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 69	99.38 265	99.37 118	99.58 126	99.62 47	99.41 20	99.87 45	99.92 17	98.81 47	100.00 1	99.97 2	99.93 32	99.94 17

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 66	99.84 35	99.44 111	99.58 126	99.69 18	99.43 16	99.98 12	99.91 25	98.62 73	100.00 1	99.97 2	99.95 22	99.90 25

test_vis1_n_1920		98.63 207	98.40 215	99.31 186	99.86 22	97.94 288	99.67 71	99.62 47	99.43 16	99.99 2	99.91 25	87.29 421	100.00 1	99.92 23	99.92 38	99.98 2

fmvsm_s_conf0.5_n_10		99.41 56	99.24 75	99.92 1	99.83 44	99.84 19	99.53 170	99.56 86	99.45 11	99.99 2	99.92 17	94.92 247	99.99 4	99.97 2	99.97 8	99.95 11

fmvsm_l_conf0.5_n_9		99.58 14	99.47 22	99.92 1	99.85 28	99.82 27	99.47 224	99.63 42	99.45 11	99.98 12	99.89 40	97.02 144	99.99 4	99.98 1	99.96 16	99.95 11

NormalMVS		99.27 85	99.19 85	99.52 134	99.89 8	98.83 212	99.65 84	99.52 125	99.10 43	99.84 52	99.76 176	95.80 208	99.99 4	99.30 87	99.84 97	99.74 109

SymmetryMVS		99.15 110	99.02 118	99.52 134	99.72 106	98.83 212	99.65 84	99.34 299	99.10 43	99.84 52	99.76 176	95.80 208	99.99 4	99.30 87	98.72 249	99.73 118

fmvsm_s_conf0.5_n_5		99.37 65	99.21 81	99.86 31	99.80 59	99.68 59	99.42 251	99.61 56	99.37 23	99.97 24	99.86 70	94.96 242	99.99 4	99.97 2	99.93 32	99.92 23

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 35	99.82 27	99.54 161	99.66 28	99.46 7	99.98 12	99.89 40	97.27 130	99.99 4	99.97 2	99.95 22	99.95 11

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 39	99.86 22	99.61 80	99.56 141	99.63 42	99.48 3	99.98 12	99.83 97	98.75 58	99.99 4	99.97 2	99.96 16	99.94 17

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 39	99.84 35	99.63 77	99.56 141	99.63 42	99.47 4	99.98 12	99.82 106	98.75 58	99.99 4	99.97 2	99.97 8	99.94 17

test_fmvsmconf_n		99.70 3	99.64 4	99.87 20	99.80 59	99.66 66	99.48 214	99.64 38	99.45 11	99.92 29	99.92 17	98.62 73	99.99 4	99.96 13	99.99 1	99.96 7

patch_mono-2		99.26 88	99.62 5	98.16 348	99.81 53	94.59 421	99.52 172	99.64 38	99.33 25	99.73 92	99.90 32	99.00 22	99.99 4	99.69 34	99.98 4	99.89 28

h-mvs33		97.70 321	97.28 344	98.97 234	99.70 117	97.27 316	99.36 280	99.45 235	98.94 73	99.66 117	99.64 241	94.93 245	99.99 4	99.48 63	84.36 456	99.65 162

xiu_mvs_v1_base_debu		99.29 81	99.27 70	99.34 178	99.63 158	98.97 178	99.12 357	99.51 144	98.86 79	99.84 52	99.47 308	98.18 101	99.99 4	99.50 56	99.31 186	99.08 287

xiu_mvs_v1_base		99.29 81	99.27 70	99.34 178	99.63 158	98.97 178	99.12 357	99.51 144	98.86 79	99.84 52	99.47 308	98.18 101	99.99 4	99.50 56	99.31 186	99.08 287

xiu_mvs_v1_base_debi		99.29 81	99.27 70	99.34 178	99.63 158	98.97 178	99.12 357	99.51 144	98.86 79	99.84 52	99.47 308	98.18 101	99.99 4	99.50 56	99.31 186	99.08 287

EPNet		98.86 172	98.71 179	99.30 191	97.20 447	98.18 268	99.62 102	98.91 390	99.28 28	98.63 351	99.81 121	95.96 196	99.99 4	99.24 97	99.72 143	99.73 118
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n_8		99.54 21	99.42 29	99.89 10	99.83 44	99.74 50	99.51 181	99.62 47	99.46 7	99.99 2	99.90 32	96.60 167	99.98 19	99.95 15	99.95 22	99.96 7

MM		99.40 61	99.28 66	99.74 75	99.67 129	99.31 130	99.52 172	98.87 397	99.55 1	99.74 90	99.80 139	96.47 174	99.98 19	99.97 2	99.97 8	99.94 17

test_cas_vis1_n_1920		99.16 106	99.01 123	99.61 104	99.81 53	98.86 206	99.65 84	99.64 38	99.39 21	99.97 24	99.94 6	93.20 322	99.98 19	99.55 49	99.91 45	99.99 1

test_vis1_n		97.92 279	97.44 320	99.34 178	99.53 207	98.08 275	99.74 47	99.49 179	99.15 33	100.00 1	99.94 6	79.51 457	99.98 19	99.88 25	99.76 135	99.97 4

xiu_mvs_v2_base		99.26 88	99.25 74	99.29 194	99.53 207	98.91 197	99.02 381	99.45 235	98.80 89	99.71 100	99.26 367	98.94 32	99.98 19	99.34 80	99.23 195	98.98 301

PS-MVSNAJ		99.32 76	99.32 51	99.30 191	99.57 191	98.94 192	98.97 395	99.46 224	98.92 76	99.71 100	99.24 369	99.01 18	99.98 19	99.35 75	99.66 154	98.97 302

QAPM		98.67 202	98.30 222	99.80 60	99.20 314	99.67 63	99.77 34	99.72 11	94.74 416	98.73 331	99.90 32	95.78 210	99.98 19	96.96 348	99.88 71	99.76 103

3Dnovator	97.25 9	99.24 93	99.05 107	99.81 56	99.12 336	99.66 66	99.84 12	99.74 10	99.09 50	98.92 304	99.90 32	95.94 199	99.98 19	98.95 136	99.92 38	99.79 88

OpenMVS	96.50 16	98.47 213	98.12 234	99.52 134	99.04 355	99.53 96	99.82 16	99.72 11	94.56 419	98.08 386	99.88 51	94.73 262	99.98 19	97.47 315	99.76 135	99.06 293

fmvsm_s_conf0.5_n_3		99.37 65	99.20 83	99.87 20	99.75 87	99.70 56	99.48 214	99.66 28	99.45 11	99.99 2	99.93 10	94.64 271	99.97 28	99.94 20	99.97 8	99.95 11

reproduce_model		99.63 7	99.54 11	99.90 7	99.78 65	99.88 9	99.56 141	99.55 95	99.15 33	99.90 33	99.90 32	99.00 22	99.97 28	99.11 113	99.91 45	99.86 41

test_fmvsmconf0.1_n		99.55 20	99.45 27	99.86 31	99.44 247	99.65 70	99.50 191	99.61 56	99.45 11	99.87 45	99.92 17	97.31 127	99.97 28	99.95 15	99.99 1	99.97 4

test_fmvs1_n		98.41 219	98.14 231	99.21 207	99.82 49	97.71 301	99.74 47	99.49 179	99.32 26	99.99 2	99.95 3	85.32 435	99.97 28	99.82 28	99.84 97	99.96 7

CANet_DTU		98.97 160	98.87 156	99.25 201	99.33 278	98.42 260	99.08 366	99.30 326	99.16 32	99.43 184	99.75 181	95.27 230	99.97 28	98.56 203	99.95 22	99.36 259

MGCNet		99.15 110	98.96 134	99.73 78	98.92 373	99.37 118	99.37 275	96.92 454	99.51 2	99.66 117	99.78 163	96.69 163	99.97 28	99.84 27	99.97 8	99.84 52

MTAPA		99.52 25	99.39 37	99.89 10	99.90 4	99.86 17	99.66 78	99.47 213	98.79 90	99.68 106	99.81 121	98.43 86	99.97 28	98.88 146	99.90 56	99.83 62

PGM-MVS		99.45 43	99.31 57	99.86 31	99.87 17	99.78 43	99.58 126	99.65 35	97.84 227	99.71 100	99.80 139	99.12 13	99.97 28	98.33 228	99.87 74	99.83 62

mPP-MVS		99.44 47	99.30 59	99.86 31	99.88 13	99.79 37	99.69 62	99.48 191	98.12 179	99.50 168	99.75 181	98.78 51	99.97 28	98.57 200	99.89 67	99.83 62

CP-MVS		99.45 43	99.32 51	99.85 39	99.83 44	99.75 47	99.69 62	99.52 125	98.07 190	99.53 163	99.63 247	98.93 36	99.97 28	98.74 171	99.91 45	99.83 62

SteuartSystems-ACMMP		99.54 21	99.42 29	99.87 20	99.82 49	99.81 32	99.59 116	99.51 144	98.62 107	99.79 71	99.83 97	99.28 4	99.97 28	98.48 210	99.90 56	99.84 52
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 100	98.97 130	99.82 53	99.17 328	99.68 59	99.81 20	99.51 144	99.20 30	98.72 332	99.89 40	95.68 214	99.97 28	98.86 154	99.86 82	99.81 75

fmvsm_s_conf0.5_n_9		99.41 56	99.28 66	99.81 56	99.84 35	99.52 100	99.48 214	99.62 47	99.46 7	99.99 2	99.92 17	95.24 234	99.96 40	99.97 2	99.97 8	99.96 7

lecture		99.60 12	99.50 17	99.89 10	99.89 8	99.90 2	99.75 42	99.59 69	99.06 56	99.88 39	99.85 77	98.41 90	99.96 40	99.28 90	99.84 97	99.83 62

KinetiMVS		99.12 123	98.92 143	99.70 82	99.67 129	99.40 116	99.67 71	99.63 42	98.73 97	99.94 27	99.81 121	94.54 277	99.96 40	98.40 219	99.93 32	99.74 109

fmvsm_s_conf0.5_n_7		99.34 72	99.29 63	99.48 148	99.70 117	98.63 233	99.42 251	99.63 42	99.46 7	99.98 12	99.88 51	95.59 217	99.96 40	99.97 2	99.98 4	99.85 45

fmvsm_s_conf0.5_n_2		99.32 76	99.13 91	99.89 10	99.80 59	99.77 44	99.44 238	99.58 74	99.47 4	99.99 2	99.93 10	94.04 298	99.96 40	99.96 13	99.93 32	99.93 22

reproduce-ours		99.61 8	99.52 12	99.90 7	99.76 77	99.88 9	99.52 172	99.54 104	99.13 36	99.89 36	99.89 40	98.96 25	99.96 40	99.04 122	99.90 56	99.85 45

our_new_method		99.61 8	99.52 12	99.90 7	99.76 77	99.88 9	99.52 172	99.54 104	99.13 36	99.89 36	99.89 40	98.96 25	99.96 40	99.04 122	99.90 56	99.85 45

fmvsm_s_conf0.5_n_a		99.56 19	99.47 22	99.85 39	99.83 44	99.64 76	99.52 172	99.65 35	99.10 43	99.98 12	99.92 17	97.35 126	99.96 40	99.94 20	99.92 38	99.95 11

fmvsm_s_conf0.5_n		99.51 26	99.40 35	99.85 39	99.84 35	99.65 70	99.51 181	99.67 23	99.13 36	99.98 12	99.92 17	96.60 167	99.96 40	99.95 15	99.96 16	99.95 11

mvsany_test1		99.50 28	99.46 26	99.62 103	99.61 176	99.09 160	98.94 401	99.48 191	99.10 43	99.96 26	99.91 25	98.85 42	99.96 40	99.72 31	99.58 164	99.82 68

test_fmvs1		98.88 166	98.79 170	99.16 212	99.69 122	97.61 305	99.55 156	99.49 179	99.32 26	99.98 12	99.91 25	91.41 370	99.96 40	99.82 28	99.92 38	99.90 25

DVP-MVS++		99.59 13	99.50 17	99.88 14	99.51 216	99.88 9	99.87 8	99.51 144	98.99 64	99.88 39	99.81 121	99.27 5	99.96 40	98.85 156	99.80 120	99.81 75

MSC_two_6792asdad				99.87 20	99.51 216	99.76 45		99.33 307					99.96 40	98.87 149	99.84 97	99.89 28

No_MVS				99.87 20	99.51 216	99.76 45		99.33 307					99.96 40	98.87 149	99.84 97	99.89 28

ZD-MVS					99.71 112	99.79 37		99.61 56	96.84 334	99.56 154	99.54 281	98.58 75	99.96 40	96.93 351	99.75 137

SED-MVS		99.61 8	99.52 12	99.88 14	99.84 35	99.90 2	99.60 109	99.48 191	99.08 51	99.91 30	99.81 121	99.20 7	99.96 40	98.91 143	99.85 89	99.79 88

test_241102_TWO								99.48 191	99.08 51	99.88 39	99.81 121	98.94 32	99.96 40	98.91 143	99.84 97	99.88 34

ZNCC-MVS		99.47 37	99.33 49	99.87 20	99.87 17	99.81 32	99.64 91	99.67 23	98.08 189	99.55 160	99.64 241	98.91 37	99.96 40	98.72 174	99.90 56	99.82 68

DVP-MVS		99.57 18	99.47 22	99.88 14	99.85 28	99.89 5	99.57 134	99.37 286	99.10 43	99.81 64	99.80 139	98.94 32	99.96 40	98.93 140	99.86 82	99.81 75
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 64	99.81 64	99.80 139	99.09 14	99.96 40	98.85 156	99.90 56	99.88 34

test_0728_SECOND				99.91 5	99.84 35	99.89 5	99.57 134	99.51 144					99.96 40	98.93 140	99.86 82	99.88 34

SR-MVS		99.43 50	99.29 63	99.86 31	99.75 87	99.83 21	99.59 116	99.62 47	98.21 163	99.73 92	99.79 156	98.68 67	99.96 40	98.44 216	99.77 132	99.79 88

