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 65	99.38 234	99.37 113	99.58 117	99.62 45	99.41 17	99.87 38	99.92 17	98.81 47	100.00 1	99.97 1	99.93 29	99.94 14

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 62	99.84 32	99.44 107	99.58 117	99.69 18	99.43 13	99.98 10	99.91 23	98.62 73	100.00 1	99.97 1	99.95 19	99.90 22

test_vis1_n_1920		98.63 177	98.40 184	99.31 163	99.86 20	97.94 263	99.67 69	99.62 45	99.43 13	99.99 2	99.91 23	87.29 389	100.00 1	99.92 20	99.92 34	99.98 2

fmvsm_s_conf0.5_n_5		99.37 61	99.21 77	99.86 28	99.80 54	99.68 56	99.42 224	99.61 53	99.37 20	99.97 21	99.86 58	94.96 217	99.99 4	99.97 1	99.93 29	99.92 20

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 10	99.89 36	97.27 129	99.99 4	99.97 1	99.95 19	99.95 10

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 36	99.86 20	99.61 77	99.56 130	99.63 42	99.48 3	99.98 10	99.83 80	98.75 58	99.99 4	99.97 1	99.96 14	99.94 14

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 36	99.84 32	99.63 74	99.56 130	99.63 42	99.47 4	99.98 10	99.82 89	98.75 58	99.99 4	99.97 1	99.97 8	99.94 14

test_fmvsmconf_n		99.70 3	99.64 4	99.87 17	99.80 54	99.66 63	99.48 193	99.64 38	99.45 10	99.92 25	99.92 17	98.62 73	99.99 4	99.96 10	99.99 1	99.96 7

patch_mono-2		99.26 83	99.62 5	98.16 317	99.81 48	94.59 386	99.52 159	99.64 38	99.33 22	99.73 79	99.90 30	99.00 22	99.99 4	99.69 30	99.98 4	99.89 25

h-mvs33		97.70 290	97.28 312	98.97 210	99.70 111	97.27 291	99.36 253	99.45 212	98.94 67	99.66 101	99.64 207	94.93 220	99.99 4	99.48 55	84.36 420	99.65 142

xiu_mvs_v1_base_debu		99.29 77	99.27 67	99.34 156	99.63 143	98.97 169	99.12 322	99.51 129	98.86 73	99.84 44	99.47 274	98.18 100	99.99 4	99.50 50	99.31 175	99.08 255

xiu_mvs_v1_base		99.29 77	99.27 67	99.34 156	99.63 143	98.97 169	99.12 322	99.51 129	98.86 73	99.84 44	99.47 274	98.18 100	99.99 4	99.50 50	99.31 175	99.08 255

xiu_mvs_v1_base_debi		99.29 77	99.27 67	99.34 156	99.63 143	98.97 169	99.12 322	99.51 129	98.86 73	99.84 44	99.47 274	98.18 100	99.99 4	99.50 50	99.31 175	99.08 255

EPNet		98.86 148	98.71 152	99.30 168	97.20 412	98.18 245	99.62 95	98.91 357	99.28 25	98.63 320	99.81 103	95.96 178	99.99 4	99.24 82	99.72 134	99.73 107
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n_8		99.54 19	99.42 27	99.89 8	99.83 40	99.74 47	99.51 168	99.62 45	99.46 7	99.99 2	99.90 30	96.60 154	99.98 15	99.95 12	99.95 19	99.96 7

MM		99.40 57	99.28 64	99.74 71	99.67 122	99.31 123	99.52 159	98.87 364	99.55 1	99.74 77	99.80 116	96.47 161	99.98 15	99.97 1	99.97 8	99.94 14

test_cas_vis1_n_1920		99.16 97	99.01 109	99.61 99	99.81 48	98.86 189	99.65 81	99.64 38	99.39 18	99.97 21	99.94 6	93.20 290	99.98 15	99.55 43	99.91 41	99.99 1

test_vis1_n		97.92 248	97.44 288	99.34 156	99.53 176	98.08 251	99.74 46	99.49 159	99.15 30	100.00 1	99.94 6	79.51 421	99.98 15	99.88 22	99.76 126	99.97 4

xiu_mvs_v2_base		99.26 83	99.25 71	99.29 171	99.53 176	98.91 183	99.02 345	99.45 212	98.80 82	99.71 86	99.26 332	98.94 32	99.98 15	99.34 69	99.23 180	98.98 269

PS-MVSNAJ		99.32 72	99.32 49	99.30 168	99.57 164	98.94 179	98.97 359	99.46 201	98.92 70	99.71 86	99.24 334	99.01 18	99.98 15	99.35 64	99.66 144	98.97 270

QAPM		98.67 173	98.30 191	99.80 56	99.20 282	99.67 60	99.77 34	99.72 11	94.74 384	98.73 300	99.90 30	95.78 188	99.98 15	96.96 315	99.88 65	99.76 97

3Dnovator	97.25 9	99.24 88	99.05 97	99.81 53	99.12 304	99.66 63	99.84 12	99.74 10	99.09 45	98.92 273	99.90 30	95.94 181	99.98 15	98.95 112	99.92 34	99.79 84

OpenMVS	96.50 16	98.47 182	98.12 203	99.52 126	99.04 322	99.53 93	99.82 16	99.72 11	94.56 387	98.08 354	99.88 44	94.73 236	99.98 15	97.47 283	99.76 126	99.06 261

fmvsm_s_conf0.5_n_3		99.37 61	99.20 79	99.87 17	99.75 82	99.70 53	99.48 193	99.66 28	99.45 10	99.99 2	99.93 10	94.64 244	99.97 24	99.94 17	99.97 8	99.95 10

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 60	99.88 8	99.56 130	99.55 88	99.15 30	99.90 28	99.90 30	99.00 22	99.97 24	99.11 93	99.91 41	99.86 38

test_fmvsmconf0.1_n		99.55 18	99.45 25	99.86 28	99.44 216	99.65 67	99.50 176	99.61 53	99.45 10	99.87 38	99.92 17	97.31 126	99.97 24	99.95 12	99.99 1	99.97 4

test_fmvs1_n		98.41 188	98.14 200	99.21 183	99.82 44	97.71 276	99.74 46	99.49 159	99.32 23	99.99 2	99.95 3	85.32 402	99.97 24	99.82 25	99.84 91	99.96 7

CANet_DTU		98.97 138	98.87 133	99.25 178	99.33 246	98.42 237	99.08 331	99.30 294	99.16 29	99.43 161	99.75 151	95.27 206	99.97 24	98.56 179	99.95 19	99.36 227

MVS_0304		99.15 99	98.96 119	99.73 74	98.92 340	99.37 113	99.37 248	96.92 418	99.51 2	99.66 101	99.78 135	96.69 151	99.97 24	99.84 24	99.97 8	99.84 49

MTAPA		99.52 23	99.39 35	99.89 8	99.90 4	99.86 16	99.66 75	99.47 192	98.79 83	99.68 92	99.81 103	98.43 86	99.97 24	98.88 122	99.90 50	99.83 59

PGM-MVS		99.45 41	99.31 55	99.86 28	99.87 15	99.78 40	99.58 117	99.65 35	97.84 197	99.71 86	99.80 116	99.12 13	99.97 24	98.33 203	99.87 68	99.83 59

mPP-MVS		99.44 45	99.30 57	99.86 28	99.88 11	99.79 34	99.69 60	99.48 171	98.12 158	99.50 146	99.75 151	98.78 51	99.97 24	98.57 176	99.89 61	99.83 59

CP-MVS		99.45 41	99.32 49	99.85 36	99.83 40	99.75 44	99.69 60	99.52 115	98.07 168	99.53 141	99.63 213	98.93 36	99.97 24	98.74 147	99.91 41	99.83 59

SteuartSystems-ACMMP		99.54 19	99.42 27	99.87 17	99.82 44	99.81 29	99.59 109	99.51 129	98.62 98	99.79 58	99.83 80	99.28 4	99.97 24	98.48 186	99.90 50	99.84 49
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 93	98.97 115	99.82 50	99.17 296	99.68 56	99.81 20	99.51 129	99.20 27	98.72 301	99.89 36	95.68 192	99.97 24	98.86 130	99.86 76	99.81 71

fmvsm_s_conf0.5_n_7		99.34 68	99.29 61	99.48 134	99.70 111	98.63 211	99.42 224	99.63 42	99.46 7	99.98 10	99.88 44	95.59 195	99.96 36	99.97 1	99.98 4	99.85 42

fmvsm_s_conf0.5_n_2		99.32 72	99.13 86	99.89 8	99.80 54	99.77 41	99.44 212	99.58 70	99.47 4	99.99 2	99.93 10	94.04 268	99.96 36	99.96 10	99.93 29	99.93 19

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 72	99.88 8	99.52 159	99.54 97	99.13 33	99.89 30	99.89 36	98.96 25	99.96 36	99.04 101	99.90 50	99.85 42

our_new_method		99.61 8	99.52 12	99.90 5	99.76 72	99.88 8	99.52 159	99.54 97	99.13 33	99.89 30	99.89 36	98.96 25	99.96 36	99.04 101	99.90 50	99.85 42

fmvsm_s_conf0.5_n_a		99.56 17	99.47 21	99.85 36	99.83 40	99.64 73	99.52 159	99.65 35	99.10 40	99.98 10	99.92 17	97.35 125	99.96 36	99.94 17	99.92 34	99.95 10

fmvsm_s_conf0.5_n		99.51 24	99.40 33	99.85 36	99.84 32	99.65 67	99.51 168	99.67 23	99.13 33	99.98 10	99.92 17	96.60 154	99.96 36	99.95 12	99.96 14	99.95 10

mvsany_test1		99.50 26	99.46 24	99.62 98	99.61 153	99.09 152	98.94 365	99.48 171	99.10 40	99.96 23	99.91 23	98.85 42	99.96 36	99.72 28	99.58 154	99.82 64

test_fmvs1		98.88 144	98.79 145	99.16 188	99.69 116	97.61 280	99.55 144	99.49 159	99.32 23	99.98 10	99.91 23	91.41 338	99.96 36	99.82 25	99.92 34	99.90 22

DVP-MVS++		99.59 12	99.50 17	99.88 11	99.51 185	99.88 8	99.87 8	99.51 129	98.99 58	99.88 33	99.81 103	99.27 5	99.96 36	98.85 132	99.80 111	99.81 71

MSC_two_6792asdad				99.87 17	99.51 185	99.76 42		99.33 276					99.96 36	98.87 125	99.84 91	99.89 25

No_MVS				99.87 17	99.51 185	99.76 42		99.33 276					99.96 36	98.87 125	99.84 91	99.89 25

ZD-MVS					99.71 106	99.79 34		99.61 53	96.84 302	99.56 134	99.54 247	98.58 75	99.96 36	96.93 318	99.75 128

SED-MVS		99.61 8	99.52 12	99.88 11	99.84 32	99.90 2	99.60 102	99.48 171	99.08 46	99.91 26	99.81 103	99.20 7	99.96 36	98.91 119	99.85 83	99.79 84

test_241102_TWO								99.48 171	99.08 46	99.88 33	99.81 103	98.94 32	99.96 36	98.91 119	99.84 91	99.88 31

ZNCC-MVS		99.47 35	99.33 47	99.87 17	99.87 15	99.81 29	99.64 84	99.67 23	98.08 167	99.55 138	99.64 207	98.91 37	99.96 36	98.72 150	99.90 50	99.82 64

DVP-MVS		99.57 16	99.47 21	99.88 11	99.85 26	99.89 4	99.57 124	99.37 256	99.10 40	99.81 52	99.80 116	98.94 32	99.96 36	98.93 116	99.86 76	99.81 71
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 58	99.81 52	99.80 116	99.09 14	99.96 36	98.85 132	99.90 50	99.88 31

test_0728_SECOND				99.91 3	99.84 32	99.89 4	99.57 124	99.51 129					99.96 36	98.93 116	99.86 76	99.88 31

SR-MVS		99.43 48	99.29 61	99.86 28	99.75 82	99.83 19	99.59 109	99.62 45	98.21 145	99.73 79	99.79 128	98.68 67	99.96 36	98.44 192	99.77 123	99.79 84

DPE-MVS		99.46 37	99.32 49	99.91 3	99.78 60	99.88 8	99.36 253	99.51 129	98.73 90	99.88 33	99.84 75	98.72 64	99.96 36	98.16 217	99.87 68	99.88 31
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 50	99.29 61	99.80 56	99.62 149	99.55 88	99.50 176	99.70 15	98.79 83	99.77 67	99.96 1	97.45 120	99.96 36	98.92 118	99.90 50	99.89 25

HFP-MVS		99.49 28	99.37 39	99.86 28	99.87 15	99.80 31	99.66 75	99.67 23	98.15 152	99.68 92	99.69 181	99.06 16	99.96 36	98.69 155	99.87 68	99.84 49

region2R		99.48 32	99.35 43	99.87 17	99.88 11	99.80 31	99.65 81	99.66 28	98.13 157	99.66 101	99.68 188	98.96 25	99.96 36	98.62 164	99.87 68	99.84 49

