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 11	97.89 3	96.53 81	98.41 74	91.73 109	98.01 59	99.02 1	96.37 4	99.30 1	98.92 10	92.39 37	99.79 33	99.16 5	99.46 40	98.08 171

PGM-MVS		96.81 42	96.53 50	97.65 42	99.35 20	93.53 60	97.65 107	98.98 2	92.22 133	97.14 52	98.44 44	91.17 62	99.85 18	94.35 116	99.46 40	99.57 26

MVS_111021_HR		96.68 51	96.58 49	96.99 70	98.46 70	92.31 93	96.20 245	98.90 3	94.30 62	95.86 105	97.74 104	92.33 38	99.38 113	96.04 65	99.42 47	99.28 65

test_fmvsmconf_n		97.49 12	97.56 9	97.29 55	97.44 142	92.37 90	97.91 76	98.88 4	95.83 8	98.92 12	99.05 5	91.45 53	99.80 30	99.12 6	99.46 40	99.69 12

ACMMP		96.27 63	95.93 65	97.28 57	99.24 28	92.62 82	98.25 37	98.81 5	92.99 109	94.56 134	98.39 48	88.96 89	99.85 18	94.57 115	97.63 133	99.36 60
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 64	96.19 63	96.39 97	98.23 91	91.35 129	96.24 243	98.79 6	93.99 69	95.80 107	97.65 111	89.92 80	99.24 124	95.87 69	99.20 72	98.58 125

patch_mono-2		96.83 41	97.44 13	95.01 175	99.05 39	85.39 304	96.98 177	98.77 7	94.70 45	97.99 32	98.66 27	93.61 19	99.91 1	97.67 18	99.50 34	99.72 11

fmvsm_s_conf0.5_n		96.85 39	97.13 16	96.04 121	98.07 105	90.28 170	97.97 69	98.76 8	94.93 30	98.84 16	99.06 4	88.80 92	99.65 58	99.06 7	98.63 100	98.18 160

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 52	98.21 92	92.75 78	97.83 86	98.73 9	95.04 28	99.30 1	98.84 20	93.34 22	99.78 35	99.32 3	99.13 78	99.50 40

fmvsm_s_conf0.5_n_a		96.75 46	96.93 29	96.20 113	97.64 129	90.72 157	98.00 61	98.73 9	94.55 50	98.91 13	99.08 3	88.22 101	99.63 67	98.91 9	98.37 112	98.25 153

FC-MVSNet-test		93.94 129	93.57 122	95.04 173	95.48 250	91.45 126	98.12 50	98.71 11	93.37 93	90.23 234	96.70 163	87.66 110	97.85 287	91.49 173	90.39 275	95.83 255

UniMVSNet (Re)		93.31 152	92.55 166	95.61 147	95.39 255	93.34 66	97.39 140	98.71 11	93.14 105	90.10 243	94.83 262	87.71 109	98.03 260	91.67 171	83.99 343	95.46 276

fmvsm_l_conf0.5_n_a		97.63 8	97.76 5	97.26 59	98.25 86	92.59 84	97.81 90	98.68 13	94.93 30	99.24 3	98.87 15	93.52 20	99.79 33	99.32 3	99.21 70	99.40 54

FIs		94.09 123	93.70 118	95.27 163	95.70 240	92.03 103	98.10 51	98.68 13	93.36 95	90.39 231	96.70 163	87.63 113	97.94 277	92.25 153	90.50 274	95.84 254

WR-MVS_H		92.00 209	91.35 205	93.95 237	95.09 281	89.47 197	98.04 57	98.68 13	91.46 157	88.34 291	94.68 269	85.86 141	97.56 312	85.77 286	84.24 341	94.82 318

VPA-MVSNet		93.24 154	92.48 171	95.51 153	95.70 240	92.39 89	97.86 81	98.66 16	92.30 132	92.09 193	95.37 240	80.49 232	98.40 214	93.95 123	85.86 315	95.75 265

UniMVSNet_NR-MVSNet		93.37 150	92.67 160	95.47 158	95.34 261	92.83 76	97.17 163	98.58 17	92.98 114	90.13 239	95.80 217	88.37 100	97.85 287	91.71 168	83.93 344	95.73 267

CSCG		96.05 67	95.91 66	96.46 91	99.24 28	90.47 165	98.30 30	98.57 18	89.01 236	93.97 148	97.57 119	92.62 33	99.76 38	94.66 110	99.27 63	99.15 75

MSLP-MVS++		96.94 33	97.06 19	96.59 79	98.72 55	91.86 107	97.67 104	98.49 19	94.66 48	97.24 49	98.41 47	92.31 40	98.94 163	96.61 43	99.46 40	98.96 94

HyFIR lowres test		93.66 141	92.92 147	95.87 129	98.24 87	89.88 183	94.58 310	98.49 19	85.06 330	93.78 151	95.78 221	82.86 189	98.67 192	91.77 166	95.71 179	99.07 85

CHOSEN 1792x2688		94.15 118	93.51 128	96.06 119	98.27 83	89.38 202	95.18 297	98.48 21	85.60 320	93.76 152	97.11 142	83.15 180	99.61 69	91.33 176	98.72 97	99.19 71

PHI-MVS		96.77 44	96.46 56	97.71 40	98.40 75	94.07 48	98.21 44	98.45 22	89.86 209	97.11 54	98.01 83	92.52 35	99.69 52	96.03 66	99.53 28	99.36 60

fmvsm_s_conf0.1_n		96.58 54	96.77 40	96.01 125	96.67 185	90.25 171	97.91 76	98.38 23	94.48 54	98.84 16	99.14 1	88.06 103	99.62 68	98.82 11	98.60 102	98.15 164

PVSNet_BlendedMVS		94.06 124	93.92 114	94.47 207	98.27 83	89.46 199	96.73 196	98.36 24	90.17 202	94.36 137	95.24 246	88.02 104	99.58 77	93.44 134	90.72 270	94.36 338

PVSNet_Blended		94.87 103	94.56 100	95.81 133	98.27 83	89.46 199	95.47 283	98.36 24	88.84 244	94.36 137	96.09 206	88.02 104	99.58 77	93.44 134	98.18 120	98.40 145

3Dnovator	91.36 5	95.19 93	94.44 108	97.44 49	96.56 194	93.36 65	98.65 11	98.36 24	94.12 65	89.25 273	98.06 77	82.20 205	99.77 37	93.41 136	99.32 60	99.18 72

FOURS1					99.55 1	93.34 66	99.29 1	98.35 27	94.98 29	98.49 23

DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 32	95.78 7	97.21 160	98.35 27	95.16 22	98.71 20	98.80 22	95.05 10	99.89 3	96.70 41	99.73 1	99.73 10
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 58	96.47 53	96.16 115	95.48 250	90.69 158	97.91 76	98.33 29	94.07 66	98.93 9	99.14 1	87.44 119	99.61 69	98.63 13	98.32 114	98.18 160

HFP-MVS		97.14 23	96.92 30	97.83 26	99.42 7	94.12 46	98.52 16	98.32 30	93.21 98	97.18 50	98.29 63	92.08 42	99.83 26	95.63 82	99.59 18	99.54 33

ACMMPR		97.07 26	96.84 33	97.79 30	99.44 6	93.88 52	98.52 16	98.31 31	93.21 98	97.15 51	98.33 57	91.35 57	99.86 8	95.63 82	99.59 18	99.62 18

test_fmvsmvis_n_1920		96.70 47	96.84 33	96.31 102	96.62 187	91.73 109	97.98 63	98.30 32	96.19 5	96.10 96	98.95 8	89.42 83	99.76 38	98.90 10	99.08 82	97.43 203

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 33	94.82 28	98.81 7	98.30 32	94.76 43	98.30 26	98.90 12	93.77 17	99.68 54	97.93 14	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 29	98.29 34	94.92 32	98.99 7	98.92 10	95.08 8

MSP-MVS		97.59 10	97.54 10	97.73 37	99.40 11	93.77 56	98.53 15	98.29 34	95.55 13	98.56 22	97.81 99	93.90 15	99.65 58	96.62 42	99.21 70	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 58	95.39 11	99.29 1	98.28 36	94.78 41	98.93 9	98.87 15	96.04 2	99.86 8	97.45 26	99.58 22	99.59 22

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 44	98.28 36					99.86 8	97.52 22	99.67 6	99.75 6

CP-MVS		97.02 29	96.81 37	97.64 44	99.33 21	93.54 59	98.80 8	98.28 36	92.99 109	96.45 82	98.30 62	91.90 45	99.85 18	95.61 84	99.68 4	99.54 33

test_fmvsmconf0.1_n		97.09 24	97.06 19	97.19 64	95.67 242	92.21 96	97.95 72	98.27 39	95.78 10	98.40 25	99.00 6	89.99 78	99.78 35	99.06 7	99.41 50	99.59 22

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 37	98.27 39	95.13 23	99.19 4	98.89 13	95.54 5	99.85 18	97.52 22	99.66 10	99.56 29

test_241102_TWO								98.27 39	95.13 23	98.93 9	98.89 13	94.99 11	99.85 18	97.52 22	99.65 12	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 39	95.09 26	99.19 4	98.81 21	95.54 5	99.65 58

SF-MVS		97.39 15	97.13 16	98.17 15	99.02 42	95.28 19	98.23 41	98.27 39	92.37 131	98.27 27	98.65 29	93.33 23	99.72 45	96.49 47	99.52 29	99.51 37

SteuartSystems-ACMMP		97.62 9	97.53 11	97.87 24	98.39 77	94.25 40	98.43 24	98.27 39	95.34 17	98.11 28	98.56 31	94.53 12	99.71 46	96.57 45	99.62 15	99.65 15
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 22	95.20 20		98.25 45	95.13 23	98.48 24	98.87 15	95.16 7

PVSNet_Blended_VisFu		95.27 88	94.91 91	96.38 98	98.20 93	90.86 150	97.27 152	98.25 45	90.21 201	94.18 142	97.27 133	87.48 118	99.73 42	93.53 131	97.77 131	98.55 126

region2R		97.07 26	96.84 33	97.77 33	99.46 2	93.79 54	98.52 16	98.24 47	93.19 101	97.14 52	98.34 54	91.59 52	99.87 7	95.46 89	99.59 18	99.64 16

PS-CasMVS		91.55 228	90.84 227	93.69 253	94.96 285	88.28 236	97.84 85	98.24 47	91.46 157	88.04 301	95.80 217	79.67 248	97.48 320	87.02 266	84.54 338	95.31 288

DU-MVS		92.90 174	92.04 181	95.49 155	94.95 286	92.83 76	97.16 164	98.24 47	93.02 108	90.13 239	95.71 224	83.47 173	97.85 287	91.71 168	83.93 344	95.78 260

9.14			96.75 41		98.93 47		97.73 97	98.23 50	91.28 165	97.88 35	98.44 44	93.00 26	99.65 58	95.76 75	99.47 39

D2MVS		91.30 243	90.95 221	92.35 296	94.71 303	85.52 300	96.18 246	98.21 51	88.89 242	86.60 328	93.82 312	79.92 244	97.95 276	89.29 217	90.95 267	93.56 351

SDMVSNet		94.17 116	93.61 121	95.86 130	98.09 101	91.37 128	97.35 144	98.20 52	93.18 102	91.79 199	97.28 131	79.13 256	98.93 164	94.61 113	92.84 230	97.28 211

XVS		97.18 21	96.96 28	97.81 28	99.38 14	94.03 50	98.59 12	98.20 52	94.85 34	96.59 74	98.29 63	91.70 48	99.80 30	95.66 77	99.40 51	99.62 18

X-MVStestdata		91.71 217	89.67 278	97.81 28	99.38 14	94.03 50	98.59 12	98.20 52	94.85 34	96.59 74	32.69 405	91.70 48	99.80 30	95.66 77	99.40 51	99.62 18

ACMMP_NAP		97.20 20	96.86 31	98.23 11	99.09 34	95.16 22	97.60 116	98.19 55	92.82 119	97.93 34	98.74 26	91.60 51	99.86 8	96.26 50	99.52 29	99.67 13

CP-MVSNet		91.89 213	91.24 212	93.82 245	95.05 282	88.57 227	97.82 88	98.19 55	91.70 150	88.21 297	95.76 222	81.96 209	97.52 318	87.86 241	84.65 333	95.37 284

