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.

thres100view900		78.37 168	77.01 170	82.46 170	91.89 99	63.21 196	91.19 179	96.33 1	72.28 163	70.45 194	87.89 187	60.31 114	95.32 151	45.16 318	77.58 181	88.83 203

thres600view7		78.00 173	76.66 175	82.03 189	91.93 96	63.69 188	91.30 173	96.33 1	72.43 158	70.46 193	87.89 187	60.31 114	94.92 163	42.64 330	76.64 191	87.48 224

thres200		79.66 142	78.33 146	83.66 146	92.54 82	65.82 135	93.06 96	96.31 3	74.90 112	73.30 160	88.66 170	59.67 123	95.61 139	47.84 307	78.67 172	89.56 200

tfpn200view9		78.79 160	77.43 161	82.88 161	92.21 88	64.49 161	92.05 136	96.28 4	73.48 137	71.75 182	88.26 180	60.07 119	95.32 151	45.16 318	77.58 181	88.83 203

thres400		78.68 162	77.43 161	82.43 171	92.21 88	64.49 161	92.05 136	96.28 4	73.48 137	71.75 182	88.26 180	60.07 119	95.32 151	45.16 318	77.58 181	87.48 224

VNet		86.20 38	85.65 45	87.84 25	93.92 46	69.99 31	95.73 21	95.94 6	78.43 67	86.00 38	93.07 100	58.22 136	97.00 84	85.22 60	84.33 133	96.52 19

baseline2		83.68 79	83.42 70	84.48 123	87.37 200	66.00 129	90.06 211	95.93 7	79.71 46	69.08 210	90.39 150	77.92 6	96.28 110	78.91 110	81.38 153	91.16 179

MCST-MVS		91.08 1	91.46 2	89.94 4	97.66 2	73.37 8	97.13 2	95.58 8	89.33 1	85.77 40	96.26 22	72.84 26	99.38 1	92.64 6	95.93 9	97.08 9

MVS		84.66 58	82.86 82	90.06 2	90.93 120	74.56 6	87.91 251	95.54 9	68.55 236	72.35 176	94.71 60	59.78 122	98.90 18	81.29 93	94.69 29	96.74 12

DPM-MVS		90.70 2	90.52 7	91.24 1	89.68 143	76.68 2	97.29 1	95.35 10	82.87 15	91.58 10	97.22 3	79.93 5	99.10 9	83.12 77	97.64 2	97.94 1

CSCG		86.87 30	86.26 36	88.72 14	95.05 31	70.79 23	93.83 73	95.33 11	68.48 238	77.63 116	94.35 73	73.04 24	98.45 28	84.92 64	93.71 43	96.92 11

WTY-MVS		86.32 36	85.81 42	87.85 24	92.82 73	69.37 47	95.20 32	95.25 12	82.71 17	81.91 71	94.73 59	67.93 43	97.63 50	79.55 102	82.25 145	96.54 18

patch_mono-2		89.71 9	90.99 5	85.85 81	96.04 24	63.70 187	95.04 38	95.19 13	86.74 5	91.53 11	95.15 49	73.86 20	97.58 53	93.38 3	92.00 65	96.28 31

IU-MVS					96.46 11	69.91 35		95.18 14	80.75 36	95.28 1				92.34 8	95.36 13	96.47 24

IB-MVS	77.80 4	82.18 100	80.46 118	87.35 37	89.14 157	70.28 29	95.59 24	95.17 15	78.85 61	70.19 198	85.82 210	70.66 35	97.67 46	72.19 159	66.52 259	94.09 105
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
PHI-MVS		86.83 32	86.85 33	86.78 53	93.47 57	65.55 141	95.39 28	95.10 16	71.77 181	85.69 42	96.52 16	62.07 99	98.77 21	86.06 56	95.60 11	96.03 37

test_yl		84.28 64	83.16 75	87.64 28	94.52 37	69.24 49	95.78 16	95.09 17	69.19 228	81.09 78	92.88 106	57.00 149	97.44 58	81.11 94	81.76 149	96.23 32

DCV-MVSNet		84.28 64	83.16 75	87.64 28	94.52 37	69.24 49	95.78 16	95.09 17	69.19 228	81.09 78	92.88 106	57.00 149	97.44 58	81.11 94	81.76 149	96.23 32

MSC_two_6792asdad				89.60 8	97.31 4	73.22 10		95.05 19					99.07 13	92.01 11	94.77 24	96.51 20

No_MVS				89.60 8	97.31 4	73.22 10		95.05 19					99.07 13	92.01 11	94.77 24	96.51 20

sss		82.71 94	82.38 91	83.73 142	89.25 154	59.58 262	92.24 127	94.89 21	77.96 72	79.86 91	92.38 117	56.70 155	97.05 79	77.26 121	80.86 157	94.55 88

EPNet		87.84 21	88.38 16	86.23 71	93.30 60	66.05 127	95.26 30	94.84 22	87.09 3	88.06 25	94.53 64	66.79 49	97.34 65	83.89 73	91.68 70	95.29 61
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		90.32 5	90.89 6	88.61 18	96.76 8	70.65 24	96.47 12	94.83 23	84.83 9	89.07 22	96.80 14	70.86 34	99.06 15	92.64 6	95.71 10	96.12 34

EI-MVSNet-Vis-set		83.77 76	83.67 63	84.06 134	92.79 76	63.56 192	91.76 152	94.81 24	79.65 47	77.87 114	94.09 81	63.35 88	97.90 39	79.35 104	79.36 165	90.74 183

tttt0517		79.50 145	78.53 145	82.41 174	87.22 202	61.43 231	89.75 221	94.76 25	69.29 226	67.91 228	88.06 185	72.92 25	95.63 137	62.91 242	73.90 209	90.16 190

GG-mvs-BLEND				86.53 62	91.91 98	69.67 43	75.02 335	94.75 26		78.67 109	90.85 142	77.91 7	94.56 179	72.25 156	93.74 41	95.36 56

gg-mvs-nofinetune		77.18 186	74.31 204	85.80 83	91.42 111	68.36 69	71.78 337	94.72 27	49.61 340	77.12 123	45.92 361	77.41 8	93.98 206	67.62 201	93.16 51	95.05 72

thisisatest0515		83.41 80	82.49 89	86.16 72	89.46 149	68.26 73	93.54 83	94.70 28	74.31 118	75.75 133	90.92 140	72.62 28	96.52 106	69.64 179	81.50 152	93.71 120

EI-MVSNet-UG-set		83.14 86	82.96 78	83.67 145	92.28 85	63.19 197	91.38 168	94.68 29	79.22 53	76.60 128	93.75 87	62.64 94	97.76 44	78.07 117	78.01 176	90.05 192

VPA-MVSNet		79.03 152	78.00 152	82.11 187	85.95 222	64.48 163	93.22 93	94.66 30	75.05 110	74.04 155	84.95 217	52.17 204	93.52 218	74.90 138	67.04 255	88.32 217

NCCC		89.07 13	89.46 13	87.91 23	96.60 10	69.05 54	96.38 13	94.64 31	84.42 10	86.74 32	96.20 23	66.56 52	98.76 22	89.03 32	94.56 30	95.92 40

ET-MVSNet_ETH3D		84.01 71	83.15 77	86.58 59	90.78 125	70.89 22	94.74 45	94.62 32	81.44 30	58.19 301	93.64 90	73.64 23	92.35 257	82.66 79	78.66 173	96.50 23

thisisatest0530		81.15 116	80.07 120	84.39 125	88.26 179	65.63 138	91.40 164	94.62 32	71.27 197	70.93 190	89.18 166	72.47 29	96.04 120	65.62 222	76.89 190	91.49 169

DVP-MVS		89.41 11	89.73 12	88.45 20	96.40 15	69.99 31	96.64 8	94.52 34	71.92 171	90.55 16	96.93 9	73.77 21	99.08 11	91.91 14	94.90 20	96.29 29
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
HY-MVS	76.49 5	84.28 64	83.36 73	87.02 46	92.22 87	67.74 86	84.65 277	94.50 35	79.15 55	82.23 69	87.93 186	66.88 48	96.94 92	80.53 97	82.20 146	96.39 27

HPM-MVS++		89.37 12	89.95 11	87.64 28	95.10 30	68.23 75	95.24 31	94.49 36	82.43 19	88.90 23	96.35 20	71.89 33	98.63 24	88.76 33	96.40 6	96.06 35

MG-MVS		87.11 28	86.27 35	89.62 7	97.79 1	76.27 4	94.96 41	94.49 36	78.74 65	83.87 60	92.94 103	64.34 73	96.94 92	75.19 132	94.09 34	95.66 45

SED-MVS		89.94 7	90.36 8	88.70 15	96.45 12	69.38 45	96.89 4	94.44 38	71.65 184	92.11 4	97.21 4	76.79 9	99.11 6	92.34 8	95.36 13	97.62 2

test_241102_ONE					96.45 12	69.38 45		94.44 38	71.65 184	92.11 4	97.05 7	76.79 9	99.11 6

test_241102_TWO								94.41 40	71.65 184	92.07 6	97.21 4	74.58 17	99.11 6	92.34 8	95.36 13	96.59 15

DeepPCF-MVS	81.17 1	89.72 8	91.38 3	84.72 115	93.00 69	58.16 279	96.72 7	94.41 40	86.50 6	90.25 18	97.83 1	75.46 14	98.67 23	92.78 5	95.49 12	97.32 6

DELS-MVS		90.05 6	90.09 9	89.94 4	93.14 66	73.88 7	97.01 3	94.40 42	88.32 2	85.71 41	94.91 55	74.11 19	98.91 17	87.26 45	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
3Dnovator	73.91 6	82.69 95	80.82 110	88.31 21	89.57 145	71.26 18	92.60 116	94.39 43	78.84 62	67.89 230	92.48 115	48.42 236	98.52 26	68.80 191	94.40 32	95.15 69

DVP-MVS++		90.53 3	91.09 4	88.87 13	97.31 4	69.91 35	93.96 62	94.37 44	72.48 155	92.07 6	96.85 11	83.82 2	99.15 2	91.53 16	97.42 4	97.55 4

test_0728_SECOND				88.70 15	96.45 12	70.43 27	96.64 8	94.37 44					99.15 2	91.91 14	94.90 20	96.51 20

test0726					96.40 15	69.99 31	96.76 6	94.33 46	71.92 171	91.89 8	97.11 6	73.77 21

MSP-MVS		90.38 4	91.87 1	85.88 78	92.83 71	64.03 178	93.06 96	94.33 46	82.19 21	93.65 3	96.15 25	85.89 1	97.19 74	91.02 20	97.75 1	96.43 25
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
MAR-MVS		84.18 68	83.43 68	86.44 64	96.25 21	65.93 132	94.28 50	94.27 48	74.41 115	79.16 100	95.61 33	53.99 186	98.88 20	69.62 181	93.26 50	94.50 94
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_one_0601					96.32 18	69.74 40		94.18 49	71.42 195	90.67 15	96.85 11	74.45 18

9.14			87.63 22		93.86 47		94.41 49	94.18 49	72.76 150	86.21 35	96.51 17	66.64 50	97.88 41	90.08 24	94.04 35

