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_fmvsm_n_1920		97.55 14	97.89 3	96.53 100	98.41 80	91.73 125	98.01 61	99.02 1	96.37 11	99.30 5	98.92 21	92.39 41	99.79 40	99.16 12	99.46 42	98.08 212

PGM-MVS		96.81 53	96.53 64	97.65 43	99.35 22	93.53 61	97.65 122	98.98 2	92.22 163	97.14 70	98.44 58	91.17 68	99.85 18	94.35 148	99.46 42	99.57 32

MVS_111021_HR		96.68 64	96.58 63	96.99 80	98.46 75	92.31 106	96.20 287	98.90 3	94.30 84	95.86 128	97.74 129	92.33 42	99.38 130	96.04 90	99.42 52	99.28 73

test_fmvsmconf_n		97.49 18	97.56 13	97.29 60	97.44 159	92.37 103	97.91 80	98.88 4	95.83 17	98.92 21	99.05 12	91.45 58	99.80 35	99.12 14	99.46 42	99.69 13

lecture		97.58 13	97.63 10	97.43 54	99.37 16	92.93 82	98.86 7	98.85 5	95.27 32	98.65 31	98.90 23	91.97 49	99.80 35	97.63 36	99.21 77	99.57 32

ACMMP		96.27 81	95.93 84	97.28 62	99.24 30	92.62 94	98.25 36	98.81 6	92.99 134	94.56 168	98.39 62	88.96 98	99.85 18	94.57 143	97.63 157	99.36 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
MVS_111021_LR		96.24 82	96.19 80	96.39 118	98.23 99	91.35 147	96.24 285	98.79 7	93.99 91	95.80 130	97.65 139	89.92 88	99.24 143	95.87 94	99.20 82	98.58 157

patch_mono-2		96.83 52	97.44 21	95.01 210	99.05 41	85.39 348	96.98 206	98.77 8	94.70 64	97.99 45	98.66 41	93.61 19	99.91 1	97.67 35	99.50 36	99.72 12

fmvsm_s_conf0.5_n		96.85 49	97.13 26	96.04 142	98.07 114	90.28 195	97.97 72	98.76 9	94.93 46	98.84 26	99.06 11	88.80 102	99.65 73	99.06 16	98.63 117	98.18 198

fmvsm_l_conf0.5_n		97.65 7	97.75 7	97.34 57	98.21 100	92.75 88	97.83 92	98.73 10	95.04 43	99.30 5	98.84 34	93.34 22	99.78 43	99.32 6	99.13 92	99.50 48

fmvsm_s_conf0.5_n_a		96.75 57	96.93 41	96.20 134	97.64 145	90.72 177	98.00 62	98.73 10	94.55 71	98.91 22	99.08 7	88.22 114	99.63 82	98.91 19	98.37 130	98.25 193

fmvsm_l_conf0.5_n_9		97.59 11	97.79 5	96.97 82	98.28 89	91.49 139	97.61 131	98.71 12	97.10 4	99.70 1	98.93 20	90.95 73	99.77 46	99.35 5	99.53 29	99.65 19

FC-MVSNet-test		93.94 168	93.57 160	95.04 208	95.48 300	91.45 144	98.12 51	98.71 12	93.37 116	90.23 280	96.70 206	87.66 124	97.85 331	91.49 211	90.39 320	95.83 306

UniMVSNet (Re)		93.31 195	92.55 208	95.61 178	95.39 306	93.34 67	97.39 165	98.71 12	93.14 129	90.10 289	94.83 308	87.71 123	98.03 304	91.67 209	83.99 394	95.46 325

fmvsm_l_conf0.5_n_a		97.63 9	97.76 6	97.26 64	98.25 94	92.59 96	97.81 97	98.68 15	94.93 46	99.24 8	98.87 29	93.52 20	99.79 40	99.32 6	99.21 77	99.40 62

FIs		94.09 159	93.70 156	95.27 197	95.70 289	92.03 118	98.10 52	98.68 15	93.36 118	90.39 277	96.70 206	87.63 127	97.94 322	92.25 189	90.50 319	95.84 305

WR-MVS_H		92.00 252	91.35 249	93.95 277	95.09 333	89.47 227	98.04 59	98.68 15	91.46 193	88.34 340	94.68 315	85.86 161	97.56 360	85.77 335	84.24 392	94.82 370

fmvsm_s_conf0.5_n_4		96.75 57	97.07 29	95.79 165	97.76 136	89.57 221	97.66 121	98.66 18	95.36 28	99.03 14	98.90 23	88.39 110	99.73 55	99.17 11	98.66 115	98.08 212

VPA-MVSNet		93.24 197	92.48 213	95.51 184	95.70 289	92.39 102	97.86 85	98.66 18	92.30 160	92.09 238	95.37 283	80.49 275	98.40 258	93.95 154	85.86 365	95.75 314

fmvsm_l_conf0.5_n_3		97.64 8	97.60 11	97.79 30	98.14 107	93.94 52	97.93 78	98.65 20	96.70 6	99.38 3	99.07 10	89.92 88	99.81 30	99.16 12	99.43 49	99.61 26

fmvsm_s_conf0.5_n_3		97.15 31	97.36 23	96.52 102	97.98 120	91.19 155	97.84 89	98.65 20	97.08 5	99.25 7	99.10 5	87.88 121	99.79 40	99.32 6	99.18 84	98.59 156

fmvsm_s_conf0.5_n_8		97.32 25	97.48 20	96.85 83	98.28 89	91.07 163	97.76 102	98.62 22	97.53 2	99.20 10	99.12 4	88.24 113	99.81 30	99.41 3	99.17 85	99.67 14

fmvsm_s_conf0.5_n_2		96.62 65	96.82 50	96.02 144	97.98 120	90.43 187	97.50 146	98.59 23	96.59 8	99.31 4	99.08 7	84.47 189	99.75 52	99.37 4	98.45 127	97.88 225

UniMVSNet_NR-MVSNet		93.37 193	92.67 202	95.47 190	95.34 312	92.83 85	97.17 189	98.58 24	92.98 139	90.13 285	95.80 259	88.37 112	97.85 331	91.71 206	83.93 395	95.73 316

CSCG		96.05 85	95.91 85	96.46 112	99.24 30	90.47 184	98.30 29	98.57 25	89.01 286	93.97 187	97.57 149	92.62 37	99.76 48	94.66 137	99.27 70	99.15 83

fmvsm_s_conf0.5_n_9		97.33 24	97.57 12	96.62 96	98.43 78	90.32 194	97.80 98	98.53 26	97.24 3	99.62 2	99.14 1	88.65 105	99.80 35	99.54 1	99.15 89	99.74 8

fmvsm_s_conf0.5_n_6		97.08 34	97.17 25	96.81 84	97.28 164	91.73 125	97.75 104	98.50 27	94.86 50	99.22 9	98.78 38	89.75 91	99.76 48	99.10 15	99.29 68	98.94 113

MSLP-MVS++		96.94 43	97.06 30	96.59 97	98.72 60	91.86 123	97.67 118	98.49 28	94.66 67	97.24 66	98.41 61	92.31 44	98.94 189	96.61 65	99.46 42	98.96 109

HyFIR lowres test		93.66 180	92.92 190	95.87 155	98.24 95	89.88 210	94.58 363	98.49 28	85.06 383	93.78 190	95.78 263	82.86 224	98.67 232	91.77 204	95.71 218	99.07 95

CHOSEN 1792x2688		94.15 154	93.51 166	96.06 140	98.27 91	89.38 232	95.18 349	98.48 30	85.60 373	93.76 191	97.11 181	83.15 214	99.61 84	91.33 214	98.72 113	99.19 79

fmvsm_s_conf0.5_n_7		96.45 72	96.80 52	95.37 193	97.29 163	88.38 265	97.23 183	98.47 31	95.14 37	98.43 36	99.09 6	87.58 128	99.72 59	98.80 23	99.21 77	98.02 216

fmvsm_s_conf0.5_n_5		97.00 40	96.97 38	97.09 75	97.58 155	92.56 97	97.68 117	98.47 31	94.02 89	98.90 23	98.89 26	88.94 99	99.78 43	99.18 10	99.03 101	98.93 117

PHI-MVS		96.77 55	96.46 71	97.71 41	98.40 81	94.07 48	98.21 43	98.45 33	89.86 258	97.11 72	98.01 98	92.52 39	99.69 67	96.03 91	99.53 29	99.36 68

fmvsm_s_conf0.1_n		96.58 68	96.77 55	96.01 147	96.67 217	90.25 196	97.91 80	98.38 34	94.48 75	98.84 26	99.14 1	88.06 116	99.62 83	98.82 21	98.60 119	98.15 202

PVSNet_BlendedMVS		94.06 160	93.92 150	94.47 244	98.27 91	89.46 229	96.73 234	98.36 35	90.17 250	94.36 173	95.24 291	88.02 117	99.58 92	93.44 167	90.72 315	94.36 390

PVSNet_Blended		94.87 131	94.56 129	95.81 162	98.27 91	89.46 229	95.47 331	98.36 35	88.84 295	94.36 173	96.09 248	88.02 117	99.58 92	93.44 167	98.18 139	98.40 178

3Dnovator	91.36 5	95.19 118	94.44 138	97.44 53	96.56 227	93.36 66	98.65 12	98.36 35	94.12 86	89.25 319	98.06 92	82.20 241	99.77 46	93.41 169	99.32 66	99.18 80

FOURS1					99.55 1	93.34 67	99.29 1	98.35 38	94.98 44	98.49 34

DPE-MVS		97.86 4	97.65 9	98.47 5	99.17 34	95.78 7	97.21 186	98.35 38	95.16 36	98.71 30	98.80 36	95.05 10	99.89 3	96.70 63	99.73 1	99.73 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_s_conf0.1_n_a		96.40 74	96.47 68	96.16 136	95.48 300	90.69 178	97.91 80	98.33 40	94.07 87	98.93 18	99.14 1	87.44 135	99.61 84	98.63 24	98.32 132	98.18 198

HFP-MVS		97.14 32	96.92 42	97.83 26	99.42 7	94.12 46	98.52 16	98.32 41	93.21 121	97.18 67	98.29 78	92.08 46	99.83 26	95.63 107	99.59 19	99.54 41

ACMMPR		97.07 36	96.84 46	97.79 30	99.44 6	93.88 53	98.52 16	98.31 42	93.21 121	97.15 69	98.33 72	91.35 62	99.86 9	95.63 107	99.59 19	99.62 23

test_fmvsmvis_n_1920		96.70 60	96.84 46	96.31 123	96.62 219	91.73 125	97.98 66	98.30 43	96.19 12	96.10 118	98.95 18	89.42 92	99.76 48	98.90 20	99.08 96	97.43 252

APDe-MVS		97.82 5	97.73 8	98.08 18	99.15 35	94.82 28	98.81 8	98.30 43	94.76 62	98.30 38	98.90 23	93.77 17	99.68 69	97.93 27	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test0726					99.45 3	95.36 13	98.31 28	98.29 45	94.92 48	98.99 16	98.92 21	95.08 8

MSP-MVS		97.59 11	97.54 14	97.73 38	99.40 11	93.77 57	98.53 15	98.29 45	95.55 25	98.56 33	97.81 123	93.90 15	99.65 73	96.62 64	99.21 77	99.77 2
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
DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 63	95.39 11	99.29 1	98.28 47	94.78 59	98.93 18	98.87 29	96.04 2	99.86 9	97.45 44	99.58 23	99.59 28

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 47					99.86 9	97.52 40	99.67 6	99.75 6

CP-MVS		97.02 38	96.81 51	97.64 45	99.33 23	93.54 60	98.80 9	98.28 47	92.99 134	96.45 105	98.30 77	91.90 50	99.85 18	95.61 109	99.68 4	99.54 41

test_fmvsmconf0.1_n		97.09 33	97.06 30	97.19 69	95.67 291	92.21 110	97.95 75	98.27 50	95.78 21	98.40 37	99.00 14	89.99 86	99.78 43	99.06 16	99.41 55	99.59 28

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 50	95.13 38	99.19 11	98.89 26	95.54 5	99.85 18	97.52 40	99.66 10	99.56 36

test_241102_TWO								98.27 50	95.13 38	98.93 18	98.89 26	94.99 11	99.85 18	97.52 40	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 50	95.09 41	99.19 11	98.81 35	95.54 5	99.65 73

SF-MVS		97.39 21	97.13 26	98.17 15	99.02 44	95.28 19	98.23 40	98.27 50	92.37 159	98.27 39	98.65 43	93.33 23	99.72 59	96.49 69	99.52 31	99.51 45

SteuartSystems-ACMMP		97.62 10	97.53 15	97.87 24	98.39 83	94.25 40	98.43 23	98.27 50	95.34 30	98.11 41	98.56 45	94.53 12	99.71 61	96.57 67	99.62 17	99.65 19
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 24	95.20 20		98.25 56	95.13 38	98.48 35	98.87 29	95.16 7

PVSNet_Blended_VisFu		95.27 110	94.91 117	96.38 119	98.20 101	90.86 171	97.27 177	98.25 56	90.21 249	94.18 180	97.27 170	87.48 134	99.73 55	93.53 164	97.77 155	98.55 159

region2R		97.07 36	96.84 46	97.77 34	99.46 2	93.79 55	98.52 16	98.24 58	93.19 124	97.14 70	98.34 69	91.59 57	99.87 7	95.46 113	99.59 19	99.64 21

PS-CasMVS		91.55 272	90.84 273	93.69 294	94.96 337	88.28 268	97.84 89	98.24 58	91.46 193	88.04 351	95.80 259	79.67 291	97.48 368	87.02 315	84.54 389	95.31 339

DU-MVS		92.90 215	92.04 224	95.49 187	94.95 338	92.83 85	97.16 190	98.24 58	93.02 133	90.13 285	95.71 266	83.47 206	97.85 331	91.71 206	83.93 395	95.78 310

9.14			96.75 56		98.93 52		97.73 108	98.23 61	91.28 202	97.88 49	98.44 58	93.00 26	99.65 73	95.76 100	99.47 41

reproduce_model		97.51 17	97.51 17	97.50 50	98.99 48	93.01 78	97.79 100	98.21 62	95.73 22	97.99 45	99.03 13	92.63 36	99.82 28	97.80 29	99.42 52	99.67 14

