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 4	91.87 1	85.88 81	92.83 72	64.03 184	93.06 107	94.33 49	82.19 28	93.65 3	96.15 35	85.89 1	97.19 82	91.02 33	97.75 1	96.43 26
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 3	91.09 4	88.87 14	97.31 4	69.91 37	93.96 70	94.37 47	72.48 176	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 12	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 45	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 2	90.52 7	91.24 1	89.68 145	76.68 2	97.29 1	95.35 13	82.87 20	91.58 12	97.22 3	79.93 5	99.10 9	83.12 92	97.64 2	97.94 1

baseline2		83.68 92	83.42 83	84.48 136	87.37 207	66.00 133	90.06 228	95.93 8	79.71 60	69.08 228	90.39 165	77.92 6	96.28 123	78.91 125	81.38 165	91.16 194

GG-mvs-BLEND				86.53 65	91.91 99	69.67 46	75.02 358	94.75 29		78.67 123	90.85 157	77.91 7	94.56 195	72.25 172	93.74 43	95.36 58

gg-mvs-nofinetune		77.18 201	74.31 222	85.80 86	91.42 112	68.36 72	71.78 361	94.72 30	49.61 362	77.12 138	45.92 385	77.41 8	93.98 223	67.62 217	93.16 53	95.05 74

SED-MVS		89.94 8	90.36 9	88.70 16	96.45 12	69.38 48	96.89 5	94.44 41	71.65 206	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 48		94.44 41	71.65 206	92.11 6	97.05 7	76.79 9	99.11 6

test_0728_THIRD									72.48 176	90.55 19	96.93 11	76.24 11	99.08 11	91.53 29	94.99 17	96.43 26

DPE-MVS		88.77 15	89.21 15	87.45 37	96.26 20	67.56 94	94.17 57	94.15 54	68.77 256	90.74 17	97.27 2	76.09 12	98.49 29	90.58 37	94.91 20	96.30 29
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 19	88.37 19	86.70 57	93.51 56	65.32 149	95.15 36	93.84 60	78.17 86	85.93 50	94.80 71	75.80 13	98.21 34	89.38 40	88.78 101	96.59 16

DeepPCF-MVS	81.17 1	89.72 9	91.38 3	84.72 124	93.00 69	58.16 297	96.72 8	94.41 43	86.50 8	90.25 21	97.83 1	75.46 14	98.67 25	92.78 18	95.49 12	97.32 6

dcpmvs_2		87.37 29	87.55 28	86.85 50	95.04 32	68.20 79	90.36 219	90.66 190	79.37 65	81.20 89	93.67 103	74.73 15	96.55 118	90.88 34	92.00 67	95.82 44

MVSTER		82.47 109	82.05 106	83.74 155	92.68 79	69.01 58	91.90 158	93.21 86	79.83 56	72.14 193	85.71 235	74.72 16	94.72 184	75.72 144	72.49 238	87.50 241

test_241102_TWO								94.41 43	71.65 206	92.07 8	97.21 4	74.58 17	99.11 6	92.34 21	95.36 13	96.59 16

test_one_0601					96.32 18	69.74 43		94.18 52	71.42 217	90.67 18	96.85 16	74.45 18

DELS-MVS		90.05 6	90.09 10	89.94 4	93.14 66	73.88 7	97.01 4	94.40 45	88.32 3	85.71 52	94.91 68	74.11 19	98.91 17	87.26 59	95.94 8	97.03 10
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 10	90.99 5	85.85 84	96.04 24	63.70 194	95.04 40	95.19 16	86.74 7	91.53 14	95.15 62	73.86 20	97.58 59	93.38 14	92.00 67	96.28 32

DVP-MVS		89.41 12	89.73 13	88.45 22	96.40 15	69.99 33	96.64 9	94.52 37	71.92 192	90.55 19	96.93 11	73.77 21	99.08 11	91.91 27	94.90 21	96.29 30
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 33	96.76 7	94.33 49	71.92 192	91.89 10	97.11 6	73.77 21

ET-MVSNet_ETH3D		84.01 82	83.15 90	86.58 62	90.78 126	70.89 24	94.74 47	94.62 35	81.44 38	58.19 322	93.64 104	73.64 23	92.35 275	82.66 94	78.66 189	96.50 24

CSCG		86.87 34	86.26 42	88.72 15	95.05 31	70.79 25	93.83 82	95.33 14	68.48 260	77.63 131	94.35 86	73.04 24	98.45 30	84.92 79	93.71 45	96.92 11

tttt0517		79.50 160	78.53 160	82.41 189	87.22 210	61.43 248	89.75 238	94.76 28	69.29 248	67.91 247	88.06 203	72.92 25	95.63 151	62.91 260	73.90 228	90.16 205

MCST-MVS		91.08 1	91.46 2	89.94 4	97.66 2	73.37 8	97.13 2	95.58 11	89.33 1	85.77 51	96.26 30	72.84 26	99.38 1	92.64 19	95.93 9	97.08 9

iter_conf05		83.27 96	82.70 98	84.98 112	93.32 59	71.84 15	94.16 58	81.76 343	82.74 21	73.83 172	88.40 191	72.77 27	94.61 189	82.10 98	75.21 216	88.48 230

thisisatest0515		83.41 93	82.49 102	86.16 75	89.46 151	68.26 76	93.54 94	94.70 31	74.31 137	75.75 148	90.92 155	72.62 28	96.52 119	69.64 195	81.50 164	93.71 129

thisisatest0530		81.15 129	80.07 134	84.39 139	88.26 183	65.63 142	91.40 178	94.62 35	71.27 219	70.93 206	89.18 182	72.47 29	96.04 134	65.62 239	76.89 206	91.49 183

TSAR-MVS + MP.		88.11 18	88.64 16	86.54 64	91.73 103	68.04 82	90.36 219	93.55 74	82.89 19	91.29 15	92.89 119	72.27 30	96.03 135	87.99 50	94.77 25	95.54 52
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EPP-MVSNet		81.79 121	81.52 113	82.61 183	88.77 170	60.21 272	93.02 111	93.66 70	68.52 259	72.90 180	90.39 165	72.19 31	94.96 176	74.93 152	79.29 183	92.67 158

CostFormer		82.33 111	81.15 116	85.86 83	89.01 164	68.46 70	82.39 316	93.01 96	75.59 120	80.25 101	81.57 281	72.03 32	94.96 176	79.06 123	77.48 200	94.16 110

HPM-MVS++		89.37 13	89.95 12	87.64 30	95.10 30	68.23 78	95.24 33	94.49 39	82.43 25	88.90 32	96.35 27	71.89 33	98.63 26	88.76 47	96.40 6	96.06 36

CNVR-MVS		90.32 5	90.89 6	88.61 19	96.76 8	70.65 26	96.47 13	94.83 26	84.83 11	89.07 31	96.80 19	70.86 34	99.06 15	92.64 19	95.71 10	96.12 35

IB-MVS	77.80 4	82.18 113	80.46 132	87.35 39	89.14 161	70.28 31	95.59 26	95.17 18	78.85 77	70.19 216	85.82 233	70.66 35	97.67 51	72.19 175	66.52 279	94.09 114
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
MM				88.92 13		71.10 22	97.02 3	96.04 6	88.70 2	91.57 13	96.19 33	70.12 36	98.91 17	96.83 1	95.06 16	96.76 12

fmvsm_l_conf0.5_n		87.49 26	88.19 21	85.39 98	86.95 216	64.37 174	94.30 54	88.45 279	80.51 48	92.70 4	96.86 15	69.98 37	97.15 86	95.83 3	88.08 108	94.65 91

baseline1		81.84 120	81.03 121	84.28 144	91.60 106	66.62 119	91.08 197	91.66 153	81.87 31	74.86 159	91.67 145	69.98 37	94.92 179	71.76 178	64.75 294	91.29 192

fmvsm_l_conf0.5_n_a		87.44 28	88.15 22	85.30 102	87.10 213	64.19 181	94.41 52	88.14 288	80.24 53	92.54 5	96.97 10	69.52 39	97.17 83	95.89 2	88.51 104	94.56 94

testing222		85.18 61	84.69 66	86.63 59	92.91 71	69.91 37	92.61 128	95.80 9	80.31 51	80.38 99	92.27 134	68.73 40	95.19 170	75.94 143	83.27 149	94.81 85

MVS_0304		90.01 7	90.50 8	88.53 20	90.14 136	70.94 23	96.47 13	95.72 10	87.33 4	89.60 28	96.26 30	68.44 41	98.74 24	95.82 4	94.72 30	95.90 42

alignmvs		87.28 30	86.97 35	88.24 24	91.30 115	71.14 21	95.61 25	93.56 73	79.30 66	87.07 41	95.25 58	68.43 42	96.93 105	87.87 51	84.33 142	96.65 14

PAPM		85.89 50	85.46 55	87.18 42	88.20 187	72.42 13	92.41 136	92.77 104	82.11 29	80.34 100	93.07 114	68.27 43	95.02 173	78.39 130	93.59 47	94.09 114

train_agg		87.21 31	87.42 30	86.60 60	94.18 41	67.28 101	94.16 58	93.51 75	71.87 197	85.52 54	95.33 51	68.19 44	97.27 80	89.09 44	94.90 21	95.25 69

test_8					94.19 40	67.19 103	94.15 61	93.42 81	71.87 197	85.38 57	95.35 50	68.19 44	96.95 102

TEST9					94.18 41	67.28 101	94.16 58	93.51 75	71.75 203	85.52 54	95.33 51	68.01 46	97.27 80

test_prior2							95.10 38		75.40 124	85.25 60	95.61 45	67.94 47		87.47 56	94.77 25

WTY-MVS		86.32 42	85.81 51	87.85 26	92.82 74	69.37 50	95.20 34	95.25 15	82.71 22	81.91 84	94.73 72	67.93 48	97.63 56	79.55 117	82.25 156	96.54 19

APDe-MVS		87.54 25	87.84 24	86.65 58	96.07 23	66.30 127	94.84 45	93.78 61	69.35 247	88.39 33	96.34 28	67.74 49	97.66 54	90.62 36	93.44 49	96.01 39
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsm_n_1920		87.69 24	88.50 17	85.27 104	87.05 215	63.55 201	93.69 87	91.08 178	84.18 13	90.17 23	97.04 8	67.58 50	97.99 39	95.72 5	90.03 92	94.26 105

tpm2		79.80 156	77.95 169	85.34 101	88.28 182	68.26 76	81.56 322	91.42 162	70.11 238	77.59 133	80.50 299	67.40 51	94.26 208	67.34 219	77.35 201	93.51 134

miper_enhance_ethall		78.86 172	77.97 168	81.54 213	88.00 192	65.17 153	91.41 176	89.15 250	75.19 127	68.79 235	83.98 253	67.17 52	92.82 253	72.73 167	65.30 285	86.62 262

SF-MVS		87.03 33	87.09 33	86.84 51	92.70 78	67.45 99	93.64 89	93.76 64	70.78 230	86.25 45	96.44 26	66.98 53	97.79 47	88.68 48	94.56 32	95.28 65

HY-MVS	76.49 5	84.28 75	83.36 86	87.02 48	92.22 88	67.74 89	84.65 296	94.50 38	79.15 70	82.23 82	87.93 204	66.88 54	96.94 103	80.53 112	82.20 157	96.39 28

EPNet		87.84 22	88.38 18	86.23 74	93.30 60	66.05 131	95.26 32	94.84 25	87.09 5	88.06 34	94.53 77	66.79 55	97.34 73	83.89 88	91.68 72	95.29 63
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
9.14			87.63 26		93.86 47		94.41 52	94.18 52	72.76 171	86.21 46	96.51 24	66.64 56	97.88 44	90.08 38	94.04 37

FIs		79.47 161	79.41 148	79.67 259	85.95 234	59.40 282	91.68 170	93.94 58	78.06 87	68.96 232	88.28 194	66.61 57	91.77 287	66.20 233	74.99 217	87.82 238

NCCC		89.07 14	89.46 14	87.91 25	96.60 10	69.05 57	96.38 15	94.64 34	84.42 12	86.74 43	96.20 32	66.56 58	98.76 23	89.03 46	94.56 32	95.92 41