DPE-MVS		99.46 39	99.32 51	99.91 5	99.78 65	99.88 9	99.36 280	99.51 144	98.73 97	99.88 39	99.84 92	98.72 64	99.96 40	98.16 243	99.87 74	99.88 34
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 52	99.29 63	99.80 60	99.62 166	99.55 91	99.50 191	99.70 15	98.79 90	99.77 80	99.96 1	97.45 121	99.96 40	98.92 142	99.90 56	99.89 28

HFP-MVS		99.49 30	99.37 41	99.86 31	99.87 17	99.80 34	99.66 78	99.67 23	98.15 170	99.68 106	99.69 214	99.06 16	99.96 40	98.69 179	99.87 74	99.84 52

region2R		99.48 34	99.35 45	99.87 20	99.88 13	99.80 34	99.65 84	99.66 28	98.13 177	99.66 117	99.68 222	98.96 25	99.96 40	98.62 188	99.87 74	99.84 52

HPM-MVS++		99.39 63	99.23 79	99.87 20	99.75 87	99.84 19	99.43 244	99.51 144	98.68 104	99.27 233	99.53 285	98.64 72	99.96 40	98.44 216	99.80 120	99.79 88

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 73	99.89 5	99.75 42	99.56 86	99.02 57	99.88 39	99.85 77	99.18 10	99.96 40	99.22 98	99.92 38	99.90 25
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 30	99.36 43	99.86 31	99.87 17	99.79 37	99.66 78	99.67 23	98.15 170	99.67 112	99.69 214	98.95 30	99.96 40	98.69 179	99.87 74	99.84 52

MP-MVS		99.33 74	99.15 89	99.87 20	99.88 13	99.82 27	99.66 78	99.46 224	98.09 185	99.48 172	99.74 186	98.29 96	99.96 40	97.93 265	99.87 74	99.82 68
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 129	98.90 148	99.74 75	99.80 59	99.46 109	99.59 116	99.49 179	97.03 321	99.63 134	99.69 214	97.27 130	99.96 40	97.82 276	99.84 97	99.81 75

PVSNet_Blended_VisFu		99.36 69	99.28 66	99.61 104	99.86 22	99.07 165	99.47 224	99.93 2	97.66 252	99.71 100	99.86 70	97.73 116	99.96 40	99.47 65	99.82 112	99.79 88

UGNet		98.87 169	98.69 181	99.40 168	99.22 311	98.72 225	99.44 238	99.68 20	99.24 29	99.18 258	99.42 319	92.74 332	99.96 40	99.34 80	99.94 30	99.53 212
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 76	99.32 51	99.32 184	99.85 28	98.29 263	99.71 57	99.66 28	98.11 181	99.41 192	99.80 139	98.37 93	99.96 40	98.99 128	99.96 16	99.72 127

ACMMP		99.45 43	99.32 51	99.82 53	99.89 8	99.67 63	99.62 102	99.69 18	98.12 179	99.63 134	99.84 92	98.73 63	99.96 40	98.55 206	99.83 108	99.81 75
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 21	99.44 28	99.85 39	99.51 216	99.67 63	99.50 191	99.64 38	99.43 16	99.98 12	99.78 163	97.26 132	99.95 75	99.95 15	99.93 32	99.92 23

fmvsm_s_conf0.5_n_4		99.36 69	99.24 75	99.73 78	99.78 65	99.53 96	99.49 208	99.60 63	99.42 19	99.99 2	99.86 70	95.15 237	99.95 75	99.95 15	99.89 67	99.73 118

fmvsm_s_conf0.1_n_2		99.37 65	99.22 80	99.81 56	99.77 73	99.75 47	99.46 228	99.60 63	99.47 4	99.98 12	99.94 6	94.98 241	99.95 75	99.97 2	99.79 127	99.73 118

test_fmvsmconf0.01_n		99.22 96	99.03 112	99.79 63	98.42 427	99.48 106	99.55 156	99.51 144	99.39 21	99.78 76	99.93 10	94.80 254	99.95 75	99.93 22	99.95 22	99.94 17

SR-MVS-dyc-post		99.45 43	99.31 57	99.85 39	99.76 77	99.82 27	99.63 97	99.52 125	98.38 132	99.76 86	99.82 106	98.53 79	99.95 75	98.61 191	99.81 115	99.77 96

GST-MVS		99.40 61	99.24 75	99.85 39	99.86 22	99.79 37	99.60 109	99.67 23	97.97 211	99.63 134	99.68 222	98.52 80	99.95 75	98.38 221	99.86 82	99.81 75

CANet		99.25 92	99.14 90	99.59 108	99.41 255	99.16 150	99.35 285	99.57 81	98.82 84	99.51 167	99.61 256	96.46 175	99.95 75	99.59 44	99.98 4	99.65 162

MP-MVS-pluss		99.37 65	99.20 83	99.88 14	99.90 4	99.87 16	99.30 299	99.52 125	97.18 303	99.60 146	99.79 156	98.79 50	99.95 75	98.83 162	99.91 45	99.83 62
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 52	99.27 70	99.88 14	99.89 8	99.80 34	99.67 71	99.50 167	98.70 101	99.77 80	99.49 299	98.21 99	99.95 75	98.46 214	99.77 132	99.88 34
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 75	96.67 363

APD-MVS_3200maxsize		99.48 34	99.35 45	99.85 39	99.76 77	99.83 21	99.63 97	99.54 104	98.36 136	99.79 71	99.82 106	98.86 41	99.95 75	98.62 188	99.81 115	99.78 94

RPMNet		96.72 373	95.90 386	99.19 209	99.18 320	98.49 252	99.22 337	99.52 125	88.72 453	99.56 154	97.38 450	94.08 297	99.95 75	86.87 458	98.58 256	99.14 279

sss		99.17 104	99.05 107	99.53 128	99.62 166	98.97 178	99.36 280	99.62 47	97.83 228	99.67 112	99.65 235	97.37 125	99.95 75	99.19 101	99.19 198	99.68 148

MVSMamba_PlusPlus		99.46 39	99.41 34	99.64 96	99.68 127	99.50 103	99.75 42	99.50 167	98.27 147	99.87 45	99.92 17	98.09 105	99.94 88	99.65 40	99.95 22	99.47 236

fmvsm_s_conf0.1_n_a		99.26 88	99.06 105	99.85 39	99.52 213	99.62 78	99.54 161	99.62 47	98.69 102	99.99 2	99.96 1	94.47 281	99.94 88	99.88 25	99.92 38	99.98 2

fmvsm_s_conf0.1_n		99.29 81	99.10 95	99.86 31	99.70 117	99.65 70	99.53 170	99.62 47	98.74 96	99.99 2	99.95 3	94.53 279	99.94 88	99.89 24	99.96 16	99.97 4

TSAR-MVS + MP.		99.58 14	99.50 17	99.81 56	99.91 1	99.66 66	99.63 97	99.39 270	98.91 77	99.78 76	99.85 77	99.36 2	99.94 88	98.84 159	99.88 71	99.82 68
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 164	98.75 173	99.39 173	99.46 240	98.61 237	99.76 37	99.50 167	98.06 194	99.81 64	99.88 51	93.91 305	99.94 88	99.11 113	99.27 189	99.61 179

mamv4		99.33 74	99.42 29	99.07 220	99.67 129	97.73 296	99.42 251	99.60 63	98.15 170	99.94 27	99.91 25	98.42 88	99.94 88	99.72 31	99.96 16	99.54 206

XVS		99.53 24	99.42 29	99.87 20	99.85 28	99.83 21	99.69 62	99.68 20	98.98 67	99.37 203	99.74 186	98.81 47	99.94 88	98.79 167	99.86 82	99.84 52

X-MVStestdata		96.55 376	95.45 395	99.87 20	99.85 28	99.83 21	99.69 62	99.68 20	98.98 67	99.37 203	64.01 473	98.81 47	99.94 88	98.79 167	99.86 82	99.84 52

旧先验2							98.96 396		96.70 341	99.47 173			99.94 88	98.19 239

新几何1				99.75 72	99.75 87	99.59 83		99.54 104	96.76 337	99.29 226	99.64 241	98.43 86	99.94 88	96.92 353	99.66 154	99.72 127

testdata				99.54 120	99.75 87	98.95 188		99.51 144	97.07 315	99.43 184	99.70 203	98.87 40	99.94 88	97.76 285	99.64 157	99.72 127

HPM-MVS		99.42 52	99.28 66	99.83 52	99.90 4	99.72 52	99.81 20	99.54 104	97.59 258	99.68 106	99.63 247	98.91 37	99.94 88	98.58 197	99.91 45	99.84 52
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 97	99.10 95	99.45 156	99.89 8	98.52 247	99.39 268	99.94 1	98.73 97	99.11 267	99.89 40	95.50 220	99.94 88	99.50 56	99.97 8	99.89 28

APD-MVS		99.27 85	99.08 101	99.84 51	99.75 87	99.79 37	99.50 191	99.50 167	97.16 305	99.77 80	99.82 106	98.78 51	99.94 88	97.56 306	99.86 82	99.80 84
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 34	99.42 29	99.65 90	99.72 106	99.40 116	99.05 373	99.66 28	99.14 35	99.57 153	99.80 139	98.46 84	99.94 88	99.57 47	99.84 97	99.60 182
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		99.06 142	98.88 155	99.61 104	99.62 166	99.16 150	99.37 275	99.56 86	98.04 203	99.53 163	99.62 252	96.84 155	99.94 88	98.85 156	98.49 264	99.72 127

DeepC-MVS	98.35 2	99.30 79	99.19 85	99.64 96	99.82 49	99.23 143	99.62 102	99.55 95	98.94 73	99.63 134	99.95 3	95.82 206	99.94 88	99.37 74	99.97 8	99.73 118
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 85	99.12 93	99.74 75	99.18 320	99.75 47	99.56 141	99.57 81	98.45 125	99.49 171	99.85 77	97.77 115	99.94 88	98.33 228	99.84 97	99.52 213

GDP-MVS		99.08 137	98.89 152	99.64 96	99.53 207	99.34 122	99.64 91	99.48 191	98.32 142	99.77 80	99.66 233	95.14 238	99.93 106	98.97 134	99.50 171	99.64 169

SDMVSNet		99.11 129	98.90 148	99.75 72	99.81 53	99.59 83	99.81 20	99.65 35	98.78 93	99.64 131	99.88 51	94.56 274	99.93 106	99.67 36	98.26 279	99.72 127

FE-MVS		98.48 212	98.17 227	99.40 168	99.54 206	98.96 182	99.68 68	98.81 404	95.54 400	99.62 138	99.70 203	93.82 308	99.93 106	97.35 324	99.46 173	99.32 265

SF-MVS		99.38 64	99.24 75	99.79 63	99.79 63	99.68 59	99.57 134	99.54 104	97.82 233	99.71 100	99.80 139	98.95 30	99.93 106	98.19 239	99.84 97	99.74 109

dcpmvs_2		99.23 94	99.58 7	98.16 348	99.83 44	94.68 418	99.76 37	99.52 125	99.07 53	99.98 12	99.88 51	98.56 77	99.93 106	99.67 36	99.98 4	99.87 39

Anonymous20240529		98.09 249	97.68 287	99.34 178	99.66 142	98.44 257	99.40 264	99.43 255	93.67 426	99.22 245	99.89 40	90.23 387	99.93 106	99.26 96	98.33 271	99.66 156

ACMMP_NAP		99.47 37	99.34 47	99.88 14	99.87 17	99.86 17	99.47 224	99.48 191	98.05 196	99.76 86	99.86 70	98.82 46	99.93 106	98.82 166	99.91 45	99.84 52

EI-MVSNet-UG-set		99.58 14	99.57 8	99.64 96	99.78 65	99.14 155	99.60 109	99.45 235	99.01 59	99.90 33	99.83 97	98.98 24	99.93 106	99.59 44	99.95 22	99.86 41

无先验							98.99 389	99.51 144	96.89 331				99.93 106	97.53 309		99.72 127

VDDNet		97.55 336	97.02 358	99.16 212	99.49 230	98.12 274	99.38 273	99.30 326	95.35 402	99.68 106	99.90 32	82.62 448	99.93 106	99.31 84	98.13 291	99.42 248

ab-mvs		98.86 172	98.63 191	99.54 120	99.64 154	99.19 145	99.44 238	99.54 104	97.77 237	99.30 223	99.81 121	94.20 291	99.93 106	99.17 107	98.82 243	99.49 227

F-COLMAP		99.19 97	99.04 109	99.64 96	99.78 65	99.27 138	99.42 251	99.54 104	97.29 294	99.41 192	99.59 261	98.42 88	99.93 106	98.19 239	99.69 148	99.73 118

BP-MVS1		99.12 123	98.94 140	99.65 90	99.51 216	99.30 133	99.67 71	98.92 385	98.48 121	99.84 52	99.69 214	94.96 242	99.92 118	99.62 43	99.79 127	99.71 136

Anonymous202405211		98.30 230	97.98 251	99.26 200	99.57 191	98.16 269	99.41 256	98.55 429	96.03 394	99.19 254	99.74 186	91.87 357	99.92 118	99.16 108	98.29 278	99.70 139

EI-MVSNet-Vis-set		99.58 14	99.56 10	99.64 96	99.78 65	99.15 154	99.61 108	99.45 235	99.01 59	99.89 36	99.82 106	99.01 18	99.92 118	99.56 48	99.95 22	99.85 45

VDD-MVS		97.73 315	97.35 332	98.88 256	99.47 238	97.12 324	99.34 288	98.85 399	98.19 165	99.67 112	99.85 77	82.98 446	99.92 118	99.49 60	98.32 275	99.60 182

VNet		99.11 129	98.90 148	99.73 78	99.52 213	99.56 89	99.41 256	99.39 270	99.01 59	99.74 90	99.78 163	95.56 218	99.92 118	99.52 54	98.18 287	99.72 127

XVG-OURS-SEG-HR		98.69 200	98.62 196	98.89 253	99.71 112	97.74 295	99.12 357	99.54 104	98.44 128	99.42 187	99.71 199	94.20 291	99.92 118	98.54 207	98.90 237	99.00 298

mvsmamba		99.06 142	98.96 134	99.36 175	99.47 238	98.64 232	99.70 58	99.05 369	97.61 257	99.65 126	99.83 97	96.54 171	99.92 118	99.19 101	99.62 160	99.51 222

