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 63	99.38 231	99.37 111	99.58 117	99.62 43	99.41 14	99.87 35	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 60	99.84 32	99.44 105	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 20

test_vis1_n_1920		98.63 174	98.40 181	99.31 160	99.86 20	97.94 260	99.67 69	99.62 43	99.43 11	99.99 2	99.91 23	87.29 386	100.00 1	99.92 17	99.92 31	99.98 2

fmvsm_s_conf0.5_n_5		99.37 59	99.21 74	99.86 27	99.80 53	99.68 55	99.42 222	99.61 50	99.37 17	99.97 18	99.86 56	94.96 214	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 75	99.56 130	99.63 41	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 72	99.56 130	99.63 41	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 61	99.48 191	99.64 38	99.45 8	99.92 22	99.92 17	98.62 73	99.99 4	99.96 9	99.99 1	99.96 7

patch_mono-2		99.26 80	99.62 5	98.16 314	99.81 47	94.59 383	99.52 159	99.64 38	99.33 19	99.73 76	99.90 30	99.00 22	99.99 4	99.69 27	99.98 4	99.89 23

h-mvs33		97.70 287	97.28 309	98.97 207	99.70 110	97.27 288	99.36 250	99.45 209	98.94 64	99.66 98	99.64 204	94.93 217	99.99 4	99.48 52	84.36 417	99.65 139

xiu_mvs_v1_base_debu		99.29 74	99.27 64	99.34 153	99.63 141	98.97 167	99.12 319	99.51 126	98.86 70	99.84 41	99.47 271	98.18 100	99.99 4	99.50 47	99.31 172	99.08 252

xiu_mvs_v1_base		99.29 74	99.27 64	99.34 153	99.63 141	98.97 167	99.12 319	99.51 126	98.86 70	99.84 41	99.47 271	98.18 100	99.99 4	99.50 47	99.31 172	99.08 252

xiu_mvs_v1_base_debi		99.29 74	99.27 64	99.34 153	99.63 141	98.97 167	99.12 319	99.51 126	98.86 70	99.84 41	99.47 271	98.18 100	99.99 4	99.50 47	99.31 172	99.08 252

EPNet		98.86 145	98.71 149	99.30 165	97.20 409	98.18 242	99.62 95	98.91 354	99.28 22	98.63 317	99.81 101	95.96 176	99.99 4	99.24 79	99.72 131	99.73 104
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		99.40 55	99.28 61	99.74 69	99.67 120	99.31 121	99.52 159	98.87 361	99.55 1	99.74 74	99.80 114	96.47 159	99.98 15	99.97 1	99.97 7	99.94 13

test_cas_vis1_n_1920		99.16 94	99.01 106	99.61 97	99.81 47	98.86 187	99.65 81	99.64 38	99.39 15	99.97 18	99.94 6	93.20 287	99.98 15	99.55 40	99.91 38	99.99 1

test_vis1_n		97.92 245	97.44 285	99.34 153	99.53 174	98.08 248	99.74 46	99.49 156	99.15 27	100.00 1	99.94 6	79.51 418	99.98 15	99.88 19	99.76 123	99.97 4

xiu_mvs_v2_base		99.26 80	99.25 68	99.29 168	99.53 174	98.91 181	99.02 342	99.45 209	98.80 79	99.71 83	99.26 329	98.94 32	99.98 15	99.34 66	99.23 177	98.98 266

PS-MVSNAJ		99.32 69	99.32 47	99.30 165	99.57 162	98.94 177	98.97 356	99.46 198	98.92 67	99.71 83	99.24 331	99.01 18	99.98 15	99.35 61	99.66 141	98.97 267

QAPM		98.67 170	98.30 188	99.80 54	99.20 279	99.67 59	99.77 34	99.72 11	94.74 381	98.73 297	99.90 30	95.78 186	99.98 15	96.96 312	99.88 62	99.76 94

3Dnovator	97.25 9	99.24 85	99.05 94	99.81 51	99.12 301	99.66 61	99.84 12	99.74 10	99.09 42	98.92 270	99.90 30	95.94 179	99.98 15	98.95 109	99.92 31	99.79 81

OpenMVS	96.50 16	98.47 179	98.12 200	99.52 124	99.04 319	99.53 91	99.82 16	99.72 11	94.56 384	98.08 351	99.88 43	94.73 233	99.98 15	97.47 280	99.76 123	99.06 258

fmvsm_s_conf0.5_n_3		99.37 59	99.20 76	99.87 16	99.75 81	99.70 52	99.48 191	99.66 28	99.45 8	99.99 2	99.93 10	94.64 241	99.97 23	99.94 14	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 85	99.15 27	99.90 25	99.90 30	99.00 22	99.97 23	99.11 90	99.91 38	99.86 36

test_fmvsmconf0.1_n		99.55 18	99.45 25	99.86 27	99.44 213	99.65 65	99.50 175	99.61 50	99.45 8	99.87 35	99.92 17	97.31 126	99.97 23	99.95 11	99.99 1	99.97 4

test_fmvs1_n		98.41 185	98.14 197	99.21 180	99.82 43	97.71 273	99.74 46	99.49 156	99.32 20	99.99 2	99.95 3	85.32 399	99.97 23	99.82 22	99.84 88	99.96 7

CANet_DTU		98.97 135	98.87 130	99.25 175	99.33 243	98.42 234	99.08 328	99.30 291	99.16 26	99.43 158	99.75 148	95.27 203	99.97 23	98.56 176	99.95 18	99.36 224

MVS_0304		99.15 96	98.96 116	99.73 72	98.92 337	99.37 111	99.37 245	96.92 415	99.51 2	99.66 98	99.78 133	96.69 150	99.97 23	99.84 21	99.97 7	99.84 46

MTAPA		99.52 21	99.39 33	99.89 8	99.90 4	99.86 16	99.66 75	99.47 189	98.79 80	99.68 89	99.81 101	98.43 86	99.97 23	98.88 119	99.90 47	99.83 56

PGM-MVS		99.45 39	99.31 53	99.86 27	99.87 15	99.78 40	99.58 117	99.65 35	97.84 194	99.71 83	99.80 114	99.12 13	99.97 23	98.33 200	99.87 65	99.83 56

mPP-MVS		99.44 43	99.30 55	99.86 27	99.88 11	99.79 34	99.69 60	99.48 168	98.12 155	99.50 143	99.75 148	98.78 51	99.97 23	98.57 173	99.89 58	99.83 56

CP-MVS		99.45 39	99.32 47	99.85 35	99.83 40	99.75 44	99.69 60	99.52 112	98.07 165	99.53 138	99.63 210	98.93 36	99.97 23	98.74 144	99.91 38	99.83 56

SteuartSystems-ACMMP		99.54 19	99.42 26	99.87 16	99.82 43	99.81 29	99.59 109	99.51 126	98.62 95	99.79 55	99.83 78	99.28 4	99.97 23	98.48 183	99.90 47	99.84 46
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 90	98.97 112	99.82 48	99.17 293	99.68 55	99.81 20	99.51 126	99.20 24	98.72 298	99.89 35	95.68 190	99.97 23	98.86 127	99.86 73	99.81 68

fmvsm_s_conf0.5_n_2		99.32 69	99.13 83	99.89 8	99.80 53	99.77 41	99.44 210	99.58 67	99.47 4	99.99 2	99.93 10	94.04 265	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 94	99.13 30	99.89 27	99.89 35	98.96 25	99.96 35	99.04 98	99.90 47	99.85 40

our_new_method		99.61 8	99.52 12	99.90 5	99.76 71	99.88 8	99.52 159	99.54 94	99.13 30	99.89 27	99.89 35	98.96 25	99.96 35	99.04 98	99.90 47	99.85 40

fmvsm_s_conf0.5_n_a		99.56 17	99.47 21	99.85 35	99.83 40	99.64 71	99.52 159	99.65 35	99.10 37	99.98 9	99.92 17	97.35 125	99.96 35	99.94 14	99.92 31	99.95 9

fmvsm_s_conf0.5_n		99.51 22	99.40 31	99.85 35	99.84 32	99.65 65	99.51 168	99.67 23	99.13 30	99.98 9	99.92 17	96.60 153	99.96 35	99.95 11	99.96 13	99.95 9

mvsany_test1		99.50 24	99.46 24	99.62 96	99.61 151	99.09 150	98.94 362	99.48 168	99.10 37	99.96 20	99.91 23	98.85 42	99.96 35	99.72 25	99.58 151	99.82 61

test_fmvs1		98.88 141	98.79 142	99.16 185	99.69 114	97.61 277	99.55 144	99.49 156	99.32 20	99.98 9	99.91 23	91.41 335	99.96 35	99.82 22	99.92 31	99.90 20

DVP-MVS++		99.59 12	99.50 17	99.88 10	99.51 183	99.88 8	99.87 8	99.51 126	98.99 55	99.88 30	99.81 101	99.27 5	99.96 35	98.85 129	99.80 108	99.81 68

MSC_two_6792asdad				99.87 16	99.51 183	99.76 42		99.33 273					99.96 35	98.87 122	99.84 88	99.89 23

No_MVS				99.87 16	99.51 183	99.76 42		99.33 273					99.96 35	98.87 122	99.84 88	99.89 23

ZD-MVS					99.71 105	99.79 34		99.61 50	96.84 299	99.56 131	99.54 244	98.58 75	99.96 35	96.93 315	99.75 125

SED-MVS		99.61 8	99.52 12	99.88 10	99.84 32	99.90 2	99.60 102	99.48 168	99.08 43	99.91 23	99.81 101	99.20 7	99.96 35	98.91 116	99.85 80	99.79 81

test_241102_TWO								99.48 168	99.08 43	99.88 30	99.81 101	98.94 32	99.96 35	98.91 116	99.84 88	99.88 29

ZNCC-MVS		99.47 33	99.33 45	99.87 16	99.87 15	99.81 29	99.64 84	99.67 23	98.08 164	99.55 135	99.64 204	98.91 37	99.96 35	98.72 147	99.90 47	99.82 61

DVP-MVS		99.57 16	99.47 21	99.88 10	99.85 26	99.89 4	99.57 124	99.37 253	99.10 37	99.81 49	99.80 114	98.94 32	99.96 35	98.93 113	99.86 73	99.81 68
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 55	99.81 49	99.80 114	99.09 14	99.96 35	98.85 129	99.90 47	99.88 29

test_0728_SECOND				99.91 3	99.84 32	99.89 4	99.57 124	99.51 126					99.96 35	98.93 113	99.86 73	99.88 29

SR-MVS		99.43 46	99.29 59	99.86 27	99.75 81	99.83 19	99.59 109	99.62 43	98.21 142	99.73 76	99.79 126	98.68 67	99.96 35	98.44 189	99.77 120	99.79 81

DPE-MVS		99.46 35	99.32 47	99.91 3	99.78 59	99.88 8	99.36 250	99.51 126	98.73 87	99.88 30	99.84 73	98.72 64	99.96 35	98.16 214	99.87 65	99.88 29
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 48	99.29 59	99.80 54	99.62 147	99.55 86	99.50 175	99.70 15	98.79 80	99.77 64	99.96 1	97.45 120	99.96 35	98.92 115	99.90 47	99.89 23

HFP-MVS		99.49 26	99.37 37	99.86 27	99.87 15	99.80 31	99.66 75	99.67 23	98.15 149	99.68 89	99.69 178	99.06 16	99.96 35	98.69 152	99.87 65	99.84 46

region2R		99.48 30	99.35 41	99.87 16	99.88 11	99.80 31	99.65 81	99.66 28	98.13 154	99.66 98	99.68 185	98.96 25	99.96 35	98.62 161	99.87 65	99.84 46

HPM-MVS++		99.39 57	99.23 72	99.87 16	99.75 81	99.84 18	99.43 215	99.51 126	98.68 92	99.27 200	99.53 248	98.64 72	99.96 35	98.44 189	99.80 108	99.79 81

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 67	99.89 4	99.75 42	99.56 77	99.02 48	99.88 30	99.85 63	99.18 10	99.96 35	99.22 80	99.92 31	99.90 20
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 26	99.36 39	99.86 27	99.87 15	99.79 34	99.66 75	99.67 23	98.15 149	99.67 93	99.69 178	98.95 30	99.96 35	98.69 152	99.87 65	99.84 46

MP-MVS		99.33 67	99.15 81	99.87 16	99.88 11	99.82 25	99.66 75	99.46 198	98.09 160	99.48 147	99.74 153	98.29 95	99.96 35	97.93 232	99.87 65	99.82 61
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 112	98.90 124	99.74 69	99.80 53	99.46 103	99.59 109	99.49 156	97.03 286	99.63 113	99.69 178	97.27 129	99.96 35	97.82 243	99.84 88	99.81 68

PVSNet_Blended_VisFu		99.36 63	99.28 61	99.61 97	99.86 20	99.07 155	99.47 199	99.93 2	97.66 217	99.71 83	99.86 56	97.73 115	99.96 35	99.47 54	99.82 101	99.79 81