DPE-MVS		88.77 14	89.21 14	87.45 35	96.26 20	67.56 90	94.17 51	94.15 51	68.77 234	90.74 14	97.27 2	76.09 12	98.49 27	90.58 23	94.91 19	96.30 28
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DeepC-MVS_fast	79.48 2	87.95 19	88.00 19	87.79 26	95.86 27	68.32 70	95.74 19	94.11 52	83.82 12	83.49 61	96.19 24	64.53 72	98.44 29	83.42 76	94.88 23	96.61 14
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SMA-MVS		88.14 15	88.29 18	87.67 27	93.21 63	68.72 62	93.85 69	94.03 53	74.18 120	91.74 9	96.67 15	65.61 60	98.42 31	89.24 29	96.08 7	95.88 41
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
FIs		79.47 146	79.41 134	79.67 240	85.95 222	59.40 264	91.68 156	93.94 54	78.06 71	68.96 213	88.28 178	66.61 51	91.77 269	66.20 216	74.99 201	87.82 220

SteuartSystems-ACMMP		86.82 33	86.90 31	86.58 59	90.42 129	66.38 120	96.09 15	93.87 55	77.73 77	84.01 59	95.66 31	63.39 87	97.94 37	87.40 43	93.55 46	95.42 51
Skip Steuart: Steuart Systems R&D Blog.
TSAR-MVS + GP.		87.96 18	88.37 17	86.70 55	93.51 56	65.32 145	95.15 34	93.84 56	78.17 70	85.93 39	94.80 58	75.80 13	98.21 32	89.38 26	88.78 98	96.59 15

CANet		89.61 10	89.99 10	88.46 19	94.39 39	69.71 41	96.53 11	93.78 57	86.89 4	89.68 19	95.78 29	65.94 56	99.10 9	92.99 4	93.91 38	96.58 17

APDe-MVS		87.54 23	87.84 20	86.65 56	96.07 23	66.30 123	94.84 43	93.78 57	69.35 225	88.39 24	96.34 21	67.74 44	97.66 48	90.62 22	93.44 47	96.01 38

TESTMET0.1,1		82.41 97	81.98 96	83.72 143	88.08 184	63.74 184	92.70 110	93.77 59	79.30 51	77.61 117	87.57 191	58.19 137	94.08 197	73.91 143	86.68 118	93.33 131

h-mvs33		83.01 88	82.56 88	84.35 127	89.34 150	62.02 219	92.72 108	93.76 60	81.45 28	82.73 66	92.25 121	60.11 117	97.13 77	87.69 39	62.96 284	93.91 114

SF-MVS		87.03 29	87.09 28	86.84 49	92.70 77	67.45 95	93.64 78	93.76 60	70.78 208	86.25 34	96.44 19	66.98 47	97.79 43	88.68 34	94.56 30	95.28 63

MVS_111021_HR		86.19 39	85.80 43	87.37 36	93.17 65	69.79 38	93.99 61	93.76 60	79.08 58	78.88 105	93.99 84	62.25 98	98.15 34	85.93 57	91.15 80	94.15 102

FC-MVSNet-test		77.99 174	78.08 151	77.70 264	84.89 239	55.51 303	90.27 205	93.75 63	76.87 87	66.80 246	87.59 190	65.71 59	90.23 290	62.89 243	73.94 207	87.37 227

QAPM		79.95 139	77.39 165	87.64 28	89.63 144	71.41 17	93.30 90	93.70 64	65.34 261	67.39 238	91.75 128	47.83 242	98.96 16	57.71 269	89.81 90	92.54 149

DeepC-MVS	77.85 3	85.52 48	85.24 48	86.37 67	88.80 165	66.64 114	92.15 129	93.68 65	81.07 33	76.91 126	93.64 90	62.59 95	98.44 29	85.50 58	92.84 55	94.03 109
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EPP-MVSNet		81.79 108	81.52 100	82.61 168	88.77 166	60.21 254	93.02 100	93.66 66	68.52 237	72.90 164	90.39 150	72.19 31	94.96 160	74.93 136	79.29 167	92.67 145

PVSNet_BlendedMVS		83.38 81	83.43 68	83.22 156	93.76 49	67.53 92	94.06 57	93.61 67	79.13 56	81.00 81	85.14 215	63.19 90	97.29 68	87.08 47	73.91 208	84.83 278

PVSNet_Blended		86.73 34	86.86 32	86.31 70	93.76 49	67.53 92	96.33 14	93.61 67	82.34 20	81.00 81	93.08 99	63.19 90	97.29 68	87.08 47	91.38 76	94.13 103

alignmvs		87.28 26	86.97 30	88.24 22	91.30 114	71.14 21	95.61 23	93.56 69	79.30 51	87.07 31	95.25 45	68.43 37	96.93 94	87.87 37	84.33 133	96.65 13

TSAR-MVS + MP.		88.11 17	88.64 15	86.54 61	91.73 102	68.04 79	90.36 202	93.55 70	82.89 14	91.29 12	92.89 105	72.27 30	96.03 121	87.99 36	94.77 24	95.54 50
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
TEST9					94.18 41	67.28 97	94.16 52	93.51 71	71.75 182	85.52 43	95.33 38	68.01 41	97.27 72

train_agg		87.21 27	87.42 26	86.60 57	94.18 41	67.28 97	94.16 52	93.51 71	71.87 176	85.52 43	95.33 38	68.19 39	97.27 72	89.09 30	94.90 20	95.25 67

ZD-MVS					96.63 9	65.50 143		93.50 73	70.74 209	85.26 48	95.19 48	64.92 67	97.29 68	87.51 41	93.01 52

ACMMP_NAP		86.05 41	85.80 43	86.80 52	91.58 106	67.53 92	91.79 149	93.49 74	74.93 111	84.61 51	95.30 40	59.42 126	97.92 38	86.13 54	94.92 18	94.94 76

cdsmvs_eth3d_5k		19.86 343	26.47 342	0.00 362	0.00 385	0.00 386	0.00 373	93.45 75	0.00 380	0.00 381	95.27 43	49.56 225	0.00 381	0.00 379	0.00 378	0.00 377

3Dnovator+	73.60 7	82.10 104	80.60 115	86.60 57	90.89 122	66.80 111	95.20 32	93.44 76	74.05 122	67.42 236	92.49 114	49.46 226	97.65 49	70.80 169	91.68 70	95.33 57

test_8					94.19 40	67.19 99	94.15 55	93.42 77	71.87 176	85.38 46	95.35 37	68.19 39	96.95 91

ZNCC-MVS		85.33 50	85.08 51	86.06 73	93.09 68	65.65 137	93.89 67	93.41 78	73.75 131	79.94 90	94.68 61	60.61 113	98.03 36	82.63 80	93.72 42	94.52 92

原ACMM1				84.42 124	93.21 63	64.27 174		93.40 79	65.39 259	79.51 95	92.50 112	58.11 138	96.69 99	65.27 227	93.96 36	92.32 154

agg_prior					94.16 43	66.97 107		93.31 80		84.49 53			96.75 98

PS-MVSNAJ		88.14 15	87.61 23	89.71 6	92.06 90	76.72 1	95.75 18	93.26 81	83.86 11	89.55 20	96.06 26	53.55 191	97.89 40	91.10 18	93.31 49	94.54 90

EI-MVSNet		78.97 154	78.22 149	81.25 201	85.33 230	62.73 210	89.53 225	93.21 82	72.39 160	72.14 177	90.13 158	60.99 108	94.72 168	67.73 200	72.49 219	86.29 247

MVSTER		82.47 96	82.05 93	83.74 140	92.68 78	69.01 55	91.90 144	93.21 82	79.83 42	72.14 177	85.71 212	74.72 16	94.72 168	75.72 128	72.49 219	87.50 223

UniMVSNet_NR-MVSNet		78.15 172	77.55 159	79.98 232	84.46 246	60.26 252	92.25 126	93.20 84	77.50 83	68.88 214	86.61 199	66.10 54	92.13 261	66.38 213	62.55 288	87.54 222

HFP-MVS		84.73 57	84.40 58	85.72 86	93.75 51	65.01 154	93.50 85	93.19 85	72.19 165	79.22 99	94.93 53	59.04 131	97.67 46	81.55 87	92.21 60	94.49 95

UniMVSNet (Re)		77.58 181	76.78 173	79.98 232	84.11 252	60.80 240	91.76 152	93.17 86	76.56 94	69.93 204	84.78 220	63.32 89	92.36 256	64.89 229	62.51 290	86.78 239

ACMMPR		84.37 61	84.06 60	85.28 98	93.56 54	64.37 170	93.50 85	93.15 87	72.19 165	78.85 107	94.86 56	56.69 156	97.45 57	81.55 87	92.20 61	94.02 110

GST-MVS		84.63 59	84.29 59	85.66 88	92.82 73	65.27 146	93.04 98	93.13 88	73.20 140	78.89 102	94.18 80	59.41 127	97.85 42	81.45 89	92.48 59	93.86 117

xiu_mvs_v2_base		87.92 20	87.38 27	89.55 11	91.41 113	76.43 3	95.74 19	93.12 89	83.53 13	89.55 20	95.95 27	53.45 195	97.68 45	91.07 19	92.62 56	94.54 90

test_prior				86.42 65	94.71 35	67.35 96		93.10 90					96.84 96			95.05 72

test11								93.01 91

CostFormer		82.33 98	81.15 103	85.86 80	89.01 160	68.46 67	82.39 297	93.01 91	75.59 101	80.25 87	81.57 258	72.03 32	94.96 160	79.06 108	77.48 184	94.16 101

PAPR		85.15 52	84.47 56	87.18 40	96.02 25	68.29 71	91.85 147	93.00 93	76.59 93	79.03 101	95.00 50	61.59 104	97.61 52	78.16 116	89.00 97	95.63 46

region2R		84.36 62	84.03 61	85.36 96	93.54 55	64.31 172	93.43 88	92.95 94	72.16 168	78.86 106	94.84 57	56.97 151	97.53 55	81.38 91	92.11 63	94.24 98

test12				87.09 43	94.60 36	68.86 58		92.91 95		82.67 68		65.44 61	97.55 54		93.69 44	94.84 80

lupinMVS		87.74 22	87.77 21	87.63 32	89.24 155	71.18 19	96.57 10	92.90 96	82.70 18	87.13 29	95.27 43	64.99 64	95.80 126	89.34 27	91.80 68	95.93 39

PAPM_NR		82.97 89	81.84 97	86.37 67	94.10 44	66.76 112	87.66 256	92.84 97	69.96 218	74.07 154	93.57 92	63.10 92	97.50 56	70.66 172	90.58 86	94.85 77

CDPH-MVS		85.71 46	85.46 46	86.46 63	94.75 34	67.19 99	93.89 67	92.83 98	70.90 204	83.09 64	95.28 41	63.62 83	97.36 63	80.63 96	94.18 33	94.84 80

tfpnnormal		70.10 260	67.36 267	78.32 258	83.45 261	60.97 238	88.85 238	92.77 99	64.85 263	60.83 288	78.53 294	43.52 268	93.48 219	31.73 360	61.70 300	80.52 324

PAPM		85.89 44	85.46 46	87.18 40	88.20 183	72.42 13	92.41 123	92.77 99	82.11 22	80.34 86	93.07 100	68.27 38	95.02 158	78.39 115	93.59 45	94.09 105

MS-PatchMatch		77.90 178	76.50 176	82.12 184	85.99 221	69.95 34	91.75 154	92.70 101	73.97 125	62.58 280	84.44 225	41.11 275	95.78 127	63.76 236	92.17 62	80.62 323

