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.

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 62	99.38 230	99.37 110	99.58 117	99.62 43	99.41 14	99.87 34	99.92 17	98.81 47	100.00 1	99.97 1	99.93 27	99.94 13

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 59	99.84 32	99.44 104	99.58 117	99.69 18	99.43 11	99.98 9	99.91 23	98.62 73	100.00 1	99.97 1	99.95 18	99.90 19

test_vis1_n_1920		98.63 173	98.40 180	99.31 159	99.86 20	97.94 259	99.67 69	99.62 43	99.43 11	99.99 2	99.91 23	87.29 385	100.00 1	99.92 16	99.92 30	99.98 2

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 32	99.82 25	99.54 149	99.66 28	99.46 7	99.98 9	99.89 35	97.27 129	99.99 4	99.97 1	99.95 18	99.95 9

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 34	99.86 20	99.61 74	99.56 130	99.63 41	99.48 3	99.98 9	99.83 77	98.75 58	99.99 4	99.97 1	99.96 13	99.94 13

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 34	99.84 32	99.63 71	99.56 130	99.63 41	99.47 4	99.98 9	99.82 86	98.75 58	99.99 4	99.97 1	99.97 7	99.94 13

test_fmvsmconf_n		99.70 3	99.64 4	99.87 16	99.80 53	99.66 60	99.48 191	99.64 38	99.45 8	99.92 21	99.92 17	98.62 73	99.99 4	99.96 8	99.99 1	99.96 7

patch_mono-2		99.26 79	99.62 5	98.16 313	99.81 47	94.59 382	99.52 159	99.64 38	99.33 18	99.73 75	99.90 30	99.00 22	99.99 4	99.69 26	99.98 4	99.89 22

h-mvs33		97.70 286	97.28 308	98.97 206	99.70 109	97.27 287	99.36 249	99.45 208	98.94 63	99.66 97	99.64 203	94.93 216	99.99 4	99.48 51	84.36 416	99.65 138

xiu_mvs_v1_base_debu		99.29 73	99.27 64	99.34 152	99.63 140	98.97 166	99.12 318	99.51 125	98.86 69	99.84 40	99.47 270	98.18 100	99.99 4	99.50 46	99.31 171	99.08 251

xiu_mvs_v1_base		99.29 73	99.27 64	99.34 152	99.63 140	98.97 166	99.12 318	99.51 125	98.86 69	99.84 40	99.47 270	98.18 100	99.99 4	99.50 46	99.31 171	99.08 251

xiu_mvs_v1_base_debi		99.29 73	99.27 64	99.34 152	99.63 140	98.97 166	99.12 318	99.51 125	98.86 69	99.84 40	99.47 270	98.18 100	99.99 4	99.50 46	99.31 171	99.08 251

EPNet		98.86 144	98.71 148	99.30 164	97.20 408	98.18 241	99.62 95	98.91 353	99.28 21	98.63 316	99.81 100	95.96 176	99.99 4	99.24 78	99.72 130	99.73 103
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		99.40 55	99.28 61	99.74 68	99.67 119	99.31 120	99.52 159	98.87 360	99.55 1	99.74 73	99.80 113	96.47 159	99.98 14	99.97 1	99.97 7	99.94 13

test_cas_vis1_n_1920		99.16 93	99.01 105	99.61 96	99.81 47	98.86 186	99.65 81	99.64 38	99.39 15	99.97 18	99.94 6	93.20 286	99.98 14	99.55 39	99.91 37	99.99 1

test_vis1_n		97.92 244	97.44 284	99.34 152	99.53 173	98.08 247	99.74 46	99.49 155	99.15 26	100.00 1	99.94 6	79.51 417	99.98 14	99.88 18	99.76 122	99.97 4

xiu_mvs_v2_base		99.26 79	99.25 68	99.29 167	99.53 173	98.91 180	99.02 341	99.45 208	98.80 78	99.71 82	99.26 328	98.94 32	99.98 14	99.34 65	99.23 176	98.98 265

PS-MVSNAJ		99.32 68	99.32 47	99.30 164	99.57 161	98.94 176	98.97 355	99.46 197	98.92 66	99.71 82	99.24 330	99.01 18	99.98 14	99.35 60	99.66 140	98.97 266

QAPM		98.67 169	98.30 187	99.80 53	99.20 278	99.67 58	99.77 34	99.72 11	94.74 380	98.73 296	99.90 30	95.78 186	99.98 14	96.96 311	99.88 61	99.76 93

3Dnovator	97.25 9	99.24 84	99.05 93	99.81 50	99.12 300	99.66 60	99.84 12	99.74 10	99.09 41	98.92 269	99.90 30	95.94 179	99.98 14	98.95 108	99.92 30	99.79 80

OpenMVS	96.50 16	98.47 178	98.12 199	99.52 123	99.04 318	99.53 90	99.82 16	99.72 11	94.56 383	98.08 350	99.88 43	94.73 232	99.98 14	97.47 279	99.76 122	99.06 257

fmvsm_s_conf0.5_n_3		99.37 59	99.20 75	99.87 16	99.75 80	99.70 52	99.48 191	99.66 28	99.45 8	99.99 2	99.93 10	94.64 240	99.97 22	99.94 13	99.97 7	99.95 9

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 58	99.88 8	99.56 130	99.55 84	99.15 26	99.90 24	99.90 30	99.00 22	99.97 22	99.11 89	99.91 37	99.86 35

test_fmvsmconf0.1_n		99.55 18	99.45 25	99.86 27	99.44 212	99.65 64	99.50 175	99.61 50	99.45 8	99.87 34	99.92 17	97.31 126	99.97 22	99.95 10	99.99 1	99.97 4

test_fmvs1_n		98.41 184	98.14 196	99.21 179	99.82 43	97.71 272	99.74 46	99.49 155	99.32 19	99.99 2	99.95 3	85.32 398	99.97 22	99.82 21	99.84 87	99.96 7

CANet_DTU		98.97 134	98.87 129	99.25 174	99.33 242	98.42 233	99.08 327	99.30 290	99.16 25	99.43 157	99.75 147	95.27 203	99.97 22	98.56 175	99.95 18	99.36 223

MVS_0304		99.15 95	98.96 115	99.73 71	98.92 336	99.37 110	99.37 244	96.92 414	99.51 2	99.66 97	99.78 132	96.69 150	99.97 22	99.84 20	99.97 7	99.84 45

MTAPA		99.52 21	99.39 33	99.89 8	99.90 4	99.86 16	99.66 75	99.47 188	98.79 79	99.68 88	99.81 100	98.43 86	99.97 22	98.88 118	99.90 46	99.83 55

PGM-MVS		99.45 39	99.31 53	99.86 27	99.87 15	99.78 40	99.58 117	99.65 35	97.84 193	99.71 82	99.80 113	99.12 13	99.97 22	98.33 199	99.87 64	99.83 55

mPP-MVS		99.44 43	99.30 55	99.86 27	99.88 11	99.79 34	99.69 60	99.48 167	98.12 154	99.50 142	99.75 147	98.78 51	99.97 22	98.57 172	99.89 57	99.83 55

CP-MVS		99.45 39	99.32 47	99.85 34	99.83 40	99.75 44	99.69 60	99.52 111	98.07 164	99.53 137	99.63 209	98.93 36	99.97 22	98.74 143	99.91 37	99.83 55

SteuartSystems-ACMMP		99.54 19	99.42 26	99.87 16	99.82 43	99.81 29	99.59 109	99.51 125	98.62 94	99.79 54	99.83 77	99.28 4	99.97 22	98.48 182	99.90 46	99.84 45
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 89	98.97 111	99.82 47	99.17 292	99.68 55	99.81 20	99.51 125	99.20 23	98.72 297	99.89 35	95.68 190	99.97 22	98.86 126	99.86 72	99.81 67

fmvsm_s_conf0.5_n_2		99.32 68	99.13 82	99.89 8	99.80 53	99.77 41	99.44 210	99.58 66	99.47 4	99.99 2	99.93 10	94.04 264	99.96 34	99.96 8	99.93 27	99.93 18

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 70	99.88 8	99.52 159	99.54 93	99.13 29	99.89 26	99.89 35	98.96 25	99.96 34	99.04 97	99.90 46	99.85 39

our_new_method		99.61 8	99.52 12	99.90 5	99.76 70	99.88 8	99.52 159	99.54 93	99.13 29	99.89 26	99.89 35	98.96 25	99.96 34	99.04 97	99.90 46	99.85 39

fmvsm_s_conf0.5_n_a		99.56 17	99.47 21	99.85 34	99.83 40	99.64 70	99.52 159	99.65 35	99.10 36	99.98 9	99.92 17	97.35 125	99.96 34	99.94 13	99.92 30	99.95 9

fmvsm_s_conf0.5_n		99.51 22	99.40 31	99.85 34	99.84 32	99.65 64	99.51 168	99.67 23	99.13 29	99.98 9	99.92 17	96.60 153	99.96 34	99.95 10	99.96 13	99.95 9

mvsany_test1		99.50 24	99.46 24	99.62 95	99.61 150	99.09 149	98.94 361	99.48 167	99.10 36	99.96 19	99.91 23	98.85 42	99.96 34	99.72 24	99.58 150	99.82 60

test_fmvs1		98.88 140	98.79 141	99.16 184	99.69 113	97.61 276	99.55 144	99.49 155	99.32 19	99.98 9	99.91 23	91.41 334	99.96 34	99.82 21	99.92 30	99.90 19

DVP-MVS++		99.59 12	99.50 17	99.88 10	99.51 182	99.88 8	99.87 8	99.51 125	98.99 54	99.88 29	99.81 100	99.27 5	99.96 34	98.85 128	99.80 107	99.81 67

MSC_two_6792asdad				99.87 16	99.51 182	99.76 42		99.33 272					99.96 34	98.87 121	99.84 87	99.89 22

No_MVS				99.87 16	99.51 182	99.76 42		99.33 272					99.96 34	98.87 121	99.84 87	99.89 22

ZD-MVS					99.71 104	99.79 34		99.61 50	96.84 298	99.56 130	99.54 243	98.58 75	99.96 34	96.93 314	99.75 124

SED-MVS		99.61 8	99.52 12	99.88 10	99.84 32	99.90 2	99.60 102	99.48 167	99.08 42	99.91 22	99.81 100	99.20 7	99.96 34	98.91 115	99.85 79	99.79 80

test_241102_TWO								99.48 167	99.08 42	99.88 29	99.81 100	98.94 32	99.96 34	98.91 115	99.84 87	99.88 28

ZNCC-MVS		99.47 33	99.33 45	99.87 16	99.87 15	99.81 29	99.64 84	99.67 23	98.08 163	99.55 134	99.64 203	98.91 37	99.96 34	98.72 146	99.90 46	99.82 60

DVP-MVS		99.57 16	99.47 21	99.88 10	99.85 26	99.89 4	99.57 124	99.37 252	99.10 36	99.81 48	99.80 113	98.94 32	99.96 34	98.93 112	99.86 72	99.81 67
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_THIRD									98.99 54	99.81 48	99.80 113	99.09 14	99.96 34	98.85 128	99.90 46	99.88 28

test_0728_SECOND				99.91 3	99.84 32	99.89 4	99.57 124	99.51 125					99.96 34	98.93 112	99.86 72	99.88 28

SR-MVS		99.43 46	99.29 59	99.86 27	99.75 80	99.83 19	99.59 109	99.62 43	98.21 141	99.73 75	99.79 125	98.68 67	99.96 34	98.44 188	99.77 119	99.79 80

DPE-MVS		99.46 35	99.32 47	99.91 3	99.78 58	99.88 8	99.36 249	99.51 125	98.73 86	99.88 29	99.84 72	98.72 64	99.96 34	98.16 213	99.87 64	99.88 28
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 48	99.29 59	99.80 53	99.62 146	99.55 85	99.50 175	99.70 15	98.79 79	99.77 63	99.96 1	97.45 120	99.96 34	98.92 114	99.90 46	99.89 22

HFP-MVS		99.49 26	99.37 37	99.86 27	99.87 15	99.80 31	99.66 75	99.67 23	98.15 148	99.68 88	99.69 177	99.06 16	99.96 34	98.69 151	99.87 64	99.84 45

region2R		99.48 30	99.35 41	99.87 16	99.88 11	99.80 31	99.65 81	99.66 28	98.13 153	99.66 97	99.68 184	98.96 25	99.96 34	98.62 160	99.87 64	99.84 45

HPM-MVS++		99.39 57	99.23 72	99.87 16	99.75 80	99.84 18	99.43 215	99.51 125	98.68 91	99.27 199	99.53 247	98.64 72	99.96 34	98.44 188	99.80 107	99.79 80

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 66	99.89 4	99.75 42	99.56 76	99.02 47	99.88 29	99.85 62	99.18 10	99.96 34	99.22 79	99.92 30	99.90 19
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 26	99.36 39	99.86 27	99.87 15	99.79 34	99.66 75	99.67 23	98.15 148	99.67 92	99.69 177	98.95 30	99.96 34	98.69 151	99.87 64	99.84 45

