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.

DP-MVS Recon		91.72 110	90.85 120	94.34 40	99.50 1	85.00 81	98.51 49	95.96 171	80.57 310	88.08 178	97.63 99	76.84 144	99.89 10	85.67 216	94.88 141	98.13 91

MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 10	98.94 31	97.10 37	95.17 4	92.11 106	98.46 39	87.33 27	99.97 2	97.21 46	99.31 4	99.63 7

MG-MVS		94.25 38	93.72 49	95.85 12	99.38 3	89.35 11	97.98 80	98.09 9	89.99 68	92.34 100	96.97 133	81.30 73	98.99 127	88.54 186	98.88 20	99.20 25

AdaColmap		88.81 193	87.61 205	92.39 143	99.33 4	79.95 237	96.70 196	95.58 198	77.51 367	83.05 262	96.69 146	61.90 338	99.72 57	84.29 226	93.47 167	97.50 155

CNVR-MVS		96.30 1	96.54 1	95.55 16	99.31 5	87.69 25	99.06 23	97.12 35	94.66 10	96.79 30	98.78 14	86.42 32	99.95 6	97.59 39	99.18 7	99.00 32

NCCC		95.63 7	95.94 8	94.69 33	99.21 6	85.15 76	99.16 11	96.96 50	94.11 15	95.59 49	98.64 24	85.07 38	99.91 7	95.61 63	99.10 9	99.00 32

OPU-MVS				97.30 2	99.19 7	92.31 3	99.12 16				98.54 29	92.06 3	99.84 17	99.11 5	99.37 1	99.74 1

ME-MVS		94.82 22	95.04 24	94.17 50	99.17 8	83.70 105	97.66 105	97.22 24	85.79 174	95.34 51	98.90 5	84.89 39	99.86 13	97.78 35	98.60 34	98.94 35

ZD-MVS					99.09 9	83.22 118		96.60 99	82.88 269	93.61 81	98.06 71	82.93 63	99.14 117	95.51 66	98.49 43

MED-MVS test				94.20 48	99.06 10	83.70 105	98.35 56	97.14 30	87.45 120	97.03 26	98.90 5		99.96 3	97.78 35	98.60 34	98.94 35

MED-MVS		95.43 12	95.84 10	94.20 48	99.06 10	83.70 105	98.35 56	97.14 30	85.79 174	97.03 26	98.90 5	89.87 12	99.96 3	97.78 35	98.60 34	98.94 35

TestfortrainingZip a		95.44 11	95.38 18	95.64 13	99.06 10	88.36 15	98.35 56	97.14 30	87.45 120	97.03 26	98.90 5	89.87 12	99.96 3	91.98 121	98.60 34	98.61 58

DVP-MVS++		96.05 4	96.41 3	94.96 25	99.05 13	85.34 65	98.13 70	96.77 71	88.38 92	97.70 13	98.77 15	92.06 3	99.84 17	97.47 40	99.37 1	99.70 3

MSC_two_6792asdad				97.14 3	99.05 13	92.19 4		96.83 62					99.81 27	98.08 26	98.81 24	99.43 11

No_MVS				97.14 3	99.05 13	92.19 4		96.83 62					99.81 27	98.08 26	98.81 24	99.43 11

DVP-MVS		95.58 9	95.91 9	94.57 36	99.05 13	85.18 71	99.06 23	96.46 119	88.75 82	96.69 31	98.76 17	87.69 25	99.76 44	97.90 30	98.85 21	98.77 45
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
test0726					99.05 13	85.18 71	99.11 19	96.78 65	88.75 82	97.65 17	98.91 2	87.69 25

test_0728_SECOND				95.14 21	99.04 18	86.14 43	99.06 23	96.77 71					99.84 17	97.90 30	98.85 21	99.45 10

SED-MVS		95.88 5	96.22 4	94.87 26	99.03 19	85.03 79	99.12 16	96.78 65	88.72 84	97.79 10	98.91 2	88.48 19	99.82 23	98.15 22	98.97 17	99.74 1

IU-MVS					99.03 19	85.34 65		96.86 60	92.05 41	98.74 1				98.15 22	98.97 17	99.42 13

test_241102_ONE					99.03 19	85.03 79		96.78 65	88.72 84	97.79 10	98.90 5	88.48 19	99.82 23

test_one_0601					98.91 22	84.56 89		96.70 82	88.06 102	96.57 36	98.77 15	88.04 23

test_part2					98.90 23	85.14 77				96.07 43

PAPR		92.74 72	92.17 93	94.45 38	98.89 24	84.87 84	97.20 143	96.20 150	87.73 112	88.40 169	98.12 63	78.71 107	99.76 44	87.99 193	96.28 118	98.74 47

DeepC-MVS_fast	89.06 2	94.48 32	94.30 41	95.02 23	98.86 25	85.68 55	98.06 76	96.64 93	93.64 21	91.74 113	98.54 29	80.17 84	99.90 8	92.28 114	98.75 29	99.49 8
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		94.56 29	94.75 28	93.96 56	98.84 26	83.40 114	98.04 78	96.41 125	85.79 174	95.00 60	98.28 53	84.32 49	99.18 114	97.35 43	98.77 28	99.28 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPE-MVS		95.32 13	95.55 14	94.64 34	98.79 27	84.87 84	97.77 96	96.74 76	86.11 161	96.54 37	98.89 10	88.39 21	99.74 52	97.67 38	99.05 12	99.31 20
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APD-MVS		93.61 49	93.59 53	93.69 70	98.76 28	83.26 117	97.21 141	96.09 158	82.41 280	94.65 67	98.21 55	81.96 70	98.81 139	94.65 78	98.36 51	99.01 31
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HFP-MVS		92.89 66	92.86 73	92.98 105	98.71 29	81.12 186	97.58 112	96.70 82	85.20 192	91.75 112	97.97 78	78.47 111	99.71 60	90.95 133	98.41 47	98.12 92

region2R		92.72 75	92.70 75	92.79 116	98.68 30	80.53 218	97.53 117	96.51 112	85.22 190	91.94 110	97.98 76	77.26 133	99.67 68	90.83 140	98.37 50	98.18 85

test_prior				93.09 100	98.68 30	81.91 160		96.40 127					99.06 124			98.29 77

ACMMPR		92.69 80	92.67 76	92.75 118	98.66 32	80.57 212	97.58 112	96.69 84	85.20 192	91.57 114	97.92 79	77.01 141	99.67 68	90.95 133	98.41 47	98.00 102

API-MVS		90.18 154	88.97 170	93.80 60	98.66 32	82.95 124	97.50 121	95.63 197	75.16 391	86.31 209	97.69 91	72.49 228	99.90 8	81.26 265	96.07 125	98.56 60

CDPH-MVS		93.12 59	92.91 70	93.74 64	98.65 34	83.88 98	97.67 104	96.26 144	83.00 266	93.22 85	98.24 54	81.31 72	99.21 107	89.12 172	98.74 30	98.14 89

TEST9					98.64 35	83.71 103	97.82 91	96.65 90	84.29 227	95.16 54	98.09 66	84.39 45	99.36 97

train_agg		94.28 36	94.45 36	93.74 64	98.64 35	83.71 103	97.82 91	96.65 90	84.50 217	95.16 54	98.09 66	84.33 46	99.36 97	95.91 59	98.96 19	98.16 87

test_8					98.63 37	83.64 109	97.81 93	96.63 95	84.50 217	95.10 57	98.11 64	84.33 46	99.23 105

HPM-MVS++		95.32 13	95.48 16	94.85 27	98.62 38	86.04 44	97.81 93	96.93 53	92.45 30	95.69 47	98.50 34	85.38 36	99.85 15	94.75 76	99.18 7	98.65 55

agg_prior					98.59 39	83.13 120		96.56 105		94.19 72			99.16 116

CSCG		92.02 100	91.65 103	93.12 98	98.53 40	80.59 209	97.47 122	97.18 28	77.06 375	84.64 233	97.98 76	83.98 53	99.52 85	90.72 142	97.33 85	99.23 24

XVS		92.69 80	92.71 74	92.63 127	98.52 41	80.29 223	97.37 133	96.44 121	87.04 138	91.38 116	97.83 87	77.24 135	99.59 76	90.46 148	98.07 58	98.02 97

X-MVStestdata		86.26 255	84.14 276	92.63 127	98.52 41	80.29 223	97.37 133	96.44 121	87.04 138	91.38 116	20.73 496	77.24 135	99.59 76	90.46 148	98.07 58	98.02 97

FOURS1					98.51 43	78.01 304	98.13 70	96.21 149	83.04 263	94.39 70

CP-MVS		92.54 86	92.60 78	92.34 146	98.50 44	79.90 239	98.40 54	96.40 127	84.75 206	90.48 133	98.09 66	77.40 131	99.21 107	91.15 130	98.23 56	97.92 109

PAPM_NR		91.46 116	90.82 121	93.37 88	98.50 44	81.81 167	95.03 313	96.13 155	84.65 211	86.10 213	97.65 97	79.24 97	99.75 49	83.20 244	96.88 104	98.56 60

MAR-MVS		90.63 142	90.22 138	91.86 180	98.47 46	78.20 300	97.18 145	96.61 96	83.87 241	88.18 175	98.18 57	68.71 276	99.75 49	83.66 238	97.15 92	97.63 138
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
patch_mono-2		95.14 15	96.08 7	92.33 148	98.44 47	77.84 312	98.43 52	97.21 25	92.58 29	97.68 15	97.65 97	86.88 29	99.83 21	98.25 18	97.60 74	99.33 18

mPP-MVS		91.88 106	91.82 99	92.07 168	98.38 48	78.63 282	97.29 138	96.09 158	85.12 198	88.45 168	97.66 93	75.53 177	99.68 66	89.83 159	98.02 61	97.88 111

SR-MVS		92.16 97	92.27 88	91.83 187	98.37 49	78.41 289	96.67 198	95.76 188	82.19 284	91.97 108	98.07 70	76.44 153	98.64 143	93.71 90	97.27 87	98.45 66

test12				94.25 43	98.34 50	85.55 61		96.35 137		92.36 99		80.84 74	99.22 106		98.31 53	97.98 104

CPTT-MVS		89.72 166	89.87 153	89.29 280	98.33 51	73.30 380	97.70 102	95.35 218	75.68 387	87.40 186	97.44 109	70.43 260	98.25 169	89.56 168	96.90 102	96.33 231

MSP-MVS		95.62 8	96.54 1	92.86 111	98.31 52	80.10 234	97.42 129	96.78 65	92.20 36	97.11 23	98.29 52	93.46 1	99.10 121	96.01 56	99.30 5	99.38 14
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
MSLP-MVS++		94.28 36	94.39 38	93.97 55	98.30 53	84.06 97	98.64 44	96.93 53	90.71 57	93.08 88	98.70 22	79.98 88	99.21 107	94.12 85	99.07 11	98.63 56

PGM-MVS		91.93 103	91.80 100	92.32 150	98.27 54	79.74 245	95.28 293	97.27 22	83.83 244	90.89 128	97.78 89	76.12 164	99.56 82	88.82 181	97.93 65	97.66 134

ZNCC-MVS		92.75 71	92.60 78	93.23 92	98.24 55	81.82 166	97.63 106	96.50 114	85.00 202	91.05 124	97.74 90	78.38 112	99.80 31	90.48 146	98.34 52	98.07 94

save fliter					98.24 55	83.34 115	98.61 46	96.57 103	91.32 47

114514_t		88.79 195	87.57 207	92.45 137	98.21 57	81.74 169	96.99 165	95.45 209	75.16 391	82.48 265	95.69 168	68.59 277	98.50 153	80.33 270	95.18 139	97.10 191

GST-MVS		92.43 91	92.22 92	93.04 102	98.17 58	81.64 174	97.40 131	96.38 131	84.71 209	90.90 127	97.40 111	77.55 129	99.76 44	89.75 163	97.74 70	97.72 128

DP-MVS		81.47 342	78.28 361	91.04 224	98.14 59	78.48 285	95.09 312	86.97 451	61.14 463	71.12 395	92.78 276	59.59 349	99.38 94	53.11 454	86.61 266	95.27 267

MP-MVS		92.61 84	92.67 76	92.42 141	98.13 60	79.73 246	97.33 136	96.20 150	85.63 178	90.53 131	97.66 93	78.14 118	99.70 63	92.12 117	98.30 54	97.85 116
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
9.14			94.26 43		98.10 61		98.14 67	96.52 111	84.74 207	94.83 64	98.80 12	82.80 65	99.37 96	95.95 58	98.42 46

PHI-MVS		93.59 50	93.63 52	93.48 84	98.05 62	81.76 168	98.64 44	97.13 33	82.60 276	94.09 74	98.49 35	80.35 79	99.85 15	94.74 77	98.62 33	98.83 42

SMA-MVS		94.70 25	94.68 31	94.76 30	98.02 63	85.94 48	97.47 122	96.77 71	85.32 187	97.92 5	98.70 22	83.09 62	99.84 17	95.79 60	99.08 10	98.49 63
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
PLC	83.97 7	88.00 218	87.38 213	89.83 270	98.02 63	76.46 342	97.16 149	94.43 282	79.26 346	81.98 275	96.28 153	69.36 269	99.27 101	77.71 303	92.25 187	93.77 301
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MTAPA		92.45 89	92.31 87	92.86 111	97.90 65	80.85 202	92.88 374	96.33 138	87.92 106	90.20 137	98.18 57	76.71 149	99.76 44	92.57 111	98.09 57	97.96 108

APD-MVS_3200maxsize		91.23 124	91.35 108	90.89 232	97.89 66	76.35 346	96.30 229	95.52 203	79.82 333	91.03 125	97.88 84	74.70 197	98.54 151	92.11 118	96.89 103	97.77 123

HPM-MVS		91.62 113	91.53 106	91.89 178	97.88 67	79.22 259	96.99 165	95.73 191	82.07 286	89.50 149	97.19 122	75.59 175	98.93 134	90.91 135	97.94 63	97.54 147
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SD-MVS		94.84 21	95.02 26	94.29 42	97.87 68	84.61 87	97.76 98	96.19 152	89.59 74	96.66 33	98.17 60	84.33 46	99.60 75	96.09 55	98.50 42	98.66 54
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
NormalMVS		92.88 67	92.97 69	92.59 130	97.80 69	82.02 151	97.94 83	94.70 252	92.34 32	92.15 104	96.53 149	77.03 139	98.57 147	91.13 131	97.12 94	97.19 185

lecture		93.17 57	93.57 55	91.96 174	97.80 69	78.79 278	98.50 50	96.98 46	86.61 152	94.75 66	98.16 61	78.36 114	99.35 99	93.89 87	97.12 94	97.75 125

dcpmvs_2		93.10 60	93.46 59	92.02 172	97.77 71	79.73 246	94.82 319	93.86 327	86.91 141	91.33 119	96.76 142	85.20 37	98.06 177	96.90 50	97.60 74	98.27 79

原ACMM1				91.22 220	97.77 71	78.10 302		96.61 96	81.05 299	91.28 121	97.42 110	77.92 122	98.98 128	79.85 278	98.51 40	96.59 222

SR-MVS-dyc-post		91.29 122	91.45 107	90.80 234	97.76 73	76.03 351	96.20 237	95.44 210	80.56 311	90.72 129	97.84 85	75.76 172	98.61 144	91.99 119	96.79 109	97.75 125

