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	99.38 236	99.37 113	99.58 118	99.62 45	99.41 17	99.87 40	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	99.58 118	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		98.63 179	98.40 186	99.31 164	99.86 20	97.94 265	99.67 69	99.62 45	99.43 13	99.99 2	99.91 23	87.29 391	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	99.42 226	99.61 53	99.37 20	99.97 21	99.86 60	94.96 219	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	99.54 151	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	99.56 132	99.63 42	99.48 3	99.98 10	99.83 83	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	99.56 132	99.63 42	99.47 4	99.98 10	99.82 92	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	99.48 195	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	98.16 319	99.81 48	94.59 391	99.52 161	99.64 38	99.33 22	99.73 81	99.90 30	99.00 22	99.99 4	99.69 31	99.98 4	99.89 25

h-mvs33		97.70 292	97.28 314	98.97 212	99.70 111	97.27 293	99.36 255	99.45 213	98.94 67	99.66 103	99.64 212	94.93 222	99.99 4	99.48 57	84.36 425	99.65 144

xiu_mvs_v1_base_debu		99.29 77	99.27 67	99.34 157	99.63 145	98.97 169	99.12 327	99.51 130	98.86 73	99.84 46	99.47 279	98.18 100	99.99 4	99.50 52	99.31 177	99.08 258

xiu_mvs_v1_base		99.29 77	99.27 67	99.34 157	99.63 145	98.97 169	99.12 327	99.51 130	98.86 73	99.84 46	99.47 279	98.18 100	99.99 4	99.50 52	99.31 177	99.08 258

xiu_mvs_v1_base_debi		99.29 77	99.27 67	99.34 157	99.63 145	98.97 169	99.12 327	99.51 130	98.86 73	99.84 46	99.47 279	98.18 100	99.99 4	99.50 52	99.31 177	99.08 258

EPNet		98.86 150	98.71 154	99.30 169	97.20 417	98.18 246	99.62 95	98.91 360	99.28 25	98.63 322	99.81 106	95.96 178	99.99 4	99.24 84	99.72 135	99.73 109
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	99.51 170	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	99.67 123	99.31 123	99.52 161	98.87 367	99.55 1	99.74 79	99.80 119	96.47 161	99.98 15	99.97 1	99.97 8	99.94 14

test_cas_vis1_n_1920		99.16 97	99.01 111	99.61 99	99.81 48	98.86 190	99.65 81	99.64 38	99.39 18	99.97 21	99.94 6	93.20 292	99.98 15	99.55 45	99.91 41	99.99 1

test_vis1_n		97.92 250	97.44 290	99.34 157	99.53 178	98.08 253	99.74 46	99.49 160	99.15 30	100.00 1	99.94 6	79.51 426	99.98 15	99.88 22	99.76 127	99.97 4

xiu_mvs_v2_base		99.26 83	99.25 71	99.29 172	99.53 178	98.91 184	99.02 350	99.45 213	98.80 83	99.71 88	99.26 337	98.94 32	99.98 15	99.34 71	99.23 182	98.98 272

PS-MVSNAJ		99.32 72	99.32 49	99.30 169	99.57 166	98.94 179	98.97 364	99.46 202	98.92 70	99.71 88	99.24 339	99.01 18	99.98 15	99.35 66	99.66 146	98.97 273

QAPM		98.67 175	98.30 193	99.80 56	99.20 284	99.67 60	99.77 34	99.72 11	94.74 386	98.73 302	99.90 30	95.78 189	99.98 15	96.96 319	99.88 65	99.76 97

3Dnovator	97.25 9	99.24 88	99.05 97	99.81 53	99.12 306	99.66 63	99.84 12	99.74 10	99.09 45	98.92 275	99.90 30	95.94 181	99.98 15	98.95 114	99.92 34	99.79 84

OpenMVS	96.50 16	98.47 184	98.12 205	99.52 126	99.04 325	99.53 93	99.82 16	99.72 11	94.56 389	98.08 356	99.88 44	94.73 238	99.98 15	97.47 286	99.76 127	99.06 264

fmvsm_s_conf0.5_n_3		99.37 61	99.20 79	99.87 17	99.75 82	99.70 53	99.48 195	99.66 28	99.45 10	99.99 2	99.93 10	94.64 246	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	99.56 132	99.55 88	99.15 30	99.90 29	99.90 30	99.00 22	99.97 24	99.11 95	99.91 41	99.86 38

test_fmvsmconf0.1_n		99.55 18	99.45 25	99.86 28	99.44 218	99.65 67	99.50 178	99.61 53	99.45 10	99.87 40	99.92 17	97.31 126	99.97 24	99.95 12	99.99 1	99.97 4

test_fmvs1_n		98.41 190	98.14 202	99.21 185	99.82 44	97.71 278	99.74 46	99.49 160	99.32 23	99.99 2	99.95 3	85.32 404	99.97 24	99.82 25	99.84 91	99.96 7

CANet_DTU		98.97 140	98.87 135	99.25 179	99.33 248	98.42 238	99.08 336	99.30 297	99.16 29	99.43 163	99.75 154	95.27 208	99.97 24	98.56 181	99.95 19	99.36 230

MVS_0304		99.15 100	98.96 121	99.73 74	98.92 343	99.37 113	99.37 250	96.92 423	99.51 2	99.66 103	99.78 138	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	99.47 193	98.79 84	99.68 94	99.81 106	98.43 86	99.97 24	98.88 124	99.90 50	99.83 59

PGM-MVS		99.45 41	99.31 55	99.86 28	99.87 15	99.78 40	99.58 118	99.65 35	97.84 199	99.71 88	99.80 119	99.12 13	99.97 24	98.33 205	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	99.48 172	98.12 160	99.50 148	99.75 154	98.78 51	99.97 24	98.57 178	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	98.07 170	99.53 143	99.63 218	98.93 36	99.97 24	98.74 149	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	99.51 130	98.62 100	99.79 60	99.83 83	99.28 4	99.97 24	98.48 188	99.90 50	99.84 49
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 93	98.97 117	99.82 50	99.17 298	99.68 56	99.81 20	99.51 130	99.20 27	98.72 303	99.89 36	95.68 193	99.97 24	98.86 132	99.86 76	99.81 71

fmvsm_s_conf0.5_n_7		99.34 68	99.29 61	99.48 135	99.70 111	98.63 212	99.42 226	99.63 42	99.46 7	99.98 10	99.88 44	95.59 196	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	99.44 214	99.58 70	99.47 4	99.99 2	99.93 10	94.04 270	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	99.52 161	99.54 97	99.13 33	99.89 32	99.89 36	98.96 25	99.96 36	99.04 103	99.90 50	99.85 42

our_new_method		99.61 8	99.52 12	99.90 5	99.76 72	99.88 8	99.52 161	99.54 97	99.13 33	99.89 32	99.89 36	98.96 25	99.96 36	99.04 103	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	99.52 161	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	99.51 170	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	99.61 155	99.09 152	98.94 370	99.48 172	99.10 40	99.96 23	99.91 23	98.85 42	99.96 36	99.72 28	99.58 156	99.82 64

test_fmvs1		98.88 146	98.79 147	99.16 190	99.69 116	97.61 282	99.55 146	99.49 160	99.32 23	99.98 10	99.91 23	91.41 340	99.96 36	99.82 25	99.92 34	99.90 22

DVP-MVS++		99.59 12	99.50 17	99.88 11	99.51 187	99.88 8	99.87 8	99.51 130	98.99 58	99.88 35	99.81 106	99.27 5	99.96 36	98.85 134	99.80 112	99.81 71

MSC_two_6792asdad				99.87 17	99.51 187	99.76 42		99.33 278					99.96 36	98.87 127	99.84 91	99.89 25

No_MVS				99.87 17	99.51 187	99.76 42		99.33 278					99.96 36	98.87 127	99.84 91	99.89 25

ZD-MVS					99.71 106	99.79 34		99.61 53	96.84 304	99.56 136	99.54 252	98.58 75	99.96 36	96.93 322	99.75 129

SED-MVS		99.61 8	99.52 12	99.88 11	99.84 32	99.90 2	99.60 102	99.48 172	99.08 46	99.91 26	99.81 106	99.20 7	99.96 36	98.91 121	99.85 83	99.79 84

test_241102_TWO								99.48 172	99.08 46	99.88 35	99.81 106	98.94 32	99.96 36	98.91 121	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	98.08 169	99.55 140	99.64 212	98.91 37	99.96 36	98.72 152	99.90 50	99.82 64

DVP-MVS		99.57 16	99.47 21	99.88 11	99.85 26	99.89 4	99.57 125	99.37 258	99.10 40	99.81 54	99.80 119	98.94 32	99.96 36	98.93 118	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 54	99.80 119	99.09 14	99.96 36	98.85 134	99.90 50	99.88 31

test_0728_SECOND				99.91 3	99.84 32	99.89 4	99.57 125	99.51 130					99.96 36	98.93 118	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	98.21 147	99.73 81	99.79 131	98.68 67	99.96 36	98.44 194	99.77 124	99.79 84

DPE-MVS		99.46 37	99.32 49	99.91 3	99.78 60	99.88 8	99.36 255	99.51 130	98.73 91	99.88 35	99.84 78	98.72 64	99.96 36	98.16 220	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	99.62 151	99.55 88	99.50 178	99.70 15	98.79 84	99.77 69	99.96 1	97.45 120	99.96 36	98.92 120	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	98.15 154	99.68 94	99.69 186	99.06 16	99.96 36	98.69 157	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	98.13 159	99.66 103	99.68 193	98.96 25	99.96 36	98.62 166	99.87 68	99.84 49

HPM-MVS++		99.39 59	99.23 75	99.87 17	99.75 82	99.84 18	99.43 219	99.51 130	98.68 97	99.27 205	99.53 256	98.64 72	99.96 36	98.44 194	99.80 112	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 35	99.85 67	99.18 10	99.96 36	99.22 85	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	98.15 154	99.67 98	99.69 186	98.95 30	99.96 36	98.69 157	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	99.46 202	98.09 165	99.48 152	99.74 159	98.29 95	99.96 36	97.93 238	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		99.11 116	98.90 129	99.74 71	99.80 54	99.46 105	99.59 109	99.49 160	97.03 291	99.63 118	99.69 186	97.27 129	99.96 36	97.82 249	99.84 91	99.81 71

PVSNet_Blended_VisFu		99.36 65	99.28 64	99.61 99	99.86 20	99.07 157	99.47 203	99.93 2	97.66 222	99.71 88	99.86 60	97.73 115	99.96 36	99.47 59	99.82 104	99.79 84

UGNet		98.87 147	98.69 156	99.40 149	99.22 281	98.72 204	99.44 214	99.68 20	99.24 26	99.18 230	99.42 290	92.74 302	99.96 36	99.34 71	99.94 27	99.53 186
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	99.32 163	99.85 26	98.29 241	99.71 55	99.66 28	98.11 162	99.41 170	99.80 119	98.37 92	99.96 36	98.99 109	99.96 14	99.72 117

ACMMP		99.45 41	99.32 49	99.82 50	99.89 8	99.67 60	99.62 95	99.69 18	98.12 160	99.63 118	99.84 78	98.73 63	99.96 36	98.55 184	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	99.51 187	99.67 60	99.50 178	99.64 38	99.43 13	99.98 10	99.78 138	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	99.49 190	99.60 60	99.42 16	99.99 2	99.86 60	95.15 214	99.95 68	99.95 12	99.89 61	99.73 109

fmvsm_s_conf0.1_n_2		99.37 61	99.22 76	99.81 53	99.77 68	99.75 44	99.46 206	99.60 60	99.47 4	99.98 10	99.94 6	94.98 218	99.95 68	99.97 1	99.79 119	99.73 109

test_fmvsmconf0.01_n		99.22 90	99.03 102	99.79 59	98.42 397	99.48 102	99.55 146	99.51 130	99.39 18	99.78 65	99.93 10	94.80 230	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	98.38 123	99.76 75	99.82 92	98.53 79	99.95 68	98.61 169	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	97.97 184	99.63 118	99.68 193	98.52 80	99.95 68	98.38 198	99.86 76	99.81 71

CANet		99.25 87	99.14 85	99.59 102	99.41 226	99.16 142	99.35 260	99.57 75	98.82 78	99.51 147	99.61 227	96.46 162	99.95 68	99.59 40	99.98 4	99.65 144

MP-MVS-pluss		99.37 61	99.20 79	99.88 11	99.90 4	99.87 15	99.30 272	99.52 115	97.18 273	99.60 128	99.79 131	98.79 50	99.95 68	98.83 140	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	99.50 150	98.70 94	99.77 69	99.49 270	98.21 98	99.95 68	98.46 192	99.77 124	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	96.67 334