HPM-MVS++		99.39 59	99.23 75	99.87 17	99.75 82	99.84 18	99.43 217	99.51 129	98.68 95	99.27 203	99.53 251	98.64 72	99.96 36	98.44 192	99.80 111	99.79 84

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 68	99.89 4	99.75 42	99.56 80	99.02 51	99.88 33	99.85 65	99.18 10	99.96 36	99.22 83	99.92 34	99.90 22
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 28	99.36 41	99.86 28	99.87 15	99.79 34	99.66 75	99.67 23	98.15 152	99.67 96	99.69 181	98.95 30	99.96 36	98.69 155	99.87 68	99.84 49

MP-MVS		99.33 70	99.15 84	99.87 17	99.88 11	99.82 25	99.66 75	99.46 201	98.09 163	99.48 150	99.74 156	98.29 95	99.96 36	97.93 235	99.87 68	99.82 64
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 115	98.90 127	99.74 71	99.80 54	99.46 105	99.59 109	99.49 159	97.03 289	99.63 116	99.69 181	97.27 129	99.96 36	97.82 246	99.84 91	99.81 71

PVSNet_Blended_VisFu		99.36 65	99.28 64	99.61 99	99.86 20	99.07 157	99.47 201	99.93 2	97.66 220	99.71 86	99.86 58	97.73 115	99.96 36	99.47 57	99.82 104	99.79 84

UGNet		98.87 145	98.69 154	99.40 148	99.22 279	98.72 203	99.44 212	99.68 20	99.24 26	99.18 228	99.42 285	92.74 300	99.96 36	99.34 69	99.94 27	99.53 183
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 72	99.32 49	99.32 162	99.85 26	98.29 240	99.71 55	99.66 28	98.11 160	99.41 168	99.80 116	98.37 92	99.96 36	98.99 107	99.96 14	99.72 115

ACMMP		99.45 41	99.32 49	99.82 50	99.89 8	99.67 60	99.62 95	99.69 18	98.12 158	99.63 116	99.84 75	98.73 63	99.96 36	98.55 182	99.83 100	99.81 71
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_6		99.54 19	99.44 26	99.85 36	99.51 185	99.67 60	99.50 176	99.64 38	99.43 13	99.98 10	99.78 135	97.26 131	99.95 68	99.95 12	99.93 29	99.92 20

fmvsm_s_conf0.5_n_4		99.36 65	99.24 72	99.73 74	99.78 60	99.53 93	99.49 188	99.60 60	99.42 16	99.99 2	99.86 58	95.15 212	99.95 68	99.95 12	99.89 61	99.73 107

fmvsm_s_conf0.1_n_2		99.37 61	99.22 76	99.81 53	99.77 68	99.75 44	99.46 204	99.60 60	99.47 4	99.98 10	99.94 6	94.98 216	99.95 68	99.97 1	99.79 118	99.73 107

test_fmvsmconf0.01_n		99.22 90	99.03 101	99.79 59	98.42 392	99.48 102	99.55 144	99.51 129	99.39 18	99.78 63	99.93 10	94.80 228	99.95 68	99.93 19	99.95 19	99.94 14

SR-MVS-dyc-post		99.45 41	99.31 55	99.85 36	99.76 72	99.82 25	99.63 90	99.52 115	98.38 121	99.76 73	99.82 89	98.53 79	99.95 68	98.61 167	99.81 107	99.77 92

GST-MVS		99.40 57	99.24 72	99.85 36	99.86 20	99.79 34	99.60 102	99.67 23	97.97 182	99.63 116	99.68 188	98.52 80	99.95 68	98.38 196	99.86 76	99.81 71

CANet		99.25 87	99.14 85	99.59 102	99.41 224	99.16 142	99.35 258	99.57 75	98.82 78	99.51 145	99.61 222	96.46 162	99.95 68	99.59 38	99.98 4	99.65 142

MP-MVS-pluss		99.37 61	99.20 79	99.88 11	99.90 4	99.87 15	99.30 270	99.52 115	97.18 271	99.60 126	99.79 128	98.79 50	99.95 68	98.83 138	99.91 41	99.83 59
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 50	99.27 67	99.88 11	99.89 8	99.80 31	99.67 69	99.50 149	98.70 92	99.77 67	99.49 265	98.21 98	99.95 68	98.46 190	99.77 123	99.88 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
testdata2													99.95 68	96.67 330

APD-MVS_3200maxsize		99.48 32	99.35 43	99.85 36	99.76 72	99.83 19	99.63 90	99.54 97	98.36 125	99.79 58	99.82 89	98.86 41	99.95 68	98.62 164	99.81 107	99.78 90

RPMNet		96.72 341	95.90 354	99.19 185	99.18 288	98.49 229	99.22 305	99.52 115	88.72 420	99.56 134	97.38 414	94.08 267	99.95 68	86.87 422	98.58 227	99.14 247

sss		99.17 95	99.05 97	99.53 120	99.62 149	98.97 169	99.36 253	99.62 45	97.83 198	99.67 96	99.65 201	97.37 124	99.95 68	99.19 85	99.19 183	99.68 132

MVSMamba_PlusPlus		99.46 37	99.41 32	99.64 91	99.68 120	99.50 99	99.75 42	99.50 149	98.27 135	99.87 38	99.92 17	98.09 104	99.94 81	99.65 34	99.95 19	99.47 204

fmvsm_s_conf0.1_n_a		99.26 83	99.06 96	99.85 36	99.52 182	99.62 75	99.54 149	99.62 45	98.69 93	99.99 2	99.96 1	94.47 253	99.94 81	99.88 22	99.92 34	99.98 2

fmvsm_s_conf0.1_n		99.29 77	99.10 90	99.86 28	99.70 111	99.65 67	99.53 158	99.62 45	98.74 89	99.99 2	99.95 3	94.53 251	99.94 81	99.89 21	99.96 14	99.97 4

TSAR-MVS + MP.		99.58 13	99.50 17	99.81 53	99.91 1	99.66 63	99.63 90	99.39 240	98.91 71	99.78 63	99.85 65	99.36 2	99.94 81	98.84 135	99.88 65	99.82 64
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 142	98.75 148	99.39 152	99.46 209	98.61 215	99.76 37	99.50 149	98.06 172	99.81 52	99.88 44	93.91 275	99.94 81	99.11 93	99.27 178	99.61 158

mamv4		99.33 70	99.42 27	99.07 196	99.67 122	97.73 271	99.42 224	99.60 60	98.15 152	99.94 24	99.91 23	98.42 88	99.94 81	99.72 28	99.96 14	99.54 177

XVS		99.53 22	99.42 27	99.87 17	99.85 26	99.83 19	99.69 60	99.68 20	98.98 61	99.37 179	99.74 156	98.81 47	99.94 81	98.79 143	99.86 76	99.84 49

X-MVStestdata		96.55 344	95.45 363	99.87 17	99.85 26	99.83 19	99.69 60	99.68 20	98.98 61	99.37 179	64.01 437	98.81 47	99.94 81	98.79 143	99.86 76	99.84 49

旧先验2							98.96 360		96.70 309	99.47 151			99.94 81	98.19 213

新几何1				99.75 68	99.75 82	99.59 80		99.54 97	96.76 305	99.29 197	99.64 207	98.43 86	99.94 81	96.92 320	99.66 144	99.72 115

testdata				99.54 112	99.75 82	98.95 176		99.51 129	97.07 283	99.43 161	99.70 171	98.87 40	99.94 81	97.76 253	99.64 147	99.72 115

HPM-MVS		99.42 50	99.28 64	99.83 49	99.90 4	99.72 49	99.81 20	99.54 97	97.59 226	99.68 92	99.63 213	98.91 37	99.94 81	98.58 173	99.91 41	99.84 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 91	99.10 90	99.45 141	99.89 8	98.52 225	99.39 241	99.94 1	98.73 90	99.11 237	99.89 36	95.50 198	99.94 81	99.50 50	99.97 8	99.89 25

APD-MVS		99.27 81	99.08 94	99.84 48	99.75 82	99.79 34	99.50 176	99.50 149	97.16 273	99.77 67	99.82 89	98.78 51	99.94 81	97.56 274	99.86 76	99.80 80
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 32	99.42 27	99.65 85	99.72 101	99.40 112	99.05 337	99.66 28	99.14 32	99.57 133	99.80 116	98.46 84	99.94 81	99.57 41	99.84 91	99.60 161
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		99.06 124	98.88 132	99.61 99	99.62 149	99.16 142	99.37 248	99.56 80	98.04 175	99.53 141	99.62 218	96.84 145	99.94 81	98.85 132	98.49 235	99.72 115

DeepC-MVS	98.35 2	99.30 75	99.19 81	99.64 91	99.82 44	99.23 135	99.62 95	99.55 88	98.94 67	99.63 116	99.95 3	95.82 187	99.94 81	99.37 63	99.97 8	99.73 107
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 81	99.12 88	99.74 71	99.18 288	99.75 44	99.56 130	99.57 75	98.45 114	99.49 149	99.85 65	97.77 114	99.94 81	98.33 203	99.84 91	99.52 184

GDP-MVS		99.08 121	98.89 130	99.64 91	99.53 176	99.34 117	99.64 84	99.48 171	98.32 130	99.77 67	99.66 199	95.14 213	99.93 99	98.97 111	99.50 160	99.64 149

SDMVSNet		99.11 115	98.90 127	99.75 68	99.81 48	99.59 80	99.81 20	99.65 35	98.78 86	99.64 113	99.88 44	94.56 247	99.93 99	99.67 32	98.26 248	99.72 115

FE-MVS		98.48 181	98.17 196	99.40 148	99.54 175	98.96 173	99.68 66	98.81 371	95.54 368	99.62 120	99.70 171	93.82 278	99.93 99	97.35 292	99.46 162	99.32 233

SF-MVS		99.38 60	99.24 72	99.79 59	99.79 58	99.68 56	99.57 124	99.54 97	97.82 202	99.71 86	99.80 116	98.95 30	99.93 99	98.19 213	99.84 91	99.74 102

dcpmvs_2		99.23 89	99.58 7	98.16 317	99.83 40	94.68 384	99.76 37	99.52 115	99.07 48	99.98 10	99.88 44	98.56 77	99.93 99	99.67 32	99.98 4	99.87 36

Anonymous20240529		98.09 218	97.68 256	99.34 156	99.66 132	98.44 234	99.40 237	99.43 226	93.67 394	99.22 215	99.89 36	90.23 355	99.93 99	99.26 81	98.33 242	99.66 138

ACMMP_NAP		99.47 35	99.34 45	99.88 11	99.87 15	99.86 16	99.47 201	99.48 171	98.05 174	99.76 73	99.86 58	98.82 46	99.93 99	98.82 142	99.91 41	99.84 49

EI-MVSNet-UG-set		99.58 13	99.57 8	99.64 91	99.78 60	99.14 147	99.60 102	99.45 212	99.01 53	99.90 28	99.83 80	98.98 24	99.93 99	99.59 38	99.95 19	99.86 38

无先验							98.99 353	99.51 129	96.89 299				99.93 99	97.53 277		99.72 115

VDDNet		97.55 305	97.02 326	99.16 188	99.49 199	98.12 250	99.38 246	99.30 294	95.35 370	99.68 92	99.90 30	82.62 414	99.93 99	99.31 73	98.13 260	99.42 216

ab-mvs		98.86 148	98.63 161	99.54 112	99.64 140	99.19 137	99.44 212	99.54 97	97.77 206	99.30 194	99.81 103	94.20 261	99.93 99	99.17 89	98.82 215	99.49 197

F-COLMAP		99.19 91	99.04 99	99.64 91	99.78 60	99.27 130	99.42 224	99.54 97	97.29 262	99.41 168	99.59 227	98.42 88	99.93 99	98.19 213	99.69 139	99.73 107

BP-MVS1		99.12 110	98.94 123	99.65 85	99.51 185	99.30 125	99.67 69	98.92 352	98.48 110	99.84 44	99.69 181	94.96 217	99.92 111	99.62 37	99.79 118	99.71 124

Anonymous202405211		98.30 199	97.98 220	99.26 177	99.57 164	98.16 246	99.41 229	98.55 395	96.03 362	99.19 224	99.74 156	91.87 325	99.92 111	99.16 90	98.29 247	99.70 126

EI-MVSNet-Vis-set		99.58 13	99.56 10	99.64 91	99.78 60	99.15 146	99.61 101	99.45 212	99.01 53	99.89 30	99.82 89	99.01 18	99.92 111	99.56 42	99.95 19	99.85 42

VDD-MVS		97.73 284	97.35 300	98.88 230	99.47 207	97.12 299	99.34 261	98.85 366	98.19 147	99.67 96	99.85 65	82.98 412	99.92 111	99.49 54	98.32 246	99.60 161

VNet		99.11 115	98.90 127	99.73 74	99.52 182	99.56 86	99.41 229	99.39 240	99.01 53	99.74 77	99.78 135	95.56 196	99.92 111	99.52 48	98.18 256	99.72 115

