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 70	99.38 266	99.37 119	99.58 127	99.62 48	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 67	99.84 35	99.44 112	99.58 127	99.69 19	99.43 16	99.98 12	99.91 25	98.62 74	100.00 1	99.97 2	99.95 22	99.90 25

test_vis1_n_1920		98.63 208	98.40 216	99.31 187	99.86 22	97.94 289	99.67 72	99.62 48	99.43 16	99.99 2	99.91 25	87.29 422	100.00 1	99.92 23	99.92 38	99.98 2

fmvsm_s_conf0.5_n_10		99.41 57	99.24 76	99.92 1	99.83 44	99.84 19	99.53 171	99.56 87	99.45 11	99.99 2	99.92 17	94.92 248	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	99.47 225	99.63 43	99.45 11	99.98 12	99.89 40	97.02 145	99.99 4	99.98 1	99.96 16	99.95 11

NormalMVS		99.27 86	99.19 86	99.52 135	99.89 8	98.83 213	99.65 85	99.52 126	99.10 44	99.84 52	99.76 177	95.80 209	99.99 4	99.30 87	99.84 98	99.74 110

SymmetryMVS		99.15 111	99.02 119	99.52 135	99.72 107	98.83 213	99.65 85	99.34 300	99.10 44	99.84 52	99.76 177	95.80 209	99.99 4	99.30 87	98.72 250	99.73 119

fmvsm_s_conf0.5_n_5		99.37 66	99.21 82	99.86 31	99.80 59	99.68 60	99.42 252	99.61 57	99.37 23	99.97 24	99.86 70	94.96 243	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	99.54 162	99.66 29	99.46 7	99.98 12	99.89 40	97.27 131	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 40	99.86 22	99.61 81	99.56 142	99.63 43	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 40	99.84 35	99.63 78	99.56 142	99.63 43	99.47 4	99.98 12	99.82 107	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 67	99.48 215	99.64 39	99.45 11	99.92 29	99.92 17	98.62 74	99.99 4	99.96 13	99.99 1	99.96 7

patch_mono-2		99.26 89	99.62 5	98.16 349	99.81 53	94.59 422	99.52 173	99.64 39	99.33 25	99.73 93	99.90 32	99.00 22	99.99 4	99.69 34	99.98 4	99.89 28

h-mvs33		97.70 322	97.28 345	98.97 235	99.70 118	97.27 317	99.36 282	99.45 236	98.94 74	99.66 118	99.64 242	94.93 246	99.99 4	99.48 63	84.36 457	99.65 163

xiu_mvs_v1_base_debu		99.29 82	99.27 71	99.34 179	99.63 159	98.97 179	99.12 359	99.51 145	98.86 80	99.84 52	99.47 309	98.18 102	99.99 4	99.50 56	99.31 187	99.08 288

xiu_mvs_v1_base		99.29 82	99.27 71	99.34 179	99.63 159	98.97 179	99.12 359	99.51 145	98.86 80	99.84 52	99.47 309	98.18 102	99.99 4	99.50 56	99.31 187	99.08 288

xiu_mvs_v1_base_debi		99.29 82	99.27 71	99.34 179	99.63 159	98.97 179	99.12 359	99.51 145	98.86 80	99.84 52	99.47 309	98.18 102	99.99 4	99.50 56	99.31 187	99.08 288

EPNet		98.86 173	98.71 180	99.30 192	97.20 448	98.18 269	99.62 103	98.91 391	99.28 28	98.63 352	99.81 122	95.96 197	99.99 4	99.24 97	99.72 144	99.73 119
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n_8		99.54 22	99.42 30	99.89 10	99.83 44	99.74 51	99.51 182	99.62 48	99.46 7	99.99 2	99.90 32	96.60 168	99.98 19	99.95 15	99.95 22	99.96 7

MM		99.40 62	99.28 67	99.74 76	99.67 130	99.31 131	99.52 173	98.87 398	99.55 1	99.74 91	99.80 140	96.47 175	99.98 19	99.97 2	99.97 8	99.94 17

test_cas_vis1_n_1920		99.16 107	99.01 124	99.61 105	99.81 53	98.86 207	99.65 85	99.64 39	99.39 21	99.97 24	99.94 6	93.20 323	99.98 19	99.55 49	99.91 45	99.99 1

test_vis1_n		97.92 280	97.44 321	99.34 179	99.53 208	98.08 276	99.74 47	99.49 180	99.15 34	100.00 1	99.94 6	79.51 458	99.98 19	99.88 25	99.76 136	99.97 4

xiu_mvs_v2_base		99.26 89	99.25 75	99.29 195	99.53 208	98.91 198	99.02 383	99.45 236	98.80 90	99.71 101	99.26 368	98.94 32	99.98 19	99.34 80	99.23 196	98.98 302

PS-MVSNAJ		99.32 77	99.32 52	99.30 192	99.57 192	98.94 193	98.97 397	99.46 225	98.92 77	99.71 101	99.24 370	99.01 18	99.98 19	99.35 75	99.66 155	98.97 303

QAPM		98.67 203	98.30 223	99.80 61	99.20 315	99.67 64	99.77 34	99.72 11	94.74 417	98.73 332	99.90 32	95.78 211	99.98 19	96.96 349	99.88 72	99.76 104

3Dnovator	97.25 9	99.24 94	99.05 108	99.81 57	99.12 337	99.66 67	99.84 12	99.74 10	99.09 51	98.92 305	99.90 32	95.94 200	99.98 19	98.95 136	99.92 38	99.79 89

OpenMVS	96.50 16	98.47 214	98.12 235	99.52 135	99.04 356	99.53 97	99.82 16	99.72 11	94.56 420	98.08 387	99.88 51	94.73 263	99.98 19	97.47 316	99.76 136	99.06 294

fmvsm_s_conf0.5_n_3		99.37 66	99.20 84	99.87 20	99.75 88	99.70 57	99.48 215	99.66 29	99.45 11	99.99 2	99.93 10	94.64 272	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 66	99.88 9	99.56 142	99.55 96	99.15 34	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 21	99.45 28	99.86 31	99.44 248	99.65 71	99.50 192	99.61 57	99.45 11	99.87 45	99.92 17	97.31 128	99.97 28	99.95 15	99.99 1	99.97 4

test_fmvs1_n		98.41 220	98.14 232	99.21 208	99.82 49	97.71 302	99.74 47	99.49 180	99.32 26	99.99 2	99.95 3	85.32 436	99.97 28	99.82 28	99.84 98	99.96 7

CANet_DTU		98.97 161	98.87 157	99.25 202	99.33 279	98.42 261	99.08 368	99.30 327	99.16 33	99.43 185	99.75 182	95.27 231	99.97 28	98.56 204	99.95 22	99.36 260

MGCNet		99.15 111	98.96 135	99.73 79	98.92 374	99.37 119	99.37 276	96.92 455	99.51 2	99.66 118	99.78 164	96.69 164	99.97 28	99.84 27	99.97 8	99.84 52

MTAPA		99.52 26	99.39 38	99.89 10	99.90 4	99.86 17	99.66 79	99.47 214	98.79 91	99.68 107	99.81 122	98.43 87	99.97 28	98.88 146	99.90 56	99.83 62

PGM-MVS		99.45 44	99.31 58	99.86 31	99.87 17	99.78 44	99.58 127	99.65 36	97.84 228	99.71 101	99.80 140	99.12 13	99.97 28	98.33 229	99.87 75	99.83 62

mPP-MVS		99.44 48	99.30 60	99.86 31	99.88 13	99.79 38	99.69 62	99.48 192	98.12 180	99.50 169	99.75 182	98.78 51	99.97 28	98.57 201	99.89 67	99.83 62

CP-MVS		99.45 44	99.32 52	99.85 40	99.83 44	99.75 48	99.69 62	99.52 126	98.07 191	99.53 164	99.63 248	98.93 36	99.97 28	98.74 172	99.91 45	99.83 62

SteuartSystems-ACMMP		99.54 22	99.42 30	99.87 20	99.82 49	99.81 32	99.59 117	99.51 145	98.62 108	99.79 72	99.83 97	99.28 4	99.97 28	98.48 211	99.90 56	99.84 52
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 101	98.97 131	99.82 54	99.17 329	99.68 60	99.81 20	99.51 145	99.20 30	98.72 333	99.89 40	95.68 215	99.97 28	98.86 154	99.86 83	99.81 76

fmvsm_s_conf0.5_n_9		99.41 57	99.28 67	99.81 57	99.84 35	99.52 101	99.48 215	99.62 48	99.46 7	99.99 2	99.92 17	95.24 235	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 70	99.06 57	99.88 39	99.85 77	98.41 91	99.96 40	99.28 90	99.84 98	99.83 62

KinetiMVS		99.12 124	98.92 144	99.70 83	99.67 130	99.40 117	99.67 72	99.63 43	98.73 98	99.94 27	99.81 122	94.54 278	99.96 40	98.40 220	99.93 32	99.74 110

fmvsm_s_conf0.5_n_7		99.34 73	99.29 64	99.48 149	99.70 118	98.63 234	99.42 252	99.63 43	99.46 7	99.98 12	99.88 51	95.59 218	99.96 40	99.97 2	99.98 4	99.85 45

fmvsm_s_conf0.5_n_2		99.32 77	99.13 92	99.89 10	99.80 59	99.77 45	99.44 239	99.58 75	99.47 4	99.99 2	99.93 10	94.04 299	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 78	99.88 9	99.52 173	99.54 105	99.13 37	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 78	99.88 9	99.52 173	99.54 105	99.13 37	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 40	99.83 44	99.64 77	99.52 173	99.65 36	99.10 44	99.98 12	99.92 17	97.35 127	99.96 40	99.94 20	99.92 38	99.95 11

fmvsm_s_conf0.5_n		99.51 27	99.40 36	99.85 40	99.84 35	99.65 71	99.51 182	99.67 24	99.13 37	99.98 12	99.92 17	96.60 168	99.96 40	99.95 15	99.96 16	99.95 11

mvsany_test1		99.50 29	99.46 26	99.62 104	99.61 177	99.09 161	98.94 403	99.48 192	99.10 44	99.96 26	99.91 25	98.85 42	99.96 40	99.72 31	99.58 165	99.82 69

test_fmvs1		98.88 167	98.79 171	99.16 213	99.69 123	97.61 306	99.55 157	99.49 180	99.32 26	99.98 12	99.91 25	91.41 371	99.96 40	99.82 28	99.92 38	99.90 25

DVP-MVS++		99.59 13	99.50 17	99.88 14	99.51 217	99.88 9	99.87 8	99.51 145	98.99 65	99.88 39	99.81 122	99.27 5	99.96 40	98.85 156	99.80 121	99.81 76

MSC_two_6792asdad				99.87 20	99.51 217	99.76 46		99.33 308					99.96 40	98.87 149	99.84 98	99.89 28

No_MVS				99.87 20	99.51 217	99.76 46		99.33 308					99.96 40	98.87 149	99.84 98	99.89 28

ZD-MVS					99.71 113	99.79 38		99.61 57	96.84 335	99.56 155	99.54 282	98.58 76	99.96 40	96.93 352	99.75 138

SED-MVS		99.61 8	99.52 12	99.88 14	99.84 35	99.90 2	99.60 110	99.48 192	99.08 52	99.91 30	99.81 122	99.20 7	99.96 40	98.91 143	99.85 90	99.79 89

test_241102_TWO								99.48 192	99.08 52	99.88 39	99.81 122	98.94 32	99.96 40	98.91 143	99.84 98	99.88 34

ZNCC-MVS		99.47 38	99.33 50	99.87 20	99.87 17	99.81 32	99.64 92	99.67 24	98.08 190	99.55 161	99.64 242	98.91 37	99.96 40	98.72 175	99.90 56	99.82 69

DVP-MVS		99.57 18	99.47 22	99.88 14	99.85 28	99.89 5	99.57 135	99.37 287	99.10 44	99.81 65	99.80 140	98.94 32	99.96 40	98.93 140	99.86 83	99.81 76
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 65	99.81 65	99.80 140	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	99.57 135	99.51 145					99.96 40	98.93 140	99.86 83	99.88 34

SR-MVS		99.43 51	99.29 64	99.86 31	99.75 88	99.83 21	99.59 117	99.62 48	98.21 164	99.73 93	99.79 157	98.68 68	99.96 40	98.44 217	99.77 133	99.79 89

DPE-MVS		99.46 40	99.32 52	99.91 5	99.78 66	99.88 9	99.36 282	99.51 145	98.73 98	99.88 39	99.84 92	98.72 65	99.96 40	98.16 244	99.87 75	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 53	99.29 64	99.80 61	99.62 167	99.55 92	99.50 192	99.70 15	98.79 91	99.77 81	99.96 1	97.45 122	99.96 40	98.92 142	99.90 56	99.89 28

HFP-MVS		99.49 31	99.37 42	99.86 31	99.87 17	99.80 35	99.66 79	99.67 24	98.15 171	99.68 107	99.69 215	99.06 16	99.96 40	98.69 180	99.87 75	99.84 52

region2R		99.48 35	99.35 46	99.87 20	99.88 13	99.80 35	99.65 85	99.66 29	98.13 178	99.66 118	99.68 223	98.96 25	99.96 40	98.62 189	99.87 75	99.84 52

HPM-MVS++		99.39 64	99.23 80	99.87 20	99.75 88	99.84 19	99.43 245	99.51 145	98.68 105	99.27 234	99.53 286	98.64 73	99.96 40	98.44 217	99.80 121	99.79 89

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 74	99.89 5	99.75 42	99.56 87	99.02 58	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 31	99.36 44	99.86 31	99.87 17	99.79 38	99.66 79	99.67 24	98.15 171	99.67 113	99.69 215	98.95 30	99.96 40	98.69 180	99.87 75	99.84 52

MP-MVS		99.33 75	99.15 90	99.87 20	99.88 13	99.82 27	99.66 79	99.46 225	98.09 186	99.48 173	99.74 187	98.29 97	99.96 40	97.93 266	99.87 75	99.82 69
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 130	98.90 149	99.74 76	99.80 59	99.46 110	99.59 117	99.49 180	97.03 322	99.63 135	99.69 215	97.27 131	99.96 40	97.82 277	99.84 98	99.81 76

