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.

LCM-MVSNet		99.43 1	99.49 1	99.24 1	99.95 1	98.13 1	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 1	97.58 1	99.94 1	99.85 2

LTVRE_ROB	93.87 1	97.93 2	98.16 2	97.26 29	98.81 32	93.86 34	99.07 2	98.98 8	97.01 17	98.92 5	98.78 19	95.22 46	98.61 194	96.85 11	99.77 9	99.31 33
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
TDRefinement		97.68 3	97.60 8	97.93 2	99.02 13	95.95 8	98.61 3	98.81 10	97.41 13	97.28 70	98.46 35	94.62 75	98.84 148	94.64 53	99.53 39	98.99 66

DVP-MVS++		95.93 63	96.34 45	94.70 127	96.54 218	86.66 169	98.45 4	98.22 57	93.26 86	97.54 49	97.36 120	93.12 118	99.38 63	93.88 70	98.68 190	98.04 204

FOURS1					99.21 3	94.68 15	98.45 4	98.81 10	97.73 9	98.27 23

UA-Net		97.35 4	97.24 15	97.69 5	98.22 83	93.87 33	98.42 6	98.19 60	96.95 18	95.46 182	99.23 9	93.45 105	99.57 14	95.34 45	99.89 2	99.63 12

OurMVSNet-221017-0		96.80 19	96.75 25	96.96 38	99.03 12	91.85 60	97.98 7	98.01 100	94.15 64	98.93 4	99.07 10	88.07 243	99.57 14	95.86 27	99.69 17	99.46 22

UniMVSNet_ETH3D		97.13 10	97.72 3	95.35 94	99.51 2	87.38 146	97.70 8	97.54 162	98.16 5	98.94 3	99.33 6	97.84 4	99.08 110	90.73 181	99.73 14	99.59 15

tt0805		95.42 89	95.93 70	93.86 171	98.75 36	88.47 124	97.68 9	94.29 338	96.48 26	95.38 185	93.63 357	94.89 64	97.94 300	95.38 43	96.92 340	95.17 394

HPM-MVS		96.81 18	96.62 30	97.36 26	98.89 23	93.53 41	97.51 10	98.44 26	92.35 103	95.95 148	96.41 211	96.71 11	99.42 37	93.99 69	99.36 66	99.13 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPP-MVSNet		93.91 174	93.68 191	94.59 137	98.08 91	85.55 203	97.44 11	94.03 344	94.22 63	94.94 220	96.19 234	82.07 326	99.57 14	87.28 292	98.89 146	98.65 130

mvs5depth		95.28 97	95.82 80	93.66 181	96.42 231	83.08 250	97.35 12	99.28 2	96.44 28	96.20 135	99.65 2	84.10 302	98.01 292	94.06 66	98.93 141	99.87 1

LS3D		96.11 56	95.83 78	96.95 39	94.75 346	94.20 22	97.34 13	97.98 103	97.31 14	95.32 190	96.77 180	93.08 120	99.20 94	91.79 148	98.16 254	97.44 278

HPM-MVS_fast		97.01 11	96.89 21	97.39 24	99.12 8	93.92 31	97.16 14	98.17 66	93.11 88	96.48 112	97.36 120	96.92 6	99.34 70	94.31 61	99.38 63	98.92 87

MVSFormer		92.18 252	92.23 245	92.04 273	94.74 349	80.06 308	97.15 15	97.37 177	88.98 215	88.83 405	92.79 379	77.02 377	99.60 9	96.41 18	96.75 347	96.46 338

test_djsdf		96.62 30	96.49 35	97.01 35	98.55 53	91.77 62	97.15 15	97.37 177	88.98 215	98.26 26	98.86 15	93.35 110	99.60 9	96.41 18	99.45 48	99.66 9

IS-MVSNet		94.49 140	94.35 161	94.92 115	98.25 82	86.46 174	97.13 17	94.31 337	96.24 34	96.28 129	96.36 219	82.88 314	99.35 67	88.19 270	99.52 41	98.96 77

Anonymous20231211		96.60 32	97.13 19	95.00 111	97.46 143	86.35 179	97.11 18	98.24 53	97.58 11	98.72 11	98.97 12	93.15 117	99.15 98	93.18 103	99.74 13	99.50 19

anonymousdsp		96.74 24	96.42 38	97.68 7	98.00 102	94.03 28	96.97 19	97.61 153	87.68 260	98.45 21	98.77 20	94.20 88	99.50 23	96.70 13	99.40 61	99.53 17

ACMMP		96.61 31	96.34 45	97.43 21	98.61 45	93.88 32	96.95 20	98.18 62	92.26 106	96.33 122	96.84 177	95.10 53	99.40 51	93.47 88	99.33 73	99.02 63
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
lecture		97.32 6	97.64 6	96.33 54	99.01 15	90.77 79	96.90 21	98.60 16	96.30 33	97.74 40	98.00 55	96.87 8	99.39 54	95.95 24	99.42 54	98.84 98

APDe-MVS		96.46 39	96.64 29	95.93 66	97.68 128	89.38 101	96.90 21	98.41 29	92.52 97	97.43 57	97.92 67	95.11 51	99.50 23	94.45 57	99.30 80	98.92 87
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
tt0320		96.97 13	97.64 6	94.96 114	98.89 23	86.86 162	96.85 23	98.45 25	98.29 3	98.88 6	99.45 3	96.48 13	98.54 212	91.73 151	99.72 15	99.47 21

EGC-MVSNET		80.97 440	75.73 458	96.67 45	98.85 28	94.55 18	96.83 24	96.60 250	2.44 501	5.32 502	98.25 42	92.24 146	98.02 291	91.85 146	99.21 98	97.45 276

v7n		96.82 16	97.31 14	95.33 96	98.54 55	86.81 163	96.83 24	98.07 84	96.59 25	98.46 20	98.43 37	92.91 128	99.52 19	96.25 21	99.76 10	99.65 11

CP-MVS		96.44 42	96.08 60	97.54 14	98.29 77	94.62 17	96.80 26	98.08 81	92.67 95	95.08 214	96.39 216	94.77 71	99.42 37	93.17 104	99.44 51	98.58 144

COLMAP_ROB	91.06 5	96.75 23	96.62 30	97.13 31	98.38 70	94.31 20	96.79 27	98.32 38	96.69 21	96.86 92	97.56 95	95.48 31	98.77 166	90.11 210	99.44 51	98.31 175
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
WR-MVS_H		96.60 32	97.05 20	95.24 102	99.02 13	86.44 175	96.78 28	98.08 81	97.42 12	98.48 19	97.86 73	91.76 159	99.63 7	94.23 63	99.84 3	99.66 9

FE-MVS		89.06 333	88.29 342	91.36 305	94.78 344	79.57 330	96.77 29	90.99 406	84.87 330	92.96 305	96.29 223	60.69 462	98.80 158	80.18 391	97.11 326	95.71 378

CS-MVS		95.77 71	95.58 90	96.37 53	96.84 186	91.72 64	96.73 30	99.06 7	94.23 62	92.48 321	94.79 310	93.56 100	99.49 29	93.47 88	99.05 118	97.89 232

sc_t1		97.21 9	97.71 4	95.71 78	99.06 10	88.89 111	96.72 31	97.79 136	98.34 2	98.97 2	99.40 5	96.81 9	98.79 159	92.58 126	99.72 15	99.45 23

tt0320-xc		97.00 12	97.67 5	94.98 112	98.89 23	86.94 160	96.72 31	98.46 24	98.28 4	98.86 7	99.43 4	96.80 10	98.51 219	91.79 148	99.76 10	99.50 19

pmmvs6		96.80 19	97.36 13	95.15 108	99.12 8	87.82 140	96.68 33	97.86 123	96.10 36	98.14 30	99.28 8	97.94 3	98.21 259	91.38 164	99.69 17	99.42 24

balanced_ft_v1		92.65 231	93.17 211	91.10 321	94.47 359	77.32 381	96.67 34	96.70 241	88.23 242	93.70 266	97.16 144	83.33 308	99.41 43	90.51 187	97.76 290	96.57 326

mvsmamba		90.24 302	89.43 316	92.64 237	95.52 315	82.36 266	96.64 35	92.29 386	81.77 375	92.14 338	96.28 225	70.59 414	99.10 109	84.44 340	95.22 396	96.47 337

3Dnovator	92.54 3	94.80 119	94.90 126	94.47 145	95.47 319	87.06 154	96.63 36	97.28 191	91.82 129	94.34 242	97.41 112	90.60 199	98.65 189	92.47 129	98.11 259	97.70 256

PS-CasMVS		96.69 27	97.43 9	94.49 144	99.13 6	84.09 227	96.61 37	97.97 105	97.91 8	98.64 16	98.13 45	95.24 44	99.65 4	93.39 95	99.84 3	99.72 4

mvs_tets		96.83 15	96.71 26	97.17 30	98.83 29	92.51 51	96.58 38	97.61 153	87.57 262	98.80 10	98.90 14	96.50 12	99.59 13	96.15 22	99.47 44	99.40 27

PEN-MVS		96.69 27	97.39 12	94.61 133	99.16 4	84.50 216	96.54 39	98.05 90	98.06 7	98.64 16	98.25 42	95.01 58	99.65 4	92.95 112	99.83 5	99.68 7

MVSMamba_PlusPlus		94.82 118	95.89 73	91.62 290	97.82 114	78.88 350	96.52 40	97.60 155	97.14 16	94.23 243	98.48 34	87.01 266	99.71 2	95.43 40	98.80 165	96.28 349

DTE-MVSNet		96.74 24	97.43 9	94.67 130	99.13 6	84.68 215	96.51 41	97.94 113	98.14 6	98.67 15	98.32 39	95.04 55	99.69 3	93.27 100	99.82 7	99.62 13

XVS		96.49 37	96.18 53	97.44 19	98.56 49	93.99 29	96.50 42	97.95 110	94.58 55	94.38 240	96.49 204	94.56 78	99.39 54	93.57 80	99.05 118	98.93 83

X-MVStestdata		90.70 283	88.45 336	97.44 19	98.56 49	93.99 29	96.50 42	97.95 110	94.58 55	94.38 240	26.89 499	94.56 78	99.39 54	93.57 80	99.05 118	98.93 83

mmtdpeth		95.82 69	96.02 65	95.23 103	96.91 180	88.62 117	96.49 44	99.26 3	95.07 49	93.41 276	99.29 7	90.25 205	97.27 359	94.49 55	99.01 126	99.80 3

EC-MVSNet		95.44 85	95.62 88	94.89 118	96.93 179	87.69 142	96.48 45	99.14 6	93.93 71	92.77 312	94.52 323	93.95 95	99.49 29	93.62 79	99.22 97	97.51 272

mPP-MVS		96.46 39	96.05 62	97.69 5	98.62 43	94.65 16	96.45 46	97.74 140	92.59 96	95.47 180	96.68 191	94.50 81	99.42 37	93.10 106	99.26 90	98.99 66

QAPM		92.88 218	92.77 221	93.22 208	95.82 292	83.31 239	96.45 46	97.35 183	83.91 340	93.75 262	96.77 180	89.25 224	98.88 141	84.56 338	97.02 333	97.49 273

jajsoiax		96.59 34	96.42 38	97.12 32	98.76 35	92.49 52	96.44 48	97.42 174	86.96 277	98.71 13	98.72 22	95.36 38	99.56 17	95.92 25	99.45 48	99.32 32

Gipuma		95.31 96	95.80 81	93.81 174	97.99 105	90.91 73	96.42 49	97.95 110	96.69 21	91.78 345	98.85 17	91.77 157	95.49 426	91.72 152	99.08 114	95.02 403
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MSP-MVS		95.34 92	94.63 146	97.48 17	98.67 40	94.05 26	96.41 50	98.18 62	91.26 154	95.12 210	95.15 291	86.60 276	99.50 23	93.43 94	96.81 344	98.89 91
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
SR-MVS-dyc-post		96.84 14	96.60 33	97.56 13	98.07 92	95.27 9	96.37 51	98.12 74	95.66 42	97.00 85	97.03 159	94.85 67	99.42 37	93.49 85	98.84 153	98.00 209

RE-MVS-def			96.66 27		98.07 92	95.27 9	96.37 51	98.12 74	95.66 42	97.00 85	97.03 159	95.40 35		93.49 85	98.84 153	98.00 209

TSAR-MVS + MP.		94.96 111	94.75 135	95.57 85	98.86 27	88.69 114	96.37 51	96.81 232	85.23 319	94.75 228	97.12 150	91.85 155	99.40 51	93.45 90	98.33 232	98.62 140
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SPE-MVS-test		95.32 93	95.10 121	95.96 62	96.86 184	90.75 80	96.33 54	99.20 4	93.99 68	91.03 360	93.73 355	93.52 102	99.55 18	91.81 147	99.45 48	97.58 266

ACMH	88.36 12	96.59 34	97.43 9	94.07 160	98.56 49	85.33 207	96.33 54	98.30 41	94.66 54	98.72 11	98.30 40	97.51 5	98.00 294	94.87 50	99.59 29	98.86 94
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MED-MVS test				95.52 87	98.69 37	88.21 130	96.32 56	98.58 18	88.79 220	97.38 64	96.22 231		99.39 54	92.89 114	99.10 110	98.96 77

MED-MVS		96.37 48	96.62 30	95.63 81	98.69 37	88.21 130	96.32 56	98.58 18	94.10 65	97.38 64	97.37 115	95.11 51	99.39 54	92.89 114	99.10 110	99.30 34

TestfortrainingZip a		96.50 36	96.80 23	95.62 82	98.69 37	88.28 127	96.32 56	98.06 88	94.10 65	97.65 42	97.37 115	94.54 80	99.28 84	95.41 42	99.04 123	99.30 34

TestfortrainingZip				93.68 180	95.25 327	86.20 184	96.32 56	96.38 264	92.81 91	92.13 339	93.87 353	87.28 260	98.61 194		95.07 400	96.23 353

region2R		96.41 44	96.09 58	97.38 25	98.62 43	93.81 38	96.32 56	97.96 107	92.26 106	95.28 194	96.57 200	95.02 57	99.41 43	93.63 78	99.11 109	98.94 81

testf1		96.77 21	96.49 35	97.60 9	99.01 15	96.70 3	96.31 61	98.33 36	94.96 50	97.30 67	97.93 62	96.05 20	97.90 301	89.32 229	99.23 94	98.19 189

APD_test2		96.77 21	96.49 35	97.60 9	99.01 15	96.70 3	96.31 61	98.33 36	94.96 50	97.30 67	97.93 62	96.05 20	97.90 301	89.32 229	99.23 94	98.19 189

APD-MVS_3200maxsize		96.82 16	96.65 28	97.32 28	97.95 106	93.82 36	96.31 61	98.25 45	95.51 44	96.99 87	97.05 158	95.63 27	99.39 54	93.31 97	98.88 148	98.75 114

CP-MVSNet		96.19 54	96.80 23	94.38 149	98.99 19	83.82 230	96.31 61	97.53 165	97.60 10	98.34 22	97.52 100	91.98 153	99.63 7	93.08 108	99.81 8	99.70 5

HFP-MVS		96.39 46	96.17 55	97.04 34	98.51 58	93.37 42	96.30 65	97.98 103	92.35 103	95.63 172	96.47 205	95.37 36	99.27 87	93.78 74	99.14 107	98.48 154