UGNet		98.87 142	98.69 151	99.40 145	99.22 276	98.72 201	99.44 210	99.68 20	99.24 23	99.18 225	99.42 282	92.74 297	99.96 35	99.34 66	99.94 25	99.53 180
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 69	99.32 47	99.32 159	99.85 26	98.29 237	99.71 55	99.66 28	98.11 157	99.41 165	99.80 114	98.37 92	99.96 35	98.99 104	99.96 13	99.72 112

ACMMP		99.45 39	99.32 47	99.82 48	99.89 8	99.67 59	99.62 95	99.69 18	98.12 155	99.63 113	99.84 73	98.73 63	99.96 35	98.55 179	99.83 97	99.81 68
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_4		99.36 63	99.24 69	99.73 72	99.78 59	99.53 91	99.49 186	99.60 57	99.42 13	99.99 2	99.86 56	95.15 209	99.95 66	99.95 11	99.89 58	99.73 104

fmvsm_s_conf0.1_n_2		99.37 59	99.22 73	99.81 51	99.77 67	99.75 44	99.46 202	99.60 57	99.47 4	99.98 9	99.94 6	94.98 213	99.95 66	99.97 1	99.79 115	99.73 104

test_fmvsmconf0.01_n		99.22 87	99.03 98	99.79 57	98.42 389	99.48 100	99.55 144	99.51 126	99.39 15	99.78 60	99.93 10	94.80 225	99.95 66	99.93 16	99.95 18	99.94 13

SR-MVS-dyc-post		99.45 39	99.31 53	99.85 35	99.76 71	99.82 25	99.63 90	99.52 112	98.38 118	99.76 70	99.82 87	98.53 79	99.95 66	98.61 164	99.81 104	99.77 89

GST-MVS		99.40 55	99.24 69	99.85 35	99.86 20	99.79 34	99.60 102	99.67 23	97.97 179	99.63 113	99.68 185	98.52 80	99.95 66	98.38 193	99.86 73	99.81 68

CANet		99.25 84	99.14 82	99.59 100	99.41 221	99.16 140	99.35 255	99.57 72	98.82 75	99.51 142	99.61 219	96.46 160	99.95 66	99.59 35	99.98 4	99.65 139

MP-MVS-pluss		99.37 59	99.20 76	99.88 10	99.90 4	99.87 15	99.30 267	99.52 112	97.18 268	99.60 123	99.79 126	98.79 50	99.95 66	98.83 135	99.91 38	99.83 56
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 48	99.27 64	99.88 10	99.89 8	99.80 31	99.67 69	99.50 146	98.70 89	99.77 64	99.49 262	98.21 98	99.95 66	98.46 187	99.77 120	99.88 29
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	96.67 327

APD-MVS_3200maxsize		99.48 30	99.35 41	99.85 35	99.76 71	99.83 19	99.63 90	99.54 94	98.36 122	99.79 55	99.82 87	98.86 41	99.95 66	98.62 161	99.81 104	99.78 87

RPMNet		96.72 338	95.90 351	99.19 182	99.18 285	98.49 226	99.22 302	99.52 112	88.72 417	99.56 131	97.38 411	94.08 264	99.95 66	86.87 419	98.58 224	99.14 244

sss		99.17 92	99.05 94	99.53 118	99.62 147	98.97 167	99.36 250	99.62 43	97.83 195	99.67 93	99.65 198	97.37 124	99.95 66	99.19 82	99.19 180	99.68 129

MVSMamba_PlusPlus		99.46 35	99.41 30	99.64 89	99.68 118	99.50 97	99.75 42	99.50 146	98.27 132	99.87 35	99.92 17	98.09 104	99.94 78	99.65 31	99.95 18	99.47 201

fmvsm_s_conf0.1_n_a		99.26 80	99.06 93	99.85 35	99.52 180	99.62 73	99.54 149	99.62 43	98.69 90	99.99 2	99.96 1	94.47 250	99.94 78	99.88 19	99.92 31	99.98 2

fmvsm_s_conf0.1_n		99.29 74	99.10 87	99.86 27	99.70 110	99.65 65	99.53 158	99.62 43	98.74 86	99.99 2	99.95 3	94.53 248	99.94 78	99.89 18	99.96 13	99.97 4

TSAR-MVS + MP.		99.58 13	99.50 17	99.81 51	99.91 1	99.66 61	99.63 90	99.39 237	98.91 68	99.78 60	99.85 63	99.36 2	99.94 78	98.84 132	99.88 62	99.82 61
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 139	98.75 145	99.39 149	99.46 206	98.61 212	99.76 37	99.50 146	98.06 169	99.81 49	99.88 43	93.91 272	99.94 78	99.11 90	99.27 175	99.61 155

mamv4		99.33 67	99.42 26	99.07 193	99.67 120	97.73 268	99.42 222	99.60 57	98.15 149	99.94 21	99.91 23	98.42 88	99.94 78	99.72 25	99.96 13	99.54 174

XVS		99.53 20	99.42 26	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 58	99.37 176	99.74 153	98.81 47	99.94 78	98.79 140	99.86 73	99.84 46

X-MVStestdata		96.55 341	95.45 360	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 58	99.37 176	64.01 434	98.81 47	99.94 78	98.79 140	99.86 73	99.84 46

旧先验2							98.96 357		96.70 306	99.47 148			99.94 78	98.19 210

新几何1				99.75 66	99.75 81	99.59 78		99.54 94	96.76 302	99.29 194	99.64 204	98.43 86	99.94 78	96.92 317	99.66 141	99.72 112

testdata				99.54 110	99.75 81	98.95 174		99.51 126	97.07 280	99.43 158	99.70 168	98.87 40	99.94 78	97.76 250	99.64 144	99.72 112

HPM-MVS		99.42 48	99.28 61	99.83 47	99.90 4	99.72 48	99.81 20	99.54 94	97.59 223	99.68 89	99.63 210	98.91 37	99.94 78	98.58 170	99.91 38	99.84 46
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 88	99.10 87	99.45 138	99.89 8	98.52 222	99.39 238	99.94 1	98.73 87	99.11 234	99.89 35	95.50 195	99.94 78	99.50 47	99.97 7	99.89 23

APD-MVS		99.27 78	99.08 91	99.84 46	99.75 81	99.79 34	99.50 175	99.50 146	97.16 270	99.77 64	99.82 87	98.78 51	99.94 78	97.56 271	99.86 73	99.80 77
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 30	99.42 26	99.65 83	99.72 100	99.40 110	99.05 334	99.66 28	99.14 29	99.57 130	99.80 114	98.46 84	99.94 78	99.57 38	99.84 88	99.60 158
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		99.06 121	98.88 129	99.61 97	99.62 147	99.16 140	99.37 245	99.56 77	98.04 172	99.53 138	99.62 215	96.84 144	99.94 78	98.85 129	98.49 232	99.72 112

DeepC-MVS	98.35 2	99.30 72	99.19 78	99.64 89	99.82 43	99.23 133	99.62 95	99.55 85	98.94 64	99.63 113	99.95 3	95.82 185	99.94 78	99.37 60	99.97 7	99.73 104
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 78	99.12 85	99.74 69	99.18 285	99.75 44	99.56 130	99.57 72	98.45 111	99.49 146	99.85 63	97.77 114	99.94 78	98.33 200	99.84 88	99.52 181

GDP-MVS		99.08 118	98.89 127	99.64 89	99.53 174	99.34 115	99.64 84	99.48 168	98.32 127	99.77 64	99.66 196	95.14 210	99.93 96	98.97 108	99.50 157	99.64 146

SDMVSNet		99.11 112	98.90 124	99.75 66	99.81 47	99.59 78	99.81 20	99.65 35	98.78 83	99.64 110	99.88 43	94.56 244	99.93 96	99.67 29	98.26 245	99.72 112

FE-MVS		98.48 178	98.17 193	99.40 145	99.54 173	98.96 171	99.68 66	98.81 368	95.54 365	99.62 117	99.70 168	93.82 275	99.93 96	97.35 289	99.46 159	99.32 230

SF-MVS		99.38 58	99.24 69	99.79 57	99.79 57	99.68 55	99.57 124	99.54 94	97.82 199	99.71 83	99.80 114	98.95 30	99.93 96	98.19 210	99.84 88	99.74 99

dcpmvs_2		99.23 86	99.58 7	98.16 314	99.83 40	94.68 381	99.76 37	99.52 112	99.07 45	99.98 9	99.88 43	98.56 77	99.93 96	99.67 29	99.98 4	99.87 34

Anonymous20240529		98.09 215	97.68 253	99.34 153	99.66 130	98.44 231	99.40 234	99.43 223	93.67 391	99.22 212	99.89 35	90.23 352	99.93 96	99.26 78	98.33 239	99.66 135

ACMMP_NAP		99.47 33	99.34 43	99.88 10	99.87 15	99.86 16	99.47 199	99.48 168	98.05 171	99.76 70	99.86 56	98.82 46	99.93 96	98.82 139	99.91 38	99.84 46

EI-MVSNet-UG-set		99.58 13	99.57 8	99.64 89	99.78 59	99.14 145	99.60 102	99.45 209	99.01 50	99.90 25	99.83 78	98.98 24	99.93 96	99.59 35	99.95 18	99.86 36

无先验							98.99 350	99.51 126	96.89 296				99.93 96	97.53 274		99.72 112

VDDNet		97.55 302	97.02 323	99.16 185	99.49 196	98.12 247	99.38 243	99.30 291	95.35 367	99.68 89	99.90 30	82.62 411	99.93 96	99.31 70	98.13 257	99.42 213

ab-mvs		98.86 145	98.63 158	99.54 110	99.64 138	99.19 135	99.44 210	99.54 94	97.77 203	99.30 191	99.81 101	94.20 258	99.93 96	99.17 86	98.82 212	99.49 194

F-COLMAP		99.19 88	99.04 96	99.64 89	99.78 59	99.27 128	99.42 222	99.54 94	97.29 259	99.41 165	99.59 224	98.42 88	99.93 96	98.19 210	99.69 136	99.73 104

BP-MVS1		99.12 107	98.94 120	99.65 83	99.51 183	99.30 123	99.67 69	98.92 349	98.48 107	99.84 41	99.69 178	94.96 214	99.92 108	99.62 34	99.79 115	99.71 121

Anonymous202405211		98.30 196	97.98 217	99.26 174	99.57 162	98.16 243	99.41 226	98.55 392	96.03 359	99.19 221	99.74 153	91.87 322	99.92 108	99.16 87	98.29 244	99.70 123

EI-MVSNet-Vis-set		99.58 13	99.56 10	99.64 89	99.78 59	99.15 144	99.61 101	99.45 209	99.01 50	99.89 27	99.82 87	99.01 18	99.92 108	99.56 39	99.95 18	99.85 40

VDD-MVS		97.73 281	97.35 297	98.88 227	99.47 204	97.12 296	99.34 258	98.85 363	98.19 144	99.67 93	99.85 63	82.98 409	99.92 108	99.49 51	98.32 243	99.60 158

VNet		99.11 112	98.90 124	99.73 72	99.52 180	99.56 84	99.41 226	99.39 237	99.01 50	99.74 74	99.78 133	95.56 193	99.92 108	99.52 45	98.18 253	99.72 112

XVG-OURS-SEG-HR		98.69 168	98.62 163	98.89 225	99.71 105	97.74 267	99.12 319	99.54 94	98.44 114	99.42 161	99.71 164	94.20 258	99.92 108	98.54 180	98.90 206	99.00 263

mvsmamba		99.06 121	98.96 116	99.36 151	99.47 204	98.64 208	99.70 56	99.05 333	97.61 222	99.65 105	99.83 78	96.54 156	99.92 108	99.19 82	99.62 147	99.51 189

HPM-MVS_fast		99.51 22	99.40 31	99.85 35	99.91 1	99.79 34	99.76 37	99.56 77	97.72 208	99.76 70	99.75 148	99.13 12	99.92 108	99.07 96	99.92 31	99.85 40

HY-MVS	97.30 7	98.85 152	98.64 157	99.47 135	99.42 216	99.08 153	99.62 95	99.36 254	97.39 251	99.28 195	99.68 185	96.44 162	99.92 108	98.37 195	98.22 248	99.40 218

DP-MVS		99.16 94	98.95 118	99.78 60	99.77 67	99.53 91	99.41 226	99.50 146	97.03 286	99.04 251	99.88 43	97.39 121	99.92 108	98.66 156	99.90 47	99.87 34

IB-MVS	95.67 18	96.22 347	95.44 361	98.57 266	99.21 277	96.70 324	98.65 391	97.74 409	96.71 305	97.27 375	98.54 386	86.03 393	99.92 108	98.47 186	86.30 415	99.10 247
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 26	99.39 33	99.77 63	99.63 141	99.59 78	99.36 250	99.46 198	99.07 45	99.79 55	99.82 87	98.85 42	99.92 108	98.68 154	99.87 65	99.82 61
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 35	99.39 33	99.67 78	99.55 170	99.58 83	99.74 46	99.51 126	98.42 115	99.87 35	99.84 73	98.05 107	99.91 120	99.58 37	99.94 25	99.52 181