PVSNet_Blended_VisFu		99.36 70	99.28 67	99.61 105	99.86 22	99.07 166	99.47 225	99.93 2	97.66 253	99.71 101	99.86 70	97.73 117	99.96 40	99.47 65	99.82 113	99.79 89

UGNet		98.87 170	98.69 182	99.40 169	99.22 312	98.72 226	99.44 239	99.68 21	99.24 29	99.18 259	99.42 320	92.74 333	99.96 40	99.34 80	99.94 30	99.53 213
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 77	99.32 52	99.32 185	99.85 28	98.29 264	99.71 57	99.66 29	98.11 182	99.41 193	99.80 140	98.37 94	99.96 40	98.99 128	99.96 16	99.72 128

ACMMP		99.45 44	99.32 52	99.82 54	99.89 8	99.67 64	99.62 103	99.69 19	98.12 180	99.63 135	99.84 92	98.73 64	99.96 40	98.55 207	99.83 109	99.81 76
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 22	99.44 29	99.85 40	99.51 217	99.67 64	99.50 192	99.64 39	99.43 16	99.98 12	99.78 164	97.26 133	99.95 75	99.95 15	99.93 32	99.92 23

fmvsm_s_conf0.5_n_4		99.36 70	99.24 76	99.73 79	99.78 66	99.53 97	99.49 209	99.60 64	99.42 19	99.99 2	99.86 70	95.15 238	99.95 75	99.95 15	99.89 67	99.73 119

fmvsm_s_conf0.1_n_2		99.37 66	99.22 81	99.81 57	99.77 74	99.75 48	99.46 229	99.60 64	99.47 4	99.98 12	99.94 6	94.98 242	99.95 75	99.97 2	99.79 128	99.73 119

test_fmvsmconf0.01_n		99.22 97	99.03 113	99.79 64	98.42 428	99.48 107	99.55 157	99.51 145	99.39 21	99.78 77	99.93 10	94.80 255	99.95 75	99.93 22	99.95 22	99.94 17

SR-MVS-dyc-post		99.45 44	99.31 58	99.85 40	99.76 78	99.82 27	99.63 98	99.52 126	98.38 133	99.76 87	99.82 107	98.53 80	99.95 75	98.61 192	99.81 116	99.77 97

GST-MVS		99.40 62	99.24 76	99.85 40	99.86 22	99.79 38	99.60 110	99.67 24	97.97 212	99.63 135	99.68 223	98.52 81	99.95 75	98.38 222	99.86 83	99.81 76

CANet		99.25 93	99.14 91	99.59 109	99.41 256	99.16 151	99.35 287	99.57 82	98.82 85	99.51 168	99.61 257	96.46 176	99.95 75	99.59 44	99.98 4	99.65 163

MP-MVS-pluss		99.37 66	99.20 84	99.88 14	99.90 4	99.87 16	99.30 301	99.52 126	97.18 304	99.60 147	99.79 157	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 53	99.27 71	99.88 14	99.89 8	99.80 35	99.67 72	99.50 168	98.70 102	99.77 81	99.49 300	98.21 100	99.95 75	98.46 215	99.77 133	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	96.67 364

APD-MVS_3200maxsize		99.48 35	99.35 46	99.85 40	99.76 78	99.83 21	99.63 98	99.54 105	98.36 137	99.79 72	99.82 107	98.86 41	99.95 75	98.62 189	99.81 116	99.78 95

RPMNet		96.72 374	95.90 387	99.19 210	99.18 321	98.49 253	99.22 339	99.52 126	88.72 454	99.56 155	97.38 451	94.08 298	99.95 75	86.87 459	98.58 257	99.14 280

sss		99.17 105	99.05 108	99.53 129	99.62 167	98.97 179	99.36 282	99.62 48	97.83 229	99.67 113	99.65 236	97.37 126	99.95 75	99.19 101	99.19 199	99.68 149

MVSMamba_PlusPlus		99.46 40	99.41 35	99.64 97	99.68 128	99.50 104	99.75 42	99.50 168	98.27 148	99.87 45	99.92 17	98.09 106	99.94 88	99.65 40	99.95 22	99.47 237

fmvsm_s_conf0.1_n_a		99.26 89	99.06 106	99.85 40	99.52 214	99.62 79	99.54 162	99.62 48	98.69 103	99.99 2	99.96 1	94.47 282	99.94 88	99.88 25	99.92 38	99.98 2

fmvsm_s_conf0.1_n		99.29 82	99.10 96	99.86 31	99.70 118	99.65 71	99.53 171	99.62 48	98.74 97	99.99 2	99.95 3	94.53 280	99.94 88	99.89 24	99.96 16	99.97 4

TSAR-MVS + MP.		99.58 14	99.50 17	99.81 57	99.91 1	99.66 67	99.63 98	99.39 271	98.91 78	99.78 77	99.85 77	99.36 2	99.94 88	98.84 159	99.88 72	99.82 69
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 165	98.75 174	99.39 174	99.46 241	98.61 238	99.76 37	99.50 168	98.06 195	99.81 65	99.88 51	93.91 306	99.94 88	99.11 113	99.27 190	99.61 180

mamv4		99.33 75	99.42 30	99.07 221	99.67 130	97.73 297	99.42 252	99.60 64	98.15 171	99.94 27	99.91 25	98.42 89	99.94 88	99.72 31	99.96 16	99.54 207

XVS		99.53 25	99.42 30	99.87 20	99.85 28	99.83 21	99.69 62	99.68 21	98.98 68	99.37 204	99.74 187	98.81 47	99.94 88	98.79 168	99.86 83	99.84 52

X-MVStestdata		96.55 377	95.45 396	99.87 20	99.85 28	99.83 21	99.69 62	99.68 21	98.98 68	99.37 204	64.01 474	98.81 47	99.94 88	98.79 168	99.86 83	99.84 52

旧先验2							98.96 398		96.70 342	99.47 174			99.94 88	98.19 240

新几何1				99.75 73	99.75 88	99.59 84		99.54 105	96.76 338	99.29 227	99.64 242	98.43 87	99.94 88	96.92 354	99.66 155	99.72 128

testdata				99.54 121	99.75 88	98.95 189		99.51 145	97.07 316	99.43 185	99.70 204	98.87 40	99.94 88	97.76 286	99.64 158	99.72 128

HPM-MVS		99.42 53	99.28 67	99.83 53	99.90 4	99.72 53	99.81 20	99.54 105	97.59 259	99.68 107	99.63 248	98.91 37	99.94 88	98.58 198	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 98	99.10 96	99.45 157	99.89 8	98.52 248	99.39 269	99.94 1	98.73 98	99.11 268	99.89 40	95.50 221	99.94 88	99.50 56	99.97 8	99.89 28

APD-MVS		99.27 86	99.08 102	99.84 52	99.75 88	99.79 38	99.50 192	99.50 168	97.16 306	99.77 81	99.82 107	98.78 51	99.94 88	97.56 307	99.86 83	99.80 85
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 35	99.42 30	99.65 91	99.72 107	99.40 117	99.05 375	99.66 29	99.14 36	99.57 154	99.80 140	98.46 85	99.94 88	99.57 47	99.84 98	99.60 183
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		99.06 143	98.88 156	99.61 105	99.62 167	99.16 151	99.37 276	99.56 87	98.04 204	99.53 164	99.62 253	96.84 156	99.94 88	98.85 156	98.49 265	99.72 128

DeepC-MVS	98.35 2	99.30 80	99.19 86	99.64 97	99.82 49	99.23 144	99.62 103	99.55 96	98.94 74	99.63 135	99.95 3	95.82 207	99.94 88	99.37 74	99.97 8	99.73 119
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 86	99.12 94	99.74 76	99.18 321	99.75 48	99.56 142	99.57 82	98.45 126	99.49 172	99.85 77	97.77 116	99.94 88	98.33 229	99.84 98	99.52 214

MED-MVS		99.56 19	99.46 26	99.86 31	99.80 59	99.81 32	99.37 276	99.70 15	99.18 31	99.83 60	99.83 97	98.74 63	99.93 106	98.83 162	99.89 67	99.83 62

GDP-MVS		99.08 138	98.89 153	99.64 97	99.53 208	99.34 123	99.64 92	99.48 192	98.32 143	99.77 81	99.66 234	95.14 239	99.93 106	98.97 134	99.50 172	99.64 170

SDMVSNet		99.11 130	98.90 149	99.75 73	99.81 53	99.59 84	99.81 20	99.65 36	98.78 94	99.64 132	99.88 51	94.56 275	99.93 106	99.67 36	98.26 280	99.72 128

FE-MVS		98.48 213	98.17 228	99.40 169	99.54 207	98.96 183	99.68 69	98.81 405	95.54 401	99.62 139	99.70 204	93.82 309	99.93 106	97.35 325	99.46 174	99.32 266

SF-MVS		99.38 65	99.24 76	99.79 64	99.79 64	99.68 60	99.57 135	99.54 105	97.82 234	99.71 101	99.80 140	98.95 30	99.93 106	98.19 240	99.84 98	99.74 110

dcpmvs_2		99.23 95	99.58 7	98.16 349	99.83 44	94.68 419	99.76 37	99.52 126	99.07 54	99.98 12	99.88 51	98.56 78	99.93 106	99.67 36	99.98 4	99.87 39

Anonymous20240529		98.09 250	97.68 288	99.34 179	99.66 143	98.44 258	99.40 265	99.43 256	93.67 427	99.22 246	99.89 40	90.23 388	99.93 106	99.26 96	98.33 272	99.66 157

ACMMP_NAP		99.47 38	99.34 48	99.88 14	99.87 17	99.86 17	99.47 225	99.48 192	98.05 197	99.76 87	99.86 70	98.82 46	99.93 106	98.82 167	99.91 45	99.84 52

EI-MVSNet-UG-set		99.58 14	99.57 8	99.64 97	99.78 66	99.14 156	99.60 110	99.45 236	99.01 60	99.90 33	99.83 97	98.98 24	99.93 106	99.59 44	99.95 22	99.86 41

无先验							98.99 391	99.51 145	96.89 332				99.93 106	97.53 310		99.72 128

VDDNet		97.55 337	97.02 359	99.16 213	99.49 231	98.12 275	99.38 274	99.30 327	95.35 403	99.68 107	99.90 32	82.62 449	99.93 106	99.31 84	98.13 292	99.42 249

ab-mvs		98.86 173	98.63 192	99.54 121	99.64 155	99.19 146	99.44 239	99.54 105	97.77 238	99.30 224	99.81 122	94.20 292	99.93 106	99.17 107	98.82 244	99.49 228

F-COLMAP		99.19 98	99.04 110	99.64 97	99.78 66	99.27 139	99.42 252	99.54 105	97.29 295	99.41 193	99.59 262	98.42 89	99.93 106	98.19 240	99.69 149	99.73 119

BP-MVS1		99.12 124	98.94 141	99.65 91	99.51 217	99.30 134	99.67 72	98.92 386	98.48 122	99.84 52	99.69 215	94.96 243	99.92 119	99.62 43	99.79 128	99.71 137

Anonymous202405211		98.30 231	97.98 252	99.26 201	99.57 192	98.16 270	99.41 257	98.55 430	96.03 395	99.19 255	99.74 187	91.87 358	99.92 119	99.16 108	98.29 279	99.70 140

EI-MVSNet-Vis-set		99.58 14	99.56 10	99.64 97	99.78 66	99.15 155	99.61 109	99.45 236	99.01 60	99.89 36	99.82 107	99.01 18	99.92 119	99.56 48	99.95 22	99.85 45

VDD-MVS		97.73 316	97.35 333	98.88 257	99.47 239	97.12 325	99.34 290	98.85 400	98.19 166	99.67 113	99.85 77	82.98 447	99.92 119	99.49 60	98.32 276	99.60 183

VNet		99.11 130	98.90 149	99.73 79	99.52 214	99.56 90	99.41 257	99.39 271	99.01 60	99.74 91	99.78 164	95.56 219	99.92 119	99.52 54	98.18 288	99.72 128

XVG-OURS-SEG-HR		98.69 201	98.62 197	98.89 254	99.71 113	97.74 296	99.12 359	99.54 105	98.44 129	99.42 188	99.71 200	94.20 292	99.92 119	98.54 208	98.90 238	99.00 299

mvsmamba		99.06 143	98.96 135	99.36 176	99.47 239	98.64 233	99.70 58	99.05 370	97.61 258	99.65 127	99.83 97	96.54 172	99.92 119	99.19 101	99.62 161	99.51 223

HPM-MVS_fast		99.51 27	99.40 36	99.85 40	99.91 1	99.79 38	99.76 37	99.56 87	97.72 244	99.76 87	99.75 182	99.13 12	99.92 119	99.07 119	99.92 38	99.85 45

HY-MVS	97.30 7	98.85 182	98.64 191	99.47 154	99.42 251	99.08 164	99.62 103	99.36 288	97.39 287	99.28 228	99.68 223	96.44 178	99.92 119	98.37 224	98.22 283	99.40 254

DP-MVS		99.16 107	98.95 139	99.78 67	99.77 74	99.53 97	99.41 257	99.50 168	97.03 322	99.04 285	99.88 51	97.39 123	99.92 119	98.66 184	99.90 56	99.87 39

IB-MVS	95.67 18	96.22 383	95.44 397	98.57 299	99.21 313	96.70 359	98.65 432	97.74 449	96.71 341	97.27 413	98.54 425	86.03 430	99.92 119	98.47 214	86.30 455	99.10 283
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 31	99.39 38	99.77 70	99.63 159	99.59 84	99.36 282	99.46 225	99.07 54	99.79 72	99.82 107	98.85 42	99.92 119	98.68 182	99.87 75	99.82 69
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 95	99.10 96	99.61 105	99.35 273	99.31 131	99.46 229	99.13 358	98.61 109	99.86 49	99.89 40	96.41 181	99.91 131	99.67 36	99.51 170	99.63 175

balanced_conf03		99.46 40	99.39 38	99.67 86	99.55 200	99.58 89	99.74 47	99.51 145	98.42 130	99.87 45	99.84 92	98.05 109	99.91 131	99.58 46	99.94 30	99.52 214