ACMMPR		96.46 39	96.14 56	97.41 23	98.60 46	93.82 36	96.30 65	97.96 107	92.35 103	95.57 175	96.61 197	94.93 63	99.41 43	93.78 74	99.15 106	99.00 64

3Dnovator+	92.74 2	95.86 68	95.77 82	96.13 57	96.81 189	90.79 78	96.30 65	97.82 131	96.13 35	94.74 229	97.23 137	91.33 173	99.16 97	93.25 101	98.30 238	98.46 155

MIMVSNet1		95.52 82	95.45 94	95.72 77	99.14 5	89.02 108	96.23 68	96.87 227	93.73 75	97.87 35	98.49 33	90.73 196	99.05 117	86.43 310	99.60 27	99.10 57

BridgeMVS		93.45 191	94.17 169	91.28 311	95.81 294	78.40 358	96.20 69	97.48 171	88.56 232	95.29 193	97.20 142	85.56 291	99.21 91	92.52 128	98.91 144	96.24 352

test2506		85.42 399	84.57 402	87.96 405	97.81 115	66.53 469	96.14 70	56.35 502	89.04 213	93.55 271	98.10 47	42.88 495	98.68 184	88.09 276	99.18 102	98.67 128

SR-MVS		96.70 26	96.42 38	97.54 14	98.05 94	94.69 14	96.13 71	98.07 84	95.17 48	96.82 96	96.73 187	95.09 54	99.43 36	92.99 111	98.71 186	98.50 151

MP-MVS		96.14 55	95.68 85	97.51 16	98.81 32	94.06 24	96.10 72	97.78 138	92.73 92	93.48 274	96.72 188	94.23 87	99.42 37	91.99 141	99.29 83	99.05 61
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		96.42 43	96.20 52	97.07 33	98.80 34	92.79 49	96.08 73	98.16 69	91.74 134	95.34 189	96.36 219	95.68 25	99.44 33	94.41 59	99.28 88	98.97 73

FA-MVS(test-final)		91.81 259	91.85 258	91.68 288	94.95 337	79.99 312	96.00 74	93.44 363	87.80 255	94.02 254	97.29 129	77.60 366	98.45 230	88.04 278	97.49 309	96.61 325

GBi-Net		93.21 205	92.96 215	93.97 163	95.40 321	84.29 220	95.99 75	96.56 254	88.63 224	95.10 211	98.53 30	81.31 334	98.98 126	86.74 298	98.38 225	98.65 130

test1		93.21 205	92.96 215	93.97 163	95.40 321	84.29 220	95.99 75	96.56 254	88.63 224	95.10 211	98.53 30	81.31 334	98.98 126	86.74 298	98.38 225	98.65 130

FMVSNet1		94.84 116	95.13 117	93.97 163	97.60 133	84.29 220	95.99 75	96.56 254	92.38 100	97.03 84	98.53 30	90.12 210	98.98 126	88.78 253	99.16 105	98.65 130

RPSCF		95.58 80	94.89 128	97.62 8	97.58 135	96.30 7	95.97 78	97.53 165	92.42 99	93.41 276	97.78 75	91.21 178	97.77 320	91.06 173	97.06 331	98.80 103

SixPastTwentyTwo		94.91 112	95.21 110	93.98 162	98.52 57	83.19 245	95.93 79	94.84 322	94.86 53	98.49 18	98.74 21	81.45 332	99.60 9	94.69 52	99.39 62	99.15 48

ambc				92.98 215	96.88 182	83.01 252	95.92 80	96.38 264		96.41 117	97.48 106	88.26 239	97.80 315	89.96 216	98.93 141	98.12 198

FC-MVSNet-test		95.32 93	95.88 74	93.62 183	98.49 65	81.77 274	95.90 81	98.32 38	93.93 71	97.53 51	97.56 95	88.48 234	99.40 51	92.91 113	99.83 5	99.68 7

reproduce_model		97.35 4	97.24 15	97.70 4	98.44 67	95.08 11	95.88 82	98.50 21	96.62 24	98.27 23	97.93 62	94.57 77	99.50 23	95.57 35	99.35 67	98.52 149

MTAPA		96.65 29	96.38 42	97.47 18	98.95 21	94.05 26	95.88 82	97.62 151	94.46 59	96.29 127	96.94 165	93.56 100	99.37 65	94.29 62	99.42 54	98.99 66

CPTT-MVS		94.74 120	94.12 171	96.60 46	98.15 87	93.01 45	95.84 84	97.66 148	89.21 211	93.28 284	95.46 279	88.89 228	98.98 126	89.80 218	98.82 159	97.80 246

ab-mvs		92.40 241	92.62 231	91.74 284	97.02 172	81.65 278	95.84 84	95.50 302	86.95 278	92.95 306	97.56 95	90.70 197	97.50 342	79.63 399	97.43 313	96.06 361

nrg030		96.32 49	96.55 34	95.62 82	97.83 113	88.55 122	95.77 86	98.29 44	92.68 93	98.03 34	97.91 70	95.13 49	98.95 134	93.85 72	99.49 43	99.36 30

ECVR-MVS		90.12 306	90.16 301	90.00 365	97.81 115	72.68 439	95.76 87	78.54 491	89.04 213	95.36 188	98.10 47	70.51 415	98.64 190	87.10 294	99.18 102	98.67 128

SteuartSystems-ACMMP		96.40 45	96.30 47	96.71 43	98.63 42	91.96 58	95.70 88	98.01 100	93.34 85	96.64 106	96.57 200	94.99 59	99.36 66	93.48 87	99.34 71	98.82 99
Skip Steuart: Steuart Systems R&D Blog.
OpenMVS	89.45 8	92.27 249	92.13 250	92.68 236	94.53 358	84.10 226	95.70 88	97.03 209	82.44 367	91.14 359	96.42 210	88.47 235	98.38 237	85.95 315	97.47 311	95.55 387

GST-MVS		96.24 52	95.99 66	97.00 36	98.65 41	92.71 50	95.69 90	98.01 100	92.08 114	95.74 165	96.28 225	95.22 46	99.42 37	93.17 104	99.06 115	98.88 93

ACMH+	88.43 11	96.48 38	96.82 22	95.47 90	98.54 55	89.06 107	95.65 91	98.61 15	96.10 36	98.16 29	97.52 100	96.90 7	98.62 193	90.30 199	99.60 27	98.72 119

APD_test1		95.91 64	95.42 98	97.36 26	98.82 30	96.62 6	95.64 92	97.64 149	93.38 84	95.89 153	97.23 137	93.35 110	97.66 331	88.20 269	98.66 194	97.79 247

sasdasda		94.59 128	94.69 139	94.30 150	95.60 310	87.03 155	95.59 93	98.24 53	91.56 141	95.21 202	92.04 399	94.95 60	98.66 186	91.45 161	97.57 305	97.20 294

test1111		90.39 295	90.61 292	89.74 369	98.04 97	71.50 446	95.59 93	79.72 488	89.41 204	95.94 149	98.14 44	70.79 413	98.81 155	88.52 263	99.32 77	98.90 90

canonicalmvs		94.59 128	94.69 139	94.30 150	95.60 310	87.03 155	95.59 93	98.24 53	91.56 141	95.21 202	92.04 399	94.95 60	98.66 186	91.45 161	97.57 305	97.20 294

SF-MVS		95.88 67	95.88 74	95.87 72	98.12 88	89.65 93	95.58 96	98.56 20	91.84 126	96.36 121	96.68 191	94.37 85	99.32 76	92.41 131	99.05 118	98.64 136

reproduce-ours		97.28 7	97.19 17	97.57 11	98.37 72	94.84 12	95.57 97	98.40 30	96.36 31	98.18 27	97.78 75	95.47 32	99.50 23	95.26 46	99.33 73	98.36 168

our_new_method		97.28 7	97.19 17	97.57 11	98.37 72	94.84 12	95.57 97	98.40 30	96.36 31	98.18 27	97.78 75	95.47 32	99.50 23	95.26 46	99.33 73	98.36 168

PS-MVSNAJss		96.01 59	96.04 63	95.89 71	98.82 30	88.51 123	95.57 97	97.88 120	88.72 222	98.81 9	98.86 15	90.77 192	99.60 9	95.43 40	99.53 39	99.57 16

PMVS	87.21 14	94.97 110	95.33 105	93.91 168	98.97 20	97.16 2	95.54 100	95.85 287	96.47 27	93.40 279	97.46 107	95.31 41	95.47 427	86.18 314	98.78 169	89.11 477
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
VDDNet		94.03 168	94.27 166	93.31 202	98.87 26	82.36 266	95.51 101	91.78 399	97.19 15	96.32 124	98.60 27	84.24 300	98.75 167	87.09 295	98.83 158	98.81 101

pm-mvs1		95.43 86	95.94 68	93.93 167	98.38 70	85.08 211	95.46 102	97.12 204	91.84 126	97.28 70	98.46 35	95.30 42	97.71 328	90.17 208	99.42 54	98.99 66

RRT-MVS		92.28 246	93.01 214	90.07 361	94.06 371	73.01 435	95.36 103	97.88 120	92.24 108	95.16 207	97.52 100	78.51 360	99.29 80	90.55 186	95.83 373	97.92 227

Vis-MVSNet		95.50 83	95.48 93	95.56 86	98.11 89	89.40 100	95.35 104	98.22 57	92.36 102	94.11 247	98.07 49	92.02 151	99.44 33	93.38 96	97.67 299	97.85 239
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test0726					98.51 58	86.69 167	95.34 105	98.18 62	91.85 123	97.63 44	97.37 115	95.58 28

FIs		94.90 114	95.35 102	93.55 187	98.28 78	81.76 275	95.33 106	98.14 71	93.05 90	97.07 80	97.18 143	87.65 253	99.29 80	91.72 152	99.69 17	99.61 14

PGM-MVS		96.32 49	95.94 68	97.43 21	98.59 48	93.84 35	95.33 106	98.30 41	91.40 151	95.76 160	96.87 173	95.26 43	99.45 32	92.77 117	99.21 98	99.00 64

LPG-MVS_test		96.38 47	96.23 50	96.84 41	98.36 75	92.13 55	95.33 106	98.25 45	91.78 130	97.07 80	97.22 139	96.38 16	99.28 84	92.07 138	99.59 29	99.11 54

MonoMVSNet		88.46 350	89.28 317	85.98 437	90.52 453	70.07 455	95.31 109	94.81 325	88.38 236	93.47 275	96.13 240	73.21 398	95.07 436	82.61 361	89.12 472	92.81 454

Elysia		96.00 60	96.36 43	94.91 116	98.01 100	85.96 191	95.29 110	97.90 115	95.31 45	98.14 30	97.28 131	88.82 229	99.51 20	97.08 7	99.38 63	99.26 37

StellarMVS		96.00 60	96.36 43	94.91 116	98.01 100	85.96 191	95.29 110	97.90 115	95.31 45	98.14 30	97.28 131	88.82 229	99.51 20	97.08 7	99.38 63	99.26 37

AllTest		94.88 115	94.51 153	96.00 59	98.02 98	92.17 53	95.26 112	98.43 27	90.48 178	95.04 216	96.74 185	92.54 137	97.86 309	85.11 330	98.98 129	97.98 213

MGCFI-Net		94.44 142	94.67 144	93.75 176	95.56 313	85.47 204	95.25 113	98.24 53	91.53 143	95.04 216	92.21 394	94.94 62	98.54 212	91.56 159	97.66 300	97.24 292

SED-MVS		96.00 60	96.41 41	94.76 124	98.51 58	86.97 157	95.21 114	98.10 78	91.95 116	97.63 44	97.25 134	96.48 13	99.35 67	93.29 98	99.29 83	97.95 219

OPU-MVS				95.15 108	96.84 186	89.43 98	95.21 114				95.66 270	93.12 118	98.06 284	86.28 313	98.61 197	97.95 219

DVP-MVS		95.82 69	96.18 53	94.72 126	98.51 58	86.69 167	95.20 116	97.00 211	91.85 123	97.40 62	97.35 123	95.58 28	99.34 70	93.44 91	99.31 78	98.13 197
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				94.88 119	98.55 53	86.72 166	95.20 116	98.22 57					99.38 63	93.44 91	99.31 78	98.53 148

Anonymous20240529		95.50 83	95.83 78	94.50 142	97.33 151	85.93 193	95.19 118	96.77 236	96.64 23	97.61 47	98.05 50	93.23 114	98.79 159	88.60 260	99.04 123	98.78 110

SMA-MVS		95.77 71	95.54 91	96.47 52	98.27 79	91.19 69	95.09 119	97.79 136	86.48 284	97.42 60	97.51 104	94.47 84	99.29 80	93.55 82	99.29 83	98.93 83
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
NR-MVSNet		95.28 97	95.28 108	95.26 100	97.75 119	87.21 150	95.08 120	97.37 177	93.92 73	97.65 42	95.90 252	90.10 212	99.33 75	90.11 210	99.66 23	99.26 37

TransMVSNet (Re)		95.27 100	96.04 63	92.97 216	98.37 72	81.92 273	95.07 121	96.76 237	93.97 70	97.77 38	98.57 28	95.72 24	97.90 301	88.89 248	99.23 94	99.08 58

UGNet		93.08 210	92.50 236	94.79 123	93.87 376	87.99 136	95.07 121	94.26 340	90.64 172	87.33 435	97.67 86	86.89 271	98.49 221	88.10 275	98.71 186	97.91 229
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
tttt0517		89.81 317	88.90 327	92.55 246	97.00 174	79.73 323	95.03 123	83.65 467	89.88 194	95.30 191	94.79 310	53.64 473	99.39 54	91.99 141	98.79 168	98.54 147

LFMVS		91.33 272	91.16 276	91.82 281	96.27 252	79.36 337	95.01 124	85.61 454	96.04 39	94.82 225	97.06 157	72.03 409	98.46 229	84.96 333	98.70 188	97.65 260

CSCG		94.69 124	94.75 135	94.52 141	97.55 137	87.87 138	95.01 124	97.57 159	92.68 93	96.20 135	93.44 363	91.92 154	98.78 163	89.11 242	99.24 93	96.92 312

GG-mvs-BLEND				83.24 461	85.06 493	71.03 448	94.99 126	65.55 500		74.09 491	75.51 491	44.57 487	94.46 446	59.57 489	87.54 477	84.24 487

EU-MVSNet		87.39 377	86.71 380	89.44 374	93.40 384	76.11 404	94.93 127	90.00 415	57.17 494	95.71 168	97.37 115	64.77 443	97.68 330	92.67 122	94.37 418	94.52 419

KD-MVS_self_test		94.10 164	94.73 138	92.19 264	97.66 130	79.49 332	94.86 128	97.12 204	89.59 202	96.87 91	97.65 88	90.40 203	98.34 244	89.08 243	99.35 67	98.75 114

MTMP							94.82 129	54.62 503

PHI-MVS		94.34 150	93.80 183	95.95 63	95.65 306	91.67 65	94.82 129	97.86 123	87.86 253	93.04 301	94.16 339	91.58 162	98.78 163	90.27 201	98.96 136	97.41 279

gg-mvs-nofinetune		82.10 432	81.02 433	85.34 443	87.46 481	71.04 447	94.74 131	67.56 498	96.44 28	79.43 485	98.99 11	45.24 485	96.15 410	67.18 475	92.17 458	88.85 478