RE-MVS-def			91.18 115		97.76 73	76.03 351	96.20 237	95.44 210	80.56 311	90.72 129	97.84 85	73.36 218		91.99 119	96.79 109	97.75 125

TSAR-MVS + MP.		94.79 24	95.17 23	93.64 73	97.66 75	84.10 96	95.85 268	96.42 124	91.26 48	97.49 20	96.80 141	86.50 31	98.49 154	95.54 65	99.03 13	98.33 72
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MGCNet		95.58 9	95.44 17	96.01 10	97.63 76	89.26 12	99.27 5	96.59 100	94.71 9	97.08 24	97.99 73	78.69 108	99.86 13	99.15 3	97.85 66	98.91 39

HPM-MVS_fast		90.38 150	90.17 141	91.03 225	97.61 77	77.35 327	97.15 151	95.48 206	79.51 339	88.79 161	96.90 134	71.64 245	98.81 139	87.01 207	97.44 79	96.94 202

EI-MVSNet-Vis-set		91.84 107	91.77 101	92.04 171	97.60 78	81.17 184	96.61 199	96.87 58	88.20 99	89.19 152	97.55 105	78.69 108	99.14 117	90.29 155	90.94 204	95.80 244

CNLPA		86.96 240	85.37 250	91.72 194	97.59 79	79.34 256	97.21 141	91.05 419	74.22 398	78.90 306	96.75 144	67.21 290	98.95 131	74.68 342	90.77 207	96.88 208

ACMMP		90.39 148	89.97 148	91.64 197	97.58 80	78.21 299	96.78 188	96.72 80	84.73 208	84.72 230	97.23 120	71.22 249	99.63 72	88.37 191	92.41 184	97.08 196
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
SF-MVS		94.17 39	94.05 46	94.55 37	97.56 81	85.95 46	97.73 100	96.43 123	84.02 234	95.07 59	98.74 19	82.93 63	99.38 94	95.42 67	98.51 40	98.32 73

CANet		94.89 19	94.64 32	95.63 14	97.55 82	88.12 19	99.06 23	96.39 129	94.07 17	95.34 51	97.80 88	76.83 146	99.87 11	97.08 48	97.64 73	98.89 40

PVSNet_BlendedMVS		90.05 156	89.96 149	90.33 251	97.47 83	83.86 99	98.02 79	96.73 78	87.98 104	89.53 147	89.61 326	76.42 154	99.57 80	94.29 82	79.59 322	87.57 405

PVSNet_Blended		93.13 58	92.98 68	93.57 78	97.47 83	83.86 99	99.32 3	96.73 78	91.02 54	89.53 147	96.21 154	76.42 154	99.57 80	94.29 82	95.81 133	97.29 177

reproduce-ours		92.70 78	93.02 66	91.75 189	97.45 85	77.77 316	96.16 240	95.94 175	84.12 230	92.45 95	98.43 41	80.06 86	99.24 103	95.35 68	97.18 90	98.24 81

our_new_method		92.70 78	93.02 66	91.75 189	97.45 85	77.77 316	96.16 240	95.94 175	84.12 230	92.45 95	98.43 41	80.06 86	99.24 103	95.35 68	97.18 90	98.24 81

新几何1				93.12 98	97.44 87	81.60 177		96.71 81	74.54 397	91.22 122	97.57 101	79.13 99	99.51 87	77.40 310	98.46 44	98.26 80

LS3D		82.22 332	79.94 347	89.06 284	97.43 88	74.06 375	93.20 368	92.05 397	61.90 457	73.33 374	95.21 193	59.35 352	99.21 107	54.54 450	92.48 180	93.90 299

reproduce_model		92.53 87	92.87 71	91.50 205	97.41 89	77.14 333	96.02 247	95.91 178	83.65 252	92.45 95	98.39 45	79.75 91	99.21 107	95.27 71	96.98 99	98.14 89

test_yl		91.46 116	90.53 127	94.24 44	97.41 89	85.18 71	98.08 73	97.72 11	80.94 300	89.85 139	96.14 155	75.61 173	98.81 139	90.42 151	88.56 242	98.74 47

DCV-MVSNet		91.46 116	90.53 127	94.24 44	97.41 89	85.18 71	98.08 73	97.72 11	80.94 300	89.85 139	96.14 155	75.61 173	98.81 139	90.42 151	88.56 242	98.74 47

EI-MVSNet-UG-set		91.35 121	91.22 111	91.73 192	97.39 92	80.68 206	96.47 211	96.83 62	87.92 106	88.30 172	97.36 112	77.84 123	99.13 119	89.43 170	89.45 219	95.37 262

旧先验1					97.39 92	79.58 250		96.54 108			98.08 69	84.00 52			97.42 81	97.62 140

TSAR-MVS + GP.		94.35 35	94.50 34	93.89 57	97.38 94	83.04 122	98.10 72	95.29 223	91.57 44	93.81 77	97.45 106	86.64 30	99.43 92	96.28 54	94.01 154	99.20 25

MVS_111021_HR		93.41 55	93.39 60	93.47 86	97.34 95	82.83 127	97.56 114	98.27 6	89.16 80	89.71 142	97.14 123	79.77 90	99.56 82	93.65 91	97.94 63	98.02 97

MP-MVS-pluss		92.58 85	92.35 84	93.29 89	97.30 96	82.53 133	96.44 214	96.04 164	84.68 210	89.12 154	98.37 48	77.48 130	99.74 52	93.31 98	98.38 49	97.59 143
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
EPNet		94.06 43	94.15 44	93.76 62	97.27 97	84.35 91	98.29 62	97.64 14	94.57 11	95.36 50	96.88 136	79.96 89	99.12 120	91.30 127	96.11 124	97.82 120
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		93.46 54	93.23 63	94.17 50	97.16 98	84.28 94	96.82 183	96.65 90	86.24 158	94.27 71	97.99 73	77.94 120	99.83 21	93.39 93	98.57 38	98.39 70

LFMVS		89.27 180	87.64 202	94.16 53	97.16 98	85.52 62	97.18 145	94.66 260	79.17 347	89.63 145	96.57 147	55.35 393	98.22 170	89.52 169	89.54 218	98.74 47

DeepPCF-MVS	89.82 1	94.61 26	96.17 5	89.91 267	97.09 100	70.21 415	98.99 29	96.69 84	95.57 2	95.08 58	99.23 1	86.40 33	99.87 11	97.84 33	98.66 32	99.65 6

VNet		92.11 99	91.22 111	94.79 29	96.91 101	86.98 32	97.91 86	97.96 10	86.38 155	93.65 79	95.74 164	70.16 263	98.95 131	93.39 93	88.87 232	98.43 68

TAPA-MVS	81.61 12	85.02 283	83.67 281	89.06 284	96.79 102	73.27 383	95.92 254	94.79 249	74.81 394	80.47 290	96.83 138	71.07 251	98.19 172	49.82 464	92.57 177	95.71 251
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Anonymous202405211		84.41 295	81.93 316	91.85 182	96.78 103	78.41 289	97.44 125	91.34 413	70.29 430	84.06 241	94.26 237	41.09 452	98.96 129	79.46 280	82.65 305	98.17 86

reproduce_monomvs		87.80 223	87.60 206	88.40 299	96.56 104	80.26 226	95.80 271	96.32 140	91.56 45	73.60 367	88.36 345	88.53 18	96.25 308	90.47 147	67.23 414	88.67 380

SPE-MVS-test		92.98 62	93.67 51	90.90 231	96.52 105	76.87 335	98.68 41	94.73 251	90.36 65	94.84 63	97.89 83	77.94 120	97.15 261	94.28 84	97.80 68	98.70 53

balanced_conf03		94.60 28	94.30 41	95.48 17	96.45 106	88.82 14	96.33 226	95.58 198	91.12 50	95.84 46	93.87 253	83.47 58	98.37 164	97.26 44	98.81 24	99.24 23

DELS-MVS		94.98 16	94.49 35	96.44 6	96.42 107	90.59 7	99.21 8	97.02 43	94.40 14	91.46 115	97.08 128	83.32 59	99.69 64	92.83 107	98.70 31	99.04 30
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
balanced_ft_v1		92.00 101	91.12 116	94.64 34	96.35 108	86.78 34	94.96 314	94.70 252	87.65 116	90.20 137	93.01 271	69.71 266	98.02 180	97.40 42	96.13 123	99.11 28

MM		95.85 6	95.74 11	96.15 8	96.34 109	89.50 9	99.18 9	98.10 8	95.68 1	96.64 34	97.92 79	80.72 75	99.80 31	99.16 2	97.96 62	99.15 27

thres200		88.92 189	87.65 201	92.73 120	96.30 110	85.62 60	97.85 89	98.86 1	84.38 222	84.82 227	93.99 250	75.12 191	98.01 182	70.86 373	86.67 265	94.56 287

CS-MVS		92.73 73	93.48 58	90.48 244	96.27 111	75.93 356	98.55 47	94.93 237	89.32 77	94.54 69	97.67 92	78.91 103	97.02 266	93.80 88	97.32 86	98.49 63

DPM-MVS		96.21 2	95.53 15	98.26 1	96.26 112	95.09 1	99.15 12	96.98 46	93.39 23	96.45 38	98.79 13	90.17 9	99.99 1	89.33 171	99.25 6	99.70 3

tfpn200view9		88.48 203	87.15 217	92.47 135	96.21 113	85.30 69	97.44 125	98.85 2	83.37 256	83.99 243	93.82 255	75.36 184	97.93 185	69.04 381	86.24 272	94.17 291

thres400		88.42 206	87.15 217	92.23 156	96.21 113	85.30 69	97.44 125	98.85 2	83.37 256	83.99 243	93.82 255	75.36 184	97.93 185	69.04 381	86.24 272	93.45 307

myMVS_eth3d28		92.72 75	92.23 90	94.21 46	96.16 115	87.46 30	97.37 133	96.99 45	88.13 101	88.18 175	95.47 180	84.12 51	98.04 178	92.46 113	91.17 201	97.14 188

test222					96.15 116	78.41 289	95.87 266	96.46 119	71.97 422	89.66 144	97.45 106	76.33 157			98.24 55	98.30 76

HY-MVS	84.06 6	91.63 112	90.37 134	95.39 20	96.12 117	88.25 18	90.22 407	97.58 15	88.33 95	90.50 132	91.96 290	79.26 96	99.06 124	90.29 155	89.07 228	98.88 41

thres100view900		88.30 209	86.95 224	92.33 148	96.10 118	84.90 83	97.14 152	98.85 2	82.69 274	83.41 256	93.66 259	75.43 181	97.93 185	69.04 381	86.24 272	94.17 291

thres600view7		88.06 215	86.70 231	92.15 164	96.10 118	85.17 75	97.14 152	98.85 2	82.70 273	83.41 256	93.66 259	75.43 181	97.82 194	67.13 390	85.88 277	93.45 307

WTY-MVS		92.65 83	91.68 102	95.56 15	96.00 120	88.90 13	98.23 64	97.65 13	88.57 87	89.82 141	97.22 121	79.29 95	99.06 124	89.57 166	88.73 234	98.73 51

testing91		91.90 105	91.31 110	93.66 72	95.99 121	85.68 55	97.39 132	96.89 56	86.75 148	88.85 160	95.23 191	83.93 54	97.90 191	88.91 175	87.89 254	97.41 166

testing99		91.91 104	91.35 108	93.60 76	95.98 122	85.70 53	97.31 137	96.92 55	86.82 144	88.91 158	95.25 187	84.26 50	97.89 192	88.80 182	87.94 253	97.21 182

MVSTER		89.25 181	88.92 173	90.24 254	95.98 122	84.66 86	96.79 186	95.36 216	87.19 133	80.33 293	90.61 311	90.02 11	95.97 317	85.38 219	78.64 331	90.09 337

testing11		92.48 88	92.04 97	93.78 61	95.94 124	86.00 45	97.56 114	97.08 38	87.52 118	89.32 150	95.40 182	84.60 42	98.02 180	91.93 123	89.04 229	97.32 173

testing3-2		91.37 119	91.01 119	92.44 139	95.93 125	83.77 102	98.83 36	97.45 16	86.88 142	86.63 204	94.69 225	84.57 43	97.75 197	89.65 164	84.44 287	95.80 244

testdata				90.13 257	95.92 126	74.17 373		96.49 117	73.49 406	94.82 65	97.99 73	78.80 106	97.93 185	83.53 241	97.52 76	98.29 77

PatchMatch-RL		85.00 284	83.66 282	89.02 286	95.86 127	74.55 370	92.49 378	93.60 356	79.30 344	79.29 305	91.47 296	58.53 359	98.45 159	70.22 377	92.17 189	94.07 296

testing222		91.09 127	90.49 129	92.87 110	95.82 128	85.04 78	96.51 209	97.28 21	86.05 164	89.13 153	95.34 184	80.16 85	96.62 295	85.82 214	88.31 249	96.96 201

ETVMVS		90.99 130	90.26 136	93.19 95	95.81 129	85.64 59	96.97 170	97.18 28	85.43 184	88.77 163	94.86 217	82.00 69	96.37 302	82.70 249	88.60 239	97.57 144

sasdasda		92.27 94	91.22 111	95.41 18	95.80 130	88.31 16	97.09 159	94.64 263	88.49 89	92.99 90	97.31 113	72.68 225	98.57 147	93.38 95	88.58 240	99.36 16

canonicalmvs		92.27 94	91.22 111	95.41 18	95.80 130	88.31 16	97.09 159	94.64 263	88.49 89	92.99 90	97.31 113	72.68 225	98.57 147	93.38 95	88.58 240	99.36 16

fmvsm_s_conf0.5_n_9		94.52 30	95.22 21	92.41 142	95.79 132	78.61 283	98.73 38	96.00 166	94.91 8	97.73 12	98.73 20	79.09 100	99.79 35	99.14 4	96.86 106	98.83 42

Anonymous20240529		83.15 315	80.60 336	90.80 234	95.74 133	78.27 294	96.81 185	94.92 238	60.10 467	81.89 277	92.54 277	45.82 434	98.82 138	79.25 286	78.32 337	95.31 264

MVS_111021_LR		91.60 114	91.64 104	91.47 207	95.74 133	78.79 278	96.15 242	96.77 71	88.49 89	88.64 165	97.07 129	72.33 231	99.19 113	93.13 104	96.48 117	96.43 226

MGCFI-Net		91.95 102	91.03 118	94.72 32	95.68 135	86.38 38	96.93 175	94.48 273	88.25 97	92.78 93	97.24 119	72.34 230	98.46 157	93.13 104	88.43 247	99.32 19

fmvsm_s_conf0.5_n_11		94.41 33	95.19 22	92.09 166	95.65 136	80.91 200	99.23 7	94.85 244	94.92 7	97.68 15	98.82 11	79.31 94	99.78 38	98.83 9	97.38 83	95.60 254

PS-MVSNAJ		94.17 39	93.52 56	96.10 9	95.65 136	92.35 2	98.21 65	95.79 187	92.42 31	96.24 40	98.18 57	71.04 252	99.17 115	96.77 51	97.39 82	96.79 212

WBMVS		87.73 225	86.79 227	90.56 241	95.61 138	85.68 55	97.63 106	95.52 203	83.77 246	78.30 313	88.44 344	86.14 34	95.78 330	82.54 250	73.15 366	90.21 332

