High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 64	99.38 232	99.37 112	99.58 117	99.62 44	99.41 15	99.87 36	99.92 17	98.81 47	100.00 1	99.97 1	99.93 27	99.94 13

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 61	99.84 32	99.44 106	99.58 117	99.69 18	99.43 11	99.98 9	99.91 23	98.62 73	100.00 1	99.97 1	99.95 18	99.90 21

test_vis1_n_1920		98.63 175	98.40 182	99.31 161	99.86 20	97.94 261	99.67 69	99.62 44	99.43 11	99.99 2	99.91 23	87.29 387	100.00 1	99.92 18	99.92 32	99.98 2

fmvsm_s_conf0.5_n_5		99.37 60	99.21 75	99.86 27	99.80 53	99.68 55	99.42 223	99.61 51	99.37 18	99.97 19	99.86 56	94.96 215	99.99 4	99.97 1	99.93 27	99.92 19

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 32	99.82 25	99.54 149	99.66 28	99.46 7	99.98 9	99.89 35	97.27 129	99.99 4	99.97 1	99.95 18	99.95 9

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 35	99.86 20	99.61 76	99.56 130	99.63 42	99.48 3	99.98 9	99.83 78	98.75 58	99.99 4	99.97 1	99.96 13	99.94 13

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 35	99.84 32	99.63 73	99.56 130	99.63 42	99.47 4	99.98 9	99.82 87	98.75 58	99.99 4	99.97 1	99.97 7	99.94 13

test_fmvsmconf_n		99.70 3	99.64 4	99.87 16	99.80 53	99.66 62	99.48 192	99.64 38	99.45 8	99.92 23	99.92 17	98.62 73	99.99 4	99.96 9	99.99 1	99.96 7

patch_mono-2		99.26 81	99.62 5	98.16 315	99.81 47	94.59 384	99.52 159	99.64 38	99.33 20	99.73 77	99.90 30	99.00 22	99.99 4	99.69 28	99.98 4	99.89 24

h-mvs33		97.70 288	97.28 310	98.97 208	99.70 110	97.27 289	99.36 251	99.45 210	98.94 65	99.66 99	99.64 205	94.93 218	99.99 4	99.48 53	84.36 418	99.65 140

xiu_mvs_v1_base_debu		99.29 75	99.27 65	99.34 154	99.63 141	98.97 168	99.12 320	99.51 127	98.86 71	99.84 42	99.47 272	98.18 100	99.99 4	99.50 48	99.31 173	99.08 253

xiu_mvs_v1_base		99.29 75	99.27 65	99.34 154	99.63 141	98.97 168	99.12 320	99.51 127	98.86 71	99.84 42	99.47 272	98.18 100	99.99 4	99.50 48	99.31 173	99.08 253

xiu_mvs_v1_base_debi		99.29 75	99.27 65	99.34 154	99.63 141	98.97 168	99.12 320	99.51 127	98.86 71	99.84 42	99.47 272	98.18 100	99.99 4	99.50 48	99.31 173	99.08 253

EPNet		98.86 146	98.71 150	99.30 166	97.20 410	98.18 243	99.62 95	98.91 355	99.28 23	98.63 318	99.81 101	95.96 177	99.99 4	99.24 80	99.72 132	99.73 105
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		99.40 56	99.28 62	99.74 70	99.67 120	99.31 122	99.52 159	98.87 362	99.55 1	99.74 75	99.80 114	96.47 160	99.98 15	99.97 1	99.97 7	99.94 13

test_cas_vis1_n_1920		99.16 95	99.01 107	99.61 98	99.81 47	98.86 188	99.65 81	99.64 38	99.39 16	99.97 19	99.94 6	93.20 288	99.98 15	99.55 41	99.91 39	99.99 1

test_vis1_n		97.92 246	97.44 286	99.34 154	99.53 174	98.08 249	99.74 46	99.49 157	99.15 28	100.00 1	99.94 6	79.51 419	99.98 15	99.88 20	99.76 124	99.97 4

xiu_mvs_v2_base		99.26 81	99.25 69	99.29 169	99.53 174	98.91 182	99.02 343	99.45 210	98.80 80	99.71 84	99.26 330	98.94 32	99.98 15	99.34 67	99.23 178	98.98 267

PS-MVSNAJ		99.32 70	99.32 48	99.30 166	99.57 162	98.94 178	98.97 357	99.46 199	98.92 68	99.71 84	99.24 332	99.01 18	99.98 15	99.35 62	99.66 142	98.97 268

QAPM		98.67 171	98.30 189	99.80 55	99.20 280	99.67 59	99.77 34	99.72 11	94.74 382	98.73 298	99.90 30	95.78 187	99.98 15	96.96 313	99.88 63	99.76 95

3Dnovator	97.25 9	99.24 86	99.05 95	99.81 52	99.12 302	99.66 62	99.84 12	99.74 10	99.09 43	98.92 271	99.90 30	95.94 180	99.98 15	98.95 110	99.92 32	99.79 82

OpenMVS	96.50 16	98.47 180	98.12 201	99.52 125	99.04 320	99.53 92	99.82 16	99.72 11	94.56 385	98.08 352	99.88 43	94.73 234	99.98 15	97.47 281	99.76 124	99.06 259

fmvsm_s_conf0.5_n_3		99.37 60	99.20 77	99.87 16	99.75 81	99.70 52	99.48 192	99.66 28	99.45 8	99.99 2	99.93 10	94.64 242	99.97 23	99.94 15	99.97 7	99.95 9

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 59	99.88 8	99.56 130	99.55 86	99.15 28	99.90 26	99.90 30	99.00 22	99.97 23	99.11 91	99.91 39	99.86 37

test_fmvsmconf0.1_n		99.55 18	99.45 25	99.86 27	99.44 214	99.65 66	99.50 175	99.61 51	99.45 8	99.87 36	99.92 17	97.31 126	99.97 23	99.95 11	99.99 1	99.97 4

test_fmvs1_n		98.41 186	98.14 198	99.21 181	99.82 43	97.71 274	99.74 46	99.49 157	99.32 21	99.99 2	99.95 3	85.32 400	99.97 23	99.82 23	99.84 89	99.96 7

CANet_DTU		98.97 136	98.87 131	99.25 176	99.33 244	98.42 235	99.08 329	99.30 292	99.16 27	99.43 159	99.75 149	95.27 204	99.97 23	98.56 177	99.95 18	99.36 225

MVS_0304		99.15 97	98.96 117	99.73 73	98.92 338	99.37 112	99.37 246	96.92 416	99.51 2	99.66 99	99.78 133	96.69 151	99.97 23	99.84 22	99.97 7	99.84 47

MTAPA		99.52 22	99.39 34	99.89 8	99.90 4	99.86 16	99.66 75	99.47 190	98.79 81	99.68 90	99.81 101	98.43 86	99.97 23	98.88 120	99.90 48	99.83 57

PGM-MVS		99.45 40	99.31 54	99.86 27	99.87 15	99.78 40	99.58 117	99.65 35	97.84 195	99.71 84	99.80 114	99.12 13	99.97 23	98.33 201	99.87 66	99.83 57

mPP-MVS		99.44 44	99.30 56	99.86 27	99.88 11	99.79 34	99.69 60	99.48 169	98.12 156	99.50 144	99.75 149	98.78 51	99.97 23	98.57 174	99.89 59	99.83 57

CP-MVS		99.45 40	99.32 48	99.85 35	99.83 40	99.75 44	99.69 60	99.52 113	98.07 166	99.53 139	99.63 211	98.93 36	99.97 23	98.74 145	99.91 39	99.83 57

SteuartSystems-ACMMP		99.54 19	99.42 27	99.87 16	99.82 43	99.81 29	99.59 109	99.51 127	98.62 96	99.79 56	99.83 78	99.28 4	99.97 23	98.48 184	99.90 48	99.84 47
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 91	98.97 113	99.82 49	99.17 294	99.68 55	99.81 20	99.51 127	99.20 25	98.72 299	99.89 35	95.68 191	99.97 23	98.86 128	99.86 74	99.81 69

fmvsm_s_conf0.5_n_2		99.32 70	99.13 84	99.89 8	99.80 53	99.77 41	99.44 211	99.58 68	99.47 4	99.99 2	99.93 10	94.04 266	99.96 35	99.96 9	99.93 27	99.93 18

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 71	99.88 8	99.52 159	99.54 95	99.13 31	99.89 28	99.89 35	98.96 25	99.96 35	99.04 99	99.90 48	99.85 41

our_new_method		99.61 8	99.52 12	99.90 5	99.76 71	99.88 8	99.52 159	99.54 95	99.13 31	99.89 28	99.89 35	98.96 25	99.96 35	99.04 99	99.90 48	99.85 41

fmvsm_s_conf0.5_n_a		99.56 17	99.47 21	99.85 35	99.83 40	99.64 72	99.52 159	99.65 35	99.10 38	99.98 9	99.92 17	97.35 125	99.96 35	99.94 15	99.92 32	99.95 9

fmvsm_s_conf0.5_n		99.51 23	99.40 32	99.85 35	99.84 32	99.65 66	99.51 168	99.67 23	99.13 31	99.98 9	99.92 17	96.60 154	99.96 35	99.95 11	99.96 13	99.95 9

mvsany_test1		99.50 25	99.46 24	99.62 97	99.61 151	99.09 151	98.94 363	99.48 169	99.10 38	99.96 21	99.91 23	98.85 42	99.96 35	99.72 26	99.58 152	99.82 62

test_fmvs1		98.88 142	98.79 143	99.16 186	99.69 114	97.61 278	99.55 144	99.49 157	99.32 21	99.98 9	99.91 23	91.41 336	99.96 35	99.82 23	99.92 32	99.90 21

DVP-MVS++		99.59 12	99.50 17	99.88 10	99.51 183	99.88 8	99.87 8	99.51 127	98.99 56	99.88 31	99.81 101	99.27 5	99.96 35	98.85 130	99.80 109	99.81 69

MSC_two_6792asdad				99.87 16	99.51 183	99.76 42		99.33 274					99.96 35	98.87 123	99.84 89	99.89 24

No_MVS				99.87 16	99.51 183	99.76 42		99.33 274					99.96 35	98.87 123	99.84 89	99.89 24

ZD-MVS					99.71 105	99.79 34		99.61 51	96.84 300	99.56 132	99.54 245	98.58 75	99.96 35	96.93 316	99.75 126

SED-MVS		99.61 8	99.52 12	99.88 10	99.84 32	99.90 2	99.60 102	99.48 169	99.08 44	99.91 24	99.81 101	99.20 7	99.96 35	98.91 117	99.85 81	99.79 82

test_241102_TWO								99.48 169	99.08 44	99.88 31	99.81 101	98.94 32	99.96 35	98.91 117	99.84 89	99.88 30

ZNCC-MVS		99.47 34	99.33 46	99.87 16	99.87 15	99.81 29	99.64 84	99.67 23	98.08 165	99.55 136	99.64 205	98.91 37	99.96 35	98.72 148	99.90 48	99.82 62

DVP-MVS		99.57 16	99.47 21	99.88 10	99.85 26	99.89 4	99.57 124	99.37 254	99.10 38	99.81 50	99.80 114	98.94 32	99.96 35	98.93 114	99.86 74	99.81 69
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 56	99.81 50	99.80 114	99.09 14	99.96 35	98.85 130	99.90 48	99.88 30

test_0728_SECOND				99.91 3	99.84 32	99.89 4	99.57 124	99.51 127					99.96 35	98.93 114	99.86 74	99.88 30

SR-MVS		99.43 47	99.29 60	99.86 27	99.75 81	99.83 19	99.59 109	99.62 44	98.21 143	99.73 77	99.79 126	98.68 67	99.96 35	98.44 190	99.77 121	99.79 82

DPE-MVS		99.46 36	99.32 48	99.91 3	99.78 59	99.88 8	99.36 251	99.51 127	98.73 88	99.88 31	99.84 73	98.72 64	99.96 35	98.16 215	99.87 66	99.88 30
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 49	99.29 60	99.80 55	99.62 147	99.55 87	99.50 175	99.70 15	98.79 81	99.77 65	99.96 1	97.45 120	99.96 35	98.92 116	99.90 48	99.89 24

HFP-MVS		99.49 27	99.37 38	99.86 27	99.87 15	99.80 31	99.66 75	99.67 23	98.15 150	99.68 90	99.69 179	99.06 16	99.96 35	98.69 153	99.87 66	99.84 47

region2R		99.48 31	99.35 42	99.87 16	99.88 11	99.80 31	99.65 81	99.66 28	98.13 155	99.66 99	99.68 186	98.96 25	99.96 35	98.62 162	99.87 66	99.84 47

HPM-MVS++		99.39 58	99.23 73	99.87 16	99.75 81	99.84 18	99.43 216	99.51 127	98.68 93	99.27 201	99.53 249	98.64 72	99.96 35	98.44 190	99.80 109	99.79 82

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 67	99.89 4	99.75 42	99.56 78	99.02 49	99.88 31	99.85 63	99.18 10	99.96 35	99.22 81	99.92 32	99.90 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 27	99.36 40	99.86 27	99.87 15	99.79 34	99.66 75	99.67 23	98.15 150	99.67 94	99.69 179	98.95 30	99.96 35	98.69 153	99.87 66	99.84 47