ACMM	88.83 9	96.30 51	96.07 61	96.97 37	98.39 69	92.95 47	94.74 131	98.03 97	90.82 166	97.15 76	96.85 174	96.25 18	99.00 124	93.10 106	99.33 73	98.95 80
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
usedtu_dtu_shiyan2		93.15 209	92.40 240	95.41 92	98.56 49	90.53 83	94.71 133	94.14 342	92.10 113	93.73 265	96.94 165	89.66 220	97.77 320	72.97 452	98.81 161	97.92 227

NormalMVS		94.10 164	93.36 204	96.31 55	99.01 15	90.84 76	94.70 134	97.90 115	90.98 160	93.22 290	95.73 265	78.94 352	99.12 104	90.38 192	99.42 54	98.97 73

SymmetryMVS		93.26 200	92.36 242	95.97 61	97.13 164	90.84 76	94.70 134	91.61 402	90.98 160	93.22 290	95.73 265	78.94 352	99.12 104	90.38 192	98.53 206	97.97 217

SD-MVS		95.19 102	95.73 83	93.55 187	96.62 211	88.88 113	94.67 136	98.05 90	91.26 154	97.25 72	96.40 212	95.42 34	94.36 449	92.72 121	99.19 100	97.40 283
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
API-MVS		91.52 268	91.61 262	91.26 312	94.16 366	86.26 181	94.66 137	94.82 323	91.17 157	92.13 339	91.08 413	90.03 215	97.06 376	79.09 406	97.35 317	90.45 473

v10		94.68 125	95.27 109	92.90 223	96.57 215	80.15 304	94.65 138	97.57 159	90.68 171	97.43 57	98.00 55	88.18 240	99.15 98	94.84 51	99.55 37	99.41 26

v8		94.65 126	95.29 107	92.74 232	96.65 202	79.77 320	94.59 139	97.17 198	91.86 122	97.47 56	97.93 62	88.16 241	99.08 110	94.32 60	99.47 44	99.38 28

APD-MVS		95.00 109	94.69 139	95.93 66	97.38 147	90.88 74	94.59 139	97.81 132	89.22 210	95.46 182	96.17 238	93.42 108	99.34 70	89.30 231	98.87 151	97.56 269
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
VPA-MVSNet		95.14 104	95.67 86	93.58 186	97.76 118	83.15 246	94.58 141	97.58 158	93.39 83	97.05 83	98.04 52	93.25 113	98.51 219	89.75 222	99.59 29	99.08 58

ACMMP_NAP		96.21 53	96.12 57	96.49 51	98.90 22	91.42 66	94.57 142	98.03 97	90.42 181	96.37 120	97.35 123	95.68 25	99.25 88	94.44 58	99.34 71	98.80 103

HQP_MVS		94.26 153	93.93 179	95.23 103	97.71 124	88.12 133	94.56 143	97.81 132	91.74 134	93.31 281	95.59 272	86.93 269	98.95 134	89.26 235	98.51 210	98.60 142

plane_prior2							94.56 143		91.74 134

tfpnnormal		94.27 152	94.87 129	92.48 253	97.71 124	80.88 294	94.55 145	95.41 306	93.70 76	96.67 103	97.72 81	91.40 172	98.18 263	87.45 288	99.18 102	98.36 168

XVG-ACMP-BASELINE		95.68 75	95.34 103	96.69 44	98.40 68	93.04 44	94.54 146	98.05 90	90.45 180	96.31 125	96.76 182	92.91 128	98.72 173	91.19 167	99.42 54	98.32 173

DP-MVS		95.62 76	95.84 77	94.97 113	97.16 161	88.62 117	94.54 146	97.64 149	96.94 19	96.58 110	97.32 127	93.07 122	98.72 173	90.45 189	98.84 153	97.57 267

MIMVSNet		87.13 385	86.54 384	88.89 386	96.05 274	76.11 404	94.39 148	88.51 422	81.37 381	88.27 420	96.75 184	72.38 403	95.52 424	65.71 479	95.47 382	95.03 402

K. test v3		93.37 194	93.27 208	93.66 181	98.05 94	82.62 262	94.35 149	86.62 441	96.05 38	97.51 53	98.85 17	76.59 384	99.65 4	93.21 102	98.20 252	98.73 118

Vis-MVSNet (Re-imp)		90.42 292	90.16 301	91.20 317	97.66 130	77.32 381	94.33 150	87.66 433	91.20 156	92.99 302	95.13 293	75.40 389	98.28 247	77.86 411	99.19 100	97.99 212

ANet_high		94.83 117	96.28 48	90.47 349	96.65 202	73.16 433	94.33 150	98.74 13	96.39 30	98.09 33	98.93 13	93.37 109	98.70 180	90.38 192	99.68 20	99.53 17

MM		94.41 144	94.14 170	95.22 105	95.84 290	87.21 150	94.31 152	90.92 408	94.48 58	92.80 310	97.52 100	85.27 292	99.49 29	96.58 17	99.57 35	98.97 73

SD_0403		88.79 343	88.88 328	88.51 395	95.89 288	72.58 440	94.27 153	95.24 311	83.77 344	87.92 426	94.38 332	87.70 251	96.47 401	66.36 477	94.40 415	96.49 335

test_fmvsmconf0.01_n		95.90 65	96.09 58	95.31 99	97.30 153	89.21 103	94.24 154	98.76 12	86.25 289	97.56 48	98.66 23	95.73 23	98.44 232	97.35 3	98.99 127	98.27 180

ACMP	88.15 13	95.71 74	95.43 97	96.54 48	98.17 86	91.73 63	94.24 154	98.08 81	89.46 203	96.61 108	96.47 205	95.85 22	99.12 104	90.45 189	99.56 36	98.77 113
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MAR-MVS		90.32 300	88.87 329	94.66 132	94.82 341	91.85 60	94.22 156	94.75 327	80.91 385	87.52 433	88.07 449	86.63 275	97.87 308	76.67 422	96.21 363	94.25 425
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
ME-MVS		95.61 77	95.65 87	95.49 89	97.62 132	88.21 130	94.21 157	97.87 122	92.48 98	96.38 118	96.22 231	94.06 92	99.32 76	92.89 114	99.10 110	98.96 77

FMVSNet2		92.78 224	92.73 225	92.95 218	95.40 321	81.98 272	94.18 158	95.53 301	88.63 224	96.05 143	97.37 115	81.31 334	98.81 155	87.38 291	98.67 192	98.06 200

fmvsm_s_conf0.1_n_a		94.26 153	94.37 158	93.95 166	97.36 149	85.72 199	94.15 159	95.44 303	83.25 349	95.51 177	98.05 50	92.54 137	97.19 366	95.55 36	97.46 312	98.94 81

Anonymous20240521		92.86 221	93.57 196	90.74 340	96.57 215	75.50 412	94.15 159	95.60 293	89.38 205	95.90 152	97.90 72	80.39 342	97.96 298	92.60 125	99.68 20	98.75 114

GeoE		94.55 132	94.68 143	94.15 155	97.23 156	85.11 210	94.14 161	97.34 184	88.71 223	95.26 196	95.50 277	94.65 74	99.12 104	90.94 177	98.40 220	98.23 183

9.14			94.81 130		97.49 140		94.11 162	98.37 34	87.56 263	95.38 185	96.03 246	94.66 73	99.08 110	90.70 182	98.97 134

BP-MVS1		91.77 260	91.10 277	93.75 176	96.42 231	83.40 236	94.10 163	91.89 396	91.27 153	93.36 280	94.85 305	64.43 444	99.29 80	94.88 49	98.74 178	98.56 146

HPM-MVS++		95.02 108	94.39 156	96.91 40	97.88 110	93.58 40	94.09 164	96.99 213	91.05 159	92.40 326	95.22 290	91.03 187	99.25 88	92.11 135	98.69 189	97.90 230

usedtu_blend_shiyan5		89.08 332	88.33 339	91.34 306	91.29 440	79.59 326	94.02 165	97.13 202	90.07 190	90.09 379	83.30 479	72.25 404	98.10 276	81.45 377	95.32 388	96.33 343

HY-MVS	82.50 18	86.81 391	85.93 393	89.47 373	93.63 380	77.93 368	94.02 165	91.58 403	75.68 429	83.64 462	93.64 356	77.40 369	97.42 350	71.70 459	92.07 459	93.05 450

Effi-MVS+-dtu		93.90 175	92.60 233	97.77 3	94.74 349	96.67 5	94.00 167	95.41 306	89.94 192	91.93 344	92.13 397	90.12 210	98.97 131	87.68 285	97.48 310	97.67 259

Effi-MVS+		92.79 223	92.74 223	92.94 220	95.10 334	83.30 240	94.00 167	97.53 165	91.36 152	89.35 399	90.65 423	94.01 94	98.66 186	87.40 290	95.30 392	96.88 317

VDD-MVS		94.37 147	94.37 158	94.40 148	97.49 140	86.07 188	93.97 169	93.28 365	94.49 57	96.24 131	97.78 75	87.99 247	98.79 159	88.92 246	99.14 107	98.34 172

SSM_0404		94.38 145	94.69 139	93.43 197	97.16 161	83.23 242	93.95 170	97.84 127	91.46 147	95.70 169	96.56 202	92.50 141	99.08 110	88.83 249	98.23 245	97.98 213

h-mvs33		92.89 217	91.99 253	95.58 84	96.97 175	90.55 82	93.94 171	94.01 347	89.23 208	93.95 256	96.19 234	76.88 380	99.14 100	91.02 174	95.71 375	97.04 306

KinetiMVS		95.09 106	95.40 99	94.15 155	97.42 146	84.35 219	93.91 172	96.69 242	94.41 60	96.67 103	97.25 134	87.67 252	99.14 100	95.78 29	98.81 161	98.97 73

EPNet		89.80 318	88.25 345	94.45 146	83.91 495	86.18 185	93.87 173	87.07 439	91.16 158	80.64 482	94.72 312	78.83 354	98.89 140	85.17 325	98.89 146	98.28 178
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvs3		92.42 240	92.40 240	92.46 255	93.80 379	87.28 148	93.86 174	97.05 208	76.86 424	96.25 130	98.66 23	82.87 315	91.26 470	95.44 39	96.83 343	98.82 99

DeepC-MVS	91.39 4	95.43 86	95.33 105	95.71 78	97.67 129	90.17 87	93.86 174	98.02 99	87.35 265	96.22 133	97.99 58	94.48 83	99.05 117	92.73 120	99.68 20	97.93 222
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LCM-MVSNet-Re		94.20 160	94.58 148	93.04 213	95.91 285	83.13 248	93.79 176	99.19 5	92.00 115	98.84 8	98.04 52	93.64 99	99.02 122	81.28 380	98.54 205	96.96 311

TranMVSNet+NR-MVSNet		96.07 58	96.26 49	95.50 88	98.26 80	87.69 142	93.75 177	97.86 123	95.96 41	97.48 55	97.14 148	95.33 40	99.44 33	90.79 179	99.76 10	99.38 28

fmvsm_s_conf0.1_n		94.19 162	94.41 155	93.52 193	97.22 158	84.37 217	93.73 178	95.26 310	84.45 335	95.76 160	98.00 55	91.85 155	97.21 363	95.62 31	97.82 288	98.98 70

PAPM_NR		91.03 277	90.81 286	91.68 288	96.73 195	81.10 290	93.72 179	96.35 266	88.19 244	88.77 411	92.12 398	85.09 295	97.25 360	82.40 366	93.90 430	96.68 324

baseline		94.26 153	94.80 131	92.64 237	96.08 271	80.99 292	93.69 180	98.04 96	90.80 167	94.89 223	96.32 221	93.19 115	98.48 226	91.68 154	98.51 210	98.43 158

dcpmvs_2		93.96 172	95.01 124	90.82 338	97.60 133	74.04 428	93.68 181	98.85 9	89.80 196	97.82 36	97.01 162	91.14 183	99.21 91	90.56 185	98.59 200	99.19 45

SSM_0407		94.23 158	94.56 150	93.24 207	96.65 202	82.79 256	93.66 182	97.84 127	91.46 147	95.19 204	96.56 202	92.50 141	98.99 125	88.83 249	98.32 234	97.93 222

GDP-MVS		91.56 266	90.83 285	93.77 175	96.34 242	83.65 232	93.66 182	98.12 74	87.32 267	92.98 304	94.71 313	63.58 450	99.30 79	92.61 124	98.14 256	98.35 171

fmvsm_s_conf0.5_n_a		94.02 169	94.08 173	93.84 172	96.72 197	85.73 198	93.65 184	95.23 312	83.30 347	95.13 209	97.56 95	92.22 147	97.17 367	95.51 37	97.41 314	98.64 136

FE-MVSNET2		94.07 167	94.47 154	92.90 223	97.45 145	81.26 286	93.58 185	97.54 162	88.28 240	96.46 114	97.92 67	91.41 171	98.74 170	88.12 274	99.44 51	98.69 126

casdiffseed414692147		94.56 131	94.90 126	93.54 189	96.60 212	83.33 238	93.57 186	98.06 88	91.57 140	95.26 196	97.31 128	94.06 92	98.39 233	88.67 256	98.95 138	98.91 89

fmvsm_s_conf0.5_n_11		94.91 112	95.44 96	93.33 201	96.45 227	83.11 249	93.56 187	98.64 14	89.76 197	95.70 169	97.97 59	92.32 143	98.08 278	95.62 31	98.95 138	98.79 105

F-COLMAP		92.28 246	91.06 278	95.95 63	97.52 138	91.90 59	93.53 188	97.18 197	83.98 339	88.70 413	94.04 342	88.41 237	98.55 211	80.17 392	95.99 368	97.39 284

test_fmvsmconf0.1_n		95.61 77	95.72 84	95.26 100	96.85 185	89.20 104	93.51 189	98.60 16	85.68 308	97.42 60	98.30 40	95.34 39	98.39 233	96.85 11	98.98 129	98.19 189

FMVSNet5		87.82 364	86.56 383	91.62 290	92.31 410	79.81 319	93.49 190	94.81 325	83.26 348	91.36 351	96.93 167	52.77 475	97.49 345	76.07 428	98.03 269	97.55 270

DPE-MVS		95.89 66	95.88 74	95.92 68	97.93 107	89.83 91	93.46 191	98.30 41	92.37 101	97.75 39	96.95 164	95.14 48	99.51 20	91.74 150	99.28 88	98.41 162
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
alignmvs		93.26 200	92.85 219	94.50 142	95.70 301	87.45 145	93.45 192	95.76 288	91.58 139	95.25 199	92.42 390	81.96 329	98.72 173	91.61 155	97.87 286	97.33 288

test_fmvsmvis_n_1920		95.08 107	95.40 99	94.13 158	96.66 201	87.75 141	93.44 193	98.49 23	85.57 312	98.27 23	97.11 151	94.11 91	97.75 324	96.26 20	98.72 184	96.89 315

