81.65 122	85.98 85	97.31 4	67.06 114	95.15 36	91.99 140	69.08 261	76.50 155	93.89 101	54.48 209	98.20 35	70.76 194	85.66 137	92.69 166

GeoE		78.90 181	77.43 186	83.29 178	88.95 174	62.02 244	92.31 144	86.23 321	70.24 245	71.34 213	89.27 192	54.43 210	94.04 228	63.31 264	80.81 182	93.81 137

XXY-MVS		77.94 201	76.44 202	82.43 195	82.60 295	64.44 177	92.01 159	91.83 151	73.59 163	70.00 228	85.82 242	54.43 210	94.76 191	69.63 202	68.02 278	88.10 246

MDTV_nov1_ep13_2view						59.90 285	80.13 343		67.65 273	72.79 190		54.33 212		59.83 286		92.58 170

Test By Simon												54.21 213

MAR-MVS		84.18 88	83.43 91	86.44 73	96.25 21	65.93 144	94.28 58	94.27 56	74.41 142	79.16 123	95.61 45	53.99 214	98.88 21	69.62 203	93.26 54	94.50 110
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
test-LLR		80.10 160	79.56 154	81.72 218	86.93 228	61.17 259	92.70 128	91.54 164	71.51 223	75.62 161	86.94 228	53.83 215	92.38 280	72.21 180	84.76 143	91.60 191

test0.0.03 1		72.76 270	72.71 256	72.88 334	80.25 319	47.99 365	91.22 200	89.45 247	71.51 223	62.51 309	87.66 217	53.83 215	85.06 356	50.16 320	67.84 281	85.58 292

v2v482		77.42 208	75.65 215	82.73 188	80.38 316	67.13 113	91.85 169	90.23 217	75.09 136	69.37 233	83.39 267	53.79 217	94.44 208	71.77 185	65.00 299	86.63 270

SR-MVS		82.81 114	82.58 110	83.50 174	93.35 63	61.16 261	92.23 148	91.28 177	64.48 295	81.27 93	95.28 54	53.71 218	95.86 147	82.87 99	88.77 105	93.49 144

pcd_1.5k_mvsjas		4.46 382	5.95 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	53.55 219	0.00 415	0.00 414	0.00 412	0.00 411

PS-MVSNAJss		77.26 210	76.31 204	80.13 255	80.64 314	59.16 296	90.63 222	91.06 189	72.80 178	68.58 248	84.57 254	53.55 219	93.96 233	72.97 169	71.96 252	87.27 259

PS-MVSNAJ		88.14 19	87.61 30	89.71 6	92.06 97	76.72 1	95.75 20	93.26 90	83.86 15	89.55 31	96.06 36	53.55 219	97.89 43	91.10 31	93.31 53	94.54 106

mPP-MVS		82.96 113	82.44 113	84.52 142	92.83 77	62.92 226	92.76 124	91.85 150	71.52 222	75.61 163	94.24 93	53.48 222	96.99 99	78.97 130	90.73 88	93.64 141

xiu_mvs_v2_base		87.92 24	87.38 34	89.55 11	91.41 121	76.43 3	95.74 21	93.12 98	83.53 18	89.55 31	95.95 38	53.45 223	97.68 50	91.07 32	92.62 60	94.54 106

test_post1							78.95 348				20.70 408	53.05 224	91.50 305	60.43 282

MDTV_nov1_ep13			72.61 257		89.06 171	68.48 75	80.33 339	90.11 222	71.84 207	71.81 206	75.92 348	53.01 225	93.92 235	48.04 330	73.38 239

FA-MVS(test-final)		79.12 176	77.23 192	84.81 128	90.54 136	63.98 193	81.35 332	91.71 156	71.09 232	74.85 171	82.94 270	52.85 226	97.05 91	67.97 219	81.73 174	93.41 145

test222					89.77 151	61.60 254	89.55 247	89.42 249	56.83 350	77.28 146	92.43 132	52.76 227			91.14 86	93.09 155

v1144		76.73 223	74.88 222	82.27 201	80.23 320	66.60 128	91.68 178	90.21 219	73.69 160	69.06 238	81.89 282	52.73 228	94.40 209	69.21 208	65.23 296	85.80 288

v10		74.77 250	72.54 259	81.46 223	80.33 318	66.71 124	89.15 258	89.08 267	70.94 234	63.08 303	79.86 316	52.52 229	94.04 228	65.70 246	62.17 322	83.64 314

CLD-MVS		82.73 115	82.35 115	83.86 161	87.90 203	67.65 99	95.45 28	92.18 135	85.06 11	72.58 194	92.27 136	52.46 230	95.78 149	84.18 90	79.06 195	88.16 245
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TranMVSNet+NR-MVSNet		75.86 236	74.52 230	79.89 264	82.44 297	60.64 275	91.37 191	91.37 171	76.63 118	67.65 261	86.21 238	52.37 231	91.55 300	61.84 275	60.81 336	87.48 251

VPA-MVSNet		79.03 177	78.00 177	82.11 212	85.95 244	64.48 175	93.22 110	94.66 38	75.05 137	74.04 180	84.95 249	52.17 232	93.52 244	74.90 161	67.04 284	88.32 244

APD-MVS_3200maxsize		81.64 133	81.32 125	82.59 193	92.36 89	58.74 301	91.39 188	91.01 192	63.35 304	79.72 115	94.62 78	51.82 233	96.14 134	79.71 122	87.93 113	92.89 164

dp		75.01 248	72.09 263	83.76 162	89.28 164	66.22 138	79.96 347	89.75 236	71.16 228	67.80 260	77.19 337	51.81 234	92.54 275	50.39 318	71.44 257	92.51 173

v144192		76.05 231	74.03 238	82.12 209	79.50 328	66.55 130	91.39 188	89.71 242	72.30 191	68.17 251	81.33 294	51.75 235	94.03 230	67.94 220	64.19 306	85.77 289

BH-untuned		78.68 187	77.08 193	83.48 175	89.84 149	63.74 198	92.70 128	88.59 287	71.57 220	66.83 273	88.65 198	51.75 235	95.39 172	59.03 290	84.77 142	91.32 200

HQP2-MVS												51.63 237

HQP-MVS		81.14 139	80.64 137	82.64 191	87.54 211	63.66 205	94.06 65	91.70 159	79.80 63	74.18 175	90.30 174	51.63 237	95.61 161	77.63 140	78.90 196	88.63 236

dmvs_testset		65.55 324	66.45 300	62.86 365	79.87 323	22.35 410	76.55 359	71.74 380	77.42 109	55.85 341	87.77 216	51.39 239	80.69 380	31.51 390	65.92 291	85.55 294