HPM-MVS_fast		99.51 26	99.40 35	99.85 39	99.91 1	99.79 37	99.76 37	99.56 86	97.72 243	99.76 86	99.75 181	99.13 12	99.92 118	99.07 119	99.92 38	99.85 45

HY-MVS	97.30 7	98.85 181	98.64 190	99.47 153	99.42 250	99.08 163	99.62 102	99.36 287	97.39 286	99.28 227	99.68 222	96.44 177	99.92 118	98.37 223	98.22 282	99.40 253

DP-MVS		99.16 106	98.95 138	99.78 66	99.77 73	99.53 96	99.41 256	99.50 167	97.03 321	99.04 284	99.88 51	97.39 122	99.92 118	98.66 183	99.90 56	99.87 39

IB-MVS	95.67 18	96.22 382	95.44 396	98.57 298	99.21 312	96.70 358	98.65 430	97.74 448	96.71 340	97.27 412	98.54 424	86.03 429	99.92 118	98.47 213	86.30 454	99.10 282
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 30	99.39 37	99.77 69	99.63 158	99.59 83	99.36 280	99.46 224	99.07 53	99.79 71	99.82 106	98.85 42	99.92 118	98.68 181	99.87 74	99.82 68
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LuminaMVS		99.23 94	99.10 95	99.61 104	99.35 272	99.31 130	99.46 228	99.13 357	98.61 108	99.86 49	99.89 40	96.41 180	99.91 130	99.67 36	99.51 169	99.63 174

balanced_conf03		99.46 39	99.39 37	99.67 85	99.55 199	99.58 88	99.74 47	99.51 144	98.42 129	99.87 45	99.84 92	98.05 108	99.91 130	99.58 46	99.94 30	99.52 213

9.14			99.10 95		99.72 106		99.40 264	99.51 144	97.53 268	99.64 131	99.78 163	98.84 44	99.91 130	97.63 297	99.82 112

SMA-MVS		99.44 47	99.30 59	99.85 39	99.73 102	99.83 21	99.56 141	99.47 213	97.45 277	99.78 76	99.82 106	99.18 10	99.91 130	98.79 167	99.89 67	99.81 75
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					99.67 129	99.65 70	99.05 373	99.41 260	96.22 379	98.95 300	99.49 299	98.77 54	99.91 130

train_agg		99.02 150	98.77 171	99.77 69	99.67 129	99.65 70	99.05 373	99.41 260	96.28 373	98.95 300	99.49 299	98.76 55	99.91 130	97.63 297	99.72 143	99.75 105

test_8					99.67 129	99.61 80	99.03 378	99.41 260	96.28 373	98.93 303	99.48 305	98.76 55	99.91 130

agg_prior					99.67 129	99.62 78		99.40 267		98.87 313			99.91 130

原ACMM1				99.65 90	99.73 102	99.33 125		99.47 213	97.46 274	99.12 265	99.66 233	98.67 69	99.91 130	97.70 294	99.69 148	99.71 136

LFMVS		97.90 282	97.35 332	99.54 120	99.52 213	99.01 172	99.39 268	98.24 437	97.10 313	99.65 126	99.79 156	84.79 438	99.91 130	99.28 90	98.38 268	99.69 142

XVG-OURS		98.73 198	98.68 182	98.88 256	99.70 117	97.73 296	98.92 403	99.55 95	98.52 117	99.45 176	99.84 92	95.27 230	99.91 130	98.08 254	98.84 241	99.00 298

PLC	97.94 4	99.02 150	98.85 162	99.53 128	99.66 142	99.01 172	99.24 330	99.52 125	96.85 333	99.27 233	99.48 305	98.25 98	99.91 130	97.76 285	99.62 160	99.65 162
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 329	97.06 357	99.47 153	99.61 176	99.09 160	98.04 456	99.25 338	91.24 444	98.51 362	99.70 203	94.55 276	99.91 130	92.76 433	99.85 89	99.42 248
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Elysia		98.88 166	98.65 188	99.58 111	99.58 186	99.34 122	99.65 84	99.52 125	98.26 150	99.83 60	99.87 62	93.37 316	99.90 143	97.81 278	99.91 45	99.49 227

StellarMVS		98.88 166	98.65 188	99.58 111	99.58 186	99.34 122	99.65 84	99.52 125	98.26 150	99.83 60	99.87 62	93.37 316	99.90 143	97.81 278	99.91 45	99.49 227

AstraMVS		99.09 135	99.03 112	99.25 201	99.66 142	98.13 272	99.57 134	98.24 437	98.82 84	99.91 30	99.88 51	95.81 207	99.90 143	99.72 31	99.67 153	99.74 109

mmtdpeth		96.95 368	96.71 367	97.67 387	99.33 278	94.90 413	99.89 2	99.28 332	98.15 170	99.72 97	98.57 423	86.56 426	99.90 143	99.82 28	89.02 449	98.20 418

UWE-MVS		97.58 335	97.29 343	98.48 311	99.09 344	96.25 378	99.01 386	96.61 460	97.86 221	99.19 254	99.01 394	88.72 402	99.90 143	97.38 322	98.69 250	99.28 268

test_vis1_rt		95.81 392	95.65 391	96.32 421	99.67 129	91.35 449	99.49 208	96.74 458	98.25 155	95.24 436	98.10 442	74.96 458	99.90 143	99.53 52	98.85 240	97.70 442

FA-MVS(test-final)		98.75 195	98.53 207	99.41 167	99.55 199	99.05 168	99.80 25	99.01 374	96.59 355	99.58 150	99.59 261	95.39 224	99.90 143	97.78 281	99.49 172	99.28 268

MCST-MVS		99.43 50	99.30 59	99.82 53	99.79 63	99.74 50	99.29 304	99.40 267	98.79 90	99.52 165	99.62 252	98.91 37	99.90 143	98.64 185	99.75 137	99.82 68

CDPH-MVS		99.13 116	98.91 146	99.80 60	99.75 87	99.71 54	99.15 351	99.41 260	96.60 353	99.60 146	99.55 276	98.83 45	99.90 143	97.48 313	99.83 108	99.78 94

NCCC		99.34 72	99.19 85	99.79 63	99.61 176	99.65 70	99.30 299	99.48 191	98.86 79	99.21 248	99.63 247	98.72 64	99.90 143	98.25 235	99.63 159	99.80 84

114514_t		98.93 162	98.67 183	99.72 81	99.85 28	99.53 96	99.62 102	99.59 69	92.65 439	99.71 100	99.78 163	98.06 107	99.90 143	98.84 159	99.91 45	99.74 109

1112_ss		98.98 158	98.77 171	99.59 108	99.68 127	99.02 170	99.25 325	99.48 191	97.23 300	99.13 263	99.58 265	96.93 149	99.90 143	98.87 149	98.78 246	99.84 52

PHI-MVS		99.30 79	99.17 88	99.70 82	99.56 195	99.52 100	99.58 126	99.80 8	97.12 309	99.62 138	99.73 192	98.58 75	99.90 143	98.61 191	99.91 45	99.68 148

AdaColmap		99.01 154	98.80 167	99.66 86	99.56 195	99.54 93	99.18 346	99.70 15	98.18 168	99.35 212	99.63 247	96.32 182	99.90 143	97.48 313	99.77 132	99.55 204

COLMAP_ROB	97.56 6	98.86 172	98.75 173	99.17 211	99.88 13	98.53 243	99.34 288	99.59 69	97.55 264	98.70 339	99.89 40	95.83 205	99.90 143	98.10 249	99.90 56	99.08 287
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 226	98.03 246	99.31 186	99.63 158	98.56 240	99.54 161	96.75 457	97.53 268	99.73 92	99.65 235	91.25 375	99.89 158	98.62 188	99.56 165	99.48 230

tttt0517		98.42 217	98.14 231	99.28 198	99.66 142	98.38 261	99.74 47	96.85 455	97.68 249	99.79 71	99.74 186	91.39 371	99.89 158	98.83 162	99.56 165	99.57 200

test12				99.75 72	99.64 154	99.61 80		99.29 330		99.21 248		98.38 92	99.89 158		99.74 140	99.74 109

Test_1112_low_res		98.89 165	98.66 186	99.57 115	99.69 122	98.95 188	99.03 378	99.47 213	96.98 323	99.15 261	99.23 370	96.77 160	99.89 158	98.83 162	98.78 246	99.86 41

CNLPA		99.14 114	98.99 126	99.59 108	99.58 186	99.41 115	99.16 348	99.44 244	98.45 125	99.19 254	99.49 299	98.08 106	99.89 158	97.73 289	99.75 137	99.48 230

diffmvs_AUTHOR		99.19 97	99.10 95	99.48 148	99.64 154	98.85 207	99.32 293	99.48 191	98.50 119	99.81 64	99.81 121	96.82 156	99.88 163	99.40 70	99.12 208	99.71 136

guyue		99.16 106	99.04 109	99.52 134	99.69 122	98.92 196	99.59 116	98.81 404	98.73 97	99.90 33	99.87 62	95.34 227	99.88 163	99.66 39	99.81 115	99.74 109

sd_testset		98.75 195	98.57 203	99.29 194	99.81 53	98.26 265	99.56 141	99.62 47	98.78 93	99.64 131	99.88 51	92.02 354	99.88 163	99.54 50	98.26 279	99.72 127

APD_test1		95.87 390	96.49 372	94.00 429	99.53 207	84.01 458	99.54 161	99.32 317	95.91 396	97.99 391	99.85 77	85.49 433	99.88 163	91.96 436	98.84 241	98.12 422

diffmvs		99.14 114	99.02 118	99.51 139	99.61 176	98.96 182	99.28 309	99.49 179	98.46 123	99.72 97	99.71 199	96.50 173	99.88 163	99.31 84	99.11 210	99.67 152
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		98.86 172	98.80 167	99.03 226	99.76 77	98.79 218	99.28 309	99.91 3	97.42 283	99.67 112	99.37 337	97.53 119	99.88 163	98.98 129	97.29 339	98.42 403

PVSNet_Blended		99.08 137	98.97 130	99.42 166	99.76 77	98.79 218	98.78 417	99.91 3	96.74 338	99.67 112	99.49 299	97.53 119	99.88 163	98.98 129	99.85 89	99.60 182

viewdifsd2359ckpt07		99.11 129	99.00 125	99.43 164	99.63 158	98.73 223	99.45 231	99.54 104	98.33 140	99.62 138	99.81 121	96.17 187	99.87 170	99.27 93	99.14 203	99.69 142

viewdifsd2359ckpt11		98.78 190	98.74 175	98.89 253	99.67 129	97.04 334	99.50 191	99.58 74	98.26 150	99.56 154	99.90 32	94.36 284	99.87 170	99.49 60	98.32 275	99.77 96

viewmsd2359difaftdt		98.78 190	98.74 175	98.90 249	99.67 129	97.04 334	99.50 191	99.58 74	98.26 150	99.56 154	99.90 32	94.36 284	99.87 170	99.49 60	98.32 275	99.77 96

MVS		97.28 357	96.55 370	99.48 148	98.78 394	98.95 188	99.27 314	99.39 270	83.53 460	98.08 386	99.54 281	96.97 147	99.87 170	94.23 414	99.16 199	99.63 174

MG-MVS		99.13 116	99.02 118	99.45 156	99.57 191	98.63 233	99.07 367	99.34 299	98.99 64	99.61 143	99.82 106	97.98 110	99.87 170	97.00 344	99.80 120	99.85 45

MSDG		98.98 158	98.80 167	99.53 128	99.76 77	99.19 145	98.75 420	99.55 95	97.25 297	99.47 173	99.77 172	97.82 113	99.87 170	96.93 351	99.90 56	99.54 206

ETV-MVS		99.26 88	99.21 81	99.40 168	99.46 240	99.30 133	99.56 141	99.52 125	98.52 117	99.44 181	99.27 365	98.41 90	99.86 176	99.10 116	99.59 163	99.04 294

thisisatest0515		98.14 244	97.79 270	99.19 209	99.50 228	98.50 251	98.61 432	96.82 456	96.95 327	99.54 161	99.43 317	91.66 366	99.86 176	98.08 254	99.51 169	99.22 276

thres600view7		97.86 288	97.51 306	98.92 243	99.72 106	97.95 286	99.59 116	98.74 414	97.94 213	99.27 233	98.62 420	91.75 360	99.86 176	93.73 420	98.19 286	98.96 304

lupinMVS		99.13 116	99.01 123	99.46 155	99.51 216	98.94 192	99.05 373	99.16 353	97.86 221	99.80 69	99.56 273	97.39 122	99.86 176	98.94 137	99.85 89	99.58 197

PVSNet	96.02 17	98.85 181	98.84 164	98.89 253	99.73 102	97.28 315	98.32 448	99.60 63	97.86 221	99.50 168	99.57 270	96.75 161	99.86 176	98.56 203	99.70 147	99.54 206

MAR-MVS		98.86 172	98.63 191	99.54 120	99.37 268	99.66 66	99.45 231	99.54 104	96.61 350	99.01 287	99.40 327	97.09 139	99.86 176	97.68 296	99.53 168	99.10 282
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
mamba_0408		99.08 137	98.96 134	99.44 161	99.62 166	98.88 199	99.25 325	99.47 213	98.05 196	99.37 203	99.81 121	96.85 151	99.85 182	98.98 129	99.25 192	99.60 182

SSM_0404		99.16 106	99.06 105	99.44 161	99.65 150	98.96 182	99.49 208	99.50 167	98.14 175	99.62 138	99.85 77	96.85 151	99.85 182	99.19 101	99.26 191	99.52 213

testing91		97.44 349	97.02 358	98.71 285	99.18 320	96.89 352	99.19 344	99.04 370	97.78 236	98.31 373	98.29 434	85.41 434	99.85 182	98.01 260	97.95 296	99.39 254

test2506		96.81 372	96.65 368	97.29 402	99.74 95	92.21 446	99.60 109	85.06 477	99.13 36	99.77 80	99.93 10	87.82 419	99.85 182	99.38 73	99.38 178	99.80 84

AllTest		98.87 169	98.72 177	99.31 186	99.86 22	98.48 254	99.56 141	99.61 56	97.85 224	99.36 209	99.85 77	95.95 197	99.85 182	96.66 364	99.83 108	99.59 193

