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 13	97.89 3	96.53 99	98.41 80	91.73 125	98.01 61	99.02 1	96.37 10	99.30 4	98.92 20	92.39 41	99.79 40	99.16 11	99.46 41	98.08 200

PGM-MVS		96.81 52	96.53 63	97.65 43	99.35 22	93.53 61	97.65 122	98.98 2	92.22 157	97.14 69	98.44 57	91.17 68	99.85 18	94.35 141	99.46 41	99.57 31

MVS_111021_HR		96.68 63	96.58 62	96.99 80	98.46 75	92.31 106	96.20 280	98.90 3	94.30 83	95.86 126	97.74 123	92.33 42	99.38 129	96.04 88	99.42 51	99.28 72

test_fmvsmconf_n		97.49 17	97.56 12	97.29 60	97.44 158	92.37 103	97.91 80	98.88 4	95.83 16	98.92 20	99.05 12	91.45 58	99.80 35	99.12 13	99.46 41	99.69 13

lecture		97.58 12	97.63 9	97.43 54	99.37 16	92.93 82	98.86 7	98.85 5	95.27 31	98.65 30	98.90 22	91.97 49	99.80 35	97.63 35	99.21 76	99.57 31

ACMMP		96.27 80	95.93 83	97.28 62	99.24 30	92.62 94	98.25 36	98.81 6	92.99 132	94.56 161	98.39 61	88.96 97	99.85 18	94.57 139	97.63 156	99.36 67
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 81	96.19 79	96.39 117	98.23 98	91.35 146	96.24 278	98.79 7	93.99 90	95.80 128	97.65 131	89.92 87	99.24 142	95.87 92	99.20 81	98.58 150

patch_mono-2		96.83 51	97.44 20	95.01 202	99.05 41	85.39 336	96.98 205	98.77 8	94.70 63	97.99 44	98.66 40	93.61 19	99.91 1	97.67 34	99.50 35	99.72 12

fmvsm_s_conf0.5_n		96.85 48	97.13 25	96.04 141	98.07 113	90.28 192	97.97 72	98.76 9	94.93 45	98.84 25	99.06 11	88.80 101	99.65 72	99.06 15	98.63 116	98.18 186

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 57	98.21 99	92.75 88	97.83 92	98.73 10	95.04 42	99.30 4	98.84 33	93.34 22	99.78 43	99.32 5	99.13 91	99.50 47

fmvsm_s_conf0.5_n_a		96.75 56	96.93 40	96.20 133	97.64 144	90.72 176	98.00 62	98.73 10	94.55 70	98.91 21	99.08 7	88.22 113	99.63 81	98.91 18	98.37 129	98.25 181

FC-MVSNet-test		93.94 161	93.57 153	95.04 200	95.48 288	91.45 143	98.12 51	98.71 12	93.37 115	90.23 268	96.70 194	87.66 123	97.85 321	91.49 202	90.39 310	95.83 294

UniMVSNet (Re)		93.31 183	92.55 196	95.61 172	95.39 294	93.34 67	97.39 164	98.71 12	93.14 128	90.10 277	94.83 296	87.71 122	98.03 294	91.67 200	83.99 382	95.46 313

fmvsm_l_conf0.5_n_a		97.63 9	97.76 5	97.26 64	98.25 93	92.59 96	97.81 97	98.68 14	94.93 45	99.24 7	98.87 28	93.52 20	99.79 40	99.32 5	99.21 76	99.40 61

FIs		94.09 152	93.70 149	95.27 190	95.70 277	92.03 118	98.10 52	98.68 14	93.36 117	90.39 265	96.70 194	87.63 126	97.94 312	92.25 180	90.50 309	95.84 293

WR-MVS_H		92.00 240	91.35 237	93.95 266	95.09 321	89.47 220	98.04 59	98.68 14	91.46 185	88.34 328	94.68 303	85.86 156	97.56 350	85.77 323	84.24 380	94.82 358

fmvsm_s_conf0.5_n_4		96.75 56	97.07 28	95.79 159	97.76 135	89.57 214	97.66 121	98.66 17	95.36 27	99.03 13	98.90 22	88.39 109	99.73 54	99.17 10	98.66 114	98.08 200

VPA-MVSNet		93.24 185	92.48 201	95.51 178	95.70 277	92.39 102	97.86 85	98.66 17	92.30 155	92.09 226	95.37 271	80.49 263	98.40 248	93.95 147	85.86 353	95.75 302

fmvsm_l_conf0.5_n_3		97.64 8	97.60 10	97.79 30	98.14 106	93.94 52	97.93 78	98.65 19	96.70 5	99.38 2	99.07 10	89.92 87	99.81 30	99.16 11	99.43 48	99.61 25

fmvsm_s_conf0.5_n_3		97.15 30	97.36 22	96.52 101	97.98 119	91.19 154	97.84 89	98.65 19	97.08 4	99.25 6	99.10 5	87.88 120	99.79 40	99.32 5	99.18 83	98.59 149

fmvsm_s_conf0.5_n_8		97.32 24	97.48 19	96.85 82	98.28 89	91.07 162	97.76 102	98.62 21	97.53 2	99.20 9	99.12 4	88.24 112	99.81 30	99.41 3	99.17 84	99.67 14

fmvsm_s_conf0.5_n_2		96.62 64	96.82 49	96.02 143	97.98 119	90.43 186	97.50 145	98.59 22	96.59 7	99.31 3	99.08 7	84.47 179	99.75 51	99.37 4	98.45 126	97.88 213

UniMVSNet_NR-MVSNet		93.37 181	92.67 190	95.47 183	95.34 300	92.83 85	97.17 188	98.58 23	92.98 137	90.13 273	95.80 247	88.37 111	97.85 321	91.71 197	83.93 383	95.73 304

CSCG		96.05 84	95.91 84	96.46 111	99.24 30	90.47 183	98.30 29	98.57 24	89.01 275	93.97 178	97.57 141	92.62 37	99.76 47	94.66 133	99.27 69	99.15 82

fmvsm_s_conf0.5_n_9		97.33 23	97.57 11	96.62 95	98.43 78	90.32 191	97.80 98	98.53 25	97.24 3	99.62 1	99.14 1	88.65 104	99.80 35	99.54 1	99.15 88	99.74 8

fmvsm_s_conf0.5_n_6		97.08 33	97.17 24	96.81 83	97.28 163	91.73 125	97.75 104	98.50 26	94.86 49	99.22 8	98.78 37	89.75 90	99.76 47	99.10 14	99.29 67	98.94 110

MSLP-MVS++		96.94 42	97.06 29	96.59 96	98.72 60	91.86 123	97.67 118	98.49 27	94.66 66	97.24 65	98.41 60	92.31 44	98.94 188	96.61 64	99.46 41	98.96 106

HyFIR lowres test		93.66 172	92.92 178	95.87 152	98.24 94	89.88 205	94.58 353	98.49 27	85.06 371	93.78 181	95.78 251	82.86 214	98.67 224	91.77 195	95.71 209	99.07 93

CHOSEN 1792x2688		94.15 147	93.51 159	96.06 139	98.27 90	89.38 225	95.18 339	98.48 29	85.60 361	93.76 182	97.11 170	83.15 204	99.61 83	91.33 205	98.72 112	99.19 78

fmvsm_s_conf0.5_n_7		96.45 71	96.80 51	95.37 186	97.29 162	88.38 257	97.23 182	98.47 30	95.14 36	98.43 35	99.09 6	87.58 127	99.72 58	98.80 22	99.21 76	98.02 204

fmvsm_s_conf0.5_n_5		97.00 39	96.97 37	97.09 75	97.58 154	92.56 97	97.68 117	98.47 30	94.02 88	98.90 22	98.89 25	88.94 98	99.78 43	99.18 9	99.03 100	98.93 114

PHI-MVS		96.77 54	96.46 70	97.71 41	98.40 81	94.07 48	98.21 43	98.45 32	89.86 247	97.11 71	98.01 97	92.52 39	99.69 66	96.03 89	99.53 29	99.36 67

fmvsm_s_conf0.1_n		96.58 67	96.77 54	96.01 146	96.67 211	90.25 193	97.91 80	98.38 33	94.48 74	98.84 25	99.14 1	88.06 115	99.62 82	98.82 20	98.60 118	98.15 190

PVSNet_BlendedMVS		94.06 153	93.92 143	94.47 235	98.27 90	89.46 222	96.73 229	98.36 34	90.17 239	94.36 166	95.24 279	88.02 116	99.58 91	93.44 158	90.72 305	94.36 378

PVSNet_Blended		94.87 126	94.56 124	95.81 157	98.27 90	89.46 222	95.47 322	98.36 34	88.84 283	94.36 166	96.09 236	88.02 116	99.58 91	93.44 158	98.18 138	98.40 170

3Dnovator	91.36 5	95.19 114	94.44 132	97.44 53	96.56 221	93.36 66	98.65 12	98.36 34	94.12 85	89.25 307	98.06 91	82.20 231	99.77 46	93.41 160	99.32 65	99.18 79

FOURS1					99.55 1	93.34 67	99.29 1	98.35 37	94.98 43	98.49 33

DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 34	95.78 7	97.21 185	98.35 37	95.16 35	98.71 29	98.80 35	95.05 10	99.89 3	96.70 62	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 73	96.47 67	96.16 135	95.48 288	90.69 177	97.91 80	98.33 39	94.07 86	98.93 17	99.14 1	87.44 134	99.61 83	98.63 23	98.32 131	98.18 186

HFP-MVS		97.14 31	96.92 41	97.83 26	99.42 7	94.12 46	98.52 16	98.32 40	93.21 120	97.18 66	98.29 77	92.08 46	99.83 26	95.63 105	99.59 19	99.54 40

ACMMPR		97.07 35	96.84 45	97.79 30	99.44 6	93.88 53	98.52 16	98.31 41	93.21 120	97.15 68	98.33 71	91.35 62	99.86 9	95.63 105	99.59 19	99.62 22

test_fmvsmvis_n_1920		96.70 59	96.84 45	96.31 122	96.62 213	91.73 125	97.98 66	98.30 42	96.19 11	96.10 116	98.95 18	89.42 91	99.76 47	98.90 19	99.08 95	97.43 240

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 35	94.82 28	98.81 8	98.30 42	94.76 61	98.30 37	98.90 22	93.77 17	99.68 68	97.93 26	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 44	94.92 47	98.99 15	98.92 20	95.08 8

MSP-MVS		97.59 11	97.54 13	97.73 38	99.40 11	93.77 57	98.53 15	98.29 44	95.55 24	98.56 32	97.81 118	93.90 15	99.65 72	96.62 63	99.21 76	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 46	94.78 58	98.93 17	98.87 28	96.04 2	99.86 9	97.45 43	99.58 23	99.59 27

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 46					99.86 9	97.52 39	99.67 6	99.75 6

CP-MVS		97.02 37	96.81 50	97.64 45	99.33 23	93.54 60	98.80 9	98.28 46	92.99 132	96.45 103	98.30 76	91.90 50	99.85 18	95.61 107	99.68 4	99.54 40

test_fmvsmconf0.1_n		97.09 32	97.06 29	97.19 69	95.67 279	92.21 110	97.95 75	98.27 49	95.78 20	98.40 36	99.00 14	89.99 85	99.78 43	99.06 15	99.41 54	99.59 27

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 49	95.13 37	99.19 10	98.89 25	95.54 5	99.85 18	97.52 39	99.66 10	99.56 35

test_241102_TWO								98.27 49	95.13 37	98.93 17	98.89 25	94.99 11	99.85 18	97.52 39	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 49	95.09 40	99.19 10	98.81 34	95.54 5	99.65 72

SF-MVS		97.39 20	97.13 25	98.17 15	99.02 44	95.28 19	98.23 40	98.27 49	92.37 154	98.27 38	98.65 42	93.33 23	99.72 58	96.49 68	99.52 30	99.51 44

SteuartSystems-ACMMP		97.62 10	97.53 14	97.87 24	98.39 83	94.25 40	98.43 23	98.27 49	95.34 29	98.11 40	98.56 44	94.53 12	99.71 60	96.57 66	99.62 17	99.65 19
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 24	95.20 20		98.25 55	95.13 37	98.48 34	98.87 28	95.16 7

PVSNet_Blended_VisFu		95.27 108	94.91 113	96.38 118	98.20 100	90.86 170	97.27 176	98.25 55	90.21 238	94.18 171	97.27 159	87.48 133	99.73 54	93.53 155	97.77 154	98.55 151

region2R		97.07 35	96.84 45	97.77 34	99.46 2	93.79 55	98.52 16	98.24 57	93.19 123	97.14 69	98.34 68	91.59 57	99.87 7	95.46 111	99.59 19	99.64 20

PS-CasMVS		91.55 260	90.84 261	93.69 282	94.96 325	88.28 260	97.84 89	98.24 57	91.46 185	88.04 339	95.80 247	79.67 279	97.48 358	87.02 303	84.54 377	95.31 327

DU-MVS		92.90 203	92.04 212	95.49 180	94.95 326	92.83 85	97.16 189	98.24 57	93.02 131	90.13 273	95.71 254	83.47 196	97.85 321	91.71 197	83.93 383	95.78 298

9.14			96.75 55		98.93 52		97.73 108	98.23 60	91.28 194	97.88 48	98.44 57	93.00 26	99.65 72	95.76 98	99.47 40

reproduce_model		97.51 16	97.51 16	97.50 50	98.99 48	93.01 78	97.79 100	98.21 61	95.73 21	97.99 44	99.03 13	92.63 36	99.82 28	97.80 28	99.42 51	99.67 14