V42		76.46 225	74.55 229	82.19 206	79.14 334	67.82 94	90.26 231	89.42 249	73.75 158	68.63 247	81.89 282	51.31 240	94.09 222	71.69 187	64.84 300	84.66 305

SR-MVS-dyc-post		81.06 142	80.70 135	82.15 207	92.02 98	58.56 303	90.90 209	90.45 203	62.76 311	78.89 125	94.46 80	51.26 241	95.61 161	78.77 133	86.77 127	92.28 179

CL-MVSNet_self_test		69.92 291	68.09 295	75.41 314	73.25 369	55.90 328	90.05 237	89.90 230	69.96 248	61.96 313	76.54 341	51.05 242	87.64 340	49.51 324	50.59 368	82.70 332

TransMVSNet (Re)		70.07 290	67.66 296	77.31 300	80.62 315	59.13 298	91.78 173	84.94 334	65.97 285	60.08 320	80.44 308	50.78 243	91.87 292	48.84 326	45.46 376	80.94 348

HQP_MVS		80.34 155	79.75 151	82.12 209	86.94 226	62.42 235	93.13 111	91.31 173	78.81 86	72.53 195	89.14 195	50.66 244	95.55 167	76.74 143	78.53 201	88.39 242

plane_prior6					87.23 218	62.32 239						50.66 244

ACMMP		81.49 134	80.67 136	83.93 160	91.71 111	62.90 227	92.13 151	92.22 132	71.79 209	71.68 209	93.49 110	50.32 246	96.96 103	78.47 135	84.22 151	91.93 189
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
MVS_111021_LR		82.02 128	81.52 123	83.51 173	88.42 186	62.88 228	89.77 244	88.93 274	76.78 115	75.55 164	93.10 113	50.31 247	95.38 173	83.82 95	87.02 122	92.26 183

1314		80.70 148	78.95 165	85.94 87	87.77 209	67.56 101	87.91 277	92.55 122	72.17 196	67.44 263	93.09 114	50.27 248	97.04 94	71.68 188	87.64 116	93.23 151

CP-MVSNet		70.50 286	69.91 283	72.26 339	80.71 312	51.00 351	87.23 288	90.30 213	67.84 270	59.64 321	82.69 273	50.23 249	82.30 374	51.28 315	59.28 344	83.46 319

LCM-MVSNet-Re		72.93 267	71.84 266	76.18 311	88.49 182	48.02 364	80.07 344	70.17 383	73.96 153	52.25 354	80.09 315	49.98 250	88.24 333	67.35 225	84.23 150	92.28 179

Vis-MVSNet		80.92 145	79.98 148	83.74 163	88.48 183	61.80 248	93.44 104	88.26 298	73.96 153	77.73 139	91.76 147	49.94 251	94.76 191	65.84 244	90.37 93	94.65 100
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v1192		75.98 233	73.92 240	82.15 207	79.73 324	66.24 137	91.22 200	89.75 236	72.67 180	68.49 249	81.42 292	49.86 252	94.27 214	67.08 230	65.02 298	85.95 285

test-mter		79.96 163	79.38 160	81.72 218	86.93 228	61.17 259	92.70 128	91.54 164	73.85 155	75.62 161	86.94 228	49.84 253	92.38 280	72.21 180	84.76 143	91.60 191

cdsmvs_eth3d_5k		19.86 377	26.47 376	0.00 396	0.00 419	0.00 421	0.00 407	93.45 84	0.00 414	0.00 415	95.27 56	49.56 254	0.00 415	0.00 414	0.00 412	0.00 411

3Dnovator+	73.60 7	82.10 127	80.60 139	86.60 66	90.89 131	66.80 122	95.20 34	93.44 85	74.05 149	67.42 264	92.49 130	49.46 255	97.65 55	70.80 193	91.68 75	95.33 64

MVP-Stereo		77.12 213	76.23 205	79.79 267	81.72 303	66.34 134	89.29 253	90.88 193	70.56 242	62.01 312	82.88 271	49.34 256	94.13 220	65.55 249	93.80 43	78.88 366
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
RE-MVS-def			80.48 141		92.02 98	58.56 303	90.90 209	90.45 203	62.76 311	78.89 125	94.46 80	49.30 257		78.77 133	86.77 127	92.28 179

OMC-MVS		78.67 189	77.91 180	80.95 239	85.76 249	57.40 316	88.49 268	88.67 284	73.85 155	72.43 199	92.10 140	49.29 258	94.55 204	72.73 174	77.89 204	90.91 207

VPNet		78.82 183	77.53 185	82.70 189	84.52 270	66.44 131	93.93 74	92.23 129	80.46 52	72.60 193	88.38 202	49.18 259	93.13 250	72.47 178	63.97 311	88.55 239

CVMVSNet		74.04 256	74.27 234	73.33 330	85.33 254	43.94 381	89.53 249	88.39 291	54.33 358	70.37 222	90.13 181	49.17 260	84.05 360	61.83 276	79.36 192	91.99 188

v1921920		75.63 241	73.49 246	82.06 213	79.38 329	66.35 133	91.07 207	89.48 245	71.98 199	67.99 252	81.22 297	49.16 261	93.90 236	66.56 234	64.56 305	85.92 287

pm-mvs1		72.89 268	71.09 272	78.26 288	79.10 335	57.62 312	90.80 214	89.30 253	67.66 272	62.91 305	81.78 284	49.11 262	92.95 255	60.29 284	58.89 346	84.22 308

pmmvs4		73.92 258	71.81 267	80.25 251	79.17 332	65.24 159	87.43 285	87.26 311	67.64 274	63.46 298	83.91 262	48.96 263	91.53 304	62.94 267	65.49 292	83.96 310

TAPA-MVS	70.22 12	74.94 249	73.53 245	79.17 278	90.40 139	52.07 345	89.19 257	89.61 243	62.69 313	70.07 226	92.67 126	48.89 264	94.32 210	38.26 370	79.97 186	91.12 205
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
3Dnovator	73.91 6	82.69 118	80.82 133	88.31 26	89.57 155	71.26 23	92.60 135	94.39 51	78.84 85	67.89 258	92.48 131	48.42 265	98.52 28	68.80 214	94.40 35	95.15 76

CPTT-MVS		79.59 168	79.16 163	80.89 241	91.54 117	59.80 286	92.10 153	88.54 289	60.42 329	72.96 187	93.28 112	48.27 266	92.80 264	78.89 132	86.50 132	90.06 216