114514_t		90.51 289	89.80 310	92.63 240	98.00 102	82.24 269	93.40 194	97.29 189	65.84 485	89.40 398	94.80 309	86.99 267	98.75 167	83.88 349	98.61 197	96.89 315

fmvsm_s_conf0.5_n		94.00 170	94.20 168	93.42 198	96.69 199	84.37 217	93.38 195	95.13 314	84.50 334	95.40 184	97.55 99	91.77 157	97.20 364	95.59 33	97.79 289	98.69 126

LuminaMVS		93.43 192	93.18 210	94.16 154	97.32 152	85.29 208	93.36 196	93.94 349	88.09 247	97.12 78	96.43 208	80.11 343	98.98 126	93.53 83	98.76 172	98.21 185

DeepC-MVS_fast	89.96 7	93.73 179	93.44 201	94.60 136	96.14 265	87.90 137	93.36 196	97.14 200	85.53 313	93.90 259	95.45 280	91.30 175	98.59 199	89.51 225	98.62 196	97.31 289
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS-pluss		96.08 57	95.92 71	96.57 47	99.06 10	91.21 68	93.25 198	98.32 38	87.89 252	96.86 92	97.38 114	95.55 30	99.39 54	95.47 38	99.47 44	99.11 54
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_0402		95.73 73	96.22 51	94.26 152	98.19 85	85.77 197	93.24 199	97.24 194	96.88 20	97.69 41	97.77 79	94.12 90	99.13 103	91.54 160	99.29 83	97.88 233

test_fmvsmconf_n		95.43 86	95.50 92	95.22 105	96.48 226	89.19 105	93.23 200	98.36 35	85.61 311	96.92 90	98.02 54	95.23 45	98.38 237	96.69 14	98.95 138	98.09 199

test_fmvsm_n_1920		94.72 121	94.74 137	94.67 130	96.30 248	88.62 117	93.19 201	98.07 84	85.63 310	97.08 79	97.35 123	90.86 189	97.66 331	95.70 30	98.48 213	97.74 254

sd_testset		93.94 173	94.39 156	92.61 243	97.93 107	83.24 241	93.17 202	95.04 316	93.65 80	95.51 177	98.63 25	94.49 82	95.89 419	81.72 373	99.35 67	98.70 123

fmvsm_s_conf0.5_n_3		95.20 101	95.95 67	92.94 220	96.60 212	82.18 270	93.13 203	98.39 32	91.44 149	97.16 75	97.68 84	93.03 125	97.82 312	97.54 2	98.63 195	98.81 101

MSLP-MVS++		93.25 203	93.88 180	91.37 304	96.34 242	82.81 255	93.11 204	97.74 140	89.37 206	94.08 249	95.29 289	90.40 203	96.35 407	90.35 196	98.25 243	94.96 404

baseline1		87.62 369	87.31 363	88.54 393	94.71 352	74.27 424	93.10 205	88.20 426	86.20 291	92.18 337	93.04 372	73.21 398	95.52 424	79.32 403	85.82 480	95.83 373

fmvsm_l_conf0.5_n_3		95.19 102	95.36 101	94.68 129	96.79 192	87.49 144	93.05 206	98.38 33	87.21 270	96.59 109	97.76 80	94.20 88	98.11 273	95.90 26	98.40 220	98.42 159

plane_prior						88.12 133	93.01 207		88.98 215						98.06 266

fmvsm_s_conf0.5_n_10		94.63 127	95.11 119	93.18 210	96.28 249	83.51 234	93.00 208	98.25 45	88.37 238	97.43 57	97.70 82	88.90 227	98.63 192	97.15 5	98.90 145	97.41 279

guyue		92.60 232	92.62 231	92.52 252	96.73 195	81.00 291	93.00 208	91.83 398	88.28 240	96.38 118	96.23 230	80.71 340	98.37 241	92.06 140	98.37 230	98.20 187

thres100view900		87.35 378	86.89 375	88.72 389	96.14 265	73.09 434	93.00 208	85.31 457	92.13 112	93.26 286	90.96 416	63.42 451	98.28 247	71.27 462	96.54 353	94.79 412

E5new		94.50 135	95.15 112	92.55 246	97.04 168	80.27 300	92.96 211	98.25 45	90.18 185	95.77 157	97.45 108	94.85 67	98.59 199	91.16 168	98.73 180	98.79 105

E6new		94.50 135	95.15 112	92.55 246	97.04 168	80.28 298	92.96 211	98.25 45	90.18 185	95.76 160	97.45 108	94.86 65	98.59 199	91.16 168	98.73 180	98.79 105

E6		94.50 135	95.15 112	92.55 246	97.04 168	80.28 298	92.96 211	98.25 45	90.18 185	95.76 160	97.45 108	94.86 65	98.59 199	91.16 168	98.73 180	98.79 105

E5		94.50 135	95.15 112	92.55 246	97.04 168	80.27 300	92.96 211	98.25 45	90.18 185	95.77 157	97.45 108	94.85 67	98.59 199	91.16 168	98.73 180	98.79 105

fmvsm_s_conf0.5_n_9		95.58 80	95.91 72	94.59 137	97.25 154	86.26 181	92.96 211	97.86 123	91.88 121	97.52 52	98.13 45	91.45 170	98.54 212	97.17 4	98.99 127	98.98 70

Patchmtry		90.11 307	89.92 307	90.66 343	90.35 457	77.00 387	92.96 211	92.81 373	90.25 184	94.74 229	96.93 167	67.11 426	97.52 341	85.17 325	98.98 129	97.46 275

LF4IMVS		92.72 227	92.02 252	94.84 121	95.65 306	91.99 57	92.92 217	96.60 250	85.08 325	92.44 324	93.62 358	86.80 272	96.35 407	86.81 297	98.25 243	96.18 356

UniMVSNet (Re)		95.32 93	95.15 112	95.80 74	97.79 117	88.91 110	92.91 218	98.07 84	93.46 82	96.31 125	95.97 251	90.14 209	99.34 70	92.11 135	99.64 25	99.16 47

TAPA-MVS	88.58 10	92.49 238	91.75 261	94.73 125	96.50 223	89.69 92	92.91 218	97.68 145	78.02 415	92.79 311	94.10 340	90.85 190	97.96 298	84.76 336	98.16 254	96.54 327
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
AstraMVS		92.75 226	92.73 225	92.79 230	97.02 172	81.48 283	92.88 220	90.62 412	87.99 249	96.48 112	96.71 189	82.02 327	98.48 226	92.44 130	98.46 215	98.40 165

MGCNet		92.88 218	92.27 244	94.69 128	92.35 409	86.03 189	92.88 220	89.68 416	90.53 177	91.52 348	96.43 208	82.52 322	99.32 76	95.01 48	99.54 38	98.71 122

fmvsm_s_conf0.5_n_5		94.50 135	94.80 131	93.60 184	96.80 190	84.93 212	92.81 222	97.59 157	85.27 318	96.85 95	97.29 129	91.48 169	98.05 285	96.67 15	98.47 214	97.83 241

thisisatest0530		88.69 347	87.52 359	92.20 263	96.33 244	79.36 337	92.81 222	84.01 466	86.44 285	93.67 267	92.68 383	53.62 474	99.25 88	89.65 224	98.45 216	98.00 209

EIA-MVS		92.35 243	92.03 251	93.30 204	95.81 294	83.97 228	92.80 224	98.17 66	87.71 258	89.79 391	87.56 451	91.17 182	99.18 96	87.97 280	97.27 318	96.77 321

IMVS_0407		92.28 246	92.83 220	90.63 345	95.19 330	76.72 393	92.79 225	96.89 221	85.92 298	93.55 271	94.50 324	91.06 184	98.07 282	88.49 264	97.07 327	97.10 298

thres600view7		87.66 367	87.10 372	89.36 377	96.05 274	73.17 432	92.72 226	85.31 457	91.89 120	93.29 283	90.97 415	63.42 451	98.39 233	73.23 449	96.99 338	96.51 331

wuyk23d		87.83 363	90.79 288	78.96 474	90.46 456	88.63 116	92.72 226	90.67 411	91.65 138	98.68 14	97.64 89	96.06 19	77.53 496	59.84 488	99.41 60	70.73 494

fmvsm_s_conf0.5_n_6		94.14 163	94.54 151	92.95 218	96.51 222	82.74 260	92.71 228	98.13 72	86.56 283	96.44 115	96.85 174	88.51 233	98.05 285	96.03 23	99.09 113	98.06 200

test_fmvs2		90.62 288	90.40 298	91.29 310	91.93 425	85.46 205	92.70 229	96.48 260	74.44 439	94.91 222	97.59 92	75.52 388	90.57 473	93.44 91	96.56 352	97.84 240

V42		93.43 192	93.58 195	92.97 216	95.34 325	81.22 288	92.67 230	96.49 259	87.25 268	96.20 135	96.37 218	87.32 259	98.85 147	92.39 132	98.21 250	98.85 97

casdiffmvs_mvg		95.10 105	95.62 88	93.53 191	96.25 255	83.23 242	92.66 231	98.19 60	93.06 89	97.49 54	97.15 147	94.78 70	98.71 179	92.27 133	98.72 184	98.65 130
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
OPM-MVS		95.61 77	95.45 94	96.08 58	98.49 65	91.00 71	92.65 232	97.33 185	90.05 191	96.77 99	96.85 174	95.04 55	98.56 209	92.77 117	99.06 115	98.70 123
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
fmvsm_s_conf0.5_n_8		94.70 123	95.34 103	92.78 231	96.77 194	81.50 282	92.64 233	98.50 21	91.51 146	97.22 73	97.93 62	88.07 243	98.45 230	96.62 16	98.80 165	98.39 166

test_vis1_n		89.01 336	89.01 323	89.03 382	92.57 402	82.46 265	92.62 234	96.06 279	73.02 451	90.40 373	95.77 263	74.86 390	89.68 479	90.78 180	94.98 402	94.95 405

fmvsm_s_conf0.5_n_4		94.26 153	94.58 148	93.31 202	96.40 233	82.73 261	92.59 235	97.41 175	86.60 281	96.33 122	97.07 155	89.91 216	98.07 282	96.88 10	98.01 272	99.13 50

DU-MVS		95.28 97	95.12 118	95.75 76	97.75 119	88.59 120	92.58 236	97.81 132	93.99 68	96.80 97	95.90 252	90.10 212	99.41 43	91.60 156	99.58 33	99.26 37

FMVSNet3		90.78 280	90.32 300	92.16 268	93.03 393	79.92 315	92.54 237	94.95 319	86.17 294	95.10 211	96.01 247	69.97 417	98.75 167	86.74 298	98.38 225	97.82 244

hse-mvs2		92.24 250	91.20 273	95.38 93	96.16 262	90.65 81	92.52 238	92.01 395	89.23 208	93.95 256	92.99 374	76.88 380	98.69 182	91.02 174	96.03 366	96.81 319

MVS_Test		92.57 236	93.29 205	90.40 352	93.53 382	75.85 407	92.52 238	96.96 214	88.73 221	92.35 330	96.70 190	90.77 192	98.37 241	92.53 127	95.49 381	96.99 308

CR-MVSNet		87.89 361	87.12 371	90.22 357	91.01 445	78.93 346	92.52 238	92.81 373	73.08 450	89.10 401	96.93 167	67.11 426	97.64 333	88.80 252	92.70 452	94.08 426

RPMNet		90.31 301	90.14 304	90.81 339	91.01 445	78.93 346	92.52 238	98.12 74	91.91 119	89.10 401	96.89 170	68.84 419	99.41 43	90.17 208	92.70 452	94.08 426

fmvsm_l_conf0.5_n		93.79 177	93.81 181	93.73 178	96.16 262	86.26 181	92.46 242	96.72 239	81.69 377	95.77 157	97.11 151	90.83 191	97.82 312	95.58 34	97.99 275	97.11 297

XVG-OURS-SEG-HR		95.38 90	95.00 125	96.51 49	98.10 90	94.07 23	92.46 242	98.13 72	90.69 170	93.75 262	96.25 229	98.03 2	97.02 377	92.08 137	95.55 379	98.45 156

EI-MVSNet-Vis-set		94.36 148	94.28 164	94.61 133	92.55 403	85.98 190	92.44 244	94.69 329	93.70 76	96.12 140	95.81 258	91.24 176	98.86 145	93.76 77	98.22 249	98.98 70

Anonymous202405211		92.58 234	92.50 236	92.83 227	96.55 217	83.22 244	92.43 245	91.64 401	94.10 65	95.59 174	96.64 193	81.88 331	97.50 342	85.12 329	98.52 208	97.77 250

AUN-MVS		90.05 311	88.30 341	95.32 98	96.09 270	90.52 84	92.42 246	92.05 394	82.08 371	88.45 417	92.86 376	65.76 436	98.69 182	88.91 247	96.07 365	96.75 323

EI-MVSNet-UG-set		94.35 149	94.27 166	94.59 137	92.46 406	85.87 195	92.42 246	94.69 329	93.67 79	96.13 139	95.84 256	91.20 179	98.86 145	93.78 74	98.23 245	99.03 62

IMVS_0403		92.20 251	92.70 228	90.69 341	95.19 330	76.72 393	92.39 248	96.89 221	85.92 298	93.66 268	94.50 324	90.18 207	98.24 255	88.49 264	97.07 327	97.10 298

NCCC		94.08 166	93.54 198	95.70 80	96.49 224	89.90 90	92.39 248	96.91 220	90.64 172	92.33 333	94.60 319	90.58 200	98.96 132	90.21 205	97.70 297	98.23 183

viewdifsd2359ckpt09		92.60 232	92.34 243	93.36 199	95.94 284	83.36 237	92.35 250	97.93 114	83.17 353	92.92 307	94.66 316	89.87 217	98.57 205	86.51 308	97.71 296	98.15 194

casdiffmvs		94.32 151	94.80 131	92.85 226	96.05 274	81.44 284	92.35 250	98.05 90	91.53 143	95.75 164	96.80 178	93.35 110	98.49 221	91.01 176	98.32 234	98.64 136
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ETV-MVS		92.99 214	92.74 223	93.72 179	95.86 289	86.30 180	92.33 252	97.84 127	91.70 137	92.81 309	86.17 461	92.22 147	99.19 95	88.03 279	97.73 292	95.66 382

fmvsm_l_conf0.5_n_a		93.59 185	93.63 192	93.49 195	96.10 269	85.66 201	92.32 253	96.57 253	81.32 382	95.63 172	97.14 148	90.19 206	97.73 327	95.37 44	98.03 269	97.07 302

EI-MVSNet		92.99 214	93.26 209	92.19 264	92.12 418	79.21 343	92.32 253	94.67 331	91.77 132	95.24 200	95.85 254	87.14 264	98.49 221	91.99 141	98.26 241	98.86 94

CVMVSNet		85.16 401	84.72 399	86.48 429	92.12 418	70.19 451	92.32 253	88.17 427	56.15 495	90.64 369	95.85 254	67.97 424	96.69 393	88.78 253	90.52 468	92.56 457

VortexMVS		92.13 253	92.56 234	90.85 336	94.54 357	76.17 403	92.30 256	96.63 249	86.20 291	96.66 105	96.79 179	79.87 345	98.16 267	91.27 166	98.76 172	98.24 182

test_fmvs1_n		88.73 346	88.38 338	89.76 368	92.06 420	82.53 263	92.30 256	96.59 252	71.14 463	92.58 318	95.41 285	68.55 420	89.57 481	91.12 172	95.66 376	97.18 296