TestCases				99.31 186	99.86 22	98.48 254		99.61 56	97.85 224	99.36 209	99.85 77	95.95 197	99.85 182	96.66 364	99.83 108	99.59 193

jason		99.13 116	99.03 112	99.45 156	99.46 240	98.87 203	99.12 357	99.26 336	98.03 205	99.79 71	99.65 235	97.02 144	99.85 182	99.02 126	99.90 56	99.65 162
jason: jason.
CNVR-MVS		99.42 52	99.30 59	99.78 66	99.62 166	99.71 54	99.26 323	99.52 125	98.82 84	99.39 199	99.71 199	98.96 25	99.85 182	98.59 196	99.80 120	99.77 96

PAPM_NR		99.04 147	98.84 164	99.66 86	99.74 95	99.44 111	99.39 268	99.38 278	97.70 247	99.28 227	99.28 362	98.34 94	99.85 182	96.96 348	99.45 174	99.69 142

viewcassd2359sk11		99.18 100	99.08 101	99.49 147	99.65 150	98.95 188	99.48 214	99.51 144	98.10 184	99.72 97	99.87 62	97.13 135	99.84 191	99.13 110	99.14 203	99.69 142

testing99		97.36 352	96.94 361	98.63 291	99.18 320	96.70 358	99.30 299	98.93 382	97.71 244	98.23 378	98.26 435	84.92 437	99.84 191	98.04 259	97.85 303	99.35 260

testing222		97.16 362	96.50 371	99.16 212	99.16 330	98.47 256	99.27 314	98.66 425	97.71 244	98.23 378	98.15 438	82.28 451	99.84 191	97.36 323	97.66 309	99.18 278

test1111		98.04 259	98.11 235	97.83 377	99.74 95	93.82 430	99.58 126	95.40 464	99.12 41	99.65 126	99.93 10	90.73 380	99.84 191	99.43 68	99.38 178	99.82 68

ECVR-MVS		98.04 259	98.05 244	98.00 361	99.74 95	94.37 425	99.59 116	94.98 465	99.13 36	99.66 117	99.93 10	90.67 381	99.84 191	99.40 70	99.38 178	99.80 84

test_yl		98.86 172	98.63 191	99.54 120	99.49 230	99.18 147	99.50 191	99.07 366	98.22 161	99.61 143	99.51 293	95.37 225	99.84 191	98.60 194	98.33 271	99.59 193

DCV-MVSNet		98.86 172	98.63 191	99.54 120	99.49 230	99.18 147	99.50 191	99.07 366	98.22 161	99.61 143	99.51 293	95.37 225	99.84 191	98.60 194	98.33 271	99.59 193

Fast-Effi-MVS+		98.70 199	98.43 212	99.51 139	99.51 216	99.28 136	99.52 172	99.47 213	96.11 389	99.01 287	99.34 347	96.20 186	99.84 191	97.88 268	98.82 243	99.39 254

TSAR-MVS + GP.		99.36 69	99.36 43	99.36 175	99.67 129	98.61 237	99.07 367	99.33 307	99.00 62	99.82 63	99.81 121	99.06 16	99.84 191	99.09 117	99.42 176	99.65 162

tpmrst		98.33 227	98.48 210	97.90 370	99.16 330	94.78 414	99.31 297	99.11 359	97.27 295	99.45 176	99.59 261	95.33 228	99.84 191	98.48 210	98.61 253	99.09 286

Vis-MVSNet		99.12 123	98.97 130	99.56 117	99.78 65	99.10 159	99.68 68	99.66 28	98.49 120	99.86 49	99.87 62	94.77 259	99.84 191	99.19 101	99.41 177	99.74 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 207	98.34 218	99.51 139	99.40 260	99.03 169	98.80 415	99.36 287	96.33 370	99.00 291	99.12 384	98.46 84	99.84 191	95.23 400	99.37 185	99.66 156

PatchMatch-RL		98.84 184	98.62 196	99.52 134	99.71 112	99.28 136	99.06 371	99.77 9	97.74 242	99.50 168	99.53 285	95.41 223	99.84 191	97.17 337	99.64 157	99.44 246

EPP-MVSNet		99.13 116	98.99 126	99.53 128	99.65 150	99.06 166	99.81 20	99.33 307	97.43 281	99.60 146	99.88 51	97.14 134	99.84 191	99.13 110	98.94 228	99.69 142

SSM_0407		99.13 116	99.03 112	99.43 164	99.62 166	98.88 199	99.51 181	99.50 167	98.14 175	99.37 203	99.85 77	96.85 151	99.83 205	99.19 101	99.25 192	99.60 182

testing3-2		97.84 293	97.70 285	98.24 343	99.53 207	95.37 402	99.55 156	98.67 424	98.46 123	99.27 233	99.34 347	86.58 425	99.83 205	99.32 83	98.63 252	99.52 213

testing11		97.50 342	97.10 355	98.71 285	99.20 314	96.91 350	99.29 304	98.82 402	97.89 218	98.21 381	98.40 429	85.63 432	99.83 205	98.45 215	98.04 294	99.37 258

thres100view900		97.76 307	97.45 315	98.69 287	99.72 106	97.86 292	99.59 116	98.74 414	97.93 214	99.26 238	98.62 420	91.75 360	99.83 205	93.22 425	98.18 287	98.37 409

tfpn200view9		97.72 317	97.38 328	98.72 282	99.69 122	97.96 283	99.50 191	98.73 420	97.83 228	99.17 259	98.45 427	91.67 364	99.83 205	93.22 425	98.18 287	98.37 409

test_prior				99.68 84	99.67 129	99.48 106		99.56 86					99.83 205			99.74 109

1314		98.68 201	98.54 206	99.11 218	98.89 377	98.65 230	99.27 314	99.49 179	96.89 331	97.99 391	99.56 273	97.72 117	99.83 205	97.74 288	99.27 189	98.84 310

thres400		97.77 306	97.38 328	98.92 243	99.69 122	97.96 283	99.50 191	98.73 420	97.83 228	99.17 259	98.45 427	91.67 364	99.83 205	93.22 425	98.18 287	98.96 304

casdiffmvs		99.13 116	98.98 129	99.56 117	99.65 150	99.16 150	99.56 141	99.50 167	98.33 140	99.41 192	99.86 70	95.92 200	99.83 205	99.45 67	99.16 199	99.70 139
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 30	99.48 20	99.54 120	99.78 65	99.30 133	99.89 2	99.58 74	98.56 113	99.73 92	99.69 214	98.55 78	99.82 214	99.69 34	99.85 89	99.48 230

MVS_Test		99.10 134	98.97 130	99.48 148	99.49 230	99.14 155	99.67 71	99.34 299	97.31 292	99.58 150	99.76 176	97.65 118	99.82 214	98.87 149	99.07 219	99.46 241

dp		97.75 311	97.80 269	97.59 393	99.10 341	93.71 433	99.32 293	98.88 395	96.48 362	99.08 275	99.55 276	92.67 338	99.82 214	96.52 368	98.58 256	99.24 274

RPSCF		98.22 234	98.62 196	96.99 408	99.82 49	91.58 448	99.72 53	99.44 244	96.61 350	99.66 117	99.89 40	95.92 200	99.82 214	97.46 316	99.10 216	99.57 200

PMMVS		98.80 188	98.62 196	99.34 178	99.27 296	98.70 226	98.76 419	99.31 321	97.34 289	99.21 248	99.07 386	97.20 133	99.82 214	98.56 203	98.87 238	99.52 213

UBG		97.85 289	97.48 309	98.95 237	99.25 303	97.64 303	99.24 330	98.74 414	97.90 217	98.64 349	98.20 437	88.65 406	99.81 219	98.27 233	98.40 266	99.42 248

EIA-MVS		99.18 100	99.09 100	99.45 156	99.49 230	99.18 147	99.67 71	99.53 120	97.66 252	99.40 197	99.44 315	98.10 104	99.81 219	98.94 137	99.62 160	99.35 260

Effi-MVS+		98.81 185	98.59 202	99.48 148	99.46 240	99.12 158	98.08 455	99.50 167	97.50 272	99.38 201	99.41 323	96.37 181	99.81 219	99.11 113	98.54 261	99.51 222

thres200		97.61 333	97.28 344	98.62 292	99.64 154	98.03 277	99.26 323	98.74 414	97.68 249	99.09 273	98.32 433	91.66 366	99.81 219	92.88 430	98.22 282	98.03 428

tpmvs		97.98 270	98.02 248	97.84 376	99.04 355	94.73 415	99.31 297	99.20 348	96.10 393	98.76 329	99.42 319	94.94 244	99.81 219	96.97 347	98.45 265	98.97 302

casdiffmvs_mvg		99.15 110	99.02 118	99.55 119	99.66 142	99.09 160	99.64 91	99.56 86	98.26 150	99.45 176	99.87 62	96.03 193	99.81 219	99.54 50	99.15 202	99.73 118
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	98.81 185	99.37 41	97.12 406	99.60 182	91.75 447	98.61 432	99.44 244	99.35 24	99.83 60	99.85 77	98.70 66	99.81 219	99.02 126	99.91 45	99.81 75

viewmacassd2359aftdt		99.08 137	98.94 140	99.50 144	99.66 142	98.96 182	99.51 181	99.54 104	98.27 147	99.42 187	99.89 40	95.88 204	99.80 226	99.20 100	99.11 210	99.76 103

viewmanbaseed2359cas		99.18 100	99.07 104	99.50 144	99.62 166	99.01 172	99.50 191	99.52 125	98.25 155	99.68 106	99.82 106	96.93 149	99.80 226	99.15 109	99.11 210	99.70 139

IMVS_0403		98.86 172	98.89 152	98.78 277	99.55 199	96.93 345	99.58 126	99.44 244	98.05 196	99.68 106	99.80 139	96.81 157	99.80 226	98.15 245	98.92 231	99.60 182

DPM-MVS		98.95 161	98.71 179	99.66 86	99.63 158	99.55 91	98.64 431	99.10 360	97.93 214	99.42 187	99.55 276	98.67 69	99.80 226	95.80 385	99.68 151	99.61 179

DP-MVS Recon		99.12 123	98.95 138	99.65 90	99.74 95	99.70 56	99.27 314	99.57 81	96.40 369	99.42 187	99.68 222	98.75 58	99.80 226	97.98 262	99.72 143	99.44 246

MVS_111021_LR		99.41 56	99.33 49	99.65 90	99.77 73	99.51 102	98.94 401	99.85 6	98.82 84	99.65 126	99.74 186	98.51 81	99.80 226	98.83 162	99.89 67	99.64 169

viewmambaseed2359dif		99.01 154	98.90 148	99.32 184	99.58 186	98.51 249	99.33 290	99.54 104	97.85 224	99.44 181	99.85 77	96.01 194	99.79 232	99.41 69	99.13 206	99.67 152

CS-MVS		99.50 28	99.48 20	99.54 120	99.76 77	99.42 113	99.90 1	99.55 95	98.56 113	99.78 76	99.70 203	98.65 71	99.79 232	99.65 40	99.78 129	99.41 251

Fast-Effi-MVS+-dtu		98.77 194	98.83 166	98.60 293	99.41 255	96.99 340	99.52 172	99.49 179	98.11 181	99.24 240	99.34 347	96.96 148	99.79 232	97.95 264	99.45 174	99.02 297

baseline1		98.31 228	97.95 255	99.38 174	99.50 228	98.74 222	99.59 116	98.93 382	98.41 130	99.14 262	99.60 259	94.59 272	99.79 232	98.48 210	93.29 422	99.61 179

baseline		99.15 110	99.02 118	99.53 128	99.66 142	99.14 155	99.72 53	99.48 191	98.35 137	99.42 187	99.84 92	96.07 190	99.79 232	99.51 55	99.14 203	99.67 152

PVSNet_0	94.43 19	96.09 387	95.47 394	97.94 366	99.31 286	94.34 427	97.81 457	99.70 15	97.12 309	97.46 406	98.75 417	89.71 392	99.79 232	97.69 295	81.69 460	99.68 148

API-MVS		99.04 147	99.03 112	99.06 222	99.40 260	99.31 130	99.55 156	99.56 86	98.54 115	99.33 217	99.39 331	98.76 55	99.78 238	96.98 346	99.78 129	98.07 425

OMC-MVS		99.08 137	99.04 109	99.20 208	99.67 129	98.22 267	99.28 309	99.52 125	98.07 190	99.66 117	99.81 121	97.79 114	99.78 238	97.79 280	99.81 115	99.60 182

GeoE		98.85 181	98.62 196	99.53 128	99.61 176	99.08 163	99.80 25	99.51 144	97.10 313	99.31 219	99.78 163	95.23 235	99.77 240	98.21 237	99.03 222	99.75 105

alignmvs		98.81 185	98.56 205	99.58 111	99.43 248	99.42 113	99.51 181	98.96 380	98.61 108	99.35 212	98.92 407	94.78 256	99.77 240	99.35 75	98.11 292	99.54 206

tpm cat1		97.39 351	97.36 330	97.50 396	99.17 328	93.73 432	99.43 244	99.31 321	91.27 443	98.71 333	99.08 385	94.31 289	99.77 240	96.41 373	98.50 263	99.00 298

CostFormer		97.72 317	97.73 282	97.71 385	99.15 334	94.02 429	99.54 161	99.02 373	94.67 417	99.04 284	99.35 343	92.35 350	99.77 240	98.50 209	97.94 297	99.34 263

MGCFI-Net		99.01 154	98.85 162	99.50 144	99.42 250	99.26 139	99.82 16	99.48 191	98.60 110	99.28 227	98.81 412	97.04 143	99.76 244	99.29 89	97.87 301	99.47 236

test_241102_ONE					99.84 35	99.90 2		99.48 191	99.07 53	99.91 30	99.74 186	99.20 7	99.76 244

MDTV_nov1_ep13			98.32 220		99.11 338	94.44 423	99.27 314	98.74 414	97.51 271	99.40 197	99.62 252	94.78 256	99.76 244	97.59 300	98.81 245

viewdifsd2359ckpt09		99.01 154	98.87 156	99.40 168	99.62 166	98.79 218	99.44 238	99.51 144	97.76 238	99.35 212	99.69 214	96.42 179	99.75 247	98.97 134	99.11 210	99.66 156

sasdasda		99.02 150	98.86 159	99.51 139	99.42 250	99.32 126	99.80 25	99.48 191	98.63 105	99.31 219	98.81 412	97.09 139	99.75 247	99.27 93	97.90 298	99.47 236

canonicalmvs		99.02 150	98.86 159	99.51 139	99.42 250	99.32 126	99.80 25	99.48 191	98.63 105	99.31 219	98.81 412	97.09 139	99.75 247	99.27 93	97.90 298	99.47 236