ZNCC-MVS		96.96 31	96.67 45	97.85 25	99.37 16	94.12 46	98.49 20	98.18 57	92.64 125	96.39 84	98.18 70	91.61 50	99.88 4	95.59 87	99.55 25	99.57 26

SMA-MVS		97.35 16	97.03 24	98.30 8	99.06 38	95.42 10	97.94 73	98.18 57	90.57 196	98.85 15	98.94 9	93.33 23	99.83 26	96.72 40	99.68 4	99.63 17
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		91.20 247	90.44 243	93.48 262	94.49 311	87.91 251	97.76 93	98.18 57	91.29 162	87.78 305	95.74 223	80.35 235	97.33 331	85.46 290	82.96 354	95.19 299

DELS-MVS		96.61 52	96.38 59	97.30 54	97.79 120	93.19 69	95.96 256	98.18 57	95.23 19	95.87 104	97.65 111	91.45 53	99.70 51	95.87 69	99.44 46	99.00 92
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		89.70 296	88.40 301	93.60 256	95.15 277	90.10 174	97.56 120	98.16 61	87.28 294	86.16 332	94.63 272	77.57 283	98.05 256	74.48 370	84.59 336	92.65 364

VNet		95.89 74	95.45 75	97.21 62	98.07 105	92.94 75	97.50 126	98.15 62	93.87 73	97.52 40	97.61 117	85.29 147	99.53 91	95.81 74	95.27 187	99.16 73

DeepPCF-MVS	93.97 1	96.61 52	97.09 18	95.15 167	98.09 101	86.63 281	96.00 254	98.15 62	95.43 14	97.95 33	98.56 31	93.40 21	99.36 114	96.77 38	99.48 38	99.45 47

SD-MVS		97.41 14	97.53 11	97.06 68	98.57 69	94.46 33	97.92 75	98.14 64	94.82 38	99.01 6	98.55 33	94.18 14	97.41 327	96.94 34	99.64 13	99.32 62
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 39	96.52 51	97.82 27	99.36 18	94.14 45	98.29 31	98.13 65	92.72 122	96.70 66	98.06 77	91.35 57	99.86 8	94.83 104	99.28 62	99.47 46

UA-Net		95.95 72	95.53 72	97.20 63	97.67 125	92.98 74	97.65 107	98.13 65	94.81 39	96.61 72	98.35 51	88.87 90	99.51 96	90.36 193	97.35 143	99.11 81

QAPM		93.45 148	92.27 176	96.98 71	96.77 180	92.62 82	98.39 26	98.12 67	84.50 338	88.27 295	97.77 102	82.39 202	99.81 29	85.40 291	98.81 94	98.51 131

Vis-MVSNet		95.23 90	94.81 92	96.51 85	97.18 149	91.58 119	98.26 36	98.12 67	94.38 60	94.90 127	98.15 72	82.28 203	98.92 165	91.45 175	98.58 104	99.01 89
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 176	91.68 195	96.40 95	95.34 261	92.73 80	98.27 34	98.12 67	84.86 333	85.78 334	97.75 103	78.89 265	99.74 41	87.50 256	98.65 99	96.73 227

TranMVSNet+NR-MVSNet		92.50 186	91.63 196	95.14 168	94.76 298	92.07 101	97.53 124	98.11 70	92.90 117	89.56 261	96.12 201	83.16 179	97.60 310	89.30 216	83.20 353	95.75 265

CPTT-MVS		95.57 82	95.19 85	96.70 73	99.27 26	91.48 123	98.33 28	98.11 70	87.79 279	95.17 124	98.03 80	87.09 125	99.61 69	93.51 132	99.42 47	99.02 86

APD-MVS		96.95 32	96.60 47	98.01 19	99.03 41	94.93 27	97.72 100	98.10 72	91.50 155	98.01 31	98.32 59	92.33 38	99.58 77	94.85 103	99.51 32	99.53 36
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 37	96.60 47	97.64 44	99.40 11	93.44 61	98.50 19	98.09 73	93.27 97	95.95 103	98.33 57	91.04 64	99.88 4	95.20 93	99.57 24	99.60 21

ZD-MVS					99.05 39	94.59 31		98.08 74	89.22 229	97.03 57	98.10 73	92.52 35	99.65 58	94.58 114	99.31 61

MTGPA								98.08 74

MTAPA		97.08 25	96.78 39	97.97 22	99.37 16	94.42 35	97.24 154	98.08 74	95.07 27	96.11 95	98.59 30	90.88 68	99.90 2	96.18 61	99.50 34	99.58 25

CNVR-MVS		97.68 6	97.44 13	98.37 7	98.90 50	95.86 6	97.27 152	98.08 74	95.81 9	97.87 36	98.31 60	94.26 13	99.68 54	97.02 33	99.49 37	99.57 26

DP-MVS Recon		95.68 78	95.12 88	97.37 51	99.19 31	94.19 42	97.03 170	98.08 74	88.35 262	95.09 126	97.65 111	89.97 79	99.48 101	92.08 160	98.59 103	98.44 142

SR-MVS		97.01 30	96.86 31	97.47 48	99.09 34	93.27 68	97.98 63	98.07 79	93.75 76	97.45 42	98.48 41	91.43 55	99.59 74	96.22 53	99.27 63	99.54 33

MCST-MVS		97.18 21	96.84 33	98.20 14	99.30 24	95.35 15	97.12 167	98.07 79	93.54 85	96.08 97	97.69 106	93.86 16	99.71 46	96.50 46	99.39 53	99.55 32

NR-MVSNet		92.34 194	91.27 211	95.53 152	94.95 286	93.05 72	97.39 140	98.07 79	92.65 124	84.46 345	95.71 224	85.00 151	97.77 296	89.71 205	83.52 350	95.78 260

MP-MVS-pluss		96.70 47	96.27 61	97.98 21	99.23 30	94.71 29	96.96 179	98.06 82	90.67 187	95.55 116	98.78 25	91.07 63	99.86 8	96.58 44	99.55 25	99.38 58
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 42	96.71 44	97.12 66	99.01 45	92.31 93	97.98 63	98.06 82	93.11 106	97.44 43	98.55 33	90.93 66	99.55 87	96.06 62	99.25 67	99.51 37

MP-MVS		96.77 44	96.45 57	97.72 38	99.39 13	93.80 53	98.41 25	98.06 82	93.37 93	95.54 118	98.34 54	90.59 72	99.88 4	94.83 104	99.54 27	99.49 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 55	96.27 61	97.22 61	99.32 22	92.74 79	98.74 9	98.06 82	90.57 196	96.77 63	98.35 51	90.21 75	99.53 91	94.80 107	99.63 14	99.38 58

HPM-MVS		96.69 49	96.45 57	97.40 50	99.36 18	93.11 71	98.87 6	98.06 82	91.17 170	96.40 83	97.99 84	90.99 65	99.58 77	95.61 84	99.61 16	99.49 42
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 109	93.80 116	96.64 74	97.07 155	91.97 105	96.32 235	98.06 82	88.94 240	94.50 135	96.78 158	84.60 155	99.27 122	91.90 161	96.02 170	98.68 122

DeepC-MVS	93.07 3	96.06 66	95.66 70	97.29 55	97.96 109	93.17 70	97.30 150	98.06 82	93.92 71	93.38 161	98.66 27	86.83 127	99.73 42	95.60 86	99.22 69	98.96 94
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 18	97.03 24	98.11 17	98.77 53	95.06 25	97.34 145	98.04 89	95.96 6	97.09 55	97.88 92	93.18 25	99.71 46	95.84 73	99.17 74	99.56 29

DeepC-MVS_fast	93.89 2	96.93 34	96.64 46	97.78 31	98.64 64	94.30 37	97.41 135	98.04 89	94.81 39	96.59 74	98.37 49	91.24 59	99.64 66	95.16 94	99.52 29	99.42 53
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 36	96.80 38	97.11 67	99.02 42	92.34 91	97.98 63	98.03 91	93.52 87	97.43 45	98.51 36	91.40 56	99.56 85	96.05 63	99.26 65	99.43 51

RE-MVS-def			96.72 43		99.02 42	92.34 91	97.98 63	98.03 91	93.52 87	97.43 45	98.51 36	90.71 70		96.05 63	99.26 65	99.43 51

RPMNet		88.98 301	87.05 315	94.77 194	94.45 313	87.19 266	90.23 382	98.03 91	77.87 384	92.40 179	87.55 387	80.17 239	99.51 96	68.84 388	93.95 217	97.60 197

save fliter					98.91 49	94.28 38	97.02 172	98.02 94	95.35 16

TEST9					98.70 56	94.19 42	96.41 224	98.02 94	88.17 266	96.03 98	97.56 121	92.74 30	99.59 74

train_agg		96.30 62	95.83 69	97.72 38	98.70 56	94.19 42	96.41 224	98.02 94	88.58 253	96.03 98	97.56 121	92.73 31	99.59 74	95.04 96	99.37 57	99.39 56

test_8					98.67 58	94.06 49	96.37 231	98.01 97	88.58 253	95.98 102	97.55 123	92.73 31	99.58 77

agg_prior					98.67 58	93.79 54		98.00 98		95.68 112			99.57 84

test_prior				97.23 60	98.67 58	92.99 73		98.00 98					99.41 109			99.29 63

WR-MVS		92.34 194	91.53 200	94.77 194	95.13 279	90.83 152	96.40 228	97.98 100	91.88 146	89.29 270	95.54 235	82.50 198	97.80 292	89.79 204	85.27 324	95.69 268

HPM-MVS++		97.34 17	96.97 27	98.47 5	99.08 36	96.16 4	97.55 123	97.97 101	95.59 11	96.61 72	97.89 90	92.57 34	99.84 23	95.95 68	99.51 32	99.40 54

CANet		96.39 59	96.02 64	97.50 47	97.62 131	93.38 63	97.02 172	97.96 102	95.42 15	94.86 128	97.81 99	87.38 121	99.82 28	96.88 36	99.20 72	99.29 63

114514_t		93.95 128	93.06 142	96.63 76	99.07 37	91.61 116	97.46 134	97.96 102	77.99 382	93.00 169	97.57 119	86.14 139	99.33 115	89.22 220	99.15 76	98.94 97

IU-MVS					99.42 7	95.39 11		97.94 104	90.40 200	98.94 8				97.41 29	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 58	96.94 1		97.93 105					99.86 8	97.68 16	99.67 6	99.77 2

No_MVS				98.86 1	98.67 58	96.94 1		97.93 105					99.86 8	97.68 16	99.67 6	99.77 2

Anonymous20231211		90.63 270	89.42 285	94.27 221	98.24 87	89.19 214	98.05 56	97.89 107	79.95 374	88.25 296	94.96 254	72.56 322	98.13 239	89.70 206	85.14 326	95.49 272

原ACMM1				96.38 98	98.59 66	91.09 143		97.89 107	87.41 290	95.22 123	97.68 107	90.25 74	99.54 89	87.95 240	99.12 80	98.49 134

CDPH-MVS		95.97 71	95.38 80	97.77 33	98.93 47	94.44 34	96.35 232	97.88 109	86.98 298	96.65 70	97.89 90	91.99 44	99.47 102	92.26 151	99.46 40	99.39 56

test11								97.88 109

EIA-MVS		95.53 83	95.47 74	95.71 141	97.06 158	89.63 188	97.82 88	97.87 111	93.57 81	93.92 149	95.04 252	90.61 71	98.95 162	94.62 112	98.68 98	98.54 127

CS-MVS		96.86 37	97.06 19	96.26 108	98.16 98	91.16 141	99.09 3	97.87 111	95.30 18	97.06 56	98.03 80	91.72 46	98.71 189	97.10 31	99.17 74	98.90 104

无先验							95.79 266	97.87 111	83.87 346				99.65 58	87.68 250		98.89 107

3Dnovator+	91.43 4	95.40 84	94.48 106	98.16 16	96.90 169	95.34 16	98.48 21	97.87 111	94.65 49	88.53 288	98.02 82	83.69 169	99.71 46	93.18 139	98.96 89	99.44 49

