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.

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 63	96.26 38	72.84 30	99.38 1	92.64 29	95.93 9	97.08 11

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 17	96.19 40	70.12 47	98.91 18	96.83 1	95.06 17	96.76 15

DELS-MVS		90.05 8	90.09 11	89.94 4	93.14 71	73.88 9	97.01 4	94.40 55	88.32 3	85.71 64	94.91 83	74.11 21	98.91 18	87.26 71	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
MVS_0304		90.32 6	90.90 7	88.55 23	94.05 45	70.23 37	97.00 5	93.73 78	87.30 4	92.15 7	96.15 42	66.38 69	98.94 17	96.71 2	94.67 33	96.47 28

EPNet		87.84 25	88.38 22	86.23 83	93.30 65	66.05 143	95.26 32	94.84 32	87.09 5	88.06 40	94.53 92	66.79 65	97.34 79	83.89 105	91.68 75	95.29 72
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CANet		89.61 12	89.99 12	88.46 24	94.39 39	69.71 51	96.53 13	93.78 71	86.89 6	89.68 33	95.78 49	65.94 74	99.10 9	92.99 26	93.91 42	96.58 21

patch_mono-2		89.71 11	90.99 6	85.85 96	96.04 24	63.70 213	95.04 41	95.19 22	86.74 7	91.53 18	95.15 76	73.86 22	97.58 64	93.38 23	92.00 69	96.28 37

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 140	93.00 76	58.16 335	96.72 9	94.41 53	86.50 8	90.25 27	97.83 1	75.46 14	98.67 25	92.78 28	95.49 13	97.32 6

fmvsm_s_conf0.5_n_8		87.96 21	88.93 17	85.07 125	88.43 198	61.78 265	94.73 53	91.74 172	85.87 9	91.66 15	97.50 2	64.03 100	98.33 34	96.28 3	90.08 99	95.10 83

CANet_DTU		84.09 105	83.52 99	85.81 97	90.30 152	66.82 125	91.87 184	89.01 296	85.27 10	86.09 60	93.74 119	47.71 299	96.98 107	77.90 163	89.78 105	93.65 156

CLD-MVS		82.73 132	82.35 132	83.86 174	87.90 216	67.65 102	95.45 28	92.18 149	85.06 11	72.58 216	92.27 152	52.46 250	95.78 165	84.18 101	79.06 219	88.16 271
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
fmvsm_l_conf0.5_n_3		87.54 28	88.29 24	85.30 116	86.92 246	62.63 246	95.02 43	90.28 241	84.95 12	90.27 26	96.86 17	65.36 81	97.52 69	94.93 11	90.03 100	95.76 50

CNVR-MVS		90.32 6	90.89 8	88.61 22	96.76 8	70.65 30	96.47 14	94.83 33	84.83 13	89.07 36	96.80 22	70.86 43	99.06 15	92.64 29	95.71 11	96.12 40

fmvsm_s_conf0.5_n_6		87.50 30	88.72 19	83.84 175	86.89 248	60.04 311	95.05 39	92.17 151	84.80 14	92.27 6	96.37 31	64.62 92	96.54 132	94.43 15	91.86 71	94.94 92

SymmetryMVS		86.32 54	86.39 53	86.12 87	90.52 147	65.95 148	94.88 46	94.58 46	84.69 15	83.67 87	94.10 111	63.16 120	96.91 119	85.31 87	86.59 143	95.51 59

NCCC		89.07 16	89.46 15	87.91 28	96.60 10	69.05 64	96.38 15	94.64 42	84.42 16	86.74 53	96.20 39	66.56 68	98.76 24	89.03 56	94.56 34	95.92 46

fmvsm_s_conf0.5_n_3		86.88 39	87.99 29	83.58 186	87.26 233	60.74 291	93.21 121	87.94 332	84.22 17	91.70 14	97.27 3	65.91 76	95.02 200	93.95 20	90.42 95	94.99 89

test_fmvsm_n_1920		87.69 27	88.50 21	85.27 119	87.05 240	63.55 220	93.69 97	91.08 208	84.18 18	90.17 29	97.04 10	67.58 60	97.99 41	95.72 6	90.03 100	94.26 126

balanced_conf03		89.08 15	88.84 18	89.81 6	93.66 54	75.15 5	90.61 243	93.43 93	84.06 19	86.20 58	90.17 197	72.42 35	96.98 107	93.09 25	95.92 10	97.29 7

PS-MVSNAJ		88.14 18	87.61 34	89.71 7	92.06 103	76.72 1	95.75 20	93.26 99	83.86 20	89.55 34	96.06 44	53.55 238	97.89 46	91.10 41	93.31 53	94.54 114

DeepC-MVS_fast	79.48 2	87.95 23	88.00 28	87.79 31	95.86 27	68.32 81	95.74 21	94.11 65	83.82 21	83.49 88	96.19 40	64.53 95	98.44 31	83.42 112	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
test_fmvsmconf_n		86.58 49	87.17 39	84.82 133	85.28 278	62.55 247	94.26 65	89.78 260	83.81 22	87.78 44	96.33 35	65.33 82	96.98 107	94.40 16	87.55 128	94.95 91

fmvsm_s_conf0.5_n_4		86.79 46	87.63 32	84.27 163	86.15 263	61.48 275	94.69 54	91.16 200	83.79 23	90.51 25	96.28 36	64.24 97	98.22 35	95.00 10	86.88 134	93.11 172

xiu_mvs_v2_base		87.92 24	87.38 38	89.55 12	91.41 130	76.43 3	95.74 21	93.12 107	83.53 24	89.55 34	95.95 47	53.45 242	97.68 54	91.07 42	92.62 60	94.54 114

test_fmvsmconf0.1_n		85.71 69	86.08 62	84.62 149	80.83 337	62.33 252	93.84 90	88.81 304	83.50 25	87.00 51	96.01 46	63.36 115	96.93 115	94.04 19	87.29 131	94.61 110

fmvsm_s_conf0.5_n_7		85.24 78	86.69 49	80.91 267	84.52 295	60.10 309	93.35 116	90.35 234	83.41 26	86.54 55	96.27 37	60.50 150	90.02 351	94.84 12	90.38 96	92.61 187

fmvsm_s_conf0.5_n_2		85.06 82	85.60 71	83.44 193	86.92 246	60.53 298	94.41 58	87.31 338	83.30 27	88.72 38	96.72 24	54.28 231	97.75 52	94.07 18	84.68 162	92.04 209

reproduce_monomvs		79.49 194	79.11 188	80.64 270	92.91 78	61.47 276	91.17 221	93.28 98	83.09 28	64.04 323	82.38 304	66.19 70	94.57 221	81.19 133	57.71 378	85.88 317

fmvsm_s_conf0.1_n_2		84.40 94	84.78 87	83.27 199	85.25 279	60.41 301	94.13 70	85.69 358	83.05 29	87.99 41	96.37 31	52.75 247	97.68 54	93.75 22	84.05 171	91.71 214

TSAR-MVS + MP.		88.11 20	88.64 20	86.54 73	91.73 118	68.04 91	90.36 249	93.55 85	82.89 30	91.29 19	92.89 137	72.27 37	96.03 159	87.99 61	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
fmvsm_s_conf0.5_n_5		86.38 53	86.94 43	84.71 142	84.67 290	63.29 226	94.04 76	89.99 255	82.88 31	87.85 43	96.03 45	62.89 126	96.36 141	94.15 17	89.95 102	94.48 120

DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 164	76.68 2	97.29 1	95.35 17	82.87 32	91.58 16	97.22 5	79.93 5	99.10 9	83.12 113	97.64 2	97.94 1

WTY-MVS		86.32 54	85.81 66	87.85 29	92.82 82	69.37 58	95.20 34	95.25 20	82.71 33	81.91 103	94.73 87	67.93 58	97.63 61	79.55 146	82.25 186	96.54 22

lupinMVS		87.74 26	87.77 31	87.63 38	89.24 179	71.18 24	96.57 12	92.90 116	82.70 34	87.13 48	95.27 69	64.99 85	95.80 164	89.34 51	91.80 73	95.93 45

fmvsm_s_conf0.5_n		86.39 52	86.91 44	84.82 133	87.36 232	63.54 221	94.74 50	90.02 253	82.52 35	90.14 30	96.92 15	62.93 124	97.84 49	95.28 9	82.26 185	93.07 175

myMVS_eth3d28		86.31 56	86.15 59	86.78 63	93.56 58	70.49 33	92.94 131	95.28 19	82.47 36	78.70 148	92.07 158	72.45 34	95.41 187	82.11 122	85.78 151	94.44 122

HPM-MVS++		89.37 14	89.95 13	87.64 34	95.10 30	68.23 87	95.24 33	94.49 49	82.43 37	88.90 37	96.35 33	71.89 40	98.63 26	88.76 57	96.40 6	96.06 41

test_fmvsmconf0.01_n		83.70 115	83.52 99	84.25 164	75.26 396	61.72 269	92.17 166	87.24 340	82.36 38	84.91 74	95.41 60	55.60 213	96.83 121	92.85 27	85.87 150	94.21 129

PVSNet_Blended		86.73 47	86.86 46	86.31 82	93.76 50	67.53 106	96.33 16	93.61 82	82.34 39	81.00 115	93.08 131	63.19 118	97.29 82	87.08 74	91.38 81	94.13 135

MSP-MVS		90.38 5	91.87 1	85.88 93	92.83 80	64.03 201	93.06 124	94.33 59	82.19 40	93.65 3	96.15 42	85.89 1	97.19 90	91.02 43	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
PAPM		85.89 66	85.46 73	87.18 49	88.20 209	72.42 15	92.41 159	92.77 120	82.11 41	80.34 124	93.07 132	68.27 53	95.02 200	78.39 160	93.59 49	94.09 137

jason		86.40 51	86.17 58	87.11 51	86.16 262	70.54 32	95.71 24	92.19 148	82.00 42	84.58 77	94.34 102	61.86 136	95.53 185	87.76 63	90.89 88	95.27 75
jason: jason.
baseline1		81.84 148	81.03 149	84.28 162	91.60 121	66.62 131	91.08 223	91.66 180	81.87 43	74.86 189	91.67 168	69.98 48	94.92 207	71.76 212	64.75 330	91.29 226

CHOSEN 1792x2688		84.98 85	83.45 104	89.57 11	89.94 159	75.14 6	92.07 173	92.32 139	81.87 43	75.68 177	88.27 224	60.18 153	98.60 27	80.46 139	90.27 98	94.96 90

fmvsm_s_conf0.1_n		85.61 72	85.93 64	84.68 144	82.95 320	63.48 223	94.03 78	89.46 272	81.69 45	89.86 31	96.74 23	61.85 137	97.75 52	94.74 13	82.01 191	92.81 183

test_vis1_n_1920		81.66 151	82.01 135	80.64 270	82.24 325	55.09 364	94.76 49	86.87 342	81.67 46	84.40 79	94.63 90	38.17 350	94.67 218	91.98 36	83.34 176	92.16 207

UBG		86.83 43	86.70 48	87.20 48	93.07 74	69.81 47	93.43 113	95.56 13	81.52 47	81.50 106	92.12 156	73.58 26	96.28 144	84.37 100	85.20 155	95.51 59

casdiffmvs_mvg		85.66 71	85.18 78	87.09 52	88.22 208	69.35 59	93.74 96	91.89 164	81.47 48	80.10 126	91.45 171	64.80 90	96.35 142	87.23 72	87.69 126	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
h-mvs33		83.01 128	82.56 128	84.35 159	89.34 171	62.02 259	92.72 141	93.76 74	81.45 49	82.73 98	92.25 154	60.11 154	97.13 96	87.69 64	62.96 343	93.91 147

hse-mvs2		81.12 163	81.11 148	81.16 255	86.52 254	57.48 344	89.40 276	91.16 200	81.45 49	82.73 98	90.49 187	60.11 154	94.58 219	87.69 64	60.41 370	91.41 220

ET-MVSNet_ETH3D		84.01 106	83.15 116	86.58 71	90.78 144	70.89 28	94.74 50	94.62 43	81.44 51	58.19 362	93.64 122	73.64 25	92.35 307	82.66 118	78.66 224	96.50 27

fmvsm_s_conf0.5_n_a		85.75 68	86.09 61	84.72 140	85.73 272	63.58 218	93.79 93	89.32 278	81.42 52	90.21 28	96.91 16	62.41 131	97.67 56	94.48 14	80.56 206	92.90 181

test_fmvsmvis_n_1920		83.80 111	83.48 102	84.77 137	82.51 323	63.72 211	91.37 207	83.99 375	81.42 52	77.68 156	95.74 51	58.37 178	97.58 64	93.38 23	86.87 135	93.00 178

testing11		86.71 48	86.44 52	87.55 40	93.54 60	71.35 21	93.65 99	95.58 11	81.36 54	80.69 118	92.21 155	72.30 36	96.46 137	85.18 90	83.43 175	94.82 100

casdiffmvs		85.37 76	84.87 84	86.84 59	88.25 206	69.07 63	93.04 126	91.76 171	81.27 55	80.84 117	92.07 158	64.23 98	96.06 157	84.98 93	87.43 130	95.39 63
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ETV-MVS		86.01 62	86.11 60	85.70 103	90.21 154	67.02 121	93.43 113	91.92 161	81.21 56	84.13 83	94.07 114	60.93 146	95.63 175	89.28 52	89.81 103	94.46 121