9.14			99.10 87		99.72 100		99.40 234	99.51 126	97.53 233	99.64 110	99.78 133	98.84 44	99.91 120	97.63 262	99.82 101

SMA-MVS		99.44 43	99.30 55	99.85 35	99.73 96	99.83 19	99.56 130	99.47 189	97.45 242	99.78 60	99.82 87	99.18 10	99.91 120	98.79 140	99.89 58	99.81 68
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 65	99.05 334	99.41 228	96.22 344	98.95 266	99.49 262	98.77 54	99.91 120

train_agg		99.02 127	98.77 143	99.77 63	99.67 120	99.65 65	99.05 334	99.41 228	96.28 338	98.95 266	99.49 262	98.76 55	99.91 120	97.63 262	99.72 131	99.75 95

test_8					99.67 120	99.61 75	99.03 339	99.41 228	96.28 338	98.93 269	99.48 268	98.76 55	99.91 120

agg_prior					99.67 120	99.62 73		99.40 234		98.87 279			99.91 120

原ACMM1				99.65 83	99.73 96	99.33 116		99.47 189	97.46 239	99.12 232	99.66 196	98.67 69	99.91 120	97.70 259	99.69 136	99.71 121

LFMVS		97.90 248	97.35 297	99.54 110	99.52 180	99.01 162	99.39 238	98.24 399	97.10 278	99.65 105	99.79 126	84.79 402	99.91 120	99.28 74	98.38 236	99.69 125

XVG-OURS		98.73 166	98.68 152	98.88 227	99.70 110	97.73 268	98.92 364	99.55 85	98.52 104	99.45 151	99.84 73	95.27 203	99.91 120	98.08 221	98.84 210	99.00 263

PLC	97.94 4	99.02 127	98.85 134	99.53 118	99.66 130	99.01 162	99.24 295	99.52 112	96.85 298	99.27 200	99.48 268	98.25 97	99.91 120	97.76 250	99.62 147	99.65 139
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 295	97.06 322	99.47 135	99.61 151	99.09 150	98.04 417	99.25 303	91.24 408	98.51 327	99.70 168	94.55 246	99.91 120	92.76 396	99.85 80	99.42 213
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
mmtdpeth		96.95 333	96.71 332	97.67 352	99.33 243	94.90 378	99.89 2	99.28 297	98.15 149	99.72 81	98.57 385	86.56 391	99.90 132	99.82 22	89.02 410	98.20 380

UWE-MVS		97.58 301	97.29 308	98.48 277	99.09 309	96.25 344	99.01 347	96.61 421	97.86 189	99.19 221	99.01 356	88.72 367	99.90 132	97.38 287	98.69 218	99.28 233

test_vis1_rt		95.81 357	95.65 356	96.32 383	99.67 120	91.35 410	99.49 186	96.74 419	98.25 135	95.24 398	98.10 404	74.96 419	99.90 132	99.53 43	98.85 209	97.70 404

FA-MVS(test-final)		98.75 163	98.53 174	99.41 144	99.55 170	99.05 158	99.80 25	99.01 338	96.59 320	99.58 127	99.59 224	95.39 198	99.90 132	97.78 246	99.49 158	99.28 233

MCST-MVS		99.43 46	99.30 55	99.82 48	99.79 57	99.74 47	99.29 272	99.40 234	98.79 80	99.52 140	99.62 215	98.91 37	99.90 132	98.64 158	99.75 125	99.82 61

CDPH-MVS		99.13 101	98.91 123	99.80 54	99.75 81	99.71 50	99.15 313	99.41 228	96.60 318	99.60 123	99.55 239	98.83 45	99.90 132	97.48 278	99.83 97	99.78 87

NCCC		99.34 66	99.19 78	99.79 57	99.61 151	99.65 65	99.30 267	99.48 168	98.86 70	99.21 215	99.63 210	98.72 64	99.90 132	98.25 206	99.63 146	99.80 77

114514_t		98.93 137	98.67 153	99.72 75	99.85 26	99.53 91	99.62 95	99.59 63	92.65 403	99.71 83	99.78 133	98.06 106	99.90 132	98.84 132	99.91 38	99.74 99

1112_ss		98.98 133	98.77 143	99.59 100	99.68 118	99.02 160	99.25 293	99.48 168	97.23 265	99.13 230	99.58 228	96.93 143	99.90 132	98.87 122	98.78 215	99.84 46

PHI-MVS		99.30 72	99.17 80	99.70 76	99.56 166	99.52 95	99.58 117	99.80 8	97.12 274	99.62 117	99.73 159	98.58 75	99.90 132	98.61 164	99.91 38	99.68 129

AdaColmap		99.01 131	98.80 139	99.66 79	99.56 166	99.54 88	99.18 308	99.70 15	98.18 147	99.35 182	99.63 210	96.32 165	99.90 132	97.48 278	99.77 120	99.55 172

COLMAP_ROB	97.56 6	98.86 145	98.75 145	99.17 184	99.88 11	98.53 218	99.34 258	99.59 63	97.55 229	98.70 305	99.89 35	95.83 184	99.90 132	98.10 216	99.90 47	99.08 252
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 192	98.03 212	99.31 160	99.63 141	98.56 215	99.54 149	96.75 418	97.53 233	99.73 76	99.65 198	91.25 340	99.89 144	98.62 161	99.56 152	99.48 195

tttt0517		98.42 183	98.14 197	99.28 172	99.66 130	98.38 235	99.74 46	96.85 416	97.68 214	99.79 55	99.74 153	91.39 336	99.89 144	98.83 135	99.56 152	99.57 169

test12				99.75 66	99.64 138	99.61 75		99.29 295		99.21 215		98.38 91	99.89 144		99.74 128	99.74 99

Test_1112_low_res		98.89 140	98.66 156	99.57 105	99.69 114	98.95 174	99.03 339	99.47 189	96.98 288	99.15 228	99.23 332	96.77 147	99.89 144	98.83 135	98.78 215	99.86 36

CNLPA		99.14 99	98.99 108	99.59 100	99.58 160	99.41 109	99.16 310	99.44 217	98.45 111	99.19 221	99.49 262	98.08 105	99.89 144	97.73 254	99.75 125	99.48 195

sd_testset		98.75 163	98.57 170	99.29 168	99.81 47	98.26 239	99.56 130	99.62 43	98.78 83	99.64 110	99.88 43	92.02 319	99.88 149	99.54 41	98.26 245	99.72 112

APD_test1		95.87 355	96.49 337	94.00 390	99.53 174	84.01 419	99.54 149	99.32 283	95.91 361	97.99 356	99.85 63	85.49 397	99.88 149	91.96 399	98.84 210	98.12 384

diffmvs		99.14 99	99.02 102	99.51 126	99.61 151	98.96 171	99.28 277	99.49 156	98.46 109	99.72 81	99.71 164	96.50 158	99.88 149	99.31 70	99.11 187	99.67 132
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		98.86 145	98.80 139	99.03 199	99.76 71	98.79 196	99.28 277	99.91 3	97.42 248	99.67 93	99.37 299	97.53 118	99.88 149	98.98 105	97.29 304	98.42 365

PVSNet_Blended		99.08 118	98.97 112	99.42 143	99.76 71	98.79 196	98.78 378	99.91 3	96.74 303	99.67 93	99.49 262	97.53 118	99.88 149	98.98 105	99.85 80	99.60 158

MVS		97.28 322	96.55 335	99.48 132	98.78 356	98.95 174	99.27 282	99.39 237	83.53 421	98.08 351	99.54 244	96.97 141	99.87 154	94.23 377	99.16 181	99.63 151

MG-MVS		99.13 101	99.02 102	99.45 138	99.57 162	98.63 209	99.07 329	99.34 266	98.99 55	99.61 120	99.82 87	97.98 109	99.87 154	97.00 308	99.80 108	99.85 40

MSDG		98.98 133	98.80 139	99.53 118	99.76 71	99.19 135	98.75 381	99.55 85	97.25 262	99.47 148	99.77 141	97.82 112	99.87 154	96.93 315	99.90 47	99.54 174

ETV-MVS		99.26 80	99.21 74	99.40 145	99.46 206	99.30 123	99.56 130	99.52 112	98.52 104	99.44 156	99.27 327	98.41 90	99.86 157	99.10 93	99.59 150	99.04 259

thisisatest0515		98.14 210	97.79 236	99.19 182	99.50 194	98.50 225	98.61 393	96.82 417	96.95 292	99.54 136	99.43 280	91.66 331	99.86 157	98.08 221	99.51 156	99.22 241

thres600view7		97.86 254	97.51 271	98.92 216	99.72 100	97.95 258	99.59 109	98.74 377	97.94 181	99.27 200	98.62 382	91.75 325	99.86 157	93.73 383	98.19 252	98.96 269

lupinMVS		99.13 101	99.01 106	99.46 137	99.51 183	98.94 177	99.05 334	99.16 318	97.86 189	99.80 53	99.56 236	97.39 121	99.86 157	98.94 110	99.85 80	99.58 166

PVSNet	96.02 17	98.85 152	98.84 136	98.89 225	99.73 96	97.28 287	98.32 409	99.60 57	97.86 189	99.50 143	99.57 233	96.75 148	99.86 157	98.56 176	99.70 135	99.54 174

MAR-MVS		98.86 145	98.63 158	99.54 110	99.37 234	99.66 61	99.45 204	99.54 94	96.61 315	99.01 254	99.40 290	97.09 134	99.86 157	97.68 261	99.53 155	99.10 247
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		97.44 314	97.02 323	98.71 254	99.18 285	96.89 318	99.19 306	99.04 334	97.78 202	98.31 338	98.29 396	85.41 398	99.85 163	98.01 227	97.95 262	99.39 219

test2506		96.81 337	96.65 333	97.29 364	99.74 89	92.21 407	99.60 102	85.06 438	99.13 30	99.77 64	99.93 10	87.82 384	99.85 163	99.38 59	99.38 164	99.80 77

AllTest		98.87 142	98.72 147	99.31 160	99.86 20	98.48 228	99.56 130	99.61 50	97.85 192	99.36 179	99.85 63	95.95 177	99.85 163	96.66 328	99.83 97	99.59 162

TestCases				99.31 160	99.86 20	98.48 228		99.61 50	97.85 192	99.36 179	99.85 63	95.95 177	99.85 163	96.66 328	99.83 97	99.59 162

jason		99.13 101	99.03 98	99.45 138	99.46 206	98.87 184	99.12 319	99.26 301	98.03 174	99.79 55	99.65 198	97.02 139	99.85 163	99.02 102	99.90 47	99.65 139
jason: jason.
CNVR-MVS		99.42 48	99.30 55	99.78 60	99.62 147	99.71 50	99.26 291	99.52 112	98.82 75	99.39 172	99.71 164	98.96 25	99.85 163	98.59 169	99.80 108	99.77 89

PAPM_NR		99.04 124	98.84 136	99.66 79	99.74 89	99.44 105	99.39 238	99.38 245	97.70 212	99.28 195	99.28 324	98.34 93	99.85 163	96.96 312	99.45 160	99.69 125

testing99		97.36 317	96.94 326	98.63 259	99.18 285	96.70 324	99.30 267	98.93 346	97.71 209	98.23 343	98.26 397	84.92 401	99.84 170	98.04 226	97.85 269	99.35 225

testing222		97.16 327	96.50 336	99.16 185	99.16 295	98.47 230	99.27 282	98.66 388	97.71 209	98.23 343	98.15 400	82.28 414	99.84 170	97.36 288	97.66 275	99.18 243

test1111		98.04 225	98.11 201	97.83 342	99.74 89	93.82 392	99.58 117	95.40 425	99.12 35	99.65 105	99.93 10	90.73 345	99.84 170	99.43 57	99.38 164	99.82 61

ECVR-MVS		98.04 225	98.05 210	98.00 327	99.74 89	94.37 387	99.59 109	94.98 426	99.13 30	99.66 98	99.93 10	90.67 346	99.84 170	99.40 58	99.38 164	99.80 77

test_yl		98.86 145	98.63 158	99.54 110	99.49 196	99.18 137	99.50 175	99.07 330	98.22 140	99.61 120	99.51 256	95.37 199	99.84 170	98.60 167	98.33 239	99.59 162

DCV-MVSNet		98.86 145	98.63 158	99.54 110	99.49 196	99.18 137	99.50 175	99.07 330	98.22 140	99.61 120	99.51 256	95.37 199	99.84 170	98.60 167	98.33 239	99.59 162

Fast-Effi-MVS+		98.70 167	98.43 178	99.51 126	99.51 183	99.28 126	99.52 159	99.47 189	96.11 354	99.01 254	99.34 309	96.20 169	99.84 170	97.88 235	98.82 212	99.39 219