OMC-MVS		94.22 159	93.69 190	95.81 73	97.25 154	91.27 67	92.27 258	97.40 176	87.10 275	94.56 235	95.42 282	93.74 97	98.11 273	86.62 303	98.85 152	98.06 200

PM-MVS		93.33 197	92.67 230	95.33 96	96.58 214	94.06 24	92.26 259	92.18 388	85.92 298	96.22 133	96.61 197	85.64 289	95.99 417	90.35 196	98.23 245	95.93 367

UniMVSNet_NR-MVSNet		95.35 91	95.21 110	95.76 75	97.69 127	88.59 120	92.26 259	97.84 127	94.91 52	96.80 97	95.78 262	90.42 201	99.41 43	91.60 156	99.58 33	99.29 36

AdaColmap		91.63 264	91.36 270	92.47 254	95.56 313	86.36 178	92.24 261	96.27 269	88.88 219	89.90 388	92.69 382	91.65 160	98.32 245	77.38 418	97.64 301	92.72 456

PVSNet_Blended_VisFu		91.63 264	91.20 273	92.94 220	97.73 122	83.95 229	92.14 262	97.46 172	78.85 411	92.35 330	94.98 300	84.16 301	99.08 110	86.36 311	96.77 346	95.79 375

Baseline_NR-MVSNet		94.47 141	95.09 122	92.60 244	98.50 64	80.82 295	92.08 263	96.68 245	93.82 74	96.29 127	98.56 29	90.10 212	97.75 324	90.10 212	99.66 23	99.24 41

Fast-Effi-MVS+-dtu		92.77 225	92.16 247	94.58 140	94.66 354	88.25 128	92.05 264	96.65 247	89.62 201	90.08 383	91.23 410	92.56 136	98.60 197	86.30 312	96.27 360	96.90 313

save fliter					97.46 143	88.05 135	92.04 265	97.08 206	87.63 261

PatchT		87.51 374	88.17 350	85.55 441	90.64 450	66.91 466	92.02 266	86.09 445	92.20 109	89.05 404	97.16 144	64.15 446	96.37 406	89.21 238	92.98 450	93.37 445

EG-PatchMatch MVS		94.54 133	94.67 144	94.14 157	97.87 112	86.50 171	92.00 267	96.74 238	88.16 246	96.93 89	97.61 91	93.04 124	97.90 301	91.60 156	98.12 258	98.03 207

fmvsm_s_conf0.1_n_2		94.38 145	94.78 134	93.19 209	97.07 167	81.72 277	91.97 268	97.51 168	87.05 276	97.31 66	97.92 67	88.29 238	98.15 269	97.10 6	98.81 161	99.70 5

v144192		93.20 207	93.54 198	92.16 268	96.05 274	78.26 365	91.95 269	97.14 200	84.98 328	95.96 147	96.11 242	87.08 265	99.04 120	93.79 73	98.84 153	99.17 46

VNet		92.67 229	92.96 215	91.79 282	96.27 252	80.15 304	91.95 269	94.98 318	92.19 110	94.52 237	96.07 244	87.43 257	97.39 353	84.83 334	98.38 225	97.83 241

1314		86.46 393	86.33 390	86.87 425	91.65 433	74.54 419	91.94 271	94.10 343	74.28 441	84.78 452	87.33 455	83.03 313	95.00 437	78.72 407	91.16 465	91.06 469

MVS		84.98 403	84.30 404	87.01 420	91.03 444	77.69 377	91.94 271	94.16 341	59.36 493	84.23 457	87.50 453	85.66 287	96.80 390	71.79 457	93.05 449	86.54 485

SDMVSNet		94.43 143	95.02 123	92.69 235	97.93 107	82.88 254	91.92 273	95.99 284	93.65 80	95.51 177	98.63 25	94.60 76	96.48 399	87.57 286	99.35 67	98.70 123

fmvsm_l_conf0.5_n_9		94.51 134	95.11 119	92.72 233	96.70 198	83.14 247	91.91 274	97.89 119	88.44 234	97.30 67	97.57 93	91.60 161	97.54 339	95.82 28	98.74 178	97.47 274

tfpn200view9		87.05 387	86.52 385	88.67 390	95.77 297	72.94 436	91.89 275	86.00 446	90.84 164	92.61 316	89.80 427	63.93 447	98.28 247	71.27 462	96.54 353	94.79 412

thres400		87.20 382	86.52 385	89.24 381	95.77 297	72.94 436	91.89 275	86.00 446	90.84 164	92.61 316	89.80 427	63.93 447	98.28 247	71.27 462	96.54 353	96.51 331

v1921920		93.26 200	93.61 194	92.19 264	96.04 278	78.31 364	91.88 277	97.24 194	85.17 321	96.19 138	96.19 234	86.76 273	99.05 117	94.18 64	98.84 153	99.22 42

XXY-MVS		92.58 234	93.16 212	90.84 337	97.75 119	79.84 316	91.87 278	96.22 274	85.94 297	95.53 176	97.68 84	92.69 134	94.48 445	83.21 353	97.51 307	98.21 185

IterMVS-LS		93.78 178	94.28 164	92.27 258	96.27 252	79.21 343	91.87 278	96.78 234	91.77 132	96.57 111	97.07 155	87.15 263	98.74 170	91.99 141	99.03 125	98.86 94
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1144		93.50 188	93.81 181	92.57 245	96.28 249	79.61 325	91.86 280	96.96 214	86.95 278	95.91 151	96.32 221	87.65 253	98.96 132	93.51 84	98.88 148	99.13 50

v1192		93.49 189	93.78 184	92.62 242	96.16 262	79.62 324	91.83 281	97.22 196	86.07 295	96.10 142	96.38 217	87.22 261	99.02 122	94.14 65	98.88 148	99.22 42

v1240		93.29 198	93.71 189	92.06 272	96.01 279	77.89 370	91.81 282	97.37 177	85.12 323	96.69 102	96.40 212	86.67 274	99.07 116	94.51 54	98.76 172	99.22 42

CNVR-MVS		94.58 130	94.29 163	95.46 91	96.94 177	89.35 102	91.81 282	96.80 233	89.66 200	93.90 259	95.44 281	92.80 132	98.72 173	92.74 119	98.52 208	98.32 173

viewdifsd2359ckpt13		92.57 236	92.48 238	92.83 227	95.60 310	82.35 268	91.80 284	97.49 170	85.04 326	93.14 296	95.41 285	90.94 188	98.25 253	86.68 301	96.24 362	97.87 236

v2v482		93.29 198	93.63 192	92.29 257	96.35 241	78.82 352	91.77 285	96.28 268	88.45 233	95.70 169	96.26 228	86.02 283	98.90 138	93.02 109	98.81 161	99.14 49

fmvsm_s_conf0.5_n_2		94.25 157	94.63 146	93.10 212	96.65 202	81.75 276	91.72 286	97.25 192	86.93 280	97.20 74	97.67 86	88.44 236	98.14 272	97.06 9	98.77 170	99.42 24

EPNet_dtu		85.63 397	84.37 403	89.40 376	86.30 486	74.33 423	91.64 287	88.26 424	84.84 331	72.96 493	89.85 425	71.27 412	97.69 329	76.60 423	97.62 302	96.18 356
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewmacassd2359aftdt		93.83 176	94.36 160	92.24 261	96.45 227	79.58 329	91.60 288	97.96 107	89.14 212	95.05 215	97.09 154	93.69 98	98.48 226	89.79 219	98.43 217	98.65 130

PLC	85.34 15	90.40 293	88.92 325	94.85 120	96.53 221	90.02 88	91.58 289	96.48 260	80.16 392	86.14 441	92.18 395	85.73 286	98.25 253	76.87 421	94.61 413	96.30 347
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
FE-MVSNET		92.02 256	92.22 246	91.41 301	96.63 210	79.08 345	91.53 290	96.84 230	85.52 315	95.16 207	96.14 239	83.97 303	97.50 342	85.48 321	98.75 176	97.64 261

VPNet		93.08 210	93.76 185	91.03 323	98.60 46	75.83 410	91.51 291	95.62 292	91.84 126	95.74 165	97.10 153	89.31 223	98.32 245	85.07 332	99.06 115	98.93 83

ttmdpeth		86.91 390	86.57 382	87.91 409	89.68 464	74.24 425	91.49 292	87.09 437	79.84 393	89.46 397	97.86 73	65.42 438	91.04 471	81.57 375	96.74 349	98.44 157

XVG-OURS		94.72 121	94.12 171	96.50 50	98.00 102	94.23 21	91.48 293	98.17 66	90.72 169	95.30 191	96.47 205	87.94 248	96.98 378	91.41 163	97.61 303	98.30 177

HQP-NCC					96.36 238		91.37 294		87.16 271	88.81 407

ACMP_Plane					96.36 238		91.37 294		87.16 271	88.81 407

HQP-MVS		92.09 254	91.49 267	93.88 169	96.36 238	84.89 213	91.37 294	97.31 186	87.16 271	88.81 407	93.40 364	84.76 297	98.60 197	86.55 306	97.73 292	98.14 196

MCST-MVS		92.91 216	92.51 235	94.10 159	97.52 138	85.72 199	91.36 297	97.13 202	80.33 391	92.91 308	94.24 335	91.23 177	98.72 173	89.99 214	97.93 282	97.86 237

E4		94.00 170	94.53 152	92.42 256	96.78 193	79.99 312	91.33 298	98.16 69	89.69 198	95.27 195	97.16 144	93.94 96	98.64 190	89.99 214	98.42 219	98.61 141

v148		92.87 220	93.29 205	91.62 290	96.25 255	77.72 376	91.28 299	95.05 315	89.69 198	95.93 150	96.04 245	87.34 258	98.38 237	90.05 213	97.99 275	98.78 110

tpmvs		84.22 410	83.97 409	84.94 447	87.09 483	65.18 476	91.21 300	88.35 423	82.87 358	85.21 445	90.96 416	65.24 441	96.75 391	79.60 402	85.25 481	92.90 453

reproduce_monomvs		87.13 385	86.90 374	87.84 411	90.92 447	68.15 461	91.19 301	93.75 354	85.84 303	94.21 245	95.83 257	42.99 492	97.10 371	89.46 227	97.88 285	98.26 181

viewmanbaseed2359cas		93.08 210	93.43 202	92.01 275	95.69 302	79.29 339	91.15 302	97.70 144	87.45 264	94.18 246	96.12 241	92.31 144	98.37 241	88.58 261	97.73 292	98.38 167

CANet		92.38 242	91.99 253	93.52 193	93.82 378	83.46 235	91.14 303	97.00 211	89.81 195	86.47 439	94.04 342	87.90 249	99.21 91	89.50 226	98.27 240	97.90 230

CNLPA		91.72 262	91.20 273	93.26 206	96.17 261	91.02 70	91.14 303	95.55 300	90.16 189	90.87 363	93.56 361	86.31 279	94.40 448	79.92 398	97.12 325	94.37 422

DP-MVS Recon		92.31 245	91.88 257	93.60 184	97.18 160	86.87 161	91.10 305	97.37 177	84.92 329	92.08 341	94.08 341	88.59 232	98.20 260	83.50 350	98.14 256	95.73 377

OpenMVS_ROB	85.12 16	89.52 321	89.05 321	90.92 332	94.58 356	81.21 289	91.10 305	93.41 364	77.03 423	93.41 276	93.99 346	83.23 310	97.80 315	79.93 396	94.80 408	93.74 437

MVStest1		84.79 405	84.06 408	86.98 421	77.73 502	74.76 415	91.08 307	85.63 451	77.70 416	96.86 92	97.97 59	41.05 499	88.24 486	92.22 134	96.28 359	97.94 221

E2		93.53 186	93.96 176	92.25 259	96.39 234	79.76 321	91.06 308	98.05 90	88.58 229	94.71 232	96.64 193	93.08 120	98.57 205	89.16 239	97.97 277	98.42 159

E3		93.53 186	93.96 176	92.25 259	96.39 234	79.76 321	91.06 308	98.05 90	88.58 229	94.71 232	96.64 193	93.07 122	98.57 205	89.16 239	97.97 277	98.42 159

TSAR-MVS + GP.		93.07 213	92.41 239	95.06 110	95.82 292	90.87 75	90.97 310	92.61 381	88.04 248	94.61 234	93.79 354	88.08 242	97.81 314	89.41 228	98.39 224	96.50 334

MVP-Stereo		90.07 310	88.92 325	93.54 189	96.31 246	86.49 172	90.93 311	95.59 297	79.80 394	91.48 349	95.59 272	80.79 338	97.39 353	78.57 409	91.19 464	96.76 322
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
viewcassd2359sk11		93.16 208	93.51 200	92.13 270	96.07 272	79.59 326	90.88 312	97.97 105	87.82 254	94.23 243	96.19 234	92.31 144	98.53 216	88.58 261	97.51 307	98.28 178

MVSTER		89.32 325	88.75 330	91.03 323	90.10 460	76.62 398	90.85 313	94.67 331	82.27 368	95.24 200	95.79 259	61.09 460	98.49 221	90.49 188	98.26 241	97.97 217

pmmvs-eth3d		91.54 267	90.73 290	93.99 161	95.76 299	87.86 139	90.83 314	93.98 348	78.23 414	94.02 254	96.22 231	82.62 321	96.83 388	86.57 304	98.33 232	97.29 290

fmvsm_s_conf0.5_n_7		93.61 183	93.94 178	92.63 240	96.11 268	82.76 259	90.81 315	97.55 161	86.57 282	93.14 296	97.69 83	90.17 208	96.83 388	94.46 56	98.93 141	98.31 175

CANet_DTU		89.85 316	89.17 319	91.87 278	92.20 415	80.02 311	90.79 316	95.87 286	86.02 296	82.53 472	91.77 403	80.01 344	98.57 205	85.66 319	97.70 297	97.01 307

E3new		92.83 222	93.10 213	92.04 273	95.78 296	79.45 333	90.76 317	97.90 115	87.23 269	93.79 261	95.70 268	91.55 163	98.49 221	88.17 272	96.99 338	98.16 192

SSC-MVS		90.16 304	92.96 215	81.78 467	97.88 110	48.48 500	90.75 318	87.69 432	96.02 40	96.70 101	97.63 90	85.60 290	97.80 315	85.73 318	98.60 199	99.06 60

test_prior4						89.91 89	90.74 319

TinyColmap		92.00 257	92.76 222	89.71 370	95.62 309	77.02 386	90.72 320	96.17 277	87.70 259	95.26 196	96.29 223	92.54 137	96.45 402	81.77 371	98.77 170	95.66 382

CDPH-MVS		92.67 229	91.83 259	95.18 107	96.94 177	88.46 125	90.70 321	97.07 207	77.38 418	92.34 332	95.08 297	92.67 135	98.88 141	85.74 317	98.57 202	98.20 187

test_vis1_n_1920		89.45 322	89.85 309	88.28 400	93.59 381	76.71 397	90.67 322	97.78 138	79.67 398	90.30 377	96.11 242	76.62 383	92.17 466	90.31 198	93.57 435	95.96 365

DSMNet-mixed		82.21 429	81.56 427	84.16 455	89.57 467	70.00 456	90.65 323	77.66 493	54.99 496	83.30 466	97.57 93	77.89 365	90.50 475	66.86 476	95.54 380	91.97 461