APD-MVS_3200maxsize		99.48 32	99.35 43	99.85 36	99.76 72	99.83 19	99.63 90	99.54 97	98.36 127	99.79 60	99.82 92	98.86 41	99.95 68	98.62 166	99.81 107	99.78 90

RPMNet		96.72 343	95.90 356	99.19 187	99.18 290	98.49 230	99.22 308	99.52 115	88.72 422	99.56 136	97.38 419	94.08 269	99.95 68	86.87 427	98.58 229	99.14 250

sss		99.17 95	99.05 97	99.53 120	99.62 151	98.97 169	99.36 255	99.62 45	97.83 200	99.67 98	99.65 206	97.37 124	99.95 68	99.19 87	99.19 185	99.68 134

MVSMamba_PlusPlus		99.46 37	99.41 32	99.64 91	99.68 121	99.50 99	99.75 42	99.50 150	98.27 137	99.87 40	99.92 17	98.09 104	99.94 81	99.65 36	99.95 19	99.47 207

fmvsm_s_conf0.1_n_a		99.26 83	99.06 96	99.85 36	99.52 184	99.62 75	99.54 151	99.62 45	98.69 95	99.99 2	99.96 1	94.47 255	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	99.53 160	99.62 45	98.74 90	99.99 2	99.95 3	94.53 253	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	99.39 242	98.91 71	99.78 65	99.85 67	99.36 2	99.94 81	98.84 137	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		98.91 144	98.75 150	99.39 153	99.46 211	98.61 216	99.76 37	99.50 150	98.06 174	99.81 54	99.88 44	93.91 277	99.94 81	99.11 95	99.27 180	99.61 160

mamv4		99.33 70	99.42 27	99.07 198	99.67 123	97.73 273	99.42 226	99.60 60	98.15 154	99.94 24	99.91 23	98.42 88	99.94 81	99.72 28	99.96 14	99.54 180

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	99.37 181	99.74 159	98.81 47	99.94 81	98.79 145	99.86 76	99.84 49

X-MVStestdata		96.55 346	95.45 365	99.87 17	99.85 26	99.83 19	99.69 60	99.68 20	98.98 61	99.37 181	64.01 442	98.81 47	99.94 81	98.79 145	99.86 76	99.84 49

旧先验2							98.96 365		96.70 311	99.47 153			99.94 81	98.19 216

新几何1				99.75 68	99.75 82	99.59 80		99.54 97	96.76 307	99.29 199	99.64 212	98.43 86	99.94 81	96.92 324	99.66 146	99.72 117

testdata				99.54 112	99.75 82	98.95 176		99.51 130	97.07 285	99.43 163	99.70 176	98.87 40	99.94 81	97.76 256	99.64 149	99.72 117

HPM-MVS		99.42 50	99.28 64	99.83 49	99.90 4	99.72 49	99.81 20	99.54 97	97.59 228	99.68 94	99.63 218	98.91 37	99.94 81	98.58 175	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	99.45 142	99.89 8	98.52 226	99.39 243	99.94 1	98.73 91	99.11 239	99.89 36	95.50 199	99.94 81	99.50 52	99.97 8	99.89 25

APD-MVS		99.27 81	99.08 94	99.84 48	99.75 82	99.79 34	99.50 178	99.50 150	97.16 275	99.77 69	99.82 92	98.78 51	99.94 81	97.56 277	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	99.05 342	99.66 28	99.14 32	99.57 135	99.80 119	98.46 84	99.94 81	99.57 43	99.84 91	99.60 163
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		99.06 126	98.88 134	99.61 99	99.62 151	99.16 142	99.37 250	99.56 80	98.04 177	99.53 143	99.62 223	96.84 145	99.94 81	98.85 134	98.49 237	99.72 117

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	99.63 118	99.95 3	95.82 187	99.94 81	99.37 65	99.97 8	99.73 109
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	99.18 290	99.75 44	99.56 132	99.57 75	98.45 116	99.49 151	99.85 67	97.77 114	99.94 81	98.33 205	99.84 91	99.52 187

GDP-MVS		99.08 123	98.89 132	99.64 91	99.53 178	99.34 117	99.64 84	99.48 172	98.32 132	99.77 69	99.66 204	95.14 215	99.93 99	98.97 113	99.50 162	99.64 151

SDMVSNet		99.11 116	98.90 129	99.75 68	99.81 48	99.59 80	99.81 20	99.65 35	98.78 87	99.64 115	99.88 44	94.56 249	99.93 99	99.67 33	98.26 250	99.72 117

FE-MVS		98.48 183	98.17 198	99.40 149	99.54 177	98.96 173	99.68 66	98.81 374	95.54 370	99.62 122	99.70 176	93.82 280	99.93 99	97.35 295	99.46 164	99.32 236

SF-MVS		99.38 60	99.24 72	99.79 59	99.79 58	99.68 56	99.57 125	99.54 97	97.82 204	99.71 88	99.80 119	98.95 30	99.93 99	98.19 216	99.84 91	99.74 102

dcpmvs_2		99.23 89	99.58 7	98.16 319	99.83 40	94.68 388	99.76 37	99.52 115	99.07 48	99.98 10	99.88 44	98.56 77	99.93 99	99.67 33	99.98 4	99.87 36

Anonymous20240529		98.09 220	97.68 258	99.34 157	99.66 133	98.44 235	99.40 239	99.43 228	93.67 396	99.22 217	99.89 36	90.23 357	99.93 99	99.26 83	98.33 244	99.66 140

ACMMP_NAP		99.47 35	99.34 45	99.88 11	99.87 15	99.86 16	99.47 203	99.48 172	98.05 176	99.76 75	99.86 60	98.82 46	99.93 99	98.82 144	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	99.45 213	99.01 53	99.90 29	99.83 83	98.98 24	99.93 99	99.59 40	99.95 19	99.86 38

无先验							98.99 358	99.51 130	96.89 301				99.93 99	97.53 280		99.72 117

VDDNet		97.55 307	97.02 328	99.16 190	99.49 201	98.12 252	99.38 248	99.30 297	95.35 372	99.68 94	99.90 30	82.62 417	99.93 99	99.31 75	98.13 262	99.42 219

ab-mvs		98.86 150	98.63 163	99.54 112	99.64 142	99.19 137	99.44 214	99.54 97	97.77 208	99.30 196	99.81 106	94.20 263	99.93 99	99.17 91	98.82 217	99.49 200

F-COLMAP		99.19 91	99.04 99	99.64 91	99.78 60	99.27 130	99.42 226	99.54 97	97.29 264	99.41 170	99.59 232	98.42 88	99.93 99	98.19 216	99.69 140	99.73 109

BP-MVS1		99.12 111	98.94 125	99.65 85	99.51 187	99.30 125	99.67 69	98.92 355	98.48 112	99.84 46	99.69 186	94.96 219	99.92 111	99.62 39	99.79 119	99.71 126

Anonymous202405211		98.30 201	97.98 222	99.26 178	99.57 166	98.16 247	99.41 231	98.55 399	96.03 364	99.19 226	99.74 159	91.87 327	99.92 111	99.16 92	98.29 249	99.70 128

EI-MVSNet-Vis-set		99.58 13	99.56 10	99.64 91	99.78 60	99.15 146	99.61 101	99.45 213	99.01 53	99.89 32	99.82 92	99.01 18	99.92 111	99.56 44	99.95 19	99.85 42

VDD-MVS		97.73 286	97.35 302	98.88 232	99.47 209	97.12 301	99.34 263	98.85 369	98.19 149	99.67 98	99.85 67	82.98 415	99.92 111	99.49 56	98.32 248	99.60 163

VNet		99.11 116	98.90 129	99.73 74	99.52 184	99.56 86	99.41 231	99.39 242	99.01 53	99.74 79	99.78 138	95.56 197	99.92 111	99.52 50	98.18 258	99.72 117

XVG-OURS-SEG-HR		98.69 173	98.62 168	98.89 230	99.71 106	97.74 272	99.12 327	99.54 97	98.44 119	99.42 166	99.71 172	94.20 263	99.92 111	98.54 185	98.90 211	99.00 269

mvsmamba		99.06 126	98.96 121	99.36 155	99.47 209	98.64 211	99.70 56	99.05 339	97.61 227	99.65 110	99.83 83	96.54 158	99.92 111	99.19 87	99.62 152	99.51 195

HPM-MVS_fast		99.51 24	99.40 33	99.85 36	99.91 1	99.79 34	99.76 37	99.56 80	97.72 213	99.76 75	99.75 154	99.13 12	99.92 111	99.07 101	99.92 34	99.85 42

HY-MVS	97.30 7	98.85 157	98.64 162	99.47 139	99.42 221	99.08 155	99.62 95	99.36 259	97.39 256	99.28 200	99.68 193	96.44 164	99.92 111	98.37 200	98.22 253	99.40 224

DP-MVS		99.16 97	98.95 123	99.78 62	99.77 68	99.53 93	99.41 231	99.50 150	97.03 291	99.04 256	99.88 44	97.39 121	99.92 111	98.66 161	99.90 50	99.87 36

IB-MVS	95.67 18	96.22 352	95.44 366	98.57 271	99.21 282	96.70 329	98.65 399	97.74 417	96.71 310	97.27 382	98.54 394	86.03 398	99.92 111	98.47 191	86.30 423	99.10 253
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	99.63 145	99.59 80	99.36 255	99.46 202	99.07 48	99.79 60	99.82 92	98.85 42	99.92 111	98.68 159	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	99.55 174	99.58 85	99.74 46	99.51 130	98.42 120	99.87 40	99.84 78	98.05 107	99.91 123	99.58 42	99.94 27	99.52 187

9.14			99.10 90		99.72 101		99.40 239	99.51 130	97.53 238	99.64 115	99.78 138	98.84 44	99.91 123	97.63 268	99.82 104

SMA-MVS		99.44 45	99.30 57	99.85 36	99.73 97	99.83 19	99.56 132	99.47 193	97.45 247	99.78 65	99.82 92	99.18 10	99.91 123	98.79 145	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					99.67 123	99.65 67	99.05 342	99.41 233	96.22 349	98.95 271	99.49 270	98.77 54	99.91 123

train_agg		99.02 132	98.77 148	99.77 65	99.67 123	99.65 67	99.05 342	99.41 233	96.28 343	98.95 271	99.49 270	98.76 55	99.91 123	97.63 268	99.72 135	99.75 98

test_8					99.67 123	99.61 77	99.03 347	99.41 233	96.28 343	98.93 274	99.48 276	98.76 55	99.91 123

agg_prior					99.67 123	99.62 75		99.40 239		98.87 284			99.91 123

原ACMM1				99.65 85	99.73 97	99.33 118		99.47 193	97.46 244	99.12 237	99.66 204	98.67 69	99.91 123	97.70 265	99.69 140	99.71 126

LFMVS		97.90 253	97.35 302	99.54 112	99.52 184	99.01 164	99.39 243	98.24 406	97.10 283	99.65 110	99.79 131	84.79 407	99.91 123	99.28 79	98.38 241	99.69 130

XVG-OURS		98.73 171	98.68 157	98.88 232	99.70 111	97.73 273	98.92 372	99.55 88	98.52 109	99.45 156	99.84 78	95.27 208	99.91 123	98.08 227	98.84 215	99.00 269

PLC	97.94 4	99.02 132	98.85 139	99.53 120	99.66 133	99.01 164	99.24 301	99.52 115	96.85 303	99.27 205	99.48 276	98.25 97	99.91 123	97.76 256	99.62 152	99.65 144
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 300	97.06 327	99.47 139	99.61 155	99.09 152	98.04 425	99.25 309	91.24 413	98.51 332	99.70 176	94.55 251	99.91 123	92.76 404	99.85 83	99.42 219
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
AstraMVS		99.09 121	99.03 102	99.25 179	99.66 133	98.13 250	99.57 125	98.24 406	98.82 78	99.91 26	99.88 44	95.81 188	99.90 135	99.72 28	99.67 145	99.74 102

mmtdpeth		96.95 338	96.71 337	97.67 358	99.33 248	94.90 384	99.89 2	99.28 303	98.15 154	99.72 86	98.57 393	86.56 396	99.90 135	99.82 25	89.02 418	98.20 388

UWE-MVS		97.58 306	97.29 313	98.48 282	99.09 314	96.25 349	99.01 355	96.61 429	97.86 194	99.19 226	99.01 364	88.72 372	99.90 135	97.38 293	98.69 223	99.28 239

test_vis1_rt		95.81 362	95.65 361	96.32 391	99.67 123	91.35 418	99.49 190	96.74 427	98.25 140	95.24 406	98.10 412	74.96 427	99.90 135	99.53 48	98.85 214	97.70 412