MP-MVS		99.33 66	99.15 80	99.87 16	99.88 11	99.82 25	99.66 75	99.46 197	98.09 159	99.48 146	99.74 152	98.29 95	99.96 34	97.93 231	99.87 64	99.82 60
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 111	98.90 123	99.74 68	99.80 53	99.46 102	99.59 109	99.49 155	97.03 285	99.63 112	99.69 177	97.27 129	99.96 34	97.82 242	99.84 87	99.81 67

PVSNet_Blended_VisFu		99.36 62	99.28 61	99.61 96	99.86 20	99.07 154	99.47 199	99.93 2	97.66 216	99.71 82	99.86 56	97.73 115	99.96 34	99.47 53	99.82 100	99.79 80

UGNet		98.87 141	98.69 150	99.40 144	99.22 275	98.72 200	99.44 210	99.68 20	99.24 22	99.18 224	99.42 281	92.74 296	99.96 34	99.34 65	99.94 25	99.53 179
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
CSCG		99.32 68	99.32 47	99.32 158	99.85 26	98.29 236	99.71 55	99.66 28	98.11 156	99.41 164	99.80 113	98.37 92	99.96 34	98.99 103	99.96 13	99.72 111

ACMMP		99.45 39	99.32 47	99.82 47	99.89 8	99.67 58	99.62 95	99.69 18	98.12 154	99.63 112	99.84 72	98.73 63	99.96 34	98.55 178	99.83 96	99.81 67
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
fmvsm_s_conf0.5_n_4		99.36 62	99.24 69	99.73 71	99.78 58	99.53 90	99.49 186	99.60 56	99.42 13	99.99 2	99.86 56	95.15 209	99.95 65	99.95 10	99.89 57	99.73 103

fmvsm_s_conf0.1_n_2		99.37 59	99.22 73	99.81 50	99.77 66	99.75 44	99.46 202	99.60 56	99.47 4	99.98 9	99.94 6	94.98 213	99.95 65	99.97 1	99.79 114	99.73 103

test_fmvsmconf0.01_n		99.22 86	99.03 97	99.79 56	98.42 388	99.48 99	99.55 144	99.51 125	99.39 15	99.78 59	99.93 10	94.80 224	99.95 65	99.93 15	99.95 18	99.94 13

SR-MVS-dyc-post		99.45 39	99.31 53	99.85 34	99.76 70	99.82 25	99.63 90	99.52 111	98.38 117	99.76 69	99.82 86	98.53 79	99.95 65	98.61 163	99.81 103	99.77 88

GST-MVS		99.40 55	99.24 69	99.85 34	99.86 20	99.79 34	99.60 102	99.67 23	97.97 178	99.63 112	99.68 184	98.52 80	99.95 65	98.38 192	99.86 72	99.81 67

CANet		99.25 83	99.14 81	99.59 99	99.41 220	99.16 139	99.35 254	99.57 71	98.82 74	99.51 141	99.61 218	96.46 160	99.95 65	99.59 34	99.98 4	99.65 138

MP-MVS-pluss		99.37 59	99.20 75	99.88 10	99.90 4	99.87 15	99.30 266	99.52 111	97.18 267	99.60 122	99.79 125	98.79 50	99.95 65	98.83 134	99.91 37	99.83 55
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 48	99.27 64	99.88 10	99.89 8	99.80 31	99.67 69	99.50 145	98.70 88	99.77 63	99.49 261	98.21 98	99.95 65	98.46 186	99.77 119	99.88 28
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
testdata2													99.95 65	96.67 326

APD-MVS_3200maxsize		99.48 30	99.35 41	99.85 34	99.76 70	99.83 19	99.63 90	99.54 93	98.36 121	99.79 54	99.82 86	98.86 41	99.95 65	98.62 160	99.81 103	99.78 86

RPMNet		96.72 337	95.90 350	99.19 181	99.18 284	98.49 225	99.22 301	99.52 111	88.72 416	99.56 130	97.38 410	94.08 263	99.95 65	86.87 418	98.58 223	99.14 243

sss		99.17 91	99.05 93	99.53 117	99.62 146	98.97 166	99.36 249	99.62 43	97.83 194	99.67 92	99.65 197	97.37 124	99.95 65	99.19 81	99.19 179	99.68 128

MVSMamba_PlusPlus		99.46 35	99.41 30	99.64 88	99.68 117	99.50 96	99.75 42	99.50 145	98.27 131	99.87 34	99.92 17	98.09 104	99.94 77	99.65 30	99.95 18	99.47 200

fmvsm_s_conf0.1_n_a		99.26 79	99.06 92	99.85 34	99.52 179	99.62 72	99.54 149	99.62 43	98.69 89	99.99 2	99.96 1	94.47 249	99.94 77	99.88 18	99.92 30	99.98 2

fmvsm_s_conf0.1_n		99.29 73	99.10 86	99.86 27	99.70 109	99.65 64	99.53 158	99.62 43	98.74 85	99.99 2	99.95 3	94.53 247	99.94 77	99.89 17	99.96 13	99.97 4

TSAR-MVS + MP.		99.58 13	99.50 17	99.81 50	99.91 1	99.66 60	99.63 90	99.39 236	98.91 67	99.78 59	99.85 62	99.36 2	99.94 77	98.84 131	99.88 61	99.82 60
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 138	98.75 144	99.39 148	99.46 205	98.61 211	99.76 37	99.50 145	98.06 168	99.81 48	99.88 43	93.91 271	99.94 77	99.11 89	99.27 174	99.61 154

mamv4		99.33 66	99.42 26	99.07 192	99.67 119	97.73 267	99.42 222	99.60 56	98.15 148	99.94 20	99.91 23	98.42 88	99.94 77	99.72 24	99.96 13	99.54 173

XVS		99.53 20	99.42 26	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 57	99.37 175	99.74 152	98.81 47	99.94 77	98.79 139	99.86 72	99.84 45

X-MVStestdata		96.55 340	95.45 359	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 57	99.37 175	64.01 433	98.81 47	99.94 77	98.79 139	99.86 72	99.84 45

旧先验2							98.96 356		96.70 305	99.47 147			99.94 77	98.19 209

新几何1				99.75 65	99.75 80	99.59 77		99.54 93	96.76 301	99.29 193	99.64 203	98.43 86	99.94 77	96.92 316	99.66 140	99.72 111

testdata				99.54 109	99.75 80	98.95 173		99.51 125	97.07 279	99.43 157	99.70 167	98.87 40	99.94 77	97.76 249	99.64 143	99.72 111

HPM-MVS		99.42 48	99.28 61	99.83 46	99.90 4	99.72 48	99.81 20	99.54 93	97.59 222	99.68 88	99.63 209	98.91 37	99.94 77	98.58 169	99.91 37	99.84 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 87	99.10 86	99.45 137	99.89 8	98.52 221	99.39 237	99.94 1	98.73 86	99.11 233	99.89 35	95.50 195	99.94 77	99.50 46	99.97 7	99.89 22

APD-MVS		99.27 77	99.08 90	99.84 45	99.75 80	99.79 34	99.50 175	99.50 145	97.16 269	99.77 63	99.82 86	98.78 51	99.94 77	97.56 270	99.86 72	99.80 76
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 30	99.42 26	99.65 82	99.72 99	99.40 109	99.05 333	99.66 28	99.14 28	99.57 129	99.80 113	98.46 84	99.94 77	99.57 37	99.84 87	99.60 157
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
WTY-MVS		99.06 120	98.88 128	99.61 96	99.62 146	99.16 139	99.37 244	99.56 76	98.04 171	99.53 137	99.62 214	96.84 144	99.94 77	98.85 128	98.49 231	99.72 111

DeepC-MVS	98.35 2	99.30 71	99.19 77	99.64 88	99.82 43	99.23 132	99.62 95	99.55 84	98.94 63	99.63 112	99.95 3	95.82 185	99.94 77	99.37 59	99.97 7	99.73 103
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LS3D		99.27 77	99.12 84	99.74 68	99.18 284	99.75 44	99.56 130	99.57 71	98.45 110	99.49 145	99.85 62	97.77 114	99.94 77	98.33 199	99.84 87	99.52 180

GDP-MVS		99.08 117	98.89 126	99.64 88	99.53 173	99.34 114	99.64 84	99.48 167	98.32 126	99.77 63	99.66 195	95.14 210	99.93 95	98.97 107	99.50 156	99.64 145

SDMVSNet		99.11 111	98.90 123	99.75 65	99.81 47	99.59 77	99.81 20	99.65 35	98.78 82	99.64 109	99.88 43	94.56 243	99.93 95	99.67 28	98.26 244	99.72 111

FE-MVS		98.48 177	98.17 192	99.40 144	99.54 172	98.96 170	99.68 66	98.81 367	95.54 364	99.62 116	99.70 167	93.82 274	99.93 95	97.35 288	99.46 158	99.32 229

SF-MVS		99.38 58	99.24 69	99.79 56	99.79 56	99.68 55	99.57 124	99.54 93	97.82 198	99.71 82	99.80 113	98.95 30	99.93 95	98.19 209	99.84 87	99.74 98

dcpmvs_2		99.23 85	99.58 7	98.16 313	99.83 40	94.68 380	99.76 37	99.52 111	99.07 44	99.98 9	99.88 43	98.56 77	99.93 95	99.67 28	99.98 4	99.87 33

Anonymous20240529		98.09 214	97.68 252	99.34 152	99.66 129	98.44 230	99.40 233	99.43 222	93.67 390	99.22 211	99.89 35	90.23 351	99.93 95	99.26 77	98.33 238	99.66 134

ACMMP_NAP		99.47 33	99.34 43	99.88 10	99.87 15	99.86 16	99.47 199	99.48 167	98.05 170	99.76 69	99.86 56	98.82 46	99.93 95	98.82 138	99.91 37	99.84 45

EI-MVSNet-UG-set		99.58 13	99.57 8	99.64 88	99.78 58	99.14 144	99.60 102	99.45 208	99.01 49	99.90 24	99.83 77	98.98 24	99.93 95	99.59 34	99.95 18	99.86 35

无先验							98.99 349	99.51 125	96.89 295				99.93 95	97.53 273		99.72 111

VDDNet		97.55 301	97.02 322	99.16 184	99.49 195	98.12 246	99.38 242	99.30 290	95.35 366	99.68 88	99.90 30	82.62 410	99.93 95	99.31 69	98.13 256	99.42 212

ab-mvs		98.86 144	98.63 157	99.54 109	99.64 137	99.19 134	99.44 210	99.54 93	97.77 202	99.30 190	99.81 100	94.20 257	99.93 95	99.17 85	98.82 211	99.49 193

F-COLMAP		99.19 87	99.04 95	99.64 88	99.78 58	99.27 127	99.42 222	99.54 93	97.29 258	99.41 164	99.59 223	98.42 88	99.93 95	98.19 209	99.69 135	99.73 103

BP-MVS1		99.12 106	98.94 119	99.65 82	99.51 182	99.30 122	99.67 69	98.92 348	98.48 106	99.84 40	99.69 177	94.96 214	99.92 107	99.62 33	99.79 114	99.71 120

Anonymous202405211		98.30 195	97.98 216	99.26 173	99.57 161	98.16 242	99.41 225	98.55 391	96.03 358	99.19 220	99.74 152	91.87 321	99.92 107	99.16 86	98.29 243	99.70 122

EI-MVSNet-Vis-set		99.58 13	99.56 10	99.64 88	99.78 58	99.15 143	99.61 101	99.45 208	99.01 49	99.89 26	99.82 86	99.01 18	99.92 107	99.56 38	99.95 18	99.85 39

VDD-MVS		97.73 280	97.35 296	98.88 226	99.47 203	97.12 295	99.34 257	98.85 362	98.19 143	99.67 92	99.85 62	82.98 408	99.92 107	99.49 50	98.32 242	99.60 157

VNet		99.11 111	98.90 123	99.73 71	99.52 179	99.56 83	99.41 225	99.39 236	99.01 49	99.74 73	99.78 132	95.56 193	99.92 107	99.52 44	98.18 252	99.72 111

XVG-OURS-SEG-HR		98.69 167	98.62 162	98.89 224	99.71 104	97.74 266	99.12 318	99.54 93	98.44 113	99.42 160	99.71 163	94.20 257	99.92 107	98.54 179	98.90 205	99.00 262

mvsmamba		99.06 120	98.96 115	99.36 150	99.47 203	98.64 207	99.70 56	99.05 332	97.61 221	99.65 104	99.83 77	96.54 156	99.92 107	99.19 81	99.62 146	99.51 188

HPM-MVS_fast		99.51 22	99.40 31	99.85 34	99.91 1	99.79 34	99.76 37	99.56 76	97.72 207	99.76 69	99.75 147	99.13 12	99.92 107	99.07 95	99.92 30	99.85 39

HY-MVS	97.30 7	98.85 151	98.64 156	99.47 134	99.42 215	99.08 152	99.62 95	99.36 253	97.39 250	99.28 194	99.68 184	96.44 162	99.92 107	98.37 194	98.22 247	99.40 217

