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.

MM		90.87 2	91.52 2	88.92 15	92.12 101	71.10 27	97.02 3	96.04 6	88.70 2	91.57 15	96.19 36	70.12 46	98.91 18	96.83 1	95.06 17	96.76 15

MVS_0304		90.32 6	90.90 7	88.55 23	94.05 45	70.23 37	97.00 5	93.73 76	87.30 4	92.15 6	96.15 38	66.38 68	98.94 17	96.71 2	94.67 33	96.47 28

fmvsm_l_conf0.5_n_a		87.44 31	88.15 25	85.30 114	87.10 233	64.19 193	94.41 53	88.14 309	80.24 64	92.54 5	96.97 11	69.52 49	97.17 88	95.89 3	88.51 112	94.56 108

fmvsm_l_conf0.5_n		87.49 29	88.19 24	85.39 110	86.95 236	64.37 186	94.30 57	88.45 300	80.51 56	92.70 4	96.86 16	69.98 47	97.15 92	95.83 4	88.08 117	94.65 105

test_fmvsm_n_1920		87.69 26	88.50 19	85.27 117	87.05 235	63.55 213	93.69 90	91.08 198	84.18 15	90.17 26	97.04 9	67.58 59	97.99 39	95.72 5	90.03 96	94.26 122

OPU-MVS				89.97 3	97.52 3	73.15 14	96.89 6				97.00 10	83.82 2	99.15 2	95.72 5	97.63 3	97.62 2

PC_three_1452									80.91 53	94.07 2	96.83 20	83.57 4	99.12 5	95.70 7	97.42 4	97.55 4

fmvsm_s_conf0.5_n		86.39 49	86.91 40	84.82 130	87.36 227	63.54 214	94.74 48	90.02 238	82.52 29	90.14 27	96.92 14	62.93 119	97.84 46	95.28 8	82.26 175	93.07 168

fmvsm_l_conf0.5_n_3		87.54 27	88.29 22	85.30 114	86.92 241	62.63 238	95.02 42	90.28 226	84.95 11	90.27 23	96.86 16	65.36 80	97.52 66	94.93 9	90.03 96	95.76 50

fmvsm_s_conf0.1_n		85.61 67	85.93 58	84.68 140	82.95 307	63.48 216	94.03 71	89.46 256	81.69 39	89.86 28	96.74 22	61.85 131	97.75 49	94.74 10	82.01 181	92.81 176

fmvsm_s_conf0.5_n_a		85.75 63	86.09 55	84.72 137	85.73 262	63.58 211	93.79 86	89.32 262	81.42 46	90.21 25	96.91 15	62.41 125	97.67 53	94.48 11	80.56 195	92.90 174

test_fmvsmconf_n		86.58 46	87.17 36	84.82 130	85.28 268	62.55 239	94.26 59	89.78 244	83.81 19	87.78 40	96.33 33	65.33 81	96.98 104	94.40 12	87.55 123	94.95 89

fmvsm_s_conf0.5_n_2		85.06 76	85.60 65	83.44 186	86.92 241	60.53 285	94.41 53	87.31 322	83.30 22	88.72 35	96.72 23	54.28 223	97.75 49	94.07 13	84.68 154	92.04 199

test_fmvsmconf0.1_n		85.71 64	86.08 56	84.62 144	80.83 324	62.33 244	93.84 83	88.81 288	83.50 21	87.00 47	96.01 41	63.36 111	96.93 112	94.04 14	87.29 126	94.61 107

fmvsm_s_conf0.5_n_3		86.88 37	87.99 27	83.58 179	87.26 228	60.74 278	93.21 113	87.94 316	84.22 14	91.70 13	97.27 2	65.91 75	95.02 191	93.95 15	90.42 93	94.99 87

fmvsm_s_conf0.1_n_a		84.76 82	84.84 79	84.53 146	80.23 334	63.50 215	92.79 129	88.73 291	80.46 57	89.84 29	96.65 25	60.96 139	97.57 63	93.80 16	80.14 197	92.53 183

fmvsm_s_conf0.1_n_2		84.40 87	84.78 80	83.27 189	85.25 269	60.41 288	94.13 64	85.69 342	83.05 24	87.99 38	96.37 30	52.75 239	97.68 51	93.75 17	84.05 163	91.71 203

test_fmvsmvis_n_1920		83.80 104	83.48 95	84.77 134	82.51 310	63.72 204	91.37 196	83.99 359	81.42 46	77.68 149	95.74 46	58.37 170	97.58 61	93.38 18	86.87 129	93.00 171

patch_mono-2		89.71 11	90.99 6	85.85 95	96.04 24	63.70 206	95.04 40	95.19 21	86.74 7	91.53 16	95.15 70	73.86 22	97.58 61	93.38 18	92.00 69	96.28 37

balanced_conf03		89.08 15	88.84 17	89.81 6	93.66 54	75.15 5	90.61 231	93.43 90	84.06 16	86.20 53	90.17 188	72.42 34	96.98 104	93.09 20	95.92 10	97.29 7

CANet		89.61 12	89.99 12	88.46 24	94.39 39	69.71 51	96.53 13	93.78 69	86.89 6	89.68 30	95.78 44	65.94 73	99.10 9	92.99 21	93.91 42	96.58 21

test_fmvsmconf0.01_n		83.70 108	83.52 92	84.25 158	75.26 377	61.72 258	92.17 155	87.24 324	82.36 32	84.91 68	95.41 55	55.60 205	96.83 117	92.85 22	85.87 142	94.21 125

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 137	93.00 76	58.16 318	96.72 9	94.41 51	86.50 8	90.25 24	97.83 1	75.46 14	98.67 25	92.78 23	95.49 13	97.32 6

MCST-MVS		91.08 1	91.46 3	89.94 4	97.66 2	73.37 10	97.13 2	95.58 11	89.33 1	85.77 58	96.26 34	72.84 29	99.38 1	92.64 24	95.93 9	97.08 11

CNVR-MVS		90.32 6	90.89 8	88.61 22	96.76 8	70.65 30	96.47 14	94.83 32	84.83 12	89.07 33	96.80 21	70.86 42	99.06 15	92.64 24	95.71 11	96.12 40

SED-MVS		89.94 9	90.36 10	88.70 18	96.45 12	69.38 56	96.89 6	94.44 49	71.65 225	92.11 7	97.21 5	76.79 9	99.11 6	92.34 26	95.36 14	97.62 2

IU-MVS					96.46 11	69.91 43		95.18 22	80.75 54	95.28 1				92.34 26	95.36 14	96.47 28

test_241102_TWO								94.41 51	71.65 225	92.07 9	97.21 5	74.58 18	99.11 6	92.34 26	95.36 14	96.59 19

MSC_two_6792asdad				89.60 9	97.31 4	73.22 12		95.05 28					99.07 13	92.01 29	94.77 26	96.51 24

No_MVS				89.60 9	97.31 4	73.22 12		95.05 28					99.07 13	92.01 29	94.77 26	96.51 24

test_vis1_n_1920		81.66 143	82.01 127	80.64 255	82.24 312	55.09 345	94.76 47	86.87 326	81.67 40	84.40 73	94.63 84	38.17 336	94.67 207	91.98 31	83.34 166	92.16 197

DVP-MVS		89.41 13	89.73 14	88.45 25	96.40 15	69.99 39	96.64 10	94.52 45	71.92 211	90.55 21	96.93 12	73.77 23	99.08 11	91.91 32	94.90 22	96.29 35
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				88.70 18	96.45 12	70.43 34	96.64 10	94.37 55					99.15 2	91.91 32	94.90 22	96.51 24

DVP-MVS++		90.53 4	91.09 5	88.87 16	97.31 4	69.91 43	93.96 73	94.37 55	72.48 195	92.07 9	96.85 18	83.82 2	99.15 2	91.53 34	97.42 4	97.55 4

test_0728_THIRD									72.48 195	90.55 21	96.93 12	76.24 11	99.08 11	91.53 34	94.99 18	96.43 31

PS-MVSNAJ		88.14 18	87.61 31	89.71 7	92.06 102	76.72 1	95.75 20	93.26 96	83.86 17	89.55 31	96.06 40	53.55 230	97.89 43	91.10 36	93.31 53	94.54 111

xiu_mvs_v2_base		87.92 23	87.38 35	89.55 12	91.41 128	76.43 3	95.74 21	93.12 104	83.53 20	89.55 31	95.95 42	53.45 234	97.68 51	91.07 37	92.62 60	94.54 111

MSP-MVS		90.38 5	91.87 1	85.88 92	92.83 80	64.03 196	93.06 116	94.33 57	82.19 34	93.65 3	96.15 38	85.89 1	97.19 87	91.02 38	97.75 1	96.43 31
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
dcpmvs_2		87.37 32	87.55 32	86.85 58	95.04 32	68.20 88	90.36 237	90.66 210	79.37 79	81.20 103	93.67 114	74.73 16	96.55 126	90.88 39	92.00 69	95.82 48

test_cas_vis1_n_1920		80.45 165	80.61 150	79.97 274	78.25 360	57.01 333	94.04 70	88.33 303	79.06 89	82.81 90	93.70 113	38.65 331	91.63 310	90.82 40	79.81 199	91.27 216

APDe-MVS		87.54 27	87.84 28	86.65 67	96.07 23	66.30 139	94.84 46	93.78 69	69.35 265	88.39 36	96.34 32	67.74 58	97.66 56	90.62 41	93.44 51	96.01 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPE-MVS		88.77 17	89.21 16	87.45 43	96.26 20	67.56 104	94.17 60	94.15 62	68.77 274	90.74 19	97.27 2	76.09 12	98.49 29	90.58 42	94.91 21	96.30 34
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
9.14			87.63 30		93.86 48		94.41 53	94.18 60	72.76 190	86.21 52	96.51 27	66.64 65	97.88 44	90.08 43	94.04 39

test9_res														89.41 44	94.96 19	95.29 71

TSAR-MVS + GP.		87.96 21	88.37 21	86.70 66	93.51 62	65.32 161	95.15 36	93.84 68	78.17 101	85.93 57	94.80 80	75.80 13	98.21 34	89.38 45	88.78 109	96.59 19

lupinMVS		87.74 25	87.77 29	87.63 38	89.24 176	71.18 24	96.57 12	92.90 113	82.70 28	87.13 44	95.27 63	64.99 84	95.80 157	89.34 46	91.80 72	95.93 45

ETV-MVS		86.01 57	86.11 54	85.70 102	90.21 151	67.02 121	93.43 106	91.92 154	81.21 50	84.13 77	94.07 107	60.93 140	95.63 168	89.28 47	89.81 98	94.46 117

SMA-MVS		88.14 18	88.29 22	87.67 33	93.21 68	68.72 73	93.85 80	94.03 65	74.18 158	91.74 12	96.67 24	65.61 78	98.42 33	89.24 48	96.08 7	95.88 47
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
train_agg		87.21 34	87.42 34	86.60 69	94.18 41	67.28 111	94.16 61	93.51 84	71.87 216	85.52 61	95.33 58	68.19 53	97.27 83	89.09 49	94.90 22	95.25 77

SD-MVS		87.49 29	87.49 33	87.50 42	93.60 56	68.82 70	93.90 77	92.63 125	76.86 122	87.90 39	95.76 45	66.17 70	97.63 58	89.06 50	91.48 78	96.05 42
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
NCCC		89.07 16	89.46 15	87.91 28	96.60 10	69.05 64	96.38 15	94.64 41	84.42 13	86.74 49	96.20 35	66.56 67	98.76 24	89.03 51	94.56 34	95.92 46

HPM-MVS++		89.37 14	89.95 13	87.64 34	95.10 30	68.23 87	95.24 33	94.49 47	82.43 31	88.90 34	96.35 31	71.89 39	98.63 26	88.76 52	96.40 6	96.06 41

SF-MVS		87.03 36	87.09 37	86.84 59	92.70 86	67.45 109	93.64 93	93.76 72	70.78 249	86.25 51	96.44 29	66.98 62	97.79 47	88.68 53	94.56 34	95.28 73

sasdasda		86.85 39	86.25 50	88.66 20	91.80 114	71.92 16	93.54 98	91.71 167	80.26 61	87.55 41	95.25 65	63.59 107	96.93 112	88.18 54	84.34 155	97.11 9

canonicalmvs		86.85 39	86.25 50	88.66 20	91.80 114	71.92 16	93.54 98	91.71 167	80.26 61	87.55 41	95.25 65	63.59 107	96.93 112	88.18 54	84.34 155	97.11 9

TSAR-MVS + MP.		88.11 20	88.64 18	86.54 73	91.73 116	68.04 91	90.36 237	93.55 83	82.89 25	91.29 17	92.89 130	72.27 36	96.03 152	87.99 56	94.77 26	95.54 58
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
alignmvs		87.28 33	86.97 39	88.24 27	91.30 130	71.14 26	95.61 25	93.56 82	79.30 80	87.07 46	95.25 65	68.43 51	96.93 112	87.87 57	84.33 157	96.65 17

jason		86.40 48	86.17 52	87.11 51	86.16 253	70.54 32	95.71 24	92.19 142	82.00 36	84.58 71	94.34 96	61.86 130	95.53 177	87.76 58	90.89 86	95.27 74
jason: jason.
h-mvs33		83.01 120	82.56 120	84.35 154	89.34 168	62.02 250	92.72 132	93.76 72	81.45 43	82.73 91	92.25 147	60.11 147	97.13 93	87.69 59	62.96 327	93.91 142

hse-mvs2		81.12 153	81.11 140	81.16 242	86.52 245	57.48 326	89.40 262	91.16 191	81.45 43	82.73 91	90.49 180	60.11 147	94.58 208	87.69 59	60.41 354	91.41 209