FA-MVS(test-final)		98.75 168	98.53 179	99.41 148	99.55 174	99.05 160	99.80 25	99.01 344	96.59 325	99.58 132	99.59 232	95.39 202	99.90 135	97.78 252	99.49 163	99.28 239

MCST-MVS		99.43 48	99.30 57	99.82 50	99.79 58	99.74 47	99.29 277	99.40 239	98.79 84	99.52 145	99.62 223	98.91 37	99.90 135	98.64 163	99.75 129	99.82 64

CDPH-MVS		99.13 105	98.91 128	99.80 56	99.75 82	99.71 51	99.15 321	99.41 233	96.60 323	99.60 128	99.55 247	98.83 45	99.90 135	97.48 284	99.83 100	99.78 90

NCCC		99.34 68	99.19 81	99.79 59	99.61 155	99.65 67	99.30 272	99.48 172	98.86 73	99.21 220	99.63 218	98.72 64	99.90 135	98.25 212	99.63 151	99.80 80

114514_t		98.93 142	98.67 158	99.72 77	99.85 26	99.53 93	99.62 95	99.59 66	92.65 408	99.71 88	99.78 138	98.06 106	99.90 135	98.84 137	99.91 41	99.74 102

1112_ss		98.98 138	98.77 148	99.59 102	99.68 121	99.02 162	99.25 298	99.48 172	97.23 270	99.13 235	99.58 236	96.93 144	99.90 135	98.87 127	98.78 220	99.84 49

PHI-MVS		99.30 75	99.17 83	99.70 78	99.56 170	99.52 97	99.58 118	99.80 8	97.12 279	99.62 122	99.73 165	98.58 75	99.90 135	98.61 169	99.91 41	99.68 134

AdaColmap		99.01 136	98.80 144	99.66 81	99.56 170	99.54 90	99.18 316	99.70 15	98.18 152	99.35 187	99.63 218	96.32 167	99.90 135	97.48 284	99.77 124	99.55 178

COLMAP_ROB	97.56 6	98.86 150	98.75 150	99.17 189	99.88 11	98.53 222	99.34 263	99.59 66	97.55 234	98.70 310	99.89 36	95.83 186	99.90 135	98.10 222	99.90 50	99.08 258
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 197	98.03 217	99.31 164	99.63 145	98.56 219	99.54 151	96.75 426	97.53 238	99.73 81	99.65 206	91.25 345	99.89 148	98.62 166	99.56 157	99.48 201

tttt0517		98.42 188	98.14 202	99.28 176	99.66 133	98.38 239	99.74 46	96.85 424	97.68 219	99.79 60	99.74 159	91.39 341	99.89 148	98.83 140	99.56 157	99.57 174

test12				99.75 68	99.64 142	99.61 77		99.29 301		99.21 220		98.38 91	99.89 148		99.74 132	99.74 102

Test_1112_low_res		98.89 145	98.66 161	99.57 107	99.69 116	98.95 176	99.03 347	99.47 193	96.98 293	99.15 233	99.23 340	96.77 148	99.89 148	98.83 140	98.78 220	99.86 38

CNLPA		99.14 103	98.99 113	99.59 102	99.58 164	99.41 111	99.16 318	99.44 222	98.45 116	99.19 226	99.49 270	98.08 105	99.89 148	97.73 260	99.75 129	99.48 201

guyue		99.16 97	99.04 99	99.52 126	99.69 116	98.92 183	99.59 109	98.81 374	98.73 91	99.90 29	99.87 55	95.34 205	99.88 153	99.66 35	99.81 107	99.74 102

sd_testset		98.75 168	98.57 175	99.29 172	99.81 48	98.26 243	99.56 132	99.62 45	98.78 87	99.64 115	99.88 44	92.02 324	99.88 153	99.54 46	98.26 250	99.72 117

APD_test1		95.87 360	96.49 342	94.00 398	99.53 178	84.01 427	99.54 151	99.32 288	95.91 366	97.99 361	99.85 67	85.49 402	99.88 153	91.96 407	98.84 215	98.12 392

diffmvs		99.14 103	99.02 107	99.51 129	99.61 155	98.96 173	99.28 282	99.49 160	98.46 114	99.72 86	99.71 172	96.50 160	99.88 153	99.31 75	99.11 192	99.67 137
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		98.86 150	98.80 144	99.03 204	99.76 72	98.79 199	99.28 282	99.91 3	97.42 253	99.67 98	99.37 307	97.53 118	99.88 153	98.98 110	97.29 309	98.42 373

PVSNet_Blended		99.08 123	98.97 117	99.42 147	99.76 72	98.79 199	98.78 386	99.91 3	96.74 308	99.67 98	99.49 270	97.53 118	99.88 153	98.98 110	99.85 83	99.60 163

MVS		97.28 327	96.55 340	99.48 135	98.78 364	98.95 176	99.27 287	99.39 242	83.53 429	98.08 356	99.54 252	96.97 142	99.87 159	94.23 385	99.16 186	99.63 156

MG-MVS		99.13 105	99.02 107	99.45 142	99.57 166	98.63 212	99.07 337	99.34 271	98.99 58	99.61 125	99.82 92	97.98 109	99.87 159	97.00 315	99.80 112	99.85 42

MSDG		98.98 138	98.80 144	99.53 120	99.76 72	99.19 137	98.75 389	99.55 88	97.25 267	99.47 153	99.77 147	97.82 112	99.87 159	96.93 322	99.90 50	99.54 180

ETV-MVS		99.26 83	99.21 77	99.40 149	99.46 211	99.30 125	99.56 132	99.52 115	98.52 109	99.44 161	99.27 335	98.41 90	99.86 162	99.10 98	99.59 155	99.04 265

thisisatest0515		98.14 215	97.79 241	99.19 187	99.50 199	98.50 229	98.61 401	96.82 425	96.95 297	99.54 141	99.43 288	91.66 336	99.86 162	98.08 227	99.51 161	99.22 247

thres600view7		97.86 259	97.51 276	98.92 221	99.72 101	97.95 263	99.59 109	98.74 384	97.94 186	99.27 205	98.62 390	91.75 330	99.86 162	93.73 391	98.19 257	98.96 275

lupinMVS		99.13 105	99.01 111	99.46 141	99.51 187	98.94 179	99.05 342	99.16 324	97.86 194	99.80 58	99.56 244	97.39 121	99.86 162	98.94 115	99.85 83	99.58 171

PVSNet	96.02 17	98.85 157	98.84 141	98.89 230	99.73 97	97.28 292	98.32 417	99.60 60	97.86 194	99.50 148	99.57 241	96.75 149	99.86 162	98.56 181	99.70 139	99.54 180

MAR-MVS		98.86 150	98.63 163	99.54 112	99.37 239	99.66 63	99.45 208	99.54 97	96.61 320	99.01 259	99.40 298	97.09 135	99.86 162	97.68 267	99.53 160	99.10 253
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		97.44 319	97.02 328	98.71 259	99.18 290	96.89 323	99.19 314	99.04 340	97.78 207	98.31 343	98.29 404	85.41 403	99.85 168	98.01 233	97.95 267	99.39 225

test2506		96.81 342	96.65 338	97.29 372	99.74 90	92.21 415	99.60 102	85.06 446	99.13 33	99.77 69	99.93 10	87.82 389	99.85 168	99.38 64	99.38 169	99.80 80

AllTest		98.87 147	98.72 152	99.31 164	99.86 20	98.48 232	99.56 132	99.61 53	97.85 197	99.36 184	99.85 67	95.95 179	99.85 168	96.66 335	99.83 100	99.59 167

TestCases				99.31 164	99.86 20	98.48 232		99.61 53	97.85 197	99.36 184	99.85 67	95.95 179	99.85 168	96.66 335	99.83 100	99.59 167

jason		99.13 105	99.03 102	99.45 142	99.46 211	98.87 187	99.12 327	99.26 307	98.03 179	99.79 60	99.65 206	97.02 140	99.85 168	99.02 107	99.90 50	99.65 144
jason: jason.
CNVR-MVS		99.42 50	99.30 57	99.78 62	99.62 151	99.71 51	99.26 296	99.52 115	98.82 78	99.39 177	99.71 172	98.96 25	99.85 168	98.59 174	99.80 112	99.77 92

PAPM_NR		99.04 129	98.84 141	99.66 81	99.74 90	99.44 107	99.39 243	99.38 250	97.70 217	99.28 200	99.28 332	98.34 93	99.85 168	96.96 319	99.45 165	99.69 130

testing99		97.36 322	96.94 331	98.63 264	99.18 290	96.70 329	99.30 272	98.93 352	97.71 214	98.23 348	98.26 405	84.92 406	99.84 175	98.04 232	97.85 274	99.35 231

testing222		97.16 332	96.50 341	99.16 190	99.16 300	98.47 234	99.27 287	98.66 395	97.71 214	98.23 348	98.15 408	82.28 420	99.84 175	97.36 294	97.66 280	99.18 249

test1111		98.04 230	98.11 206	97.83 348	99.74 90	93.82 400	99.58 118	95.40 433	99.12 38	99.65 110	99.93 10	90.73 350	99.84 175	99.43 62	99.38 169	99.82 64

ECVR-MVS		98.04 230	98.05 215	98.00 332	99.74 90	94.37 395	99.59 109	94.98 434	99.13 33	99.66 103	99.93 10	90.67 351	99.84 175	99.40 63	99.38 169	99.80 80

test_yl		98.86 150	98.63 163	99.54 112	99.49 201	99.18 139	99.50 178	99.07 336	98.22 145	99.61 125	99.51 264	95.37 203	99.84 175	98.60 172	98.33 244	99.59 167

DCV-MVSNet		98.86 150	98.63 163	99.54 112	99.49 201	99.18 139	99.50 178	99.07 336	98.22 145	99.61 125	99.51 264	95.37 203	99.84 175	98.60 172	98.33 244	99.59 167

Fast-Effi-MVS+		98.70 172	98.43 183	99.51 129	99.51 187	99.28 128	99.52 161	99.47 193	96.11 359	99.01 259	99.34 317	96.20 171	99.84 175	97.88 241	98.82 217	99.39 225

TSAR-MVS + GP.		99.36 65	99.36 41	99.36 155	99.67 123	98.61 216	99.07 337	99.33 278	99.00 56	99.82 53	99.81 106	99.06 16	99.84 175	99.09 99	99.42 167	99.65 144

tpmrst		98.33 198	98.48 181	97.90 341	99.16 300	94.78 385	99.31 270	99.11 329	97.27 265	99.45 156	99.59 232	95.33 206	99.84 175	98.48 188	98.61 226	99.09 257

Vis-MVSNet		99.12 111	98.97 117	99.56 109	99.78 60	99.10 151	99.68 66	99.66 28	98.49 111	99.86 44	99.87 55	94.77 235	99.84 175	99.19 87	99.41 168	99.74 102
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 179	98.34 189	99.51 129	99.40 231	99.03 161	98.80 384	99.36 259	96.33 340	99.00 263	99.12 354	98.46 84	99.84 175	95.23 371	99.37 176	99.66 140

PatchMatch-RL		98.84 160	98.62 168	99.52 126	99.71 106	99.28 128	99.06 340	99.77 9	97.74 212	99.50 148	99.53 256	95.41 201	99.84 175	97.17 308	99.64 149	99.44 217

EPP-MVSNet		99.13 105	98.99 113	99.53 120	99.65 140	99.06 158	99.81 20	99.33 278	97.43 251	99.60 128	99.88 44	97.14 133	99.84 175	99.13 93	98.94 206	99.69 130

testing3-2		97.84 264	97.70 256	98.24 314	99.53 178	95.37 373	99.55 146	98.67 394	98.46 114	99.27 205	99.34 317	86.58 395	99.83 188	99.32 74	98.63 225	99.52 187

testing11		97.50 312	97.10 325	98.71 259	99.20 284	96.91 321	99.29 277	98.82 372	97.89 191	98.21 351	98.40 399	85.63 401	99.83 188	98.45 193	98.04 265	99.37 229

thres100view900		97.76 278	97.45 285	98.69 261	99.72 101	97.86 269	99.59 109	98.74 384	97.93 187	99.26 210	98.62 390	91.75 330	99.83 188	93.22 396	98.18 258	98.37 379

tfpn200view9		97.72 288	97.38 298	98.72 257	99.69 116	97.96 261	99.50 178	98.73 390	97.83 200	99.17 231	98.45 397	91.67 334	99.83 188	93.22 396	98.18 258	98.37 379

test_prior				99.68 79	99.67 123	99.48 102		99.56 80					99.83 188			99.74 102

1314		98.68 174	98.54 178	99.11 196	98.89 347	98.65 209	99.27 287	99.49 160	96.89 301	97.99 361	99.56 244	97.72 116	99.83 188	97.74 259	99.27 180	98.84 281

thres400		97.77 277	97.38 298	98.92 221	99.69 116	97.96 261	99.50 178	98.73 390	97.83 200	99.17 231	98.45 397	91.67 334	99.83 188	93.22 396	98.18 258	98.96 275

casdiffmvs		99.13 105	98.98 116	99.56 109	99.65 140	99.16 142	99.56 132	99.50 150	98.33 131	99.41 170	99.86 60	95.92 182	99.83 188	99.45 61	99.16 186	99.70 128
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	98.56 105	99.73 81	99.69 186	98.55 78	99.82 196	99.69 31	99.85 83	99.48 201