Effi-MVS+-dtu		98.78 190	98.89 152	98.47 316	99.33 278	96.91 350	99.57 134	99.30 326	98.47 122	99.41 192	98.99 397	96.78 159	99.74 250	98.73 173	99.38 178	98.74 326

patchmatchnet-post											98.70 418	94.79 255	99.74 250

SCA		98.19 238	98.16 228	98.27 342	99.30 287	95.55 393	99.07 367	98.97 378	97.57 261	99.43 184	99.57 270	92.72 333	99.74 250	97.58 301	99.20 197	99.52 213

BH-untuned		98.42 217	98.36 216	98.59 294	99.49 230	96.70 358	99.27 314	99.13 357	97.24 299	98.80 324	99.38 334	95.75 211	99.74 250	97.07 342	99.16 199	99.33 264

BH-RMVSNet		98.41 219	98.08 240	99.40 168	99.41 255	98.83 212	99.30 299	98.77 410	97.70 247	98.94 302	99.65 235	92.91 328	99.74 250	96.52 368	99.55 167	99.64 169

MVS_111021_HR		99.41 56	99.32 51	99.66 86	99.72 106	99.47 108	98.95 399	99.85 6	98.82 84	99.54 161	99.73 192	98.51 81	99.74 250	98.91 143	99.88 71	99.77 96

test_post											65.99 471	94.65 270	99.73 256

XVG-ACMP-BASELINE		97.83 296	97.71 284	98.20 345	99.11 338	96.33 374	99.41 256	99.52 125	98.06 194	99.05 283	99.50 296	89.64 394	99.73 256	97.73 289	97.38 336	98.53 391

HyFIR lowres test		99.11 129	98.92 143	99.65 90	99.90 4	99.37 118	99.02 381	99.91 3	97.67 251	99.59 149	99.75 181	95.90 202	99.73 256	99.53 52	99.02 224	99.86 41

DeepMVS_CX				93.34 432	99.29 291	82.27 461		99.22 344	85.15 458	96.33 428	99.05 389	90.97 378	99.73 256	93.57 422	97.77 306	98.01 429

Patchmatch-test		97.93 276	97.65 290	98.77 278	99.18 320	97.07 329	99.03 378	99.14 356	96.16 384	98.74 330	99.57 270	94.56 274	99.72 260	93.36 424	99.11 210	99.52 213

LPG-MVS_test		98.22 234	98.13 233	98.49 309	99.33 278	97.05 331	99.58 126	99.55 95	97.46 274	99.24 240	99.83 97	92.58 340	99.72 260	98.09 250	97.51 322	98.68 344

LGP-MVS_train				98.49 309	99.33 278	97.05 331		99.55 95	97.46 274	99.24 240	99.83 97	92.58 340	99.72 260	98.09 250	97.51 322	98.68 344

BH-w/o		98.00 268	97.89 264	98.32 334	99.35 272	96.20 380	99.01 386	98.90 392	96.42 367	98.38 369	99.00 395	95.26 232	99.72 260	96.06 378	98.61 253	99.03 295

ACMP	97.20 11	98.06 253	97.94 257	98.45 319	99.37 268	97.01 338	99.44 238	99.49 179	97.54 267	98.45 366	99.79 156	91.95 356	99.72 260	97.91 266	97.49 327	98.62 374
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 263	97.90 260	98.40 327	99.23 307	96.80 356	99.70 58	99.60 63	97.12 309	98.18 383	99.70 203	91.73 362	99.72 260	98.39 220	97.45 329	98.68 344
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
viewdifsd2359ckpt13		99.06 142	98.93 142	99.45 156	99.63 158	98.96 182	99.50 191	99.51 144	97.83 228	99.28 227	99.80 139	96.68 165	99.71 266	99.05 121	99.12 208	99.68 148

test_post1							99.23 333				65.14 472	94.18 294	99.71 266	97.58 301

ADS-MVSNet		98.20 237	98.08 240	98.56 302	99.33 278	96.48 369	99.23 333	99.15 354	96.24 377	99.10 270	99.67 228	94.11 295	99.71 266	96.81 356	99.05 220	99.48 230

JIA-IIPM		97.50 342	97.02 358	98.93 241	98.73 403	97.80 294	99.30 299	98.97 378	91.73 442	98.91 305	94.86 460	95.10 239	99.71 266	97.58 301	97.98 295	99.28 268

EPMVS		97.82 299	97.65 290	98.35 331	98.88 378	95.98 384	99.49 208	94.71 467	97.57 261	99.26 238	99.48 305	92.46 347	99.71 266	97.87 270	99.08 218	99.35 260

TDRefinement		95.42 398	94.57 406	97.97 363	89.83 470	96.11 383	99.48 214	98.75 411	96.74 338	96.68 425	99.88 51	88.65 406	99.71 266	98.37 223	82.74 459	98.09 424

ACMM	97.58 5	98.37 225	98.34 218	98.48 311	99.41 255	97.10 325	99.56 141	99.45 235	98.53 116	99.04 284	99.85 77	93.00 324	99.71 266	98.74 171	97.45 329	98.64 365
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 273	97.77 275	98.57 298	99.59 184	96.61 365	99.45 231	99.08 363	98.21 163	98.88 310	99.80 139	88.66 405	99.70 273	98.58 197	97.72 307	99.39 254

CHOSEN 280x420		99.12 123	99.13 91	99.08 219	99.66 142	97.89 289	98.43 442	99.71 13	98.88 78	99.62 138	99.76 176	96.63 166	99.70 273	99.46 66	99.99 1	99.66 156

EC-MVSNet		99.44 47	99.39 37	99.58 111	99.56 195	99.49 104	99.88 4	99.58 74	98.38 132	99.73 92	99.69 214	98.20 100	99.70 273	99.64 42	99.82 112	99.54 206

PatchmatchNet		98.31 228	98.36 216	98.19 346	99.16 330	95.32 403	99.27 314	98.92 385	97.37 287	99.37 203	99.58 265	94.90 249	99.70 273	97.43 319	99.21 196	99.54 206
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 248	97.99 250	98.44 322	99.41 255	96.96 344	99.60 109	99.56 86	98.09 185	98.15 384	99.91 25	90.87 379	99.70 273	98.88 146	97.45 329	98.67 352
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 342	96.90 362	99.29 194	99.23 307	98.78 221	99.32 293	98.90 392	97.52 270	98.56 359	98.09 443	84.72 439	99.69 278	97.86 271	97.88 300	99.39 254

HQP_MVS		98.27 233	98.22 226	98.44 322	99.29 291	96.97 342	99.39 268	99.47 213	98.97 70	99.11 267	99.61 256	92.71 335	99.69 278	97.78 281	97.63 310	98.67 352

plane_prior5								99.47 213					99.69 278	97.78 281	97.63 310	98.67 352

D2MVS		98.41 219	98.50 209	98.15 351	99.26 299	96.62 364	99.40 264	99.61 56	97.71 244	98.98 294	99.36 340	96.04 192	99.67 281	98.70 176	97.41 334	98.15 421

IS-MVSNet		99.05 146	98.87 156	99.57 115	99.73 102	99.32 126	99.75 42	99.20 348	98.02 208	99.56 154	99.86 70	96.54 171	99.67 281	98.09 250	99.13 206	99.73 118

CLD-MVS		98.16 242	98.10 236	98.33 332	99.29 291	96.82 355	98.75 420	99.44 244	97.83 228	99.13 263	99.55 276	92.92 326	99.67 281	98.32 230	97.69 308	98.48 395
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 359	97.30 341	97.09 407	99.43 248	93.31 439	99.73 51	98.87 397	98.83 83	99.28 227	99.80 139	84.45 440	99.66 284	97.88 268	97.45 329	98.30 411

AUN-MVS		96.88 370	96.31 376	98.59 294	99.48 237	97.04 334	99.27 314	99.22 344	97.44 280	98.51 362	99.41 323	91.97 355	99.66 284	97.71 292	83.83 457	99.07 292

UniMVSNet_ETH3D		97.32 356	96.81 364	98.87 260	99.40 260	97.46 309	99.51 181	99.53 120	95.86 397	98.54 361	99.77 172	82.44 449	99.66 284	98.68 181	97.52 321	99.50 226

OPM-MVS		98.19 238	98.10 236	98.45 319	98.88 378	97.07 329	99.28 309	99.38 278	98.57 112	99.22 245	99.81 121	92.12 352	99.66 284	98.08 254	97.54 319	98.61 383
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 279	97.78 273	98.32 334	99.46 240	96.68 362	99.56 141	99.54 104	98.41 130	97.79 402	99.87 62	90.18 388	99.66 284	98.05 258	97.18 344	98.62 374

IMVS_0407		98.86 172	98.91 146	98.72 282	99.55 199	96.93 345	99.50 191	99.44 244	98.05 196	99.66 117	99.80 139	97.13 135	99.65 289	98.15 245	98.92 231	99.60 182

hse-mvs2		97.50 342	97.14 352	98.59 294	99.49 230	97.05 331	99.28 309	99.22 344	98.94 73	99.66 117	99.42 319	94.93 245	99.65 289	99.48 63	83.80 458	99.08 287

VPA-MVSNet		98.29 231	97.95 255	99.30 191	99.16 330	99.54 93	99.50 191	99.58 74	98.27 147	99.35 212	99.37 337	92.53 342	99.65 289	99.35 75	94.46 403	98.72 328

TR-MVS		97.76 307	97.41 326	98.82 269	99.06 350	97.87 290	98.87 409	98.56 428	96.63 349	98.68 341	99.22 371	92.49 343	99.65 289	95.40 396	97.79 305	98.95 306

reproduce_monomvs		97.89 283	97.87 265	97.96 365	99.51 216	95.45 398	99.60 109	99.25 338	99.17 31	98.85 318	99.49 299	89.29 397	99.64 293	99.35 75	96.31 360	98.78 314

gm-plane-assit					98.54 423	92.96 441			94.65 418		99.15 379		99.64 293	97.56 306

HQP4-MVS										98.66 342			99.64 293			98.64 365

HQP-MVS		98.02 263	97.90 260	98.37 330	99.19 317	96.83 353	98.98 392	99.39 270	98.24 157	98.66 342	99.40 327	92.47 344	99.64 293	97.19 334	97.58 315	98.64 365

PAPM		97.59 334	97.09 356	99.07 220	99.06 350	98.26 265	98.30 449	99.10 360	94.88 412	98.08 386	99.34 347	96.27 184	99.64 293	89.87 444	98.92 231	99.31 266

TAPA-MVS	97.07 15	97.74 313	97.34 335	98.94 239	99.70 117	97.53 306	99.25 325	99.51 144	91.90 441	99.30 223	99.63 247	98.78 51	99.64 293	88.09 451	99.87 74	99.65 162
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 223	98.09 239	99.24 204	99.26 299	99.32 126	99.56 141	99.55 95	97.45 277	98.71 333	99.83 97	93.23 319	99.63 299	98.88 146	96.32 359	98.76 320

ITE_SJBPF				98.08 354	99.29 291	96.37 372		98.92 385	98.34 138	98.83 319	99.75 181	91.09 376	99.62 300	95.82 383	97.40 335	98.25 415

LF4IMVS		97.52 339	97.46 314	97.70 386	98.98 366	95.55 393	99.29 304	98.82 402	98.07 190	98.66 342	99.64 241	89.97 389	99.61 301	97.01 343	96.68 349	97.94 436

tpm		97.67 328	97.55 299	98.03 356	99.02 357	95.01 410	99.43 244	98.54 430	96.44 365	99.12 265	99.34 347	91.83 359	99.60 302	97.75 287	96.46 355	99.48 230

tpm2		97.44 349	97.34 335	97.74 384	99.15 334	94.36 426	99.45 231	98.94 381	93.45 431	98.90 307	99.44 315	91.35 372	99.59 303	97.31 325	98.07 293	99.29 267

SSM_04072		99.06 142	98.96 134	99.35 177	99.62 166	98.88 199	99.25 325	99.47 213	98.05 196	99.37 203	99.81 121	96.85 151	99.58 304	98.98 129	99.25 192	99.60 182

SD_0403		97.55 336	97.53 303	97.62 389	99.61 176	93.64 436	99.72 53	99.44 244	98.03 205	98.62 354	99.39 331	96.06 191	99.57 305	87.88 453	99.01 225	99.66 156

baseline2		97.87 286	97.55 299	98.82 269	99.18 320	98.02 278	99.41 256	96.58 461	96.97 324	96.51 426	99.17 376	93.43 314	99.57 305	97.71 292	99.03 222	98.86 308

MS-PatchMatch		97.24 361	97.32 339	96.99 408	98.45 426	93.51 438	98.82 413	99.32 317	97.41 284	98.13 385	99.30 358	88.99 399	99.56 307	95.68 389	99.80 120	97.90 439

TinyColmap		97.12 364	96.89 363	97.83 377	99.07 348	95.52 396	98.57 435	98.74 414	97.58 260	97.81 401	99.79 156	88.16 413	99.56 307	95.10 401	97.21 342	98.39 407

USDC		97.34 354	97.20 349	97.75 382	99.07 348	95.20 405	98.51 439	99.04 370	97.99 209	98.31 373	99.86 70	89.02 398	99.55 309	95.67 390	97.36 337	98.49 394

MSLP-MVS++		99.46 39	99.47 22	99.44 161	99.60 182	99.16 150	99.41 256	99.71 13	98.98 67	99.45 176	99.78 163	99.19 9	99.54 310	99.28 90	99.84 97	99.63 174

UWE-MVS-28		97.36 352	97.24 348	97.75 382	98.84 387	94.44 423	99.24 330	97.58 450	97.98 210	99.00 291	99.00 395	91.35 372	99.53 311	93.75 419	98.39 267	99.27 272

TAMVS		99.12 123	99.08 101	99.24 204	99.46 240	98.55 241	99.51 181	99.46 224	98.09 185	99.45 176	99.82 106	98.34 94	99.51 312	98.70 176	98.93 229	99.67 152