DP-MVS		99.16 93	98.95 117	99.78 59	99.77 66	99.53 90	99.41 225	99.50 145	97.03 285	99.04 250	99.88 43	97.39 121	99.92 107	98.66 155	99.90 46	99.87 33

IB-MVS	95.67 18	96.22 346	95.44 360	98.57 265	99.21 276	96.70 323	98.65 390	97.74 408	96.71 304	97.27 374	98.54 385	86.03 392	99.92 107	98.47 185	86.30 414	99.10 246
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
DeepC-MVS_fast	98.69 1	99.49 26	99.39 33	99.77 62	99.63 140	99.59 77	99.36 249	99.46 197	99.07 44	99.79 54	99.82 86	98.85 42	99.92 107	98.68 153	99.87 64	99.82 60
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
balanced_conf03		99.46 35	99.39 33	99.67 77	99.55 169	99.58 82	99.74 46	99.51 125	98.42 114	99.87 34	99.84 72	98.05 107	99.91 119	99.58 36	99.94 25	99.52 180

9.14			99.10 86		99.72 99		99.40 233	99.51 125	97.53 232	99.64 109	99.78 132	98.84 44	99.91 119	97.63 261	99.82 100

SMA-MVS		99.44 43	99.30 55	99.85 34	99.73 95	99.83 19	99.56 130	99.47 188	97.45 241	99.78 59	99.82 86	99.18 10	99.91 119	98.79 139	99.89 57	99.81 67
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
TEST9					99.67 119	99.65 64	99.05 333	99.41 227	96.22 343	98.95 265	99.49 261	98.77 54	99.91 119

train_agg		99.02 126	98.77 142	99.77 62	99.67 119	99.65 64	99.05 333	99.41 227	96.28 337	98.95 265	99.49 261	98.76 55	99.91 119	97.63 261	99.72 130	99.75 94

test_8					99.67 119	99.61 74	99.03 338	99.41 227	96.28 337	98.93 268	99.48 267	98.76 55	99.91 119

agg_prior					99.67 119	99.62 72		99.40 233		98.87 278			99.91 119

原ACMM1				99.65 82	99.73 95	99.33 115		99.47 188	97.46 238	99.12 231	99.66 195	98.67 69	99.91 119	97.70 258	99.69 135	99.71 120

LFMVS		97.90 247	97.35 296	99.54 109	99.52 179	99.01 161	99.39 237	98.24 398	97.10 277	99.65 104	99.79 125	84.79 401	99.91 119	99.28 73	98.38 235	99.69 124

XVG-OURS		98.73 165	98.68 151	98.88 226	99.70 109	97.73 267	98.92 363	99.55 84	98.52 103	99.45 150	99.84 72	95.27 203	99.91 119	98.08 220	98.84 209	99.00 262

PLC	97.94 4	99.02 126	98.85 133	99.53 117	99.66 129	99.01 161	99.24 294	99.52 111	96.85 297	99.27 199	99.48 267	98.25 97	99.91 119	97.76 249	99.62 146	99.65 138
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 294	97.06 321	99.47 134	99.61 150	99.09 149	98.04 416	99.25 302	91.24 407	98.51 326	99.70 167	94.55 245	99.91 119	92.76 395	99.85 79	99.42 212
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
mmtdpeth		96.95 332	96.71 331	97.67 351	99.33 242	94.90 377	99.89 2	99.28 296	98.15 148	99.72 80	98.57 384	86.56 390	99.90 131	99.82 21	89.02 409	98.20 379

UWE-MVS		97.58 300	97.29 307	98.48 276	99.09 308	96.25 343	99.01 346	96.61 420	97.86 188	99.19 220	99.01 355	88.72 366	99.90 131	97.38 286	98.69 217	99.28 232

test_vis1_rt		95.81 356	95.65 355	96.32 382	99.67 119	91.35 409	99.49 186	96.74 418	98.25 134	95.24 397	98.10 403	74.96 418	99.90 131	99.53 42	98.85 208	97.70 403

FA-MVS(test-final)		98.75 162	98.53 173	99.41 143	99.55 169	99.05 157	99.80 25	99.01 337	96.59 319	99.58 126	99.59 223	95.39 198	99.90 131	97.78 245	99.49 157	99.28 232

MCST-MVS		99.43 46	99.30 55	99.82 47	99.79 56	99.74 47	99.29 271	99.40 233	98.79 79	99.52 139	99.62 214	98.91 37	99.90 131	98.64 157	99.75 124	99.82 60

CDPH-MVS		99.13 100	98.91 122	99.80 53	99.75 80	99.71 50	99.15 312	99.41 227	96.60 317	99.60 122	99.55 238	98.83 45	99.90 131	97.48 277	99.83 96	99.78 86

NCCC		99.34 65	99.19 77	99.79 56	99.61 150	99.65 64	99.30 266	99.48 167	98.86 69	99.21 214	99.63 209	98.72 64	99.90 131	98.25 205	99.63 145	99.80 76

114514_t		98.93 136	98.67 152	99.72 74	99.85 26	99.53 90	99.62 95	99.59 62	92.65 402	99.71 82	99.78 132	98.06 106	99.90 131	98.84 131	99.91 37	99.74 98

1112_ss		98.98 132	98.77 142	99.59 99	99.68 117	99.02 159	99.25 292	99.48 167	97.23 264	99.13 229	99.58 227	96.93 143	99.90 131	98.87 121	98.78 214	99.84 45

PHI-MVS		99.30 71	99.17 79	99.70 75	99.56 165	99.52 94	99.58 117	99.80 8	97.12 273	99.62 116	99.73 158	98.58 75	99.90 131	98.61 163	99.91 37	99.68 128

AdaColmap		99.01 130	98.80 138	99.66 78	99.56 165	99.54 87	99.18 307	99.70 15	98.18 146	99.35 181	99.63 209	96.32 165	99.90 131	97.48 277	99.77 119	99.55 171

COLMAP_ROB	97.56 6	98.86 144	98.75 144	99.17 183	99.88 11	98.53 217	99.34 257	99.59 62	97.55 228	98.70 304	99.89 35	95.83 184	99.90 131	98.10 215	99.90 46	99.08 251
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 191	98.03 211	99.31 159	99.63 140	98.56 214	99.54 149	96.75 417	97.53 232	99.73 75	99.65 197	91.25 339	99.89 143	98.62 160	99.56 151	99.48 194

tttt0517		98.42 182	98.14 196	99.28 171	99.66 129	98.38 234	99.74 46	96.85 415	97.68 213	99.79 54	99.74 152	91.39 335	99.89 143	98.83 134	99.56 151	99.57 168

test12				99.75 65	99.64 137	99.61 74		99.29 294		99.21 214		98.38 91	99.89 143		99.74 127	99.74 98

Test_1112_low_res		98.89 139	98.66 155	99.57 104	99.69 113	98.95 173	99.03 338	99.47 188	96.98 287	99.15 227	99.23 331	96.77 147	99.89 143	98.83 134	98.78 214	99.86 35

CNLPA		99.14 98	98.99 107	99.59 99	99.58 159	99.41 108	99.16 309	99.44 216	98.45 110	99.19 220	99.49 261	98.08 105	99.89 143	97.73 253	99.75 124	99.48 194

sd_testset		98.75 162	98.57 169	99.29 167	99.81 47	98.26 238	99.56 130	99.62 43	98.78 82	99.64 109	99.88 43	92.02 318	99.88 148	99.54 40	98.26 244	99.72 111

APD_test1		95.87 354	96.49 336	94.00 389	99.53 173	84.01 418	99.54 149	99.32 282	95.91 360	97.99 355	99.85 62	85.49 396	99.88 148	91.96 398	98.84 209	98.12 383

diffmvs		99.14 98	99.02 101	99.51 125	99.61 150	98.96 170	99.28 276	99.49 155	98.46 108	99.72 80	99.71 163	96.50 158	99.88 148	99.31 69	99.11 186	99.67 131
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS		98.86 144	98.80 138	99.03 198	99.76 70	98.79 195	99.28 276	99.91 3	97.42 247	99.67 92	99.37 298	97.53 118	99.88 148	98.98 104	97.29 303	98.42 364

PVSNet_Blended		99.08 117	98.97 111	99.42 142	99.76 70	98.79 195	98.78 377	99.91 3	96.74 302	99.67 92	99.49 261	97.53 118	99.88 148	98.98 104	99.85 79	99.60 157

MVS		97.28 321	96.55 334	99.48 131	98.78 355	98.95 173	99.27 281	99.39 236	83.53 420	98.08 350	99.54 243	96.97 141	99.87 153	94.23 376	99.16 180	99.63 150

MG-MVS		99.13 100	99.02 101	99.45 137	99.57 161	98.63 208	99.07 328	99.34 265	98.99 54	99.61 119	99.82 86	97.98 109	99.87 153	97.00 307	99.80 107	99.85 39

MSDG		98.98 132	98.80 138	99.53 117	99.76 70	99.19 134	98.75 380	99.55 84	97.25 261	99.47 147	99.77 140	97.82 112	99.87 153	96.93 314	99.90 46	99.54 173

ETV-MVS		99.26 79	99.21 74	99.40 144	99.46 205	99.30 122	99.56 130	99.52 111	98.52 103	99.44 155	99.27 326	98.41 90	99.86 156	99.10 92	99.59 149	99.04 258

thisisatest0515		98.14 209	97.79 235	99.19 181	99.50 193	98.50 224	98.61 392	96.82 416	96.95 291	99.54 135	99.43 279	91.66 330	99.86 156	98.08 220	99.51 155	99.22 240

thres600view7		97.86 253	97.51 270	98.92 215	99.72 99	97.95 257	99.59 109	98.74 376	97.94 180	99.27 199	98.62 381	91.75 324	99.86 156	93.73 382	98.19 251	98.96 268

lupinMVS		99.13 100	99.01 105	99.46 136	99.51 182	98.94 176	99.05 333	99.16 317	97.86 188	99.80 52	99.56 235	97.39 121	99.86 156	98.94 109	99.85 79	99.58 165

PVSNet	96.02 17	98.85 151	98.84 135	98.89 224	99.73 95	97.28 286	98.32 408	99.60 56	97.86 188	99.50 142	99.57 232	96.75 148	99.86 156	98.56 175	99.70 134	99.54 173

MAR-MVS		98.86 144	98.63 157	99.54 109	99.37 233	99.66 60	99.45 204	99.54 93	96.61 314	99.01 253	99.40 289	97.09 134	99.86 156	97.68 260	99.53 154	99.10 246
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
testing91		97.44 313	97.02 322	98.71 253	99.18 284	96.89 317	99.19 305	99.04 333	97.78 201	98.31 337	98.29 395	85.41 397	99.85 162	98.01 226	97.95 261	99.39 218

test2506		96.81 336	96.65 332	97.29 363	99.74 88	92.21 406	99.60 102	85.06 437	99.13 29	99.77 63	99.93 10	87.82 383	99.85 162	99.38 58	99.38 163	99.80 76

AllTest		98.87 141	98.72 146	99.31 159	99.86 20	98.48 227	99.56 130	99.61 50	97.85 191	99.36 178	99.85 62	95.95 177	99.85 162	96.66 327	99.83 96	99.59 161

TestCases				99.31 159	99.86 20	98.48 227		99.61 50	97.85 191	99.36 178	99.85 62	95.95 177	99.85 162	96.66 327	99.83 96	99.59 161

jason		99.13 100	99.03 97	99.45 137	99.46 205	98.87 183	99.12 318	99.26 300	98.03 173	99.79 54	99.65 197	97.02 139	99.85 162	99.02 101	99.90 46	99.65 138
jason: jason.
CNVR-MVS		99.42 48	99.30 55	99.78 59	99.62 146	99.71 50	99.26 290	99.52 111	98.82 74	99.39 171	99.71 163	98.96 25	99.85 162	98.59 168	99.80 107	99.77 88

PAPM_NR		99.04 123	98.84 135	99.66 78	99.74 88	99.44 104	99.39 237	99.38 244	97.70 211	99.28 194	99.28 323	98.34 93	99.85 162	96.96 311	99.45 159	99.69 124

testing99		97.36 316	96.94 325	98.63 258	99.18 284	96.70 323	99.30 266	98.93 345	97.71 208	98.23 342	98.26 396	84.92 400	99.84 169	98.04 225	97.85 268	99.35 224

testing222		97.16 326	96.50 335	99.16 184	99.16 294	98.47 229	99.27 281	98.66 387	97.71 208	98.23 342	98.15 399	82.28 413	99.84 169	97.36 287	97.66 274	99.18 242

test1111		98.04 224	98.11 200	97.83 341	99.74 88	93.82 391	99.58 117	95.40 424	99.12 34	99.65 104	99.93 10	90.73 344	99.84 169	99.43 56	99.38 163	99.82 60

ECVR-MVS		98.04 224	98.05 209	98.00 326	99.74 88	94.37 386	99.59 109	94.98 425	99.13 29	99.66 97	99.93 10	90.67 345	99.84 169	99.40 57	99.38 163	99.80 76

test_yl		98.86 144	98.63 157	99.54 109	99.49 195	99.18 136	99.50 175	99.07 329	98.22 139	99.61 119	99.51 255	95.37 199	99.84 169	98.60 166	98.33 238	99.59 161