MVS_Test		99.10 120	98.97 117	99.48 135	99.49 201	99.14 147	99.67 69	99.34 271	97.31 262	99.58 132	99.76 151	97.65 117	99.82 196	98.87 127	99.07 198	99.46 212

dp		97.75 282	97.80 240	97.59 363	99.10 311	93.71 403	99.32 267	98.88 365	96.48 332	99.08 247	99.55 247	92.67 308	99.82 196	96.52 339	98.58 229	99.24 245

RPSCF		98.22 205	98.62 168	96.99 378	99.82 44	91.58 417	99.72 52	99.44 222	96.61 320	99.66 103	99.89 36	95.92 182	99.82 196	97.46 287	99.10 195	99.57 174

PMMVS		98.80 164	98.62 168	99.34 157	99.27 266	98.70 205	98.76 388	99.31 292	97.34 259	99.21 220	99.07 356	97.20 132	99.82 196	98.56 181	98.87 212	99.52 187

UBG		97.85 260	97.48 279	98.95 215	99.25 273	97.64 280	99.24 301	98.74 384	97.90 190	98.64 320	98.20 407	88.65 376	99.81 201	98.27 210	98.40 239	99.42 219

EIA-MVS		99.18 93	99.09 93	99.45 142	99.49 201	99.18 139	99.67 69	99.53 110	97.66 222	99.40 175	99.44 286	98.10 103	99.81 201	98.94 115	99.62 152	99.35 231

Effi-MVS+		98.81 161	98.59 174	99.48 135	99.46 211	99.12 150	98.08 424	99.50 150	97.50 242	99.38 179	99.41 294	96.37 166	99.81 201	99.11 95	98.54 234	99.51 195

thres200		97.61 304	97.28 314	98.62 265	99.64 142	98.03 255	99.26 296	98.74 384	97.68 219	99.09 245	98.32 403	91.66 336	99.81 201	92.88 401	98.22 253	98.03 398

tpmvs		97.98 241	98.02 219	97.84 347	99.04 325	94.73 386	99.31 270	99.20 319	96.10 363	98.76 300	99.42 290	94.94 221	99.81 201	96.97 318	98.45 238	98.97 273

casdiffmvs_mvg		99.15 100	99.02 107	99.55 111	99.66 133	99.09 152	99.64 84	99.56 80	98.26 139	99.45 156	99.87 55	96.03 176	99.81 201	99.54 46	99.15 189	99.73 109
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	98.81 161	99.37 39	97.12 376	99.60 160	91.75 416	98.61 401	99.44 222	99.35 21	99.83 52	99.85 67	98.70 66	99.81 201	99.02 107	99.91 41	99.81 71

DPM-MVS		98.95 141	98.71 154	99.66 81	99.63 145	99.55 88	98.64 400	99.10 330	97.93 187	99.42 166	99.55 247	98.67 69	99.80 208	95.80 356	99.68 143	99.61 160

DP-MVS Recon		99.12 111	98.95 123	99.65 85	99.74 90	99.70 53	99.27 287	99.57 75	96.40 339	99.42 166	99.68 193	98.75 58	99.80 208	97.98 235	99.72 135	99.44 217

MVS_111021_LR		99.41 54	99.33 47	99.65 85	99.77 68	99.51 98	98.94 370	99.85 6	98.82 78	99.65 110	99.74 159	98.51 81	99.80 208	98.83 140	99.89 61	99.64 151

CS-MVS		99.50 26	99.48 19	99.54 112	99.76 72	99.42 109	99.90 1	99.55 88	98.56 105	99.78 65	99.70 176	98.65 71	99.79 211	99.65 36	99.78 121	99.41 222

Fast-Effi-MVS+-dtu		98.77 167	98.83 143	98.60 266	99.41 226	96.99 315	99.52 161	99.49 160	98.11 162	99.24 212	99.34 317	96.96 143	99.79 211	97.95 237	99.45 165	99.02 268

baseline1		98.31 199	97.95 226	99.38 154	99.50 199	98.74 202	99.59 109	98.93 352	98.41 121	99.14 234	99.60 230	94.59 247	99.79 211	98.48 188	93.29 392	99.61 160

baseline		99.15 100	99.02 107	99.53 120	99.66 133	99.14 147	99.72 52	99.48 172	98.35 128	99.42 166	99.84 78	96.07 174	99.79 211	99.51 51	99.14 190	99.67 137

PVSNet_0	94.43 19	96.09 357	95.47 364	97.94 337	99.31 256	94.34 397	97.81 426	99.70 15	97.12 279	97.46 376	98.75 387	89.71 362	99.79 211	97.69 266	81.69 429	99.68 134

API-MVS		99.04 129	99.03 102	99.06 200	99.40 231	99.31 123	99.55 146	99.56 80	98.54 107	99.33 191	99.39 302	98.76 55	99.78 216	96.98 317	99.78 121	98.07 395

OMC-MVS		99.08 123	99.04 99	99.20 186	99.67 123	98.22 245	99.28 282	99.52 115	98.07 170	99.66 103	99.81 106	97.79 113	99.78 216	97.79 251	99.81 107	99.60 163

GeoE		98.85 157	98.62 168	99.53 120	99.61 155	99.08 155	99.80 25	99.51 130	97.10 283	99.31 193	99.78 138	95.23 212	99.77 218	98.21 214	99.03 201	99.75 98

alignmvs		98.81 161	98.56 177	99.58 105	99.43 219	99.42 109	99.51 170	98.96 350	98.61 101	99.35 187	98.92 377	94.78 232	99.77 218	99.35 66	98.11 263	99.54 180

tpm cat1		97.39 321	97.36 300	97.50 366	99.17 298	93.73 402	99.43 219	99.31 292	91.27 412	98.71 304	99.08 355	94.31 261	99.77 218	96.41 344	98.50 236	99.00 269

CostFormer		97.72 288	97.73 253	97.71 356	99.15 304	94.02 399	99.54 151	99.02 343	94.67 387	99.04 256	99.35 313	92.35 320	99.77 218	98.50 187	97.94 268	99.34 234

MGCFI-Net		99.01 136	98.85 139	99.50 134	99.42 221	99.26 131	99.82 16	99.48 172	98.60 102	99.28 200	98.81 382	97.04 139	99.76 222	99.29 78	97.87 272	99.47 207

test_241102_ONE					99.84 32	99.90 2		99.48 172	99.07 48	99.91 26	99.74 159	99.20 7	99.76 222

MDTV_nov1_ep13			98.32 191		99.11 308	94.44 393	99.27 287	98.74 384	97.51 241	99.40 175	99.62 223	94.78 232	99.76 222	97.59 271	98.81 219

sasdasda		99.02 132	98.86 137	99.51 129	99.42 221	99.32 119	99.80 25	99.48 172	98.63 98	99.31 193	98.81 382	97.09 135	99.75 225	99.27 81	97.90 269	99.47 207

canonicalmvs		99.02 132	98.86 137	99.51 129	99.42 221	99.32 119	99.80 25	99.48 172	98.63 98	99.31 193	98.81 382	97.09 135	99.75 225	99.27 81	97.90 269	99.47 207

Effi-MVS+-dtu		98.78 165	98.89 132	98.47 287	99.33 248	96.91 321	99.57 125	99.30 297	98.47 113	99.41 170	98.99 367	96.78 147	99.74 227	98.73 151	99.38 169	98.74 296

patchmatchnet-post											98.70 388	94.79 231	99.74 227

SCA		98.19 209	98.16 199	98.27 313	99.30 257	95.55 364	99.07 337	98.97 348	97.57 231	99.43 163	99.57 241	92.72 303	99.74 227	97.58 272	99.20 184	99.52 187

BH-untuned		98.42 188	98.36 187	98.59 267	99.49 201	96.70 329	99.27 287	99.13 328	97.24 269	98.80 295	99.38 304	95.75 190	99.74 227	97.07 313	99.16 186	99.33 235

BH-RMVSNet		98.41 190	98.08 211	99.40 149	99.41 226	98.83 195	99.30 272	98.77 380	97.70 217	98.94 273	99.65 206	92.91 298	99.74 227	96.52 339	99.55 159	99.64 151

MVS_111021_HR		99.41 54	99.32 49	99.66 81	99.72 101	99.47 104	98.95 368	99.85 6	98.82 78	99.54 141	99.73 165	98.51 81	99.74 227	98.91 121	99.88 65	99.77 92

test_post											65.99 440	94.65 245	99.73 233

XVG-ACMP-BASELINE		97.83 267	97.71 255	98.20 316	99.11 308	96.33 345	99.41 231	99.52 115	98.06 174	99.05 255	99.50 267	89.64 364	99.73 233	97.73 260	97.38 307	98.53 361

HyFIR lowres test		99.11 116	98.92 126	99.65 85	99.90 4	99.37 113	99.02 350	99.91 3	97.67 221	99.59 131	99.75 154	95.90 184	99.73 233	99.53 48	99.02 203	99.86 38

DeepMVS_CX				93.34 401	99.29 261	82.27 430		99.22 315	85.15 427	96.33 398	99.05 359	90.97 348	99.73 233	93.57 393	97.77 277	98.01 399

Patchmatch-test		97.93 247	97.65 261	98.77 253	99.18 290	97.07 306	99.03 347	99.14 327	96.16 354	98.74 301	99.57 241	94.56 249	99.72 237	93.36 395	99.11 192	99.52 187

LPG-MVS_test		98.22 205	98.13 204	98.49 280	99.33 248	97.05 308	99.58 118	99.55 88	97.46 244	99.24 212	99.83 83	92.58 310	99.72 237	98.09 223	97.51 293	98.68 314

LGP-MVS_train				98.49 280	99.33 248	97.05 308		99.55 88	97.46 244	99.24 212	99.83 83	92.58 310	99.72 237	98.09 223	97.51 293	98.68 314

BH-w/o		98.00 239	97.89 235	98.32 305	99.35 243	96.20 351	99.01 355	98.90 362	96.42 337	98.38 339	99.00 365	95.26 210	99.72 237	96.06 349	98.61 226	99.03 266

ACMP	97.20 11	98.06 224	97.94 228	98.45 290	99.37 239	97.01 313	99.44 214	99.49 160	97.54 237	98.45 336	99.79 131	91.95 326	99.72 237	97.91 239	97.49 298	98.62 344
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 234	97.90 231	98.40 298	99.23 277	96.80 327	99.70 56	99.60 60	97.12 279	98.18 353	99.70 176	91.73 332	99.72 237	98.39 197	97.45 300	98.68 314
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							99.23 304				65.14 441	94.18 266	99.71 243	97.58 272

ADS-MVSNet		98.20 208	98.08 211	98.56 274	99.33 248	96.48 340	99.23 304	99.15 325	96.24 347	99.10 242	99.67 199	94.11 267	99.71 243	96.81 327	99.05 199	99.48 201

JIA-IIPM		97.50 312	97.02 328	98.93 219	98.73 373	97.80 271	99.30 272	98.97 348	91.73 411	98.91 276	94.86 429	95.10 216	99.71 243	97.58 272	97.98 266	99.28 239

EPMVS		97.82 270	97.65 261	98.35 302	98.88 348	95.98 355	99.49 190	94.71 436	97.57 231	99.26 210	99.48 276	92.46 317	99.71 243	97.87 243	99.08 197	99.35 231

TDRefinement		95.42 368	94.57 376	97.97 334	89.83 439	96.11 354	99.48 195	98.75 381	96.74 308	96.68 395	99.88 44	88.65 376	99.71 243	98.37 200	82.74 428	98.09 394

ACMM	97.58 5	98.37 196	98.34 189	98.48 282	99.41 226	97.10 302	99.56 132	99.45 213	98.53 108	99.04 256	99.85 67	93.00 294	99.71 243	98.74 149	97.45 300	98.64 335
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 244	97.77 246	98.57 271	99.59 162	96.61 336	99.45 208	99.08 333	98.21 147	98.88 281	99.80 119	88.66 375	99.70 249	98.58 175	97.72 278	99.39 225