TSAR-MVS + GP.		99.36 63	99.36 39	99.36 151	99.67 120	98.61 212	99.07 329	99.33 273	99.00 53	99.82 48	99.81 101	99.06 16	99.84 170	99.09 94	99.42 162	99.65 139

tpmrst		98.33 193	98.48 176	97.90 336	99.16 295	94.78 379	99.31 265	99.11 323	97.27 260	99.45 151	99.59 224	95.33 201	99.84 170	98.48 183	98.61 221	99.09 251

Vis-MVSNet		99.12 107	98.97 112	99.56 107	99.78 59	99.10 149	99.68 66	99.66 28	98.49 106	99.86 39	99.87 52	94.77 230	99.84 170	99.19 82	99.41 163	99.74 99
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 174	98.34 184	99.51 126	99.40 226	99.03 159	98.80 376	99.36 254	96.33 335	99.00 258	99.12 346	98.46 84	99.84 170	95.23 363	99.37 171	99.66 135

PatchMatch-RL		98.84 155	98.62 163	99.52 124	99.71 105	99.28 126	99.06 332	99.77 9	97.74 207	99.50 143	99.53 248	95.41 197	99.84 170	97.17 302	99.64 144	99.44 211

EPP-MVSNet		99.13 101	98.99 108	99.53 118	99.65 136	99.06 156	99.81 20	99.33 273	97.43 246	99.60 123	99.88 43	97.14 132	99.84 170	99.13 88	98.94 201	99.69 125

testing3-2		97.84 259	97.70 251	98.24 309	99.53 174	95.37 368	99.55 144	98.67 387	98.46 109	99.27 200	99.34 309	86.58 390	99.83 183	99.32 69	98.63 220	99.52 181

testing11		97.50 307	97.10 320	98.71 254	99.20 279	96.91 316	99.29 272	98.82 366	97.89 186	98.21 346	98.40 391	85.63 396	99.83 183	98.45 188	98.04 260	99.37 223

thres100view900		97.76 273	97.45 280	98.69 256	99.72 100	97.86 264	99.59 109	98.74 377	97.93 182	99.26 205	98.62 382	91.75 325	99.83 183	93.22 388	98.18 253	98.37 371

tfpn200view9		97.72 283	97.38 293	98.72 252	99.69 114	97.96 256	99.50 175	98.73 383	97.83 195	99.17 226	98.45 389	91.67 329	99.83 183	93.22 388	98.18 253	98.37 371

test_prior				99.68 77	99.67 120	99.48 100		99.56 77					99.83 183			99.74 99

1314		98.68 169	98.54 173	99.11 191	98.89 340	98.65 206	99.27 282	99.49 156	96.89 296	97.99 356	99.56 236	97.72 116	99.83 183	97.74 253	99.27 175	98.84 275

thres400		97.77 272	97.38 293	98.92 216	99.69 114	97.96 256	99.50 175	98.73 383	97.83 195	99.17 226	98.45 389	91.67 329	99.83 183	93.22 388	98.18 253	98.96 269

casdiffmvs		99.13 101	98.98 111	99.56 107	99.65 136	99.16 140	99.56 130	99.50 146	98.33 126	99.41 165	99.86 56	95.92 180	99.83 183	99.45 56	99.16 181	99.70 123
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 26	99.48 19	99.54 110	99.78 59	99.30 123	99.89 2	99.58 67	98.56 100	99.73 76	99.69 178	98.55 78	99.82 191	99.69 27	99.85 80	99.48 195

MVS_Test		99.10 116	98.97 112	99.48 132	99.49 196	99.14 145	99.67 69	99.34 266	97.31 257	99.58 127	99.76 145	97.65 117	99.82 191	98.87 122	99.07 193	99.46 206

dp		97.75 277	97.80 235	97.59 356	99.10 306	93.71 395	99.32 262	98.88 359	96.48 327	99.08 242	99.55 239	92.67 303	99.82 191	96.52 332	98.58 224	99.24 239

RPSCF		98.22 200	98.62 163	96.99 370	99.82 43	91.58 409	99.72 52	99.44 217	96.61 315	99.66 98	99.89 35	95.92 180	99.82 191	97.46 281	99.10 190	99.57 169

PMMVS		98.80 159	98.62 163	99.34 153	99.27 261	98.70 202	98.76 380	99.31 287	97.34 254	99.21 215	99.07 348	97.20 131	99.82 191	98.56 176	98.87 207	99.52 181

UBG		97.85 255	97.48 274	98.95 210	99.25 268	97.64 275	99.24 295	98.74 377	97.90 185	98.64 315	98.20 399	88.65 371	99.81 196	98.27 205	98.40 234	99.42 213

EIA-MVS		99.18 90	99.09 90	99.45 138	99.49 196	99.18 137	99.67 69	99.53 107	97.66 217	99.40 170	99.44 278	98.10 103	99.81 196	98.94 110	99.62 147	99.35 225

Effi-MVS+		98.81 156	98.59 169	99.48 132	99.46 206	99.12 148	98.08 416	99.50 146	97.50 237	99.38 174	99.41 286	96.37 164	99.81 196	99.11 90	98.54 229	99.51 189

thres200		97.61 299	97.28 309	98.62 260	99.64 138	98.03 250	99.26 291	98.74 377	97.68 214	99.09 240	98.32 395	91.66 331	99.81 196	92.88 393	98.22 248	98.03 390

tpmvs		97.98 236	98.02 214	97.84 341	99.04 319	94.73 380	99.31 265	99.20 313	96.10 358	98.76 295	99.42 282	94.94 216	99.81 196	96.97 311	98.45 233	98.97 267

casdiffmvs_mvg		99.15 96	99.02 102	99.55 109	99.66 130	99.09 150	99.64 84	99.56 77	98.26 134	99.45 151	99.87 52	96.03 174	99.81 196	99.54 41	99.15 184	99.73 104
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	98.81 156	99.37 37	97.12 368	99.60 156	91.75 408	98.61 393	99.44 217	99.35 18	99.83 47	99.85 63	98.70 66	99.81 196	99.02 102	99.91 38	99.81 68

DPM-MVS		98.95 136	98.71 149	99.66 79	99.63 141	99.55 86	98.64 392	99.10 324	97.93 182	99.42 161	99.55 239	98.67 69	99.80 203	95.80 348	99.68 139	99.61 155

DP-MVS Recon		99.12 107	98.95 118	99.65 83	99.74 89	99.70 52	99.27 282	99.57 72	96.40 334	99.42 161	99.68 185	98.75 58	99.80 203	97.98 229	99.72 131	99.44 211

MVS_111021_LR		99.41 52	99.33 45	99.65 83	99.77 67	99.51 96	98.94 362	99.85 6	98.82 75	99.65 105	99.74 153	98.51 81	99.80 203	98.83 135	99.89 58	99.64 146

CS-MVS		99.50 24	99.48 19	99.54 110	99.76 71	99.42 107	99.90 1	99.55 85	98.56 100	99.78 60	99.70 168	98.65 71	99.79 206	99.65 31	99.78 117	99.41 216

Fast-Effi-MVS+-dtu		98.77 162	98.83 138	98.60 261	99.41 221	96.99 310	99.52 159	99.49 156	98.11 157	99.24 207	99.34 309	96.96 142	99.79 206	97.95 231	99.45 160	99.02 262

baseline1		98.31 194	97.95 221	99.38 150	99.50 194	98.74 199	99.59 109	98.93 346	98.41 116	99.14 229	99.60 222	94.59 242	99.79 206	98.48 183	93.29 386	99.61 155

baseline		99.15 96	99.02 102	99.53 118	99.66 130	99.14 145	99.72 52	99.48 168	98.35 123	99.42 161	99.84 73	96.07 172	99.79 206	99.51 46	99.14 185	99.67 132

PVSNet_0	94.43 19	96.09 352	95.47 359	97.94 332	99.31 251	94.34 389	97.81 418	99.70 15	97.12 274	97.46 369	98.75 379	89.71 357	99.79 206	97.69 260	81.69 421	99.68 129

API-MVS		99.04 124	99.03 98	99.06 195	99.40 226	99.31 121	99.55 144	99.56 77	98.54 102	99.33 186	99.39 294	98.76 55	99.78 211	96.98 310	99.78 117	98.07 387

OMC-MVS		99.08 118	99.04 96	99.20 181	99.67 120	98.22 241	99.28 277	99.52 112	98.07 165	99.66 98	99.81 101	97.79 113	99.78 211	97.79 245	99.81 104	99.60 158

GeoE		98.85 152	98.62 163	99.53 118	99.61 151	99.08 153	99.80 25	99.51 126	97.10 278	99.31 188	99.78 133	95.23 207	99.77 213	98.21 208	99.03 196	99.75 95

alignmvs		98.81 156	98.56 172	99.58 103	99.43 214	99.42 107	99.51 168	98.96 344	98.61 96	99.35 182	98.92 369	94.78 227	99.77 213	99.35 61	98.11 258	99.54 174

tpm cat1		97.39 316	97.36 295	97.50 359	99.17 293	93.73 394	99.43 215	99.31 287	91.27 407	98.71 299	99.08 347	94.31 256	99.77 213	96.41 337	98.50 231	99.00 263

CostFormer		97.72 283	97.73 248	97.71 350	99.15 299	94.02 391	99.54 149	99.02 337	94.67 382	99.04 251	99.35 305	92.35 315	99.77 213	98.50 182	97.94 263	99.34 228

MGCFI-Net		99.01 131	98.85 134	99.50 131	99.42 216	99.26 129	99.82 16	99.48 168	98.60 97	99.28 195	98.81 374	97.04 138	99.76 217	99.29 73	97.87 267	99.47 201

test_241102_ONE					99.84 32	99.90 2		99.48 168	99.07 45	99.91 23	99.74 153	99.20 7	99.76 217

MDTV_nov1_ep13			98.32 186		99.11 303	94.44 385	99.27 282	98.74 377	97.51 236	99.40 170	99.62 215	94.78 227	99.76 217	97.59 265	98.81 214

sasdasda		99.02 127	98.86 132	99.51 126	99.42 216	99.32 117	99.80 25	99.48 168	98.63 93	99.31 188	98.81 374	97.09 134	99.75 220	99.27 76	97.90 264	99.47 201

canonicalmvs		99.02 127	98.86 132	99.51 126	99.42 216	99.32 117	99.80 25	99.48 168	98.63 93	99.31 188	98.81 374	97.09 134	99.75 220	99.27 76	97.90 264	99.47 201

Effi-MVS+-dtu		98.78 160	98.89 127	98.47 282	99.33 243	96.91 316	99.57 124	99.30 291	98.47 108	99.41 165	98.99 359	96.78 146	99.74 222	98.73 146	99.38 164	98.74 290

patchmatchnet-post											98.70 380	94.79 226	99.74 222

SCA		98.19 204	98.16 194	98.27 308	99.30 252	95.55 359	99.07 329	98.97 342	97.57 226	99.43 158	99.57 233	92.72 298	99.74 222	97.58 266	99.20 179	99.52 181

BH-untuned		98.42 183	98.36 182	98.59 262	99.49 196	96.70 324	99.27 282	99.13 322	97.24 264	98.80 290	99.38 296	95.75 187	99.74 222	97.07 306	99.16 181	99.33 229

BH-RMVSNet		98.41 185	98.08 206	99.40 145	99.41 221	98.83 192	99.30 267	98.77 373	97.70 212	98.94 268	99.65 198	92.91 293	99.74 222	96.52 332	99.55 154	99.64 146

MVS_111021_HR		99.41 52	99.32 47	99.66 79	99.72 100	99.47 102	98.95 360	99.85 6	98.82 75	99.54 136	99.73 159	98.51 81	99.74 222	98.91 116	99.88 62	99.77 89

test_post											65.99 432	94.65 240	99.73 228

XVG-ACMP-BASELINE		97.83 262	97.71 250	98.20 311	99.11 303	96.33 340	99.41 226	99.52 112	98.06 169	99.05 250	99.50 259	89.64 359	99.73 228	97.73 254	97.38 302	98.53 353

HyFIR lowres test		99.11 112	98.92 121	99.65 83	99.90 4	99.37 111	99.02 342	99.91 3	97.67 216	99.59 126	99.75 148	95.90 182	99.73 228	99.53 43	99.02 198	99.86 36

DeepMVS_CX				93.34 393	99.29 256	82.27 422		99.22 309	85.15 419	96.33 390	99.05 351	90.97 343	99.73 228	93.57 385	97.77 272	98.01 391

Patchmatch-test		97.93 242	97.65 256	98.77 248	99.18 285	97.07 301	99.03 339	99.14 321	96.16 349	98.74 296	99.57 233	94.56 244	99.72 232	93.36 387	99.11 187	99.52 181