GBi-Net		75.65 239	73.83 241	81.10 233	88.85 175	65.11 163	90.01 238	90.32 209	70.84 236	67.04 269	80.25 312	48.03 267	91.54 301	59.80 287	69.34 265	86.64 267

test1		75.65 239	73.83 241	81.10 233	88.85 175	65.11 163	90.01 238	90.32 209	70.84 236	67.04 269	80.25 312	48.03 267	91.54 301	59.80 287	69.34 265	86.64 267

FMVSNet2		76.07 228	74.01 239	82.26 203	88.85 175	67.66 98	91.33 194	91.61 162	70.84 236	65.98 276	82.25 278	48.03 267	92.00 291	58.46 292	68.73 273	87.10 261

LFMVS		84.34 82	82.73 108	89.18 14	94.76 33	73.25 11	94.99 43	91.89 146	71.90 202	82.16 87	93.49 110	47.98 270	97.05 91	82.55 102	84.82 141	97.25 7

SDMVSNet		80.26 156	78.88 166	84.40 146	89.25 165	67.63 100	85.35 299	93.02 100	76.77 116	70.84 216	87.12 226	47.95 271	96.09 137	85.04 81	74.55 228	89.48 227

QAPM		79.95 164	77.39 190	87.64 34	89.63 154	71.41 20	93.30 107	93.70 73	65.34 291	67.39 266	91.75 148	47.83 272	98.96 16	57.71 295	89.81 96	92.54 171

HPM-MVS_fast		80.25 157	79.55 156	82.33 199	91.55 116	59.95 284	91.32 195	89.16 260	65.23 292	74.71 172	93.07 116	47.81 273	95.74 152	74.87 162	88.23 109	91.31 201

CANet_DTU		84.09 90	83.52 84	85.81 92	90.30 141	66.82 120	91.87 167	89.01 270	85.27 9	86.09 52	93.74 103	47.71 274	96.98 100	77.90 139	89.78 98	93.65 140

v1240		75.21 246	72.98 251	81.88 215	79.20 331	66.00 141	90.75 216	89.11 265	71.63 218	67.41 265	81.22 297	47.36 275	93.87 237	65.46 250	64.72 303	85.77 289

PEN-MVS		69.46 296	68.56 290	72.17 341	79.27 330	49.71 357	86.90 292	89.24 255	67.24 279	59.08 326	82.51 276	47.23 276	83.54 365	48.42 328	57.12 349	83.25 322

dmvs_re		76.93 215	75.36 218	81.61 220	87.78 208	60.71 272	80.00 345	87.99 303	79.42 71	69.02 239	89.47 190	46.77 277	94.32 210	63.38 263	74.45 231	89.81 220

CNLPA		74.31 253	72.30 261	80.32 247	91.49 118	61.66 253	90.85 212	80.72 358	56.67 351	63.85 295	90.64 164	46.75 278	90.84 309	53.79 309	75.99 224	88.47 241

114514_t		79.17 175	77.67 181	83.68 168	95.32 29	65.53 154	92.85 122	91.60 163	63.49 302	67.92 255	90.63 166	46.65 279	95.72 157	67.01 231	83.54 153	89.79 221

PS-CasMVS		69.86 293	69.13 288	72.07 343	80.35 317	50.57 353	87.02 290	89.75 236	67.27 276	59.19 325	82.28 277	46.58 280	82.24 375	50.69 317	59.02 345	83.39 321

DTE-MVSNet		68.46 305	67.33 298	71.87 345	77.94 350	49.00 362	86.16 297	88.58 288	66.36 283	58.19 330	82.21 279	46.36 281	83.87 363	44.97 347	55.17 356	82.73 329

test1111		80.84 146	80.02 145	83.33 177	87.87 204	60.76 269	92.62 133	86.86 315	77.86 98	75.73 159	91.39 156	46.35 282	94.70 197	72.79 173	88.68 106	94.52 108

ECVR-MVS		81.29 137	80.38 143	84.01 159	88.39 188	61.96 246	92.56 140	86.79 316	77.66 102	76.63 152	91.42 154	46.34 283	95.24 178	74.36 164	89.23 100	94.85 87

PMMVS		81.98 129	82.04 117	81.78 216	89.76 152	56.17 325	91.13 204	90.69 196	77.96 95	80.09 111	93.57 108	46.33 284	94.99 185	81.41 110	87.46 118	94.17 118

OPM-MVS		79.00 178	78.09 175	81.73 217	83.52 286	63.83 195	91.64 180	90.30 213	76.36 122	71.97 204	89.93 185	46.30 285	95.17 181	75.10 156	77.70 206	86.19 277
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BH-RMVSNet		79.46 172	77.65 182	84.89 122	91.68 112	65.66 148	93.55 96	88.09 301	72.93 174	73.37 184	91.12 160	46.20 286	96.12 135	56.28 300	85.61 138	92.91 162

mvsmamba		76.85 219	75.71 214	80.25 251	83.07 291	59.16 296	91.44 182	80.64 359	76.84 113	67.95 254	86.33 236	46.17 287	94.24 217	76.06 148	72.92 244	87.36 255

FE-MVS		75.97 234	73.02 250	84.82 125	89.78 150	65.56 152	77.44 357	91.07 188	64.55 294	72.66 191	79.85 317	46.05 288	96.69 116	54.97 304	80.82 181	92.21 184

TR-MVS		78.77 186	77.37 191	82.95 184	90.49 137	60.88 265	93.67 90	90.07 223	70.08 247	74.51 173	91.37 157	45.69 289	95.70 158	60.12 285	80.32 184	92.29 178

IterMVS-SCA-FT		71.55 281	69.97 281	76.32 309	81.48 305	60.67 274	87.64 283	85.99 324	66.17 284	59.50 322	78.88 323	45.53 290	83.65 364	62.58 271	61.93 325	84.63 307

SCA		75.82 237	72.76 253	85.01 120	86.63 230	70.08 38	81.06 334	89.19 258	71.60 219	70.01 227	77.09 338	45.53 290	90.25 314	60.43 282	73.27 240	94.68 97

IterMVS		72.65 275	70.83 273	78.09 290	82.17 299	62.96 223	87.64 283	86.28 319	71.56 221	60.44 317	78.85 324	45.42 292	86.66 347	63.30 265	61.83 326	84.65 306
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Syy-MVS		69.65 294	69.52 286	70.03 349	87.87 204	43.21 383	88.07 273	89.01 270	72.91 175	63.11 301	88.10 209	45.28 293	85.54 352	22.07 396	69.23 268	81.32 344

WB-MVSnew		77.14 212	76.18 207	80.01 259	86.18 239	63.24 216	91.26 197	94.11 60	71.72 212	73.52 183	87.29 224	45.14 294	93.00 253	56.98 297	79.42 190	83.80 313

