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 64	99.38 233	99.37 112	99.58 117	99.62 45	99.41 16	99.87 37	99.92 17	98.81 47	100.00 1	99.97 1	99.93 28	99.94 13

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 61	99.84 32	99.44 106	99.58 117	99.69 18	99.43 12	99.98 9	99.91 23	98.62 73	100.00 1	99.97 1	99.95 19	99.90 21

test_vis1_n_1920		98.63 176	98.40 183	99.31 162	99.86 20	97.94 262	99.67 69	99.62 45	99.43 12	99.99 2	99.91 23	87.29 388	100.00 1	99.92 19	99.92 33	99.98 2

fmvsm_s_conf0.5_n_5		99.37 60	99.21 76	99.86 27	99.80 53	99.68 55	99.42 223	99.61 52	99.37 19	99.97 20	99.86 57	94.96 216	99.99 4	99.97 1	99.93 28	99.92 19

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 32	99.82 25	99.54 149	99.66 28	99.46 7	99.98 9	99.89 35	97.27 129	99.99 4	99.97 1	99.95 19	99.95 9

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 35	99.86 20	99.61 76	99.56 130	99.63 42	99.48 3	99.98 9	99.83 79	98.75 58	99.99 4	99.97 1	99.96 14	99.94 13

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 35	99.84 32	99.63 73	99.56 130	99.63 42	99.47 4	99.98 9	99.82 88	98.75 58	99.99 4	99.97 1	99.97 8	99.94 13

test_fmvsmconf_n		99.70 3	99.64 4	99.87 16	99.80 53	99.66 62	99.48 192	99.64 38	99.45 9	99.92 24	99.92 17	98.62 73	99.99 4	99.96 10	99.99 1	99.96 7

patch_mono-2		99.26 82	99.62 5	98.16 316	99.81 47	94.59 385	99.52 159	99.64 38	99.33 21	99.73 78	99.90 30	99.00 22	99.99 4	99.69 29	99.98 4	99.89 24

h-mvs33		97.70 289	97.28 311	98.97 209	99.70 110	97.27 290	99.36 252	99.45 211	98.94 66	99.66 100	99.64 206	94.93 219	99.99 4	99.48 54	84.36 419	99.65 141

xiu_mvs_v1_base_debu		99.29 76	99.27 66	99.34 155	99.63 142	98.97 168	99.12 321	99.51 128	98.86 72	99.84 43	99.47 273	98.18 100	99.99 4	99.50 49	99.31 174	99.08 254

xiu_mvs_v1_base		99.29 76	99.27 66	99.34 155	99.63 142	98.97 168	99.12 321	99.51 128	98.86 72	99.84 43	99.47 273	98.18 100	99.99 4	99.50 49	99.31 174	99.08 254

xiu_mvs_v1_base_debi		99.29 76	99.27 66	99.34 155	99.63 142	98.97 168	99.12 321	99.51 128	98.86 72	99.84 43	99.47 273	98.18 100	99.99 4	99.50 49	99.31 174	99.08 254

EPNet		98.86 147	98.71 151	99.30 167	97.20 411	98.18 244	99.62 95	98.91 356	99.28 24	98.63 319	99.81 102	95.96 177	99.99 4	99.24 81	99.72 133	99.73 106
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		99.40 56	99.28 63	99.74 70	99.67 121	99.31 122	99.52 159	98.87 363	99.55 1	99.74 76	99.80 115	96.47 160	99.98 15	99.97 1	99.97 8	99.94 13

test_cas_vis1_n_1920		99.16 96	99.01 108	99.61 98	99.81 47	98.86 188	99.65 81	99.64 38	99.39 17	99.97 20	99.94 6	93.20 289	99.98 15	99.55 42	99.91 40	99.99 1

test_vis1_n		97.92 247	97.44 287	99.34 155	99.53 175	98.08 250	99.74 46	99.49 158	99.15 29	100.00 1	99.94 6	79.51 420	99.98 15	99.88 21	99.76 125	99.97 4

xiu_mvs_v2_base		99.26 82	99.25 70	99.29 170	99.53 175	98.91 182	99.02 344	99.45 211	98.80 81	99.71 85	99.26 331	98.94 32	99.98 15	99.34 68	99.23 179	98.98 268

PS-MVSNAJ		99.32 71	99.32 48	99.30 167	99.57 163	98.94 178	98.97 358	99.46 200	98.92 69	99.71 85	99.24 333	99.01 18	99.98 15	99.35 63	99.66 143	98.97 269

QAPM		98.67 172	98.30 190	99.80 55	99.20 281	99.67 59	99.77 34	99.72 11	94.74 383	98.73 299	99.90 30	95.78 187	99.98 15	96.96 314	99.88 64	99.76 96

3Dnovator	97.25 9	99.24 87	99.05 96	99.81 52	99.12 303	99.66 62	99.84 12	99.74 10	99.09 44	98.92 272	99.90 30	95.94 180	99.98 15	98.95 111	99.92 33	99.79 83

OpenMVS	96.50 16	98.47 181	98.12 202	99.52 125	99.04 321	99.53 92	99.82 16	99.72 11	94.56 386	98.08 353	99.88 43	94.73 235	99.98 15	97.47 282	99.76 125	99.06 260

fmvsm_s_conf0.5_n_3		99.37 60	99.20 78	99.87 16	99.75 81	99.70 52	99.48 192	99.66 28	99.45 9	99.99 2	99.93 10	94.64 243	99.97 23	99.94 16	99.97 8	99.95 9

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 59	99.88 8	99.56 130	99.55 87	99.15 29	99.90 27	99.90 30	99.00 22	99.97 23	99.11 92	99.91 40	99.86 37

test_fmvsmconf0.1_n		99.55 18	99.45 25	99.86 27	99.44 215	99.65 66	99.50 175	99.61 52	99.45 9	99.87 37	99.92 17	97.31 126	99.97 23	99.95 12	99.99 1	99.97 4

test_fmvs1_n		98.41 187	98.14 199	99.21 182	99.82 43	97.71 275	99.74 46	99.49 158	99.32 22	99.99 2	99.95 3	85.32 401	99.97 23	99.82 24	99.84 90	99.96 7

CANet_DTU		98.97 137	98.87 132	99.25 177	99.33 245	98.42 236	99.08 330	99.30 293	99.16 28	99.43 160	99.75 150	95.27 205	99.97 23	98.56 178	99.95 19	99.36 226

MVS_0304		99.15 98	98.96 118	99.73 73	98.92 339	99.37 112	99.37 247	96.92 417	99.51 2	99.66 100	99.78 134	96.69 151	99.97 23	99.84 23	99.97 8	99.84 48

MTAPA		99.52 22	99.39 34	99.89 8	99.90 4	99.86 16	99.66 75	99.47 191	98.79 82	99.68 91	99.81 102	98.43 86	99.97 23	98.88 121	99.90 49	99.83 58

PGM-MVS		99.45 40	99.31 54	99.86 27	99.87 15	99.78 40	99.58 117	99.65 35	97.84 196	99.71 85	99.80 115	99.12 13	99.97 23	98.33 202	99.87 67	99.83 58

mPP-MVS		99.44 44	99.30 56	99.86 27	99.88 11	99.79 34	99.69 60	99.48 170	98.12 157	99.50 145	99.75 150	98.78 51	99.97 23	98.57 175	99.89 60	99.83 58

CP-MVS		99.45 40	99.32 48	99.85 35	99.83 40	99.75 44	99.69 60	99.52 114	98.07 167	99.53 140	99.63 212	98.93 36	99.97 23	98.74 146	99.91 40	99.83 58

SteuartSystems-ACMMP		99.54 19	99.42 27	99.87 16	99.82 43	99.81 29	99.59 109	99.51 128	98.62 97	99.79 57	99.83 79	99.28 4	99.97 23	98.48 185	99.90 49	99.84 48
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 92	98.97 114	99.82 49	99.17 295	99.68 55	99.81 20	99.51 128	99.20 26	98.72 300	99.89 35	95.68 191	99.97 23	98.86 129	99.86 75	99.81 70

fmvsm_s_conf0.5_n_7		99.34 67	99.29 60	99.48 133	99.70 110	98.63 210	99.42 223	99.63 42	99.46 7	99.98 9	99.88 43	95.59 194	99.96 35	99.97 1	99.98 4	99.85 41

fmvsm_s_conf0.5_n_2		99.32 71	99.13 85	99.89 8	99.80 53	99.77 41	99.44 211	99.58 69	99.47 4	99.99 2	99.93 10	94.04 267	99.96 35	99.96 10	99.93 28	99.93 18

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 71	99.88 8	99.52 159	99.54 96	99.13 32	99.89 29	99.89 35	98.96 25	99.96 35	99.04 100	99.90 49	99.85 41

our_new_method		99.61 8	99.52 12	99.90 5	99.76 71	99.88 8	99.52 159	99.54 96	99.13 32	99.89 29	99.89 35	98.96 25	99.96 35	99.04 100	99.90 49	99.85 41

fmvsm_s_conf0.5_n_a		99.56 17	99.47 21	99.85 35	99.83 40	99.64 72	99.52 159	99.65 35	99.10 39	99.98 9	99.92 17	97.35 125	99.96 35	99.94 16	99.92 33	99.95 9

fmvsm_s_conf0.5_n		99.51 23	99.40 32	99.85 35	99.84 32	99.65 66	99.51 168	99.67 23	99.13 32	99.98 9	99.92 17	96.60 154	99.96 35	99.95 12	99.96 14	99.95 9

mvsany_test1		99.50 25	99.46 24	99.62 97	99.61 152	99.09 151	98.94 364	99.48 170	99.10 39	99.96 22	99.91 23	98.85 42	99.96 35	99.72 27	99.58 153	99.82 63

test_fmvs1		98.88 143	98.79 144	99.16 187	99.69 115	97.61 279	99.55 144	99.49 158	99.32 22	99.98 9	99.91 23	91.41 337	99.96 35	99.82 24	99.92 33	99.90 21

DVP-MVS++		99.59 12	99.50 17	99.88 10	99.51 184	99.88 8	99.87 8	99.51 128	98.99 57	99.88 32	99.81 102	99.27 5	99.96 35	98.85 131	99.80 110	99.81 70

MSC_two_6792asdad				99.87 16	99.51 184	99.76 42		99.33 275					99.96 35	98.87 124	99.84 90	99.89 24

No_MVS				99.87 16	99.51 184	99.76 42		99.33 275					99.96 35	98.87 124	99.84 90	99.89 24

ZD-MVS					99.71 105	99.79 34		99.61 52	96.84 301	99.56 133	99.54 246	98.58 75	99.96 35	96.93 317	99.75 127

SED-MVS		99.61 8	99.52 12	99.88 10	99.84 32	99.90 2	99.60 102	99.48 170	99.08 45	99.91 25	99.81 102	99.20 7	99.96 35	98.91 118	99.85 82	99.79 83

test_241102_TWO								99.48 170	99.08 45	99.88 32	99.81 102	98.94 32	99.96 35	98.91 118	99.84 90	99.88 30

ZNCC-MVS		99.47 34	99.33 46	99.87 16	99.87 15	99.81 29	99.64 84	99.67 23	98.08 166	99.55 137	99.64 206	98.91 37	99.96 35	98.72 149	99.90 49	99.82 63

DVP-MVS		99.57 16	99.47 21	99.88 10	99.85 26	99.89 4	99.57 124	99.37 255	99.10 39	99.81 51	99.80 115	98.94 32	99.96 35	98.93 115	99.86 75	99.81 70
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 57	99.81 51	99.80 115	99.09 14	99.96 35	98.85 131	99.90 49	99.88 30

test_0728_SECOND				99.91 3	99.84 32	99.89 4	99.57 124	99.51 128					99.96 35	98.93 115	99.86 75	99.88 30

SR-MVS		99.43 47	99.29 60	99.86 27	99.75 81	99.83 19	99.59 109	99.62 45	98.21 144	99.73 78	99.79 127	98.68 67	99.96 35	98.44 191	99.77 122	99.79 83

DPE-MVS		99.46 36	99.32 48	99.91 3	99.78 59	99.88 8	99.36 252	99.51 128	98.73 89	99.88 32	99.84 74	98.72 64	99.96 35	98.16 216	99.87 67	99.88 30
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 49	99.29 60	99.80 55	99.62 148	99.55 87	99.50 175	99.70 15	98.79 82	99.77 66	99.96 1	97.45 120	99.96 35	98.92 117	99.90 49	99.89 24

HFP-MVS		99.49 27	99.37 38	99.86 27	99.87 15	99.80 31	99.66 75	99.67 23	98.15 151	99.68 91	99.69 180	99.06 16	99.96 35	98.69 154	99.87 67	99.84 48

region2R		99.48 31	99.35 42	99.87 16	99.88 11	99.80 31	99.65 81	99.66 28	98.13 156	99.66 100	99.68 187	98.96 25	99.96 35	98.62 163	99.87 67	99.84 48

HPM-MVS++		99.39 58	99.23 74	99.87 16	99.75 81	99.84 18	99.43 216	99.51 128	98.68 94	99.27 202	99.53 250	98.64 72	99.96 35	98.44 191	99.80 110	99.79 83