XVG-OURS-SEG-HR		98.69 171	98.62 166	98.89 228	99.71 106	97.74 270	99.12 322	99.54 97	98.44 117	99.42 164	99.71 167	94.20 261	99.92 111	98.54 183	98.90 209	99.00 266

mvsmamba		99.06 124	98.96 119	99.36 154	99.47 207	98.64 210	99.70 56	99.05 336	97.61 225	99.65 108	99.83 80	96.54 158	99.92 111	99.19 85	99.62 150	99.51 192

HPM-MVS_fast		99.51 24	99.40 33	99.85 36	99.91 1	99.79 34	99.76 37	99.56 80	97.72 211	99.76 73	99.75 151	99.13 12	99.92 111	99.07 99	99.92 34	99.85 42

HY-MVS	97.30 7	98.85 155	98.64 160	99.47 138	99.42 219	99.08 155	99.62 95	99.36 257	97.39 254	99.28 198	99.68 188	96.44 164	99.92 111	98.37 198	98.22 251	99.40 221

DP-MVS		99.16 97	98.95 121	99.78 62	99.77 68	99.53 93	99.41 229	99.50 149	97.03 289	99.04 254	99.88 44	97.39 121	99.92 111	98.66 159	99.90 50	99.87 36

IB-MVS	95.67 18	96.22 350	95.44 364	98.57 269	99.21 280	96.70 327	98.65 394	97.74 412	96.71 308	97.27 378	98.54 389	86.03 396	99.92 111	98.47 189	86.30 418	99.10 250
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 28	99.39 35	99.77 65	99.63 143	99.59 80	99.36 253	99.46 201	99.07 48	99.79 58	99.82 89	98.85 42	99.92 111	98.68 157	99.87 68	99.82 64
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 37	99.39 35	99.67 80	99.55 172	99.58 85	99.74 46	99.51 129	98.42 118	99.87 38	99.84 75	98.05 107	99.91 123	99.58 40	99.94 27	99.52 184

9.14			99.10 90		99.72 101		99.40 237	99.51 129	97.53 236	99.64 113	99.78 135	98.84 44	99.91 123	97.63 265	99.82 104

SMA-MVS		99.44 45	99.30 57	99.85 36	99.73 97	99.83 19	99.56 130	99.47 192	97.45 245	99.78 63	99.82 89	99.18 10	99.91 123	98.79 143	99.89 61	99.81 71
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					99.67 122	99.65 67	99.05 337	99.41 231	96.22 347	98.95 269	99.49 265	98.77 54	99.91 123

train_agg		99.02 130	98.77 146	99.77 65	99.67 122	99.65 67	99.05 337	99.41 231	96.28 341	98.95 269	99.49 265	98.76 55	99.91 123	97.63 265	99.72 134	99.75 98

test_8					99.67 122	99.61 77	99.03 342	99.41 231	96.28 341	98.93 272	99.48 271	98.76 55	99.91 123

agg_prior					99.67 122	99.62 75		99.40 237		98.87 282			99.91 123

原ACMM1				99.65 85	99.73 97	99.33 118		99.47 192	97.46 242	99.12 235	99.66 199	98.67 69	99.91 123	97.70 262	99.69 139	99.71 124

LFMVS		97.90 251	97.35 300	99.54 112	99.52 182	99.01 164	99.39 241	98.24 402	97.10 281	99.65 108	99.79 128	84.79 405	99.91 123	99.28 77	98.38 239	99.69 128

XVG-OURS		98.73 169	98.68 155	98.88 230	99.70 111	97.73 271	98.92 367	99.55 88	98.52 107	99.45 154	99.84 75	95.27 206	99.91 123	98.08 224	98.84 213	99.00 266

PLC	97.94 4	99.02 130	98.85 137	99.53 120	99.66 132	99.01 164	99.24 298	99.52 115	96.85 301	99.27 203	99.48 271	98.25 97	99.91 123	97.76 253	99.62 150	99.65 142
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 298	97.06 325	99.47 138	99.61 153	99.09 152	98.04 420	99.25 306	91.24 411	98.51 330	99.70 171	94.55 249	99.91 123	92.76 399	99.85 83	99.42 216
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
mmtdpeth		96.95 336	96.71 335	97.67 355	99.33 246	94.90 381	99.89 2	99.28 300	98.15 152	99.72 84	98.57 388	86.56 394	99.90 135	99.82 25	89.02 413	98.20 383

UWE-MVS		97.58 304	97.29 311	98.48 280	99.09 312	96.25 347	99.01 350	96.61 424	97.86 192	99.19 224	99.01 359	88.72 370	99.90 135	97.38 290	98.69 221	99.28 236

test_vis1_rt		95.81 360	95.65 359	96.32 386	99.67 122	91.35 413	99.49 188	96.74 422	98.25 138	95.24 401	98.10 407	74.96 422	99.90 135	99.53 46	98.85 212	97.70 407

FA-MVS(test-final)		98.75 166	98.53 177	99.41 147	99.55 172	99.05 160	99.80 25	99.01 341	96.59 323	99.58 130	99.59 227	95.39 201	99.90 135	97.78 249	99.49 161	99.28 236

MCST-MVS		99.43 48	99.30 57	99.82 50	99.79 58	99.74 47	99.29 275	99.40 237	98.79 83	99.52 143	99.62 218	98.91 37	99.90 135	98.64 161	99.75 128	99.82 64

CDPH-MVS		99.13 104	98.91 126	99.80 56	99.75 82	99.71 51	99.15 316	99.41 231	96.60 321	99.60 126	99.55 242	98.83 45	99.90 135	97.48 281	99.83 100	99.78 90

NCCC		99.34 68	99.19 81	99.79 59	99.61 153	99.65 67	99.30 270	99.48 171	98.86 73	99.21 218	99.63 213	98.72 64	99.90 135	98.25 209	99.63 149	99.80 80

114514_t		98.93 140	98.67 156	99.72 77	99.85 26	99.53 93	99.62 95	99.59 66	92.65 406	99.71 86	99.78 135	98.06 106	99.90 135	98.84 135	99.91 41	99.74 102

1112_ss		98.98 136	98.77 146	99.59 102	99.68 120	99.02 162	99.25 296	99.48 171	97.23 268	99.13 233	99.58 231	96.93 144	99.90 135	98.87 125	98.78 218	99.84 49

PHI-MVS		99.30 75	99.17 83	99.70 78	99.56 168	99.52 97	99.58 117	99.80 8	97.12 277	99.62 120	99.73 162	98.58 75	99.90 135	98.61 167	99.91 41	99.68 132

AdaColmap		99.01 134	98.80 142	99.66 81	99.56 168	99.54 90	99.18 311	99.70 15	98.18 150	99.35 185	99.63 213	96.32 167	99.90 135	97.48 281	99.77 123	99.55 175

COLMAP_ROB	97.56 6	98.86 148	98.75 148	99.17 187	99.88 11	98.53 221	99.34 261	99.59 66	97.55 232	98.70 308	99.89 36	95.83 186	99.90 135	98.10 219	99.90 50	99.08 255
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 195	98.03 215	99.31 163	99.63 143	98.56 218	99.54 149	96.75 421	97.53 236	99.73 79	99.65 201	91.25 343	99.89 147	98.62 164	99.56 155	99.48 198

tttt0517		98.42 186	98.14 200	99.28 175	99.66 132	98.38 238	99.74 46	96.85 419	97.68 217	99.79 58	99.74 156	91.39 339	99.89 147	98.83 138	99.56 155	99.57 172

test12				99.75 68	99.64 140	99.61 77		99.29 298		99.21 218		98.38 91	99.89 147		99.74 131	99.74 102

Test_1112_low_res		98.89 143	98.66 159	99.57 107	99.69 116	98.95 176	99.03 342	99.47 192	96.98 291	99.15 231	99.23 335	96.77 148	99.89 147	98.83 138	98.78 218	99.86 38

CNLPA		99.14 102	98.99 111	99.59 102	99.58 162	99.41 111	99.16 313	99.44 220	98.45 114	99.19 224	99.49 265	98.08 105	99.89 147	97.73 257	99.75 128	99.48 198

sd_testset		98.75 166	98.57 173	99.29 171	99.81 48	98.26 242	99.56 130	99.62 45	98.78 86	99.64 113	99.88 44	92.02 322	99.88 152	99.54 44	98.26 248	99.72 115

APD_test1		95.87 358	96.49 340	94.00 393	99.53 176	84.01 422	99.54 149	99.32 286	95.91 364	97.99 359	99.85 65	85.49 400	99.88 152	91.96 402	98.84 213	98.12 387

diffmvs		99.14 102	99.02 105	99.51 128	99.61 153	98.96 173	99.28 280	99.49 159	98.46 112	99.72 84	99.71 167	96.50 160	99.88 152	99.31 73	99.11 190	99.67 135
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		98.86 148	98.80 142	99.03 202	99.76 72	98.79 198	99.28 280	99.91 3	97.42 251	99.67 96	99.37 302	97.53 118	99.88 152	98.98 108	97.29 307	98.42 368

PVSNet_Blended		99.08 121	98.97 115	99.42 146	99.76 72	98.79 198	98.78 381	99.91 3	96.74 306	99.67 96	99.49 265	97.53 118	99.88 152	98.98 108	99.85 83	99.60 161

MVS		97.28 325	96.55 338	99.48 134	98.78 359	98.95 176	99.27 285	99.39 240	83.53 424	98.08 354	99.54 247	96.97 142	99.87 157	94.23 380	99.16 184	99.63 154

MG-MVS		99.13 104	99.02 105	99.45 141	99.57 164	98.63 211	99.07 332	99.34 269	98.99 58	99.61 123	99.82 89	97.98 109	99.87 157	97.00 311	99.80 111	99.85 42

MSDG		98.98 136	98.80 142	99.53 120	99.76 72	99.19 137	98.75 384	99.55 88	97.25 265	99.47 151	99.77 144	97.82 112	99.87 157	96.93 318	99.90 50	99.54 177

ETV-MVS		99.26 83	99.21 77	99.40 148	99.46 209	99.30 125	99.56 130	99.52 115	98.52 107	99.44 159	99.27 330	98.41 90	99.86 160	99.10 96	99.59 153	99.04 262

thisisatest0515		98.14 213	97.79 239	99.19 185	99.50 197	98.50 228	98.61 396	96.82 420	96.95 295	99.54 139	99.43 283	91.66 334	99.86 160	98.08 224	99.51 159	99.22 244

thres600view7		97.86 257	97.51 274	98.92 219	99.72 101	97.95 261	99.59 109	98.74 380	97.94 184	99.27 203	98.62 385	91.75 328	99.86 160	93.73 386	98.19 255	98.96 272

lupinMVS		99.13 104	99.01 109	99.46 140	99.51 185	98.94 179	99.05 337	99.16 321	97.86 192	99.80 56	99.56 239	97.39 121	99.86 160	98.94 113	99.85 83	99.58 169

PVSNet	96.02 17	98.85 155	98.84 139	98.89 228	99.73 97	97.28 290	98.32 412	99.60 60	97.86 192	99.50 146	99.57 236	96.75 149	99.86 160	98.56 179	99.70 138	99.54 177

MAR-MVS		98.86 148	98.63 161	99.54 112	99.37 237	99.66 63	99.45 206	99.54 97	96.61 318	99.01 257	99.40 293	97.09 135	99.86 160	97.68 264	99.53 158	99.10 250
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		97.44 317	97.02 326	98.71 257	99.18 288	96.89 321	99.19 309	99.04 337	97.78 205	98.31 341	98.29 399	85.41 401	99.85 166	98.01 230	97.95 265	99.39 222

test2506		96.81 340	96.65 336	97.29 367	99.74 90	92.21 410	99.60 102	85.06 441	99.13 33	99.77 67	99.93 10	87.82 387	99.85 166	99.38 62	99.38 167	99.80 80

AllTest		98.87 145	98.72 150	99.31 163	99.86 20	98.48 231	99.56 130	99.61 53	97.85 195	99.36 182	99.85 65	95.95 179	99.85 166	96.66 331	99.83 100	99.59 165

TestCases				99.31 163	99.86 20	98.48 231		99.61 53	97.85 195	99.36 182	99.85 65	95.95 179	99.85 166	96.66 331	99.83 100	99.59 165

jason		99.13 104	99.03 101	99.45 141	99.46 209	98.87 186	99.12 322	99.26 304	98.03 177	99.79 58	99.65 201	97.02 140	99.85 166	99.02 105	99.90 50	99.65 142
jason: jason.
CNVR-MVS		99.42 50	99.30 57	99.78 62	99.62 149	99.71 51	99.26 294	99.52 115	98.82 78	99.39 175	99.71 167	98.96 25	99.85 166	98.59 172	99.80 111	99.77 92

PAPM_NR		99.04 127	98.84 139	99.66 81	99.74 90	99.44 107	99.39 241	99.38 248	97.70 215	99.28 198	99.28 327	98.34 93	99.85 166	96.96 315	99.45 163	99.69 128

testing99		97.36 320	96.94 329	98.63 262	99.18 288	96.70 327	99.30 270	98.93 349	97.71 212	98.23 346	98.26 400	84.92 404	99.84 173	98.04 229	97.85 272	99.35 228

testing222		97.16 330	96.50 339	99.16 188	99.16 298	98.47 233	99.27 285	98.66 391	97.71 212	98.23 346	98.15 403	82.28 417	99.84 173	97.36 291	97.66 278	99.18 246

test1111		98.04 228	98.11 204	97.83 345	99.74 90	93.82 395	99.58 117	95.40 428	99.12 38	99.65 108	99.93 10	90.73 348	99.84 173	99.43 60	99.38 167	99.82 64