D2MVS		91.30 289	90.95 267	92.35 342	94.71 353	85.52 342	96.18 289	98.21 62	88.89 293	86.60 380	93.82 364	79.92 287	97.95 320	89.29 264	90.95 312	93.56 405

reproduce-ours		97.53 15	97.51 17	97.60 47	98.97 49	93.31 69	97.71 113	98.20 64	95.80 19	97.88 49	98.98 16	92.91 27	99.81 30	97.68 31	99.43 49	99.67 14

our_new_method		97.53 15	97.51 17	97.60 47	98.97 49	93.31 69	97.71 113	98.20 64	95.80 19	97.88 49	98.98 16	92.91 27	99.81 30	97.68 31	99.43 49	99.67 14

SDMVSNet		94.17 152	93.61 159	95.86 158	98.09 110	91.37 146	97.35 169	98.20 64	93.18 126	91.79 246	97.28 168	79.13 299	98.93 190	94.61 140	92.84 278	97.28 260

XVS		97.18 29	96.96 40	97.81 28	99.38 14	94.03 50	98.59 13	98.20 64	94.85 51	96.59 93	98.29 78	91.70 53	99.80 35	95.66 102	99.40 57	99.62 23

X-MVStestdata		91.71 261	89.67 327	97.81 28	99.38 14	94.03 50	98.59 13	98.20 64	94.85 51	96.59 93	32.69 466	91.70 53	99.80 35	95.66 102	99.40 57	99.62 23

ACMMP_NAP		97.20 28	96.86 44	98.23 11	99.09 36	95.16 22	97.60 132	98.19 69	92.82 148	97.93 48	98.74 40	91.60 56	99.86 9	96.26 74	99.52 31	99.67 14

CP-MVSNet		91.89 257	91.24 256	93.82 286	95.05 334	88.57 258	97.82 94	98.19 69	91.70 182	88.21 346	95.76 264	81.96 246	97.52 366	87.86 290	84.65 383	95.37 335

ZNCC-MVS		96.96 41	96.67 59	97.85 25	99.37 16	94.12 46	98.49 20	98.18 71	92.64 154	96.39 107	98.18 85	91.61 55	99.88 4	95.59 112	99.55 26	99.57 32

SMA-MVS		97.35 22	97.03 35	98.30 8	99.06 40	95.42 10	97.94 76	98.18 71	90.57 241	98.85 25	98.94 19	93.33 23	99.83 26	96.72 61	99.68 4	99.63 22
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
PEN-MVS		91.20 294	90.44 290	93.48 305	94.49 361	87.91 283	97.76 102	98.18 71	91.29 199	87.78 355	95.74 265	80.35 278	97.33 379	85.46 339	82.96 405	95.19 350

DELS-MVS		96.61 66	96.38 75	97.30 59	97.79 134	93.19 74	95.96 301	98.18 71	95.23 33	95.87 127	97.65 139	91.45 58	99.70 66	95.87 94	99.44 48	99.00 104
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
tfpnnormal		89.70 346	88.40 352	93.60 298	95.15 329	90.10 199	97.56 137	98.16 75	87.28 346	86.16 386	94.63 319	77.57 327	98.05 300	74.48 425	84.59 387	92.65 418

VNet		95.89 93	95.45 96	97.21 67	98.07 114	92.94 81	97.50 146	98.15 76	93.87 95	97.52 56	97.61 145	85.29 173	99.53 106	95.81 99	95.27 231	99.16 81

DeepPCF-MVS	93.97 1	96.61 66	97.09 28	95.15 201	98.09 110	86.63 315	96.00 299	98.15 76	95.43 26	97.95 47	98.56 45	93.40 21	99.36 131	96.77 58	99.48 40	99.45 55

SD-MVS		97.41 20	97.53 15	97.06 78	98.57 74	94.46 34	97.92 79	98.14 78	94.82 55	99.01 15	98.55 47	94.18 14	97.41 375	96.94 53	99.64 14	99.32 70
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
GST-MVS		96.85 49	96.52 65	97.82 27	99.36 20	94.14 45	98.29 30	98.13 79	92.72 151	96.70 85	98.06 92	91.35 62	99.86 9	94.83 129	99.28 69	99.47 54

UA-Net		95.95 90	95.53 92	97.20 68	97.67 141	92.98 80	97.65 122	98.13 79	94.81 57	96.61 91	98.35 66	88.87 100	99.51 111	90.36 239	97.35 168	99.11 89

QAPM		93.45 191	92.27 218	96.98 81	96.77 212	92.62 94	98.39 25	98.12 81	84.50 391	88.27 344	97.77 127	82.39 238	99.81 30	85.40 340	98.81 109	98.51 164

Vis-MVSNet		95.23 115	94.81 118	96.51 106	97.18 169	91.58 136	98.26 35	98.12 81	94.38 82	94.90 157	98.15 87	82.28 239	98.92 192	91.45 213	98.58 121	99.01 101
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 218	91.68 239	96.40 116	95.34 312	92.73 90	98.27 33	98.12 81	84.86 386	85.78 388	97.75 128	78.89 309	99.74 53	87.50 305	98.65 116	96.73 277

TranMVSNet+NR-MVSNet		92.50 227	91.63 240	95.14 202	94.76 349	92.07 115	97.53 143	98.11 84	92.90 145	89.56 307	96.12 243	83.16 213	97.60 358	89.30 263	83.20 404	95.75 314

CPTT-MVS		95.57 103	95.19 107	96.70 87	99.27 28	91.48 141	98.33 27	98.11 84	87.79 331	95.17 152	98.03 95	87.09 142	99.61 84	93.51 165	99.42 52	99.02 98

APD-MVS		96.95 42	96.60 61	98.01 20	99.03 43	94.93 27	97.72 111	98.10 86	91.50 191	98.01 44	98.32 74	92.33 42	99.58 92	94.85 127	99.51 34	99.53 44
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 47	96.60 61	97.64 45	99.40 11	93.44 62	98.50 19	98.09 87	93.27 120	95.95 125	98.33 72	91.04 70	99.88 4	95.20 116	99.57 25	99.60 27

ZD-MVS					99.05 41	94.59 32		98.08 88	89.22 279	97.03 75	98.10 88	92.52 39	99.65 73	94.58 142	99.31 67

MTGPA								98.08 88

MTAPA		97.08 34	96.78 54	97.97 23	99.37 16	94.42 36	97.24 179	98.08 88	95.07 42	96.11 117	98.59 44	90.88 76	99.90 2	96.18 86	99.50 36	99.58 31

CNVR-MVS		97.68 6	97.44 21	98.37 7	98.90 55	95.86 6	97.27 177	98.08 88	95.81 18	97.87 52	98.31 75	94.26 13	99.68 69	97.02 52	99.49 39	99.57 32

DP-MVS Recon		95.68 98	95.12 111	97.37 56	99.19 33	94.19 42	97.03 197	98.08 88	88.35 313	95.09 154	97.65 139	89.97 87	99.48 118	92.08 198	98.59 120	98.44 175

SR-MVS		97.01 39	96.86 44	97.47 52	99.09 36	93.27 71	97.98 66	98.07 93	93.75 98	97.45 58	98.48 55	91.43 60	99.59 89	96.22 77	99.27 70	99.54 41

MCST-MVS		97.18 29	96.84 46	98.20 14	99.30 26	95.35 15	97.12 193	98.07 93	93.54 108	96.08 119	97.69 134	93.86 16	99.71 61	96.50 68	99.39 59	99.55 39

NR-MVSNet		92.34 236	91.27 255	95.53 183	94.95 338	93.05 77	97.39 165	98.07 93	92.65 153	84.46 399	95.71 266	85.00 180	97.77 342	89.71 251	83.52 401	95.78 310

MP-MVS-pluss		96.70 60	96.27 78	97.98 22	99.23 32	94.71 29	96.96 208	98.06 96	90.67 231	95.55 141	98.78 38	91.07 69	99.86 9	96.58 66	99.55 26	99.38 66
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 53	96.71 58	97.12 72	99.01 47	92.31 106	97.98 66	98.06 96	93.11 130	97.44 59	98.55 47	90.93 74	99.55 102	96.06 87	99.25 74	99.51 45

MP-MVS		96.77 55	96.45 72	97.72 39	99.39 13	93.80 54	98.41 24	98.06 96	93.37 116	95.54 143	98.34 69	90.59 80	99.88 4	94.83 129	99.54 28	99.49 50
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 69	96.27 78	97.22 66	99.32 24	92.74 89	98.74 10	98.06 96	90.57 241	96.77 82	98.35 66	90.21 83	99.53 106	94.80 133	99.63 16	99.38 66

HPM-MVS		96.69 62	96.45 72	97.40 55	99.36 20	93.11 76	98.87 6	98.06 96	91.17 210	96.40 106	97.99 101	90.99 71	99.58 92	95.61 109	99.61 18	99.49 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 143	93.80 152	96.64 89	97.07 175	91.97 120	96.32 277	98.06 96	88.94 291	94.50 170	96.78 201	84.60 186	99.27 141	91.90 199	96.02 208	98.68 150

DeepC-MVS	93.07 3	96.06 84	95.66 89	97.29 60	97.96 122	93.17 75	97.30 175	98.06 96	93.92 93	93.38 206	98.66 41	86.83 144	99.73 55	95.60 111	99.22 76	98.96 109
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		97.30 26	97.03 35	98.11 17	98.77 58	95.06 25	97.34 170	98.04 103	95.96 13	97.09 73	97.88 113	93.18 25	99.71 61	95.84 98	99.17 85	99.56 36

DeepC-MVS_fast	93.89 2	96.93 44	96.64 60	97.78 32	98.64 69	94.30 37	97.41 160	98.04 103	94.81 57	96.59 93	98.37 64	91.24 65	99.64 81	95.16 118	99.52 31	99.42 61
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		96.88 46	96.80 52	97.11 74	99.02 44	92.34 104	97.98 66	98.03 105	93.52 111	97.43 61	98.51 50	91.40 61	99.56 100	96.05 88	99.26 72	99.43 59

RE-MVS-def			96.72 57		99.02 44	92.34 104	97.98 66	98.03 105	93.52 111	97.43 61	98.51 50	90.71 78		96.05 88	99.26 72	99.43 59

RPMNet		88.98 352	87.05 366	94.77 228	94.45 363	87.19 299	90.23 439	98.03 105	77.87 439	92.40 224	87.55 446	80.17 282	99.51 111	68.84 446	93.95 264	97.60 245

save fliter					98.91 54	94.28 38	97.02 199	98.02 108	95.35 29

TEST9					98.70 61	94.19 42	96.41 264	98.02 108	88.17 317	96.03 120	97.56 151	92.74 33	99.59 89

train_agg		96.30 80	95.83 88	97.72 39	98.70 61	94.19 42	96.41 264	98.02 108	88.58 304	96.03 120	97.56 151	92.73 34	99.59 89	95.04 120	99.37 63	99.39 64

test_8					98.67 63	94.06 49	96.37 271	98.01 111	88.58 304	95.98 124	97.55 153	92.73 34	99.58 92

agg_prior					98.67 63	93.79 55		98.00 112		95.68 137			99.57 99

test_prior				97.23 65	98.67 63	92.99 79		98.00 112					99.41 126			99.29 71

WR-MVS		92.34 236	91.53 244	94.77 228	95.13 331	90.83 172	96.40 268	97.98 114	91.88 177	89.29 316	95.54 277	82.50 234	97.80 338	89.79 250	85.27 374	95.69 317

HPM-MVS++		97.34 23	96.97 38	98.47 5	99.08 38	96.16 4	97.55 142	97.97 115	95.59 23	96.61 91	97.89 110	92.57 38	99.84 23	95.95 93	99.51 34	99.40 62

CANet		96.39 75	96.02 83	97.50 50	97.62 148	93.38 64	97.02 199	97.96 116	95.42 27	94.86 158	97.81 123	87.38 137	99.82 28	96.88 55	99.20 82	99.29 71

114514_t		93.95 167	93.06 184	96.63 93	99.07 39	91.61 133	97.46 157	97.96 116	77.99 437	93.00 215	97.57 149	86.14 158	99.33 133	89.22 267	99.15 89	98.94 113

IU-MVS					99.42 7	95.39 11		97.94 118	90.40 247	98.94 17				97.41 47	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 63	96.94 1		97.93 119					99.86 9	97.68 31	99.67 6	99.77 2

No_MVS				98.86 1	98.67 63	96.94 1		97.93 119					99.86 9	97.68 31	99.67 6	99.77 2

fmvsm_s_conf0.1_n_2		96.33 79	96.44 74	96.00 148	97.30 162	90.37 193	97.53 143	97.92 121	96.52 9	99.14 13	99.08 7	83.21 211	99.74 53	99.22 9	98.06 144	97.88 225

Anonymous20231211		90.63 318	89.42 334	94.27 258	98.24 95	89.19 244	98.05 58	97.89 122	79.95 429	88.25 345	94.96 300	72.56 368	98.13 283	89.70 252	85.14 376	95.49 321

原ACMM1				96.38 119	98.59 71	91.09 162		97.89 122	87.41 342	95.22 151	97.68 135	90.25 82	99.54 104	87.95 289	99.12 94	98.49 167

CDPH-MVS		95.97 89	95.38 101	97.77 34	98.93 52	94.44 35	96.35 272	97.88 124	86.98 350	96.65 89	97.89 110	91.99 48	99.47 119	92.26 187	99.46 42	99.39 64

test11								97.88 124

EIA-MVS		95.53 104	95.47 95	95.71 173	97.06 178	89.63 217	97.82 94	97.87 126	93.57 104	93.92 188	95.04 297	90.61 79	98.95 187	94.62 139	98.68 114	98.54 160

CS-MVS		96.86 47	97.06 30	96.26 129	98.16 106	91.16 160	99.09 3	97.87 126	95.30 31	97.06 74	98.03 95	91.72 51	98.71 226	97.10 50	99.17 85	98.90 122