EPNet_dtu		98.03 261	97.96 253	98.23 344	98.27 429	95.54 395	99.23 333	98.75 411	99.02 57	97.82 400	99.71 199	96.11 189	99.48 313	93.04 428	99.65 156	99.69 142
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 374	96.22 378	97.97 363	97.00 451	96.28 376	98.66 429	99.03 372	96.61 350	96.93 423	99.79 156	87.20 422	99.47 314	96.65 366	94.13 410	98.16 420

EG-PatchMatch MVS		95.97 389	95.69 390	96.81 415	97.78 436	92.79 442	99.16 348	98.93 382	96.16 384	94.08 444	99.22 371	82.72 447	99.47 314	95.67 390	97.50 324	98.17 419

myMVS_eth3d28		97.69 322	97.34 335	98.73 280	99.27 296	97.52 307	99.33 290	98.78 409	98.03 205	98.82 321	98.49 425	86.64 424	99.46 316	98.44 216	98.24 281	99.23 275

MVP-Stereo		97.81 301	97.75 280	97.99 362	97.53 440	96.60 366	98.96 396	98.85 399	97.22 301	97.23 413	99.36 340	95.28 229	99.46 316	95.51 392	99.78 129	97.92 438
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 209	98.67 183	98.30 336	99.35 272	95.59 392	99.50 191	99.55 95	98.60 110	99.39 199	99.83 97	94.48 280	99.45 318	98.75 170	98.56 259	99.85 45

test-LLR		98.06 253	97.90 260	98.55 304	98.79 391	97.10 325	98.67 426	97.75 446	97.34 289	98.61 355	98.85 409	94.45 282	99.45 318	97.25 328	99.38 178	99.10 282

TESTMET0.1,1		97.55 336	97.27 347	98.40 327	98.93 371	96.53 367	98.67 426	97.61 449	96.96 325	98.64 349	99.28 362	88.63 408	99.45 318	97.30 326	99.38 178	99.21 277

test-mter		97.49 347	97.13 354	98.55 304	98.79 391	97.10 325	98.67 426	97.75 446	96.65 345	98.61 355	98.85 409	88.23 412	99.45 318	97.25 328	99.38 178	99.10 282

mvs_anonymous		99.03 149	98.99 126	99.16 212	99.38 265	98.52 247	99.51 181	99.38 278	97.79 234	99.38 201	99.81 121	97.30 128	99.45 318	99.35 75	98.99 226	99.51 222

tfpnnormal		97.84 293	97.47 312	98.98 232	99.20 314	99.22 144	99.64 91	99.61 56	96.32 371	98.27 377	99.70 203	93.35 318	99.44 323	95.69 388	95.40 386	98.27 413

v7n		97.87 286	97.52 304	98.92 243	98.76 401	98.58 239	99.84 12	99.46 224	96.20 380	98.91 305	99.70 203	94.89 250	99.44 323	96.03 379	93.89 415	98.75 322

jajsoiax		98.43 216	98.28 223	98.88 256	98.60 418	98.43 258	99.82 16	99.53 120	98.19 165	98.63 351	99.80 139	93.22 321	99.44 323	99.22 98	97.50 324	98.77 318

mvs_tets		98.40 222	98.23 225	98.91 247	98.67 411	98.51 249	99.66 78	99.53 120	98.19 165	98.65 348	99.81 121	92.75 330	99.44 323	99.31 84	97.48 328	98.77 318

sc_t1		95.75 393	95.05 400	97.87 372	98.83 388	94.61 420	99.21 339	99.45 235	87.45 454	97.97 393	99.85 77	81.19 454	99.43 327	98.27 233	93.20 424	99.57 200

Vis-MVSNet (Re-imp)		98.87 169	98.72 177	99.31 186	99.71 112	98.88 199	99.80 25	99.44 244	97.91 216	99.36 209	99.78 163	95.49 221	99.43 327	97.91 266	99.11 210	99.62 177

OPU-MVS				99.64 96	99.56 195	99.72 52	99.60 109				99.70 203	99.27 5	99.42 329	98.24 236	99.80 120	99.79 88

Anonymous20231211		97.88 284	97.54 302	98.90 249	99.71 112	98.53 243	99.48 214	99.57 81	94.16 422	98.81 322	99.68 222	93.23 319	99.42 329	98.84 159	94.42 405	98.76 320

ttmdpeth		97.80 303	97.63 294	98.29 337	98.77 399	97.38 312	99.64 91	99.36 287	98.78 93	96.30 429	99.58 265	92.34 351	99.39 331	98.36 225	95.58 381	98.10 423

VPNet		97.84 293	97.44 320	99.01 228	99.21 312	98.94 192	99.48 214	99.57 81	98.38 132	99.28 227	99.73 192	88.89 400	99.39 331	99.19 101	93.27 423	98.71 330

nrg030		98.64 206	98.42 213	99.28 198	99.05 353	99.69 58	99.81 20	99.46 224	98.04 203	99.01 287	99.82 106	96.69 163	99.38 333	99.34 80	94.59 402	98.78 314

GA-MVS		97.85 289	97.47 312	99.00 230	99.38 265	97.99 280	98.57 435	99.15 354	97.04 320	98.90 307	99.30 358	89.83 391	99.38 333	96.70 361	98.33 271	99.62 177

UniMVSNet (Re)		98.29 231	98.00 249	99.13 217	99.00 360	99.36 121	99.49 208	99.51 144	97.95 212	98.97 296	99.13 381	96.30 183	99.38 333	98.36 225	93.34 421	98.66 361

FIs		98.78 190	98.63 191	99.23 206	99.18 320	99.54 93	99.83 15	99.59 69	98.28 145	98.79 326	99.81 121	96.75 161	99.37 336	99.08 118	96.38 357	98.78 314

PS-MVSNAJss		98.92 163	98.92 143	98.90 249	98.78 394	98.53 243	99.78 32	99.54 104	98.07 190	99.00 291	99.76 176	99.01 18	99.37 336	99.13 110	97.23 341	98.81 311

CDS-MVSNet		99.09 135	99.03 112	99.25 201	99.42 250	98.73 223	99.45 231	99.46 224	98.11 181	99.46 175	99.77 172	98.01 109	99.37 336	98.70 176	98.92 231	99.66 156
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 393	95.16 398	97.51 395	99.30 287	93.69 434	98.88 407	95.78 462	85.09 459	98.78 327	92.65 462	91.29 374	99.37 336	94.85 406	99.85 89	99.46 241

v1192		97.81 301	97.44 320	98.91 247	98.88 378	98.68 227	99.51 181	99.34 299	96.18 382	99.20 251	99.34 347	94.03 299	99.36 340	95.32 398	95.18 390	98.69 339

EI-MVSNet		98.67 202	98.67 183	98.68 288	99.35 272	97.97 281	99.50 191	99.38 278	96.93 330	99.20 251	99.83 97	97.87 111	99.36 340	98.38 221	97.56 317	98.71 330

MVSTER		98.49 211	98.32 220	99.00 230	99.35 272	99.02 170	99.54 161	99.38 278	97.41 284	99.20 251	99.73 192	93.86 307	99.36 340	98.87 149	97.56 317	98.62 374

gg-mvs-nofinetune		96.17 385	95.32 397	98.73 280	98.79 391	98.14 271	99.38 273	94.09 468	91.07 446	98.07 389	91.04 466	89.62 395	99.35 343	96.75 358	99.09 217	98.68 344

pm-mvs1		97.68 325	97.28 344	98.88 256	99.06 350	98.62 235	99.50 191	99.45 235	96.32 371	97.87 398	99.79 156	92.47 344	99.35 343	97.54 308	93.54 419	98.67 352

OurMVSNet-221017-0		97.88 284	97.77 275	98.19 346	98.71 407	96.53 367	99.88 4	99.00 375	97.79 234	98.78 327	99.94 6	91.68 363	99.35 343	97.21 330	96.99 348	98.69 339

EGC-MVSNET		82.80 431	77.86 437	97.62 389	97.91 433	96.12 382	99.33 290	99.28 332	8.40 474	25.05 475	99.27 365	84.11 441	99.33 346	89.20 446	98.22 282	97.42 448

pmmvs6		96.53 377	96.09 382	97.82 379	98.69 409	95.47 397	99.37 275	99.47 213	93.46 430	97.41 407	99.78 163	87.06 423	99.33 346	96.92 353	92.70 431	98.65 363

V42		98.06 253	97.79 270	98.86 263	98.98 366	98.84 209	99.69 62	99.34 299	96.53 357	99.30 223	99.37 337	94.67 267	99.32 348	97.57 305	94.66 400	98.42 403

lessismore_v0				97.79 381	98.69 409	95.44 400		94.75 466		95.71 435	99.87 62	88.69 404	99.32 348	95.89 382	94.93 397	98.62 374

OpenMVS_ROB	92.34 20	94.38 410	93.70 416	96.41 420	97.38 442	93.17 440	99.06 371	98.75 411	86.58 457	94.84 442	98.26 435	81.53 452	99.32 348	89.01 447	97.87 301	96.76 451

v8		97.95 275	97.63 294	98.93 241	98.95 370	98.81 217	99.80 25	99.41 260	96.03 394	99.10 270	99.42 319	94.92 247	99.30 351	96.94 350	94.08 412	98.66 361

v1921920		97.80 303	97.45 315	98.84 267	98.80 390	98.53 243	99.52 172	99.34 299	96.15 386	99.24 240	99.47 308	93.98 301	99.29 352	95.40 396	95.13 392	98.69 339

anonymousdsp		98.44 215	98.28 223	98.94 239	98.50 424	98.96 182	99.77 34	99.50 167	97.07 315	98.87 313	99.77 172	94.76 260	99.28 353	98.66 183	97.60 313	98.57 389

MVSFormer		99.17 104	99.12 93	99.29 194	99.51 216	98.94 192	99.88 4	99.46 224	97.55 264	99.80 69	99.65 235	97.39 122	99.28 353	99.03 124	99.85 89	99.65 162

test_djsdf		98.67 202	98.57 203	98.98 232	98.70 408	98.91 197	99.88 4	99.46 224	97.55 264	99.22 245	99.88 51	95.73 212	99.28 353	99.03 124	97.62 312	98.75 322

VortexMVS		98.67 202	98.66 186	98.68 288	99.62 166	97.96 283	99.59 116	99.41 260	98.13 177	99.31 219	99.70 203	95.48 222	99.27 356	99.40 70	97.32 338	98.79 312

SSC-MVS3.2		97.34 354	97.15 351	97.93 367	99.02 357	95.76 389	99.48 214	99.58 74	97.62 256	99.09 273	99.53 285	87.95 415	99.27 356	96.42 371	95.66 379	98.75 322

cascas		97.69 322	97.43 324	98.48 311	98.60 418	97.30 314	98.18 453	99.39 270	92.96 435	98.41 367	98.78 416	93.77 310	99.27 356	98.16 243	98.61 253	98.86 308

v144192		97.92 279	97.60 297	98.87 260	98.83 388	98.65 230	99.55 156	99.34 299	96.20 380	99.32 218	99.40 327	94.36 284	99.26 359	96.37 375	95.03 394	98.70 335

dmvs_re		98.08 251	98.16 228	97.85 374	99.55 199	94.67 419	99.70 58	98.92 385	98.15 170	99.06 281	99.35 343	93.67 313	99.25 360	97.77 284	97.25 340	99.64 169

v2v482		98.06 253	97.77 275	98.92 243	98.90 376	98.82 215	99.57 134	99.36 287	96.65 345	99.19 254	99.35 343	94.20 291	99.25 360	97.72 291	94.97 395	98.69 339

v1240		97.69 322	97.32 339	98.79 275	98.85 385	98.43 258	99.48 214	99.36 287	96.11 389	99.27 233	99.36 340	93.76 311	99.24 362	94.46 410	95.23 389	98.70 335

WBMVS		97.74 313	97.50 307	98.46 317	99.24 305	97.43 310	99.21 339	99.42 257	97.45 277	98.96 298	99.41 323	88.83 401	99.23 363	98.94 137	96.02 365	98.71 330

v1144		97.98 270	97.69 286	98.85 266	98.87 381	98.66 229	99.54 161	99.35 294	96.27 375	99.23 244	99.35 343	94.67 267	99.23 363	96.73 359	95.16 391	98.68 344

v10		97.85 289	97.52 304	98.86 263	98.99 363	98.67 228	99.75 42	99.41 260	95.70 398	98.98 294	99.41 323	94.75 261	99.23 363	96.01 381	94.63 401	98.67 352

WR-MVS_H		98.13 245	97.87 265	98.90 249	99.02 357	98.84 209	99.70 58	99.59 69	97.27 295	98.40 368	99.19 375	95.53 219	99.23 363	98.34 227	93.78 417	98.61 383

miper_enhance_ethall		98.16 242	98.08 240	98.41 325	98.96 369	97.72 298	98.45 441	99.32 317	96.95 327	98.97 296	99.17 376	97.06 142	99.22 367	97.86 271	95.99 368	98.29 412

GG-mvs-BLEND				98.45 319	98.55 422	98.16 269	99.43 244	93.68 469		97.23 413	98.46 426	89.30 396	99.22 367	95.43 395	98.22 282	97.98 434

FC-MVSNet-test		98.75 195	98.62 196	99.15 216	99.08 347	99.45 110	99.86 11	99.60 63	98.23 160	98.70 339	99.82 106	96.80 158	99.22 367	99.07 119	96.38 357	98.79 312

UniMVSNet_NR-MVSNet		98.22 234	97.97 252	98.96 235	98.92 373	98.98 175	99.48 214	99.53 120	97.76 238	98.71 333	99.46 312	96.43 178	99.22 367	98.57 200	92.87 429	98.69 339

DU-MVS		98.08 251	97.79 270	98.96 235	98.87 381	98.98 175	99.41 256	99.45 235	97.87 220	98.71 333	99.50 296	94.82 252	99.22 367	98.57 200	92.87 429	98.68 344

cl____		98.01 266	97.84 268	98.55 304	99.25 303	97.97 281	98.71 424	99.34 299	96.47 364	98.59 358	99.54 281	95.65 215	99.21 372	97.21 330	95.77 374	98.46 400