UBG		92.68 82	92.35 84	93.70 69	95.61 138	85.65 58	97.25 139	97.06 40	87.92 106	89.28 151	95.03 205	86.06 35	98.07 176	92.24 115	90.69 208	97.37 170

Anonymous20231211		79.72 362	77.19 370	87.33 335	95.59 140	77.16 332	95.18 304	94.18 309	59.31 470	72.57 382	86.20 386	47.89 427	95.66 338	74.53 346	69.24 394	89.18 358

alignmvs		92.97 63	92.26 89	95.12 22	95.54 141	87.77 23	98.67 42	96.38 131	88.04 103	93.01 89	97.45 106	79.20 98	98.60 145	93.25 99	88.76 233	98.99 34

PVSNet	82.34 9	89.02 185	87.79 199	92.71 121	95.49 142	81.50 178	97.70 102	97.29 20	87.76 111	85.47 219	95.12 201	56.90 382	98.90 135	80.33 270	94.02 153	97.71 130

tpmvs		83.04 318	80.77 332	89.84 269	95.43 143	77.96 306	85.59 448	95.32 220	75.31 390	76.27 342	83.70 417	73.89 209	97.41 235	59.53 428	81.93 312	94.14 293

SteuartSystems-ACMMP		94.13 42	94.44 37	93.20 94	95.41 144	81.35 181	99.02 27	96.59 100	89.50 76	94.18 73	98.36 49	83.68 57	99.45 91	94.77 75	98.45 45	98.81 44
Skip Steuart: Steuart Systems R&D Blog.
EPMVS		87.47 235	85.90 240	92.18 161	95.41 144	82.26 146	87.00 438	96.28 142	85.88 173	84.23 238	85.57 394	75.07 192	96.26 306	71.14 371	92.50 179	98.03 96

MVSMamba_PlusPlus		92.37 93	91.55 105	94.83 28	95.37 146	87.69 25	95.60 282	95.42 214	74.65 396	93.95 76	92.81 273	83.11 61	97.70 199	94.49 80	98.53 39	99.11 28

BH-RMVSNet		86.84 243	85.28 253	91.49 206	95.35 147	80.26 226	96.95 173	92.21 395	82.86 270	81.77 280	95.46 181	59.34 353	97.64 203	69.79 379	93.81 161	96.57 223

OMC-MVS		88.80 194	88.16 192	90.72 237	95.30 148	77.92 309	94.81 320	94.51 271	86.80 145	84.97 225	96.85 137	67.53 286	98.60 145	85.08 220	87.62 257	95.63 252

test_fmvsm_n_1920		94.81 23	95.60 12	92.45 137	95.29 149	80.96 197	99.29 4	97.21 25	94.50 13	97.29 22	98.44 40	82.15 67	99.78 38	98.56 12	97.68 72	96.61 221

MVS_Test		90.29 153	89.18 164	93.62 75	95.23 150	84.93 82	94.41 327	94.66 260	84.31 223	90.37 136	91.02 304	75.13 190	97.82 194	83.11 246	94.42 149	98.12 92

F-COLMAP		84.50 294	83.44 291	87.67 323	95.22 151	72.22 390	95.95 251	93.78 338	75.74 386	76.30 341	95.18 196	59.50 351	98.45 159	72.67 359	86.59 267	92.35 316

baseline1		88.85 192	87.49 209	92.93 109	95.21 152	86.85 33	95.47 287	94.61 266	87.29 126	83.11 261	94.99 209	80.70 76	96.89 279	82.28 254	73.72 359	95.05 273

fmvsm_l_conf0.5_n_9		94.91 17	95.60 12	92.84 114	95.20 153	80.55 213	99.45 1	96.36 136	95.17 4	98.48 3	98.55 27	80.53 78	99.78 38	98.87 7	97.79 69	98.19 84

fmvsm_s_conf0.5_n_10		94.36 34	94.73 29	93.23 92	95.19 154	82.87 126	99.18 9	96.39 129	93.97 18	97.91 7	98.53 31	75.88 170	99.82 23	98.58 11	96.95 101	97.00 199

SymmetryMVS		92.45 89	92.33 86	92.82 115	95.19 154	82.02 151	97.94 83	97.43 17	92.34 32	92.15 104	96.53 149	77.03 139	98.57 147	91.13 131	91.19 199	97.87 113

CHOSEN 1792x2688		91.07 129	90.21 139	93.64 73	95.18 156	83.53 111	96.26 231	96.13 155	88.92 81	84.90 226	93.10 269	72.86 222	99.62 74	88.86 176	95.67 134	97.79 122

UGNet		87.73 225	86.55 233	91.27 215	95.16 157	79.11 263	96.35 224	96.23 147	88.14 100	87.83 183	90.48 312	50.65 413	99.09 122	80.13 275	94.03 152	95.60 254
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
fmvsm_s_conf0.5_n_8		94.52 30	95.04 24	92.96 106	95.15 158	81.14 185	99.09 20	96.66 89	95.53 3	97.84 9	98.71 21	76.33 157	99.81 27	99.24 1	96.85 108	97.92 109

VDD-MVS		88.28 210	87.02 222	92.06 169	95.09 159	80.18 231	97.55 116	94.45 279	83.09 261	89.10 155	95.92 161	47.97 425	98.49 154	93.08 106	86.91 264	97.52 153

PVSNet_Blended_VisFu		91.24 123	90.77 122	92.66 123	95.09 159	82.40 141	97.77 96	95.87 184	88.26 96	86.39 208	93.94 251	76.77 147	99.27 101	88.80 182	94.00 155	96.31 232

h-mvs33		89.30 179	88.95 172	90.36 250	95.07 161	76.04 350	96.96 172	97.11 36	90.39 63	92.22 102	95.10 202	74.70 197	98.86 136	93.14 102	65.89 424	96.16 234

xiu_mvs_v2_base		93.92 46	93.26 62	95.91 11	95.07 161	92.02 6	98.19 66	95.68 193	92.06 39	96.01 45	98.14 62	70.83 257	98.96 129	96.74 53	96.57 115	96.76 216

cl22		85.11 280	84.17 274	87.92 318	95.06 163	78.82 271	95.51 285	94.22 302	79.74 335	76.77 331	87.92 353	75.96 166	95.68 337	79.93 277	72.42 368	89.27 355

BH-w/o		88.24 211	87.47 211	90.54 243	95.03 164	78.54 284	97.41 130	93.82 333	84.08 232	78.23 314	94.51 229	69.34 270	97.21 254	80.21 274	94.58 146	95.87 243

CHOSEN 280x420		91.71 111	91.85 98	91.29 214	94.94 165	82.69 130	87.89 431	96.17 153	85.94 171	87.27 190	94.31 235	90.27 8	95.65 340	94.04 86	95.86 131	95.53 258

GG-mvs-BLEND				93.49 83	94.94 165	86.26 39	81.62 463	97.00 44		88.32 171	94.30 236	91.23 5	96.21 310	88.49 188	97.43 80	98.00 102

HyFIR lowres test		89.36 177	88.60 178	91.63 199	94.91 167	80.76 205	95.60 282	95.53 201	82.56 277	84.03 242	91.24 301	78.03 119	96.81 286	87.07 206	88.41 248	97.32 173

miper_enhance_ethall		85.95 260	85.20 254	88.19 312	94.85 168	79.76 242	96.00 248	94.06 316	82.98 267	77.74 319	88.76 335	79.42 92	95.46 350	80.58 268	72.42 368	89.36 353

mvsmamba		90.53 147	90.08 143	91.88 179	94.81 169	80.93 198	93.94 345	94.45 279	88.24 98	87.02 196	92.35 280	68.04 278	95.80 328	94.86 74	97.03 98	98.92 38

mvs_anonymous		88.68 196	87.62 204	91.86 180	94.80 170	81.69 172	93.53 357	94.92 238	82.03 287	78.87 308	90.43 314	75.77 171	95.34 354	85.04 221	93.16 172	98.55 62

CANet_DTU		90.98 131	90.04 146	93.83 59	94.76 171	86.23 42	96.32 227	93.12 379	93.11 25	93.71 78	96.82 140	63.08 324	99.48 89	84.29 226	95.12 140	95.77 249

PMMVS		89.46 172	89.92 151	88.06 315	94.64 172	69.57 421	96.22 235	94.95 236	87.27 129	91.37 118	96.54 148	65.88 301	97.39 239	88.54 186	93.89 159	97.23 178

TR-MVS		86.30 254	84.93 262	90.42 246	94.63 173	77.58 322	96.57 203	93.82 333	80.30 321	82.42 267	95.16 197	58.74 357	97.55 215	74.88 340	87.82 255	96.13 236

EPNet_dtu		87.65 230	87.89 196	86.93 344	94.57 174	71.37 407	96.72 192	96.50 114	88.56 88	87.12 194	95.02 206	75.91 169	94.01 406	66.62 394	90.00 213	95.42 261
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n		93.69 48	94.13 45	92.34 146	94.56 175	82.01 153	99.07 22	97.13 33	92.09 37	96.25 39	98.53 31	76.47 152	99.80 31	98.39 14	94.71 144	95.22 268

FMVSNet3		84.71 287	82.71 305	90.70 238	94.55 176	87.71 24	95.92 254	94.67 259	81.73 291	75.82 350	88.08 351	66.99 292	94.47 398	71.23 368	75.38 350	89.91 341

ETV-MVS		92.72 75	92.87 71	92.28 152	94.54 177	81.89 162	97.98 80	95.21 227	89.77 72	93.11 87	96.83 138	77.23 137	97.50 224	95.74 61	95.38 138	97.44 164

fmvsm_l_conf0.5_n_3		94.61 26	94.92 27	93.68 71	94.52 178	82.80 128	99.33 2	96.37 134	95.08 6	97.59 19	98.48 37	77.40 131	99.79 35	98.28 16	97.21 89	98.44 67

EIA-MVS		91.73 108	92.05 96	90.78 236	94.52 178	76.40 345	98.06 76	95.34 219	89.19 79	88.90 159	97.28 118	77.56 128	97.73 198	90.77 141	96.86 106	98.20 83

BH-untuned		86.95 241	85.94 239	89.99 262	94.52 178	77.46 324	96.78 188	93.37 368	81.80 289	76.62 334	93.81 257	66.64 296	97.02 266	76.06 325	93.88 160	95.48 260

DeepC-MVS	86.58 3	91.53 115	91.06 117	92.94 108	94.52 178	81.89 162	95.95 251	95.98 169	90.76 56	83.76 249	96.76 142	73.24 219	99.71 60	91.67 125	96.96 100	97.22 179
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
gg-mvs-nofinetune		85.48 272	82.90 301	93.24 91	94.51 182	85.82 50	79.22 468	96.97 49	61.19 462	87.33 188	53.01 485	90.58 6	96.07 313	86.07 213	97.23 88	97.81 121

fmvsm_l_conf0.5_n_a		94.91 17	95.30 19	93.72 67	94.50 183	84.30 93	99.14 14	96.00 166	91.94 42	97.91 7	98.60 25	84.78 41	99.77 42	98.84 8	96.03 127	97.08 196

3Dnovator+	82.88 8	89.63 169	87.85 197	94.99 24	94.49 184	86.76 36	97.84 90	95.74 190	86.10 162	75.47 355	96.02 158	65.00 309	99.51 87	82.91 248	97.07 97	98.72 52

RRT-MVS		89.67 167	88.67 176	92.67 122	94.44 185	81.08 188	94.34 331	94.45 279	86.05 164	85.79 215	92.39 279	63.39 322	98.16 174	93.22 100	93.95 158	98.76 46

fmvsm_l_conf0.5_n		94.89 19	95.24 20	93.86 58	94.42 186	84.61 87	99.13 15	96.15 154	92.06 39	97.92 5	98.52 33	84.52 44	99.74 52	98.76 10	95.67 134	97.22 179

fmvsm_s_conf0.5_n_3		93.95 45	94.53 33	92.20 160	94.41 187	80.04 236	98.90 33	95.96 171	94.53 12	97.63 18	98.58 26	75.95 167	99.79 35	98.25 18	96.60 114	96.77 214

ET-MVSNet_ETH3D		90.01 157	89.03 166	92.95 107	94.38 188	86.77 35	98.14 67	96.31 141	89.30 78	63.33 439	96.72 145	90.09 10	93.63 414	90.70 144	82.29 309	98.46 65

tpmrst		88.36 207	87.38 213	91.31 212	94.36 189	79.92 238	87.32 435	95.26 225	85.32 187	88.34 170	86.13 387	80.60 77	96.70 291	83.78 232	85.34 284	97.30 176

FE-MVS		86.06 258	84.15 275	91.78 188	94.33 190	79.81 240	84.58 455	96.61 96	76.69 381	85.00 224	87.38 361	70.71 259	98.37 164	70.39 376	91.70 194	97.17 187

MVS		90.60 143	88.64 177	96.50 5	94.25 191	90.53 8	93.33 362	97.21 25	77.59 366	78.88 307	97.31 113	71.52 247	99.69 64	89.60 165	98.03 60	99.27 22

dp		84.30 297	82.31 310	90.28 253	94.24 192	77.97 305	86.57 441	95.53 201	79.94 332	80.75 287	85.16 402	71.49 248	96.39 301	63.73 411	83.36 295	96.48 225

FA-MVS(test-final)		87.71 228	86.23 237	92.17 162	94.19 193	80.55 213	87.16 437	96.07 161	82.12 285	85.98 214	88.35 346	72.04 239	98.49 154	80.26 272	89.87 215	97.48 157

UWE-MVS		88.56 202	88.91 174	87.50 331	94.17 194	72.19 392	95.82 270	97.05 41	84.96 203	84.78 228	93.51 263	81.33 71	94.75 389	79.43 281	89.17 226	95.57 256

sss		90.87 136	89.96 149	93.60 76	94.15 195	83.84 101	97.14 152	98.13 7	85.93 172	89.68 143	96.09 157	71.67 243	99.30 100	87.69 199	89.16 227	97.66 134

SDMVSNet		87.02 239	85.61 245	91.24 217	94.14 196	83.30 116	93.88 347	95.98 169	84.30 225	79.63 301	92.01 286	58.23 361	97.68 201	90.28 157	82.02 310	92.75 310

sd_testset		84.62 290	83.11 296	89.17 282	94.14 196	77.78 315	91.54 395	94.38 288	84.30 225	79.63 301	92.01 286	52.28 406	96.98 271	77.67 304	82.02 310	92.75 310

PatchmatchNet		86.83 244	85.12 258	91.95 175	94.12 198	82.27 145	86.55 442	95.64 196	84.59 213	82.98 263	84.99 406	77.26 133	95.96 320	68.61 384	91.34 198	97.64 136
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
fmvsm_s_conf0.5_n_2		92.97 63	93.38 61	91.73 192	94.10 199	80.64 208	98.96 30	95.89 180	94.09 16	97.05 25	98.40 44	68.92 275	99.80 31	98.53 13	94.50 148	94.74 281

MDTV_nov1_ep13			83.69 279		94.09 200	81.01 190	86.78 440	96.09 158	83.81 245	84.75 229	84.32 411	74.44 203	96.54 296	63.88 410	85.07 285