DeepC-MVS	77.85 3	85.52 75	85.24 77	86.37 79	88.80 189	66.64 130	92.15 167	93.68 80	81.07 57	76.91 168	93.64 122	62.59 128	98.44 31	85.50 85	92.84 59	94.03 141
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline		85.01 84	84.44 90	86.71 65	88.33 203	68.73 72	90.24 254	91.82 170	81.05 58	81.18 111	92.50 144	63.69 107	96.08 156	84.45 99	86.71 141	95.32 70

PC_three_1452									80.91 59	94.07 2	96.83 21	83.57 4	99.12 5	95.70 8	97.42 4	97.55 4

IU-MVS					96.46 11	69.91 43		95.18 23	80.75 60	95.28 1				92.34 31	95.36 14	96.47 28

diffmvs		84.28 98	83.83 95	85.61 105	87.40 230	68.02 92	90.88 229	89.24 281	80.54 61	81.64 105	92.52 143	59.83 158	94.52 227	87.32 70	85.11 156	94.29 125
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_l_conf0.5_n		87.49 31	88.19 26	85.39 111	86.95 241	64.37 189	94.30 63	88.45 316	80.51 62	92.70 4	96.86 17	69.98 48	97.15 95	95.83 5	88.08 122	94.65 108

fmvsm_s_conf0.1_n_a		84.76 89	84.84 85	84.53 151	80.23 350	63.50 222	92.79 138	88.73 307	80.46 63	89.84 32	96.65 26	60.96 145	97.57 66	93.80 21	80.14 208	92.53 192

VPNet		78.82 207	77.53 210	82.70 213	84.52 295	66.44 135	93.93 82	92.23 142	80.46 63	72.60 215	88.38 222	49.18 284	93.13 274	72.47 205	63.97 340	88.55 265

testing99		86.01 62	85.47 72	87.63 38	93.62 55	71.25 23	93.47 111	95.23 21	80.42 65	80.60 120	91.95 161	71.73 41	96.50 135	80.02 143	82.22 187	95.13 81

testing222		85.18 80	84.69 88	86.63 68	92.91 78	69.91 43	92.61 149	95.80 9	80.31 66	80.38 123	92.27 152	68.73 51	95.19 197	75.94 173	83.27 177	94.81 101

testing91		85.93 64	85.31 76	87.78 32	93.59 57	71.47 19	93.50 108	95.08 28	80.26 67	80.53 121	91.93 162	70.43 45	96.51 134	80.32 141	82.13 189	95.37 65

sasdasda		86.85 41	86.25 56	88.66 20	91.80 116	71.92 16	93.54 105	91.71 175	80.26 67	87.55 45	95.25 71	63.59 111	96.93 115	88.18 59	84.34 163	97.11 9

canonicalmvs		86.85 41	86.25 56	88.66 20	91.80 116	71.92 16	93.54 105	91.71 175	80.26 67	87.55 45	95.25 71	63.59 111	96.93 115	88.18 59	84.34 163	97.11 9

fmvsm_l_conf0.5_n_a		87.44 33	88.15 27	85.30 116	87.10 238	64.19 196	94.41 58	88.14 325	80.24 70	92.54 5	96.97 12	69.52 50	97.17 91	95.89 4	88.51 117	94.56 111

SPE-MVS-test		86.14 60	87.01 41	83.52 187	92.63 88	59.36 323	95.49 27	91.92 161	80.09 71	85.46 69	95.53 58	61.82 138	95.77 167	86.77 78	93.37 52	95.41 62

CS-MVS		85.80 67	86.65 51	83.27 199	92.00 108	58.92 327	95.31 31	91.86 166	79.97 72	84.82 75	95.40 61	62.26 132	95.51 186	86.11 82	92.08 68	95.37 65

BP-MVS1		86.54 50	86.68 50	86.13 86	87.80 221	67.18 115	92.97 129	95.62 10	79.92 73	82.84 95	94.14 110	74.95 15	96.46 137	82.91 116	88.96 113	94.74 102

MVSTER		82.47 137	82.05 133	83.74 177	92.68 87	69.01 65	91.90 183	93.21 100	79.83 74	72.14 226	85.71 268	74.72 17	94.72 214	75.72 175	72.49 272	87.50 278

HQP-NCC					87.54 226		94.06 72		79.80 75	74.18 196

ACMP_Plane					87.54 226		94.06 72		79.80 75	74.18 196

HQP-MVS		81.14 161	80.64 157	82.64 215	87.54 226	63.66 216	94.06 72	91.70 178	79.80 75	74.18 196	90.30 192	51.63 258	95.61 177	77.63 164	78.90 220	88.63 262

baseline2		83.68 116	83.42 107	84.48 154	87.37 231	66.00 145	90.06 258	95.93 8	79.71 78	69.08 263	90.39 189	77.92 6	96.28 144	78.91 155	81.38 197	91.16 228

MGCFI-Net		85.59 73	85.73 69	85.17 123	91.41 130	62.44 248	92.87 136	91.31 192	79.65 79	86.99 52	95.14 77	62.90 125	96.12 151	87.13 73	84.13 170	96.96 13

EI-MVSNet-Vis-set		83.77 112	83.67 97	84.06 167	92.79 85	63.56 219	91.76 191	94.81 34	79.65 79	77.87 154	94.09 112	63.35 116	97.90 45	79.35 148	79.36 215	90.74 234

ETVMVS		84.22 102	83.71 96	85.76 100	92.58 90	68.25 86	92.45 158	95.53 15	79.54 81	79.46 134	91.64 169	70.29 46	94.18 239	69.16 236	82.76 183	94.84 97

EIA-MVS		84.84 87	84.88 83	84.69 143	91.30 132	62.36 251	93.85 87	92.04 154	79.45 82	79.33 137	94.28 106	62.42 130	96.35 142	80.05 142	91.25 84	95.38 64

dmvs_re		76.93 242	75.36 244	81.61 245	87.78 222	60.71 293	80.00 379	87.99 329	79.42 83	69.02 265	89.47 208	46.77 303	94.32 231	63.38 292	74.45 256	89.81 246

AstraMVS		80.66 171	79.79 173	83.28 198	85.07 285	61.64 271	92.19 165	90.58 225	79.40 84	74.77 191	90.18 195	45.93 314	95.61 177	83.04 115	76.96 241	92.60 188

plane_prior						62.42 249	93.85 87		79.38 85						78.80 222

dcpmvs_2		87.37 34	87.55 35	86.85 58	95.04 32	68.20 88	90.36 249	90.66 222	79.37 86	81.20 110	93.67 121	74.73 16	96.55 131	90.88 44	92.00 69	95.82 48

alignmvs		87.28 35	86.97 42	88.24 27	91.30 132	71.14 26	95.61 25	93.56 84	79.30 87	87.07 50	95.25 71	68.43 52	96.93 115	87.87 62	84.33 165	96.65 17

TESTMET0.1,1		82.41 138	81.98 136	83.72 181	88.08 210	63.74 208	92.70 143	93.77 73	79.30 87	77.61 158	87.57 240	58.19 181	94.08 244	73.91 191	86.68 142	93.33 165

EI-MVSNet-UG-set		83.14 125	82.96 118	83.67 184	92.28 94	63.19 231	91.38 206	94.68 40	79.22 89	76.60 170	93.75 118	62.64 127	97.76 51	78.07 162	78.01 227	90.05 243

PVSNet	73.49 8	80.05 184	78.63 192	84.31 160	90.92 140	64.97 173	92.47 157	91.05 211	79.18 90	72.43 223	90.51 186	37.05 365	94.06 246	68.06 247	86.00 148	93.90 149

HY-MVS	76.49 5	84.28 98	83.36 110	87.02 55	92.22 96	67.74 99	84.65 332	94.50 48	79.15 91	82.23 101	87.93 233	66.88 64	96.94 113	80.53 138	82.20 188	96.39 33

PVSNet_BlendedMVS		83.38 120	83.43 105	83.22 201	93.76 50	67.53 106	94.06 72	93.61 82	79.13 92	81.00 115	85.14 273	63.19 118	97.29 82	87.08 74	73.91 262	84.83 334

plane_prior3						61.95 262			79.09 93	72.53 217

MonoMVSNet		76.99 241	75.08 248	82.73 211	83.32 314	63.24 228	86.47 324	86.37 346	79.08 94	66.31 304	79.30 352	49.80 277	91.72 322	79.37 147	65.70 318	93.23 167

MVS_111021_HR		86.19 59	85.80 67	87.37 44	93.17 70	69.79 48	93.99 79	93.76 74	79.08 94	78.88 144	93.99 115	62.25 133	98.15 38	85.93 84	91.15 85	94.15 134

test_cas_vis1_n_1920		80.45 176	80.61 158	79.97 289	78.25 377	57.01 351	94.04 76	88.33 319	79.06 96	82.81 97	93.70 120	38.65 345	91.63 325	90.82 45	79.81 210	91.27 227

MSLP-MVS++		86.27 57	85.91 65	87.35 45	92.01 107	68.97 67	95.04 41	92.70 122	79.04 97	81.50 106	96.50 29	58.98 173	96.78 122	83.49 111	93.93 41	96.29 35

IB-MVS	77.80 4	82.18 141	80.46 163	87.35 45	89.14 181	70.28 36	95.59 26	95.17 24	78.85 98	70.19 251	85.82 266	70.66 44	97.67 56	72.19 209	66.52 313	94.09 137
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
3Dnovator	73.91 6	82.69 135	80.82 152	88.31 26	89.57 166	71.26 22	92.60 150	94.39 56	78.84 99	67.89 284	92.48 147	48.42 290	98.52 28	68.80 241	94.40 36	95.15 80

HQP_MVS		80.34 178	79.75 174	82.12 234	86.94 242	62.42 249	93.13 122	91.31 192	78.81 100	72.53 217	89.14 214	50.66 266	95.55 183	76.74 167	78.53 225	88.39 268

plane_prior2							93.13 122		78.81 100

MG-MVS		87.11 37	86.27 54	89.62 8	97.79 1	76.27 4	94.96 45	94.49 49	78.74 102	83.87 85	92.94 135	64.34 96	96.94 113	75.19 179	94.09 38	95.66 53

guyue		81.23 159	80.57 160	83.21 203	86.64 249	61.85 263	92.52 156	92.78 119	78.69 103	74.92 188	89.42 209	50.07 272	95.35 191	80.79 136	79.31 217	92.42 194

gm-plane-assit					88.42 199	67.04 120			78.62 104		91.83 164		97.37 76	76.57 169

SSC-MVS3.2		74.92 278	73.32 276	79.74 296	86.53 253	60.31 304	89.03 287	92.70 122	78.61 105	68.98 267	83.34 294	41.93 333	92.23 311	52.77 344	65.97 316	86.69 294

mvsmamba		81.55 153	80.72 154	84.03 171	91.42 127	66.93 123	83.08 349	89.13 289	78.55 106	67.50 289	87.02 250	51.79 255	90.07 350	87.48 67	90.49 94	95.10 83

VNet		86.20 58	85.65 70	87.84 30	93.92 47	69.99 39	95.73 23	95.94 7	78.43 107	86.00 61	93.07 132	58.22 180	97.00 103	85.22 88	84.33 165	96.52 23

testing3-2		83.11 126	83.15 116	82.98 206	91.92 111	64.01 202	94.39 61	95.37 16	78.32 108	75.53 182	90.06 203	73.18 27	93.18 273	74.34 189	75.27 251	91.77 213

tpm		78.58 214	77.03 219	83.22 201	85.94 268	64.56 178	83.21 348	91.14 204	78.31 109	73.67 203	79.68 348	64.01 101	92.09 315	66.07 271	71.26 282	93.03 176

save fliter					93.84 49	67.89 96	95.05 39	92.66 127	78.19 110

TSAR-MVS + GP.		87.96 21	88.37 23	86.70 66	93.51 62	65.32 163	95.15 36	93.84 70	78.17 111	85.93 62	94.80 86	75.80 13	98.21 36	89.38 50	88.78 114	96.59 19

FIs		79.47 195	79.41 181	79.67 297	85.95 266	59.40 320	91.68 195	93.94 68	78.06 112	68.96 268	88.28 223	66.61 67	91.77 321	66.20 270	74.99 252	87.82 274

sss		82.71 134	82.38 131	83.73 179	89.25 176	59.58 318	92.24 163	94.89 31	77.96 113	79.86 129	92.38 149	56.70 199	97.05 98	77.26 166	80.86 201	94.55 112

PMMVS		81.98 147	82.04 134	81.78 241	89.76 163	56.17 355	91.13 222	90.69 219	77.96 113	80.09 127	93.57 124	46.33 310	94.99 203	81.41 129	87.46 129	94.17 132

EC-MVSNet		84.53 93	85.04 81	83.01 205	89.34 171	61.37 278	94.42 57	91.09 206	77.91 115	83.24 89	94.20 108	58.37 178	95.40 188	85.35 86	91.41 80	92.27 203

test1111		80.84 168	80.02 167	83.33 194	87.87 217	60.76 289	92.62 148	86.86 343	77.86 116	75.73 176	91.39 174	46.35 308	94.70 217	72.79 199	88.68 116	94.52 116

VortexMVS		77.62 230	76.44 228	81.13 256	88.58 192	63.73 210	91.24 215	91.30 196	77.81 117	65.76 306	81.97 310	49.69 278	93.72 262	76.40 171	65.26 323	85.94 315

GDP-MVS		85.54 74	85.32 75	86.18 84	87.64 224	67.95 95	92.91 134	92.36 138	77.81 117	83.69 86	94.31 104	72.84 30	96.41 139	80.39 140	85.95 149	94.19 130

MVS_Test		84.16 104	83.20 113	87.05 54	91.56 123	69.82 46	89.99 263	92.05 153	77.77 119	82.84 95	86.57 255	63.93 103	96.09 153	74.91 184	89.18 109	95.25 78