MP-MVS		99.33 68	99.15 82	99.87 16	99.88 11	99.82 25	99.66 75	99.46 199	98.09 161	99.48 148	99.74 154	98.29 95	99.96 35	97.93 233	99.87 66	99.82 62
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 113	98.90 125	99.74 70	99.80 53	99.46 104	99.59 109	99.49 157	97.03 287	99.63 114	99.69 179	97.27 129	99.96 35	97.82 244	99.84 89	99.81 69

PVSNet_Blended_VisFu		99.36 64	99.28 62	99.61 98	99.86 20	99.07 156	99.47 200	99.93 2	97.66 218	99.71 84	99.86 56	97.73 115	99.96 35	99.47 55	99.82 102	99.79 82

UGNet		98.87 143	98.69 152	99.40 146	99.22 277	98.72 202	99.44 211	99.68 20	99.24 24	99.18 226	99.42 283	92.74 298	99.96 35	99.34 67	99.94 25	99.53 181
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 70	99.32 48	99.32 160	99.85 26	98.29 238	99.71 55	99.66 28	98.11 158	99.41 166	99.80 114	98.37 92	99.96 35	98.99 105	99.96 13	99.72 113

ACMMP		99.45 40	99.32 48	99.82 49	99.89 8	99.67 59	99.62 95	99.69 18	98.12 156	99.63 114	99.84 73	98.73 63	99.96 35	98.55 180	99.83 98	99.81 69
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
fmvsm_s_conf0.5_n_6		99.54 19	99.44 26	99.85 35	99.51 183	99.67 59	99.50 175	99.64 38	99.43 11	99.98 9	99.78 133	97.26 131	99.95 66	99.95 11	99.93 27	99.92 19

fmvsm_s_conf0.5_n_4		99.36 64	99.24 70	99.73 73	99.78 59	99.53 92	99.49 187	99.60 58	99.42 14	99.99 2	99.86 56	95.15 210	99.95 66	99.95 11	99.89 59	99.73 105

fmvsm_s_conf0.1_n_2		99.37 60	99.22 74	99.81 52	99.77 67	99.75 44	99.46 203	99.60 58	99.47 4	99.98 9	99.94 6	94.98 214	99.95 66	99.97 1	99.79 116	99.73 105

test_fmvsmconf0.01_n		99.22 88	99.03 99	99.79 58	98.42 390	99.48 101	99.55 144	99.51 127	99.39 16	99.78 61	99.93 10	94.80 226	99.95 66	99.93 17	99.95 18	99.94 13

SR-MVS-dyc-post		99.45 40	99.31 54	99.85 35	99.76 71	99.82 25	99.63 90	99.52 113	98.38 119	99.76 71	99.82 87	98.53 79	99.95 66	98.61 165	99.81 105	99.77 90

GST-MVS		99.40 56	99.24 70	99.85 35	99.86 20	99.79 34	99.60 102	99.67 23	97.97 180	99.63 114	99.68 186	98.52 80	99.95 66	98.38 194	99.86 74	99.81 69

CANet		99.25 85	99.14 83	99.59 101	99.41 222	99.16 141	99.35 256	99.57 73	98.82 76	99.51 143	99.61 220	96.46 161	99.95 66	99.59 36	99.98 4	99.65 140

MP-MVS-pluss		99.37 60	99.20 77	99.88 10	99.90 4	99.87 15	99.30 268	99.52 113	97.18 269	99.60 124	99.79 126	98.79 50	99.95 66	98.83 136	99.91 39	99.83 57
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 49	99.27 65	99.88 10	99.89 8	99.80 31	99.67 69	99.50 147	98.70 90	99.77 65	99.49 263	98.21 98	99.95 66	98.46 188	99.77 121	99.88 30
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
testdata2													99.95 66	96.67 328

APD-MVS_3200maxsize		99.48 31	99.35 42	99.85 35	99.76 71	99.83 19	99.63 90	99.54 95	98.36 123	99.79 56	99.82 87	98.86 41	99.95 66	98.62 162	99.81 105	99.78 88

RPMNet		96.72 339	95.90 352	99.19 183	99.18 286	98.49 227	99.22 303	99.52 113	88.72 418	99.56 132	97.38 412	94.08 265	99.95 66	86.87 420	98.58 225	99.14 245

sss		99.17 93	99.05 95	99.53 119	99.62 147	98.97 168	99.36 251	99.62 44	97.83 196	99.67 94	99.65 199	97.37 124	99.95 66	99.19 83	99.19 181	99.68 130

MVSMamba_PlusPlus		99.46 36	99.41 31	99.64 90	99.68 118	99.50 98	99.75 42	99.50 147	98.27 133	99.87 36	99.92 17	98.09 104	99.94 79	99.65 32	99.95 18	99.47 202

fmvsm_s_conf0.1_n_a		99.26 81	99.06 94	99.85 35	99.52 180	99.62 74	99.54 149	99.62 44	98.69 91	99.99 2	99.96 1	94.47 251	99.94 79	99.88 20	99.92 32	99.98 2

fmvsm_s_conf0.1_n		99.29 75	99.10 88	99.86 27	99.70 110	99.65 66	99.53 158	99.62 44	98.74 87	99.99 2	99.95 3	94.53 249	99.94 79	99.89 19	99.96 13	99.97 4

TSAR-MVS + MP.		99.58 13	99.50 17	99.81 52	99.91 1	99.66 62	99.63 90	99.39 238	98.91 69	99.78 61	99.85 63	99.36 2	99.94 79	98.84 133	99.88 63	99.82 62
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 140	98.75 146	99.39 150	99.46 207	98.61 213	99.76 37	99.50 147	98.06 170	99.81 50	99.88 43	93.91 273	99.94 79	99.11 91	99.27 176	99.61 156

mamv4		99.33 68	99.42 27	99.07 194	99.67 120	97.73 269	99.42 223	99.60 58	98.15 150	99.94 22	99.91 23	98.42 88	99.94 79	99.72 26	99.96 13	99.54 175

XVS		99.53 21	99.42 27	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 59	99.37 177	99.74 154	98.81 47	99.94 79	98.79 141	99.86 74	99.84 47

X-MVStestdata		96.55 342	95.45 361	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 59	99.37 177	64.01 435	98.81 47	99.94 79	98.79 141	99.86 74	99.84 47

旧先验2							98.96 358		96.70 307	99.47 149			99.94 79	98.19 211

新几何1				99.75 67	99.75 81	99.59 79		99.54 95	96.76 303	99.29 195	99.64 205	98.43 86	99.94 79	96.92 318	99.66 142	99.72 113

testdata				99.54 111	99.75 81	98.95 175		99.51 127	97.07 281	99.43 159	99.70 169	98.87 40	99.94 79	97.76 251	99.64 145	99.72 113

HPM-MVS		99.42 49	99.28 62	99.83 48	99.90 4	99.72 48	99.81 20	99.54 95	97.59 224	99.68 90	99.63 211	98.91 37	99.94 79	98.58 171	99.91 39	99.84 47
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 89	99.10 88	99.45 139	99.89 8	98.52 223	99.39 239	99.94 1	98.73 88	99.11 235	99.89 35	95.50 196	99.94 79	99.50 48	99.97 7	99.89 24

APD-MVS		99.27 79	99.08 92	99.84 47	99.75 81	99.79 34	99.50 175	99.50 147	97.16 271	99.77 65	99.82 87	98.78 51	99.94 79	97.56 272	99.86 74	99.80 78
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 31	99.42 27	99.65 84	99.72 100	99.40 111	99.05 335	99.66 28	99.14 30	99.57 131	99.80 114	98.46 84	99.94 79	99.57 39	99.84 89	99.60 159
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		99.06 122	98.88 130	99.61 98	99.62 147	99.16 141	99.37 246	99.56 78	98.04 173	99.53 139	99.62 216	96.84 145	99.94 79	98.85 130	98.49 233	99.72 113

DeepC-MVS	98.35 2	99.30 73	99.19 79	99.64 90	99.82 43	99.23 134	99.62 95	99.55 86	98.94 65	99.63 114	99.95 3	95.82 186	99.94 79	99.37 61	99.97 7	99.73 105
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 79	99.12 86	99.74 70	99.18 286	99.75 44	99.56 130	99.57 73	98.45 112	99.49 147	99.85 63	97.77 114	99.94 79	98.33 201	99.84 89	99.52 182

GDP-MVS		99.08 119	98.89 128	99.64 90	99.53 174	99.34 116	99.64 84	99.48 169	98.32 128	99.77 65	99.66 197	95.14 211	99.93 97	98.97 109	99.50 158	99.64 147

SDMVSNet		99.11 113	98.90 125	99.75 67	99.81 47	99.59 79	99.81 20	99.65 35	98.78 84	99.64 111	99.88 43	94.56 245	99.93 97	99.67 30	98.26 246	99.72 113

FE-MVS		98.48 179	98.17 194	99.40 146	99.54 173	98.96 172	99.68 66	98.81 369	95.54 366	99.62 118	99.70 169	93.82 276	99.93 97	97.35 290	99.46 160	99.32 231

SF-MVS		99.38 59	99.24 70	99.79 58	99.79 57	99.68 55	99.57 124	99.54 95	97.82 200	99.71 84	99.80 114	98.95 30	99.93 97	98.19 211	99.84 89	99.74 100

dcpmvs_2		99.23 87	99.58 7	98.16 315	99.83 40	94.68 382	99.76 37	99.52 113	99.07 46	99.98 9	99.88 43	98.56 77	99.93 97	99.67 30	99.98 4	99.87 35

Anonymous20240529		98.09 216	97.68 254	99.34 154	99.66 130	98.44 232	99.40 235	99.43 224	93.67 392	99.22 213	99.89 35	90.23 353	99.93 97	99.26 79	98.33 240	99.66 136

ACMMP_NAP		99.47 34	99.34 44	99.88 10	99.87 15	99.86 16	99.47 200	99.48 169	98.05 172	99.76 71	99.86 56	98.82 46	99.93 97	98.82 140	99.91 39	99.84 47

EI-MVSNet-UG-set		99.58 13	99.57 8	99.64 90	99.78 59	99.14 146	99.60 102	99.45 210	99.01 51	99.90 26	99.83 78	98.98 24	99.93 97	99.59 36	99.95 18	99.86 37

无先验							98.99 351	99.51 127	96.89 297				99.93 97	97.53 275		99.72 113

VDDNet		97.55 303	97.02 324	99.16 186	99.49 197	98.12 248	99.38 244	99.30 292	95.35 368	99.68 90	99.90 30	82.62 412	99.93 97	99.31 71	98.13 258	99.42 214

ab-mvs		98.86 146	98.63 159	99.54 111	99.64 138	99.19 136	99.44 211	99.54 95	97.77 204	99.30 192	99.81 101	94.20 259	99.93 97	99.17 87	98.82 213	99.49 195

F-COLMAP		99.19 89	99.04 97	99.64 90	99.78 59	99.27 129	99.42 223	99.54 95	97.29 260	99.41 166	99.59 225	98.42 88	99.93 97	98.19 211	99.69 137	99.73 105

BP-MVS1		99.12 108	98.94 121	99.65 84	99.51 183	99.30 124	99.67 69	98.92 350	98.48 108	99.84 42	99.69 179	94.96 215	99.92 109	99.62 35	99.79 116	99.71 122

Anonymous202405211		98.30 197	97.98 218	99.26 175	99.57 162	98.16 244	99.41 227	98.55 393	96.03 360	99.19 222	99.74 154	91.87 323	99.92 109	99.16 88	98.29 245	99.70 124

EI-MVSNet-Vis-set		99.58 13	99.56 10	99.64 90	99.78 59	99.15 145	99.61 101	99.45 210	99.01 51	99.89 28	99.82 87	99.01 18	99.92 109	99.56 40	99.95 18	99.85 41

VDD-MVS		97.73 282	97.35 298	98.88 228	99.47 205	97.12 297	99.34 259	98.85 364	98.19 145	99.67 94	99.85 63	82.98 410	99.92 109	99.49 52	98.32 244	99.60 159

VNet		99.11 113	98.90 125	99.73 73	99.52 180	99.56 85	99.41 227	99.39 238	99.01 51	99.74 75	99.78 133	95.56 194	99.92 109	99.52 46	98.18 254	99.72 113

XVG-OURS-SEG-HR		98.69 169	98.62 164	98.89 226	99.71 105	97.74 268	99.12 320	99.54 95	98.44 115	99.42 162	99.71 165	94.20 259	99.92 109	98.54 181	98.90 207	99.00 264

mvsmamba		99.06 122	98.96 117	99.36 152	99.47 205	98.64 209	99.70 56	99.05 334	97.61 223	99.65 106	99.83 78	96.54 157	99.92 109	99.19 83	99.62 148	99.51 190

HPM-MVS_fast		99.51 23	99.40 32	99.85 35	99.91 1	99.79 34	99.76 37	99.56 78	97.72 209	99.76 71	99.75 149	99.13 12	99.92 109	99.07 97	99.92 32	99.85 41