D2MVS		91.30 277	90.95 255	92.35 330	94.71 341	85.52 332	96.18 282	98.21 61	88.89 281	86.60 368	93.82 352	79.92 275	97.95 310	89.29 252	90.95 302	93.56 393

reproduce-ours		97.53 14	97.51 16	97.60 47	98.97 49	93.31 69	97.71 113	98.20 63	95.80 18	97.88 48	98.98 16	92.91 27	99.81 30	97.68 30	99.43 48	99.67 14

our_new_method		97.53 14	97.51 16	97.60 47	98.97 49	93.31 69	97.71 113	98.20 63	95.80 18	97.88 48	98.98 16	92.91 27	99.81 30	97.68 30	99.43 48	99.67 14

SDMVSNet		94.17 145	93.61 152	95.86 154	98.09 109	91.37 145	97.35 168	98.20 63	93.18 125	91.79 234	97.28 157	79.13 287	98.93 189	94.61 136	92.84 268	97.28 248

XVS		97.18 28	96.96 39	97.81 28	99.38 14	94.03 50	98.59 13	98.20 63	94.85 50	96.59 92	98.29 77	91.70 53	99.80 35	95.66 100	99.40 56	99.62 22

X-MVStestdata		91.71 249	89.67 315	97.81 28	99.38 14	94.03 50	98.59 13	98.20 63	94.85 50	96.59 92	32.69 453	91.70 53	99.80 35	95.66 100	99.40 56	99.62 22

ACMMP_NAP		97.20 27	96.86 43	98.23 11	99.09 36	95.16 22	97.60 131	98.19 68	92.82 144	97.93 47	98.74 39	91.60 56	99.86 9	96.26 72	99.52 30	99.67 14

CP-MVSNet		91.89 245	91.24 244	93.82 274	95.05 322	88.57 250	97.82 94	98.19 68	91.70 175	88.21 334	95.76 252	81.96 236	97.52 356	87.86 278	84.65 371	95.37 323

ZNCC-MVS		96.96 40	96.67 58	97.85 25	99.37 16	94.12 46	98.49 20	98.18 70	92.64 150	96.39 105	98.18 84	91.61 55	99.88 4	95.59 110	99.55 26	99.57 31

SMA-MVS		97.35 21	97.03 34	98.30 8	99.06 40	95.42 10	97.94 76	98.18 70	90.57 230	98.85 24	98.94 19	93.33 23	99.83 26	96.72 60	99.68 4	99.63 21
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		91.20 282	90.44 278	93.48 293	94.49 349	87.91 275	97.76 102	98.18 70	91.29 191	87.78 343	95.74 253	80.35 266	97.33 369	85.46 327	82.96 393	95.19 338

DELS-MVS		96.61 65	96.38 74	97.30 59	97.79 133	93.19 74	95.96 293	98.18 70	95.23 32	95.87 125	97.65 131	91.45 58	99.70 65	95.87 92	99.44 47	99.00 101
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		89.70 334	88.40 340	93.60 286	95.15 317	90.10 195	97.56 136	98.16 74	87.28 334	86.16 374	94.63 307	77.57 315	98.05 290	74.48 413	84.59 375	92.65 406

VNet		95.89 92	95.45 95	97.21 67	98.07 113	92.94 81	97.50 145	98.15 75	93.87 94	97.52 55	97.61 137	85.29 166	99.53 105	95.81 97	95.27 221	99.16 80

DeepPCF-MVS	93.97 1	96.61 65	97.09 27	95.15 194	98.09 109	86.63 306	96.00 291	98.15 75	95.43 25	97.95 46	98.56 44	93.40 21	99.36 130	96.77 57	99.48 39	99.45 54

SD-MVS		97.41 19	97.53 14	97.06 78	98.57 74	94.46 34	97.92 79	98.14 77	94.82 54	99.01 14	98.55 46	94.18 14	97.41 365	96.94 52	99.64 14	99.32 69
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 48	96.52 64	97.82 27	99.36 20	94.14 45	98.29 30	98.13 78	92.72 147	96.70 84	98.06 91	91.35 62	99.86 9	94.83 127	99.28 68	99.47 53

UA-Net		95.95 89	95.53 91	97.20 68	97.67 140	92.98 80	97.65 122	98.13 78	94.81 56	96.61 90	98.35 65	88.87 99	99.51 110	90.36 227	97.35 166	99.11 88

QAPM		93.45 179	92.27 206	96.98 81	96.77 206	92.62 94	98.39 25	98.12 80	84.50 379	88.27 332	97.77 121	82.39 228	99.81 30	85.40 328	98.81 108	98.51 156

Vis-MVSNet		95.23 111	94.81 114	96.51 105	97.18 168	91.58 136	98.26 35	98.12 80	94.38 81	94.90 151	98.15 86	82.28 229	98.92 191	91.45 204	98.58 120	99.01 98
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 206	91.68 227	96.40 115	95.34 300	92.73 90	98.27 33	98.12 80	84.86 374	85.78 376	97.75 122	78.89 297	99.74 52	87.50 293	98.65 115	96.73 265

TranMVSNet+NR-MVSNet		92.50 215	91.63 228	95.14 195	94.76 337	92.07 115	97.53 142	98.11 83	92.90 141	89.56 295	96.12 231	83.16 203	97.60 348	89.30 251	83.20 392	95.75 302

CPTT-MVS		95.57 102	95.19 105	96.70 86	99.27 28	91.48 140	98.33 27	98.11 83	87.79 319	95.17 147	98.03 94	87.09 140	99.61 83	93.51 156	99.42 51	99.02 95

APD-MVS		96.95 41	96.60 60	98.01 20	99.03 43	94.93 27	97.72 111	98.10 85	91.50 183	98.01 43	98.32 73	92.33 42	99.58 91	94.85 125	99.51 33	99.53 43
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 46	96.60 60	97.64 45	99.40 11	93.44 62	98.50 19	98.09 86	93.27 119	95.95 123	98.33 71	91.04 70	99.88 4	95.20 114	99.57 25	99.60 26

ZD-MVS					99.05 41	94.59 32		98.08 87	89.22 268	97.03 74	98.10 87	92.52 39	99.65 72	94.58 138	99.31 66

MTGPA								98.08 87

MTAPA		97.08 33	96.78 53	97.97 23	99.37 16	94.42 36	97.24 178	98.08 87	95.07 41	96.11 115	98.59 43	90.88 75	99.90 2	96.18 84	99.50 35	99.58 30

CNVR-MVS		97.68 6	97.44 20	98.37 7	98.90 55	95.86 6	97.27 176	98.08 87	95.81 17	97.87 51	98.31 74	94.26 13	99.68 68	97.02 51	99.49 38	99.57 31

DP-MVS Recon		95.68 97	95.12 109	97.37 56	99.19 33	94.19 42	97.03 196	98.08 87	88.35 301	95.09 149	97.65 131	89.97 86	99.48 117	92.08 189	98.59 119	98.44 167

SR-MVS		97.01 38	96.86 43	97.47 52	99.09 36	93.27 71	97.98 66	98.07 92	93.75 97	97.45 57	98.48 54	91.43 60	99.59 88	96.22 75	99.27 69	99.54 40

MCST-MVS		97.18 28	96.84 45	98.20 14	99.30 26	95.35 15	97.12 192	98.07 92	93.54 107	96.08 117	97.69 126	93.86 16	99.71 60	96.50 67	99.39 58	99.55 38

NR-MVSNet		92.34 224	91.27 243	95.53 177	94.95 326	93.05 77	97.39 164	98.07 92	92.65 149	84.46 387	95.71 254	85.00 172	97.77 332	89.71 239	83.52 389	95.78 298

MP-MVS-pluss		96.70 59	96.27 77	97.98 22	99.23 32	94.71 29	96.96 207	98.06 95	90.67 220	95.55 139	98.78 37	91.07 69	99.86 9	96.58 65	99.55 26	99.38 65
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 52	96.71 57	97.12 72	99.01 47	92.31 106	97.98 66	98.06 95	93.11 129	97.44 58	98.55 46	90.93 73	99.55 101	96.06 85	99.25 73	99.51 44

MP-MVS		96.77 54	96.45 71	97.72 39	99.39 13	93.80 54	98.41 24	98.06 95	93.37 115	95.54 141	98.34 68	90.59 79	99.88 4	94.83 127	99.54 28	99.49 49
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 68	96.27 77	97.22 66	99.32 24	92.74 89	98.74 10	98.06 95	90.57 230	96.77 81	98.35 65	90.21 82	99.53 105	94.80 130	99.63 16	99.38 65

HPM-MVS		96.69 61	96.45 71	97.40 55	99.36 20	93.11 76	98.87 6	98.06 95	91.17 201	96.40 104	97.99 98	90.99 71	99.58 91	95.61 107	99.61 18	99.49 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 137	93.80 145	96.64 88	97.07 174	91.97 120	96.32 270	98.06 95	88.94 279	94.50 163	96.78 189	84.60 176	99.27 140	91.90 190	96.02 199	98.68 143

DeepC-MVS	93.07 3	96.06 83	95.66 88	97.29 60	97.96 121	93.17 75	97.30 174	98.06 95	93.92 92	93.38 194	98.66 40	86.83 142	99.73 54	95.60 109	99.22 75	98.96 106
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 25	97.03 34	98.11 17	98.77 58	95.06 25	97.34 169	98.04 102	95.96 12	97.09 72	97.88 109	93.18 25	99.71 60	95.84 96	99.17 84	99.56 35

DeepC-MVS_fast	93.89 2	96.93 43	96.64 59	97.78 32	98.64 69	94.30 37	97.41 159	98.04 102	94.81 56	96.59 92	98.37 63	91.24 65	99.64 80	95.16 116	99.52 30	99.42 60
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 45	96.80 51	97.11 74	99.02 44	92.34 104	97.98 66	98.03 104	93.52 110	97.43 60	98.51 49	91.40 61	99.56 99	96.05 86	99.26 71	99.43 58

RE-MVS-def			96.72 56		99.02 44	92.34 104	97.98 66	98.03 104	93.52 110	97.43 60	98.51 49	90.71 77		96.05 86	99.26 71	99.43 58

RPMNet		88.98 340	87.05 354	94.77 220	94.45 351	87.19 291	90.23 428	98.03 104	77.87 426	92.40 212	87.55 433	80.17 270	99.51 110	68.84 433	93.95 254	97.60 233

save fliter					98.91 54	94.28 38	97.02 198	98.02 107	95.35 28

TEST9					98.70 61	94.19 42	96.41 257	98.02 107	88.17 305	96.03 118	97.56 143	92.74 33	99.59 88

train_agg		96.30 79	95.83 87	97.72 39	98.70 61	94.19 42	96.41 257	98.02 107	88.58 292	96.03 118	97.56 143	92.73 34	99.59 88	95.04 118	99.37 62	99.39 63

test_8					98.67 63	94.06 49	96.37 264	98.01 110	88.58 292	95.98 122	97.55 145	92.73 34	99.58 91

agg_prior					98.67 63	93.79 55		98.00 111		95.68 135			99.57 98

test_prior				97.23 65	98.67 63	92.99 79		98.00 111					99.41 125			99.29 70

WR-MVS		92.34 224	91.53 232	94.77 220	95.13 319	90.83 171	96.40 261	97.98 113	91.88 170	89.29 304	95.54 265	82.50 224	97.80 328	89.79 238	85.27 362	95.69 305

HPM-MVS++		97.34 22	96.97 37	98.47 5	99.08 38	96.16 4	97.55 141	97.97 114	95.59 22	96.61 90	97.89 107	92.57 38	99.84 23	95.95 91	99.51 33	99.40 61

CANet		96.39 74	96.02 82	97.50 50	97.62 147	93.38 64	97.02 198	97.96 115	95.42 26	94.86 152	97.81 118	87.38 136	99.82 28	96.88 54	99.20 81	99.29 70

114514_t		93.95 160	93.06 174	96.63 92	99.07 39	91.61 133	97.46 156	97.96 115	77.99 424	93.00 203	97.57 141	86.14 154	99.33 132	89.22 255	99.15 88	98.94 110

IU-MVS					99.42 7	95.39 11		97.94 117	90.40 236	98.94 16				97.41 46	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 63	96.94 1		97.93 118					99.86 9	97.68 30	99.67 6	99.77 2

No_MVS				98.86 1	98.67 63	96.94 1		97.93 118					99.86 9	97.68 30	99.67 6	99.77 2

fmvsm_s_conf0.1_n_2		96.33 78	96.44 73	96.00 147	97.30 161	90.37 190	97.53 142	97.92 120	96.52 8	99.14 12	99.08 7	83.21 201	99.74 52	99.22 8	98.06 143	97.88 213

Anonymous20231211		90.63 306	89.42 322	94.27 249	98.24 94	89.19 237	98.05 58	97.89 121	79.95 416	88.25 333	94.96 288	72.56 356	98.13 273	89.70 240	85.14 364	95.49 309

原ACMM1				96.38 118	98.59 71	91.09 161		97.89 121	87.41 330	95.22 146	97.68 127	90.25 81	99.54 103	87.95 277	99.12 93	98.49 159

CDPH-MVS		95.97 88	95.38 100	97.77 34	98.93 52	94.44 35	96.35 265	97.88 123	86.98 338	96.65 88	97.89 107	91.99 48	99.47 118	92.26 178	99.46 41	99.39 63

test11								97.88 123

EIA-MVS		95.53 103	95.47 94	95.71 167	97.06 177	89.63 210	97.82 94	97.87 125	93.57 103	93.92 179	95.04 285	90.61 78	98.95 186	94.62 135	98.68 113	98.54 152

CS-MVS		96.86 46	97.06 29	96.26 128	98.16 105	91.16 159	99.09 3	97.87 125	95.30 30	97.06 73	98.03 94	91.72 51	98.71 221	97.10 49	99.17 84	98.90 119