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 67	99.89 4	99.75 42	99.56 79	99.02 50	99.88 32	99.85 64	99.18 10	99.96 35	99.22 82	99.92 33	99.90 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 27	99.36 40	99.86 27	99.87 15	99.79 34	99.66 75	99.67 23	98.15 151	99.67 95	99.69 180	98.95 30	99.96 35	98.69 154	99.87 67	99.84 48

MP-MVS		99.33 69	99.15 83	99.87 16	99.88 11	99.82 25	99.66 75	99.46 200	98.09 162	99.48 149	99.74 155	98.29 95	99.96 35	97.93 234	99.87 67	99.82 63
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 114	98.90 126	99.74 70	99.80 53	99.46 104	99.59 109	99.49 158	97.03 288	99.63 115	99.69 180	97.27 129	99.96 35	97.82 245	99.84 90	99.81 70

PVSNet_Blended_VisFu		99.36 64	99.28 63	99.61 98	99.86 20	99.07 156	99.47 200	99.93 2	97.66 219	99.71 85	99.86 57	97.73 115	99.96 35	99.47 56	99.82 103	99.79 83

UGNet		98.87 144	98.69 153	99.40 147	99.22 278	98.72 202	99.44 211	99.68 20	99.24 25	99.18 227	99.42 284	92.74 299	99.96 35	99.34 68	99.94 26	99.53 182
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 71	99.32 48	99.32 161	99.85 26	98.29 239	99.71 55	99.66 28	98.11 159	99.41 167	99.80 115	98.37 92	99.96 35	98.99 106	99.96 14	99.72 114

ACMMP		99.45 40	99.32 48	99.82 49	99.89 8	99.67 59	99.62 95	99.69 18	98.12 157	99.63 115	99.84 74	98.73 63	99.96 35	98.55 181	99.83 99	99.81 70
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 35	99.51 184	99.67 59	99.50 175	99.64 38	99.43 12	99.98 9	99.78 134	97.26 131	99.95 67	99.95 12	99.93 28	99.92 19

fmvsm_s_conf0.5_n_4		99.36 64	99.24 71	99.73 73	99.78 59	99.53 92	99.49 187	99.60 59	99.42 15	99.99 2	99.86 57	95.15 211	99.95 67	99.95 12	99.89 60	99.73 106

fmvsm_s_conf0.1_n_2		99.37 60	99.22 75	99.81 52	99.77 67	99.75 44	99.46 203	99.60 59	99.47 4	99.98 9	99.94 6	94.98 215	99.95 67	99.97 1	99.79 117	99.73 106

test_fmvsmconf0.01_n		99.22 89	99.03 100	99.79 58	98.42 391	99.48 101	99.55 144	99.51 128	99.39 17	99.78 62	99.93 10	94.80 227	99.95 67	99.93 18	99.95 19	99.94 13

SR-MVS-dyc-post		99.45 40	99.31 54	99.85 35	99.76 71	99.82 25	99.63 90	99.52 114	98.38 120	99.76 72	99.82 88	98.53 79	99.95 67	98.61 166	99.81 106	99.77 91

GST-MVS		99.40 56	99.24 71	99.85 35	99.86 20	99.79 34	99.60 102	99.67 23	97.97 181	99.63 115	99.68 187	98.52 80	99.95 67	98.38 195	99.86 75	99.81 70

CANet		99.25 86	99.14 84	99.59 101	99.41 223	99.16 141	99.35 257	99.57 74	98.82 77	99.51 144	99.61 221	96.46 161	99.95 67	99.59 37	99.98 4	99.65 141

MP-MVS-pluss		99.37 60	99.20 78	99.88 10	99.90 4	99.87 15	99.30 269	99.52 114	97.18 270	99.60 125	99.79 127	98.79 50	99.95 67	98.83 137	99.91 40	99.83 58
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 49	99.27 66	99.88 10	99.89 8	99.80 31	99.67 69	99.50 148	98.70 91	99.77 66	99.49 264	98.21 98	99.95 67	98.46 189	99.77 122	99.88 30
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 67	96.67 329

APD-MVS_3200maxsize		99.48 31	99.35 42	99.85 35	99.76 71	99.83 19	99.63 90	99.54 96	98.36 124	99.79 57	99.82 88	98.86 41	99.95 67	98.62 163	99.81 106	99.78 89

RPMNet		96.72 340	95.90 353	99.19 184	99.18 287	98.49 228	99.22 304	99.52 114	88.72 419	99.56 133	97.38 413	94.08 266	99.95 67	86.87 421	98.58 226	99.14 246

sss		99.17 94	99.05 96	99.53 119	99.62 148	98.97 168	99.36 252	99.62 45	97.83 197	99.67 95	99.65 200	97.37 124	99.95 67	99.19 84	99.19 182	99.68 131

MVSMamba_PlusPlus		99.46 36	99.41 31	99.64 90	99.68 119	99.50 98	99.75 42	99.50 148	98.27 134	99.87 37	99.92 17	98.09 104	99.94 80	99.65 33	99.95 19	99.47 203

fmvsm_s_conf0.1_n_a		99.26 82	99.06 95	99.85 35	99.52 181	99.62 74	99.54 149	99.62 45	98.69 92	99.99 2	99.96 1	94.47 252	99.94 80	99.88 21	99.92 33	99.98 2

fmvsm_s_conf0.1_n		99.29 76	99.10 89	99.86 27	99.70 110	99.65 66	99.53 158	99.62 45	98.74 88	99.99 2	99.95 3	94.53 250	99.94 80	99.89 20	99.96 14	99.97 4

TSAR-MVS + MP.		99.58 13	99.50 17	99.81 52	99.91 1	99.66 62	99.63 90	99.39 239	98.91 70	99.78 62	99.85 64	99.36 2	99.94 80	98.84 134	99.88 64	99.82 63
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 141	98.75 147	99.39 151	99.46 208	98.61 214	99.76 37	99.50 148	98.06 171	99.81 51	99.88 43	93.91 274	99.94 80	99.11 92	99.27 177	99.61 157

mamv4		99.33 69	99.42 27	99.07 195	99.67 121	97.73 270	99.42 223	99.60 59	98.15 151	99.94 23	99.91 23	98.42 88	99.94 80	99.72 27	99.96 14	99.54 176

XVS		99.53 21	99.42 27	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 60	99.37 178	99.74 155	98.81 47	99.94 80	98.79 142	99.86 75	99.84 48

X-MVStestdata		96.55 343	95.45 362	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 60	99.37 178	64.01 436	98.81 47	99.94 80	98.79 142	99.86 75	99.84 48

旧先验2							98.96 359		96.70 308	99.47 150			99.94 80	98.19 212

新几何1				99.75 67	99.75 81	99.59 79		99.54 96	96.76 304	99.29 196	99.64 206	98.43 86	99.94 80	96.92 319	99.66 143	99.72 114

testdata				99.54 111	99.75 81	98.95 175		99.51 128	97.07 282	99.43 160	99.70 170	98.87 40	99.94 80	97.76 252	99.64 146	99.72 114

HPM-MVS		99.42 49	99.28 63	99.83 48	99.90 4	99.72 48	99.81 20	99.54 96	97.59 225	99.68 91	99.63 212	98.91 37	99.94 80	98.58 172	99.91 40	99.84 48
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 90	99.10 89	99.45 140	99.89 8	98.52 224	99.39 240	99.94 1	98.73 89	99.11 236	99.89 35	95.50 197	99.94 80	99.50 49	99.97 8	99.89 24

APD-MVS		99.27 80	99.08 93	99.84 47	99.75 81	99.79 34	99.50 175	99.50 148	97.16 272	99.77 66	99.82 88	98.78 51	99.94 80	97.56 273	99.86 75	99.80 79
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 31	99.42 27	99.65 84	99.72 100	99.40 111	99.05 336	99.66 28	99.14 31	99.57 132	99.80 115	98.46 84	99.94 80	99.57 40	99.84 90	99.60 160
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		99.06 123	98.88 131	99.61 98	99.62 148	99.16 141	99.37 247	99.56 79	98.04 174	99.53 140	99.62 217	96.84 145	99.94 80	98.85 131	98.49 234	99.72 114

DeepC-MVS	98.35 2	99.30 74	99.19 80	99.64 90	99.82 43	99.23 134	99.62 95	99.55 87	98.94 66	99.63 115	99.95 3	95.82 186	99.94 80	99.37 62	99.97 8	99.73 106
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 80	99.12 87	99.74 70	99.18 287	99.75 44	99.56 130	99.57 74	98.45 113	99.49 148	99.85 64	97.77 114	99.94 80	98.33 202	99.84 90	99.52 183

GDP-MVS		99.08 120	98.89 129	99.64 90	99.53 175	99.34 116	99.64 84	99.48 170	98.32 129	99.77 66	99.66 198	95.14 212	99.93 98	98.97 110	99.50 159	99.64 148

SDMVSNet		99.11 114	98.90 126	99.75 67	99.81 47	99.59 79	99.81 20	99.65 35	98.78 85	99.64 112	99.88 43	94.56 246	99.93 98	99.67 31	98.26 247	99.72 114

FE-MVS		98.48 180	98.17 195	99.40 147	99.54 174	98.96 172	99.68 66	98.81 370	95.54 367	99.62 119	99.70 170	93.82 277	99.93 98	97.35 291	99.46 161	99.32 232

SF-MVS		99.38 59	99.24 71	99.79 58	99.79 57	99.68 55	99.57 124	99.54 96	97.82 201	99.71 85	99.80 115	98.95 30	99.93 98	98.19 212	99.84 90	99.74 101

dcpmvs_2		99.23 88	99.58 7	98.16 316	99.83 40	94.68 383	99.76 37	99.52 114	99.07 47	99.98 9	99.88 43	98.56 77	99.93 98	99.67 31	99.98 4	99.87 35

Anonymous20240529		98.09 217	97.68 255	99.34 155	99.66 131	98.44 233	99.40 236	99.43 225	93.67 393	99.22 214	99.89 35	90.23 354	99.93 98	99.26 80	98.33 241	99.66 137

ACMMP_NAP		99.47 34	99.34 44	99.88 10	99.87 15	99.86 16	99.47 200	99.48 170	98.05 173	99.76 72	99.86 57	98.82 46	99.93 98	98.82 141	99.91 40	99.84 48

EI-MVSNet-UG-set		99.58 13	99.57 8	99.64 90	99.78 59	99.14 146	99.60 102	99.45 211	99.01 52	99.90 27	99.83 79	98.98 24	99.93 98	99.59 37	99.95 19	99.86 37

无先验							98.99 352	99.51 128	96.89 298				99.93 98	97.53 276		99.72 114

VDDNet		97.55 304	97.02 325	99.16 187	99.49 198	98.12 249	99.38 245	99.30 293	95.35 369	99.68 91	99.90 30	82.62 413	99.93 98	99.31 72	98.13 259	99.42 215

ab-mvs		98.86 147	98.63 160	99.54 111	99.64 139	99.19 136	99.44 211	99.54 96	97.77 205	99.30 193	99.81 102	94.20 260	99.93 98	99.17 88	98.82 214	99.49 196

F-COLMAP		99.19 90	99.04 98	99.64 90	99.78 59	99.27 129	99.42 223	99.54 96	97.29 261	99.41 167	99.59 226	98.42 88	99.93 98	98.19 212	99.69 138	99.73 106

BP-MVS1		99.12 109	98.94 122	99.65 84	99.51 184	99.30 124	99.67 69	98.92 351	98.48 109	99.84 43	99.69 180	94.96 216	99.92 110	99.62 36	99.79 117	99.71 123

Anonymous202405211		98.30 198	97.98 219	99.26 176	99.57 163	98.16 245	99.41 228	98.55 394	96.03 361	99.19 223	99.74 155	91.87 324	99.92 110	99.16 89	98.29 246	99.70 125

EI-MVSNet-Vis-set		99.58 13	99.56 10	99.64 90	99.78 59	99.15 145	99.61 101	99.45 211	99.01 52	99.89 29	99.82 88	99.01 18	99.92 110	99.56 41	99.95 19	99.85 41

VDD-MVS		97.73 283	97.35 299	98.88 229	99.47 206	97.12 298	99.34 260	98.85 365	98.19 146	99.67 95	99.85 64	82.98 411	99.92 110	99.49 53	98.32 245	99.60 160

VNet		99.11 114	98.90 126	99.73 73	99.52 181	99.56 85	99.41 228	99.39 239	99.01 52	99.74 76	99.78 134	95.56 195	99.92 110	99.52 47	98.18 255	99.72 114

XVG-OURS-SEG-HR		98.69 170	98.62 165	98.89 227	99.71 105	97.74 269	99.12 321	99.54 96	98.44 116	99.42 163	99.71 166	94.20 260	99.92 110	98.54 182	98.90 208	99.00 265

mvsmamba		99.06 123	98.96 118	99.36 153	99.47 206	98.64 209	99.70 56	99.05 335	97.61 224	99.65 107	99.83 79	96.54 157	99.92 110	99.19 84	99.62 149	99.51 191