HY-MVS	97.30 7	98.85 153	98.64 158	99.47 136	99.42 217	99.08 154	99.62 95	99.36 255	97.39 252	99.28 196	99.68 186	96.44 163	99.92 109	98.37 196	98.22 249	99.40 219

DP-MVS		99.16 95	98.95 119	99.78 61	99.77 67	99.53 92	99.41 227	99.50 147	97.03 287	99.04 252	99.88 43	97.39 121	99.92 109	98.66 157	99.90 48	99.87 35

IB-MVS	95.67 18	96.22 348	95.44 362	98.57 267	99.21 278	96.70 325	98.65 392	97.74 410	96.71 306	97.27 376	98.54 387	86.03 394	99.92 109	98.47 187	86.30 416	99.10 248
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
DeepC-MVS_fast	98.69 1	99.49 27	99.39 34	99.77 64	99.63 141	99.59 79	99.36 251	99.46 199	99.07 46	99.79 56	99.82 87	98.85 42	99.92 109	98.68 155	99.87 66	99.82 62
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
balanced_conf03		99.46 36	99.39 34	99.67 79	99.55 170	99.58 84	99.74 46	99.51 127	98.42 116	99.87 36	99.84 73	98.05 107	99.91 121	99.58 38	99.94 25	99.52 182

9.14			99.10 88		99.72 100		99.40 235	99.51 127	97.53 234	99.64 111	99.78 133	98.84 44	99.91 121	97.63 263	99.82 102

SMA-MVS		99.44 44	99.30 56	99.85 35	99.73 96	99.83 19	99.56 130	99.47 190	97.45 243	99.78 61	99.82 87	99.18 10	99.91 121	98.79 141	99.89 59	99.81 69
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					99.67 120	99.65 66	99.05 335	99.41 229	96.22 345	98.95 267	99.49 263	98.77 54	99.91 121

train_agg		99.02 128	98.77 144	99.77 64	99.67 120	99.65 66	99.05 335	99.41 229	96.28 339	98.95 267	99.49 263	98.76 55	99.91 121	97.63 263	99.72 132	99.75 96

test_8					99.67 120	99.61 76	99.03 340	99.41 229	96.28 339	98.93 270	99.48 269	98.76 55	99.91 121

agg_prior					99.67 120	99.62 74		99.40 235		98.87 280			99.91 121

原ACMM1				99.65 84	99.73 96	99.33 117		99.47 190	97.46 240	99.12 233	99.66 197	98.67 69	99.91 121	97.70 260	99.69 137	99.71 122

LFMVS		97.90 249	97.35 298	99.54 111	99.52 180	99.01 163	99.39 239	98.24 400	97.10 279	99.65 106	99.79 126	84.79 403	99.91 121	99.28 75	98.38 237	99.69 126

XVG-OURS		98.73 167	98.68 153	98.88 228	99.70 110	97.73 269	98.92 365	99.55 86	98.52 105	99.45 152	99.84 73	95.27 204	99.91 121	98.08 222	98.84 211	99.00 264

PLC	97.94 4	99.02 128	98.85 135	99.53 119	99.66 130	99.01 163	99.24 296	99.52 113	96.85 299	99.27 201	99.48 269	98.25 97	99.91 121	97.76 251	99.62 148	99.65 140
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 296	97.06 323	99.47 136	99.61 151	99.09 151	98.04 418	99.25 304	91.24 409	98.51 328	99.70 169	94.55 247	99.91 121	92.76 397	99.85 81	99.42 214
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
mmtdpeth		96.95 334	96.71 333	97.67 353	99.33 244	94.90 379	99.89 2	99.28 298	98.15 150	99.72 82	98.57 386	86.56 392	99.90 133	99.82 23	89.02 411	98.20 381

UWE-MVS		97.58 302	97.29 309	98.48 278	99.09 310	96.25 345	99.01 348	96.61 422	97.86 190	99.19 222	99.01 357	88.72 368	99.90 133	97.38 288	98.69 219	99.28 234

test_vis1_rt		95.81 358	95.65 357	96.32 384	99.67 120	91.35 411	99.49 187	96.74 420	98.25 136	95.24 399	98.10 405	74.96 420	99.90 133	99.53 44	98.85 210	97.70 405

FA-MVS(test-final)		98.75 164	98.53 175	99.41 145	99.55 170	99.05 159	99.80 25	99.01 339	96.59 321	99.58 128	99.59 225	95.39 199	99.90 133	97.78 247	99.49 159	99.28 234

MCST-MVS		99.43 47	99.30 56	99.82 49	99.79 57	99.74 47	99.29 273	99.40 235	98.79 81	99.52 141	99.62 216	98.91 37	99.90 133	98.64 159	99.75 126	99.82 62

CDPH-MVS		99.13 102	98.91 124	99.80 55	99.75 81	99.71 50	99.15 314	99.41 229	96.60 319	99.60 124	99.55 240	98.83 45	99.90 133	97.48 279	99.83 98	99.78 88

NCCC		99.34 67	99.19 79	99.79 58	99.61 151	99.65 66	99.30 268	99.48 169	98.86 71	99.21 216	99.63 211	98.72 64	99.90 133	98.25 207	99.63 147	99.80 78

114514_t		98.93 138	98.67 154	99.72 76	99.85 26	99.53 92	99.62 95	99.59 64	92.65 404	99.71 84	99.78 133	98.06 106	99.90 133	98.84 133	99.91 39	99.74 100

1112_ss		98.98 134	98.77 144	99.59 101	99.68 118	99.02 161	99.25 294	99.48 169	97.23 266	99.13 231	99.58 229	96.93 144	99.90 133	98.87 123	98.78 216	99.84 47

PHI-MVS		99.30 73	99.17 81	99.70 77	99.56 166	99.52 96	99.58 117	99.80 8	97.12 275	99.62 118	99.73 160	98.58 75	99.90 133	98.61 165	99.91 39	99.68 130

AdaColmap		99.01 132	98.80 140	99.66 80	99.56 166	99.54 89	99.18 309	99.70 15	98.18 148	99.35 183	99.63 211	96.32 166	99.90 133	97.48 279	99.77 121	99.55 173

COLMAP_ROB	97.56 6	98.86 146	98.75 146	99.17 185	99.88 11	98.53 219	99.34 259	99.59 64	97.55 230	98.70 306	99.89 35	95.83 185	99.90 133	98.10 217	99.90 48	99.08 253
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 193	98.03 213	99.31 161	99.63 141	98.56 216	99.54 149	96.75 419	97.53 234	99.73 77	99.65 199	91.25 341	99.89 145	98.62 162	99.56 153	99.48 196

tttt0517		98.42 184	98.14 198	99.28 173	99.66 130	98.38 236	99.74 46	96.85 417	97.68 215	99.79 56	99.74 154	91.39 337	99.89 145	98.83 136	99.56 153	99.57 170

test12				99.75 67	99.64 138	99.61 76		99.29 296		99.21 216		98.38 91	99.89 145		99.74 129	99.74 100

Test_1112_low_res		98.89 141	98.66 157	99.57 106	99.69 114	98.95 175	99.03 340	99.47 190	96.98 289	99.15 229	99.23 333	96.77 148	99.89 145	98.83 136	98.78 216	99.86 37

CNLPA		99.14 100	98.99 109	99.59 101	99.58 160	99.41 110	99.16 311	99.44 218	98.45 112	99.19 222	99.49 263	98.08 105	99.89 145	97.73 255	99.75 126	99.48 196

sd_testset		98.75 164	98.57 171	99.29 169	99.81 47	98.26 240	99.56 130	99.62 44	98.78 84	99.64 111	99.88 43	92.02 320	99.88 150	99.54 42	98.26 246	99.72 113

APD_test1		95.87 356	96.49 338	94.00 391	99.53 174	84.01 420	99.54 149	99.32 284	95.91 362	97.99 357	99.85 63	85.49 398	99.88 150	91.96 400	98.84 211	98.12 385

diffmvs		99.14 100	99.02 103	99.51 127	99.61 151	98.96 172	99.28 278	99.49 157	98.46 110	99.72 82	99.71 165	96.50 159	99.88 150	99.31 71	99.11 188	99.67 133
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		98.86 146	98.80 140	99.03 200	99.76 71	98.79 197	99.28 278	99.91 3	97.42 249	99.67 94	99.37 300	97.53 118	99.88 150	98.98 106	97.29 305	98.42 366

PVSNet_Blended		99.08 119	98.97 113	99.42 144	99.76 71	98.79 197	98.78 379	99.91 3	96.74 304	99.67 94	99.49 263	97.53 118	99.88 150	98.98 106	99.85 81	99.60 159

MVS		97.28 323	96.55 336	99.48 133	98.78 357	98.95 175	99.27 283	99.39 238	83.53 422	98.08 352	99.54 245	96.97 142	99.87 155	94.23 378	99.16 182	99.63 152

MG-MVS		99.13 102	99.02 103	99.45 139	99.57 162	98.63 210	99.07 330	99.34 267	98.99 56	99.61 121	99.82 87	97.98 109	99.87 155	97.00 309	99.80 109	99.85 41

MSDG		98.98 134	98.80 140	99.53 119	99.76 71	99.19 136	98.75 382	99.55 86	97.25 263	99.47 149	99.77 142	97.82 112	99.87 155	96.93 316	99.90 48	99.54 175

ETV-MVS		99.26 81	99.21 75	99.40 146	99.46 207	99.30 124	99.56 130	99.52 113	98.52 105	99.44 157	99.27 328	98.41 90	99.86 158	99.10 94	99.59 151	99.04 260

thisisatest0515		98.14 211	97.79 237	99.19 183	99.50 195	98.50 226	98.61 394	96.82 418	96.95 293	99.54 137	99.43 281	91.66 332	99.86 158	98.08 222	99.51 157	99.22 242

thres600view7		97.86 255	97.51 272	98.92 217	99.72 100	97.95 259	99.59 109	98.74 378	97.94 182	99.27 201	98.62 383	91.75 326	99.86 158	93.73 384	98.19 253	98.96 270

lupinMVS		99.13 102	99.01 107	99.46 138	99.51 183	98.94 178	99.05 335	99.16 319	97.86 190	99.80 54	99.56 237	97.39 121	99.86 158	98.94 111	99.85 81	99.58 167

PVSNet	96.02 17	98.85 153	98.84 137	98.89 226	99.73 96	97.28 288	98.32 410	99.60 58	97.86 190	99.50 144	99.57 234	96.75 149	99.86 158	98.56 177	99.70 136	99.54 175

MAR-MVS		98.86 146	98.63 159	99.54 111	99.37 235	99.66 62	99.45 205	99.54 95	96.61 316	99.01 255	99.40 291	97.09 135	99.86 158	97.68 262	99.53 156	99.10 248
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
testing91		97.44 315	97.02 324	98.71 255	99.18 286	96.89 319	99.19 307	99.04 335	97.78 203	98.31 339	98.29 397	85.41 399	99.85 164	98.01 228	97.95 263	99.39 220

test2506		96.81 338	96.65 334	97.29 365	99.74 89	92.21 408	99.60 102	85.06 439	99.13 31	99.77 65	99.93 10	87.82 385	99.85 164	99.38 60	99.38 165	99.80 78

AllTest		98.87 143	98.72 148	99.31 161	99.86 20	98.48 229	99.56 130	99.61 51	97.85 193	99.36 180	99.85 63	95.95 178	99.85 164	96.66 329	99.83 98	99.59 163

TestCases				99.31 161	99.86 20	98.48 229		99.61 51	97.85 193	99.36 180	99.85 63	95.95 178	99.85 164	96.66 329	99.83 98	99.59 163

jason		99.13 102	99.03 99	99.45 139	99.46 207	98.87 185	99.12 320	99.26 302	98.03 175	99.79 56	99.65 199	97.02 140	99.85 164	99.02 103	99.90 48	99.65 140
jason: jason.
CNVR-MVS		99.42 49	99.30 56	99.78 61	99.62 147	99.71 50	99.26 292	99.52 113	98.82 76	99.39 173	99.71 165	98.96 25	99.85 164	98.59 170	99.80 109	99.77 90

PAPM_NR		99.04 125	98.84 137	99.66 80	99.74 89	99.44 106	99.39 239	99.38 246	97.70 213	99.28 196	99.28 325	98.34 93	99.85 164	96.96 313	99.45 161	99.69 126

testing99		97.36 318	96.94 327	98.63 260	99.18 286	96.70 325	99.30 268	98.93 347	97.71 210	98.23 344	98.26 398	84.92 402	99.84 171	98.04 227	97.85 270	99.35 226

testing222		97.16 328	96.50 337	99.16 186	99.16 296	98.47 231	99.27 283	98.66 389	97.71 210	98.23 344	98.15 401	82.28 415	99.84 171	97.36 289	97.66 276	99.18 244

test1111		98.04 226	98.11 202	97.83 343	99.74 89	93.82 393	99.58 117	95.40 426	99.12 36	99.65 106	99.93 10	90.73 346	99.84 171	99.43 58	99.38 165	99.82 62