SD-MVS		87.49 26	87.49 29	87.50 36	93.60 53	68.82 63	93.90 74	92.63 112	76.86 105	87.90 35	95.76 41	66.17 59	97.63 56	89.06 45	91.48 76	96.05 37
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		78.15 187	77.55 174	79.98 250	84.46 261	60.26 270	92.25 139	93.20 88	77.50 99	68.88 233	86.61 222	66.10 60	92.13 279	66.38 230	62.55 310	87.54 240

CHOSEN 280x420		77.35 199	76.95 187	78.55 275	87.07 214	62.68 224	69.71 367	82.95 339	68.80 255	71.48 202	87.27 216	66.03 61	84.00 354	76.47 140	82.81 153	88.95 220

CANet		89.61 11	89.99 11	88.46 21	94.39 39	69.71 44	96.53 12	93.78 61	86.89 6	89.68 27	95.78 40	65.94 62	99.10 9	92.99 16	93.91 40	96.58 18

segment_acmp												65.94 62

Vis-MVSNet (Re-imp)		79.24 164	79.57 143	78.24 280	88.46 175	52.29 336	90.41 217	89.12 252	74.24 138	69.13 226	91.91 140	65.77 64	90.09 312	59.00 283	88.09 107	92.33 167

FC-MVSNet-test		77.99 189	78.08 166	77.70 283	84.89 254	55.51 322	90.27 222	93.75 67	76.87 104	66.80 265	87.59 209	65.71 65	90.23 309	62.89 261	73.94 226	87.37 245

SMA-MVS		88.14 16	88.29 20	87.67 29	93.21 63	68.72 65	93.85 77	94.03 57	74.18 139	91.74 11	96.67 21	65.61 66	98.42 33	89.24 43	96.08 7	95.88 43
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 45	94.60 36	68.86 61		92.91 100		82.67 81		65.44 67	97.55 62		93.69 46	94.84 83

test_fmvsmconf_n		86.58 39	87.17 32	84.82 117	85.28 246	62.55 225	94.26 56	89.78 223	83.81 16	87.78 36	96.33 29	65.33 68	96.98 98	94.40 11	87.55 113	94.95 78

旧先验1					91.94 96	60.74 262		91.50 159			94.36 82	65.23 69			91.84 69	94.55 95

1112_ss		80.56 140	79.83 140	82.77 178	88.65 171	60.78 258	92.29 138	88.36 281	72.58 174	72.46 189	94.95 64	65.09 70	93.42 238	66.38 230	77.71 194	94.10 113

MVSFormer		83.75 89	82.88 94	86.37 70	89.24 159	71.18 19	89.07 252	90.69 187	65.80 279	87.13 39	94.34 87	64.99 71	92.67 261	72.83 164	91.80 70	95.27 66

lupinMVS		87.74 23	87.77 25	87.63 34	89.24 159	71.18 19	96.57 11	92.90 101	82.70 23	87.13 39	95.27 56	64.99 71	95.80 140	89.34 41	91.80 70	95.93 40

tpmrst		80.57 139	79.14 154	84.84 116	90.10 137	68.28 75	81.70 320	89.72 230	77.63 97	75.96 147	79.54 313	64.94 73	92.71 258	75.43 146	77.28 203	93.55 133

ZD-MVS					96.63 9	65.50 147		93.50 77	70.74 231	85.26 59	95.19 61	64.92 74	97.29 76	87.51 55	93.01 54

testing3		70.38 279	70.83 263	69.03 345	85.82 238	43.93 373	90.72 209	90.56 193	68.06 261	60.24 310	86.82 221	64.83 75	84.12 350	26.33 383	64.10 300	79.04 357

casdiffmvs_mvg		85.66 55	85.18 58	87.09 45	88.22 186	69.35 51	93.74 86	91.89 139	81.47 35	80.10 102	91.45 147	64.80 76	96.35 121	87.23 60	87.69 111	95.58 50
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		77.60 195	76.44 192	81.09 227	85.70 241	64.41 172	90.65 211	88.64 275	72.31 182	67.37 258	82.52 267	64.77 77	92.64 265	70.67 187	65.30 285	86.24 267

Test_1112_low_res		79.56 159	78.60 159	82.43 186	88.24 185	60.39 269	92.09 147	87.99 292	72.10 190	71.84 196	87.42 212	64.62 78	93.04 242	65.80 237	77.30 202	93.85 127

test2506		83.29 95	82.92 93	84.37 140	88.39 179	63.18 211	92.01 152	91.35 164	77.66 95	78.49 124	91.42 148	64.58 79	95.09 172	73.19 160	89.23 97	94.85 80

DeepC-MVS_fast	79.48 2	87.95 20	88.00 23	87.79 28	95.86 27	68.32 73	95.74 21	94.11 55	83.82 15	83.49 73	96.19 33	64.53 80	98.44 31	83.42 91	94.88 24	96.61 15
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 32	86.27 41	89.62 7	97.79 1	76.27 4	94.96 43	94.49 39	78.74 81	83.87 72	92.94 117	64.34 81	96.94 103	75.19 148	94.09 36	95.66 47

casdiffmvs		85.37 58	84.87 64	86.84 51	88.25 184	69.07 56	93.04 109	91.76 146	81.27 41	80.84 96	92.07 138	64.23 82	96.06 133	84.98 78	87.43 115	95.39 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
cl22		77.94 191	76.78 188	81.42 215	87.57 201	64.93 161	90.67 210	88.86 265	72.45 178	67.63 253	82.68 266	64.07 83	92.91 251	71.79 176	65.30 285	86.44 263

tpm		78.58 180	77.03 184	83.22 171	85.94 236	64.56 163	83.21 310	91.14 174	78.31 84	73.67 173	79.68 311	64.01 84	92.09 281	66.07 234	71.26 248	93.03 149

CDS-MVSNet		81.43 126	80.74 124	83.52 162	86.26 228	64.45 168	92.09 147	90.65 191	75.83 119	73.95 171	89.81 177	63.97 85	92.91 251	71.27 181	82.82 152	93.20 143
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS_Test		84.16 80	83.20 87	87.05 47	91.56 108	69.82 40	89.99 233	92.05 130	77.77 92	82.84 77	86.57 223	63.93 86	96.09 129	74.91 153	89.18 99	95.25 69

APD-MVS		85.93 49	85.99 48	85.76 88	95.98 26	65.21 152	93.59 92	92.58 114	66.54 274	86.17 47	95.88 39	63.83 87	97.00 94	86.39 67	92.94 55	95.06 73
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mvs_anonymous		81.36 127	79.99 137	85.46 95	90.39 132	68.40 71	86.88 286	90.61 192	74.41 134	70.31 215	84.67 244	63.79 88	92.32 276	73.13 161	85.70 132	95.67 46

PVSNet_Blended_VisFu		83.97 83	83.50 77	85.39 98	90.02 138	66.59 121	93.77 84	91.73 147	77.43 101	77.08 140	89.81 177	63.77 89	96.97 100	79.67 116	88.21 106	92.60 160

baseline		85.01 64	84.44 68	86.71 56	88.33 181	68.73 64	90.24 224	91.82 145	81.05 44	81.18 90	92.50 126	63.69 90	96.08 132	84.45 83	86.71 125	95.32 61

myMVS_eth3d		72.58 266	72.74 244	72.10 334	87.87 195	49.45 351	88.07 266	89.01 258	72.91 167	63.11 293	88.10 200	63.63 91	85.54 344	32.73 376	69.23 259	81.32 336

CDPH-MVS		85.71 53	85.46 55	86.46 66	94.75 34	67.19 103	93.89 75	92.83 103	70.90 226	83.09 76	95.28 54	63.62 92	97.36 71	80.63 111	94.18 35	94.84 83

HyFIR lowres test		81.03 134	79.56 144	85.43 96	87.81 198	68.11 81	90.18 225	90.01 218	70.65 232	72.95 179	86.06 231	63.61 93	94.50 199	75.01 151	79.75 178	93.67 130

canonicalmvs		86.85 35	86.25 43	88.66 18	91.80 102	71.92 14	93.54 94	91.71 149	80.26 52	87.55 37	95.25 58	63.59 94	96.93 105	88.18 49	84.34 141	97.11 8

c3_l		76.83 210	75.47 206	80.93 231	85.02 252	64.18 182	90.39 218	88.11 289	71.66 205	66.65 266	81.64 279	63.58 95	92.56 266	69.31 201	62.86 307	86.04 274

SteuartSystems-ACMMP		86.82 37	86.90 37	86.58 62	90.42 130	66.38 124	96.09 17	93.87 59	77.73 93	84.01 71	95.66 43	63.39 96	97.94 40	87.40 57	93.55 48	95.42 53
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsmconf0.1_n		85.71 53	86.08 47	84.62 131	80.83 299	62.33 229	93.84 80	88.81 266	83.50 18	87.00 42	96.01 37	63.36 97	96.93 105	94.04 12	87.29 116	94.61 93

EI-MVSNet-Vis-set		83.77 88	83.67 74	84.06 149	92.79 77	63.56 200	91.76 166	94.81 27	79.65 61	77.87 128	94.09 94	63.35 98	97.90 42	79.35 119	79.36 181	90.74 198

UniMVSNet (Re)		77.58 196	76.78 188	79.98 250	84.11 267	60.80 257	91.76 166	93.17 90	76.56 113	69.93 222	84.78 243	63.32 99	92.36 274	64.89 246	62.51 312	86.78 257

PVSNet_BlendedMVS		83.38 94	83.43 81	83.22 171	93.76 49	67.53 96	94.06 63	93.61 71	79.13 71	81.00 94	85.14 238	63.19 100	97.29 76	87.08 61	73.91 227	84.83 297

PVSNet_Blended		86.73 38	86.86 38	86.31 73	93.76 49	67.53 96	96.33 16	93.61 71	82.34 27	81.00 94	93.08 113	63.19 100	97.29 76	87.08 61	91.38 78	94.13 112

PAPM_NR		82.97 102	81.84 110	86.37 70	94.10 44	66.76 116	87.66 275	92.84 102	69.96 240	74.07 169	93.57 106	63.10 102	97.50 64	70.66 188	90.58 88	94.85 80

nrg030		80.93 135	79.86 139	84.13 148	83.69 272	68.83 62	93.23 103	91.20 169	75.55 121	75.06 158	88.22 199	63.04 103	94.74 183	81.88 100	66.88 276	88.82 224

fmvsm_s_conf0.5_n		86.39 41	86.91 36	84.82 117	87.36 208	63.54 202	94.74 47	90.02 217	82.52 24	90.14 24	96.92 13	62.93 104	97.84 46	95.28 8	82.26 155	93.07 148

EI-MVSNet-UG-set		83.14 99	82.96 91	83.67 160	92.28 86	63.19 210	91.38 182	94.68 32	79.22 68	76.60 143	93.75 100	62.64 105	97.76 48	78.07 132	78.01 192	90.05 207

DeepC-MVS	77.85 3	85.52 57	85.24 57	86.37 70	88.80 169	66.64 118	92.15 143	93.68 69	81.07 43	76.91 141	93.64 104	62.59 106	98.44 31	85.50 72	92.84 57	94.03 118
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 66	84.88 63	84.69 126	91.30 115	62.36 228	93.85 77	92.04 131	79.45 62	79.33 112	94.28 90	62.42 107	96.35 121	80.05 114	91.25 81	95.38 56

fmvsm_s_conf0.5_n_a		85.75 52	86.09 46	84.72 124	85.73 240	63.58 199	93.79 83	89.32 241	81.42 39	90.21 22	96.91 14	62.41 108	97.67 51	94.48 10	80.56 172	92.90 154

CS-MVS		85.80 51	86.65 40	83.27 170	92.00 95	58.92 290	95.31 31	91.86 141	79.97 55	84.82 62	95.40 49	62.26 109	95.51 161	86.11 69	92.08 66	95.37 57

MVS_111021_HR		86.19 45	85.80 52	87.37 38	93.17 65	69.79 41	93.99 69	93.76 64	79.08 73	78.88 119	93.99 97	62.25 110	98.15 36	85.93 71	91.15 82	94.15 111