9.14			99.10 96		99.72 107		99.40 265	99.51 145	97.53 269	99.64 132	99.78 164	98.84 44	99.91 131	97.63 298	99.82 113

SMA-MVS		99.44 48	99.30 60	99.85 40	99.73 103	99.83 21	99.56 142	99.47 214	97.45 278	99.78 77	99.82 107	99.18 10	99.91 131	98.79 168	99.89 67	99.81 76
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					99.67 130	99.65 71	99.05 375	99.41 261	96.22 380	98.95 301	99.49 300	98.77 54	99.91 131

train_agg		99.02 151	98.77 172	99.77 70	99.67 130	99.65 71	99.05 375	99.41 261	96.28 374	98.95 301	99.49 300	98.76 55	99.91 131	97.63 298	99.72 144	99.75 106

test_8					99.67 130	99.61 81	99.03 380	99.41 261	96.28 374	98.93 304	99.48 306	98.76 55	99.91 131

agg_prior					99.67 130	99.62 79		99.40 268		98.87 314			99.91 131

原ACMM1				99.65 91	99.73 103	99.33 126		99.47 214	97.46 275	99.12 266	99.66 234	98.67 70	99.91 131	97.70 295	99.69 149	99.71 137

LFMVS		97.90 283	97.35 333	99.54 121	99.52 214	99.01 173	99.39 269	98.24 438	97.10 314	99.65 127	99.79 157	84.79 439	99.91 131	99.28 90	98.38 269	99.69 143

XVG-OURS		98.73 199	98.68 183	98.88 257	99.70 118	97.73 297	98.92 405	99.55 96	98.52 118	99.45 177	99.84 92	95.27 231	99.91 131	98.08 255	98.84 242	99.00 299

PLC	97.94 4	99.02 151	98.85 163	99.53 129	99.66 143	99.01 173	99.24 332	99.52 126	96.85 334	99.27 234	99.48 306	98.25 99	99.91 131	97.76 286	99.62 161	99.65 163
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 330	97.06 358	99.47 154	99.61 177	99.09 161	98.04 458	99.25 339	91.24 445	98.51 363	99.70 204	94.55 277	99.91 131	92.76 434	99.85 90	99.42 249
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Elysia		98.88 167	98.65 189	99.58 112	99.58 187	99.34 123	99.65 85	99.52 126	98.26 151	99.83 60	99.87 62	93.37 317	99.90 144	97.81 279	99.91 45	99.49 228

StellarMVS		98.88 167	98.65 189	99.58 112	99.58 187	99.34 123	99.65 85	99.52 126	98.26 151	99.83 60	99.87 62	93.37 317	99.90 144	97.81 279	99.91 45	99.49 228

AstraMVS		99.09 136	99.03 113	99.25 202	99.66 143	98.13 273	99.57 135	98.24 438	98.82 85	99.91 30	99.88 51	95.81 208	99.90 144	99.72 31	99.67 154	99.74 110

mmtdpeth		96.95 369	96.71 368	97.67 388	99.33 279	94.90 414	99.89 2	99.28 333	98.15 171	99.72 98	98.57 424	86.56 427	99.90 144	99.82 28	89.02 450	98.20 419

UWE-MVS		97.58 336	97.29 344	98.48 312	99.09 345	96.25 379	99.01 388	96.61 461	97.86 222	99.19 255	99.01 395	88.72 403	99.90 144	97.38 323	98.69 251	99.28 269

test_vis1_rt		95.81 393	95.65 392	96.32 422	99.67 130	91.35 450	99.49 209	96.74 459	98.25 156	95.24 437	98.10 443	74.96 459	99.90 144	99.53 52	98.85 241	97.70 443

FA-MVS(test-final)		98.75 196	98.53 208	99.41 168	99.55 200	99.05 169	99.80 25	99.01 375	96.59 356	99.58 151	99.59 262	95.39 225	99.90 144	97.78 282	99.49 173	99.28 269

MCST-MVS		99.43 51	99.30 60	99.82 54	99.79 64	99.74 51	99.29 306	99.40 268	98.79 91	99.52 166	99.62 253	98.91 37	99.90 144	98.64 186	99.75 138	99.82 69

CDPH-MVS		99.13 117	98.91 147	99.80 61	99.75 88	99.71 55	99.15 353	99.41 261	96.60 354	99.60 147	99.55 277	98.83 45	99.90 144	97.48 314	99.83 109	99.78 95

NCCC		99.34 73	99.19 86	99.79 64	99.61 177	99.65 71	99.30 301	99.48 192	98.86 80	99.21 249	99.63 248	98.72 65	99.90 144	98.25 236	99.63 160	99.80 85

114514_t		98.93 163	98.67 184	99.72 82	99.85 28	99.53 97	99.62 103	99.59 70	92.65 440	99.71 101	99.78 164	98.06 108	99.90 144	98.84 159	99.91 45	99.74 110

1112_ss		98.98 159	98.77 172	99.59 109	99.68 128	99.02 171	99.25 327	99.48 192	97.23 301	99.13 264	99.58 266	96.93 150	99.90 144	98.87 149	98.78 247	99.84 52

PHI-MVS		99.30 80	99.17 89	99.70 83	99.56 196	99.52 101	99.58 127	99.80 8	97.12 310	99.62 139	99.73 193	98.58 76	99.90 144	98.61 192	99.91 45	99.68 149

AdaColmap		99.01 155	98.80 168	99.66 87	99.56 196	99.54 94	99.18 348	99.70 15	98.18 169	99.35 213	99.63 248	96.32 183	99.90 144	97.48 314	99.77 133	99.55 205

COLMAP_ROB	97.56 6	98.86 173	98.75 174	99.17 212	99.88 13	98.53 244	99.34 290	99.59 70	97.55 265	98.70 340	99.89 40	95.83 206	99.90 144	98.10 250	99.90 56	99.08 288
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 227	98.03 247	99.31 187	99.63 159	98.56 241	99.54 162	96.75 458	97.53 269	99.73 93	99.65 236	91.25 376	99.89 159	98.62 189	99.56 166	99.48 231

tttt0517		98.42 218	98.14 232	99.28 199	99.66 143	98.38 262	99.74 47	96.85 456	97.68 250	99.79 72	99.74 187	91.39 372	99.89 159	98.83 162	99.56 166	99.57 201

test12				99.75 73	99.64 155	99.61 81		99.29 331		99.21 249		98.38 93	99.89 159		99.74 141	99.74 110

Test_1112_low_res		98.89 166	98.66 187	99.57 116	99.69 123	98.95 189	99.03 380	99.47 214	96.98 324	99.15 262	99.23 371	96.77 161	99.89 159	98.83 162	98.78 247	99.86 41

CNLPA		99.14 115	98.99 127	99.59 109	99.58 187	99.41 116	99.16 350	99.44 245	98.45 126	99.19 255	99.49 300	98.08 107	99.89 159	97.73 290	99.75 138	99.48 231

diffmvs_AUTHOR		99.19 98	99.10 96	99.48 149	99.64 155	98.85 208	99.32 295	99.48 192	98.50 120	99.81 65	99.81 122	96.82 157	99.88 164	99.40 70	99.12 209	99.71 137

guyue		99.16 107	99.04 110	99.52 135	99.69 123	98.92 197	99.59 117	98.81 405	98.73 98	99.90 33	99.87 62	95.34 228	99.88 164	99.66 39	99.81 116	99.74 110

sd_testset		98.75 196	98.57 204	99.29 195	99.81 53	98.26 266	99.56 142	99.62 48	98.78 94	99.64 132	99.88 51	92.02 355	99.88 164	99.54 50	98.26 280	99.72 128

APD_test1		95.87 391	96.49 373	94.00 430	99.53 208	84.01 459	99.54 162	99.32 318	95.91 397	97.99 392	99.85 77	85.49 434	99.88 164	91.96 437	98.84 242	98.12 423

diffmvs		99.14 115	99.02 119	99.51 140	99.61 177	98.96 183	99.28 311	99.49 180	98.46 124	99.72 98	99.71 200	96.50 174	99.88 164	99.31 84	99.11 211	99.67 153
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		98.86 173	98.80 168	99.03 227	99.76 78	98.79 219	99.28 311	99.91 3	97.42 284	99.67 113	99.37 338	97.53 120	99.88 164	98.98 129	97.29 340	98.42 404

PVSNet_Blended		99.08 138	98.97 131	99.42 167	99.76 78	98.79 219	98.78 419	99.91 3	96.74 339	99.67 113	99.49 300	97.53 120	99.88 164	98.98 129	99.85 90	99.60 183

viewdifsd2359ckpt07		99.11 130	99.00 126	99.43 165	99.63 159	98.73 224	99.45 232	99.54 105	98.33 141	99.62 139	99.81 122	96.17 188	99.87 171	99.27 93	99.14 204	99.69 143

viewdifsd2359ckpt11		98.78 191	98.74 176	98.89 254	99.67 130	97.04 335	99.50 192	99.58 75	98.26 151	99.56 155	99.90 32	94.36 285	99.87 171	99.49 60	98.32 276	99.77 97

viewmsd2359difaftdt		98.78 191	98.74 176	98.90 250	99.67 130	97.04 335	99.50 192	99.58 75	98.26 151	99.56 155	99.90 32	94.36 285	99.87 171	99.49 60	98.32 276	99.77 97

MVS		97.28 358	96.55 371	99.48 149	98.78 395	98.95 189	99.27 316	99.39 271	83.53 461	98.08 387	99.54 282	96.97 148	99.87 171	94.23 415	99.16 200	99.63 175

MG-MVS		99.13 117	99.02 119	99.45 157	99.57 192	98.63 234	99.07 369	99.34 300	98.99 65	99.61 144	99.82 107	97.98 111	99.87 171	97.00 345	99.80 121	99.85 45

MSDG		98.98 159	98.80 168	99.53 129	99.76 78	99.19 146	98.75 422	99.55 96	97.25 298	99.47 174	99.77 173	97.82 114	99.87 171	96.93 352	99.90 56	99.54 207

ETV-MVS		99.26 89	99.21 82	99.40 169	99.46 241	99.30 134	99.56 142	99.52 126	98.52 118	99.44 182	99.27 366	98.41 91	99.86 177	99.10 116	99.59 164	99.04 295

thisisatest0515		98.14 245	97.79 271	99.19 210	99.50 229	98.50 252	98.61 434	96.82 457	96.95 328	99.54 162	99.43 318	91.66 367	99.86 177	98.08 255	99.51 170	99.22 277

thres600view7		97.86 289	97.51 307	98.92 244	99.72 107	97.95 287	99.59 117	98.74 415	97.94 214	99.27 234	98.62 421	91.75 361	99.86 177	93.73 421	98.19 287	98.96 305

lupinMVS		99.13 117	99.01 124	99.46 156	99.51 217	98.94 193	99.05 375	99.16 354	97.86 222	99.80 70	99.56 274	97.39 123	99.86 177	98.94 137	99.85 90	99.58 198

PVSNet	96.02 17	98.85 182	98.84 165	98.89 254	99.73 103	97.28 316	98.32 450	99.60 64	97.86 222	99.50 169	99.57 271	96.75 162	99.86 177	98.56 204	99.70 148	99.54 207

MAR-MVS		98.86 173	98.63 192	99.54 121	99.37 269	99.66 67	99.45 232	99.54 105	96.61 351	99.01 288	99.40 328	97.09 140	99.86 177	97.68 297	99.53 169	99.10 283
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		99.08 138	98.96 135	99.44 162	99.62 167	98.88 200	99.25 327	99.47 214	98.05 197	99.37 204	99.81 122	96.85 152	99.85 183	98.98 129	99.25 193	99.60 183

SSM_0404		99.16 107	99.06 106	99.44 162	99.65 151	98.96 183	99.49 209	99.50 168	98.14 176	99.62 139	99.85 77	96.85 152	99.85 183	99.19 101	99.26 192	99.52 214

testing91		97.44 350	97.02 359	98.71 286	99.18 321	96.89 353	99.19 346	99.04 371	97.78 237	98.31 374	98.29 435	85.41 435	99.85 183	98.01 261	97.95 297	99.39 255

test2506		96.81 373	96.65 369	97.29 403	99.74 96	92.21 447	99.60 110	85.06 478	99.13 37	99.77 81	99.93 10	87.82 420	99.85 183	99.38 73	99.38 179	99.80 85

AllTest		98.87 170	98.72 178	99.31 187	99.86 22	98.48 255	99.56 142	99.61 57	97.85 225	99.36 210	99.85 77	95.95 198	99.85 183	96.66 365	99.83 109	99.59 194

TestCases				99.31 187	99.86 22	98.48 255		99.61 57	97.85 225	99.36 210	99.85 77	95.95 198	99.85 183	96.66 365	99.83 109	99.59 194

jason		99.13 117	99.03 113	99.45 157	99.46 241	98.87 204	99.12 359	99.26 337	98.03 206	99.79 72	99.65 236	97.02 145	99.85 183	99.02 126	99.90 56	99.65 163
jason: jason.
CNVR-MVS		99.42 53	99.30 60	99.78 67	99.62 167	99.71 55	99.26 325	99.52 126	98.82 85	99.39 200	99.71 200	98.96 25	99.85 183	98.59 197	99.80 121	99.77 97