ECVR-MVS		98.04 226	98.05 211	98.00 328	99.74 89	94.37 388	99.59 109	94.98 427	99.13 31	99.66 99	99.93 10	90.67 347	99.84 171	99.40 59	99.38 165	99.80 78

test_yl		98.86 146	98.63 159	99.54 111	99.49 197	99.18 138	99.50 175	99.07 331	98.22 141	99.61 121	99.51 257	95.37 200	99.84 171	98.60 168	98.33 240	99.59 163

DCV-MVSNet		98.86 146	98.63 159	99.54 111	99.49 197	99.18 138	99.50 175	99.07 331	98.22 141	99.61 121	99.51 257	95.37 200	99.84 171	98.60 168	98.33 240	99.59 163

Fast-Effi-MVS+		98.70 168	98.43 179	99.51 127	99.51 183	99.28 127	99.52 159	99.47 190	96.11 355	99.01 255	99.34 310	96.20 170	99.84 171	97.88 236	98.82 213	99.39 220

TSAR-MVS + GP.		99.36 64	99.36 40	99.36 152	99.67 120	98.61 213	99.07 330	99.33 274	99.00 54	99.82 49	99.81 101	99.06 16	99.84 171	99.09 95	99.42 163	99.65 140

tpmrst		98.33 194	98.48 177	97.90 337	99.16 296	94.78 380	99.31 266	99.11 324	97.27 261	99.45 152	99.59 225	95.33 202	99.84 171	98.48 184	98.61 222	99.09 252

Vis-MVSNet		99.12 108	98.97 113	99.56 108	99.78 59	99.10 150	99.68 66	99.66 28	98.49 107	99.86 40	99.87 52	94.77 231	99.84 171	99.19 83	99.41 164	99.74 100
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 175	98.34 185	99.51 127	99.40 227	99.03 160	98.80 377	99.36 255	96.33 336	99.00 259	99.12 347	98.46 84	99.84 171	95.23 364	99.37 172	99.66 136

PatchMatch-RL		98.84 156	98.62 164	99.52 125	99.71 105	99.28 127	99.06 333	99.77 9	97.74 208	99.50 144	99.53 249	95.41 198	99.84 171	97.17 303	99.64 145	99.44 212

EPP-MVSNet		99.13 102	98.99 109	99.53 119	99.65 136	99.06 157	99.81 20	99.33 274	97.43 247	99.60 124	99.88 43	97.14 133	99.84 171	99.13 89	98.94 202	99.69 126

testing3-2		97.84 260	97.70 252	98.24 310	99.53 174	95.37 369	99.55 144	98.67 388	98.46 110	99.27 201	99.34 310	86.58 391	99.83 184	99.32 70	98.63 221	99.52 182

testing11		97.50 308	97.10 321	98.71 255	99.20 280	96.91 317	99.29 273	98.82 367	97.89 187	98.21 347	98.40 392	85.63 397	99.83 184	98.45 189	98.04 261	99.37 224

thres100view900		97.76 274	97.45 281	98.69 257	99.72 100	97.86 265	99.59 109	98.74 378	97.93 183	99.26 206	98.62 383	91.75 326	99.83 184	93.22 389	98.18 254	98.37 372

tfpn200view9		97.72 284	97.38 294	98.72 253	99.69 114	97.96 257	99.50 175	98.73 384	97.83 196	99.17 227	98.45 390	91.67 330	99.83 184	93.22 389	98.18 254	98.37 372

test_prior				99.68 78	99.67 120	99.48 101		99.56 78					99.83 184			99.74 100

1314		98.68 170	98.54 174	99.11 192	98.89 341	98.65 207	99.27 283	99.49 157	96.89 297	97.99 357	99.56 237	97.72 116	99.83 184	97.74 254	99.27 176	98.84 276

thres400		97.77 273	97.38 294	98.92 217	99.69 114	97.96 257	99.50 175	98.73 384	97.83 196	99.17 227	98.45 390	91.67 330	99.83 184	93.22 389	98.18 254	98.96 270

casdiffmvs		99.13 102	98.98 112	99.56 108	99.65 136	99.16 141	99.56 130	99.50 147	98.33 127	99.41 166	99.86 56	95.92 181	99.83 184	99.45 57	99.16 182	99.70 124
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SPE-MVS-test		99.49 27	99.48 19	99.54 111	99.78 59	99.30 124	99.89 2	99.58 68	98.56 101	99.73 77	99.69 179	98.55 78	99.82 192	99.69 28	99.85 81	99.48 196

MVS_Test		99.10 117	98.97 113	99.48 133	99.49 197	99.14 146	99.67 69	99.34 267	97.31 258	99.58 128	99.76 146	97.65 117	99.82 192	98.87 123	99.07 194	99.46 207

dp		97.75 278	97.80 236	97.59 357	99.10 307	93.71 396	99.32 263	98.88 360	96.48 328	99.08 243	99.55 240	92.67 304	99.82 192	96.52 333	98.58 225	99.24 240

RPSCF		98.22 201	98.62 164	96.99 371	99.82 43	91.58 410	99.72 52	99.44 218	96.61 316	99.66 99	99.89 35	95.92 181	99.82 192	97.46 282	99.10 191	99.57 170

PMMVS		98.80 160	98.62 164	99.34 154	99.27 262	98.70 203	98.76 381	99.31 288	97.34 255	99.21 216	99.07 349	97.20 132	99.82 192	98.56 177	98.87 208	99.52 182

UBG		97.85 256	97.48 275	98.95 211	99.25 269	97.64 276	99.24 296	98.74 378	97.90 186	98.64 316	98.20 400	88.65 372	99.81 197	98.27 206	98.40 235	99.42 214

EIA-MVS		99.18 91	99.09 91	99.45 139	99.49 197	99.18 138	99.67 69	99.53 108	97.66 218	99.40 171	99.44 279	98.10 103	99.81 197	98.94 111	99.62 148	99.35 226

Effi-MVS+		98.81 157	98.59 170	99.48 133	99.46 207	99.12 149	98.08 417	99.50 147	97.50 238	99.38 175	99.41 287	96.37 165	99.81 197	99.11 91	98.54 230	99.51 190

thres200		97.61 300	97.28 310	98.62 261	99.64 138	98.03 251	99.26 292	98.74 378	97.68 215	99.09 241	98.32 396	91.66 332	99.81 197	92.88 394	98.22 249	98.03 391

tpmvs		97.98 237	98.02 215	97.84 342	99.04 320	94.73 381	99.31 266	99.20 314	96.10 359	98.76 296	99.42 283	94.94 217	99.81 197	96.97 312	98.45 234	98.97 268

casdiffmvs_mvg		99.15 97	99.02 103	99.55 110	99.66 130	99.09 151	99.64 84	99.56 78	98.26 135	99.45 152	99.87 52	96.03 175	99.81 197	99.54 42	99.15 185	99.73 105
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	98.81 157	99.37 38	97.12 369	99.60 156	91.75 409	98.61 394	99.44 218	99.35 19	99.83 48	99.85 63	98.70 66	99.81 197	99.02 103	99.91 39	99.81 69

DPM-MVS		98.95 137	98.71 150	99.66 80	99.63 141	99.55 87	98.64 393	99.10 325	97.93 183	99.42 162	99.55 240	98.67 69	99.80 204	95.80 349	99.68 140	99.61 156

DP-MVS Recon		99.12 108	98.95 119	99.65 84	99.74 89	99.70 52	99.27 283	99.57 73	96.40 335	99.42 162	99.68 186	98.75 58	99.80 204	97.98 230	99.72 132	99.44 212

MVS_111021_LR		99.41 53	99.33 46	99.65 84	99.77 67	99.51 97	98.94 363	99.85 6	98.82 76	99.65 106	99.74 154	98.51 81	99.80 204	98.83 136	99.89 59	99.64 147

CS-MVS		99.50 25	99.48 19	99.54 111	99.76 71	99.42 108	99.90 1	99.55 86	98.56 101	99.78 61	99.70 169	98.65 71	99.79 207	99.65 32	99.78 118	99.41 217

Fast-Effi-MVS+-dtu		98.77 163	98.83 139	98.60 262	99.41 222	96.99 311	99.52 159	99.49 157	98.11 158	99.24 208	99.34 310	96.96 143	99.79 207	97.95 232	99.45 161	99.02 263

baseline1		98.31 195	97.95 222	99.38 151	99.50 195	98.74 200	99.59 109	98.93 347	98.41 117	99.14 230	99.60 223	94.59 243	99.79 207	98.48 184	93.29 387	99.61 156

baseline		99.15 97	99.02 103	99.53 119	99.66 130	99.14 146	99.72 52	99.48 169	98.35 124	99.42 162	99.84 73	96.07 173	99.79 207	99.51 47	99.14 186	99.67 133

PVSNet_0	94.43 19	96.09 353	95.47 360	97.94 333	99.31 252	94.34 390	97.81 419	99.70 15	97.12 275	97.46 370	98.75 380	89.71 358	99.79 207	97.69 261	81.69 422	99.68 130

API-MVS		99.04 125	99.03 99	99.06 196	99.40 227	99.31 122	99.55 144	99.56 78	98.54 103	99.33 187	99.39 295	98.76 55	99.78 212	96.98 311	99.78 118	98.07 388

OMC-MVS		99.08 119	99.04 97	99.20 182	99.67 120	98.22 242	99.28 278	99.52 113	98.07 166	99.66 99	99.81 101	97.79 113	99.78 212	97.79 246	99.81 105	99.60 159

GeoE		98.85 153	98.62 164	99.53 119	99.61 151	99.08 154	99.80 25	99.51 127	97.10 279	99.31 189	99.78 133	95.23 208	99.77 214	98.21 209	99.03 197	99.75 96

alignmvs		98.81 157	98.56 173	99.58 104	99.43 215	99.42 108	99.51 168	98.96 345	98.61 97	99.35 183	98.92 370	94.78 228	99.77 214	99.35 62	98.11 259	99.54 175

tpm cat1		97.39 317	97.36 296	97.50 360	99.17 294	93.73 395	99.43 216	99.31 288	91.27 408	98.71 300	99.08 348	94.31 257	99.77 214	96.41 338	98.50 232	99.00 264

CostFormer		97.72 284	97.73 249	97.71 351	99.15 300	94.02 392	99.54 149	99.02 338	94.67 383	99.04 252	99.35 306	92.35 316	99.77 214	98.50 183	97.94 264	99.34 229

MGCFI-Net		99.01 132	98.85 135	99.50 132	99.42 217	99.26 130	99.82 16	99.48 169	98.60 98	99.28 196	98.81 375	97.04 139	99.76 218	99.29 74	97.87 268	99.47 202

test_241102_ONE					99.84 32	99.90 2		99.48 169	99.07 46	99.91 24	99.74 154	99.20 7	99.76 218

MDTV_nov1_ep13			98.32 187		99.11 304	94.44 386	99.27 283	98.74 378	97.51 237	99.40 171	99.62 216	94.78 228	99.76 218	97.59 266	98.81 215

sasdasda		99.02 128	98.86 133	99.51 127	99.42 217	99.32 118	99.80 25	99.48 169	98.63 94	99.31 189	98.81 375	97.09 135	99.75 221	99.27 77	97.90 265	99.47 202

canonicalmvs		99.02 128	98.86 133	99.51 127	99.42 217	99.32 118	99.80 25	99.48 169	98.63 94	99.31 189	98.81 375	97.09 135	99.75 221	99.27 77	97.90 265	99.47 202

Effi-MVS+-dtu		98.78 161	98.89 128	98.47 283	99.33 244	96.91 317	99.57 124	99.30 292	98.47 109	99.41 166	98.99 360	96.78 147	99.74 223	98.73 147	99.38 165	98.74 291

patchmatchnet-post											98.70 381	94.79 227	99.74 223

SCA		98.19 205	98.16 195	98.27 309	99.30 253	95.55 360	99.07 330	98.97 343	97.57 227	99.43 159	99.57 234	92.72 299	99.74 223	97.58 267	99.20 180	99.52 182

BH-untuned		98.42 184	98.36 183	98.59 263	99.49 197	96.70 325	99.27 283	99.13 323	97.24 265	98.80 291	99.38 297	95.75 188	99.74 223	97.07 307	99.16 182	99.33 230

BH-RMVSNet		98.41 186	98.08 207	99.40 146	99.41 222	98.83 193	99.30 268	98.77 374	97.70 213	98.94 269	99.65 199	92.91 294	99.74 223	96.52 333	99.55 155	99.64 147

MVS_111021_HR		99.41 53	99.32 48	99.66 80	99.72 100	99.47 103	98.95 361	99.85 6	98.82 76	99.54 137	99.73 160	98.51 81	99.74 223	98.91 117	99.88 63	99.77 90

test_post											65.99 433	94.65 241	99.73 229

XVG-ACMP-BASELINE		97.83 263	97.71 251	98.20 312	99.11 304	96.33 341	99.41 227	99.52 113	98.06 170	99.05 251	99.50 260	89.64 360	99.73 229	97.73 255	97.38 303	98.53 354