SteuartSystems-ACMMP		86.82 45	86.90 45	86.58 71	90.42 149	66.38 136	96.09 17	93.87 69	77.73 120	84.01 84	95.66 52	63.39 114	97.94 42	87.40 69	93.55 50	95.42 61
Skip Steuart: Steuart Systems R&D Blog.
EPNet_dtu		78.80 208	79.26 185	77.43 325	88.06 211	49.71 391	91.96 181	91.95 160	77.67 121	76.56 171	91.28 176	58.51 176	90.20 347	56.37 329	80.95 200	92.39 195
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test2506		83.29 121	82.92 121	84.37 158	88.39 201	63.18 232	92.01 176	91.35 191	77.66 122	78.49 150	91.42 172	64.58 94	95.09 199	73.19 193	89.23 107	94.85 94

ECVR-MVS		81.29 158	80.38 164	84.01 172	88.39 201	61.96 261	92.56 155	86.79 344	77.66 122	76.63 169	91.42 172	46.34 309	95.24 196	74.36 188	89.23 107	94.85 94

tpmrst		80.57 172	79.14 187	84.84 132	90.10 156	68.28 83	81.70 361	89.72 267	77.63 124	75.96 174	79.54 350	64.94 87	92.71 291	75.43 177	77.28 238	93.55 158

testdata1							89.21 281		77.55 125

UniMVSNet_NR-MVSNet		78.15 221	77.55 209	79.98 287	84.46 298	60.26 305	92.25 162	93.20 102	77.50 126	68.88 269	86.61 254	66.10 72	92.13 313	66.38 267	62.55 347	87.54 277

UA-Net		80.02 185	79.65 175	81.11 258	89.33 173	57.72 339	86.33 325	89.00 299	77.44 127	81.01 114	89.15 213	59.33 166	95.90 162	61.01 308	84.28 167	89.73 249

PVSNet_Blended_VisFu		83.97 107	83.50 101	85.39 111	90.02 157	66.59 133	93.77 94	91.73 173	77.43 128	77.08 167	89.81 205	63.77 106	96.97 110	79.67 145	88.21 120	92.60 188

dmvs_testset		65.55 354	66.45 330	62.86 401	79.87 353	22.35 447	76.55 393	71.74 414	77.42 129	55.85 374	87.77 236	51.39 260	80.69 414	31.51 426	65.92 317	85.55 324

NR-MVSNet		76.05 259	74.59 253	80.44 273	82.96 318	62.18 257	90.83 231	91.73 173	77.12 130	60.96 345	86.35 257	59.28 167	91.80 320	60.74 309	61.34 362	87.35 283

RRT-MVS		82.61 136	81.16 143	86.96 57	91.10 136	68.75 71	87.70 309	92.20 146	76.97 131	72.68 212	87.10 249	51.30 262	96.41 139	83.56 110	87.84 124	95.74 51

FC-MVSNet-test		77.99 224	78.08 200	77.70 320	84.89 288	55.51 361	90.27 252	93.75 77	76.87 132	66.80 301	87.59 239	65.71 78	90.23 346	62.89 298	73.94 261	87.37 282

SD-MVS		87.49 31	87.49 36	87.50 42	93.60 56	68.82 70	93.90 84	92.63 131	76.86 133	87.90 42	95.76 50	66.17 71	97.63 61	89.06 55	91.48 79	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
WBMVS		81.67 150	80.98 151	83.72 181	93.07 74	69.40 54	94.33 62	93.05 109	76.84 134	72.05 228	84.14 284	74.49 19	93.88 258	72.76 200	68.09 301	87.88 273

UGNet		79.87 188	78.68 191	83.45 192	89.96 158	61.51 273	92.13 168	90.79 217	76.83 135	78.85 146	86.33 259	38.16 351	96.17 149	67.93 250	87.17 132	92.67 185
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
MVS_111021_LR		82.02 146	81.52 140	83.51 189	88.42 199	62.88 241	89.77 266	88.93 300	76.78 136	75.55 181	93.10 129	50.31 269	95.38 190	83.82 106	87.02 133	92.26 204

SDMVSNet		80.26 179	78.88 190	84.40 156	89.25 176	67.63 103	85.35 328	93.02 110	76.77 137	70.84 242	87.12 247	47.95 296	96.09 153	85.04 91	74.55 253	89.48 253

sd_testset		77.08 240	75.37 243	82.20 230	89.25 176	62.11 258	82.06 358	89.09 292	76.77 137	70.84 242	87.12 247	41.43 335	95.01 202	67.23 257	74.55 253	89.48 253

TranMVSNet+NR-MVSNet		75.86 264	74.52 256	79.89 291	82.44 324	60.64 296	91.37 207	91.37 190	76.63 139	67.65 287	86.21 260	52.37 251	91.55 327	61.84 304	60.81 365	87.48 279

PAPR		85.15 81	84.47 89	87.18 49	96.02 25	68.29 82	91.85 186	93.00 113	76.59 140	79.03 140	95.00 78	61.59 139	97.61 63	78.16 161	89.00 112	95.63 54

UniMVSNet (Re)		77.58 232	76.78 223	79.98 287	84.11 304	60.80 286	91.76 191	93.17 104	76.56 141	69.93 257	84.78 277	63.32 117	92.36 306	64.89 283	62.51 349	86.78 293

DU-MVS		76.86 243	75.84 238	79.91 290	82.96 318	60.26 305	91.26 213	91.54 183	76.46 142	68.88 269	86.35 257	56.16 206	92.13 313	66.38 267	62.55 347	87.35 283

OPM-MVS		79.00 202	78.09 199	81.73 242	83.52 312	63.83 205	91.64 197	90.30 239	76.36 143	71.97 229	89.93 204	46.30 311	95.17 198	75.10 180	77.70 230	86.19 305
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
WR-MVS		76.76 248	75.74 240	79.82 293	84.60 292	62.27 255	92.60 150	92.51 135	76.06 144	67.87 285	85.34 271	56.76 197	90.24 345	62.20 302	63.69 342	86.94 291

GA-MVS		78.33 219	76.23 232	84.65 145	83.65 310	66.30 139	91.44 199	90.14 247	76.01 145	70.32 249	84.02 286	42.50 330	94.72 214	70.98 218	77.00 240	92.94 179

PVSNet_0	68.08 15	71.81 307	68.32 323	82.27 226	84.68 289	62.31 254	88.68 291	90.31 238	75.84 146	57.93 367	80.65 335	37.85 356	94.19 238	69.94 227	29.05 435	90.31 240

CDS-MVSNet		81.43 155	80.74 153	83.52 187	86.26 259	64.45 183	92.09 171	90.65 223	75.83 147	73.95 202	89.81 205	63.97 102	92.91 284	71.27 216	82.82 180	93.20 169
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
UWE-MVS		80.81 169	81.01 150	80.20 280	89.33 173	57.05 349	91.91 182	94.71 38	75.67 148	75.01 187	89.37 210	63.13 121	91.44 333	67.19 258	82.80 182	92.12 208

CostFormer		82.33 139	81.15 144	85.86 95	89.01 184	68.46 78	82.39 357	93.01 111	75.59 149	80.25 125	81.57 318	72.03 39	94.96 204	79.06 152	77.48 235	94.16 133

nrg030		80.93 166	79.86 171	84.13 166	83.69 309	68.83 69	93.23 119	91.20 198	75.55 150	75.06 186	88.22 228	63.04 123	94.74 213	81.88 124	66.88 310	88.82 260

VDD-MVS		83.06 127	81.81 138	86.81 61	90.86 142	67.70 100	95.40 29	91.50 186	75.46 151	81.78 104	92.34 151	40.09 340	97.13 96	86.85 77	82.04 190	95.60 55

Effi-MVS+-dtu		76.14 255	75.28 246	78.72 311	83.22 315	55.17 363	89.87 264	87.78 333	75.42 152	67.98 280	81.43 320	45.08 321	92.52 300	75.08 181	71.63 277	88.48 266

test_prior2							95.10 38		75.40 153	85.25 73	95.61 54	67.94 57		87.47 68	94.77 26

KinetiMVS		81.43 155	80.11 165	85.38 113	86.60 251	65.47 162	92.90 135	93.54 86	75.33 154	77.31 162	90.39 189	46.81 302	96.75 123	71.65 215	86.46 146	93.93 146

MTAPA		83.91 108	83.38 109	85.50 107	91.89 114	65.16 168	81.75 360	92.23 142	75.32 155	80.53 121	95.21 74	56.06 209	97.16 94	84.86 95	92.55 62	94.18 131

EPMVS		78.49 216	75.98 236	86.02 89	91.21 134	69.68 52	80.23 375	91.20 198	75.25 156	72.48 221	78.11 359	54.65 223	93.69 264	57.66 325	83.04 178	94.69 104

miper_enhance_ethall		78.86 206	77.97 202	81.54 247	88.00 214	65.17 167	91.41 200	89.15 287	75.19 157	68.79 271	83.98 287	67.17 62	92.82 286	72.73 201	65.30 320	86.62 299

v2v482		77.42 234	75.65 241	82.73 211	80.38 346	67.13 117	91.85 186	90.23 244	75.09 158	69.37 259	83.39 293	53.79 236	94.44 229	71.77 211	65.00 327	86.63 298

VPA-MVSNet		79.03 201	78.00 201	82.11 237	85.95 266	64.48 182	93.22 120	94.66 41	75.05 159	74.04 201	84.95 275	52.17 252	93.52 267	74.90 185	67.04 309	88.32 270

ACMMP_NAP		86.05 61	85.80 67	86.80 62	91.58 122	67.53 106	91.79 188	93.49 90	74.93 160	84.61 76	95.30 65	59.42 164	97.92 43	86.13 81	94.92 20	94.94 92

thres200		79.66 190	78.33 195	83.66 185	92.54 91	65.82 152	93.06 124	96.31 3	74.90 161	73.30 206	88.66 217	59.67 161	95.61 177	47.84 366	78.67 223	89.56 252

TAMVS		80.37 177	79.45 180	83.13 204	85.14 282	63.37 224	91.23 216	90.76 218	74.81 162	72.65 214	88.49 219	60.63 148	92.95 279	69.41 232	81.95 192	93.08 174

MP-MVS-pluss		85.24 78	85.13 79	85.56 106	91.42 127	65.59 156	91.54 198	92.51 135	74.56 163	80.62 119	95.64 53	59.15 168	97.00 103	86.94 76	93.80 43	94.07 139
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
UWE-MVS-28		76.83 246	77.60 208	74.51 353	84.58 294	50.34 387	88.22 298	94.60 45	74.46 164	66.66 302	88.98 216	62.53 129	85.50 388	57.55 326	80.80 204	87.69 276

mvs_anonymous		81.36 157	79.99 169	85.46 108	90.39 151	68.40 79	86.88 321	90.61 224	74.41 165	70.31 250	84.67 278	63.79 105	92.32 309	73.13 194	85.70 152	95.67 52

MAR-MVS		84.18 103	83.43 105	86.44 76	96.25 21	65.93 149	94.28 64	94.27 61	74.41 165	79.16 139	95.61 54	53.99 233	98.88 22	69.62 230	93.26 54	94.50 118
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
BH-w/o		80.49 175	79.30 184	84.05 170	90.83 143	64.36 191	93.60 102	89.42 275	74.35 167	69.09 262	90.15 199	55.23 217	95.61 177	64.61 284	86.43 147	92.17 206

thisisatest0515		83.41 119	82.49 129	86.16 85	89.46 170	68.26 84	93.54 105	94.70 39	74.31 168	75.75 175	90.92 179	72.62 32	96.52 133	69.64 228	81.50 196	93.71 154

Vis-MVSNet (Re-imp)		79.24 198	79.57 176	78.24 317	88.46 196	52.29 375	90.41 246	89.12 290	74.24 169	69.13 261	91.91 163	65.77 77	90.09 349	59.00 320	88.09 121	92.33 197

SMA-MVS		88.14 18	88.29 24	87.67 33	93.21 68	68.72 73	93.85 87	94.03 67	74.18 170	91.74 13	96.67 25	65.61 79	98.42 33	89.24 53	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
AUN-MVS		78.37 217	77.43 211	81.17 254	86.60 251	57.45 345	89.46 275	91.16 200	74.11 171	74.40 195	90.49 187	55.52 214	94.57 221	74.73 187	60.43 369	91.48 218

3Dnovator+	73.60 7	82.10 145	80.60 159	86.60 69	90.89 141	66.80 127	95.20 34	93.44 92	74.05 172	67.42 291	92.49 146	49.46 280	97.65 60	70.80 220	91.68 75	95.33 68

XVS		83.87 109	83.47 103	85.05 126	93.22 66	63.78 206	92.92 132	92.66 127	73.99 173	78.18 151	94.31 104	55.25 215	97.41 74	79.16 150	91.58 77	93.95 144

X-MVStestdata		76.86 243	74.13 265	85.05 126	93.22 66	63.78 206	92.92 132	92.66 127	73.99 173	78.18 151	10.19 447	55.25 215	97.41 74	79.16 150	91.58 77	93.95 144

MS-PatchMatch		77.90 228	76.50 227	82.12 234	85.99 265	69.95 42	91.75 193	92.70 122	73.97 175	62.58 339	84.44 282	41.11 337	95.78 165	63.76 290	92.17 66	80.62 382

LCM-MVSNet-Re		72.93 296	71.84 295	76.18 340	88.49 194	48.02 399	80.07 378	70.17 419	73.96 176	52.25 389	80.09 344	49.98 273	88.24 366	67.35 254	84.23 168	92.28 200