DCV-MVSNet		98.86 144	98.63 157	99.54 109	99.49 195	99.18 136	99.50 175	99.07 329	98.22 139	99.61 119	99.51 255	95.37 199	99.84 169	98.60 166	98.33 238	99.59 161

Fast-Effi-MVS+		98.70 166	98.43 177	99.51 125	99.51 182	99.28 125	99.52 159	99.47 188	96.11 353	99.01 253	99.34 308	96.20 169	99.84 169	97.88 234	98.82 211	99.39 218

TSAR-MVS + GP.		99.36 62	99.36 39	99.36 150	99.67 119	98.61 211	99.07 328	99.33 272	99.00 52	99.82 47	99.81 100	99.06 16	99.84 169	99.09 93	99.42 161	99.65 138

tpmrst		98.33 192	98.48 175	97.90 335	99.16 294	94.78 378	99.31 264	99.11 322	97.27 259	99.45 150	99.59 223	95.33 201	99.84 169	98.48 182	98.61 220	99.09 250

Vis-MVSNet		99.12 106	98.97 111	99.56 106	99.78 58	99.10 148	99.68 66	99.66 28	98.49 105	99.86 38	99.87 52	94.77 229	99.84 169	99.19 81	99.41 162	99.74 98
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 173	98.34 183	99.51 125	99.40 225	99.03 158	98.80 375	99.36 253	96.33 334	99.00 257	99.12 345	98.46 84	99.84 169	95.23 362	99.37 170	99.66 134

PatchMatch-RL		98.84 154	98.62 162	99.52 123	99.71 104	99.28 125	99.06 331	99.77 9	97.74 206	99.50 142	99.53 247	95.41 197	99.84 169	97.17 301	99.64 143	99.44 210

EPP-MVSNet		99.13 100	98.99 107	99.53 117	99.65 135	99.06 155	99.81 20	99.33 272	97.43 245	99.60 122	99.88 43	97.14 132	99.84 169	99.13 87	98.94 200	99.69 124

testing3-2		97.84 258	97.70 250	98.24 308	99.53 173	95.37 367	99.55 144	98.67 386	98.46 108	99.27 199	99.34 308	86.58 389	99.83 182	99.32 68	98.63 219	99.52 180

testing11		97.50 306	97.10 319	98.71 253	99.20 278	96.91 315	99.29 271	98.82 365	97.89 185	98.21 345	98.40 390	85.63 395	99.83 182	98.45 187	98.04 259	99.37 222

thres100view900		97.76 272	97.45 279	98.69 255	99.72 99	97.86 263	99.59 109	98.74 376	97.93 181	99.26 204	98.62 381	91.75 324	99.83 182	93.22 387	98.18 252	98.37 370

tfpn200view9		97.72 282	97.38 292	98.72 251	99.69 113	97.96 255	99.50 175	98.73 382	97.83 194	99.17 225	98.45 388	91.67 328	99.83 182	93.22 387	98.18 252	98.37 370

test_prior				99.68 76	99.67 119	99.48 99		99.56 76					99.83 182			99.74 98

1314		98.68 168	98.54 172	99.11 190	98.89 339	98.65 205	99.27 281	99.49 155	96.89 295	97.99 355	99.56 235	97.72 116	99.83 182	97.74 252	99.27 174	98.84 274

thres400		97.77 271	97.38 292	98.92 215	99.69 113	97.96 255	99.50 175	98.73 382	97.83 194	99.17 225	98.45 388	91.67 328	99.83 182	93.22 387	98.18 252	98.96 268

casdiffmvs		99.13 100	98.98 110	99.56 106	99.65 135	99.16 139	99.56 130	99.50 145	98.33 125	99.41 164	99.86 56	95.92 180	99.83 182	99.45 55	99.16 180	99.70 122
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SPE-MVS-test		99.49 26	99.48 19	99.54 109	99.78 58	99.30 122	99.89 2	99.58 66	98.56 99	99.73 75	99.69 177	98.55 78	99.82 190	99.69 26	99.85 79	99.48 194

MVS_Test		99.10 115	98.97 111	99.48 131	99.49 195	99.14 144	99.67 69	99.34 265	97.31 256	99.58 126	99.76 144	97.65 117	99.82 190	98.87 121	99.07 192	99.46 205

dp		97.75 276	97.80 234	97.59 355	99.10 305	93.71 394	99.32 261	98.88 358	96.48 326	99.08 241	99.55 238	92.67 302	99.82 190	96.52 331	98.58 223	99.24 238

RPSCF		98.22 199	98.62 162	96.99 369	99.82 43	91.58 408	99.72 52	99.44 216	96.61 314	99.66 97	99.89 35	95.92 180	99.82 190	97.46 280	99.10 189	99.57 168

PMMVS		98.80 158	98.62 162	99.34 152	99.27 260	98.70 201	98.76 379	99.31 286	97.34 253	99.21 214	99.07 347	97.20 131	99.82 190	98.56 175	98.87 206	99.52 180

UBG		97.85 254	97.48 273	98.95 209	99.25 267	97.64 274	99.24 294	98.74 376	97.90 184	98.64 314	98.20 398	88.65 370	99.81 195	98.27 204	98.40 233	99.42 212

EIA-MVS		99.18 89	99.09 89	99.45 137	99.49 195	99.18 136	99.67 69	99.53 106	97.66 216	99.40 169	99.44 277	98.10 103	99.81 195	98.94 109	99.62 146	99.35 224

Effi-MVS+		98.81 155	98.59 168	99.48 131	99.46 205	99.12 147	98.08 415	99.50 145	97.50 236	99.38 173	99.41 285	96.37 164	99.81 195	99.11 89	98.54 228	99.51 188

thres200		97.61 298	97.28 308	98.62 259	99.64 137	98.03 249	99.26 290	98.74 376	97.68 213	99.09 239	98.32 394	91.66 330	99.81 195	92.88 392	98.22 247	98.03 389

tpmvs		97.98 235	98.02 213	97.84 340	99.04 318	94.73 379	99.31 264	99.20 312	96.10 357	98.76 294	99.42 281	94.94 215	99.81 195	96.97 310	98.45 232	98.97 266

casdiffmvs_mvg		99.15 95	99.02 101	99.55 108	99.66 129	99.09 149	99.64 84	99.56 76	98.26 133	99.45 150	99.87 52	96.03 174	99.81 195	99.54 40	99.15 183	99.73 103
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepPCF-MVS	98.18 3	98.81 155	99.37 37	97.12 367	99.60 155	91.75 407	98.61 392	99.44 216	99.35 17	99.83 46	99.85 62	98.70 66	99.81 195	99.02 101	99.91 37	99.81 67

DPM-MVS		98.95 135	98.71 148	99.66 78	99.63 140	99.55 85	98.64 391	99.10 323	97.93 181	99.42 160	99.55 238	98.67 69	99.80 202	95.80 347	99.68 138	99.61 154

DP-MVS Recon		99.12 106	98.95 117	99.65 82	99.74 88	99.70 52	99.27 281	99.57 71	96.40 333	99.42 160	99.68 184	98.75 58	99.80 202	97.98 228	99.72 130	99.44 210

MVS_111021_LR		99.41 52	99.33 45	99.65 82	99.77 66	99.51 95	98.94 361	99.85 6	98.82 74	99.65 104	99.74 152	98.51 81	99.80 202	98.83 134	99.89 57	99.64 145

CS-MVS		99.50 24	99.48 19	99.54 109	99.76 70	99.42 106	99.90 1	99.55 84	98.56 99	99.78 59	99.70 167	98.65 71	99.79 205	99.65 30	99.78 116	99.41 215

Fast-Effi-MVS+-dtu		98.77 161	98.83 137	98.60 260	99.41 220	96.99 309	99.52 159	99.49 155	98.11 156	99.24 206	99.34 308	96.96 142	99.79 205	97.95 230	99.45 159	99.02 261

baseline1		98.31 193	97.95 220	99.38 149	99.50 193	98.74 198	99.59 109	98.93 345	98.41 115	99.14 228	99.60 221	94.59 241	99.79 205	98.48 182	93.29 385	99.61 154

baseline		99.15 95	99.02 101	99.53 117	99.66 129	99.14 144	99.72 52	99.48 167	98.35 122	99.42 160	99.84 72	96.07 172	99.79 205	99.51 45	99.14 184	99.67 131

PVSNet_0	94.43 19	96.09 351	95.47 358	97.94 331	99.31 250	94.34 388	97.81 417	99.70 15	97.12 273	97.46 368	98.75 378	89.71 356	99.79 205	97.69 259	81.69 420	99.68 128

API-MVS		99.04 123	99.03 97	99.06 194	99.40 225	99.31 120	99.55 144	99.56 76	98.54 101	99.33 185	99.39 293	98.76 55	99.78 210	96.98 309	99.78 116	98.07 386

OMC-MVS		99.08 117	99.04 95	99.20 180	99.67 119	98.22 240	99.28 276	99.52 111	98.07 164	99.66 97	99.81 100	97.79 113	99.78 210	97.79 244	99.81 103	99.60 157

GeoE		98.85 151	98.62 162	99.53 117	99.61 150	99.08 152	99.80 25	99.51 125	97.10 277	99.31 187	99.78 132	95.23 207	99.77 212	98.21 207	99.03 195	99.75 94

alignmvs		98.81 155	98.56 171	99.58 102	99.43 213	99.42 106	99.51 168	98.96 343	98.61 95	99.35 181	98.92 368	94.78 226	99.77 212	99.35 60	98.11 257	99.54 173

tpm cat1		97.39 315	97.36 294	97.50 358	99.17 292	93.73 393	99.43 215	99.31 286	91.27 406	98.71 298	99.08 346	94.31 255	99.77 212	96.41 336	98.50 230	99.00 262

CostFormer		97.72 282	97.73 247	97.71 349	99.15 298	94.02 390	99.54 149	99.02 336	94.67 381	99.04 250	99.35 304	92.35 314	99.77 212	98.50 181	97.94 262	99.34 227

MGCFI-Net		99.01 130	98.85 133	99.50 130	99.42 215	99.26 128	99.82 16	99.48 167	98.60 96	99.28 194	98.81 373	97.04 138	99.76 216	99.29 72	97.87 266	99.47 200

test_241102_ONE					99.84 32	99.90 2		99.48 167	99.07 44	99.91 22	99.74 152	99.20 7	99.76 216

MDTV_nov1_ep13			98.32 185		99.11 302	94.44 384	99.27 281	98.74 376	97.51 235	99.40 169	99.62 214	94.78 226	99.76 216	97.59 264	98.81 213

sasdasda		99.02 126	98.86 131	99.51 125	99.42 215	99.32 116	99.80 25	99.48 167	98.63 92	99.31 187	98.81 373	97.09 134	99.75 219	99.27 75	97.90 263	99.47 200

canonicalmvs		99.02 126	98.86 131	99.51 125	99.42 215	99.32 116	99.80 25	99.48 167	98.63 92	99.31 187	98.81 373	97.09 134	99.75 219	99.27 75	97.90 263	99.47 200

Effi-MVS+-dtu		98.78 159	98.89 126	98.47 281	99.33 242	96.91 315	99.57 124	99.30 290	98.47 107	99.41 164	98.99 358	96.78 146	99.74 221	98.73 145	99.38 163	98.74 289

patchmatchnet-post											98.70 379	94.79 225	99.74 221

SCA		98.19 203	98.16 193	98.27 307	99.30 251	95.55 358	99.07 328	98.97 341	97.57 225	99.43 157	99.57 232	92.72 297	99.74 221	97.58 265	99.20 178	99.52 180

BH-untuned		98.42 182	98.36 181	98.59 261	99.49 195	96.70 323	99.27 281	99.13 321	97.24 263	98.80 289	99.38 295	95.75 187	99.74 221	97.07 305	99.16 180	99.33 228

BH-RMVSNet		98.41 184	98.08 205	99.40 144	99.41 220	98.83 191	99.30 266	98.77 372	97.70 211	98.94 267	99.65 197	92.91 292	99.74 221	96.52 331	99.55 153	99.64 145

MVS_111021_HR		99.41 52	99.32 47	99.66 78	99.72 99	99.47 101	98.95 359	99.85 6	98.82 74	99.54 135	99.73 158	98.51 81	99.74 221	98.91 115	99.88 61	99.77 88

test_post											65.99 431	94.65 239	99.73 227

XVG-ACMP-BASELINE		97.83 261	97.71 249	98.20 310	99.11 302	96.33 339	99.41 225	99.52 111	98.06 168	99.05 249	99.50 258	89.64 358	99.73 227	97.73 253	97.38 301	98.53 352

HyFIR lowres test		99.11 111	98.92 120	99.65 82	99.90 4	99.37 110	99.02 341	99.91 3	97.67 215	99.59 125	99.75 147	95.90 182	99.73 227	99.53 42	99.02 197	99.86 35