Effi-MVS+-dtu		76.14 227	75.28 220	78.72 283	83.22 288	55.17 332	89.87 242	87.78 306	75.42 131	67.98 253	81.43 291	45.08 295	92.52 276	75.08 157	71.63 253	88.48 240

XVG-OURS-SEG-HR		74.70 251	73.08 249	79.57 272	78.25 346	57.33 317	80.49 337	87.32 309	63.22 306	68.76 245	90.12 184	44.89 296	91.59 299	70.55 197	74.09 235	89.79 221

v7n		71.31 282	68.65 289	79.28 276	76.40 357	60.77 268	86.71 294	89.45 247	64.17 297	58.77 329	78.24 327	44.59 297	93.54 243	57.76 294	61.75 328	83.52 317

pmmvs5		73.35 262	71.52 269	78.86 282	78.64 342	60.61 276	91.08 205	86.90 313	67.69 271	63.32 299	83.64 263	44.33 298	90.53 311	62.04 274	66.02 290	85.46 296

OpenMVS	70.45 11	78.54 191	75.92 210	86.41 75	85.93 247	71.68 18	92.74 125	92.51 123	66.49 282	64.56 287	91.96 142	43.88 299	98.10 37	54.61 305	90.65 90	89.44 229

AdaColmap		78.94 180	77.00 196	84.76 130	96.34 17	65.86 145	92.66 132	87.97 305	62.18 316	70.56 218	92.37 134	43.53 300	97.35 73	64.50 256	82.86 158	91.05 206

tfpnnormal		70.10 289	67.36 297	78.32 286	83.45 287	60.97 264	88.85 262	92.77 109	64.85 293	60.83 316	78.53 325	43.52 301	93.48 245	31.73 387	61.70 330	80.52 353

mvsany_test1		68.77 301	68.56 290	69.39 351	73.57 368	45.88 377	80.93 335	60.88 396	59.65 335	71.56 210	90.26 177	43.22 302	75.05 385	74.26 165	62.70 317	87.25 260

test_djsdf		73.76 261	72.56 258	77.39 298	77.00 355	53.93 338	89.07 259	90.69 196	65.80 286	63.92 293	82.03 281	43.14 303	92.67 270	72.83 171	68.53 274	85.57 293

GA-MVS		78.33 195	76.23 205	84.65 136	83.65 284	66.30 135	91.44 182	90.14 221	76.01 124	70.32 223	84.02 260	42.50 304	94.72 194	70.98 191	77.00 217	92.94 161

PLC	68.80 14	75.23 245	73.68 244	79.86 265	92.93 75	58.68 302	90.64 220	88.30 294	60.90 326	64.43 291	90.53 167	42.38 305	94.57 201	56.52 298	76.54 220	86.33 273
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
D2MVS		73.80 259	72.02 264	79.15 280	79.15 333	62.97 222	88.58 267	90.07 223	72.94 173	59.22 324	78.30 326	42.31 306	92.70 269	65.59 248	72.00 251	81.79 341

Fast-Effi-MVS+-dtu		75.04 247	73.37 247	80.07 256	80.86 309	59.52 290	91.20 202	85.38 329	71.90 202	65.20 281	84.84 250	41.46 307	92.97 254	66.50 237	72.96 243	87.73 248

sd_testset		77.08 214	75.37 217	82.20 205	89.25 165	62.11 243	82.06 324	89.09 266	76.77 116	70.84 216	87.12 226	41.43 308	95.01 184	67.23 228	74.55 228	89.48 227

MS-PatchMatch		77.90 203	76.50 201	82.12 209	85.99 243	69.95 42	91.75 176	92.70 112	73.97 152	62.58 308	84.44 256	41.11 309	95.78 149	63.76 261	92.17 67	80.62 352

our_test_3		68.29 306	64.69 314	79.11 281	78.92 336	64.85 170	88.40 270	85.06 332	60.32 331	52.68 352	76.12 346	40.81 310	89.80 324	44.25 349	55.65 354	82.67 334

XVG-OURS		74.25 254	72.46 260	79.63 270	78.45 344	57.59 313	80.33 339	87.39 308	63.86 299	68.76 245	89.62 188	40.50 311	91.72 296	69.00 211	74.25 233	89.58 224

VDD-MVS		83.06 110	81.81 121	86.81 59	90.86 132	67.70 97	95.40 29	91.50 167	75.46 130	81.78 89	92.34 135	40.09 312	97.13 89	86.85 68	82.04 169	95.60 53

DP-MVS		69.90 292	66.48 299	80.14 254	95.36 28	62.93 224	89.56 246	76.11 366	50.27 370	57.69 336	85.23 246	39.68 313	95.73 153	33.35 380	71.05 259	81.78 342

ppachtmachnet_test		67.72 310	63.70 321	79.77 268	78.92 336	66.04 140	88.68 265	82.90 353	60.11 333	55.45 342	75.96 347	39.19 314	90.55 310	39.53 365	52.55 364	82.71 331

ADS-MVSNet2		66.90 316	63.44 323	77.26 301	88.06 198	60.70 273	68.01 381	75.56 370	57.57 343	64.48 288	69.87 368	38.68 315	84.10 359	40.87 361	67.89 279	86.97 262

ADS-MVSNet		68.54 304	64.38 319	81.03 237	88.06 198	66.90 119	68.01 381	84.02 342	57.57 343	64.48 288	69.87 368	38.68 315	89.21 327	40.87 361	67.89 279	86.97 262

test_cas_vis1_n_1920		80.45 153	80.61 138	79.97 262	78.25 346	57.01 321	94.04 69	88.33 293	79.06 82	82.81 82	93.70 104	38.65 317	91.63 298	90.82 35	79.81 187	91.27 203

LPG-MVS_test		75.82 237	74.58 228	79.56 273	84.31 275	59.37 292	90.44 223	89.73 239	69.49 253	64.86 283	88.42 200	38.65 317	94.30 212	72.56 176	72.76 245	85.01 302

LGP-MVS_train				79.56 273	84.31 275	59.37 292		89.73 239	69.49 253	64.86 283	88.42 200	38.65 317	94.30 212	72.56 176	72.76 245	85.01 302

VDDNet		80.50 151	78.26 173	87.21 47	86.19 238	69.79 47	94.48 53	91.31 173	60.42 329	79.34 120	90.91 162	38.48 320	96.56 121	82.16 103	81.05 178	95.27 71

ACMP	71.68 10	75.58 242	74.23 235	79.62 271	84.97 263	59.64 287	90.80 214	89.07 268	70.39 243	62.95 304	87.30 223	38.28 321	93.87 237	72.89 170	71.45 256	85.36 298
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n_1920		81.66 132	82.01 118	80.64 243	82.24 298	55.09 333	94.76 49	86.87 314	81.67 34	84.40 70	94.63 77	38.17 322	94.67 198	91.98 26	83.34 155	92.16 186