PHI-MVS		86.83 36	86.85 39	86.78 55	93.47 57	65.55 145	95.39 30	95.10 19	71.77 202	85.69 53	96.52 23	62.07 111	98.77 22	86.06 70	95.60 11	96.03 38

MP-MVS		85.02 63	84.97 62	85.17 108	92.60 82	64.27 179	93.24 102	92.27 121	73.13 161	79.63 108	94.43 80	61.90 112	97.17 83	85.00 77	92.56 59	94.06 117
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
jason		86.40 40	86.17 44	87.11 44	86.16 231	70.54 28	95.71 24	92.19 127	82.00 30	84.58 64	94.34 87	61.86 113	95.53 160	87.76 52	90.89 84	95.27 66
jason: jason.
fmvsm_s_conf0.1_n		85.61 56	85.93 49	84.68 127	82.95 283	63.48 204	94.03 68	89.46 235	81.69 33	89.86 25	96.74 20	61.85 114	97.75 49	94.74 9	82.01 159	92.81 156

iter_conf_final		81.74 122	80.93 122	84.18 146	92.66 80	69.10 55	92.94 113	82.80 341	79.01 76	74.85 160	88.40 191	61.83 115	94.61 189	79.36 118	76.52 209	88.83 221

CS-MVS-test		86.14 46	87.01 34	83.52 162	92.63 81	59.36 285	95.49 27	91.92 136	80.09 54	85.46 56	95.53 47	61.82 116	95.77 143	86.77 65	93.37 50	95.41 54

PAPR		85.15 62	84.47 67	87.18 42	96.02 25	68.29 74	91.85 161	93.00 98	76.59 112	79.03 115	95.00 63	61.59 117	97.61 58	78.16 131	89.00 100	95.63 48

IS-MVSNet		80.14 149	79.41 148	82.33 190	87.91 193	60.08 274	91.97 156	88.27 285	72.90 169	71.44 203	91.73 144	61.44 118	93.66 233	62.47 264	86.53 127	93.24 141

cl____		76.07 217	74.67 213	80.28 240	85.15 248	61.76 241	90.12 226	88.73 270	71.16 220	65.43 270	81.57 281	61.15 119	92.95 246	66.54 227	62.17 314	86.13 272

DIV-MVS_self_test		76.07 217	74.67 213	80.28 240	85.14 249	61.75 242	90.12 226	88.73 270	71.16 220	65.42 271	81.60 280	61.15 119	92.94 250	66.54 227	62.16 316	86.14 270

EI-MVSNet		78.97 169	78.22 164	81.25 218	85.33 244	62.73 223	89.53 242	93.21 86	72.39 181	72.14 193	90.13 173	60.99 121	94.72 184	67.73 216	72.49 238	86.29 265

IterMVS-LS		76.49 213	75.18 211	80.43 237	84.49 260	62.74 222	90.64 212	88.80 267	72.40 180	65.16 273	81.72 277	60.98 122	92.27 277	67.74 215	64.65 296	86.29 265
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 67	84.84 65	84.53 133	80.23 309	63.50 203	92.79 117	88.73 270	80.46 49	89.84 26	96.65 22	60.96 123	97.57 61	93.80 13	80.14 174	92.53 163

ETV-MVS		86.01 48	86.11 45	85.70 90	90.21 135	67.02 110	93.43 99	91.92 136	81.21 42	84.13 70	94.07 96	60.93 124	95.63 151	89.28 42	89.81 93	94.46 103

tpm cat1		75.30 233	72.21 252	84.58 132	88.52 172	67.77 88	78.16 348	88.02 291	61.88 314	68.45 241	76.37 336	60.65 125	94.03 221	53.77 302	74.11 224	91.93 179

TAMVS		80.37 144	79.45 147	83.13 173	85.14 249	63.37 205	91.23 191	90.76 186	74.81 132	72.65 183	88.49 188	60.63 126	92.95 246	69.41 199	81.95 160	93.08 147

ZNCC-MVS		85.33 59	85.08 60	86.06 76	93.09 68	65.65 141	93.89 75	93.41 82	73.75 150	79.94 104	94.68 74	60.61 127	98.03 38	82.63 95	93.72 44	94.52 99

thres100view900		78.37 183	77.01 185	82.46 185	91.89 100	63.21 209	91.19 195	96.33 1	72.28 184	70.45 212	87.89 205	60.31 128	95.32 165	45.16 336	77.58 197	88.83 221

thres600view7		78.00 188	76.66 190	82.03 205	91.93 97	63.69 195	91.30 188	96.33 1	72.43 179	70.46 211	87.89 205	60.31 128	94.92 179	42.64 348	76.64 207	87.48 242

CHOSEN 1792x2688		84.98 65	83.45 80	89.57 10	89.94 140	75.14 5	92.07 149	92.32 119	81.87 31	75.68 150	88.27 195	60.18 130	98.60 27	80.46 113	90.27 91	94.96 77

h-mvs33		83.01 101	82.56 101	84.35 141	89.34 152	62.02 235	92.72 120	93.76 64	81.45 36	82.73 79	92.25 136	60.11 131	97.13 87	87.69 53	62.96 306	93.91 123

hse-mvs2		81.12 132	81.11 120	81.16 221	86.52 223	57.48 307	89.40 245	91.16 171	81.45 36	82.73 79	90.49 163	60.11 131	94.58 191	87.69 53	60.41 333	91.41 186

tfpn200view9		78.79 175	77.43 176	82.88 176	92.21 89	64.49 165	92.05 150	96.28 4	73.48 156	71.75 198	88.26 196	60.07 133	95.32 165	45.16 336	77.58 197	88.83 221

thres400		78.68 177	77.43 176	82.43 186	92.21 89	64.49 165	92.05 150	96.28 4	73.48 156	71.75 198	88.26 196	60.07 133	95.32 165	45.16 336	77.58 197	87.48 242

diffmvs		84.28 75	83.83 73	85.61 92	87.40 206	68.02 83	90.88 203	89.24 244	80.54 47	81.64 86	92.52 125	59.83 135	94.52 198	87.32 58	85.11 135	94.29 104
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 69	82.86 95	90.06 2	90.93 121	74.56 6	87.91 270	95.54 12	68.55 258	72.35 192	94.71 73	59.78 136	98.90 19	81.29 108	94.69 31	96.74 13

thres200		79.66 157	78.33 161	83.66 161	92.54 83	65.82 139	93.06 107	96.31 3	74.90 131	73.30 176	88.66 186	59.67 137	95.61 153	47.84 325	78.67 188	89.56 216

Effi-MVS+		83.82 86	82.76 96	86.99 49	89.56 148	69.40 47	91.35 185	86.12 312	72.59 173	83.22 75	92.81 123	59.60 138	96.01 137	81.76 101	87.80 110	95.56 51

eth_miper_zixun_eth		75.96 224	74.40 221	80.66 233	84.66 256	63.02 213	89.28 247	88.27 285	71.88 196	65.73 268	81.65 278	59.45 139	92.81 254	68.13 210	60.53 330	86.14 270

ACMMP_NAP		86.05 47	85.80 52	86.80 54	91.58 107	67.53 96	91.79 163	93.49 78	74.93 130	84.61 63	95.30 53	59.42 140	97.92 41	86.13 68	94.92 19	94.94 79

GST-MVS		84.63 70	84.29 70	85.66 91	92.82 74	65.27 150	93.04 109	93.13 92	73.20 159	78.89 116	94.18 93	59.41 141	97.85 45	81.45 104	92.48 61	93.86 126

UA-Net		80.02 152	79.65 142	81.11 223	89.33 154	57.72 302	86.33 289	89.00 261	77.44 100	81.01 93	89.15 183	59.33 142	95.90 138	61.01 271	84.28 144	89.73 213

NR-MVSNet		76.05 220	74.59 216	80.44 236	82.96 281	62.18 233	90.83 205	91.73 147	77.12 103	60.96 307	86.35 225	59.28 143	91.80 286	60.74 272	61.34 325	87.35 247

MP-MVS-pluss		85.24 60	85.13 59	85.56 93	91.42 112	65.59 143	91.54 173	92.51 116	74.56 133	80.62 97	95.64 44	59.15 144	97.00 94	86.94 63	93.80 41	94.07 116
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		84.73 68	84.40 69	85.72 89	93.75 51	65.01 158	93.50 96	93.19 89	72.19 186	79.22 113	94.93 66	59.04 145	97.67 51	81.55 102	92.21 62	94.49 102

MSLP-MVS++		86.27 43	85.91 50	87.35 39	92.01 94	68.97 60	95.04 40	92.70 106	79.04 75	81.50 87	96.50 25	58.98 146	96.78 110	83.49 90	93.93 39	96.29 30

Patchmatch-test		65.86 312	60.94 326	80.62 235	83.75 271	58.83 291	58.91 385	75.26 361	44.50 375	50.95 353	77.09 330	58.81 147	87.90 327	35.13 368	64.03 301	95.12 72

EPNet_dtu		78.80 174	79.26 152	77.43 288	88.06 189	49.71 349	91.96 157	91.95 135	77.67 94	76.56 144	91.28 152	58.51 148	90.20 310	56.37 291	80.95 168	92.39 165
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmvis_n_1920		83.80 87	83.48 78	84.77 121	82.51 285	63.72 192	91.37 183	83.99 332	81.42 39	77.68 130	95.74 42	58.37 149	97.58 59	93.38 14	86.87 119	93.00 151

EC-MVSNet		84.53 71	85.04 61	83.01 174	89.34 152	61.37 249	94.42 51	91.09 176	77.91 90	83.24 74	94.20 92	58.37 149	95.40 162	85.35 73	91.41 77	92.27 173

VNet		86.20 44	85.65 54	87.84 27	93.92 46	69.99 33	95.73 23	95.94 7	78.43 83	86.00 49	93.07 114	58.22 151	97.00 94	85.22 74	84.33 142	96.52 20

TESTMET0.1,1		82.41 110	81.98 109	83.72 158	88.08 188	63.74 190	92.70 122	93.77 63	79.30 66	77.61 132	87.57 210	58.19 152	94.08 214	73.91 159	86.68 126	93.33 140

原ACMM1				84.42 137	93.21 63	64.27 179		93.40 83	65.39 282	79.51 109	92.50 126	58.11 153	96.69 112	65.27 244	93.96 38	92.32 168

sam_mvs1												57.85 154				94.68 88

CR-MVSNet		73.79 250	70.82 265	82.70 180	83.15 278	67.96 84	70.25 364	84.00 330	73.67 154	69.97 220	72.41 350	57.82 155	89.48 316	52.99 305	73.13 231	90.64 200

Patchmtry		67.53 304	63.93 311	78.34 276	82.12 290	64.38 173	68.72 368	84.00 330	48.23 367	59.24 315	72.41 350	57.82 155	89.27 317	46.10 333	56.68 345	81.36 335

patchmatchnet-post											67.62 365	57.62 157	90.25 305

PCF-MVS	73.15 9	79.29 163	77.63 173	84.29 143	86.06 232	65.96 135	87.03 282	91.10 175	69.86 242	69.79 223	90.64 158	57.54 158	96.59 114	64.37 249	82.29 154	90.32 203
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Fast-Effi-MVS+		81.14 130	80.01 136	84.51 135	90.24 134	65.86 137	94.12 62	89.15 250	73.81 149	75.37 156	88.26 196	57.26 159	94.53 197	66.97 224	84.92 136	93.15 144

miper_lstm_enhance		73.05 255	71.73 258	77.03 294	83.80 270	58.32 296	81.76 318	88.88 263	69.80 243	61.01 306	78.23 320	57.19 160	87.51 335	65.34 243	59.53 335	85.27 293

PatchT		69.11 289	65.37 301	80.32 238	82.07 291	63.68 196	67.96 373	87.62 296	50.86 359	69.37 224	65.18 368	57.09 161	88.53 322	41.59 351	66.60 278	88.74 225

testdata				81.34 217	89.02 163	57.72 302		89.84 222	58.65 333	85.32 58	94.09 94	57.03 162	93.28 239	69.34 200	90.56 89	93.03 149