无先验							95.79 312	97.87 126	83.87 399				99.65 73	87.68 299		98.89 127

3Dnovator+	91.43 4	95.40 105	94.48 136	98.16 16	96.90 193	95.34 16	98.48 21	97.87 126	94.65 68	88.53 336	98.02 97	83.69 202	99.71 61	93.18 173	98.96 104	99.44 57

VPNet		92.23 244	91.31 252	94.99 211	95.56 296	90.96 166	97.22 185	97.86 130	92.96 140	90.96 268	96.62 218	75.06 348	98.20 277	91.90 199	83.65 400	95.80 308

test_vis1_n_1920		94.17 152	94.58 128	92.91 326	97.42 160	82.02 396	97.83 92	97.85 131	94.68 65	98.10 42	98.49 52	70.15 387	99.32 135	97.91 28	98.82 108	97.40 254

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 131	94.92 48	98.73 28	98.87 29	95.08 8	99.84 23	97.52 40	99.67 6	99.48 52
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
TSAR-MVS + MP.		97.42 19	97.33 24	97.69 42	99.25 29	94.24 41	98.07 56	97.85 131	93.72 99	98.57 32	98.35 66	93.69 18	99.40 127	97.06 51	99.46 42	99.44 57
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SPE-MVS-test		96.89 45	97.04 34	96.45 113	98.29 88	91.66 132	99.03 4	97.85 131	95.84 16	96.90 77	97.97 103	91.24 65	98.75 216	96.92 54	99.33 65	98.94 113

test_fmvsmconf0.01_n		96.15 83	95.85 87	97.03 79	92.66 414	91.83 124	97.97 72	97.84 135	95.57 24	97.53 55	99.00 14	84.20 195	99.76 48	98.82 21	99.08 96	99.48 52

GDP-MVS		95.62 100	95.13 109	97.09 75	96.79 206	93.26 72	97.89 83	97.83 136	93.58 103	96.80 79	97.82 121	83.06 218	99.16 155	94.40 146	97.95 150	98.87 130

balanced_conf03		96.84 51	96.89 43	96.68 88	97.63 147	92.22 109	98.17 49	97.82 137	94.44 77	98.23 40	97.36 163	90.97 72	99.22 145	97.74 30	99.66 10	98.61 153

AdaColmap		94.34 147	93.68 157	96.31 123	98.59 71	91.68 131	96.59 253	97.81 138	89.87 257	92.15 234	97.06 184	83.62 205	99.54 104	89.34 262	98.07 143	97.70 238

MVSMamba_PlusPlus		96.51 69	96.48 67	96.59 97	98.07 114	91.97 120	98.14 50	97.79 139	90.43 245	97.34 64	97.52 154	91.29 64	99.19 148	98.12 26	99.64 14	98.60 154

KinetiMVS		95.26 111	94.75 123	96.79 85	96.99 187	92.05 116	97.82 94	97.78 140	94.77 61	96.46 103	97.70 132	80.62 272	99.34 132	92.37 186	98.28 134	98.97 106

mamv4		94.66 140	96.10 82	90.37 395	98.01 117	73.41 446	96.82 223	97.78 140	89.95 256	94.52 169	97.43 159	92.91 27	99.09 168	98.28 25	99.16 88	98.60 154

ETV-MVS		96.02 86	95.89 86	96.40 116	97.16 170	92.44 101	97.47 155	97.77 142	94.55 71	96.48 101	94.51 325	91.23 67	98.92 192	95.65 105	98.19 138	97.82 233

新几何1				97.32 58	98.60 70	93.59 59		97.75 143	81.58 420	95.75 132	97.85 117	90.04 85	99.67 71	86.50 321	99.13 92	98.69 149

旧先验1					98.38 84	93.38 64		97.75 143			98.09 90	92.30 45			99.01 102	99.16 81

EC-MVSNet		96.42 73	96.47 68	96.26 129	97.01 185	91.52 138	98.89 5	97.75 143	94.42 78	96.64 90	97.68 135	89.32 93	98.60 241	97.45 44	99.11 95	98.67 151

EI-MVSNet-Vis-set		96.51 69	96.47 68	96.63 93	98.24 95	91.20 154	96.89 215	97.73 146	94.74 63	96.49 100	98.49 52	90.88 76	99.58 92	96.44 70	98.32 132	99.13 85

PAPM_NR		95.01 122	94.59 127	96.26 129	98.89 56	90.68 179	97.24 179	97.73 146	91.80 178	92.93 220	96.62 218	89.13 96	99.14 160	89.21 268	97.78 154	98.97 106

Anonymous20240529		91.98 253	90.73 280	95.73 171	98.14 107	89.40 231	97.99 63	97.72 148	79.63 431	93.54 199	97.41 161	69.94 389	99.56 100	91.04 221	91.11 308	98.22 195

CHOSEN 280x420		93.12 203	92.72 201	94.34 252	96.71 216	87.27 295	90.29 438	97.72 148	86.61 357	91.34 257	95.29 285	84.29 194	98.41 257	93.25 171	98.94 105	97.35 257

EI-MVSNet-UG-set		96.34 78	96.30 77	96.47 110	98.20 101	90.93 168	96.86 218	97.72 148	94.67 66	96.16 116	98.46 56	90.43 81	99.58 92	96.23 76	97.96 149	98.90 122

LS3D		93.57 184	92.61 206	96.47 110	97.59 151	91.61 133	97.67 118	97.72 148	85.17 381	90.29 279	98.34 69	84.60 186	99.73 55	83.85 363	98.27 135	98.06 214

PAPR		94.18 151	93.42 173	96.48 109	97.64 145	91.42 145	95.55 326	97.71 152	88.99 288	92.34 230	95.82 258	89.19 94	99.11 163	86.14 327	97.38 166	98.90 122

UGNet		94.04 162	93.28 176	96.31 123	96.85 198	91.19 155	97.88 84	97.68 153	94.40 80	93.00 215	96.18 238	73.39 365	99.61 84	91.72 205	98.46 126	98.13 203
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
testdata				95.46 191	98.18 105	88.90 251		97.66 154	82.73 411	97.03 75	98.07 91	90.06 84	98.85 199	89.67 253	98.98 103	98.64 152

test12				97.65 43	98.46 75	94.26 39		97.66 154		95.52 144		90.89 75	99.46 120		99.25 74	99.22 78

DTE-MVSNet		90.56 319	89.75 325	93.01 322	93.95 376	87.25 296	97.64 126	97.65 156	90.74 226	87.12 368	95.68 269	79.97 286	97.00 392	83.33 364	81.66 411	94.78 377

TAPA-MVS	90.10 7	92.30 239	91.22 258	95.56 180	98.33 86	89.60 219	96.79 227	97.65 156	81.83 417	91.52 252	97.23 173	87.94 119	98.91 194	71.31 440	98.37 130	98.17 201
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 204	92.45 214	95.05 206	98.09 110	89.21 241	96.89 215	97.64 158	93.18 126	91.79 246	97.28 168	75.35 347	98.65 235	88.99 273	92.84 278	97.28 260

test_cas_vis1_n_1920		94.48 145	94.55 132	94.28 257	96.78 210	86.45 320	97.63 128	97.64 158	93.32 119	97.68 54	98.36 65	73.75 363	99.08 171	96.73 60	99.05 98	97.31 259

NormalMVS		96.36 77	96.11 81	97.12 72	99.37 16	92.90 83	97.99 63	97.63 160	95.92 14	96.57 96	97.93 105	85.34 171	99.50 114	94.99 123	99.21 77	98.97 106

Elysia		94.00 164	93.12 181	96.64 89	96.08 275	92.72 91	97.50 146	97.63 160	91.15 212	94.82 159	97.12 179	74.98 350	99.06 177	90.78 226	98.02 145	98.12 205

StellarMVS		94.00 164	93.12 181	96.64 89	96.08 275	92.72 91	97.50 146	97.63 160	91.15 212	94.82 159	97.12 179	74.98 350	99.06 177	90.78 226	98.02 145	98.12 205

cdsmvs_eth3d_5k		23.24 436	30.99 438	0.00 454	0.00 477	0.00 479	0.00 465	97.63 160	0.00 472	0.00 473	96.88 197	84.38 191	0.00 473	0.00 472	0.00 471	0.00 469

DPM-MVS		95.69 97	94.92 116	98.01 20	98.08 113	95.71 9	95.27 342	97.62 164	90.43 245	95.55 141	97.07 183	91.72 51	99.50 114	89.62 255	98.94 105	98.82 136

sasdasda		96.02 86	95.45 96	97.75 36	97.59 151	95.15 23	98.28 31	97.60 165	94.52 73	96.27 111	96.12 243	87.65 125	99.18 151	96.20 82	94.82 240	98.91 119

canonicalmvs		96.02 86	95.45 96	97.75 36	97.59 151	95.15 23	98.28 31	97.60 165	94.52 73	96.27 111	96.12 243	87.65 125	99.18 151	96.20 82	94.82 240	98.91 119

test222					98.24 95	92.21 110	95.33 337	97.60 165	79.22 433	95.25 149	97.84 119	88.80 102			99.15 89	98.72 146

cascas		91.20 294	90.08 307	94.58 238	94.97 336	89.16 245	93.65 403	97.59 168	79.90 430	89.40 311	92.92 390	75.36 346	98.36 265	92.14 192	94.75 243	96.23 287

h-mvs33		94.15 154	93.52 165	96.04 142	97.81 133	90.22 197	97.62 130	97.58 169	95.19 34	96.74 83	97.45 156	83.67 203	99.61 84	95.85 96	79.73 418	98.29 191

MGCFI-Net		95.94 91	95.40 100	97.56 49	97.59 151	94.62 31	98.21 43	97.57 170	94.41 79	96.17 115	96.16 241	87.54 130	99.17 153	96.19 84	94.73 245	98.91 119

MVSFormer		95.37 106	95.16 108	95.99 149	96.34 251	91.21 152	98.22 41	97.57 170	91.42 195	96.22 113	97.32 164	86.20 156	97.92 325	94.07 151	99.05 98	98.85 132

test_djsdf		93.07 206	92.76 196	94.00 271	93.49 393	88.70 255	98.22 41	97.57 170	91.42 195	90.08 291	95.55 276	82.85 225	97.92 325	94.07 151	91.58 299	95.40 332

OMC-MVS		95.09 120	94.70 124	96.25 132	98.46 75	91.28 148	96.43 260	97.57 170	92.04 173	94.77 163	97.96 104	87.01 143	99.09 168	91.31 215	96.77 189	98.36 182

viewcassd2359sk11		95.26 111	95.09 112	95.80 163	96.95 191	89.72 215	96.80 226	97.56 174	92.21 165	95.37 147	97.80 125	87.17 141	98.77 211	94.82 131	97.10 181	98.90 122

PS-MVSNAJss		93.74 177	93.51 166	94.44 246	93.91 378	89.28 239	97.75 104	97.56 174	92.50 155	89.94 293	96.54 221	88.65 105	98.18 280	93.83 160	90.90 313	95.86 302

casdiffmvs_mvg		95.81 96	95.57 90	96.51 106	96.87 195	91.49 139	97.50 146	97.56 174	93.99 91	95.13 153	97.92 108	87.89 120	98.78 208	95.97 92	97.33 169	99.26 75
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jajsoiax		92.42 232	91.89 232	94.03 270	93.33 401	88.50 262	97.73 108	97.53 177	92.00 175	88.85 328	96.50 223	75.62 345	98.11 287	93.88 158	91.56 300	95.48 322

mvs_tets		92.31 238	91.76 235	93.94 279	93.41 398	88.29 267	97.63 128	97.53 177	92.04 173	88.76 331	96.45 225	74.62 355	98.09 292	93.91 156	91.48 301	95.45 327

dcpmvs_2		96.37 76	97.05 33	94.31 255	98.96 51	84.11 369	97.56 137	97.51 179	93.92 93	97.43 61	98.52 49	92.75 32	99.32 135	97.32 49	99.50 36	99.51 45

HQP_MVS		93.78 176	93.43 171	94.82 221	96.21 255	89.99 203	97.74 106	97.51 179	94.85 51	91.34 257	96.64 211	81.32 258	98.60 241	93.02 179	92.23 287	95.86 302

plane_prior5								97.51 179					98.60 241	93.02 179	92.23 287	95.86 302

viewmanbaseed2359cas		95.24 114	95.02 114	95.91 152	96.87 195	89.98 205	96.82 223	97.49 182	92.26 161	95.47 145	97.82 121	86.47 149	98.69 227	94.80 133	97.20 177	99.06 96

reproduce_monomvs		91.30 289	91.10 262	91.92 356	96.82 203	82.48 390	97.01 202	97.49 182	94.64 69	88.35 339	95.27 288	70.53 382	98.10 288	95.20 116	84.60 386	95.19 350

viewmacassd2359aftdt		95.07 121	94.80 119	95.87 155	96.53 232	89.84 211	96.90 214	97.48 184	92.44 156	95.36 148	97.89 110	85.23 174	98.68 229	94.40 146	97.00 184	99.09 91

PS-MVSNAJ		95.37 106	95.33 103	95.49 187	97.35 161	90.66 180	95.31 339	97.48 184	93.85 96	96.51 99	95.70 268	88.65 105	99.65 73	94.80 133	98.27 135	96.17 291

API-MVS		94.84 133	94.49 135	95.90 153	97.90 128	92.00 119	97.80 98	97.48 184	89.19 280	94.81 161	96.71 204	88.84 101	99.17 153	88.91 275	98.76 112	96.53 280

MG-MVS		95.61 101	95.38 101	96.31 123	98.42 79	90.53 182	96.04 296	97.48 184	93.47 113	95.67 138	98.10 88	89.17 95	99.25 142	91.27 216	98.77 111	99.13 85

MAR-MVS		94.22 150	93.46 168	96.51 106	98.00 119	92.19 113	97.67 118	97.47 188	88.13 321	93.00 215	95.84 256	84.86 184	99.51 111	87.99 288	98.17 140	97.83 232
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
CLD-MVS		92.98 210	92.53 210	94.32 253	96.12 270	89.20 242	95.28 340	97.47 188	92.66 152	89.90 294	95.62 272	80.58 273	98.40 258	92.73 184	92.40 285	95.38 334
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 287	90.22 303	94.68 232	94.86 345	87.86 284	97.23 183	97.46 190	87.99 322	89.90 294	96.92 195	66.35 417	98.23 274	90.30 240	90.99 311	97.96 219

nrg030		94.05 161	93.31 175	96.27 128	95.22 323	94.59 32	98.34 26	97.46 190	92.93 141	91.21 266	96.64 211	87.23 140	98.22 275	94.99 123	85.80 366	95.98 301