MSLP-MVS++		86.27 37	85.91 41	87.35 37	92.01 93	68.97 57	95.04 38	92.70 101	79.04 59	81.50 74	96.50 18	58.98 132	96.78 97	83.49 75	93.93 37	96.29 29

ab-mvs		80.18 133	78.31 147	85.80 83	88.44 172	65.49 144	83.00 294	92.67 103	71.82 179	77.36 120	85.01 216	54.50 178	96.59 101	76.35 126	75.63 198	95.32 59

save fliter					93.84 48	67.89 83	95.05 37	92.66 104	78.19 69

XVS		83.87 74	83.47 66	85.05 103	93.22 61	63.78 182	92.92 103	92.66 104	73.99 123	78.18 111	94.31 76	55.25 169	97.41 60	79.16 106	91.58 72	93.95 112

X-MVStestdata		76.86 188	74.13 208	85.05 103	93.22 61	63.78 182	92.92 103	92.66 104	73.99 123	78.18 111	10.19 376	55.25 169	97.41 60	79.16 106	91.58 72	93.95 112

SD-MVS		87.49 24	87.49 25	87.50 34	93.60 53	68.82 60	93.90 66	92.63 107	76.86 88	87.90 26	95.76 30	66.17 53	97.63 50	89.06 31	91.48 74	96.05 36
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
无先验							92.71 109	92.61 108	62.03 288				97.01 83	66.63 208		93.97 111

APD-MVS		85.93 43	85.99 40	85.76 85	95.98 26	65.21 148	93.59 81	92.58 109	66.54 251	86.17 36	95.88 28	63.83 79	97.00 84	86.39 53	92.94 53	95.06 71
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
1314		80.70 125	78.95 141	85.94 77	87.77 193	67.56 90	87.91 251	92.55 110	72.17 167	67.44 235	93.09 98	50.27 219	97.04 82	71.68 164	87.64 107	93.23 133

MP-MVS-pluss		85.24 51	85.13 50	85.56 90	91.42 111	65.59 139	91.54 159	92.51 111	74.56 114	80.62 84	95.64 32	59.15 130	97.00 84	86.94 49	93.80 39	94.07 107
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
WR-MVS		76.76 193	75.74 187	79.82 237	84.60 242	62.27 217	92.60 116	92.51 111	76.06 97	67.87 231	85.34 213	56.76 153	90.24 289	62.20 247	63.69 283	86.94 237

OpenMVS	70.45 11	78.54 166	75.92 184	86.41 66	85.93 225	71.68 16	92.74 107	92.51 111	66.49 252	64.56 261	91.96 124	43.88 266	98.10 35	54.61 279	90.65 85	89.44 201

CHOSEN 1792x2688		84.98 55	83.45 67	89.57 10	89.94 138	75.14 5	92.07 135	92.32 114	81.87 24	75.68 135	88.27 179	60.18 116	98.60 25	80.46 98	90.27 89	94.96 75

CP-MVS		83.71 78	83.40 71	84.65 117	93.14 66	63.84 180	94.59 46	92.28 115	71.03 202	77.41 119	94.92 54	55.21 172	96.19 112	81.32 92	90.70 84	93.91 114

MP-MVS		85.02 53	84.97 53	85.17 102	92.60 81	64.27 174	93.24 91	92.27 116	73.13 142	79.63 94	94.43 67	61.90 100	97.17 75	85.00 62	92.56 57	94.06 108
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTGPA								92.23 117

MTAPA		83.91 73	83.38 72	85.50 91	91.89 99	65.16 150	81.75 299	92.23 117	75.32 106	80.53 85	95.21 47	56.06 164	97.16 76	84.86 65	92.55 58	94.18 99

VPNet		78.82 158	77.53 160	82.70 165	84.52 244	66.44 119	93.93 64	92.23 117	80.46 38	72.60 168	88.38 177	49.18 230	93.13 224	72.47 155	63.97 281	88.55 211

ACMMP		81.49 112	80.67 113	83.93 137	91.71 103	62.90 206	92.13 130	92.22 120	71.79 180	71.68 184	93.49 94	50.32 217	96.96 90	78.47 114	84.22 137	91.93 165
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
PGM-MVS		83.25 84	82.70 85	84.92 107	92.81 75	64.07 177	90.44 198	92.20 121	71.28 196	77.23 122	94.43 67	55.17 173	97.31 67	79.33 105	91.38 76	93.37 128

jason		86.40 35	86.17 38	87.11 42	86.16 219	70.54 26	95.71 22	92.19 122	82.00 23	84.58 52	94.34 74	61.86 101	95.53 146	87.76 38	90.89 82	95.27 64
jason: jason.
tt0805		73.07 236	70.73 246	80.07 229	78.37 315	57.05 294	87.78 253	92.18 123	61.23 295	67.04 241	86.49 201	31.35 324	94.58 175	65.06 228	67.12 254	88.57 210

CLD-MVS		82.73 92	82.35 92	83.86 138	87.90 190	67.65 89	95.45 26	92.18 123	85.06 8	72.58 169	92.27 120	52.46 202	95.78 127	84.18 69	79.06 168	88.16 218
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS_Test		84.16 69	83.20 74	87.05 45	91.56 107	69.82 37	89.99 216	92.05 125	77.77 76	82.84 65	86.57 200	63.93 78	96.09 116	74.91 137	89.18 96	95.25 67

EIA-MVS		84.84 56	84.88 54	84.69 116	91.30 114	62.36 214	93.85 69	92.04 126	79.45 48	79.33 98	94.28 77	62.42 96	96.35 108	80.05 99	91.25 79	95.38 54

WR-MVS_H		70.59 257	69.94 252	72.53 310	81.03 280	51.43 322	87.35 260	92.03 127	67.38 245	60.23 290	80.70 272	55.84 167	83.45 337	46.33 314	58.58 318	82.72 302

FMVSNet3		77.73 179	76.04 182	82.80 162	91.20 117	68.99 56	91.87 145	91.99 128	73.35 139	67.04 241	83.19 238	56.62 157	92.14 260	59.80 261	69.34 238	87.28 231

DP-MVS Recon		82.73 92	81.65 99	85.98 75	97.31 4	67.06 103	95.15 34	91.99 128	69.08 231	76.50 130	93.89 86	54.48 181	98.20 33	70.76 170	85.66 124	92.69 144

EPNet_dtu		78.80 159	79.26 138	77.43 269	88.06 185	49.71 331	91.96 143	91.95 130	77.67 78	76.56 129	91.28 137	58.51 134	90.20 291	56.37 273	80.95 156	92.39 151
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FOURS1					93.95 45	61.77 224	93.96 62	91.92 131	62.14 287	86.57 33

ETV-MVS		86.01 42	86.11 39	85.70 87	90.21 134	67.02 106	93.43 88	91.92 131	81.21 32	84.13 58	94.07 83	60.93 110	95.63 137	89.28 28	89.81 90	94.46 96

CS-MVS-test		86.14 40	87.01 29	83.52 147	92.63 80	59.36 267	95.49 25	91.92 131	80.09 40	85.46 45	95.53 35	61.82 103	95.77 129	86.77 51	93.37 48	95.41 52

LFMVS		84.34 63	82.73 84	89.18 12	94.76 33	73.25 9	94.99 40	91.89 134	71.90 173	82.16 70	93.49 94	47.98 241	97.05 79	82.55 81	84.82 128	97.25 7

casdiffmvs_mvg		85.66 47	85.18 49	87.09 43	88.22 182	69.35 48	93.74 76	91.89 134	81.47 27	80.10 88	91.45 132	64.80 68	96.35 108	87.23 46	87.69 106	95.58 48
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS		85.80 45	86.65 34	83.27 155	92.00 94	58.92 272	95.31 29	91.86 136	79.97 41	84.82 50	95.40 36	62.26 97	95.51 147	86.11 55	92.08 64	95.37 55

HPM-MVS		83.25 84	82.95 79	84.17 132	92.25 86	62.88 207	90.91 184	91.86 136	70.30 214	77.12 123	93.96 85	56.75 154	96.28 110	82.04 84	91.34 78	93.34 129
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		82.96 90	82.44 90	84.52 121	92.83 71	62.92 205	92.76 106	91.85 138	71.52 192	75.61 138	94.24 78	53.48 194	96.99 87	78.97 109	90.73 83	93.64 123

XXY-MVS		77.94 176	76.44 177	82.43 171	82.60 268	64.44 165	92.01 138	91.83 139	73.59 136	70.00 201	85.82 210	54.43 182	94.76 165	69.63 180	68.02 249	88.10 219

baseline		85.01 54	84.44 57	86.71 54	88.33 177	68.73 61	90.24 207	91.82 140	81.05 34	81.18 77	92.50 112	63.69 82	96.08 118	84.45 68	86.71 117	95.32 59

casdiffmvs		85.37 49	84.87 55	86.84 49	88.25 180	69.07 53	93.04 98	91.76 141	81.27 31	80.84 83	92.07 123	64.23 74	96.06 119	84.98 63	87.43 109	95.39 53
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
NR-MVSNet		76.05 202	74.59 198	80.44 219	82.96 266	62.18 218	90.83 189	91.73 142	77.12 86	60.96 287	86.35 202	59.28 129	91.80 268	60.74 254	61.34 303	87.35 229

PVSNet_Blended_VisFu		83.97 72	83.50 65	85.39 95	90.02 136	66.59 117	93.77 74	91.73 142	77.43 85	77.08 125	89.81 162	63.77 81	96.97 89	79.67 101	88.21 102	92.60 147

FA-MVS(test-final)		79.12 151	77.23 167	84.81 112	90.54 127	63.98 179	81.35 305	91.71 144	71.09 201	74.85 145	82.94 239	52.85 198	97.05 79	67.97 196	81.73 151	93.41 127

canonicalmvs		86.85 31	86.25 37	88.66 17	91.80 101	71.92 14	93.54 83	91.71 144	80.26 39	87.55 27	95.25 45	63.59 85	96.93 94	88.18 35	84.34 132	97.11 8

HQP3-MVS								91.70 146							78.90 169

HQP-MVS		81.14 117	80.64 114	82.64 167	87.54 195	63.66 190	94.06 57	91.70 146	79.80 43	74.18 150	90.30 152	51.63 209	95.61 139	77.63 119	78.90 169	88.63 208

baseline1		81.84 107	81.03 108	84.28 130	91.60 105	66.62 115	91.08 181	91.66 148	81.87 24	74.86 144	91.67 130	69.98 36	94.92 163	71.76 162	64.75 273	91.29 178

FMVSNet2		76.07 199	74.01 210	82.26 179	88.85 162	67.66 88	91.33 171	91.61 149	70.84 205	65.98 249	82.25 247	48.03 238	92.00 265	58.46 266	68.73 244	87.10 234

114514_t		79.17 150	77.67 156	83.68 144	95.32 29	65.53 142	92.85 105	91.60 150	63.49 272	67.92 227	90.63 145	46.65 248	95.72 135	67.01 206	83.54 138	89.79 195

test-LLR		80.10 135	79.56 130	81.72 193	86.93 208	61.17 233	92.70 110	91.54 151	71.51 193	75.62 136	86.94 197	53.83 187	92.38 254	72.21 157	84.76 130	91.60 167

test-mter		79.96 138	79.38 136	81.72 193	86.93 208	61.17 233	92.70 110	91.54 151	73.85 128	75.62 136	86.94 197	49.84 224	92.38 254	72.21 157	84.76 130	91.60 167

DU-MVS		76.86 188	75.84 185	79.91 234	82.96 266	60.26 252	91.26 174	91.54 151	76.46 95	68.88 214	86.35 202	56.16 161	92.13 261	66.38 213	62.55 288	87.35 229

旧先验1					91.94 95	60.74 245		91.50 154			94.36 69	65.23 62			91.84 67	94.55 88

VDD-MVS		83.06 87	81.81 98	86.81 51	90.86 123	67.70 87	95.40 27	91.50 154	75.46 103	81.78 72	92.34 119	40.09 278	97.13 77	86.85 50	82.04 147	95.60 47