ZD-MVS					96.63 9	65.50 159		93.50 86	70.74 250	85.26 66	95.19 69	64.92 87	97.29 79	87.51 61	93.01 56

mvsmamba		81.55 145	80.72 146	84.03 165	91.42 125	66.93 123	83.08 332	89.13 273	78.55 97	67.50 274	87.02 239	51.79 247	90.07 334	87.48 62	90.49 92	95.10 82

test_prior2							95.10 38		75.40 142	85.25 67	95.61 49	67.94 56		87.47 63	94.77 26

SteuartSystems-ACMMP		86.82 43	86.90 41	86.58 71	90.42 146	66.38 136	96.09 17	93.87 67	77.73 109	84.01 78	95.66 47	63.39 110	97.94 40	87.40 64	93.55 50	95.42 60
Skip Steuart: Steuart Systems R&D Blog.
diffmvs		84.28 91	83.83 88	85.61 104	87.40 225	68.02 92	90.88 217	89.24 265	80.54 55	81.64 98	92.52 136	59.83 151	94.52 216	87.32 65	85.11 148	94.29 121
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DELS-MVS		90.05 8	90.09 11	89.94 4	93.14 71	73.88 9	97.01 4	94.40 53	88.32 3	85.71 59	94.91 77	74.11 21	98.91 18	87.26 66	95.94 8	97.03 12
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
casdiffmvs_mvg		85.66 66	85.18 72	87.09 52	88.22 203	69.35 59	93.74 89	91.89 157	81.47 42	80.10 119	91.45 164	64.80 89	96.35 135	87.23 67	87.69 121	95.58 56
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MGCFI-Net		85.59 68	85.73 63	85.17 121	91.41 128	62.44 240	92.87 127	91.31 184	79.65 73	86.99 48	95.14 71	62.90 120	96.12 144	87.13 68	84.13 162	96.96 13

PVSNet_BlendedMVS		83.38 113	83.43 98	83.22 191	93.76 50	67.53 106	94.06 66	93.61 80	79.13 85	81.00 108	85.14 259	63.19 114	97.29 79	87.08 69	73.91 248	84.83 318

PVSNet_Blended		86.73 44	86.86 42	86.31 82	93.76 50	67.53 106	96.33 16	93.61 80	82.34 33	81.00 108	93.08 124	63.19 114	97.29 79	87.08 69	91.38 80	94.13 131

MP-MVS-pluss		85.24 73	85.13 73	85.56 105	91.42 125	65.59 155	91.54 187	92.51 129	74.56 151	80.62 112	95.64 48	59.15 160	97.00 100	86.94 71	93.80 43	94.07 135
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
VDD-MVS		83.06 119	81.81 130	86.81 61	90.86 140	67.70 100	95.40 29	91.50 178	75.46 140	81.78 97	92.34 144	40.09 326	97.13 93	86.85 72	82.04 180	95.60 55

SPE-MVS-test		86.14 55	87.01 38	83.52 180	92.63 88	59.36 307	95.49 27	91.92 154	80.09 65	85.46 63	95.53 53	61.82 132	95.77 160	86.77 73	93.37 52	95.41 61

agg_prior2														86.41 74	94.75 30	95.33 67

APD-MVS		85.93 59	85.99 57	85.76 99	95.98 26	65.21 164	93.59 96	92.58 127	66.54 292	86.17 54	95.88 43	63.83 100	97.00 100	86.39 75	92.94 57	95.06 83
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ACMMP_NAP		86.05 56	85.80 61	86.80 62	91.58 120	67.53 106	91.79 177	93.49 87	74.93 148	84.61 70	95.30 60	59.42 156	97.92 41	86.13 76	94.92 20	94.94 90

CS-MVS		85.80 62	86.65 46	83.27 189	92.00 107	58.92 311	95.31 31	91.86 159	79.97 66	84.82 69	95.40 56	62.26 126	95.51 178	86.11 77	92.08 68	95.37 64

PHI-MVS		86.83 41	86.85 43	86.78 63	93.47 63	65.55 157	95.39 30	95.10 24	71.77 221	85.69 60	96.52 26	62.07 128	98.77 23	86.06 78	95.60 12	96.03 43

MVS_111021_HR		86.19 54	85.80 61	87.37 44	93.17 70	69.79 48	93.99 72	93.76 72	79.08 87	78.88 137	93.99 108	62.25 127	98.15 36	85.93 79	91.15 84	94.15 130

DeepC-MVS	77.85 3	85.52 70	85.24 71	86.37 79	88.80 186	66.64 130	92.15 156	93.68 78	81.07 51	76.91 160	93.64 115	62.59 122	98.44 31	85.50 80	92.84 59	94.03 137
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EC-MVSNet		84.53 86	85.04 75	83.01 194	89.34 168	61.37 265	94.42 52	91.09 196	77.91 105	83.24 82	94.20 102	58.37 170	95.40 180	85.35 81	91.41 79	92.27 193

test_fmvs1		74.07 268	73.69 256	75.22 327	78.91 352	47.34 385	89.06 271	74.69 388	63.68 315	79.41 128	91.59 163	24.36 390	87.77 353	85.22 82	76.26 233	90.55 225

VNet		86.20 53	85.65 64	87.84 30	93.92 47	69.99 39	95.73 23	95.94 7	78.43 98	86.00 56	93.07 125	58.22 172	97.00 100	85.22 82	84.33 157	96.52 23

testing11		86.71 45	86.44 47	87.55 40	93.54 60	71.35 21	93.65 92	95.58 11	81.36 48	80.69 111	92.21 148	72.30 35	96.46 131	85.18 84	83.43 165	94.82 97

SDMVSNet		80.26 168	78.88 179	84.40 151	89.25 173	67.63 103	85.35 312	93.02 107	76.77 126	70.84 228	87.12 236	47.95 286	96.09 146	85.04 85	74.55 239	89.48 240

MP-MVS		85.02 77	84.97 76	85.17 121	92.60 89	64.27 191	93.24 110	92.27 135	73.13 180	79.63 125	94.43 89	61.90 129	97.17 88	85.00 86	92.56 61	94.06 136
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
casdiffmvs		85.37 71	84.87 78	86.84 59	88.25 201	69.07 63	93.04 118	91.76 164	81.27 49	80.84 110	92.07 151	64.23 95	96.06 150	84.98 87	87.43 125	95.39 62
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CSCG		86.87 38	86.26 49	88.72 17	95.05 31	70.79 29	93.83 85	95.33 17	68.48 278	77.63 150	94.35 95	73.04 27	98.45 30	84.92 88	93.71 47	96.92 14

MTAPA		83.91 101	83.38 102	85.50 106	91.89 112	65.16 166	81.75 341	92.23 136	75.32 143	80.53 114	95.21 68	56.06 201	97.16 91	84.86 89	92.55 62	94.18 127

MVSMamba_PlusPlus		84.97 80	83.65 91	88.93 14	90.17 152	74.04 8	87.84 290	92.69 120	62.18 330	81.47 101	87.64 227	71.47 41	96.28 137	84.69 90	94.74 31	96.47 28

test_fmvs1_n		72.69 287	71.92 278	74.99 330	71.15 390	47.08 387	87.34 299	75.67 383	63.48 317	78.08 146	91.17 170	20.16 402	87.87 350	84.65 91	75.57 237	90.01 231

test_vis1_n		71.63 293	70.73 289	74.31 338	69.63 396	47.29 386	86.91 303	72.11 394	63.21 321	75.18 176	90.17 188	20.40 400	85.76 365	84.59 92	74.42 243	89.87 232

baseline		85.01 78	84.44 83	86.71 65	88.33 198	68.73 72	90.24 242	91.82 163	81.05 52	81.18 104	92.50 137	63.69 103	96.08 149	84.45 93	86.71 135	95.32 69

UBG		86.83 41	86.70 44	87.20 48	93.07 74	69.81 47	93.43 106	95.56 13	81.52 41	81.50 99	92.12 149	73.58 26	96.28 137	84.37 94	85.20 147	95.51 59

CLD-MVS		82.73 124	82.35 124	83.86 168	87.90 211	67.65 102	95.45 28	92.18 143	85.06 10	72.58 204	92.27 145	52.46 242	95.78 158	84.18 95	79.06 207	88.16 257
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
xiu_mvs_v1_base_debu		82.16 134	81.12 137	85.26 118	86.42 246	68.72 73	92.59 143	90.44 217	73.12 181	84.20 74	94.36 91	38.04 339	95.73 162	84.12 96	86.81 130	91.33 210

xiu_mvs_v1_base		82.16 134	81.12 137	85.26 118	86.42 246	68.72 73	92.59 143	90.44 217	73.12 181	84.20 74	94.36 91	38.04 339	95.73 162	84.12 96	86.81 130	91.33 210

xiu_mvs_v1_base_debi		82.16 134	81.12 137	85.26 118	86.42 246	68.72 73	92.59 143	90.44 217	73.12 181	84.20 74	94.36 91	38.04 339	95.73 162	84.12 96	86.81 130	91.33 210

EPNet		87.84 24	88.38 20	86.23 83	93.30 65	66.05 143	95.26 32	94.84 31	87.09 5	88.06 37	94.53 86	66.79 64	97.34 76	83.89 99	91.68 74	95.29 71
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVS_111021_LR		82.02 138	81.52 132	83.51 182	88.42 194	62.88 233	89.77 254	88.93 284	76.78 125	75.55 173	93.10 122	50.31 261	95.38 182	83.82 100	87.02 128	92.26 194

reproduce-ours		83.51 110	83.33 104	84.06 161	92.18 99	60.49 286	90.74 223	92.04 147	64.35 307	83.24 82	95.59 51	59.05 161	97.27 83	83.61 101	89.17 105	94.41 119

our_new_method		83.51 110	83.33 104	84.06 161	92.18 99	60.49 286	90.74 223	92.04 147	64.35 307	83.24 82	95.59 51	59.05 161	97.27 83	83.61 101	89.17 105	94.41 119

RRT-MVS		82.61 128	81.16 135	86.96 57	91.10 134	68.75 71	87.70 293	92.20 140	76.97 120	72.68 200	87.10 238	51.30 254	96.41 133	83.56 103	87.84 119	95.74 51

MSLP-MVS++		86.27 52	85.91 59	87.35 45	92.01 106	68.97 67	95.04 40	92.70 118	79.04 90	81.50 99	96.50 28	58.98 165	96.78 118	83.49 104	93.93 41	96.29 35

DeepC-MVS_fast	79.48 2	87.95 22	88.00 26	87.79 31	95.86 27	68.32 81	95.74 21	94.11 63	83.82 18	83.49 81	96.19 36	64.53 93	98.44 31	83.42 105	94.88 25	96.61 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 161	76.68 2	97.29 1	95.35 16	82.87 26	91.58 14	97.22 4	79.93 5	99.10 9	83.12 106	97.64 2	97.94 1

reproduce_model		83.15 117	82.96 110	83.73 172	92.02 103	59.74 299	90.37 236	92.08 145	63.70 314	82.86 87	95.48 54	58.62 167	97.17 88	83.06 107	88.42 113	94.26 122

BP-MVS1		86.54 47	86.68 45	86.13 86	87.80 216	67.18 115	92.97 121	95.62 10	79.92 67	82.84 88	94.14 104	74.95 15	96.46 131	82.91 108	88.96 108	94.74 99

SR-MVS		82.81 123	82.58 119	83.50 183	93.35 64	61.16 268	92.23 154	91.28 188	64.48 306	81.27 102	95.28 61	53.71 229	95.86 156	82.87 109	88.77 110	93.49 154

ET-MVSNet_ETH3D		84.01 99	83.15 109	86.58 71	90.78 142	70.89 28	94.74 48	94.62 42	81.44 45	58.19 345	93.64 115	73.64 25	92.35 293	82.66 110	78.66 212	96.50 27

ZNCC-MVS		85.33 72	85.08 74	86.06 87	93.09 73	65.65 153	93.89 78	93.41 92	73.75 169	79.94 121	94.68 83	60.61 143	98.03 38	82.63 111	93.72 46	94.52 113

LFMVS		84.34 90	82.73 117	89.18 13	94.76 33	73.25 11	94.99 43	91.89 157	71.90 213	82.16 95	93.49 119	47.98 285	97.05 95	82.55 112	84.82 150	97.25 8

VDDNet		80.50 163	78.26 186	87.21 47	86.19 251	69.79 48	94.48 51	91.31 184	60.42 344	79.34 129	90.91 173	38.48 334	96.56 125	82.16 113	81.05 189	95.27 74

myMVS_eth3d28		86.31 51	86.15 53	86.78 63	93.56 58	70.49 33	92.94 123	95.28 18	82.47 30	78.70 141	92.07 151	72.45 33	95.41 179	82.11 114	85.78 143	94.44 118