无先验							95.79 303	97.87 125	83.87 387				99.65 72	87.68 287		98.89 123

3Dnovator+	91.43 4	95.40 104	94.48 130	98.16 16	96.90 191	95.34 16	98.48 21	97.87 125	94.65 67	88.53 324	98.02 96	83.69 192	99.71 60	93.18 164	98.96 103	99.44 56

VPNet		92.23 232	91.31 240	94.99 203	95.56 284	90.96 165	97.22 184	97.86 129	92.96 138	90.96 256	96.62 206	75.06 336	98.20 267	91.90 190	83.65 388	95.80 296

test_vis1_n_1920		94.17 145	94.58 123	92.91 314	97.42 159	82.02 383	97.83 92	97.85 130	94.68 64	98.10 41	98.49 51	70.15 375	99.32 134	97.91 27	98.82 107	97.40 242

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 130	94.92 47	98.73 27	98.87 28	95.08 8	99.84 23	97.52 39	99.67 6	99.48 51
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 18	97.33 23	97.69 42	99.25 29	94.24 41	98.07 56	97.85 130	93.72 98	98.57 31	98.35 65	93.69 18	99.40 126	97.06 50	99.46 41	99.44 56
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 44	97.04 33	96.45 112	98.29 88	91.66 132	99.03 4	97.85 130	95.84 15	96.90 76	97.97 100	91.24 65	98.75 213	96.92 53	99.33 64	98.94 110

test_fmvsmconf0.01_n		96.15 82	95.85 86	97.03 79	92.66 402	91.83 124	97.97 72	97.84 134	95.57 23	97.53 54	99.00 14	84.20 185	99.76 47	98.82 20	99.08 95	99.48 51

GDP-MVS		95.62 99	95.13 107	97.09 75	96.79 202	93.26 72	97.89 83	97.83 135	93.58 102	96.80 78	97.82 117	83.06 208	99.16 154	94.40 140	97.95 149	98.87 125

balanced_conf03		96.84 50	96.89 42	96.68 87	97.63 146	92.22 109	98.17 49	97.82 136	94.44 76	98.23 39	97.36 154	90.97 72	99.22 144	97.74 29	99.66 10	98.61 146

AdaColmap		94.34 141	93.68 150	96.31 122	98.59 71	91.68 131	96.59 248	97.81 137	89.87 246	92.15 222	97.06 173	83.62 195	99.54 103	89.34 250	98.07 142	97.70 226

MVSMamba_PlusPlus		96.51 68	96.48 66	96.59 96	98.07 113	91.97 120	98.14 50	97.79 138	90.43 234	97.34 63	97.52 146	91.29 64	99.19 147	98.12 25	99.64 14	98.60 147

KinetiMVS		95.26 109	94.75 118	96.79 84	96.99 186	92.05 116	97.82 94	97.78 139	94.77 60	96.46 101	97.70 125	80.62 260	99.34 131	92.37 177	98.28 133	98.97 103

mamv4		94.66 134	96.10 81	90.37 383	98.01 116	73.41 433	96.82 220	97.78 139	89.95 245	94.52 162	97.43 150	92.91 27	99.09 167	98.28 24	99.16 87	98.60 147

ETV-MVS		96.02 85	95.89 85	96.40 115	97.16 169	92.44 101	97.47 154	97.77 141	94.55 70	96.48 99	94.51 313	91.23 67	98.92 191	95.65 103	98.19 137	97.82 221

新几何1				97.32 58	98.60 70	93.59 59		97.75 142	81.58 407	95.75 130	97.85 113	90.04 84	99.67 70	86.50 309	99.13 91	98.69 142

旧先验1					98.38 84	93.38 64		97.75 142			98.09 89	92.30 45			99.01 101	99.16 80

EC-MVSNet		96.42 72	96.47 67	96.26 128	97.01 184	91.52 138	98.89 5	97.75 142	94.42 77	96.64 89	97.68 127	89.32 92	98.60 232	97.45 43	99.11 94	98.67 144

EI-MVSNet-Vis-set		96.51 68	96.47 67	96.63 92	98.24 94	91.20 153	96.89 212	97.73 145	94.74 62	96.49 98	98.49 51	90.88 75	99.58 91	96.44 69	98.32 131	99.13 84

PAPM_NR		95.01 117	94.59 122	96.26 128	98.89 56	90.68 178	97.24 178	97.73 145	91.80 171	92.93 208	96.62 206	89.13 95	99.14 159	89.21 256	97.78 153	98.97 103

Anonymous20240529		91.98 241	90.73 268	95.73 165	98.14 106	89.40 224	97.99 63	97.72 147	79.63 418	93.54 188	97.41 152	69.94 377	99.56 99	91.04 212	91.11 298	98.22 183

CHOSEN 280x420		93.12 191	92.72 189	94.34 243	96.71 210	87.27 287	90.29 427	97.72 147	86.61 345	91.34 245	95.29 273	84.29 184	98.41 247	93.25 162	98.94 104	97.35 245

EI-MVSNet-UG-set		96.34 77	96.30 76	96.47 109	98.20 100	90.93 167	96.86 215	97.72 147	94.67 65	96.16 114	98.46 55	90.43 80	99.58 91	96.23 74	97.96 148	98.90 119

LS3D		93.57 175	92.61 194	96.47 109	97.59 150	91.61 133	97.67 118	97.72 147	85.17 369	90.29 267	98.34 68	84.60 176	99.73 54	83.85 351	98.27 134	98.06 202

PAPR		94.18 144	93.42 165	96.48 108	97.64 144	91.42 144	95.55 317	97.71 151	88.99 276	92.34 218	95.82 246	89.19 93	99.11 162	86.14 315	97.38 164	98.90 119

UGNet		94.04 155	93.28 168	96.31 122	96.85 194	91.19 154	97.88 84	97.68 152	94.40 79	93.00 203	96.18 226	73.39 353	99.61 83	91.72 196	98.46 125	98.13 191
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				95.46 184	98.18 104	88.90 243		97.66 153	82.73 398	97.03 74	98.07 90	90.06 83	98.85 198	89.67 241	98.98 102	98.64 145

test12				97.65 43	98.46 75	94.26 39		97.66 153		95.52 142		90.89 74	99.46 119		99.25 73	99.22 77

DTE-MVSNet		90.56 307	89.75 313	93.01 310	93.95 364	87.25 288	97.64 126	97.65 155	90.74 215	87.12 356	95.68 257	79.97 274	97.00 382	83.33 352	81.66 399	94.78 365

TAPA-MVS	90.10 7	92.30 227	91.22 246	95.56 174	98.33 86	89.60 212	96.79 222	97.65 155	81.83 404	91.52 240	97.23 162	87.94 118	98.91 193	71.31 428	98.37 129	98.17 189
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 192	92.45 202	95.05 199	98.09 109	89.21 234	96.89 212	97.64 157	93.18 125	91.79 234	97.28 157	75.35 335	98.65 227	88.99 261	92.84 268	97.28 248

test_cas_vis1_n_1920		94.48 139	94.55 127	94.28 248	96.78 204	86.45 311	97.63 128	97.64 157	93.32 118	97.68 53	98.36 64	73.75 351	99.08 170	96.73 59	99.05 97	97.31 247

NormalMVS		96.36 76	96.11 80	97.12 72	99.37 16	92.90 83	97.99 63	97.63 159	95.92 13	96.57 95	97.93 102	85.34 164	99.50 113	94.99 121	99.21 76	98.97 103

Elysia		94.00 157	93.12 171	96.64 88	96.08 263	92.72 91	97.50 145	97.63 159	91.15 203	94.82 153	97.12 168	74.98 338	99.06 176	90.78 215	98.02 144	98.12 193

StellarMVS		94.00 157	93.12 171	96.64 88	96.08 263	92.72 91	97.50 145	97.63 159	91.15 203	94.82 153	97.12 168	74.98 338	99.06 176	90.78 215	98.02 144	98.12 193

cdsmvs_eth3d_5k		23.24 423	30.99 425	0.00 441	0.00 464	0.00 466	0.00 452	97.63 159	0.00 459	0.00 460	96.88 185	84.38 181	0.00 460	0.00 459	0.00 458	0.00 456

DPM-MVS		95.69 96	94.92 112	98.01 20	98.08 112	95.71 9	95.27 333	97.62 163	90.43 234	95.55 139	97.07 172	91.72 51	99.50 113	89.62 243	98.94 104	98.82 131

sasdasda		96.02 85	95.45 95	97.75 36	97.59 150	95.15 23	98.28 31	97.60 164	94.52 72	96.27 109	96.12 231	87.65 124	99.18 150	96.20 80	94.82 230	98.91 116

canonicalmvs		96.02 85	95.45 95	97.75 36	97.59 150	95.15 23	98.28 31	97.60 164	94.52 72	96.27 109	96.12 231	87.65 124	99.18 150	96.20 80	94.82 230	98.91 116

test222					98.24 94	92.21 110	95.33 328	97.60 164	79.22 420	95.25 144	97.84 115	88.80 101			99.15 88	98.72 139

cascas		91.20 282	90.08 295	94.58 229	94.97 324	89.16 238	93.65 392	97.59 167	79.90 417	89.40 299	92.92 378	75.36 334	98.36 255	92.14 183	94.75 233	96.23 275

h-mvs33		94.15 147	93.52 158	96.04 141	97.81 132	90.22 194	97.62 130	97.58 168	95.19 33	96.74 82	97.45 147	83.67 193	99.61 83	95.85 94	79.73 406	98.29 179

MGCFI-Net		95.94 90	95.40 99	97.56 49	97.59 150	94.62 31	98.21 43	97.57 169	94.41 78	96.17 113	96.16 229	87.54 129	99.17 152	96.19 82	94.73 235	98.91 116

MVSFormer		95.37 105	95.16 106	95.99 148	96.34 243	91.21 151	98.22 41	97.57 169	91.42 187	96.22 111	97.32 155	86.20 152	97.92 315	94.07 144	99.05 97	98.85 127

test_djsdf		93.07 194	92.76 184	94.00 260	93.49 381	88.70 247	98.22 41	97.57 169	91.42 187	90.08 279	95.55 264	82.85 215	97.92 315	94.07 144	91.58 289	95.40 320

OMC-MVS		95.09 116	94.70 119	96.25 131	98.46 75	91.28 147	96.43 255	97.57 169	92.04 166	94.77 157	97.96 101	87.01 141	99.09 167	91.31 206	96.77 184	98.36 174

PS-MVSNAJss		93.74 170	93.51 159	94.44 237	93.91 366	89.28 232	97.75 104	97.56 173	92.50 151	89.94 281	96.54 209	88.65 104	98.18 270	93.83 153	90.90 303	95.86 290

casdiffmvs_mvg		95.81 95	95.57 89	96.51 105	96.87 192	91.49 139	97.50 145	97.56 173	93.99 90	95.13 148	97.92 105	87.89 119	98.78 207	95.97 90	97.33 167	99.26 74
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		92.42 220	91.89 220	94.03 259	93.33 389	88.50 254	97.73 108	97.53 175	92.00 168	88.85 316	96.50 211	75.62 333	98.11 277	93.88 151	91.56 290	95.48 310

mvs_tets		92.31 226	91.76 223	93.94 268	93.41 386	88.29 259	97.63 128	97.53 175	92.04 166	88.76 319	96.45 213	74.62 343	98.09 282	93.91 149	91.48 291	95.45 315

dcpmvs_2		96.37 75	97.05 32	94.31 246	98.96 51	84.11 357	97.56 136	97.51 177	93.92 92	97.43 60	98.52 48	92.75 32	99.32 134	97.32 48	99.50 35	99.51 44

HQP_MVS		93.78 169	93.43 163	94.82 213	96.21 247	89.99 199	97.74 106	97.51 177	94.85 50	91.34 245	96.64 199	81.32 248	98.60 232	93.02 170	92.23 277	95.86 290

plane_prior5								97.51 177					98.60 232	93.02 170	92.23 277	95.86 290

reproduce_monomvs		91.30 277	91.10 250	91.92 344	96.82 199	82.48 377	97.01 201	97.49 180	94.64 68	88.35 327	95.27 276	70.53 370	98.10 278	95.20 114	84.60 374	95.19 338

PS-MVSNAJ		95.37 105	95.33 102	95.49 180	97.35 160	90.66 179	95.31 330	97.48 181	93.85 95	96.51 97	95.70 256	88.65 104	99.65 72	94.80 130	98.27 134	96.17 279

API-MVS		94.84 127	94.49 129	95.90 151	97.90 127	92.00 119	97.80 98	97.48 181	89.19 269	94.81 155	96.71 192	88.84 100	99.17 152	88.91 263	98.76 111	96.53 268

MG-MVS		95.61 100	95.38 100	96.31 122	98.42 79	90.53 181	96.04 288	97.48 181	93.47 112	95.67 136	98.10 87	89.17 94	99.25 141	91.27 207	98.77 110	99.13 84

MAR-MVS		94.22 143	93.46 161	96.51 105	98.00 118	92.19 113	97.67 118	97.47 184	88.13 309	93.00 203	95.84 244	84.86 174	99.51 110	87.99 276	98.17 139	97.83 220
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		92.98 198	92.53 198	94.32 244	96.12 260	89.20 235	95.28 331	97.47 184	92.66 148	89.90 282	95.62 260	80.58 261	98.40 248	92.73 175	92.40 275	95.38 322
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 275	90.22 291	94.68 223	94.86 333	87.86 276	97.23 182	97.46 186	87.99 310	89.90 282	96.92 183	66.35 405	98.23 264	90.30 228	90.99 301	97.96 207

nrg030		94.05 154	93.31 167	96.27 127	95.22 311	94.59 32	98.34 26	97.46 186	92.93 139	91.21 254	96.64 199	87.23 139	98.22 265	94.99 121	85.80 354	95.98 289