VPNet		92.23 202	91.31 208	94.99 176	95.56 246	90.96 146	97.22 159	97.86 115	92.96 115	90.96 223	96.62 176	75.06 304	98.20 232	91.90 161	83.65 349	95.80 258

test_vis1_n_1920		94.17 116	94.58 99	92.91 282	97.42 143	82.02 343	97.83 86	97.85 116	94.68 46	98.10 29	98.49 38	70.15 337	99.32 117	97.91 15	98.82 93	97.40 205

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 44	97.85 116	94.92 32	98.73 18	98.87 15	95.08 8	99.84 23	97.52 22	99.67 6	99.48 44
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 13	97.33 15	97.69 41	99.25 27	94.24 41	98.07 54	97.85 116	93.72 77	98.57 21	98.35 51	93.69 18	99.40 110	97.06 32	99.46 40	99.44 49
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CS-MVS-test		96.89 35	97.04 23	96.45 92	98.29 82	91.66 115	99.03 4	97.85 116	95.84 7	96.90 59	97.97 86	91.24 59	98.75 183	96.92 35	99.33 59	98.94 97

test_fmvsmconf0.01_n		96.15 65	95.85 68	97.03 69	92.66 359	91.83 108	97.97 69	97.84 120	95.57 12	97.53 39	99.00 6	84.20 163	99.76 38	98.82 11	99.08 82	99.48 44

AdaColmap		94.34 112	93.68 119	96.31 102	98.59 66	91.68 114	96.59 215	97.81 121	89.87 208	92.15 189	97.06 145	83.62 172	99.54 89	89.34 215	98.07 123	97.70 190

ETV-MVS		96.02 68	95.89 67	96.40 95	97.16 150	92.44 88	97.47 132	97.77 122	94.55 50	96.48 79	94.51 277	91.23 61	98.92 165	95.65 80	98.19 119	97.82 185

新几何1				97.32 53	98.60 65	93.59 58		97.75 123	81.58 365	95.75 109	97.85 96	90.04 77	99.67 56	86.50 272	99.13 78	98.69 121

旧先验1					98.38 78	93.38 63		97.75 123			98.09 75	92.30 41			99.01 87	99.16 73

EC-MVSNet		96.42 57	96.47 53	96.26 108	97.01 165	91.52 121	98.89 5	97.75 123	94.42 56	96.64 71	97.68 107	89.32 84	98.60 199	97.45 26	99.11 81	98.67 123

EI-MVSNet-Vis-set		96.51 55	96.47 53	96.63 76	98.24 87	91.20 136	96.89 183	97.73 126	94.74 44	96.49 78	98.49 38	90.88 68	99.58 77	96.44 48	98.32 114	99.13 77

PAPM_NR		95.01 95	94.59 98	96.26 108	98.89 51	90.68 160	97.24 154	97.73 126	91.80 147	92.93 174	96.62 176	89.13 87	99.14 137	89.21 221	97.78 130	98.97 93

Anonymous20240529		91.98 210	90.73 233	95.73 139	98.14 99	89.40 201	97.99 62	97.72 128	79.63 376	93.54 156	97.41 127	69.94 339	99.56 85	91.04 183	91.11 263	98.22 157

CHOSEN 280x420		93.12 161	92.72 159	94.34 215	96.71 184	87.27 262	90.29 381	97.72 128	86.61 305	91.34 211	95.29 242	84.29 162	98.41 213	93.25 138	98.94 90	97.35 208

EI-MVSNet-UG-set		96.34 61	96.30 60	96.47 89	98.20 93	90.93 148	96.86 185	97.72 128	94.67 47	96.16 94	98.46 42	90.43 73	99.58 77	96.23 52	97.96 126	98.90 104

LS3D		93.57 144	92.61 164	96.47 89	97.59 135	91.61 116	97.67 104	97.72 128	85.17 328	90.29 233	98.34 54	84.60 155	99.73 42	83.85 312	98.27 116	98.06 172

PAPR		94.18 115	93.42 135	96.48 88	97.64 129	91.42 127	95.55 278	97.71 132	88.99 237	92.34 185	95.82 216	89.19 85	99.11 140	86.14 278	97.38 141	98.90 104

UGNet		94.04 126	93.28 138	96.31 102	96.85 171	91.19 137	97.88 79	97.68 133	94.40 58	93.00 169	96.18 196	73.39 319	99.61 69	91.72 167	98.46 109	98.13 165
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				95.46 159	98.18 97	88.90 220		97.66 134	82.73 356	97.03 57	98.07 76	90.06 76	98.85 172	89.67 207	98.98 88	98.64 124

test12				97.65 42	98.46 70	94.26 39		97.66 134		95.52 119		90.89 67	99.46 103		99.25 67	99.22 70

DTE-MVSNet		90.56 271	89.75 276	93.01 278	93.95 326	87.25 263	97.64 111	97.65 136	90.74 182	87.12 317	95.68 227	79.97 243	97.00 343	83.33 313	81.66 360	94.78 325

TAPA-MVS	90.10 7	92.30 197	91.22 214	95.56 149	98.33 80	89.60 190	96.79 191	97.65 136	81.83 362	91.52 206	97.23 136	87.94 106	98.91 167	71.31 383	98.37 112	98.17 163
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 162	92.45 172	95.05 172	98.09 101	89.21 211	96.89 183	97.64 138	93.18 102	91.79 199	97.28 131	75.35 303	98.65 194	88.99 226	92.84 230	97.28 211

test_cas_vis1_n_1920		94.48 110	94.55 103	94.28 220	96.78 178	86.45 285	97.63 113	97.64 138	93.32 96	97.68 38	98.36 50	73.75 317	99.08 146	96.73 39	99.05 84	97.31 210

cdsmvs_eth3d_5k		23.24 375	30.99 377	0.00 393	0.00 416	0.00 418	0.00 404	97.63 140	0.00 411	0.00 412	96.88 155	84.38 159	0.00 412	0.00 411	0.00 410	0.00 408

DPM-MVS		95.69 77	94.92 90	98.01 19	98.08 104	95.71 9	95.27 293	97.62 141	90.43 199	95.55 116	97.07 144	91.72 46	99.50 99	89.62 209	98.94 90	98.82 113

sasdasda		96.02 68	95.45 75	97.75 35	97.59 135	95.15 23	98.28 32	97.60 142	94.52 52	96.27 88	96.12 201	87.65 111	99.18 130	96.20 58	94.82 195	98.91 101

canonicalmvs		96.02 68	95.45 75	97.75 35	97.59 135	95.15 23	98.28 32	97.60 142	94.52 52	96.27 88	96.12 201	87.65 111	99.18 130	96.20 58	94.82 195	98.91 101

test222					98.24 87	92.21 96	95.33 288	97.60 142	79.22 378	95.25 121	97.84 98	88.80 92			99.15 76	98.72 118

cascas		91.20 247	90.08 260	94.58 203	94.97 284	89.16 215	93.65 347	97.59 145	79.90 375	89.40 265	92.92 336	75.36 302	98.36 220	92.14 156	94.75 198	96.23 237

h-mvs33		94.15 118	93.52 127	96.04 121	97.81 119	90.22 172	97.62 115	97.58 146	95.19 20	96.74 64	97.45 124	83.67 170	99.61 69	95.85 71	79.73 367	98.29 152

MGCFI-Net		95.94 73	95.40 79	97.56 46	97.59 135	94.62 30	98.21 44	97.57 147	94.41 57	96.17 92	96.16 199	87.54 115	99.17 132	96.19 60	94.73 200	98.91 101

MVSFormer		95.37 85	95.16 86	95.99 126	96.34 212	91.21 134	98.22 42	97.57 147	91.42 159	96.22 90	97.32 129	86.20 137	97.92 281	94.07 120	99.05 84	98.85 110

test_djsdf		93.07 165	92.76 154	94.00 232	93.49 342	88.70 224	98.22 42	97.57 147	91.42 159	90.08 245	95.55 234	82.85 190	97.92 281	94.07 120	91.58 252	95.40 281

OMC-MVS		95.09 94	94.70 96	96.25 111	98.46 70	91.28 130	96.43 222	97.57 147	92.04 142	94.77 130	97.96 87	87.01 126	99.09 144	91.31 177	96.77 157	98.36 149

PS-MVSNAJss		93.74 138	93.51 128	94.44 209	93.91 328	89.28 209	97.75 94	97.56 151	92.50 128	89.94 248	96.54 179	88.65 95	98.18 235	93.83 129	90.90 268	95.86 251

casdiffmvs_mvg		95.81 76	95.57 71	96.51 85	96.87 170	91.49 122	97.50 126	97.56 151	93.99 69	95.13 125	97.92 89	87.89 107	98.78 178	95.97 67	97.33 144	99.26 67
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		92.42 190	91.89 189	94.03 231	93.33 348	88.50 231	97.73 97	97.53 153	92.00 144	88.85 280	96.50 182	75.62 301	98.11 244	93.88 127	91.56 253	95.48 273

mvs_tets		92.31 196	91.76 191	93.94 239	93.41 345	88.29 235	97.63 113	97.53 153	92.04 142	88.76 283	96.45 184	74.62 309	98.09 248	93.91 125	91.48 254	95.45 277

dcpmvs_2		96.37 60	97.05 22	94.31 218	98.96 46	84.11 322	97.56 120	97.51 155	93.92 71	97.43 45	98.52 35	92.75 29	99.32 117	97.32 30	99.50 34	99.51 37

HQP_MVS		93.78 137	93.43 133	94.82 187	96.21 216	89.99 178	97.74 95	97.51 155	94.85 34	91.34 211	96.64 168	81.32 219	98.60 199	93.02 145	92.23 239	95.86 251

plane_prior5								97.51 155					98.60 199	93.02 145	92.23 239	95.86 251

PS-MVSNAJ		95.37 85	95.33 82	95.49 155	97.35 144	90.66 161	95.31 290	97.48 158	93.85 74	96.51 77	95.70 226	88.65 95	99.65 58	94.80 107	98.27 116	96.17 241

API-MVS		94.84 104	94.49 105	95.90 128	97.90 115	92.00 104	97.80 91	97.48 158	89.19 230	94.81 129	96.71 161	88.84 91	99.17 132	88.91 228	98.76 96	96.53 230

MG-MVS		95.61 80	95.38 80	96.31 102	98.42 73	90.53 163	96.04 251	97.48 158	93.47 89	95.67 113	98.10 73	89.17 86	99.25 123	91.27 178	98.77 95	99.13 77

MAR-MVS		94.22 114	93.46 130	96.51 85	98.00 108	92.19 99	97.67 104	97.47 161	88.13 269	93.00 169	95.84 214	84.86 153	99.51 96	87.99 239	98.17 121	97.83 184
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		92.98 169	92.53 168	94.32 216	96.12 226	89.20 212	95.28 291	97.47 161	92.66 123	89.90 249	95.62 230	80.58 230	98.40 214	92.73 149	92.40 237	95.38 283
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 241	90.22 256	94.68 197	94.86 294	87.86 252	97.23 158	97.46 163	87.99 270	89.90 249	96.92 153	66.35 364	98.23 229	90.30 194	90.99 266	97.96 175

nrg030		94.05 125	93.31 137	96.27 107	95.22 272	94.59 31	98.34 27	97.46 163	92.93 116	91.21 221	96.64 168	87.23 124	98.22 230	94.99 101	85.80 316	95.98 250

XVG-OURS		93.72 139	93.35 136	94.80 192	97.07 155	88.61 225	94.79 305	97.46 163	91.97 145	93.99 146	97.86 95	81.74 214	98.88 169	92.64 150	92.67 235	96.92 222

LPG-MVS_test		92.94 172	92.56 165	94.10 226	96.16 221	88.26 237	97.65 107	97.46 163	91.29 162	90.12 241	97.16 139	79.05 258	98.73 185	92.25 153	91.89 247	95.31 288

LGP-MVS_train				94.10 226	96.16 221	88.26 237		97.46 163	91.29 162	90.12 241	97.16 139	79.05 258	98.73 185	92.25 153	91.89 247	95.31 288

MVS		91.71 217	90.44 243	95.51 153	95.20 274	91.59 118	96.04 251	97.45 168	73.44 390	87.36 314	95.60 231	85.42 146	99.10 141	85.97 283	97.46 136	95.83 255