HPM-MVS		83.25 115	82.95 112	84.17 159	92.25 95	62.88 233	90.91 214	91.86 159	70.30 254	77.12 157	93.96 109	56.75 190	96.28 137	82.04 115	91.34 82	93.34 157
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
nrg030		80.93 156	79.86 161	84.13 160	83.69 296	68.83 69	93.23 111	91.20 189	75.55 139	75.06 177	88.22 217	63.04 118	94.74 202	81.88 116	66.88 296	88.82 246

Effi-MVS+		83.82 103	82.76 116	86.99 56	89.56 164	69.40 54	91.35 198	86.12 336	72.59 192	83.22 85	92.81 134	59.60 154	96.01 154	81.76 117	87.80 120	95.56 57

HFP-MVS		84.73 83	84.40 84	85.72 101	93.75 52	65.01 170	93.50 101	93.19 100	72.19 205	79.22 131	94.93 75	59.04 163	97.67 53	81.55 118	92.21 64	94.49 116

ACMMPR		84.37 88	84.06 86	85.28 116	93.56 58	64.37 186	93.50 101	93.15 102	72.19 205	78.85 139	94.86 78	56.69 192	97.45 68	81.55 118	92.20 65	94.02 138

GST-MVS		84.63 85	84.29 85	85.66 103	92.82 82	65.27 162	93.04 118	93.13 103	73.20 178	78.89 134	94.18 103	59.41 157	97.85 45	81.45 120	92.48 63	93.86 145

PMMVS		81.98 139	82.04 126	81.78 228	89.76 160	56.17 337	91.13 210	90.69 207	77.96 103	80.09 120	93.57 117	46.33 299	94.99 194	81.41 121	87.46 124	94.17 128

region2R		84.36 89	84.03 87	85.36 112	93.54 60	64.31 189	93.43 106	92.95 111	72.16 208	78.86 138	94.84 79	56.97 187	97.53 65	81.38 122	92.11 67	94.24 124

CP-MVS		83.71 107	83.40 101	84.65 141	93.14 71	63.84 198	94.59 50	92.28 134	71.03 243	77.41 153	94.92 76	55.21 210	96.19 141	81.32 123	90.70 88	93.91 142

MVS		84.66 84	82.86 115	90.06 2	90.93 137	74.56 7	87.91 288	95.54 14	68.55 276	72.35 211	94.71 82	59.78 152	98.90 20	81.29 124	94.69 32	96.74 16

reproduce_monomvs		79.49 183	79.11 177	80.64 255	92.91 78	61.47 263	91.17 209	93.28 95	83.09 23	64.04 307	82.38 289	66.19 69	94.57 210	81.19 125	57.71 362	85.88 301

test_yl		84.28 91	83.16 107	87.64 34	94.52 37	69.24 60	95.78 18	95.09 25	69.19 268	81.09 105	92.88 131	57.00 185	97.44 69	81.11 126	81.76 183	96.23 38

DCV-MVSNet		84.28 91	83.16 107	87.64 34	94.52 37	69.24 60	95.78 18	95.09 25	69.19 268	81.09 105	92.88 131	57.00 185	97.44 69	81.11 126	81.76 183	96.23 38

CDPH-MVS		85.71 64	85.46 67	86.46 75	94.75 34	67.19 113	93.89 78	92.83 115	70.90 245	83.09 86	95.28 61	63.62 105	97.36 74	80.63 128	94.18 37	94.84 94

HY-MVS	76.49 5	84.28 91	83.36 103	87.02 55	92.22 96	67.74 99	84.65 316	94.50 46	79.15 84	82.23 94	87.93 222	66.88 63	96.94 110	80.53 129	82.20 178	96.39 33

CHOSEN 1792x2688		84.98 79	83.45 97	89.57 11	89.94 156	75.14 6	92.07 162	92.32 133	81.87 37	75.68 169	88.27 213	60.18 146	98.60 27	80.46 130	90.27 95	94.96 88

GDP-MVS		85.54 69	85.32 69	86.18 84	87.64 219	67.95 95	92.91 126	92.36 132	77.81 107	83.69 80	94.31 98	72.84 29	96.41 133	80.39 131	85.95 141	94.19 126

testing91		85.93 59	85.31 70	87.78 32	93.59 57	71.47 19	93.50 101	95.08 27	80.26 61	80.53 114	91.93 155	70.43 44	96.51 128	80.32 132	82.13 179	95.37 64

EIA-MVS		84.84 81	84.88 77	84.69 139	91.30 130	62.36 243	93.85 80	92.04 147	79.45 76	79.33 130	94.28 100	62.42 124	96.35 135	80.05 133	91.25 83	95.38 63

testing99		86.01 57	85.47 66	87.63 38	93.62 55	71.25 23	93.47 104	95.23 20	80.42 59	80.60 113	91.95 154	71.73 40	96.50 129	80.02 134	82.22 177	95.13 80

APD-MVS_3200maxsize		81.64 144	81.32 134	82.59 205	92.36 92	58.74 313	91.39 193	91.01 203	63.35 318	79.72 124	94.62 85	51.82 245	96.14 143	79.71 135	87.93 118	92.89 175

PVSNet_Blended_VisFu		83.97 100	83.50 94	85.39 110	90.02 154	66.59 133	93.77 87	91.73 165	77.43 117	77.08 159	89.81 195	63.77 102	96.97 107	79.67 136	88.21 115	92.60 180

WTY-MVS		86.32 50	85.81 60	87.85 29	92.82 82	69.37 58	95.20 34	95.25 19	82.71 27	81.91 96	94.73 81	67.93 57	97.63 58	79.55 137	82.25 176	96.54 22

MonoMVSNet		76.99 228	75.08 235	82.73 199	83.32 301	63.24 220	86.47 308	86.37 330	79.08 87	66.31 289	79.30 336	49.80 268	91.72 307	79.37 138	65.70 303	93.23 161

EI-MVSNet-Vis-set		83.77 105	83.67 90	84.06 161	92.79 85	63.56 212	91.76 180	94.81 33	79.65 73	77.87 147	94.09 105	63.35 112	97.90 42	79.35 139	79.36 204	90.74 221

PGM-MVS		83.25 115	82.70 118	84.92 126	92.81 84	64.07 195	90.44 232	92.20 140	71.28 237	77.23 156	94.43 89	55.17 211	97.31 78	79.33 140	91.38 80	93.37 156

XVS		83.87 102	83.47 96	85.05 123	93.22 66	63.78 200	92.92 124	92.66 122	73.99 161	78.18 144	94.31 98	55.25 207	97.41 71	79.16 141	91.58 76	93.95 140

X-MVStestdata		76.86 230	74.13 250	85.05 123	93.22 66	63.78 200	92.92 124	92.66 122	73.99 161	78.18 144	10.19 428	55.25 207	97.41 71	79.16 141	91.58 76	93.95 140

CostFormer		82.33 131	81.15 136	85.86 94	89.01 181	68.46 78	82.39 338	93.01 108	75.59 138	80.25 118	81.57 302	72.03 38	94.96 195	79.06 143	77.48 223	94.16 129

mPP-MVS		82.96 122	82.44 122	84.52 147	92.83 80	62.92 231	92.76 130	91.85 161	71.52 233	75.61 172	94.24 101	53.48 233	96.99 103	78.97 144	90.73 87	93.64 151

baseline2		83.68 109	83.42 100	84.48 149	87.37 226	66.00 145	90.06 246	95.93 8	79.71 72	69.08 249	90.39 182	77.92 6	96.28 137	78.91 145	81.38 187	91.16 217

CPTT-MVS		79.59 180	79.16 175	80.89 253	91.54 123	59.80 298	92.10 159	88.54 299	60.42 344	72.96 196	93.28 121	48.27 281	92.80 274	78.89 146	86.50 138	90.06 229

SR-MVS-dyc-post		81.06 154	80.70 147	82.15 219	92.02 103	58.56 315	90.90 215	90.45 214	62.76 325	78.89 134	94.46 87	51.26 255	95.61 170	78.77 147	86.77 133	92.28 190

RE-MVS-def			80.48 153		92.02 103	58.56 315	90.90 215	90.45 214	62.76 325	78.89 134	94.46 87	49.30 272		78.77 147	86.77 133	92.28 190

ACMMP		81.49 146	80.67 148	83.93 167	91.71 117	62.90 232	92.13 157	92.22 139	71.79 220	71.68 220	93.49 119	50.32 260	96.96 108	78.47 149	84.22 161	91.93 201
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
PAPM		85.89 61	85.46 67	87.18 49	88.20 204	72.42 15	92.41 149	92.77 116	82.11 35	80.34 117	93.07 125	68.27 52	95.02 191	78.39 150	93.59 49	94.09 133

PAPR		85.15 75	84.47 82	87.18 49	96.02 25	68.29 82	91.85 175	93.00 110	76.59 129	79.03 133	95.00 72	61.59 133	97.61 60	78.16 151	89.00 107	95.63 54

EI-MVSNet-UG-set		83.14 118	82.96 110	83.67 177	92.28 94	63.19 223	91.38 195	94.68 39	79.22 82	76.60 162	93.75 111	62.64 121	97.76 48	78.07 152	78.01 215	90.05 230

CANet_DTU		84.09 98	83.52 92	85.81 96	90.30 149	66.82 125	91.87 173	89.01 280	85.27 9	86.09 55	93.74 112	47.71 289	96.98 104	77.90 153	89.78 100	93.65 150

BP-MVS														77.63 154

HQP-MVS		81.14 151	80.64 149	82.64 203	87.54 221	63.66 209	94.06 66	91.70 170	79.80 69	74.18 184	90.30 184	51.63 250	95.61 170	77.63 154	78.90 208	88.63 248

sss		82.71 126	82.38 123	83.73 172	89.25 173	59.58 302	92.24 153	94.89 30	77.96 103	79.86 122	92.38 142	56.70 191	97.05 95	77.26 156	80.86 191	94.55 109

HQP_MVS		80.34 167	79.75 163	82.12 221	86.94 237	62.42 241	93.13 114	91.31 184	78.81 93	72.53 205	89.14 203	50.66 258	95.55 175	76.74 157	78.53 213	88.39 254

plane_prior5								91.31 184					95.55 175	76.74 157	78.53 213	88.39 254

gm-plane-assit					88.42 194	67.04 120			78.62 96		91.83 157		97.37 73	76.57 159

CHOSEN 280x420		77.35 222	76.95 211	78.55 296	87.07 234	62.68 237	69.71 393	82.95 366	68.80 273	71.48 223	87.27 235	66.03 72	84.00 377	76.47 160	82.81 171	88.95 243

ab-mvs		80.18 170	78.31 185	85.80 97	88.44 193	65.49 160	83.00 335	92.67 121	71.82 219	77.36 154	85.01 260	54.50 216	96.59 122	76.35 161	75.63 236	95.32 69

testing222		85.18 74	84.69 81	86.63 68	92.91 78	69.91 43	92.61 140	95.80 9	80.31 60	80.38 116	92.27 145	68.73 50	95.19 188	75.94 162	83.27 167	94.81 98

mmtdpeth		68.33 319	66.37 316	74.21 339	82.81 308	51.73 358	84.34 318	80.42 373	67.01 290	71.56 221	68.58 389	30.52 377	92.35 293	75.89 163	36.21 405	78.56 383

MVSTER		82.47 129	82.05 125	83.74 170	92.68 87	69.01 65	91.90 172	93.21 97	79.83 68	72.14 212	85.71 255	74.72 17	94.72 203	75.72 164	72.49 258	87.50 264

test_fmvs2		65.78 337	64.84 326	68.60 370	66.54 402	41.71 402	83.27 328	69.81 401	54.38 373	67.91 267	84.54 267	15.35 407	81.22 394	75.65 165	66.16 300	82.88 339

tpmrst		80.57 161	79.14 176	84.84 129	90.10 153	68.28 83	81.70 342	89.72 251	77.63 113	75.96 166	79.54 334	64.94 86	92.71 277	75.43 166	77.28 226	93.55 152

旧先验2							92.00 168		59.37 352	87.54 43			93.47 256	75.39 167

MG-MVS		87.11 35	86.27 48	89.62 8	97.79 1	76.27 4	94.96 44	94.49 47	78.74 95	83.87 79	92.94 128	64.34 94	96.94 110	75.19 168	94.09 38	95.66 53

OPM-MVS		79.00 191	78.09 188	81.73 229	83.52 299	63.83 199	91.64 186	90.30 224	76.36 132	71.97 215	89.93 194	46.30 300	95.17 189	75.10 169	77.70 218	86.19 290
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Effi-MVS+-dtu		76.14 240	75.28 233	78.72 295	83.22 302	55.17 344	89.87 252	87.78 317	75.42 141	67.98 265	81.43 304	45.08 309	92.52 286	75.08 170	71.63 263	88.48 252