HyFIR lowres test		99.11 113	98.92 122	99.65 84	99.90 4	99.37 112	99.02 343	99.91 3	97.67 217	99.59 127	99.75 149	95.90 183	99.73 229	99.53 44	99.02 199	99.86 37

DeepMVS_CX				93.34 394	99.29 257	82.27 423		99.22 310	85.15 420	96.33 391	99.05 352	90.97 344	99.73 229	93.57 386	97.77 273	98.01 392

Patchmatch-test		97.93 243	97.65 257	98.77 249	99.18 286	97.07 302	99.03 340	99.14 322	96.16 350	98.74 297	99.57 234	94.56 245	99.72 233	93.36 388	99.11 188	99.52 182

LPG-MVS_test		98.22 201	98.13 200	98.49 276	99.33 244	97.05 304	99.58 117	99.55 86	97.46 240	99.24 208	99.83 78	92.58 306	99.72 233	98.09 218	97.51 289	98.68 309

LGP-MVS_train				98.49 276	99.33 244	97.05 304		99.55 86	97.46 240	99.24 208	99.83 78	92.58 306	99.72 233	98.09 218	97.51 289	98.68 309

BH-w/o		98.00 235	97.89 231	98.32 301	99.35 239	96.20 347	99.01 348	98.90 357	96.42 333	98.38 335	99.00 358	95.26 206	99.72 233	96.06 342	98.61 222	99.03 261

ACMP	97.20 11	98.06 220	97.94 224	98.45 286	99.37 235	97.01 309	99.44 211	99.49 157	97.54 233	98.45 332	99.79 126	91.95 322	99.72 233	97.91 234	97.49 294	98.62 337
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 230	97.90 227	98.40 294	99.23 273	96.80 323	99.70 56	99.60 58	97.12 275	98.18 349	99.70 169	91.73 328	99.72 233	98.39 193	97.45 296	98.68 309
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
test_post1							99.23 299				65.14 434	94.18 262	99.71 239	97.58 267

ADS-MVSNet		98.20 204	98.08 207	98.56 270	99.33 244	96.48 336	99.23 299	99.15 320	96.24 343	99.10 238	99.67 192	94.11 263	99.71 239	96.81 321	99.05 195	99.48 196

JIA-IIPM		97.50 308	97.02 324	98.93 215	98.73 366	97.80 267	99.30 268	98.97 343	91.73 407	98.91 272	94.86 422	95.10 212	99.71 239	97.58 267	97.98 262	99.28 234

EPMVS		97.82 266	97.65 257	98.35 298	98.88 342	95.98 351	99.49 187	94.71 429	97.57 227	99.26 206	99.48 269	92.46 313	99.71 239	97.87 238	99.08 193	99.35 226

TDRefinement		95.42 362	94.57 369	97.97 330	89.83 432	96.11 350	99.48 192	98.75 375	96.74 304	96.68 388	99.88 43	88.65 372	99.71 239	98.37 196	82.74 421	98.09 387

ACMM	97.58 5	98.37 192	98.34 185	98.48 278	99.41 222	97.10 298	99.56 130	99.45 210	98.53 104	99.04 252	99.85 63	93.00 290	99.71 239	98.74 145	97.45 296	98.64 328
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 240	97.77 242	98.57 267	99.59 158	96.61 332	99.45 205	99.08 328	98.21 143	98.88 277	99.80 114	88.66 371	99.70 245	98.58 171	97.72 274	99.39 220

CHOSEN 280x420		99.12 108	99.13 84	99.08 193	99.66 130	97.89 262	98.43 404	99.71 13	98.88 70	99.62 118	99.76 146	96.63 153	99.70 245	99.46 56	99.99 1	99.66 136

EC-MVSNet		99.44 44	99.39 34	99.58 104	99.56 166	99.49 99	99.88 4	99.58 68	98.38 119	99.73 77	99.69 179	98.20 99	99.70 245	99.64 34	99.82 102	99.54 175

PatchmatchNet		98.31 195	98.36 183	98.19 313	99.16 296	95.32 370	99.27 283	98.92 350	97.37 253	99.37 177	99.58 229	94.90 221	99.70 245	97.43 285	99.21 179	99.54 175
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 215	97.99 217	98.44 289	99.41 222	96.96 315	99.60 102	99.56 78	98.09 161	98.15 350	99.91 23	90.87 345	99.70 245	98.88 120	97.45 296	98.67 316
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 308	96.90 328	99.29 169	99.23 273	98.78 199	99.32 263	98.90 357	97.52 236	98.56 325	98.09 406	84.72 404	99.69 250	97.86 239	97.88 267	99.39 220

HQP_MVS		98.27 200	98.22 193	98.44 289	99.29 257	96.97 313	99.39 239	99.47 190	98.97 62	99.11 235	99.61 220	92.71 301	99.69 250	97.78 247	97.63 277	98.67 316

plane_prior5								99.47 190					99.69 250	97.78 247	97.63 277	98.67 316

D2MVS		98.41 186	98.50 176	98.15 318	99.26 265	96.62 331	99.40 235	99.61 51	97.71 210	98.98 262	99.36 303	96.04 174	99.67 253	98.70 150	97.41 301	98.15 384

IS-MVSNet		99.05 124	98.87 131	99.57 106	99.73 96	99.32 118	99.75 42	99.20 314	98.02 177	99.56 132	99.86 56	96.54 157	99.67 253	98.09 218	99.13 187	99.73 105

CLD-MVS		98.16 209	98.10 203	98.33 299	99.29 257	96.82 322	98.75 382	99.44 218	97.83 196	99.13 231	99.55 240	92.92 292	99.67 253	98.32 203	97.69 275	98.48 358
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 325	97.30 307	97.09 370	99.43 215	93.31 401	99.73 50	98.87 362	98.83 75	99.28 196	99.80 114	84.45 405	99.66 256	97.88 236	97.45 296	98.30 374

AUN-MVS		96.88 336	96.31 342	98.59 263	99.48 204	97.04 307	99.27 283	99.22 310	97.44 246	98.51 328	99.41 287	91.97 321	99.66 256	97.71 258	83.83 419	99.07 258

UniMVSNet_ETH3D		97.32 322	96.81 330	98.87 232	99.40 227	97.46 282	99.51 168	99.53 108	95.86 363	98.54 327	99.77 142	82.44 413	99.66 256	98.68 155	97.52 288	99.50 194

OPM-MVS		98.19 205	98.10 203	98.45 286	98.88 342	97.07 302	99.28 278	99.38 246	98.57 100	99.22 213	99.81 101	92.12 318	99.66 256	98.08 222	97.54 286	98.61 346
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 246	97.78 240	98.32 301	99.46 207	96.68 329	99.56 130	99.54 95	98.41 117	97.79 366	99.87 52	90.18 354	99.66 256	98.05 226	97.18 310	98.62 337

hse-mvs2		97.50 308	97.14 318	98.59 263	99.49 197	97.05 304	99.28 278	99.22 310	98.94 65	99.66 99	99.42 283	94.93 218	99.65 261	99.48 53	83.80 420	99.08 253

VPA-MVSNet		98.29 198	97.95 222	99.30 166	99.16 296	99.54 89	99.50 175	99.58 68	98.27 133	99.35 183	99.37 300	92.53 308	99.65 261	99.35 62	94.46 369	98.72 293

TR-MVS		97.76 274	97.41 292	98.82 241	99.06 316	97.87 263	98.87 371	98.56 392	96.63 315	98.68 308	99.22 334	92.49 309	99.65 261	95.40 360	97.79 272	98.95 272

reproduce_monomvs		97.89 250	97.87 232	97.96 332	99.51 183	95.45 365	99.60 102	99.25 304	99.17 26	98.85 285	99.49 263	89.29 363	99.64 264	99.35 62	96.31 326	98.78 279

gm-plane-assit					98.54 386	92.96 403			94.65 384		99.15 342		99.64 264	97.56 272

HQP4-MVS										98.66 309			99.64 264			98.64 328

HQP-MVS		98.02 230	97.90 227	98.37 297	99.19 283	96.83 320	98.98 354	99.39 238	98.24 137	98.66 309	99.40 291	92.47 310	99.64 264	97.19 300	97.58 282	98.64 328

PAPM		97.59 301	97.09 322	99.07 194	99.06 316	98.26 240	98.30 411	99.10 325	94.88 378	98.08 352	99.34 310	96.27 168	99.64 264	89.87 408	98.92 205	99.31 232

TAPA-MVS	97.07 15	97.74 280	97.34 301	98.94 213	99.70 110	97.53 279	99.25 294	99.51 127	91.90 406	99.30 192	99.63 211	98.78 51	99.64 264	88.09 415	99.87 66	99.65 140
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 190	98.09 206	99.24 178	99.26 265	99.32 118	99.56 130	99.55 86	97.45 243	98.71 300	99.83 78	93.23 285	99.63 270	98.88 120	96.32 325	98.76 285

ITE_SJBPF				98.08 321	99.29 257	96.37 339		98.92 350	98.34 125	98.83 286	99.75 149	91.09 342	99.62 271	95.82 347	97.40 302	98.25 378

LF4IMVS		97.52 305	97.46 280	97.70 352	98.98 331	95.55 360	99.29 273	98.82 367	98.07 166	98.66 309	99.64 205	89.97 355	99.61 272	97.01 308	96.68 315	97.94 399

tpm		97.67 295	97.55 266	98.03 323	99.02 322	95.01 376	99.43 216	98.54 394	96.44 331	99.12 233	99.34 310	91.83 325	99.60 273	97.75 253	96.46 321	99.48 196

tpm2		97.44 315	97.34 301	97.74 350	99.15 300	94.36 389	99.45 205	98.94 346	93.45 397	98.90 274	99.44 279	91.35 338	99.59 274	97.31 291	98.07 260	99.29 233

baseline2		97.87 253	97.55 266	98.82 241	99.18 286	98.02 252	99.41 227	96.58 423	96.97 290	96.51 389	99.17 339	93.43 282	99.57 275	97.71 258	99.03 197	98.86 274

MS-PatchMatch		97.24 327	97.32 305	96.99 371	98.45 389	93.51 400	98.82 375	99.32 284	97.41 250	98.13 351	99.30 321	88.99 365	99.56 276	95.68 353	99.80 109	97.90 402

TinyColmap		97.12 330	96.89 329	97.83 343	99.07 314	95.52 363	98.57 397	98.74 378	97.58 226	97.81 365	99.79 126	88.16 379	99.56 276	95.10 365	97.21 308	98.39 370

USDC		97.34 320	97.20 315	97.75 348	99.07 314	95.20 372	98.51 401	99.04 335	97.99 178	98.31 339	99.86 56	89.02 364	99.55 278	95.67 354	97.36 304	98.49 357

MSLP-MVS++		99.46 36	99.47 21	99.44 143	99.60 156	99.16 141	99.41 227	99.71 13	98.98 59	99.45 152	99.78 133	99.19 9	99.54 279	99.28 75	99.84 89	99.63 152

UWE-MVS-28		97.36 318	97.24 314	97.75 348	98.84 351	94.44 386	99.24 296	97.58 412	97.98 179	99.00 259	99.00 358	91.35 338	99.53 280	93.75 383	98.39 236	99.27 238

TAMVS		99.12 108	99.08 92	99.24 178	99.46 207	98.55 217	99.51 168	99.46 199	98.09 161	99.45 152	99.82 87	98.34 93	99.51 281	98.70 150	98.93 203	99.67 133

EPNet_dtu		98.03 228	97.96 220	98.23 311	98.27 392	95.54 362	99.23 299	98.75 375	99.02 49	97.82 364	99.71 165	96.11 172	99.48 282	93.04 392	99.65 144	99.69 126
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 340	96.22 344	97.97 330	97.00 414	96.28 343	98.66 391	99.03 337	96.61 316	96.93 386	99.79 126	87.20 388	99.47 283	96.65 331	94.13 376	98.16 383

EG-PatchMatch MVS		95.97 355	95.69 356	96.81 378	97.78 399	92.79 404	99.16 311	98.93 347	96.16 350	94.08 407	99.22 334	82.72 411	99.47 283	95.67 354	97.50 291	98.17 382

myMVS_eth3d28		97.69 289	97.34 301	98.73 251	99.27 262	97.52 280	99.33 261	98.78 373	98.03 175	98.82 288	98.49 388	86.64 390	99.46 285	98.44 190	98.24 248	99.23 241

MVP-Stereo		97.81 268	97.75 247	97.99 329	97.53 403	96.60 333	98.96 358	98.85 364	97.22 267	97.23 377	99.36 303	95.28 203	99.46 285	95.51 356	99.78 118	97.92 401
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 177	98.67 154	98.30 303	99.35 239	95.59 359	99.50 175	99.55 86	98.60 98	99.39 173	99.83 78	94.48 250	99.45 287	98.75 144	98.56 228	99.85 41

test-LLR		98.06 220	97.90 227	98.55 272	98.79 354	97.10 298	98.67 388	97.75 408	97.34 255	98.61 321	98.85 372	94.45 252	99.45 287	97.25 294	99.38 165	99.10 248