CHOSEN 280x420		99.12 111	99.13 86	99.08 197	99.66 133	97.89 266	98.43 411	99.71 13	98.88 72	99.62 122	99.76 151	96.63 153	99.70 249	99.46 60	99.99 1	99.66 140

EC-MVSNet		99.44 45	99.39 35	99.58 105	99.56 170	99.49 100	99.88 4	99.58 70	98.38 123	99.73 81	99.69 186	98.20 99	99.70 249	99.64 38	99.82 104	99.54 180

PatchmatchNet		98.31 199	98.36 187	98.19 317	99.16 300	95.32 374	99.27 287	98.92 355	97.37 257	99.37 181	99.58 236	94.90 225	99.70 249	97.43 290	99.21 183	99.54 180
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 219	97.99 221	98.44 293	99.41 226	96.96 319	99.60 102	99.56 80	98.09 165	98.15 354	99.91 23	90.87 349	99.70 249	98.88 124	97.45 300	98.67 322
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 312	96.90 332	99.29 172	99.23 277	98.78 201	99.32 267	98.90 362	97.52 240	98.56 329	98.09 413	84.72 408	99.69 254	97.86 244	97.88 271	99.39 225

HQP_MVS		98.27 204	98.22 197	98.44 293	99.29 261	96.97 317	99.39 243	99.47 193	98.97 64	99.11 239	99.61 227	92.71 305	99.69 254	97.78 252	97.63 281	98.67 322

plane_prior5								99.47 193					99.69 254	97.78 252	97.63 281	98.67 322

D2MVS		98.41 190	98.50 180	98.15 322	99.26 269	96.62 335	99.40 239	99.61 53	97.71 214	98.98 266	99.36 310	96.04 175	99.67 257	98.70 154	97.41 305	98.15 391

IS-MVSNet		99.05 128	98.87 135	99.57 107	99.73 97	99.32 119	99.75 42	99.20 319	98.02 181	99.56 136	99.86 60	96.54 158	99.67 257	98.09 223	99.13 191	99.73 109

CLD-MVS		98.16 213	98.10 207	98.33 303	99.29 261	96.82 326	98.75 389	99.44 222	97.83 200	99.13 235	99.55 247	92.92 296	99.67 257	98.32 207	97.69 279	98.48 365
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 329	97.30 311	97.09 377	99.43 219	93.31 408	99.73 50	98.87 367	98.83 77	99.28 200	99.80 119	84.45 409	99.66 260	97.88 241	97.45 300	98.30 381

AUN-MVS		96.88 340	96.31 346	98.59 267	99.48 208	97.04 311	99.27 287	99.22 315	97.44 250	98.51 332	99.41 294	91.97 325	99.66 260	97.71 263	83.83 426	99.07 263

UniMVSNet_ETH3D		97.32 326	96.81 334	98.87 236	99.40 231	97.46 286	99.51 170	99.53 110	95.86 367	98.54 331	99.77 147	82.44 418	99.66 260	98.68 159	97.52 292	99.50 199

OPM-MVS		98.19 209	98.10 207	98.45 290	98.88 348	97.07 306	99.28 282	99.38 250	98.57 104	99.22 217	99.81 106	92.12 322	99.66 260	98.08 227	97.54 290	98.61 353
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 250	97.78 244	98.32 305	99.46 211	96.68 333	99.56 132	99.54 97	98.41 121	97.79 372	99.87 55	90.18 358	99.66 260	98.05 231	97.18 314	98.62 344

hse-mvs2		97.50 312	97.14 322	98.59 267	99.49 201	97.05 308	99.28 282	99.22 315	98.94 67	99.66 103	99.42 290	94.93 222	99.65 265	99.48 57	83.80 427	99.08 258

VPA-MVSNet		98.29 202	97.95 226	99.30 169	99.16 300	99.54 90	99.50 178	99.58 70	98.27 137	99.35 187	99.37 307	92.53 312	99.65 265	99.35 66	94.46 373	98.72 298

TR-MVS		97.76 278	97.41 296	98.82 245	99.06 320	97.87 267	98.87 378	98.56 398	96.63 319	98.68 312	99.22 341	92.49 313	99.65 265	95.40 367	97.79 276	98.95 277

reproduce_monomvs		97.89 254	97.87 236	97.96 336	99.51 187	95.45 369	99.60 102	99.25 309	99.17 28	98.85 289	99.49 270	89.29 367	99.64 268	99.35 66	96.31 330	98.78 284

gm-plane-assit					98.54 393	92.96 410			94.65 388		99.15 349		99.64 268	97.56 277

HQP4-MVS										98.66 313			99.64 268			98.64 335

HQP-MVS		98.02 234	97.90 231	98.37 301	99.19 287	96.83 324	98.98 361	99.39 242	98.24 141	98.66 313	99.40 298	92.47 314	99.64 268	97.19 305	97.58 286	98.64 335

PAPM		97.59 305	97.09 326	99.07 198	99.06 320	98.26 243	98.30 418	99.10 330	94.88 382	98.08 356	99.34 317	96.27 169	99.64 268	89.87 415	98.92 209	99.31 237

TAPA-MVS	97.07 15	97.74 284	97.34 305	98.94 217	99.70 111	97.53 283	99.25 298	99.51 130	91.90 410	99.30 196	99.63 218	98.78 51	99.64 268	88.09 422	99.87 68	99.65 144
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 194	98.09 210	99.24 182	99.26 269	99.32 119	99.56 132	99.55 88	97.45 247	98.71 304	99.83 83	93.23 289	99.63 274	98.88 124	96.32 329	98.76 290

ITE_SJBPF				98.08 325	99.29 261	96.37 343		98.92 355	98.34 129	98.83 290	99.75 154	91.09 346	99.62 275	95.82 354	97.40 306	98.25 385

LF4IMVS		97.52 309	97.46 284	97.70 357	98.98 336	95.55 364	99.29 277	98.82 372	98.07 170	98.66 313	99.64 212	89.97 359	99.61 276	97.01 314	96.68 319	97.94 406

tpm		97.67 299	97.55 270	98.03 327	99.02 327	95.01 381	99.43 219	98.54 400	96.44 335	99.12 237	99.34 317	91.83 329	99.60 277	97.75 258	96.46 325	99.48 201

tpm2		97.44 319	97.34 305	97.74 355	99.15 304	94.36 396	99.45 208	98.94 351	93.45 401	98.90 278	99.44 286	91.35 342	99.59 278	97.31 296	98.07 264	99.29 238

baseline2		97.87 257	97.55 270	98.82 245	99.18 290	98.02 256	99.41 231	96.58 430	96.97 294	96.51 396	99.17 346	93.43 286	99.57 279	97.71 263	99.03 201	98.86 279

MS-PatchMatch		97.24 331	97.32 309	96.99 378	98.45 396	93.51 407	98.82 382	99.32 288	97.41 254	98.13 355	99.30 328	88.99 369	99.56 280	95.68 360	99.80 112	97.90 409

TinyColmap		97.12 334	96.89 333	97.83 348	99.07 318	95.52 367	98.57 404	98.74 384	97.58 230	97.81 371	99.79 131	88.16 383	99.56 280	95.10 372	97.21 312	98.39 377

USDC		97.34 324	97.20 319	97.75 353	99.07 318	95.20 376	98.51 408	99.04 340	97.99 182	98.31 343	99.86 60	89.02 368	99.55 282	95.67 361	97.36 308	98.49 364

MSLP-MVS++		99.46 37	99.47 21	99.44 146	99.60 160	99.16 142	99.41 231	99.71 13	98.98 61	99.45 156	99.78 138	99.19 9	99.54 283	99.28 79	99.84 91	99.63 156

UWE-MVS-28		97.36 322	97.24 318	97.75 353	98.84 357	94.44 393	99.24 301	97.58 419	97.98 183	99.00 263	99.00 365	91.35 342	99.53 284	93.75 390	98.39 240	99.27 243

TAMVS		99.12 111	99.08 94	99.24 182	99.46 211	98.55 220	99.51 170	99.46 202	98.09 165	99.45 156	99.82 92	98.34 93	99.51 285	98.70 154	98.93 207	99.67 137

EPNet_dtu		98.03 232	97.96 224	98.23 315	98.27 399	95.54 366	99.23 304	98.75 381	99.02 51	97.82 370	99.71 172	96.11 173	99.48 286	93.04 399	99.65 148	99.69 130
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 344	96.22 348	97.97 334	97.00 421	96.28 347	98.66 398	99.03 342	96.61 320	96.93 393	99.79 131	87.20 392	99.47 287	96.65 337	94.13 380	98.16 390

EG-PatchMatch MVS		95.97 359	95.69 360	96.81 385	97.78 406	92.79 411	99.16 318	98.93 352	96.16 354	94.08 414	99.22 341	82.72 416	99.47 287	95.67 361	97.50 295	98.17 389

myMVS_eth3d28		97.69 293	97.34 305	98.73 255	99.27 266	97.52 284	99.33 265	98.78 379	98.03 179	98.82 292	98.49 395	86.64 394	99.46 289	98.44 194	98.24 252	99.23 246

MVP-Stereo		97.81 272	97.75 251	97.99 333	97.53 410	96.60 337	98.96 365	98.85 369	97.22 271	97.23 383	99.36 310	95.28 207	99.46 289	95.51 363	99.78 121	97.92 408
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 181	98.67 158	98.30 307	99.35 243	95.59 363	99.50 178	99.55 88	98.60 102	99.39 177	99.83 83	94.48 254	99.45 291	98.75 148	98.56 232	99.85 42

test-LLR		98.06 224	97.90 231	98.55 276	98.79 361	97.10 302	98.67 395	97.75 415	97.34 259	98.61 325	98.85 379	94.45 256	99.45 291	97.25 299	99.38 169	99.10 253

TESTMET0.1,1		97.55 307	97.27 317	98.40 298	98.93 341	96.53 338	98.67 395	97.61 418	96.96 295	98.64 320	99.28 332	88.63 378	99.45 291	97.30 297	99.38 169	99.21 248

test-mter		97.49 317	97.13 324	98.55 276	98.79 361	97.10 302	98.67 395	97.75 415	96.65 315	98.61 325	98.85 379	88.23 382	99.45 291	97.25 299	99.38 169	99.10 253

mvs_anonymous		99.03 131	98.99 113	99.16 190	99.38 236	98.52 226	99.51 170	99.38 250	97.79 205	99.38 179	99.81 106	97.30 127	99.45 291	99.35 66	98.99 204	99.51 195

tfpnnormal		97.84 264	97.47 282	98.98 210	99.20 284	99.22 136	99.64 84	99.61 53	96.32 341	98.27 347	99.70 176	93.35 288	99.44 296	95.69 359	95.40 356	98.27 383

v7n		97.87 257	97.52 274	98.92 221	98.76 371	98.58 218	99.84 12	99.46 202	96.20 350	98.91 276	99.70 176	94.89 226	99.44 296	96.03 350	93.89 385	98.75 292

jajsoiax		98.43 187	98.28 194	98.88 232	98.60 388	98.43 236	99.82 16	99.53 110	98.19 149	98.63 322	99.80 119	93.22 291	99.44 296	99.22 85	97.50 295	98.77 288

mvs_tets		98.40 193	98.23 196	98.91 225	98.67 381	98.51 228	99.66 75	99.53 110	98.19 149	98.65 319	99.81 106	92.75 300	99.44 296	99.31 75	97.48 299	98.77 288

sc_t1		95.75 363	95.05 370	97.87 343	98.83 358	94.61 390	99.21 310	99.45 213	87.45 423	97.97 363	99.85 67	81.19 423	99.43 300	98.27 210	93.20 394	99.57 174

Vis-MVSNet (Re-imp)		98.87 147	98.72 152	99.31 164	99.71 106	98.88 186	99.80 25	99.44 222	97.91 189	99.36 184	99.78 138	95.49 200	99.43 300	97.91 239	99.11 192	99.62 158

OPU-MVS				99.64 91	99.56 170	99.72 49	99.60 102				99.70 176	99.27 5	99.42 302	98.24 213	99.80 112	99.79 84

Anonymous20231211		97.88 255	97.54 273	98.90 227	99.71 106	98.53 222	99.48 195	99.57 75	94.16 392	98.81 293	99.68 193	93.23 289	99.42 302	98.84 137	94.42 375	98.76 290

ttmdpeth		97.80 274	97.63 265	98.29 308	98.77 369	97.38 289	99.64 84	99.36 259	98.78 87	96.30 399	99.58 236	92.34 321	99.39 304	98.36 202	95.58 351	98.10 393