新几何1				84.73 114	92.32 84	64.28 173		91.46 156	59.56 307	79.77 92	92.90 104	56.95 152	96.57 103	63.40 237	92.91 54	93.34 129

tpm2		79.80 141	77.95 154	85.34 97	88.28 178	68.26 73	81.56 302	91.42 157	70.11 216	77.59 118	80.50 276	67.40 45	94.26 191	67.34 203	77.35 185	93.51 125

TranMVSNet+NR-MVSNet		75.86 207	74.52 201	79.89 235	82.44 269	60.64 248	91.37 169	91.37 158	76.63 92	67.65 233	86.21 206	52.37 203	91.55 273	61.84 249	60.81 306	87.48 224

test2506		83.29 82	82.92 80	84.37 126	88.39 175	63.18 198	92.01 138	91.35 159	77.66 79	78.49 110	91.42 133	64.58 71	95.09 157	73.19 144	89.23 94	94.85 77

VDDNet		80.50 128	78.26 148	87.21 39	86.19 218	69.79 38	94.48 47	91.31 160	60.42 299	79.34 97	90.91 141	38.48 286	96.56 104	82.16 82	81.05 155	95.27 64

HQP_MVS		80.34 131	79.75 127	82.12 184	86.94 206	62.42 212	93.13 94	91.31 160	78.81 63	72.53 170	89.14 168	50.66 215	95.55 144	76.74 122	78.53 174	88.39 215

plane_prior5								91.31 160					95.55 144	76.74 122	78.53 174	88.39 215

SR-MVS		82.81 91	82.58 87	83.50 150	93.35 58	61.16 235	92.23 128	91.28 163	64.48 265	81.27 75	95.28 41	53.71 190	95.86 125	82.87 78	88.77 99	93.49 126

nrg030		80.93 122	79.86 125	84.13 133	83.69 257	68.83 59	93.23 92	91.20 164	75.55 102	75.06 143	88.22 183	63.04 93	94.74 167	81.88 85	66.88 256	88.82 206

EPMVS		78.49 167	75.98 183	86.02 74	91.21 116	69.68 42	80.23 314	91.20 164	75.25 107	72.48 172	78.11 298	54.65 177	93.69 215	57.66 270	83.04 140	94.69 83

hse-mvs2		81.12 119	81.11 107	81.16 204	86.52 212	57.48 289	89.40 228	91.16 166	81.45 28	82.73 66	90.49 148	60.11 117	94.58 175	87.69 39	60.41 311	91.41 172

AUN-MVS		78.37 168	77.43 161	81.17 203	86.60 211	57.45 290	89.46 227	91.16 166	74.11 121	74.40 149	90.49 148	55.52 168	94.57 177	74.73 140	60.43 310	91.48 170

cascas		78.18 171	75.77 186	85.41 94	87.14 204	69.11 51	92.96 101	91.15 168	66.71 250	70.47 192	86.07 207	37.49 297	96.48 107	70.15 175	79.80 162	90.65 184

tpm		78.58 165	77.03 169	83.22 156	85.94 224	64.56 159	83.21 291	91.14 169	78.31 68	73.67 158	79.68 288	64.01 76	92.09 263	66.07 217	71.26 229	93.03 139

PCF-MVS	73.15 9	79.29 148	77.63 158	84.29 129	86.06 220	65.96 131	87.03 263	91.10 170	69.86 220	69.79 205	90.64 143	57.54 143	96.59 101	64.37 232	82.29 144	90.32 188
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Anonymous20240529		76.84 191	74.15 207	84.88 109	91.02 118	64.95 156	93.84 72	91.09 171	53.57 329	73.00 161	87.42 193	35.91 307	97.32 66	69.14 187	72.41 221	92.36 152

DROMVSNet		84.53 60	85.04 52	83.01 159	89.34 150	61.37 232	94.42 48	91.09 171	77.91 74	83.24 62	94.20 79	58.37 135	95.40 148	85.35 59	91.41 75	92.27 159

FE-MVS		75.97 205	73.02 221	84.82 111	89.78 140	65.56 140	77.44 329	91.07 173	64.55 264	72.66 166	79.85 286	46.05 257	96.69 99	54.97 278	80.82 158	92.21 161

PS-MVSNAJss		77.26 185	76.31 179	80.13 228	80.64 285	59.16 269	90.63 197	91.06 174	72.80 149	68.58 220	84.57 223	53.55 191	93.96 207	72.97 146	71.96 223	87.27 232

PVSNet	73.49 8	80.05 136	78.63 143	84.31 128	90.92 121	64.97 155	92.47 122	91.05 175	79.18 54	72.43 174	90.51 147	37.05 303	94.06 199	68.06 195	86.00 122	93.90 116

API-MVS		82.28 99	80.53 116	87.54 33	96.13 22	70.59 25	93.63 79	91.04 176	65.72 258	75.45 140	92.83 108	56.11 163	98.89 19	64.10 233	89.75 93	93.15 135

APD-MVS_3200maxsize		81.64 111	81.32 102	82.59 169	92.36 83	58.74 274	91.39 166	91.01 177	63.35 274	79.72 93	94.62 63	51.82 205	96.14 114	79.71 100	87.93 104	92.89 143

MVP-Stereo		77.12 187	76.23 180	79.79 238	81.72 276	66.34 122	89.29 229	90.88 178	70.56 212	62.01 283	82.88 240	49.34 227	94.13 194	65.55 224	93.80 39	78.88 336
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UGNet		79.87 140	78.68 142	83.45 152	89.96 137	61.51 229	92.13 130	90.79 179	76.83 90	78.85 107	86.33 204	38.16 289	96.17 113	67.93 198	87.17 110	92.67 145
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
TAMVS		80.37 130	79.45 133	83.13 158	85.14 234	63.37 193	91.23 175	90.76 180	74.81 113	72.65 167	88.49 172	60.63 112	92.95 228	69.41 183	81.95 148	93.08 138

MVSFormer		83.75 77	82.88 81	86.37 67	89.24 155	71.18 19	89.07 235	90.69 181	65.80 256	87.13 29	94.34 74	64.99 64	92.67 243	72.83 148	91.80 68	95.27 64

test_djsdf		73.76 233	72.56 229	77.39 270	77.00 325	53.93 311	89.07 235	90.69 181	65.80 256	63.92 267	82.03 250	43.14 270	92.67 243	72.83 148	68.53 245	85.57 267

PMMVS		81.98 106	82.04 94	81.78 191	89.76 142	56.17 298	91.13 180	90.69 181	77.96 72	80.09 89	93.57 92	46.33 253	94.99 159	81.41 90	87.46 108	94.17 100

dcpmvs_2		87.37 25	87.55 24	86.85 48	95.04 32	68.20 76	90.36 202	90.66 184	79.37 50	81.20 76	93.67 89	74.73 15	96.55 105	90.88 21	92.00 65	95.82 42

CDS-MVSNet		81.43 113	80.74 111	83.52 147	86.26 217	64.45 164	92.09 133	90.65 185	75.83 100	73.95 156	89.81 162	63.97 77	92.91 233	71.27 165	82.82 142	93.20 134
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
mvs_anonymous		81.36 114	79.99 123	85.46 92	90.39 131	68.40 68	86.88 268	90.61 186	74.41 115	70.31 197	84.67 221	63.79 80	92.32 258	73.13 145	85.70 123	95.67 44

SR-MVS-dyc-post		81.06 120	80.70 112	82.15 182	92.02 91	58.56 276	90.90 185	90.45 187	62.76 281	78.89 102	94.46 65	51.26 212	95.61 139	78.77 112	86.77 115	92.28 156

RE-MVS-def			80.48 117		92.02 91	58.56 276	90.90 185	90.45 187	62.76 281	78.89 102	94.46 65	49.30 228		78.77 112	86.77 115	92.28 156

RPMNet		70.42 259	65.68 276	84.63 119	83.15 263	67.96 81	70.25 340	90.45 187	46.83 348	69.97 202	65.10 347	56.48 160	95.30 154	35.79 349	73.13 212	90.64 185

xiu_mvs_v1_base_debu		82.16 101	81.12 104	85.26 99	86.42 213	68.72 62	92.59 118	90.44 190	73.12 143	84.20 55	94.36 69	38.04 291	95.73 131	84.12 70	86.81 112	91.33 173

xiu_mvs_v1_base		82.16 101	81.12 104	85.26 99	86.42 213	68.72 62	92.59 118	90.44 190	73.12 143	84.20 55	94.36 69	38.04 291	95.73 131	84.12 70	86.81 112	91.33 173

xiu_mvs_v1_base_debi		82.16 101	81.12 104	85.26 99	86.42 213	68.72 62	92.59 118	90.44 190	73.12 143	84.20 55	94.36 69	38.04 291	95.73 131	84.12 70	86.81 112	91.33 173

GBi-Net		75.65 210	73.83 212	81.10 207	88.85 162	65.11 151	90.01 213	90.32 193	70.84 205	67.04 241	80.25 281	48.03 238	91.54 274	59.80 261	69.34 238	86.64 240

test1		75.65 210	73.83 212	81.10 207	88.85 162	65.11 151	90.01 213	90.32 193	70.84 205	67.04 241	80.25 281	48.03 238	91.54 274	59.80 261	69.34 238	86.64 240

FMVSNet1		72.71 244	69.91 253	81.10 207	83.60 259	65.11 151	90.01 213	90.32 193	63.92 268	63.56 271	80.25 281	36.35 306	91.54 274	54.46 280	66.75 257	86.64 240

PVSNet_0	68.08 15	71.81 249	68.32 264	82.27 177	84.68 240	62.31 216	88.68 241	90.31 196	75.84 99	57.93 306	80.65 275	37.85 294	94.19 193	69.94 177	29.05 368	90.31 189

OPM-MVS		79.00 153	78.09 150	81.73 192	83.52 260	63.83 181	91.64 158	90.30 197	76.36 96	71.97 179	89.93 161	46.30 254	95.17 156	75.10 133	77.70 179	86.19 251
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CP-MVSNet		70.50 258	69.91 253	72.26 313	80.71 283	51.00 325	87.23 262	90.30 197	67.84 240	59.64 292	82.69 242	50.23 220	82.30 345	51.28 289	59.28 314	83.46 291

KD-MVS_2432*1600		69.03 269	66.37 272	77.01 276	85.56 228	61.06 236	81.44 303	90.25 199	67.27 246	58.00 304	76.53 311	54.49 179	87.63 315	48.04 304	35.77 360	82.34 308

miper_refine_blended		69.03 269	66.37 272	77.01 276	85.56 228	61.06 236	81.44 303	90.25 199	67.27 246	58.00 304	76.53 311	54.49 179	87.63 315	48.04 304	35.77 360	82.34 308

v148		76.19 197	74.47 202	81.36 199	80.05 293	64.44 165	91.75 154	90.23 201	73.68 134	67.13 240	80.84 271	55.92 166	93.86 213	68.95 189	61.73 299	85.76 265

v2v482		77.42 183	75.65 189	82.73 164	80.38 287	67.13 102	91.85 147	90.23 201	75.09 109	69.37 206	83.39 236	53.79 189	94.44 184	71.77 161	65.00 270	86.63 243

v1144		76.73 194	74.88 194	82.27 177	80.23 292	66.60 116	91.68 156	90.21 203	73.69 133	69.06 211	81.89 251	52.73 200	94.40 185	69.21 186	65.23 267	85.80 262