PAPM_NR		99.04 148	98.84 165	99.66 87	99.74 96	99.44 112	99.39 269	99.38 279	97.70 248	99.28 228	99.28 363	98.34 95	99.85 183	96.96 349	99.45 175	99.69 143

viewcassd2359sk11		99.18 101	99.08 102	99.49 148	99.65 151	98.95 189	99.48 215	99.51 145	98.10 185	99.72 98	99.87 62	97.13 136	99.84 192	99.13 110	99.14 204	99.69 143

testing99		97.36 353	96.94 362	98.63 292	99.18 321	96.70 359	99.30 301	98.93 383	97.71 245	98.23 379	98.26 436	84.92 438	99.84 192	98.04 260	97.85 304	99.35 261

testing222		97.16 363	96.50 372	99.16 213	99.16 331	98.47 257	99.27 316	98.66 426	97.71 245	98.23 379	98.15 439	82.28 452	99.84 192	97.36 324	97.66 310	99.18 279

test1111		98.04 260	98.11 236	97.83 378	99.74 96	93.82 431	99.58 127	95.40 465	99.12 42	99.65 127	99.93 10	90.73 381	99.84 192	99.43 68	99.38 179	99.82 69

ECVR-MVS		98.04 260	98.05 245	98.00 362	99.74 96	94.37 426	99.59 117	94.98 466	99.13 37	99.66 118	99.93 10	90.67 382	99.84 192	99.40 70	99.38 179	99.80 85

test_yl		98.86 173	98.63 192	99.54 121	99.49 231	99.18 148	99.50 192	99.07 367	98.22 162	99.61 144	99.51 294	95.37 226	99.84 192	98.60 195	98.33 272	99.59 194

DCV-MVSNet		98.86 173	98.63 192	99.54 121	99.49 231	99.18 148	99.50 192	99.07 367	98.22 162	99.61 144	99.51 294	95.37 226	99.84 192	98.60 195	98.33 272	99.59 194

Fast-Effi-MVS+		98.70 200	98.43 213	99.51 140	99.51 217	99.28 137	99.52 173	99.47 214	96.11 390	99.01 288	99.34 348	96.20 187	99.84 192	97.88 269	98.82 244	99.39 255

TSAR-MVS + GP.		99.36 70	99.36 44	99.36 176	99.67 130	98.61 238	99.07 369	99.33 308	99.00 63	99.82 64	99.81 122	99.06 16	99.84 192	99.09 117	99.42 177	99.65 163

tpmrst		98.33 228	98.48 211	97.90 371	99.16 331	94.78 415	99.31 299	99.11 360	97.27 296	99.45 177	99.59 262	95.33 229	99.84 192	98.48 211	98.61 254	99.09 287

Vis-MVSNet		99.12 124	98.97 131	99.56 118	99.78 66	99.10 160	99.68 69	99.66 29	98.49 121	99.86 49	99.87 62	94.77 260	99.84 192	99.19 101	99.41 178	99.74 110
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 208	98.34 219	99.51 140	99.40 261	99.03 170	98.80 417	99.36 288	96.33 371	99.00 292	99.12 385	98.46 85	99.84 192	95.23 401	99.37 186	99.66 157

PatchMatch-RL		98.84 185	98.62 197	99.52 135	99.71 113	99.28 137	99.06 373	99.77 9	97.74 243	99.50 169	99.53 286	95.41 224	99.84 192	97.17 338	99.64 158	99.44 247

EPP-MVSNet		99.13 117	98.99 127	99.53 129	99.65 151	99.06 167	99.81 20	99.33 308	97.43 282	99.60 147	99.88 51	97.14 135	99.84 192	99.13 110	98.94 229	99.69 143

SSM_0407		99.13 117	99.03 113	99.43 165	99.62 167	98.88 200	99.51 182	99.50 168	98.14 176	99.37 204	99.85 77	96.85 152	99.83 206	99.19 101	99.25 193	99.60 183

testing3-2		97.84 294	97.70 286	98.24 344	99.53 208	95.37 403	99.55 157	98.67 425	98.46 124	99.27 234	99.34 348	86.58 426	99.83 206	99.32 83	98.63 253	99.52 214

testing11		97.50 343	97.10 356	98.71 286	99.20 315	96.91 351	99.29 306	98.82 403	97.89 219	98.21 382	98.40 430	85.63 433	99.83 206	98.45 216	98.04 295	99.37 259

thres100view900		97.76 308	97.45 316	98.69 288	99.72 107	97.86 293	99.59 117	98.74 415	97.93 215	99.26 239	98.62 421	91.75 361	99.83 206	93.22 426	98.18 288	98.37 410

tfpn200view9		97.72 318	97.38 329	98.72 283	99.69 123	97.96 284	99.50 192	98.73 421	97.83 229	99.17 260	98.45 428	91.67 365	99.83 206	93.22 426	98.18 288	98.37 410

test_prior				99.68 85	99.67 130	99.48 107		99.56 87					99.83 206			99.74 110

1314		98.68 202	98.54 207	99.11 219	98.89 378	98.65 231	99.27 316	99.49 180	96.89 332	97.99 392	99.56 274	97.72 118	99.83 206	97.74 289	99.27 190	98.84 311

thres400		97.77 307	97.38 329	98.92 244	99.69 123	97.96 284	99.50 192	98.73 421	97.83 229	99.17 260	98.45 428	91.67 365	99.83 206	93.22 426	98.18 288	98.96 305

casdiffmvs		99.13 117	98.98 130	99.56 118	99.65 151	99.16 151	99.56 142	99.50 168	98.33 141	99.41 193	99.86 70	95.92 201	99.83 206	99.45 67	99.16 200	99.70 140
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 31	99.48 20	99.54 121	99.78 66	99.30 134	99.89 2	99.58 75	98.56 114	99.73 93	99.69 215	98.55 79	99.82 215	99.69 34	99.85 90	99.48 231

MVS_Test		99.10 135	98.97 131	99.48 149	99.49 231	99.14 156	99.67 72	99.34 300	97.31 293	99.58 151	99.76 177	97.65 119	99.82 215	98.87 149	99.07 220	99.46 242

dp		97.75 312	97.80 270	97.59 394	99.10 342	93.71 434	99.32 295	98.88 396	96.48 363	99.08 276	99.55 277	92.67 339	99.82 215	96.52 369	98.58 257	99.24 275

RPSCF		98.22 235	98.62 197	96.99 409	99.82 49	91.58 449	99.72 53	99.44 245	96.61 351	99.66 118	99.89 40	95.92 201	99.82 215	97.46 317	99.10 217	99.57 201

PMMVS		98.80 189	98.62 197	99.34 179	99.27 297	98.70 227	98.76 421	99.31 322	97.34 290	99.21 249	99.07 387	97.20 134	99.82 215	98.56 204	98.87 239	99.52 214

UBG		97.85 290	97.48 310	98.95 238	99.25 304	97.64 304	99.24 332	98.74 415	97.90 218	98.64 350	98.20 438	88.65 407	99.81 220	98.27 234	98.40 267	99.42 249

EIA-MVS		99.18 101	99.09 101	99.45 157	99.49 231	99.18 148	99.67 72	99.53 121	97.66 253	99.40 198	99.44 316	98.10 105	99.81 220	98.94 137	99.62 161	99.35 261

Effi-MVS+		98.81 186	98.59 203	99.48 149	99.46 241	99.12 159	98.08 457	99.50 168	97.50 273	99.38 202	99.41 324	96.37 182	99.81 220	99.11 113	98.54 262	99.51 223

thres200		97.61 334	97.28 345	98.62 293	99.64 155	98.03 278	99.26 325	98.74 415	97.68 250	99.09 274	98.32 434	91.66 367	99.81 220	92.88 431	98.22 283	98.03 429

tpmvs		97.98 271	98.02 249	97.84 377	99.04 356	94.73 416	99.31 299	99.20 349	96.10 394	98.76 330	99.42 320	94.94 245	99.81 220	96.97 348	98.45 266	98.97 303

casdiffmvs_mvg		99.15 111	99.02 119	99.55 120	99.66 143	99.09 161	99.64 92	99.56 87	98.26 151	99.45 177	99.87 62	96.03 194	99.81 220	99.54 50	99.15 203	99.73 119
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	98.81 186	99.37 42	97.12 407	99.60 183	91.75 448	98.61 434	99.44 245	99.35 24	99.83 60	99.85 77	98.70 67	99.81 220	99.02 126	99.91 45	99.81 76

viewmacassd2359aftdt		99.08 138	98.94 141	99.50 145	99.66 143	98.96 183	99.51 182	99.54 105	98.27 148	99.42 188	99.89 40	95.88 205	99.80 227	99.20 100	99.11 211	99.76 104

viewmanbaseed2359cas		99.18 101	99.07 105	99.50 145	99.62 167	99.01 173	99.50 192	99.52 126	98.25 156	99.68 107	99.82 107	96.93 150	99.80 227	99.15 109	99.11 211	99.70 140

IMVS_0403		98.86 173	98.89 153	98.78 278	99.55 200	96.93 346	99.58 127	99.44 245	98.05 197	99.68 107	99.80 140	96.81 158	99.80 227	98.15 246	98.92 232	99.60 183

DPM-MVS		98.95 162	98.71 180	99.66 87	99.63 159	99.55 92	98.64 433	99.10 361	97.93 215	99.42 188	99.55 277	98.67 70	99.80 227	95.80 386	99.68 152	99.61 180

DP-MVS Recon		99.12 124	98.95 139	99.65 91	99.74 96	99.70 57	99.27 316	99.57 82	96.40 370	99.42 188	99.68 223	98.75 58	99.80 227	97.98 263	99.72 144	99.44 247

MVS_111021_LR		99.41 57	99.33 50	99.65 91	99.77 74	99.51 103	98.94 403	99.85 6	98.82 85	99.65 127	99.74 187	98.51 82	99.80 227	98.83 162	99.89 67	99.64 170

viewmambaseed2359dif		99.01 155	98.90 149	99.32 185	99.58 187	98.51 250	99.33 292	99.54 105	97.85 225	99.44 182	99.85 77	96.01 195	99.79 233	99.41 69	99.13 207	99.67 153

CS-MVS		99.50 29	99.48 20	99.54 121	99.76 78	99.42 114	99.90 1	99.55 96	98.56 114	99.78 77	99.70 204	98.65 72	99.79 233	99.65 40	99.78 130	99.41 252

Fast-Effi-MVS+-dtu		98.77 195	98.83 167	98.60 294	99.41 256	96.99 341	99.52 173	99.49 180	98.11 182	99.24 241	99.34 348	96.96 149	99.79 233	97.95 265	99.45 175	99.02 298

baseline1		98.31 229	97.95 256	99.38 175	99.50 229	98.74 223	99.59 117	98.93 383	98.41 131	99.14 263	99.60 260	94.59 273	99.79 233	98.48 211	93.29 423	99.61 180

baseline		99.15 111	99.02 119	99.53 129	99.66 143	99.14 156	99.72 53	99.48 192	98.35 138	99.42 188	99.84 92	96.07 191	99.79 233	99.51 55	99.14 204	99.67 153

PVSNet_0	94.43 19	96.09 388	95.47 395	97.94 367	99.31 287	94.34 428	97.81 459	99.70 15	97.12 310	97.46 407	98.75 418	89.71 393	99.79 233	97.69 296	81.69 461	99.68 149

API-MVS		99.04 148	99.03 113	99.06 223	99.40 261	99.31 131	99.55 157	99.56 87	98.54 116	99.33 218	99.39 332	98.76 55	99.78 239	96.98 347	99.78 130	98.07 426

OMC-MVS		99.08 138	99.04 110	99.20 209	99.67 130	98.22 268	99.28 311	99.52 126	98.07 191	99.66 118	99.81 122	97.79 115	99.78 239	97.79 281	99.81 116	99.60 183

GeoE		98.85 182	98.62 197	99.53 129	99.61 177	99.08 164	99.80 25	99.51 145	97.10 314	99.31 220	99.78 164	95.23 236	99.77 241	98.21 238	99.03 223	99.75 106

alignmvs		98.81 186	98.56 206	99.58 112	99.43 249	99.42 114	99.51 182	98.96 381	98.61 109	99.35 213	98.92 408	94.78 257	99.77 241	99.35 75	98.11 293	99.54 207

tpm cat1		97.39 352	97.36 331	97.50 397	99.17 329	93.73 433	99.43 245	99.31 322	91.27 444	98.71 334	99.08 386	94.31 290	99.77 241	96.41 374	98.50 264	99.00 299

CostFormer		97.72 318	97.73 283	97.71 386	99.15 335	94.02 430	99.54 162	99.02 374	94.67 418	99.04 285	99.35 344	92.35 351	99.77 241	98.50 210	97.94 298	99.34 264

MGCFI-Net		99.01 155	98.85 163	99.50 145	99.42 251	99.26 140	99.82 16	99.48 192	98.60 111	99.28 228	98.81 413	97.04 144	99.76 245	99.29 89	97.87 302	99.47 237

test_241102_ONE					99.84 35	99.90 2		99.48 192	99.07 54	99.91 30	99.74 187	99.20 7	99.76 245

MDTV_nov1_ep13			98.32 221		99.11 339	94.44 424	99.27 316	98.74 415	97.51 272	99.40 198	99.62 253	94.78 257	99.76 245	97.59 301	98.81 246

viewdifsd2359ckpt09		99.01 155	98.87 157	99.40 169	99.62 167	98.79 219	99.44 239	99.51 145	97.76 239	99.35 213	99.69 215	96.42 180	99.75 248	98.97 134	99.11 211	99.66 157

sasdasda		99.02 151	98.86 160	99.51 140	99.42 251	99.32 127	99.80 25	99.48 192	98.63 106	99.31 220	98.81 413	97.09 140	99.75 248	99.27 93	97.90 299	99.47 237

canonicalmvs		99.02 151	98.86 160	99.51 140	99.42 251	99.32 127	99.80 25	99.48 192	98.63 106	99.31 220	98.81 413	97.09 140	99.75 248	99.27 93	97.90 299	99.47 237

Effi-MVS+-dtu		98.78 191	98.89 153	98.47 317	99.33 279	96.91 351	99.57 135	99.30 327	98.47 123	99.41 193	98.99 398	96.78 160	99.74 251	98.73 174	99.38 179	98.74 327

patchmatchnet-post											98.70 419	94.79 256	99.74 251

SCA		98.19 239	98.16 229	98.27 343	99.30 288	95.55 394	99.07 369	98.97 379	97.57 262	99.43 185	99.57 271	92.72 334	99.74 251	97.58 302	99.20 198	99.52 214