PatchmatchNet		77.46 197	74.63 215	85.96 79	89.55 149	70.35 30	79.97 339	89.55 233	72.23 185	70.94 205	76.91 332	57.03 162	92.79 256	54.27 299	81.17 166	94.74 86
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_yl		84.28 75	83.16 88	87.64 30	94.52 37	69.24 52	95.78 18	95.09 20	69.19 250	81.09 91	92.88 120	57.00 164	97.44 66	81.11 109	81.76 161	96.23 33

DCV-MVSNet		84.28 75	83.16 88	87.64 30	94.52 37	69.24 52	95.78 18	95.09 20	69.19 250	81.09 91	92.88 120	57.00 164	97.44 66	81.11 109	81.76 161	96.23 33

region2R		84.36 73	84.03 72	85.36 100	93.54 55	64.31 177	93.43 99	92.95 99	72.16 189	78.86 120	94.84 70	56.97 166	97.53 63	81.38 106	92.11 65	94.24 106

新几何1				84.73 123	92.32 85	64.28 178		91.46 161	59.56 329	79.77 106	92.90 118	56.95 167	96.57 116	63.40 254	92.91 56	93.34 138

WR-MVS		76.76 211	75.74 203	79.82 256	84.60 257	62.27 232	92.60 129	92.51 116	76.06 116	67.87 250	85.34 236	56.76 168	90.24 308	62.20 265	63.69 305	86.94 255

HPM-MVS		83.25 97	82.95 92	84.17 147	92.25 87	62.88 220	90.91 200	91.86 141	70.30 236	77.12 138	93.96 98	56.75 169	96.28 123	82.04 99	91.34 80	93.34 138
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		82.71 107	82.38 104	83.73 157	89.25 156	59.58 280	92.24 140	94.89 24	77.96 88	79.86 105	92.38 131	56.70 170	97.05 89	77.26 136	80.86 169	94.55 95

ACMMPR		84.37 72	84.06 71	85.28 103	93.56 54	64.37 174	93.50 96	93.15 91	72.19 186	78.85 121	94.86 69	56.69 171	97.45 65	81.55 102	92.20 63	94.02 119

FMVSNet3		77.73 194	76.04 198	82.80 177	91.20 118	68.99 59	91.87 159	91.99 133	73.35 158	67.04 260	83.19 261	56.62 172	92.14 278	59.80 279	69.34 256	87.28 249

Patchmatch-RL test		68.17 298	64.49 308	79.19 267	71.22 363	53.93 330	70.07 366	71.54 372	69.22 249	56.79 331	62.89 372	56.58 173	88.61 319	69.53 198	52.61 355	95.03 76

test_post											23.01 395	56.49 174	92.67 261

RPMNet		70.42 278	65.68 297	84.63 130	83.15 278	67.96 84	70.25 364	90.45 194	46.83 370	69.97 220	65.10 369	56.48 175	95.30 168	35.79 367	73.13 231	90.64 200

DU-MVS		76.86 206	75.84 201	79.91 253	82.96 281	60.26 270	91.26 189	91.54 156	76.46 114	68.88 233	86.35 225	56.16 176	92.13 279	66.38 230	62.55 310	87.35 247

Baseline_NR-MVSNet		73.99 247	72.83 242	77.48 287	80.78 300	59.29 286	91.79 163	84.55 325	68.85 254	68.99 231	80.70 295	56.16 176	92.04 282	62.67 262	60.98 327	81.11 338

API-MVS		82.28 112	80.53 130	87.54 35	96.13 22	70.59 27	93.63 90	91.04 182	65.72 281	75.45 155	92.83 122	56.11 178	98.89 20	64.10 250	89.75 96	93.15 144

MTAPA		83.91 84	83.38 85	85.50 94	91.89 100	65.16 154	81.75 319	92.23 122	75.32 125	80.53 98	95.21 60	56.06 179	97.16 85	84.86 80	92.55 60	94.18 108

JIA-IIPM		66.06 311	62.45 320	76.88 298	81.42 296	54.45 329	57.49 386	88.67 273	49.36 363	63.86 286	46.86 384	56.06 179	90.25 305	49.53 315	68.83 262	85.95 277

v148		76.19 215	74.47 220	81.36 216	80.05 311	64.44 169	91.75 168	90.23 208	73.68 153	67.13 259	80.84 294	55.92 181	93.86 230	68.95 205	61.73 321	85.76 283

WR-MVS_H		70.59 276	69.94 272	72.53 328	81.03 297	51.43 340	87.35 279	92.03 132	67.38 268	60.23 311	80.70 295	55.84 182	83.45 358	46.33 332	58.58 340	82.72 322

test_fmvsmconf0.01_n		83.70 91	83.52 75	84.25 145	75.26 351	61.72 243	92.17 142	87.24 301	82.36 26	84.91 61	95.41 48	55.60 183	96.83 109	92.85 17	85.87 131	94.21 107

AUN-MVS		78.37 183	77.43 176	81.17 220	86.60 222	57.45 308	89.46 244	91.16 171	74.11 140	74.40 164	90.49 163	55.52 184	94.57 193	74.73 156	60.43 332	91.48 184

XVS		83.87 85	83.47 79	85.05 109	93.22 61	63.78 188	92.92 114	92.66 109	73.99 142	78.18 125	94.31 89	55.25 185	97.41 68	79.16 121	91.58 74	93.95 121

X-MVStestdata		76.86 206	74.13 226	85.05 109	93.22 61	63.78 188	92.92 114	92.66 109	73.99 142	78.18 125	10.19 400	55.25 185	97.41 68	79.16 121	91.58 74	93.95 121

BH-w/o		80.49 142	79.30 151	84.05 150	90.83 125	64.36 176	93.60 91	89.42 238	74.35 136	69.09 227	90.15 172	55.23 187	95.61 153	64.61 247	86.43 129	92.17 176

CP-MVS		83.71 90	83.40 84	84.65 128	93.14 66	63.84 186	94.59 49	92.28 120	71.03 224	77.41 134	94.92 67	55.21 188	96.19 125	81.32 107	90.70 86	93.91 123

PGM-MVS		83.25 97	82.70 98	84.92 113	92.81 76	64.07 183	90.44 215	92.20 126	71.28 218	77.23 137	94.43 80	55.17 189	97.31 75	79.33 120	91.38 78	93.37 137

tpmvs		72.88 259	69.76 275	82.22 195	90.98 120	67.05 108	78.22 347	88.30 283	63.10 302	64.35 284	74.98 343	55.09 190	94.27 206	43.25 342	69.57 255	85.34 291

v8		75.35 232	73.26 237	81.61 211	80.67 302	66.82 113	89.54 241	89.27 243	71.65 206	63.30 292	80.30 303	54.99 191	94.06 216	67.33 220	62.33 313	83.94 303

sam_mvs												54.91 192

EPMVS		78.49 182	75.98 199	86.02 77	91.21 117	69.68 45	80.23 334	91.20 169	75.25 126	72.48 188	78.11 321	54.65 193	93.69 232	57.66 288	83.04 150	94.69 87

ab-mvs		80.18 148	78.31 162	85.80 86	88.44 176	65.49 148	83.00 313	92.67 108	71.82 200	77.36 135	85.01 239	54.50 194	96.59 114	76.35 141	75.63 214	95.32 61

KD-MVS_2432*1600		69.03 290	66.37 293	77.01 295	85.56 242	61.06 253	81.44 323	90.25 206	67.27 269	58.00 325	76.53 334	54.49 195	87.63 333	48.04 322	35.77 382	82.34 328

miper_refine_blended		69.03 290	66.37 293	77.01 295	85.56 242	61.06 253	81.44 323	90.25 206	67.27 269	58.00 325	76.53 334	54.49 195	87.63 333	48.04 322	35.77 382	82.34 328

DP-MVS Recon		82.73 105	81.65 112	85.98 78	97.31 4	67.06 107	95.15 36	91.99 133	69.08 253	76.50 145	93.89 99	54.48 197	98.20 35	70.76 186	85.66 133	92.69 157

GeoE		78.90 171	77.43 176	83.29 169	88.95 165	62.02 235	92.31 137	86.23 310	70.24 237	71.34 204	89.27 181	54.43 198	94.04 219	63.31 256	80.81 171	93.81 128

XXY-MVS		77.94 191	76.44 192	82.43 186	82.60 284	64.44 169	92.01 152	91.83 144	73.59 155	70.00 219	85.82 233	54.43 198	94.76 181	69.63 196	68.02 269	88.10 237

MDTV_nov1_ep13_2view						59.90 276	80.13 336		67.65 266	72.79 181		54.33 200		59.83 278		92.58 161

Test By Simon												54.21 201

MAR-MVS		84.18 79	83.43 81	86.44 67	96.25 21	65.93 136	94.28 55	94.27 51	74.41 134	79.16 114	95.61 45	53.99 202	98.88 21	69.62 197	93.26 52	94.50 101
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		80.10 150	79.56 144	81.72 209	86.93 219	61.17 250	92.70 122	91.54 156	71.51 215	75.62 151	86.94 219	53.83 203	92.38 272	72.21 173	84.76 139	91.60 181

test0.0.03 1		72.76 260	72.71 246	72.88 326	80.25 308	47.99 357	91.22 192	89.45 236	71.51 215	62.51 301	87.66 208	53.83 203	85.06 348	50.16 312	67.84 272	85.58 284

v2v482		77.42 198	75.65 205	82.73 179	80.38 305	67.13 106	91.85 161	90.23 208	75.09 128	69.37 224	83.39 259	53.79 205	94.44 200	71.77 177	65.00 291	86.63 261

SR-MVS		82.81 104	82.58 100	83.50 165	93.35 58	61.16 252	92.23 141	91.28 168	64.48 288	81.27 88	95.28 54	53.71 206	95.86 139	82.87 93	88.77 102	93.49 135

pcd_1.5k_mvsjas		4.46 371	5.95 374	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	53.55 207	0.00 405	0.00 404	0.00 402	0.00 401

PS-MVSNAJss		77.26 200	76.31 194	80.13 245	80.64 303	59.16 287	90.63 214	91.06 180	72.80 170	68.58 239	84.57 246	53.55 207	93.96 224	72.97 162	71.96 242	87.27 250

PS-MVSNAJ		88.14 16	87.61 27	89.71 6	92.06 91	76.72 1	95.75 20	93.26 85	83.86 14	89.55 29	96.06 36	53.55 207	97.89 43	91.10 31	93.31 51	94.54 97

mPP-MVS		82.96 103	82.44 103	84.52 134	92.83 72	62.92 218	92.76 118	91.85 143	71.52 214	75.61 153	94.24 91	53.48 210	96.99 97	78.97 124	90.73 85	93.64 132

xiu_mvs_v2_base		87.92 21	87.38 31	89.55 11	91.41 114	76.43 3	95.74 21	93.12 93	83.53 17	89.55 29	95.95 38	53.45 211	97.68 50	91.07 32	92.62 58	94.54 97

test_post1							78.95 341				20.70 398	53.05 212	91.50 297	60.43 274

MDTV_nov1_ep13			72.61 247		89.06 162	68.48 69	80.33 332	90.11 212	71.84 199	71.81 197	75.92 340	53.01 213	93.92 226	48.04 322	73.38 229

FA-MVS(test-final)		79.12 166	77.23 182	84.81 120	90.54 128	63.98 185	81.35 325	91.71 149	71.09 223	74.85 160	82.94 262	52.85 214	97.05 89	67.97 212	81.73 163	93.41 136

test222					89.77 143	61.60 245	89.55 240	89.42 238	56.83 342	77.28 136	92.43 130	52.76 215			91.14 83	93.09 146

v1144		76.73 212	74.88 212	82.27 192	80.23 309	66.60 120	91.68 170	90.21 210	73.69 152	69.06 229	81.89 274	52.73 216	94.40 201	69.21 202	65.23 288	85.80 280

v10		74.77 239	72.54 249	81.46 214	80.33 307	66.71 117	89.15 251	89.08 255	70.94 225	63.08 295	79.86 308	52.52 217	94.04 219	65.70 238	62.17 314	83.64 306