ECVR-MVS		98.04 228	98.05 213	98.00 330	99.74 90	94.37 390	99.59 109	94.98 429	99.13 33	99.66 101	99.93 10	90.67 349	99.84 173	99.40 61	99.38 167	99.80 80

test_yl		98.86 148	98.63 161	99.54 112	99.49 199	99.18 139	99.50 176	99.07 333	98.22 143	99.61 123	99.51 259	95.37 202	99.84 173	98.60 170	98.33 242	99.59 165

DCV-MVSNet		98.86 148	98.63 161	99.54 112	99.49 199	99.18 139	99.50 176	99.07 333	98.22 143	99.61 123	99.51 259	95.37 202	99.84 173	98.60 170	98.33 242	99.59 165

Fast-Effi-MVS+		98.70 170	98.43 181	99.51 128	99.51 185	99.28 128	99.52 159	99.47 192	96.11 357	99.01 257	99.34 312	96.20 171	99.84 173	97.88 238	98.82 215	99.39 222

TSAR-MVS + GP.		99.36 65	99.36 41	99.36 154	99.67 122	98.61 215	99.07 332	99.33 276	99.00 56	99.82 51	99.81 103	99.06 16	99.84 173	99.09 97	99.42 165	99.65 142

tpmrst		98.33 196	98.48 179	97.90 339	99.16 298	94.78 382	99.31 268	99.11 326	97.27 263	99.45 154	99.59 227	95.33 204	99.84 173	98.48 186	98.61 224	99.09 254

Vis-MVSNet		99.12 110	98.97 115	99.56 109	99.78 60	99.10 151	99.68 66	99.66 28	98.49 109	99.86 42	99.87 54	94.77 233	99.84 173	99.19 85	99.41 166	99.74 102
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 177	98.34 187	99.51 128	99.40 229	99.03 161	98.80 379	99.36 257	96.33 338	99.00 261	99.12 349	98.46 84	99.84 173	95.23 366	99.37 174	99.66 138

PatchMatch-RL		98.84 158	98.62 166	99.52 126	99.71 106	99.28 128	99.06 335	99.77 9	97.74 210	99.50 146	99.53 251	95.41 200	99.84 173	97.17 305	99.64 147	99.44 214

EPP-MVSNet		99.13 104	98.99 111	99.53 120	99.65 138	99.06 158	99.81 20	99.33 276	97.43 249	99.60 126	99.88 44	97.14 133	99.84 173	99.13 91	98.94 204	99.69 128

testing3-2		97.84 262	97.70 254	98.24 312	99.53 176	95.37 371	99.55 144	98.67 390	98.46 112	99.27 203	99.34 312	86.58 393	99.83 186	99.32 72	98.63 223	99.52 184

testing11		97.50 310	97.10 323	98.71 257	99.20 282	96.91 319	99.29 275	98.82 369	97.89 189	98.21 349	98.40 394	85.63 399	99.83 186	98.45 191	98.04 263	99.37 226

thres100view900		97.76 276	97.45 283	98.69 259	99.72 101	97.86 267	99.59 109	98.74 380	97.93 185	99.26 208	98.62 385	91.75 328	99.83 186	93.22 391	98.18 256	98.37 374

tfpn200view9		97.72 286	97.38 296	98.72 255	99.69 116	97.96 259	99.50 176	98.73 386	97.83 198	99.17 229	98.45 392	91.67 332	99.83 186	93.22 391	98.18 256	98.37 374

test_prior				99.68 79	99.67 122	99.48 102		99.56 80					99.83 186			99.74 102

1314		98.68 172	98.54 176	99.11 194	98.89 343	98.65 208	99.27 285	99.49 159	96.89 299	97.99 359	99.56 239	97.72 116	99.83 186	97.74 256	99.27 178	98.84 278

thres400		97.77 275	97.38 296	98.92 219	99.69 116	97.96 259	99.50 176	98.73 386	97.83 198	99.17 229	98.45 392	91.67 332	99.83 186	93.22 391	98.18 256	98.96 272

casdiffmvs		99.13 104	98.98 114	99.56 109	99.65 138	99.16 142	99.56 130	99.50 149	98.33 129	99.41 168	99.86 58	95.92 182	99.83 186	99.45 59	99.16 184	99.70 126
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 28	99.48 19	99.54 112	99.78 60	99.30 125	99.89 2	99.58 70	98.56 103	99.73 79	99.69 181	98.55 78	99.82 194	99.69 30	99.85 83	99.48 198

MVS_Test		99.10 119	98.97 115	99.48 134	99.49 199	99.14 147	99.67 69	99.34 269	97.31 260	99.58 130	99.76 148	97.65 117	99.82 194	98.87 125	99.07 196	99.46 209

dp		97.75 280	97.80 238	97.59 359	99.10 309	93.71 398	99.32 265	98.88 362	96.48 330	99.08 245	99.55 242	92.67 306	99.82 194	96.52 335	98.58 227	99.24 242

RPSCF		98.22 203	98.62 166	96.99 373	99.82 44	91.58 412	99.72 52	99.44 220	96.61 318	99.66 101	99.89 36	95.92 182	99.82 194	97.46 284	99.10 193	99.57 172

PMMVS		98.80 162	98.62 166	99.34 156	99.27 264	98.70 204	98.76 383	99.31 290	97.34 257	99.21 218	99.07 351	97.20 132	99.82 194	98.56 179	98.87 210	99.52 184

UBG		97.85 258	97.48 277	98.95 213	99.25 271	97.64 278	99.24 298	98.74 380	97.90 188	98.64 318	98.20 402	88.65 374	99.81 199	98.27 208	98.40 237	99.42 216

EIA-MVS		99.18 93	99.09 93	99.45 141	99.49 199	99.18 139	99.67 69	99.53 110	97.66 220	99.40 173	99.44 281	98.10 103	99.81 199	98.94 113	99.62 150	99.35 228

Effi-MVS+		98.81 159	98.59 172	99.48 134	99.46 209	99.12 150	98.08 419	99.50 149	97.50 240	99.38 177	99.41 289	96.37 166	99.81 199	99.11 93	98.54 232	99.51 192

thres200		97.61 302	97.28 312	98.62 263	99.64 140	98.03 253	99.26 294	98.74 380	97.68 217	99.09 243	98.32 398	91.66 334	99.81 199	92.88 396	98.22 251	98.03 393

tpmvs		97.98 239	98.02 217	97.84 344	99.04 322	94.73 383	99.31 268	99.20 316	96.10 361	98.76 298	99.42 285	94.94 219	99.81 199	96.97 314	98.45 236	98.97 270

casdiffmvs_mvg		99.15 99	99.02 105	99.55 111	99.66 132	99.09 152	99.64 84	99.56 80	98.26 137	99.45 154	99.87 54	96.03 176	99.81 199	99.54 44	99.15 187	99.73 107
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	98.81 159	99.37 39	97.12 371	99.60 158	91.75 411	98.61 396	99.44 220	99.35 21	99.83 50	99.85 65	98.70 66	99.81 199	99.02 105	99.91 41	99.81 71

DPM-MVS		98.95 139	98.71 152	99.66 81	99.63 143	99.55 88	98.64 395	99.10 327	97.93 185	99.42 164	99.55 242	98.67 69	99.80 206	95.80 351	99.68 142	99.61 158

DP-MVS Recon		99.12 110	98.95 121	99.65 85	99.74 90	99.70 53	99.27 285	99.57 75	96.40 337	99.42 164	99.68 188	98.75 58	99.80 206	97.98 232	99.72 134	99.44 214

MVS_111021_LR		99.41 54	99.33 47	99.65 85	99.77 68	99.51 98	98.94 365	99.85 6	98.82 78	99.65 108	99.74 156	98.51 81	99.80 206	98.83 138	99.89 61	99.64 149

CS-MVS		99.50 26	99.48 19	99.54 112	99.76 72	99.42 109	99.90 1	99.55 88	98.56 103	99.78 63	99.70 171	98.65 71	99.79 209	99.65 34	99.78 120	99.41 219

Fast-Effi-MVS+-dtu		98.77 165	98.83 141	98.60 264	99.41 224	96.99 313	99.52 159	99.49 159	98.11 160	99.24 210	99.34 312	96.96 143	99.79 209	97.95 234	99.45 163	99.02 265

baseline1		98.31 197	97.95 224	99.38 153	99.50 197	98.74 201	99.59 109	98.93 349	98.41 119	99.14 232	99.60 225	94.59 245	99.79 209	98.48 186	93.29 389	99.61 158

baseline		99.15 99	99.02 105	99.53 120	99.66 132	99.14 147	99.72 52	99.48 171	98.35 126	99.42 164	99.84 75	96.07 174	99.79 209	99.51 49	99.14 188	99.67 135

PVSNet_0	94.43 19	96.09 355	95.47 362	97.94 335	99.31 254	94.34 392	97.81 421	99.70 15	97.12 277	97.46 372	98.75 382	89.71 360	99.79 209	97.69 263	81.69 424	99.68 132

API-MVS		99.04 127	99.03 101	99.06 198	99.40 229	99.31 123	99.55 144	99.56 80	98.54 105	99.33 189	99.39 297	98.76 55	99.78 214	96.98 313	99.78 120	98.07 390

OMC-MVS		99.08 121	99.04 99	99.20 184	99.67 122	98.22 244	99.28 280	99.52 115	98.07 168	99.66 101	99.81 103	97.79 113	99.78 214	97.79 248	99.81 107	99.60 161

GeoE		98.85 155	98.62 166	99.53 120	99.61 153	99.08 155	99.80 25	99.51 129	97.10 281	99.31 191	99.78 135	95.23 210	99.77 216	98.21 211	99.03 199	99.75 98

alignmvs		98.81 159	98.56 175	99.58 105	99.43 217	99.42 109	99.51 168	98.96 347	98.61 99	99.35 185	98.92 372	94.78 230	99.77 216	99.35 64	98.11 261	99.54 177

tpm cat1		97.39 319	97.36 298	97.50 362	99.17 296	93.73 397	99.43 217	99.31 290	91.27 410	98.71 302	99.08 350	94.31 259	99.77 216	96.41 340	98.50 234	99.00 266

CostFormer		97.72 286	97.73 251	97.71 353	99.15 302	94.02 394	99.54 149	99.02 340	94.67 385	99.04 254	99.35 308	92.35 318	99.77 216	98.50 185	97.94 266	99.34 231

MGCFI-Net		99.01 134	98.85 137	99.50 133	99.42 219	99.26 131	99.82 16	99.48 171	98.60 100	99.28 198	98.81 377	97.04 139	99.76 220	99.29 76	97.87 270	99.47 204

test_241102_ONE					99.84 32	99.90 2		99.48 171	99.07 48	99.91 26	99.74 156	99.20 7	99.76 220

MDTV_nov1_ep13			98.32 189		99.11 306	94.44 388	99.27 285	98.74 380	97.51 239	99.40 173	99.62 218	94.78 230	99.76 220	97.59 268	98.81 217

sasdasda		99.02 130	98.86 135	99.51 128	99.42 219	99.32 119	99.80 25	99.48 171	98.63 96	99.31 191	98.81 377	97.09 135	99.75 223	99.27 79	97.90 267	99.47 204

canonicalmvs		99.02 130	98.86 135	99.51 128	99.42 219	99.32 119	99.80 25	99.48 171	98.63 96	99.31 191	98.81 377	97.09 135	99.75 223	99.27 79	97.90 267	99.47 204

Effi-MVS+-dtu		98.78 163	98.89 130	98.47 285	99.33 246	96.91 319	99.57 124	99.30 294	98.47 111	99.41 168	98.99 362	96.78 147	99.74 225	98.73 149	99.38 167	98.74 293

patchmatchnet-post											98.70 383	94.79 229	99.74 225

SCA		98.19 207	98.16 197	98.27 311	99.30 255	95.55 362	99.07 332	98.97 345	97.57 229	99.43 161	99.57 236	92.72 301	99.74 225	97.58 269	99.20 182	99.52 184

BH-untuned		98.42 186	98.36 185	98.59 265	99.49 199	96.70 327	99.27 285	99.13 325	97.24 267	98.80 293	99.38 299	95.75 189	99.74 225	97.07 309	99.16 184	99.33 232

BH-RMVSNet		98.41 188	98.08 209	99.40 148	99.41 224	98.83 194	99.30 270	98.77 376	97.70 215	98.94 271	99.65 201	92.91 296	99.74 225	96.52 335	99.55 157	99.64 149

MVS_111021_HR		99.41 54	99.32 49	99.66 81	99.72 101	99.47 104	98.95 363	99.85 6	98.82 78	99.54 139	99.73 162	98.51 81	99.74 225	98.91 119	99.88 65	99.77 92

test_post											65.99 435	94.65 243	99.73 231

XVG-ACMP-BASELINE		97.83 265	97.71 253	98.20 314	99.11 306	96.33 343	99.41 229	99.52 115	98.06 172	99.05 253	99.50 262	89.64 362	99.73 231	97.73 257	97.38 305	98.53 356