GA-MVS		78.33 170	76.23 180	84.65 117	83.65 258	66.30 123	91.44 160	90.14 204	76.01 98	70.32 196	84.02 229	42.50 271	94.72 168	70.98 167	77.00 189	92.94 141

MDTV_nov1_ep13			72.61 228		89.06 158	68.48 66	80.33 312	90.11 205	71.84 178	71.81 181	75.92 317	53.01 197	93.92 209	48.04 304	73.38 210

D2MVS		73.80 231	72.02 235	79.15 251	79.15 303	62.97 201	88.58 243	90.07 206	72.94 146	59.22 295	78.30 295	42.31 273	92.70 242	65.59 223	72.00 222	81.79 314

TR-MVS		78.77 161	77.37 166	82.95 160	90.49 128	60.88 239	93.67 77	90.07 206	70.08 217	74.51 148	91.37 136	45.69 258	95.70 136	60.12 259	80.32 160	92.29 155

Anonymous20231211		73.08 235	70.39 249	81.13 205	90.62 126	63.33 194	91.40 164	90.06 208	51.84 334	64.46 264	80.67 274	36.49 305	94.07 198	63.83 235	64.17 278	85.98 258

jajsoiax		73.05 237	71.51 241	77.67 265	77.46 322	54.83 307	88.81 239	90.04 209	69.13 230	62.85 278	83.51 234	31.16 325	92.75 239	70.83 168	69.80 234	85.43 270

HyFIR lowres test		81.03 121	79.56 130	85.43 93	87.81 192	68.11 78	90.18 208	90.01 210	70.65 210	72.95 163	86.06 208	63.61 84	94.50 183	75.01 135	79.75 163	93.67 121

ACMM	69.62 13	74.34 224	72.73 226	79.17 249	84.25 251	57.87 282	90.36 202	89.93 211	63.17 278	65.64 251	86.04 209	37.79 295	94.10 195	65.89 218	71.52 226	85.55 268
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CL-MVSNet_self_test		69.92 262	68.09 265	75.41 287	73.25 337	55.90 301	90.05 212	89.90 212	69.96 218	61.96 284	76.54 310	51.05 213	87.64 314	49.51 298	50.59 338	82.70 304

UnsupCasMVSNet_eth		65.79 293	63.10 294	73.88 300	70.71 345	50.29 329	81.09 306	89.88 213	72.58 153	49.25 337	74.77 322	32.57 318	87.43 318	55.96 275	41.04 353	83.90 285

testdata				81.34 200	89.02 159	57.72 284		89.84 214	58.65 311	85.32 47	94.09 81	57.03 147	93.28 222	69.34 184	90.56 87	93.03 139

mvs_tets		72.71 244	71.11 242	77.52 266	77.41 323	54.52 309	88.45 245	89.76 215	68.76 235	62.70 279	83.26 237	29.49 329	92.71 240	70.51 174	69.62 236	85.34 272

v1192		75.98 204	73.92 211	82.15 182	79.73 294	66.24 125	91.22 176	89.75 216	72.67 151	68.49 221	81.42 261	49.86 223	94.27 189	67.08 205	65.02 269	85.95 259

PS-CasMVS		69.86 264	69.13 258	72.07 316	80.35 289	50.57 327	87.02 264	89.75 216	67.27 246	59.19 296	82.28 246	46.58 249	82.24 346	50.69 291	59.02 315	83.39 293

dp		75.01 219	72.09 234	83.76 139	89.28 153	66.22 126	79.96 319	89.75 216	71.16 198	67.80 232	77.19 306	51.81 206	92.54 249	50.39 292	71.44 228	92.51 150

LPG-MVS_test		75.82 208	74.58 199	79.56 244	84.31 249	59.37 265	90.44 198	89.73 219	69.49 223	64.86 256	88.42 173	38.65 284	94.30 187	72.56 153	72.76 216	85.01 276

LGP-MVS_train				79.56 244	84.31 249	59.37 265		89.73 219	69.49 223	64.86 256	88.42 173	38.65 284	94.30 187	72.56 153	72.76 216	85.01 276

tpmrst		80.57 126	79.14 140	84.84 110	90.10 135	68.28 72	81.70 300	89.72 221	77.63 81	75.96 132	79.54 290	64.94 66	92.71 240	75.43 130	77.28 187	93.55 124

v144192		76.05 202	74.03 209	82.12 184	79.50 298	66.55 118	91.39 166	89.71 222	72.30 162	68.17 223	81.33 263	51.75 207	94.03 204	67.94 197	64.19 277	85.77 263

TAPA-MVS	70.22 12	74.94 220	73.53 216	79.17 249	90.40 130	52.07 319	89.19 233	89.61 223	62.69 283	70.07 199	92.67 110	48.89 235	94.32 186	38.26 344	79.97 161	91.12 180
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PatchmatchNet		77.46 182	74.63 197	85.96 76	89.55 147	70.35 28	79.97 318	89.55 224	72.23 164	70.94 189	76.91 309	57.03 147	92.79 238	54.27 281	81.17 154	94.74 82
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v1921920		75.63 212	73.49 217	82.06 188	79.38 299	66.35 121	91.07 183	89.48 225	71.98 170	67.99 224	81.22 266	49.16 232	93.90 210	66.56 209	64.56 276	85.92 261

v7n		71.31 254	68.65 259	79.28 247	76.40 327	60.77 242	86.71 269	89.45 226	64.17 267	58.77 300	78.24 296	44.59 264	93.54 217	57.76 268	61.75 298	83.52 289

test0.0.03 1		72.76 242	72.71 227	72.88 308	80.25 291	47.99 337	91.22 176	89.45 226	71.51 193	62.51 281	87.66 189	53.83 187	85.06 328	50.16 294	67.84 252	85.58 266

test222					89.77 141	61.60 228	89.55 223	89.42 228	56.83 320	77.28 121	92.43 116	52.76 199			91.14 81	93.09 137

V42		76.46 196	74.55 200	82.19 181	79.14 304	67.82 84	90.26 206	89.42 228	73.75 131	68.63 219	81.89 251	51.31 211	94.09 196	71.69 163	64.84 271	84.66 279

BH-w/o		80.49 129	79.30 137	84.05 135	90.83 124	64.36 171	93.60 80	89.42 228	74.35 117	69.09 209	90.15 157	55.23 171	95.61 139	64.61 230	86.43 121	92.17 162

pm-mvs1		72.89 240	71.09 243	78.26 260	79.10 305	57.62 287	90.80 190	89.30 231	67.66 242	62.91 277	81.78 253	49.11 233	92.95 228	60.29 258	58.89 316	84.22 282

v8		75.35 214	73.26 219	81.61 195	80.67 284	66.82 109	89.54 224	89.27 232	71.65 184	63.30 274	80.30 280	54.99 175	94.06 199	67.33 204	62.33 291	83.94 284

diffmvs		84.28 64	83.83 62	85.61 89	87.40 199	68.02 80	90.88 187	89.24 233	80.54 37	81.64 73	92.52 111	59.83 121	94.52 182	87.32 44	85.11 126	94.29 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PEN-MVS		69.46 266	68.56 260	72.17 315	79.27 300	49.71 331	86.90 267	89.24 233	67.24 249	59.08 297	82.51 245	47.23 246	83.54 336	48.42 302	57.12 319	83.25 294

UniMVSNet_ETH3D		72.74 243	70.53 248	79.36 246	78.62 313	56.64 296	85.01 275	89.20 235	63.77 270	64.84 258	84.44 225	34.05 312	91.86 267	63.94 234	70.89 231	89.57 199

SCA		75.82 208	72.76 225	85.01 105	86.63 210	70.08 30	81.06 307	89.19 236	71.60 189	70.01 200	77.09 307	45.53 259	90.25 286	60.43 256	73.27 211	94.68 84

EG-PatchMatch MVS		68.55 274	65.41 279	77.96 263	78.69 311	62.93 203	89.86 218	89.17 237	60.55 298	50.27 332	77.73 301	22.60 345	94.06 199	47.18 310	72.65 218	76.88 344

HPM-MVS_fast		80.25 132	79.55 132	82.33 175	91.55 108	59.95 257	91.32 172	89.16 238	65.23 262	74.71 147	93.07 100	47.81 243	95.74 130	74.87 139	88.23 101	91.31 177

miper_enhance_ethall		78.86 157	77.97 153	81.54 196	88.00 188	65.17 149	91.41 162	89.15 239	75.19 108	68.79 216	83.98 230	67.17 46	92.82 235	72.73 151	65.30 264	86.62 244

Fast-Effi-MVS+		81.14 117	80.01 122	84.51 122	90.24 133	65.86 133	94.12 56	89.15 239	73.81 130	75.37 141	88.26 180	57.26 144	94.53 181	66.97 207	84.92 127	93.15 135

Vis-MVSNet (Re-imp)		79.24 149	79.57 129	78.24 261	88.46 171	52.29 318	90.41 200	89.12 241	74.24 119	69.13 208	91.91 125	65.77 58	90.09 293	59.00 265	88.09 103	92.33 153

v1240		75.21 217	72.98 222	81.88 190	79.20 301	66.00 129	90.75 192	89.11 242	71.63 188	67.41 237	81.22 266	47.36 245	93.87 211	65.46 225	64.72 274	85.77 263

v10		74.77 221	72.54 230	81.46 197	80.33 290	66.71 113	89.15 234	89.08 243	70.94 203	63.08 275	79.86 285	52.52 201	94.04 202	65.70 221	62.17 292	83.64 286

ACMP	71.68 10	75.58 213	74.23 206	79.62 242	84.97 238	59.64 260	90.80 190	89.07 244	70.39 213	62.95 276	87.30 195	38.28 287	93.87 211	72.89 147	71.45 227	85.36 271
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UnsupCasMVSNet_bld		61.60 309	57.71 313	73.29 305	68.73 351	51.64 320	78.61 322	89.05 245	57.20 317	46.11 342	61.96 353	28.70 332	88.60 301	50.08 295	38.90 357	79.63 331

CANet_DTU		84.09 70	83.52 64	85.81 82	90.30 132	66.82 109	91.87 145	89.01 246	85.27 7	86.09 37	93.74 88	47.71 244	96.98 88	77.90 118	89.78 92	93.65 122

UA-Net		80.02 137	79.65 128	81.11 206	89.33 152	57.72 284	86.33 271	89.00 247	77.44 84	81.01 80	89.15 167	59.33 128	95.90 124	61.01 253	84.28 135	89.73 197

MVS_111021_LR		82.02 105	81.52 100	83.51 149	88.42 173	62.88 207	89.77 220	88.93 248	76.78 91	75.55 139	93.10 97	50.31 218	95.38 150	83.82 74	87.02 111	92.26 160

miper_lstm_enhance		73.05 237	71.73 239	77.03 275	83.80 255	58.32 278	81.76 298	88.88 249	69.80 221	61.01 286	78.23 297	57.19 145	87.51 317	65.34 226	59.53 313	85.27 274

anonymousdsp		71.14 255	69.37 257	76.45 281	72.95 338	54.71 308	84.19 279	88.88 249	61.92 290	62.15 282	79.77 287	38.14 290	91.44 279	68.90 190	67.45 253	83.21 295

cl22		77.94 176	76.78 173	81.42 198	87.57 194	64.93 157	90.67 193	88.86 251	72.45 157	67.63 234	82.68 243	64.07 75	92.91 233	71.79 160	65.30 264	86.44 245

MIMVSNet		71.64 250	68.44 262	81.23 202	81.97 275	64.44 165	73.05 336	88.80 252	69.67 222	64.59 259	74.79 321	32.79 316	87.82 311	53.99 282	76.35 194	91.42 171