XVG-OURS-SEG-HR		93.86 133	93.55 123	94.81 189	97.06 158	88.53 230	95.28 291	97.45 168	91.68 151	94.08 145	97.68 107	82.41 201	98.90 168	93.84 128	92.47 236	96.98 218

baseline		95.58 81	95.42 78	96.08 117	96.78 178	90.41 168	97.16 164	97.45 168	93.69 80	95.65 114	97.85 96	87.29 122	98.68 191	95.66 77	97.25 148	99.13 77

ab-mvs		93.57 144	92.55 166	96.64 74	97.28 145	91.96 106	95.40 285	97.45 168	89.81 213	93.22 167	96.28 192	79.62 250	99.46 103	90.74 187	93.11 227	98.50 132

xiu_mvs_v2_base		95.32 87	95.29 83	95.40 160	97.22 146	90.50 164	95.44 284	97.44 172	93.70 79	96.46 81	96.18 196	88.59 98	99.53 91	94.79 109	97.81 129	96.17 241

1314		92.81 181	92.03 182	95.14 168	95.33 264	89.52 196	96.04 251	97.44 172	87.72 283	86.25 331	95.33 241	83.84 167	98.79 177	89.26 218	97.05 153	97.11 216

casdiffmvs		95.64 79	95.49 73	96.08 117	96.76 183	90.45 166	97.29 151	97.44 172	94.00 68	95.46 120	97.98 85	87.52 117	98.73 185	95.64 81	97.33 144	99.08 83
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		92.16 204	91.23 213	94.95 181	94.75 300	90.94 147	97.47 132	97.43 175	89.14 231	88.90 277	96.43 185	79.71 247	98.24 228	89.56 210	87.68 299	95.67 270

anonymousdsp		92.16 204	91.55 199	93.97 235	92.58 361	89.55 193	97.51 125	97.42 176	89.42 224	88.40 290	94.84 261	80.66 228	97.88 286	91.87 163	91.28 259	94.48 333

Effi-MVS+		94.93 100	94.45 107	96.36 100	96.61 188	91.47 124	96.41 224	97.41 177	91.02 176	94.50 135	95.92 210	87.53 116	98.78 178	93.89 126	96.81 156	98.84 112

HQP3-MVS								97.39 178							92.10 244

HQP-MVS		93.19 157	92.74 157	94.54 205	95.86 233	89.33 205	96.65 206	97.39 178	93.55 82	90.14 235	95.87 212	80.95 222	98.50 207	92.13 157	92.10 244	95.78 260

PLC	91.00 6	94.11 122	93.43 133	96.13 116	98.58 68	91.15 142	96.69 202	97.39 178	87.29 293	91.37 210	96.71 161	88.39 99	99.52 95	87.33 259	97.13 152	97.73 188
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 264	89.86 269	93.45 264	93.54 339	87.60 258	97.70 103	97.37 181	88.85 243	87.65 307	94.08 304	81.08 221	98.10 245	84.68 299	83.79 348	94.66 330

UnsupCasMVSNet_eth		85.99 334	84.45 338	90.62 338	89.97 379	82.40 340	93.62 348	97.37 181	89.86 209	78.59 379	92.37 345	65.25 371	95.35 372	82.27 326	70.75 388	94.10 344

ACMM	89.79 8	92.96 170	92.50 170	94.35 213	96.30 214	88.71 223	97.58 118	97.36 183	91.40 161	90.53 228	96.65 167	79.77 246	98.75 183	91.24 179	91.64 250	95.59 271
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 95	94.76 93	95.75 136	96.58 191	91.71 111	96.25 240	97.35 184	92.99 109	96.70 66	96.63 173	82.67 193	99.44 106	96.22 53	97.46 136	96.11 246

xiu_mvs_v1_base		95.01 95	94.76 93	95.75 136	96.58 191	91.71 111	96.25 240	97.35 184	92.99 109	96.70 66	96.63 173	82.67 193	99.44 106	96.22 53	97.46 136	96.11 246

xiu_mvs_v1_base_debi		95.01 95	94.76 93	95.75 136	96.58 191	91.71 111	96.25 240	97.35 184	92.99 109	96.70 66	96.63 173	82.67 193	99.44 106	96.22 53	97.46 136	96.11 246

diffmvs		95.25 89	95.13 87	95.63 145	96.43 208	89.34 204	95.99 255	97.35 184	92.83 118	96.31 85	97.37 128	86.44 132	98.67 192	96.26 50	97.19 150	98.87 109
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		94.71 108	94.02 112	96.79 72	97.71 124	92.05 102	96.59 215	97.35 184	90.61 193	94.64 132	96.93 150	86.41 133	99.39 111	91.20 180	94.71 201	98.94 97

F-COLMAP		93.58 143	92.98 145	95.37 161	98.40 75	88.98 218	97.18 162	97.29 189	87.75 282	90.49 229	97.10 143	85.21 148	99.50 99	86.70 269	96.72 160	97.63 192

XVG-ACMP-BASELINE		90.93 260	90.21 257	93.09 276	94.31 319	85.89 295	95.33 288	97.26 190	91.06 175	89.38 266	95.44 239	68.61 348	98.60 199	89.46 212	91.05 264	94.79 323

PCF-MVS	89.48 11	91.56 227	89.95 266	96.36 100	96.60 189	92.52 86	92.51 367	97.26 190	79.41 377	88.90 277	96.56 178	84.04 166	99.55 87	77.01 361	97.30 146	97.01 217
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 185	92.14 179	94.05 229	96.40 209	88.20 240	97.36 143	97.25 192	91.52 154	88.30 293	96.64 168	78.46 270	98.72 188	91.86 164	91.48 254	95.23 295
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		93.28 153	92.76 154	94.82 187	94.63 306	90.77 155	96.65 206	97.18 193	93.72 77	91.68 203	97.26 134	79.33 254	98.63 196	92.13 157	92.28 238	95.07 301
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 174	92.02 183	95.56 149	98.19 95	90.80 153	95.27 293	97.18 193	87.96 271	91.86 198	95.68 227	80.44 233	98.99 160	84.01 307	97.54 135	96.89 223

alignmvs		95.87 75	95.23 84	97.78 31	97.56 140	95.19 21	97.86 81	97.17 195	94.39 59	96.47 80	96.40 187	85.89 140	99.20 127	96.21 57	95.11 191	98.95 96

MVS_Test		94.89 102	94.62 97	95.68 143	96.83 174	89.55 193	96.70 200	97.17 195	91.17 170	95.60 115	96.11 205	87.87 108	98.76 182	93.01 147	97.17 151	98.72 118

Fast-Effi-MVS+		93.46 147	92.75 156	95.59 148	96.77 180	90.03 175	96.81 190	97.13 197	88.19 265	91.30 214	94.27 293	86.21 136	98.63 196	87.66 251	96.46 167	98.12 166

EI-MVSNet		93.03 167	92.88 149	93.48 262	95.77 238	86.98 271	96.44 220	97.12 198	90.66 189	91.30 214	97.64 114	86.56 129	98.05 256	89.91 200	90.55 272	95.41 278

MVSTER		93.20 156	92.81 153	94.37 212	96.56 194	89.59 191	97.06 169	97.12 198	91.24 166	91.30 214	95.96 208	82.02 208	98.05 256	93.48 133	90.55 272	95.47 275

test_yl		94.78 106	94.23 110	96.43 93	97.74 122	91.22 132	96.85 186	97.10 200	91.23 167	95.71 110	96.93 150	84.30 160	99.31 119	93.10 140	95.12 189	98.75 115

DCV-MVSNet		94.78 106	94.23 110	96.43 93	97.74 122	91.22 132	96.85 186	97.10 200	91.23 167	95.71 110	96.93 150	84.30 160	99.31 119	93.10 140	95.12 189	98.75 115

LTVRE_ROB	88.41 13	90.99 256	89.92 268	94.19 222	96.18 219	89.55 193	96.31 236	97.09 202	87.88 274	85.67 335	95.91 211	78.79 266	98.57 203	81.50 329	89.98 278	94.44 336
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		92.73 183	92.88 149	92.29 299	96.08 229	81.05 351	97.98 63	97.08 203	90.72 184	96.79 62	98.18 70	63.07 375	98.45 211	97.62 20	98.42 111	97.36 206

v10		91.04 254	90.23 254	93.49 261	94.12 322	88.16 243	97.32 148	97.08 203	88.26 264	88.29 294	94.22 298	82.17 206	97.97 268	86.45 273	84.12 342	94.33 339

v144192		91.06 253	90.28 250	93.39 265	93.66 337	87.23 265	96.83 189	97.07 205	87.43 289	89.69 256	94.28 292	81.48 217	98.00 263	87.18 263	84.92 332	94.93 309

v1192		91.07 252	90.23 254	93.58 258	93.70 334	87.82 254	96.73 196	97.07 205	87.77 280	89.58 259	94.32 290	80.90 226	97.97 268	86.52 271	85.48 319	94.95 305

v8		91.29 244	90.53 242	93.57 259	94.15 321	88.12 244	97.34 145	97.06 207	88.99 237	88.32 292	94.26 295	83.08 182	98.01 262	87.62 253	83.92 346	94.57 332

mvs_anonymous		93.82 135	93.74 117	94.06 228	96.44 207	85.41 302	95.81 264	97.05 208	89.85 211	90.09 244	96.36 189	87.44 119	97.75 297	93.97 122	96.69 161	99.02 86

IterMVS-LS		92.29 198	91.94 186	93.34 267	96.25 215	86.97 272	96.57 218	97.05 208	90.67 187	89.50 264	94.80 264	86.59 128	97.64 305	89.91 200	86.11 314	95.40 281
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 262	90.03 265	93.29 269	93.55 338	86.96 273	96.74 195	97.04 210	87.36 291	89.52 263	94.34 287	80.23 238	97.97 268	86.27 274	85.21 325	94.94 307

CDS-MVSNet		94.14 121	93.54 124	95.93 127	96.18 219	91.46 125	96.33 234	97.04 210	88.97 239	93.56 154	96.51 180	87.55 114	97.89 285	89.80 203	95.95 172	98.44 142
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v1144		91.37 238	90.60 238	93.68 254	93.89 329	88.23 239	96.84 188	97.03 212	88.37 261	89.69 256	94.39 284	82.04 207	97.98 265	87.80 243	85.37 321	94.84 315

v1240		90.70 268	89.85 270	93.23 271	93.51 341	86.80 274	96.61 212	97.02 213	87.16 296	89.58 259	94.31 291	79.55 251	97.98 265	85.52 289	85.44 320	94.90 312

EPP-MVSNet		95.22 91	95.04 89	95.76 134	97.49 141	89.56 192	98.67 10	97.00 214	90.69 185	94.24 140	97.62 116	89.79 81	98.81 176	93.39 137	96.49 165	98.92 100

V42		91.58 226	90.87 223	93.73 249	94.05 325	88.50 231	97.32 148	96.97 215	88.80 249	89.71 254	94.33 288	82.54 197	98.05 256	89.01 225	85.07 328	94.64 331

test_fmvs1		93.21 155	93.53 125	92.25 301	96.55 196	81.20 350	97.40 139	96.96 216	90.68 186	96.80 61	98.04 79	69.25 344	98.40 214	97.58 21	98.50 105	97.16 215

FMVSNet2		91.31 242	90.08 260	94.99 176	96.51 201	92.21 96	97.41 135	96.95 217	88.82 246	88.62 285	94.75 266	73.87 313	97.42 326	85.20 294	88.55 293	95.35 285

ACMH	87.59 16	90.53 272	89.42 285	93.87 243	96.21 216	87.92 249	97.24 154	96.94 218	88.45 259	83.91 355	96.27 193	71.92 323	98.62 198	84.43 302	89.43 284	95.05 303
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 239	90.27 251	94.59 199	96.51 201	91.18 138	97.50 126	96.93 219	88.82 246	89.35 267	94.51 277	73.87 313	97.29 333	86.12 279	88.82 288	95.31 288

test1		91.35 239	90.27 251	94.59 199	96.51 201	91.18 138	97.50 126	96.93 219	88.82 246	89.35 267	94.51 277	73.87 313	97.29 333	86.12 279	88.82 288	95.31 288

FMVSNet3		91.78 215	90.69 236	95.03 174	96.53 199	92.27 95	97.02 172	96.93 219	89.79 214	89.35 267	94.65 271	77.01 286	97.47 321	86.12 279	88.82 288	95.35 285