HyFIR lowres test		99.11 115	98.92 124	99.65 85	99.90 4	99.37 113	99.02 345	99.91 3	97.67 219	99.59 129	99.75 151	95.90 184	99.73 231	99.53 46	99.02 201	99.86 38

DeepMVS_CX				93.34 396	99.29 259	82.27 425		99.22 312	85.15 422	96.33 393	99.05 354	90.97 346	99.73 231	93.57 388	97.77 275	98.01 394

Patchmatch-test		97.93 245	97.65 259	98.77 251	99.18 288	97.07 304	99.03 342	99.14 324	96.16 352	98.74 299	99.57 236	94.56 247	99.72 235	93.36 390	99.11 190	99.52 184

LPG-MVS_test		98.22 203	98.13 202	98.49 278	99.33 246	97.05 306	99.58 117	99.55 88	97.46 242	99.24 210	99.83 80	92.58 308	99.72 235	98.09 220	97.51 291	98.68 311

LGP-MVS_train				98.49 278	99.33 246	97.05 306		99.55 88	97.46 242	99.24 210	99.83 80	92.58 308	99.72 235	98.09 220	97.51 291	98.68 311

BH-w/o		98.00 237	97.89 233	98.32 303	99.35 241	96.20 349	99.01 350	98.90 359	96.42 335	98.38 337	99.00 360	95.26 208	99.72 235	96.06 344	98.61 224	99.03 263

ACMP	97.20 11	98.06 222	97.94 226	98.45 288	99.37 237	97.01 311	99.44 212	99.49 159	97.54 235	98.45 334	99.79 128	91.95 324	99.72 235	97.91 236	97.49 296	98.62 339
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 232	97.90 229	98.40 296	99.23 275	96.80 325	99.70 56	99.60 60	97.12 277	98.18 351	99.70 171	91.73 330	99.72 235	98.39 195	97.45 298	98.68 311
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							99.23 301				65.14 436	94.18 264	99.71 241	97.58 269

ADS-MVSNet		98.20 206	98.08 209	98.56 272	99.33 246	96.48 338	99.23 301	99.15 322	96.24 345	99.10 240	99.67 194	94.11 265	99.71 241	96.81 323	99.05 197	99.48 198

JIA-IIPM		97.50 310	97.02 326	98.93 217	98.73 368	97.80 269	99.30 270	98.97 345	91.73 409	98.91 274	94.86 424	95.10 214	99.71 241	97.58 269	97.98 264	99.28 236

EPMVS		97.82 268	97.65 259	98.35 300	98.88 344	95.98 353	99.49 188	94.71 431	97.57 229	99.26 208	99.48 271	92.46 315	99.71 241	97.87 240	99.08 195	99.35 228

TDRefinement		95.42 364	94.57 371	97.97 332	89.83 434	96.11 352	99.48 193	98.75 377	96.74 306	96.68 390	99.88 44	88.65 374	99.71 241	98.37 198	82.74 423	98.09 389

ACMM	97.58 5	98.37 194	98.34 187	98.48 280	99.41 224	97.10 300	99.56 130	99.45 212	98.53 106	99.04 254	99.85 65	93.00 292	99.71 241	98.74 147	97.45 298	98.64 330
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 242	97.77 244	98.57 269	99.59 160	96.61 334	99.45 206	99.08 330	98.21 145	98.88 279	99.80 116	88.66 373	99.70 247	98.58 173	97.72 276	99.39 222

CHOSEN 280x420		99.12 110	99.13 86	99.08 195	99.66 132	97.89 264	98.43 406	99.71 13	98.88 72	99.62 120	99.76 148	96.63 153	99.70 247	99.46 58	99.99 1	99.66 138

EC-MVSNet		99.44 45	99.39 35	99.58 105	99.56 168	99.49 100	99.88 4	99.58 70	98.38 121	99.73 79	99.69 181	98.20 99	99.70 247	99.64 36	99.82 104	99.54 177

PatchmatchNet		98.31 197	98.36 185	98.19 315	99.16 298	95.32 372	99.27 285	98.92 352	97.37 255	99.37 179	99.58 231	94.90 223	99.70 247	97.43 287	99.21 181	99.54 177
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 217	97.99 219	98.44 291	99.41 224	96.96 317	99.60 102	99.56 80	98.09 163	98.15 352	99.91 23	90.87 347	99.70 247	98.88 122	97.45 298	98.67 318
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 310	96.90 330	99.29 171	99.23 275	98.78 200	99.32 265	98.90 359	97.52 238	98.56 327	98.09 408	84.72 406	99.69 252	97.86 241	97.88 269	99.39 222

HQP_MVS		98.27 202	98.22 195	98.44 291	99.29 259	96.97 315	99.39 241	99.47 192	98.97 64	99.11 237	99.61 222	92.71 303	99.69 252	97.78 249	97.63 279	98.67 318

plane_prior5								99.47 192					99.69 252	97.78 249	97.63 279	98.67 318

D2MVS		98.41 188	98.50 178	98.15 320	99.26 267	96.62 333	99.40 237	99.61 53	97.71 212	98.98 264	99.36 305	96.04 175	99.67 255	98.70 152	97.41 303	98.15 386

IS-MVSNet		99.05 126	98.87 133	99.57 107	99.73 97	99.32 119	99.75 42	99.20 316	98.02 179	99.56 134	99.86 58	96.54 158	99.67 255	98.09 220	99.13 189	99.73 107

CLD-MVS		98.16 211	98.10 205	98.33 301	99.29 259	96.82 324	98.75 384	99.44 220	97.83 198	99.13 233	99.55 242	92.92 294	99.67 255	98.32 205	97.69 277	98.48 360
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 327	97.30 309	97.09 372	99.43 217	93.31 403	99.73 50	98.87 364	98.83 77	99.28 198	99.80 116	84.45 407	99.66 258	97.88 238	97.45 298	98.30 376

AUN-MVS		96.88 338	96.31 344	98.59 265	99.48 206	97.04 309	99.27 285	99.22 312	97.44 248	98.51 330	99.41 289	91.97 323	99.66 258	97.71 260	83.83 421	99.07 260

UniMVSNet_ETH3D		97.32 324	96.81 332	98.87 234	99.40 229	97.46 284	99.51 168	99.53 110	95.86 365	98.54 329	99.77 144	82.44 415	99.66 258	98.68 157	97.52 290	99.50 196

OPM-MVS		98.19 207	98.10 205	98.45 288	98.88 344	97.07 304	99.28 280	99.38 248	98.57 102	99.22 215	99.81 103	92.12 320	99.66 258	98.08 224	97.54 288	98.61 348
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 248	97.78 242	98.32 303	99.46 209	96.68 331	99.56 130	99.54 97	98.41 119	97.79 368	99.87 54	90.18 356	99.66 258	98.05 228	97.18 312	98.62 339

hse-mvs2		97.50 310	97.14 320	98.59 265	99.49 199	97.05 306	99.28 280	99.22 312	98.94 67	99.66 101	99.42 285	94.93 220	99.65 263	99.48 55	83.80 422	99.08 255

VPA-MVSNet		98.29 200	97.95 224	99.30 168	99.16 298	99.54 90	99.50 176	99.58 70	98.27 135	99.35 185	99.37 302	92.53 310	99.65 263	99.35 64	94.46 371	98.72 295

TR-MVS		97.76 276	97.41 294	98.82 243	99.06 318	97.87 265	98.87 373	98.56 394	96.63 317	98.68 310	99.22 336	92.49 311	99.65 263	95.40 362	97.79 274	98.95 274

reproduce_monomvs		97.89 252	97.87 234	97.96 334	99.51 185	95.45 367	99.60 102	99.25 306	99.17 28	98.85 287	99.49 265	89.29 365	99.64 266	99.35 64	96.31 328	98.78 281

gm-plane-assit					98.54 388	92.96 405			94.65 386		99.15 344		99.64 266	97.56 274

HQP4-MVS										98.66 311			99.64 266			98.64 330

HQP-MVS		98.02 232	97.90 229	98.37 299	99.19 285	96.83 322	98.98 356	99.39 240	98.24 139	98.66 311	99.40 293	92.47 312	99.64 266	97.19 302	97.58 284	98.64 330

PAPM		97.59 303	97.09 324	99.07 196	99.06 318	98.26 242	98.30 413	99.10 327	94.88 380	98.08 354	99.34 312	96.27 169	99.64 266	89.87 410	98.92 207	99.31 234

TAPA-MVS	97.07 15	97.74 282	97.34 303	98.94 215	99.70 111	97.53 281	99.25 296	99.51 129	91.90 408	99.30 194	99.63 213	98.78 51	99.64 266	88.09 417	99.87 68	99.65 142
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 192	98.09 208	99.24 180	99.26 267	99.32 119	99.56 130	99.55 88	97.45 245	98.71 302	99.83 80	93.23 287	99.63 272	98.88 122	96.32 327	98.76 287

ITE_SJBPF				98.08 323	99.29 259	96.37 341		98.92 352	98.34 127	98.83 288	99.75 151	91.09 344	99.62 273	95.82 349	97.40 304	98.25 380

LF4IMVS		97.52 307	97.46 282	97.70 354	98.98 333	95.55 362	99.29 275	98.82 369	98.07 168	98.66 311	99.64 207	89.97 357	99.61 274	97.01 310	96.68 317	97.94 401

tpm		97.67 297	97.55 268	98.03 325	99.02 324	95.01 378	99.43 217	98.54 396	96.44 333	99.12 235	99.34 312	91.83 327	99.60 275	97.75 255	96.46 323	99.48 198

tpm2		97.44 317	97.34 303	97.74 352	99.15 302	94.36 391	99.45 206	98.94 348	93.45 399	98.90 276	99.44 281	91.35 340	99.59 276	97.31 293	98.07 262	99.29 235

baseline2		97.87 255	97.55 268	98.82 243	99.18 288	98.02 254	99.41 229	96.58 425	96.97 292	96.51 391	99.17 341	93.43 284	99.57 277	97.71 260	99.03 199	98.86 276

MS-PatchMatch		97.24 329	97.32 307	96.99 373	98.45 391	93.51 402	98.82 377	99.32 286	97.41 252	98.13 353	99.30 323	88.99 367	99.56 278	95.68 355	99.80 111	97.90 404

TinyColmap		97.12 332	96.89 331	97.83 345	99.07 316	95.52 365	98.57 399	98.74 380	97.58 228	97.81 367	99.79 128	88.16 381	99.56 278	95.10 367	97.21 310	98.39 372

USDC		97.34 322	97.20 317	97.75 350	99.07 316	95.20 374	98.51 403	99.04 337	97.99 180	98.31 341	99.86 58	89.02 366	99.55 280	95.67 356	97.36 306	98.49 359

MSLP-MVS++		99.46 37	99.47 21	99.44 145	99.60 158	99.16 142	99.41 229	99.71 13	98.98 61	99.45 154	99.78 135	99.19 9	99.54 281	99.28 77	99.84 91	99.63 154

UWE-MVS-28		97.36 320	97.24 316	97.75 350	98.84 353	94.44 388	99.24 298	97.58 414	97.98 181	99.00 261	99.00 360	91.35 340	99.53 282	93.75 385	98.39 238	99.27 240

TAMVS		99.12 110	99.08 94	99.24 180	99.46 209	98.55 219	99.51 168	99.46 201	98.09 163	99.45 154	99.82 89	98.34 93	99.51 283	98.70 152	98.93 205	99.67 135

EPNet_dtu		98.03 230	97.96 222	98.23 313	98.27 394	95.54 364	99.23 301	98.75 377	99.02 51	97.82 366	99.71 167	96.11 173	99.48 284	93.04 394	99.65 146	99.69 128
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 342	96.22 346	97.97 332	97.00 416	96.28 345	98.66 393	99.03 339	96.61 318	96.93 388	99.79 128	87.20 390	99.47 285	96.65 333	94.13 378	98.16 385

EG-PatchMatch MVS		95.97 357	95.69 358	96.81 380	97.78 401	92.79 406	99.16 313	98.93 349	96.16 352	94.08 409	99.22 336	82.72 413	99.47 285	95.67 356	97.50 293	98.17 384

myMVS_eth3d28		97.69 291	97.34 303	98.73 253	99.27 264	97.52 282	99.33 263	98.78 375	98.03 177	98.82 290	98.49 390	86.64 392	99.46 287	98.44 192	98.24 250	99.23 243

MVP-Stereo		97.81 270	97.75 249	97.99 331	97.53 405	96.60 335	98.96 360	98.85 366	97.22 269	97.23 379	99.36 305	95.28 205	99.46 287	95.51 358	99.78 120	97.92 403
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 179	98.67 156	98.30 305	99.35 241	95.59 361	99.50 176	99.55 88	98.60 100	99.39 175	99.83 80	94.48 252	99.45 289	98.75 146	98.56 230	99.85 42

test-LLR		98.06 222	97.90 229	98.55 274	98.79 356	97.10 300	98.67 390	97.75 410	97.34 257	98.61 323	98.85 374	94.45 254	99.45 289	97.25 296	99.38 167	99.10 250