LPG-MVS_test		98.22 200	98.13 199	98.49 275	99.33 243	97.05 303	99.58 117	99.55 85	97.46 239	99.24 207	99.83 78	92.58 305	99.72 232	98.09 217	97.51 288	98.68 308

LGP-MVS_train				98.49 275	99.33 243	97.05 303		99.55 85	97.46 239	99.24 207	99.83 78	92.58 305	99.72 232	98.09 217	97.51 288	98.68 308

BH-w/o		98.00 234	97.89 230	98.32 300	99.35 238	96.20 346	99.01 347	98.90 356	96.42 332	98.38 334	99.00 357	95.26 205	99.72 232	96.06 341	98.61 221	99.03 260

ACMP	97.20 11	98.06 219	97.94 223	98.45 285	99.37 234	97.01 308	99.44 210	99.49 156	97.54 232	98.45 331	99.79 126	91.95 321	99.72 232	97.91 233	97.49 293	98.62 336
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 229	97.90 226	98.40 293	99.23 272	96.80 322	99.70 56	99.60 57	97.12 274	98.18 348	99.70 168	91.73 327	99.72 232	98.39 192	97.45 295	98.68 308
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							99.23 298				65.14 433	94.18 261	99.71 238	97.58 266

ADS-MVSNet		98.20 203	98.08 206	98.56 269	99.33 243	96.48 335	99.23 298	99.15 319	96.24 342	99.10 237	99.67 191	94.11 262	99.71 238	96.81 320	99.05 194	99.48 195

JIA-IIPM		97.50 307	97.02 323	98.93 214	98.73 365	97.80 266	99.30 267	98.97 342	91.73 406	98.91 271	94.86 421	95.10 211	99.71 238	97.58 266	97.98 261	99.28 233

EPMVS		97.82 265	97.65 256	98.35 297	98.88 341	95.98 350	99.49 186	94.71 428	97.57 226	99.26 205	99.48 268	92.46 312	99.71 238	97.87 237	99.08 192	99.35 225

TDRefinement		95.42 361	94.57 368	97.97 329	89.83 431	96.11 349	99.48 191	98.75 374	96.74 303	96.68 387	99.88 43	88.65 371	99.71 238	98.37 195	82.74 420	98.09 386

ACMM	97.58 5	98.37 191	98.34 184	98.48 277	99.41 221	97.10 297	99.56 130	99.45 209	98.53 103	99.04 251	99.85 63	93.00 289	99.71 238	98.74 144	97.45 295	98.64 327
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 239	97.77 241	98.57 266	99.59 158	96.61 331	99.45 204	99.08 327	98.21 142	98.88 276	99.80 114	88.66 370	99.70 244	98.58 170	97.72 273	99.39 219

CHOSEN 280x420		99.12 107	99.13 83	99.08 192	99.66 130	97.89 261	98.43 403	99.71 13	98.88 69	99.62 117	99.76 145	96.63 152	99.70 244	99.46 55	99.99 1	99.66 135

EC-MVSNet		99.44 43	99.39 33	99.58 103	99.56 166	99.49 98	99.88 4	99.58 67	98.38 118	99.73 76	99.69 178	98.20 99	99.70 244	99.64 33	99.82 101	99.54 174

PatchmatchNet		98.31 194	98.36 182	98.19 312	99.16 295	95.32 369	99.27 282	98.92 349	97.37 252	99.37 176	99.58 228	94.90 220	99.70 244	97.43 284	99.21 178	99.54 174
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 214	97.99 216	98.44 288	99.41 221	96.96 314	99.60 102	99.56 77	98.09 160	98.15 349	99.91 23	90.87 344	99.70 244	98.88 119	97.45 295	98.67 315
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 307	96.90 327	99.29 168	99.23 272	98.78 198	99.32 262	98.90 356	97.52 235	98.56 324	98.09 405	84.72 403	99.69 249	97.86 238	97.88 266	99.39 219

HQP_MVS		98.27 199	98.22 192	98.44 288	99.29 256	96.97 312	99.39 238	99.47 189	98.97 61	99.11 234	99.61 219	92.71 300	99.69 249	97.78 246	97.63 276	98.67 315

plane_prior5								99.47 189					99.69 249	97.78 246	97.63 276	98.67 315

D2MVS		98.41 185	98.50 175	98.15 317	99.26 264	96.62 330	99.40 234	99.61 50	97.71 209	98.98 261	99.36 302	96.04 173	99.67 252	98.70 149	97.41 300	98.15 383

IS-MVSNet		99.05 123	98.87 130	99.57 105	99.73 96	99.32 117	99.75 42	99.20 313	98.02 176	99.56 131	99.86 56	96.54 156	99.67 252	98.09 217	99.13 186	99.73 104

CLD-MVS		98.16 208	98.10 202	98.33 298	99.29 256	96.82 321	98.75 381	99.44 217	97.83 195	99.13 230	99.55 239	92.92 291	99.67 252	98.32 202	97.69 274	98.48 357
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 324	97.30 306	97.09 369	99.43 214	93.31 400	99.73 50	98.87 361	98.83 74	99.28 195	99.80 114	84.45 404	99.66 255	97.88 235	97.45 295	98.30 373

AUN-MVS		96.88 335	96.31 341	98.59 262	99.48 203	97.04 306	99.27 282	99.22 309	97.44 245	98.51 327	99.41 286	91.97 320	99.66 255	97.71 257	83.83 418	99.07 257

UniMVSNet_ETH3D		97.32 321	96.81 329	98.87 231	99.40 226	97.46 281	99.51 168	99.53 107	95.86 362	98.54 326	99.77 141	82.44 412	99.66 255	98.68 154	97.52 287	99.50 193

OPM-MVS		98.19 204	98.10 202	98.45 285	98.88 341	97.07 301	99.28 277	99.38 245	98.57 99	99.22 212	99.81 101	92.12 317	99.66 255	98.08 221	97.54 285	98.61 345
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 245	97.78 239	98.32 300	99.46 206	96.68 328	99.56 130	99.54 94	98.41 116	97.79 365	99.87 52	90.18 353	99.66 255	98.05 225	97.18 309	98.62 336

hse-mvs2		97.50 307	97.14 317	98.59 262	99.49 196	97.05 303	99.28 277	99.22 309	98.94 64	99.66 98	99.42 282	94.93 217	99.65 260	99.48 52	83.80 419	99.08 252

VPA-MVSNet		98.29 197	97.95 221	99.30 165	99.16 295	99.54 88	99.50 175	99.58 67	98.27 132	99.35 182	99.37 299	92.53 307	99.65 260	99.35 61	94.46 368	98.72 292

TR-MVS		97.76 273	97.41 291	98.82 240	99.06 315	97.87 262	98.87 370	98.56 391	96.63 314	98.68 307	99.22 333	92.49 308	99.65 260	95.40 359	97.79 271	98.95 271

reproduce_monomvs		97.89 249	97.87 231	97.96 331	99.51 183	95.45 364	99.60 102	99.25 303	99.17 25	98.85 284	99.49 262	89.29 362	99.64 263	99.35 61	96.31 325	98.78 278

gm-plane-assit					98.54 385	92.96 402			94.65 383		99.15 341		99.64 263	97.56 271

HQP4-MVS										98.66 308			99.64 263			98.64 327

HQP-MVS		98.02 229	97.90 226	98.37 296	99.19 282	96.83 319	98.98 353	99.39 237	98.24 136	98.66 308	99.40 290	92.47 309	99.64 263	97.19 299	97.58 281	98.64 327

PAPM		97.59 300	97.09 321	99.07 193	99.06 315	98.26 239	98.30 410	99.10 324	94.88 377	98.08 351	99.34 309	96.27 167	99.64 263	89.87 407	98.92 204	99.31 231

TAPA-MVS	97.07 15	97.74 279	97.34 300	98.94 212	99.70 110	97.53 278	99.25 293	99.51 126	91.90 405	99.30 191	99.63 210	98.78 51	99.64 263	88.09 414	99.87 65	99.65 139
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 189	98.09 205	99.24 177	99.26 264	99.32 117	99.56 130	99.55 85	97.45 242	98.71 299	99.83 78	93.23 284	99.63 269	98.88 119	96.32 324	98.76 284

ITE_SJBPF				98.08 320	99.29 256	96.37 338		98.92 349	98.34 124	98.83 285	99.75 148	91.09 341	99.62 270	95.82 346	97.40 301	98.25 377

LF4IMVS		97.52 304	97.46 279	97.70 351	98.98 330	95.55 359	99.29 272	98.82 366	98.07 165	98.66 308	99.64 204	89.97 354	99.61 271	97.01 307	96.68 314	97.94 398

tpm		97.67 294	97.55 265	98.03 322	99.02 321	95.01 375	99.43 215	98.54 393	96.44 330	99.12 232	99.34 309	91.83 324	99.60 272	97.75 252	96.46 320	99.48 195

tpm2		97.44 314	97.34 300	97.74 349	99.15 299	94.36 388	99.45 204	98.94 345	93.45 396	98.90 273	99.44 278	91.35 337	99.59 273	97.31 290	98.07 259	99.29 232

baseline2		97.87 252	97.55 265	98.82 240	99.18 285	98.02 251	99.41 226	96.58 422	96.97 289	96.51 388	99.17 338	93.43 281	99.57 274	97.71 257	99.03 196	98.86 273

MS-PatchMatch		97.24 326	97.32 304	96.99 370	98.45 388	93.51 399	98.82 374	99.32 283	97.41 249	98.13 350	99.30 320	88.99 364	99.56 275	95.68 352	99.80 108	97.90 401

TinyColmap		97.12 329	96.89 328	97.83 342	99.07 313	95.52 362	98.57 396	98.74 377	97.58 225	97.81 364	99.79 126	88.16 378	99.56 275	95.10 364	97.21 307	98.39 369

USDC		97.34 319	97.20 314	97.75 347	99.07 313	95.20 371	98.51 400	99.04 334	97.99 177	98.31 338	99.86 56	89.02 363	99.55 277	95.67 353	97.36 303	98.49 356

MSLP-MVS++		99.46 35	99.47 21	99.44 142	99.60 156	99.16 140	99.41 226	99.71 13	98.98 58	99.45 151	99.78 133	99.19 9	99.54 278	99.28 74	99.84 88	99.63 151

UWE-MVS-28		97.36 317	97.24 313	97.75 347	98.84 350	94.44 385	99.24 295	97.58 411	97.98 178	99.00 258	99.00 357	91.35 337	99.53 279	93.75 382	98.39 235	99.27 237

TAMVS		99.12 107	99.08 91	99.24 177	99.46 206	98.55 216	99.51 168	99.46 198	98.09 160	99.45 151	99.82 87	98.34 93	99.51 280	98.70 149	98.93 202	99.67 132

EPNet_dtu		98.03 227	97.96 219	98.23 310	98.27 391	95.54 361	99.23 298	98.75 374	99.02 48	97.82 363	99.71 164	96.11 171	99.48 281	93.04 391	99.65 143	99.69 125
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 339	96.22 343	97.97 329	97.00 413	96.28 342	98.66 390	99.03 336	96.61 315	96.93 385	99.79 126	87.20 387	99.47 282	96.65 330	94.13 375	98.16 382

EG-PatchMatch MVS		95.97 354	95.69 355	96.81 377	97.78 398	92.79 403	99.16 310	98.93 346	96.16 349	94.08 406	99.22 333	82.72 410	99.47 282	95.67 353	97.50 290	98.17 381

myMVS_eth3d28		97.69 288	97.34 300	98.73 250	99.27 261	97.52 279	99.33 260	98.78 372	98.03 174	98.82 287	98.49 387	86.64 389	99.46 284	98.44 189	98.24 247	99.23 240

MVP-Stereo		97.81 267	97.75 246	97.99 328	97.53 402	96.60 332	98.96 357	98.85 363	97.22 266	97.23 376	99.36 302	95.28 202	99.46 284	95.51 355	99.78 117	97.92 400
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 176	98.67 153	98.30 302	99.35 238	95.59 358	99.50 175	99.55 85	98.60 97	99.39 172	99.83 78	94.48 249	99.45 286	98.75 143	98.56 227	99.85 40

test-LLR		98.06 219	97.90 226	98.55 271	98.79 353	97.10 297	98.67 387	97.75 407	97.34 254	98.61 320	98.85 371	94.45 251	99.45 286	97.25 293	99.38 164	99.10 247