HPM-MVS_fast		99.51 23	99.40 32	99.85 35	99.91 1	99.79 34	99.76 37	99.56 79	97.72 210	99.76 72	99.75 150	99.13 12	99.92 110	99.07 98	99.92 33	99.85 41

HY-MVS	97.30 7	98.85 154	98.64 159	99.47 137	99.42 218	99.08 154	99.62 95	99.36 256	97.39 253	99.28 197	99.68 187	96.44 163	99.92 110	98.37 197	98.22 250	99.40 220

DP-MVS		99.16 96	98.95 120	99.78 61	99.77 67	99.53 92	99.41 228	99.50 148	97.03 288	99.04 253	99.88 43	97.39 121	99.92 110	98.66 158	99.90 49	99.87 35

IB-MVS	95.67 18	96.22 349	95.44 363	98.57 268	99.21 279	96.70 326	98.65 393	97.74 411	96.71 307	97.27 377	98.54 388	86.03 395	99.92 110	98.47 188	86.30 417	99.10 249
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 27	99.39 34	99.77 64	99.63 142	99.59 79	99.36 252	99.46 200	99.07 47	99.79 57	99.82 88	98.85 42	99.92 110	98.68 156	99.87 67	99.82 63
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 36	99.39 34	99.67 79	99.55 171	99.58 84	99.74 46	99.51 128	98.42 117	99.87 37	99.84 74	98.05 107	99.91 122	99.58 39	99.94 26	99.52 183

9.14			99.10 89		99.72 100		99.40 236	99.51 128	97.53 235	99.64 112	99.78 134	98.84 44	99.91 122	97.63 264	99.82 103

SMA-MVS		99.44 44	99.30 56	99.85 35	99.73 96	99.83 19	99.56 130	99.47 191	97.45 244	99.78 62	99.82 88	99.18 10	99.91 122	98.79 142	99.89 60	99.81 70
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					99.67 121	99.65 66	99.05 336	99.41 230	96.22 346	98.95 268	99.49 264	98.77 54	99.91 122

train_agg		99.02 129	98.77 145	99.77 64	99.67 121	99.65 66	99.05 336	99.41 230	96.28 340	98.95 268	99.49 264	98.76 55	99.91 122	97.63 264	99.72 133	99.75 97

test_8					99.67 121	99.61 76	99.03 341	99.41 230	96.28 340	98.93 271	99.48 270	98.76 55	99.91 122

agg_prior					99.67 121	99.62 74		99.40 236		98.87 281			99.91 122

原ACMM1				99.65 84	99.73 96	99.33 117		99.47 191	97.46 241	99.12 234	99.66 198	98.67 69	99.91 122	97.70 261	99.69 138	99.71 123

LFMVS		97.90 250	97.35 299	99.54 111	99.52 181	99.01 163	99.39 240	98.24 401	97.10 280	99.65 107	99.79 127	84.79 404	99.91 122	99.28 76	98.38 238	99.69 127

XVG-OURS		98.73 168	98.68 154	98.88 229	99.70 110	97.73 270	98.92 366	99.55 87	98.52 106	99.45 153	99.84 74	95.27 205	99.91 122	98.08 223	98.84 212	99.00 265

PLC	97.94 4	99.02 129	98.85 136	99.53 119	99.66 131	99.01 163	99.24 297	99.52 114	96.85 300	99.27 202	99.48 270	98.25 97	99.91 122	97.76 252	99.62 149	99.65 141
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 297	97.06 324	99.47 137	99.61 152	99.09 151	98.04 419	99.25 305	91.24 410	98.51 329	99.70 170	94.55 248	99.91 122	92.76 398	99.85 82	99.42 215
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
mmtdpeth		96.95 335	96.71 334	97.67 354	99.33 245	94.90 380	99.89 2	99.28 299	98.15 151	99.72 83	98.57 387	86.56 393	99.90 134	99.82 24	89.02 412	98.20 382

UWE-MVS		97.58 303	97.29 310	98.48 279	99.09 311	96.25 346	99.01 349	96.61 423	97.86 191	99.19 223	99.01 358	88.72 369	99.90 134	97.38 289	98.69 220	99.28 235

test_vis1_rt		95.81 359	95.65 358	96.32 385	99.67 121	91.35 412	99.49 187	96.74 421	98.25 137	95.24 400	98.10 406	74.96 421	99.90 134	99.53 45	98.85 211	97.70 406

FA-MVS(test-final)		98.75 165	98.53 176	99.41 146	99.55 171	99.05 159	99.80 25	99.01 340	96.59 322	99.58 129	99.59 226	95.39 200	99.90 134	97.78 248	99.49 160	99.28 235

MCST-MVS		99.43 47	99.30 56	99.82 49	99.79 57	99.74 47	99.29 274	99.40 236	98.79 82	99.52 142	99.62 217	98.91 37	99.90 134	98.64 160	99.75 127	99.82 63

CDPH-MVS		99.13 103	98.91 125	99.80 55	99.75 81	99.71 50	99.15 315	99.41 230	96.60 320	99.60 125	99.55 241	98.83 45	99.90 134	97.48 280	99.83 99	99.78 89

NCCC		99.34 67	99.19 80	99.79 58	99.61 152	99.65 66	99.30 269	99.48 170	98.86 72	99.21 217	99.63 212	98.72 64	99.90 134	98.25 208	99.63 148	99.80 79

114514_t		98.93 139	98.67 155	99.72 76	99.85 26	99.53 92	99.62 95	99.59 65	92.65 405	99.71 85	99.78 134	98.06 106	99.90 134	98.84 134	99.91 40	99.74 101

1112_ss		98.98 135	98.77 145	99.59 101	99.68 119	99.02 161	99.25 295	99.48 170	97.23 267	99.13 232	99.58 230	96.93 144	99.90 134	98.87 124	98.78 217	99.84 48

PHI-MVS		99.30 74	99.17 82	99.70 77	99.56 167	99.52 96	99.58 117	99.80 8	97.12 276	99.62 119	99.73 161	98.58 75	99.90 134	98.61 166	99.91 40	99.68 131

AdaColmap		99.01 133	98.80 141	99.66 80	99.56 167	99.54 89	99.18 310	99.70 15	98.18 149	99.35 184	99.63 212	96.32 166	99.90 134	97.48 280	99.77 122	99.55 174

COLMAP_ROB	97.56 6	98.86 147	98.75 147	99.17 186	99.88 11	98.53 220	99.34 260	99.59 65	97.55 231	98.70 307	99.89 35	95.83 185	99.90 134	98.10 218	99.90 49	99.08 254
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 194	98.03 214	99.31 162	99.63 142	98.56 217	99.54 149	96.75 420	97.53 235	99.73 78	99.65 200	91.25 342	99.89 146	98.62 163	99.56 154	99.48 197

tttt0517		98.42 185	98.14 199	99.28 174	99.66 131	98.38 237	99.74 46	96.85 418	97.68 216	99.79 57	99.74 155	91.39 338	99.89 146	98.83 137	99.56 154	99.57 171

test12				99.75 67	99.64 139	99.61 76		99.29 297		99.21 217		98.38 91	99.89 146		99.74 130	99.74 101

Test_1112_low_res		98.89 142	98.66 158	99.57 106	99.69 115	98.95 175	99.03 341	99.47 191	96.98 290	99.15 230	99.23 334	96.77 148	99.89 146	98.83 137	98.78 217	99.86 37

CNLPA		99.14 101	98.99 110	99.59 101	99.58 161	99.41 110	99.16 312	99.44 219	98.45 113	99.19 223	99.49 264	98.08 105	99.89 146	97.73 256	99.75 127	99.48 197

sd_testset		98.75 165	98.57 172	99.29 170	99.81 47	98.26 241	99.56 130	99.62 45	98.78 85	99.64 112	99.88 43	92.02 321	99.88 151	99.54 43	98.26 247	99.72 114

APD_test1		95.87 357	96.49 339	94.00 392	99.53 175	84.01 421	99.54 149	99.32 285	95.91 363	97.99 358	99.85 64	85.49 399	99.88 151	91.96 401	98.84 212	98.12 386

diffmvs		99.14 101	99.02 104	99.51 127	99.61 152	98.96 172	99.28 279	99.49 158	98.46 111	99.72 83	99.71 166	96.50 159	99.88 151	99.31 72	99.11 189	99.67 134
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		98.86 147	98.80 141	99.03 201	99.76 71	98.79 197	99.28 279	99.91 3	97.42 250	99.67 95	99.37 301	97.53 118	99.88 151	98.98 107	97.29 306	98.42 367

PVSNet_Blended		99.08 120	98.97 114	99.42 145	99.76 71	98.79 197	98.78 380	99.91 3	96.74 305	99.67 95	99.49 264	97.53 118	99.88 151	98.98 107	99.85 82	99.60 160

MVS		97.28 324	96.55 337	99.48 133	98.78 358	98.95 175	99.27 284	99.39 239	83.53 423	98.08 353	99.54 246	96.97 142	99.87 156	94.23 379	99.16 183	99.63 153

MG-MVS		99.13 103	99.02 104	99.45 140	99.57 163	98.63 210	99.07 331	99.34 268	98.99 57	99.61 122	99.82 88	97.98 109	99.87 156	97.00 310	99.80 110	99.85 41

MSDG		98.98 135	98.80 141	99.53 119	99.76 71	99.19 136	98.75 383	99.55 87	97.25 264	99.47 150	99.77 143	97.82 112	99.87 156	96.93 317	99.90 49	99.54 176

ETV-MVS		99.26 82	99.21 76	99.40 147	99.46 208	99.30 124	99.56 130	99.52 114	98.52 106	99.44 158	99.27 329	98.41 90	99.86 159	99.10 95	99.59 152	99.04 261

thisisatest0515		98.14 212	97.79 238	99.19 184	99.50 196	98.50 227	98.61 395	96.82 419	96.95 294	99.54 138	99.43 282	91.66 333	99.86 159	98.08 223	99.51 158	99.22 243

thres600view7		97.86 256	97.51 273	98.92 218	99.72 100	97.95 260	99.59 109	98.74 379	97.94 183	99.27 202	98.62 384	91.75 327	99.86 159	93.73 385	98.19 254	98.96 271

lupinMVS		99.13 103	99.01 108	99.46 139	99.51 184	98.94 178	99.05 336	99.16 320	97.86 191	99.80 55	99.56 238	97.39 121	99.86 159	98.94 112	99.85 82	99.58 168

PVSNet	96.02 17	98.85 154	98.84 138	98.89 227	99.73 96	97.28 289	98.32 411	99.60 59	97.86 191	99.50 145	99.57 235	96.75 149	99.86 159	98.56 178	99.70 137	99.54 176

MAR-MVS		98.86 147	98.63 160	99.54 111	99.37 236	99.66 62	99.45 205	99.54 96	96.61 317	99.01 256	99.40 292	97.09 135	99.86 159	97.68 263	99.53 157	99.10 249
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		97.44 316	97.02 325	98.71 256	99.18 287	96.89 320	99.19 308	99.04 336	97.78 204	98.31 340	98.29 398	85.41 400	99.85 165	98.01 229	97.95 264	99.39 221

test2506		96.81 339	96.65 335	97.29 366	99.74 89	92.21 409	99.60 102	85.06 440	99.13 32	99.77 66	99.93 10	87.82 386	99.85 165	99.38 61	99.38 166	99.80 79

AllTest		98.87 144	98.72 149	99.31 162	99.86 20	98.48 230	99.56 130	99.61 52	97.85 194	99.36 181	99.85 64	95.95 178	99.85 165	96.66 330	99.83 99	99.59 164

TestCases				99.31 162	99.86 20	98.48 230		99.61 52	97.85 194	99.36 181	99.85 64	95.95 178	99.85 165	96.66 330	99.83 99	99.59 164

jason		99.13 103	99.03 100	99.45 140	99.46 208	98.87 185	99.12 321	99.26 303	98.03 176	99.79 57	99.65 200	97.02 140	99.85 165	99.02 104	99.90 49	99.65 141
jason: jason.
CNVR-MVS		99.42 49	99.30 56	99.78 61	99.62 148	99.71 50	99.26 293	99.52 114	98.82 77	99.39 174	99.71 166	98.96 25	99.85 165	98.59 171	99.80 110	99.77 91

PAPM_NR		99.04 126	98.84 138	99.66 80	99.74 89	99.44 106	99.39 240	99.38 247	97.70 214	99.28 197	99.28 326	98.34 93	99.85 165	96.96 314	99.45 162	99.69 127

testing99		97.36 319	96.94 328	98.63 261	99.18 287	96.70 326	99.30 269	98.93 348	97.71 211	98.23 345	98.26 399	84.92 403	99.84 172	98.04 228	97.85 271	99.35 227

testing222		97.16 329	96.50 338	99.16 187	99.16 297	98.47 232	99.27 284	98.66 390	97.71 211	98.23 345	98.15 402	82.28 416	99.84 172	97.36 290	97.66 277	99.18 245

test1111		98.04 227	98.11 203	97.83 344	99.74 89	93.82 394	99.58 117	95.40 427	99.12 37	99.65 107	99.93 10	90.73 347	99.84 172	99.43 59	99.38 166	99.82 63