UGNet		79.87 165	78.68 167	83.45 176	89.96 147	61.51 255	92.13 151	90.79 194	76.83 114	78.85 130	86.33 236	38.16 323	96.17 133	67.93 221	87.17 121	92.67 167
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
anonymousdsp		71.14 283	69.37 287	76.45 308	72.95 370	54.71 335	84.19 305	88.88 275	61.92 320	62.15 311	79.77 318	38.14 324	91.44 306	68.90 213	67.45 282	83.21 323

xiu_mvs_v1_base_debu		82.16 124	81.12 127	85.26 113	86.42 233	68.72 70	92.59 137	90.44 206	73.12 170	84.20 71	94.36 84	38.04 325	95.73 153	84.12 91	86.81 124	91.33 197

xiu_mvs_v1_base		82.16 124	81.12 127	85.26 113	86.42 233	68.72 70	92.59 137	90.44 206	73.12 170	84.20 71	94.36 84	38.04 325	95.73 153	84.12 91	86.81 124	91.33 197

xiu_mvs_v1_base_debi		82.16 124	81.12 127	85.26 113	86.42 233	68.72 70	92.59 137	90.44 206	73.12 170	84.20 71	94.36 84	38.04 325	95.73 153	84.12 91	86.81 124	91.33 197

PVSNet_0	68.08 15	71.81 278	68.32 294	82.27 201	84.68 266	62.31 240	88.68 265	90.31 212	75.84 125	57.93 335	80.65 306	37.85 328	94.19 218	69.94 200	29.05 399	90.31 214

Anonymous20231206		67.53 313	65.78 304	72.79 335	74.95 363	47.59 367	88.23 271	87.32 309	61.75 323	58.07 332	77.29 335	37.79 329	87.29 345	42.91 352	63.71 312	83.48 318

ACMM	69.62 13	74.34 252	72.73 255	79.17 278	84.25 277	57.87 308	90.36 227	89.93 229	63.17 308	65.64 278	86.04 241	37.79 329	94.10 221	65.89 243	71.52 255	85.55 294
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
cascas		78.18 196	75.77 212	85.41 105	87.14 221	69.11 60	92.96 118	91.15 182	66.71 280	70.47 219	86.07 239	37.49 331	96.48 126	70.15 199	79.80 188	90.65 209

LS3D		69.17 297	66.40 301	77.50 295	91.92 104	56.12 326	85.12 300	80.37 360	46.96 378	56.50 340	87.51 220	37.25 332	93.71 240	32.52 386	79.40 191	82.68 333

MDA-MVSNet_test_wron		63.78 333	60.16 337	74.64 320	78.15 348	60.41 277	83.49 310	84.03 341	56.17 354	39.17 390	71.59 364	37.22 333	83.24 369	42.87 354	48.73 370	80.26 356

YYNet1		63.76 334	60.14 338	74.62 321	78.06 349	60.19 282	83.46 312	83.99 345	56.18 353	39.25 389	71.56 365	37.18 334	83.34 367	42.90 353	48.70 371	80.32 355

FMVSNet5		68.04 308	65.66 307	75.18 317	84.43 273	57.89 307	83.54 309	86.26 320	61.83 322	53.64 350	73.30 355	37.15 335	85.08 355	48.99 325	61.77 327	82.56 335

test20.03		63.83 332	62.65 328	67.38 360	70.58 379	39.94 389	86.57 295	84.17 340	63.29 305	51.86 355	77.30 334	37.09 336	82.47 372	38.87 369	54.13 360	79.73 359

PVSNet	73.49 8	80.05 161	78.63 168	84.31 150	90.92 130	64.97 167	92.47 141	91.05 190	79.18 77	72.43 199	90.51 168	37.05 337	94.06 225	68.06 218	86.00 134	93.90 134

EU-MVSNet		64.01 331	63.01 325	67.02 361	74.40 366	38.86 393	83.27 314	86.19 322	45.11 383	54.27 346	81.15 300	36.91 338	80.01 382	48.79 327	57.02 350	82.19 339

Anonymous20231211		73.08 263	70.39 279	81.13 231	90.62 135	63.33 214	91.40 186	90.06 225	51.84 364	64.46 290	80.67 305	36.49 339	94.07 224	63.83 260	64.17 307	85.98 284

FMVSNet1		72.71 272	69.91 283	81.10 233	83.60 285	65.11 163	90.01 238	90.32 209	63.92 298	63.56 297	80.25 312	36.35 340	91.54 301	54.46 306	66.75 286	86.64 267

Anonymous20240529		76.84 220	74.15 236	84.88 123	91.02 127	64.95 168	93.84 82	91.09 185	53.57 359	73.00 186	87.42 221	35.91 341	97.32 75	69.14 210	72.41 250	92.36 175

WB-MVS		46.23 359	44.94 361	50.11 379	62.13 393	21.23 412	76.48 360	55.49 398	45.89 381	35.78 391	61.44 387	35.54 342	72.83 389	9.96 406	21.75 401	56.27 394

CMPMVS	48.56 21	66.77 317	64.41 318	73.84 327	70.65 378	50.31 354	77.79 356	85.73 328	45.54 382	44.76 380	82.14 280	35.40 343	90.14 320	63.18 266	74.54 230	81.07 347
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs6		67.57 312	64.76 313	76.00 312	72.82 372	53.37 340	88.71 264	86.78 317	53.19 360	57.58 337	78.03 330	35.33 344	92.41 279	55.56 302	54.88 358	82.21 338

PatchMatch-RL		72.06 277	69.98 280	78.28 287	89.51 158	55.70 329	83.49 310	83.39 350	61.24 324	63.72 296	82.76 272	34.77 345	93.03 252	53.37 312	77.59 207	86.12 281

LTVRE_ROB	59.60 19	66.27 319	63.54 322	74.45 322	84.00 280	51.55 347	67.08 384	83.53 347	58.78 339	54.94 344	80.31 310	34.54 346	93.23 249	40.64 363	68.03 277	78.58 369
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
SSC-MVS		44.51 361	43.35 363	47.99 383	61.01 395	18.90 414	74.12 368	54.36 399	43.42 388	34.10 394	60.02 388	34.42 347	70.39 392	9.14 408	19.57 402	54.68 395

UniMVSNet_ETH3D		72.74 271	70.53 278	79.36 275	78.62 343	56.64 323	85.01 301	89.20 257	63.77 300	64.84 285	84.44 256	34.05 348	91.86 293	63.94 259	70.89 260	89.57 225