CLD-MVS		82.73 105	82.35 105	83.86 153	87.90 194	67.65 92	95.45 28	92.18 128	85.06 10	72.58 185	92.27 134	52.46 218	95.78 141	84.18 84	79.06 184	88.16 236
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		75.86 225	74.52 219	79.89 254	82.44 286	60.64 266	91.37 183	91.37 163	76.63 111	67.65 252	86.21 229	52.37 219	91.55 292	61.84 267	60.81 328	87.48 242

VPA-MVSNet		79.03 167	78.00 167	82.11 203	85.95 234	64.48 167	93.22 104	94.66 33	75.05 129	74.04 170	84.95 240	52.17 220	93.52 235	74.90 154	67.04 275	88.32 235

APD-MVS_3200maxsize		81.64 124	81.32 115	82.59 184	92.36 84	58.74 292	91.39 180	91.01 183	63.35 297	79.72 107	94.62 76	51.82 221	96.14 127	79.71 115	87.93 109	92.89 155

dp		75.01 237	72.09 253	83.76 154	89.28 155	66.22 130	79.96 340	89.75 225	71.16 220	67.80 251	77.19 329	51.81 222	92.54 267	50.39 310	71.44 247	92.51 164

v144192		76.05 220	74.03 227	82.12 200	79.50 317	66.55 122	91.39 180	89.71 231	72.30 183	68.17 242	81.33 286	51.75 223	94.03 221	67.94 213	64.19 298	85.77 281

BH-untuned		78.68 177	77.08 183	83.48 166	89.84 141	63.74 190	92.70 122	88.59 276	71.57 212	66.83 264	88.65 187	51.75 223	95.39 163	59.03 282	84.77 138	91.32 190

HQP2-MVS												51.63 225

HQP-MVS		81.14 130	80.64 127	82.64 182	87.54 202	63.66 197	94.06 63	91.70 151	79.80 57	74.18 165	90.30 167	51.63 225	95.61 153	77.63 134	78.90 185	88.63 226

dmvs_testset		65.55 315	66.45 291	62.86 357	79.87 312	22.35 400	76.55 352	71.74 370	77.42 102	55.85 333	87.77 207	51.39 227	80.69 372	31.51 382	65.92 283	85.55 286

V42		76.46 214	74.55 218	82.19 197	79.14 323	67.82 87	90.26 223	89.42 238	73.75 150	68.63 238	81.89 274	51.31 228	94.09 213	71.69 179	64.84 292	84.66 298

SR-MVS-dyc-post		81.06 133	80.70 125	82.15 198	92.02 92	58.56 294	90.90 201	90.45 194	62.76 304	78.89 116	94.46 78	51.26 229	95.61 153	78.77 127	86.77 123	92.28 170

CL-MVSNet_self_test		69.92 282	68.09 286	75.41 306	73.25 358	55.90 320	90.05 229	89.90 220	69.96 240	61.96 304	76.54 333	51.05 230	87.64 332	49.51 316	50.59 360	82.70 324

TransMVSNet (Re)		70.07 281	67.66 287	77.31 291	80.62 304	59.13 289	91.78 165	84.94 322	65.97 278	60.08 312	80.44 300	50.78 231	91.87 284	48.84 318	45.46 368	80.94 340

HQP_MVS		80.34 145	79.75 141	82.12 200	86.94 217	62.42 226	93.13 105	91.31 165	78.81 79	72.53 186	89.14 184	50.66 232	95.55 158	76.74 137	78.53 190	88.39 233

plane_prior6					87.23 209	62.32 230						50.66 232

ACMMP		81.49 125	80.67 126	83.93 152	91.71 104	62.90 219	92.13 144	92.22 125	71.79 201	71.68 200	93.49 108	50.32 234	96.96 101	78.47 129	84.22 146	91.93 179
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		82.02 118	81.52 113	83.51 164	88.42 177	62.88 220	89.77 237	88.93 262	76.78 108	75.55 154	93.10 111	50.31 235	95.38 164	83.82 89	87.02 118	92.26 174

1314		80.70 138	78.95 155	85.94 80	87.77 200	67.56 94	87.91 270	92.55 115	72.17 188	67.44 254	93.09 112	50.27 236	97.04 92	71.68 180	87.64 112	93.23 142

CP-MVSNet		70.50 277	69.91 273	72.26 331	80.71 301	51.00 343	87.23 281	90.30 204	67.84 263	59.64 313	82.69 265	50.23 237	82.30 366	51.28 307	59.28 336	83.46 311

LCM-MVSNet-Re		72.93 257	71.84 256	76.18 303	88.49 173	48.02 356	80.07 337	70.17 373	73.96 145	52.25 346	80.09 307	49.98 238	88.24 325	67.35 218	84.23 145	92.28 170

Vis-MVSNet		80.92 136	79.98 138	83.74 155	88.48 174	61.80 239	93.44 98	88.26 287	73.96 145	77.73 129	91.76 142	49.94 239	94.76 181	65.84 236	90.37 90	94.65 91
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v1192		75.98 222	73.92 229	82.15 198	79.73 313	66.24 129	91.22 192	89.75 225	72.67 172	68.49 240	81.42 284	49.86 240	94.27 206	67.08 222	65.02 290	85.95 277

test-mter		79.96 153	79.38 150	81.72 209	86.93 219	61.17 250	92.70 122	91.54 156	73.85 147	75.62 151	86.94 219	49.84 241	92.38 272	72.21 173	84.76 139	91.60 181

cdsmvs_eth3d_5k		19.86 366	26.47 365	0.00 386	0.00 408	0.00 411	0.00 397	93.45 79	0.00 404	0.00 405	95.27 56	49.56 242	0.00 405	0.00 404	0.00 402	0.00 401

3Dnovator+	73.60 7	82.10 117	80.60 129	86.60 60	90.89 123	66.80 115	95.20 34	93.44 80	74.05 141	67.42 255	92.49 128	49.46 243	97.65 55	70.80 185	91.68 72	95.33 59

MVP-Stereo		77.12 203	76.23 195	79.79 257	81.72 293	66.34 126	89.29 246	90.88 184	70.56 234	62.01 303	82.88 263	49.34 244	94.13 211	65.55 241	93.80 41	78.88 358
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
RE-MVS-def			80.48 131		92.02 92	58.56 294	90.90 201	90.45 194	62.76 304	78.89 116	94.46 78	49.30 245		78.77 127	86.77 123	92.28 170

OMC-MVS		78.67 179	77.91 170	80.95 230	85.76 239	57.40 309	88.49 261	88.67 273	73.85 147	72.43 190	92.10 137	49.29 246	94.55 196	72.73 167	77.89 193	90.91 197

VPNet		78.82 173	77.53 175	82.70 180	84.52 259	66.44 123	93.93 72	92.23 122	80.46 49	72.60 184	88.38 193	49.18 247	93.13 241	72.47 171	63.97 303	88.55 229

CVMVSNet		74.04 246	74.27 223	73.33 322	85.33 244	43.94 372	89.53 242	88.39 280	54.33 350	70.37 213	90.13 173	49.17 248	84.05 352	61.83 268	79.36 181	91.99 178

v1921920		75.63 230	73.49 235	82.06 204	79.38 318	66.35 125	91.07 199	89.48 234	71.98 191	67.99 243	81.22 289	49.16 249	93.90 227	66.56 226	64.56 297	85.92 279

pm-mvs1		72.89 258	71.09 262	78.26 279	79.10 324	57.62 305	90.80 206	89.30 242	67.66 265	62.91 297	81.78 276	49.11 250	92.95 246	60.29 276	58.89 338	84.22 301

pmmvs4		73.92 248	71.81 257	80.25 242	79.17 321	65.24 151	87.43 278	87.26 300	67.64 267	63.46 290	83.91 254	48.96 251	91.53 296	62.94 259	65.49 284	83.96 302

TAPA-MVS	70.22 12	74.94 238	73.53 234	79.17 268	90.40 131	52.07 337	89.19 250	89.61 232	62.69 306	70.07 217	92.67 124	48.89 252	94.32 202	38.26 362	79.97 175	91.12 195
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
3Dnovator	73.91 6	82.69 108	80.82 123	88.31 23	89.57 147	71.26 18	92.60 129	94.39 46	78.84 78	67.89 249	92.48 129	48.42 253	98.52 28	68.80 207	94.40 34	95.15 71

CPTT-MVS		79.59 158	79.16 153	80.89 232	91.54 110	59.80 277	92.10 146	88.54 278	60.42 322	72.96 178	93.28 110	48.27 254	92.80 255	78.89 126	86.50 128	90.06 206

GBi-Net		75.65 228	73.83 230	81.10 224	88.85 166	65.11 155	90.01 230	90.32 200	70.84 227	67.04 260	80.25 304	48.03 255	91.54 293	59.80 279	69.34 256	86.64 258

test1		75.65 228	73.83 230	81.10 224	88.85 166	65.11 155	90.01 230	90.32 200	70.84 227	67.04 260	80.25 304	48.03 255	91.54 293	59.80 279	69.34 256	86.64 258

FMVSNet2		76.07 217	74.01 228	82.26 194	88.85 166	67.66 91	91.33 186	91.61 154	70.84 227	65.98 267	82.25 270	48.03 255	92.00 283	58.46 284	68.73 264	87.10 252

LFMVS		84.34 74	82.73 97	89.18 12	94.76 33	73.25 9	94.99 42	91.89 139	71.90 194	82.16 83	93.49 108	47.98 258	97.05 89	82.55 96	84.82 137	97.25 7

SDMVSNet		80.26 146	78.88 156	84.40 138	89.25 156	67.63 93	85.35 292	93.02 95	76.77 109	70.84 207	87.12 217	47.95 259	96.09 129	85.04 76	74.55 218	89.48 217

QAPM		79.95 154	77.39 180	87.64 30	89.63 146	71.41 17	93.30 101	93.70 68	65.34 284	67.39 257	91.75 143	47.83 260	98.96 16	57.71 287	89.81 93	92.54 162

HPM-MVS_fast		80.25 147	79.55 146	82.33 190	91.55 109	59.95 275	91.32 187	89.16 249	65.23 285	74.71 162	93.07 114	47.81 261	95.74 144	74.87 155	88.23 105	91.31 191

CANet_DTU		84.09 81	83.52 75	85.81 85	90.30 133	66.82 113	91.87 159	89.01 258	85.27 9	86.09 48	93.74 101	47.71 262	96.98 98	77.90 133	89.78 95	93.65 131

v1240		75.21 235	72.98 240	81.88 206	79.20 320	66.00 133	90.75 208	89.11 253	71.63 210	67.41 256	81.22 289	47.36 263	93.87 228	65.46 242	64.72 295	85.77 281

PEN-MVS		69.46 287	68.56 281	72.17 333	79.27 319	49.71 349	86.90 285	89.24 244	67.24 272	59.08 318	82.51 268	47.23 264	83.54 357	48.42 320	57.12 341	83.25 314

dmvs_re		76.93 205	75.36 208	81.61 211	87.78 199	60.71 263	80.00 338	87.99 292	79.42 63	69.02 230	89.47 180	46.77 265	94.32 202	63.38 255	74.45 221	89.81 210

CNLPA		74.31 243	72.30 251	80.32 238	91.49 111	61.66 244	90.85 204	80.72 347	56.67 343	63.85 287	90.64 158	46.75 266	90.84 300	53.79 301	75.99 213	88.47 232

114514_t		79.17 165	77.67 171	83.68 159	95.32 29	65.53 146	92.85 116	91.60 155	63.49 295	67.92 246	90.63 160	46.65 267	95.72 149	67.01 223	83.54 147	89.79 211

PS-CasMVS		69.86 284	69.13 279	72.07 335	80.35 306	50.57 345	87.02 283	89.75 225	67.27 269	59.19 317	82.28 269	46.58 268	82.24 367	50.69 309	59.02 337	83.39 313

DTE-MVSNet		68.46 296	67.33 289	71.87 337	77.94 339	49.00 354	86.16 290	88.58 277	66.36 276	58.19 322	82.21 271	46.36 269	83.87 355	44.97 339	55.17 348	82.73 321

test1111		80.84 137	80.02 135	83.33 168	87.87 195	60.76 260	92.62 127	86.86 304	77.86 91	75.73 149	91.39 150	46.35 270	94.70 187	72.79 166	88.68 103	94.52 99