DeepMVS_CX				93.34 392	99.29 255	82.27 421		99.22 308	85.15 418	96.33 389	99.05 350	90.97 342	99.73 227	93.57 384	97.77 271	98.01 390

Patchmatch-test		97.93 241	97.65 255	98.77 247	99.18 284	97.07 300	99.03 338	99.14 320	96.16 348	98.74 295	99.57 232	94.56 243	99.72 231	93.36 386	99.11 186	99.52 180

LPG-MVS_test		98.22 199	98.13 198	98.49 274	99.33 242	97.05 302	99.58 117	99.55 84	97.46 238	99.24 206	99.83 77	92.58 304	99.72 231	98.09 216	97.51 287	98.68 307

LGP-MVS_train				98.49 274	99.33 242	97.05 302		99.55 84	97.46 238	99.24 206	99.83 77	92.58 304	99.72 231	98.09 216	97.51 287	98.68 307

BH-w/o		98.00 233	97.89 229	98.32 299	99.35 237	96.20 345	99.01 346	98.90 355	96.42 331	98.38 333	99.00 356	95.26 205	99.72 231	96.06 340	98.61 220	99.03 259

ACMP	97.20 11	98.06 218	97.94 222	98.45 284	99.37 233	97.01 307	99.44 210	99.49 155	97.54 231	98.45 330	99.79 125	91.95 320	99.72 231	97.91 232	97.49 292	98.62 335
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 228	97.90 225	98.40 292	99.23 271	96.80 321	99.70 56	99.60 56	97.12 273	98.18 347	99.70 167	91.73 326	99.72 231	98.39 191	97.45 294	98.68 307
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
test_post1							99.23 297				65.14 432	94.18 260	99.71 237	97.58 265

ADS-MVSNet		98.20 202	98.08 205	98.56 268	99.33 242	96.48 334	99.23 297	99.15 318	96.24 341	99.10 236	99.67 190	94.11 261	99.71 237	96.81 319	99.05 193	99.48 194

JIA-IIPM		97.50 306	97.02 322	98.93 213	98.73 364	97.80 265	99.30 266	98.97 341	91.73 405	98.91 270	94.86 420	95.10 211	99.71 237	97.58 265	97.98 260	99.28 232

EPMVS		97.82 264	97.65 255	98.35 296	98.88 340	95.98 349	99.49 186	94.71 427	97.57 225	99.26 204	99.48 267	92.46 311	99.71 237	97.87 236	99.08 191	99.35 224

TDRefinement		95.42 360	94.57 367	97.97 328	89.83 430	96.11 348	99.48 191	98.75 373	96.74 302	96.68 386	99.88 43	88.65 370	99.71 237	98.37 194	82.74 419	98.09 385

ACMM	97.58 5	98.37 190	98.34 183	98.48 276	99.41 220	97.10 296	99.56 130	99.45 208	98.53 102	99.04 250	99.85 62	93.00 288	99.71 237	98.74 143	97.45 294	98.64 326
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 238	97.77 240	98.57 265	99.59 157	96.61 330	99.45 204	99.08 326	98.21 141	98.88 275	99.80 113	88.66 369	99.70 243	98.58 169	97.72 272	99.39 218

CHOSEN 280x420		99.12 106	99.13 82	99.08 191	99.66 129	97.89 260	98.43 402	99.71 13	98.88 68	99.62 116	99.76 144	96.63 152	99.70 243	99.46 54	99.99 1	99.66 134

EC-MVSNet		99.44 43	99.39 33	99.58 102	99.56 165	99.49 97	99.88 4	99.58 66	98.38 117	99.73 75	99.69 177	98.20 99	99.70 243	99.64 32	99.82 100	99.54 173

PatchmatchNet		98.31 193	98.36 181	98.19 311	99.16 294	95.32 368	99.27 281	98.92 348	97.37 251	99.37 175	99.58 227	94.90 219	99.70 243	97.43 283	99.21 177	99.54 173
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 213	97.99 215	98.44 287	99.41 220	96.96 313	99.60 102	99.56 76	98.09 159	98.15 348	99.91 23	90.87 343	99.70 243	98.88 118	97.45 294	98.67 314
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 306	96.90 326	99.29 167	99.23 271	98.78 197	99.32 261	98.90 355	97.52 234	98.56 323	98.09 404	84.72 402	99.69 248	97.86 237	97.88 265	99.39 218

HQP_MVS		98.27 198	98.22 191	98.44 287	99.29 255	96.97 311	99.39 237	99.47 188	98.97 60	99.11 233	99.61 218	92.71 299	99.69 248	97.78 245	97.63 275	98.67 314

plane_prior5								99.47 188					99.69 248	97.78 245	97.63 275	98.67 314

D2MVS		98.41 184	98.50 174	98.15 316	99.26 263	96.62 329	99.40 233	99.61 50	97.71 208	98.98 260	99.36 301	96.04 173	99.67 251	98.70 148	97.41 299	98.15 382

IS-MVSNet		99.05 122	98.87 129	99.57 104	99.73 95	99.32 116	99.75 42	99.20 312	98.02 175	99.56 130	99.86 56	96.54 156	99.67 251	98.09 216	99.13 185	99.73 103

CLD-MVS		98.16 207	98.10 201	98.33 297	99.29 255	96.82 320	98.75 380	99.44 216	97.83 194	99.13 229	99.55 238	92.92 290	99.67 251	98.32 201	97.69 273	98.48 356
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 323	97.30 305	97.09 368	99.43 213	93.31 399	99.73 50	98.87 360	98.83 73	99.28 194	99.80 113	84.45 403	99.66 254	97.88 234	97.45 294	98.30 372

AUN-MVS		96.88 334	96.31 340	98.59 261	99.48 202	97.04 305	99.27 281	99.22 308	97.44 244	98.51 326	99.41 285	91.97 319	99.66 254	97.71 256	83.83 417	99.07 256

UniMVSNet_ETH3D		97.32 320	96.81 328	98.87 230	99.40 225	97.46 280	99.51 168	99.53 106	95.86 361	98.54 325	99.77 140	82.44 411	99.66 254	98.68 153	97.52 286	99.50 192

OPM-MVS		98.19 203	98.10 201	98.45 284	98.88 340	97.07 300	99.28 276	99.38 244	98.57 98	99.22 211	99.81 100	92.12 316	99.66 254	98.08 220	97.54 284	98.61 344
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 244	97.78 238	98.32 299	99.46 205	96.68 327	99.56 130	99.54 93	98.41 115	97.79 364	99.87 52	90.18 352	99.66 254	98.05 224	97.18 308	98.62 335

hse-mvs2		97.50 306	97.14 316	98.59 261	99.49 195	97.05 302	99.28 276	99.22 308	98.94 63	99.66 97	99.42 281	94.93 216	99.65 259	99.48 51	83.80 418	99.08 251

VPA-MVSNet		98.29 196	97.95 220	99.30 164	99.16 294	99.54 87	99.50 175	99.58 66	98.27 131	99.35 181	99.37 298	92.53 306	99.65 259	99.35 60	94.46 367	98.72 291

TR-MVS		97.76 272	97.41 290	98.82 239	99.06 314	97.87 261	98.87 369	98.56 390	96.63 313	98.68 306	99.22 332	92.49 307	99.65 259	95.40 358	97.79 270	98.95 270

reproduce_monomvs		97.89 248	97.87 230	97.96 330	99.51 182	95.45 363	99.60 102	99.25 302	99.17 24	98.85 283	99.49 261	89.29 361	99.64 262	99.35 60	96.31 324	98.78 277

gm-plane-assit					98.54 384	92.96 401			94.65 382		99.15 340		99.64 262	97.56 270

HQP4-MVS										98.66 307			99.64 262			98.64 326

HQP-MVS		98.02 228	97.90 225	98.37 295	99.19 281	96.83 318	98.98 352	99.39 236	98.24 135	98.66 307	99.40 289	92.47 308	99.64 262	97.19 298	97.58 280	98.64 326

PAPM		97.59 299	97.09 320	99.07 192	99.06 314	98.26 238	98.30 409	99.10 323	94.88 376	98.08 350	99.34 308	96.27 167	99.64 262	89.87 406	98.92 203	99.31 230

TAPA-MVS	97.07 15	97.74 278	97.34 299	98.94 211	99.70 109	97.53 277	99.25 292	99.51 125	91.90 404	99.30 190	99.63 209	98.78 51	99.64 262	88.09 413	99.87 64	99.65 138
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 188	98.09 204	99.24 176	99.26 263	99.32 116	99.56 130	99.55 84	97.45 241	98.71 298	99.83 77	93.23 283	99.63 268	98.88 118	96.32 323	98.76 283

ITE_SJBPF				98.08 319	99.29 255	96.37 337		98.92 348	98.34 123	98.83 284	99.75 147	91.09 340	99.62 269	95.82 345	97.40 300	98.25 376

LF4IMVS		97.52 303	97.46 278	97.70 350	98.98 329	95.55 358	99.29 271	98.82 365	98.07 164	98.66 307	99.64 203	89.97 353	99.61 270	97.01 306	96.68 313	97.94 397

tpm		97.67 293	97.55 264	98.03 321	99.02 320	95.01 374	99.43 215	98.54 392	96.44 329	99.12 231	99.34 308	91.83 323	99.60 271	97.75 251	96.46 319	99.48 194

tpm2		97.44 313	97.34 299	97.74 348	99.15 298	94.36 387	99.45 204	98.94 344	93.45 395	98.90 272	99.44 277	91.35 336	99.59 272	97.31 289	98.07 258	99.29 231

baseline2		97.87 251	97.55 264	98.82 239	99.18 284	98.02 250	99.41 225	96.58 421	96.97 288	96.51 387	99.17 337	93.43 280	99.57 273	97.71 256	99.03 195	98.86 272

MS-PatchMatch		97.24 325	97.32 303	96.99 369	98.45 387	93.51 398	98.82 373	99.32 282	97.41 248	98.13 349	99.30 319	88.99 363	99.56 274	95.68 351	99.80 107	97.90 400

TinyColmap		97.12 328	96.89 327	97.83 341	99.07 312	95.52 361	98.57 395	98.74 376	97.58 224	97.81 363	99.79 125	88.16 377	99.56 274	95.10 363	97.21 306	98.39 368

USDC		97.34 318	97.20 313	97.75 346	99.07 312	95.20 370	98.51 399	99.04 333	97.99 176	98.31 337	99.86 56	89.02 362	99.55 276	95.67 352	97.36 302	98.49 355

MSLP-MVS++		99.46 35	99.47 21	99.44 141	99.60 155	99.16 139	99.41 225	99.71 13	98.98 57	99.45 150	99.78 132	99.19 9	99.54 277	99.28 73	99.84 87	99.63 150

UWE-MVS-28		97.36 316	97.24 312	97.75 346	98.84 349	94.44 384	99.24 294	97.58 410	97.98 177	99.00 257	99.00 356	91.35 336	99.53 278	93.75 381	98.39 234	99.27 236

TAMVS		99.12 106	99.08 90	99.24 176	99.46 205	98.55 215	99.51 168	99.46 197	98.09 159	99.45 150	99.82 86	98.34 93	99.51 279	98.70 148	98.93 201	99.67 131

EPNet_dtu		98.03 226	97.96 218	98.23 309	98.27 390	95.54 360	99.23 297	98.75 373	99.02 47	97.82 362	99.71 163	96.11 171	99.48 280	93.04 390	99.65 142	99.69 124
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 338	96.22 342	97.97 328	97.00 412	96.28 341	98.66 389	99.03 335	96.61 314	96.93 384	99.79 125	87.20 386	99.47 281	96.65 329	94.13 374	98.16 381

EG-PatchMatch MVS		95.97 353	95.69 354	96.81 376	97.78 397	92.79 402	99.16 309	98.93 345	96.16 348	94.08 405	99.22 332	82.72 409	99.47 281	95.67 352	97.50 289	98.17 380

myMVS_eth3d28		97.69 287	97.34 299	98.73 249	99.27 260	97.52 278	99.33 259	98.78 371	98.03 173	98.82 286	98.49 386	86.64 388	99.46 283	98.44 188	98.24 246	99.23 239

MVP-Stereo		97.81 266	97.75 245	97.99 327	97.53 401	96.60 331	98.96 356	98.85 362	97.22 265	97.23 375	99.36 301	95.28 202	99.46 283	95.51 354	99.78 116	97.92 399
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 175	98.67 152	98.30 301	99.35 237	95.59 357	99.50 175	99.55 84	98.60 96	99.39 171	99.83 77	94.48 248	99.45 285	98.75 142	98.56 226	99.85 39

test-LLR		98.06 218	97.90 225	98.55 270	98.79 352	97.10 296	98.67 386	97.75 406	97.34 253	98.61 319	98.85 370	94.45 250	99.45 285	97.25 292	99.38 163	99.10 246