XVG-OURS		93.72 171	93.35 166	94.80 218	97.07 174	88.61 248	94.79 348	97.46 186	91.97 169	93.99 176	97.86 112	81.74 242	98.88 195	92.64 176	92.67 273	96.92 260

LPG-MVS_test		92.94 201	92.56 195	94.10 254	96.16 255	88.26 261	97.65 122	97.46 186	91.29 191	90.12 275	97.16 165	79.05 290	98.73 216	92.25 180	91.89 285	95.31 327

LGP-MVS_train				94.10 254	96.16 255	88.26 261		97.46 186	91.29 191	90.12 275	97.16 165	79.05 290	98.73 216	92.25 180	91.89 285	95.31 327

MVS		91.71 249	90.44 278	95.51 178	95.20 313	91.59 135	96.04 288	97.45 191	73.44 434	87.36 352	95.60 261	85.42 163	99.10 164	85.97 320	97.46 159	95.83 294

XVG-OURS-SEG-HR		93.86 166	93.55 154	94.81 215	97.06 177	88.53 253	95.28 331	97.45 191	91.68 176	94.08 175	97.68 127	82.41 227	98.90 194	93.84 152	92.47 274	96.98 256

baseline		95.58 101	95.42 98	96.08 137	96.78 204	90.41 187	97.16 189	97.45 191	93.69 101	95.65 137	97.85 113	87.29 137	98.68 223	95.66 100	97.25 173	99.13 84

ab-mvs		93.57 175	92.55 196	96.64 88	97.28 163	91.96 122	95.40 324	97.45 191	89.81 251	93.22 200	96.28 222	79.62 281	99.46 119	90.74 218	93.11 265	98.50 157

xiu_mvs_v2_base		95.32 107	95.29 103	95.40 185	97.22 165	90.50 182	95.44 323	97.44 195	93.70 100	96.46 101	96.18 226	88.59 108	99.53 105	94.79 132	97.81 152	96.17 279

1314		92.81 210	92.03 213	95.14 195	95.33 303	89.52 219	96.04 288	97.44 195	87.72 323	86.25 373	95.33 272	83.84 190	98.79 206	89.26 253	97.05 179	97.11 254

casdiffmvs		95.64 98	95.49 92	96.08 137	96.76 209	90.45 184	97.29 175	97.44 195	94.00 89	95.46 143	97.98 99	87.52 132	98.73 216	95.64 104	97.33 167	99.08 91
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		92.16 234	91.23 245	94.95 209	94.75 338	90.94 166	97.47 154	97.43 198	89.14 270	88.90 312	96.43 214	79.71 278	98.24 263	89.56 244	87.68 335	95.67 306

anonymousdsp		92.16 234	91.55 231	93.97 264	92.58 404	89.55 216	97.51 144	97.42 199	89.42 263	88.40 326	94.84 295	80.66 259	97.88 320	91.87 192	91.28 295	94.48 373

Effi-MVS+		94.93 122	94.45 131	96.36 120	96.61 214	91.47 141	96.41 257	97.41 200	91.02 209	94.50 163	95.92 240	87.53 130	98.78 207	93.89 150	96.81 183	98.84 130

RRT-MVS		94.51 137	94.35 134	94.98 205	96.40 238	86.55 309	97.56 136	97.41 200	93.19 123	94.93 150	97.04 174	79.12 288	99.30 138	96.19 82	97.32 169	99.09 90

HQP3-MVS								97.39 202							92.10 282

HQP-MVS		93.19 188	92.74 187	94.54 232	95.86 269	89.33 228	96.65 239	97.39 202	93.55 104	90.14 269	95.87 242	80.95 252	98.50 241	92.13 186	92.10 282	95.78 298

PLC	91.00 6	94.11 151	93.43 163	96.13 136	98.58 73	91.15 160	96.69 235	97.39 202	87.29 333	91.37 244	96.71 192	88.39 109	99.52 109	87.33 296	97.13 177	97.73 224
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 299	89.86 306	93.45 295	93.54 378	87.60 282	97.70 116	97.37 205	88.85 282	87.65 345	94.08 343	81.08 251	98.10 278	84.68 337	83.79 387	94.66 370

UnsupCasMVSNet_eth		85.99 376	84.45 380	90.62 379	89.97 422	82.40 380	93.62 393	97.37 205	89.86 247	78.59 424	92.37 388	65.25 413	95.35 414	82.27 365	70.75 432	94.10 384

ACMM	89.79 8	92.96 199	92.50 200	94.35 241	96.30 245	88.71 246	97.58 132	97.36 207	91.40 189	90.53 262	96.65 198	79.77 277	98.75 213	91.24 208	91.64 287	95.59 308
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 117	94.76 115	95.75 162	96.58 217	91.71 128	96.25 275	97.35 208	92.99 132	96.70 84	96.63 203	82.67 219	99.44 122	96.22 75	97.46 159	96.11 285

xiu_mvs_v1_base		95.01 117	94.76 115	95.75 162	96.58 217	91.71 128	96.25 275	97.35 208	92.99 132	96.70 84	96.63 203	82.67 219	99.44 122	96.22 75	97.46 159	96.11 285

xiu_mvs_v1_base_debi		95.01 117	94.76 115	95.75 162	96.58 217	91.71 128	96.25 275	97.35 208	92.99 132	96.70 84	96.63 203	82.67 219	99.44 122	96.22 75	97.46 159	96.11 285

diffmvs		95.25 110	95.13 107	95.63 170	96.43 237	89.34 227	95.99 292	97.35 208	92.83 143	96.31 107	97.37 153	86.44 147	98.67 224	96.26 72	97.19 175	98.87 125
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		94.71 133	94.02 141	96.79 84	97.71 138	92.05 116	96.59 248	97.35 208	90.61 226	94.64 159	96.93 180	86.41 148	99.39 127	91.20 209	94.71 236	98.94 110

mamba_test_0407		94.54 136	94.12 140	95.80 158	96.79 202	90.38 189	96.79 222	97.29 213	91.24 195	93.68 183	97.60 138	85.03 170	98.67 224	92.14 183	96.51 191	98.35 176

mamba_0404		94.73 132	94.31 136	95.98 149	97.05 179	90.90 169	97.01 201	97.29 213	91.24 195	94.17 172	97.60 138	85.03 170	98.76 211	92.14 183	97.30 170	98.29 179

F-COLMAP		93.58 174	92.98 176	95.37 186	98.40 81	88.98 241	97.18 187	97.29 213	87.75 322	90.49 263	97.10 171	85.21 167	99.50 113	86.70 306	96.72 187	97.63 228

VortexMVS		92.88 205	92.64 191	93.58 288	96.58 217	87.53 283	96.93 209	97.28 216	92.78 146	89.75 287	94.99 286	82.73 218	97.76 333	94.60 137	88.16 330	95.46 313

XVG-ACMP-BASELINE		90.93 295	90.21 292	93.09 308	94.31 357	85.89 325	95.33 328	97.26 217	91.06 208	89.38 300	95.44 270	68.61 388	98.60 232	89.46 246	91.05 299	94.79 363

PCF-MVS	89.48 11	91.56 259	89.95 303	96.36 120	96.60 215	92.52 99	92.51 412	97.26 217	79.41 419	88.90 312	96.56 208	84.04 189	99.55 101	77.01 404	97.30 170	97.01 255
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 214	92.14 209	94.05 257	96.40 238	88.20 264	97.36 167	97.25 219	91.52 182	88.30 330	96.64 199	78.46 302	98.72 220	91.86 193	91.48 291	95.23 334
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407		93.94 161	93.75 147	94.49 234	96.19 250	86.16 320	96.35 265	97.24 220	91.54 179	93.50 190	97.04 174	85.64 161	98.54 238	90.68 220	95.59 213	98.76 133

ICG_test_0404		92.44 218	91.92 218	94.00 260	96.19 250	86.16 320	93.84 385	97.24 220	91.54 179	88.17 336	97.04 174	76.96 320	97.09 376	90.68 220	95.59 213	98.76 133

icg_test_0403		93.98 159	93.79 146	94.55 231	96.19 250	86.16 320	96.35 265	97.24 220	91.54 179	93.59 185	97.04 174	85.86 156	98.73 216	90.68 220	95.59 213	98.76 133

OPM-MVS		93.28 184	92.76 184	94.82 213	94.63 344	90.77 174	96.65 239	97.18 223	93.72 98	91.68 238	97.26 160	79.33 285	98.63 229	92.13 186	92.28 276	95.07 341
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 203	92.02 214	95.56 174	98.19 102	90.80 172	95.27 333	97.18 223	87.96 311	91.86 233	95.68 257	80.44 264	98.99 184	84.01 346	97.54 158	96.89 261

alignmvs		95.87 94	95.23 104	97.78 32	97.56 156	95.19 21	97.86 85	97.17 225	94.39 80	96.47 100	96.40 216	85.89 155	99.20 146	96.21 79	95.11 226	98.95 109

MVS_Test		94.89 124	94.62 121	95.68 168	96.83 197	89.55 216	96.70 233	97.17 225	91.17 201	95.60 138	96.11 235	87.87 121	98.76 211	93.01 172	97.17 176	98.72 139

Fast-Effi-MVS+		93.46 178	92.75 186	95.59 173	96.77 206	90.03 196	96.81 221	97.13 227	88.19 304	91.30 248	94.27 331	86.21 151	98.63 229	87.66 288	96.46 195	98.12 193

EI-MVSNet		93.03 196	92.88 180	93.48 293	95.77 275	86.98 296	96.44 253	97.12 228	90.66 222	91.30 248	97.64 134	86.56 144	98.05 290	89.91 234	90.55 307	95.41 317

MVSTER		93.20 187	92.81 183	94.37 240	96.56 221	89.59 213	97.06 195	97.12 228	91.24 195	91.30 248	95.96 238	82.02 235	98.05 290	93.48 157	90.55 307	95.47 312

test_yl		94.78 130	94.23 137	96.43 113	97.74 136	91.22 149	96.85 216	97.10 230	91.23 198	95.71 132	96.93 180	84.30 182	99.31 136	93.10 165	95.12 224	98.75 136

DCV-MVSNet		94.78 130	94.23 137	96.43 113	97.74 136	91.22 149	96.85 216	97.10 230	91.23 198	95.71 132	96.93 180	84.30 182	99.31 136	93.10 165	95.12 224	98.75 136

LTVRE_ROB	88.41 13	90.99 291	89.92 305	94.19 250	96.18 253	89.55 216	96.31 271	97.09 232	87.88 314	85.67 377	95.91 241	78.79 298	98.57 236	81.50 368	89.98 312	94.44 376
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_fmvs1_n		92.73 212	92.88 180	92.29 334	96.08 263	81.05 391	97.98 66	97.08 233	90.72 217	96.79 80	98.18 84	63.07 417	98.45 245	97.62 37	98.42 128	97.36 243

v10		91.04 289	90.23 289	93.49 292	94.12 360	88.16 267	97.32 172	97.08 233	88.26 303	88.29 331	94.22 336	82.17 232	97.97 302	86.45 310	84.12 381	94.33 379

v144192		91.06 288	90.28 285	93.39 296	93.66 375	87.23 290	96.83 219	97.07 235	87.43 329	89.69 290	94.28 330	81.48 245	98.00 297	87.18 300	84.92 370	94.93 349

v1192		91.07 287	90.23 289	93.58 288	93.70 372	87.82 278	96.73 229	97.07 235	87.77 320	89.58 293	94.32 328	80.90 256	97.97 302	86.52 308	85.48 357	94.95 345

v8		91.29 279	90.53 277	93.57 290	94.15 359	88.12 268	97.34 169	97.06 237	88.99 276	88.32 329	94.26 333	83.08 206	98.01 296	87.62 290	83.92 385	94.57 372

mvs_anonymous		93.82 167	93.74 148	94.06 256	96.44 236	85.41 334	95.81 301	97.05 238	89.85 249	90.09 278	96.36 218	87.44 134	97.75 335	93.97 146	96.69 188	99.02 95

IterMVS-LS		92.29 228	91.94 217	93.34 298	96.25 246	86.97 297	96.57 251	97.05 238	90.67 220	89.50 298	94.80 298	86.59 143	97.64 343	89.91 234	86.11 352	95.40 320
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 297	90.03 300	93.29 300	93.55 377	86.96 298	96.74 228	97.04 240	87.36 331	89.52 297	94.34 325	80.23 269	97.97 302	86.27 311	85.21 363	94.94 347

CDS-MVSNet		94.14 150	93.54 155	95.93 150	96.18 253	91.46 142	96.33 269	97.04 240	88.97 278	93.56 186	96.51 210	87.55 128	97.89 319	89.80 237	95.95 201	98.44 167
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 333	89.26 326	91.19 368	95.16 314	80.29 402	94.53 355	97.03 242	91.79 172	88.86 315	94.10 340	69.94 377	97.82 325	85.29 329	86.66 348	95.45 315

v1144		91.37 272	90.60 273	93.68 283	93.89 367	88.23 263	96.84 218	97.03 242	88.37 300	89.69 290	94.39 320	82.04 234	97.98 299	87.80 280	85.37 359	94.84 355

v1240		90.70 303	89.85 307	93.23 302	93.51 380	86.80 299	96.61 245	97.02 244	87.16 336	89.58 293	94.31 329	79.55 282	97.98 299	85.52 326	85.44 358	94.90 352