BH-untuned		98.42 218	98.36 217	98.59 295	99.49 231	96.70 359	99.27 316	99.13 358	97.24 300	98.80 325	99.38 335	95.75 212	99.74 251	97.07 343	99.16 200	99.33 265

BH-RMVSNet		98.41 220	98.08 241	99.40 169	99.41 256	98.83 213	99.30 301	98.77 411	97.70 248	98.94 303	99.65 236	92.91 329	99.74 251	96.52 369	99.55 168	99.64 170

MVS_111021_HR		99.41 57	99.32 52	99.66 87	99.72 107	99.47 109	98.95 401	99.85 6	98.82 85	99.54 162	99.73 193	98.51 82	99.74 251	98.91 143	99.88 72	99.77 97

test_post											65.99 472	94.65 271	99.73 257

XVG-ACMP-BASELINE		97.83 297	97.71 285	98.20 346	99.11 339	96.33 375	99.41 257	99.52 126	98.06 195	99.05 284	99.50 297	89.64 395	99.73 257	97.73 290	97.38 337	98.53 392

HyFIR lowres test		99.11 130	98.92 144	99.65 91	99.90 4	99.37 119	99.02 383	99.91 3	97.67 252	99.59 150	99.75 182	95.90 203	99.73 257	99.53 52	99.02 225	99.86 41

DeepMVS_CX				93.34 433	99.29 292	82.27 462		99.22 345	85.15 459	96.33 429	99.05 390	90.97 379	99.73 257	93.57 423	97.77 307	98.01 430

Patchmatch-test		97.93 277	97.65 291	98.77 279	99.18 321	97.07 330	99.03 380	99.14 357	96.16 385	98.74 331	99.57 271	94.56 275	99.72 261	93.36 425	99.11 211	99.52 214

LPG-MVS_test		98.22 235	98.13 234	98.49 310	99.33 279	97.05 332	99.58 127	99.55 96	97.46 275	99.24 241	99.83 97	92.58 341	99.72 261	98.09 251	97.51 323	98.68 345

LGP-MVS_train				98.49 310	99.33 279	97.05 332		99.55 96	97.46 275	99.24 241	99.83 97	92.58 341	99.72 261	98.09 251	97.51 323	98.68 345

BH-w/o		98.00 269	97.89 265	98.32 335	99.35 273	96.20 381	99.01 388	98.90 393	96.42 368	98.38 370	99.00 396	95.26 233	99.72 261	96.06 379	98.61 254	99.03 296

ACMP	97.20 11	98.06 254	97.94 258	98.45 320	99.37 269	97.01 339	99.44 239	99.49 180	97.54 268	98.45 367	99.79 157	91.95 357	99.72 261	97.91 267	97.49 328	98.62 375
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 264	97.90 261	98.40 328	99.23 308	96.80 357	99.70 58	99.60 64	97.12 310	98.18 384	99.70 204	91.73 363	99.72 261	98.39 221	97.45 330	98.68 345
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		99.06 143	98.93 143	99.45 157	99.63 159	98.96 183	99.50 192	99.51 145	97.83 229	99.28 228	99.80 140	96.68 166	99.71 267	99.05 121	99.12 209	99.68 149

test_post1							99.23 335				65.14 473	94.18 295	99.71 267	97.58 302

ADS-MVSNet		98.20 238	98.08 241	98.56 303	99.33 279	96.48 370	99.23 335	99.15 355	96.24 378	99.10 271	99.67 229	94.11 296	99.71 267	96.81 357	99.05 221	99.48 231

JIA-IIPM		97.50 343	97.02 359	98.93 242	98.73 404	97.80 295	99.30 301	98.97 379	91.73 443	98.91 306	94.86 461	95.10 240	99.71 267	97.58 302	97.98 296	99.28 269

EPMVS		97.82 300	97.65 291	98.35 332	98.88 379	95.98 385	99.49 209	94.71 468	97.57 262	99.26 239	99.48 306	92.46 348	99.71 267	97.87 271	99.08 219	99.35 261

TDRefinement		95.42 399	94.57 407	97.97 364	89.83 471	96.11 384	99.48 215	98.75 412	96.74 339	96.68 426	99.88 51	88.65 407	99.71 267	98.37 224	82.74 460	98.09 425

ACMM	97.58 5	98.37 226	98.34 219	98.48 312	99.41 256	97.10 326	99.56 142	99.45 236	98.53 117	99.04 285	99.85 77	93.00 325	99.71 267	98.74 172	97.45 330	98.64 366
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 274	97.77 276	98.57 299	99.59 185	96.61 366	99.45 232	99.08 364	98.21 164	98.88 311	99.80 140	88.66 406	99.70 274	98.58 198	97.72 308	99.39 255

CHOSEN 280x420		99.12 124	99.13 92	99.08 220	99.66 143	97.89 290	98.43 444	99.71 13	98.88 79	99.62 139	99.76 177	96.63 167	99.70 274	99.46 66	99.99 1	99.66 157

EC-MVSNet		99.44 48	99.39 38	99.58 112	99.56 196	99.49 105	99.88 4	99.58 75	98.38 133	99.73 93	99.69 215	98.20 101	99.70 274	99.64 42	99.82 113	99.54 207

PatchmatchNet		98.31 229	98.36 217	98.19 347	99.16 331	95.32 404	99.27 316	98.92 386	97.37 288	99.37 204	99.58 266	94.90 250	99.70 274	97.43 320	99.21 197	99.54 207
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 249	97.99 251	98.44 323	99.41 256	96.96 345	99.60 110	99.56 87	98.09 186	98.15 385	99.91 25	90.87 380	99.70 274	98.88 146	97.45 330	98.67 353
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 343	96.90 363	99.29 195	99.23 308	98.78 222	99.32 295	98.90 393	97.52 271	98.56 360	98.09 444	84.72 440	99.69 279	97.86 272	97.88 301	99.39 255

HQP_MVS		98.27 234	98.22 227	98.44 323	99.29 292	96.97 343	99.39 269	99.47 214	98.97 71	99.11 268	99.61 257	92.71 336	99.69 279	97.78 282	97.63 311	98.67 353

plane_prior5								99.47 214					99.69 279	97.78 282	97.63 311	98.67 353

D2MVS		98.41 220	98.50 210	98.15 352	99.26 300	96.62 365	99.40 265	99.61 57	97.71 245	98.98 295	99.36 341	96.04 193	99.67 282	98.70 177	97.41 335	98.15 422

IS-MVSNet		99.05 147	98.87 157	99.57 116	99.73 103	99.32 127	99.75 42	99.20 349	98.02 209	99.56 155	99.86 70	96.54 172	99.67 282	98.09 251	99.13 207	99.73 119

CLD-MVS		98.16 243	98.10 237	98.33 333	99.29 292	96.82 356	98.75 422	99.44 245	97.83 229	99.13 264	99.55 277	92.92 327	99.67 282	98.32 231	97.69 309	98.48 396
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 360	97.30 342	97.09 408	99.43 249	93.31 440	99.73 51	98.87 398	98.83 84	99.28 228	99.80 140	84.45 441	99.66 285	97.88 269	97.45 330	98.30 412

AUN-MVS		96.88 371	96.31 377	98.59 295	99.48 238	97.04 335	99.27 316	99.22 345	97.44 281	98.51 363	99.41 324	91.97 356	99.66 285	97.71 293	83.83 458	99.07 293

UniMVSNet_ETH3D		97.32 357	96.81 365	98.87 261	99.40 261	97.46 310	99.51 182	99.53 121	95.86 398	98.54 362	99.77 173	82.44 450	99.66 285	98.68 182	97.52 322	99.50 227

OPM-MVS		98.19 239	98.10 237	98.45 320	98.88 379	97.07 330	99.28 311	99.38 279	98.57 113	99.22 246	99.81 122	92.12 353	99.66 285	98.08 255	97.54 320	98.61 384
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 280	97.78 274	98.32 335	99.46 241	96.68 363	99.56 142	99.54 105	98.41 131	97.79 403	99.87 62	90.18 389	99.66 285	98.05 259	97.18 345	98.62 375

IMVS_0407		98.86 173	98.91 147	98.72 283	99.55 200	96.93 346	99.50 192	99.44 245	98.05 197	99.66 118	99.80 140	97.13 136	99.65 290	98.15 246	98.92 232	99.60 183

hse-mvs2		97.50 343	97.14 353	98.59 295	99.49 231	97.05 332	99.28 311	99.22 345	98.94 74	99.66 118	99.42 320	94.93 246	99.65 290	99.48 63	83.80 459	99.08 288

VPA-MVSNet		98.29 232	97.95 256	99.30 192	99.16 331	99.54 94	99.50 192	99.58 75	98.27 148	99.35 213	99.37 338	92.53 343	99.65 290	99.35 75	94.46 404	98.72 329

TR-MVS		97.76 308	97.41 327	98.82 270	99.06 351	97.87 291	98.87 411	98.56 429	96.63 350	98.68 342	99.22 372	92.49 344	99.65 290	95.40 397	97.79 306	98.95 307

reproduce_monomvs		97.89 284	97.87 266	97.96 366	99.51 217	95.45 399	99.60 110	99.25 339	99.17 32	98.85 319	99.49 300	89.29 398	99.64 294	99.35 75	96.31 361	98.78 315

gm-plane-assit					98.54 424	92.96 442			94.65 419		99.15 380		99.64 294	97.56 307

HQP4-MVS										98.66 343			99.64 294			98.64 366

HQP-MVS		98.02 264	97.90 261	98.37 331	99.19 318	96.83 354	98.98 394	99.39 271	98.24 158	98.66 343	99.40 328	92.47 345	99.64 294	97.19 335	97.58 316	98.64 366

PAPM		97.59 335	97.09 357	99.07 221	99.06 351	98.26 266	98.30 451	99.10 361	94.88 413	98.08 387	99.34 348	96.27 185	99.64 294	89.87 445	98.92 232	99.31 267

TAPA-MVS	97.07 15	97.74 314	97.34 336	98.94 240	99.70 118	97.53 307	99.25 327	99.51 145	91.90 442	99.30 224	99.63 248	98.78 51	99.64 294	88.09 452	99.87 75	99.65 163
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 224	98.09 240	99.24 205	99.26 300	99.32 127	99.56 142	99.55 96	97.45 278	98.71 334	99.83 97	93.23 320	99.63 300	98.88 146	96.32 360	98.76 321

ITE_SJBPF				98.08 355	99.29 292	96.37 373		98.92 386	98.34 139	98.83 320	99.75 182	91.09 377	99.62 301	95.82 384	97.40 336	98.25 416

LF4IMVS		97.52 340	97.46 315	97.70 387	98.98 367	95.55 394	99.29 306	98.82 403	98.07 191	98.66 343	99.64 242	89.97 390	99.61 302	97.01 344	96.68 350	97.94 437

tpm		97.67 329	97.55 300	98.03 357	99.02 358	95.01 411	99.43 245	98.54 431	96.44 366	99.12 266	99.34 348	91.83 360	99.60 303	97.75 288	96.46 356	99.48 231

tpm2		97.44 350	97.34 336	97.74 385	99.15 335	94.36 427	99.45 232	98.94 382	93.45 432	98.90 308	99.44 316	91.35 373	99.59 304	97.31 326	98.07 294	99.29 268

SSM_04072		99.06 143	98.96 135	99.35 178	99.62 167	98.88 200	99.25 327	99.47 214	98.05 197	99.37 204	99.81 122	96.85 152	99.58 305	98.98 129	99.25 193	99.60 183

SD_0403		97.55 337	97.53 304	97.62 390	99.61 177	93.64 437	99.72 53	99.44 245	98.03 206	98.62 355	99.39 332	96.06 192	99.57 306	87.88 454	99.01 226	99.66 157

baseline2		97.87 287	97.55 300	98.82 270	99.18 321	98.02 279	99.41 257	96.58 462	96.97 325	96.51 427	99.17 377	93.43 315	99.57 306	97.71 293	99.03 223	98.86 309

MS-PatchMatch		97.24 362	97.32 340	96.99 409	98.45 427	93.51 439	98.82 415	99.32 318	97.41 285	98.13 386	99.30 359	88.99 400	99.56 308	95.68 390	99.80 121	97.90 440

TinyColmap		97.12 365	96.89 364	97.83 378	99.07 349	95.52 397	98.57 437	98.74 415	97.58 261	97.81 402	99.79 157	88.16 414	99.56 308	95.10 402	97.21 343	98.39 408

USDC		97.34 355	97.20 350	97.75 383	99.07 349	95.20 406	98.51 441	99.04 371	97.99 210	98.31 374	99.86 70	89.02 399	99.55 310	95.67 391	97.36 338	98.49 395

MSLP-MVS++		99.46 40	99.47 22	99.44 162	99.60 183	99.16 151	99.41 257	99.71 13	98.98 68	99.45 177	99.78 164	99.19 9	99.54 311	99.28 90	99.84 98	99.63 175

UWE-MVS-28		97.36 353	97.24 349	97.75 383	98.84 388	94.44 424	99.24 332	97.58 451	97.98 211	99.00 292	99.00 396	91.35 373	99.53 312	93.75 420	98.39 268	99.27 273

TAMVS		99.12 124	99.08 102	99.24 205	99.46 241	98.55 242	99.51 182	99.46 225	98.09 186	99.45 177	99.82 107	98.34 95	99.51 313	98.70 177	98.93 230	99.67 153

EPNet_dtu		98.03 262	97.96 254	98.23 345	98.27 430	95.54 396	99.23 335	98.75 412	99.02 58	97.82 401	99.71 200	96.11 190	99.48 314	93.04 429	99.65 157	99.69 143
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 375	96.22 379	97.97 364	97.00 452	96.28 377	98.66 431	99.03 373	96.61 351	96.93 424	99.79 157	87.20 423	99.47 315	96.65 367	94.13 411	98.16 421