Vis-MVSNet		80.92 167	79.98 170	83.74 177	88.48 195	61.80 264	93.44 112	88.26 324	73.96 176	77.73 155	91.76 165	49.94 274	94.76 211	65.84 273	90.37 97	94.65 108
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test-mter		79.96 186	79.38 183	81.72 243	86.93 244	61.17 279	92.70 143	91.54 183	73.85 178	75.62 178	86.94 251	49.84 276	92.38 304	72.21 207	84.76 160	91.60 215

OMC-MVS		78.67 213	77.91 204	80.95 265	85.76 271	57.40 346	88.49 294	88.67 310	73.85 178	72.43 223	92.10 157	49.29 283	94.55 225	72.73 201	77.89 228	90.91 233

Fast-Effi-MVS+		81.14 161	80.01 168	84.51 153	90.24 153	65.86 150	94.12 71	89.15 287	73.81 180	75.37 184	88.26 225	57.26 188	94.53 226	66.97 261	84.92 157	93.15 170

ZNCC-MVS		85.33 77	85.08 80	86.06 88	93.09 73	65.65 154	93.89 85	93.41 95	73.75 181	79.94 128	94.68 89	60.61 149	98.03 40	82.63 119	93.72 46	94.52 116

V42		76.46 251	74.55 255	82.19 231	79.14 364	67.82 97	90.26 253	89.42 275	73.75 181	68.63 274	81.89 311	51.31 261	94.09 243	71.69 213	64.84 328	84.66 335

v1144		76.73 249	74.88 249	82.27 226	80.23 350	66.60 132	91.68 195	90.21 246	73.69 183	69.06 264	81.89 311	52.73 248	94.40 230	69.21 235	65.23 324	85.80 318

v148		76.19 254	74.47 257	81.36 250	80.05 352	64.44 184	91.75 193	90.23 244	73.68 184	67.13 295	80.84 331	55.92 211	93.86 261	68.95 239	61.73 358	85.76 321

CR-MVSNet		73.79 289	70.82 304	82.70 213	83.15 316	67.96 93	70.25 409	84.00 373	73.67 185	69.97 255	72.41 392	57.82 184	89.48 355	52.99 343	73.13 266	90.64 236

XXY-MVS		77.94 226	76.44 228	82.43 220	82.60 322	64.44 184	92.01 176	91.83 169	73.59 186	70.00 254	85.82 266	54.43 228	94.76 211	69.63 229	68.02 303	88.10 272

tfpn200view9		78.79 209	77.43 211	82.88 208	92.21 97	64.49 180	92.05 174	96.28 4	73.48 187	71.75 232	88.26 225	60.07 156	95.32 192	45.16 379	77.58 232	88.83 258

thres400		78.68 211	77.43 211	82.43 220	92.21 97	64.49 180	92.05 174	96.28 4	73.48 187	71.75 232	88.26 225	60.07 156	95.32 192	45.16 379	77.58 232	87.48 279

FMVSNet3		77.73 229	76.04 235	82.80 209	91.20 135	68.99 66	91.87 184	91.99 158	73.35 189	67.04 296	83.19 296	56.62 201	92.14 312	59.80 316	69.34 289	87.28 285

GST-MVS		84.63 92	84.29 92	85.66 104	92.82 82	65.27 164	93.04 126	93.13 106	73.20 190	78.89 141	94.18 109	59.41 165	97.85 48	81.45 128	92.48 63	93.86 150

USDC		67.43 345	64.51 347	76.19 339	77.94 381	55.29 362	78.38 386	85.00 363	73.17 191	48.36 406	80.37 338	21.23 417	92.48 302	52.15 345	64.02 339	80.81 380

MP-MVS		85.02 83	84.97 82	85.17 123	92.60 89	64.27 194	93.24 118	92.27 141	73.13 192	79.63 132	94.43 95	61.90 135	97.17 91	85.00 92	92.56 61	94.06 140
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
xiu_mvs_v1_base_debu		82.16 142	81.12 145	85.26 120	86.42 255	68.72 73	92.59 152	90.44 231	73.12 193	84.20 80	94.36 97	38.04 353	95.73 169	84.12 102	86.81 136	91.33 221

xiu_mvs_v1_base		82.16 142	81.12 145	85.26 120	86.42 255	68.72 73	92.59 152	90.44 231	73.12 193	84.20 80	94.36 97	38.04 353	95.73 169	84.12 102	86.81 136	91.33 221

xiu_mvs_v1_base_debi		82.16 142	81.12 145	85.26 120	86.42 255	68.72 73	92.59 152	90.44 231	73.12 193	84.20 80	94.36 97	38.04 353	95.73 169	84.12 102	86.81 136	91.33 221

D2MVS		73.80 288	72.02 293	79.15 308	79.15 363	62.97 235	88.58 293	90.07 249	72.94 196	59.22 355	78.30 356	42.31 332	92.70 293	65.59 277	72.00 275	81.79 371

BH-RMVSNet		79.46 196	77.65 206	84.89 130	91.68 120	65.66 153	93.55 104	88.09 327	72.93 197	73.37 205	91.12 178	46.20 312	96.12 151	56.28 330	85.61 154	92.91 180

Syy-MVS		69.65 323	69.52 315	70.03 383	87.87 217	43.21 419	88.07 300	89.01 296	72.91 198	63.11 332	88.10 229	45.28 319	85.54 385	22.07 433	69.23 292	81.32 374

myMVS_eth3d		72.58 305	72.74 283	72.10 375	87.87 217	49.45 393	88.07 300	89.01 296	72.91 198	63.11 332	88.10 229	63.63 108	85.54 385	32.73 420	69.23 292	81.32 374

IS-MVSNet		80.14 182	79.41 181	82.33 224	87.91 215	60.08 310	91.97 180	88.27 322	72.90 200	71.44 238	91.73 167	61.44 140	93.66 265	62.47 301	86.53 144	93.24 166

PS-MVSNAJss		77.26 236	76.31 231	80.13 282	80.64 342	59.16 325	90.63 242	91.06 210	72.80 201	68.58 275	84.57 280	53.55 238	93.96 254	72.97 195	71.96 276	87.27 286

9.14			87.63 32		93.86 48		94.41 58	94.18 62	72.76 202	86.21 57	96.51 28	66.64 66	97.88 47	90.08 48	94.04 39

v1192		75.98 261	73.92 268	82.15 232	79.73 354	66.24 141	91.22 217	89.75 262	72.67 203	68.49 276	81.42 321	49.86 275	94.27 235	67.08 259	65.02 326	85.95 313

Effi-MVS+		83.82 110	82.76 124	86.99 56	89.56 167	69.40 54	91.35 209	86.12 352	72.59 204	83.22 92	92.81 141	59.60 162	96.01 161	81.76 125	87.80 125	95.56 57

UnsupCasMVSNet_eth		65.79 352	63.10 355	73.88 359	70.71 411	50.29 389	81.09 367	89.88 258	72.58 205	49.25 403	74.77 385	32.57 383	87.43 377	55.96 331	41.04 416	83.90 342

1112_ss		80.56 173	79.83 172	82.77 210	88.65 191	60.78 287	92.29 161	88.36 318	72.58 205	72.46 222	94.95 79	65.09 84	93.42 270	66.38 267	77.71 229	94.10 136

DVP-MVS++		90.53 4	91.09 5	88.87 16	97.31 4	69.91 43	93.96 80	94.37 57	72.48 207	92.07 10	96.85 19	83.82 2	99.15 2	91.53 39	97.42 4	97.55 4

test_0728_THIRD									72.48 207	90.55 23	96.93 13	76.24 11	99.08 11	91.53 39	94.99 18	96.43 31

cl22		77.94 226	76.78 223	81.42 249	87.57 225	64.93 175	90.67 238	88.86 303	72.45 209	67.63 288	82.68 301	64.07 99	92.91 284	71.79 210	65.30 320	86.44 300

thres600view7		78.00 223	76.66 225	82.03 239	91.93 110	63.69 214	91.30 212	96.33 1	72.43 210	70.46 246	87.89 234	60.31 151	94.92 207	42.64 391	76.64 243	87.48 279

IterMVS-LS		76.49 250	75.18 247	80.43 274	84.49 297	62.74 243	90.64 240	88.80 305	72.40 211	65.16 312	81.72 314	60.98 144	92.27 310	67.74 251	64.65 332	86.29 302
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		78.97 203	78.22 198	81.25 252	85.33 276	62.73 244	89.53 273	93.21 100	72.39 212	72.14 226	90.13 200	60.99 143	94.72 214	67.73 252	72.49 272	86.29 302

miper_ehance_all_eth		77.60 231	76.44 228	81.09 262	85.70 273	64.41 187	90.65 239	88.64 312	72.31 213	67.37 294	82.52 302	64.77 91	92.64 297	70.67 222	65.30 320	86.24 304

v144192		76.05 259	74.03 266	82.12 234	79.50 358	66.55 134	91.39 204	89.71 268	72.30 214	68.17 278	81.33 323	51.75 256	94.03 251	67.94 249	64.19 335	85.77 319

thres100view900		78.37 217	77.01 220	82.46 219	91.89 114	63.21 230	91.19 220	96.33 1	72.28 215	70.45 247	87.89 234	60.31 151	95.32 192	45.16 379	77.58 232	88.83 258

PatchmatchNet		77.46 233	74.63 252	85.96 91	89.55 168	70.35 35	79.97 380	89.55 270	72.23 216	70.94 240	76.91 371	57.03 191	92.79 289	54.27 337	81.17 198	94.74 102
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
HFP-MVS		84.73 90	84.40 91	85.72 102	93.75 52	65.01 172	93.50 108	93.19 103	72.19 217	79.22 138	94.93 81	59.04 171	97.67 56	81.55 126	92.21 64	94.49 119

ACMMPR		84.37 95	84.06 93	85.28 118	93.56 58	64.37 189	93.50 108	93.15 105	72.19 217	78.85 146	94.86 84	56.69 200	97.45 71	81.55 126	92.20 65	94.02 142

1314		80.70 170	78.95 189	85.94 92	87.77 223	67.56 104	87.91 304	92.55 134	72.17 219	67.44 290	93.09 130	50.27 270	97.04 101	71.68 214	87.64 127	93.23 167

region2R		84.36 96	84.03 94	85.36 114	93.54 60	64.31 192	93.43 113	92.95 114	72.16 220	78.86 145	94.84 85	56.97 195	97.53 68	81.38 130	92.11 67	94.24 128

Test_1112_low_res		79.56 192	78.60 193	82.43 220	88.24 207	60.39 303	92.09 171	87.99 329	72.10 221	71.84 230	87.42 242	64.62 92	93.04 275	65.80 274	77.30 237	93.85 151

v1921920		75.63 269	73.49 274	82.06 238	79.38 359	66.35 137	91.07 225	89.48 271	71.98 222	67.99 279	81.22 326	49.16 286	93.90 257	66.56 263	64.56 333	85.92 316

DVP-MVS		89.41 13	89.73 14	88.45 25	96.40 15	69.99 39	96.64 10	94.52 47	71.92 223	90.55 23	96.93 13	73.77 23	99.08 11	91.91 37	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
test0726					96.40 15	69.99 39	96.76 8	94.33 59	71.92 223	91.89 12	97.11 8	73.77 23

Fast-Effi-MVS+-dtu		75.04 275	73.37 275	80.07 283	80.86 336	59.52 319	91.20 219	85.38 359	71.90 225	65.20 311	84.84 276	41.46 334	92.97 278	66.50 266	72.96 268	87.73 275

LFMVS		84.34 97	82.73 125	89.18 13	94.76 33	73.25 11	94.99 44	91.89 164	71.90 225	82.16 102	93.49 126	47.98 295	97.05 98	82.55 120	84.82 158	97.25 8

eth_miper_zixun_eth		75.96 263	74.40 258	80.66 269	84.66 291	63.02 234	89.28 279	88.27 322	71.88 227	65.73 307	81.65 315	59.45 163	92.81 287	68.13 244	60.53 367	86.14 306

train_agg		87.21 36	87.42 37	86.60 69	94.18 41	67.28 111	94.16 67	93.51 87	71.87 228	85.52 67	95.33 63	68.19 54	97.27 86	89.09 54	94.90 22	95.25 78

test_8					94.19 40	67.19 113	94.15 69	93.42 94	71.87 228	85.38 70	95.35 62	68.19 54	96.95 112

MDTV_nov1_ep13			72.61 286		89.06 182	68.48 77	80.33 373	90.11 248	71.84 230	71.81 231	75.92 379	53.01 244	93.92 256	48.04 363	73.38 264

ab-mvs		80.18 181	78.31 196	85.80 98	88.44 197	65.49 161	83.00 352	92.67 126	71.82 231	77.36 161	85.01 274	54.50 224	96.59 127	76.35 172	75.63 249	95.32 70

ACMMP		81.49 154	80.67 156	83.93 173	91.71 119	62.90 240	92.13 168	92.22 145	71.79 232	71.68 234	93.49 126	50.32 268	96.96 111	78.47 159	84.22 169	91.93 211
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
PHI-MVS		86.83 43	86.85 47	86.78 63	93.47 63	65.55 158	95.39 30	95.10 25	71.77 233	85.69 65	96.52 27	62.07 134	98.77 23	86.06 83	95.60 12	96.03 43

TEST9					94.18 41	67.28 111	94.16 67	93.51 87	71.75 234	85.52 67	95.33 63	68.01 56	97.27 86

WB-MVSnew		77.14 238	76.18 234	80.01 286	86.18 261	63.24 228	91.26 213	94.11 65	71.72 235	73.52 204	87.29 245	45.14 320	93.00 277	56.98 327	79.42 213	83.80 343

c3_l		76.83 246	75.47 242	80.93 266	85.02 286	64.18 197	90.39 247	88.11 326	71.66 236	66.65 303	81.64 316	63.58 113	92.56 298	69.31 234	62.86 344	86.04 310