IterMVS-LS		76.49 195	75.18 193	80.43 220	84.49 245	62.74 209	90.64 195	88.80 252	72.40 159	65.16 255	81.72 254	60.98 109	92.27 259	67.74 199	64.65 275	86.29 247
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
RRT_MVS		74.44 223	72.97 223	78.84 254	82.36 270	57.66 286	89.83 219	88.79 254	70.61 211	64.58 260	84.89 218	39.24 280	92.65 246	70.11 176	66.34 260	86.21 250

cl____		76.07 199	74.67 195	80.28 223	85.15 233	61.76 225	90.12 209	88.73 255	71.16 198	65.43 252	81.57 258	61.15 106	92.95 228	66.54 210	62.17 292	86.13 254

DIV-MVS_self_test		76.07 199	74.67 195	80.28 223	85.14 234	61.75 226	90.12 209	88.73 255	71.16 198	65.42 253	81.60 257	61.15 106	92.94 232	66.54 210	62.16 294	86.14 252

JIA-IIPM		66.06 291	62.45 299	76.88 279	81.42 279	54.45 310	57.49 362	88.67 257	49.36 341	63.86 268	46.86 360	56.06 164	90.25 286	49.53 297	68.83 242	85.95 259

OMC-MVS		78.67 164	77.91 155	80.95 213	85.76 226	57.40 291	88.49 244	88.67 257	73.85 128	72.43 174	92.10 122	49.29 229	94.55 180	72.73 151	77.89 177	90.91 182

miper_ehance_all_eth		77.60 180	76.44 177	81.09 210	85.70 227	64.41 168	90.65 194	88.64 259	72.31 161	67.37 239	82.52 244	64.77 69	92.64 247	70.67 171	65.30 264	86.24 249

BH-untuned		78.68 162	77.08 168	83.48 151	89.84 139	63.74 184	92.70 110	88.59 260	71.57 190	66.83 245	88.65 171	51.75 207	95.39 149	59.03 264	84.77 129	91.32 176

DTE-MVSNet		68.46 276	67.33 268	71.87 318	77.94 319	49.00 334	86.16 272	88.58 261	66.36 253	58.19 301	82.21 248	46.36 250	83.87 334	44.97 321	55.17 326	82.73 301

CPTT-MVS		79.59 143	79.16 139	80.89 215	91.54 109	59.80 259	92.10 132	88.54 262	60.42 299	72.96 162	93.28 96	48.27 237	92.80 237	78.89 111	86.50 120	90.06 191

CVMVSNet		74.04 228	74.27 205	73.33 304	85.33 230	43.94 352	89.53 225	88.39 263	54.33 328	70.37 195	90.13 158	49.17 231	84.05 331	61.83 250	79.36 165	91.99 164

1112_ss		80.56 127	79.83 126	82.77 163	88.65 167	60.78 241	92.29 125	88.36 264	72.58 153	72.46 173	94.95 51	65.09 63	93.42 221	66.38 213	77.71 178	94.10 104

tpmvs		72.88 241	69.76 255	82.22 180	90.98 119	67.05 104	78.22 326	88.30 265	63.10 279	64.35 266	74.98 320	55.09 174	94.27 189	43.25 324	69.57 237	85.34 272

PLC	68.80 14	75.23 216	73.68 215	79.86 236	92.93 70	58.68 275	90.64 195	88.30 265	60.90 296	64.43 265	90.53 146	42.38 272	94.57 177	56.52 272	76.54 192	86.33 246
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
eth_miper_zixun_eth		75.96 206	74.40 203	80.66 216	84.66 241	63.02 200	89.28 230	88.27 267	71.88 175	65.73 250	81.65 255	59.45 125	92.81 236	68.13 194	60.53 308	86.14 252

IS-MVSNet		80.14 134	79.41 134	82.33 175	87.91 189	60.08 256	91.97 142	88.27 267	72.90 148	71.44 187	91.73 129	61.44 105	93.66 216	62.47 246	86.53 119	93.24 132

Vis-MVSNet		80.92 123	79.98 124	83.74 140	88.48 170	61.80 223	93.44 87	88.26 269	73.96 126	77.73 115	91.76 127	49.94 222	94.76 165	65.84 219	90.37 88	94.65 87
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
c3_l		76.83 192	75.47 190	80.93 214	85.02 237	64.18 176	90.39 201	88.11 270	71.66 183	66.65 247	81.64 256	63.58 86	92.56 248	69.31 185	62.86 285	86.04 256

BH-RMVSNet		79.46 147	77.65 157	84.89 108	91.68 104	65.66 136	93.55 82	88.09 271	72.93 147	73.37 159	91.12 139	46.20 255	96.12 115	56.28 274	85.61 125	92.91 142

tpm cat1		75.30 215	72.21 233	84.58 120	88.52 168	67.77 85	78.16 327	88.02 272	61.88 291	68.45 222	76.37 313	60.65 111	94.03 204	53.77 284	74.11 205	91.93 165

Test_1112_low_res		79.56 144	78.60 144	82.43 171	88.24 181	60.39 251	92.09 133	87.99 273	72.10 169	71.84 180	87.42 193	64.62 70	93.04 225	65.80 220	77.30 186	93.85 118

AdaColmap		78.94 155	77.00 171	84.76 113	96.34 17	65.86 133	92.66 114	87.97 274	62.18 286	70.56 191	92.37 118	43.53 267	97.35 64	64.50 231	82.86 141	91.05 181

Effi-MVS+-dtu		76.14 198	75.28 192	78.72 255	83.22 262	55.17 305	89.87 217	87.78 275	75.42 104	67.98 225	81.43 260	45.08 262	92.52 250	75.08 134	71.63 224	88.48 212

PatchT		69.11 268	65.37 280	80.32 221	82.07 274	63.68 189	67.96 349	87.62 276	50.86 337	69.37 206	65.18 346	57.09 146	88.53 303	41.59 333	66.60 258	88.74 207

XVG-OURS		74.25 226	72.46 231	79.63 241	78.45 314	57.59 288	80.33 312	87.39 277	63.86 269	68.76 217	89.62 164	40.50 277	91.72 270	69.00 188	74.25 204	89.58 198

Anonymous20231206		67.53 284	65.78 274	72.79 309	74.95 331	47.59 339	88.23 247	87.32 278	61.75 293	58.07 303	77.29 304	37.79 295	87.29 319	42.91 326	63.71 282	83.48 290

XVG-OURS-SEG-HR		74.70 222	73.08 220	79.57 243	78.25 316	57.33 292	80.49 310	87.32 278	63.22 276	68.76 217	90.12 160	44.89 263	91.59 272	70.55 173	74.09 206	89.79 195

pmmvs4		73.92 230	71.81 238	80.25 225	79.17 302	65.24 147	87.43 259	87.26 280	67.64 244	63.46 272	83.91 231	48.96 234	91.53 277	62.94 241	65.49 263	83.96 283

pmmvs5		73.35 234	71.52 240	78.86 253	78.64 312	60.61 249	91.08 181	86.90 281	67.69 241	63.32 273	83.64 232	44.33 265	90.53 283	62.04 248	66.02 262	85.46 269

test_vis1_n_1920		81.66 110	82.01 95	80.64 217	82.24 271	55.09 306	94.76 44	86.87 282	81.67 26	84.40 54	94.63 62	38.17 288	94.67 172	91.98 13	83.34 139	92.16 163

test1111		80.84 124	80.02 121	83.33 153	87.87 191	60.76 243	92.62 115	86.86 283	77.86 75	75.73 134	91.39 135	46.35 251	94.70 171	72.79 150	88.68 100	94.52 92

ECVR-MVS		81.29 115	80.38 119	84.01 136	88.39 175	61.96 221	92.56 121	86.79 284	77.66 79	76.63 127	91.42 133	46.34 252	95.24 155	74.36 141	89.23 94	94.85 77

pmmvs6		67.57 283	64.76 283	76.00 285	72.82 340	53.37 313	88.71 240	86.78 285	53.19 330	57.58 308	78.03 299	35.33 309	92.41 253	55.56 276	54.88 328	82.21 311

MVS_0304		68.99 271	67.23 269	74.28 299	80.36 288	52.54 316	87.01 265	86.36 286	59.89 305	66.22 248	73.56 324	24.25 340	88.03 308	57.34 271	70.11 233	82.27 310

F-COLMAP		70.66 256	68.44 262	77.32 271	86.37 216	55.91 300	88.00 249	86.32 287	56.94 319	57.28 309	88.07 184	33.58 314	92.49 251	51.02 290	68.37 246	83.55 287

IterMVS		72.65 247	70.83 244	78.09 262	82.17 272	62.96 202	87.64 257	86.28 288	71.56 191	60.44 289	78.85 293	45.42 261	86.66 321	63.30 239	61.83 296	84.65 280
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet5		68.04 279	65.66 277	75.18 290	84.43 247	57.89 281	83.54 283	86.26 289	61.83 292	53.64 320	73.30 325	37.15 301	85.08 327	48.99 299	61.77 297	82.56 307

GeoE		78.90 156	77.43 161	83.29 154	88.95 161	62.02 219	92.31 124	86.23 290	70.24 215	71.34 188	89.27 165	54.43 182	94.04 202	63.31 238	80.81 159	93.81 119

EU-MVSNet		64.01 301	63.01 295	67.02 332	74.40 334	38.86 362	83.27 288	86.19 291	45.11 350	54.27 316	81.15 269	36.91 304	80.01 352	48.79 301	57.02 320	82.19 312

Effi-MVS+		83.82 75	82.76 83	86.99 47	89.56 146	69.40 44	91.35 170	86.12 292	72.59 152	83.22 63	92.81 109	59.60 124	96.01 123	81.76 86	87.80 105	95.56 49

IterMVS-SCA-FT		71.55 253	69.97 251	76.32 282	81.48 277	60.67 247	87.64 257	85.99 293	66.17 254	59.50 293	78.88 292	45.53 259	83.65 335	62.58 245	61.93 295	84.63 281

XVG-ACMP-BASELINE		68.04 279	65.53 278	75.56 286	74.06 335	52.37 317	78.43 323	85.88 294	62.03 288	58.91 299	81.21 268	20.38 350	91.15 280	60.69 255	68.18 247	83.16 296

ambc				69.61 322	61.38 361	41.35 355	49.07 367	85.86 295		50.18 334	66.40 344	10.16 364	88.14 307	45.73 317	44.20 347	79.32 334

CMPMVS	48.56 21	66.77 288	64.41 288	73.84 301	70.65 346	50.31 328	77.79 328	85.73 296	45.54 349	44.76 349	82.14 249	35.40 308	90.14 292	63.18 240	74.54 202	81.07 318
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Fast-Effi-MVS+-dtu		75.04 218	73.37 218	80.07 229	80.86 281	59.52 263	91.20 178	85.38 297	71.90 173	65.20 254	84.84 219	41.46 274	92.97 227	66.50 212	72.96 214	87.73 221

Anonymous202405211		77.96 175	75.33 191	85.87 79	93.73 52	64.52 160	94.85 42	85.36 298	62.52 284	76.11 131	90.18 155	29.43 330	97.29 68	68.51 193	77.24 188	95.81 43

Anonymous20240521		62.09 307	59.08 310	71.10 319	67.19 353	48.72 335	83.91 281	85.23 299	50.38 338	47.84 340	71.22 337	20.74 348	85.51 326	46.47 313	58.75 317	79.06 335

our_test_3		68.29 277	64.69 284	79.11 252	78.92 306	64.85 158	88.40 246	85.06 300	60.32 301	52.68 322	76.12 315	40.81 276	89.80 296	44.25 323	55.65 324	82.67 306