ECVR-MVS		98.04 227	98.05 212	98.00 329	99.74 89	94.37 389	99.59 109	94.98 428	99.13 32	99.66 100	99.93 10	90.67 348	99.84 172	99.40 60	99.38 166	99.80 79

test_yl		98.86 147	98.63 160	99.54 111	99.49 198	99.18 138	99.50 175	99.07 332	98.22 142	99.61 122	99.51 258	95.37 201	99.84 172	98.60 169	98.33 241	99.59 164

DCV-MVSNet		98.86 147	98.63 160	99.54 111	99.49 198	99.18 138	99.50 175	99.07 332	98.22 142	99.61 122	99.51 258	95.37 201	99.84 172	98.60 169	98.33 241	99.59 164

Fast-Effi-MVS+		98.70 169	98.43 180	99.51 127	99.51 184	99.28 127	99.52 159	99.47 191	96.11 356	99.01 256	99.34 311	96.20 170	99.84 172	97.88 237	98.82 214	99.39 221

TSAR-MVS + GP.		99.36 64	99.36 40	99.36 153	99.67 121	98.61 214	99.07 331	99.33 275	99.00 55	99.82 50	99.81 102	99.06 16	99.84 172	99.09 96	99.42 164	99.65 141

tpmrst		98.33 195	98.48 178	97.90 338	99.16 297	94.78 381	99.31 267	99.11 325	97.27 262	99.45 153	99.59 226	95.33 203	99.84 172	98.48 185	98.61 223	99.09 253

Vis-MVSNet		99.12 109	98.97 114	99.56 108	99.78 59	99.10 150	99.68 66	99.66 28	98.49 108	99.86 41	99.87 53	94.77 232	99.84 172	99.19 84	99.41 165	99.74 101
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 176	98.34 186	99.51 127	99.40 228	99.03 160	98.80 378	99.36 256	96.33 337	99.00 260	99.12 348	98.46 84	99.84 172	95.23 365	99.37 173	99.66 137

PatchMatch-RL		98.84 157	98.62 165	99.52 125	99.71 105	99.28 127	99.06 334	99.77 9	97.74 209	99.50 145	99.53 250	95.41 199	99.84 172	97.17 304	99.64 146	99.44 213

EPP-MVSNet		99.13 103	98.99 110	99.53 119	99.65 137	99.06 157	99.81 20	99.33 275	97.43 248	99.60 125	99.88 43	97.14 133	99.84 172	99.13 90	98.94 203	99.69 127

testing3-2		97.84 261	97.70 253	98.24 311	99.53 175	95.37 370	99.55 144	98.67 389	98.46 111	99.27 202	99.34 311	86.58 392	99.83 185	99.32 71	98.63 222	99.52 183

testing11		97.50 309	97.10 322	98.71 256	99.20 281	96.91 318	99.29 274	98.82 368	97.89 188	98.21 348	98.40 393	85.63 398	99.83 185	98.45 190	98.04 262	99.37 225

thres100view900		97.76 275	97.45 282	98.69 258	99.72 100	97.86 266	99.59 109	98.74 379	97.93 184	99.26 207	98.62 384	91.75 327	99.83 185	93.22 390	98.18 255	98.37 373

tfpn200view9		97.72 285	97.38 295	98.72 254	99.69 115	97.96 258	99.50 175	98.73 385	97.83 197	99.17 228	98.45 391	91.67 331	99.83 185	93.22 390	98.18 255	98.37 373

test_prior				99.68 78	99.67 121	99.48 101		99.56 79					99.83 185			99.74 101

1314		98.68 171	98.54 175	99.11 193	98.89 342	98.65 207	99.27 284	99.49 158	96.89 298	97.99 358	99.56 238	97.72 116	99.83 185	97.74 255	99.27 177	98.84 277

thres400		97.77 274	97.38 295	98.92 218	99.69 115	97.96 258	99.50 175	98.73 385	97.83 197	99.17 228	98.45 391	91.67 331	99.83 185	93.22 390	98.18 255	98.96 271

casdiffmvs		99.13 103	98.98 113	99.56 108	99.65 137	99.16 141	99.56 130	99.50 148	98.33 128	99.41 167	99.86 57	95.92 181	99.83 185	99.45 58	99.16 183	99.70 125
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SPE-MVS-test		99.49 27	99.48 19	99.54 111	99.78 59	99.30 124	99.89 2	99.58 69	98.56 102	99.73 78	99.69 180	98.55 78	99.82 193	99.69 29	99.85 82	99.48 197

MVS_Test		99.10 118	98.97 114	99.48 133	99.49 198	99.14 146	99.67 69	99.34 268	97.31 259	99.58 129	99.76 147	97.65 117	99.82 193	98.87 124	99.07 195	99.46 208

dp		97.75 279	97.80 237	97.59 358	99.10 308	93.71 397	99.32 264	98.88 361	96.48 329	99.08 244	99.55 241	92.67 305	99.82 193	96.52 334	98.58 226	99.24 241

RPSCF		98.22 202	98.62 165	96.99 372	99.82 43	91.58 411	99.72 52	99.44 219	96.61 317	99.66 100	99.89 35	95.92 181	99.82 193	97.46 283	99.10 192	99.57 171

PMMVS		98.80 161	98.62 165	99.34 155	99.27 263	98.70 203	98.76 382	99.31 289	97.34 256	99.21 217	99.07 350	97.20 132	99.82 193	98.56 178	98.87 209	99.52 183

UBG		97.85 257	97.48 276	98.95 212	99.25 270	97.64 277	99.24 297	98.74 379	97.90 187	98.64 317	98.20 401	88.65 373	99.81 198	98.27 207	98.40 236	99.42 215

EIA-MVS		99.18 92	99.09 92	99.45 140	99.49 198	99.18 138	99.67 69	99.53 109	97.66 219	99.40 172	99.44 280	98.10 103	99.81 198	98.94 112	99.62 149	99.35 227

Effi-MVS+		98.81 158	98.59 171	99.48 133	99.46 208	99.12 149	98.08 418	99.50 148	97.50 239	99.38 176	99.41 288	96.37 165	99.81 198	99.11 92	98.54 231	99.51 191

thres200		97.61 301	97.28 311	98.62 262	99.64 139	98.03 252	99.26 293	98.74 379	97.68 216	99.09 242	98.32 397	91.66 333	99.81 198	92.88 395	98.22 250	98.03 392

tpmvs		97.98 238	98.02 216	97.84 343	99.04 321	94.73 382	99.31 267	99.20 315	96.10 360	98.76 297	99.42 284	94.94 218	99.81 198	96.97 313	98.45 235	98.97 269

casdiffmvs_mvg		99.15 98	99.02 104	99.55 110	99.66 131	99.09 151	99.64 84	99.56 79	98.26 136	99.45 153	99.87 53	96.03 175	99.81 198	99.54 43	99.15 186	99.73 106
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	98.81 158	99.37 38	97.12 370	99.60 157	91.75 410	98.61 395	99.44 219	99.35 20	99.83 49	99.85 64	98.70 66	99.81 198	99.02 104	99.91 40	99.81 70

DPM-MVS		98.95 138	98.71 151	99.66 80	99.63 142	99.55 87	98.64 394	99.10 326	97.93 184	99.42 163	99.55 241	98.67 69	99.80 205	95.80 350	99.68 141	99.61 157

DP-MVS Recon		99.12 109	98.95 120	99.65 84	99.74 89	99.70 52	99.27 284	99.57 74	96.40 336	99.42 163	99.68 187	98.75 58	99.80 205	97.98 231	99.72 133	99.44 213

MVS_111021_LR		99.41 53	99.33 46	99.65 84	99.77 67	99.51 97	98.94 364	99.85 6	98.82 77	99.65 107	99.74 155	98.51 81	99.80 205	98.83 137	99.89 60	99.64 148

CS-MVS		99.50 25	99.48 19	99.54 111	99.76 71	99.42 108	99.90 1	99.55 87	98.56 102	99.78 62	99.70 170	98.65 71	99.79 208	99.65 33	99.78 119	99.41 218

Fast-Effi-MVS+-dtu		98.77 164	98.83 140	98.60 263	99.41 223	96.99 312	99.52 159	99.49 158	98.11 159	99.24 209	99.34 311	96.96 143	99.79 208	97.95 233	99.45 162	99.02 264

baseline1		98.31 196	97.95 223	99.38 152	99.50 196	98.74 200	99.59 109	98.93 348	98.41 118	99.14 231	99.60 224	94.59 244	99.79 208	98.48 185	93.29 388	99.61 157

baseline		99.15 98	99.02 104	99.53 119	99.66 131	99.14 146	99.72 52	99.48 170	98.35 125	99.42 163	99.84 74	96.07 173	99.79 208	99.51 48	99.14 187	99.67 134

PVSNet_0	94.43 19	96.09 354	95.47 361	97.94 334	99.31 253	94.34 391	97.81 420	99.70 15	97.12 276	97.46 371	98.75 381	89.71 359	99.79 208	97.69 262	81.69 423	99.68 131

API-MVS		99.04 126	99.03 100	99.06 197	99.40 228	99.31 122	99.55 144	99.56 79	98.54 104	99.33 188	99.39 296	98.76 55	99.78 213	96.98 312	99.78 119	98.07 389

OMC-MVS		99.08 120	99.04 98	99.20 183	99.67 121	98.22 243	99.28 279	99.52 114	98.07 167	99.66 100	99.81 102	97.79 113	99.78 213	97.79 247	99.81 106	99.60 160

GeoE		98.85 154	98.62 165	99.53 119	99.61 152	99.08 154	99.80 25	99.51 128	97.10 280	99.31 190	99.78 134	95.23 209	99.77 215	98.21 210	99.03 198	99.75 97

alignmvs		98.81 158	98.56 174	99.58 104	99.43 216	99.42 108	99.51 168	98.96 346	98.61 98	99.35 184	98.92 371	94.78 229	99.77 215	99.35 63	98.11 260	99.54 176

tpm cat1		97.39 318	97.36 297	97.50 361	99.17 295	93.73 396	99.43 216	99.31 289	91.27 409	98.71 301	99.08 349	94.31 258	99.77 215	96.41 339	98.50 233	99.00 265

CostFormer		97.72 285	97.73 250	97.71 352	99.15 301	94.02 393	99.54 149	99.02 339	94.67 384	99.04 253	99.35 307	92.35 317	99.77 215	98.50 184	97.94 265	99.34 230

MGCFI-Net		99.01 133	98.85 136	99.50 132	99.42 218	99.26 130	99.82 16	99.48 170	98.60 99	99.28 197	98.81 376	97.04 139	99.76 219	99.29 75	97.87 269	99.47 203

test_241102_ONE					99.84 32	99.90 2		99.48 170	99.07 47	99.91 25	99.74 155	99.20 7	99.76 219

MDTV_nov1_ep13			98.32 188		99.11 305	94.44 387	99.27 284	98.74 379	97.51 238	99.40 172	99.62 217	94.78 229	99.76 219	97.59 267	98.81 216

sasdasda		99.02 129	98.86 134	99.51 127	99.42 218	99.32 118	99.80 25	99.48 170	98.63 95	99.31 190	98.81 376	97.09 135	99.75 222	99.27 78	97.90 266	99.47 203

canonicalmvs		99.02 129	98.86 134	99.51 127	99.42 218	99.32 118	99.80 25	99.48 170	98.63 95	99.31 190	98.81 376	97.09 135	99.75 222	99.27 78	97.90 266	99.47 203

Effi-MVS+-dtu		98.78 162	98.89 129	98.47 284	99.33 245	96.91 318	99.57 124	99.30 293	98.47 110	99.41 167	98.99 361	96.78 147	99.74 224	98.73 148	99.38 166	98.74 292

patchmatchnet-post											98.70 382	94.79 228	99.74 224

SCA		98.19 206	98.16 196	98.27 310	99.30 254	95.55 361	99.07 331	98.97 344	97.57 228	99.43 160	99.57 235	92.72 300	99.74 224	97.58 268	99.20 181	99.52 183

BH-untuned		98.42 185	98.36 184	98.59 264	99.49 198	96.70 326	99.27 284	99.13 324	97.24 266	98.80 292	99.38 298	95.75 188	99.74 224	97.07 308	99.16 183	99.33 231

BH-RMVSNet		98.41 187	98.08 208	99.40 147	99.41 223	98.83 193	99.30 269	98.77 375	97.70 214	98.94 270	99.65 200	92.91 295	99.74 224	96.52 334	99.55 156	99.64 148

MVS_111021_HR		99.41 53	99.32 48	99.66 80	99.72 100	99.47 103	98.95 362	99.85 6	98.82 77	99.54 138	99.73 161	98.51 81	99.74 224	98.91 118	99.88 64	99.77 91

test_post											65.99 434	94.65 242	99.73 230

XVG-ACMP-BASELINE		97.83 264	97.71 252	98.20 313	99.11 305	96.33 342	99.41 228	99.52 114	98.06 171	99.05 252	99.50 261	89.64 361	99.73 230	97.73 256	97.38 304	98.53 355