EG-PatchMatch MVS		95.97 390	95.69 391	96.81 416	97.78 437	92.79 443	99.16 350	98.93 383	96.16 385	94.08 445	99.22 372	82.72 448	99.47 315	95.67 391	97.50 325	98.17 420

myMVS_eth3d28		97.69 323	97.34 336	98.73 281	99.27 297	97.52 308	99.33 292	98.78 410	98.03 206	98.82 322	98.49 426	86.64 425	99.46 317	98.44 217	98.24 282	99.23 276

MVP-Stereo		97.81 302	97.75 281	97.99 363	97.53 441	96.60 367	98.96 398	98.85 400	97.22 302	97.23 414	99.36 341	95.28 230	99.46 317	95.51 393	99.78 130	97.92 439
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 210	98.67 184	98.30 337	99.35 273	95.59 393	99.50 192	99.55 96	98.60 111	99.39 200	99.83 97	94.48 281	99.45 319	98.75 171	98.56 260	99.85 45

test-LLR		98.06 254	97.90 261	98.55 305	98.79 392	97.10 326	98.67 428	97.75 447	97.34 290	98.61 356	98.85 410	94.45 283	99.45 319	97.25 329	99.38 179	99.10 283

TESTMET0.1,1		97.55 337	97.27 348	98.40 328	98.93 372	96.53 368	98.67 428	97.61 450	96.96 326	98.64 350	99.28 363	88.63 409	99.45 319	97.30 327	99.38 179	99.21 278

test-mter		97.49 348	97.13 355	98.55 305	98.79 392	97.10 326	98.67 428	97.75 447	96.65 346	98.61 356	98.85 410	88.23 413	99.45 319	97.25 329	99.38 179	99.10 283

mvs_anonymous		99.03 150	98.99 127	99.16 213	99.38 266	98.52 248	99.51 182	99.38 279	97.79 235	99.38 202	99.81 122	97.30 129	99.45 319	99.35 75	98.99 227	99.51 223

tfpnnormal		97.84 294	97.47 313	98.98 233	99.20 315	99.22 145	99.64 92	99.61 57	96.32 372	98.27 378	99.70 204	93.35 319	99.44 324	95.69 389	95.40 387	98.27 414

v7n		97.87 287	97.52 305	98.92 244	98.76 402	98.58 240	99.84 12	99.46 225	96.20 381	98.91 306	99.70 204	94.89 251	99.44 324	96.03 380	93.89 416	98.75 323

jajsoiax		98.43 217	98.28 224	98.88 257	98.60 419	98.43 259	99.82 16	99.53 121	98.19 166	98.63 352	99.80 140	93.22 322	99.44 324	99.22 98	97.50 325	98.77 319

mvs_tets		98.40 223	98.23 226	98.91 248	98.67 412	98.51 250	99.66 79	99.53 121	98.19 166	98.65 349	99.81 122	92.75 331	99.44 324	99.31 84	97.48 329	98.77 319

sc_t1		95.75 394	95.05 401	97.87 373	98.83 389	94.61 421	99.21 341	99.45 236	87.45 455	97.97 394	99.85 77	81.19 455	99.43 328	98.27 234	93.20 425	99.57 201

Vis-MVSNet (Re-imp)		98.87 170	98.72 178	99.31 187	99.71 113	98.88 200	99.80 25	99.44 245	97.91 217	99.36 210	99.78 164	95.49 222	99.43 328	97.91 267	99.11 211	99.62 178

OPU-MVS				99.64 97	99.56 196	99.72 53	99.60 110				99.70 204	99.27 5	99.42 330	98.24 237	99.80 121	99.79 89

Anonymous20231211		97.88 285	97.54 303	98.90 250	99.71 113	98.53 244	99.48 215	99.57 82	94.16 423	98.81 323	99.68 223	93.23 320	99.42 330	98.84 159	94.42 406	98.76 321

ttmdpeth		97.80 304	97.63 295	98.29 338	98.77 400	97.38 313	99.64 92	99.36 288	98.78 94	96.30 430	99.58 266	92.34 352	99.39 332	98.36 226	95.58 382	98.10 424

VPNet		97.84 294	97.44 321	99.01 229	99.21 313	98.94 193	99.48 215	99.57 82	98.38 133	99.28 228	99.73 193	88.89 401	99.39 332	99.19 101	93.27 424	98.71 331

nrg030		98.64 207	98.42 214	99.28 199	99.05 354	99.69 59	99.81 20	99.46 225	98.04 204	99.01 288	99.82 107	96.69 164	99.38 334	99.34 80	94.59 403	98.78 315

GA-MVS		97.85 290	97.47 313	99.00 231	99.38 266	97.99 281	98.57 437	99.15 355	97.04 321	98.90 308	99.30 359	89.83 392	99.38 334	96.70 362	98.33 272	99.62 178

UniMVSNet (Re)		98.29 232	98.00 250	99.13 218	99.00 361	99.36 122	99.49 209	99.51 145	97.95 213	98.97 297	99.13 382	96.30 184	99.38 334	98.36 226	93.34 422	98.66 362

FIs		98.78 191	98.63 192	99.23 207	99.18 321	99.54 94	99.83 15	99.59 70	98.28 146	98.79 327	99.81 122	96.75 162	99.37 337	99.08 118	96.38 358	98.78 315

PS-MVSNAJss		98.92 164	98.92 144	98.90 250	98.78 395	98.53 244	99.78 32	99.54 105	98.07 191	99.00 292	99.76 177	99.01 18	99.37 337	99.13 110	97.23 342	98.81 312

CDS-MVSNet		99.09 136	99.03 113	99.25 202	99.42 251	98.73 224	99.45 232	99.46 225	98.11 182	99.46 176	99.77 173	98.01 110	99.37 337	98.70 177	98.92 232	99.66 157
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 394	95.16 399	97.51 396	99.30 288	93.69 435	98.88 409	95.78 463	85.09 460	98.78 328	92.65 463	91.29 375	99.37 337	94.85 407	99.85 90	99.46 242

v1192		97.81 302	97.44 321	98.91 248	98.88 379	98.68 228	99.51 182	99.34 300	96.18 383	99.20 252	99.34 348	94.03 300	99.36 341	95.32 399	95.18 391	98.69 340

EI-MVSNet		98.67 203	98.67 184	98.68 289	99.35 273	97.97 282	99.50 192	99.38 279	96.93 331	99.20 252	99.83 97	97.87 112	99.36 341	98.38 222	97.56 318	98.71 331

MVSTER		98.49 212	98.32 221	99.00 231	99.35 273	99.02 171	99.54 162	99.38 279	97.41 285	99.20 252	99.73 193	93.86 308	99.36 341	98.87 149	97.56 318	98.62 375

gg-mvs-nofinetune		96.17 386	95.32 398	98.73 281	98.79 392	98.14 272	99.38 274	94.09 469	91.07 447	98.07 390	91.04 467	89.62 396	99.35 344	96.75 359	99.09 218	98.68 345

pm-mvs1		97.68 326	97.28 345	98.88 257	99.06 351	98.62 236	99.50 192	99.45 236	96.32 372	97.87 399	99.79 157	92.47 345	99.35 344	97.54 309	93.54 420	98.67 353

OurMVSNet-221017-0		97.88 285	97.77 276	98.19 347	98.71 408	96.53 368	99.88 4	99.00 376	97.79 235	98.78 328	99.94 6	91.68 364	99.35 344	97.21 331	96.99 349	98.69 340

EGC-MVSNET		82.80 432	77.86 438	97.62 390	97.91 434	96.12 383	99.33 292	99.28 333	8.40 475	25.05 476	99.27 366	84.11 442	99.33 347	89.20 447	98.22 283	97.42 449

pmmvs6		96.53 378	96.09 383	97.82 380	98.69 410	95.47 398	99.37 276	99.47 214	93.46 431	97.41 408	99.78 164	87.06 424	99.33 347	96.92 354	92.70 432	98.65 364

V42		98.06 254	97.79 271	98.86 264	98.98 367	98.84 210	99.69 62	99.34 300	96.53 358	99.30 224	99.37 338	94.67 268	99.32 349	97.57 306	94.66 401	98.42 404

lessismore_v0				97.79 382	98.69 410	95.44 401		94.75 467		95.71 436	99.87 62	88.69 405	99.32 349	95.89 383	94.93 398	98.62 375

OpenMVS_ROB	92.34 20	94.38 411	93.70 417	96.41 421	97.38 443	93.17 441	99.06 373	98.75 412	86.58 458	94.84 443	98.26 436	81.53 453	99.32 349	89.01 448	97.87 302	96.76 452

v8		97.95 276	97.63 295	98.93 242	98.95 371	98.81 218	99.80 25	99.41 261	96.03 395	99.10 271	99.42 320	94.92 248	99.30 352	96.94 351	94.08 413	98.66 362

v1921920		97.80 304	97.45 316	98.84 268	98.80 391	98.53 244	99.52 173	99.34 300	96.15 387	99.24 241	99.47 309	93.98 302	99.29 353	95.40 397	95.13 393	98.69 340

anonymousdsp		98.44 216	98.28 224	98.94 240	98.50 425	98.96 183	99.77 34	99.50 168	97.07 316	98.87 314	99.77 173	94.76 261	99.28 354	98.66 184	97.60 314	98.57 390

MVSFormer		99.17 105	99.12 94	99.29 195	99.51 217	98.94 193	99.88 4	99.46 225	97.55 265	99.80 70	99.65 236	97.39 123	99.28 354	99.03 124	99.85 90	99.65 163

test_djsdf		98.67 203	98.57 204	98.98 233	98.70 409	98.91 198	99.88 4	99.46 225	97.55 265	99.22 246	99.88 51	95.73 213	99.28 354	99.03 124	97.62 313	98.75 323

VortexMVS		98.67 203	98.66 187	98.68 289	99.62 167	97.96 284	99.59 117	99.41 261	98.13 178	99.31 220	99.70 204	95.48 223	99.27 357	99.40 70	97.32 339	98.79 313

SSC-MVS3.2		97.34 355	97.15 352	97.93 368	99.02 358	95.76 390	99.48 215	99.58 75	97.62 257	99.09 274	99.53 286	87.95 416	99.27 357	96.42 372	95.66 380	98.75 323

cascas		97.69 323	97.43 325	98.48 312	98.60 419	97.30 315	98.18 455	99.39 271	92.96 436	98.41 368	98.78 417	93.77 311	99.27 357	98.16 244	98.61 254	98.86 309

v144192		97.92 280	97.60 298	98.87 261	98.83 389	98.65 231	99.55 157	99.34 300	96.20 381	99.32 219	99.40 328	94.36 285	99.26 360	96.37 376	95.03 395	98.70 336

dmvs_re		98.08 252	98.16 229	97.85 375	99.55 200	94.67 420	99.70 58	98.92 386	98.15 171	99.06 282	99.35 344	93.67 314	99.25 361	97.77 285	97.25 341	99.64 170

v2v482		98.06 254	97.77 276	98.92 244	98.90 377	98.82 216	99.57 135	99.36 288	96.65 346	99.19 255	99.35 344	94.20 292	99.25 361	97.72 292	94.97 396	98.69 340

v1240		97.69 323	97.32 340	98.79 276	98.85 386	98.43 259	99.48 215	99.36 288	96.11 390	99.27 234	99.36 341	93.76 312	99.24 363	94.46 411	95.23 390	98.70 336

WBMVS		97.74 314	97.50 308	98.46 318	99.24 306	97.43 311	99.21 341	99.42 258	97.45 278	98.96 299	99.41 324	88.83 402	99.23 364	98.94 137	96.02 366	98.71 331

v1144		97.98 271	97.69 287	98.85 267	98.87 382	98.66 230	99.54 162	99.35 295	96.27 376	99.23 245	99.35 344	94.67 268	99.23 364	96.73 360	95.16 392	98.68 345

v10		97.85 290	97.52 305	98.86 264	98.99 364	98.67 229	99.75 42	99.41 261	95.70 399	98.98 295	99.41 324	94.75 262	99.23 364	96.01 382	94.63 402	98.67 353

WR-MVS_H		98.13 246	97.87 266	98.90 250	99.02 358	98.84 210	99.70 58	99.59 70	97.27 296	98.40 369	99.19 376	95.53 220	99.23 364	98.34 228	93.78 418	98.61 384

miper_enhance_ethall		98.16 243	98.08 241	98.41 326	98.96 370	97.72 299	98.45 443	99.32 318	96.95 328	98.97 297	99.17 377	97.06 143	99.22 368	97.86 272	95.99 369	98.29 413

GG-mvs-BLEND				98.45 320	98.55 423	98.16 270	99.43 245	93.68 470		97.23 414	98.46 427	89.30 397	99.22 368	95.43 396	98.22 283	97.98 435

FC-MVSNet-test		98.75 196	98.62 197	99.15 217	99.08 348	99.45 111	99.86 11	99.60 64	98.23 161	98.70 340	99.82 107	96.80 159	99.22 368	99.07 119	96.38 358	98.79 313

UniMVSNet_NR-MVSNet		98.22 235	97.97 253	98.96 236	98.92 374	98.98 176	99.48 215	99.53 121	97.76 239	98.71 334	99.46 313	96.43 179	99.22 368	98.57 201	92.87 430	98.69 340

DU-MVS		98.08 252	97.79 271	98.96 236	98.87 382	98.98 176	99.41 257	99.45 236	97.87 221	98.71 334	99.50 297	94.82 253	99.22 368	98.57 201	92.87 430	98.68 345

cl____		98.01 267	97.84 269	98.55 305	99.25 304	97.97 282	98.71 426	99.34 300	96.47 365	98.59 359	99.54 282	95.65 216	99.21 373	97.21 331	95.77 375	98.46 401

WR-MVS		98.06 254	97.73 283	99.06 223	98.86 385	99.25 142	99.19 346	99.35 295	97.30 294	98.66 343	99.43 318	93.94 303	99.21 373	98.58 198	94.28 408	98.71 331

test_0402		96.64 376	96.24 378	97.85 375	98.85 386	96.43 372	99.44 239	99.26 337	93.52 429	96.98 422	99.52 290	88.52 410	99.20 375	92.58 436	97.50 325	97.93 438

icg_test_0407_2		98.79 190	98.86 160	98.57 299	99.55 200	96.93 346	99.07 369	99.44 245	98.05 197	99.66 118	99.80 140	97.13 136	99.18 376	98.15 246	98.92 232	99.60 183