VPNet		97.84 264	97.44 290	99.01 206	99.21 282	98.94 179	99.48 195	99.57 75	98.38 123	99.28 200	99.73 165	88.89 370	99.39 304	99.19 87	93.27 393	98.71 300

nrg030		98.64 178	98.42 184	99.28 176	99.05 323	99.69 55	99.81 20	99.46 202	98.04 177	99.01 259	99.82 92	96.69 151	99.38 306	99.34 71	94.59 372	98.78 284

GA-MVS		97.85 260	97.47 282	99.00 208	99.38 236	97.99 258	98.57 404	99.15 325	97.04 290	98.90 278	99.30 328	89.83 361	99.38 306	96.70 332	98.33 244	99.62 158

UniMVSNet (Re)		98.29 202	98.00 220	99.13 195	99.00 330	99.36 116	99.49 190	99.51 130	97.95 185	98.97 268	99.13 351	96.30 168	99.38 306	98.36 202	93.34 391	98.66 331

FIs		98.78 165	98.63 163	99.23 184	99.18 290	99.54 90	99.83 15	99.59 66	98.28 135	98.79 297	99.81 106	96.75 149	99.37 309	99.08 100	96.38 327	98.78 284

PS-MVSNAJss		98.92 143	98.92 126	98.90 227	98.78 364	98.53 222	99.78 32	99.54 97	98.07 170	99.00 263	99.76 151	99.01 18	99.37 309	99.13 93	97.23 311	98.81 282

CDS-MVSNet		99.09 121	99.03 102	99.25 179	99.42 221	98.73 203	99.45 208	99.46 202	98.11 162	99.46 155	99.77 147	98.01 108	99.37 309	98.70 154	98.92 209	99.66 140
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 363	95.16 368	97.51 365	99.30 257	93.69 404	98.88 376	95.78 431	85.09 428	98.78 298	92.65 431	91.29 344	99.37 309	94.85 377	99.85 83	99.46 212

v1192		97.81 272	97.44 290	98.91 225	98.88 348	98.68 206	99.51 170	99.34 271	96.18 352	99.20 223	99.34 317	94.03 271	99.36 313	95.32 369	95.18 360	98.69 309

EI-MVSNet		98.67 175	98.67 158	98.68 262	99.35 243	97.97 259	99.50 178	99.38 250	96.93 300	99.20 223	99.83 83	97.87 110	99.36 313	98.38 198	97.56 288	98.71 300

MVSTER		98.49 182	98.32 191	99.00 208	99.35 243	99.02 162	99.54 151	99.38 250	97.41 254	99.20 223	99.73 165	93.86 279	99.36 313	98.87 127	97.56 288	98.62 344

gg-mvs-nofinetune		96.17 355	95.32 367	98.73 255	98.79 361	98.14 249	99.38 248	94.09 437	91.07 415	98.07 359	91.04 435	89.62 365	99.35 316	96.75 329	99.09 196	98.68 314

pm-mvs1		97.68 296	97.28 314	98.88 232	99.06 320	98.62 214	99.50 178	99.45 213	96.32 341	97.87 368	99.79 131	92.47 314	99.35 316	97.54 279	93.54 389	98.67 322

OurMVSNet-221017-0		97.88 255	97.77 246	98.19 317	98.71 377	96.53 338	99.88 4	99.00 345	97.79 205	98.78 298	99.94 6	91.68 333	99.35 316	97.21 301	96.99 318	98.69 309

EGC-MVSNET		82.80 400	77.86 406	97.62 360	97.91 403	96.12 353	99.33 265	99.28 303	8.40 443	25.05 444	99.27 335	84.11 410	99.33 319	89.20 417	98.22 253	97.42 417

pmmvs6		96.53 347	96.09 352	97.82 350	98.69 379	95.47 368	99.37 250	99.47 193	93.46 400	97.41 377	99.78 138	87.06 393	99.33 319	96.92 324	92.70 401	98.65 333

V42		98.06 224	97.79 241	98.86 239	98.98 336	98.84 192	99.69 60	99.34 271	96.53 327	99.30 196	99.37 307	94.67 243	99.32 321	97.57 276	94.66 370	98.42 373

lessismore_v0				97.79 352	98.69 379	95.44 371		94.75 435		95.71 405	99.87 55	88.69 374	99.32 321	95.89 353	94.93 367	98.62 344

OpenMVS_ROB	92.34 20	94.38 380	93.70 386	96.41 390	97.38 412	93.17 409	99.06 340	98.75 381	86.58 426	94.84 412	98.26 405	81.53 421	99.32 321	89.01 418	97.87 272	96.76 420

v8		97.95 246	97.63 265	98.93 219	98.95 340	98.81 198	99.80 25	99.41 233	96.03 364	99.10 242	99.42 290	94.92 224	99.30 324	96.94 321	94.08 382	98.66 331

v1921920		97.80 274	97.45 285	98.84 243	98.80 360	98.53 222	99.52 161	99.34 271	96.15 356	99.24 212	99.47 279	93.98 273	99.29 325	95.40 367	95.13 362	98.69 309

anonymousdsp		98.44 186	98.28 194	98.94 217	98.50 394	98.96 173	99.77 34	99.50 150	97.07 285	98.87 284	99.77 147	94.76 236	99.28 326	98.66 161	97.60 284	98.57 359

MVSFormer		99.17 95	99.12 88	99.29 172	99.51 187	98.94 179	99.88 4	99.46 202	97.55 234	99.80 58	99.65 206	97.39 121	99.28 326	99.03 105	99.85 83	99.65 144

test_djsdf		98.67 175	98.57 175	98.98 210	98.70 378	98.91 184	99.88 4	99.46 202	97.55 234	99.22 217	99.88 44	95.73 191	99.28 326	99.03 105	97.62 283	98.75 292

SSC-MVS3.2		97.34 324	97.15 321	97.93 338	99.02 327	95.76 360	99.48 195	99.58 70	97.62 226	99.09 245	99.53 256	87.95 385	99.27 329	96.42 342	95.66 349	98.75 292

cascas		97.69 293	97.43 294	98.48 282	98.60 388	97.30 291	98.18 422	99.39 242	92.96 404	98.41 337	98.78 386	93.77 282	99.27 329	98.16 220	98.61 226	98.86 279

v144192		97.92 250	97.60 268	98.87 236	98.83 358	98.65 209	99.55 146	99.34 271	96.20 350	99.32 192	99.40 298	94.36 258	99.26 331	96.37 346	95.03 364	98.70 305

dmvs_re		98.08 222	98.16 199	97.85 345	99.55 174	94.67 389	99.70 56	98.92 355	98.15 154	99.06 253	99.35 313	93.67 285	99.25 332	97.77 255	97.25 310	99.64 151

v2v482		98.06 224	97.77 246	98.92 221	98.90 346	98.82 196	99.57 125	99.36 259	96.65 315	99.19 226	99.35 313	94.20 263	99.25 332	97.72 262	94.97 365	98.69 309

v1240		97.69 293	97.32 309	98.79 251	98.85 355	98.43 236	99.48 195	99.36 259	96.11 359	99.27 205	99.36 310	93.76 283	99.24 334	94.46 381	95.23 359	98.70 305

WBMVS		97.74 284	97.50 277	98.46 288	99.24 275	97.43 287	99.21 310	99.42 230	97.45 247	98.96 270	99.41 294	88.83 371	99.23 335	98.94 115	96.02 335	98.71 300

v1144		97.98 241	97.69 257	98.85 242	98.87 351	98.66 208	99.54 151	99.35 266	96.27 345	99.23 216	99.35 313	94.67 243	99.23 335	96.73 330	95.16 361	98.68 314

v10		97.85 260	97.52 274	98.86 239	98.99 333	98.67 207	99.75 42	99.41 233	95.70 368	98.98 266	99.41 294	94.75 237	99.23 335	96.01 352	94.63 371	98.67 322

WR-MVS_H		98.13 216	97.87 236	98.90 227	99.02 327	98.84 192	99.70 56	99.59 66	97.27 265	98.40 338	99.19 345	95.53 198	99.23 335	98.34 204	93.78 387	98.61 353

miper_enhance_ethall		98.16 213	98.08 211	98.41 296	98.96 339	97.72 275	98.45 410	99.32 288	96.95 297	98.97 268	99.17 346	97.06 138	99.22 339	97.86 244	95.99 338	98.29 382

GG-mvs-BLEND				98.45 290	98.55 392	98.16 247	99.43 219	93.68 438		97.23 383	98.46 396	89.30 366	99.22 339	95.43 366	98.22 253	97.98 404

FC-MVSNet-test		98.75 168	98.62 168	99.15 194	99.08 317	99.45 106	99.86 11	99.60 60	98.23 144	98.70 310	99.82 92	96.80 146	99.22 339	99.07 101	96.38 327	98.79 283

UniMVSNet_NR-MVSNet		98.22 205	97.97 223	98.96 213	98.92 343	98.98 166	99.48 195	99.53 110	97.76 209	98.71 304	99.46 283	96.43 165	99.22 339	98.57 178	92.87 399	98.69 309

DU-MVS		98.08 222	97.79 241	98.96 213	98.87 351	98.98 166	99.41 231	99.45 213	97.87 193	98.71 304	99.50 267	94.82 228	99.22 339	98.57 178	92.87 399	98.68 314

cl____		98.01 237	97.84 239	98.55 276	99.25 273	97.97 259	98.71 393	99.34 271	96.47 334	98.59 328	99.54 252	95.65 194	99.21 344	97.21 301	95.77 344	98.46 370

WR-MVS		98.06 224	97.73 253	99.06 200	98.86 354	99.25 133	99.19 314	99.35 266	97.30 263	98.66 313	99.43 288	93.94 274	99.21 344	98.58 175	94.28 377	98.71 300

test_0402		96.64 345	96.24 347	97.85 345	98.85 355	96.43 342	99.44 214	99.26 307	93.52 398	96.98 391	99.52 260	88.52 379	99.20 346	92.58 406	97.50 295	97.93 407

SixPastTwentyTwo		97.50 312	97.33 308	98.03 327	98.65 382	96.23 350	99.77 34	98.68 393	97.14 276	97.90 366	99.93 10	90.45 352	99.18 347	97.00 315	96.43 326	98.67 322

cl22		97.85 260	97.64 264	98.48 282	99.09 314	97.87 267	98.60 403	99.33 278	97.11 282	98.87 284	99.22 341	92.38 319	99.17 348	98.21 214	95.99 338	98.42 373

tt0320		95.71 365	95.07 369	97.62 360	99.05 323	95.02 380	99.25 298	99.52 115	86.81 424	97.97 363	99.72 169	83.58 413	99.15 349	96.38 345	93.35 390	98.68 314

WB-MVSnew		97.65 301	97.65 261	97.63 359	98.78 364	97.62 281	99.13 324	98.33 403	97.36 258	99.07 248	98.94 373	95.64 195	99.15 349	92.95 400	98.68 224	96.12 427

IterMVS-SCA-FT		97.82 270	97.75 251	98.06 326	99.57 166	96.36 344	99.02 350	99.49 160	97.18 273	98.71 304	99.72 169	92.72 303	99.14 351	97.44 289	95.86 343	98.67 322

pmmvs5		97.52 309	97.30 311	98.16 319	98.57 391	96.73 328	99.27 287	98.90 362	96.14 357	98.37 340	99.53 256	91.54 339	99.14 351	97.51 281	95.87 342	98.63 342

v148		97.79 276	97.55 270	98.50 279	98.74 372	97.72 275	99.54 151	99.33 278	96.26 346	98.90 278	99.51 264	94.68 242	99.14 351	97.83 248	93.15 396	98.63 342

miper_ehance_all_eth		98.18 211	98.10 207	98.41 296	99.23 277	97.72 275	98.72 392	99.31 292	96.60 323	98.88 281	99.29 330	97.29 128	99.13 354	97.60 270	95.99 338	98.38 378

NR-MVSNet		97.97 244	97.61 267	99.02 205	98.87 351	99.26 131	99.47 203	99.42 230	97.63 224	97.08 389	99.50 267	95.07 217	99.13 354	97.86 244	93.59 388	98.68 314

IterMVS		97.83 267	97.77 246	98.02 329	99.58 164	96.27 348	99.02 350	99.48 172	97.22 271	98.71 304	99.70 176	92.75 300	99.13 354	97.46 287	96.00 337	98.67 322
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 381	94.90 372	91.84 406	97.24 416	80.01 436	98.52 407	99.48 172	89.01 420	91.99 423	99.67 199	85.67 400	99.13 354	95.44 365	97.03 317	96.39 424
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 229	97.96 224	98.33 303	99.26 269	97.38 289	98.56 406	99.31 292	96.65 315	98.88 281	99.52 260	96.58 156	99.12 358	97.39 292	95.53 354	98.47 367

pmmvs4		98.13 216	97.90 231	98.81 248	98.61 387	98.87 187	98.99 358	99.21 318	96.44 335	99.06 253	99.58 236	95.90 184	99.11 359	97.18 307	96.11 334	98.46 370