HyFIR lowres test		99.11 114	98.92 123	99.65 84	99.90 4	99.37 112	99.02 344	99.91 3	97.67 218	99.59 128	99.75 150	95.90 183	99.73 230	99.53 45	99.02 200	99.86 37

DeepMVS_CX				93.34 395	99.29 258	82.27 424		99.22 311	85.15 421	96.33 392	99.05 353	90.97 345	99.73 230	93.57 387	97.77 274	98.01 393

Patchmatch-test		97.93 244	97.65 258	98.77 250	99.18 287	97.07 303	99.03 341	99.14 323	96.16 351	98.74 298	99.57 235	94.56 246	99.72 234	93.36 389	99.11 189	99.52 183

LPG-MVS_test		98.22 202	98.13 201	98.49 277	99.33 245	97.05 305	99.58 117	99.55 87	97.46 241	99.24 209	99.83 79	92.58 307	99.72 234	98.09 219	97.51 290	98.68 310

LGP-MVS_train				98.49 277	99.33 245	97.05 305		99.55 87	97.46 241	99.24 209	99.83 79	92.58 307	99.72 234	98.09 219	97.51 290	98.68 310

BH-w/o		98.00 236	97.89 232	98.32 302	99.35 240	96.20 348	99.01 349	98.90 358	96.42 334	98.38 336	99.00 359	95.26 207	99.72 234	96.06 343	98.61 223	99.03 262

ACMP	97.20 11	98.06 221	97.94 225	98.45 287	99.37 236	97.01 310	99.44 211	99.49 158	97.54 234	98.45 333	99.79 127	91.95 323	99.72 234	97.91 235	97.49 295	98.62 338
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 231	97.90 228	98.40 295	99.23 274	96.80 324	99.70 56	99.60 59	97.12 276	98.18 350	99.70 170	91.73 329	99.72 234	98.39 194	97.45 297	98.68 310
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							99.23 300				65.14 435	94.18 263	99.71 240	97.58 268

ADS-MVSNet		98.20 205	98.08 208	98.56 271	99.33 245	96.48 337	99.23 300	99.15 321	96.24 344	99.10 239	99.67 193	94.11 264	99.71 240	96.81 322	99.05 196	99.48 197

JIA-IIPM		97.50 309	97.02 325	98.93 216	98.73 367	97.80 268	99.30 269	98.97 344	91.73 408	98.91 273	94.86 423	95.10 213	99.71 240	97.58 268	97.98 263	99.28 235

EPMVS		97.82 267	97.65 258	98.35 299	98.88 343	95.98 352	99.49 187	94.71 430	97.57 228	99.26 207	99.48 270	92.46 314	99.71 240	97.87 239	99.08 194	99.35 227

TDRefinement		95.42 363	94.57 370	97.97 331	89.83 433	96.11 351	99.48 192	98.75 376	96.74 305	96.68 389	99.88 43	88.65 373	99.71 240	98.37 197	82.74 422	98.09 388

ACMM	97.58 5	98.37 193	98.34 186	98.48 279	99.41 223	97.10 299	99.56 130	99.45 211	98.53 105	99.04 253	99.85 64	93.00 291	99.71 240	98.74 146	97.45 297	98.64 329
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 241	97.77 243	98.57 268	99.59 159	96.61 333	99.45 205	99.08 329	98.21 144	98.88 278	99.80 115	88.66 372	99.70 246	98.58 172	97.72 275	99.39 221

CHOSEN 280x420		99.12 109	99.13 85	99.08 194	99.66 131	97.89 263	98.43 405	99.71 13	98.88 71	99.62 119	99.76 147	96.63 153	99.70 246	99.46 57	99.99 1	99.66 137

EC-MVSNet		99.44 44	99.39 34	99.58 104	99.56 167	99.49 99	99.88 4	99.58 69	98.38 120	99.73 78	99.69 180	98.20 99	99.70 246	99.64 35	99.82 103	99.54 176

PatchmatchNet		98.31 196	98.36 184	98.19 314	99.16 297	95.32 371	99.27 284	98.92 351	97.37 254	99.37 178	99.58 230	94.90 222	99.70 246	97.43 286	99.21 180	99.54 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 216	97.99 218	98.44 290	99.41 223	96.96 316	99.60 102	99.56 79	98.09 162	98.15 351	99.91 23	90.87 346	99.70 246	98.88 121	97.45 297	98.67 317
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 309	96.90 329	99.29 170	99.23 274	98.78 199	99.32 264	98.90 358	97.52 237	98.56 326	98.09 407	84.72 405	99.69 251	97.86 240	97.88 268	99.39 221

HQP_MVS		98.27 201	98.22 194	98.44 290	99.29 258	96.97 314	99.39 240	99.47 191	98.97 63	99.11 236	99.61 221	92.71 302	99.69 251	97.78 248	97.63 278	98.67 317

plane_prior5								99.47 191					99.69 251	97.78 248	97.63 278	98.67 317

D2MVS		98.41 187	98.50 177	98.15 319	99.26 266	96.62 332	99.40 236	99.61 52	97.71 211	98.98 263	99.36 304	96.04 174	99.67 254	98.70 151	97.41 302	98.15 385

IS-MVSNet		99.05 125	98.87 132	99.57 106	99.73 96	99.32 118	99.75 42	99.20 315	98.02 178	99.56 133	99.86 57	96.54 157	99.67 254	98.09 219	99.13 188	99.73 106

CLD-MVS		98.16 210	98.10 204	98.33 300	99.29 258	96.82 323	98.75 383	99.44 219	97.83 197	99.13 232	99.55 241	92.92 293	99.67 254	98.32 204	97.69 276	98.48 359
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 326	97.30 308	97.09 371	99.43 216	93.31 402	99.73 50	98.87 363	98.83 76	99.28 197	99.80 115	84.45 406	99.66 257	97.88 237	97.45 297	98.30 375

AUN-MVS		96.88 337	96.31 343	98.59 264	99.48 205	97.04 308	99.27 284	99.22 311	97.44 247	98.51 329	99.41 288	91.97 322	99.66 257	97.71 259	83.83 420	99.07 259

UniMVSNet_ETH3D		97.32 323	96.81 331	98.87 233	99.40 228	97.46 283	99.51 168	99.53 109	95.86 364	98.54 328	99.77 143	82.44 414	99.66 257	98.68 156	97.52 289	99.50 195

OPM-MVS		98.19 206	98.10 204	98.45 287	98.88 343	97.07 303	99.28 279	99.38 247	98.57 101	99.22 214	99.81 102	92.12 319	99.66 257	98.08 223	97.54 287	98.61 347
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 247	97.78 241	98.32 302	99.46 208	96.68 330	99.56 130	99.54 96	98.41 118	97.79 367	99.87 53	90.18 355	99.66 257	98.05 227	97.18 311	98.62 338

hse-mvs2		97.50 309	97.14 319	98.59 264	99.49 198	97.05 305	99.28 279	99.22 311	98.94 66	99.66 100	99.42 284	94.93 219	99.65 262	99.48 54	83.80 421	99.08 254

VPA-MVSNet		98.29 199	97.95 223	99.30 167	99.16 297	99.54 89	99.50 175	99.58 69	98.27 134	99.35 184	99.37 301	92.53 309	99.65 262	99.35 63	94.46 370	98.72 294

TR-MVS		97.76 275	97.41 293	98.82 242	99.06 317	97.87 264	98.87 372	98.56 393	96.63 316	98.68 309	99.22 335	92.49 310	99.65 262	95.40 361	97.79 273	98.95 273

reproduce_monomvs		97.89 251	97.87 233	97.96 333	99.51 184	95.45 366	99.60 102	99.25 305	99.17 27	98.85 286	99.49 264	89.29 364	99.64 265	99.35 63	96.31 327	98.78 280

gm-plane-assit					98.54 387	92.96 404			94.65 385		99.15 343		99.64 265	97.56 273

HQP4-MVS										98.66 310			99.64 265			98.64 329

HQP-MVS		98.02 231	97.90 228	98.37 298	99.19 284	96.83 321	98.98 355	99.39 239	98.24 138	98.66 310	99.40 292	92.47 311	99.64 265	97.19 301	97.58 283	98.64 329

PAPM		97.59 302	97.09 323	99.07 195	99.06 317	98.26 241	98.30 412	99.10 326	94.88 379	98.08 353	99.34 311	96.27 168	99.64 265	89.87 409	98.92 206	99.31 233

TAPA-MVS	97.07 15	97.74 281	97.34 302	98.94 214	99.70 110	97.53 280	99.25 295	99.51 128	91.90 407	99.30 193	99.63 212	98.78 51	99.64 265	88.09 416	99.87 67	99.65 141
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 191	98.09 207	99.24 179	99.26 266	99.32 118	99.56 130	99.55 87	97.45 244	98.71 301	99.83 79	93.23 286	99.63 271	98.88 121	96.32 326	98.76 286

ITE_SJBPF				98.08 322	99.29 258	96.37 340		98.92 351	98.34 126	98.83 287	99.75 150	91.09 343	99.62 272	95.82 348	97.40 303	98.25 379

LF4IMVS		97.52 306	97.46 281	97.70 353	98.98 332	95.55 361	99.29 274	98.82 368	98.07 167	98.66 310	99.64 206	89.97 356	99.61 273	97.01 309	96.68 316	97.94 400

tpm		97.67 296	97.55 267	98.03 324	99.02 323	95.01 377	99.43 216	98.54 395	96.44 332	99.12 234	99.34 311	91.83 326	99.60 274	97.75 254	96.46 322	99.48 197

tpm2		97.44 316	97.34 302	97.74 351	99.15 301	94.36 390	99.45 205	98.94 347	93.45 398	98.90 275	99.44 280	91.35 339	99.59 275	97.31 292	98.07 261	99.29 234

baseline2		97.87 254	97.55 267	98.82 242	99.18 287	98.02 253	99.41 228	96.58 424	96.97 291	96.51 390	99.17 340	93.43 283	99.57 276	97.71 259	99.03 198	98.86 275

MS-PatchMatch		97.24 328	97.32 306	96.99 372	98.45 390	93.51 401	98.82 376	99.32 285	97.41 251	98.13 352	99.30 322	88.99 366	99.56 277	95.68 354	99.80 110	97.90 403

TinyColmap		97.12 331	96.89 330	97.83 344	99.07 315	95.52 364	98.57 398	98.74 379	97.58 227	97.81 366	99.79 127	88.16 380	99.56 277	95.10 366	97.21 309	98.39 371

USDC		97.34 321	97.20 316	97.75 349	99.07 315	95.20 373	98.51 402	99.04 336	97.99 179	98.31 340	99.86 57	89.02 365	99.55 279	95.67 355	97.36 305	98.49 358

MSLP-MVS++		99.46 36	99.47 21	99.44 144	99.60 157	99.16 141	99.41 228	99.71 13	98.98 60	99.45 153	99.78 134	99.19 9	99.54 280	99.28 76	99.84 90	99.63 153

UWE-MVS-28		97.36 319	97.24 315	97.75 349	98.84 352	94.44 387	99.24 297	97.58 413	97.98 180	99.00 260	99.00 359	91.35 339	99.53 281	93.75 384	98.39 237	99.27 239

TAMVS		99.12 109	99.08 93	99.24 179	99.46 208	98.55 218	99.51 168	99.46 200	98.09 162	99.45 153	99.82 88	98.34 93	99.51 282	98.70 151	98.93 204	99.67 134

EPNet_dtu		98.03 229	97.96 221	98.23 312	98.27 393	95.54 363	99.23 300	98.75 376	99.02 50	97.82 365	99.71 166	96.11 172	99.48 283	93.04 393	99.65 145	99.69 127
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 341	96.22 345	97.97 331	97.00 415	96.28 344	98.66 392	99.03 338	96.61 317	96.93 387	99.79 127	87.20 389	99.47 284	96.65 332	94.13 377	98.16 384

EG-PatchMatch MVS		95.97 356	95.69 357	96.81 379	97.78 400	92.79 405	99.16 312	98.93 348	96.16 351	94.08 408	99.22 335	82.72 412	99.47 284	95.67 355	97.50 292	98.17 383

myMVS_eth3d28		97.69 290	97.34 302	98.73 252	99.27 263	97.52 281	99.33 262	98.78 374	98.03 176	98.82 289	98.49 389	86.64 391	99.46 286	98.44 191	98.24 249	99.23 242

MVP-Stereo		97.81 269	97.75 248	97.99 330	97.53 404	96.60 334	98.96 359	98.85 365	97.22 268	97.23 378	99.36 304	95.28 204	99.46 286	95.51 357	99.78 119	97.92 402
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 178	98.67 155	98.30 304	99.35 240	95.59 360	99.50 175	99.55 87	98.60 99	99.39 174	99.83 79	94.48 251	99.45 288	98.75 145	98.56 229	99.85 41

test-LLR		98.06 221	97.90 228	98.55 273	98.79 355	97.10 299	98.67 389	97.75 409	97.34 256	98.61 322	98.85 373	94.45 253	99.45 288	97.25 295	99.38 166	99.10 249