SixPastTwentyTwo		97.50 343	97.33 339	98.03 357	98.65 413	96.23 380	99.77 34	98.68 424	97.14 307	97.90 397	99.93 10	90.45 383	99.18 376	97.00 345	96.43 357	98.67 353

cl22		97.85 290	97.64 294	98.48 312	99.09 345	97.87 291	98.60 436	99.33 308	97.11 313	98.87 314	99.22 372	92.38 350	99.17 378	98.21 238	95.99 369	98.42 404

tt0320		95.71 396	95.07 400	97.62 390	99.05 354	95.02 410	99.25 327	99.52 126	86.81 456	97.97 394	99.72 197	83.58 445	99.15 379	96.38 375	93.35 421	98.68 345

WB-MVSnew		97.65 331	97.65 291	97.63 389	98.78 395	97.62 305	99.13 356	98.33 435	97.36 289	99.07 277	98.94 404	95.64 217	99.15 379	92.95 430	98.68 252	96.12 459

IterMVS-SCA-FT		97.82 300	97.75 281	98.06 356	99.57 192	96.36 374	99.02 383	99.49 180	97.18 304	98.71 334	99.72 197	92.72 334	99.14 381	97.44 319	95.86 374	98.67 353

pmmvs5		97.52 340	97.30 342	98.16 349	98.57 422	96.73 358	99.27 316	98.90 393	96.14 388	98.37 371	99.53 286	91.54 370	99.14 381	97.51 311	95.87 373	98.63 373

v148		97.79 306	97.55 300	98.50 309	98.74 403	97.72 299	99.54 162	99.33 308	96.26 377	98.90 308	99.51 294	94.68 267	99.14 381	97.83 276	93.15 427	98.63 373

IMVS_0404		98.53 211	98.52 209	98.55 305	99.55 200	96.93 346	99.20 344	99.44 245	98.05 197	98.96 299	99.80 140	94.66 270	99.13 384	98.15 246	98.92 232	99.60 183

miper_ehance_all_eth		98.18 241	98.10 237	98.41 326	99.23 308	97.72 299	98.72 425	99.31 322	96.60 354	98.88 311	99.29 361	97.29 130	99.13 384	97.60 300	95.99 369	98.38 409

NR-MVSNet		97.97 274	97.61 297	99.02 228	98.87 382	99.26 140	99.47 225	99.42 258	97.63 255	97.08 420	99.50 297	95.07 241	99.13 384	97.86 272	93.59 419	98.68 345

IterMVS		97.83 297	97.77 276	98.02 359	99.58 187	96.27 378	99.02 383	99.48 192	97.22 302	98.71 334	99.70 204	92.75 331	99.13 384	97.46 317	96.00 368	98.67 353
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 412	94.90 403	91.84 438	97.24 447	80.01 468	98.52 440	99.48 192	89.01 452	91.99 455	99.67 229	85.67 432	99.13 384	95.44 395	97.03 348	96.39 456
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 259	97.96 254	98.33 333	99.26 300	97.38 313	98.56 439	99.31 322	96.65 346	98.88 311	99.52 290	96.58 170	99.12 389	97.39 322	95.53 385	98.47 398

pmmvs4		98.13 246	97.90 261	98.81 273	98.61 418	98.87 204	98.99 391	99.21 348	96.44 366	99.06 282	99.58 266	95.90 203	99.11 390	97.18 337	96.11 365	98.46 401

TransMVSNet (Re)		97.15 364	96.58 370	98.86 264	99.12 337	98.85 208	99.49 209	98.91 391	95.48 402	97.16 418	99.80 140	93.38 316	99.11 390	94.16 417	91.73 437	98.62 375

ambc				93.06 436	92.68 467	82.36 461	98.47 442	98.73 421		95.09 441	97.41 450	55.55 468	99.10 392	96.42 372	91.32 438	97.71 441

Baseline_NR-MVSNet		97.76 308	97.45 316	98.68 289	99.09 345	98.29 264	99.41 257	98.85 400	95.65 400	98.63 352	99.67 229	94.82 253	99.10 392	98.07 258	92.89 429	98.64 366

test_vis3_rt		87.04 428	85.81 431	90.73 442	93.99 466	81.96 463	99.76 37	90.23 477	92.81 438	81.35 465	91.56 465	40.06 474	99.07 394	94.27 414	88.23 452	91.15 465

CP-MVSNet		98.09 250	97.78 274	99.01 229	98.97 369	99.24 143	99.67 72	99.46 225	97.25 298	98.48 366	99.64 242	93.79 310	99.06 395	98.63 188	94.10 412	98.74 327

PS-CasMVS		97.93 277	97.59 299	98.95 238	98.99 364	99.06 167	99.68 69	99.52 126	97.13 308	98.31 374	99.68 223	92.44 349	99.05 396	98.51 209	94.08 413	98.75 323

K. test v3		97.10 366	96.79 366	98.01 360	98.72 406	96.33 375	99.87 8	97.05 454	97.59 259	96.16 432	99.80 140	88.71 404	99.04 397	96.69 363	96.55 355	98.65 364

new_pmnet		96.38 382	96.03 384	97.41 399	98.13 433	95.16 409	99.05 375	99.20 349	93.94 424	97.39 411	98.79 416	91.61 369	99.04 397	90.43 443	95.77 375	98.05 428

DIV-MVS_self_test		98.01 267	97.85 268	98.48 312	99.24 306	97.95 287	98.71 426	99.35 295	96.50 359	98.60 358	99.54 282	95.72 214	99.03 399	97.21 331	95.77 375	98.46 401

IterMVS-LS		98.46 215	98.42 214	98.58 298	99.59 185	98.00 280	99.37 276	99.43 256	96.94 330	99.07 277	99.59 262	97.87 112	99.03 399	98.32 231	95.62 381	98.71 331
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 331	97.68 288	97.55 395	98.62 416	94.97 412	98.84 413	99.30 327	96.83 337	98.19 383	99.34 348	97.01 147	99.02 401	95.00 405	96.01 367	98.64 366

Patchmtry		97.75 312	97.40 328	98.81 273	99.10 342	98.87 204	99.11 365	99.33 308	94.83 415	98.81 323	99.38 335	94.33 288	99.02 401	96.10 378	95.57 383	98.53 392

N_pmnet		94.95 406	95.83 389	92.31 437	98.47 426	79.33 469	99.12 359	92.81 475	93.87 425	97.68 404	99.13 382	93.87 307	99.01 403	91.38 440	96.19 363	98.59 388

CR-MVSNet		98.17 242	97.93 259	98.87 261	99.18 321	98.49 253	99.22 339	99.33 308	96.96 326	99.56 155	99.38 335	94.33 288	99.00 404	94.83 408	98.58 257	99.14 280

c3_l		98.12 248	98.04 246	98.38 330	99.30 288	97.69 303	98.81 416	99.33 308	96.67 344	98.83 320	99.34 348	97.11 139	98.99 405	97.58 302	95.34 388	98.48 396

test0.0.03 1		97.71 321	97.42 326	98.56 303	98.41 429	97.82 294	98.78 419	98.63 427	97.34 290	98.05 391	98.98 400	94.45 283	98.98 406	95.04 404	97.15 346	98.89 308

PatchT		97.03 368	96.44 374	98.79 276	98.99 364	98.34 263	99.16 350	99.07 367	92.13 441	99.52 166	97.31 454	94.54 278	98.98 406	88.54 450	98.73 249	99.03 296

GBi-Net		97.68 326	97.48 310	98.29 338	99.51 217	97.26 319	99.43 245	99.48 192	96.49 360	99.07 277	99.32 356	90.26 385	98.98 406	97.10 339	96.65 351	98.62 375

test1		97.68 326	97.48 310	98.29 338	99.51 217	97.26 319	99.43 245	99.48 192	96.49 360	99.07 277	99.32 356	90.26 385	98.98 406	97.10 339	96.65 351	98.62 375

FMVSNet3		98.03 262	97.76 280	98.84 268	99.39 264	98.98 176	99.40 265	99.38 279	96.67 344	99.07 277	99.28 363	92.93 326	98.98 406	97.10 339	96.65 351	98.56 391

FMVSNet2		97.72 318	97.36 331	98.80 275	99.51 217	98.84 210	99.45 232	99.42 258	96.49 360	98.86 318	99.29 361	90.26 385	98.98 406	96.44 371	96.56 354	98.58 389

FMVSNet1		96.84 372	96.36 376	98.29 338	99.32 286	97.26 319	99.43 245	99.48 192	95.11 407	98.55 361	99.32 356	83.95 443	98.98 406	95.81 385	96.26 362	98.62 375

ppachtmachnet_test		97.49 348	97.45 316	97.61 393	98.62 416	95.24 405	98.80 417	99.46 225	96.11 390	98.22 381	99.62 253	96.45 177	98.97 413	93.77 419	95.97 372	98.61 384

TranMVSNet+NR-MVSNet		97.93 277	97.66 290	98.76 280	98.78 395	98.62 236	99.65 85	99.49 180	97.76 239	98.49 365	99.60 260	94.23 291	98.97 413	98.00 262	92.90 428	98.70 336

MVStest1		96.08 389	95.48 394	97.89 372	98.93 372	96.70 359	99.56 142	99.35 295	92.69 439	91.81 456	99.46 313	89.90 391	98.96 415	95.00 405	92.61 433	98.00 433

tt0320-xc		95.31 402	94.59 406	97.45 398	98.92 374	94.73 416	99.20 344	99.31 322	86.74 457	97.23 414	99.72 197	81.14 456	98.95 416	97.08 342	91.98 436	98.67 353

test_method		91.10 423	91.36 425	90.31 443	95.85 455	73.72 476	94.89 465	99.25 339	68.39 467	95.82 435	99.02 394	80.50 457	98.95 416	93.64 422	94.89 400	98.25 416

ADS-MVSNet2		98.02 264	98.07 244	97.87 373	99.33 279	95.19 407	99.23 335	99.08 364	96.24 378	99.10 271	99.67 229	94.11 296	98.93 418	96.81 357	99.05 221	99.48 231

ET-MVSNet_ETH3D		96.49 379	95.64 393	99.05 225	99.53 208	98.82 216	98.84 413	97.51 452	97.63 255	84.77 461	99.21 375	92.09 354	98.91 419	98.98 129	92.21 435	99.41 252

miper_lstm_enhance		98.00 269	97.91 260	98.28 342	99.34 278	97.43 311	98.88 409	99.36 288	96.48 363	98.80 325	99.55 277	95.98 196	98.91 419	97.27 328	95.50 386	98.51 394

MonoMVSNet		98.38 224	98.47 212	98.12 354	98.59 421	96.19 382	99.72 53	98.79 409	97.89 219	99.44 182	99.52 290	96.13 189	98.90 421	98.64 186	97.54 320	99.28 269

PEN-MVS		97.76 308	97.44 321	98.72 283	98.77 400	98.54 243	99.78 32	99.51 145	97.06 318	98.29 377	99.64 242	92.63 340	98.89 422	98.09 251	93.16 426	98.72 329

testing3		97.28 358	96.76 367	98.82 270	99.37 269	98.07 277	99.45 232	99.36 288	97.56 264	97.89 398	98.95 403	83.70 444	98.82 423	96.03 380	98.56 260	99.58 198

testgi		97.65 331	97.50 308	98.13 353	99.36 272	96.45 371	99.42 252	99.48 192	97.76 239	97.87 399	99.45 315	91.09 377	98.81 424	94.53 410	98.52 263	99.13 282

testf1		90.42 426	90.68 427	89.65 446	97.78 437	73.97 474	99.13 356	98.81 405	89.62 449	91.80 457	98.93 405	62.23 466	98.80 425	86.61 460	91.17 439	96.19 457

APD_test2		90.42 426	90.68 427	89.65 446	97.78 437	73.97 474	99.13 356	98.81 405	89.62 449	91.80 457	98.93 405	62.23 466	98.80 425	86.61 460	91.17 439	96.19 457

MIMVSNet		97.73 316	97.45 316	98.57 299	99.45 247	97.50 309	99.02 383	98.98 378	96.11 390	99.41 193	99.14 381	90.28 384	98.74 427	95.74 387	98.93 230	99.47 237

LCM-MVSNet-Re		97.83 297	98.15 231	96.87 415	99.30 288	92.25 446	99.59 117	98.26 436	97.43 282	96.20 431	99.13 382	96.27 185	98.73 428	98.17 243	98.99 227	99.64 170

Syy-MVS		97.09 367	97.14 353	96.95 412	99.00 361	92.73 444	99.29 306	99.39 271	97.06 318	97.41 408	98.15 439	93.92 305	98.68 429	91.71 438	98.34 270	99.45 245

myMVS_eth3d		96.89 370	96.37 375	98.43 325	99.00 361	97.16 323	99.29 306	99.39 271	97.06 318	97.41 408	98.15 439	83.46 446	98.68 429	95.27 400	98.34 270	99.45 245

DTE-MVSNet		97.51 342	97.19 351	98.46 318	98.63 415	98.13 273	99.84 12	99.48 192	96.68 343	97.97 394	99.67 229	92.92 327	98.56 431	96.88 356	92.60 434	98.70 336

PC_three_1452									98.18 169	99.84 52	99.70 204	99.31 3	98.52 432	98.30 233	99.80 121	99.81 76

mvsany_test3		93.77 415	93.45 418	94.74 428	95.78 456	88.01 454	99.64 92	98.25 437	98.28 146	94.31 444	97.97 446	68.89 462	98.51 433	97.50 312	90.37 444	97.71 441

UnsupCasMVSNet_bld		93.53 416	92.51 422	96.58 420	97.38 443	93.82 431	98.24 452	99.48 192	91.10 446	93.10 450	96.66 456	74.89 460	98.37 434	94.03 418	87.71 453	97.56 446