TEST9					96.45 227	89.46 96	90.60 324	96.92 218	79.09 407	90.49 370	94.39 330	91.31 174	98.88 141

train_agg		92.71 228	91.83 259	95.35 94	96.45 227	89.46 96	90.60 324	96.92 218	79.37 402	90.49 370	94.39 330	91.20 179	98.88 141	88.66 257	98.43 217	97.72 255

PatchmatchNet		85.22 400	84.64 400	86.98 421	89.51 468	69.83 457	90.52 326	87.34 436	78.87 410	87.22 436	92.74 381	66.91 428	96.53 396	81.77 371	86.88 478	94.58 418
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_8					96.37 236	89.14 106	90.51 327	96.89 221	79.37 402	90.42 372	94.36 333	91.20 179	98.82 150

viewdifsd2359ckpt11		93.36 195	93.99 174	91.48 297	95.50 317	78.39 360	90.47 328	96.69 242	88.59 227	96.03 145	96.88 171	93.48 103	97.63 334	90.20 206	98.07 264	98.41 162

viewmsd2359difaftdt		93.36 195	93.99 174	91.48 297	95.50 317	78.39 360	90.47 328	96.69 242	88.59 227	96.03 145	96.88 171	93.48 103	97.63 334	90.20 206	98.07 264	98.41 162

test_yl		90.11 307	89.73 313	91.26 312	94.09 369	79.82 317	90.44 330	92.65 378	90.90 162	93.19 293	93.30 366	73.90 395	98.03 288	82.23 367	96.87 341	95.93 367

DCV-MVSNet		90.11 307	89.73 313	91.26 312	94.09 369	79.82 317	90.44 330	92.65 378	90.90 162	93.19 293	93.30 366	73.90 395	98.03 288	82.23 367	96.87 341	95.93 367

tpm2		81.46 435	80.35 443	84.80 448	89.90 461	65.14 477	90.44 330	85.36 456	65.82 486	82.05 475	92.44 388	57.94 465	96.69 393	70.71 466	88.49 475	92.56 457

test_fmvs1		87.59 370	87.27 365	88.54 393	88.32 476	81.26 286	90.43 333	95.72 290	70.55 469	91.70 346	94.63 317	68.13 421	89.42 483	90.59 184	95.34 387	94.94 407

test_vis3_rt		90.40 293	90.03 305	91.52 296	92.58 401	88.95 109	90.38 334	97.72 143	73.30 448	97.79 37	97.51 104	77.05 374	87.10 488	89.03 244	94.89 404	98.50 151

CostFormer		83.09 422	82.21 424	85.73 438	89.27 470	67.01 465	90.35 335	86.47 442	70.42 470	83.52 464	93.23 369	61.18 459	96.85 387	77.21 419	88.26 476	93.34 446

TAMVS		90.16 304	89.05 321	93.49 195	96.49 224	86.37 177	90.34 336	92.55 382	80.84 388	92.99 302	94.57 322	81.94 330	98.20 260	73.51 447	98.21 250	95.90 370

EPMVS		81.17 439	80.37 442	83.58 459	85.58 489	65.08 478	90.31 337	71.34 497	77.31 421	85.80 443	91.30 409	59.38 463	92.70 464	79.99 393	82.34 487	92.96 452

CMPMVS	68.83 22	87.28 379	85.67 395	92.09 271	88.77 474	85.42 206	90.31 337	94.38 336	70.02 472	88.00 423	93.30 366	73.78 397	94.03 454	75.96 430	96.54 353	96.83 318
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_post1							90.21 339				5.85 503	65.36 439	96.00 416	79.61 400

test_prior2							90.21 339		89.33 207	90.77 365	94.81 307	90.41 202		88.21 268	98.55 203

MVS_111021_LR		93.66 180	93.28 207	94.80 122	96.25 255	90.95 72	90.21 339	95.43 305	87.91 250	93.74 264	94.40 329	92.88 130	96.38 405	90.39 191	98.28 239	97.07 302

WR-MVS		93.49 189	93.72 186	92.80 229	97.57 136	80.03 310	90.14 342	95.68 291	93.70 76	96.62 107	95.39 287	87.21 262	99.04 120	87.50 287	99.64 25	99.33 31

tpmrst		82.85 426	82.93 419	82.64 463	87.65 478	58.99 493	90.14 342	87.90 431	75.54 431	83.93 460	91.63 406	66.79 431	95.36 430	81.21 382	81.54 488	93.57 444

PVSNet_BlendedMVS		90.35 298	89.96 306	91.54 295	94.81 342	78.80 354	90.14 342	96.93 216	79.43 401	88.68 414	95.06 298	86.27 280	98.15 269	80.27 388	98.04 268	97.68 258

viewdifsd2359ckpt07		93.63 181	94.33 162	91.55 293	96.19 260	77.86 371	90.11 345	97.74 140	90.76 168	96.11 141	96.61 197	94.37 85	98.27 251	88.82 251	98.23 245	98.51 150

BH-untuned		90.68 284	90.90 281	90.05 364	95.98 280	79.57 330	90.04 346	94.94 320	87.91 250	94.07 250	93.00 373	87.76 250	97.78 319	79.19 405	95.17 397	92.80 455

新几何2							90.02 347

旧先验2							90.00 348		68.65 477	92.71 314			96.52 397	85.15 327

无先验							89.94 349	95.75 289	70.81 467				98.59 199	81.17 383		94.81 410

xiu_mvs_v1_base_debu		91.47 269	91.52 264	91.33 307	95.69 302	81.56 279	89.92 350	96.05 281	83.22 350	91.26 353	90.74 418	91.55 163	98.82 150	89.29 232	95.91 369	93.62 441

xiu_mvs_v1_base		91.47 269	91.52 264	91.33 307	95.69 302	81.56 279	89.92 350	96.05 281	83.22 350	91.26 353	90.74 418	91.55 163	98.82 150	89.29 232	95.91 369	93.62 441

xiu_mvs_v1_base_debi		91.47 269	91.52 264	91.33 307	95.69 302	81.56 279	89.92 350	96.05 281	83.22 350	91.26 353	90.74 418	91.55 163	98.82 150	89.29 232	95.91 369	93.62 441

mvs_anonymous		90.37 297	91.30 272	87.58 413	92.17 417	68.00 462	89.84 353	94.73 328	83.82 342	93.22 290	97.40 113	87.54 255	97.40 352	87.94 281	95.05 401	97.34 287

test20.03		90.80 279	90.85 284	90.63 345	95.63 308	79.24 341	89.81 354	92.87 372	89.90 193	94.39 239	96.40 212	85.77 284	95.27 434	73.86 446	99.05 118	97.39 284

testing3		83.66 416	82.52 421	87.08 418	95.84 290	65.84 474	89.80 355	77.17 495	88.17 245	90.84 364	88.63 442	30.95 503	98.11 273	84.05 345	97.19 323	97.28 291

WB-MVS		89.44 323	92.15 249	81.32 468	97.73 122	48.22 501	89.73 356	87.98 430	95.24 47	96.05 143	96.99 163	85.18 293	96.95 380	82.45 365	97.97 277	98.78 110

1112_ss		88.42 352	87.41 362	91.45 299	96.69 199	80.99 292	89.72 357	96.72 239	73.37 447	87.00 437	90.69 421	77.38 370	98.20 260	81.38 379	93.72 433	95.15 396

UnsupCasMVSNet_eth		90.33 299	90.34 299	90.28 354	94.64 355	80.24 302	89.69 358	95.88 285	85.77 305	93.94 258	95.69 269	81.99 328	92.98 463	84.21 344	91.30 463	97.62 262

MG-MVS		89.54 320	89.80 310	88.76 388	94.88 338	72.47 442	89.60 359	92.44 384	85.82 304	89.48 396	95.98 250	82.85 316	97.74 326	81.87 370	95.27 394	96.08 360

Patchmatch-test		86.10 395	86.01 392	86.38 433	90.63 451	74.22 426	89.57 360	86.69 440	85.73 307	89.81 390	92.83 377	65.24 441	91.04 471	77.82 414	95.78 374	93.88 434

Anonymous20231206		88.77 344	88.29 342	90.20 359	96.31 246	78.81 353	89.56 361	93.49 362	74.26 442	92.38 327	95.58 275	82.21 323	95.43 429	72.07 456	98.75 176	96.34 342

dmvs_re		84.69 407	83.94 410	86.95 423	92.24 412	82.93 253	89.51 362	87.37 435	84.38 337	85.37 444	85.08 471	72.44 402	86.59 489	68.05 472	91.03 467	91.33 466

DeepPCF-MVS	90.46 6	94.20 160	93.56 197	96.14 56	95.96 281	92.96 46	89.48 363	97.46 172	85.14 322	96.23 132	95.42 282	93.19 115	98.08 278	90.37 195	98.76 172	97.38 286

test_cas_vis1_n_1920		88.25 356	88.27 344	88.20 402	92.19 416	78.92 348	89.45 364	95.44 303	75.29 436	93.23 289	95.65 271	71.58 410	90.23 477	88.05 277	93.55 437	95.44 390

SCA		87.43 376	87.21 367	88.10 404	92.01 422	71.98 444	89.43 365	88.11 428	82.26 369	88.71 412	92.83 377	78.65 356	97.59 336	79.61 400	93.30 441	94.75 414

testgi		90.38 296	91.34 271	87.50 414	97.49 140	71.54 445	89.43 365	95.16 313	88.38 236	94.54 236	94.68 315	92.88 130	93.09 461	71.60 460	97.85 287	97.88 233

JIA-IIPM		85.08 402	83.04 417	91.19 318	87.56 479	86.14 186	89.40 367	84.44 465	88.98 215	82.20 473	97.95 61	56.82 468	96.15 410	76.55 425	83.45 484	91.30 467

原ACMM2							89.34 368

tpm		84.38 409	84.08 407	85.30 444	90.47 455	63.43 484	89.34 368	85.63 451	77.24 422	87.62 431	95.03 299	61.00 461	97.30 356	79.26 404	91.09 466	95.16 395

MVS_111021_HR		93.63 181	93.42 203	94.26 152	96.65 202	86.96 159	89.30 370	96.23 272	88.36 239	93.57 270	94.60 319	93.45 105	97.77 320	90.23 204	98.38 225	98.03 207

tpm cat1		80.61 444	79.46 447	84.07 456	88.78 473	65.06 479	89.26 371	88.23 425	62.27 491	81.90 477	89.66 433	62.70 456	95.29 433	71.72 458	80.60 489	91.86 464

CDS-MVSNet		89.55 319	88.22 348	93.53 191	95.37 324	86.49 172	89.26 371	93.59 358	79.76 396	91.15 358	92.31 391	77.12 373	98.38 237	77.51 416	97.92 283	95.71 378
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+		91.28 274	90.86 283	92.53 251	95.45 320	82.53 263	89.25 373	96.52 258	85.00 327	89.91 387	88.55 444	92.94 126	98.84 148	84.72 337	95.44 383	96.22 354

BH-RMVSNet		90.47 291	90.44 296	90.56 348	95.21 329	78.65 356	89.15 374	93.94 349	88.21 243	92.74 313	94.22 336	86.38 277	97.88 305	78.67 408	95.39 385	95.14 397

diffmvs_AUTHOR		92.34 244	92.70 228	91.26 312	94.20 365	78.42 357	89.12 375	97.60 155	87.16 271	93.17 295	95.50 277	88.66 231	97.57 338	91.30 165	97.61 303	97.79 247

thres200		85.85 396	85.18 397	87.88 410	94.44 360	72.52 441	89.08 376	86.21 443	88.57 231	91.44 350	88.40 445	64.22 445	98.00 294	68.35 471	95.88 372	93.12 447

USDC		89.02 334	89.08 320	88.84 387	95.07 335	74.50 421	88.97 377	96.39 263	73.21 449	93.27 285	96.28 225	82.16 325	96.39 404	77.55 415	98.80 165	95.62 385

testdata1							88.96 378		88.44 234

pmmvs5		87.87 362	87.14 369	90.07 361	93.26 388	76.97 390	88.89 379	92.18 388	73.71 445	88.36 418	93.89 350	76.86 382	96.73 392	80.32 387	96.81 344	96.51 331

dmvs_testset		78.23 455	78.99 449	75.94 476	91.99 423	55.34 498	88.86 380	78.70 490	82.69 359	81.64 479	79.46 488	75.93 386	85.74 491	48.78 495	82.85 486	86.76 484

patch_mono-2		92.46 239	92.72 227	91.71 286	96.65 202	78.91 349	88.85 381	97.17 198	83.89 341	92.45 323	96.76 182	89.86 218	97.09 372	90.24 203	98.59 200	99.12 53

viewmambaseed2359dif		90.77 281	90.81 286	90.64 344	93.46 383	77.04 385	88.83 382	96.29 267	80.79 389	92.21 336	95.11 294	88.99 226	97.28 357	85.39 324	96.20 364	97.59 265

test222					96.95 176	85.27 209	88.83 382	93.61 357	65.09 487	90.74 366	94.85 305	84.62 299			97.36 316	93.91 432

mamba_0408		93.60 184	93.72 186	93.27 205	96.65 202	82.79 256	88.81 384	97.68 145	90.62 174	95.19 204	96.01 247	91.54 167	99.08 110	88.63 258	98.32 234	97.93 222

SSM_04072		93.25 203	93.72 186	91.84 279	96.65 202	82.79 256	88.81 384	97.68 145	90.62 174	95.19 204	96.01 247	91.54 167	94.81 441	88.63 258	98.32 234	97.93 222

baseline2		83.38 419	81.54 429	88.90 385	91.38 437	72.84 438	88.78 386	81.22 481	78.97 408	79.82 484	87.56 451	61.73 458	97.80 315	74.30 443	90.05 470	96.05 362

diffmvs		91.74 261	91.93 255	91.15 320	93.06 391	78.17 366	88.77 387	97.51 168	86.28 288	92.42 325	93.96 347	88.04 245	97.46 346	90.69 183	96.67 350	97.82 244
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MDTV_nov1_ep13			83.88 412		89.42 469	61.52 487	88.74 388	87.41 434	73.99 443	84.96 451	94.01 345	65.25 440	95.53 423	78.02 410	93.16 444

D2MVS		89.93 313	89.60 315	90.92 332	94.03 372	78.40 358	88.69 389	94.85 321	78.96 409	93.08 298	95.09 296	74.57 391	96.94 381	88.19 270	98.96 136	97.41 279

TR-MVS		87.70 365	87.17 368	89.27 379	94.11 368	79.26 340	88.69 389	91.86 397	81.94 372	90.69 368	89.79 429	82.82 317	97.42 350	72.65 454	91.98 460	91.14 468

PatchMatch-RL		89.18 326	88.02 353	92.64 237	95.90 286	92.87 48	88.67 391	91.06 405	80.34 390	90.03 385	91.67 405	83.34 307	94.42 447	76.35 426	94.84 407	90.64 472

PAPR		87.65 368	86.77 379	90.27 355	92.85 398	77.38 380	88.56 392	96.23 272	76.82 426	84.98 450	89.75 431	86.08 282	97.16 369	72.33 455	93.35 440	96.26 351

testing3-2		83.95 414	84.22 406	83.13 462	96.28 249	54.34 499	88.51 393	83.01 473	92.19 110	89.09 403	90.98 414	45.51 484	97.44 348	74.38 441	98.01 272	97.60 264