F-COLMAP		70.66 284	68.44 292	77.32 299	86.37 236	55.91 327	88.00 275	86.32 318	56.94 349	57.28 338	88.07 211	33.58 349	92.49 277	51.02 316	68.37 275	83.55 315

pmmvs-eth3d		65.53 325	62.32 330	75.19 316	69.39 382	59.59 288	82.80 321	83.43 348	62.52 314	51.30 359	72.49 356	32.86 350	87.16 346	55.32 303	50.73 367	78.83 367

MDA-MVSNet-bldmvs		61.54 340	57.70 345	73.05 332	79.53 327	57.00 322	83.08 318	81.23 355	57.57 343	34.91 393	72.45 357	32.79 351	86.26 350	35.81 374	41.95 381	75.89 376

MIMVSNet		71.64 279	68.44 292	81.23 228	81.97 302	64.44 177	73.05 370	88.80 279	69.67 252	64.59 286	74.79 352	32.79 351	87.82 337	53.99 308	76.35 221	91.42 195

UnsupCasMVSNet_eth		65.79 322	63.10 324	73.88 326	70.71 377	50.29 355	81.09 333	89.88 231	72.58 182	49.25 367	74.77 353	32.57 353	87.43 344	55.96 301	41.04 383	83.90 312

N_pmnet		50.55 355	49.11 358	54.88 374	77.17 354	4.02 418	84.36 304	2.00 416	48.59 374	45.86 376	68.82 371	32.22 354	82.80 371	31.58 388	51.38 366	77.81 372

test_0402		64.54 328	61.09 334	74.92 319	84.10 279	60.75 270	87.95 276	79.71 362	52.03 362	52.41 353	77.20 336	32.21 355	91.64 297	23.14 394	61.03 334	72.36 382

DSMNet-mixed		56.78 350	54.44 354	63.79 364	63.21 390	29.44 405	64.43 387	64.10 392	42.12 390	51.32 358	71.60 363	31.76 356	75.04 386	36.23 372	65.20 297	86.87 265

MSDG		69.54 295	65.73 305	80.96 238	85.11 261	63.71 201	84.19 305	83.28 351	56.95 348	54.50 345	84.03 259	31.50 357	96.03 143	42.87 354	69.13 270	83.14 325

RPSCF		64.24 330	61.98 332	71.01 347	76.10 359	45.00 378	75.83 364	75.94 367	46.94 379	58.96 327	84.59 253	31.40 358	82.00 376	47.76 334	60.33 342	86.04 282

tt0805		73.07 264	70.73 276	80.07 256	78.37 345	57.05 319	87.78 280	92.18 135	61.23 325	67.04 269	86.49 233	31.35 359	94.58 199	65.06 253	67.12 283	88.57 238

jajsoiax		73.05 265	71.51 270	77.67 293	77.46 352	54.83 334	88.81 263	90.04 226	69.13 260	62.85 306	83.51 265	31.16 360	92.75 266	70.83 192	69.80 261	85.43 297

MVS-HIRNet		60.25 344	55.55 351	74.35 323	84.37 274	56.57 324	71.64 372	74.11 374	34.44 393	45.54 378	42.24 400	31.11 361	89.81 322	40.36 364	76.10 223	76.67 375

SixPastTwentyTwo		64.92 326	61.78 333	74.34 324	78.74 340	49.76 356	83.42 313	79.51 363	62.86 310	50.27 362	77.35 333	30.92 362	90.49 312	45.89 342	47.06 373	82.78 327

KD-MVS_self_test		60.87 341	58.60 342	67.68 358	66.13 387	39.93 390	75.63 366	84.70 335	57.32 346	49.57 365	68.45 372	29.55 363	82.87 370	48.09 329	47.94 372	80.25 357

mvs_tets		72.71 272	71.11 271	77.52 294	77.41 353	54.52 336	88.45 269	89.76 235	68.76 265	62.70 307	83.26 268	29.49 364	92.71 267	70.51 198	69.62 263	85.34 299

Anonymous202405211		77.96 200	75.33 219	85.87 89	93.73 54	64.52 172	94.85 46	85.36 330	62.52 314	76.11 156	90.18 178	29.43 365	97.29 77	68.51 216	77.24 215	95.81 49

K. test v3		63.09 335	59.61 340	73.53 329	76.26 358	49.38 361	83.27 314	77.15 365	64.35 296	47.77 372	72.32 360	28.73 366	87.79 338	49.93 322	36.69 389	83.41 320

UnsupCasMVSNet_bld		61.60 339	57.71 344	73.29 331	68.73 383	51.64 346	78.61 350	89.05 269	57.20 347	46.11 373	61.96 385	28.70 367	88.60 329	50.08 321	38.90 387	79.63 360

lessismore_v0				73.72 328	72.93 371	47.83 366		61.72 395		45.86 376	73.76 354	28.63 368	89.81 322	47.75 335	31.37 396	83.53 316

new-patchmatchnet		59.30 347	56.48 349	67.79 357	65.86 388	44.19 379	82.47 322	81.77 354	59.94 334	43.65 384	66.20 376	27.67 369	81.68 377	39.34 366	41.40 382	77.50 373

ACMH	63.93 17	68.62 302	64.81 312	80.03 258	85.22 257	63.25 215	87.72 281	84.66 336	60.83 327	51.57 357	79.43 322	27.29 370	94.96 186	41.76 357	64.84 300	81.88 340
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OurMVSNet-221017-0		64.68 327	62.17 331	72.21 340	76.08 360	47.35 368	80.67 336	81.02 356	56.19 352	51.60 356	79.66 320	27.05 371	88.56 330	53.60 311	53.63 361	80.71 351

ACMH+	65.35 16	67.65 311	64.55 315	76.96 305	84.59 269	57.10 318	88.08 272	80.79 357	58.59 341	53.00 351	81.09 301	26.63 372	92.95 255	46.51 338	61.69 331	80.82 349

OpenMVS_ROB	61.12 18	66.39 318	62.92 326	76.80 307	76.51 356	57.77 309	89.22 255	83.41 349	55.48 355	53.86 349	77.84 331	26.28 373	93.95 234	34.90 377	68.76 272	78.68 368

test_fmvs1		74.07 255	73.69 243	75.22 315	78.91 338	47.34 369	89.06 261	74.69 373	63.68 301	79.41 119	91.59 152	24.36 374	87.77 339	85.22 78	76.26 222	90.55 212