ECVR-MVS		81.29 128	80.38 133	84.01 151	88.39 179	61.96 237	92.56 134	86.79 305	77.66 95	76.63 142	91.42 148	46.34 271	95.24 169	74.36 157	89.23 97	94.85 80

PMMVS		81.98 119	82.04 107	81.78 207	89.76 144	56.17 317	91.13 196	90.69 187	77.96 88	80.09 103	93.57 106	46.33 272	94.99 175	81.41 105	87.46 114	94.17 109

OPM-MVS		79.00 168	78.09 165	81.73 208	83.52 275	63.83 187	91.64 172	90.30 204	76.36 115	71.97 195	89.93 176	46.30 273	95.17 171	75.10 149	77.70 195	86.19 269
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BH-RMVSNet		79.46 162	77.65 172	84.89 114	91.68 105	65.66 140	93.55 93	88.09 290	72.93 166	73.37 175	91.12 154	46.20 274	96.12 128	56.28 292	85.61 134	92.91 153

mvsmamba		76.85 208	75.71 204	80.25 242	83.07 280	59.16 287	91.44 174	80.64 348	76.84 106	67.95 245	86.33 227	46.17 275	94.24 209	76.06 142	72.92 234	87.36 246

FE-MVS		75.97 223	73.02 239	84.82 117	89.78 142	65.56 144	77.44 350	91.07 179	64.55 287	72.66 182	79.85 309	46.05 276	96.69 112	54.97 296	80.82 170	92.21 175

TR-MVS		78.77 176	77.37 181	82.95 175	90.49 129	60.88 256	93.67 88	90.07 213	70.08 239	74.51 163	91.37 151	45.69 277	95.70 150	60.12 277	80.32 173	92.29 169

IterMVS-SCA-FT		71.55 272	69.97 271	76.32 301	81.48 294	60.67 265	87.64 276	85.99 313	66.17 277	59.50 314	78.88 315	45.53 278	83.65 356	62.58 263	61.93 317	84.63 300

SCA		75.82 226	72.76 243	85.01 111	86.63 221	70.08 32	81.06 327	89.19 247	71.60 211	70.01 218	77.09 330	45.53 278	90.25 305	60.43 274	73.27 230	94.68 88

IterMVS		72.65 265	70.83 263	78.09 281	82.17 289	62.96 215	87.64 276	86.28 308	71.56 213	60.44 309	78.85 316	45.42 280	86.66 339	63.30 257	61.83 318	84.65 299
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Syy-MVS		69.65 285	69.52 277	70.03 341	87.87 195	43.21 374	88.07 266	89.01 258	72.91 167	63.11 293	88.10 200	45.28 281	85.54 344	22.07 387	69.23 259	81.32 336

WB-MVSnew		77.14 202	76.18 197	80.01 249	86.18 230	63.24 208	91.26 189	94.11 55	71.72 204	73.52 174	87.29 215	45.14 282	93.00 244	56.98 289	79.42 179	83.80 305

Effi-MVS+-dtu		76.14 216	75.28 210	78.72 274	83.22 277	55.17 324	89.87 234	87.78 295	75.42 123	67.98 244	81.43 283	45.08 283	92.52 268	75.08 150	71.63 243	88.48 230

XVG-OURS-SEG-HR		74.70 240	73.08 238	79.57 262	78.25 335	57.33 310	80.49 330	87.32 298	63.22 299	68.76 236	90.12 175	44.89 284	91.59 291	70.55 189	74.09 225	89.79 211

v7n		71.31 273	68.65 280	79.28 266	76.40 347	60.77 259	86.71 287	89.45 236	64.17 290	58.77 321	78.24 319	44.59 285	93.54 234	57.76 286	61.75 320	83.52 309

pmmvs5		73.35 252	71.52 259	78.86 272	78.64 331	60.61 267	91.08 197	86.90 302	67.69 264	63.32 291	83.64 255	44.33 286	90.53 302	62.04 266	66.02 282	85.46 288

OpenMVS	70.45 11	78.54 181	75.92 200	86.41 69	85.93 237	71.68 16	92.74 119	92.51 116	66.49 275	64.56 279	91.96 139	43.88 287	98.10 37	54.61 297	90.65 87	89.44 219

AdaColmap		78.94 170	77.00 186	84.76 122	96.34 17	65.86 137	92.66 126	87.97 294	62.18 309	70.56 209	92.37 132	43.53 288	97.35 72	64.50 248	82.86 151	91.05 196

tfpnnormal		70.10 280	67.36 288	78.32 277	83.45 276	60.97 255	88.85 255	92.77 104	64.85 286	60.83 308	78.53 317	43.52 289	93.48 236	31.73 379	61.70 322	80.52 345

mvsany_test1		68.77 292	68.56 281	69.39 343	73.57 357	45.88 368	80.93 328	60.88 386	59.65 328	71.56 201	90.26 169	43.22 290	75.05 376	74.26 158	62.70 309	87.25 251

test_djsdf		73.76 251	72.56 248	77.39 289	77.00 345	53.93 330	89.07 252	90.69 187	65.80 279	63.92 285	82.03 273	43.14 291	92.67 261	72.83 164	68.53 265	85.57 285

GA-MVS		78.33 185	76.23 195	84.65 128	83.65 273	66.30 127	91.44 174	90.14 211	76.01 117	70.32 214	84.02 252	42.50 292	94.72 184	70.98 183	77.00 205	92.94 152

PLC	68.80 14	75.23 234	73.68 233	79.86 255	92.93 70	58.68 293	90.64 212	88.30 283	60.90 319	64.43 283	90.53 161	42.38 293	94.57 193	56.52 290	76.54 208	86.33 264
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
D2MVS		73.80 249	72.02 254	79.15 270	79.15 322	62.97 214	88.58 260	90.07 213	72.94 165	59.22 316	78.30 318	42.31 294	92.70 260	65.59 240	72.00 241	81.79 333

Fast-Effi-MVS+-dtu		75.04 236	73.37 236	80.07 246	80.86 298	59.52 281	91.20 194	85.38 317	71.90 194	65.20 272	84.84 242	41.46 295	92.97 245	66.50 229	72.96 233	87.73 239

sd_testset		77.08 204	75.37 207	82.20 196	89.25 156	62.11 234	82.06 317	89.09 254	76.77 109	70.84 207	87.12 217	41.43 296	95.01 174	67.23 221	74.55 218	89.48 217

MS-PatchMatch		77.90 193	76.50 191	82.12 200	85.99 233	69.95 36	91.75 168	92.70 106	73.97 144	62.58 300	84.44 248	41.11 297	95.78 141	63.76 253	92.17 64	80.62 344

our_test_3		68.29 297	64.69 305	79.11 271	78.92 325	64.85 162	88.40 263	85.06 320	60.32 324	52.68 344	76.12 338	40.81 298	89.80 315	44.25 341	55.65 346	82.67 326

XVG-OURS		74.25 244	72.46 250	79.63 260	78.45 333	57.59 306	80.33 332	87.39 297	63.86 292	68.76 236	89.62 179	40.50 299	91.72 288	69.00 204	74.25 223	89.58 214

VDD-MVS		83.06 100	81.81 111	86.81 53	90.86 124	67.70 90	95.40 29	91.50 159	75.46 122	81.78 85	92.34 133	40.09 300	97.13 87	86.85 64	82.04 158	95.60 49

DP-MVS		69.90 283	66.48 290	80.14 244	95.36 28	62.93 216	89.56 239	76.11 355	50.27 361	57.69 328	85.23 237	39.68 301	95.73 145	33.35 372	71.05 249	81.78 334

RRT_MVS		74.44 241	72.97 241	78.84 273	82.36 287	57.66 304	89.83 236	88.79 269	70.61 233	64.58 278	84.89 241	39.24 302	92.65 264	70.11 192	66.34 280	86.21 268

ppachtmachnet_test		67.72 301	63.70 312	79.77 258	78.92 325	66.04 132	88.68 258	82.90 340	60.11 326	55.45 334	75.96 339	39.19 303	90.55 301	39.53 357	52.55 356	82.71 323

ADS-MVSNet2		66.90 307	63.44 314	77.26 292	88.06 189	60.70 264	68.01 371	75.56 359	57.57 335	64.48 280	69.87 360	38.68 304	84.10 351	40.87 353	67.89 270	86.97 253

ADS-MVSNet		68.54 295	64.38 310	81.03 228	88.06 189	66.90 112	68.01 371	84.02 329	57.57 335	64.48 280	69.87 360	38.68 304	89.21 318	40.87 353	67.89 270	86.97 253

test_cas_vis1_n_1920		80.45 143	80.61 128	79.97 252	78.25 335	57.01 313	94.04 67	88.33 282	79.06 74	82.81 78	93.70 102	38.65 306	91.63 290	90.82 35	79.81 176	91.27 193

LPG-MVS_test		75.82 226	74.58 217	79.56 263	84.31 264	59.37 283	90.44 215	89.73 228	69.49 245	64.86 274	88.42 189	38.65 306	94.30 204	72.56 169	72.76 235	85.01 295

LGP-MVS_train				79.56 263	84.31 264	59.37 283		89.73 228	69.49 245	64.86 274	88.42 189	38.65 306	94.30 204	72.56 169	72.76 235	85.01 295

VDDNet		80.50 141	78.26 163	87.21 41	86.19 229	69.79 41	94.48 50	91.31 165	60.42 322	79.34 111	90.91 156	38.48 309	96.56 117	82.16 97	81.05 167	95.27 66

ACMP	71.68 10	75.58 231	74.23 224	79.62 261	84.97 253	59.64 278	90.80 206	89.07 256	70.39 235	62.95 296	87.30 214	38.28 310	93.87 228	72.89 163	71.45 246	85.36 290
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n_1920		81.66 123	82.01 108	80.64 234	82.24 288	55.09 325	94.76 46	86.87 303	81.67 34	84.40 66	94.63 75	38.17 311	94.67 188	91.98 26	83.34 148	92.16 177

UGNet		79.87 155	78.68 157	83.45 167	89.96 139	61.51 246	92.13 144	90.79 185	76.83 107	78.85 121	86.33 227	38.16 312	96.17 126	67.93 214	87.17 117	92.67 158
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		71.14 274	69.37 278	76.45 300	72.95 359	54.71 327	84.19 298	88.88 263	61.92 313	62.15 302	79.77 310	38.14 313	91.44 298	68.90 206	67.45 273	83.21 315

xiu_mvs_v1_base_debu		82.16 114	81.12 117	85.26 105	86.42 224	68.72 65	92.59 131	90.44 197	73.12 162	84.20 67	94.36 82	38.04 314	95.73 145	84.12 85	86.81 120	91.33 187

xiu_mvs_v1_base		82.16 114	81.12 117	85.26 105	86.42 224	68.72 65	92.59 131	90.44 197	73.12 162	84.20 67	94.36 82	38.04 314	95.73 145	84.12 85	86.81 120	91.33 187

xiu_mvs_v1_base_debi		82.16 114	81.12 117	85.26 105	86.42 224	68.72 65	92.59 131	90.44 197	73.12 162	84.20 67	94.36 82	38.04 314	95.73 145	84.12 85	86.81 120	91.33 187

PVSNet_0	68.08 15	71.81 268	68.32 285	82.27 192	84.68 255	62.31 231	88.68 258	90.31 203	75.84 118	57.93 327	80.65 298	37.85 317	94.19 210	69.94 193	29.05 390	90.31 204

Anonymous20231206		67.53 304	65.78 295	72.79 327	74.95 352	47.59 359	88.23 264	87.32 298	61.75 316	58.07 324	77.29 327	37.79 318	87.29 337	42.91 344	63.71 304	83.48 310

ACMM	69.62 13	74.34 242	72.73 245	79.17 268	84.25 266	57.87 300	90.36 219	89.93 219	63.17 301	65.64 269	86.04 232	37.79 318	94.10 212	65.89 235	71.52 245	85.55 286
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
cascas		78.18 186	75.77 202	85.41 97	87.14 212	69.11 54	92.96 112	91.15 173	66.71 273	70.47 210	86.07 230	37.49 320	96.48 120	70.15 191	79.80 177	90.65 199