TESTMET0.1,1		97.55 302	97.27 312	98.40 293	98.93 335	96.53 333	98.67 387	97.61 410	96.96 290	98.64 315	99.28 324	88.63 373	99.45 286	97.30 291	99.38 164	99.21 242

test-mter		97.49 312	97.13 319	98.55 271	98.79 353	97.10 297	98.67 387	97.75 407	96.65 310	98.61 320	98.85 371	88.23 377	99.45 286	97.25 293	99.38 164	99.10 247

mvs_anonymous		99.03 126	98.99 108	99.16 185	99.38 231	98.52 222	99.51 168	99.38 245	97.79 200	99.38 174	99.81 101	97.30 127	99.45 286	99.35 61	98.99 199	99.51 189

tfpnnormal		97.84 259	97.47 277	98.98 205	99.20 279	99.22 134	99.64 84	99.61 50	96.32 336	98.27 342	99.70 168	93.35 283	99.44 291	95.69 351	95.40 351	98.27 375

v7n		97.87 252	97.52 269	98.92 216	98.76 363	98.58 214	99.84 12	99.46 198	96.20 345	98.91 271	99.70 168	94.89 221	99.44 291	96.03 342	93.89 380	98.75 286

jajsoiax		98.43 182	98.28 189	98.88 227	98.60 380	98.43 232	99.82 16	99.53 107	98.19 144	98.63 317	99.80 114	93.22 286	99.44 291	99.22 80	97.50 290	98.77 282

mvs_tets		98.40 188	98.23 191	98.91 220	98.67 373	98.51 224	99.66 75	99.53 107	98.19 144	98.65 314	99.81 101	92.75 295	99.44 291	99.31 70	97.48 294	98.77 282

Vis-MVSNet (Re-imp)		98.87 142	98.72 147	99.31 160	99.71 105	98.88 183	99.80 25	99.44 217	97.91 184	99.36 179	99.78 133	95.49 196	99.43 295	97.91 233	99.11 187	99.62 153

OPU-MVS				99.64 89	99.56 166	99.72 48	99.60 102				99.70 168	99.27 5	99.42 296	98.24 207	99.80 108	99.79 81

Anonymous20231211		97.88 250	97.54 268	98.90 222	99.71 105	98.53 218	99.48 191	99.57 72	94.16 387	98.81 288	99.68 185	93.23 284	99.42 296	98.84 132	94.42 370	98.76 284

ttmdpeth		97.80 269	97.63 260	98.29 303	98.77 361	97.38 284	99.64 84	99.36 254	98.78 83	96.30 391	99.58 228	92.34 316	99.39 298	98.36 197	95.58 346	98.10 385

VPNet		97.84 259	97.44 285	99.01 201	99.21 277	98.94 177	99.48 191	99.57 72	98.38 118	99.28 195	99.73 159	88.89 365	99.39 298	99.19 82	93.27 387	98.71 294

nrg030		98.64 173	98.42 179	99.28 172	99.05 318	99.69 54	99.81 20	99.46 198	98.04 172	99.01 254	99.82 87	96.69 150	99.38 300	99.34 66	94.59 367	98.78 278

GA-MVS		97.85 255	97.47 277	99.00 203	99.38 231	97.99 253	98.57 396	99.15 319	97.04 285	98.90 273	99.30 320	89.83 356	99.38 300	96.70 325	98.33 239	99.62 153

UniMVSNet (Re)		98.29 197	98.00 215	99.13 190	99.00 324	99.36 114	99.49 186	99.51 126	97.95 180	98.97 263	99.13 343	96.30 166	99.38 300	98.36 197	93.34 385	98.66 323

FIs		98.78 160	98.63 158	99.23 179	99.18 285	99.54 88	99.83 15	99.59 63	98.28 130	98.79 292	99.81 101	96.75 148	99.37 303	99.08 95	96.38 322	98.78 278

PS-MVSNAJss		98.92 138	98.92 121	98.90 222	98.78 356	98.53 218	99.78 32	99.54 94	98.07 165	99.00 258	99.76 145	99.01 18	99.37 303	99.13 88	97.23 306	98.81 276

CDS-MVSNet		99.09 117	99.03 98	99.25 175	99.42 216	98.73 200	99.45 204	99.46 198	98.11 157	99.46 150	99.77 141	98.01 108	99.37 303	98.70 149	98.92 204	99.66 135
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 358	95.16 363	97.51 358	99.30 252	93.69 396	98.88 368	95.78 423	85.09 420	98.78 293	92.65 423	91.29 339	99.37 303	94.85 369	99.85 80	99.46 206

v1192		97.81 267	97.44 285	98.91 220	98.88 341	98.68 203	99.51 168	99.34 266	96.18 347	99.20 218	99.34 309	94.03 266	99.36 307	95.32 361	95.18 355	98.69 303

EI-MVSNet		98.67 170	98.67 153	98.68 257	99.35 238	97.97 254	99.50 175	99.38 245	96.93 295	99.20 218	99.83 78	97.87 110	99.36 307	98.38 193	97.56 283	98.71 294

MVSTER		98.49 177	98.32 186	99.00 203	99.35 238	99.02 160	99.54 149	99.38 245	97.41 249	99.20 218	99.73 159	93.86 274	99.36 307	98.87 122	97.56 283	98.62 336

gg-mvs-nofinetune		96.17 350	95.32 362	98.73 250	98.79 353	98.14 245	99.38 243	94.09 429	91.07 410	98.07 354	91.04 427	89.62 360	99.35 310	96.75 322	99.09 191	98.68 308

pm-mvs1		97.68 291	97.28 309	98.88 227	99.06 315	98.62 210	99.50 175	99.45 209	96.32 336	97.87 361	99.79 126	92.47 309	99.35 310	97.54 273	93.54 384	98.67 315

OurMVSNet-221017-0		97.88 250	97.77 241	98.19 312	98.71 369	96.53 333	99.88 4	99.00 339	97.79 200	98.78 293	99.94 6	91.68 328	99.35 310	97.21 295	96.99 313	98.69 303

EGC-MVSNET		82.80 392	77.86 398	97.62 354	97.91 395	96.12 348	99.33 260	99.28 297	8.40 435	25.05 436	99.27 327	84.11 405	99.33 313	89.20 409	98.22 248	97.42 409

pmmvs6		96.53 342	96.09 347	97.82 344	98.69 371	95.47 363	99.37 245	99.47 189	93.46 395	97.41 370	99.78 133	87.06 388	99.33 313	96.92 317	92.70 394	98.65 325

V42		98.06 219	97.79 236	98.86 234	98.98 330	98.84 189	99.69 60	99.34 266	96.53 322	99.30 191	99.37 299	94.67 238	99.32 315	97.57 270	94.66 365	98.42 365

lessismore_v0				97.79 346	98.69 371	95.44 366		94.75 427		95.71 397	99.87 52	88.69 369	99.32 315	95.89 345	94.93 362	98.62 336

OpenMVS_ROB	92.34 20	94.38 372	93.70 378	96.41 382	97.38 404	93.17 401	99.06 332	98.75 374	86.58 418	94.84 404	98.26 397	81.53 415	99.32 315	89.01 410	97.87 267	96.76 412

v8		97.95 241	97.63 260	98.93 214	98.95 334	98.81 195	99.80 25	99.41 228	96.03 359	99.10 237	99.42 282	94.92 219	99.30 318	96.94 314	94.08 377	98.66 323

v1921920		97.80 269	97.45 280	98.84 238	98.80 352	98.53 218	99.52 159	99.34 266	96.15 351	99.24 207	99.47 271	93.98 268	99.29 319	95.40 359	95.13 357	98.69 303

anonymousdsp		98.44 181	98.28 189	98.94 212	98.50 386	98.96 171	99.77 34	99.50 146	97.07 280	98.87 279	99.77 141	94.76 231	99.28 320	98.66 156	97.60 279	98.57 351

MVSFormer		99.17 92	99.12 85	99.29 168	99.51 183	98.94 177	99.88 4	99.46 198	97.55 229	99.80 53	99.65 198	97.39 121	99.28 320	99.03 100	99.85 80	99.65 139

test_djsdf		98.67 170	98.57 170	98.98 205	98.70 370	98.91 181	99.88 4	99.46 198	97.55 229	99.22 212	99.88 43	95.73 188	99.28 320	99.03 100	97.62 278	98.75 286

SSC-MVS3.2		97.34 319	97.15 316	97.93 333	99.02 321	95.76 355	99.48 191	99.58 67	97.62 221	99.09 240	99.53 248	87.95 380	99.27 323	96.42 335	95.66 344	98.75 286

cascas		97.69 288	97.43 289	98.48 277	98.60 380	97.30 286	98.18 414	99.39 237	92.96 399	98.41 332	98.78 378	93.77 277	99.27 323	98.16 214	98.61 221	98.86 273

v144192		97.92 245	97.60 263	98.87 231	98.83 351	98.65 206	99.55 144	99.34 266	96.20 345	99.32 187	99.40 290	94.36 253	99.26 325	96.37 338	95.03 359	98.70 299

dmvs_re		98.08 217	98.16 194	97.85 339	99.55 170	94.67 382	99.70 56	98.92 349	98.15 149	99.06 248	99.35 305	93.67 280	99.25 326	97.77 249	97.25 305	99.64 146

v2v482		98.06 219	97.77 241	98.92 216	98.90 339	98.82 193	99.57 124	99.36 254	96.65 310	99.19 221	99.35 305	94.20 258	99.25 326	97.72 256	94.97 360	98.69 303

v1240		97.69 288	97.32 304	98.79 246	98.85 348	98.43 232	99.48 191	99.36 254	96.11 354	99.27 200	99.36 302	93.76 278	99.24 328	94.46 373	95.23 354	98.70 299

WBMVS		97.74 279	97.50 272	98.46 283	99.24 270	97.43 282	99.21 304	99.42 225	97.45 242	98.96 265	99.41 286	88.83 366	99.23 329	98.94 110	96.02 330	98.71 294

v1144		97.98 236	97.69 252	98.85 237	98.87 344	98.66 205	99.54 149	99.35 261	96.27 340	99.23 211	99.35 305	94.67 238	99.23 329	96.73 323	95.16 356	98.68 308

v10		97.85 255	97.52 269	98.86 234	98.99 327	98.67 204	99.75 42	99.41 228	95.70 363	98.98 261	99.41 286	94.75 232	99.23 329	96.01 344	94.63 366	98.67 315

WR-MVS_H		98.13 211	97.87 231	98.90 222	99.02 321	98.84 189	99.70 56	99.59 63	97.27 260	98.40 333	99.19 337	95.53 194	99.23 329	98.34 199	93.78 382	98.61 345

miper_enhance_ethall		98.16 208	98.08 206	98.41 291	98.96 333	97.72 270	98.45 402	99.32 283	96.95 292	98.97 263	99.17 338	97.06 137	99.22 333	97.86 238	95.99 333	98.29 374

GG-mvs-BLEND				98.45 285	98.55 384	98.16 243	99.43 215	93.68 430		97.23 376	98.46 388	89.30 361	99.22 333	95.43 358	98.22 248	97.98 396

FC-MVSNet-test		98.75 163	98.62 163	99.15 189	99.08 312	99.45 104	99.86 11	99.60 57	98.23 139	98.70 305	99.82 87	96.80 145	99.22 333	99.07 96	96.38 322	98.79 277

UniMVSNet_NR-MVSNet		98.22 200	97.97 218	98.96 208	98.92 337	98.98 164	99.48 191	99.53 107	97.76 204	98.71 299	99.46 275	96.43 163	99.22 333	98.57 173	92.87 392	98.69 303

DU-MVS		98.08 217	97.79 236	98.96 208	98.87 344	98.98 164	99.41 226	99.45 209	97.87 188	98.71 299	99.50 259	94.82 223	99.22 333	98.57 173	92.87 392	98.68 308

cl____		98.01 232	97.84 234	98.55 271	99.25 268	97.97 254	98.71 385	99.34 266	96.47 329	98.59 323	99.54 244	95.65 191	99.21 338	97.21 295	95.77 339	98.46 362

WR-MVS		98.06 219	97.73 248	99.06 195	98.86 347	99.25 131	99.19 306	99.35 261	97.30 258	98.66 308	99.43 280	93.94 269	99.21 338	98.58 170	94.28 372	98.71 294

test_0402		96.64 340	96.24 342	97.85 339	98.85 348	96.43 337	99.44 210	99.26 301	93.52 393	96.98 383	99.52 252	88.52 374	99.20 340	92.58 398	97.50 290	97.93 399

SixPastTwentyTwo		97.50 307	97.33 303	98.03 322	98.65 374	96.23 345	99.77 34	98.68 386	97.14 271	97.90 359	99.93 10	90.45 347	99.18 341	97.00 308	96.43 321	98.67 315

cl22		97.85 255	97.64 259	98.48 277	99.09 309	97.87 262	98.60 395	99.33 273	97.11 277	98.87 279	99.22 333	92.38 314	99.17 342	98.21 208	95.99 333	98.42 365

WB-MVSnew		97.65 296	97.65 256	97.63 353	98.78 356	97.62 276	99.13 316	98.33 396	97.36 253	99.07 243	98.94 365	95.64 192	99.15 343	92.95 392	98.68 219	96.12 419