MDTV_nov1_ep13_2view						42.48 504	88.45 394		67.22 481	83.56 463		66.80 429		72.86 453		94.06 428

WB-MVSnew		84.20 411	83.89 411	85.16 446	91.62 434	66.15 473	88.44 395	81.00 482	76.23 428	87.98 424	87.77 450	84.98 296	93.35 459	62.85 486	94.10 428	95.98 364

jason		89.17 329	88.32 340	91.70 287	95.73 300	80.07 307	88.10 396	93.22 366	71.98 457	90.09 379	92.79 379	78.53 359	98.56 209	87.43 289	97.06 331	96.46 338
jason: jason.
mvsany_test3		89.11 331	88.21 349	91.83 280	91.30 439	90.25 86	88.09 397	78.76 489	76.37 427	96.43 116	98.39 38	83.79 305	90.43 476	86.57 304	94.20 423	94.80 411

BH-w/o		87.21 381	87.02 373	87.79 412	94.77 345	77.27 383	87.90 398	93.21 368	81.74 376	89.99 386	88.39 446	83.47 306	96.93 383	71.29 461	92.43 456	89.15 476

MS-PatchMatch		88.05 360	87.75 355	88.95 383	93.28 386	77.93 368	87.88 399	92.49 383	75.42 432	92.57 319	93.59 360	80.44 341	94.24 452	81.28 380	92.75 451	94.69 417

UWE-MVS-28		74.73 459	73.18 460	79.35 473	85.42 491	55.55 497	87.63 400	65.92 499	74.39 440	77.33 488	88.19 447	47.63 480	89.48 482	39.01 497	93.14 446	93.03 451

DELS-MVS		92.05 255	92.16 247	91.72 285	94.44 360	80.13 306	87.62 401	97.25 192	87.34 266	92.22 335	93.18 371	89.54 222	98.73 172	89.67 223	98.20 252	96.30 347
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
ADS-MVSNet2		84.01 412	82.20 425	89.41 375	89.04 471	76.37 402	87.57 402	90.98 407	72.71 454	84.46 453	92.45 386	68.08 422	96.48 399	70.58 467	83.97 482	95.38 391

ADS-MVSNet		82.25 428	81.55 428	84.34 453	89.04 471	65.30 475	87.57 402	85.13 461	72.71 454	84.46 453	92.45 386	68.08 422	92.33 465	70.58 467	83.97 482	95.38 391

IterMVS-SCA-FT		91.65 263	91.55 263	91.94 277	93.89 375	79.22 342	87.56 404	93.51 361	91.53 143	95.37 187	96.62 196	78.65 356	98.90 138	91.89 145	94.95 403	97.70 256

IterMVS		90.18 303	90.16 301	90.21 358	93.15 389	75.98 406	87.56 404	92.97 371	86.43 286	94.09 248	96.40 212	78.32 361	97.43 349	87.87 282	94.69 411	97.23 293
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Test_1112_low_res		87.50 375	86.58 381	90.25 356	96.80 190	77.75 375	87.53 406	96.25 270	69.73 474	86.47 439	93.61 359	75.67 387	97.88 305	79.95 394	93.20 443	95.11 400

c3_l		91.32 273	91.42 268	91.00 326	92.29 411	76.79 392	87.52 407	96.42 262	85.76 306	94.72 231	93.89 350	82.73 318	98.16 267	90.93 178	98.55 203	98.04 204

blended_shiyan8		88.43 351	87.44 360	91.40 302	92.37 407	79.45 333	87.43 408	93.92 351	82.51 364	91.24 356	85.42 467	74.35 392	98.23 257	84.43 341	95.28 393	96.52 330

blended_shiyan6		88.42 352	87.43 361	91.40 302	92.37 407	79.43 335	87.41 409	93.91 352	82.51 364	91.17 357	85.44 466	74.34 393	98.24 255	84.38 342	95.32 388	96.53 329

UnsupCasMVSNet_bld		88.50 349	88.03 352	89.90 366	95.52 315	78.88 350	87.39 410	94.02 346	79.32 405	93.06 299	94.02 344	80.72 339	94.27 450	75.16 435	93.08 448	96.54 327

gbinet_0.2-2-1-0.02		88.14 359	86.86 376	91.99 276	90.70 449	80.51 296	87.36 411	93.01 369	83.45 345	90.38 374	82.42 484	72.73 400	98.54 212	85.40 322	96.27 360	96.90 313

lupinMVS		88.34 355	87.31 363	91.45 299	94.74 349	80.06 308	87.23 412	92.27 387	71.10 464	88.83 405	91.15 411	77.02 377	98.53 216	86.67 302	96.75 347	95.76 376

pmmvs4		88.95 339	87.70 357	92.70 234	94.30 363	85.60 202	87.22 413	92.16 390	74.62 438	89.75 393	94.19 337	77.97 364	96.41 403	82.71 357	96.36 357	96.09 359

WTY-MVS		86.93 389	86.50 387	88.24 401	94.96 336	74.64 417	87.19 414	92.07 393	78.29 413	88.32 419	91.59 407	78.06 363	94.27 450	74.88 436	93.15 445	95.80 374

ET-MVSNet_ETH3D		86.15 394	84.27 405	91.79 282	93.04 392	81.28 285	87.17 415	86.14 444	79.57 399	83.65 461	88.66 441	57.10 466	98.18 263	87.74 284	95.40 384	95.90 370

MVS-HIRNet		78.83 454	80.60 439	73.51 478	93.07 390	47.37 502	87.10 416	78.00 492	68.94 476	77.53 487	97.26 133	71.45 411	94.62 443	63.28 484	88.74 474	78.55 493

blend_shiyan4		83.29 420	80.66 438	91.19 318	91.86 426	79.59 326	87.05 417	93.91 352	82.66 360	89.60 395	83.36 478	42.82 497	98.10 276	81.45 377	73.26 494	95.87 372

xiu_mvs_v2_base		89.00 337	89.19 318	88.46 398	94.86 340	74.63 418	86.97 418	95.60 293	80.88 386	87.83 427	88.62 443	91.04 186	98.81 155	82.51 364	94.38 417	91.93 462

DPM-MVS		89.35 324	88.40 337	92.18 267	96.13 267	84.20 224	86.96 419	96.15 278	75.40 433	87.36 434	91.55 408	83.30 309	98.01 292	82.17 369	96.62 351	94.32 424

eth_miper_zixun_eth		90.72 282	90.61 292	91.05 322	92.04 421	76.84 391	86.91 420	96.67 246	85.21 320	94.41 238	93.92 348	79.53 348	98.26 252	89.76 221	97.02 333	98.06 200

dp		79.28 452	78.62 452	81.24 469	85.97 488	56.45 495	86.91 420	85.26 459	72.97 452	81.45 480	89.17 440	56.01 470	95.45 428	73.19 450	76.68 493	91.82 465

sss		87.23 380	86.82 377	88.46 398	93.96 373	77.94 367	86.84 422	92.78 376	77.59 417	87.61 432	91.83 402	78.75 355	91.92 467	77.84 412	94.20 423	95.52 389

miper_ehance_all_eth		90.48 290	90.42 297	90.69 341	91.62 434	76.57 399	86.83 423	96.18 276	83.38 346	94.06 251	92.66 384	82.20 324	98.04 287	89.79 219	97.02 333	97.45 276

CLD-MVS		91.82 258	91.41 269	93.04 213	96.37 236	83.65 232	86.82 424	97.29 189	84.65 333	92.27 334	89.67 432	92.20 149	97.85 311	83.95 348	99.47 44	97.62 262
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
cl____		90.65 286	90.56 294	90.91 334	91.85 427	76.98 389	86.75 425	95.36 308	85.53 313	94.06 251	94.89 303	77.36 372	97.98 297	90.27 201	98.98 129	97.76 251

DIV-MVS_self_test		90.65 286	90.56 294	90.91 334	91.85 427	76.99 388	86.75 425	95.36 308	85.52 315	94.06 251	94.89 303	77.37 371	97.99 296	90.28 200	98.97 134	97.76 251

PS-MVSNAJ		88.86 341	88.99 324	88.48 397	94.88 338	74.71 416	86.69 427	95.60 293	80.88 386	87.83 427	87.37 454	90.77 192	98.82 150	82.52 363	94.37 418	91.93 462

PVSNet_Blended		88.74 345	88.16 351	90.46 351	94.81 342	78.80 354	86.64 428	96.93 216	74.67 437	88.68 414	89.18 439	86.27 280	98.15 269	80.27 388	96.00 367	94.44 421

MSDG		90.82 278	90.67 291	91.26 312	94.16 366	83.08 250	86.63 429	96.19 275	90.60 176	91.94 343	91.89 401	89.16 225	95.75 421	80.96 385	94.51 414	94.95 405

cl22		89.02 334	88.50 335	90.59 347	89.76 462	76.45 400	86.62 430	94.03 344	82.98 357	92.65 315	92.49 385	72.05 408	97.53 340	88.93 245	97.02 333	97.78 249

CL-MVSNet_self_test		90.04 312	89.90 308	90.47 349	95.24 328	77.81 372	86.60 431	92.62 380	85.64 309	93.25 288	93.92 348	83.84 304	96.06 414	79.93 396	98.03 269	97.53 271

IMVS_0404		90.67 285	91.06 278	89.50 372	95.19 330	76.72 393	86.58 432	96.89 221	85.92 298	89.17 400	94.50 324	85.77 284	94.67 442	88.49 264	97.07 327	97.10 298

PCF-MVS	84.52 17	89.12 330	87.71 356	93.34 200	96.06 273	85.84 196	86.58 432	97.31 186	68.46 478	93.61 269	93.89 350	87.51 256	98.52 218	67.85 473	98.11 259	95.66 382
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_f		86.65 392	87.13 370	85.19 445	90.28 458	86.11 187	86.52 434	91.66 400	69.76 473	95.73 167	97.21 141	69.51 418	81.28 495	89.15 241	94.40 415	88.17 481

UWE-MVS		80.29 447	79.10 448	83.87 457	91.97 424	59.56 491	86.50 435	77.43 494	75.40 433	87.79 429	88.10 448	44.08 489	96.90 385	64.23 481	96.36 357	95.14 397

testing91		83.56 418	82.45 422	86.91 424	92.92 396	67.29 463	86.33 436	88.07 429	86.22 290	84.26 456	85.76 463	48.15 479	97.17 367	76.27 427	94.08 429	96.27 350

usedtu_dtu_shiyan1		89.18 326	88.59 332	90.95 330	94.75 346	77.79 373	86.25 437	94.63 333	81.61 378	90.88 361	92.24 393	77.03 375	98.08 278	82.62 359	97.27 318	96.97 309

FE-MVSNET3		89.18 326	88.59 332	90.95 330	94.75 346	77.79 373	86.25 437	94.63 333	81.61 378	90.88 361	92.25 392	77.03 375	98.08 278	82.62 359	97.27 318	96.97 309

testing222		80.54 445	78.53 453	86.58 428	92.54 405	68.60 460	86.24 439	82.72 475	83.78 343	82.68 471	84.24 474	39.25 501	95.94 418	60.25 487	95.09 399	95.20 393

Patchmatch-RL test		88.81 342	88.52 334	89.69 371	95.33 326	79.94 314	86.22 440	92.71 377	78.46 412	95.80 156	94.18 338	66.25 434	95.33 432	89.22 237	98.53 206	93.78 435

ETVMVS		79.85 450	77.94 457	85.59 439	92.97 394	66.20 472	86.13 441	80.99 483	81.41 380	83.52 464	83.89 475	41.81 498	94.98 440	56.47 491	94.25 422	95.61 386

testing99		82.94 424	81.72 426	86.59 427	92.55 403	66.53 469	86.08 442	85.70 449	85.47 317	83.95 459	85.70 464	45.87 483	97.07 375	76.58 424	93.56 436	96.17 358

Syy-MVS		84.81 404	84.93 398	84.42 452	91.71 431	63.36 485	85.89 443	81.49 479	81.03 383	85.13 447	81.64 486	77.44 368	95.00 437	85.94 316	94.12 426	94.91 408

myMVS_eth3d		79.62 451	78.26 454	83.72 458	91.71 431	61.25 489	85.89 443	81.49 479	81.03 383	85.13 447	81.64 486	32.12 502	95.00 437	71.17 465	94.12 426	94.91 408

testing11		81.98 433	80.52 440	86.38 433	92.69 400	67.13 464	85.79 445	84.80 462	82.16 370	81.19 481	85.41 468	45.24 485	96.88 386	74.14 444	93.24 442	95.14 397

FPMVS		84.50 408	83.28 415	88.16 403	96.32 245	94.49 19	85.76 446	85.47 455	83.09 354	85.20 446	94.26 334	63.79 449	86.58 490	63.72 483	91.88 462	83.40 488

IB-MVS	77.21 19	83.11 421	81.05 432	89.29 378	91.15 443	75.85 407	85.66 447	86.00 446	79.70 397	82.02 476	86.61 457	48.26 477	98.39 233	77.84 412	92.22 457	93.63 440
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
wanda-best-256-512		87.53 372	86.39 388	90.97 328	91.29 440	78.39 360	85.63 448	93.75 354	81.91 373	90.09 379	83.30 479	72.25 404	98.18 263	83.96 346	95.32 388	96.33 343

FE-blended-shiyan7		87.53 372	86.39 388	90.97 328	91.29 440	78.39 360	85.63 448	93.75 354	81.91 373	90.09 379	83.30 479	72.25 404	98.18 263	83.96 346	95.32 388	96.33 343

MDA-MVSNet-bldmvs		91.04 276	90.88 282	91.55 293	94.68 353	80.16 303	85.49 450	92.14 391	90.41 182	94.93 221	95.79 259	85.10 294	96.93 383	85.15 327	94.19 425	97.57 267

test_vis1_rt		85.58 398	84.58 401	88.60 392	87.97 477	86.76 164	85.45 451	93.59 358	66.43 482	87.64 430	89.20 438	79.33 349	85.38 492	81.59 374	89.98 471	93.66 439

new-patchmatchnet		88.97 338	90.79 288	83.50 460	94.28 364	55.83 496	85.34 452	93.56 360	86.18 293	95.47 180	95.73 265	83.10 311	96.51 398	85.40 322	98.06 266	98.16 192

miper_enhance_ethall		88.42 352	87.87 354	90.07 361	88.67 475	75.52 411	85.10 453	95.59 297	75.68 429	92.49 320	89.45 435	78.96 351	97.88 305	87.86 283	97.02 333	96.81 319

HyFIR lowres test		87.19 383	85.51 396	92.24 261	97.12 166	80.51 296	85.03 454	96.06 279	66.11 484	91.66 347	92.98 375	70.12 416	99.14 100	75.29 433	95.23 395	97.07 302

pmmvs3		80.83 442	78.96 450	86.45 430	87.23 482	77.48 379	84.87 455	82.31 476	63.83 489	85.03 449	89.50 434	49.66 476	93.10 460	73.12 451	95.10 398	88.78 480

test0.0.03 1		82.48 427	81.47 430	85.48 442	89.70 463	73.57 431	84.73 456	81.64 478	83.07 355	88.13 422	86.61 457	62.86 454	89.10 485	66.24 478	90.29 469	93.77 436