TESTMET0.1,1		97.55 303	97.27 313	98.40 294	98.93 336	96.53 334	98.67 388	97.61 411	96.96 291	98.64 316	99.28 325	88.63 374	99.45 287	97.30 292	99.38 165	99.21 243

test-mter		97.49 313	97.13 320	98.55 272	98.79 354	97.10 298	98.67 388	97.75 408	96.65 311	98.61 321	98.85 372	88.23 378	99.45 287	97.25 294	99.38 165	99.10 248

mvs_anonymous		99.03 127	98.99 109	99.16 186	99.38 232	98.52 223	99.51 168	99.38 246	97.79 201	99.38 175	99.81 101	97.30 127	99.45 287	99.35 62	98.99 200	99.51 190

tfpnnormal		97.84 260	97.47 278	98.98 206	99.20 280	99.22 135	99.64 84	99.61 51	96.32 337	98.27 343	99.70 169	93.35 284	99.44 292	95.69 352	95.40 352	98.27 376

v7n		97.87 253	97.52 270	98.92 217	98.76 364	98.58 215	99.84 12	99.46 199	96.20 346	98.91 272	99.70 169	94.89 222	99.44 292	96.03 343	93.89 381	98.75 287

jajsoiax		98.43 183	98.28 190	98.88 228	98.60 381	98.43 233	99.82 16	99.53 108	98.19 145	98.63 318	99.80 114	93.22 287	99.44 292	99.22 81	97.50 291	98.77 283

mvs_tets		98.40 189	98.23 192	98.91 221	98.67 374	98.51 225	99.66 75	99.53 108	98.19 145	98.65 315	99.81 101	92.75 296	99.44 292	99.31 71	97.48 295	98.77 283

Vis-MVSNet (Re-imp)		98.87 143	98.72 148	99.31 161	99.71 105	98.88 184	99.80 25	99.44 218	97.91 185	99.36 180	99.78 133	95.49 197	99.43 296	97.91 234	99.11 188	99.62 154

OPU-MVS				99.64 90	99.56 166	99.72 48	99.60 102				99.70 169	99.27 5	99.42 297	98.24 208	99.80 109	99.79 82

Anonymous20231211		97.88 251	97.54 269	98.90 223	99.71 105	98.53 219	99.48 192	99.57 73	94.16 388	98.81 289	99.68 186	93.23 285	99.42 297	98.84 133	94.42 371	98.76 285

ttmdpeth		97.80 270	97.63 261	98.29 304	98.77 362	97.38 285	99.64 84	99.36 255	98.78 84	96.30 392	99.58 229	92.34 317	99.39 299	98.36 198	95.58 347	98.10 386

VPNet		97.84 260	97.44 286	99.01 202	99.21 278	98.94 178	99.48 192	99.57 73	98.38 119	99.28 196	99.73 160	88.89 366	99.39 299	99.19 83	93.27 388	98.71 295

nrg030		98.64 174	98.42 180	99.28 173	99.05 319	99.69 54	99.81 20	99.46 199	98.04 173	99.01 255	99.82 87	96.69 151	99.38 301	99.34 67	94.59 368	98.78 279

GA-MVS		97.85 256	97.47 278	99.00 204	99.38 232	97.99 254	98.57 397	99.15 320	97.04 286	98.90 274	99.30 321	89.83 357	99.38 301	96.70 326	98.33 240	99.62 154

UniMVSNet (Re)		98.29 198	98.00 216	99.13 191	99.00 325	99.36 115	99.49 187	99.51 127	97.95 181	98.97 264	99.13 344	96.30 167	99.38 301	98.36 198	93.34 386	98.66 324

FIs		98.78 161	98.63 159	99.23 180	99.18 286	99.54 89	99.83 15	99.59 64	98.28 131	98.79 293	99.81 101	96.75 149	99.37 304	99.08 96	96.38 323	98.78 279

PS-MVSNAJss		98.92 139	98.92 122	98.90 223	98.78 357	98.53 219	99.78 32	99.54 95	98.07 166	99.00 259	99.76 146	99.01 18	99.37 304	99.13 89	97.23 307	98.81 277

CDS-MVSNet		99.09 118	99.03 99	99.25 176	99.42 217	98.73 201	99.45 205	99.46 199	98.11 158	99.46 151	99.77 142	98.01 108	99.37 304	98.70 150	98.92 205	99.66 136
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 359	95.16 364	97.51 359	99.30 253	93.69 397	98.88 369	95.78 424	85.09 421	98.78 294	92.65 424	91.29 340	99.37 304	94.85 370	99.85 81	99.46 207

v1192		97.81 268	97.44 286	98.91 221	98.88 342	98.68 204	99.51 168	99.34 267	96.18 348	99.20 219	99.34 310	94.03 267	99.36 308	95.32 362	95.18 356	98.69 304

EI-MVSNet		98.67 171	98.67 154	98.68 258	99.35 239	97.97 255	99.50 175	99.38 246	96.93 296	99.20 219	99.83 78	97.87 110	99.36 308	98.38 194	97.56 284	98.71 295

MVSTER		98.49 178	98.32 187	99.00 204	99.35 239	99.02 161	99.54 149	99.38 246	97.41 250	99.20 219	99.73 160	93.86 275	99.36 308	98.87 123	97.56 284	98.62 337

gg-mvs-nofinetune		96.17 351	95.32 363	98.73 251	98.79 354	98.14 246	99.38 244	94.09 430	91.07 411	98.07 355	91.04 428	89.62 361	99.35 311	96.75 323	99.09 192	98.68 309

pm-mvs1		97.68 292	97.28 310	98.88 228	99.06 316	98.62 211	99.50 175	99.45 210	96.32 337	97.87 362	99.79 126	92.47 310	99.35 311	97.54 274	93.54 385	98.67 316

OurMVSNet-221017-0		97.88 251	97.77 242	98.19 313	98.71 370	96.53 334	99.88 4	99.00 340	97.79 201	98.78 294	99.94 6	91.68 329	99.35 311	97.21 296	96.99 314	98.69 304

EGC-MVSNET		82.80 393	77.86 399	97.62 355	97.91 396	96.12 349	99.33 261	99.28 298	8.40 436	25.05 437	99.27 328	84.11 406	99.33 314	89.20 410	98.22 249	97.42 410

pmmvs6		96.53 343	96.09 348	97.82 345	98.69 372	95.47 364	99.37 246	99.47 190	93.46 396	97.41 371	99.78 133	87.06 389	99.33 314	96.92 318	92.70 395	98.65 326

V42		98.06 220	97.79 237	98.86 235	98.98 331	98.84 190	99.69 60	99.34 267	96.53 323	99.30 192	99.37 300	94.67 239	99.32 316	97.57 271	94.66 366	98.42 366

lessismore_v0				97.79 347	98.69 372	95.44 367		94.75 428		95.71 398	99.87 52	88.69 370	99.32 316	95.89 346	94.93 363	98.62 337

OpenMVS_ROB	92.34 20	94.38 373	93.70 379	96.41 383	97.38 405	93.17 402	99.06 333	98.75 375	86.58 419	94.84 405	98.26 398	81.53 416	99.32 316	89.01 411	97.87 268	96.76 413

v8		97.95 242	97.63 261	98.93 215	98.95 335	98.81 196	99.80 25	99.41 229	96.03 360	99.10 238	99.42 283	94.92 220	99.30 319	96.94 315	94.08 378	98.66 324

v1921920		97.80 270	97.45 281	98.84 239	98.80 353	98.53 219	99.52 159	99.34 267	96.15 352	99.24 208	99.47 272	93.98 269	99.29 320	95.40 360	95.13 358	98.69 304

anonymousdsp		98.44 182	98.28 190	98.94 213	98.50 387	98.96 172	99.77 34	99.50 147	97.07 281	98.87 280	99.77 142	94.76 232	99.28 321	98.66 157	97.60 280	98.57 352

MVSFormer		99.17 93	99.12 86	99.29 169	99.51 183	98.94 178	99.88 4	99.46 199	97.55 230	99.80 54	99.65 199	97.39 121	99.28 321	99.03 101	99.85 81	99.65 140

test_djsdf		98.67 171	98.57 171	98.98 206	98.70 371	98.91 182	99.88 4	99.46 199	97.55 230	99.22 213	99.88 43	95.73 189	99.28 321	99.03 101	97.62 279	98.75 287

SSC-MVS3.2		97.34 320	97.15 317	97.93 334	99.02 322	95.76 356	99.48 192	99.58 68	97.62 222	99.09 241	99.53 249	87.95 381	99.27 324	96.42 336	95.66 345	98.75 287

cascas		97.69 289	97.43 290	98.48 278	98.60 381	97.30 287	98.18 415	99.39 238	92.96 400	98.41 333	98.78 379	93.77 278	99.27 324	98.16 215	98.61 222	98.86 274

v144192		97.92 246	97.60 264	98.87 232	98.83 352	98.65 207	99.55 144	99.34 267	96.20 346	99.32 188	99.40 291	94.36 254	99.26 326	96.37 339	95.03 360	98.70 300

dmvs_re		98.08 218	98.16 195	97.85 340	99.55 170	94.67 383	99.70 56	98.92 350	98.15 150	99.06 249	99.35 306	93.67 281	99.25 327	97.77 250	97.25 306	99.64 147

v2v482		98.06 220	97.77 242	98.92 217	98.90 340	98.82 194	99.57 124	99.36 255	96.65 311	99.19 222	99.35 306	94.20 259	99.25 327	97.72 257	94.97 361	98.69 304

v1240		97.69 289	97.32 305	98.79 247	98.85 349	98.43 233	99.48 192	99.36 255	96.11 355	99.27 201	99.36 303	93.76 279	99.24 329	94.46 374	95.23 355	98.70 300

WBMVS		97.74 280	97.50 273	98.46 284	99.24 271	97.43 283	99.21 305	99.42 226	97.45 243	98.96 266	99.41 287	88.83 367	99.23 330	98.94 111	96.02 331	98.71 295

v1144		97.98 237	97.69 253	98.85 238	98.87 345	98.66 206	99.54 149	99.35 262	96.27 341	99.23 212	99.35 306	94.67 239	99.23 330	96.73 324	95.16 357	98.68 309

v10		97.85 256	97.52 270	98.86 235	98.99 328	98.67 205	99.75 42	99.41 229	95.70 364	98.98 262	99.41 287	94.75 233	99.23 330	96.01 345	94.63 367	98.67 316

WR-MVS_H		98.13 212	97.87 232	98.90 223	99.02 322	98.84 190	99.70 56	99.59 64	97.27 261	98.40 334	99.19 338	95.53 195	99.23 330	98.34 200	93.78 383	98.61 346

miper_enhance_ethall		98.16 209	98.08 207	98.41 292	98.96 334	97.72 271	98.45 403	99.32 284	96.95 293	98.97 264	99.17 339	97.06 138	99.22 334	97.86 239	95.99 334	98.29 375

GG-mvs-BLEND				98.45 286	98.55 385	98.16 244	99.43 216	93.68 431		97.23 377	98.46 389	89.30 362	99.22 334	95.43 359	98.22 249	97.98 397

FC-MVSNet-test		98.75 164	98.62 164	99.15 190	99.08 313	99.45 105	99.86 11	99.60 58	98.23 140	98.70 306	99.82 87	96.80 146	99.22 334	99.07 97	96.38 323	98.79 278

UniMVSNet_NR-MVSNet		98.22 201	97.97 219	98.96 209	98.92 338	98.98 165	99.48 192	99.53 108	97.76 205	98.71 300	99.46 276	96.43 164	99.22 334	98.57 174	92.87 393	98.69 304

DU-MVS		98.08 218	97.79 237	98.96 209	98.87 345	98.98 165	99.41 227	99.45 210	97.87 189	98.71 300	99.50 260	94.82 224	99.22 334	98.57 174	92.87 393	98.68 309

cl____		98.01 233	97.84 235	98.55 272	99.25 269	97.97 255	98.71 386	99.34 267	96.47 330	98.59 324	99.54 245	95.65 192	99.21 339	97.21 296	95.77 340	98.46 363

WR-MVS		98.06 220	97.73 249	99.06 196	98.86 348	99.25 132	99.19 307	99.35 262	97.30 259	98.66 309	99.43 281	93.94 270	99.21 339	98.58 171	94.28 373	98.71 295

test_0402		96.64 341	96.24 343	97.85 340	98.85 349	96.43 338	99.44 211	99.26 302	93.52 394	96.98 384	99.52 253	88.52 375	99.20 341	92.58 399	97.50 291	97.93 400

SixPastTwentyTwo		97.50 308	97.33 304	98.03 323	98.65 375	96.23 346	99.77 34	98.68 387	97.14 272	97.90 360	99.93 10	90.45 348	99.18 342	97.00 309	96.43 322	98.67 316

cl22		97.85 256	97.64 260	98.48 278	99.09 310	97.87 263	98.60 396	99.33 274	97.11 278	98.87 280	99.22 334	92.38 315	99.17 343	98.21 209	95.99 334	98.42 366

WB-MVSnew		97.65 297	97.65 257	97.63 354	98.78 357	97.62 277	99.13 317	98.33 397	97.36 254	99.07 244	98.94 366	95.64 193	99.15 344	92.95 393	98.68 220	96.12 420