TransMVSNet (Re)		97.15 333	96.58 339	98.86 239	99.12 306	98.85 191	99.49 190	98.91 360	95.48 371	97.16 387	99.80 119	93.38 287	99.11 359	94.16 387	91.73 406	98.62 344

ambc				93.06 404	92.68 435	82.36 429	98.47 409	98.73 390		95.09 410	97.41 418	55.55 436	99.10 361	96.42 342	91.32 407	97.71 410

Baseline_NR-MVSNet		97.76 278	97.45 285	98.68 262	99.09 314	98.29 241	99.41 231	98.85 369	95.65 369	98.63 322	99.67 199	94.82 228	99.10 361	98.07 230	92.89 398	98.64 335

test_vis3_rt		87.04 396	85.81 399	90.73 410	93.99 434	81.96 431	99.76 37	90.23 445	92.81 406	81.35 433	91.56 433	40.06 442	99.07 363	94.27 384	88.23 420	91.15 433

CP-MVSNet		98.09 220	97.78 244	99.01 206	98.97 338	99.24 134	99.67 69	99.46 202	97.25 267	98.48 335	99.64 212	93.79 281	99.06 364	98.63 165	94.10 381	98.74 296

PS-CasMVS		97.93 247	97.59 269	98.95 215	98.99 333	99.06 158	99.68 66	99.52 115	97.13 277	98.31 343	99.68 193	92.44 318	99.05 365	98.51 186	94.08 382	98.75 292

K. test v3		97.10 335	96.79 335	98.01 330	98.72 375	96.33 345	99.87 8	97.05 422	97.59 228	96.16 401	99.80 119	88.71 373	99.04 366	96.69 333	96.55 324	98.65 333

new_pmnet		96.38 351	96.03 353	97.41 368	98.13 402	95.16 379	99.05 342	99.20 319	93.94 393	97.39 380	98.79 385	91.61 338	99.04 366	90.43 413	95.77 344	98.05 397

DIV-MVS_self_test		98.01 237	97.85 238	98.48 282	99.24 275	97.95 263	98.71 393	99.35 266	96.50 328	98.60 327	99.54 252	95.72 192	99.03 368	97.21 301	95.77 344	98.46 370

IterMVS-LS		98.46 185	98.42 184	98.58 270	99.59 162	98.00 257	99.37 250	99.43 228	96.94 299	99.07 248	99.59 232	97.87 110	99.03 368	98.32 207	95.62 350	98.71 300
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 301	97.68 258	97.55 364	98.62 385	94.97 382	98.84 380	99.30 297	96.83 306	98.19 352	99.34 317	97.01 141	99.02 370	95.00 375	96.01 336	98.64 335

Patchmtry		97.75 282	97.40 297	98.81 248	99.10 311	98.87 187	99.11 333	99.33 278	94.83 384	98.81 293	99.38 304	94.33 259	99.02 370	96.10 348	95.57 352	98.53 361

N_pmnet		94.95 375	95.83 358	92.31 405	98.47 395	79.33 437	99.12 327	92.81 443	93.87 394	97.68 373	99.13 351	93.87 278	99.01 372	91.38 410	96.19 332	98.59 357

CR-MVSNet		98.17 212	97.93 229	98.87 236	99.18 290	98.49 230	99.22 308	99.33 278	96.96 295	99.56 136	99.38 304	94.33 259	99.00 373	94.83 378	98.58 229	99.14 250

c3_l		98.12 218	98.04 216	98.38 300	99.30 257	97.69 279	98.81 383	99.33 278	96.67 313	98.83 290	99.34 317	97.11 134	98.99 374	97.58 272	95.34 357	98.48 365

test0.0.03 1		97.71 291	97.42 295	98.56 274	98.41 398	97.82 270	98.78 386	98.63 396	97.34 259	98.05 360	98.98 369	94.45 256	98.98 375	95.04 374	97.15 315	98.89 278

PatchT		97.03 337	96.44 343	98.79 251	98.99 333	98.34 240	99.16 318	99.07 336	92.13 409	99.52 145	97.31 422	94.54 252	98.98 375	88.54 420	98.73 222	99.03 266

GBi-Net		97.68 296	97.48 279	98.29 308	99.51 187	97.26 295	99.43 219	99.48 172	96.49 329	99.07 248	99.32 325	90.26 354	98.98 375	97.10 309	96.65 320	98.62 344

test1		97.68 296	97.48 279	98.29 308	99.51 187	97.26 295	99.43 219	99.48 172	96.49 329	99.07 248	99.32 325	90.26 354	98.98 375	97.10 309	96.65 320	98.62 344

FMVSNet3		98.03 232	97.76 250	98.84 243	99.39 234	98.98 166	99.40 239	99.38 250	96.67 313	99.07 248	99.28 332	92.93 295	98.98 375	97.10 309	96.65 320	98.56 360

FMVSNet2		97.72 288	97.36 300	98.80 250	99.51 187	98.84 192	99.45 208	99.42 230	96.49 329	98.86 288	99.29 330	90.26 354	98.98 375	96.44 341	96.56 323	98.58 358

FMVSNet1		96.84 341	96.36 345	98.29 308	99.32 255	97.26 295	99.43 219	99.48 172	95.11 376	98.55 330	99.32 325	83.95 411	98.98 375	95.81 355	96.26 331	98.62 344

ppachtmachnet_test		97.49 317	97.45 285	97.61 362	98.62 385	95.24 375	98.80 384	99.46 202	96.11 359	98.22 350	99.62 223	96.45 163	98.97 382	93.77 389	95.97 341	98.61 353

TranMVSNet+NR-MVSNet		97.93 247	97.66 260	98.76 254	98.78 364	98.62 214	99.65 81	99.49 160	97.76 209	98.49 334	99.60 230	94.23 262	98.97 382	98.00 234	92.90 397	98.70 305

MVStest1		96.08 358	95.48 363	97.89 342	98.93 341	96.70 329	99.56 132	99.35 266	92.69 407	91.81 424	99.46 283	89.90 360	98.96 384	95.00 375	92.61 402	98.00 402

tt0320-xc		95.31 371	94.59 375	97.45 367	98.92 343	94.73 386	99.20 313	99.31 292	86.74 425	97.23 383	99.72 169	81.14 424	98.95 385	97.08 312	91.98 405	98.67 322

test_method		91.10 391	91.36 393	90.31 411	95.85 424	73.72 444	94.89 432	99.25 309	68.39 435	95.82 404	99.02 363	80.50 425	98.95 385	93.64 392	94.89 369	98.25 385

ADS-MVSNet2		98.02 234	98.07 214	97.87 343	99.33 248	95.19 377	99.23 304	99.08 333	96.24 347	99.10 242	99.67 199	94.11 267	98.93 387	96.81 327	99.05 199	99.48 201

ET-MVSNet_ETH3D		96.49 348	95.64 362	99.05 202	99.53 178	98.82 196	98.84 380	97.51 420	97.63 224	84.77 429	99.21 344	92.09 323	98.91 388	98.98 110	92.21 404	99.41 222

miper_lstm_enhance		98.00 239	97.91 230	98.28 312	99.34 247	97.43 287	98.88 376	99.36 259	96.48 332	98.80 295	99.55 247	95.98 177	98.91 388	97.27 298	95.50 355	98.51 363

MonoMVSNet		98.38 194	98.47 182	98.12 324	98.59 390	96.19 352	99.72 52	98.79 378	97.89 191	99.44 161	99.52 260	96.13 172	98.90 390	98.64 163	97.54 290	99.28 239

PEN-MVS		97.76 278	97.44 290	98.72 257	98.77 369	98.54 221	99.78 32	99.51 130	97.06 287	98.29 346	99.64 212	92.63 309	98.89 391	98.09 223	93.16 395	98.72 298

testing3		97.28 327	96.76 336	98.82 245	99.37 239	98.07 254	99.45 208	99.36 259	97.56 233	97.89 367	98.95 372	83.70 412	98.82 392	96.03 350	98.56 232	99.58 171

testgi		97.65 301	97.50 277	98.13 323	99.36 242	96.45 341	99.42 226	99.48 172	97.76 209	97.87 368	99.45 285	91.09 346	98.81 393	94.53 380	98.52 235	99.13 252

testf1		90.42 394	90.68 395	89.65 414	97.78 406	73.97 442	99.13 324	98.81 374	89.62 417	91.80 425	98.93 374	62.23 434	98.80 394	86.61 428	91.17 408	96.19 425

APD_test2		90.42 394	90.68 395	89.65 414	97.78 406	73.97 442	99.13 324	98.81 374	89.62 417	91.80 425	98.93 374	62.23 434	98.80 394	86.61 428	91.17 408	96.19 425

MIMVSNet		97.73 286	97.45 285	98.57 271	99.45 217	97.50 285	99.02 350	98.98 347	96.11 359	99.41 170	99.14 350	90.28 353	98.74 396	95.74 357	98.93 207	99.47 207

LCM-MVSNet-Re		97.83 267	98.15 201	96.87 384	99.30 257	92.25 414	99.59 109	98.26 404	97.43 251	96.20 400	99.13 351	96.27 169	98.73 397	98.17 219	98.99 204	99.64 151

Syy-MVS		97.09 336	97.14 322	96.95 381	99.00 330	92.73 412	99.29 277	99.39 242	97.06 287	97.41 377	98.15 408	93.92 276	98.68 398	91.71 408	98.34 242	99.45 215

myMVS_eth3d		96.89 339	96.37 344	98.43 295	99.00 330	97.16 299	99.29 277	99.39 242	97.06 287	97.41 377	98.15 408	83.46 414	98.68 398	95.27 370	98.34 242	99.45 215

DTE-MVSNet		97.51 311	97.19 320	98.46 288	98.63 384	98.13 250	99.84 12	99.48 172	96.68 312	97.97 363	99.67 199	92.92 296	98.56 400	96.88 326	92.60 403	98.70 305

PC_three_1452									98.18 152	99.84 46	99.70 176	99.31 3	98.52 401	98.30 209	99.80 112	99.81 71

mvsany_test3		93.77 383	93.45 387	94.74 396	95.78 425	88.01 422	99.64 84	98.25 405	98.28 135	94.31 413	97.97 415	68.89 430	98.51 402	97.50 282	90.37 413	97.71 410

UnsupCasMVSNet_bld		93.53 384	92.51 390	96.58 389	97.38 412	93.82 400	98.24 419	99.48 172	91.10 414	93.10 418	96.66 424	74.89 428	98.37 403	94.03 388	87.71 421	97.56 415

Anonymous20240521		96.20 354	95.89 357	97.13 375	97.72 409	94.96 383	99.79 31	99.29 301	93.01 403	97.20 386	99.03 361	89.69 363	98.36 404	91.16 411	96.13 333	98.07 395

test_f		91.90 390	91.26 394	93.84 399	95.52 429	85.92 424	99.69 60	98.53 401	95.31 373	93.87 415	96.37 426	55.33 437	98.27 405	95.70 358	90.98 411	97.32 418

MDA-MVSNet_test_wron		95.45 367	94.60 374	98.01 330	98.16 401	97.21 298	99.11 333	99.24 312	93.49 399	80.73 435	98.98 369	93.02 293	98.18 406	94.22 386	94.45 374	98.64 335

UnsupCasMVSNet_eth		96.44 349	96.12 350	97.40 369	98.65 382	95.65 361	99.36 255	99.51 130	97.13 277	96.04 403	98.99 367	88.40 380	98.17 407	96.71 331	90.27 414	98.40 376

KD-MVS_2432*1600		94.62 376	93.72 384	97.31 370	97.19 418	95.82 358	98.34 414	99.20 319	95.00 380	97.57 374	98.35 401	87.95 385	98.10 408	92.87 402	77.00 433	98.01 399

miper_refine_blended		94.62 376	93.72 384	97.31 370	97.19 418	95.82 358	98.34 414	99.20 319	95.00 380	97.57 374	98.35 401	87.95 385	98.10 408	92.87 402	77.00 433	98.01 399

YYNet1		95.36 369	94.51 377	97.92 339	97.89 404	97.10 302	99.10 335	99.23 313	93.26 402	80.77 434	99.04 360	92.81 299	98.02 410	94.30 382	94.18 379	98.64 335

EU-MVSNet		97.98 241	98.03 217	97.81 351	98.72 375	96.65 334	99.66 75	99.66 28	98.09 165	98.35 341	99.82 92	95.25 211	98.01 411	97.41 291	95.30 358	98.78 284