LS3D		69.17 288	66.40 292	77.50 286	91.92 98	56.12 318	85.12 293	80.37 349	46.96 368	56.50 332	87.51 211	37.25 321	93.71 231	32.52 378	79.40 180	82.68 325

MDA-MVSNet_test_wron		63.78 324	60.16 327	74.64 312	78.15 337	60.41 268	83.49 303	84.03 328	56.17 346	39.17 380	71.59 356	37.22 322	83.24 361	42.87 346	48.73 362	80.26 348

YYNet1		63.76 325	60.14 328	74.62 313	78.06 338	60.19 273	83.46 305	83.99 332	56.18 345	39.25 379	71.56 357	37.18 323	83.34 359	42.90 345	48.70 363	80.32 347

FMVSNet5		68.04 299	65.66 298	75.18 309	84.43 262	57.89 299	83.54 302	86.26 309	61.83 315	53.64 342	73.30 347	37.15 324	85.08 347	48.99 317	61.77 319	82.56 327

test20.03		63.83 323	62.65 319	67.38 352	70.58 368	39.94 380	86.57 288	84.17 327	63.29 298	51.86 347	77.30 326	37.09 325	82.47 364	38.87 361	54.13 352	79.73 351

PVSNet	73.49 8	80.05 151	78.63 158	84.31 142	90.92 122	64.97 159	92.47 135	91.05 181	79.18 69	72.43 190	90.51 162	37.05 326	94.06 216	68.06 211	86.00 130	93.90 125

EU-MVSNet		64.01 322	63.01 316	67.02 353	74.40 355	38.86 384	83.27 307	86.19 311	45.11 373	54.27 338	81.15 292	36.91 327	80.01 374	48.79 319	57.02 342	82.19 331

Anonymous20231211		73.08 253	70.39 269	81.13 222	90.62 127	63.33 206	91.40 178	90.06 215	51.84 356	64.46 282	80.67 297	36.49 328	94.07 215	63.83 252	64.17 299	85.98 276

FMVSNet1		72.71 262	69.91 273	81.10 224	83.60 274	65.11 155	90.01 230	90.32 200	63.92 291	63.56 289	80.25 304	36.35 329	91.54 293	54.46 298	66.75 277	86.64 258

Anonymous20240529		76.84 209	74.15 225	84.88 115	91.02 119	64.95 160	93.84 80	91.09 176	53.57 351	73.00 177	87.42 212	35.91 330	97.32 74	69.14 203	72.41 240	92.36 166

WB-MVS		46.23 348	44.94 350	50.11 369	62.13 382	21.23 402	76.48 353	55.49 388	45.89 371	35.78 381	61.44 377	35.54 331	72.83 380	9.96 396	21.75 391	56.27 384

CMPMVS	48.56 21	66.77 308	64.41 309	73.84 319	70.65 367	50.31 346	77.79 349	85.73 316	45.54 372	44.76 371	82.14 272	35.40 332	90.14 311	63.18 258	74.54 220	81.07 339
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs6		67.57 303	64.76 304	76.00 304	72.82 361	53.37 332	88.71 257	86.78 306	53.19 352	57.58 329	78.03 322	35.33 333	92.41 271	55.56 294	54.88 350	82.21 330

PatchMatch-RL		72.06 267	69.98 270	78.28 278	89.51 150	55.70 321	83.49 303	83.39 337	61.24 317	63.72 288	82.76 264	34.77 334	93.03 243	53.37 304	77.59 196	86.12 273

LTVRE_ROB	59.60 19	66.27 310	63.54 313	74.45 314	84.00 269	51.55 339	67.08 374	83.53 334	58.78 332	54.94 336	80.31 302	34.54 335	93.23 240	40.64 355	68.03 268	78.58 361
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		44.51 350	43.35 352	47.99 373	61.01 384	18.90 404	74.12 359	54.36 389	43.42 378	34.10 384	60.02 378	34.42 336	70.39 383	9.14 398	19.57 392	54.68 385

UniMVSNet_ETH3D		72.74 261	70.53 268	79.36 265	78.62 332	56.64 315	85.01 294	89.20 246	63.77 293	64.84 276	84.44 248	34.05 337	91.86 285	63.94 251	70.89 250	89.57 215

bld_raw_dy_0_64		71.59 271	69.71 276	77.22 293	77.82 341	58.12 298	87.71 274	73.66 364	68.01 262	61.90 305	84.29 250	33.68 338	88.43 323	69.91 194	70.43 251	85.11 294

F-COLMAP		70.66 275	68.44 283	77.32 290	86.37 227	55.91 319	88.00 268	86.32 307	56.94 341	57.28 330	88.07 202	33.58 339	92.49 269	51.02 308	68.37 266	83.55 307

pmmvs-eth3d		65.53 316	62.32 321	75.19 308	69.39 371	59.59 279	82.80 314	83.43 335	62.52 307	51.30 351	72.49 348	32.86 340	87.16 338	55.32 295	50.73 359	78.83 359

MDA-MVSNet-bldmvs		61.54 331	57.70 335	73.05 324	79.53 316	57.00 314	83.08 311	81.23 344	57.57 335	34.91 383	72.45 349	32.79 341	86.26 342	35.81 366	41.95 373	75.89 368

MIMVSNet		71.64 269	68.44 283	81.23 219	81.97 292	64.44 169	73.05 360	88.80 267	69.67 244	64.59 277	74.79 344	32.79 341	87.82 329	53.99 300	76.35 210	91.42 185

UnsupCasMVSNet_eth		65.79 313	63.10 315	73.88 318	70.71 366	50.29 347	81.09 326	89.88 221	72.58 174	49.25 359	74.77 345	32.57 343	87.43 336	55.96 293	41.04 375	83.90 304

N_pmnet		50.55 344	49.11 347	54.88 365	77.17 344	4.02 408	84.36 297	2.00 406	48.59 364	45.86 367	68.82 362	32.22 344	82.80 363	31.58 380	51.38 358	77.81 364

test_0402		64.54 319	61.09 325	74.92 311	84.10 268	60.75 261	87.95 269	79.71 351	52.03 354	52.41 345	77.20 328	32.21 345	91.64 289	23.14 385	61.03 326	72.36 374

DSMNet-mixed		56.78 340	54.44 343	63.79 356	63.21 379	29.44 395	64.43 377	64.10 382	42.12 380	51.32 350	71.60 355	31.76 346	75.04 377	36.23 364	65.20 289	86.87 256

MSDG		69.54 286	65.73 296	80.96 229	85.11 251	63.71 193	84.19 298	83.28 338	56.95 340	54.50 337	84.03 251	31.50 347	96.03 135	42.87 346	69.13 261	83.14 317

RPSCF		64.24 321	61.98 323	71.01 339	76.10 349	45.00 369	75.83 356	75.94 356	46.94 369	58.96 319	84.59 245	31.40 348	82.00 368	47.76 326	60.33 334	86.04 274

tt0805		73.07 254	70.73 266	80.07 246	78.37 334	57.05 312	87.78 272	92.18 128	61.23 318	67.04 260	86.49 224	31.35 349	94.58 191	65.06 245	67.12 274	88.57 228

jajsoiax		73.05 255	71.51 260	77.67 284	77.46 342	54.83 326	88.81 256	90.04 216	69.13 252	62.85 298	83.51 257	31.16 350	92.75 257	70.83 184	69.80 252	85.43 289

MVS-HIRNet		60.25 334	55.55 341	74.35 315	84.37 263	56.57 316	71.64 362	74.11 363	34.44 383	45.54 369	42.24 390	31.11 351	89.81 313	40.36 356	76.10 212	76.67 367

SixPastTwentyTwo		64.92 317	61.78 324	74.34 316	78.74 329	49.76 348	83.42 306	79.51 352	62.86 303	50.27 354	77.35 325	30.92 352	90.49 303	45.89 334	47.06 365	82.78 319

KD-MVS_self_test		60.87 332	58.60 332	67.68 350	66.13 376	39.93 381	75.63 357	84.70 323	57.32 338	49.57 357	68.45 363	29.55 353	82.87 362	48.09 321	47.94 364	80.25 349

mvs_tets		72.71 262	71.11 261	77.52 285	77.41 343	54.52 328	88.45 262	89.76 224	68.76 257	62.70 299	83.26 260	29.49 354	92.71 258	70.51 190	69.62 254	85.34 291

Anonymous202405211		77.96 190	75.33 209	85.87 82	93.73 52	64.52 164	94.85 44	85.36 318	62.52 307	76.11 146	90.18 170	29.43 355	97.29 76	68.51 209	77.24 204	95.81 45

K. test v3		63.09 326	59.61 330	73.53 321	76.26 348	49.38 353	83.27 307	77.15 354	64.35 289	47.77 363	72.32 352	28.73 356	87.79 330	49.93 314	36.69 381	83.41 312

UnsupCasMVSNet_bld		61.60 330	57.71 334	73.29 323	68.73 372	51.64 338	78.61 343	89.05 257	57.20 339	46.11 364	61.96 375	28.70 357	88.60 320	50.08 313	38.90 379	79.63 352

lessismore_v0				73.72 320	72.93 360	47.83 358		61.72 385		45.86 367	73.76 346	28.63 358	89.81 313	47.75 327	31.37 387	83.53 308

new-patchmatchnet		59.30 337	56.48 339	67.79 349	65.86 377	44.19 370	82.47 315	81.77 342	59.94 327	43.65 375	66.20 367	27.67 359	81.68 369	39.34 358	41.40 374	77.50 365

ACMH	63.93 17	68.62 293	64.81 303	80.03 248	85.22 247	63.25 207	87.72 273	84.66 324	60.83 320	51.57 349	79.43 314	27.29 360	94.96 176	41.76 349	64.84 292	81.88 332
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OurMVSNet-221017-0		64.68 318	62.17 322	72.21 332	76.08 350	47.35 360	80.67 329	81.02 345	56.19 344	51.60 348	79.66 312	27.05 361	88.56 321	53.60 303	53.63 353	80.71 343

ACMH+	65.35 16	67.65 302	64.55 306	76.96 297	84.59 258	57.10 311	88.08 265	80.79 346	58.59 334	53.00 343	81.09 293	26.63 362	92.95 246	46.51 330	61.69 323	80.82 341

OpenMVS_ROB	61.12 18	66.39 309	62.92 317	76.80 299	76.51 346	57.77 301	89.22 248	83.41 336	55.48 347	53.86 341	77.84 323	26.28 363	93.95 225	34.90 369	68.76 263	78.68 360

test_fmvs1		74.07 245	73.69 232	75.22 307	78.91 327	47.34 361	89.06 254	74.69 362	63.68 294	79.41 110	91.59 146	24.36 364	87.77 331	85.22 74	76.26 211	90.55 202

COLMAP_ROB	57.96 20	62.98 327	59.65 329	72.98 325	81.44 295	53.00 334	83.75 301	75.53 360	48.34 366	48.81 360	81.40 285	24.14 365	90.30 304	32.95 374	60.52 331	75.65 369
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet1		60.16 335	57.33 336	68.67 346	69.71 369	44.13 371	78.92 342	84.21 326	55.05 348	44.63 372	71.85 354	23.91 366	81.54 370	32.63 377	55.03 349	80.35 346

testgi		64.48 320	62.87 318	69.31 344	71.24 362	40.62 379	85.49 291	79.92 350	65.36 283	54.18 339	83.49 258	23.74 367	84.55 349	41.60 350	60.79 329	82.77 320

ITE_SJBPF				70.43 340	74.44 354	47.06 364		77.32 353	60.16 325	54.04 340	83.53 256	23.30 368	84.01 353	43.07 343	61.58 324	80.21 350

EG-PatchMatch MVS		68.55 294	65.41 300	77.96 282	78.69 330	62.93 216	89.86 235	89.17 248	60.55 321	50.27 354	77.73 324	22.60 369	94.06 216	47.18 328	72.65 237	76.88 366

tmp_tt		22.26 365	23.75 367	17.80 382	5.23 405	12.06 407	35.26 393	39.48 400	2.82 400	18.94 391	44.20 389	22.23 370	24.64 401	36.30 363	9.31 398	16.69 395