IterMVS-SCA-FT		97.82 266	97.75 247	98.06 322	99.57 162	96.36 340	99.02 343	99.49 157	97.18 269	98.71 300	99.72 164	92.72 299	99.14 345	97.44 284	95.86 339	98.67 316

pmmvs5		97.52 305	97.30 307	98.16 315	98.57 384	96.73 324	99.27 283	98.90 357	96.14 353	98.37 336	99.53 249	91.54 335	99.14 345	97.51 276	95.87 338	98.63 335

v148		97.79 272	97.55 266	98.50 275	98.74 365	97.72 271	99.54 149	99.33 274	96.26 342	98.90 274	99.51 257	94.68 238	99.14 345	97.83 243	93.15 390	98.63 335

miper_ehance_all_eth		98.18 207	98.10 203	98.41 292	99.23 273	97.72 271	98.72 385	99.31 288	96.60 319	98.88 277	99.29 323	97.29 128	99.13 348	97.60 265	95.99 334	98.38 371

NR-MVSNet		97.97 240	97.61 263	99.02 201	98.87 345	99.26 130	99.47 200	99.42 226	97.63 220	97.08 382	99.50 260	95.07 213	99.13 348	97.86 239	93.59 384	98.68 309

IterMVS		97.83 263	97.77 242	98.02 325	99.58 160	96.27 344	99.02 343	99.48 169	97.22 267	98.71 300	99.70 169	92.75 296	99.13 348	97.46 282	96.00 333	98.67 316
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 374	94.90 366	91.84 399	97.24 409	80.01 429	98.52 400	99.48 169	89.01 416	91.99 416	99.67 192	85.67 396	99.13 348	95.44 358	97.03 313	96.39 417
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 225	97.96 220	98.33 299	99.26 265	97.38 285	98.56 399	99.31 288	96.65 311	98.88 277	99.52 253	96.58 155	99.12 352	97.39 287	95.53 350	98.47 360

pmmvs4		98.13 212	97.90 227	98.81 244	98.61 380	98.87 185	98.99 351	99.21 313	96.44 331	99.06 249	99.58 229	95.90 183	99.11 353	97.18 302	96.11 330	98.46 363

TransMVSNet (Re)		97.15 329	96.58 335	98.86 235	99.12 302	98.85 189	99.49 187	98.91 355	95.48 367	97.16 380	99.80 114	93.38 283	99.11 353	94.16 380	91.73 399	98.62 337

ambc				93.06 397	92.68 428	82.36 422	98.47 402	98.73 384		95.09 403	97.41 411	55.55 429	99.10 355	96.42 336	91.32 400	97.71 403

Baseline_NR-MVSNet		97.76 274	97.45 281	98.68 258	99.09 310	98.29 238	99.41 227	98.85 364	95.65 365	98.63 318	99.67 192	94.82 224	99.10 355	98.07 225	92.89 392	98.64 328

test_vis3_rt		87.04 389	85.81 392	90.73 403	93.99 427	81.96 424	99.76 37	90.23 438	92.81 402	81.35 426	91.56 426	40.06 435	99.07 357	94.27 377	88.23 413	91.15 426

CP-MVSNet		98.09 216	97.78 240	99.01 202	98.97 333	99.24 133	99.67 69	99.46 199	97.25 263	98.48 331	99.64 205	93.79 277	99.06 358	98.63 161	94.10 377	98.74 291

PS-CasMVS		97.93 243	97.59 265	98.95 211	98.99 328	99.06 157	99.68 66	99.52 113	97.13 273	98.31 339	99.68 186	92.44 314	99.05 359	98.51 182	94.08 378	98.75 287

K. test v3		97.10 331	96.79 331	98.01 326	98.72 368	96.33 341	99.87 8	97.05 415	97.59 224	96.16 394	99.80 114	88.71 369	99.04 360	96.69 327	96.55 320	98.65 326

new_pmnet		96.38 347	96.03 349	97.41 361	98.13 395	95.16 375	99.05 335	99.20 314	93.94 389	97.39 374	98.79 378	91.61 334	99.04 360	90.43 406	95.77 340	98.05 390

DIV-MVS_self_test		98.01 233	97.85 234	98.48 278	99.24 271	97.95 259	98.71 386	99.35 262	96.50 324	98.60 323	99.54 245	95.72 190	99.03 362	97.21 296	95.77 340	98.46 363

IterMVS-LS		98.46 181	98.42 180	98.58 266	99.59 158	98.00 253	99.37 246	99.43 224	96.94 295	99.07 244	99.59 225	97.87 110	99.03 362	98.32 203	95.62 346	98.71 295
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 297	97.68 254	97.55 358	98.62 378	94.97 377	98.84 373	99.30 292	96.83 302	98.19 348	99.34 310	97.01 141	99.02 364	95.00 368	96.01 332	98.64 328

Patchmtry		97.75 278	97.40 293	98.81 244	99.10 307	98.87 185	99.11 326	99.33 274	94.83 380	98.81 289	99.38 297	94.33 255	99.02 364	96.10 341	95.57 348	98.53 354

N_pmnet		94.95 368	95.83 354	92.31 398	98.47 388	79.33 430	99.12 320	92.81 436	93.87 390	97.68 367	99.13 344	93.87 274	99.01 366	91.38 403	96.19 328	98.59 350

CR-MVSNet		98.17 208	97.93 225	98.87 232	99.18 286	98.49 227	99.22 303	99.33 274	96.96 291	99.56 132	99.38 297	94.33 255	99.00 367	94.83 371	98.58 225	99.14 245

c3_l		98.12 214	98.04 212	98.38 296	99.30 253	97.69 275	98.81 376	99.33 274	96.67 309	98.83 286	99.34 310	97.11 134	98.99 368	97.58 267	95.34 353	98.48 358

test0.0.03 1		97.71 287	97.42 291	98.56 270	98.41 391	97.82 266	98.78 379	98.63 390	97.34 255	98.05 356	98.98 362	94.45 252	98.98 369	95.04 367	97.15 311	98.89 273

PatchT		97.03 333	96.44 339	98.79 247	98.99 328	98.34 237	99.16 311	99.07 331	92.13 405	99.52 141	97.31 415	94.54 248	98.98 369	88.54 413	98.73 218	99.03 261

GBi-Net		97.68 292	97.48 275	98.29 304	99.51 183	97.26 291	99.43 216	99.48 169	96.49 325	99.07 244	99.32 318	90.26 350	98.98 369	97.10 304	96.65 316	98.62 337

test1		97.68 292	97.48 275	98.29 304	99.51 183	97.26 291	99.43 216	99.48 169	96.49 325	99.07 244	99.32 318	90.26 350	98.98 369	97.10 304	96.65 316	98.62 337

FMVSNet3		98.03 228	97.76 246	98.84 239	99.39 230	98.98 165	99.40 235	99.38 246	96.67 309	99.07 244	99.28 325	92.93 291	98.98 369	97.10 304	96.65 316	98.56 353

FMVSNet2		97.72 284	97.36 296	98.80 246	99.51 183	98.84 190	99.45 205	99.42 226	96.49 325	98.86 284	99.29 323	90.26 350	98.98 369	96.44 335	96.56 319	98.58 351

FMVSNet1		96.84 337	96.36 341	98.29 304	99.32 251	97.26 291	99.43 216	99.48 169	95.11 372	98.55 326	99.32 318	83.95 407	98.98 369	95.81 348	96.26 327	98.62 337

ppachtmachnet_test		97.49 313	97.45 281	97.61 356	98.62 378	95.24 371	98.80 377	99.46 199	96.11 355	98.22 346	99.62 216	96.45 162	98.97 376	93.77 382	95.97 337	98.61 346

TranMVSNet+NR-MVSNet		97.93 243	97.66 256	98.76 250	98.78 357	98.62 211	99.65 81	99.49 157	97.76 205	98.49 330	99.60 223	94.23 258	98.97 376	98.00 229	92.90 391	98.70 300

MVStest1		96.08 354	95.48 359	97.89 338	98.93 336	96.70 325	99.56 130	99.35 262	92.69 403	91.81 417	99.46 276	89.90 356	98.96 378	95.00 368	92.61 396	98.00 395

test_method		91.10 384	91.36 386	90.31 404	95.85 417	73.72 437	94.89 425	99.25 304	68.39 428	95.82 397	99.02 356	80.50 418	98.95 379	93.64 385	94.89 365	98.25 378

ADS-MVSNet2		98.02 230	98.07 210	97.87 339	99.33 244	95.19 373	99.23 299	99.08 328	96.24 343	99.10 238	99.67 192	94.11 263	98.93 380	96.81 321	99.05 195	99.48 196

ET-MVSNet_ETH3D		96.49 344	95.64 358	99.05 198	99.53 174	98.82 194	98.84 373	97.51 413	97.63 220	84.77 422	99.21 337	92.09 319	98.91 381	98.98 106	92.21 398	99.41 217

miper_lstm_enhance		98.00 235	97.91 226	98.28 308	99.34 243	97.43 283	98.88 369	99.36 255	96.48 328	98.80 291	99.55 240	95.98 176	98.91 381	97.27 293	95.50 351	98.51 356

MonoMVSNet		98.38 190	98.47 178	98.12 320	98.59 383	96.19 348	99.72 52	98.79 372	97.89 187	99.44 157	99.52 253	96.13 171	98.90 383	98.64 159	97.54 286	99.28 234

PEN-MVS		97.76 274	97.44 286	98.72 253	98.77 362	98.54 218	99.78 32	99.51 127	97.06 283	98.29 342	99.64 205	92.63 305	98.89 384	98.09 218	93.16 389	98.72 293

testing3		97.28 323	96.76 332	98.82 241	99.37 235	98.07 250	99.45 205	99.36 255	97.56 229	97.89 361	98.95 365	83.70 408	98.82 385	96.03 343	98.56 228	99.58 167

testgi		97.65 297	97.50 273	98.13 319	99.36 238	96.45 337	99.42 223	99.48 169	97.76 205	97.87 362	99.45 278	91.09 342	98.81 386	94.53 373	98.52 231	99.13 247

testf1		90.42 387	90.68 388	89.65 407	97.78 399	73.97 435	99.13 317	98.81 369	89.62 413	91.80 418	98.93 367	62.23 427	98.80 387	86.61 421	91.17 401	96.19 418

APD_test2		90.42 387	90.68 388	89.65 407	97.78 399	73.97 435	99.13 317	98.81 369	89.62 413	91.80 418	98.93 367	62.23 427	98.80 387	86.61 421	91.17 401	96.19 418

MIMVSNet		97.73 282	97.45 281	98.57 267	99.45 213	97.50 281	99.02 343	98.98 342	96.11 355	99.41 166	99.14 343	90.28 349	98.74 389	95.74 350	98.93 203	99.47 202

LCM-MVSNet-Re		97.83 263	98.15 197	96.87 377	99.30 253	92.25 407	99.59 109	98.26 398	97.43 247	96.20 393	99.13 344	96.27 168	98.73 390	98.17 214	98.99 200	99.64 147

Syy-MVS		97.09 332	97.14 318	96.95 374	99.00 325	92.73 405	99.29 273	99.39 238	97.06 283	97.41 371	98.15 401	93.92 272	98.68 391	91.71 401	98.34 238	99.45 210

myMVS_eth3d		96.89 335	96.37 340	98.43 291	99.00 325	97.16 295	99.29 273	99.39 238	97.06 283	97.41 371	98.15 401	83.46 409	98.68 391	95.27 363	98.34 238	99.45 210

DTE-MVSNet		97.51 307	97.19 316	98.46 284	98.63 377	98.13 247	99.84 12	99.48 169	96.68 308	97.97 359	99.67 192	92.92 292	98.56 393	96.88 320	92.60 397	98.70 300

PC_three_1452									98.18 148	99.84 42	99.70 169	99.31 3	98.52 394	98.30 205	99.80 109	99.81 69

mvsany_test3		93.77 376	93.45 380	94.74 389	95.78 418	88.01 415	99.64 84	98.25 399	98.28 131	94.31 406	97.97 408	68.89 423	98.51 395	97.50 277	90.37 406	97.71 403

UnsupCasMVSNet_bld		93.53 377	92.51 383	96.58 382	97.38 405	93.82 393	98.24 412	99.48 169	91.10 410	93.10 411	96.66 417	74.89 421	98.37 396	94.03 381	87.71 414	97.56 408

Anonymous20240521		96.20 350	95.89 353	97.13 368	97.72 402	94.96 378	99.79 31	99.29 296	93.01 399	97.20 379	99.03 354	89.69 359	98.36 397	91.16 404	96.13 329	98.07 388

test_f		91.90 383	91.26 387	93.84 392	95.52 422	85.92 417	99.69 60	98.53 395	95.31 369	93.87 408	96.37 419	55.33 430	98.27 398	95.70 351	90.98 404	97.32 411

MDA-MVSNet_test_wron		95.45 361	94.60 368	98.01 326	98.16 394	97.21 294	99.11 326	99.24 307	93.49 395	80.73 428	98.98 362	93.02 289	98.18 399	94.22 379	94.45 370	98.64 328