XVG-OURS		93.72 178	93.35 174	94.80 226	97.07 175	88.61 256	94.79 358	97.46 190	91.97 176	93.99 185	97.86 116	81.74 252	98.88 196	92.64 185	92.67 283	96.92 272

LPG-MVS_test		92.94 213	92.56 207	94.10 265	96.16 265	88.26 269	97.65 122	97.46 190	91.29 199	90.12 287	97.16 176	79.05 302	98.73 220	92.25 189	91.89 295	95.31 339

LGP-MVS_train				94.10 265	96.16 265	88.26 269		97.46 190	91.29 199	90.12 287	97.16 176	79.05 302	98.73 220	92.25 189	91.89 295	95.31 339

MVS		91.71 261	90.44 290	95.51 184	95.20 325	91.59 135	96.04 296	97.45 195	73.44 447	87.36 364	95.60 273	85.42 170	99.10 165	85.97 332	97.46 161	95.83 306

XVG-OURS-SEG-HR		93.86 173	93.55 161	94.81 223	97.06 178	88.53 261	95.28 340	97.45 195	91.68 183	94.08 184	97.68 135	82.41 237	98.90 195	93.84 159	92.47 284	96.98 268

baseline		95.58 102	95.42 99	96.08 138	96.78 210	90.41 188	97.16 190	97.45 195	93.69 102	95.65 139	97.85 117	87.29 138	98.68 229	95.66 102	97.25 175	99.13 85

ab-mvs		93.57 184	92.55 208	96.64 89	97.28 164	91.96 122	95.40 333	97.45 195	89.81 262	93.22 212	96.28 234	79.62 293	99.46 120	90.74 229	93.11 275	98.50 165

xiu_mvs_v2_base		95.32 109	95.29 104	95.40 192	97.22 166	90.50 183	95.44 332	97.44 199	93.70 101	96.46 103	96.18 238	88.59 109	99.53 106	94.79 136	97.81 153	96.17 291

1314		92.81 222	92.03 225	95.14 202	95.33 315	89.52 226	96.04 296	97.44 199	87.72 335	86.25 385	95.33 284	83.84 200	98.79 207	89.26 265	97.05 183	97.11 266

casdiffmvs		95.64 99	95.49 93	96.08 138	96.76 215	90.45 185	97.29 176	97.44 199	94.00 90	95.46 146	97.98 102	87.52 133	98.73 220	95.64 106	97.33 169	99.08 93
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
XXY-MVS		92.16 246	91.23 257	94.95 217	94.75 350	90.94 167	97.47 155	97.43 202	89.14 281	88.90 324	96.43 226	79.71 290	98.24 273	89.56 256	87.68 347	95.67 318

anonymousdsp		92.16 246	91.55 243	93.97 275	92.58 416	89.55 223	97.51 145	97.42 203	89.42 274	88.40 338	94.84 307	80.66 271	97.88 330	91.87 201	91.28 305	94.48 385

Effi-MVS+		94.93 127	94.45 137	96.36 121	96.61 220	91.47 142	96.41 264	97.41 204	91.02 218	94.50 170	95.92 252	87.53 131	98.78 208	93.89 157	96.81 188	98.84 135

RRT-MVS		94.51 143	94.35 140	94.98 213	96.40 245	86.55 318	97.56 137	97.41 204	93.19 124	94.93 156	97.04 185	79.12 300	99.30 139	96.19 84	97.32 171	99.09 91

HQP3-MVS								97.39 206							92.10 292

HQP-MVS		93.19 200	92.74 199	94.54 241	95.86 281	89.33 235	96.65 244	97.39 206	93.55 105	90.14 281	95.87 254	80.95 262	98.50 251	92.13 195	92.10 292	95.78 310

PLC	91.00 6	94.11 158	93.43 171	96.13 137	98.58 73	91.15 161	96.69 240	97.39 206	87.29 345	91.37 256	96.71 204	88.39 110	99.52 110	87.33 308	97.13 180	97.73 236
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
diffmvs_AUTHOR		95.33 108	95.27 105	95.50 186	96.37 249	89.08 247	96.08 294	97.38 209	93.09 132	96.53 98	97.74 129	86.45 150	98.68 229	96.32 72	97.48 160	98.75 142

v7n		90.76 311	89.86 318	93.45 307	93.54 390	87.60 290	97.70 116	97.37 210	88.85 294	87.65 357	94.08 355	81.08 261	98.10 288	84.68 349	83.79 399	94.66 382

UnsupCasMVSNet_eth		85.99 388	84.45 392	90.62 391	89.97 434	82.40 393	93.62 404	97.37 210	89.86 258	78.59 437	92.37 400	65.25 426	95.35 426	82.27 377	70.75 445	94.10 396

viewdifsd2359ckpt13		94.87 131	94.52 133	95.90 153	96.88 194	90.19 198	96.92 211	97.36 212	91.26 203	94.65 165	97.46 155	85.79 164	98.64 236	93.64 163	96.76 190	98.88 129

ACMM	89.79 8	92.96 211	92.50 212	94.35 250	96.30 253	88.71 254	97.58 133	97.36 212	91.40 197	90.53 274	96.65 210	79.77 289	98.75 216	91.24 217	91.64 297	95.59 320
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 122	94.76 120	95.75 168	96.58 223	91.71 128	96.25 282	97.35 214	92.99 134	96.70 85	96.63 215	82.67 229	99.44 123	96.22 77	97.46 161	96.11 297

xiu_mvs_v1_base		95.01 122	94.76 120	95.75 168	96.58 223	91.71 128	96.25 282	97.35 214	92.99 134	96.70 85	96.63 215	82.67 229	99.44 123	96.22 77	97.46 161	96.11 297

xiu_mvs_v1_base_debi		95.01 122	94.76 120	95.75 168	96.58 223	91.71 128	96.25 282	97.35 214	92.99 134	96.70 85	96.63 215	82.67 229	99.44 123	96.22 77	97.46 161	96.11 297

diffmvs		95.25 113	95.13 109	95.63 176	96.43 244	89.34 234	95.99 300	97.35 214	92.83 147	96.31 109	97.37 162	86.44 151	98.67 232	96.26 74	97.19 178	98.87 130
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WTY-MVS		94.71 139	94.02 148	96.79 85	97.71 139	92.05 116	96.59 253	97.35 214	90.61 237	94.64 166	96.93 192	86.41 152	99.39 128	91.20 218	94.71 246	98.94 113

SSM_0407		94.54 142	94.12 147	95.80 163	96.79 206	90.38 190	96.79 227	97.29 219	91.24 204	93.68 192	97.60 146	85.03 178	98.67 232	92.14 192	96.51 198	98.35 184

SSM_0404		94.73 138	94.31 142	95.98 150	97.05 180	90.90 170	97.01 202	97.29 219	91.24 204	94.17 181	97.60 146	85.03 178	98.76 213	92.14 192	97.30 172	98.29 191

F-COLMAP		93.58 182	92.98 188	95.37 193	98.40 81	88.98 249	97.18 188	97.29 219	87.75 334	90.49 275	97.10 182	85.21 175	99.50 114	86.70 318	96.72 193	97.63 240

VortexMVS		92.88 217	92.64 203	93.58 300	96.58 223	87.53 291	96.93 210	97.28 222	92.78 150	89.75 299	94.99 298	82.73 228	97.76 343	94.60 141	88.16 342	95.46 325

XVG-ACMP-BASELINE		90.93 307	90.21 304	93.09 320	94.31 369	85.89 335	95.33 337	97.26 223	91.06 217	89.38 312	95.44 282	68.61 400	98.60 241	89.46 258	91.05 309	94.79 375

PCF-MVS	89.48 11	91.56 271	89.95 315	96.36 121	96.60 221	92.52 99	92.51 423	97.26 223	79.41 432	88.90 324	96.56 220	84.04 199	99.55 102	77.01 416	97.30 172	97.01 267
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 226	92.14 221	94.05 268	96.40 245	88.20 272	97.36 168	97.25 225	91.52 190	88.30 342	96.64 211	78.46 314	98.72 225	91.86 202	91.48 301	95.23 346
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 182	93.46 168	93.94 279	96.19 259	86.16 329	93.73 398	97.24 226	91.54 186	93.50 201	97.04 185	85.64 167	96.91 395	90.68 231	95.59 222	98.76 138

IMVS_0407		93.94 168	93.75 154	94.49 243	96.19 259	86.16 329	96.35 272	97.24 226	91.54 186	93.50 201	97.04 185	85.64 167	98.54 248	90.68 231	95.59 222	98.76 138

IMVS_0404		92.44 230	91.92 230	94.00 271	96.19 259	86.16 329	93.84 395	97.24 226	91.54 186	88.17 348	97.04 185	76.96 332	97.09 386	90.68 231	95.59 222	98.76 138

IMVS_0403		93.98 166	93.79 153	94.55 240	96.19 259	86.16 329	96.35 272	97.24 226	91.54 186	93.59 196	97.04 185	85.86 161	98.73 220	90.68 231	95.59 222	98.76 138

OPM-MVS		93.28 196	92.76 196	94.82 221	94.63 356	90.77 175	96.65 244	97.18 230	93.72 99	91.68 250	97.26 171	79.33 297	98.63 238	92.13 195	92.28 286	95.07 353
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 215	92.02 226	95.56 180	98.19 103	90.80 173	95.27 342	97.18 230	87.96 323	91.86 245	95.68 269	80.44 276	98.99 185	84.01 358	97.54 159	96.89 273

alignmvs		95.87 95	95.23 106	97.78 32	97.56 157	95.19 21	97.86 85	97.17 232	94.39 81	96.47 102	96.40 228	85.89 160	99.20 147	96.21 81	95.11 236	98.95 112

MVS_Test		94.89 129	94.62 126	95.68 174	96.83 201	89.55 223	96.70 238	97.17 232	91.17 210	95.60 140	96.11 247	87.87 122	98.76 213	93.01 181	97.17 179	98.72 146

Fast-Effi-MVS+		93.46 188	92.75 198	95.59 179	96.77 212	90.03 200	96.81 225	97.13 234	88.19 316	91.30 260	94.27 343	86.21 155	98.63 238	87.66 300	96.46 204	98.12 205

EI-MVSNet		93.03 208	92.88 192	93.48 305	95.77 287	86.98 304	96.44 258	97.12 235	90.66 233	91.30 260	97.64 142	86.56 146	98.05 300	89.91 246	90.55 317	95.41 329

MVSTER		93.20 199	92.81 195	94.37 249	96.56 227	89.59 220	97.06 196	97.12 235	91.24 204	91.30 260	95.96 250	82.02 245	98.05 300	93.48 166	90.55 317	95.47 324

viewmambaseed2359dif		94.28 148	94.14 145	94.71 231	96.21 255	86.97 305	95.93 303	97.11 237	89.00 287	95.00 155	97.70 132	86.02 159	98.59 245	93.71 162	96.59 197	98.57 158

test_yl		94.78 136	94.23 143	96.43 114	97.74 137	91.22 150	96.85 219	97.10 238	91.23 207	95.71 134	96.93 192	84.30 192	99.31 137	93.10 174	95.12 234	98.75 142

DCV-MVSNet		94.78 136	94.23 143	96.43 114	97.74 137	91.22 150	96.85 219	97.10 238	91.23 207	95.71 134	96.93 192	84.30 192	99.31 137	93.10 174	95.12 234	98.75 142

LTVRE_ROB	88.41 13	90.99 303	89.92 317	94.19 259	96.18 263	89.55 223	96.31 278	97.09 240	87.88 326	85.67 389	95.91 253	78.79 310	98.57 246	81.50 380	89.98 322	94.44 388
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
viewmsd2359difaftdt		93.46 188	93.23 178	94.17 260	96.12 270	85.42 344	96.43 260	97.08 241	92.91 142	94.21 177	98.00 99	80.82 268	98.74 218	94.41 145	89.05 331	98.34 188

test_fmvs1_n		92.73 224	92.88 192	92.29 346	96.08 275	81.05 404	97.98 66	97.08 241	90.72 228	96.79 81	98.18 85	63.07 430	98.45 255	97.62 38	98.42 129	97.36 255

v10		91.04 301	90.23 301	93.49 304	94.12 372	88.16 275	97.32 173	97.08 241	88.26 315	88.29 343	94.22 348	82.17 242	97.97 312	86.45 322	84.12 393	94.33 391

viewdifsd2359ckpt11		93.46 188	93.22 179	94.17 260	96.11 272	85.42 344	96.43 260	97.07 244	92.91 142	94.20 178	98.00 99	80.82 268	98.73 220	94.42 144	89.04 333	98.34 188

mamba_0408		93.70 179	92.99 185	95.83 160	96.79 206	90.38 190	88.69 448	97.07 244	90.96 220	93.68 192	97.31 166	84.97 181	98.76 213	90.95 222	96.51 198	98.35 184

SSM_04072		93.51 187	92.99 185	95.05 206	96.79 206	90.38 190	88.69 448	97.07 244	90.96 220	93.68 192	97.31 166	84.97 181	96.42 406	90.95 222	96.51 198	98.35 184

v144192		91.06 300	90.28 297	93.39 308	93.66 387	87.23 298	96.83 222	97.07 244	87.43 341	89.69 302	94.28 342	81.48 255	98.00 307	87.18 312	84.92 382	94.93 361

v1192		91.07 299	90.23 301	93.58 300	93.70 384	87.82 286	96.73 234	97.07 244	87.77 332	89.58 305	94.32 340	80.90 266	97.97 312	86.52 320	85.48 369	94.95 357

v8		91.29 291	90.53 289	93.57 302	94.15 371	88.12 276	97.34 170	97.06 249	88.99 288	88.32 341	94.26 345	83.08 216	98.01 306	87.62 302	83.92 397	94.57 384

mvs_anonymous		93.82 174	93.74 155	94.06 267	96.44 243	85.41 346	95.81 310	97.05 250	89.85 260	90.09 290	96.36 230	87.44 135	97.75 345	93.97 153	96.69 194	99.02 98