TESTMET0.1,1		97.55 301	97.27 311	98.40 292	98.93 334	96.53 332	98.67 386	97.61 409	96.96 289	98.64 314	99.28 323	88.63 372	99.45 285	97.30 290	99.38 163	99.21 241

test-mter		97.49 311	97.13 318	98.55 270	98.79 352	97.10 296	98.67 386	97.75 406	96.65 309	98.61 319	98.85 370	88.23 376	99.45 285	97.25 292	99.38 163	99.10 246

mvs_anonymous		99.03 125	98.99 107	99.16 184	99.38 230	98.52 221	99.51 168	99.38 244	97.79 199	99.38 173	99.81 100	97.30 127	99.45 285	99.35 60	98.99 198	99.51 188

tfpnnormal		97.84 258	97.47 276	98.98 204	99.20 278	99.22 133	99.64 84	99.61 50	96.32 335	98.27 341	99.70 167	93.35 282	99.44 290	95.69 350	95.40 350	98.27 374

v7n		97.87 251	97.52 268	98.92 215	98.76 362	98.58 213	99.84 12	99.46 197	96.20 344	98.91 270	99.70 167	94.89 220	99.44 290	96.03 341	93.89 379	98.75 285

jajsoiax		98.43 181	98.28 188	98.88 226	98.60 379	98.43 231	99.82 16	99.53 106	98.19 143	98.63 316	99.80 113	93.22 285	99.44 290	99.22 79	97.50 289	98.77 281

mvs_tets		98.40 187	98.23 190	98.91 219	98.67 372	98.51 223	99.66 75	99.53 106	98.19 143	98.65 313	99.81 100	92.75 294	99.44 290	99.31 69	97.48 293	98.77 281

Vis-MVSNet (Re-imp)		98.87 141	98.72 146	99.31 159	99.71 104	98.88 182	99.80 25	99.44 216	97.91 183	99.36 178	99.78 132	95.49 196	99.43 294	97.91 232	99.11 186	99.62 152

OPU-MVS				99.64 88	99.56 165	99.72 48	99.60 102				99.70 167	99.27 5	99.42 295	98.24 206	99.80 107	99.79 80

Anonymous20231211		97.88 249	97.54 267	98.90 221	99.71 104	98.53 217	99.48 191	99.57 71	94.16 386	98.81 287	99.68 184	93.23 283	99.42 295	98.84 131	94.42 369	98.76 283

ttmdpeth		97.80 268	97.63 259	98.29 302	98.77 360	97.38 283	99.64 84	99.36 253	98.78 82	96.30 390	99.58 227	92.34 315	99.39 297	98.36 196	95.58 345	98.10 384

VPNet		97.84 258	97.44 284	99.01 200	99.21 276	98.94 176	99.48 191	99.57 71	98.38 117	99.28 194	99.73 158	88.89 364	99.39 297	99.19 81	93.27 386	98.71 293

nrg030		98.64 172	98.42 178	99.28 171	99.05 317	99.69 54	99.81 20	99.46 197	98.04 171	99.01 253	99.82 86	96.69 150	99.38 299	99.34 65	94.59 366	98.78 277

GA-MVS		97.85 254	97.47 276	99.00 202	99.38 230	97.99 252	98.57 395	99.15 318	97.04 284	98.90 272	99.30 319	89.83 355	99.38 299	96.70 324	98.33 238	99.62 152

UniMVSNet (Re)		98.29 196	98.00 214	99.13 189	99.00 323	99.36 113	99.49 186	99.51 125	97.95 179	98.97 262	99.13 342	96.30 166	99.38 299	98.36 196	93.34 384	98.66 322

FIs		98.78 159	98.63 157	99.23 178	99.18 284	99.54 87	99.83 15	99.59 62	98.28 129	98.79 291	99.81 100	96.75 148	99.37 302	99.08 94	96.38 321	98.78 277

PS-MVSNAJss		98.92 137	98.92 120	98.90 221	98.78 355	98.53 217	99.78 32	99.54 93	98.07 164	99.00 257	99.76 144	99.01 18	99.37 302	99.13 87	97.23 305	98.81 275

CDS-MVSNet		99.09 116	99.03 97	99.25 174	99.42 215	98.73 199	99.45 204	99.46 197	98.11 156	99.46 149	99.77 140	98.01 108	99.37 302	98.70 148	98.92 203	99.66 134
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 357	95.16 362	97.51 357	99.30 251	93.69 395	98.88 367	95.78 422	85.09 419	98.78 292	92.65 422	91.29 338	99.37 302	94.85 368	99.85 79	99.46 205

v1192		97.81 266	97.44 284	98.91 219	98.88 340	98.68 202	99.51 168	99.34 265	96.18 346	99.20 217	99.34 308	94.03 265	99.36 306	95.32 360	95.18 354	98.69 302

EI-MVSNet		98.67 169	98.67 152	98.68 256	99.35 237	97.97 253	99.50 175	99.38 244	96.93 294	99.20 217	99.83 77	97.87 110	99.36 306	98.38 192	97.56 282	98.71 293

MVSTER		98.49 176	98.32 185	99.00 202	99.35 237	99.02 159	99.54 149	99.38 244	97.41 248	99.20 217	99.73 158	93.86 273	99.36 306	98.87 121	97.56 282	98.62 335

gg-mvs-nofinetune		96.17 349	95.32 361	98.73 249	98.79 352	98.14 244	99.38 242	94.09 428	91.07 409	98.07 353	91.04 426	89.62 359	99.35 309	96.75 321	99.09 190	98.68 307

pm-mvs1		97.68 290	97.28 308	98.88 226	99.06 314	98.62 209	99.50 175	99.45 208	96.32 335	97.87 360	99.79 125	92.47 308	99.35 309	97.54 272	93.54 383	98.67 314

OurMVSNet-221017-0		97.88 249	97.77 240	98.19 311	98.71 368	96.53 332	99.88 4	99.00 338	97.79 199	98.78 292	99.94 6	91.68 327	99.35 309	97.21 294	96.99 312	98.69 302

EGC-MVSNET		82.80 391	77.86 397	97.62 353	97.91 394	96.12 347	99.33 259	99.28 296	8.40 434	25.05 435	99.27 326	84.11 404	99.33 312	89.20 408	98.22 247	97.42 408

pmmvs6		96.53 341	96.09 346	97.82 343	98.69 370	95.47 362	99.37 244	99.47 188	93.46 394	97.41 369	99.78 132	87.06 387	99.33 312	96.92 316	92.70 393	98.65 324

V42		98.06 218	97.79 235	98.86 233	98.98 329	98.84 188	99.69 60	99.34 265	96.53 321	99.30 190	99.37 298	94.67 237	99.32 314	97.57 269	94.66 364	98.42 364

lessismore_v0				97.79 345	98.69 370	95.44 365		94.75 426		95.71 396	99.87 52	88.69 368	99.32 314	95.89 344	94.93 361	98.62 335

OpenMVS_ROB	92.34 20	94.38 371	93.70 377	96.41 381	97.38 403	93.17 400	99.06 331	98.75 373	86.58 417	94.84 403	98.26 396	81.53 414	99.32 314	89.01 409	97.87 266	96.76 411

v8		97.95 240	97.63 259	98.93 213	98.95 333	98.81 194	99.80 25	99.41 227	96.03 358	99.10 236	99.42 281	94.92 218	99.30 317	96.94 313	94.08 376	98.66 322

v1921920		97.80 268	97.45 279	98.84 237	98.80 351	98.53 217	99.52 159	99.34 265	96.15 350	99.24 206	99.47 270	93.98 267	99.29 318	95.40 358	95.13 356	98.69 302

anonymousdsp		98.44 180	98.28 188	98.94 211	98.50 385	98.96 170	99.77 34	99.50 145	97.07 279	98.87 278	99.77 140	94.76 230	99.28 319	98.66 155	97.60 278	98.57 350

MVSFormer		99.17 91	99.12 84	99.29 167	99.51 182	98.94 176	99.88 4	99.46 197	97.55 228	99.80 52	99.65 197	97.39 121	99.28 319	99.03 99	99.85 79	99.65 138

test_djsdf		98.67 169	98.57 169	98.98 204	98.70 369	98.91 180	99.88 4	99.46 197	97.55 228	99.22 211	99.88 43	95.73 188	99.28 319	99.03 99	97.62 277	98.75 285

SSC-MVS3.2		97.34 318	97.15 315	97.93 332	99.02 320	95.76 354	99.48 191	99.58 66	97.62 220	99.09 239	99.53 247	87.95 379	99.27 322	96.42 334	95.66 343	98.75 285

cascas		97.69 287	97.43 288	98.48 276	98.60 379	97.30 285	98.18 413	99.39 236	92.96 398	98.41 331	98.78 377	93.77 276	99.27 322	98.16 213	98.61 220	98.86 272

v144192		97.92 244	97.60 262	98.87 230	98.83 350	98.65 205	99.55 144	99.34 265	96.20 344	99.32 186	99.40 289	94.36 252	99.26 324	96.37 337	95.03 358	98.70 298

dmvs_re		98.08 216	98.16 193	97.85 338	99.55 169	94.67 381	99.70 56	98.92 348	98.15 148	99.06 247	99.35 304	93.67 279	99.25 325	97.77 248	97.25 304	99.64 145

v2v482		98.06 218	97.77 240	98.92 215	98.90 338	98.82 192	99.57 124	99.36 253	96.65 309	99.19 220	99.35 304	94.20 257	99.25 325	97.72 255	94.97 359	98.69 302

v1240		97.69 287	97.32 303	98.79 245	98.85 347	98.43 231	99.48 191	99.36 253	96.11 353	99.27 199	99.36 301	93.76 277	99.24 327	94.46 372	95.23 353	98.70 298

WBMVS		97.74 278	97.50 271	98.46 282	99.24 269	97.43 281	99.21 303	99.42 224	97.45 241	98.96 264	99.41 285	88.83 365	99.23 328	98.94 109	96.02 329	98.71 293

v1144		97.98 235	97.69 251	98.85 236	98.87 343	98.66 204	99.54 149	99.35 260	96.27 339	99.23 210	99.35 304	94.67 237	99.23 328	96.73 322	95.16 355	98.68 307

v10		97.85 254	97.52 268	98.86 233	98.99 326	98.67 203	99.75 42	99.41 227	95.70 362	98.98 260	99.41 285	94.75 231	99.23 328	96.01 343	94.63 365	98.67 314

WR-MVS_H		98.13 210	97.87 230	98.90 221	99.02 320	98.84 188	99.70 56	99.59 62	97.27 259	98.40 332	99.19 336	95.53 194	99.23 328	98.34 198	93.78 381	98.61 344

miper_enhance_ethall		98.16 207	98.08 205	98.41 290	98.96 332	97.72 269	98.45 401	99.32 282	96.95 291	98.97 262	99.17 337	97.06 137	99.22 332	97.86 237	95.99 332	98.29 373

GG-mvs-BLEND				98.45 284	98.55 383	98.16 242	99.43 215	93.68 429		97.23 375	98.46 387	89.30 360	99.22 332	95.43 357	98.22 247	97.98 395

FC-MVSNet-test		98.75 162	98.62 162	99.15 188	99.08 311	99.45 103	99.86 11	99.60 56	98.23 138	98.70 304	99.82 86	96.80 145	99.22 332	99.07 95	96.38 321	98.79 276

UniMVSNet_NR-MVSNet		98.22 199	97.97 217	98.96 207	98.92 336	98.98 163	99.48 191	99.53 106	97.76 203	98.71 298	99.46 274	96.43 163	99.22 332	98.57 172	92.87 391	98.69 302

DU-MVS		98.08 216	97.79 235	98.96 207	98.87 343	98.98 163	99.41 225	99.45 208	97.87 187	98.71 298	99.50 258	94.82 222	99.22 332	98.57 172	92.87 391	98.68 307

cl____		98.01 231	97.84 233	98.55 270	99.25 267	97.97 253	98.71 384	99.34 265	96.47 328	98.59 322	99.54 243	95.65 191	99.21 337	97.21 294	95.77 338	98.46 361

WR-MVS		98.06 218	97.73 247	99.06 194	98.86 346	99.25 130	99.19 305	99.35 260	97.30 257	98.66 307	99.43 279	93.94 268	99.21 337	98.58 169	94.28 371	98.71 293

test_0402		96.64 339	96.24 341	97.85 338	98.85 347	96.43 336	99.44 210	99.26 300	93.52 392	96.98 382	99.52 251	88.52 373	99.20 339	92.58 397	97.50 289	97.93 398

SixPastTwentyTwo		97.50 306	97.33 302	98.03 321	98.65 373	96.23 344	99.77 34	98.68 385	97.14 270	97.90 358	99.93 10	90.45 346	99.18 340	97.00 307	96.43 320	98.67 314

cl22		97.85 254	97.64 258	98.48 276	99.09 308	97.87 261	98.60 394	99.33 272	97.11 276	98.87 278	99.22 332	92.38 313	99.17 341	98.21 207	95.99 332	98.42 364

WB-MVSnew		97.65 295	97.65 255	97.63 352	98.78 355	97.62 275	99.13 315	98.33 395	97.36 252	99.07 242	98.94 364	95.64 192	99.15 342	92.95 391	98.68 218	96.12 418