SED-MVS		89.94 9	90.36 10	88.70 18	96.45 12	69.38 56	96.89 6	94.44 51	71.65 237	92.11 8	97.21 6	76.79 9	99.11 6	92.34 31	95.36 14	97.62 2

test_241102_TWO								94.41 53	71.65 237	92.07 10	97.21 6	74.58 18	99.11 6	92.34 31	95.36 14	96.59 19

test_241102_ONE					96.45 12	69.38 56		94.44 51	71.65 237	92.11 8	97.05 9	76.79 9	99.11 6

v8		75.35 271	73.26 277	81.61 245	80.67 341	66.82 125	89.54 272	89.27 280	71.65 237	63.30 331	80.30 340	54.99 221	94.06 246	67.33 256	62.33 350	83.94 341

v1240		75.21 274	72.98 280	81.88 240	79.20 361	66.00 145	90.75 234	89.11 291	71.63 241	67.41 292	81.22 326	47.36 300	93.87 259	65.46 279	64.72 331	85.77 319

SCA		75.82 265	72.76 282	85.01 128	86.63 250	70.08 38	81.06 368	89.19 284	71.60 242	70.01 253	77.09 369	45.53 316	90.25 342	60.43 311	73.27 265	94.68 105

BH-untuned		78.68 211	77.08 218	83.48 191	89.84 160	63.74 208	92.70 143	88.59 313	71.57 243	66.83 300	88.65 218	51.75 256	95.39 189	59.03 319	84.77 159	91.32 224

IterMVS		72.65 304	70.83 302	78.09 318	82.17 326	62.96 236	87.64 311	86.28 348	71.56 244	60.44 348	78.85 354	45.42 318	86.66 380	63.30 294	61.83 355	84.65 336
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
mPP-MVS		82.96 130	82.44 130	84.52 152	92.83 80	62.92 239	92.76 139	91.85 168	71.52 245	75.61 180	94.24 107	53.48 241	96.99 106	78.97 153	90.73 89	93.64 157

test-LLR		80.10 183	79.56 177	81.72 243	86.93 244	61.17 279	92.70 143	91.54 183	71.51 246	75.62 178	86.94 251	53.83 234	92.38 304	72.21 207	84.76 160	91.60 215

test0.0.03 1		72.76 299	72.71 285	72.88 367	80.25 349	47.99 400	91.22 217	89.45 273	71.51 246	62.51 340	87.66 237	53.83 234	85.06 390	50.16 352	67.84 306	85.58 322

test_one_0601					96.32 18	69.74 50		94.18 62	71.42 248	90.67 22	96.85 19	74.45 20

PGM-MVS		83.25 122	82.70 126	84.92 129	92.81 84	64.07 200	90.44 244	92.20 146	71.28 249	77.23 164	94.43 95	55.17 219	97.31 81	79.33 149	91.38 81	93.37 162

thisisatest0530		81.15 160	80.07 166	84.39 157	88.26 205	65.63 155	91.40 202	94.62 43	71.27 250	70.93 241	89.18 212	72.47 33	96.04 158	65.62 276	76.89 242	91.49 217

cl____		76.07 256	74.67 250	80.28 277	85.15 281	61.76 267	90.12 256	88.73 307	71.16 251	65.43 309	81.57 318	61.15 141	92.95 279	66.54 264	62.17 351	86.13 308

DIV-MVS_self_test		76.07 256	74.67 250	80.28 277	85.14 282	61.75 268	90.12 256	88.73 307	71.16 251	65.42 310	81.60 317	61.15 141	92.94 283	66.54 264	62.16 353	86.14 306

dp		75.01 276	72.09 292	83.76 176	89.28 175	66.22 142	79.96 381	89.75 262	71.16 251	67.80 286	77.19 368	51.81 254	92.54 299	50.39 350	71.44 281	92.51 193

FA-MVS(test-final)		79.12 200	77.23 217	84.81 136	90.54 146	63.98 203	81.35 366	91.71 175	71.09 254	74.85 190	82.94 297	52.85 245	97.05 98	67.97 248	81.73 195	93.41 161

CP-MVS		83.71 114	83.40 108	84.65 145	93.14 71	63.84 204	94.59 55	92.28 140	71.03 255	77.41 160	94.92 82	55.21 218	96.19 148	81.32 131	90.70 90	93.91 147

v10		74.77 279	72.54 288	81.46 248	80.33 348	66.71 129	89.15 283	89.08 293	70.94 256	63.08 334	79.86 345	52.52 249	94.04 249	65.70 275	62.17 351	83.64 344

CDPH-MVS		85.71 69	85.46 73	86.46 75	94.75 34	67.19 113	93.89 85	92.83 118	70.90 257	83.09 93	95.28 67	63.62 109	97.36 77	80.63 137	94.18 37	94.84 97

GBi-Net		75.65 267	73.83 269	81.10 259	88.85 186	65.11 169	90.01 260	90.32 235	70.84 258	67.04 296	80.25 341	48.03 292	91.54 328	59.80 316	69.34 289	86.64 295

test1		75.65 267	73.83 269	81.10 259	88.85 186	65.11 169	90.01 260	90.32 235	70.84 258	67.04 296	80.25 341	48.03 292	91.54 328	59.80 316	69.34 289	86.64 295

FMVSNet2		76.07 256	74.01 267	82.26 228	88.85 186	67.66 101	91.33 210	91.61 181	70.84 258	65.98 305	82.25 306	48.03 292	92.00 317	58.46 321	68.73 297	87.10 288

SF-MVS		87.03 38	87.09 40	86.84 59	92.70 86	67.45 109	93.64 100	93.76 74	70.78 261	86.25 56	96.44 30	66.98 63	97.79 50	88.68 58	94.56 34	95.28 74

ZD-MVS					96.63 9	65.50 160		93.50 89	70.74 262	85.26 72	95.19 75	64.92 88	97.29 82	87.51 66	93.01 56

HyFIR lowres test		81.03 165	79.56 177	85.43 109	87.81 220	68.11 90	90.18 255	90.01 254	70.65 263	72.95 209	86.06 262	63.61 110	94.50 228	75.01 182	79.75 212	93.67 155

MVP-Stereo		77.12 239	76.23 232	79.79 294	81.72 330	66.34 138	89.29 278	90.88 214	70.56 264	62.01 342	82.88 298	49.34 281	94.13 241	65.55 278	93.80 43	78.88 397
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMP	71.68 10	75.58 270	74.23 261	79.62 299	84.97 287	59.64 316	90.80 232	89.07 294	70.39 265	62.95 335	87.30 244	38.28 349	93.87 259	72.89 196	71.45 280	85.36 328
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HPM-MVS		83.25 122	82.95 120	84.17 165	92.25 95	62.88 241	90.91 226	91.86 166	70.30 266	77.12 165	93.96 116	56.75 198	96.28 144	82.04 123	91.34 83	93.34 163
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
GeoE		78.90 205	77.43 211	83.29 197	88.95 185	62.02 259	92.31 160	86.23 350	70.24 267	71.34 239	89.27 211	54.43 228	94.04 249	63.31 293	80.81 203	93.81 152

tpm2		79.80 189	77.95 203	85.34 115	88.28 204	68.26 84	81.56 363	91.42 189	70.11 268	77.59 159	80.50 336	67.40 61	94.26 237	67.34 255	77.35 236	93.51 159

TR-MVS		78.77 210	77.37 216	82.95 207	90.49 148	60.88 285	93.67 98	90.07 249	70.08 269	74.51 194	91.37 175	45.69 315	95.70 174	60.12 314	80.32 207	92.29 199

CL-MVSNet_self_test		69.92 320	68.09 324	75.41 343	73.25 403	55.90 359	90.05 259	89.90 257	69.96 270	61.96 343	76.54 372	51.05 264	87.64 373	49.51 356	50.59 398	82.70 362

PAPM_NR		82.97 129	81.84 137	86.37 79	94.10 44	66.76 128	87.66 310	92.84 117	69.96 270	74.07 200	93.57 124	63.10 122	97.50 70	70.66 223	90.58 92	94.85 94

PCF-MVS	73.15 9	79.29 197	77.63 207	84.29 161	86.06 264	65.96 147	87.03 317	91.10 205	69.86 272	69.79 258	90.64 182	57.54 187	96.59 127	64.37 286	82.29 184	90.32 239
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
miper_lstm_enhance		73.05 294	71.73 297	77.03 331	83.80 307	58.32 334	81.76 359	88.88 301	69.80 273	61.01 344	78.23 358	57.19 189	87.51 376	65.34 280	59.53 372	85.27 331

MIMVSNet		71.64 308	68.44 321	81.23 253	81.97 329	64.44 184	73.05 403	88.80 305	69.67 274	64.59 316	74.79 384	32.79 381	87.82 370	53.99 338	76.35 245	91.42 219

LPG-MVS_test		75.82 265	74.58 254	79.56 301	84.31 301	59.37 321	90.44 244	89.73 265	69.49 275	64.86 313	88.42 220	38.65 345	94.30 233	72.56 203	72.76 269	85.01 332

LGP-MVS_train				79.56 301	84.31 301	59.37 321		89.73 265	69.49 275	64.86 313	88.42 220	38.65 345	94.30 233	72.56 203	72.76 269	85.01 332

APDe-MVS		87.54 28	87.84 30	86.65 67	96.07 23	66.30 139	94.84 48	93.78 71	69.35 277	88.39 39	96.34 34	67.74 59	97.66 59	90.62 46	93.44 51	96.01 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
tttt0517		79.50 193	78.53 194	82.41 223	87.22 235	61.43 277	89.75 267	94.76 35	69.29 278	67.91 282	88.06 232	72.92 29	95.63 175	62.91 297	73.90 263	90.16 241

Patchmatch-RL test		68.17 337	64.49 348	79.19 305	71.22 408	53.93 369	70.07 411	71.54 416	69.22 279	56.79 372	62.89 419	56.58 202	88.61 359	69.53 231	52.61 393	95.03 88

test_yl		84.28 98	83.16 114	87.64 34	94.52 37	69.24 60	95.78 18	95.09 26	69.19 280	81.09 112	92.88 138	57.00 193	97.44 72	81.11 134	81.76 193	96.23 38

DCV-MVSNet		84.28 98	83.16 114	87.64 34	94.52 37	69.24 60	95.78 18	95.09 26	69.19 280	81.09 112	92.88 138	57.00 193	97.44 72	81.11 134	81.76 193	96.23 38

jajsoiax		73.05 294	71.51 299	77.67 321	77.46 386	54.83 365	88.81 289	90.04 252	69.13 282	62.85 337	83.51 291	31.16 390	92.75 290	70.83 219	69.80 285	85.43 327

DP-MVS Recon		82.73 132	81.65 139	85.98 90	97.31 4	67.06 118	95.15 36	91.99 158	69.08 283	76.50 172	93.89 117	54.48 227	98.20 37	70.76 221	85.66 153	92.69 184

Baseline_NR-MVSNet		73.99 286	72.83 281	77.48 324	80.78 339	59.29 324	91.79 188	84.55 368	68.85 284	68.99 266	80.70 332	56.16 206	92.04 316	62.67 299	60.98 364	81.11 376

CHOSEN 280x420		77.35 235	76.95 222	78.55 312	87.07 239	62.68 245	69.71 412	82.95 382	68.80 285	71.48 237	87.27 246	66.03 73	84.00 396	76.47 170	82.81 181	88.95 257

DPE-MVS		88.77 17	89.21 16	87.45 43	96.26 20	67.56 104	94.17 66	94.15 64	68.77 286	90.74 21	97.27 3	76.09 12	98.49 29	90.58 47	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
mvs_tets		72.71 301	71.11 300	77.52 322	77.41 387	54.52 367	88.45 295	89.76 261	68.76 287	62.70 338	83.26 295	29.49 395	92.71 291	70.51 225	69.62 287	85.34 329

MVS		84.66 91	82.86 123	90.06 2	90.93 139	74.56 7	87.91 304	95.54 14	68.55 288	72.35 225	94.71 88	59.78 159	98.90 20	81.29 132	94.69 32	96.74 16

EPP-MVSNet		81.79 149	81.52 140	82.61 216	88.77 190	60.21 307	93.02 128	93.66 81	68.52 289	72.90 210	90.39 189	72.19 38	94.96 204	74.93 183	79.29 218	92.67 185

CSCG		86.87 40	86.26 55	88.72 17	95.05 31	70.79 29	93.83 92	95.33 18	68.48 290	77.63 157	94.35 101	73.04 28	98.45 30	84.92 94	93.71 47	96.92 14

lecture		84.77 88	84.81 86	84.65 145	92.12 101	62.27 255	94.74 50	92.64 130	68.35 291	85.53 66	95.30 65	59.77 160	97.91 44	83.73 107	91.15 85	93.77 153

LuminaMVS		78.14 222	76.66 225	82.60 217	80.82 338	64.64 177	89.33 277	90.45 227	68.25 292	74.73 192	85.51 270	41.15 336	94.14 240	78.96 154	80.69 205	89.04 256

testing3		70.38 317	70.83 302	69.03 387	85.82 270	43.93 418	90.72 237	90.56 226	68.06 293	60.24 349	86.82 253	64.83 89	84.12 392	26.33 428	64.10 337	79.04 395