TESTMET0.1,1		97.55 305	97.27 315	98.40 296	98.93 338	96.53 336	98.67 390	97.61 413	96.96 293	98.64 318	99.28 327	88.63 376	99.45 289	97.30 294	99.38 167	99.21 245

test-mter		97.49 315	97.13 322	98.55 274	98.79 356	97.10 300	98.67 390	97.75 410	96.65 313	98.61 323	98.85 374	88.23 380	99.45 289	97.25 296	99.38 167	99.10 250

mvs_anonymous		99.03 129	98.99 111	99.16 188	99.38 234	98.52 225	99.51 168	99.38 248	97.79 203	99.38 177	99.81 103	97.30 127	99.45 289	99.35 64	98.99 202	99.51 192

tfpnnormal		97.84 262	97.47 280	98.98 208	99.20 282	99.22 136	99.64 84	99.61 53	96.32 339	98.27 345	99.70 171	93.35 286	99.44 294	95.69 354	95.40 354	98.27 378

v7n		97.87 255	97.52 272	98.92 219	98.76 366	98.58 217	99.84 12	99.46 201	96.20 348	98.91 274	99.70 171	94.89 224	99.44 294	96.03 345	93.89 383	98.75 289

jajsoiax		98.43 185	98.28 192	98.88 230	98.60 383	98.43 235	99.82 16	99.53 110	98.19 147	98.63 320	99.80 116	93.22 289	99.44 294	99.22 83	97.50 293	98.77 285

mvs_tets		98.40 191	98.23 194	98.91 223	98.67 376	98.51 227	99.66 75	99.53 110	98.19 147	98.65 317	99.81 103	92.75 298	99.44 294	99.31 73	97.48 297	98.77 285

Vis-MVSNet (Re-imp)		98.87 145	98.72 150	99.31 163	99.71 106	98.88 185	99.80 25	99.44 220	97.91 187	99.36 182	99.78 135	95.49 199	99.43 298	97.91 236	99.11 190	99.62 156

OPU-MVS				99.64 91	99.56 168	99.72 49	99.60 102				99.70 171	99.27 5	99.42 299	98.24 210	99.80 111	99.79 84

Anonymous20231211		97.88 253	97.54 271	98.90 225	99.71 106	98.53 221	99.48 193	99.57 75	94.16 390	98.81 291	99.68 188	93.23 287	99.42 299	98.84 135	94.42 373	98.76 287

ttmdpeth		97.80 272	97.63 263	98.29 306	98.77 364	97.38 287	99.64 84	99.36 257	98.78 86	96.30 394	99.58 231	92.34 319	99.39 301	98.36 200	95.58 349	98.10 388

VPNet		97.84 262	97.44 288	99.01 204	99.21 280	98.94 179	99.48 193	99.57 75	98.38 121	99.28 198	99.73 162	88.89 368	99.39 301	99.19 85	93.27 390	98.71 297

nrg030		98.64 176	98.42 182	99.28 175	99.05 321	99.69 55	99.81 20	99.46 201	98.04 175	99.01 257	99.82 89	96.69 151	99.38 303	99.34 69	94.59 370	98.78 281

GA-MVS		97.85 258	97.47 280	99.00 206	99.38 234	97.99 256	98.57 399	99.15 322	97.04 288	98.90 276	99.30 323	89.83 359	99.38 303	96.70 328	98.33 242	99.62 156

UniMVSNet (Re)		98.29 200	98.00 218	99.13 193	99.00 327	99.36 116	99.49 188	99.51 129	97.95 183	98.97 266	99.13 346	96.30 168	99.38 303	98.36 200	93.34 388	98.66 326

FIs		98.78 163	98.63 161	99.23 182	99.18 288	99.54 90	99.83 15	99.59 66	98.28 133	98.79 295	99.81 103	96.75 149	99.37 306	99.08 98	96.38 325	98.78 281

PS-MVSNAJss		98.92 141	98.92 124	98.90 225	98.78 359	98.53 221	99.78 32	99.54 97	98.07 168	99.00 261	99.76 148	99.01 18	99.37 306	99.13 91	97.23 309	98.81 279

CDS-MVSNet		99.09 120	99.03 101	99.25 178	99.42 219	98.73 202	99.45 206	99.46 201	98.11 160	99.46 153	99.77 144	98.01 108	99.37 306	98.70 152	98.92 207	99.66 138
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 361	95.16 366	97.51 361	99.30 255	93.69 399	98.88 371	95.78 426	85.09 423	98.78 296	92.65 426	91.29 342	99.37 306	94.85 372	99.85 83	99.46 209

v1192		97.81 270	97.44 288	98.91 223	98.88 344	98.68 205	99.51 168	99.34 269	96.18 350	99.20 221	99.34 312	94.03 269	99.36 310	95.32 364	95.18 358	98.69 306

EI-MVSNet		98.67 173	98.67 156	98.68 260	99.35 241	97.97 257	99.50 176	99.38 248	96.93 298	99.20 221	99.83 80	97.87 110	99.36 310	98.38 196	97.56 286	98.71 297

MVSTER		98.49 180	98.32 189	99.00 206	99.35 241	99.02 162	99.54 149	99.38 248	97.41 252	99.20 221	99.73 162	93.86 277	99.36 310	98.87 125	97.56 286	98.62 339

gg-mvs-nofinetune		96.17 353	95.32 365	98.73 253	98.79 356	98.14 248	99.38 246	94.09 432	91.07 413	98.07 357	91.04 430	89.62 363	99.35 313	96.75 325	99.09 194	98.68 311

pm-mvs1		97.68 294	97.28 312	98.88 230	99.06 318	98.62 213	99.50 176	99.45 212	96.32 339	97.87 364	99.79 128	92.47 312	99.35 313	97.54 276	93.54 387	98.67 318

OurMVSNet-221017-0		97.88 253	97.77 244	98.19 315	98.71 372	96.53 336	99.88 4	99.00 342	97.79 203	98.78 296	99.94 6	91.68 331	99.35 313	97.21 298	96.99 316	98.69 306

EGC-MVSNET		82.80 395	77.86 401	97.62 357	97.91 398	96.12 351	99.33 263	99.28 300	8.40 438	25.05 439	99.27 330	84.11 408	99.33 316	89.20 412	98.22 251	97.42 412

pmmvs6		96.53 345	96.09 350	97.82 347	98.69 374	95.47 366	99.37 248	99.47 192	93.46 398	97.41 373	99.78 135	87.06 391	99.33 316	96.92 320	92.70 397	98.65 328

V42		98.06 222	97.79 239	98.86 237	98.98 333	98.84 191	99.69 60	99.34 269	96.53 325	99.30 194	99.37 302	94.67 241	99.32 318	97.57 273	94.66 368	98.42 368

lessismore_v0				97.79 349	98.69 374	95.44 369		94.75 430		95.71 400	99.87 54	88.69 372	99.32 318	95.89 348	94.93 365	98.62 339

OpenMVS_ROB	92.34 20	94.38 375	93.70 381	96.41 385	97.38 407	93.17 404	99.06 335	98.75 377	86.58 421	94.84 407	98.26 400	81.53 418	99.32 318	89.01 413	97.87 270	96.76 415

v8		97.95 244	97.63 263	98.93 217	98.95 337	98.81 197	99.80 25	99.41 231	96.03 362	99.10 240	99.42 285	94.92 222	99.30 321	96.94 317	94.08 380	98.66 326

v1921920		97.80 272	97.45 283	98.84 241	98.80 355	98.53 221	99.52 159	99.34 269	96.15 354	99.24 210	99.47 274	93.98 271	99.29 322	95.40 362	95.13 360	98.69 306

anonymousdsp		98.44 184	98.28 192	98.94 215	98.50 389	98.96 173	99.77 34	99.50 149	97.07 283	98.87 282	99.77 144	94.76 234	99.28 323	98.66 159	97.60 282	98.57 354

MVSFormer		99.17 95	99.12 88	99.29 171	99.51 185	98.94 179	99.88 4	99.46 201	97.55 232	99.80 56	99.65 201	97.39 121	99.28 323	99.03 103	99.85 83	99.65 142

test_djsdf		98.67 173	98.57 173	98.98 208	98.70 373	98.91 183	99.88 4	99.46 201	97.55 232	99.22 215	99.88 44	95.73 190	99.28 323	99.03 103	97.62 281	98.75 289

SSC-MVS3.2		97.34 322	97.15 319	97.93 336	99.02 324	95.76 358	99.48 193	99.58 70	97.62 224	99.09 243	99.53 251	87.95 383	99.27 326	96.42 338	95.66 347	98.75 289

cascas		97.69 291	97.43 292	98.48 280	98.60 383	97.30 289	98.18 417	99.39 240	92.96 402	98.41 335	98.78 381	93.77 280	99.27 326	98.16 217	98.61 224	98.86 276

v144192		97.92 248	97.60 266	98.87 234	98.83 354	98.65 208	99.55 144	99.34 269	96.20 348	99.32 190	99.40 293	94.36 256	99.26 328	96.37 341	95.03 362	98.70 302

dmvs_re		98.08 220	98.16 197	97.85 342	99.55 172	94.67 385	99.70 56	98.92 352	98.15 152	99.06 251	99.35 308	93.67 283	99.25 329	97.77 252	97.25 308	99.64 149

v2v482		98.06 222	97.77 244	98.92 219	98.90 342	98.82 195	99.57 124	99.36 257	96.65 313	99.19 224	99.35 308	94.20 261	99.25 329	97.72 259	94.97 363	98.69 306

v1240		97.69 291	97.32 307	98.79 249	98.85 351	98.43 235	99.48 193	99.36 257	96.11 357	99.27 203	99.36 305	93.76 281	99.24 331	94.46 376	95.23 357	98.70 302

WBMVS		97.74 282	97.50 275	98.46 286	99.24 273	97.43 285	99.21 307	99.42 228	97.45 245	98.96 268	99.41 289	88.83 369	99.23 332	98.94 113	96.02 333	98.71 297

v1144		97.98 239	97.69 255	98.85 240	98.87 347	98.66 207	99.54 149	99.35 264	96.27 343	99.23 214	99.35 308	94.67 241	99.23 332	96.73 326	95.16 359	98.68 311

v10		97.85 258	97.52 272	98.86 237	98.99 330	98.67 206	99.75 42	99.41 231	95.70 366	98.98 264	99.41 289	94.75 235	99.23 332	96.01 347	94.63 369	98.67 318

WR-MVS_H		98.13 214	97.87 234	98.90 225	99.02 324	98.84 191	99.70 56	99.59 66	97.27 263	98.40 336	99.19 340	95.53 197	99.23 332	98.34 202	93.78 385	98.61 348

miper_enhance_ethall		98.16 211	98.08 209	98.41 294	98.96 336	97.72 273	98.45 405	99.32 286	96.95 295	98.97 266	99.17 341	97.06 138	99.22 336	97.86 241	95.99 336	98.29 377

GG-mvs-BLEND				98.45 288	98.55 387	98.16 246	99.43 217	93.68 433		97.23 379	98.46 391	89.30 364	99.22 336	95.43 361	98.22 251	97.98 399

FC-MVSNet-test		98.75 166	98.62 166	99.15 192	99.08 315	99.45 106	99.86 11	99.60 60	98.23 142	98.70 308	99.82 89	96.80 146	99.22 336	99.07 99	96.38 325	98.79 280

UniMVSNet_NR-MVSNet		98.22 203	97.97 221	98.96 211	98.92 340	98.98 166	99.48 193	99.53 110	97.76 207	98.71 302	99.46 278	96.43 165	99.22 336	98.57 176	92.87 395	98.69 306

DU-MVS		98.08 220	97.79 239	98.96 211	98.87 347	98.98 166	99.41 229	99.45 212	97.87 191	98.71 302	99.50 262	94.82 226	99.22 336	98.57 176	92.87 395	98.68 311

cl____		98.01 235	97.84 237	98.55 274	99.25 271	97.97 257	98.71 388	99.34 269	96.47 332	98.59 326	99.54 247	95.65 193	99.21 341	97.21 298	95.77 342	98.46 365

WR-MVS		98.06 222	97.73 251	99.06 198	98.86 350	99.25 133	99.19 309	99.35 264	97.30 261	98.66 311	99.43 283	93.94 272	99.21 341	98.58 173	94.28 375	98.71 297

test_0402		96.64 343	96.24 345	97.85 342	98.85 351	96.43 340	99.44 212	99.26 304	93.52 396	96.98 386	99.52 255	88.52 377	99.20 343	92.58 401	97.50 293	97.93 402

SixPastTwentyTwo		97.50 310	97.33 306	98.03 325	98.65 377	96.23 348	99.77 34	98.68 389	97.14 274	97.90 362	99.93 10	90.45 350	99.18 344	97.00 311	96.43 324	98.67 318

cl22		97.85 258	97.64 262	98.48 280	99.09 312	97.87 265	98.60 398	99.33 276	97.11 280	98.87 282	99.22 336	92.38 317	99.17 345	98.21 211	95.99 336	98.42 368