COLMAP_ROB	57.96 20	62.98 336	59.65 339	72.98 333	81.44 306	53.00 342	83.75 308	75.53 371	48.34 376	48.81 369	81.40 293	24.14 375	90.30 313	32.95 382	60.52 339	75.65 377
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet1		60.16 345	57.33 346	68.67 354	69.71 380	44.13 380	78.92 349	84.21 339	55.05 356	44.63 381	71.85 362	23.91 376	81.54 378	32.63 385	55.03 357	80.35 354

testgi		64.48 329	62.87 327	69.31 352	71.24 373	40.62 388	85.49 298	79.92 361	65.36 290	54.18 347	83.49 266	23.74 377	84.55 357	41.60 358	60.79 337	82.77 328

ITE_SJBPF				70.43 348	74.44 365	47.06 372		77.32 364	60.16 332	54.04 348	83.53 264	23.30 378	84.01 361	43.07 351	61.58 332	80.21 358

EG-PatchMatch MVS		68.55 303	65.41 309	77.96 291	78.69 341	62.93 224	89.86 243	89.17 259	60.55 328	50.27 362	77.73 332	22.60 379	94.06 225	47.18 336	72.65 247	76.88 374

tmp_tt		22.26 376	23.75 378	17.80 392	5.23 416	12.06 417	35.26 403	39.48 410	2.82 410	18.94 401	44.20 399	22.23 380	24.64 411	36.30 371	9.31 408	16.69 405

USDC		67.43 315	64.51 316	76.19 310	77.94 350	55.29 331	78.38 352	85.00 333	73.17 168	48.36 370	80.37 309	21.23 381	92.48 278	52.15 314	64.02 310	80.81 350

Anonymous20240521		62.09 337	59.08 341	71.10 346	67.19 385	48.72 363	83.91 307	85.23 331	50.38 369	47.84 371	71.22 367	20.74 382	85.51 354	46.47 339	58.75 347	79.06 364

test_vis1_n		71.63 280	70.73 276	74.31 325	69.63 381	47.29 370	86.91 291	72.11 378	63.21 307	75.18 167	90.17 179	20.40 383	85.76 351	84.59 87	74.42 232	89.87 219

XVG-ACMP-BASELINE		68.04 308	65.53 308	75.56 313	74.06 367	52.37 343	78.43 351	85.88 325	62.03 318	58.91 328	81.21 299	20.38 384	91.15 308	60.69 281	68.18 276	83.16 324

test_fmvs1_n		72.69 274	71.92 265	74.99 318	71.15 375	47.08 371	87.34 287	75.67 368	63.48 303	78.08 136	91.17 159	20.16 385	87.87 336	84.65 86	75.57 226	90.01 218

AllTest		61.66 338	58.06 343	72.46 337	79.57 325	51.42 349	80.17 342	68.61 386	51.25 366	45.88 374	81.23 295	19.86 386	86.58 348	38.98 367	57.01 351	79.39 361

TestCases				72.46 337	79.57 325	51.42 349		68.61 386	51.25 366	45.88 374	81.23 295	19.86 386	86.58 348	38.98 367	57.01 351	79.39 361

test_vis1_rt		59.09 348	57.31 347	64.43 363	68.44 384	46.02 376	83.05 319	48.63 405	51.96 363	49.57 365	63.86 381	16.30 388	80.20 381	71.21 190	62.79 316	67.07 388

pmmvs3		55.51 351	51.50 357	67.53 359	57.90 397	50.93 352	80.37 338	73.66 375	40.63 391	44.15 383	64.75 379	16.30 388	78.97 383	44.77 348	40.98 385	72.69 380

test_fmvs2		65.78 323	64.84 311	68.60 355	66.54 386	41.71 385	83.27 314	69.81 384	54.38 357	67.91 256	84.54 255	15.35 390	81.22 379	75.65 152	66.16 289	82.88 326

TDRefinement		55.28 352	51.58 356	66.39 362	59.53 396	46.15 375	76.23 361	72.80 376	44.60 384	42.49 386	76.28 345	15.29 391	82.39 373	33.20 381	43.75 378	70.62 384

new_pmnet		49.31 356	46.44 359	57.93 369	62.84 391	40.74 387	68.47 380	62.96 394	36.48 392	35.09 392	57.81 389	14.97 392	72.18 390	32.86 383	46.44 374	60.88 391

TinyColmap		60.32 343	56.42 350	72.00 344	78.78 339	53.18 341	78.36 353	75.64 369	52.30 361	41.59 388	75.82 349	14.76 393	88.35 332	35.84 373	54.71 359	74.46 378

EGC-MVSNET		42.35 362	38.09 365	55.11 373	74.57 364	46.62 373	71.63 373	55.77 397	0.04 411	0.24 412	62.70 383	14.24 394	74.91 387	17.59 400	46.06 375	43.80 397

LF4IMVS		54.01 354	52.12 355	59.69 368	62.41 392	39.91 391	68.59 379	68.28 388	42.96 389	44.55 382	75.18 350	14.09 395	68.39 394	41.36 360	51.68 365	70.78 383

PM-MVS		59.40 346	56.59 348	67.84 356	63.63 389	41.86 384	76.76 358	63.22 393	59.01 338	51.07 360	72.27 361	11.72 396	83.25 368	61.34 277	50.28 369	78.39 370

mvsany_test3		48.86 357	46.35 360	56.41 370	46.00 405	31.67 401	62.26 389	47.25 406	43.71 387	45.54 378	68.15 373	10.84 397	64.44 403	57.95 293	35.44 393	73.13 379

ambc				69.61 350	61.38 394	41.35 386	49.07 401	85.86 327		50.18 364	66.40 375	10.16 398	88.14 334	45.73 343	44.20 377	79.32 363

FPMVS		45.64 360	43.10 364	53.23 377	51.42 402	36.46 395	64.97 386	71.91 379	29.13 397	27.53 397	61.55 386	9.83 399	65.01 401	16.00 403	55.58 355	58.22 393

ANet_high		40.27 366	35.20 369	55.47 372	34.74 413	34.47 398	63.84 388	71.56 381	48.42 375	18.80 402	41.08 401	9.52 400	64.45 402	20.18 397	8.66 409	67.49 387

test_method		38.59 367	35.16 370	48.89 381	54.33 398	21.35 411	45.32 402	53.71 400	7.41 408	28.74 396	51.62 392	8.70 401	52.87 406	33.73 378	32.89 395	72.47 381

EMVS		23.76 375	23.20 379	25.46 391	41.52 411	16.90 416	60.56 392	38.79 412	14.62 406	8.99 410	20.24 409	7.35 402	45.82 409	7.25 410	9.46 407	13.64 407

test_f		46.58 358	43.45 362	55.96 371	45.18 406	32.05 400	61.18 390	49.49 404	33.39 394	42.05 387	62.48 384	7.00 403	65.56 399	47.08 337	43.21 380	70.27 385

test_fmvs3		56.82 349	54.86 353	62.69 367	53.59 399	35.47 396	75.87 363	65.64 391	43.91 386	55.10 343	71.43 366	6.91 404	74.40 388	68.64 215	52.63 362	78.20 371