UA-Net		88.92 189	88.48 185	90.24 254	94.06 201	77.18 331	93.04 370	94.66 260	87.39 124	91.09 123	93.89 252	74.92 193	98.18 173	75.83 328	91.43 197	95.35 263

Fast-Effi-MVS+		87.93 220	86.94 225	90.92 229	94.04 202	79.16 261	98.26 63	93.72 348	81.29 295	83.94 246	92.90 272	69.83 264	96.68 292	76.70 316	91.74 193	96.93 203

QAPM		86.88 242	84.51 265	93.98 54	94.04 202	85.89 49	97.19 144	96.05 162	73.62 403	75.12 358	95.62 174	62.02 335	99.74 52	70.88 372	96.06 126	96.30 233

thisisatest0515		90.95 133	90.26 136	93.01 103	94.03 204	84.27 95	97.91 86	96.67 86	83.18 259	86.87 202	95.51 178	88.66 17	97.85 193	80.46 269	89.01 230	96.92 205

fmvsm_s_conf0.5_n_4		93.59 50	94.32 40	91.41 209	93.89 205	79.24 257	98.89 34	96.53 110	92.82 27	97.37 21	98.47 38	77.21 138	99.78 38	98.11 25	95.59 136	95.21 269

Vis-MVSNet (Re-imp)		88.88 191	88.87 175	88.91 288	93.89 205	74.43 371	96.93 175	94.19 308	84.39 221	83.22 259	95.67 169	78.24 115	94.70 391	78.88 290	94.40 150	97.61 141

ADS-MVSNet2		79.57 364	77.53 367	85.71 364	93.78 207	72.13 393	79.48 466	86.11 458	73.09 409	80.14 295	79.99 446	62.15 331	90.14 451	59.49 429	83.52 292	94.85 278

ADS-MVSNet		81.26 346	78.36 360	89.96 265	93.78 207	79.78 241	79.48 466	93.60 356	73.09 409	80.14 295	79.99 446	62.15 331	95.24 362	59.49 429	83.52 292	94.85 278

EPP-MVSNet		89.76 165	89.72 154	89.87 268	93.78 207	76.02 353	97.22 140	96.51 112	79.35 341	85.11 222	95.01 207	84.82 40	97.10 264	87.46 202	88.21 251	96.50 224

3Dnovator	82.32 10	89.33 178	87.64 202	94.42 39	93.73 210	85.70 53	97.73 100	96.75 75	86.73 149	76.21 344	95.93 159	62.17 328	99.68 66	81.67 258	97.81 67	97.88 111

E3new		90.90 135	90.35 135	92.55 132	93.63 211	82.40 141	96.79 186	94.49 272	87.07 137	88.54 166	95.70 166	73.85 210	97.60 205	91.23 129	91.86 192	97.64 136

Effi-MVS+		90.70 140	89.90 152	93.09 100	93.61 212	83.48 112	95.20 301	92.79 384	83.22 258	91.82 111	95.70 166	71.82 242	97.48 226	91.25 128	93.67 164	98.32 73

IS-MVSNet		88.67 197	88.16 192	90.20 256	93.61 212	76.86 336	96.77 190	93.07 380	84.02 234	83.62 252	95.60 175	74.69 200	96.24 309	78.43 294	93.66 165	97.49 156

AUN-MVS		86.25 256	85.57 246	88.26 305	93.57 214	73.38 378	95.45 288	95.88 182	83.94 238	85.47 219	94.21 240	73.70 215	96.67 293	83.54 240	64.41 428	94.73 285

test2506		90.96 132	90.39 132	92.65 124	93.54 215	82.46 139	96.37 220	97.35 19	86.78 146	87.55 184	95.25 187	77.83 124	97.50 224	84.07 228	94.80 142	97.98 104

ECVR-MVS		88.35 208	87.25 215	91.65 196	93.54 215	79.40 253	96.56 205	90.78 424	86.78 146	85.57 217	95.25 187	57.25 380	97.56 211	84.73 224	94.80 142	97.98 104

hse-mvs2		88.22 212	88.21 190	88.25 307	93.54 215	73.41 377	95.41 290	95.89 180	90.39 63	92.22 102	94.22 239	74.70 197	96.66 294	93.14 102	64.37 429	94.69 286

LCM-MVSNet-Re		83.75 305	83.54 288	84.39 390	93.54 215	64.14 447	92.51 377	84.03 469	83.90 240	66.14 427	86.59 375	67.36 288	92.68 421	84.89 223	92.87 174	96.35 228

EC-MVSNet		91.73 108	92.11 94	90.58 240	93.54 215	77.77 316	98.07 75	94.40 285	87.44 122	92.99 90	97.11 126	74.59 201	96.87 282	93.75 89	97.08 96	97.11 189

tpm cat1		83.63 307	81.38 324	90.39 247	93.53 220	78.19 301	85.56 449	95.09 230	70.78 428	78.51 310	83.28 421	74.80 196	97.03 265	66.77 392	84.05 290	95.95 239

fmvsm_s_conf0.5_n_6		94.17 39	94.70 30	92.58 131	93.50 221	81.20 183	99.08 21	96.48 118	92.24 35	98.62 2	98.39 45	78.58 110	99.72 57	98.08 26	97.36 84	96.81 211

thisisatest0530		89.65 168	89.02 167	91.53 202	93.46 222	80.78 204	96.52 207	96.67 86	81.69 292	83.79 248	94.90 214	88.85 16	97.68 201	77.80 299	87.49 261	96.14 235

MSDG		80.62 356	77.77 366	89.14 283	93.43 223	77.24 328	91.89 387	90.18 428	69.86 434	68.02 415	91.94 293	52.21 407	98.84 137	59.32 431	83.12 296	91.35 318

fmvsm_s_conf0.5_n_a		93.34 56	93.71 50	92.22 157	93.38 224	81.71 171	98.86 35	96.98 46	91.64 43	96.85 29	98.55 27	75.58 176	99.77 42	97.88 32	93.68 163	95.18 270

ab-mvs		87.08 238	84.94 261	93.48 84	93.34 225	83.67 108	88.82 420	95.70 192	81.18 297	84.55 234	90.14 320	62.72 325	98.94 133	85.49 218	82.54 306	97.85 116

viewdifsd2359ckpt09		90.00 158	89.28 163	92.15 164	93.31 226	81.38 179	96.37 220	93.64 353	86.34 156	86.62 205	95.64 171	71.58 246	97.52 221	88.93 174	91.06 202	97.54 147

VortexMVS		85.45 273	84.40 269	88.63 294	93.25 227	81.66 173	95.39 292	94.34 290	87.15 135	75.10 359	87.65 357	66.58 298	95.19 364	86.89 208	73.21 365	89.03 368

viewcassd2359sk11		90.66 141	90.06 145	92.47 135	93.22 228	82.21 148	96.70 196	94.47 276	86.94 140	88.22 174	95.50 179	73.15 220	97.59 207	90.86 137	91.48 196	97.60 142

1314		88.94 188	87.20 216	94.17 50	93.21 229	85.73 52	93.33 362	96.64 93	82.89 268	75.98 347	96.36 151	66.83 295	99.39 93	83.52 242	96.02 128	97.39 169

1112_ss		88.60 200	87.47 211	92.00 173	93.21 229	80.97 192	96.47 211	92.46 387	83.64 253	80.86 286	97.30 116	80.24 82	97.62 204	77.60 305	85.49 281	97.40 168

GeoE		86.36 252	85.20 254	89.83 270	93.17 231	76.13 348	97.53 117	92.11 396	79.58 338	80.99 284	94.01 247	66.60 297	96.17 312	73.48 354	89.30 224	97.20 184

test1111		88.11 213	87.04 221	91.35 211	93.15 232	78.79 278	96.57 203	90.78 424	86.88 142	85.04 223	95.20 194	57.23 381	97.39 239	83.88 230	94.59 145	97.87 113

Test_1112_low_res		88.03 216	86.73 228	91.94 177	93.15 232	80.88 201	96.44 214	92.41 391	83.59 255	80.74 288	91.16 302	80.18 83	97.59 207	77.48 308	85.40 282	97.36 171

CostFormer		89.08 183	88.39 186	91.15 221	93.13 234	79.15 262	88.61 423	96.11 157	83.14 260	89.58 146	86.93 370	83.83 56	96.87 282	88.22 192	85.92 276	97.42 165

IB-MVS	85.34 4	88.67 197	87.14 219	93.26 90	93.12 235	84.32 92	98.76 37	97.27 22	87.19 133	79.36 304	90.45 313	83.92 55	98.53 152	84.41 225	69.79 388	96.93 203
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
diffmvs		91.17 125	90.74 123	92.44 139	93.11 236	82.50 138	96.25 232	93.62 355	87.79 110	90.40 135	95.93 159	73.44 217	97.42 234	93.62 92	92.55 178	97.41 166
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt13		90.08 155	89.36 160	92.26 153	93.03 237	81.90 161	96.37 220	94.34 290	86.16 159	87.44 185	95.30 185	70.93 256	97.55 215	89.05 173	91.59 195	97.35 172

tttt0517		88.57 201	88.19 191	89.71 274	93.00 238	75.99 354	95.67 277	96.67 86	80.78 305	81.82 278	94.40 234	88.97 15	97.58 209	76.05 326	86.31 269	95.57 256

MVSFormer		91.36 120	90.57 126	93.73 66	93.00 238	88.08 20	94.80 321	94.48 273	80.74 306	94.90 61	97.13 124	78.84 104	95.10 373	83.77 233	97.46 77	98.02 97

lupinMVS		93.87 47	93.58 54	94.75 31	93.00 238	88.08 20	99.15 12	95.50 205	91.03 53	94.90 61	97.66 93	78.84 104	97.56 211	94.64 79	97.46 77	98.62 57

casdiffmvs_mvg		91.13 126	90.45 130	93.17 96	92.99 241	83.58 110	97.46 124	94.56 269	87.69 113	87.19 192	94.98 210	74.50 202	97.60 205	91.88 124	92.79 175	98.34 71
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmanbaseed2359cas		90.74 139	90.07 144	92.76 117	92.98 242	82.93 125	96.53 206	94.28 296	87.08 136	88.96 157	95.64 171	72.03 240	97.58 209	90.85 138	92.26 186	97.76 124

test_fmvs1		87.79 224	88.52 184	85.62 367	92.98 242	64.31 445	97.88 88	92.42 390	87.95 105	92.24 101	95.82 162	47.94 426	98.44 161	95.31 70	94.09 151	94.09 295

mamba_0408		85.26 278	83.10 297	91.74 191	92.94 244	82.53 133	72.52 483	91.77 402	80.36 318	83.50 253	94.01 247	64.97 310	96.90 277	79.37 282	88.51 244	95.79 246

SSM_04072		84.64 289	83.10 297	89.25 281	92.94 244	82.53 133	72.52 483	91.77 402	80.36 318	83.50 253	94.01 247	64.97 310	89.41 453	79.37 282	88.51 244	95.79 246

SSM_0407		87.33 237	85.87 241	91.71 195	92.94 244	82.53 133	94.30 334	92.33 393	80.11 326	83.50 253	94.18 242	64.68 314	96.80 288	82.34 252	88.51 244	95.79 246

SSM_0404		87.69 229	86.26 235	91.95 175	92.94 244	83.02 123	94.69 323	92.33 393	80.11 326	84.65 232	94.18 242	64.68 314	96.90 277	82.34 252	90.44 209	95.94 240

tpm2		87.35 236	86.26 235	90.62 239	92.93 248	78.67 281	88.06 430	95.99 168	79.33 342	87.40 186	86.43 381	80.28 81	96.40 300	80.23 273	85.73 280	96.79 212

baseline		90.76 138	90.10 142	92.74 119	92.90 249	82.56 132	94.60 324	94.56 269	87.69 113	89.06 156	95.67 169	73.76 212	97.51 223	90.43 150	92.23 188	98.16 87

fmvsm_s_conf0.5_n_5		93.57 52	93.75 48	93.01 103	92.87 250	82.73 129	98.93 32	95.90 179	90.96 55	95.61 48	98.39 45	76.57 150	99.63 72	98.32 15	96.24 119	96.68 220

GDP-MVS		92.85 70	92.55 80	93.75 63	92.82 251	85.76 51	97.63 106	95.05 233	88.34 94	93.15 86	97.10 127	86.92 28	98.01 182	87.95 194	94.00 155	97.47 158

test_fmvsmconf_n		93.99 44	94.36 39	92.86 111	92.82 251	81.12 186	99.26 6	96.37 134	93.47 22	95.16 54	98.21 55	79.00 101	99.64 70	98.21 20	96.73 112	97.83 118

casdiffmvs		90.95 133	90.39 132	92.63 127	92.82 251	82.53 133	96.83 181	94.47 276	87.69 113	88.47 167	95.56 177	74.04 208	97.54 218	90.90 136	92.74 176	97.83 118
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.5_n_7		92.88 67	93.82 47	90.08 258	92.79 254	76.45 343	98.54 48	96.74 76	92.28 34	95.22 53	98.49 35	74.91 194	98.15 175	98.28 16	97.13 93	95.63 252

Vis-MVSNet		88.67 197	87.82 198	91.24 217	92.68 255	78.82 271	96.95 173	93.85 328	87.55 117	87.07 195	95.13 200	63.43 321	97.21 254	77.58 306	96.15 122	97.70 131
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
E2		90.33 151	89.65 155	92.37 144	92.66 256	81.99 154	96.58 201	94.39 286	86.71 150	87.88 180	95.25 187	72.18 234	97.56 211	90.37 153	90.88 205	97.57 144

GBi-Net		82.42 328	80.43 339	88.39 300	92.66 256	81.95 156	94.30 334	93.38 365	79.06 350	75.82 350	85.66 390	56.38 388	93.84 409	71.23 368	75.38 350	89.38 349

test1		82.42 328	80.43 339	88.39 300	92.66 256	81.95 156	94.30 334	93.38 365	79.06 350	75.82 350	85.66 390	56.38 388	93.84 409	71.23 368	75.38 350	89.38 349

FMVSNet2		82.79 322	80.44 338	89.83 270	92.66 256	85.43 63	95.42 289	94.35 289	79.06 350	74.46 363	87.28 362	56.38 388	94.31 401	69.72 380	74.68 356	89.76 342

E3		90.33 151	89.65 155	92.37 144	92.64 260	81.99 154	96.58 201	94.39 286	86.71 150	87.87 181	95.27 186	72.17 235	97.56 211	90.37 153	90.88 205	97.57 144

BP-MVS1		93.55 53	93.50 57	93.71 68	92.64 260	85.39 64	97.78 95	96.84 61	89.52 75	92.00 107	97.06 130	88.21 22	98.03 179	91.45 126	96.00 129	97.70 131

miper_ehance_all_eth		84.57 292	83.60 287	87.50 331	92.64 260	78.25 295	95.40 291	93.47 360	79.28 345	76.41 338	87.64 358	76.53 151	95.24 362	78.58 292	72.42 368	89.01 372

cascas		86.50 248	84.48 267	92.55 132	92.64 260	85.95 46	97.04 163	95.07 232	75.32 389	80.50 289	91.02 304	54.33 401	97.98 184	86.79 210	87.62 257	93.71 302