CP-MVSNet		70.50 315	69.91 312	72.26 372	80.71 340	51.00 384	87.23 316	90.30 239	67.84 294	59.64 352	82.69 300	50.23 271	82.30 408	51.28 346	59.28 373	83.46 349

pmmvs5		73.35 291	71.52 298	78.86 310	78.64 372	60.61 297	91.08 223	86.90 341	67.69 295	63.32 330	83.64 289	44.33 324	90.53 339	62.04 303	66.02 315	85.46 326

pm-mvs1		72.89 297	71.09 301	78.26 316	79.10 365	57.62 341	90.80 232	89.30 279	67.66 296	62.91 336	81.78 313	49.11 287	92.95 279	60.29 313	58.89 375	84.22 339

MDTV_nov1_ep13_2view						59.90 313	80.13 377		67.65 297	72.79 211		54.33 230		59.83 315		92.58 190

pmmvs4		73.92 287	71.81 296	80.25 279	79.17 362	65.24 165	87.43 313	87.26 339	67.64 298	63.46 329	83.91 288	48.96 288	91.53 331	62.94 296	65.49 319	83.96 340

WR-MVS_H		70.59 314	69.94 311	72.53 369	81.03 335	51.43 380	87.35 314	92.03 157	67.38 299	60.23 350	80.70 332	55.84 212	83.45 400	46.33 374	58.58 377	82.72 360

KD-MVS_2432*1600		69.03 328	66.37 332	77.01 332	85.56 274	61.06 282	81.44 364	90.25 242	67.27 300	58.00 365	76.53 373	54.49 225	87.63 374	48.04 363	35.77 426	82.34 366

miper_refine_blended		69.03 328	66.37 332	77.01 332	85.56 274	61.06 282	81.44 364	90.25 242	67.27 300	58.00 365	76.53 373	54.49 225	87.63 374	48.04 363	35.77 426	82.34 366

PS-CasMVS		69.86 322	69.13 317	72.07 376	80.35 347	50.57 386	87.02 318	89.75 262	67.27 300	59.19 356	82.28 305	46.58 306	82.24 409	50.69 349	59.02 374	83.39 351

PEN-MVS		69.46 325	68.56 319	72.17 374	79.27 360	49.71 391	86.90 320	89.24 281	67.24 303	59.08 357	82.51 303	47.23 301	83.54 399	48.42 361	57.12 379	83.25 352

mmtdpeth		68.33 335	66.37 332	74.21 358	82.81 321	51.73 377	84.34 334	80.42 389	67.01 304	71.56 235	68.58 406	30.52 393	92.35 307	75.89 174	36.21 424	78.56 402

cascas		78.18 220	75.77 239	85.41 110	87.14 237	69.11 62	92.96 130	91.15 203	66.71 305	70.47 245	86.07 261	37.49 359	96.48 136	70.15 226	79.80 211	90.65 235

APD-MVS		85.93 64	85.99 63	85.76 100	95.98 26	65.21 166	93.59 103	92.58 133	66.54 306	86.17 59	95.88 48	63.83 104	97.00 103	86.39 80	92.94 57	95.06 85
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
OpenMVS	70.45 11	78.54 215	75.92 237	86.41 78	85.93 269	71.68 18	92.74 140	92.51 135	66.49 307	64.56 317	91.96 160	43.88 325	98.10 39	54.61 335	90.65 91	89.44 255

DTE-MVSNet		68.46 334	67.33 328	71.87 378	77.94 381	49.00 397	86.16 326	88.58 314	66.36 308	58.19 362	82.21 307	46.36 307	83.87 397	44.97 382	55.17 386	82.73 359

IterMVS-SCA-FT		71.55 310	69.97 310	76.32 338	81.48 332	60.67 295	87.64 311	85.99 353	66.17 309	59.50 353	78.88 353	45.53 316	83.65 398	62.58 300	61.93 354	84.63 338

TransMVSNet (Re)		70.07 319	67.66 325	77.31 328	80.62 343	59.13 326	91.78 190	84.94 364	65.97 310	60.08 351	80.44 337	50.78 265	91.87 318	48.84 359	45.46 408	80.94 378

MVSFormer		83.75 113	82.88 122	86.37 79	89.24 179	71.18 24	89.07 284	90.69 219	65.80 311	87.13 48	94.34 102	64.99 85	92.67 294	72.83 197	91.80 73	95.27 75

test_djsdf		73.76 290	72.56 287	77.39 326	77.00 389	53.93 369	89.07 284	90.69 219	65.80 311	63.92 324	82.03 309	43.14 329	92.67 294	72.83 197	68.53 298	85.57 323

API-MVS		82.28 140	80.53 161	87.54 41	96.13 22	70.59 31	93.63 101	91.04 212	65.72 313	75.45 183	92.83 140	56.11 208	98.89 21	64.10 287	89.75 106	93.15 170

原ACMM1				84.42 155	93.21 68	64.27 194		93.40 96	65.39 314	79.51 133	92.50 144	58.11 182	96.69 125	65.27 281	93.96 40	92.32 198

testgi		64.48 360	62.87 358	69.31 386	71.24 407	40.62 424	85.49 327	79.92 391	65.36 315	54.18 380	83.49 292	23.74 410	84.55 391	41.60 393	60.79 366	82.77 358

QAPM		79.95 187	77.39 215	87.64 34	89.63 165	71.41 20	93.30 117	93.70 79	65.34 316	67.39 293	91.75 166	47.83 297	98.96 16	57.71 324	89.81 103	92.54 191

HPM-MVS_fast		80.25 180	79.55 179	82.33 224	91.55 124	59.95 312	91.32 211	89.16 286	65.23 317	74.71 193	93.07 132	47.81 298	95.74 168	74.87 186	88.23 119	91.31 225

tfpnnormal		70.10 318	67.36 327	78.32 314	83.45 313	60.97 284	88.85 288	92.77 120	64.85 318	60.83 346	78.53 355	43.52 327	93.48 268	31.73 423	61.70 359	80.52 383

FE-MVS		75.97 262	73.02 279	84.82 133	89.78 161	65.56 157	77.44 391	91.07 209	64.55 319	72.66 213	79.85 346	46.05 313	96.69 125	54.97 334	80.82 202	92.21 205

SR-MVS		82.81 131	82.58 127	83.50 190	93.35 64	61.16 281	92.23 164	91.28 197	64.48 320	81.27 109	95.28 67	53.71 237	95.86 163	82.87 117	88.77 115	93.49 160

reproduce-ours		83.51 117	83.33 111	84.06 167	92.18 99	60.49 299	90.74 235	92.04 154	64.35 321	83.24 89	95.59 56	59.05 169	97.27 86	83.61 108	89.17 110	94.41 123

our_new_method		83.51 117	83.33 111	84.06 167	92.18 99	60.49 299	90.74 235	92.04 154	64.35 321	83.24 89	95.59 56	59.05 169	97.27 86	83.61 108	89.17 110	94.41 123

K. test v3		63.09 367	59.61 371	73.53 362	76.26 392	49.38 395	83.27 345	77.15 396	64.35 321	47.77 408	72.32 394	28.73 397	87.79 371	49.93 354	36.69 423	83.41 350

v7n		71.31 311	68.65 318	79.28 304	76.40 391	60.77 288	86.71 322	89.45 273	64.17 324	58.77 360	78.24 357	44.59 323	93.54 266	57.76 323	61.75 357	83.52 347

FMVSNet1		72.71 301	69.91 312	81.10 259	83.60 311	65.11 169	90.01 260	90.32 235	63.92 325	63.56 328	80.25 341	36.35 368	91.54 328	54.46 336	66.75 311	86.64 295

XVG-OURS		74.25 283	72.46 289	79.63 298	78.45 375	57.59 343	80.33 373	87.39 335	63.86 326	68.76 272	89.62 207	40.50 339	91.72 322	69.00 238	74.25 258	89.58 250

UniMVSNet_ETH3D		72.74 300	70.53 307	79.36 303	78.62 373	56.64 353	85.01 330	89.20 283	63.77 327	64.84 315	84.44 282	34.05 378	91.86 319	63.94 288	70.89 284	89.57 251

reproduce_model		83.15 124	82.96 118	83.73 179	92.02 104	59.74 315	90.37 248	92.08 152	63.70 328	82.86 94	95.48 59	58.62 175	97.17 91	83.06 114	88.42 118	94.26 126

test_fmvs1		74.07 284	73.69 271	75.22 345	78.91 368	47.34 404	89.06 286	74.69 404	63.68 329	79.41 135	91.59 170	24.36 407	87.77 372	85.22 88	76.26 246	90.55 238

114514_t		79.17 199	77.67 205	83.68 183	95.32 29	65.53 159	92.85 137	91.60 182	63.49 330	67.92 281	90.63 184	46.65 305	95.72 173	67.01 260	83.54 174	89.79 247

test_fmvs1_n		72.69 303	71.92 294	74.99 349	71.15 409	47.08 406	87.34 315	75.67 399	63.48 331	78.08 153	91.17 177	20.16 421	87.87 369	84.65 97	75.57 250	90.01 244

APD-MVS_3200maxsize		81.64 152	81.32 142	82.59 218	92.36 92	58.74 329	91.39 204	91.01 213	63.35 332	79.72 131	94.62 91	51.82 253	96.14 150	79.71 144	87.93 123	92.89 182

test20.03		63.83 363	62.65 359	67.38 394	70.58 413	39.94 426	86.57 323	84.17 370	63.29 333	51.86 391	77.30 365	37.09 364	82.47 406	38.87 404	54.13 390	79.73 389

XVG-OURS-SEG-HR		74.70 280	73.08 278	79.57 300	78.25 377	57.33 347	80.49 371	87.32 336	63.22 334	68.76 272	90.12 202	44.89 322	91.59 326	70.55 224	74.09 260	89.79 247

test_vis1_n		71.63 309	70.73 305	74.31 357	69.63 415	47.29 405	86.91 319	72.11 412	63.21 335	75.18 185	90.17 197	20.40 419	85.76 384	84.59 98	74.42 257	89.87 245

ACMM	69.62 13	74.34 281	72.73 284	79.17 306	84.25 303	57.87 337	90.36 249	89.93 256	63.17 336	65.64 308	86.04 263	37.79 357	94.10 242	65.89 272	71.52 279	85.55 324
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmvs		72.88 298	69.76 314	82.22 229	90.98 138	67.05 119	78.22 388	88.30 320	63.10 337	64.35 322	74.98 382	55.09 220	94.27 235	43.25 385	69.57 288	85.34 329

SixPastTwentyTwo		64.92 357	61.78 364	74.34 356	78.74 370	49.76 390	83.42 344	79.51 393	62.86 338	50.27 398	77.35 364	30.92 392	90.49 340	45.89 376	47.06 403	82.78 357

SR-MVS-dyc-post		81.06 164	80.70 155	82.15 232	92.02 104	58.56 332	90.90 227	90.45 227	62.76 339	78.89 141	94.46 93	51.26 263	95.61 177	78.77 157	86.77 139	92.28 200

RE-MVS-def			80.48 162		92.02 104	58.56 332	90.90 227	90.45 227	62.76 339	78.89 141	94.46 93	49.30 282		78.77 157	86.77 139	92.28 200

TAPA-MVS	70.22 12	74.94 277	73.53 273	79.17 306	90.40 150	52.07 376	89.19 282	89.61 269	62.69 341	70.07 252	92.67 142	48.89 289	94.32 231	38.26 405	79.97 209	91.12 229
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Anonymous202405211		77.96 225	75.33 245	85.87 94	93.73 53	64.52 179	94.85 47	85.36 360	62.52 342	76.11 173	90.18 195	29.43 396	97.29 82	68.51 243	77.24 239	95.81 49

pmmvs-eth3d		65.53 355	62.32 361	75.19 346	69.39 416	59.59 317	82.80 353	83.43 378	62.52 342	51.30 395	72.49 390	32.86 380	87.16 379	55.32 333	50.73 397	78.83 398

MVSMamba_PlusPlus		84.97 86	83.65 98	88.93 14	90.17 155	74.04 8	87.84 306	92.69 125	62.18 344	81.47 108	87.64 238	71.47 42	96.28 144	84.69 96	94.74 31	96.47 28

AdaColmap		78.94 204	77.00 221	84.76 138	96.34 17	65.86 150	92.66 147	87.97 331	62.18 344	70.56 244	92.37 150	43.53 326	97.35 78	64.50 285	82.86 179	91.05 230

FOURS1					93.95 46	61.77 266	93.96 80	91.92 161	62.14 346	86.57 54

无先验							92.71 142	92.61 132	62.03 347				97.01 102	66.63 262		93.97 143

XVG-ACMP-BASELINE		68.04 338	65.53 339	75.56 342	74.06 401	52.37 374	78.43 385	85.88 354	62.03 347	58.91 359	81.21 328	20.38 420	91.15 335	60.69 310	68.18 300	83.16 354

anonymousdsp		71.14 312	69.37 316	76.45 337	72.95 404	54.71 366	84.19 336	88.88 301	61.92 349	62.15 341	79.77 347	38.14 352	91.44 333	68.90 240	67.45 307	83.21 353

tpm cat1		75.30 272	72.21 291	84.58 150	88.52 193	67.77 98	78.16 389	88.02 328	61.88 350	68.45 277	76.37 375	60.65 147	94.03 251	53.77 340	74.11 259	91.93 211

FMVSNet5		68.04 338	65.66 338	75.18 347	84.43 299	57.89 336	83.54 340	86.26 349	61.83 351	53.64 384	73.30 387	37.15 363	85.08 389	48.99 358	61.77 356	82.56 365