HyFIR lowres test		81.03 155	79.56 166	85.43 108	87.81 215	68.11 90	90.18 243	90.01 239	70.65 251	72.95 197	86.06 251	63.61 106	94.50 217	75.01 171	79.75 201	93.67 149

EPP-MVSNet		81.79 141	81.52 132	82.61 204	88.77 187	60.21 293	93.02 120	93.66 79	68.52 277	72.90 198	90.39 182	72.19 37	94.96 195	74.93 172	79.29 206	92.67 178

MVS_Test		84.16 97	83.20 106	87.05 54	91.56 121	69.82 46	89.99 251	92.05 146	77.77 108	82.84 88	86.57 244	63.93 99	96.09 146	74.91 173	89.18 104	95.25 77

VPA-MVSNet		79.03 190	78.00 190	82.11 224	85.95 256	64.48 179	93.22 112	94.66 40	75.05 147	74.04 189	84.95 261	52.17 244	93.52 254	74.90 174	67.04 295	88.32 256

HPM-MVS_fast		80.25 169	79.55 168	82.33 211	91.55 122	59.95 296	91.32 200	89.16 270	65.23 303	74.71 181	93.07 125	47.81 288	95.74 161	74.87 175	88.23 114	91.31 214

AUN-MVS		78.37 206	77.43 200	81.17 241	86.60 244	57.45 327	89.46 261	91.16 191	74.11 159	74.40 183	90.49 180	55.52 206	94.57 210	74.73 176	60.43 353	91.48 207

ECVR-MVS		81.29 149	80.38 155	84.01 166	88.39 196	61.96 252	92.56 146	86.79 328	77.66 111	76.63 161	91.42 165	46.34 298	95.24 187	74.36 177	89.23 102	94.85 91

mvsany_test1		68.77 314	68.56 303	69.39 366	73.57 383	45.88 394	80.93 350	60.88 414	59.65 350	71.56 221	90.26 186	43.22 316	75.05 401	74.26 178	62.70 330	87.25 273

TESTMET0.1,1		82.41 130	81.98 128	83.72 174	88.08 205	63.74 202	92.70 134	93.77 71	79.30 80	77.61 151	87.57 229	58.19 173	94.08 232	73.91 179	86.68 136	93.33 159

mamv4		65.18 340	67.43 310	58.44 386	77.88 366	49.36 377	69.40 394	70.99 399	48.31 392	57.78 351	85.53 256	59.01 164	51.88 424	73.67 180	64.32 318	74.07 394

test2506		83.29 114	82.92 113	84.37 153	88.39 196	63.18 224	92.01 165	91.35 183	77.66 111	78.49 143	91.42 165	64.58 92	95.09 190	73.19 181	89.23 102	94.85 91

mvs_anonymous		81.36 148	79.99 159	85.46 107	90.39 148	68.40 79	86.88 305	90.61 212	74.41 153	70.31 236	84.67 264	63.79 101	92.32 295	73.13 182	85.70 144	95.67 52

PS-MVSNAJss		77.26 223	76.31 218	80.13 267	80.64 328	59.16 309	90.63 230	91.06 200	72.80 189	68.58 260	84.57 266	53.55 230	93.96 242	72.97 183	71.96 262	87.27 272

ACMP	71.68 10	75.58 255	74.23 248	79.62 283	84.97 276	59.64 300	90.80 220	89.07 278	70.39 253	62.95 319	87.30 233	38.28 335	93.87 247	72.89 184	71.45 266	85.36 312
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVSFormer		83.75 106	82.88 114	86.37 79	89.24 176	71.18 24	89.07 269	90.69 207	65.80 297	87.13 44	94.34 96	64.99 84	92.67 280	72.83 185	91.80 72	95.27 74

test_djsdf		73.76 274	72.56 271	77.39 310	77.00 370	53.93 350	89.07 269	90.69 207	65.80 297	63.92 308	82.03 294	43.14 317	92.67 280	72.83 185	68.53 284	85.57 307

test1111		80.84 158	80.02 157	83.33 187	87.87 212	60.76 276	92.62 139	86.86 327	77.86 106	75.73 168	91.39 167	46.35 297	94.70 206	72.79 187	88.68 111	94.52 113

WBMVS		81.67 142	80.98 143	83.72 174	93.07 74	69.40 54	94.33 56	93.05 106	76.84 123	72.05 214	84.14 270	74.49 19	93.88 246	72.76 188	68.09 287	87.88 259

miper_enhance_ethall		78.86 195	77.97 191	81.54 234	88.00 209	65.17 165	91.41 189	89.15 271	75.19 145	68.79 256	83.98 273	67.17 61	92.82 272	72.73 189	65.30 305	86.62 284

OMC-MVS		78.67 202	77.91 193	80.95 251	85.76 261	57.40 328	88.49 278	88.67 294	73.85 166	72.43 209	92.10 150	49.29 273	94.55 214	72.73 189	77.89 216	90.91 220

LPG-MVS_test		75.82 250	74.58 241	79.56 285	84.31 288	59.37 305	90.44 232	89.73 249	69.49 263	64.86 297	88.42 209	38.65 331	94.30 222	72.56 191	72.76 255	85.01 316

LGP-MVS_train				79.56 285	84.31 288	59.37 305		89.73 249	69.49 263	64.86 297	88.42 209	38.65 331	94.30 222	72.56 191	72.76 255	85.01 316

VPNet		78.82 196	77.53 199	82.70 201	84.52 283	66.44 135	93.93 75	92.23 136	80.46 57	72.60 203	88.38 211	49.18 274	93.13 260	72.47 193	63.97 324	88.55 251

GG-mvs-BLEND				86.53 74	91.91 111	69.67 53	75.02 382	94.75 35		78.67 142	90.85 174	77.91 7	94.56 213	72.25 194	93.74 45	95.36 66

test-LLR		80.10 172	79.56 166	81.72 230	86.93 239	61.17 266	92.70 134	91.54 175	71.51 234	75.62 170	86.94 240	53.83 226	92.38 290	72.21 195	84.76 152	91.60 204

test-mter		79.96 175	79.38 172	81.72 230	86.93 239	61.17 266	92.70 134	91.54 175	73.85 166	75.62 170	86.94 240	49.84 267	92.38 290	72.21 195	84.76 152	91.60 204

IB-MVS	77.80 4	82.18 133	80.46 154	87.35 45	89.14 178	70.28 36	95.59 26	95.17 23	78.85 91	70.19 237	85.82 253	70.66 43	97.67 53	72.19 197	66.52 299	94.09 133
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
cl22		77.94 214	76.78 212	81.42 236	87.57 220	64.93 173	90.67 226	88.86 287	72.45 197	67.63 273	82.68 286	64.07 96	92.91 270	71.79 198	65.30 305	86.44 285

v2v482		77.42 221	75.65 228	82.73 199	80.38 330	67.13 117	91.85 175	90.23 229	75.09 146	69.37 245	83.39 279	53.79 228	94.44 218	71.77 199	65.00 311	86.63 283

baseline1		81.84 140	81.03 141	84.28 157	91.60 119	66.62 131	91.08 211	91.66 172	81.87 37	74.86 179	91.67 161	69.98 47	94.92 198	71.76 200	64.75 314	91.29 215

V42		76.46 238	74.55 242	82.19 218	79.14 348	67.82 97	90.26 241	89.42 259	73.75 169	68.63 259	81.89 295	51.31 253	94.09 231	71.69 201	64.84 312	84.66 319

1314		80.70 160	78.95 178	85.94 91	87.77 218	67.56 104	87.91 288	92.55 128	72.17 207	67.44 275	93.09 123	50.27 262	97.04 98	71.68 202	87.64 122	93.23 161

CDS-MVSNet		81.43 147	80.74 145	83.52 180	86.26 250	64.45 180	92.09 160	90.65 211	75.83 136	73.95 190	89.81 195	63.97 98	92.91 270	71.27 203	82.82 170	93.20 163
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test_vis1_rt		59.09 364	57.31 363	64.43 379	68.44 399	46.02 393	83.05 334	48.63 423	51.96 379	49.57 382	63.86 399	16.30 405	80.20 396	71.21 204	62.79 329	67.07 406

GA-MVS		78.33 208	76.23 219	84.65 141	83.65 297	66.30 139	91.44 188	90.14 232	76.01 134	70.32 235	84.02 272	42.50 318	94.72 203	70.98 205	77.00 228	92.94 172

jajsoiax		73.05 278	71.51 283	77.67 305	77.46 367	54.83 346	88.81 273	90.04 237	69.13 270	62.85 321	83.51 277	31.16 374	92.75 276	70.83 206	69.80 271	85.43 311

3Dnovator+	73.60 7	82.10 137	80.60 151	86.60 69	90.89 139	66.80 127	95.20 34	93.44 89	74.05 160	67.42 276	92.49 139	49.46 270	97.65 57	70.80 207	91.68 74	95.33 67

DP-MVS Recon		82.73 124	81.65 131	85.98 89	97.31 4	67.06 118	95.15 36	91.99 151	69.08 271	76.50 164	93.89 110	54.48 219	98.20 35	70.76 208	85.66 145	92.69 177

miper_ehance_all_eth		77.60 218	76.44 216	81.09 248	85.70 263	64.41 184	90.65 227	88.64 296	72.31 201	67.37 279	82.52 287	64.77 90	92.64 283	70.67 209	65.30 305	86.24 289

PAPM_NR		82.97 121	81.84 129	86.37 79	94.10 44	66.76 128	87.66 294	92.84 114	69.96 258	74.07 188	93.57 117	63.10 117	97.50 67	70.66 210	90.58 90	94.85 91

XVG-OURS-SEG-HR		74.70 264	73.08 262	79.57 284	78.25 360	57.33 329	80.49 352	87.32 320	63.22 320	68.76 257	90.12 193	44.89 310	91.59 311	70.55 211	74.09 246	89.79 234

mvs_tets		72.71 285	71.11 284	77.52 306	77.41 368	54.52 348	88.45 279	89.76 245	68.76 275	62.70 322	83.26 280	29.49 379	92.71 277	70.51 212	69.62 273	85.34 313

cascas		78.18 209	75.77 226	85.41 109	87.14 232	69.11 62	92.96 122	91.15 193	66.71 291	70.47 231	86.07 250	37.49 345	96.48 130	70.15 213	79.80 200	90.65 222

PVSNet_0	68.08 15	71.81 291	68.32 307	82.27 213	84.68 278	62.31 246	88.68 275	90.31 223	75.84 135	57.93 350	80.65 319	37.85 342	94.19 227	69.94 214	29.05 416	90.31 227

thisisatest0515		83.41 112	82.49 121	86.16 85	89.46 167	68.26 84	93.54 98	94.70 38	74.31 156	75.75 167	90.92 172	72.62 31	96.52 127	69.64 215	81.50 186	93.71 148

XXY-MVS		77.94 214	76.44 216	82.43 207	82.60 309	64.44 181	92.01 165	91.83 162	73.59 174	70.00 240	85.82 253	54.43 220	94.76 200	69.63 216	68.02 289	88.10 258

MAR-MVS		84.18 96	83.43 98	86.44 76	96.25 21	65.93 148	94.28 58	94.27 59	74.41 153	79.16 132	95.61 49	53.99 225	98.88 22	69.62 217	93.26 54	94.50 115
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
Patchmatch-RL test		68.17 321	64.49 332	79.19 289	71.22 389	53.93 350	70.07 392	71.54 398	69.22 267	56.79 355	62.89 400	56.58 194	88.61 341	69.53 218	52.61 377	95.03 86

TAMVS		80.37 166	79.45 169	83.13 193	85.14 272	63.37 217	91.23 204	90.76 206	74.81 150	72.65 202	88.49 208	60.63 142	92.95 265	69.41 219	81.95 182	93.08 167

testdata				81.34 238	89.02 180	57.72 322		89.84 243	58.65 355	85.32 65	94.09 105	57.03 183	93.28 258	69.34 220	90.56 91	93.03 169

c3_l		76.83 233	75.47 229	80.93 252	85.02 275	64.18 194	90.39 235	88.11 310	71.66 224	66.65 288	81.64 300	63.58 109	92.56 284	69.31 221	62.86 328	86.04 295

v1144		76.73 236	74.88 236	82.27 213	80.23 334	66.60 132	91.68 184	90.21 231	73.69 171	69.06 250	81.89 295	52.73 240	94.40 219	69.21 222	65.23 308	85.80 302

ETVMVS		84.22 95	83.71 89	85.76 99	92.58 90	68.25 86	92.45 148	95.53 15	79.54 75	79.46 127	91.64 162	70.29 45	94.18 228	69.16 223	82.76 173	94.84 94

Anonymous20240529		76.84 232	74.15 249	84.88 128	91.02 135	64.95 172	93.84 83	91.09 196	53.57 375	73.00 195	87.42 231	35.91 355	97.32 77	69.14 224	72.41 260	92.36 186