TESTMET0.1,1		89.83 164	89.34 161	91.31 212	92.54 264	80.19 230	97.11 155	96.57 103	86.15 160	86.85 203	91.83 295	79.32 93	96.95 273	81.30 263	92.35 185	96.77 214

guyue		89.85 162	89.33 162	91.40 210	92.53 265	80.15 232	96.82 183	95.68 193	89.66 73	86.43 207	94.23 238	67.00 291	97.16 257	91.96 122	89.65 217	96.89 206

COLMAP_ROB	73.24 19	75.74 399	73.00 406	83.94 392	92.38 266	69.08 423	91.85 389	86.93 452	61.48 460	65.32 431	90.27 316	42.27 445	96.93 276	50.91 460	75.63 349	85.80 434
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_vis1_n_1920		89.95 159	90.59 125	88.03 317	92.36 267	68.98 424	99.12 16	94.34 290	93.86 19	93.64 80	97.01 132	51.54 408	99.59 76	96.76 52	96.71 113	95.53 258

viewdifsd2359ckpt07		89.04 184	88.30 188	91.27 215	92.32 268	78.90 268	95.89 263	93.77 341	84.48 219	85.18 221	95.16 197	69.83 264	97.70 199	88.75 184	89.29 225	97.22 179

xiu_mvs_v1_base_debu		90.54 144	89.54 157	93.55 79	92.31 269	87.58 27	96.99 165	94.87 241	87.23 130	93.27 82	97.56 102	57.43 376	98.32 166	92.72 108	93.46 168	94.74 281

xiu_mvs_v1_base		90.54 144	89.54 157	93.55 79	92.31 269	87.58 27	96.99 165	94.87 241	87.23 130	93.27 82	97.56 102	57.43 376	98.32 166	92.72 108	93.46 168	94.74 281

xiu_mvs_v1_base_debi		90.54 144	89.54 157	93.55 79	92.31 269	87.58 27	96.99 165	94.87 241	87.23 130	93.27 82	97.56 102	57.43 376	98.32 166	92.72 108	93.46 168	94.74 281

icg_test_0407_2		87.55 232	86.59 232	90.43 245	92.30 272	78.81 273	92.17 383	93.84 329	85.14 194	83.68 250	94.49 230	67.75 281	95.02 381	81.33 259	88.61 235	97.46 159

IMVS_0407		87.82 222	86.72 229	91.14 222	92.30 272	78.81 273	93.34 361	93.84 329	85.14 194	83.68 250	94.49 230	67.75 281	97.14 262	81.33 259	88.61 235	97.46 159

IMVS_0404		85.34 275	83.69 279	90.29 252	92.30 272	78.81 273	90.62 404	93.84 329	85.14 194	72.51 384	94.49 230	54.36 400	94.61 394	81.33 259	88.61 235	97.46 159

IMVS_0403		88.07 214	87.02 222	91.24 217	92.30 272	78.81 273	93.62 353	93.84 329	85.14 194	84.36 235	94.49 230	69.49 268	97.46 233	81.33 259	88.61 235	97.46 159

SCA		85.63 266	83.64 285	91.60 200	92.30 272	81.86 164	92.88 374	95.56 200	84.85 204	82.52 264	85.12 404	58.04 364	95.39 351	73.89 350	87.58 259	97.54 147

fmvsm_s_conf0.1_n_2		92.26 96	92.48 82	91.60 200	92.29 277	80.55 213	98.73 38	94.33 293	93.80 20	96.18 41	98.11 64	66.93 293	99.75 49	98.19 21	93.74 162	94.50 288

gm-plane-assit					92.27 278	79.64 249			84.47 220		95.15 199		97.93 185	85.81 215

test-LLR		88.48 203	87.98 194	89.98 263	92.26 279	77.23 329	97.11 155	95.96 171	83.76 247	86.30 210	91.38 298	72.30 232	96.78 289	80.82 266	91.92 190	95.94 240

test-mter		88.95 187	88.60 178	89.98 263	92.26 279	77.23 329	97.11 155	95.96 171	85.32 187	86.30 210	91.38 298	76.37 156	96.78 289	80.82 266	91.92 190	95.94 240

PAPM		92.87 69	92.40 83	94.30 41	92.25 281	87.85 22	96.40 219	96.38 131	91.07 52	88.72 164	96.90 134	82.11 68	97.37 244	90.05 158	97.70 71	97.67 133

viewmambaseed2359dif		89.52 170	89.02 167	91.03 225	92.24 282	78.83 270	95.89 263	93.77 341	83.04 263	88.28 173	95.80 163	72.08 238	97.40 237	89.76 162	90.32 210	96.87 209

cl____		83.27 312	82.12 312	86.74 345	92.20 283	75.95 355	95.11 309	93.27 371	78.44 359	74.82 361	87.02 369	74.19 205	95.19 364	74.67 343	69.32 392	89.09 361

DIV-MVS_self_test		83.27 312	82.12 312	86.74 345	92.19 284	75.92 357	95.11 309	93.26 372	78.44 359	74.81 362	87.08 368	74.19 205	95.19 364	74.66 344	69.30 393	89.11 360

AllTest		75.92 397	73.06 405	84.47 386	92.18 285	67.29 430	91.07 399	84.43 464	67.63 440	63.48 436	90.18 317	38.20 458	97.16 257	57.04 440	73.37 361	88.97 375

TestCases				84.47 386	92.18 285	67.29 430		84.43 464	67.63 440	63.48 436	90.18 317	38.20 458	97.16 257	57.04 440	73.37 361	88.97 375

KinetiMVS		89.13 182	87.95 195	92.65 124	92.16 287	82.39 143	97.04 163	96.05 162	86.59 153	88.08 178	94.85 218	61.54 340	98.38 163	81.28 264	93.99 157	97.19 185

CLD-MVS		87.97 219	87.48 210	89.44 278	92.16 287	80.54 217	98.14 67	94.92 238	91.41 46	79.43 303	95.40 182	62.34 327	97.27 250	90.60 145	82.90 301	90.50 327
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Syy-MVS		77.97 382	78.05 363	77.74 440	92.13 289	56.85 471	93.97 343	94.23 300	82.43 278	73.39 370	93.57 261	57.95 367	87.86 462	32.40 484	82.34 307	88.51 383

myMVS_eth3d		81.93 335	82.18 311	81.18 421	92.13 289	67.18 432	93.97 343	94.23 300	82.43 278	73.39 370	93.57 261	76.98 142	87.86 462	50.53 462	82.34 307	88.51 383

c3_l		83.80 304	82.65 306	87.25 339	92.10 291	77.74 320	95.25 298	93.04 381	78.58 356	76.01 346	87.21 366	75.25 189	95.11 372	77.54 307	68.89 396	88.91 378

HQP-NCC					92.08 292		97.63 106		90.52 60	82.30 268

ACMP_Plane					92.08 292		97.63 106		90.52 60	82.30 268

HQP-MVS		87.91 221	87.55 208	88.98 287	92.08 292	78.48 285	97.63 106	94.80 247	90.52 60	82.30 268	94.56 227	65.40 305	97.32 245	87.67 200	83.01 298	91.13 319

PCF-MVS	84.09 5	86.77 246	85.00 260	92.08 167	92.06 295	83.07 121	92.14 384	94.47 276	79.63 337	76.90 330	94.78 220	71.15 250	99.20 112	72.87 357	91.05 203	93.98 297
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
NP-MVS					92.04 296	78.22 296					94.56 227

diffmvs_AUTHOR		90.86 137	90.41 131	92.24 154	92.01 297	82.22 147	96.18 239	93.64 353	87.28 127	90.46 134	95.64 171	72.82 223	97.39 239	93.17 101	92.46 181	97.11 189

plane_prior6					91.98 298	77.92 309						64.77 312

Effi-MVS+-dtu		84.61 291	84.90 263	83.72 397	91.96 299	63.14 453	94.95 315	93.34 369	85.57 179	79.79 299	87.12 367	61.99 336	95.61 344	83.55 239	85.83 278	92.41 314

plane_prior1					91.95 300

CDS-MVSNet		89.50 171	88.96 171	91.14 222	91.94 301	80.93 198	97.09 159	95.81 186	84.26 228	84.72 230	94.20 241	80.31 80	95.64 341	83.37 243	88.96 231	96.85 210
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
E4		89.85 162	89.06 165	92.22 157	91.88 302	81.63 175	96.43 216	94.27 297	86.32 157	87.29 189	94.97 211	70.81 258	97.52 221	89.57 166	90.00 213	97.51 154

HQP_MVS		87.50 234	87.09 220	88.74 292	91.86 303	77.96 306	97.18 145	94.69 256	89.89 70	81.33 281	94.15 244	64.77 312	97.30 247	87.08 204	82.82 302	90.96 321

plane_prior7					91.86 303	77.55 323

eth_miper_zixun_eth		83.12 316	82.01 314	86.47 350	91.85 305	74.80 366	94.33 332	93.18 375	79.11 348	75.74 353	87.25 365	72.71 224	95.32 356	76.78 315	67.13 415	89.27 355

E5new		89.38 173	88.55 180	91.85 182	91.77 306	80.97 192	95.90 259	94.22 302	86.03 166	86.88 198	94.90 214	69.05 271	97.47 227	88.86 176	89.35 220	97.10 191

E5		89.38 173	88.55 180	91.85 182	91.77 306	80.97 192	95.90 259	94.22 302	86.03 166	86.88 198	94.90 214	69.05 271	97.47 227	88.86 176	89.35 220	97.10 191

E6new		89.37 175	88.55 180	91.85 182	91.75 308	80.97 192	95.90 259	94.22 302	86.03 166	86.88 198	94.91 212	69.05 271	97.47 227	88.86 176	89.34 222	97.10 191

E6		89.37 175	88.55 180	91.85 182	91.75 308	80.97 192	95.90 259	94.22 302	86.03 166	86.88 198	94.91 212	69.05 271	97.47 227	88.86 176	89.34 222	97.10 191

viewmacassd2359aftdt		89.89 161	89.01 169	92.52 134	91.56 310	82.46 139	96.32 227	94.06 316	86.41 154	88.11 177	95.01 207	69.68 267	97.47 227	88.73 185	91.19 199	97.63 138

VDDNet		86.44 249	84.51 265	92.22 157	91.56 310	81.83 165	97.10 158	94.64 263	69.50 435	87.84 182	95.19 195	48.01 424	97.92 190	89.82 160	86.92 263	96.89 206

EI-MVSNet		85.80 262	85.20 254	87.59 327	91.55 312	77.41 325	95.13 307	95.36 216	80.43 316	80.33 293	94.71 223	73.72 213	95.97 317	76.96 314	78.64 331	89.39 347

CVMVSNet		84.83 286	85.57 246	82.63 409	91.55 312	60.38 463	95.13 307	95.03 234	80.60 309	82.10 274	94.71 223	66.40 299	90.19 450	74.30 347	90.32 210	97.31 175

ACMP	81.66 11	84.00 301	83.22 295	86.33 351	91.53 314	72.95 388	95.91 258	93.79 337	83.70 250	73.79 366	92.22 282	54.31 402	96.89 279	83.98 229	79.74 320	89.16 359
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
IterMVS-LS		83.93 302	82.80 304	87.31 337	91.46 315	77.39 326	95.66 278	93.43 363	80.44 314	75.51 354	87.26 364	73.72 213	95.16 367	76.99 312	70.72 379	89.39 347
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		84.10 299	82.90 301	87.70 322	91.41 316	73.28 381	90.59 405	93.19 373	85.02 200	77.96 318	93.68 258	57.92 369	96.18 311	75.50 334	80.87 314	93.63 303

WB-MVSnew		84.08 300	83.51 289	85.80 360	91.34 317	76.69 340	95.62 281	96.27 143	81.77 290	81.81 279	92.81 273	58.23 361	94.70 391	66.66 393	87.06 262	85.99 430

Patchmatch-test		78.25 377	74.72 392	88.83 290	91.20 318	74.10 374	73.91 481	88.70 444	59.89 468	66.82 422	85.12 404	78.38 112	94.54 396	48.84 467	79.58 323	97.86 115

miper_lstm_enhance		81.66 341	80.66 335	84.67 382	91.19 319	71.97 397	91.94 386	93.19 373	77.86 363	72.27 385	85.26 398	73.46 216	93.42 417	73.71 353	67.05 416	88.61 381

ACMM	80.70 13	83.72 306	82.85 303	86.31 354	91.19 319	72.12 394	95.88 265	94.29 295	80.44 314	77.02 328	91.96 290	55.24 394	97.14 262	79.30 285	80.38 317	89.67 343
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
testing3		80.74 354	81.17 327	79.44 431	91.15 321	63.48 451	97.16 149	95.76 188	80.83 303	71.36 391	93.15 268	78.22 116	87.30 467	43.19 476	79.67 321	87.55 408

UWE-MVS-28		85.41 274	86.36 234	82.59 410	91.12 322	66.81 437	93.88 347	97.03 42	83.86 243	78.55 309	93.84 254	77.76 126	88.55 457	73.47 355	87.69 256	92.41 314

TAMVS		88.48 203	87.79 199	90.56 241	91.09 323	79.18 260	96.45 213	95.88 182	83.64 253	83.12 260	93.33 264	75.94 168	95.74 336	82.40 251	88.27 250	96.75 217

ACMH+	76.62 16	77.47 388	74.94 389	85.05 376	91.07 324	71.58 404	93.26 366	90.01 429	71.80 423	64.76 433	88.55 338	41.62 448	96.48 298	62.35 417	71.00 376	87.09 414

OpenMVS	79.58 14	86.09 257	83.62 286	93.50 82	90.95 325	86.71 37	97.44 125	95.83 185	75.35 388	72.64 381	95.72 165	57.42 379	99.64 70	71.41 366	95.85 132	94.13 294

LPG-MVS_test		84.20 298	83.49 290	86.33 351	90.88 326	73.06 384	95.28 293	94.13 311	82.20 282	76.31 339	93.20 265	54.83 398	96.95 273	83.72 235	80.83 315	88.98 373

LGP-MVS_train				86.33 351	90.88 326	73.06 384		94.13 311	82.20 282	76.31 339	93.20 265	54.83 398	96.95 273	83.72 235	80.83 315	88.98 373

test_fmvsmvis_n_1920		92.12 98	92.10 95	92.17 162	90.87 328	81.04 189	98.34 60	93.90 324	92.71 28	87.24 191	97.90 82	74.83 195	99.72 57	96.96 49	96.20 120	95.76 250

KD-MVS_2432*1600		77.63 385	74.92 390	85.77 361	90.86 329	79.44 251	88.08 428	93.92 322	76.26 383	67.05 420	82.78 423	72.15 236	91.92 432	61.53 418	41.62 484	85.94 431

miper_refine_blended		77.63 385	74.92 390	85.77 361	90.86 329	79.44 251	88.08 428	93.92 322	76.26 383	67.05 420	82.78 423	72.15 236	91.92 432	61.53 418	41.62 484	85.94 431

baseline2		90.39 148	90.21 139	90.93 228	90.86 329	80.99 191	95.20 301	97.41 18	86.03 166	80.07 298	94.61 226	90.58 6	97.47 227	87.29 203	89.86 216	94.35 289

AstraMVS		88.99 186	88.35 187	90.92 229	90.81 332	78.29 292	96.73 191	94.24 299	89.96 69	86.13 212	95.04 204	62.12 333	97.41 235	92.54 112	87.57 260	97.06 198