IterMVS-SCA-FT		97.82 265	97.75 246	98.06 321	99.57 162	96.36 339	99.02 342	99.49 156	97.18 268	98.71 299	99.72 163	92.72 298	99.14 344	97.44 283	95.86 338	98.67 315

pmmvs5		97.52 304	97.30 306	98.16 314	98.57 383	96.73 323	99.27 282	98.90 356	96.14 352	98.37 335	99.53 248	91.54 334	99.14 344	97.51 275	95.87 337	98.63 334

v148		97.79 271	97.55 265	98.50 274	98.74 364	97.72 270	99.54 149	99.33 273	96.26 341	98.90 273	99.51 256	94.68 237	99.14 344	97.83 242	93.15 389	98.63 334

miper_ehance_all_eth		98.18 206	98.10 202	98.41 291	99.23 272	97.72 270	98.72 384	99.31 287	96.60 318	98.88 276	99.29 322	97.29 128	99.13 347	97.60 264	95.99 333	98.38 370

NR-MVSNet		97.97 239	97.61 262	99.02 200	98.87 344	99.26 129	99.47 199	99.42 225	97.63 219	97.08 381	99.50 259	95.07 212	99.13 347	97.86 238	93.59 383	98.68 308

IterMVS		97.83 262	97.77 241	98.02 324	99.58 160	96.27 343	99.02 342	99.48 168	97.22 266	98.71 299	99.70 168	92.75 295	99.13 347	97.46 281	96.00 332	98.67 315
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 373	94.90 365	91.84 398	97.24 408	80.01 428	98.52 399	99.48 168	89.01 415	91.99 415	99.67 191	85.67 395	99.13 347	95.44 357	97.03 312	96.39 416
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 224	97.96 219	98.33 298	99.26 264	97.38 284	98.56 398	99.31 287	96.65 310	98.88 276	99.52 252	96.58 154	99.12 351	97.39 286	95.53 349	98.47 359

pmmvs4		98.13 211	97.90 226	98.81 243	98.61 379	98.87 184	98.99 350	99.21 312	96.44 330	99.06 248	99.58 228	95.90 182	99.11 352	97.18 301	96.11 329	98.46 362

TransMVSNet (Re)		97.15 328	96.58 334	98.86 234	99.12 301	98.85 188	99.49 186	98.91 354	95.48 366	97.16 379	99.80 114	93.38 282	99.11 352	94.16 379	91.73 398	98.62 336

ambc				93.06 396	92.68 427	82.36 421	98.47 401	98.73 383		95.09 402	97.41 410	55.55 428	99.10 354	96.42 335	91.32 399	97.71 402

Baseline_NR-MVSNet		97.76 273	97.45 280	98.68 257	99.09 309	98.29 237	99.41 226	98.85 363	95.65 364	98.63 317	99.67 191	94.82 223	99.10 354	98.07 224	92.89 391	98.64 327

test_vis3_rt		87.04 388	85.81 391	90.73 402	93.99 426	81.96 423	99.76 37	90.23 437	92.81 401	81.35 425	91.56 425	40.06 434	99.07 356	94.27 376	88.23 412	91.15 425

CP-MVSNet		98.09 215	97.78 239	99.01 201	98.97 332	99.24 132	99.67 69	99.46 198	97.25 262	98.48 330	99.64 204	93.79 276	99.06 357	98.63 160	94.10 376	98.74 290

PS-CasMVS		97.93 242	97.59 264	98.95 210	98.99 327	99.06 156	99.68 66	99.52 112	97.13 272	98.31 338	99.68 185	92.44 313	99.05 358	98.51 181	94.08 377	98.75 286

K. test v3		97.10 330	96.79 330	98.01 325	98.72 367	96.33 340	99.87 8	97.05 414	97.59 223	96.16 393	99.80 114	88.71 368	99.04 359	96.69 326	96.55 319	98.65 325

new_pmnet		96.38 346	96.03 348	97.41 360	98.13 394	95.16 374	99.05 334	99.20 313	93.94 388	97.39 373	98.79 377	91.61 333	99.04 359	90.43 405	95.77 339	98.05 389

DIV-MVS_self_test		98.01 232	97.85 233	98.48 277	99.24 270	97.95 258	98.71 385	99.35 261	96.50 323	98.60 322	99.54 244	95.72 189	99.03 361	97.21 295	95.77 339	98.46 362

IterMVS-LS		98.46 180	98.42 179	98.58 265	99.59 158	98.00 252	99.37 245	99.43 223	96.94 294	99.07 243	99.59 224	97.87 110	99.03 361	98.32 202	95.62 345	98.71 294
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 296	97.68 253	97.55 357	98.62 377	94.97 376	98.84 372	99.30 291	96.83 301	98.19 347	99.34 309	97.01 140	99.02 363	95.00 367	96.01 331	98.64 327

Patchmtry		97.75 277	97.40 292	98.81 243	99.10 306	98.87 184	99.11 325	99.33 273	94.83 379	98.81 288	99.38 296	94.33 254	99.02 363	96.10 340	95.57 347	98.53 353

N_pmnet		94.95 367	95.83 353	92.31 397	98.47 387	79.33 429	99.12 319	92.81 435	93.87 389	97.68 366	99.13 343	93.87 273	99.01 365	91.38 402	96.19 327	98.59 349

CR-MVSNet		98.17 207	97.93 224	98.87 231	99.18 285	98.49 226	99.22 302	99.33 273	96.96 290	99.56 131	99.38 296	94.33 254	99.00 366	94.83 370	98.58 224	99.14 244

c3_l		98.12 213	98.04 211	98.38 295	99.30 252	97.69 274	98.81 375	99.33 273	96.67 308	98.83 285	99.34 309	97.11 133	98.99 367	97.58 266	95.34 352	98.48 357

test0.0.03 1		97.71 286	97.42 290	98.56 269	98.41 390	97.82 265	98.78 378	98.63 389	97.34 254	98.05 355	98.98 361	94.45 251	98.98 368	95.04 366	97.15 310	98.89 272

PatchT		97.03 332	96.44 338	98.79 246	98.99 327	98.34 236	99.16 310	99.07 330	92.13 404	99.52 140	97.31 414	94.54 247	98.98 368	88.54 412	98.73 217	99.03 260

GBi-Net		97.68 291	97.48 274	98.29 303	99.51 183	97.26 290	99.43 215	99.48 168	96.49 324	99.07 243	99.32 317	90.26 349	98.98 368	97.10 303	96.65 315	98.62 336

test1		97.68 291	97.48 274	98.29 303	99.51 183	97.26 290	99.43 215	99.48 168	96.49 324	99.07 243	99.32 317	90.26 349	98.98 368	97.10 303	96.65 315	98.62 336

FMVSNet3		98.03 227	97.76 245	98.84 238	99.39 229	98.98 164	99.40 234	99.38 245	96.67 308	99.07 243	99.28 324	92.93 290	98.98 368	97.10 303	96.65 315	98.56 352

FMVSNet2		97.72 283	97.36 295	98.80 245	99.51 183	98.84 189	99.45 204	99.42 225	96.49 324	98.86 283	99.29 322	90.26 349	98.98 368	96.44 334	96.56 318	98.58 350

FMVSNet1		96.84 336	96.36 340	98.29 303	99.32 250	97.26 290	99.43 215	99.48 168	95.11 371	98.55 325	99.32 317	83.95 406	98.98 368	95.81 347	96.26 326	98.62 336

ppachtmachnet_test		97.49 312	97.45 280	97.61 355	98.62 377	95.24 370	98.80 376	99.46 198	96.11 354	98.22 345	99.62 215	96.45 161	98.97 375	93.77 381	95.97 336	98.61 345

TranMVSNet+NR-MVSNet		97.93 242	97.66 255	98.76 249	98.78 356	98.62 210	99.65 81	99.49 156	97.76 204	98.49 329	99.60 222	94.23 257	98.97 375	98.00 228	92.90 390	98.70 299

MVStest1		96.08 353	95.48 358	97.89 337	98.93 335	96.70 324	99.56 130	99.35 261	92.69 402	91.81 416	99.46 275	89.90 355	98.96 377	95.00 367	92.61 395	98.00 394

test_method		91.10 383	91.36 385	90.31 403	95.85 416	73.72 436	94.89 424	99.25 303	68.39 427	95.82 396	99.02 355	80.50 417	98.95 378	93.64 384	94.89 364	98.25 377

ADS-MVSNet2		98.02 229	98.07 209	97.87 338	99.33 243	95.19 372	99.23 298	99.08 327	96.24 342	99.10 237	99.67 191	94.11 262	98.93 379	96.81 320	99.05 194	99.48 195

ET-MVSNet_ETH3D		96.49 343	95.64 357	99.05 197	99.53 174	98.82 193	98.84 372	97.51 412	97.63 219	84.77 421	99.21 336	92.09 318	98.91 380	98.98 105	92.21 397	99.41 216

miper_lstm_enhance		98.00 234	97.91 225	98.28 307	99.34 242	97.43 282	98.88 368	99.36 254	96.48 327	98.80 290	99.55 239	95.98 175	98.91 380	97.27 292	95.50 350	98.51 355

MonoMVSNet		98.38 189	98.47 177	98.12 319	98.59 382	96.19 347	99.72 52	98.79 371	97.89 186	99.44 156	99.52 252	96.13 170	98.90 382	98.64 158	97.54 285	99.28 233

PEN-MVS		97.76 273	97.44 285	98.72 252	98.77 361	98.54 217	99.78 32	99.51 126	97.06 282	98.29 341	99.64 204	92.63 304	98.89 383	98.09 217	93.16 388	98.72 292

testing3		97.28 322	96.76 331	98.82 240	99.37 234	98.07 249	99.45 204	99.36 254	97.56 228	97.89 360	98.95 364	83.70 407	98.82 384	96.03 342	98.56 227	99.58 166

testgi		97.65 296	97.50 272	98.13 318	99.36 237	96.45 336	99.42 222	99.48 168	97.76 204	97.87 361	99.45 277	91.09 341	98.81 385	94.53 372	98.52 230	99.13 246

testf1		90.42 386	90.68 387	89.65 406	97.78 398	73.97 434	99.13 316	98.81 368	89.62 412	91.80 417	98.93 366	62.23 426	98.80 386	86.61 420	91.17 400	96.19 417

APD_test2		90.42 386	90.68 387	89.65 406	97.78 398	73.97 434	99.13 316	98.81 368	89.62 412	91.80 417	98.93 366	62.23 426	98.80 386	86.61 420	91.17 400	96.19 417

MIMVSNet		97.73 281	97.45 280	98.57 266	99.45 212	97.50 280	99.02 342	98.98 341	96.11 354	99.41 165	99.14 342	90.28 348	98.74 388	95.74 349	98.93 202	99.47 201

LCM-MVSNet-Re		97.83 262	98.15 196	96.87 376	99.30 252	92.25 406	99.59 109	98.26 397	97.43 246	96.20 392	99.13 343	96.27 167	98.73 389	98.17 213	98.99 199	99.64 146

Syy-MVS		97.09 331	97.14 317	96.95 373	99.00 324	92.73 404	99.29 272	99.39 237	97.06 282	97.41 370	98.15 400	93.92 271	98.68 390	91.71 400	98.34 237	99.45 209

myMVS_eth3d		96.89 334	96.37 339	98.43 290	99.00 324	97.16 294	99.29 272	99.39 237	97.06 282	97.41 370	98.15 400	83.46 408	98.68 390	95.27 362	98.34 237	99.45 209

DTE-MVSNet		97.51 306	97.19 315	98.46 283	98.63 376	98.13 246	99.84 12	99.48 168	96.68 307	97.97 358	99.67 191	92.92 291	98.56 392	96.88 319	92.60 396	98.70 299

PC_three_1452									98.18 147	99.84 41	99.70 168	99.31 3	98.52 393	98.30 204	99.80 108	99.81 68

mvsany_test3		93.77 375	93.45 379	94.74 388	95.78 417	88.01 414	99.64 84	98.25 398	98.28 130	94.31 405	97.97 407	68.89 422	98.51 394	97.50 276	90.37 405	97.71 402

UnsupCasMVSNet_bld		93.53 376	92.51 382	96.58 381	97.38 404	93.82 392	98.24 411	99.48 168	91.10 409	93.10 410	96.66 416	74.89 420	98.37 395	94.03 380	87.71 413	97.56 407

Anonymous20240521		96.20 349	95.89 352	97.13 367	97.72 401	94.96 377	99.79 31	99.29 295	93.01 398	97.20 378	99.03 353	89.69 358	98.36 396	91.16 403	96.13 328	98.07 387

test_f		91.90 382	91.26 386	93.84 391	95.52 421	85.92 416	99.69 60	98.53 394	95.31 368	93.87 407	96.37 418	55.33 429	98.27 397	95.70 350	90.98 403	97.32 410

MDA-MVSNet_test_wron		95.45 360	94.60 367	98.01 325	98.16 393	97.21 293	99.11 325	99.24 306	93.49 394	80.73 427	98.98 361	93.02 288	98.18 398	94.22 378	94.45 369	98.64 327

UnsupCasMVSNet_eth		96.44 344	96.12 345	97.40 361	98.65 374	95.65 356	99.36 250	99.51 126	97.13 272	96.04 395	98.99 359	88.40 375	98.17 399	96.71 324	90.27 406	98.40 368