XVG-OURS		74.25 267	72.46 273	79.63 282	78.45 358	57.59 325	80.33 354	87.39 319	63.86 312	68.76 257	89.62 197	40.50 325	91.72 307	69.00 225	74.25 244	89.58 237

v148		76.19 239	74.47 244	81.36 237	80.05 336	64.44 181	91.75 182	90.23 229	73.68 172	67.13 280	80.84 315	55.92 203	93.86 249	68.95 226	61.73 342	85.76 305

anonymousdsp		71.14 296	69.37 300	76.45 320	72.95 385	54.71 347	84.19 319	88.88 285	61.92 335	62.15 325	79.77 331	38.14 338	91.44 318	68.90 227	67.45 293	83.21 336

3Dnovator	73.91 6	82.69 127	80.82 144	88.31 26	89.57 163	71.26 22	92.60 141	94.39 54	78.84 92	67.89 269	92.48 140	48.42 280	98.52 28	68.80 228	94.40 36	95.15 79

test_fmvs3		56.82 365	54.86 369	62.69 384	53.59 417	35.47 414	75.87 378	65.64 408	43.91 402	55.10 359	71.43 383	6.91 422	74.40 404	68.64 229	52.63 376	78.20 385

Anonymous202405211		77.96 213	75.33 232	85.87 93	93.73 53	64.52 176	94.85 45	85.36 344	62.52 328	76.11 165	90.18 187	29.43 380	97.29 79	68.51 230	77.24 227	95.81 49

eth_miper_zixun_eth		75.96 248	74.40 245	80.66 254	84.66 279	63.02 226	89.28 264	88.27 306	71.88 215	65.73 291	81.65 299	59.45 155	92.81 273	68.13 231	60.53 351	86.14 291

PVSNet	73.49 8	80.05 173	78.63 181	84.31 155	90.92 138	64.97 171	92.47 147	91.05 201	79.18 83	72.43 209	90.51 179	37.05 351	94.06 234	68.06 232	86.00 140	93.90 144

FA-MVS(test-final)		79.12 189	77.23 206	84.81 133	90.54 144	63.98 197	81.35 347	91.71 167	71.09 242	74.85 180	82.94 282	52.85 237	97.05 95	67.97 233	81.73 185	93.41 155

v144192		76.05 244	74.03 251	82.12 221	79.50 342	66.55 134	91.39 193	89.71 252	72.30 202	68.17 263	81.33 307	51.75 248	94.03 239	67.94 234	64.19 319	85.77 303

UGNet		79.87 177	78.68 180	83.45 185	89.96 155	61.51 261	92.13 157	90.79 205	76.83 124	78.85 139	86.33 248	38.16 337	96.17 142	67.93 235	87.17 127	92.67 178
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
IterMVS-LS		76.49 237	75.18 234	80.43 259	84.49 284	62.74 235	90.64 228	88.80 289	72.40 199	65.16 296	81.72 298	60.98 138	92.27 296	67.74 236	64.65 316	86.29 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		78.97 192	78.22 187	81.25 239	85.33 266	62.73 236	89.53 259	93.21 97	72.39 200	72.14 212	90.13 191	60.99 137	94.72 203	67.73 237	72.49 258	86.29 287

gg-mvs-nofinetune		77.18 224	74.31 246	85.80 97	91.42 125	68.36 80	71.78 387	94.72 36	49.61 387	77.12 157	45.92 413	77.41 8	93.98 241	67.62 238	93.16 55	95.05 84

LCM-MVSNet-Re		72.93 280	71.84 279	76.18 323	88.49 190	48.02 380	80.07 359	70.17 400	73.96 164	52.25 370	80.09 328	49.98 264	88.24 347	67.35 239	84.23 160	92.28 190

tpm2		79.80 178	77.95 192	85.34 113	88.28 199	68.26 84	81.56 344	91.42 181	70.11 256	77.59 152	80.50 320	67.40 60	94.26 226	67.34 240	77.35 224	93.51 153

v8		75.35 256	73.26 261	81.61 232	80.67 327	66.82 125	89.54 258	89.27 264	71.65 225	63.30 315	80.30 324	54.99 213	94.06 234	67.33 241	62.33 334	83.94 324

sd_testset		77.08 227	75.37 230	82.20 217	89.25 173	62.11 249	82.06 339	89.09 276	76.77 126	70.84 228	87.12 236	41.43 322	95.01 193	67.23 242	74.55 239	89.48 240

UWE-MVS		80.81 159	81.01 142	80.20 265	89.33 170	57.05 331	91.91 171	94.71 37	75.67 137	75.01 178	89.37 199	63.13 116	91.44 318	67.19 243	82.80 172	92.12 198

v1192		75.98 246	73.92 253	82.15 219	79.73 338	66.24 141	91.22 205	89.75 246	72.67 191	68.49 261	81.42 305	49.86 266	94.27 224	67.08 244	65.02 310	85.95 298

114514_t		79.17 188	77.67 194	83.68 176	95.32 29	65.53 158	92.85 128	91.60 174	63.49 316	67.92 266	90.63 177	46.65 294	95.72 166	67.01 245	83.54 164	89.79 234

Fast-Effi-MVS+		81.14 151	80.01 158	84.51 148	90.24 150	65.86 149	94.12 65	89.15 271	73.81 168	75.37 175	88.26 214	57.26 180	94.53 215	66.97 246	84.92 149	93.15 164

无先验							92.71 133	92.61 126	62.03 333				97.01 99	66.63 247		93.97 139

v1921920		75.63 254	73.49 259	82.06 225	79.38 343	66.35 137	91.07 213	89.48 255	71.98 210	67.99 264	81.22 310	49.16 276	93.90 245	66.56 248	64.56 317	85.92 300

cl____		76.07 241	74.67 237	80.28 262	85.15 271	61.76 256	90.12 244	88.73 291	71.16 239	65.43 293	81.57 302	61.15 135	92.95 265	66.54 249	62.17 335	86.13 293

DIV-MVS_self_test		76.07 241	74.67 237	80.28 262	85.14 272	61.75 257	90.12 244	88.73 291	71.16 239	65.42 294	81.60 301	61.15 135	92.94 269	66.54 249	62.16 337	86.14 291

Fast-Effi-MVS+-dtu		75.04 260	73.37 260	80.07 268	80.86 323	59.52 303	91.20 207	85.38 343	71.90 213	65.20 295	84.84 262	41.46 321	92.97 264	66.50 251	72.96 254	87.73 261

UniMVSNet_NR-MVSNet		78.15 210	77.55 198	79.98 272	84.46 285	60.26 291	92.25 152	93.20 99	77.50 115	68.88 254	86.61 243	66.10 71	92.13 298	66.38 252	62.55 331	87.54 263

DU-MVS		76.86 230	75.84 225	79.91 275	82.96 305	60.26 291	91.26 202	91.54 175	76.46 131	68.88 254	86.35 246	56.16 198	92.13 298	66.38 252	62.55 331	87.35 269

1112_ss		80.56 162	79.83 162	82.77 198	88.65 188	60.78 274	92.29 151	88.36 302	72.58 193	72.46 208	94.95 73	65.09 83	93.42 257	66.38 252	77.71 217	94.10 132

FIs		79.47 184	79.41 170	79.67 281	85.95 256	59.40 304	91.68 184	93.94 66	78.06 102	68.96 253	88.28 212	66.61 66	91.77 306	66.20 255	74.99 238	87.82 260

tpm		78.58 203	77.03 208	83.22 191	85.94 258	64.56 175	83.21 331	91.14 194	78.31 99	73.67 191	79.68 332	64.01 97	92.09 300	66.07 256	71.26 268	93.03 169

ACMM	69.62 13	74.34 265	72.73 268	79.17 290	84.25 290	57.87 320	90.36 237	89.93 240	63.17 322	65.64 292	86.04 252	37.79 343	94.10 230	65.89 257	71.52 265	85.55 308
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Vis-MVSNet		80.92 157	79.98 160	83.74 170	88.48 191	61.80 254	93.44 105	88.26 308	73.96 164	77.73 148	91.76 158	49.94 265	94.76 200	65.84 258	90.37 94	94.65 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Test_1112_low_res		79.56 181	78.60 182	82.43 207	88.24 202	60.39 290	92.09 160	87.99 313	72.10 209	71.84 216	87.42 231	64.62 91	93.04 261	65.80 259	77.30 225	93.85 146

v10		74.77 263	72.54 272	81.46 235	80.33 332	66.71 129	89.15 268	89.08 277	70.94 244	63.08 318	79.86 329	52.52 241	94.04 237	65.70 260	62.17 335	83.64 327

thisisatest0530		81.15 150	80.07 156	84.39 152	88.26 200	65.63 154	91.40 191	94.62 42	71.27 238	70.93 227	89.18 201	72.47 32	96.04 151	65.62 261	76.89 229	91.49 206

D2MVS		73.80 272	72.02 277	79.15 292	79.15 347	62.97 227	88.58 277	90.07 234	72.94 184	59.22 339	78.30 340	42.31 320	92.70 279	65.59 262	72.00 261	81.79 354

MVP-Stereo		77.12 226	76.23 219	79.79 279	81.72 317	66.34 138	89.29 263	90.88 204	70.56 252	62.01 326	82.88 283	49.34 271	94.13 229	65.55 263	93.80 43	78.88 379
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1240		75.21 259	72.98 264	81.88 227	79.20 345	66.00 145	90.75 222	89.11 275	71.63 229	67.41 277	81.22 310	47.36 290	93.87 247	65.46 264	64.72 315	85.77 303

miper_lstm_enhance		73.05 278	71.73 281	77.03 314	83.80 294	58.32 317	81.76 340	88.88 285	69.80 261	61.01 328	78.23 342	57.19 181	87.51 357	65.34 265	59.53 356	85.27 315

原ACMM1				84.42 150	93.21 68	64.27 191		93.40 93	65.39 300	79.51 126	92.50 137	58.11 174	96.69 120	65.27 266	93.96 40	92.32 188

tt0805		73.07 277	70.73 289	80.07 268	78.37 359	57.05 331	87.78 291	92.18 143	61.23 340	67.04 281	86.49 245	31.35 373	94.58 208	65.06 267	67.12 294	88.57 250

UniMVSNet (Re)		77.58 219	76.78 212	79.98 272	84.11 291	60.80 273	91.76 180	93.17 101	76.56 130	69.93 243	84.78 263	63.32 113	92.36 292	64.89 268	62.51 333	86.78 279

BH-w/o		80.49 164	79.30 173	84.05 164	90.83 141	64.36 188	93.60 95	89.42 259	74.35 155	69.09 248	90.15 190	55.23 209	95.61 170	64.61 269	86.43 139	92.17 196

AdaColmap		78.94 193	77.00 210	84.76 135	96.34 17	65.86 149	92.66 138	87.97 315	62.18 330	70.56 230	92.37 143	43.53 314	97.35 75	64.50 270	82.86 169	91.05 219

PCF-MVS	73.15 9	79.29 186	77.63 196	84.29 156	86.06 254	65.96 147	87.03 301	91.10 195	69.86 260	69.79 244	90.64 175	57.54 179	96.59 122	64.37 271	82.29 174	90.32 226
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
API-MVS		82.28 132	80.53 152	87.54 41	96.13 22	70.59 31	93.63 94	91.04 202	65.72 299	75.45 174	92.83 133	56.11 200	98.89 21	64.10 272	89.75 101	93.15 164

UniMVSNet_ETH3D		72.74 284	70.53 291	79.36 287	78.62 357	56.64 335	85.01 314	89.20 267	63.77 313	64.84 299	84.44 268	34.05 362	91.86 304	63.94 273	70.89 270	89.57 238

Anonymous20231211		73.08 276	70.39 292	81.13 243	90.62 143	63.33 218	91.40 191	90.06 236	51.84 380	64.46 304	80.67 318	36.49 353	94.07 233	63.83 274	64.17 320	85.98 297

MS-PatchMatch		77.90 216	76.50 215	82.12 221	85.99 255	69.95 42	91.75 182	92.70 118	73.97 163	62.58 323	84.44 268	41.11 323	95.78 158	63.76 275	92.17 66	80.62 365

新几何1				84.73 136	92.32 93	64.28 190		91.46 180	59.56 351	79.77 123	92.90 129	56.95 188	96.57 124	63.40 276	92.91 58	93.34 157

dmvs_re		76.93 229	75.36 231	81.61 232	87.78 217	60.71 280	80.00 360	87.99 313	79.42 77	69.02 251	89.47 198	46.77 292	94.32 220	63.38 277	74.45 242	89.81 233

GeoE		78.90 194	77.43 200	83.29 188	88.95 182	62.02 250	92.31 150	86.23 334	70.24 255	71.34 225	89.27 200	54.43 220	94.04 237	63.31 278	80.81 193	93.81 147

IterMVS		72.65 288	70.83 286	78.09 302	82.17 313	62.96 228	87.64 295	86.28 332	71.56 232	60.44 332	78.85 338	45.42 306	86.66 361	63.30 279	61.83 339	84.65 320
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	48.56 21	66.77 331	64.41 333	73.84 341	70.65 393	50.31 369	77.79 371	85.73 341	45.54 398	44.76 397	82.14 293	35.40 357	90.14 332	63.18 280	74.54 241	81.07 360
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs4		73.92 271	71.81 280	80.25 264	79.17 346	65.24 163	87.43 297	87.26 323	67.64 284	63.46 313	83.91 274	48.96 278	91.53 316	62.94 281	65.49 304	83.96 323

tttt0517		79.50 182	78.53 183	82.41 210	87.22 230	61.43 264	89.75 255	94.76 34	69.29 266	67.91 267	88.06 221	72.92 28	95.63 168	62.91 282	73.90 249	90.16 228