WB-MVSnew		97.65 299	97.65 259	97.63 356	98.78 359	97.62 279	99.13 319	98.33 399	97.36 256	99.07 246	98.94 368	95.64 194	99.15 346	92.95 395	98.68 222	96.12 422

IterMVS-SCA-FT		97.82 268	97.75 249	98.06 324	99.57 164	96.36 342	99.02 345	99.49 159	97.18 271	98.71 302	99.72 166	92.72 301	99.14 347	97.44 286	95.86 341	98.67 318

pmmvs5		97.52 307	97.30 309	98.16 317	98.57 386	96.73 326	99.27 285	98.90 359	96.14 355	98.37 338	99.53 251	91.54 337	99.14 347	97.51 278	95.87 340	98.63 337

v148		97.79 274	97.55 268	98.50 277	98.74 367	97.72 273	99.54 149	99.33 276	96.26 344	98.90 276	99.51 259	94.68 240	99.14 347	97.83 245	93.15 392	98.63 337

miper_ehance_all_eth		98.18 209	98.10 205	98.41 294	99.23 275	97.72 273	98.72 387	99.31 290	96.60 321	98.88 279	99.29 325	97.29 128	99.13 350	97.60 267	95.99 336	98.38 373

NR-MVSNet		97.97 242	97.61 265	99.02 203	98.87 347	99.26 131	99.47 201	99.42 228	97.63 222	97.08 384	99.50 262	95.07 215	99.13 350	97.86 241	93.59 386	98.68 311

IterMVS		97.83 265	97.77 244	98.02 327	99.58 162	96.27 346	99.02 345	99.48 171	97.22 269	98.71 302	99.70 171	92.75 298	99.13 350	97.46 284	96.00 335	98.67 318
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 376	94.90 368	91.84 401	97.24 411	80.01 431	98.52 402	99.48 171	89.01 418	91.99 418	99.67 194	85.67 398	99.13 350	95.44 360	97.03 315	96.39 419
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 227	97.96 222	98.33 301	99.26 267	97.38 287	98.56 401	99.31 290	96.65 313	98.88 279	99.52 255	96.58 156	99.12 354	97.39 289	95.53 352	98.47 362

pmmvs4		98.13 214	97.90 229	98.81 246	98.61 382	98.87 186	98.99 353	99.21 315	96.44 333	99.06 251	99.58 231	95.90 184	99.11 355	97.18 304	96.11 332	98.46 365

TransMVSNet (Re)		97.15 331	96.58 337	98.86 237	99.12 304	98.85 190	99.49 188	98.91 357	95.48 369	97.16 382	99.80 116	93.38 285	99.11 355	94.16 382	91.73 401	98.62 339

ambc				93.06 399	92.68 430	82.36 424	98.47 404	98.73 386		95.09 405	97.41 413	55.55 431	99.10 357	96.42 338	91.32 402	97.71 405

Baseline_NR-MVSNet		97.76 276	97.45 283	98.68 260	99.09 312	98.29 240	99.41 229	98.85 366	95.65 367	98.63 320	99.67 194	94.82 226	99.10 357	98.07 227	92.89 394	98.64 330

test_vis3_rt		87.04 391	85.81 394	90.73 405	93.99 429	81.96 426	99.76 37	90.23 440	92.81 404	81.35 428	91.56 428	40.06 437	99.07 359	94.27 379	88.23 415	91.15 428

CP-MVSNet		98.09 218	97.78 242	99.01 204	98.97 335	99.24 134	99.67 69	99.46 201	97.25 265	98.48 333	99.64 207	93.79 279	99.06 360	98.63 163	94.10 379	98.74 293

PS-CasMVS		97.93 245	97.59 267	98.95 213	98.99 330	99.06 158	99.68 66	99.52 115	97.13 275	98.31 341	99.68 188	92.44 316	99.05 361	98.51 184	94.08 380	98.75 289

K. test v3		97.10 333	96.79 333	98.01 328	98.72 370	96.33 343	99.87 8	97.05 417	97.59 226	96.16 396	99.80 116	88.71 371	99.04 362	96.69 329	96.55 322	98.65 328

new_pmnet		96.38 349	96.03 351	97.41 363	98.13 397	95.16 377	99.05 337	99.20 316	93.94 391	97.39 376	98.79 380	91.61 336	99.04 362	90.43 408	95.77 342	98.05 392

DIV-MVS_self_test		98.01 235	97.85 236	98.48 280	99.24 273	97.95 261	98.71 388	99.35 264	96.50 326	98.60 325	99.54 247	95.72 191	99.03 364	97.21 298	95.77 342	98.46 365

IterMVS-LS		98.46 183	98.42 182	98.58 268	99.59 160	98.00 255	99.37 248	99.43 226	96.94 297	99.07 246	99.59 227	97.87 110	99.03 364	98.32 205	95.62 348	98.71 297
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 299	97.68 256	97.55 360	98.62 380	94.97 379	98.84 375	99.30 294	96.83 304	98.19 350	99.34 312	97.01 141	99.02 366	95.00 370	96.01 334	98.64 330

Patchmtry		97.75 280	97.40 295	98.81 246	99.10 309	98.87 186	99.11 328	99.33 276	94.83 382	98.81 291	99.38 299	94.33 257	99.02 366	96.10 343	95.57 350	98.53 356

N_pmnet		94.95 370	95.83 356	92.31 400	98.47 390	79.33 432	99.12 322	92.81 438	93.87 392	97.68 369	99.13 346	93.87 276	99.01 368	91.38 405	96.19 330	98.59 352

CR-MVSNet		98.17 210	97.93 227	98.87 234	99.18 288	98.49 229	99.22 305	99.33 276	96.96 293	99.56 134	99.38 299	94.33 257	99.00 369	94.83 373	98.58 227	99.14 247

c3_l		98.12 216	98.04 214	98.38 298	99.30 255	97.69 277	98.81 378	99.33 276	96.67 311	98.83 288	99.34 312	97.11 134	98.99 370	97.58 269	95.34 355	98.48 360

test0.0.03 1		97.71 289	97.42 293	98.56 272	98.41 393	97.82 268	98.78 381	98.63 392	97.34 257	98.05 358	98.98 364	94.45 254	98.98 371	95.04 369	97.15 313	98.89 275

PatchT		97.03 335	96.44 341	98.79 249	98.99 330	98.34 239	99.16 313	99.07 333	92.13 407	99.52 143	97.31 417	94.54 250	98.98 371	88.54 415	98.73 220	99.03 263

GBi-Net		97.68 294	97.48 277	98.29 306	99.51 185	97.26 293	99.43 217	99.48 171	96.49 327	99.07 246	99.32 320	90.26 352	98.98 371	97.10 306	96.65 318	98.62 339

test1		97.68 294	97.48 277	98.29 306	99.51 185	97.26 293	99.43 217	99.48 171	96.49 327	99.07 246	99.32 320	90.26 352	98.98 371	97.10 306	96.65 318	98.62 339

FMVSNet3		98.03 230	97.76 248	98.84 241	99.39 232	98.98 166	99.40 237	99.38 248	96.67 311	99.07 246	99.28 327	92.93 293	98.98 371	97.10 306	96.65 318	98.56 355

FMVSNet2		97.72 286	97.36 298	98.80 248	99.51 185	98.84 191	99.45 206	99.42 228	96.49 327	98.86 286	99.29 325	90.26 352	98.98 371	96.44 337	96.56 321	98.58 353

FMVSNet1		96.84 339	96.36 343	98.29 306	99.32 253	97.26 293	99.43 217	99.48 171	95.11 374	98.55 328	99.32 320	83.95 409	98.98 371	95.81 350	96.26 329	98.62 339

ppachtmachnet_test		97.49 315	97.45 283	97.61 358	98.62 380	95.24 373	98.80 379	99.46 201	96.11 357	98.22 348	99.62 218	96.45 163	98.97 378	93.77 384	95.97 339	98.61 348

TranMVSNet+NR-MVSNet		97.93 245	97.66 258	98.76 252	98.78 359	98.62 213	99.65 81	99.49 159	97.76 207	98.49 332	99.60 225	94.23 260	98.97 378	98.00 231	92.90 393	98.70 302

MVStest1		96.08 356	95.48 361	97.89 340	98.93 338	96.70 327	99.56 130	99.35 264	92.69 405	91.81 419	99.46 278	89.90 358	98.96 380	95.00 370	92.61 398	98.00 397

test_method		91.10 386	91.36 388	90.31 406	95.85 419	73.72 439	94.89 427	99.25 306	68.39 430	95.82 399	99.02 358	80.50 420	98.95 381	93.64 387	94.89 367	98.25 380

ADS-MVSNet2		98.02 232	98.07 212	97.87 341	99.33 246	95.19 375	99.23 301	99.08 330	96.24 345	99.10 240	99.67 194	94.11 265	98.93 382	96.81 323	99.05 197	99.48 198

ET-MVSNet_ETH3D		96.49 346	95.64 360	99.05 200	99.53 176	98.82 195	98.84 375	97.51 415	97.63 222	84.77 424	99.21 339	92.09 321	98.91 383	98.98 108	92.21 400	99.41 219

miper_lstm_enhance		98.00 237	97.91 228	98.28 310	99.34 245	97.43 285	98.88 371	99.36 257	96.48 330	98.80 293	99.55 242	95.98 177	98.91 383	97.27 295	95.50 353	98.51 358

MonoMVSNet		98.38 192	98.47 180	98.12 322	98.59 385	96.19 350	99.72 52	98.79 374	97.89 189	99.44 159	99.52 255	96.13 172	98.90 385	98.64 161	97.54 288	99.28 236

PEN-MVS		97.76 276	97.44 288	98.72 255	98.77 364	98.54 220	99.78 32	99.51 129	97.06 285	98.29 344	99.64 207	92.63 307	98.89 386	98.09 220	93.16 391	98.72 295

testing3		97.28 325	96.76 334	98.82 243	99.37 237	98.07 252	99.45 206	99.36 257	97.56 231	97.89 363	98.95 367	83.70 410	98.82 387	96.03 345	98.56 230	99.58 169

testgi		97.65 299	97.50 275	98.13 321	99.36 240	96.45 339	99.42 224	99.48 171	97.76 207	97.87 364	99.45 280	91.09 344	98.81 388	94.53 375	98.52 233	99.13 249

testf1		90.42 389	90.68 390	89.65 409	97.78 401	73.97 437	99.13 319	98.81 371	89.62 415	91.80 420	98.93 369	62.23 429	98.80 389	86.61 423	91.17 403	96.19 420

APD_test2		90.42 389	90.68 390	89.65 409	97.78 401	73.97 437	99.13 319	98.81 371	89.62 415	91.80 420	98.93 369	62.23 429	98.80 389	86.61 423	91.17 403	96.19 420

MIMVSNet		97.73 284	97.45 283	98.57 269	99.45 215	97.50 283	99.02 345	98.98 344	96.11 357	99.41 168	99.14 345	90.28 351	98.74 391	95.74 352	98.93 205	99.47 204

LCM-MVSNet-Re		97.83 265	98.15 199	96.87 379	99.30 255	92.25 409	99.59 109	98.26 400	97.43 249	96.20 395	99.13 346	96.27 169	98.73 392	98.17 216	98.99 202	99.64 149

Syy-MVS		97.09 334	97.14 320	96.95 376	99.00 327	92.73 407	99.29 275	99.39 240	97.06 285	97.41 373	98.15 403	93.92 274	98.68 393	91.71 403	98.34 240	99.45 212

myMVS_eth3d		96.89 337	96.37 342	98.43 293	99.00 327	97.16 297	99.29 275	99.39 240	97.06 285	97.41 373	98.15 403	83.46 411	98.68 393	95.27 365	98.34 240	99.45 212

DTE-MVSNet		97.51 309	97.19 318	98.46 286	98.63 379	98.13 249	99.84 12	99.48 171	96.68 310	97.97 361	99.67 194	92.92 294	98.56 395	96.88 322	92.60 399	98.70 302

PC_three_1452									98.18 150	99.84 44	99.70 171	99.31 3	98.52 396	98.30 207	99.80 111	99.81 71

mvsany_test3		93.77 378	93.45 382	94.74 391	95.78 420	88.01 417	99.64 84	98.25 401	98.28 133	94.31 408	97.97 410	68.89 425	98.51 397	97.50 279	90.37 408	97.71 405

UnsupCasMVSNet_bld		93.53 379	92.51 385	96.58 384	97.38 407	93.82 395	98.24 414	99.48 171	91.10 412	93.10 413	96.66 419	74.89 423	98.37 398	94.03 383	87.71 416	97.56 410

Anonymous20240521		96.20 352	95.89 355	97.13 370	97.72 404	94.96 380	99.79 31	99.29 298	93.01 401	97.20 381	99.03 356	89.69 361	98.36 399	91.16 406	96.13 331	98.07 390

test_f		91.90 385	91.26 389	93.84 394	95.52 424	85.92 419	99.69 60	98.53 397	95.31 371	93.87 410	96.37 421	55.33 432	98.27 400	95.70 353	90.98 406	97.32 413