IterMVS-LS		92.29 240	91.94 229	93.34 310	96.25 254	86.97 305	96.57 256	97.05 250	90.67 231	89.50 310	94.80 310	86.59 145	97.64 353	89.91 246	86.11 364	95.40 332
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 309	90.03 312	93.29 312	93.55 389	86.96 307	96.74 233	97.04 252	87.36 343	89.52 309	94.34 337	80.23 281	97.97 312	86.27 323	85.21 375	94.94 359

CDS-MVSNet		94.14 157	93.54 162	95.93 151	96.18 263	91.46 143	96.33 276	97.04 252	88.97 290	93.56 197	96.51 222	87.55 129	97.89 329	89.80 249	95.95 210	98.44 175
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 345	89.26 338	91.19 380	95.16 326	80.29 415	94.53 365	97.03 254	91.79 179	88.86 327	94.10 352	69.94 389	97.82 335	85.29 341	86.66 360	95.45 327

v1144		91.37 284	90.60 285	93.68 295	93.89 379	88.23 271	96.84 221	97.03 254	88.37 312	89.69 302	94.39 332	82.04 244	97.98 309	87.80 292	85.37 371	94.84 367

v1240		90.70 315	89.85 319	93.23 314	93.51 392	86.80 308	96.61 250	97.02 256	87.16 348	89.58 305	94.31 341	79.55 294	97.98 309	85.52 338	85.44 370	94.90 364

EPP-MVSNet		95.22 116	95.04 113	95.76 166	97.49 158	89.56 222	98.67 11	97.00 257	90.69 229	94.24 176	97.62 144	89.79 90	98.81 205	93.39 170	96.49 202	98.92 118

V42		91.58 270	90.87 269	93.73 290	94.05 375	88.50 262	97.32 173	96.97 258	88.80 300	89.71 300	94.33 338	82.54 233	98.05 300	89.01 272	85.07 378	94.64 383

test_fmvs1		93.21 198	93.53 163	92.25 349	96.55 229	81.20 403	97.40 164	96.96 259	90.68 230	96.80 79	98.04 94	69.25 395	98.40 258	97.58 39	98.50 122	97.16 265

FMVSNet2		91.31 288	90.08 307	94.99 211	96.51 236	92.21 110	97.41 160	96.95 260	88.82 297	88.62 333	94.75 312	73.87 359	97.42 374	85.20 344	88.55 339	95.35 336

ACMH	87.59 16	90.53 320	89.42 334	93.87 284	96.21 255	87.92 281	97.24 179	96.94 261	88.45 310	83.91 409	96.27 235	71.92 371	98.62 240	84.43 352	89.43 328	95.05 355
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 285	90.27 298	94.59 234	96.51 236	91.18 157	97.50 146	96.93 262	88.82 297	89.35 313	94.51 325	73.87 359	97.29 381	86.12 328	88.82 334	95.31 339

test1		91.35 285	90.27 298	94.59 234	96.51 236	91.18 157	97.50 146	96.93 262	88.82 297	89.35 313	94.51 325	73.87 359	97.29 381	86.12 328	88.82 334	95.31 339

FMVSNet3		91.78 259	90.69 283	95.03 209	96.53 232	92.27 108	97.02 199	96.93 262	89.79 263	89.35 313	94.65 318	77.01 330	97.47 369	86.12 328	88.82 334	95.35 336

FMVSNet1		89.88 340	88.31 353	94.59 234	95.41 305	91.18 157	97.50 146	96.93 262	86.62 356	87.41 362	94.51 325	65.94 422	97.29 381	83.04 367	87.43 350	95.31 339

GeoE		93.89 171	93.28 176	95.72 172	96.96 190	89.75 214	98.24 39	96.92 266	89.47 271	92.12 236	97.21 174	84.42 190	98.39 263	87.71 295	96.50 201	99.01 101

SymmetryMVS		95.94 91	95.54 91	97.15 70	97.85 130	92.90 83	97.99 63	96.91 267	95.92 14	96.57 96	97.93 105	85.34 171	99.50 114	94.99 123	96.39 205	99.05 97

miper_enhance_ethall		91.54 274	91.01 265	93.15 318	95.35 311	87.07 303	93.97 387	96.90 268	86.79 354	89.17 320	93.43 384	86.55 147	97.64 353	89.97 245	86.93 355	94.74 379

eth_miper_zixun_eth		91.02 302	90.59 286	92.34 344	95.33 315	84.35 365	94.10 384	96.90 268	88.56 306	88.84 329	94.33 338	84.08 197	97.60 358	88.77 278	84.37 391	95.06 354

TAMVS		94.01 163	93.46 168	95.64 175	96.16 265	90.45 185	96.71 237	96.89 270	89.27 278	93.46 204	96.92 195	87.29 138	97.94 322	88.70 280	95.74 216	98.53 161

miper_ehance_all_eth		91.59 268	91.13 261	92.97 324	95.55 297	86.57 316	94.47 368	96.88 271	87.77 332	88.88 326	94.01 357	86.22 154	97.54 362	89.49 257	86.93 355	94.79 375

v2v482		91.59 268	90.85 272	93.80 287	93.87 380	88.17 274	96.94 209	96.88 271	89.54 268	89.53 308	94.90 304	81.70 253	98.02 305	89.25 266	85.04 380	95.20 347

CNLPA		94.28 148	93.53 163	96.52 102	98.38 84	92.55 98	96.59 253	96.88 271	90.13 253	91.91 242	97.24 172	85.21 175	99.09 168	87.64 301	97.83 152	97.92 222

PAPM		91.52 275	90.30 296	95.20 199	95.30 318	89.83 212	93.38 409	96.85 274	86.26 364	88.59 334	95.80 259	84.88 183	98.15 282	75.67 421	95.93 211	97.63 240

c3_l		91.38 282	90.89 268	92.88 328	95.58 295	86.30 323	94.68 360	96.84 275	88.17 317	88.83 330	94.23 346	85.65 166	97.47 369	89.36 261	84.63 384	94.89 365

pm-mvs1		90.72 314	89.65 329	93.96 276	94.29 370	89.63 217	97.79 100	96.82 276	89.07 283	86.12 387	95.48 281	78.61 312	97.78 340	86.97 316	81.67 410	94.46 386

test_vis1_n		92.37 235	92.26 219	92.72 334	94.75 350	82.64 386	98.02 60	96.80 277	91.18 209	97.77 53	97.93 105	58.02 440	98.29 271	97.63 36	98.21 137	97.23 263

CMPMVS	62.92 21	85.62 393	84.92 388	87.74 418	89.14 439	73.12 448	94.17 382	96.80 277	73.98 444	73.65 446	94.93 302	66.36 416	97.61 357	83.95 360	91.28 305	92.48 423
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 327	89.77 323	91.78 365	94.33 367	84.72 362	95.55 326	96.73 279	86.17 366	86.36 384	95.28 287	71.28 376	97.80 338	84.09 357	98.14 141	92.81 415

Effi-MVS+-dtu		93.08 205	93.21 180	92.68 337	96.02 278	83.25 379	97.14 192	96.72 280	93.85 96	91.20 267	93.44 381	83.08 216	98.30 270	91.69 208	95.73 217	96.50 282

TSAR-MVS + GP.		96.69 62	96.49 66	97.27 63	98.31 87	93.39 63	96.79 227	96.72 280	94.17 85	97.44 59	97.66 138	92.76 31	99.33 133	96.86 57	97.76 156	99.08 93

1112_ss		93.37 193	92.42 215	96.21 133	97.05 180	90.99 164	96.31 278	96.72 280	86.87 353	89.83 297	96.69 208	86.51 148	99.14 160	88.12 285	93.67 269	98.50 165

PVSNet	86.66 18	92.24 243	91.74 238	93.73 290	97.77 135	83.69 376	92.88 418	96.72 280	87.91 325	93.00 215	94.86 306	78.51 313	99.05 180	86.53 319	97.45 165	98.47 170

miper_lstm_enhance		90.50 323	90.06 311	91.83 361	95.33 315	83.74 373	93.86 393	96.70 284	87.56 339	87.79 354	93.81 365	83.45 208	96.92 394	87.39 306	84.62 385	94.82 370

v148		90.99 303	90.38 292	92.81 331	93.83 381	85.80 336	96.78 231	96.68 285	89.45 273	88.75 332	93.93 361	82.96 222	97.82 335	87.83 291	83.25 402	94.80 373

ACMH+	87.92 14	90.20 331	89.18 340	93.25 313	96.48 239	86.45 320	96.99 205	96.68 285	88.83 296	84.79 398	96.22 237	70.16 386	98.53 249	84.42 353	88.04 343	94.77 378

CANet_DTU		94.37 146	93.65 158	96.55 99	96.46 242	92.13 114	96.21 286	96.67 287	94.38 82	93.53 200	97.03 190	79.34 296	99.71 61	90.76 228	98.45 127	97.82 233

cl____		90.96 306	90.32 294	92.89 327	95.37 309	86.21 326	94.46 370	96.64 288	87.82 328	88.15 349	94.18 349	82.98 220	97.54 362	87.70 296	85.59 367	94.92 363

HY-MVS	89.66 9	93.87 172	92.95 189	96.63 93	97.10 174	92.49 100	95.64 323	96.64 288	89.05 285	93.00 215	95.79 262	85.77 165	99.45 122	89.16 271	94.35 248	97.96 219

Test_1112_low_res		92.84 220	91.84 233	95.85 159	97.04 182	89.97 207	95.53 328	96.64 288	85.38 376	89.65 304	95.18 292	85.86 161	99.10 165	87.70 296	93.58 274	98.49 167

DIV-MVS_self_test		90.97 305	90.33 293	92.88 328	95.36 310	86.19 328	94.46 370	96.63 291	87.82 328	88.18 347	94.23 346	82.99 219	97.53 364	87.72 293	85.57 368	94.93 361

Fast-Effi-MVS+-dtu		92.29 240	91.99 227	93.21 316	95.27 319	85.52 342	97.03 197	96.63 291	92.09 171	89.11 322	95.14 294	80.33 279	98.08 293	87.54 304	94.74 244	96.03 300

UnsupCasMVSNet_bld		82.13 410	79.46 415	90.14 398	88.00 447	82.47 391	90.89 436	96.62 293	78.94 434	75.61 441	84.40 452	56.63 443	96.31 408	77.30 413	66.77 453	91.63 433

cl22		91.21 293	90.56 288	93.14 319	96.09 274	86.80 308	94.41 372	96.58 294	87.80 330	88.58 335	93.99 359	80.85 267	97.62 356	89.87 248	86.93 355	94.99 356

jason		94.84 133	94.39 139	96.18 135	95.52 298	90.93 168	96.09 293	96.52 295	89.28 277	96.01 123	97.32 164	84.70 185	98.77 211	95.15 119	98.91 107	98.85 132
jason: jason.
tt0805		91.09 298	90.07 310	94.16 263	95.61 293	88.31 266	97.56 137	96.51 296	89.56 267	89.17 320	95.64 271	67.08 414	98.38 264	91.07 220	88.44 340	95.80 308

AUN-MVS		91.76 260	90.75 278	94.81 223	97.00 186	88.57 258	96.65 244	96.49 297	89.63 265	92.15 234	96.12 243	78.66 311	98.50 251	90.83 224	79.18 421	97.36 255

hse-mvs2		93.45 191	92.99 185	94.81 223	97.02 184	88.59 257	96.69 240	96.47 298	95.19 34	96.74 83	96.16 241	83.67 203	98.48 254	95.85 96	79.13 422	97.35 257

SD_0403		90.01 335	90.02 313	89.96 401	95.65 292	76.76 436	95.76 314	96.46 299	90.58 240	86.59 381	96.29 233	82.12 243	94.78 430	73.00 435	93.76 267	98.35 184

EG-PatchMatch MVS		87.02 375	85.44 380	91.76 367	92.67 413	85.00 356	96.08 294	96.45 300	83.41 407	79.52 432	93.49 378	57.10 442	97.72 347	79.34 404	90.87 314	92.56 420

KD-MVS_self_test		85.95 389	84.95 387	88.96 412	89.55 438	79.11 430	95.13 350	96.42 301	85.91 369	84.07 407	90.48 423	70.03 388	94.82 429	80.04 396	72.94 442	92.94 413

pmmvs6		87.81 367	86.19 375	92.69 336	91.32 426	86.30 323	97.34 170	96.41 302	80.59 428	84.05 408	94.37 334	67.37 409	97.67 350	84.75 348	79.51 420	94.09 398

PMMVS		92.86 218	92.34 216	94.42 248	94.92 341	86.73 311	94.53 365	96.38 303	84.78 388	94.27 175	95.12 296	83.13 215	98.40 258	91.47 212	96.49 202	98.12 205

RPSCF		90.75 312	90.86 270	90.42 394	96.84 199	76.29 439	95.61 324	96.34 304	83.89 397	91.38 255	97.87 114	76.45 336	98.78 208	87.16 313	92.23 287	96.20 289

BP-MVS1		95.89 93	95.49 93	97.08 77	96.67 217	93.20 73	98.08 54	96.32 305	94.56 70	96.32 108	97.84 119	84.07 198	99.15 157	96.75 59	98.78 110	98.90 122

MSDG		91.42 280	90.24 300	94.96 216	97.15 172	88.91 250	93.69 401	96.32 305	85.72 372	86.93 377	96.47 224	80.24 280	98.98 186	80.57 393	95.05 237	96.98 268

WBMVS		90.69 317	89.99 314	92.81 331	96.48 239	85.00 356	95.21 347	96.30 307	89.46 272	89.04 323	94.05 356	72.45 369	97.82 335	89.46 258	87.41 352	95.61 319

OurMVSNet-221017-0		90.51 322	90.19 305	91.44 373	93.41 398	81.25 401	96.98 206	96.28 308	91.68 183	86.55 382	96.30 232	74.20 358	97.98 309	88.96 274	87.40 353	95.09 352