FC-MVSNet-test		77.99 212	78.08 189	77.70 304	84.89 277	55.51 342	90.27 240	93.75 75	76.87 121	66.80 286	87.59 228	65.71 77	90.23 330	62.89 283	73.94 247	87.37 268

Baseline_NR-MVSNet		73.99 270	72.83 265	77.48 308	80.78 325	59.29 308	91.79 177	84.55 352	68.85 272	68.99 252	80.70 316	56.16 198	92.04 301	62.67 284	60.98 348	81.11 359

IterMVS-SCA-FT		71.55 294	69.97 294	76.32 321	81.48 319	60.67 282	87.64 295	85.99 337	66.17 295	59.50 337	78.88 337	45.53 304	83.65 379	62.58 285	61.93 338	84.63 321

IS-MVSNet		80.14 171	79.41 170	82.33 211	87.91 210	60.08 295	91.97 169	88.27 306	72.90 188	71.44 224	91.73 160	61.44 134	93.66 252	62.47 286	86.53 137	93.24 160

WR-MVS		76.76 235	75.74 227	79.82 278	84.60 280	62.27 247	92.60 141	92.51 129	76.06 133	67.87 270	85.34 257	56.76 189	90.24 329	62.20 287	63.69 326	86.94 277

pmmvs5		73.35 275	71.52 282	78.86 294	78.64 356	60.61 284	91.08 211	86.90 325	67.69 281	63.32 314	83.64 275	44.33 312	90.53 323	62.04 288	66.02 301	85.46 310

TranMVSNet+NR-MVSNet		75.86 249	74.52 243	79.89 276	82.44 311	60.64 283	91.37 196	91.37 182	76.63 128	67.65 272	86.21 249	52.37 243	91.55 312	61.84 289	60.81 349	87.48 265

CVMVSNet		74.04 269	74.27 247	73.33 344	85.33 266	43.94 398	89.53 259	88.39 301	54.33 374	70.37 234	90.13 191	49.17 275	84.05 375	61.83 290	79.36 204	91.99 200

PM-MVS		59.40 362	56.59 364	67.84 371	63.63 406	41.86 401	76.76 373	63.22 411	59.01 353	51.07 377	72.27 378	11.72 414	83.25 383	61.34 291	50.28 383	78.39 384

testdata2													96.09 146	61.26 292

UA-Net		80.02 174	79.65 164	81.11 244	89.33 170	57.72 322	86.33 309	89.00 283	77.44 116	81.01 107	89.15 202	59.33 158	95.90 155	61.01 293	84.28 159	89.73 236

NR-MVSNet		76.05 244	74.59 240	80.44 258	82.96 305	62.18 248	90.83 219	91.73 165	77.12 119	60.96 329	86.35 246	59.28 159	91.80 305	60.74 294	61.34 346	87.35 269

XVG-ACMP-BASELINE		68.04 322	65.53 323	75.56 325	74.06 382	52.37 355	78.43 366	85.88 338	62.03 333	58.91 343	81.21 312	20.38 401	91.15 320	60.69 295	68.18 286	83.16 337

test_post1							78.95 363				20.70 426	53.05 235	91.50 317	60.43 296

SCA		75.82 250	72.76 266	85.01 125	86.63 243	70.08 38	81.06 349	89.19 268	71.60 230	70.01 239	77.09 353	45.53 304	90.25 326	60.43 296	73.27 251	94.68 102

pm-mvs1		72.89 281	71.09 285	78.26 300	79.10 349	57.62 324	90.80 220	89.30 263	67.66 282	62.91 320	81.78 297	49.11 277	92.95 265	60.29 298	58.89 359	84.22 322

TR-MVS		78.77 199	77.37 205	82.95 195	90.49 145	60.88 272	93.67 91	90.07 234	70.08 257	74.51 182	91.37 168	45.69 303	95.70 167	60.12 299	80.32 196	92.29 189

MDTV_nov1_ep13_2view						59.90 297	80.13 358		67.65 283	72.79 199		54.33 222		59.83 300		92.58 181

GBi-Net		75.65 252	73.83 254	81.10 245	88.85 183	65.11 167	90.01 248	90.32 220	70.84 246	67.04 281	80.25 325	48.03 282	91.54 313	59.80 301	69.34 275	86.64 280

test1		75.65 252	73.83 254	81.10 245	88.85 183	65.11 167	90.01 248	90.32 220	70.84 246	67.04 281	80.25 325	48.03 282	91.54 313	59.80 301	69.34 275	86.64 280

FMVSNet3		77.73 217	76.04 222	82.80 197	91.20 133	68.99 66	91.87 173	91.99 151	73.35 177	67.04 281	83.19 281	56.62 193	92.14 297	59.80 301	69.34 275	87.28 271

BH-untuned		78.68 200	77.08 207	83.48 184	89.84 157	63.74 202	92.70 134	88.59 297	71.57 231	66.83 285	88.65 207	51.75 248	95.39 181	59.03 304	84.77 151	91.32 213

Vis-MVSNet (Re-imp)		79.24 187	79.57 165	78.24 301	88.46 192	52.29 356	90.41 234	89.12 274	74.24 157	69.13 247	91.91 156	65.77 76	90.09 333	59.00 305	88.09 116	92.33 187

FMVSNet2		76.07 241	74.01 252	82.26 215	88.85 183	67.66 101	91.33 199	91.61 173	70.84 246	65.98 290	82.25 291	48.03 282	92.00 302	58.46 306	68.73 283	87.10 274

mvsany_test3		48.86 375	46.35 378	56.41 388	46.00 423	31.67 419	62.26 407	47.25 424	43.71 403	45.54 395	68.15 391	10.84 415	64.44 420	57.95 307	35.44 409	73.13 397

v7n		71.31 295	68.65 302	79.28 288	76.40 372	60.77 275	86.71 306	89.45 257	64.17 310	58.77 344	78.24 341	44.59 311	93.54 253	57.76 308	61.75 341	83.52 330

QAPM		79.95 176	77.39 204	87.64 34	89.63 162	71.41 20	93.30 109	93.70 77	65.34 302	67.39 278	91.75 159	47.83 287	98.96 16	57.71 309	89.81 98	92.54 182

EPMVS		78.49 205	75.98 223	86.02 88	91.21 132	69.68 52	80.23 356	91.20 189	75.25 144	72.48 207	78.11 343	54.65 215	93.69 251	57.66 310	83.04 168	94.69 101

UWE-MVS-28		76.83 233	77.60 197	74.51 334	84.58 282	50.34 368	88.22 282	94.60 44	74.46 152	66.66 287	88.98 205	62.53 123	85.50 369	57.55 311	80.80 194	87.69 262

WB-MVSnew		77.14 225	76.18 221	80.01 271	86.18 252	63.24 220	91.26 202	94.11 63	71.72 223	73.52 192	87.29 234	45.14 308	93.00 263	56.98 312	79.42 202	83.80 326

PLC	68.80 14	75.23 258	73.68 257	79.86 277	92.93 77	58.68 314	90.64 228	88.30 304	60.90 341	64.43 305	90.53 178	42.38 319	94.57 210	56.52 313	76.54 231	86.33 286
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EPNet_dtu		78.80 197	79.26 174	77.43 309	88.06 206	49.71 372	91.96 170	91.95 153	77.67 110	76.56 163	91.28 169	58.51 168	90.20 331	56.37 314	80.95 190	92.39 185
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
BH-RMVSNet		79.46 185	77.65 195	84.89 127	91.68 118	65.66 152	93.55 97	88.09 311	72.93 185	73.37 193	91.12 171	46.20 301	96.12 144	56.28 315	85.61 146	92.91 173

UnsupCasMVSNet_eth		65.79 336	63.10 339	73.88 340	70.71 392	50.29 370	81.09 348	89.88 242	72.58 193	49.25 384	74.77 369	32.57 367	87.43 358	55.96 316	41.04 397	83.90 325

pmmvs6		67.57 326	64.76 328	76.00 324	72.82 387	53.37 352	88.71 274	86.78 329	53.19 376	57.58 353	78.03 344	35.33 358	92.41 289	55.56 317	54.88 372	82.21 351

pmmvs-eth3d		65.53 339	62.32 345	75.19 328	69.39 397	59.59 301	82.80 336	83.43 362	62.52 328	51.30 376	72.49 373	32.86 364	87.16 360	55.32 318	50.73 381	78.83 380

FE-MVS		75.97 247	73.02 263	84.82 130	89.78 158	65.56 156	77.44 372	91.07 199	64.55 305	72.66 201	79.85 330	46.05 302	96.69 120	54.97 319	80.82 192	92.21 195

OpenMVS	70.45 11	78.54 204	75.92 224	86.41 78	85.93 259	71.68 18	92.74 131	92.51 129	66.49 293	64.56 301	91.96 153	43.88 313	98.10 37	54.61 320	90.65 89	89.44 242

FMVSNet1		72.71 285	69.91 296	81.10 245	83.60 298	65.11 167	90.01 248	90.32 220	63.92 311	63.56 312	80.25 325	36.35 354	91.54 313	54.46 321	66.75 297	86.64 280

PatchmatchNet		77.46 220	74.63 239	85.96 90	89.55 165	70.35 35	79.97 361	89.55 254	72.23 204	70.94 226	76.91 355	57.03 183	92.79 275	54.27 322	81.17 188	94.74 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MIMVSNet		71.64 292	68.44 305	81.23 240	81.97 316	64.44 181	73.05 384	88.80 289	69.67 262	64.59 300	74.79 368	32.79 365	87.82 351	53.99 323	76.35 232	91.42 208

CNLPA		74.31 266	72.30 274	80.32 260	91.49 124	61.66 259	90.85 218	80.72 372	56.67 367	63.85 310	90.64 175	46.75 293	90.84 321	53.79 324	75.99 235	88.47 253

tpm cat1		75.30 257	72.21 275	84.58 145	88.52 189	67.77 98	78.16 370	88.02 312	61.88 336	68.45 262	76.37 359	60.65 141	94.03 239	53.77 325	74.11 245	91.93 201

OurMVSNet-221017-0		64.68 342	62.17 346	72.21 354	76.08 375	47.35 384	80.67 351	81.02 370	56.19 368	51.60 373	79.66 333	27.05 387	88.56 343	53.60 326	53.63 375	80.71 364

PatchMatch-RL		72.06 290	69.98 293	78.28 299	89.51 166	55.70 341	83.49 324	83.39 364	61.24 339	63.72 311	82.76 284	34.77 359	93.03 262	53.37 327	77.59 219	86.12 294

CR-MVSNet		73.79 273	70.82 288	82.70 201	83.15 303	67.96 93	70.25 390	84.00 357	73.67 173	69.97 241	72.41 375	57.82 176	89.48 338	52.99 328	73.13 252	90.64 223

USDC		67.43 329	64.51 331	76.19 322	77.94 364	55.29 343	78.38 367	85.00 347	73.17 179	48.36 387	80.37 322	21.23 398	92.48 288	52.15 329	64.02 323	80.81 363

CP-MVSNet		70.50 299	69.91 296	72.26 353	80.71 326	51.00 365	87.23 300	90.30 224	67.84 280	59.64 336	82.69 285	50.23 263	82.30 389	51.28 330	59.28 357	83.46 332

F-COLMAP		70.66 297	68.44 305	77.32 311	86.37 249	55.91 339	88.00 286	86.32 331	56.94 365	57.28 354	88.07 220	33.58 363	92.49 287	51.02 331	68.37 285	83.55 328

PS-CasMVS		69.86 306	69.13 301	72.07 357	80.35 331	50.57 367	87.02 302	89.75 246	67.27 286	59.19 340	82.28 290	46.58 295	82.24 390	50.69 332	59.02 358	83.39 334

dp		75.01 261	72.09 276	83.76 169	89.28 172	66.22 142	79.96 362	89.75 246	71.16 239	67.80 271	77.19 352	51.81 246	92.54 285	50.39 333	71.44 267	92.51 184

test_vis3_rt		40.46 383	37.79 384	48.47 400	44.49 425	33.35 417	66.56 403	32.84 431	32.39 412	29.65 413	39.13 421	3.91 429	68.65 410	50.17 334	40.99 398	43.40 416

test0.0.03 1		72.76 283	72.71 269	72.88 348	80.25 333	47.99 381	91.22 205	89.45 257	71.51 234	62.51 324	87.66 226	53.83 226	85.06 371	50.16 335	67.84 292	85.58 306

UnsupCasMVSNet_bld		61.60 354	57.71 359	73.29 345	68.73 398	51.64 359	78.61 365	89.05 279	57.20 363	46.11 390	61.96 403	28.70 382	88.60 342	50.08 336	38.90 402	79.63 373

K. test v3		63.09 350	59.61 355	73.53 343	76.26 373	49.38 376	83.27 328	77.15 380	64.35 307	47.77 389	72.32 377	28.73 381	87.79 352	49.93 337	36.69 404	83.41 333