WR-MVS		98.06 253	97.73 282	99.06 222	98.86 384	99.25 141	99.19 344	99.35 294	97.30 293	98.66 342	99.43 317	93.94 302	99.21 372	98.58 197	94.28 407	98.71 330

test_0402		96.64 375	96.24 377	97.85 374	98.85 385	96.43 371	99.44 238	99.26 336	93.52 428	96.98 421	99.52 289	88.52 409	99.20 374	92.58 435	97.50 324	97.93 437

icg_test_0407_2		98.79 189	98.86 159	98.57 298	99.55 199	96.93 345	99.07 367	99.44 244	98.05 196	99.66 117	99.80 139	97.13 135	99.18 375	98.15 245	98.92 231	99.60 182

SixPastTwentyTwo		97.50 342	97.33 338	98.03 356	98.65 412	96.23 379	99.77 34	98.68 423	97.14 306	97.90 396	99.93 10	90.45 382	99.18 375	97.00 344	96.43 356	98.67 352

cl22		97.85 289	97.64 293	98.48 311	99.09 344	97.87 290	98.60 434	99.33 307	97.11 312	98.87 313	99.22 371	92.38 349	99.17 377	98.21 237	95.99 368	98.42 403

tt0320		95.71 395	95.07 399	97.62 389	99.05 353	95.02 409	99.25 325	99.52 125	86.81 455	97.97 393	99.72 196	83.58 444	99.15 378	96.38 374	93.35 420	98.68 344

WB-MVSnew		97.65 330	97.65 290	97.63 388	98.78 394	97.62 304	99.13 354	98.33 434	97.36 288	99.07 276	98.94 403	95.64 216	99.15 378	92.95 429	98.68 251	96.12 458

IterMVS-SCA-FT		97.82 299	97.75 280	98.06 355	99.57 191	96.36 373	99.02 381	99.49 179	97.18 303	98.71 333	99.72 196	92.72 333	99.14 380	97.44 318	95.86 373	98.67 352

pmmvs5		97.52 339	97.30 341	98.16 348	98.57 421	96.73 357	99.27 314	98.90 392	96.14 387	98.37 370	99.53 285	91.54 369	99.14 380	97.51 310	95.87 372	98.63 372

v148		97.79 305	97.55 299	98.50 308	98.74 402	97.72 298	99.54 161	99.33 307	96.26 376	98.90 307	99.51 293	94.68 266	99.14 380	97.83 275	93.15 426	98.63 372

IMVS_0404		98.53 210	98.52 208	98.55 304	99.55 199	96.93 345	99.20 342	99.44 244	98.05 196	98.96 298	99.80 139	94.66 269	99.13 383	98.15 245	98.92 231	99.60 182

miper_ehance_all_eth		98.18 240	98.10 236	98.41 325	99.23 307	97.72 298	98.72 423	99.31 321	96.60 353	98.88 310	99.29 360	97.29 129	99.13 383	97.60 299	95.99 368	98.38 408

NR-MVSNet		97.97 273	97.61 296	99.02 227	98.87 381	99.26 139	99.47 224	99.42 257	97.63 254	97.08 419	99.50 296	95.07 240	99.13 383	97.86 271	93.59 418	98.68 344

IterMVS		97.83 296	97.77 275	98.02 358	99.58 186	96.27 377	99.02 381	99.48 191	97.22 301	98.71 333	99.70 203	92.75 330	99.13 383	97.46 316	96.00 367	98.67 352
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 411	94.90 402	91.84 437	97.24 446	80.01 467	98.52 438	99.48 191	89.01 451	91.99 454	99.67 228	85.67 431	99.13 383	95.44 394	97.03 347	96.39 455
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 258	97.96 253	98.33 332	99.26 299	97.38 312	98.56 437	99.31 321	96.65 345	98.88 310	99.52 289	96.58 169	99.12 388	97.39 321	95.53 384	98.47 397

pmmvs4		98.13 245	97.90 260	98.81 272	98.61 417	98.87 203	98.99 389	99.21 347	96.44 365	99.06 281	99.58 265	95.90 202	99.11 389	97.18 336	96.11 364	98.46 400

TransMVSNet (Re)		97.15 363	96.58 369	98.86 263	99.12 336	98.85 207	99.49 208	98.91 390	95.48 401	97.16 417	99.80 139	93.38 315	99.11 389	94.16 416	91.73 436	98.62 374

ambc				93.06 435	92.68 466	82.36 460	98.47 440	98.73 420		95.09 440	97.41 449	55.55 467	99.10 391	96.42 371	91.32 437	97.71 440

Baseline_NR-MVSNet		97.76 307	97.45 315	98.68 288	99.09 344	98.29 263	99.41 256	98.85 399	95.65 399	98.63 351	99.67 228	94.82 252	99.10 391	98.07 257	92.89 428	98.64 365

test_vis3_rt		87.04 427	85.81 430	90.73 441	93.99 465	81.96 462	99.76 37	90.23 476	92.81 437	81.35 464	91.56 464	40.06 473	99.07 393	94.27 413	88.23 451	91.15 464

CP-MVSNet		98.09 249	97.78 273	99.01 228	98.97 368	99.24 142	99.67 71	99.46 224	97.25 297	98.48 365	99.64 241	93.79 309	99.06 394	98.63 187	94.10 411	98.74 326

PS-CasMVS		97.93 276	97.59 298	98.95 237	98.99 363	99.06 166	99.68 68	99.52 125	97.13 307	98.31 373	99.68 222	92.44 348	99.05 395	98.51 208	94.08 412	98.75 322

K. test v3		97.10 365	96.79 365	98.01 359	98.72 405	96.33 374	99.87 8	97.05 453	97.59 258	96.16 431	99.80 139	88.71 403	99.04 396	96.69 362	96.55 354	98.65 363

new_pmnet		96.38 381	96.03 383	97.41 398	98.13 432	95.16 408	99.05 373	99.20 348	93.94 423	97.39 410	98.79 415	91.61 368	99.04 396	90.43 442	95.77 374	98.05 427

DIV-MVS_self_test		98.01 266	97.85 267	98.48 311	99.24 305	97.95 286	98.71 424	99.35 294	96.50 358	98.60 357	99.54 281	95.72 213	99.03 398	97.21 330	95.77 374	98.46 400

IterMVS-LS		98.46 214	98.42 213	98.58 297	99.59 184	98.00 279	99.37 275	99.43 255	96.94 329	99.07 276	99.59 261	97.87 111	99.03 398	98.32 230	95.62 380	98.71 330
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 330	97.68 287	97.55 394	98.62 415	94.97 411	98.84 411	99.30 326	96.83 336	98.19 382	99.34 347	97.01 146	99.02 400	95.00 404	96.01 366	98.64 365

Patchmtry		97.75 311	97.40 327	98.81 272	99.10 341	98.87 203	99.11 363	99.33 307	94.83 414	98.81 322	99.38 334	94.33 287	99.02 400	96.10 377	95.57 382	98.53 391

N_pmnet		94.95 405	95.83 388	92.31 436	98.47 425	79.33 468	99.12 357	92.81 474	93.87 424	97.68 403	99.13 381	93.87 306	99.01 402	91.38 439	96.19 362	98.59 387

CR-MVSNet		98.17 241	97.93 258	98.87 260	99.18 320	98.49 252	99.22 337	99.33 307	96.96 325	99.56 154	99.38 334	94.33 287	99.00 403	94.83 407	98.58 256	99.14 279

c3_l		98.12 247	98.04 245	98.38 329	99.30 287	97.69 302	98.81 414	99.33 307	96.67 343	98.83 319	99.34 347	97.11 138	98.99 404	97.58 301	95.34 387	98.48 395

test0.0.03 1		97.71 320	97.42 325	98.56 302	98.41 428	97.82 293	98.78 417	98.63 426	97.34 289	98.05 390	98.98 399	94.45 282	98.98 405	95.04 403	97.15 345	98.89 307

PatchT		97.03 367	96.44 373	98.79 275	98.99 363	98.34 262	99.16 348	99.07 366	92.13 440	99.52 165	97.31 453	94.54 277	98.98 405	88.54 449	98.73 248	99.03 295

GBi-Net		97.68 325	97.48 309	98.29 337	99.51 216	97.26 318	99.43 244	99.48 191	96.49 359	99.07 276	99.32 355	90.26 384	98.98 405	97.10 338	96.65 350	98.62 374

test1		97.68 325	97.48 309	98.29 337	99.51 216	97.26 318	99.43 244	99.48 191	96.49 359	99.07 276	99.32 355	90.26 384	98.98 405	97.10 338	96.65 350	98.62 374

FMVSNet3		98.03 261	97.76 279	98.84 267	99.39 263	98.98 175	99.40 264	99.38 278	96.67 343	99.07 276	99.28 362	92.93 325	98.98 405	97.10 338	96.65 350	98.56 390

FMVSNet2		97.72 317	97.36 330	98.80 274	99.51 216	98.84 209	99.45 231	99.42 257	96.49 359	98.86 317	99.29 360	90.26 384	98.98 405	96.44 370	96.56 353	98.58 388

FMVSNet1		96.84 371	96.36 375	98.29 337	99.32 285	97.26 318	99.43 244	99.48 191	95.11 406	98.55 360	99.32 355	83.95 442	98.98 405	95.81 384	96.26 361	98.62 374

ppachtmachnet_test		97.49 347	97.45 315	97.61 392	98.62 415	95.24 404	98.80 415	99.46 224	96.11 389	98.22 380	99.62 252	96.45 176	98.97 412	93.77 418	95.97 371	98.61 383

TranMVSNet+NR-MVSNet		97.93 276	97.66 289	98.76 279	98.78 394	98.62 235	99.65 84	99.49 179	97.76 238	98.49 364	99.60 259	94.23 290	98.97 412	98.00 261	92.90 427	98.70 335

MVStest1		96.08 388	95.48 393	97.89 371	98.93 371	96.70 358	99.56 141	99.35 294	92.69 438	91.81 455	99.46 312	89.90 390	98.96 414	95.00 404	92.61 432	98.00 432

tt0320-xc		95.31 401	94.59 405	97.45 397	98.92 373	94.73 415	99.20 342	99.31 321	86.74 456	97.23 413	99.72 196	81.14 455	98.95 415	97.08 341	91.98 435	98.67 352

test_method		91.10 422	91.36 424	90.31 442	95.85 454	73.72 475	94.89 463	99.25 338	68.39 466	95.82 434	99.02 393	80.50 456	98.95 415	93.64 421	94.89 399	98.25 415

ADS-MVSNet2		98.02 263	98.07 243	97.87 372	99.33 278	95.19 406	99.23 333	99.08 363	96.24 377	99.10 270	99.67 228	94.11 295	98.93 417	96.81 356	99.05 220	99.48 230

ET-MVSNet_ETH3D		96.49 378	95.64 392	99.05 224	99.53 207	98.82 215	98.84 411	97.51 451	97.63 254	84.77 460	99.21 374	92.09 353	98.91 418	98.98 129	92.21 434	99.41 251

miper_lstm_enhance		98.00 268	97.91 259	98.28 341	99.34 277	97.43 310	98.88 407	99.36 287	96.48 362	98.80 324	99.55 276	95.98 195	98.91 418	97.27 327	95.50 385	98.51 393

MonoMVSNet		98.38 223	98.47 211	98.12 353	98.59 420	96.19 381	99.72 53	98.79 408	97.89 218	99.44 181	99.52 289	96.13 188	98.90 420	98.64 185	97.54 319	99.28 268

PEN-MVS		97.76 307	97.44 320	98.72 282	98.77 399	98.54 242	99.78 32	99.51 144	97.06 317	98.29 376	99.64 241	92.63 339	98.89 421	98.09 250	93.16 425	98.72 328

testing3		97.28 357	96.76 366	98.82 269	99.37 268	98.07 276	99.45 231	99.36 287	97.56 263	97.89 397	98.95 402	83.70 443	98.82 422	96.03 379	98.56 259	99.58 197

testgi		97.65 330	97.50 307	98.13 352	99.36 271	96.45 370	99.42 251	99.48 191	97.76 238	97.87 398	99.45 314	91.09 376	98.81 423	94.53 409	98.52 262	99.13 281

testf1		90.42 425	90.68 426	89.65 445	97.78 436	73.97 473	99.13 354	98.81 404	89.62 448	91.80 456	98.93 404	62.23 465	98.80 424	86.61 459	91.17 438	96.19 456

APD_test2		90.42 425	90.68 426	89.65 445	97.78 436	73.97 473	99.13 354	98.81 404	89.62 448	91.80 456	98.93 404	62.23 465	98.80 424	86.61 459	91.17 438	96.19 456

MIMVSNet		97.73 315	97.45 315	98.57 298	99.45 246	97.50 308	99.02 381	98.98 377	96.11 389	99.41 192	99.14 380	90.28 383	98.74 426	95.74 386	98.93 229	99.47 236

LCM-MVSNet-Re		97.83 296	98.15 230	96.87 414	99.30 287	92.25 445	99.59 116	98.26 435	97.43 281	96.20 430	99.13 381	96.27 184	98.73 427	98.17 242	98.99 226	99.64 169

Syy-MVS		97.09 366	97.14 352	96.95 411	99.00 360	92.73 443	99.29 304	99.39 270	97.06 317	97.41 407	98.15 438	93.92 304	98.68 428	91.71 437	98.34 269	99.45 244

myMVS_eth3d		96.89 369	96.37 374	98.43 324	99.00 360	97.16 322	99.29 304	99.39 270	97.06 317	97.41 407	98.15 438	83.46 445	98.68 428	95.27 399	98.34 269	99.45 244

DTE-MVSNet		97.51 341	97.19 350	98.46 317	98.63 414	98.13 272	99.84 12	99.48 191	96.68 342	97.97 393	99.67 228	92.92 326	98.56 430	96.88 355	92.60 433	98.70 335

PC_three_1452									98.18 168	99.84 52	99.70 203	99.31 3	98.52 431	98.30 232	99.80 120	99.81 75

mvsany_test3		93.77 414	93.45 417	94.74 427	95.78 455	88.01 453	99.64 91	98.25 436	98.28 145	94.31 443	97.97 445	68.89 461	98.51 432	97.50 311	90.37 443	97.71 440