TESTMET0.1,1		97.55 304	97.27 314	98.40 295	98.93 337	96.53 335	98.67 389	97.61 412	96.96 292	98.64 317	99.28 326	88.63 375	99.45 288	97.30 293	99.38 166	99.21 244

test-mter		97.49 314	97.13 321	98.55 273	98.79 355	97.10 299	98.67 389	97.75 409	96.65 312	98.61 322	98.85 373	88.23 379	99.45 288	97.25 295	99.38 166	99.10 249

mvs_anonymous		99.03 128	98.99 110	99.16 187	99.38 233	98.52 224	99.51 168	99.38 247	97.79 202	99.38 176	99.81 102	97.30 127	99.45 288	99.35 63	98.99 201	99.51 191

tfpnnormal		97.84 261	97.47 279	98.98 207	99.20 281	99.22 135	99.64 84	99.61 52	96.32 338	98.27 344	99.70 170	93.35 285	99.44 293	95.69 353	95.40 353	98.27 377

v7n		97.87 254	97.52 271	98.92 218	98.76 365	98.58 216	99.84 12	99.46 200	96.20 347	98.91 273	99.70 170	94.89 223	99.44 293	96.03 344	93.89 382	98.75 288

jajsoiax		98.43 184	98.28 191	98.88 229	98.60 382	98.43 234	99.82 16	99.53 109	98.19 146	98.63 319	99.80 115	93.22 288	99.44 293	99.22 82	97.50 292	98.77 284

mvs_tets		98.40 190	98.23 193	98.91 222	98.67 375	98.51 226	99.66 75	99.53 109	98.19 146	98.65 316	99.81 102	92.75 297	99.44 293	99.31 72	97.48 296	98.77 284

Vis-MVSNet (Re-imp)		98.87 144	98.72 149	99.31 162	99.71 105	98.88 184	99.80 25	99.44 219	97.91 186	99.36 181	99.78 134	95.49 198	99.43 297	97.91 235	99.11 189	99.62 155

OPU-MVS				99.64 90	99.56 167	99.72 48	99.60 102				99.70 170	99.27 5	99.42 298	98.24 209	99.80 110	99.79 83

Anonymous20231211		97.88 252	97.54 270	98.90 224	99.71 105	98.53 220	99.48 192	99.57 74	94.16 389	98.81 290	99.68 187	93.23 286	99.42 298	98.84 134	94.42 372	98.76 286

ttmdpeth		97.80 271	97.63 262	98.29 305	98.77 363	97.38 286	99.64 84	99.36 256	98.78 85	96.30 393	99.58 230	92.34 318	99.39 300	98.36 199	95.58 348	98.10 387

VPNet		97.84 261	97.44 287	99.01 203	99.21 279	98.94 178	99.48 192	99.57 74	98.38 120	99.28 197	99.73 161	88.89 367	99.39 300	99.19 84	93.27 389	98.71 296

nrg030		98.64 175	98.42 181	99.28 174	99.05 320	99.69 54	99.81 20	99.46 200	98.04 174	99.01 256	99.82 88	96.69 151	99.38 302	99.34 68	94.59 369	98.78 280

GA-MVS		97.85 257	97.47 279	99.00 205	99.38 233	97.99 255	98.57 398	99.15 321	97.04 287	98.90 275	99.30 322	89.83 358	99.38 302	96.70 327	98.33 241	99.62 155

UniMVSNet (Re)		98.29 199	98.00 217	99.13 192	99.00 326	99.36 115	99.49 187	99.51 128	97.95 182	98.97 265	99.13 345	96.30 167	99.38 302	98.36 199	93.34 387	98.66 325

FIs		98.78 162	98.63 160	99.23 181	99.18 287	99.54 89	99.83 15	99.59 65	98.28 132	98.79 294	99.81 102	96.75 149	99.37 305	99.08 97	96.38 324	98.78 280

PS-MVSNAJss		98.92 140	98.92 123	98.90 224	98.78 358	98.53 220	99.78 32	99.54 96	98.07 167	99.00 260	99.76 147	99.01 18	99.37 305	99.13 90	97.23 308	98.81 278

CDS-MVSNet		99.09 119	99.03 100	99.25 177	99.42 218	98.73 201	99.45 205	99.46 200	98.11 159	99.46 152	99.77 143	98.01 108	99.37 305	98.70 151	98.92 206	99.66 137
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 360	95.16 365	97.51 360	99.30 254	93.69 398	98.88 370	95.78 425	85.09 422	98.78 295	92.65 425	91.29 341	99.37 305	94.85 371	99.85 82	99.46 208

v1192		97.81 269	97.44 287	98.91 222	98.88 343	98.68 204	99.51 168	99.34 268	96.18 349	99.20 220	99.34 311	94.03 268	99.36 309	95.32 363	95.18 357	98.69 305

EI-MVSNet		98.67 172	98.67 155	98.68 259	99.35 240	97.97 256	99.50 175	99.38 247	96.93 297	99.20 220	99.83 79	97.87 110	99.36 309	98.38 195	97.56 285	98.71 296

MVSTER		98.49 179	98.32 188	99.00 205	99.35 240	99.02 161	99.54 149	99.38 247	97.41 251	99.20 220	99.73 161	93.86 276	99.36 309	98.87 124	97.56 285	98.62 338

gg-mvs-nofinetune		96.17 352	95.32 364	98.73 252	98.79 355	98.14 247	99.38 245	94.09 431	91.07 412	98.07 356	91.04 429	89.62 362	99.35 312	96.75 324	99.09 193	98.68 310

pm-mvs1		97.68 293	97.28 311	98.88 229	99.06 317	98.62 212	99.50 175	99.45 211	96.32 338	97.87 363	99.79 127	92.47 311	99.35 312	97.54 275	93.54 386	98.67 317

OurMVSNet-221017-0		97.88 252	97.77 243	98.19 314	98.71 371	96.53 335	99.88 4	99.00 341	97.79 202	98.78 295	99.94 6	91.68 330	99.35 312	97.21 297	96.99 315	98.69 305

EGC-MVSNET		82.80 394	77.86 400	97.62 356	97.91 397	96.12 350	99.33 262	99.28 299	8.40 437	25.05 438	99.27 329	84.11 407	99.33 315	89.20 411	98.22 250	97.42 411

pmmvs6		96.53 344	96.09 349	97.82 346	98.69 373	95.47 365	99.37 247	99.47 191	93.46 397	97.41 372	99.78 134	87.06 390	99.33 315	96.92 319	92.70 396	98.65 327

V42		98.06 221	97.79 238	98.86 236	98.98 332	98.84 190	99.69 60	99.34 268	96.53 324	99.30 193	99.37 301	94.67 240	99.32 317	97.57 272	94.66 367	98.42 367

lessismore_v0				97.79 348	98.69 373	95.44 368		94.75 429		95.71 399	99.87 53	88.69 371	99.32 317	95.89 347	94.93 364	98.62 338

OpenMVS_ROB	92.34 20	94.38 374	93.70 380	96.41 384	97.38 406	93.17 403	99.06 334	98.75 376	86.58 420	94.84 406	98.26 399	81.53 417	99.32 317	89.01 412	97.87 269	96.76 414

v8		97.95 243	97.63 262	98.93 216	98.95 336	98.81 196	99.80 25	99.41 230	96.03 361	99.10 239	99.42 284	94.92 221	99.30 320	96.94 316	94.08 379	98.66 325

v1921920		97.80 271	97.45 282	98.84 240	98.80 354	98.53 220	99.52 159	99.34 268	96.15 353	99.24 209	99.47 273	93.98 270	99.29 321	95.40 361	95.13 359	98.69 305

anonymousdsp		98.44 183	98.28 191	98.94 214	98.50 388	98.96 172	99.77 34	99.50 148	97.07 282	98.87 281	99.77 143	94.76 233	99.28 322	98.66 158	97.60 281	98.57 353

MVSFormer		99.17 94	99.12 87	99.29 170	99.51 184	98.94 178	99.88 4	99.46 200	97.55 231	99.80 55	99.65 200	97.39 121	99.28 322	99.03 102	99.85 82	99.65 141

test_djsdf		98.67 172	98.57 172	98.98 207	98.70 372	98.91 182	99.88 4	99.46 200	97.55 231	99.22 214	99.88 43	95.73 189	99.28 322	99.03 102	97.62 280	98.75 288

SSC-MVS3.2		97.34 321	97.15 318	97.93 335	99.02 323	95.76 357	99.48 192	99.58 69	97.62 223	99.09 242	99.53 250	87.95 382	99.27 325	96.42 337	95.66 346	98.75 288

cascas		97.69 290	97.43 291	98.48 279	98.60 382	97.30 288	98.18 416	99.39 239	92.96 401	98.41 334	98.78 380	93.77 279	99.27 325	98.16 216	98.61 223	98.86 275

v144192		97.92 247	97.60 265	98.87 233	98.83 353	98.65 207	99.55 144	99.34 268	96.20 347	99.32 189	99.40 292	94.36 255	99.26 327	96.37 340	95.03 361	98.70 301

dmvs_re		98.08 219	98.16 196	97.85 341	99.55 171	94.67 384	99.70 56	98.92 351	98.15 151	99.06 250	99.35 307	93.67 282	99.25 328	97.77 251	97.25 307	99.64 148

v2v482		98.06 221	97.77 243	98.92 218	98.90 341	98.82 194	99.57 124	99.36 256	96.65 312	99.19 223	99.35 307	94.20 260	99.25 328	97.72 258	94.97 362	98.69 305

v1240		97.69 290	97.32 306	98.79 248	98.85 350	98.43 234	99.48 192	99.36 256	96.11 356	99.27 202	99.36 304	93.76 280	99.24 330	94.46 375	95.23 356	98.70 301

WBMVS		97.74 281	97.50 274	98.46 285	99.24 272	97.43 284	99.21 306	99.42 227	97.45 244	98.96 267	99.41 288	88.83 368	99.23 331	98.94 112	96.02 332	98.71 296

v1144		97.98 238	97.69 254	98.85 239	98.87 346	98.66 206	99.54 149	99.35 263	96.27 342	99.23 213	99.35 307	94.67 240	99.23 331	96.73 325	95.16 358	98.68 310

v10		97.85 257	97.52 271	98.86 236	98.99 329	98.67 205	99.75 42	99.41 230	95.70 365	98.98 263	99.41 288	94.75 234	99.23 331	96.01 346	94.63 368	98.67 317

WR-MVS_H		98.13 213	97.87 233	98.90 224	99.02 323	98.84 190	99.70 56	99.59 65	97.27 262	98.40 335	99.19 339	95.53 196	99.23 331	98.34 201	93.78 384	98.61 347

miper_enhance_ethall		98.16 210	98.08 208	98.41 293	98.96 335	97.72 272	98.45 404	99.32 285	96.95 294	98.97 265	99.17 340	97.06 138	99.22 335	97.86 240	95.99 335	98.29 376

GG-mvs-BLEND				98.45 287	98.55 386	98.16 245	99.43 216	93.68 432		97.23 378	98.46 390	89.30 363	99.22 335	95.43 360	98.22 250	97.98 398

FC-MVSNet-test		98.75 165	98.62 165	99.15 191	99.08 314	99.45 105	99.86 11	99.60 59	98.23 141	98.70 307	99.82 88	96.80 146	99.22 335	99.07 98	96.38 324	98.79 279

UniMVSNet_NR-MVSNet		98.22 202	97.97 220	98.96 210	98.92 339	98.98 165	99.48 192	99.53 109	97.76 206	98.71 301	99.46 277	96.43 164	99.22 335	98.57 175	92.87 394	98.69 305

DU-MVS		98.08 219	97.79 238	98.96 210	98.87 346	98.98 165	99.41 228	99.45 211	97.87 190	98.71 301	99.50 261	94.82 225	99.22 335	98.57 175	92.87 394	98.68 310

cl____		98.01 234	97.84 236	98.55 273	99.25 270	97.97 256	98.71 387	99.34 268	96.47 331	98.59 325	99.54 246	95.65 192	99.21 340	97.21 297	95.77 341	98.46 364

WR-MVS		98.06 221	97.73 250	99.06 197	98.86 349	99.25 132	99.19 308	99.35 263	97.30 260	98.66 310	99.43 282	93.94 271	99.21 340	98.58 172	94.28 374	98.71 296

test_0402		96.64 342	96.24 344	97.85 341	98.85 350	96.43 339	99.44 211	99.26 303	93.52 395	96.98 385	99.52 254	88.52 376	99.20 342	92.58 400	97.50 292	97.93 401

SixPastTwentyTwo		97.50 309	97.33 305	98.03 324	98.65 376	96.23 347	99.77 34	98.68 388	97.14 273	97.90 361	99.93 10	90.45 349	99.18 343	97.00 310	96.43 323	98.67 317

cl22		97.85 257	97.64 261	98.48 279	99.09 311	97.87 264	98.60 397	99.33 275	97.11 279	98.87 281	99.22 335	92.38 316	99.17 344	98.21 210	95.99 335	98.42 367

WB-MVSnew		97.65 298	97.65 258	97.63 355	98.78 358	97.62 278	99.13 318	98.33 398	97.36 255	99.07 245	98.94 367	95.64 193	99.15 345	92.95 394	98.68 221	96.12 421