Elysia		76.45 252	74.17 262	83.30 195	80.43 344	64.12 198	89.58 268	90.83 215	61.78 352	72.53 217	85.92 264	34.30 376	94.81 209	68.10 245	84.01 172	90.97 231

StellarMVS		76.45 252	74.17 262	83.30 195	80.43 344	64.12 198	89.58 268	90.83 215	61.78 352	72.53 217	85.92 264	34.30 376	94.81 209	68.10 245	84.01 172	90.97 231

Anonymous20231206		67.53 343	65.78 335	72.79 368	74.95 397	47.59 402	88.23 297	87.32 336	61.75 354	58.07 364	77.29 366	37.79 357	87.29 378	42.91 387	63.71 341	83.48 348

PatchMatch-RL		72.06 306	69.98 309	78.28 315	89.51 169	55.70 360	83.49 341	83.39 380	61.24 355	63.72 327	82.76 299	34.77 373	93.03 276	53.37 342	77.59 231	86.12 309

tt0805		73.07 293	70.73 305	80.07 283	78.37 376	57.05 349	87.78 307	92.18 149	61.23 356	67.04 296	86.49 256	31.35 389	94.58 219	65.06 282	67.12 308	88.57 264

PLC	68.80 14	75.23 273	73.68 272	79.86 292	92.93 77	58.68 330	90.64 240	88.30 320	60.90 357	64.43 321	90.53 185	42.38 331	94.57 221	56.52 328	76.54 244	86.33 301
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ACMH	63.93 17	68.62 331	64.81 343	80.03 285	85.22 280	63.25 227	87.72 308	84.66 366	60.83 358	51.57 393	79.43 351	27.29 402	94.96 204	41.76 392	64.84 328	81.88 370
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EG-PatchMatch MVS		68.55 332	65.41 340	77.96 319	78.69 371	62.93 237	89.86 265	89.17 285	60.55 359	50.27 398	77.73 363	22.60 415	94.06 246	47.18 370	72.65 271	76.88 408

VDDNet		80.50 174	78.26 197	87.21 47	86.19 260	69.79 48	94.48 56	91.31 192	60.42 360	79.34 136	90.91 180	38.48 348	96.56 130	82.16 121	81.05 199	95.27 75

CPTT-MVS		79.59 191	79.16 186	80.89 268	91.54 125	59.80 314	92.10 170	88.54 315	60.42 360	72.96 208	93.28 128	48.27 291	92.80 288	78.89 156	86.50 145	90.06 242

our_test_3		68.29 336	64.69 345	79.11 309	78.92 366	64.85 176	88.40 296	85.06 362	60.32 362	52.68 387	76.12 377	40.81 338	89.80 354	44.25 384	55.65 384	82.67 364

ITE_SJBPF				70.43 382	74.44 399	47.06 407		77.32 395	60.16 363	54.04 381	83.53 290	23.30 412	84.01 395	43.07 386	61.58 361	80.21 388

ppachtmachnet_test		67.72 340	63.70 352	79.77 295	78.92 366	66.04 144	88.68 291	82.90 383	60.11 364	55.45 375	75.96 378	39.19 342	90.55 338	39.53 400	52.55 394	82.71 361

new-patchmatchnet		59.30 382	56.48 384	67.79 391	65.86 423	44.19 415	82.47 356	81.77 384	59.94 365	43.65 420	66.20 413	27.67 401	81.68 411	39.34 401	41.40 415	77.50 407

mvsany_test1		68.77 330	68.56 319	69.39 385	73.57 402	45.88 413	80.93 369	60.88 433	59.65 366	71.56 235	90.26 194	43.22 328	75.05 420	74.26 190	62.70 346	87.25 287

新几何1				84.73 139	92.32 93	64.28 193		91.46 188	59.56 367	79.77 130	92.90 136	56.95 196	96.57 129	63.40 291	92.91 58	93.34 163

旧先验2							92.00 179		59.37 368	87.54 47			93.47 269	75.39 178

PM-MVS		59.40 381	56.59 383	67.84 390	63.63 425	41.86 420	76.76 392	63.22 430	59.01 369	51.07 396	72.27 395	11.72 433	83.25 402	61.34 306	50.28 399	78.39 403

LTVRE_ROB	59.60 19	66.27 349	63.54 353	74.45 354	84.00 306	51.55 379	67.08 421	83.53 377	58.78 370	54.94 377	80.31 339	34.54 374	93.23 272	40.64 398	68.03 302	78.58 401
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
testdata				81.34 251	89.02 183	57.72 339		89.84 259	58.65 371	85.32 71	94.09 112	57.03 191	93.28 271	69.34 233	90.56 93	93.03 176

ACMH+	65.35 16	67.65 341	64.55 346	76.96 334	84.59 293	57.10 348	88.08 299	80.79 387	58.59 372	53.00 386	81.09 330	26.63 404	92.95 279	46.51 372	61.69 360	80.82 379

kuosan		60.86 377	60.24 367	62.71 402	81.57 331	46.43 410	75.70 399	85.88 354	57.98 373	48.95 404	69.53 404	58.42 177	76.53 418	28.25 427	35.87 425	65.15 426

ADS-MVSNet2		66.90 346	63.44 354	77.26 329	88.06 211	60.70 294	68.01 417	75.56 401	57.57 374	64.48 318	69.87 402	38.68 343	84.10 393	40.87 396	67.89 304	86.97 289

ADS-MVSNet		68.54 333	64.38 350	81.03 263	88.06 211	66.90 124	68.01 417	84.02 372	57.57 374	64.48 318	69.87 402	38.68 343	89.21 357	40.87 396	67.89 304	86.97 289

MDA-MVSNet-bldmvs		61.54 373	57.70 377	73.05 365	79.53 357	57.00 352	83.08 349	81.23 385	57.57 374	34.91 430	72.45 391	32.79 381	86.26 383	35.81 409	41.95 414	75.89 410

mvs5depth		61.03 375	57.65 378	71.18 379	67.16 420	47.04 408	72.74 404	77.49 394	57.47 377	60.52 347	72.53 389	22.84 414	88.38 364	49.15 357	38.94 420	78.11 405

KD-MVS_self_test		60.87 376	58.60 374	67.68 392	66.13 422	39.93 427	75.63 400	84.70 365	57.32 378	49.57 401	68.45 407	29.55 394	82.87 404	48.09 362	47.94 402	80.25 387

UnsupCasMVSNet_bld		61.60 372	57.71 376	73.29 364	68.73 417	51.64 378	78.61 384	89.05 295	57.20 379	46.11 409	61.96 422	28.70 398	88.60 360	50.08 353	38.90 421	79.63 390

MSDG		69.54 324	65.73 336	80.96 264	85.11 284	63.71 212	84.19 336	83.28 381	56.95 380	54.50 378	84.03 285	31.50 387	96.03 159	42.87 389	69.13 294	83.14 355

F-COLMAP		70.66 313	68.44 321	77.32 327	86.37 258	55.91 358	88.00 302	86.32 347	56.94 381	57.28 371	88.07 231	33.58 379	92.49 301	51.02 347	68.37 299	83.55 345

test222					89.77 162	61.60 272	89.55 271	89.42 275	56.83 382	77.28 163	92.43 148	52.76 246			91.14 87	93.09 173

CNLPA		74.31 282	72.30 290	80.32 275	91.49 126	61.66 270	90.85 230	80.72 388	56.67 383	63.85 326	90.64 182	46.75 304	90.84 336	53.79 339	75.99 248	88.47 267

OurMVSNet-221017-0		64.68 358	62.17 362	72.21 373	76.08 394	47.35 403	80.67 370	81.02 386	56.19 384	51.60 392	79.66 349	27.05 403	88.56 361	53.60 341	53.63 391	80.71 381

YYNet1		63.76 366	60.14 369	74.62 352	78.06 380	60.19 308	83.46 343	83.99 375	56.18 385	39.25 425	71.56 399	37.18 362	83.34 401	42.90 388	48.70 401	80.32 385

MDA-MVSNet_test_wron		63.78 365	60.16 368	74.64 351	78.15 379	60.41 301	83.49 341	84.03 371	56.17 386	39.17 426	71.59 398	37.22 361	83.24 403	42.87 389	48.73 400	80.26 386

OpenMVS_ROB	61.12 18	66.39 348	62.92 357	76.80 336	76.51 390	57.77 338	89.22 280	83.41 379	55.48 387	53.86 382	77.84 361	26.28 405	93.95 255	34.90 412	68.76 296	78.68 400

MIMVSNet1		60.16 380	57.33 380	68.67 388	69.71 414	44.13 416	78.92 383	84.21 369	55.05 388	44.63 417	71.85 396	23.91 409	81.54 412	32.63 421	55.03 387	80.35 384

test_fmvs2		65.78 353	64.84 342	68.60 389	66.54 421	41.71 421	83.27 345	69.81 420	54.38 389	67.91 282	84.54 281	15.35 426	81.22 413	75.65 176	66.16 314	82.88 356

CVMVSNet		74.04 285	74.27 260	73.33 363	85.33 276	43.94 417	89.53 273	88.39 317	54.33 390	70.37 248	90.13 200	49.17 285	84.05 394	61.83 305	79.36 215	91.99 210

Anonymous20240529		76.84 245	74.15 264	84.88 131	91.02 137	64.95 174	93.84 90	91.09 206	53.57 391	73.00 207	87.42 242	35.91 369	97.32 80	69.14 237	72.41 274	92.36 196

pmmvs6		67.57 342	64.76 344	76.00 341	72.82 406	53.37 371	88.71 290	86.78 345	53.19 392	57.58 370	78.03 360	35.33 372	92.41 303	55.56 332	54.88 388	82.21 368

TinyColmap		60.32 378	56.42 385	72.00 377	78.78 369	53.18 372	78.36 387	75.64 400	52.30 393	41.59 424	75.82 380	14.76 429	88.35 365	35.84 408	54.71 389	74.46 412

test_0402		64.54 359	61.09 365	74.92 350	84.10 305	60.75 290	87.95 303	79.71 392	52.03 394	52.41 388	77.20 367	32.21 385	91.64 324	23.14 431	61.03 363	72.36 419

test_vis1_rt		59.09 383	57.31 381	64.43 398	68.44 418	46.02 412	83.05 351	48.63 442	51.96 395	49.57 401	63.86 418	16.30 424	80.20 415	71.21 217	62.79 345	67.07 425

Anonymous20231211		73.08 292	70.39 308	81.13 256	90.62 145	63.33 225	91.40 202	90.06 251	51.84 396	64.46 320	80.67 334	36.49 367	94.07 245	63.83 289	64.17 336	85.98 312

dongtai		55.18 388	55.46 387	54.34 413	76.03 395	36.88 431	76.07 396	84.61 367	51.28 397	43.41 421	64.61 417	56.56 203	67.81 431	18.09 436	28.50 436	58.32 429

AllTest		61.66 371	58.06 375	72.46 370	79.57 355	51.42 381	80.17 376	68.61 422	51.25 398	45.88 410	81.23 324	19.86 422	86.58 381	38.98 402	57.01 381	79.39 391

TestCases				72.46 370	79.57 355	51.42 381		68.61 422	51.25 398	45.88 410	81.23 324	19.86 422	86.58 381	38.98 402	57.01 381	79.39 391

PatchT		69.11 327	65.37 341	80.32 275	82.07 328	63.68 215	67.96 419	87.62 334	50.86 400	69.37 259	65.18 414	57.09 190	88.53 362	41.59 394	66.60 312	88.74 261

Anonymous20240521		62.09 369	59.08 373	71.10 380	67.19 419	48.72 398	83.91 338	85.23 361	50.38 401	47.84 407	71.22 401	20.74 418	85.51 387	46.47 373	58.75 376	79.06 394

DP-MVS		69.90 321	66.48 329	80.14 281	95.36 28	62.93 237	89.56 270	76.11 397	50.27 402	57.69 369	85.23 272	39.68 341	95.73 169	33.35 415	71.05 283	81.78 372

gg-mvs-nofinetune		77.18 237	74.31 259	85.80 98	91.42 127	68.36 80	71.78 406	94.72 37	49.61 403	77.12 165	45.92 432	77.41 8	93.98 253	67.62 253	93.16 55	95.05 86

JIA-IIPM		66.06 350	62.45 360	76.88 335	81.42 334	54.45 368	57.49 433	88.67 310	49.36 404	63.86 325	46.86 431	56.06 209	90.25 342	49.53 355	68.83 295	85.95 313

N_pmnet		50.55 392	49.11 394	54.88 411	77.17 388	4.02 455	84.36 333	2.00 453	48.59 405	45.86 412	68.82 405	32.22 384	82.80 405	31.58 424	51.38 396	77.81 406

ANet_high		40.27 403	35.20 406	55.47 409	34.74 450	34.47 435	63.84 425	71.56 415	48.42 406	18.80 439	41.08 438	9.52 437	64.45 438	20.18 434	8.66 446	67.49 424

COLMAP_ROB	57.96 20	62.98 368	59.65 370	72.98 366	81.44 333	53.00 373	83.75 339	75.53 402	48.34 407	48.81 405	81.40 322	24.14 408	90.30 341	32.95 417	60.52 368	75.65 411
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
mamv4		65.18 356	67.43 326	58.44 405	77.88 383	49.36 396	69.40 413	70.99 418	48.31 408	57.78 368	85.53 269	59.01 172	51.88 443	73.67 192	64.32 334	74.07 413

Patchmtry		67.53 343	63.93 351	78.34 313	82.12 327	64.38 188	68.72 414	84.00 373	48.23 409	59.24 354	72.41 392	57.82 184	89.27 356	46.10 375	56.68 383	81.36 373