Gipuma		90.99 392	90.15 397	93.51 400	98.73 373	90.12 420	93.98 433	99.45 213	79.32 431	92.28 421	94.91 428	69.61 429	97.98 412	87.42 424	95.67 348	92.45 431
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 370	94.73 373	97.15 373	95.53 428	95.94 356	99.35 260	99.10 330	95.13 374	93.55 416	97.54 417	88.15 384	97.91 413	94.58 379	89.69 417	97.61 413

PM-MVS		92.96 387	92.23 391	95.14 395	95.61 426	89.98 421	99.37 250	98.21 408	94.80 385	95.04 411	97.69 416	65.06 431	97.90 414	94.30 382	89.98 416	97.54 416

MDA-MVSNet-bldmvs		94.96 374	93.98 381	97.92 339	98.24 400	97.27 293	99.15 321	99.33 278	93.80 395	80.09 436	99.03 361	88.31 381	97.86 415	93.49 394	94.36 376	98.62 344

Patchmatch-RL test		95.84 361	95.81 359	95.95 393	95.61 426	90.57 419	98.24 419	98.39 402	95.10 378	95.20 408	98.67 389	94.78 232	97.77 416	96.28 347	90.02 415	99.51 195

Anonymous20231206		96.22 352	96.03 353	96.79 386	97.31 415	94.14 398	99.63 90	99.08 333	96.17 353	97.04 390	99.06 358	93.94 274	97.76 417	86.96 426	95.06 363	98.47 367

SD-MVS		99.41 54	99.52 12	99.05 202	99.74 90	99.68 56	99.46 206	99.52 115	99.11 39	99.88 35	99.91 23	99.43 1	97.70 418	98.72 152	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		97.25 329	97.35 302	96.95 381	97.84 405	93.61 406	99.57 125	96.63 428	96.13 358	98.87 284	98.61 392	94.59 247	97.70 418	95.08 373	98.86 213	99.55 178

dongtai		93.26 385	92.93 389	94.25 397	99.39 234	85.68 425	97.68 428	93.27 439	92.87 405	96.85 394	99.39 302	82.33 419	97.48 420	76.78 433	97.80 275	99.58 171

pmmvs3		94.09 382	93.25 388	96.60 388	94.76 433	94.49 392	98.92 372	98.18 410	89.66 416	96.48 397	98.06 414	86.28 397	97.33 421	89.68 416	87.20 422	97.97 405

KD-MVS_self_test		95.00 373	94.34 378	96.96 380	97.07 420	95.39 372	99.56 132	99.44 222	95.11 376	97.13 388	97.32 421	91.86 328	97.27 422	90.35 414	81.23 430	98.23 387

FMVSNet5		96.43 350	96.19 349	97.15 373	99.11 308	95.89 357	99.32 267	99.52 115	94.47 391	98.34 342	99.07 356	87.54 390	97.07 423	92.61 405	95.72 347	98.47 367

new-patchmatchnet		94.48 379	94.08 380	95.67 394	95.08 431	92.41 413	99.18 316	99.28 303	94.55 390	93.49 417	97.37 420	87.86 388	97.01 424	91.57 409	88.36 419	97.61 413

LCM-MVSNet		86.80 398	85.22 402	91.53 408	87.81 440	80.96 434	98.23 421	98.99 346	71.05 433	90.13 428	96.51 425	48.45 441	96.88 425	90.51 412	85.30 424	96.76 420

CL-MVSNet_self_test		94.49 378	93.97 382	96.08 392	96.16 423	93.67 405	98.33 416	99.38 250	95.13 374	97.33 381	98.15 408	92.69 307	96.57 426	88.67 419	79.87 431	97.99 403

MIMVSNet1		95.51 366	95.04 371	96.92 383	97.38 412	95.60 362	99.52 161	99.50 150	93.65 397	96.97 392	99.17 346	85.28 405	96.56 427	88.36 421	95.55 353	98.60 356

test20.03		96.12 356	95.96 355	96.63 387	97.44 411	95.45 369	99.51 170	99.38 250	96.55 326	96.16 401	99.25 338	93.76 283	96.17 428	87.35 425	94.22 378	98.27 383

tmp_tt		82.80 400	81.52 403	86.66 416	66.61 446	68.44 445	92.79 435	97.92 412	68.96 434	80.04 437	99.85 67	85.77 399	96.15 429	97.86 244	43.89 439	95.39 429

test_fmvs3		92.10 389	91.77 392	93.08 403	96.19 422	86.25 423	99.82 16	98.62 397	96.65 315	95.19 409	96.90 423	55.05 438	95.93 430	96.63 338	90.92 412	97.06 419

kuosan		90.92 393	90.11 398	93.34 401	98.78 364	85.59 426	98.15 423	93.16 441	89.37 419	92.07 422	98.38 400	81.48 422	95.19 431	62.54 440	97.04 316	99.25 244

dmvs_testset		95.02 372	96.12 350	91.72 407	99.10 311	80.43 435	99.58 118	97.87 414	97.47 243	95.22 407	98.82 381	93.99 272	95.18 432	88.09 422	94.91 368	99.56 177

PMMVS2		86.87 397	85.37 401	91.35 409	90.21 438	83.80 428	98.89 375	97.45 421	83.13 430	91.67 427	95.03 427	48.49 440	94.70 433	85.86 430	77.62 432	95.54 428

PMVS	70.75 22	75.98 406	74.97 407	79.01 422	70.98 445	55.18 447	93.37 434	98.21 408	65.08 439	61.78 440	93.83 430	21.74 447	92.53 434	78.59 432	91.12 410	89.34 435
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 399	85.65 400	82.75 420	86.77 441	63.39 446	98.35 413	98.92 355	74.11 432	83.39 431	98.98 369	50.85 439	92.40 435	84.54 431	94.97 365	92.46 430

WB-MVS		93.10 386	94.10 379	90.12 412	95.51 430	81.88 432	99.73 50	99.27 306	95.05 379	93.09 419	98.91 378	94.70 241	91.89 436	76.62 434	94.02 384	96.58 422

SSC-MVS		92.73 388	93.73 383	89.72 413	95.02 432	81.38 433	99.76 37	99.23 313	94.87 383	92.80 420	98.93 374	94.71 240	91.37 437	74.49 436	93.80 386	96.42 423

MVE	76.82 21	76.91 405	74.31 409	84.70 417	85.38 443	76.05 441	96.88 431	93.17 440	67.39 436	71.28 438	89.01 437	21.66 448	87.69 438	71.74 437	72.29 435	90.35 434
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 402	79.88 404	82.81 419	90.75 437	76.38 440	97.69 427	95.76 432	66.44 437	83.52 430	92.25 432	62.54 433	87.16 439	68.53 438	61.40 436	84.89 437

EMVS		80.02 403	79.22 405	82.43 421	91.19 436	76.40 439	97.55 430	92.49 444	66.36 438	83.01 432	91.27 434	64.63 432	85.79 440	65.82 439	60.65 437	85.08 436

ANet_high		77.30 404	74.86 408	84.62 418	75.88 444	77.61 438	97.63 429	93.15 442	88.81 421	64.27 439	89.29 436	36.51 443	83.93 441	75.89 435	52.31 438	92.33 432

wuyk23d		40.18 407	41.29 412	36.84 423	86.18 442	49.12 448	79.73 436	22.81 448	27.64 440	25.46 443	28.45 443	21.98 446	48.89 442	55.80 441	23.56 442	12.51 440

test123		39.01 409	42.50 411	28.53 424	39.17 447	20.91 449	98.75 389	19.17 449	19.83 442	38.57 441	66.67 439	33.16 444	15.42 443	37.50 443	29.66 441	49.26 438

testmvs		39.17 408	43.78 410	25.37 425	36.04 448	16.84 450	98.36 412	26.56 447	20.06 441	38.51 442	67.32 438	29.64 445	15.30 444	37.59 442	39.90 440	43.98 439

mmdepth		0.02 414	0.03 417	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	0.27 445	0.00 449	0.00 445	0.00 444	0.00 443	0.00 441

monomultidepth		0.02 414	0.03 417	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	0.27 445	0.00 449	0.00 445	0.00 444	0.00 443	0.00 441

test_blank		0.13 413	0.17 416	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	1.57 444	0.00 449	0.00 445	0.00 444	0.00 443	0.00 441

uanet_test		0.02 414	0.03 417	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	0.27 445	0.00 449	0.00 445	0.00 444	0.00 443	0.00 441

DCPMVS		0.02 414	0.03 417	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	0.27 445	0.00 449	0.00 445	0.00 444	0.00 443	0.00 441

cdsmvs_eth3d_5k		24.64 410	32.85 413	0.00 426	0.00 449	0.00 451	0.00 437	99.51 130	0.00 444	0.00 445	99.56 244	96.58 156	0.00 445	0.00 444	0.00 443	0.00 441

pcd_1.5k_mvsjas		8.27 412	11.03 415	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	0.27 445	99.01 18	0.00 445	0.00 444	0.00 443	0.00 441

sosnet-low-res		0.02 414	0.03 417	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	0.27 445	0.00 449	0.00 445	0.00 444	0.00 443	0.00 441

sosnet		0.02 414	0.03 417	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	0.27 445	0.00 449	0.00 445	0.00 444	0.00 443	0.00 441

uncertanet		0.02 414	0.03 417	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	0.27 445	0.00 449	0.00 445	0.00 444	0.00 443	0.00 441

Regformer		0.02 414	0.03 417	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	0.27 445	0.00 449	0.00 445	0.00 444	0.00 443	0.00 441

ab-mvs-re		8.30 411	11.06 414	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	99.58 236	0.00 449	0.00 445	0.00 444	0.00 443	0.00 441

uanet		0.02 414	0.03 417	0.00 426	0.00 449	0.00 451	0.00 437	0.00 450	0.00 444	0.00 445	0.27 445	0.00 449	0.00 445	0.00 444	0.00 443	0.00 441

WAC-MVS						97.16 299								95.47 364

FOURS1					99.91 1	99.93 1	99.87 8	99.56 80	99.10 40	99.81 54

test_one_0601					99.81 48	99.88 8		99.49 160	98.97 64	99.65 110	99.81 106	99.09 14

eth-test2					0.00 449

eth-test					0.00 449

RE-MVS-def			99.34 45		99.76 72	99.82 25	99.63 90	99.52 115	98.38 123	99.76 75	99.82 92	98.75 58		98.61 169	99.81 107	99.77 92

IU-MVS					99.84 32	99.88 8		99.32 288	98.30 134	99.84 46				98.86 132	99.85 83	99.89 25

save fliter					99.76 72	99.59 80	99.14 323	99.40 239	99.00 56

test0726					99.85 26	99.89 4	99.62 95	99.50 150	99.10 40	99.86 44	99.82 92	98.94 32

GSMVS																99.52 187

test_part2					99.81 48	99.83 19				99.77 69

sam_mvs1												94.86 227				99.52 187

sam_mvs												94.72 239

MTGPA								99.47 193

MTMP							99.54 151	98.88 365

test9_res														97.49 283	99.72 135	99.75 98

agg_prior2														97.21 301	99.73 134	99.75 98

test_prior4						99.56 86	98.99 358

test_prior2							98.96 365		98.34 129	99.01 259	99.52 260	98.68 67		97.96 236	99.74 132

新几何2							99.01 355

旧先验1					99.74 90	99.59 80		99.54 97			99.69 186	98.47 83			99.68 143	99.73 109

原ACMM2							98.95 368

test222					99.75 82	99.49 100	98.91 374	99.49 160	96.42 337	99.34 190	99.65 206	98.28 96			99.69 140	99.72 117

segment_acmp												98.96 25

testdata1							98.85 379		98.32 132

plane_prior7					99.29 261	97.03 312

plane_prior6					99.27 266	96.98 316						92.71 305

plane_prior4											99.61 227

plane_prior3						97.00 314			98.69 95	99.11 239

plane_prior2							99.39 243		98.97 64

plane_prior1					99.26 269

plane_prior						96.97 317	99.21 310		98.45 116						97.60 284

n2								0.00 450

nn								0.00 450

door-mid								98.05 411

test11								99.35 266

door								97.92 412

HQP5-MVS						96.83 324

HQP-NCC					99.19 287		98.98 361		98.24 141	98.66 313

ACMP_Plane					99.19 287		98.98 361		98.24 141	98.66 313

BP-MVS														97.19 305

HQP3-MVS								99.39 242							97.58 286

HQP2-MVS												92.47 314

NP-MVS					99.23 277	96.92 320					99.40 298

MDTV_nov1_ep13_2view						95.18 378	99.35 260		96.84 304	99.58 132		95.19 213		97.82 249		99.46 212

ACMMP++_ref															97.19 313

ACMMP++															97.43 304

Test By Simon												98.75 58

High-resolution multi-view benchmark