IterMVS-SCA-FT		97.82 267	97.75 248	98.06 323	99.57 163	96.36 341	99.02 344	99.49 158	97.18 270	98.71 301	99.72 165	92.72 300	99.14 346	97.44 285	95.86 340	98.67 317

pmmvs5		97.52 306	97.30 308	98.16 316	98.57 385	96.73 325	99.27 284	98.90 358	96.14 354	98.37 337	99.53 250	91.54 336	99.14 346	97.51 277	95.87 339	98.63 336

v148		97.79 273	97.55 267	98.50 276	98.74 366	97.72 272	99.54 149	99.33 275	96.26 343	98.90 275	99.51 258	94.68 239	99.14 346	97.83 244	93.15 391	98.63 336

miper_ehance_all_eth		98.18 208	98.10 204	98.41 293	99.23 274	97.72 272	98.72 386	99.31 289	96.60 320	98.88 278	99.29 324	97.29 128	99.13 349	97.60 266	95.99 335	98.38 372

NR-MVSNet		97.97 241	97.61 264	99.02 202	98.87 346	99.26 130	99.47 200	99.42 227	97.63 221	97.08 383	99.50 261	95.07 214	99.13 349	97.86 240	93.59 385	98.68 310

IterMVS		97.83 264	97.77 243	98.02 326	99.58 161	96.27 345	99.02 344	99.48 170	97.22 268	98.71 301	99.70 170	92.75 297	99.13 349	97.46 283	96.00 334	98.67 317
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 375	94.90 367	91.84 400	97.24 410	80.01 430	98.52 401	99.48 170	89.01 417	91.99 417	99.67 193	85.67 397	99.13 349	95.44 359	97.03 314	96.39 418
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 226	97.96 221	98.33 300	99.26 266	97.38 286	98.56 400	99.31 289	96.65 312	98.88 278	99.52 254	96.58 155	99.12 353	97.39 288	95.53 351	98.47 361

pmmvs4		98.13 213	97.90 228	98.81 245	98.61 381	98.87 185	98.99 352	99.21 314	96.44 332	99.06 250	99.58 230	95.90 183	99.11 354	97.18 303	96.11 331	98.46 364

TransMVSNet (Re)		97.15 330	96.58 336	98.86 236	99.12 303	98.85 189	99.49 187	98.91 356	95.48 368	97.16 381	99.80 115	93.38 284	99.11 354	94.16 381	91.73 400	98.62 338

ambc				93.06 398	92.68 429	82.36 423	98.47 403	98.73 385		95.09 404	97.41 412	55.55 430	99.10 356	96.42 337	91.32 401	97.71 404

Baseline_NR-MVSNet		97.76 275	97.45 282	98.68 259	99.09 311	98.29 239	99.41 228	98.85 365	95.65 366	98.63 319	99.67 193	94.82 225	99.10 356	98.07 226	92.89 393	98.64 329

test_vis3_rt		87.04 390	85.81 393	90.73 404	93.99 428	81.96 425	99.76 37	90.23 439	92.81 403	81.35 427	91.56 427	40.06 436	99.07 358	94.27 378	88.23 414	91.15 427

CP-MVSNet		98.09 217	97.78 241	99.01 203	98.97 334	99.24 133	99.67 69	99.46 200	97.25 264	98.48 332	99.64 206	93.79 278	99.06 359	98.63 162	94.10 378	98.74 292

PS-CasMVS		97.93 244	97.59 266	98.95 212	98.99 329	99.06 157	99.68 66	99.52 114	97.13 274	98.31 340	99.68 187	92.44 315	99.05 360	98.51 183	94.08 379	98.75 288

K. test v3		97.10 332	96.79 332	98.01 327	98.72 369	96.33 342	99.87 8	97.05 416	97.59 225	96.16 395	99.80 115	88.71 370	99.04 361	96.69 328	96.55 321	98.65 327

new_pmnet		96.38 348	96.03 350	97.41 362	98.13 396	95.16 376	99.05 336	99.20 315	93.94 390	97.39 375	98.79 379	91.61 335	99.04 361	90.43 407	95.77 341	98.05 391

DIV-MVS_self_test		98.01 234	97.85 235	98.48 279	99.24 272	97.95 260	98.71 387	99.35 263	96.50 325	98.60 324	99.54 246	95.72 190	99.03 363	97.21 297	95.77 341	98.46 364

IterMVS-LS		98.46 182	98.42 181	98.58 267	99.59 159	98.00 254	99.37 247	99.43 225	96.94 296	99.07 245	99.59 226	97.87 110	99.03 363	98.32 204	95.62 347	98.71 296
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 298	97.68 255	97.55 359	98.62 379	94.97 378	98.84 374	99.30 293	96.83 303	98.19 349	99.34 311	97.01 141	99.02 365	95.00 369	96.01 333	98.64 329

Patchmtry		97.75 279	97.40 294	98.81 245	99.10 308	98.87 185	99.11 327	99.33 275	94.83 381	98.81 290	99.38 298	94.33 256	99.02 365	96.10 342	95.57 349	98.53 355

N_pmnet		94.95 369	95.83 355	92.31 399	98.47 389	79.33 431	99.12 321	92.81 437	93.87 391	97.68 368	99.13 345	93.87 275	99.01 367	91.38 404	96.19 329	98.59 351

CR-MVSNet		98.17 209	97.93 226	98.87 233	99.18 287	98.49 228	99.22 304	99.33 275	96.96 292	99.56 133	99.38 298	94.33 256	99.00 368	94.83 372	98.58 226	99.14 246

c3_l		98.12 215	98.04 213	98.38 297	99.30 254	97.69 276	98.81 377	99.33 275	96.67 310	98.83 287	99.34 311	97.11 134	98.99 369	97.58 268	95.34 354	98.48 359

test0.0.03 1		97.71 288	97.42 292	98.56 271	98.41 392	97.82 267	98.78 380	98.63 391	97.34 256	98.05 357	98.98 363	94.45 253	98.98 370	95.04 368	97.15 312	98.89 274

PatchT		97.03 334	96.44 340	98.79 248	98.99 329	98.34 238	99.16 312	99.07 332	92.13 406	99.52 142	97.31 416	94.54 249	98.98 370	88.54 414	98.73 219	99.03 262

GBi-Net		97.68 293	97.48 276	98.29 305	99.51 184	97.26 292	99.43 216	99.48 170	96.49 326	99.07 245	99.32 319	90.26 351	98.98 370	97.10 305	96.65 317	98.62 338

test1		97.68 293	97.48 276	98.29 305	99.51 184	97.26 292	99.43 216	99.48 170	96.49 326	99.07 245	99.32 319	90.26 351	98.98 370	97.10 305	96.65 317	98.62 338

FMVSNet3		98.03 229	97.76 247	98.84 240	99.39 231	98.98 165	99.40 236	99.38 247	96.67 310	99.07 245	99.28 326	92.93 292	98.98 370	97.10 305	96.65 317	98.56 354

FMVSNet2		97.72 285	97.36 297	98.80 247	99.51 184	98.84 190	99.45 205	99.42 227	96.49 326	98.86 285	99.29 324	90.26 351	98.98 370	96.44 336	96.56 320	98.58 352

FMVSNet1		96.84 338	96.36 342	98.29 305	99.32 252	97.26 292	99.43 216	99.48 170	95.11 373	98.55 327	99.32 319	83.95 408	98.98 370	95.81 349	96.26 328	98.62 338

ppachtmachnet_test		97.49 314	97.45 282	97.61 357	98.62 379	95.24 372	98.80 378	99.46 200	96.11 356	98.22 347	99.62 217	96.45 162	98.97 377	93.77 383	95.97 338	98.61 347

TranMVSNet+NR-MVSNet		97.93 244	97.66 257	98.76 251	98.78 358	98.62 212	99.65 81	99.49 158	97.76 206	98.49 331	99.60 224	94.23 259	98.97 377	98.00 230	92.90 392	98.70 301

MVStest1		96.08 355	95.48 360	97.89 339	98.93 337	96.70 326	99.56 130	99.35 263	92.69 404	91.81 418	99.46 277	89.90 357	98.96 379	95.00 369	92.61 397	98.00 396

test_method		91.10 385	91.36 387	90.31 405	95.85 418	73.72 438	94.89 426	99.25 305	68.39 429	95.82 398	99.02 357	80.50 419	98.95 380	93.64 386	94.89 366	98.25 379

ADS-MVSNet2		98.02 231	98.07 211	97.87 340	99.33 245	95.19 374	99.23 300	99.08 329	96.24 344	99.10 239	99.67 193	94.11 264	98.93 381	96.81 322	99.05 196	99.48 197

ET-MVSNet_ETH3D		96.49 345	95.64 359	99.05 199	99.53 175	98.82 194	98.84 374	97.51 414	97.63 221	84.77 423	99.21 338	92.09 320	98.91 382	98.98 107	92.21 399	99.41 218

miper_lstm_enhance		98.00 236	97.91 227	98.28 309	99.34 244	97.43 284	98.88 370	99.36 256	96.48 329	98.80 292	99.55 241	95.98 176	98.91 382	97.27 294	95.50 352	98.51 357

MonoMVSNet		98.38 191	98.47 179	98.12 321	98.59 384	96.19 349	99.72 52	98.79 373	97.89 188	99.44 158	99.52 254	96.13 171	98.90 384	98.64 160	97.54 287	99.28 235

PEN-MVS		97.76 275	97.44 287	98.72 254	98.77 363	98.54 219	99.78 32	99.51 128	97.06 284	98.29 343	99.64 206	92.63 306	98.89 385	98.09 219	93.16 390	98.72 294

testing3		97.28 324	96.76 333	98.82 242	99.37 236	98.07 251	99.45 205	99.36 256	97.56 230	97.89 362	98.95 366	83.70 409	98.82 386	96.03 344	98.56 229	99.58 168

testgi		97.65 298	97.50 274	98.13 320	99.36 239	96.45 338	99.42 223	99.48 170	97.76 206	97.87 363	99.45 279	91.09 343	98.81 387	94.53 374	98.52 232	99.13 248

testf1		90.42 388	90.68 389	89.65 408	97.78 400	73.97 436	99.13 318	98.81 370	89.62 414	91.80 419	98.93 368	62.23 428	98.80 388	86.61 422	91.17 402	96.19 419

APD_test2		90.42 388	90.68 389	89.65 408	97.78 400	73.97 436	99.13 318	98.81 370	89.62 414	91.80 419	98.93 368	62.23 428	98.80 388	86.61 422	91.17 402	96.19 419

MIMVSNet		97.73 283	97.45 282	98.57 268	99.45 214	97.50 282	99.02 344	98.98 343	96.11 356	99.41 167	99.14 344	90.28 350	98.74 390	95.74 351	98.93 204	99.47 203

LCM-MVSNet-Re		97.83 264	98.15 198	96.87 378	99.30 254	92.25 408	99.59 109	98.26 399	97.43 248	96.20 394	99.13 345	96.27 168	98.73 391	98.17 215	98.99 201	99.64 148

Syy-MVS		97.09 333	97.14 319	96.95 375	99.00 326	92.73 406	99.29 274	99.39 239	97.06 284	97.41 372	98.15 402	93.92 273	98.68 392	91.71 402	98.34 239	99.45 211

myMVS_eth3d		96.89 336	96.37 341	98.43 292	99.00 326	97.16 296	99.29 274	99.39 239	97.06 284	97.41 372	98.15 402	83.46 410	98.68 392	95.27 364	98.34 239	99.45 211

DTE-MVSNet		97.51 308	97.19 317	98.46 285	98.63 378	98.13 248	99.84 12	99.48 170	96.68 309	97.97 360	99.67 193	92.92 293	98.56 394	96.88 321	92.60 398	98.70 301

PC_three_1452									98.18 149	99.84 43	99.70 170	99.31 3	98.52 395	98.30 206	99.80 110	99.81 70

mvsany_test3		93.77 377	93.45 381	94.74 390	95.78 419	88.01 416	99.64 84	98.25 400	98.28 132	94.31 407	97.97 409	68.89 424	98.51 396	97.50 278	90.37 407	97.71 404

UnsupCasMVSNet_bld		93.53 378	92.51 384	96.58 383	97.38 406	93.82 394	98.24 413	99.48 170	91.10 411	93.10 412	96.66 418	74.89 422	98.37 397	94.03 382	87.71 415	97.56 409

Anonymous20240521		96.20 351	95.89 354	97.13 369	97.72 403	94.96 379	99.79 31	99.29 297	93.01 400	97.20 380	99.03 355	89.69 360	98.36 398	91.16 405	96.13 330	98.07 389

test_f		91.90 384	91.26 388	93.84 393	95.52 423	85.92 418	99.69 60	98.53 396	95.31 370	93.87 409	96.37 420	55.33 431	98.27 399	95.70 352	90.98 405	97.32 412

MDA-MVSNet_test_wron		95.45 362	94.60 369	98.01 327	98.16 395	97.21 295	99.11 327	99.24 308	93.49 396	80.73 429	98.98 363	93.02 290	98.18 400	94.22 380	94.45 371	98.64 329