IterMVS-SCA-FT		97.82 264	97.75 245	98.06 320	99.57 161	96.36 338	99.02 341	99.49 155	97.18 267	98.71 298	99.72 162	92.72 297	99.14 343	97.44 282	95.86 337	98.67 314

pmmvs5		97.52 303	97.30 305	98.16 313	98.57 382	96.73 322	99.27 281	98.90 355	96.14 351	98.37 334	99.53 247	91.54 333	99.14 343	97.51 274	95.87 336	98.63 333

v148		97.79 270	97.55 264	98.50 273	98.74 363	97.72 269	99.54 149	99.33 272	96.26 340	98.90 272	99.51 255	94.68 236	99.14 343	97.83 241	93.15 388	98.63 333

miper_ehance_all_eth		98.18 205	98.10 201	98.41 290	99.23 271	97.72 269	98.72 383	99.31 286	96.60 317	98.88 275	99.29 321	97.29 128	99.13 346	97.60 263	95.99 332	98.38 369

NR-MVSNet		97.97 238	97.61 261	99.02 199	98.87 343	99.26 128	99.47 199	99.42 224	97.63 218	97.08 380	99.50 258	95.07 212	99.13 346	97.86 237	93.59 382	98.68 307

IterMVS		97.83 261	97.77 240	98.02 323	99.58 159	96.27 342	99.02 341	99.48 167	97.22 265	98.71 298	99.70 167	92.75 294	99.13 346	97.46 280	96.00 331	98.67 314
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 372	94.90 364	91.84 397	97.24 407	80.01 427	98.52 398	99.48 167	89.01 414	91.99 414	99.67 190	85.67 394	99.13 346	95.44 356	97.03 311	96.39 415
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 223	97.96 218	98.33 297	99.26 263	97.38 283	98.56 397	99.31 286	96.65 309	98.88 275	99.52 251	96.58 154	99.12 350	97.39 285	95.53 348	98.47 358

pmmvs4		98.13 210	97.90 225	98.81 242	98.61 378	98.87 183	98.99 349	99.21 311	96.44 329	99.06 247	99.58 227	95.90 182	99.11 351	97.18 300	96.11 328	98.46 361

TransMVSNet (Re)		97.15 327	96.58 333	98.86 233	99.12 300	98.85 187	99.49 186	98.91 353	95.48 365	97.16 378	99.80 113	93.38 281	99.11 351	94.16 378	91.73 397	98.62 335

ambc				93.06 395	92.68 426	82.36 420	98.47 400	98.73 382		95.09 401	97.41 409	55.55 427	99.10 353	96.42 334	91.32 398	97.71 401

Baseline_NR-MVSNet		97.76 272	97.45 279	98.68 256	99.09 308	98.29 236	99.41 225	98.85 362	95.65 363	98.63 316	99.67 190	94.82 222	99.10 353	98.07 223	92.89 390	98.64 326

test_vis3_rt		87.04 387	85.81 390	90.73 401	93.99 425	81.96 422	99.76 37	90.23 436	92.81 400	81.35 424	91.56 424	40.06 433	99.07 355	94.27 375	88.23 411	91.15 424

CP-MVSNet		98.09 214	97.78 238	99.01 200	98.97 331	99.24 131	99.67 69	99.46 197	97.25 261	98.48 329	99.64 203	93.79 275	99.06 356	98.63 159	94.10 375	98.74 289

PS-CasMVS		97.93 241	97.59 263	98.95 209	98.99 326	99.06 155	99.68 66	99.52 111	97.13 271	98.31 337	99.68 184	92.44 312	99.05 357	98.51 180	94.08 376	98.75 285

K. test v3		97.10 329	96.79 329	98.01 324	98.72 366	96.33 339	99.87 8	97.05 413	97.59 222	96.16 392	99.80 113	88.71 367	99.04 358	96.69 325	96.55 318	98.65 324

new_pmnet		96.38 345	96.03 347	97.41 359	98.13 393	95.16 373	99.05 333	99.20 312	93.94 387	97.39 372	98.79 376	91.61 332	99.04 358	90.43 404	95.77 338	98.05 388

DIV-MVS_self_test		98.01 231	97.85 232	98.48 276	99.24 269	97.95 257	98.71 384	99.35 260	96.50 322	98.60 321	99.54 243	95.72 189	99.03 360	97.21 294	95.77 338	98.46 361

IterMVS-LS		98.46 179	98.42 178	98.58 264	99.59 157	98.00 251	99.37 244	99.43 222	96.94 293	99.07 242	99.59 223	97.87 110	99.03 360	98.32 201	95.62 344	98.71 293
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 295	97.68 252	97.55 356	98.62 376	94.97 375	98.84 371	99.30 290	96.83 300	98.19 346	99.34 308	97.01 140	99.02 362	95.00 366	96.01 330	98.64 326

Patchmtry		97.75 276	97.40 291	98.81 242	99.10 305	98.87 183	99.11 324	99.33 272	94.83 378	98.81 287	99.38 295	94.33 253	99.02 362	96.10 339	95.57 346	98.53 352

N_pmnet		94.95 366	95.83 352	92.31 396	98.47 386	79.33 428	99.12 318	92.81 434	93.87 388	97.68 365	99.13 342	93.87 272	99.01 364	91.38 401	96.19 326	98.59 348

CR-MVSNet		98.17 206	97.93 223	98.87 230	99.18 284	98.49 225	99.22 301	99.33 272	96.96 289	99.56 130	99.38 295	94.33 253	99.00 365	94.83 369	98.58 223	99.14 243

c3_l		98.12 212	98.04 210	98.38 294	99.30 251	97.69 273	98.81 374	99.33 272	96.67 307	98.83 284	99.34 308	97.11 133	98.99 366	97.58 265	95.34 351	98.48 356

test0.0.03 1		97.71 285	97.42 289	98.56 268	98.41 389	97.82 264	98.78 377	98.63 388	97.34 253	98.05 354	98.98 360	94.45 250	98.98 367	95.04 365	97.15 309	98.89 271

PatchT		97.03 331	96.44 337	98.79 245	98.99 326	98.34 235	99.16 309	99.07 329	92.13 403	99.52 139	97.31 413	94.54 246	98.98 367	88.54 411	98.73 216	99.03 259

GBi-Net		97.68 290	97.48 273	98.29 302	99.51 182	97.26 289	99.43 215	99.48 167	96.49 323	99.07 242	99.32 316	90.26 348	98.98 367	97.10 302	96.65 314	98.62 335

test1		97.68 290	97.48 273	98.29 302	99.51 182	97.26 289	99.43 215	99.48 167	96.49 323	99.07 242	99.32 316	90.26 348	98.98 367	97.10 302	96.65 314	98.62 335

FMVSNet3		98.03 226	97.76 244	98.84 237	99.39 228	98.98 163	99.40 233	99.38 244	96.67 307	99.07 242	99.28 323	92.93 289	98.98 367	97.10 302	96.65 314	98.56 351

FMVSNet2		97.72 282	97.36 294	98.80 244	99.51 182	98.84 188	99.45 204	99.42 224	96.49 323	98.86 282	99.29 321	90.26 348	98.98 367	96.44 333	96.56 317	98.58 349

FMVSNet1		96.84 335	96.36 339	98.29 302	99.32 249	97.26 289	99.43 215	99.48 167	95.11 370	98.55 324	99.32 316	83.95 405	98.98 367	95.81 346	96.26 325	98.62 335

ppachtmachnet_test		97.49 311	97.45 279	97.61 354	98.62 376	95.24 369	98.80 375	99.46 197	96.11 353	98.22 344	99.62 214	96.45 161	98.97 374	93.77 380	95.97 335	98.61 344

TranMVSNet+NR-MVSNet		97.93 241	97.66 254	98.76 248	98.78 355	98.62 209	99.65 81	99.49 155	97.76 203	98.49 328	99.60 221	94.23 256	98.97 374	98.00 227	92.90 389	98.70 298

MVStest1		96.08 352	95.48 357	97.89 336	98.93 334	96.70 323	99.56 130	99.35 260	92.69 401	91.81 415	99.46 274	89.90 354	98.96 376	95.00 366	92.61 394	98.00 393

test_method		91.10 382	91.36 384	90.31 402	95.85 415	73.72 435	94.89 423	99.25 302	68.39 426	95.82 395	99.02 354	80.50 416	98.95 377	93.64 383	94.89 363	98.25 376

ADS-MVSNet2		98.02 228	98.07 208	97.87 337	99.33 242	95.19 371	99.23 297	99.08 326	96.24 341	99.10 236	99.67 190	94.11 261	98.93 378	96.81 319	99.05 193	99.48 194

ET-MVSNet_ETH3D		96.49 342	95.64 356	99.05 196	99.53 173	98.82 192	98.84 371	97.51 411	97.63 218	84.77 420	99.21 335	92.09 317	98.91 379	98.98 104	92.21 396	99.41 215

miper_lstm_enhance		98.00 233	97.91 224	98.28 306	99.34 241	97.43 281	98.88 367	99.36 253	96.48 326	98.80 289	99.55 238	95.98 175	98.91 379	97.27 291	95.50 349	98.51 354

MonoMVSNet		98.38 188	98.47 176	98.12 318	98.59 381	96.19 346	99.72 52	98.79 370	97.89 185	99.44 155	99.52 251	96.13 170	98.90 381	98.64 157	97.54 284	99.28 232

PEN-MVS		97.76 272	97.44 284	98.72 251	98.77 360	98.54 216	99.78 32	99.51 125	97.06 281	98.29 340	99.64 203	92.63 303	98.89 382	98.09 216	93.16 387	98.72 291

testing3		97.28 321	96.76 330	98.82 239	99.37 233	98.07 248	99.45 204	99.36 253	97.56 227	97.89 359	98.95 363	83.70 406	98.82 383	96.03 341	98.56 226	99.58 165

testgi		97.65 295	97.50 271	98.13 317	99.36 236	96.45 335	99.42 222	99.48 167	97.76 203	97.87 360	99.45 276	91.09 340	98.81 384	94.53 371	98.52 229	99.13 245

testf1		90.42 385	90.68 386	89.65 405	97.78 397	73.97 433	99.13 315	98.81 367	89.62 411	91.80 416	98.93 365	62.23 425	98.80 385	86.61 419	91.17 399	96.19 416

APD_test2		90.42 385	90.68 386	89.65 405	97.78 397	73.97 433	99.13 315	98.81 367	89.62 411	91.80 416	98.93 365	62.23 425	98.80 385	86.61 419	91.17 399	96.19 416

MIMVSNet		97.73 280	97.45 279	98.57 265	99.45 211	97.50 279	99.02 341	98.98 340	96.11 353	99.41 164	99.14 341	90.28 347	98.74 387	95.74 348	98.93 201	99.47 200

LCM-MVSNet-Re		97.83 261	98.15 195	96.87 375	99.30 251	92.25 405	99.59 109	98.26 396	97.43 245	96.20 391	99.13 342	96.27 167	98.73 388	98.17 212	98.99 198	99.64 145

Syy-MVS		97.09 330	97.14 316	96.95 372	99.00 323	92.73 403	99.29 271	99.39 236	97.06 281	97.41 369	98.15 399	93.92 270	98.68 389	91.71 399	98.34 236	99.45 208

myMVS_eth3d		96.89 333	96.37 338	98.43 289	99.00 323	97.16 293	99.29 271	99.39 236	97.06 281	97.41 369	98.15 399	83.46 407	98.68 389	95.27 361	98.34 236	99.45 208

DTE-MVSNet		97.51 305	97.19 314	98.46 282	98.63 375	98.13 245	99.84 12	99.48 167	96.68 306	97.97 357	99.67 190	92.92 290	98.56 391	96.88 318	92.60 395	98.70 298

PC_three_1452									98.18 146	99.84 40	99.70 167	99.31 3	98.52 392	98.30 203	99.80 107	99.81 67

mvsany_test3		93.77 374	93.45 378	94.74 387	95.78 416	88.01 413	99.64 84	98.25 397	98.28 129	94.31 404	97.97 406	68.89 421	98.51 393	97.50 275	90.37 404	97.71 401

UnsupCasMVSNet_bld		93.53 375	92.51 381	96.58 380	97.38 403	93.82 391	98.24 410	99.48 167	91.10 408	93.10 409	96.66 415	74.89 419	98.37 394	94.03 379	87.71 412	97.56 406

Anonymous20240521		96.20 348	95.89 351	97.13 366	97.72 400	94.96 376	99.79 31	99.29 294	93.01 397	97.20 377	99.03 352	89.69 357	98.36 395	91.16 402	96.13 327	98.07 386

test_f		91.90 381	91.26 385	93.84 390	95.52 420	85.92 415	99.69 60	98.53 393	95.31 367	93.87 406	96.37 417	55.33 428	98.27 396	95.70 349	90.98 402	97.32 409

MDA-MVSNet_test_wron		95.45 359	94.60 366	98.01 324	98.16 392	97.21 292	99.11 324	99.24 305	93.49 393	80.73 426	98.98 360	93.02 287	98.18 397	94.22 377	94.45 368	98.64 326