N_pmnet		88.90 340	87.25 366	93.83 173	94.40 362	93.81 38	84.73 456	87.09 437	79.36 404	93.26 286	92.43 389	79.29 350	91.68 468	77.50 417	97.22 322	96.00 363

GA-MVS		87.70 365	86.82 377	90.31 353	93.27 387	77.22 384	84.72 458	92.79 375	85.11 324	89.82 389	90.07 424	66.80 429	97.76 323	84.56 338	94.27 421	95.96 365

myMVS_eth3d28		80.97 440	80.42 441	82.62 464	93.35 385	58.25 494	84.70 459	85.62 453	86.31 287	84.04 458	85.20 470	46.00 482	94.07 453	62.93 485	95.65 377	95.53 388

icg_test_0407_2		91.18 275	91.92 256	88.94 384	95.19 330	76.72 393	84.66 460	96.89 221	85.92 298	93.55 271	94.50 324	91.06 184	92.99 462	88.49 264	97.07 327	97.10 298

ppachtmachnet_test		88.61 348	88.64 331	88.50 396	91.76 429	70.99 449	84.59 461	92.98 370	79.30 406	92.38 327	93.53 362	79.57 347	97.45 347	86.50 309	97.17 324	97.07 302

CHOSEN 1792x2688		87.19 383	85.92 394	91.00 326	97.13 164	79.41 336	84.51 462	95.60 293	64.14 488	90.07 384	94.81 307	78.26 362	97.14 370	73.34 448	95.38 386	96.46 338

thisisatest0515		84.72 406	82.99 418	89.90 366	92.96 395	75.33 413	84.36 463	83.42 469	77.37 419	88.27 420	86.65 456	53.94 472	98.72 173	82.56 362	97.40 315	95.67 381

cascas		87.02 388	86.28 391	89.25 380	91.56 436	76.45 400	84.33 464	96.78 234	71.01 465	86.89 438	85.91 462	81.35 333	96.94 381	83.09 354	95.60 378	94.35 423

new_pmnet		81.22 437	81.01 434	81.86 466	90.92 447	70.15 452	84.03 465	80.25 487	70.83 466	85.97 442	89.78 430	67.93 425	84.65 493	67.44 474	91.90 461	90.78 471

PAPM		81.91 434	80.11 445	87.31 417	93.87 376	72.32 443	84.02 466	93.22 366	69.47 475	76.13 490	89.84 426	72.15 407	97.23 361	53.27 493	89.02 473	92.37 459

UBG		80.28 448	78.94 451	84.31 454	92.86 397	61.77 486	83.87 467	83.31 472	77.33 420	82.78 470	83.72 476	47.60 481	96.06 414	65.47 480	93.48 438	95.11 400

our_test_3		87.55 371	87.59 358	87.44 415	91.76 429	70.48 450	83.83 468	90.55 413	79.79 395	92.06 342	92.17 396	78.63 358	95.63 422	84.77 335	94.73 409	96.22 354

WBMVS		84.00 413	83.48 413	85.56 440	92.71 399	61.52 487	83.82 469	89.38 418	79.56 400	90.74 366	93.20 370	48.21 478	97.28 357	75.63 432	98.10 261	97.88 233

miper_lstm_enhance		89.90 314	89.80 310	90.19 360	91.37 438	77.50 378	83.82 469	95.00 317	84.84 331	93.05 300	94.96 301	76.53 385	95.20 435	89.96 216	98.67 192	97.86 237

test-LLR		83.58 417	83.17 416	84.79 449	89.68 464	66.86 467	83.08 471	84.52 463	83.07 355	82.85 468	84.78 472	62.86 454	93.49 457	82.85 355	94.86 405	94.03 429

TESTMET0.1,1		79.09 453	78.04 455	82.25 465	87.52 480	64.03 482	83.08 471	80.62 485	70.28 471	80.16 483	83.22 482	44.13 488	90.56 474	79.95 394	93.36 439	92.15 460

test-mter		81.21 438	80.01 446	84.79 449	89.68 464	66.86 467	83.08 471	84.52 463	73.85 444	82.85 468	84.78 472	43.66 490	93.49 457	82.85 355	94.86 405	94.03 429

SSC-MVS3.2		89.88 315	91.06 278	86.31 435	95.90 286	63.76 483	82.68 474	92.43 385	91.42 150	92.37 329	94.58 321	86.34 278	96.60 395	84.35 343	99.50 42	98.57 145

test123		9.49 467	12.01 470	1.91 484	2.87 507	1.30 509	82.38 475	1.34 509	1.36 502	2.84 503	6.56 501	2.45 506	0.97 503	2.73 501	5.56 501	3.47 499

PMMVS		83.00 423	81.11 431	88.66 391	83.81 496	86.44 175	82.24 476	85.65 450	61.75 492	82.07 474	85.64 465	79.75 346	91.59 469	75.99 429	93.09 447	87.94 482

KD-MVS_2432*1600		82.17 430	80.75 436	86.42 431	82.04 499	70.09 453	81.75 477	90.80 409	82.56 361	90.37 375	89.30 436	42.90 493	96.11 412	74.47 439	92.55 454	93.06 448

miper_refine_blended		82.17 430	80.75 436	86.42 431	82.04 499	70.09 453	81.75 477	90.80 409	82.56 361	90.37 375	89.30 436	42.90 493	96.11 412	74.47 439	92.55 454	93.06 448

mvsany_test1		83.91 415	82.93 419	86.84 426	86.18 487	85.93 193	81.11 479	75.03 496	70.80 468	88.57 416	94.63 317	83.08 312	87.38 487	80.39 386	86.57 479	87.21 483

YYNet1		88.17 357	88.24 346	87.93 407	92.21 414	73.62 430	80.75 480	88.77 420	82.51 364	94.99 219	95.11 294	82.70 319	93.70 455	83.33 351	93.83 431	96.48 336

MDA-MVSNet_test_wron		88.16 358	88.23 347	87.93 407	92.22 413	73.71 429	80.71 481	88.84 419	82.52 363	94.88 224	95.14 292	82.70 319	93.61 456	83.28 352	93.80 432	96.46 338

0.4-1-1-0.1		77.15 456	73.55 459	87.95 406	85.49 490	75.84 409	80.59 482	82.87 474	73.51 446	73.61 492	68.65 493	42.84 496	97.22 362	75.20 434	79.18 490	90.80 470

testmvs		9.02 468	11.42 471	1.81 485	2.77 508	1.13 510	79.44 483	1.90 508	1.18 503	2.65 504	6.80 500	1.95 507	0.87 504	2.62 502	3.45 502	3.44 500

0.3-1-1-0.015		75.73 458	71.83 464	87.44 415	83.47 497	74.98 414	78.69 484	83.38 471	72.24 456	70.43 495	65.81 494	39.55 500	97.08 373	74.57 437	78.30 492	90.28 474

PVSNet	76.22 20	82.89 425	82.37 423	84.48 451	93.96 373	64.38 481	78.60 485	88.61 421	71.50 461	84.43 455	86.36 460	74.27 394	94.60 444	69.87 469	93.69 434	94.46 420

0.4-1-1-0.2		75.80 457	72.05 463	87.04 419	82.70 498	74.17 427	77.51 486	83.48 468	71.80 458	71.57 494	65.16 495	43.07 491	96.96 379	74.34 442	78.78 491	90.00 475

dongtai		53.72 462	53.79 465	53.51 481	79.69 501	36.70 505	77.18 487	32.53 507	71.69 459	68.63 497	60.79 496	26.65 504	73.11 497	30.67 499	36.29 499	50.73 495

kuosan		43.63 464	44.25 468	41.78 482	66.04 504	34.37 506	75.56 488	32.62 506	53.25 497	50.46 500	51.18 497	25.28 505	49.13 500	13.44 500	30.41 500	41.84 497

PVSNet_0	70.34 21	74.58 460	72.96 461	79.47 472	90.63 451	66.24 471	73.26 489	83.40 470	63.67 490	78.02 486	78.35 490	72.53 401	89.59 480	56.68 490	60.05 497	82.57 491

E-PMN		80.72 443	80.86 435	80.29 471	85.11 492	68.77 459	72.96 490	81.97 477	87.76 257	83.25 467	83.01 483	62.22 457	89.17 484	77.15 420	94.31 420	82.93 489

CHOSEN 280x420		80.04 449	77.97 456	86.23 436	90.13 459	74.53 420	72.87 491	89.59 417	66.38 483	76.29 489	85.32 469	56.96 467	95.36 430	69.49 470	94.72 410	88.79 479

EMVS		80.35 446	80.28 444	80.54 470	84.73 494	69.07 458	72.54 492	80.73 484	87.80 255	81.66 478	81.73 485	62.89 453	89.84 478	75.79 431	94.65 412	82.71 490

PMMVS2		81.31 436	83.44 414	74.92 477	90.52 453	46.49 503	69.19 493	85.23 460	84.30 338	87.95 425	94.71 313	76.95 379	84.36 494	64.07 482	98.09 262	93.89 433

tmp_tt		37.97 465	44.33 467	18.88 483	11.80 506	21.54 507	63.51 494	45.66 505	4.23 500	51.34 499	50.48 498	59.08 464	22.11 502	44.50 496	68.35 496	13.00 498

MVE	59.87 23	73.86 461	72.65 462	77.47 475	87.00 485	74.35 422	61.37 495	60.93 501	67.27 480	69.69 496	86.49 459	81.24 337	72.33 498	56.45 492	83.45 484	85.74 486
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.44 463	48.94 466	54.93 479	39.68 505	12.38 508	28.59 496	90.09 414	6.82 499	41.10 501	78.41 489	54.41 471	70.69 499	50.12 494	51.26 498	81.72 492

mmdepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

monomultidepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

test_blank		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet_test		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

DCPMVS		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

cdsmvs_eth3d_5k		23.35 466	31.13 469	0.00 486	0.00 509	0.00 511	0.00 497	95.58 299	0.00 504	0.00 505	91.15 411	93.43 107	0.00 505	0.00 503	0.00 503	0.00 501

pcd_1.5k_mvsjas		7.56 469	10.09 472	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	90.77 192	0.00 505	0.00 503	0.00 503	0.00 501

sosnet-low-res		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uncertanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

Regformer		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

ab-mvs-re		7.56 469	10.08 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	90.69 421	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

WAC-MVS						61.25 489								74.55 438

MSC_two_6792asdad				95.90 69	96.54 218	89.57 94		96.87 227					99.41 43	94.06 66	99.30 80	98.72 119

PC_three_1452									75.31 435	95.87 154	95.75 264	92.93 127	96.34 409	87.18 293	98.68 190	98.04 204

No_MVS				95.90 69	96.54 218	89.57 94		96.87 227					99.41 43	94.06 66	99.30 80	98.72 119

test_one_0601					98.26 80	87.14 152		98.18 62	94.25 61	96.99 87	97.36 120	95.13 49

eth-test2					0.00 509

eth-test					0.00 509

ZD-MVS					97.23 156	90.32 85		97.54 162	84.40 336	94.78 227	95.79 259	92.76 133	99.39 54	88.72 255	98.40 220

IU-MVS					98.51 58	86.66 169		96.83 231	72.74 453	95.83 155				93.00 110	99.29 83	98.64 136

test_241102_TWO								98.10 78	91.95 116	97.54 49	97.25 134	95.37 36	99.35 67	93.29 98	99.25 91	98.49 153

test_241102_ONE					98.51 58	86.97 157		98.10 78	91.85 123	97.63 44	97.03 159	96.48 13	98.95 134

test_0728_THIRD									93.26 86	97.40 62	97.35 123	94.69 72	99.34 70	93.88 70	99.42 54	98.89 91

GSMVS																94.75 414

test_part2					98.21 84	89.41 99				96.72 100

sam_mvs1												66.64 432				94.75 414

sam_mvs												66.41 433

MTGPA								97.62 151

test_post											6.07 502	65.74 437	95.84 420

patchmatchnet-post											91.71 404	66.22 435	97.59 336

gm-plane-assit					87.08 484	59.33 492			71.22 462		83.58 477		97.20 364	73.95 445

test9_res														88.16 273	98.40 220	97.83 241

agg_prior2														87.06 296	98.36 231	97.98 213

agg_prior					96.20 258	88.89 111		96.88 226		90.21 378			98.78 163

TestCases				96.00 59	98.02 98	92.17 53		98.43 27	90.48 178	95.04 216	96.74 185	92.54 137	97.86 309	85.11 330	98.98 129	97.98 213

test_prior				94.61 133	95.95 282	87.23 149		97.36 182					98.68 184			97.93 222

新几何1				93.17 211	97.16 161	87.29 147		94.43 335	67.95 479	91.29 352	94.94 302	86.97 268	98.23 257	81.06 384	97.75 291	93.98 431

旧先验1					96.20 258	84.17 225		94.82 323			95.57 276	89.57 221			97.89 284	96.32 346

原ACMM1				92.87 225	96.91 180	84.22 223		97.01 210	76.84 425	89.64 394	94.46 328	88.00 246	98.70 180	81.53 376	98.01 272	95.70 380

testdata2													98.03 288	80.24 390

segment_acmp												92.14 150

testdata				91.03 323	96.87 183	82.01 271		94.28 339	71.55 460	92.46 322	95.42 282	85.65 288	97.38 355	82.64 358	97.27 318	93.70 438

test12				94.43 147	95.95 282	86.75 165		96.24 271		89.76 392		89.79 219	98.79 159		97.95 281	97.75 253

plane_prior7					97.71 124	88.68 115

plane_prior6					97.21 159	88.23 129						86.93 269

plane_prior5								97.81 132					98.95 134	89.26 235	98.51 210	98.60 142

plane_prior4											95.59 272

plane_prior3						88.43 126			90.35 183	93.31 281

plane_prior1					97.38 147

n2								0.00 510

nn								0.00 510

door-mid								92.13 392

lessismore_v0				93.87 170	98.05 94	83.77 231		80.32 486		97.13 77	97.91 70	77.49 367	99.11 108	92.62 123	98.08 263	98.74 117

LGP-MVS_train				96.84 41	98.36 75	92.13 55		98.25 45	91.78 130	97.07 80	97.22 139	96.38 16	99.28 84	92.07 138	99.59 29	99.11 54

test11								96.65 247

door								91.26 404

HQP5-MVS						84.89 213

BP-MVS														86.55 306

HQP4-MVS										88.81 407			98.61 194			98.15 194

HQP3-MVS								97.31 186							97.73 292

HQP2-MVS												84.76 297

NP-MVS					96.82 188	87.10 153					93.40 364

ACMMP++_ref															98.82 159

ACMMP++															99.25 91

Test By Simon												90.61 198

ITE_SJBPF				95.95 63	97.34 150	93.36 43		96.55 257	91.93 118	94.82 225	95.39 287	91.99 152	97.08 373	85.53 320	97.96 280	97.41 279

DeepMVS_CX				53.83 480	70.38 503	64.56 480		48.52 504	33.01 498	65.50 498	74.21 492	56.19 469	46.64 501	38.45 498	70.07 495	50.30 496

High-resolution multi-view benchmark