FMVSNet1		89.88 291	88.31 302	94.59 199	95.41 254	91.18 138	97.50 126	96.93 219	86.62 304	87.41 312	94.51 277	65.94 368	97.29 333	83.04 316	87.43 302	95.31 288

GeoE		93.89 131	93.28 138	95.72 140	96.96 168	89.75 187	98.24 40	96.92 223	89.47 222	92.12 191	97.21 137	84.42 158	98.39 218	87.71 246	96.50 164	99.01 89

miper_enhance_ethall		91.54 229	91.01 220	93.15 274	95.35 260	87.07 270	93.97 333	96.90 224	86.79 302	89.17 274	93.43 331	86.55 130	97.64 305	89.97 199	86.93 306	94.74 327

eth_miper_zixun_eth		91.02 255	90.59 239	92.34 298	95.33 264	84.35 318	94.10 330	96.90 224	88.56 255	88.84 281	94.33 288	84.08 165	97.60 310	88.77 231	84.37 340	95.06 302

TAMVS		94.01 127	93.46 130	95.64 144	96.16 221	90.45 166	96.71 199	96.89 226	89.27 228	93.46 159	96.92 153	87.29 122	97.94 277	88.70 232	95.74 177	98.53 128

miper_ehance_all_eth		91.59 224	91.13 217	92.97 280	95.55 247	86.57 282	94.47 314	96.88 227	87.77 280	88.88 279	94.01 305	86.22 135	97.54 314	89.49 211	86.93 306	94.79 323

v2v482		91.59 224	90.85 226	93.80 246	93.87 330	88.17 242	96.94 180	96.88 227	89.54 219	89.53 262	94.90 258	81.70 215	98.02 261	89.25 219	85.04 330	95.20 296

CNLPA		94.28 113	93.53 125	96.52 82	98.38 78	92.55 85	96.59 215	96.88 227	90.13 205	91.91 195	97.24 135	85.21 148	99.09 144	87.64 252	97.83 128	97.92 177

PAPM		91.52 230	90.30 249	95.20 165	95.30 267	89.83 184	93.38 353	96.85 230	86.26 311	88.59 286	95.80 217	84.88 152	98.15 237	75.67 366	95.93 173	97.63 192

c3_l		91.38 236	90.89 222	92.88 284	95.58 245	86.30 288	94.68 307	96.84 231	88.17 266	88.83 282	94.23 296	85.65 144	97.47 321	89.36 214	84.63 334	94.89 313

pm-mvs1		90.72 267	89.65 280	93.96 236	94.29 320	89.63 188	97.79 92	96.82 232	89.07 233	86.12 333	95.48 238	78.61 268	97.78 294	86.97 267	81.67 359	94.46 334

test_vis1_n		92.37 193	92.26 177	92.72 289	94.75 300	82.64 335	98.02 58	96.80 233	91.18 169	97.77 37	97.93 88	58.02 383	98.29 226	97.63 19	98.21 118	97.23 214

CMPMVS	62.92 21	85.62 338	84.92 335	87.74 359	89.14 384	73.12 389	94.17 328	96.80 233	73.98 388	73.65 387	94.93 256	66.36 363	97.61 309	83.95 309	91.28 259	92.48 368
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 279	89.77 274	91.78 314	94.33 317	84.72 316	95.55 278	96.73 235	86.17 313	86.36 330	95.28 244	71.28 328	97.80 292	84.09 306	98.14 122	92.81 361

Effi-MVS+-dtu		93.08 164	93.21 140	92.68 292	96.02 230	83.25 332	97.14 166	96.72 236	93.85 74	91.20 222	93.44 328	83.08 182	98.30 225	91.69 170	95.73 178	96.50 232

TSAR-MVS + GP.		96.69 49	96.49 52	97.27 58	98.31 81	93.39 62	96.79 191	96.72 236	94.17 64	97.44 43	97.66 110	92.76 28	99.33 115	96.86 37	97.76 132	99.08 83

1112_ss		93.37 150	92.42 173	96.21 112	97.05 160	90.99 144	96.31 236	96.72 236	86.87 301	89.83 252	96.69 165	86.51 131	99.14 137	88.12 237	93.67 221	98.50 132

PVSNet	86.66 18	92.24 201	91.74 194	93.73 249	97.77 121	83.69 329	92.88 362	96.72 236	87.91 273	93.00 169	94.86 260	78.51 269	99.05 154	86.53 270	97.45 140	98.47 137

miper_lstm_enhance		90.50 275	90.06 264	91.83 310	95.33 264	83.74 326	93.86 339	96.70 240	87.56 287	87.79 304	93.81 313	83.45 175	96.92 345	87.39 257	84.62 335	94.82 318

v148		90.99 256	90.38 245	92.81 287	93.83 331	85.80 296	96.78 193	96.68 241	89.45 223	88.75 284	93.93 309	82.96 188	97.82 291	87.83 242	83.25 351	94.80 321

ACMH+	87.92 14	90.20 283	89.18 290	93.25 270	96.48 204	86.45 285	96.99 176	96.68 241	88.83 245	84.79 344	96.22 195	70.16 336	98.53 205	84.42 303	88.04 296	94.77 326

CANet_DTU		94.37 111	93.65 120	96.55 80	96.46 206	92.13 100	96.21 244	96.67 243	94.38 60	93.53 157	97.03 147	79.34 253	99.71 46	90.76 186	98.45 110	97.82 185

cl____		90.96 259	90.32 247	92.89 283	95.37 258	86.21 291	94.46 316	96.64 244	87.82 276	88.15 299	94.18 299	82.98 186	97.54 314	87.70 247	85.59 317	94.92 311

HY-MVS	89.66 9	93.87 132	92.95 146	96.63 76	97.10 154	92.49 87	95.64 275	96.64 244	89.05 235	93.00 169	95.79 220	85.77 143	99.45 105	89.16 224	94.35 203	97.96 175

Test_1112_low_res		92.84 179	91.84 190	95.85 131	97.04 161	89.97 181	95.53 280	96.64 244	85.38 323	89.65 258	95.18 247	85.86 141	99.10 141	87.70 247	93.58 226	98.49 134

DIV-MVS_self_test		90.97 258	90.33 246	92.88 284	95.36 259	86.19 292	94.46 316	96.63 247	87.82 276	88.18 298	94.23 296	82.99 185	97.53 316	87.72 244	85.57 318	94.93 309

Fast-Effi-MVS+-dtu		92.29 198	91.99 184	93.21 273	95.27 268	85.52 300	97.03 170	96.63 247	92.09 140	89.11 276	95.14 249	80.33 236	98.08 249	87.54 255	94.74 199	96.03 249

UnsupCasMVSNet_bld		82.13 351	79.46 356	90.14 344	88.00 389	82.47 338	90.89 379	96.62 249	78.94 379	75.61 383	84.40 392	56.63 386	96.31 354	77.30 358	66.77 395	91.63 375

cl22		91.21 246	90.56 241	93.14 275	96.09 228	86.80 274	94.41 318	96.58 250	87.80 278	88.58 287	93.99 307	80.85 227	97.62 308	89.87 202	86.93 306	94.99 304

RRT_MVS		93.10 162	92.83 151	93.93 241	94.76 298	88.04 245	98.47 22	96.55 251	93.44 90	90.01 247	97.04 146	80.64 229	97.93 280	94.33 117	90.21 277	95.83 255

jason		94.84 104	94.39 109	96.18 114	95.52 248	90.93 148	96.09 249	96.52 252	89.28 227	96.01 101	97.32 129	84.70 154	98.77 181	95.15 95	98.91 92	98.85 110
jason: jason.
tt0805		91.09 251	90.07 263	94.16 224	95.61 243	88.31 234	97.56 120	96.51 253	89.56 218	89.17 274	95.64 229	67.08 362	98.38 219	91.07 182	88.44 294	95.80 258

AUN-MVS		91.76 216	90.75 231	94.81 189	97.00 166	88.57 227	96.65 206	96.49 254	89.63 216	92.15 189	96.12 201	78.66 267	98.50 207	90.83 184	79.18 370	97.36 206

hse-mvs2		93.45 148	92.99 143	94.81 189	97.02 162	88.59 226	96.69 202	96.47 255	95.19 20	96.74 64	96.16 199	83.67 170	98.48 210	95.85 71	79.13 371	97.35 208

EG-PatchMatch MVS		87.02 324	85.44 328	91.76 316	92.67 358	85.00 311	96.08 250	96.45 256	83.41 352	79.52 375	93.49 325	57.10 385	97.72 299	79.34 349	90.87 269	92.56 365

KD-MVS_self_test		85.95 335	84.95 334	88.96 354	89.55 383	79.11 374	95.13 298	96.42 257	85.91 316	84.07 353	90.48 365	70.03 338	94.82 374	80.04 341	72.94 385	92.94 359

pmmvs6		87.81 316	86.19 323	92.69 291	91.32 371	86.30 288	97.34 145	96.41 258	80.59 373	84.05 354	94.37 286	67.37 357	97.67 302	84.75 298	79.51 369	94.09 346

PMMVS		92.86 176	92.34 174	94.42 211	94.92 289	86.73 277	94.53 312	96.38 259	84.78 335	94.27 139	95.12 251	83.13 181	98.40 214	91.47 174	96.49 165	98.12 166

RPSCF		90.75 265	90.86 224	90.42 341	96.84 172	76.29 382	95.61 276	96.34 260	83.89 344	91.38 209	97.87 93	76.45 291	98.78 178	87.16 264	92.23 239	96.20 239

MSDG		91.42 234	90.24 253	94.96 180	97.15 152	88.91 219	93.69 345	96.32 261	85.72 319	86.93 325	96.47 183	80.24 237	98.98 161	80.57 338	95.05 192	96.98 218

OurMVSNet-221017-0		90.51 274	90.19 258	91.44 322	93.41 345	81.25 348	96.98 177	96.28 262	91.68 151	86.55 329	96.30 191	74.20 312	97.98 265	88.96 227	87.40 304	95.09 300

MVP-Stereo		90.74 266	90.08 260	92.71 290	93.19 350	88.20 240	95.86 261	96.27 263	86.07 314	84.86 343	94.76 265	77.84 281	97.75 297	83.88 311	98.01 124	92.17 373
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 99	94.56 100	96.29 106	96.34 212	91.21 134	95.83 263	96.27 263	88.93 241	96.22 90	96.88 155	86.20 137	98.85 172	95.27 92	99.05 84	98.82 113

BH-untuned		92.94 172	92.62 163	93.92 242	97.22 146	86.16 293	96.40 228	96.25 265	90.06 206	89.79 253	96.17 198	83.19 178	98.35 221	87.19 262	97.27 147	97.24 213

CL-MVSNet_self_test		86.31 330	85.15 332	89.80 348	88.83 386	81.74 346	93.93 336	96.22 266	86.67 303	85.03 341	90.80 364	78.09 277	94.50 375	74.92 369	71.86 387	93.15 357

IS-MVSNet		94.90 101	94.52 104	96.05 120	97.67 125	90.56 162	98.44 23	96.22 266	93.21 98	93.99 146	97.74 104	85.55 145	98.45 211	89.98 198	97.86 127	99.14 76

FA-MVS(test-final)		93.52 146	92.92 147	95.31 162	96.77 180	88.54 229	94.82 304	96.21 268	89.61 217	94.20 141	95.25 245	83.24 177	99.14 137	90.01 197	96.16 169	98.25 153

GA-MVS		91.38 236	90.31 248	94.59 199	94.65 305	87.62 257	94.34 321	96.19 269	90.73 183	90.35 232	93.83 310	71.84 324	97.96 272	87.22 261	93.61 224	98.21 158

IterMVS-SCA-FT		90.31 277	89.81 272	91.82 311	95.52 248	84.20 321	94.30 324	96.15 270	90.61 193	87.39 313	94.27 293	75.80 298	96.44 352	87.34 258	86.88 310	94.82 318