JIA-IIPM		66.06 334	62.45 344	76.88 318	81.42 321	54.45 349	57.49 414	88.67 294	49.36 388	63.86 309	46.86 412	56.06 201	90.25 326	49.53 338	68.83 281	85.95 298

CL-MVSNet_self_test		69.92 304	68.09 308	75.41 326	73.25 384	55.90 340	90.05 247	89.90 241	69.96 258	61.96 327	76.54 356	51.05 256	87.64 354	49.51 339	50.59 382	82.70 345

mvs5depth		61.03 356	57.65 361	71.18 360	67.16 401	47.04 389	72.74 385	77.49 378	57.47 361	60.52 331	72.53 372	22.84 395	88.38 345	49.15 340	38.94 401	78.11 386

FMVSNet5		68.04 322	65.66 322	75.18 329	84.43 286	57.89 319	83.54 323	86.26 333	61.83 337	53.64 366	73.30 371	37.15 349	85.08 370	48.99 341	61.77 340	82.56 348

TransMVSNet (Re)		70.07 303	67.66 309	77.31 312	80.62 329	59.13 310	91.78 179	84.94 348	65.97 296	60.08 335	80.44 321	50.78 257	91.87 303	48.84 342	45.46 390	80.94 361

EU-MVSNet		64.01 346	63.01 340	67.02 376	74.40 381	38.86 411	83.27 328	86.19 335	45.11 399	54.27 362	81.15 313	36.91 352	80.01 397	48.79 343	57.02 364	82.19 352

PEN-MVS		69.46 309	68.56 303	72.17 355	79.27 344	49.71 372	86.90 304	89.24 265	67.24 289	59.08 341	82.51 288	47.23 291	83.54 380	48.42 344	57.12 363	83.25 335

KD-MVS_self_test		60.87 357	58.60 357	67.68 373	66.13 403	39.93 408	75.63 381	84.70 349	57.32 362	49.57 382	68.45 390	29.55 378	82.87 385	48.09 345	47.94 386	80.25 370

KD-MVS_2432*1600		69.03 312	66.37 316	77.01 315	85.56 264	61.06 269	81.44 345	90.25 227	67.27 286	58.00 348	76.53 357	54.49 217	87.63 355	48.04 346	35.77 407	82.34 349

miper_refine_blended		69.03 312	66.37 316	77.01 315	85.56 264	61.06 269	81.44 345	90.25 227	67.27 286	58.00 348	76.53 357	54.49 217	87.63 355	48.04 346	35.77 407	82.34 349

MDTV_nov1_ep13			72.61 270		89.06 179	68.48 77	80.33 354	90.11 233	71.84 218	71.81 217	75.92 363	53.01 236	93.92 244	48.04 346	73.38 250

thres200		79.66 179	78.33 184	83.66 178	92.54 91	65.82 151	93.06 116	96.31 3	74.90 149	73.30 194	88.66 206	59.67 153	95.61 170	47.84 349	78.67 211	89.56 239

RPSCF		64.24 345	61.98 347	71.01 362	76.10 374	45.00 395	75.83 379	75.94 382	46.94 395	58.96 342	84.59 265	31.40 372	82.00 391	47.76 350	60.33 355	86.04 295

lessismore_v0				73.72 342	72.93 386	47.83 382		61.72 413		45.86 393	73.76 370	28.63 383	89.81 335	47.75 351	31.37 412	83.53 329

EG-PatchMatch MVS		68.55 316	65.41 324	77.96 303	78.69 355	62.93 229	89.86 253	89.17 269	60.55 343	50.27 379	77.73 347	22.60 396	94.06 234	47.18 352	72.65 257	76.88 389

test_f		46.58 376	43.45 380	55.96 389	45.18 424	32.05 418	61.18 408	49.49 422	33.39 411	42.05 404	62.48 402	7.00 421	65.56 416	47.08 353	43.21 394	70.27 403

ACMH+	65.35 16	67.65 325	64.55 330	76.96 317	84.59 281	57.10 330	88.08 283	80.79 371	58.59 356	53.00 367	81.09 314	26.63 388	92.95 265	46.51 354	61.69 344	80.82 362

Anonymous20240521		62.09 352	59.08 356	71.10 361	67.19 400	48.72 379	83.91 321	85.23 345	50.38 385	47.84 388	71.22 384	20.74 399	85.51 368	46.47 355	58.75 360	79.06 377

WR-MVS_H		70.59 298	69.94 295	72.53 350	81.03 322	51.43 361	87.35 298	92.03 150	67.38 285	60.23 334	80.70 316	55.84 204	83.45 381	46.33 356	58.58 361	82.72 343

Patchmtry		67.53 327	63.93 335	78.34 297	82.12 314	64.38 185	68.72 395	84.00 357	48.23 393	59.24 338	72.41 375	57.82 176	89.27 339	46.10 357	56.68 367	81.36 356

SixPastTwentyTwo		64.92 341	61.78 348	74.34 337	78.74 354	49.76 371	83.42 327	79.51 377	62.86 324	50.27 379	77.35 348	30.92 376	90.49 324	45.89 358	47.06 387	82.78 340

ambc				69.61 365	61.38 412	41.35 403	49.07 419	85.86 340		50.18 381	66.40 393	10.16 416	88.14 348	45.73 359	44.20 391	79.32 376

thres100view900		78.37 206	77.01 209	82.46 206	91.89 112	63.21 222	91.19 208	96.33 1	72.28 203	70.45 233	87.89 223	60.31 144	95.32 183	45.16 360	77.58 220	88.83 244

tfpn200view9		78.79 198	77.43 200	82.88 196	92.21 97	64.49 177	92.05 163	96.28 4	73.48 175	71.75 218	88.26 214	60.07 149	95.32 183	45.16 360	77.58 220	88.83 244

thres400		78.68 200	77.43 200	82.43 207	92.21 97	64.49 177	92.05 163	96.28 4	73.48 175	71.75 218	88.26 214	60.07 149	95.32 183	45.16 360	77.58 220	87.48 265

DTE-MVSNet		68.46 318	67.33 312	71.87 359	77.94 364	49.00 378	86.16 310	88.58 298	66.36 294	58.19 345	82.21 292	46.36 296	83.87 378	44.97 363	55.17 370	82.73 342

pmmvs3		55.51 367	51.50 373	67.53 374	57.90 415	50.93 366	80.37 353	73.66 390	40.63 408	44.15 400	64.75 397	16.30 405	78.97 398	44.77 364	40.98 399	72.69 398

our_test_3		68.29 320	64.69 329	79.11 293	78.92 350	64.85 174	88.40 280	85.06 346	60.32 346	52.68 368	76.12 361	40.81 324	89.80 337	44.25 365	55.65 368	82.67 347

tpmvs		72.88 282	69.76 298	82.22 216	90.98 136	67.05 119	78.22 369	88.30 304	63.10 323	64.35 306	74.98 366	55.09 212	94.27 224	43.25 366	69.57 274	85.34 313

ITE_SJBPF				70.43 363	74.44 380	47.06 388		77.32 379	60.16 347	54.04 364	83.53 276	23.30 394	84.01 376	43.07 367	61.58 345	80.21 371

Anonymous20231206		67.53 327	65.78 319	72.79 349	74.95 378	47.59 383	88.23 281	87.32 320	61.75 338	58.07 347	77.29 350	37.79 343	87.29 359	42.91 368	63.71 325	83.48 331

YYNet1		63.76 349	60.14 353	74.62 333	78.06 363	60.19 294	83.46 326	83.99 359	56.18 369	39.25 406	71.56 382	37.18 348	83.34 382	42.90 369	48.70 385	80.32 368

MDA-MVSNet_test_wron		63.78 348	60.16 352	74.64 332	78.15 362	60.41 288	83.49 324	84.03 355	56.17 370	39.17 407	71.59 381	37.22 347	83.24 384	42.87 370	48.73 384	80.26 369

MSDG		69.54 308	65.73 320	80.96 250	85.11 274	63.71 205	84.19 319	83.28 365	56.95 364	54.50 361	84.03 271	31.50 371	96.03 152	42.87 370	69.13 280	83.14 338

thres600view7		78.00 211	76.66 214	82.03 226	91.93 109	63.69 207	91.30 201	96.33 1	72.43 198	70.46 232	87.89 223	60.31 144	94.92 198	42.64 372	76.64 230	87.48 265

ACMH	63.93 17	68.62 315	64.81 327	80.03 270	85.22 270	63.25 219	87.72 292	84.66 350	60.83 342	51.57 374	79.43 335	27.29 386	94.96 195	41.76 373	64.84 312	81.88 353
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
testgi		64.48 344	62.87 342	69.31 367	71.24 388	40.62 405	85.49 311	79.92 375	65.36 301	54.18 363	83.49 278	23.74 393	84.55 372	41.60 374	60.79 350	82.77 341

PatchT		69.11 311	65.37 325	80.32 260	82.07 315	63.68 208	67.96 400	87.62 318	50.86 384	69.37 245	65.18 395	57.09 182	88.53 344	41.59 375	66.60 298	88.74 247

LF4IMVS		54.01 370	52.12 371	59.69 385	62.41 409	39.91 409	68.59 396	68.28 405	42.96 405	44.55 399	75.18 365	14.09 412	68.39 411	41.36 376	51.68 379	70.78 401

ADS-MVSNet2		66.90 330	63.44 338	77.26 313	88.06 206	60.70 281	68.01 398	75.56 385	57.57 358	64.48 302	69.87 385	38.68 329	84.10 374	40.87 377	67.89 290	86.97 275

ADS-MVSNet		68.54 317	64.38 334	81.03 249	88.06 206	66.90 124	68.01 398	84.02 356	57.57 358	64.48 302	69.87 385	38.68 329	89.21 340	40.87 377	67.89 290	86.97 275

LTVRE_ROB	59.60 19	66.27 333	63.54 337	74.45 335	84.00 293	51.55 360	67.08 402	83.53 361	58.78 354	54.94 360	80.31 323	34.54 360	93.23 259	40.64 379	68.03 288	78.58 382
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
MVS-HIRNet		60.25 360	55.55 367	74.35 336	84.37 287	56.57 336	71.64 388	74.11 389	34.44 410	45.54 395	42.24 418	31.11 375	89.81 335	40.36 380	76.10 234	76.67 390

ppachtmachnet_test		67.72 324	63.70 336	79.77 280	78.92 350	66.04 144	88.68 275	82.90 367	60.11 348	55.45 358	75.96 362	39.19 328	90.55 322	39.53 381	52.55 378	82.71 344

new-patchmatchnet		59.30 363	56.48 365	67.79 372	65.86 404	44.19 396	82.47 337	81.77 368	59.94 349	43.65 401	66.20 394	27.67 385	81.68 392	39.34 382	41.40 396	77.50 388

AllTest		61.66 353	58.06 358	72.46 351	79.57 339	51.42 362	80.17 357	68.61 403	51.25 382	45.88 391	81.23 308	19.86 403	86.58 362	38.98 383	57.01 365	79.39 374

TestCases				72.46 351	79.57 339	51.42 362		68.61 403	51.25 382	45.88 391	81.23 308	19.86 403	86.58 362	38.98 383	57.01 365	79.39 374

test20.03		63.83 347	62.65 343	67.38 375	70.58 394	39.94 407	86.57 307	84.17 354	63.29 319	51.86 372	77.30 349	37.09 350	82.47 387	38.87 385	54.13 374	79.73 372

TAPA-MVS	70.22 12	74.94 262	73.53 258	79.17 290	90.40 147	52.07 357	89.19 267	89.61 253	62.69 327	70.07 238	92.67 135	48.89 279	94.32 220	38.26 386	79.97 198	91.12 218
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
tmp_tt		22.26 394	23.75 396	17.80 410	5.23 434	12.06 435	35.26 421	39.48 428	2.82 428	18.94 419	44.20 417	22.23 397	24.64 429	36.30 387	9.31 426	16.69 423

DSMNet-mixed		56.78 366	54.44 370	63.79 380	63.21 407	29.44 423	64.43 405	64.10 410	42.12 407	51.32 375	71.60 380	31.76 370	75.04 402	36.23 388	65.20 309	86.87 278

TinyColmap		60.32 359	56.42 366	72.00 358	78.78 353	53.18 353	78.36 368	75.64 384	52.30 377	41.59 405	75.82 364	14.76 410	88.35 346	35.84 389	54.71 373	74.46 393

MDA-MVSNet-bldmvs		61.54 355	57.70 360	73.05 346	79.53 341	57.00 334	83.08 332	81.23 369	57.57 358	34.91 411	72.45 374	32.79 365	86.26 364	35.81 390	41.95 395	75.89 391

RPMNet		70.42 300	65.68 321	84.63 143	83.15 303	67.96 93	70.25 390	90.45 214	46.83 396	69.97 241	65.10 396	56.48 197	95.30 186	35.79 391	73.13 252	90.64 223

Patchmatch-test		65.86 335	60.94 350	80.62 257	83.75 295	58.83 312	58.91 413	75.26 387	44.50 401	50.95 378	77.09 353	58.81 166	87.90 349	35.13 392	64.03 322	95.12 81