USDC		67.43 286	64.51 286	76.19 283	77.94 319	55.29 304	78.38 324	85.00 301	73.17 141	48.36 339	80.37 278	21.23 347	92.48 252	52.15 288	64.02 280	80.81 321

TransMVSNet (Re)		70.07 261	67.66 266	77.31 272	80.62 286	59.13 271	91.78 151	84.94 302	65.97 255	60.08 291	80.44 277	50.78 214	91.87 266	48.84 300	45.46 346	80.94 319

KD-MVS_self_test		60.87 311	58.60 311	67.68 329	66.13 355	39.93 359	75.63 334	84.70 303	57.32 316	49.57 335	68.45 341	29.55 328	82.87 341	48.09 303	47.94 342	80.25 328

ACMH	63.93 17	68.62 273	64.81 282	80.03 231	85.22 232	63.25 195	87.72 254	84.66 304	60.83 297	51.57 327	79.43 291	27.29 335	94.96 160	41.76 331	64.84 271	81.88 313
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Baseline_NR-MVSNet		73.99 229	72.83 224	77.48 268	80.78 282	59.29 268	91.79 149	84.55 305	68.85 232	68.99 212	80.70 272	56.16 161	92.04 264	62.67 244	60.98 305	81.11 317

MIMVSNet1		60.16 314	57.33 315	68.67 325	69.71 348	44.13 351	78.92 321	84.21 306	55.05 326	44.63 350	71.85 332	23.91 342	81.54 349	32.63 358	55.03 327	80.35 325

test20.03		63.83 302	62.65 298	67.38 331	70.58 347	39.94 358	86.57 270	84.17 307	63.29 275	51.86 325	77.30 303	37.09 302	82.47 343	38.87 343	54.13 330	79.73 330

MDA-MVSNet_test_wron		63.78 303	60.16 306	74.64 293	78.15 317	60.41 250	83.49 284	84.03 308	56.17 324	39.17 358	71.59 334	37.22 299	83.24 340	42.87 328	48.73 340	80.26 327

ADS-MVSNet		68.54 275	64.38 289	81.03 211	88.06 185	66.90 108	68.01 347	84.02 309	57.57 313	64.48 262	69.87 338	38.68 282	89.21 299	40.87 335	67.89 250	86.97 235

CR-MVSNet		73.79 232	70.82 245	82.70 165	83.15 263	67.96 81	70.25 340	84.00 310	73.67 135	69.97 202	72.41 328	57.82 140	89.48 297	52.99 287	73.13 212	90.64 185

Patchmtry		67.53 284	63.93 290	78.34 257	82.12 273	64.38 169	68.72 344	84.00 310	48.23 345	59.24 294	72.41 328	57.82 140	89.27 298	46.10 315	56.68 323	81.36 316

YYNet1		63.76 304	60.14 307	74.62 294	78.06 318	60.19 255	83.46 286	83.99 312	56.18 323	39.25 357	71.56 335	37.18 300	83.34 338	42.90 327	48.70 341	80.32 326

LTVRE_ROB	59.60 19	66.27 290	63.54 292	74.45 295	84.00 254	51.55 321	67.08 350	83.53 313	58.78 310	54.94 314	80.31 279	34.54 311	93.23 223	40.64 337	68.03 248	78.58 339
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
pmmvs-eth3d		65.53 295	62.32 300	75.19 289	69.39 350	59.59 261	82.80 295	83.43 314	62.52 284	51.30 329	72.49 326	32.86 315	87.16 320	55.32 277	50.73 337	78.83 337

OpenMVS_ROB	61.12 18	66.39 289	62.92 296	76.80 280	76.51 326	57.77 283	89.22 231	83.41 315	55.48 325	53.86 319	77.84 300	26.28 338	93.95 208	34.90 351	68.76 243	78.68 338

PatchMatch-RL		72.06 248	69.98 250	78.28 259	89.51 148	55.70 302	83.49 284	83.39 316	61.24 294	63.72 270	82.76 241	34.77 310	93.03 226	53.37 286	77.59 180	86.12 255

MSDG		69.54 265	65.73 275	80.96 212	85.11 236	63.71 186	84.19 279	83.28 317	56.95 318	54.50 315	84.03 228	31.50 322	96.03 121	42.87 328	69.13 241	83.14 297

CHOSEN 280x420		77.35 184	76.95 172	78.55 256	87.07 205	62.68 211	69.71 343	82.95 318	68.80 233	71.48 186	87.27 196	66.03 55	84.00 333	76.47 125	82.81 143	88.95 202

ppachtmachnet_test		67.72 281	63.70 291	79.77 239	78.92 306	66.04 128	88.68 241	82.90 319	60.11 303	55.45 312	75.96 316	39.19 281	90.55 282	39.53 339	52.55 334	82.71 303

iter_conf_final		81.74 109	80.93 109	84.18 131	92.66 79	69.10 52	92.94 102	82.80 320	79.01 60	74.85 145	88.40 175	61.83 102	94.61 173	79.36 103	76.52 193	88.83 203

new-patchmatchnet		59.30 316	56.48 318	67.79 328	65.86 356	44.19 350	82.47 296	81.77 321	59.94 304	43.65 353	66.20 345	27.67 334	81.68 348	39.34 340	41.40 352	77.50 343

iter_conf05		83.27 83	82.70 85	84.98 106	93.32 59	71.84 15	94.16 52	81.76 322	82.74 16	73.83 157	88.40 175	72.77 27	94.61 173	82.10 83	75.21 200	88.48 212

MDA-MVSNet-bldmvs		61.54 310	57.70 314	73.05 306	79.53 297	57.00 295	83.08 292	81.23 323	57.57 313	34.91 360	72.45 327	32.79 316	86.26 324	35.81 348	41.95 351	75.89 346

OurMVSNet-221017-0		64.68 297	62.17 301	72.21 314	76.08 330	47.35 340	80.67 309	81.02 324	56.19 322	51.60 326	79.66 289	27.05 336	88.56 302	53.60 285	53.63 331	80.71 322

ACMH+	65.35 16	67.65 282	64.55 285	76.96 278	84.59 243	57.10 293	88.08 248	80.79 325	58.59 312	53.00 321	81.09 270	26.63 337	92.95 228	46.51 312	61.69 301	80.82 320

CNLPA		74.31 225	72.30 232	80.32 221	91.49 110	61.66 227	90.85 188	80.72 326	56.67 321	63.85 269	90.64 143	46.75 247	90.84 281	53.79 283	75.99 197	88.47 214

mvsmamba		76.85 190	75.71 188	80.25 225	83.07 265	59.16 269	91.44 160	80.64 327	76.84 89	67.95 226	86.33 204	46.17 256	94.24 192	76.06 127	72.92 215	87.36 228

LS3D		69.17 267	66.40 271	77.50 267	91.92 97	56.12 299	85.12 274	80.37 328	46.96 346	56.50 311	87.51 192	37.25 298	93.71 214	32.52 359	79.40 164	82.68 305

testgi		64.48 299	62.87 297	69.31 324	71.24 341	40.62 357	85.49 273	79.92 329	65.36 260	54.18 317	83.49 235	23.74 343	84.55 329	41.60 332	60.79 307	82.77 300

test_0402		64.54 298	61.09 304	74.92 292	84.10 253	60.75 244	87.95 250	79.71 330	52.03 332	52.41 323	77.20 305	32.21 320	91.64 271	23.14 363	61.03 304	72.36 352

SixPastTwentyTwo		64.92 296	61.78 303	74.34 297	78.74 310	49.76 330	83.42 287	79.51 331	62.86 280	50.27 332	77.35 302	30.92 327	90.49 284	45.89 316	47.06 343	82.78 299

ITE_SJBPF				70.43 321	74.44 333	47.06 344		77.32 332	60.16 302	54.04 318	83.53 233	23.30 344	84.01 332	43.07 325	61.58 302	80.21 329

K. test v3		63.09 305	59.61 309	73.53 303	76.26 328	49.38 333	83.27 288	77.15 333	64.35 266	47.77 341	72.32 330	28.73 331	87.79 312	49.93 296	36.69 359	83.41 292

DP-MVS		69.90 263	66.48 270	80.14 227	95.36 28	62.93 203	89.56 222	76.11 334	50.27 339	57.69 307	85.23 214	39.68 279	95.73 131	33.35 354	71.05 230	81.78 315

RPSCF		64.24 300	61.98 302	71.01 320	76.10 329	45.00 349	75.83 333	75.94 335	46.94 347	58.96 298	84.59 222	31.40 323	82.00 347	47.76 308	60.33 312	86.04 256

test_fmvs1_n		72.69 246	71.92 236	74.99 291	71.15 343	47.08 343	87.34 261	75.67 336	63.48 273	78.08 113	91.17 138	20.16 351	87.87 310	84.65 66	75.57 199	90.01 193

TinyColmap		60.32 312	56.42 319	72.00 317	78.78 309	53.18 314	78.36 325	75.64 337	52.30 331	41.59 356	75.82 318	14.76 359	88.35 305	35.84 347	54.71 329	74.46 348

ADS-MVSNet2		66.90 287	63.44 293	77.26 273	88.06 185	60.70 246	68.01 347	75.56 338	57.57 313	64.48 262	69.87 338	38.68 282	84.10 330	40.87 335	67.89 250	86.97 235

COLMAP_ROB	57.96 20	62.98 306	59.65 308	72.98 307	81.44 278	53.00 315	83.75 282	75.53 339	48.34 344	48.81 338	81.40 262	24.14 341	90.30 285	32.95 356	60.52 309	75.65 347
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Patchmatch-test		65.86 292	60.94 305	80.62 218	83.75 256	58.83 273	58.91 361	75.26 340	44.50 352	50.95 331	77.09 307	58.81 133	87.90 309	35.13 350	64.03 279	95.12 70

test_fmvs1		74.07 227	73.69 214	75.22 288	78.91 308	47.34 341	89.06 237	74.69 341	63.68 271	79.41 96	91.59 131	24.36 339	87.77 313	85.22 60	76.26 195	90.55 187

MVS-HIRNet		60.25 313	55.55 320	74.35 296	84.37 248	56.57 297	71.64 338	74.11 342	34.44 359	45.54 347	42.24 366	31.11 326	89.81 294	40.36 338	76.10 196	76.67 345

bld_raw_dy_0_64		71.59 252	69.71 256	77.22 274	77.82 321	58.12 280	87.71 255	73.66 343	68.01 239	61.90 285	84.29 227	33.68 313	88.43 304	69.91 178	70.43 232	85.11 275

pmmvs3		55.51 320	51.50 325	67.53 330	57.90 363	50.93 326	80.37 311	73.66 343	40.63 357	44.15 352	64.75 348	16.30 354	78.97 353	44.77 322	40.98 355	72.69 350

TDRefinement		55.28 321	51.58 324	66.39 333	59.53 362	46.15 346	76.23 331	72.80 345	44.60 351	42.49 354	76.28 314	15.29 357	82.39 344	33.20 355	43.75 348	70.62 354

Gipuma		34.91 335	31.44 338	45.30 350	70.99 344	39.64 361	19.85 372	72.56 346	20.10 368	16.16 372	21.47 373	5.08 373	71.16 359	13.07 371	43.70 349	25.08 370
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_vis1_n		71.63 251	70.73 246	74.31 298	69.63 349	47.29 342	86.91 266	72.11 347	63.21 277	75.18 142	90.17 156	20.40 349	85.76 325	84.59 67	74.42 203	89.87 194