USDC		67.43 306	64.51 307	76.19 302	77.94 339	55.29 323	78.38 345	85.00 321	73.17 160	48.36 361	80.37 301	21.23 371	92.48 270	52.15 306	64.02 302	80.81 342

Anonymous20240521		62.09 328	59.08 331	71.10 338	67.19 374	48.72 355	83.91 300	85.23 319	50.38 360	47.84 362	71.22 359	20.74 372	85.51 346	46.47 331	58.75 339	79.06 356

test_vis1_n		71.63 270	70.73 266	74.31 317	69.63 370	47.29 362	86.91 284	72.11 368	63.21 300	75.18 157	90.17 171	20.40 373	85.76 343	84.59 82	74.42 222	89.87 209

XVG-ACMP-BASELINE		68.04 299	65.53 299	75.56 305	74.06 356	52.37 335	78.43 344	85.88 314	62.03 311	58.91 320	81.21 291	20.38 374	91.15 299	60.69 273	68.18 267	83.16 316

test_fmvs1_n		72.69 264	71.92 255	74.99 310	71.15 364	47.08 363	87.34 280	75.67 357	63.48 296	78.08 127	91.17 153	20.16 375	87.87 328	84.65 81	75.57 215	90.01 208

AllTest		61.66 329	58.06 333	72.46 329	79.57 314	51.42 341	80.17 335	68.61 376	51.25 357	45.88 365	81.23 287	19.86 376	86.58 340	38.98 359	57.01 343	79.39 353

TestCases				72.46 329	79.57 314	51.42 341		68.61 376	51.25 357	45.88 365	81.23 287	19.86 376	86.58 340	38.98 359	57.01 343	79.39 353

test_vis1_rt		59.09 338	57.31 337	64.43 355	68.44 373	46.02 367	83.05 312	48.63 395	51.96 355	49.57 357	63.86 371	16.30 378	80.20 373	71.21 182	62.79 308	67.07 380

pmmvs3		55.51 341	51.50 346	67.53 351	57.90 386	50.93 344	80.37 331	73.66 364	40.63 381	44.15 374	64.75 370	16.30 378	78.97 375	44.77 340	40.98 377	72.69 372

test_fmvs2		65.78 314	64.84 302	68.60 347	66.54 375	41.71 376	83.27 307	69.81 374	54.38 349	67.91 247	84.54 247	15.35 380	81.22 371	75.65 145	66.16 281	82.88 318

TDRefinement		55.28 342	51.58 345	66.39 354	59.53 385	46.15 366	76.23 354	72.80 366	44.60 374	42.49 376	76.28 337	15.29 381	82.39 365	33.20 373	43.75 370	70.62 376

new_pmnet		49.31 345	46.44 348	57.93 360	62.84 380	40.74 378	68.47 370	62.96 384	36.48 382	35.09 382	57.81 379	14.97 382	72.18 381	32.86 375	46.44 366	60.88 382

TinyColmap		60.32 333	56.42 340	72.00 336	78.78 328	53.18 333	78.36 346	75.64 358	52.30 353	41.59 378	75.82 341	14.76 383	88.35 324	35.84 365	54.71 351	74.46 370

EGC-MVSNET		42.35 351	38.09 354	55.11 364	74.57 353	46.62 365	71.63 363	55.77 387	0.04 401	0.24 402	62.70 373	14.24 384	74.91 378	17.59 390	46.06 367	43.80 387

LF4IMVS		54.01 343	52.12 344	59.69 359	62.41 381	39.91 382	68.59 369	68.28 378	42.96 379	44.55 373	75.18 342	14.09 385	68.39 385	41.36 352	51.68 357	70.78 375

PM-MVS		59.40 336	56.59 338	67.84 348	63.63 378	41.86 375	76.76 351	63.22 383	59.01 331	51.07 352	72.27 353	11.72 386	83.25 360	61.34 269	50.28 361	78.39 362

mvsany_test3		48.86 346	46.35 349	56.41 361	46.00 394	31.67 391	62.26 379	47.25 396	43.71 377	45.54 369	68.15 364	10.84 387	64.44 393	57.95 285	35.44 384	73.13 371

ambc				69.61 342	61.38 383	41.35 377	49.07 391	85.86 315		50.18 356	66.40 366	10.16 388	88.14 326	45.73 335	44.20 369	79.32 355

FPMVS		45.64 349	43.10 353	53.23 367	51.42 391	36.46 385	64.97 376	71.91 369	29.13 387	27.53 387	61.55 376	9.83 389	65.01 391	16.00 393	55.58 347	58.22 383

ANet_high		40.27 355	35.20 358	55.47 363	34.74 402	34.47 388	63.84 378	71.56 371	48.42 365	18.80 392	41.08 391	9.52 390	64.45 392	20.18 388	8.66 399	67.49 379

test_method		38.59 356	35.16 359	48.89 371	54.33 387	21.35 401	45.32 392	53.71 390	7.41 398	28.74 386	51.62 382	8.70 391	52.87 396	33.73 370	32.89 386	72.47 373

EMVS		23.76 364	23.20 368	25.46 381	41.52 400	16.90 406	60.56 382	38.79 402	14.62 396	8.99 400	20.24 399	7.35 392	45.82 399	7.25 400	9.46 397	13.64 397

test_f		46.58 347	43.45 351	55.96 362	45.18 395	32.05 390	61.18 380	49.49 394	33.39 384	42.05 377	62.48 374	7.00 393	65.56 389	47.08 329	43.21 372	70.27 377

test_fmvs3		56.82 339	54.86 342	62.69 358	53.59 388	35.47 386	75.87 355	65.64 381	43.91 376	55.10 335	71.43 358	6.91 394	74.40 379	68.64 208	52.63 354	78.20 363

E-PMN		24.61 362	24.00 366	26.45 380	43.74 397	18.44 405	60.86 381	39.66 399	15.11 395	9.53 399	22.10 396	6.52 395	46.94 398	8.31 399	10.14 396	13.98 396

DeepMVS_CX				34.71 379	51.45 390	24.73 399		28.48 405	31.46 386	17.49 395	52.75 381	5.80 396	42.60 400	18.18 389	19.42 393	36.81 392

Gipuma		34.91 358	31.44 361	45.30 374	70.99 365	39.64 383	19.85 396	72.56 367	20.10 392	16.16 396	21.47 397	5.08 397	71.16 382	13.07 394	43.70 371	25.08 394
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
APD_test1		40.50 353	37.31 356	50.09 370	51.88 389	35.27 387	59.45 384	52.59 391	21.64 390	26.12 388	57.80 380	4.56 398	66.56 387	22.64 386	39.09 378	48.43 386

LCM-MVSNet		40.54 352	35.79 357	54.76 366	36.92 401	30.81 392	51.41 389	69.02 375	22.07 389	24.63 389	45.37 386	4.56 398	65.81 388	33.67 371	34.50 385	67.67 378

PMMVS2		37.93 357	33.61 360	50.92 368	46.31 393	24.76 398	60.55 383	50.05 392	28.94 388	20.93 390	47.59 383	4.41 400	65.13 390	25.14 384	18.55 394	62.87 381

test_vis3_rt		40.46 354	37.79 355	48.47 372	44.49 396	33.35 389	66.56 375	32.84 403	32.39 385	29.65 385	39.13 393	3.91 401	68.65 384	50.17 311	40.99 376	43.40 388

testf1		32.77 359	29.47 362	42.67 376	41.89 398	30.81 392	52.07 387	43.45 397	15.45 393	18.52 393	44.82 387	2.12 402	58.38 394	16.05 391	30.87 388	38.83 389

APD_test2		32.77 359	29.47 362	42.67 376	41.89 398	30.81 392	52.07 387	43.45 397	15.45 393	18.52 393	44.82 387	2.12 402	58.38 394	16.05 391	30.87 388	38.83 389

PMVS	26.43 22	31.84 361	28.16 364	42.89 375	25.87 404	27.58 396	50.92 390	49.78 393	21.37 391	14.17 397	40.81 392	2.01 404	66.62 386	9.61 397	38.88 380	34.49 393
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	24.84 23	24.35 363	19.77 369	38.09 378	34.56 403	26.92 397	26.57 394	38.87 401	11.73 397	11.37 398	27.44 394	1.37 405	50.42 397	11.41 395	14.60 395	36.93 391
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		11.30 367	10.95 370	12.33 383	48.05 392	19.89 403	25.89 395	1.92 407	3.58 399	3.12 401	1.37 401	0.64 406	15.77 402	6.23 401	7.77 400	1.35 398

test123		6.92 370	9.21 373	0.08 384	0.03 407	0.05 409	81.65 321	0.01 409	0.02 403	0.14 404	0.85 403	0.03 407	0.02 403	0.12 403	0.00 402	0.16 399

testmvs		7.23 369	9.62 372	0.06 385	0.04 406	0.02 410	84.98 295	0.02 408	0.03 402	0.18 403	1.21 402	0.01 408	0.02 403	0.14 402	0.01 401	0.13 400

test_blank		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 402	0.00 401

uanet_test		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 402	0.00 401

DCPMVS		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 402	0.00 401

sosnet-low-res		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 402	0.00 401

sosnet		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 402	0.00 401

uncertanet		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 402	0.00 401

Regformer		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 402	0.00 401

ab-mvs-re		7.91 368	10.55 371	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	94.95 64	0.00 409	0.00 405	0.00 404	0.00 402	0.00 401

uanet		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 402	0.00 401

WAC-MVS						49.45 351								31.56 381

FOURS1					93.95 45	61.77 240	93.96 70	91.92 136	62.14 310	86.57 44

MSC_two_6792asdad				89.60 8	97.31 4	73.22 10		95.05 22					99.07 13	92.01 24	94.77 25	96.51 21

No_MVS				89.60 8	97.31 4	73.22 10		95.05 22					99.07 13	92.01 24	94.77 25	96.51 21

eth-test2					0.00 408

eth-test					0.00 408

IU-MVS					96.46 11	69.91 37		95.18 17	80.75 46	95.28 1				92.34 21	95.36 13	96.47 25

save fliter					93.84 48	67.89 86	95.05 39	92.66 109	78.19 85

test_0728_SECOND				88.70 16	96.45 12	70.43 29	96.64 9	94.37 47					99.15 2	91.91 27	94.90 21	96.51 21

GSMVS																94.68 88

test_part2					96.29 19	68.16 80				90.78 16

MTGPA								92.23 122

MTMP							93.77 84	32.52 404

gm-plane-assit					88.42 177	67.04 109			78.62 82		91.83 141		97.37 70	76.57 139

test9_res														89.41 39	94.96 18	95.29 63

agg_prior2														86.41 66	94.75 29	95.33 59

agg_prior					94.16 43	66.97 111		93.31 84		84.49 65			96.75 111

test_prior4						67.18 105	93.92 73

test_prior				86.42 68	94.71 35	67.35 100		93.10 94					96.84 108			95.05 74

旧先验2							92.00 155		59.37 330	87.54 38			93.47 237	75.39 147

新几何2							91.41 176

无先验							92.71 121	92.61 113	62.03 311				97.01 93	66.63 225		93.97 120

原ACMM2							92.01 152

testdata2													96.09 129	61.26 270

testdata1							89.21 249		77.55 98

plane_prior7					86.94 217	61.51 246

plane_prior5								91.31 165					95.55 158	76.74 137	78.53 190	88.39 233

plane_prior4											89.14 184

plane_prior3						61.95 238			79.09 72	72.53 186

plane_prior2							93.13 105		78.81 79

plane_prior1					87.15 211

plane_prior						62.42 226	93.85 77		79.38 64						78.80 187

n2								0.00 410

nn								0.00 410

door-mid								66.01 380

test11								93.01 96

door								66.57 379

HQP5-MVS						63.66 197

HQP-NCC					87.54 202		94.06 63		79.80 57	74.18 165

ACMP_Plane					87.54 202		94.06 63		79.80 57	74.18 165

BP-MVS														77.63 134

HQP4-MVS										74.18 165			95.61 153			88.63 226

HQP3-MVS								91.70 151							78.90 185

NP-MVS					87.41 205	63.04 212					90.30 167

ACMMP++_ref															71.63 243

ACMMP++															69.72 253

High-resolution multi-view benchmark