UnsupCasMVSNet_eth		96.44 346	96.12 347	97.40 363	98.65 376	95.65 358	99.36 252	99.51 128	97.13 274	96.04 397	98.99 361	88.40 377	98.17 401	96.71 326	90.27 408	98.40 370

KD-MVS_2432*1600		94.62 370	93.72 378	97.31 364	97.19 412	95.82 355	98.34 408	99.20 315	95.00 377	97.57 369	98.35 395	87.95 382	98.10 402	92.87 396	77.00 427	98.01 393

miper_refine_blended		94.62 370	93.72 378	97.31 364	97.19 412	95.82 355	98.34 408	99.20 315	95.00 377	97.57 369	98.35 395	87.95 382	98.10 402	92.87 396	77.00 427	98.01 393

YYNet1		95.36 364	94.51 371	97.92 336	97.89 398	97.10 299	99.10 329	99.23 309	93.26 399	80.77 428	99.04 354	92.81 296	98.02 404	94.30 376	94.18 376	98.64 329

EU-MVSNet		97.98 238	98.03 214	97.81 347	98.72 369	96.65 331	99.66 75	99.66 28	98.09 162	98.35 338	99.82 88	95.25 208	98.01 405	97.41 287	95.30 355	98.78 280

Gipuma		90.99 386	90.15 391	93.51 394	98.73 367	90.12 414	93.98 427	99.45 211	79.32 425	92.28 415	94.91 422	69.61 423	97.98 406	87.42 418	95.67 345	92.45 425
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 365	94.73 368	97.15 367	95.53 422	95.94 353	99.35 257	99.10 326	95.13 371	93.55 410	97.54 411	88.15 381	97.91 407	94.58 373	89.69 411	97.61 407

PM-MVS		92.96 381	92.23 385	95.14 389	95.61 420	89.98 415	99.37 247	98.21 402	94.80 382	95.04 405	97.69 410	65.06 425	97.90 408	94.30 376	89.98 410	97.54 410

MDA-MVSNet-bldmvs		94.96 368	93.98 375	97.92 336	98.24 394	97.27 290	99.15 315	99.33 275	93.80 392	80.09 430	99.03 355	88.31 378	97.86 409	93.49 388	94.36 373	98.62 338

Patchmatch-RL test		95.84 358	95.81 356	95.95 387	95.61 420	90.57 413	98.24 413	98.39 397	95.10 375	95.20 402	98.67 383	94.78 229	97.77 410	96.28 341	90.02 409	99.51 191

Anonymous20231206		96.22 349	96.03 350	96.79 380	97.31 409	94.14 392	99.63 90	99.08 329	96.17 350	97.04 384	99.06 352	93.94 271	97.76 411	86.96 420	95.06 360	98.47 361

SD-MVS		99.41 53	99.52 12	99.05 199	99.74 89	99.68 55	99.46 203	99.52 114	99.11 38	99.88 32	99.91 23	99.43 1	97.70 412	98.72 149	99.93 28	99.77 91
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		97.25 326	97.35 299	96.95 375	97.84 399	93.61 400	99.57 124	96.63 422	96.13 355	98.87 281	98.61 386	94.59 244	97.70 412	95.08 367	98.86 210	99.55 174

dongtai		93.26 379	92.93 383	94.25 391	99.39 231	85.68 419	97.68 422	93.27 433	92.87 402	96.85 388	99.39 296	82.33 415	97.48 414	76.78 427	97.80 272	99.58 168

pmmvs3		94.09 376	93.25 382	96.60 382	94.76 427	94.49 386	98.92 366	98.18 404	89.66 413	96.48 391	98.06 408	86.28 394	97.33 415	89.68 410	87.20 416	97.97 399

KD-MVS_self_test		95.00 367	94.34 372	96.96 374	97.07 414	95.39 369	99.56 130	99.44 219	95.11 373	97.13 382	97.32 415	91.86 325	97.27 416	90.35 408	81.23 424	98.23 381

FMVSNet5		96.43 347	96.19 346	97.15 367	99.11 305	95.89 354	99.32 264	99.52 114	94.47 388	98.34 339	99.07 350	87.54 387	97.07 417	92.61 399	95.72 344	98.47 361

new-patchmatchnet		94.48 373	94.08 374	95.67 388	95.08 425	92.41 407	99.18 310	99.28 299	94.55 387	93.49 411	97.37 414	87.86 385	97.01 418	91.57 403	88.36 413	97.61 407

LCM-MVSNet		86.80 392	85.22 396	91.53 402	87.81 434	80.96 428	98.23 415	98.99 342	71.05 427	90.13 422	96.51 419	48.45 435	96.88 419	90.51 406	85.30 418	96.76 414

CL-MVSNet_self_test		94.49 372	93.97 376	96.08 386	96.16 417	93.67 399	98.33 410	99.38 247	95.13 371	97.33 376	98.15 402	92.69 304	96.57 420	88.67 413	79.87 425	97.99 397

MIMVSNet1		95.51 361	95.04 366	96.92 377	97.38 406	95.60 359	99.52 159	99.50 148	93.65 394	96.97 386	99.17 340	85.28 402	96.56 421	88.36 415	95.55 350	98.60 350

test20.03		96.12 353	95.96 352	96.63 381	97.44 405	95.45 366	99.51 168	99.38 247	96.55 323	96.16 395	99.25 332	93.76 280	96.17 422	87.35 419	94.22 375	98.27 377

tmp_tt		82.80 394	81.52 397	86.66 410	66.61 440	68.44 439	92.79 429	97.92 406	68.96 428	80.04 431	99.85 64	85.77 396	96.15 423	97.86 240	43.89 433	95.39 423

test_fmvs3		92.10 383	91.77 386	93.08 397	96.19 416	86.25 417	99.82 16	98.62 392	96.65 312	95.19 403	96.90 417	55.05 432	95.93 424	96.63 333	90.92 406	97.06 413

kuosan		90.92 387	90.11 392	93.34 395	98.78 358	85.59 420	98.15 417	93.16 435	89.37 416	92.07 416	98.38 394	81.48 418	95.19 425	62.54 434	97.04 313	99.25 240

dmvs_testset		95.02 366	96.12 347	91.72 401	99.10 308	80.43 429	99.58 117	97.87 408	97.47 240	95.22 401	98.82 375	93.99 269	95.18 426	88.09 416	94.91 365	99.56 173

PMMVS2		86.87 391	85.37 395	91.35 403	90.21 432	83.80 422	98.89 369	97.45 415	83.13 424	91.67 421	95.03 421	48.49 434	94.70 427	85.86 424	77.62 426	95.54 422

PMVS	70.75 22	75.98 400	74.97 401	79.01 416	70.98 439	55.18 441	93.37 428	98.21 402	65.08 433	61.78 434	93.83 424	21.74 441	92.53 428	78.59 426	91.12 404	89.34 429
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 393	85.65 394	82.75 414	86.77 435	63.39 440	98.35 407	98.92 351	74.11 426	83.39 425	98.98 363	50.85 433	92.40 429	84.54 425	94.97 362	92.46 424

WB-MVS		93.10 380	94.10 373	90.12 406	95.51 424	81.88 426	99.73 50	99.27 302	95.05 376	93.09 413	98.91 372	94.70 238	91.89 430	76.62 428	94.02 381	96.58 416

SSC-MVS		92.73 382	93.73 377	89.72 407	95.02 426	81.38 427	99.76 37	99.23 309	94.87 380	92.80 414	98.93 368	94.71 237	91.37 431	74.49 430	93.80 383	96.42 417

MVE	76.82 21	76.91 399	74.31 403	84.70 411	85.38 437	76.05 435	96.88 425	93.17 434	67.39 430	71.28 432	89.01 431	21.66 442	87.69 432	71.74 431	72.29 429	90.35 428
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 396	79.88 398	82.81 413	90.75 431	76.38 434	97.69 421	95.76 426	66.44 431	83.52 424	92.25 426	62.54 427	87.16 433	68.53 432	61.40 430	84.89 431

EMVS		80.02 397	79.22 399	82.43 415	91.19 430	76.40 433	97.55 424	92.49 438	66.36 432	83.01 426	91.27 428	64.63 426	85.79 434	65.82 433	60.65 431	85.08 430

ANet_high		77.30 398	74.86 402	84.62 412	75.88 438	77.61 432	97.63 423	93.15 436	88.81 418	64.27 433	89.29 430	36.51 437	83.93 435	75.89 429	52.31 432	92.33 426

wuyk23d		40.18 401	41.29 406	36.84 417	86.18 436	49.12 442	79.73 430	22.81 442	27.64 434	25.46 437	28.45 437	21.98 440	48.89 436	55.80 435	23.56 436	12.51 434

test123		39.01 403	42.50 405	28.53 418	39.17 441	20.91 443	98.75 383	19.17 443	19.83 436	38.57 435	66.67 433	33.16 438	15.42 437	37.50 437	29.66 435	49.26 432

testmvs		39.17 402	43.78 404	25.37 419	36.04 442	16.84 444	98.36 406	26.56 441	20.06 435	38.51 436	67.32 432	29.64 439	15.30 438	37.59 436	39.90 434	43.98 433

mmdepth		0.02 408	0.03 411	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.27 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

monomultidepth		0.02 408	0.03 411	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.27 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

test_blank		0.13 407	0.17 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	1.57 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uanet_test		0.02 408	0.03 411	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.27 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

DCPMVS		0.02 408	0.03 411	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.27 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

cdsmvs_eth3d_5k		24.64 404	32.85 407	0.00 420	0.00 443	0.00 445	0.00 431	99.51 128	0.00 438	0.00 439	99.56 238	96.58 155	0.00 439	0.00 438	0.00 437	0.00 435

pcd_1.5k_mvsjas		8.27 406	11.03 409	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.27 439	99.01 18	0.00 439	0.00 438	0.00 437	0.00 435

sosnet-low-res		0.02 408	0.03 411	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.27 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

sosnet		0.02 408	0.03 411	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.27 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uncertanet		0.02 408	0.03 411	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.27 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

Regformer		0.02 408	0.03 411	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.27 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

ab-mvs-re		8.30 405	11.06 408	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	99.58 230	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uanet		0.02 408	0.03 411	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.27 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

WAC-MVS						97.16 296								95.47 358

FOURS1					99.91 1	99.93 1	99.87 8	99.56 79	99.10 39	99.81 51

test_one_0601					99.81 47	99.88 8		99.49 158	98.97 63	99.65 107	99.81 102	99.09 14

eth-test2					0.00 443

eth-test					0.00 443

RE-MVS-def			99.34 44		99.76 71	99.82 25	99.63 90	99.52 114	98.38 120	99.76 72	99.82 88	98.75 58		98.61 166	99.81 106	99.77 91

IU-MVS					99.84 32	99.88 8		99.32 285	98.30 131	99.84 43				98.86 129	99.85 82	99.89 24

save fliter					99.76 71	99.59 79	99.14 317	99.40 236	99.00 55

test0726					99.85 26	99.89 4	99.62 95	99.50 148	99.10 39	99.86 41	99.82 88	98.94 32

GSMVS																99.52 183

test_part2					99.81 47	99.83 19				99.77 66

sam_mvs1												94.86 224				99.52 183

sam_mvs												94.72 236

MTGPA								99.47 191

MTMP							99.54 149	98.88 361

test9_res														97.49 279	99.72 133	99.75 97

agg_prior2														97.21 297	99.73 132	99.75 97

test_prior4						99.56 85	98.99 352

test_prior2							98.96 359		98.34 126	99.01 256	99.52 254	98.68 67		97.96 232	99.74 130

新几何2							99.01 349

旧先验1					99.74 89	99.59 79		99.54 96			99.69 180	98.47 83			99.68 141	99.73 106

原ACMM2							98.95 362

test222					99.75 81	99.49 99	98.91 368	99.49 158	96.42 334	99.34 187	99.65 200	98.28 96			99.69 138	99.72 114

segment_acmp												98.96 25

testdata1							98.85 373		98.32 129

plane_prior7					99.29 258	97.03 309

plane_prior6					99.27 263	96.98 313						92.71 302

plane_prior4											99.61 221

plane_prior3						97.00 311			98.69 92	99.11 236

plane_prior2							99.39 240		98.97 63

plane_prior1					99.26 266

plane_prior						96.97 314	99.21 306		98.45 113						97.60 281

n2								0.00 444

nn								0.00 444

door-mid								98.05 405

test11								99.35 263

door								97.92 406

HQP5-MVS						96.83 321

HQP-NCC					99.19 284		98.98 355		98.24 138	98.66 310

ACMP_Plane					99.19 284		98.98 355		98.24 138	98.66 310

BP-MVS														97.19 301

HQP3-MVS								99.39 239							97.58 283

HQP2-MVS												92.47 311

NP-MVS					99.23 274	96.92 317					99.40 292

MDTV_nov1_ep13_2view						95.18 375	99.35 257		96.84 301	99.58 129		95.19 210		97.82 245		99.46 208

ACMMP++_ref															97.19 310

ACMMP++															97.43 301

Test By Simon												98.75 58

High-resolution multi-view benchmark