PVSNet_0	77.72 15	81.70 339	78.95 358	89.94 266	90.77 333	76.72 339	95.96 250	96.95 51	85.01 201	70.24 406	88.53 340	52.32 405	98.20 171	86.68 211	44.08 481	94.89 276

ACMH	75.40 17	77.99 380	74.96 388	87.10 342	90.67 334	76.41 344	93.19 369	91.64 407	72.47 417	63.44 438	87.61 359	43.34 440	97.16 257	58.34 434	73.94 358	87.72 400
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS-HIRNet		71.36 424	67.00 430	84.46 388	90.58 335	69.74 419	79.15 469	87.74 448	46.09 482	61.96 448	50.50 486	45.14 435	95.64 341	53.74 452	88.11 252	88.00 397

fmvsm_s_conf0.1_n		92.93 65	93.16 65	92.24 154	90.52 336	81.92 159	98.42 53	96.24 146	91.17 49	96.02 44	98.35 50	75.34 187	99.74 52	97.84 33	94.58 146	95.05 273

jason		92.73 73	92.23 90	94.21 46	90.50 337	87.30 31	98.65 43	95.09 230	90.61 59	92.76 94	97.13 124	75.28 188	97.30 247	93.32 97	96.75 111	98.02 97
jason: jason.
LTVRE_ROB	73.68 18	77.99 380	75.74 383	84.74 379	90.45 338	72.02 395	86.41 443	91.12 416	72.57 416	66.63 424	87.27 363	54.95 397	96.98 271	56.29 444	75.98 345	85.21 437
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
viewdifsd2359ckpt11		86.38 250	85.29 251	89.66 276	90.42 339	75.65 360	95.27 296	92.45 388	85.54 182	84.27 237	94.73 221	62.16 329	97.39 239	87.78 196	74.97 353	95.96 237

viewmsd2359difaftdt		86.38 250	85.29 251	89.67 275	90.42 339	75.65 360	95.27 296	92.45 388	85.54 182	84.28 236	94.73 221	62.16 329	97.39 239	87.78 196	74.97 353	95.96 237

XVG-OURS		85.18 279	84.38 270	87.59 327	90.42 339	71.73 402	91.06 400	94.07 315	82.00 288	83.29 258	95.08 203	56.42 387	97.55 215	83.70 237	83.42 294	93.49 306

VPA-MVSNet		85.32 276	83.83 278	89.77 273	90.25 342	82.63 131	96.36 223	97.07 39	83.03 265	81.21 283	89.02 332	61.58 339	96.31 305	85.02 222	70.95 377	90.36 328

XVG-OURS-SEG-HR		85.74 264	85.16 257	87.49 333	90.22 343	71.45 405	91.29 396	94.09 314	81.37 294	83.90 247	95.22 192	60.30 346	97.53 220	85.58 217	84.42 289	93.50 305

SD_0403		81.29 345	81.13 329	81.78 418	90.20 344	60.43 462	89.97 409	91.31 415	83.87 241	71.78 388	93.08 270	63.86 318	89.61 452	60.00 427	86.07 275	95.30 265

tpm		85.55 270	84.47 268	88.80 291	90.19 345	75.39 363	88.79 421	94.69 256	84.83 205	83.96 245	85.21 400	78.22 116	94.68 393	76.32 324	78.02 339	96.34 229

CR-MVSNet		83.53 308	81.36 325	90.06 259	90.16 346	79.75 243	79.02 470	91.12 416	84.24 229	82.27 272	80.35 443	75.45 179	93.67 413	63.37 414	86.25 270	96.75 217

RPMNet		79.85 360	75.92 380	91.64 197	90.16 346	79.75 243	79.02 470	95.44 210	58.43 472	82.27 272	72.55 473	73.03 221	98.41 162	46.10 471	86.25 270	96.75 217

test_cas_vis1_n_1920		89.90 160	90.02 147	89.54 277	90.14 348	74.63 368	98.71 40	94.43 282	93.04 26	92.40 98	96.35 152	53.41 404	99.08 123	95.59 64	96.16 121	94.90 275

FIs		86.73 247	86.10 238	88.61 295	90.05 349	80.21 228	96.14 243	96.95 51	85.56 181	78.37 312	92.30 281	76.73 148	95.28 358	79.51 279	79.27 325	90.35 329

FMVSNet5		76.46 395	74.16 398	83.35 402	90.05 349	76.17 347	89.58 413	89.85 430	71.39 426	65.29 432	80.42 442	50.61 414	87.70 465	61.05 423	69.24 394	86.18 425

0.4-1-1-0.2		87.73 225	85.82 242	93.46 87	89.97 351	85.31 68	98.49 51	96.55 106	81.24 296	87.14 193	89.63 325	76.16 162	97.02 266	86.84 209	66.38 422	98.05 95

IterMVS		80.67 355	79.16 355	85.20 374	89.79 352	76.08 349	92.97 372	91.86 399	80.28 322	71.20 393	85.14 403	57.93 368	91.34 439	72.52 360	70.74 378	88.18 394
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSC-MVS3.2		81.06 349	79.49 353	85.75 363	89.78 353	73.00 386	94.40 330	95.23 226	83.76 247	76.61 335	87.82 355	49.48 420	94.88 383	66.80 391	71.56 373	89.38 349

mvsany_test1		87.58 231	88.22 189	85.67 365	89.78 353	67.18 432	95.25 298	87.93 446	83.96 237	88.79 161	97.06 130	72.52 227	94.53 397	92.21 116	86.45 268	95.30 265

UniMVSNet (Re)		85.31 277	84.23 272	88.55 296	89.75 355	80.55 213	96.72 192	96.89 56	85.42 185	78.40 311	88.93 333	75.38 183	95.52 348	78.58 292	68.02 405	89.57 346

Patchmtry		77.36 389	74.59 393	85.67 365	89.75 355	75.75 359	77.85 473	91.12 416	60.28 465	71.23 392	80.35 443	75.45 179	93.56 415	57.94 435	67.34 413	87.68 402

JIA-IIPM		79.00 370	77.20 369	84.40 389	89.74 357	64.06 448	75.30 478	95.44 210	62.15 456	81.90 276	59.08 483	78.92 102	95.59 345	66.51 397	85.78 279	93.54 304

0.4-1-1-0.1		87.53 233	85.67 244	93.13 97	89.70 358	84.41 90	98.30 61	96.55 106	80.85 302	86.94 197	89.53 327	76.18 160	96.99 270	86.62 212	66.36 423	97.98 104

kuosan		73.55 409	72.39 409	77.01 444	89.68 359	66.72 438	85.24 452	93.44 361	67.76 439	60.04 457	83.40 420	71.90 241	84.25 475	45.34 473	54.75 449	80.06 470

MS-PatchMatch		83.05 317	81.82 318	86.72 349	89.64 360	79.10 264	94.88 317	94.59 268	79.70 336	70.67 398	89.65 324	50.43 415	96.82 285	70.82 375	95.99 130	84.25 445

IterMVS-SCA-FT		80.51 357	79.10 356	84.73 380	89.63 361	74.66 367	92.98 371	91.81 401	80.05 329	71.06 396	85.18 401	58.04 364	91.40 438	72.48 361	70.70 380	88.12 395

mmtdpeth		78.04 379	76.76 374	81.86 417	89.60 362	66.12 440	92.34 382	87.18 450	76.83 379	85.55 218	76.49 461	46.77 431	97.02 266	90.85 138	45.24 478	82.43 458

Fast-Effi-MVS+-dtu		83.33 311	82.60 307	85.50 369	89.55 363	69.38 422	96.09 246	91.38 410	82.30 281	75.96 348	91.41 297	56.71 383	95.58 346	75.13 339	84.90 286	91.54 317

PatchT		79.75 361	76.85 373	88.42 297	89.55 363	75.49 362	77.37 474	94.61 266	63.07 452	82.46 266	73.32 470	75.52 178	93.41 418	51.36 458	84.43 288	96.36 227

GA-MVS		85.79 263	84.04 277	91.02 227	89.47 365	80.27 225	96.90 178	94.84 245	85.57 179	80.88 285	89.08 330	56.56 386	96.47 299	77.72 302	85.35 283	96.34 229

UniMVSNet_NR-MVSNet		85.49 271	84.59 264	88.21 311	89.44 366	79.36 254	96.71 194	96.41 125	85.22 190	78.11 315	90.98 306	76.97 143	95.14 370	79.14 287	68.30 402	90.12 335

FC-MVSNet-test		85.96 259	85.39 249	87.66 324	89.38 367	78.02 303	95.65 279	96.87 58	85.12 198	77.34 321	91.94 293	76.28 159	94.74 390	77.09 311	78.82 329	90.21 332

WR-MVS		84.32 296	82.96 299	88.41 298	89.38 367	80.32 222	96.59 200	96.25 145	83.97 236	76.63 333	90.36 315	67.53 286	94.86 385	75.82 329	70.09 386	90.06 339

VPNet		84.69 288	82.92 300	90.01 261	89.01 369	83.45 113	96.71 194	95.46 208	85.71 177	79.65 300	92.18 285	56.66 385	96.01 316	83.05 247	67.84 408	90.56 326

Elysia		85.62 267	83.66 282	91.51 203	88.76 370	82.21 148	95.15 305	94.70 252	76.96 377	84.13 239	92.20 283	50.81 411	97.26 251	77.81 297	92.42 182	95.06 271

StellarMVS		85.62 267	83.66 282	91.51 203	88.76 370	82.21 148	95.15 305	94.70 252	76.96 377	84.13 239	92.20 283	50.81 411	97.26 251	77.81 297	92.42 182	95.06 271

nrg030		86.79 245	85.43 248	90.87 233	88.76 370	85.34 65	97.06 162	94.33 293	84.31 223	80.45 291	91.98 289	72.36 229	96.36 303	88.48 189	71.13 375	90.93 323

DU-MVS		84.57 292	83.33 292	88.28 304	88.76 370	79.36 254	96.43 216	95.41 215	85.42 185	78.11 315	90.82 307	67.61 283	95.14 370	79.14 287	68.30 402	90.33 330

NR-MVSNet		83.35 310	81.52 323	88.84 289	88.76 370	81.31 182	94.45 326	95.16 228	84.65 211	67.81 416	90.82 307	70.36 261	94.87 384	74.75 341	66.89 418	90.33 330

test_0402		72.68 415	69.54 422	82.09 415	88.67 375	71.81 401	92.72 376	86.77 455	61.52 459	62.21 446	83.91 415	43.22 441	93.76 412	34.60 482	72.23 371	80.72 469

RPSCF		77.73 384	76.63 375	81.06 422	88.66 376	55.76 476	87.77 432	87.88 447	64.82 449	74.14 365	92.79 275	49.22 421	96.81 286	67.47 388	76.88 341	90.62 325

LuminaMVS		88.02 217	86.89 226	91.43 208	88.65 377	83.16 119	94.84 318	94.41 284	83.67 251	86.56 206	91.95 292	62.04 334	96.88 281	89.78 161	90.06 212	94.24 290

FMVSNet1		79.50 365	76.54 376	88.39 300	88.47 378	81.95 156	94.30 334	93.38 365	73.14 408	72.04 387	85.66 390	43.86 437	93.84 409	65.48 401	72.53 367	89.38 349

test_fmvsmconf0.1_n		93.08 61	93.22 64	92.65 124	88.45 379	80.81 203	99.00 28	95.11 229	93.21 24	94.00 75	97.91 81	76.84 144	99.59 76	97.91 29	96.55 116	97.54 147

MonoMVSNet		85.68 265	84.22 273	90.03 260	88.43 380	77.83 313	92.95 373	91.46 409	87.28 127	78.11 315	85.96 389	66.31 300	94.81 387	90.71 143	76.81 342	97.46 159

OPM-MVS		85.84 261	85.10 259	88.06 315	88.34 381	77.83 313	95.72 273	94.20 307	87.89 109	80.45 291	94.05 246	58.57 358	97.26 251	83.88 230	82.76 304	89.09 361
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tfpnnormal		78.14 378	75.42 386	86.31 354	88.33 382	79.24 257	94.41 327	96.22 148	73.51 404	69.81 409	85.52 396	55.43 392	95.75 333	47.65 469	67.86 407	83.95 448

TinyColmap		72.41 416	68.99 425	82.68 407	88.11 383	69.59 420	88.41 424	85.20 460	65.55 446	57.91 463	84.82 408	30.80 474	95.94 321	51.38 457	68.70 397	82.49 457

fmvsm_s_conf0.1_n_a		92.38 92	92.49 81	92.06 169	88.08 384	81.62 176	97.97 82	96.01 165	90.62 58	96.58 35	98.33 51	74.09 207	99.71 60	97.23 45	93.46 168	94.86 277

WR-MVS_H		81.02 350	80.09 342	83.79 394	88.08 384	71.26 408	94.46 325	96.54 108	80.08 328	72.81 380	86.82 371	70.36 261	92.65 422	64.18 408	67.50 411	87.46 410

CP-MVSNet		81.01 351	80.08 343	83.79 394	87.91 386	70.51 411	94.29 338	95.65 195	80.83 303	72.54 383	88.84 334	63.71 319	92.32 427	68.58 385	68.36 401	88.55 382

D2MVS		82.67 324	81.55 321	86.04 358	87.77 387	76.47 341	95.21 300	96.58 102	82.66 275	70.26 404	85.46 397	60.39 345	95.80 328	76.40 322	79.18 326	85.83 433

TranMVSNet+NR-MVSNet		83.24 314	81.71 319	87.83 319	87.71 388	78.81 273	96.13 245	94.82 246	84.52 216	76.18 345	90.78 309	64.07 317	94.60 395	74.60 345	66.59 421	90.09 337

USDC		78.65 375	76.25 377	85.85 359	87.58 389	74.60 369	89.58 413	90.58 427	84.05 233	63.13 440	88.23 348	40.69 456	96.86 284	66.57 396	75.81 348	86.09 427

PS-CasMVS		80.27 358	79.18 354	83.52 400	87.56 390	69.88 417	94.08 341	95.29 223	80.27 323	72.08 386	88.51 341	59.22 355	92.23 429	67.49 387	68.15 404	88.45 388

test_fmvs1_n		86.34 253	86.72 229	85.17 375	87.54 391	63.64 450	96.91 177	92.37 392	87.49 119	91.33 119	95.58 176	40.81 455	98.46 157	95.00 73	93.49 166	93.41 309

MIMVSNet		79.18 369	75.99 379	88.72 293	87.37 392	80.66 207	79.96 464	91.82 400	77.38 369	74.33 364	81.87 434	41.78 447	90.74 445	66.36 399	83.10 297	94.76 280

XXY-MVS		83.84 303	82.00 315	89.35 279	87.13 393	81.38 179	95.72 273	94.26 298	80.15 325	75.92 349	90.63 310	61.96 337	96.52 297	78.98 289	73.28 364	90.14 334