IterMVS		90.15 285	89.67 278	91.61 318	95.48 250	83.72 327	94.33 322	96.12 271	89.99 207	87.31 316	94.15 301	75.78 300	96.27 355	86.97 267	86.89 309	94.83 316
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 182	91.51 203	96.52 82	98.77 53	90.99 144	97.38 142	96.08 272	82.38 358	89.29 270	97.87 93	83.77 168	99.69 52	81.37 334	96.69 161	98.89 107

pmmvs4		90.93 260	89.85 270	94.17 223	93.34 347	90.79 154	94.60 309	96.02 273	84.62 336	87.45 310	95.15 248	81.88 212	97.45 323	87.70 247	87.87 298	94.27 343

ppachtmachnet_test		88.35 311	87.29 310	91.53 319	92.45 364	83.57 330	93.75 342	95.97 274	84.28 339	85.32 340	94.18 299	79.00 264	96.93 344	75.71 365	84.99 331	94.10 344

Anonymous20240521		86.42 328	85.44 328	89.34 352	90.33 376	79.79 366	96.73 196	95.92 275	83.71 348	83.25 358	91.36 361	63.92 373	96.01 356	78.39 353	85.36 322	92.22 371

ITE_SJBPF				92.43 295	95.34 261	85.37 305		95.92 275	91.47 156	87.75 306	96.39 188	71.00 330	97.96 272	82.36 325	89.86 280	93.97 347

test_fmvs2		89.77 295	89.93 267	89.31 353	93.68 336	76.37 381	97.64 111	95.90 277	89.84 212	91.49 207	96.26 194	58.77 382	97.10 337	94.65 111	91.13 262	94.46 334

USDC		88.94 302	87.83 307	92.27 300	94.66 304	84.96 312	93.86 339	95.90 277	87.34 292	83.40 357	95.56 233	67.43 356	98.19 234	82.64 324	89.67 282	93.66 350

COLMAP_ROB	87.81 15	90.40 276	89.28 288	93.79 247	97.95 110	87.13 269	96.92 181	95.89 279	82.83 355	86.88 327	97.18 138	73.77 316	99.29 121	78.44 352	93.62 223	94.95 305
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 135	93.08 141	96.02 123	97.88 116	89.96 182	97.72 100	95.85 280	92.43 129	95.86 105	98.44 44	68.42 352	99.39 111	96.31 49	94.85 193	98.71 120

VDDNet		93.05 166	92.07 180	96.02 123	96.84 172	90.39 169	98.08 53	95.85 280	86.22 312	95.79 108	98.46 42	67.59 355	99.19 128	94.92 102	94.85 193	98.47 137

Vis-MVSNet (Re-imp)		94.15 118	93.88 115	94.95 181	97.61 132	87.92 249	98.10 51	95.80 282	92.22 133	93.02 168	97.45 124	84.53 157	97.91 284	88.24 236	97.97 125	99.02 86

MM		97.29 19	96.98 26	98.23 11	98.01 107	95.03 26	98.07 54	95.76 283	97.78 1	97.52 40	98.80 22	88.09 102	99.86 8	99.44 1	99.37 57	99.80 1

KD-MVS_2432*1600		84.81 342	82.64 346	91.31 324	91.07 373	85.34 306	91.22 374	95.75 284	85.56 321	83.09 359	90.21 368	67.21 358	95.89 358	77.18 359	62.48 398	92.69 362

miper_refine_blended		84.81 342	82.64 346	91.31 324	91.07 373	85.34 306	91.22 374	95.75 284	85.56 321	83.09 359	90.21 368	67.21 358	95.89 358	77.18 359	62.48 398	92.69 362

FE-MVS		92.05 208	91.05 218	95.08 171	96.83 174	87.93 248	93.91 338	95.70 286	86.30 309	94.15 143	94.97 253	76.59 289	99.21 126	84.10 305	96.86 154	98.09 170

tpm cat1		88.36 310	87.21 313	91.81 312	95.13 279	80.55 357	92.58 366	95.70 286	74.97 387	87.45 310	91.96 355	78.01 280	98.17 236	80.39 340	88.74 291	96.72 228

our_test_3		88.78 306	87.98 306	91.20 328	92.45 364	82.53 337	93.61 349	95.69 288	85.77 318	84.88 342	93.71 315	79.99 242	96.78 350	79.47 346	86.24 311	94.28 342

BH-w/o		92.14 206	91.75 192	93.31 268	96.99 167	85.73 297	95.67 271	95.69 288	88.73 251	89.26 272	94.82 263	82.97 187	98.07 253	85.26 293	96.32 168	96.13 245

CR-MVSNet		90.82 263	89.77 274	93.95 237	94.45 313	87.19 266	90.23 382	95.68 290	86.89 300	92.40 179	92.36 348	80.91 224	97.05 339	81.09 337	93.95 217	97.60 197

Patchmtry		88.64 308	87.25 311	92.78 288	94.09 323	86.64 278	89.82 385	95.68 290	80.81 370	87.63 308	92.36 348	80.91 224	97.03 340	78.86 350	85.12 327	94.67 329

testing91		91.90 212	91.02 219	94.53 206	96.54 197	86.55 284	95.86 261	95.64 292	91.77 148	91.89 196	93.47 327	69.94 339	98.86 170	90.23 196	93.86 219	98.18 160

BH-RMVSNet		92.72 184	91.97 185	94.97 179	97.16 150	87.99 247	96.15 247	95.60 293	90.62 192	91.87 197	97.15 141	78.41 271	98.57 203	83.16 314	97.60 134	98.36 149

PVSNet_0	82.17 19	85.46 339	83.64 342	90.92 331	95.27 268	79.49 370	90.55 380	95.60 293	83.76 347	83.00 361	89.95 370	71.09 329	97.97 268	82.75 322	60.79 400	95.31 288

SCA		91.84 214	91.18 216	93.83 244	95.59 244	84.95 313	94.72 306	95.58 295	90.82 179	92.25 187	93.69 316	75.80 298	98.10 245	86.20 276	95.98 171	98.45 139

AllTest		90.23 281	88.98 293	93.98 233	97.94 111	86.64 278	96.51 219	95.54 296	85.38 323	85.49 337	96.77 159	70.28 334	99.15 135	80.02 342	92.87 228	96.15 243

TestCases				93.98 233	97.94 111	86.64 278		95.54 296	85.38 323	85.49 337	96.77 159	70.28 334	99.15 135	80.02 342	92.87 228	96.15 243

iter_conf05		93.18 160	92.63 161	94.83 186	96.64 186	90.69 158	97.60 116	95.53 298	92.52 127	91.58 204	96.64 168	76.35 294	98.13 239	95.43 90	91.42 256	95.68 269

mvsmamba		93.83 134	93.46 130	94.93 184	94.88 293	90.85 151	98.55 14	95.49 299	94.24 63	91.29 217	96.97 149	83.04 184	98.14 238	95.56 88	91.17 261	95.78 260

tpmvs		89.83 294	89.15 291	91.89 308	94.92 289	80.30 361	93.11 358	95.46 300	86.28 310	88.08 300	92.65 338	80.44 233	98.52 206	81.47 330	89.92 279	96.84 224

pmmvs5		89.86 293	88.87 296	92.82 286	92.86 354	86.23 290	96.26 239	95.39 301	84.24 340	87.12 317	94.51 277	74.27 311	97.36 330	87.61 254	87.57 300	94.86 314

PatchmatchNet		91.91 211	91.35 205	93.59 257	95.38 256	84.11 322	93.15 357	95.39 301	89.54 219	92.10 192	93.68 318	82.82 191	98.13 239	84.81 297	95.32 186	98.52 129
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 233	91.32 207	91.79 313	95.15 277	79.20 373	93.42 352	95.37 303	88.55 256	93.49 158	93.67 319	82.49 199	98.27 227	90.41 191	89.34 285	97.90 178

Anonymous20231206		87.09 323	86.14 324	89.93 347	91.22 372	80.35 359	96.11 248	95.35 304	83.57 350	84.16 349	93.02 334	73.54 318	95.61 366	72.16 380	86.14 313	93.84 349

MIMVSNet1		84.93 341	83.05 343	90.56 339	89.56 382	84.84 315	95.40 285	95.35 304	83.91 343	80.38 371	92.21 352	57.23 384	93.34 387	70.69 386	82.75 357	93.50 352

TDRefinement		86.53 326	84.76 337	91.85 309	82.23 399	84.25 319	96.38 230	95.35 304	84.97 332	84.09 352	94.94 255	65.76 369	98.34 224	84.60 301	74.52 381	92.97 358

TR-MVS		91.48 232	90.59 239	94.16 224	96.40 209	87.33 259	95.67 271	95.34 307	87.68 284	91.46 208	95.52 236	76.77 288	98.35 221	82.85 319	93.61 224	96.79 226

EPNet_dtu		91.71 217	91.28 210	92.99 279	93.76 333	83.71 328	96.69 202	95.28 308	93.15 104	87.02 321	95.95 209	83.37 176	97.38 329	79.46 347	96.84 155	97.88 180
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 320	85.79 326	91.78 314	94.80 297	87.28 261	95.49 282	95.28 308	84.09 342	83.85 356	91.82 356	62.95 376	94.17 379	78.48 351	85.34 323	93.91 348

MDTV_nov1_ep13			90.76 230		95.22 272	80.33 360	93.03 360	95.28 308	88.14 268	92.84 175	93.83 310	81.34 218	98.08 249	82.86 317	94.34 204

LF4IMVS		87.94 314	87.25 311	89.98 346	92.38 366	80.05 365	94.38 319	95.25 311	87.59 286	84.34 346	94.74 267	64.31 372	97.66 304	84.83 296	87.45 301	92.23 370

TransMVSNet (Re)		88.94 302	87.56 308	93.08 277	94.35 316	88.45 233	97.73 97	95.23 312	87.47 288	84.26 348	95.29 242	79.86 245	97.33 331	79.44 348	74.44 382	93.45 354

test20.03		86.14 333	85.40 330	88.35 355	90.12 377	80.06 364	95.90 260	95.20 313	88.59 252	81.29 366	93.62 321	71.43 327	92.65 389	71.26 384	81.17 362	92.34 369

new-patchmatchnet		83.18 348	81.87 351	87.11 362	86.88 391	75.99 383	93.70 343	95.18 314	85.02 331	77.30 382	88.40 380	65.99 367	93.88 384	74.19 374	70.18 389	91.47 379

MDA-MVSNet_test_wron		85.87 336	84.23 340	90.80 336	92.38 366	82.57 336	93.17 355	95.15 315	82.15 359	67.65 391	92.33 351	78.20 273	95.51 369	77.33 356	79.74 366	94.31 341

YYNet1		85.87 336	84.23 340	90.78 337	92.38 366	82.46 339	93.17 355	95.14 316	82.12 360	67.69 390	92.36 348	78.16 276	95.50 370	77.31 357	79.73 367	94.39 337

Baseline_NR-MVSNet		91.20 247	90.62 237	92.95 281	93.83 331	88.03 246	97.01 175	95.12 317	88.42 260	89.70 255	95.13 250	83.47 173	97.44 324	89.66 208	83.24 352	93.37 355

thres200		92.23 202	91.39 204	94.75 196	97.61 132	89.03 217	96.60 214	95.09 318	92.08 141	93.28 164	94.00 306	78.39 272	99.04 157	81.26 336	94.18 208	96.19 240

ADS-MVSNet		89.89 290	88.68 298	93.53 260	95.86 233	84.89 314	90.93 377	95.07 319	83.23 353	91.28 218	91.81 357	79.01 262	97.85 287	79.52 344	91.39 257	97.84 182

pmmvs-eth3d		86.22 331	84.45 338	91.53 319	88.34 388	87.25 263	94.47 314	95.01 320	83.47 351	79.51 376	89.61 373	69.75 341	95.71 363	83.13 315	76.73 378	91.64 374

Anonymous202405211		92.07 207	90.83 228	95.76 134	98.19 95	88.75 222	97.58 118	95.00 321	86.00 315	93.64 153	97.45 124	66.24 366	99.53 91	90.68 189	92.71 233	99.01 89