UnsupCasMVSNet_eth		96.44 345	96.12 346	97.40 362	98.65 375	95.65 357	99.36 251	99.51 127	97.13 273	96.04 396	98.99 360	88.40 376	98.17 400	96.71 325	90.27 407	98.40 369

KD-MVS_2432*1600		94.62 369	93.72 377	97.31 363	97.19 411	95.82 354	98.34 407	99.20 314	95.00 376	97.57 368	98.35 394	87.95 381	98.10 401	92.87 395	77.00 426	98.01 392

miper_refine_blended		94.62 369	93.72 377	97.31 363	97.19 411	95.82 354	98.34 407	99.20 314	95.00 376	97.57 368	98.35 394	87.95 381	98.10 401	92.87 395	77.00 426	98.01 392

YYNet1		95.36 363	94.51 370	97.92 335	97.89 397	97.10 298	99.10 328	99.23 308	93.26 398	80.77 427	99.04 353	92.81 295	98.02 403	94.30 375	94.18 375	98.64 328

EU-MVSNet		97.98 237	98.03 213	97.81 346	98.72 368	96.65 330	99.66 75	99.66 28	98.09 161	98.35 337	99.82 87	95.25 207	98.01 404	97.41 286	95.30 354	98.78 279

Gipuma		90.99 385	90.15 390	93.51 393	98.73 366	90.12 413	93.98 426	99.45 210	79.32 424	92.28 414	94.91 421	69.61 422	97.98 405	87.42 417	95.67 344	92.45 424
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 364	94.73 367	97.15 366	95.53 421	95.94 352	99.35 256	99.10 325	95.13 370	93.55 409	97.54 410	88.15 380	97.91 406	94.58 372	89.69 410	97.61 406

PM-MVS		92.96 380	92.23 384	95.14 388	95.61 419	89.98 414	99.37 246	98.21 401	94.80 381	95.04 404	97.69 409	65.06 424	97.90 407	94.30 375	89.98 409	97.54 409

MDA-MVSNet-bldmvs		94.96 367	93.98 374	97.92 335	98.24 393	97.27 289	99.15 314	99.33 274	93.80 391	80.09 429	99.03 354	88.31 377	97.86 408	93.49 387	94.36 372	98.62 337

Patchmatch-RL test		95.84 357	95.81 355	95.95 386	95.61 419	90.57 412	98.24 412	98.39 396	95.10 374	95.20 401	98.67 382	94.78 228	97.77 409	96.28 340	90.02 408	99.51 190

Anonymous20231206		96.22 348	96.03 349	96.79 379	97.31 408	94.14 391	99.63 90	99.08 328	96.17 349	97.04 383	99.06 351	93.94 270	97.76 410	86.96 419	95.06 359	98.47 360

SD-MVS		99.41 53	99.52 12	99.05 198	99.74 89	99.68 55	99.46 203	99.52 113	99.11 37	99.88 31	99.91 23	99.43 1	97.70 411	98.72 148	99.93 27	99.77 90
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		97.25 325	97.35 298	96.95 374	97.84 398	93.61 399	99.57 124	96.63 421	96.13 354	98.87 280	98.61 385	94.59 243	97.70 411	95.08 366	98.86 209	99.55 173

dongtai		93.26 378	92.93 382	94.25 390	99.39 230	85.68 418	97.68 421	93.27 432	92.87 401	96.85 387	99.39 295	82.33 414	97.48 413	76.78 426	97.80 271	99.58 167

pmmvs3		94.09 375	93.25 381	96.60 381	94.76 426	94.49 385	98.92 365	98.18 403	89.66 412	96.48 390	98.06 407	86.28 393	97.33 414	89.68 409	87.20 415	97.97 398

KD-MVS_self_test		95.00 366	94.34 371	96.96 373	97.07 413	95.39 368	99.56 130	99.44 218	95.11 372	97.13 381	97.32 414	91.86 324	97.27 415	90.35 407	81.23 423	98.23 380

FMVSNet5		96.43 346	96.19 345	97.15 366	99.11 304	95.89 353	99.32 263	99.52 113	94.47 387	98.34 338	99.07 349	87.54 386	97.07 416	92.61 398	95.72 343	98.47 360

new-patchmatchnet		94.48 372	94.08 373	95.67 387	95.08 424	92.41 406	99.18 309	99.28 298	94.55 386	93.49 410	97.37 413	87.86 384	97.01 417	91.57 402	88.36 412	97.61 406

LCM-MVSNet		86.80 391	85.22 395	91.53 401	87.81 433	80.96 427	98.23 414	98.99 341	71.05 426	90.13 421	96.51 418	48.45 434	96.88 418	90.51 405	85.30 417	96.76 413

CL-MVSNet_self_test		94.49 371	93.97 375	96.08 385	96.16 416	93.67 398	98.33 409	99.38 246	95.13 370	97.33 375	98.15 401	92.69 303	96.57 419	88.67 412	79.87 424	97.99 396

MIMVSNet1		95.51 360	95.04 365	96.92 376	97.38 405	95.60 358	99.52 159	99.50 147	93.65 393	96.97 385	99.17 339	85.28 401	96.56 420	88.36 414	95.55 349	98.60 349

test20.03		96.12 352	95.96 351	96.63 380	97.44 404	95.45 365	99.51 168	99.38 246	96.55 322	96.16 394	99.25 331	93.76 279	96.17 421	87.35 418	94.22 374	98.27 376

tmp_tt		82.80 393	81.52 396	86.66 409	66.61 439	68.44 438	92.79 428	97.92 405	68.96 427	80.04 430	99.85 63	85.77 395	96.15 422	97.86 239	43.89 432	95.39 422

test_fmvs3		92.10 382	91.77 385	93.08 396	96.19 415	86.25 416	99.82 16	98.62 391	96.65 311	95.19 402	96.90 416	55.05 431	95.93 423	96.63 332	90.92 405	97.06 412

kuosan		90.92 386	90.11 391	93.34 394	98.78 357	85.59 419	98.15 416	93.16 434	89.37 415	92.07 415	98.38 393	81.48 417	95.19 424	62.54 433	97.04 312	99.25 239

dmvs_testset		95.02 365	96.12 346	91.72 400	99.10 307	80.43 428	99.58 117	97.87 407	97.47 239	95.22 400	98.82 374	93.99 268	95.18 425	88.09 415	94.91 364	99.56 172

PMMVS2		86.87 390	85.37 394	91.35 402	90.21 431	83.80 421	98.89 368	97.45 414	83.13 423	91.67 420	95.03 420	48.49 433	94.70 426	85.86 423	77.62 425	95.54 421

PMVS	70.75 22	75.98 399	74.97 400	79.01 415	70.98 438	55.18 440	93.37 427	98.21 401	65.08 432	61.78 433	93.83 423	21.74 440	92.53 427	78.59 425	91.12 403	89.34 428
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 392	85.65 393	82.75 413	86.77 434	63.39 439	98.35 406	98.92 350	74.11 425	83.39 424	98.98 362	50.85 432	92.40 428	84.54 424	94.97 361	92.46 423

WB-MVS		93.10 379	94.10 372	90.12 405	95.51 423	81.88 425	99.73 50	99.27 301	95.05 375	93.09 412	98.91 371	94.70 237	91.89 429	76.62 427	94.02 380	96.58 415

SSC-MVS		92.73 381	93.73 376	89.72 406	95.02 425	81.38 426	99.76 37	99.23 308	94.87 379	92.80 413	98.93 367	94.71 236	91.37 430	74.49 429	93.80 382	96.42 416

MVE	76.82 21	76.91 398	74.31 402	84.70 410	85.38 436	76.05 434	96.88 424	93.17 433	67.39 429	71.28 431	89.01 430	21.66 441	87.69 431	71.74 430	72.29 428	90.35 427
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 395	79.88 397	82.81 412	90.75 430	76.38 433	97.69 420	95.76 425	66.44 430	83.52 423	92.25 425	62.54 426	87.16 432	68.53 431	61.40 429	84.89 430

EMVS		80.02 396	79.22 398	82.43 414	91.19 429	76.40 432	97.55 423	92.49 437	66.36 431	83.01 425	91.27 427	64.63 425	85.79 433	65.82 432	60.65 430	85.08 429

ANet_high		77.30 397	74.86 401	84.62 411	75.88 437	77.61 431	97.63 422	93.15 435	88.81 417	64.27 432	89.29 429	36.51 436	83.93 434	75.89 428	52.31 431	92.33 425

wuyk23d		40.18 400	41.29 405	36.84 416	86.18 435	49.12 441	79.73 429	22.81 441	27.64 433	25.46 436	28.45 436	21.98 439	48.89 435	55.80 434	23.56 435	12.51 433

test123		39.01 402	42.50 404	28.53 417	39.17 440	20.91 442	98.75 382	19.17 442	19.83 435	38.57 434	66.67 432	33.16 437	15.42 436	37.50 436	29.66 434	49.26 431

testmvs		39.17 401	43.78 403	25.37 418	36.04 441	16.84 443	98.36 405	26.56 440	20.06 434	38.51 435	67.32 431	29.64 438	15.30 437	37.59 435	39.90 433	43.98 432

mmdepth		0.02 407	0.03 410	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.27 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

monomultidepth		0.02 407	0.03 410	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.27 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

test_blank		0.13 406	0.17 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	1.57 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet_test		0.02 407	0.03 410	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.27 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

DCPMVS		0.02 407	0.03 410	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.27 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

cdsmvs_eth3d_5k		24.64 403	32.85 406	0.00 419	0.00 442	0.00 444	0.00 430	99.51 127	0.00 437	0.00 438	99.56 237	96.58 155	0.00 438	0.00 437	0.00 436	0.00 434

pcd_1.5k_mvsjas		8.27 405	11.03 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.27 438	99.01 18	0.00 438	0.00 437	0.00 436	0.00 434

sosnet-low-res		0.02 407	0.03 410	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.27 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

sosnet		0.02 407	0.03 410	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.27 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uncertanet		0.02 407	0.03 410	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.27 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

Regformer		0.02 407	0.03 410	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.27 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

ab-mvs-re		8.30 404	11.06 407	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	99.58 229	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet		0.02 407	0.03 410	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.27 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

WAC-MVS						97.16 295								95.47 357

FOURS1					99.91 1	99.93 1	99.87 8	99.56 78	99.10 38	99.81 50

test_one_0601					99.81 47	99.88 8		99.49 157	98.97 62	99.65 106	99.81 101	99.09 14

eth-test2					0.00 442

eth-test					0.00 442

RE-MVS-def			99.34 44		99.76 71	99.82 25	99.63 90	99.52 113	98.38 119	99.76 71	99.82 87	98.75 58		98.61 165	99.81 105	99.77 90

IU-MVS					99.84 32	99.88 8		99.32 284	98.30 130	99.84 42				98.86 128	99.85 81	99.89 24

save fliter					99.76 71	99.59 79	99.14 316	99.40 235	99.00 54

test0726					99.85 26	99.89 4	99.62 95	99.50 147	99.10 38	99.86 40	99.82 87	98.94 32

GSMVS																99.52 182

test_part2					99.81 47	99.83 19				99.77 65

sam_mvs1												94.86 223				99.52 182

sam_mvs												94.72 235

MTGPA								99.47 190

MTMP							99.54 149	98.88 360

test9_res														97.49 278	99.72 132	99.75 96

agg_prior2														97.21 296	99.73 131	99.75 96

test_prior4						99.56 85	98.99 351

test_prior2							98.96 358		98.34 125	99.01 255	99.52 253	98.68 67		97.96 231	99.74 129

新几何2							99.01 348

旧先验1					99.74 89	99.59 79		99.54 95			99.69 179	98.47 83			99.68 140	99.73 105

原ACMM2							98.95 361

test222					99.75 81	99.49 99	98.91 367	99.49 157	96.42 333	99.34 186	99.65 199	98.28 96			99.69 137	99.72 113

segment_acmp												98.96 25

testdata1							98.85 372		98.32 128

plane_prior7					99.29 257	97.03 308

plane_prior6					99.27 262	96.98 312						92.71 301

plane_prior4											99.61 220

plane_prior3						97.00 310			98.69 91	99.11 235

plane_prior2							99.39 239		98.97 62

plane_prior1					99.26 265

plane_prior						96.97 313	99.21 305		98.45 112						97.60 280

n2								0.00 443

nn								0.00 443

door-mid								98.05 404

test11								99.35 262

door								97.92 405

HQP5-MVS						96.83 320

HQP-NCC					99.19 283		98.98 354		98.24 137	98.66 309

ACMP_Plane					99.19 283		98.98 354		98.24 137	98.66 309

BP-MVS														97.19 300

HQP3-MVS								99.39 238							97.58 282

HQP2-MVS												92.47 310

NP-MVS					99.23 273	96.92 316					99.40 291

MDTV_nov1_ep13_2view						95.18 374	99.35 256		96.84 300	99.58 128		95.19 209		97.82 244		99.46 207

ACMMP++_ref															97.19 309

ACMMP++															97.43 300

Test By Simon												98.75 58

High-resolution multi-view benchmark