MVP-Stereo		90.74 313	90.08 307	92.71 335	93.19 403	88.20 272	95.86 307	96.27 309	86.07 367	84.86 397	94.76 311	77.84 325	97.75 345	83.88 362	98.01 147	92.17 430
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 126	94.56 129	96.29 127	96.34 251	91.21 152	95.83 309	96.27 309	88.93 292	96.22 113	96.88 197	86.20 156	98.85 199	95.27 115	99.05 98	98.82 136

BH-untuned		92.94 213	92.62 205	93.92 283	97.22 166	86.16 329	96.40 268	96.25 311	90.06 254	89.79 298	96.17 240	83.19 212	98.35 266	87.19 311	97.27 174	97.24 262

CL-MVSNet_self_test		86.31 384	85.15 384	89.80 403	88.83 442	81.74 399	93.93 390	96.22 312	86.67 355	85.03 395	90.80 421	78.09 321	94.50 431	74.92 424	71.86 444	93.15 411

IS-MVSNet		94.90 128	94.52 133	96.05 141	97.67 141	90.56 181	98.44 22	96.22 312	93.21 121	93.99 185	97.74 129	85.55 169	98.45 255	89.98 244	97.86 151	99.14 84

FA-MVS(test-final)		93.52 186	92.92 190	95.31 196	96.77 212	88.54 260	94.82 357	96.21 314	89.61 266	94.20 178	95.25 290	83.24 210	99.14 160	90.01 243	96.16 207	98.25 193

GA-MVS		91.38 282	90.31 295	94.59 234	94.65 355	87.62 289	94.34 375	96.19 315	90.73 227	90.35 278	93.83 362	71.84 372	97.96 316	87.22 310	93.61 272	98.21 196

LuminaMVS		94.89 129	94.35 140	96.53 100	95.48 300	92.80 87	96.88 217	96.18 316	92.85 146	95.92 126	96.87 199	81.44 256	98.83 202	96.43 71	97.10 181	97.94 221

IterMVS-SCA-FT		90.31 325	89.81 321	91.82 362	95.52 298	84.20 368	94.30 378	96.15 317	90.61 237	87.39 363	94.27 343	75.80 342	96.44 405	87.34 307	86.88 359	94.82 370

IterMVS		90.15 333	89.67 327	91.61 369	95.48 300	83.72 374	94.33 376	96.12 318	89.99 255	87.31 366	94.15 351	75.78 344	96.27 409	86.97 316	86.89 358	94.83 368
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 223	91.51 247	96.52 102	98.77 58	90.99 164	97.38 167	96.08 319	82.38 413	89.29 316	97.87 114	83.77 201	99.69 67	81.37 386	96.69 194	98.89 127

pmmvs4		90.93 307	89.85 319	94.17 260	93.34 400	90.79 174	94.60 362	96.02 320	84.62 389	87.45 360	95.15 293	81.88 250	97.45 371	87.70 296	87.87 345	94.27 395

ppachtmachnet_test		88.35 362	87.29 361	91.53 370	92.45 419	83.57 377	93.75 397	95.97 321	84.28 392	85.32 394	94.18 349	79.00 308	96.93 393	75.71 420	84.99 381	94.10 396

Anonymous20240521		86.42 382	85.44 380	89.34 410	90.33 431	79.79 421	96.73 234	95.92 322	83.71 402	83.25 413	91.36 418	63.92 428	96.01 410	78.39 408	85.36 372	92.22 428

ITE_SJBPF				92.43 340	95.34 312	85.37 349		95.92 322	91.47 192	87.75 356	96.39 229	71.00 378	97.96 316	82.36 376	89.86 324	93.97 401

test_fmvs2		89.77 344	89.93 316	89.31 411	93.68 386	76.37 438	97.64 126	95.90 324	89.84 261	91.49 253	96.26 236	58.77 438	97.10 385	94.65 138	91.13 307	94.46 386

USDC		88.94 353	87.83 358	92.27 347	94.66 354	84.96 358	93.86 393	95.90 324	87.34 344	83.40 411	95.56 275	67.43 408	98.19 279	82.64 375	89.67 326	93.66 404

COLMAP_ROB	87.81 15	90.40 324	89.28 337	93.79 288	97.95 123	87.13 302	96.92 211	95.89 326	82.83 410	86.88 379	97.18 175	73.77 362	99.29 140	78.44 407	93.62 271	94.95 357
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 174	93.08 183	96.02 144	97.88 129	89.96 208	97.72 111	95.85 327	92.43 157	95.86 128	98.44 58	68.42 404	99.39 128	96.31 73	94.85 238	98.71 148

VDDNet		93.05 207	92.07 222	96.02 144	96.84 199	90.39 189	98.08 54	95.85 327	86.22 365	95.79 131	98.46 56	67.59 407	99.19 148	94.92 126	94.85 238	98.47 170

mvsmamba		94.57 141	94.14 145	95.87 155	97.03 183	89.93 209	97.84 89	95.85 327	91.34 198	94.79 162	96.80 200	80.67 270	98.81 205	94.85 127	98.12 142	98.85 132

Vis-MVSNet (Re-imp)		94.15 154	93.88 151	94.95 217	97.61 149	87.92 281	98.10 52	95.80 330	92.22 163	93.02 214	97.45 156	84.53 188	97.91 328	88.24 284	97.97 148	99.02 98

MM		97.29 27	96.98 37	98.23 11	98.01 117	95.03 26	98.07 56	95.76 331	97.78 1	97.52 56	98.80 36	88.09 115	99.86 9	99.44 2	99.37 63	99.80 1

KD-MVS_2432*1600		84.81 399	82.64 402	91.31 375	91.07 428	85.34 350	91.22 431	95.75 332	85.56 374	83.09 414	90.21 426	67.21 410	95.89 412	77.18 414	62.48 457	92.69 416

miper_refine_blended		84.81 399	82.64 402	91.31 375	91.07 428	85.34 350	91.22 431	95.75 332	85.56 374	83.09 414	90.21 426	67.21 410	95.89 412	77.18 414	62.48 457	92.69 416

FE-MVS		92.05 251	91.05 263	95.08 205	96.83 201	87.93 280	93.91 392	95.70 334	86.30 362	94.15 182	94.97 299	76.59 334	99.21 146	84.10 356	96.86 186	98.09 211

tpm cat1		88.36 361	87.21 364	91.81 363	95.13 331	80.55 410	92.58 422	95.70 334	74.97 443	87.45 360	91.96 411	78.01 324	98.17 281	80.39 395	88.74 337	96.72 278

our_test_3		88.78 357	87.98 357	91.20 379	92.45 419	82.53 388	93.61 405	95.69 336	85.77 371	84.88 396	93.71 367	79.99 285	96.78 401	79.47 401	86.24 361	94.28 394

BH-w/o		92.14 248	91.75 236	93.31 311	96.99 187	85.73 339	95.67 318	95.69 336	88.73 302	89.26 318	94.82 309	82.97 221	98.07 297	85.26 343	96.32 206	96.13 296

CR-MVSNet		90.82 310	89.77 323	93.95 277	94.45 363	87.19 299	90.23 439	95.68 338	86.89 352	92.40 224	92.36 403	80.91 264	97.05 388	81.09 390	93.95 264	97.60 245

Patchmtry		88.64 359	87.25 362	92.78 333	94.09 373	86.64 312	89.82 443	95.68 338	80.81 425	87.63 358	92.36 403	80.91 264	97.03 389	78.86 405	85.12 377	94.67 381

testing91		91.90 256	91.02 264	94.53 242	96.54 230	86.55 318	95.86 307	95.64 340	91.77 180	91.89 243	93.47 380	69.94 389	98.86 197	90.23 242	93.86 266	98.18 198

BH-RMVSNet		92.72 225	91.97 228	94.97 215	97.16 170	87.99 279	96.15 291	95.60 341	90.62 236	91.87 244	97.15 178	78.41 315	98.57 246	83.16 365	97.60 158	98.36 182

PVSNet_0	82.17 19	85.46 394	83.64 397	90.92 383	95.27 319	79.49 426	90.55 437	95.60 341	83.76 401	83.00 416	89.95 428	71.09 377	97.97 312	82.75 373	60.79 459	95.31 339

guyue		95.17 119	94.96 115	95.82 161	96.97 189	89.65 216	97.56 137	95.58 343	94.82 55	95.72 133	97.42 160	82.90 223	98.84 201	96.71 62	96.93 185	98.96 109

SCA		91.84 258	91.18 260	93.83 285	95.59 294	84.95 359	94.72 359	95.58 343	90.82 223	92.25 232	93.69 369	75.80 342	98.10 288	86.20 325	95.98 209	98.45 172

MonoMVSNet		91.92 254	91.77 234	92.37 341	92.94 407	83.11 382	97.09 195	95.55 345	92.91 142	90.85 270	94.55 322	81.27 260	96.52 404	93.01 181	87.76 346	97.47 251

AllTest		90.23 329	88.98 343	93.98 273	97.94 124	86.64 312	96.51 257	95.54 346	85.38 376	85.49 391	96.77 202	70.28 384	99.15 157	80.02 397	92.87 276	96.15 294

TestCases				93.98 273	97.94 124	86.64 312		95.54 346	85.38 376	85.49 391	96.77 202	70.28 384	99.15 157	80.02 397	92.87 276	96.15 294

mmtdpeth		89.70 346	88.96 344	91.90 358	95.84 286	84.42 364	97.46 157	95.53 348	90.27 248	94.46 172	90.50 422	69.74 393	98.95 187	97.39 48	69.48 448	92.34 424

tpmvs		89.83 343	89.15 341	91.89 359	94.92 341	80.30 414	93.11 414	95.46 349	86.28 363	88.08 350	92.65 393	80.44 276	98.52 250	81.47 382	89.92 323	96.84 274

pmmvs5		89.86 342	88.87 347	92.82 330	92.86 409	86.23 325	96.26 281	95.39 350	84.24 393	87.12 368	94.51 325	74.27 357	97.36 378	87.61 303	87.57 348	94.86 366

PatchmatchNet		91.91 255	91.35 249	93.59 299	95.38 307	84.11 369	93.15 413	95.39 350	89.54 268	92.10 237	93.68 371	82.82 226	98.13 283	84.81 347	95.32 230	98.52 162
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 279	91.32 251	91.79 364	95.15 329	79.20 429	93.42 408	95.37 352	88.55 307	93.49 203	93.67 372	82.49 235	98.27 272	90.41 237	89.34 329	97.90 223

Anonymous20231206		87.09 374	86.14 376	89.93 402	91.22 427	80.35 412	96.11 292	95.35 353	83.57 404	84.16 403	93.02 388	73.54 364	95.61 420	72.16 437	86.14 363	93.84 403

MIMVSNet1		84.93 397	83.05 399	90.56 392	89.56 437	84.84 361	95.40 333	95.35 353	83.91 396	80.38 428	92.21 408	57.23 441	93.34 444	70.69 443	82.75 408	93.50 406

TDRefinement		86.53 378	84.76 390	91.85 360	82.23 460	84.25 366	96.38 270	95.35 353	84.97 385	84.09 406	94.94 301	65.76 423	98.34 269	84.60 351	74.52 438	92.97 412

TR-MVS		91.48 278	90.59 286	94.16 263	96.40 245	87.33 292	95.67 318	95.34 356	87.68 336	91.46 254	95.52 278	76.77 333	98.35 266	82.85 370	93.61 272	96.79 276

EPNet_dtu		91.71 261	91.28 254	92.99 323	93.76 383	83.71 375	96.69 240	95.28 357	93.15 128	87.02 373	95.95 251	83.37 209	97.38 377	79.46 402	96.84 187	97.88 225
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 371	85.79 378	91.78 365	94.80 348	87.28 294	95.49 330	95.28 357	84.09 395	83.85 410	91.82 412	62.95 431	94.17 435	78.48 406	85.34 373	93.91 402

MDTV_nov1_ep13			90.76 276		95.22 323	80.33 413	93.03 416	95.28 357	88.14 320	92.84 221	93.83 362	81.34 257	98.08 293	82.86 368	94.34 249

LF4IMVS		87.94 365	87.25 362	89.98 400	92.38 421	80.05 420	94.38 373	95.25 360	87.59 338	84.34 400	94.74 313	64.31 427	97.66 352	84.83 346	87.45 349	92.23 427

TransMVSNet (Re)		88.94 353	87.56 359	93.08 321	94.35 366	88.45 264	97.73 108	95.23 361	87.47 340	84.26 402	95.29 285	79.86 288	97.33 379	79.44 403	74.44 439	93.45 408

test20.03		86.14 387	85.40 382	88.35 413	90.12 432	80.06 419	95.90 306	95.20 362	88.59 303	81.29 423	93.62 374	71.43 375	92.65 448	71.26 441	81.17 413	92.34 424

new-patchmatchnet		83.18 406	81.87 409	87.11 421	86.88 451	75.99 440	93.70 399	95.18 363	85.02 384	77.30 440	88.40 439	65.99 421	93.88 440	74.19 429	70.18 446	91.47 438

MDA-MVSNet_test_wron		85.87 391	84.23 394	90.80 389	92.38 421	82.57 387	93.17 411	95.15 364	82.15 414	67.65 452	92.33 406	78.20 317	95.51 423	77.33 411	79.74 417	94.31 393

YYNet1		85.87 391	84.23 394	90.78 390	92.38 421	82.46 392	93.17 411	95.14 365	82.12 415	67.69 450	92.36 403	78.16 320	95.50 424	77.31 412	79.73 418	94.39 389

Baseline_NR-MVSNet		91.20 294	90.62 284	92.95 325	93.83 381	88.03 278	97.01 202	95.12 366	88.42 311	89.70 301	95.13 295	83.47 206	97.44 372	89.66 254	83.24 403	93.37 409

thres200		92.23 244	91.39 248	94.75 230	97.61 149	89.03 248	96.60 252	95.09 367	92.08 172	93.28 209	94.00 358	78.39 316	99.04 183	81.26 389	94.18 255	96.19 290