EPP-MVSNet		95.22 112	95.04 110	95.76 160	97.49 157	89.56 215	98.67 11	97.00 245	90.69 218	94.24 169	97.62 136	89.79 89	98.81 204	93.39 161	96.49 193	98.92 115

V42		91.58 258	90.87 257	93.73 278	94.05 363	88.50 254	97.32 172	96.97 246	88.80 288	89.71 288	94.33 326	82.54 223	98.05 290	89.01 260	85.07 366	94.64 371

test_fmvs1		93.21 186	93.53 156	92.25 337	96.55 223	81.20 390	97.40 163	96.96 247	90.68 219	96.80 78	98.04 93	69.25 383	98.40 248	97.58 38	98.50 121	97.16 253

FMVSNet2		91.31 276	90.08 295	94.99 203	96.51 229	92.21 110	97.41 159	96.95 248	88.82 285	88.62 321	94.75 300	73.87 347	97.42 364	85.20 332	88.55 327	95.35 324

ACMH	87.59 16	90.53 308	89.42 322	93.87 272	96.21 247	87.92 273	97.24 178	96.94 249	88.45 298	83.91 397	96.27 223	71.92 359	98.62 231	84.43 340	89.43 318	95.05 343
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 273	90.27 286	94.59 225	96.51 229	91.18 156	97.50 145	96.93 250	88.82 285	89.35 301	94.51 313	73.87 347	97.29 371	86.12 316	88.82 322	95.31 327

test1		91.35 273	90.27 286	94.59 225	96.51 229	91.18 156	97.50 145	96.93 250	88.82 285	89.35 301	94.51 313	73.87 347	97.29 371	86.12 316	88.82 322	95.31 327

FMVSNet3		91.78 247	90.69 271	95.03 201	96.53 226	92.27 108	97.02 198	96.93 250	89.79 252	89.35 301	94.65 306	77.01 318	97.47 359	86.12 316	88.82 322	95.35 324

FMVSNet1		89.88 328	88.31 341	94.59 225	95.41 293	91.18 156	97.50 145	96.93 250	86.62 344	87.41 350	94.51 313	65.94 410	97.29 371	83.04 355	87.43 338	95.31 327

GeoE		93.89 164	93.28 168	95.72 166	96.96 189	89.75 208	98.24 39	96.92 254	89.47 260	92.12 224	97.21 163	84.42 180	98.39 253	87.71 283	96.50 192	99.01 98

SymmetryMVS		95.94 90	95.54 90	97.15 70	97.85 129	92.90 83	97.99 63	96.91 255	95.92 13	96.57 95	97.93 102	85.34 164	99.50 113	94.99 121	96.39 196	99.05 94

miper_enhance_ethall		91.54 262	91.01 253	93.15 306	95.35 299	87.07 295	93.97 377	96.90 256	86.79 342	89.17 308	93.43 372	86.55 145	97.64 343	89.97 233	86.93 343	94.74 367

eth_miper_zixun_eth		91.02 290	90.59 274	92.34 332	95.33 303	84.35 353	94.10 374	96.90 256	88.56 294	88.84 317	94.33 326	84.08 187	97.60 348	88.77 266	84.37 379	95.06 342

TAMVS		94.01 156	93.46 161	95.64 169	96.16 255	90.45 184	96.71 232	96.89 258	89.27 267	93.46 192	96.92 183	87.29 137	97.94 312	88.70 268	95.74 207	98.53 153

miper_ehance_all_eth		91.59 256	91.13 249	92.97 312	95.55 285	86.57 307	94.47 358	96.88 259	87.77 320	88.88 314	94.01 345	86.22 150	97.54 352	89.49 245	86.93 343	94.79 363

v2v482		91.59 256	90.85 260	93.80 275	93.87 368	88.17 266	96.94 208	96.88 259	89.54 257	89.53 296	94.90 292	81.70 243	98.02 295	89.25 254	85.04 368	95.20 335

CNLPA		94.28 142	93.53 156	96.52 101	98.38 84	92.55 98	96.59 248	96.88 259	90.13 242	91.91 230	97.24 161	85.21 167	99.09 167	87.64 289	97.83 151	97.92 210

PAPM		91.52 263	90.30 284	95.20 192	95.30 306	89.83 206	93.38 398	96.85 262	86.26 352	88.59 322	95.80 247	84.88 173	98.15 272	75.67 409	95.93 202	97.63 228

c3_l		91.38 270	90.89 256	92.88 316	95.58 283	86.30 314	94.68 350	96.84 263	88.17 305	88.83 318	94.23 334	85.65 160	97.47 359	89.36 249	84.63 372	94.89 353

pm-mvs1		90.72 302	89.65 317	93.96 265	94.29 358	89.63 210	97.79 100	96.82 264	89.07 272	86.12 375	95.48 269	78.61 300	97.78 330	86.97 304	81.67 398	94.46 374

test_vis1_n		92.37 223	92.26 207	92.72 322	94.75 338	82.64 373	98.02 60	96.80 265	91.18 200	97.77 52	97.93 102	58.02 427	98.29 261	97.63 35	98.21 136	97.23 251

CMPMVS	62.92 21	85.62 381	84.92 376	87.74 405	89.14 427	73.12 435	94.17 372	96.80 265	73.98 431	73.65 433	94.93 290	66.36 404	97.61 347	83.95 348	91.28 295	92.48 411
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 315	89.77 311	91.78 353	94.33 355	84.72 350	95.55 317	96.73 267	86.17 354	86.36 372	95.28 275	71.28 364	97.80 328	84.09 345	98.14 140	92.81 403

Effi-MVS+-dtu		93.08 193	93.21 170	92.68 325	96.02 266	83.25 367	97.14 191	96.72 268	93.85 95	91.20 255	93.44 369	83.08 206	98.30 260	91.69 199	95.73 208	96.50 270

TSAR-MVS + GP.		96.69 61	96.49 65	97.27 63	98.31 87	93.39 63	96.79 222	96.72 268	94.17 84	97.44 58	97.66 130	92.76 31	99.33 132	96.86 56	97.76 155	99.08 91

1112_ss		93.37 181	92.42 203	96.21 132	97.05 179	90.99 163	96.31 271	96.72 268	86.87 341	89.83 285	96.69 196	86.51 146	99.14 159	88.12 273	93.67 259	98.50 157

PVSNet	86.66 18	92.24 231	91.74 226	93.73 278	97.77 134	83.69 364	92.88 407	96.72 268	87.91 313	93.00 203	94.86 294	78.51 301	99.05 179	86.53 307	97.45 163	98.47 162

miper_lstm_enhance		90.50 311	90.06 299	91.83 349	95.33 303	83.74 361	93.86 383	96.70 272	87.56 327	87.79 342	93.81 353	83.45 198	96.92 384	87.39 294	84.62 373	94.82 358

v148		90.99 291	90.38 280	92.81 319	93.83 369	85.80 326	96.78 226	96.68 273	89.45 262	88.75 320	93.93 349	82.96 212	97.82 325	87.83 279	83.25 390	94.80 361

ACMH+	87.92 14	90.20 319	89.18 328	93.25 301	96.48 232	86.45 311	96.99 204	96.68 273	88.83 284	84.79 386	96.22 225	70.16 374	98.53 239	84.42 341	88.04 331	94.77 366

CANet_DTU		94.37 140	93.65 151	96.55 98	96.46 235	92.13 114	96.21 279	96.67 275	94.38 81	93.53 189	97.03 178	79.34 284	99.71 60	90.76 217	98.45 126	97.82 221

cl____		90.96 294	90.32 282	92.89 315	95.37 297	86.21 317	94.46 360	96.64 276	87.82 316	88.15 337	94.18 337	82.98 210	97.54 352	87.70 284	85.59 355	94.92 351

HY-MVS	89.66 9	93.87 165	92.95 177	96.63 92	97.10 173	92.49 100	95.64 314	96.64 276	89.05 274	93.00 203	95.79 250	85.77 159	99.45 121	89.16 259	94.35 238	97.96 207

Test_1112_low_res		92.84 208	91.84 221	95.85 155	97.04 181	89.97 202	95.53 319	96.64 276	85.38 364	89.65 292	95.18 280	85.86 156	99.10 164	87.70 284	93.58 264	98.49 159

DIV-MVS_self_test		90.97 293	90.33 281	92.88 316	95.36 298	86.19 319	94.46 360	96.63 279	87.82 316	88.18 335	94.23 334	82.99 209	97.53 354	87.72 281	85.57 356	94.93 349

Fast-Effi-MVS+-dtu		92.29 228	91.99 215	93.21 304	95.27 307	85.52 332	97.03 196	96.63 279	92.09 164	89.11 310	95.14 282	80.33 267	98.08 283	87.54 292	94.74 234	96.03 288

UnsupCasMVSNet_bld		82.13 397	79.46 402	90.14 386	88.00 435	82.47 378	90.89 425	96.62 281	78.94 421	75.61 428	84.40 439	56.63 430	96.31 396	77.30 401	66.77 440	91.63 421

cl22		91.21 281	90.56 276	93.14 307	96.09 262	86.80 299	94.41 362	96.58 282	87.80 318	88.58 323	93.99 347	80.85 257	97.62 346	89.87 236	86.93 343	94.99 344

jason		94.84 127	94.39 133	96.18 134	95.52 286	90.93 167	96.09 286	96.52 283	89.28 266	96.01 121	97.32 155	84.70 175	98.77 210	95.15 117	98.91 106	98.85 127
jason: jason.
tt0805		91.09 286	90.07 298	94.16 252	95.61 281	88.31 258	97.56 136	96.51 284	89.56 256	89.17 308	95.64 259	67.08 402	98.38 254	91.07 211	88.44 328	95.80 296

AUN-MVS		91.76 248	90.75 266	94.81 215	97.00 185	88.57 250	96.65 239	96.49 285	89.63 254	92.15 222	96.12 231	78.66 299	98.50 241	90.83 213	79.18 409	97.36 243

hse-mvs2		93.45 179	92.99 175	94.81 215	97.02 183	88.59 249	96.69 235	96.47 286	95.19 33	96.74 82	96.16 229	83.67 193	98.48 244	95.85 94	79.13 410	97.35 245

SD_0403		90.01 323	90.02 301	89.96 389	95.65 280	76.76 423	95.76 305	96.46 287	90.58 229	86.59 369	96.29 221	82.12 233	94.78 418	73.00 423	93.76 257	98.35 176

EG-PatchMatch MVS		87.02 363	85.44 368	91.76 355	92.67 401	85.00 344	96.08 287	96.45 288	83.41 394	79.52 420	93.49 366	57.10 429	97.72 337	79.34 392	90.87 304	92.56 408

KD-MVS_self_test		85.95 377	84.95 375	88.96 399	89.55 426	79.11 417	95.13 340	96.42 289	85.91 357	84.07 395	90.48 411	70.03 376	94.82 417	80.04 384	72.94 429	92.94 401

pmmvs6		87.81 355	86.19 363	92.69 324	91.32 414	86.30 314	97.34 169	96.41 290	80.59 415	84.05 396	94.37 322	67.37 397	97.67 340	84.75 336	79.51 408	94.09 386

PMMVS		92.86 206	92.34 204	94.42 239	94.92 329	86.73 302	94.53 355	96.38 291	84.78 376	94.27 168	95.12 284	83.13 205	98.40 248	91.47 203	96.49 193	98.12 193

RPSCF		90.75 300	90.86 258	90.42 382	96.84 195	76.29 426	95.61 315	96.34 292	83.89 385	91.38 243	97.87 110	76.45 324	98.78 207	87.16 301	92.23 277	96.20 277

BP-MVS1		95.89 92	95.49 92	97.08 77	96.67 211	93.20 73	98.08 54	96.32 293	94.56 69	96.32 106	97.84 115	84.07 188	99.15 156	96.75 58	98.78 109	98.90 119

MSDG		91.42 268	90.24 288	94.96 208	97.15 171	88.91 242	93.69 390	96.32 293	85.72 360	86.93 365	96.47 212	80.24 268	98.98 185	80.57 381	95.05 227	96.98 256

WBMVS		90.69 305	89.99 302	92.81 319	96.48 232	85.00 344	95.21 338	96.30 295	89.46 261	89.04 311	94.05 344	72.45 357	97.82 325	89.46 246	87.41 340	95.61 307

OurMVSNet-221017-0		90.51 310	90.19 293	91.44 361	93.41 386	81.25 388	96.98 205	96.28 296	91.68 176	86.55 370	96.30 220	74.20 346	97.98 299	88.96 262	87.40 341	95.09 340

MVP-Stereo		90.74 301	90.08 295	92.71 323	93.19 391	88.20 264	95.86 298	96.27 297	86.07 355	84.86 385	94.76 299	77.84 313	97.75 335	83.88 350	98.01 146	92.17 418
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 121	94.56 124	96.29 126	96.34 243	91.21 151	95.83 300	96.27 297	88.93 280	96.22 111	96.88 185	86.20 152	98.85 198	95.27 113	99.05 97	98.82 131

BH-untuned		92.94 201	92.62 193	93.92 271	97.22 165	86.16 320	96.40 261	96.25 299	90.06 243	89.79 286	96.17 228	83.19 202	98.35 256	87.19 299	97.27 172	97.24 250

CL-MVSNet_self_test		86.31 372	85.15 372	89.80 391	88.83 430	81.74 386	93.93 380	96.22 300	86.67 343	85.03 383	90.80 409	78.09 309	94.50 419	74.92 412	71.86 431	93.15 399

IS-MVSNet		94.90 123	94.52 128	96.05 140	97.67 140	90.56 180	98.44 22	96.22 300	93.21 120	93.99 176	97.74 123	85.55 162	98.45 245	89.98 232	97.86 150	99.14 83