FPMVS		45.64 327	43.10 330	53.23 345	51.42 368	36.46 363	64.97 352	71.91 348	29.13 363	27.53 363	61.55 354	9.83 365	65.01 367	16.00 370	55.58 325	58.22 361

ANet_high		40.27 332	35.20 335	55.47 341	34.74 379	34.47 366	63.84 354	71.56 349	48.42 343	18.80 368	41.08 367	9.52 366	64.45 368	20.18 365	8.66 375	67.49 357

Patchmatch-RL test		68.17 278	64.49 287	79.19 248	71.22 342	53.93 311	70.07 342	71.54 350	69.22 227	56.79 310	62.89 350	56.58 158	88.61 300	69.53 182	52.61 333	95.03 74

LCM-MVSNet-Re		72.93 239	71.84 237	76.18 284	88.49 169	48.02 336	80.07 317	70.17 351	73.96 126	52.25 324	80.09 284	49.98 221	88.24 306	67.35 202	84.23 136	92.28 156

test_fmvs2		65.78 294	64.84 281	68.60 326	66.54 354	41.71 354	83.27 288	69.81 352	54.38 327	67.91 228	84.54 224	15.35 356	81.22 350	75.65 129	66.16 261	82.88 298

LCM-MVSNet		40.54 329	35.79 334	54.76 344	36.92 378	30.81 370	51.41 365	69.02 353	22.07 365	24.63 365	45.37 362	4.56 374	65.81 364	33.67 353	34.50 363	67.67 356

AllTest		61.66 308	58.06 312	72.46 311	79.57 295	51.42 323	80.17 315	68.61 354	51.25 335	45.88 343	81.23 264	19.86 352	86.58 322	38.98 341	57.01 321	79.39 332

TestCases				72.46 311	79.57 295	51.42 323		68.61 354	51.25 335	45.88 343	81.23 264	19.86 352	86.58 322	38.98 341	57.01 321	79.39 332

LF4IMVS		54.01 322	52.12 323	59.69 337	62.41 360	39.91 360	68.59 345	68.28 356	42.96 355	44.55 351	75.18 319	14.09 361	68.39 361	41.36 334	51.68 335	70.78 353

door								66.57 357

door-mid								66.01 358

test_fmvs3		56.82 318	54.86 321	62.69 336	53.59 365	35.47 364	75.87 332	65.64 359	43.91 353	55.10 313	71.43 336	6.91 370	74.40 357	68.64 192	52.63 332	78.20 341

DSMNet-mixed		56.78 319	54.44 322	63.79 335	63.21 358	29.44 373	64.43 353	64.10 360	42.12 356	51.32 328	71.60 333	31.76 321	75.04 355	36.23 346	65.20 268	86.87 238

PM-MVS		59.40 315	56.59 317	67.84 327	63.63 357	41.86 353	76.76 330	63.22 361	59.01 309	51.07 330	72.27 331	11.72 362	83.25 339	61.34 251	50.28 339	78.39 340

new_pmnet		49.31 324	46.44 327	57.93 338	62.84 359	40.74 356	68.47 346	62.96 362	36.48 358	35.09 359	57.81 355	14.97 358	72.18 358	32.86 357	46.44 344	60.88 360

lessismore_v0				73.72 302	72.93 339	47.83 338		61.72 363		45.86 345	73.76 323	28.63 333	89.81 294	47.75 309	31.37 365	83.53 288

mvsany_test1		68.77 272	68.56 260	69.39 323	73.57 336	45.88 348	80.93 308	60.88 364	59.65 306	71.56 185	90.26 154	43.22 269	75.05 354	74.26 142	62.70 287	87.25 233

EGC-MVSNET		42.35 328	38.09 331	55.11 342	74.57 332	46.62 345	71.63 339	55.77 365	0.04 377	0.24 378	62.70 351	14.24 360	74.91 356	17.59 367	46.06 345	43.80 363

test_method		38.59 333	35.16 336	48.89 348	54.33 364	21.35 378	45.32 368	53.71 366	7.41 374	28.74 362	51.62 358	8.70 367	52.87 372	33.73 352	32.89 364	72.47 351

APD_test1		40.50 330	37.31 333	50.09 347	51.88 366	35.27 365	59.45 360	52.59 367	21.64 366	26.12 364	57.80 356	4.56 374	66.56 363	22.64 364	39.09 356	48.43 362

PMMVS2		37.93 334	33.61 337	50.92 346	46.31 370	24.76 376	60.55 359	50.05 368	28.94 364	20.93 366	47.59 359	4.41 376	65.13 366	25.14 362	18.55 370	62.87 359

PMVS	26.43 22	31.84 338	28.16 341	42.89 351	25.87 381	27.58 374	50.92 366	49.78 369	21.37 367	14.17 373	40.81 368	2.01 380	66.62 362	9.61 373	38.88 358	34.49 369
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_f		46.58 326	43.45 329	55.96 340	45.18 372	32.05 368	61.18 356	49.49 370	33.39 360	42.05 355	62.48 352	7.00 369	65.56 365	47.08 311	43.21 350	70.27 355

test_vis1_rt		59.09 317	57.31 316	64.43 334	68.44 352	46.02 347	83.05 293	48.63 371	51.96 333	49.57 335	63.86 349	16.30 354	80.20 351	71.21 166	62.79 286	67.07 358

mvsany_test3		48.86 325	46.35 328	56.41 339	46.00 371	31.67 369	62.26 355	47.25 372	43.71 354	45.54 347	68.15 342	10.84 363	64.44 369	57.95 267	35.44 362	73.13 349

testf1		32.77 336	29.47 339	42.67 352	41.89 375	30.81 370	52.07 363	43.45 373	15.45 369	18.52 369	44.82 363	2.12 378	58.38 370	16.05 368	30.87 366	38.83 365

APD_test2		32.77 336	29.47 339	42.67 352	41.89 375	30.81 370	52.07 363	43.45 373	15.45 369	18.52 369	44.82 363	2.12 378	58.38 370	16.05 368	30.87 366	38.83 365

E-PMN		24.61 339	24.00 343	26.45 356	43.74 374	18.44 380	60.86 357	39.66 375	15.11 371	9.53 375	22.10 372	6.52 371	46.94 374	8.31 374	10.14 372	13.98 372

tmp_tt		22.26 342	23.75 344	17.80 358	5.23 382	12.06 382	35.26 369	39.48 376	2.82 376	18.94 367	44.20 365	22.23 346	24.64 377	36.30 345	9.31 374	16.69 371

MVE	24.84 23	24.35 340	19.77 346	38.09 354	34.56 380	26.92 375	26.57 370	38.87 377	11.73 373	11.37 374	27.44 370	1.37 381	50.42 373	11.41 372	14.60 371	36.93 367
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		23.76 341	23.20 345	25.46 357	41.52 377	16.90 381	60.56 358	38.79 378	14.62 372	8.99 376	20.24 375	7.35 368	45.82 375	7.25 375	9.46 373	13.64 373

test_vis3_rt		40.46 331	37.79 332	48.47 349	44.49 373	33.35 367	66.56 351	32.84 379	32.39 361	29.65 361	39.13 369	3.91 377	68.65 360	50.17 293	40.99 354	43.40 364

MTMP							93.77 74	32.52 380

DeepMVS_CX				34.71 355	51.45 367	24.73 377		28.48 381	31.46 362	17.49 371	52.75 357	5.80 372	42.60 376	18.18 366	19.42 369	36.81 368

N_pmnet		50.55 323	49.11 326	54.88 343	77.17 324	4.02 383	84.36 278	2.00 382	48.59 342	45.86 345	68.82 340	32.22 319	82.80 342	31.58 361	51.38 336	77.81 342

wuyk23d		11.30 344	10.95 347	12.33 359	48.05 369	19.89 379	25.89 371	1.92 383	3.58 375	3.12 377	1.37 377	0.64 382	15.77 378	6.23 376	7.77 376	1.35 374

testmvs		7.23 346	9.62 349	0.06 361	0.04 383	0.02 385	84.98 276	0.02 384	0.03 378	0.18 379	1.21 378	0.01 384	0.02 379	0.14 377	0.01 377	0.13 376

test123		6.92 347	9.21 350	0.08 360	0.03 384	0.05 384	81.65 301	0.01 385	0.02 379	0.14 380	0.85 379	0.03 383	0.02 379	0.12 378	0.00 378	0.16 375

test_blank		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 378	0.00 377

uanet_test		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 378	0.00 377

DCPMVS		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 378	0.00 377

pcd_1.5k_mvsjas		4.46 348	5.95 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	53.55 191	0.00 381	0.00 379	0.00 378	0.00 377

sosnet-low-res		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 378	0.00 377

sosnet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 378	0.00 377

uncertanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 378	0.00 377

Regformer		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 378	0.00 377

n2								0.00 386

nn								0.00 386

ab-mvs-re		7.91 345	10.55 348	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	94.95 51	0.00 385	0.00 381	0.00 379	0.00 378	0.00 377

uanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 378	0.00 377

PC_three_1452									80.91 35	94.07 2	96.83 13	83.57 4	99.12 5	95.70 2	97.42 4	97.55 4

eth-test2					0.00 385

eth-test					0.00 385

OPU-MVS				89.97 3	97.52 3	73.15 12	96.89 4				97.00 8	83.82 2	99.15 2	95.72 1	97.63 3	97.62 2

test_0728_THIRD									72.48 155	90.55 16	96.93 9	76.24 11	99.08 11	91.53 16	94.99 16	96.43 25

GSMVS																94.68 84

test_part2					96.29 19	68.16 77				90.78 13

sam_mvs1												57.85 139				94.68 84

sam_mvs												54.91 176

test_post1							78.95 320				20.70 374	53.05 196	91.50 278	60.43 256

test_post											23.01 371	56.49 159	92.67 243

patchmatchnet-post											67.62 343	57.62 142	90.25 286

gm-plane-assit					88.42 173	67.04 105			78.62 66		91.83 126		97.37 62	76.57 124

test9_res														89.41 25	94.96 17	95.29 61

agg_prior2														86.41 52	94.75 28	95.33 57

test_prior4						67.18 101	93.92 65

test_prior2							95.10 36		75.40 105	85.25 49	95.61 33	67.94 42		87.47 42	94.77 24

旧先验2							92.00 141		59.37 308	87.54 28			93.47 220	75.39 131

新几何2							91.41 162

原ACMM2							92.01 138

testdata2													96.09 116	61.26 252

segment_acmp												65.94 56

testdata1							89.21 232		77.55 82

plane_prior7					86.94 206	61.51 229

plane_prior6					87.23 201	62.32 215						50.66 215

plane_prior4											89.14 168

plane_prior3						61.95 222			79.09 57	72.53 170

plane_prior2							93.13 94		78.81 63

plane_prior1					87.15 203

plane_prior						62.42 212	93.85 69		79.38 49						78.80 171

HQP5-MVS						63.66 190

HQP-NCC					87.54 195		94.06 57		79.80 43	74.18 150

ACMP_Plane					87.54 195		94.06 57		79.80 43	74.18 150

BP-MVS														77.63 119

HQP4-MVS										74.18 150			95.61 139			88.63 208

HQP2-MVS												51.63 209

NP-MVS					87.41 198	63.04 199					90.30 152

MDTV_nov1_ep13_2view						59.90 258	80.13 316		67.65 243	72.79 165		54.33 184		59.83 260		92.58 148

ACMMP++_ref															71.63 224

ACMMP++															69.72 235

Test By Simon												54.21 185

High-resolution multi-view benchmark