MDA-MVSNet_test_wron		95.45 363	94.60 370	98.01 328	98.16 396	97.21 296	99.11 328	99.24 309	93.49 397	80.73 430	98.98 364	93.02 291	98.18 401	94.22 381	94.45 372	98.64 330

UnsupCasMVSNet_eth		96.44 347	96.12 348	97.40 364	98.65 377	95.65 359	99.36 253	99.51 129	97.13 275	96.04 398	98.99 362	88.40 378	98.17 402	96.71 327	90.27 409	98.40 371

KD-MVS_2432*1600		94.62 371	93.72 379	97.31 365	97.19 413	95.82 356	98.34 409	99.20 316	95.00 378	97.57 370	98.35 396	87.95 383	98.10 403	92.87 397	77.00 428	98.01 394

miper_refine_blended		94.62 371	93.72 379	97.31 365	97.19 413	95.82 356	98.34 409	99.20 316	95.00 378	97.57 370	98.35 396	87.95 383	98.10 403	92.87 397	77.00 428	98.01 394

YYNet1		95.36 365	94.51 372	97.92 337	97.89 399	97.10 300	99.10 330	99.23 310	93.26 400	80.77 429	99.04 355	92.81 297	98.02 405	94.30 377	94.18 377	98.64 330

EU-MVSNet		97.98 239	98.03 215	97.81 348	98.72 370	96.65 332	99.66 75	99.66 28	98.09 163	98.35 339	99.82 89	95.25 209	98.01 406	97.41 288	95.30 356	98.78 281

Gipuma		90.99 387	90.15 392	93.51 395	98.73 368	90.12 415	93.98 428	99.45 212	79.32 426	92.28 416	94.91 423	69.61 424	97.98 407	87.42 419	95.67 346	92.45 426
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 366	94.73 369	97.15 368	95.53 423	95.94 354	99.35 258	99.10 327	95.13 372	93.55 411	97.54 412	88.15 382	97.91 408	94.58 374	89.69 412	97.61 408

PM-MVS		92.96 382	92.23 386	95.14 390	95.61 421	89.98 416	99.37 248	98.21 403	94.80 383	95.04 406	97.69 411	65.06 426	97.90 409	94.30 377	89.98 411	97.54 411

MDA-MVSNet-bldmvs		94.96 369	93.98 376	97.92 337	98.24 395	97.27 291	99.15 316	99.33 276	93.80 393	80.09 431	99.03 356	88.31 379	97.86 410	93.49 389	94.36 374	98.62 339

Patchmatch-RL test		95.84 359	95.81 357	95.95 388	95.61 421	90.57 414	98.24 414	98.39 398	95.10 376	95.20 403	98.67 384	94.78 230	97.77 411	96.28 342	90.02 410	99.51 192

Anonymous20231206		96.22 350	96.03 351	96.79 381	97.31 410	94.14 393	99.63 90	99.08 330	96.17 351	97.04 385	99.06 353	93.94 272	97.76 412	86.96 421	95.06 361	98.47 362

SD-MVS		99.41 54	99.52 12	99.05 200	99.74 90	99.68 56	99.46 204	99.52 115	99.11 39	99.88 33	99.91 23	99.43 1	97.70 413	98.72 150	99.93 29	99.77 92
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		97.25 327	97.35 300	96.95 376	97.84 400	93.61 401	99.57 124	96.63 423	96.13 356	98.87 282	98.61 387	94.59 245	97.70 413	95.08 368	98.86 211	99.55 175

dongtai		93.26 380	92.93 384	94.25 392	99.39 232	85.68 420	97.68 423	93.27 434	92.87 403	96.85 389	99.39 297	82.33 416	97.48 415	76.78 428	97.80 273	99.58 169

pmmvs3		94.09 377	93.25 383	96.60 383	94.76 428	94.49 387	98.92 367	98.18 405	89.66 414	96.48 392	98.06 409	86.28 395	97.33 416	89.68 411	87.20 417	97.97 400

KD-MVS_self_test		95.00 368	94.34 373	96.96 375	97.07 415	95.39 370	99.56 130	99.44 220	95.11 374	97.13 383	97.32 416	91.86 326	97.27 417	90.35 409	81.23 425	98.23 382

FMVSNet5		96.43 348	96.19 347	97.15 368	99.11 306	95.89 355	99.32 265	99.52 115	94.47 389	98.34 340	99.07 351	87.54 388	97.07 418	92.61 400	95.72 345	98.47 362

new-patchmatchnet		94.48 374	94.08 375	95.67 389	95.08 426	92.41 408	99.18 311	99.28 300	94.55 388	93.49 412	97.37 415	87.86 386	97.01 419	91.57 404	88.36 414	97.61 408

LCM-MVSNet		86.80 393	85.22 397	91.53 403	87.81 435	80.96 429	98.23 416	98.99 343	71.05 428	90.13 423	96.51 420	48.45 436	96.88 420	90.51 407	85.30 419	96.76 415

CL-MVSNet_self_test		94.49 373	93.97 377	96.08 387	96.16 418	93.67 400	98.33 411	99.38 248	95.13 372	97.33 377	98.15 403	92.69 305	96.57 421	88.67 414	79.87 426	97.99 398

MIMVSNet1		95.51 362	95.04 367	96.92 378	97.38 407	95.60 360	99.52 159	99.50 149	93.65 395	96.97 387	99.17 341	85.28 403	96.56 422	88.36 416	95.55 351	98.60 351

test20.03		96.12 354	95.96 353	96.63 382	97.44 406	95.45 367	99.51 168	99.38 248	96.55 324	96.16 396	99.25 333	93.76 281	96.17 423	87.35 420	94.22 376	98.27 378

tmp_tt		82.80 395	81.52 398	86.66 411	66.61 441	68.44 440	92.79 430	97.92 407	68.96 429	80.04 432	99.85 65	85.77 397	96.15 424	97.86 241	43.89 434	95.39 424

test_fmvs3		92.10 384	91.77 387	93.08 398	96.19 417	86.25 418	99.82 16	98.62 393	96.65 313	95.19 404	96.90 418	55.05 433	95.93 425	96.63 334	90.92 407	97.06 414

kuosan		90.92 388	90.11 393	93.34 396	98.78 359	85.59 421	98.15 418	93.16 436	89.37 417	92.07 417	98.38 395	81.48 419	95.19 426	62.54 435	97.04 314	99.25 241

dmvs_testset		95.02 367	96.12 348	91.72 402	99.10 309	80.43 430	99.58 117	97.87 409	97.47 241	95.22 402	98.82 376	93.99 270	95.18 427	88.09 417	94.91 366	99.56 174

PMMVS2		86.87 392	85.37 396	91.35 404	90.21 433	83.80 423	98.89 370	97.45 416	83.13 425	91.67 422	95.03 422	48.49 435	94.70 428	85.86 425	77.62 427	95.54 423

PMVS	70.75 22	75.98 401	74.97 402	79.01 417	70.98 440	55.18 442	93.37 429	98.21 403	65.08 434	61.78 435	93.83 425	21.74 442	92.53 429	78.59 427	91.12 405	89.34 430
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 394	85.65 395	82.75 415	86.77 436	63.39 441	98.35 408	98.92 352	74.11 427	83.39 426	98.98 364	50.85 434	92.40 430	84.54 426	94.97 363	92.46 425

WB-MVS		93.10 381	94.10 374	90.12 407	95.51 425	81.88 427	99.73 50	99.27 303	95.05 377	93.09 414	98.91 373	94.70 239	91.89 431	76.62 429	94.02 382	96.58 417

SSC-MVS		92.73 383	93.73 378	89.72 408	95.02 427	81.38 428	99.76 37	99.23 310	94.87 381	92.80 415	98.93 369	94.71 238	91.37 432	74.49 431	93.80 384	96.42 418

MVE	76.82 21	76.91 400	74.31 404	84.70 412	85.38 438	76.05 436	96.88 426	93.17 435	67.39 431	71.28 433	89.01 432	21.66 443	87.69 433	71.74 432	72.29 430	90.35 429
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 397	79.88 399	82.81 414	90.75 432	76.38 435	97.69 422	95.76 427	66.44 432	83.52 425	92.25 427	62.54 428	87.16 434	68.53 433	61.40 431	84.89 432

EMVS		80.02 398	79.22 400	82.43 416	91.19 431	76.40 434	97.55 425	92.49 439	66.36 433	83.01 427	91.27 429	64.63 427	85.79 435	65.82 434	60.65 432	85.08 431

ANet_high		77.30 399	74.86 403	84.62 413	75.88 439	77.61 433	97.63 424	93.15 437	88.81 419	64.27 434	89.29 431	36.51 438	83.93 436	75.89 430	52.31 433	92.33 427

wuyk23d		40.18 402	41.29 407	36.84 418	86.18 437	49.12 443	79.73 431	22.81 443	27.64 435	25.46 438	28.45 438	21.98 441	48.89 437	55.80 436	23.56 437	12.51 435

test123		39.01 404	42.50 406	28.53 419	39.17 442	20.91 444	98.75 384	19.17 444	19.83 437	38.57 436	66.67 434	33.16 439	15.42 438	37.50 438	29.66 436	49.26 433

testmvs		39.17 403	43.78 405	25.37 420	36.04 443	16.84 445	98.36 407	26.56 442	20.06 436	38.51 437	67.32 433	29.64 440	15.30 439	37.59 437	39.90 435	43.98 434

mmdepth		0.02 409	0.03 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.27 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		0.02 409	0.03 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.27 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		0.13 408	0.17 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	1.57 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet_test		0.02 409	0.03 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.27 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		0.02 409	0.03 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.27 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

cdsmvs_eth3d_5k		24.64 405	32.85 408	0.00 421	0.00 444	0.00 446	0.00 432	99.51 129	0.00 439	0.00 440	99.56 239	96.58 156	0.00 440	0.00 439	0.00 438	0.00 436

pcd_1.5k_mvsjas		8.27 407	11.03 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.27 440	99.01 18	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		0.02 409	0.03 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.27 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		0.02 409	0.03 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.27 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		0.02 409	0.03 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.27 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		0.02 409	0.03 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.27 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

ab-mvs-re		8.30 406	11.06 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	99.58 231	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		0.02 409	0.03 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.27 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

WAC-MVS						97.16 297								95.47 359

FOURS1					99.91 1	99.93 1	99.87 8	99.56 80	99.10 40	99.81 52

test_one_0601					99.81 48	99.88 8		99.49 159	98.97 64	99.65 108	99.81 103	99.09 14

eth-test2					0.00 444

eth-test					0.00 444

RE-MVS-def			99.34 45		99.76 72	99.82 25	99.63 90	99.52 115	98.38 121	99.76 73	99.82 89	98.75 58		98.61 167	99.81 107	99.77 92

IU-MVS					99.84 32	99.88 8		99.32 286	98.30 132	99.84 44				98.86 130	99.85 83	99.89 25

save fliter					99.76 72	99.59 80	99.14 318	99.40 237	99.00 56

test0726					99.85 26	99.89 4	99.62 95	99.50 149	99.10 40	99.86 42	99.82 89	98.94 32

GSMVS																99.52 184

test_part2					99.81 48	99.83 19				99.77 67

sam_mvs1												94.86 225				99.52 184

sam_mvs												94.72 237

MTGPA								99.47 192

MTMP							99.54 149	98.88 362

test9_res														97.49 280	99.72 134	99.75 98

agg_prior2														97.21 298	99.73 133	99.75 98

test_prior4						99.56 86	98.99 353

test_prior2							98.96 360		98.34 127	99.01 257	99.52 255	98.68 67		97.96 233	99.74 131

新几何2							99.01 350

旧先验1					99.74 90	99.59 80		99.54 97			99.69 181	98.47 83			99.68 142	99.73 107

原ACMM2							98.95 363

test222					99.75 82	99.49 100	98.91 369	99.49 159	96.42 335	99.34 188	99.65 201	98.28 96			99.69 139	99.72 115

segment_acmp												98.96 25

testdata1							98.85 374		98.32 130

plane_prior7					99.29 259	97.03 310

plane_prior6					99.27 264	96.98 314						92.71 303

plane_prior4											99.61 222

plane_prior3						97.00 312			98.69 93	99.11 237

plane_prior2							99.39 241		98.97 64

plane_prior1					99.26 267

plane_prior						96.97 315	99.21 307		98.45 114						97.60 282

n2								0.00 445

nn								0.00 445

door-mid								98.05 406

test11								99.35 264

door								97.92 407

HQP5-MVS						96.83 322

HQP-NCC					99.19 285		98.98 356		98.24 139	98.66 311

ACMP_Plane					99.19 285		98.98 356		98.24 139	98.66 311

BP-MVS														97.19 302

HQP3-MVS								99.39 240							97.58 284

HQP2-MVS												92.47 312

NP-MVS					99.23 275	96.92 318					99.40 293

MDTV_nov1_ep13_2view						95.18 376	99.35 258		96.84 302	99.58 130		95.19 211		97.82 246		99.46 209

ACMMP++_ref															97.19 311

ACMMP++															97.43 302

Test By Simon												98.75 58

High-resolution multi-view benchmark