FA-MVS(test-final)		93.52 177	92.92 178	95.31 189	96.77 206	88.54 252	94.82 347	96.21 302	89.61 255	94.20 170	95.25 278	83.24 200	99.14 159	90.01 231	96.16 198	98.25 181

GA-MVS		91.38 270	90.31 283	94.59 225	94.65 343	87.62 281	94.34 365	96.19 303	90.73 216	90.35 266	93.83 350	71.84 360	97.96 306	87.22 298	93.61 262	98.21 184

LuminaMVS		94.89 124	94.35 134	96.53 99	95.48 288	92.80 87	96.88 214	96.18 304	92.85 142	95.92 124	96.87 187	81.44 246	98.83 201	96.43 70	97.10 178	97.94 209

IterMVS-SCA-FT		90.31 313	89.81 309	91.82 350	95.52 286	84.20 356	94.30 368	96.15 305	90.61 226	87.39 351	94.27 331	75.80 330	96.44 394	87.34 295	86.88 347	94.82 358

IterMVS		90.15 321	89.67 315	91.61 357	95.48 288	83.72 362	94.33 366	96.12 306	89.99 244	87.31 354	94.15 339	75.78 332	96.27 397	86.97 304	86.89 346	94.83 356
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 211	91.51 235	96.52 101	98.77 58	90.99 163	97.38 166	96.08 307	82.38 400	89.29 304	97.87 110	83.77 191	99.69 66	81.37 374	96.69 188	98.89 123

pmmvs4		90.93 295	89.85 307	94.17 251	93.34 388	90.79 173	94.60 352	96.02 308	84.62 377	87.45 348	95.15 281	81.88 240	97.45 361	87.70 284	87.87 333	94.27 383

ppachtmachnet_test		88.35 350	87.29 349	91.53 358	92.45 407	83.57 365	93.75 387	95.97 309	84.28 380	85.32 382	94.18 337	79.00 296	96.93 383	75.71 408	84.99 369	94.10 384

Anonymous20240521		86.42 370	85.44 368	89.34 397	90.33 419	79.79 408	96.73 229	95.92 310	83.71 390	83.25 401	91.36 406	63.92 415	96.01 398	78.39 396	85.36 360	92.22 416

ITE_SJBPF				92.43 328	95.34 300	85.37 337		95.92 310	91.47 184	87.75 344	96.39 217	71.00 366	97.96 306	82.36 364	89.86 314	93.97 389

test_fmvs2		89.77 332	89.93 304	89.31 398	93.68 374	76.37 425	97.64 126	95.90 312	89.84 250	91.49 241	96.26 224	58.77 425	97.10 375	94.65 134	91.13 297	94.46 374

USDC		88.94 341	87.83 346	92.27 335	94.66 342	84.96 346	93.86 383	95.90 312	87.34 332	83.40 399	95.56 263	67.43 396	98.19 269	82.64 363	89.67 316	93.66 392

COLMAP_ROB	87.81 15	90.40 312	89.28 325	93.79 276	97.95 122	87.13 294	96.92 210	95.89 314	82.83 397	86.88 367	97.18 164	73.77 350	99.29 139	78.44 395	93.62 261	94.95 345
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 167	93.08 173	96.02 143	97.88 128	89.96 203	97.72 111	95.85 315	92.43 152	95.86 126	98.44 57	68.42 392	99.39 127	96.31 71	94.85 228	98.71 141

VDDNet		93.05 195	92.07 210	96.02 143	96.84 195	90.39 188	98.08 54	95.85 315	86.22 353	95.79 129	98.46 55	67.59 395	99.19 147	94.92 124	94.85 228	98.47 162

mvsmamba		94.57 135	94.14 139	95.87 152	97.03 182	89.93 204	97.84 89	95.85 315	91.34 190	94.79 156	96.80 188	80.67 258	98.81 204	94.85 125	98.12 141	98.85 127

Vis-MVSNet (Re-imp)		94.15 147	93.88 144	94.95 209	97.61 148	87.92 273	98.10 52	95.80 318	92.22 157	93.02 202	97.45 147	84.53 178	97.91 318	88.24 272	97.97 147	99.02 95

MM		97.29 26	96.98 36	98.23 11	98.01 116	95.03 26	98.07 56	95.76 319	97.78 1	97.52 55	98.80 35	88.09 114	99.86 9	99.44 2	99.37 62	99.80 1

KD-MVS_2432*1600		84.81 387	82.64 390	91.31 363	91.07 416	85.34 338	91.22 420	95.75 320	85.56 362	83.09 402	90.21 414	67.21 398	95.89 400	77.18 402	62.48 444	92.69 404

miper_refine_blended		84.81 387	82.64 390	91.31 363	91.07 416	85.34 338	91.22 420	95.75 320	85.56 362	83.09 402	90.21 414	67.21 398	95.89 400	77.18 402	62.48 444	92.69 404

FE-MVS		92.05 239	91.05 251	95.08 198	96.83 197	87.93 272	93.91 382	95.70 322	86.30 350	94.15 173	94.97 287	76.59 322	99.21 145	84.10 344	96.86 181	98.09 199

tpm cat1		88.36 349	87.21 352	91.81 351	95.13 319	80.55 397	92.58 411	95.70 322	74.97 430	87.45 348	91.96 399	78.01 312	98.17 271	80.39 383	88.74 325	96.72 266

our_test_3		88.78 345	87.98 345	91.20 367	92.45 407	82.53 375	93.61 394	95.69 324	85.77 359	84.88 384	93.71 355	79.99 273	96.78 390	79.47 389	86.24 349	94.28 382

BH-w/o		92.14 236	91.75 224	93.31 299	96.99 186	85.73 329	95.67 309	95.69 324	88.73 290	89.26 306	94.82 297	82.97 211	98.07 287	85.26 331	96.32 197	96.13 284

CR-MVSNet		90.82 298	89.77 311	93.95 266	94.45 351	87.19 291	90.23 428	95.68 326	86.89 340	92.40 212	92.36 391	80.91 254	97.05 378	81.09 378	93.95 254	97.60 233

Patchmtry		88.64 347	87.25 350	92.78 321	94.09 361	86.64 303	89.82 432	95.68 326	80.81 412	87.63 346	92.36 391	80.91 254	97.03 379	78.86 393	85.12 365	94.67 369

testing91		91.90 244	91.02 252	94.53 233	96.54 224	86.55 309	95.86 298	95.64 328	91.77 173	91.89 231	93.47 368	69.94 377	98.86 196	90.23 230	93.86 256	98.18 186

BH-RMVSNet		92.72 213	91.97 216	94.97 207	97.16 169	87.99 271	96.15 284	95.60 329	90.62 225	91.87 232	97.15 167	78.41 303	98.57 236	83.16 353	97.60 157	98.36 174

PVSNet_0	82.17 19	85.46 382	83.64 385	90.92 371	95.27 307	79.49 413	90.55 426	95.60 329	83.76 389	83.00 404	89.95 416	71.09 365	97.97 302	82.75 361	60.79 446	95.31 327

guyue		95.17 115	94.96 111	95.82 156	96.97 188	89.65 209	97.56 136	95.58 331	94.82 54	95.72 131	97.42 151	82.90 213	98.84 200	96.71 61	96.93 180	98.96 106

SCA		91.84 246	91.18 248	93.83 273	95.59 282	84.95 347	94.72 349	95.58 331	90.82 212	92.25 220	93.69 357	75.80 330	98.10 278	86.20 313	95.98 200	98.45 164

MonoMVSNet		91.92 242	91.77 222	92.37 329	92.94 395	83.11 369	97.09 194	95.55 333	92.91 140	90.85 258	94.55 310	81.27 250	96.52 393	93.01 172	87.76 334	97.47 239

AllTest		90.23 317	88.98 331	93.98 262	97.94 123	86.64 303	96.51 252	95.54 334	85.38 364	85.49 379	96.77 190	70.28 372	99.15 156	80.02 385	92.87 266	96.15 282

TestCases				93.98 262	97.94 123	86.64 303		95.54 334	85.38 364	85.49 379	96.77 190	70.28 372	99.15 156	80.02 385	92.87 266	96.15 282

mmtdpeth		89.70 334	88.96 332	91.90 346	95.84 274	84.42 352	97.46 156	95.53 336	90.27 237	94.46 165	90.50 410	69.74 381	98.95 186	97.39 47	69.48 435	92.34 412

tpmvs		89.83 331	89.15 329	91.89 347	94.92 329	80.30 401	93.11 403	95.46 337	86.28 351	88.08 338	92.65 381	80.44 264	98.52 240	81.47 370	89.92 313	96.84 262

pmmvs5		89.86 330	88.87 335	92.82 318	92.86 397	86.23 316	96.26 274	95.39 338	84.24 381	87.12 356	94.51 313	74.27 345	97.36 368	87.61 291	87.57 336	94.86 354

PatchmatchNet		91.91 243	91.35 237	93.59 287	95.38 295	84.11 357	93.15 402	95.39 338	89.54 257	92.10 225	93.68 359	82.82 216	98.13 273	84.81 335	95.32 220	98.52 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 267	91.32 239	91.79 352	95.15 317	79.20 416	93.42 397	95.37 340	88.55 295	93.49 191	93.67 360	82.49 225	98.27 262	90.41 225	89.34 319	97.90 211

Anonymous20231206		87.09 362	86.14 364	89.93 390	91.22 415	80.35 399	96.11 285	95.35 341	83.57 392	84.16 391	93.02 376	73.54 352	95.61 408	72.16 425	86.14 351	93.84 391

MIMVSNet1		84.93 385	83.05 387	90.56 380	89.56 425	84.84 349	95.40 324	95.35 341	83.91 384	80.38 416	92.21 396	57.23 428	93.34 431	70.69 431	82.75 396	93.50 394

TDRefinement		86.53 366	84.76 378	91.85 348	82.23 447	84.25 354	96.38 263	95.35 341	84.97 373	84.09 394	94.94 289	65.76 411	98.34 259	84.60 339	74.52 425	92.97 400

TR-MVS		91.48 266	90.59 274	94.16 252	96.40 238	87.33 284	95.67 309	95.34 344	87.68 324	91.46 242	95.52 266	76.77 321	98.35 256	82.85 358	93.61 262	96.79 264

EPNet_dtu		91.71 249	91.28 242	92.99 311	93.76 371	83.71 363	96.69 235	95.28 345	93.15 127	87.02 361	95.95 239	83.37 199	97.38 367	79.46 390	96.84 182	97.88 213
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 359	85.79 366	91.78 353	94.80 336	87.28 286	95.49 321	95.28 345	84.09 383	83.85 398	91.82 400	62.95 418	94.17 423	78.48 394	85.34 361	93.91 390

MDTV_nov1_ep13			90.76 264		95.22 311	80.33 400	93.03 405	95.28 345	88.14 308	92.84 209	93.83 350	81.34 247	98.08 283	82.86 356	94.34 239

LF4IMVS		87.94 353	87.25 350	89.98 388	92.38 409	80.05 407	94.38 363	95.25 348	87.59 326	84.34 388	94.74 301	64.31 414	97.66 342	84.83 334	87.45 337	92.23 415

TransMVSNet (Re)		88.94 341	87.56 347	93.08 309	94.35 354	88.45 256	97.73 108	95.23 349	87.47 328	84.26 390	95.29 273	79.86 276	97.33 369	79.44 391	74.44 426	93.45 396

test20.03		86.14 375	85.40 370	88.35 400	90.12 420	80.06 406	95.90 297	95.20 350	88.59 291	81.29 411	93.62 362	71.43 363	92.65 435	71.26 429	81.17 401	92.34 412

new-patchmatchnet		83.18 393	81.87 396	87.11 408	86.88 438	75.99 427	93.70 388	95.18 351	85.02 372	77.30 427	88.40 426	65.99 409	93.88 428	74.19 417	70.18 433	91.47 425

MDA-MVSNet_test_wron		85.87 379	84.23 382	90.80 377	92.38 409	82.57 374	93.17 400	95.15 352	82.15 401	67.65 439	92.33 394	78.20 305	95.51 411	77.33 399	79.74 405	94.31 381

YYNet1		85.87 379	84.23 382	90.78 378	92.38 409	82.46 379	93.17 400	95.14 353	82.12 402	67.69 437	92.36 391	78.16 308	95.50 412	77.31 400	79.73 406	94.39 377

Baseline_NR-MVSNet		91.20 282	90.62 272	92.95 313	93.83 369	88.03 270	97.01 201	95.12 354	88.42 299	89.70 289	95.13 283	83.47 196	97.44 362	89.66 242	83.24 391	93.37 397

thres200		92.23 232	91.39 236	94.75 222	97.61 148	89.03 240	96.60 247	95.09 355	92.08 165	93.28 197	94.00 346	78.39 304	99.04 182	81.26 377	94.18 245	96.19 278

ADS-MVSNet		89.89 327	88.68 337	93.53 291	95.86 269	84.89 348	90.93 423	95.07 356	83.23 395	91.28 251	91.81 401	79.01 294	97.85 321	79.52 387	91.39 293	97.84 218

pmmvs-eth3d		86.22 373	84.45 380	91.53 358	88.34 434	87.25 288	94.47 358	95.01 357	83.47 393	79.51 421	89.61 419	69.75 380	95.71 405	83.13 354	76.73 419	91.64 420

Anonymous202405211		92.07 238	90.83 262	95.76 160	98.19 102	88.75 245	97.58 132	95.00 358	86.00 356	93.64 184	97.45 147	66.24 407	99.53 105	90.68 220	92.71 271	99.01 98