ITE_SJBPF				82.38 412	87.00 394	65.59 441		89.55 433	79.99 331	69.37 411	91.30 300	41.60 449	95.33 355	62.86 416	74.63 357	86.24 424

dongtai		69.47 430	68.98 426	70.93 455	86.87 395	58.45 468	88.19 426	93.18 375	63.98 450	56.04 468	80.17 445	70.97 255	79.24 482	33.46 483	47.94 474	75.09 476

test0.0.03 1		82.79 322	82.48 308	83.74 396	86.81 396	72.22 390	96.52 207	95.03 234	83.76 247	73.00 377	93.20 265	72.30 232	88.88 455	64.15 409	77.52 340	90.12 335

v8		81.88 336	80.06 345	87.32 336	86.63 397	79.04 267	94.41 327	93.65 352	78.77 354	73.19 376	85.57 394	66.87 294	95.81 327	73.84 352	67.61 410	87.11 413

usedtu_dtu_shiyan1		85.03 281	83.24 293	90.37 248	86.62 398	86.24 40	96.23 233	95.30 221	84.55 214	77.22 324	88.47 342	67.85 279	95.27 359	76.59 317	76.35 343	89.61 344

FE-MVSNET3		85.03 281	83.24 293	90.37 248	86.62 398	86.24 40	96.23 233	95.30 221	84.55 214	77.22 324	88.47 342	67.85 279	95.27 359	76.59 317	76.35 343	89.61 344

tt0805		81.20 348	79.06 357	87.61 325	86.50 400	72.97 387	93.66 351	95.48 206	74.11 399	76.23 343	91.99 288	41.36 451	97.40 237	77.44 309	74.78 355	92.45 313

v10		81.43 343	79.53 352	87.11 341	86.38 401	78.87 269	94.31 333	93.43 363	77.88 362	73.24 375	85.26 398	65.44 304	95.75 333	72.14 362	67.71 409	86.72 417

PEN-MVS		79.47 366	78.26 362	83.08 403	86.36 402	68.58 425	93.85 349	94.77 250	79.76 334	71.37 390	88.55 338	59.79 347	92.46 423	64.50 406	65.40 425	88.19 393

UniMVSNet_ETH3D		80.86 353	78.75 359	87.22 340	86.31 403	72.02 395	91.95 385	93.76 343	73.51 404	75.06 360	90.16 319	43.04 443	95.66 338	76.37 323	78.55 334	93.98 297

v1144		82.90 321	81.27 326	87.78 321	86.29 404	79.07 266	96.14 243	93.93 320	80.05 329	77.38 320	86.80 372	65.50 303	95.93 322	75.21 338	70.13 383	88.33 391

V42		83.04 318	81.53 322	87.57 329	86.27 405	79.09 265	95.87 266	94.11 313	80.35 320	77.22 324	86.79 373	65.32 307	96.02 315	77.74 301	70.14 382	87.61 404

v2v482		83.46 309	81.86 317	88.25 307	86.19 406	79.65 248	96.34 225	94.02 318	81.56 293	77.32 322	88.23 348	65.62 302	96.03 314	77.77 300	69.72 390	89.09 361

v148		82.41 330	80.89 330	86.99 343	86.18 407	76.81 337	96.27 230	93.82 333	80.49 313	75.28 357	86.11 388	67.32 289	95.75 333	75.48 335	67.03 417	88.42 389

pmmvs4		82.54 326	80.79 331	87.79 320	86.11 408	80.49 221	93.55 356	93.18 375	77.29 370	73.35 373	89.40 329	65.26 308	95.05 380	75.32 337	73.61 360	87.83 399

MVP-Stereo		82.65 325	81.67 320	85.59 368	86.10 409	78.29 292	93.33 362	92.82 383	77.75 364	69.17 413	87.98 352	59.28 354	95.76 332	71.77 363	96.88 104	82.73 454
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		82.31 331	80.55 337	87.60 326	85.94 410	78.47 288	95.85 268	93.80 336	79.33 342	76.97 329	86.51 376	63.33 323	95.87 324	73.11 356	70.13 383	88.46 387

TransMVSNet (Re)		76.94 392	74.38 395	84.62 384	85.92 411	75.25 364	95.28 293	89.18 438	73.88 402	67.22 417	86.46 378	59.64 348	94.10 404	59.24 432	52.57 464	84.50 443

PS-MVSNAJss		84.91 285	84.30 271	86.74 345	85.89 412	74.40 372	94.95 315	94.16 310	83.93 239	76.45 337	90.11 321	71.04 252	95.77 331	83.16 245	79.02 328	90.06 339

v144192		82.43 327	80.73 333	87.54 330	85.81 413	78.22 296	95.98 249	93.78 338	79.09 349	77.11 327	86.49 377	64.66 316	95.91 323	74.20 348	69.42 391	88.49 385

v1921920		82.02 334	80.23 341	87.41 334	85.62 414	77.92 309	95.79 272	93.69 350	78.86 353	76.67 332	86.44 379	62.50 326	95.83 326	72.69 358	69.77 389	88.47 386

v1240		81.70 339	79.83 349	87.30 338	85.50 415	77.70 321	95.48 286	93.44 361	78.46 358	76.53 336	86.44 379	60.85 344	95.84 325	71.59 365	70.17 381	88.35 390

pm-mvs1		80.05 359	78.02 364	86.15 356	85.42 416	75.81 358	95.11 309	92.69 386	77.13 372	70.36 400	87.43 360	58.44 360	95.27 359	71.36 367	64.25 430	87.36 411

our_test_3		77.90 383	75.37 387	85.48 370	85.39 417	76.74 338	93.63 352	91.67 405	73.39 407	65.72 429	84.65 409	58.20 363	93.13 420	57.82 436	67.87 406	86.57 420

ppachtmachnet_test		77.19 390	74.22 397	86.13 357	85.39 417	78.22 296	93.98 342	91.36 412	71.74 424	67.11 419	84.87 407	56.67 384	93.37 419	52.21 455	64.59 427	86.80 416

MDA-MVSNet-bldmvs		71.45 422	67.94 429	81.98 416	85.33 419	68.50 426	92.35 381	88.76 442	70.40 429	42.99 481	81.96 433	46.57 432	91.31 440	48.75 468	54.39 453	86.11 426

Baseline_NR-MVSNet		81.22 347	80.07 344	84.68 381	85.32 420	75.12 365	96.48 210	88.80 441	76.24 385	77.28 323	86.40 382	67.61 283	94.39 400	75.73 330	66.73 419	84.54 442

DTE-MVSNet		78.37 376	77.06 371	82.32 414	85.22 421	67.17 435	93.40 358	93.66 351	78.71 355	70.53 399	88.29 347	59.06 356	92.23 429	61.38 421	63.28 434	87.56 406

pmmvs5		81.34 344	79.54 351	86.73 348	85.02 422	76.91 334	96.22 235	91.65 406	77.65 365	73.55 368	88.61 337	55.70 391	94.43 399	74.12 349	73.35 363	88.86 379

XVG-ACMP-BASELINE		79.38 367	77.90 365	83.81 393	84.98 423	67.14 436	89.03 419	93.18 375	80.26 324	72.87 379	88.15 350	38.55 457	96.26 306	76.05 326	78.05 338	88.02 396

test_vis1_n		85.60 269	85.70 243	85.33 372	84.79 424	64.98 443	96.83 181	91.61 408	87.36 125	91.00 126	94.84 219	36.14 462	97.18 256	95.66 62	93.03 173	93.82 300

MDA-MVSNet_test_wron		73.54 410	70.43 418	82.86 405	84.55 425	71.85 399	91.74 391	91.32 414	67.63 440	46.73 478	81.09 440	55.11 395	90.42 449	55.91 446	59.76 440	86.31 423

SixPastTwentyTwo		76.04 396	74.32 396	81.22 420	84.54 426	61.43 460	91.16 398	89.30 437	77.89 361	64.04 435	86.31 383	48.23 422	94.29 402	63.54 413	63.84 432	87.93 398

YYNet1		73.53 411	70.43 418	82.85 406	84.52 427	71.73 402	91.69 392	91.37 411	67.63 440	46.79 477	81.21 439	55.04 396	90.43 448	55.93 445	59.70 441	86.38 422

tt0320-xc		69.70 427	65.27 439	82.99 404	84.33 428	71.92 398	89.56 415	82.08 475	50.11 479	61.87 449	77.50 453	30.48 476	92.34 426	60.30 425	51.20 466	84.71 440

N_pmnet		61.30 443	60.20 446	64.60 463	84.32 429	17.00 504	91.67 393	10.98 502	61.77 458	58.45 462	78.55 450	49.89 418	91.83 435	42.27 478	63.94 431	84.97 438

mvs_tets		81.74 338	80.71 334	84.84 378	84.22 430	70.29 414	93.91 346	93.78 338	82.77 272	73.37 372	89.46 328	47.36 430	95.31 357	81.99 256	79.55 324	88.92 377

jajsoiax		82.12 333	81.15 328	85.03 377	84.19 431	70.70 410	94.22 339	93.95 319	83.07 262	73.48 369	89.75 323	49.66 419	95.37 353	82.24 255	79.76 318	89.02 370

EU-MVSNet		76.92 393	76.95 372	76.83 446	84.10 432	54.73 478	91.77 390	92.71 385	72.74 412	69.57 410	88.69 336	58.03 366	87.43 466	64.91 404	70.00 387	88.33 391

test_djsdf		83.00 320	82.45 309	84.64 383	84.07 433	69.78 418	94.80 321	94.48 273	80.74 306	75.41 356	87.70 356	61.32 343	95.10 373	83.77 233	79.76 318	89.04 367

v7n		79.32 368	77.34 368	85.28 373	84.05 434	72.89 389	93.38 359	93.87 326	75.02 393	70.68 397	84.37 410	59.58 350	95.62 343	67.60 386	67.50 411	87.32 412

test_vis1_rt		73.96 405	72.40 408	78.64 437	83.91 435	61.16 461	95.63 280	68.18 491	76.32 382	60.09 456	74.77 464	29.01 478	97.54 218	87.74 198	75.94 346	77.22 474

dmvs_testset		72.00 421	73.36 404	67.91 458	83.83 436	31.90 498	85.30 451	77.12 483	82.80 271	63.05 442	92.46 278	61.54 340	82.55 480	42.22 479	71.89 372	89.29 354

sc_t1		72.37 417	68.03 428	85.39 371	83.78 437	70.51 411	91.27 397	83.70 471	52.46 478	68.29 414	82.02 432	30.58 475	94.81 387	64.50 406	55.69 447	90.85 324

OurMVSNet-221017-0		77.18 391	76.06 378	80.55 425	83.78 437	60.00 465	90.35 406	91.05 419	77.01 376	66.62 425	87.92 353	47.73 428	94.03 405	71.63 364	68.44 400	87.62 403

EG-PatchMatch MVS		74.92 402	72.02 410	83.62 398	83.76 439	73.28 381	93.62 353	92.04 398	68.57 438	58.88 460	83.80 416	31.87 472	95.57 347	56.97 442	78.67 330	82.00 462

tt0320		70.21 426	66.07 434	82.64 408	83.42 440	70.82 409	89.63 411	84.10 467	49.75 481	62.71 444	77.28 456	33.35 468	92.45 425	58.78 433	55.62 448	84.64 441

K. test v3		73.62 407	71.59 412	79.69 429	82.98 441	59.85 466	90.85 402	88.83 440	77.13 372	58.90 459	82.11 430	43.62 438	91.72 436	65.83 400	54.10 454	87.50 409

test_fmvs2		79.59 363	79.90 348	78.67 436	82.86 442	55.82 475	95.20 301	89.55 433	81.09 298	80.12 297	89.80 322	34.31 467	93.51 416	87.82 195	78.36 336	86.69 418

test_fmvsmconf0.01_n		91.08 128	90.68 124	92.29 151	82.43 443	80.12 233	97.94 83	93.93 320	92.07 38	91.97 108	97.60 100	67.56 285	99.53 84	97.09 47	95.56 137	97.21 182

EGC-MVSNET		52.46 451	47.56 454	67.15 459	81.98 444	60.11 464	82.54 462	72.44 487	0.11 499	0.70 500	74.59 465	25.11 479	83.26 477	29.04 486	61.51 438	58.09 484

anonymousdsp		80.98 352	79.97 346	84.01 391	81.73 445	70.44 413	92.49 378	93.58 358	77.10 374	72.98 378	86.31 383	57.58 375	94.90 382	79.32 284	78.63 333	86.69 418

Anonymous20231206		75.29 401	73.64 402	80.22 427	80.75 446	63.38 452	93.36 360	90.71 426	73.09 409	67.12 418	83.70 417	50.33 416	90.85 444	53.63 453	70.10 385	86.44 421

Gipuma		45.11 456	42.05 458	54.30 473	80.69 447	51.30 480	35.80 492	83.81 470	28.13 487	27.94 491	34.53 491	11.41 493	76.70 487	21.45 490	54.65 450	34.90 491
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
lessismore_v0				79.98 428	80.59 448	58.34 469		80.87 477		58.49 461	83.46 419	43.10 442	93.89 408	63.11 415	48.68 471	87.72 400

OpenMVS_ROB	68.52 20	73.02 414	69.57 421	83.37 401	80.54 449	71.82 400	93.60 355	88.22 445	62.37 455	61.98 447	83.15 422	35.31 466	95.47 349	45.08 474	75.88 347	82.82 452

testgi		74.88 403	73.40 403	79.32 432	80.13 450	61.75 457	93.21 367	86.64 456	79.49 340	66.56 426	91.06 303	35.51 465	88.67 456	56.79 443	71.25 374	87.56 406

blend_shiyan4		81.76 337	79.58 350	88.31 303	80.00 451	80.59 209	95.95 251	93.73 346	72.26 420	71.14 394	82.52 425	76.13 163	95.15 368	77.83 295	66.62 420	89.19 357

wanda-best-256-512		78.87 371	75.75 381	88.22 309	79.74 452	80.51 219	95.92 254	93.75 344	72.60 414	70.34 401	82.14 426	57.91 370	95.09 375	75.61 331	53.77 456	89.05 364

FE-blended-shiyan7		78.87 371	75.75 381	88.22 309	79.74 452	80.51 219	95.92 254	93.75 344	72.60 414	70.34 401	82.14 426	57.91 370	95.09 375	75.61 331	53.77 456	89.05 364

usedtu_blend_shiyan5		77.51 387	73.93 401	88.26 305	79.74 452	80.59 209	90.76 403	89.69 431	63.21 451	70.34 401	82.14 426	57.91 370	95.15 368	77.83 295	53.77 456	89.05 364

CMPMVS	54.94 21	75.71 400	74.56 394	79.17 433	79.69 455	55.98 473	89.59 412	93.30 370	60.28 465	53.85 472	89.07 331	47.68 429	96.33 304	76.55 319	81.02 313	85.22 436
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
blended_shiyan6		78.74 374	75.63 385	88.07 314	79.63 456	80.10 234	95.72 273	93.73 346	72.43 418	70.17 407	82.09 431	57.69 373	95.07 378	75.47 336	53.77 456	89.03 368

blended_shiyan8		78.76 373	75.65 384	88.10 313	79.58 457	80.20 229	95.70 276	93.71 349	72.43 418	70.26 404	82.12 429	57.66 374	95.08 377	75.57 333	53.80 455	89.02 370

LF4IMVS		72.36 418	70.82 414	76.95 445	79.18 458	56.33 472	86.12 445	86.11 458	69.30 436	63.06 441	86.66 374	33.03 470	92.25 428	65.33 402	68.64 398	82.28 459

pmmvs6		74.65 404	71.67 411	83.60 399	79.13 459	69.94 416	93.31 365	90.88 423	61.05 464	65.83 428	84.15 413	43.43 439	94.83 386	66.62 394	60.63 439	86.02 429