Anonymous20240521		96.20 385	95.89 388	97.13 406	97.72 440	94.96 413	99.79 31	99.29 331	93.01 435	97.20 417	99.03 392	89.69 394	98.36 435	91.16 441	96.13 364	98.07 426

test_f		91.90 422	91.26 426	93.84 431	95.52 460	85.92 456	99.69 62	98.53 432	95.31 404	93.87 446	96.37 458	55.33 469	98.27 436	95.70 388	90.98 442	97.32 450

MDA-MVSNet_test_wron		95.45 398	94.60 405	98.01 360	98.16 432	97.21 322	99.11 365	99.24 342	93.49 430	80.73 467	98.98 400	93.02 324	98.18 437	94.22 416	94.45 405	98.64 366

UnsupCasMVSNet_eth		96.44 380	96.12 381	97.40 400	98.65 413	95.65 391	99.36 282	99.51 145	97.13 308	96.04 434	98.99 398	88.40 411	98.17 438	96.71 361	90.27 445	98.40 407

KD-MVS_2432*1600		94.62 407	93.72 415	97.31 401	97.19 449	95.82 388	98.34 447	99.20 349	95.00 411	97.57 405	98.35 432	87.95 416	98.10 439	92.87 432	77.00 465	98.01 430

miper_refine_blended		94.62 407	93.72 415	97.31 401	97.19 449	95.82 388	98.34 447	99.20 349	95.00 411	97.57 405	98.35 432	87.95 416	98.10 439	92.87 432	77.00 465	98.01 430

YYNet1		95.36 400	94.51 408	97.92 369	97.89 435	97.10 326	99.10 367	99.23 343	93.26 433	80.77 466	99.04 391	92.81 330	98.02 441	94.30 412	94.18 410	98.64 366

EU-MVSNet		97.98 271	98.03 247	97.81 381	98.72 406	96.65 364	99.66 79	99.66 29	98.09 186	98.35 372	99.82 107	95.25 234	98.01 442	97.41 321	95.30 389	98.78 315

Gipuma		90.99 424	90.15 429	93.51 432	98.73 404	90.12 452	93.98 466	99.45 236	79.32 463	92.28 453	94.91 460	69.61 461	97.98 443	87.42 456	95.67 379	92.45 463
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 401	94.73 404	97.15 404	95.53 459	95.94 386	99.35 287	99.10 361	95.13 405	93.55 448	97.54 449	88.15 415	97.91 444	94.58 409	89.69 449	97.61 444

PM-MVS		92.96 419	92.23 423	95.14 427	95.61 457	89.98 453	99.37 276	98.21 440	94.80 416	95.04 442	97.69 447	65.06 463	97.90 445	94.30 412	89.98 447	97.54 447

MDA-MVSNet-bldmvs		94.96 405	93.98 412	97.92 369	98.24 431	97.27 317	99.15 353	99.33 308	93.80 426	80.09 468	99.03 392	88.31 412	97.86 446	93.49 424	94.36 407	98.62 375

Patchmatch-RL test		95.84 392	95.81 390	95.95 425	95.61 457	90.57 451	98.24 452	98.39 433	95.10 409	95.20 439	98.67 420	94.78 257	97.77 447	96.28 377	90.02 446	99.51 223

Anonymous20231206		96.22 383	96.03 384	96.79 417	97.31 446	94.14 429	99.63 98	99.08 364	96.17 384	97.04 421	99.06 389	93.94 303	97.76 448	86.96 458	95.06 394	98.47 398

SD-MVS		99.41 57	99.52 12	99.05 225	99.74 96	99.68 60	99.46 229	99.52 126	99.11 43	99.88 39	99.91 25	99.43 1	97.70 449	98.72 175	99.93 32	99.77 97
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		97.25 360	97.35 333	96.95 412	97.84 436	93.61 438	99.57 135	96.63 460	96.13 389	98.87 314	98.61 423	94.59 273	97.70 449	95.08 403	98.86 240	99.55 205

dongtai		93.26 417	92.93 421	94.25 429	99.39 264	85.68 457	97.68 461	93.27 471	92.87 437	96.85 425	99.39 332	82.33 451	97.48 451	76.78 465	97.80 305	99.58 198

pmmvs3		94.09 413	93.25 420	96.60 419	94.76 464	94.49 423	98.92 405	98.18 442	89.66 448	96.48 428	98.06 445	86.28 429	97.33 452	89.68 446	87.20 454	97.97 436

KD-MVS_self_test		95.00 404	94.34 409	96.96 411	97.07 451	95.39 402	99.56 142	99.44 245	95.11 407	97.13 419	97.32 453	91.86 359	97.27 453	90.35 444	81.23 462	98.23 418

FMVSNet5		96.43 381	96.19 380	97.15 404	99.11 339	95.89 387	99.32 295	99.52 126	94.47 422	98.34 373	99.07 387	87.54 421	97.07 454	92.61 435	95.72 378	98.47 398

new-patchmatchnet		94.48 410	94.08 411	95.67 426	95.08 462	92.41 445	99.18 348	99.28 333	94.55 421	93.49 449	97.37 452	87.86 419	97.01 455	91.57 439	88.36 451	97.61 444

LCM-MVSNet		86.80 430	85.22 434	91.53 440	87.81 472	80.96 466	98.23 454	98.99 377	71.05 465	90.13 460	96.51 457	48.45 473	96.88 456	90.51 442	85.30 456	96.76 452

CL-MVSNet_self_test		94.49 409	93.97 413	96.08 424	96.16 454	93.67 436	98.33 449	99.38 279	95.13 405	97.33 412	98.15 439	92.69 338	96.57 457	88.67 449	79.87 463	97.99 434

MIMVSNet1		95.51 397	95.04 402	96.92 414	97.38 443	95.60 392	99.52 173	99.50 168	93.65 428	96.97 423	99.17 377	85.28 437	96.56 458	88.36 451	95.55 384	98.60 387

FE-MVSNET		94.07 414	93.36 419	96.22 423	94.05 465	94.71 418	99.56 142	98.36 434	93.15 434	93.76 447	97.55 448	86.47 428	96.49 459	87.48 455	89.83 448	97.48 448

test20.03		96.12 387	95.96 386	96.63 418	97.44 442	95.45 399	99.51 182	99.38 279	96.55 357	96.16 432	99.25 369	93.76 312	96.17 460	87.35 457	94.22 409	98.27 414

tmp_tt		82.80 432	81.52 435	86.66 448	66.61 478	68.44 477	92.79 468	97.92 444	68.96 466	80.04 469	99.85 77	85.77 431	96.15 461	97.86 272	43.89 471	95.39 461

test_fmvs3		92.10 421	91.77 424	93.08 435	96.19 453	86.25 455	99.82 16	98.62 428	96.65 346	95.19 440	96.90 455	55.05 470	95.93 462	96.63 368	90.92 443	97.06 451

kuosan		90.92 425	90.11 430	93.34 433	98.78 395	85.59 458	98.15 456	93.16 473	89.37 451	92.07 454	98.38 431	81.48 454	95.19 463	62.54 472	97.04 347	99.25 274

dmvs_testset		95.02 403	96.12 381	91.72 439	99.10 342	80.43 467	99.58 127	97.87 446	97.47 274	95.22 438	98.82 412	93.99 301	95.18 464	88.09 452	94.91 399	99.56 204

PMMVS2		86.87 429	85.37 433	91.35 441	90.21 470	83.80 460	98.89 408	97.45 453	83.13 462	91.67 459	95.03 459	48.49 472	94.70 465	85.86 462	77.62 464	95.54 460

PMVS	70.75 22	75.98 438	74.97 439	79.01 454	70.98 477	55.18 479	93.37 467	98.21 440	65.08 471	61.78 472	93.83 462	21.74 479	92.53 466	78.59 464	91.12 441	89.34 467
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 431	85.65 432	82.75 452	86.77 473	63.39 478	98.35 446	98.92 386	74.11 464	83.39 463	98.98 400	50.85 471	92.40 467	84.54 463	94.97 396	92.46 462

WB-MVS		93.10 418	94.10 410	90.12 444	95.51 461	81.88 464	99.73 51	99.27 336	95.05 410	93.09 451	98.91 409	94.70 266	91.89 468	76.62 466	94.02 415	96.58 454

SSC-MVS		92.73 420	93.73 414	89.72 445	95.02 463	81.38 465	99.76 37	99.23 343	94.87 414	92.80 452	98.93 405	94.71 265	91.37 469	74.49 468	93.80 417	96.42 455

MVE	76.82 21	76.91 437	74.31 441	84.70 449	85.38 475	76.05 473	96.88 464	93.17 472	67.39 468	71.28 470	89.01 469	21.66 480	87.69 470	71.74 469	72.29 467	90.35 466
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 434	79.88 436	82.81 451	90.75 469	76.38 472	97.69 460	95.76 464	66.44 469	83.52 462	92.25 464	62.54 465	87.16 471	68.53 470	61.40 468	84.89 469

EMVS		80.02 435	79.22 437	82.43 453	91.19 468	76.40 471	97.55 463	92.49 476	66.36 470	83.01 464	91.27 466	64.63 464	85.79 472	65.82 471	60.65 469	85.08 468

ANet_high		77.30 436	74.86 440	84.62 450	75.88 476	77.61 470	97.63 462	93.15 474	88.81 453	64.27 471	89.29 468	36.51 475	83.93 473	75.89 467	52.31 470	92.33 464

wuyk23d		40.18 439	41.29 444	36.84 455	86.18 474	49.12 480	79.73 469	22.81 480	27.64 472	25.46 475	28.45 475	21.98 478	48.89 474	55.80 473	23.56 474	12.51 472

test123		39.01 441	42.50 443	28.53 456	39.17 479	20.91 481	98.75 422	19.17 481	19.83 474	38.57 473	66.67 471	33.16 476	15.42 475	37.50 475	29.66 473	49.26 470

testmvs		39.17 440	43.78 442	25.37 457	36.04 480	16.84 482	98.36 445	26.56 479	20.06 473	38.51 474	67.32 470	29.64 477	15.30 476	37.59 474	39.90 472	43.98 471

mmdepth		0.02 446	0.03 449	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.27 477	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

monomultidepth		0.02 446	0.03 449	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.27 477	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

test_blank		0.13 445	0.17 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	1.57 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

uanet_test		0.02 446	0.03 449	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.27 477	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

DCPMVS		0.02 446	0.03 449	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.27 477	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

cdsmvs_eth3d_5k		24.64 442	32.85 445	0.00 458	0.00 481	0.00 483	0.00 470	99.51 145	0.00 476	0.00 477	99.56 274	96.58 170	0.00 477	0.00 476	0.00 475	0.00 473

pcd_1.5k_mvsjas		8.27 444	11.03 447	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.27 477	99.01 18	0.00 477	0.00 476	0.00 475	0.00 473

sosnet-low-res		0.02 446	0.03 449	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.27 477	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

sosnet		0.02 446	0.03 449	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.27 477	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

uncertanet		0.02 446	0.03 449	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.27 477	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

Regformer		0.02 446	0.03 449	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.27 477	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

ab-mvs-re		8.30 443	11.06 446	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	99.58 266	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

uanet		0.02 446	0.03 449	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.27 477	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

TestfortrainingZip							99.69 62

WAC-MVS						97.16 323								95.47 394

FOURS1					99.91 1	99.93 1	99.87 8	99.56 87	99.10 44	99.81 65

test_one_0601					99.81 53	99.88 9		99.49 180	98.97 71	99.65 127	99.81 122	99.09 14

eth-test2					0.00 481

eth-test					0.00 481

RE-MVS-def			99.34 48		99.76 78	99.82 27	99.63 98	99.52 126	98.38 133	99.76 87	99.82 107	98.75 58		98.61 192	99.81 116	99.77 97

IU-MVS					99.84 35	99.88 9		99.32 318	98.30 145	99.84 52				98.86 154	99.85 90	99.89 28

save fliter					99.76 78	99.59 84	99.14 355	99.40 268	99.00 63

test0726					99.85 28	99.89 5	99.62 103	99.50 168	99.10 44	99.86 49	99.82 107	98.94 32

GSMVS																99.52 214

test_part2					99.81 53	99.83 21				99.77 81

sam_mvs1												94.86 252				99.52 214

sam_mvs												94.72 264

MTGPA								99.47 214

MTMP							99.54 162	98.88 396

test9_res														97.49 313	99.72 144	99.75 106

agg_prior2														97.21 331	99.73 143	99.75 106

test_prior4						99.56 90	98.99 391

test_prior2							98.96 398		98.34 139	99.01 288	99.52 290	98.68 68		97.96 264	99.74 141

新几何2							99.01 388

旧先验1					99.74 96	99.59 84		99.54 105			99.69 215	98.47 84			99.68 152	99.73 119

原ACMM2							98.95 401

test222					99.75 88	99.49 105	98.91 407	99.49 180	96.42 368	99.34 217	99.65 236	98.28 98			99.69 149	99.72 128

segment_acmp												98.96 25

testdata1							98.85 412		98.32 143

plane_prior7					99.29 292	97.03 338

plane_prior6					99.27 297	96.98 342						92.71 336

plane_prior4											99.61 257

plane_prior3						97.00 340			98.69 103	99.11 268

plane_prior2							99.39 269		98.97 71

plane_prior1					99.26 300

plane_prior						96.97 343	99.21 341		98.45 126						97.60 314

n2								0.00 482

nn								0.00 482

door-mid								98.05 443

test11								99.35 295

door								97.92 444

HQP5-MVS						96.83 354

HQP-NCC					99.19 318		98.98 394		98.24 158	98.66 343

ACMP_Plane					99.19 318		98.98 394		98.24 158	98.66 343

BP-MVS														97.19 335

HQP3-MVS								99.39 271							97.58 316

HQP2-MVS												92.47 345

NP-MVS					99.23 308	96.92 350					99.40 328

MDTV_nov1_ep13_2view						95.18 408	99.35 287		96.84 335	99.58 151		95.19 237		97.82 277		99.46 242

ACMMP++_ref															97.19 344

ACMMP++															97.43 334

Test By Simon												98.75 58

High-resolution multi-view benchmark