ADS-MVSNet		89.89 339	88.68 349	93.53 303	95.86 281	84.89 360	90.93 434	95.07 368	83.23 408	91.28 263	91.81 413	79.01 306	97.85 331	79.52 399	91.39 303	97.84 230

pmmvs-eth3d		86.22 385	84.45 392	91.53 370	88.34 446	87.25 296	94.47 368	95.01 369	83.47 405	79.51 433	89.61 431	69.75 392	95.71 417	83.13 366	76.73 431	91.64 432

Anonymous202405211		92.07 250	90.83 274	95.76 166	98.19 103	88.75 253	97.58 133	95.00 370	86.00 368	93.64 195	97.45 156	66.24 419	99.53 106	90.68 231	92.71 281	99.01 101

MDA-MVSNet-bldmvs		85.00 396	82.95 401	91.17 381	93.13 405	83.33 378	94.56 364	95.00 370	84.57 390	65.13 456	92.65 393	70.45 383	95.85 414	73.57 432	77.49 427	94.33 391

ambc				86.56 424	83.60 457	70.00 451	85.69 455	94.97 372		80.60 427	88.45 438	37.42 459	96.84 398	82.69 374	75.44 436	92.86 414

testgi		87.97 364	87.21 364	90.24 397	92.86 409	80.76 405	96.67 243	94.97 372	91.74 181	85.52 390	95.83 257	62.66 433	94.47 433	76.25 418	88.36 341	95.48 322

myMVS_eth3d28		91.52 275	90.97 266	93.17 317	96.91 192	83.24 380	95.61 324	94.96 374	92.24 162	91.98 240	93.28 385	69.31 394	98.40 258	88.71 279	95.68 219	97.88 225

dp		88.90 355	88.26 355	90.81 387	94.58 359	76.62 437	92.85 419	94.93 375	85.12 382	90.07 292	93.07 387	75.81 341	98.12 286	80.53 394	87.42 351	97.71 237

test_fmvs3		83.21 405	83.02 400	83.78 428	86.77 452	68.34 454	96.76 232	94.91 376	86.49 358	84.14 405	89.48 432	36.04 460	91.73 450	91.86 202	80.77 415	91.26 440

test_0402		86.46 381	84.79 389	91.45 372	95.02 335	85.55 341	96.29 280	94.89 377	80.90 422	82.21 419	93.97 360	68.21 405	97.29 381	62.98 451	88.68 338	91.51 435

tfpn200view9		92.38 234	91.52 245	94.95 217	97.85 130	89.29 237	97.41 160	94.88 378	92.19 168	93.27 210	94.46 330	78.17 318	99.08 171	81.40 383	94.08 259	96.48 283

CVMVSNet		91.23 292	91.75 236	89.67 404	95.77 287	74.69 441	96.44 258	94.88 378	85.81 370	92.18 233	97.64 142	79.07 301	95.58 422	88.06 287	95.86 214	98.74 145

thres400		92.42 232	91.52 245	95.12 204	97.85 130	89.29 237	97.41 160	94.88 378	92.19 168	93.27 210	94.46 330	78.17 318	99.08 171	81.40 383	94.08 259	96.98 268

tt0320		85.39 395	83.12 398	92.19 351	93.44 397	85.79 337	96.19 288	94.87 381	71.19 450	82.92 417	91.76 415	58.43 439	96.81 399	81.03 391	78.26 426	93.98 400

EPNet		95.20 117	94.56 129	97.14 71	92.80 411	92.68 93	97.85 88	94.87 381	96.64 7	92.46 223	97.80 125	86.23 153	99.65 73	93.72 161	98.62 118	99.10 90
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 266	90.72 281	94.32 253	96.48 239	86.11 334	95.81 310	94.76 383	91.55 185	91.75 248	93.44 381	68.55 402	98.82 203	90.43 236	93.69 268	98.04 215

sc_t1		86.48 380	84.10 396	93.63 296	93.45 396	85.76 338	96.79 227	94.71 384	73.06 448	86.45 383	94.35 335	55.13 446	97.95 320	84.38 354	78.55 425	97.18 264

SixPastTwentyTwo		89.15 351	88.54 351	90.98 382	93.49 393	80.28 416	96.70 238	94.70 385	90.78 224	84.15 404	95.57 274	71.78 373	97.71 348	84.63 350	85.07 378	94.94 359

thres100view900		92.43 231	91.58 242	94.98 213	97.92 126	89.37 233	97.71 113	94.66 386	92.20 166	93.31 208	94.90 304	78.06 322	99.08 171	81.40 383	94.08 259	96.48 283

thres600view7		92.49 229	91.60 241	95.18 200	97.91 127	89.47 227	97.65 122	94.66 386	92.18 170	93.33 207	94.91 303	78.06 322	99.10 165	81.61 379	94.06 263	96.98 268

PatchT		88.87 356	87.42 360	93.22 315	94.08 374	85.10 354	89.51 444	94.64 388	81.92 416	92.36 227	88.15 442	80.05 284	97.01 391	72.43 436	93.65 270	97.54 248

baseline1		92.82 221	91.90 231	95.55 182	97.20 168	90.77 175	97.19 187	94.58 389	92.20 166	92.36 227	96.34 231	84.16 196	98.21 276	89.20 269	83.90 398	97.68 239

AstraMVS		94.82 135	94.64 125	95.34 195	96.36 250	88.09 277	97.58 133	94.56 390	94.98 44	95.70 136	97.92 108	81.93 249	98.93 190	96.87 56	95.88 212	98.99 105

UBG		91.55 272	90.76 276	93.94 279	96.52 235	85.06 355	95.22 345	94.54 391	90.47 244	91.98 240	92.71 392	72.02 370	98.74 218	88.10 286	95.26 232	98.01 217

Gipuma		67.86 426	65.41 428	75.18 441	92.66 414	73.45 445	66.50 462	94.52 392	53.33 461	57.80 462	66.07 462	30.81 462	89.20 454	48.15 460	78.88 424	62.90 462
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 264	90.75 278	94.47 244	96.53 232	86.56 317	95.76 314	94.51 393	91.10 216	91.24 265	93.59 375	68.59 401	98.86 197	91.10 219	94.29 251	98.00 218

CostFormer		91.18 297	90.70 282	92.62 338	94.84 346	81.76 398	94.09 385	94.43 394	84.15 394	92.72 222	93.77 366	79.43 295	98.20 277	90.70 230	92.18 290	97.90 223

tpm2		89.96 336	89.21 339	92.23 350	94.91 343	81.25 401	93.78 396	94.42 395	80.62 427	91.56 251	93.44 381	76.44 337	97.94 322	85.60 337	92.08 294	97.49 249

testing3-2		92.10 249	92.05 223	92.27 347	97.71 139	79.56 423	97.42 159	94.41 396	93.53 109	93.22 212	95.49 279	69.16 396	99.11 163	93.25 171	94.22 253	98.13 203

MVS_0304		96.74 59	96.31 76	98.02 19	96.87 195	94.65 30	97.58 133	94.39 397	96.47 10	97.16 68	98.39 62	87.53 131	99.87 7	98.97 18	99.41 55	99.55 39

JIA-IIPM		88.26 363	87.04 367	91.91 357	93.52 391	81.42 400	89.38 445	94.38 398	80.84 424	90.93 269	80.74 454	79.22 298	97.92 325	82.76 372	91.62 298	96.38 286

dmvs_re		90.21 330	89.50 332	92.35 342	95.47 304	85.15 352	95.70 317	94.37 399	90.94 222	88.42 337	93.57 376	74.63 354	95.67 419	82.80 371	89.57 327	96.22 288

Patchmatch-test		89.42 349	87.99 356	93.70 293	95.27 319	85.11 353	88.98 446	94.37 399	81.11 421	87.10 371	93.69 369	82.28 239	97.50 367	74.37 427	94.76 242	98.48 169

LCM-MVSNet		72.55 419	69.39 423	82.03 430	70.81 470	65.42 459	90.12 441	94.36 401	55.02 460	65.88 454	81.72 453	24.16 468	89.96 451	74.32 428	68.10 451	90.71 443

ADS-MVSNet2		89.45 348	88.59 350	92.03 354	95.86 281	82.26 394	90.93 434	94.32 402	83.23 408	91.28 263	91.81 413	79.01 306	95.99 411	79.52 399	91.39 303	97.84 230

mvs5depth		86.53 378	85.08 385	90.87 384	88.74 444	82.52 389	91.91 427	94.23 403	86.35 361	87.11 370	93.70 368	66.52 415	97.76 343	81.37 386	75.80 433	92.31 426

EU-MVSNet		88.72 358	88.90 346	88.20 415	93.15 404	74.21 443	96.63 249	94.22 404	85.18 380	87.32 365	95.97 249	76.16 339	94.98 428	85.27 342	86.17 362	95.41 329

tt0320-xc		84.83 398	82.33 406	92.31 345	93.66 387	86.20 327	96.17 290	94.06 405	71.26 449	82.04 421	92.22 407	55.07 447	96.72 402	81.49 381	75.04 437	94.02 399

MIMVSNet		88.50 360	86.76 370	93.72 292	94.84 346	87.77 287	91.39 429	94.05 406	86.41 360	87.99 352	92.59 396	63.27 429	95.82 416	77.44 410	92.84 278	97.57 247

OpenMVS_ROB	81.14 20	84.42 401	82.28 407	90.83 385	90.06 433	84.05 371	95.73 316	94.04 407	73.89 446	80.17 431	91.53 417	59.15 437	97.64 353	66.92 449	89.05 331	90.80 442

TinyColmap		86.82 376	85.35 383	91.21 377	94.91 343	82.99 384	93.94 389	94.02 408	83.58 403	81.56 422	94.68 315	62.34 434	98.13 283	75.78 419	87.35 354	92.52 422

ETVMVS		90.52 321	89.14 342	94.67 233	96.81 205	87.85 285	95.91 305	93.97 409	89.71 264	92.34 230	92.48 398	65.41 425	97.96 316	81.37 386	94.27 252	98.21 196

IB-MVS	87.33 17	89.91 337	88.28 354	94.79 227	95.26 322	87.70 288	95.12 351	93.95 410	89.35 276	87.03 372	92.49 397	70.74 381	99.19 148	89.18 270	81.37 412	97.49 249
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
Syy-MVS		87.13 373	87.02 368	87.47 419	95.16 326	73.21 447	95.00 353	93.93 411	88.55 307	86.96 374	91.99 409	75.90 340	94.00 437	61.59 453	94.11 256	95.20 347

myMVS_eth3d		87.18 372	86.38 373	89.58 405	95.16 326	79.53 424	95.00 353	93.93 411	88.55 307	86.96 374	91.99 409	56.23 444	94.00 437	75.47 423	94.11 256	95.20 347

testing222		90.31 325	88.96 344	94.35 250	96.54 230	87.29 293	95.50 329	93.84 413	90.97 219	91.75 248	92.96 389	62.18 435	98.00 307	82.86 368	94.08 259	97.76 235

test_f		80.57 412	79.62 414	83.41 429	83.38 458	67.80 456	93.57 406	93.72 414	80.80 426	77.91 439	87.63 445	33.40 461	92.08 449	87.14 314	79.04 423	90.34 444

LCM-MVSNet-Re		92.50 227	92.52 211	92.44 339	96.82 203	81.89 397	96.92 211	93.71 415	92.41 158	84.30 401	94.60 320	85.08 177	97.03 389	91.51 210	97.36 167	98.40 178

tpm		90.25 328	89.74 326	91.76 367	93.92 377	79.73 422	93.98 386	93.54 416	88.28 314	91.99 239	93.25 386	77.51 328	97.44 372	87.30 309	87.94 344	98.12 205

ET-MVSNet_ETH3D		91.49 277	90.11 306	95.63 176	96.40 245	91.57 137	95.34 336	93.48 417	90.60 239	75.58 442	95.49 279	80.08 283	96.79 400	94.25 149	89.76 325	98.52 162

LFMVS		93.60 181	92.63 204	96.52 102	98.13 109	91.27 149	97.94 76	93.39 418	90.57 241	96.29 110	98.31 75	69.00 397	99.16 155	94.18 150	95.87 213	99.12 88

MVStest1		82.38 409	80.04 413	89.37 408	87.63 449	82.83 385	95.03 352	93.37 419	73.90 445	73.50 447	94.35 335	62.89 432	93.25 446	73.80 430	65.92 454	92.04 431

FE-MVSNET		83.85 402	81.97 408	89.51 406	87.19 450	83.19 381	95.21 347	93.17 420	83.45 406	78.90 435	89.05 435	65.46 424	93.84 441	69.71 445	75.56 435	91.51 435

Patchmatch-RL test		87.38 370	86.24 374	90.81 387	88.74 444	78.40 433	88.12 453	93.17 420	87.11 349	82.17 420	89.29 433	81.95 247	95.60 421	88.64 281	77.02 428	98.41 177

ttmdpeth		85.91 390	84.76 390	89.36 409	89.14 439	80.25 417	95.66 321	93.16 422	83.77 400	83.39 412	95.26 289	66.24 419	95.26 427	80.65 392	75.57 434	92.57 419

test-LLR		91.42 280	91.19 259	92.12 352	94.59 357	80.66 407	94.29 379	92.98 423	91.11 214	90.76 272	92.37 400	79.02 304	98.07 297	88.81 276	96.74 191	97.63 240

test-mter		90.19 332	89.54 331	92.12 352	94.59 357	80.66 407	94.29 379	92.98 423	87.68 336	90.76 272	92.37 400	67.67 406	98.07 297	88.81 276	96.74 191	97.63 240