MDA-MVSNet-bldmvs		85.00 340	82.95 345	91.17 329	93.13 352	83.33 331	94.56 311	95.00 321	84.57 337	65.13 395	92.65 338	70.45 333	95.85 360	73.57 376	77.49 374	94.33 339

ambc				86.56 365	83.60 396	70.00 392	85.69 394	94.97 323		80.60 370	88.45 379	37.42 398	96.84 348	82.69 323	75.44 380	92.86 360

testgi		87.97 313	87.21 313	90.24 343	92.86 354	80.76 352	96.67 205	94.97 323	91.74 149	85.52 336	95.83 215	62.66 377	94.47 377	76.25 363	88.36 295	95.48 273

dp		88.90 304	88.26 304	90.81 334	94.58 309	76.62 380	92.85 363	94.93 325	85.12 329	90.07 246	93.07 333	75.81 297	98.12 243	80.53 339	87.42 303	97.71 189

test_fmvs3		83.21 347	83.02 344	83.78 369	86.77 392	68.34 395	96.76 194	94.91 326	86.49 306	84.14 351	89.48 374	36.04 399	91.73 391	91.86 164	80.77 364	91.26 381

test_0402		86.46 327	84.79 336	91.45 321	95.02 283	85.55 299	96.29 238	94.89 327	80.90 367	82.21 363	93.97 308	68.21 353	97.29 333	62.98 392	88.68 292	91.51 377

tfpn200view9		92.38 192	91.52 201	94.95 181	97.85 117	89.29 207	97.41 135	94.88 328	92.19 137	93.27 165	94.46 282	78.17 274	99.08 146	81.40 331	94.08 212	96.48 233

CVMVSNet		91.23 245	91.75 192	89.67 349	95.77 238	74.69 384	96.44 220	94.88 328	85.81 317	92.18 188	97.64 114	79.07 257	95.58 368	88.06 238	95.86 175	98.74 117

thres400		92.42 190	91.52 201	95.12 170	97.85 117	89.29 207	97.41 135	94.88 328	92.19 137	93.27 165	94.46 282	78.17 274	99.08 146	81.40 331	94.08 212	96.98 218

EPNet		95.20 92	94.56 100	97.14 65	92.80 356	92.68 81	97.85 84	94.87 331	96.64 3	92.46 178	97.80 101	86.23 134	99.65 58	93.72 130	98.62 101	99.10 82
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 222	90.72 234	94.32 216	96.48 204	86.11 294	95.81 264	94.76 332	91.55 153	91.75 201	93.44 328	68.55 350	98.82 174	90.43 190	93.69 220	98.04 173

SixPastTwentyTwo		89.15 300	88.54 300	90.98 330	93.49 342	80.28 362	96.70 200	94.70 333	90.78 180	84.15 350	95.57 232	71.78 325	97.71 300	84.63 300	85.07 328	94.94 307

iter_conf05_11		93.70 140	92.99 143	95.84 132	97.02 162	90.22 172	95.57 277	94.66 334	92.81 120	96.17 92	96.51 180	69.56 342	99.07 150	95.03 97	99.60 17	98.23 155

thres100view900		92.43 189	91.58 198	94.98 178	97.92 113	89.37 203	97.71 102	94.66 334	92.20 135	93.31 163	94.90 258	78.06 278	99.08 146	81.40 331	94.08 212	96.48 233

thres600view7		92.49 188	91.60 197	95.18 166	97.91 114	89.47 197	97.65 107	94.66 334	92.18 139	93.33 162	94.91 257	78.06 278	99.10 141	81.61 328	94.06 216	96.98 218

PatchT		88.87 305	87.42 309	93.22 272	94.08 324	85.10 310	89.51 386	94.64 337	81.92 361	92.36 182	88.15 383	80.05 241	97.01 342	72.43 379	93.65 222	97.54 200

baseline1		92.82 180	91.90 188	95.55 151	97.20 148	90.77 155	97.19 161	94.58 338	92.20 135	92.36 182	96.34 190	84.16 164	98.21 231	89.20 222	83.90 347	97.68 191

Gipuma		67.86 366	65.41 368	75.18 382	92.66 359	73.45 387	66.50 401	94.52 339	53.33 400	57.80 401	66.07 401	30.81 401	89.20 395	48.15 401	78.88 373	62.90 401
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 220	90.75 231	94.47 207	96.53 199	86.56 283	95.76 268	94.51 340	91.10 174	91.24 220	93.59 322	68.59 349	98.86 170	91.10 181	94.29 205	98.00 174

CostFormer		91.18 250	90.70 235	92.62 293	94.84 295	81.76 345	94.09 331	94.43 341	84.15 341	92.72 176	93.77 314	79.43 252	98.20 232	90.70 188	92.18 242	97.90 178

tpm2		89.96 287	89.21 289	92.23 302	94.91 291	81.25 348	93.78 341	94.42 342	80.62 372	91.56 205	93.44 328	76.44 292	97.94 277	85.60 288	92.08 246	97.49 201

JIA-IIPM		88.26 312	87.04 316	91.91 307	93.52 340	81.42 347	89.38 387	94.38 343	80.84 369	90.93 224	80.74 394	79.22 255	97.92 281	82.76 321	91.62 251	96.38 236

dmvs_re		90.21 282	89.50 283	92.35 296	95.47 253	85.15 308	95.70 270	94.37 344	90.94 178	88.42 289	93.57 323	74.63 308	95.67 365	82.80 320	89.57 283	96.22 238

Patchmatch-test		89.42 298	87.99 305	93.70 252	95.27 268	85.11 309	88.98 388	94.37 344	81.11 366	87.10 319	93.69 316	82.28 203	97.50 319	74.37 372	94.76 197	98.48 136

LCM-MVSNet		72.55 360	69.39 364	82.03 371	70.81 409	65.42 400	90.12 384	94.36 346	55.02 399	65.88 393	81.72 393	24.16 407	89.96 392	74.32 373	68.10 393	90.71 384

ADS-MVSNet2		89.45 297	88.59 299	92.03 305	95.86 233	82.26 341	90.93 377	94.32 347	83.23 353	91.28 218	91.81 357	79.01 262	95.99 357	79.52 344	91.39 257	97.84 182

EU-MVSNet		88.72 307	88.90 295	88.20 357	93.15 351	74.21 385	96.63 211	94.22 348	85.18 327	87.32 315	95.97 207	76.16 295	94.98 373	85.27 292	86.17 312	95.41 278

MVS_0304		97.04 28	96.73 42	97.96 23	97.60 134	94.36 36	98.01 59	94.09 349	97.33 2	96.29 86	98.79 24	89.73 82	99.86 8	99.36 2	99.42 47	99.67 13

MIMVSNet		88.50 309	86.76 319	93.72 251	94.84 295	87.77 255	91.39 372	94.05 350	86.41 308	87.99 302	92.59 341	63.27 374	95.82 362	77.44 355	92.84 230	97.57 199

OpenMVS_ROB	81.14 20	84.42 344	82.28 350	90.83 332	90.06 378	84.05 324	95.73 269	94.04 351	73.89 389	80.17 374	91.53 360	59.15 381	97.64 305	66.92 390	89.05 287	90.80 383

TinyColmap		86.82 325	85.35 331	91.21 326	94.91 291	82.99 334	93.94 335	94.02 352	83.58 349	81.56 365	94.68 269	62.34 378	98.13 239	75.78 364	87.35 305	92.52 367

ETVMVS		90.52 273	89.14 292	94.67 198	96.81 177	87.85 253	95.91 259	93.97 353	89.71 215	92.34 185	92.48 343	65.41 370	97.96 272	81.37 334	94.27 206	98.21 158

bld_raw_dy_0_64		92.85 178	91.91 187	95.69 142	97.02 162	89.81 185	97.88 79	93.96 354	92.57 126	92.59 177	96.79 157	69.53 343	99.02 158	95.03 97	91.78 249	98.23 155

IB-MVS	87.33 17	89.91 288	88.28 303	94.79 193	95.26 271	87.70 256	95.12 299	93.95 355	89.35 226	87.03 320	92.49 342	70.74 332	99.19 128	89.18 223	81.37 361	97.49 201
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		87.13 322	87.02 317	87.47 360	95.16 275	73.21 388	95.00 300	93.93 356	88.55 256	86.96 322	91.99 353	75.90 296	94.00 381	61.59 394	94.11 209	95.20 296

myMVS_eth3d		87.18 321	86.38 321	89.58 350	95.16 275	79.53 368	95.00 300	93.93 356	88.55 256	86.96 322	91.99 353	56.23 387	94.00 381	75.47 368	94.11 209	95.20 296

testing222		90.31 277	88.96 294	94.35 213	96.54 197	87.29 260	95.50 281	93.84 358	90.97 177	91.75 201	92.96 335	62.18 379	98.00 263	82.86 317	94.08 212	97.76 187

test_f		80.57 353	79.62 355	83.41 370	83.38 397	67.80 397	93.57 350	93.72 359	80.80 371	77.91 381	87.63 386	33.40 400	92.08 390	87.14 265	79.04 372	90.34 385

LCM-MVSNet-Re		92.50 186	92.52 169	92.44 294	96.82 176	81.89 344	96.92 181	93.71 360	92.41 130	84.30 347	94.60 273	85.08 150	97.03 340	91.51 172	97.36 142	98.40 145

tpm		90.25 280	89.74 277	91.76 316	93.92 327	79.73 367	93.98 332	93.54 361	88.28 263	91.99 194	93.25 332	77.51 284	97.44 324	87.30 260	87.94 297	98.12 166

ET-MVSNet_ETH3D		91.49 231	90.11 259	95.63 145	96.40 209	91.57 120	95.34 287	93.48 362	90.60 195	75.58 384	95.49 237	80.08 240	96.79 349	94.25 118	89.76 281	98.52 129

LFMVS		93.60 142	92.63 161	96.52 82	98.13 100	91.27 131	97.94 73	93.39 363	90.57 196	96.29 86	98.31 60	69.00 345	99.16 134	94.18 119	95.87 174	99.12 80

Patchmatch-RL test		87.38 319	86.24 322	90.81 334	88.74 387	78.40 377	88.12 392	93.17 364	87.11 297	82.17 364	89.29 375	81.95 210	95.60 367	88.64 233	77.02 375	98.41 144

test-LLR		91.42 234	91.19 215	92.12 303	94.59 307	80.66 354	94.29 325	92.98 365	91.11 172	90.76 226	92.37 345	79.02 260	98.07 253	88.81 229	96.74 158	97.63 192

test-mter		90.19 284	89.54 282	92.12 303	94.59 307	80.66 354	94.29 325	92.98 365	87.68 284	90.76 226	92.37 345	67.67 354	98.07 253	88.81 229	96.74 158	97.63 192

WB-MVSnew		89.88 291	89.56 281	90.82 333	94.57 310	83.06 333	95.65 274	92.85 367	87.86 275	90.83 225	94.10 302	79.66 249	96.88 346	76.34 362	94.19 207	92.54 366

testing3		87.67 317	86.88 318	90.05 345	96.14 224	80.71 353	97.10 168	92.85 367	90.15 204	87.54 309	94.55 275	55.70 388	94.10 380	73.77 375	94.10 211	95.35 285

test_method		66.11 367	64.89 369	69.79 384	72.62 407	35.23 415	65.19 402	92.83 369	20.35 405	65.20 394	88.08 384	43.14 396	82.70 402	73.12 378	63.46 397	91.45 380

test0.0.03 1		89.37 299	88.70 297	91.41 323	92.47 363	85.63 298	95.22 296	92.70 370	91.11 172	86.91 326	93.65 320	79.02 260	93.19 388	78.00 354	89.18 286	95.41 278

new_pmnet		82.89 349	81.12 354	88.18 358	89.63 381	80.18 363	91.77 371	92.57 371	76.79 386	75.56 385	88.23 382	61.22 380	94.48 376	71.43 382	82.92 355	89.87 386

mvsany_test1		93.93 130	93.98 113	93.78 248	94.94 288	86.80 274	94.62 308	92.55 372	88.77 250	96.85 60	98.49 38	88.98 88	98.08 249	95.03 97	95.62 181	96.46 235

thisisatest0515		92.29 198	91.30 209	95.25 164	96.60 189	88.90 220	94.36 320	92.32 373	87.92 272	93.43 160	94.57 274	77.28 285	99.00 159	89.42 213	95.86 175	97.86 181

thisisatest0530		93.03 167	92.21 178	95.49 155	97.07 155	89.11 216	97.49 131	92.19 374	90.16 203	94.09 144	96.41 186	76.43 293	99.05 154	90.38 192	95.68 180	98.31 151

tttt0517		92.96 170	92.33 175	94.87 185	97.11 153	87.16 268	97.97 69	92.09 375	90.63 191	93.88 150	97.01 148	76.50 290	99.06 153	90.29 195	95.45 184	98.38 147