MDA-MVSNet-bldmvs		85.00 384	82.95 389	91.17 369	93.13 393	83.33 366	94.56 354	95.00 358	84.57 378	65.13 443	92.65 381	70.45 371	95.85 402	73.57 420	77.49 415	94.33 379

ambc				86.56 411	83.60 444	70.00 438	85.69 442	94.97 360		80.60 415	88.45 425	37.42 446	96.84 387	82.69 362	75.44 423	92.86 402

testgi		87.97 352	87.21 352	90.24 385	92.86 397	80.76 392	96.67 238	94.97 360	91.74 174	85.52 378	95.83 245	62.66 420	94.47 421	76.25 406	88.36 329	95.48 310

myMVS_eth3d28		91.52 263	90.97 254	93.17 305	96.91 190	83.24 368	95.61 315	94.96 362	92.24 156	91.98 228	93.28 373	69.31 382	98.40 248	88.71 267	95.68 210	97.88 213

dp		88.90 343	88.26 343	90.81 375	94.58 347	76.62 424	92.85 408	94.93 363	85.12 370	90.07 280	93.07 375	75.81 329	98.12 276	80.53 382	87.42 339	97.71 225

test_fmvs3		83.21 392	83.02 388	83.78 415	86.77 439	68.34 441	96.76 227	94.91 364	86.49 346	84.14 393	89.48 420	36.04 447	91.73 437	91.86 193	80.77 403	91.26 427

test_0402		86.46 369	84.79 377	91.45 360	95.02 323	85.55 331	96.29 273	94.89 365	80.90 409	82.21 407	93.97 348	68.21 393	97.29 371	62.98 438	88.68 326	91.51 423

tfpn200view9		92.38 222	91.52 233	94.95 209	97.85 129	89.29 230	97.41 159	94.88 366	92.19 161	93.27 198	94.46 318	78.17 306	99.08 170	81.40 371	94.08 249	96.48 271

CVMVSNet		91.23 280	91.75 224	89.67 392	95.77 275	74.69 428	96.44 253	94.88 366	85.81 358	92.18 221	97.64 134	79.07 289	95.58 410	88.06 275	95.86 205	98.74 138

thres400		92.42 220	91.52 233	95.12 197	97.85 129	89.29 230	97.41 159	94.88 366	92.19 161	93.27 198	94.46 318	78.17 306	99.08 170	81.40 371	94.08 249	96.98 256

tt0320		85.39 383	83.12 386	92.19 339	93.44 385	85.79 327	96.19 281	94.87 369	71.19 437	82.92 405	91.76 403	58.43 426	96.81 388	81.03 379	78.26 414	93.98 388

EPNet		95.20 113	94.56 124	97.14 71	92.80 399	92.68 93	97.85 88	94.87 369	96.64 6	92.46 211	97.80 120	86.23 149	99.65 72	93.72 154	98.62 117	99.10 89
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 254	90.72 269	94.32 244	96.48 232	86.11 324	95.81 301	94.76 371	91.55 178	91.75 236	93.44 369	68.55 390	98.82 202	90.43 224	93.69 258	98.04 203

sc_t1		86.48 368	84.10 384	93.63 284	93.45 384	85.76 328	96.79 222	94.71 372	73.06 435	86.45 371	94.35 323	55.13 433	97.95 310	84.38 342	78.55 413	97.18 252

SixPastTwentyTwo		89.15 339	88.54 339	90.98 370	93.49 381	80.28 403	96.70 233	94.70 373	90.78 213	84.15 392	95.57 262	71.78 361	97.71 338	84.63 338	85.07 366	94.94 347

thres100view900		92.43 219	91.58 230	94.98 205	97.92 125	89.37 226	97.71 113	94.66 374	92.20 159	93.31 196	94.90 292	78.06 310	99.08 170	81.40 371	94.08 249	96.48 271

thres600view7		92.49 217	91.60 229	95.18 193	97.91 126	89.47 220	97.65 122	94.66 374	92.18 163	93.33 195	94.91 291	78.06 310	99.10 164	81.61 367	94.06 253	96.98 256

PatchT		88.87 344	87.42 348	93.22 303	94.08 362	85.10 342	89.51 433	94.64 376	81.92 403	92.36 215	88.15 429	80.05 272	97.01 381	72.43 424	93.65 260	97.54 236

baseline1		92.82 209	91.90 219	95.55 176	97.20 167	90.77 174	97.19 186	94.58 377	92.20 159	92.36 215	96.34 219	84.16 186	98.21 266	89.20 257	83.90 386	97.68 227

AstraMVS		94.82 129	94.64 120	95.34 188	96.36 242	88.09 269	97.58 132	94.56 378	94.98 43	95.70 134	97.92 105	81.93 239	98.93 189	96.87 55	95.88 203	98.99 102

UBG		91.55 260	90.76 264	93.94 268	96.52 228	85.06 343	95.22 336	94.54 379	90.47 233	91.98 228	92.71 380	72.02 358	98.74 215	88.10 274	95.26 222	98.01 205

Gipuma		67.86 413	65.41 415	75.18 428	92.66 402	73.45 432	66.50 449	94.52 380	53.33 448	57.80 449	66.07 449	30.81 449	89.20 441	48.15 447	78.88 412	62.90 449
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 252	90.75 266	94.47 235	96.53 226	86.56 308	95.76 305	94.51 381	91.10 207	91.24 253	93.59 363	68.59 389	98.86 196	91.10 210	94.29 241	98.00 206

CostFormer		91.18 285	90.70 270	92.62 326	94.84 334	81.76 385	94.09 375	94.43 382	84.15 382	92.72 210	93.77 354	79.43 283	98.20 267	90.70 219	92.18 280	97.90 211

tpm2		89.96 324	89.21 327	92.23 338	94.91 331	81.25 388	93.78 386	94.42 383	80.62 414	91.56 239	93.44 369	76.44 325	97.94 312	85.60 325	92.08 284	97.49 237

testing3-2		92.10 237	92.05 211	92.27 335	97.71 138	79.56 410	97.42 158	94.41 384	93.53 108	93.22 200	95.49 267	69.16 384	99.11 162	93.25 162	94.22 243	98.13 191

MVS_0304		96.74 58	96.31 75	98.02 19	96.87 192	94.65 30	97.58 132	94.39 385	96.47 9	97.16 67	98.39 61	87.53 130	99.87 7	98.97 17	99.41 54	99.55 38

JIA-IIPM		88.26 351	87.04 355	91.91 345	93.52 379	81.42 387	89.38 434	94.38 386	80.84 411	90.93 257	80.74 441	79.22 286	97.92 315	82.76 360	91.62 288	96.38 274

dmvs_re		90.21 318	89.50 320	92.35 330	95.47 292	85.15 340	95.70 308	94.37 387	90.94 211	88.42 325	93.57 364	74.63 342	95.67 407	82.80 359	89.57 317	96.22 276

Patchmatch-test		89.42 337	87.99 344	93.70 281	95.27 307	85.11 341	88.98 435	94.37 387	81.11 408	87.10 359	93.69 357	82.28 229	97.50 357	74.37 415	94.76 232	98.48 161

LCM-MVSNet		72.55 406	69.39 410	82.03 417	70.81 457	65.42 446	90.12 430	94.36 389	55.02 447	65.88 441	81.72 440	24.16 455	89.96 438	74.32 416	68.10 438	90.71 430

ADS-MVSNet2		89.45 336	88.59 338	92.03 342	95.86 269	82.26 381	90.93 423	94.32 390	83.23 395	91.28 251	91.81 401	79.01 294	95.99 399	79.52 387	91.39 293	97.84 218

mvs5depth		86.53 366	85.08 373	90.87 372	88.74 432	82.52 376	91.91 416	94.23 391	86.35 349	87.11 358	93.70 356	66.52 403	97.76 333	81.37 374	75.80 421	92.31 414

EU-MVSNet		88.72 346	88.90 334	88.20 402	93.15 392	74.21 430	96.63 244	94.22 392	85.18 368	87.32 353	95.97 237	76.16 327	94.98 416	85.27 330	86.17 350	95.41 317

tt0320-xc		84.83 386	82.33 394	92.31 333	93.66 375	86.20 318	96.17 283	94.06 393	71.26 436	82.04 409	92.22 395	55.07 434	96.72 391	81.49 369	75.04 424	94.02 387

MIMVSNet		88.50 348	86.76 358	93.72 280	94.84 334	87.77 279	91.39 418	94.05 394	86.41 348	87.99 340	92.59 384	63.27 416	95.82 404	77.44 398	92.84 268	97.57 235

OpenMVS_ROB	81.14 20	84.42 389	82.28 395	90.83 373	90.06 421	84.05 359	95.73 307	94.04 395	73.89 433	80.17 419	91.53 405	59.15 424	97.64 343	66.92 436	89.05 321	90.80 429

TinyColmap		86.82 364	85.35 371	91.21 365	94.91 331	82.99 371	93.94 379	94.02 396	83.58 391	81.56 410	94.68 303	62.34 421	98.13 273	75.78 407	87.35 342	92.52 410

ETVMVS		90.52 309	89.14 330	94.67 224	96.81 201	87.85 277	95.91 296	93.97 397	89.71 253	92.34 218	92.48 386	65.41 412	97.96 306	81.37 374	94.27 242	98.21 184

IB-MVS	87.33 17	89.91 325	88.28 342	94.79 219	95.26 310	87.70 280	95.12 341	93.95 398	89.35 265	87.03 360	92.49 385	70.74 369	99.19 147	89.18 258	81.37 400	97.49 237
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		87.13 361	87.02 356	87.47 406	95.16 314	73.21 434	95.00 343	93.93 399	88.55 295	86.96 362	91.99 397	75.90 328	94.00 425	61.59 440	94.11 246	95.20 335

myMVS_eth3d		87.18 360	86.38 361	89.58 393	95.16 314	79.53 411	95.00 343	93.93 399	88.55 295	86.96 362	91.99 397	56.23 431	94.00 425	75.47 411	94.11 246	95.20 335

testing222		90.31 313	88.96 332	94.35 241	96.54 224	87.29 285	95.50 320	93.84 401	90.97 210	91.75 236	92.96 377	62.18 422	98.00 297	82.86 356	94.08 249	97.76 223

test_f		80.57 399	79.62 401	83.41 416	83.38 445	67.80 443	93.57 395	93.72 402	80.80 413	77.91 426	87.63 432	33.40 448	92.08 436	87.14 302	79.04 411	90.34 431

LCM-MVSNet-Re		92.50 215	92.52 199	92.44 327	96.82 199	81.89 384	96.92 210	93.71 403	92.41 153	84.30 389	94.60 308	85.08 169	97.03 379	91.51 201	97.36 165	98.40 170

tpm		90.25 316	89.74 314	91.76 355	93.92 365	79.73 409	93.98 376	93.54 404	88.28 302	91.99 227	93.25 374	77.51 316	97.44 362	87.30 297	87.94 332	98.12 193

ET-MVSNet_ETH3D		91.49 265	90.11 294	95.63 170	96.40 238	91.57 137	95.34 327	93.48 405	90.60 228	75.58 429	95.49 267	80.08 271	96.79 389	94.25 142	89.76 315	98.52 154

LFMVS		93.60 173	92.63 192	96.52 101	98.13 108	91.27 148	97.94 76	93.39 406	90.57 230	96.29 108	98.31 74	69.00 385	99.16 154	94.18 143	95.87 204	99.12 87

MVStest1		82.38 396	80.04 400	89.37 395	87.63 437	82.83 372	95.03 342	93.37 407	73.90 432	73.50 434	94.35 323	62.89 419	93.25 433	73.80 418	65.92 441	92.04 419

Patchmatch-RL test		87.38 358	86.24 362	90.81 375	88.74 432	78.40 420	88.12 440	93.17 408	87.11 337	82.17 408	89.29 421	81.95 237	95.60 409	88.64 269	77.02 416	98.41 169

ttmdpeth		85.91 378	84.76 378	89.36 396	89.14 427	80.25 404	95.66 312	93.16 409	83.77 388	83.39 400	95.26 277	66.24 407	95.26 415	80.65 380	75.57 422	92.57 407

test-LLR		91.42 268	91.19 247	92.12 340	94.59 345	80.66 394	94.29 369	92.98 410	91.11 205	90.76 260	92.37 388	79.02 292	98.07 287	88.81 264	96.74 185	97.63 228

test-mter		90.19 320	89.54 319	92.12 340	94.59 345	80.66 394	94.29 369	92.98 410	87.68 324	90.76 260	92.37 388	67.67 394	98.07 287	88.81 264	96.74 185	97.63 228

WB-MVSnew		89.88 328	89.56 318	90.82 374	94.57 348	83.06 370	95.65 313	92.85 412	87.86 315	90.83 259	94.10 340	79.66 280	96.88 385	76.34 405	94.19 244	92.54 409

testing3		87.67 356	86.88 357	90.05 387	96.14 258	80.71 393	97.10 193	92.85 412	90.15 241	87.54 347	94.55 310	55.70 432	94.10 424	73.77 419	94.10 248	95.35 324

test_method		66.11 414	64.89 416	69.79 431	72.62 455	35.23 463	65.19 450	92.83 414	20.35 453	65.20 442	88.08 430	43.14 444	82.70 448	73.12 422	63.46 443	91.45 426

test0.0.03 1		89.37 338	88.70 336	91.41 362	92.47 406	85.63 330	95.22 336	92.70 415	91.11 205	86.91 366	93.65 361	79.02 292	93.19 434	78.00 397	89.18 320	95.41 317

new_pmnet		82.89 394	81.12 399	88.18 403	89.63 424	80.18 405	91.77 417	92.57 416	76.79 428	75.56 430	88.23 428	61.22 423	94.48 420	71.43 427	82.92 394	89.87 432

mvsany_test1		93.93 163	93.98 142	93.78 277	94.94 328	86.80 299	94.62 351	92.55 417	88.77 289	96.85 77	98.49 51	88.98 96	98.08 283	95.03 119	95.62 212	96.46 273

thisisatest0515		92.29 228	91.30 241	95.25 191	96.60 215	88.90 243	94.36 364	92.32 418	87.92 312	93.43 193	94.57 309	77.28 317	99.00 183	89.42 248	95.86 205	97.86 217

thisisatest0530		93.03 196	92.21 208	95.49 180	97.07 174	89.11 239	97.49 153	92.19 419	90.16 240	94.09 174	96.41 215	76.43 326	99.05 179	90.38 226	95.68 210	98.31 178

tttt0517		92.96 199	92.33 205	94.87 212	97.11 172	87.16 293	97.97 72	92.09 420	90.63 224	93.88 180	97.01 179	76.50 323	99.06 176	90.29 229	95.45 218	98.38 172