WB-MVSnew		89.88 340	89.56 330	90.82 386	94.57 360	83.06 383	95.65 322	92.85 425	87.86 327	90.83 271	94.10 352	79.66 292	96.88 396	76.34 417	94.19 254	92.54 421

testing3		87.67 368	86.88 369	90.05 399	96.14 268	80.71 406	97.10 194	92.85 425	90.15 252	87.54 359	94.55 322	55.70 445	94.10 436	73.77 431	94.10 258	95.35 336

test_method		66.11 427	64.89 429	69.79 444	72.62 468	35.23 476	65.19 463	92.83 427	20.35 466	65.20 455	88.08 443	43.14 457	82.70 461	73.12 434	63.46 456	91.45 439

test0.0.03 1		89.37 350	88.70 348	91.41 374	92.47 418	85.63 340	95.22 345	92.70 428	91.11 214	86.91 378	93.65 373	79.02 304	93.19 447	78.00 409	89.18 330	95.41 329

new_pmnet		82.89 407	81.12 412	88.18 416	89.63 436	80.18 418	91.77 428	92.57 429	76.79 441	75.56 443	88.23 441	61.22 436	94.48 432	71.43 439	82.92 406	89.87 445

mvsany_test1		93.93 170	93.98 149	93.78 289	94.94 340	86.80 308	94.62 361	92.55 430	88.77 301	96.85 78	98.49 52	88.98 97	98.08 293	95.03 121	95.62 221	96.46 285

thisisatest0515		92.29 240	91.30 253	95.25 198	96.60 221	88.90 251	94.36 374	92.32 431	87.92 324	93.43 205	94.57 321	77.28 329	99.00 184	89.42 260	95.86 214	97.86 229

thisisatest0530		93.03 208	92.21 220	95.49 187	97.07 175	89.11 246	97.49 154	92.19 432	90.16 251	94.09 183	96.41 227	76.43 338	99.05 180	90.38 238	95.68 219	98.31 190

tttt0517		92.96 211	92.33 217	94.87 220	97.11 173	87.16 301	97.97 72	92.09 433	90.63 235	93.88 189	97.01 191	76.50 335	99.06 177	90.29 241	95.45 228	98.38 180

K. test v3		87.64 369	86.75 371	90.32 396	93.02 406	79.48 427	96.61 250	92.08 434	90.66 233	80.25 430	94.09 354	67.21 410	96.65 403	85.96 333	80.83 414	94.83 368

TESTMET0.1,1		90.06 334	89.42 334	91.97 355	94.41 365	80.62 409	94.29 379	91.97 435	87.28 346	90.44 276	92.47 399	68.79 398	97.67 350	88.50 283	96.60 196	97.61 244

PM-MVS		83.48 404	81.86 410	88.31 414	87.83 448	77.59 435	93.43 407	91.75 436	86.91 351	80.63 426	89.91 429	44.42 456	95.84 415	85.17 345	76.73 431	91.50 437

baseline2		91.63 265	90.86 270	93.94 279	94.33 367	86.32 322	95.92 304	91.64 437	89.37 275	86.94 376	94.69 314	81.62 254	98.69 227	88.64 281	94.57 247	96.81 275

APD_test1		79.31 414	77.70 417	84.14 427	89.11 441	69.07 453	92.36 426	91.50 438	69.07 452	73.87 445	92.63 395	39.93 458	94.32 434	70.54 444	80.25 416	89.02 447

FPMVS		71.27 420	69.85 422	75.50 440	74.64 465	59.03 465	91.30 430	91.50 438	58.80 457	57.92 461	88.28 440	29.98 464	85.53 460	53.43 458	82.84 407	81.95 453

door								91.13 440

door-mid								91.06 441

EGC-MVSNET		68.77 425	63.01 431	86.07 426	92.49 417	82.24 395	93.96 388	90.96 442	0.71 471	2.62 472	90.89 420	53.66 448	93.46 442	57.25 456	84.55 388	82.51 452

mvsany_test3		83.59 403	82.44 405	87.03 422	83.80 455	73.82 444	93.70 399	90.92 443	86.42 359	82.51 418	90.26 425	46.76 455	95.71 417	90.82 225	76.76 430	91.57 434

pmmvs3		79.97 413	77.50 418	87.39 420	82.80 459	79.38 428	92.70 421	90.75 444	70.69 451	78.66 436	87.47 447	51.34 451	93.40 443	73.39 433	69.65 447	89.38 446

UWE-MVS		89.91 337	89.48 333	91.21 377	95.88 280	78.23 434	94.91 356	90.26 445	89.11 282	92.35 229	94.52 324	68.76 399	97.96 316	83.95 360	95.59 222	97.42 253

DSMNet-mixed		86.34 383	86.12 377	87.00 423	89.88 435	70.43 449	94.93 355	90.08 446	77.97 438	85.42 393	92.78 391	74.44 356	93.96 439	74.43 426	95.14 233	96.62 279

MVS-HIRNet		82.47 408	81.21 411	86.26 425	95.38 307	69.21 452	88.96 447	89.49 447	66.28 454	80.79 425	74.08 459	68.48 403	97.39 376	71.93 438	95.47 227	92.18 429

WB-MVS		76.77 416	76.63 419	77.18 435	85.32 453	56.82 467	94.53 365	89.39 448	82.66 412	71.35 448	89.18 434	75.03 349	88.88 455	35.42 464	66.79 452	85.84 449

test1111		93.19 200	92.82 194	94.30 256	97.58 155	84.56 363	98.21 43	89.02 449	93.53 109	94.58 167	98.21 82	72.69 366	99.05 180	93.06 177	98.48 125	99.28 73

SSC-MVS		76.05 417	75.83 420	76.72 439	84.77 454	56.22 468	94.32 377	88.96 450	81.82 418	70.52 449	88.91 436	74.79 353	88.71 456	33.69 465	64.71 455	85.23 450

ECVR-MVS		93.19 200	92.73 200	94.57 239	97.66 143	85.41 346	98.21 43	88.23 451	93.43 114	94.70 164	98.21 82	72.57 367	99.07 175	93.05 178	98.49 123	99.25 76

EPMVS		90.70 315	89.81 321	93.37 309	94.73 352	84.21 367	93.67 402	88.02 452	89.50 270	92.38 226	93.49 378	77.82 326	97.78 340	86.03 331	92.68 282	98.11 210

ANet_high		63.94 429	59.58 432	77.02 436	61.24 472	66.06 457	85.66 456	87.93 453	78.53 436	42.94 464	71.04 461	25.42 467	80.71 463	52.60 459	30.83 465	84.28 451

PMMVS2		70.19 421	66.92 425	80.01 431	76.35 464	65.67 458	86.22 454	87.58 454	64.83 456	62.38 457	80.29 456	26.78 466	88.49 458	63.79 450	54.07 461	85.88 448

lessismore_v0				90.45 393	91.96 424	79.09 431		87.19 455		80.32 429	94.39 332	66.31 418	97.55 361	84.00 359	76.84 429	94.70 380

PMVS	53.92 22	58.58 430	55.40 433	68.12 445	51.00 473	48.64 470	78.86 459	87.10 456	46.77 462	35.84 468	74.28 458	8.76 472	86.34 459	42.07 462	73.91 440	69.38 459
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 377	86.41 372	88.02 417	92.87 408	74.60 442	95.38 335	86.70 457	88.17 317	87.28 367	94.67 317	70.83 380	93.30 445	67.45 447	94.31 250	96.17 291

test_vis1_rt		86.16 386	85.06 386	89.46 407	93.47 395	80.46 411	96.41 264	86.61 458	85.22 379	79.15 434	88.64 437	52.41 450	97.06 387	93.08 176	90.57 316	90.87 441

testf1		69.31 423	66.76 426	76.94 437	78.61 462	61.93 461	88.27 451	86.11 459	55.62 458	59.69 458	85.31 450	20.19 470	89.32 452	57.62 454	69.44 449	79.58 454

APD_test2		69.31 423	66.76 426	76.94 437	78.61 462	61.93 461	88.27 451	86.11 459	55.62 458	59.69 458	85.31 450	20.19 470	89.32 452	57.62 454	69.44 449	79.58 454

gg-mvs-nofinetune		87.82 366	85.61 379	94.44 246	94.46 362	89.27 240	91.21 433	84.61 461	80.88 423	89.89 296	74.98 457	71.50 374	97.53 364	85.75 336	97.21 176	96.51 281

dmvs_testset		81.38 411	82.60 404	77.73 434	91.74 425	51.49 469	93.03 416	84.21 462	89.07 283	78.28 438	91.25 419	76.97 331	88.53 457	56.57 457	82.24 409	93.16 410

GG-mvs-BLEND				93.62 297	93.69 385	89.20 242	92.39 425	83.33 463		87.98 353	89.84 430	71.00 378	96.87 397	82.08 378	95.40 229	94.80 373

MTMP							97.86 85	82.03 464

DeepMVS_CX				74.68 442	90.84 430	64.34 460		81.61 465	65.34 455	67.47 453	88.01 444	48.60 454	80.13 464	62.33 452	73.68 441	79.58 454

E-PMN		53.28 431	52.56 435	55.43 448	74.43 466	47.13 471	83.63 458	76.30 466	42.23 463	42.59 465	62.22 464	28.57 465	74.40 465	31.53 466	31.51 464	44.78 463

test2506		91.60 267	90.78 275	94.04 269	97.66 143	83.81 372	98.27 33	75.53 467	93.43 114	95.23 150	98.21 82	67.21 410	99.07 175	93.01 181	98.49 123	99.25 76

EMVS		52.08 433	51.31 436	54.39 449	72.62 468	45.39 473	83.84 457	75.51 468	41.13 464	40.77 466	59.65 465	30.08 463	73.60 466	28.31 468	29.90 466	44.18 464

test_vis3_rt		72.73 418	70.55 421	79.27 432	80.02 461	68.13 455	93.92 391	74.30 469	76.90 440	58.99 460	73.58 460	20.29 469	95.37 425	84.16 355	72.80 443	74.31 457

MVE	50.73 23	53.25 432	48.81 437	66.58 447	65.34 471	57.50 466	72.49 461	70.94 470	40.15 465	39.28 467	63.51 463	6.89 474	73.48 467	38.29 463	42.38 463	68.76 461
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 434	53.82 434	46.29 450	33.73 474	45.30 474	78.32 460	67.24 471	18.02 467	50.93 463	87.05 448	52.99 449	53.11 469	70.76 442	25.29 467	40.46 465

kuosan		65.27 428	64.66 430	67.11 446	83.80 455	61.32 464	88.53 450	60.77 472	68.22 453	67.67 451	80.52 455	49.12 453	70.76 468	29.67 467	53.64 462	69.26 460

dongtai		69.99 422	69.33 424	71.98 443	88.78 443	61.64 463	89.86 442	59.93 473	75.67 442	74.96 444	85.45 449	50.19 452	81.66 462	43.86 461	55.27 460	72.63 458

N_pmnet		78.73 415	78.71 416	78.79 433	92.80 411	46.50 472	94.14 383	43.71 474	78.61 435	80.83 424	91.66 416	74.94 352	96.36 407	67.24 448	84.45 390	93.50 406

wuyk23d		25.11 435	24.57 439	26.74 451	73.98 467	39.89 475	57.88 464	9.80 475	12.27 468	10.39 469	6.97 471	7.03 473	36.44 470	25.43 469	17.39 468	3.89 468

testmvs		13.36 437	16.33 440	4.48 453	5.04 475	2.26 478	93.18 410	3.28 476	2.70 469	8.24 470	21.66 467	2.29 476	2.19 471	7.58 470	2.96 469	9.00 467

test123		13.04 438	15.66 441	5.18 452	4.51 476	3.45 477	92.50 424	1.81 477	2.50 470	7.58 471	20.15 468	3.67 475	2.18 472	7.13 471	1.07 470	9.90 466

mmdepth		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

monomultidepth		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

test_blank		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uanet_test		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

DCPMVS		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

pcd_1.5k_mvsjas		7.39 440	9.85 443	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	88.65 105	0.00 473	0.00 472	0.00 471	0.00 469

sosnet-low-res		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

sosnet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uncertanet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

Regformer		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

n2								0.00 478

nn								0.00 478

ab-mvs-re		8.06 439	10.74 442	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	96.69 208	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uanet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

WAC-MVS						79.53 424								75.56 422

PC_three_1452									90.77 225	98.89 24	98.28 80	96.24 1	98.35 266	95.76 100	99.58 23	99.59 28

eth-test2					0.00 477

eth-test					0.00 477

OPU-MVS				98.55 3	98.82 57	96.86 3	98.25 36				98.26 81	96.04 2	99.24 143	95.36 114	99.59 19	99.56 36

test_0728_THIRD									94.78 59	98.73 28	98.87 29	95.87 4	99.84 23	97.45 44	99.72 2	99.77 2

GSMVS																98.45 172

test_part2					99.28 27	95.74 8				98.10 42

sam_mvs1												82.76 227				98.45 172

sam_mvs												81.94 248

test_post1							92.81 420				16.58 470	80.53 274	97.68 349	86.20 325

test_post											17.58 469	81.76 251	98.08 293

patchmatchnet-post											90.45 424	82.65 232	98.10 288

gm-plane-assit					93.22 402	78.89 432			84.82 387		93.52 377		98.64 236	87.72 293

test9_res														94.81 132	99.38 60	99.45 55

agg_prior2														93.94 155	99.38 60	99.50 48

test_prior4						93.66 58	96.42 263

test_prior2							96.35 272		92.80 149	96.03 120	97.59 148	92.01 47		95.01 122	99.38 60

旧先验2							95.94 302		81.66 419	97.34 64			98.82 203	92.26 187

新几何2							95.79 312

原ACMM2							95.67 318

testdata2													99.67 71	85.96 333

segment_acmp												92.89 30

testdata1							95.26 344		93.10 131

plane_prior7					96.21 255	89.98 205

plane_prior6					96.10 273	90.00 201						81.32 258

plane_prior4											96.64 211

plane_prior3						90.00 201			94.46 76	91.34 257

plane_prior2							97.74 106		94.85 51

plane_prior1					96.14 268

plane_prior						89.99 203	97.24 179		94.06 88						92.16 291

HQP5-MVS						89.33 235

HQP-NCC					95.86 281		96.65 244		93.55 105	90.14 281

ACMP_Plane					95.86 281		96.65 244		93.55 105	90.14 281

BP-MVS														92.13 195

HQP4-MVS										90.14 281			98.50 251			95.78 310

HQP2-MVS												80.95 262

NP-MVS					95.99 279	89.81 213					95.87 254

MDTV_nov1_ep13_2view						70.35 450	93.10 415		83.88 398	93.55 198		82.47 236		86.25 324		98.38 180

ACMMP++_ref															90.30 321

ACMMP++															91.02 310

Test By Simon												88.73 104

High-resolution multi-view benchmark