UnsupCasMVSNet_bld		93.53 415	92.51 421	96.58 419	97.38 442	93.82 430	98.24 450	99.48 191	91.10 445	93.10 449	96.66 455	74.89 459	98.37 433	94.03 417	87.71 452	97.56 445

Anonymous20240521		96.20 384	95.89 387	97.13 405	97.72 439	94.96 412	99.79 31	99.29 330	93.01 434	97.20 416	99.03 391	89.69 393	98.36 434	91.16 440	96.13 363	98.07 425

test_f		91.90 421	91.26 425	93.84 430	95.52 459	85.92 455	99.69 62	98.53 431	95.31 403	93.87 445	96.37 457	55.33 468	98.27 435	95.70 387	90.98 441	97.32 449

MDA-MVSNet_test_wron		95.45 397	94.60 404	98.01 359	98.16 431	97.21 321	99.11 363	99.24 341	93.49 429	80.73 466	98.98 399	93.02 323	98.18 436	94.22 415	94.45 404	98.64 365

UnsupCasMVSNet_eth		96.44 379	96.12 380	97.40 399	98.65 412	95.65 390	99.36 280	99.51 144	97.13 307	96.04 433	98.99 397	88.40 410	98.17 437	96.71 360	90.27 444	98.40 406

KD-MVS_2432*1600		94.62 406	93.72 414	97.31 400	97.19 448	95.82 387	98.34 445	99.20 348	95.00 410	97.57 404	98.35 431	87.95 415	98.10 438	92.87 431	77.00 464	98.01 429

miper_refine_blended		94.62 406	93.72 414	97.31 400	97.19 448	95.82 387	98.34 445	99.20 348	95.00 410	97.57 404	98.35 431	87.95 415	98.10 438	92.87 431	77.00 464	98.01 429

YYNet1		95.36 399	94.51 407	97.92 368	97.89 434	97.10 325	99.10 365	99.23 342	93.26 432	80.77 465	99.04 390	92.81 329	98.02 440	94.30 411	94.18 409	98.64 365

EU-MVSNet		97.98 270	98.03 246	97.81 380	98.72 405	96.65 363	99.66 78	99.66 28	98.09 185	98.35 371	99.82 106	95.25 233	98.01 441	97.41 320	95.30 388	98.78 314

Gipuma		90.99 423	90.15 428	93.51 431	98.73 403	90.12 451	93.98 464	99.45 235	79.32 462	92.28 452	94.91 459	69.61 460	97.98 442	87.42 455	95.67 378	92.45 462
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 400	94.73 403	97.15 403	95.53 458	95.94 385	99.35 285	99.10 360	95.13 404	93.55 447	97.54 448	88.15 414	97.91 443	94.58 408	89.69 448	97.61 443

PM-MVS		92.96 418	92.23 422	95.14 426	95.61 456	89.98 452	99.37 275	98.21 439	94.80 415	95.04 441	97.69 446	65.06 462	97.90 444	94.30 411	89.98 446	97.54 446

MDA-MVSNet-bldmvs		94.96 404	93.98 411	97.92 368	98.24 430	97.27 316	99.15 351	99.33 307	93.80 425	80.09 467	99.03 391	88.31 411	97.86 445	93.49 423	94.36 406	98.62 374

Patchmatch-RL test		95.84 391	95.81 389	95.95 424	95.61 456	90.57 450	98.24 450	98.39 432	95.10 408	95.20 438	98.67 419	94.78 256	97.77 446	96.28 376	90.02 445	99.51 222

Anonymous20231206		96.22 382	96.03 383	96.79 416	97.31 445	94.14 428	99.63 97	99.08 363	96.17 383	97.04 420	99.06 388	93.94 302	97.76 447	86.96 457	95.06 393	98.47 397

SD-MVS		99.41 56	99.52 12	99.05 224	99.74 95	99.68 59	99.46 228	99.52 125	99.11 42	99.88 39	99.91 25	99.43 1	97.70 448	98.72 174	99.93 32	99.77 96
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		97.25 359	97.35 332	96.95 411	97.84 435	93.61 437	99.57 134	96.63 459	96.13 388	98.87 313	98.61 422	94.59 272	97.70 448	95.08 402	98.86 239	99.55 204

dongtai		93.26 416	92.93 420	94.25 428	99.39 263	85.68 456	97.68 459	93.27 470	92.87 436	96.85 424	99.39 331	82.33 450	97.48 450	76.78 464	97.80 304	99.58 197

pmmvs3		94.09 412	93.25 419	96.60 418	94.76 463	94.49 422	98.92 403	98.18 441	89.66 447	96.48 427	98.06 444	86.28 428	97.33 451	89.68 445	87.20 453	97.97 435

KD-MVS_self_test		95.00 403	94.34 408	96.96 410	97.07 450	95.39 401	99.56 141	99.44 244	95.11 406	97.13 418	97.32 452	91.86 358	97.27 452	90.35 443	81.23 461	98.23 417

FMVSNet5		96.43 380	96.19 379	97.15 403	99.11 338	95.89 386	99.32 293	99.52 125	94.47 421	98.34 372	99.07 386	87.54 420	97.07 453	92.61 434	95.72 377	98.47 397

new-patchmatchnet		94.48 409	94.08 410	95.67 425	95.08 461	92.41 444	99.18 346	99.28 332	94.55 420	93.49 448	97.37 451	87.86 418	97.01 454	91.57 438	88.36 450	97.61 443

LCM-MVSNet		86.80 429	85.22 433	91.53 439	87.81 471	80.96 465	98.23 452	98.99 376	71.05 464	90.13 459	96.51 456	48.45 472	96.88 455	90.51 441	85.30 455	96.76 451

CL-MVSNet_self_test		94.49 408	93.97 412	96.08 423	96.16 453	93.67 435	98.33 447	99.38 278	95.13 404	97.33 411	98.15 438	92.69 337	96.57 456	88.67 448	79.87 462	97.99 433

MIMVSNet1		95.51 396	95.04 401	96.92 413	97.38 442	95.60 391	99.52 172	99.50 167	93.65 427	96.97 422	99.17 376	85.28 436	96.56 457	88.36 450	95.55 383	98.60 386

FE-MVSNET		94.07 413	93.36 418	96.22 422	94.05 464	94.71 417	99.56 141	98.36 433	93.15 433	93.76 446	97.55 447	86.47 427	96.49 458	87.48 454	89.83 447	97.48 447

test20.03		96.12 386	95.96 385	96.63 417	97.44 441	95.45 398	99.51 181	99.38 278	96.55 356	96.16 431	99.25 368	93.76 311	96.17 459	87.35 456	94.22 408	98.27 413

tmp_tt		82.80 431	81.52 434	86.66 447	66.61 477	68.44 476	92.79 466	97.92 443	68.96 465	80.04 468	99.85 77	85.77 430	96.15 460	97.86 271	43.89 470	95.39 460

test_fmvs3		92.10 420	91.77 423	93.08 434	96.19 452	86.25 454	99.82 16	98.62 427	96.65 345	95.19 439	96.90 454	55.05 469	95.93 461	96.63 367	90.92 442	97.06 450

kuosan		90.92 424	90.11 429	93.34 432	98.78 394	85.59 457	98.15 454	93.16 472	89.37 450	92.07 453	98.38 430	81.48 453	95.19 462	62.54 471	97.04 346	99.25 273

dmvs_testset		95.02 402	96.12 380	91.72 438	99.10 341	80.43 466	99.58 126	97.87 445	97.47 273	95.22 437	98.82 411	93.99 300	95.18 463	88.09 451	94.91 398	99.56 203

PMMVS2		86.87 428	85.37 432	91.35 440	90.21 469	83.80 459	98.89 406	97.45 452	83.13 461	91.67 458	95.03 458	48.49 471	94.70 464	85.86 461	77.62 463	95.54 459

PMVS	70.75 22	75.98 437	74.97 438	79.01 453	70.98 476	55.18 478	93.37 465	98.21 439	65.08 470	61.78 471	93.83 461	21.74 478	92.53 465	78.59 463	91.12 440	89.34 466
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 430	85.65 431	82.75 451	86.77 472	63.39 477	98.35 444	98.92 385	74.11 463	83.39 462	98.98 399	50.85 470	92.40 466	84.54 462	94.97 395	92.46 461

WB-MVS		93.10 417	94.10 409	90.12 443	95.51 460	81.88 463	99.73 51	99.27 335	95.05 409	93.09 450	98.91 408	94.70 265	91.89 467	76.62 465	94.02 414	96.58 453

SSC-MVS		92.73 419	93.73 413	89.72 444	95.02 462	81.38 464	99.76 37	99.23 342	94.87 413	92.80 451	98.93 404	94.71 264	91.37 468	74.49 467	93.80 416	96.42 454

MVE	76.82 21	76.91 436	74.31 440	84.70 448	85.38 474	76.05 472	96.88 462	93.17 471	67.39 467	71.28 469	89.01 468	21.66 479	87.69 469	71.74 468	72.29 466	90.35 465
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 433	79.88 435	82.81 450	90.75 468	76.38 471	97.69 458	95.76 463	66.44 468	83.52 461	92.25 463	62.54 464	87.16 470	68.53 469	61.40 467	84.89 468

EMVS		80.02 434	79.22 436	82.43 452	91.19 467	76.40 470	97.55 461	92.49 475	66.36 469	83.01 463	91.27 465	64.63 463	85.79 471	65.82 470	60.65 468	85.08 467

ANet_high		77.30 435	74.86 439	84.62 449	75.88 475	77.61 469	97.63 460	93.15 473	88.81 452	64.27 470	89.29 467	36.51 474	83.93 472	75.89 466	52.31 469	92.33 463

wuyk23d		40.18 438	41.29 443	36.84 454	86.18 473	49.12 479	79.73 467	22.81 479	27.64 471	25.46 474	28.45 474	21.98 477	48.89 473	55.80 472	23.56 473	12.51 471

test123		39.01 440	42.50 442	28.53 455	39.17 478	20.91 480	98.75 420	19.17 480	19.83 473	38.57 472	66.67 470	33.16 475	15.42 474	37.50 474	29.66 472	49.26 469

testmvs		39.17 439	43.78 441	25.37 456	36.04 479	16.84 481	98.36 443	26.56 478	20.06 472	38.51 473	67.32 469	29.64 476	15.30 475	37.59 473	39.90 471	43.98 470

mmdepth		0.02 445	0.03 448	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.27 476	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

monomultidepth		0.02 445	0.03 448	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.27 476	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

test_blank		0.13 444	0.17 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	1.57 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

uanet_test		0.02 445	0.03 448	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.27 476	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

DCPMVS		0.02 445	0.03 448	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.27 476	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

cdsmvs_eth3d_5k		24.64 441	32.85 444	0.00 457	0.00 480	0.00 482	0.00 468	99.51 144	0.00 475	0.00 476	99.56 273	96.58 169	0.00 476	0.00 475	0.00 474	0.00 472

pcd_1.5k_mvsjas		8.27 443	11.03 446	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.27 476	99.01 18	0.00 476	0.00 475	0.00 474	0.00 472

sosnet-low-res		0.02 445	0.03 448	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.27 476	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

sosnet		0.02 445	0.03 448	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.27 476	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

uncertanet		0.02 445	0.03 448	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.27 476	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

Regformer		0.02 445	0.03 448	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.27 476	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

ab-mvs-re		8.30 442	11.06 445	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	99.58 265	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

uanet		0.02 445	0.03 448	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.27 476	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

WAC-MVS						97.16 322								95.47 393

FOURS1					99.91 1	99.93 1	99.87 8	99.56 86	99.10 43	99.81 64

test_one_0601					99.81 53	99.88 9		99.49 179	98.97 70	99.65 126	99.81 121	99.09 14

eth-test2					0.00 480

eth-test					0.00 480

RE-MVS-def			99.34 47		99.76 77	99.82 27	99.63 97	99.52 125	98.38 132	99.76 86	99.82 106	98.75 58		98.61 191	99.81 115	99.77 96

IU-MVS					99.84 35	99.88 9		99.32 317	98.30 144	99.84 52				98.86 154	99.85 89	99.89 28

save fliter					99.76 77	99.59 83	99.14 353	99.40 267	99.00 62

test0726					99.85 28	99.89 5	99.62 102	99.50 167	99.10 43	99.86 49	99.82 106	98.94 32

GSMVS																99.52 213

test_part2					99.81 53	99.83 21				99.77 80

sam_mvs1												94.86 251				99.52 213

sam_mvs												94.72 263

MTGPA								99.47 213

MTMP							99.54 161	98.88 395

test9_res														97.49 312	99.72 143	99.75 105

agg_prior2														97.21 330	99.73 142	99.75 105

test_prior4						99.56 89	98.99 389

test_prior2							98.96 396		98.34 138	99.01 287	99.52 289	98.68 67		97.96 263	99.74 140

新几何2							99.01 386

旧先验1					99.74 95	99.59 83		99.54 104			99.69 214	98.47 83			99.68 151	99.73 118

原ACMM2							98.95 399

test222					99.75 87	99.49 104	98.91 405	99.49 179	96.42 367	99.34 216	99.65 235	98.28 97			99.69 148	99.72 127

segment_acmp												98.96 25

testdata1							98.85 410		98.32 142

plane_prior7					99.29 291	97.03 337

plane_prior6					99.27 296	96.98 341						92.71 335

plane_prior4											99.61 256

plane_prior3						97.00 339			98.69 102	99.11 267

plane_prior2							99.39 268		98.97 70

plane_prior1					99.26 299

plane_prior						96.97 342	99.21 339		98.45 125						97.60 313

n2								0.00 481

nn								0.00 481

door-mid								98.05 442

test11								99.35 294

door								97.92 443

HQP5-MVS						96.83 353

HQP-NCC					99.19 317		98.98 392		98.24 157	98.66 342

ACMP_Plane					99.19 317		98.98 392		98.24 157	98.66 342

BP-MVS														97.19 334

HQP3-MVS								99.39 270							97.58 315

HQP2-MVS												92.47 344

NP-MVS					99.23 307	96.92 349					99.40 327

MDTV_nov1_ep13_2view						95.18 407	99.35 285		96.84 334	99.58 150		95.19 236		97.82 276		99.46 241

ACMMP++_ref															97.19 343

ACMMP++															97.43 333

Test By Simon												98.75 58

High-resolution multi-view benchmark