LS3D		69.17 326	66.40 331	77.50 323	91.92 111	56.12 356	85.12 329	80.37 390	46.96 410	56.50 373	87.51 241	37.25 360	93.71 263	32.52 422	79.40 214	82.68 363

RPSCF		64.24 361	61.98 363	71.01 381	76.10 393	45.00 414	75.83 398	75.94 398	46.94 411	58.96 358	84.59 279	31.40 388	82.00 410	47.76 368	60.33 371	86.04 310

RPMNet		70.42 316	65.68 337	84.63 148	83.15 316	67.96 93	70.25 409	90.45 227	46.83 412	69.97 255	65.10 415	56.48 205	95.30 195	35.79 410	73.13 266	90.64 236

sc_t1		63.81 364	59.39 372	77.10 330	77.62 384	56.03 357	84.32 335	73.56 408	46.66 413	58.22 361	73.06 388	23.28 413	90.62 337	50.93 348	46.84 404	84.64 337

WB-MVS		46.23 396	44.94 398	50.11 416	62.13 429	21.23 449	76.48 394	55.49 435	45.89 414	35.78 427	61.44 424	35.54 370	72.83 424	9.96 443	21.75 438	56.27 431

CMPMVS	48.56 21	66.77 347	64.41 349	73.84 360	70.65 412	50.31 388	77.79 390	85.73 357	45.54 415	44.76 416	82.14 308	35.40 371	90.14 348	63.18 295	74.54 255	81.07 377
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		64.01 362	63.01 356	67.02 395	74.40 400	38.86 430	83.27 345	86.19 351	45.11 416	54.27 379	81.15 329	36.91 366	80.01 416	48.79 360	57.02 380	82.19 369

TDRefinement		55.28 387	51.58 391	66.39 396	59.53 433	46.15 411	76.23 395	72.80 409	44.60 417	42.49 422	76.28 376	15.29 427	82.39 407	33.20 416	43.75 410	70.62 421

Patchmatch-test		65.86 351	60.94 366	80.62 272	83.75 308	58.83 328	58.91 432	75.26 403	44.50 418	50.95 397	77.09 369	58.81 174	87.90 368	35.13 411	64.03 338	95.12 82

tt0320-xc		61.51 374	56.89 382	75.37 344	78.50 374	58.61 331	82.61 355	71.27 417	44.31 419	53.17 385	68.03 410	23.38 411	88.46 363	47.77 367	43.00 413	79.03 396

test_fmvs3		56.82 384	54.86 388	62.69 403	53.59 436	35.47 433	75.87 397	65.64 427	43.91 420	55.10 376	71.43 400	6.91 441	74.40 423	68.64 242	52.63 392	78.20 404

mvsany_test3		48.86 394	46.35 397	56.41 407	46.00 442	31.67 438	62.26 426	47.25 443	43.71 421	45.54 414	68.15 409	10.84 434	64.44 439	57.95 322	35.44 428	73.13 416

tt0320		61.85 370	57.45 379	75.03 348	77.49 385	57.60 342	82.74 354	73.65 407	43.65 422	53.65 383	68.18 408	25.47 406	88.66 358	45.56 378	46.68 405	78.81 399

SSC-MVS		44.51 398	43.35 400	47.99 420	61.01 432	18.90 451	74.12 402	54.36 436	43.42 423	34.10 431	60.02 425	34.42 375	70.39 427	9.14 445	19.57 439	54.68 432

LF4IMVS		54.01 389	52.12 390	59.69 404	62.41 428	39.91 428	68.59 415	68.28 424	42.96 424	44.55 418	75.18 381	14.09 431	68.39 430	41.36 395	51.68 395	70.78 420

ttmdpeth		53.34 390	49.96 393	63.45 400	62.07 430	40.04 425	72.06 405	65.64 427	42.54 425	51.88 390	77.79 362	13.94 432	76.48 419	32.93 418	30.82 434	73.84 414

DSMNet-mixed		56.78 385	54.44 389	63.79 399	63.21 426	29.44 442	64.43 424	64.10 429	42.12 426	51.32 394	71.60 397	31.76 386	75.04 421	36.23 407	65.20 325	86.87 292

pmmvs3		55.51 386	51.50 392	67.53 393	57.90 434	50.93 385	80.37 372	73.66 406	40.63 427	44.15 419	64.75 416	16.30 424	78.97 417	44.77 383	40.98 418	72.69 417

new_pmnet		49.31 393	46.44 396	57.93 406	62.84 427	40.74 423	68.47 416	62.96 431	36.48 428	35.09 429	57.81 426	14.97 428	72.18 425	32.86 419	46.44 406	60.88 428

MVS-HIRNet		60.25 379	55.55 386	74.35 355	84.37 300	56.57 354	71.64 407	74.11 405	34.44 429	45.54 414	42.24 437	31.11 391	89.81 352	40.36 399	76.10 247	76.67 409

test_f		46.58 395	43.45 399	55.96 408	45.18 443	32.05 437	61.18 427	49.49 441	33.39 430	42.05 423	62.48 421	7.00 440	65.56 435	47.08 371	43.21 412	70.27 422

test_vis3_rt		40.46 402	37.79 403	48.47 419	44.49 444	33.35 436	66.56 422	32.84 450	32.39 431	29.65 432	39.13 440	3.91 448	68.65 429	50.17 351	40.99 417	43.40 435

DeepMVS_CX				34.71 426	51.45 438	24.73 446		28.48 452	31.46 432	17.49 442	52.75 428	5.80 443	42.60 447	18.18 435	19.42 440	36.81 439

MVStest1		51.35 391	46.89 395	64.74 397	65.06 424	51.10 383	67.33 420	72.58 410	30.20 433	35.30 428	74.82 383	27.70 400	69.89 428	24.44 430	24.57 437	73.22 415

FPMVS		45.64 397	43.10 401	53.23 414	51.42 439	36.46 432	64.97 423	71.91 413	29.13 434	27.53 434	61.55 423	9.83 436	65.01 437	16.00 440	55.58 385	58.22 430

PMMVS2		37.93 405	33.61 408	50.92 415	46.31 441	24.76 445	60.55 430	50.05 439	28.94 435	20.93 437	47.59 430	4.41 447	65.13 436	25.14 429	18.55 441	62.87 427

LCM-MVSNet		40.54 400	35.79 405	54.76 412	36.92 449	30.81 439	51.41 436	69.02 421	22.07 436	24.63 436	45.37 433	4.56 445	65.81 434	33.67 414	34.50 429	67.67 423

APD_test1		40.50 401	37.31 404	50.09 417	51.88 437	35.27 434	59.45 431	52.59 438	21.64 437	26.12 435	57.80 427	4.56 445	66.56 433	22.64 432	39.09 419	48.43 433

PMVS	26.43 22	31.84 409	28.16 412	42.89 422	25.87 452	27.58 443	50.92 437	49.78 440	21.37 438	14.17 444	40.81 439	2.01 451	66.62 432	9.61 444	38.88 422	34.49 440
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		34.91 406	31.44 409	45.30 421	70.99 410	39.64 429	19.85 443	72.56 411	20.10 439	16.16 443	21.47 444	5.08 444	71.16 426	13.07 441	43.70 411	25.08 441
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testf1		32.77 407	29.47 410	42.67 423	41.89 446	30.81 439	52.07 434	43.45 444	15.45 440	18.52 440	44.82 434	2.12 449	58.38 440	16.05 438	30.87 432	38.83 436

APD_test2		32.77 407	29.47 410	42.67 423	41.89 446	30.81 439	52.07 434	43.45 444	15.45 440	18.52 440	44.82 434	2.12 449	58.38 440	16.05 438	30.87 432	38.83 436

E-PMN		24.61 410	24.00 414	26.45 427	43.74 445	18.44 452	60.86 428	39.66 446	15.11 442	9.53 446	22.10 443	6.52 442	46.94 445	8.31 446	10.14 443	13.98 443

EMVS		23.76 412	23.20 416	25.46 428	41.52 448	16.90 453	60.56 429	38.79 449	14.62 443	8.99 447	20.24 446	7.35 439	45.82 446	7.25 447	9.46 444	13.64 444

MVE	24.84 23	24.35 411	19.77 417	38.09 425	34.56 451	26.92 444	26.57 441	38.87 448	11.73 444	11.37 445	27.44 441	1.37 452	50.42 444	11.41 442	14.60 442	36.93 438
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		38.59 404	35.16 407	48.89 418	54.33 435	21.35 448	45.32 439	53.71 437	7.41 445	28.74 433	51.62 429	8.70 438	52.87 442	33.73 413	32.89 430	72.47 418

wuyk23d		11.30 415	10.95 418	12.33 430	48.05 440	19.89 450	25.89 442	1.92 454	3.58 446	3.12 448	1.37 448	0.64 453	15.77 449	6.23 448	7.77 447	1.35 445

tmp_tt		22.26 413	23.75 415	17.80 429	5.23 453	12.06 454	35.26 440	39.48 447	2.82 447	18.94 438	44.20 436	22.23 416	24.64 448	36.30 406	9.31 445	16.69 442

EGC-MVSNET		42.35 399	38.09 402	55.11 410	74.57 398	46.62 409	71.63 408	55.77 434	0.04 448	0.24 449	62.70 420	14.24 430	74.91 422	17.59 437	46.06 407	43.80 434

testmvs		7.23 417	9.62 420	0.06 432	0.04 454	0.02 457	84.98 331	0.02 455	0.03 449	0.18 450	1.21 449	0.01 455	0.02 450	0.14 449	0.01 448	0.13 447

test123		6.92 418	9.21 421	0.08 431	0.03 455	0.05 456	81.65 362	0.01 456	0.02 450	0.14 451	0.85 450	0.03 454	0.02 450	0.12 450	0.00 449	0.16 446

mmdepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 449	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 449	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 449	0.00 448

uanet_test		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 449	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 449	0.00 448

cdsmvs_eth3d_5k		19.86 414	26.47 413	0.00 433	0.00 456	0.00 458	0.00 444	93.45 91	0.00 451	0.00 452	95.27 69	49.56 279	0.00 452	0.00 451	0.00 449	0.00 448

pcd_1.5k_mvsjas		4.46 419	5.95 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	53.55 238	0.00 452	0.00 451	0.00 449	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 449	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 449	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 449	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 449	0.00 448

ab-mvs-re		7.91 416	10.55 419	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	94.95 79	0.00 456	0.00 452	0.00 451	0.00 449	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 449	0.00 448

WAC-MVS						49.45 393								31.56 425

MSC_two_6792asdad				89.60 9	97.31 4	73.22 12		95.05 29					99.07 13	92.01 34	94.77 26	96.51 24

No_MVS				89.60 9	97.31 4	73.22 12		95.05 29					99.07 13	92.01 34	94.77 26	96.51 24

eth-test2					0.00 456

eth-test					0.00 456

OPU-MVS				89.97 3	97.52 3	73.15 14	96.89 6				97.00 11	83.82 2	99.15 2	95.72 6	97.63 3	97.62 2

test_0728_SECOND				88.70 18	96.45 12	70.43 34	96.64 10	94.37 57					99.15 2	91.91 37	94.90 22	96.51 24

GSMVS																94.68 105

test_part2					96.29 19	68.16 89				90.78 20

sam_mvs1												57.85 183				94.68 105

sam_mvs												54.91 222

ambc				69.61 384	61.38 431	41.35 422	49.07 438	85.86 356		50.18 400	66.40 412	10.16 435	88.14 367	45.73 377	44.20 409	79.32 393

MTGPA								92.23 142

test_post1							78.95 382				20.70 445	53.05 243	91.50 332	60.43 311

test_post											23.01 442	56.49 204	92.67 294

patchmatchnet-post											67.62 411	57.62 186	90.25 342

GG-mvs-BLEND				86.53 74	91.91 113	69.67 53	75.02 401	94.75 36		78.67 149	90.85 181	77.91 7	94.56 224	72.25 206	93.74 45	95.36 67

MTMP							93.77 94	32.52 451

test9_res														89.41 49	94.96 19	95.29 72

agg_prior2														86.41 79	94.75 30	95.33 68

agg_prior					94.16 43	66.97 122		93.31 97		84.49 78			96.75 123

test_prior4						67.18 115	93.92 83

test_prior				86.42 77	94.71 35	67.35 110		93.10 108					96.84 120			95.05 86

新几何2							91.41 200

旧先验1					91.94 109	60.74 291		91.50 186			94.36 97	65.23 83			91.84 72	94.55 112

原ACMM2							92.01 176

testdata2													96.09 153	61.26 307

segment_acmp												65.94 74

test12				87.09 52	94.60 36	68.86 68		92.91 115		82.67 100		65.44 80	97.55 67		93.69 48	94.84 97

plane_prior7					86.94 242	61.51 273

plane_prior6					87.23 234	62.32 253						50.66 266

plane_prior5								91.31 192					95.55 183	76.74 167	78.53 225	88.39 268

plane_prior4											89.14 214

plane_prior1					87.15 236

n2								0.00 457

nn								0.00 457

door-mid								66.01 426

lessismore_v0				73.72 361	72.93 405	47.83 401		61.72 432		45.86 412	73.76 386	28.63 399	89.81 352	47.75 369	31.37 431	83.53 346

test11								93.01 111

door								66.57 425

HQP5-MVS						63.66 216

BP-MVS														77.63 164

HQP4-MVS										74.18 196			95.61 177			88.63 262

HQP3-MVS								91.70 178							78.90 220

HQP2-MVS												51.63 258

NP-MVS					87.41 229	63.04 233					90.30 192

ACMMP++_ref															71.63 277

ACMMP++															69.72 286

Test By Simon												54.21 232

High-resolution multi-view benchmark