K. test v3		87.64 357	86.75 359	90.32 384	93.02 394	79.48 414	96.61 245	92.08 421	90.66 222	80.25 418	94.09 342	67.21 398	96.65 392	85.96 321	80.83 402	94.83 356

TESTMET0.1,1		90.06 322	89.42 322	91.97 343	94.41 353	80.62 396	94.29 369	91.97 422	87.28 334	90.44 264	92.47 387	68.79 386	97.67 340	88.50 271	96.60 190	97.61 232

PM-MVS		83.48 391	81.86 397	88.31 401	87.83 436	77.59 422	93.43 396	91.75 423	86.91 339	80.63 414	89.91 417	44.42 443	95.84 403	85.17 333	76.73 419	91.50 424

baseline2		91.63 253	90.86 258	93.94 268	94.33 355	86.32 313	95.92 295	91.64 424	89.37 264	86.94 364	94.69 302	81.62 244	98.69 222	88.64 269	94.57 237	96.81 263

APD_test1		79.31 401	77.70 404	84.14 414	89.11 429	69.07 440	92.36 415	91.50 425	69.07 439	73.87 432	92.63 383	39.93 445	94.32 422	70.54 432	80.25 404	89.02 434

FPMVS		71.27 407	69.85 409	75.50 427	74.64 452	59.03 452	91.30 419	91.50 425	58.80 444	57.92 448	88.28 427	29.98 451	85.53 447	53.43 445	82.84 395	81.95 440

door								91.13 427

door-mid								91.06 428

EGC-MVSNET		68.77 412	63.01 418	86.07 413	92.49 405	82.24 382	93.96 378	90.96 429	0.71 458	2.62 459	90.89 408	53.66 435	93.46 429	57.25 443	84.55 376	82.51 439

mvsany_test3		83.59 390	82.44 393	87.03 409	83.80 442	73.82 431	93.70 388	90.92 430	86.42 347	82.51 406	90.26 413	46.76 442	95.71 405	90.82 214	76.76 418	91.57 422

pmmvs3		79.97 400	77.50 405	87.39 407	82.80 446	79.38 415	92.70 410	90.75 431	70.69 438	78.66 423	87.47 434	51.34 438	93.40 430	73.39 421	69.65 434	89.38 433

UWE-MVS		89.91 325	89.48 321	91.21 365	95.88 268	78.23 421	94.91 346	90.26 432	89.11 271	92.35 217	94.52 312	68.76 387	97.96 306	83.95 348	95.59 213	97.42 241

DSMNet-mixed		86.34 371	86.12 365	87.00 410	89.88 423	70.43 436	94.93 345	90.08 433	77.97 425	85.42 381	92.78 379	74.44 344	93.96 427	74.43 414	95.14 223	96.62 267

MVS-HIRNet		82.47 395	81.21 398	86.26 412	95.38 295	69.21 439	88.96 436	89.49 434	66.28 441	80.79 413	74.08 446	68.48 391	97.39 366	71.93 426	95.47 217	92.18 417

WB-MVS		76.77 403	76.63 406	77.18 422	85.32 440	56.82 454	94.53 355	89.39 435	82.66 399	71.35 435	89.18 422	75.03 337	88.88 442	35.42 451	66.79 439	85.84 436

test1111		93.19 188	92.82 182	94.30 247	97.58 154	84.56 351	98.21 43	89.02 436	93.53 108	94.58 160	98.21 81	72.69 354	99.05 179	93.06 168	98.48 124	99.28 72

SSC-MVS		76.05 404	75.83 407	76.72 426	84.77 441	56.22 455	94.32 367	88.96 437	81.82 405	70.52 436	88.91 423	74.79 341	88.71 443	33.69 452	64.71 442	85.23 437

ECVR-MVS		93.19 188	92.73 188	94.57 230	97.66 142	85.41 334	98.21 43	88.23 438	93.43 113	94.70 158	98.21 81	72.57 355	99.07 174	93.05 169	98.49 122	99.25 75

EPMVS		90.70 303	89.81 309	93.37 297	94.73 340	84.21 355	93.67 391	88.02 439	89.50 259	92.38 214	93.49 366	77.82 314	97.78 330	86.03 319	92.68 272	98.11 198

ANet_high		63.94 416	59.58 419	77.02 423	61.24 459	66.06 444	85.66 443	87.93 440	78.53 423	42.94 451	71.04 448	25.42 454	80.71 450	52.60 446	30.83 452	84.28 438

PMMVS2		70.19 408	66.92 412	80.01 418	76.35 451	65.67 445	86.22 441	87.58 441	64.83 443	62.38 444	80.29 443	26.78 453	88.49 445	63.79 437	54.07 448	85.88 435

lessismore_v0				90.45 381	91.96 412	79.09 418		87.19 442		80.32 417	94.39 320	66.31 406	97.55 351	84.00 347	76.84 417	94.70 368

PMVS	53.92 22	58.58 417	55.40 420	68.12 432	51.00 460	48.64 457	78.86 446	87.10 443	46.77 449	35.84 455	74.28 445	8.76 459	86.34 446	42.07 449	73.91 427	69.38 446
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 365	86.41 360	88.02 404	92.87 396	74.60 429	95.38 326	86.70 444	88.17 305	87.28 355	94.67 305	70.83 368	93.30 432	67.45 434	94.31 240	96.17 279

test_vis1_rt		86.16 374	85.06 374	89.46 394	93.47 383	80.46 398	96.41 257	86.61 445	85.22 367	79.15 422	88.64 424	52.41 437	97.06 377	93.08 167	90.57 306	90.87 428

testf1		69.31 410	66.76 413	76.94 424	78.61 449	61.93 448	88.27 438	86.11 446	55.62 445	59.69 445	85.31 437	20.19 457	89.32 439	57.62 441	69.44 436	79.58 441

APD_test2		69.31 410	66.76 413	76.94 424	78.61 449	61.93 448	88.27 438	86.11 446	55.62 445	59.69 445	85.31 437	20.19 457	89.32 439	57.62 441	69.44 436	79.58 441

gg-mvs-nofinetune		87.82 354	85.61 367	94.44 237	94.46 350	89.27 233	91.21 422	84.61 448	80.88 410	89.89 284	74.98 444	71.50 362	97.53 354	85.75 324	97.21 174	96.51 269

dmvs_testset		81.38 398	82.60 392	77.73 421	91.74 413	51.49 456	93.03 405	84.21 449	89.07 272	78.28 425	91.25 407	76.97 319	88.53 444	56.57 444	82.24 397	93.16 398

GG-mvs-BLEND				93.62 285	93.69 373	89.20 235	92.39 414	83.33 450		87.98 341	89.84 418	71.00 366	96.87 386	82.08 366	95.40 219	94.80 361

MTMP							97.86 85	82.03 451

DeepMVS_CX				74.68 429	90.84 418	64.34 447		81.61 452	65.34 442	67.47 440	88.01 431	48.60 441	80.13 451	62.33 439	73.68 428	79.58 441

E-PMN		53.28 418	52.56 422	55.43 435	74.43 453	47.13 458	83.63 445	76.30 453	42.23 450	42.59 452	62.22 451	28.57 452	74.40 452	31.53 453	31.51 451	44.78 450

test2506		91.60 255	90.78 263	94.04 258	97.66 142	83.81 360	98.27 33	75.53 454	93.43 113	95.23 145	98.21 81	67.21 398	99.07 174	93.01 172	98.49 122	99.25 75

EMVS		52.08 420	51.31 423	54.39 436	72.62 455	45.39 460	83.84 444	75.51 455	41.13 451	40.77 453	59.65 452	30.08 450	73.60 453	28.31 455	29.90 453	44.18 451

test_vis3_rt		72.73 405	70.55 408	79.27 419	80.02 448	68.13 442	93.92 381	74.30 456	76.90 427	58.99 447	73.58 447	20.29 456	95.37 413	84.16 343	72.80 430	74.31 444

MVE	50.73 23	53.25 419	48.81 424	66.58 434	65.34 458	57.50 453	72.49 448	70.94 457	40.15 452	39.28 454	63.51 450	6.89 461	73.48 454	38.29 450	42.38 450	68.76 448
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 421	53.82 421	46.29 437	33.73 461	45.30 461	78.32 447	67.24 458	18.02 454	50.93 450	87.05 435	52.99 436	53.11 456	70.76 430	25.29 454	40.46 452

kuosan		65.27 415	64.66 417	67.11 433	83.80 442	61.32 451	88.53 437	60.77 459	68.22 440	67.67 438	80.52 442	49.12 440	70.76 455	29.67 454	53.64 449	69.26 447

dongtai		69.99 409	69.33 411	71.98 430	88.78 431	61.64 450	89.86 431	59.93 460	75.67 429	74.96 431	85.45 436	50.19 439	81.66 449	43.86 448	55.27 447	72.63 445

N_pmnet		78.73 402	78.71 403	78.79 420	92.80 399	46.50 459	94.14 373	43.71 461	78.61 422	80.83 412	91.66 404	74.94 340	96.36 395	67.24 435	84.45 378	93.50 394

wuyk23d		25.11 422	24.57 426	26.74 438	73.98 454	39.89 462	57.88 451	9.80 462	12.27 455	10.39 456	6.97 458	7.03 460	36.44 457	25.43 456	17.39 455	3.89 455

testmvs		13.36 424	16.33 427	4.48 440	5.04 462	2.26 465	93.18 399	3.28 463	2.70 456	8.24 457	21.66 454	2.29 463	2.19 458	7.58 457	2.96 456	9.00 454

test123		13.04 425	15.66 428	5.18 439	4.51 463	3.45 464	92.50 413	1.81 464	2.50 457	7.58 458	20.15 455	3.67 462	2.18 459	7.13 458	1.07 457	9.90 453

mmdepth		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

monomultidepth		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

test_blank		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

uanet_test		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

DCPMVS		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

pcd_1.5k_mvsjas		7.39 427	9.85 430	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	88.65 104	0.00 460	0.00 459	0.00 458	0.00 456

sosnet-low-res		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

sosnet		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

uncertanet		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

Regformer		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

n2								0.00 465

nn								0.00 465

ab-mvs-re		8.06 426	10.74 429	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	96.69 196	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

uanet		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

WAC-MVS						79.53 411								75.56 410

PC_three_1452									90.77 214	98.89 23	98.28 79	96.24 1	98.35 256	95.76 98	99.58 23	99.59 27

eth-test2					0.00 464

eth-test					0.00 464

OPU-MVS				98.55 3	98.82 57	96.86 3	98.25 36				98.26 80	96.04 2	99.24 142	95.36 112	99.59 19	99.56 35

test_0728_THIRD									94.78 58	98.73 27	98.87 28	95.87 4	99.84 23	97.45 43	99.72 2	99.77 2

GSMVS																98.45 164

test_part2					99.28 27	95.74 8				98.10 41

sam_mvs1												82.76 217				98.45 164

sam_mvs												81.94 238

test_post1							92.81 409				16.58 457	80.53 262	97.68 339	86.20 313

test_post											17.58 456	81.76 241	98.08 283

patchmatchnet-post											90.45 412	82.65 222	98.10 278

gm-plane-assit					93.22 390	78.89 419			84.82 375		93.52 365		98.64 228	87.72 281

test9_res														94.81 129	99.38 59	99.45 54

agg_prior2														93.94 148	99.38 59	99.50 47

test_prior4						93.66 58	96.42 256

test_prior2							96.35 265		92.80 145	96.03 118	97.59 140	92.01 47		95.01 120	99.38 59

旧先验2							95.94 294		81.66 406	97.34 63			98.82 202	92.26 178

新几何2							95.79 303

原ACMM2							95.67 309

testdata2													99.67 70	85.96 321

segment_acmp												92.89 30

testdata1							95.26 335		93.10 130

plane_prior7					96.21 247	89.98 201

plane_prior6					96.10 261	90.00 197						81.32 248

plane_prior4											96.64 199

plane_prior3						90.00 197			94.46 75	91.34 245

plane_prior2							97.74 106		94.85 50

plane_prior1					96.14 258

plane_prior						89.99 199	97.24 178		94.06 87						92.16 281

HQP5-MVS						89.33 228

HQP-NCC					95.86 269		96.65 239		93.55 104	90.14 269

ACMP_Plane					95.86 269		96.65 239		93.55 104	90.14 269

BP-MVS														92.13 186

HQP4-MVS										90.14 269			98.50 241			95.78 298

HQP2-MVS												80.95 252

NP-MVS					95.99 267	89.81 207					95.87 242

MDTV_nov1_ep13_2view						70.35 437	93.10 404		83.88 386	93.55 187		82.47 226		86.25 312		98.38 172

ACMMP++_ref															90.30 311

ACMMP++															91.02 300

Test By Simon												88.73 103

High-resolution multi-view benchmark