UnsupCasMVSNet_eth		96.44 343	96.12 344	97.40 360	98.65 373	95.65 355	99.36 249	99.51 125	97.13 271	96.04 394	98.99 358	88.40 374	98.17 398	96.71 323	90.27 405	98.40 367

KD-MVS_2432*1600		94.62 367	93.72 375	97.31 361	97.19 409	95.82 352	98.34 405	99.20 312	95.00 374	97.57 366	98.35 392	87.95 379	98.10 399	92.87 393	77.00 424	98.01 390

miper_refine_blended		94.62 367	93.72 375	97.31 361	97.19 409	95.82 352	98.34 405	99.20 312	95.00 374	97.57 366	98.35 392	87.95 379	98.10 399	92.87 393	77.00 424	98.01 390

YYNet1		95.36 361	94.51 368	97.92 333	97.89 395	97.10 296	99.10 326	99.23 306	93.26 396	80.77 425	99.04 351	92.81 293	98.02 401	94.30 373	94.18 373	98.64 326

EU-MVSNet		97.98 235	98.03 211	97.81 344	98.72 366	96.65 328	99.66 75	99.66 28	98.09 159	98.35 335	99.82 86	95.25 206	98.01 402	97.41 284	95.30 352	98.78 277

Gipuma		90.99 383	90.15 388	93.51 391	98.73 364	90.12 411	93.98 424	99.45 208	79.32 422	92.28 412	94.91 419	69.61 420	97.98 403	87.42 415	95.67 342	92.45 422
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 362	94.73 365	97.15 364	95.53 419	95.94 350	99.35 254	99.10 323	95.13 368	93.55 407	97.54 408	88.15 378	97.91 404	94.58 370	89.69 408	97.61 404

PM-MVS		92.96 378	92.23 382	95.14 386	95.61 417	89.98 412	99.37 244	98.21 399	94.80 379	95.04 402	97.69 407	65.06 422	97.90 405	94.30 373	89.98 407	97.54 407

MDA-MVSNet-bldmvs		94.96 365	93.98 372	97.92 333	98.24 391	97.27 287	99.15 312	99.33 272	93.80 389	80.09 427	99.03 352	88.31 375	97.86 406	93.49 385	94.36 370	98.62 335

Patchmatch-RL test		95.84 355	95.81 353	95.95 384	95.61 417	90.57 410	98.24 410	98.39 394	95.10 372	95.20 399	98.67 380	94.78 226	97.77 407	96.28 338	90.02 406	99.51 188

Anonymous20231206		96.22 346	96.03 347	96.79 377	97.31 406	94.14 389	99.63 90	99.08 326	96.17 347	97.04 381	99.06 349	93.94 268	97.76 408	86.96 417	95.06 357	98.47 358

SD-MVS		99.41 52	99.52 12	99.05 196	99.74 88	99.68 55	99.46 202	99.52 111	99.11 35	99.88 29	99.91 23	99.43 1	97.70 409	98.72 146	99.93 27	99.77 88
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
DSMNet-mixed		97.25 323	97.35 296	96.95 372	97.84 396	93.61 397	99.57 124	96.63 419	96.13 352	98.87 278	98.61 383	94.59 241	97.70 409	95.08 364	98.86 207	99.55 171

dongtai		93.26 376	92.93 380	94.25 388	99.39 228	85.68 416	97.68 419	93.27 430	92.87 399	96.85 385	99.39 293	82.33 412	97.48 411	76.78 424	97.80 269	99.58 165

pmmvs3		94.09 373	93.25 379	96.60 379	94.76 424	94.49 383	98.92 363	98.18 401	89.66 410	96.48 388	98.06 405	86.28 391	97.33 412	89.68 407	87.20 413	97.97 396

KD-MVS_self_test		95.00 364	94.34 369	96.96 371	97.07 411	95.39 366	99.56 130	99.44 216	95.11 370	97.13 379	97.32 412	91.86 322	97.27 413	90.35 405	81.23 421	98.23 378

FMVSNet5		96.43 344	96.19 343	97.15 364	99.11 302	95.89 351	99.32 261	99.52 111	94.47 385	98.34 336	99.07 347	87.54 384	97.07 414	92.61 396	95.72 341	98.47 358

new-patchmatchnet		94.48 370	94.08 371	95.67 385	95.08 422	92.41 404	99.18 307	99.28 296	94.55 384	93.49 408	97.37 411	87.86 382	97.01 415	91.57 400	88.36 410	97.61 404

LCM-MVSNet		86.80 389	85.22 393	91.53 399	87.81 431	80.96 425	98.23 412	98.99 339	71.05 424	90.13 419	96.51 416	48.45 432	96.88 416	90.51 403	85.30 415	96.76 411

CL-MVSNet_self_test		94.49 369	93.97 373	96.08 383	96.16 414	93.67 396	98.33 407	99.38 244	95.13 368	97.33 373	98.15 399	92.69 301	96.57 417	88.67 410	79.87 422	97.99 394

MIMVSNet1		95.51 358	95.04 363	96.92 374	97.38 403	95.60 356	99.52 159	99.50 145	93.65 391	96.97 383	99.17 337	85.28 399	96.56 418	88.36 412	95.55 347	98.60 347

test20.03		96.12 350	95.96 349	96.63 378	97.44 402	95.45 363	99.51 168	99.38 244	96.55 320	96.16 392	99.25 329	93.76 277	96.17 419	87.35 416	94.22 372	98.27 374

tmp_tt		82.80 391	81.52 394	86.66 407	66.61 437	68.44 436	92.79 426	97.92 403	68.96 425	80.04 428	99.85 62	85.77 393	96.15 420	97.86 237	43.89 430	95.39 420

test_fmvs3		92.10 380	91.77 383	93.08 394	96.19 413	86.25 414	99.82 16	98.62 389	96.65 309	95.19 400	96.90 414	55.05 429	95.93 421	96.63 330	90.92 403	97.06 410

kuosan		90.92 384	90.11 389	93.34 392	98.78 355	85.59 417	98.15 414	93.16 432	89.37 413	92.07 413	98.38 391	81.48 415	95.19 422	62.54 431	97.04 310	99.25 237

dmvs_testset		95.02 363	96.12 344	91.72 398	99.10 305	80.43 426	99.58 117	97.87 405	97.47 237	95.22 398	98.82 372	93.99 266	95.18 423	88.09 413	94.91 362	99.56 170

PMMVS2		86.87 388	85.37 392	91.35 400	90.21 429	83.80 419	98.89 366	97.45 412	83.13 421	91.67 418	95.03 418	48.49 431	94.70 424	85.86 421	77.62 423	95.54 419

PMVS	70.75 22	75.98 397	74.97 398	79.01 413	70.98 436	55.18 438	93.37 425	98.21 399	65.08 430	61.78 431	93.83 421	21.74 438	92.53 425	78.59 423	91.12 401	89.34 426
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 390	85.65 391	82.75 411	86.77 432	63.39 437	98.35 404	98.92 348	74.11 423	83.39 422	98.98 360	50.85 430	92.40 426	84.54 422	94.97 359	92.46 421

WB-MVS		93.10 377	94.10 370	90.12 403	95.51 421	81.88 423	99.73 50	99.27 299	95.05 373	93.09 410	98.91 369	94.70 235	91.89 427	76.62 425	94.02 378	96.58 413

SSC-MVS		92.73 379	93.73 374	89.72 404	95.02 423	81.38 424	99.76 37	99.23 306	94.87 377	92.80 411	98.93 365	94.71 234	91.37 428	74.49 427	93.80 380	96.42 414

MVE	76.82 21	76.91 396	74.31 400	84.70 408	85.38 434	76.05 432	96.88 422	93.17 431	67.39 427	71.28 429	89.01 428	21.66 439	87.69 429	71.74 428	72.29 426	90.35 425
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 393	79.88 395	82.81 410	90.75 428	76.38 431	97.69 418	95.76 423	66.44 428	83.52 421	92.25 423	62.54 424	87.16 430	68.53 429	61.40 427	84.89 428

EMVS		80.02 394	79.22 396	82.43 412	91.19 427	76.40 430	97.55 421	92.49 435	66.36 429	83.01 423	91.27 425	64.63 423	85.79 431	65.82 430	60.65 428	85.08 427

ANet_high		77.30 395	74.86 399	84.62 409	75.88 435	77.61 429	97.63 420	93.15 433	88.81 415	64.27 430	89.29 427	36.51 434	83.93 432	75.89 426	52.31 429	92.33 423

wuyk23d		40.18 398	41.29 403	36.84 414	86.18 433	49.12 439	79.73 427	22.81 439	27.64 431	25.46 434	28.45 434	21.98 437	48.89 433	55.80 432	23.56 433	12.51 431

test123		39.01 400	42.50 402	28.53 415	39.17 438	20.91 440	98.75 380	19.17 440	19.83 433	38.57 432	66.67 430	33.16 435	15.42 434	37.50 434	29.66 432	49.26 429

testmvs		39.17 399	43.78 401	25.37 416	36.04 439	16.84 441	98.36 403	26.56 438	20.06 432	38.51 433	67.32 429	29.64 436	15.30 435	37.59 433	39.90 431	43.98 430

mmdepth		0.02 405	0.03 408	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.27 436	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

monomultidepth		0.02 405	0.03 408	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.27 436	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

test_blank		0.13 404	0.17 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	1.57 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

uanet_test		0.02 405	0.03 408	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.27 436	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

DCPMVS		0.02 405	0.03 408	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.27 436	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

cdsmvs_eth3d_5k		24.64 401	32.85 404	0.00 417	0.00 440	0.00 442	0.00 428	99.51 125	0.00 435	0.00 436	99.56 235	96.58 154	0.00 436	0.00 435	0.00 434	0.00 432

pcd_1.5k_mvsjas		8.27 403	11.03 406	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.27 436	99.01 18	0.00 436	0.00 435	0.00 434	0.00 432

sosnet-low-res		0.02 405	0.03 408	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.27 436	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

sosnet		0.02 405	0.03 408	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.27 436	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

uncertanet		0.02 405	0.03 408	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.27 436	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

Regformer		0.02 405	0.03 408	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.27 436	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

ab-mvs-re		8.30 402	11.06 405	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	99.58 227	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

uanet		0.02 405	0.03 408	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.27 436	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

WAC-MVS						97.16 293								95.47 355

FOURS1					99.91 1	99.93 1	99.87 8	99.56 76	99.10 36	99.81 48

test_one_0601					99.81 47	99.88 8		99.49 155	98.97 60	99.65 104	99.81 100	99.09 14

eth-test2					0.00 440

eth-test					0.00 440

RE-MVS-def			99.34 43		99.76 70	99.82 25	99.63 90	99.52 111	98.38 117	99.76 69	99.82 86	98.75 58		98.61 163	99.81 103	99.77 88

IU-MVS					99.84 32	99.88 8		99.32 282	98.30 128	99.84 40				98.86 126	99.85 79	99.89 22

save fliter					99.76 70	99.59 77	99.14 314	99.40 233	99.00 52

test0726					99.85 26	99.89 4	99.62 95	99.50 145	99.10 36	99.86 38	99.82 86	98.94 32

GSMVS																99.52 180

test_part2					99.81 47	99.83 19				99.77 63

sam_mvs1												94.86 221				99.52 180

sam_mvs												94.72 233

MTGPA								99.47 188

MTMP							99.54 149	98.88 358

test9_res														97.49 276	99.72 130	99.75 94

agg_prior2														97.21 294	99.73 129	99.75 94

test_prior4						99.56 83	98.99 349

test_prior2							98.96 356		98.34 123	99.01 253	99.52 251	98.68 67		97.96 229	99.74 127

新几何2							99.01 346

旧先验1					99.74 88	99.59 77		99.54 93			99.69 177	98.47 83			99.68 138	99.73 103

原ACMM2							98.95 359

test222					99.75 80	99.49 97	98.91 365	99.49 155	96.42 331	99.34 184	99.65 197	98.28 96			99.69 135	99.72 111

segment_acmp												98.96 25

testdata1							98.85 370		98.32 126

plane_prior7					99.29 255	97.03 306

plane_prior6					99.27 260	96.98 310						92.71 299

plane_prior4											99.61 218

plane_prior3						97.00 308			98.69 89	99.11 233

plane_prior2							99.39 237		98.97 60

plane_prior1					99.26 263

plane_prior						96.97 311	99.21 303		98.45 110						97.60 278

n2								0.00 441

nn								0.00 441

door-mid								98.05 402

test11								99.35 260

door								97.92 403

HQP5-MVS						96.83 318

HQP-NCC					99.19 281		98.98 352		98.24 135	98.66 307

ACMP_Plane					99.19 281		98.98 352		98.24 135	98.66 307

BP-MVS														97.19 298

HQP3-MVS								99.39 236							97.58 280

HQP2-MVS												92.47 308

NP-MVS					99.23 271	96.92 314					99.40 289

MDTV_nov1_ep13_2view						95.18 372	99.35 254		96.84 298	99.58 126		95.19 208		97.82 242		99.46 205

ACMMP++_ref															97.19 307

ACMMP++															97.43 298

Test By Simon												98.75 58

High-resolution multi-view benchmark