OpenMVS_ROB	61.12 18	66.39 332	62.92 341	76.80 319	76.51 371	57.77 321	89.22 265	83.41 363	55.48 371	53.86 365	77.84 345	26.28 389	93.95 243	34.90 393	68.76 282	78.68 381

test_method		38.59 385	35.16 388	48.89 399	54.33 416	21.35 429	45.32 420	53.71 418	7.41 426	28.74 414	51.62 410	8.70 419	52.87 423	33.73 394	32.89 411	72.47 399

LCM-MVSNet		40.54 381	35.79 386	54.76 393	36.92 430	30.81 420	51.41 417	69.02 402	22.07 417	24.63 417	45.37 414	4.56 426	65.81 415	33.67 395	34.50 410	67.67 404

DP-MVS		69.90 305	66.48 313	80.14 266	95.36 28	62.93 229	89.56 256	76.11 381	50.27 386	57.69 352	85.23 258	39.68 327	95.73 162	33.35 396	71.05 269	81.78 355

TDRefinement		55.28 368	51.58 372	66.39 377	59.53 414	46.15 392	76.23 376	72.80 391	44.60 400	42.49 403	76.28 360	15.29 408	82.39 388	33.20 397	43.75 392	70.62 402

COLMAP_ROB	57.96 20	62.98 351	59.65 354	72.98 347	81.44 320	53.00 354	83.75 322	75.53 386	48.34 391	48.81 386	81.40 306	24.14 391	90.30 325	32.95 398	60.52 352	75.65 392
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ttmdpeth		53.34 371	49.96 374	63.45 381	62.07 411	40.04 406	72.06 386	65.64 408	42.54 406	51.88 371	77.79 346	13.94 413	76.48 400	32.93 399	30.82 415	73.84 395

new_pmnet		49.31 374	46.44 377	57.93 387	62.84 408	40.74 404	68.47 397	62.96 412	36.48 409	35.09 410	57.81 407	14.97 409	72.18 406	32.86 400	46.44 388	60.88 409

myMVS_eth3d		72.58 289	72.74 267	72.10 356	87.87 212	49.45 374	88.07 284	89.01 280	72.91 186	63.11 316	88.10 218	63.63 104	85.54 366	32.73 401	69.23 278	81.32 357

MIMVSNet1		60.16 361	57.33 362	68.67 369	69.71 395	44.13 397	78.92 364	84.21 353	55.05 372	44.63 398	71.85 379	23.91 392	81.54 393	32.63 402	55.03 371	80.35 367

LS3D		69.17 310	66.40 315	77.50 307	91.92 110	56.12 338	85.12 313	80.37 374	46.96 394	56.50 356	87.51 230	37.25 346	93.71 250	32.52 403	79.40 203	82.68 346

tfpnnormal		70.10 302	67.36 311	78.32 298	83.45 300	60.97 271	88.85 272	92.77 116	64.85 304	60.83 330	78.53 339	43.52 315	93.48 255	31.73 404	61.70 343	80.52 366

N_pmnet		50.55 373	49.11 375	54.88 392	77.17 369	4.02 436	84.36 317	2.00 434	48.59 389	45.86 393	68.82 388	32.22 368	82.80 386	31.58 405	51.38 380	77.81 387

WAC-MVS						49.45 374								31.56 406

dmvs_testset		65.55 338	66.45 314	62.86 382	79.87 337	22.35 428	76.55 374	71.74 396	77.42 118	55.85 357	87.77 225	51.39 252	80.69 395	31.51 407	65.92 302	85.55 308

kuosan		60.86 358	60.24 351	62.71 383	81.57 318	46.43 391	75.70 380	85.88 338	57.98 357	48.95 385	69.53 387	58.42 169	76.53 399	28.25 408	35.87 406	65.15 407

testing3		70.38 301	70.83 286	69.03 368	85.82 260	43.93 399	90.72 225	90.56 213	68.06 279	60.24 333	86.82 242	64.83 88	84.12 373	26.33 409	64.10 321	79.04 378

PMMVS2		37.93 386	33.61 389	50.92 396	46.31 422	24.76 426	60.55 411	50.05 420	28.94 416	20.93 418	47.59 411	4.41 428	65.13 417	25.14 410	18.55 422	62.87 408

MVStest1		51.35 372	46.89 376	64.74 378	65.06 405	51.10 364	67.33 401	72.58 392	30.20 414	35.30 409	74.82 367	27.70 384	69.89 409	24.44 411	24.57 418	73.22 396

test_0402		64.54 343	61.09 349	74.92 331	84.10 292	60.75 277	87.95 287	79.71 376	52.03 378	52.41 369	77.20 351	32.21 369	91.64 309	23.14 412	61.03 347	72.36 400

APD_test1		40.50 382	37.31 385	50.09 398	51.88 418	35.27 415	59.45 412	52.59 419	21.64 418	26.12 416	57.80 408	4.56 426	66.56 414	22.64 413	39.09 400	48.43 414

Syy-MVS		69.65 307	69.52 299	70.03 364	87.87 212	43.21 400	88.07 284	89.01 280	72.91 186	63.11 316	88.10 218	45.28 307	85.54 366	22.07 414	69.23 278	81.32 357

ANet_high		40.27 384	35.20 387	55.47 390	34.74 431	34.47 416	63.84 406	71.56 397	48.42 390	18.80 420	41.08 419	9.52 418	64.45 419	20.18 415	8.66 427	67.49 405

DeepMVS_CX				34.71 407	51.45 419	24.73 427		28.48 433	31.46 413	17.49 423	52.75 409	5.80 424	42.60 428	18.18 416	19.42 421	36.81 420

dongtai		55.18 369	55.46 368	54.34 394	76.03 376	36.88 412	76.07 377	84.61 351	51.28 381	43.41 402	64.61 398	56.56 195	67.81 412	18.09 417	28.50 417	58.32 410

EGC-MVSNET		42.35 380	38.09 383	55.11 391	74.57 379	46.62 390	71.63 389	55.77 415	0.04 429	0.24 430	62.70 401	14.24 411	74.91 403	17.59 418	46.06 389	43.80 415

testf1		32.77 388	29.47 391	42.67 404	41.89 427	30.81 420	52.07 415	43.45 425	15.45 421	18.52 421	44.82 415	2.12 430	58.38 421	16.05 419	30.87 413	38.83 417

APD_test2		32.77 388	29.47 391	42.67 404	41.89 427	30.81 420	52.07 415	43.45 425	15.45 421	18.52 421	44.82 415	2.12 430	58.38 421	16.05 419	30.87 413	38.83 417

FPMVS		45.64 378	43.10 382	53.23 395	51.42 420	36.46 413	64.97 404	71.91 395	29.13 415	27.53 415	61.55 404	9.83 417	65.01 418	16.00 421	55.58 369	58.22 411

Gipuma		34.91 387	31.44 390	45.30 402	70.99 391	39.64 410	19.85 424	72.56 393	20.10 420	16.16 424	21.47 425	5.08 425	71.16 407	13.07 422	43.70 393	25.08 422
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVE	24.84 23	24.35 392	19.77 398	38.09 406	34.56 432	26.92 425	26.57 422	38.87 429	11.73 425	11.37 426	27.44 422	1.37 433	50.42 425	11.41 423	14.60 423	36.93 419
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
WB-MVS		46.23 377	44.94 379	50.11 397	62.13 410	21.23 430	76.48 375	55.49 416	45.89 397	35.78 408	61.44 405	35.54 356	72.83 405	9.96 424	21.75 419	56.27 412

PMVS	26.43 22	31.84 390	28.16 393	42.89 403	25.87 433	27.58 424	50.92 418	49.78 421	21.37 419	14.17 425	40.81 420	2.01 432	66.62 413	9.61 425	38.88 403	34.49 421
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SSC-MVS		44.51 379	43.35 381	47.99 401	61.01 413	18.90 432	74.12 383	54.36 417	43.42 404	34.10 412	60.02 406	34.42 361	70.39 408	9.14 426	19.57 420	54.68 413

E-PMN		24.61 391	24.00 395	26.45 408	43.74 426	18.44 433	60.86 409	39.66 427	15.11 423	9.53 427	22.10 424	6.52 423	46.94 426	8.31 427	10.14 424	13.98 424

EMVS		23.76 393	23.20 397	25.46 409	41.52 429	16.90 434	60.56 410	38.79 430	14.62 424	8.99 428	20.24 427	7.35 420	45.82 427	7.25 428	9.46 425	13.64 425

wuyk23d		11.30 396	10.95 399	12.33 411	48.05 421	19.89 431	25.89 423	1.92 435	3.58 427	3.12 429	1.37 429	0.64 434	15.77 430	6.23 429	7.77 428	1.35 426

testmvs		7.23 398	9.62 401	0.06 413	0.04 435	0.02 438	84.98 315	0.02 436	0.03 430	0.18 431	1.21 430	0.01 436	0.02 431	0.14 430	0.01 429	0.13 428

test123		6.92 399	9.21 402	0.08 412	0.03 436	0.05 437	81.65 343	0.01 437	0.02 431	0.14 432	0.85 431	0.03 435	0.02 431	0.12 431	0.00 430	0.16 427

mmdepth		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 430	0.00 429

monomultidepth		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 430	0.00 429

test_blank		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 430	0.00 429

uanet_test		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 430	0.00 429

DCPMVS		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 430	0.00 429

cdsmvs_eth3d_5k		19.86 395	26.47 394	0.00 414	0.00 437	0.00 439	0.00 425	93.45 88	0.00 432	0.00 433	95.27 63	49.56 269	0.00 433	0.00 432	0.00 430	0.00 429

pcd_1.5k_mvsjas		4.46 400	5.95 403	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	53.55 230	0.00 433	0.00 432	0.00 430	0.00 429

sosnet-low-res		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 430	0.00 429

sosnet		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 430	0.00 429

uncertanet		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 430	0.00 429

Regformer		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 430	0.00 429

ab-mvs-re		7.91 397	10.55 400	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	94.95 73	0.00 437	0.00 433	0.00 432	0.00 430	0.00 429

uanet		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 430	0.00 429

FOURS1					93.95 46	61.77 255	93.96 73	91.92 154	62.14 332	86.57 50

test_one_0601					96.32 18	69.74 50		94.18 60	71.42 236	90.67 20	96.85 18	74.45 20

eth-test2					0.00 437

eth-test					0.00 437

test_241102_ONE					96.45 12	69.38 56		94.44 49	71.65 225	92.11 7	97.05 8	76.79 9	99.11 6

save fliter					93.84 49	67.89 96	95.05 39	92.66 122	78.19 100

test0726					96.40 15	69.99 39	96.76 8	94.33 57	71.92 211	91.89 11	97.11 7	73.77 23

GSMVS																94.68 102

test_part2					96.29 19	68.16 89				90.78 18

sam_mvs1												57.85 175				94.68 102

sam_mvs												54.91 214

MTGPA								92.23 136

test_post											23.01 423	56.49 196	92.67 280

patchmatchnet-post											67.62 392	57.62 178	90.25 326

MTMP							93.77 87	32.52 432

TEST9					94.18 41	67.28 111	94.16 61	93.51 84	71.75 222	85.52 61	95.33 58	68.01 55	97.27 83

test_8					94.19 40	67.19 113	94.15 63	93.42 91	71.87 216	85.38 64	95.35 57	68.19 53	96.95 109

agg_prior					94.16 43	66.97 122		93.31 94		84.49 72			96.75 119

test_prior4						67.18 115	93.92 76

test_prior				86.42 77	94.71 35	67.35 110		93.10 105					96.84 116			95.05 84

新几何2							91.41 189

旧先验1					91.94 108	60.74 278		91.50 178			94.36 91	65.23 82			91.84 71	94.55 109

原ACMM2							92.01 165

test222					89.77 159	61.60 260	89.55 257	89.42 259	56.83 366	77.28 155	92.43 141	52.76 238			91.14 85	93.09 166

segment_acmp												65.94 73

testdata1							89.21 266		77.55 114

test12				87.09 52	94.60 36	68.86 68		92.91 112		82.67 93		65.44 79	97.55 64		93.69 48	94.84 94

plane_prior7					86.94 237	61.51 261

plane_prior6					87.23 229	62.32 245						50.66 258

plane_prior4											89.14 203

plane_prior3						61.95 253			79.09 86	72.53 205

plane_prior2							93.13 114		78.81 93

plane_prior1					87.15 231

plane_prior						62.42 241	93.85 80		79.38 78						78.80 210

n2								0.00 438

nn								0.00 438

door-mid								66.01 407

test11								93.01 108

door								66.57 406

HQP5-MVS						63.66 209

HQP-NCC					87.54 221		94.06 66		79.80 69	74.18 184

ACMP_Plane					87.54 221		94.06 66		79.80 69	74.18 184

HQP4-MVS										74.18 184			95.61 170			88.63 248

HQP3-MVS								91.70 170							78.90 208

HQP2-MVS												51.63 250

NP-MVS					87.41 224	63.04 225					90.30 184

ACMMP++_ref															71.63 263

ACMMP++															69.72 272

Test By Simon												54.21 224

High-resolution multi-view benchmark