MVStest1		66.93 438	63.01 442	78.69 435	78.56 460	71.43 406	85.51 450	86.81 453	49.79 480	48.57 476	84.15 413	53.46 403	83.31 476	43.14 477	37.15 487	81.34 468

DeepMVS_CX				64.06 464	78.53 461	43.26 489		68.11 493	69.94 433	38.55 483	76.14 462	18.53 484	79.34 481	43.72 475	41.62 484	69.57 479

CL-MVSNet_self_test		75.81 398	74.14 399	80.83 424	78.33 462	67.79 429	94.22 339	93.52 359	77.28 371	69.82 408	81.54 437	61.47 342	89.22 454	57.59 438	53.51 460	85.48 435

test20.03		72.36 418	71.15 413	75.98 450	77.79 463	59.16 467	92.40 380	89.35 436	74.09 400	61.50 450	84.32 411	48.09 423	85.54 473	50.63 461	62.15 437	83.24 449

UnsupCasMVSNet_eth		73.25 412	70.57 417	81.30 419	77.53 464	66.33 439	87.24 436	93.89 325	80.38 317	57.90 464	81.59 435	42.91 444	90.56 446	65.18 403	48.51 472	87.01 415

DSMNet-mixed		73.13 413	72.45 407	75.19 452	77.51 465	46.82 483	85.09 453	82.01 476	67.61 444	69.27 412	81.33 438	50.89 410	86.28 470	54.54 450	83.80 291	92.46 312

Patchmatch-RL test		76.65 394	74.01 400	84.55 385	77.37 466	64.23 446	78.49 472	82.84 474	78.48 357	64.63 434	73.40 469	76.05 165	91.70 437	76.99 312	57.84 443	97.72 128

Anonymous20240521		72.06 420	69.91 420	78.50 438	77.11 467	61.67 459	91.62 394	90.97 421	65.52 447	62.37 445	79.05 449	36.32 461	90.96 443	57.75 437	68.52 399	82.87 451

test_method		56.77 445	54.53 449	63.49 465	76.49 468	40.70 491	75.68 477	74.24 485	19.47 493	48.73 475	71.89 475	19.31 483	65.80 493	57.46 439	47.51 476	83.97 447

MIMVSNet1		69.44 431	66.65 433	77.84 439	76.48 469	62.84 454	87.42 434	88.97 439	66.96 445	57.75 466	79.72 448	32.77 471	85.83 472	46.32 470	63.42 433	84.85 439

pmmvs-eth3d		73.59 408	70.66 416	82.38 412	76.40 470	73.38 378	89.39 417	89.43 435	72.69 413	60.34 455	77.79 452	46.43 433	91.26 441	66.42 398	57.06 445	82.51 455

new_pmnet		66.18 439	63.18 441	75.18 453	76.27 471	61.74 458	83.79 458	84.66 463	56.64 474	51.57 474	71.85 476	31.29 473	87.93 461	49.98 463	62.55 435	75.86 475

KD-MVS_self_test		70.97 425	69.31 423	75.95 451	76.24 472	55.39 477	87.45 433	90.94 422	70.20 432	62.96 443	77.48 454	44.01 436	88.09 460	61.25 422	53.26 461	84.37 444

ttmdpeth		69.58 428	66.92 432	77.54 442	75.95 473	62.40 455	88.09 427	84.32 466	62.87 454	65.70 430	86.25 385	36.53 460	88.53 458	55.65 448	46.96 477	81.70 465

mvs5depth		71.40 423	68.36 427	80.54 426	75.31 474	65.56 442	79.94 465	85.14 461	69.11 437	71.75 389	81.59 435	41.02 453	93.94 407	60.90 424	50.46 467	82.10 460

FE-MVSNET2		73.72 406	70.80 415	82.46 411	74.97 475	73.81 376	91.88 388	91.73 404	76.70 380	59.74 458	77.41 455	42.26 446	90.52 447	64.75 405	57.79 444	83.06 450

UnsupCasMVSNet_bld		68.60 436	64.50 440	80.92 423	74.63 476	67.80 428	83.97 457	92.94 382	65.12 448	54.63 471	68.23 479	35.97 463	92.17 431	60.13 426	44.83 479	82.78 453

FE-MVSNET		69.26 433	66.03 435	78.93 434	73.82 477	68.33 427	89.65 410	84.06 468	70.21 431	57.79 465	76.94 460	41.48 450	86.98 469	45.85 472	54.51 452	81.48 467

PM-MVS		69.32 432	66.93 431	76.49 447	73.60 478	55.84 474	85.91 446	79.32 481	74.72 395	61.09 452	78.18 451	21.76 482	91.10 442	70.86 373	56.90 446	82.51 455

new-patchmatchnet		68.85 435	65.93 436	77.61 441	73.57 479	63.94 449	90.11 408	88.73 443	71.62 425	55.08 470	73.60 468	40.84 454	87.22 468	51.35 459	48.49 473	81.67 466

WB-MVS		57.26 444	56.22 447	60.39 469	69.29 480	35.91 496	86.39 444	70.06 489	59.84 469	46.46 479	72.71 471	51.18 409	78.11 483	15.19 493	34.89 488	67.14 482

test_fmvs3		69.56 429	69.19 424	70.67 456	69.01 481	47.05 482	90.87 401	86.81 453	71.31 427	66.79 423	77.15 457	16.40 486	83.17 478	81.84 257	62.51 436	81.79 464

SSC-MVS		56.01 447	54.96 448	59.17 470	68.42 482	34.13 497	84.98 454	69.23 490	58.08 473	45.36 480	71.67 477	50.30 417	77.46 484	14.28 494	32.33 489	65.91 483

ambc				76.02 449	68.11 483	51.43 479	64.97 488	89.59 432		60.49 454	74.49 466	17.17 485	92.46 423	61.50 420	52.85 463	84.17 446

APD_test1		56.56 446	53.58 450	65.50 460	67.93 484	46.51 485	77.24 476	72.95 486	38.09 484	42.75 482	75.17 463	13.38 489	82.78 479	40.19 480	54.53 451	67.23 481

pmmvs3		65.75 440	62.18 443	76.45 448	67.12 485	64.54 444	88.68 422	85.05 462	54.77 476	57.54 467	73.79 467	29.40 477	86.21 471	55.49 449	47.77 475	78.62 472

TDRefinement		69.20 434	65.78 437	79.48 430	66.04 486	62.21 456	88.21 425	86.12 457	62.92 453	61.03 453	85.61 393	33.23 469	94.16 403	55.82 447	53.02 462	82.08 461

usedtu_dtu_shiyan2		64.65 441	60.40 445	77.38 443	64.24 487	57.84 470	89.16 418	87.60 449	52.95 477	53.43 473	71.31 478	23.41 480	88.27 459	51.95 456	49.58 469	86.03 428

mvsany_test3		67.19 437	65.34 438	72.72 454	63.08 488	48.57 481	83.12 460	78.09 482	72.07 421	61.21 451	77.11 458	22.94 481	87.78 464	78.59 291	51.88 465	81.80 463

test_f		64.01 442	62.13 444	69.65 457	63.00 489	45.30 488	83.66 459	80.68 478	61.30 461	55.70 469	72.62 472	14.23 488	84.64 474	69.84 378	58.11 442	79.00 471

test_vis3_rt		54.10 449	51.04 452	63.27 466	58.16 490	46.08 487	84.17 456	49.32 501	56.48 475	36.56 485	49.48 488	8.03 496	91.91 434	67.29 389	49.87 468	51.82 487

FPMVS		55.09 448	52.93 451	61.57 467	55.98 491	40.51 492	83.11 461	83.41 473	37.61 485	34.95 486	71.95 474	14.40 487	76.95 485	29.81 485	65.16 426	67.25 480

PMMVS2		50.90 452	46.31 455	64.67 462	55.53 492	46.67 484	77.30 475	71.02 488	40.89 483	34.16 487	59.32 482	9.83 494	76.14 488	40.09 481	28.63 490	71.21 477

wuyk23d		14.10 463	13.89 466	14.72 479	55.23 493	22.91 503	33.83 493	3.56 503	4.94 496	4.11 497	2.28 499	2.06 501	19.66 498	10.23 497	8.74 496	1.59 496

E-PMN		32.70 460	32.39 462	33.65 477	53.35 494	25.70 501	74.07 480	53.33 499	21.08 491	17.17 495	33.63 493	11.85 492	54.84 495	12.98 495	14.04 492	20.42 492

testf1		45.70 454	42.41 456	55.58 471	53.29 495	40.02 493	68.96 486	62.67 495	27.45 488	29.85 488	61.58 480	5.98 497	73.83 490	28.49 488	43.46 482	52.90 485

APD_test2		45.70 454	42.41 456	55.58 471	53.29 495	40.02 493	68.96 486	62.67 495	27.45 488	29.85 488	61.58 480	5.98 497	73.83 490	28.49 488	43.46 482	52.90 485

EMVS		31.70 461	31.45 463	32.48 478	50.72 497	23.95 502	74.78 479	52.30 500	20.36 492	16.08 496	31.48 494	12.80 490	53.60 496	11.39 496	13.10 495	19.88 493

LCM-MVSNet		52.52 450	48.24 453	65.35 461	47.63 498	41.45 490	72.55 482	83.62 472	31.75 486	37.66 484	57.92 484	9.19 495	76.76 486	49.26 465	44.60 480	77.84 473

MVE	35.65 22	33.85 459	29.49 464	46.92 475	41.86 499	36.28 495	50.45 491	56.52 498	18.75 494	18.28 493	37.84 490	2.41 500	58.41 494	18.71 491	20.62 491	46.06 489
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		46.22 453	41.28 460	61.04 468	39.91 500	46.25 486	70.59 485	76.18 484	58.87 471	23.09 492	48.00 489	12.58 491	66.54 492	28.65 487	13.62 493	70.35 478

PMVS	34.80 23	39.19 458	35.53 461	50.18 474	29.72 501	30.30 499	59.60 490	66.20 494	26.06 490	17.91 494	49.53 487	3.12 499	74.09 489	18.19 492	49.40 470	46.14 488
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		41.54 457	41.93 459	40.38 476	20.10 502	26.84 500	61.93 489	59.09 497	14.81 495	28.51 490	80.58 441	35.53 464	48.33 497	63.70 412	13.11 494	45.96 490

testmvs		9.92 464	12.94 467	0.84 481	0.65 503	0.29 506	93.78 350	0.39 504	0.42 497	2.85 498	15.84 497	0.17 503	0.30 500	2.18 498	0.21 497	1.91 495

test123		9.07 465	11.73 468	1.11 480	0.50 504	0.77 505	89.44 416	0.20 505	0.34 498	2.15 499	10.72 498	0.34 502	0.32 499	1.79 499	0.08 498	2.23 494

mmdepth		0.00 468	0.00 471	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	0.00 500	0.00 504	0.00 501	0.00 500	0.00 499	0.00 497

monomultidepth		0.00 468	0.00 471	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	0.00 500	0.00 504	0.00 501	0.00 500	0.00 499	0.00 497

test_blank		0.00 468	0.00 471	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	0.00 500	0.00 504	0.00 501	0.00 500	0.00 499	0.00 497

eth-test2					0.00 505

eth-test					0.00 505

uanet_test		0.00 468	0.00 471	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	0.00 500	0.00 504	0.00 501	0.00 500	0.00 499	0.00 497

DCPMVS		0.00 468	0.00 471	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	0.00 500	0.00 504	0.00 501	0.00 500	0.00 499	0.00 497

cdsmvs_eth3d_5k		21.43 462	28.57 465	0.00 482	0.00 505	0.00 507	0.00 494	95.93 177	0.00 500	0.00 501	97.66 93	63.57 320	0.00 501	0.00 500	0.00 499	0.00 497

pcd_1.5k_mvsjas		5.92 467	7.89 470	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	0.00 500	71.04 252	0.00 501	0.00 500	0.00 499	0.00 497

sosnet-low-res		0.00 468	0.00 471	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	0.00 500	0.00 504	0.00 501	0.00 500	0.00 499	0.00 497

sosnet		0.00 468	0.00 471	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	0.00 500	0.00 504	0.00 501	0.00 500	0.00 499	0.00 497

uncertanet		0.00 468	0.00 471	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	0.00 500	0.00 504	0.00 501	0.00 500	0.00 499	0.00 497

Regformer		0.00 468	0.00 471	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	0.00 500	0.00 504	0.00 501	0.00 500	0.00 499	0.00 497

ab-mvs-re		8.11 466	10.81 469	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	97.30 116	0.00 504	0.00 501	0.00 500	0.00 499	0.00 497

uanet		0.00 468	0.00 471	0.00 482	0.00 505	0.00 507	0.00 494	0.00 506	0.00 500	0.00 501	0.00 500	0.00 504	0.00 501	0.00 500	0.00 499	0.00 497

TestfortrainingZip							98.35 56

WAC-MVS						67.18 432								49.00 466

PC_three_1452									91.12 50	98.33 4	98.42 43	92.51 2	99.81 27	98.96 6	99.37 1	99.70 3

test_241102_TWO								96.78 65	88.72 84	97.70 13	98.91 2	87.86 24	99.82 23	98.15 22	99.00 15	99.47 9

test_0728_THIRD									88.38 92	96.69 31	98.76 17	89.64 14	99.76 44	97.47 40	98.84 23	99.38 14

GSMVS																97.54 147

sam_mvs1												77.59 127				97.54 147

sam_mvs												75.35 186

MTGPA								96.33 138

test_post1							85.88 447				30.24 495	73.77 211	95.07 378	73.89 350

test_post											33.80 492	76.17 161	95.97 317

patchmatchnet-post											77.09 459	77.78 125	95.39 351

MTMP							97.53 117	68.16 492

test9_res														96.00 57	99.03 13	98.31 75

agg_prior2														94.30 81	99.00 15	98.57 59

test_prior4						82.34 144	97.75 99

test_prior2							98.37 55		86.08 163	94.57 68	98.02 72	83.14 60		95.05 72	98.79 27

旧先验2							96.97 170		74.06 401	96.10 42			97.76 196	88.38 190

新几何2							96.42 218

无先验							96.87 179	96.78 65	77.39 368				99.52 85	79.95 276		98.43 68

原ACMM2							96.84 180

testdata2													99.48 89	76.45 321

segment_acmp												82.69 66

testdata1							95.57 284		87.44 122

plane_prior5								94.69 256					97.30 247	87.08 204	82.82 302	90.96 321

plane_prior4											94.15 244

plane_prior3						77.75 319			90.17 67	81.33 281

plane_prior2							97.18 145		89.89 70

plane_prior						77.96 306	97.52 120		90.36 65						82.96 300

n2								0.00 506

nn								0.00 506

door-mid								79.75 480

test11								96.50 114

door								80.13 479

HQP5-MVS						78.48 285

BP-MVS														87.67 200

HQP4-MVS										82.30 268			97.32 245			91.13 319

HQP3-MVS								94.80 247							83.01 298

HQP2-MVS												65.40 305

MDTV_nov1_ep13_2view						81.74 169	86.80 439		80.65 308	85.65 216		74.26 204		76.52 320		96.98 200

ACMMP++_ref															78.45 335

ACMMP++															79.05 327

Test By Simon												71.65 244

High-resolution multi-view benchmark