KD-MVS_2432*1600		94.62 368	93.72 376	97.31 362	97.19 410	95.82 353	98.34 406	99.20 313	95.00 375	97.57 367	98.35 393	87.95 380	98.10 400	92.87 394	77.00 425	98.01 391

miper_refine_blended		94.62 368	93.72 376	97.31 362	97.19 410	95.82 353	98.34 406	99.20 313	95.00 375	97.57 367	98.35 393	87.95 380	98.10 400	92.87 394	77.00 425	98.01 391

YYNet1		95.36 362	94.51 369	97.92 334	97.89 396	97.10 297	99.10 327	99.23 307	93.26 397	80.77 426	99.04 352	92.81 294	98.02 402	94.30 374	94.18 374	98.64 327

EU-MVSNet		97.98 236	98.03 212	97.81 345	98.72 367	96.65 329	99.66 75	99.66 28	98.09 160	98.35 336	99.82 87	95.25 206	98.01 403	97.41 285	95.30 353	98.78 278

Gipuma		90.99 384	90.15 389	93.51 392	98.73 365	90.12 412	93.98 425	99.45 209	79.32 423	92.28 413	94.91 420	69.61 421	97.98 404	87.42 416	95.67 343	92.45 423
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 363	94.73 366	97.15 365	95.53 420	95.94 351	99.35 255	99.10 324	95.13 369	93.55 408	97.54 409	88.15 379	97.91 405	94.58 371	89.69 409	97.61 405

PM-MVS		92.96 379	92.23 383	95.14 387	95.61 418	89.98 413	99.37 245	98.21 400	94.80 380	95.04 403	97.69 408	65.06 423	97.90 406	94.30 374	89.98 408	97.54 408

MDA-MVSNet-bldmvs		94.96 366	93.98 373	97.92 334	98.24 392	97.27 288	99.15 313	99.33 273	93.80 390	80.09 428	99.03 353	88.31 376	97.86 407	93.49 386	94.36 371	98.62 336

Patchmatch-RL test		95.84 356	95.81 354	95.95 385	95.61 418	90.57 411	98.24 411	98.39 395	95.10 373	95.20 400	98.67 381	94.78 227	97.77 408	96.28 339	90.02 407	99.51 189

Anonymous20231206		96.22 347	96.03 348	96.79 378	97.31 407	94.14 390	99.63 90	99.08 327	96.17 348	97.04 382	99.06 350	93.94 269	97.76 409	86.96 418	95.06 358	98.47 359

SD-MVS		99.41 52	99.52 12	99.05 197	99.74 89	99.68 55	99.46 202	99.52 112	99.11 36	99.88 30	99.91 23	99.43 1	97.70 410	98.72 147	99.93 27	99.77 89
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		97.25 324	97.35 297	96.95 373	97.84 397	93.61 398	99.57 124	96.63 420	96.13 353	98.87 279	98.61 384	94.59 242	97.70 410	95.08 365	98.86 208	99.55 172

dongtai		93.26 377	92.93 381	94.25 389	99.39 229	85.68 417	97.68 420	93.27 431	92.87 400	96.85 386	99.39 294	82.33 413	97.48 412	76.78 425	97.80 270	99.58 166

pmmvs3		94.09 374	93.25 380	96.60 380	94.76 425	94.49 384	98.92 364	98.18 402	89.66 411	96.48 389	98.06 406	86.28 392	97.33 413	89.68 408	87.20 414	97.97 397

KD-MVS_self_test		95.00 365	94.34 370	96.96 372	97.07 412	95.39 367	99.56 130	99.44 217	95.11 371	97.13 380	97.32 413	91.86 323	97.27 414	90.35 406	81.23 422	98.23 379

FMVSNet5		96.43 345	96.19 344	97.15 365	99.11 303	95.89 352	99.32 262	99.52 112	94.47 386	98.34 337	99.07 348	87.54 385	97.07 415	92.61 397	95.72 342	98.47 359

new-patchmatchnet		94.48 371	94.08 372	95.67 386	95.08 423	92.41 405	99.18 308	99.28 297	94.55 385	93.49 409	97.37 412	87.86 383	97.01 416	91.57 401	88.36 411	97.61 405

LCM-MVSNet		86.80 390	85.22 394	91.53 400	87.81 432	80.96 426	98.23 413	98.99 340	71.05 425	90.13 420	96.51 417	48.45 433	96.88 417	90.51 404	85.30 416	96.76 412

CL-MVSNet_self_test		94.49 370	93.97 374	96.08 384	96.16 415	93.67 397	98.33 408	99.38 245	95.13 369	97.33 374	98.15 400	92.69 302	96.57 418	88.67 411	79.87 423	97.99 395

MIMVSNet1		95.51 359	95.04 364	96.92 375	97.38 404	95.60 357	99.52 159	99.50 146	93.65 392	96.97 384	99.17 338	85.28 400	96.56 419	88.36 413	95.55 348	98.60 348

test20.03		96.12 351	95.96 350	96.63 379	97.44 403	95.45 364	99.51 168	99.38 245	96.55 321	96.16 393	99.25 330	93.76 278	96.17 420	87.35 417	94.22 373	98.27 375

tmp_tt		82.80 392	81.52 395	86.66 408	66.61 438	68.44 437	92.79 427	97.92 404	68.96 426	80.04 429	99.85 63	85.77 394	96.15 421	97.86 238	43.89 431	95.39 421

test_fmvs3		92.10 381	91.77 384	93.08 395	96.19 414	86.25 415	99.82 16	98.62 390	96.65 310	95.19 401	96.90 415	55.05 430	95.93 422	96.63 331	90.92 404	97.06 411

kuosan		90.92 385	90.11 390	93.34 393	98.78 356	85.59 418	98.15 415	93.16 433	89.37 414	92.07 414	98.38 392	81.48 416	95.19 423	62.54 432	97.04 311	99.25 238

dmvs_testset		95.02 364	96.12 345	91.72 399	99.10 306	80.43 427	99.58 117	97.87 406	97.47 238	95.22 399	98.82 373	93.99 267	95.18 424	88.09 414	94.91 363	99.56 171

PMMVS2		86.87 389	85.37 393	91.35 401	90.21 430	83.80 420	98.89 367	97.45 413	83.13 422	91.67 419	95.03 419	48.49 432	94.70 425	85.86 422	77.62 424	95.54 420

PMVS	70.75 22	75.98 398	74.97 399	79.01 414	70.98 437	55.18 439	93.37 426	98.21 400	65.08 431	61.78 432	93.83 422	21.74 439	92.53 426	78.59 424	91.12 402	89.34 427
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 391	85.65 392	82.75 412	86.77 433	63.39 438	98.35 405	98.92 349	74.11 424	83.39 423	98.98 361	50.85 431	92.40 427	84.54 423	94.97 360	92.46 422

WB-MVS		93.10 378	94.10 371	90.12 404	95.51 422	81.88 424	99.73 50	99.27 300	95.05 374	93.09 411	98.91 370	94.70 236	91.89 428	76.62 426	94.02 379	96.58 414

SSC-MVS		92.73 380	93.73 375	89.72 405	95.02 424	81.38 425	99.76 37	99.23 307	94.87 378	92.80 412	98.93 366	94.71 235	91.37 429	74.49 428	93.80 381	96.42 415

MVE	76.82 21	76.91 397	74.31 401	84.70 409	85.38 435	76.05 433	96.88 423	93.17 432	67.39 428	71.28 430	89.01 429	21.66 440	87.69 430	71.74 429	72.29 427	90.35 426
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 394	79.88 396	82.81 411	90.75 429	76.38 432	97.69 419	95.76 424	66.44 429	83.52 422	92.25 424	62.54 425	87.16 431	68.53 430	61.40 428	84.89 429

EMVS		80.02 395	79.22 397	82.43 413	91.19 428	76.40 431	97.55 422	92.49 436	66.36 430	83.01 424	91.27 426	64.63 424	85.79 432	65.82 431	60.65 429	85.08 428

ANet_high		77.30 396	74.86 400	84.62 410	75.88 436	77.61 430	97.63 421	93.15 434	88.81 416	64.27 431	89.29 428	36.51 435	83.93 433	75.89 427	52.31 430	92.33 424

wuyk23d		40.18 399	41.29 404	36.84 415	86.18 434	49.12 440	79.73 428	22.81 440	27.64 432	25.46 435	28.45 435	21.98 438	48.89 434	55.80 433	23.56 434	12.51 432

test123		39.01 401	42.50 403	28.53 416	39.17 439	20.91 441	98.75 381	19.17 441	19.83 434	38.57 433	66.67 431	33.16 436	15.42 435	37.50 435	29.66 433	49.26 430

testmvs		39.17 400	43.78 402	25.37 417	36.04 440	16.84 442	98.36 404	26.56 439	20.06 433	38.51 434	67.32 430	29.64 437	15.30 436	37.59 434	39.90 432	43.98 431

mmdepth		0.02 406	0.03 409	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.27 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

monomultidepth		0.02 406	0.03 409	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.27 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

test_blank		0.13 405	0.17 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	1.57 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet_test		0.02 406	0.03 409	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.27 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

DCPMVS		0.02 406	0.03 409	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.27 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

cdsmvs_eth3d_5k		24.64 402	32.85 405	0.00 418	0.00 441	0.00 443	0.00 429	99.51 126	0.00 436	0.00 437	99.56 236	96.58 154	0.00 437	0.00 436	0.00 435	0.00 433

pcd_1.5k_mvsjas		8.27 404	11.03 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.27 437	99.01 18	0.00 437	0.00 436	0.00 435	0.00 433

sosnet-low-res		0.02 406	0.03 409	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.27 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet		0.02 406	0.03 409	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.27 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uncertanet		0.02 406	0.03 409	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.27 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

Regformer		0.02 406	0.03 409	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.27 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

ab-mvs-re		8.30 403	11.06 406	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	99.58 228	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet		0.02 406	0.03 409	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.27 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

WAC-MVS						97.16 294								95.47 356

FOURS1					99.91 1	99.93 1	99.87 8	99.56 77	99.10 37	99.81 49

test_one_0601					99.81 47	99.88 8		99.49 156	98.97 61	99.65 105	99.81 101	99.09 14

eth-test2					0.00 441

eth-test					0.00 441

RE-MVS-def			99.34 43		99.76 71	99.82 25	99.63 90	99.52 112	98.38 118	99.76 70	99.82 87	98.75 58		98.61 164	99.81 104	99.77 89

IU-MVS					99.84 32	99.88 8		99.32 283	98.30 129	99.84 41				98.86 127	99.85 80	99.89 23

save fliter					99.76 71	99.59 78	99.14 315	99.40 234	99.00 53

test0726					99.85 26	99.89 4	99.62 95	99.50 146	99.10 37	99.86 39	99.82 87	98.94 32

GSMVS																99.52 181

test_part2					99.81 47	99.83 19				99.77 64

sam_mvs1												94.86 222				99.52 181

sam_mvs												94.72 234

MTGPA								99.47 189

MTMP							99.54 149	98.88 359

test9_res														97.49 277	99.72 131	99.75 95

agg_prior2														97.21 295	99.73 130	99.75 95

test_prior4						99.56 84	98.99 350

test_prior2							98.96 357		98.34 124	99.01 254	99.52 252	98.68 67		97.96 230	99.74 128

新几何2							99.01 347

旧先验1					99.74 89	99.59 78		99.54 94			99.69 178	98.47 83			99.68 139	99.73 104

原ACMM2							98.95 360

test222					99.75 81	99.49 98	98.91 366	99.49 156	96.42 332	99.34 185	99.65 198	98.28 96			99.69 136	99.72 112

segment_acmp												98.96 25

testdata1							98.85 371		98.32 127

plane_prior7					99.29 256	97.03 307

plane_prior6					99.27 261	96.98 311						92.71 300

plane_prior4											99.61 219

plane_prior3						97.00 309			98.69 90	99.11 234

plane_prior2							99.39 238		98.97 61

plane_prior1					99.26 264

plane_prior						96.97 312	99.21 304		98.45 111						97.60 279

n2								0.00 442

nn								0.00 442

door-mid								98.05 403

test11								99.35 261

door								97.92 404

HQP5-MVS						96.83 319

HQP-NCC					99.19 282		98.98 353		98.24 136	98.66 308

ACMP_Plane					99.19 282		98.98 353		98.24 136	98.66 308

BP-MVS														97.19 299

HQP3-MVS								99.39 237							97.58 281

HQP2-MVS												92.47 309

NP-MVS					99.23 272	96.92 315					99.40 290

MDTV_nov1_ep13_2view						95.18 373	99.35 255		96.84 299	99.58 127		95.19 208		97.82 243		99.46 206

ACMMP++_ref															97.19 308

ACMMP++															97.43 299

Test By Simon												98.75 58

High-resolution multi-view benchmark