K. test v3		87.64 318	86.75 320	90.32 342	93.02 353	79.48 371	96.61 212	92.08 376	90.66 189	80.25 373	94.09 303	67.21 358	96.65 351	85.96 284	80.83 363	94.83 316

TESTMET0.1,1		90.06 286	89.42 285	91.97 306	94.41 315	80.62 356	94.29 325	91.97 377	87.28 294	90.44 230	92.47 344	68.79 346	97.67 302	88.50 235	96.60 163	97.61 196

PM-MVS		83.48 346	81.86 352	88.31 356	87.83 390	77.59 379	93.43 351	91.75 378	86.91 299	80.63 369	89.91 371	44.42 395	95.84 361	85.17 295	76.73 378	91.50 378

baseline2		91.63 221	90.86 224	93.94 239	94.33 317	86.32 287	95.92 258	91.64 379	89.37 225	86.94 324	94.69 268	81.62 216	98.69 190	88.64 233	94.57 202	96.81 225

APD_test1		79.31 355	77.70 358	84.14 368	89.11 385	69.07 394	92.36 370	91.50 380	69.07 392	73.87 386	92.63 340	39.93 397	94.32 378	70.54 387	80.25 365	89.02 388

FPMVS		71.27 361	69.85 363	75.50 381	74.64 404	59.03 404	91.30 373	91.50 380	58.80 396	57.92 400	88.28 381	29.98 403	85.53 401	53.43 399	82.84 356	81.95 394

door								91.13 382

door-mid								91.06 383

EGC-MVSNET		68.77 365	63.01 370	86.07 367	92.49 362	82.24 342	93.96 334	90.96 384	0.71 410	2.62 411	90.89 363	53.66 389	93.46 385	57.25 397	84.55 337	82.51 393

mvsany_test3		83.59 345	82.44 349	87.03 363	83.80 395	73.82 386	93.70 343	90.92 385	86.42 307	82.51 362	90.26 367	46.76 394	95.71 363	90.82 185	76.76 377	91.57 376

pmmvs3		79.97 354	77.50 359	87.39 361	82.80 398	79.38 372	92.70 365	90.75 386	70.69 391	78.66 378	87.47 388	51.34 392	93.40 386	73.39 377	69.65 390	89.38 387

UWE-MVS		89.91 288	89.48 284	91.21 326	95.88 232	78.23 378	94.91 303	90.26 387	89.11 232	92.35 184	94.52 276	68.76 347	97.96 272	83.95 309	95.59 182	97.42 204

DSMNet-mixed		86.34 329	86.12 325	87.00 364	89.88 380	70.43 390	94.93 302	90.08 388	77.97 383	85.42 339	92.78 337	74.44 310	93.96 383	74.43 371	95.14 188	96.62 229

MVS-HIRNet		82.47 350	81.21 353	86.26 366	95.38 256	69.21 393	88.96 389	89.49 389	66.28 393	80.79 368	74.08 398	68.48 351	97.39 328	71.93 381	95.47 183	92.18 372

WB-MVS		76.77 357	76.63 360	77.18 376	85.32 393	56.82 406	94.53 312	89.39 390	82.66 357	71.35 388	89.18 376	75.03 305	88.88 396	35.42 404	66.79 394	85.84 390

test1111		93.19 157	92.82 152	94.30 219	97.58 139	84.56 317	98.21 44	89.02 391	93.53 86	94.58 133	98.21 67	72.69 320	99.05 154	93.06 143	98.48 108	99.28 65

SSC-MVS		76.05 358	75.83 361	76.72 380	84.77 394	56.22 407	94.32 323	88.96 392	81.82 363	70.52 389	88.91 377	74.79 307	88.71 397	33.69 405	64.71 396	85.23 391

ECVR-MVS		93.19 157	92.73 158	94.57 204	97.66 127	85.41 302	98.21 44	88.23 393	93.43 91	94.70 131	98.21 67	72.57 321	99.07 150	93.05 144	98.49 106	99.25 68

EPMVS		90.70 268	89.81 272	93.37 266	94.73 302	84.21 320	93.67 346	88.02 394	89.50 221	92.38 181	93.49 325	77.82 282	97.78 294	86.03 282	92.68 234	98.11 169

ANet_high		63.94 368	59.58 371	77.02 377	61.24 411	66.06 398	85.66 395	87.93 395	78.53 381	42.94 403	71.04 400	25.42 406	80.71 403	52.60 400	30.83 404	84.28 392

PMMVS2		70.19 362	66.92 365	80.01 372	76.35 403	65.67 399	86.22 393	87.58 396	64.83 395	62.38 396	80.29 395	26.78 405	88.49 399	63.79 391	54.07 401	85.88 389

lessismore_v0				90.45 340	91.96 369	79.09 375		87.19 397		80.32 372	94.39 284	66.31 365	97.55 313	84.00 308	76.84 376	94.70 328

PMVS	53.92 22	58.58 369	55.40 372	68.12 385	51.00 412	48.64 409	78.86 398	87.10 398	46.77 401	35.84 407	74.28 397	8.76 411	86.34 400	42.07 402	73.91 383	69.38 399
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis1_rt		86.16 332	85.06 333	89.46 351	93.47 344	80.46 358	96.41 224	86.61 399	85.22 326	79.15 377	88.64 378	52.41 391	97.06 338	93.08 142	90.57 271	90.87 382

testf1		69.31 363	66.76 366	76.94 378	78.61 401	61.93 402	88.27 390	86.11 400	55.62 397	59.69 397	85.31 390	20.19 409	89.32 393	57.62 395	69.44 391	79.58 395

APD_test2		69.31 363	66.76 366	76.94 378	78.61 401	61.93 402	88.27 390	86.11 400	55.62 397	59.69 397	85.31 390	20.19 409	89.32 393	57.62 395	69.44 391	79.58 395

gg-mvs-nofinetune		87.82 315	85.61 327	94.44 209	94.46 312	89.27 210	91.21 376	84.61 402	80.88 368	89.89 251	74.98 396	71.50 326	97.53 316	85.75 287	97.21 149	96.51 231

dmvs_testset		81.38 352	82.60 348	77.73 375	91.74 370	51.49 408	93.03 360	84.21 403	89.07 233	78.28 380	91.25 362	76.97 287	88.53 398	56.57 398	82.24 358	93.16 356

GG-mvs-BLEND				93.62 255	93.69 335	89.20 212	92.39 369	83.33 404		87.98 303	89.84 372	71.00 330	96.87 347	82.08 327	95.40 185	94.80 321

MTMP							97.86 81	82.03 405

DeepMVS_CX				74.68 383	90.84 375	64.34 401		81.61 406	65.34 394	67.47 392	88.01 385	48.60 393	80.13 404	62.33 393	73.68 384	79.58 395

E-PMN		53.28 370	52.56 374	55.43 387	74.43 405	47.13 410	83.63 397	76.30 407	42.23 402	42.59 404	62.22 403	28.57 404	74.40 405	31.53 406	31.51 403	44.78 402

test2506		91.60 223	90.78 229	94.04 230	97.66 127	83.81 325	98.27 34	75.53 408	93.43 91	95.23 122	98.21 67	67.21 358	99.07 150	93.01 147	98.49 106	99.25 68

EMVS		52.08 372	51.31 375	54.39 388	72.62 407	45.39 412	83.84 396	75.51 409	41.13 403	40.77 405	59.65 404	30.08 402	73.60 406	28.31 407	29.90 405	44.18 403

test_vis3_rt		72.73 359	70.55 362	79.27 373	80.02 400	68.13 396	93.92 337	74.30 410	76.90 385	58.99 399	73.58 399	20.29 408	95.37 371	84.16 304	72.80 386	74.31 398

MVE	50.73 23	53.25 371	48.81 376	66.58 386	65.34 410	57.50 405	72.49 400	70.94 411	40.15 404	39.28 406	63.51 402	6.89 413	73.48 407	38.29 403	42.38 402	68.76 400
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 373	53.82 373	46.29 389	33.73 413	45.30 413	78.32 399	67.24 412	18.02 406	50.93 402	87.05 389	52.99 390	53.11 408	70.76 385	25.29 406	40.46 404

N_pmnet		78.73 356	78.71 357	78.79 374	92.80 356	46.50 411	94.14 329	43.71 413	78.61 380	80.83 367	91.66 359	74.94 306	96.36 353	67.24 389	84.45 339	93.50 352

wuyk23d		25.11 374	24.57 378	26.74 390	73.98 406	39.89 414	57.88 403	9.80 414	12.27 407	10.39 408	6.97 410	7.03 412	36.44 409	25.43 408	17.39 407	3.89 407

testmvs		13.36 376	16.33 379	4.48 392	5.04 414	2.26 417	93.18 354	3.28 415	2.70 408	8.24 409	21.66 406	2.29 415	2.19 410	7.58 409	2.96 408	9.00 406

test123		13.04 377	15.66 380	5.18 391	4.51 415	3.45 416	92.50 368	1.81 416	2.50 409	7.58 410	20.15 407	3.67 414	2.18 411	7.13 410	1.07 409	9.90 405

test_blank		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet_test		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

DCPMVS		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

pcd_1.5k_mvsjas		7.39 379	9.85 382	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	88.65 95	0.00 412	0.00 411	0.00 410	0.00 408

sosnet-low-res		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uncertanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

Regformer		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

n2								0.00 417

nn								0.00 417

ab-mvs-re		8.06 378	10.74 381	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	96.69 165	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

WAC-MVS						79.53 368								75.56 367

PC_three_1452									90.77 181	98.89 14	98.28 65	96.24 1	98.35 221	95.76 75	99.58 22	99.59 22

eth-test2					0.00 416

eth-test					0.00 416

OPU-MVS				98.55 3	98.82 52	96.86 3	98.25 37				98.26 66	96.04 2	99.24 124	95.36 91	99.59 18	99.56 29

test_0728_THIRD									94.78 41	98.73 18	98.87 15	95.87 4	99.84 23	97.45 26	99.72 2	99.77 2

GSMVS																98.45 139

test_part2					99.28 25	95.74 8				98.10 29

sam_mvs1												82.76 192				98.45 139

sam_mvs												81.94 211

test_post1							92.81 364				16.58 409	80.53 231	97.68 301	86.20 276

test_post											17.58 408	81.76 213	98.08 249

patchmatchnet-post											90.45 366	82.65 196	98.10 245

gm-plane-assit					93.22 349	78.89 376			84.82 334		93.52 324		98.64 195	87.72 244

test9_res														94.81 106	99.38 54	99.45 47

agg_prior2														93.94 124	99.38 54	99.50 40

test_prior4						93.66 57	96.42 223

test_prior2							96.35 232		92.80 121	96.03 98	97.59 118	92.01 43		95.01 100	99.38 54

旧先验2							95.94 257		81.66 364	97.34 48			98.82 174	92.26 151

新几何2							95.79 266

原ACMM2							95.67 271

testdata2													99.67 56	85.96 284

segment_acmp												92.89 27

testdata1							95.26 295		93.10 107

plane_prior7					96.21 216	89.98 180

plane_prior6					96.10 227	90.00 176						81.32 219

plane_prior4											96.64 168

plane_prior3						90.00 176			94.46 55	91.34 211

plane_prior2							97.74 95		94.85 34

plane_prior1					96.14 224

plane_prior						89.99 178	97.24 154		94.06 67						92.16 243

HQP5-MVS						89.33 205

HQP-NCC					95.86 233		96.65 206		93.55 82	90.14 235

ACMP_Plane					95.86 233		96.65 206		93.55 82	90.14 235

BP-MVS														92.13 157

HQP4-MVS										90.14 235			98.50 207			95.78 260

HQP2-MVS												80.95 222

NP-MVS					95.99 231	89.81 185					95.87 212

MDTV_nov1_ep13_2view						70.35 391	93.10 359		83.88 345	93.55 155		82.47 200		86.25 275		98.38 147

ACMMP++_ref															90.30 276

ACMMP++															91.02 265

Test By Simon												88.73 94

High-resolution multi-view benchmark