E-PMN		24.61 373	24.00 377	26.45 390	43.74 408	18.44 415	60.86 391	39.66 409	15.11 405	9.53 409	22.10 406	6.52 405	46.94 408	8.31 409	10.14 406	13.98 406

DeepMVS_CX				34.71 389	51.45 401	24.73 409		28.48 415	31.46 396	17.49 405	52.75 391	5.80 406	42.60 410	18.18 398	19.42 403	36.81 402

Gipuma		34.91 369	31.44 372	45.30 384	70.99 376	39.64 392	19.85 406	72.56 377	20.10 402	16.16 406	21.47 407	5.08 407	71.16 391	13.07 404	43.70 379	25.08 404
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
APD_test1		40.50 364	37.31 367	50.09 380	51.88 400	35.27 397	59.45 394	52.59 401	21.64 400	26.12 398	57.80 390	4.56 408	66.56 397	22.64 395	39.09 386	48.43 396

LCM-MVSNet		40.54 363	35.79 368	54.76 375	36.92 412	30.81 402	51.41 399	69.02 385	22.07 399	24.63 399	45.37 396	4.56 408	65.81 398	33.67 379	34.50 394	67.67 386

PMMVS2		37.93 368	33.61 371	50.92 378	46.31 404	24.76 408	60.55 393	50.05 402	28.94 398	20.93 400	47.59 393	4.41 410	65.13 400	25.14 393	18.55 404	62.87 390

test_vis3_rt		40.46 365	37.79 366	48.47 382	44.49 407	33.35 399	66.56 385	32.84 413	32.39 395	29.65 395	39.13 403	3.91 411	68.65 393	50.17 319	40.99 384	43.40 398

testf1		32.77 370	29.47 373	42.67 386	41.89 409	30.81 402	52.07 397	43.45 407	15.45 403	18.52 403	44.82 397	2.12 412	58.38 404	16.05 401	30.87 397	38.83 399

APD_test2		32.77 370	29.47 373	42.67 386	41.89 409	30.81 402	52.07 397	43.45 407	15.45 403	18.52 403	44.82 397	2.12 412	58.38 404	16.05 401	30.87 397	38.83 399

PMVS	26.43 22	31.84 372	28.16 375	42.89 385	25.87 415	27.58 406	50.92 400	49.78 403	21.37 401	14.17 407	40.81 402	2.01 414	66.62 396	9.61 407	38.88 388	34.49 403
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	24.84 23	24.35 374	19.77 380	38.09 388	34.56 414	26.92 407	26.57 404	38.87 411	11.73 407	11.37 408	27.44 404	1.37 415	50.42 407	11.41 405	14.60 405	36.93 401
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		11.30 378	10.95 381	12.33 393	48.05 403	19.89 413	25.89 405	1.92 417	3.58 409	3.12 411	1.37 411	0.64 416	15.77 412	6.23 411	7.77 410	1.35 408

test123		6.92 381	9.21 384	0.08 394	0.03 418	0.05 419	81.65 328	0.01 419	0.02 413	0.14 414	0.85 413	0.03 417	0.02 413	0.12 413	0.00 412	0.16 409

testmvs		7.23 380	9.62 383	0.06 395	0.04 417	0.02 420	84.98 302	0.02 418	0.03 412	0.18 413	1.21 412	0.01 418	0.02 413	0.14 412	0.01 411	0.13 410

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 412	0.00 411

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 412	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 412	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 412	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 412	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 412	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 412	0.00 411

ab-mvs-re		7.91 379	10.55 382	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	94.95 66	0.00 419	0.00 415	0.00 414	0.00 412	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 412	0.00 411

WAC-MVS						49.45 359								31.56 389

FOURS1					93.95 47	61.77 249	93.96 72	91.92 143	62.14 317	86.57 48

MSC_two_6792asdad				89.60 8	97.31 4	73.22 12		95.05 26					99.07 13	92.01 24	94.77 25	96.51 24

No_MVS				89.60 8	97.31 4	73.22 12		95.05 26					99.07 13	92.01 24	94.77 25	96.51 24

eth-test2					0.00 419

eth-test					0.00 419

IU-MVS					96.46 11	69.91 43		95.18 20	80.75 49	95.28 1				92.34 21	95.36 13	96.47 28

save fliter					93.84 50	67.89 93	95.05 40	92.66 116	78.19 92

test_0728_SECOND				88.70 18	96.45 12	70.43 35	96.64 9	94.37 52					99.15 2	91.91 27	94.90 21	96.51 24

GSMVS																94.68 97

test_part2					96.29 19	68.16 87				90.78 16

MTGPA								92.23 129

MTMP							93.77 86	32.52 414

gm-plane-assit					88.42 186	67.04 116			78.62 89		91.83 146		97.37 71	76.57 145

test9_res														89.41 41	94.96 18	95.29 68

agg_prior2														86.41 70	94.75 29	95.33 64

agg_prior					94.16 43	66.97 118		93.31 89		84.49 69			96.75 115

test_prior4						67.18 112	93.92 75

test_prior				86.42 74	94.71 35	67.35 107		93.10 99					96.84 112			95.05 80

旧先验2							92.00 162		59.37 337	87.54 41			93.47 246	75.39 154

新几何2							91.41 184

无先验							92.71 127	92.61 120	62.03 318				97.01 95	66.63 233		93.97 129

原ACMM2							92.01 159

testdata2													96.09 137	61.26 278

testdata1							89.21 256		77.55 105

plane_prior7					86.94 226	61.51 255

plane_prior5								91.31 173					95.55 167	76.74 143	78.53 201	88.39 242

plane_prior4											89.14 195

plane_prior3						61.95 247			79.09 80	72.53 195

plane_prior2							93.13 111		78.81 86

plane_prior1					87.15 220

plane_prior						62.42 235	93.85 79		79.38 72						78.80 198

n2								0.00 420

nn								0.00 420

door-mid								66.01 390

test11								93.01 101

door								66.57 389

HQP5-MVS						63.66 205

HQP-NCC					87.54 211		94.06 65		79.80 63	74.18 175

ACMP_Plane					87.54 211		94.06 65		79.80 63	74.18 175

BP-MVS														77.63 140

HQP4-MVS										74.18 175			95.61 161			88.63 236

HQP3-MVS								91.70 159							78.90 196

NP-MVS					87.41 214	63.04 220					90.30 174

ACMMP++_ref															71.63 253

ACMMP++															69.72 262

High-resolution multi-view benchmark